diff options
749 files changed, 9256 insertions, 4153 deletions
diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index c55df2911136..cd9c9f6a7cd9 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -94,14 +94,11 @@ has a requirements for a minimum number of vectors the driver can pass a min_vecs argument set to this limit, and the PCI core will return -ENOSPC if it can't meet the minimum number of vectors. -The flags argument should normally be set to 0, but can be used to pass the -PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support -MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in -case the device does not support legacy interrupt lines. - -By default this function will spread the interrupts around the available -CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY -flag. +The flags argument is used to specify which type of interrupt can be used +by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX). +A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for +any possible kind of interrupt. If the PCI_IRQ_AFFINITY flag is set, +pci_alloc_irq_vectors() will spread the interrupts around the available CPUs. To get the Linux IRQ numbers passed to request_irq() and free_irq() and the vectors, use the following function: @@ -131,7 +128,7 @@ larger than the number supported by the device it will automatically be capped to the supported limit, so there is no need to query the number of vectors supported beforehand: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES) if (nvec < 0) goto out_err; @@ -140,7 +137,7 @@ interrupts it can request a particular number of interrupts by passing that number to pci_alloc_irq_vectors() function as both 'min_vecs' and 'max_vecs' parameters: - ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0); + ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; @@ -148,15 +145,14 @@ The most notorious example of the request type described above is enabling the single MSI mode for a device. It could be done by passing two 1s as 'min_vecs' and 'max_vecs': - ret = pci_alloc_irq_vectors(pdev, 1, 1, 0); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; Some devices might not support using legacy line interrupts, in which case -the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform -can't provide MSI or MSI-X interrupts: +the driver can specify that only MSI or MSI-X is acceptable: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (nvec < 0) goto out_err; diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index 4da60b463995..ccc60324e738 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -53,6 +53,7 @@ stable kernels. | ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | | ARM | Cortex-A57 | #852523 | N/A | | ARM | Cortex-A57 | #834220 | ARM64_ERRATUM_834220 | +| ARM | Cortex-A72 | #853709 | N/A | | ARM | MMU-500 | #841119,#826419 | N/A | | | | | | | Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 | diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index d515d58962b9..2a3904030dea 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -14,6 +14,12 @@ add_random (RW) This file allows to turn off the disk entropy contribution. Default value of this file is '1'(on). +dax (RO) +-------- +This file indicates whether the device supports Direct Access (DAX), +used by CPU-addressable storage to bypass the pagecache. It shows '1' +if true, '0' if not. + discard_granularity (RO) ----------------------- This shows the size of internal allocation of the device in bytes, if @@ -46,6 +52,12 @@ hw_sector_size (RO) ------------------- This is the hardware sector size of the device, in bytes. +io_poll (RW) +------------ +When read, this file shows the total number of block IO polls and how +many returned success. Writing '0' to this file will disable polling +for this device. Writing any non-zero value will enable this feature. + iostats (RW) ------------- This file is used to control (on/off) the iostats accounting of the @@ -151,5 +163,11 @@ device state. This means that it might not be safe to toggle the setting from "write back" to "write through", since that will also eliminate cache flushes issued by the kernel. +write_same_max_bytes (RO) +------------------------- +This is the number of bytes the device can write in a single write-same +command. A value of '0' means write-same is not supported by this +device. + Jens Axboe <jens.axboe@oracle.com>, February 2009 diff --git a/Documentation/conf.py b/Documentation/conf.py index 96b7aa66c89c..106ae9c740b9 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -131,7 +131,7 @@ pygments_style = 'sphinx' todo_include_todos = False primary_domain = 'C' -highlight_language = 'C' +highlight_language = 'guess' # -- Options for HTML output ---------------------------------------------- diff --git a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt index 6f6c2f8e908d..0741dff048dd 100644 --- a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt +++ b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt @@ -8,8 +8,6 @@ Required properties: - interrupts: Interrupt number for McPDM - interrupt-parent: The parent interrupt controller - ti,hwmods: Name of the hwmod associated to the McPDM -- clocks: phandle for the pdmclk provider, likely <&twl6040> -- clock-names: Must be "pdmclk" Example: @@ -21,11 +19,3 @@ mcpdm: mcpdm@40132000 { interrupt-parent = <&gic>; ti,hwmods = "mcpdm"; }; - -In board DTS file the pdmclk needs to be added: - -&mcpdm { - clocks = <&twl6040>; - clock-names = "pdmclk"; - status = "okay"; -}; diff --git a/Documentation/devicetree/bindings/thermal/thermal.txt b/Documentation/devicetree/bindings/thermal/thermal.txt index 41b817f7b670..88b6ea1ad290 100644 --- a/Documentation/devicetree/bindings/thermal/thermal.txt +++ b/Documentation/devicetree/bindings/thermal/thermal.txt @@ -62,7 +62,7 @@ For more examples of cooling devices, refer to the example sections below. Required properties: - #cooling-cells: Used to provide cooling device specific information Type: unsigned while referring to it. Must be at least 2, in order - Size: one cell to specify minimum and maximum cooling state used + Size: one cell to specify minimum and maximum cooling state used in the reference. The first cell is the minimum cooling state requested and the second cell is the maximum cooling state requested in the reference. @@ -119,7 +119,7 @@ Required properties: Optional property: - contribution: The cooling contribution to the thermal zone of the Type: unsigned referred cooling device at the referred trip point. - Size: one cell The contribution is a ratio of the sum + Size: one cell The contribution is a ratio of the sum of all cooling contributions within a thermal zone. Note: Using the THERMAL_NO_LIMIT (-1UL) constant in the cooling-device phandle @@ -145,7 +145,7 @@ Required properties: Size: one cell - thermal-sensors: A list of thermal sensor phandles and sensor specifier - Type: list of used while monitoring the thermal zone. + Type: list of used while monitoring the thermal zone. phandles + sensor specifier @@ -473,7 +473,7 @@ thermal-zones { <&adc>; /* pcb north */ /* hotspot = 100 * bandgap - 120 * adc + 484 */ - coefficients = <100 -120 484>; + coefficients = <100 -120 484>; trips { ... @@ -502,7 +502,7 @@ from the ADC sensor. The binding would be then: thermal-sensors = <&adc>; /* hotspot = 1 * adc + 6000 */ - coefficients = <1 6000>; + coefficients = <1 6000>; (d) - Board thermal diff --git a/Documentation/hwmon/ftsteutates b/Documentation/hwmon/ftsteutates index 2a1bf69c6a26..8c10a916de20 100644 --- a/Documentation/hwmon/ftsteutates +++ b/Documentation/hwmon/ftsteutates @@ -19,5 +19,5 @@ enhancements. It can monitor up to 4 voltages, 16 temperatures and implemented in this driver. Specification of the chip can be found here: -ftp:///pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf -ftp:///pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf +ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf +ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf diff --git a/Documentation/kernel-documentation.rst b/Documentation/kernel-documentation.rst index c4eb5049da39..391decc66a18 100644 --- a/Documentation/kernel-documentation.rst +++ b/Documentation/kernel-documentation.rst @@ -366,8 +366,6 @@ Domain`_ references. Cross-referencing from reStructuredText ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -.. highlight:: none - To cross-reference the functions and types defined in the kernel-doc comments from reStructuredText documents, please use the `Sphinx C Domain`_ references. For example:: @@ -390,8 +388,6 @@ For further details, please refer to the `Sphinx C Domain`_ documentation. Function documentation ---------------------- -.. highlight:: c - The general format of a function and function-like macro kernel-doc comment is:: /** @@ -572,8 +568,6 @@ DocBook XML [DEPRECATED] Converting DocBook to Sphinx ---------------------------- -.. highlight:: none - Over time, we expect all of the documents under ``Documentation/DocBook`` to be converted to Sphinx and reStructuredText. For most DocBook XML documents, a good enough solution is to use the simple ``Documentation/sphinx/tmplcvt`` script, diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 46c030a49186..a4f4d693e2c1 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3032,6 +3032,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted. PAGE_SIZE is used as alignment. PCI-PCI bridge can be specified, if resource windows need to be expanded. + To specify the alignment for several + instances of a device, the PCI vendor, + device, subvendor, and subdevice may be + specified, e.g., 4096@pci:8086:9c22:103c:198f ecrc= Enable/disable PCIe ECRC (transaction layer end-to-end CRC checking). bios: Use BIOS/firmware settings. This is the diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt index 16a924c486bf..70c926ae212d 100644 --- a/Documentation/networking/rxrpc.txt +++ b/Documentation/networking/rxrpc.txt @@ -790,13 +790,12 @@ The kernel interface functions are as follows: Data messages can have their contents extracted with the usual bunch of socket buffer manipulation functions. A data message can be determined to be the last one in a sequence with rxrpc_kernel_is_data_last(). When a - data message has been used up, rxrpc_kernel_data_delivered() should be - called on it.. + data message has been used up, rxrpc_kernel_data_consumed() should be + called on it. - Non-data messages should be handled to rxrpc_kernel_free_skb() to dispose - of. It is possible to get extra refs on all types of message for later - freeing, but this may pin the state of a call until the message is finally - freed. + Messages should be handled to rxrpc_kernel_free_skb() to dispose of. It + is possible to get extra refs on all types of message for later freeing, + but this may pin the state of a call until the message is finally freed. (*) Accept an incoming call. @@ -821,12 +820,14 @@ The kernel interface functions are as follows: Other errors may be returned if the call had been aborted (-ECONNABORTED) or had timed out (-ETIME). - (*) Record the delivery of a data message and free it. + (*) Record the delivery of a data message. - void rxrpc_kernel_data_delivered(struct sk_buff *skb); + void rxrpc_kernel_data_consumed(struct rxrpc_call *call, + struct sk_buff *skb); - This is used to record a data message as having been delivered and to - update the ACK state for the call. The socket buffer will be freed. + This is used to record a data message as having been consumed and to + update the ACK state for the call. The message must still be passed to + rxrpc_kernel_free_skb() for disposal by the caller. (*) Free a message. diff --git a/Documentation/power/basic-pm-debugging.txt b/Documentation/power/basic-pm-debugging.txt index b96098ccfe69..708f87f78a75 100644 --- a/Documentation/power/basic-pm-debugging.txt +++ b/Documentation/power/basic-pm-debugging.txt @@ -164,7 +164,32 @@ load n/2 modules more and try again. Again, if you find the offending module(s), it(they) must be unloaded every time before hibernation, and please report the problem with it(them). -c) Advanced debugging +c) Using the "test_resume" hibernation option + +/sys/power/disk generally tells the kernel what to do after creating a +hibernation image. One of the available options is "test_resume" which +causes the just created image to be used for immediate restoration. Namely, +after doing: + +# echo test_resume > /sys/power/disk +# echo disk > /sys/power/state + +a hibernation image will be created and a resume from it will be triggered +immediately without involving the platform firmware in any way. + +That test can be used to check if failures to resume from hibernation are +related to bad interactions with the platform firmware. That is, if the above +works every time, but resume from actual hibernation does not work or is +unreliable, the platform firmware may be responsible for the failures. + +On architectures and platforms that support using different kernels to restore +hibernation images (that is, the kernel used to read the image from storage and +load it into memory is different from the one included in the image) or support +kernel address space randomization, it also can be used to check if failures +to resume may be related to the differences between the restore and image +kernels. + +d) Advanced debugging In case that hibernation does not work on your system even in the minimal configuration and compiling more drivers as modules is not practical or some diff --git a/Documentation/power/interface.txt b/Documentation/power/interface.txt index f1f0f59a7c47..974916ff6608 100644 --- a/Documentation/power/interface.txt +++ b/Documentation/power/interface.txt @@ -1,75 +1,76 @@ -Power Management Interface - - -The power management subsystem provides a unified sysfs interface to -userspace, regardless of what architecture or platform one is -running. The interface exists in /sys/power/ directory (assuming sysfs -is mounted at /sys). - -/sys/power/state controls system power state. Reading from this file -returns what states are supported, which is hard-coded to 'freeze', -'standby' (Power-On Suspend), 'mem' (Suspend-to-RAM), and 'disk' -(Suspend-to-Disk). - -Writing to this file one of those strings causes the system to -transition into that state. Please see the file -Documentation/power/states.txt for a description of each of those -states. - - -/sys/power/disk controls the operating mode of the suspend-to-disk -mechanism. Suspend-to-disk can be handled in several ways. We have a -few options for putting the system to sleep - using the platform driver -(e.g. ACPI or other suspend_ops), powering off the system or rebooting the -system (for testing). - -Additionally, /sys/power/disk can be used to turn on one of the two testing -modes of the suspend-to-disk mechanism: 'testproc' or 'test'. If the -suspend-to-disk mechanism is in the 'testproc' mode, writing 'disk' to -/sys/power/state will cause the kernel to disable nonboot CPUs and freeze -tasks, wait for 5 seconds, unfreeze tasks and enable nonboot CPUs. If it is -in the 'test' mode, writing 'disk' to /sys/power/state will cause the kernel -to disable nonboot CPUs and freeze tasks, shrink memory, suspend devices, wait -for 5 seconds, resume devices, unfreeze tasks and enable nonboot CPUs. Then, -we are able to look in the log messages and work out, for example, which code -is being slow and which device drivers are misbehaving. - -Reading from this file will display all supported modes and the currently -selected one in brackets, for example - - [shutdown] reboot test testproc - -Writing to this file will accept one of - - 'platform' (only if the platform supports it) - 'shutdown' - 'reboot' - 'testproc' - 'test' - -/sys/power/image_size controls the size of the image created by -the suspend-to-disk mechanism. It can be written a string -representing a non-negative integer that will be used as an upper -limit of the image size, in bytes. The suspend-to-disk mechanism will -do its best to ensure the image size will not exceed that number. However, -if this turns out to be impossible, it will try to suspend anyway using the -smallest image possible. In particular, if "0" is written to this file, the -suspend image will be as small as possible. - -Reading from this file will display the current image size limit, which -is set to 2/5 of available RAM by default. - -/sys/power/pm_trace controls the code which saves the last PM event point in -the RTC across reboots, so that you can debug a machine that just hangs -during suspend (or more commonly, during resume). Namely, the RTC is only -used to save the last PM event point if this file contains '1'. Initially it -contains '0' which may be changed to '1' by writing a string representing a -nonzero integer into it. - -To use this debugging feature you should attempt to suspend the machine, then -reboot it and run - - dmesg -s 1000000 | grep 'hash matches' - -CAUTION: Using it will cause your machine's real-time (CMOS) clock to be -set to a random invalid time after a resume. +Power Management Interface for System Sleep + +Copyright (c) 2016 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com> + +The power management subsystem provides userspace with a unified sysfs interface +for system sleep regardless of the underlying system architecture or platform. +The interface is located in the /sys/power/ directory (assuming that sysfs is +mounted at /sys). + +/sys/power/state is the system sleep state control file. + +Reading from it returns a list of supported sleep states, encoded as: + +'freeze' (Suspend-to-Idle) +'standby' (Power-On Suspend) +'mem' (Suspend-to-RAM) +'disk' (Suspend-to-Disk) + +Suspend-to-Idle is always supported. Suspend-to-Disk is always supported +too as long the kernel has been configured to support hibernation at all +(ie. CONFIG_HIBERNATION is set in the kernel configuration file). Support +for Suspend-to-RAM and Power-On Suspend depends on the capabilities of the +platform. + +If one of the strings listed in /sys/power/state is written to it, the system +will attempt to transition into the corresponding sleep state. Refer to +Documentation/power/states.txt for a description of each of those states. + +/sys/power/disk controls the operating mode of hibernation (Suspend-to-Disk). +Specifically, it tells the kernel what to do after creating a hibernation image. + +Reading from it returns a list of supported options encoded as: + +'platform' (put the system into sleep using a platform-provided method) +'shutdown' (shut the system down) +'reboot' (reboot the system) +'suspend' (trigger a Suspend-to-RAM transition) +'test_resume' (resume-after-hibernation test mode) + +The currently selected option is printed in square brackets. + +The 'platform' option is only available if the platform provides a special +mechanism to put the system to sleep after creating a hibernation image (ACPI +does that, for example). The 'suspend' option is available if Suspend-to-RAM +is supported. Refer to Documentation/power/basic_pm_debugging.txt for the +description of the 'test_resume' option. + +To select an option, write the string representing it to /sys/power/disk. + +/sys/power/image_size controls the size of hibernation images. + +It can be written a string representing a non-negative integer that will be +used as a best-effort upper limit of the image size, in bytes. The hibernation +core will do its best to ensure that the image size will not exceed that number. +However, if that turns out to be impossible to achieve, a hibernation image will +still be created and its size will be as small as possible. In particular, +writing '0' to this file will enforce hibernation images to be as small as +possible. + +Reading from this file returns the current image size limit, which is set to +around 2/5 of available RAM by default. + +/sys/power/pm_trace controls the PM trace mechanism saving the last suspend +or resume event point in the RTC across reboots. + +It helps to debug hard lockups or reboots due to device driver failures that +occur during system suspend or resume (which is more common) more effectively. + +If /sys/power/pm_trace contains '1', the fingerprint of each suspend/resume +event point in turn will be stored in the RTC memory (overwriting the actual +RTC information), so it will survive a system crash if one occurs right after +storing it and it can be used later to identify the driver that caused the crash +to happen (see Documentation/power/s2ram.txt for more information). + +Initially it contains '0' which may be changed to '1' by writing a string +representing a nonzero integer into it. diff --git a/Documentation/sphinx-static/theme_overrides.css b/Documentation/sphinx-static/theme_overrides.css index 3a2ac4bcfd78..e88461c4c1e6 100644 --- a/Documentation/sphinx-static/theme_overrides.css +++ b/Documentation/sphinx-static/theme_overrides.css @@ -42,11 +42,12 @@ caption a.headerlink { opacity: 0; } caption a.headerlink:hover { opacity: 1; } - /* inline literal: drop the borderbox and red color */ + /* inline literal: drop the borderbox, padding and red color */ code, .rst-content tt, .rst-content code { color: inherit; border: none; + padding: unset; background: inherit; font-size: 85%; } diff --git a/MAINTAINERS b/MAINTAINERS index 20bb1d00098c..5689d6ea9149 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -881,6 +881,15 @@ S: Supported F: drivers/gpu/drm/arc/ F: Documentation/devicetree/bindings/display/snps,arcpgu.txt +ARM ARCHITECTED TIMER DRIVER +M: Mark Rutland <mark.rutland@arm.com> +M: Marc Zyngier <marc.zyngier@arm.com> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: arch/arm/include/asm/arch_timer.h +F: arch/arm64/include/asm/arch_timer.h +F: drivers/clocksource/arm_arch_timer.c + ARM HDLCD DRM DRIVER M: Liviu Dudau <liviu.dudau@arm.com> S: Supported @@ -1004,6 +1013,7 @@ N: meson ARM/Annapurna Labs ALPINE ARCHITECTURE M: Tsahee Zidenberg <tsahee@annapurnalabs.com> M: Antoine Tenart <antoine.tenart@free-electrons.com> +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-alpine/ F: arch/arm/boot/dts/alpine* @@ -2564,6 +2574,13 @@ F: arch/arm/mach-bcm/bcm_5301x.c F: arch/arm/boot/dts/bcm5301x*.dtsi F: arch/arm/boot/dts/bcm470* +BROADCOM BCM53573 ARM ARCHITECTURE +M: RafaÅ‚ MiÅ‚ecki <rafal@milecki.pl> +L: linux-arm-kernel@lists.infradead.org +S: Maintained +F: arch/arm/boot/dts/bcm53573* +F: arch/arm/boot/dts/bcm47189* + BROADCOM BCM63XX ARM ARCHITECTURE M: Florian Fainelli <f.fainelli@gmail.com> M: bcm-kernel-feedback-list@broadcom.com @@ -4524,6 +4541,12 @@ L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/sb_edac.c +EDAC-SKYLAKE +M: Tony Luck <tony.luck@intel.com> +L: linux-edac@vger.kernel.org +S: Maintained +F: drivers/edac/skx_edac.c + EDAC-XGENE APPLIED MICRO (APM) X-GENE SOC EDAC M: Loc Ho <lho@apm.com> @@ -7654,7 +7677,7 @@ L: linux-rdma@vger.kernel.org S: Supported W: https://github.com/SoftRoCE/rxe-dev/wiki/rxe-dev:-Home Q: http://patchwork.kernel.org/project/linux-rdma/list/ -F: drivers/infiniband/hw/rxe/ +F: drivers/infiniband/sw/rxe/ F: include/uapi/rdma/rdma_user_rxe.h MEMBARRIER SUPPORT @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 8 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc4 NAME = Psychotic Stoned Sheep # *DOCUMENTATION* @@ -635,13 +635,6 @@ endif # Tell gcc to never replace conditional load with a non-conditional one KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0) -PHONY += gcc-plugins -gcc-plugins: scripts_basic -ifdef CONFIG_GCC_PLUGINS - $(Q)$(MAKE) $(build)=scripts/gcc-plugins -endif - @: - include scripts/Makefile.gcc-plugins ifdef CONFIG_READABLE_ASM diff --git a/arch/Kconfig b/arch/Kconfig index bd8056b5b246..e9c9334507dd 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -461,6 +461,15 @@ config CC_STACKPROTECTOR_STRONG endchoice +config HAVE_ARCH_WITHIN_STACK_FRAMES + bool + help + An architecture should select this if it can walk the kernel stack + frames to determine if an object is part of either the arguments + or local variables (i.e. that it excludes saved return addresses, + and similar) by implementing an inline arch_within_stack_frames(), + which is used by CONFIG_HARDENED_USERCOPY. + config HAVE_CONTEXT_TRACKING bool help diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h index ad7860c5ce15..51597f344a62 100644 --- a/arch/arc/include/asm/entry.h +++ b/arch/arc/include/asm/entry.h @@ -142,7 +142,7 @@ #ifdef CONFIG_ARC_CURR_IN_REG ; Retrieve orig r25 and save it with rest of callee_regs - ld.as r12, [r12, PT_user_r25] + ld r12, [r12, PT_user_r25] PUSH r12 #else PUSH r25 @@ -198,7 +198,7 @@ ; SP is back to start of pt_regs #ifdef CONFIG_ARC_CURR_IN_REG - st.as r12, [sp, PT_user_r25] + st r12, [sp, PT_user_r25] #endif .endm diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h index c1d36458bfb7..4c6eed80cd8b 100644 --- a/arch/arc/include/asm/irqflags-compact.h +++ b/arch/arc/include/asm/irqflags-compact.h @@ -188,10 +188,10 @@ static inline int arch_irqs_disabled(void) .endm .macro IRQ_ENABLE scratch + TRACE_ASM_IRQ_ENABLE lr \scratch, [status32] or \scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK) flag \scratch - TRACE_ASM_IRQ_ENABLE .endm #endif /* __ASSEMBLY__ */ diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h index 0f92d97432a2..89eeb3720051 100644 --- a/arch/arc/include/asm/pgtable.h +++ b/arch/arc/include/asm/pgtable.h @@ -280,7 +280,7 @@ static inline void pmd_set(pmd_t *pmdp, pte_t *ptep) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) #define mk_pte(page, prot) pfn_pte(page_to_pfn(page), prot) -#define pfn_pte(pfn, prot) (__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot))) +#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot)) /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/ #define pte_pfn(pte) (pte_val(pte) >> PAGE_SHIFT) diff --git a/arch/arc/include/uapi/asm/elf.h b/arch/arc/include/uapi/asm/elf.h index 0f99ac8fcbb2..0037a587320d 100644 --- a/arch/arc/include/uapi/asm/elf.h +++ b/arch/arc/include/uapi/asm/elf.h @@ -13,8 +13,15 @@ /* Machine specific ELF Hdr flags */ #define EF_ARC_OSABI_MSK 0x00000f00 -#define EF_ARC_OSABI_ORIG 0x00000000 /* MUST be zero for back-compat */ -#define EF_ARC_OSABI_CURRENT 0x00000300 /* v3 (no legacy syscalls) */ + +#define EF_ARC_OSABI_V3 0x00000300 /* v3 (no legacy syscalls) */ +#define EF_ARC_OSABI_V4 0x00000400 /* v4 (64bit data any reg align) */ + +#if __GNUC__ < 6 +#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V3 +#else +#define EF_ARC_OSABI_CURRENT EF_ARC_OSABI_V4 +#endif typedef unsigned long elf_greg_t; typedef unsigned long elf_fpregset_t; diff --git a/arch/arc/kernel/arcksyms.c b/arch/arc/kernel/arcksyms.c index 4d9e77724bed..000dd041ab42 100644 --- a/arch/arc/kernel/arcksyms.c +++ b/arch/arc/kernel/arcksyms.c @@ -28,6 +28,7 @@ extern void __muldf3(void); extern void __divdf3(void); extern void __floatunsidf(void); extern void __floatunsisf(void); +extern void __udivdi3(void); EXPORT_SYMBOL(__ashldi3); EXPORT_SYMBOL(__ashrdi3); @@ -45,6 +46,7 @@ EXPORT_SYMBOL(__muldf3); EXPORT_SYMBOL(__divdf3); EXPORT_SYMBOL(__floatunsidf); EXPORT_SYMBOL(__floatunsisf); +EXPORT_SYMBOL(__udivdi3); /* ARC optimised assembler routines */ EXPORT_SYMBOL(memset); diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c index b5db9e7fd649..be1972bd2729 100644 --- a/arch/arc/kernel/process.c +++ b/arch/arc/kernel/process.c @@ -199,7 +199,7 @@ int elf_check_arch(const struct elf32_hdr *x) } eflags = x->e_flags; - if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) { + if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) { pr_err("ABI mismatch - you need newer toolchain\n"); force_sigsegv(SIGSEGV, current); return 0; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index a946400a86d0..f52a0d0dc462 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -291,8 +291,10 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len) cpu->dccm.base_addr, TO_KB(cpu->dccm.sz), cpu->iccm.base_addr, TO_KB(cpu->iccm.sz)); - n += scnprintf(buf + n, len - n, - "OS ABI [v3]\t: no-legacy-syscalls\n"); + n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n", + EF_ARC_OSABI_CURRENT >> 8, + EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ? + "no-legacy-syscalls" : "64-bit data any register aligned"); return buf; } diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 5a294b2c3cb3..0b10efe3a6a7 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -921,6 +921,15 @@ void arc_cache_init(void) printk(arc_cache_mumbojumbo(0, str, sizeof(str))); + /* + * Only master CPU needs to execute rest of function: + * - Assume SMP so all cores will have same cache config so + * any geomtry checks will be same for all + * - IOC setup / dma callbacks only need to be setup once + */ + if (cpu) + return; + if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) { struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache; diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index 04f83322c9fd..77ff64a874a1 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -61,6 +61,7 @@ void *kmap(struct page *page) return kmap_high(page); } +EXPORT_SYMBOL(kmap); void *kmap_atomic(struct page *page) { diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 2d601d769a1c..a9c4e48bb7ec 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -35,6 +35,7 @@ config ARM select HARDIRQS_SW_RESEND select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 + select HAVE_ARCH_HARDENED_USERCOPY select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_MMAP_RND_BITS if MMU diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug index 88440f63c31e..d83f7c369e51 100644 --- a/arch/arm/Kconfig.debug +++ b/arch/arm/Kconfig.debug @@ -186,10 +186,11 @@ choice config DEBUG_BRCMSTB_UART bool "Use BRCMSTB UART for low-level debug" depends on ARCH_BRCMSTB - select DEBUG_UART_8250 help Say Y here if you want the debug print routines to direct - their output to the first serial port on these devices. + their output to the first serial port on these devices. The + UART physical and virtual address is automatically provided + based on the chip identification register value. If you have a Broadcom STB chip and would like early print messages to appear over the UART, select this option. @@ -1430,6 +1431,7 @@ config DEBUG_LL_INCLUDE default "debug/zynq.S" if DEBUG_ZYNQ_UART0 || DEBUG_ZYNQ_UART1 default "debug/bcm63xx.S" if DEBUG_BCM63XX_UART default "debug/digicolor.S" if DEBUG_DIGICOLOR_UA0 + default "debug/brcmstb.S" if DEBUG_BRCMSTB_UART default "mach/debug-macro.S" # Compatibility options for PL01x @@ -1520,7 +1522,6 @@ config DEBUG_UART_PHYS default 0xe6e60000 if DEBUG_RCAR_GEN2_SCIF0 default 0xe8008000 if DEBUG_R7S72100_SCIF2 default 0xf0000be0 if ARCH_EBSA110 - default 0xf040ab00 if DEBUG_BRCMSTB_UART default 0xf1012000 if DEBUG_MVEBU_UART0_ALTERNATE default 0xf1012100 if DEBUG_MVEBU_UART1_ALTERNATE default 0xf7fc9000 if DEBUG_BERLIN_UART @@ -1604,7 +1605,6 @@ config DEBUG_UART_VIRT default 0xfb009000 if DEBUG_REALVIEW_STD_PORT default 0xfb00c000 if DEBUG_AT91_SAMA5D4_USART3 default 0xfb10c000 if DEBUG_REALVIEW_PB1176_PORT - default 0xfc40ab00 if DEBUG_BRCMSTB_UART default 0xfc705000 if DEBUG_ZTE_ZX default 0xfcfe8600 if DEBUG_BCM63XX_UART default 0xfd000000 if DEBUG_SPEAR3XX || DEBUG_SPEAR13XX @@ -1677,8 +1677,7 @@ config DEBUG_UART_8250_WORD DEBUG_ALPINE_UART0 || \ DEBUG_DAVINCI_DMx_UART0 || DEBUG_DAVINCI_DA8XX_UART1 || \ DEBUG_DAVINCI_DA8XX_UART2 || \ - DEBUG_BCM_KONA_UART || DEBUG_RK32_UART2 || \ - DEBUG_BRCMSTB_UART + DEBUG_BCM_KONA_UART || DEBUG_RK32_UART2 config DEBUG_UART_8250_PALMCHIP bool "8250 UART is Palmchip BK-310x" @@ -1697,7 +1696,8 @@ config DEBUG_UNCOMPRESS bool depends on ARCH_MULTIPLATFORM || PLAT_SAMSUNG || ARM_SINGLE_ARMV7M default y if DEBUG_LL && !DEBUG_OMAP2PLUS_UART && \ - (!DEBUG_TEGRA_UART || !ZBOOT_ROM) + (!DEBUG_TEGRA_UART || !ZBOOT_ROM) && \ + !DEBUG_BRCMSTB_UART help This option influences the normal decompressor output for multiplatform kernels. Normally, multiplatform kernels disable diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 56ea5c60b318..61f6ccc19cfa 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -260,12 +260,14 @@ machdirs := $(patsubst %,arch/arm/mach-%/,$(machine-y)) platdirs := $(patsubst %,arch/arm/plat-%/,$(sort $(plat-y))) ifneq ($(CONFIG_ARCH_MULTIPLATFORM),y) +ifneq ($(CONFIG_ARM_SINGLE_ARMV7M),y) ifeq ($(KBUILD_SRC),) KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(machdirs) $(platdirs)) else KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(machdirs) $(platdirs)) endif endif +endif export TEXT_OFFSET GZFLAGS MMUEXT diff --git a/arch/arm/boot/dts/arm-realview-pbx-a9.dts b/arch/arm/boot/dts/arm-realview-pbx-a9.dts index db808f92dd79..90d00b407f85 100644 --- a/arch/arm/boot/dts/arm-realview-pbx-a9.dts +++ b/arch/arm/boot/dts/arm-realview-pbx-a9.dts @@ -70,13 +70,12 @@ * associativity as these may be erroneously set * up by boot loader(s). */ - cache-size = <1048576>; // 1MB - cache-sets = <4096>; + cache-size = <131072>; // 128KB + cache-sets = <512>; cache-line-size = <32>; arm,parity-disable; - arm,tag-latency = <1>; - arm,data-latency = <1 1>; - arm,dirty-latency = <1>; + arm,tag-latency = <1 1 1>; + arm,data-latency = <1 1 1>; }; scu: scu@1f000000 { diff --git a/arch/arm/boot/dts/integratorap.dts b/arch/arm/boot/dts/integratorap.dts index cf06e32ee108..4b34b54e09a1 100644 --- a/arch/arm/boot/dts/integratorap.dts +++ b/arch/arm/boot/dts/integratorap.dts @@ -42,7 +42,7 @@ }; syscon { - compatible = "arm,integrator-ap-syscon"; + compatible = "arm,integrator-ap-syscon", "syscon"; reg = <0x11000000 0x100>; interrupt-parent = <&pic>; /* These are the logical module IRQs */ diff --git a/arch/arm/boot/dts/integratorcp.dts b/arch/arm/boot/dts/integratorcp.dts index d43f15b4f79a..79430fbfec3b 100644 --- a/arch/arm/boot/dts/integratorcp.dts +++ b/arch/arm/boot/dts/integratorcp.dts @@ -94,7 +94,7 @@ }; syscon { - compatible = "arm,integrator-cp-syscon"; + compatible = "arm,integrator-cp-syscon", "syscon"; reg = <0xcb000000 0x100>; }; diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi index 00cb314d5e4d..e23f46d15c80 100644 --- a/arch/arm/boot/dts/keystone.dtsi +++ b/arch/arm/boot/dts/keystone.dtsi @@ -70,14 +70,6 @@ cpu_on = <0x84000003>; }; - psci { - compatible = "arm,psci"; - method = "smc"; - cpu_suspend = <0x84000001>; - cpu_off = <0x84000002>; - cpu_on = <0x84000003>; - }; - soc { #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/tegra124-jetson-tk1.dts b/arch/arm/boot/dts/tegra124-jetson-tk1.dts index e52b82449a79..6403e0de540e 100644 --- a/arch/arm/boot/dts/tegra124-jetson-tk1.dts +++ b/arch/arm/boot/dts/tegra124-jetson-tk1.dts @@ -1382,7 +1382,7 @@ * Pin 41: BR_UART1_TXD * Pin 44: BR_UART1_RXD */ - serial@70006000 { + serial@0,70006000 { compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart"; status = "okay"; }; @@ -1394,7 +1394,7 @@ * Pin 71: UART2_CTS_L * Pin 74: UART2_RTS_L */ - serial@70006040 { + serial@0,70006040 { compatible = "nvidia,tegra124-hsuart", "nvidia,tegra30-hsuart"; status = "okay"; }; diff --git a/arch/arm/configs/aspeed_g4_defconfig b/arch/arm/configs/aspeed_g4_defconfig index b6e54ee9bdbd..ca39c04fec6b 100644 --- a/arch/arm/configs/aspeed_g4_defconfig +++ b/arch/arm/configs/aspeed_g4_defconfig @@ -58,7 +58,7 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_FIRMWARE_MEMMAP=y CONFIG_FANOTIFY=y -CONFIG_PRINTK_TIME=1 +CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_STRIP_ASM_SYMS=y CONFIG_PAGE_POISONING=y diff --git a/arch/arm/configs/aspeed_g5_defconfig b/arch/arm/configs/aspeed_g5_defconfig index 892605167357..4f366b0370e9 100644 --- a/arch/arm/configs/aspeed_g5_defconfig +++ b/arch/arm/configs/aspeed_g5_defconfig @@ -59,7 +59,7 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_FIRMWARE_MEMMAP=y CONFIG_FANOTIFY=y -CONFIG_PRINTK_TIME=1 +CONFIG_PRINTK_TIME=y CONFIG_DYNAMIC_DEBUG=y CONFIG_STRIP_ASM_SYMS=y CONFIG_PAGE_POISONING=y diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 62a6f65029e6..a93c0f99acf7 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -480,7 +480,10 @@ arm_copy_from_user(void *to, const void __user *from, unsigned long n); static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n) { - unsigned int __ua_flags = uaccess_save_and_enable(); + unsigned int __ua_flags; + + check_object_size(to, n, false); + __ua_flags = uaccess_save_and_enable(); n = arm_copy_from_user(to, from, n); uaccess_restore(__ua_flags); return n; @@ -495,11 +498,15 @@ static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) { #ifndef CONFIG_UACCESS_WITH_MEMCPY - unsigned int __ua_flags = uaccess_save_and_enable(); + unsigned int __ua_flags; + + check_object_size(from, n, true); + __ua_flags = uaccess_save_and_enable(); n = arm_copy_to_user(to, from, n); uaccess_restore(__ua_flags); return n; #else + check_object_size(from, n, true); return arm_copy_to_user(to, from, n); #endif } diff --git a/arch/arm/include/debug/brcmstb.S b/arch/arm/include/debug/brcmstb.S new file mode 100644 index 000000000000..9113d7b33ae0 --- /dev/null +++ b/arch/arm/include/debug/brcmstb.S @@ -0,0 +1,145 @@ +/* + * Copyright (C) 2016 Broadcom + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation version 2. + * + * This program is distributed "as is" WITHOUT ANY WARRANTY of any + * kind, whether express or implied; without even the implied warranty + * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ +#include <linux/serial_reg.h> + +/* Physical register offset and virtual register offset */ +#define REG_PHYS_BASE 0xf0000000 +#define REG_VIRT_BASE 0xfc000000 +#define REG_PHYS_ADDR(x) ((x) + REG_PHYS_BASE) + +/* Product id can be read from here */ +#define SUN_TOP_CTRL_BASE REG_PHYS_ADDR(0x404000) + +#define UARTA_3390 REG_PHYS_ADDR(0x40a900) +#define UARTA_7250 REG_PHYS_ADDR(0x40b400) +#define UARTA_7268 REG_PHYS_ADDR(0x40c000) +#define UARTA_7271 UARTA_7268 +#define UARTA_7364 REG_PHYS_ADDR(0x40b000) +#define UARTA_7366 UARTA_7364 +#define UARTA_74371 REG_PHYS_ADDR(0x406b00) +#define UARTA_7439 REG_PHYS_ADDR(0x40a900) +#define UARTA_7445 REG_PHYS_ADDR(0x40ab00) + +#define UART_SHIFT 2 + +#define checkuart(rp, rv, family_id, family) \ + /* Load family id */ \ + ldr rp, =family_id ; \ + /* Compare SUN_TOP_CTRL value against it */ \ + cmp rp, rv ; \ + /* Passed test, load address */ \ + ldreq rp, =UARTA_##family ; \ + /* Jump to save UART address */ \ + beq 91f + + .macro addruart, rp, rv, tmp + adr \rp, 99f @ actual addr of 99f + ldr \rv, [\rp] @ linked addr is stored there + sub \rv, \rv, \rp @ offset between the two + ldr \rp, [\rp, #4] @ linked brcmstb_uart_config + sub \tmp, \rp, \rv @ actual brcmstb_uart_config + ldr \rp, [\tmp] @ Load brcmstb_uart_config + cmp \rp, #1 @ needs initialization? + bne 100f @ no; go load the addresses + mov \rv, #0 @ yes; record init is done + str \rv, [\tmp] + + /* Check SUN_TOP_CTRL base */ + ldr \rp, =SUN_TOP_CTRL_BASE @ load SUN_TOP_CTRL PA + ldr \rv, [\rp, #0] @ get register contents + and \rv, \rv, #0xffffff00 @ strip revision bits [7:0] + + /* Chip specific detection starts here */ +20: checkuart(\rp, \rv, 0x33900000, 3390) +21: checkuart(\rp, \rv, 0x72500000, 7250) +22: checkuart(\rp, \rv, 0x72680000, 7268) +23: checkuart(\rp, \rv, 0x72710000, 7271) +24: checkuart(\rp, \rv, 0x73640000, 7364) +25: checkuart(\rp, \rv, 0x73660000, 7366) +26: checkuart(\rp, \rv, 0x07437100, 74371) +27: checkuart(\rp, \rv, 0x74390000, 7439) +28: checkuart(\rp, \rv, 0x74450000, 7445) + + /* No valid UART found */ +90: mov \rp, #0 + /* fall through */ + + /* Record whichever UART we chose */ +91: str \rp, [\tmp, #4] @ Store in brcmstb_uart_phys + cmp \rp, #0 @ Valid UART address? + bne 92f @ Yes, go process it + str \rp, [\tmp, #8] @ Store 0 in brcmstb_uart_virt + b 100f @ Done +92: and \rv, \rp, #0xffffff @ offset within 16MB section + add \rv, \rv, #REG_VIRT_BASE + str \rv, [\tmp, #8] @ Store in brcmstb_uart_virt + b 100f + + .align +99: .word . + .word brcmstb_uart_config + .ltorg + + /* Load previously selected UART address */ +100: ldr \rp, [\tmp, #4] @ Load brcmstb_uart_phys + ldr \rv, [\tmp, #8] @ Load brcmstb_uart_virt + .endm + + .macro store, rd, rx:vararg + str \rd, \rx + .endm + + .macro load, rd, rx:vararg + ldr \rd, \rx + .endm + + .macro senduart,rd,rx + store \rd, [\rx, #UART_TX << UART_SHIFT] + .endm + + .macro busyuart,rd,rx +1002: load \rd, [\rx, #UART_LSR << UART_SHIFT] + and \rd, \rd, #UART_LSR_TEMT | UART_LSR_THRE + teq \rd, #UART_LSR_TEMT | UART_LSR_THRE + bne 1002b + .endm + + .macro waituart,rd,rx + .endm + +/* + * Storage for the state maintained by the macros above. + * + * In the kernel proper, this data is located in arch/arm/mach-bcm/brcmstb.c. + * That's because this header is included from multiple files, and we only + * want a single copy of the data. In particular, the UART probing code above + * assumes it's running using physical addresses. This is true when this file + * is included from head.o, but not when included from debug.o. So we need + * to share the probe results between the two copies, rather than having + * to re-run the probing again later. + * + * In the decompressor, we put the symbol/storage right here, since common.c + * isn't included in the decompressor build. This symbol gets put in .text + * even though it's really data, since .data is discarded from the + * decompressor. Luckily, .text is writeable in the decompressor, unless + * CONFIG_ZBOOT_ROM. That dependency is handled in arch/arm/Kconfig.debug. + */ +#if defined(ZIMAGE) +brcmstb_uart_config: + /* Debug UART initialization required */ + .word 1 + /* Debug UART physical address */ + .word 0 + /* Debug UART virtual address */ + .word 0 +#endif diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index bc5f50799d75..9f157e7c51e7 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -295,6 +295,7 @@ __und_svc_fault: bl __und_fault __und_svc_finish: + get_thread_info tsk ldr r5, [sp, #S_PSR] @ Get SVC cpsr svc_exit r5 @ return from exception UNWIND(.fnend ) diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c index 087acb569b63..5f221acd21ae 100644 --- a/arch/arm/kernel/sys_oabi-compat.c +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd, mm_segment_t fs; long ret, err, i; - if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event))) + if (maxevents <= 0 || + maxevents > (INT_MAX/sizeof(*kbuf)) || + maxevents > (INT_MAX/sizeof(*events))) return -EINVAL; + if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents)) + return -EFAULT; kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL); if (!kbuf) return -ENOMEM; @@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid, if (nsops < 1 || nsops > SEMOPM) return -EINVAL; + if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops)) + return -EFAULT; sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL); if (!sops) return -ENOMEM; diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index d94bb9093ead..75f130ef6504 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -1009,9 +1009,13 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_CREATE_IRQCHIP: { + int ret; if (!vgic_present) return -ENXIO; - return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_lock(&kvm->lock); + ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); + mutex_unlock(&kvm->lock); + return ret; } case KVM_ARM_SET_DEVICE_ADDR: { struct kvm_arm_device_addr dev_addr; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index bda27b6b1aa2..29d0b23af2a9 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -1309,7 +1309,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, smp_rmb(); pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable); - if (is_error_pfn(pfn)) + if (is_error_noslot_pfn(pfn)) return -EFAULT; if (kvm_is_device_pfn(pfn)) { diff --git a/arch/arm/mach-bcm/Kconfig b/arch/arm/mach-bcm/Kconfig index 34f0fca0b847..6a6302d1b40f 100644 --- a/arch/arm/mach-bcm/Kconfig +++ b/arch/arm/mach-bcm/Kconfig @@ -159,6 +159,20 @@ config ARCH_BCM2835 This enables support for the Broadcom BCM2835 and BCM2836 SoCs. This SoC is used in the Raspberry Pi and Roku 2 devices. +config ARCH_BCM_53573 + bool "Broadcom BCM53573 SoC series support" + depends on ARCH_MULTI_V7 + select ARCH_BCM_IPROC + select HAVE_ARM_ARCH_TIMER + help + BCM53573 series is set of SoCs using ARM Cortex-A7 CPUs with wireless + embedded in the chipset. + This SoC line is mostly used in home routers and is some cheaper + alternative for Northstar family. + + The base chip is BCM53573 and there are some packaging modifications + like BCM47189 and BCM47452. + config ARCH_BCM_63XX bool "Broadcom BCM63xx DSL SoC" depends on ARCH_MULTI_V7 diff --git a/arch/arm/mach-bcm/brcmstb.c b/arch/arm/mach-bcm/brcmstb.c index 99a67cfb7c0d..07e3a86c6466 100644 --- a/arch/arm/mach-bcm/brcmstb.c +++ b/arch/arm/mach-bcm/brcmstb.c @@ -19,6 +19,22 @@ #include <asm/mach-types.h> #include <asm/mach/arch.h> +/* + * Storage for debug-macro.S's state. + * + * This must be in .data not .bss so that it gets initialized each time the + * kernel is loaded. The data is declared here rather than debug-macro.S so + * that multiple inclusions of debug-macro.S point at the same data. + */ +u32 brcmstb_uart_config[3] = { + /* Debug UART initialization required */ + 1, + /* Debug UART physical address */ + 0, + /* Debug UART virtual address */ + 0, +}; + static void __init brcmstb_init_irq(void) { irqchip_init(); diff --git a/arch/arm/mach-clps711x/Kconfig b/arch/arm/mach-clps711x/Kconfig index dc7c6edeab39..61284b9389cf 100644 --- a/arch/arm/mach-clps711x/Kconfig +++ b/arch/arm/mach-clps711x/Kconfig @@ -1,13 +1,13 @@ menuconfig ARCH_CLPS711X bool "Cirrus Logic EP721x/EP731x-based" depends on ARCH_MULTI_V4T - select ARCH_REQUIRE_GPIOLIB select AUTO_ZRELADDR select CLKSRC_OF select CLPS711X_TIMER select COMMON_CLK select CPU_ARM720T select GENERIC_CLOCKEVENTS + select GPIOLIB select MFD_SYSCON select OF_IRQ select USE_OF diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c index 0d046accb35b..ed3d0e9f72ac 100644 --- a/arch/arm/mach-davinci/da850.c +++ b/arch/arm/mach-davinci/da850.c @@ -501,6 +501,7 @@ static struct clk_lookup da850_clks[] = { CLK("da8xx_lcdc.0", "fck", &lcdc_clk), CLK("da830-mmc.0", NULL, &mmcsd0_clk), CLK("da830-mmc.1", NULL, &mmcsd1_clk), + CLK("ti-aemif", NULL, &aemif_clk), CLK(NULL, "aemif", &aemif_clk), CLK(NULL, "usb11", &usb11_clk), CLK(NULL, "usb20", &usb20_clk), diff --git a/arch/arm/mach-davinci/da8xx-dt.c b/arch/arm/mach-davinci/da8xx-dt.c index 754f478110b4..35c0d65fe7f1 100644 --- a/arch/arm/mach-davinci/da8xx-dt.c +++ b/arch/arm/mach-davinci/da8xx-dt.c @@ -37,6 +37,7 @@ static struct of_dev_auxdata da850_auxdata_lookup[] __initdata = { OF_DEV_AUXDATA("ti,davinci-dm6467-emac", 0x01e20000, "davinci_emac.1", NULL), OF_DEV_AUXDATA("ti,da830-mcasp-audio", 0x01d00000, "davinci-mcasp.0", NULL), + OF_DEV_AUXDATA("ti,da850-aemif", 0x68000000, "ti-aemif", NULL), {} }; diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index 8f820de890b4..b085855c1d0b 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -12,6 +12,7 @@ menuconfig ARCH_EXYNOS depends on ARCH_MULTI_V7 select ARCH_HAS_BANDGAP select ARCH_HAS_HOLES_MEMORYMODEL + select ARCH_SUPPORTS_BIG_ENDIAN select ARM_AMBA select ARM_GIC select COMMON_CLK_SAMSUNG diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c index acabf0bffc5d..757fc11de30d 100644 --- a/arch/arm/mach-exynos/exynos.c +++ b/arch/arm/mach-exynos/exynos.c @@ -30,25 +30,10 @@ static struct map_desc exynos4_iodesc[] __initdata = { { - .virtual = (unsigned long)S5P_VA_CMU, - .pfn = __phys_to_pfn(EXYNOS4_PA_CMU), - .length = SZ_128K, - .type = MT_DEVICE, - }, { .virtual = (unsigned long)S5P_VA_COREPERI_BASE, .pfn = __phys_to_pfn(EXYNOS4_PA_COREPERI), .length = SZ_8K, .type = MT_DEVICE, - }, { - .virtual = (unsigned long)S5P_VA_DMC0, - .pfn = __phys_to_pfn(EXYNOS4_PA_DMC0), - .length = SZ_64K, - .type = MT_DEVICE, - }, { - .virtual = (unsigned long)S5P_VA_DMC1, - .pfn = __phys_to_pfn(EXYNOS4_PA_DMC1), - .length = SZ_64K, - .type = MT_DEVICE, }, }; diff --git a/arch/arm/mach-exynos/include/mach/map.h b/arch/arm/mach-exynos/include/mach/map.h index c48ba4fbdfd2..5fb0040cc6d3 100644 --- a/arch/arm/mach-exynos/include/mach/map.h +++ b/arch/arm/mach-exynos/include/mach/map.h @@ -18,11 +18,6 @@ #define EXYNOS_PA_CHIPID 0x10000000 -#define EXYNOS4_PA_CMU 0x10030000 - -#define EXYNOS4_PA_DMC0 0x10400000 -#define EXYNOS4_PA_DMC1 0x10410000 - #define EXYNOS4_PA_COREPERI 0x10500000 #endif /* __ASM_ARCH_MAP_H */ diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c index fd8720532471..0df062d8b2c9 100644 --- a/arch/arm/mach-imx/gpc.c +++ b/arch/arm/mach-imx/gpc.c @@ -271,6 +271,12 @@ static int __init imx_gpc_init(struct device_node *node, for (i = 0; i < IMR_NUM; i++) writel_relaxed(~0, gpc_base + GPC_IMR1 + i * 4); + /* + * Clear the OF_POPULATED flag set in of_irq_init so that + * later the GPC power domain driver will not be skipped. + */ + of_node_clear_flag(node, OF_POPULATED); + return 0; } IRQCHIP_DECLARE(imx_gpc, "fsl,imx6q-gpc", imx_gpc_init); diff --git a/arch/arm/mach-mvebu/Makefile b/arch/arm/mach-mvebu/Makefile index e53c6cfcab51..6c6497e80a7b 100644 --- a/arch/arm/mach-mvebu/Makefile +++ b/arch/arm/mach-mvebu/Makefile @@ -1,5 +1,4 @@ -ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \ - -I$(srctree)/arch/arm/plat-orion/include +ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-orion/include AFLAGS_coherency_ll.o := -Wa,-march=armv7-a CFLAGS_pmsu.o := -march=armv7-a diff --git a/arch/arm/mach-oxnas/Kconfig b/arch/arm/mach-oxnas/Kconfig index 567496bd250a..29100beb2e7f 100644 --- a/arch/arm/mach-oxnas/Kconfig +++ b/arch/arm/mach-oxnas/Kconfig @@ -11,11 +11,13 @@ if ARCH_OXNAS config MACH_OX810SE bool "Support OX810SE Based Products" + select ARCH_HAS_RESET_CONTROLLER select COMMON_CLK_OXNAS select CPU_ARM926T select MFD_SYSCON select OXNAS_RPS_TIMER select PINCTRL_OXNAS + select RESET_CONTROLLER select RESET_OXNAS select VERSATILE_FPGA_IRQ help diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c index dc109dc3a622..10bfdb169366 100644 --- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -13,6 +13,7 @@ */ #include <linux/kernel.h> +#include <linux/module.h> /* symbol_get ; symbol_put */ #include <linux/init.h> #include <linux/platform_device.h> #include <linux/major.h> diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 1080580b1343..2c150bfc0cd5 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -13,6 +13,7 @@ */ #include <linux/kernel.h> +#include <linux/module.h> /* symbol_get ; symbol_put */ #include <linux/platform_device.h> #include <linux/delay.h> #include <linux/gpio_keys.h> diff --git a/arch/arm/mach-qcom/Makefile b/arch/arm/mach-qcom/Makefile index e324375fa919..12878e9a2c0c 100644 --- a/arch/arm/mach-qcom/Makefile +++ b/arch/arm/mach-qcom/Makefile @@ -1,2 +1 @@ -obj-y := board.o obj-$(CONFIG_SMP) += platsmp.o diff --git a/arch/arm/mach-qcom/board.c b/arch/arm/mach-qcom/board.c deleted file mode 100644 index d8060dfd1a21..000000000000 --- a/arch/arm/mach-qcom/board.c +++ /dev/null @@ -1,31 +0,0 @@ -/* Copyright (c) 2010-2014 The Linux Foundation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 and - * only version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - */ - -#include <linux/init.h> - -#include <asm/mach/arch.h> - -static const char * const qcom_dt_match[] __initconst = { - "qcom,apq8064", - "qcom,apq8074-dragonboard", - "qcom,apq8084", - "qcom,ipq8062", - "qcom,ipq8064", - "qcom,msm8660-surf", - "qcom,msm8960-cdp", - "qcom,mdm9615", - NULL -}; - -DT_MACHINE_START(QCOM_DT, "Qualcomm (Flattened Device Tree)") - .dt_compat = qcom_dt_match, -MACHINE_END diff --git a/arch/arm/mach-realview/Makefile b/arch/arm/mach-realview/Makefile index dae8d86ef4cc..404882130956 100644 --- a/arch/arm/mach-realview/Makefile +++ b/arch/arm/mach-realview/Makefile @@ -1,8 +1,7 @@ # # Makefile for the linux kernel. # -ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/$(src)/include \ - -I$(srctree)/arch/arm/plat-versatile/include +ccflags-$(CONFIG_ARCH_MULTIPLATFORM) := -I$(srctree)/arch/arm/plat-versatile/include obj-y := core.o obj-$(CONFIG_REALVIEW_DT) += realview-dt.o diff --git a/arch/arm/mach-s3c24xx/common.c b/arch/arm/mach-s3c24xx/common.c index bf50328107bd..fe7485dc7fb5 100644 --- a/arch/arm/mach-s3c24xx/common.c +++ b/arch/arm/mach-s3c24xx/common.c @@ -21,7 +21,7 @@ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ - +#include <linux/dma-mapping.h> #include <linux/init.h> #include <linux/module.h> #include <linux/interrupt.h> @@ -304,6 +304,8 @@ struct s3c24xx_uart_resources s3c2410_uart_resources[] __initdata = { }, }; +#define s3c24xx_device_dma_mask (*((u64[]) { DMA_BIT_MASK(32) })) + #if defined(CONFIG_CPU_S3C2410) || defined(CONFIG_CPU_S3C2412) || \ defined(CONFIG_CPU_S3C2440) || defined(CONFIG_CPU_S3C2442) static struct resource s3c2410_dma_resource[] = { @@ -354,7 +356,9 @@ struct platform_device s3c2410_device_dma = { .num_resources = ARRAY_SIZE(s3c2410_dma_resource), .resource = s3c2410_dma_resource, .dev = { - .platform_data = &s3c2410_dma_platdata, + .dma_mask = &s3c24xx_device_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + .platform_data = &s3c2410_dma_platdata, }, }; #endif @@ -395,7 +399,9 @@ struct platform_device s3c2412_device_dma = { .num_resources = ARRAY_SIZE(s3c2410_dma_resource), .resource = s3c2410_dma_resource, .dev = { - .platform_data = &s3c2412_dma_platdata, + .dma_mask = &s3c24xx_device_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + .platform_data = &s3c2412_dma_platdata, }, }; #endif @@ -451,7 +457,9 @@ struct platform_device s3c2440_device_dma = { .num_resources = ARRAY_SIZE(s3c2410_dma_resource), .resource = s3c2410_dma_resource, .dev = { - .platform_data = &s3c2440_dma_platdata, + .dma_mask = &s3c24xx_device_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + .platform_data = &s3c2440_dma_platdata, }, }; #endif @@ -503,7 +511,9 @@ struct platform_device s3c2443_device_dma = { .num_resources = ARRAY_SIZE(s3c2443_dma_resource), .resource = s3c2443_dma_resource, .dev = { - .platform_data = &s3c2443_dma_platdata, + .dma_mask = &s3c24xx_device_dma_mask, + .coherent_dma_mask = DMA_BIT_MASK(32), + .platform_data = &s3c2443_dma_platdata, }, }; #endif diff --git a/arch/arm/mach-s3c24xx/mach-mini2440.c b/arch/arm/mach-s3c24xx/mach-mini2440.c index a8521684a7f5..bbf41322d726 100644 --- a/arch/arm/mach-s3c24xx/mach-mini2440.c +++ b/arch/arm/mach-s3c24xx/mach-mini2440.c @@ -516,6 +516,7 @@ static struct platform_device *mini2440_devices[] __initdata = { &mini2440_button_device, &s3c_device_nand, &s3c_device_sdi, + &s3c2440_device_dma, &s3c_device_iis, &uda1340_codec, &mini2440_audio, diff --git a/arch/arm/mach-s3c64xx/mach-crag6410-module.c b/arch/arm/mach-s3c64xx/mach-crag6410-module.c index 571f95cc5a53..ccc3ab8d58e7 100644 --- a/arch/arm/mach-s3c64xx/mach-crag6410-module.c +++ b/arch/arm/mach-s3c64xx/mach-crag6410-module.c @@ -393,8 +393,7 @@ static const struct i2c_device_id wlf_gf_module_id[] = { static struct i2c_driver wlf_gf_module_driver = { .driver = { - .name = "wlf-gf-module", - .owner = THIS_MODULE, + .name = "wlf-gf-module" }, .probe = wlf_gf_module_probe, .id_table = wlf_gf_module_id, diff --git a/arch/arm/mach-s5pv210/Makefile b/arch/arm/mach-s5pv210/Makefile index 72b9e9671507..fa7fb716e388 100644 --- a/arch/arm/mach-s5pv210/Makefile +++ b/arch/arm/mach-s5pv210/Makefile @@ -5,7 +5,7 @@ # # Licensed under GPLv2 -ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/$(src)/include -I$(srctree)/arch/arm/plat-samsung/include +ccflags-$(CONFIG_ARCH_MULTIPLATFORM) += -I$(srctree)/arch/arm/plat-samsung/include # Core diff --git a/arch/arm/mach-shmobile/platsmp.c b/arch/arm/mach-shmobile/platsmp.c index f3dba6f356e2..02e21bceb085 100644 --- a/arch/arm/mach-shmobile/platsmp.c +++ b/arch/arm/mach-shmobile/platsmp.c @@ -40,5 +40,8 @@ bool shmobile_smp_cpu_can_disable(unsigned int cpu) bool __init shmobile_smp_init_fallback_ops(void) { /* fallback on PSCI/smp_ops if no other DT based method is detected */ + if (!IS_ENABLED(CONFIG_SMP)) + return false; + return platform_can_secondary_boot() ? true : false; } diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 62f4d01941f7..6344913f0804 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -728,7 +728,8 @@ static void *__init late_alloc(unsigned long sz) { void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz)); - BUG_ON(!ptr); + if (!ptr || !pgtable_page_ctor(virt_to_page(ptr))) + BUG(); return ptr; } @@ -1155,10 +1156,19 @@ void __init sanity_check_meminfo(void) { phys_addr_t memblock_limit = 0; int highmem = 0; - phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1; + u64 vmalloc_limit; struct memblock_region *reg; bool should_use_highmem = false; + /* + * Let's use our own (unoptimized) equivalent of __pa() that is + * not affected by wrap-arounds when sizeof(phys_addr_t) == 4. + * The result is used as the upper bound on physical memory address + * and may itself be outside the valid range for which phys_addr_t + * and therefore __pa() is defined. + */ + vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET; + for_each_memblock(memory, reg) { phys_addr_t block_start = reg->base; phys_addr_t block_end = reg->base + reg->size; @@ -1183,10 +1193,11 @@ void __init sanity_check_meminfo(void) if (reg->size > size_limit) { phys_addr_t overlap_size = reg->size - size_limit; - pr_notice("Truncating RAM at %pa-%pa to -%pa", - &block_start, &block_end, &vmalloc_limit); - memblock_remove(vmalloc_limit, overlap_size); + pr_notice("Truncating RAM at %pa-%pa", + &block_start, &block_end); block_end = vmalloc_limit; + pr_cont(" to -%pa", &block_end); + memblock_remove(vmalloc_limit, overlap_size); should_use_highmem = true; } } diff --git a/arch/arm/plat-samsung/include/plat/map-s5p.h b/arch/arm/plat-samsung/include/plat/map-s5p.h index b63aeebb93f3..0fe2828f9354 100644 --- a/arch/arm/plat-samsung/include/plat/map-s5p.h +++ b/arch/arm/plat-samsung/include/plat/map-s5p.h @@ -14,10 +14,6 @@ #define __ASM_PLAT_MAP_S5P_H __FILE__ #define S5P_VA_CHIPID S3C_ADDR(0x02000000) -#define S5P_VA_CMU S3C_ADDR(0x02100000) - -#define S5P_VA_DMC0 S3C_ADDR(0x02440000) -#define S5P_VA_DMC1 S3C_ADDR(0x02480000) #define S5P_VA_COREPERI_BASE S3C_ADDR(0x02800000) #define S5P_VA_COREPERI(x) (S5P_VA_COREPERI_BASE + (x)) diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index b0b82f5ea338..3d2cef6488ea 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -50,7 +50,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); static struct vcpu_info __percpu *xen_vcpu_info; /* Linux <-> Xen vCPU id mapping */ -DEFINE_PER_CPU(int, xen_vcpu_id) = -1; +DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); /* These are unused until we support booting "pre-ballooned" */ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 69c8787bec7d..bc3f00f586f1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -54,6 +54,7 @@ config ARM64 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_BITREVERSE + select HAVE_ARCH_HARDENED_USERCOPY select HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if SPARSEMEM_VMEMMAP && !(ARM64_16K_PAGES && ARM64_VA_BITS_48) diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index bb2616b16157..be5d824ebdba 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -8,7 +8,7 @@ config ARCH_SUNXI config ARCH_ALPINE bool "Annapurna Labs Alpine platform" - select ALPINE_MSI + select ALPINE_MSI if PCI help This enables support for the Annapurna Labs Alpine Soc family. @@ -66,7 +66,7 @@ config ARCH_LG1K config ARCH_HISI bool "Hisilicon SoC Family" select ARM_TIMER_SP804 - select HISILICON_IRQ_MBIGEN + select HISILICON_IRQ_MBIGEN if PCI help This enables support for Hisilicon ARMv8 SoC family diff --git a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts index 299f3ce969ab..c528dd52ba2d 100644 --- a/arch/arm64/boot/dts/exynos/exynos7-espresso.dts +++ b/arch/arm64/boot/dts/exynos/exynos7-espresso.dts @@ -12,6 +12,7 @@ /dts-v1/; #include "exynos7.dtsi" #include <dt-bindings/interrupt-controller/irq.h> +#include <dt-bindings/clock/samsung,s2mps11.h> / { model = "Samsung Exynos7 Espresso board based on EXYNOS7"; @@ -43,6 +44,8 @@ &rtc { status = "okay"; + clocks = <&clock_ccore PCLK_RTC>, <&s2mps15_osc S2MPS11_CLK_AP>; + clock-names = "rtc", "rtc_src"; }; &watchdog { diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 0555b7caaf2c..eadf4855ad2d 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1,4 +1,3 @@ -# CONFIG_LOCALVERSION_AUTO is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y @@ -15,10 +14,14 @@ CONFIG_IKCONFIG_PROC=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_MEMCG=y CONFIG_MEMCG_SWAP=y +CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_PIDS=y CONFIG_CGROUP_HUGETLB=y -# CONFIG_UTS_NS is not set -# CONFIG_IPC_NS is not set -# CONFIG_NET_NS is not set +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_USER_NS=y CONFIG_SCHED_AUTOGROUP=y CONFIG_BLK_DEV_INITRD=y CONFIG_KALLSYMS_ALL=y @@ -71,6 +74,7 @@ CONFIG_PREEMPT=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_CMA=y +CONFIG_SECCOMP=y CONFIG_XEN=y CONFIG_KEXEC=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set @@ -84,10 +88,37 @@ CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y CONFIG_INET=y +CONFIG_IP_MULTICAST=y CONFIG_IP_PNP=y CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y -# CONFIG_IPV6 is not set +CONFIG_IPV6=m +CONFIG_NETFILTER=y +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_EVENTS=y +CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m +CONFIG_NETFILTER_XT_TARGET_LOG=m +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NF_CONNTRACK_IPV4=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_MANGLE=m +CONFIG_NF_CONNTRACK_IPV6=m +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_IP6_NF_NAT=m +CONFIG_IP6_NF_TARGET_MASQUERADE=m +CONFIG_BRIDGE=m +CONFIG_BRIDGE_VLAN_FILTERING=y +CONFIG_VLAN_8021Q=m +CONFIG_VLAN_8021Q_GVRP=y +CONFIG_VLAN_8021Q_MVRP=y CONFIG_BPF_JIT=y CONFIG_CFG80211=m CONFIG_MAC80211=m @@ -103,6 +134,7 @@ CONFIG_MTD=y CONFIG_MTD_M25P80=y CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_LOOP=y +CONFIG_BLK_DEV_NBD=m CONFIG_VIRTIO_BLK=y CONFIG_SRAM=y # CONFIG_SCSI_PROC_FS is not set @@ -120,7 +152,10 @@ CONFIG_SATA_SIL24=y CONFIG_PATA_PLATFORM=y CONFIG_PATA_OF_PLATFORM=y CONFIG_NETDEVICES=y +CONFIG_MACVLAN=m +CONFIG_MACVTAP=m CONFIG_TUN=y +CONFIG_VETH=m CONFIG_VIRTIO_NET=y CONFIG_AMD_XGBE=y CONFIG_NET_XGENE=y @@ -350,12 +385,16 @@ CONFIG_EXYNOS_ADC=y CONFIG_PWM_SAMSUNG=y CONFIG_EXT2_FS=y CONFIG_EXT3_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_FANOTIFY=y CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y CONFIG_QUOTA=y CONFIG_AUTOFS4_FS=y -CONFIG_FUSE_FS=y -CONFIG_CUSE=y +CONFIG_FUSE_FS=m +CONFIG_CUSE=m +CONFIG_OVERLAY_FS=m CONFIG_VFAT_FS=y CONFIG_TMPFS=y CONFIG_HUGETLBFS=y diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h index 61b49150dfa3..1737aecfcc5e 100644 --- a/arch/arm64/include/asm/kprobes.h +++ b/arch/arm64/include/asm/kprobes.h @@ -22,7 +22,6 @@ #define __ARCH_WANT_KPROBES_INSN_SLOT #define MAX_INSN_SIZE 1 -#define MAX_STACK_SIZE 128 #define flush_insn_slot(p) do { } while (0) #define kretprobe_blacklist_size 0 @@ -47,7 +46,6 @@ struct kprobe_ctlblk { struct prev_kprobe prev_kprobe; struct kprobe_step_ctx ss_ctx; struct pt_regs jprobe_saved_regs; - char jprobes_stack[MAX_STACK_SIZE]; }; void arch_remove_kprobe(struct kprobe *); diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 5e834d10b291..c47257c91b77 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -265,22 +265,25 @@ extern unsigned long __must_check __clear_user(void __user *addr, unsigned long static inline unsigned long __must_check __copy_from_user(void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); - return __arch_copy_from_user(to, from, n); + check_object_size(to, n, false); + return __arch_copy_from_user(to, from, n); } static inline unsigned long __must_check __copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); - return __arch_copy_to_user(to, from, n); + check_object_size(from, n, true); + return __arch_copy_to_user(to, from, n); } static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); - if (access_ok(VERIFY_READ, from, n)) + if (access_ok(VERIFY_READ, from, n)) { + check_object_size(to, n, false); n = __arch_copy_from_user(to, from, n); - else /* security hole - plug it */ + } else /* security hole - plug it */ memset(to, 0, n); return n; } @@ -289,8 +292,10 @@ static inline unsigned long __must_check copy_to_user(void __user *to, const voi { kasan_check_read(from, n); - if (access_ok(VERIFY_WRITE, to, n)) + if (access_ok(VERIFY_WRITE, to, n)) { + check_object_size(from, n, true); n = __arch_copy_to_user(to, from, n); + } return n; } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 96e4a2b64cc1..441420ca7d08 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -353,6 +353,8 @@ el1_sync: lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1 b.eq el1_da + cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1 + b.eq el1_ia cmp x24, #ESR_ELx_EC_SYS64 // configurable trap b.eq el1_undef cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception @@ -364,6 +366,11 @@ el1_sync: cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 b.ge el1_dbg b el1_inv + +el1_ia: + /* + * Fall through to the Data abort case + */ el1_da: /* * Data abort handling diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index b77f58355da1..3e7b050e99dc 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -757,6 +757,9 @@ ENTRY(__enable_mmu) isb bl __create_page_tables // recreate kernel mapping + tlbi vmalle1 // Remove any stale TLB entries + dsb nsh + msr sctlr_el1, x19 // re-enable the MMU isb ic iallu // flush instructions fetched diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 21ab5df9fa76..65d81f965e74 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -35,6 +35,7 @@ #include <asm/sections.h> #include <asm/smp.h> #include <asm/suspend.h> +#include <asm/sysreg.h> #include <asm/virt.h> /* @@ -217,12 +218,22 @@ static int create_safe_exec_page(void *src_start, size_t length, set_pte(pte, __pte(virt_to_phys((void *)dst) | pgprot_val(PAGE_KERNEL_EXEC))); - /* Load our new page tables */ - asm volatile("msr ttbr0_el1, %0;" - "isb;" - "tlbi vmalle1is;" - "dsb ish;" - "isb" : : "r"(virt_to_phys(pgd))); + /* + * Load our new page tables. A strict BBM approach requires that we + * ensure that TLBs are free of any entries that may overlap with the + * global mappings we are about to install. + * + * For a real hibernate/resume cycle TTBR0 currently points to a zero + * page, but TLBs may contain stale ASID-tagged entries (e.g. for EFI + * runtime services), while for a userspace-driven test_resume cycle it + * points to userspace page tables (and we must point it at a zero page + * ourselves). Elsewhere we only (un)install the idmap with preemption + * disabled, so T0SZ should be as required regardless. + */ + cpu_set_reserved_ttbr0(); + local_flush_tlb_all(); + write_sysreg(virt_to_phys(pgd), ttbr0_el1); + isb(); *phys_dst_addr = virt_to_phys((void *)dst); @@ -394,6 +405,38 @@ int swsusp_arch_resume(void) void *, phys_addr_t, phys_addr_t); /* + * Restoring the memory image will overwrite the ttbr1 page tables. + * Create a second copy of just the linear map, and use this when + * restoring. + */ + tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!tmp_pg_dir) { + pr_err("Failed to allocate memory for temporary page tables."); + rc = -ENOMEM; + goto out; + } + rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); + if (rc) + goto out; + + /* + * Since we only copied the linear map, we need to find restore_pblist's + * linear map address. + */ + lm_restore_pblist = LMADDR(restore_pblist); + + /* + * We need a zero page that is zero before & after resume in order to + * to break before make on the ttbr1 page tables. + */ + zero_page = (void *)get_safe_page(GFP_ATOMIC); + if (!zero_page) { + pr_err("Failed to allocate zero page."); + rc = -ENOMEM; + goto out; + } + + /* * Locate the exit code in the bottom-but-one page, so that *NULL * still has disastrous affects. */ @@ -419,27 +462,6 @@ int swsusp_arch_resume(void) __flush_dcache_area(hibernate_exit, exit_size); /* - * Restoring the memory image will overwrite the ttbr1 page tables. - * Create a second copy of just the linear map, and use this when - * restoring. - */ - tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); - if (!tmp_pg_dir) { - pr_err("Failed to allocate memory for temporary page tables."); - rc = -ENOMEM; - goto out; - } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, 0); - if (rc) - goto out; - - /* - * Since we only copied the linear map, we need to find restore_pblist's - * linear map address. - */ - lm_restore_pblist = LMADDR(restore_pblist); - - /* * KASLR will cause the el2 vectors to be in a different location in * the resumed kernel. Load hibernate's temporary copy into el2. * @@ -453,12 +475,6 @@ int swsusp_arch_resume(void) __hyp_set_vectors(el2_vectors); } - /* - * We need a zero page that is zero before & after resume in order to - * to break before make on the ttbr1 page tables. - */ - zero_page = (void *)get_safe_page(GFP_ATOMIC); - hibernate_exit(virt_to_phys(tmp_pg_dir), resume_hdr.ttbr1_el1, resume_hdr.reenter_kernel, lm_restore_pblist, resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page)); diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index bf9768588288..c6b0f40620d8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -41,18 +41,6 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); static void __kprobes post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); -static inline unsigned long min_stack_size(unsigned long addr) -{ - unsigned long size; - - if (on_irq_stack(addr, raw_smp_processor_id())) - size = IRQ_STACK_PTR(raw_smp_processor_id()) - addr; - else - size = (unsigned long)current_thread_info() + THREAD_START_SP - addr; - - return min(size, FIELD_SIZEOF(struct kprobe_ctlblk, jprobes_stack)); -} - static void __kprobes arch_prepare_ss_slot(struct kprobe *p) { /* prepare insn slot */ @@ -489,20 +477,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); - long stack_ptr = kernel_stack_pointer(regs); kcb->jprobe_saved_regs = *regs; /* - * As Linus pointed out, gcc assumes that the callee - * owns the argument space and could overwrite it, e.g. - * tailcall optimization. So, to be absolutely safe - * we also save and restore enough stack bytes to cover - * the argument area. + * Since we can't be sure where in the stack frame "stacked" + * pass-by-value arguments are stored we just don't try to + * duplicate any of the stack. Do not use jprobes on functions that + * use more than 64 bytes (after padding each to an 8 byte boundary) + * of arguments, or pass individual arguments larger than 16 bytes. */ - kasan_disable_current(); - memcpy(kcb->jprobes_stack, (void *)stack_ptr, - min_stack_size(stack_ptr)); - kasan_enable_current(); instruction_pointer_set(regs, (unsigned long) jp->entry); preempt_disable(); @@ -554,10 +537,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) } unpause_graph_tracing(); *regs = kcb->jprobe_saved_regs; - kasan_disable_current(); - memcpy((void *)stack_addr, kcb->jprobes_stack, - min_stack_size(stack_addr)); - kasan_enable_current(); preempt_enable_no_resched(); return 1; } diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 9a3aec97ac09..ccf79d849e0a 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -101,12 +101,20 @@ ENTRY(cpu_resume) bl el2_setup // if in EL2 drop to EL1 cleanly /* enable the MMU early - so we can access sleep_save_stash by va */ adr_l lr, __enable_mmu /* __cpu_setup will return here */ - ldr x27, =_cpu_resume /* __enable_mmu will branch here */ + adr_l x27, _resume_switched /* __enable_mmu will branch here */ adrp x25, idmap_pg_dir adrp x26, swapper_pg_dir b __cpu_setup ENDPROC(cpu_resume) + .pushsection ".idmap.text", "ax" +_resume_switched: + ldr x8, =_cpu_resume + br x8 +ENDPROC(_resume_switched) + .ltorg + .popsection + ENTRY(_cpu_resume) mrs x1, mpidr_el1 adrp x8, mpidr_hash diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 76a6d9263908..d93d43352504 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -661,9 +661,9 @@ void __init smp_init_cpus(void) acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, acpi_parse_gic_cpu_interface, 0); - if (cpu_count > NR_CPUS) - pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n", - cpu_count, NR_CPUS); + if (cpu_count > nr_cpu_ids) + pr_warn("Number of cores (%d) exceeds configured maximum of %d - clipping\n", + cpu_count, nr_cpu_ids); if (!bootcpu_valid) { pr_err("missing boot CPU MPIDR, not enabling secondaries\n"); @@ -677,7 +677,7 @@ void __init smp_init_cpus(void) * with entries in cpu_logical_map while initializing the cpus. * If the cpu set-up fails, invalidate the cpu_logical_map entry. */ - for (i = 1; i < NR_CPUS; i++) { + for (i = 1; i < nr_cpu_ids; i++) { if (cpu_logical_map(i) != INVALID_HWID) { if (smp_cpu_setup(i)) cpu_logical_map(i) = INVALID_HWID; diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index ae7855f16ec2..5a84b4562603 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -256,7 +256,7 @@ static int __hyp_text __guest_run(struct kvm_vcpu *vcpu) /* * We must restore the 32-bit state before the sysregs, thanks - * to Cortex-A57 erratum #852523. + * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). */ __sysreg32_restore_state(vcpu); __sysreg_restore_guest_state(guest_ctxt); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index b0b225ceca18..e51367d159d0 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -823,14 +823,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 * - * We could trap ID_DFR0 and tell the guest we don't support performance - * monitoring. Unfortunately the patch to make the kernel check ID_DFR0 was - * NAKed, so it will read the PMCR anyway. - * - * Therefore we tell the guest we have 0 counters. Unfortunately, we - * must always support PMCCNTR (the cycle counter): we just RAZ/WI for - * all PM registers, which doesn't crash the guest kernel at least. - * * Debug handling: We do trap most, if not all debug related system * registers. The implementation is good enough to ensure that a guest * can use these with minimal performance degradation. The drawback is @@ -1360,7 +1352,7 @@ static const struct sys_reg_desc cp15_regs[] = { { Op1( 0), CRn(10), CRm( 3), Op2( 1), access_vm_reg, NULL, c10_AMAIR1 }, /* ICC_SRE */ - { Op1( 0), CRn(12), CRm(12), Op2( 5), trap_raz_wi }, + { Op1( 0), CRn(12), CRm(12), Op2( 5), access_gic_sre }, { Op1( 0), CRn(13), CRm( 0), Op2( 1), access_vm_reg, NULL, c13_CID }, diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index f94b80eb295d..9c3e75df2180 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -242,7 +242,7 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) { - pte_t *pte = pte_offset_kernel(pmd, 0); + pte_t *pte = pte_offset_kernel(pmd, 0UL); unsigned long addr; unsigned i; @@ -254,7 +254,7 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start) static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) { - pmd_t *pmd = pmd_offset(pud, 0); + pmd_t *pmd = pmd_offset(pud, 0UL); unsigned long addr; unsigned i; @@ -271,7 +271,7 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start) static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start) { - pud_t *pud = pud_offset(pgd, 0); + pud_t *pud = pud_offset(pgd, 0UL); unsigned long addr; unsigned i; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index c8beaa0da7df..05d2bd776c69 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -153,6 +153,11 @@ int ptep_set_access_flags(struct vm_area_struct *vma, } #endif +static bool is_el1_instruction_abort(unsigned int esr) +{ + return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; +} + /* * The kernel tried to access some page that wasn't present. */ @@ -161,8 +166,9 @@ static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr, { /* * Are we prepared to handle this kernel fault? + * We are almost certainly not prepared to handle instruction faults. */ - if (fixup_exception(regs)) + if (!is_el1_instruction_abort(esr) && fixup_exception(regs)) return; /* @@ -267,7 +273,8 @@ static inline bool is_permission_fault(unsigned int esr) unsigned int ec = ESR_ELx_EC(esr); unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE; - return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM); + return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) || + (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM); } static bool is_el0_instruction_abort(unsigned int esr) @@ -312,6 +319,9 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr, if (regs->orig_addr_limit == KERNEL_DS) die("Accessing user space memory with fs=KERNEL_DS", regs, esr); + if (is_el1_instruction_abort(esr)) + die("Attempting to execute userspace memory", regs, esr); + if (!search_exception_tables(regs->pc)) die("Accessing user space memory outside uaccess.h routines", regs, esr); } diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index c7fe3ec70774..5bb15eab6f00 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -23,6 +23,8 @@ #include <linux/module.h> #include <linux/of.h> +#include <asm/acpi.h> + struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; EXPORT_SYMBOL(node_data); nodemask_t numa_nodes_parsed __initdata; diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h index 2e221c5f0203..f86918aed9e1 100644 --- a/arch/h8300/include/asm/io.h +++ b/arch/h8300/include/asm/io.h @@ -3,6 +3,8 @@ #ifdef __KERNEL__ +#include <linux/types.h> + /* H8/300 internal I/O functions */ #define __raw_readb __raw_readb diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 6a15083cc366..18ca6a9ce566 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -52,6 +52,7 @@ config IA64 select MODULES_USE_ELF_RELA select ARCH_USE_CMPXCHG_LOCKREF select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_HARDENED_USERCOPY default y help The Itanium Processor Family is Intel's 64-bit successor to diff --git a/arch/ia64/include/asm/uaccess.h b/arch/ia64/include/asm/uaccess.h index 2189d5ddc1ee..465c70982f40 100644 --- a/arch/ia64/include/asm/uaccess.h +++ b/arch/ia64/include/asm/uaccess.h @@ -241,12 +241,18 @@ extern unsigned long __must_check __copy_user (void __user *to, const void __use static inline unsigned long __copy_to_user (void __user *to, const void *from, unsigned long count) { + if (!__builtin_constant_p(count)) + check_object_size(from, count, true); + return __copy_user(to, (__force void __user *) from, count); } static inline unsigned long __copy_from_user (void *to, const void __user *from, unsigned long count) { + if (!__builtin_constant_p(count)) + check_object_size(to, count, false); + return __copy_user((__force void __user *) to, from, count); } @@ -258,8 +264,11 @@ __copy_from_user (void *to, const void __user *from, unsigned long count) const void *__cu_from = (from); \ long __cu_len = (n); \ \ - if (__access_ok(__cu_to, __cu_len, get_fs())) \ - __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \ + if (__access_ok(__cu_to, __cu_len, get_fs())) { \ + if (!__builtin_constant_p(n)) \ + check_object_size(__cu_from, __cu_len, true); \ + __cu_len = __copy_user(__cu_to, (__force void __user *) __cu_from, __cu_len); \ + } \ __cu_len; \ }) @@ -270,8 +279,11 @@ __copy_from_user (void *to, const void __user *from, unsigned long count) long __cu_len = (n); \ \ __chk_user_ptr(__cu_from); \ - if (__access_ok(__cu_from, __cu_len, get_fs())) \ + if (__access_ok(__cu_from, __cu_len, get_fs())) { \ + if (!__builtin_constant_p(n)) \ + check_object_size(__cu_to, __cu_len, false); \ __cu_len = __copy_user((__force void __user *) __cu_to, __cu_from, __cu_len); \ + } \ __cu_len; \ }) diff --git a/arch/m68k/kernel/signal.c b/arch/m68k/kernel/signal.c index 2dcee3a88867..9202f82dfce6 100644 --- a/arch/m68k/kernel/signal.c +++ b/arch/m68k/kernel/signal.c @@ -213,7 +213,6 @@ static inline int frame_extra_sizes(int f) static inline void adjustformat(struct pt_regs *regs) { - ((struct switch_stack *)regs - 1)->a5 = current->mm->start_data; /* * set format byte to make stack appear modulo 4, which it will * be when doing the rte diff --git a/arch/metag/mm/init.c b/arch/metag/mm/init.c index 11fa51c89617..c0ec116b3993 100644 --- a/arch/metag/mm/init.c +++ b/arch/metag/mm/init.c @@ -390,7 +390,6 @@ void __init mem_init(void) free_all_bootmem(); mem_init_print_info(NULL); - show_mem(0); } void free_initmem(void) diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h index ea0cd9773914..5f987598054f 100644 --- a/arch/mips/include/asm/page.h +++ b/arch/mips/include/asm/page.h @@ -164,7 +164,7 @@ typedef struct { unsigned long pgprot; } pgprot_t; */ static inline unsigned long ___pa(unsigned long x) { - if (config_enabled(CONFIG_64BIT)) { + if (IS_ENABLED(CONFIG_64BIT)) { /* * For MIPS64 the virtual address may either be in one of * the compatibility segements ckseg0 or ckseg1, or it may @@ -173,7 +173,7 @@ static inline unsigned long ___pa(unsigned long x) return x < CKSEG0 ? XPHYSADDR(x) : CPHYSADDR(x); } - if (!config_enabled(CONFIG_EVA)) { + if (!IS_ENABLED(CONFIG_EVA)) { /* * We're using the standard MIPS32 legacy memory map, ie. * the address x is going to be in kseg0 or kseg1. We can diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 6eb52b9c9818..e788515f766b 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -1642,8 +1642,14 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, preempt_disable(); if (KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG0) { - if (kvm_mips_host_tlb_lookup(vcpu, va) < 0) - kvm_mips_handle_kseg0_tlb_fault(va, vcpu); + if (kvm_mips_host_tlb_lookup(vcpu, va) < 0 && + kvm_mips_handle_kseg0_tlb_fault(va, vcpu)) { + kvm_err("%s: handling mapped kseg0 tlb fault for %lx, vcpu: %p, ASID: %#lx\n", + __func__, va, vcpu, read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; + } } else if ((KVM_GUEST_KSEGX(va) < KVM_GUEST_KSEG0) || KVM_GUEST_KSEGX(va) == KVM_GUEST_KSEG23) { int index; @@ -1680,12 +1686,18 @@ enum emulation_result kvm_mips_emulate_cache(union mips_instruction inst, run, vcpu); preempt_enable(); goto dont_update_pc; - } else { - /* - * We fault an entry from the guest tlb to the - * shadow host TLB - */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb); + } + /* + * We fault an entry from the guest tlb to the + * shadow host TLB + */ + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + preempt_enable(); + goto done; } } } else { @@ -2659,7 +2671,12 @@ enum emulation_result kvm_mips_handle_tlbmiss(u32 cause, * OK we have a Guest TLB entry, now inject it into the * shadow host TLB */ - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, tlb)) { + kvm_err("%s: handling mapped seg tlb fault for %lx, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, va, index, vcpu, + read_c0_entryhi()); + er = EMULATE_FAIL; + } } } diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 57319ee57c4f..121008c0fcc9 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -40,7 +40,7 @@ static int kvm_mips_map_page(struct kvm *kvm, gfn_t gfn) srcu_idx = srcu_read_lock(&kvm->srcu); pfn = gfn_to_pfn(kvm, gfn); - if (is_error_pfn(pfn)) { + if (is_error_noslot_pfn(pfn)) { kvm_err("Couldn't get pfn for gfn %#llx!\n", gfn); err = -EFAULT; goto out; @@ -99,7 +99,7 @@ int kvm_mips_handle_kseg0_tlb_fault(unsigned long badvaddr, } gfn = (KVM_GUEST_CPHYSADDR(badvaddr) >> PAGE_SHIFT); - if (gfn >= kvm->arch.guest_pmap_npages) { + if ((gfn | 1) >= kvm->arch.guest_pmap_npages) { kvm_err("%s: Invalid gfn: %#llx, BadVaddr: %#lx\n", __func__, gfn, badvaddr); kvm_mips_dump_host_tlbs(); @@ -138,35 +138,49 @@ int kvm_mips_handle_mapped_seg_tlb_fault(struct kvm_vcpu *vcpu, unsigned long entryhi = 0, entrylo0 = 0, entrylo1 = 0; struct kvm *kvm = vcpu->kvm; kvm_pfn_t pfn0, pfn1; + gfn_t gfn0, gfn1; + long tlb_lo[2]; int ret; - if ((tlb->tlb_hi & VPN2_MASK) == 0) { - pfn0 = 0; - pfn1 = 0; - } else { - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) - >> PAGE_SHIFT) < 0) - return -1; - - if (kvm_mips_map_page(kvm, mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) - >> PAGE_SHIFT) < 0) - return -1; - - pfn0 = kvm->arch.guest_pmap[ - mips3_tlbpfn_to_paddr(tlb->tlb_lo[0]) >> PAGE_SHIFT]; - pfn1 = kvm->arch.guest_pmap[ - mips3_tlbpfn_to_paddr(tlb->tlb_lo[1]) >> PAGE_SHIFT]; + tlb_lo[0] = tlb->tlb_lo[0]; + tlb_lo[1] = tlb->tlb_lo[1]; + + /* + * The commpage address must not be mapped to anything else if the guest + * TLB contains entries nearby, or commpage accesses will break. + */ + if (!((tlb->tlb_hi ^ KVM_GUEST_COMMPAGE_ADDR) & + VPN2_MASK & (PAGE_MASK << 1))) + tlb_lo[(KVM_GUEST_COMMPAGE_ADDR >> PAGE_SHIFT) & 1] = 0; + + gfn0 = mips3_tlbpfn_to_paddr(tlb_lo[0]) >> PAGE_SHIFT; + gfn1 = mips3_tlbpfn_to_paddr(tlb_lo[1]) >> PAGE_SHIFT; + if (gfn0 >= kvm->arch.guest_pmap_npages || + gfn1 >= kvm->arch.guest_pmap_npages) { + kvm_err("%s: Invalid gfn: [%#llx, %#llx], EHi: %#lx\n", + __func__, gfn0, gfn1, tlb->tlb_hi); + kvm_mips_dump_guest_tlbs(vcpu); + return -1; } + if (kvm_mips_map_page(kvm, gfn0) < 0) + return -1; + + if (kvm_mips_map_page(kvm, gfn1) < 0) + return -1; + + pfn0 = kvm->arch.guest_pmap[gfn0]; + pfn1 = kvm->arch.guest_pmap[gfn1]; + /* Get attributes from the Guest TLB */ entrylo0 = mips3_paddr_to_tlbpfn(pfn0 << PAGE_SHIFT) | ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb->tlb_lo[0] & ENTRYLO_D) | - (tlb->tlb_lo[0] & ENTRYLO_V); + (tlb_lo[0] & ENTRYLO_D) | + (tlb_lo[0] & ENTRYLO_V); entrylo1 = mips3_paddr_to_tlbpfn(pfn1 << PAGE_SHIFT) | ((_page_cachable_default >> _CACHE_SHIFT) << ENTRYLO_C_SHIFT) | - (tlb->tlb_lo[1] & ENTRYLO_D) | - (tlb->tlb_lo[1] & ENTRYLO_V); + (tlb_lo[1] & ENTRYLO_D) | + (tlb_lo[1] & ENTRYLO_V); kvm_debug("@ %#lx tlb_lo0: 0x%08lx tlb_lo1: 0x%08lx\n", vcpu->arch.pc, tlb->tlb_lo[0], tlb->tlb_lo[1]); @@ -354,9 +368,15 @@ u32 kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu) local_irq_restore(flags); return KVM_INVALID_INST; } - kvm_mips_handle_mapped_seg_tlb_fault(vcpu, - &vcpu->arch. - guest_tlb[index]); + if (kvm_mips_handle_mapped_seg_tlb_fault(vcpu, + &vcpu->arch.guest_tlb[index])) { + kvm_err("%s: handling mapped seg tlb fault failed for %p, index: %u, vcpu: %p, ASID: %#lx\n", + __func__, opc, index, vcpu, + read_c0_entryhi()); + kvm_mips_dump_guest_tlbs(vcpu); + local_irq_restore(flags); + return KVM_INVALID_INST; + } inst = *(opc); } local_irq_restore(flags); diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h index c0ae62520d15..274d5bc6ecce 100644 --- a/arch/parisc/include/uapi/asm/errno.h +++ b/arch/parisc/include/uapi/asm/errno.h @@ -97,10 +97,10 @@ #define ENOTCONN 235 /* Transport endpoint is not connected */ #define ESHUTDOWN 236 /* Cannot send after transport endpoint shutdown */ #define ETOOMANYREFS 237 /* Too many references: cannot splice */ -#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */ #define ETIMEDOUT 238 /* Connection timed out */ #define ECONNREFUSED 239 /* Connection refused */ -#define EREMOTERELEASE 240 /* Remote peer released connection */ +#define EREFUSED ECONNREFUSED /* for HP's NFS apparently */ +#define EREMOTERELEASE 240 /* Remote peer released connection */ #define EHOSTDOWN 241 /* Host is down */ #define EHOSTUNREACH 242 /* No route to host */ diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 5adc339eb7c8..0c2a94a0f751 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -51,8 +51,6 @@ EXPORT_SYMBOL(_parisc_requires_coherency); DEFINE_PER_CPU(struct cpuinfo_parisc, cpu_data); -extern int update_cr16_clocksource(void); /* from time.c */ - /* ** PARISC CPU driver - claim "device" and initialize CPU data structures. ** @@ -228,12 +226,6 @@ static int processor_probe(struct parisc_device *dev) } #endif - /* If we've registered more than one cpu, - * we'll use the jiffies clocksource since cr16 - * is not synchronized between CPUs. - */ - update_cr16_clocksource(); - return 0; } diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c index 505cf1ac5af2..4b0b963d52a7 100644 --- a/arch/parisc/kernel/time.c +++ b/arch/parisc/kernel/time.c @@ -221,18 +221,6 @@ static struct clocksource clocksource_cr16 = { .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; -int update_cr16_clocksource(void) -{ - /* since the cr16 cycle counters are not synchronized across CPUs, - we'll check if we should switch to a safe clocksource: */ - if (clocksource_cr16.rating != 0 && num_online_cpus() > 1) { - clocksource_change_rating(&clocksource_cr16, 0); - return 1; - } - - return 0; -} - void __init start_cpu_itimer(void) { unsigned int cpu = smp_processor_id(); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index ec4047e170a0..927d2ab2ce08 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -166,6 +166,7 @@ config PPC select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS select GENERIC_CPU_AUTOPROBE select HAVE_VIRT_CPU_ACCOUNTING + select HAVE_ARCH_HARDENED_USERCOPY config GENERIC_CSUM def_bool CPU_LITTLE_ENDIAN diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index ca254546cd05..1934707bf321 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -66,29 +66,28 @@ endif UTS_MACHINE := $(OLDARCH) ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) -override CC += -mlittle-endian -ifneq ($(cc-name),clang) -override CC += -mno-strict-align -endif -override AS += -mlittle-endian override LD += -EL -override CROSS32CC += -mlittle-endian override CROSS32AS += -mlittle-endian LDEMULATION := lppc GNUTARGET := powerpcle MULTIPLEWORD := -mno-multiple KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-save-toc-indirect) else -ifeq ($(call cc-option-yn,-mbig-endian),y) -override CC += -mbig-endian -override AS += -mbig-endian -endif override LD += -EB LDEMULATION := ppc GNUTARGET := powerpc MULTIPLEWORD := -mmultiple endif +cflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) +cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian +ifneq ($(cc-name),clang) + cflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mno-strict-align +endif + +aflags-$(CONFIG_CPU_BIG_ENDIAN) += $(call cc-option,-mbig-endian) +aflags-$(CONFIG_CPU_LITTLE_ENDIAN) += -mlittle-endian + ifeq ($(HAS_BIARCH),y) override AS += -a$(CONFIG_WORD_SIZE) override LD += -m elf$(CONFIG_WORD_SIZE)$(LDEMULATION) @@ -232,6 +231,9 @@ cpu-as-$(CONFIG_E200) += -Wa,-me200 KBUILD_AFLAGS += $(cpu-as-y) KBUILD_CFLAGS += $(cpu-as-y) +KBUILD_AFLAGS += $(aflags-y) +KBUILD_CFLAGS += $(cflags-y) + head-y := arch/powerpc/kernel/head_$(CONFIG_WORD_SIZE).o head-$(CONFIG_8xx) := arch/powerpc/kernel/head_8xx.o head-$(CONFIG_40x) := arch/powerpc/kernel/head_40x.o diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c index bfe3d37a24ef..9fa046d56eba 100644 --- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c +++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c @@ -4,6 +4,7 @@ #include <linux/module.h> #include <linux/string.h> #include <linux/kernel.h> +#include <linux/cpufeature.h> #include <asm/switch_to.h> #define CHKSUM_BLOCK_SIZE 1 @@ -157,7 +158,7 @@ static void __exit crc32c_vpmsum_mod_fini(void) crypto_unregister_shash(&alg); } -module_init(crc32c_vpmsum_mod_init); +module_cpu_feature_match(PPC_MODULE_FEATURE_VEC_CRYPTO, crc32c_vpmsum_mod_init); module_exit(crc32c_vpmsum_mod_fini); MODULE_AUTHOR("Anton Blanchard <anton@samba.org>"); diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h index 3d7fc06532a1..01b8a13f0224 100644 --- a/arch/powerpc/include/asm/cpuidle.h +++ b/arch/powerpc/include/asm/cpuidle.h @@ -19,4 +19,17 @@ extern u64 pnv_first_deep_stop_state; #endif +/* Idle state entry routines */ +#ifdef CONFIG_PPC_P7_NAP +#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ + /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ + std r0,0(r1); \ + ptesync; \ + ld r0,0(r1); \ +1: cmp cr0,r0,r0; \ + bne 1b; \ + IDLE_INST; \ + b . +#endif /* CONFIG_PPC_P7_NAP */ + #endif diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index 57fec8ac7b92..ddf54f5bbdd1 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -186,6 +186,7 @@ label##3: \ #ifndef __ASSEMBLY__ void apply_feature_fixups(void); +void setup_feature_keys(void); #endif #endif /* __ASM_POWERPC_FEATURE_FIXUPS_H */ diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h index 0a74ebe934e1..17c8380673a6 100644 --- a/arch/powerpc/include/asm/switch_to.h +++ b/arch/powerpc/include/asm/switch_to.h @@ -75,14 +75,6 @@ static inline void disable_kernel_spe(void) static inline void __giveup_spe(struct task_struct *t) { } #endif -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -extern void flush_tmregs_to_thread(struct task_struct *); -#else -static inline void flush_tmregs_to_thread(struct task_struct *t) -{ -} -#endif - static inline void clear_task_ebb(struct task_struct *t) { #ifdef CONFIG_PPC_BOOK3S_64 diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index b7c20f0b8fbe..c1dc6c14deb8 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -310,10 +310,15 @@ static inline unsigned long copy_from_user(void *to, { unsigned long over; - if (access_ok(VERIFY_READ, from, n)) + if (access_ok(VERIFY_READ, from, n)) { + if (!__builtin_constant_p(n)) + check_object_size(to, n, false); return __copy_tofrom_user((__force void __user *)to, from, n); + } if ((unsigned long)from < TASK_SIZE) { over = (unsigned long)from + n - TASK_SIZE; + if (!__builtin_constant_p(n - over)) + check_object_size(to, n - over, false); return __copy_tofrom_user((__force void __user *)to, from, n - over) + over; } @@ -325,10 +330,15 @@ static inline unsigned long copy_to_user(void __user *to, { unsigned long over; - if (access_ok(VERIFY_WRITE, to, n)) + if (access_ok(VERIFY_WRITE, to, n)) { + if (!__builtin_constant_p(n)) + check_object_size(from, n, true); return __copy_tofrom_user(to, (__force void __user *)from, n); + } if ((unsigned long)to < TASK_SIZE) { over = (unsigned long)to + n - TASK_SIZE; + if (!__builtin_constant_p(n)) + check_object_size(from, n - over, true); return __copy_tofrom_user(to, (__force void __user *)from, n - over) + over; } @@ -372,6 +382,10 @@ static inline unsigned long __copy_from_user_inatomic(void *to, if (ret == 0) return 0; } + + if (!__builtin_constant_p(n)) + check_object_size(to, n, false); + return __copy_tofrom_user((__force void __user *)to, from, n); } @@ -398,6 +412,9 @@ static inline unsigned long __copy_to_user_inatomic(void __user *to, if (ret == 0) return 0; } + if (!__builtin_constant_p(n)) + check_object_size(from, n, true); + return __copy_tofrom_user(to, (__force const void __user *)from, n); } diff --git a/arch/powerpc/include/asm/xics.h b/arch/powerpc/include/asm/xics.h index f5f729c11578..f0b238516e9b 100644 --- a/arch/powerpc/include/asm/xics.h +++ b/arch/powerpc/include/asm/xics.h @@ -159,6 +159,8 @@ extern void xics_teardown_cpu(void); extern void xics_kexec_teardown_cpu(int secondary); extern void xics_migrate_irqs_away(void); extern void icp_native_eoi(struct irq_data *d); +extern int xics_set_irq_type(struct irq_data *d, unsigned int flow_type); +extern int xics_retrigger(struct irq_data *data); #ifdef CONFIG_SMP extern int xics_get_irq_server(unsigned int virq, const struct cpumask *cpumask, unsigned int strict_check); diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index c9bc78e9c610..7429556eb8df 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -168,10 +168,10 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len) int n = 0, l = 0; char buffer[128]; - n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n", + n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); - pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n", + pr_warn("EEH: of node=%04x:%02x:%02x.%01x\n", edev->phb->global_number, pdn->busno, PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn)); diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 41091fdf9bd8..df6d45eb4115 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -144,29 +144,14 @@ machine_check_pSeries_1: * vector */ SET_SCRATCH0(r13) /* save r13 */ -#ifdef CONFIG_PPC_P7_NAP -BEGIN_FTR_SECTION - /* Running native on arch 2.06 or later, check if we are - * waking up from nap. We only handle no state loss and - * supervisor state loss. We do -not- handle hypervisor - * state loss at this time. + /* + * Running native on arch 2.06 or later, we may wakeup from winkle + * inside machine check. If yes, then last bit of HSPGR0 would be set + * to 1. Hence clear it unconditionally. */ - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - beq 9f - - mfspr r13,SPRN_SRR1 - rlwinm. r13,r13,47-31,30,31 - /* waking up from powersave (nap) state */ - cmpwi cr1,r13,2 - /* Total loss of HV state is fatal. let's just stay stuck here */ - OPT_GET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) - bgt cr1,. -9: - OPT_SET_SPR(r13, SPRN_CFAR, CPU_FTR_CFAR) -END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) -#endif /* CONFIG_PPC_P7_NAP */ + GET_PACA(r13) + clrrdi r13,r13,1 + SET_PACA(r13) EXCEPTION_PROLOG_0(PACA_EXMC) BEGIN_FTR_SECTION b machine_check_powernv_early @@ -1273,25 +1258,51 @@ machine_check_handle_early: * Check if thread was in power saving mode. We come here when any * of the following is true: * a. thread wasn't in power saving mode - * b. thread was in power saving mode with no state loss or - * supervisor state loss + * b. thread was in power saving mode with no state loss, + * supervisor state loss or hypervisor state loss. * - * Go back to nap again if (b) is true. + * Go back to nap/sleep/winkle mode again if (b) is true. */ rlwinm. r11,r12,47-31,30,31 /* Was it in power saving mode? */ beq 4f /* No, it wasn;t */ /* Thread was in power saving mode. Go back to nap again. */ cmpwi r11,2 - bne 3f - /* Supervisor state loss */ + blt 3f + /* Supervisor/Hypervisor state loss */ li r0,1 stb r0,PACA_NAPSTATELOST(r13) 3: bl machine_check_queue_event MACHINE_CHECK_HANDLER_WINDUP GET_PACA(r13) ld r1,PACAR1(r13) - li r3,PNV_THREAD_NAP - b pnv_enter_arch207_idle_mode + /* + * Check what idle state this CPU was in and go back to same mode + * again. + */ + lbz r3,PACA_THREAD_IDLE_STATE(r13) + cmpwi r3,PNV_THREAD_NAP + bgt 10f + IDLE_STATE_ENTER_SEQ(PPC_NAP) + /* No return */ +10: + cmpwi r3,PNV_THREAD_SLEEP + bgt 2f + IDLE_STATE_ENTER_SEQ(PPC_SLEEP) + /* No return */ + +2: + /* + * Go back to winkle. Please note that this thread was woken up in + * machine check from winkle and have not restored the per-subcore + * state. Hence before going back to winkle, set last bit of HSPGR0 + * to 1. This will make sure that if this thread gets woken up + * again at reset vector 0x100 then it will get chance to restore + * the subcore state. + */ + ori r13,r13,1 + SET_PACA(r13) + IDLE_STATE_ENTER_SEQ(PPC_WINKLE) + /* No return */ 4: #endif /* diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S index ba79d15f4ddd..2265c6398a17 100644 --- a/arch/powerpc/kernel/idle_book3s.S +++ b/arch/powerpc/kernel/idle_book3s.S @@ -44,18 +44,6 @@ PSSCR_PSLL_MASK | PSSCR_TR_MASK | \ PSSCR_MTL_MASK -/* Idle state entry routines */ - -#define IDLE_STATE_ENTER_SEQ(IDLE_INST) \ - /* Magic NAP/SLEEP/WINKLE mode enter sequence */ \ - std r0,0(r1); \ - ptesync; \ - ld r0,0(r1); \ -1: cmp cr0,r0,r0; \ - bne 1b; \ - IDLE_INST; \ - b . - .text /* @@ -363,8 +351,8 @@ _GLOBAL(power9_idle_stop) * cr3 - set to gt if waking up with partial/complete hypervisor state loss */ _GLOBAL(pnv_restore_hyp_resource) - ld r2,PACATOC(r13); BEGIN_FTR_SECTION + ld r2,PACATOC(r13); /* * POWER ISA 3. Use PSSCR to determine if we * are waking up from deep idle state @@ -395,6 +383,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) */ clrldi r5,r13,63 clrrdi r13,r13,1 + + /* Now that we are sure r13 is corrected, load TOC */ + ld r2,PACATOC(r13); cmpwi cr4,r5,1 mtspr SPRN_HSPRG0,r13 diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c index ef267fd9dd22..5e7ece0fda9f 100644 --- a/arch/powerpc/kernel/mce.c +++ b/arch/powerpc/kernel/mce.c @@ -92,7 +92,8 @@ void save_mce_event(struct pt_regs *regs, long handled, mce->in_use = 1; mce->initiator = MCE_INITIATOR_CPU; - if (handled) + /* Mark it recovered if we have handled it and MSR(RI=1). */ + if (handled && (regs->msr & MSR_RI)) mce->disposition = MCE_DISPOSITION_RECOVERED; else mce->disposition = MCE_DISPOSITION_NOT_RECOVERED; diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index a5c0153ede37..7fdf324d5b51 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -78,6 +78,7 @@ EXPORT_SYMBOL(get_pci_dma_ops); static int get_phb_number(struct device_node *dn) { int ret, phb_id = -1; + u32 prop_32; u64 prop; /* @@ -86,8 +87,10 @@ static int get_phb_number(struct device_node *dn) * reading "ibm,opal-phbid", only present in OPAL environment. */ ret = of_property_read_u64(dn, "ibm,opal-phbid", &prop); - if (ret) - ret = of_property_read_u32_index(dn, "reg", 1, (u32 *)&prop); + if (ret) { + ret = of_property_read_u32_index(dn, "reg", 1, &prop_32); + prop = prop_32; + } if (!ret) phb_id = (int)(prop & (MAX_PHBS - 1)); diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 58ccf86415b4..9ee2623e0f67 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1074,26 +1074,6 @@ static inline void restore_sprs(struct thread_struct *old_thread, #endif } -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -void flush_tmregs_to_thread(struct task_struct *tsk) -{ - /* - * Process self tracing is not yet supported through - * ptrace interface. Ptrace generic code should have - * prevented this from happening in the first place. - * Warn once here with the message, if some how it - * is attempted. - */ - WARN_ONCE(tsk == current, - "Not expecting ptrace on self: TM regs may be incorrect\n"); - - /* - * If task is not current, it should have been flushed - * already to it's thread_struct during __switch_to(). - */ -} -#endif - struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *new) { diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 6ee4b72cda42..4e74fc588a3f 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2940,7 +2940,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4, /* Don't print anything after quiesce under OPAL, it crashes OFW */ if (of_platform != PLATFORM_OPAL) { - prom_printf("Booting Linux via __start() ...\n"); + prom_printf("Booting Linux via __start() @ 0x%lx ...\n", kbase); prom_debug("->dt_header_start=0x%x\n", hdr); } diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c index 4f3c5756cc09..bf91658a8a40 100644 --- a/arch/powerpc/kernel/ptrace.c +++ b/arch/powerpc/kernel/ptrace.c @@ -38,6 +38,7 @@ #include <asm/page.h> #include <asm/pgtable.h> #include <asm/switch_to.h> +#include <asm/tm.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> @@ -118,6 +119,24 @@ static const struct pt_regs_offset regoffset_table[] = { REG_OFFSET_END, }; +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM +static void flush_tmregs_to_thread(struct task_struct *tsk) +{ + /* + * If task is not current, it will have been flushed already to + * it's thread_struct during __switch_to(). + * + * A reclaim flushes ALL the state. + */ + + if (tsk == current && MSR_TM_SUSPENDED(mfmsr())) + tm_reclaim_current(TM_CAUSE_SIGNAL); + +} +#else +static inline void flush_tmregs_to_thread(struct task_struct *tsk) { } +#endif + /** * regs_query_register_offset() - query register offset from its name * @name: the name of a register diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index c3e861df4b20..24ec3ea4b3a2 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -93,15 +93,16 @@ notrace unsigned long __init early_init(unsigned long dt_ptr) * and we are running with enough of the MMU enabled to have our * proper kernel virtual addresses * - * Find out what kind of machine we're on and save any data we need - * from the early boot process (devtree is copied on pmac by prom_init()). - * This is called very early on the boot process, after a minimal - * MMU environment has been set up but before MMU_init is called. + * We do the initial parsing of the flat device-tree and prepares + * for the MMU to be fully initialized. */ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */ notrace void __init machine_init(u64 dt_ptr) { + /* Configure static keys first, now that we're relocated. */ + setup_feature_keys(); + /* Enable early debugging if any specified (see udbg.h) */ udbg_early_init(); diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index eafb9a79e011..7ac8e6eaab5b 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -300,6 +300,7 @@ void __init early_setup(unsigned long dt_ptr) /* Apply all the dynamic patching */ apply_feature_fixups(); + setup_feature_keys(); /* Initialize the hash table or TLB handling */ early_init_mmu(); diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c index 6767605ea8da..4111d30badfa 100644 --- a/arch/powerpc/kernel/vdso.c +++ b/arch/powerpc/kernel/vdso.c @@ -22,6 +22,7 @@ #include <linux/security.h> #include <linux/memblock.h> +#include <asm/cpu_has_feature.h> #include <asm/pgtable.h> #include <asm/processor.h> #include <asm/mmu.h> diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index cbabd143acae..78a7449bf489 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -30,7 +30,7 @@ CPPFLAGS_vdso32.lds += -P -C -Upowerpc $(obj)/vdso32_wrapper.o : $(obj)/vdso32.so # link rule for the .so file, .lds has to be first -$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) +$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) FORCE $(call if_changed,vdso32ld) # strip rule for the .so file @@ -39,12 +39,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso32): %.o: %.S +$(obj-vdso32): %.o: %.S FORCE $(call if_changed_dep,vdso32as) # actual build commands quiet_cmd_vdso32ld = VDSO32L $@ - cmd_vdso32ld = $(CROSS32CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso32ld = $(CROSS32CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso32as = VDSO32A $@ cmd_vdso32as = $(CROSS32CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index c710802b8fb6..366ae09b14c1 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -23,7 +23,7 @@ CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) $(obj)/vdso64_wrapper.o : $(obj)/vdso64.so # link rule for the .so file, .lds has to be first -$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) +$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) FORCE $(call if_changed,vdso64ld) # strip rule for the .so file @@ -32,12 +32,12 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE $(call if_changed,objcopy) # assembly rules for the .S files -$(obj-vdso64): %.o: %.S +$(obj-vdso64): %.o: %.S FORCE $(call if_changed_dep,vdso64as) # actual build commands quiet_cmd_vdso64ld = VDSO64L $@ - cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@ + cmd_vdso64ld = $(CC) $(c_flags) -o $@ -Wl,-T$(filter %.lds,$^) $(filter %.o,$^) quiet_cmd_vdso64as = VDSO64A $@ cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $< diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index a75ba38a2d81..05aa11399a78 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -1329,20 +1329,16 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) xics->kvm = kvm; /* Already there ? */ - mutex_lock(&kvm->lock); if (kvm->arch.xics) ret = -EEXIST; else kvm->arch.xics = xics; - mutex_unlock(&kvm->lock); if (ret) { kfree(xics); return ret; } - xics_debugfs_init(xics); - #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE if (cpu_has_feature(CPU_FTR_ARCH_206)) { /* Enable real mode support */ @@ -1354,9 +1350,17 @@ static int kvmppc_xics_create(struct kvm_device *dev, u32 type) return 0; } +static void kvmppc_xics_init(struct kvm_device *dev) +{ + struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private; + + xics_debugfs_init(xics); +} + struct kvm_device_ops kvm_xics_ops = { .name = "kvm-xics", .create = kvmppc_xics_create, + .init = kvmppc_xics_init, .destroy = kvmppc_xics_free, .set_attr = xics_set_attr, .get_attr = xics_get_attr, diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S index d90870a66b60..0a57fe6d49cc 100644 --- a/arch/powerpc/lib/checksum_32.S +++ b/arch/powerpc/lib/checksum_32.S @@ -127,8 +127,9 @@ _GLOBAL(csum_partial_copy_generic) stw r7,12(r1) stw r8,8(r1) - andi. r0,r4,1 /* is destination address even ? */ - cmplwi cr7,r0,0 + rlwinm r0,r4,3,0x8 + rlwnm r6,r6,r0,0,31 /* odd destination address: rotate one byte */ + cmplwi cr7,r0,0 /* is destination address even ? */ addic r12,r6,0 addi r6,r4,-4 neg r0,r4 @@ -237,7 +238,7 @@ _GLOBAL(csum_partial_copy_generic) 66: addze r3,r12 addi r1,r1,16 beqlr+ cr7 - rlwinm r3,r3,8,0,31 /* swap bytes for odd destination */ + rlwinm r3,r3,8,0,31 /* odd destination address: rotate one byte */ blr /* read fault */ diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 74145f02ad41..043415f0bdb1 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -188,7 +188,10 @@ void __init apply_feature_fixups(void) &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup); #endif do_final_fixups(); +} +void __init setup_feature_keys(void) +{ /* * Initialise jump label. This causes all the cpu/mmu_has_feature() * checks to take on their correct polarity based on the current set of diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index 5be15cff758d..2975754c65ea 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -496,8 +496,10 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, umode_t mode) gang = alloc_spu_gang(); SPUFS_I(inode)->i_ctx = NULL; SPUFS_I(inode)->i_gang = gang; - if (!gang) + if (!gang) { + ret = -ENOMEM; goto out_iput; + } inode->i_op = &simple_dir_inode_operations; inode->i_fop = &simple_dir_operations; diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index 309d9ccccd50..c61667e8bb06 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -187,6 +187,11 @@ static void pci_dma_dev_setup_pasemi(struct pci_dev *dev) if (dev->vendor == 0x1959 && dev->device == 0xa007 && !firmware_has_feature(FW_FEATURE_LPAR)) { dev->dev.archdata.dma_ops = &dma_direct_ops; + /* + * Set the coherent DMA mask to prevent the iommu + * being used unnecessarily + */ + dev->dev.coherent_dma_mask = DMA_BIT_MASK(44); return; } #endif diff --git a/arch/powerpc/platforms/powernv/opal-irqchip.c b/arch/powerpc/platforms/powernv/opal-irqchip.c index e505223b4ec5..ed8bba68a162 100644 --- a/arch/powerpc/platforms/powernv/opal-irqchip.c +++ b/arch/powerpc/platforms/powernv/opal-irqchip.c @@ -228,7 +228,8 @@ int __init opal_event_init(void) } /* Install interrupt handler */ - rc = request_irq(virq, opal_interrupt, 0, "opal", NULL); + rc = request_irq(virq, opal_interrupt, IRQF_TRIGGER_LOW, + "opal", NULL); if (rc) { irq_dispose_mapping(virq); pr_warn("Error %d requesting irq %d (0x%x)\n", diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index 8b4fc68cebcb..6c9a65b52e63 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -399,6 +399,7 @@ static int opal_recover_mce(struct pt_regs *regs, if (!