diff options
655 files changed, 7395 insertions, 3526 deletions
diff --git a/Documentation/core-api/printk-formats.rst b/Documentation/core-api/printk-formats.rst index 8ebe46b1af39..5dfcc4592b23 100644 --- a/Documentation/core-api/printk-formats.rst +++ b/Documentation/core-api/printk-formats.rst @@ -112,6 +112,20 @@ used when printing stack backtraces. The specifier takes into consideration the effect of compiler optimisations which may occur when tail-calls are used and marked with the noreturn GCC attribute. +Probed Pointers from BPF / tracing +---------------------------------- + +:: + + %pks kernel string + %pus user string + +The ``k`` and ``u`` specifiers are used for printing prior probed memory from +either kernel memory (k) or user memory (u). The subsequent ``s`` specifier +results in printing a string. For direct use in regular vsnprintf() the (k) +and (u) annotation is ignored, however, when used out of BPF's bpf_trace_printk(), +for example, it reads the memory it is pointing to without faulting. + Kernel Pointers --------------- diff --git a/Documentation/devicetree/bindings/dma/fsl-edma.txt b/Documentation/devicetree/bindings/dma/fsl-edma.txt index e77b08ebcd06..ee1754739b4b 100644 --- a/Documentation/devicetree/bindings/dma/fsl-edma.txt +++ b/Documentation/devicetree/bindings/dma/fsl-edma.txt @@ -10,7 +10,8 @@ Required properties: - compatible : - "fsl,vf610-edma" for eDMA used similar to that on Vybrid vf610 SoC - "fsl,imx7ulp-edma" for eDMA2 used similar to that on i.mx7ulp - - "fsl,fsl,ls1028a-edma" for eDMA used similar to that on Vybrid vf610 SoC + - "fsl,ls1028a-edma" followed by "fsl,vf610-edma" for eDMA used on the + LS1028A SoC. - reg : Specifies base physical address(s) and size of the eDMA registers. The 1st region is eDMA control register's address and size. The 2nd and the 3rd regions are programmable channel multiplexing diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index 5b58fc4e1268..4574352d6ff4 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -61,8 +61,8 @@ The ``ice`` driver reports the following versions - running - ICE OS Default Package - The name of the DDP package that is active in the device. The DDP - package is loaded by the driver during initialization. Each varation - of DDP package shall have a unique name. + package is loaded by the driver during initialization. Each + variation of the DDP package has a unique name. * - ``fw.app`` - running - 1.3.1.0 diff --git a/Documentation/usb/raw-gadget.rst b/Documentation/usb/raw-gadget.rst index 9e78cb858f86..68d879a8009e 100644 --- a/Documentation/usb/raw-gadget.rst +++ b/Documentation/usb/raw-gadget.rst @@ -27,9 +27,8 @@ differences are: 3. Raw Gadget provides a way to select a UDC device/driver to bind to, while GadgetFS currently binds to the first available UDC. -4. Raw Gadget uses predictable endpoint names (handles) across different - UDCs (as long as UDCs have enough endpoints of each required transfer - type). +4. Raw Gadget explicitly exposes information about endpoints addresses and + capabilities allowing a user to write UDC-agnostic gadgets. 5. Raw Gadget has ioctl-based interface instead of a filesystem-based one. @@ -50,12 +49,36 @@ The typical usage of Raw Gadget looks like: Raw Gadget and react to those depending on what kind of USB device needs to be emulated. +Note, that some UDC drivers have fixed addresses assigned to endpoints, and +therefore arbitrary endpoint addresses can't be used in the descriptors. +Nevertheles, Raw Gadget provides a UDC-agnostic way to write USB gadgets. +Once a USB_RAW_EVENT_CONNECT event is received via USB_RAW_IOCTL_EVENT_FETCH, +the USB_RAW_IOCTL_EPS_INFO ioctl can be used to find out information about +endpoints that the UDC driver has. Based on that information, the user must +chose UDC endpoints that will be used for the gadget being emulated, and +properly assign addresses in endpoint descriptors. + +You can find usage examples (along with a test suite) here: + +https://github.com/xairy/raw-gadget + +Internal details +~~~~~~~~~~~~~~~~ + +Currently every endpoint read/write ioctl submits a USB request and waits until +its completion. This is the desired mode for coverage-guided fuzzing (as we'd +like all USB request processing happen during the lifetime of a syscall), +and must be kept in the implementation. (This might be slow for real world +applications, thus the O_NONBLOCK improvement suggestion below.) + Potential future improvements ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -- Implement ioctl's for setting/clearing halt status on endpoints. - -- Reporting more events (suspend, resume, etc.) through - USB_RAW_IOCTL_EVENT_FETCH. +- Report more events (suspend, resume, etc.) through USB_RAW_IOCTL_EVENT_FETCH. - Support O_NONBLOCK I/O. + +- Support USB 3 features (accept SS endpoint companion descriptor when + enabling endpoints; allow providing stream_id for bulk transfers). + +- Support ISO transfer features (expose frame_number for completed requests). diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index dcc252634cf9..b6833c7bb474 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -28,3 +28,5 @@ KVM arm/index devices/index + + running-nested-guests diff --git a/Documentation/virt/kvm/running-nested-guests.rst b/Documentation/virt/kvm/running-nested-guests.rst new file mode 100644 index 000000000000..d0a1fc754c84 --- /dev/null +++ b/Documentation/virt/kvm/running-nested-guests.rst @@ -0,0 +1,276 @@ +============================== +Running nested guests with KVM +============================== + +A nested guest is the ability to run a guest inside another guest (it +can be KVM-based or a different hypervisor). The straightforward +example is a KVM guest that in turn runs on a KVM guest (the rest of +this document is built on this example):: + + .----------------. .----------------. + | | | | + | L2 | | L2 | + | (Nested Guest) | | (Nested Guest) | + | | | | + |----------------'--'----------------| + | | + | L1 (Guest Hypervisor) | + | KVM (/dev/kvm) | + | | + .