(regs->msr & MSR_RI)) { /* If MSR_RI isn't set, we cannot recover */ + pr_err("Machine check interrupt unrecoverable: MSR(RI=0)\n"); recovered = 0; } else if (evt->disposition == MCE_DISPOSITION_RECOVERED) { /* Platform corrected itself */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 6b9528307f62..fd9444f9fb0c 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -111,10 +111,17 @@ static int __init iommu_setup(char *str) } early_param("iommu", iommu_setup); -static inline bool pnv_pci_is_mem_pref_64(unsigned long flags) +static inline bool pnv_pci_is_m64(struct pnv_phb *phb, struct resource *r) { - return ((flags & (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)) == - (IORESOURCE_MEM_64 | IORESOURCE_PREFETCH)); + /* + * WARNING: We cannot rely on the resource flags. The Linux PCI + * allocation code sometimes decides to put a 64-bit prefetchable + * BAR in the 32-bit window, so we have to compare the addresses. + * + * For simplicity we only test resource start. + */ + return (r->start >= phb->ioda.m64_base && + r->start < (phb->ioda.m64_base + phb->ioda.m64_size)); } static struct pnv_ioda_pe *pnv_ioda_init_pe(struct pnv_phb *phb, int pe_no) @@ -229,7 +236,7 @@ static void pnv_ioda_reserve_dev_m64_pe(struct pci_dev *pdev, sgsz = phb->ioda.m64_segsize; for (i = 0; i <= PCI_ROM_RESOURCE; i++) { r = &pdev->resource[i]; - if (!r->parent || !pnv_pci_is_mem_pref_64(r->flags)) + if (!r->parent || !pnv_pci_is_m64(phb, r)) continue; start = _ALIGN_DOWN(r->start - base, sgsz); @@ -1877,7 +1884,7 @@ static void pnv_pci_phb3_tce_invalidate(struct pnv_ioda_pe *pe, bool rm, unsigned shift, unsigned long index, unsigned long npages) { - __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, false); + __be64 __iomem *invalidate = pnv_ioda_get_inval_reg(pe->phb, rm); unsigned long start, end, inc; /* We'll invalidate DMA address in PE scope */ @@ -2863,7 +2870,7 @@ static void pnv_pci_ioda_fixup_iov_resources(struct pci_dev *pdev) res = &pdev->resource[i + PCI_IOV_RESOURCES]; if (!res->flags || res->parent) continue; - if (!pnv_pci_is_mem_pref_64(res->flags)) { + if (!pnv_pci_is_m64(phb, res)) { dev_warn(&pdev->dev, "Don't support SR-IOV with" " non M64 VF BAR%d: %pR. \n", i, res); @@ -2958,7 +2965,7 @@ static void pnv_ioda_setup_pe_res(struct pnv_ioda_pe *pe, index++; } } else if ((res->flags & IORESOURCE_MEM) && - !pnv_pci_is_mem_pref_64(res->flags)) { + !pnv_pci_is_m64(phb, res)) { region.start = res->start - phb->hose->mem_offset[0] - phb->ioda.m32_pci_base; @@ -3083,9 +3090,12 @@ static resource_size_t pnv_pci_window_alignment(struct pci_bus *bus, bridge = bridge->bus->self; } - /* We fail back to M32 if M64 isn't supported */ - if (phb->ioda.m64_segsize && - pnv_pci_is_mem_pref_64(type)) + /* + * We fall back to M32 if M64 isn't supported. We enforce the M64 + * alignment for any 64-bit resource, PCIe doesn't care and + * bridges only do 64-bit prefetchable anyway. + */ + if (phb->ioda.m64_segsize && (type & IORESOURCE_MEM_64)) return phb->ioda.m64_segsize; if (type & IORESOURCE_MEM) return phb->ioda.m32_segsize; @@ -3125,7 +3135,7 @@ static void pnv_pci_fixup_bridge_resources(struct pci_bus *bus, w = NULL; if (r->flags & type & IORESOURCE_IO) w = &hose->io_resource; - else if (pnv_pci_is_mem_pref_64(r->flags) && + else if (pnv_pci_is_m64(phb, r) && (type & IORESOURCE_PREFETCH) && phb->ioda.m64_segsize) w = &hose->mem_resources[1]; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 43f7beb2902d..76ec104e88be 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -320,19 +320,6 @@ static int dlpar_remove_device_tree_lmb(struct of_drconf_cell *lmb) return dlpar_update_device_tree_lmb(lmb); } -static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) -{ - unsigned long section_nr; - struct mem_section *mem_sect; - struct memory_block *mem_block; - - section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); - mem_sect = __nr_to_section(section_nr); - - mem_block = find_memory_block(mem_sect); - return mem_block; -} - #ifdef CONFIG_MEMORY_HOTREMOVE static int pseries_remove_memblock(unsigned long base, unsigned int memblock_size) { @@ -420,6 +407,19 @@ static bool lmb_is_removable(struct of_drconf_cell *lmb) static int dlpar_add_lmb(struct of_drconf_cell *); +static struct memory_block *lmb_to_memblock(struct of_drconf_cell *lmb) +{ + unsigned long section_nr; + struct mem_section *mem_sect; + struct memory_block *mem_block; + + section_nr = pfn_to_section_nr(PFN_DOWN(lmb->base_addr)); + mem_sect = __nr_to_section(section_nr); + + mem_block = find_memory_block(mem_sect); + return mem_block; +} + static int dlpar_remove_lmb(struct of_drconf_cell *lmb) { struct memory_block *mem_block; diff --git a/arch/powerpc/sysdev/xics/Kconfig b/arch/powerpc/sysdev/xics/Kconfig index 0031eda320c3..385e7aa9e273 100644 --- a/arch/powerpc/sysdev/xics/Kconfig +++ b/arch/powerpc/sysdev/xics/Kconfig @@ -1,6 +1,7 @@ config PPC_XICS def_bool n select PPC_SMP_MUXED_IPI + select HARDIRQS_SW_RESEND config PPC_ICP_NATIVE def_bool n diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c index 27c936c080a6..1c6bf4b66f56 100644 --- a/arch/powerpc/sysdev/xics/ics-opal.c +++ b/arch/powerpc/sysdev/xics/ics-opal.c @@ -156,7 +156,9 @@ static struct irq_chip ics_opal_irq_chip = { .irq_mask = ics_opal_mask_irq, .irq_unmask = ics_opal_unmask_irq, .irq_eoi = NULL, /* Patched at init time */ - .irq_set_affinity = ics_opal_set_affinity + .irq_set_affinity = ics_opal_set_affinity, + .irq_set_type = xics_set_irq_type, + .irq_retrigger = xics_retrigger, }; static int ics_opal_map(struct ics *ics, unsigned int virq); diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c index 3854dd41558d..78ee5c778ef8 100644 --- a/arch/powerpc/sysdev/xics/ics-rtas.c +++ b/arch/powerpc/sysdev/xics/ics-rtas.c @@ -163,7 +163,9 @@ static struct irq_chip ics_rtas_irq_chip = { .irq_mask = ics_rtas_mask_irq, .irq_unmask = ics_rtas_unmask_irq, .irq_eoi = NULL, /* Patched at init time */ - .irq_set_affinity = ics_rtas_set_affinity + .irq_set_affinity = ics_rtas_set_affinity, + .irq_set_type = xics_set_irq_type, + .irq_retrigger = xics_retrigger, }; static int ics_rtas_map(struct ics *ics, unsigned int virq) diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c index a795a5f0301c..9d530f479588 100644 --- a/arch/powerpc/sysdev/xics/xics-common.c +++ b/arch/powerpc/sysdev/xics/xics-common.c @@ -328,8 +328,12 @@ static int xics_host_map(struct irq_domain *h, unsigned int virq, pr_devel("xics: map virq %d, hwirq 0x%lx\n", virq, hw); - /* They aren't all level sensitive but we just don't really know */ - irq_set_status_flags(virq, IRQ_LEVEL); + /* + * Mark interrupts as edge sensitive by default so that resend + * actually works. The device-tree parsing will turn the LSIs + * back to level. + */ + irq_clear_status_flags(virq, IRQ_LEVEL); /* Don't call into ICS for IPIs */ if (hw == XICS_IPI) { @@ -351,13 +355,54 @@ static int xics_host_xlate(struct irq_domain *h, struct device_node *ct, irq_hw_number_t *out_hwirq, unsigned int *out_flags) { - /* Current xics implementation translates everything - * to level. It is not technically right for MSIs but this - * is irrelevant at this point. We might get smarter in the future - */ *out_hwirq = intspec[0]; - *out_flags = IRQ_TYPE_LEVEL_LOW; + /* + * If intsize is at least 2, we look for the type in the second cell, + * we assume the LSB indicates a level interrupt. + */ + if (intsize > 1) { + if (intspec[1] & 1) + *out_flags = IRQ_TYPE_LEVEL_LOW; + else + *out_flags = IRQ_TYPE_EDGE_RISING; + } else + *out_flags = IRQ_TYPE_LEVEL_LOW; + + return 0; +} + +int xics_set_irq_type(struct irq_data *d, unsigned int flow_type) +{ + /* + * We only support these. This has really no effect other than setting + * the corresponding descriptor bits mind you but those will in turn + * affect the resend function when re-enabling an edge interrupt. + * + * Set set the default to edge as explained in map(). + */ + if (flow_type == IRQ_TYPE_DEFAULT || flow_type == IRQ_TYPE_NONE) + flow_type = IRQ_TYPE_EDGE_RISING; + + if (flow_type != IRQ_TYPE_EDGE_RISING && + flow_type != IRQ_TYPE_LEVEL_LOW) + return -EINVAL; + + irqd_set_trigger_type(d, flow_type); + + return IRQ_SET_MASK_OK_NOCOPY; +} + +int xics_retrigger(struct irq_data *data) +{ + /* + * We need to push a dummy CPPR when retriggering, since the subsequent + * EOI will try to pop it. Passing 0 works, as the function hard codes + * the priority value anyway. + */ + xics_push_cppr(0); + + /* Tell the core to do a soft retrigger */ return 0; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 9e607bf2d640..e751fe25d6ab 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -123,6 +123,7 @@ config S390 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_EARLY_PFN_TO_NID + select HAVE_ARCH_HARDENED_USERCOPY select HAVE_ARCH_JUMP_LABEL select CPU_NO_EFFICIENT_FFS if !HAVE_MARCH_Z9_109_FEATURES select HAVE_ARCH_SECCOMP_FILTER @@ -871,4 +872,17 @@ config S390_GUEST Select this option if you want to run the kernel as a guest under the KVM hypervisor. +config S390_GUEST_OLD_TRANSPORT + def_bool y + prompt "Guest support for old s390 virtio transport (DEPRECATED)" + depends on S390_GUEST + help + Enable this option to add support for the old s390-virtio + transport (i.e. virtio devices NOT based on virtio-ccw). This + type of virtio devices is only available on the experimental + kuli userspace or with old (< 2.6) qemu. If you are running + with a modern version of qemu (which supports virtio-ccw since + 1.4 and uses it by default since version 2.4), you probably won't + need this. + endmenu diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S index f86a4eef28a9..28c4f96a2d9c 100644 --- a/arch/s390/boot/compressed/head.S +++ b/arch/s390/boot/compressed/head.S @@ -21,16 +21,21 @@ ENTRY(startup_continue) lg %r15,.Lstack-.LPG1(%r13) aghi %r15,-160 brasl %r14,decompress_kernel - # setup registers for memory mover & branch to target + # Set up registers for memory mover. We move the decompressed image to + # 0x11000, starting at offset 0x11000 in the decompressed image so + # that code living at 0x11000 in the image will end up at 0x11000 in + # memory. lgr %r4,%r2 lg %r2,.Loffset-.LPG1(%r13) la %r4,0(%r2,%r4) lg %r3,.Lmvsize-.LPG1(%r13) lgr %r5,%r3 - # move the memory mover someplace safe + # Move the memory mover someplace safe so it doesn't overwrite itself. la %r1,0x200 mvc 0(mover_end-mover,%r1),mover-.LPG1(%r13) - # decompress image is started at 0x11000 + # When the memory mover is done we pass control to + # arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in + # the decompressed image. lgr %r6,%r2 br %r1 mover: diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 889ea3450210..26e0c7f08814 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -678,7 +678,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 1bcfd764910a..24879dab47bc 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -616,7 +616,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index 13ff090139c8..a5c1e5f2a0ca 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -615,7 +615,7 @@ CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m CONFIG_CRYPTO_GHASH_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_ASYMMETRIC_KEY_TYPE=y CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m CONFIG_X509_CERTIFICATE_PARSER=m diff --git a/arch/s390/crypto/crc32-vx.c b/arch/s390/crypto/crc32-vx.c index 577ae1d4ae89..2bad9d837029 100644 --- a/arch/s390/crypto/crc32-vx.c +++ b/arch/s390/crypto/crc32-vx.c @@ -51,6 +51,9 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); struct kernel_fpu vxstate; \ unsigned long prealign, aligned, remaining; \ \ + if (datalen < VX_MIN_LEN + VX_ALIGN_MASK) \ + return ___crc32_sw(crc, data, datalen); \ + \ if ((unsigned long)data & VX_ALIGN_MASK) { \ prealign = VX_ALIGNMENT - \ ((unsigned long)data & VX_ALIGN_MASK); \ @@ -59,9 +62,6 @@ u32 crc32c_le_vgfm_16(u32 crc, unsigned char const *buf, size_t size); data = (void *)((unsigned long)data + prealign); \ } \ \ - if (datalen < VX_MIN_LEN) \ - return ___crc32_sw(crc, data, datalen); \ - \ aligned = datalen & ~VX_ALIGN_MASK; \ remaining = datalen & VX_ALIGN_MASK; \ \ diff --git a/arch/s390/defconfig b/arch/s390/defconfig index ccccebeeaaf6..73610f2e3b4f 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -234,7 +234,7 @@ CONFIG_CRYPTO_SHA256_S390=m CONFIG_CRYPTO_SHA512_S390=m CONFIG_CRYPTO_DES_S390=m CONFIG_CRYPTO_AES_S390=m -CONFIG_CRYPTO_CRC32_S390=m +CONFIG_CRYPTO_CRC32_S390=y CONFIG_CRC7=m # CONFIG_XZ_DEC_X86 is not set # CONFIG_XZ_DEC_POWERPC is not set diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S index 56e4d8234ef2..4431905f8cfa 100644 --- a/arch/s390/kernel/head.S +++ b/arch/s390/kernel/head.S @@ -309,7 +309,9 @@ ENTRY(startup_kdump) l %r15,.Lstack-.LPG0(%r13) ahi %r15,-STACK_FRAME_OVERHEAD brasl %r14,verify_facilities - /* Continue with startup code in head64.S */ +# For uncompressed images, continue in +# arch/s390/kernel/head64.S. For compressed images, continue in +# arch/s390/boot/compressed/head.S. jg startup_continue .Lstack: diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index ba5f456edaa9..7f7ba5f23f13 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -204,11 +204,9 @@ static void __init conmode_default(void) #endif } } else if (MACHINE_IS_KVM) { - if (sclp.has_vt220 && - config_enabled(CONFIG_SCLP_VT220_CONSOLE)) + if (sclp.has_vt220 && IS_ENABLED(CONFIG_SCLP_VT220_CONSOLE)) SET_CONSOLE_VT220; - else if (sclp.has_linemode && - config_enabled(CONFIG_SCLP_CONSOLE)) + else if (sclp.has_linemode && IS_ENABLED(CONFIG_SCLP_CONSOLE)) SET_CONSOLE_SCLP; else SET_CONSOLE_HVC; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 3f3ae4865d57..f142215ed30d 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -1672,6 +1672,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) KVM_SYNC_CRS | KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT; + kvm_s390_set_prefix(vcpu, 0); if (test_kvm_facility(vcpu->kvm, 64)) vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; /* fprs can be synchronized via vrs, even if the guest has no vx. With @@ -2361,8 +2362,10 @@ retry: rc = gmap_mprotect_notify(vcpu->arch.gmap, kvm_s390_get_prefix(vcpu), PAGE_SIZE * 2, PROT_WRITE); - if (rc) + if (rc) { + kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); return rc; + } goto retry; } diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c index e390bbb16443..48352bffbc92 100644 --- a/arch/s390/lib/string.c +++ b/arch/s390/lib/string.c @@ -237,11 +237,10 @@ char * strrchr(const char * s, int c) EXPORT_SYMBOL(strrchr); static inline int clcle(const char *s1, unsigned long l1, - const char *s2, unsigned long l2, - int *diff) + const char *s2, unsigned long l2) { register unsigned long r2 asm("2") = (unsigned long) s1; - register unsigned long r3 asm("3") = (unsigned long) l2; + register unsigned long r3 asm("3") = (unsigned long) l1; register unsigned long r4 asm("4") = (unsigned long) s2; register unsigned long r5 asm("5") = (unsigned long) l2; int cc; @@ -252,7 +251,6 @@ static inline int clcle(const char *s1, unsigned long l1, " srl %0,28" : "=&d" (cc), "+a" (r2), "+a" (r3), "+a" (r4), "+a" (r5) : : "cc"); - *diff = *(char *)r2 - *(char *)r4; return cc; } @@ -270,9 +268,9 @@ char * strstr(const char * s1,const char * s2) return (char *) s1; l1 = __strend(s1) - s1; while (l1-- >= l2) { - int cc, dummy; + int cc; - cc = clcle(s1, l1, s2, l2, &dummy); + cc = clcle(s1, l2, s2, l2); if (!cc) return (char *) s1; s1++; @@ -313,11 +311,11 @@ EXPORT_SYMBOL(memchr); */ int memcmp(const void *cs, const void *ct, size_t n) { - int ret, diff; + int ret; - ret = clcle(cs, n, ct, n, &diff); + ret = clcle(cs, n, ct, n); if (ret) - ret = diff; + ret = ret == 1 ? -1 : 1; return ret; } EXPORT_SYMBOL(memcmp); diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c index d96596128e9f..f481fcde067b 100644 --- a/arch/s390/lib/uaccess.c +++ b/arch/s390/lib/uaccess.c @@ -104,6 +104,7 @@ static inline unsigned long copy_from_user_mvcp(void *x, const void __user *ptr, unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { + check_object_size(to, n, false); if (static_branch_likely(&have_mvcos)) return copy_from_user_mvcos(to, from, n); return copy_from_user_mvcp(to, from, n); @@ -177,6 +178,7 @@ static inline unsigned long copy_to_user_mvcs(void __user *ptr, const void *x, unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { + check_object_size(from, n, true); if (static_branch_likely(&have_mvcos)) return copy_to_user_mvcos(to, from, n); return copy_to_user_mvcs(to, from, n); diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 7104ffb5a67f..af7cf28cf97e 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -252,6 +252,8 @@ static int change_page_attr(unsigned long addr, unsigned long end, int rc = -EINVAL; pgd_t *pgdp; + if (addr == end) + return 0; if (end >= MODULES_END) return -EINVAL; mutex_lock(&cpa_mutex); diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 546293d9e6c5..59b09600dd32 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -43,6 +43,7 @@ config SPARC select OLD_SIGSUSPEND select ARCH_HAS_SG_CHAIN select CPU_NO_EFFICIENT_FFS + select HAVE_ARCH_HARDENED_USERCOPY config SPARC32 def_bool !64BIT diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h index 57aca2792d29..341a5a133f48 100644 --- a/arch/sparc/include/asm/uaccess_32.h +++ b/arch/sparc/include/asm/uaccess_32.h @@ -248,22 +248,28 @@ unsigned long __copy_user(void __user *to, const void __user *from, unsigned lon static inline unsigned long copy_to_user(void __user *to, const void *from, unsigned long n) { - if (n && __access_ok((unsigned long) to, n)) + if (n && __access_ok((unsigned long) to, n)) { + if (!__builtin_constant_p(n)) + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); - else + } else return n; } static inline unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n) { + if (!__builtin_constant_p(n)) + check_object_size(from, n, true); return __copy_user(to, (__force void __user *) from, n); } static inline unsigned long copy_from_user(void *to, const void __user *from, unsigned long n) { - if (n && __access_ok((unsigned long) from, n)) + if (n && __access_ok((unsigned long) from, n)) { + if (!__builtin_constant_p(n)) + check_object_size(to, n, false); return __copy_user((__force void __user *) to, from, n); - else + } else return n; } diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index e9a51d64974d..8bda94fab8e8 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -210,8 +210,12 @@ unsigned long copy_from_user_fixup(void *to, const void __user *from, static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long size) { - unsigned long ret = ___copy_from_user(to, from, size); + unsigned long ret; + if (!__builtin_constant_p(size)) + check_object_size(to, size, false); + + ret = ___copy_from_user(to, from, size); if (unlikely(ret)) ret = copy_from_user_fixup(to, from, size); @@ -227,8 +231,11 @@ unsigned long copy_to_user_fixup(void __user *to, const void *from, static inline unsigned long __must_check copy_to_user(void __user *to, const void *from, unsigned long size) { - unsigned long ret = ___copy_to_user(to, from, size); + unsigned long ret; + if (!__builtin_constant_p(size)) + check_object_size(from, size, true); + ret = ___copy_to_user(to, from, size); if (unlikely(ret)) ret = copy_to_user_fixup(to, from, size); return ret; diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S index 1dd5bd8a8c59..133055311dce 100644 --- a/arch/um/include/asm/common.lds.S +++ b/arch/um/include/asm/common.lds.S @@ -81,7 +81,7 @@ .altinstr_replacement : { *(.altinstr_replacement) } /* .exit.text is discard at runtime, not link time, to deal with references from .altinstructions and .eh_frame */ - .exit.text : { *(.exit.text) } + .exit.text : { EXIT_TEXT } .exit.data : { *(.exit.data) } .preinit_array : { diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h index e35632ef23c7..62dfc644c908 100644 --- a/arch/unicore32/include/asm/mmu_context.h +++ b/arch/unicore32/include/asm/mmu_context.h @@ -98,7 +98,7 @@ static inline void arch_bprm_mm_init(struct mm_struct *mm, } static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, - bool write, bool foreign) + bool write, bool execute, bool foreign) { /* by default, allow everything */ return true; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5c6e7471b732..c580d8c33562 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -80,6 +80,7 @@ config X86 select HAVE_ALIGNED_STRUCT_PAGE if SLUB select HAVE_AOUT if X86_32 select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_HARDENED_USERCOPY select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_KASAN if X86_64 && SPARSEMEM_VMEMMAP @@ -91,6 +92,7 @@ config X86 select HAVE_ARCH_SOFT_DIRTY if X86_64 select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE + select HAVE_ARCH_WITHIN_STACK_FRAMES select HAVE_EBPF_JIT if X86_64 select HAVE_CC_STACKPROTECTOR select HAVE_CMPXCHG_DOUBLE diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c index 89fa85e8b10c..6f97fb33ae21 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb.c +++ b/arch/x86/crypto/sha256-mb/sha256_mb.c @@ -485,10 +485,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S index b691da981cd9..a78a0694ddef 100644 --- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S +++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S @@ -265,13 +265,14 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2) vpinsrd $1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0 vpinsrd $3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0 - movl _args_digest+4*32(state, idx, 4), tmp2_w + vmovd _args_digest(state , idx, 4) , %xmm0 vpinsrd $1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1 vpinsrd $3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1 - vmovdqu %xmm0, _result_digest(job_rax) - movl tmp2_w, _result_digest+1*16(job_rax) + vmovdqu %xmm0, _result_digest(job_rax) + offset = (_result_digest + 1*16) + vmovdqu %xmm1, offset(job_rax) pop %rbx diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c index f4cf5b78fd36..d210174a52b0 100644 --- a/arch/x86/crypto/sha512-mb/sha512_mb.c +++ b/arch/x86/crypto/sha512-mb/sha512_mb.c @@ -497,10 +497,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx, req = cast_mcryptd_ctx_to_req(req_ctx); if (irqs_disabled()) - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); else { local_bh_disable(); - rctx->complete(&req->base, ret); + req_ctx->complete(&req->base, ret); local_bh_enable(); } } diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index fe91c25092da..77f28ce9c646 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -5,6 +5,8 @@ OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y +CFLAGS_syscall_64.o += -Wno-override-init +CFLAGS_syscall_32.o += -Wno-override-init obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index b846875aeea6..d172c619c449 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -288,11 +288,15 @@ return_from_SYSCALL_64: jne opportunistic_sysret_failed /* - * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, - * restoring TF results in a trap from userspace immediately after - * SYSRET. This would cause an infinite loop whenever #DB happens - * with register state that satisfies the opportunistic SYSRET - * conditions. For example, single-stepping this user code: + * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot + * restore RF properly. If the slowpath sets it for whatever reason, we + * need to restore it correctly. + * + * SYSRET can restore TF, but unlike IRET, restoring TF results in a + * trap from userspace immediately after SYSRET. This would cause an + * infinite loop whenever #DB happens with register state that satisfies + * the opportunistic SYSRET conditions. For example, single-stepping + * this user code: * * movq $stuck_here, %rcx * pushfq @@ -601,9 +605,20 @@ apicinterrupt3 \num trace(\sym) smp_trace(\sym) .endm #endif +/* Make sure APIC interrupt handlers end up in the irqentry section: */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN) +# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax" +# define POP_SECTION_IRQENTRY .popsection +#else +# define PUSH_SECTION_IRQENTRY +# define POP_SECTION_IRQENTRY +#endif + .macro apicinterrupt num sym do_sym +PUSH_SECTION_IRQENTRY apicinterrupt3 \num \sym \do_sym trace_apicinterrupt \num \sym +POP_SECTION_IRQENTRY .endm #ifdef CONFIG_SMP diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 97a69dbba649..9d35ec0cb8fc 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -100,6 +100,12 @@ static void snb_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void snb_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL); +} + static void snb_uncore_msr_exit_box(struct intel_uncore_box *box) { if (box->pmu->pmu_idx == 0) @@ -127,6 +133,7 @@ static struct attribute_group snb_uncore_format_group = { static struct intel_uncore_ops snb_uncore_msr_ops = { .init_box = snb_uncore_msr_init_box, + .enable_box = snb_uncore_msr_enable_box, .exit_box = snb_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, @@ -192,6 +199,12 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box) } } +static void skl_uncore_msr_enable_box(struct intel_uncore_box *box) +{ + wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, + SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL); +} + static void skl_uncore_msr_exit_box(struct intel_uncore_box *box) { if (box->pmu->pmu_idx == 0) @@ -200,6 +213,7 @@ static void skl_uncore_msr_exit_box(struct intel_uncore_box *box) static struct intel_uncore_ops skl_uncore_msr_ops = { .init_box = skl_uncore_msr_init_box, + .enable_box = skl_uncore_msr_enable_box, .exit_box = skl_uncore_msr_exit_box, .disable_event = snb_uncore_msr_disable_event, .enable_event = snb_uncore_msr_enable_event, diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 824e54086e07..8aee83bcf71f 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -2626,7 +2626,7 @@ void hswep_uncore_cpu_init(void) static struct intel_uncore_type hswep_uncore_ha = { .name = "ha", - .num_counters = 5, + .num_counters = 4, .num_boxes = 2, .perf_ctr_bits = 48, SNBEP_UNCORE_PCI_COMMON_INIT(), @@ -2645,7 +2645,7 @@ static struct uncore_event_desc hswep_uncore_imc_events[] = { static struct intel_uncore_type hswep_uncore_imc = { .name = "imc", - .num_counters = 5, + .num_counters = 4, .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, @@ -2691,7 +2691,7 @@ static struct intel_uncore_type hswep_uncore_irp = { static struct intel_uncore_type hswep_uncore_qpi = { .name = "qpi", - .num_counters = 5, + .num_counters = 4, .num_boxes = 3, .perf_ctr_bits = 48, .perf_ctr = SNBEP_PCI_PMON_CTR0, @@ -2773,7 +2773,7 @@ static struct event_constraint hswep_uncore_r3qpi_constraints[] = { static struct intel_uncore_type hswep_uncore_r3qpi = { .name = "r3qpi", - .num_counters = 4, + .num_counters = 3, .num_boxes = 3, .perf_ctr_bits = 44, .constraints = hswep_uncore_r3qpi_constraints, @@ -2972,7 +2972,7 @@ static struct intel_uncore_type bdx_uncore_ha = { static struct intel_uncore_type bdx_uncore_imc = { .name = "imc", - .num_counters = 5, + .num_counters = 4, .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index f5befd4945f2..124357773ffa 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -135,6 +135,7 @@ extern void init_apic_mappings(void); void register_lapic_address(unsigned long address); extern void setup_boot_APIC_clock(void); extern void setup_secondary_APIC_clock(void); +extern void lapic_update_tsc_freq(void); extern int APIC_init_uniprocessor(void); #ifdef CONFIG_X86_64 @@ -170,6 +171,7 @@ static inline void init_apic_mappings(void) { } static inline void disable_local_APIC(void) { } # define setup_boot_APIC_clock x86_init_noop # define setup_secondary_APIC_clock x86_init_noop +static inline void lapic_update_tsc_freq(void) { } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 7178043b0e1d..59405a248fc2 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -22,10 +22,6 @@ typedef struct { #ifdef CONFIG_SMP unsigned int irq_resched_count; unsigned int irq_call_count; - /* - * irq_tlb_count is double-counted in irq_call_count, so it must be - * subtracted from irq_call_count when displaying irq_call_count - */ unsigned int irq_tlb_count; #endif #ifdef CONFIG_X86_THERMAL_VECTOR diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 223042086f4e..737da62bfeb0 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -5,10 +5,10 @@ struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ void *context; /* context for alloc_pgt_page */ unsigned long pmd_flag; /* page flag for PMD entry */ - bool kernel_mapping; /* kernel mapping or ident mapping */ + unsigned long offset; /* ident mapping offset */ }; int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, - unsigned long addr, unsigned long end); + unsigned long pstart, unsigned long pend); #endif /* _ASM_X86_INIT_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 7e8ec7ae10fa..1cc82ece9ac1 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -145,7 +145,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2|1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names - * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry + * | OFFSET (14->63) | TYPE (9-13) |0|X|X|X| X| X|X|X|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above @@ -156,7 +156,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) #define SWP_TYPE_BITS 5 /* Place the offset above the type: */ -#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1) +#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 9c6b890d5e7a..b2988c0ed829 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -58,7 +58,15 @@ extern unsigned char boot_gdt[]; extern unsigned char secondary_startup_64[]; #endif +static inline size_t real_mode_size_needed(void) +{ + if (real_mode_header) + return 0; /* already allocated. */ + + return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE); +} + +void set_real_mode_mem(phys_addr_t mem, size_t size); void reserve_real_mode(void); -void setup_real_mode(void); #endif /* _ARCH_X86_REALMODE_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 84b59846154a..8b7c8d8e0852 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -176,6 +176,50 @@ static inline unsigned long current_stack_pointer(void) return sp; } +/* + * Walks up the stack frames to make sure that the specified object is + * entirely contained by a single stack frame. + * + * Returns: + * 1 if within a frame + * -1 if placed across a frame boundary (or outside stack) + * 0 unable to determine (no frame pointers, etc) + */ +static inline int arch_within_stack_frames(const void * const stack, + const void * const stackend, + const void *obj, unsigned long len) +{ +#if defined(CONFIG_FRAME_POINTER) + const void *frame = NULL; + const void *oldframe; + + oldframe = __builtin_frame_address(1); + if (oldframe) + frame = __builtin_frame_address(2); + /* + * low ----------------------------------------------> high + * [saved bp][saved ip][args][local vars][saved bp][saved ip] + * ^----------------^ + * allow copies only within here + */ + while (stack <= frame && frame < stackend) { + /* + * If obj + len extends past the last frame, this + * check won't pass and the next frame will be 0, + * causing us to bail out and correctly report + * the copy as invalid. + */ + if (obj + len <= frame) + return obj >= oldframe + 2 * sizeof(void *) ? 1 : -1; + oldframe = frame; + frame = *(const void * const *)frame; + } + return -1; +#else + return 0; +#endif +} + #else /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 4e5be94e079a..6fa85944af83 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -135,7 +135,14 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask) static inline void __native_flush_tlb(void) { + /* + * If current->mm == NULL then we borrow a mm which may change during a + * task switch and therefore we must not be preempted while we write CR3 + * back: + */ + preempt_disable(); native_write_cr3(native_read_cr3()); + preempt_enable(); } static inline void __native_flush_tlb_global_irq_disabled(void) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index c03bfb68c503..a0ae610b9280 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -761,9 +761,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n) * case, and do only runtime checking for non-constant sizes. */ - if (likely(sz < 0 || sz >= n)) + if (likely(sz < 0 || sz >= n)) { + check_object_size(to, n, false); n = _copy_from_user(to, from, n); - else if(__builtin_constant_p(n)) + } else if (__builtin_constant_p(n)) copy_from_user_overflow(); else __copy_from_user_overflow(sz, n); @@ -781,9 +782,10 @@ copy_to_user(void __user *to, const void *from, unsigned long n) might_fault(); /* See the comment in copy_from_user() above. */ - if (likely(sz < 0 || sz >= n)) + if (likely(sz < 0 || sz >= n)) { + check_object_size(from, n, true); n = _copy_to_user(to, from, n); - else if(__builtin_constant_p(n)) + } else if (__builtin_constant_p(n)) copy_to_user_overflow(); else __copy_to_user_overflow(sz, n); @@ -812,21 +814,21 @@ copy_to_user(void __user *to, const void *from, unsigned long n) #define user_access_begin() __uaccess_begin() #define user_access_end() __uaccess_end() -#define unsafe_put_user(x, ptr) \ -({ \ +#define unsafe_put_user(x, ptr, err_label) \ +do { \ int __pu_err; \ __put_user_size((x), (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \ - __builtin_expect(__pu_err, 0); \ -}) + if (unlikely(__pu_err)) goto err_label; \ +} while (0) -#define unsafe_get_user(x, ptr) \ -({ \ +#define unsafe_get_user(x, ptr, err_label) \ +do { \ int __gu_err; \ unsigned long __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ - __builtin_expect(__gu_err, 0); \ -}) + if (unlikely(__gu_err)) goto err_label; \ +} while (0) #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index 4b32da24faaf..7d3bdd1ed697 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -37,6 +37,7 @@ unsigned long __must_check __copy_from_user_ll_nocache_nozero static __always_inline unsigned long __must_check __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) { + check_object_size(from, n, true); return __copy_to_user_ll(to, from, n); } @@ -95,6 +96,7 @@ static __always_inline unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n) { might_fault(); + check_object_size(to, n, false); if (__builtin_constant_p(n)) { unsigned long ret; diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index 2eac2aa3e37f..673059a109fe 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -54,6 +54,7 @@ int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size) { int ret = 0; + check_object_size(dst, size, false); if (!__builtin_constant_p(size)) return copy_user_generic(dst, (__force void *)src, size); switch (size) { @@ -119,6 +120,7 @@ int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size) { int ret = 0; + check_object_size(src, size, true); if (!__builtin_constant_p(size)) return copy_user_generic((__force void *)dst, src, size); switch (size) { diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index c852590254d5..e652a7cc6186 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -79,7 +79,7 @@ struct uv_gam_range_entry { u16 nasid; /* HNasid */ u16 sockid; /* Socket ID, high bits of APIC ID */ u16 pnode; /* Index to MMR and GRU spaces */ - u32 pxm; /* ACPI proximity domain number */ + u32 unused2; u32 limit; /* PA bits 56:26 (UV_GAM_RANGE_SHFT) */ }; @@ -88,7 +88,8 @@ struct uv_gam_range_entry { #define UV_SYSTAB_VERSION_UV4 0x400 /* UV4 BIOS base version */ #define UV_SYSTAB_VERSION_UV4_1 0x401 /* + gpa_shift */ #define UV_SYSTAB_VERSION_UV4_2 0x402 /* + TYPE_NVRAM/WINDOW/MBOX */ -#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_2 +#define UV_SYSTAB_VERSION_UV4_3 0x403 /* - GAM Range PXM Value */ +#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_3 #define UV_SYSTAB_TYPE_UNUSED 0 /* End of table (offset == 0) */ #define UV_SYSTAB_TYPE_GAM_PARAMS 1 /* GAM PARAM conversions */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 20abd912f0e4..50c95af0f017 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -313,7 +313,7 @@ int lapic_get_maxlvt(void) /* Clock divisor */ #define APIC_DIVISOR 16 -#define TSC_DIVISOR 32 +#define TSC_DIVISOR 8 /* * This function sets up the local APIC timer, with a timeout of @@ -565,13 +565,37 @@ static void setup_APIC_timer(void) CLOCK_EVT_FEAT_DUMMY); levt->set_next_event = lapic_next_deadline; clockevents_config_and_register(levt, - (tsc_khz / TSC_DIVISOR) * 1000, + tsc_khz * (1000 / TSC_DIVISOR), 0xF, ~0UL); } else clockevents_register_device(levt); } /* + * Install the updated TSC frequency from recalibration at the TSC + * deadline clockevent devices. + */ +static void __lapic_update_tsc_freq(void *info) +{ + struct clock_event_device *levt = this_cpu_ptr(&lapic_events); + + if (!this_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return; + + clockevents_update_freq(levt, tsc_khz * (1000 / TSC_DIVISOR)); +} + +void lapic_update_tsc_freq(void) +{ + /* + * The clockevent device's ->mult and ->shift can both be + * changed. In order to avoid races, schedule the frequency + * update code on each CPU. + */ + on_each_cpu(__lapic_update_tsc_freq, NULL, 0); +} + +/* * In this functions we calibrate APIC bus clocks to the external timer. * * We want to do the calibration only once since we want to have local timer @@ -1599,6 +1623,9 @@ void __init enable_IR_x2apic(void) unsigned long flags; int ret, ir_stat; + if (skip_ioapic_setup) + return; + ir_stat = irq_remapping_prepare(); if (ir_stat < 0 && !x2apic_supported()) return; diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 6368fa69d2af..54f35d988025 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -155,7 +155,7 @@ static void init_x2apic_ldr(void) /* * At CPU state changes, update the x2apic cluster sibling info. */ -int x2apic_prepare_cpu(unsigned int cpu) +static int x2apic_prepare_cpu(unsigned int cpu) { if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL)) return -ENOMEM; @@ -168,7 +168,7 @@ int x2apic_prepare_cpu(unsigned int cpu) return 0; } -int x2apic_dead_cpu(unsigned int this_cpu) +static int x2apic_dead_cpu(unsigned int this_cpu) { int cpu; @@ -186,13 +186,18 @@ int x2apic_dead_cpu(unsigned int this_cpu) static int x2apic_cluster_probe(void) { int cpu = smp_processor_id(); + int ret; if (!x2apic_mode) return 0; + ret = cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE", + x2apic_prepare_cpu, x2apic_dead_cpu); + if (ret < 0) { + pr_err("Failed to register X2APIC_PREPARE\n"); + return 0; + } cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu)); - cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE", - x2apic_prepare_cpu, x2apic_dead_cpu); return 1; } diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 09b59adaea3f..cb0673c1e940 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -223,6 +223,11 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id) if (strncmp(oem_id, "SGI", 3) != 0) return 0; + if (numa_off) { + pr_err("UV: NUMA is off, disabling UV support\n"); + return 0; + } + /* Setup early hub type field in uv_hub_info for Node 0 */ uv_cpu_info->p_uv_hub_info = &uv_hub_info_node0; @@ -325,7 +330,7 @@ static __init void build_uv_gr_table(void) struct uv_gam_range_entry *gre = uv_gre_table; struct uv_gam_range_s *grt; unsigned long last_limit = 0, ram_limit = 0; - int bytes, i, sid, lsid = -1; + int bytes, i, sid, lsid = -1, indx = 0, lindx = -1; if (!gre) return; @@ -356,11 +361,12 @@ static __init void build_uv_gr_table(void) } sid = gre->sockid - _min_socket; if (lsid < sid) { /* new range */ - grt = &_gr_table[sid]; - grt->base = lsid; + grt = &_gr_table[indx]; + grt->base = lindx; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; lsid = sid; + lindx = indx++; continue; } if (lsid == sid && !ram_limit) { /* update range */ @@ -371,7 +377,7 @@ static __init void build_uv_gr_table(void) } if (!ram_limit) { /* non-contiguous ram range */ grt++; - grt->base = sid - 1; + grt->base = lindx; grt->nasid = gre->nasid; grt->limit = last_limit = gre->limit; continue; @@ -1155,19 +1161,18 @@ static void __init decode_gam_rng_tbl(unsigned long ptr) for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (!index) { pr_info("UV: GAM Range Table...\n"); - pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s %3s\n", + pr_info("UV: # %20s %14s %5s %4s %5s %3s %2s\n", "Range", "", "Size", "Type", "NASID", - "SID", "PN", "PXM"); + "SID", "PN"); } pr_info( - "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x %3d\n", + "UV: %2d: 0x%014lx-0x%014lx %5luG %3d %04x %02x %02x\n", index++, (unsigned long)lgre << UV_GAM_RANGE_SHFT, (unsigned long)gre->limit << UV_GAM_RANGE_SHFT, ((unsigned long)(gre->limit - lgre)) >> (30 - UV_GAM_RANGE_SHFT), /* 64M -> 1G */ - gre->type, gre->nasid, gre->sockid, - gre->pnode, gre->pxm); + gre->type, gre->nasid, gre->sockid, gre->pnode); lgre = gre->limit; if (sock_min > gre->sockid) @@ -1286,7 +1291,7 @@ static void __init build_socket_tables(void) _pnode_to_socket[i] = SOCK_EMPTY; /* fill in pnode/node/addr conversion list values */ - pr_info("UV: GAM Building socket/pnode/pxm conversion tables\n"); + pr_info("UV: GAM Building socket/pnode conversion tables\n"); for (; gre->type != UV_GAM_RANGE_TYPE_UNUSED; gre++) { if (gre->type == UV_GAM_RANGE_TYPE_HOLE) continue; @@ -1294,20 +1299,18 @@ static void __init build_socket_tables(void) if (_socket_to_pnode[i] != SOCK_EMPTY) continue; /* duplicate */ _socket_to_pnode[i] = gre->pnode; - _socket_to_node[i] = gre->pxm; i = gre->pnode - minpnode; _pnode_to_socket[i] = gre->sockid; pr_info( - "UV: sid:%02x type:%d nasid:%04x pn:%02x pxm:%2d pn2s:%2x\n", + "UV: sid:%02x type:%d nasid:%04x pn:%02x pn2s:%2x\n", gre->sockid, gre->type, gre->nasid, _socket_to_pnode[gre->sockid - minsock], - _socket_to_node[gre->sockid - minsock], _pnode_to_socket[gre->pnode - minpnode]); } - /* check socket -> node values */ + /* Set socket -> node values */ lnid = -1; for_each_present_cpu(cpu) { int nid = cpu_to_node(cpu); @@ -1318,14 +1321,9 @@ static void __init build_socket_tables(void) lnid = nid; apicid = per_cpu(x86_cpu_to_apicid, cpu); sockid = apicid >> uv_cpuid.socketid_shift; - i = sockid - minsock; - - if (nid != _socket_to_node[i]) { - pr_warn( - "UV: %02x: type:%d socket:%02x PXM:%02x != node:%2d\n", - i, sockid, gre->type, _socket_to_node[i], nid); - _socket_to_node[i] = nid; - } + _socket_to_node[sockid - minsock] = nid; + pr_info("UV: sid:%02x: apicid:%04x node:%2d\n", + sockid, apicid, nid); } /* Setup physical blade to pnode translation from GAM Range Table */ diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 27a0228c9cae..b816971f5da4 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -355,6 +355,7 @@ void load_ucode_amd_ap(void) unsigned int cpu = smp_processor_id(); struct equiv_cpu_entry *eq; struct microcode_amd *mc; + u8 *cont = container; u32 rev, eax; u16 eq_id; @@ -371,8 +372,11 @@ void load_ucode_amd_ap(void) if (check_current_patch_level(&rev, false)) return; + /* Add CONFIG_RANDOMIZE_MEMORY offset. */ + cont += PAGE_OFFSET - __PAGE_OFFSET_BASE; + eax = cpuid_eax(0x00000001); - eq = (struct equiv_cpu_entry *)(container + CONTAINER_HDR_SZ); + eq = (struct equiv_cpu_entry *)(cont + CONTAINER_HDR_SZ); eq_id = find_equiv_id(eq, eax); if (!eq_id) @@ -434,6 +438,9 @@ int __init save_microcode_in_initrd_amd(void) else container = cont_va; + /* Add CONFIG_RANDOMIZE_MEMORY offset. */ + container += PAGE_OFFSET - __PAGE_OFFSET_BASE; + eax = cpuid_eax(0x00000001); eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 680049aa4593..01567aa87503 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -866,105 +866,17 @@ const void *get_xsave_field_ptr(int xsave_state) return get_xsave_addr(&fpu->state.xsave, xsave_state); } - -/* - * Set xfeatures (aka XSTATE_BV) bit for a feature that we want - * to take out of its "init state". This will ensure that an - * XRSTOR actually restores the state. - */ -static void fpu__xfeature_set_non_init(struct xregs_state *xsave, - int xstate_feature_mask) -{ - xsave->header.xfeatures |= xstate_feature_mask; -} - -/* - * This function is safe to call whether the FPU is in use or not. - * - * Note that this only works on the current task. - * - * Inputs: - * @xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP, - * XFEATURE_MASK_SSE, etc...) - * @xsave_state_ptr: a pointer to a copy of the state that you would - * like written in to the current task's FPU xsave state. This pointer - * must not be located in the current tasks's xsave area. - * Output: - * address of the state in the xsave area or NULL if the state - * is not present or is in its 'init state'. - */ -static void fpu__xfeature_set_state(int xstate_feature_mask, - void *xstate_feature_src, size_t len) -{ - struct xregs_state *xsave = ¤t->thread.fpu.state.xsave; - struct fpu *fpu = ¤t->thread.fpu; - void *dst; - - if (!boot_cpu_has(X86_FEATURE_XSAVE)) { - WARN_ONCE(1, "%s() attempted with no xsave support", __func__); - return; - } - - /* - * Tell the FPU code that we need the FPU state to be in - * 'fpu' (not in the registers), and that we need it to - * be stable while we write to it. - */ - fpu__current_fpstate_write_begin(); - - /* - * This method *WILL* *NOT* work for compact-format - * buffers. If the 'xstate_feature_mask' is unset in - * xcomp_bv then we may need to move other feature state - * "up" in the buffer. - */ - if (xsave->header.xcomp_bv & xstate_feature_mask) { - WARN_ON_ONCE(1); - goto out; - } - - /* find the location in the xsave buffer of the desired state */ - dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask); - - /* - * Make sure that the pointer being passed in did not - * come from the xsave buffer itself. - */ - WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself"); - - /* put the caller-provided data in the location */ - memcpy(dst, xstate_feature_src, len); - - /* - * Mark the xfeature so that the CPU knows there is state - * in the buffer now. - */ - fpu__xfeature_set_non_init(xsave, xstate_feature_mask); -out: - /* - * We are done writing to the 'fpu'. Reenable preeption - * and (possibly) move the fpstate back in to the fpregs. - */ - fpu__current_fpstate_write_end(); -} - #define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) #define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* - * This will go out and modify the XSAVE buffer so that PKRU is - * set to a particular state for access to 'pkey'. - * - * PKRU state does affect kernel access to user memory. We do - * not modfiy PKRU *itself* here, only the XSAVE state that will - * be restored in to PKRU when we return back to userspace. + * This will go out and modify PKRU register to set the access + * rights for @pkey to @init_val. */ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, unsigned long init_val) { - struct xregs_state *xsave = &tsk->thread.fpu.state.xsave; - struct pkru_state *old_pkru_state; - struct pkru_state new_pkru_state; + u32 old_pkru; int pkey_shift = (pkey * PKRU_BITS_PER_PKEY); u32 new_pkru_bits = 0; @@ -974,6 +886,15 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL; + /* + * For most XSAVE components, this would be an arduous task: + * brining fpstate up to date with fpregs, updating fpstate, + * then re-populating fpregs. But, for components that are + * never lazily managed, we can just access the fpregs + * directly. PKRU is never managed lazily, so we can just + * manipulate it directly. Make sure it stays that way. + */ + WARN_ON_ONCE(!use_eager_fpu()); /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) @@ -984,37 +905,12 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, /* Shift the bits in to the correct place in PKRU for pkey: */ new_pkru_bits <<= pkey_shift; - /* Locate old copy of the state in the xsave buffer: */ - old_pkru_state = get_xsave_addr(xsave, XFEATURE_MASK_PKRU); - - /* - * When state is not in the buffer, it is in the init - * state, set it manually. Otherwise, copy out the old - * state. - */ - if (!old_pkru_state) - new_pkru_state.pkru = 0; - else - new_pkru_state.pkru = old_pkru_state->pkru; - - /* Mask off any old bits in place: */ - new_pkru_state.pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); - - /* Set the newly-requested bits: */ - new_pkru_state.pkru |= new_pkru_bits; - - /* - * We could theoretically live without zeroing pkru.pad. - * The current XSAVE feature state definition says that - * only bytes 0->3 are used. But we do not want to - * chance leaking kernel stack out to userspace in case a - * memcpy() of the whole xsave buffer was done. - * - * They're in the same cacheline anyway. - */ - new_pkru_state.pad = 0; + /* Get old PKRU and mask off any old bits in place: */ + old_pkru = read_pkru(); + old_pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift); - fpu__xfeature_set_state(XFEATURE_MASK_PKRU, &new_pkru_state, sizeof(new_pkru_state)); + /* Write old part along with new part: */ + write_pkru(old_pkru | new_pkru_bits); return 0; } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 2dda0bc4576e..f16c55bfc090 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -25,8 +25,6 @@ static void __init i386_default_early_setup(void) /* Initialize 32bit specific setup functions */ x86_init.resources.reserve_resources = i386_reserve_resources; x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; - - reserve_bios_regions(); } asmlinkage __visible void __init i386_start_kernel(void) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 99d48e7d2974..54a2372f5dbb 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -183,7 +183,6 @@ void __init x86_64_start_reservations(char *real_mode_data) copy_bootdata(__va(real_mode_data)); x86_early_init_platform_quirks(); - reserve_bios_regions(); switch (boot_params.hdr.hardware_subarch) { case X86_SUBARCH_INTEL_MID: diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ed16e58658a4..c6dfd801df97 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1242,7 +1242,7 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) memset(&curr_time, 0, sizeof(struct rtc_time)); if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) - mc146818_set_time(&curr_time); + mc146818_get_time(&curr_time); if (hpet_rtc_flags & RTC_UIE && curr_time.tm_sec != hpet_prev_update_sec) { diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 61521dc19c10..9f669fdd2010 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -102,8 +102,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) seq_puts(p, " Rescheduling interrupts\n"); seq_printf(p, "%*s: ", prec, "CAL"); for_each_online_cpu(j) - seq_printf(p, "%10u ", irq_stats(j)->irq_call_count - - irq_stats(j)->irq_tlb_count); + seq_printf(p, "%10u ", irq_stats(j)->irq_call_count); seq_puts(p, " Function call interrupts\n"); seq_printf(p, "%*s: ", prec, "TLB"); for_each_online_cpu(j) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 991b77986d57..0fa60f5f5a16 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -936,8 +936,6 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); - kernel_randomize_memory(); - iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; setup_memory_map(); parse_setup_data(); @@ -1055,6 +1053,12 @@ void __init setup_arch(char **cmdline_p) max_possible_pfn = max_pfn; + /* + * Define random base addresses for memory sections after max_pfn is + * defined and before each memory section base is used. + */ + kernel_randomize_memory(); + #ifdef CONFIG_X86_32 /* max_low_pfn get updated here */ find_low_pfn_range(); @@ -1097,6 +1101,8 @@ void __init setup_arch(char **cmdline_p) efi_find_mirror(); } + reserve_bios_regions(); + /* * The EFI specification says that boot service code won't be called * after ExitBootServices(). This is, in fact, a lie. @@ -1125,7 +1131,15 @@ void __init setup_arch(char **cmdline_p) early_trap_pf_init(); - setup_real_mode(); + /* + * Update mmu_cr4_features (and, indirectly, trampoline_cr4_features) + * with the current CR4 value. This may not be necessary, but + * auditing all the early-boot CR4 manipulation would be needed to + * rule it out. + */ + if (boot_cpu_data.cpuid_level >= 0) + /* A CPU has %cr4 if and only if it has CPUID. */ + mmu_cr4_features = __read_cr4(); memblock_set_current_limit(get_max_mapped()); @@ -1174,13 +1188,6 @@ void __init setup_arch(char **cmdline_p) kasan_init(); - if (boot_cpu_data.cpuid_level >= 0) { - /* A CPU has %cr4 if and only if it has CPUID */ - mmu_cr4_features = __read_cr4(); - if (trampoline_cr4_features) - *trampoline_cr4_features = mmu_cr4_features; - } - #ifdef CONFIG_X86_32 /* sync back kernel address range */ clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY, diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2a6e84a30a54..4296beb8fdd3 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -100,10 +100,11 @@ EXPORT_PER_CPU_SYMBOL(cpu_info); /* Logical package management. We might want to allocate that dynamically */ static int *physical_to_logical_pkg __read_mostly; static unsigned long *physical_package_map __read_mostly;; -static unsigned long *logical_package_map __read_mostly; static unsigned int max_physical_pkg_id __read_mostly; unsigned int __max_logical_packages __read_mostly; EXPORT_SYMBOL(__max_logical_packages); +static unsigned int logical_packages __read_mostly; +static bool logical_packages_frozen __read_mostly; /* Maximum number of SMT threads on any online core */ int __max_smt_threads __read_mostly; @@ -277,14 +278,14 @@ int topology_update_package_map(unsigned int apicid, unsigned int cpu) if (test_and_set_bit(pkg, physical_package_map)) goto found; - new = find_first_zero_bit(logical_package_map, __max_logical_packages); - if (new >= __max_logical_packages) { + if (logical_packages_frozen) { physical_to_logical_pkg[pkg] = -1; - pr_warn("APIC(%x) Package %u exceeds logical package map\n", + pr_warn("APIC(%x) Package %u exceeds logical package max\n", apicid, pkg); return -ENOSPC; } - set_bit(new, logical_package_map); + + new = logical_packages++; pr_info("APIC(%x) Converting physical %u to logical package %u\n", apicid, pkg, new); physical_to_logical_pkg[pkg] = new; @@ -341,6 +342,7 @@ static void __init smp_init_package_map(void) } __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); + logical_packages = 0; /* * Possibly larger than what we need as the number of apic ids per @@ -352,10 +354,6 @@ static void __init smp_init_package_map(void) memset(physical_to_logical_pkg, 0xff, size); size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long); physical_package_map = kzalloc(size, GFP_KERNEL); - size = BITS_TO_LONGS(__max_logical_packages) * sizeof(unsigned long); - logical_package_map = kzalloc(size, GFP_KERNEL); - - pr_info("Max logical packages: %u\n", __max_logical_packages); for_each_present_cpu(cpu) { unsigned int apicid = apic->cpu_present_to_apicid(cpu); @@ -369,6 +367,15 @@ static void __init smp_init_package_map(void) set_cpu_possible(cpu, false); set_cpu_present(cpu, false); } + + if (logical_packages > __max_logical_packages) { + pr_warn("Detected more packages (%u), then computed by BIOS data (%u).\n", + logical_packages, __max_logical_packages); + logical_packages_frozen = true; + __max_logical_packages = logical_packages; + } + + pr_info("Max logical packages: %u\n", __max_logical_packages); } void __init smp_store_boot_cpu_info(void) diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1ef87e887051..78b9cb5a26af 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -22,6 +22,7 @@ #include <asm/nmi.h> #include <asm/x86_init.h> #include <asm/geode.h> +#include <asm/apic.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -1249,6 +1250,9 @@ static void tsc_refine_calibration_work(struct work_struct *work) (unsigned long)tsc_khz / 1000, (unsigned long)tsc_khz % 1000); + /* Inform the TSC deadline clockevent devices about the recalibration */ + lapic_update_tsc_freq(); + out: if (boot_cpu_has(X86_FEATURE_ART)) art_related_clocksource = &clocksource_tsc; diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 6c1ff31d99ff..495c776de4b4 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -357,20 +357,22 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) *cursor &= 0xfe; } /* - * Similar treatment for VEX3 prefix. - * TODO: add XOP/EVEX treatment when insn decoder supports them + * Similar treatment for VEX3/EVEX prefix. + * TODO: add XOP treatment when insn decoder supports them */ - if (insn->vex_prefix.nbytes == 3) { + if (insn->vex_prefix.nbytes >= 3) { /* * vex2: c5 rvvvvLpp (has no b bit) * vex3/xop: c4/8f rxbmmmmm wvvvvLpp * evex: 62 rxbR00mm wvvvv1pp zllBVaaa - * (evex will need setting of both b and x since - * in non-sib encoding evex.x is 4th bit of MODRM.rm) - * Setting VEX3.b (setting because it has inverted meaning): + * Setting VEX3.b (setting because it has inverted meaning). + * Setting EVEX.x since (in non-SIB encoding) EVEX.x + * is the 4th bit of MODRM.rm, and needs the same treatment. + * For VEX3-encoded insns, VEX3.x value has no effect in + * non-SIB encoding, the change is superfluous but harmless. */ cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1; - *cursor |= 0x20; + *cursor |= 0x60; } /* @@ -415,12 +417,10 @@ static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) reg = MODRM_REG(insn); /* Fetch modrm.reg */ reg2 = 0xff; /* Fetch vex.vvvv */ - if (insn->vex_prefix.nbytes == 2) - reg2 = insn->vex_prefix.bytes[1]; - else if (insn->vex_prefix.nbytes == 3) + if (insn->vex_prefix.nbytes) reg2 = insn->vex_prefix.bytes[2]; /* - * TODO: add XOP, EXEV vvvv reading. + * TODO: add XOP vvvv reading. * * vex.vvvv field is in bits 6-3, bits are inverted. * But in 32-bit mode, high-order bit may be ignored. diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index a45d8580f91e..5cede40e2552 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -422,6 +422,7 @@ struct nested_vmx { struct list_head vmcs02_pool; int vmcs02_num; u64 vmcs01_tsc_offset; + bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; /* @@ -435,6 +436,8 @@ struct nested_vmx { bool pi_pending; u16 posted_intr_nv; + unsigned long *msr_bitmap; + struct hrtimer preemption_timer; bool preemption_timer_expired; @@ -924,7 +927,6 @@ static unsigned long *vmx_msr_bitmap_legacy; static unsigned long *vmx_msr_bitmap_longmode; static unsigned long *vmx_msr_bitmap_legacy_x2apic; static unsigned long *vmx_msr_bitmap_longmode_x2apic; -static unsigned long *vmx_msr_bitmap_nested; static unsigned long *vmx_vmread_bitmap; static unsigned long *vmx_vmwrite_bitmap; @@ -2198,6 +2200,12 @@ static void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) new.control) != old.control); } +static void decache_tsc_multiplier(struct vcpu_vmx *vmx) +{ + vmx->current_tsc_ratio = vmx->vcpu.arch.tsc_scaling_ratio; + vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); +} + /* * Switches to specified vcpu, until a matching vcpu_put(), but assumes * vcpu mutex is already taken. @@ -2256,10 +2264,8 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) /* Setup TSC multiplier */ if (kvm_has_tsc_control && - vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) { - vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio; - vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio); - } + vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) + decache_tsc_multiplier(vmx); vmx_vcpu_pi_load(vcpu, cpu); vmx->host_pkru = read_pkru(); @@ -2508,7 +2514,7 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu) unsigned long *msr_bitmap; if (is_guest_mode(vcpu)) - msr_bitmap = vmx_msr_bitmap_nested; + msr_bitmap = to_vmx(vcpu)->nested.msr_bitmap; else if (cpu_has_secondary_exec_ctrls() && (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) & SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) { @@ -6363,13 +6369,6 @@ static __init int hardware_setup(void) if (!vmx_msr_bitmap_longmode_x2apic) goto out4; - if (nested) { - vmx_msr_bitmap_nested = - (unsigned long *)__get_free_page(GFP_KERNEL); - if (!vmx_msr_bitmap_nested) - goto out5; - } - vmx_vmread_bitmap = (unsigned long *)__get_free_page(GFP_KERNEL); if (!vmx_vmread_bitmap) goto out6; @@ -6392,8 +6391,6 @@ static __init int hardware_setup(void) memset(vmx_msr_bitmap_legacy, 0xff, PAGE_SIZE); memset(vmx_msr_bitmap_longmode, 0xff, PAGE_SIZE); - if (nested) - memset(vmx_msr_bitmap_nested, 0xff, PAGE_SIZE); if (setup_vmcs_config(&vmcs_config) < 0) { r = -EIO; @@ -6529,9 +6526,6 @@ out8: out7: free_page((unsigned long)vmx_vmread_bitmap); out6: - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); -out5: free_page((unsigned long)vmx_msr_bitmap_longmode_x2apic); out4: free_page((unsigned long)vmx_msr_bitmap_longmode); @@ -6557,8 +6551,6 @@ static __exit void hardware_unsetup(void) free_page((unsigned long)vmx_io_bitmap_a); free_page((unsigned long)vmx_vmwrite_bitmap); free_page((unsigned long)vmx_vmread_bitmap); - if (nested) - free_page((unsigned long)vmx_msr_bitmap_nested); free_kvm_area(); } @@ -6995,16 +6987,21 @@ static int handle_vmon(struct kvm_vcpu *vcpu) return 1; } + if (cpu_has_vmx_msr_bitmap()) { + vmx->nested.msr_bitmap = + (unsigned long *)__get_free_page(GFP_KERNEL); + if (!vmx->nested.msr_bitmap) + goto out_msr_bitmap; + } + vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL); if (!vmx->nested.cached_vmcs12) - return -ENOMEM; + goto out_cached_vmcs12; if (enable_shadow_vmcs) { shadow_vmcs = alloc_vmcs(); - if (!shadow_vmcs) { - kfree(vmx->nested.cached_vmcs12); - return -ENOMEM; - } + if (!shadow_vmcs) + goto out_shadow_vmcs; /* mark vmcs as shadow */ shadow_vmcs->revision_id |= (1u << 31); /* init shadow vmcs */ @@ -7024,6 +7021,15 @@ static int handle_vmon(struct kvm_vcpu *vcpu) skip_emulated_instruction(vcpu); nested_vmx_succeed(vcpu); return 1; + +out_shadow_vmcs: + kfree(vmx->nested.cached_vmcs12); + +out_cached_vmcs12: + free_page((unsigned long)vmx->nested.msr_bitmap); + +out_msr_bitmap: + return -ENOMEM; } /* @@ -7098,6 +7104,10 @@ static void free_nested(struct vcpu_vmx *vmx) vmx->nested.vmxon = false; free_vpid(vmx->nested.vpid02); nested_release_vmcs12(vmx); + if (vmx->nested.msr_bitmap) { + free_page((unsigned long)vmx->nested.msr_bitmap); + vmx->nested.msr_bitmap = NULL; + } if (enable_shadow_vmcs) free_vmcs(vmx->nested.current_shadow_vmcs); kfree(vmx->nested.cached_vmcs12); @@ -8419,6 +8429,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) { u32 sec_exec_control; + /* Postpone execution until vmcs01 is the current VMCS. */ + if (is_guest_mode(vcpu)) { + to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true; + return; + } + /* * There is not point to enable virtualize x2apic without enable * apicv @@ -9472,8 +9488,10 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, { int msr; struct page *page; - unsigned long *msr_bitmap; + unsigned long *msr_bitmap_l1; + unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.msr_bitmap; + /* This shortcut is ok because we support only x2APIC MSRs so far. */ if (!nested_cpu_has_virt_x2apic_mode(vmcs12)) return false; @@ -9482,63 +9500,37 @@ static inline bool nested_vmx_merge_msr_bitmap(struct kvm_vcpu *vcpu, WARN_ON(1); return false; } - msr_bitmap = (unsigned long *)kmap(page); - if (!msr_bitmap) { + msr_bitmap_l1 = (unsigned long *)kmap(page); + if (!msr_bitmap_l1) { nested_release_page_clean(page); WARN_ON(1); return false; } + memset(msr_bitmap_l0, 0xff, PAGE_SIZE); + if (nested_cpu_has_virt_x2apic_mode(vmcs12)) { if (nested_cpu_has_apic_reg_virt(vmcs12)) for (msr = 0x800; msr <= 0x8ff; msr++) nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, msr, MSR_TYPE_R); - /* TPR is allowed */ - nested_vmx_disable_intercept_for_msr(msr_bitmap, - vmx_msr_bitmap_nested, + + nested_vmx_disable_intercept_for_msr( + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_TASKPRI >> 4), MSR_TYPE_R | MSR_TYPE_W); + if (nested_cpu_has_vid(vmcs12)) { - /* EOI and self-IPI are allowed */ nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_EOI >> 4), MSR_TYPE_W); nested_vmx_disable_intercept_for_msr( - msr_bitmap, - vmx_msr_bitmap_nested, + msr_bitmap_l1, msr_bitmap_l0, APIC_BASE_MSR + (APIC_SELF_IPI >> 4), MSR_TYPE_W); } - } else { - /* - * Enable reading intercept of all the x2apic - * MSRs. We should not rely on vmcs12 to do any - * optimizations here, it may have been modified - * by L1. - */ - for (msr = 0x800; msr <= 0x8ff; msr++) - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - msr, - MSR_TYPE_R); - - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_TASKPRI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_EOI >> 4), - MSR_TYPE_W); - __vmx_enable_intercept_for_msr( - vmx_msr_bitmap_nested, - APIC_BASE_MSR + (APIC_SELF_IPI >> 4), - MSR_TYPE_W); } kunmap(page); nested_release_page_clean(page); @@ -9957,10 +9949,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) } if (cpu_has_vmx_msr_bitmap() && - exec_control & CPU_BASED_USE_MSR_BITMAPS) { - nested_vmx_merge_msr_bitmap(vcpu, vmcs12); - /* MSR_BITMAP will be set by following vmx_set_efer. */ - } else + exec_control & CPU_BASED_USE_MSR_BITMAPS && + nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) + ; /* MSR_BITMAP will be set by following vmx_set_efer. */ + else exec_control &= ~CPU_BASED_USE_MSR_BITMAPS; /* @@ -10011,6 +10003,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); else vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); + if (kvm_has_tsc_control) + decache_tsc_multiplier(vmx); if (enable_vpid) { /* @@ -10767,6 +10761,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, else vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); + if (kvm_has_tsc_control) + decache_tsc_multiplier(vmx); + + if (vmx->nested.change_vmcs01_virtual_x2apic_mode) { + vmx->nested.change_vmcs01_virtual_x2apic_mode = false; + vmx_set_virtual_x2apic_mode(vcpu, + vcpu->arch.apic_base & X2APIC_ENABLE); + } /* This is needed for same reason as it was needed in prepare_vmcs02 */ vmx->host_rsp = 0; diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index 02de3d74d2c5..8a602a1e404a 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -35,6 +35,7 @@ ENDPROC(__sw_hweight32) ENTRY(__sw_hweight64) #ifdef CONFIG_X86_64 + pushq %rdi pushq %rdx movq %rdi, %rdx # w -> t @@ -60,6 +61,7 @@ ENTRY(__sw_hweight64) shrq $56, %rax # w = w_tmp >> 56 popq %rdx + popq %rdi ret #else /* CONFIG_X86_32 */ /* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */ diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index f7dfeda83e5c..121f59c6ee54 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -19,7 +19,7 @@ #include <asm/cpufeature.h> #include <asm/setup.h> -#define debug_putstr(v) early_printk(v) +#define debug_putstr(v) early_printk("%s", v) #define has_cpuflag(f) boot_cpu_has(f) #define get_boot_seed() kaslr_offset() #endif diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index ec21796ac5fd..4473cb4f8b90 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -3,15 +3,17 @@ * included by both the compressed kernel and the regular kernel. */ -static void ident_pmd_init(unsigned long pmd_flag, pmd_t *pmd_page, +static void ident_pmd_init(struct x86_mapping_info *info, pmd_t *pmd_page, unsigned long addr, unsigned long end) { addr &= PMD_MASK; for (; addr < end; addr += PMD_SIZE) { pmd_t *pmd = pmd_page + pmd_index(addr); - if (!pmd_present(*pmd)) - set_pmd(pmd, __pmd(addr | pmd_flag)); + if (pmd_present(*pmd)) + continue; + + set_pmd(pmd, __pmd((addr - info->offset) | info->pmd_flag)); } } @@ -30,13 +32,13 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, if (pud_present(*pud)) { pmd = pmd_offset(pud, 0); - ident_pmd_init(info->pmd_flag, pmd, addr, next); + ident_pmd_init(info, pmd, addr, next); continue; } pmd = (pmd_t *)info->alloc_pgt_page(info->context); if (!pmd) return -ENOMEM; - ident_pmd_init(info->pmd_flag, pmd, addr, next); + ident_pmd_init(info, pmd, addr, next); set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE)); } @@ -44,14 +46,15 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, } int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, - unsigned long addr, unsigned long end) + unsigned long pstart, unsigned long pend) { + unsigned long addr = pstart + info->offset; + unsigned long end = pend + info->offset; unsigned long next; int result; - int off = info->kernel_mapping ? pgd_index(__PAGE_OFFSET) : 0; for (; addr < end; addr = next) { - pgd_t *pgd = pgd_page + pgd_index(addr) + off; + pgd_t *pgd = pgd_page + pgd_index(addr); pud_t *pud; next = (addr & PGDIR_MASK) + PGDIR_SIZE; diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 620928903be3..d28a2d741f9e 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -122,8 +122,18 @@ __ref void *alloc_low_pages(unsigned int num) return __va(pfn << PAGE_SHIFT); } -/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */ -#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE) +/* + * By default need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS. + * With KASLR memory randomization, depending on the machine e820 memory + * and the PUD alignment. We may need twice more pages when KASLR memory + * randomization is enabled. + */ +#ifndef CONFIG_RANDOMIZE_MEMORY +#define INIT_PGD_PAGE_COUNT 6 +#else +#define INIT_PGD_PAGE_COUNT 12 +#endif +#define INIT_PGT_BUF_SIZE (INIT_PGD_PAGE_COUNT * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 26dccd6c0df1..bda8d5eef04d 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -77,7 +77,7 @@ static inline unsigned long get_padding(struct kaslr_memory_region *region) */ static inline bool kaslr_memory_enabled(void) { - return kaslr_enabled() && !config_enabled(CONFIG_KASAN); + return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN); } /* Initialize base and padding for each memory region randomized with KASLR */ @@ -97,7 +97,7 @@ void __init kernel_randomize_memory(void) * add padding if needed (especially for memory hotplug support). */ BUG_ON(kaslr_regions[0].base != &page_offset_base); - memory_tb = ((max_pfn << PAGE_SHIFT) >> TB_SHIFT) + + memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) + CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING; /* Adapt phyiscal memory region size based on available memory */ diff --git a/arch/x86/pci/vmd.c b/arch/x86/pci/vmd.c index b814ca675131..7948be342ee9 100644 --- a/arch/x86/pci/vmd.c +++ b/arch/x86/pci/vmd.c @@ -41,6 +41,7 @@ static DEFINE_RAW_SPINLOCK(list_lock); * @node: list item for parent traversal. * @rcu: RCU callback item for freeing. * @irq: back pointer to parent. + * @enabled: true if driver enabled IRQ * @virq: the virtual IRQ value provided to the requesting driver. * * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to @@ -50,6 +51,7 @@ struct vmd_irq { struct list_head node; struct rcu_head rcu; struct vmd_irq_list *irq; + bool enabled; unsigned int virq; }; @@ -122,7 +124,9 @@ static void vmd_irq_enable(struct irq_data *data) unsigned long flags; raw_spin_lock_irqsave(&list_lock, flags); + WARN_ON(vmdirq->enabled); list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); + vmdirq->enabled = true; raw_spin_unlock_irqrestore(&list_lock, flags); data->chip->irq_unmask(data); @@ -136,8 +140,10 @@ static void vmd_irq_disable(struct irq_data *data) data->chip->irq_mask(data); raw_spin_lock_irqsave(&list_lock, flags); - list_del_rcu(&vmdirq->node); - INIT_LIST_HEAD_RCU(&vmdirq->node); + if (vmdirq->enabled) { + list_del_rcu(&vmdirq->node); + vmdirq->enabled = false; + } raw_spin_unlock_irqrestore(&list_lock, flags); } diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 4480c06cade7..89d1146f5a6f 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -254,6 +254,7 @@ void __init efi_free_boot_services(void) for_each_efi_memory_desc(md) { unsigned long long start = md->phys_addr; unsigned long long size = md->num_pages << EFI_PAGE_SHIFT; + size_t rm_size; if (md->type != EFI_BOOT_SERVICES_CODE && md->type != EFI_BOOT_SERVICES_DATA) @@ -263,6 +264,26 @@ void __init efi_free_boot_services(void) if (md->attribute & EFI_MEMORY_RUNTIME) continue; + /* + * Nasty quirk: if all sub-1MB memory is used for boot + * services, we can get here without having allocated the + * real mode trampoline. It's too late to hand boot services + * memory back to the memblock allocator, so instead + * try to manually allocate the trampoline if needed. + * + * I've seen this on a Dell XPS 13 9350 with firmware + * 1.4.4 with SGX enabled booting Linux via Fedora 24's + * grub2-efi on a hard disk. (And no, I don't know why + * this happened, but Linux should still try to boot rather + * panicing early.) + */ + rm_size = real_mode_size_needed(); + if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) { + set_real_mode_mem(start, rm_size); + start += rm_size; + size -= rm_size; + } + free_bootmem_late(start, size); } diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 66b2166ea4a1..23f2f3e41c7f 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -187,7 +187,8 @@ EXPORT_SYMBOL_GPL(uv_bios_set_legacy_vga_target); void uv_bios_init(void) { uv_systab = NULL; - if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab) { + if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || + !efi.uv_systab || efi_runtime_disabled()) { pr_crit("UV: UVsystab: missing\n"); return; } @@ -199,12 +200,14 @@ void uv_bios_init(void) return; } + /* Starting with UV4 the UV systab size is variable */ if (uv_systab->revision >= UV_SYSTAB_VERSION_UV4) { + int size = uv_systab->size; + iounmap(uv_systab); - uv_systab = ioremap(efi.uv_systab, uv_systab->size); + uv_systab = ioremap(efi.uv_systab, size); if (!uv_systab) { - pr_err("UV: UVsystab: ioremap(%d) failed!\n", - uv_systab->size); + pr_err("UV: UVsystab: ioremap(%d) failed!\n", size); return; } } diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index f0b5f2d402af..9634557a5444 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -87,7 +87,7 @@ static int set_up_temporary_mappings(void) struct x86_mapping_info info = { .alloc_pgt_page = alloc_pgt_page, .pmd_flag = __PAGE_KERNEL_LARGE_EXEC, - .kernel_mapping = true, + .offset = __PAGE_OFFSET, }; unsigned long mstart, mend; pgd_t *pgd; @@ -113,7 +113,7 @@ static int set_up_temporary_mappings(void) return result; } - temp_level4_pgt = (unsigned long)pgd - __PAGE_OFFSET; + temp_level4_pgt = __pa(pgd); return 0; } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 705e3fffb4a1..5db706f14111 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -1,9 +1,11 @@ #include <linux/io.h> +#include <linux/slab.h> #include <linux/memblock.h> #include <asm/cacheflush.h> #include <asm/pgtable.h> #include <asm/realmode.h> +#include <asm/tlbflush.h> struct real_mode_header *real_mode_header; u32 *trampoline_cr4_features; @@ -11,25 +13,37 @@ u32 *trampoline_cr4_features; /* Hold the pgd entry used on booting additional CPUs */ pgd_t trampoline_pgd_entry; +void __init set_real_mode_mem(phys_addr_t mem, size_t size) +{ + void *base = __va(mem); + + real_mode_header = (struct real_mode_header *) base; + printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", + base, (unsigned long long)mem, size); +} + void __init reserve_real_mode(void) { phys_addr_t mem; - unsigned char *base; - size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); + size_t size = real_mode_size_needed(); + + if (!size) + return; + + WARN_ON(slab_is_available()); /* Has to be under 1M so we can execute real-mode AP code. */ mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); - if (!mem) - panic("Cannot allocate trampoline\n"); + if (!mem) { + pr_info("No sub-1M memory is available for the trampoline\n"); + return; + } - base = __va(mem); memblock_reserve(mem, size); - real_mode_header = (struct real_mode_header *) base; - printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", - base, (unsigned long long)mem, size); + set_real_mode_mem(mem, size); } -void __init setup_real_mode(void) +static void __init setup_real_mode(void) { u16 real_mode_seg; const u32 *rel; @@ -84,7 +98,7 @@ void __init setup_real_mode(void) trampoline_header->start = (u64) secondary_startup_64; trampoline_cr4_features = &trampoline_header->cr4; - *trampoline_cr4_features = __read_cr4(); + *trampoline_cr4_features = mmu_cr4_features; trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); trampoline_pgd[0] = trampoline_pgd_entry.pgd; @@ -100,7 +114,7 @@ void __init setup_real_mode(void) * need to mark it executable at do_pre_smp_initcalls() at least, * thus run it as a early_initcall(). */ -static int __init set_real_mode_permissions(void) +static void __init set_real_mode_permissions(void) { unsigned char *base = (unsigned char *) real_mode_header; size_t size = PAGE_ALIGN(real_mode_blob_end - real_mode_blob); @@ -119,7 +133,16 @@ static int __init set_real_mode_permissions(void) set_memory_nx((unsigned long) base, size >> PAGE_SHIFT); set_memory_ro((unsigned long) base, ro_size >> PAGE_SHIFT); set_memory_x((unsigned long) text_start, text_size >> PAGE_SHIFT); +} + +static int __init init_real_mode(void) +{ + if (!real_mode_header) + panic("Real mode trampoline was not allocated"); + + setup_real_mode(); + set_real_mode_permissions(); return 0; } -early_initcall(set_real_mode_permissions); +early_initcall(init_real_mode); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 8ffb089b19a5..b86ebb1a9a7f 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -118,7 +118,7 @@ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); /* Linux <-> Xen vCPU id mapping */ -DEFINE_PER_CPU(int, xen_vcpu_id) = -1; +DEFINE_PER_CPU(uint32_t, xen_vcpu_id); EXPORT_PER_CPU_SYMBOL(xen_vcpu_id); enum xen_domain_type xen_domain_type = XEN_NATIVE; diff --git a/block/bio.c b/block/bio.c index f39477538fef..aa7354088008 100644 --- a/block/bio.c +++ b/block/bio.c @@ -667,18 +667,19 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - if (bio_op(bio) == REQ_OP_DISCARD) - goto integrity_clone; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + break; + case REQ_OP_WRITE_SAME: bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; - goto integrity_clone; + break; + default: + bio_for_each_segment(bv, bio_src, iter) + bio->bi_io_vec[bio->bi_vcnt++] = bv; + break; } - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - -integrity_clone: if (bio_integrity(bio_src)) { int ret; @@ -1788,7 +1789,7 @@ struct bio *bio_split(struct bio *bio, int sectors, * Discards need a mutable bio_vec to accommodate the payload * required by the DSM TRIM and UNMAP commands. */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) split = bio_clone_bioset(bio, gfp, bs); else split = bio_clone_fast(bio, gfp, bs); diff --git a/block/blk-core.c b/block/blk-core.c index 999442ec4601..36c7ac328d8c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -515,7 +515,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end); void blk_set_queue_dying(struct request_queue *q) { - queue_flag_set_unlocked(QUEUE_FLAG_DYING, q); + spin_lock_irq(q->queue_lock); + queue_flag_set(QUEUE_FLAG_DYING, q); + spin_unlock_irq(q->queue_lock); if (q->mq_ops) blk_mq_wake_waiters(q); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3eec75a9e91d..2642e5fc8b69 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -94,9 +94,31 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, bool do_split = true; struct bio *new = NULL; const unsigned max_sectors = get_max_io_size(q, bio); + unsigned bvecs = 0; bio_for_each_segment(bv, bio, iter) { /* + * With arbitrary bio size, the incoming bio may be very + * big. We have to split the bio into small bios so that + * each holds at most BIO_MAX_PAGES bvecs because + * bio_clone() can fail to allocate big bvecs. + * + * It should have been better to apply the limit per + * request queue in which bio_clone() is involved, + * instead of globally. The biggest blocker is the + * bio_clone() in bio bounce. + * + * If bio is splitted by this reason, we should have + * allowed to continue bios merging, but don't do + * that now for making the change simple. + * + * TODO: deal with bio bounce's bio_clone() gracefully + * and convert the global limit into per-queue limit. + */ + if (bvecs++ >= BIO_MAX_PAGES) + goto split; + + /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ @@ -172,12 +194,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, struct bio *split, *res; unsigned nsegs; - if (bio_op(*bio) == REQ_OP_DISCARD) + switch (bio_op(*bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, bs, &nsegs); - else if (bio_op(*bio) == REQ_OP_WRITE_SAME) + break; + case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, bs, &nsegs); - else + break; + default: split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); + break; + } /* physical segments can be figured out during splitting */ res = split ? split : *bio; @@ -213,7 +241,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, * This should probably be returning 0, but blk_add_request_payload() * (Christoph!!!!) */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) return 1; if (bio_op(bio) == REQ_OP_WRITE_SAME) @@ -385,7 +413,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, nsegs = 0; cluster = blk_queue_cluster(q); - if (bio_op(bio) == REQ_OP_DISCARD) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: /* * This is a hack - drivers should be neither modifying the * biovec, nor relying on bi_vcnt - but because of @@ -393,19 +423,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, * a payload we need to set up here (thank you Christoph) and * bi_vcnt is really the only way of telling if we need to. */ - - if (bio->bi_vcnt) - goto single_segment; - - return 0; - } - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { -single_segment: + if (!bio->bi_vcnt) + return 0; + /* Fall through */ + case REQ_OP_WRITE_SAME: *sg = sglist; bvec = bio_iovec(bio); sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); return 1; + default: + break; } for_each_bio(bio) diff --git a/block/blk-mq.c b/block/blk-mq.c index e931a0e8e73d..13f5a6c1de76 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -793,11 +793,12 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) struct list_head *dptr; int queued; - WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)); - if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return; + WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) && + cpu_online(hctx->next_cpu)); + hctx->run++; /* @@ -1036,10 +1037,11 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) EXPORT_SYMBOL(blk_mq_delay_queue); static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, - struct blk_mq_ctx *ctx, struct request *rq, bool at_head) { + struct blk_mq_ctx *ctx = rq->mq_ctx; + trace_block_rq_insert(hctx->queue, rq); if (at_head) @@ -1053,20 +1055,16 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, { struct blk_mq_ctx *ctx = rq->mq_ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, at_head); + __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, - bool async) + bool async) { + struct blk_mq_ctx *ctx = rq->mq_ctx; struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx; - - current_ctx = blk_mq_get_ctx(q); - if (!cpu_online(ctx->cpu)) - rq->mq_ctx = ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); @@ -1076,8 +1074,6 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, if (run_queue) blk_mq_run_hw_queue(hctx, async); - - blk_mq_put_ctx(current_ctx); } static void blk_mq_insert_requests(struct request_queue *q, @@ -1088,14 +1084,9 @@ static void blk_mq_insert_requests(struct request_queue *q, { struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *current_ctx; trace_block_unplug(q, depth, !from_schedule); - current_ctx = blk_mq_get_ctx(q); - - if (!cpu_online(ctx->cpu)) - ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); /* @@ -1107,15 +1098,14 @@ static void blk_mq_insert_requests(struct request_queue *q, struct request *rq; rq = list_first_entry(list, struct request, queuelist); + BUG_ON(rq->mq_ctx != ctx); list_del_init(&rq->queuelist); - rq->mq_ctx = ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, false); + __blk_mq_insert_req_list(hctx, rq, false); } blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); blk_mq_run_hw_queue(hctx, from_schedule); - blk_mq_put_ctx(current_ctx); } static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b) @@ -1630,16 +1620,17 @@ static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node) return 0; } +/* + * 'cpu' is going away. splice any existing rq_list entries from this + * software queue to the hw queue dispatch list, and ensure that it + * gets run. + */ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) { - struct request_queue *q = hctx->queue; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); - /* - * Move ctx entries to new CPU, if this one is going away. - */ - ctx = __blk_mq_get_ctx(q, cpu); + ctx = __blk_mq_get_ctx(hctx->queue, cpu); spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_list)) { @@ -1651,24 +1642,11 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) if (list_empty(&tmp)) return NOTIFY_OK; - ctx = blk_mq_get_ctx(q); - spin_lock(&ctx->lock); - - while (!list_empty(&tmp)) { - struct request *rq; - - rq = list_first_entry(&tmp, struct request, queuelist); - rq->mq_ctx = ctx; - list_move_tail(&rq->queuelist, &ctx->rq_list); - } - - hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_hctx_mark_pending(hctx, ctx); - - spin_unlock(&ctx->lock); + spin_lock(&hctx->lock); + list_splice_tail_init(&tmp, &hctx->dispatch); + spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); - blk_mq_put_ctx(ctx); return NOTIFY_OK; } diff --git a/block/elevator.c b/block/elevator.c index 7096c22041e7..f7d973a56fd7 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -366,7 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); - if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD)) + if (req_op(rq) != req_op(pos)) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; diff --git a/crypto/Kconfig b/crypto/Kconfig index a9377bef25e3..84d71482bf08 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -439,7 +439,7 @@ config CRYPTO_CRC32C_INTEL config CRYPT_CRC32C_VPMSUM tristate "CRC32c CRC algorithm (powerpc64)" - depends on PPC64 + depends on PPC64 && ALTIVEC select CRYPTO_HASH select CRC32 help diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c index 62264397a2d2..7e8ed96236ce 100644 --- a/crypto/sha3_generic.c +++ b/crypto/sha3_generic.c @@ -24,14 +24,14 @@ #define ROTL64(x, y) (((x) << (y)) | ((x) >> (64 - (y)))) static const u64 keccakf_rndc[24] = { - 0x0000000000000001, 0x0000000000008082, 0x800000000000808a, - 0x8000000080008000, 0x000000000000808b, 0x0000000080000001, - 0x8000000080008081, 0x8000000000008009, 0x000000000000008a, - 0x0000000000000088, 0x0000000080008009, 0x000000008000000a, - 0x000000008000808b, 0x800000000000008b, 0x8000000000008089, - 0x8000000000008003, 0x8000000000008002, 0x8000000000000080, - 0x000000000000800a, 0x800000008000000a, 0x8000000080008081, - 0x8000000000008080, 0x0000000080000001, 0x8000000080008008 + 0x0000000000000001ULL, 0x0000000000008082ULL, 0x800000000000808aULL, + 0x8000000080008000ULL, 0x000000000000808bULL, 0x0000000080000001ULL, + 0x8000000080008081ULL, 0x8000000000008009ULL, 0x000000000000008aULL, + 0x0000000000000088ULL, 0x0000000080008009ULL, 0x000000008000000aULL, + 0x000000008000808bULL, 0x800000000000008bULL, 0x8000000000008089ULL, + 0x8000000000008003ULL, 0x8000000000008002ULL, 0x8000000000000080ULL, + 0x000000000000800aULL, 0x800000008000000aULL, 0x8000000080008081ULL, + 0x8000000000008080ULL, 0x0000000080000001ULL, 0x8000000080008008ULL }; static const int keccakf_rotc[24] = { diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index 8c234dd9b8bc..80cc7c089a15 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -1527,11 +1527,12 @@ static u32 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw) { struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR]; u64 offset = nfit_blk->stat_offset + mmio->size * bw; + const u32 STATUS_MASK = 0x80000037; if (mmio->num_lines) offset = to_interleave_offset(offset, mmio); - return readl(mmio->addr.base + offset); + return readl(mmio->addr.base + offset) & STATUS_MASK; } static void write_blk_ctl(struct nfit_blk *nfit_blk, unsigned int bw, diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index b71a9c767009..e3d8e4ced4a2 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3706,22 +3706,21 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) if (UFDCS->rawcmd == 1) UFDCS->rawcmd = 2; - if (mode & (FMODE_READ|FMODE_WRITE)) { - UDRS->last_checked = 0; - clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); - check_disk_change(bdev); - if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) - goto out; - if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + if (!(mode & FMODE_NDELAY)) { + if (mode & (FMODE_READ|FMODE_WRITE)) { + UDRS->last_checked = 0; + clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); + check_disk_change(bdev); + if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) + goto out; + if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + goto out; + } + res = -EROFS; + if ((mode & FMODE_WRITE) && + !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) goto out; } - - res = -EROFS; - - if ((mode & FMODE_WRITE) && - !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) - goto out; - mutex_unlock(&open_lock); mutex_unlock(&floppy_mutex); return 0; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 1a04af6d2421..6c6519f6492a 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3950,6 +3950,7 @@ static void rbd_dev_release(struct device *dev) bool need_put = !!rbd_dev->opts; ceph_oid_destroy(&rbd_dev->header_oid); + ceph_oloc_destroy(&rbd_dev->header_oloc); rbd_put_client(rbd_dev->rbd_client); rbd_spec_put(rbd_dev->spec); @@ -5336,15 +5337,6 @@ static ssize_t do_rbd_add(struct bus_type *bus, } spec->pool_id = (u64)rc; - /* The ceph file layout needs to fit pool id in 32 bits */ - - if (spec->pool_id > (u64)U32_MAX) { - rbd_warn(NULL, "pool id too large (%llu > %u)", - (unsigned long long)spec->pool_id, U32_MAX); - rc = -EIO; - goto err_out_client; - } - rbd_dev = rbd_dev_create(rbdc, spec, rbd_opts); if (!rbd_dev) { rc = -ENOMEM; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 1523e05c46fc..93b1aaa5ba3b 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -391,22 +391,16 @@ static int init_vq(struct virtio_blk *vblk) num_vqs = 1; vblk->vqs = kmalloc(sizeof(*vblk->vqs) * num_vqs, GFP_KERNEL); - if (!vblk->vqs) { - err = -ENOMEM; - goto out; - } + if (!vblk->vqs) + return -ENOMEM; names = kmalloc(sizeof(*names) * num_vqs, GFP_KERNEL); - if (!names) - goto err_names; - callbacks = kmalloc(sizeof(*callbacks) * num_vqs, GFP_KERNEL); - if (!callbacks) - goto err_callbacks; - vqs = kmalloc(sizeof(*vqs) * num_vqs, GFP_KERNEL); - if (!vqs) - goto err_vqs; + if (!names || !callbacks || !vqs) { + err = -ENOMEM; + goto out; + } for (i = 0; i < num_vqs; i++) { callbacks[i] = virtblk_done; @@ -417,7 +411,7 @@ static int init_vq(struct virtio_blk *vblk) /* Discover virtqueues and write information to configuration. */ err = vdev->config->find_vqs(vdev, num_vqs, vqs, callbacks, names); if (err) - goto err_find_vqs; + goto out; for (i = 0; i < num_vqs; i++) { spin_lock_init(&vblk->vqs[i].lock); @@ -425,16 +419,12 @@ static int init_vq(struct virtio_blk *vblk) } vblk->num_vqs = num_vqs; - err_find_vqs: +out: kfree(vqs); - err_vqs: kfree(callbacks); - err_callbacks: kfree(names); - err_names: if (err) kfree(vblk->vqs); - out: return err; } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index be4fea6a5dd3..88ef6d4729b4 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -189,6 +189,8 @@ struct blkfront_info struct mutex mutex; struct xenbus_device *xbdev; struct gendisk *gd; + u16 sector_size; + unsigned int physical_sector_size; int vdevice; blkif_vdev_t handle; enum blkif_state connected; @@ -910,9 +912,45 @@ static struct blk_mq_ops blkfront_mq_ops = { .map_queue = blk_mq_map_queue, }; +static void blkif_set_queue_limits(struct blkfront_info *info) +{ + struct request_queue *rq = info->rq; + struct gendisk *gd = info->gd; + unsigned int segments = info->max_indirect_segments ? : + BLKIF_MAX_SEGMENTS_PER_REQUEST; + + queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); + + if (info->feature_discard) { + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq); + blk_queue_max_discard_sectors(rq, get_capacity(gd)); + rq->limits.discard_granularity = info->discard_granularity; + rq->limits.discard_alignment = info->discard_alignment; + if (info->feature_secdiscard) + queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq); + } + + /* Hard sector size and max sectors impersonate the equiv. hardware. */ + blk_queue_logical_block_size(rq, info->sector_size); + blk_queue_physical_block_size(rq, info->physical_sector_size); + blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512); + + /* Each segment in a request is up to an aligned page in size. */ + blk_queue_segment_boundary(rq, PAGE_SIZE - 1); + blk_queue_max_segment_size(rq, PAGE_SIZE); + + /* Ensure a merged request will fit in a single I/O ring slot. */ + blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG); + + /* Make sure buffer addresses are sector-aligned. */ + blk_queue_dma_alignment(rq, 511); + + /* Make sure we don't use bounce buffers. */ + blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); +} + static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, - unsigned int physical_sector_size, - unsigned int segments) + unsigned int physical_sector_size) { struct request_queue *rq; struct blkfront_info *info = gd->private_data; @@ -944,36 +982,11 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, } rq->queuedata = info; - queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq); - - if (info->feature_discard) { - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq); - blk_queue_max_discard_sectors(rq, get_capacity(gd)); - rq->limits.discard_granularity = info->discard_granularity; - rq->limits.discard_alignment = info->discard_alignment; - if (info->feature_secdiscard) - queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, rq); - } - - /* Hard sector size and max sectors impersonate the equiv. hardware. */ - blk_queue_logical_block_size(rq, sector_size); - blk_queue_physical_block_size(rq, physical_sector_size); - blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512); - - /* Each segment in a request is up to an aligned page in size. */ - blk_queue_segment_boundary(rq, PAGE_SIZE - 1); - blk_queue_max_segment_size(rq, PAGE_SIZE); - - /* Ensure a merged request will fit in a single I/O ring slot. */ - blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG); - - /* Make sure buffer addresses are sector-aligned. */ - blk_queue_dma_alignment(rq, 511); - - /* Make sure we don't use bounce buffers. */ - blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY); - - gd->queue = rq; + info->rq = gd->queue = rq; + info->gd = gd; + info->sector_size = sector_size; + info->physical_sector_size = physical_sector_size; + blkif_set_queue_limits(info); return 0; } @@ -1136,16 +1149,11 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, gd->private_data = info; set_capacity(gd, capacity); - if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size, - info->max_indirect_segments ? : - BLKIF_MAX_SEGMENTS_PER_REQUEST)) { + if (xlvbd_init_blk_queue(gd, sector_size, physical_sector_size)) { del_gendisk(gd); goto release; } - info->rq = gd->queue; - info->gd = gd; - xlvbd_flush(info); if (vdisk_info & VDISK_READONLY) @@ -1315,7 +1323,7 @@ free_shadow: rinfo->ring_ref[i] = GRANT_INVALID_REF; } } - free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * PAGE_SIZE)); + free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE)); rinfo->ring.sring = NULL; if (rinfo->irq) @@ -2007,8 +2015,10 @@ static int blkif_recover(struct blkfront_info *info) struct split_bio *split_bio; blkfront_gather_backend_features(info); + /* Reset limits changed by blk_mq_update_nr_hw_queues(). */ + blkif_set_queue_limits(info); segs = info->max_indirect_segments ? : BLKIF_MAX_SEGMENTS_PER_REQUEST; - blk_queue_max_segments(info->rq, segs); + blk_queue_max_segments(info->rq, segs / GRANTS_PER_PSEG); for (r_index = 0; r_index < info->nr_rings; r_index++) { struct blkfront_ring_info *rinfo = &info->rinfo[r_index]; @@ -2432,7 +2442,7 @@ static void blkfront_connect(struct blkfront_info *info) if (err) { xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s", info->xbdev->otherend); - return; + goto fail; } xenbus_switch_state(info->xbdev, XenbusStateConnected); @@ -2445,6 +2455,11 @@ static void blkfront_connect(struct blkfront_info *info) device_add_disk(&info->xbdev->dev, info->gd); info->is_ready = 1; + return; + +fail: + blkif_free(info, 0); + return; } /** diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 28bce3f4f81d..57700541f951 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -8,6 +8,9 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + +#define pr_fmt(fmt) "arm_arch_timer: " fmt + #include <linux/init.h> #include <linux/kernel.h> #include <linux/device.h> @@ -370,16 +373,33 @@ static bool arch_timer_has_nonsecure_ppi(void) arch_timer_ppi[PHYS_NONSECURE_PPI]); } +static u32 check_ppi_trigger(int irq) +{ + u32 flags = irq_get_trigger_type(irq); + + if (flags != IRQF_TRIGGER_HIGH && flags != IRQF_TRIGGER_LOW) { + pr_warn("WARNING: Invalid trigger for IRQ%d, assuming level low\n", irq); + pr_warn("WARNING: Please fix your firmware\n"); + flags = IRQF_TRIGGER_LOW; + } + + return flags; +} + static int arch_timer_starting_cpu(unsigned int cpu) { struct clock_event_device *clk = this_cpu_ptr(arch_timer_evt); + u32 flags; __arch_timer_setup(ARCH_CP15_TIMER, clk); - enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], 0); + flags = check_ppi_trigger(arch_timer_ppi[arch_timer_uses_ppi]); + enable_percpu_irq(arch_timer_ppi[arch_timer_uses_ppi], flags); - if (arch_timer_has_nonsecure_ppi()) - enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], 0); + if (arch_timer_has_nonsecure_ppi()) { + flags = check_ppi_trigger(arch_timer_ppi[PHYS_NONSECURE_PPI]); + enable_percpu_irq(arch_timer_ppi[PHYS_NONSECURE_PPI], flags); + } arch_counter_set_user_access(); if (evtstrm_enable) diff --git a/drivers/clocksource/bcm_kona_timer.c b/drivers/clocksource/bcm_kona_timer.c index 7e3fd375a627..92f6e4deee74 100644 --- a/drivers/clocksource/bcm_kona_timer.c +++ b/drivers/clocksource/bcm_kona_timer.c @@ -66,10 +66,10 @@ static void kona_timer_disable_and_clear(void __iomem *base) } -static void +static int kona_timer_get_counter(void __iomem *timer_base, uint32_t *msw, uint32_t *lsw) { - int loop_limit = 4; + int loop_limit = 3; /* * Read 64-bit free running counter @@ -83,18 +83,19 @@ kona_timer_get_counter(void __iomem *timer_base, uint32_t *msw, uint32_t *lsw) * if new hi-word is equal to previously read hi-word then stop. */ - while (--loop_limit) { + do { *msw = readl(timer_base + KONA_GPTIMER_STCHI_OFFSET); *lsw = readl(timer_base + KONA_GPTIMER_STCLO_OFFSET); if (*msw == readl(timer_base + KONA_GPTIMER_STCHI_OFFSET)) break; - } + } while (--loop_limit); if (!loop_limit) { pr_err("bcm_kona_timer: getting counter failed.\n"); pr_err(" Timer will be impacted\n"); + return -ETIMEDOUT; } - return; + return 0; } static int kona_timer_set_next_event(unsigned long clc, @@ -112,8 +113,11 @@ static int kona_timer_set_next_event(unsigned long clc, uint32_t lsw, msw; uint32_t reg; + int ret; - kona_timer_get_counter(timers.tmr_regs, &msw, &lsw); + ret = kona_timer_get_counter(timers.tmr_regs, &msw, &lsw); + if (ret) + return ret; /* Load the "next" event tick value */ writel(lsw + clc, timers.tmr_regs + KONA_GPTIMER_STCM0_OFFSET); diff --git a/drivers/clocksource/mips-gic-timer.c b/drivers/clocksource/mips-gic-timer.c index d91e8725917c..b4b3ab5a11ad 100644 --- a/drivers/clocksource/mips-gic-timer.c +++ b/drivers/clocksource/mips-gic-timer.c @@ -164,7 +164,7 @@ void __init gic_clocksource_init(unsigned int frequency) gic_start_count(); } -static void __init gic_clocksource_of_init(struct device_node *node) +static int __init gic_clocksource_of_init(struct device_node *node) { struct clk *clk; int ret; diff --git a/drivers/clocksource/pxa_timer.c b/drivers/clocksource/pxa_timer.c index 937e10b84d58..3e1cb512f3ce 100644 --- a/drivers/clocksource/pxa_timer.c +++ b/drivers/clocksource/pxa_timer.c @@ -21,6 +21,8 @@ #include <linux/of_irq.h> #include <linux/sched_clock.h> +#include <clocksource/pxa.h> + #include <asm/div64.h> #define OSMR0 0x00 /* OS Timer 0 Match Register */ diff --git a/drivers/clocksource/sun4i_timer.c b/drivers/clocksource/sun4i_timer.c index 97669ee4df2a..c83452cacb41 100644 --- a/drivers/clocksource/sun4i_timer.c +++ b/drivers/clocksource/sun4i_timer.c @@ -123,12 +123,16 @@ static struct clock_event_device sun4i_clockevent = { .set_next_event = sun4i_clkevt_next_event, }; +static void sun4i_timer_clear_interrupt(void) +{ + writel(TIMER_IRQ_EN(0), timer_base + TIMER_IRQ_ST_REG); +} static irqreturn_t sun4i_timer_interrupt(int irq, void *dev_id) { struct clock_event_device *evt = (struct clock_event_device *)dev_id; - writel(0x1, timer_base + TIMER_IRQ_ST_REG); + sun4i_timer_clear_interrupt(); evt->event_handler(evt); return IRQ_HANDLED; @@ -208,6 +212,9 @@ static int __init sun4i_timer_init(struct device_node *node) /* Make sure timer is stopped before playing with interrupts */ sun4i_clkevt_time_stop(0); + /* clear timer0 interrupt */ + sun4i_timer_clear_interrupt(); + sun4i_clockevent.cpumask = cpu_possible_mask; sun4i_clockevent.irq = irq; diff --git a/drivers/clocksource/time-armada-370-xp.c b/drivers/clocksource/time-armada-370-xp.c index 719b478d136e..3c39e6f45971 100644 --- a/drivers/clocksource/time-armada-370-xp.c +++ b/drivers/clocksource/time-armada-370-xp.c @@ -338,7 +338,6 @@ static int __init armada_xp_timer_init(struct device_node *np) struct clk *clk = of_clk_get_by_name(np, "fixed"); int ret; - clk = of_clk_get(np, 0); if (IS_ERR(clk)) { pr_err("Failed to get clock"); return PTR_ERR(clk); diff --git a/drivers/clocksource/time-pistachio.c b/drivers/clocksource/time-pistachio.c index a7d9a08e4b0e..a8e6c7df853d 100644 --- a/drivers/clocksource/time-pistachio.c +++ b/drivers/clocksource/time-pistachio.c @@ -202,10 +202,10 @@ static int __init pistachio_clksrc_of_init(struct device_node *node) rate = clk_get_rate(fast_clk); /* Disable irq's for clocksource usage */ - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 0); - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 1); - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 2); - gpt_writel(&pcs_gpt.base, 0, TIMER_IRQ_MASK, 3); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 0); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 1); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 2); + gpt_writel(pcs_gpt.base, 0, TIMER_IRQ_MASK, 3); /* Enable timer block */ writel(TIMER_ME_GLOBAL, pcs_gpt.base); diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c index 1ffac0cb0cb7..3494bc5a21d5 100644 --- a/drivers/clocksource/timer-atmel-pit.c +++ b/drivers/clocksource/timer-atmel-pit.c @@ -261,6 +261,12 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node) return PTR_ERR(data->mck); } + ret = clk_prepare_enable(data->mck); + if (ret) { + pr_err("Unable to enable mck\n"); + return ret; + } + /* Get the interrupts property */ data->irq = irq_of_parse_and_map(node, 0); if (!data->irq) { diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 87796e0864e9..d3ffde806629 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -145,11 +145,30 @@ static struct powernv_pstate_info { /* Use following macros for conversions between pstate_id and index */ static inline int idx_to_pstate(unsigned int i) { + if (unlikely(i >= powernv_pstate_info.nr_pstates)) { + pr_warn_once("index %u is out of bound\n", i); + return powernv_freqs[powernv_pstate_info.nominal].driver_data; + } + return powernv_freqs[i].driver_data; } static inline unsigned int pstate_to_idx(int pstate) { + int min = powernv_freqs[powernv_pstate_info.min].driver_data; + int max = powernv_freqs[powernv_pstate_info.max].driver_data; + + if (min > 0) { + if (unlikely((pstate < max) || (pstate > min))) { + pr_warn_once("pstate %d is out of bound\n", pstate); + return powernv_pstate_info.nominal; + } + } else { + if (unlikely((pstate > max) || (pstate < min))) { + pr_warn_once("pstate %d is out of bound\n", pstate); + return powernv_pstate_info.nominal; + } + } /* * abs() is deliberately used so that is works with * both monotonically increasing and decreasing @@ -593,7 +612,7 @@ void gpstate_timer_handler(unsigned long data) } else { gpstate_idx = calc_global_pstate(gpstates->elapsed_time, gpstates->highest_lpstate_idx, - freq_data.pstate_id); + gpstates->last_lpstate_idx); } /* diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c index ea8189f4b021..6dc597126b79 100644 --- a/drivers/crypto/caam/caamalg.c +++ b/drivers/crypto/caam/caamalg.c @@ -441,6 +441,9 @@ static int aead_set_sh_desc(struct crypto_aead *aead) OP_ALG_AAI_CTR_MOD128); const bool is_rfc3686 = alg->caam.rfc3686; + if (!ctx->authsize) + return 0; + /* NULL encryption / decryption */ if (!ctx->enckeylen) return aead_null_set_sh_desc(aead); @@ -614,7 +617,7 @@ skip_enc: keys_fit_inline = true; /* aead_givencrypt shared descriptor */ - desc = ctx->sh_desc_givenc; + desc = ctx->sh_desc_enc; /* Note: Context registers are saved. */ init_sh_desc_key_aead(desc, ctx, keys_fit_inline, is_rfc3686); @@ -645,13 +648,13 @@ copy_iv: append_operation(desc, ctx->class2_alg_type | OP_ALG_AS_INITFINAL | OP_ALG_ENCRYPT); - /* ivsize + cryptlen = seqoutlen - authsize */ - append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize); - /* Read and write assoclen bytes */ append_math_add(desc, VARSEQINLEN, ZERO, REG3, CAAM_CMD_SZ); append_math_add(desc, VARSEQOUTLEN, ZERO, REG3, CAAM_CMD_SZ); + /* ivsize + cryptlen = seqoutlen - authsize */ + append_math_sub_imm_u32(desc, REG3, SEQOUTLEN, IMM, ctx->authsize); + /* Skip assoc data */ append_seq_fifo_store(desc, 0, FIFOST_TYPE_SKIP | FIFOLDST_VLF); @@ -697,7 +700,7 @@ copy_iv: ctx->sh_desc_enc_dma = dma_map_single(jrdev, desc, desc_bytes(desc), DMA_TO_DEVICE); - if (dma_mapping_error(jrdev, ctx->sh_desc_givenc_dma)) { + if (dma_mapping_error(jrdev, ctx->sh_desc_enc_dma)) { dev_err(jrdev, "unable to map shared descriptor\n"); return -ENOMEM; } diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c index f1ecc8df8d41..36365b3efdfd 100644 --- a/drivers/crypto/caam/caamhash.c +++ b/drivers/crypto/caam/caamhash.c @@ -1898,6 +1898,7 @@ caam_hash_alloc(struct caam_hash_template *template, template->name); snprintf(alg->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s", template->driver_name); + t_alg->ahash_alg.setkey = NULL; } alg->cra_module = THIS_MODULE; alg->cra_init = caam_hash_cra_init; diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c index dfb168568af1..1f01e98c83c7 100644 --- a/drivers/dax/pmem.c +++ b/drivers/dax/pmem.c @@ -116,6 +116,9 @@ static int dax_pmem_probe(struct device *dev) if (rc) return rc; + /* adjust the dax_region resource to the start of data */ + res.start += le64_to_cpu(pfn_sb->dataoff); + nd_region = to_nd_region(dev->parent); dax_region = alloc_dax_region(dev, nd_region->id, &res, le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP); diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig index d0c1dab9b435..dff1a4a6dc1b 100644 --- a/drivers/edac/Kconfig +++ b/drivers/edac/Kconfig @@ -251,6 +251,14 @@ config EDAC_SBRIDGE Support for error detection and correction the Intel Sandy Bridge, Ivy Bridge and Haswell Integrated Memory Controllers. +config EDAC_SKX + tristate "Intel Skylake server Integrated MC" + depends on EDAC_MM_EDAC && PCI && X86_64 && X86_MCE_INTEL + depends on PCI_MMCONFIG + help + Support for error detection and correction the Intel + Skylake server Integrated Memory Controllers. + config EDAC_MPC85XX tristate "Freescale MPC83xx / MPC85xx" depends on EDAC_MM_EDAC && FSL_SOC diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index f9e4a3e0e6e9..986049925b08 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -31,6 +31,7 @@ obj-$(CONFIG_EDAC_I5400) += i5400_edac.o obj-$(CONFIG_EDAC_I7300) += i7300_edac.o obj-$(CONFIG_EDAC_I7CORE) += i7core_edac.o obj-$(CONFIG_EDAC_SBRIDGE) += sb_edac.o +obj-$(CONFIG_EDAC_SKX) += skx_edac.o obj-$(CONFIG_EDAC_E7XXX) += e7xxx_edac.o obj-$(CONFIG_EDAC_E752X) += e752x_edac.o obj-$(CONFIG_EDAC_I82443BXGX) += i82443bxgx_edac.o diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c index 4fb2eb7c800d..ce0067b7a2f6 100644 --- a/drivers/edac/sb_edac.c +++ b/drivers/edac/sb_edac.c @@ -552,9 +552,9 @@ static const struct pci_id_table pci_dev_descr_haswell_table[] = { /* Knight's Landing Support */ /* * KNL's memory channels are swizzled between memory controllers. - * MC0 is mapped to CH3,5,6 and MC1 is mapped to CH0,1,2 + * MC0 is mapped to CH3,4,5 and MC1 is mapped to CH0,1,2 */ -#define knl_channel_remap(channel) ((channel + 3) % 6) +#define knl_channel_remap(mc, chan) ((mc) ? (chan) : (chan) + 3) /* Memory controller, TAD tables, error injection - 2-8-0, 2-9-0 (2 of these) */ #define PCI_DEVICE_ID_INTEL_KNL_IMC_MC 0x7840 @@ -1286,7 +1286,7 @@ static u32 knl_get_mc_route(int entry, u32 reg) mc = GET_BITFIELD(reg, entry*3, (entry*3)+2); chan = GET_BITFIELD(reg, (entry*2) + 18, (entry*2) + 18 + 1); - return knl_channel_remap(mc*3 + chan); + return knl_channel_remap(mc, chan); } /* @@ -2997,8 +2997,15 @@ static void sbridge_mce_output_error(struct mem_ctl_info *mci, } else { char A = *("A"); - channel = knl_channel_remap(channel); + /* + * Reported channel is in range 0-2, so we can't map it + * back to mc. To figure out mc we check machine check + * bank register that reported this error. + * bank15 means mc0 and bank16 means mc1. + */ + channel = knl_channel_remap(m->bank == 16, channel); channel_mask = 1 << channel; + snprintf(msg, sizeof(msg), "%s%s err_code:%04x:%04x channel:%d (DIMM_%c)", overflow ? " OVERFLOW" : "", diff --git a/drivers/edac/skx_edac.c b/drivers/edac/skx_edac.c new file mode 100644 index 000000000000..0ff4878c2aa1 --- /dev/null +++ b/drivers/edac/skx_edac.c @@ -0,0 +1,1121 @@ +/* + * EDAC driver for Intel(R) Xeon(R) Skylake processors + * Copyright (c) 2016, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/module.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/edac.h> +#include <linux/mmzone.h> +#include <linux/smp.h> +#include <linux/bitmap.h> +#include <linux/math64.h> +#include <linux/mod_devicetable.h> +#include <asm/cpu_device_id.h> +#include <asm/processor.h> +#include <asm/mce.h> + +#include "edac_core.h" + +#define SKX_REVISION " Ver: 1.0 " + +/* + * Debug macros + */ +#define skx_printk(level, fmt, arg...) \ + edac_printk(level, "skx", fmt, ##arg) + +#define skx_mc_printk(mci, level, fmt, arg...) \ + edac_mc_chipset_printk(mci, level, "skx", fmt, ##arg) + +/* + * Get a bit field at register value <v>, from bit <lo> to bit <hi> + */ +#define GET_BITFIELD(v, lo, hi) \ + (((v) & GENMASK_ULL((hi), (lo))) >> (lo)) + +static LIST_HEAD(skx_edac_list); + +static u64 skx_tolm, skx_tohm; + +#define NUM_IMC 2 /* memory controllers per socket */ +#define NUM_CHANNELS 3 /* channels per memory controller */ +#define NUM_DIMMS 2 /* Max DIMMS per channel */ + +#define MASK26 0x3FFFFFF /* Mask for 2^26 */ +#define MASK29 0x1FFFFFFF /* Mask for 2^29 */ + +/* + * Each cpu socket contains some pci devices that provide global + * information, and also some that are local to each of the two + * memory controllers on the die. + */ +struct skx_dev { + struct list_head list; + u8 bus[4]; + struct pci_dev *sad_all; + struct pci_dev *util_all; + u32 mcroute; + struct skx_imc { + struct mem_ctl_info *mci; + u8 mc; /* system wide mc# */ + u8 lmc; /* socket relative mc# */ + u8 src_id, node_id; + struct skx_channel { + struct pci_dev *cdev; + struct skx_dimm { + u8 close_pg; + u8 bank_xor_enable; + u8 fine_grain_bank; + u8 rowbits; + u8 colbits; + } dimms[NUM_DIMMS]; + } chan[NUM_CHANNELS]; + } imc[NUM_IMC]; +}; +static int skx_num_sockets; + +struct skx_pvt { + struct skx_imc *imc; +}; + +struct decoded_addr { + struct skx_dev *dev; + u64 addr; + int socket; + int imc; + int channel; + u64 chan_addr; + int sktways; + int chanways; + int dimm; + int rank; + int channel_rank; + u64 rank_address; + int row; + int column; + int bank_address; + int bank_group; +}; + +static struct skx_dev *get_skx_dev(u8 bus, u8 idx) +{ + struct skx_dev *d; + + list_for_each_entry(d, &skx_edac_list, list) { + if (d->bus[idx] == bus) + return d; + } + + return NULL; +} + +enum munittype { + CHAN0, CHAN1, CHAN2, SAD_ALL, UTIL_ALL, SAD +}; + +struct munit { + u16 did; + u16 devfn[NUM_IMC]; + u8 busidx; + u8 per_socket; + enum munittype mtype; +}; + +/* + * List of PCI device ids that we need together with some device + * number and function numbers to tell which memory controller the + * device belongs to. + */ +static const struct munit skx_all_munits[] = { + { 0x2054, { }, 1, 1, SAD_ALL }, + { 0x2055, { }, 1, 1, UTIL_ALL }, + { 0x2040, { PCI_DEVFN(10, 0), PCI_DEVFN(12, 0) }, 2, 2, CHAN0 }, + { 0x2044, { PCI_DEVFN(10, 4), PCI_DEVFN(12, 4) }, 2, 2, CHAN1 }, + { 0x2048, { PCI_DEVFN(11, 0), PCI_DEVFN(13, 0) }, 2, 2, CHAN2 }, + { 0x208e, { }, 1, 0, SAD }, + { } +}; + +/* + * We use the per-socket device 0x2016 to count how many sockets are present, + * and to detemine which PCI buses are associated with each socket. Allocate + * and build the full list of all the skx_dev structures that we need here. + */ +static int get_all_bus_mappings(void) +{ + struct pci_dev *pdev, *prev; + struct skx_dev *d; + u32 reg; + int ndev = 0; + + prev = NULL; + for (;;) { + pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2016, prev); + if (!pdev) + break; + ndev++; + d = kzalloc(sizeof(*d), GFP_KERNEL); + if (!d) { + pci_dev_put(pdev); + return -ENOMEM; + } + pci_read_config_dword(pdev, 0xCC, ®); + d->bus[0] = GET_BITFIELD(reg, 0, 7); + d->bus[1] = GET_BITFIELD(reg, 8, 15); + d->bus[2] = GET_BITFIELD(reg, 16, 23); + d->bus[3] = GET_BITFIELD(reg, 24, 31); + edac_dbg(2, "busses: %x, %x, %x, %x\n", + d->bus[0], d->bus[1], d->bus[2], d->bus[3]); + list_add_tail(&d->list, &skx_edac_list); + skx_num_sockets++; + prev = pdev; + } + + return ndev; +} + +static int get_all_munits(const struct munit *m) +{ + struct pci_dev *pdev, *prev; + struct skx_dev *d; + u32 reg; + int i = 0, ndev = 0; + + prev = NULL; + for (;;) { + pdev = pci_get_device(PCI_VENDOR_ID_INTEL, m->did, prev); + if (!pdev) + break; + ndev++; + if (m->per_socket == NUM_IMC) { + for (i = 0; i < NUM_IMC; i++) + if (m->devfn[i] == pdev->devfn) + break; + if (i == NUM_IMC) + goto fail; + } + d = get_skx_dev(pdev->bus->number, m->busidx); + if (!d) + goto fail; + + /* Be sure that the device is enabled */ + if (unlikely(pci_enable_device(pdev) < 0)) { + skx_printk(KERN_ERR, + "Couldn't enable %04x:%04x\n", PCI_VENDOR_ID_INTEL, m->did); + goto fail; + } + + switch (m->mtype) { + case CHAN0: case CHAN1: case CHAN2: + pci_dev_get(pdev); + d->imc[i].chan[m->mtype].cdev = pdev; + break; + case SAD_ALL: + pci_dev_get(pdev); + d->sad_all = pdev; + break; + case UTIL_ALL: + pci_dev_get(pdev); + d->util_all = pdev; + break; + case SAD: + /* + * one of these devices per core, including cores + * that don't exist on this SKU. Ignore any that + * read a route table of zero, make sure all the + * non-zero values match. + */ + pci_read_config_dword(pdev, 0xB4, ®); + if (reg != 0) { + if (d->mcroute == 0) + d->mcroute = reg; + else if (d->mcroute != reg) { + skx_printk(KERN_ERR, + "mcroute mismatch\n"); + goto fail; + } + } + ndev--; + break; + } + + prev = pdev; + } + + return ndev; +fail: + pci_dev_put(pdev); + return -ENODEV; +} + +const struct x86_cpu_id skx_cpuids[] = { + { X86_VENDOR_INTEL, 6, 0x55, 0, 0 }, /* Skylake */ + { } +}; +MODULE_DEVICE_TABLE(x86cpu, skx_cpuids); + +static u8 get_src_id(struct skx_dev *d) +{ + u32 reg; + + pci_read_config_dword(d->util_all, 0xF0, ®); + + return GET_BITFIELD(reg, 12, 14); +} + +static u8 skx_get_node_id(struct skx_dev *d) +{ + u32 reg; + + pci_read_config_dword(d->util_all, 0xF4, ®); + + return GET_BITFIELD(reg, 0, 2); +} + +static int get_dimm_attr(u32 reg, int lobit, int hibit, int add, int minval, + int maxval, char *name) +{ + u32 val = GET_BITFIELD(reg, lobit, hibit); + + if (val < minval || val > maxval) { + edac_dbg(2, "bad %s = %d (raw=%x)\n", name, val, reg); + return -EINVAL; + } + return val + add; +} + +#define IS_DIMM_PRESENT(mtr) GET_BITFIELD((mtr), 15, 15) + +#define numrank(reg) get_dimm_attr((reg), 12, 13, 0, 1, 2, "ranks") +#define numrow(reg) get_dimm_attr((reg), 2, 4, 12, 1, 6, "rows") +#define numcol(reg) get_dimm_attr((reg), 0, 1, 10, 0, 2, "cols") + +static int get_width(u32 mtr) +{ + switch (GET_BITFIELD(mtr, 8, 9)) { + case 0: + return DEV_X4; + case 1: + return DEV_X8; + case 2: + return DEV_X16; + } + return DEV_UNKNOWN; +} + +static int skx_get_hi_lo(void) +{ + struct pci_dev *pdev; + u32 reg; + + pdev = pci_get_device(PCI_VENDOR_ID_INTEL, 0x2034, NULL); + if (!pdev) { + edac_dbg(0, "Can't get tolm/tohm\n"); + return -ENODEV; + } + + pci_read_config_dword(pdev, 0xD0, ®); + skx_tolm = reg; + pci_read_config_dword(pdev, 0xD4, ®); + skx_tohm = reg; + pci_read_config_dword(pdev, 0xD8, ®); + skx_tohm |= (u64)reg << 32; + + pci_dev_put(pdev); + edac_dbg(2, "tolm=%llx tohm=%llx\n", skx_tolm, skx_tohm); + + return 0; +} + +static int get_dimm_info(u32 mtr, u32 amap, struct dimm_info *dimm, + struct skx_imc *imc, int chan, int dimmno) +{ + int banks = 16, ranks, rows, cols, npages; + u64 size; + + if (!IS_DIMM_PRESENT(mtr)) + return 0; + ranks = numrank(mtr); + rows = numrow(mtr); + cols = numcol(mtr); + + /* + * Compute size in 8-byte (2^3) words, then shift to MiB (2^20) + */ + size = ((1ull << (rows + cols + ranks)) * banks) >> (20 - 3); + npages = MiB_TO_PAGES(size); + + edac_dbg(0, "mc#%d: channel %d, dimm %d, %lld Mb (%d pages) bank: %d, rank: %d, row: %#x, col: %#x\n", + imc->mc, chan, dimmno, size, npages, + banks, ranks, rows, cols); + + imc->chan[chan].dimms[dimmno].close_pg = GET_BITFIELD(mtr, 0, 0); + imc->chan[chan].dimms[dimmno].bank_xor_enable = GET_BITFIELD(mtr, 9, 9); + imc->chan[chan].dimms[dimmno].fine_grain_bank = GET_BITFIELD(amap, 0, 0); + imc->chan[chan].dimms[dimmno].rowbits = rows; + imc->chan[chan].dimms[dimmno].colbits = cols; + + dimm->nr_pages = npages; + dimm->grain = 32; + dimm->dtype = get_width(mtr); + dimm->mtype = MEM_DDR4; + dimm->edac_mode = EDAC_SECDED; /* likely better than this */ + snprintf(dimm->label, sizeof(dimm->label), "CPU_SrcID#%u_MC#%u_Chan#%u_DIMM#%u", + imc->src_id, imc->lmc, chan, dimmno); + + return 1; +} + +#define SKX_GET_MTMTR(dev, reg) \ + pci_read_config_dword((dev), 0x87c, ®) + +static bool skx_check_ecc(struct pci_dev *pdev) +{ + u32 mtmtr; + + SKX_GET_MTMTR(pdev, mtmtr); + + return !!GET_BITFIELD(mtmtr, 2, 2); +} + +static int skx_get_dimm_config(struct mem_ctl_info *mci) +{ + struct skx_pvt *pvt = mci->pvt_info; + struct skx_imc *imc = pvt->imc; + struct dimm_info *dimm; + int i, j; + u32 mtr, amap; + int ndimms; + + for (i = 0; i < NUM_CHANNELS; i++) { + ndimms = 0; + pci_read_config_dword(imc->chan[i].cdev, 0x8C, &amap); + for (j = 0; j < NUM_DIMMS; j++) { + dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, + mci->n_layers, i, j, 0); + pci_read_config_dword(imc->chan[i].cdev, + 0x80 + 4*j, &mtr); + ndimms += get_dimm_info(mtr, amap, dimm, imc, i, j); + } + if (ndimms && !skx_check_ecc(imc->chan[0].cdev)) { + skx_printk(KERN_ERR, "ECC is disabled on imc %d\n", imc->mc); + return -ENODEV; + } + } + + return 0; +} + +static void skx_unregister_mci(struct skx_imc *imc) +{ + struct mem_ctl_info *mci = imc->mci; + + if (!mci) + return; + + edac_dbg(0, "MC%d: mci = %p\n", imc->mc, mci); + + /* Remove MC sysfs nodes */ + edac_mc_del_mc(mci->pdev); + + edac_dbg(1, "%s: free mci struct\n", mci->ctl_name); + kfree(mci->ctl_name); + edac_mc_free(mci); +} + +static int skx_register_mci(struct skx_imc *imc) +{ + struct mem_ctl_info *mci; + struct edac_mc_layer layers[2]; + struct pci_dev *pdev = imc->chan[0].cdev; + struct skx_pvt *pvt; + int rc; + + /* allocate a new MC control structure */ + layers[0].type = EDAC_MC_LAYER_CHANNEL; + layers[0].size = NUM_CHANNELS; + layers[0].is_virt_csrow = false; + layers[1].type = EDAC_MC_LAYER_SLOT; + layers[1].size = NUM_DIMMS; + layers[1].is_virt_csrow = true; + mci = edac_mc_alloc(imc->mc, ARRAY_SIZE(layers), layers, + sizeof(struct skx_pvt)); + + if (unlikely(!mci)) + return -ENOMEM; + + edac_dbg(0, "MC#%d: mci = %p\n", imc->mc, mci); + + /* Associate skx_dev and mci for future usage */ + imc->mci = mci; + pvt = mci->pvt_info; + pvt->imc = imc; + + mci->ctl_name = kasprintf(GFP_KERNEL, "Skylake Socket#%d IMC#%d", + imc->node_id, imc->lmc); + mci->mtype_cap = MEM_FLAG_DDR4; + mci->edac_ctl_cap = EDAC_FLAG_NONE; + mci->edac_cap = EDAC_FLAG_NONE; + mci->mod_name = "skx_edac.c"; + mci->dev_name = pci_name(imc->chan[0].cdev); + mci->mod_ver = SKX_REVISION; + mci->ctl_page_to_phys = NULL; + + rc = skx_get_dimm_config(mci); + if (rc < 0) + goto fail; + + /* record ptr to the generic device */ + mci->pdev = &pdev->dev; + + /* add this new MC control structure to EDAC's list of MCs */ + if (unlikely(edac_mc_add_mc(mci))) { + edac_dbg(0, "MC: failed edac_mc_add_mc()\n"); + rc = -EINVAL; + goto fail; + } + + return 0; + +fail: + kfree(mci->ctl_name); + edac_mc_free(mci); + imc->mci = NULL; + return rc; +} + +#define SKX_MAX_SAD 24 + +#define SKX_GET_SAD(d, i, reg) \ + pci_read_config_dword((d)->sad_all, 0x60 + 8 * (i), ®) +#define SKX_GET_ILV(d, i, reg) \ + pci_read_config_dword((d)->sad_all, 0x64 + 8 * (i), ®) + +#define SKX_SAD_MOD3MODE(sad) GET_BITFIELD((sad), 30, 31) +#define SKX_SAD_MOD3(sad) GET_BITFIELD((sad), 27, 27) +#define SKX_SAD_LIMIT(sad) (((u64)GET_BITFIELD((sad), 7, 26) << 26) | MASK26) +#define SKX_SAD_MOD3ASMOD2(sad) GET_BITFIELD((sad), 5, 6) +#define SKX_SAD_ATTR(sad) GET_BITFIELD((sad), 3, 4) +#define SKX_SAD_INTERLEAVE(sad) GET_BITFIELD((sad), 1, 2) +#define SKX_SAD_ENABLE(sad) GET_BITFIELD((sad), 0, 0) + +#define SKX_ILV_REMOTE(tgt) (((tgt) & 8) == 0) +#define SKX_ILV_TARGET(tgt) ((tgt) & 7) + +static bool skx_sad_decode(struct decoded_addr *res) +{ + struct skx_dev *d = list_first_entry(&skx_edac_list, typeof(*d), list); + u64 addr = res->addr; + int i, idx, tgt, lchan, shift; + u32 sad, ilv; + u64 limit, prev_limit; + int remote = 0; + + /* Simple sanity check for I/O space or out of range */ + if (addr >= skx_tohm || (addr >= skx_tolm && addr < BIT_ULL(32))) { + edac_dbg(0, "Address %llx out of range\n", addr); + return false; + } + +restart: + prev_limit = 0; + for (i = 0; i < SKX_MAX_SAD; i++) { + SKX_GET_SAD(d, i, sad); + limit = SKX_SAD_LIMIT(sad); + if (SKX_SAD_ENABLE(sad)) { + if (addr >= prev_limit && addr <= limit) + goto sad_found; + } + prev_limit = limit + 1; + } + edac_dbg(0, "No SAD entry for %llx\n", addr); + return false; + +sad_found: + SKX_GET_ILV(d, i, ilv); + + switch (SKX_SAD_INTERLEAVE(sad)) { + case 0: + idx = GET_BITFIELD(addr, 6, 8); + break; + case 1: + idx = GET_BITFIELD(addr, 8, 10); + break; + case 2: + idx = GET_BITFIELD(addr, 12, 14); + break; + case 3: + idx = GET_BITFIELD(addr, 30, 32); + break; + } + + tgt = GET_BITFIELD(ilv, 4 * idx, 4 * idx + 3); + + /* If point to another node, find it and start over */ + if (SKX_ILV_REMOTE(tgt)) { + if (remote) { + edac_dbg(0, "Double remote!\n"); + return false; + } + remote = 1; + list_for_each_entry(d, &skx_edac_list, list) { + if (d->imc[0].src_id == SKX_ILV_TARGET(tgt)) + goto restart; + } + edac_dbg(0, "Can't find node %d\n", SKX_ILV_TARGET(tgt)); + return false; + } + + if (SKX_SAD_MOD3(sad) == 0) + lchan = SKX_ILV_TARGET(tgt); + else { + switch (SKX_SAD_MOD3MODE(sad)) { + case 0: + shift = 6; + break; + case 1: + shift = 8; + break; + case 2: + shift = 12; + break; + default: + edac_dbg(0, "illegal mod3mode\n"); + return false; + } + switch (SKX_SAD_MOD3ASMOD2(sad)) { + case 0: + lchan = (addr >> shift) % 3; + break; + case 1: + lchan = (addr >> shift) % 2; + break; + case 2: + lchan = (addr >> shift) % 2; + lchan = (lchan << 1) | ~lchan; + break; + case 3: + lchan = ((addr >> shift) % 2) << 1; + break; + } + lchan = (lchan << 1) | (SKX_ILV_TARGET(tgt) & 1); + } + + res->dev = d; + res->socket = d->imc[0].src_id; + res->imc = GET_BITFIELD(d->mcroute, lchan * 3, lchan * 3 + 2); + res->channel = GET_BITFIELD(d->mcroute, lchan * 2 + 18, lchan * 2 + 19); + + edac_dbg(2, "%llx: socket=%d imc=%d channel=%d\n", + res->addr, res->socket, res->imc, res->channel); + return true; +} + +#define SKX_MAX_TAD 8 + +#define SKX_GET_TADBASE(d, mc, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[0].cdev, 0x850 + 4 * (i), ®) +#define SKX_GET_TADWAYNESS(d, mc, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[0].cdev, 0x880 + 4 * (i), ®) +#define SKX_GET_TADCHNILVOFFSET(d, mc, ch, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[ch].cdev, 0x90 + 4 * (i), ®) + +#define SKX_TAD_BASE(b) ((u64)GET_BITFIELD((b), 12, 31) << 26) +#define SKX_TAD_SKT_GRAN(b) GET_BITFIELD((b), 4, 5) +#define SKX_TAD_CHN_GRAN(b) GET_BITFIELD((b), 6, 7) +#define SKX_TAD_LIMIT(b) (((u64)GET_BITFIELD((b), 12, 31) << 26) | MASK26) +#define SKX_TAD_OFFSET(b) ((u64)GET_BITFIELD((b), 4, 23) << 26) +#define SKX_TAD_SKTWAYS(b) (1 << GET_BITFIELD((b), 10, 11)) +#define SKX_TAD_CHNWAYS(b) (GET_BITFIELD((b), 8, 9) + 1) + +/* which bit used for both socket and channel interleave */ +static int skx_granularity[] = { 6, 8, 12, 30 }; + +static u64 skx_do_interleave(u64 addr, int shift, int ways, u64 lowbits) +{ + addr >>= shift; + addr /= ways; + addr <<= shift; + + return addr | (lowbits & ((1ull << shift) - 1)); +} + +static bool skx_tad_decode(struct decoded_addr *res) +{ + int i; + u32 base, wayness, chnilvoffset; + int skt_interleave_bit, chn_interleave_bit; + u64 channel_addr; + + for (i = 0; i < SKX_MAX_TAD; i++) { + SKX_GET_TADBASE(res->dev, res->imc, i, base); + SKX_GET_TADWAYNESS(res->dev, res->imc, i, wayness); + if (SKX_TAD_BASE(base) <= res->addr && res->addr <= SKX_TAD_LIMIT(wayness)) + goto tad_found; + } + edac_dbg(0, "No TAD entry for %llx\n", res->addr); + return false; + +tad_found: + res->sktways = SKX_TAD_SKTWAYS(wayness); + res->chanways = SKX_TAD_CHNWAYS(wayness); + skt_interleave_bit = skx_granularity[SKX_TAD_SKT_GRAN(base)]; + chn_interleave_bit = skx_granularity[SKX_TAD_CHN_GRAN(base)]; + + SKX_GET_TADCHNILVOFFSET(res->dev, res->imc, res->channel, i, chnilvoffset); + channel_addr = res->addr - SKX_TAD_OFFSET(chnilvoffset); + + if (res->chanways == 3 && skt_interleave_bit > chn_interleave_bit) { + /* Must handle channel first, then socket */ + channel_addr = skx_do_interleave(channel_addr, chn_interleave_bit, + res->chanways, channel_addr); + channel_addr = skx_do_interleave(channel_addr, skt_interleave_bit, + res->sktways, channel_addr); + } else { + /* Handle socket then channel. Preserve low bits from original address */ + channel_addr = skx_do_interleave(channel_addr, skt_interleave_bit, + res->sktways, res->addr); + channel_addr = skx_do_interleave(channel_addr, chn_interleave_bit, + res->chanways, res->addr); + } + + res->chan_addr = channel_addr; + + edac_dbg(2, "%llx: chan_addr=%llx sktways=%d chanways=%d\n", + res->addr, res->chan_addr, res->sktways, res->chanways); + return true; +} + +#define SKX_MAX_RIR 4 + +#define SKX_GET_RIRWAYNESS(d, mc, ch, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[ch].cdev, \ + 0x108 + 4 * (i), ®) +#define SKX_GET_RIRILV(d, mc, ch, idx, i, reg) \ + pci_read_config_dword((d)->imc[mc].chan[ch].cdev, \ + 0x120 + 16 * idx + 4 * (i), ®) + +#define SKX_RIR_VALID(b) GET_BITFIELD((b), 31, 31) +#define SKX_RIR_LIMIT(b) (((u64)GET_BITFIELD((b), 1, 11) << 29) | MASK29) +#define SKX_RIR_WAYS(b) (1 << GET_BITFIELD((b), 28, 29)) +#define SKX_RIR_CHAN_RANK(b) GET_BITFIELD((b), 16, 19) +#define SKX_RIR_OFFSET(b) ((u64)(GET_BITFIELD((b), 2, 15) << 26)) + +static bool skx_rir_decode(struct decoded_addr *res) +{ + int i, idx, chan_rank; + int shift; + u32 rirway, rirlv; + u64 rank_addr, prev_limit = 0, limit; + + if (res->dev->imc[res->imc].chan[res->channel].dimms[0].close_pg) + shift = 6; + else + shift = 13; + + for (i = 0; i < SKX_MAX_RIR; i++) { + SKX_GET_RIRWAYNESS(res->dev, res->imc, res->channel, i, rirway); + limit = SKX_RIR_LIMIT(rirway); + if (SKX_RIR_VALID(rirway)) { + if (prev_limit <= res->chan_addr && + res->chan_addr <= limit) + goto rir_found; + } + prev_limit = limit; + } + edac_dbg(0, "No RIR entry for %llx\n", res->addr); + return false; + +rir_found: + rank_addr = res->chan_addr >> shift; + rank_addr /= SKX_RIR_WAYS(rirway); + rank_addr <<= shift; + rank_addr |= res->chan_addr & GENMASK_ULL(shift - 1, 0); + + res->rank_address = rank_addr; + idx = (res->chan_addr >> shift) % SKX_RIR_WAYS(rirway); + + SKX_GET_RIRILV(res->dev, res->imc, res->channel, idx, i, rirlv); + res->rank_address = rank_addr - SKX_RIR_OFFSET(rirlv); + chan_rank = SKX_RIR_CHAN_RANK(rirlv); + res->channel_rank = chan_rank; + res->dimm = chan_rank / 4; + res->rank = chan_rank % 4; + + edac_dbg(2, "%llx: dimm=%d rank=%d chan_rank=%d rank_addr=%llx\n", + res->addr, res->dimm, res->rank, + res->channel_rank, res->rank_address); + return true; +} + +static u8 skx_close_row[] = { + 15, 16, 17, 18, 20, 21, 22, 28, 10, 11, 12, 13, 29, 30, 31, 32, 33 +}; +static u8 skx_close_column[] = { + 3, 4, 5, 14, 19, 23, 24, 25, 26, 27 +}; +static u8 skx_open_row[] = { + 14, 15, 16, 20, 28, 21, 22, 23, 24, 25, 26, 27, 29, 30, 31, 32, 33 +}; +static u8 skx_open_column[] = { + 3, 4, 5, 6, 7, 8, 9, 10, 11, 12 +}; +static u8 skx_open_fine_column[] = { + 3, 4, 5, 7, 8, 9, 10, 11, 12, 13 +}; + +static int skx_bits(u64 addr, int nbits, u8 *bits) +{ + int i, res = 0; + + for (i = 0; i < nbits; i++) + res |= ((addr >> bits[i]) & 1) << i; + return res; +} + +static int skx_bank_bits(u64 addr, int b0, int b1, int do_xor, int x0, int x1) +{ + int ret = GET_BITFIELD(addr, b0, b0) | (GET_BITFIELD(addr, b1, b1) << 1); + + if (do_xor) + ret ^= GET_BITFIELD(addr, x0, x0) | (GET_BITFIELD(addr, x1, x1) << 1); + + return ret; +} + +static bool skx_mad_decode(struct decoded_addr *r) +{ + struct skx_dimm *dimm = &r->dev->imc[r->imc].chan[r->channel].dimms[r->dimm]; + int bg0 = dimm->fine_grain_bank ? 6 : 13; + + if (dimm->close_pg) { + r->row = skx_bits(r->rank_address, dimm->rowbits, skx_close_row); + r->column = skx_bits(r->rank_address, dimm->colbits, skx_close_column); + r->column |= 0x400; /* C10 is autoprecharge, always set */ + r->bank_address = skx_bank_bits(r->rank_address, 8, 9, dimm->bank_xor_enable, 22, 28); + r->bank_group = skx_bank_bits(r->rank_address, 6, 7, dimm->bank_xor_enable, 20, 21); + } else { + r->row = skx_bits(r->rank_address, dimm->rowbits, skx_open_row); + if (dimm->fine_grain_bank) + r->column = skx_bits(r->rank_address, dimm->colbits, skx_open_fine_column); + else + r->column = skx_bits(r->rank_address, dimm->colbits, skx_open_column); + r->bank_address = skx_bank_bits(r->rank_address, 18, 19, dimm->bank_xor_enable, 22, 23); + r->bank_group = skx_bank_bits(r->rank_address, bg0, 17, dimm->bank_xor_enable, 20, 21); + } + r->row &= (1u << dimm->rowbits) - 1; + + edac_dbg(2, "%llx: row=%x col=%x bank_addr=%d bank_group=%d\n", + r->addr, r->row, r->column, r->bank_address, + r->bank_group); + return true; +} + +static bool skx_decode(struct decoded_addr *res) +{ + + return skx_sad_decode(res) && skx_tad_decode(res) && + skx_rir_decode(res) && skx_mad_decode(res); +} + +#ifdef CONFIG_EDAC_DEBUG +/* + * Debug feature. Make /sys/kernel/debug/skx_edac_test/addr. + * Write an address to this file to exercise the address decode + * logic in this driver. + */ +static struct dentry *skx_test; +static u64 skx_fake_addr; + +static int debugfs_u64_set(void *data, u64 val) +{ + struct decoded_addr res; + + res.addr = val; + skx_decode(&res); + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n"); + +static struct dentry *mydebugfs_create(const char *name, umode_t mode, + struct dentry *parent, u64 *value) +{ + return debugfs_create_file(name, mode, parent, value, &fops_u64_wo); +} + +static void setup_skx_debug(void) +{ + skx_test = debugfs_create_dir("skx_edac_test", NULL); + mydebugfs_create("addr", S_IWUSR, skx_test, &skx_fake_addr); +} + +static void teardown_skx_debug(void) +{ + debugfs_remove_recursive(skx_test); +} +#else +static void setup_skx_debug(void) +{ +} + +static void teardown_skx_debug(void) +{ +} +#endif /*CONFIG_EDAC_DEBUG*/ + +static void skx_mce_output_error(struct mem_ctl_info *mci, + const struct mce *m, + struct decoded_addr *res) +{ + enum hw_event_mc_err_type tp_event; + char *type, *optype, msg[256]; + bool ripv = GET_BITFIELD(m->mcgstatus, 0, 0); + bool overflow = GET_BITFIELD(m->status, 62, 62); + bool uncorrected_error = GET_BITFIELD(m->status, 61, 61); + bool recoverable; + u32 core_err_cnt = GET_BITFIELD(m->status, 38, 52); + u32 mscod = GET_BITFIELD(m->status, 16, 31); + u32 errcode = GET_BITFIELD(m->status, 0, 15); + u32 optypenum = GET_BITFIELD(m->status, 4, 6); + + recoverable = GET_BITFIELD(m->status, 56, 56); + + if (uncorrected_error) { + if (ripv) { + type = "FATAL"; + tp_event = HW_EVENT_ERR_FATAL; + } else { + type = "NON_FATAL"; + tp_event = HW_EVENT_ERR_UNCORRECTED; + } + } else { + type = "CORRECTED"; + tp_event = HW_EVENT_ERR_CORRECTED; + } + + /* + * According with Table 15-9 of the Intel Architecture spec vol 3A, + * memory errors should fit in this mask: + * 000f 0000 1mmm cccc (binary) + * where: + * f = Correction Report Filtering Bit. If 1, subsequent errors + * won't be shown + * mmm = error type + * cccc = channel + * If the mask doesn't match, report an error to the parsing logic + */ + if (!((errcode & 0xef80) == 0x80)) { + optype = "Can't parse: it is not a mem"; + } else { + switch (optypenum) { + case 0: + optype = "generic undef request error"; + break; + case 1: + optype = "memory read error"; + break; + case 2: + optype = "memory write error"; + break; + case 3: + optype = "addr/cmd error"; + break; + case 4: + optype = "memory scrubbing error"; + break; + default: + optype = "reserved"; + break; + } + } + + snprintf(msg, sizeof(msg), + "%s%s err_code:%04x:%04x socket:%d imc:%d rank:%d bg:%d ba:%d row:%x col:%x", + overflow ? " OVERFLOW" : "", + (uncorrected_error && recoverable) ? " recoverable" : "", + mscod, errcode, + res->socket, res->imc, res->rank, + res->bank_group, res->bank_address, res->row, res->column); + + edac_dbg(0, "%s\n", msg); + + /* Call the helper to output message */ + edac_mc_handle_error(tp_event, mci, core_err_cnt, + m->addr >> PAGE_SHIFT, m->addr & ~PAGE_MASK, 0, + res->channel, res->dimm, -1, + optype, msg); +} + +static int skx_mce_check_error(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + struct decoded_addr res; + struct mem_ctl_info *mci; + char *type; + + if (get_edac_report_status() == EDAC_REPORTING_DISABLED) + return NOTIFY_DONE; + + /* ignore unless this is memory related with an address */ + if ((mce->status & 0xefff) >> 7 != 1 || !(mce->status & MCI_STATUS_ADDRV)) + return NOTIFY_DONE; + + res.addr = mce->addr; + if (!skx_decode(&res)) + return NOTIFY_DONE; + mci = res.dev->imc[res.imc].mci; + + if (mce->mcgstatus & MCG_STATUS_MCIP) + type = "Exception"; + else + type = "Event"; + + skx_mc_printk(mci, KERN_DEBUG, "HANDLING MCE MEMORY ERROR\n"); + + skx_mc_printk(mci, KERN_DEBUG, "CPU %d: Machine Check %s: %Lx " + "Bank %d: %016Lx\n", mce->extcpu, type, + mce->mcgstatus, mce->bank, mce->status); + skx_mc_printk(mci, KERN_DEBUG, "TSC %llx ", mce->tsc); + skx_mc_printk(mci, KERN_DEBUG, "ADDR %llx ", mce->addr); + skx_mc_printk(mci, KERN_DEBUG, "MISC %llx ", mce->misc); + + skx_mc_printk(mci, KERN_DEBUG, "PROCESSOR %u:%x TIME %llu SOCKET " + "%u APIC %x\n", mce->cpuvendor, mce->cpuid, + mce->time, mce->socketid, mce->apicid); + + skx_mce_output_error(mci, mce, &res); + + return NOTIFY_DONE; +} + +static struct notifier_block skx_mce_dec = { + .notifier_call = skx_mce_check_error, +}; + +static void skx_remove(void) +{ + int i, j; + struct skx_dev *d, *tmp; + + edac_dbg(0, "\n"); + + list_for_each_entry_safe(d, tmp, &skx_edac_list, list) { + list_del(&d->list); + for (i = 0; i < NUM_IMC; i++) { + skx_unregister_mci(&d->imc[i]); + for (j = 0; j < NUM_CHANNELS; j++) + pci_dev_put(d->imc[i].chan[j].cdev); + } + pci_dev_put(d->util_all); + pci_dev_put(d->sad_all); + + kfree(d); + } +} + +/* + * skx_init: + * make sure we are running on the correct cpu model + * search for all the devices we need + * check which DIMMs are present. + */ +int __init skx_init(void) +{ + const struct x86_cpu_id *id; + const struct munit *m; + int rc = 0, i; + u8 mc = 0, src_id, node_id; + struct skx_dev *d; + + edac_dbg(2, "\n"); + + id = x86_match_cpu(skx_cpuids); + if (!id) + return -ENODEV; + + rc = skx_get_hi_lo(); + if (rc) + return rc; + + rc = get_all_bus_mappings(); + if (rc < 0) + goto fail; + if (rc == 0) { + edac_dbg(2, "No memory controllers found\n"); + return -ENODEV; + } + + for (m = skx_all_munits; m->did; m++) { + rc = get_all_munits(m); + if (rc < 0) + goto fail; + if (rc != m->per_socket * skx_num_sockets) { + edac_dbg(2, "Expected %d, got %d of %x\n", + m->per_socket * skx_num_sockets, rc, m->did); + rc = -ENODEV; + goto fail; + } + } + + list_for_each_entry(d, &skx_edac_list, list) { + src_id = get_src_id(d); + node_id = skx_get_node_id(d); + edac_dbg(2, "src_id=%d node_id=%d\n", src_id, node_id); + for (i = 0; i < NUM_IMC; i++) { + d->imc[i].mc = mc++; + d->imc[i].lmc = i; + d->imc[i].src_id = src_id; + d->imc[i].node_id = node_id; + rc = skx_register_mci(&d->imc[i]); + if (rc < 0) + goto fail; + } + } + + /* Ensure that the OPSTATE is set correctly for POLL or NMI */ + opstate_init(); + + setup_skx_debug(); + + mce_register_decode_chain(&skx_mce_dec); + + return 0; +fail: + skx_remove(); + return rc; +} + +static void __exit skx_exit(void) +{ + edac_dbg(2, "\n"); + mce_unregister_decode_chain(&skx_mce_dec); + skx_remove(); + teardown_skx_debug(); +} + +module_init(skx_init); +module_exit(skx_exit); + +module_param(edac_op_state, int, 0444); +MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI"); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Tony Luck"); +MODULE_DESCRIPTION("MC Driver for Intel Skylake server processors"); diff --git a/drivers/firmware/efi/capsule-loader.c b/drivers/firmware/efi/capsule-loader.c index c99c24bc79b0..9ae6c116c474 100644 --- a/drivers/firmware/efi/capsule-loader.c +++ b/drivers/firmware/efi/capsule-loader.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/mutex.h> #include <linux/efi.h> +#include <linux/vmalloc.h> #define NO_FURTHER_WRITE_ACTION -1 @@ -108,14 +109,15 @@ static ssize_t efi_capsule_submit_update(struct capsule_info *cap_info) int ret; void *cap_hdr_temp; - cap_hdr_temp = kmap(cap_info->pages[0]); + cap_hdr_temp = vmap(cap_info->pages, cap_info->index, + VM_MAP, PAGE_KERNEL); if (!cap_hdr_temp) { - pr_debug("%s: kmap() failed\n", __func__); + pr_debug("%s: vmap() failed\n", __func__); return -EFAULT; } ret = efi_capsule_update(cap_hdr_temp, cap_info->pages); - kunmap(cap_info->pages[0]); + vunmap(cap_hdr_temp); if (ret) { pr_err("%s: efi_capsule_update() failed\n", __func__); return ret; diff --git a/drivers/firmware/efi/capsule.c b/drivers/firmware/efi/capsule.c index 53b9fd2293ee..6eedff45e6d7 100644 --- a/drivers/firmware/efi/capsule.c +++ b/drivers/firmware/efi/capsule.c @@ -190,9 +190,9 @@ efi_capsule_update_locked(efi_capsule_header_t *capsule, * map the capsule described by @capsule with its data in @pages and * send it to the firmware via the UpdateCapsule() runtime service. * - * @capsule must be a virtual mapping of the first page in @pages - * (@pages[0]) in the kernel address space. That is, a - * capsule_header_t that describes the entire contents of the capsule + * @capsule must be a virtual mapping of the complete capsule update in the + * kernel address space, as the capsule can be consumed immediately. + * A capsule_header_t that describes the entire contents of the capsule * must be at the start of the first data page. * * Even though this function will validate that the firmware supports diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 98dd47a30fc7..66a94103798b 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -50,6 +50,7 @@ config GPIO_DEVRES config OF_GPIO def_bool y depends on OF + depends on HAS_IOMEM config GPIO_ACPI def_bool y @@ -188,7 +189,7 @@ config GPIO_EP93XX config GPIO_ETRAXFS bool "Axis ETRAX FS General I/O" depends on CRIS || COMPILE_TEST - depends on OF + depends on OF_GPIO select GPIO_GENERIC select GPIOLIB_IRQCHIP help @@ -214,7 +215,7 @@ config GPIO_GENERIC_PLATFORM config GPIO_GRGPIO tristate "Aeroflex Gaisler GRGPIO support" - depends on OF + depends on OF_GPIO select GPIO_GENERIC select IRQ_DOMAIN help @@ -312,7 +313,7 @@ config GPIO_MPC8XXX config GPIO_MVEBU def_bool y depends on PLAT_ORION - depends on OF + depends on OF_GPIO select GENERIC_IRQ_CHIP config GPIO_MXC @@ -405,7 +406,7 @@ config GPIO_TEGRA bool "NVIDIA Tegra GPIO support" default ARCH_TEGRA depends on ARCH_TEGRA || COMPILE_TEST - depends on OF + depends on OF_GPIO help Say yes here to support GPIO pins on NVIDIA Tegra SoCs. @@ -1099,7 +1100,7 @@ menu "SPI GPIO expanders" config GPIO_74X164 tristate "74x164 serial-in/parallel-out 8-bits shift register" - depends on OF + depends on OF_GPIO help Driver for 74x164 compatible serial-in/parallel-out 8-outputs shift registers. This driver can be used to provide access diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c index 08807368f007..946d09195598 100644 --- a/drivers/gpio/gpio-max730x.c +++ b/drivers/gpio/gpio-max730x.c @@ -192,6 +192,10 @@ int __max730x_probe(struct max7301 *ts) ts->chip.parent = dev; ts->chip.owner = THIS_MODULE; + ret = gpiochip_add_data(&ts->chip, ts); + if (ret) + goto exit_destroy; + /* * initialize pullups according to platform data and cache the * register values for later use. @@ -213,10 +217,6 @@ int __max730x_probe(struct max7301 *ts) } } - ret = gpiochip_add_data(&ts->chip, ts); - if (ret) - goto exit_destroy; - return ret; exit_destroy: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 8ebc5f1eb4c0..700c56baf2de 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -426,6 +426,8 @@ struct amdgpu_mman { /* custom LRU management */ struct amdgpu_mman_lru log2_size[AMDGPU_TTM_LRU_SIZE]; + /* guard for log2_size array, don't add anything in between */ + struct amdgpu_mman_lru guard; }; int amdgpu_copy_buffer(struct amdgpu_ring *ring, @@ -646,9 +648,9 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev); void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev); int amdgpu_gart_init(struct amdgpu_device *adev); void amdgpu_gart_fini(struct amdgpu_device *adev); -void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset, +void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset, int pages); -int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset, +int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset, int pages, struct page **pagelist, dma_addr_t *dma_addr, uint32_t flags); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 983175363b06..fe872b82e619 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -321,6 +321,19 @@ bool amdgpu_atombios_get_connector_info_from_object_table(struct amdgpu_device * (le16_to_cpu(path->usConnObjectId) & OBJECT_TYPE_MASK) >> OBJECT_TYPE_SHIFT; + /* Skip TV/CV support */ + if ((le16_to_cpu(path->usDeviceTag) == + ATOM_DEVICE_TV1_SUPPORT) || + (le16_to_cpu(path->usDeviceTag) == + ATOM_DEVICE_CV_SUPPORT)) + continue; + + if (con_obj_id >= ARRAY_SIZE(object_connector_convert)) { + DRM_ERROR("invalid con_obj_id %d for device tag 0x%04x\n", + con_obj_id, le16_to_cpu(path->usDeviceTag)); + continue; + } + connector_type = object_connector_convert[con_obj_id]; connector_object_id = con_obj_id; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 49de92600074..10b5ddf2c588 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -200,16 +200,7 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx) atpx->is_hybrid = false; if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) { printk("ATPX Hybrid Graphics\n"); -#if 1 - /* This is a temporary hack until the D3 cold support - * makes it upstream. The ATPX power_control method seems - * to still work on even if the system should be using - * the new standardized hybrid D3 cold ACPI interface. - */ - atpx->functions.power_cntl = true; -#else atpx->functions.power_cntl = false; -#endif atpx->is_hybrid = true; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index 921bce2df0b0..0feea347f680 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -221,7 +221,7 @@ void amdgpu_gart_table_vram_free(struct amdgpu_device *adev) * Unbinds the requested pages from the gart page table and * replaces them with the dummy page (all asics). */ -void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset, +void amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset, int pages) { unsigned t; @@ -268,7 +268,7 @@ void amdgpu_gart_unbind(struct amdgpu_device *adev, unsigned offset, * (all asics). * Returns 0 for success, -EINVAL for failure. */ -int amdgpu_gart_bind(struct amdgpu_device *adev, unsigned offset, +int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset, int pages, struct page **pagelist, dma_addr_t *dma_addr, uint32_t flags) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index ff63b88b0ffa..5cc7052e391d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -305,7 +305,7 @@ static ssize_t amdgpu_get_pp_table(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = ddev->dev_private; char *table = NULL; - int size, i; + int size; if (adev->pp_enabled) size = amdgpu_dpm_get_pp_table(adev, &table); @@ -315,10 +315,7 @@ static ssize_t amdgpu_get_pp_table(struct device *dev, if (size >= PAGE_SIZE) size = PAGE_SIZE - 1; - for (i = 0; i < size; i++) { - sprintf(buf + i, "%02x", table[i]); - } - sprintf(buf + i, "\n"); + memcpy(buf, table, size); return size; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index b7742e62972a..716f2afeb6a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -251,8 +251,8 @@ static int amdgpu_move_blit(struct ttm_buffer_object *bo, adev = amdgpu_get_adev(bo->bdev); ring = adev->mman.buffer_funcs_ring; - old_start = old_mem->start << PAGE_SHIFT; - new_start = new_mem->start << PAGE_SHIFT; + old_start = (u64)old_mem->start << PAGE_SHIFT; + new_start = (u64)new_mem->start << PAGE_SHIFT; switch (old_mem->mem_type) { case TTM_PL_VRAM: @@ -335,7 +335,7 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, if (unlikely(r)) { goto out_cleanup; } - r = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem); + r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, new_mem); out_cleanup: ttm_bo_mem_put(bo, &tmp_mem); return r; @@ -368,7 +368,7 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, if (unlikely(r)) { return r; } - r = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem); + r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, &tmp_mem); if (unlikely(r)) { goto out_cleanup; } @@ -950,6 +950,8 @@ static struct list_head *amdgpu_ttm_lru_tail(struct ttm_buffer_object *tbo) struct list_head *res = lru->lru[tbo->mem.mem_type]; lru->lru[tbo->mem.mem_type] = &tbo->lru; + while ((++lru)->lru[tbo->mem.mem_type] == res) + lru->lru[tbo->mem.mem_type] = &tbo->lru; return res; } @@ -960,6 +962,8 @@ static struct list_head *amdgpu_ttm_swap_lru_tail(struct ttm_buffer_object *tbo) struct list_head *res = lru->swap_lru; lru->swap_lru = &tbo->swap; + while ((++lru)->swap_lru == res) + lru->swap_lru = &tbo->swap; return res; } @@ -1011,6 +1015,10 @@ int amdgpu_ttm_init(struct amdgpu_device *adev) lru->swap_lru = &adev->mman.bdev.glob->swap_lru; } + for (j = 0; j < TTM_NUM_MEM_TYPES; ++j) + adev->mman.guard.lru[j] = NULL; + adev->mman.guard.swap_lru = NULL; + adev->mman.initialized = true; r = ttm_bo_init_mm(&adev->mman.bdev, TTM_PL_VRAM, adev->mc.real_vram_size >> PAGE_SHIFT); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index b11f4e8868d7..4aa993d19018 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -1187,7 +1187,8 @@ int amdgpu_uvd_ring_test_ib(struct amdgpu_ring *ring, long timeout) r = 0; } -error: fence_put(fence); + +error: return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 8e642fc48df4..80120fa4092c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1535,7 +1535,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm) r = amd_sched_entity_init(&ring->sched, &vm->entity, rq, amdgpu_sched_jobs); if (r) - return r; + goto err; vm->page_directory_fence = NULL; @@ -1565,6 +1565,9 @@ error_free_page_directory: error_free_sched_entity: amd_sched_entity_fini(&ring->sched, &vm->entity); +err: + drm_free_large(vm->page_tables); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c index e2f0e5d58d5c..a5c94b482459 100644 --- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c @@ -5779,6 +5779,7 @@ static int ci_dpm_init_microcode(struct amdgpu_device *adev) break; case CHIP_KAVERI: case CHIP_KABINI: + case CHIP_MULLINS: default: BUG(); } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index bff8668e9e6d..b8184617ca25 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -270,7 +270,8 @@ static const u32 tonga_mgcg_cgcg_init[] = static const u32 golden_settings_polaris11_a11[] = { - mmCB_HW_CONTROL, 0xfffdf3cf, 0x00006208, + mmCB_HW_CONTROL, 0x0000f3cf, 0x00007208, + mmCB_HW_CONTROL_2, 0x0f000000, 0x0f000000, mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040, mmDB_DEBUG2, 0xf00fffff, 0x00000400, mmPA_SC_ENHANCE, 0xffffffff, 0x20000001, @@ -279,7 +280,7 @@ static const u32 golden_settings_polaris11_a11[] = mmPA_SC_RASTER_CONFIG_1, 0x0000003f, 0x00000000, mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0001003c, mmRLC_CGCG_CGLS_CTRL_3D, 0xffffffff, 0x0001003c, - mmSQ_CONFIG, 0x07f80000, 0x07180000, + mmSQ_CONFIG, 0x07f80000, 0x01180000, mmTA_CNTL_AUX, 0x000f000f, 0x000b0000, mmTCC_CTRL, 0x00100000, 0xf31fff7f, mmTCP_ADDR_CONFIG, 0x000003ff, 0x000000f3, @@ -301,8 +302,8 @@ static const u32 polaris11_golden_common_all[] = static const u32 golden_settings_polaris10_a11[] = { mmATC_MISC_CG, 0x000c0fc0, 0x000c0200, - mmCB_HW_CONTROL, 0xfffdf3cf, 0x00007208, - mmCB_HW_CONTROL_2, 0, 0x0f000000, + mmCB_HW_CONTROL, 0x0001f3cf, 0x00007208, + mmCB_HW_CONTROL_2, 0x0f000000, 0x0f000000, mmCB_HW_CONTROL_3, 0x000001ff, 0x00000040, mmDB_DEBUG2, 0xf00fffff, 0x00000400, mmPA_SC_ENHANCE, 0xffffffff, 0x20000001, @@ -409,6 +410,7 @@ static const u32 golden_settings_iceland_a11[] = mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000, mmPA_SC_RASTER_CONFIG, 0x3f3fffff, 0x00000002, mmPA_SC_RASTER_CONFIG_1, 0x0000003f, 0x00000000, + mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0000003c, mmSQ_RANDOM_WAVE_PRI, 0x001fffff, 0x000006fd, mmTA_CNTL_AUX, 0x000f000f, 0x000b0000, mmTCC_CTRL, 0x00100000, 0xf31fff7f, @@ -505,8 +507,10 @@ static const u32 cz_golden_settings_a11[] = mmGB_GPU_ID, 0x0000000f, 0x00000000, mmPA_SC_ENHANCE, 0xffffffff, 0x00000001, mmPA_SC_LINE_STIPPLE_STATE, 0x0000ff0f, 0x00000000, + mmRLC_CGCG_CGLS_CTRL, 0x00000003, 0x0000003c, mmSQ_RANDOM_WAVE_PRI, 0x001fffff, 0x000006fd, mmTA_CNTL_AUX, 0x000f000f, 0x00010000, + mmTCC_CTRL, 0x00100000, 0xf31fff7f, mmTCC_EXE_DISABLE, 0x00000002, 0x00000002, mmTCP_ADDR_CONFIG, 0x0000000f, 0x000000f3, mmTCP_CHAN_STEER_LO, 0xffffffff, 0x00001302 diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index d24a82bd0c7a..0b0f08641eed 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -144,6 +144,7 @@ static int gmc_v7_0_init_microcode(struct amdgpu_device *adev) break; case CHIP_KAVERI: case CHIP_KABINI: + case CHIP_MULLINS: return 0; default: BUG(); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 717359d3ba8c..2aee2c6f3cd5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -103,6 +103,11 @@ static const u32 stoney_mgcg_cgcg_init[] = mmMC_MEM_POWER_LS, 0xffffffff, 0x00000104 }; +static const u32 golden_settings_stoney_common[] = +{ + mmMC_HUB_RDREQ_UVD, MC_HUB_RDREQ_UVD__PRESCALE_MASK, 0x00000004, + mmMC_RD_GRP_OTH, MC_RD_GRP_OTH__UVD_MASK, 0x00600000 +}; static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev) { @@ -142,6 +147,9 @@ static void gmc_v8_0_init_golden_registers(struct amdgpu_device *adev) amdgpu_program_register_sequence(adev, stoney_mgcg_cgcg_init, (const u32)ARRAY_SIZE(stoney_mgcg_cgcg_init)); + amdgpu_program_register_sequence(adev, + golden_settings_stoney_common, + (const u32)ARRAY_SIZE(golden_settings_stoney_common)); break; default: break; diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c index 1351c7e834a2..a64715d90503 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c @@ -714,7 +714,7 @@ static int sdma_v2_4_ring_test_ib(struct amdgpu_ring *ring, long timeout) DRM_ERROR("amdgpu: IB test timed out\n"); r = -ETIMEDOUT; goto err1; - } else if (r) { + } else if (r < 0) { DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r); goto err1; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c index e621eba63126..a7d3cb3fead0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c @@ -184,7 +184,7 @@ u32 __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd, sizeof(u32)) + inx; pr_debug("kfd: get kernel queue doorbell\n" - " doorbell offset == 0x%08d\n" + " doorbell offset == 0x%08X\n" " kernel address == 0x%08lX\n", *doorbell_off, (uintptr_t)(kfd->doorbell_kernel_ptr + inx)); diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c index ef312bb75fda..963a24d46a93 100644 --- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c +++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c @@ -405,7 +405,7 @@ void amd_sched_job_recovery(struct amd_gpu_scheduler *sched) spin_lock(&sched->job_list_lock); s_job = list_first_entry_or_null(&sched->ring_mirror_list, struct amd_sched_job, node); - if (s_job) + if (s_job && sched->timeout != MAX_SCHEDULE_TIMEOUT) schedule_delayed_work(&s_job->work_tdr, sched->timeout); list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) { diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c index 80446e2d3ab6..76bcb43e7c06 100644 --- a/drivers/gpu/drm/cirrus/cirrus_main.c +++ b/drivers/gpu/drm/cirrus/cirrus_main.c @@ -185,14 +185,23 @@ int cirrus_driver_load(struct drm_device *dev, unsigned long flags) goto out; } + /* + * cirrus_modeset_init() is initializing/registering the emulated fbdev + * and DRM internals can access/test some of the fields in + * mode_config->funcs as part of the fbdev registration process. + * Make sure dev->mode_config.funcs is properly set to avoid + * dereferencing a NULL pointer. + * FIXME: mode_config.funcs assignment should probably be done in + * cirrus_modeset_init() (that's a common pattern seen in other DRM + * drivers). + */ + dev->mode_config.funcs = &cirrus_mode_funcs; r = cirrus_modeset_init(cdev); if (r) { dev_err(&dev->pdev->dev, "Fatal error during modeset init: %d\n", r); goto out; } - dev->mode_config.funcs = (void *)&cirrus_mode_funcs; - return 0; out: cirrus_driver_unload(dev); diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index fa3930757972..2a3ded44cf2a 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -475,7 +475,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, val, -1, &replaced); - state->color_mgmt_changed = replaced; + state->color_mgmt_changed |= replaced; return ret; } else if (property == config->ctm_property) { ret = drm_atomic_replace_property_blob_from_id(crtc, @@ -483,7 +483,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, val, sizeof(struct drm_color_ctm), &replaced); - state->color_mgmt_changed = replaced; + state->color_mgmt_changed |= replaced; return ret; } else if (property == config->gamma_lut_property) { ret = drm_atomic_replace_property_blob_from_id(crtc, @@ -491,7 +491,7 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc, val, -1, &replaced); - state->color_mgmt_changed = replaced; + state->color_mgmt_changed |= replaced; return ret; } else if (crtc->funcs->atomic_set_property) return crtc->funcs->atomic_set_property(crtc, state, property, val); diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index f1d9f0569d7f..ddebe54cd5ca 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -1121,16 +1121,14 @@ static int drm_connector_register_all(struct drm_device *dev) struct drm_connector *connector; int ret; - mutex_lock(&dev->mode_config.mutex); - - drm_for_each_connector(connector, dev) { + /* FIXME: taking the mode config mutex ends up in a clash with + * fbcon/backlight registration */ + list_for_each_entry(connector, &dev->mode_config.connector_list, head) { ret = drm_connector_register(connector); if (ret) goto err; } - mutex_unlock(&dev->mode_config.mutex); - return 0; err: @@ -5406,6 +5404,9 @@ int drm_mode_page_flip_ioctl(struct drm_device *dev, struct drm_pending_vblank_event *e = NULL; int ret = -EINVAL; + if (!drm_core_check_feature(dev, DRIVER_MODESET)) + return -EINVAL; + if (page_flip->flags & ~DRM_MODE_PAGE_FLIP_FLAGS || page_flip->reserved != 0) return -EINVAL; diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 7df26d4b7ad8..637a0aa4d3a0 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -74,6 +74,8 @@ #define EDID_QUIRK_FORCE_8BPC (1 << 8) /* Force 12bpc */ #define EDID_QUIRK_FORCE_12BPC (1 << 9) +/* Force 6bpc */ +#define EDID_QUIRK_FORCE_6BPC (1 << 10) struct detailed_mode_closure { struct drm_connector *connector; @@ -100,6 +102,9 @@ static struct edid_quirk { /* Unknown Acer */ { "ACR", 2423, EDID_QUIRK_FIRST_DETAILED_PREFERRED }, + /* AEO model 0 reports 8 bpc, but is a 6 bpc panel */ + { "AEO", 0, EDID_QUIRK_FORCE_6BPC }, + /* Belinea 10 15 55 */ { "MAX", 1516, EDID_QUIRK_PREFER_LARGE_60 }, { "MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60 }, @@ -3862,6 +3867,20 @@ static void drm_add_display_info(struct edid *edid, /* HDMI deep color modes supported? Assign to info, if so */ drm_assign_hdmi_deep_color_info(edid, info, connector); + /* + * Digital sink with "DFP 1.x compliant TMDS" according to EDID 1.3? + * + * For such displays, the DFP spec 1.0, section 3.10 "EDID support" + * tells us to assume 8 bpc color depth if the EDID doesn't have + * extensions which tell otherwise. + */ + if ((info->bpc == 0) && (edid->revision < 4) && + (edid->input & DRM_EDID_DIGITAL_TYPE_DVI)) { + info->bpc = 8; + DRM_DEBUG("%s: Assigning DFP sink color depth as %d bpc.\n", + connector->name, info->bpc); + } + /* Only defined for 1.4 with digital displays */ if (edid->revision < 4) return; @@ -4082,6 +4101,9 @@ int drm_add_edid_modes(struct drm_connector *connector, struct edid *edid) drm_add_display_info(edid, &connector->display_info, connector); + if (quirks & EDID_QUIRK_FORCE_6BPC) + connector->display_info.bpc = 6; + if (quirks & EDID_QUIRK_FORCE_8BPC) connector->display_info.bpc = 8; diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index ce54e985d91b..0a06f9120b5a 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -464,7 +464,7 @@ static bool drm_fb_helper_is_bound(struct drm_fb_helper *fb_helper) /* Sometimes user space wants everything disabled, so don't steal the * display if there's a master. */ - if (lockless_dereference(dev->master)) + if (READ_ONCE(dev->master)) return false; drm_for_each_crtc(crtc, dev) { diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c index 87ef34150d46..b382cf505262 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c @@ -1333,8 +1333,6 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu, if (ret < 0) return ret; - mutex_lock(&gpu->lock); - /* * TODO * @@ -1348,16 +1346,18 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu, if (unlikely(event == ~0U)) { DRM_ERROR("no free event\n"); ret = -EBUSY; - goto out_unlock; + goto out_pm_put; } fence = etnaviv_gpu_fence_alloc(gpu); if (!fence) { event_free(gpu, event); ret = -ENOMEM; - goto out_unlock; + goto out_pm_put; } + mutex_lock(&gpu->lock); + gpu->event[event].fence = fence; submit->fence = fence->seqno; gpu->active_fence = submit->fence; @@ -1395,9 +1395,9 @@ int etnaviv_gpu_submit(struct etnaviv_gpu *gpu, hangcheck_timer_reset(gpu); ret = 0; -out_unlock: mutex_unlock(&gpu->lock); +out_pm_put: etnaviv_gpu_pm_put(gpu); return ret; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 21f939074abc..f68c78918d63 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -882,11 +882,12 @@ struct i915_gem_context { struct i915_ctx_hang_stats hang_stats; - /* Unique identifier for this context, used by the hw for tracking */ unsigned long flags; #define CONTEXT_NO_ZEROMAP BIT(0) #define CONTEXT_NO_ERROR_CAPTURE BIT(1) - unsigned hw_id; + + /* Unique identifier for this context, used by the hw for tracking */ + unsigned int hw_id; u32 user_handle; u32 ggtt_alignment; @@ -1854,6 +1855,7 @@ struct drm_i915_private { enum modeset_restore modeset_restore; struct mutex modeset_restore_lock; struct drm_atomic_state *modeset_restore_state; + struct drm_modeset_acquire_ctx reset_ctx; struct list_head vm_list; /* Global list of all address spaces */ struct i915_ggtt ggtt; /* VM representing the global address space */ @@ -1962,6 +1964,13 @@ struct drm_i915_private { struct i915_suspend_saved_registers regfile; struct vlv_s0ix_state vlv_s0ix_state; + enum { + I915_SKL_SAGV_UNKNOWN = 0, + I915_SKL_SAGV_DISABLED, + I915_SKL_SAGV_ENABLED, + I915_SKL_SAGV_NOT_CONTROLLED + } skl_sagv_status; + struct { /* * Raw watermark latency values: @@ -3590,6 +3599,7 @@ int i915_gem_evict_vm(struct i915_address_space *vm, bool do_idle); /* belongs in i915_gem_gtt.h */ static inline void i915_gem_chipset_flush(struct drm_i915_private *dev_priv) { + wmb(); if (INTEL_GEN(dev_priv) < 6) intel_gtt_chipset_flush(); } diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 11681501d7b1..a77ce9983f69 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -879,9 +879,12 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, ret = i915_gem_shmem_pread(dev, obj, args, file); /* pread for non shmem backed objects */ - if (ret == -EFAULT || ret == -ENODEV) + if (ret == -EFAULT || ret == -ENODEV) { + intel_runtime_pm_get(to_i915(dev)); ret = i915_gem_gtt_pread(dev, obj, args->size, args->offset, args->data_ptr); + intel_runtime_pm_put(to_i915(dev)); + } out: drm_gem_object_unreference(&obj->base); @@ -1306,7 +1309,7 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, * textures). Fallback to the shmem path in that case. */ } - if (ret == -EFAULT) { + if (ret == -EFAULT || ret == -ENOSPC) { if (obj->phys_handle) ret = i915_gem_phys_pwrite(obj, args, file); else if (i915_gem_object_has_struct_page(obj)) @@ -3169,6 +3172,8 @@ static void i915_gem_reset_engine_cleanup(struct intel_engine_cs *engine) } intel_ring_init_seqno(engine, engine->last_submitted_seqno); + + engine->i915->gt.active_engines &= ~intel_engine_flag(engine); } void i915_gem_reset(struct drm_device *dev) @@ -3186,6 +3191,7 @@ void i915_gem_reset(struct drm_device *dev) for_each_engine(engine, dev_priv) i915_gem_reset_engine_cleanup(engine); + mod_delayed_work(dev_priv->wq, &dev_priv->gt.idle_work, 0); i915_gem_context_reset(dev); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index 1978633e7549..b35e5b6475b2 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -943,8 +943,6 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, { const unsigned other_rings = ~intel_engine_flag(req->engine); struct i915_vma *vma; - uint32_t flush_domains = 0; - bool flush_chipset = false; int ret; list_for_each_entry(vma, vmas, exec_list) { @@ -957,16 +955,11 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, } if (obj->base.write_domain & I915_GEM_DOMAIN_CPU) - flush_chipset |= i915_gem_clflush_object(obj, false); - - flush_domains |= obj->base.write_domain; + i915_gem_clflush_object(obj, false); } - if (flush_chipset) - i915_gem_chipset_flush(req->engine->i915); - - if (flush_domains & I915_GEM_DOMAIN_GTT) - wmb(); + /* Unconditionally flush any chipset caches (for streaming writes). */ + i915_gem_chipset_flush(req->engine->i915); /* Unconditionally invalidate gpu caches and ensure that we do flush * any residual writes from the previous batch. diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 10f1e32767e6..7a30af79d799 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -2873,6 +2873,7 @@ void i915_ggtt_cleanup_hw(struct drm_device *dev) struct i915_hw_ppgtt *ppgtt = dev_priv->mm.aliasing_ppgtt; ppgtt->base.cleanup(&ppgtt->base); + kfree(ppgtt); } i915_gem_cleanup_stolen(dev); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index ce14fe09d962..bf2cad3f9e1f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1536,6 +1536,7 @@ enum skl_disp_power_wells { #define BALANCE_LEG_MASK(port) (7<<(8+3*(port))) /* Balance leg disable bits */ #define BALANCE_LEG_DISABLE_SHIFT 23 +#define BALANCE_LEG_DISABLE(port) (1 << (23 + (port))) /* * Fence registers @@ -7144,6 +7145,15 @@ enum { #define GEN6_PCODE_MAILBOX _MMIO(0x138124) #define GEN6_PCODE_READY (1<<31) +#define GEN6_PCODE_ERROR_MASK 0xFF +#define GEN6_PCODE_SUCCESS 0x0 +#define GEN6_PCODE_ILLEGAL_CMD 0x1 +#define GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x2 +#define GEN6_PCODE_TIMEOUT 0x3 +#define GEN6_PCODE_UNIMPLEMENTED_CMD 0xFF +#define GEN7_PCODE_TIMEOUT 0x2 +#define GEN7_PCODE_ILLEGAL_DATA 0x3 +#define GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE 0x10 #define GEN6_PCODE_WRITE_RC6VIDS 0x4 #define GEN6_PCODE_READ_RC6VIDS 0x5 #define GEN6_ENCODE_RC6_VID(mv) (((mv) - 245) / 5) @@ -7165,6 +7175,10 @@ enum { #define HSW_PCODE_DE_WRITE_FREQ_REQ 0x17 #define DISPLAY_IPS_CONTROL 0x19 #define HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL 0x1A +#define GEN9_PCODE_SAGV_CONTROL 0x21 +#define GEN9_SAGV_DISABLE 0x0 +#define GEN9_SAGV_IS_DISABLED 0x1 +#define GEN9_SAGV_ENABLE 0x3 #define GEN6_PCODE_DATA _MMIO(0x138128) #define GEN6_PCODE_FREQ_IA_RATIO_SHIFT 8 #define GEN6_PCODE_FREQ_RING_RATIO_SHIFT 16 diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index 6700a7be7f78..d32f586f9c05 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -600,6 +600,8 @@ static void i915_audio_component_codec_wake_override(struct device *dev, if (!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv)) return; + i915_audio_component_get_power(dev); + /* * Enable/disable generating the codec wake signal, overriding the * internal logic to generate the codec wake to controller. @@ -615,6 +617,8 @@ static void i915_audio_component_codec_wake_override(struct device *dev, I915_WRITE(HSW_AUD_CHICKENBIT, tmp); usleep_range(1000, 1500); } + + i915_audio_component_put_power(dev); } /* Get CDCLK in kHz */ @@ -648,6 +652,7 @@ static int i915_audio_component_sync_audio_rate(struct device *dev, !IS_HASWELL(dev_priv)) return 0; + i915_audio_component_get_power(dev); mutex_lock(&dev_priv->av_mutex); /* 1. get the pipe */ intel_encoder = dev_priv->dig_port_map[port]; @@ -698,6 +703,7 @@ static int i915_audio_component_sync_audio_rate(struct device *dev, unlock: mutex_unlock(&dev_priv->av_mutex); + i915_audio_component_put_power(dev); return err; } diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 3edb9580928e..c3b33a10c15c 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -41,15 +41,15 @@ * be moved to FW_FAILED. */ -#define I915_CSR_KBL "i915/kbl_dmc_ver1.bin" +#define I915_CSR_KBL "i915/kbl_dmc_ver1_01.bin" MODULE_FIRMWARE(I915_CSR_KBL); #define KBL_CSR_VERSION_REQUIRED CSR_VERSION(1, 1) -#define I915_CSR_SKL "i915/skl_dmc_ver1.bin" +#define I915_CSR_SKL "i915/skl_dmc_ver1_26.bin" MODULE_FIRMWARE(I915_CSR_SKL); -#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 23) +#define SKL_CSR_VERSION_REQUIRED CSR_VERSION(1, 26) -#define I915_CSR_BXT "i915/bxt_dmc_ver1.bin" +#define I915_CSR_BXT "i915/bxt_dmc_ver1_07.bin" MODULE_FIRMWARE(I915_CSR_BXT); #define BXT_CSR_VERSION_REQUIRED CSR_VERSION(1, 7) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index dd1d6fe12297..1a7efac65fd5 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -145,7 +145,7 @@ static const struct ddi_buf_trans skl_ddi_translations_dp[] = { static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = { { 0x0000201B, 0x000000A2, 0x0 }, { 0x00005012, 0x00000088, 0x0 }, - { 0x80007011, 0x000000CD, 0x0 }, + { 0x80007011, 0x000000CD, 0x1 }, { 0x80009010, 0x000000C0, 0x1 }, { 0x0000201B, 0x0000009D, 0x0 }, { 0x80005012, 0x000000C0, 0x1 }, @@ -158,7 +158,7 @@ static const struct ddi_buf_trans skl_u_ddi_translations_dp[] = { static const struct ddi_buf_trans skl_y_ddi_translations_dp[] = { { 0x00000018, 0x000000A2, 0x0 }, { 0x00005012, 0x00000088, 0x0 }, - { 0x80007011, 0x000000CD, 0x0 }, + { 0x80007011, 0x000000CD, 0x3 }, { 0x80009010, 0x000000C0, 0x3 }, { 0x00000018, 0x0000009D, 0x0 }, { 0x80005012, 0x000000C0, 0x3 }, @@ -388,6 +388,40 @@ skl_get_buf_trans_hdmi(struct drm_i915_private *dev_priv, int *n_entries) } } +static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port) +{ + int n_hdmi_entries; + int hdmi_level; + int hdmi_default_entry; + + hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift; + + if (IS_BROXTON(dev_priv)) + return hdmi_level; + + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) { + skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries); + hdmi_default_entry = 8; + } else if (IS_BROADWELL(dev_priv)) { + n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); + hdmi_default_entry = 7; + } else if (IS_HASWELL(dev_priv)) { + n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi); + hdmi_default_entry = 6; + } else { + WARN(1, "ddi translation table missing\n"); + n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); + hdmi_default_entry = 7; + } + + /* Choose a good default if VBT is badly populated */ + if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN || + hdmi_level >= n_hdmi_entries) + hdmi_level = hdmi_default_entry; + + return hdmi_level; +} + /* * Starting with Haswell, DDI port buffers must be programmed with correct * values in advance. The buffer values are different for FDI and DP modes, @@ -399,7 +433,7 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); u32 iboost_bit = 0; - int i, n_hdmi_entries, n_dp_entries, n_edp_entries, hdmi_default_entry, + int i, n_hdmi_entries, n_dp_entries, n_edp_entries, size; int hdmi_level; enum port port; @@ -410,7 +444,7 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) const struct ddi_buf_trans *ddi_translations; port = intel_ddi_get_encoder_port(encoder); - hdmi_level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift; + hdmi_level = intel_ddi_hdmi_level(dev_priv, port); if (IS_BROXTON(dev_priv)) { if (encoder->type != INTEL_OUTPUT_HDMI) @@ -430,7 +464,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) skl_get_buf_trans_edp(dev_priv, &n_edp_entries); ddi_translations_hdmi = skl_get_buf_trans_hdmi(dev_priv, &n_hdmi_entries); - hdmi_default_entry = 8; /* If we're boosting the current, set bit 31 of trans1 */ if (dev_priv->vbt.ddi_port_info[port].hdmi_boost_level || dev_priv->vbt.ddi_port_info[port].dp_boost_level) @@ -456,7 +489,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); - hdmi_default_entry = 7; } else if (IS_HASWELL(dev_priv)) { ddi_translations_fdi = hsw_ddi_translations_fdi; ddi_translations_dp = hsw_ddi_translations_dp; @@ -464,7 +496,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) ddi_translations_hdmi = hsw_ddi_translations_hdmi; n_dp_entries = n_edp_entries = ARRAY_SIZE(hsw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(hsw_ddi_translations_hdmi); - hdmi_default_entry = 6; } else { WARN(1, "ddi translation table missing\n"); ddi_translations_edp = bdw_ddi_translations_dp; @@ -474,7 +505,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) n_edp_entries = ARRAY_SIZE(bdw_ddi_translations_edp); n_dp_entries = ARRAY_SIZE(bdw_ddi_translations_dp); n_hdmi_entries = ARRAY_SIZE(bdw_ddi_translations_hdmi); - hdmi_default_entry = 7; } switch (encoder->type) { @@ -505,11 +535,6 @@ void intel_prepare_ddi_buffer(struct intel_encoder *encoder) if (encoder->type != INTEL_OUTPUT_HDMI) return; - /* Choose a good default if VBT is badly populated */ - if (hdmi_level == HDMI_LEVEL_SHIFT_UNKNOWN || - hdmi_level >= n_hdmi_entries) - hdmi_level = hdmi_default_entry; - /* Entry 9 is for HDMI: */ I915_WRITE(DDI_BUF_TRANS_LO(port, i), ddi_translations_hdmi[hdmi_level].trans1 | iboost_bit); @@ -1379,14 +1404,30 @@ void intel_ddi_disable_pipe_clock(struct intel_crtc *intel_crtc) TRANS_CLK_SEL_DISABLED); } -static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv, - u32 level, enum port port, int type) +static void _skl_ddi_set_iboost(struct drm_i915_private *dev_priv, + enum port port, uint8_t iboost) { + u32 tmp; + + tmp = I915_READ(DISPIO_CR_TX_BMU_CR0); + tmp &= ~(BALANCE_LEG_MASK(port) | BALANCE_LEG_DISABLE(port)); + if (iboost) + tmp |= iboost << BALANCE_LEG_SHIFT(port); + else + tmp |= BALANCE_LEG_DISABLE(port); + I915_WRITE(DISPIO_CR_TX_BMU_CR0, tmp); +} + +static void skl_ddi_set_iboost(struct intel_encoder *encoder, u32 level) +{ + struct intel_digital_port *intel_dig_port = enc_to_dig_port(&encoder->base); + struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev); + enum port port = intel_dig_port->port; + int type = encoder->type; const struct ddi_buf_trans *ddi_translations; uint8_t iboost; uint8_t dp_iboost, hdmi_iboost; int n_entries; - u32 reg; /* VBT may override standard boost values */ dp_iboost = dev_priv->vbt.ddi_port_info[port].dp_boost_level; @@ -1428,16 +1469,10 @@ static void skl_ddi_set_iboost(struct drm_i915_private *dev_priv, return; } - reg = I915_READ(DISPIO_CR_TX_BMU_CR0); - reg &= ~BALANCE_LEG_MASK(port); - reg &= ~(1 << (BALANCE_LEG_DISABLE_SHIFT + port)); - - if (iboost) - reg |= iboost << BALANCE_LEG_SHIFT(port); - else - reg |= 1 << (BALANCE_LEG_DISABLE_SHIFT + port); + _skl_ddi_set_iboost(dev_priv, port, iboost); - I915_WRITE(DISPIO_CR_TX_BMU_CR0, reg); + if (port == PORT_A && intel_dig_port->max_lanes == 4) + _skl_ddi_set_iboost(dev_priv, PORT_E, iboost); } static void bxt_ddi_vswing_sequence(struct drm_i915_private *dev_priv, @@ -1568,7 +1603,7 @@ uint32_t ddi_signal_levels(struct intel_dp *intel_dp) level = translate_signal_level(signal_levels); if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) - skl_ddi_set_iboost(dev_priv, level, port, encoder->type); + skl_ddi_set_iboost(encoder, level); else if (IS_BROXTON(dev_priv)) bxt_ddi_vswing_sequence(dev_priv, level, port, encoder->type); @@ -1637,6 +1672,10 @@ static void intel_ddi_pre_enable(struct intel_encoder *intel_encoder) intel_dp_stop_link_train(intel_dp); } else if (type == INTEL_OUTPUT_HDMI) { struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder); + int level = intel_ddi_hdmi_level(dev_priv, port); + + if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) + skl_ddi_set_iboost(intel_encoder, level); intel_hdmi->set_infoframes(encoder, crtc->config->has_hdmi_sink, diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index c457eed76f1f..175595fc3e45 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -3093,40 +3093,110 @@ static void intel_update_primary_planes(struct drm_device *dev) for_each_crtc(dev, crtc) { struct intel_plane *plane = to_intel_plane(crtc->primary); - struct intel_plane_state *plane_state; - - drm_modeset_lock_crtc(crtc, &plane->base); - plane_state = to_intel_plane_state(plane->base.state); + struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); if (plane_state->visible) plane->update_plane(&plane->base, to_intel_crtc_state(crtc->state), plane_state); + } +} + +static int +__intel_display_resume(struct drm_device *dev, + struct drm_atomic_state *state) +{ + struct drm_crtc_state *crtc_state; + struct drm_crtc *crtc; + int i, ret; + + intel_modeset_setup_hw_state(dev); + i915_redisable_vga(dev); + + if (!state) + return 0; - drm_modeset_unlock_crtc(crtc); + for_each_crtc_in_state(state, crtc, crtc_state, i) { + /* + * Force recalculation even if we restore + * current state. With fast modeset this may not result + * in a modeset when the state is compatible. + */ + crtc_state->mode_changed = true; } + + /* ignore any reset values/BIOS leftovers in the WM registers */ + to_intel_atomic_state(state)->skip_intermediate_wm = true; + + ret = drm_atomic_commit(state); + + WARN_ON(ret == -EDEADLK); + return ret; } void intel_prepare_reset(struct drm_i915_private *dev_priv) { + struct drm_device *dev = &dev_priv->drm; + struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx; + struct drm_atomic_state *state; + int ret; + /* no reset support for gen2 */ if (IS_GEN2(dev_priv)) return; - /* reset doesn't touch the display */ + /* + * Need mode_config.mutex so that we don't + * trample ongoing ->detect() and whatnot. + */ + mutex_lock(&dev->mode_config.mutex); + drm_modeset_acquire_init(ctx, 0); + while (1) { + ret = drm_modeset_lock_all_ctx(dev, ctx); + if (ret != -EDEADLK) + break; + + drm_modeset_backoff(ctx); + } + + /* reset doesn't touch the display, but flips might get nuked anyway, */ if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) return; - drm_modeset_lock_all(&dev_priv->drm); /* * Disabling the crtcs gracefully seems nicer. Also the * g33 docs say we should at least disable all the planes. */ - intel_display_suspend(&dev_priv->drm); + state = drm_atomic_helper_duplicate_state(dev, ctx); + if (IS_ERR(state)) { + ret = PTR_ERR(state); + state = NULL; + DRM_ERROR("Duplicating state failed with %i\n", ret); + goto err; + } + + ret = drm_atomic_helper_disable_all(dev, ctx); + if (ret) { + DRM_ERROR("Suspending crtc's failed with %i\n", ret); + goto err; + } + + dev_priv->modeset_restore_state = state; + state->acquire_ctx = ctx; + return; + +err: + drm_atomic_state_free(state); } void intel_finish_reset(struct drm_i915_private *dev_priv) { + struct drm_device *dev = &dev_priv->drm; + struct drm_modeset_acquire_ctx *ctx = &dev_priv->reset_ctx; + struct drm_atomic_state *state = dev_priv->modeset_restore_state; + int ret; + /* * Flips in the rings will be nuked by the reset, * so complete all pending flips so that user space @@ -3138,6 +3208,8 @@ void intel_finish_reset(struct drm_i915_private *dev_priv) if (IS_GEN2(dev_priv)) return; + dev_priv->modeset_restore_state = NULL; + /* reset doesn't touch the display */ if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv)) { /* @@ -3149,29 +3221,32 @@ void intel_finish_reset(struct drm_i915_private *dev_priv) * FIXME: Atomic will make this obsolete since we won't schedule * CS-based flips (which might get lost in gpu resets) any more. */ - intel_update_primary_planes(&dev_priv->drm); - return; - } - - /* - * The display has been reset as well, - * so need a full re-initialization. - */ - intel_runtime_pm_disable_interrupts(dev_priv); - intel_runtime_pm_enable_interrupts(dev_priv); + intel_update_primary_planes(dev); + } else { + /* + * The display has been reset as well, + * so need a full re-initialization. + */ + intel_runtime_pm_disable_interrupts(dev_priv); + intel_runtime_pm_enable_interrupts(dev_priv); - intel_modeset_init_hw(&dev_priv->drm); + intel_modeset_init_hw(dev); - spin_lock_irq(&dev_priv->irq_lock); - if (dev_priv->display.hpd_irq_setup) - dev_priv->display.hpd_irq_setup(dev_priv); - spin_unlock_irq(&dev_priv->irq_lock); + spin_lock_irq(&dev_priv->irq_lock); + if (dev_priv->display.hpd_irq_setup) + dev_priv->display.hpd_irq_setup(dev_priv); + spin_unlock_irq(&dev_priv->irq_lock); - intel_display_resume(&dev_priv->drm); + ret = __intel_display_resume(dev, state); + if (ret) + DRM_ERROR("Restoring old state failed with %i\n", ret); - intel_hpd_init(dev_priv); + intel_hpd_init(dev_priv); + } - drm_modeset_unlock_all(&dev_priv->drm); + drm_modeset_drop_locks(ctx); + drm_modeset_acquire_fini(ctx); + mutex_unlock(&dev->mode_config.mutex); } static bool intel_crtc_has_pending_flip(struct drm_crtc *crtc) @@ -5691,15 +5766,7 @@ static bool skl_cdclk_pcu_ready(struct drm_i915_private *dev_priv) static bool skl_cdclk_wait_for_pcu_ready(struct drm_i915_private *dev_priv) { - unsigned int i; - - for (i = 0; i < 15; i++) { - if (skl_cdclk_pcu_ready(dev_priv)) - return true; - udelay(10); - } - - return false; + return _wait_for(skl_cdclk_pcu_ready(dev_priv), 3000, 10) == 0; } static void skl_set_cdclk(struct drm_i915_private *dev_priv, int cdclk, int vco) @@ -12114,21 +12181,11 @@ connected_sink_compute_bpp(struct intel_connector *connector, pipe_config->pipe_bpp = connector->base.display_info.bpc*3; } - /* Clamp bpp to default limit on screens without EDID 1.4 */ - if (connector->base.display_info.bpc == 0) { - int type = connector->base.connector_type; - int clamp_bpp = 24; - - /* Fall back to 18 bpp when DP sink capability is unknown. */ - if (type == DRM_MODE_CONNECTOR_DisplayPort || - type == DRM_MODE_CONNECTOR_eDP) - clamp_bpp = 18; - - if (bpp > clamp_bpp) { - DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of %d\n", - bpp, clamp_bpp); - pipe_config->pipe_bpp = clamp_bpp; - } + /* Clamp bpp to 8 on screens without EDID 1.4 */ + if (connector->base.display_info.bpc == 0 && bpp > 24) { + DRM_DEBUG_KMS("clamping display bpp (was %d) to default limit of 24\n", + bpp); + pipe_config->pipe_bpp = 24; } } @@ -13702,6 +13759,13 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_state->cdclk_pll_vco != dev_priv->cdclk_pll.vco)) dev_priv->display.modeset_commit_cdclk(state); + /* + * SKL workaround: bspec recommends we disable the SAGV when we + * have more then one pipe enabled + */ + if (IS_SKYLAKE(dev_priv) && !skl_can_enable_sagv(state)) + skl_disable_sagv(dev_priv); + intel_modeset_verify_disabled(dev); } @@ -13775,6 +13839,10 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state) intel_modeset_verify_crtc(crtc, old_crtc_state, crtc->state); } + if (IS_SKYLAKE(dev_priv) && intel_state->modeset && + skl_can_enable_sagv(state)) + skl_enable_sagv(dev_priv); + drm_atomic_helper_commit_hw_done(state); if (intel_state->modeset) @@ -16174,9 +16242,10 @@ void intel_display_resume(struct drm_device *dev) struct drm_atomic_state *state = dev_priv->modeset_restore_state; struct drm_modeset_acquire_ctx ctx; int ret; - bool setup = false; dev_priv->modeset_restore_state = NULL; + if (state) + state->acquire_ctx = &ctx; /* * This is a cludge because with real atomic modeset mode_config.mutex @@ -16187,43 +16256,17 @@ void intel_display_resume(struct drm_device *dev) mutex_lock(&dev->mode_config.mutex); drm_modeset_acquire_init(&ctx, 0); -retry: - ret = drm_modeset_lock_all_ctx(dev, &ctx); - - if (ret == 0 && !setup) { - setup = true; - - intel_modeset_setup_hw_state(dev); - i915_redisable_vga(dev); - } - - if (ret == 0 && state) { - struct drm_crtc_state *crtc_state; - struct drm_crtc *crtc; - int i; - - state->acquire_ctx = &ctx; - - /* ignore any reset values/BIOS leftovers in the WM registers */ - to_intel_atomic_state(state)->skip_intermediate_wm = true; - - for_each_crtc_in_state(state, crtc, crtc_state, i) { - /* - * Force recalculation even if we restore - * current state. With fast modeset this may not result - * in a modeset when the state is compatible. - */ - crtc_state->mode_changed = true; - } - - ret = drm_atomic_commit(state); - } + while (1) { + ret = drm_modeset_lock_all_ctx(dev, &ctx); + if (ret != -EDEADLK) + break; - if (ret == -EDEADLK) { drm_modeset_backoff(&ctx); - goto retry; } + if (!ret) + ret = __intel_display_resume(dev, state); + drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); mutex_unlock(&dev->mode_config.mutex); diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index cc937a19b1ba..ff399b9a5c1f 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1716,6 +1716,9 @@ void ilk_wm_get_hw_state(struct drm_device *dev); void skl_wm_get_hw_state(struct drm_device *dev); void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, struct skl_ddb_allocation *ddb /* out */); +bool skl_can_enable_sagv(struct drm_atomic_state *state); +int skl_enable_sagv(struct drm_i915_private *dev_priv); +int skl_disable_sagv(struct drm_i915_private *dev_priv); uint32_t ilk_pipe_pixel_rate(const struct intel_crtc_state *pipe_config); bool ilk_disable_lp_wm(struct drm_device *dev); int sanitize_rc6_option(struct drm_i915_private *dev_priv, int enable_rc6); diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c index 6a7ad3ed1463..3836a1c79714 100644 --- a/drivers/gpu/drm/i915/intel_fbc.c +++ b/drivers/gpu/drm/i915/intel_fbc.c @@ -1230,12 +1230,29 @@ static int intel_sanitize_fbc_option(struct drm_i915_private *dev_priv) if (i915.enable_fbc >= 0) return !!i915.enable_fbc; + if (!HAS_FBC(dev_priv)) + return 0; + if (IS_BROADWELL(dev_priv)) return 1; return 0; } +static bool need_fbc_vtd_wa(struct drm_i915_private *dev_priv) +{ +#ifdef CONFIG_INTEL_IOMMU + /* WaFbcTurnOffFbcWhenHyperVisorIsUsed:skl,bxt */ + if (intel_iommu_gfx_mapped && + (IS_SKYLAKE(dev_priv) || IS_BROXTON(dev_priv))) { + DRM_INFO("Disabling framebuffer compression (FBC) to prevent screen flicker with VT-d enabled\n"); + return true; + } +#endif + + return false; +} + /** * intel_fbc_init - Initialize FBC * @dev_priv: the i915 device @@ -1253,6 +1270,9 @@ void intel_fbc_init(struct drm_i915_private *dev_priv) fbc->active = false; fbc->work.scheduled = false; + if (need_fbc_vtd_wa(dev_priv)) + mkwrite_device_info(dev_priv)->has_fbc = false; + i915.enable_fbc = intel_sanitize_fbc_option(dev_priv); DRM_DEBUG_KMS("Sanitized enable_fbc value: %d\n", i915.enable_fbc); diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index 86b00c6db1a6..3e3632c18733 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -782,7 +782,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous struct intel_fbdev *ifbdev = dev_priv->fbdev; struct fb_info *info; - if (!ifbdev) + if (!ifbdev || !ifbdev->fb) return; info = ifbdev->helper.fbdev; @@ -827,31 +827,28 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous void intel_fbdev_output_poll_changed(struct drm_device *dev) { - struct drm_i915_private *dev_priv = to_i915(dev); - if (dev_priv->fbdev) - drm_fb_helper_hotplug_event(&dev_priv->fbdev->helper); + struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; + + if (ifbdev && ifbdev->fb) + drm_fb_helper_hotplug_event(&ifbdev->helper); } void intel_fbdev_restore_mode(struct drm_device *dev) { - int ret; - struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_fbdev *ifbdev = dev_priv->fbdev; - struct drm_fb_helper *fb_helper; + struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; if (!ifbdev) return; intel_fbdev_sync(ifbdev); + if (!ifbdev->fb) + return; - fb_helper = &ifbdev->helper; - - ret = drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper); - if (ret) { + if (drm_fb_helper_restore_fbdev_mode_unlocked(&ifbdev->helper)) { DRM_DEBUG("failed to restore crtc mode\n"); } else { - mutex_lock(&fb_helper->dev->struct_mutex); + mutex_lock(&dev->struct_mutex); intel_fb_obj_invalidate(ifbdev->fb->obj, ORIGIN_GTT); - mutex_unlock(&fb_helper->dev->struct_mutex); + mutex_unlock(&dev->struct_mutex); } } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index f4f3fcc8b3be..53e13c10e4ea 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2852,6 +2852,7 @@ bool ilk_disable_lp_wm(struct drm_device *dev) #define SKL_DDB_SIZE 896 /* in blocks */ #define BXT_DDB_SIZE 512 +#define SKL_SAGV_BLOCK_TIME 30 /* µs */ /* * Return the index of a plane in the SKL DDB and wm result arrays. Primary @@ -2875,6 +2876,153 @@ skl_wm_plane_id(const struct intel_plane *plane) } } +/* + * SAGV dynamically adjusts the system agent voltage and clock frequencies + * depending on power and performance requirements. The display engine access + * to system memory is blocked during the adjustment time. Because of the + * blocking time, having this enabled can cause full system hangs and/or pipe + * underruns if we don't meet all of the following requirements: + * + * - <= 1 pipe enabled + * - All planes can enable watermarks for latencies >= SAGV engine block time + * - We're not using an interlaced display configuration + */ +int +skl_enable_sagv(struct drm_i915_private *dev_priv) +{ + int ret; + + if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED || + dev_priv->skl_sagv_status == I915_SKL_SAGV_ENABLED) + return 0; + + DRM_DEBUG_KMS("Enabling the SAGV\n"); + mutex_lock(&dev_priv->rps.hw_lock); + + ret = sandybridge_pcode_write(dev_priv, GEN9_PCODE_SAGV_CONTROL, + GEN9_SAGV_ENABLE); + + /* We don't need to wait for the SAGV when enabling */ + mutex_unlock(&dev_priv->rps.hw_lock); + + /* + * Some skl systems, pre-release machines in particular, + * don't actually have an SAGV. + */ + if (ret == -ENXIO) { + DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n"); + dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED; + return 0; + } else if (ret < 0) { + DRM_ERROR("Failed to enable the SAGV\n"); + return ret; + } + + dev_priv->skl_sagv_status = I915_SKL_SAGV_ENABLED; + return 0; +} + +static int +skl_do_sagv_disable(struct drm_i915_private *dev_priv) +{ + int ret; + uint32_t temp = GEN9_SAGV_DISABLE; + + ret = sandybridge_pcode_read(dev_priv, GEN9_PCODE_SAGV_CONTROL, + &temp); + if (ret) + return ret; + else + return temp & GEN9_SAGV_IS_DISABLED; +} + +int +skl_disable_sagv(struct drm_i915_private *dev_priv) +{ + int ret, result; + + if (dev_priv->skl_sagv_status == I915_SKL_SAGV_NOT_CONTROLLED || + dev_priv->skl_sagv_status == I915_SKL_SAGV_DISABLED) + return 0; + + DRM_DEBUG_KMS("Disabling the SAGV\n"); + mutex_lock(&dev_priv->rps.hw_lock); + + /* bspec says to keep retrying for at least 1 ms */ + ret = wait_for(result = skl_do_sagv_disable(dev_priv), 1); + mutex_unlock(&dev_priv->rps.hw_lock); + + if (ret == -ETIMEDOUT) { + DRM_ERROR("Request to disable SAGV timed out\n"); + return -ETIMEDOUT; + } + + /* + * Some skl systems, pre-release machines in particular, + * don't actually have an SAGV. + */ + if (result == -ENXIO) { + DRM_DEBUG_DRIVER("No SAGV found on system, ignoring\n"); + dev_priv->skl_sagv_status = I915_SKL_SAGV_NOT_CONTROLLED; + return 0; + } else if (result < 0) { + DRM_ERROR("Failed to disable the SAGV\n"); + return result; + } + + dev_priv->skl_sagv_status = I915_SKL_SAGV_DISABLED; + return 0; +} + +bool skl_can_enable_sagv(struct drm_atomic_state *state) +{ + struct drm_device *dev = state->dev; + struct drm_i915_private *dev_priv = to_i915(dev); + struct intel_atomic_state *intel_state = to_intel_atomic_state(state); + struct drm_crtc *crtc; + enum pipe pipe; + int level, plane; + + /* + * SKL workaround: bspec recommends we disable the SAGV when we have + * more then one pipe enabled + * + * If there are no active CRTCs, no additional checks need be performed + */ + if (hweight32(intel_state->active_crtcs) == 0) + return true; + else if (hweight32(intel_state->active_crtcs) > 1) + return false; + + /* Since we're now guaranteed to only have one active CRTC... */ + pipe = ffs(intel_state->active_crtcs) - 1; + crtc = dev_priv->pipe_to_crtc_mapping[pipe]; + + if (crtc->state->mode.flags & DRM_MODE_FLAG_INTERLACE) + return false; + + for_each_plane(dev_priv, pipe, plane) { + /* Skip this plane if it's not enabled */ + if (intel_state->wm_results.plane[pipe][plane][0] == 0) + continue; + + /* Find the highest enabled wm level for this plane */ + for (level = ilk_wm_max_level(dev); + intel_state->wm_results.plane[pipe][plane][level] == 0; --level) + { } + + /* + * If any of the planes on this pipe don't enable wm levels + * that incur memory latencies higher then 30µs we can't enable + * the SAGV + */ + if (dev_priv->wm.skl_latency[level] < SKL_SAGV_BLOCK_TIME) + return false; + } + + return true; +} + static void skl_ddb_get_pipe_allocation_limits(struct drm_device *dev, const struct intel_crtc_state *cstate, @@ -3107,8 +3255,6 @@ skl_get_total_relative_data_rate(struct intel_crtc_state *intel_cstate) total_data_rate += intel_cstate->wm.skl.plane_y_data_rate[id]; } - WARN_ON(cstate->plane_mask && total_data_rate == 0); - return total_data_rate; } @@ -3344,6 +3490,8 @@ static uint32_t skl_wm_method2(uint32_t pixel_rate, uint32_t pipe_htotal, plane_bytes_per_line *= 4; plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512); plane_blocks_per_line /= 4; + } else if (tiling == DRM_FORMAT_MOD_NONE) { + plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512) + 1; } else { plane_blocks_per_line = DIV_ROUND_UP(plane_bytes_per_line, 512); } @@ -3910,9 +4058,24 @@ skl_compute_ddb(struct drm_atomic_state *state) * pretend that all pipes switched active status so that we'll * ensure a full DDB recompute. */ - if (dev_priv->wm.distrust_bios_wm) + if (dev_priv->wm.distrust_bios_wm) { + ret = drm_modeset_lock(&dev->mode_config.connection_mutex, + state->acquire_ctx); + if (ret) + return ret; + intel_state->active_pipe_changes = ~0; + /* + * We usually only initialize intel_state->active_crtcs if we + * we're doing a modeset; make sure this field is always + * initialized during the sanitization process that happens + * on the first commit too. + */ + if (!intel_state->modeset) + intel_state->active_crtcs = dev_priv->active_crtcs; + } + /* * If the modeset changes which CRTC's are active, we need to * recompute the DDB allocation for *all* active pipes, even @@ -3941,11 +4104,33 @@ skl_compute_ddb(struct drm_atomic_state *state) ret = skl_allocate_pipe_ddb(cstate, ddb); if (ret) return ret; + + ret = drm_atomic_add_affected_planes(state, &intel_crtc->base); + if (ret) + return ret; } return 0; } +static void +skl_copy_wm_for_pipe(struct skl_wm_values *dst, + struct skl_wm_values *src, + enum pipe pipe) +{ + dst->wm_linetime[pipe] = src->wm_linetime[pipe]; + memcpy(dst->plane[pipe], src->plane[pipe], + sizeof(dst->plane[pipe])); + memcpy(dst->plane_trans[pipe], src->plane_trans[pipe], + sizeof(dst->plane_trans[pipe])); + + dst->ddb.pipe[pipe] = src->ddb.pipe[pipe]; + memcpy(dst->ddb.y_plane[pipe], src->ddb.y_plane[pipe], + sizeof(dst->ddb.y_plane[pipe])); + memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe], + sizeof(dst->ddb.plane[pipe])); +} + static int skl_compute_wm(struct drm_atomic_state *state) { @@ -4018,8 +4203,10 @@ static void skl_update_wm(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct drm_i915_private *dev_priv = to_i915(dev); struct skl_wm_values *results = &dev_priv->wm.skl_results; + struct skl_wm_values *hw_vals = &dev_priv->wm.skl_hw; struct intel_crtc_state *cstate = to_intel_crtc_state(crtc->state); struct skl_pipe_wm *pipe_wm = &cstate->wm.skl.optimal; + int pipe; if ((results->dirty_pipes & drm_crtc_mask(crtc)) == 0) return; @@ -4031,8 +4218,12 @@ static void skl_update_wm(struct drm_crtc *crtc) skl_write_wm_values(dev_priv, results); skl_flush_wm_values(dev_priv, results); - /* store the new configuration */ - dev_priv->wm.skl_hw = *results; + /* + * Store the new configuration (but only for the pipes that have + * changed; the other values weren't recomputed). + */ + for_each_pipe_masked(dev_priv, pipe, results->dirty_pipes) + skl_copy_wm_for_pipe(hw_vals, results, pipe); mutex_unlock(&dev_priv->wm.wm_mutex); } @@ -4892,7 +5083,8 @@ void gen6_rps_idle(struct drm_i915_private *dev_priv) else gen6_set_rps(dev_priv, dev_priv->rps.idle_freq); dev_priv->rps.last_adj = 0; - I915_WRITE(GEN6_PMINTRMSK, 0xffffffff); + I915_WRITE(GEN6_PMINTRMSK, + gen6_sanitize_rps_pm_mask(dev_priv, ~0)); } mutex_unlock(&dev_priv->rps.hw_lock); @@ -6573,9 +6765,7 @@ void intel_init_gt_powersave(struct drm_i915_private *dev_priv) void intel_cleanup_gt_powersave(struct drm_i915_private *dev_priv) { - if (IS_CHERRYVIEW(dev_priv)) - return; - else if (IS_VALLEYVIEW(dev_priv)) + if (IS_VALLEYVIEW(dev_priv)) valleyview_cleanup_gt_powersave(dev_priv); if (!i915.enable_rc6) @@ -7657,8 +7847,53 @@ void intel_init_pm(struct drm_device *dev) } } +static inline int gen6_check_mailbox_status(struct drm_i915_private *dev_priv) +{ + uint32_t flags = + I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK; + + switch (flags) { + case GEN6_PCODE_SUCCESS: + return 0; + case GEN6_PCODE_UNIMPLEMENTED_CMD: + case GEN6_PCODE_ILLEGAL_CMD: + return -ENXIO; + case GEN6_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: + return -EOVERFLOW; + case GEN6_PCODE_TIMEOUT: + return -ETIMEDOUT; + default: + MISSING_CASE(flags) + return 0; + } +} + +static inline int gen7_check_mailbox_status(struct drm_i915_private *dev_priv) +{ + uint32_t flags = + I915_READ_FW(GEN6_PCODE_MAILBOX) & GEN6_PCODE_ERROR_MASK; + + switch (flags) { + case GEN6_PCODE_SUCCESS: + return 0; + case GEN6_PCODE_ILLEGAL_CMD: + return -ENXIO; + case GEN7_PCODE_TIMEOUT: + return -ETIMEDOUT; + case GEN7_PCODE_ILLEGAL_DATA: + return -EINVAL; + case GEN7_PCODE_MIN_FREQ_TABLE_GT_RATIO_OUT_OF_RANGE: + return -EOVERFLOW; + default: + MISSING_CASE(flags); + return 0; + } +} + int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val) { + int status; + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock)); /* GEN6_PCODE_* are outside of the forcewake domain, we can @@ -7685,12 +7920,25 @@ int sandybridge_pcode_read(struct drm_i915_private *dev_priv, u32 mbox, u32 *val *val = I915_READ_FW(GEN6_PCODE_DATA); I915_WRITE_FW(GEN6_PCODE_DATA, 0); + if (INTEL_GEN(dev_priv) > 6) + status = gen7_check_mailbox_status(dev_priv); + else + status = gen6_check_mailbox_status(dev_priv); + + if (status) { + DRM_DEBUG_DRIVER("warning: pcode (read) mailbox access failed: %d\n", + status); + return status; + } + return 0; } int sandybridge_pcode_write(struct drm_i915_private *dev_priv, - u32 mbox, u32 val) + u32 mbox, u32 val) { + int status; + WARN_ON(!mutex_is_locked(&dev_priv->rps.hw_lock)); /* GEN6_PCODE_* are outside of the forcewake domain, we can @@ -7715,6 +7963,17 @@ int sandybridge_pcode_write(struct drm_i915_private *dev_priv, I915_WRITE_FW(GEN6_PCODE_DATA, 0); + if (INTEL_GEN(dev_priv) > 6) + status = gen7_check_mailbox_status(dev_priv); + else + status = gen6_check_mailbox_status(dev_priv); + + if (status) { + DRM_DEBUG_DRIVER("warning: pcode (write) mailbox access failed: %d\n", + status); + return status; + } + return 0; } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index cca7792f26d5..1d3161bbea24 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -1178,8 +1178,8 @@ static int bxt_init_workarounds(struct intel_engine_cs *engine) I915_WRITE(GEN8_L3SQCREG1, L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2)); - /* WaInsertDummyPushConstPs:bxt */ - if (IS_BXT_REVID(dev_priv, 0, BXT_REVID_B0)) + /* WaToEnableHwFixForPushConstHWBug:bxt */ + if (IS_BXT_REVID(dev_priv, BXT_REVID_C0, REVID_FOREVER)) WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); @@ -1222,8 +1222,8 @@ static int kbl_init_workarounds(struct intel_engine_cs *engine) I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_RO_PERF_DIS); - /* WaInsertDummyPushConstPs:kbl */ - if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) + /* WaToEnableHwFixForPushConstHWBug:kbl */ + if (IS_KBL_REVID(dev_priv, KBL_REVID_C0, REVID_FOREVER)) WA_SET_BIT_MASKED(COMMON_SLICE_CHICKEN2, GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION); diff --git a/drivers/gpu/drm/mediatek/Kconfig b/drivers/gpu/drm/mediatek/Kconfig index 23ac8041c562..294de4549922 100644 --- a/drivers/gpu/drm/mediatek/Kconfig +++ b/drivers/gpu/drm/mediatek/Kconfig @@ -2,6 +2,9 @@ config DRM_MEDIATEK tristate "DRM Support for Mediatek SoCs" depends on DRM depends on ARCH_MEDIATEK || (ARM && COMPILE_TEST) + depends on COMMON_CLK + depends on HAVE_ARM_SMCCC + depends on OF select DRM_GEM_CMA_HELPER select DRM_KMS_HELPER select DRM_MIPI_DSI diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 528bdeffb339..6190035edfea 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1151,7 +1151,7 @@ nouveau_bo_move_flipd(struct ttm_buffer_object *bo, bool evict, bool intr, if (ret) goto out; - ret = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem); + ret = ttm_bo_move_ttm(bo, true, intr, no_wait_gpu, new_mem); out: ttm_bo_mem_put(bo, &tmp_mem); return ret; @@ -1179,7 +1179,7 @@ nouveau_bo_move_flips(struct ttm_buffer_object *bo, bool evict, bool intr, if (ret) return ret; - ret = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem); + ret = ttm_bo_move_ttm(bo, true, intr, no_wait_gpu, &tmp_mem); if (ret) goto out; diff --git a/drivers/gpu/drm/qxl/qxl_fb.c b/drivers/gpu/drm/qxl/qxl_fb.c index df2657051afd..28c1423049c5 100644 --- a/drivers/gpu/drm/qxl/qxl_fb.c +++ b/drivers/gpu/drm/qxl/qxl_fb.c @@ -73,10 +73,12 @@ static void qxl_fb_image_init(struct qxl_fb_image *qxl_fb_image, } } +#ifdef CONFIG_DRM_FBDEV_EMULATION static struct fb_deferred_io qxl_defio = { .delay = QXL_DIRTY_DELAY, .deferred_io = drm_fb_helper_deferred_io, }; +#endif static struct fb_ops qxlfb_ops = { .owner = THIS_MODULE, @@ -313,8 +315,10 @@ static int qxlfb_create(struct qxl_fbdev *qfbdev, goto out_destroy_fbi; } +#ifdef CONFIG_DRM_FBDEV_EMULATION info->fbdefio = &qxl_defio; fb_deferred_io_init(info); +#endif qdev->fbdev_info = info; qdev->fbdev_qfb = &qfbdev->qfb; diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c index a97abc8af657..1dcf39084555 100644 --- a/drivers/gpu/drm/radeon/atombios_crtc.c +++ b/drivers/gpu/drm/radeon/atombios_crtc.c @@ -627,7 +627,9 @@ static u32 atombios_adjust_pll(struct drm_crtc *crtc, if (radeon_crtc->ss.refdiv) { radeon_crtc->pll_flags |= RADEON_PLL_USE_REF_DIV; radeon_crtc->pll_reference_div = radeon_crtc->ss.refdiv; - if (rdev->family >= CHIP_RV770) + if (ASIC_IS_AVIVO(rdev) && + rdev->family != CHIP_RS780 && + rdev->family != CHIP_RS880) radeon_crtc->pll_flags |= RADEON_PLL_USE_FRAC_FB_DIV; } } diff --git a/drivers/gpu/drm/radeon/radeon_atpx_handler.c b/drivers/gpu/drm/radeon/radeon_atpx_handler.c index 6de342861202..ddef0d494084 100644 --- a/drivers/gpu/drm/radeon/radeon_atpx_handler.c +++ b/drivers/gpu/drm/radeon/radeon_atpx_handler.c @@ -198,16 +198,7 @@ static int radeon_atpx_validate(struct radeon_atpx *atpx) atpx->is_hybrid = false; if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) { printk("ATPX Hybrid Graphics\n"); -#if 1 - /* This is a temporary hack until the D3 cold support - * makes it upstream. The ATPX power_control method seems - * to still work on even if the system should be using - * the new standardized hybrid D3 cold ACPI interface. - */ - atpx->functions.power_cntl = true; -#else atpx->functions.power_cntl = false; -#endif atpx->is_hybrid = true; } diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index ffdad81ef964..c2e0a1ccdfbc 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -263,8 +263,8 @@ static int radeon_move_blit(struct ttm_buffer_object *bo, rdev = radeon_get_rdev(bo->bdev); ridx = radeon_copy_ring_index(rdev); - old_start = old_mem->start << PAGE_SHIFT; - new_start = new_mem->start << PAGE_SHIFT; + old_start = (u64)old_mem->start << PAGE_SHIFT; + new_start = (u64)new_mem->start << PAGE_SHIFT; switch (old_mem->mem_type) { case TTM_PL_VRAM: @@ -346,7 +346,7 @@ static int radeon_move_vram_ram(struct ttm_buffer_object *bo, if (unlikely(r)) { goto out_cleanup; } - r = ttm_bo_move_ttm(bo, true, no_wait_gpu, new_mem); + r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, new_mem); out_cleanup: ttm_bo_mem_put(bo, &tmp_mem); return r; @@ -379,7 +379,7 @@ static int radeon_move_ram_vram(struct ttm_buffer_object *bo, if (unlikely(r)) { return r; } - r = ttm_bo_move_ttm(bo, true, no_wait_gpu, &tmp_mem); + r = ttm_bo_move_ttm(bo, true, interruptible, no_wait_gpu, &tmp_mem); if (unlikely(r)) { goto out_cleanup; } diff --git a/drivers/gpu/drm/rcar-du/rcar_du_hdmienc.c b/drivers/gpu/drm/rcar-du/rcar_du_hdmienc.c index 4de3ff0dbebd..e03004f4588d 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_hdmienc.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_hdmienc.c @@ -125,6 +125,7 @@ int rcar_du_hdmienc_init(struct rcar_du_device *rcdu, /* Link drm_bridge to encoder */ bridge->encoder = encoder; + encoder->bridge = bridge; ret = drm_bridge_attach(rcdu->ddev, bridge); if (ret) { diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index 3d228ad90e0f..3dea1216bafd 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -840,6 +840,21 @@ static const struct drm_encoder_funcs tegra_dsi_encoder_funcs = { .destroy = tegra_output_encoder_destroy, }; +static void tegra_dsi_unprepare(struct tegra_dsi *dsi) +{ + int err; + + if (dsi->slave) + tegra_dsi_unprepare(dsi->slave); + + err = tegra_mipi_disable(dsi->mipi); + if (err < 0) + dev_err(dsi->dev, "failed to disable MIPI calibration: %d\n", + err); + + pm_runtime_put(dsi->dev); +} + static void tegra_dsi_encoder_disable(struct drm_encoder *encoder) { struct tegra_output *output = encoder_to_output(encoder); @@ -876,7 +891,26 @@ static void tegra_dsi_encoder_disable(struct drm_encoder *encoder) tegra_dsi_disable(dsi); - pm_runtime_put(dsi->dev); + tegra_dsi_unprepare(dsi); +} + +static void tegra_dsi_prepare(struct tegra_dsi *dsi) +{ + int err; + + pm_runtime_get_sync(dsi->dev); + + err = tegra_mipi_enable(dsi->mipi); + if (err < 0) + dev_err(dsi->dev, "failed to enable MIPI calibration: %d\n", + err); + + err = tegra_dsi_pad_calibrate(dsi); + if (err < 0) + dev_err(dsi->dev, "MIPI calibration failed: %d\n", err); + + if (dsi->slave) + tegra_dsi_prepare(dsi->slave); } static void tegra_dsi_encoder_enable(struct drm_encoder *encoder) @@ -887,13 +921,8 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder) struct tegra_dsi *dsi = to_dsi(output); struct tegra_dsi_state *state; u32 value; - int err; - - pm_runtime_get_sync(dsi->dev); - err = tegra_dsi_pad_calibrate(dsi); - if (err < 0) - dev_err(dsi->dev, "MIPI calibration failed: %d\n", err); + tegra_dsi_prepare(dsi); state = tegra_dsi_get_state(dsi); diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 4054d804fe06..42c074a9c955 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -354,7 +354,8 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, if (!(old_man->flags & TTM_MEMTYPE_FLAG_FIXED) && !(new_man->flags & TTM_MEMTYPE_FLAG_FIXED)) - ret = ttm_bo_move_ttm(bo, evict, no_wait_gpu, mem); + ret = ttm_bo_move_ttm(bo, evict, interruptible, no_wait_gpu, + mem); else if (bdev->driver->move) ret = bdev->driver->move(bo, evict, interruptible, no_wait_gpu, mem); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 2df602a35f92..f157a9efd220 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -45,7 +45,7 @@ void ttm_bo_free_old_node(struct ttm_buffer_object *bo) } int ttm_bo_move_ttm(struct ttm_buffer_object *bo, - bool evict, + bool evict, bool interruptible, bool no_wait_gpu, struct ttm_mem_reg *new_mem) { struct ttm_tt *ttm = bo->ttm; @@ -53,6 +53,14 @@ int ttm_bo_move_ttm(struct ttm_buffer_object *bo, int ret; if (old_mem->mem_type != TTM_PL_SYSTEM) { + ret = ttm_bo_wait(bo, interruptible, no_wait_gpu); + + if (unlikely(ret != 0)) { + if (ret != -ERESTARTSYS) + pr_err("Failed to expire sync object before unbinding TTM\n"); + return ret; + } + ttm_tt_unbind(ttm); ttm_bo_free_old_node(bo); ttm_flag_masked(&old_mem->placement, TTM_PL_FLAG_SYSTEM, diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c index d5df555aeba0..9688bfa92ccd 100644 --- a/drivers/gpu/drm/udl/udl_fb.c +++ b/drivers/gpu/drm/udl/udl_fb.c @@ -203,6 +203,7 @@ static int udl_fb_open(struct fb_info *info, int user) ufbdev->fb_count++; +#ifdef CONFIG_DRM_FBDEV_EMULATION if (fb_defio && (info->fbdefio == NULL)) { /* enable defio at last moment if not disabled by client */ @@ -218,6 +219,7 @@ static int udl_fb_open(struct fb_info *info, int user) info->fbdefio = fbdefio; fb_deferred_io_init(info); } +#endif pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n", info->node, user, info, ufbdev->fb_count); @@ -235,12 +237,14 @@ static int udl_fb_release(struct fb_info *info, int user) ufbdev->fb_count--; +#ifdef CONFIG_DRM_FBDEV_EMULATION if ((ufbdev->fb_count == 0) && (info->fbdefio)) { fb_deferred_io_cleanup(info); kfree(info->fbdefio); info->fbdefio = NULL; info->fbops->fb_mmap = udl_fb_mmap; } +#endif pr_warn("released /dev/fb%d user=%d count=%d\n", info->node, user, ufbdev->fb_count); diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c index 52a6fd224127..e00809d996a2 100644 --- a/drivers/gpu/host1x/mipi.c +++ b/drivers/gpu/host1x/mipi.c @@ -242,20 +242,6 @@ struct tegra_mipi_device *tegra_mipi_request(struct device *device) dev->pads = args.args[0]; dev->device = device; - mutex_lock(&dev->mipi->lock); - - if (dev->mipi->usage_count++ == 0) { - err = tegra_mipi_power_up(dev->mipi); - if (err < 0) { - dev_err(dev->mipi->dev, - "failed to power up MIPI bricks: %d\n", - err); - return ERR_PTR(err); - } - } - - mutex_unlock(&dev->mipi->lock); - return dev; put: @@ -270,29 +256,42 @@ EXPORT_SYMBOL(tegra_mipi_request); void tegra_mipi_free(struct tegra_mipi_device *device) { - int err; + platform_device_put(device->pdev); + kfree(device); +} +EXPORT_SYMBOL(tegra_mipi_free); - mutex_lock(&device->mipi->lock); +int tegra_mipi_enable(struct tegra_mipi_device *dev) +{ + int err = 0; - if (--device->mipi->usage_count == 0) { - err = tegra_mipi_power_down(device->mipi); - if (err < 0) { - /* - * Not much that can be done here, so an error message - * will have to do. - */ - dev_err(device->mipi->dev, - "failed to power down MIPI bricks: %d\n", - err); - } - } + mutex_lock(&dev->mipi->lock); - mutex_unlock(&device->mipi->lock); + if (dev->mipi->usage_count++ == 0) + err = tegra_mipi_power_up(dev->mipi); + + mutex_unlock(&dev->mipi->lock); + + return err; - platform_device_put(device->pdev); - kfree(device); } -EXPORT_SYMBOL(tegra_mipi_free); +EXPORT_SYMBOL(tegra_mipi_enable); + +int tegra_mipi_disable(struct tegra_mipi_device *dev) +{ + int err = 0; + + mutex_lock(&dev->mipi->lock); + + if (--dev->mipi->usage_count == 0) + err = tegra_mipi_power_down(dev->mipi); + + mutex_unlock(&dev->mipi->lock); + + return err; + +} +EXPORT_SYMBOL(tegra_mipi_disable); static int tegra_mipi_wait(struct tegra_mipi *mipi) { diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c index 730d84028260..d0203a115eff 100644 --- a/drivers/hwmon/it87.c +++ b/drivers/hwmon/it87.c @@ -491,7 +491,7 @@ struct it87_sio_data { struct it87_data { const struct attribute_group *groups[7]; enum chips type; - u16 features; + u32 features; u8 peci_mask; u8 old_peci_mask; diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c index f23372669f77..1bb97f658b47 100644 --- a/drivers/i2c/busses/i2c-at91.c +++ b/drivers/i2c/busses/i2c-at91.c @@ -38,6 +38,7 @@ #define AT91_I2C_TIMEOUT msecs_to_jiffies(100) /* transfer timeout */ #define AT91_I2C_DMA_THRESHOLD 8 /* enable DMA if transfer size is bigger than this threshold */ #define AUTOSUSPEND_TIMEOUT 2000 +#define AT91_I2C_MAX_ALT_CMD_DATA_SIZE 256 /* AT91 TWI register definitions */ #define AT91_TWI_CR 0x0000 /* Control Register */ @@ -141,6 +142,7 @@ struct at91_twi_dev { unsigned twi_cwgr_reg; struct at91_twi_pdata *pdata; bool use_dma; + bool use_alt_cmd; bool recv_len_abort; u32 fifo_size; struct at91_twi_dma dma; @@ -269,7 +271,7 @@ static void at91_twi_write_next_byte(struct at91_twi_dev *dev) /* send stop when last byte has been written */ if (--dev->buf_len == 0) - if (!dev->pdata->has_alt_cmd) + if (!dev->use_alt_cmd) at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); dev_dbg(dev->dev, "wrote 0x%x, to go %d\n", *dev->buf, dev->buf_len); @@ -292,7 +294,7 @@ static void at91_twi_write_data_dma_callback(void *data) * we just have to enable TXCOMP one. */ at91_twi_write(dev, AT91_TWI_IER, AT91_TWI_TXCOMP); - if (!dev->pdata->has_alt_cmd) + if (!dev->use_alt_cmd) at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); } @@ -410,7 +412,7 @@ static void at91_twi_read_next_byte(struct at91_twi_dev *dev) } /* send stop if second but last byte has been read */ - if (!dev->pdata->has_alt_cmd && dev->buf_len == 1) + if (!dev->use_alt_cmd && dev->buf_len == 1) at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_STOP); dev_dbg(dev->dev, "read 0x%x, to go %d\n", *dev->buf, dev->buf_len); @@ -426,7 +428,7 @@ static void at91_twi_read_data_dma_callback(void *data) dma_unmap_single(dev->dev, sg_dma_address(&dev->dma.sg[0]), dev->buf_len, DMA_FROM_DEVICE); - if (!dev->pdata->has_alt_cmd) { + if (!dev->use_alt_cmd) { /* The last two bytes have to be read without using dma */ dev->buf += dev->buf_len - 2; dev->buf_len = 2; @@ -443,7 +445,7 @@ static void at91_twi_read_data_dma(struct at91_twi_dev *dev) struct dma_chan *chan_rx = dma->chan_rx; size_t buf_len; - buf_len = (dev->pdata->has_alt_cmd) ? dev->buf_len : dev->buf_len - 2; + buf_len = (dev->use_alt_cmd) ? dev->buf_len : dev->buf_len - 2; dma->direction = DMA_FROM_DEVICE; /* Keep in mind that we won't use dma to read the last two bytes */ @@ -651,7 +653,7 @@ static int at91_do_twi_transfer(struct at91_twi_dev *dev) unsigned start_flags = AT91_TWI_START; /* if only one byte is to be read, immediately stop transfer */ - if (!has_alt_cmd && dev->buf_len <= 1 && + if (!dev->use_alt_cmd && dev->buf_len <= 1 && !(dev->msg->flags & I2C_M_RECV_LEN)) start_flags |= AT91_TWI_STOP; at91_twi_write(dev, AT91_TWI_CR, start_flags); @@ -745,7 +747,7 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num) int ret; unsigned int_addr_flag = 0; struct i2c_msg *m_start = msg; - bool is_read, use_alt_cmd = false; + bool is_read; dev_dbg(&adap->dev, "at91_xfer: processing %d messages:\n", num); @@ -768,14 +770,16 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num) at91_twi_write(dev, AT91_TWI_IADR, internal_address); } + dev->use_alt_cmd = false; is_read = (m_start->flags & I2C_M_RD); if (dev->pdata->has_alt_cmd) { - if (m_start->len > 0) { + if (m_start->len > 0 && + m_start->len < AT91_I2C_MAX_ALT_CMD_DATA_SIZE) { at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_ACMEN); at91_twi_write(dev, AT91_TWI_ACR, AT91_TWI_ACR_DATAL(m_start->len) | ((is_read) ? AT91_TWI_ACR_DIR : 0)); - use_alt_cmd = true; + dev->use_alt_cmd = true; } else { at91_twi_write(dev, AT91_TWI_CR, AT91_TWI_ACMDIS); } @@ -784,7 +788,7 @@ static int at91_twi_xfer(struct i2c_adapter *adap, struct i2c_msg *msg, int num) at91_twi_write(dev, AT91_TWI_MMR, (m_start->addr << 16) | int_addr_flag | - ((!use_alt_cmd && is_read) ? AT91_TWI_MREAD : 0)); + ((!dev->use_alt_cmd && is_read) ? AT91_TWI_MREAD : 0)); dev->buf_len = m_start->len; dev->buf = m_start->buf; diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c index 19c843828fe2..95f7cac76f89 100644 --- a/drivers/i2c/busses/i2c-bcm-iproc.c +++ b/drivers/i2c/busses/i2c-bcm-iproc.c @@ -158,7 +158,7 @@ static irqreturn_t bcm_iproc_i2c_isr(int irq, void *data) if (status & BIT(IS_M_START_BUSY_SHIFT)) { iproc_i2c->xfer_is_done = 1; - complete_all(&iproc_i2c->done); + complete(&iproc_i2c->done); } writel(status, iproc_i2c->base + IS_OFFSET); diff --git a/drivers/i2c/busses/i2c-bcm-kona.c b/drivers/i2c/busses/i2c-bcm-kona.c index ac9f47679c3a..f98743277e3c 100644 --- a/drivers/i2c/busses/i2c-bcm-kona.c +++ b/drivers/i2c/busses/i2c-bcm-kona.c @@ -229,7 +229,7 @@ static irqreturn_t bcm_kona_i2c_isr(int irq, void *devid) dev->base + TXFCR_OFFSET); writel(status & ~ISR_RESERVED_MASK, dev->base + ISR_OFFSET); - complete_all(&dev->done); + complete(&dev->done); return IRQ_HANDLED; } diff --git a/drivers/i2c/busses/i2c-brcmstb.c b/drivers/i2c/busses/i2c-brcmstb.c index 3f5a4d71d3bf..385b57bfcb38 100644 --- a/drivers/i2c/busses/i2c-brcmstb.c +++ b/drivers/i2c/busses/i2c-brcmstb.c @@ -228,7 +228,7 @@ static irqreturn_t brcmstb_i2c_isr(int irq, void *devid) return IRQ_NONE; brcmstb_i2c_enable_disable_irq(dev, INT_DISABLE); - complete_all(&dev->done); + complete(&dev->done); dev_dbg(dev->device, "isr handled"); return IRQ_HANDLED; diff --git a/drivers/i2c/busses/i2c-cros-ec-tunnel.c b/drivers/i2c/busses/i2c-cros-ec-tunnel.c index a0d95ff682ae..2d5ff86398d0 100644 --- a/drivers/i2c/busses/i2c-cros-ec-tunnel.c +++ b/drivers/i2c/busses/i2c-cros-ec-tunnel.c @@ -215,7 +215,7 @@ static int ec_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg i2c_msgs[], msg->outsize = request_len; msg->insize = response_len; - result = cros_ec_cmd_xfer(bus->ec, msg); + result = cros_ec_cmd_xfer_status(bus->ec, msg); if (result < 0) { dev_err(dev, "Error transferring EC i2c message %d\n", result); goto exit; diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c index 71d3929adf54..76e28980904f 100644 --- a/drivers/i2c/busses/i2c-meson.c +++ b/drivers/i2c/busses/i2c-meson.c @@ -211,7 +211,7 @@ static void meson_i2c_stop(struct meson_i2c *i2c) meson_i2c_add_token(i2c, TOKEN_STOP); } else { i2c->state = STATE_IDLE; - complete_all(&i2c->done); + complete(&i2c->done); } } @@ -238,7 +238,7 @@ static irqreturn_t meson_i2c_irq(int irqno, void *dev_id) dev_dbg(i2c->dev, "error bit set\n"); i2c->error = -ENXIO; i2c->state = STATE_IDLE; - complete_all(&i2c->done); + complete(&i2c->done); goto out; } @@ -269,7 +269,7 @@ static irqreturn_t meson_i2c_irq(int irqno, void *dev_id) break; case STATE_STOP: i2c->state = STATE_IDLE; - complete_all(&i2c->done); + complete(&i2c->done); break; case STATE_IDLE: break; diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index dfa7a4b4a91d..ac88a524143e 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -379,6 +379,7 @@ static int ocores_i2c_of_probe(struct platform_device *pdev, if (!clock_frequency_present) { dev_err(&pdev->dev, "Missing required parameter 'opencores,ip-clock-frequency'\n"); + clk_disable_unprepare(i2c->clk); return -ENODEV; } i2c->ip_clock_khz = clock_frequency / 1000; @@ -467,20 +468,21 @@ static int ocores_i2c_probe(struct platform_device *pdev) default: dev_err(&pdev->dev, "Unsupported I/O width (%d)\n", i2c->reg_io_width); - return -EINVAL; + ret = -EINVAL; + goto err_clk; } } ret = ocores_init(&pdev->dev, i2c); if (ret) - return ret; + goto err_clk; init_waitqueue_head(&i2c->wait); ret = devm_request_irq(&pdev->dev, irq, ocores_isr, 0, pdev->name, i2c); if (ret) { dev_err(&pdev->dev, "Cannot claim IRQ\n"); - return ret; + goto err_clk; } /* hook up driver to tree */ @@ -494,7 +496,7 @@ static int ocores_i2c_probe(struct platform_device *pdev) ret = i2c_add_adapter(&i2c->adap); if (ret) { dev_err(&pdev->dev, "Failed to add adapter\n"); - return ret; + goto err_clk; } /* add in known devices to the bus */ @@ -504,6 +506,10 @@ static int ocores_i2c_probe(struct platform_device *pdev) } return 0; + +err_clk: + clk_disable_unprepare(i2c->clk); + return ret; } static int ocores_i2c_remove(struct platform_device *pdev) diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c index 8de073aed001..215ac87f606d 100644 --- a/drivers/i2c/muxes/i2c-demux-pinctrl.c +++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c @@ -68,7 +68,7 @@ static int i2c_demux_activate_master(struct i2c_demux_pinctrl_priv *priv, u32 ne adap = of_find_i2c_adapter_by_node(priv->chan[new_chan].parent_np); if (!adap) { ret = -ENODEV; - goto err; + goto err_with_revert; } p = devm_pinctrl_get_select(adap->dev.parent, priv->bus_name); @@ -103,6 +103,8 @@ static int i2c_demux_activate_master(struct i2c_demux_pinctrl_priv *priv, u32 ne err_with_put: i2c_put_adapter(adap); + err_with_revert: + of_changeset_revert(&priv->chan[new_chan].chgset); err: dev_err(priv->dev, "failed to setup demux-adapter %d (%d)\n", new_chan, ret); return ret; diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index e6dfa1bd3def..5f65a78b27c9 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2462,18 +2462,24 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) if (addr->dev_addr.bound_dev_if) { ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if); - if (!ndev) - return -ENODEV; + if (!ndev) { + ret = -ENODEV; + goto err2; + } if (ndev->flags & IFF_LOOPBACK) { dev_put(ndev); - if (!id_priv->id.device->get_netdev) - return -EOPNOTSUPP; + if (!id_priv->id.device->get_netdev) { + ret = -EOPNOTSUPP; + goto err2; + } ndev = id_priv->id.device->get_netdev(id_priv->id.device, id_priv->id.port_num); - if (!ndev) - return -ENODEV; + if (!ndev) { + ret = -ENODEV; + goto err2; + } } route->path_rec->net = &init_net; diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 3aca7f6171b4..b6a953aed7e8 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1827,8 +1827,12 @@ static int process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb) (ep->mpa_pkt + sizeof(*mpa)); ep->ird = ntohs(mpa_v2_params->ird) & MPA_V2_IRD_ORD_MASK; + ep->ird = min_t(u32, ep->ird, + cur_max_read_depth(ep->com.dev)); ep->ord = ntohs(mpa_v2_params->ord) & MPA_V2_IRD_ORD_MASK; + ep->ord = min_t(u32, ep->ord, + cur_max_read_depth(ep->com.dev)); PDBG("%s initiator ird %u ord %u\n", __func__, ep->ird, ep->ord); if (ntohs(mpa_v2_params->ird) & MPA_V2_PEER2PEER_MODEL) @@ -3136,7 +3140,7 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) { if (conn_param->ord > ep->ird) { if (RELAXED_IRD_NEGOTIATION) { - ep->ord = ep->ird; + conn_param->ord = ep->ird; } else { ep->ird = conn_param->ird; ep->ord = conn_param->ord; diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c index 812ab7278b8e..ac926c942fee 100644 --- a/drivers/infiniband/hw/cxgb4/cq.c +++ b/drivers/infiniband/hw/cxgb4/cq.c @@ -1016,15 +1016,15 @@ int c4iw_resize_cq(struct ib_cq *cq, int cqe, struct ib_udata *udata) int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) { struct c4iw_cq *chp; - int ret; + int ret = 0; unsigned long flag; chp = to_c4iw_cq(ibcq); spin_lock_irqsave(&chp->lock, flag); - ret = t4_arm_cq(&chp->cq, - (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED); + t4_arm_cq(&chp->cq, + (flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED); + if (flags & IB_CQ_REPORT_MISSED_EVENTS) + ret = t4_cq_notempty(&chp->cq); spin_unlock_irqrestore(&chp->lock, flag); - if (ret && !(flags & IB_CQ_REPORT_MISSED_EVENTS)) - ret = 0; return ret; } diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h index 6126bbe36095..02173f4315fa 100644 --- a/drivers/infiniband/hw/cxgb4/t4.h +++ b/drivers/infiniband/hw/cxgb4/t4.h @@ -634,6 +634,11 @@ static inline int t4_valid_cqe(struct t4_cq *cq, struct t4_cqe *cqe) return (CQE_GENBIT(cqe) == cq->gen); } +static inline int t4_cq_notempty(struct t4_cq *cq) +{ + return cq->sw_in_use || t4_valid_cqe(cq, &cq->queue[cq->cidx]); +} + static inline int t4_next_hw_cqe(struct t4_cq *cq, struct t4_cqe **cqe) { int ret; diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 79575ee873f2..0566393e5aba 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -47,7 +47,6 @@ #include <linux/topology.h> #include <linux/cpumask.h> #include <linux/module.h> -#include <linux/cpumask.h> #include "hfi.h" #include "affinity.h" @@ -682,7 +681,7 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, size_t count) { struct hfi1_affinity_node *entry; - struct cpumask mask; + cpumask_var_t mask; int ret, i; spin_lock(&node_affinity.lock); @@ -692,19 +691,24 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, if (!entry) return -EINVAL; - ret = cpulist_parse(buf, &mask); + ret = zalloc_cpumask_var(&mask, GFP_KERNEL); + if (!ret) + return -ENOMEM; + + ret = cpulist_parse(buf, mask); if (ret) - return ret; + goto out; - if (!cpumask_subset(&mask, cpu_online_mask) || cpumask_empty(&mask)) { + if (!cpumask_subset(mask, cpu_online_mask) || cpumask_empty(mask)) { dd_dev_warn(dd, "Invalid CPU mask\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } mutex_lock(&sdma_affinity_mutex); /* reset the SDMA interrupt affinity details */ init_cpu_mask_set(&entry->def_intr); - cpumask_copy(&entry->def_intr.mask, &mask); + cpumask_copy(&entry->def_intr.mask, mask); /* * Reassign the affinity for each SDMA interrupt. */ @@ -720,8 +724,9 @@ int hfi1_set_sdma_affinity(struct hfi1_devdata *dd, const char *buf, if (ret) break; } - mutex_unlock(&sdma_affinity_mutex); +out: + free_cpumask_var(mask); return ret ? ret : strnlen(buf, PAGE_SIZE); } diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c index dbab9d9cc288..a49cc88f08a2 100644 --- a/drivers/infiniband/hw/hfi1/debugfs.c +++ b/drivers/infiniband/hw/hfi1/debugfs.c @@ -223,28 +223,32 @@ DEBUGFS_SEQ_FILE_OPEN(ctx_stats) DEBUGFS_FILE_OPS(ctx_stats); static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) -__acquires(RCU) + __acquires(RCU) { struct qp_iter *iter; loff_t n = *pos; - rcu_read_lock(); iter = qp_iter_init(s->private); + + /* stop calls rcu_read_unlock */ + rcu_read_lock(); + if (!iter) return NULL; - while (n--) { + do { if (qp_iter_next(iter)) { kfree(iter); return NULL; } - } + } while (n--); return iter; } static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, loff_t *pos) + __must_hold(RCU) { struct qp_iter *iter = iter_ptr; @@ -259,7 +263,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, } static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) -__releases(RCU) + __releases(RCU) { rcu_read_unlock(); } diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c index 8246dc7d0573..303f10555729 100644 --- a/drivers/infiniband/hw/hfi1/driver.c +++ b/drivers/infiniband/hw/hfi1/driver.c @@ -888,14 +888,15 @@ void set_all_slowpath(struct hfi1_devdata *dd) } static inline int set_armed_to_active(struct hfi1_ctxtdata *rcd, - struct hfi1_packet packet, + struct hfi1_packet *packet, struct hfi1_devdata *dd) { struct work_struct *lsaw = &rcd->ppd->linkstate_active_work; - struct hfi1_message_header *hdr = hfi1_get_msgheader(packet.rcd->dd, - packet.rhf_addr); + struct hfi1_message_header *hdr = hfi1_get_msgheader(packet->rcd->dd, + packet->rhf_addr); + u8 etype = rhf_rcv_type(packet->rhf); - if (hdr2sc(hdr, packet.rhf) != 0xf) { + if (etype == RHF_RCV_TYPE_IB && hdr2sc(hdr, packet->rhf) != 0xf) { int hwstate = read_logical_state(dd); if (hwstate != LSTATE_ACTIVE) { @@ -979,7 +980,7 @@ int handle_receive_interrupt(struct hfi1_ctxtdata *rcd, int thread) /* Auto activate link on non-SC15 packet receive */ if (unlikely(rcd->ppd->host_link_state == HLS_UP_ARMED) && - set_armed_to_active(rcd, packet, dd)) + set_armed_to_active(rcd, &packet, dd)) goto bail; last = process_rcv_packet(&packet, thread); } diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index 1ecbec192358..7e03ccd2554d 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -183,6 +183,7 @@ static int hfi1_file_open(struct inode *inode, struct file *fp) if (fd) { fd->rec_cpu_num = -1; /* no cpu affinity by default */ fd->mm = current->mm; + atomic_inc(&fd->mm->mm_count); } fp->private_data = fd; @@ -222,7 +223,7 @@ static long hfi1_file_ioctl(struct file *fp, unsigned int cmd, ret = assign_ctxt(fp, &uinfo); if (ret < 0) return ret; - setup_ctxt(fp); + ret = setup_ctxt(fp); if (ret) return ret; ret = user_init(fp); @@ -779,6 +780,7 @@ static int hfi1_file_close(struct inode *inode, struct file *fp) mutex_unlock(&hfi1_mutex); hfi1_free_ctxtdata(dd, uctxt); done: + mmdrop(fdata->mm); kobject_put(&dd->kobj); kfree(fdata); return 0; diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 1000e0fd96d9..a021e660d482 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1272,9 +1272,26 @@ static inline int hdr2sc(struct hfi1_message_header *hdr, u64 rhf) ((!!(rhf_dc_info(rhf))) << 4); } +#define HFI1_JKEY_WIDTH 16 +#define HFI1_JKEY_MASK (BIT(16) - 1) +#define HFI1_ADMIN_JKEY_RANGE 32 + +/* + * J_KEYs are split and allocated in the following groups: + * 0 - 31 - users with administrator privileges + * 32 - 63 - kernel protocols using KDETH packets + * 64 - 65535 - all other users using KDETH packets + */ static inline u16 generate_jkey(kuid_t uid) { - return from_kuid(current_user_ns(), uid) & 0xffff; + u16 jkey = from_kuid(current_user_ns(), uid) & HFI1_JKEY_MASK; + + if (capable(CAP_SYS_ADMIN)) + jkey &= HFI1_ADMIN_JKEY_RANGE - 1; + else if (jkey < 64) + jkey |= BIT(HFI1_JKEY_WIDTH - 1); + + return jkey; } /* @@ -1656,7 +1673,6 @@ struct cc_state *get_cc_state_protected(struct hfi1_pportdata *ppd) struct hfi1_devdata *hfi1_init_dd(struct pci_dev *, const struct pci_device_id *); void hfi1_free_devdata(struct hfi1_devdata *); -void cc_state_reclaim(struct rcu_head *rcu); struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra); /* LED beaconing functions */ diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index a358d23ecd54..b7935451093c 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1333,7 +1333,7 @@ static void cleanup_device_data(struct hfi1_devdata *dd) spin_unlock(&ppd->cc_state_lock); if (cc_state) - call_rcu(&cc_state->rcu, cc_state_reclaim); + kfree_rcu(cc_state, rcu); } free_credit_return(dd); diff --git a/drivers/infiniband/hw/hfi1/mad.c b/drivers/infiniband/hw/hfi1/mad.c index 1263abe01999..39e42c373a01 100644 --- a/drivers/infiniband/hw/hfi1/mad.c +++ b/drivers/infiniband/hw/hfi1/mad.c @@ -1819,6 +1819,11 @@ static int __subn_get_opa_cable_info(struct opa_smp *smp, u32 am, u8 *data, u32 len = OPA_AM_CI_LEN(am) + 1; int ret; + if (dd->pport->port_type != PORT_TYPE_QSFP) { + smp->status |= IB_SMP_INVALID_FIELD; + return reply((struct ib_mad_hdr *)smp); + } + #define __CI_PAGE_SIZE BIT(7) /* 128 bytes */ #define __CI_PAGE_MASK ~(__CI_PAGE_SIZE - 1) #define __CI_PAGE_NUM(a) ((a) & __CI_PAGE_MASK) @@ -3398,7 +3403,7 @@ static void apply_cc_state(struct hfi1_pportdata *ppd) spin_unlock(&ppd->cc_state_lock); - call_rcu(&old_cc_state->rcu, cc_state_reclaim); + kfree_rcu(old_cc_state, rcu); } static int __subn_set_opa_cong_setting(struct opa_smp *smp, u32 am, u8 *data, @@ -3553,13 +3558,6 @@ static int __subn_get_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, return reply((struct ib_mad_hdr *)smp); } -void cc_state_reclaim(struct rcu_head *rcu) -{ - struct cc_state *cc_state = container_of(rcu, struct cc_state, rcu); - - kfree(cc_state); -} - static int __subn_set_opa_cc_table(struct opa_smp *smp, u32 am, u8 *data, struct ib_device *ibdev, u8 port, u32 *resp_len) diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index a5aa3517e7d5..4e4d8317c281 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -656,10 +656,6 @@ struct qp_iter *qp_iter_init(struct hfi1_ibdev *dev) iter->dev = dev; iter->specials = dev->rdi.ibdev.phys_port_cnt * 2; - if (qp_iter_next(iter)) { - kfree(iter); - return NULL; - } return iter; } diff --git a/drivers/infiniband/hw/hfi1/qsfp.c b/drivers/infiniband/hw/hfi1/qsfp.c index a207717ade2a..4e95ad810847 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.c +++ b/drivers/infiniband/hw/hfi1/qsfp.c @@ -706,8 +706,8 @@ int get_cable_info(struct hfi1_devdata *dd, u32 port_num, u32 addr, u32 len, u8 *data) { struct hfi1_pportdata *ppd; - u32 excess_len = 0; - int ret = 0; + u32 excess_len = len; + int ret = 0, offset = 0; if (port_num > dd->num_pports || port_num < 1) { dd_dev_info(dd, "%s: Invalid port number %d\n", @@ -740,6 +740,34 @@ int get_cable_info(struct hfi1_devdata *dd, u32 port_num, u32 addr, u32 len, } memcpy(data, &ppd->qsfp_info.cache[addr], len); + + if (addr <= QSFP_MONITOR_VAL_END && + (addr + len) >= QSFP_MONITOR_VAL_START) { + /* Overlap with the dynamic channel monitor range */ + if (addr < QSFP_MONITOR_VAL_START) { + if (addr + len <= QSFP_MONITOR_VAL_END) + len = addr + len - QSFP_MONITOR_VAL_START; + else + len = QSFP_MONITOR_RANGE; + offset = QSFP_MONITOR_VAL_START - addr; + addr = QSFP_MONITOR_VAL_START; + } else if (addr == QSFP_MONITOR_VAL_START) { + offset = 0; + if (addr + len > QSFP_MONITOR_VAL_END) + len = QSFP_MONITOR_RANGE; + } else { + offset = 0; + if (addr + len > QSFP_MONITOR_VAL_END) + len = QSFP_MONITOR_VAL_END - addr + 1; + } + /* Refresh the values of the dynamic monitors from the cable */ + ret = one_qsfp_read(ppd, dd->hfi1_id, addr, data + offset, len); + if (ret != len) { + ret = -EAGAIN; + goto set_zeroes; + } + } + return 0; set_zeroes: diff --git a/drivers/infiniband/hw/hfi1/qsfp.h b/drivers/infiniband/hw/hfi1/qsfp.h index 69275ebd9597..36cf52359848 100644 --- a/drivers/infiniband/hw/hfi1/qsfp.h +++ b/drivers/infiniband/hw/hfi1/qsfp.h @@ -74,6 +74,9 @@ /* Defined fields that Intel requires of qualified cables */ /* Byte 0 is Identifier, not checked */ /* Byte 1 is reserved "status MSB" */ +#define QSFP_MONITOR_VAL_START 22 +#define QSFP_MONITOR_VAL_END 81 +#define QSFP_MONITOR_RANGE (QSFP_MONITOR_VAL_END - QSFP_MONITOR_VAL_START + 1) #define QSFP_TX_CTRL_BYTE_OFFS 86 #define QSFP_PWR_CTRL_BYTE_OFFS 93 #define QSFP_CDR_CTRL_BYTE_OFFS 98 diff --git a/drivers/infiniband/hw/i40iw/i40iw.h b/drivers/infiniband/hw/i40iw/i40iw.h index b738acdb9b02..8ec09e470f84 100644 --- a/drivers/infiniband/hw/i40iw/i40iw.h +++ b/drivers/infiniband/hw/i40iw/i40iw.h @@ -232,7 +232,7 @@ struct i40iw_device { struct i40e_client *client; struct i40iw_hw hw; struct i40iw_cm_core cm_core; - unsigned long *mem_resources; + u8 *mem_resources; unsigned long *allocated_qps; unsigned long *allocated_cqs; unsigned long *allocated_mrs; @@ -435,8 +435,8 @@ static inline int i40iw_alloc_resource(struct i40iw_device *iwdev, *next = resource_num + 1; if (*next == max_resources) *next = 0; - spin_unlock_irqrestore(&iwdev->resource_lock, flags); *req_resource_num = resource_num; + spin_unlock_irqrestore(&iwdev->resource_lock, flags); return 0; } diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index 5026dc79978a..7ca0638579c0 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -535,8 +535,8 @@ static struct i40iw_puda_buf *i40iw_form_cm_frame(struct i40iw_cm_node *cm_node, buf += hdr_len; } - if (pd_len) - memcpy(buf, pdata->addr, pd_len); + if (pdata && pdata->addr) + memcpy(buf, pdata->addr, pdata->size); atomic_set(&sqbuf->refcount, 1); @@ -3347,26 +3347,6 @@ int i40iw_cm_disconn(struct i40iw_qp *iwqp) } /** - * i40iw_loopback_nop - Send a nop - * @qp: associated hw qp - */ -static void i40iw_loopback_nop(struct i40iw_sc_qp *qp) -{ - u64 *wqe; - u64 header; - - wqe = qp->qp_uk.sq_base->elem; - set_64bit_val(wqe, 0, 0); - set_64bit_val(wqe, 8, 0); - set_64bit_val(wqe, 16, 0); - - header = LS_64(I40IWQP_OP_NOP, I40IWQPSQ_OPCODE) | - LS_64(0, I40IWQPSQ_SIGCOMPL) | - LS_64(qp->qp_uk.swqe_polarity, I40IWQPSQ_VALID); - set_64bit_val(wqe, 24, header); -} - -/** * i40iw_qp_disconnect - free qp and close cm * @iwqp: associate qp for the connection */ @@ -3638,7 +3618,7 @@ int i40iw_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) } else { if (iwqp->page) iwqp->sc_qp.qp_uk.sq_base = kmap(iwqp->page); - i40iw_loopback_nop(&iwqp->sc_qp); + dev->iw_priv_qp_ops->qp_send_lsmm(&iwqp->sc_qp, NULL, 0, 0); } if (iwqp->page) diff --git a/drivers/infiniband/hw/i40iw/i40iw_main.c b/drivers/infiniband/hw/i40iw/i40iw_main.c index 6e9081380a27..0cbbe4038298 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_main.c +++ b/drivers/infiniband/hw/i40iw/i40iw_main.c @@ -1558,6 +1558,10 @@ static int i40iw_open(struct i40e_info *ldev, struct i40e_client *client) enum i40iw_status_code status; struct i40iw_handler *hdl; + hdl = i40iw_find_netdev(ldev->netdev); + if (hdl) + return 0; + hdl = kzalloc(sizeof(*hdl), GFP_KERNEL); if (!hdl) return -ENOMEM; diff --git a/drivers/infiniband/hw/i40iw/i40iw_utils.c b/drivers/infiniband/hw/i40iw/i40iw_utils.c index 0e8db0a35141..6fd043b1d714 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_utils.c +++ b/drivers/infiniband/hw/i40iw/i40iw_utils.c @@ -673,8 +673,11 @@ enum i40iw_status_code i40iw_free_virt_mem(struct i40iw_hw *hw, { if (!mem) return I40IW_ERR_PARAM; + /* + * mem->va points to the parent of mem, so both mem and mem->va + * can not be touched once mem->va is freed + */ kfree(mem->va); - mem->va = NULL; return 0; } diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c index 2360338877bf..6329c971c22f 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c +++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c @@ -794,7 +794,6 @@ static struct ib_qp *i40iw_create_qp(struct ib_pd *ibpd, return &iwqp->ibqp; error: i40iw_free_qp_resources(iwdev, iwqp, qp_num); - kfree(mem); return ERR_PTR(err_code); } @@ -1926,8 +1925,7 @@ static int i40iw_dereg_mr(struct ib_mr *ib_mr) } if (iwpbl->pbl_allocated) i40iw_free_pble(iwdev->pble_rsrc, palloc); - kfree(iwpbl->iwmr); - iwpbl->iwmr = NULL; + kfree(iwmr); return 0; } diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c index d6fc8a6e8c33..006db6436e3b 100644 --- a/drivers/infiniband/hw/mlx4/cq.c +++ b/drivers/infiniband/hw/mlx4/cq.c @@ -576,8 +576,8 @@ static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum) checksum == cpu_to_be16(0xffff); } -static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc, - unsigned tail, struct mlx4_cqe *cqe, int is_eth) +static void use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc, + unsigned tail, struct mlx4_cqe *cqe, int is_eth) { struct mlx4_ib_proxy_sqp_hdr *hdr; @@ -600,8 +600,6 @@ static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct wc->slid = be16_to_cpu(hdr->tun.slid_mac_47_32); wc->sl = (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12); } - - return 0; } static void mlx4_ib_qp_sw_comp(struct mlx4_ib_qp *qp, int num_entries, @@ -692,7 +690,7 @@ repoll: if (unlikely((cqe->owner_sr_opcode & MLX4_CQE_OPCODE_MASK) == MLX4_OPCODE_NOP && is_send)) { pr_warn("Completion for NOP opcode detected!