------------------------------------------------------. + | L0 (Host Hypervisor) | + | KVM (/dev/kvm) | + |------------------------------------------------------| + | Hardware (with virtualization extensions) | + '------------------------------------------------------' + +Terminology: + +- L0 – level-0; the bare metal host, running KVM + +- L1 – level-1 guest; a VM running on L0; also called the "guest + hypervisor", as it itself is capable of running KVM. + +- L2 – level-2 guest; a VM running on L1, this is the "nested guest" + +.. note:: The above diagram is modelled after the x86 architecture; + s390x, ppc64 and other architectures are likely to have + a different design for nesting. + + For example, s390x always has an LPAR (LogicalPARtition) + hypervisor running on bare metal, adding another layer and + resulting in at least four levels in a nested setup — L0 (bare + metal, running the LPAR hypervisor), L1 (host hypervisor), L2 + (guest hypervisor), L3 (nested guest). + + This document will stick with the three-level terminology (L0, + L1, and L2) for all architectures; and will largely focus on + x86. + + +Use Cases +--------- + +There are several scenarios where nested KVM can be useful, to name a +few: + +- As a developer, you want to test your software on different operating + systems (OSes). Instead of renting multiple VMs from a Cloud + Provider, using nested KVM lets you rent a large enough "guest + hypervisor" (level-1 guest). This in turn allows you to create + multiple nested guests (level-2 guests), running different OSes, on + which you can develop and test your software. + +- Live migration of "guest hypervisors" and their nested guests, for + load balancing, disaster recovery, etc. + +- VM image creation tools (e.g. ``virt-install``, etc) often run + their own VM, and users expect these to work inside a VM. + +- Some OSes use virtualization internally for security (e.g. to let + applications run safely in isolation). + + +Enabling "nested" (x86) +----------------------- + +From Linux kernel v4.19 onwards, the ``nested`` KVM parameter is enabled +by default for Intel and AMD. (Though your Linux distribution might +override this default.) + +In case you are running a Linux kernel older than v4.19, to enable +nesting, set the ``nested`` KVM module parameter to ``Y`` or ``1``. To +persist this setting across reboots, you can add it in a config file, as +shown below: + +1. On the bare metal host (L0), list the kernel modules and ensure that + the KVM modules:: + + $ lsmod | grep -i kvm + kvm_intel 133627 0 + kvm 435079 1 kvm_intel + +2. Show information for ``kvm_intel`` module:: + + $ modinfo kvm_intel | grep -i nested + parm: nested:bool + +3. For the nested KVM configuration to persist across reboots, place the + below in ``/etc/modprobed/kvm_intel.conf`` (create the file if it + doesn't exist):: + + $ cat /etc/modprobe.d/kvm_intel.conf + options kvm-intel nested=y + +4. Unload and re-load the KVM Intel module:: + + $ sudo rmmod kvm-intel + $ sudo modprobe kvm-intel + +5. Verify if the ``nested`` parameter for KVM is enabled:: + + $ cat /sys/module/kvm_intel/parameters/nested + Y + +For AMD hosts, the process is the same as above, except that the module +name is ``kvm-amd``. + + +Additional nested-related kernel parameters (x86) +------------------------------------------------- + +If your hardware is sufficiently advanced (Intel Haswell processor or +higher, which has newer hardware virt extensions), the following +additional features will also be enabled by default: "Shadow VMCS +(Virtual Machine Control Structure)", APIC Virtualization on your bare +metal host (L0). Parameters for Intel hosts:: + + $ cat /sys/module/kvm_intel/parameters/enable_shadow_vmcs + Y + + $ cat /sys/module/kvm_intel/parameters/enable_apicv + Y + + $ cat /sys/module/kvm_intel/parameters/ept + Y + +.. note:: If you suspect your L2 (i.e. nested guest) is running slower, + ensure the above are enabled (particularly + ``enable_shadow_vmcs`` and ``ept``). + + +Starting a nested guest (x86) +----------------------------- + +Once your bare metal host (L0) is configured for nesting, you should be +able to start an L1 guest with:: + + $ qemu-kvm -cpu host [...] + +The above will pass through the host CPU's capabilities as-is to the +gues); or for better live migration compatibility, use a named CPU +model supported by QEMU. e.g.:: + + $ qemu-kvm -cpu Haswell-noTSX-IBRS,vmx=on + +then the guest hypervisor will subsequently be capable of running a +nested guest with accelerated KVM. + + +Enabling "nested" (s390x) +------------------------- + +1. On the host hypervisor (L0), enable the ``nested`` parameter on + s390x:: + + $ rmmod kvm + $ modprobe kvm nested=1 + +.. note:: On s390x, the kernel parameter ``hpage`` is mutually exclusive + with the ``nested`` paramter — i.e. to be able to enable + ``nested``, the ``hpage`` parameter *must* be disabled. + +2. The guest hypervisor (L1) must be provided with the ``sie`` CPU + feature — with QEMU, this can be done by using "host passthrough" + (via the command-line ``-cpu host``). + +3. Now the KVM module can be loaded in the L1 (guest hypervisor):: + + $ modprobe kvm + + +Live migration with nested KVM +------------------------------ + +Migrating an L1 guest, with a *live* nested guest in it, to another +bare metal host, works as of Linux kernel 5.3 and QEMU 4.2.0 for +Intel x86 systems, and even on older versions for s390x. + +On AMD systems, once an L1 guest has started an L2 guest, the L1 guest +should no longer be migrated or saved (refer to QEMU documentation on +"savevm"/"loadvm") until the L2 guest shuts down. Attempting to migrate +or save-and-load an L1 guest while an L2 guest is running will result in +undefined behavior. You might see a ``kernel BUG!`` entry in ``dmesg``, a +kernel 'oops', or an outright kernel panic. Such a migrated or loaded L1 +guest can no longer be considered stable or secure, and must be restarted. +Migrating an L1 guest merely configured to support nesting, while not +actually running L2 guests, is expected to function normally even on AMD +systems but may fail once guests are started. + +Migrating an L2 guest is always expected to succeed, so all the following +scenarios should work even on AMD systems: + +- Migrating a nested guest (L2) to another L1 guest on the *same* bare + metal host. + +- Migrating a nested guest (L2) to another L1 guest on a *different* + bare metal host. + +- Migrating a nested guest (L2) to a bare metal host. + +Reporting bugs from nested setups +----------------------------------- + +Debugging "nested" problems can involve sifting through log files across +L0, L1 and L2; this can result in tedious back-n-forth between the bug +reporter and the bug fixer. + +- Mention that you are in a "nested" setup. If you are running any kind + of "nesting" at all, say so. Unfortunately, this needs to be called + out because when reporting bugs, people tend to forget to even + *mention* that they're using nested virtualization. + +- Ensure you are actually running KVM on KVM. Sometimes people do not + have KVM enabled for their guest hypervisor (L1), which results in + them running with pure emulation or what QEMU calls it as "TCG", but + they think they're running nested KVM. Thus confusing "nested Virt" + (which could also mean, QEMU on KVM) with "nested KVM" (KVM on KVM). + +Information to collect (generic) +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The following is not an exhaustive list, but a very good starting point: + + - Kernel, libvirt, and QEMU version from L0 + + - Kernel, libvirt and QEMU version from L1 + + - QEMU command-line of L1 -- when using libvirt, you'll find it here: + ``/var/log/libvirt/qemu/instance.log`` + + - QEMU command-line of L2 -- as above, when using libvirt, get the + complete libvirt-generated QEMU command-line + + - ``cat /sys/cpuinfo`` from L0 + + - ``cat /sys/cpuinfo`` from L1 + + - ``lscpu`` from L0 + + - ``lscpu`` from L1 + + - Full ``dmesg`` output from L0 + + - Full ``dmesg`` output from L1 + +x86-specific info to collect +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Both the below commands, ``x86info`` and ``dmidecode``, should be +available on most Linux distributions with the same name: + + - Output of: ``x86info -a`` from L0 + + - Output of: ``x86info -a`` from L1 + + - Output of: ``dmidecode`` from L0 + + - Output of: ``dmidecode`` from L1 + +s390x-specific info to collect +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Along with the earlier mentioned generic details, the below is +also recommended: + + - ``/proc/sysinfo`` from L1; this will also include the info from L0 diff --git a/MAINTAINERS b/MAINTAINERS index 2926327e4976..ecc0749810b0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3936,11 +3936,9 @@ F: arch/powerpc/platforms/cell/ CEPH COMMON CODE (LIBCEPH) M: Ilya Dryomov <idryomov@gmail.com> M: Jeff Layton <jlayton@kernel.org> -M: Sage Weil <sage@redhat.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: include/linux/ceph/ F: include/linux/crush/ @@ -3948,12 +3946,10 @@ F: net/ceph/ CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH) M: Jeff Layton <jlayton@kernel.org> -M: Sage Weil <sage@redhat.com> M: Ilya Dryomov <idryomov@gmail.com> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: Documentation/filesystems/ceph.rst F: fs/ceph/ @@ -5935,9 +5931,9 @@ F: lib/dynamic_debug.c DYNAMIC INTERRUPT MODERATION M: Tal Gilboa <talgi@mellanox.com> S: Maintained +F: Documentation/networking/net_dim.rst F: include/linux/dim.h F: lib/dim/ -F: Documentation/networking/net_dim.rst DZ DECSTATION DZ11 SERIAL DRIVER M: "Maciej W. Rozycki" <macro@linux-mips.org> @@ -7119,9 +7115,10 @@ F: include/uapi/asm-generic/ GENERIC PHY FRAMEWORK M: Kishon Vijay Abraham I <kishon@ti.com> +M: Vinod Koul <vkoul@kernel.org> L: linux-kernel@vger.kernel.org S: Supported -T: git git://git.kernel.org/pub/scm/linux/kernel/git/kishon/linux-phy.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git F: Documentation/devicetree/bindings/phy/ F: drivers/phy/ F: include/linux/phy/ @@ -7746,11 +7743,6 @@ L: platform-driver-x86@vger.kernel.org S: Orphan F: drivers/platform/x86/tc1100-wmi.c -HP100: Driver for HP 10/100 Mbit/s Voice Grade Network Adapter Series -M: Jaroslav Kysela <perex@perex.cz> -S: Obsolete -F: drivers/staging/hp/hp100.* - HPET: High Precision Event Timers driver M: Clemens Ladisch <clemens@ladisch.de> S: Maintained @@ -11718,8 +11710,9 @@ F: net/core/drop_monitor.c NETWORKING DRIVERS M: "David S. Miller" <davem@davemloft.net> +M: Jakub Kicinski <kuba@kernel.org> L: netdev@vger.kernel.org -S: Odd Fixes +S: Maintained W: http://www.linuxfoundation.org/en/Net Q: http://patchwork.ozlabs.org/project/netdev/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git @@ -14102,12 +14095,10 @@ F: drivers/media/radio/radio-tea5777.c RADOS BLOCK DEVICE (RBD) M: Ilya Dryomov <idryomov@gmail.com> -M: Sage Weil <sage@redhat.com> R: Dongsheng Yang <dongsheng.yang@easystack.cn> L: ceph-devel@vger.kernel.org S: Supported W: http://ceph.com/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git T: git git://github.com/ceph/ceph-client.git F: Documentation/ABI/testing/sysfs-bus-rbd F: drivers/block/rbd.c @@ -14644,6 +14635,7 @@ F: drivers/iommu/s390-iommu.c S390 IUCV NETWORK LAYER M: Julian Wiedmann <jwi@linux.ibm.com> +M: Karsten Graul <kgraul@linux.ibm.com> M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported @@ -14654,6 +14646,7 @@ F: net/iucv/ S390 NETWORK DRIVERS M: Julian Wiedmann <jwi@linux.ibm.com> +M: Karsten Graul <kgraul@linux.ibm.com> M: Ursula Braun <ubraun@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc6 NAME = Kleptomaniac Octopus # *DOCUMENTATION* @@ -729,10 +729,6 @@ else ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE KBUILD_CFLAGS += -Os endif -ifdef CONFIG_CC_DISABLE_WARN_MAYBE_UNINITIALIZED -KBUILD_CFLAGS += -Wno-maybe-uninitialized -endif - # Tell gcc to never replace conditional load with a non-conditional one