\n"); - return -EINVAL; + return -EAGAIN; } /* Resize CQ in progress */ @@ -723,7 +721,7 @@ repoll: if (unlikely(!mqp)) { pr_warn("CQ %06x with entry for unknown QPN %06x\n", cq->mcq.cqn, be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_QPN_MASK); - return -EINVAL; + return -EAGAIN; } *cur_qp = to_mibqp(mqp); @@ -741,7 +739,7 @@ repoll: if (unlikely(!msrq)) { pr_warn("CQ %06x with entry for unknown SRQN %06x\n", cq->mcq.cqn, srq_num); - return -EINVAL; + return -EAGAIN; } } @@ -852,9 +850,11 @@ repoll: if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) { if ((*cur_qp)->mlx4_ib_qp_type & (MLX4_IB_QPT_PROXY_SMI_OWNER | - MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) - return use_tunnel_data(*cur_qp, cq, wc, tail, - cqe, is_eth); + MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI)) { + use_tunnel_data(*cur_qp, cq, wc, tail, cqe, + is_eth); + return 0; + } } wc->slid = be16_to_cpu(cqe->rlid); diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index a84bb766fc62..1b4094baa2de 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -37,7 +37,6 @@ #include <linux/pci.h> #include <linux/dma-mapping.h> #include <linux/slab.h> -#include <linux/io-mapping.h> #if defined(CONFIG_X86) #include <asm/pat.h> #endif diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c index 16740dcb876b..67fc0b6857e1 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c @@ -1156,18 +1156,18 @@ static void ocrdma_get_attr(struct ocrdma_dev *dev, attr->max_srq = (rsp->max_srq_rpir_qps & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SRQ_OFFSET; - attr->max_send_sge = ((rsp->max_write_send_sge & + attr->max_send_sge = ((rsp->max_recv_send_sge & OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT); - attr->max_recv_sge = (rsp->max_write_send_sge & - OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK) >> - OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT; + attr->max_recv_sge = (rsp->max_recv_send_sge & + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK) >> + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT; attr->max_srq_sge = (rsp->max_srq_rqe_sge & OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET; - attr->max_rdma_sge = (rsp->max_write_send_sge & - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK) >> - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT; + attr->max_rdma_sge = (rsp->max_wr_rd_sge & + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK) >> + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT; attr->max_ord_per_qp = (rsp->max_ird_ord_per_qp & OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK) >> OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT; diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h index 0efc9662c6d8..37df4481bb8f 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h @@ -554,9 +554,9 @@ enum { OCRDMA_MBX_QUERY_CFG_L3_TYPE_MASK = 0x18, OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_SHIFT = 0, OCRDMA_MBX_QUERY_CFG_MAX_SEND_SGE_MASK = 0xFFFF, - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT = 16, - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_MASK = 0xFFFF << - OCRDMA_MBX_QUERY_CFG_MAX_WRITE_SGE_SHIFT, + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT = 16, + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_MASK = 0xFFFF << + OCRDMA_MBX_QUERY_CFG_MAX_RECV_SGE_SHIFT, OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_SHIFT = 0, OCRDMA_MBX_QUERY_CFG_MAX_ORD_PER_QP_MASK = 0xFFFF, @@ -612,6 +612,8 @@ enum { OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET = 0, OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_MASK = 0xFFFF << OCRDMA_MBX_QUERY_CFG_MAX_SRQ_SGE_OFFSET, + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_SHIFT = 0, + OCRDMA_MBX_QUERY_CFG_MAX_RD_SGE_MASK = 0xFFFF, }; struct ocrdma_mbx_query_config { @@ -619,7 +621,7 @@ struct ocrdma_mbx_query_config { struct ocrdma_mbx_rsp rsp; u32 qp_srq_cq_ird_ord; u32 max_pd_ca_ack_delay; - u32 max_write_send_sge; + u32 max_recv_send_sge; u32 max_ird_ord_per_qp; u32 max_shared_ird_ord; u32 max_mr; @@ -639,6 +641,8 @@ struct ocrdma_mbx_query_config { u32 max_wqes_rqes_per_q; u32 max_cq_cqes_per_cq; u32 max_srq_rqe_sge; + u32 max_wr_rd_sge; + u32 ird_pgsz_num_pages; }; struct ocrdma_fw_ver_rsp { diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index b1a3d91fe8b9..0aa854737e74 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -125,8 +125,8 @@ int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr, IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_LOCAL_DMA_LKEY | IB_DEVICE_MEM_MGT_EXTENSIONS; - attr->max_sge = dev->attr.max_send_sge; - attr->max_sge_rd = attr->max_sge; + attr->max_sge = min(dev->attr.max_send_sge, dev->attr.max_recv_sge); + attr->max_sge_rd = dev->attr.max_rdma_sge; attr->max_cq = dev->attr.max_cq; attr->max_cqe = dev->attr.max_cqe; attr->max_mr = dev->attr.max_mr; diff --git a/drivers/infiniband/hw/qib/qib_debugfs.c b/drivers/infiniband/hw/qib/qib_debugfs.c index 5e75b43c596b..5bad8e3b40bb 100644 --- a/drivers/infiniband/hw/qib/qib_debugfs.c +++ b/drivers/infiniband/hw/qib/qib_debugfs.c @@ -189,27 +189,32 @@ static int _ctx_stats_seq_show(struct seq_file *s, void *v) DEBUGFS_FILE(ctx_stats) static void *_qp_stats_seq_start(struct seq_file *s, loff_t *pos) + __acquires(RCU) { struct qib_qp_iter *iter; loff_t n = *pos; - rcu_read_lock(); iter = qib_qp_iter_init(s->private); + + /* stop calls rcu_read_unlock */ + rcu_read_lock(); + if (!iter) return NULL; - while (n--) { + do { if (qib_qp_iter_next(iter)) { kfree(iter); return NULL; } - } + } while (n--); return iter; } static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, loff_t *pos) + __must_hold(RCU) { struct qib_qp_iter *iter = iter_ptr; @@ -224,6 +229,7 @@ static void *_qp_stats_seq_next(struct seq_file *s, void *iter_ptr, } static void _qp_stats_seq_stop(struct seq_file *s, void *iter_ptr) + __releases(RCU) { rcu_read_unlock(); } diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c index fcdf37913a26..c3edc033f7c4 100644 --- a/drivers/infiniband/hw/qib/qib_fs.c +++ b/drivers/infiniband/hw/qib/qib_fs.c @@ -328,26 +328,12 @@ static ssize_t flash_write(struct file *file, const char __user *buf, pos = *ppos; - if (pos != 0) { - ret = -EINVAL; - goto bail; - } - - if (count != sizeof(struct qib_flash)) { - ret = -EINVAL; - goto bail; - } - - tmp = kmalloc(count, GFP_KERNEL); - if (!tmp) { - ret = -ENOMEM; - goto bail; - } + if (pos != 0 || count != sizeof(struct qib_flash)) + return -EINVAL; - if (copy_from_user(tmp, buf, count)) { - ret = -EFAULT; - goto bail_tmp; - } + tmp = memdup_user(buf, count); + if (IS_ERR(tmp)) + return PTR_ERR(tmp); dd = private2dd(file); if (qib_eeprom_write(dd, pos, tmp, count)) { @@ -361,8 +347,6 @@ static ssize_t flash_write(struct file *file, const char __user *buf, bail_tmp: kfree(tmp); - -bail: return ret; } diff --git a/drivers/infiniband/hw/qib/qib_qp.c b/drivers/infiniband/hw/qib/qib_qp.c index 9cc0aae1d781..f9b8cd2354d1 100644 --- a/drivers/infiniband/hw/qib/qib_qp.c +++ b/drivers/infiniband/hw/qib/qib_qp.c @@ -573,10 +573,6 @@ struct qib_qp_iter *qib_qp_iter_init(struct qib_ibdev *dev) return NULL; iter->dev = dev; - if (qib_qp_iter_next(iter)) { - kfree(iter); - return NULL; - } return iter; } diff --git a/drivers/infiniband/hw/usnic/usnic_ib_main.c b/drivers/infiniband/hw/usnic/usnic_ib_main.c index c229b9f4a52d..0a89a955550b 100644 --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@ -664,7 +664,8 @@ static int __init usnic_ib_init(void) return err; } - if (pci_register_driver(&usnic_ib_pci_driver)) { + err = pci_register_driver(&usnic_ib_pci_driver); + if (err) { usnic_err("Unable to register with PCI\n"); goto out_umem_fini; } diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index bdb540f25a88..870b4f212fbc 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -873,7 +873,8 @@ bail_qpn: free_qpn(&rdi->qp_dev->qpn_table, qp->ibqp.qp_num); bail_rq_wq: - vfree(qp->r_rq.wq); + if (!qp->ip) + vfree(qp->r_rq.wq); bail_driver_priv: rdi->driver_f.qp_priv_free(rdi, qp); diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c index ba6be060a476..7914c14478cd 100644 --- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -448,7 +448,7 @@ isert_alloc_login_buf(struct isert_conn *isert_conn, isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL); if (!isert_conn->login_rsp_buf) { - isert_err("Unable to allocate isert_conn->login_rspbuf\n"); + ret = -ENOMEM; goto out_unmap_login_req_buf; } diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index dfa23b075a88..883bbfe08e0e 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -522,6 +522,11 @@ static int srpt_refresh_port(struct srpt_port *sport) if (ret) goto err_query_port; + snprintf(sport->port_guid, sizeof(sport->port_guid), + "0x%016llx%016llx", + be64_to_cpu(sport->gid.global.subnet_prefix), + be64_to_cpu(sport->gid.global.interface_id)); + if (!sport->mad_agent) { memset(®_req, 0, sizeof(reg_req)); reg_req.mgmt_class = IB_MGMT_CLASS_DEVICE_MGMT; @@ -2548,10 +2553,6 @@ static void srpt_add_one(struct ib_device *device) sdev->device->name, i); goto err_ring; } - snprintf(sport->port_guid, sizeof(sport->port_guid), - "0x%016llx%016llx", - be64_to_cpu(sport->gid.global.subnet_prefix), - be64_to_cpu(sport->gid.global.interface_id)); } spin_lock(&srpt_dev_lock); diff --git a/drivers/input/keyboard/tegra-kbc.c b/drivers/input/keyboard/tegra-kbc.c index 7d61439be5f2..0c07e1023a46 100644 --- a/drivers/input/keyboard/tegra-kbc.c +++ b/drivers/input/keyboard/tegra-kbc.c @@ -376,7 +376,7 @@ static int tegra_kbc_start(struct tegra_kbc *kbc) /* Reset the KBC controller to clear all previous status.*/ reset_control_assert(kbc->rst); udelay(100); - reset_control_assert(kbc->rst); + reset_control_deassert(kbc->rst); udelay(100); tegra_kbc_config_pins(kbc); diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c index faa295ec4f31..c83bce89028b 100644 --- a/drivers/input/rmi4/rmi_driver.c +++ b/drivers/input/rmi4/rmi_driver.c @@ -553,7 +553,6 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, goto free_struct_buff; reg = find_first_bit(rdesc->presense_map, RMI_REG_DESC_PRESENSE_BITS); - map_offset = 0; for (i = 0; i < rdesc->num_registers; i++) { struct rmi_register_desc_item *item = &rdesc->registers[i]; int reg_size = struct_buf[offset]; @@ -576,6 +575,8 @@ int rmi_read_register_desc(struct rmi_device *d, u16 addr, item->reg = reg; item->reg_size = reg_size; + map_offset = 0; + do { for (b = 0; b < 7; b++) { if (struct_buf[offset] & (0x1 << b)) diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index b4d34086e73f..405252a884dd 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1305,6 +1305,7 @@ static int __init i8042_create_aux_port(int idx) serio->write = i8042_aux_write; serio->start = i8042_start; serio->stop = i8042_stop; + serio->ps2_cmd_mutex = &i8042_mutex; serio->port_data = port; serio->dev.parent = &i8042_platform_device->dev; if (idx < 0) { diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c index a61b2153ab8c..1ce3ecbe37f8 100644 --- a/drivers/input/touchscreen/ads7846.c +++ b/drivers/input/touchscreen/ads7846.c @@ -1473,7 +1473,6 @@ static int ads7846_remove(struct spi_device *spi) ads784x_hwmon_unregister(spi, ts); - regulator_disable(ts->reg); regulator_put(ts->reg); if (!ts->get_pendown_state) { diff --git a/drivers/input/touchscreen/silead.c b/drivers/input/touchscreen/silead.c index 7379fe153cf9..b2744a64e933 100644 --- a/drivers/input/touchscreen/silead.c +++ b/drivers/input/touchscreen/silead.c @@ -464,7 +464,7 @@ static int silead_ts_probe(struct i2c_client *client, return -ENODEV; /* Power GPIO pin */ - data->gpio_power = gpiod_get_optional(dev, "power", GPIOD_OUT_LOW); + data->gpio_power = devm_gpiod_get_optional(dev, "power", GPIOD_OUT_LOW); if (IS_ERR(data->gpio_power)) { if (PTR_ERR(data->gpio_power) != -EPROBE_DEFER) dev_err(dev, "Shutdown GPIO request failed\n"); diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index ce801170d5f2..641e88761319 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -879,7 +879,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) * We may have concurrent producers, so we need to be careful * not to touch any of the shadow cmdq state. */ - queue_read(cmd, Q_ENT(q, idx), q->ent_dwords); + queue_read(cmd, Q_ENT(q, cons), q->ent_dwords); dev_err(smmu->dev, "skipping command in error state:\n"); for (i = 0; i < ARRAY_SIZE(cmd); ++i) dev_err(smmu->dev, "\t0x%016llx\n", (unsigned long long)cmd[i]); @@ -890,7 +890,7 @@ static void arm_smmu_cmdq_skip_err(struct arm_smmu_device *smmu) return; } - queue_write(cmd, Q_ENT(q, idx), q->ent_dwords); + queue_write(Q_ENT(q, cons), cmd, q->ent_dwords); } static void arm_smmu_cmdq_issue_cmd(struct arm_smmu_device *smmu, @@ -1034,6 +1034,9 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_device *smmu, u32 sid, case STRTAB_STE_0_CFG_S2_TRANS: ste_live = true; break; + case STRTAB_STE_0_CFG_ABORT: + if (disable_bypass) + break; default: BUG(); /* STE corruption */ } diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c index 4f49fe29f202..2db74ebc3240 100644 --- a/drivers/iommu/arm-smmu.c +++ b/drivers/iommu/arm-smmu.c @@ -686,8 +686,7 @@ static struct iommu_gather_ops arm_smmu_gather_ops = { static irqreturn_t arm_smmu_context_fault(int irq, void *dev) { - int flags, ret; - u32 fsr, fsynr, resume; + u32 fsr, fsynr; unsigned long iova; struct iommu_domain *domain = dev; struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); @@ -701,34 +700,15 @@ static irqreturn_t arm_smmu_context_fault(int irq, void *dev) if (!(fsr & FSR_FAULT)) return IRQ_NONE; - if (fsr & FSR_IGN) - dev_err_ratelimited(smmu->dev, - "Unexpected context fault (fsr 0x%x)\n", - fsr); - fsynr = readl_relaxed(cb_base + ARM_SMMU_CB_FSYNR0); - flags = fsynr & FSYNR0_WNR ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ; - iova = readq_relaxed(cb_base + ARM_SMMU_CB_FAR); - if (!report_iommu_fault(domain, smmu->dev, iova, flags)) { - ret = IRQ_HANDLED; - resume = RESUME_RETRY; - } else { - dev_err_ratelimited(smmu->dev, - "Unhandled context fault: iova=0x%08lx, fsynr=0x%x, cb=%d\n", - iova, fsynr, cfg->cbndx); - ret = IRQ_NONE; - resume = RESUME_TERMINATE; - } - - /* Clear the faulting FSR */ - writel(fsr, cb_base + ARM_SMMU_CB_FSR); - /* Retry or terminate any stalled transactions */ - if (fsr & FSR_SS) - writel_relaxed(resume, cb_base + ARM_SMMU_CB_RESUME); + dev_err_ratelimited(smmu->dev, + "Unhandled context fault: fsr=0x%x, iova=0x%08lx, fsynr=0x%x, cb=%d\n", + fsr, iova, fsynr, cfg->cbndx); - return ret; + writel(fsr, cb_base + ARM_SMMU_CB_FSR); + return IRQ_HANDLED; } static irqreturn_t arm_smmu_global_fault(int irq, void *dev) @@ -837,7 +817,7 @@ static void arm_smmu_init_context_bank(struct arm_smmu_domain *smmu_domain, } /* SCTLR */ - reg = SCTLR_CFCFG | SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP; + reg = SCTLR_CFIE | SCTLR_CFRE | SCTLR_M | SCTLR_EAE_SBOP; if (stage1) reg |= SCTLR_S1_ASIDPNE; #ifdef __BIG_ENDIAN diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c index 08a1e2f3690f..00c8a08d56e7 100644 --- a/drivers/iommu/dma-iommu.c +++ b/drivers/iommu/dma-iommu.c @@ -68,7 +68,8 @@ void iommu_put_dma_cookie(struct iommu_domain *domain) if (!iovad) return; - put_iova_domain(iovad); + if (iovad->granule) + put_iova_domain(iovad); kfree(iovad); domain->iova_cookie = NULL; } @@ -151,12 +152,15 @@ int dma_direction_to_prot(enum dma_data_direction dir, bool coherent) } } -static struct iova *__alloc_iova(struct iova_domain *iovad, size_t size, +static struct iova *__alloc_iova(struct iommu_domain *domain, size_t size, dma_addr_t dma_limit) { + struct iova_domain *iovad = domain->iova_cookie; unsigned long shift = iova_shift(iovad); unsigned long length = iova_align(iovad, size) >> shift; + if (domain->geometry.force_aperture) + dma_limit = min(dma_limit, domain->geometry.aperture_end); /* * Enforce size-alignment to be safe - there could perhaps be an * attribute to control this per-device, or at least per-domain... @@ -314,7 +318,7 @@ struct page **iommu_dma_alloc(struct device *dev, size_t size, gfp_t gfp, if (!pages) return NULL; - iova = __alloc_iova(iovad, size, dev->coherent_dma_mask); + iova = __alloc_iova(domain, size, dev->coherent_dma_mask); if (!iova) goto out_free_pages; @@ -386,7 +390,7 @@ dma_addr_t iommu_dma_map_page(struct device *dev, struct page *page, phys_addr_t phys = page_to_phys(page) + offset; size_t iova_off = iova_offset(iovad, phys); size_t len = iova_align(iovad, size + iova_off); - struct iova *iova = __alloc_iova(iovad, len, dma_get_mask(dev)); + struct iova *iova = __alloc_iova(domain, len, dma_get_mask(dev)); if (!iova) return DMA_ERROR_CODE; @@ -538,7 +542,7 @@ int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, prev = s; } - iova = __alloc_iova(iovad, iova_len, dma_get_mask(dev)); + iova = __alloc_iova(domain, iova_len, dma_get_mask(dev)); if (!iova) goto out_restore_sg; diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c index 8c6139986d7d..def8ca1c982d 100644 --- a/drivers/iommu/io-pgtable-arm-v7s.c +++ b/drivers/iommu/io-pgtable-arm-v7s.c @@ -286,12 +286,14 @@ static int arm_v7s_pte_to_prot(arm_v7s_iopte pte, int lvl) int prot = IOMMU_READ; arm_v7s_iopte attr = pte >> ARM_V7S_ATTR_SHIFT(lvl); - if (attr & ARM_V7S_PTE_AP_RDONLY) + if (!(attr & ARM_V7S_PTE_AP_RDONLY)) prot |= IOMMU_WRITE; if ((attr & (ARM_V7S_TEX_MASK << ARM_V7S_TEX_SHIFT)) == 0) prot |= IOMMU_MMIO; else if (pte & ARM_V7S_ATTR_C) prot |= IOMMU_CACHE; + if (pte & ARM_V7S_ATTR_XN(lvl)) + prot |= IOMMU_NOEXEC; return prot; } diff --git a/drivers/iommu/mtk_iommu.h b/drivers/iommu/mtk_iommu.h index 9ed0a8462ccf..3dab13b4a211 100644 --- a/drivers/iommu/mtk_iommu.h +++ b/drivers/iommu/mtk_iommu.h @@ -55,19 +55,19 @@ struct mtk_iommu_data { bool enable_4GB; }; -static int compare_of(struct device *dev, void *data) +static inline int compare_of(struct device *dev, void *data) { return dev->of_node == data; } -static int mtk_iommu_bind(struct device *dev) +static inline int mtk_iommu_bind(struct device *dev) { struct mtk_iommu_data *data = dev_get_drvdata(dev); return component_bind_all(dev, &data->smi_imu); } -static void mtk_iommu_unbind(struct device *dev) +static inline void mtk_iommu_unbind(struct device *dev) { struct mtk_iommu_data *data = dev_get_drvdata(dev); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 7ceaba81efb4..36b9c28a5c91 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1545,7 +1545,12 @@ static int its_force_quiescent(void __iomem *base) u32 val; val = readl_relaxed(base + GITS_CTLR); - if (val & GITS_CTLR_QUIESCENT) + /* + * GIC architecture specification requires the ITS to be both + * disabled and quiescent for writes to GITS_BASER<n> or + * GITS_CBASER to not have UNPREDICTABLE results. + */ + if ((val & GITS_CTLR_QUIESCENT) && !(val & GITS_CTLR_ENABLE)) return 0; /* Disable the generation of all interrupts to this ITS */ diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 6fc56c3466b0..ede5672ab34d 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -667,13 +667,20 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, #endif #ifdef CONFIG_CPU_PM +/* Check whether it's single security state view */ +static bool gic_dist_security_disabled(void) +{ + return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS; +} + static int gic_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { if (cmd == CPU_PM_EXIT) { - gic_enable_redist(true); + if (gic_dist_security_disabled()) + gic_enable_redist(true); gic_cpu_sys_reg_init(); - } else if (cmd == CPU_PM_ENTER) { + } else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) { gic_write_grpen1(0); gic_enable_redist(false); } diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index c2cab572c511..390fac59c6bc 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -769,6 +769,13 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) int cpu; unsigned long flags, map = 0; + if (unlikely(nr_cpu_ids == 1)) { + /* Only one CPU? let's do a self-IPI... */ + writel_relaxed(2 << 24 | irq, + gic_data_dist_base(&gic_data[0]) + GIC_DIST_SOFTINT); + return; + } + raw_spin_lock_irqsave(&irq_controller_lock, flags); /* Convert our logical CPU mask into a physical one. */ diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index c5f33c3bd228..83f498393a7f 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -713,9 +713,6 @@ static int gic_shared_irq_domain_map(struct irq_domain *d, unsigned int virq, unsigned long flags; int i; - irq_set_chip_and_handler(virq, &gic_level_irq_controller, - handle_level_irq); - spin_lock_irqsave(&gic_lock, flags); gic_map_to_pin(intr, gic_cpu_pin); gic_map_to_vpe(intr, mips_cm_vp_id(vpe)); @@ -732,6 +729,10 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, { if (GIC_HWIRQ_TO_LOCAL(hw) < GIC_NUM_LOCAL_INTRS) return gic_local_irq_domain_map(d, virq, hw); + + irq_set_chip_and_handler(virq, &gic_level_irq_controller, + handle_level_irq); + return gic_shared_irq_domain_map(d, virq, hw, 0); } @@ -771,11 +772,13 @@ static int gic_irq_domain_alloc(struct irq_domain *d, unsigned int virq, hwirq = GIC_SHARED_TO_HWIRQ(base_hwirq + i); ret = irq_domain_set_hwirq_and_chip(d, virq + i, hwirq, - &gic_edge_irq_controller, + &gic_level_irq_controller, NULL); if (ret) goto error; + irq_set_handler(virq + i, handle_level_irq); + ret = gic_shared_irq_domain_map(d, virq + i, hwirq, cpu); if (ret) goto error; @@ -890,10 +893,17 @@ void gic_dev_domain_free(struct irq_domain *d, unsigned int virq, return; } +static void gic_dev_domain_activate(struct irq_domain *domain, + struct irq_data *d) +{ + gic_shared_irq_domain_map(domain, d->irq, d->hwirq, 0); +} + static struct irq_domain_ops gic_dev_domain_ops = { .xlate = gic_dev_domain_xlate, .alloc = gic_dev_domain_alloc, .free = gic_dev_domain_free, + .activate = gic_dev_domain_activate, }; static int gic_ipi_domain_xlate(struct irq_domain *d, struct device_node *ctrlr, diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 95a4ca6ce6ff..849ad441cd76 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -760,7 +760,8 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size, if (!d->nr_stripes || d->nr_stripes > INT_MAX || d->nr_stripes > SIZE_MAX / sizeof(atomic_t)) { - pr_err("nr_stripes too large"); + pr_err("nr_stripes too large or invalid: %u (start sector beyond end of disk?)", + (unsigned)d->nr_stripes); return -ENOMEM; } @@ -1820,7 +1821,7 @@ static int cache_alloc(struct cache *ca) free = roundup_pow_of_two(ca->sb.nbuckets) >> 10; if (!init_fifo(&ca->free[RESERVE_BTREE], 8, GFP_KERNEL) || - !init_fifo(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || + !init_fifo_exact(&ca->free[RESERVE_PRIO], prio_buckets(ca), GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_MOVINGGC], free, GFP_KERNEL) || !init_fifo(&ca->free[RESERVE_NONE], free, GFP_KERNEL) || !init_fifo(&ca->free_inc, free << 2, GFP_KERNEL) || @@ -1844,7 +1845,7 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, struct block_device *bdev, struct cache *ca) { char name[BDEVNAME_SIZE]; - const char *err = NULL; + const char *err = NULL; /* must be set for any error case */ int ret = 0; memcpy(&ca->sb, sb, sizeof(struct cache_sb)); @@ -1861,8 +1862,13 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, ca->discard = CACHE_DISCARD(&ca->sb); ret = cache_alloc(ca); - if (ret != 0) + if (ret != 0) { + if (ret == -ENOMEM) + err = "cache_alloc(): -ENOMEM"; + else + err = "cache_alloc(): unknown error"; goto err; + } if (kobject_add(&ca->kobj, &part_to_dev(bdev->bd_part)->kobj, "bcache")) { err = "error calling kobject_add"; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 4e9784b4e0ac..eedba67b0e3e 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -181,7 +181,7 @@ struct crypt_config { u8 key[0]; }; -#define MIN_IOS 16 +#define MIN_IOS 64 static void clone_init(struct dm_crypt_io *, struct bio *); static void kcryptd_queue_crypt(struct dm_crypt_io *io); diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 97e446d54a15..6a2e8dd44a1b 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -289,15 +289,13 @@ static int flakey_map(struct dm_target *ti, struct bio *bio) pb->bio_submitted = true; /* - * Map reads as normal only if corrupt_bio_byte set. + * Error reads if neither corrupt_bio_byte or drop_writes are set. + * Otherwise, flakey_end_io() will decide if the reads should be modified. */ if (bio_data_dir(bio) == READ) { - /* If flags were specified, only corrupt those that match. */ - if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && - all_corrupt_bio_flags_match(bio, fc)) - goto map_bio; - else + if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags)) return -EIO; + goto map_bio; } /* @@ -334,14 +332,21 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error) struct flakey_c *fc = ti->private; struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data)); - /* - * Corrupt successful READs while in down state. - */ if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) { - if (fc->corrupt_bio_byte) + if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) && + all_corrupt_bio_flags_match(bio, fc)) { + /* + * Corrupt successful matching READs while in down state. + */ corrupt_bio_data(bio, fc); - else + + } else if (!test_bit(DROP_WRITES, &fc->flags)) { + /* + * Error read during the down_interval if drop_writes + * wasn't configured. + */ return -EIO; + } } return error; diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index 4ca2d1df5b44..07fc1ad42ec5 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -291,9 +291,10 @@ static void header_from_disk(struct log_header_core *core, struct log_header_dis core->nr_regions = le64_to_cpu(disk->nr_regions); } -static int rw_header(struct log_c *lc, int rw) +static int rw_header(struct log_c *lc, int op) { - lc->io_req.bi_op = rw; + lc->io_req.bi_op = op; + lc->io_req.bi_op_flags = 0; return dm_io(&lc->io_req, 1, &lc->header_location, NULL); } @@ -316,7 +317,7 @@ static int read_header(struct log_c *log) { int r; - r = rw_header(log, READ); + r = rw_header(log, REQ_OP_READ); if (r) return r; @@ -630,7 +631,7 @@ static int disk_resume(struct dm_dirty_log *log) header_to_disk(&lc->header, lc->disk_header); /* write the new header */ - r = rw_header(lc, WRITE); + r = rw_header(lc, REQ_OP_WRITE); if (!r) { r = flush_header(lc); if (r) @@ -698,7 +699,7 @@ static int disk_flush(struct dm_dirty_log *log) log_clear_bit(lc, lc->clean_bits, i); } - r = rw_header(lc, WRITE); + r = rw_header(lc, REQ_OP_WRITE); if (r) fail_log_device(lc); else { diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 1b9795d75ef8..8abde6b8cedc 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -191,7 +191,6 @@ struct raid_dev { #define RT_FLAG_RS_BITMAP_LOADED 2 #define RT_FLAG_UPDATE_SBS 3 #define RT_FLAG_RESHAPE_RS 4 -#define RT_FLAG_KEEP_RS_FROZEN 5 /* Array elements of 64 bit needed for rebuild/failed disk bits */ #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8) @@ -861,6 +860,9 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size) { unsigned long min_region_size = rs->ti->len / (1 << 21); + if (rs_is_raid0(rs)) + return 0; + if (!region_size) { /* * Choose a reasonable default. All figures in sectors. @@ -930,6 +932,8 @@ static int validate_raid_redundancy(struct raid_set *rs) rebuild_cnt++; switch (rs->raid_type->level) { + case 0: + break; case 1: if (rebuild_cnt >= rs->md.raid_disks) goto too_many; @@ -2335,6 +2339,13 @@ static int analyse_superblocks(struct dm_target *ti, struct raid_set *rs) case 0: break; default: + /* + * We have to keep any raid0 data/metadata device pairs or + * the MD raid0 personality will fail to start the array. + */ + if (rs_is_raid0(rs)) + continue; + dev = container_of(rdev, struct raid_dev, rdev); if (dev->meta_dev) dm_put_device(ti, dev->meta_dev); @@ -2579,7 +2590,6 @@ static int rs_prepare_reshape(struct raid_set *rs) } else { /* Process raid1 without delta_disks */ mddev->raid_disks = rs->raid_disks; - set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags); reshape = false; } } else { @@ -2590,7 +2600,6 @@ static int rs_prepare_reshape(struct raid_set *rs) if (reshape) { set_bit(RT_FLAG_RESHAPE_RS, &rs->runtime_flags); set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); - set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags); } else if (mddev->raid_disks < rs->raid_disks) /* Create new superblocks and bitmaps, if any new disks */ set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); @@ -2902,7 +2911,6 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto bad; set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); - set_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags); /* Takeover ain't recovery, so disable recovery */ rs_setup_recovery(rs, MaxSector); rs_set_new(rs); @@ -3386,21 +3394,28 @@ static void raid_postsuspend(struct dm_target *ti) { struct raid_set *rs = ti->private; - if (test_and_clear_bit(RT_FLAG_RS_RESUMED, &rs->runtime_flags)) { - if (!rs->md.suspended) - mddev_suspend(&rs->md); - rs->md.ro = 1; - } + if (!rs->md.suspended) + mddev_suspend(&rs->md); + + rs->md.ro = 1; } static void attempt_restore_of_faulty_devices(struct raid_set *rs) { int i; - uint64_t failed_devices, cleared_failed_devices = 0; + uint64_t cleared_failed_devices[DISKS_ARRAY_ELEMS]; unsigned long flags; + bool cleared = false; struct dm_raid_superblock *sb; + struct mddev *mddev = &rs->md; struct md_rdev *r; + /* RAID personalities have to provide hot add/remove methods or we need to bail out. */ + if (!mddev->pers || !mddev->pers->hot_add_disk || !mddev->pers->hot_remove_disk) + return; + + memset(cleared_failed_devices, 0, sizeof(cleared_failed_devices)); + for (i = 0; i < rs->md.raid_disks; i++) { r = &rs->dev[i].rdev; if (test_bit(Faulty, &r->flags) && r->sb_page && @@ -3420,7 +3435,7 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs) * ourselves. */ if ((r->raid_disk >= 0) && - (r->mddev->pers->hot_remove_disk(r->mddev, r) != 0)) + (mddev->pers->hot_remove_disk(mddev, r) != 0)) /* Failed to revive this device, try next */ continue; @@ -3430,22 +3445,30 @@ static void attempt_restore_of_faulty_devices(struct raid_set *rs) clear_bit(Faulty, &r->flags); clear_bit(WriteErrorSeen, &r->flags); clear_bit(In_sync, &r->flags); - if (r->mddev->pers->hot_add_disk(r->mddev, r)) { + if (mddev->pers->hot_add_disk(mddev, r)) { r->raid_disk = -1; r->saved_raid_disk = -1; r->flags = flags; } else { r->recovery_offset = 0; - cleared_failed_devices |= 1 << i; + set_bit(i, (void *) cleared_failed_devices); + cleared = true; } } } - if (cleared_failed_devices) { + + /* If any failed devices could be cleared, update all sbs failed_devices bits */ + if (cleared) { + uint64_t failed_devices[DISKS_ARRAY_ELEMS]; + rdev_for_each(r, &rs->md) { sb = page_address(r->sb_page); - failed_devices = le64_to_cpu(sb->failed_devices); - failed_devices &= ~cleared_failed_devices; - sb->failed_devices = cpu_to_le64(failed_devices); + sb_retrieve_failed_devices(sb, failed_devices); + + for (i = 0; i < DISKS_ARRAY_ELEMS; i++) + failed_devices[i] &= ~cleared_failed_devices[i]; + + sb_update_failed_devices(sb, failed_devices); } } } @@ -3610,26 +3633,15 @@ static void raid_resume(struct dm_target *ti) * devices are reachable again. */ attempt_restore_of_faulty_devices(rs); - } else { - mddev->ro = 0; - mddev->in_sync = 0; + } - /* - * When passing in flags to the ctr, we expect userspace - * to reset them because they made it to the superblocks - * and reload the mapping anyway. - * - * -> only unfreeze recovery in case of a table reload or - * we'll have a bogus recovery/reshape position - * retrieved from the superblock by the ctr because - * the ongoing recovery/reshape will change it after read. - */ - if (!test_bit(RT_FLAG_KEEP_RS_FROZEN, &rs->runtime_flags)) - clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + mddev->ro = 0; + mddev->in_sync = 0; - if (mddev->suspended) - mddev_resume(mddev); - } + clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); + + if (mddev->suspended) + mddev_resume(mddev); } static struct target_type raid_target = { diff --git a/drivers/md/dm-round-robin.c b/drivers/md/dm-round-robin.c index 4ace1da17db8..6c25213ab38c 100644 --- a/drivers/md/dm-round-robin.c +++ b/drivers/md/dm-round-robin.c @@ -210,14 +210,17 @@ static struct dm_path *rr_select_path(struct path_selector *ps, size_t nr_bytes) struct path_info *pi = NULL; struct dm_path *current_path = NULL; + local_irq_save(flags); current_path = *this_cpu_ptr(s->current_path); if (current_path) { percpu_counter_dec(&s->repeat_count); - if (percpu_counter_read_positive(&s->repeat_count) > 0) + if (percpu_counter_read_positive(&s->repeat_count) > 0) { + local_irq_restore(flags); return current_path; + } } - spin_lock_irqsave(&s->lock, flags); + spin_lock(&s->lock); if (!list_empty(&s->valid_paths)) { pi = list_entry(s->valid_paths.next, struct path_info, list); list_move_tail(&pi->list, &s->valid_paths); diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 4387ccb79e64..7410c6d9a34d 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -69,5 +69,6 @@ OBJCOPYFLAGS := OBJCOPYFLAGS_lkdtm_rodata_objcopy.o := \ --set-section-flags .text=alloc,readonly \ --rename-section .text=.rodata -$(obj)/lkdtm_rodata_objcopy.o: $(obj)/lkdtm_rodata.o +targets += lkdtm_rodata.o lkdtm_rodata_objcopy.o +$(obj)/lkdtm_rodata_objcopy.o: $(obj)/lkdtm_rodata.o FORCE $(call if_changed,objcopy) diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c index bdee9a01ef35..c466ee2b0c97 100644 --- a/drivers/misc/cxl/context.c +++ b/drivers/misc/cxl/context.c @@ -90,8 +90,7 @@ int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master, */ mutex_lock(&afu->contexts_lock); idr_preload(GFP_KERNEL); - i = idr_alloc(&ctx->afu->contexts_idr, ctx, - ctx->afu->adapter->native->sl_ops->min_pe, + i = idr_alloc(&ctx->afu->contexts_idr, ctx, ctx->afu->adapter->min_pe, ctx->afu->num_procs, GFP_NOWAIT); idr_preload_end(); mutex_unlock(&afu->contexts_lock); diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h index de090533f18c..344a0ff8f8c7 100644 --- a/drivers/misc/cxl/cxl.h +++ b/drivers/misc/cxl/cxl.h @@ -561,7 +561,6 @@ struct cxl_service_layer_ops { u64 (*timebase_read)(struct cxl *adapter); int capi_mode; bool needs_reset_before_disable; - int min_pe; }; struct cxl_native { @@ -603,6 +602,7 @@ struct cxl { struct bin_attribute cxl_attr; int adapter_num; int user_irqs; + int min_pe; u64 ps_size; u16 psl_rev; u16 base_image; diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c index 3bcdaee11ba1..e606fdc4bc9c 100644 --- a/drivers/misc/cxl/native.c +++ b/drivers/misc/cxl/native.c @@ -924,7 +924,7 @@ static irqreturn_t native_irq_multiplexed(int irq, void *data) return fail_psl_irq(afu, &irq_info); } -void native_irq_wait(struct cxl_context *ctx) +static void native_irq_wait(struct cxl_context *ctx) { u64 dsisr; int timeout = 1000; diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index d152e2de8c93..6f0c4ac4b649 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -379,7 +379,7 @@ static int calc_capp_routing(struct pci_dev *dev, u64 *chipid, u64 *capp_unit_id static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_dev *dev) { - u64 psl_dsnctl; + u64 psl_dsnctl, psl_fircntl; u64 chipid; u64 capp_unit_id; int rc; @@ -398,8 +398,11 @@ static int init_implementation_adapter_psl_regs(struct cxl *adapter, struct pci_ cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL); /* snoop write mask */ cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL); - /* set fir_accum */ - cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, 0x0800000000000000ULL); + /* set fir_cntl to recommended value for production env */ + psl_fircntl = (0x2ULL << (63-3)); /* ce_report */ + psl_fircntl |= (0x1ULL << (63-6)); /* FIR_report */ + psl_fircntl |= 0x1ULL; /* ce_thresh */ + cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, psl_fircntl); /* for debugging with trace arrays */ cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL); @@ -1521,14 +1524,15 @@ static const struct cxl_service_layer_ops xsl_ops = { .write_timebase_ctrl = write_timebase_ctrl_xsl, .timebase_read = timebase_read_xsl, .capi_mode = OPAL_PHB_CAPI_MODE_DMA, - .min_pe = 1, /* Workaround for Mellanox CX4 HW bug */ }; static void set_sl_ops(struct cxl *adapter, struct pci_dev *dev) { if (dev->vendor == PCI_VENDOR_ID_MELLANOX && dev->device == 0x1013) { + /* Mellanox CX-4 */ dev_info(&adapter->dev, "Device uses an XSL\n"); adapter->native->sl_ops = &xsl_ops; + adapter->min_pe = 1; /* Workaround for CX-4 hardware bug */ } else { dev_info(&adapter->dev, "Device uses a PSL\n"); adapter->native->sl_ops = &psl_ops; diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c index dee8def1c193..7ada5f1b7bb6 100644 --- a/drivers/misc/cxl/vphb.c +++ b/drivers/misc/cxl/vphb.c @@ -221,7 +221,7 @@ int cxl_pci_vphb_add(struct cxl_afu *afu) /* Setup the PHB using arch provided callback */ phb->ops = &cxl_pcie_pci_ops; phb->cfg_addr = NULL; - phb->cfg_data = 0; + phb->cfg_data = NULL; phb->private_data = afu; phb->controller_ops = cxl_pci_controller_ops; diff --git a/drivers/misc/lkdtm_usercopy.c b/drivers/misc/lkdtm_usercopy.c index 5a3fd76eec27..5525a204db93 100644 --- a/drivers/misc/lkdtm_usercopy.c +++ b/drivers/misc/lkdtm_usercopy.c @@ -49,7 +49,7 @@ static noinline void do_usercopy_stack(bool to_user, bool bad_frame) /* This is a pointer to outside our current stack frame. */ if (bad_frame) { - bad_stack = do_usercopy_stack_callee((uintptr_t)bad_stack); + bad_stack = do_usercopy_stack_callee((uintptr_t)&bad_stack); } else { /* Put start address just inside stack. */ bad_stack = task_stack_page(current) + THREAD_SIZE; diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 48a5dd740f3b..2206d4477dbb 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -1726,6 +1726,7 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req) break; if (req_op(next) == REQ_OP_DISCARD || + req_op(next) == REQ_OP_SECURE_ERASE || req_op(next) == REQ_OP_FLUSH) break; @@ -2150,6 +2151,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) struct mmc_card *card = md->queue.card; struct mmc_host *host = card->host; unsigned long flags; + bool req_is_special = mmc_req_is_special(req); if (req && !mq->mqrq_prev->req) /* claim host only for the first request */ @@ -2190,8 +2192,7 @@ static int mmc_blk_issue_rq(struct mmc_queue *mq, struct request *req) } out: - if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || - mmc_req_is_special(req)) + if ((!req && !(mq->flags & MMC_QUEUE_NEW_REQUEST)) || req_is_special) /* * Release host when there are no more requests * and after special request(discard, flush) is done. diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index bf14642a576a..708057261b38 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -33,7 +33,8 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) /* * We only like normal block requests and discards. */ - if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) { + if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD && + req_op(req) != REQ_OP_SECURE_ERASE) { blk_dump_rq_flags(req, "MMC bad request"); return BLKPREP_KILL; } @@ -64,6 +65,8 @@ static int mmc_queue_thread(void *d) spin_unlock_irq(q->queue_lock); if (req || mq->mqrq_prev->req) { + bool req_is_special = mmc_req_is_special(req); + set_current_state(TASK_RUNNING); mq->issue_fn(mq, req); cond_resched(); @@ -79,7 +82,7 @@ static int mmc_queue_thread(void *d) * has been finished. Do not assign it to previous * request. */ - if (mmc_req_is_special(req)) + if (req_is_special) mq->mqrq_cur->req = NULL; mq->mqrq_prev->brq.mrq.data = NULL; diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index d62531124d54..fee5e1271465 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -4,7 +4,9 @@ static inline bool mmc_req_is_special(struct request *req) { return req && - (req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD); + (req_op(req) == REQ_OP_FLUSH || + req_op(req) == REQ_OP_DISCARD || + req_op(req) == REQ_OP_SECURE_ERASE); } struct request; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1f276fa30ba6..217e8da0628c 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -152,7 +152,7 @@ module_param(lacp_rate, charp, 0); MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner; " "0 for slow, 1 for fast"); module_param(ad_select, charp, 0); -MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic; " +MODULE_PARM_DESC(ad_select, "802.3ad aggregation selection logic; " "0 for stable (default), 1 for bandwidth, " "2 for count"); module_param(min_links, int, 0); diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index 8f12bddd5dc9..a0b453ea34c9 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -258,7 +258,7 @@ * BCM5325 and BCM5365 share most definitions below */ #define B53_ARLTBL_MAC_VID_ENTRY(n) (0x10 * (n)) -#define ARLTBL_MAC_MASK 0xffffffffffff +#define ARLTBL_MAC_MASK 0xffffffffffffULL #define ARLTBL_VID_S 48 #define ARLTBL_VID_MASK_25 0xff #define ARLTBL_VID_MASK 0xfff diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index d36aedde8cb9..d1d9d3cf9139 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3187,6 +3187,7 @@ static int mv88e6xxx_set_addr(struct dsa_switch *ds, u8 *addr) return err; } +#ifdef CONFIG_NET_DSA_HWMON static int mv88e6xxx_mdio_page_read(struct dsa_switch *ds, int port, int page, int reg) { @@ -3212,6 +3213,7 @@ static int mv88e6xxx_mdio_page_write(struct dsa_switch *ds, int port, int page, return ret; } +#endif static int mv88e6xxx_port_to_mdio_addr(struct mv88e6xxx_chip *chip, int port) { diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 37a0f463b8de..18bb9556dd00 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -793,6 +793,8 @@ int xgene_enet_phy_connect(struct net_device *ndev) netdev_err(ndev, "Could not connect to PHY\n"); return -ENODEV; } +#else + return -ENODEV; #endif } diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 4bff0f3040df..b0da9693f28a 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -771,8 +771,10 @@ int arc_emac_probe(struct net_device *ndev, int interface) priv->dev = dev; priv->regs = devm_ioremap_resource(dev, &res_regs); - if (IS_ERR(priv->regs)) - return PTR_ERR(priv->regs); + if (IS_ERR(priv->regs)) { + err = PTR_ERR(priv->regs); + goto out_put_node; + } dev_dbg(dev, "Registers base address is 0x%p\n", priv->regs); diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index ff300f7cf529..659261218d9f 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -12552,10 +12552,6 @@ static int tg3_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, info->data = TG3_RSS_MAX_NUM_QS; } - /* The first interrupt vector only - * handles link interrupts. - */ - info->data -= 1; return 0; default: @@ -14014,6 +14010,7 @@ static int tg3_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) } if ((ec->rx_coalesce_usecs > MAX_RXCOL_TICKS) || + (!ec->rx_coalesce_usecs) || (ec->tx_coalesce_usecs > MAX_TXCOL_TICKS) || (ec->rx_max_coalesced_frames > MAX_RXMAX_FRAMES) || (ec->tx_max_coalesced_frames > MAX_TXMAX_FRAMES) || diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 36893d8958d4..b6fcf10621b6 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -403,11 +403,11 @@ #define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII 0x00000004 #define MACB_CAPS_NO_GIGABIT_HALF 0x00000008 #define MACB_CAPS_USRIO_DISABLED 0x00000010 +#define MACB_CAPS_JUMBO 0x00000020 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 #define MACB_CAPS_MACB_IS_GEM 0x80000000 -#define MACB_CAPS_JUMBO 0x00000010 /* Bit manipulation macros */ #define MACB_BIT(name) \ diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 1471e16ba719..f45385f5c6e5 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1299,6 +1299,7 @@ static int dm9000_open(struct net_device *dev) { struct board_info *db = netdev_priv(dev); + unsigned int irq_flags = irq_get_trigger_type(dev->irq); if (netif_msg_ifup(db)) dev_dbg(db->dev, "enabling %s\n", dev->name); @@ -1306,9 +1307,11 @@ dm9000_open(struct net_device *dev) /* If there is no IRQ type specified, tell the user that this is a * problem */ - if (irq_get_trigger_type(dev->irq) == IRQF_TRIGGER_NONE) + if (irq_flags == IRQF_TRIGGER_NONE) dev_warn(db->dev, "WARNING: no IRQ resource flags set.\n"); + irq_flags |= IRQF_SHARED; + /* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */ iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */ mdelay(1); /* delay needs by DM9000B */ @@ -1316,8 +1319,7 @@ dm9000_open(struct net_device *dev) /* Initialize DM9000 board */ dm9000_init_dm9000(dev); - if (request_irq(dev->irq, dm9000_interrupt, IRQF_SHARED, - dev->name, dev)) + if (request_irq(dev->irq, dm9000_interrupt, irq_flags, dev->name, dev)) return -EAGAIN; /* Now that we have an interrupt handler hooked up we can unmask * our interrupts diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index 1235c7f2564b..1e1eb92998fb 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -17,7 +17,7 @@ static const struct mac_stats_string g_gmac_stats_string[] = { {"gmac_rx_octets_total_ok", MAC_STATS_FIELD_OFF(rx_good_bytes)}, {"gmac_rx_octets_bad", MAC_STATS_FIELD_OFF(rx_bad_bytes)}, {"gmac_rx_uc_pkts", MAC_STATS_FIELD_OFF(rx_uc_pkts)}, - {"gamc_rx_mc_pkts", MAC_STATS_FIELD_OFF(rx_mc_pkts)}, + {"gmac_rx_mc_pkts", MAC_STATS_FIELD_OFF(rx_mc_pkts)}, {"gmac_rx_bc_pkts", MAC_STATS_FIELD_OFF(rx_bc_pkts)}, {"gmac_rx_pkts_64octets", MAC_STATS_FIELD_OFF(rx_64bytes)}, {"gmac_rx_pkts_65to127", MAC_STATS_FIELD_OFF(rx_65to127)}, diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 7fd4d54599e4..6b03c8553e59 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -2032,7 +2032,8 @@ const struct e1000_info e1000_82574_info = { | FLAG2_DISABLE_ASPM_L0S | FLAG2_DISABLE_ASPM_L1 | FLAG2_NO_DISABLE_RX - | FLAG2_DMA_BURST, + | FLAG2_DMA_BURST + | FLAG2_CHECK_SYSTIM_OVERFLOW, .pba = 32, .max_hw_frame_size = DEFAULT_JUMBO, .get_variants = e1000_get_variants_82571, @@ -2053,7 +2054,8 @@ const struct e1000_info e1000_82583_info = { | FLAG_HAS_CTRLEXT_ON_LOAD, .flags2 = FLAG2_DISABLE_ASPM_L0S | FLAG2_DISABLE_ASPM_L1 - | FLAG2_NO_DISABLE_RX, + | FLAG2_NO_DISABLE_RX + | FLAG2_CHECK_SYSTIM_OVERFLOW, .pba = 32, .max_hw_frame_size = DEFAULT_JUMBO, .get_variants = e1000_get_variants_82571, diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index ef96cd11d6d2..879cca47b021 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -452,6 +452,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca); #define FLAG2_PCIM2PCI_ARBITER_WA BIT(11) #define FLAG2_DFLT_CRC_STRIPPING BIT(12) #define FLAG2_CHECK_RX_HWTSTAMP BIT(13) +#define FLAG2_CHECK_SYSTIM_OVERFLOW BIT(14) #define E1000_RX_DESC_PS(R, i) \ (&(((union e1000_rx_desc_packet_split *)((R).desc))[i])) diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 3e11322d8d58..f3aaca743ea3 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -5885,7 +5885,8 @@ const struct e1000_info e1000_pch_lpt_info = { | FLAG_HAS_JUMBO_FRAMES | FLAG_APME_IN_WUC, .flags2 = FLAG2_HAS_PHY_STATS - | FLAG2_HAS_EEE, + | FLAG2_HAS_EEE + | FLAG2_CHECK_SYSTIM_OVERFLOW, .pba = 26, .max_hw_frame_size = 9022, .get_variants = e1000_get_variants_ich8lan, diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 02f443958f31..7017281ba2dc 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -4303,6 +4303,42 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter) } /** + * e1000e_sanitize_systim - sanitize raw cycle counter reads + * @hw: pointer to the HW structure + * @systim: cycle_t value read, sanitized and returned + * + * Errata for 82574/82583 possible bad bits read from SYSTIMH/L: + * check to see that the time is incrementing at a reasonable + * rate and is a multiple of incvalue. + **/ +static cycle_t e1000e_sanitize_systim(struct e1000_hw *hw, cycle_t systim) +{ + u64 time_delta, rem, temp; + cycle_t systim_next; + u32 incvalue; + int i; + + incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK; + for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) { + /* latch SYSTIMH on read of SYSTIML */ + systim_next = (cycle_t)er32(SYSTIML); + systim_next |= (cycle_t)er32(SYSTIMH) << 32; + + time_delta = systim_next - systim; + temp = time_delta; + /* VMWare users have seen incvalue of zero, don't div / 0 */ + rem = incvalue ? do_div(temp, incvalue) : (time_delta != 0); + + systim = systim_next; + + if ((time_delta < E1000_82574_SYSTIM_EPSILON) && (rem == 0)) + break; + } + + return systim; +} + +/** * e1000e_cyclecounter_read - read raw cycle counter (used by time counter) * @cc: cyclecounter structure **/ @@ -4312,7 +4348,7 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc) cc); struct e1000_hw *hw = &adapter->hw; u32 systimel, systimeh; - cycle_t systim, systim_next; + cycle_t systim; /* SYSTIMH latching upon SYSTIML read does not work well. * This means that if SYSTIML overflows after we read it but before * we read SYSTIMH, the value of SYSTIMH has been incremented and we @@ -4335,33 +4371,9 @@ static cycle_t e1000e_cyclecounter_read(const struct cyclecounter *cc) systim = (cycle_t)systimel; systim |= (cycle_t)systimeh << 32; - if ((hw->mac.type == e1000_82574) || (hw->mac.type == e1000_82583)) { - u64 time_delta, rem, temp; - u32 incvalue; - int i; - - /* errata for 82574/82583 possible bad bits read from SYSTIMH/L - * check to see that the time is incrementing at a reasonable - * rate and is a multiple of incvalue - */ - incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK; - for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) { - /* latch SYSTIMH on read of SYSTIML */ - systim_next = (cycle_t)er32(SYSTIML); - systim_next |= (cycle_t)er32(SYSTIMH) << 32; - - time_delta = systim_next - systim; - temp = time_delta; - /* VMWare users have seen incvalue of zero, don't div / 0 */ - rem = incvalue ? do_div(temp, incvalue) : (time_delta != 0); - - systim = systim_next; + if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW) + systim = e1000e_sanitize_systim(hw, systim); - if ((time_delta < E1000_82574_SYSTIM_EPSILON) && - (rem == 0)) - break; - } - } return systim; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 81c99e1be708..c6ac7a61812f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4554,23 +4554,38 @@ static u8 i40e_get_iscsi_tc_map(struct i40e_pf *pf) **/ static u8 i40e_dcb_get_num_tc(struct i40e_dcbx_config *dcbcfg) { + int i, tc_unused = 0; u8 num_tc = 0; - int i; + u8 ret = 0; /* Scan the ETS Config Priority Table to find * traffic class enabled for a given priority - * and use the traffic class index to get the - * number of traffic classes enabled + * and create a bitmask of enabled TCs */ - for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { - if (dcbcfg->etscfg.prioritytable[i] > num_tc) - num_tc = dcbcfg->etscfg.prioritytable[i]; - } + for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) + num_tc |= BIT(dcbcfg->etscfg.prioritytable[i]); - /* Traffic class index starts from zero so - * increment to return the actual count + /* Now scan the bitmask to check for + * contiguous TCs starting with TC0 */ - return num_tc + 1; + for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) { + if (num_tc & BIT(i)) { + if (!tc_unused) { + ret++; + } else { + pr_err("Non-contiguous TC - Disabling DCB\n"); + return 1; + } + } else { + tc_unused = 1; + } + } + + /* There is always at least TC0 */ + if (!ret) + ret = 1; + + return ret; } /** diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index e61b647f5f2a..336c103ae374 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -744,7 +744,8 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) } } - shhwtstamps.hwtstamp = ktime_sub_ns(shhwtstamps.hwtstamp, adjust); + shhwtstamps.hwtstamp = + ktime_add_ns(shhwtstamps.hwtstamp, adjust); skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps); dev_kfree_skb_any(adapter->ptp_tx_skb); @@ -767,13 +768,32 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, struct sk_buff *skb) { __le64 *regval = (__le64 *)va; + struct igb_adapter *adapter = q_vector->adapter; + int adjust = 0; /* The timestamp is recorded in little endian format. * DWORD: 0 1 2 3 * Field: Reserved Reserved SYSTIML SYSTIMH */ - igb_ptp_systim_to_hwtstamp(q_vector->adapter, skb_hwtstamps(skb), + igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), le64_to_cpu(regval[1])); + + /* adjust timestamp for the RX latency based on link speed */ + if (adapter->hw.mac.type == e1000_i210) { + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGB_I210_RX_LATENCY_10; + break; + case SPEED_100: + adjust = IGB_I210_RX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGB_I210_RX_LATENCY_1000; + break; + } + } + skb_hwtstamps(skb)->hwtstamp = + ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); } /** @@ -825,7 +845,7 @@ void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, } } skb_hwtstamps(skb)->hwtstamp = - ktime_add_ns(skb_hwtstamps(skb)->hwtstamp, adjust); + ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); /* Update the last_rx_timestamp timer in order to enable watchdog check * for error case of latched timestamp on a dropped packet. diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 5418c69a7463..b4f03748adc0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4100,6 +4100,8 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; u32 vlnctrl, i; + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: @@ -4112,8 +4114,7 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) /* fall through */ case ixgbe_mac_82598EB: /* legacy case, we can just disable VLAN filtering */ - vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); - vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); + vlnctrl &= ~IXGBE_VLNCTRL_VFE; IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); return; } @@ -4125,6 +4126,10 @@ static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) /* Set flag so we don't redo unnecessary work */ adapter->flags2 |= IXGBE_FLAG2_VLAN_PROMISC; + /* For VMDq and SR-IOV we must leave VLAN filtering enabled */ + vlnctrl |= IXGBE_VLNCTRL_VFE; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + /* Add PF to all active pools */ for (i = IXGBE_VLVF_ENTRIES; --i;) { u32 reg_offset = IXGBE_VLVFB(i * 2 + VMDQ_P(0) / 32); @@ -4191,6 +4196,11 @@ static void ixgbe_vlan_promisc_disable(struct ixgbe_adapter *adapter) struct ixgbe_hw *hw = &adapter->hw; u32 vlnctrl, i; + /* Set VLAN filtering to enabled */ + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlnctrl |= IXGBE_VLNCTRL_VFE; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: @@ -4202,10 +4212,6 @@ static void ixgbe_vlan_promisc_disable(struct ixgbe_adapter *adapter) break; /* fall through */ case ixgbe_mac_82598EB: - vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); - vlnctrl &= ~IXGBE_VLNCTRL_CFIEN; - vlnctrl |= IXGBE_VLNCTRL_VFE; - IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); return; } @@ -8390,12 +8396,14 @@ static int parse_tc_actions(struct ixgbe_adapter *adapter, struct tcf_exts *exts, u64 *action, u8 *queue) { const struct tc_action *a; + LIST_HEAD(actions); int err; if (tc_no_actions(exts)) return -EINVAL; - tc_for_each_action(a, exts) { + tcf_exts_to_list(exts, &actions); + list_for_each_entry(a, &actions, list) { /* Drop action */ if (is_tcf_gact_shot(a)) { @@ -9517,6 +9525,7 @@ skip_sriov: /* copy netdev features into list of user selectable features */ netdev->hw_features |= netdev->features | + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_RXALL | diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index b57ae3afb994..f1609542adf1 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -245,12 +245,16 @@ static int mtk_phy_connect(struct mtk_mac *mac) case PHY_INTERFACE_MODE_MII: ge_mode = 1; break; - case PHY_INTERFACE_MODE_RMII: + case PHY_INTERFACE_MODE_REVMII: ge_mode = 2; break; + case PHY_INTERFACE_MODE_RMII: + if (!mac->id) + goto err_phy; + ge_mode = 3; + break; default: - dev_err(eth->dev, "invalid phy_mode\n"); - return -1; + goto err_phy; } /* put the gmac into the right mode */ @@ -263,13 +267,25 @@ static int mtk_phy_connect(struct mtk_mac *mac) mac->phy_dev->autoneg = AUTONEG_ENABLE; mac->phy_dev->speed = 0; mac->phy_dev->duplex = 0; + + if (of_phy_is_fixed_link(mac->of_node)) + mac->phy_dev->supported |= + SUPPORTED_Pause | SUPPORTED_Asym_Pause; + mac->phy_dev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause; mac->phy_dev->advertising = mac->phy_dev->supported | ADVERTISED_Autoneg; phy_start_aneg(mac->phy_dev); + of_node_put(np); + return 0; + +err_phy: + of_node_put(np); + dev_err(eth->dev, "invalid phy_mode\n"); + return -EINVAL; } static int mtk_mdio_init(struct mtk_eth *eth) @@ -542,15 +558,15 @@ static inline struct mtk_tx_buf *mtk_desc_to_tx_buf(struct mtk_tx_ring *ring, return &ring->buf[idx]; } -static void mtk_tx_unmap(struct device *dev, struct mtk_tx_buf *tx_buf) +static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf) { if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) { - dma_unmap_single(dev, + dma_unmap_single(eth->dev, dma_unmap_addr(tx_buf, dma_addr0), dma_unmap_len(tx_buf, dma_len0), DMA_TO_DEVICE); } else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) { - dma_unmap_page(dev, + dma_unmap_page(eth->dev, dma_unmap_addr(tx_buf, dma_addr0), dma_unmap_len(tx_buf, dma_len0), DMA_TO_DEVICE); @@ -595,9 +611,9 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, if (skb_vlan_tag_present(skb)) txd4 |= TX_DMA_INS_VLAN | skb_vlan_tag_get(skb); - mapped_addr = dma_map_single(&dev->dev, skb->data, + mapped_addr = dma_map_single(eth->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) + if (unlikely(dma_mapping_error(eth->dev, mapped_addr))) return -ENOMEM; WRITE_ONCE(itxd->txd1, mapped_addr); @@ -623,10 +639,10 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, n_desc++; frag_map_size = min(frag_size, MTK_TX_DMA_BUF_LEN); - mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset, + mapped_addr = skb_frag_dma_map(eth->dev, frag, offset, frag_map_size, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(&dev->dev, mapped_addr))) + if (unlikely(dma_mapping_error(eth->dev, mapped_addr))) goto err_dma; if (i == nr_frags - 1 && @@ -679,7 +695,7 @@ err_dma: tx_buf = mtk_desc_to_tx_buf(ring, itxd); /* unmap dma */ - mtk_tx_unmap(&dev->dev, tx_buf); + mtk_tx_unmap(eth, tx_buf); itxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; itxd = mtk_qdma_phys_to_virt(ring, itxd->txd2); @@ -836,11 +852,11 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, netdev->stats.rx_dropped++; goto release_desc; } - dma_addr = dma_map_single(ð->netdev[mac]->dev, + dma_addr = dma_map_single(eth->dev, new_data + NET_SKB_PAD, ring->buf_size, DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) { + if (unlikely(dma_mapping_error(eth->dev, dma_addr))) { skb_free_frag(new_data); netdev->stats.rx_dropped++; goto release_desc; @@ -855,7 +871,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, } skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); - dma_unmap_single(&netdev->dev, trxd.rxd1, + dma_unmap_single(eth->dev, trxd.rxd1, ring->buf_size, DMA_FROM_DEVICE); pktlen = RX_DMA_GET_PLEN0(trxd.rxd2); skb->dev = netdev; @@ -937,7 +953,7 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) done[mac]++; budget--; } - mtk_tx_unmap(eth->dev, tx_buf); + mtk_tx_unmap(eth, tx_buf); ring->last_free = desc; atomic_inc(&ring->free_count); @@ -1092,7 +1108,7 @@ static void mtk_tx_clean(struct mtk_eth *eth) if (ring->buf) { for (i = 0; i < MTK_DMA_SIZE; i++) - mtk_tx_unmap(eth->dev, &ring->buf[i]); + mtk_tx_unmap(eth, &ring->buf[i]); kfree(ring->buf); ring->buf = NULL; } @@ -1751,6 +1767,7 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) goto free_netdev; } spin_lock_init(&mac->hw_stats->stats_lock); + u64_stats_init(&mac->hw_stats->syncp); mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET; SET_NETDEV_DEV(eth->netdev[id], eth->dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 0f19b01e3fff..dc8b1cb0fdc8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -318,6 +318,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, u32 *action, u32 *flow_tag) { const struct tc_action *a; + LIST_HEAD(actions); if (tc_no_actions(exts)) return -EINVAL; @@ -325,7 +326,8 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, *flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; *action = 0; - tc_for_each_action(a, exts) { + tcf_exts_to_list(exts, &actions); + list_for_each_entry(a, &actions, list) { /* Only support a single action per rule */ if (*action) return -EINVAL; @@ -362,13 +364,15 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, u32 *action, u32 *dest_vport) { const struct tc_action *a; + LIST_HEAD(actions); if (tc_no_actions(exts)) return -EINVAL; *action = 0; - tc_for_each_action(a, exts) { + tcf_exts_to_list(exts, &actions); + list_for_each_entry(a, &actions, list) { /* Only support a single action per rule */ if (*action) return -EINVAL; @@ -503,6 +507,7 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow; struct tc_action *a; struct mlx5_fc *counter; + LIST_HEAD(actions); u64 bytes; u64 packets; u64 lastuse; @@ -518,7 +523,8 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv, mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); - tc_for_each_action(a, f->exts) + tcf_exts_to_list(f->exts, &actions); + list_for_each_entry(a, &actions, list) tcf_action_stats_update(a, bytes, packets, lastuse); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 7ca9201f7dcb..1721098eef13 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -3383,6 +3383,15 @@ MLXSW_ITEM32(reg, ritr, ipv4_fe, 0x04, 29, 1); */ MLXSW_ITEM32(reg, ritr, ipv6_fe, 0x04, 28, 1); +/* reg_ritr_lb_en + * Loop-back filter enable for unicast packets. + * If the flag is set then loop-back filter for unicast packets is + * implemented on the RIF. Multicast packets are always subject to + * loop-back filtering. + * Access: RW + */ +MLXSW_ITEM32(reg, ritr, lb_en, 0x04, 24, 1); + /* reg_ritr_virtual_router * Virtual router ID associated with the router interface. * Access: RW @@ -3484,6 +3493,7 @@ static inline void mlxsw_reg_ritr_pack(char *payload, bool enable, mlxsw_reg_ritr_op_set(payload, op); mlxsw_reg_ritr_rif_set(payload, rif); mlxsw_reg_ritr_ipv4_fe_set(payload, 1); + mlxsw_reg_ritr_lb_en_set(payload, 1); mlxsw_reg_ritr_mtu_set(payload, mtu); mlxsw_reg_ritr_if_mac_memcpy_to(payload, mac); } @@ -4000,6 +4010,7 @@ static inline void mlxsw_reg_ralue_pack(char *payload, { MLXSW_REG_ZERO(ralue, payload); mlxsw_reg_ralue_protocol_set(payload, protocol); + mlxsw_reg_ralue_op_set(payload, op); mlxsw_reg_ralue_virtual_router_set(payload, virtual_router); mlxsw_reg_ralue_prefix_len_set(payload, prefix_len); mlxsw_reg_ralue_entry_type_set(payload, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index c3e61500819d..1f8168906811 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -942,8 +942,8 @@ static void mlxsw_sp_port_vport_destroy(struct mlxsw_sp_port *mlxsw_sp_vport) kfree(mlxsw_sp_vport); } -int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, - u16 vid) +static int mlxsw_sp_port_add_vid(struct net_device *dev, + __be16 __always_unused proto, u16 vid) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp_port *mlxsw_sp_vport; @@ -956,16 +956,12 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, if (!vid) return 0; - if (mlxsw_sp_port_vport_find(mlxsw_sp_port, vid)) { - netdev_warn(dev, "VID=%d already configured\n", vid); + if (mlxsw_sp_port_vport_find(mlxsw_sp_port, vid)) return 0; - } mlxsw_sp_vport = mlxsw_sp_port_vport_create(mlxsw_sp_port, vid); - if (!mlxsw_sp_vport) { - netdev_err(dev, "Failed to create vPort for VID=%d\n", vid); + if (!mlxsw_sp_vport) return -ENOMEM; - } /* When adding the first VLAN interface on a bridged port we need to * transition all the active 802.1Q bridge VLANs to use explicit @@ -973,24 +969,17 @@ int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, */ if (list_is_singular(&mlxsw_sp_port->vports_list)) { err = mlxsw_sp_port_vp_mode_trans(mlxsw_sp_port); - if (err) { - netdev_err(dev, "Failed to set to Virtual mode\n"); + if (err) goto err_port_vp_mode_trans; - } } err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, false); - if (err) { - netdev_err(dev, "Failed to disable learning for VID=%d\n", vid); + if (err) goto err_port_vid_learning_set; - } err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, true, untagged); - if (err) { - netdev_err(dev, "Failed to set VLAN membership for VID=%d\n", - vid); + if (err) goto err_port_add_vid; - } return 0; @@ -1010,7 +999,6 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev, struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); struct mlxsw_sp_port *mlxsw_sp_vport; struct mlxsw_sp_fid *f; - int err; /* VLAN 0 is removed from HW filter when device goes down, but * it is reserved in our case, so simply return. @@ -1019,23 +1007,12 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev, return 0; mlxsw_sp_vport = mlxsw_sp_port_vport_find(mlxsw_sp_port, vid); - if (!mlxsw_sp_vport) { - netdev_warn(dev, "VID=%d does not exist\n", vid); + if (WARN_ON(!mlxsw_sp_vport)) return 0; - } - err = mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false); - if (err) { - netdev_err(dev, "Failed to set VLAN membership for VID=%d\n", - vid); - return err; - } + mlxsw_sp_port_vlan_set(mlxsw_sp_vport, vid, vid, false, false); - err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true); - if (err) { - netdev_err(dev, "Failed to enable learning for VID=%d\n", vid); - return err; - } + mlxsw_sp_port_vid_learning_set(mlxsw_sp_vport, vid, true); /* Drop FID reference. If this was the last reference the * resources will be freed. @@ -1048,13 +1025,8 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev, * transition all active 802.1Q bridge VLANs to use VID to FID * mappings and set port's mode to VLAN mode. */ - if (list_is_singular(&mlxsw_sp_port->vports_list)) { - err = mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); - if (err) { - netdev_err(dev, "Failed to set to VLAN mode\n"); - return err; - } - } + if (list_is_singular(&mlxsw_sp_port->vports_list)) + mlxsw_sp_port_vlan_mode_trans(mlxsw_sp_port); mlxsw_sp_port_vport_destroy(mlxsw_sp_vport); @@ -1149,6 +1121,7 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, bool ingress) { const struct tc_action *a; + LIST_HEAD(actions); int err; if (!tc_single_action(cls->exts)) { @@ -1156,7 +1129,8 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, return -ENOTSUPP; } - tc_for_each_action(a, cls->exts) { + tcf_exts_to_list(cls->exts, &actions); + list_for_each_entry(a, &actions, list) { if (!is_tcf_mirred_mirror(a) || protocol != htons(ETH_P_ALL)) return -ENOTSUPP; @@ -2076,6 +2050,18 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port) return 0; } +static int mlxsw_sp_port_pvid_vport_create(struct mlxsw_sp_port *mlxsw_sp_port) +{ + mlxsw_sp_port->pvid = 1; + + return mlxsw_sp_port_add_vid(mlxsw_sp_port->dev, 0, 1); +} + +static int mlxsw_sp_port_pvid_vport_destroy(struct mlxsw_sp_port *mlxsw_sp_port) +{ + return mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1); +} + static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, bool split, u8 module, u8 width, u8 lane) { @@ -2191,7 +2177,15 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_port_dcb_init; } + err = mlxsw_sp_port_pvid_vport_create(mlxsw_sp_port); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to create PVID vPort\n", + mlxsw_sp_port->local_port); + goto err_port_pvid_vport_create; + } + mlxsw_sp_port_switchdev_init(mlxsw_sp_port); + mlxsw_sp->ports[local_port] = mlxsw_sp_port; err = register_netdev(dev); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to register netdev\n", @@ -2208,24 +2202,23 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port, goto err_core_port_init; } - err = mlxsw_sp_port_vlan_init(mlxsw_sp_port); - if (err) - goto err_port_vlan_init; - - mlxsw_sp->ports[local_port] = mlxsw_sp_port; return 0; -err_port_vlan_init: - mlxsw_core_port_fini(&mlxsw_sp_port->core_port); err_core_port_init: unregister_netdev(dev); err_register_netdev: + mlxsw_sp->ports[local_port] = NULL; + mlxsw_sp_port_switchdev_fini(mlxsw_sp_port); + mlxsw_sp_port_pvid_vport_destroy(mlxsw_sp_port); +err_port_pvid_vport_create: + mlxsw_sp_port_dcb_fini(mlxsw_sp_port); err_port_dcb_init: err_port_ets_init: err_port_buffers_init: err_port_admin_status_set: err_port_mtu_set: err_port_speed_by_width_set: + mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); err_port_swid_set: err_port_system_port_mapping_set: err_dev_addr_init: @@ -2245,12 +2238,12 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) if (!mlxsw_sp_port) return; - mlxsw_sp->ports[local_port] = NULL; mlxsw_core_port_fini(&mlxsw_sp_port->core_port); unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */ - mlxsw_sp_port_dcb_fini(mlxsw_sp_port); - mlxsw_sp_port_kill_vid(mlxsw_sp_port->dev, 0, 1); + mlxsw_sp->ports[local_port] = NULL; mlxsw_sp_port_switchdev_fini(mlxsw_sp_port); + mlxsw_sp_port_pvid_vport_destroy(mlxsw_sp_port); + mlxsw_sp_port_dcb_fini(mlxsw_sp_port); mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT); mlxsw_sp_port_module_unmap(mlxsw_sp, mlxsw_sp_port->local_port); free_percpu(mlxsw_sp_port->pcpu_stats); @@ -2662,6 +2655,26 @@ static const struct mlxsw_rx_listener mlxsw_sp_rx_listener[] = { { .func = mlxsw_sp_rx_listener_func, .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_MTUERROR, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_TTLERROR, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_LBERROR, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, + .trap_id = MLXSW_TRAP_ID_OSPF, + }, + { + .func = mlxsw_sp_rx_listener_func, + .local_port = MLXSW_PORT_DONT_CARE, .trap_id = MLXSW_TRAP_ID_IP2ME, }, { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index f69aa37d1521..ab3feb81bd43 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -536,8 +536,6 @@ int mlxsw_sp_port_vid_to_fid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid); int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin, u16 vid_end, bool is_member, bool untagged); -int mlxsw_sp_port_add_vid(struct net_device *dev, __be16 __always_unused proto, - u16 vid); int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 fid, bool set); void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 074cdda7b6f3..237418a0e6e0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -330,7 +330,7 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = { MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, - MLXSW_SP_CPU_PORT_SB_CM, + MLXSW_SP_SB_CM(MLXSW_SP_BYTES_TO_CELLS(10000), 0, 0), MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, MLXSW_SP_CPU_PORT_SB_CM, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c index 01cfb7512827..b6ed7f7c531e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c @@ -341,6 +341,8 @@ static int mlxsw_sp_port_pfc_set(struct mlxsw_sp_port *mlxsw_sp_port, char pfcc_pl[MLXSW_REG_PFCC_LEN]; mlxsw_reg_pfcc_pack(pfcc_pl, mlxsw_sp_port->local_port); + mlxsw_reg_pfcc_pprx_set(pfcc_pl, mlxsw_sp_port->link.rx_pause); + mlxsw_reg_pfcc_pptx_set(pfcc_pl, mlxsw_sp_port->link.tx_pause); mlxsw_reg_pfcc_prio_pack(pfcc_pl, pfc->pfc_en); return mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(pfcc), @@ -351,17 +353,17 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + bool pause_en = mlxsw_sp_port_is_pause_en(mlxsw_sp_port); int err; - if ((mlxsw_sp_port->link.tx_pause || mlxsw_sp_port->link.rx_pause) && - pfc->pfc_en) { + if (pause_en && pfc->pfc_en) { netdev_err(dev, "PAUSE frames already enabled on port\n"); return -EINVAL; } err = __mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, mlxsw_sp_port->dcb.ets->prio_tc, - false, pfc); + pause_en, pfc); if (err) { netdev_err(dev, "Failed to configure port's headroom for PFC\n"); return err; @@ -380,7 +382,7 @@ static int mlxsw_sp_dcbnl_ieee_setpfc(struct net_device *dev, err_port_pfc_set: __mlxsw_sp_port_headroom_set(mlxsw_sp_port, dev->mtu, - mlxsw_sp_port->dcb.ets->prio_tc, false, + mlxsw_sp_port->dcb.ets->prio_tc, pause_en, mlxsw_sp_port->dcb.pfc); return err; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 81418d629231..90bb93b037ec 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -1651,9 +1651,10 @@ static void mlxsw_sp_router_fib4_add_info_destroy(void const *data) const struct mlxsw_sp_router_fib4_add_info *info = data; struct mlxsw_sp_fib_entry *fib_entry = info->fib_entry; struct mlxsw_sp *mlxsw_sp = info->mlxsw_sp; + struct mlxsw_sp_vr *vr = fib_entry->vr; mlxsw_sp_fib_entry_destroy(fib_entry); - mlxsw_sp_vr_put(mlxsw_sp, fib_entry->vr); + mlxsw_sp_vr_put(mlxsw_sp, vr); kfree(info); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index a1ad5e6bdfa8..d1b59cdfacc1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -450,6 +450,8 @@ void mlxsw_sp_fid_destroy(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *f) kfree(f); + mlxsw_sp_fid_map(mlxsw_sp, fid, false); + mlxsw_sp_fid_op(mlxsw_sp, fid, false); } @@ -997,13 +999,13 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev, } static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, - u16 vid_begin, u16 vid_end, bool init) + u16 vid_begin, u16 vid_end) { struct net_device *dev = mlxsw_sp_port->dev; u16 vid, pvid; int err; - if (!init && !mlxsw_sp_port->bridged) + if (!mlxsw_sp_port->bridged) return -EINVAL; err = __mlxsw_sp_port_vlans_set(mlxsw_sp_port, vid_begin, vid_end, @@ -1014,9 +1016,6 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, return err; } - if (init) - goto out; - pvid = mlxsw_sp_port->pvid; if (pvid >= vid_begin && pvid <= vid_end) { err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0); @@ -1028,7 +1027,6 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, mlxsw_sp_port_fid_leave(mlxsw_sp_port, vid_begin, vid_end); -out: /* Changing activity bits only if HW operation succeded */ for (vid = vid_begin; vid <= vid_end; vid++) clear_bit(vid, mlxsw_sp_port->active_vlans); @@ -1039,8 +1037,8 @@ out: static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, const struct switchdev_obj_port_vlan *vlan) { - return __mlxsw_sp_port_vlans_del(mlxsw_sp_port, - vlan->vid_begin, vlan->vid_end, false); + return __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vlan->vid_begin, + vlan->vid_end); } void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port) @@ -1048,7 +1046,7 @@ void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port) u16 vid; for_each_set_bit(vid, mlxsw_sp_port->active_vlans, VLAN_N_VID) - __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vid, vid, false); + __mlxsw_sp_port_vlans_del(mlxsw_sp_port, vid, vid); } static int @@ -1546,32 +1544,6 @@ void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_sp_fdb_fini(mlxsw_sp); } -int mlxsw_sp_port_vlan_init(struct mlxsw_sp_port *mlxsw_sp_port) -{ - struct net_device *dev = mlxsw_sp_port->dev; - int err; - - /* Allow only untagged packets to ingress and tag them internally - * with VID 1. - */ - mlxsw_sp_port->pvid = 1; - err = __mlxsw_sp_port_vlans_del(mlxsw_sp_port, 0, VLAN_N_VID - 1, - true); - if (err) { - netdev_err(dev, "Unable to init VLANs\n"); - return err; - } - - /* Add implicit VLAN interface in the device, so that untagged - * packets will be classified to the default vFID. - */ - err = mlxsw_sp_port_add_vid(dev, 0, 1); - if (err) - netdev_err(dev, "Failed to configure default vFID\n"); - - return err; -} - void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port) { mlxsw_sp_port->dev->switchdev_ops = &mlxsw_sp_port_switchdev_ops; diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 470d7696e9fe..ed8e30186400 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -56,6 +56,10 @@ enum { MLXSW_TRAP_ID_IGMP_V3_REPORT = 0x34, MLXSW_TRAP_ID_ARPBC = 0x50, MLXSW_TRAP_ID_ARPUC = 0x51, + MLXSW_TRAP_ID_MTUERROR = 0x52, + MLXSW_TRAP_ID_TTLERROR = 0x53, + MLXSW_TRAP_ID_LBERROR = 0x54, + MLXSW_TRAP_ID_OSPF = 0x55, MLXSW_TRAP_ID_IP2ME = 0x5F, MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70, MLXSW_TRAP_ID_HOST_MISS_IPV4 = 0x90, diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index d0dc28f93c0e..226cb08cc055 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -52,40 +52,94 @@ static bool qed_dcbx_app_ethtype(u32 app_info_bitmap) DCBX_APP_SF_ETHTYPE); } +static bool qed_dcbx_ieee_app_ethtype(u32 app_info_bitmap) +{ + u8 mfw_val = QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF_IEEE); + + /* Old MFW */ + if (mfw_val == DCBX_APP_SF_IEEE_RESERVED) + return qed_dcbx_app_ethtype(app_info_bitmap); + + return !!(mfw_val == DCBX_APP_SF_IEEE_ETHTYPE); +} + static bool qed_dcbx_app_port(u32 app_info_bitmap) { return !!(QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF) == DCBX_APP_SF_PORT); } -static bool qed_dcbx_default_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_ieee_app_port(u32 app_info_bitmap, u8 type) { - return !!(qed_dcbx_app_ethtype(app_info_bitmap) && - proto_id == QED_ETH_TYPE_DEFAULT); + u8 mfw_val = QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF_IEEE); + + /* Old MFW */ + if (mfw_val == DCBX_APP_SF_IEEE_RESERVED) + return qed_dcbx_app_port(app_info_bitmap); + + return !!(mfw_val == type || mfw_val == DCBX_APP_SF_IEEE_TCP_UDP_PORT); } -static bool qed_dcbx_iscsi_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_default_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_port(app_info_bitmap) && - proto_id == QED_TCP_PORT_ISCSI); + bool ethtype; + + if (ieee) + ethtype = qed_dcbx_ieee_app_ethtype(app_info_bitmap); + else + ethtype = qed_dcbx_app_ethtype(app_info_bitmap); + + return !!(ethtype && (proto_id == QED_ETH_TYPE_DEFAULT)); } -static bool qed_dcbx_fcoe_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_iscsi_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_ethtype(app_info_bitmap) && - proto_id == QED_ETH_TYPE_FCOE); + bool port; + + if (ieee) + port = qed_dcbx_ieee_app_port(app_info_bitmap, + DCBX_APP_SF_IEEE_TCP_PORT); + else + port = qed_dcbx_app_port(app_info_bitmap); + + return !!(port && (proto_id == QED_TCP_PORT_ISCSI)); } -static bool qed_dcbx_roce_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_fcoe_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_ethtype(app_info_bitmap) && - proto_id == QED_ETH_TYPE_ROCE); + bool ethtype; + + if (ieee) + ethtype = qed_dcbx_ieee_app_ethtype(app_info_bitmap); + else + ethtype = qed_dcbx_app_ethtype(app_info_bitmap); + + return !!(ethtype && (proto_id == QED_ETH_TYPE_FCOE)); } -static bool qed_dcbx_roce_v2_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_roce_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_port(app_info_bitmap) && - proto_id == QED_UDP_PORT_TYPE_ROCE_V2); + bool ethtype; + + if (ieee) + ethtype = qed_dcbx_ieee_app_ethtype(app_info_bitmap); + else + ethtype = qed_dcbx_app_ethtype(app_info_bitmap); + + return !!(ethtype && (proto_id == QED_ETH_TYPE_ROCE)); +} + +static bool qed_dcbx_roce_v2_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) +{ + bool port; + + if (ieee) + port = qed_dcbx_ieee_app_port(app_info_bitmap, + DCBX_APP_SF_IEEE_UDP_PORT); + else + port = qed_dcbx_app_port(app_info_bitmap); + + return !!(port && (proto_id == QED_UDP_PORT_TYPE_ROCE_V2)); } static void @@ -164,17 +218,17 @@ qed_dcbx_update_app_info(struct qed_dcbx_results *p_data, static bool qed_dcbx_get_app_protocol_type(struct qed_hwfn *p_hwfn, u32 app_prio_bitmap, - u16 id, enum dcbx_protocol_type *type) + u16 id, enum dcbx_protocol_type *type, bool ieee) { - if (qed_dcbx_fcoe_tlv(app_prio_bitmap, id)) { + if (qed_dcbx_fcoe_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_FCOE; - } else if (qed_dcbx_roce_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_roce_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ROCE; - } else if (qed_dcbx_iscsi_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_iscsi_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ISCSI; - } else if (qed_dcbx_default_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_default_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ETH; - } else if (qed_dcbx_roce_v2_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_roce_v2_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ROCE_V2; } else { *type = DCBX_MAX_PROTOCOL_TYPE; @@ -194,17 +248,18 @@ static int qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, struct qed_dcbx_results *p_data, struct dcbx_app_priority_entry *p_tbl, - u32 pri_tc_tbl, int count, bool dcbx_enabled) + u32 pri_tc_tbl, int count, u8 dcbx_version) { u8 tc, priority_map; enum dcbx_protocol_type type; + bool enable, ieee; u16 protocol_id; int priority; - bool enable; int i; DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Num APP entries = %d\n", count); + ieee = (dcbx_version == DCBX_CONFIG_VERSION_IEEE); /* Parse APP TLV */ for (i = 0; i < count; i++) { protocol_id = QED_MFW_GET_FIELD(p_tbl[i].entry, @@ -219,7 +274,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, tc = QED_DCBX_PRIO2TC(pri_tc_tbl, priority); if (qed_dcbx_get_app_protocol_type(p_hwfn, p_tbl[i].entry, - protocol_id, &type)) { + protocol_id, &type, ieee)) { /* ETH always have the enable bit reset, as it gets * vlan information per packet. For other protocols, * should be set according to the dcbx_enabled @@ -275,15 +330,12 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn) struct dcbx_ets_feature *p_ets; struct qed_hw_info *p_info; u32 pri_tc_tbl, flags; - bool dcbx_enabled; + u8 dcbx_version; int num_entries; int rc = 0; - /* If DCBx version is non zero, then negotiation was - * successfuly performed - */ flags = p_hwfn->p_dcbx_info->operational.flags; - dcbx_enabled = !!QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION); + dcbx_version = QED_MFW_GET_FIELD(flags, DCBX_CONFIG_VERSION); p_app = &p_hwfn->p_dcbx_info->operational.features.app; p_tbl = p_app->app_pri_tbl; @@ -295,13 +347,13 @@ static int qed_dcbx_process_mib_info(struct qed_hwfn *p_hwfn) num_entries = QED_MFW_GET_FIELD(p_app->flags, DCBX_APP_NUM_ENTRIES); rc = qed_dcbx_process_tlv(p_hwfn, &data, p_tbl, pri_tc_tbl, - num_entries, dcbx_enabled); + num_entries, dcbx_version); if (rc) return rc; p_info->num_tc = QED_MFW_GET_FIELD(p_ets->flags, DCBX_ETS_MAX_TCS); data.pf_id = p_hwfn->rel_pf_id; - data.dcbx_enabled = dcbx_enabled; + data.dcbx_enabled = !!dcbx_version; qed_dcbx_dp_protocol(p_hwfn, &data); @@ -400,7 +452,7 @@ static void qed_dcbx_get_app_data(struct qed_hwfn *p_hwfn, struct dcbx_app_priority_feature *p_app, struct dcbx_app_priority_entry *p_tbl, - struct qed_dcbx_params *p_params) + struct qed_dcbx_params *p_params, bool ieee) { struct qed_app_entry *entry; u8 pri_map; @@ -414,15 +466,46 @@ qed_dcbx_get_app_data(struct qed_hwfn *p_hwfn, DCBX_APP_NUM_ENTRIES); for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) { entry = &p_params->app_entry[i]; - entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry, - DCBX_APP_SF)); + if (ieee) { + u8 sf_ieee; + u32 val; + + sf_ieee = QED_MFW_GET_FIELD(p_tbl[i].entry, + DCBX_APP_SF_IEEE); + switch (sf_ieee) { + case DCBX_APP_SF_IEEE_RESERVED: + /* Old MFW */ + val = QED_MFW_GET_FIELD(p_tbl[i].entry, + DCBX_APP_SF); + entry->sf_ieee = val ? + QED_DCBX_SF_IEEE_TCP_UDP_PORT : + QED_DCBX_SF_IEEE_ETHTYPE; + break; + case DCBX_APP_SF_IEEE_ETHTYPE: + entry->sf_ieee = QED_DCBX_SF_IEEE_ETHTYPE; + break; + case DCBX_APP_SF_IEEE_TCP_PORT: + entry->sf_ieee = QED_DCBX_SF_IEEE_TCP_PORT; + break; + case DCBX_APP_SF_IEEE_UDP_PORT: + entry->sf_ieee = QED_DCBX_SF_IEEE_UDP_PORT; + break; + case DCBX_APP_SF_IEEE_TCP_UDP_PORT: + entry->sf_ieee = QED_DCBX_SF_IEEE_TCP_UDP_PORT; + break; + } + } else { + entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry, + DCBX_APP_SF)); + } + pri_map = QED_MFW_GET_FIELD(p_tbl[i].entry, DCBX_APP_PRI_MAP); entry->prio = ffs(pri_map) - 1; entry->proto_id = QED_MFW_GET_FIELD(p_tbl[i].entry, DCBX_APP_PROTOCOL_ID); qed_dcbx_get_app_protocol_type(p_hwfn, p_tbl[i].entry, entry->proto_id, - &entry->proto_type); + &entry->proto_type, ieee); } DP_VERBOSE(p_hwfn, QED_MSG_DCB, @@ -483,7 +566,7 @@ qed_dcbx_get_ets_data(struct qed_hwfn *p_hwfn, bw_map[1] = be32_to_cpu(p_ets->tc_bw_tbl[1]); tsa_map[0] = be32_to_cpu(p_ets->tc_tsa_tbl[0]); tsa_map[1] = be32_to_cpu(p_ets->tc_tsa_tbl[1]); - pri_map = be32_to_cpu(p_ets->pri_tc_tbl[0]); + pri_map = p_ets->pri_tc_tbl[0]; for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) { p_params->ets_tc_bw_tbl[i] = ((u8 *)bw_map)[i]; p_params->ets_tc_tsa_tbl[i] = ((u8 *)tsa_map)[i]; @@ -500,9 +583,9 @@ qed_dcbx_get_common_params(struct qed_hwfn *p_hwfn, struct dcbx_app_priority_feature *p_app, struct dcbx_app_priority_entry *p_tbl, struct dcbx_ets_feature *p_ets, - u32 pfc, struct qed_dcbx_params *p_params) + u32 pfc, struct qed_dcbx_params *p_params, bool ieee) { - qed_dcbx_get_app_data(p_hwfn, p_app, p_tbl, p_params); + qed_dcbx_get_app_data(p_hwfn, p_app, p_tbl, p_params, ieee); qed_dcbx_get_ets_data(p_hwfn, p_ets, p_params); qed_dcbx_get_pfc_data(p_hwfn, pfc, p_params); } @@ -516,7 +599,7 @@ qed_dcbx_get_local_params(struct qed_hwfn *p_hwfn, p_feat = &p_hwfn->p_dcbx_info->local_admin.features; qed_dcbx_get_common_params(p_hwfn, &p_feat->app, p_feat->app.app_pri_tbl, &p_feat->ets, - p_feat->pfc, ¶ms->local.params); + p_feat->pfc, ¶ms->local.params, false); params->local.valid = true; } @@ -529,7 +612,7 @@ qed_dcbx_get_remote_params(struct qed_hwfn *p_hwfn, p_feat = &p_hwfn->p_dcbx_info->remote.features; qed_dcbx_get_common_params(p_hwfn, &p_feat->app, p_feat->app.app_pri_tbl, &p_feat->ets, - p_feat->pfc, ¶ms->remote.params); + p_feat->pfc, ¶ms->remote.params, false); params->remote.valid = true; } @@ -574,7 +657,8 @@ qed_dcbx_get_operational_params(struct qed_hwfn *p_hwfn, qed_dcbx_get_common_params(p_hwfn, &p_feat->app, p_feat->app.app_pri_tbl, &p_feat->ets, - p_feat->pfc, ¶ms->operational.params); + p_feat->pfc, ¶ms->operational.params, + p_operational->ieee); qed_dcbx_get_priority_info(p_hwfn, &p_operational->app_prio, p_results); err = QED_MFW_GET_FIELD(p_feat->app.flags, DCBX_APP_ERROR); p_operational->err = err; @@ -944,7 +1028,6 @@ qed_dcbx_set_ets_data(struct qed_hwfn *p_hwfn, val = (((u32)p_params->ets_pri_tc_tbl[i]) << ((7 - i) * 4)); p_ets->pri_tc_tbl[0] |= val; } - p_ets->pri_tc_tbl[0] = cpu_to_be32(p_ets->pri_tc_tbl[0]); for (i = 0; i < 2; i++) { p_ets->tc_bw_tbl[i] = cpu_to_be32(p_ets->tc_bw_tbl[i]); p_ets->tc_tsa_tbl[i] = cpu_to_be32(p_ets->tc_tsa_tbl[i]); @@ -954,7 +1037,7 @@ qed_dcbx_set_ets_data(struct qed_hwfn *p_hwfn, static void qed_dcbx_set_app_data(struct qed_hwfn *p_hwfn, struct dcbx_app_priority_feature *p_app, - struct qed_dcbx_params *p_params) + struct qed_dcbx_params *p_params, bool ieee) { u32 *entry; int i; @@ -975,12 +1058,36 @@ qed_dcbx_set_app_data(struct qed_hwfn *p_hwfn, for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) { entry = &p_app->app_pri_tbl[i].entry; - *entry &= ~DCBX_APP_SF_MASK; - if (p_params->app_entry[i].ethtype) - *entry |= ((u32)DCBX_APP_SF_ETHTYPE << - DCBX_APP_SF_SHIFT); - else - *entry |= ((u32)DCBX_APP_SF_PORT << DCBX_APP_SF_SHIFT); + if (ieee) { + *entry &= ~DCBX_APP_SF_IEEE_MASK; + switch (p_params->app_entry[i].sf_ieee) { + case QED_DCBX_SF_IEEE_ETHTYPE: + *entry |= ((u32)DCBX_APP_SF_IEEE_ETHTYPE << + DCBX_APP_SF_IEEE_SHIFT); + break; + case QED_DCBX_SF_IEEE_TCP_PORT: + *entry |= ((u32)DCBX_APP_SF_IEEE_TCP_PORT << + DCBX_APP_SF_IEEE_SHIFT); + break; + case QED_DCBX_SF_IEEE_UDP_PORT: + *entry |= ((u32)DCBX_APP_SF_IEEE_UDP_PORT << + DCBX_APP_SF_IEEE_SHIFT); + break; + case QED_DCBX_SF_IEEE_TCP_UDP_PORT: + *entry |= ((u32)DCBX_APP_SF_IEEE_TCP_UDP_PORT << + DCBX_APP_SF_IEEE_SHIFT); + break; + } + } else { + *entry &= ~DCBX_APP_SF_MASK; + if (p_params->app_entry[i].ethtype) + *entry |= ((u32)DCBX_APP_SF_ETHTYPE << + DCBX_APP_SF_SHIFT); + else + *entry |= ((u32)DCBX_APP_SF_PORT << + DCBX_APP_SF_SHIFT); + } + *entry &= ~DCBX_APP_PROTOCOL_ID_MASK; *entry |= ((u32)p_params->app_entry[i].proto_id << DCBX_APP_PROTOCOL_ID_SHIFT); @@ -995,15 +1102,19 @@ qed_dcbx_set_local_params(struct qed_hwfn *p_hwfn, struct dcbx_local_params *local_admin, struct qed_dcbx_set *params) { + bool ieee = false; + local_admin->flags = 0; memcpy(&local_admin->features, &p_hwfn->p_dcbx_info->operational.features, sizeof(local_admin->features)); - if (params->enabled) + if (params->enabled) { local_admin->config = params->ver_num; - else + ieee = !!(params->ver_num & DCBX_CONFIG_VERSION_IEEE); + } else { local_admin->config = DCBX_CONFIG_VERSION_DISABLED; + } if (params->override_flags & QED_DCBX_OVERRIDE_PFC_CFG) qed_dcbx_set_pfc_data(p_hwfn, &local_admin->features.pfc, @@ -1015,7 +1126,7 @@ qed_dcbx_set_local_params(struct qed_hwfn *p_hwfn, if (params->override_flags & QED_DCBX_OVERRIDE_APP_CFG) qed_dcbx_set_app_data(p_hwfn, &local_admin->features.app, - ¶ms->config.params); + ¶ms->config.params, ieee); } int qed_dcbx_config_params(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, @@ -1596,8 +1707,10 @@ static int qed_dcbnl_setapp(struct qed_dev *cdev, if ((entry->ethtype == ethtype) && (entry->proto_id == idval)) break; /* First empty slot */ - if (!entry->proto_id) + if (!entry->proto_id) { + dcbx_set.config.params.num_app_entries++; break; + } } if (i == QED_DCBX_MAX_APP_PROTOCOL) { @@ -2117,8 +2230,10 @@ int qed_dcbnl_ieee_setapp(struct qed_dev *cdev, struct dcb_app *app) (entry->proto_id == app->protocol)) break; /* First empty slot */ - if (!entry->proto_id) + if (!entry->proto_id) { + dcbx_set.config.params.num_app_entries++; break; + } } if (i == QED_DCBX_MAX_APP_PROTOCOL) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 592784019994..6f9d3b831a2a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -6850,6 +6850,14 @@ struct dcbx_app_priority_entry { #define DCBX_APP_SF_SHIFT 8 #define DCBX_APP_SF_ETHTYPE 0 #define DCBX_APP_SF_PORT 1 +#define DCBX_APP_SF_IEEE_MASK 0x0000f000 +#define DCBX_APP_SF_IEEE_SHIFT 12 +#define DCBX_APP_SF_IEEE_RESERVED 0 +#define DCBX_APP_SF_IEEE_ETHTYPE 1 +#define DCBX_APP_SF_IEEE_TCP_PORT 2 +#define DCBX_APP_SF_IEEE_UDP_PORT 3 +#define DCBX_APP_SF_IEEE_TCP_UDP_PORT 4 + #define DCBX_APP_PROTOCOL_ID_MASK 0xffff0000 #define DCBX_APP_PROTOCOL_ID_SHIFT 16 }; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index fd973f4f16c7..49bad00a0f8f 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -37,8 +37,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 3 -#define _QLCNIC_LINUX_SUBVERSION 64 -#define QLCNIC_LINUX_VERSIONID "5.3.64" +#define _QLCNIC_LINUX_SUBVERSION 65 +#define QLCNIC_LINUX_VERSIONID "5.3.65" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 87c642d3b075..fedd7366713c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -102,7 +102,6 @@ #define QLCNIC_RESPONSE_DESC 0x05 #define QLCNIC_LRO_DESC 0x12 -#define QLCNIC_TX_POLL_BUDGET 128 #define QLCNIC_TCP_HDR_SIZE 20 #define QLCNIC_TCP_TS_OPTION_SIZE 12 #define QLCNIC_FETCH_RING_ID(handle) ((handle) >> 63) @@ -2008,7 +2007,6 @@ static int qlcnic_83xx_msix_tx_poll(struct napi_struct *napi, int budget) struct qlcnic_host_tx_ring *tx_ring; struct qlcnic_adapter *adapter; - budget = QLCNIC_TX_POLL_BUDGET; tx_ring = container_of(napi, struct qlcnic_host_tx_ring, napi); adapter = tx_ring->adapter; work_done = qlcnic_process_cmd_ring(adapter, tx_ring, budget); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h index 017d8c2c8285..24061b9b92e8 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h @@ -156,10 +156,8 @@ struct qlcnic_vf_info { spinlock_t vlan_list_lock; /* Lock for VLAN list */ }; -struct qlcnic_async_work_list { +struct qlcnic_async_cmd { struct list_head list; - struct work_struct work; - void *ptr; struct qlcnic_cmd_args *cmd; }; @@ -168,7 +166,10 @@ struct qlcnic_back_channel { struct workqueue_struct *bc_trans_wq; struct workqueue_struct *bc_async_wq; struct workqueue_struct *bc_flr_wq; - struct list_head async_list; + struct qlcnic_adapter *adapter; + struct list_head async_cmd_list; + struct work_struct vf_async_work; + spinlock_t queue_lock; /* async_cmd_list queue lock */ }; struct qlcnic_sriov { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 7327b729ba2e..d7107055ec60 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -29,6 +29,7 @@ #define QLC_83XX_VF_RESET_FAIL_THRESH 8 #define QLC_BC_CMD_MAX_RETRY_CNT 5 +static void qlcnic_sriov_handle_async_issue_cmd(struct work_struct *work); static void qlcnic_sriov_vf_free_mac_list(struct qlcnic_adapter *); static int qlcnic_sriov_alloc_bc_mbx_args(struct qlcnic_cmd_args *, u32); static void qlcnic_sriov_vf_poll_dev_state(struct work_struct *); @@ -177,7 +178,10 @@ int qlcnic_sriov_init(struct qlcnic_adapter *adapter, int num_vfs) } bc->bc_async_wq = wq; - INIT_LIST_HEAD(&bc->async_list); + INIT_LIST_HEAD(&bc->async_cmd_list); + INIT_WORK(&bc->vf_async_work, qlcnic_sriov_handle_async_issue_cmd); + spin_lock_init(&bc->queue_lock); + bc->adapter = adapter; for (i = 0; i < num_vfs; i++) { vf = &sriov->vf_info[i]; @@ -1517,17 +1521,21 @@ static void qlcnic_vf_add_mc_list(struct net_device *netdev, const u8 *mac, void qlcnic_sriov_cleanup_async_list(struct qlcnic_back_channel *bc) { - struct list_head *head = &bc->async_list; - struct qlcnic_async_work_list *entry; + struct list_head *head = &bc->async_cmd_list; + struct qlcnic_async_cmd *entry; flush_workqueue(bc->bc_async_wq); + cancel_work_sync(&bc->vf_async_work); + + spin_lock(&bc->queue_lock); while (!list_empty(head)) { - entry = list_entry(head->next, struct qlcnic_async_work_list, + entry = list_entry(head->next, struct qlcnic_async_cmd, list); - cancel_work_sync(&entry->work); list_del(&entry->list); + kfree(entry->cmd); kfree(entry); } + spin_unlock(&bc->queue_lock); } void qlcnic_sriov_vf_set_multi(struct net_device *netdev) @@ -1587,57 +1595,64 @@ void qlcnic_sriov_vf_set_multi(struct net_device *netdev) static void qlcnic_sriov_handle_async_issue_cmd(struct work_struct *work) { - struct qlcnic_async_work_list *entry; - struct qlcnic_adapter *adapter; + struct qlcnic_async_cmd *entry, *tmp; + struct qlcnic_back_channel *bc; struct qlcnic_cmd_args *cmd; + struct list_head *head; + LIST_HEAD(del_list); + + bc = container_of(work, struct qlcnic_back_channel, vf_async_work); + head = &bc->async_cmd_list; + + spin_lock(&bc->queue_lock); + list_splice_init(head, &del_list); + spin_unlock(&bc->queue_lock); + + list_for_each_entry_safe(entry, tmp, &del_list, list) { + list_del(&entry->list); + cmd = entry->cmd; + __qlcnic_sriov_issue_cmd(bc->adapter, cmd); + kfree(entry); + } + + if (!list_empty(head)) + queue_work(bc->bc_async_wq, &bc->vf_async_work); - entry = container_of(work, struct qlcnic_async_work_list, work); - adapter = entry->ptr; - cmd = entry->cmd; - __qlcnic_sriov_issue_cmd(adapter, cmd); return; } -static struct qlcnic_async_work_list * -qlcnic_sriov_get_free_node_async_work(struct qlcnic_back_channel *bc) +static struct qlcnic_async_cmd * +qlcnic_sriov_alloc_async_cmd(struct qlcnic_back_channel *bc, + struct qlcnic_cmd_args *cmd) { - struct list_head *node; - struct qlcnic_async_work_list *entry = NULL; - u8 empty = 0; + struct qlcnic_async_cmd *entry = NULL; - list_for_each(node, &bc->async_list) { - entry = list_entry(node, struct qlcnic_async_work_list, list); - if (!work_pending(&entry->work)) { - empty = 1; - break; - } - } + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) + return NULL; - if (!empty) { - entry = kzalloc(sizeof(struct qlcnic_async_work_list), - GFP_ATOMIC); - if (entry == NULL) - return NULL; - list_add_tail(&entry->list, &bc->async_list); - } + entry->cmd = cmd; + + spin_lock(&bc->queue_lock); + list_add_tail(&entry->list, &bc->async_cmd_list); + spin_unlock(&bc->queue_lock); return entry; } static void qlcnic_sriov_schedule_async_cmd(struct qlcnic_back_channel *bc, - work_func_t func, void *data, struct qlcnic_cmd_args *cmd) { - struct qlcnic_async_work_list *entry = NULL; + struct qlcnic_async_cmd *entry = NULL; - entry = qlcnic_sriov_get_free_node_async_work(bc); - if (!entry) + entry = qlcnic_sriov_alloc_async_cmd(bc, cmd); + if (!entry) { + qlcnic_free_mbx_args(cmd); + kfree(cmd); return; + } - entry->ptr = data; - entry->cmd = cmd; - INIT_WORK(&entry->work, func); - queue_work(bc->bc_async_wq, &entry->work); + queue_work(bc->bc_async_wq, &bc->vf_async_work); } static int qlcnic_sriov_async_issue_cmd(struct qlcnic_adapter *adapter, @@ -1649,8 +1664,8 @@ static int qlcnic_sriov_async_issue_cmd(struct qlcnic_adapter *adapter, if (adapter->need_fw_reset) return -EIO; - qlcnic_sriov_schedule_async_cmd(bc, qlcnic_sriov_handle_async_issue_cmd, - adapter, cmd); + qlcnic_sriov_schedule_async_cmd(bc, cmd); + return 0; } diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index c51f34693eae..f85d605e4560 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -734,6 +734,7 @@ static void cpsw_rx_handler(void *token, int len, int status) netif_receive_skb(skb); ndev->stats.rx_bytes += len; ndev->stats.rx_packets++; + kmemleak_not_leak(new_skb); } else { ndev->stats.rx_dropped++; new_skb = skb; @@ -1325,6 +1326,7 @@ static int cpsw_ndo_open(struct net_device *ndev) kfree_skb(skb); goto err_cleanup; } + kmemleak_not_leak(skb); } /* continue even if we didn't manage to submit all * receive descs diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c index 01a77145a0fa..8fd131207ee1 100644 --- a/drivers/net/ethernet/tundra/tsi108_eth.c +++ b/drivers/net/ethernet/tundra/tsi108_eth.c @@ -166,6 +166,7 @@ static struct platform_driver tsi_eth_driver = { static void tsi108_timed_checker(unsigned long dev_ptr); +#ifdef DEBUG static void dump_eth_one(struct net_device *dev) { struct tsi108_prv_data *data = netdev_priv(dev); @@ -190,6 +191,7 @@ static void dump_eth_one(struct net_device *dev) TSI_READ(TSI108_EC_RXESTAT), TSI_READ(TSI108_EC_RXERR), data->rxpending); } +#endif /* Synchronization is needed between the thread and up/down events. * Note that the PHY is accessed through the same registers for both diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 467fb8b4d083..591af71eae56 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -644,12 +644,6 @@ struct netvsc_reconfig { u32 event; }; -struct garp_wrk { - struct work_struct dwrk; - struct net_device *netdev; - struct netvsc_device *netvsc_dev; -}; - /* The context of the netvsc device */ struct net_device_context { /* point back to our device context */ @@ -667,7 +661,6 @@ struct net_device_context { struct work_struct work; u32 msg_enable; /* debug level */ - struct garp_wrk gwrk; struct netvsc_stats __percpu *tx_stats; struct netvsc_stats __percpu *rx_stats; @@ -678,6 +671,15 @@ struct net_device_context { /* the device is going away */ bool start_remove; + + /* State to manage the associated VF interface. */ + struct net_device *vf_netdev; + bool vf_inject; + atomic_t vf_use_cnt; + /* 1: allocated, serial number is valid. 0: not allocated */ + u32 vf_alloc; + /* Serial number of the VF to team with */ + u32 vf_serial; }; /* Per netvsc device */ @@ -733,15 +735,7 @@ struct netvsc_device { u32 max_pkt; /* max number of pkt in one send, e.g. 8 */ u32 pkt_align; /* alignment bytes, e.g. 8 */ - /* 1: allocated, serial number is valid. 0: not allocated */ - u32 vf_alloc; - /* Serial number of the VF to team with */ - u32 vf_serial; atomic_t open_cnt; - /* State to manage the associated VF interface. */ - bool vf_inject; - struct net_device *vf_netdev; - atomic_t vf_use_cnt; }; static inline struct netvsc_device * diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 20e09174ff62..410fb8e81376 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -77,13 +77,9 @@ static struct netvsc_device *alloc_net_device(void) init_waitqueue_head(&net_device->wait_drain); net_device->destroy = false; atomic_set(&net_device->open_cnt, 0); - atomic_set(&net_device->vf_use_cnt, 0); net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT; net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT; - net_device->vf_netdev = NULL; - net_device->vf_inject = false; - return net_device; } @@ -1106,16 +1102,16 @@ static void netvsc_send_table(struct hv_device *hdev, nvscdev->send_table[i] = tab[i]; } -static void netvsc_send_vf(struct netvsc_device *nvdev, +static void netvsc_send_vf(struct net_device_context *net_device_ctx, struct nvsp_message *nvmsg) { - nvdev->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; - nvdev->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; + net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; + net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; } static inline void netvsc_receive_inband(struct hv_device *hdev, - struct netvsc_device *nvdev, - struct nvsp_message *nvmsg) + struct net_device_context *net_device_ctx, + struct nvsp_message *nvmsg) { switch (nvmsg->hdr.msg_type) { case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE: @@ -1123,7 +1119,7 @@ static inline void netvsc_receive_inband(struct hv_device *hdev, break; case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION: - netvsc_send_vf(nvdev, nvmsg); + netvsc_send_vf(net_device_ctx, nvmsg); break; } } @@ -1136,6 +1132,7 @@ static void netvsc_process_raw_pkt(struct hv_device *device, struct vmpacket_descriptor *desc) { struct nvsp_message *nvmsg; + struct net_device_context *net_device_ctx = netdev_priv(ndev); nvmsg = (struct nvsp_message *)((unsigned long) desc + (desc->offset8 << 3)); @@ -1150,7 +1147,7 @@ static void netvsc_process_raw_pkt(struct hv_device *device, break; case VM_PKT_DATA_INBAND: - netvsc_receive_inband(device, net_device, nvmsg); + netvsc_receive_inband(device, net_device_ctx, nvmsg); break; default: diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 41bd952cc28d..3ba29fc80d05 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -658,20 +658,19 @@ int netvsc_recv_callback(struct hv_device *device_obj, struct sk_buff *skb; struct sk_buff *vf_skb; struct netvsc_stats *rx_stats; - struct netvsc_device *netvsc_dev = net_device_ctx->nvdev; u32 bytes_recvd = packet->total_data_buflen; int ret = 0; if (!net || net->reg_state != NETREG_REGISTERED) return NVSP_STAT_FAIL; - if (READ_ONCE(netvsc_dev->vf_inject)) { - atomic_inc(&netvsc_dev->vf_use_cnt); - if (!READ_ONCE(netvsc_dev->vf_inject)) { + if (READ_ONCE(net_device_ctx->vf_inject)) { + atomic_inc(&net_device_ctx->vf_use_cnt); + if (!READ_ONCE(net_device_ctx->vf_inject)) { /* * We raced; just move on. */ - atomic_dec(&netvsc_dev->vf_use_cnt); + atomic_dec(&net_device_ctx->vf_use_cnt); goto vf_injection_done; } @@ -683,17 +682,19 @@ int netvsc_recv_callback(struct hv_device *device_obj, * the host). Deliver these via the VF interface * in the guest. */ - vf_skb = netvsc_alloc_recv_skb(netvsc_dev->vf_netdev, packet, - csum_info, *data, vlan_tci); + vf_skb = netvsc_alloc_recv_skb(net_device_ctx->vf_netdev, + packet, csum_info, *data, + vlan_tci); if (vf_skb != NULL) { - ++netvsc_dev->vf_netdev->stats.rx_packets; - netvsc_dev->vf_netdev->stats.rx_bytes += bytes_recvd; + ++net_device_ctx->vf_netdev->stats.rx_packets; + net_device_ctx->vf_netdev->stats.rx_bytes += + bytes_recvd; netif_receive_skb(vf_skb); } else { ++net->stats.rx_dropped; ret = NVSP_STAT_FAIL; } - atomic_dec(&netvsc_dev->vf_use_cnt); + atomic_dec(&net_device_ctx->vf_use_cnt); return ret; } @@ -1150,17 +1151,6 @@ static void netvsc_free_netdev(struct net_device *netdev) free_netdev(netdev); } -static void netvsc_notify_peers(struct work_struct *wrk) -{ - struct garp_wrk *gwrk; - - gwrk = container_of(wrk, struct garp_wrk, dwrk); - - netdev_notify_peers(gwrk->netdev); - - atomic_dec(&gwrk->netvsc_dev->vf_use_cnt); -} - static struct net_device *get_netvsc_net_device(char *mac) { struct net_device *dev, *found = NULL; @@ -1203,7 +1193,7 @@ static int netvsc_register_vf(struct net_device *vf_netdev) net_device_ctx = netdev_priv(ndev); netvsc_dev = net_device_ctx->nvdev; - if (netvsc_dev == NULL) + if (!netvsc_dev || net_device_ctx->vf_netdev) return NOTIFY_DONE; netdev_info(ndev, "VF registering: %s\n", vf_netdev->name); @@ -1211,10 +1201,23 @@ static int netvsc_register_vf(struct net_device *vf_netdev) * Take a reference on the module. */ try_module_get(THIS_MODULE); - netvsc_dev->vf_netdev = vf_netdev; + net_device_ctx->vf_netdev = vf_netdev; return NOTIFY_OK; } +static void netvsc_inject_enable(struct net_device_context *net_device_ctx) +{ + net_device_ctx->vf_inject = true; +} + +static void netvsc_inject_disable(struct net_device_context *net_device_ctx) +{ + net_device_ctx->vf_inject = false; + + /* Wait for currently active users to drain out. */ + while (atomic_read(&net_device_ctx->vf_use_cnt) != 0) + udelay(50); +} static int netvsc_vf_up(struct net_device *vf_netdev) { @@ -1233,11 +1236,11 @@ static int netvsc_vf_up(struct net_device *vf_netdev) net_device_ctx = netdev_priv(ndev); netvsc_dev = net_device_ctx->nvdev; - if ((netvsc_dev == NULL) || (netvsc_dev->vf_netdev == NULL)) + if (!netvsc_dev || !net_device_ctx->vf_netdev) return NOTIFY_DONE; netdev_info(ndev, "VF up: %s\n", vf_netdev->name); - netvsc_dev->vf_inject = true; + netvsc_inject_enable(net_device_ctx); /* * Open the device before switching data path. @@ -1252,15 +1255,8 @@ static int netvsc_vf_up(struct net_device *vf_netdev) netif_carrier_off(ndev); - /* - * Now notify peers. We are scheduling work to - * notify peers; take a reference to prevent - * the VF interface from vanishing. - */ - atomic_inc(&netvsc_dev->vf_use_cnt); - net_device_ctx->gwrk.netdev = vf_netdev; - net_device_ctx->gwrk.netvsc_dev = netvsc_dev; - schedule_work(&net_device_ctx->gwrk.dwrk); + /* Now notify peers through VF device. */ + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, vf_netdev); return NOTIFY_OK; } @@ -1283,29 +1279,18 @@ static int netvsc_vf_down(struct net_device *vf_netdev) net_device_ctx = netdev_priv(ndev); netvsc_dev = net_device_ctx->nvdev; - if ((netvsc_dev == NULL) || (netvsc_dev->vf_netdev == NULL)) + if (!netvsc_dev || !net_device_ctx->vf_netdev) return NOTIFY_DONE; netdev_info(ndev, "VF down: %s\n", vf_netdev->name); - netvsc_dev->vf_inject = false; - /* - * Wait for currently active users to - * drain out. - */ - - while (atomic_read(&netvsc_dev->vf_use_cnt) != 0) - udelay(50); + netvsc_inject_disable(net_device_ctx); netvsc_switch_datapath(ndev, false); netdev_info(ndev, "Data path switched from VF: %s\n", vf_netdev->name); rndis_filter_close(netvsc_dev); netif_carrier_on(ndev); - /* - * Notify peers. - */ - atomic_inc(&netvsc_dev->vf_use_cnt); - net_device_ctx->gwrk.netdev = ndev; - net_device_ctx->gwrk.netvsc_dev = netvsc_dev; - schedule_work(&net_device_ctx->gwrk.dwrk); + + /* Now notify peers through netvsc device. */ + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, ndev); return NOTIFY_OK; } @@ -1327,11 +1312,11 @@ static int netvsc_unregister_vf(struct net_device *vf_netdev) net_device_ctx = netdev_priv(ndev); netvsc_dev = net_device_ctx->nvdev; - if (netvsc_dev == NULL) + if (!netvsc_dev || !net_device_ctx->vf_netdev) return NOTIFY_DONE; netdev_info(ndev, "VF unregistering: %s\n", vf_netdev->name); - - netvsc_dev->vf_netdev = NULL; + netvsc_inject_disable(net_device_ctx); + net_device_ctx->vf_netdev = NULL; module_put(THIS_MODULE); return NOTIFY_OK; } @@ -1377,11 +1362,14 @@ static int netvsc_probe(struct hv_device *dev, INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change); INIT_WORK(&net_device_ctx->work, do_set_multicast); - INIT_WORK(&net_device_ctx->gwrk.dwrk, netvsc_notify_peers); spin_lock_init(&net_device_ctx->lock); INIT_LIST_HEAD(&net_device_ctx->reconfig_events); + atomic_set(&net_device_ctx->vf_use_cnt, 0); + net_device_ctx->vf_netdev = NULL; + net_device_ctx->vf_inject = false; + net->netdev_ops = &device_ops; net->hw_features = NETVSC_HW_FEATURES; @@ -1494,8 +1482,13 @@ static int netvsc_netdev_event(struct notifier_block *this, { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr); - /* Avoid Vlan, Bonding dev with same MAC registering as VF */ - if (event_dev->priv_flags & (IFF_802_1Q_VLAN | IFF_BONDING)) + /* Avoid Vlan dev with same MAC registering as VF */ + if (event_dev->priv_flags & IFF_802_1Q_VLAN) + return NOTIFY_DONE; + + /* Avoid Bonding master dev with same MAC registering as VF */ + if (event_dev->priv_flags & IFF_BONDING && + event_dev->flags & IFF_MASTER) return NOTIFY_DONE; switch (event) { diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index d13e6e15d7b5..351e701eb043 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -270,6 +270,7 @@ struct macsec_dev { struct pcpu_secy_stats __percpu *stats; struct list_head secys; struct gro_cells gro_cells; + unsigned int nest_level; }; /** @@ -2699,6 +2700,8 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, #define MACSEC_FEATURES \ (NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST) +static struct lock_class_key macsec_netdev_addr_lock_key; + static int macsec_dev_init(struct net_device *dev) { struct macsec_dev *macsec = macsec_priv(dev); @@ -2910,6 +2913,13 @@ static int macsec_get_iflink(const struct net_device *dev) return macsec_priv(dev)->real_dev->ifindex; } + +static int macsec_get_nest_level(struct net_device *dev) +{ + return macsec_priv(dev)->nest_level; +} + + static const struct net_device_ops macsec_netdev_ops = { .ndo_init = macsec_dev_init, .ndo_uninit = macsec_dev_uninit, @@ -2923,6 +2933,7 @@ static const struct net_device_ops macsec_netdev_ops = { .ndo_start_xmit = macsec_start_xmit, .ndo_get_stats64 = macsec_get_stats64, .ndo_get_iflink = macsec_get_iflink, + .ndo_get_lock_subclass = macsec_get_nest_level, }; static const struct device_type macsec_type = { @@ -3047,22 +3058,31 @@ static void macsec_del_dev(struct macsec_dev *macsec) } } +static void macsec_common_dellink(struct net_device *dev, struct list_head *head) +{ + struct macsec_dev *macsec = macsec_priv(dev); + struct net_device *real_dev = macsec->real_dev; + + unregister_netdevice_queue(dev, head); + list_del_rcu(&macsec->secys); + macsec_del_dev(macsec); + netdev_upper_dev_unlink(real_dev, dev); + + macsec_generation++; +} + static void macsec_dellink(struct net_device *dev, struct list_head *head) { struct macsec_dev *macsec = macsec_priv(dev); struct net_device *real_dev = macsec->real_dev; struct macsec_rxh_data *rxd = macsec_data_rtnl(real_dev); - macsec_generation++; + macsec_common_dellink(dev, head); - unregister_netdevice_queue(dev, head); - list_del_rcu(&macsec->secys); if (list_empty(&rxd->secys)) { netdev_rx_handler_unregister(real_dev); kfree(rxd); } - - macsec_del_dev(macsec); } static int register_macsec_dev(struct net_device *real_dev, @@ -3181,6 +3201,16 @@ static int macsec_newlink(struct net *net, struct net_device *dev, dev_hold(real_dev); + macsec->nest_level = dev_get_nest_level(real_dev) + 1; + netdev_lockdep_set_classes(dev); + lockdep_set_class_and_subclass(&dev->addr_list_lock, + &macsec_netdev_addr_lock_key, + macsec_get_nest_level(dev)); + + err = netdev_upper_dev_link(real_dev, dev); + if (err < 0) + goto unregister; + /* need to be already registered so that ->init has run and * the MAC addr is set */ @@ -3193,12 +3223,12 @@ static int macsec_newlink(struct net *net, struct net_device *dev, if (rx_handler && sci_exists(real_dev, sci)) { err = -EBUSY; - goto unregister; + goto unlink; } err = macsec_add_dev(dev, sci, icv_len); if (err) - goto unregister; + goto unlink; if (data) macsec_changelink_common(dev, data); @@ -3213,6 +3243,8 @@ static int macsec_newlink(struct net *net, struct net_device *dev, del_dev: macsec_del_dev(macsec); +unlink: + netdev_upper_dev_unlink(real_dev, dev); unregister: unregister_netdevice(dev); return err; @@ -3382,8 +3414,12 @@ static int macsec_notify(struct notifier_block *this, unsigned long event, rxd = macsec_data_rtnl(real_dev); list_for_each_entry_safe(m, n, &rxd->secys, secys) { - macsec_dellink(m->secy.netdev, &head); + macsec_common_dellink(m->secy.netdev, &head); } + + netdev_rx_handler_unregister(real_dev); + kfree(rxd); + unregister_netdevice_many(&head); break; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index cd9b53834bf6..3234fcdea317 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1315,7 +1315,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; - vlan->nest_level = dev_get_nest_level(lowerdev, netif_is_macvlan) + 1; + vlan->nest_level = dev_get_nest_level(lowerdev) + 1; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index a38c0dac514b..070e3290aa6e 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -275,7 +275,6 @@ static void macvtap_put_queue(struct macvtap_queue *q) rtnl_unlock(); synchronize_rcu(); - skb_array_cleanup(&q->skb_array); sock_put(&q->sk); } @@ -533,10 +532,8 @@ static void macvtap_sock_write_space(struct sock *sk) static void macvtap_sock_destruct(struct sock *sk) { struct macvtap_queue *q = container_of(sk, struct macvtap_queue, sk); - struct sk_buff *skb; - while ((skb = skb_array_consume(&q->skb_array)) != NULL) - kfree_skb(skb); + skb_array_cleanup(&q->skb_array); } static int macvtap_open(struct inode *inode, struct file *file) diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 1882d9828c99..053e87905b94 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -677,17 +677,28 @@ static void kszphy_get_stats(struct phy_device *phydev, data[i] = kszphy_get_stat(phydev, i); } -static int kszphy_resume(struct phy_device *phydev) +static int kszphy_suspend(struct phy_device *phydev) { - int value; + /* Disable PHY Interrupts */ + if (phy_interrupt_is_valid(phydev)) { + phydev->interrupts = PHY_INTERRUPT_DISABLED; + if (phydev->drv->config_intr) + phydev->drv->config_intr(phydev); + } - mutex_lock(&phydev->lock); + return genphy_suspend(phydev); +} - value = phy_read(phydev, MII_BMCR); - phy_write(phydev, MII_BMCR, value & ~BMCR_PDOWN); +static int kszphy_resume(struct phy_device *phydev) +{ + genphy_resume(phydev); - kszphy_config_intr(phydev); - mutex_unlock(&phydev->lock); + /* Enable PHY Interrupts */ + if (phy_interrupt_is_valid(phydev)) { + phydev->interrupts = PHY_INTERRUPT_ENABLED; + if (phydev->drv->config_intr) + phydev->drv->config_intr(phydev); + } return 0; } @@ -900,7 +911,7 @@ static struct phy_driver ksphy_driver[] = { .get_sset_count = kszphy_get_sset_count, .get_strings = kszphy_get_strings, .get_stats = kszphy_get_stats, - .suspend = genphy_suspend, + .suspend = kszphy_suspend, .resume = kszphy_resume, }, { .phy_id = PHY_ID_KSZ8061, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index da4e3d6632f6..c0dda6fc0921 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -1811,7 +1811,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, fl4.flowi4_mark = skb->mark; fl4.flowi4_proto = IPPROTO_UDP; fl4.daddr = daddr; - fl4.saddr = vxlan->cfg.saddr.sin.sin_addr.s_addr; + fl4.saddr = *saddr; rt = ip_route_output_key(vxlan->net, &fl4); if (!IS_ERR(rt)) { @@ -1847,7 +1847,7 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = oif; fl6.daddr = *daddr; - fl6.saddr = vxlan->cfg.saddr.sin6.sin6_addr; + fl6.saddr = *saddr; fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = IPPROTO_UDP; @@ -1920,7 +1920,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct rtable *rt = NULL; const struct iphdr *old_iph; union vxlan_addr *dst; - union vxlan_addr remote_ip; + union vxlan_addr remote_ip, local_ip; + union vxlan_addr *src; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; __be16 src_port = 0, dst_port; @@ -1938,6 +1939,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = rdst->remote_vni; dst = &rdst->remote_ip; + src = &vxlan->cfg.saddr; dst_cache = &rdst->dst_cache; } else { if (!info) { @@ -1948,11 +1950,15 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = vxlan_tun_id_to_vni(info->key.tun_id); remote_ip.sa.sa_family = ip_tunnel_info_af(info); - if (remote_ip.sa.sa_family == AF_INET) + if (remote_ip.sa.sa_family == AF_INET) { remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst; - else + local_ip.sin.sin_addr.s_addr = info->key.u.ipv4.src; + } else { remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst; + local_ip.sin6.sin6_addr = info->key.u.ipv6.src; + } dst = &remote_ip; + src = &local_ip; dst_cache = &info->dst_cache; } @@ -1992,15 +1998,14 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } if (dst->sa.sa_family == AF_INET) { - __be32 saddr; - if (!vxlan->vn4_sock) goto drop; sk = vxlan->vn4_sock->sock->sk; rt = vxlan_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, tos, - dst->sin.sin_addr.s_addr, &saddr, + dst->sin.sin_addr.s_addr, + &src->sin.sin_addr.s_addr, dst_cache, info); if (IS_ERR(rt)) { netdev_dbg(dev, "no route to %pI4\n", @@ -2017,7 +2022,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } /* Bypass encapsulation if the destination is local */ - if (rt->rt_flags & RTCF_LOCAL && + if (!info && rt->rt_flags & RTCF_LOCAL && !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) { struct vxlan_dev *dst_vxlan; @@ -2043,13 +2048,12 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (err < 0) goto xmit_tx_error; - udp_tunnel_xmit_skb(rt, sk, skb, saddr, + udp_tunnel_xmit_skb(rt, sk, skb, src->sin.sin_addr.s_addr, dst->sin.sin_addr.s_addr, tos, ttl, df, src_port, dst_port, xnet, !udp_sum); #if IS_ENABLED(CONFIG_IPV6) } else { struct dst_entry *ndst; - struct in6_addr saddr; u32 rt6i_flags; if (!vxlan->vn6_sock) @@ -2058,7 +2062,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ndst = vxlan6_get_route(vxlan, skb, rdst ? rdst->remote_ifindex : 0, tos, - label, &dst->sin6.sin6_addr, &saddr, + label, &dst->sin6.sin6_addr, + &src->sin6.sin6_addr, dst_cache, info); if (IS_ERR(ndst)) { netdev_dbg(dev, "no route to %pI6\n", @@ -2077,7 +2082,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, /* Bypass encapsulation if the destination is local */ rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags; - if (rt6i_flags & RTF_LOCAL && + if (!info && rt6i_flags & RTF_LOCAL && !(rt6i_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) { struct vxlan_dev *dst_vxlan; @@ -2104,7 +2109,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, return; } udp_tunnel6_xmit_skb(ndst, sk, skb, dev, - &saddr, &dst->sin6.sin6_addr, tos, ttl, + &src->sin6.sin6_addr, + &dst->sin6.sin6_addr, tos, ttl, label, src_port, dst_port, !udp_sum); #endif } diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 1d689169da76..9e1f2d9c9865 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -5700,10 +5700,11 @@ out: mutex_unlock(&wl->mutex); } -static u32 wlcore_op_get_expected_throughput(struct ieee80211_sta *sta) +static u32 wlcore_op_get_expected_throughput(struct ieee80211_hw *hw, + struct ieee80211_sta *sta) { struct wl1271_station *wl_sta = (struct wl1271_station *)sta->drv_priv; - struct wl1271 *wl = wl_sta->wl; + struct wl1271 *wl = hw->priv; u8 hlid = wl_sta->hlid; /* return in units of Kbps */ diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c index 88e91666f145..368795aad5c9 100644 --- a/drivers/nvdimm/btt.c +++ b/drivers/nvdimm/btt.c @@ -1269,6 +1269,7 @@ static int btt_blk_init(struct btt *btt) } } set_capacity(btt->btt_disk, btt->nlba * btt->sector_size >> 9); + btt->nd_btt->size = btt->nlba * (u64)btt->sector_size; revalidate_disk(btt->btt_disk); return 0; diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c index 3fa7919f94a8..97dd2925ed6e 100644 --- a/drivers/nvdimm/btt_devs.c +++ b/drivers/nvdimm/btt_devs.c @@ -140,10 +140,30 @@ static ssize_t namespace_store(struct device *dev, } static DEVICE_ATTR_RW(namespace); +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_btt *nd_btt = to_nd_btt(dev); + ssize_t rc; + + device_lock(dev); + if (dev->driver) + rc = sprintf(buf, "%llu\n", nd_btt->size); + else { + /* no size to convey if the btt instance is disabled */ + rc = -ENXIO; + } + device_unlock(dev); + + return rc; +} +static DEVICE_ATTR_RO(size); + static struct attribute *nd_btt_attributes[] = { &dev_attr_sector_size.attr, &dev_attr_namespace.attr, &dev_attr_uuid.attr, + &dev_attr_size.attr, NULL, }; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 40476399d227..8024a0ef86d3 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -143,6 +143,7 @@ struct nd_btt { struct nd_namespace_common *ndns; struct btt *btt; unsigned long lbasize; + u64 size; u8 *uuid; int id; }; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7ff2e820bbf4..2feacc70bf61 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -81,10 +81,12 @@ EXPORT_SYMBOL_GPL(nvme_cancel_request); bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, enum nvme_ctrl_state new_state) { - enum nvme_ctrl_state old_state = ctrl->state; + enum nvme_ctrl_state old_state; bool changed = false; spin_lock_irq(&ctrl->lock); + + old_state = ctrl->state; switch (new_state) { case NVME_CTRL_LIVE: switch (old_state) { @@ -140,11 +142,12 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, default: break; } - spin_unlock_irq(&ctrl->lock); if (changed) ctrl->state = new_state; + spin_unlock_irq(&ctrl->lock); + return changed; } EXPORT_SYMBOL_GPL(nvme_change_ctrl_state); @@ -608,7 +611,7 @@ int nvme_get_features(struct nvme_ctrl *dev, unsigned fid, unsigned nsid, ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, NVME_QID_ANY, 0, 0); - if (ret >= 0) + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } @@ -628,7 +631,7 @@ int nvme_set_features(struct nvme_ctrl *dev, unsigned fid, unsigned dword11, ret = __nvme_submit_sync_cmd(dev->admin_q, &c, &cqe, NULL, 0, 0, NVME_QID_ANY, 0, 0); - if (ret >= 0) + if (ret >= 0 && result) *result = le32_to_cpu(cqe.result); return ret; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index d7c33f9361aa..8dcf5a960951 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1543,15 +1543,10 @@ static void nvme_disable_io_queues(struct nvme_dev *dev) reinit_completion(&dev->ioq_wait); retry: timeout = ADMIN_TIMEOUT; - for (; i > 0; i--) { - struct nvme_queue *nvmeq = dev->queues[i]; - - if (!pass) - nvme_suspend_queue(nvmeq); - if (nvme_delete_queue(nvmeq, opcode)) + for (; i > 0; i--, sent++) + if (nvme_delete_queue(dev->queues[i], opcode)) break; - ++sent; - } + while (sent--) { timeout = wait_for_completion_io_timeout(&dev->ioq_wait, timeout); if (timeout == 0) @@ -1693,11 +1688,12 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) nvme_stop_queues(&dev->ctrl); csts = readl(dev->bar + NVME_REG_CSTS); } + + for (i = dev->queue_count - 1; i > 0; i--) + nvme_suspend_queue(dev->queues[i]); + if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) { - for (i = dev->queue_count - 1; i >= 0; i--) { - struct nvme_queue *nvmeq = dev->queues[i]; - nvme_suspend_queue(nvmeq); - } + nvme_suspend_queue(dev->queues[0]); } else { nvme_disable_io_queues(dev); nvme_disable_admin_queue(dev, shutdown); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 3e3ce2b0424e..8d2875b4c56d 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -12,13 +12,11 @@ * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/delay.h> #include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/string.h> -#include <linux/jiffies.h> #include <linux/atomic.h> #include <linux/blk-mq.h> #include <linux/types.h> @@ -26,7 +24,6 @@ #include <linux/mutex.h> #include <linux/scatterlist.h> #include <linux/nvme.h> -#include <linux/t10-pi.h> #include <asm/unaligned.h> #include <rdma/ib_verbs.h> @@ -169,7 +166,6 @@ MODULE_PARM_DESC(register_always, static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event); static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc); -static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl); /* XXX: really should move to a generic header sooner or later.. */ static inline void put_unaligned_le24(u32 val, u8 *p) @@ -687,11 +683,6 @@ static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl) list_del(&ctrl->list); mutex_unlock(&nvme_rdma_ctrl_mutex); - if (ctrl->ctrl.tagset) { - blk_cleanup_queue(ctrl->ctrl.connect_q); - blk_mq_free_tag_set(&ctrl->tag_set); - nvme_rdma_dev_put(ctrl->device); - } kfree(ctrl->queues); nvmf_free_options(nctrl->opts); free_ctrl: @@ -748,8 +739,11 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work) changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); WARN_ON_ONCE(!changed); - if (ctrl->queue_count > 1) + if (ctrl->queue_count > 1) { nvme_start_queues(&ctrl->ctrl); + nvme_queue_scan(&ctrl->ctrl); + nvme_queue_async_events(&ctrl->ctrl); + } dev_info(ctrl->ctrl.device, "Successfully reconnected\n"); @@ -1269,7 +1263,7 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue) { struct nvme_rdma_ctrl *ctrl = queue->ctrl; struct rdma_conn_param param = { }; - struct nvme_rdma_cm_req priv; + struct nvme_rdma_cm_req priv = { }; int ret; param.qp_num = queue->qp->qp_num; @@ -1318,37 +1312,39 @@ out_destroy_queue_ib: * that caught the event. Since we hold the callout until the controller * deletion is completed, we'll deadlock if the controller deletion will * call rdma_destroy_id on this queue's cm_id. Thus, we claim ownership - * of destroying this queue before-hand, destroy the queue resources - * after the controller deletion completed with the exception of destroying - * the cm_id implicitely by returning a non-zero rc to the callout. + * of destroying this queue before-hand, destroy the queue resources, + * then queue the controller deletion which won't destroy this queue and + * we destroy the cm_id implicitely by returning a non-zero rc to the callout. */ static int nvme_rdma_device_unplug(struct nvme_rdma_queue *queue) { struct nvme_rdma_ctrl *ctrl = queue->ctrl; - int ret, ctrl_deleted = 0; + int ret; - /* First disable the queue so ctrl delete won't free it */ - if (!test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) - goto out; + /* Own the controller deletion */ + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_DELETING)) + return 0; - /* delete the controller */ - ret = __nvme_rdma_del_ctrl(ctrl); - if (!ret) { - dev_warn(ctrl->ctrl.device, - "Got rdma device removal event, deleting ctrl\n"); - flush_work(&ctrl->delete_work); + dev_warn(ctrl->ctrl.device, + "Got rdma device removal event, deleting ctrl\n"); - /* Return non-zero so the cm_id will destroy implicitly */ - ctrl_deleted = 1; + /* Get rid of reconnect work if its running */ + cancel_delayed_work_sync(&ctrl->reconnect_work); + /* Disable the queue so ctrl delete won't free it */ + if (test_and_clear_bit(NVME_RDMA_Q_CONNECTED, &queue->flags)) { /* Free this queue ourselves */ - rdma_disconnect(queue->cm_id); - ib_drain_qp(queue->qp); + nvme_rdma_stop_queue(queue); nvme_rdma_destroy_queue_ib(queue); + + /* Return non-zero so the cm_id will destroy implicitly */ + ret = 1; } -out: - return ctrl_deleted; + /* Queue controller deletion */ + queue_work(nvme_rdma_wq, &ctrl->delete_work); + flush_work(&ctrl->delete_work); + return ret; } static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id, @@ -1648,7 +1644,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_rdma_free_io_queues(ctrl); } - if (ctrl->ctrl.state == NVME_CTRL_LIVE) + if (test_bit(NVME_RDMA_Q_CONNECTED, &ctrl->queues[0].flags)) nvme_shutdown_ctrl(&ctrl->ctrl); blk_mq_stop_hw_queues(ctrl->ctrl.admin_q); @@ -1657,15 +1653,27 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl) nvme_rdma_destroy_admin_queue(ctrl); } +static void __nvme_rdma_remove_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown) +{ + nvme_uninit_ctrl(&ctrl->ctrl); + if (shutdown) + nvme_rdma_shutdown_ctrl(ctrl); + + if (ctrl->ctrl.tagset) { + blk_cleanup_queue(ctrl->ctrl.connect_q); + blk_mq_free_tag_set(&ctrl->tag_set); + nvme_rdma_dev_put(ctrl->device); + } + + nvme_put_ctrl(&ctrl->ctrl); +} + static void nvme_rdma_del_ctrl_work(struct work_struct *work) { struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, delete_work); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_rdma_shutdown_ctrl(ctrl); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); + __nvme_rdma_remove_ctrl(ctrl, true); } static int __nvme_rdma_del_ctrl(struct nvme_rdma_ctrl *ctrl) @@ -1698,9 +1706,7 @@ static void nvme_rdma_remove_ctrl_work(struct work_struct *work) struct nvme_rdma_ctrl *ctrl = container_of(work, struct nvme_rdma_ctrl, delete_work); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_uninit_ctrl(&ctrl->ctrl); - nvme_put_ctrl(&ctrl->ctrl); + __nvme_rdma_remove_ctrl(ctrl, false); } static void nvme_rdma_reset_ctrl_work(struct work_struct *work) @@ -1739,6 +1745,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work) if (ctrl->queue_count > 1) { nvme_start_queues(&ctrl->ctrl); nvme_queue_scan(&ctrl->ctrl); + nvme_queue_async_events(&ctrl->ctrl); } return; diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 2fac17a5ad53..47c564b5a289 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -13,7 +13,6 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> -#include <linux/random.h> #include <generated/utsrelease.h> #include "nvmet.h" @@ -83,7 +82,6 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) { struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvme_id_ctrl *id; - u64 serial; u16 status = 0; id = kzalloc(sizeof(*id), GFP_KERNEL); @@ -96,10 +94,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->vid = 0; id->ssvid = 0; - /* generate a random serial number as our controllers are ephemeral: */ - get_random_bytes(&serial, sizeof(serial)); memset(id->sn, ' ', sizeof(id->sn)); - snprintf(id->sn, sizeof(id->sn), "%llx", serial); + snprintf(id->sn, sizeof(id->sn), "%llx", ctrl->serial); memset(id->mn, ' ', sizeof(id->mn)); strncpy((char *)id->mn, "Linux", sizeof(id->mn)); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 8a891ca53367..6559d5afa7bf 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -13,6 +13,7 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> +#include <linux/random.h> #include "nvmet.h" static struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX]; @@ -728,6 +729,9 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, memcpy(ctrl->subsysnqn, subsysnqn, NVMF_NQN_SIZE); memcpy(ctrl->hostnqn, hostnqn, NVMF_NQN_SIZE); + /* generate a random serial number as our controllers are ephemeral: */ + get_random_bytes(&ctrl->serial, sizeof(ctrl->serial)); + kref_init(&ctrl->ref); ctrl->subsys = subsys; diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 94e782987cc9..7affd40a6b33 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -414,9 +414,8 @@ static void nvme_loop_del_ctrl_work(struct work_struct *work) struct nvme_loop_ctrl *ctrl = container_of(work, struct nvme_loop_ctrl, delete_work); - nvme_remove_namespaces(&ctrl->ctrl); - nvme_loop_shutdown_ctrl(ctrl); nvme_uninit_ctrl(&ctrl->ctrl); + nvme_loop_shutdown_ctrl(ctrl); nvme_put_ctrl(&ctrl->ctrl); } @@ -501,7 +500,6 @@ out_free_queues: nvme_loop_destroy_admin_queue(ctrl); out_disable: dev_warn(ctrl->ctrl.device, "Removing after reset failure\n"); - nvme_remove_namespaces(&ctrl->ctrl); nvme_uninit_ctrl(&ctrl->ctrl); nvme_put_ctrl(&ctrl->ctrl); } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 57dd6d834c28..76b6eedccaf9 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -113,6 +113,7 @@ struct nvmet_ctrl { struct mutex lock; u64 cap; + u64 serial; u32 cc; u32 csts; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index e06d504bdf0c..b4d648536c3e 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -77,6 +77,7 @@ enum nvmet_rdma_queue_state { NVMET_RDMA_Q_CONNECTING, NVMET_RDMA_Q_LIVE, NVMET_RDMA_Q_DISCONNECTING, + NVMET_RDMA_IN_DEVICE_REMOVAL, }; struct nvmet_rdma_queue { @@ -615,15 +616,10 @@ static u16 nvmet_rdma_map_sgl_keyed(struct nvmet_rdma_rsp *rsp, if (!len) return 0; - /* use the already allocated data buffer if possible */ - if (len <= NVMET_RDMA_INLINE_DATA_SIZE && rsp->queue->host_qid) { - nvmet_rdma_use_inline_sg(rsp, len, 0); - } else { - status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt, - len); - if (status) - return status; - } + status = nvmet_rdma_alloc_sgl(&rsp->req.sg, &rsp->req.sg_cnt, + len); + if (status) + return status; ret = rdma_rw_ctx_init(&rsp->rw, cm_id->qp, cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, 0, addr, key, @@ -984,7 +980,10 @@ static void nvmet_rdma_release_queue_work(struct work_struct *w) struct nvmet_rdma_device *dev = queue->dev; nvmet_rdma_free_queue(queue); - rdma_destroy_id(cm_id); + + if (queue->state != NVMET_RDMA_IN_DEVICE_REMOVAL) + rdma_destroy_id(cm_id); + kref_put(&dev->ref, nvmet_rdma_free_dev); } @@ -1233,8 +1232,9 @@ static void __nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue) switch (queue->state) { case NVMET_RDMA_Q_CONNECTING: case NVMET_RDMA_Q_LIVE: - disconnect = true; queue->state = NVMET_RDMA_Q_DISCONNECTING; + case NVMET_RDMA_IN_DEVICE_REMOVAL: + disconnect = true; break; case NVMET_RDMA_Q_DISCONNECTING: break; @@ -1272,6 +1272,62 @@ static void nvmet_rdma_queue_connect_fail(struct rdma_cm_id *cm_id, schedule_work(&queue->release_work); } +/** + * nvme_rdma_device_removal() - Handle RDMA device removal + * @queue: nvmet rdma queue (cm id qp_context) + * @addr: nvmet address (cm_id context) + * + * DEVICE_REMOVAL event notifies us that the RDMA device is about + * to unplug so we should take care of destroying our RDMA resources. + * This event will be generated for each allocated cm_id. + * + * Note that this event can be generated on a normal queue cm_id + * and/or a device bound listener cm_id (where in this case + * queue will be null). + * + * we claim ownership on destroying the cm_id. For queues we move + * the queue state to NVMET_RDMA_IN_DEVICE_REMOVAL and for port + * we nullify the priv to prevent double cm_id destruction and destroying + * the cm_id implicitely by returning a non-zero rc to the callout. + */ +static int nvmet_rdma_device_removal(struct rdma_cm_id *cm_id, + struct nvmet_rdma_queue *queue) +{ + unsigned long flags; + + if (!queue) { + struct nvmet_port *port = cm_id->context; + + /* + * This is a listener cm_id. Make sure that + * future remove_port won't invoke a double + * cm_id destroy. use atomic xchg to make sure + * we don't compete with remove_port. + */ + if (xchg(&port->priv, NULL) != cm_id) + return 0; + } else { + /* + * This is a queue cm_id. Make sure that + * release queue will not destroy the cm_id + * and schedule all ctrl queues removal (only + * if the queue is not disconnecting already). + */ + spin_lock_irqsave(&queue->state_lock, flags); + if (queue->state != NVMET_RDMA_Q_DISCONNECTING) + queue->state = NVMET_RDMA_IN_DEVICE_REMOVAL; + spin_unlock_irqrestore(&queue->state_lock, flags); + nvmet_rdma_queue_disconnect(queue); + flush_scheduled_work(); + } + + /* + * We need to return 1 so that the core will destroy + * it's own ID. What a great API design.. + */ + return 1; +} + static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event) { @@ -1294,20 +1350,11 @@ static int nvmet_rdma_cm_handler(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ADDR_CHANGE: case RDMA_CM_EVENT_DISCONNECTED: - case RDMA_CM_EVENT_DEVICE_REMOVAL: case RDMA_CM_EVENT_TIMEWAIT_EXIT: - /* - * We can get the device removal callback even for a - * CM ID that we aren't actually using. In that case - * the context pointer is NULL, so we shouldn't try - * to disconnect a non-existing queue. But we also - * need to return 1 so that the core will destroy - * it's own ID. What a great API design.. - */ - if (queue) - nvmet_rdma_queue_disconnect(queue); - else - ret = 1; + nvmet_rdma_queue_disconnect(queue); + break; + case RDMA_CM_EVENT_DEVICE_REMOVAL: + ret = nvmet_rdma_device_removal(cm_id, queue); break; case RDMA_CM_EVENT_REJECTED: case RDMA_CM_EVENT_UNREACHABLE: @@ -1396,9 +1443,10 @@ out_destroy_id: static void nvmet_rdma_remove_port(struct nvmet_port *port) { - struct rdma_cm_id *cm_id = port->priv; + struct rdma_cm_id *cm_id = xchg(&port->priv, NULL); - rdma_destroy_id(cm_id); + if (cm_id) + rdma_destroy_id(cm_id); } static struct nvmet_fabrics_ops nvmet_rdma_ops = { diff --git a/drivers/of/base.c b/drivers/of/base.c index 7792266db259..3ce69536a7b3 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -1631,8 +1631,7 @@ static int __of_parse_phandle_with_args(const struct device_node *np, */ err: - if (it.node) - of_node_put(it.node); + of_node_put(it.node); return rc; } @@ -2343,20 +2342,13 @@ struct device_node *of_graph_get_endpoint_by_regs( const struct device_node *parent, int port_reg, int reg) { struct of_endpoint endpoint; - struct device_node *node, *prev_node = NULL; - - while (1) { - node = of_graph_get_next_endpoint(parent, prev_node); - of_node_put(prev_node); - if (!node) - break; + struct device_node *node = NULL; + for_each_endpoint_of_node(parent, node) { of_graph_parse_endpoint(node, &endpoint); if (((port_reg == -1) || (endpoint.port == port_reg)) && ((reg == -1) || (endpoint.id == reg))) return node; - - prev_node = node; } return NULL; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 55f1b8391149..085c6389afd1 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -517,7 +517,7 @@ static void *__unflatten_device_tree(const void *blob, pr_warning("End of tree marker overwritten: %08x\n", be32_to_cpup(mem + size)); - if (detached) { + if (detached && mynodes) { of_node_set_flag(*mynodes, OF_DETACHED); pr_debug("unflattened tree is detached\n"); } diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 89a71c6074fc..a2e68f740eda 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -544,12 +544,15 @@ void __init of_irq_init(const struct of_device_id *matches) list_del(&desc->list); + of_node_set_flag(desc->dev, OF_POPULATED); + pr_debug("of_irq_init: init %s (%p), parent %p\n", desc->dev->full_name, desc->dev, desc->interrupt_parent); ret = desc->irq_init_cb(desc->dev, desc->interrupt_parent); if (ret) { + of_node_clear_flag(desc->dev, OF_POPULATED); kfree(desc); continue; } @@ -559,8 +562,6 @@ void __init of_irq_init(const struct of_device_id *matches) * its children can get processed in a subsequent pass. */ list_add_tail(&desc->list, &intc_parent_list); - - of_node_set_flag(desc->dev, OF_POPULATED); } /* Get the next pending parent that might have children */ diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 8aa197691074..f39ccd5aa701 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -497,6 +497,7 @@ int of_platform_default_populate(struct device_node *root, } EXPORT_SYMBOL_GPL(of_platform_default_populate); +#ifndef CONFIG_PPC static int __init of_platform_default_populate_init(void) { struct device_node *node; @@ -521,6 +522,7 @@ static int __init of_platform_default_populate_init(void) return 0; } arch_initcall_sync(of_platform_default_populate_init); +#endif static int of_platform_device_destroy(struct device *dev, void *data) { diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index a02981efdad5..98f12223c734 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1069,7 +1069,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, nvec = maxvec; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1105,7 +1105,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, **/ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) { - return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY); + return __pci_enable_msi_range(dev, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msi_range); @@ -1120,7 +1120,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, return -ERANGE; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1160,8 +1160,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) { - return __pci_enable_msix_range(dev, entries, minvec, maxvec, - PCI_IRQ_NOAFFINITY); + return __pci_enable_msix_range(dev, entries, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msix_range); @@ -1187,22 +1186,25 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, { int vecs = -ENOSPC; - if (!(flags & PCI_IRQ_NOMSIX)) { + if (flags & PCI_IRQ_MSIX) { vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } - if (!(flags & PCI_IRQ_NOMSI)) { + if (flags & PCI_IRQ_MSI) { vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } /* use legacy irq if allowed */ - if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1) + if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) { + pci_intx(dev, 1); return 1; + } + return vecs; } EXPORT_SYMBOL(pci_alloc_irq_vectors); @@ -1411,6 +1413,8 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) pci_msi_domain_update_chip_ops(info); + info->flags |= MSI_FLAG_ACTIVATE_EARLY; + domain = msi_create_irq_domain(fwnode, info, parent); if (!domain) return NULL; diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c index 6ccb994bdfcb..c494613c1909 100644 --- a/drivers/perf/arm_pmu.c +++ b/drivers/perf/arm_pmu.c @@ -688,7 +688,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler) return 0; } -static DEFINE_MUTEX(arm_pmu_mutex); +static DEFINE_SPINLOCK(arm_pmu_lock); static LIST_HEAD(arm_pmu_list); /* @@ -701,7 +701,7 @@ static int arm_perf_starting_cpu(unsigned int cpu) { struct arm_pmu *pmu; - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_for_each_entry(pmu, &arm_pmu_list, entry) { if (!cpumask_test_cpu(cpu, &pmu->supported_cpus)) @@ -709,7 +709,7 @@ static int arm_perf_starting_cpu(unsigned int cpu) if (pmu->reset) pmu->reset(pmu); } - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); return 0; } @@ -821,9 +821,9 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu) if (!cpu_hw_events) return -ENOMEM; - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_add_tail(&cpu_pmu->entry, &arm_pmu_list); - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); err = cpu_pm_pmu_register(cpu_pmu); if (err) @@ -859,9 +859,9 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu) return 0; out_unregister: - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_del(&cpu_pmu->entry); - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); free_percpu(cpu_hw_events); return err; } @@ -869,9 +869,9 @@ out_unregister: static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu) { cpu_pm_pmu_unregister(cpu_pmu); - mutex_lock(&arm_pmu_mutex); + spin_lock(&arm_pmu_lock); list_del(&cpu_pmu->entry); - mutex_unlock(&arm_pmu_mutex); + spin_unlock(&arm_pmu_lock); free_percpu(cpu_pmu->hw_events); } @@ -967,11 +967,12 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu) /* If we didn't manage to parse anything, try the interrupt affinity */ if (cpumask_weight(&pmu->supported_cpus) == 0) { - if (!using_spi) { + int irq = platform_get_irq(pdev, 0); + + if (irq_is_percpu(irq)) { /* If using PPIs, check the affinity of the partition */ - int ret, irq; + int ret; - irq = platform_get_irq(pdev, 0); ret = irq_get_percpu_devid_partition(irq, &pmu->supported_cpus); if (ret) { kfree(irqs); diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c index eb4990ff26ca..7fb765642ee7 100644 --- a/drivers/pinctrl/intel/pinctrl-merrifield.c +++ b/drivers/pinctrl/intel/pinctrl-merrifield.c @@ -11,6 +11,7 @@ #include <linux/bitops.h> #include <linux/err.h> +#include <linux/io.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/pinctrl/pinconf.h> diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index 11623c6b0cb3..44e69c963f5d 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -727,13 +727,7 @@ static int meson_pinctrl_probe(struct platform_device *pdev) return PTR_ERR(pc->pcdev); } - ret = meson_gpiolib_register(pc); - if (ret) { - pinctrl_unregister(pc->pcdev); - return ret; - } - - return 0; + return meson_gpiolib_register(pc); } static struct platform_driver meson_pinctrl_driver = { diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 634b4d30eefb..b3e772390ab6 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -43,17 +43,6 @@ static int amd_gpio_direction_input(struct gpio_chip *gc, unsigned offset) spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + offset * 4); - /* - * Suppose BIOS or Bootloader sets specific debounce for the - * GPIO. if not, set debounce to be 2.75ms and remove glitch. - */ - if ((pin_reg & DB_TMR_OUT_MASK) == 0) { - pin_reg |= 0xf; - pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); - pin_reg |= DB_TYPE_REMOVE_GLITCH << DB_CNTRL_OFF; - pin_reg &= ~BIT(DB_TMR_LARGE_OFF); - } - pin_reg &= ~BIT(OUTPUT_ENABLE_OFF); writel(pin_reg, gpio_dev->base + offset * 4); spin_unlock_irqrestore(&gpio_dev->lock, flags); @@ -326,15 +315,6 @@ static void amd_gpio_irq_enable(struct irq_data *d) spin_lock_irqsave(&gpio_dev->lock, flags); pin_reg = readl(gpio_dev->base + (d->hwirq)*4); - /* - Suppose BIOS or Bootloader sets specific debounce for the - GPIO. if not, set debounce to be 2.75ms. - */ - if ((pin_reg & DB_TMR_OUT_MASK) == 0) { - pin_reg |= 0xf; - pin_reg |= BIT(DB_TMR_OUT_UNIT_OFF); - pin_reg &= ~BIT(DB_TMR_LARGE_OFF); - } pin_reg |= BIT(INTERRUPT_ENABLE_OFF); pin_reg |= BIT(INTERRUPT_MASK_OFF); writel(pin_reg, gpio_dev->base + (d->hwirq)*4); diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c index c6d410ef8de0..7bad200bd67c 100644 --- a/drivers/pinctrl/pinctrl-pistachio.c +++ b/drivers/pinctrl/pinctrl-pistachio.c @@ -1432,7 +1432,6 @@ static int pistachio_pinctrl_probe(struct platform_device *pdev) { struct pistachio_pinctrl *pctl; struct resource *res; - int ret; pctl = devm_kzalloc(&pdev->dev, sizeof(*pctl), GFP_KERNEL); if (!pctl) @@ -1464,13 +1463,7 @@ static int pistachio_pinctrl_probe(struct platform_device *pdev) return PTR_ERR(pctl->pctldev); } - ret = pistachio_gpio_register(pctl); - if (ret < 0) { - pinctrl_unregister(pctl->pctldev); - return ret; - } - - return 0; + return pistachio_gpio_register(pctl); } static struct platform_driver pistachio_pinctrl_driver = { diff --git a/drivers/platform/x86/dell-wmi.c b/drivers/platform/x86/dell-wmi.c index d2bc092defd7..da2fe18162e1 100644 --- a/drivers/platform/x86/dell-wmi.c +++ b/drivers/platform/x86/dell-wmi.c @@ -110,8 +110,8 @@ static const struct key_entry dell_wmi_keymap_type_0000[] __initconst = { /* BIOS error detected */ { KE_IGNORE, 0xe00d, { KEY_RESERVED } }, - /* Unknown, defined in ACPI DSDT */ - /* { KE_IGNORE, 0xe00e, { KEY_RESERVED } }, */ + /* Battery was removed or inserted */ + { KE_IGNORE, 0xe00e, { KEY_RESERVED } }, /* Wifi Catcher */ { KE_KEY, 0xe011, { KEY_PROG2 } }, diff --git a/drivers/power/max17042_battery.c b/drivers/power/max17042_battery.c index 9c65f134d447..da7a75f82489 100644 --- a/drivers/power/max17042_battery.c +++ b/drivers/power/max17042_battery.c @@ -457,13 +457,16 @@ static inline void max17042_write_model_data(struct max17042_chip *chip, } static inline void max17042_read_model_data(struct max17042_chip *chip, - u8 addr, u32 *data, int size) + u8 addr, u16 *data, int size) { struct regmap *map = chip->regmap; int i; + u32 tmp; - for (i = 0; i < size; i++) - regmap_read(map, addr + i, &data[i]); + for (i = 0; i < size; i++) { + regmap_read(map, addr + i, &tmp); + data[i] = (u16)tmp; + } } static inline int max17042_model_data_compare(struct max17042_chip *chip, @@ -486,7 +489,7 @@ static int max17042_init_model(struct max17042_chip *chip) { int ret; int table_size = ARRAY_SIZE(chip->pdata->config_data->cell_char_tbl); - u32 *temp_data; + u16 *temp_data; temp_data = kcalloc(table_size, sizeof(*temp_data), GFP_KERNEL); if (!temp_data) @@ -501,7 +504,7 @@ static int max17042_init_model(struct max17042_chip *chip) ret = max17042_model_data_compare( chip, chip->pdata->config_data->cell_char_tbl, - (u16 *)temp_data, + temp_data, table_size); max10742_lock_model(chip); @@ -514,7 +517,7 @@ static int max17042_verify_model_lock(struct max17042_chip *chip) { int i; int table_size = ARRAY_SIZE(chip->pdata->config_data->cell_char_tbl); - u32 *temp_data; + u16 *temp_data; int ret = 0; temp_data = kcalloc(table_size, sizeof(*temp_data), GFP_KERNEL); diff --git a/drivers/power/reset/Kconfig b/drivers/power/reset/Kconfig index 3bfac539334b..c74c3f67b8da 100644 --- a/drivers/power/reset/Kconfig +++ b/drivers/power/reset/Kconfig @@ -200,8 +200,8 @@ config REBOOT_MODE config SYSCON_REBOOT_MODE tristate "Generic SYSCON regmap reboot mode driver" depends on OF + depends on MFD_SYSCON select REBOOT_MODE - select MFD_SYSCON help Say y here will enable reboot mode driver. This will get reboot mode arguments and store it in SYSCON mapped diff --git a/drivers/power/reset/hisi-reboot.c b/drivers/power/reset/hisi-reboot.c index 9ab7f562a83b..f69387e12c1e 100644 --- a/drivers/power/reset/hisi-reboot.c +++ b/drivers/power/reset/hisi-reboot.c @@ -53,13 +53,16 @@ static int hisi_reboot_probe(struct platform_device *pdev) if (of_property_read_u32(np, "reboot-offset", &reboot_offset) < 0) { pr_err("failed to find reboot-offset property\n"); + iounmap(base); return -EINVAL; } err = register_restart_handler(&hisi_restart_nb); - if (err) + if (err) { dev_err(&pdev->dev, "cannot register restart handler (err=%d)\n", err); + iounmap(base); + } return err; } diff --git a/drivers/power/tps65217_charger.c b/drivers/power/tps65217_charger.c index 73dfae41def8..4c56e54af6ac 100644 --- a/drivers/power/tps65217_charger.c +++ b/drivers/power/tps65217_charger.c @@ -206,6 +206,7 @@ static int tps65217_charger_probe(struct platform_device *pdev) if (!charger) return -ENOMEM; + platform_set_drvdata(pdev, charger); charger->tps = tps; charger->dev = &pdev->dev; diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c index cecc15a880de..3fa17ac8df54 100644 --- a/drivers/rapidio/rio_cm.c +++ b/drivers/rapidio/rio_cm.c @@ -1080,8 +1080,8 @@ static int riocm_send_ack(struct rio_channel *ch) static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id, long timeout) { - struct rio_channel *ch = NULL; - struct rio_channel *new_ch = NULL; + struct rio_channel *ch; + struct rio_channel *new_ch; struct conn_req *req; struct cm_peer *peer; int found = 0; @@ -1155,6 +1155,7 @@ static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id, spin_unlock_bh(&ch->lock); riocm_put_channel(ch); + ch = NULL; kfree(req); down_read(&rdev_sem); @@ -1172,7 +1173,7 @@ static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id, if (!found) { /* If peer device object not found, simply ignore the request */ err = -ENODEV; - goto err_nodev; + goto err_put_new_ch; } new_ch->rdev = peer->rdev; @@ -1184,15 +1185,16 @@ static struct rio_channel *riocm_ch_accept(u16 ch_id, u16 *new_ch_id, *new_ch_id = new_ch->id; return new_ch; + +err_put_new_ch: + spin_lock_bh(&idr_lock); + idr_remove(&ch_idr, new_ch->id); + spin_unlock_bh(&idr_lock); + riocm_put_channel(new_ch); + err_put: - riocm_put_channel(ch); -err_nodev: - if (new_ch) { - spin_lock_bh(&idr_lock); - idr_remove(&ch_idr, new_ch->id); - spin_unlock_bh(&idr_lock); - riocm_put_channel(new_ch); - } + if (ch) + riocm_put_channel(ch); *new_ch_id = 0; return ERR_PTR(err); } diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 8973d34ce5ba..fb1b56a71475 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -1643,9 +1643,18 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, u8 *sense = NULL; int expires; + cqr = (struct dasd_ccw_req *) intparm; if (IS_ERR(irb)) { switch (PTR_ERR(irb)) { case -EIO: + if (cqr && cqr->status == DASD_CQR_CLEAR_PENDING) { + device = (struct dasd_device *) cqr->startdev; + cqr->status = DASD_CQR_CLEARED; + dasd_device_clear_timer(device); + wake_up(&dasd_flush_wq); + dasd_schedule_device_bh(device); + return; + } break; case -ETIMEDOUT: DBF_EVENT_DEVID(DBF_WARNING, cdev, "%s: " @@ -1661,7 +1670,6 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm, } now = get_tod_clock(); - cqr = (struct dasd_ccw_req *) intparm; /* check for conditions that should be handled immediately */ if (!cqr || !(scsw_dstat(&irb->scsw) == (DEV_STAT_CHN_END | DEV_STAT_DEV_END) && diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index fd2eff440098..98bbec44bcd0 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -5078,6 +5078,8 @@ static int dasd_eckd_read_message_buffer(struct dasd_device *device, return PTR_ERR(cqr); } + cqr->lpm = lpum; +retry: cqr->startdev = device; cqr->memdev = device; cqr->block = NULL; @@ -5122,6 +5124,14 @@ static int dasd_eckd_read_message_buffer(struct dasd_device *device, (prssdp + 1); memcpy(messages, message_buf, sizeof(struct dasd_rssd_messages)); + } else if (cqr->lpm) { + /* + * on z/VM we might not be able to do I/O on the requested path + * but instead we get the required information on any path + * so retry with open path mask + */ + cqr->lpm = 0; + goto retry; } else DBF_EVENT_DEVID(DBF_WARNING, device->cdev, "Reading messages failed with rc=%d\n" diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c index 7ada078ffdd0..6a58bc8f46e2 100644 --- a/drivers/s390/cio/device.c +++ b/drivers/s390/cio/device.c @@ -762,7 +762,6 @@ static int io_subchannel_initialize_dev(struct subchannel *sch, priv->state = DEV_STATE_NOT_OPER; priv->dev_id.devno = sch->schib.pmcw.dev; priv->dev_id.ssid = sch->schid.ssid; - priv->schid = sch->schid; INIT_WORK(&priv->todo_work, ccw_device_todo); INIT_LIST_HEAD(&priv->cmb_list); @@ -1000,7 +999,6 @@ static int ccw_device_move_to_sch(struct ccw_device *cdev, put_device(&old_sch->dev); /* Initialize new subchannel. */ spin_lock_irq(sch->lock); - cdev->private->schid = sch->schid; cdev->ccwlock = sch->lock; if (!sch_is_pseudo_sch(sch)) sch_set_cdev(sch, cdev); diff --git a/drivers/s390/cio/device_status.c b/drivers/s390/cio/device_status.c index 15b56a15db15..9bc3512374c9 100644 --- a/drivers/s390/cio/device_status.c +++ b/drivers/s390/cio/device_status.c @@ -26,6 +26,7 @@ static void ccw_device_msg_control_check(struct ccw_device *cdev, struct irb *irb) { + struct subchannel *sch = to_subchannel(cdev->dev.parent); char dbf_text[15]; if (!scsw_is_valid_cstat(&irb->scsw) || @@ -36,10 +37,10 @@ ccw_device_msg_control_check(struct ccw_device *cdev, struct irb *irb) "received" " ... device %04x on subchannel 0.%x.%04x, dev_stat " ": %02X sch_stat : %02X\n", - cdev->private->dev_id.devno, cdev->private->schid.ssid, - cdev->private->schid.sch_no, + cdev->private->dev_id.devno, sch->schid.ssid, + sch->schid.sch_no, scsw_dstat(&irb->scsw), scsw_cstat(&irb->scsw)); - sprintf(dbf_text, "chk%x", cdev->private->schid.sch_no); + sprintf(dbf_text, "chk%x", sch->schid.sch_no); CIO_TRACE_EVENT(0, dbf_text); CIO_HEX_EVENT(0, irb, sizeof(struct irb)); } diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h index 8975060af96c..220f49145b2f 100644 --- a/drivers/s390/cio/io_sch.h +++ b/drivers/s390/cio/io_sch.h @@ -120,7 +120,6 @@ struct ccw_device_private { int state; /* device state */ atomic_t onoff; struct ccw_dev_id dev_id; /* device id */ - struct subchannel_id schid; /* subchannel number */ struct ccw_request req; /* internal I/O request */ int iretry; u8 pgid_valid_mask; /* mask of valid PGIDs */ diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c index 4bb5262f7aee..71bf9bded485 100644 --- a/drivers/s390/cio/qdio_main.c +++ b/drivers/s390/cio/qdio_main.c @@ -686,6 +686,15 @@ static void qdio_kick_handler(struct qdio_q *q) q->qdio_error = 0; } +static inline int qdio_tasklet_schedule(struct qdio_q *q) +{ + if (likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE)) { + tasklet_schedule(&q->tasklet); + return 0; + } + return -EPERM; +} + static void __qdio_inbound_processing(struct qdio_q *q) { qperf_inc(q, tasklet_inbound); @@ -698,10 +707,8 @@ static void __qdio_inbound_processing(struct qdio_q *q) if (!qdio_inbound_q_done(q)) { /* means poll time is not yet over */ qperf_inc(q, tasklet_inbound_resched); - if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) { - tasklet_schedule(&q->tasklet); + if (!qdio_tasklet_schedule(q)) return; - } } qdio_stop_polling(q); @@ -711,8 +718,7 @@ static void __qdio_inbound_processing(struct qdio_q *q) */ if (!qdio_inbound_q_done(q)) { qperf_inc(q, tasklet_inbound_resched2); - if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } } @@ -869,16 +875,15 @@ static void __qdio_outbound_processing(struct qdio_q *q) * is noticed and outbound_handler is called after some time. */ if (qdio_outbound_q_done(q)) - del_timer(&q->u.out.timer); + del_timer_sync(&q->u.out.timer); else - if (!timer_pending(&q->u.out.timer)) + if (!timer_pending(&q->u.out.timer) && + likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE)) mod_timer(&q->u.out.timer, jiffies + 10 * HZ); return; sched: - if (unlikely(q->irq_ptr->state == QDIO_IRQ_STATE_STOPPED)) - return; - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } /* outbound tasklet */ @@ -892,9 +897,7 @@ void qdio_outbound_timer(unsigned long data) { struct qdio_q *q = (struct qdio_q *)data; - if (unlikely(q->irq_ptr->state == QDIO_IRQ_STATE_STOPPED)) - return; - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } static inline void qdio_check_outbound_after_thinint(struct qdio_q *q) @@ -907,7 +910,7 @@ static inline void qdio_check_outbound_after_thinint(struct qdio_q *q) for_each_output_queue(q->irq_ptr, out, i) if (!qdio_outbound_q_done(out)) - tasklet_schedule(&out->tasklet); + qdio_tasklet_schedule(out); } static void __tiqdio_inbound_processing(struct qdio_q *q) @@ -929,10 +932,8 @@ static void __tiqdio_inbound_processing(struct qdio_q *q) if (!qdio_inbound_q_done(q)) { qperf_inc(q, tasklet_inbound_resched); - if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) { - tasklet_schedule(&q->tasklet); + if (!qdio_tasklet_schedule(q)) return; - } } qdio_stop_polling(q); @@ -942,8 +943,7 @@ static void __tiqdio_inbound_processing(struct qdio_q *q) */ if (!qdio_inbound_q_done(q)) { qperf_inc(q, tasklet_inbound_resched2); - if (likely(q->irq_ptr->state != QDIO_IRQ_STATE_STOPPED)) - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } } @@ -977,7 +977,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr) int i; struct qdio_q *q; - if (unlikely(irq_ptr->state == QDIO_IRQ_STATE_STOPPED)) + if (unlikely(irq_ptr->state != QDIO_IRQ_STATE_ACTIVE)) return; for_each_input_queue(irq_ptr, q, i) { @@ -1003,7 +1003,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr) continue; if (need_siga_sync(q) && need_siga_sync_out_after_pci(q)) qdio_siga_sync_q(q); - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); } } @@ -1066,10 +1066,12 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, struct irb *irb) { struct qdio_irq *irq_ptr = cdev->private->qdio_data; + struct subchannel_id schid; int cstat, dstat; if (!intparm || !irq_ptr) { - DBF_ERROR("qint:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_ERROR("qint:%4x", schid.sch_no); return; } @@ -1122,12 +1124,14 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm, int qdio_get_ssqd_desc(struct ccw_device *cdev, struct qdio_ssqd_desc *data) { + struct subchannel_id schid; if (!cdev || !cdev->private) return -EINVAL; - DBF_EVENT("get ssqd:%4x", cdev->private->schid.sch_no); - return qdio_setup_get_ssqd(NULL, &cdev->private->schid, data); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("get ssqd:%4x", schid.sch_no); + return qdio_setup_get_ssqd(NULL, &schid, data); } EXPORT_SYMBOL_GPL(qdio_get_ssqd_desc); @@ -1141,7 +1145,7 @@ static void qdio_shutdown_queues(struct ccw_device *cdev) tasklet_kill(&q->tasklet); for_each_output_queue(irq_ptr, q, i) { - del_timer(&q->u.out.timer); + del_timer_sync(&q->u.out.timer); tasklet_kill(&q->tasklet); } } @@ -1154,14 +1158,15 @@ static void qdio_shutdown_queues(struct ccw_device *cdev) int qdio_shutdown(struct ccw_device *cdev, int how) { struct qdio_irq *irq_ptr = cdev->private->qdio_data; + struct subchannel_id schid; int rc; - unsigned long flags; if (!irq_ptr) return -ENODEV; WARN_ON_ONCE(irqs_disabled()); - DBF_EVENT("qshutdown:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("qshutdown:%4x", schid.sch_no); mutex_lock(&irq_ptr->setup_mutex); /* @@ -1184,7 +1189,7 @@ int qdio_shutdown(struct ccw_device *cdev, int how) qdio_shutdown_debug_entries(irq_ptr); /* cleanup subchannel */ - spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + spin_lock_irq(get_ccwdev_lock(cdev)); if (how & QDIO_FLAG_CLEANUP_USING_CLEAR) rc = ccw_device_clear(cdev, QDIO_DOING_CLEANUP); @@ -1198,12 +1203,12 @@ int qdio_shutdown(struct ccw_device *cdev, int how) } qdio_set_state(irq_ptr, QDIO_IRQ_STATE_CLEANUP); - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + spin_unlock_irq(get_ccwdev_lock(cdev)); wait_event_interruptible_timeout(cdev->private->wait_q, irq_ptr->state == QDIO_IRQ_STATE_INACTIVE || irq_ptr->state == QDIO_IRQ_STATE_ERR, 10 * HZ); - spin_lock_irqsave(get_ccwdev_lock(cdev), flags); + spin_lock_irq(get_ccwdev_lock(cdev)); no_cleanup: qdio_shutdown_thinint(irq_ptr); @@ -1211,7 +1216,7 @@ no_cleanup: /* restore interrupt handler */ if ((void *)cdev->handler == (void *)qdio_int_handler) cdev->handler = irq_ptr->orig_handler; - spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags); + spin_unlock_irq(get_ccwdev_lock(cdev)); qdio_set_state(irq_ptr, QDIO_IRQ_STATE_INACTIVE); mutex_unlock(&irq_ptr->setup_mutex); @@ -1228,11 +1233,13 @@ EXPORT_SYMBOL_GPL(qdio_shutdown); int qdio_free(struct ccw_device *cdev) { struct qdio_irq *irq_ptr = cdev->private->qdio_data; + struct subchannel_id schid; if (!irq_ptr) return -ENODEV; - DBF_EVENT("qfree:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("qfree:%4x", schid.sch_no); DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf abandoned"); mutex_lock(&irq_ptr->setup_mutex); @@ -1251,9 +1258,11 @@ EXPORT_SYMBOL_GPL(qdio_free); */ int qdio_allocate(struct qdio_initialize *init_data) { + struct subchannel_id schid; struct qdio_irq *irq_ptr; - DBF_EVENT("qallocate:%4x", init_data->cdev->private->schid.sch_no); + ccw_device_get_schid(init_data->cdev, &schid); + DBF_EVENT("qallocate:%4x", schid.sch_no); if ((init_data->no_input_qs && !init_data->input_handler) || (init_data->no_output_qs && !init_data->output_handler)) @@ -1331,20 +1340,18 @@ static void qdio_detect_hsicq(struct qdio_irq *irq_ptr) */ int qdio_establish(struct qdio_initialize *init_data) { - struct qdio_irq *irq_ptr; struct ccw_device *cdev = init_data->cdev; - unsigned long saveflags; + struct subchannel_id schid; + struct qdio_irq *irq_ptr; int rc; - DBF_EVENT("qestablish:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("qestablish:%4x", schid.sch_no); irq_ptr = cdev->private->qdio_data; if (!irq_ptr) return -ENODEV; - if (cdev->private->state != DEV_STATE_ONLINE) - return -EINVAL; - mutex_lock(&irq_ptr->setup_mutex); qdio_setup_irq(init_data); @@ -1361,17 +1368,14 @@ int qdio_establish(struct qdio_initialize *init_data) irq_ptr->ccw.count = irq_ptr->equeue.count; irq_ptr->ccw.cda = (u32)((addr_t)irq_ptr->qdr); - spin_lock_irqsave(get_ccwdev_lock(cdev), saveflags); + spin_lock_irq(get_ccwdev_lock(cdev)); ccw_device_set_options_mask(cdev, 0); rc = ccw_device_start(cdev, &irq_ptr->ccw, QDIO_DOING_ESTABLISH, 0, 0); + spin_unlock_irq(get_ccwdev_lock(cdev)); if (rc) { DBF_ERROR("%4x est IO ERR", irq_ptr->schid.sch_no); DBF_ERROR("rc:%4x", rc); - } - spin_unlock_irqrestore(get_ccwdev_lock(cdev), saveflags); - - if (rc) { mutex_unlock(&irq_ptr->setup_mutex); qdio_shutdown(cdev, QDIO_FLAG_CLEANUP_USING_CLEAR); return rc; @@ -1407,19 +1411,17 @@ EXPORT_SYMBOL_GPL(qdio_establish); */ int qdio_activate(struct ccw_device *cdev) { + struct subchannel_id schid; struct qdio_irq *irq_ptr; int rc; - unsigned long saveflags; - DBF_EVENT("qactivate:%4x", cdev->private->schid.sch_no); + ccw_device_get_schid(cdev, &schid); + DBF_EVENT("qactivate:%4x", schid.sch_no); irq_ptr = cdev->private->qdio_data; if (!irq_ptr) return -ENODEV; - if (cdev->private->state != DEV_STATE_ONLINE) - return -EINVAL; - mutex_lock(&irq_ptr->setup_mutex); if (irq_ptr->state == QDIO_IRQ_STATE_INACTIVE) { rc = -EBUSY; @@ -1431,19 +1433,17 @@ int qdio_activate(struct ccw_device *cdev) irq_ptr->ccw.count = irq_ptr->aqueue.count; irq_ptr->ccw.cda = 0; - spin_lock_irqsave(get_ccwdev_lock(cdev), saveflags); + spin_lock_irq(get_ccwdev_lock(cdev)); ccw_device_set_options(cdev, CCWDEV_REPORT_ALL); rc = ccw_device_start(cdev, &irq_ptr->ccw, QDIO_DOING_ACTIVATE, 0, DOIO_DENY_PREFETCH); + spin_unlock_irq(get_ccwdev_lock(cdev)); if (rc) { DBF_ERROR("%4x act IO ERR", irq_ptr->schid.sch_no); DBF_ERROR("rc:%4x", rc); - } - spin_unlock_irqrestore(get_ccwdev_lock(cdev), saveflags); - - if (rc) goto out; + } if (is_thinint_irq(irq_ptr)) tiqdio_add_input_queues(irq_ptr); @@ -1585,10 +1585,11 @@ static int handle_outbound(struct qdio_q *q, unsigned int callflags, /* in case of SIGA errors we must process the error immediately */ if (used >= q->u.out.scan_threshold || rc) - tasklet_schedule(&q->tasklet); + qdio_tasklet_schedule(q); else /* free the SBALs in case of no further traffic */ - if (!timer_pending(&q->u.out.timer)) + if (!timer_pending(&q->u.out.timer) && + likely(q->irq_ptr->state == QDIO_IRQ_STATE_ACTIVE)) mod_timer(&q->u.out.timer, jiffies + HZ); return rc; } diff --git a/drivers/s390/virtio/Makefile b/drivers/s390/virtio/Makefile index 241891a57caf..df40692a9011 100644 --- a/drivers/s390/virtio/Makefile +++ b/drivers/s390/virtio/Makefile @@ -6,4 +6,8 @@ # it under the terms of the GNU General Public License (version 2 only) # as published by the Free Software Foundation. -obj-$(CONFIG_S390_GUEST) += kvm_virtio.o virtio_ccw.o +s390-virtio-objs := virtio_ccw.o +ifdef CONFIG_S390_GUEST_OLD_TRANSPORT +s390-virtio-objs += kvm_virtio.o +endif +obj-$(CONFIG_S390_GUEST) += $(s390-virtio-objs) diff --git a/drivers/s390/virtio/kvm_virtio.c b/drivers/s390/virtio/kvm_virtio.c index 1d060fd293a3..5e5c11f37b24 100644 --- a/drivers/s390/virtio/kvm_virtio.c +++ b/drivers/s390/virtio/kvm_virtio.c @@ -458,6 +458,8 @@ static int __init kvm_devices_init(void) if (test_devices_support(total_memory_size) < 0) return -ENODEV; + pr_warn("The s390-virtio transport is deprecated. Please switch to a modern host providing virtio-ccw.\n"); + rc = vmem_add_mapping(total_memory_size, PAGE_SIZE); if (rc) return rc; @@ -482,7 +484,7 @@ static int __init kvm_devices_init(void) } /* code for early console output with virtio_console */ -static __init int early_put_chars(u32 vtermno, const char *buf, int count) +static int early_put_chars(u32 vtermno, const char *buf, int count) { char scratch[17]; unsigned int len = count; diff --git a/drivers/scsi/aacraid/commctrl.c b/drivers/scsi/aacraid/commctrl.c index b381b3718a98..5648b715fed9 100644 --- a/drivers/scsi/aacraid/commctrl.c +++ b/drivers/scsi/aacraid/commctrl.c @@ -63,7 +63,7 @@ static int ioctl_send_fib(struct aac_dev * dev, void __user *arg) struct fib *fibptr; struct hw_fib * hw_fib = (struct hw_fib *)0; dma_addr_t hw_fib_pa = (dma_addr_t)0LL; - unsigned size; + unsigned int size, osize; int retval; if (dev->in_reset) { @@ -87,7 +87,8 @@ static int ioctl_send_fib(struct aac_dev * dev, void __user *arg) * will not overrun the buffer when we copy the memory. Return * an error if we would. */ - size = le16_to_cpu(kfib->header.Size) + sizeof(struct aac_fibhdr); + osize = size = le16_to_cpu(kfib->header.Size) + + sizeof(struct aac_fibhdr); if (size < le16_to_cpu(kfib->header.SenderSize)) size = le16_to_cpu(kfib->header.SenderSize); if (size > dev->max_fib_size) { @@ -118,6 +119,14 @@ static int ioctl_send_fib(struct aac_dev * dev, void __user *arg) goto cleanup; } + /* Sanity check the second copy */ + if ((osize != le16_to_cpu(kfib->header.Size) + + sizeof(struct aac_fibhdr)) + || (size < le16_to_cpu(kfib->header.SenderSize))) { + retval = -EINVAL; + goto cleanup; + } + if (kfib->header.Command == cpu_to_le16(TakeABreakPt)) { aac_adapter_interrupt(dev); /* diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index a569c65f22b1..dcf36537a767 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -2923,7 +2923,7 @@ static int fcoe_ctlr_vlan_recv(struct fcoe_ctlr *fip, struct sk_buff *skb) mutex_unlock(&fip->ctlr_mutex); drop: - kfree(skb); + kfree_skb(skb); return rc; } diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c index bf85974be862..17d04c702e1b 100644 --- a/drivers/scsi/ipr.c +++ b/drivers/scsi/ipr.c @@ -10410,8 +10410,11 @@ static int ipr_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id) __ipr_remove(pdev); return rc; } + spin_lock_irqsave(ioa_cfg->host->host_lock, flags); + ioa_cfg->scan_enabled = 1; + schedule_work(&ioa_cfg->work_q); + spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags); - scsi_scan_host(ioa_cfg->host); ioa_cfg->iopoll_weight = ioa_cfg->chip_cfg->iopoll_weight; if (ioa_cfg->iopoll_weight && ioa_cfg->sis64 && ioa_cfg->nvectors > 1) { @@ -10421,10 +10424,8 @@ static int ipr_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id) } } - spin_lock_irqsave(ioa_cfg->host->host_lock, flags); - ioa_cfg->scan_enabled = 1; - schedule_work(&ioa_cfg->work_q); - spin_unlock_irqrestore(ioa_cfg->host->host_lock, flags); + scsi_scan_host(ioa_cfg->host); + return 0; } diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 2dab3dc2aa69..c1ed25adb17e 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -5037,7 +5037,7 @@ static int megasas_init_fw(struct megasas_instance *instance) /* Find first memory bar */ bar_list = pci_select_bars(instance->pdev, IORESOURCE_MEM); instance->bar = find_first_bit(&bar_list, sizeof(unsigned long)); - if (pci_request_selected_regions(instance->pdev, instance->bar, + if (pci_request_selected_regions(instance->pdev, 1<<instance->bar, "megasas: LSI")) { dev_printk(KERN_DEBUG, &instance->pdev->dev, "IO memory region busy!\n"); return -EBUSY; @@ -5339,7 +5339,7 @@ fail_ready_state: iounmap(instance->reg_set); fail_ioremap: - pci_release_selected_regions(instance->pdev, instance->bar); + pci_release_selected_regions(instance->pdev, 1<<instance->bar); return -EINVAL; } @@ -5360,7 +5360,7 @@ static void megasas_release_mfi(struct megasas_instance *instance) iounmap(instance->reg_set); - pci_release_selected_regions(instance->pdev, instance->bar); + pci_release_selected_regions(instance->pdev, 1<<instance->bar); } /** diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index ec837544f784..52d8bbf7feb5 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -2603,7 +2603,7 @@ megasas_release_fusion(struct megasas_instance *instance) iounmap(instance->reg_set); - pci_release_selected_regions(instance->pdev, instance->bar); + pci_release_selected_regions(instance->pdev, 1<<instance->bar); } /** diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 751f13edece0..750f82c339d4 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2188,6 +2188,17 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc) } else ioc->msix96_vector = 0; + if (ioc->is_warpdrive) { + ioc->reply_post_host_index[0] = (resource_size_t __iomem *) + &ioc->chip->ReplyPostHostIndex; + + for (i = 1; i < ioc->cpu_msix_table_sz; i++) + ioc->reply_post_host_index[i] = + (resource_size_t __iomem *) + ((u8 __iomem *)&ioc->chip->Doorbell + (0x4000 + ((i - 1) + * 4))); + } + list_for_each_entry(reply_q, &ioc->reply_queue_list, list) pr_info(MPT3SAS_FMT "%s: IRQ %d\n", reply_q->name, ((ioc->msix_enable) ? "PCI-MSI-X enabled" : @@ -5280,17 +5291,6 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) if (r) goto out_free_resources; - if (ioc->is_warpdrive) { - ioc->reply_post_host_index[0] = (resource_size_t __iomem *) - &ioc->chip->ReplyPostHostIndex; - - for (i = 1; i < ioc->cpu_msix_table_sz; i++) - ioc->reply_post_host_index[i] = - (resource_size_t __iomem *) - ((u8 __iomem *)&ioc->chip->Doorbell + (0x4000 + ((i - 1) - * 4))); - } - pci_set_drvdata(ioc->pdev, ioc->shost); r = _base_get_ioc_facts(ioc, CAN_SLEEP); if (r) diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c index 53ef1cb6418e..0e8601aa877a 100644 --- a/drivers/scsi/ses.c +++ b/drivers/scsi/ses.c @@ -778,6 +778,8 @@ static void ses_intf_remove_enclosure(struct scsi_device *sdev) if (!edev) return; + enclosure_unregister(edev); + ses_dev = edev->scratch; edev->scratch = NULL; @@ -789,7 +791,6 @@ static void ses_intf_remove_enclosure(struct scsi_device *sdev) kfree(edev->component[0].scratch); put_device(&edev->edev); - enclosure_unregister(edev); } static void ses_intf_remove(struct device *cdev, diff --git a/drivers/thermal/clock_cooling.c b/drivers/thermal/clock_cooling.c index 1b4ff0f4c716..ed5dd0e88657 100644 --- a/drivers/thermal/clock_cooling.c +++ b/drivers/thermal/clock_cooling.c @@ -426,6 +426,7 @@ clock_cooling_register(struct device *dev, const char *clock_name) if (!ccdev) return ERR_PTR(-ENOMEM); + mutex_init(&ccdev->lock); ccdev->dev = dev; ccdev->clk = devm_clk_get(dev, clock_name); if (IS_ERR(ccdev->clk)) diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index 3788ed74c9ab..a32b41783b77 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -740,12 +740,22 @@ static int cpufreq_power2state(struct thermal_cooling_device *cdev, } /* Bind cpufreq callbacks to thermal cooling device ops */ + static struct thermal_cooling_device_ops cpufreq_cooling_ops = { .get_max_state = cpufreq_get_max_state, .get_cur_state = cpufreq_get_cur_state, .set_cur_state = cpufreq_set_cur_state, }; +static struct thermal_cooling_device_ops cpufreq_power_cooling_ops = { + .get_max_state = cpufreq_get_max_state, + .get_cur_state = cpufreq_get_cur_state, + .set_cur_state = cpufreq_set_cur_state, + .get_requested_power = cpufreq_get_requested_power, + .state2power = cpufreq_state2power, + .power2state = cpufreq_power2state, +}; + /* Notifier for cpufreq policy change */ static struct notifier_block thermal_cpufreq_notifier_block = { .notifier_call = cpufreq_thermal_notifier, @@ -795,6 +805,7 @@ __cpufreq_cooling_register(struct device_node *np, struct cpumask temp_mask; unsigned int freq, i, num_cpus; int ret; + struct thermal_cooling_device_ops *cooling_ops; cpumask_and(&temp_mask, clip_cpus, cpu_online_mask); policy = cpufreq_cpu_get(cpumask_first(&temp_mask)); @@ -850,10 +861,6 @@ __cpufreq_cooling_register(struct device_node *np, cpumask_copy(&cpufreq_dev->allowed_cpus, clip_cpus); if (capacitance) { - cpufreq_cooling_ops.get_requested_power = - cpufreq_get_requested_power; - cpufreq_cooling_ops.state2power = cpufreq_state2power; - cpufreq_cooling_ops.power2state = cpufreq_power2state; cpufreq_dev->plat_get_static_power = plat_static_func; ret = build_dyn_power_table(cpufreq_dev, capacitance); @@ -861,6 +868,10 @@ __cpufreq_cooling_register(struct device_node *np, cool_dev = ERR_PTR(ret); goto free_table; } + + cooling_ops = &cpufreq_power_cooling_ops; + } else { + cooling_ops = &cpufreq_cooling_ops; } ret = get_idr(&cpufreq_idr, &cpufreq_dev->id); @@ -885,7 +896,7 @@ __cpufreq_cooling_register(struct device_node *np, cpufreq_dev->id); cool_dev = thermal_of_cooling_device_register(np, dev_name, cpufreq_dev, - &cpufreq_cooling_ops); + cooling_ops); if (IS_ERR(cool_dev)) goto remove_idr; diff --git a/drivers/thermal/fair_share.c b/drivers/thermal/fair_share.c index 34fe36504a55..68bd1b569118 100644 --- a/drivers/thermal/fair_share.c +++ b/drivers/thermal/fair_share.c @@ -116,7 +116,9 @@ static int fair_share_throttle(struct thermal_zone_device *tz, int trip) instance->target = get_target_state(tz, cdev, percentage, cur_trip_level); + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; + mutex_unlock(&instance->cdev->lock); thermal_cdev_update(cdev); } return 0; diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c index fc52016d4e85..bb118a152cbb 100644 --- a/drivers/thermal/gov_bang_bang.c +++ b/drivers/thermal/gov_bang_bang.c @@ -71,7 +71,9 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) dev_dbg(&instance->cdev->device, "target=%d\n", (int)instance->target); + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; /* cdev needs update */ + mutex_unlock(&instance->cdev->lock); } mutex_unlock(&tz->lock); diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c index c5547bd711db..e473548b5d28 100644 --- a/drivers/thermal/imx_thermal.c +++ b/drivers/thermal/imx_thermal.c @@ -471,8 +471,6 @@ MODULE_DEVICE_TABLE(of, of_imx_thermal_match); static int imx_thermal_probe(struct platform_device *pdev) { - const struct of_device_id *of_id = - of_match_device(of_imx_thermal_match, &pdev->dev); struct imx_thermal_data *data; struct regmap *map; int measure_freq; @@ -490,7 +488,7 @@ static int imx_thermal_probe(struct platform_device *pdev) } data->tempmon = map; - data->socdata = of_id->data; + data->socdata = of_device_get_match_data(&pdev->dev); /* make sure the IRQ flag is clear before enabling irq on i.MX6SX */ if (data->socdata->version == TEMPMON_IMX6SX) { diff --git a/drivers/thermal/int340x_thermal/int3406_thermal.c b/drivers/thermal/int340x_thermal/int3406_thermal.c index a578cd257db4..1891f34ab7fc 100644 --- a/drivers/thermal/int340x_thermal/int3406_thermal.c +++ b/drivers/thermal/int340x_thermal/int3406_thermal.c @@ -225,7 +225,6 @@ static struct platform_driver int3406_thermal_driver = { .remove = int3406_thermal_remove, .driver = { .name = "int3406 thermal", - .owner = THIS_MODULE, .acpi_match_table = int3406_thermal_match, }, }; diff --git a/drivers/thermal/intel_pch_thermal.c b/drivers/thermal/intel_pch_thermal.c index 6a6ec1c95a7a..9b4815e81b0d 100644 --- a/drivers/thermal/intel_pch_thermal.c +++ b/drivers/thermal/intel_pch_thermal.c @@ -21,6 +21,7 @@ #include <linux/init.h> #include <linux/pci.h> #include <linux/thermal.h> +#include <linux/pm.h> /* Intel PCH thermal Device IDs */ #define PCH_THERMAL_DID_WPT 0x9CA4 /* Wildcat Point */ @@ -65,6 +66,7 @@ struct pch_thermal_device { unsigned long crt_temp; int hot_trip_id; unsigned long hot_temp; + bool bios_enabled; }; static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips) @@ -75,8 +77,10 @@ static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips) *nr_trips = 0; /* Check if BIOS has already enabled thermal sensor */ - if (WPT_TSS_TSDSS & readb(ptd->hw_base + WPT_TSS)) + if (WPT_TSS_TSDSS & readb(ptd->hw_base + WPT_TSS)) { + ptd->bios_enabled = true; goto read_trips; + } tsel = readb(ptd->hw_base + WPT_TSEL); /* @@ -130,9 +134,39 @@ static int pch_wpt_get_temp(struct pch_thermal_device *ptd, int *temp) return 0; } +static int pch_wpt_suspend(struct pch_thermal_device *ptd) +{ + u8 tsel; + + if (ptd->bios_enabled) + return 0; + + tsel = readb(ptd->hw_base + WPT_TSEL); + + writeb(tsel & 0xFE, ptd->hw_base + WPT_TSEL); + + return 0; +} + +static int pch_wpt_resume(struct pch_thermal_device *ptd) +{ + u8 tsel; + + if (ptd->bios_enabled) + return 0; + + tsel = readb(ptd->hw_base + WPT_TSEL); + + writeb(tsel | WPT_TSEL_ETS, ptd->hw_base + WPT_TSEL); + + return 0; +} + struct pch_dev_ops { int (*hw_init)(struct pch_thermal_device *ptd, int *nr_trips); int (*get_temp)(struct pch_thermal_device *ptd, int *temp); + int (*suspend)(struct pch_thermal_device *ptd); + int (*resume)(struct pch_thermal_device *ptd); }; @@ -140,6 +174,8 @@ struct pch_dev_ops { static const struct pch_dev_ops pch_dev_ops_wpt = { .hw_init = pch_wpt_init, .get_temp = pch_wpt_get_temp, + .suspend = pch_wpt_suspend, + .resume = pch_wpt_resume, }; static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp) @@ -269,6 +305,22 @@ static void intel_pch_thermal_remove(struct pci_dev *pdev) pci_disable_device(pdev); } +static int intel_pch_thermal_suspend(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct pch_thermal_device *ptd = pci_get_drvdata(pdev); + + return ptd->ops->suspend(ptd); +} + +static int intel_pch_thermal_resume(struct device *device) +{ + struct pci_dev *pdev = to_pci_dev(device); + struct pch_thermal_device *ptd = pci_get_drvdata(pdev); + + return ptd->ops->resume(ptd); +} + static struct pci_device_id intel_pch_thermal_id[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT) }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL) }, @@ -276,11 +328,17 @@ static struct pci_device_id intel_pch_thermal_id[] = { }; MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id); +static const struct dev_pm_ops intel_pch_pm_ops = { + .suspend = intel_pch_thermal_suspend, + .resume = intel_pch_thermal_resume, +}; + static struct pci_driver intel_pch_thermal_driver = { .name = "intel_pch_thermal", .id_table = intel_pch_thermal_id, .probe = intel_pch_thermal_probe, .remove = intel_pch_thermal_remove, + .driver.pm = &intel_pch_pm_ops, }; module_pci_driver(intel_pch_thermal_driver); diff --git a/drivers/thermal/intel_powerclamp.c b/drivers/thermal/intel_powerclamp.c index 015ce2eb6eb7..0e4dc0afcfd2 100644 --- a/drivers/thermal/intel_powerclamp.c +++ b/drivers/thermal/intel_powerclamp.c @@ -388,7 +388,7 @@ static int clamp_thread(void *arg) int sleeptime; unsigned long target_jiffies; unsigned int guard; - unsigned int compensation = 0; + unsigned int compensated_ratio; int interval; /* jiffies to sleep for each attempt */ unsigned int duration_jiffies = msecs_to_jiffies(duration); unsigned int window_size_now; @@ -409,8 +409,11 @@ static int clamp_thread(void *arg) * c-states, thus we need to compensate the injected idle ratio * to achieve the actual target reported by the HW. */ - compensation = get_compensation(target_ratio); - interval = duration_jiffies*100/(target_ratio+compensation); + compensated_ratio = target_ratio + + get_compensation(target_ratio); + if (compensated_ratio <= 0) + compensated_ratio = 1; + interval = duration_jiffies * 100 / compensated_ratio; /* align idle time */ target_jiffies = roundup(jiffies, interval); @@ -647,8 +650,8 @@ static int powerclamp_set_cur_state(struct thermal_cooling_device *cdev, goto exit_set; } else if (set_target_ratio > 0 && new_target_ratio == 0) { pr_info("Stop forced idle injection\n"); - set_target_ratio = 0; end_power_clamp(); + set_target_ratio = 0; } else /* adjust currently running */ { set_target_ratio = new_target_ratio; /* make new set_target_ratio visible to other cpus */ diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c index 2f1a863a8e15..b4d3116cfdaf 100644 --- a/drivers/thermal/power_allocator.c +++ b/drivers/thermal/power_allocator.c @@ -529,7 +529,9 @@ static void allow_maximum_power(struct thermal_zone_device *tz) continue; instance->target = 0; + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; + mutex_unlock(&instance->cdev->lock); thermal_cdev_update(instance->cdev); } } diff --git a/drivers/thermal/step_wise.c b/drivers/thermal/step_wise.c index ea9366ad3e6b..bcef2e7c4ec9 100644 --- a/drivers/thermal/step_wise.c +++ b/drivers/thermal/step_wise.c @@ -175,7 +175,9 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip) update_passive_instance(tz, trip_type, -1); instance->initialized = true; + mutex_lock(&instance->cdev->lock); instance->cdev->updated = false; /* cdev needs update */ + mutex_unlock(&instance->cdev->lock); } mutex_unlock(&tz->lock); diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 5133cd1e10b7..e2fc6161dded 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -1093,7 +1093,9 @@ int power_actor_set_power(struct thermal_cooling_device *cdev, return ret; instance->target = state; + mutex_lock(&cdev->lock); cdev->updated = false; + mutex_unlock(&cdev->lock); thermal_cdev_update(cdev); return 0; @@ -1623,11 +1625,13 @@ void thermal_cdev_update(struct thermal_cooling_device *cdev) struct thermal_instance *instance; unsigned long target = 0; + mutex_lock(&cdev->lock); /* cooling device is updated*/ - if (cdev->updated) + if (cdev->updated) { + mutex_unlock(&cdev->lock); return; + } - mutex_lock(&cdev->lock); /* Make sure cdev enters the deepest cooling state */ list_for_each_entry(instance, &cdev->thermal_instances, cdev_node) { dev_dbg(&cdev->device, "zone%d->target=%lu\n", @@ -1637,9 +1641,9 @@ void thermal_cdev_update(struct thermal_cooling_device *cdev) if (instance->target > target) target = instance->target; } - mutex_unlock(&cdev->lock); cdev->ops->set_cur_state(cdev, target); cdev->updated = true; + mutex_unlock(&cdev->lock); trace_cdev_update(cdev, target); dev_dbg(&cdev->device, "set to state %lu\n", target); } diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c index 06fd2ed9ef9d..c41c7742903a 100644 --- a/drivers/thermal/thermal_hwmon.c +++ b/drivers/thermal/thermal_hwmon.c @@ -232,6 +232,7 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz) return result; } +EXPORT_SYMBOL_GPL(thermal_add_hwmon_sysfs); void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) { @@ -270,3 +271,4 @@ void thermal_remove_hwmon_sysfs(struct thermal_zone_device *tz) hwmon_device_unregister(hwmon->device); kfree(hwmon); } +EXPORT_SYMBOL_GPL(thermal_remove_hwmon_sysfs); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 71912301ef7f..0f3f62e81e5b 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -1354,7 +1354,6 @@ made_compressed_probe: spin_lock_init(&acm->write_lock); spin_lock_init(&acm->read_lock); mutex_init(&acm->mutex); - acm->rx_endpoint = usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress); acm->is_int_ep = usb_endpoint_xfer_int(epread); if (acm->is_int_ep) acm->bInterval = epread->bInterval; @@ -1394,14 +1393,14 @@ made_compressed_probe: urb->transfer_dma = rb->dma; if (acm->is_int_ep) { usb_fill_int_urb(urb, acm->dev, - acm->rx_endpoint, + usb_rcvintpipe(usb_dev, epread->bEndpointAddress), rb->base, acm->readsize, acm_read_bulk_callback, rb, acm->bInterval); } else { usb_fill_bulk_urb(urb, acm->dev, - acm->rx_endpoint, + usb_rcvbulkpipe(usb_dev, epread->bEndpointAddress), rb->base, acm->readsize, acm_read_bulk_callback, rb); diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index 05ce308d5d2a..1f1eabfd8462 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -96,7 +96,6 @@ struct acm { struct acm_rb read_buffers[ACM_NR]; struct acm_wb *putbuffer; /* for acm_tty_put_char() */ int rx_buflimit; - int rx_endpoint; spinlock_t read_lock; int write_used; /* number of non-empty write buffers */ int transmitting; diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c index 31ccdccd7a04..051163189810 100644 --- a/drivers/usb/core/config.c +++ b/drivers/usb/core/config.c @@ -171,6 +171,31 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno, ep, buffer, size); } +static const unsigned short low_speed_maxpacket_maxes[4] = { + [USB_ENDPOINT_XFER_CONTROL] = 8, + [USB_ENDPOINT_XFER_ISOC] = 0, + [USB_ENDPOINT_XFER_BULK] = 0, + [USB_ENDPOINT_XFER_INT] = 8, +}; +static const unsigned short full_speed_maxpacket_maxes[4] = { + [USB_ENDPOINT_XFER_CONTROL] = 64, + [USB_ENDPOINT_XFER_ISOC] = 1023, + [USB_ENDPOINT_XFER_BULK] = 64, + [USB_ENDPOINT_XFER_INT] = 64, +}; +static const unsigned short high_speed_maxpacket_maxes[4] = { + [USB_ENDPOINT_XFER_CONTROL] = 64, + [USB_ENDPOINT_XFER_ISOC] = 1024, + [USB_ENDPOINT_XFER_BULK] = 512, + [USB_ENDPOINT_XFER_INT] = 1023, +}; +static const unsigned short super_speed_maxpacket_maxes[4] = { + [USB_ENDPOINT_XFER_CONTROL] = 512, + [USB_ENDPOINT_XFER_ISOC] = 1024, + [USB_ENDPOINT_XFER_BULK] = 1024, + [USB_ENDPOINT_XFER_INT] = 1024, +}; + static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, int asnum, struct usb_host_interface *ifp, int num_ep, unsigned char *buffer, int size) @@ -179,6 +204,8 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, struct usb_endpoint_descriptor *d; struct usb_host_endpoint *endpoint; int n, i, j, retval; + unsigned int maxp; + const unsigned short *maxpacket_maxes; d = (struct usb_endpoint_descriptor *) buffer; buffer += d->bLength; @@ -286,6 +313,42 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, endpoint->desc.wMaxPacketSize = cpu_to_le16(8); } + /* Validate the wMaxPacketSize field */ + maxp = usb_endpoint_maxp(&endpoint->desc); + + /* Find the highest legal maxpacket size for this endpoint */ + i = 0; /* additional transactions per microframe */ + switch (to_usb_device(ddev)->speed) { + case USB_SPEED_LOW: + maxpacket_maxes = low_speed_maxpacket_maxes; + break; + case USB_SPEED_FULL: + maxpacket_maxes = full_speed_maxpacket_maxes; + break; + case USB_SPEED_HIGH: + /* Bits 12..11 are allowed only for HS periodic endpoints */ + if (usb_endpoint_xfer_int(d) || usb_endpoint_xfer_isoc(d)) { + i = maxp & (BIT(12) | BIT(11)); + maxp &= ~i; + } + /* fallthrough */ + default: + maxpacket_maxes = high_speed_maxpacket_maxes; + break; + case USB_SPEED_SUPER: + case USB_SPEED_SUPER_PLUS: + maxpacket_maxes = super_speed_maxpacket_maxes; + break; + } + j = maxpacket_maxes[usb_endpoint_type(&endpoint->desc)]; + + if (maxp > j) { + dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has invalid maxpacket %d, setting to %d\n", + cfgno, inum, asnum, d->bEndpointAddress, maxp, j); + maxp = j; + endpoint->desc.wMaxPacketSize = cpu_to_le16(i | maxp); + } + /* * Some buggy high speed devices have bulk endpoints using * maxpacket sizes other than 512. High speed HCDs may not @@ -293,9 +356,6 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum, */ if (to_usb_device(ddev)->speed == USB_SPEED_HIGH && usb_endpoint_xfer_bulk(d)) { - unsigned maxp; - - maxp = usb_endpoint_maxp(&endpoint->desc) & 0x07ff; if (maxp != 512) dev_warn(ddev, "config %d interface %d altsetting %d " "bulk endpoint 0x%X has invalid maxpacket %d\n", diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index e9f5043a2167..e6a6d67c8705 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -241,7 +241,8 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) goto error_decrease_mem; } - mem = usb_alloc_coherent(ps->dev, size, GFP_USER, &dma_handle); + mem = usb_alloc_coherent(ps->dev, size, GFP_USER | __GFP_NOWARN, + &dma_handle); if (!mem) { ret = -ENOMEM; goto error_free_usbm; @@ -2582,7 +2583,9 @@ static unsigned int usbdev_poll(struct file *file, if (file->f_mode & FMODE_WRITE && !list_empty(&ps->async_completed)) mask |= POLLOUT | POLLWRNORM; if (!connected(ps)) - mask |= POLLERR | POLLHUP; + mask |= POLLHUP; + if (list_empty(&ps->list)) + mask |= POLLERR; return mask; } diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index bee13517676f..1d5fc32d06d0 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -1052,14 +1052,11 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) /* Continue a partial initialization */ if (type == HUB_INIT2 || type == HUB_INIT3) { - device_lock(hub->intfdev); + device_lock(&hdev->dev); /* Was the hub disconnected while we were waiting? */ - if (hub->disconnected) { - device_unlock(hub->intfdev); - kref_put(&hub->kref, hub_release); - return; - } + if (hub->disconnected) + goto disconnected; if (type == HUB_INIT2) goto init2; goto init3; @@ -1262,7 +1259,7 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) queue_delayed_work(system_power_efficient_wq, &hub->init_work, msecs_to_jiffies(delay)); - device_unlock(hub->intfdev); + device_unlock(&hdev->dev); return; /* Continues at init3: below */ } else { msleep(delay); @@ -1281,12 +1278,12 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type) /* Scan all ports that need attention */ kick_hub_wq(hub); - /* Allow autosuspend if it was suppressed */ - if (type <= HUB_INIT3) + if (type == HUB_INIT2 || type == HUB_INIT3) { + /* Allow autosuspend if it was suppressed */ + disconnected: usb_autopm_put_interface_async(to_usb_interface(hub->intfdev)); - - if (type == HUB_INIT2 || type == HUB_INIT3) - device_unlock(hub->intfdev); + device_unlock(&hdev->dev); + } kref_put(&hub->kref, hub_release); } @@ -1315,8 +1312,6 @@ static void hub_quiesce(struct usb_hub *hub, enum hub_quiescing_type type) struct usb_device *hdev = hub->hdev; int i; - cancel_delayed_work_sync(&hub->init_work); - /* hub_wq and related activity won't re-trigger */ hub->quiescing = 1; diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 974335377d9f..e56d59b19a0e 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -61,6 +61,7 @@ static int dwc3_of_simple_probe(struct platform_device *pdev) if (!simple->clks) return -ENOMEM; + platform_set_drvdata(pdev, simple); simple->dev = dev; for (i = 0; i < simple->num_clocks; i++) { diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 45f5a232d9fb..2eb84d6c24a6 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -37,6 +37,7 @@ #define PCI_DEVICE_ID_INTEL_BXT 0x0aaa #define PCI_DEVICE_ID_INTEL_BXT_M 0x1aaa #define PCI_DEVICE_ID_INTEL_APL 0x5aaa +#define PCI_DEVICE_ID_INTEL_KBP 0xa2b0 static const struct acpi_gpio_params reset_gpios = { 0, 0, false }; static const struct acpi_gpio_params cs_gpios = { 1, 0, false }; @@ -227,6 +228,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BXT), }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BXT_M), }, { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_APL), }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_KBP), }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_NL_USB), }, { } /* Terminating Entry */ }; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 8f8c2157910e..1f5597ef945d 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -829,7 +829,7 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep, if (!req->request.no_interrupt && !chain) trb->ctrl |= DWC3_TRB_CTRL_IOC | DWC3_TRB_CTRL_ISP_IMI; - if (last) + if (last && !usb_endpoint_xfer_isoc(dep->endpoint.desc)) trb->ctrl |= DWC3_TRB_CTRL_LST; if (chain) @@ -1955,7 +1955,8 @@ static void dwc3_gadget_free_endpoints(struct dwc3 *dwc) static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep, struct dwc3_request *req, struct dwc3_trb *trb, - const struct dwc3_event_depevt *event, int status) + const struct dwc3_event_depevt *event, int status, + int chain) { unsigned int count; unsigned int s_pkt = 0; @@ -1964,17 +1965,22 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep, dep->queued_requests--; trace_dwc3_complete_trb(dep, trb); + /* + * If we're in the middle of series of chained TRBs and we + * receive a short transfer along the way, DWC3 will skip + * through all TRBs including the last TRB in the chain (the + * where CHN bit is zero. DWC3 will also avoid clearing HWO + * bit and SW has to do it manually. + * + * We're going to do that here to avoid problems of HW trying + * to use bogus TRBs for transfers. + */ + if (chain && (trb->ctrl & DWC3_TRB_CTRL_HWO)) + trb->ctrl &= ~DWC3_TRB_CTRL_HWO; + if ((trb->ctrl & DWC3_TRB_CTRL_HWO) && status != -ESHUTDOWN) - /* - * We continue despite the error. There is not much we - * can do. If we don't clean it up we loop forever. If - * we skip the TRB then it gets overwritten after a - * while since we use them in a ring buffer. A BUG() - * would help. Lets hope that if this occurs, someone - * fixes the root cause instead of looking away :) - */ - dev_err(dwc->dev, "%s's TRB (%p) still owned by HW\n", - dep->name, trb); + return 1; + count = trb->size & DWC3_TRB_SIZE_MASK; if (dep->direction) { @@ -2013,15 +2019,7 @@ static int __dwc3_cleanup_done_trbs(struct dwc3 *dwc, struct dwc3_ep *dep, s_pkt = 1; } - /* - * We assume here we will always receive the entire data block - * which we should receive. Meaning, if we program RX to - * receive 4K but we receive only 2K, we assume that's all we - * should receive and we simply bounce the request back to the - * gadget driver for further processing. - */ - req->request.actual += req->request.length - count; - if (s_pkt) + if (s_pkt && !chain) return 1; if ((event->status & DEPEVT_STATUS_LST) && (trb->ctrl & (DWC3_TRB_CTRL_LST | @@ -2040,13 +2038,17 @@ static int dwc3_cleanup_done_reqs(struct dwc3 *dwc, struct dwc3_ep *dep, struct dwc3_trb *trb; unsigned int slot; unsigned int i; + int count = 0; int ret; do { + int chain; + req = next_request(&dep->started_list); if (WARN_ON_ONCE(!req)) return 1; + chain = req->request.num_mapped_sgs > 0; i = 0; do { slot = req->first_trb_index + i; @@ -2054,13 +2056,22 @@ static int dwc3_cleanup_done_reqs(struct dwc3 *dwc, struct dwc3_ep *dep, slot++; slot %= DWC3_TRB_NUM; trb = &dep->trb_pool[slot]; + count += trb->size & DWC3_TRB_SIZE_MASK; ret = __dwc3_cleanup_done_trbs(dwc, dep, req, trb, - event, status); + event, status, chain); if (ret) break; } while (++i < req->request.num_mapped_sgs); + /* + * We assume here we will always receive the entire data block + * which we should receive. Meaning, if we program RX to + * receive 4K but we receive only 2K, we assume that's all we + * should receive and we simply bounce the request back to the + * gadget driver for further processing. + */ + req->request.actual += req->request.length - count; dwc3_gadget_giveback(dep, req, status); if (ret) diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index eb648485a58c..5ebe6af7976e 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -1913,6 +1913,8 @@ unknown: break; case USB_RECIP_ENDPOINT: + if (!cdev->config) + break; endp = ((w_index & 0x80) >> 3) | (w_index & 0x0f); list_for_each_entry(f, &cdev->config->functions, list) { if (test_bit(endp, f->endpoints)) @@ -2124,14 +2126,14 @@ int composite_os_desc_req_prepare(struct usb_composite_dev *cdev, cdev->os_desc_req = usb_ep_alloc_request(ep0, GFP_KERNEL); if (!cdev->os_desc_req) { - ret = PTR_ERR(cdev->os_desc_req); + ret = -ENOMEM; goto end; } /* OS feature descriptor length <= 4kB */ cdev->os_desc_req->buf = kmalloc(4096, GFP_KERNEL); if (!cdev->os_desc_req->buf) { - ret = PTR_ERR(cdev->os_desc_req->buf); + ret = -ENOMEM; kfree(cdev->os_desc_req); goto end; } diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 70cf3477f951..f9237fe2be05 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -1490,7 +1490,9 @@ void unregister_gadget_item(struct config_item *item) { struct gadget_info *gi = to_gadget_info(item); + mutex_lock(&gi->lock); unregister_gadget(gi); + mutex_unlock(&gi->lock); } EXPORT_SYMBOL_GPL(unregister_gadget_item); diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 943c21aafd3b..ab6ac1b74ac0 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -680,6 +680,12 @@ static int rndis_reset_response(struct rndis_params *params, { rndis_reset_cmplt_type *resp; rndis_resp_t *r; + u8 *xbuf; + u32 length; + + /* drain the response queue */ + while ((xbuf = rndis_get_next_response(params, &length))) + rndis_free_response(params, xbuf); r = rndis_add_response(params, sizeof(rndis_reset_cmplt_type)); if (!r) diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c index a3f7e7c55ebb..5f562c1ec795 100644 --- a/drivers/usb/gadget/function/u_ether.c +++ b/drivers/usb/gadget/function/u_ether.c @@ -556,7 +556,8 @@ static netdev_tx_t eth_start_xmit(struct sk_buff *skb, /* Multi frame CDC protocols may store the frame for * later which is not a dropped frame. */ - if (dev->port_usb->supports_multi_frame) + if (dev->port_usb && + dev->port_usb->supports_multi_frame) goto multiframe; goto drop; } diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 66753ba7a42e..31125a4a2658 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -2023,7 +2023,7 @@ static int uvcg_streaming_class_allow_link(struct config_item *src, if (!data) { kfree(*class_array); *class_array = NULL; - ret = PTR_ERR(data); + ret = -ENOMEM; goto unlock; } cl_arr = *class_array; diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index aa3707bdebb4..16104b5ebdcb 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -542,7 +542,7 @@ static ssize_t ep_aio(struct kiocb *iocb, */ spin_lock_irq(&epdata->dev->lock); value = -ENODEV; - if (unlikely(epdata->ep)) + if (unlikely(epdata->ep == NULL)) goto fail; req = usb_ep_alloc_request(epdata->ep, GFP_ATOMIC); @@ -606,7 +606,7 @@ ep_read_iter(struct kiocb *iocb, struct iov_iter *to) } if (is_sync_kiocb(iocb)) { value = ep_io(epdata, buf, len); - if (value >= 0 && copy_to_iter(buf, value, to)) + if (value >= 0 && (copy_to_iter(buf, value, to) != value)) value = -EFAULT; } else { struct kiocb_priv *priv = kzalloc(sizeof *priv, GFP_KERNEL); diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c index ff8685ea7219..934f83881c30 100644 --- a/drivers/usb/gadget/udc/core.c +++ b/drivers/usb/gadget/udc/core.c @@ -1145,7 +1145,7 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, if (ret != -EPROBE_DEFER) list_del(&driver->pending); if (ret) - goto err4; + goto err5; break; } } @@ -1154,6 +1154,9 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, return 0; +err5: + device_del(&udc->dev); + err4: list_del(&udc->list); mutex_unlock(&udc_lock); diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index 93d28cb00b76..cf8819a5c5b2 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -2053,7 +2053,7 @@ static void setup_received_handle(struct qe_udc *udc, struct qe_ep *ep; if (wValue != 0 || wLength != 0 - || pipe > USB_MAX_ENDPOINTS) + || pipe >= USB_MAX_ENDPOINTS) break; ep = &udc->eps[pipe]; diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index a962b89b65a6..1e5f529d51a2 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -332,11 +332,11 @@ static void ehci_turn_off_all_ports(struct ehci_hcd *ehci) int port = HCS_N_PORTS(ehci->hcs_params); while (port--) { - ehci_writel(ehci, PORT_RWC_BITS, - &ehci->regs->port_status[port]); spin_unlock_irq(&ehci->lock); ehci_port_power(ehci, port, false); spin_lock_irq(&ehci->lock); + ehci_writel(ehci, PORT_RWC_BITS, + &ehci->regs->port_status[port]); } } diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c index c369c29e496d..2f7690092a7f 100644 --- a/drivers/usb/host/max3421-hcd.c +++ b/drivers/usb/host/max3421-hcd.c @@ -1675,7 +1675,7 @@ max3421_gpout_set_value(struct usb_hcd *hcd, u8 pin_number, u8 value) if (pin_number > 7) return; - mask = 1u << pin_number; + mask = 1u << (pin_number % 4); idx = pin_number / 4; if (value) diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index d61fcc48099e..730b9fd26685 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -386,6 +386,9 @@ static int xhci_stop_device(struct xhci_hcd *xhci, int slot_id, int suspend) ret = 0; virt_dev = xhci->devs[slot_id]; + if (!virt_dev) + return -ENODEV; + cmd = xhci_alloc_command(xhci, false, true, GFP_NOIO); if (!cmd) { xhci_dbg(xhci, "Couldn't allocate command structure.\n"); diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 4fd041bec332..d7b0f97abbad 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -314,11 +314,12 @@ static void xhci_pci_remove(struct pci_dev *dev) usb_remove_hcd(xhci->shared_hcd); usb_put_hcd(xhci->shared_hcd); } - usb_hcd_pci_remove(dev); /* Workaround for spurious wakeups at shutdown with HSW */ if (xhci->quirks & XHCI_SPURIOUS_WAKEUP) pci_set_power_state(dev, PCI_D3hot); + + usb_hcd_pci_remove(dev); } #ifdef CONFIG_PM diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 918e0c739b79..fd9fd12e4861 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1334,12 +1334,6 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, cmd = list_entry(xhci->cmd_list.next, struct xhci_command, cmd_list); - if (cmd->command_trb != xhci->cmd_ring->dequeue) { - xhci_err(xhci, - "Command completion event does not match command\n"); - return; - } - del_timer(&xhci->cmd_timer); trace_xhci_cmd_completion(cmd_trb, (struct xhci_generic_trb *) event); @@ -1351,6 +1345,13 @@ static void handle_cmd_completion(struct xhci_hcd *xhci, xhci_handle_stopped_cmd_ring(xhci, cmd); return; } + + if (cmd->command_trb != xhci->cmd_ring->dequeue) { + xhci_err(xhci, + "Command completion event does not match command\n"); + return; + } + /* * Host aborted the command ring, check if the current command was * supposed to be aborted, otherwise continue normally. @@ -3243,7 +3244,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, send_addr = addr; /* Queue the TRBs, even if they are zero-length */ - for (enqd_len = 0; enqd_len < full_len; enqd_len += trb_buff_len) { + for (enqd_len = 0; first_trb || enqd_len < full_len; + enqd_len += trb_buff_len) { field = TRB_TYPE(TRB_NORMAL); /* TRB buffer should not cross 64KB boundaries */ diff --git a/drivers/usb/misc/ftdi-elan.c b/drivers/usb/misc/ftdi-elan.c index 52c27cab78c3..9b5b3b2281ca 100644 --- a/drivers/usb/misc/ftdi-elan.c +++ b/drivers/usb/misc/ftdi-elan.c @@ -665,7 +665,7 @@ static ssize_t ftdi_elan_read(struct file *file, char __user *buffer, { char data[30 *3 + 4]; char *d = data; - int m = (sizeof(data) - 1) / 3; + int m = (sizeof(data) - 1) / 3 - 1; int bytes_read = 0; int retry_on_empty = 10; int retry_on_timeout = 5; @@ -1684,7 +1684,7 @@ wait:if (ftdi->disconnected > 0) { int i = 0; char data[30 *3 + 4]; char *d = data; - int m = (sizeof(data) - 1) / 3; + int m = (sizeof(data) - 1) / 3 - 1; int l = 0; struct u132_target *target = &ftdi->target[ed]; struct u132_command *command = &ftdi->command[ @@ -1876,7 +1876,7 @@ more:{ if (packet_bytes > 2) { char diag[30 *3 + 4]; char *d = diag; - int m = (sizeof(diag) - 1) / 3; + int m = (sizeof(diag) - 1) / 3 - 1; char *b = ftdi->bulk_in_buffer; int bytes_read = 0; diag[0] = 0; @@ -2053,7 +2053,7 @@ static int ftdi_elan_synchronize(struct usb_ftdi *ftdi) if (packet_bytes > 2) { char diag[30 *3 + 4]; char *d = diag; - int m = (sizeof(diag) - 1) / 3; + int m = (sizeof(diag) - 1) / 3 - 1; char *b = ftdi->bulk_in_buffer; int bytes_read = 0; unsigned char c = 0; @@ -2155,7 +2155,7 @@ more:{ if (packet_bytes > 2) { char diag[30 *3 + 4]; char *d = diag; - int m = (sizeof(diag) - 1) / 3; + int m = (sizeof(diag) - 1) / 3 - 1; char *b = ftdi->bulk_in_buffer; int bytes_read = 0; diag[0] = 0; diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c index 6b978f04b8d7..5c8210dc6fd9 100644 --- a/drivers/usb/misc/usbtest.c +++ b/drivers/usb/misc/usbtest.c @@ -585,7 +585,6 @@ static void sg_timeout(unsigned long _req) { struct usb_sg_request *req = (struct usb_sg_request *) _req; - req->status = -ETIMEDOUT; usb_sg_cancel(req); } @@ -616,8 +615,10 @@ static int perform_sglist( mod_timer(&sg_timer, jiffies + msecs_to_jiffies(SIMPLE_IO_TIMEOUT)); usb_sg_wait(req); - del_timer_sync(&sg_timer); - retval = req->status; + if (!del_timer_sync(&sg_timer)) + retval = -ETIMEDOUT; + else + retval = req->status; /* FIXME check resulting data pattern */ @@ -2602,7 +2603,7 @@ usbtest_ioctl(struct usb_interface *intf, unsigned int code, void *buf) ktime_get_ts64(&start); retval = usbtest_do_ioctl(intf, param_32); - if (retval) + if (retval < 0) goto free_mutex; ktime_get_ts64(&end); diff --git a/drivers/usb/phy/phy-omap-otg.c b/drivers/usb/phy/phy-omap-otg.c index 6f6d2a7fd5a0..6523af4f8f93 100644 --- a/drivers/usb/phy/phy-omap-otg.c +++ b/drivers/usb/phy/phy-omap-otg.c @@ -140,6 +140,8 @@ static int omap_otg_probe(struct platform_device *pdev) (rev >> 4) & 0xf, rev & 0xf, config->extcon, otg_dev->id, otg_dev->vbus); + platform_set_drvdata(pdev, otg_dev); + return 0; } diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c index 8fbbc2d32371..ac67bab9124c 100644 --- a/drivers/usb/renesas_usbhs/common.c +++ b/drivers/usb/renesas_usbhs/common.c @@ -514,7 +514,8 @@ static struct renesas_usbhs_platform_info *usbhs_parse_dt(struct device *dev) if (gpio > 0) dparam->enable_gpio = gpio; - if (dparam->type == USBHS_TYPE_RCAR_GEN2) + if (dparam->type == USBHS_TYPE_RCAR_GEN2 || + dparam->type == USBHS_TYPE_RCAR_GEN3) dparam->has_usb_dmac = 1; return info; diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index 280ed5ff021b..857e78337324 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -871,7 +871,7 @@ static int usbhsf_dma_prepare_push(struct usbhs_pkt *pkt, int *is_done) /* use PIO if packet is less than pio_dma_border or pipe is DCP */ if ((len < usbhs_get_dparam(priv, pio_dma_border)) || - usbhs_pipe_is_dcp(pipe)) + usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC)) goto usbhsf_pio_prepare_push; /* check data length if this driver don't use USB-DMAC */ @@ -976,7 +976,7 @@ static int usbhsf_dma_prepare_pop_with_usb_dmac(struct usbhs_pkt *pkt, /* use PIO if packet is less than pio_dma_border or pipe is DCP */ if ((pkt->length < usbhs_get_dparam(priv, pio_dma_border)) || - usbhs_pipe_is_dcp(pipe)) + usbhs_pipe_type_is(pipe, USB_ENDPOINT_XFER_ISOC)) goto usbhsf_pio_prepare_pop; fifo = usbhsf_get_dma_fifo(priv, pkt); diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c index 50f3363cc382..92bc83b92d10 100644 --- a/drivers/usb/renesas_usbhs/mod_gadget.c +++ b/drivers/usb/renesas_usbhs/mod_gadget.c @@ -617,10 +617,13 @@ static int usbhsg_ep_enable(struct usb_ep *ep, * use dmaengine if possible. * It will use pio handler if impossible. */ - if (usb_endpoint_dir_in(desc)) + if (usb_endpoint_dir_in(desc)) { pipe->handler = &usbhs_fifo_dma_push_handler; - else + } else { pipe->handler = &usbhs_fifo_dma_pop_handler; + usbhs_xxxsts_clear(priv, BRDYSTS, + usbhs_pipe_number(pipe)); + } ret = 0; } diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c index 00820809139a..b2d767e743fc 100644 --- a/drivers/usb/serial/ftdi_sio.c +++ b/drivers/usb/serial/ftdi_sio.c @@ -648,6 +648,8 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(FTDI_VID, FTDI_ELV_TFD128_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ELV_FM3RX_PID) }, { USB_DEVICE(FTDI_VID, FTDI_ELV_WS777_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_PALMSENS_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_IVIUM_XSTAT_PID) }, { USB_DEVICE(FTDI_VID, LINX_SDMUSBQSS_PID) }, { USB_DEVICE(FTDI_VID, LINX_MASTERDEVEL2_PID) }, { USB_DEVICE(FTDI_VID, LINX_FUTURE_0_PID) }, @@ -1008,6 +1010,7 @@ static const struct usb_device_id id_table_combined[] = { { USB_DEVICE(ICPDAS_VID, ICPDAS_I7560U_PID) }, { USB_DEVICE(ICPDAS_VID, ICPDAS_I7561U_PID) }, { USB_DEVICE(ICPDAS_VID, ICPDAS_I7563U_PID) }, + { USB_DEVICE(WICED_VID, WICED_USB20706V2_PID) }, { } /* Terminating entry */ }; diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h index c5d6c1e73e8e..f87a938cf005 100644 --- a/drivers/usb/serial/ftdi_sio_ids.h +++ b/drivers/usb/serial/ftdi_sio_ids.h @@ -406,6 +406,12 @@ #define FTDI_4N_GALAXY_DE_3_PID 0xF3C2 /* + * Ivium Technologies product IDs + */ +#define FTDI_PALMSENS_PID 0xf440 +#define FTDI_IVIUM_XSTAT_PID 0xf441 + +/* * Linx Technologies product ids */ #define LINX_SDMUSBQSS_PID 0xF448 /* Linx SDM-USB-QS-S */ @@ -673,6 +679,12 @@ #define INTREPID_NEOVI_PID 0x0701 /* + * WICED USB UART + */ +#define WICED_VID 0x0A5C +#define WICED_USB20706V2_PID 0x6422 + +/* * Definitions for ID TECH (www.idt-net.com) devices */ #define IDTECH_VID 0x0ACD /* ID TECH Vendor ID */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 8e07536c233a..bc472584a229 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -274,6 +274,12 @@ static void option_instat_callback(struct urb *urb); #define TELIT_PRODUCT_LE920 0x1200 #define TELIT_PRODUCT_LE910 0x1201 #define TELIT_PRODUCT_LE910_USBCFG4 0x1206 +#define TELIT_PRODUCT_LE920A4_1207 0x1207 +#define TELIT_PRODUCT_LE920A4_1208 0x1208 +#define TELIT_PRODUCT_LE920A4_1211 0x1211 +#define TELIT_PRODUCT_LE920A4_1212 0x1212 +#define TELIT_PRODUCT_LE920A4_1213 0x1213 +#define TELIT_PRODUCT_LE920A4_1214 0x1214 /* ZTE PRODUCTS */ #define ZTE_VENDOR_ID 0x19d2 @@ -628,6 +634,11 @@ static const struct option_blacklist_info telit_le920_blacklist = { .reserved = BIT(1) | BIT(5), }; +static const struct option_blacklist_info telit_le920a4_blacklist_1 = { + .sendsetup = BIT(0), + .reserved = BIT(1), +}; + static const struct option_blacklist_info telit_le922_blacklist_usbcfg0 = { .sendsetup = BIT(2), .reserved = BIT(0) | BIT(1) | BIT(3), @@ -1203,6 +1214,16 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920), .driver_info = (kernel_ulong_t)&telit_le920_blacklist }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1207) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1208), + .driver_info = (kernel_ulong_t)&telit_le920a4_blacklist_1 }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1211), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1212), + .driver_info = (kernel_ulong_t)&telit_le920a4_blacklist_1 }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1213, 0xff) }, + { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE920A4_1214), + .driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg3 }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff), .driver_info = (kernel_ulong_t)&net_intf1_blacklist }, @@ -1966,6 +1987,7 @@ static const struct usb_device_id option_ids[] = { .driver_info = (kernel_ulong_t)&net_intf4_blacklist }, { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */ { USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) }, /* OLICARD300 - MT6225 */ { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c index b1b9bac44016..d213cf44a7e4 100644 --- a/drivers/usb/serial/usb-serial.c +++ b/drivers/usb/serial/usb-serial.c @@ -1433,7 +1433,7 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[] rc = usb_register(udriver); if (rc) - return rc; + goto failed_usb_register; for (sd = serial_drivers; *sd; ++sd) { (*sd)->usb_driver = udriver; @@ -1451,6 +1451,8 @@ int usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[] while (sd-- > serial_drivers) usb_serial_deregister(*sd); usb_deregister(udriver); +failed_usb_register: + kfree(udriver); return rc; } EXPORT_SYMBOL_GPL(usb_serial_register_drivers); diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c index 15ecfc9c5f6c..152b43822ef1 100644 --- a/drivers/vfio/pci/vfio_pci_intrs.c +++ b/drivers/vfio/pci/vfio_pci_intrs.c @@ -564,67 +564,80 @@ static int vfio_pci_set_msi_trigger(struct vfio_pci_device *vdev, } static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx, - uint32_t flags, void *data) + unsigned int count, uint32_t flags, + void *data) { - int32_t fd = *(int32_t *)data; - - if (!