KBUILD_CFLAGS += $(call cc-option,--param=allow-store-data-races=0) KBUILD_CFLAGS += $(call cc-option,-fno-allow-store-data-races) @@ -881,6 +877,17 @@ KBUILD_CFLAGS += -Wno-pointer-sign # disable stringop warnings in gcc 8+ KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) +# We'll want to enable this eventually, but it's not going away for 5.7 at least +KBUILD_CFLAGS += $(call cc-disable-warning, zero-length-bounds) +KBUILD_CFLAGS += $(call cc-disable-warning, array-bounds) +KBUILD_CFLAGS += $(call cc-disable-warning, stringop-overflow) + +# Another good warning that we'll want to enable eventually +KBUILD_CFLAGS += $(call cc-disable-warning, restrict) + +# Enabled with W=2, disabled by default as noisy +KBUILD_CFLAGS += $(call cc-disable-warning, maybe-uninitialized) + # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 66a04f6f4775..c77c93c485a0 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -12,6 +12,7 @@ config ARM select ARCH_HAS_KEEPINITRD select ARCH_HAS_KCOV select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_SPECIAL if ARM_LPAE select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_SETUP_DMA_OPS diff --git a/arch/arm/boot/dts/am574x-idk.dts b/arch/arm/boot/dts/am574x-idk.dts index fa0088025b2c..85c95cc551dd 100644 --- a/arch/arm/boot/dts/am574x-idk.dts +++ b/arch/arm/boot/dts/am574x-idk.dts @@ -40,3 +40,7 @@ status = "okay"; dual_emac; }; + +&m_can0 { + status = "disabled"; +}; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 4740989ed9c4..7191ee6a1b82 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -172,6 +172,7 @@ #address-cells = <1>; ranges = <0x51000000 0x51000000 0x3000 0x0 0x20000000 0x10000000>; + dma-ranges; /** * To enable PCI endpoint mode, disable the pcie1_rc * node and enable pcie1_ep mode. @@ -185,7 +186,6 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x20013000 0x13000 0 0xffed000>; - dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; @@ -230,6 +230,7 @@ #address-cells = <1>; ranges = <0x51800000 0x51800000 0x3000 0x0 0x30000000 0x10000000>; + dma-ranges; status = "disabled"; pcie2_rc: pcie@51800000 { reg = <0x51800000 0x2000>, <0x51802000 0x14c>, <0x1000 0x2000>; @@ -240,7 +241,6 @@ device_type = "pci"; ranges = <0x81000000 0 0 0x03000 0 0x00010000 0x82000000 0 0x30013000 0x13000 0 0xffed000>; - dma-ranges = <0x02000000 0x0 0x00000000 0x00000000 0x1 0x00000000>; bus-range = <0x00 0xff>; #interrupt-cells = <1>; num-lanes = <1>; diff --git a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts index 0cd75dadf292..188639738dc3 100644 --- a/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts +++ b/arch/arm/boot/dts/imx27-phytec-phycard-s-rdk.dts @@ -75,8 +75,8 @@ imx27-phycard-s-rdk { pinctrl_i2c1: i2c1grp { fsl,pins = < - MX27_PAD_I2C2_SDA__I2C2_SDA 0x0 - MX27_PAD_I2C2_SCL__I2C2_SCL 0x0 + MX27_PAD_I2C_DATA__I2C_DATA 0x0 + MX27_PAD_I2C_CLK__I2C_CLK 0x0 >; }; diff --git a/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts b/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts index 0d594e4bd559..a1173bf5bff5 100644 --- a/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts +++ b/arch/arm/boot/dts/imx6dl-yapp4-ursa.dts @@ -38,7 +38,7 @@ }; &switch_ports { - /delete-node/ port@2; + /delete-node/ port@3; }; &touchscreen { diff --git a/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi b/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi index ede2e0c999b1..e10f99278c77 100644 --- a/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi +++ b/arch/arm/boot/dts/iwg20d-q7-dbcm-ca.dtsi @@ -72,8 +72,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/motorola-mapphone-common.dtsi index 9067e0ef4240..06fbffa81636 100644 --- a/arch/arm/boot/dts/motorola-mapphone-common.dtsi +++ b/arch/arm/boot/dts/motorola-mapphone-common.dtsi @@ -367,6 +367,8 @@ }; &mmc3 { + pinctrl-names = "default"; + pinctrl-0 = <&mmc3_pins>; vmmc-supply = <&wl12xx_vmmc>; /* uart2_tx.sdmmc3_dat1 pad as wakeirq */ interrupts-extended = <&wakeupgen GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH @@ -472,6 +474,37 @@ >; }; + /* + * Android uses PIN_OFF_INPUT_PULLDOWN | PIN_INPUT_PULLUP | MUX_MODE3 + * for gpio_100, but the internal pull makes wlan flakey on some + * devices. Off mode value should be tested if we have off mode working + * later on. + */ + mmc3_pins: pinmux_mmc3_pins { + pinctrl-single,pins = < + /* 0x4a10008e gpmc_wait2.gpio_100 d23 */ + OMAP4_IOPAD(0x08e, PIN_INPUT | MUX_MODE3) + + /* 0x4a100102 abe_mcbsp1_dx.sdmmc3_dat2 ab25 */ + OMAP4_IOPAD(0x102, PIN_INPUT_PULLUP | MUX_MODE1) + + /* 0x4a100104 abe_mcbsp1_fsx.sdmmc3_dat3 ac27 */ + OMAP4_IOPAD(0x104, PIN_INPUT_PULLUP | MUX_MODE1) + + /* 0x4a100118 uart2_cts.sdmmc3_clk ab26 */ + OMAP4_IOPAD(0x118, PIN_INPUT | MUX_MODE1) + + /* 0x4a10011a uart2_rts.sdmmc3_cmd ab27 */ + OMAP4_IOPAD(0x11a, PIN_INPUT_PULLUP | MUX_MODE1) + + /* 0x4a10011c uart2_rx.sdmmc3_dat0 aa25 */ + OMAP4_IOPAD(0x11c, PIN_INPUT_PULLUP | MUX_MODE1) + + /* 0x4a10011e uart2_tx.sdmmc3_dat1 aa26 */ + OMAP4_IOPAD(0x11e, PIN_INPUT_PULLUP | MUX_MODE1) + >; + }; + /* gpmc_ncs0.gpio_50 */ poweroff_gpio: pinmux_poweroff_pins { pinctrl-single,pins = < @@ -690,14 +723,18 @@ }; /* - * As uart1 is wired to mdm6600 with rts and cts, we can use the cts pin for - * uart1 wakeirq. + * The uart1 port is wired to mdm6600 with rts and cts. The modem uses gpio_149 + * for wake-up events for both the USB PHY and the UART. We can use gpio_149 + * pad as the shared wakeirq for the UART rather than the RX or CTS pad as we + * have gpio_149 trigger before the UART transfer starts. */ &uart1 { pinctrl-names = "default"; pinctrl-0 = <&uart1_pins>; interrupts-extended = <&wakeupgen GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH - &omap4_pmx_core 0xfc>; + &omap4_pmx_core 0x110>; + uart-has-rtscts; + current-speed = <115200>; }; &uart3 { diff --git a/arch/arm/boot/dts/r7s9210.dtsi b/arch/arm/boot/dts/r7s9210.dtsi index 72b79770e336..cace43807497 100644 --- a/arch/arm/boot/dts/r7s9210.dtsi +++ b/arch/arm/boot/dts/r7s9210.dtsi @@ -304,7 +304,6 @@ reg = <0xe803b000 0x30>; interrupts = <GIC_SPI 56 IRQ_TYPE_EDGE_RISING>; clocks = <&cpg CPG_MOD 36>; - clock-names = "ostm0"; power-domains = <&cpg>; status = "disabled"; }; @@ -314,7 +313,6 @@ reg = <0xe803c000 0x30>; interrupts = <GIC_SPI 57 IRQ_TYPE_EDGE_RISING>; clocks = <&cpg CPG_MOD 35>; - clock-names = "ostm1"; power-domains = <&cpg>; status = "disabled"; }; @@ -324,7 +322,6 @@ reg = <0xe803d000 0x30>; interrupts = <GIC_SPI 58 IRQ_TYPE_EDGE_RISING>; clocks = <&cpg CPG_MOD 34>; - clock-names = "ostm2"; power-domains = <&cpg>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/r8a73a4.dtsi b/arch/arm/boot/dts/r8a73a4.dtsi index a5cd31229fbd..a3ba722a9d7f 100644 --- a/arch/arm/boot/dts/r8a73a4.dtsi +++ b/arch/arm/boot/dts/r8a73a4.dtsi @@ -131,7 +131,14 @@ cmt1: timer@e6130000 { compatible = "renesas,r8a73a4-cmt1", "renesas,rcar-gen2-cmt1"; reg = <0 0xe6130000 0 0x1004>; - interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>; clocks = <&mstp3_clks R8A73A4_CLK_CMT1>; clock-names = "fck"; power-domains = <&pd_c5>; diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi index ebc1ff64f530..90feb2cf9960 100644 --- a/arch/arm/boot/dts/r8a7740.dtsi +++ b/arch/arm/boot/dts/r8a7740.dtsi @@ -479,7 +479,7 @@ cpg_clocks: cpg_clocks@e6150000 { compatible = "renesas,r8a7740-cpg-clocks"; reg = <0xe6150000 0x10000>; - clocks = <&extal1_clk>, <&extalr_clk>; + clocks = <&extal1_clk>, <&extal2_clk>, <&extalr_clk>; #clock-cells = <1>; clock-output-names = "system", "pllc0", "pllc1", "pllc2", "r", diff --git a/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts b/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts index 92aa26ba423c..b1f679da36b2 100644 --- a/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts +++ b/arch/arm/boot/dts/r8a7745-iwg22d-sodimm-dbhd-ca.dts @@ -84,8 +84,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/r8a7790-lager.dts b/arch/arm/boot/dts/r8a7790-lager.dts index 69745def44d4..bfe778c4c47b 100644 --- a/arch/arm/boot/dts/r8a7790-lager.dts +++ b/arch/arm/boot/dts/r8a7790-lager.dts @@ -364,8 +364,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/r8a7790-stout.dts b/arch/arm/boot/dts/r8a7790-stout.dts index 4138efb2766d..6a457bc9280a 100644 --- a/arch/arm/boot/dts/r8a7790-stout.dts +++ b/arch/arm/boot/dts/r8a7790-stout.dts @@ -297,8 +297,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts index 687167b70cb6..fc74c6cd6def 100644 --- a/arch/arm/boot/dts/r8a7791-koelsch.dts +++ b/arch/arm/boot/dts/r8a7791-koelsch.dts @@ -387,8 +387,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/r8a7791-porter.dts b/arch/arm/boot/dts/r8a7791-porter.dts index a8e0335148a5..114bf1c4199b 100644 --- a/arch/arm/boot/dts/r8a7791-porter.dts +++ b/arch/arm/boot/dts/r8a7791-porter.dts @@ -181,8 +181,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/r8a7792-blanche.dts b/arch/arm/boot/dts/r8a7792-blanche.dts index 248eb717eb35..9368ac2cf508 100644 --- a/arch/arm/boot/dts/r8a7792-blanche.dts +++ b/arch/arm/boot/dts/r8a7792-blanche.dts @@ -289,8 +289,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/r8a7792-wheat.dts b/arch/arm/boot/dts/r8a7792-wheat.dts index bd2a63bdab3d..ba2d2a589012 100644 --- a/arch/arm/boot/dts/r8a7792-wheat.dts +++ b/arch/arm/boot/dts/r8a7792-wheat.dts @@ -249,14 +249,12 @@ */ hdmi@3d { compatible = "adi,adv7513"; - reg = <0x3d>, <0x2d>, <0x4d>, <0x5d>; - reg-names = "main", "cec", "edid", "packet"; + reg = <0x3d>, <0x4d>, <0x2d>, <0x5d>; + reg-names = "main", "edid", "cec", "packet"; adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; @@ -280,14 +278,12 @@ hdmi@39 { compatible = "adi,adv7513"; - reg = <0x39>, <0x29>, <0x49>, <0x59>; - reg-names = "main", "cec", "edid", "packet"; + reg = <0x39>, <0x49>, <0x29>, <0x59>; + reg-names = "main", "edid", "cec", "packet"; adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/r8a7793-gose.dts b/arch/arm/boot/dts/r8a7793-gose.dts index cfe06a74ce89..79baf06019f5 100644 --- a/arch/arm/boot/dts/r8a7793-gose.dts +++ b/arch/arm/boot/dts/r8a7793-gose.dts @@ -366,8 +366,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/r8a7794-silk.dts b/arch/arm/boot/dts/r8a7794-silk.dts index 9aaa96ea9943..b8b0941f677c 100644 --- a/arch/arm/boot/dts/r8a7794-silk.dts +++ b/arch/arm/boot/dts/r8a7794-silk.dts @@ -255,8 +255,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm/boot/dts/rk3036.dtsi b/arch/arm/boot/dts/rk3036.dtsi index 781ac7583522..d9a0c9a29b68 100644 --- a/arch/arm/boot/dts/rk3036.dtsi +++ b/arch/arm/boot/dts/rk3036.dtsi @@ -128,7 +128,7 @@ assigned-clocks = <&cru SCLK_GPU>; assigned-clock-rates = <100000000>; clocks = <&cru SCLK_GPU>, <&cru SCLK_GPU>; - clock-names = "core", "bus"; + clock-names = "bus", "core"; resets = <&cru SRST_GPU>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/rk3228-evb.dts b/arch/arm/boot/dts/rk3228-evb.dts index 5670b33fd1bd..aed879db6c15 100644 --- a/arch/arm/boot/dts/rk3228-evb.dts +++ b/arch/arm/boot/dts/rk3228-evb.dts @@ -46,7 +46,7 @@ #address-cells = <1>; #size-cells = <0>; - phy: phy@0 { + phy: ethernet-phy@0 { compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22"; reg = <0>; clocks = <&cru SCLK_MAC_PHY>; diff --git a/arch/arm/boot/dts/rk3229-xms6.dts b/arch/arm/boot/dts/rk3229-xms6.dts index 679fc2b00e5a..933ef69da32a 100644 --- a/arch/arm/boot/dts/rk3229-xms6.dts +++ b/arch/arm/boot/dts/rk3229-xms6.dts @@ -150,7 +150,7 @@ #address-cells = <1>; #size-cells = <0>; - phy: phy@0 { + phy: ethernet-phy@0 { compatible = "ethernet-phy-id1234.d400", "ethernet-phy-ieee802.3-c22"; reg = <0>; diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi index 06172ebbf0ce..5485a9918da6 100644 --- a/arch/arm/boot/dts/rk322x.dtsi +++ b/arch/arm/boot/dts/rk322x.dtsi @@ -555,7 +555,7 @@ "pp1", "ppmmu1"; clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>; - clock-names = "core", "bus"; + clock-names = "bus", "core"; resets = <&cru SRST_GPU_A>; status = "disabled"; }; @@ -1020,7 +1020,7 @@ }; }; - spi-0 { + spi0 { spi0_clk: spi0-clk { rockchip,pins = <0 RK_PB1 2 &pcfg_pull_up>; }; @@ -1038,7 +1038,7 @@ }; }; - spi-1 { + spi1 { spi1_clk: spi1-clk { rockchip,pins = <0 RK_PC7 2 &pcfg_pull_up>; }; diff --git a/arch/arm/boot/dts/rk3xxx.dtsi b/arch/arm/boot/dts/rk3xxx.dtsi index f9fcb7e9657b..d929b60517ab 100644 --- a/arch/arm/boot/dts/rk3xxx.dtsi +++ b/arch/arm/boot/dts/rk3xxx.dtsi @@ -84,7 +84,7 @@ compatible = "arm,mali-400"; reg = <0x10090000 0x10000>; clocks = <&cru ACLK_GPU>, <&cru ACLK_GPU>; - clock-names = "core", "bus"; + clock-names = "bus", "core"; assigned-clocks = <&cru ACLK_GPU>; assigned-clock-rates = <100000000>; resets = <&cru SRST_GPU>; diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig index 11e2211f9007..84a3b055f253 100644 --- a/arch/arm/configs/keystone_defconfig +++ b/arch/arm/configs/keystone_defconfig @@ -147,6 +147,7 @@ CONFIG_I2C_DAVINCI=y CONFIG_SPI=y CONFIG_SPI_DAVINCI=y CONFIG_SPI_SPIDEV=y +CONFIG_PTP_1588_CLOCK=y CONFIG_PINCTRL_SINGLE=y CONFIG_GPIOLIB=y CONFIG_GPIO_SYSFS=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 3cc3ca5fa027..8b83d4a5d309 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -274,6 +274,7 @@ CONFIG_SPI_TI_QSPI=m CONFIG_HSI=m CONFIG_OMAP_SSI=m CONFIG_SSI_PROTOCOL=m +CONFIG_PTP_1588_CLOCK=y CONFIG_PINCTRL_SINGLE=y CONFIG_DEBUG_GPIO=y CONFIG_GPIO_SYSFS=y diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c index 6fdb0ac62b3d..59da6c0b63b6 100644 --- a/arch/arm/crypto/chacha-glue.c +++ b/arch/arm/crypto/chacha-glue.c @@ -91,9 +91,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, return; } - kernel_neon_begin(); - chacha_doneon(state, dst, src, bytes, nrounds); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_neon_begin(); + chacha_doneon(state, dst, src, todo, nrounds); + kernel_neon_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c index ae5aefc44a4d..ffa8d73fe722 100644 --- a/arch/arm/crypto/nhpoly1305-neon-glue.c +++ b/arch/arm/crypto/nhpoly1305-neon-glue.c @@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_neon_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c index ceec04ec2f40..13cfef4ae22e 100644 --- a/arch/arm/crypto/poly1305-glue.c +++ b/arch/arm/crypto/poly1305-glue.c @@ -160,13 +160,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE); if (static_branch_likely(&have_neon) && do_neon) { - kernel_neon_begin(); - poly1305_blocks_neon(&dctx->h, src, len, 1); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, len, SZ_4K); + + kernel_neon_begin(); + poly1305_blocks_neon(&dctx->h, src, todo, 1); + kernel_neon_end(); + + len -= todo; + src += todo; + } while (len); } else { poly1305_blocks_arm(&dctx->h, src, len, 1); + src += len; } - src += len; nbytes %= POLY1305_BLOCK_SIZE; } diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index e133da303a98..a9151884bc85 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -165,8 +165,13 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) preempt_enable(); #endif - if (!ret) - *oval = oldval; + /* + * Store unconditionally. If ret != 0 the extra store is the least + * of the worries but GCC cannot figure out that __futex_atomic_op() + * is either setting ret to -EFAULT or storing the old value in + * oldval which results in a uninitialized warning at the call site. + */ + *oval = oldval; return ret; } diff --git a/arch/arm/mach-oxnas/platsmp.c b/arch/arm/mach-oxnas/platsmp.c index ab35275b7ee3..f0a50b9e61df 100644 --- a/arch/arm/mach-oxnas/platsmp.c +++ b/arch/arm/mach-oxnas/platsmp.c @@ -27,7 +27,8 @@ static void __iomem *gic_cpu_ctrl; #define GIC_CPU_CTRL 0x00 #define GIC_CPU_CTRL_ENABLE 1 -int __init ox820_boot_secondary(unsigned int cpu, struct task_struct *idle) +static int __init ox820_boot_secondary(unsigned int cpu, + struct task_struct *idle) { /* * Write the address of secondary startup into the diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 40fb05d96c60..5d513f461957 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -20,6 +20,7 @@ config ARM64 select ARCH_HAS_KCOV select ARCH_HAS_KEEPINITRD select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PTE_DEVMAP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SETUP_DMA_OPS diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts index 316e8a443913..dc4ab6b434f9 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pinetab.dts @@ -98,7 +98,7 @@ }; &codec_analog { - hpvcc-supply = <®_eldo1>; + cpvdd-supply = <®_eldo1>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index 31143fe64d91..c26cc1fcaffd 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -154,24 +154,6 @@ }; }; - sound_spdif { - compatible = "simple-audio-card"; - simple-audio-card,name = "On-board SPDIF"; - - simple-audio-card,cpu { - sound-dai = <&spdif>; - }; - - simple-audio-card,codec { - sound-dai = <&spdif_out>; - }; - }; - - spdif_out: spdif-out { - #sound-dai-cells = <0>; - compatible = "linux,spdif-dit"; - }; - timer { compatible = "arm,armv8-timer"; allwinner,erratum-unknown1; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index 0882ea215b88..c0aef7d69117 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -2319,7 +2319,7 @@ reg = <0x0 0xff400000 0x0 0x40000>; interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clkc CLKID_USB1_DDR_BRIDGE>; - clock-names = "ddr"; + clock-names = "otg"; phys = <&usb2_phy1>; phy-names = "usb2-phy"; dr_mode = "peripheral"; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12.dtsi index 783e5a397f86..55d39020ec72 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12.dtsi @@ -1,4 +1,3 @@ - // SPDX-License-Identifier: (GPL-2.0+ OR MIT) /* * Copyright (c) 2019 BayLibre, SAS diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi index c33e85fbdaba..c6c8caed8327 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-khadas-vim3.dtsi @@ -154,6 +154,10 @@ clock-latency = <50000>; }; +&frddr_a { + status = "okay"; +}; + &frddr_b { status = "okay"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts b/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts index 325e448eb09c..06c5430eb92d 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts +++ b/arch/arm64/boot/dts/amlogic/meson-g12b-ugoos-am6.dts @@ -545,7 +545,7 @@ &usb { status = "okay"; dr_mode = "host"; - vbus-regulator = <&usb_pwr_en>; + vbus-supply = <&usb_pwr_en>; }; &usb2_phy0 { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 2a7f70b71149..13d0570c7ed6 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -447,7 +447,7 @@ edma0: dma-controller@22c0000 { #dma-cells = <2>; - compatible = "fsl,ls1028a-edma"; + compatible = "fsl,ls1028a-edma", "fsl,vf610-edma"; reg = <0x0 0x22c0000 0x0 0x10000>, <0x0 0x22d0000 0x0 0x10000>, <0x0 0x22e0000 0x0 0x10000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index cc7152ecedd9..8829628f757a 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -264,7 +264,7 @@ aips1: bus@30000000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x301f0000 0x10000>; + reg = <0x30000000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges = <0x30000000 0x30000000 0x400000>; @@ -543,7 +543,7 @@ aips2: bus@30400000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x305f0000 0x10000>; + reg = <0x30400000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges = <0x30400000 0x30400000 0x400000>; @@ -603,7 +603,7 @@ aips3: bus@30800000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x309f0000 0x10000>; + reg = <0x30800000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges = <0x30800000 0x30800000 0x400000>, @@ -863,7 +863,7 @@ aips4: bus@32c00000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x32df0000 0x10000>; + reg = <0x32c00000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges = <0x32c00000 0x32c00000 0x400000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index fa78f0163270..43971abe218b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -241,7 +241,7 @@ aips1: bus@30000000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x301f0000 0x10000>; + reg = <0x30000000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges; @@ -448,7 +448,7 @@ aips2: bus@30400000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x305f0000 0x10000>; + reg = <0x30400000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges; @@ -508,7 +508,7 @@ aips3: bus@30800000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x309f0000 0x10000>; + reg = <0x30800000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges; @@ -718,7 +718,7 @@ reg = <0x30bd0000 0x10000>; interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clk IMX8MN_CLK_SDMA1_ROOT>, - <&clk IMX8MN_CLK_SDMA1_ROOT>; + <&clk IMX8MN_CLK_AHB>; clock-names = "ipg", "ahb"; #dma-cells = <3>; fsl,sdma-ram-script-name = "imx/sdma/sdma-imx7d.bin"; @@ -754,7 +754,7 @@ aips4: bus@32c00000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x32df0000 0x10000>; + reg = <0x32c00000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mp-pinfunc.h index da78f89b6c98..319ab34cab3e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mp-pinfunc.h @@ -151,26 +151,26 @@ #define MX8MP_IOMUXC_ENET_TXC__SIM_M_HADDR22 0x070 0x2D0 0x000 0x7 0x0 #define MX8MP_IOMUXC_ENET_RX_CTL__ENET_QOS_RGMII_RX_CTL 0x074 0x2D4 0x000 0x0 0x0 #define MX8MP_IOMUXC_ENET_RX_CTL__AUDIOMIX_SAI7_TX_SYNC 0x074 0x2D4 0x540 0x2 0x0 -#define MX8MP_IOMUXC_ENET_RX_CTL__AUDIOMIX_BIT_STREAM03 0x074 0x2D4 0x4CC 0x3 0x0 +#define MX8MP_IOMUXC_ENET_RX_CTL__AUDIOMIX_BIT_STREAM03 0x074 0x2D4 0x4CC 0x3 0x1 #define MX8MP_IOMUXC_ENET_RX_CTL__GPIO1_IO24 0x074 0x2D4 0x000 0x5 0x0 #define MX8MP_IOMUXC_ENET_RX_CTL__USDHC3_DATA2 0x074 0x2D4 0x618 0x6 0x0 #define MX8MP_IOMUXC_ENET_RX_CTL__SIM_M_HADDR23 0x074 0x2D4 0x000 0x7 0x0 #define MX8MP_IOMUXC_ENET_RXC__CCM_ENET_QOS_CLOCK_GENERATE_RX_CLK 0x078 0x2D8 0x000 0x0 0x0 #define MX8MP_IOMUXC_ENET_RXC__ENET_QOS_RX_ER 0x078 0x2D8 0x000 0x1 0x0 #define MX8MP_IOMUXC_ENET_RXC__AUDIOMIX_SAI7_TX_BCLK 0x078 0x2D8 0x53C 0x2 0x0 -#define MX8MP_IOMUXC_ENET_RXC__AUDIOMIX_BIT_STREAM02 0x078 0x2D8 0x4C8 0x3 0x0 +#define MX8MP_IOMUXC_ENET_RXC__AUDIOMIX_BIT_STREAM02 0x078 0x2D8 0x4C8 0x3 0x1 #define MX8MP_IOMUXC_ENET_RXC__GPIO1_IO25 0x078 0x2D8 0x000 0x5 0x0 #define MX8MP_IOMUXC_ENET_RXC__USDHC3_DATA3 0x078 0x2D8 0x61C 0x6 0x0 #define MX8MP_IOMUXC_ENET_RXC__SIM_M_HADDR24 0x078 0x2D8 0x000 0x7 0x0 #define MX8MP_IOMUXC_ENET_RD0__ENET_QOS_RGMII_RD0 0x07C 0x2DC 0x000 0x0 0x0 #define MX8MP_IOMUXC_ENET_RD0__AUDIOMIX_SAI7_RX_DATA00 0x07C 0x2DC 0x534 0x2 0x0 -#define MX8MP_IOMUXC_ENET_RD0__AUDIOMIX_BIT_STREAM01 0x07C 0x2DC 0x4C4 0x3 0x0 +#define MX8MP_IOMUXC_ENET_RD0__AUDIOMIX_BIT_STREAM01 0x07C 0x2DC 0x4C4 0x3 0x1 #define MX8MP_IOMUXC_ENET_RD0__GPIO1_IO26 0x07C 0x2DC 0x000 0x5 0x0 #define MX8MP_IOMUXC_ENET_RD0__USDHC3_DATA4 0x07C 0x2DC 0x620 0x6 0x0 #define MX8MP_IOMUXC_ENET_RD0__SIM_M_HADDR25 0x07C 0x2DC 0x000 0x7 0x0 #define MX8MP_IOMUXC_ENET_RD1__ENET_QOS_RGMII_RD1 0x080 0x2E0 0x000 0x0 0x0 #define MX8MP_IOMUXC_ENET_RD1__AUDIOMIX_SAI7_RX_SYNC 0x080 0x2E0 0x538 0x2 0x0 -#define MX8MP_IOMUXC_ENET_RD1__AUDIOMIX_BIT_STREAM00 0x080 0x2E0 0x4C0 0x3 0x0 +#define MX8MP_IOMUXC_ENET_RD1__AUDIOMIX_BIT_STREAM00 0x080 0x2E0 0x4C0 0x3 0x1 #define MX8MP_IOMUXC_ENET_RD1__GPIO1_IO27 0x080 0x2E0 0x000 0x5 0x0 #define MX8MP_IOMUXC_ENET_RD1__USDHC3_RESET_B 0x080 0x2E0 0x000 0x6 0x0 #define MX8MP_IOMUXC_ENET_RD1__SIM_M_HADDR26 0x080 0x2E0 0x000 0x7 0x0 @@ -291,7 +291,7 @@ #define MX8MP_IOMUXC_SD2_DATA0__I2C4_SDA 0x0C8 0x328 0x5C0 0x2 0x1 #define MX8MP_IOMUXC_SD2_DATA0__UART2_DCE_RX 0x0C8 0x328 0x5F0 0x3 0x2 #define MX8MP_IOMUXC_SD2_DATA0__UART2_DTE_TX 0x0C8 0x328 0x000 0x3 0x0 -#define MX8MP_IOMUXC_SD2_DATA0__AUDIOMIX_BIT_STREAM00 0x0C8 0x328 0x4C0 0x4 0x1 +#define MX8MP_IOMUXC_SD2_DATA0__AUDIOMIX_BIT_STREAM00 0x0C8 0x328 0x4C0 0x4 0x2 #define MX8MP_IOMUXC_SD2_DATA0__GPIO2_IO15 0x0C8 0x328 0x000 0x5 0x0 #define MX8MP_IOMUXC_SD2_DATA0__CCMSRCGPCMIX_OBSERVE2 0x0C8 0x328 0x000 0x6 0x0 #define MX8MP_IOMUXC_SD2_DATA0__OBSERVE_MUX_OUT02 0x0C8 0x328 0x000 0x7 0x0 @@ -313,7 +313,7 @@ #define MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x0D4 0x334 0x000 0x0 0x0 #define MX8MP_IOMUXC_SD2_DATA3__ECSPI2_MISO 0x0D4 0x334 0x56C 0x2 0x0 #define MX8MP_IOMUXC_SD2_DATA3__AUDIOMIX_SPDIF_IN 