(flags & VFIO_IRQ_SET_DATA_TYPE_MASK)) - return -EINVAL; - /* DATA_NONE/DATA_BOOL enables loopback testing */ if (flags & VFIO_IRQ_SET_DATA_NONE) { - if (*ctx) - eventfd_signal(*ctx, 1); - return 0; + if (*ctx) { + if (count) { + eventfd_signal(*ctx, 1); + } else { + eventfd_ctx_put(*ctx); + *ctx = NULL; + } + return 0; + } } else if (flags & VFIO_IRQ_SET_DATA_BOOL) { - uint8_t trigger = *(uint8_t *)data; + uint8_t trigger; + + if (!count) + return -EINVAL; + + trigger = *(uint8_t *)data; if (trigger && *ctx) eventfd_signal(*ctx, 1); - return 0; - } - /* Handle SET_DATA_EVENTFD */ - if (fd == -1) { - if (*ctx) - eventfd_ctx_put(*ctx); - *ctx = NULL; return 0; - } else if (fd >= 0) { - struct eventfd_ctx *efdctx; - efdctx = eventfd_ctx_fdget(fd); - if (IS_ERR(efdctx)) - return PTR_ERR(efdctx); - if (*ctx) - eventfd_ctx_put(*ctx); - *ctx = efdctx; + } else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) { + int32_t fd; + + if (!count) + return -EINVAL; + + fd = *(int32_t *)data; + if (fd == -1) { + if (*ctx) + eventfd_ctx_put(*ctx); + *ctx = NULL; + } else if (fd >= 0) { + struct eventfd_ctx *efdctx; + + efdctx = eventfd_ctx_fdget(fd); + if (IS_ERR(efdctx)) + return PTR_ERR(efdctx); + + if (*ctx) + eventfd_ctx_put(*ctx); + + *ctx = efdctx; + } return 0; - } else - return -EINVAL; + } + + return -EINVAL; } static int vfio_pci_set_err_trigger(struct vfio_pci_device *vdev, unsigned index, unsigned start, unsigned count, uint32_t flags, void *data) { - if (index != VFIO_PCI_ERR_IRQ_INDEX) + if (index != VFIO_PCI_ERR_IRQ_INDEX || start != 0 || count > 1) return -EINVAL; - /* - * We should sanitize start & count, but that wasn't caught - * originally, so this IRQ index must forever ignore them :-( - */ - - return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, flags, data); + return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger, + count, flags, data); } static int vfio_pci_set_req_trigger(struct vfio_pci_device *vdev, unsigned index, unsigned start, unsigned count, uint32_t flags, void *data) { - if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count != 1) + if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count > 1) return -EINVAL; - return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, flags, data); + return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger, + count, flags, data); } int vfio_pci_set_irqs_ioctl(struct vfio_pci_device *vdev, uint32_t flags, diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 9d6320e8ff3e..6e29d053843d 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -88,7 +88,7 @@ struct vhost_scsi_cmd { struct scatterlist *tvc_prot_sgl; struct page **tvc_upages; /* Pointer to response header iovec */ - struct iovec *tvc_resp_iov; + struct iovec tvc_resp_iov; /* Pointer to vhost_scsi for our device */ struct vhost_scsi *tvc_vhost; /* Pointer to vhost_virtqueue for the cmd */ @@ -547,7 +547,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) memcpy(v_rsp.sense, cmd->tvc_sense_buf, se_cmd->scsi_sense_length); - iov_iter_init(&iov_iter, READ, cmd->tvc_resp_iov, + iov_iter_init(&iov_iter, READ, &cmd->tvc_resp_iov, cmd->tvc_in_iovs, sizeof(v_rsp)); ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter); if (likely(ret == sizeof(v_rsp))) { @@ -1044,7 +1044,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) } cmd->tvc_vhost = vs; cmd->tvc_vq = vq; - cmd->tvc_resp_iov = &vq->iov[out]; + cmd->tvc_resp_iov = vq->iov[out]; cmd->tvc_in_iovs = in; pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n", diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c index 388eec4e1a90..97fb2f8fa930 100644 --- a/drivers/vhost/test.c +++ b/drivers/vhost/test.c @@ -220,20 +220,20 @@ static long vhost_test_reset_owner(struct vhost_test *n) { void *priv = NULL; long err; - struct vhost_memory *memory; + struct vhost_umem *umem; mutex_lock(&n->dev.mutex); err = vhost_dev_check_owner(&n->dev); if (err) goto done; - memory = vhost_dev_reset_owner_prepare(); - if (!memory) { + umem = vhost_dev_reset_owner_prepare(); + if (!umem) { err = -ENOMEM; goto done; } vhost_test_stop(n, &priv); vhost_test_flush(n); - vhost_dev_reset_owner(&n->dev, memory); + vhost_dev_reset_owner(&n->dev, umem); done: mutex_unlock(&n->dev.mutex); return err; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 0ddf3a2dbfc4..e3b30ea9ece5 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -307,6 +307,8 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) vhost_disable_notify(&vsock->dev, vq); for (;;) { + u32 len; + if (!vhost_vsock_more_replies(vsock)) { /* Stop tx until the device processes already * pending replies. Leave tx virtqueue @@ -334,13 +336,15 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work) continue; } + len = pkt->len; + /* Only accept correctly addressed packets */ if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid) virtio_transport_recv_pkt(pkt); else virtio_transport_free_pkt(pkt); - vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len); + vhost_add_used(vq, head, sizeof(pkt->hdr) + len); added = true; } diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 114a0c88afb8..e383ecdaca59 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -327,6 +327,8 @@ static inline int virtqueue_add(struct virtqueue *_vq, * host should service the ring ASAP. */ if (out_sgs) vq->notify(&vq->vq); + if (indirect) + kfree(desc); END_USE(vq); return -ENOSPC; } @@ -426,6 +428,7 @@ unmap_release: if (indirect) kfree(desc); + END_USE(vq); return -EIO; } diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 7487971f9f78..c1010f018bd8 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -316,7 +316,7 @@ static int xenbus_write_transaction(unsigned msg_type, rc = -ENOMEM; goto out; } - } else { + } else if (msg_type == XS_TRANSACTION_END) { list_for_each_entry(trans, &u->transactions, list) if (trans->handle.id == u->u.msg.tx_id) break; diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 4b0eff6da674..85737e96ab8b 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -189,11 +189,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, case 1: _debug("extract FID count"); ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("FID count: %u", call->count); @@ -210,11 +207,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, _debug("extract FID array"); ret = afs_extract_data(call, skb, last, call->buffer, call->count * 3 * 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; _debug("unmarshall FID array"); call->request = kcalloc(call->count, @@ -239,11 +233,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, case 3: _debug("extract CB count"); ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; tmp = ntohl(call->tmp); _debug("CB count: %u", tmp); @@ -258,11 +249,8 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, _debug("extract CB array"); ret = afs_extract_data(call, skb, last, call->request, call->count * 3 * 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; _debug("unmarshall CB array"); cb = call->request; @@ -278,9 +266,9 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, call->unmarshall++; case 5: - _debug("trailer"); - if (skb->len != 0) - return -EBADMSG; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; /* Record that the message was unmarshalled successfully so * that the call destructor can know do the callback breaking @@ -294,8 +282,6 @@ static int afs_deliver_cb_callback(struct afs_call *call, struct sk_buff *skb, break; } - if (!last) - return 0; call->state = AFS_CALL_REPLYING; @@ -335,13 +321,13 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call, { struct afs_server *server; struct in_addr addr; + int ret; _enter(",{%u},%d", skb->len, last); - if (skb->len > 0) - return -EBADMSG; - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; @@ -371,8 +357,10 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call, _enter(",{%u},%d", skb->len, last); + /* There are some arguments that we ignore */ + afs_data_consumed(call, skb); if (!last) - return 0; + return -EAGAIN; /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; @@ -408,12 +396,13 @@ static void SRXAFSCB_Probe(struct work_struct *work) static int afs_deliver_cb_probe(struct afs_call *call, struct sk_buff *skb, bool last) { + int ret; + _enter(",{%u},%d", skb->len, last); - if (skb->len > 0) - return -EBADMSG; - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; @@ -460,10 +449,9 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb, _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - if (skb->len > 0) - return -EBADMSG; - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; switch (call->unmarshall) { case 0: @@ -509,8 +497,9 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call, struct sk_buff *skb, break; } - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; call->state = AFS_CALL_REPLYING; @@ -588,12 +577,13 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call, struct sk_buff *skb, bool last) { + int ret; + _enter(",{%u},%d", skb->len, last); - if (skb->len > 0) - return -EBADMSG; - if (!last) - return 0; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; /* no unmarshalling required */ call->state = AFS_CALL_REPLYING; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index c2e930ec2888..9312b92e54be 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -240,15 +240,13 @@ static int afs_deliver_fs_fetch_status(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter(",,%u", last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -335,11 +333,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, case 1: _debug("extract data length (MSW)"); ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("DATA length MSW: %u", call->count); @@ -353,11 +348,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, case 2: _debug("extract data length"); ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("DATA length: %u", call->count); @@ -375,11 +367,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, ret = afs_extract_data(call, skb, last, buffer, call->count); kunmap_atomic(buffer); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; } call->offset = 0; @@ -389,11 +378,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, case 4: ret = afs_extract_data(call, skb, last, call->buffer, (21 + 3 + 6) * 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; bp = call->buffer; xdr_decode_AFSFetchStatus(&bp, &vnode->status, vnode, NULL); @@ -405,15 +391,12 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call, call->unmarshall++; case 5: - _debug("trailer"); - if (skb->len != 0) - return -EBADMSG; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; break; } - if (!last) - return 0; - if (call->count < PAGE_SIZE) { _debug("clear"); page = call->reply3; @@ -537,9 +520,8 @@ static int afs_deliver_fs_give_up_callbacks(struct afs_call *call, { _enter(",{%u},%d", skb->len, last); - if (skb->len > 0) - return -EBADMSG; /* shouldn't be any reply data */ - return 0; + /* shouldn't be any reply data */ + return afs_data_complete(call, skb, last); } /* @@ -622,15 +604,13 @@ static int afs_deliver_fs_create_vnode(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -721,15 +701,13 @@ static int afs_deliver_fs_remove(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -804,15 +782,13 @@ static int afs_deliver_fs_link(struct afs_call *call, { struct afs_vnode *dvnode = call->reply, *vnode = call->reply2; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -892,15 +868,13 @@ static int afs_deliver_fs_symlink(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -999,15 +973,13 @@ static int afs_deliver_fs_rename(struct afs_call *call, { struct afs_vnode *orig_dvnode = call->reply, *new_dvnode = call->reply2; const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -1105,20 +1077,13 @@ static int afs_deliver_fs_store_data(struct afs_call *call, { struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter(",,%u", last); - afs_transfer_reply(call, skb); - if (!last) { - _leave(" = 0 [more]"); - return 0; - } - - if (call->reply_size != call->reply_max) { - _leave(" = -EBADMSG [%u != %u]", - call->reply_size, call->reply_max); - return -EBADMSG; - } + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; @@ -1292,20 +1257,13 @@ static int afs_deliver_fs_store_status(struct afs_call *call, afs_dataversion_t *store_version; struct afs_vnode *vnode = call->reply; const __be32 *bp; + int ret; _enter(",,%u", last); - afs_transfer_reply(call, skb); - if (!last) { - _leave(" = 0 [more]"); - return 0; - } - - if (call->reply_size != call->reply_max) { - _leave(" = -EBADMSG [%u != %u]", - call->reply_size, call->reply_max); - return -EBADMSG; - } + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ store_version = NULL; @@ -1504,11 +1462,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, _debug("extract status"); ret = afs_extract_data(call, skb, last, call->buffer, 12 * 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; bp = call->buffer; xdr_decode_AFSFetchVolumeStatus(&bp, call->reply2); @@ -1518,11 +1473,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the volume name length */ case 2: ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("volname length: %u", call->count); @@ -1537,11 +1489,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, if (call->count > 0) { ret = afs_extract_data(call, skb, last, call->reply3, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; } p = call->reply3; @@ -1561,11 +1510,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, case 4: ret = afs_extract_data(call, skb, last, call->buffer, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->offset = 0; call->unmarshall++; @@ -1574,11 +1520,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the offline message length */ case 5: ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("offline msg length: %u", call->count); @@ -1593,11 +1536,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, if (call->count > 0) { ret = afs_extract_data(call, skb, last, call->reply3, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; } p = call->reply3; @@ -1617,11 +1557,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, case 7: ret = afs_extract_data(call, skb, last, call->buffer, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->offset = 0; call->unmarshall++; @@ -1630,11 +1567,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, /* extract the message of the day length */ case 8: ret = afs_extract_data(call, skb, last, &call->tmp, 4); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->count = ntohl(call->tmp); _debug("motd length: %u", call->count); @@ -1649,11 +1583,8 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, if (call->count > 0) { ret = afs_extract_data(call, skb, last, call->reply3, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; } p = call->reply3; @@ -1673,26 +1604,20 @@ static int afs_deliver_fs_get_volume_status(struct afs_call *call, case 10: ret = afs_extract_data(call, skb, last, call->buffer, call->count); - switch (ret) { - case 0: break; - case -EAGAIN: return 0; - default: return ret; - } + if (ret < 0) + return ret; call->offset = 0; call->unmarshall++; no_motd_padding: case 11: - _debug("trailer %d", skb->len); - if (skb->len != 0) - return -EBADMSG; + ret = afs_data_complete(call, skb, last); + if (ret < 0) + return ret; break; } - if (!last) - return 0; - _leave(" = 0 [done]"); return 0; } @@ -1764,15 +1689,13 @@ static int afs_deliver_fs_xxxx_lock(struct afs_call *call, struct sk_buff *skb, bool last) { const __be32 *bp; + int ret; _enter("{%u},{%u},%d", call->unmarshall, skb->len, last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ bp = call->buffer; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 71d5982312f3..df976b2a7f40 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -609,17 +609,29 @@ extern void afs_proc_cell_remove(struct afs_cell *); */ extern int afs_open_socket(void); extern void afs_close_socket(void); +extern void afs_data_consumed(struct afs_call *, struct sk_buff *); extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, const struct afs_wait_mode *); extern struct afs_call *afs_alloc_flat_call(const struct afs_call_type *, size_t, size_t); extern void afs_flat_call_destructor(struct afs_call *); -extern void afs_transfer_reply(struct afs_call *, struct sk_buff *); +extern int afs_transfer_reply(struct afs_call *, struct sk_buff *, bool); extern void afs_send_empty_reply(struct afs_call *); extern void afs_send_simple_reply(struct afs_call *, const void *, size_t); extern int afs_extract_data(struct afs_call *, struct sk_buff *, bool, void *, size_t); +static inline int afs_data_complete(struct afs_call *call, struct sk_buff *skb, + bool last) +{ + if (skb->len > 0) + return -EBADMSG; + afs_data_consumed(call, skb); + if (!last) + return -EAGAIN; + return 0; +} + /* * security.c */ diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 4832de84d52c..14d04c848465 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -150,10 +150,9 @@ void afs_close_socket(void) } /* - * note that the data in a socket buffer is now delivered and that the buffer - * should be freed + * Note that the data in a socket buffer is now consumed. */ -static void afs_data_delivered(struct sk_buff *skb) +void afs_data_consumed(struct afs_call *call, struct sk_buff *skb) { if (!skb) { _debug("DLVR NULL [%d]", atomic_read(&afs_outstanding_skbs)); @@ -161,9 +160,7 @@ static void afs_data_delivered(struct sk_buff *skb) } else { _debug("DLVR %p{%u} [%d]", skb, skb->mark, atomic_read(&afs_outstanding_skbs)); - if (atomic_dec_return(&afs_outstanding_skbs) == -1) - BUG(); - rxrpc_kernel_data_delivered(skb); + rxrpc_kernel_data_consumed(call->rxcall, skb); } } @@ -489,9 +486,15 @@ static void afs_deliver_to_call(struct afs_call *call) last = rxrpc_kernel_is_data_last(skb); ret = call->type->deliver(call, skb, last); switch (ret) { + case -EAGAIN: + if (last) { + _debug("short data"); + goto unmarshal_error; + } + break; case 0: - if (last && - call->state == AFS_CALL_AWAIT_REPLY) + ASSERT(last); + if (call->state == AFS_CALL_AWAIT_REPLY) call->state = AFS_CALL_COMPLETE; break; case -ENOTCONN: @@ -501,6 +504,7 @@ static void afs_deliver_to_call(struct afs_call *call) abort_code = RX_INVALID_OPERATION; goto do_abort; default: + unmarshal_error: abort_code = RXGEN_CC_UNMARSHAL; if (call->state != AFS_CALL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; @@ -511,9 +515,7 @@ static void afs_deliver_to_call(struct afs_call *call) call->state = AFS_CALL_ERROR; break; } - afs_data_delivered(skb); - skb = NULL; - continue; + break; case RXRPC_SKB_MARK_FINAL_ACK: _debug("Rcv ACK"); call->state = AFS_CALL_COMPLETE; @@ -685,15 +687,35 @@ static void afs_process_async_call(struct afs_call *call) } /* - * empty a socket buffer into a flat reply buffer + * Empty a socket buffer into a flat reply buffer. */ -void afs_transfer_reply(struct afs_call *call, struct sk_buff *skb) +int afs_transfer_reply(struct afs_call *call, struct sk_buff *skb, bool last) { size_t len = skb->len; - if (skb_copy_bits(skb, 0, call->buffer + call->reply_size, len) < 0) - BUG(); - call->reply_size += len; + if (len > call->reply_max - call->reply_size) { + _leave(" = -EBADMSG [%zu > %u]", + len, call->reply_max - call->reply_size); + return -EBADMSG; + } + + if (len > 0) { + if (skb_copy_bits(skb, 0, call->buffer + call->reply_size, + len) < 0) + BUG(); + call->reply_size += len; + } + + afs_data_consumed(call, skb); + if (!last) + return -EAGAIN; + + if (call->reply_size != call->reply_max) { + _leave(" = -EBADMSG [%u != %u]", + call->reply_size, call->reply_max); + return -EBADMSG; + } + return 0; } /* @@ -745,7 +767,8 @@ static void afs_collect_incoming_call(struct work_struct *work) } /* - * grab the operation ID from an incoming cache manager call + * Grab the operation ID from an incoming cache manager call. The socket + * buffer is discarded on error or if we don't yet have sufficient data. */ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb, bool last) @@ -766,12 +789,9 @@ static int afs_deliver_cm_op_id(struct afs_call *call, struct sk_buff *skb, call->offset += len; if (call->offset < 4) { - if (last) { - _leave(" = -EBADMSG [op ID short]"); - return -EBADMSG; - } - _leave(" = 0 [incomplete]"); - return 0; + afs_data_consumed(call, skb); + _leave(" = -EAGAIN"); + return -EAGAIN; } call->state = AFS_CALL_AWAIT_REQUEST; @@ -855,7 +875,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) } /* - * extract a piece of data from the received data socket buffers + * Extract a piece of data from the received data socket buffers. */ int afs_extract_data(struct afs_call *call, struct sk_buff *skb, bool last, void *buf, size_t count) @@ -873,10 +893,7 @@ int afs_extract_data(struct afs_call *call, struct sk_buff *skb, call->offset += len; if (call->offset < count) { - if (last) { - _leave(" = -EBADMSG [%d < %zu]", call->offset, count); - return -EBADMSG; - } + afs_data_consumed(call, skb); _leave(" = -EAGAIN"); return -EAGAIN; } diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c index 340afd0cd182..f94d1abdc3eb 100644 --- a/fs/afs/vlclient.c +++ b/fs/afs/vlclient.c @@ -64,16 +64,13 @@ static int afs_deliver_vl_get_entry_by_xxx(struct afs_call *call, struct afs_cache_vlocation *entry; __be32 *bp; u32 tmp; - int loop; + int loop, ret; _enter(",,%u", last); - afs_transfer_reply(call, skb); - if (!last) - return 0; - - if (call->reply_size != call->reply_max) - return -EBADMSG; + ret = afs_transfer_reply(call, skb, last); + if (ret < 0) + return ret; /* unmarshall the reply once we've received all of it */ entry = call->reply; diff --git a/fs/block_dev.c b/fs/block_dev.c index c3cdde87cc8c..08ae99343d92 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -249,7 +249,8 @@ struct super_block *freeze_bdev(struct block_device *bdev) * thaw_bdev drops it. */ sb = get_super(bdev); - drop_super(sb); + if (sb) + drop_super(sb); mutex_unlock(&bdev->bd_fsfreeze_mutex); return sb; } @@ -646,7 +647,7 @@ static struct dentry *bd_mount(struct file_system_type *fs_type, { struct dentry *dent; dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC); - if (dent) + if (!IS_ERR(dent)) dent->d_sb->s_iflags |= SB_I_CGROUPWB; return dent; } diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 2b88439c2ee8..455a6b2fd539 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -589,6 +589,7 @@ static void __merge_refs(struct list_head *head, int mode) list_del(&ref2->list); kmem_cache_free(btrfs_prelim_ref_cache, ref2); + cond_resched(); } } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2fe8f89091a3..eff3993c77b3 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1028,6 +1028,7 @@ struct btrfs_fs_info { struct btrfs_workqueue *qgroup_rescan_workers; struct completion qgroup_rescan_completion; struct btrfs_work qgroup_rescan_work; + bool qgroup_rescan_running; /* protected by qgroup_rescan_lock */ /* filesystem state */ unsigned long fs_state; @@ -1079,6 +1080,8 @@ struct btrfs_fs_info { struct list_head pinned_chunks; int creating_free_space_tree; + /* Used to record internally whether fs has been frozen */ + int fs_frozen; }; struct btrfs_subvolume_writers { @@ -2578,7 +2581,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 root_objectid, u64 owner, u64 offset, struct btrfs_key *ins); -int btrfs_reserve_extent(struct btrfs_root *root, u64 num_bytes, +int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index b6d210e7a993..ac02e041464b 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -541,7 +541,6 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_head *existing; struct btrfs_delayed_ref_head *head_ref = NULL; struct btrfs_delayed_ref_root *delayed_refs; - struct btrfs_qgroup_extent_record *qexisting; int count_mod = 1; int must_insert_reserved = 0; @@ -606,10 +605,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info, qrecord->num_bytes = num_bytes; qrecord->old_roots = NULL; - qexisting = btrfs_qgroup_insert_dirty_extent(fs_info, - delayed_refs, - qrecord); - if (qexisting) + if(btrfs_qgroup_insert_dirty_extent_nolock(fs_info, + delayed_refs, qrecord)) kfree(qrecord); } @@ -862,33 +859,6 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, return 0; } -int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, - u64 ref_root, u64 bytenr, u64 num_bytes) -{ - struct btrfs_delayed_ref_root *delayed_refs; - struct btrfs_delayed_ref_head *ref_head; - int ret = 0; - - if (!fs_info->quota_enabled || !is_fstree(ref_root)) - return 0; - - delayed_refs = &trans->transaction->delayed_refs; - - spin_lock(&delayed_refs->lock); - ref_head = find_ref_head(&delayed_refs->href_root, bytenr, 0); - if (!ref_head) { - ret = -ENOENT; - goto out; - } - WARN_ON(ref_head->qgroup_reserved || ref_head->qgroup_ref_root); - ref_head->qgroup_ref_root = ref_root; - ref_head->qgroup_reserved = num_bytes; -out: - spin_unlock(&delayed_refs->lock); - return ret; -} - int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 5fca9534a271..43f3629760e9 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -250,9 +250,6 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, u64 parent, u64 ref_root, u64 owner, u64 offset, u64 reserved, int action, struct btrfs_delayed_extent_op *extent_op); -int btrfs_add_delayed_qgroup_reserve(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, - u64 ref_root, u64 bytenr, u64 num_bytes); int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 59febfb8d04a..54bc8c7c6bcd 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -559,8 +559,29 @@ static noinline int check_leaf(struct btrfs_root *root, u32 nritems = btrfs_header_nritems(leaf); int slot; - if (nritems == 0) + if (nritems == 0) { + struct btrfs_root *check_root; + + key.objectid = btrfs_header_owner(leaf); + key.type = BTRFS_ROOT_ITEM_KEY; + key.offset = (u64)-1; + + check_root = btrfs_get_fs_root(root->fs_info, &key, false); + /* + * The only reason we also check NULL here is that during + * open_ctree() some roots has not yet been set up. + */ + if (!IS_ERR_OR_NULL(check_root)) { + /* if leaf is the root, then it's fine */ + if (leaf->start != + btrfs_root_bytenr(&check_root->root_item)) { + CORRUPT("non-root leaf's nritems is 0", + leaf, root, 0); + return -EIO; + } + } return 0; + } /* Check the 0 item */ if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) != @@ -612,6 +633,19 @@ static noinline int check_leaf(struct btrfs_root *root, return 0; } +static int check_node(struct btrfs_root *root, struct extent_buffer *node) +{ + unsigned long nr = btrfs_header_nritems(node); + + if (nr == 0 || nr > BTRFS_NODEPTRS_PER_BLOCK(root)) { + btrfs_crit(root->fs_info, + "corrupt node: block %llu root %llu nritems %lu", + node->start, root->objectid, nr); + return -EIO; + } + return 0; +} + static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, u64 phy_offset, struct page *page, u64 start, u64 end, int mirror) @@ -682,6 +716,9 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, ret = -EIO; } + if (found_level > 0 && check_node(root, eb)) + ret = -EIO; + if (!ret) set_extent_buffer_uptodate(eb); err: @@ -1618,8 +1655,8 @@ fail: return ret; } -static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, - u64 root_id) +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id) { struct btrfs_root *root; @@ -2298,6 +2335,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info) fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; fs_info->qgroup_ulist = NULL; + fs_info->qgroup_rescan_running = false; mutex_init(&fs_info->qgroup_rescan_lock); } @@ -2624,6 +2662,7 @@ int open_ctree(struct super_block *sb, atomic_set(&fs_info->qgroup_op_seq, 0); atomic_set(&fs_info->reada_works_cnt, 0); atomic64_set(&fs_info->tree_mod_seq, 0); + fs_info->fs_frozen = 0; fs_info->sb = sb; fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE; fs_info->metadata_ratio = 0; @@ -3739,8 +3778,15 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info, if (btrfs_root_refs(&root->root_item) == 0) synchronize_srcu(&fs_info->subvol_srcu); - if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) + if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) { btrfs_free_log(NULL, root); + if (root->reloc_root) { + free_extent_buffer(root->reloc_root->node); + free_extent_buffer(root->reloc_root->commit_root); + btrfs_put_fs_root(root->reloc_root); + root->reloc_root = NULL; + } + } if (root->free_ino_pinned) __btrfs_remove_free_space_cache(root->free_ino_pinned); @@ -3851,7 +3897,7 @@ void close_ctree(struct btrfs_root *root) smp_mb(); /* wait for the qgroup rescan worker to stop */ - btrfs_qgroup_wait_for_completion(fs_info); + btrfs_qgroup_wait_for_completion(fs_info, false); /* wait for the uuid_scan task to finish */ down(&fs_info->uuid_tree_rescan_sem); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index b3207a0e09f7..f19a982f5a4f 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -68,6 +68,8 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info, struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root, struct btrfs_key *location); int btrfs_init_fs_root(struct btrfs_root *root); +struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info, + u64 root_id); int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info, struct btrfs_root *root); void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 61b494e8e604..0450dc410533 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -60,21 +60,6 @@ enum { CHUNK_ALLOC_FORCE = 2, }; -/* - * Control how reservations are dealt with. - * - * RESERVE_FREE - freeing a reservation. - * RESERVE_ALLOC - allocating space and we need to update bytes_may_use for - * ENOSPC accounting - * RESERVE_ALLOC_NO_ACCOUNT - allocating space and we should not update - * bytes_may_use as the ENOSPC accounting is done elsewhere - */ -enum { - RESERVE_FREE = 0, - RESERVE_ALLOC = 1, - RESERVE_ALLOC_NO_ACCOUNT = 2, -}; - static int update_block_group(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, int alloc); @@ -104,9 +89,10 @@ static int find_next_key(struct btrfs_path *path, int level, struct btrfs_key *key); static void dump_space_info(struct btrfs_space_info *info, u64 bytes, int dump_block_groups); -static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, - int delalloc); +static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 ram_bytes, u64 num_bytes, int delalloc); +static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int delalloc); static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv, u64 num_bytes); int btrfs_pin_extent(struct btrfs_root *root, @@ -3501,7 +3487,6 @@ again: dcs = BTRFS_DC_SETUP; else if (ret == -ENOSPC) set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags); - btrfs_free_reserved_data_space(inode, 0, num_pages); out_put: iput(inode); @@ -4472,6 +4457,15 @@ void check_system_chunk(struct btrfs_trans_handle *trans, } } +/* + * If force is CHUNK_ALLOC_FORCE: + * - return 1 if it successfully allocates a chunk, + * - return errors including -ENOSPC otherwise. + * If force is NOT CHUNK_ALLOC_FORCE: + * - return 0 if it doesn't need to allocate a new chunk, + * - return 1 if it successfully allocates a chunk, + * - return errors including -ENOSPC otherwise. + */ static int do_chunk_alloc(struct btrfs_trans_handle *trans, struct btrfs_root *extent_root, u64 flags, int force) { @@ -4882,7 +4876,7 @@ static int flush_space(struct btrfs_root *root, btrfs_get_alloc_profile(root, 0), CHUNK_ALLOC_NO_FORCE); btrfs_end_transaction(trans, root); - if (ret == -ENOSPC) + if (ret > 0 || ret == -ENOSPC) ret = 0; break; case COMMIT_TRANS: @@ -6497,19 +6491,15 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) } /** - * btrfs_update_reserved_bytes - update the block_group and space info counters + * btrfs_add_reserved_bytes - update the block_group and space info counters * @cache: The cache we are manipulating + * @ram_bytes: The number of bytes of file content, and will be same to + * @num_bytes except for the compress path. * @num_bytes: The number of bytes in question - * @reserve: One of the reservation enums * @delalloc: The blocks are allocated for the delalloc write * - * This is called by the allocator when it reserves space, or by somebody who is - * freeing space that was never actually used on disk. For example if you - * reserve some space for a new leaf in transaction A and before transaction A - * commits you free that leaf, you call this with reserve set to 0 in order to - * clear the reservation. - * - * Metadata reservations should be called with RESERVE_ALLOC so we do the proper + * This is called by the allocator when it reserves space. Metadata + * reservations should be called with RESERVE_ALLOC so we do the proper * ENOSPC accounting. For data we handle the reservation through clearing the * delalloc bits in the io_tree. We have to do this since we could end up * allocating less disk space for the amount of data we have reserved in the @@ -6519,44 +6509,63 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg) * make the reservation and return -EAGAIN, otherwise this function always * succeeds. */ -static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, - u64 num_bytes, int reserve, int delalloc) +static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 ram_bytes, u64 num_bytes, int delalloc) { struct btrfs_space_info *space_info = cache->space_info; int ret = 0; spin_lock(&space_info->lock); spin_lock(&cache->lock); - if (reserve != RESERVE_FREE) { - if (cache->ro) { - ret = -EAGAIN; - } else { - cache->reserved += num_bytes; - space_info->bytes_reserved += num_bytes; - if (reserve == RESERVE_ALLOC) { - trace_btrfs_space_reservation(cache->fs_info, - "space_info", space_info->flags, - num_bytes, 0); - space_info->bytes_may_use -= num_bytes; - } - - if (delalloc) - cache->delalloc_bytes += num_bytes; - } + if (cache->ro) { + ret = -EAGAIN; } else { - if (cache->ro) - space_info->bytes_readonly += num_bytes; - cache->reserved -= num_bytes; - space_info->bytes_reserved -= num_bytes; + cache->reserved += num_bytes; + space_info->bytes_reserved += num_bytes; + trace_btrfs_space_reservation(cache->fs_info, + "space_info", space_info->flags, + ram_bytes, 0); + space_info->bytes_may_use -= ram_bytes; if (delalloc) - cache->delalloc_bytes -= num_bytes; + cache->delalloc_bytes += num_bytes; } spin_unlock(&cache->lock); spin_unlock(&space_info->lock); return ret; } +/** + * btrfs_free_reserved_bytes - update the block_group and space info counters + * @cache: The cache we are manipulating + * @num_bytes: The number of bytes in question + * @delalloc: The blocks are allocated for the delalloc write + * + * This is called by somebody who is freeing space that was never actually used + * on disk. For example if you reserve some space for a new leaf in transaction + * A and before transaction A commits you free that leaf, you call this with + * reserve set to 0 in order to clear the reservation. + */ + +static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache, + u64 num_bytes, int delalloc) +{ + struct btrfs_space_info *space_info = cache->space_info; + int ret = 0; + + spin_lock(&space_info->lock); + spin_lock(&cache->lock); + if (cache->ro) + space_info->bytes_readonly += num_bytes; + cache->reserved -= num_bytes; + space_info->bytes_reserved -= num_bytes; + + if (delalloc) + cache->delalloc_bytes -= num_bytes; + spin_unlock(&cache->lock); + spin_unlock(&space_info->lock); + return ret; +} void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, struct btrfs_root *root) { @@ -7191,7 +7200,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)); btrfs_add_free_space(cache, buf->start, buf->len); - btrfs_update_reserved_bytes(cache, buf->len, RESERVE_FREE, 0); + btrfs_free_reserved_bytes(cache, buf->len, 0); btrfs_put_block_group(cache); trace_btrfs_reserved_extent_free(root, buf->start, buf->len); pin = 0; @@ -7416,9 +7425,9 @@ btrfs_release_block_group(struct btrfs_block_group_cache *cache, * the free space extent currently. */ static noinline int find_free_extent(struct btrfs_root *orig_root, - u64 num_bytes, u64 empty_size, - u64 hint_byte, struct btrfs_key *ins, - u64 flags, int delalloc) + u64 ram_bytes, u64 num_bytes, u64 empty_size, + u64 hint_byte, struct btrfs_key *ins, + u64 flags, int delalloc) { int ret = 0; struct btrfs_root *root = orig_root->fs_info->extent_root; @@ -7430,8 +7439,6 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, struct btrfs_space_info *space_info; int loop = 0; int index = __get_raid_index(flags); - int alloc_type = (flags & BTRFS_BLOCK_GROUP_DATA) ? - RESERVE_ALLOC_NO_ACCOUNT : RESERVE_ALLOC; bool failed_cluster_refill = false; bool failed_alloc = false; bool use_cluster = true; @@ -7763,8 +7770,8 @@ checks: search_start - offset); BUG_ON(offset > search_start); - ret = btrfs_update_reserved_bytes(block_group, num_bytes, - alloc_type, delalloc); + ret = btrfs_add_reserved_bytes(block_group, ram_bytes, + num_bytes, delalloc); if (ret == -EAGAIN) { btrfs_add_free_space(block_group, offset, num_bytes); goto loop; @@ -7936,7 +7943,7 @@ again: up_read(&info->groups_sem); } -int btrfs_reserve_extent(struct btrfs_root *root, +int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes, u64 min_alloc_size, u64 empty_size, u64 hint_byte, struct btrfs_key *ins, int is_data, int delalloc) @@ -7948,8 +7955,8 @@ int btrfs_reserve_extent(struct btrfs_root *root, flags = btrfs_get_alloc_profile(root, is_data); again: WARN_ON(num_bytes < root->sectorsize); - ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins, - flags, delalloc); + ret = find_free_extent(root, ram_bytes, num_bytes, empty_size, + hint_byte, ins, flags, delalloc); if (!ret && !is_data) { btrfs_dec_block_group_reservations(root->fs_info, ins->objectid); @@ -7958,6 +7965,7 @@ again: num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, root->sectorsize); num_bytes = max(num_bytes, min_alloc_size); + ram_bytes = num_bytes; if (num_bytes == min_alloc_size) final_tried = true; goto again; @@ -7995,7 +8003,7 @@ static int __btrfs_free_reserved_extent(struct btrfs_root *root, if (btrfs_test_opt(root->fs_info, DISCARD)) ret = btrfs_discard_extent(root, start, len, NULL); btrfs_add_free_space(cache, start, len); - btrfs_update_reserved_bytes(cache, len, RESERVE_FREE, delalloc); + btrfs_free_reserved_bytes(cache, len, delalloc); trace_btrfs_reserved_extent_free(root, start, len); } @@ -8223,8 +8231,8 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans, if (!block_group) return -EINVAL; - ret = btrfs_update_reserved_bytes(block_group, ins->offset, - RESERVE_ALLOC_NO_ACCOUNT, 0); + ret = btrfs_add_reserved_bytes(block_group, ins->offset, + ins->offset, 0); BUG_ON(ret); /* logic error */ ret = alloc_reserved_file_extent(trans, root, 0, root_objectid, 0, owner, offset, ins, 1); @@ -8368,7 +8376,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans, if (IS_ERR(block_rsv)) return ERR_CAST(block_rsv); - ret = btrfs_reserve_extent(root, blocksize, blocksize, + ret = btrfs_reserve_extent(root, blocksize, blocksize, blocksize, empty_size, hint, &ins, 0, 0); if (ret) goto out_unuse; @@ -8521,35 +8529,6 @@ reada: wc->reada_slot = slot; } -/* - * These may not be seen by the usual inc/dec ref code so we have to - * add them here. - */ -static int record_one_subtree_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, u64 bytenr, - u64 num_bytes) -{ - struct btrfs_qgroup_extent_record *qrecord; - struct btrfs_delayed_ref_root *delayed_refs; - - qrecord = kmalloc(sizeof(*qrecord), GFP_NOFS); - if (!qrecord) - return -ENOMEM; - - qrecord->bytenr = bytenr; - qrecord->num_bytes = num_bytes; - qrecord->old_roots = NULL; - - delayed_refs = &trans->transaction->delayed_refs; - spin_lock(&delayed_refs->lock); - if (btrfs_qgroup_insert_dirty_extent(trans->fs_info, - delayed_refs, qrecord)) - kfree(qrecord); - spin_unlock(&delayed_refs->lock); - - return 0; -} - static int account_leaf_items(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *eb) @@ -8583,7 +8562,8 @@ static int account_leaf_items(struct btrfs_trans_handle *trans, num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi); - ret = record_one_subtree_extent(trans, root, bytenr, num_bytes); + ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info, + bytenr, num_bytes, GFP_NOFS); if (ret) return ret; } @@ -8732,8 +8712,9 @@ walk_down: btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); path->locks[level] = BTRFS_READ_LOCK_BLOCKING; - ret = record_one_subtree_extent(trans, root, child_bytenr, - root->nodesize); + ret = btrfs_qgroup_insert_dirty_extent(trans, + root->fs_info, child_bytenr, + root->nodesize, GFP_NOFS); if (ret) goto out; } @@ -9906,6 +9887,7 @@ static int find_first_block_group(struct btrfs_root *root, } else { ret = 0; } + free_extent_map(em); goto out; } path->slots[0]++; @@ -9942,6 +9924,7 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info) block_group->iref = 0; block_group->inode = NULL; spin_unlock(&block_group->lock); + ASSERT(block_group->io_ctl.inode == NULL); iput(inode); last = block_group->key.objectid + block_group->key.offset; btrfs_put_block_group(block_group); @@ -9999,6 +9982,10 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) free_excluded_extents(info->extent_root, block_group); btrfs_remove_free_space_cache(block_group); + ASSERT(list_empty(&block_group->dirty_list)); + ASSERT(list_empty(&block_group->io_list)); + ASSERT(list_empty(&block_group->bg_list)); + ASSERT(atomic_read(&block_group->count) == 1); btrfs_put_block_group(block_group); spin_lock(&info->block_group_cache_lock); diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index bc2729a7612d..28cd88fccc7e 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -20,6 +20,7 @@ #define EXTENT_DAMAGED (1U << 14) #define EXTENT_NORESERVE (1U << 15) #define EXTENT_QGROUP_RESERVED (1U << 16) +#define EXTENT_CLEAR_DATA_RESV (1U << 17) #define EXTENT_IOBITS (EXTENT_LOCKED | EXTENT_WRITEBACK) #define EXTENT_CTLBITS (EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC) diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 9404121fd5f7..fea31a4a6e36 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2033,6 +2033,14 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) */ clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags); + /* + * An ordered extent might have started before and completed + * already with io errors, in which case the inode was not + * updated and we end up here. So check the inode's mapping + * flags for any errors that might have happened while doing + * writeback of file data. + */ + ret = btrfs_inode_check_errors(inode); inode_unlock(inode); goto out; } @@ -2062,7 +2070,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) } trans->sync = true; - btrfs_init_log_ctx(&ctx); + btrfs_init_log_ctx(&ctx, inode); ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx); if (ret < 0) { @@ -2667,6 +2675,7 @@ static long btrfs_fallocate(struct file *file, int mode, alloc_start = round_down(offset, blocksize); alloc_end = round_up(offset + len, blocksize); + cur_offset = alloc_start; /* Make sure we aren't being give some crap mode */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) @@ -2759,7 +2768,6 @@ static long btrfs_fallocate(struct file *file, int mode, /* First, check if we exceed the qgroup limit */ INIT_LIST_HEAD(&reserve_list); - cur_offset = alloc_start; while (1) { em = btrfs_get_extent(inode, NULL, 0, cur_offset, alloc_end - cur_offset, 0); @@ -2786,6 +2794,14 @@ static long btrfs_fallocate(struct file *file, int mode, last_byte - cur_offset); if (ret < 0) break; + } else { + /* + * Do not need to reserve unwritten extent for this + * range, free reserved data space first, otherwise + * it'll result in false ENOSPC error. + */ + btrfs_free_reserved_data_space(inode, cur_offset, + last_byte - cur_offset); } free_extent_map(em); cur_offset = last_byte; @@ -2803,6 +2819,9 @@ static long btrfs_fallocate(struct file *file, int mode, range->start, range->len, 1 << inode->i_blkbits, offset + len, &alloc_hint); + else + btrfs_free_reserved_data_space(inode, range->start, + range->len); list_del(&range->list); kfree(range); } @@ -2837,18 +2856,11 @@ out_unlock: unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end, &cached_state, GFP_KERNEL); out: - /* - * As we waited the extent range, the data_rsv_map must be empty - * in the range, as written data range will be released from it. - * And for prealloacted extent, it will also be released when - * its metadata is written. - * So this is completely used as cleanup. - */ - btrfs_qgroup_free_data(inode, alloc_start, alloc_end - alloc_start); inode_unlock(inode); /* Let go of our reservation. */ - btrfs_free_reserved_data_space(inode, alloc_start, - alloc_end - alloc_start); + if (ret != 0) + btrfs_free_reserved_data_space(inode, alloc_start, + alloc_end - cur_offset); return ret; } diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index aa6fabaee72e..359ee861b5a4 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -495,10 +495,9 @@ again: ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc, prealloc, prealloc, &alloc_hint); if (ret) { - btrfs_delalloc_release_space(inode, 0, prealloc); + btrfs_delalloc_release_metadata(inode, prealloc); goto out_put; } - btrfs_free_reserved_data_space(inode, 0, prealloc); ret = btrfs_write_out_ino_cache(root, trans, path, inode); out_put: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2f5975954ccf..e6811c42e41e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -566,6 +566,8 @@ cont: PAGE_SET_WRITEBACK | page_error_op | PAGE_END_WRITEBACK); + btrfs_free_reserved_data_space_noquota(inode, start, + end - start + 1); goto free_pages_out; } } @@ -742,7 +744,7 @@ retry: lock_extent(io_tree, async_extent->start, async_extent->start + async_extent->ram_size - 1); - ret = btrfs_reserve_extent(root, + ret = btrfs_reserve_extent(root, async_extent->ram_size, async_extent->compressed_size, async_extent->compressed_size, 0, alloc_hint, &ins, 1, 1); @@ -969,7 +971,8 @@ static noinline int cow_file_range(struct inode *inode, EXTENT_DEFRAG, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK); - + btrfs_free_reserved_data_space_noquota(inode, start, + end - start + 1); *nr_written = *nr_written + (end - start + PAGE_SIZE) / PAGE_SIZE; *page_started = 1; @@ -989,7 +992,7 @@ static noinline int cow_file_range(struct inode *inode, unsigned long op; cur_alloc_size = disk_num_bytes; - ret = btrfs_reserve_extent(root, cur_alloc_size, + ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size, root->sectorsize, 0, alloc_hint, &ins, 1, 1); if (ret < 0) @@ -1489,8 +1492,10 @@ out_check: extent_clear_unlock_delalloc(inode, cur_offset, cur_offset + num_bytes - 1, locked_page, EXTENT_LOCKED | - EXTENT_DELALLOC, PAGE_UNLOCK | - PAGE_SET_PRIVATE2); + EXTENT_DELALLOC | + EXTENT_CLEAR_DATA_RESV, + PAGE_UNLOCK | PAGE_SET_PRIVATE2); + if (!nolock && nocow) btrfs_end_write_no_snapshoting(root); cur_offset = extent_end; @@ -1807,7 +1812,9 @@ static void btrfs_clear_bit_hook(struct inode *inode, return; if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID - && do_list && !(state->state & EXTENT_NORESERVE)) + && do_list && !(state->state & EXTENT_NORESERVE) + && (*bits & (EXTENT_DO_ACCOUNTING | + EXTENT_CLEAR_DATA_RESV))) btrfs_free_reserved_data_space_noquota(inode, state->start, len); @@ -3435,10 +3442,10 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) found_key.offset = 0; inode = btrfs_iget(root->fs_info->sb, &found_key, root, NULL); ret = PTR_ERR_OR_ZERO(inode); - if (ret && ret != -ESTALE) + if (ret && ret != -ENOENT) goto out; - if (ret == -ESTALE && root == root->fs_info->tree_root) { + if (ret == -ENOENT && root == root->fs_info->tree_root) { struct btrfs_root *dead_root; struct btrfs_fs_info *fs_info = root->fs_info; int is_dead_root = 0; @@ -3474,7 +3481,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) * Inode is already gone but the orphan item is still there, * kill the orphan item. */ - if (ret == -ESTALE) { + if (ret == -ENOENT) { trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); @@ -3633,7 +3640,7 @@ static noinline int acls_after_inode_item(struct extent_buffer *leaf, /* * read an inode from the btree into the in-memory inode */ -static void btrfs_read_locked_inode(struct inode *inode) +static int btrfs_read_locked_inode(struct inode *inode) { struct btrfs_path *path; struct extent_buffer *leaf; @@ -3652,14 +3659,19 @@ static void btrfs_read_locked_inode(struct inode *inode) filled = true; path = btrfs_alloc_path(); - if (!path) + if (!path) { + ret = -ENOMEM; goto make_bad; + } memcpy(&location, &BTRFS_I(inode)->location, sizeof(location)); ret = btrfs_lookup_inode(NULL, root, path, &location, 0); - if (ret) + if (ret) { + if (ret > 0) + ret = -ENOENT; goto make_bad; + } leaf = path->nodes[0]; @@ -3812,11 +3824,12 @@ cache_acl: } btrfs_update_iflags(inode); - return; + return 0; make_bad: btrfs_free_path(path); make_bad_inode(inode); + return ret; } /* @@ -4204,6 +4217,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) int err = 0; struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_trans_handle *trans; + u64 last_unlink_trans; if (inode->i_size > BTRFS_EMPTY_DIR_SIZE) return -ENOTEMPTY; @@ -4226,11 +4240,27 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) if (err) goto out; + last_unlink_trans = BTRFS_I(inode)->last_unlink_trans; + /* now the directory is empty */ err = btrfs_unlink_inode(trans, root, dir, d_inode(dentry), dentry->d_name.name, dentry->d_name.len); - if (!err) + if (!err) { btrfs_i_size_write(inode, 0); + /* + * Propagate the last_unlink_trans value of the deleted dir to + * its parent directory. This is to prevent an unrecoverable + * log tree in the case we do something like this: + * 1) create dir foo + * 2) create snapshot under dir foo + * 3) delete the snapshot + * 4) rmdir foo + * 5) mkdir foo + * 6) fsync foo or some file inside foo + */ + if (last_unlink_trans >= trans->transid) + BTRFS_I(dir)->last_unlink_trans = last_unlink_trans; + } out: btrfs_end_transaction(trans, root); btrfs_btree_balance_dirty(root); @@ -5606,7 +5636,9 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, return ERR_PTR(-ENOMEM); if (inode->i_state & I_NEW) { - btrfs_read_locked_inode(inode); + int ret; + + ret = btrfs_read_locked_inode(inode); if (!is_bad_inode(inode)) { inode_tree_add(inode); unlock_new_inode(inode); @@ -5615,7 +5647,8 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location, } else { unlock_new_inode(inode); iput(inode); - inode = ERR_PTR(-ESTALE); + ASSERT(ret < 0); + inode = ERR_PTR(ret < 0 ? ret : -ESTALE); } } @@ -7225,7 +7258,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode, int ret; alloc_hint = get_extent_allocation_hint(inode, start, len); - ret = btrfs_reserve_extent(root, len, root->sectorsize, 0, + ret = btrfs_reserve_extent(root, len, len, root->sectorsize, 0, alloc_hint, &ins, 1, 1); if (ret) return ERR_PTR(ret); @@ -7725,6 +7758,13 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, ret = PTR_ERR(em2); goto unlock_err; } + /* + * For inode marked NODATACOW or extent marked PREALLOC, + * use the existing or preallocated extent, so does not + * need to adjust btrfs_space_info's bytes_may_use. + */ + btrfs_free_reserved_data_space_noquota(inode, + start, len); goto unlock; } } @@ -7759,7 +7799,6 @@ unlock: i_size_write(inode, start + len); adjust_dio_outstanding_extents(inode, dio_data, len); - btrfs_free_reserved_data_space(inode, start, len); WARN_ON(dio_data->reserve < len); dio_data->reserve -= len; dio_data->unsubmitted_oe_range_end = start + len; @@ -10280,6 +10319,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, u64 last_alloc = (u64)-1; int ret = 0; bool own_trans = true; + u64 end = start + num_bytes - 1; if (trans) own_trans = false; @@ -10301,8 +10341,8 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode, * sized chunks. */ cur_bytes = min(cur_bytes, last_alloc); - ret = btrfs_reserve_extent(root, cur_bytes, min_size, 0, - *alloc_hint, &ins, 1, 0); + ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes, + min_size, 0, *alloc_hint, &ins, 1, 0); if (ret) { if (own_trans) btrfs_end_transaction(trans, root); @@ -10388,6 +10428,9 @@ next: if (own_trans) btrfs_end_transaction(trans, root); } + if (cur_offset < end) + btrfs_free_reserved_data_space(inode, cur_offset, + end - cur_offset + 1); return ret; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 14ed1e9e6bc8..b2a2da5893af 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5084,7 +5084,7 @@ static long btrfs_ioctl_quota_rescan_wait(struct file *file, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; - return btrfs_qgroup_wait_for_completion(root->fs_info); + return btrfs_qgroup_wait_for_completion(root->fs_info, true); } static long _btrfs_ioctl_set_received_subvol(struct file *file, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 93ee1c18ef9d..8db2e29fdcf4 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -995,7 +995,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, goto out; fs_info->quota_enabled = 0; fs_info->pending_quota_state = 0; - btrfs_qgroup_wait_for_completion(fs_info); + btrfs_qgroup_wait_for_completion(fs_info, false); spin_lock(&fs_info->qgroup_lock); quota_root = fs_info->quota_root; fs_info->quota_root = NULL; @@ -1453,10 +1453,9 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, return ret; } -struct btrfs_qgroup_extent_record * -btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record) +int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record) { struct rb_node **p = &delayed_refs->dirty_extent_root.rb_node; struct rb_node *parent_node = NULL; @@ -1475,12 +1474,42 @@ btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, else if (bytenr > entry->bytenr) p = &(*p)->rb_right; else - return entry; + return 1; } rb_link_node(&record->node, parent_node, p); rb_insert_color(&record->node, &delayed_refs->dirty_extent_root); - return NULL; + return 0; +} + +int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, + gfp_t gfp_flag) +{ + struct btrfs_qgroup_extent_record *record; + struct btrfs_delayed_ref_root *delayed_refs; + int ret; + + if (!fs_info->quota_enabled || bytenr == 0 || num_bytes == 0) + return 0; + if (WARN_ON(trans == NULL)) + return -EINVAL; + record = kmalloc(sizeof(*record), gfp_flag); + if (!record) + return -ENOMEM; + + delayed_refs = &trans->transaction->delayed_refs; + record->bytenr = bytenr; + record->num_bytes = num_bytes; + record->old_roots = NULL; + + spin_lock(&delayed_refs->lock); + ret = btrfs_qgroup_insert_dirty_extent_nolock(fs_info, delayed_refs, + record); + spin_unlock(&delayed_refs->lock); + if (ret > 0) + kfree(record); + return 0; } #define UPDATE_NEW 0 @@ -2303,6 +2332,10 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) int err = -ENOMEM; int ret = 0; + mutex_lock(&fs_info->qgroup_rescan_lock); + fs_info->qgroup_rescan_running = true; + mutex_unlock(&fs_info->qgroup_rescan_lock); + path = btrfs_alloc_path(); if (!path) goto out; @@ -2369,6 +2402,9 @@ out: } done: + mutex_lock(&fs_info->qgroup_rescan_lock); + fs_info->qgroup_rescan_running = false; + mutex_unlock(&fs_info->qgroup_rescan_lock); complete_all(&fs_info->qgroup_rescan_completion); } @@ -2487,20 +2523,26 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info) return 0; } -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info) +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible) { int running; int ret = 0; mutex_lock(&fs_info->qgroup_rescan_lock); spin_lock(&fs_info->qgroup_lock); - running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN; + running = fs_info->qgroup_rescan_running; spin_unlock(&fs_info->qgroup_lock); mutex_unlock(&fs_info->qgroup_rescan_lock); - if (running) + if (!running) + return 0; + + if (interruptible) ret = wait_for_completion_interruptible( &fs_info->qgroup_rescan_completion); + else + wait_for_completion(&fs_info->qgroup_rescan_completion); return ret; } diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h index 710887c06aaf..1bc64c864b62 100644 --- a/fs/btrfs/qgroup.h +++ b/fs/btrfs/qgroup.h @@ -46,7 +46,8 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info); void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info); -int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info); +int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info, + bool interruptible); int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, u64 src, u64 dst); int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, @@ -63,10 +64,35 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info); struct btrfs_delayed_extent_op; int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info); -struct btrfs_qgroup_extent_record * -btrfs_qgroup_insert_dirty_extent(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - struct btrfs_qgroup_extent_record *record); +/* + * Insert one dirty extent record into @delayed_refs, informing qgroup to + * account that extent at commit trans time. + * + * No lock version, caller must acquire delayed ref lock and allocate memory. + * + * Return 0 for success insert + * Return >0 for existing record, caller can free @record safely. + * Error is not possible + */ +int btrfs_qgroup_insert_dirty_extent_nolock( + struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_qgroup_extent_record *record); + +/* + * Insert one dirty extent record into @delayed_refs, informing qgroup to + * account that extent at commit trans time. + * + * Better encapsulated version. + * + * Return 0 if the operation is done. + * Return <0 for error, like memory allocation failure or invalid parameter + * (NULL trans) + */ +int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes, + gfp_t gfp_flag); + int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, struct btrfs_fs_info *fs_info, diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index b26a5aea41b4..8a2c2a07987b 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -31,6 +31,7 @@ #include "async-thread.h" #include "free-space-cache.h" #include "inode-map.h" +#include "qgroup.h" /* * backref_node, mapping_node and tree_block start with this @@ -3037,15 +3038,19 @@ int prealloc_file_extent_cluster(struct inode *inode, u64 num_bytes; int nr = 0; int ret = 0; + u64 prealloc_start = cluster->start - offset; + u64 prealloc_end = cluster->end - offset; + u64 cur_offset; BUG_ON(cluster->start != cluster->boundary[0]); inode_lock(inode); - ret = btrfs_check_data_free_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + ret = btrfs_check_data_free_space(inode, prealloc_start, + prealloc_end + 1 - prealloc_start); if (ret) goto out; + cur_offset = prealloc_start; while (nr < cluster->nr) { start = cluster->boundary[nr] - offset; if (nr + 1 < cluster->nr) @@ -3055,16 +3060,21 @@ int prealloc_file_extent_cluster(struct inode *inode, lock_extent(&BTRFS_I(inode)->io_tree, start, end); num_bytes = end + 1 - start; + if (cur_offset < start) + btrfs_free_reserved_data_space(inode, cur_offset, + start - cur_offset); ret = btrfs_prealloc_file_range(inode, 0, start, num_bytes, num_bytes, end + 1, &alloc_hint); + cur_offset = end + 1; unlock_extent(&BTRFS_I(inode)->io_tree, start, end); if (ret) break; nr++; } - btrfs_free_reserved_data_space(inode, cluster->start, - cluster->end + 1 - cluster->start); + if (cur_offset < prealloc_end) + btrfs_free_reserved_data_space(inode, cur_offset, + prealloc_end + 1 - cur_offset); out: inode_unlock(inode); return ret; @@ -3916,6 +3926,90 @@ int prepare_to_relocate(struct reloc_control *rc) return 0; } +/* + * Qgroup fixer for data chunk relocation. + * The data relocation is done in the following steps + * 1) Copy data extents into data reloc tree + * 2) Create tree reloc tree(special snapshot) for related subvolumes + * 3) Modify file extents in tree reloc tree + * 4) Merge tree reloc tree with original fs tree, by swapping tree blocks + * + * The problem is, data and tree reloc tree are not accounted to qgroup, + * and 4) will only info qgroup to track tree blocks change, not file extents + * in the tree blocks. + * + * The good news is, related data extents are all in data reloc tree, so we + * only need to info qgroup to track all file extents in data reloc tree + * before commit trans. + */ +static int qgroup_fix_relocated_data_extents(struct btrfs_trans_handle *trans, + struct reloc_control *rc) +{ + struct btrfs_fs_info *fs_info = rc->extent_root->fs_info; + struct inode *inode = rc->data_inode; + struct btrfs_root *data_reloc_root = BTRFS_I(inode)->root; + struct btrfs_path *path; + struct btrfs_key key; + int ret = 0; + + if (!fs_info->quota_enabled) + return 0; + + /* + * Only for stage where we update data pointers the qgroup fix is + * valid. + * For MOVING_DATA stage, we will miss the timing of swapping tree + * blocks, and won't fix it. + */ + if (!(rc->stage == UPDATE_DATA_PTRS && rc->extents_found)) + return 0; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + key.objectid = btrfs_ino(inode); + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = 0; + + ret = btrfs_search_slot(NULL, data_reloc_root, &key, path, 0, 0); + if (ret < 0) + goto out; + + lock_extent(&BTRFS_I(inode)->io_tree, 0, (u64)-1); + while (1) { + struct btrfs_file_extent_item *fi; + + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid > btrfs_ino(inode)) + break; + if (key.type != BTRFS_EXTENT_DATA_KEY) + goto next; + fi = btrfs_item_ptr(path->nodes[0], path->slots[0], + struct btrfs_file_extent_item); + if (btrfs_file_extent_type(path->nodes[0], fi) != + BTRFS_FILE_EXTENT_REG) + goto next; + ret = btrfs_qgroup_insert_dirty_extent(trans, fs_info, + btrfs_file_extent_disk_bytenr(path->nodes[0], fi), + btrfs_file_extent_disk_num_bytes(path->nodes[0], fi), + GFP_NOFS); + if (ret < 0) + break; +next: + ret = btrfs_next_item(data_reloc_root, path); + if (ret < 0) + break; + if (ret > 0) { + ret = 0; + break; + } + } + unlock_extent(&BTRFS_I(inode)->io_tree, 0 , (u64)-1); +out: + btrfs_free_path(path); + return ret; +} + static noinline_for_stack int relocate_block_group(struct reloc_control *rc) { struct rb_root blocks = RB_ROOT; @@ -4102,10 +4196,16 @@ restart: /* get rid of pinned extents */ trans = btrfs_join_transaction(rc->extent_root); - if (IS_ERR(trans)) + if (IS_ERR(trans)) { err = PTR_ERR(trans); - else - btrfs_commit_transaction(trans, rc->extent_root); + goto out_free; + } + err = qgroup_fix_relocated_data_extents(trans, rc); + if (err < 0) { + btrfs_abort_transaction(trans, err); + goto out_free; + } + btrfs_commit_transaction(trans, rc->extent_root); out_free: btrfs_free_block_rsv(rc->extent_root, rc->block_rsv); btrfs_free_path(path); @@ -4468,10 +4568,16 @@ int btrfs_recover_relocation(struct btrfs_root *root) unset_reloc_control(rc); trans = btrfs_join_transaction(rc->extent_root); - if (IS_ERR(trans)) + if (IS_ERR(trans)) { err = PTR_ERR(trans); - else - err = btrfs_commit_transaction(trans, rc->extent_root); + goto out_free; + } + err = qgroup_fix_relocated_data_extents(trans, rc); + if (err < 0) { + btrfs_abort_transaction(trans, err); + goto out_free; + } + err = btrfs_commit_transaction(trans, rc->extent_root); out_free: kfree(rc); out: diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 7fd7e1830cfe..091296062456 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -272,6 +272,23 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) root_key.objectid = key.offset; key.offset++; + /* + * The root might have been inserted already, as before we look + * for orphan roots, log replay might have happened, which + * triggers a transaction commit and qgroup accounting, which + * in turn reads and inserts fs roots while doing backref + * walking. + */ + root = btrfs_lookup_fs_root(tree_root->fs_info, + root_key.objectid); + if (root) { + WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, + &root->state)); + if (btrfs_root_refs(&root->root_item) == 0) + btrfs_add_dead_root(root); + continue; + } + root = btrfs_read_fs_root(tree_root, &root_key); err = PTR_ERR_OR_ZERO(root); if (err && err != -ENOENT) { @@ -310,16 +327,8 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root) set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state); err = btrfs_insert_fs_root(root->fs_info, root); - /* - * The root might have been inserted already, as before we look - * for orphan roots, log replay might have happened, which - * triggers a transaction commit and qgroup accounting, which - * in turn reads and inserts fs roots while doing backref - * walking. - */ - if (err == -EEXIST) - err = 0; if (err) { + BUG_ON(err == -EEXIST); btrfs_free_fs_root(root); break; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index b71dd298385c..efe129fe2678 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -231,7 +231,6 @@ struct pending_dir_move { u64 parent_ino; u64 ino; u64 gen; - bool is_orphan; struct list_head update_refs; }; @@ -274,6 +273,39 @@ struct name_cache_entry { char name[]; }; +static void inconsistent_snapshot_error(struct send_ctx *sctx, + enum btrfs_compare_tree_result result, + const char *what) +{ + const char *result_string; + + switch (result) { + case BTRFS_COMPARE_TREE_NEW: + result_string = "new"; + break; + case BTRFS_COMPARE_TREE_DELETED: + result_string = "deleted"; + break; + case BTRFS_COMPARE_TREE_CHANGED: + result_string = "updated"; + break; + case BTRFS_COMPARE_TREE_SAME: + ASSERT(0); + result_string = "unchanged"; + break; + default: + ASSERT(0); + result_string = "unexpected"; + } + + btrfs_err(sctx->send_root->fs_info, + "Send: inconsistent snapshot, found %s %s for inode %llu without updated inode item, send root is %llu, parent root is %llu", + result_string, what, sctx->cmp_key->objectid, + sctx->send_root->root_key.objectid, + (sctx->parent_root ? + sctx->parent_root->root_key.objectid : 0)); +} + static int is_waiting_for_move(struct send_ctx *sctx, u64 ino); static struct waiting_dir_move * @@ -1861,7 +1893,8 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen, * was already unlinked/moved, so we can safely assume that we will not * overwrite anything at this point in time. */ - if (other_inode > sctx->send_progress) { + if (other_inode > sctx->send_progress || + is_waiting_for_move(sctx, other_inode)) { ret = get_inode_info(sctx->parent_root, other_inode, NULL, who_gen, NULL, NULL, NULL, NULL); if (ret < 0) @@ -2502,6 +2535,8 @@ verbose_printk("btrfs: send_utimes %llu\n", ino); key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, sctx->send_root, &key, path, 0, 0); + if (ret > 0) + ret = -ENOENT; if (ret < 0) goto out; @@ -2947,6 +2982,10 @@ static int can_rmdir(struct send_ctx *sctx, u64 dir, u64 dir_gen, } if (loc.objectid > send_progress) { + struct orphan_dir_info *odi; + + odi = get_orphan_dir_info(sctx, dir); + free_orphan_dir_info(sctx, odi); ret = 0; goto out; } @@ -3047,7 +3086,6 @@ static int add_pending_dir_move(struct send_ctx *sctx, pm->parent_ino = parent_ino; pm->ino = ino; pm->gen = ino_gen; - pm->is_orphan = is_orphan; INIT_LIST_HEAD(&pm->list); INIT_LIST_HEAD(&pm->update_refs); RB_CLEAR_NODE(&pm->node); @@ -3113,6 +3151,48 @@ static struct pending_dir_move *get_pending_dir_moves(struct send_ctx *sctx, return NULL; } +static int path_loop(struct send_ctx *sctx, struct fs_path *name, + u64 ino, u64 gen, u64 *ancestor_ino) +{ + int ret = 0; + u64 parent_inode = 0; + u64 parent_gen = 0; + u64 start_ino = ino; + + *ancestor_ino = 0; + while (ino != BTRFS_FIRST_FREE_OBJECTID) { + fs_path_reset(name); + + if (is_waiting_for_rm(sctx, ino)) + break; + if (is_waiting_for_move(sctx, ino)) { + if (*ancestor_ino == 0) + *ancestor_ino = ino; + ret = get_first_ref(sctx->parent_root, ino, + &parent_inode, &parent_gen, name); + } else { + ret = __get_cur_name_and_parent(sctx, ino, gen, + &parent_inode, + &parent_gen, name); + if (ret > 0) { + ret = 0; + break; + } + } + if (ret < 0) + break; + if (parent_inode == start_ino) { + ret = 1; + if (*ancestor_ino == 0) + *ancestor_ino = ino; + break; + } + ino = parent_inode; + gen = parent_gen; + } + return ret; +} + static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) { struct fs_path *from_path = NULL; @@ -3123,6 +3203,8 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) u64 parent_ino, parent_gen; struct waiting_dir_move *dm = NULL; u64 rmdir_ino = 0; + u64 ancestor; + bool is_orphan; int ret; name = fs_path_alloc(); @@ -3135,9 +3217,10 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) dm = get_waiting_dir_move(sctx, pm->ino); ASSERT(dm); rmdir_ino = dm->rmdir_ino; + is_orphan = dm->orphanized; free_waiting_dir_move(sctx, dm); - if (pm->is_orphan) { + if (is_orphan) { ret = gen_unique_name(sctx, pm->ino, pm->gen, from_path); } else { @@ -3155,6 +3238,24 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) goto out; sctx->send_progress = sctx->cur_ino + 1; + ret = path_loop(sctx, name, pm->ino, pm->gen, &ancestor); + if (ret < 0) + goto out; + if (ret) { + LIST_HEAD(deleted_refs); + ASSERT(ancestor > BTRFS_FIRST_FREE_OBJECTID); + ret = add_pending_dir_move(sctx, pm->ino, pm->gen, ancestor, + &pm->update_refs, &deleted_refs, + is_orphan); + if (ret < 0) + goto out; + if (rmdir_ino) { + dm = get_waiting_dir_move(sctx, pm->ino); + ASSERT(dm); + dm->rmdir_ino = rmdir_ino; + } + goto out; + } fs_path_reset(name); to_path = name; name = NULL; @@ -3174,7 +3275,7 @@ static int apply_dir_move(struct send_ctx *sctx, struct pending_dir_move *pm) /* already deleted */ goto finish; } - ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino + 1); + ret = can_rmdir(sctx, rmdir_ino, odi->gen, sctx->cur_ino); if (ret < 0) goto out; if (!ret) @@ -3204,8 +3305,18 @@ finish: * and old parent(s). */ list_for_each_entry(cur, &pm->update_refs, list) { - if (cur->dir == rmdir_ino) + /* + * The parent inode might have been deleted in the send snapshot + */ + ret = get_inode_info(sctx->send_root, cur->dir, NULL, + NULL, NULL, NULL, NULL, NULL); + if (ret == -ENOENT) { + ret = 0; continue; + } + if (ret < 0) + goto out; + ret = send_utimes(sctx, cur->dir, cur->dir_gen); if (ret < 0) goto out; @@ -3325,6 +3436,7 @@ static int wait_for_dest_dir_move(struct send_ctx *sctx, u64 left_gen; u64 right_gen; int ret = 0; + struct waiting_dir_move *wdm; if (RB_EMPTY_ROOT(&sctx->waiting_dir_moves)) return 0; @@ -3383,7 +3495,8 @@ static int wait_for_dest_dir_move(struct send_ctx *sctx, goto out; } - if (is_waiting_for_move(sctx, di_key.objectid)) { + wdm = get_waiting_dir_move(sctx, di_key.objectid); + if (wdm && !wdm->orphanized) { ret = add_pending_dir_move(sctx, sctx->cur_ino, sctx->cur_inode_gen, @@ -3470,7 +3583,8 @@ static int wait_for_parent_move(struct send_ctx *sctx, ret = is_ancestor(sctx->parent_root, sctx->cur_ino, sctx->cur_inode_gen, ino, path_before); - break; + if (ret) + break; } fs_path_reset(path_before); @@ -3643,11 +3757,26 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); goto out; if (ret) { struct name_cache_entry *nce; + struct waiting_dir_move *wdm; ret = orphanize_inode(sctx, ow_inode, ow_gen, cur->full_path); if (ret < 0) goto out; + + /* + * If ow_inode has its rename operation delayed + * make sure that its orphanized name is used in + * the source path when performing its rename + * operation. + */ + if (is_waiting_for_move(sctx, ow_inode)) { + wdm = get_waiting_dir_move(sctx, + ow_inode); + ASSERT(wdm); + wdm->orphanized = true; + } + /* * Make sure we clear our orphanized inode's * name from the name cache. This is because the @@ -3663,6 +3792,19 @@ verbose_printk("btrfs: process_recorded_refs %llu\n", sctx->cur_ino); name_cache_delete(sctx, nce); kfree(nce); } + + /* + * ow_inode might currently be an ancestor of + * cur_ino, therefore compute valid_path (the + * current path of cur_ino) again because it + * might contain the pre-orphanization name of + * ow_inode, which is no longer valid. + */ + fs_path_reset(valid_path); + ret = get_cur_path(sctx, sctx->cur_ino, + sctx->cur_inode_gen, valid_path); + if (ret < 0) + goto out; } else { ret = send_unlink(sctx, cur->full_path); if (ret < 0) @@ -5602,7 +5744,10 @@ static int changed_ref(struct send_ctx *sctx, { int ret = 0; - BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid); + if (sctx->cur_ino != sctx->cmp_key->objectid) { + inconsistent_snapshot_error(sctx, result, "reference"); + return -EIO; + } if (!sctx->cur_inode_new_gen && sctx->cur_ino != BTRFS_FIRST_FREE_OBJECTID) { @@ -5627,7 +5772,10 @@ static int changed_xattr(struct send_ctx *sctx, { int ret = 0; - BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid); + if (sctx->cur_ino != sctx->cmp_key->objectid) { + inconsistent_snapshot_error(sctx, result, "xattr"); + return -EIO; + } if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) { if (result == BTRFS_COMPARE_TREE_NEW) @@ -5651,7 +5799,10 @@ static int changed_extent(struct send_ctx *sctx, { int ret = 0; - BUG_ON(sctx->cur_ino != sctx->cmp_key->objectid); + if (sctx->cur_ino != sctx->cmp_key->objectid) { + inconsistent_snapshot_error(sctx, result, "extent"); + return -EIO; + } if (!sctx->cur_inode_new_gen && !sctx->cur_inode_deleted) { if (result != BTRFS_COMPARE_TREE_DELETED) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 864ce334f696..4071fe2bd098 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2241,6 +2241,13 @@ static int btrfs_freeze(struct super_block *sb) struct btrfs_trans_handle *trans; struct btrfs_root *root = btrfs_sb(sb)->tree_root; + root->fs_info->fs_frozen = 1; + /* + * We don't need a barrier here, we'll wait for any transaction that + * could be in progress on other threads (and do delayed iputs that + * we want to avoid on a frozen filesystem), or do the commit + * ourselves. + */ trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { /* no transaction, don't bother */ @@ -2251,6 +2258,14 @@ static int btrfs_freeze(struct super_block *sb) return btrfs_commit_transaction(trans, root); } +static int btrfs_unfreeze(struct super_block *sb) +{ + struct btrfs_root *root = btrfs_sb(sb)->tree_root; + + root->fs_info->fs_frozen = 0; + return 0; +} + static int btrfs_show_devname(struct seq_file *m, struct dentry *root) { struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb); @@ -2299,6 +2314,7 @@ static const struct super_operations btrfs_super_ops = { .statfs = btrfs_statfs, .remount_fs = btrfs_remount, .freeze_fs = btrfs_freeze, + .unfreeze_fs = btrfs_unfreeze, }; static const struct file_operations btrfs_ctl_fops = { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 9cca0a721961..95d41919d034 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2278,8 +2278,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, kmem_cache_free(btrfs_trans_handle_cachep, trans); + /* + * If fs has been frozen, we can not handle delayed iputs, otherwise + * it'll result in deadlock about SB_FREEZE_FS. + */ if (current != root->fs_info->transaction_kthread && - current != root->fs_info->cleaner_kthread) + current != root->fs_info->cleaner_kthread && + !root->fs_info->fs_frozen) btrfs_run_delayed_iputs(root); return ret; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index d31a0c4f56be..e935035ac034 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -27,6 +27,7 @@ #include "backref.h" #include "hash.h" #include "compression.h" +#include "qgroup.h" /* magic values for the inode_only field in btrfs_log_inode: * @@ -680,6 +681,21 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ins.type = BTRFS_EXTENT_ITEM_KEY; offset = key->offset - btrfs_file_extent_offset(eb, item); + /* + * Manually record dirty extent, as here we did a shallow + * file extent item copy and skip normal backref update, + * but modifying extent tree all by ourselves. + * So need to manually record dirty extent for qgroup, + * as the owner of the file extent changed from log tree + * (doesn't affect qgroup) to fs/file tree(affects qgroup) + */ + ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info, + btrfs_file_extent_disk_bytenr(eb, item), + btrfs_file_extent_disk_num_bytes(eb, item), + GFP_NOFS); + if (ret < 0) + goto out; + if (ins.objectid > 0) { u64 csum_start; u64 csum_end; @@ -2807,7 +2823,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, */ mutex_unlock(&root->log_mutex); - btrfs_init_log_ctx(&root_log_ctx); + btrfs_init_log_ctx(&root_log_ctx, NULL); mutex_lock(&log_root_tree->log_mutex); atomic_inc(&log_root_tree->log_batch); @@ -4469,7 +4485,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans, static int btrfs_check_ref_name_override(struct extent_buffer *eb, const int slot, const struct btrfs_key *key, - struct inode *inode) + struct inode *inode, + u64 *other_ino) { int ret; struct btrfs_path *search_path; @@ -4528,7 +4545,16 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb, search_path, parent, name, this_name_len, 0); if (di && !IS_ERR(di)) { - ret = 1; + struct btrfs_key di_key; + + btrfs_dir_item_key_to_cpu(search_path->nodes[0], + di, &di_key); + if (di_key.type == BTRFS_INODE_ITEM_KEY) { + ret = 1; + *other_ino = di_key.objectid; + } else { + ret = -EAGAIN; + } goto out; } else if (IS_ERR(di)) { ret = PTR_ERR(di); @@ -4722,16 +4748,72 @@ again: if ((min_key.type == BTRFS_INODE_REF_KEY || min_key.type == BTRFS_INODE_EXTREF_KEY) && BTRFS_I(inode)->generation == trans->transid) { + u64 other_ino = 0; + ret = btrfs_check_ref_name_override(path->nodes[0], path->slots[0], - &min_key, inode); + &min_key, inode, + &other_ino); if (ret < 0) { err = ret; goto out_unlock; - } else if (ret > 0) { - err = 1; - btrfs_set_log_full_commit(root->fs_info, trans); - goto out_unlock; + } else if (ret > 0 && ctx && + other_ino != btrfs_ino(ctx->inode)) { + struct btrfs_key inode_key; + struct inode *other_inode; + + if (ins_nr > 0) { + ins_nr++; + } else { + ins_nr = 1; + ins_start_slot = path->slots[0]; + } + ret = copy_items(trans, inode, dst_path, path, + &last_extent, ins_start_slot, + ins_nr, inode_only, + logged_isize); + if (ret < 0) { + err = ret; + goto out_unlock; + } + ins_nr = 0; + btrfs_release_path(path); + inode_key.objectid = other_ino; + inode_key.type = BTRFS_INODE_ITEM_KEY; + inode_key.offset = 0; + other_inode = btrfs_iget(root->fs_info->sb, + &inode_key, root, + NULL); + /* + * If the other inode that had a conflicting dir + * entry was deleted in the current transaction, + * we don't need to do more work nor fallback to + * a transaction commit. + */ + if (IS_ERR(other_inode) && + PTR_ERR(other_inode) == -ENOENT) { + goto next_key; + } else if (IS_ERR(other_inode)) { + err = PTR_ERR(other_inode); + goto out_unlock; + } + /* + * We are safe logging the other inode without + * acquiring its i_mutex as long as we log with + * the LOG_INODE_EXISTS mode. We're safe against + * concurrent renames of the other inode as well + * because during a rename we pin the log and + * update the log with the new name before we + * unpin it. + */ + err = btrfs_log_inode(trans, root, other_inode, + LOG_INODE_EXISTS, + 0, LLONG_MAX, ctx); + iput(other_inode); + if (err) + goto out_unlock; + else + goto next_key; } } @@ -4799,7 +4881,7 @@ next_slot: ins_nr = 0; } btrfs_release_path(path); - +next_key: if (min_key.offset < (u64)-1) { min_key.offset++; } else if (min_key.type < max_key.type) { @@ -4993,8 +5075,12 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, if (!parent || d_really_is_negative(parent) || sb != parent->d_sb) break; - if (IS_ROOT(parent)) + if (IS_ROOT(parent)) { + inode = d_inode(parent); + if (btrfs_must_commit_transaction(trans, inode)) + ret = 1; break; + } parent = dget_parent(parent); dput(old_parent); diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index a9f1b75d080d..ab858e31ccbc 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -30,15 +30,18 @@ struct btrfs_log_ctx { int log_transid; int io_err; bool log_new_dentries; + struct inode *inode; struct list_head list; }; -static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx) +static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx, + struct inode *inode) { ctx->log_ret = 0; ctx->log_transid = 0; ctx->io_err = 0; ctx->log_new_dentries = false; + ctx->inode = inode; INIT_LIST_HEAD(&ctx->list); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 51f125508771..035efce603a9 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -834,10 +834,6 @@ static void __free_device(struct work_struct *work) struct btrfs_device *device; device = container_of(work, struct btrfs_device, rcu_work); - - if (device->bdev) - blkdev_put(device->bdev, device->mode); - rcu_string_free(device->name); kfree(device); } @@ -852,6 +848,17 @@ static void free_device(struct rcu_head *head) schedule_work(&device->rcu_work); } +static void btrfs_close_bdev(struct btrfs_device *device) +{ + if (device->bdev && device->writeable) { + sync_blockdev(device->bdev); + invalidate_bdev(device->bdev); + } + + if (device->bdev) + blkdev_put(device->bdev, device->mode); +} + static void btrfs_close_one_device(struct btrfs_device *device) { struct btrfs_fs_devices *fs_devices = device->fs_devices; @@ -870,10 +877,7 @@ static void btrfs_close_one_device(struct btrfs_device *device) if (device->missing) fs_devices->missing_devices--; - if (device->bdev && device->writeable) { - sync_blockdev(device->bdev); - invalidate_bdev(device->bdev); - } + btrfs_close_bdev(device); new_device = btrfs_alloc_device(NULL, &device->devid, device->uuid); @@ -1932,6 +1936,8 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path, u64 devid) btrfs_sysfs_rm_device_link(root->fs_info->fs_devices, device); } + btrfs_close_bdev(device); + call_rcu(&device->rcu, free_device); num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1; @@ -2025,6 +2031,9 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info, /* zero out the old super if it is writable */ btrfs_scratch_superblocks(srcdev->bdev, srcdev->name->str); } + + btrfs_close_bdev(srcdev); + call_rcu(&srcdev->rcu, free_device); /* @@ -2080,6 +2089,8 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, * the device_list_mutex lock. */ btrfs_scratch_superblocks(tgtdev->bdev, tgtdev->name->str); + + btrfs_close_bdev(tgtdev); call_rcu(&tgtdev->rcu, free_device); } diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 99115cae1652..16e6ded0b7f2 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1347,9 +1347,12 @@ void ceph_flush_snaps(struct ceph_inode_info *ci, { struct inode *inode = &ci->vfs_inode; struct ceph_mds_client *mdsc = ceph_inode_to_client(inode)->mdsc; - struct ceph_mds_session *session = *psession; + struct ceph_mds_session *session = NULL; int mds; + dout("ceph_flush_snaps %p\n", inode); + if (psession) + session = *psession; retry: spin_lock(&ci->i_ceph_lock); if (!(ci->i_ceph_flags & CEPH_I_FLUSH_SNAPS)) { diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index fa59a85226b2..f72d4ae303b2 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2759,6 +2759,7 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, } else { path = NULL; pathlen = 0; + pathbase = 0; } spin_lock(&ci->i_ceph_lock); diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c index eea64912c9c0..466f7d60edc2 100644 --- a/fs/dlm/debug_fs.c +++ b/fs/dlm/debug_fs.c @@ -607,20 +607,54 @@ static const struct file_operations format2_fops; static const struct file_operations format3_fops; static const struct file_operations format4_fops; -static int table_open(struct inode *inode, struct file *file) +static int table_open1(struct inode *inode, struct file *file) { struct seq_file *seq; - int ret = -1; + int ret; - if (file->f_op == &format1_fops) - ret = seq_open(file, &format1_seq_ops); - else if (file->f_op == &format2_fops) - ret = seq_open(file, &format2_seq_ops); - else if (file->f_op == &format3_fops) - ret = seq_open(file, &format3_seq_ops); - else if (file->f_op == &format4_fops) - ret = seq_open(file, &format4_seq_ops); + ret = seq_open(file, &format1_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open2(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &format2_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open3(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + + ret = seq_open(file, &format3_seq_ops); + if (ret) + return ret; + + seq = file->private_data; + seq->private = inode->i_private; /* the dlm_ls */ + return 0; +} + +static int table_open4(struct inode *inode, struct file *file) +{ + struct seq_file *seq; + int ret; + ret = seq_open(file, &format4_seq_ops); if (ret) return ret; @@ -631,7 +665,7 @@ static int table_open(struct inode *inode, struct file *file) static const struct file_operations format1_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open1, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -639,7 +673,7 @@ static const struct file_operations format1_fops = { static const struct file_operations format2_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open2, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -647,7 +681,7 @@ static const struct file_operations format2_fops = { static const struct file_operations format3_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open3, .read = seq_read, .llseek = seq_lseek, .release = seq_release @@ -655,7 +689,7 @@ static const struct file_operations format3_fops = { static const struct file_operations format4_fops = { .owner = THIS_MODULE, - .open = table_open, + .open = table_open4, .read = seq_read, .llseek = seq_lseek, .release = seq_release diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index d64d2a515cb2..ccb401eebc11 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -1699,11 +1699,11 @@ static int f2fs_write_end(struct file *file, trace_f2fs_write_end(inode, pos, len, copied); set_page_dirty(page); - f2fs_put_page(page, 1); if (pos + copied > i_size_read(inode)) f2fs_i_size_write(inode, pos + copied); + f2fs_put_page(page, 1); f2fs_update_time(F2FS_I_SB(inode), REQ_TIME); return copied; } diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 675fa79d86f6..14f5fe2b841e 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -538,7 +538,7 @@ struct f2fs_nm_info { /* NAT cache management */ struct radix_tree_root nat_root;/* root of the nat entry cache */ struct radix_tree_root nat_set_root;/* root of the nat set cache */ - struct percpu_rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ + struct rw_semaphore nat_tree_lock; /* protect nat_tree_lock */ struct list_head nat_entries; /* cached nat entry list (clean) */ unsigned int nat_cnt; /* the # of cached nat entries */ unsigned int dirty_nat_cnt; /* total num of nat entries in set */ @@ -787,7 +787,7 @@ struct f2fs_sb_info { struct f2fs_checkpoint *ckpt; /* raw checkpoint pointer */ struct inode *meta_inode; /* cache meta blocks */ struct mutex cp_mutex; /* checkpoint procedure lock */ - struct percpu_rw_semaphore cp_rwsem; /* blocking FS operations */ + struct rw_semaphore cp_rwsem; /* blocking FS operations */ struct rw_semaphore node_write; /* locking node writes */ wait_queue_head_t cp_wait; unsigned long last_time[MAX_TIME]; /* to store time in jiffies */ @@ -1074,22 +1074,22 @@ static inline void clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f) static inline void f2fs_lock_op(struct f2fs_sb_info *sbi) { - percpu_down_read(&sbi->cp_rwsem); + down_read(&sbi->cp_rwsem); } static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi) { - percpu_up_read(&sbi->cp_rwsem); + up_read(&sbi->cp_rwsem); } static inline void f2fs_lock_all(struct f2fs_sb_info *sbi) { - percpu_down_write(&sbi->cp_rwsem); + down_write(&sbi->cp_rwsem); } static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi) { - percpu_up_write(&sbi->cp_rwsem); + up_write(&sbi->cp_rwsem); } static inline int __get_cp_reason(struct f2fs_sb_info *sbi) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 0e493f63ea41..47abb96098e4 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2086,15 +2086,19 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, if (unlikely(f2fs_readonly(src->i_sb))) return -EROFS; - if (S_ISDIR(src->i_mode) || S_ISDIR(dst->i_mode)) - return -EISDIR; + if (!S_ISREG(src->i_mode) || !S_ISREG(dst->i_mode)) + return -EINVAL; if (f2fs_encrypted_inode(src) || f2fs_encrypted_inode(dst)) return -EOPNOTSUPP; inode_lock(src); - if (src != dst) - inode_lock(dst); + if (src != dst) { + if (!inode_trylock(dst)) { + ret = -EBUSY; + goto out; + } + } ret = -EINVAL; if (pos_in + len > src->i_size || pos_in + len < pos_in) @@ -2152,6 +2156,7 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in, out_unlock: if (src != dst) inode_unlock(dst); +out: inode_unlock(src); return ret; } diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index b2fa4b615925..f75d197d5beb 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -206,14 +206,14 @@ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid) struct nat_entry *e; bool need = false; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { if (!get_nat_flag(e, IS_CHECKPOINTED) && !get_nat_flag(e, HAS_FSYNCED_INODE)) need = true; } - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need; } @@ -223,11 +223,11 @@ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid) struct nat_entry *e; bool is_cp = true; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e && !get_nat_flag(e, IS_CHECKPOINTED)) is_cp = false; - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return is_cp; } @@ -237,13 +237,13 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino) struct nat_entry *e; bool need_update = true; - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ino); if (e && get_nat_flag(e, HAS_LAST_FSYNC) && (get_nat_flag(e, IS_CHECKPOINTED) || get_nat_flag(e, HAS_FSYNCED_INODE))) need_update = false; - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return need_update; } @@ -284,7 +284,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, struct f2fs_nm_info *nm_i = NM_I(sbi); struct nat_entry *e; - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, ni->nid); if (!e) { e = grab_nat_entry(nm_i, ni->nid); @@ -334,7 +334,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni, set_nat_flag(e, HAS_FSYNCED_INODE, true); set_nat_flag(e, HAS_LAST_FSYNC, fsync_done); } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) @@ -342,7 +342,8 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) struct f2fs_nm_info *nm_i = NM_I(sbi); int nr = nr_shrink; - percpu_down_write(&nm_i->nat_tree_lock); + if (!down_write_trylock(&nm_i->nat_tree_lock)) + return 0; while (nr_shrink && !list_empty(&nm_i->nat_entries)) { struct nat_entry *ne; @@ -351,7 +352,7 @@ int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink) __del_from_nat_cache(nm_i, ne); nr_shrink--; } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); return nr - nr_shrink; } @@ -373,13 +374,13 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) ni->nid = nid; /* Check nat cache */ - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); e = __lookup_nat_cache(nm_i, nid); if (e) { ni->ino = nat_get_ino(e); ni->blk_addr = nat_get_blkaddr(e); ni->version = nat_get_version(e); - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); return; } @@ -403,11 +404,11 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni) node_info_from_raw_nat(ni, &ne); f2fs_put_page(page, 1); cache: - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); /* cache nat entry */ - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); cache_nat_entry(sbi, nid, &ne); - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); } /* @@ -1788,7 +1789,7 @@ void build_free_nids(struct f2fs_sb_info *sbi) ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES, META_NAT, true); - percpu_down_read(&nm_i->nat_tree_lock); + down_read(&nm_i->nat_tree_lock); while (1) { struct page *page = get_current_nat_page(sbi, nid); @@ -1820,7 +1821,7 @@ void build_free_nids(struct f2fs_sb_info *sbi) remove_free_nid(nm_i, nid); } up_read(&curseg->journal_rwsem); - percpu_up_read(&nm_i->nat_tree_lock); + up_read(&nm_i->nat_tree_lock); ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nm_i->next_scan_nid), nm_i->ra_nid_pages, META_NAT, false); @@ -2209,7 +2210,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) if (!nm_i->dirty_nat_cnt) return; - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); /* * if there are no enough space in journal to store dirty nat @@ -2232,7 +2233,7 @@ void flush_nat_entries(struct f2fs_sb_info *sbi) list_for_each_entry_safe(set, tmp, &sets, set_list) __flush_nat_entry_set(sbi, set); - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); f2fs_bug_on(sbi, nm_i->dirty_nat_cnt); } @@ -2268,8 +2269,7 @@ static int init_node_manager(struct f2fs_sb_info *sbi) mutex_init(&nm_i->build_lock); spin_lock_init(&nm_i->free_nid_list_lock); - if (percpu_init_rwsem(&nm_i->nat_tree_lock)) - return -ENOMEM; + init_rwsem(&nm_i->nat_tree_lock); nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid); nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP); @@ -2326,7 +2326,7 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) spin_unlock(&nm_i->free_nid_list_lock); /* destroy nat cache */ - percpu_down_write(&nm_i->nat_tree_lock); + down_write(&nm_i->nat_tree_lock); while ((found = __gang_lookup_nat_cache(nm_i, nid, NATVEC_SIZE, natvec))) { unsigned idx; @@ -2351,9 +2351,8 @@ void destroy_node_manager(struct f2fs_sb_info *sbi) kmem_cache_free(nat_entry_set_slab, setvec[idx]); } } - percpu_up_write(&nm_i->nat_tree_lock); + up_write(&nm_i->nat_tree_lock); - percpu_free_rwsem(&nm_i->nat_tree_lock); kfree(nm_i->nat_bitmap); sbi->nm_info = NULL; kfree(nm_i); diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 1b86d3f638ef..7f863a645ab1 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -706,8 +706,6 @@ static void destroy_percpu_info(struct f2fs_sb_info *sbi) percpu_counter_destroy(&sbi->nr_pages[i]); percpu_counter_destroy(&sbi->alloc_valid_block_count); percpu_counter_destroy(&sbi->total_valid_inode_count); - - percpu_free_rwsem(&sbi->cp_rwsem); } static void f2fs_put_super(struct super_block *sb) @@ -1483,9 +1481,6 @@ static int init_percpu_info(struct f2fs_sb_info *sbi) { int i, err; - if (percpu_init_rwsem(&sbi->cp_rwsem)) - return -ENOMEM; - for (i = 0; i < NR_COUNT_TYPE; i++) { err = percpu_counter_init(&sbi->nr_pages[i], 0, GFP_KERNEL); if (err) @@ -1686,6 +1681,7 @@ try_onemore: sbi->write_io[i].bio = NULL; } + init_rwsem(&sbi->cp_rwsem); init_waitqueue_head(&sbi->cp_wait); init_sb_info(sbi); diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 4d09d4441e3e..05713a5da083 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1949,6 +1949,12 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason) { struct backing_dev_info *bdi; + /* + * If we are expecting writeback progress we must submit plugged IO. + */ + if (blk_needs_flush_plug(current)) + blk_schedule_flush_plug(current); + if (!nr_pages) nr_pages = get_nr_dirty_pages(); diff --git a/fs/iomap.c b/fs/iomap.c index 48141b8eff5f..0342254646e3 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -84,8 +84,11 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags, * Now the data has been copied, commit the range we've copied. This * should not fail unless the filesystem has had a fatal error. */ - ret = ops->iomap_end(inode, pos, length, written > 0 ? written : 0, - flags, &iomap); + if (ops->iomap_end) { + ret = ops->iomap_end(inode, pos, length, + written > 0 ? written : 0, + flags, &iomap); + } return written ? written : ret; } @@ -194,12 +197,9 @@ again: if (mapping_writably_mapped(inode->i_mapping)) flush_dcache_page(page); - pagefault_disable(); copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes); - pagefault_enable(); flush_dcache_page(page); - mark_page_accessed(page); status = iomap_write_end(inode, pos, bytes, copied, page); if (unlikely(status < 0)) @@ -470,13 +470,18 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi, if (ret) return ret; - ret = filemap_write_and_wait(inode->i_mapping); - if (ret) - return ret; + if (fi->fi_flags & FIEMAP_FLAG_SYNC) { + ret = filemap_write_and_wait(inode->i_mapping); + if (ret) + return ret; + } while (len > 0) { ret = iomap_apply(inode, start, len, 0, ops, &ctx, iomap_fiemap_actor); + /* inode with no (attribute) mapping will give ENOENT */ + if (ret == -ENOENT) + break; if (ret < 0) return ret; if (ret == 0) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 33da841a21bb..6f4752734804 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -338,6 +338,8 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata) case 0: break; case -NFS4ERR_EXPIRED: + case -NFS4ERR_ADMIN_REVOKED: + case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_OLD_STATEID: case -NFS4ERR_BAD_STATEID: diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 324bfdc21250..9bf64eacba5b 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -396,6 +396,10 @@ extern void nfs4_schedule_state_renewal(struct nfs_client *); extern void nfs4_renewd_prepare_shutdown(struct nfs_server *); extern void nfs4_kill_renewd(struct nfs_client *); extern void nfs4_renew_state(struct work_struct *); +extern void nfs4_set_lease_period(struct nfs_client *clp, + unsigned long lease, + unsigned long lastrenewed); + /* nfs4state.c */ struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a036e93bdf96..1949bbd806eb 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4237,12 +4237,9 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str err = _nfs4_do_fsinfo(server, fhandle, fsinfo); trace_nfs4_fsinfo(server, fhandle, fsinfo->fattr, err); if (err == 0) { - struct nfs_client *clp = server->nfs_client; - - spin_lock(&clp->cl_lock); - clp->cl_lease_time = fsinfo->lease_time * HZ; - clp->cl_last_renewal = now; - spin_unlock(&clp->cl_lock); + nfs4_set_lease_period(server->nfs_client, + fsinfo->lease_time * HZ, + now); break; } err = nfs4_handle_exception(server, err, &exception); diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c index e1ba58c3d1ad..82e77198d17e 100644 --- a/fs/nfs/nfs4renewd.c +++ b/fs/nfs/nfs4renewd.c @@ -136,6 +136,26 @@ nfs4_kill_renewd(struct nfs_client *clp) cancel_delayed_work_sync(&clp->cl_renewd); } +/** + * nfs4_set_lease_period - Sets the lease period on a nfs_client + * + * @clp: pointer to nfs_client + * @lease: new value for lease period + * @lastrenewed: time at which lease was last renewed + */ +void nfs4_set_lease_period(struct nfs_client *clp, + unsigned long lease, + unsigned long lastrenewed) +{ + spin_lock(&clp->cl_lock); + clp->cl_lease_time = lease; + clp->cl_last_renewal = lastrenewed; + spin_unlock(&clp->cl_lock); + + /* Cap maximum reconnect timeout at 1/2 lease period */ + rpc_cap_max_reconnect_timeout(clp->cl_rpcclient, lease >> 1); +} + /* * Local variables: * c-basic-offset: 8 diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 834b875900d6..cada00aa5096 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -277,20 +277,17 @@ static int nfs41_setup_state_renewal(struct nfs_client *clp) { int status; struct nfs_fsinfo fsinfo; + unsigned long now; if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) { nfs4_schedule_state_renewal(clp); return 0; } + now = jiffies; status = nfs4_proc_get_lease_time(clp, &fsinfo); if (status == 0) { - /* Update lease time and schedule renewal */ - spin_lock(&clp->cl_lock); - clp->cl_lease_time = fsinfo.lease_time * HZ; - clp->cl_last_renewal = jiffies; - spin_unlock(&clp->cl_lock); - + nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now); nfs4_schedule_state_renewal(clp); } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 8410ca275db1..a204d7e109d4 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4903,6 +4903,32 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfs_ok; } +static __be32 +nfsd4_free_lock_stateid(stateid_t *stateid, struct nfs4_stid *s) +{ + struct nfs4_ol_stateid *stp = openlockstateid(s); + __be32 ret; + + mutex_lock(&stp->st_mutex); + + ret = check_stateid_generation(stateid, &s->sc_stateid, 1); + if (ret) + goto out; + + ret = nfserr_locks_held; + if (check_for_locks(stp->st_stid.sc_file, + lockowner(stp->st_stateowner))) + goto out; + + release_lock_stateid(stp); + ret = nfs_ok; + +out: + mutex_unlock(&stp->st_mutex); + nfs4_put_stid(s); + return ret; +} + __be32 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *free_stateid) @@ -4910,7 +4936,6 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; - struct nfs4_ol_stateid *stp; struct nfs4_client *cl = cstate->session->se_client; __be32 ret = nfserr_bad_stateid; @@ -4929,18 +4954,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, ret = nfserr_locks_held; break; case NFS4_LOCK_STID: - ret = check_stateid_generation(stateid, &s->sc_stateid, 1); - if (ret) - break; - stp = openlockstateid(s); - ret = nfserr_locks_held; - if (check_for_locks(stp->st_stid.sc_file, - lockowner(stp->st_stateowner))) - break; - WARN_ON(!unhash_lock_stateid(stp)); + atomic_inc(&s->sc_count); spin_unlock(&cl->cl_lock); - nfs4_put_stid(s); - ret = nfs_ok; + ret = nfsd4_free_lock_stateid(stateid, s); goto out; case NFS4_REVOKED_DELEG_STID: dp = delegstateid(s); @@ -5507,7 +5523,7 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, - struct nfs4_ol_stateid **lst, bool *new) + struct nfs4_ol_stateid **plst, bool *new) { __be32 status; struct nfs4_file *fi = ost->st_stid.sc_file; @@ -5515,7 +5531,9 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_client *cl = oo->oo_owner.so_client; struct inode *inode = d_inode(cstate->current_fh.fh_dentry); struct nfs4_lockowner *lo; + struct nfs4_ol_stateid *lst; unsigned int strhashval; + bool hashed; lo = find_lockowner_str(cl, &lock->lk_new_owner); if (!lo) { @@ -5531,12 +5549,27 @@ lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, goto out; } - *lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); - if (*lst == NULL) { +retry: + lst = find_or_create_lock_stateid(lo, fi, inode, ost, new); + if (lst == NULL) { status = nfserr_jukebox; goto out; } + + mutex_lock(&lst->st_mutex); + + /* See if it's still hashed to avoid race with FREE_STATEID */ + spin_lock(&cl->cl_lock); + hashed = !list_empty(&lst->st_perfile); + spin_unlock(&cl->cl_lock); + + if (!hashed) { + mutex_unlock(&lst->st_mutex); + nfs4_put_stid(&lst->st_stid); + goto retry; + } status = nfs_ok; + *plst = lst; out: nfs4_put_stateowner(&lo->lo_owner); return status; @@ -5603,8 +5636,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; status = lookup_or_create_lock_state(cstate, open_stp, lock, &lock_stp, &new); - if (status == nfs_ok) - mutex_lock(&lock_stp->st_mutex); } else { status = nfs4_preprocess_seqid_op(cstate, lock->lk_old_lock_seqid, diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index ba944123167b..ff476e654b8f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1252,10 +1252,13 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp, if (IS_ERR(dchild)) return nfserrno(host_err); err = fh_compose(resfhp, fhp->fh_export, dchild, fhp); - if (err) { - dput(dchild); + /* + * We unconditionally drop our ref to dchild as fh_compose will have + * already grabbed its own ref for it. + */ + dput(dchild); + if (err) return err; - } return nfsd_create_locked(rqstp, fhp, fname, flen, iap, type, rdev, resfhp); } diff --git a/fs/pipe.c b/fs/pipe.c index 4b32928f5426..4ebe6b2e5217 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -144,10 +144,8 @@ static int anon_pipe_buf_steal(struct pipe_inode_info *pipe, struct page *page = buf->page; if (page_count(page) == 1) { - if (memcg_kmem_enabled()) { + if (memcg_kmem_enabled()) memcg_kmem_uncharge(page, 0); - __ClearPageKmemcg(page); - } __SetPageLocked(page); return 0; } diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c index 09e18fdf61e5..b9a8c813e5e6 100644 --- a/fs/proc/meminfo.c +++ b/fs/proc/meminfo.c @@ -46,7 +46,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v) cached = 0; for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) - pages[lru] = global_page_state(NR_LRU_BASE + lru); + pages[lru] = global_node_page_state(NR_LRU_BASE + lru); available = si_mem_available(); diff --git a/fs/seq_file.c b/fs/seq_file.c index 19f532e7d35e..6dc4296eed62 100644 --- a/fs/seq_file.c +++ b/fs/seq_file.c @@ -223,8 +223,10 @@ ssize_t seq_read(struct file *file, char __user *buf, size_t size, loff_t *ppos) size -= n; buf += n; copied += n; - if (!m->count) + if (!m->count) { + m->from = 0; m->index++; + } if (!size) goto Done; } diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c index b45345d701e7..51157da3f76e 100644 --- a/fs/ubifs/tnc_commit.c +++ b/fs/ubifs/tnc_commit.c @@ -370,7 +370,7 @@ static int layout_in_gaps(struct ubifs_info *c, int cnt) p = c->gap_lebs; do { - ubifs_assert(p < c->gap_lebs + sizeof(int) * c->lst.idx_lebs); + ubifs_assert(p < c->gap_lebs + c->lst.idx_lebs); written = layout_leb_in_gaps(c, p); if (written < 0) { err = written; diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c index e237811f09ce..11a004114eba 100644 --- a/fs/ubifs/xattr.c +++ b/fs/ubifs/xattr.c @@ -575,7 +575,8 @@ static int ubifs_xattr_get(const struct xattr_handler *handler, dbg_gen("xattr '%s', ino %lu ('%pd'), buf size %zd", name, inode->i_ino, dentry, size); - return __ubifs_getxattr(inode, name, buffer, size); + name = xattr_full_name(handler, name); + return __ubifs_getxattr(inode, name, buffer, size); } static int ubifs_xattr_set(const struct xattr_handler *handler, @@ -586,6 +587,8 @@ static int ubifs_xattr_set(const struct xattr_handler *handler, dbg_gen("xattr '%s', host ino %lu ('%pd'), size %zd", name, inode->i_ino, dentry, size); + name = xattr_full_name(handler, name); + if (value) return __ubifs_setxattr(inode, name, value, size, flags); else diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 776ae2f325d1..3dd8f1d54498 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -1582,6 +1582,7 @@ xfs_alloc_ag_vextent_small( xfs_extlen_t *flenp, /* result length */ int *stat) /* status: 0-freelist, 1-normal/none */ { + struct xfs_owner_info oinfo; int error; xfs_agblock_t fbno; xfs_extlen_t flen; @@ -1624,6 +1625,18 @@ xfs_alloc_ag_vextent_small( error0); args->wasfromfl = 1; trace_xfs_alloc_small_freelist(args); + + /* + * If we're feeding an AGFL block to something that + * doesn't live in the free space, we need to clear + * out the OWN_AG rmap. + */ + xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG); + error = xfs_rmap_free(args->tp, args->agbp, args->agno, + fbno, 1, &oinfo); + if (error) + goto error0; + *stat = 0; return 0; } @@ -2264,6 +2277,7 @@ xfs_alloc_log_agf( offsetof(xfs_agf_t, agf_longest), offsetof(xfs_agf_t, agf_btreeblks), offsetof(xfs_agf_t, agf_uuid), + offsetof(xfs_agf_t, agf_rmap_blocks), sizeof(xfs_agf_t) }; diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index f814d42c73b2..e6a8bea0f7ba 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -640,12 +640,15 @@ typedef struct xfs_agf { __be32 agf_btreeblks; /* # of blocks held in AGF btrees */ uuid_t agf_uuid; /* uuid of filesystem */ + __be32 agf_rmap_blocks; /* rmapbt blocks used */ + __be32 agf_padding; /* padding */ + /* * reserve some contiguous space for future logged fields before we add * the unlogged fields. This makes the range logging via flags and * structure offsets much simpler. */ - __be64 agf_spare64[16]; + __be64 agf_spare64[15]; /* unlogged fields, written during buffer writeback. */ __be64 agf_lsn; /* last write sequence */ @@ -670,7 +673,8 @@ typedef struct xfs_agf { #define XFS_AGF_LONGEST 0x00000400 #define XFS_AGF_BTREEBLKS 0x00000800 #define XFS_AGF_UUID 0x00001000 -#define XFS_AGF_NUM_BITS 13 +#define XFS_AGF_RMAP_BLOCKS 0x00002000 +#define XFS_AGF_NUM_BITS 14 #define XFS_AGF_ALL_BITS ((1 << XFS_AGF_NUM_BITS) - 1) #define XFS_AGF_FLAGS \ @@ -686,7 +690,8 @@ typedef struct xfs_agf { { XFS_AGF_FREEBLKS, "FREEBLKS" }, \ { XFS_AGF_LONGEST, "LONGEST" }, \ { XFS_AGF_BTREEBLKS, "BTREEBLKS" }, \ - { XFS_AGF_UUID, "UUID" } + { XFS_AGF_UUID, "UUID" }, \ + { XFS_AGF_RMAP_BLOCKS, "RMAP_BLOCKS" } /* disk block (xfs_daddr_t) in the AG */ #define XFS_AGF_DADDR(mp) ((xfs_daddr_t)(1 << (mp)->m_sectbb_log)) diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c index bc1faebc84ec..17b8eeb34ac8 100644 --- a/fs/xfs/libxfs/xfs_rmap_btree.c +++ b/fs/xfs/libxfs/xfs_rmap_btree.c @@ -98,6 +98,8 @@ xfs_rmapbt_alloc_block( union xfs_btree_ptr *new, int *stat) { + struct xfs_buf *agbp = cur->bc_private.a.agbp; + struct xfs_agf *agf = XFS_BUF_TO_AGF(agbp); int error; xfs_agblock_t bno; @@ -124,6 +126,8 @@ xfs_rmapbt_alloc_block( xfs_trans_agbtree_delta(cur->bc_tp, 1); new->s = cpu_to_be32(bno); + be32_add_cpu(&agf->agf_rmap_blocks, 1); + xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS); XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT); *stat = 1; @@ -143,6 +147,8 @@ xfs_rmapbt_free_block( bno = xfs_daddr_to_agbno(cur->bc_mp, XFS_BUF_ADDR(bp)); trace_xfs_rmapbt_free_block(cur->bc_mp, cur->bc_private.a.agno, bno, 1); + be32_add_cpu(&agf->agf_rmap_blocks, -1); + xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS); error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1); if (error) return error; diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 47a318ce82e0..607cc29bba21 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -115,7 +115,6 @@ xfs_buf_ioacct_dec( if (!(bp->b_flags & _XBF_IN_FLIGHT)) return; - ASSERT(bp->b_flags & XBF_ASYNC); bp->b_flags &= ~_XBF_IN_FLIGHT; percpu_counter_dec(&bp->b_target->bt_io_count); } diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index ed95e5bb04e6..e612a0233710 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -741,9 +741,20 @@ xfs_file_dax_write( * page is inserted into the pagecache when we have to serve a write * fault on a hole. It should never be dirtied and can simply be * dropped from the pagecache once we get real data for the page. + * + * XXX: This is racy against mmap, and there's nothing we can do about + * it. dax_do_io() should really do this invalidation internally as + * it will know if we've allocated over a holei for this specific IO and + * if so it needs to update the mapping tree and invalidate existing + * PTEs over the newly allocated range. Remove this invalidation when + * dax_do_io() is fixed up. */ if (mapping->nrpages) { - ret = invalidate_inode_pages2(mapping); + loff_t end = iocb->ki_pos + iov_iter_count(from) - 1; + + ret = invalidate_inode_pages2_range(mapping, + iocb->ki_pos >> PAGE_SHIFT, + end >> PAGE_SHIFT); WARN_ON_ONCE(ret); } diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 0f96847b90e1..0b7f986745c1 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -248,6 +248,7 @@ xfs_growfs_data_private( agf->agf_roots[XFS_BTNUM_RMAPi] = cpu_to_be32(XFS_RMAP_BLOCK(mp)); agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1); + agf->agf_rmap_blocks = cpu_to_be32(1); } agf->agf_flfirst = cpu_to_be32(1); diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 2114d53df433..2af0dda1c978 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -715,12 +715,16 @@ xfs_iomap_write_allocate( * is in the delayed allocation extent on which we sit * but before our buffer starts. */ - nimaps = 0; while (nimaps == 0) { nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK); - - error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, nres, + /* + * We have already reserved space for the extent and any + * indirect blocks when creating the delalloc extent, + * there is no need to reserve space in this transaction + * again. + */ + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, XFS_TRANS_RESERVE, &tp); if (error) return error; @@ -1037,20 +1041,14 @@ xfs_file_iomap_begin( return error; trace_xfs_iomap_alloc(ip, offset, length, 0, &imap); - xfs_bmbt_to_iomap(ip, iomap, &imap); - } else if (nimaps) { - xfs_iunlock(ip, XFS_ILOCK_EXCL); - trace_xfs_iomap_found(ip, offset, length, 0, &imap); - xfs_bmbt_to_iomap(ip, iomap, &imap); } else { + ASSERT(nimaps); + xfs_iunlock(ip, XFS_ILOCK_EXCL); - trace_xfs_iomap_not_found(ip, offset, length, 0, &imap); - iomap->blkno = IOMAP_NULL_BLOCK; - iomap->type = IOMAP_HOLE; - iomap->offset = offset; - iomap->length = length; + trace_xfs_iomap_found(ip, offset, length, 0, &imap); } + xfs_bmbt_to_iomap(ip, iomap, &imap); return 0; } @@ -1112,3 +1110,48 @@ struct iomap_ops xfs_iomap_ops = { .iomap_begin = xfs_file_iomap_begin, .iomap_end = xfs_file_iomap_end, }; + +static int +xfs_xattr_iomap_begin( + struct inode *inode, + loff_t offset, + loff_t length, + unsigned flags, + struct iomap *iomap) +{ + struct xfs_inode *ip = XFS_I(inode); + struct xfs_mount *mp = ip->i_mount; + xfs_fileoff_t offset_fsb = XFS_B_TO_FSBT(mp, offset); + xfs_fileoff_t end_fsb = XFS_B_TO_FSB(mp, offset + length); + struct xfs_bmbt_irec imap; + int nimaps = 1, error = 0; + unsigned lockmode; + + if (XFS_FORCED_SHUTDOWN(mp)) + return -EIO; + + lockmode = xfs_ilock_data_map_shared(ip); + + /* if there are no attribute fork or extents, return ENOENT */ + if (XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) { + error = -ENOENT; + goto out_unlock; + } + + ASSERT(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL); + error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap, + &nimaps, XFS_BMAPI_ENTIRE | XFS_BMAPI_ATTRFORK); +out_unlock: + xfs_iunlock(ip, lockmode); + + if (!error) { + ASSERT(nimaps); + xfs_bmbt_to_iomap(ip, iomap, &imap); + } + + return error; +} + +struct iomap_ops xfs_xattr_iomap_ops = { + .iomap_begin = xfs_xattr_iomap_begin, +}; diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h index e066d045e2ff..fb8aca3d69ab 100644 --- a/fs/xfs/xfs_iomap.h +++ b/fs/xfs/xfs_iomap.h @@ -35,5 +35,6 @@ void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *, struct xfs_bmbt_irec *); extern struct iomap_ops xfs_iomap_ops; +extern struct iomap_ops xfs_xattr_iomap_ops; #endif /* __XFS_IOMAP_H__*/ diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index ab820f84ed50..b24c3102fa93 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1009,7 +1009,14 @@ xfs_vn_fiemap( int error; xfs_ilock(XFS_I(inode), XFS_IOLOCK_SHARED); - error = iomap_fiemap(inode, fieinfo, start, length, &xfs_iomap_ops); + if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { + fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR; + error = iomap_fiemap(inode, fieinfo, start, length, + &xfs_xattr_iomap_ops); + } else { + error = iomap_fiemap(inode, fieinfo, start, length, + &xfs_iomap_ops); + } xfs_iunlock(XFS_I(inode), XFS_IOLOCK_SHARED); return error; diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index 551b7e26980c..7e88bec3f359 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -1298,7 +1298,6 @@ DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc); DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct); DEFINE_IOMAP_EVENT(xfs_iomap_alloc); DEFINE_IOMAP_EVENT(xfs_iomap_found); -DEFINE_IOMAP_EVENT(xfs_iomap_not_found); DECLARE_EVENT_CLASS(xfs_simple_io_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count), diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 54a8e65e18b6..7d026bf27713 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -25,7 +25,20 @@ #include <asm-generic/qrwlock_types.h> /* - * Writer states & reader shift and bias + * Writer states & reader shift and bias. + * + * | +0 | +1 | +2 | +3 | + * ----+----+----+----+----+ + * LE | 78 | 56 | 34 | 12 | 0x12345678 + * ----+----+----+----+----+ + * | wr | rd | + * +----+----+----+----+ + * + * ----+----+----+----+----+ + * BE | 12 | 34 | 56 | 78 | 0x12345678 + * ----+----+----+----+----+ + * | rd | wr | + * +----+----+----+----+ */ #define _QW_WAITING 1 /* A writer is waiting */ #define _QW_LOCKED 0xff /* A writer holds the lock */ @@ -134,12 +147,22 @@ static inline void queued_read_unlock(struct qrwlock *lock) } /** + * __qrwlock_write_byte - retrieve the write byte address of a queue rwlock + * @lock : Pointer to queue rwlock structure + * Return: the write byte address of a queue rwlock + */ +static inline u8 *__qrwlock_write_byte(struct qrwlock *lock) +{ + return (u8 *)lock + 3 * IS_BUILTIN(CONFIG_CPU_BIG_ENDIAN); +} + +/** * queued_write_unlock - release write lock of a queue rwlock * @lock : Pointer to queue rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { - smp_store_release((u8 *)&lock->cnts, 0); + smp_store_release(__qrwlock_write_byte(lock), 0); } /* diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h index 4348d6d5877a..99c6d01d24f2 100644 --- a/include/drm/ttm/ttm_bo_driver.h +++ b/include/drm/ttm/ttm_bo_driver.h @@ -962,6 +962,7 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev, * * @bo: A pointer to a struct ttm_buffer_object. * @evict: 1: This is an eviction. Don't try to pipeline. + * @interruptible: Sleep interruptible if waiting. * @no_wait_gpu: Return immediately if the GPU is busy. * @new_mem: struct ttm_mem_reg indicating where to move. * @@ -976,7 +977,7 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev, */ extern int ttm_bo_move_ttm(struct ttm_buffer_object *bo, - bool evict, bool no_wait_gpu, + bool evict, bool interruptible, bool no_wait_gpu, struct ttm_mem_reg *new_mem); /** diff --git a/include/linux/bio.h b/include/linux/bio.h index 59ffaa68b11b..23ddf4b46a9b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -71,7 +71,8 @@ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && - bio_op(bio) != REQ_OP_DISCARD) + bio_op(bio) != REQ_OP_DISCARD && + bio_op(bio) != REQ_OP_SECURE_ERASE) return true; return false; @@ -79,7 +80,9 @@ static inline bool bio_has_data(struct bio *bio) static inline bool bio_no_advance_iter(struct bio *bio) { - return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME; + return bio_op(bio) == REQ_OP_DISCARD || + bio_op(bio) == REQ_OP_SECURE_ERASE || + bio_op(bio) == REQ_OP_WRITE_SAME; } static inline bool bio_is_rw(struct bio *bio) @@ -199,6 +202,9 @@ static inline unsigned bio_segments(struct bio *bio) if (bio_op(bio) == REQ_OP_DISCARD) return 1; + if (bio_op(bio) == REQ_OP_SECURE_ERASE) + return 1; + if (bio_op(bio) == REQ_OP_WRITE_SAME) return 1; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c210b6a7bcf..e79055c8b577 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -882,7 +882,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { - if (unlikely(op == REQ_OP_DISCARD)) + if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> 9); if (unlikely(op == REQ_OP_WRITE_SAME)) @@ -913,7 +913,9 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; - if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD)) + if (!q->limits.chunk_sectors || + req_op(rq) == REQ_OP_DISCARD || + req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, offset), diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 701b64a3b7c5..89b65b82d98f 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -74,7 +74,8 @@ static inline void bvec_iter_advance(const struct bio_vec *bv, "Attempted to advance past end of bvec iter\n"); while (bytes) { - unsigned len = min(bytes, bvec_iter_len(bv, *iter)); + unsigned iter_len = bvec_iter_len(bv, *iter); + unsigned len = min(bytes, iter_len); bytes -= len; iter->bi_size -= len; diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index e2949397c19b..8dbc8929a6a0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -242,7 +242,11 @@ */ #define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +/* + * sparse (__CHECKER__) pretends to be gcc, but can't do constant + * folding in __builtin_bswap*() (yet), so don't set these for it. + */ +#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) #if GCC_VERSION >= 40400 #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ @@ -250,7 +254,7 @@ #if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ #endif -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ #if GCC_VERSION >= 50000 #define KASAN_ABI_VERSION 4 diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 1bb954842725..436aa4e42221 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -527,13 +527,13 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * object's lifetime is managed by something other than RCU. That * "something other" might be reference counting or simple immortality. * - * The seemingly unused void * variable is to validate @p is indeed a pointer - * type. All pointer types silently cast to void *. + * The seemingly unused size_t variable is to validate @p is indeed a pointer + * type by making sure it can be dereferenced. */ #define lockless_dereference(p) \ ({ \ typeof(p) _________p1 = READ_ONCE(p); \ - __maybe_unused const void * const _________p2 = _________p1; \ + size_t __maybe_unused __size_of_ptr = sizeof(*(p)); \ smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) diff --git a/include/linux/host1x.h b/include/linux/host1x.h index d2ba7d334039..1ffbf2a8cb99 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -304,6 +304,8 @@ struct tegra_mipi_device; struct tegra_mipi_device *tegra_mipi_request(struct device *device); void tegra_mipi_free(struct tegra_mipi_device *device); +int tegra_mipi_enable(struct tegra_mipi_device *device); +int tegra_mipi_disable(struct tegra_mipi_device *device); int tegra_mipi_calibrate(struct tegra_mipi_device *device); #endif diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 56b0b7ec66aa..99ac022edc60 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -337,6 +337,7 @@ */ #define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107 #define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109 +#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307 #define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507 #define E_ITS_MAPD_DEVICE_OOR 0x010801 #define E_ITS_MAPC_PROCNUM_OOR 0x010902 diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01e908ac4a39..9c28b4d4c90b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1113,9 +1113,21 @@ struct kvm_device { /* create, destroy, and name are mandatory */ struct kvm_device_ops { const char *name; + + /* + * create is called holding kvm->lock and any operations not suitable + * to do while holding the lock should be deferred to init (see + * below). + */ int (*create)(struct kvm_device *dev, u32 type); /* + * init is called after create if create is successful and is called + * outside of holding kvm->lock. + */ + void (*init)(struct kvm_device *dev); + + /* * Destroy is responsible for freeing dev. * * Destroy may be called before or after destructors are called diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f2e4e90621ec..d572b78b65e1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -68,8 +68,10 @@ extern char * const migratetype_names[MIGRATE_TYPES]; #ifdef CONFIG_CMA # define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) +# define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA) #else # define is_migrate_cma(migratetype) false +# define is_migrate_cma_page(_page) false #endif #define for_each_migratetype_order(order, type) \ diff --git a/include/linux/msi.h b/include/linux/msi.h index 4f0bfe5912b2..e8c81fbd5f9c 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -270,6 +270,8 @@ enum { MSI_FLAG_MULTI_PCI_MSI = (1 << 2), /* Support PCI MSIX interrupts */ MSI_FLAG_PCI_MSIX = (1 << 3), + /* Needs early activate, required for PCI */ + MSI_FLAG_ACTIVATE_EARLY = (1 << 4), }; int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 076df5360ba5..3a788bf0affd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3891,8 +3891,7 @@ void netdev_default_l2upper_neigh_destroy(struct net_device *dev, extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); -int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(const struct net_device *dev)); +int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); diff --git a/include/linux/pci.h b/include/linux/pci.h index 2599a980340f..fbc1fa625c3e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1251,10 +1251,12 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno); int pci_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags); -#define PCI_IRQ_NOLEGACY (1 << 0) /* don't use legacy interrupts */ -#define PCI_IRQ_NOMSI (1 << 1) /* don't use MSI interrupts */ -#define PCI_IRQ_NOMSIX (1 << 2) /* don't use MSI-X interrupts */ -#define PCI_IRQ_NOAFFINITY (1 << 3) /* don't auto-assign affinity */ +#define PCI_IRQ_LEGACY (1 << 0) /* allow legacy interrupts */ +#define PCI_IRQ_MSI (1 << 1) /* allow MSI interrupts */ +#define PCI_IRQ_MSIX (1 << 2) /* allow MSI-X interrupts */ +#define PCI_IRQ_AFFINITY (1 << 3) /* auto-assign affinity */ +#define PCI_IRQ_ALL_TYPES \ + (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) /* kmem_cache style wrapper around pci_alloc_consistent() */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 8ed4326164cc..2b6b43cc0dd5 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -743,7 +743,9 @@ struct perf_event_context { u64 parent_gen; u64 generation; int pin_count; +#ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ +#endif void *task_ctx_data; /* pmu specific data */ struct rcu_head rcu_head; }; @@ -769,7 +771,9 @@ struct perf_cpu_context { unsigned int hrtimer_active; struct pmu *unique_pmu; +#ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; +#endif }; struct perf_output_handle { diff --git a/include/linux/printk.h b/include/linux/printk.h index 8dc155dab3ed..696a56be7d3e 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -266,39 +266,21 @@ extern asmlinkage void dump_stack(void) __cold; * and other debug macros are compiled out unless either DEBUG is defined * or CONFIG_DYNAMIC_DEBUG is set. */ - -#ifdef CONFIG_PRINTK - -asmlinkage __printf(1, 2) __cold void __pr_emerg(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_alert(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_crit(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_err(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_warn(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_notice(const char *fmt, ...); -asmlinkage __printf(1, 2) __cold void __pr_info(const char *fmt, ...); - -#define pr_emerg(fmt, ...) __pr_emerg(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert(fmt, ...) __pr_alert(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit(fmt, ...) __pr_crit(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err(fmt, ...) __pr_err(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn(fmt, ...) __pr_warn(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_notice(fmt, ...) __pr_notice(pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) __pr_info(pr_fmt(fmt), ##__VA_ARGS__) - -#else - -#define pr_emerg(fmt, ...) printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) -#define pr_alert(fmt, ...) printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_crit(fmt, ...) printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) -#define pr_err(fmt, ...) printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) -#define pr_warn(fmt, ...) printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) -#define pr_notice(fmt, ...) printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) -#define pr_info(fmt, ...) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) - -#endif - -#define pr_warning pr_warn - +#define pr_emerg(fmt, ...) \ + printk(KERN_EMERG pr_fmt(fmt), ##__VA_ARGS__) +#define pr_alert(fmt, ...) \ + printk(KERN_ALERT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_crit(fmt, ...) \ + printk(KERN_CRIT pr_fmt(fmt), ##__VA_ARGS__) +#define pr_err(fmt, ...) \ + printk(KERN_ERR pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warning(fmt, ...) \ + printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) +#define pr_warn pr_warning +#define pr_notice(fmt, ...) \ + printk(KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__) +#define pr_info(fmt, ...) \ + printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) /* * Like KERN_CONT, pr_cont() should only be used when continuing * a line with no newline ('\n') enclosed. Otherwise it defaults diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b1e3c57c7117..d6c4177df7cb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -70,8 +70,16 @@ struct qed_dbcx_pfc_params { u8 max_tc; }; +enum qed_dcbx_sf_ieee_type { + QED_DCBX_SF_IEEE_ETHTYPE, + QED_DCBX_SF_IEEE_TCP_PORT, + QED_DCBX_SF_IEEE_UDP_PORT, + QED_DCBX_SF_IEEE_TCP_UDP_PORT +}; + struct qed_app_entry { bool ethtype; + enum qed_dcbx_sf_ieee_type sf_ieee; bool enabled; u8 prio; u16 proto_id; diff --git a/include/linux/sctp.h b/include/linux/sctp.h index de1f64318fc4..fcb4c3646173 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -705,70 +705,6 @@ typedef struct sctp_auth_chunk { sctp_authhdr_t auth_hdr; } __packed sctp_auth_chunk_t; -struct sctp_info { - __u32 sctpi_tag; - __u32 sctpi_state; - __u32 sctpi_rwnd; - __u16 sctpi_unackdata; - __u16 sctpi_penddata; - __u16 sctpi_instrms; - __u16 sctpi_outstrms; - __u32 sctpi_fragmentation_point; - __u32 sctpi_inqueue; - __u32 sctpi_outqueue; - __u32 sctpi_overall_error; - __u32 sctpi_max_burst; - __u32 sctpi_maxseg; - __u32 sctpi_peer_rwnd; - __u32 sctpi_peer_tag; - __u8 sctpi_peer_capable; - __u8 sctpi_peer_sack; - __u16 __reserved1; - - /* assoc status info */ - __u64 sctpi_isacks; - __u64 sctpi_osacks; - __u64 sctpi_opackets; - __u64 sctpi_ipackets; - __u64 sctpi_rtxchunks; - __u64 sctpi_outofseqtsns; - __u64 sctpi_idupchunks; - __u64 sctpi_gapcnt; - __u64 sctpi_ouodchunks; - __u64 sctpi_iuodchunks; - __u64 sctpi_oodchunks; - __u64 sctpi_iodchunks; - __u64 sctpi_octrlchunks; - __u64 sctpi_ictrlchunks; - - /* primary transport info */ - struct sockaddr_storage sctpi_p_address; - __s32 sctpi_p_state; - __u32 sctpi_p_cwnd; - __u32 sctpi_p_srtt; - __u32 sctpi_p_rto; - __u32 sctpi_p_hbinterval; - __u32 sctpi_p_pathmaxrxt; - __u32 sctpi_p_sackdelay; - __u32 sctpi_p_sackfreq; - __u32 sctpi_p_ssthresh; - __u32 sctpi_p_partial_bytes_acked; - __u32 sctpi_p_flight_size; - __u16 sctpi_p_error; - __u16 __reserved2; - - /* sctp sock info */ - __u32 sctpi_s_autoclose; - __u32 sctpi_s_adaptation_ind; - __u32 sctpi_s_pd_point; - __u8 sctpi_s_nodelay; - __u8 sctpi_s_disable_fragments; - __u8 sctpi_s_v4mapped; - __u8 sctpi_s_frag_interleave; - __u32 sctpi_s_type; - __u32 __reserved3; -}; - struct sctp_infox { struct sctp_info *sctpinfo; struct sctp_association *asoc; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f0b3e0adc73..0f665cb26b50 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2847,6 +2847,18 @@ static inline int skb_linearize_cow(struct sk_buff *skb) __skb_linearize(skb) : 0; } +static __always_inline void +__skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, + unsigned int off) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_block_sub(skb->csum, + csum_partial(start, len, 0), off); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) < 0) + skb->ip_summed = CHECKSUM_NONE; +} + /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update @@ -2857,36 +2869,38 @@ static inline int skb_linearize_cow(struct sk_buff *skb) * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ - static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); - else if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_start_offset(skb) < 0) - skb->ip_summed = CHECKSUM_NONE; + __skb_postpull_rcsum(skb, start, len, 0); } -unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +static __always_inline void +__skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, + unsigned int off) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_block_add(skb->csum, + csum_partial(start, len, 0), off); +} +/** + * skb_postpush_rcsum - update checksum for received skb after push + * @skb: buffer to update + * @start: start of data after push + * @len: length of data pushed + * + * After doing a push on a received packet, you need to call this to + * update the CHECKSUM_COMPLETE checksum. + */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - /* For performing the reverse operation to skb_postpull_rcsum(), - * we can instead of ... - * - * skb->csum = csum_add(skb->csum, csum_partial(start, len, 0)); - * - * ... just use this equivalent version here to save a few - * instructions. Feeding csum of 0 in csum_partial() and later - * on adding skb->csum is equivalent to feed skb->csum in the - * first place. - */ - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_partial(start, len, skb->csum); + __skb_postpush_rcsum(skb, start, len, 0); } +unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); + /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update diff --git a/include/linux/slab.h b/include/linux/slab.h index 1a4ea551aae5..4293808d8cfb 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -155,6 +155,18 @@ void kfree(const void *); void kzfree(const void *); size_t ksize(const void *); +#ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR +const char *__check_heap_object(const void *ptr, unsigned long n, + struct page *page); +#else +static inline const char *__check_heap_object(const void *ptr, + unsigned long n, + struct page *page) +{ + return NULL; +} +#endif + /* * Some archs want to perform DMA into kmalloc caches and need a guaranteed * alignment larger than the alignment of a 64-bit integer. diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h index b6810c92b8bb..5c02b0691587 100644 --- a/include/linux/sunrpc/clnt.h +++ b/include/linux/sunrpc/clnt.h @@ -195,6 +195,8 @@ int rpc_clnt_add_xprt(struct rpc_clnt *, struct xprt_create *, struct rpc_xprt *, void *), void *data); +void rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + unsigned long timeo); const char *rpc_proc_name(const struct rpc_task *task); #endif /* __KERNEL__ */ diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h index 5e3e1b63dbb3..a16070dd03ee 100644 --- a/include/linux/sunrpc/xprt.h +++ b/include/linux/sunrpc/xprt.h @@ -218,7 +218,8 @@ struct rpc_xprt { struct work_struct task_cleanup; struct timer_list timer; unsigned long last_used, - idle_timeout; + idle_timeout, + max_reconnect_timeout; /* * Send stuff diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 697e160c78d0..a4f7203a9017 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -42,6 +42,8 @@ extern int proc_dostring(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec(struct ctl_table *, int, + void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_jiffies(struct ctl_table *, int, diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 352b1542f5cc..cbd8990e2e77 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -105,6 +105,30 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag) #define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) +#ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES +static inline int arch_within_stack_frames(const void * const stack, + const void * const stackend, + const void *obj, unsigned long len) +{ + return 0; +} +#endif + +#ifdef CONFIG_HARDENED_USERCOPY +extern void __check_object_size(const void *ptr, unsigned long n, + bool to_user); + +static inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ + __check_object_size(ptr, n, to_user); +} +#else +static inline void check_object_size(const void *ptr, unsigned long n, + bool to_user) +{ } +#endif /* CONFIG_HARDENED_USERCOPY */ + #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 349557825428..f30c187ed785 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -114,8 +114,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); #ifndef user_access_begin #define user_access_begin() do { } while (0) #define user_access_end() do { } while (0) -#define unsafe_get_user(x, ptr) __get_user(x, ptr) -#define unsafe_put_user(x, ptr) __put_user(x, ptr) +#define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) +#define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) #endif #endif /* __LINUX_UACCESS_H__ */ diff --git a/include/net/act_api.h b/include/net/act_api.h index 41e6a24a44b9..82f3c912a5b1 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -176,8 +176,8 @@ int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_unregister_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_action_destroy(struct list_head *actions, int bind); -int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, - struct tcf_result *res); +int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, + int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct nlattr *nla, struct nlattr *est, char *n, int ovr, int bind, struct list_head *); @@ -189,30 +189,17 @@ int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); -#define tc_no_actions(_exts) \ - (list_empty(&(_exts)->actions)) - -#define tc_for_each_action(_a, _exts) \ - list_for_each_entry(a, &(_exts)->actions, list) - -#define tc_single_action(_exts) \ - (list_is_singular(&(_exts)->actions)) +#endif /* CONFIG_NET_CLS_ACT */ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 lastuse) { +#ifdef CONFIG_NET_CLS_ACT if (!a->ops->stats_update) return; a->ops->stats_update(a, bytes, packets, lastuse); +#endif } -#else /* CONFIG_NET_CLS_ACT */ - -#define tc_no_actions(_exts) true -#define tc_for_each_action(_a, _exts) while ((void)(_a), 0) -#define tc_single_action(_exts) false -#define tcf_action_stats_update(a, bytes, packets, lastuse) - -#endif /* CONFIG_NET_CLS_ACT */ #endif diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index ac1bc3c49fbd..7b0f88699b25 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -40,12 +40,12 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *, unsigned long, gfp_t); int rxrpc_kernel_send_data(struct rxrpc_call *, struct msghdr *, size_t); +void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); void rxrpc_kernel_abort_call(struct rxrpc_call *, u32); void rxrpc_kernel_end_call(struct rxrpc_call *); bool rxrpc_kernel_is_data_last(struct sk_buff *); u32 rxrpc_kernel_get_abort_code(struct sk_buff *); int rxrpc_kernel_get_error_number(struct sk_buff *); -void rxrpc_kernel_data_delivered(struct sk_buff *); void rxrpc_kernel_free_skb(struct sk_buff *); struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *, unsigned long); int rxrpc_kernel_reject_call(struct socket *); diff --git a/include/net/gre.h b/include/net/gre.h index 7a54a31d1d4c..73ea256eb7d7 100644 --- a/include/net/gre.h +++ b/include/net/gre.h @@ -104,6 +104,7 @@ static inline void gre_build_header(struct sk_buff *skb, int hdr_len, skb_push(skb, hdr_len); + skb_set_inner_protocol(skb, proto); skb_reset_transport_header(skb); greh = (struct gre_base_hdr *)skb->data; greh->flags = gre_tnl_flags_to_gre_flags(flags); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 0dc0a51da38f..dce2d586d9ce 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -128,7 +128,8 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) to = from | htonl(INET_ECN_CE << 20); *(__be32 *)iph = to; if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_add(csum_sub(skb->csum, from), to); + skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), + (__force __wsum)to); return 1; } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index b4faadbb4e01..cca510a585c3 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3620,7 +3620,8 @@ struct ieee80211_ops { int (*join_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); void (*leave_ibss)(struct ieee80211_hw *hw, struct ieee80211_vif *vif); - u32 (*get_expected_throughput)(struct ieee80211_sta *sta); + u32 (*get_expected_throughput)(struct ieee80211_hw *hw, + struct ieee80211_sta *sta); int (*get_txpower)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int *dbm); diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 6f8d65342d3a..c99508d426cc 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -59,7 +59,8 @@ tcf_unbind_filter(struct tcf_proto *tp, struct tcf_result *r) struct tcf_exts { #ifdef CONFIG_NET_CLS_ACT __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ - struct list_head actions; + int nr_actions; + struct tc_action **actions; #endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. @@ -72,7 +73,10 @@ static inline void tcf_exts_init(struct tcf_exts *exts, int action, int police) { #ifdef CONFIG_NET_CLS_ACT exts->type = 0; - INIT_LIST_HEAD(&exts->actions); + exts->nr_actions = 0; + exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *), + GFP_KERNEL); + WARN_ON(!exts->actions); /* TODO: propagate the error to callers */ #endif exts->action = action; exts->police = police; @@ -89,7 +93,7 @@ static inline int tcf_exts_is_predicative(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - return !list_empty(&exts->actions); + return exts->nr_actions; #else return 0; #endif @@ -108,6 +112,20 @@ tcf_exts_is_available(struct tcf_exts *exts) return tcf_exts_is_predicative(exts); } +static inline void tcf_exts_to_list(const struct tcf_exts *exts, + struct list_head *actions) +{ +#ifdef CONFIG_NET_CLS_ACT + int i; + + for (i = 0; i < exts->nr_actions; i++) { + struct tc_action *a = exts->actions[i]; + + list_add(&a->list, actions); + } +#endif +} + /** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer @@ -124,12 +142,25 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, struct tcf_result *res) { #ifdef CONFIG_NET_CLS_ACT - if (!list_empty(&exts->actions)) - return tcf_action_exec(skb, &exts->actions, res); + if (exts->nr_actions) + return tcf_action_exec(skb, exts->actions, exts->nr_actions, + res); #endif return 0; } +#ifdef CONFIG_NET_CLS_ACT + +#define tc_no_actions(_exts) ((_exts)->nr_actions == 0) +#define tc_single_action(_exts) ((_exts)->nr_actions == 1) + +#else /* CONFIG_NET_CLS_ACT */ + +#define tc_no_actions(_exts) true +#define tc_single_action(_exts) false + +#endif /* CONFIG_NET_CLS_ACT */ + int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr); diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 8e90dd28bb75..e1f96737c2a1 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2115,22 +2115,17 @@ static inline bool ib_is_udata_cleared(struct ib_udata *udata, size_t len) { const void __user *p = udata->inbuf + offset; - bool ret = false; + bool ret; u8 *buf; if (len > USHRT_MAX) return false; - buf = kmalloc(len, GFP_KERNEL); - if (!buf) + buf = memdup_user(p, len); + if (IS_ERR(buf)) return false; - if (copy_from_user(buf, p, len)) - goto free; - ret = !memchr_inv(buf, 0, len); - -free: kfree(buf); return ret; } diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index 51440131d337..28c5da6fdfac 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -330,24 +330,32 @@ TRACE_EVENT(itimer_expire, #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ - tick_dep_name(NONE) \ + tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name_end(CLOCK_UNSTABLE) #undef tick_dep_name +#undef tick_dep_mask_name #undef tick_dep_name_end -#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); -#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +/* The MASK will convert to their bits and they need to be processed too */ +#define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ + TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +#define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ + TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); +/* NONE only has a mask defined for it */ +#define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name +#undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, +#define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index da218fec6056..9e5fc168c8a3 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -339,7 +339,7 @@ enum bpf_func_id { BPF_FUNC_skb_change_type, /** - * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb + * bpf_skb_under_cgroup(skb, map, index) - Check cgroup2 membership of skb * @skb: pointer to skb * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type * @index: index of the cgroup in the bpf_map @@ -348,7 +348,7 @@ enum bpf_func_id { * == 1 skb succeeded the cgroup2 descendant test * < 0 error */ - BPF_FUNC_skb_in_cgroup, + BPF_FUNC_skb_under_cgroup, /** * bpf_get_hash_recalc(skb) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 01751faccaf8..c674ba2563b7 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -24,7 +24,7 @@ enum nft_registers { __NFT_REG_MAX, NFT_REG32_00 = 8, - MFT_REG32_01, + NFT_REG32_01, NFT_REG32_02, NFT_REG32_03, NFT_REG32_04, diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index d304f4c9792c..a406adcc0793 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -944,4 +944,68 @@ struct sctp_default_prinfo { __u16 pr_policy; }; +struct sctp_info { + __u32 sctpi_tag; + __u32 sctpi_state; + __u32 sctpi_rwnd; + __u16 sctpi_unackdata; + __u16 sctpi_penddata; + __u16 sctpi_instrms; + __u16 sctpi_outstrms; + __u32 sctpi_fragmentation_point; + __u32 sctpi_inqueue; + __u32 sctpi_outqueue; + __u32 sctpi_overall_error; + __u32 sctpi_max_burst; + __u32 sctpi_maxseg; + __u32 sctpi_peer_rwnd; + __u32 sctpi_peer_tag; + __u8 sctpi_peer_capable; + __u8 sctpi_peer_sack; + __u16 __reserved1; + + /* assoc status info */ + __u64 sctpi_isacks; + __u64 sctpi_osacks; + __u64 sctpi_opackets; + __u64 sctpi_ipackets; + __u64 sctpi_rtxchunks; + __u64 sctpi_outofseqtsns; + __u64 sctpi_idupchunks; + __u64 sctpi_gapcnt; + __u64 sctpi_ouodchunks; + __u64 sctpi_iuodchunks; + __u64 sctpi_oodchunks; + __u64 sctpi_iodchunks; + __u64 sctpi_octrlchunks; + __u64 sctpi_ictrlchunks; + + /* primary transport info */ + struct sockaddr_storage sctpi_p_address; + __s32 sctpi_p_state; + __u32 sctpi_p_cwnd; + __u32 sctpi_p_srtt; + __u32 sctpi_p_rto; + __u32 sctpi_p_hbinterval; + __u32 sctpi_p_pathmaxrxt; + __u32 sctpi_p_sackdelay; + __u32 sctpi_p_sackfreq; + __u32 sctpi_p_ssthresh; + __u32 sctpi_p_partial_bytes_acked; + __u32 sctpi_p_flight_size; + __u16 sctpi_p_error; + __u16 __reserved2; + + /* sctp sock info */ + __u32 sctpi_s_autoclose; + __u32 sctpi_s_adaptation_ind; + __u32 sctpi_s_pd_point; + __u8 sctpi_s_nodelay; + __u8 sctpi_s_disable_fragments; + __u8 sctpi_s_v4mapped; + __u8 sctpi_s_frag_interleave; + __u32 sctpi_s_type; + __u32 __reserved3; +}; + #endif /* _UAPI_SCTP_H */ diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h index 6b011c19b50f..1d57ed3d84d2 100644 --- a/include/uapi/linux/virtio_vsock.h +++ b/include/uapi/linux/virtio_vsock.h @@ -32,7 +32,7 @@ */ #ifndef _UAPI_LINUX_VIRTIO_VSOCK_H -#define _UAPI_LINUX_VIRTIO_VOSCK_H +#define _UAPI_LINUX_VIRTIO_VSOCK_H #include <linux/types.h> #include <linux/virtio_ids.h> diff --git a/include/uapi/misc/cxl.h b/include/uapi/misc/cxl.h index cbae529b7ce0..180d526a55c3 100644 --- a/include/uapi/misc/cxl.h +++ b/include/uapi/misc/cxl.h @@ -136,8 +136,8 @@ struct cxl_event_afu_driver_reserved { * * Of course the contents will be ABI, but that's up the AFU driver. */ - size_t data_size; - u8 data[]; + __u32 data_size; + __u8 data[]; }; struct cxl_event { diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h index 9a37c541822f..b5486e648607 100644 --- a/include/xen/xen-ops.h +++ b/include/xen/xen-ops.h @@ -9,8 +9,8 @@ DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu); -DECLARE_PER_CPU(int, xen_vcpu_id); -static inline int xen_vcpu_nr(int cpu) +DECLARE_PER_CPU(uint32_t, xen_vcpu_id); +static inline uint32_t xen_vcpu_nr(int cpu) { return per_cpu(xen_vcpu_id, cpu); } diff --git a/init/Kconfig b/init/Kconfig index 69886493ff1e..cac3f096050d 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1761,6 +1761,7 @@ choice config SLAB bool "SLAB" + select HAVE_HARDENED_USERCOPY_ALLOCATOR help The regular slab allocator that is established and known to work well in all environments. It organizes cache hot objects in @@ -1768,6 +1769,7 @@ config SLAB config SLUB bool "SLUB (Unqueued Allocator)" + select HAVE_HARDENED_USERCOPY_ALLOCATOR help SLUB is a slab allocator that minimizes cache line usage instead of managing queues of cached objects (SLAB approach). diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index fff3650d52fc..570eeca7bdfa 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -26,11 +26,18 @@ struct bpf_htab { struct bucket *buckets; void *elems; struct pcpu_freelist freelist; + void __percpu *extra_elems; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ }; +enum extra_elem_state { + HTAB_NOT_AN_EXTRA_ELEM = 0, + HTAB_EXTRA_ELEM_FREE, + HTAB_EXTRA_ELEM_USED +}; + /* each htab element is struct htab_elem + key + value */ struct htab_elem { union { @@ -38,7 +45,10 @@ struct htab_elem { struct bpf_htab *htab; struct pcpu_freelist_node fnode; }; - struct rcu_head rcu; + union { + struct rcu_head rcu; + enum extra_elem_state state; + }; u32 hash; char key[0] __aligned(8); }; @@ -113,6 +123,23 @@ free_elems: return err; } +static int alloc_extra_elems(struct bpf_htab *htab) +{ + void __percpu *pptr; + int cpu; + + pptr = __alloc_percpu_gfp(htab->elem_size, 8, GFP_USER | __GFP_NOWARN); + if (!pptr) + return -ENOMEM; + + for_each_possible_cpu(cpu) { + ((struct htab_elem *)per_cpu_ptr(pptr, cpu))->state = + HTAB_EXTRA_ELEM_FREE; + } + htab->extra_elems = pptr; + return 0; +} + /* Called from syscall */ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { @@ -185,6 +212,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (percpu) cost += (u64) round_up(htab->map.value_size, 8) * num_possible_cpus() * htab->map.max_entries; + else + cost += (u64) htab->elem_size * num_possible_cpus(); if (cost >= U32_MAX - PAGE_SIZE) /* make sure page count doesn't overflow */ @@ -212,14 +241,22 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) raw_spin_lock_init(&htab->buckets[i].lock); } + if (!percpu) { + err = alloc_extra_elems(htab); + if (err) + goto free_buckets; + } + if (!(attr->map_flags & BPF_F_NO_PREALLOC)) { err = prealloc_elems_and_freelist(htab); if (err) - goto free_buckets; + goto free_extra_elems; } return &htab->map; +free_extra_elems: + free_percpu(htab->extra_elems); free_buckets: kvfree(htab->buckets); free_htab: @@ -349,7 +386,6 @@ static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); kfree(l); - } static void htab_elem_free_rcu(struct rcu_head *head) @@ -370,6 +406,11 @@ static void htab_elem_free_rcu(struct rcu_head *head) static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { + if (l->state == HTAB_EXTRA_ELEM_USED) { + l->state = HTAB_EXTRA_ELEM_FREE; + return; + } + if (!(htab->map.map_flags & BPF_F_NO_PREALLOC)) { pcpu_freelist_push(&htab->freelist, &l->fnode); } else { @@ -381,25 +422,44 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, - bool percpu, bool onallcpus) + bool percpu, bool onallcpus, + bool old_elem_exists) { u32 size = htab->map.value_size; bool prealloc = !(htab->map.map_flags & BPF_F_NO_PREALLOC); struct htab_elem *l_new; void __percpu *pptr; + int err = 0; if (prealloc) { l_new = (struct htab_elem *)pcpu_freelist_pop(&htab->freelist); if (!l_new) - return ERR_PTR(-E2BIG); + err = -E2BIG; } else { if (atomic_inc_return(&htab->count) > htab->map.max_entries) { atomic_dec(&htab->count); - return ERR_PTR(-E2BIG); + err = -E2BIG; + } else { + l_new = kmalloc(htab->elem_size, + GFP_ATOMIC | __GFP_NOWARN); + if (!l_new) + return ERR_PTR(-ENOMEM); } - l_new = kmalloc(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (!l_new) - return ERR_PTR(-ENOMEM); + } + + if (err) { + if (!old_elem_exists) + return ERR_PTR(err); + + /* if we're updating the existing element and the hash table + * is full, use per-cpu extra elems + */ + l_new = this_cpu_ptr(htab->extra_elems); + if (l_new->state != HTAB_EXTRA_ELEM_FREE) + return ERR_PTR(-E2BIG); + l_new->state = HTAB_EXTRA_ELEM_USED; + } else { + l_new->state = HTAB_NOT_AN_EXTRA_ELEM; } memcpy(l_new->key, key, key_size); @@ -489,7 +549,8 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (ret) goto err; - l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false); + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false, + !!l_old); if (IS_ERR(l_new)) { /* all pre-allocated elements are in use or memory exhausted */ ret = PTR_ERR(l_new); @@ -563,7 +624,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, } } else { l_new = alloc_htab_elem(htab, key, value, key_size, - hash, true, onallcpus); + hash, true, onallcpus, false); if (IS_ERR(l_new)) { ret = PTR_ERR(l_new); goto err; @@ -652,6 +713,7 @@ static void htab_map_free(struct bpf_map *map) htab_free_elems(htab); pcpu_freelist_destroy(&htab->freelist); } + free_percpu(htab->extra_elems); kvfree(htab->buckets); kfree(htab); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index f72f23b8fdab..daea765d72e6 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -194,6 +194,7 @@ struct verifier_env { struct verifier_state_list **explored_states; /* search pruning optimization */ struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */ u32 used_map_cnt; /* number of used maps */ + u32 id_gen; /* used to generate unique reg IDs */ bool allow_ptr_leaks; }; @@ -1052,7 +1053,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) goto error; break; case BPF_MAP_TYPE_CGROUP_ARRAY: - if (func_id != BPF_FUNC_skb_in_cgroup) + if (func_id != BPF_FUNC_skb_under_cgroup) goto error; break; default: @@ -1074,7 +1075,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) if (map->map_type != BPF_MAP_TYPE_STACK_TRACE) goto error; break; - case BPF_FUNC_skb_in_cgroup: + case BPF_FUNC_skb_under_cgroup: if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY) goto error; break; @@ -1301,7 +1302,7 @@ add_imm: /* dst_reg stays as pkt_ptr type and since some positive * integer value was added to the pointer, increment its 'id' */ - dst_reg->id++; + dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range and off to zero */ dst_reg->off = 0; diff --git a/kernel/events/core.c b/kernel/events/core.c index a19550d80ab1..3cfabdf7b942 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -242,18 +242,6 @@ unlock: return ret; } -static void event_function_local(struct perf_event *event, event_f func, void *data) -{ - struct event_function_struct efs = { - .event = event, - .func = func, - .data = data, - }; - - int ret = event_function(&efs); - WARN_ON_ONCE(ret); -} - static void event_function_call(struct perf_event *event, event_f func, void *data) { struct perf_event_context *ctx = event->ctx; @@ -303,6 +291,54 @@ again: raw_spin_unlock_irq(&ctx->lock); } +/* + * Similar to event_function_call() + event_function(), but hard assumes IRQs + * are already disabled and we're on the right CPU. + */ +static void event_function_local(struct perf_event *event, event_f func, void *data) +{ + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct task_struct *task = READ_ONCE(ctx->task); + struct perf_event_context *task_ctx = NULL; + + WARN_ON_ONCE(!irqs_disabled()); + + if (task) { + if (task == TASK_TOMBSTONE) + return; + + task_ctx = ctx; + } + + perf_ctx_lock(cpuctx, task_ctx); + + task = ctx->task; + if (task == TASK_TOMBSTONE) + goto unlock; + + if (task) { + /* + * We must be either inactive or active and the right task, + * otherwise we're screwed, since we cannot IPI to somewhere + * else. + */ + if (ctx->is_active) { + if (WARN_ON_ONCE(task != current)) + goto unlock; + + if (WARN_ON_ONCE(cpuctx->task_ctx != ctx)) + goto unlock; + } + } else { + WARN_ON_ONCE(&cpuctx->ctx != ctx); + } + + func(event, cpuctx, ctx, data); +unlock: + perf_ctx_unlock(cpuctx, task_ctx); +} + #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ PERF_FLAG_FD_OUTPUT |\ PERF_FLAG_PID_CGROUP |\ @@ -843,6 +879,32 @@ perf_cgroup_mark_enabled(struct perf_event *event, } } } + +/* + * Update cpuctx->cgrp so that it is set when first cgroup event is added and + * cleared when last cgroup event is removed. + */ +static inline void +list_update_cgroup_event(struct perf_event *event, + struct perf_event_context *ctx, bool add) +{ + struct perf_cpu_context *cpuctx; + + if (!is_cgroup_event(event)) + return; + + if (add && ctx->nr_cgroups++) + return; + else if (!add && --ctx->nr_cgroups) + return; + /* + * Because cgroup events are always per-cpu events, + * this will always be called from the right CPU. + */ + cpuctx = __get_cpu_context(ctx); + cpuctx->cgrp = add ? event->cgrp : NULL; +} + #else /* !CONFIG_CGROUP_PERF */ static inline bool @@ -920,6 +982,13 @@ perf_cgroup_mark_enabled(struct perf_event *event, struct perf_event_context *ctx) { } + +static inline void +list_update_cgroup_event(struct perf_event *event, + struct perf_event_context *ctx, bool add) +{ +} + #endif /* @@ -1392,6 +1461,7 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) static void list_add_event(struct perf_event *event, struct perf_event_context *ctx) { + lockdep_assert_held(&ctx->lock); WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); @@ -1412,8 +1482,7 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) list_add_tail(&event->group_entry, list); } - if (is_cgroup_event(event)) - ctx->nr_cgroups++; + list_update_cgroup_event(event, ctx, true); list_add_rcu(&event->event_entry, &ctx->event_list); ctx->nr_events++; @@ -1581,8 +1650,6 @@ static void perf_group_attach(struct perf_event *event) static void list_del_event(struct perf_event *event, struct perf_event_context *ctx) { - struct perf_cpu_context *cpuctx; - WARN_ON_ONCE(event->ctx != ctx); lockdep_assert_held(&ctx->lock); @@ -1594,20 +1661,7 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) event->attach_state &= ~PERF_ATTACH_CONTEXT; - if (is_cgroup_event(event)) { - ctx->nr_cgroups--; - /* - * Because cgroup events are always per-cpu events, this will - * always be called from the right CPU. - */ - cpuctx = __get_cpu_context(ctx); - /* - * If there are no more cgroup events then clear cgrp to avoid - * stale pointer in update_cgrp_time_from_cpuctx(). - */ - if (!ctx->nr_cgroups) - cpuctx->cgrp = NULL; - } + list_update_cgroup_event(event, ctx, false); ctx->nr_events--; if (event->attr.inherit_stat) @@ -1716,8 +1770,8 @@ static inline int pmu_filter_match(struct perf_event *event) static inline int event_filter_match(struct perf_event *event) { - return (event->cpu == -1 || event->cpu == smp_processor_id()) - && perf_cgroup_match(event) && pmu_filter_match(event); + return (event->cpu == -1 || event->cpu == smp_processor_id()) && + perf_cgroup_match(event) && pmu_filter_match(event); } static void @@ -1737,8 +1791,8 @@ event_sched_out(struct perf_event *event, * maintained, otherwise bogus information is return * via read() for time_enabled, time_running: */ - if (event->state == PERF_EVENT_STATE_INACTIVE - && !event_filter_match(event)) { + if (event->state == PERF_EVENT_STATE_INACTIVE && + !event_filter_match(event)) { delta = tstamp - event->tstamp_stopped; event->tstamp_running += delta; event->tstamp_stopped = tstamp; @@ -2236,10 +2290,15 @@ perf_install_in_context(struct perf_event_context *ctx, lockdep_assert_held(&ctx->mutex); - event->ctx = ctx; if (event->cpu != -1) event->cpu = cpu; + /* + * Ensures that if we can observe event->ctx, both the event and ctx + * will be 'complete'. See perf_iterate_sb_cpu(). + */ + smp_store_release(&event->ctx, ctx); + if (!task) { cpu_function_call(cpu, __perf_install_in_context, event); return; @@ -3490,9 +3549,10 @@ static int perf_event_read(struct perf_event *event, bool group) .group = group, .ret = 0, }; - smp_call_function_single(event->oncpu, - __perf_event_read, &data, 1); - ret = data.ret; + ret = smp_call_function_single(event->oncpu, __perf_event_read, &data, 1); + /* The event must have been read from an online CPU: */ + WARN_ON_ONCE(ret); + ret = ret ? : data.ret; } else if (event->state == PERF_EVENT_STATE_INACTIVE) { struct perf_event_context *ctx = event->ctx; unsigned long flags; @@ -5969,6 +6029,14 @@ static void perf_iterate_sb_cpu(perf_iterate_f output, void *data) struct perf_event *event; list_for_each_entry_rcu(event, &pel->list, sb_list) { + /* + * Skip events that are not fully formed yet; ensure that + * if we observe event->ctx, both event and ctx will be + * complete enough. See perf_install_in_context(). + */ + if (!smp_load_acquire(&event->ctx)) + continue; + if (event->state < PERF_EVENT_STATE_INACTIVE) continue; if (!event_filter_match(event)) @@ -6098,7 +6166,7 @@ static int __perf_pmu_output_stop(void *info) { struct perf_event *event = info; struct pmu *pmu = event->pmu; - struct perf_cpu_context *cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); struct remote_output ro = { .rb = event->rb, }; @@ -6553,15 +6621,6 @@ got_name: } /* - * Whether this @filter depends on a dynamic object which is not loaded - * yet or its load addresses are not known. - */ -static bool perf_addr_filter_needs_mmap(struct perf_addr_filter *filter) -{ - return filter->filter && filter->inode; -} - -/* * Check whether inode and address range match filter criteria. */ static bool perf_addr_filter_match(struct perf_addr_filter *filter, @@ -6622,6 +6681,13 @@ static void perf_addr_filters_adjust(struct vm_area_struct *vma) struct perf_event_context *ctx; int ctxn; + /* + * Data tracing isn't supported yet and as such there is no need + * to keep track of anything that isn't related to executable code: + */ + if (!(vma->vm_flags & VM_EXEC)) + return; + rcu_read_lock(); for_each_task_context_nr(ctxn) { ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); @@ -7774,7 +7840,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event) list_for_each_entry(filter, &ifh->list, entry) { event->addr_filters_offs[count] = 0; - if (perf_addr_filter_needs_mmap(filter)) + /* + * Adjust base offset if the filter is associated to a binary + * that needs to be mapped: + */ + if (filter->inode) event->addr_filters_offs[count] = perf_addr_filter_apply(filter, mm); @@ -7905,8 +7975,10 @@ perf_event_parse_addr_filter(struct perf_event *event, char *fstr, goto fail; } - if (token == IF_SRC_FILE) { - filename = match_strdup(&args[2]); + if (token == IF_SRC_FILE || token == IF_SRC_FILEADDR) { + int fpos = filter->range ? 2 : 1; + + filename = match_strdup(&args[fpos]); if (!filename) { ret = -ENOMEM; goto fail; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index b7a525ab2083..8c50276b60d1 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -172,8 +172,10 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); err = -EAGAIN; ptep = page_check_address(page, mm, addr, &ptl, 0); - if (!ptep) + if (!ptep) { + mem_cgroup_cancel_charge(kpage, memcg, false); goto unlock; + } get_page(kpage); page_add_new_anon_rmap(kpage, vma, addr, false); @@ -200,7 +202,6 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, err = 0; unlock: - mem_cgroup_cancel_charge(kpage, memcg, false); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); unlock_page(page); return err; diff --git a/kernel/futex.c b/kernel/futex.c index 33664f70e2d2..46cb3a301bc1 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -179,7 +179,15 @@ int __read_mostly futex_cmpxchg_enabled; * Futex flags used to encode options to functions and preserve them across * restarts. */ -#define FLAGS_SHARED 0x01 +#ifdef CONFIG_MMU +# define FLAGS_SHARED 0x01 +#else +/* + * NOMMU does not have per process address space. Let the compiler optimize + * code away. + */ +# define FLAGS_SHARED 0x00 +#endif #define FLAGS_CLOCKRT 0x02 #define FLAGS_HAS_TIMEOUT 0x04 @@ -405,6 +413,16 @@ static void get_futex_key_refs(union futex_key *key) if (!key->both.ptr) return; + /* + * On MMU less systems futexes are always "private" as there is no per + * process address space. We need the smp wmb nevertheless - yes, + * arch/blackfin has MMU less SMP ... + */ + if (!IS_ENABLED(CONFIG_MMU)) { + smp_mb(); /* explicit smp_mb(); (B) */ + return; + } + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: ihold(key->shared.inode); /* implies smp_mb(); (B) */ @@ -436,6 +454,9 @@ static void drop_futex_key_refs(union futex_key *key) return; } + if (!IS_ENABLED(CONFIG_MMU)) + return; + switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: iput(key->shared.inode); diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index f68959341c0f..32f6cfcff212 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -39,6 +39,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs) return NULL; } + get_online_cpus(); if (max_vecs >= num_online_cpus()) { cpumask_copy(affinity_mask, cpu_online_mask); *nr_vecs = num_online_cpus(); @@ -56,6 +57,7 @@ struct cpumask *irq_create_affinity_mask(unsigned int *nr_vecs) } *nr_vecs = vecs; } + put_online_cpus(); return affinity_mask; } diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index b4c1bc7c9ca2..637389088b3f 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -820,6 +820,17 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle, desc->name = name; if (handle != handle_bad_irq && is_chained) { + /* + * We're about to start this interrupt immediately, + * hence the need to set the trigger configuration. + * But the .set_type callback may have overridden the + * flow handler, ignoring that we're dealing with a + * chained interrupt. Reset it immediately because we + * do know better. + */ + __irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data)); + desc->handle_irq = handle; + irq_settings_set_noprobe(desc); irq_settings_set_norequest(desc); irq_settings_set_nothread(desc); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 73a2b786b5e9..9530fcd27704 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1681,8 +1681,10 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler, action->dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); - if (retval < 0) + if (retval < 0) { + kfree(action); return retval; + } chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); @@ -1985,8 +1987,10 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, action->percpu_dev_id = dev_id; retval = irq_chip_pm_get(&desc->irq_data); - if (retval < 0) + if (retval < 0) { + kfree(action); return retval; + } chip_bus_lock(desc); retval = __setup_irq(irq, desc, action); diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 54999350162c..19e9dfbe97fa 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -359,6 +359,17 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, else dev_dbg(dev, "irq [%d-%d] for MSI\n", virq, virq + desc->nvec_used - 1); + /* + * This flag is set by the PCI layer as we need to activate + * the MSI entries before the PCI layer enables MSI in the + * card. Otherwise the card latches a random msi message. + */ + if (info->flags & MSI_FLAG_ACTIVATE_EARLY) { + struct irq_data *irq_data; + + irq_data = irq_domain_get_irq_data(domain, desc->irq); + irq_domain_activate_irq(irq_data); + } } return 0; diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 37649e69056c..8a99abf58080 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -450,7 +450,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) goto gotlock; } } - WRITE_ONCE(pn->state, vcpu_halted); + WRITE_ONCE(pn->state, vcpu_hashed); qstat_inc(qstat_pv_wait_head, true); qstat_inc(qstat_pv_wait_again, waitcnt); pv_wait(&l->locked, _Q_SLOW_VAL); diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index 22e025309845..b9d031516254 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -153,7 +153,6 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf, */ if ((counter == qstat_pv_latency_kick) || (counter == qstat_pv_latency_wake)) { - stat = 0; if (kicks) stat = DIV_ROUND_CLOSEST_ULL(stat, kicks); } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index a881c6a7ba74..33c79b6105c5 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -300,12 +300,12 @@ static int create_image(int platform_mode) save_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, true); error = swsusp_arch_suspend(); + /* Restore control flow magically appears here */ + restore_processor_state(); trace_suspend_resume(TPS("machine_suspend"), PM_EVENT_HIBERNATE, false); if (error) printk(KERN_ERR "PM: Error %d creating hibernation image\n", error); - /* Restore control flow magically appears here */ - restore_processor_state(); if (!in_suspend) events_check_enabled = false; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 9a0178c2ac1d..b02228411d57 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -835,9 +835,9 @@ static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn) */ static bool rtree_next_node(struct memory_bitmap *bm) { - bm->cur.node = list_entry(bm->cur.node->list.next, - struct rtree_node, list); - if (&bm->cur.node->list != &bm->cur.zone->leaves) { + if (!list_is_last(&bm->cur.node->list, &bm->cur.zone->leaves)) { + bm->cur.node = list_entry(bm->cur.node->list.next, + struct rtree_node, list); bm->cur.node_pfn += BM_BITS_PER_BLOCK; bm->cur.node_bit = 0; touch_softlockup_watchdog(); @@ -845,9 +845,9 @@ static bool rtree_next_node(struct memory_bitmap *bm) } /* No more nodes, goto next zone */ - bm->cur.zone = list_entry(bm->cur.zone->list.next, + if (!list_is_last(&bm->cur.zone->list, &bm->zones)) { + bm->cur.zone = list_entry(bm->cur.zone->list.next, struct mem_zone_bm_rtree, list); - if (&bm->cur.zone->list != &bm->zones) { bm->cur.node = list_entry(bm->cur.zone->leaves.next, struct rtree_node, list); bm->cur.node_pfn = 0; diff --git a/kernel/printk/braille.c b/kernel/printk/braille.c index 276762f3a460..d5760c42f042 100644 --- a/kernel/printk/braille.c +++ b/kernel/printk/braille.c @@ -9,10 +9,10 @@ char *_braille_console_setup(char **str, char **brl_options) { - if (!memcmp(*str, "brl,", 4)) { + if (!strncmp(*str, "brl,", 4)) { *brl_options = ""; *str += 4; - } else if (!memcmp(str, "brl=", 4)) { + } else if (!strncmp(*str, "brl=", 4)) { *brl_options = *str + 4; *str = strchr(*brl_options, ','); if (!*str) diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h index 5d4505f30083..7fd2838fa417 100644 --- a/kernel/printk/internal.h +++ b/kernel/printk/internal.h @@ -16,11 +16,9 @@ */ #include <linux/percpu.h> -typedef __printf(2, 0) int (*printk_func_t)(int level, const char *fmt, - va_list args); +typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args); -__printf(2, 0) -int vprintk_default(int level, const char *fmt, va_list args); +int __printf(1, 0) vprintk_default(const char *fmt, va_list args); #ifdef CONFIG_PRINTK_NMI @@ -33,10 +31,9 @@ extern raw_spinlock_t logbuf_lock; * via per-CPU variable. */ DECLARE_PER_CPU(printk_func_t, printk_func); -__printf(2, 0) -static inline int vprintk_func(int level, const char *fmt, va_list args) +static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { - return this_cpu_read(printk_func)(level, fmt, args); + return this_cpu_read(printk_func)(fmt, args); } extern atomic_t nmi_message_lost; @@ -47,10 +44,9 @@ static inline int get_nmi_message_lost(void) #else /* CONFIG_PRINTK_NMI */ -__printf(2, 0) -static inline int vprintk_func(int level, const char *fmt, va_list args) +static inline __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { - return vprintk_default(level, fmt, args); + return vprintk_default(fmt, args); } static inline int get_nmi_message_lost(void) diff --git a/kernel/printk/nmi.c b/kernel/printk/nmi.c index bc3eeb1ae6da..b69eb8a2876f 100644 --- a/kernel/printk/nmi.c +++ b/kernel/printk/nmi.c @@ -58,7 +58,7 @@ static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq); * one writer running. But the buffer might get flushed from another * CPU, so we need to be careful. */ -static int vprintk_nmi(int level, const char *fmt, va_list args) +static int vprintk_nmi(const char *fmt, va_list args) { struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq); int add = 0; @@ -79,16 +79,7 @@ again: if (!len) smp_rmb(); - if (level != LOGLEVEL_DEFAULT) { - add = snprintf(s->buffer + len, sizeof(s->buffer) - len, - KERN_SOH "%c", '0' + level); - add += vsnprintf(s->buffer + len + add, - sizeof(s->buffer) - len - add, - fmt, args); - } else { - add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, - fmt, args); - } + add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args); /* * Do it once again if the buffer has been flushed in the meantime. diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a5ef95ca18c9..eea6dbc2d8cf 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1930,28 +1930,7 @@ asmlinkage int printk_emit(int facility, int level, } EXPORT_SYMBOL(printk_emit); -#ifdef CONFIG_PRINTK -#define define_pr_level(func, loglevel) \ -asmlinkage __visible void func(const char *fmt, ...) \ -{ \ - va_list args; \ - \ - va_start(args, fmt); \ - vprintk_default(loglevel, fmt, args); \ - va_end(args); \ -} \ -EXPORT_SYMBOL(func) - -define_pr_level(__pr_emerg, LOGLEVEL_EMERG); -define_pr_level(__pr_alert, LOGLEVEL_ALERT); -define_pr_level(__pr_crit, LOGLEVEL_CRIT); -define_pr_level(__pr_err, LOGLEVEL_ERR); -define_pr_level(__pr_warn, LOGLEVEL_WARNING); -define_pr_level(__pr_notice, LOGLEVEL_NOTICE); -define_pr_level(__pr_info, LOGLEVEL_INFO); -#endif - -int vprintk_default(int level, const char *fmt, va_list args) +int vprintk_default(const char *fmt, va_list args) { int r; @@ -1961,7 +1940,7 @@ int vprintk_default(int level, const char *fmt, va_list args) return r; } #endif - r = vprintk_emit(0, level, NULL, 0, fmt, args); + r = vprintk_emit(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args); return r; } @@ -1994,7 +1973,7 @@ asmlinkage __visible int printk(const char *fmt, ...) int r; va_start(args, fmt); - r = vprintk_func(LOGLEVEL_DEFAULT, fmt, args); + r = vprintk_func(fmt, args); va_end(args); return r; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5c883fe8e440..2a906f20fba7 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -74,6 +74,7 @@ #include <linux/context_tracking.h> #include <linux/compiler.h> #include <linux/frame.h> +#include <linux/prefetch.h> #include <asm/switch_to.h> #include <asm/tlb.h> @@ -2972,6 +2973,23 @@ EXPORT_PER_CPU_SYMBOL(kstat); EXPORT_PER_CPU_SYMBOL(kernel_cpustat); /* + * The function fair_sched_class.update_curr accesses the struct curr + * and its field curr->exec_start; when called from task_sched_runtime(), + * we observe a high rate of cache misses in practice. + * Prefetching this data results in improved performance. + */ +static inline void prefetch_curr_exec_start(struct task_struct *p) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + struct sched_entity *curr = (&p->se)->cfs_rq->curr; +#else + struct sched_entity *curr = (&task_rq(p)->cfs)->curr; +#endif + prefetch(curr); + prefetch(&curr->exec_start); +} + +/* * Return accounted runtime for the task. * In case the task is currently running, return the runtime plus current's * pending runtime that have not been accounted yet. @@ -3005,6 +3023,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) * thread, breaking clock_gettime(). */ if (task_current(rq, p) && task_on_rq_queued(p)) { + prefetch_curr_exec_start(p); update_rq_clock(rq); p->sched_class->update_curr(rq); } diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 5be58820465c..d4184498c9f5 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -168,7 +168,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) if (old_idx == IDX_INVALID) { cp->size++; - cp->elements[cp->size - 1].dl = 0; + cp->elements[cp->size - 1].dl = dl; cp->elements[cp->size - 1].cpu = cpu; cp->elements[cpu].idx = cp->size - 1; cpudl_change_key(cp, cp->size - 1, dl); diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 1934f658c036..a846cf89eb96 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -263,6 +263,11 @@ void account_idle_time(cputime_t cputime) cpustat[CPUTIME_IDLE] += (__force u64) cputime; } +/* + * When a guest is interrupted for a longer amount of time, missed clock + * ticks are not redelivered later. Due to that, this function may on + * occasion account more time than the calling functions think elapsed. + */ static __always_inline cputime_t steal_account_process_time(cputime_t maxtime) { #ifdef CONFIG_PARAVIRT @@ -371,7 +376,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, * idle, or potentially user or system time. Due to rounding, * other time can exceed ticks occasionally. */ - other = account_other_time(cputime); + other = account_other_time(ULONG_MAX); if (other >= cputime) return; cputime -= other; @@ -486,7 +491,7 @@ void account_process_tick(struct task_struct *p, int user_tick) } cputime = cputime_one_jiffy; - steal = steal_account_process_time(cputime); + steal = steal_account_process_time(ULONG_MAX); if (steal >= cputime) return; @@ -508,13 +513,21 @@ void account_process_tick(struct task_struct *p, int user_tick) */ void account_idle_ticks(unsigned long ticks) { + cputime_t cputime, steal; if (sched_clock_irqtime) { irqtime_account_idle_ticks(ticks); return; } - account_idle_time(jiffies_to_cputime(ticks)); + cputime = jiffies_to_cputime(ticks); + steal = steal_account_process_time(ULONG_MAX); + + if (steal >= cputime) + return; + + cputime -= steal; + account_idle_time(cputime); } /* @@ -606,19 +619,25 @@ static void cputime_adjust(struct task_cputime *curr, stime = curr->stime; utime = curr->utime; - if (utime == 0) { - stime = rtime; + /* + * If either stime or both stime and utime are 0, assume all runtime is + * userspace. Once a task gets some ticks, the monotonicy code at + * 'update' will ensure things converge to the observed ratio. + */ + if (stime == 0) { + utime = rtime; goto update; } - if (stime == 0) { - utime = rtime; + if (utime == 0) { + stime = rtime; goto update; } stime = scale_stime((__force u64)stime, (__force u64)rtime, (__force u64)(stime + utime)); +update: /* * Make sure stime doesn't go backwards; this preserves monotonicity * for utime because rtime is monotonic. @@ -641,7 +660,6 @@ static void cputime_adjust(struct task_cputime *curr, stime = rtime - utime; } -update: prev->stime = stime; prev->utime = utime; out: @@ -686,6 +704,13 @@ static cputime_t get_vtime_delta(struct task_struct *tsk) unsigned long now = READ_ONCE(jiffies); cputime_t delta, other; + /* + * Unlike tick based timing, vtime based timing never has lost + * ticks, and no need for steal time accounting to make up for + * lost ticks. Vtime accounts a rounded version of actual + * elapsed time. Limit account_other_time to prevent rounding + * errors from causing elapsed vtime to go negative. + */ delta = jiffies_to_cputime(now - tsk->vtime_snap); other = account_other_time(delta); WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index fcb7f0217ff4..1ce8867283dc 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -658,8 +658,11 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * * XXX figure out if select_task_rq_dl() deals with offline cpus. */ - if (unlikely(!rq->online)) + if (unlikely(!rq->online)) { + lockdep_unpin_lock(&rq->lock, rf.cookie); rq = dl_task_offline_migration(rq, p); + rf.cookie = lockdep_pin_lock(&rq->lock); + } /* * Queueing this task back might have overloaded rq, check if we need diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4088eedea763..039de34f1521 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4269,7 +4269,7 @@ static void sync_throttle(struct task_group *tg, int cpu) pcfs_rq = tg->parent->cfs_rq[cpu]; cfs_rq->throttle_count = pcfs_rq->throttle_count; - pcfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu)); + cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu)); } /* conditionally throttle active cfs_rq's from put_prev_entity() */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b43d0b27c1fe..a13bbdaab47d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2140,6 +2140,21 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, return 0; } +static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + if (*negp) + return -EINVAL; + *valp = *lvalp; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long)val; + } + return 0; +} + static const char proc_wspace_sep[] = { ' ', '\t', '\n' }; static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, @@ -2259,8 +2274,27 @@ static int do_proc_dointvec(struct ctl_table *table, int write, int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,buffer,lenp,ppos, - NULL,NULL); + return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); +} + +/** + * proc_douintvec - read a vector of unsigned integers + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. + * + * Returns 0 on success. + */ +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_conv, NULL); } /* @@ -2858,6 +2892,12 @@ int proc_dointvec(struct ctl_table *table, int write, return -ENOSYS; } +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -2903,6 +2943,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, * exception granted :-) */ EXPORT_SYMBOL(proc_dointvec); +EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 3b65746c7f15..e07fb093f819 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -401,7 +401,10 @@ static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); - now = ktime_to_ns(tkr->base) + timekeeping_get_ns(tkr); + now = ktime_to_ns(tkr->base); + + now += clocksource_delta(tkr->read(tkr->clock), + tkr->cycle_last, tkr->mask); } while (read_seqcount_retry(&tkf->seq, seq)); return now; diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index f6bd65236712..107310a6f36f 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -23,7 +23,9 @@ #include "timekeeping_internal.h" -static unsigned int sleep_time_bin[32] = {0}; +#define NUM_BINS 32 + +static unsigned int sleep_time_bin[NUM_BINS] = {0}; static int tk_debug_show_sleep_time(struct seq_file *s, void *data) { @@ -69,6 +71,9 @@ late_initcall(tk_debug_sleep_time_init); void tk_debug_account_sleep_time(struct timespec64 *t) { - sleep_time_bin[fls(t->tv_sec)]++; + /* Cap bin index so we don't overflow the array */ + int bin = min(fls(t->tv_sec), NUM_BINS-1); + + sleep_time_bin[bin]++; } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 555670a5143c..32bf6f75a8fe 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1496,6 +1496,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); u64 expires = KTIME_MAX; unsigned long nextevt; + bool is_max_delta; /* * Pretend that there is no timer pending if the cpu is offline. @@ -1506,6 +1507,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) spin_lock(&base->lock); nextevt = __next_timer_interrupt(base); + is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA); base->next_expiry = nextevt; /* * We have a fresh next event. Check whether we can forward the base: @@ -1519,7 +1521,8 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) expires = basem; base->is_idle = false; } else { - expires = basem + (nextevt - basej) * TICK_NSEC; + if (!is_max_delta) + expires = basem + (nextevt - basej) * TICK_NSEC; /* * If we expect to sleep more than a tick, mark the base idle: */ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7598e6ca817a..dbafc5df03f3 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -223,7 +223,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, what |= MASK_TC_BIT(op_flags, META); what |= MASK_TC_BIT(op_flags, PREFLUSH); what |= MASK_TC_BIT(op_flags, FUA); - if (op == REQ_OP_DISCARD) + if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE) what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 5d845ffd7982..5ba520b544d7 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -30,7 +30,7 @@ #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U -#define BUCKET_LOCKS_PER_CPU 128UL +#define BUCKET_LOCKS_PER_CPU 32UL static u32 head_hashfn(struct rhashtable *ht, const struct bucket_table *tbl, @@ -70,7 +70,7 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, unsigned int nr_pcpus = num_possible_cpus(); #endif - nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL); + nr_pcpus = min_t(unsigned int, nr_pcpus, 64UL); size = roundup_pow_of_two(nr_pcpus * ht->p.locks_mul); /* Never allocate more than 0.5 locks per bucket */ @@ -83,6 +83,9 @@ static int alloc_bucket_locks(struct rhashtable *ht, struct bucket_table *tbl, tbl->locks = vmalloc(size * sizeof(spinlock_t)); else #endif + if (gfp != GFP_KERNEL) + gfp |= __GFP_NOWARN | __GFP_NORETRY; + tbl->locks = kmalloc_array(size, sizeof(spinlock_t), gfp); if (!tbl->locks) @@ -321,12 +324,14 @@ static int rhashtable_expand(struct rhashtable *ht) static int rhashtable_shrink(struct rhashtable *ht) { struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht); - unsigned int size; + unsigned int nelems = atomic_read(&ht->nelems); + unsigned int size = 0; int err; ASSERT_RHT_MUTEX(ht); - size = roundup_pow_of_two(atomic_read(&ht->nelems) * 3 / 2); + if (nelems) + size = roundup_pow_of_two(nelems * 3 / 2); if (size < ht->p.min_size) size = ht->p.min_size; diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index 33f655ef48cd..9c5fe8110413 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -40,8 +40,8 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, long unsigned long c, data; /* Fall back to byte-at-a-time if we get a page fault */ - if (unlikely(unsafe_get_user(c,(unsigned long __user *)(src+res)))) - break; + unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); + *(unsigned long *)(dst+res) = c; if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); @@ -56,8 +56,7 @@ byte_at_a_time: while (max) { char c; - if (unlikely(unsafe_get_user(c,src+res))) - return -EFAULT; + unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; @@ -76,6 +75,7 @@ byte_at_a_time: * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ +efault: return -EFAULT; } diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 2625943625d7..8e105ed4df12 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -45,8 +45,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, src -= align; max += align; - if (unlikely(unsafe_get_user(c,(unsigned long __user *)src))) - return 0; + unsafe_get_user(c, (unsigned long __user *)src, efault); c |= aligned_byte_mask(align); for (;;) { @@ -61,8 +60,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, if (unlikely(max <= sizeof(unsigned long))) break; max -= sizeof(unsigned long); - if (unlikely(unsafe_get_user(c,(unsigned long __user *)(src+res)))) - return 0; + unsafe_get_user(c, (unsigned long __user *)(src+res), efault); } res -= align; @@ -77,6 +75,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's 0. */ +efault: return 0; } diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 297fdb5e74bd..64e899b63337 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -38,7 +38,7 @@ MODULE_PARM_DESC(runs, "Number of test runs per variant (default: 4)"); static int max_size = 0; module_param(max_size, int, 0); -MODULE_PARM_DESC(runs, "Maximum table size (default: calculated)"); +MODULE_PARM_DESC(max_size, "Maximum table size (default: calculated)"); static bool shrinking = false; module_param(shrinking, bool, 0); diff --git a/mm/Kconfig b/mm/Kconfig index 78a23c5c302d..be0ee11fa0d9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -262,7 +262,14 @@ config COMPACTION select MIGRATION depends on MMU help - Allows the compaction of memory for the allocation of huge pages. + Compaction is the only memory management component to form + high order (larger physically contiguous) memory blocks + reliably. The page allocator relies on compaction heavily and + the lack of the feature can lead to unexpected OOM killer + invocations for high order memory requests. You shouldn't + disable this option unless there really is a strong reason for + it and then we would be really interested to hear about that at + linux-mm@kvack.org. # # support for page migration diff --git a/mm/Makefile b/mm/Makefile index fc059666c760..2ca1faf3fa09 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -21,6 +21,9 @@ KCOV_INSTRUMENT_memcontrol.o := n KCOV_INSTRUMENT_mmzone.o := n KCOV_INSTRUMENT_vmstat.o := n +# Since __builtin_frame_address does work as used, disable the warning. +CFLAGS_usercopy.o += $(call cc-disable-warning, frame-address) + mmu-y := nommu.o mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ @@ -99,3 +102,4 @@ obj-$(CONFIG_USERFAULTFD) += userfaultfd.o obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o obj-$(CONFIG_FRAME_VECTOR) += frame_vector.o obj-$(CONFIG_DEBUG_PAGE_REF) += debug_page_ref.o +obj-$(CONFIG_HARDENED_USERCOPY) += usercopy.o diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2373f0a7d340..2db2112aa31e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1512,7 +1512,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, struct page *page; pgtable_t pgtable; pmd_t _pmd; - bool young, write, dirty; + bool young, write, dirty, soft_dirty; unsigned long addr; int i; @@ -1546,6 +1546,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, write = pmd_write(*pmd); young = pmd_young(*pmd); dirty = pmd_dirty(*pmd); + soft_dirty = pmd_soft_dirty(*pmd); pmdp_huge_split_prepare(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); @@ -1562,6 +1563,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, swp_entry_t swp_entry; swp_entry = make_migration_entry(page + i, write); entry = swp_entry_to_pte(swp_entry); + if (soft_dirty) + entry = pte_swp_mksoft_dirty(entry); } else { entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(entry, vma); @@ -1569,6 +1572,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pte_wrprotect(entry); if (!young) entry = pte_mkold(entry); + if (soft_dirty) + entry = pte_mksoft_dirty(entry); } if (dirty) SetPageDirty(page + i); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b9aa1b0b38b0..87e11d8ad536 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1448,6 +1448,7 @@ static void dissolve_free_huge_page(struct page *page) list_del(&page->lru); h->free_huge_pages--; h->free_huge_pages_node[nid]--; + h->max_huge_pages--; update_and_free_page(h, page); } spin_unlock(&hugetlb_lock); diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index b6728a33a4ac..baabaad4a4aa 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -217,11 +217,8 @@ void quarantine_reduce(void) new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) / QUARANTINE_FRACTION; percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus(); - if (WARN_ONCE(new_quarantine_size < percpu_quarantines, - "Too little memory, disabling global KASAN quarantine.\n")) - new_quarantine_size = 0; - else - new_quarantine_size -= percpu_quarantines; + new_quarantine_size = (new_quarantine_size < percpu_quarantines) ? + 0 : new_quarantine_size - percpu_quarantines; WRITE_ONCE(quarantine_size, new_quarantine_size); last = global_quarantine.head; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 66beca1ad92f..9a6a51a7c416 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2337,8 +2337,11 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) return 0; memcg = get_mem_cgroup_from_mm(current->mm); - if (!mem_cgroup_is_root(memcg)) + if (!mem_cgroup_is_root(memcg)) { ret = memcg_kmem_charge_memcg(page, gfp, order, memcg); + if (!ret) + __SetPageKmemcg(page); + } css_put(&memcg->css); return ret; } @@ -2365,6 +2368,11 @@ void memcg_kmem_uncharge(struct page *page, int order) page_counter_uncharge(&memcg->memsw, nr_pages); page->mem_cgroup = NULL; + + /* slab pages do not have PageKmemcg flag set */ + if (PageKmemcg(page)) + __ClearPageKmemcg(page); + css_put_many(&memcg->css, nr_pages); } #endif /* !CONFIG_SLOB */ @@ -4069,14 +4077,14 @@ static struct cftype mem_cgroup_legacy_files[] = { static DEFINE_IDR(mem_cgroup_idr); -static void mem_cgroup_id_get(struct mem_cgroup *memcg) +static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) { - atomic_inc(&memcg->id.ref); + atomic_add(n, &memcg->id.ref); } -static void mem_cgroup_id_put(struct mem_cgroup *memcg) +static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { - if (atomic_dec_and_test(&memcg->id.ref)) { + if (atomic_sub_and_test(n, &memcg->id.ref)) { idr_remove(&mem_cgroup_idr, memcg->id.id); memcg->id.id = 0; @@ -4085,6 +4093,16 @@ static void mem_cgroup_id_put(struct mem_cgroup *memcg) } } +static inline void mem_cgroup_id_get(struct mem_cgroup *memcg) +{ + mem_cgroup_id_get_many(memcg, 1); +} + +static inline void mem_cgroup_id_put(struct mem_cgroup *memcg) +{ + mem_cgroup_id_put_many(memcg, 1); +} + /** * mem_cgroup_from_id - look up a memcg from a memcg id * @id: the memcg id to look up @@ -4719,6 +4737,8 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.from)) page_counter_uncharge(&mc.from->memsw, mc.moved_swap); + mem_cgroup_id_put_many(mc.from, mc.moved_swap); + /* * we charged both to->memory and to->memsw, so we * should uncharge to->memory. @@ -4726,9 +4746,9 @@ static void __mem_cgroup_clear_mc(void) if (!mem_cgroup_is_root(mc.to)) page_counter_uncharge(&mc.to->memory, mc.moved_swap); - css_put_many(&mc.from->css, mc.moved_swap); + mem_cgroup_id_get_many(mc.to, mc.moved_swap); + css_put_many(&mc.to->css, mc.moved_swap); - /* we've already done css_get(mc.to) */ mc.moved_swap = 0; } memcg_oom_recover(from); @@ -5537,8 +5557,10 @@ static void uncharge_list(struct list_head *page_list) else nr_file += nr_pages; pgpgout++; - } else + } else { nr_kmem += 1 << compound_order(page); + __ClearPageKmemcg(page); + } page->mem_cgroup = NULL; } while (next != page_list); @@ -5781,6 +5803,24 @@ static int __init mem_cgroup_init(void) subsys_initcall(mem_cgroup_init); #ifdef CONFIG_MEMCG_SWAP +static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) +{ + while (!atomic_inc_not_zero(&memcg->id.ref)) { + /* + * The root cgroup cannot be destroyed, so it's refcount must + * always be >= 1. + */ + if (WARN_ON_ONCE(memcg == root_mem_cgroup)) { + VM_BUG_ON(1); + break; + } + memcg = parent_mem_cgroup(memcg); + if (!memcg) + memcg = root_mem_cgroup; + } + return memcg; +} + /** * mem_cgroup_swapout - transfer a memsw charge to swap * @page: page whose memsw charge to transfer @@ -5790,7 +5830,7 @@ subsys_initcall(mem_cgroup_init); */ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) { - struct mem_cgroup *memcg; + struct mem_cgroup *memcg, *swap_memcg; unsigned short oldid; VM_BUG_ON_PAGE(PageLRU(page), page); @@ -5805,16 +5845,27 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (!memcg) return; - mem_cgroup_id_get(memcg); - oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); + /* + * In case the memcg owning these pages has been offlined and doesn't + * have an ID allocated to it anymore, charge the closest online + * ancestor for the swap instead and transfer the memory+swap charge. + */ + swap_memcg = mem_cgroup_id_get_online(memcg); + oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg)); VM_BUG_ON_PAGE(oldid, page); - mem_cgroup_swap_statistics(memcg, true); + mem_cgroup_swap_statistics(swap_memcg, true); page->mem_cgroup = NULL; if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memory, 1); + if (memcg != swap_memcg) { + if (!mem_cgroup_is_root(swap_memcg)) + page_counter_charge(&swap_memcg->memsw, 1); + page_counter_uncharge(&memcg->memsw, 1); + } + /* * Interrupts should be disabled here because the caller holds the * mapping->tree_lock lock which is taken with interrupts-off. It is @@ -5853,11 +5904,14 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) if (!memcg) return 0; + memcg = mem_cgroup_id_get_online(memcg); + if (!mem_cgroup_is_root(memcg) && - !page_counter_try_charge(&memcg->swap, 1, &counter)) + !page_counter_try_charge(&memcg->swap, 1, &counter)) { + mem_cgroup_id_put(memcg); return -ENOMEM; + } - mem_cgroup_id_get(memcg); oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); VM_BUG_ON_PAGE(oldid, page); mem_cgroup_swap_statistics(memcg, true); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3894b65b1555..41266dc29f33 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1219,6 +1219,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) /* init node's zones as empty zones, we don't have any present pages.*/ free_area_init_node(nid, zones_size, start_pfn, zholes_size); + pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat); /* * The node we allocated has no zone fallback lists. For avoiding @@ -1249,6 +1250,7 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) static void rollback_node_hotadd(int nid, pg_data_t *pgdat) { arch_refresh_nodedata(nid, NULL); + free_percpu(pgdat->per_cpu_nodestats); arch_free_nodedata(pgdat); return; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 7d0a275df822..d53a9aa00977 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -764,7 +764,7 @@ bool task_will_free_mem(struct task_struct *task) { struct mm_struct *mm = task->mm; struct task_struct *p; - bool ret; + bool ret = true; /* * Skip tasks without mm because it might have passed its exit_mm and diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fb975cec3518..3fbe73a6fe4b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1008,10 +1008,8 @@ static __always_inline bool free_pages_prepare(struct page *page, } if (PageMappingFlags(page)) page->mapping = NULL; - if (memcg_kmem_enabled() && PageKmemcg(page)) { + if (memcg_kmem_enabled() && PageKmemcg(page)) memcg_kmem_uncharge(page, order); - __ClearPageKmemcg(page); - } if (check_free) bad += free_pages_check(page); if (bad) @@ -3756,12 +3754,10 @@ no_zone: } out: - if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page) { - if (unlikely(memcg_kmem_charge(page, gfp_mask, order))) { - __free_pages(page, order); - page = NULL; - } else - __SetPageKmemcg(page); + if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page && + unlikely(memcg_kmem_charge(page, gfp_mask, order) != 0)) { + __free_pages(page, order); + page = NULL; } if (kmemcheck_enabled && page) @@ -4064,7 +4060,7 @@ long si_mem_available(void) int lru; for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++) - pages[lru] = global_page_state(NR_LRU_BASE + lru); + pages[lru] = global_node_page_state(NR_LRU_BASE + lru); for_each_zone(zone) wmark_low += zone->watermark[WMARK_LOW]; @@ -4761,6 +4757,8 @@ int local_memory_node(int node) } #endif +static void setup_min_unmapped_ratio(void); +static void setup_min_slab_ratio(void); #else /* CONFIG_NUMA */ static void set_zonelist_order(void) @@ -5882,9 +5880,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) zone->managed_pages = is_highmem_idx(j) ? realsize : freesize; #ifdef CONFIG_NUMA zone->node = nid; - pgdat->min_unmapped_pages += (freesize*sysctl_min_unmapped_ratio) - / 100; - pgdat->min_slab_pages += (freesize * sysctl_min_slab_ratio) / 100; #endif zone->name = zone_names[j]; zone->zone_pgdat = pgdat; @@ -6805,6 +6800,12 @@ int __meminit init_per_zone_wmark_min(void) setup_per_zone_wmarks(); refresh_zone_stat_thresholds(); setup_per_zone_lowmem_reserve(); + +#ifdef CONFIG_NUMA + setup_min_unmapped_ratio(); + setup_min_slab_ratio(); +#endif + return 0; } core_initcall(init_per_zone_wmark_min) @@ -6846,43 +6847,58 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write, } #ifdef CONFIG_NUMA +static void setup_min_unmapped_ratio(void) +{ + pg_data_t *pgdat; + struct zone *zone; + + for_each_online_pgdat(pgdat) + pgdat->min_unmapped_pages = 0; + + for_each_zone(zone) + zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages * + sysctl_min_unmapped_ratio) / 100; +} + + int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { - struct pglist_data *pgdat; - struct zone *zone; int rc; rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; + setup_min_unmapped_ratio(); + + return 0; +} + +static void setup_min_slab_ratio(void) +{ + pg_data_t *pgdat; + struct zone *zone; + for_each_online_pgdat(pgdat) pgdat->min_slab_pages = 0; for_each_zone(zone) - zone->zone_pgdat->min_unmapped_pages += (zone->managed_pages * - sysctl_min_unmapped_ratio) / 100; - return 0; + zone->zone_pgdat->min_slab_pages += (zone->managed_pages * + sysctl_min_slab_ratio) / 100; } int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) { - struct pglist_data *pgdat; - struct zone *zone; int rc; rc = proc_dointvec_minmax(table, write, buffer, length, ppos); if (rc) return rc; - for_each_online_pgdat(pgdat) - pgdat->min_slab_pages = 0; + setup_min_slab_ratio(); - for_each_zone(zone) - zone->zone_pgdat->min_slab_pages += (zone->managed_pages * - sysctl_min_slab_ratio) / 100; return 0; } #endif diff --git a/mm/readahead.c b/mm/readahead.c index 65ec288dc057..c8a955b1297e 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -8,6 +8,7 @@ */ #include <linux/kernel.h> +#include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/blkdev.h> @@ -544,6 +545,14 @@ do_readahead(struct address_space *mapping, struct file *filp, if (!mapping || !mapping->a_ops) return -EINVAL; + /* + * Readahead doesn't make sense for DAX inodes, but we don't want it + * to report a failure either. Instead, we just return success and + * don't do any work. + */ + if (dax_mapping(mapping)) + return 0; + return force_page_cache_readahead(mapping, filp, index, nr); } diff --git a/mm/rmap.c b/mm/rmap.c index 709bc83703b1..1ef36404e7b2 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1284,8 +1284,9 @@ void page_add_file_rmap(struct page *page, bool compound) VM_BUG_ON_PAGE(!PageSwapBacked(page), page); __inc_node_page_state(page, NR_SHMEM_PMDMAPPED); } else { - if (PageTransCompound(page)) { - VM_BUG_ON_PAGE(!PageLocked(page), page); + if (PageTransCompound(page) && page_mapping(page)) { + VM_WARN_ON_ONCE(!PageLocked(page)); + SetPageDoubleMap(compound_head(page)); if (PageMlocked(page)) clear_page_mlock(compound_head(page)); @@ -1303,7 +1304,7 @@ static void page_remove_file_rmap(struct page *page, bool compound) { int i, nr = 1; - VM_BUG_ON_PAGE(compound && !PageTransHuge(page), page); + VM_BUG_ON_PAGE(compound && !PageHead(page), page); lock_page_memcg(page); /* Hugepages are not counted in NR_FILE_MAPPED for now. */ diff --git a/mm/shmem.c b/mm/shmem.c index 7f7748a0f9e1..fd8b2b5741b1 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3975,7 +3975,9 @@ static ssize_t shmem_enabled_store(struct kobject *kobj, struct kobj_attribute shmem_enabled_attr = __ATTR(shmem_enabled, 0644, shmem_enabled_show, shmem_enabled_store); +#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */ +#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE bool shmem_huge_enabled(struct vm_area_struct *vma) { struct inode *inode = file_inode(vma->vm_file); @@ -4006,7 +4008,7 @@ bool shmem_huge_enabled(struct vm_area_struct *vma) return false; } } -#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE && CONFIG_SYSFS */ +#endif /* CONFIG_TRANSPARENT_HUGE_PAGECACHE */ #else /* !CONFIG_SHMEM */ diff --git a/mm/slab.c b/mm/slab.c index 261147ba156f..b67271024135 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -4441,6 +4441,36 @@ static int __init slab_proc_init(void) module_init(slab_proc_init); #endif +#ifdef CONFIG_HARDENED_USERCOPY +/* + * Rejects objects that are incorrectly sized. + * + * Returns NULL if check passes, otherwise const char * to name of cache + * to indicate an error. + */ +const char *__check_heap_object(const void *ptr, unsigned long n, + struct page *page) +{ + struct kmem_cache *cachep; + unsigned int objnr; + unsigned long offset; + + /* Find and validate object. */ + cachep = page->slab_cache; + objnr = obj_to_index(cachep, page, (void *)ptr); + BUG_ON(objnr >= cachep->num); + + /* Find offset within object. */ + offset = ptr - index_to_obj(cachep, page, objnr) - obj_offset(cachep); + + /* Allow address range falling entirely within object size. */ + if (offset <= cachep->object_size && n <= cachep->object_size - offset) + return NULL; + + return cachep->name; +} +#endif /* CONFIG_HARDENED_USERCOPY */ + /** * ksize - get the actual amount of memory allocated for a given object * @objp: Pointer to the object diff --git a/mm/slub.c b/mm/slub.c index 850737bdfbd8..9adae58462f8 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3629,6 +3629,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, */ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) { + LIST_HEAD(discard); struct page *page, *h; BUG_ON(irqs_disabled()); @@ -3636,13 +3637,16 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { remove_partial(n, page); - discard_slab(s, page); + list_add(&page->lru, &discard); } else { list_slab_objects(s, page, "Objects remaining in %s on __kmem_cache_shutdown()"); } } spin_unlock_irq(&n->list_lock); + + list_for_each_entry_safe(page, h, &discard, lru) + discard_slab(s, page); } /* @@ -3764,6 +3768,46 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) EXPORT_SYMBOL(__kmalloc_node); #endif +#ifdef CONFIG_HARDENED_USERCOPY +/* + * Rejects objects that are incorrectly sized. + * + * Returns NULL if check passes, otherwise const char * to name of cache + * to indicate an error. + */ +const char *__check_heap_object(const void *ptr, unsigned long n, + struct page *page) +{ + struct kmem_cache *s; + unsigned long offset; + size_t object_size; + + /* Find object and usable object size. */ + s = page->slab_cache; + object_size = slab_ksize(s); + + /* Reject impossible pointers. */ + if (ptr < page_address(page)) + return s->name; + + /* Find offset within object. */ + offset = (ptr - page_address(page)) % s->size; + + /* Adjust for redzone and reject if within the redzone. */ + if (kmem_cache_debug(s) && s->flags & SLAB_RED_ZONE) { + if (offset < s->red_left_pad) + return s->name; + offset -= s->red_left_pad; + } + + /* Allow address range falling entirely within object size. */ + if (offset <= object_size && n <= object_size - offset) + return NULL; + + return s->name; +} +#endif /* CONFIG_HARDENED_USERCOPY */ + static size_t __ksize(const void *object) { struct page *page; diff --git a/mm/usercopy.c b/mm/usercopy.c new file mode 100644 index 000000000000..a3cc3052f830 --- /dev/null +++ b/mm/usercopy.c @@ -0,0 +1,268 @@ +/* + * This implements the various checks for CONFIG_HARDENED_USERCOPY*, + * which are designed to protect kernel memory from needless exposure + * and overwrite under many unintended conditions. This code is based + * on PAX_USERCOPY, which is: + * + * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source + * Security Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/mm.h> +#include <linux/slab.h> +#include <asm/sections.h> + +enum { + BAD_STACK = -1, + NOT_STACK = 0, + GOOD_FRAME, + GOOD_STACK, +}; + +/* + * Checks if a given pointer and length is contained by the current + * stack frame (if possible). + * + * Returns: + * NOT_STACK: not at all on the stack + * GOOD_FRAME: fully within a valid stack frame + * GOOD_STACK: fully on the stack (when can't do frame-checking) + * BAD_STACK: error condition (invalid stack position or bad stack frame) + */ +static noinline int check_stack_object(const void *obj, unsigned long len) +{ + const void * const stack = task_stack_page(current); + const void * const stackend = stack + THREAD_SIZE; + int ret; + + /* Object is not on the stack at all. */ + if (obj + len <= stack || stackend <= obj) + return NOT_STACK; + + /* + * Reject: object partially overlaps the stack (passing the + * the check above means at least one end is within the stack, + * so if this check fails, the other end is outside the stack). + */ + if (obj < stack || stackend < obj + len) + return BAD_STACK; + + /* Check if object is safely within a valid frame. */ + ret = arch_within_stack_frames(stack, stackend, obj, len); + if (ret) + return ret; + + return GOOD_STACK; +} + +static void report_usercopy(const void *ptr, unsigned long len, + bool to_user, const char *type) +{ + pr_emerg("kernel memory %s attempt detected %s %p (%s) (%lu bytes)\n", + to_user ? "exposure" : "overwrite", + to_user ? "from" : "to", ptr, type ? : "unknown", len); + /* + * For greater effect, it would be nice to do do_group_exit(), + * but BUG() actually hooks all the lock-breaking and per-arch + * Oops code, so that is used here instead. + */ + BUG(); +} + +/* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */ +static bool overlaps(const void *ptr, unsigned long n, unsigned long low, + unsigned long high) +{ + unsigned long check_low = (uintptr_t)ptr; + unsigned long check_high = check_low + n; + + /* Does not overlap if entirely above or entirely below. */ + if (check_low >= high || check_high <= low) + return false; + + return true; +} + +/* Is this address range in the kernel text area? */ +static inline const char *check_kernel_text_object(const void *ptr, + unsigned long n) +{ + unsigned long textlow = (unsigned long)_stext; + unsigned long texthigh = (unsigned long)_etext; + unsigned long textlow_linear, texthigh_linear; + + if (overlaps(ptr, n, textlow, texthigh)) + return "<kernel text>"; + + /* + * Some architectures have virtual memory mappings with a secondary + * mapping of the kernel text, i.e. there is more than one virtual + * kernel address that points to the kernel image. It is usually + * when there is a separate linear physical memory mapping, in that + * __pa() is not just the reverse of __va(). This can be detected + * and checked: + */ + textlow_linear = (unsigned long)__va(__pa(textlow)); + /* No different mapping: we're done. */ + if (textlow_linear == textlow) + return NULL; + + /* Check the secondary mapping... */ + texthigh_linear = (unsigned long)__va(__pa(texthigh)); + if (overlaps(ptr, n, textlow_linear, texthigh_linear)) + return "<linear kernel text>"; + + return NULL; +} + +static inline const char *check_bogus_address(const void *ptr, unsigned long n) +{ + /* Reject if object wraps past end of memory. */ + if ((unsigned long)ptr + n < (unsigned long)ptr) + return "<wrapped address>"; + + /* Reject if NULL or ZERO-allocation. */ + if (ZERO_OR_NULL_PTR(ptr)) + return "<null>"; + + return NULL; +} + +static inline const char *check_heap_object(const void *ptr, unsigned long n, + bool to_user) +{ + struct page *page, *endpage; + const void *end = ptr + n - 1; + bool is_reserved, is_cma; + + /* + * Some architectures (arm64) return true for virt_addr_valid() on + * vmalloced addresses. Work around this by checking for vmalloc + * first. + */ + if (is_vmalloc_addr(ptr)) + return NULL; + + if (!virt_addr_valid(ptr)) + return NULL; + + page = virt_to_head_page(ptr); + + /* Check slab allocator for flags and size. */ + if (PageSlab(page)) + return __check_heap_object(ptr, n, page); + + /* + * Sometimes the kernel data regions are not marked Reserved (see + * check below). And sometimes [_sdata,_edata) does not cover + * rodata and/or bss, so check each range explicitly. + */ + + /* Allow reads of kernel rodata region (if not marked as Reserved). */ + if (ptr >= (const void *)__start_rodata && + end <= (const void *)__end_rodata) { + if (!to_user) + return "<rodata>"; + return NULL; + } + + /* Allow kernel data region (if not marked as Reserved). */ + if (ptr >= (const void *)_sdata && end <= (const void *)_edata) + return NULL; + + /* Allow kernel bss region (if not marked as Reserved). */ + if (ptr >= (const void *)__bss_start && + end <= (const void *)__bss_stop) + return NULL; + + /* Is the object wholly within one base page? */ + if (likely(((unsigned long)ptr & (unsigned long)PAGE_MASK) == + ((unsigned long)end & (unsigned long)PAGE_MASK))) + return NULL; + + /* Allow if start and end are inside the same compound page. */ + endpage = virt_to_head_page(end); + if (likely(endpage == page)) + return NULL; + + /* + * Reject if range is entirely either Reserved (i.e. special or + * device memory), or CMA. Otherwise, reject since the object spans + * several independently allocated pages. + */ + is_reserved = PageReserved(page); + is_cma = is_migrate_cma_page(page); + if (!is_reserved && !is_cma) + goto reject; + + for (ptr += PAGE_SIZE; ptr <= end; ptr += PAGE_SIZE) { + page = virt_to_head_page(ptr); + if (is_reserved && !PageReserved(page)) + goto reject; + if (is_cma && !is_migrate_cma_page(page)) + goto reject; + } + + return NULL; + +reject: + return "<spans multiple pages>"; +} + +/* + * Validates that the given object is: + * - not bogus address + * - known-safe heap or stack object + * - not in kernel text + */ +void __check_object_size(const void *ptr, unsigned long n, bool to_user) +{ + const char *err; + + /* Skip all tests if size is zero. */ + if (!n) + return; + + /* Check for invalid addresses. */ + err = check_bogus_address(ptr, n); + if (err) + goto report; + + /* Check for bad heap object. */ + err = check_heap_object(ptr, n, to_user); + if (err) + goto report; + + /* Check for bad stack object. */ + switch (check_stack_object(ptr, n)) { + case NOT_STACK: + /* Object is not touching the current process stack. */ + break; + case GOOD_FRAME: + case GOOD_STACK: + /* + * Object is either in the correct frame (when it + * is possible to check) or just generally on the + * process stack (when frame checking not available). + */ + return; + default: + err = "<process stack>"; + goto report; + } + + /* Check for object in kernel to avoid text exposure. */ + err = check_kernel_text_object(ptr, n); + if (!err) + return; + +report: + report_usercopy(ptr, n, to_user, err); +} +EXPORT_SYMBOL(__check_object_size); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 82a116ba590e..8de138d3306b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -169,7 +169,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; - vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1; + vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 4acb1d5417aa..f24b25c25106 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -507,8 +507,8 @@ err_out: /* wakeup anybody waiting for slots to pin pages */ wake_up(&vp_wq); } - kfree(in_pages); - kfree(out_pages); + kvfree(in_pages); + kvfree(out_pages); return err; } diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index c18080ad4085..cd620fab41b0 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -267,7 +267,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) /* If old entry was unassociated with any port, then delete it. */ f = __br_fdb_get(br, br->dev->dev_addr, 0); - if (f && f->is_local && !f->dst) + if (f && f->is_local && !f->dst && !f->added_by_user) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, 0); @@ -282,7 +282,7 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) if (!br_vlan_should_use(v)) continue; f = __br_fdb_get(br, br->dev->dev_addr, v->vid); - if (f && f->is_local && !f->dst) + if (f && f->is_local && !f->dst && !f->added_by_user) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, v->vid); } @@ -764,20 +764,25 @@ out: } /* Update (create or replace) forwarding database entry */ -static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, - __u16 state, __u16 flags, __u16 vid) +static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, + const __u8 *addr, __u16 state, __u16 flags, __u16 vid) { - struct net_bridge *br = source->br; struct hlist_head *head = &br->hash[br_mac_hash(addr, vid)]; struct net_bridge_fdb_entry *fdb; bool modified = false; /* If the port cannot learn allow only local and static entries */ - if (!(state & NUD_PERMANENT) && !(state & NUD_NOARP) && + if (source && !(state & NUD_PERMANENT) && !(state & NUD_NOARP) && !(source->state == BR_STATE_LEARNING || source->state == BR_STATE_FORWARDING)) return -EPERM; + if (!source && !(state & NUD_PERMANENT)) { + pr_info("bridge: RTM_NEWNEIGH %s without NUD_PERMANENT\n", + br->dev->name); + return -EINVAL; + } + fdb = fdb_find(head, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) @@ -832,22 +837,28 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr, return 0; } -static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge_port *p, - const unsigned char *addr, u16 nlh_flags, u16 vid) +static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, + struct net_bridge_port *p, const unsigned char *addr, + u16 nlh_flags, u16 vid) { int err = 0; if (ndm->ndm_flags & NTF_USE) { + if (!p) { + pr_info("bridge: RTM_NEWNEIGH %s with NTF_USE is not supported\n", + br->dev->name); + return -EINVAL; + } local_bh_disable(); rcu_read_lock(); - br_fdb_update(p->br, p, addr, vid, true); + br_fdb_update(br, p, addr, vid, true); rcu_read_unlock(); local_bh_enable(); } else { - spin_lock_bh(&p->br->hash_lock); - err = fdb_add_entry(p, addr, ndm->ndm_state, + spin_lock_bh(&br->hash_lock); + err = fdb_add_entry(br, p, addr, ndm->ndm_state, nlh_flags, vid); - spin_unlock_bh(&p->br->hash_lock); + spin_unlock_bh(&br->hash_lock); } return err; @@ -884,6 +895,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], dev->name); return -EINVAL; } + br = p->br; vg = nbp_vlan_group(p); } @@ -895,15 +907,9 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], } /* VID was specified, so use it. */ - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, vid); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, vid); } else { - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, 0); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, 0); if (err || !vg || !vg->num_vlans) goto out; @@ -914,11 +920,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], list_for_each_entry(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; - if (dev->priv_flags & IFF_EBRIDGE) - err = br_fdb_insert(br, NULL, addr, v->vid); - else - err = __br_fdb_add(ndm, p, addr, nlh_flags, - v->vid); + err = __br_fdb_add(ndm, br, p, addr, nlh_flags, v->vid); if (err) goto out; } diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c index c83326c5ba58..ef34a02719d7 100644 --- a/net/ceph/mon_client.c +++ b/net/ceph/mon_client.c @@ -574,7 +574,7 @@ static void complete_generic_request(struct ceph_mon_generic_request *req) put_generic_request(req); } -void cancel_generic_request(struct ceph_mon_generic_request *req) +static void cancel_generic_request(struct ceph_mon_generic_request *req) { struct ceph_mon_client *monc = req->monc; struct ceph_mon_generic_request *lookup_req; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index b5ec09612ff7..a97e7b506612 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -4220,7 +4220,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) pages = ceph_alloc_page_vector(calc_pages_for(0, data_len), GFP_NOIO); - if (!pages) { + if (IS_ERR(pages)) { ceph_msg_put(m); return NULL; } diff --git a/net/ceph/string_table.c b/net/ceph/string_table.c index ca53c8319209..22fb96efcf34 100644 --- a/net/ceph/string_table.c +++ b/net/ceph/string_table.c @@ -84,12 +84,6 @@ retry: } EXPORT_SYMBOL(ceph_find_or_create_string); -static void ceph_free_string(struct rcu_head *head) -{ - struct ceph_string *cs = container_of(head, struct ceph_string, rcu); - kfree(cs); -} - void ceph_release_string(struct kref *ref) { struct ceph_string *cs = container_of(ref, struct ceph_string, kref); @@ -101,7 +95,7 @@ void ceph_release_string(struct kref *ref) } spin_unlock(&string_tree_lock); - call_rcu(&cs->rcu, ceph_free_string); + kfree_rcu(cs, rcu); } EXPORT_SYMBOL(ceph_release_string); diff --git a/net/core/dev.c b/net/core/dev.c index 4ce07dc25573..dd6ce598de89 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6045,8 +6045,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_dev_get_private); -int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(const struct net_device *dev)) +int dev_get_nest_level(struct net_device *dev) { struct net_device *lower = NULL; struct list_head *iter; @@ -6056,15 +6055,12 @@ int dev_get_nest_level(struct net_device *dev, ASSERT_RTNL(); netdev_for_each_lower_dev(dev, lower, iter) { - nest = dev_get_nest_level(lower, type_check); + nest = dev_get_nest_level(lower); if (max_nest < nest) max_nest = nest; } - if (type_check(dev)) - max_nest++; - - return max_nest; + return max_nest + 1; } EXPORT_SYMBOL(dev_get_nest_level); diff --git a/net/core/filter.c b/net/core/filter.c index 5708999f8a79..cb06aceb512a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1355,56 +1355,47 @@ static inline int bpf_try_make_writable(struct sk_buff *skb, { int err; - if (!skb_cloned(skb)) - return 0; - if (skb_clone_writable(skb, write_len)) - return 0; - err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (!err) - bpf_compute_data_end(skb); + err = skb_ensure_writable(skb, write_len); + bpf_compute_data_end(skb); + return err; } +static inline void bpf_push_mac_rcsum(struct sk_buff *skb) +{ + if (skb_at_tc_ingress(skb)) + skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len); +} + +static inline void bpf_pull_mac_rcsum(struct sk_buff *skb) +{ + if (skb_at_tc_ingress(skb)) + skb_postpull_rcsum(skb, skb_mac_header(skb), skb->mac_len); +} + static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) { - struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp); struct sk_buff *skb = (struct sk_buff *) (long) r1; - int offset = (int) r2; + unsigned int offset = (unsigned int) r2; void *from = (void *) (long) r3; unsigned int len = (unsigned int) r4; void *ptr; if (unlikely(flags & ~(BPF_F_RECOMPUTE_CSUM | BPF_F_INVALIDATE_HASH))) return -EINVAL; - - /* bpf verifier guarantees that: - * 'from' pointer points to bpf program stack - * 'len' bytes of it were initialized - * 'len' > 0 - * 'skb' is a valid pointer to 'struct sk_buff' - * - * so check for invalid 'offset' and too large 'len' - */ - if (unlikely((u32) offset > 0xffff || len > sizeof(sp->buff))) + if (unlikely(offset > 0xffff)) return -EFAULT; if (unlikely(bpf_try_make_writable(skb, offset + len))) return -EFAULT; - ptr = skb_header_pointer(skb, offset, len, sp->buff); - if (unlikely(!ptr)) - return -EFAULT; - + ptr = skb->data + offset; if (flags & BPF_F_RECOMPUTE_CSUM) - skb_postpull_rcsum(skb, ptr, len); + __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); - if (ptr == sp->buff) - /* skb_store_bits cannot return -EFAULT here */ - skb_store_bits(skb, offset, ptr, len); - if (flags & BPF_F_RECOMPUTE_CSUM) - skb_postpush_rcsum(skb, ptr, len); + __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) skb_clear_hash(skb); @@ -1425,12 +1416,12 @@ static const struct bpf_func_proto bpf_skb_store_bytes_proto = { static u64 bpf_skb_load_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { const struct sk_buff *skb = (const struct sk_buff *)(unsigned long) r1; - int offset = (int) r2; + unsigned int offset = (unsigned int) r2; void *to = (void *)(unsigned long) r3; unsigned int len = (unsigned int) r4; void *ptr; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff)) goto err_clear; ptr = skb_header_pointer(skb, offset, len, to); @@ -1458,20 +1449,17 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) { struct sk_buff *skb = (struct sk_buff *) (long) r1; - int offset = (int) r2; - __sum16 sum, *ptr; + unsigned int offset = (unsigned int) r2; + __sum16 *ptr; if (unlikely(flags & ~(BPF_F_HDR_FIELD_MASK))) return -EINVAL; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; - if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum)))) - return -EFAULT; - - ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); - if (unlikely(!ptr)) + if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; + ptr = (__sum16 *)(skb->data + offset); switch (flags & BPF_F_HDR_FIELD_MASK) { case 0: if (unlikely(from != 0)) @@ -1489,10 +1477,6 @@ static u64 bpf_l3_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) return -EINVAL; } - if (ptr == &sum) - /* skb_store_bits guaranteed to not return -EFAULT here */ - skb_store_bits(skb, offset, ptr, sizeof(sum)); - return 0; } @@ -1512,20 +1496,18 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) struct sk_buff *skb = (struct sk_buff *) (long) r1; bool is_pseudo = flags & BPF_F_PSEUDO_HDR; bool is_mmzero = flags & BPF_F_MARK_MANGLED_0; - int offset = (int) r2; - __sum16 sum, *ptr; + unsigned int offset = (unsigned int) r2; + __sum16 *ptr; if (unlikely(flags & ~(BPF_F_MARK_MANGLED_0 | BPF_F_PSEUDO_HDR | BPF_F_HDR_FIELD_MASK))) return -EINVAL; - if (unlikely((u32) offset > 0xffff)) + if (unlikely(offset > 0xffff || offset & 1)) return -EFAULT; - if (unlikely(bpf_try_make_writable(skb, offset + sizeof(sum)))) + if (unlikely(bpf_try_make_writable(skb, offset + sizeof(*ptr)))) return -EFAULT; - ptr = skb_header_pointer(skb, offset, sizeof(sum), &sum); - if (unlikely(!ptr)) - return -EFAULT; + ptr = (__sum16 *)(skb->data + offset); if (is_mmzero && !*ptr) return 0; @@ -1548,10 +1530,6 @@ static u64 bpf_l4_csum_replace(u64 r1, u64 r2, u64 from, u64 to, u64 flags) if (is_mmzero && !*ptr) *ptr = CSUM_MANGLED_0; - if (ptr == &sum) - /* skb_store_bits guaranteed to not return -EFAULT here */ - skb_store_bits(skb, offset, ptr, sizeof(sum)); - return 0; } @@ -1607,9 +1585,6 @@ static const struct bpf_func_proto bpf_csum_diff_proto = { static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb) { - if (skb_at_tc_ingress(skb)) - skb_postpush_rcsum(skb, skb_mac_header(skb), skb->mac_len); - return dev_forward_skb(dev, skb); } @@ -1648,6 +1623,8 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) if (unlikely(!skb)) return -ENOMEM; + bpf_push_mac_rcsum(skb); + return flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); } @@ -1693,6 +1670,8 @@ int skb_do_redirect(struct sk_buff *skb) return -EINVAL; } + bpf_push_mac_rcsum(skb); + return ri->flags & BPF_F_INGRESS ? __bpf_rx_skb(dev, skb) : __bpf_tx_skb(dev, skb); } @@ -1756,7 +1735,10 @@ static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) vlan_proto != htons(ETH_P_8021AD))) vlan_proto = htons(ETH_P_8021Q); + bpf_push_mac_rcsum(skb); ret = skb_vlan_push(skb, vlan_proto, vlan_tci); + bpf_pull_mac_rcsum(skb); + bpf_compute_data_end(skb); return ret; } @@ -1776,7 +1758,10 @@ static u64 bpf_skb_vlan_pop(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) struct sk_buff *skb = (struct sk_buff *) (long) r1; int ret; + bpf_push_mac_rcsum(skb); ret = skb_vlan_pop(skb); + bpf_pull_mac_rcsum(skb); + bpf_compute_data_end(skb); return ret; } @@ -2298,7 +2283,7 @@ bpf_get_skb_set_tunnel_proto(enum bpf_func_id which) } #ifdef CONFIG_SOCK_CGROUP_DATA -static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +static u64 bpf_skb_under_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *)(long)r1; struct bpf_map *map = (struct bpf_map *)(long)r2; @@ -2321,8 +2306,8 @@ static u64 bpf_skb_in_cgroup(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return cgroup_is_descendant(sock_cgroup_ptr(&sk->sk_cgrp_data), cgrp); } -static const struct bpf_func_proto bpf_skb_in_cgroup_proto = { - .func = bpf_skb_in_cgroup, +static const struct bpf_func_proto bpf_skb_under_cgroup_proto = { + .func = bpf_skb_under_cgroup, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -2402,8 +2387,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) case BPF_FUNC_get_smp_processor_id: return &bpf_get_smp_processor_id_proto; #ifdef CONFIG_SOCK_CGROUP_DATA - case BPF_FUNC_skb_in_cgroup: - return &bpf_skb_in_cgroup_proto; + case BPF_FUNC_skb_under_cgroup: + return &bpf_skb_under_cgroup_proto; #endif default: return sk_filter_func_proto(func_id); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index d07fc076bea0..febca0f1008c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2452,9 +2452,7 @@ struct fib_route_iter { static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, loff_t pos) { - struct fib_table *tb = iter->main_tb; struct key_vector *l, **tp = &iter->tnode; - struct trie *t; t_key key; /* use cache location of next-to-find key */ @@ -2462,8 +2460,6 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter, pos -= iter->pos; key = iter->key; } else { - t = (struct trie *)tb->tb_data; - iter->tnode = t->kv; iter->pos = 0; key = 0; } @@ -2504,12 +2500,12 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos) return NULL; iter->main_tb = tb; + t = (struct trie *)tb->tb_data; + iter->tnode = t->kv; if (*pos != 0) return fib_route_get_idx(iter, *pos); - t = (struct trie *)tb->tb_data; - iter->tnode = t->kv; iter->pos = 0; iter->key = 0; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5b1481be0282..113cc43df789 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -370,7 +370,6 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, tunnel->parms.o_flags, proto, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, proto); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index a917903d5e97..cc701fa70b12 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -557,6 +557,33 @@ static struct rtnl_link_ops vti_link_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +static bool is_vti_tunnel(const struct net_device *dev) +{ + return dev->netdev_ops == &vti_netdev_ops; +} + +static int vti_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct ip_tunnel *tunnel = netdev_priv(dev); + + if (!is_vti_tunnel(dev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_DOWN: + if (!net_eq(tunnel->net, dev_net(dev))) + xfrm_garbage_collect(tunnel->net); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block vti_notifier_block __read_mostly = { + .notifier_call = vti_device_event, +}; + static int __init vti_init(void) { const char *msg; @@ -564,6 +591,8 @@ static int __init vti_init(void) pr_info("IPv4 over IPsec tunneling driver\n"); + register_netdevice_notifier(&vti_notifier_block); + msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) @@ -596,6 +625,7 @@ xfrm_proto_ah_failed: xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); pernet_dev_failed: + unregister_netdevice_notifier(&vti_notifier_block); pr_err("vti init: failed to register %s\n", msg); return err; } @@ -607,6 +637,7 @@ static void __exit vti_fini(void) xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); + unregister_netdevice_notifier(&vti_notifier_block); } module_init(vti_init); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ab3e796596b1..df8425fcbc2c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3543,7 +3543,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ - keep_addr = !(how || _keep_addr <= 0); + keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6); /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { @@ -3599,7 +3599,7 @@ restart: /* re-combine the user config with event to determine if permanent * addresses are to be removed from the interface list */ - keep_addr = (!how && _keep_addr > 0); + keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); INIT_LIST_HEAD(&del_list); list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index c53b92c617c5..37ac9de713c6 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -952,8 +952,10 @@ calipso_opt_insert(struct ipv6_opt_hdr *hop, memcpy(new, hop, start); ret_val = calipso_genopt((unsigned char *)new, start, buf_len, doi_def, secattr); - if (ret_val < 0) + if (ret_val < 0) { + kfree(new); return ERR_PTR(ret_val); + } buf_len = start + ret_val; /* At this point buf_len aligns to 4n, so (buf_len & 4) pads to 8n */ diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 776d145113e1..704274cbd495 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -519,8 +519,6 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, protocol, tunnel->parms.o_key, htonl(tunnel->o_seqno)); - skb_set_inner_protocol(skb, protocol); - return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, NEXTHDR_GRE); } diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index fed40d1ec29b..0900352c924c 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -55,7 +55,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) struct icmp6hdr user_icmph; int addr_type; struct in6_addr *daddr; - int iif = 0; + int oif = 0; struct flowi6 fl6; int err; struct dst_entry *dst; @@ -78,25 +78,30 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (u->sin6_family != AF_INET6) { return -EAFNOSUPPORT; } - if (sk->sk_bound_dev_if && - sk->sk_bound_dev_if != u->sin6_scope_id) { - return -EINVAL; - } daddr = &(u->sin6_addr); - iif = u->sin6_scope_id; + if (__ipv6_addr_needs_scope_id(ipv6_addr_type(daddr))) + oif = u->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; daddr = &sk->sk_v6_daddr; } - if (!iif) - iif = sk->sk_bound_dev_if; + if (!oif) + oif = sk->sk_bound_dev_if; + + if (!oif) + oif = np->sticky_pktinfo.ipi6_ifindex; + + if (!oif && ipv6_addr_is_multicast(daddr)) + oif = np->mcast_oif; + else if (!oif) + oif = np->ucast_oif; addr_type = ipv6_addr_type(daddr); - if (__ipv6_addr_needs_scope_id(addr_type) && !iif) - return -EINVAL; - if (addr_type & IPV6_ADDR_MAPPED) + if ((__ipv6_addr_needs_scope_id(addr_type) && !oif) || + (addr_type & IPV6_ADDR_MAPPED) || + (oif && sk->sk_bound_dev_if && oif != sk->sk_bound_dev_if)) return -EINVAL; /* TODO: use ip6_datagram_send_ctl to get options from cmsg */ @@ -106,16 +111,12 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowi6_proto = IPPROTO_ICMPV6; fl6.saddr = np->saddr; fl6.daddr = *daddr; + fl6.flowi6_oif = oif; fl6.flowi6_mark = sk->sk_mark; fl6.fl6_icmp_type = user_icmph.icmp6_type; fl6.fl6_icmp_code = user_icmph.icmp6_code; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) - fl6.flowi6_oif = np->mcast_oif; - else if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->ucast_oif; - ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 4a7ae32afa09..1138eaf5c682 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -185,8 +185,12 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv, self->magic = IAS_MAGIC; self->mode = mode; - if (mode == IAS_CLIENT) - iriap_register_lsap(self, slsap_sel, mode); + if (mode == IAS_CLIENT) { + if (iriap_register_lsap(self, slsap_sel, mode)) { + kfree(self); + return NULL; + } + } self->confirm = callback; self->priv = priv; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 47e99ab8d97a..543b1d4fc33d 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -869,7 +869,7 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) /* free all potentially still buffered bcast frames */ local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf); - skb_queue_purge(&sdata->u.ap.ps.bc_buf); + ieee80211_purge_tx_queue(&local->hw, &sdata->u.ap.ps.bc_buf); mutex_lock(&local->mtx); ieee80211_vif_copy_chanctx_to_vlans(sdata, true); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 184473c257eb..ba5fc1f01e53 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1094,7 +1094,7 @@ static inline u32 drv_get_expected_throughput(struct ieee80211_local *local, trace_drv_get_expected_throughput(sta); if (local->ops->get_expected_throughput) - ret = local->ops->get_expected_throughput(sta); + ret = local->ops->get_expected_throughput(&local->hw, sta); trace_drv_return_u32(local, ret); return ret; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index c66411df9863..42120d965263 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -881,20 +881,22 @@ void ieee80211_stop_mesh(struct ieee80211_sub_if_data *sdata) netif_carrier_off(sdata->dev); + /* flush STAs and mpaths on this iface */ + sta_info_flush(sdata); + mesh_path_flush_by_iface(sdata); + /* stop the beacon */ ifmsh->mesh_id_len = 0; sdata->vif.bss_conf.enable_beacon = false; clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_BEACON_ENABLED); + + /* remove beacon */ bcn = rcu_dereference_protected(ifmsh->beacon, lockdep_is_held(&sdata->wdev.mtx)); RCU_INIT_POINTER(ifmsh->beacon, NULL); kfree_rcu(bcn, rcu_head); - /* flush STAs and mpaths on this iface */ - sta_info_flush(sdata); - mesh_path_flush_by_iface(sdata); - /* free all potentially still buffered group-addressed frames */ local->total_ps_buffered -= skb_queue_len(&ifmsh->ps.bc_buf); skb_queue_purge(&ifmsh->ps.bc_buf); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 2e8a9024625a..9dce3b157908 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1268,7 +1268,7 @@ static void sta_ps_start(struct sta_info *sta) for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]); - if (!txqi->tin.backlog_packets) + if (txqi->tin.backlog_packets) set_bit(tid, &sta->txq_buffered_tids); else clear_bit(tid, &sta->txq_buffered_tids); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index c6d5c724e032..a2a68269675d 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -771,6 +771,13 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) clear_sta_flag(sta, WLAN_STA_SP); acked = !!(info->flags & IEEE80211_TX_STAT_ACK); + + /* mesh Peer Service Period support */ + if (ieee80211_vif_is_mesh(&sta->sdata->vif) && + ieee80211_is_data_qos(fc)) + ieee80211_mpsp_trigger_process( + ieee80211_get_qos_ctl(hdr), sta, true, acked); + if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) { /* * The STA is in power save mode, so assume @@ -781,13 +788,6 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb) return; } - /* mesh Peer Service Period support */ - if (ieee80211_vif_is_mesh(&sta->sdata->vif) && - ieee80211_is_data_qos(fc)) - ieee80211_mpsp_trigger_process( - ieee80211_get_qos_ctl(hdr), - sta, true, acked); - if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) && (ieee80211_is_data(hdr->frame_control)) && (rates_idx != -1)) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 91461c415525..502396694f47 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -368,7 +368,7 @@ static void purge_old_ps_buffers(struct ieee80211_local *local) skb = skb_dequeue(&ps->bc_buf); if (skb) { purged++; - dev_kfree_skb(skb); + ieee80211_free_txskb(&local->hw, skb); } total += skb_queue_len(&ps->bc_buf); } @@ -451,7 +451,7 @@ ieee80211_tx_h_multicast_ps_buf(struct ieee80211_tx_data *tx) if (skb_queue_len(&ps->bc_buf) >= AP_MAX_BC_BUFFER) { ps_dbg(tx->sdata, "BC TX buffer full - dropping the oldest frame\n"); - dev_kfree_skb(skb_dequeue(&ps->bc_buf)); + ieee80211_free_txskb(&tx->local->hw, skb_dequeue(&ps->bc_buf)); } else tx->local->total_ps_buffered++; @@ -4275,7 +4275,7 @@ ieee80211_get_buffered_bc(struct ieee80211_hw *hw, sdata = IEEE80211_DEV_TO_SUB_IF(skb->dev); if (!ieee80211_tx_prepare(sdata, &tx, NULL, skb)) break; - dev_kfree_skb_any(skb); + ieee80211_free_txskb(hw, skb); } info = IEEE80211_SKB_CB(skb); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 9e3693128313..f8dbacf66795 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -574,7 +574,7 @@ static int exp_seq_show(struct seq_file *s, void *v) helper = rcu_dereference(nfct_help(expect->master)->helper); if (helper) { seq_printf(s, "%s%s", expect->flags ? " " : "", helper->name); - if (helper->expect_policy[expect->class].name) + if (helper->expect_policy[expect->class].name[0]) seq_printf(s, "/%s", helper->expect_policy[expect->class].name); } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index bb77a97961bf..5c0db5c64734 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -1473,7 +1473,8 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, "timeout to %u seconds for", info->timeout); nf_ct_dump_tuple(&exp->tuple); - mod_timer(&exp->timeout, jiffies + info->timeout * HZ); + mod_timer_pending(&exp->timeout, + jiffies + info->timeout * HZ); } spin_unlock_bh(&nf_conntrack_expect_lock); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 050bb3420a6b..fdfc71f416b7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1894,6 +1894,8 @@ static int ctnetlink_new_conntrack(struct net *net, struct sock *ctnl, if (!cda[CTA_TUPLE_ORIG] || !cda[CTA_TUPLE_REPLY]) return -EINVAL; + if (otuple.dst.protonum != rtuple.dst.protonum) + return -EINVAL; ct = ctnetlink_create_conntrack(net, &zone, cda, &otuple, &rtuple, u3); @@ -2362,12 +2364,8 @@ ctnetlink_glue_attach_expect(const struct nlattr *attr, struct nf_conn *ct, return PTR_ERR(exp); err = nf_ct_expect_related_report(exp, portid, report); - if (err < 0) { - nf_ct_expect_put(exp); - return err; - } - - return 0; + nf_ct_expect_put(exp); + return err; } static void ctnetlink_glue_seqadj(struct sk_buff *skb, struct nf_conn *ct, diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 8d9db9d4702b..7d77217de6a3 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1383,7 +1383,7 @@ static int process_sip_response(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } @@ -1446,7 +1446,7 @@ static int process_sip_request(struct sk_buff *skb, unsigned int protoff, return NF_DROP; } cseq = simple_strtoul(*dptr + matchoff, NULL, 10); - if (!cseq) { + if (!cseq && *(*dptr + matchoff) != '0') { nf_ct_helper_log(skb, ct, "cannot get cseq"); return NF_DROP; } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 5d36a0926b4a..f49f45081acb 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1145,10 +1145,8 @@ static int nfqnl_recv_verdict(struct net *net, struct sock *ctnl, struct nfnl_queue_net *q = nfnl_queue_pernet(net); int err; - queue = instance_lookup(q, queue_num); - if (!queue) - queue = verdict_instance_lookup(q, queue_num, - NETLINK_CB(skb).portid); + queue = verdict_instance_lookup(q, queue_num, + NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index ba7aed13e174..82c264e40278 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -59,6 +59,7 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_exthdr *priv = nft_expr_priv(expr); + u32 offset, len; if (tb[NFTA_EXTHDR_DREG] == NULL || tb[NFTA_EXTHDR_TYPE] == NULL || @@ -66,9 +67,15 @@ static int nft_exthdr_init(const struct nft_ctx *ctx, tb[NFTA_EXTHDR_LEN] == NULL) return -EINVAL; + offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); + len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + + if (offset > U8_MAX || len > U8_MAX) + return -ERANGE; + priv->type = nla_get_u8(tb[NFTA_EXTHDR_TYPE]); - priv->offset = ntohl(nla_get_be32(tb[NFTA_EXTHDR_OFFSET])); - priv->len = ntohl(nla_get_be32(tb[NFTA_EXTHDR_LEN])); + priv->offset = offset; + priv->len = len; priv->dreg = nft_parse_register(tb[NFTA_EXTHDR_DREG]); return nft_validate_register_store(ctx, priv->dreg, NULL, diff --git a/net/netfilter/nft_rbtree.c b/net/netfilter/nft_rbtree.c index 6473936d05c6..ffe9ae062d23 100644 --- a/net/netfilter/nft_rbtree.c +++ b/net/netfilter/nft_rbtree.c @@ -70,7 +70,6 @@ static bool nft_rbtree_lookup(const struct net *net, const struct nft_set *set, } else if (d > 0) parent = parent->rb_right; else { -found: if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; @@ -84,9 +83,12 @@ found: } } - if (set->flags & NFT_SET_INTERVAL && interval != NULL) { - rbe = interval; - goto found; + if (set->flags & NFT_SET_INTERVAL && interval != NULL && + nft_set_elem_active(&interval->ext, genmask) && + !nft_rbtree_interval_end(interval)) { + spin_unlock_bh(&nft_rbtree_lock); + *ext = &interval->ext; + return true; } out: spin_unlock_bh(&nft_rbtree_lock); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c644c78ed485..e054a748ff25 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -433,7 +433,6 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple tuple; struct nf_conntrack_tuple_hash *h; - enum ip_conntrack_info ctinfo; struct nf_conn *ct; unsigned int dataoff; u8 protonum; @@ -458,13 +457,8 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, ct = nf_ct_tuplehash_to_ctrack(h); - ctinfo = ovs_ct_get_info(h); - if (ctinfo == IP_CT_NEW) { - /* This should not happen. */ - WARN_ONCE(1, "ovs_ct_find_existing: new packet for %p\n", ct); - } skb->nfct = &ct->ct_general; - skb->nfctinfo = ctinfo; + skb->nfctinfo = ovs_ct_get_info(h); return ct; } diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c index 1a1fcec88695..5aaf3babfc3f 100644 --- a/net/openvswitch/vport-geneve.c +++ b/net/openvswitch/vport-geneve.c @@ -93,7 +93,14 @@ static struct vport *geneve_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + goto error; + } + rtnl_unlock(); return vport; error: diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c index 7f8897f33a67..0e72d95b0e8f 100644 --- a/net/openvswitch/vport-gre.c +++ b/net/openvswitch/vport-gre.c @@ -54,6 +54,7 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) struct net *net = ovs_dp_get_net(parms->dp); struct net_device *dev; struct vport *vport; + int err; vport = ovs_vport_alloc(0, &ovs_gre_vport_ops, parms); if (IS_ERR(vport)) @@ -67,9 +68,15 @@ static struct vport *gre_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); - rtnl_unlock(); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + return ERR_PTR(err); + } + rtnl_unlock(); return vport; } diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index 434e04c3a189..95c36147a6e1 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -140,7 +140,7 @@ internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) static void internal_set_rx_headroom(struct net_device *dev, int new_hr) { - dev->needed_headroom = new_hr; + dev->needed_headroom = new_hr < 0 ? 0 : new_hr; } static const struct net_device_ops internal_dev_netdev_ops = { diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index 5eb7694348b5..7eb955e453e6 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -130,7 +130,14 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) return ERR_CAST(dev); } - dev_change_flags(dev, dev->flags | IFF_UP); + err = dev_change_flags(dev, dev->flags | IFF_UP); + if (err < 0) { + rtnl_delete_link(dev); + rtnl_unlock(); + ovs_vport_free(vport); + goto error; + } + rtnl_unlock(); return vport; error: diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 1bb9e7ac9e14..ff83fb1ddd47 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -425,6 +425,7 @@ struct rxrpc_call { spinlock_t lock; rwlock_t state_lock; /* lock for state transition */ atomic_t usage; + atomic_t skb_count; /* Outstanding packets on this call */ atomic_t sequence; /* Tx data packet sequence counter */ u32 local_abort; /* local abort code */ u32 remote_abort; /* remote abort code */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 0b2832141bd0..9bae21e66d65 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -130,6 +130,7 @@ static int rxrpc_accept_incoming_call(struct rxrpc_local *local, call->state = RXRPC_CALL_SERVER_ACCEPTING; list_add_tail(&call->accept_link, &rx->acceptq); rxrpc_get_call(call); + atomic_inc(&call->skb_count); nsp = rxrpc_skb(notification); nsp->call = call; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index fc32aa5764a2..e60cf65c2232 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -460,6 +460,7 @@ static void rxrpc_insert_oos_packet(struct rxrpc_call *call, ASSERTCMP(sp->call, ==, NULL); sp->call = call; rxrpc_get_call(call); + atomic_inc(&call->skb_count); /* insert into the buffer in sequence order */ spin_lock_bh(&call->lock); @@ -734,6 +735,7 @@ all_acked: skb->mark = RXRPC_SKB_MARK_FINAL_ACK; sp->call = call; rxrpc_get_call(call); + atomic_inc(&call->skb_count); spin_lock_bh(&call->lock); if (rxrpc_queue_rcv_skb(call, skb, true, true) < 0) BUG(); @@ -793,6 +795,7 @@ static int rxrpc_post_message(struct rxrpc_call *call, u32 mark, u32 error, sp->error = error; sp->call = call; rxrpc_get_call(call); + atomic_inc(&call->skb_count); spin_lock_bh(&call->lock); ret = rxrpc_queue_rcv_skb(call, skb, true, fatal); @@ -834,6 +837,9 @@ void rxrpc_process_call(struct work_struct *work) return; } + if (!call->conn) + goto skip_msg_init; + /* there's a good chance we're going to have to send a message, so set * one up in advance */ msg.msg_name = &call->conn->params.peer->srx.transport; @@ -856,6 +862,7 @@ void rxrpc_process_call(struct work_struct *work) memset(iov, 0, sizeof(iov)); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); +skip_msg_init: /* deal with events of a final nature */ if (test_bit(RXRPC_CALL_EV_RCVD_ERROR, &call->events)) { diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 91287c9d01bb..ae057e0740f3 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -275,6 +275,7 @@ error: list_del_init(&call->link); write_unlock_bh(&rxrpc_call_lock); + set_bit(RXRPC_CALL_RELEASED, &call->flags); call->state = RXRPC_CALL_DEAD; rxrpc_put_call(call); _leave(" = %d", ret); @@ -287,6 +288,7 @@ error: */ found_user_ID_now_present: write_unlock(&rx->call_lock); + set_bit(RXRPC_CALL_RELEASED, &call->flags); call->state = RXRPC_CALL_DEAD; rxrpc_put_call(call); _leave(" = -EEXIST [%p]", call); @@ -491,15 +493,9 @@ void rxrpc_release_call(struct rxrpc_call *call) spin_lock_bh(&call->lock); while ((skb = skb_dequeue(&call->rx_queue)) || (skb = skb_dequeue(&call->rx_oos_queue))) { - sp = rxrpc_skb(skb); - if (sp->call) { - ASSERTCMP(sp->call, ==, call); - rxrpc_put_call(call); - sp->call = NULL; - } - skb->destructor = NULL; spin_unlock_bh(&call->lock); + sp = rxrpc_skb(skb); _debug("- zap %s %%%u #%u", rxrpc_pkts[sp->hdr.type], sp->hdr.serial, sp->hdr.seq); @@ -605,6 +601,7 @@ void __rxrpc_put_call(struct rxrpc_call *call) if (atomic_dec_and_test(&call->usage)) { _debug("call %d dead", call->debug_id); + WARN_ON(atomic_read(&call->skb_count) != 0); ASSERTCMP(call->state, ==, RXRPC_CALL_DEAD); rxrpc_queue_work(&call->destroyer); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 991a20d25093..70bb77818dea 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -55,9 +55,6 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb, if (test_bit(RXRPC_CALL_TERMINAL_MSG, &call->flags)) { _debug("already terminated"); ASSERTCMP(call->state, >=, RXRPC_CALL_COMPLETE); - skb->destructor = NULL; - sp->call = NULL; - rxrpc_put_call(call); rxrpc_free_skb(skb); return 0; } @@ -111,13 +108,7 @@ int rxrpc_queue_rcv_skb(struct rxrpc_call *call, struct sk_buff *skb, ret = 0; out: - /* release the socket buffer */ - if (skb) { - skb->destructor = NULL; - sp->call = NULL; - rxrpc_put_call(call); - rxrpc_free_skb(skb); - } + rxrpc_free_skb(skb); _leave(" = %d", ret); return ret; @@ -133,11 +124,15 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, struct rxrpc_skb_priv *sp; bool terminal; int ret, ackbit, ack; + u32 serial; + u8 flags; _enter("{%u,%u},,{%u}", call->rx_data_post, call->rx_first_oos, seq); sp = rxrpc_skb(skb); ASSERTCMP(sp->call, ==, NULL); + flags = sp->hdr.flags; + serial = sp->hdr.serial; spin_lock(&call->lock); @@ -200,8 +195,9 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, sp->call = call; rxrpc_get_call(call); - terminal = ((sp->hdr.flags & RXRPC_LAST_PACKET) && - !(sp->hdr.flags & RXRPC_CLIENT_INITIATED)); + atomic_inc(&call->skb_count); + terminal = ((flags & RXRPC_LAST_PACKET) && + !(flags & RXRPC_CLIENT_INITIATED)); ret = rxrpc_queue_rcv_skb(call, skb, false, terminal); if (ret < 0) { if (ret == -ENOMEM || ret == -ENOBUFS) { @@ -213,12 +209,13 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, } skb = NULL; + sp = NULL; _debug("post #%u", seq); ASSERTCMP(call->rx_data_post, ==, seq); call->rx_data_post++; - if (sp->hdr.flags & RXRPC_LAST_PACKET) + if (flags & RXRPC_LAST_PACKET) set_bit(RXRPC_CALL_RCVD_LAST, &call->flags); /* if we've reached an out of sequence packet then we need to drain @@ -234,7 +231,7 @@ static int rxrpc_fast_process_data(struct rxrpc_call *call, spin_unlock(&call->lock); atomic_inc(&call->ackr_not_idle); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, sp->hdr.serial, false); + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false); _leave(" = 0 [posted]"); return 0; @@ -247,7 +244,7 @@ out: discard_and_ack: _debug("discard and ACK packet %p", skb); - __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true); + __rxrpc_propose_ACK(call, ack, serial, true); discard: spin_unlock(&call->lock); rxrpc_free_skb(skb); @@ -255,7 +252,7 @@ discard: return 0; enqueue_and_ack: - __rxrpc_propose_ACK(call, ack, sp->hdr.serial, true); + __rxrpc_propose_ACK(call, ack, serial, true); enqueue_packet: _net("defer skb %p", skb); spin_unlock(&call->lock); @@ -575,13 +572,13 @@ done: * post connection-level events to the connection * - this includes challenges, responses and some aborts */ -static bool rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, +static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, struct sk_buff *skb) { _enter("%p,%p", conn, skb); skb_queue_tail(&conn->rx_queue, skb); - return rxrpc_queue_conn(conn); + rxrpc_queue_conn(conn); } /* @@ -702,7 +699,6 @@ void rxrpc_data_ready(struct sock *sk) rcu_read_lock(); -retry_find_conn: conn = rxrpc_find_connection_rcu(local, skb); if (!conn) goto cant_route_call; @@ -710,8 +706,7 @@ retry_find_conn: if (sp->hdr.callNumber == 0) { /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); - if (!rxrpc_post_packet_to_conn(conn, skb)) - goto retry_find_conn; + rxrpc_post_packet_to_conn(conn, skb); } else { /* Call-bound packets are routed by connection channel. */ unsigned int channel = sp->hdr.cid & RXRPC_CHANNELMASK; @@ -749,6 +744,8 @@ cant_route_call: if (sp->hdr.type != RXRPC_PACKET_TYPE_ABORT) { _debug("reject type %d",sp->hdr.type); rxrpc_reject_packet(local, skb); + } else { + rxrpc_free_skb(skb); } _leave(" [no call]"); return; diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index a3fa2ed85d63..9ed66d533002 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -203,6 +203,9 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, } /* we transferred the whole data packet */ + if (!(flags & MSG_PEEK)) + rxrpc_kernel_data_consumed(call, skb); + if (sp->hdr.flags & RXRPC_LAST_PACKET) { _debug("last"); if (rxrpc_conn_is_client(call->conn)) { @@ -360,28 +363,6 @@ wait_error: } /** - * rxrpc_kernel_data_delivered - Record delivery of data message - * @skb: Message holding data - * - * Record the delivery of a data message. This permits RxRPC to keep its - * tracking correct. The socket buffer will be deleted. - */ -void rxrpc_kernel_data_delivered(struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxrpc_call *call = sp->call; - - ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv); - ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1); - call->rx_data_recv = sp->hdr.seq; - - ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten); - rxrpc_free_skb(skb); -} - -EXPORT_SYMBOL(rxrpc_kernel_data_delivered); - -/** * rxrpc_kernel_is_data_last - Determine if data message is last one * @skb: Message holding data * diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index eee0cfd9ac8c..06c51d4b622d 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -98,11 +98,39 @@ static void rxrpc_hard_ACK_data(struct rxrpc_call *call, spin_unlock_bh(&call->lock); } +/** + * rxrpc_kernel_data_consumed - Record consumption of data message + * @call: The call to which the message pertains. + * @skb: Message holding data + * + * Record the consumption of a data message and generate an ACK if appropriate. + * The call state is shifted if this was the final packet. The caller must be + * in process context with no spinlocks held. + * + * TODO: Actually generate the ACK here rather than punting this to the + * workqueue. + */ +void rxrpc_kernel_data_consumed(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + _enter("%d,%p{%u}", call->debug_id, skb, sp->hdr.seq); + + ASSERTCMP(sp->call, ==, call); + ASSERTCMP(sp->hdr.type, ==, RXRPC_PACKET_TYPE_DATA); + + /* TODO: Fix the sequence number tracking */ + ASSERTCMP(sp->hdr.seq, >=, call->rx_data_recv); + ASSERTCMP(sp->hdr.seq, <=, call->rx_data_recv + 1); + ASSERTCMP(sp->hdr.seq, >, call->rx_data_eaten); + + call->rx_data_recv = sp->hdr.seq; + rxrpc_hard_ACK_data(call, sp); +} +EXPORT_SYMBOL(rxrpc_kernel_data_consumed); + /* - * destroy a packet that has an RxRPC control buffer - * - advance the hard-ACK state of the parent call (done here in case something - * in the kernel bypasses recvmsg() and steals the packet directly off of the - * socket receive queue) + * Destroy a packet that has an RxRPC control buffer */ void rxrpc_packet_destructor(struct sk_buff *skb) { @@ -112,9 +140,8 @@ void rxrpc_packet_destructor(struct sk_buff *skb) _enter("%p{%p}", skb, call); if (call) { - /* send the final ACK on a client call */ - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) - rxrpc_hard_ACK_data(call, sp); + if (atomic_dec_return(&call->skb_count) < 0) + BUG(); rxrpc_put_call(call); sp->call = NULL; } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e4a5f2607ffa..d09d0687594b 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -64,7 +64,6 @@ int __tcf_hash_release(struct tc_action *p, bool bind, bool strict) if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) { if (p->ops->cleanup) p->ops->cleanup(p, bind); - list_del(&p->list); tcf_hash_destroy(p->hinfo, p); ret = ACT_P_DELETED; } @@ -421,18 +420,19 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind) return res; } -int tcf_action_exec(struct sk_buff *skb, const struct list_head *actions, - struct tcf_result *res) +int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, + int nr_actions, struct tcf_result *res) { - const struct tc_action *a; - int ret = -1; + int ret = -1, i; if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); ret = TC_ACT_OK; goto exec_done; } - list_for_each_entry(a, actions, list) { + for (i = 0; i < nr_actions; i++) { + const struct tc_action *a = actions[i]; + repeat: ret = a->ops->act(skb, a, res); if (ret == TC_ACT_REPEAT) @@ -754,16 +754,6 @@ err_out: return ERR_PTR(err); } -static void cleanup_a(struct list_head *actions) -{ - struct tc_action *a, *tmp; - - list_for_each_entry_safe(a, tmp, actions, list) { - list_del(&a->list); - kfree(a); - } -} - static int tca_action_flush(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 portid) { @@ -905,7 +895,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, return ret; } err: - cleanup_a(&actions); + tcf_action_destroy(&actions, 0); return ret; } @@ -942,15 +932,9 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, ret = tcf_action_init(net, nla, NULL, NULL, ovr, 0, &actions); if (ret) - goto done; + return ret; - /* dump then free all the actions after update; inserted policy - * stays intact - */ - ret = tcf_add_notify(net, n, &actions, portid); - cleanup_a(&actions); -done: - return ret; + return tcf_add_notify(net, n, &actions, portid); } static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n) diff --git a/net/sched/act_police.c b/net/sched/act_police.c index b3c7e975fc9e..8a3be1d99775 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -63,49 +63,8 @@ static int tcf_act_police_walker(struct net *net, struct sk_buff *skb, const struct tc_action_ops *ops) { struct tc_action_net *tn = net_generic(net, police_net_id); - struct tcf_hashinfo *hinfo = tn->hinfo; - int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; - struct nlattr *nest; - - spin_lock_bh(&hinfo->lock); - - s_i = cb->args[0]; - - for (i = 0; i < (POL_TAB_MASK + 1); i++) { - struct hlist_head *head; - struct tc_action *p; - - head = &hinfo->htab[tcf_hash(i, POL_TAB_MASK)]; - - hlist_for_each_entry_rcu(p, head, tcfa_head) { - index++; - if (index < s_i) - continue; - nest = nla_nest_start(skb, index); - if (nest == NULL) - goto nla_put_failure; - if (type == RTM_DELACTION) - err = tcf_action_dump_1(skb, p, 0, 1); - else - err = tcf_action_dump_1(skb, p, 0, 0); - if (err < 0) { - index--; - nla_nest_cancel(skb, nest); - goto done; - } - nla_nest_end(skb, nest); - n_i++; - } - } -done: - spin_unlock_bh(&hinfo->lock); - if (n_i) - cb->args[0] += n_i; - return n_i; -nla_put_failure: - nla_nest_cancel(skb, nest); - goto done; + return tcf_generic_walker(tn, skb, cb, type, ops); } static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { @@ -125,6 +84,7 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, police_net_id); + bool exists = false; int size; if (nla == NULL) @@ -139,24 +99,24 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla, size = nla_len(tb[TCA_POLICE_TBF]); if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat)) return -EINVAL; + parm = nla_data(tb[TCA_POLICE_TBF]); + exists = tcf_hash_check(tn, parm->index, a, bind); + if (exists && bind) + return 0; - if (parm->index) { - if (tcf_hash_check(tn, parm->index, a, bind)) { - if (ovr) - goto override; - /* not replacing */ - return -EEXIST; - } - } else { + if (!exists) { ret = tcf_hash_create(tn, parm->index, NULL, a, &act_police_ops, bind, false); if (ret) return ret; ret = ACT_P_CREATED; + } else { + tcf_hash_release(*a, bind); + if (!ovr) + return -EEXIST; } -override: police = to_police(*a); if (parm->rate.rate) { err = -ENOMEM; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 843a716a4303..a7c5645373af 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -541,8 +541,12 @@ out: void tcf_exts_destroy(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT - tcf_action_destroy(&exts->actions, TCA_ACT_UNBIND); - INIT_LIST_HEAD(&exts->actions); + LIST_HEAD(actions); + + tcf_exts_to_list(exts, &actions); + tcf_action_destroy(&actions, TCA_ACT_UNBIND); + kfree(exts->actions); + exts->nr_actions = 0; #endif } EXPORT_SYMBOL(tcf_exts_destroy); @@ -554,7 +558,6 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, { struct tc_action *act; - INIT_LIST_HEAD(&exts->actions); if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tb[exts->police], rate_tlv, "police", ovr, @@ -563,14 +566,20 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, return PTR_ERR(act); act->type = exts->type = TCA_OLD_COMPAT; - list_add(&act->list, &exts->actions); + exts->actions[0] = act; + exts->nr_actions = 1; } else if (exts->action && tb[exts->action]) { - int err; + LIST_HEAD(actions); + int err, i = 0; + err = tcf_action_init(net, tb[exts->action], rate_tlv, NULL, ovr, - TCA_ACT_BIND, &exts->actions); + TCA_ACT_BIND, &actions); if (err) return err; + list_for_each_entry(act, &actions, list) + exts->actions[i++] = act; + exts->nr_actions = i; } } #else @@ -587,37 +596,49 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, struct tcf_exts *src) { #ifdef CONFIG_NET_CLS_ACT - LIST_HEAD(tmp); + struct tcf_exts old = *dst; + tcf_tree_lock(tp); - list_splice_init(&dst->actions, &tmp); - list_splice(&src->actions, &dst->actions); + dst->nr_actions = src->nr_actions; + dst->actions = src->actions; dst->type = src->type; tcf_tree_unlock(tp); - tcf_action_destroy(&tmp, TCA_ACT_UNBIND); + + tcf_exts_destroy(&old); #endif } EXPORT_SYMBOL(tcf_exts_change); -#define tcf_exts_first_act(ext) \ - list_first_entry_or_null(&(exts)->actions, \ - struct tc_action, list) +#ifdef CONFIG_NET_CLS_ACT +static struct tc_action *tcf_exts_first_act(struct tcf_exts *exts) +{ + if (exts->nr_actions == 0) + return NULL; + else + return exts->actions[0]; +} +#endif int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT struct nlattr *nest; - if (exts->action && !list_empty(&exts->actions)) { + if (exts->action && exts->nr_actions) { /* * again for backward compatible mode - we want * to work with both old and new modes of entering * tc data even if iproute2 was newer - jhs */ if (exts->type != TCA_OLD_COMPAT) { + LIST_HEAD(actions); + nest = nla_nest_start(skb, exts->action); if (nest == NULL) goto nla_put_failure; - if (tcf_action_dump(skb, &exts->actions, 0, 0) < 0) + + tcf_exts_to_list(exts, &actions); + if (tcf_action_dump(skb, &actions, 0, 0) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } else if (exts->police) { diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 4cb5aedfe3ee..ef8ba77a5bea 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -293,6 +293,7 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) return ERR_PTR(err); } + iter->start_fail = 0; return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos); } diff --git a/net/sctp/sctp_diag.c b/net/sctp/sctp_diag.c index f69edcf219e5..bb691538adc8 100644 --- a/net/sctp/sctp_diag.c +++ b/net/sctp/sctp_diag.c @@ -13,6 +13,7 @@ static void inet_diag_msg_sctpasoc_fill(struct inet_diag_msg *r, { union sctp_addr laddr, paddr; struct dst_entry *dst; + struct timer_list *t3_rtx = &asoc->peer.primary_path->T3_rtx_timer; laddr = list_entry(asoc->base.bind_addr.address_list.next, struct sctp_sockaddr_entry, list)->a; @@ -40,10 +41,15 @@ static void inet_diag_msg_sctpasoc_fill(struct inet_diag_msg *r, } r->idiag_state = asoc->state; - r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX; - r->idiag_retrans = asoc->rtx_data_chunks; - r->idiag_expires = jiffies_to_msecs( - asoc->timeouts[SCTP_EVENT_TIMEOUT_T3_RTX] - jiffies); + if (timer_pending(t3_rtx)) { + r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX; + r->idiag_retrans = asoc->rtx_data_chunks; + r->idiag_expires = jiffies_to_msecs(t3_rtx->expires - jiffies); + } else { + r->idiag_timer = 0; + r->idiag_retrans = 0; + r->idiag_expires = 0; + } } static int inet_diag_msg_sctpladdrs_fill(struct sk_buff *skb, @@ -350,7 +356,7 @@ static int sctp_ep_dump(struct sctp_endpoint *ep, void *p) if (cb->args[4] < cb->args[1]) goto next; - if ((r->idiag_states & ~TCPF_LISTEN) && !list_empty(&ep->asocs)) + if (!(r->idiag_states & TCPF_LISTEN) && !list_empty(&ep->asocs)) goto next; if (r->sdiag_family != AF_UNSPEC && @@ -465,7 +471,7 @@ skip: * 3 : to mark if we have dumped the ep info of the current asoc * 4 : to work as a temporary variable to traversal list */ - if (!(idiag_states & ~TCPF_LISTEN)) + if (!(idiag_states & ~(TCPF_LISTEN | TCPF_CLOSE))) goto done; sctp_for_each_transport(sctp_tsp_dump, net, cb->args[2], &commp); done: diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 1bc4f71aaba8..d85b803da11d 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -702,14 +702,14 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, */ sctp_ulpevent_init(event, 0, skb->len + sizeof(struct sk_buff)); - sctp_ulpevent_receive_data(event, asoc); - /* And hold the chunk as we need it for getting the IP headers * later in recvmsg */ sctp_chunk_hold(chunk); event->chunk = chunk; + sctp_ulpevent_receive_data(event, asoc); + event->stream = ntohs(chunk->subh.data_hdr->stream); event->ssn = ntohs(chunk->subh.data_hdr->ssn); event->ppid = chunk->subh.data_hdr->ppid; diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 23c8e7c39656..976c7812bbd5 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -340,12 +340,14 @@ gss_release_msg(struct gss_upcall_msg *gss_msg) } static struct gss_upcall_msg * -__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid) +__gss_find_upcall(struct rpc_pipe *pipe, kuid_t uid, const struct gss_auth *auth) { struct gss_upcall_msg *pos; list_for_each_entry(pos, &pipe->in_downcall, list) { if (!uid_eq(pos->uid, uid)) continue; + if (auth && pos->auth->service != auth->service) + continue; atomic_inc(&pos->count); dprintk("RPC: %s found msg %p\n", __func__, pos); return pos; @@ -365,7 +367,7 @@ gss_add_msg(struct gss_upcall_msg *gss_msg) struct gss_upcall_msg *old; spin_lock(&pipe->lock); - old = __gss_find_upcall(pipe, gss_msg->uid); + old = __gss_find_upcall(pipe, gss_msg->uid, gss_msg->auth); if (old == NULL) { atomic_inc(&gss_msg->count); list_add(&gss_msg->list, &pipe->in_downcall); @@ -714,7 +716,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) err = -ENOENT; /* Find a matching upcall */ spin_lock(&pipe->lock); - gss_msg = __gss_find_upcall(pipe, uid); + gss_msg = __gss_find_upcall(pipe, uid, NULL); if (gss_msg == NULL) { spin_unlock(&pipe->lock); goto err_put_ctx; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index cb49898a5a58..7f79fb7dc6a0 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2638,6 +2638,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, { struct rpc_xprt_switch *xps; struct rpc_xprt *xprt; + unsigned long reconnect_timeout; unsigned char resvport; int ret = 0; @@ -2649,6 +2650,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, return -EAGAIN; } resvport = xprt->resvport; + reconnect_timeout = xprt->max_reconnect_timeout; rcu_read_unlock(); xprt = xprt_create_transport(xprtargs); @@ -2657,6 +2659,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, goto out_put_switch; } xprt->resvport = resvport; + xprt->max_reconnect_timeout = reconnect_timeout; rpc_xprt_switch_set_roundrobin(xps); if (setup) { @@ -2673,6 +2676,27 @@ out_put_switch: } EXPORT_SYMBOL_GPL(rpc_clnt_add_xprt); +static int +rpc_xprt_cap_max_reconnect_timeout(struct rpc_clnt *clnt, + struct rpc_xprt *xprt, + void *data) +{ + unsigned long timeout = *((unsigned long *)data); + + if (timeout < xprt->max_reconnect_timeout) + xprt->max_reconnect_timeout = timeout; + return 0; +} + +void +rpc_cap_max_reconnect_timeout(struct rpc_clnt *clnt, unsigned long timeo) +{ + rpc_clnt_iterate_for_each_xprt(clnt, + rpc_xprt_cap_max_reconnect_timeout, + &timeo); +} +EXPORT_SYMBOL_GPL(rpc_cap_max_reconnect_timeout); + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) static void rpc_show_header(void) { diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 8313960cac52..ea244b29138b 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -680,6 +680,20 @@ out: spin_unlock_bh(&xprt->transport_lock); } +static bool +xprt_has_timer(const struct rpc_xprt *xprt) +{ + return xprt->idle_timeout != 0; +} + +static void +xprt_schedule_autodisconnect(struct rpc_xprt *xprt) + __must_hold(&xprt->transport_lock) +{ + if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) + mod_timer(&xprt->timer, xprt->last_used + xprt->idle_timeout); +} + static void xprt_init_autodisconnect(unsigned long data) { @@ -688,6 +702,8 @@ xprt_init_autodisconnect(unsigned long data) spin_lock(&xprt->transport_lock); if (!list_empty(&xprt->recv)) goto out_abort; + /* Reset xprt->last_used to avoid connect/autodisconnect cycling */ + xprt->last_used = jiffies; if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) goto out_abort; spin_unlock(&xprt->transport_lock); @@ -725,6 +741,7 @@ void xprt_unlock_connect(struct rpc_xprt *xprt, void *cookie) goto out; xprt->snd_task =NULL; xprt->ops->release_xprt(xprt, NULL); + xprt_schedule_autodisconnect(xprt); out: spin_unlock_bh(&xprt->transport_lock); wake_up_bit(&xprt->state, XPRT_LOCKED); @@ -888,11 +905,6 @@ static void xprt_timer(struct rpc_task *task) spin_unlock_bh(&xprt->transport_lock); } -static inline int xprt_has_timer(struct rpc_xprt *xprt) -{ - return xprt->idle_timeout != 0; -} - /** * xprt_prepare_transmit - reserve the transport before sending a request * @task: RPC task about to send a request @@ -1280,9 +1292,7 @@ void xprt_release(struct rpc_task *task) if (!list_empty(&req->rq_list)) list_del(&req->rq_list); xprt->last_used = jiffies; - if (list_empty(&xprt->recv) && xprt_has_timer(xprt)) - mod_timer(&xprt->timer, - xprt->last_used + xprt->idle_timeout); + xprt_schedule_autodisconnect(xprt); spin_unlock_bh(&xprt->transport_lock); if (req->rq_buffer) xprt->ops->buf_free(req->rq_buffer); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 111767ab124a..8ede3bc52481 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -177,7 +177,6 @@ static struct ctl_table sunrpc_table[] = { * increase over time if the server is down or not responding. */ #define XS_TCP_INIT_REEST_TO (3U * HZ) -#define XS_TCP_MAX_REEST_TO (5U * 60 * HZ) /* * TCP idle timeout; client drops the transport socket if it is idle @@ -2173,6 +2172,8 @@ static void xs_udp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) write_unlock_bh(&sk->sk_callback_lock); } xs_udp_do_set_buffer_size(xprt); + + xprt->stat.connect_start = jiffies; } static void xs_udp_setup_socket(struct work_struct *work) @@ -2236,6 +2237,7 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) unsigned int keepcnt = xprt->timeout->to_retries + 1; unsigned int opt_on = 1; unsigned int timeo; + unsigned int addr_pref = IPV6_PREFER_SRC_PUBLIC; /* TCP Keepalive options */ kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE, @@ -2247,6 +2249,16 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) kernel_setsockopt(sock, SOL_TCP, TCP_KEEPCNT, (char *)&keepcnt, sizeof(keepcnt)); + /* Avoid temporary address, they are bad for long-lived + * connections such as NFS mounts. + * RFC4941, section 3.6 suggests that: + * Individual applications, which have specific + * knowledge about the normal duration of connections, + * MAY override this as appropriate. + */ + kernel_setsockopt(sock, SOL_IPV6, IPV6_ADDR_PREFERENCES, + (char *)&addr_pref, sizeof(addr_pref)); + /* TCP user timeout (see RFC5482) */ timeo = jiffies_to_msecs(xprt->timeout->to_initval) * (xprt->timeout->to_retries + 1); @@ -2295,6 +2307,10 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* SYN_SENT! */ if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + break; + case -EADDRNOTAVAIL: + /* Source port number is unavailable. Try a new one! */ + transport->srcport = 0; } out: return ret; @@ -2369,6 +2385,25 @@ out: xprt_wake_pending_tasks(xprt, status); } +static unsigned long xs_reconnect_delay(const struct rpc_xprt *xprt) +{ + unsigned long start, now = jiffies; + + start = xprt->stat.connect_start + xprt->reestablish_timeout; + if (time_after(start, now)) + return start - now; + return 0; +} + +static void xs_reconnect_backoff(struct rpc_xprt *xprt) +{ + xprt->reestablish_timeout <<= 1; + if (xprt->reestablish_timeout > xprt->max_reconnect_timeout) + xprt->reestablish_timeout = xprt->max_reconnect_timeout; + if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; +} + /** * xs_connect - connect a socket to a remote endpoint * @xprt: pointer to transport structure @@ -2386,6 +2421,7 @@ out: static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) { struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); + unsigned long delay = 0; WARN_ON_ONCE(!xprt_lock_connect(xprt, task, transport)); @@ -2397,19 +2433,15 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) /* Start by resetting any existing state */ xs_reset_transport(transport); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, - xprt->reestablish_timeout); - xprt->reestablish_timeout <<= 1; - if (xprt->reestablish_timeout < XS_TCP_INIT_REEST_TO) - xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; - if (xprt->reestablish_timeout > XS_TCP_MAX_REEST_TO) - xprt->reestablish_timeout = XS_TCP_MAX_REEST_TO; - } else { + delay = xs_reconnect_delay(xprt); + xs_reconnect_backoff(xprt); + + } else dprintk("RPC: xs_connect scheduled xprt %p\n", xprt); - queue_delayed_work(xprtiod_workqueue, - &transport->connect_worker, 0); - } + + queue_delayed_work(xprtiod_workqueue, + &transport->connect_worker, + delay); } /** @@ -2961,6 +2993,8 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args) xprt->ops = &xs_tcp_ops; xprt->timeout = &xs_tcp_default_timeout; + xprt->max_reconnect_timeout = xprt->timeout->to_maxval; + INIT_WORK(&transport->recv_worker, xs_tcp_data_receive_workfn); INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_setup_socket); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index b62caa1c770c..ed97a5876ebe 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -728,12 +728,13 @@ int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id, u32 *prev_node) { struct tipc_monitor *mon = tipc_monitor(net, bearer_id); - struct tipc_peer *peer = mon->self; + struct tipc_peer *peer; if (!mon) return -EINVAL; read_lock_bh(&mon->lock); + peer = mon->self; do { if (*prev_node) { if (peer->addr == *prev_node) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c49b8df438cb..f9f5f3c3dab5 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2180,7 +2180,8 @@ restart: TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, onode, dport, oport, TIPC_CONN_SHUTDOWN); - tipc_node_xmit_skb(net, skb, dnode, tsk->portid); + if (skb) + tipc_node_xmit_skb(net, skb, dnode, tsk->portid); } tsk->connected = 0; sock->state = SS_DISCONNECTING; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 699dfabdbccd..936d7eee62d0 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -87,9 +87,6 @@ virtio_transport_send_pkt_work(struct work_struct *work) vq = vsock->vqs[VSOCK_VQ_TX]; - /* Avoid unnecessary interrupts while we're processing the ring */ - virtqueue_disable_cb(vq); - for (;;) { struct virtio_vsock_pkt *pkt; struct scatterlist hdr, buf, *sgs[2]; @@ -99,7 +96,6 @@ virtio_transport_send_pkt_work(struct work_struct *work) spin_lock_bh(&vsock->send_pkt_list_lock); if (list_empty(&vsock->send_pkt_list)) { spin_unlock_bh(&vsock->send_pkt_list_lock); - virtqueue_enable_cb(vq); break; } @@ -118,13 +114,13 @@ virtio_transport_send_pkt_work(struct work_struct *work) } ret = virtqueue_add_sgs(vq, sgs, out_sg, in_sg, pkt, GFP_KERNEL); + /* Usually this means that there is no more space available in + * the vq + */ if (ret < 0) { spin_lock_bh(&vsock->send_pkt_list_lock); list_add(&pkt->list, &vsock->send_pkt_list); spin_unlock_bh(&vsock->send_pkt_list_lock); - - if (!virtqueue_enable_cb(vq) && ret == -ENOSPC) - continue; /* retry now that we have more space */ break; } diff --git a/net/wireless/chan.c b/net/wireless/chan.c index b0e11b6dc994..0f506220a3bd 100644 --- a/net/wireless/chan.c +++ b/net/wireless/chan.c @@ -513,6 +513,7 @@ static bool cfg80211_chandef_dfs_available(struct wiphy *wiphy, r = cfg80211_get_chans_dfs_available(wiphy, chandef->center_freq2, width); + break; default: WARN_ON(chandef->center_freq2); break; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 46417f9cce68..f02653a08993 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5380,6 +5380,7 @@ static int nl80211_parse_mesh_config(struct genl_info *info, { struct nlattr *tb[NL80211_MESHCONF_ATTR_MAX + 1]; u32 mask = 0; + u16 ht_opmode; #define FILL_IN_MESH_PARAM_IF_SET(tb, cfg, param, min, max, mask, attr, fn) \ do { \ @@ -5471,9 +5472,36 @@ do { \ FILL_IN_MESH_PARAM_IF_SET(tb, cfg, rssi_threshold, -255, 0, mask, NL80211_MESHCONF_RSSI_THRESHOLD, nl80211_check_s32); - FILL_IN_MESH_PARAM_IF_SET(tb, cfg, ht_opmode, 0, 16, - mask, NL80211_MESHCONF_HT_OPMODE, - nl80211_check_u16); + /* + * Check HT operation mode based on + * IEEE 802.11 2012 8.4.2.59 HT Operation element. + */ + if (tb[NL80211_MESHCONF_HT_OPMODE]) { + ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]); + + if (ht_opmode & ~(IEEE80211_HT_OP_MODE_PROTECTION | + IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT | + IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) + return -EINVAL; + + if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) && + (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) + return -EINVAL; + + switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) { + case IEEE80211_HT_OP_MODE_PROTECTION_NONE: + case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ: + if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT) + return -EINVAL; + break; + case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER: + case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED: + if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) + return -EINVAL; + break; + } + cfg->ht_opmode = ht_opmode; + } FILL_IN_MESH_PARAM_IF_SET(tb, cfg, dot11MeshHWMPactivePathToRootTimeout, 1, 65535, mask, NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 217c8d507f2e..7927a090fa0d 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -72,8 +72,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag (void *) BPF_FUNC_l3_csum_replace; static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) = (void *) BPF_FUNC_l4_csum_replace; -static int (*bpf_skb_in_cgroup)(void *ctx, void *map, int index) = - (void *) BPF_FUNC_skb_in_cgroup; +static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = + (void *) BPF_FUNC_skb_under_cgroup; #if defined(__x86_64__) diff --git a/samples/bpf/test_cgrp2_tc_kern.c b/samples/bpf/test_cgrp2_tc_kern.c index 2732c37c8d5b..10ff73404e3a 100644 --- a/samples/bpf/test_cgrp2_tc_kern.c +++ b/samples/bpf/test_cgrp2_tc_kern.c @@ -57,7 +57,7 @@ int handle_egress(struct __sk_buff *skb) bpf_trace_printk(dont_care_msg, sizeof(dont_care_msg), eth->h_proto, ip6h->nexthdr); return TC_ACT_OK; - } else if (bpf_skb_in_cgroup(skb, &test_cgrp2_array_pin, 0) != 1) { + } else if (bpf_skb_under_cgroup(skb, &test_cgrp2_array_pin, 0) != 1) { bpf_trace_printk(pass_msg, sizeof(pass_msg)); return TC_ACT_OK; } else { diff --git a/samples/bpf/test_maps.c b/samples/bpf/test_maps.c index 47bf0858f9e4..cce2b59751eb 100644 --- a/samples/bpf/test_maps.c +++ b/samples/bpf/test_maps.c @@ -68,7 +68,16 @@ static void test_hashmap_sanity(int i, void *data) assert(bpf_update_elem(map_fd, &key, &value, BPF_NOEXIST) == -1 && errno == E2BIG); + /* update existing element, thought the map is full */ + key = 1; + assert(bpf_update_elem(map_fd, &key, &value, BPF_EXIST) == 0); + key = 2; + assert(bpf_update_elem(map_fd, &key, &value, BPF_ANY) == 0); + key = 1; + assert(bpf_update_elem(map_fd, &key, &value, BPF_ANY) == 0); + /* check that key = 0 doesn't exist */ + key = 0; assert(bpf_delete_elem(map_fd, &key) == -1 && errno == ENOENT); /* iterate over two elements */ @@ -413,10 +422,12 @@ static void do_work(int fn, void *data) for (i = fn; i < MAP_SIZE; i += TASKS) { key = value = i; - if (do_update) + if (do_update) { assert(bpf_update_elem(map_fd, &key, &value, BPF_NOEXIST) == 0); - else + assert(bpf_update_elem(map_fd, &key, &value, BPF_EXIST) == 0); + } else { assert(bpf_delete_elem(map_fd, &key) == 0); + } } } diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index 15b196fc2f49..179219845dfc 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -108,16 +108,20 @@ as-option = $(call try-run,\ as-instr = $(call try-run,\ printf "%b\n" "$(1)" | $(CC) $(KBUILD_AFLAGS) -c -x assembler -o "$$TMP" -,$(2),$(3)) +# Do not attempt to build with gcc plugins during cc-option tests. +# (And this uses delayed resolution so the flags will be up to date.) +CC_OPTION_CFLAGS = $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS)) + # cc-option # Usage: cflags-y += $(call cc-option,-march=winchip-c6,-march=i586) cc-option = $(call try-run,\ - $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2)) + $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",$(1),$(2)) # cc-option-yn # Usage: flag := $(call cc-option-yn,-march=winchip-c6) cc-option-yn = $(call try-run,\ - $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n) + $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) $(1) -c -x c /dev/null -o "$$TMP",y,n) # cc-option-align # Prefix align with either -falign or -malign @@ -127,7 +131,7 @@ cc-option-align = $(subst -functions=0,,\ # cc-disable-warning # Usage: cflags-y += $(call cc-disable-warning,unused-but-set-variable) cc-disable-warning = $(call try-run,\ - $(CC) $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1))) + $(CC) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -W$(strip $(1)) -c -x c /dev/null -o "$$TMP",-Wno-$(strip $(1))) # cc-name # Expands to either gcc or clang diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins index 5e22b60589c1..61f0e6db909b 100644 --- a/scripts/Makefile.gcc-plugins +++ b/scripts/Makefile.gcc-plugins @@ -19,25 +19,42 @@ ifdef CONFIG_GCC_PLUGINS endif endif - GCC_PLUGINS_CFLAGS := $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) + GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y)) - export PLUGINCC GCC_PLUGINS_CFLAGS GCC_PLUGIN SANCOV_PLUGIN + export PLUGINCC GCC_PLUGINS_CFLAGS GCC_PLUGIN GCC_PLUGIN_SUBDIR SANCOV_PLUGIN + ifneq ($(PLUGINCC),) + # SANCOV_PLUGIN can be only in CFLAGS_KCOV because avoid duplication. + GCC_PLUGINS_CFLAGS := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGINS_CFLAGS)) + endif + + KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS) + GCC_PLUGIN := $(gcc-plugin-y) + GCC_PLUGIN_SUBDIR := $(gcc-plugin-subdir-y) +endif + +# If plugins aren't supported, abort the build before hard-to-read compiler +# errors start getting spewed by the main build. +PHONY += gcc-plugins-check +gcc-plugins-check: FORCE +ifdef CONFIG_GCC_PLUGINS ifeq ($(PLUGINCC),) ifneq ($(GCC_PLUGINS_CFLAGS),) ifeq ($(call cc-ifversion, -ge, 0405, y), y) - PLUGINCC := $(shell $(CONFIG_SHELL) -x $(srctree)/scripts/gcc-plugin.sh "$(__PLUGINCC)" "$(HOSTCXX)" "$(CC)") - $(warning warning: your gcc installation does not support plugins, perhaps the necessary headers are missing?) + $(Q)$(srctree)/scripts/gcc-plugin.sh --show-error "$(__PLUGINCC)" "$(HOSTCXX)" "$(CC)" || true + @echo "Cannot use CONFIG_GCC_PLUGINS: your gcc installation does not support plugins, perhaps the necessary headers are missing?" >&2 && exit 1 else - $(warning warning: your gcc version does not support plugins, you should upgrade it to gcc 4.5 at least) + @echo "Cannot use CONFIG_GCC_PLUGINS: your gcc version does not support plugins, you should upgrade it to at least gcc 4.5" >&2 && exit 1 endif endif - else - # SANCOV_PLUGIN can be only in CFLAGS_KCOV because avoid duplication. - GCC_PLUGINS_CFLAGS := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGINS_CFLAGS)) endif +endif + @: - KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS) - GCC_PLUGIN := $(gcc-plugin-y) - +# Actually do the build, if requested. +PHONY += gcc-plugins +gcc-plugins: scripts_basic gcc-plugins-check +ifdef CONFIG_GCC_PLUGINS + $(Q)$(MAKE) $(build)=scripts/gcc-plugins endif + @: diff --git a/scripts/gcc-plugin.sh b/scripts/gcc-plugin.sh index fb9207565471..b65224bfb847 100755 --- a/scripts/gcc-plugin.sh +++ b/scripts/gcc-plugin.sh @@ -1,5 +1,12 @@ #!/bin/sh srctree=$(dirname "$0") + +SHOW_ERROR= +if [ "$1" = "--show-error" ] ; then + SHOW_ERROR=1 + shift || true +fi + gccplugins_dir=$($3 -print-file-name=plugin) plugincc=$($1 -E -x c++ - -o /dev/null -I"${srctree}"/gcc-plugins -I"${gccplugins_dir}"/include 2>&1 <<EOF #include "gcc-common.h" @@ -13,6 +20,9 @@ EOF if [ $? -ne 0 ] then + if [ -n "$SHOW_ERROR" ] ; then + echo "${plugincc}" >&2 + fi exit 1 fi @@ -48,4 +58,8 @@ then echo "$2" exit 0 fi + +if [ -n "$SHOW_ERROR" ] ; then + echo "${plugincc}" >&2 +fi exit 1 diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile index 88c8ec47232b..8b29dc17c73c 100644 --- a/scripts/gcc-plugins/Makefile +++ b/scripts/gcc-plugins/Makefile @@ -12,16 +12,18 @@ else export HOST_EXTRACXXFLAGS endif -export GCCPLUGINS_DIR HOSTLIBS - ifneq ($(CFLAGS_KCOV), $(SANCOV_PLUGIN)) GCC_PLUGIN := $(filter-out $(SANCOV_PLUGIN), $(GCC_PLUGIN)) endif -$(HOSTLIBS)-y := $(GCC_PLUGIN) +export HOSTLIBS + +$(HOSTLIBS)-y := $(foreach p,$(GCC_PLUGIN),$(if $(findstring /,$(p)),,$(p))) always := $($(HOSTLIBS)-y) -cyc_complexity_plugin-objs := cyc_complexity_plugin.o -sancov_plugin-objs := sancov_plugin.o +$(foreach p,$($(HOSTLIBS)-y:%.so=%),$(eval $(p)-objs := $(p).o)) + +subdir-y := $(GCC_PLUGIN_SUBDIR) +subdir- += $(GCC_PLUGIN_SUBDIR) clean-files += *.so diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index 122fcdaf42c8..aed4511f0304 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -432,7 +432,7 @@ foreach my $file (@ARGV) { die "$P: file '${file}' not found\n"; } } - if ($from_filename || vcs_file_exists($file)) { + if ($from_filename || ($file ne "&STDIN" && vcs_file_exists($file))) { $file =~ s/^\Q${cur_path}\E//; #strip any absolute path $file =~ s/^\Q${lk_path}\E//; #or the path to the lk tree push(@files, $file); @@ -2136,9 +2136,11 @@ sub vcs_file_exists { my $cmd = $VCS_cmds{"file_exists_cmd"}; $cmd =~ s/(\$\w+)/$1/eeg; # interpolate $cmd - + $cmd .= " 2>&1"; $exists = &{$VCS_cmds{"execute_cmd"}}($cmd); + return 0 if ($? != 0); + return $exists; } diff --git a/security/Kconfig b/security/Kconfig index 176758cdfa57..da10d9b573a4 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -118,6 +118,35 @@ config LSM_MMAP_MIN_ADDR this low address space will need the permission specific to the systems running LSM. +config HAVE_HARDENED_USERCOPY_ALLOCATOR + bool + help + The heap allocator implements __check_heap_object() for + validating memory ranges against heap object sizes in + support of CONFIG_HARDENED_USERCOPY. + +config HAVE_ARCH_HARDENED_USERCOPY + bool + help + The architecture supports CONFIG_HARDENED_USERCOPY by + calling check_object_size() just before performing the + userspace copies in the low level implementation of + copy_to_user() and copy_from_user(). + +config HARDENED_USERCOPY + bool "Harden memory copies between kernel and userspace" + depends on HAVE_ARCH_HARDENED_USERCOPY + depends on HAVE_HARDENED_USERCOPY_ALLOCATOR + select BUG + help + This option checks for obviously wrong memory regions when + copying memory to/from the kernel (via copy_to_user() and + copy_from_user() functions) by rejecting memory ranges that + are larger than the specified heap object, span multiple + separately allocates pages, are not on the process stack, + or are part of the kernel text. This kills entire classes + of heap overflow exploits and similar kernel memory exposures. + source security/selinux/Kconfig source security/smack/Kconfig source security/tomoyo/Kconfig diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 89dacf9b4e6c..160c7f713722 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -906,20 +906,23 @@ static int azx_resume(struct device *dev) struct snd_card *card = dev_get_drvdata(dev); struct azx *chip; struct hda_intel *hda; + struct hdac_bus *bus; if (!card) return 0; chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); + bus = azx_bus(chip); if (chip->disabled || hda->init_failed || !chip->running) return 0; - if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL - && hda->need_i915_power) { - snd_hdac_display_power(azx_bus(chip), true); - snd_hdac_i915_set_bclk(azx_bus(chip)); + if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) { + snd_hdac_display_power(bus, true); + if (hda->need_i915_power) + snd_hdac_i915_set_bclk(bus); } + if (chip->msi) if (pci_enable_msi(pci) < 0) chip->msi = 0; @@ -929,6 +932,11 @@ static int azx_resume(struct device *dev) hda_intel_init_chip(chip, true); + /* power down again for link-controlled chips */ + if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) && + !hda->need_i915_power) + snd_hdac_display_power(bus, false); + snd_power_change_state(card, SNDRV_CTL_POWER_D0); trace_azx_resume(chip); @@ -1008,6 +1016,7 @@ static int azx_runtime_resume(struct device *dev) chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); + bus = azx_bus(chip); if (chip->disabled || hda->init_failed) return 0; @@ -1015,15 +1024,9 @@ static int azx_runtime_resume(struct device *dev) return 0; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) { - bus = azx_bus(chip); - if (hda->need_i915_power) { - snd_hdac_display_power(bus, true); + snd_hdac_display_power(bus, true); + if (hda->need_i915_power) snd_hdac_i915_set_bclk(bus); - } else { - /* toggle codec wakeup bit for STATESTS read */ - snd_hdac_set_codec_wakeup(bus, true); - snd_hdac_set_codec_wakeup(bus, false); - } } /* Read STATESTS before controller reset */ @@ -1043,6 +1046,11 @@ static int azx_runtime_resume(struct device *dev) azx_writew(chip, WAKEEN, azx_readw(chip, WAKEEN) & ~STATESTS_INT_MASK); + /* power down again for link-controlled chips */ + if ((chip->driver_caps & AZX_DCAPS_I915_POWERWELL) && + !hda->need_i915_power) + snd_hdac_display_power(bus, false); + trace_azx_runtime_resume(chip); return 0; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 574b1b48996f..7100f05e651a 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4828,7 +4828,7 @@ enum { ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, ALC292_FIXUP_TPT440_DOCK, ALC292_FIXUP_TPT440, - ALC283_FIXUP_BXBT2807_MIC, + ALC283_FIXUP_HEADSET_MIC, ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED, ALC282_FIXUP_ASPIRE_V5_PINS, ALC280_FIXUP_HP_GPIO4, @@ -5321,7 +5321,7 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC292_FIXUP_TPT440_DOCK, }, - [ALC283_FIXUP_BXBT2807_MIC] = { + [ALC283_FIXUP_HEADSET_MIC] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl[]) { { 0x19, 0x04a110f0 }, @@ -5651,7 +5651,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10cf, 0x1757, "Lifebook E752", ALC269_FIXUP_LIFEBOOK_HP_PIN), SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), - SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_BXBT2807_MIC), + SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c index 54c09acd3fed..16e459aedffe 100644 --- a/sound/soc/atmel/atmel_ssc_dai.c +++ b/sound/soc/atmel/atmel_ssc_dai.c @@ -299,8 +299,9 @@ static int atmel_ssc_startup(struct snd_pcm_substream *substream, clk_enable(ssc_p->ssc->clk); ssc_p->mck_rate = clk_get_rate(ssc_p->ssc->clk); - /* Reset the SSC to keep it at a clean status */ - ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST)); + /* Reset the SSC unless initialized to keep it in a clean state */ + if (!ssc_p->initialized) + ssc_writel(ssc_p->ssc->regs, CR, SSC_BIT(CR_SWRST)); if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) { dir = 0; diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c index e5527bc570ae..bcf1834c5648 100644 --- a/sound/soc/codecs/da7213.c +++ b/sound/soc/codecs/da7213.c @@ -1247,8 +1247,8 @@ static int da7213_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) return -EINVAL; } - /* By default only 32 BCLK per WCLK is supported */ - dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_32; + /* By default only 64 BCLK per WCLK is supported */ + dai_clk_mode |= DA7213_DAI_BCLKS_PER_WCLK_64; snd_soc_write(codec, DA7213_DAI_CLK_MODE, dai_clk_mode); snd_soc_update_bits(codec, DA7213_DAI_CTRL, DA7213_DAI_FORMAT_MASK, diff --git a/sound/soc/codecs/max98371.c b/sound/soc/codecs/max98371.c index cf0a39bb631a..02352ed8961c 100644 --- a/sound/soc/codecs/max98371.c +++ b/sound/soc/codecs/max98371.c @@ -412,6 +412,7 @@ static int max98371_i2c_remove(struct i2c_client *client) static const struct i2c_device_id max98371_i2c_id[] = { { "max98371", 0 }, + { } }; MODULE_DEVICE_TABLE(i2c, max98371_i2c_id); diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c index 5c9707ac4bbf..2e59a85e360b 100644 --- a/sound/soc/codecs/nau8825.c +++ b/sound/soc/codecs/nau8825.c @@ -212,31 +212,6 @@ static const unsigned short logtable[256] = { 0xfa2f, 0xfaea, 0xfba5, 0xfc60, 0xfd1a, 0xfdd4, 0xfe8e, 0xff47 }; -static struct snd_soc_dai *nau8825_get_codec_dai(struct nau8825 *nau8825) -{ - struct snd_soc_codec *codec = snd_soc_dapm_to_codec(nau8825->dapm); - struct snd_soc_component *component = &codec->component; - struct snd_soc_dai *codec_dai, *_dai; - - list_for_each_entry_safe(codec_dai, _dai, &component->dai_list, list) { - if (!strncmp(codec_dai->name, NUVOTON_CODEC_DAI, - strlen(NUVOTON_CODEC_DAI))) - return codec_dai; - } - return NULL; -} - -static bool nau8825_dai_is_active(struct nau8825 *nau8825) -{ - struct snd_soc_dai *codec_dai = nau8825_get_codec_dai(nau8825); - - if (codec_dai) { - if (codec_dai->playback_active || codec_dai->capture_active) - return true; - } - return false; -} - /** * nau8825_sema_acquire - acquire the semaphore of nau88l25 * @nau8825: component to register the codec private data with @@ -250,19 +225,26 @@ static bool nau8825_dai_is_active(struct nau8825 *nau8825) * Acquires the semaphore without jiffies. If no more tasks are allowed * to acquire the semaphore, calling this function will put the task to * sleep until the semaphore is released. - * It returns if the semaphore was acquired. + * If the semaphore is not released within the specified number of jiffies, + * this function returns -ETIME. + * If the sleep is interrupted by a signal, this function will return -EINTR. + * It returns 0 if the semaphore was acquired successfully. */ -static void nau8825_sema_acquire(struct nau8825 *nau8825, long timeout) +static int nau8825_sema_acquire(struct nau8825 *nau8825, long timeout) { int ret; - if (timeout) + if (timeout) { ret = down_timeout(&nau8825->xtalk_sem, timeout); - else + if (ret < 0) + dev_warn(nau8825->dev, "Acquire semaphone timeout\n"); + } else { ret = down_interruptible(&nau8825->xtalk_sem); + if (ret < 0) + dev_warn(nau8825->dev, "Acquire semaphone fail\n"); + } - if (ret < 0) - dev_warn(nau8825->dev, "Acquire semaphone fail\n"); + return ret; } /** @@ -1205,6 +1187,8 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream, struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); unsigned int val_len = 0; + nau8825_sema_acquire(nau8825, 2 * HZ); + switch (params_width(params)) { case 16: val_len |= NAU8825_I2S_DL_16; @@ -1225,6 +1209,9 @@ static int nau8825_hw_params(struct snd_pcm_substream *substream, regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL1, NAU8825_I2S_DL_MASK, val_len); + /* Release the semaphone. */ + nau8825_sema_release(nau8825); + return 0; } @@ -1234,6 +1221,8 @@ static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); unsigned int ctrl1_val = 0, ctrl2_val = 0; + nau8825_sema_acquire(nau8825, 2 * HZ); + switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) { case SND_SOC_DAIFMT_CBM_CFM: ctrl2_val |= NAU8825_I2S_MS_MASTER; @@ -1282,6 +1271,9 @@ static int nau8825_set_dai_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt) regmap_update_bits(nau8825->regmap, NAU8825_REG_I2S_PCM_CTRL2, NAU8825_I2S_MS_MASK, ctrl2_val); + /* Release the semaphone. */ + nau8825_sema_release(nau8825); + return 0; } @@ -1611,8 +1603,11 @@ static irqreturn_t nau8825_interrupt(int irq, void *data) * cess and restore changes if process * is ongoing when ejection. */ + int ret; nau8825->xtalk_protect = true; - nau8825_sema_acquire(nau8825, 0); + ret = nau8825_sema_acquire(nau8825, 0); + if (ret < 0) + nau8825->xtalk_protect = false; } /* Startup cross talk detection process */ nau8825->xtalk_state = NAU8825_XTALK_PREPARE; @@ -2238,23 +2233,14 @@ static int __maybe_unused nau8825_suspend(struct snd_soc_codec *codec) static int __maybe_unused nau8825_resume(struct snd_soc_codec *codec) { struct nau8825 *nau8825 = snd_soc_codec_get_drvdata(codec); + int ret; regcache_cache_only(nau8825->regmap, false); regcache_sync(nau8825->regmap); - if (nau8825_is_jack_inserted(nau8825->regmap)) { - /* If the jack is inserted, we need to check whether the play- - * back is active before suspend. If active, the driver has to - * raise the protection for cross talk function to avoid the - * playback recovers before cross talk process finish. Other- - * wise, the playback will be interfered by cross talk func- - * tion. It is better to apply hardware related parameters - * before starting playback or record. - */ - if (nau8825_dai_is_active(nau8825)) { - nau8825->xtalk_protect = true; - nau8825_sema_acquire(nau8825, 0); - } - } + nau8825->xtalk_protect = true; + ret = nau8825_sema_acquire(nau8825, 0); + if (ret < 0) + nau8825->xtalk_protect = false; enable_irq(nau8825->irq); return 0; diff --git a/sound/soc/codecs/wm2000.c b/sound/soc/codecs/wm2000.c index a67ea10f41a1..f2664396be6f 100644 --- a/sound/soc/codecs/wm2000.c +++ b/sound/soc/codecs/wm2000.c @@ -581,7 +581,7 @@ static int wm2000_anc_transition(struct wm2000_priv *wm2000, if (anc_transitions[i].dest == ANC_OFF) clk_disable_unprepare(wm2000->mclk); - return ret; + return 0; } static int wm2000_anc_set_mode(struct wm2000_priv *wm2000) diff --git a/sound/soc/generic/Makefile b/sound/soc/generic/Makefile index 45602ca8536e..2d53c8d70705 100644 --- a/sound/soc/generic/Makefile +++ b/sound/soc/generic/Makefile @@ -1,5 +1,5 @@ -obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) := simple-card-utils.o - +snd-soc-simple-card-utils-objs := simple-card-utils.o snd-soc-simple-card-objs := simple-card.o -obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o +obj-$(CONFIG_SND_SIMPLE_CARD_UTILS) += snd-soc-simple-card-utils.o +obj-$(CONFIG_SND_SIMPLE_CARD) += snd-soc-simple-card.o diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c index d89a9a1b2471..9599de69a880 100644 --- a/sound/soc/generic/simple-card-utils.c +++ b/sound/soc/generic/simple-card-utils.c @@ -7,6 +7,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/module.h> #include <linux/of.h> #include <sound/simple_card_utils.h> @@ -95,3 +96,8 @@ int asoc_simple_card_parse_card_name(struct snd_soc_card *card, return 0; } EXPORT_SYMBOL_GPL(asoc_simple_card_parse_card_name); + +/* Module information */ +MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>"); +MODULE_DESCRIPTION("ALSA SoC Simple Card Utils"); +MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/intel/skylake/skl-sst-utils.c b/sound/soc/intel/skylake/skl-sst-utils.c index 25fcb796bd86..ddcb52a51854 100644 --- a/sound/soc/intel/skylake/skl-sst-utils.c +++ b/sound/soc/intel/skylake/skl-sst-utils.c @@ -123,6 +123,11 @@ int snd_skl_get_module_info(struct skl_sst *ctx, u8 *uuid, uuid_mod = (uuid_le *)uuid; + if (list_empty(&ctx->uuid_list)) { + dev_err(ctx->dev, "Module list is empty\n"); + return -EINVAL; + } + list_for_each_entry(module, &ctx->uuid_list, list) { if (uuid_le_cmp(*uuid_mod, module->uuid) == 0) { dfw_config->module_id = module->id; diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c index cd59536a761d..e3e764167765 100644 --- a/sound/soc/intel/skylake/skl.c +++ b/sound/soc/intel/skylake/skl.c @@ -672,8 +672,10 @@ static int skl_probe(struct pci_dev *pci, skl->nhlt = skl_nhlt_init(bus->dev); - if (skl->nhlt == NULL) + if (skl->nhlt == NULL) { + err = -ENODEV; goto out_free; + } skl_nhlt_update_topology_bin(skl); diff --git a/sound/soc/omap/omap-abe-twl6040.c b/sound/soc/omap/omap-abe-twl6040.c index 0843a68f277c..f61b3b58083b 100644 --- a/sound/soc/omap/omap-abe-twl6040.c +++ b/sound/soc/omap/omap-abe-twl6040.c @@ -38,10 +38,10 @@ struct abe_twl6040 { int jack_detection; /* board can detect jack events */ int mclk_freq; /* MCLK frequency speed for twl6040 */ - - struct platform_device *dmic_codec_dev; }; +struct platform_device *dmic_codec_dev; + static int omap_abe_hw_params(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params) { @@ -258,8 +258,6 @@ static int omap_abe_probe(struct platform_device *pdev) if (priv == NULL) return -ENOMEM; - priv->dmic_codec_dev = ERR_PTR(-EINVAL); - if (snd_soc_of_parse_card_name(card, "ti,model")) { dev_err(&pdev->dev, "Card name is not provided\n"); return -ENODEV; @@ -284,13 +282,6 @@ static int omap_abe_probe(struct platform_device *pdev) num_links = 2; abe_twl6040_dai_links[1].cpu_of_node = dai_node; abe_twl6040_dai_links[1].platform_of_node = dai_node; - - priv->dmic_codec_dev = platform_device_register_simple( - "dmic-codec", -1, NULL, 0); - if (IS_ERR(priv->dmic_codec_dev)) { - dev_err(&pdev->dev, "Can't instantiate dmic-codec\n"); - return PTR_ERR(priv->dmic_codec_dev); - } } else { num_links = 1; } @@ -299,16 +290,14 @@ static int omap_abe_probe(struct platform_device *pdev) of_property_read_u32(node, "ti,mclk-freq", &priv->mclk_freq); if (!priv->mclk_freq) { dev_err(&pdev->dev, "MCLK frequency not provided\n"); - ret = -EINVAL; - goto err_unregister; + return -EINVAL; } card->fully_routed = 1; if (!priv->mclk_freq) { dev_err(&pdev->dev, "MCLK frequency missing\n"); - ret = -ENODEV; - goto err_unregister; + return -ENODEV; } card->dai_link = abe_twl6040_dai_links; @@ -317,17 +306,9 @@ static int omap_abe_probe(struct platform_device *pdev) snd_soc_card_set_drvdata(card, priv); ret = snd_soc_register_card(card); - if (ret) { + if (ret) dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n", ret); - goto err_unregister; - } - - return 0; - -err_unregister: - if (!IS_ERR(priv->dmic_codec_dev)) - platform_device_unregister(priv->dmic_codec_dev); return ret; } @@ -335,13 +316,9 @@ err_unregister: static int omap_abe_remove(struct platform_device *pdev) { struct snd_soc_card *card = platform_get_drvdata(pdev); - struct abe_twl6040 *priv = snd_soc_card_get_drvdata(card); snd_soc_unregister_card(card); - if (!IS_ERR(priv->dmic_codec_dev)) - platform_device_unregister(priv->dmic_codec_dev); - return 0; } @@ -361,7 +338,33 @@ static struct platform_driver omap_abe_driver = { .remove = omap_abe_remove, }; -module_platform_driver(omap_abe_driver); +static int __init omap_abe_init(void) +{ + int ret; + + dmic_codec_dev = platform_device_register_simple("dmic-codec", -1, NULL, + 0); + if (IS_ERR(dmic_codec_dev)) { + pr_err("%s: dmic-codec device registration failed\n", __func__); + return PTR_ERR(dmic_codec_dev); + } + + ret = platform_driver_register(&omap_abe_driver); + if (ret) { + pr_err("%s: platform driver registration failed\n", __func__); + platform_device_unregister(dmic_codec_dev); + } + + return ret; +} +module_init(omap_abe_init); + +static void __exit omap_abe_exit(void) +{ + platform_driver_unregister(&omap_abe_driver); + platform_device_unregister(dmic_codec_dev); +} +module_exit(omap_abe_exit); MODULE_AUTHOR("Misael Lopez Cruz <misael.lopez@ti.com>"); MODULE_DESCRIPTION("ALSA SoC for OMAP boards with ABE and twl6040 codec"); diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c index e7cdc51fd806..64609c77a79d 100644 --- a/sound/soc/omap/omap-mcpdm.c +++ b/sound/soc/omap/omap-mcpdm.c @@ -31,7 +31,6 @@ #include <linux/err.h> #include <linux/io.h> #include <linux/irq.h> -#include <linux/clk.h> #include <linux/slab.h> #include <linux/pm_runtime.h> #include <linux/of_device.h> @@ -55,7 +54,6 @@ struct omap_mcpdm { unsigned long phys_base; void __iomem *io_base; int irq; - struct clk *pdmclk; struct mutex mutex; @@ -390,15 +388,14 @@ static int omap_mcpdm_probe(struct snd_soc_dai *dai) struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); int ret; - clk_prepare_enable(mcpdm->pdmclk); pm_runtime_enable(mcpdm->dev); /* Disable lines while request is ongoing */ pm_runtime_get_sync(mcpdm->dev); omap_mcpdm_write(mcpdm, MCPDM_REG_CTRL, 0x00); - ret = devm_request_irq(mcpdm->dev, mcpdm->irq, omap_mcpdm_irq_handler, - 0, "McPDM", (void *)mcpdm); + ret = request_irq(mcpdm->irq, omap_mcpdm_irq_handler, 0, "McPDM", + (void *)mcpdm); pm_runtime_put_sync(mcpdm->dev); @@ -423,9 +420,9 @@ static int omap_mcpdm_remove(struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); + free_irq(mcpdm->irq, (void *)mcpdm); pm_runtime_disable(mcpdm->dev); - clk_disable_unprepare(mcpdm->pdmclk); return 0; } @@ -445,8 +442,6 @@ static int omap_mcpdm_suspend(struct snd_soc_dai *dai) mcpdm->pm_active_count++; } - clk_disable_unprepare(mcpdm->pdmclk); - return 0; } @@ -454,8 +449,6 @@ static int omap_mcpdm_resume(struct snd_soc_dai *dai) { struct omap_mcpdm *mcpdm = snd_soc_dai_get_drvdata(dai); - clk_prepare_enable(mcpdm->pdmclk); - if (mcpdm->pm_active_count) { while (mcpdm->pm_active_count--) pm_runtime_get_sync(mcpdm->dev); @@ -549,15 +542,6 @@ static int asoc_mcpdm_probe(struct platform_device *pdev) mcpdm->dev = &pdev->dev; - mcpdm->pdmclk = devm_clk_get(&pdev->dev, "pdmclk"); - if (IS_ERR(mcpdm->pdmclk)) { - if (PTR_ERR(mcpdm->pdmclk) == -EPROBE_DEFER) - return -EPROBE_DEFER; - dev_warn(&pdev->dev, "Error getting pdmclk (%ld)!\n", - PTR_ERR(mcpdm->pdmclk)); - mcpdm->pdmclk = NULL; - } - ret = devm_snd_soc_register_component(&pdev->dev, &omap_mcpdm_component, &omap_mcpdm_dai, 1); diff --git a/sound/soc/samsung/s3c24xx_uda134x.c b/sound/soc/samsung/s3c24xx_uda134x.c index 50849e137fc0..92e88bca386e 100644 --- a/sound/soc/samsung/s3c24xx_uda134x.c +++ b/sound/soc/samsung/s3c24xx_uda134x.c @@ -58,10 +58,12 @@ static struct platform_device *s3c24xx_uda134x_snd_device; static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream) { - int ret = 0; + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct snd_soc_dai *cpu_dai = rtd->cpu_dai; #ifdef ENFORCE_RATES struct snd_pcm_runtime *runtime = substream->runtime; #endif + int ret = 0; mutex_lock(&clk_lock); pr_debug("%s %d\n", __func__, clk_users); @@ -71,8 +73,7 @@ static int s3c24xx_uda134x_startup(struct snd_pcm_substream *substream) printk(KERN_ERR "%s cannot get xtal\n", __func__); ret = PTR_ERR(xtal); } else { - pclk = clk_get(&s3c24xx_uda134x_snd_device->dev, - "pclk"); + pclk = clk_get(cpu_dai->dev, "iis"); if (IS_ERR(pclk)) { printk(KERN_ERR "%s cannot get pclk\n", __func__); diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c index e39f916d0f2f..969a5169de25 100644 --- a/sound/soc/sh/rcar/src.c +++ b/sound/soc/sh/rcar/src.c @@ -226,8 +226,12 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io, ifscr = 0; fsrate = 0; if (fin != fout) { + u64 n; + ifscr = 1; - fsrate = 0x0400000 / fout * fin; + n = (u64)0x0400000 * fin; + do_div(n, fout); + fsrate = n; } /* diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c index d2df46c14c68..bf7b52fce597 100644 --- a/sound/soc/soc-compress.c +++ b/sound/soc/soc-compress.c @@ -121,7 +121,7 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) dpcm_be_disconnect(fe, stream); fe->dpcm[stream].runtime = NULL; - goto fe_err; + goto path_err; } dpcm_clear_pending_state(fe, stream); @@ -136,6 +136,8 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream) return 0; +path_err: + dpcm_path_put(&list); fe_err: if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown) fe->dai_link->compr_ops->shutdown(cstream); diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index 16369cad4803..4afa8dba5e98 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -1056,7 +1056,7 @@ static int soc_bind_dai_link(struct snd_soc_card *card, if (!rtd->platform) { dev_err(card->dev, "ASoC: platform %s not registered\n", dai_link->platform_name); - return -EPROBE_DEFER; + goto _err_defer; } soc_add_pcm_runtime(card, rtd); @@ -2083,14 +2083,13 @@ static int soc_cleanup_card_resources(struct snd_soc_card *card) /* remove auxiliary devices */ soc_remove_aux_devices(card); + snd_soc_dapm_free(&card->dapm); soc_cleanup_card_debugfs(card); /* remove the card */ if (card->remove) card->remove(card); - snd_soc_dapm_free(&card->dapm); - snd_card_free(card->snd_card); return 0; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 8698c26773b3..d908ff8f9755 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -3493,6 +3493,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, const struct snd_soc_pcm_stream *config = w->params + w->params_select; struct snd_pcm_substream substream; struct snd_pcm_hw_params *params = NULL; + struct snd_pcm_runtime *runtime = NULL; u64 fmt; int ret; @@ -3541,6 +3542,14 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, memset(&substream, 0, sizeof(substream)); + /* Allocate a dummy snd_pcm_runtime for startup() and other ops() */ + runtime = kzalloc(sizeof(*runtime), GFP_KERNEL); + if (!runtime) { + ret = -ENOMEM; + goto out; + } + substream.runtime = runtime; + switch (event) { case SND_SOC_DAPM_PRE_PMU: substream.stream = SNDRV_PCM_STREAM_CAPTURE; @@ -3606,6 +3615,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w, } out: + kfree(runtime); kfree(params); return ret; } diff --git a/sound/usb/line6/pcm.c b/sound/usb/line6/pcm.c index 204cc074adb9..41aa3355e920 100644 --- a/sound/usb/line6/pcm.c +++ b/sound/usb/line6/pcm.c @@ -55,7 +55,6 @@ static int snd_line6_impulse_volume_put(struct snd_kcontrol *kcontrol, err = line6_pcm_acquire(line6pcm, LINE6_STREAM_IMPULSE); if (err < 0) { line6pcm->impulse_volume = 0; - line6_pcm_release(line6pcm, LINE6_STREAM_IMPULSE); return err; } } else { @@ -211,7 +210,9 @@ static void line6_stream_stop(struct snd_line6_pcm *line6pcm, int direction, spin_lock_irqsave(&pstr->lock, flags); clear_bit(type, &pstr->running); if (!pstr->running) { + spin_unlock_irqrestore(&pstr->lock, flags); line6_unlink_audio_urbs(line6pcm, pstr); + spin_lock_irqsave(&pstr->lock, flags); if (direction == SNDRV_PCM_STREAM_CAPTURE) { line6pcm->prev_fbuf = NULL; line6pcm->prev_fsize = 0; diff --git a/sound/usb/line6/pod.c b/sound/usb/line6/pod.c index daf81d169a42..45dd34874f43 100644 --- a/sound/usb/line6/pod.c +++ b/sound/usb/line6/pod.c @@ -244,8 +244,8 @@ static int pod_set_system_param_int(struct usb_line6_pod *pod, int value, static ssize_t serial_number_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%u\n", pod->serial_number); } @@ -256,8 +256,8 @@ static ssize_t serial_number_show(struct device *dev, static ssize_t firmware_version_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%d.%02d\n", pod->firmware_version / 100, pod->firmware_version % 100); @@ -269,8 +269,8 @@ static ssize_t firmware_version_show(struct device *dev, static ssize_t device_id_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct usb_interface *interface = to_usb_interface(dev); - struct usb_line6_pod *pod = usb_get_intfdata(interface); + struct snd_card *card = dev_to_snd_card(dev); + struct usb_line6_pod *pod = card->private_data; return sprintf(buf, "%d\n", pod->device_id); } diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 6adde457b602..6cf1f3597455 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1128,6 +1128,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) { /* devices which do not support reading the sample rate. */ switch (chip->usb_id) { + case USB_ID(0x041E, 0x4080): /* Creative Live Cam VF0610 */ case USB_ID(0x045E, 0x075D): /* MS Lifecam Cinema */ case USB_ID(0x045E, 0x076D): /* MS Lifecam HD-5000 */ case USB_ID(0x045E, 0x076E): /* MS Lifecam HD-5001 */ @@ -1138,6 +1139,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x047F, 0xAA05): /* Plantronics DA45 */ case USB_ID(0x04D8, 0xFEEA): /* Benchmark DAC1 Pre */ case USB_ID(0x0556, 0x0014): /* Phoenix Audio TMX320VC */ + case USB_ID(0x05A3, 0x9420): /* ELP HD USB Camera */ case USB_ID(0x074D, 0x3553): /* Outlaw RR2150 (Micronas UAC3553B) */ case USB_ID(0x1de7, 0x0013): /* Phoenix Audio MT202exe */ case USB_ID(0x1de7, 0x0014): /* Phoenix Audio TMX320 */ diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index f209ea151dca..3051f86a9b5f 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -87,9 +87,11 @@ struct kvm_regs { /* Supported VGICv3 address types */ #define KVM_VGIC_V3_ADDR_TYPE_DIST 2 #define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 +#define KVM_VGIC_ITS_ADDR_TYPE 4 #define KVM_VGIC_V3_DIST_SIZE SZ_64K #define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) +#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K) #define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ #define KVM_ARM_VCPU_EL1_32BIT 1 /* CPU running a 32bit VM */ diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 3b8e99ef9d58..a2ffec4139ad 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -93,6 +93,47 @@ struct kvm_s390_vm_cpu_machine { __u64 fac_list[256]; }; +#define KVM_S390_VM_CPU_PROCESSOR_FEAT 2 +#define KVM_S390_VM_CPU_MACHINE_FEAT 3 + +#define KVM_S390_VM_CPU_FEAT_NR_BITS 1024 +#define KVM_S390_VM_CPU_FEAT_ESOP 0 +#define KVM_S390_VM_CPU_FEAT_SIEF2 1 +#define KVM_S390_VM_CPU_FEAT_64BSCAO 2 +#define KVM_S390_VM_CPU_FEAT_SIIF 3 +#define KVM_S390_VM_CPU_FEAT_GPERE 4 +#define KVM_S390_VM_CPU_FEAT_GSLS 5 +#define KVM_S390_VM_CPU_FEAT_IB 6 +#define KVM_S390_VM_CPU_FEAT_CEI 7 +#define KVM_S390_VM_CPU_FEAT_IBS 8 +#define KVM_S390_VM_CPU_FEAT_SKEY 9 +#define KVM_S390_VM_CPU_FEAT_CMMA 10 +#define KVM_S390_VM_CPU_FEAT_PFMFI 11 +#define KVM_S390_VM_CPU_FEAT_SIGPIF 12 +struct kvm_s390_vm_cpu_feat { + __u64 feat[16]; +}; + +#define KVM_S390_VM_CPU_PROCESSOR_SUBFUNC 4 +#define KVM_S390_VM_CPU_MACHINE_SUBFUNC 5 +/* for "test bit" instructions MSB 0 bit ordering, for "query" raw blocks */ +struct kvm_s390_vm_cpu_subfunc { + __u8 plo[32]; /* always */ + __u8 ptff[16]; /* with TOD-clock steering */ + __u8 kmac[16]; /* with MSA */ + __u8 kmc[16]; /* with MSA */ + __u8 km[16]; /* with MSA */ + __u8 kimd[16]; /* with MSA */ + __u8 klmd[16]; /* with MSA */ + __u8 pckmo[16]; /* with MSA3 */ + __u8 kmctr[16]; /* with MSA4 */ + __u8 kmf[16]; /* with MSA4 */ + __u8 kmo[16]; /* with MSA4 */ + __u8 pcc[16]; /* with MSA4 */ + __u8 ppno[16]; /* with MSA5 */ + __u8 reserved[1824]; +}; + /* kvm attributes for crypto */ #define KVM_S390_VM_CRYPTO_ENABLE_AES_KW 0 #define KVM_S390_VM_CRYPTO_ENABLE_DEA_KW 1 diff --git a/tools/arch/s390/include/uapi/asm/sie.h b/tools/arch/s390/include/uapi/asm/sie.h index 8fb5d4a6dd25..3ac634368939 100644 --- a/tools/arch/s390/include/uapi/asm/sie.h +++ b/tools/arch/s390/include/uapi/asm/sie.h @@ -140,6 +140,7 @@ exit_code_ipa0(0xB2, 0x4c, "TAR"), \ exit_code_ipa0(0xB2, 0x50, "CSP"), \ exit_code_ipa0(0xB2, 0x54, "MVPG"), \ + exit_code_ipa0(0xB2, 0x56, "STHYI"), \ exit_code_ipa0(0xB2, 0x58, "BSG"), \ exit_code_ipa0(0xB2, 0x5a, "BSA"), \ exit_code_ipa0(0xB2, 0x5f, "CHSC"), \ diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 4a413485f9eb..92a8308b96f6 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -225,7 +225,6 @@ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ #define X86_FEATURE_ADX ( 9*32+19) /* The ADCX and ADOX instructions */ #define X86_FEATURE_SMAP ( 9*32+20) /* Supervisor Mode Access Prevention */ -#define X86_FEATURE_PCOMMIT ( 9*32+22) /* PCOMMIT instruction */ #define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* CLFLUSHOPT instruction */ #define X86_FEATURE_CLWB ( 9*32+24) /* CLWB instruction */ #define X86_FEATURE_AVX512PF ( 9*32+26) /* AVX-512 Prefetch */ @@ -301,10 +300,6 @@ #define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */ #define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */ #define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* SYSRET doesn't fix up SS attrs */ -#define X86_BUG_NULL_SEG X86_BUG(9) /* Nulling a selector preserves the base */ -#define X86_BUG_SWAPGS_FENCE X86_BUG(10) /* SWAPGS without input dep on GS */ - - #ifdef CONFIG_X86_32 /* * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional @@ -312,5 +307,7 @@ */ #define X86_BUG_ESPFIX X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */ #endif - +#define X86_BUG_NULL_SEG X86_BUG(10) /* Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h index 911e9358ceb1..85599ad4d024 100644 --- a/tools/arch/x86/include/asm/disabled-features.h +++ b/tools/arch/x86/include/asm/disabled-features.h @@ -56,5 +56,7 @@ #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 #define DISABLED_MASK16 (DISABLE_PKU|DISABLE_OSPKE) +#define DISABLED_MASK17 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/tools/arch/x86/include/asm/required-features.h b/tools/arch/x86/include/asm/required-features.h index 4916144e3c42..fac9a5c0abe9 100644 --- a/tools/arch/x86/include/asm/required-features.h +++ b/tools/arch/x86/include/asm/required-features.h @@ -99,5 +99,7 @@ #define REQUIRED_MASK14 0 #define REQUIRED_MASK15 0 #define REQUIRED_MASK16 0 +#define REQUIRED_MASK17 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 18) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h index 5b15d94a33f8..37fee272618f 100644 --- a/tools/arch/x86/include/uapi/asm/vmx.h +++ b/tools/arch/x86/include/uapi/asm/vmx.h @@ -78,7 +78,6 @@ #define EXIT_REASON_PML_FULL 62 #define EXIT_REASON_XSAVES 63 #define EXIT_REASON_XRSTORS 64 -#define EXIT_REASON_PCOMMIT 65 #define VMX_EXIT_REASONS \ { EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \ @@ -127,8 +126,7 @@ { EXIT_REASON_INVVPID, "INVVPID" }, \ { EXIT_REASON_INVPCID, "INVPCID" }, \ { EXIT_REASON_XSAVES, "XSAVES" }, \ - { EXIT_REASON_XRSTORS, "XRSTORS" }, \ - { EXIT_REASON_PCOMMIT, "PCOMMIT" } + { EXIT_REASON_XRSTORS, "XRSTORS" } #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 448ed96b3b4f..1c14c2595158 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -1,5 +1,5 @@ /* - * gpio-hammer - example swiss army knife to shake GPIO lines on a system + * gpio-event-mon - monitor GPIO line events from userspace * * Copyright (C) 2016 Linus Walleij * diff --git a/tools/include/linux/string.h b/tools/include/linux/string.h index b96879477311..f436d2420a18 100644 --- a/tools/include/linux/string.h +++ b/tools/include/linux/string.h @@ -8,7 +8,11 @@ void *memdup(const void *src, size_t len); int strtobool(const char *s, bool *res); -#ifdef __GLIBC__ +/* + * glibc based builds needs the extern while uClibc doesn't. + * However uClibc headers also define __GLIBC__ hence the hack below + */ +#if defined(__GLIBC__) && !defined(__UCLIBC__) extern size_t strlcpy(char *dest, const char *src, size_t size); #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 406459b935a2..da218fec6056 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -84,6 +84,7 @@ enum bpf_map_type { BPF_MAP_TYPE_PERCPU_HASH, BPF_MAP_TYPE_PERCPU_ARRAY, BPF_MAP_TYPE_STACK_TRACE, + BPF_MAP_TYPE_CGROUP_ARRAY, }; enum bpf_prog_type { @@ -93,6 +94,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SCHED_CLS, BPF_PROG_TYPE_SCHED_ACT, BPF_PROG_TYPE_TRACEPOINT, + BPF_PROG_TYPE_XDP, }; #define BPF_PSEUDO_MAP_FD 1 @@ -313,6 +315,66 @@ enum bpf_func_id { */ BPF_FUNC_skb_get_tunnel_opt, BPF_FUNC_skb_set_tunnel_opt, + + /** + * bpf_skb_change_proto(skb, proto, flags) + * Change protocol of the skb. Currently supported is + * v4 -> v6, v6 -> v4 transitions. The helper will also + * resize the skb. eBPF program is expected to fill the + * new headers via skb_store_bytes and lX_csum_replace. + * @skb: pointer to skb + * @proto: new skb->protocol type + * @flags: reserved + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_proto, + + /** + * bpf_skb_change_type(skb, type) + * Change packet type of skb. + * @skb: pointer to skb + * @type: new skb->pkt_type type + * Return: 0 on success or negative error + */ + BPF_FUNC_skb_change_type, + + /** + * bpf_skb_in_cgroup(skb, map, index) - Check cgroup2 membership of skb + * @skb: pointer to skb + * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type + * @index: index of the cgroup in the bpf_map + * Return: + * == 0 skb failed the cgroup2 descendant test + * == 1 skb succeeded the cgroup2 descendant test + * < 0 error + */ + BPF_FUNC_skb_in_cgroup, + + /** + * bpf_get_hash_recalc(skb) + * Retrieve and possibly recalculate skb->hash. + * @skb: pointer to skb + * Return: hash + */ + BPF_FUNC_get_hash_recalc, + + /** + * u64 bpf_get_current_task(void) + * Returns current task_struct + * Return: current + */ + BPF_FUNC_get_current_task, + + /** + * bpf_probe_write_user(void *dst, void *src, int len) + * safely attempt to write to a location + * @dst: destination address in userspace + * @src: source address on stack + * @len: number of bytes to copy + * Return: 0 on success or negative error + */ + BPF_FUNC_probe_write_user, + __BPF_FUNC_MAX_ID, }; @@ -347,9 +409,11 @@ enum bpf_func_id { #define BPF_F_ZERO_CSUM_TX (1ULL << 1) #define BPF_F_DONT_FRAGMENT (1ULL << 2) -/* BPF_FUNC_perf_event_output flags. */ +/* BPF_FUNC_perf_event_output and BPF_FUNC_perf_event_read flags. */ #define BPF_F_INDEX_MASK 0xffffffffULL #define BPF_F_CURRENT_CPU BPF_F_INDEX_MASK +/* BPF_FUNC_perf_event_output for sk_buff input context. */ +#define BPF_F_CTXLEN_MASK (0xfffffULL << 32) /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure @@ -386,4 +450,24 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* User return codes for XDP prog type. + * A valid XDP program must return one of these defined values. All other + * return codes are reserved for future use. Unknown return codes will result + * in packet drop. + */ +enum xdp_action { + XDP_ABORTED = 0, + XDP_DROP, + XDP_PASS, + XDP_TX, +}; + +/* user accessible metadata for XDP packet hook + * new fields must be added to the end of this structure + */ +struct xdp_md { + __u32 data; + __u32 data_end; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt index 736da44596e4..b303bcdd8ed1 100644 --- a/tools/perf/Documentation/perf-probe.txt +++ b/tools/perf/Documentation/perf-probe.txt @@ -176,10 +176,18 @@ Each probe argument follows below syntax. 'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.) '$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters. -'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. Currently, basic types (u8/u16/u32/u64/s8/s16/s32/s64), signedness casting (u/s), "string" and bitfield are supported. (see TYPES for detail) On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid. +TYPES +----- +Basic types (u8/u16/u32/u64/s8/s16/s32/s64) are integer types. Prefix 's' and 'u' means those types are signed and unsigned respectively. Traced arguments are shown in decimal (signed) or hex (unsigned). You can also use 's' or 'u' to specify only signedness and leave its size auto-detected by perf probe. +String type is a special type, which fetches a "null-terminated" string from kernel space. This means it will fail and store NULL if the string container has been paged out. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type. +Bitfield is another special type, which takes 3 parameters, bit-width, bit-offset, and container-size (usually 32). The syntax is; + + b<bit-width>@<bit-offset>/<container-size> + LINE SYNTAX ----------- Line range is described by following syntax. diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 1f6c70594f0f..053bbbd84ece 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -116,8 +116,8 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, brstack, brstacksym, flags. - Field list can be prepended with the type, trace, sw or hw, + srcline, period, iregs, brstack, brstacksym, flags, bpf-output, + callindent. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index c6d0f91731a1..35745a733100 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -54,10 +54,6 @@ int arch__compare_symbol_names(const char *namea, const char *nameb) #endif #if defined(_CALL_ELF) && _CALL_ELF == 2 -bool arch__prefers_symtab(void) -{ - return true; -} #ifdef HAVE_LIBELF_SUPPORT void arch__sym_update(struct symbol *s, GElf_Sym *sym) @@ -100,4 +96,29 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev, tev->point.offset += lep_offset; } } + +#ifdef HAVE_LIBELF_SUPPORT +void arch__post_process_probe_trace_events(struct perf_probe_event *pev, + int ntevs) +{ + struct probe_trace_event *tev; + struct map *map; + struct symbol *sym = NULL; + struct rb_node *tmp; + int i = 0; + + map = get_target_map(pev->target, pev->uprobes); + if (!map || map__load(map, NULL) < 0) + return; + + for (i = 0; i < ntevs; i++) { + tev = &pev->tevs[i]; + map__for_each_symbol(map, sym, tmp) { + if (map->unmap_ip(map, sym->start) == tev->point.address) + arch__fix_tev_from_maps(pev, tev, map, sym); + } + } +} +#endif /* HAVE_LIBELF_SUPPORT */ + #endif diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index fb51457ba338..a2412e9d883b 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -501,7 +501,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, struct intel_pt_recording *ptr = container_of(itr, struct intel_pt_recording, itr); struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu; - bool have_timing_info; + bool have_timing_info, need_immediate = false; struct perf_evsel *evsel, *intel_pt_evsel = NULL; const struct cpu_map *cpus = evlist->cpus; bool privileged = geteuid() == 0 || perf_event_paranoid() < 0; @@ -655,6 +655,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, ptr->have_sched_switch = 3; } else { opts->record_switch_events = true; + need_immediate = true; if (cpu_wide) ptr->have_sched_switch = 3; else @@ -700,6 +701,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr, tracking_evsel->attr.freq = 0; tracking_evsel->attr.sample_period = 1; + if (need_immediate) + tracking_evsel->immediate = true; + /* In per-cpu case, always need the time of mmap events etc */ if (!cpu_map__empty(cpus)) { perf_evsel__set_sample_bit(tracking_evsel, TIME); diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c index d608a2c9e48c..d1ce29be560e 100644 --- a/tools/perf/builtin-mem.c +++ b/tools/perf/builtin-mem.c @@ -88,6 +88,9 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem) if (mem->operation & MEM_OPERATION_LOAD) perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true; + if (mem->operation & MEM_OPERATION_STORE) + perf_mem_events[PERF_MEM_EVENTS__STORE].record = true; + if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record) rec_argv[i++] = "-W"; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 971ff91b16cb..c859e59dfe3e 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -371,14 +371,16 @@ static int perf_session__check_output_opt(struct perf_session *session) if (!no_callchain) { bool use_callchain = false; + bool not_pipe = false; evlist__for_each_entry(session->evlist, evsel) { + not_pipe = true; if (evsel->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { use_callchain = true; break; } } - if (!use_callchain) + if (not_pipe && !use_callchain) symbol_conf.use_callchain = false; } @@ -1690,8 +1692,13 @@ static int list_available_scripts(const struct option *opt __maybe_unused, snprintf(scripts_path, MAXPATHLEN, "%s/scripts", get_argv_exec_path()); scripts_dir = opendir(scripts_path); - if (!scripts_dir) - return -1; + if (!scripts_dir) { + fprintf(stdout, + "open(%s) failed.\n" + "Check \"PERF_EXEC_PATH\" env to set scripts dir.\n", + scripts_path); + exit(-1); + } for_each_lang(scripts_path, scripts_dir, lang_dirent) { snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path, @@ -2116,7 +2123,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __maybe_unused) "Valid types: hw,sw,trace,raw. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," "addr,symoff,period,iregs,brstack,brstacksym,flags," - "callindent", parse_output_fields), + "bpf-output,callindent", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide, "system-wide collection from all CPUs"), OPT_STRING('S', "symbols", &symbol_conf.sym_list_str, "symbol[,symbol...]", diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 0c16d20d7e32..3c7452b39f57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -331,7 +331,7 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static void read_counters(bool close_counters) +static void read_counters(void) { struct perf_evsel *counter; @@ -341,11 +341,6 @@ static void read_counters(bool close_counters) if (perf_stat_process_counter(&stat_config, counter)) pr_warning("failed to process counter %s\n", counter->name); - - if (close_counters) { - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), - thread_map__nr(evsel_list->threads)); - } } } @@ -353,7 +348,7 @@ static void process_interval(void) { struct timespec ts, rs; - read_counters(false); + read_counters(); clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); @@ -380,6 +375,17 @@ static void enable_counters(void) perf_evlist__enable(evsel_list); } +static void disable_counters(void) +{ + /* + * If we don't have tracee (attaching to task or cpu), counters may + * still be running. To get accurate group ratios, we must stop groups + * from counting before reading their constituent counters. + */ + if (!target__none(&target)) + perf_evlist__disable(evsel_list); +} + static volatile int workload_exec_errno; /* @@ -657,11 +663,20 @@ try_again: } } + disable_counters(); + t1 = rdclock(); update_stats(&walltime_nsecs_stats, t1 - t0); - read_counters(true); + /* + * Closing a group leader splits the group, and as we only disable + * group leaders, results in remaining events becoming enabled. To + * avoid arbitrary skew, we must read all counters before closing any + * group leaders. + */ + read_counters(); + perf_evlist__close(evsel_list); return WEXITSTATUS(status); } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index d9b80ef881cd..21fd573106ed 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -507,17 +507,17 @@ static int __perf_evsel__hw_cache_name(u64 config, char *bf, size_t size) u8 op, result, type = (config >> 0) & 0xff; const char *err = "unknown-ext-hardware-cache-type"; - if (type > PERF_COUNT_HW_CACHE_MAX) + if (type >= PERF_COUNT_HW_CACHE_MAX) goto out_err; op = (config >> 8) & 0xff; err = "unknown-ext-hardware-cache-op"; - if (op > PERF_COUNT_HW_CACHE_OP_MAX) + if (op >= PERF_COUNT_HW_CACHE_OP_MAX) goto out_err; result = (config >> 16) & 0xff; err = "unknown-ext-hardware-cache-result"; - if (result > PERF_COUNT_HW_CACHE_RESULT_MAX) + if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX) goto out_err; err = "invalid-cache"; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c index 9c8f15da86ce..8ff6c6a61291 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c @@ -123,8 +123,6 @@ struct intel_pt_decoder { bool have_calc_cyc_to_tsc; int exec_mode; unsigned int insn_bytes; - uint64_t sign_bit; - uint64_t sign_bits; uint64_t period; enum intel_pt_period_type period_type; uint64_t tot_insn_cnt; @@ -191,9 +189,6 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params) decoder->data = params->data; decoder->return_compression = params->return_compression; - decoder->sign_bit = (uint64_t)1 << 47; - decoder->sign_bits = ~(((uint64_t)1 << 48) - 1); - decoder->period = params->period; decoder->period_type = params->period_type; @@ -362,21 +357,30 @@ int intel_pt__strerror(int code, char *buf, size_t buflen) return 0; } -static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder, - const struct intel_pt_pkt *packet, +static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet, uint64_t last_ip) { uint64_t ip; switch (packet->count) { - case 2: + case 1: ip = (last_ip & (uint64_t)0xffffffffffff0000ULL) | packet->payload; break; - case 4: + case 2: ip = (last_ip & (uint64_t)0xffffffff00000000ULL) | packet->payload; break; + case 3: + ip = packet->payload; + /* Sign-extend 6-byte ip */ + if (ip & (uint64_t)0x800000000000ULL) + ip |= (uint64_t)0xffff000000000000ULL; + break; + case 4: + ip = (last_ip & (uint64_t)0xffff000000000000ULL) | + packet->payload; + break; case 6: ip = packet->payload; break; @@ -384,16 +388,12 @@ static uint64_t intel_pt_calc_ip(struct intel_pt_decoder *decoder, return 0; } - if (ip & decoder->sign_bit) - return ip | decoder->sign_bits; - return ip; } static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder) { - decoder->last_ip = intel_pt_calc_ip(decoder, &decoder->packet, - decoder->last_ip); + decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip); } static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder) @@ -1657,6 +1657,12 @@ next: } } +static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder) +{ + return decoder->last_ip || decoder->packet.count == 0 || + decoder->packet.count == 3 || decoder->packet.count == 6; +} + /* Walk PSB+ packets to get in sync. */ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) { @@ -1677,8 +1683,7 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: decoder->pge = true; - if (decoder->last_ip || decoder->packet.count == 6 || - decoder->packet.count == 0) { + if (intel_pt_have_ip(decoder)) { uint64_t current_ip = decoder->ip; intel_pt_set_ip(decoder); @@ -1767,8 +1772,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_TIP_PGE: case INTEL_PT_TIP: decoder->pge = decoder->packet.type != INTEL_PT_TIP_PGD; - if (decoder->last_ip || decoder->packet.count == 6 || - decoder->packet.count == 0) + if (intel_pt_have_ip(decoder)) intel_pt_set_ip(decoder); if (decoder->ip) return 0; @@ -1776,9 +1780,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder) case INTEL_PT_FUP: if (decoder->overflow) { - if (decoder->last_ip || - decoder->packet.count == 6 || - decoder->packet.count == 0) + if (intel_pt_have_ip(decoder)) intel_pt_set_ip(decoder); if (decoder->ip) return 0; diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index b1257c816310..4f7b32020487 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -292,36 +292,46 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte, const unsigned char *buf, size_t len, struct intel_pt_pkt *packet) { - switch (byte >> 5) { + int ip_len; + + packet->count = byte >> 5; + + switch (packet->count) { case 0: - packet->count = 0; + ip_len = 0; break; case 1: if (len < 3) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 2; + ip_len = 2; packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1)); break; case 2: if (len < 5) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 4; + ip_len = 4; packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1)); break; case 3: - case 6: + case 4: if (len < 7) return INTEL_PT_NEED_MORE_BYTES; - packet->count = 6; + ip_len = 6; memcpy_le64(&packet->payload, buf + 1, 6); break; + case 6: + if (len < 9) + return INTEL_PT_NEED_MORE_BYTES; + ip_len = 8; + packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1)); + break; default: return INTEL_PT_BAD_PACKET; } packet->type = type; - return packet->count + 1; + return ip_len + 1; } static int intel_pt_get_mode(const unsigned char *buf, size_t len, diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 9f3305f6b6d5..95f0884aae02 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -1,3 +1,4 @@ +#include <sys/sysmacros.h> #include <sys/types.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index 953dc1ab2ed7..28733962cd80 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -170,15 +170,17 @@ static struct map *kernel_get_module_map(const char *module) module = "kernel"; for (pos = maps__first(maps); pos; pos = map__next(pos)) { + /* short_name is "[module]" */ if (strncmp(pos->dso->short_name + 1, module, - pos->dso->short_name_len - 2) == 0) { + pos->dso->short_name_len - 2) == 0 && + module[pos->dso->short_name_len - 2] == '\0') { return pos; } } return NULL; } -static struct map *get_target_map(const char *target, bool user) +struct map *get_target_map(const char *target, bool user) { /* Init maps of given executable or kernel */ if (user) @@ -385,7 +387,7 @@ static int find_alternative_probe_point(struct debuginfo *dinfo, if (uprobes) address = sym->start; else - address = map->unmap_ip(map, sym->start); + address = map->unmap_ip(map, sym->start) - map->reloc; break; } if (!address) { @@ -664,22 +666,14 @@ static int add_module_to_probe_trace_events(struct probe_trace_event *tevs, return ret; } -/* Post processing the probe events */ -static int post_process_probe_trace_events(struct probe_trace_event *tevs, - int ntevs, const char *module, - bool uprobe) +static int +post_process_kernel_probe_trace_events(struct probe_trace_event *tevs, + int ntevs) { struct ref_reloc_sym *reloc_sym; char *tmp; int i, skipped = 0; - if (uprobe) - return add_exec_to_probe_trace_events(tevs, ntevs, module); - - /* Note that currently ref_reloc_sym based probe is not for drivers */ - if (module) - return add_module_to_probe_trace_events(tevs, ntevs, module); - reloc_sym = kernel_get_ref_reloc_sym(); if (!reloc_sym) { pr_warning("Relocated base symbol is not found!\n"); @@ -711,6 +705,34 @@ static int post_process_probe_trace_events(struct probe_trace_event *tevs, return skipped; } +void __weak +arch__post_process_probe_trace_events(struct perf_probe_event *pev __maybe_unused, + int ntevs __maybe_unused) +{ +} + +/* Post processing the probe events */ +static int post_process_probe_trace_events(struct perf_probe_event *pev, + struct probe_trace_event *tevs, + int ntevs, const char *module, + bool uprobe) +{ + int ret; + + if (uprobe) + ret = add_exec_to_probe_trace_events(tevs, ntevs, module); + else if (module) + /* Currently ref_reloc_sym based probe is not for drivers */ + ret = add_module_to_probe_trace_events(tevs, ntevs, module); + else + ret = post_process_kernel_probe_trace_events(tevs, ntevs); + + if (ret >= 0) + arch__post_process_probe_trace_events(pev, ntevs); + + return ret; +} + /* Try to find perf_probe_event with debuginfo */ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, struct probe_trace_event **tevs) @@ -749,7 +771,7 @@ static int try_to_find_probe_trace_events(struct perf_probe_event *pev, if (ntevs > 0) { /* Succeeded to find trace events */ pr_debug("Found %d probe_trace_events.\n", ntevs); - ret = post_process_probe_trace_events(*tevs, ntevs, + ret = post_process_probe_trace_events(pev, *tevs, ntevs, pev->target, pev->uprobes); if (ret < 0 || ret == ntevs) { clear_probe_trace_events(*tevs, ntevs); @@ -2936,8 +2958,6 @@ errout: return err; } -bool __weak arch__prefers_symtab(void) { return false; } - /* Concatinate two arrays */ static void *memcat(void *a, size_t sz_a, void *b, size_t sz_b) { @@ -3158,12 +3178,6 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, if (ret > 0 || pev->sdt) /* SDT can be found only in the cache */ return ret == 0 ? -ENOENT : ret; /* Found in probe cache */ - if (arch__prefers_symtab() && !perf_probe_event_need_dwarf(pev)) { - ret = find_probe_trace_events_from_map(pev, tevs); - if (ret > 0) - return ret; /* Found in symbol table */ - } - /* Convert perf_probe_event with debuginfo */ ret = try_to_find_probe_trace_events(pev, tevs); if (ret != 0) diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h index e18ea9fe6385..f4f45db77c1c 100644 --- a/tools/perf/util/probe-event.h +++ b/tools/perf/util/probe-event.h @@ -158,7 +158,6 @@ int show_line_range(struct line_range *lr, const char *module, bool user); int show_available_vars(struct perf_probe_event *pevs, int npevs, struct strfilter *filter); int show_available_funcs(const char *module, struct strfilter *filter, bool user); -bool arch__prefers_symtab(void); void arch__fix_tev_from_maps(struct perf_probe_event *pev, struct probe_trace_event *tev, struct map *map, struct symbol *sym); @@ -173,4 +172,9 @@ int e_snprintf(char *str, size_t size, const char *format, ...) int copy_to_probe_trace_arg(struct probe_trace_arg *tvar, struct perf_probe_arg *pvar); +struct map *get_target_map(const char *target, bool user); + +void arch__post_process_probe_trace_events(struct perf_probe_event *pev, + int ntevs); + #endif /*_PROBE_EVENT_H */ diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c index 9aed9c332da6..9c3b9ed5b3c3 100644 --- a/tools/perf/util/probe-file.c +++ b/tools/perf/util/probe-file.c @@ -133,7 +133,7 @@ int probe_file__open_both(int *kfd, int *ufd, int flag) /* Get raw string list of current kprobe_events or uprobe_events */ struct strlist *probe_file__get_rawlist(int fd) { - int ret, idx; + int ret, idx, fddup; FILE *fp; char buf[MAX_CMDLEN]; char *p; @@ -143,8 +143,17 @@ struct strlist *probe_file__get_rawlist(int fd) return NULL; sl = strlist__new(NULL, NULL); + if (sl == NULL) + return NULL; + + fddup = dup(fd); + if (fddup < 0) + goto out_free_sl; + + fp = fdopen(fddup, "r"); + if (!fp) + goto out_close_fddup; - fp = fdopen(dup(fd), "r"); while (!feof(fp)) { p = fgets(buf, MAX_CMDLEN, fp); if (!p) @@ -156,13 +165,21 @@ struct strlist *probe_file__get_rawlist(int fd) ret = strlist__add(sl, buf); if (ret < 0) { pr_debug("strlist__add failed (%d)\n", ret); - strlist__delete(sl); - return NULL; + goto out_close_fp; } } fclose(fp); return sl; + +out_close_fp: + fclose(fp); + goto out_free_sl; +out_close_fddup: + close(fddup); +out_free_sl: + strlist__delete(sl); + return NULL; } static struct strlist *__probe_file__get_namelist(int fd, bool include_group) @@ -447,12 +464,17 @@ static int probe_cache__load(struct probe_cache *pcache) { struct probe_cache_entry *entry = NULL; char buf[MAX_CMDLEN], *p; - int ret = 0; + int ret = 0, fddup; FILE *fp; - fp = fdopen(dup(pcache->fd), "r"); - if (!fp) + fddup = dup(pcache->fd); + if (fddup < 0) + return -errno; + fp = fdopen(fddup, "r"); + if (!fp) { + close(fddup); return -EINVAL; + } while (!feof(fp)) { if (!fgets(buf, MAX_CMDLEN, fp)) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index f2d9ff064e2d..5c290c682afe 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -297,10 +297,13 @@ static int convert_variable_type(Dwarf_Die *vr_die, char sbuf[STRERR_BUFSIZE]; int bsize, boffs, total; int ret; + char sign; /* TODO: check all types */ - if (cast && strcmp(cast, "string") != 0) { + if (cast && strcmp(cast, "string") != 0 && + strcmp(cast, "s") != 0 && strcmp(cast, "u") != 0) { /* Non string type is OK */ + /* and respect signedness cast */ tvar->type = strdup(cast); return (tvar->type == NULL) ? -ENOMEM : 0; } @@ -361,6 +364,13 @@ static int convert_variable_type(Dwarf_Die *vr_die, return (tvar->type == NULL) ? -ENOMEM : 0; } + if (cast && (strcmp(cast, "u") == 0)) + sign = 'u'; + else if (cast && (strcmp(cast, "s") == 0)) + sign = 's'; + else + sign = die_is_signed_type(&type) ? 's' : 'u'; + ret = dwarf_bytesize(&type); if (ret <= 0) /* No size ... try to use default type */ @@ -373,8 +383,7 @@ static int convert_variable_type(Dwarf_Die *vr_die, dwarf_diename(&type), MAX_BASIC_TYPE_BITS); ret = MAX_BASIC_TYPE_BITS; } - ret = snprintf(buf, 16, "%c%d", - die_is_signed_type(&type) ? 's' : 'u', ret); + ret = snprintf(buf, 16, "%c%d", sign, ret); formatted: if (ret < 0 || ret >= 16) { diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 947d21f38398..3d3cb8392c86 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -588,7 +588,11 @@ static char *get_trace_output(struct hist_entry *he) } else { pevent_event_info(&seq, evsel->tp_format, &rec); } - return seq.buffer; + /* + * Trim the buffer, it starts at 4KB and we're not going to + * add anything more to this buffer. + */ + return realloc(seq.buffer, seq.len + 1); } static int64_t diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index a34321e9b44d..a811c13a74d6 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -837,7 +837,8 @@ int dso__load_sym(struct dso *dso, struct map *map, sec = syms_ss->symtab; shdr = syms_ss->symshdr; - if (elf_section_by_name(elf, &ehdr, &tshdr, ".text", NULL)) + if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr, + ".text", NULL)) dso->text_offset = tshdr.sh_addr - tshdr.sh_offset; if (runtime_ss->opdsec) diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index cf5e250bc78e..783a53fb7a4e 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -66,7 +66,7 @@ static int entry(u64 ip, struct unwind_info *ui) if (__report_module(&al, ip, ui)) return -1; - e->ip = ip; + e->ip = al.addr; e->map = al.map; e->sym = al.sym; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 97c0f8fc5561..20c2e5743903 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -542,7 +542,7 @@ static int entry(u64 ip, struct thread *thread, thread__find_addr_location(thread, PERF_RECORD_MISC_USER, MAP__FUNCTION, ip, &al); - e.ip = ip; + e.ip = al.addr; e.map = al.map; e.sym = al.sym; diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 5404efa578a3..dd48f421844c 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -13,6 +13,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/platform_device.h> #include <linux/dma-mapping.h> +#include <linux/workqueue.h> #include <linux/libnvdimm.h> #include <linux/vmalloc.h> #include <linux/device.h> @@ -1474,6 +1475,7 @@ static int nfit_test_probe(struct platform_device *pdev) if (nfit_test->setup != nfit_test0_setup) return 0; + flush_work(&acpi_desc->work); nfit_test->setup_hotplug = 1; nfit_test->setup(nfit_test); diff --git a/tools/testing/selftests/powerpc/Makefile b/tools/testing/selftests/powerpc/Makefile index 3c40c9d0e6c7..1cc6d64c39b7 100644 --- a/tools/testing/selftests/powerpc/Makefile +++ b/tools/testing/selftests/powerpc/Makefile @@ -8,7 +8,7 @@ ifeq ($(ARCH),powerpc) GIT_VERSION = $(shell git describe --always --long --dirty || echo "unknown") -CFLAGS := -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) +CFLAGS := -std=gnu99 -Wall -O2 -Wall -Werror -DGIT_VERSION='"$(GIT_VERSION)"' -I$(CURDIR) $(CFLAGS) export CFLAGS diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h index 4f93af89ae16..18601f6689b9 100644 --- a/tools/virtio/linux/dma-mapping.h +++ b/tools/virtio/linux/dma-mapping.h @@ -14,4 +14,20 @@ enum dma_data_direction { DMA_NONE = 3, }; +#define dma_alloc_coherent(d, s, hp, f) ({ \ + void *__dma_alloc_coherent_p = kmalloc((s), (f)); \ + *(hp) = (unsigned long)__dma_alloc_coherent_p; \ + __dma_alloc_coherent_p; \ +}) + +#define dma_free_coherent(d, s, p, h) kfree(p) + +#define dma_map_page(d, p, o, s, dir) (page_to_phys(p) + (o)) + +#define dma_map_single(d, p, s, dir) (virt_to_phys(p)) +#define dma_mapping_error(...) (0) + +#define dma_unmap_single(...) do { } while (0) +#define dma_unmap_page(...) do { } while (0) + #endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 033849948215..d9554fc3f340 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -20,7 +20,9 @@ #define PAGE_SIZE getpagesize() #define PAGE_MASK (~(PAGE_SIZE-1)) +#define PAGE_ALIGN(x) ((x + PAGE_SIZE - 1) & PAGE_MASK) +typedef unsigned long long phys_addr_t; typedef unsigned long long dma_addr_t; typedef size_t __kernel_size_t; typedef unsigned int __wsum; @@ -57,6 +59,11 @@ static inline void *kzalloc(size_t s, gfp_t gfp) return p; } +static inline void *alloc_pages_exact(size_t s, gfp_t gfp) +{ + return kmalloc(s, gfp); +} + static inline void kfree(void *p) { if (p >= __kfree_ignore_start && p < __kfree_ignore_end) @@ -64,6 +71,11 @@ static inline void kfree(void *p) free(p); } +static inline void free_pages_exact(void *p, size_t s) +{ + kfree(p); +} + static inline void *krealloc(void *p, size_t s, gfp_t gfp) { return realloc(p, s); @@ -105,6 +117,8 @@ static inline void free_page(unsigned long addr) #define dev_err(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__) #define dev_warn(dev, format, ...) fprintf (stderr, format, ## __VA_ARGS__) +#define WARN_ON_ONCE(cond) ((cond) && fprintf (stderr, "WARNING\n")) + #define min(x, y) ({ \ typeof(x) _min1 = (x); \ typeof(y) _min2 = (y); \ diff --git a/tools/virtio/linux/slab.h b/tools/virtio/linux/slab.h index 81baeac8ae40..7e1c1197d439 100644 --- a/tools/virtio/linux/slab.h +++ b/tools/virtio/linux/slab.h @@ -1,2 +1,6 @@ #ifndef LINUX_SLAB_H +#define GFP_KERNEL 0 +#define GFP_ATOMIC 0 +#define __GFP_NOWARN 0 +#define __GFP_ZERO 0 #endif diff --git a/tools/virtio/linux/virtio.h b/tools/virtio/linux/virtio.h index ee125e714053..9377c8b4ac16 100644 --- a/tools/virtio/linux/virtio.h +++ b/tools/virtio/linux/virtio.h @@ -3,8 +3,12 @@ #include <linux/scatterlist.h> #include <linux/kernel.h> +struct device { + void *parent; +}; + struct virtio_device { - void *dev; + struct device dev; u64 features; }; diff --git a/tools/virtio/linux/virtio_config.h b/tools/virtio/linux/virtio_config.h index 57a6964a1e35..9ba11815e0a1 100644 --- a/tools/virtio/linux/virtio_config.h +++ b/tools/virtio/linux/virtio_config.h @@ -40,6 +40,19 @@ static inline void __virtio_clear_bit(struct virtio_device *vdev, #define virtio_has_feature(dev, feature) \ (__virtio_test_bit((dev), feature)) +/** + * virtio_has_iommu_quirk - determine whether this device has the iommu quirk + * @vdev: the device + */ +static inline bool virtio_has_iommu_quirk(const struct virtio_device *vdev) +{ + /* + * Note the reverse polarity of the quirk feature (compared to most + * other features), this is for compatibility with legacy systems. + */ + return !virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); +} + static inline bool virtio_is_little_endian(struct virtio_device *vdev) { return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) || diff --git a/tools/virtio/ringtest/ptr_ring.c b/tools/virtio/ringtest/ptr_ring.c index 68e4f9f0da3a..bd2ad1d3b7a9 100644 --- a/tools/virtio/ringtest/ptr_ring.c +++ b/tools/virtio/ringtest/ptr_ring.c @@ -13,6 +13,7 @@ #define cache_line_size() SMP_CACHE_BYTES #define ____cacheline_aligned_in_smp __attribute__ ((aligned (SMP_CACHE_BYTES))) #define unlikely(x) (__builtin_expect(!!(x), 0)) +#define likely(x) (__builtin_expect(!!(x), 1)) #define ALIGN(x, a) (((x) + (a) - 1) / (a) * (a)) typedef pthread_spinlock_t spinlock_t; diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 4fde8c7dfcfe..77e6ccf14901 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -33,6 +33,7 @@ static struct timecounter *timecounter; static struct workqueue_struct *wqueue; static unsigned int host_vtimer_irq; +static u32 host_vtimer_irq_flags; void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { @@ -365,7 +366,7 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) static void kvm_timer_init_interrupt(void *info) { - enable_percpu_irq(host_vtimer_irq, 0); + enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); } int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) @@ -432,6 +433,14 @@ int kvm_timer_hyp_init(void) } host_vtimer_irq = info->virtual_irq; + host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq); + if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH && + host_vtimer_irq_flags != IRQF_TRIGGER_LOW) { + kvm_err("Invalid trigger for IRQ%d, assuming level low\n", + host_vtimer_irq); + host_vtimer_irq_flags = IRQF_TRIGGER_LOW; + } + err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler, "kvm guest timer", kvm_get_running_vcpus()); if (err) { diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index fb4b0a79a950..83777c1cbae0 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -73,12 +73,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) int i, vcpu_lock_idx = -1, ret; struct kvm_vcpu *vcpu; - mutex_lock(&kvm->lock); - - if (irqchip_in_kernel(kvm)) { - ret = -EEXIST; - goto out; - } + if (irqchip_in_kernel(kvm)) + return -EEXIST; /* * This function is also called by the KVM_CREATE_IRQCHIP handler, @@ -87,10 +83,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) * the proper checks already. */ if (type == KVM_DEV_TYPE_ARM_VGIC_V2 && - !kvm_vgic_global_state.can_emulate_gicv2) { - ret = -ENODEV; - goto out; - } + !kvm_vgic_global_state.can_emulate_gicv2) + return -ENODEV; /* * Any time a vcpu is run, vcpu_load is called which tries to grab the @@ -138,9 +132,6 @@ out_unlock: vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx); mutex_unlock(&vcpu->mutex); } - -out: - mutex_unlock(&kvm->lock); return ret; } diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 07411cf967b9..4660a7d04eea 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -51,7 +51,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid) irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL); if (!irq) - return NULL; + return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&irq->lpi_list); INIT_LIST_HEAD(&irq->ap_list); @@ -441,39 +441,63 @@ static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, * Find the target VCPU and the LPI number for a given devid/eventid pair * and make this IRQ pending, possibly injecting it. * Must be called with the its_lock mutex held. + * Returns 0 on success, a positive error value for any ITS mapping + * related errors and negative error values for generic errors. */ -static void vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, - u32 devid, u32 eventid) +static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, + u32 devid, u32 eventid) { + struct kvm_vcpu *vcpu; struct its_itte *itte; if (!its->enabled) - return; + return -EBUSY; itte = find_itte(its, devid, eventid); - /* Triggering an unmapped IRQ gets silently dropped. */ - if (itte && its_is_collection_mapped(itte->collection)) { - struct kvm_vcpu *vcpu; - - vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); - if (vcpu && vcpu->arch.vgic_cpu.lpis_enabled) { - spin_lock(&itte->irq->irq_lock); - itte->irq->pending = true; - vgic_queue_irq_unlock(kvm, itte->irq); - } - } + if (!itte || !its_is_collection_mapped(itte->collection)) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); + if (!vcpu) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + if (!vcpu->arch.vgic_cpu.lpis_enabled) + return -EBUSY; + + spin_lock(&itte->irq->irq_lock); + itte->irq->pending = true; + vgic_queue_irq_unlock(kvm, itte->irq); + + return 0; +} + +static struct vgic_io_device *vgic_get_its_iodev(struct kvm_io_device *dev) +{ + struct vgic_io_device *iodev; + + if (dev->ops != &kvm_io_gic_ops) + return NULL; + + iodev = container_of(dev, struct vgic_io_device, dev); + + if (iodev->iodev_type != IODEV_ITS) + return NULL; + + return iodev; } /* * Queries the KVM IO bus framework to get the ITS pointer from the given * doorbell address. * We then call vgic_its_trigger_msi() with the decoded data. + * According to the KVM_SIGNAL_MSI API description returns 1 on success. */ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) { u64 address; struct kvm_io_device *kvm_io_dev; struct vgic_io_device *iodev; + int ret; if (!vgic_has_its(kvm)) return -ENODEV; @@ -485,15 +509,28 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) kvm_io_dev = kvm_io_bus_get_dev(kvm, KVM_MMIO_BUS, address); if (!kvm_io_dev) - return -ENODEV; + return -EINVAL; - iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); + iodev = vgic_get_its_iodev(kvm_io_dev); + if (!iodev) + return -EINVAL; mutex_lock(&iodev->its->its_lock); - vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); + ret = vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); mutex_unlock(&iodev->its->its_lock); - return 0; + if (ret < 0) + return ret; + + /* + * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 + * if the guest has blocked the MSI. So we map any LPI mapping + * related error to that. + */ + if (ret) + return 0; + else + return 1; } /* Requires the its_lock to be held. */ @@ -502,7 +539,8 @@ static void its_free_itte(struct kvm *kvm, struct its_itte *itte) list_del(&itte->itte_list); /* This put matches the get in vgic_add_lpi. */ - vgic_put_irq(kvm, itte->irq); + if (itte->irq) + vgic_put_irq(kvm, itte->irq); kfree(itte); } @@ -697,6 +735,7 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, struct its_device *device; struct its_collection *collection, *new_coll = NULL; int lpi_nr; + struct vgic_irq *irq; device = find_its_device(its, device_id); if (!device) @@ -710,6 +749,10 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, lpi_nr >= max_lpis_propbaser(kvm->arch.vgic.propbaser)) return E_ITS_MAPTI_PHYSICALID_OOR; + /* If there is an existing mapping, behavior is UNPREDICTABLE. */ + if (find_itte(its, device_id, event_id)) + return 0; + collection = find_collection(its, coll_id); if (!collection) { int ret = vgic_its_alloc_collection(its, &collection, coll_id); @@ -718,22 +761,28 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its, new_coll = collection; } - itte = find_itte(its, device_id, event_id); + itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL); if (!itte) { - itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL); - if (!itte) { - if (new_coll) - vgic_its_free_collection(its, coll_id); - return -ENOMEM; - } - - itte->event_id = event_id; - list_add_tail(&itte->itte_list, &device->itt_head); + if (new_coll) + vgic_its_free_collection(its, coll_id); + return -ENOMEM; } + itte->event_id = event_id; + list_add_tail(&itte->itte_list, &device->itt_head); + itte->collection = collection; itte->lpi = lpi_nr; - itte->irq = vgic_add_lpi(kvm, lpi_nr); + + irq = vgic_add_lpi(kvm, lpi_nr); + if (IS_ERR(irq)) { + if (new_coll) + vgic_its_free_collection(its, coll_id); + its_free_itte(kvm, itte); + return PTR_ERR(irq); + } + itte->irq = irq; + update_affinity_itte(kvm, itte); /* @@ -981,9 +1030,7 @@ static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, u32 msi_data = its_cmd_get_id(its_cmd); u64 msi_devid = its_cmd_get_deviceid(its_cmd); - vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); - - return 0; + return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); } /* @@ -1288,13 +1335,13 @@ void vgic_enable_lpis(struct kvm_vcpu *vcpu) its_sync_lpi_pending_table(vcpu); } -static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its) +static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its) { struct vgic_io_device *iodev = &its->iodev; int ret; - if (its->initialized) - return 0; + if (!its->initialized) + return -EBUSY; if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) return -ENXIO; @@ -1311,9 +1358,6 @@ static int vgic_its_init_its(struct kvm *kvm, struct vgic_its *its) KVM_VGIC_V3_ITS_SIZE, &iodev->dev); mutex_unlock(&kvm->slots_lock); - if (!ret) - its->initialized = true; - return ret; } @@ -1435,9 +1479,6 @@ static int vgic_its_set_attr(struct kvm_device *dev, if (type != KVM_VGIC_ITS_ADDR_TYPE) return -ENODEV; - if (its->initialized) - return -EBUSY; - if (copy_from_user(&addr, uaddr, sizeof(addr))) return -EFAULT; @@ -1453,7 +1494,9 @@ static int vgic_its_set_attr(struct kvm_device *dev, case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: - return vgic_its_init_its(dev->kvm, its); + its->initialized = true; + + return 0; } break; } @@ -1498,3 +1541,30 @@ int kvm_vgic_register_its_device(void) return kvm_register_device_ops(&kvm_arm_vgic_its_ops, KVM_DEV_TYPE_ARM_VGIC_ITS); } + +/* + * Registers all ITSes with the kvm_io_bus framework. + * To follow the existing VGIC initialization sequence, this has to be + * done as late as possible, just before the first VCPU runs. + */ +int vgic_register_its_iodevs(struct kvm *kvm) +{ + struct kvm_device *dev; + int ret = 0; + + list_for_each_entry(dev, &kvm->devices, vm_node) { + if (dev->ops != &kvm_arm_vgic_its_ops) + continue; + + ret = vgic_register_its_iodev(kvm, dev->private); + if (ret) + return ret; + /* + * We don't need to care about tearing down previously + * registered ITSes, as the kvm_io_bus framework removes + * them for us if the VM gets destroyed. + */ + } + + return ret; +} diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index ff668e0dd586..90d81811fdda 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -306,16 +306,19 @@ static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu, { struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 propbaser = dist->propbaser; + u64 old_propbaser, propbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_cpu->lpis_enabled) return; - propbaser = update_64bit_reg(propbaser, addr & 4, len, val); - propbaser = vgic_sanitise_propbaser(propbaser); - - dist->propbaser = propbaser; + do { + old_propbaser = dist->propbaser; + propbaser = old_propbaser; + propbaser = update_64bit_reg(propbaser, addr & 4, len, val); + propbaser = vgic_sanitise_propbaser(propbaser); + } while (cmpxchg64(&dist->propbaser, old_propbaser, + propbaser) != old_propbaser); } static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu, @@ -331,16 +334,19 @@ static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu, unsigned long val) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - u64 pendbaser = vgic_cpu->pendbaser; + u64 old_pendbaser, pendbaser; /* Storing a value with LPIs already enabled is undefined */ if (vgic_cpu->lpis_enabled) return; - pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); - pendbaser = vgic_sanitise_pendbaser(pendbaser); - - vgic_cpu->pendbaser = pendbaser; + do { + old_pendbaser = vgic_cpu->pendbaser; + pendbaser = old_pendbaser; + pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val); + pendbaser = vgic_sanitise_pendbaser(pendbaser); + } while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser, + pendbaser) != old_pendbaser); } /* diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c index 0506543df38a..9f0dae397d9c 100644 --- a/virt/kvm/arm/vgic/vgic-v3.c +++ b/virt/kvm/arm/vgic/vgic-v3.c @@ -289,6 +289,14 @@ int vgic_v3_map_resources(struct kvm *kvm) goto out; } + if (vgic_has_its(kvm)) { + ret = vgic_register_its_iodevs(kvm); + if (ret) { + kvm_err("Unable to register VGIC ITS MMIO regions\n"); + goto out; + } + } + dist->ready = true; out: diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c index e7aeac719e09..e83b7fe4baae 100644 --- a/virt/kvm/arm/vgic/vgic.c +++ b/virt/kvm/arm/vgic/vgic.c @@ -117,17 +117,17 @@ static void vgic_irq_release(struct kref *ref) void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq) { - struct vgic_dist *dist; + struct vgic_dist *dist = &kvm->arch.vgic; if (irq->intid < VGIC_MIN_LPI) return; - if (!kref_put(&irq->refcount, vgic_irq_release)) + spin_lock(&dist->lpi_list_lock); + if (!kref_put(&irq->refcount, vgic_irq_release)) { + spin_unlock(&dist->lpi_list_lock); return; + }; - dist = &kvm->arch.vgic; - - spin_lock(&dist->lpi_list_lock); list_del(&irq->lpi_list); dist->lpi_list_count--; spin_unlock(&dist->lpi_list_lock); diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h index 1d8e21d5c13f..6c4625c46368 100644 --- a/virt/kvm/arm/vgic/vgic.h +++ b/virt/kvm/arm/vgic/vgic.h @@ -84,6 +84,7 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu); int vgic_v3_probe(const struct gic_kvm_info *info); int vgic_v3_map_resources(struct kvm *kvm); int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address); +int vgic_register_its_iodevs(struct kvm *kvm); bool vgic_has_its(struct kvm *kvm); int kvm_vgic_register_its_device(void); void vgic_enable_lpis(struct kvm_vcpu *vcpu); @@ -140,6 +141,11 @@ static inline int vgic_register_redist_iodevs(struct kvm *kvm, return -ENODEV; } +static inline int vgic_register_its_iodevs(struct kvm *kvm) +{ + return -ENODEV; +} + static inline bool vgic_has_its(struct kvm *kvm) { return false; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cc081ccfcaa3..195078225aa5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -696,6 +696,11 @@ static void kvm_destroy_devices(struct kvm *kvm) { struct kvm_device *dev, *tmp; + /* + * We do not need to take the kvm->lock here, because nobody else + * has a reference to the struct kvm at this point and therefore + * cannot access the devices list anyhow. + */ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { list_del(&dev->vm_node); dev->ops->destroy(dev); @@ -2832,19 +2837,28 @@ static int kvm_ioctl_create_device(struct kvm *kvm, dev->ops = ops; dev->kvm = kvm; + mutex_lock(&kvm->lock); ret = ops->create(dev, cd->type); if (ret < 0) { + mutex_unlock(&kvm->lock); kfree(dev); return ret; } + list_add(&dev->vm_node, &kvm->devices); + mutex_unlock(&kvm->lock); + + if (ops->init) + ops->init(dev); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { ops->destroy(dev); + mutex_lock(&kvm->lock); + list_del(&dev->vm_node); + mutex_unlock(&kvm->lock); return ret; } - list_add(&dev->vm_node, &kvm->devices); kvm_get_kvm(kvm); cd->fd = ret; return 0; |