0x0D4 0x334 0x544 0x3 0x1 -#define MX8MP_IOMUXC_SD2_DATA3__AUDIOMIX_BIT_STREAM03 0x0D4 0x334 0x4CC 0x4 0x1 +#define MX8MP_IOMUXC_SD2_DATA3__AUDIOMIX_BIT_STREAM03 0x0D4 0x334 0x4CC 0x4 0x2 #define MX8MP_IOMUXC_SD2_DATA3__GPIO2_IO18 0x0D4 0x334 0x000 0x5 0x0 #define MX8MP_IOMUXC_SD2_DATA3__CCMSRCGPCMIX_EARLY_RESET 0x0D4 0x334 0x000 0x6 0x0 #define MX8MP_IOMUXC_SD2_RESET_B__USDHC2_RESET_B 0x0D8 0x338 0x000 0x0 0x0 @@ -487,27 +487,27 @@ #define MX8MP_IOMUXC_SAI5_RXD0__AUDIOMIX_SAI1_TX_DATA02 0x134 0x394 0x000 0x1 0x0 #define MX8MP_IOMUXC_SAI5_RXD0__PWM2_OUT 0x134 0x394 0x000 0x2 0x0 #define MX8MP_IOMUXC_SAI5_RXD0__I2C5_SCL 0x134 0x394 0x5C4 0x3 0x1 -#define MX8MP_IOMUXC_SAI5_RXD0__AUDIOMIX_BIT_STREAM00 0x134 0x394 0x4C0 0x4 0x2 +#define MX8MP_IOMUXC_SAI5_RXD0__AUDIOMIX_BIT_STREAM00 0x134 0x394 0x4C0 0x4 0x3 #define MX8MP_IOMUXC_SAI5_RXD0__GPIO3_IO21 0x134 0x394 0x000 0x5 0x0 #define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_SAI5_RX_DATA01 0x138 0x398 0x4FC 0x0 0x0 #define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_SAI1_TX_DATA03 0x138 0x398 0x000 0x1 0x0 #define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_SAI1_TX_SYNC 0x138 0x398 0x4D8 0x2 0x0 #define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_SAI5_TX_SYNC 0x138 0x398 0x510 0x3 0x0 -#define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_BIT_STREAM01 0x138 0x398 0x4C4 0x4 0x2 +#define MX8MP_IOMUXC_SAI5_RXD1__AUDIOMIX_BIT_STREAM01 0x138 0x398 0x4C4 0x4 0x3 #define MX8MP_IOMUXC_SAI5_RXD1__GPIO3_IO22 0x138 0x398 0x000 0x5 0x0 #define MX8MP_IOMUXC_SAI5_RXD1__CAN1_TX 0x138 0x398 0x000 0x6 0x0 #define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_SAI5_RX_DATA02 0x13C 0x39C 0x500 0x0 0x0 #define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_SAI1_TX_DATA04 0x13C 0x39C 0x000 0x1 0x0 #define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_SAI1_TX_SYNC 0x13C 0x39C 0x4D8 0x2 0x1 #define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_SAI5_TX_BCLK 0x13C 0x39C 0x50C 0x3 0x0 -#define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_BIT_STREAM02 0x13C 0x39C 0x4C8 0x4 0x2 +#define MX8MP_IOMUXC_SAI5_RXD2__AUDIOMIX_BIT_STREAM02 0x13C 0x39C 0x4C8 0x4 0x3 #define MX8MP_IOMUXC_SAI5_RXD2__GPIO3_IO23 0x13C 0x39C 0x000 0x5 0x0 #define MX8MP_IOMUXC_SAI5_RXD2__CAN1_RX 0x13C 0x39C 0x54C 0x6 0x0 #define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_SAI5_RX_DATA03 0x140 0x3A0 0x504 0x0 0x0 #define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_SAI1_TX_DATA05 0x140 0x3A0 0x000 0x1 0x0 #define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_SAI1_TX_SYNC 0x140 0x3A0 0x4D8 0x2 0x2 #define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_SAI5_TX_DATA00 0x140 0x3A0 0x000 0x3 0x0 -#define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_BIT_STREAM03 0x140 0x3A0 0x4CC 0x4 0x2 +#define MX8MP_IOMUXC_SAI5_RXD3__AUDIOMIX_BIT_STREAM03 0x140 0x3A0 0x4CC 0x4 0x3 #define MX8MP_IOMUXC_SAI5_RXD3__GPIO3_IO24 0x140 0x3A0 0x000 0x5 0x0 #define MX8MP_IOMUXC_SAI5_RXD3__CAN2_TX 0x140 0x3A0 0x000 0x6 0x0 #define MX8MP_IOMUXC_SAI5_MCLK__AUDIOMIX_SAI5_MCLK 0x144 0x3A4 0x4F0 0x0 0x0 @@ -528,22 +528,22 @@ #define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_SAI1_RX_DATA00 0x150 0x3B0 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_SAI5_RX_DATA00 0x150 0x3B0 0x4F8 0x1 0x1 #define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_SAI1_TX_DATA01 0x150 0x3B0 0x000 0x2 0x0 -#define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_BIT_STREAM00 0x150 0x3B0 0x4C0 0x3 0x3 +#define MX8MP_IOMUXC_SAI1_RXD0__AUDIOMIX_BIT_STREAM00 0x150 0x3B0 0x4C0 0x3 0x4 #define MX8MP_IOMUXC_SAI1_RXD0__ENET1_1588_EVENT1_IN 0x150 0x3B0 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI1_RXD0__GPIO4_IO02 0x150 0x3B0 0x000 0x5 0x0 #define MX8MP_IOMUXC_SAI1_RXD1__AUDIOMIX_SAI1_RX_DATA01 0x154 0x3B4 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI1_RXD1__AUDIOMIX_SAI5_RX_DATA01 0x154 0x3B4 0x4FC 0x1 0x1 -#define MX8MP_IOMUXC_SAI1_RXD1__AUDIOMIX_BIT_STREAM01 0x154 0x3B4 0x4C4 0x3 0x3 +#define MX8MP_IOMUXC_SAI1_RXD1__AUDIOMIX_BIT_STREAM01 0x154 0x3B4 0x4C4 0x3 0x4 #define MX8MP_IOMUXC_SAI1_RXD1__ENET1_1588_EVENT1_OUT 0x154 0x3B4 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI1_RXD1__GPIO4_IO03 0x154 0x3B4 0x000 0x5 0x0 #define MX8MP_IOMUXC_SAI1_RXD2__AUDIOMIX_SAI1_RX_DATA02 0x158 0x3B8 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI1_RXD2__AUDIOMIX_SAI5_RX_DATA02 0x158 0x3B8 0x500 0x1 0x1 -#define MX8MP_IOMUXC_SAI1_RXD2__AUDIOMIX_BIT_STREAM02 0x158 0x3B8 0x4C8 0x3 0x3 +#define MX8MP_IOMUXC_SAI1_RXD2__AUDIOMIX_BIT_STREAM02 0x158 0x3B8 0x4C8 0x3 0x4 #define MX8MP_IOMUXC_SAI1_RXD2__ENET1_MDC 0x158 0x3B8 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI1_RXD2__GPIO4_IO04 0x158 0x3B8 0x000 0x5 0x0 #define MX8MP_IOMUXC_SAI1_RXD3__AUDIOMIX_SAI1_RX_DATA03 0x15C 0x3BC 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI1_RXD3__AUDIOMIX_SAI5_RX_DATA03 0x15C 0x3BC 0x504 0x1 0x1 -#define MX8MP_IOMUXC_SAI1_RXD3__AUDIOMIX_BIT_STREAM03 0x15C 0x3BC 0x4CC 0x3 0x3 +#define MX8MP_IOMUXC_SAI1_RXD3__AUDIOMIX_BIT_STREAM03 0x15C 0x3BC 0x4CC 0x3 0x4 #define MX8MP_IOMUXC_SAI1_RXD3__ENET1_MDIO 0x15C 0x3BC 0x57C 0x4 0x1 #define MX8MP_IOMUXC_SAI1_RXD3__GPIO4_IO05 0x15C 0x3BC 0x000 0x5 0x0 #define MX8MP_IOMUXC_SAI1_RXD4__AUDIOMIX_SAI1_RX_DATA04 0x160 0x3C0 0x000 0x0 0x0 @@ -624,7 +624,7 @@ #define MX8MP_IOMUXC_SAI2_RXFS__UART1_DCE_TX 0x19C 0x3FC 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI2_RXFS__UART1_DTE_RX 0x19C 0x3FC 0x5E8 0x4 0x2 #define MX8MP_IOMUXC_SAI2_RXFS__GPIO4_IO21 0x19C 0x3FC 0x000 0x5 0x0 -#define MX8MP_IOMUXC_SAI2_RXFS__AUDIOMIX_BIT_STREAM02 0x19C 0x3FC 0x4C8 0x6 0x4 +#define MX8MP_IOMUXC_SAI2_RXFS__AUDIOMIX_BIT_STREAM02 0x19C 0x3FC 0x4C8 0x6 0x5 #define MX8MP_IOMUXC_SAI2_RXFS__SIM_M_HSIZE00 0x19C 0x3FC 0x000 0x7 0x0 #define MX8MP_IOMUXC_SAI2_RXC__AUDIOMIX_SAI2_RX_BCLK 0x1A0 0x400 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI2_RXC__AUDIOMIX_SAI5_TX_BCLK 0x1A0 0x400 0x50C 0x1 0x2 @@ -632,7 +632,7 @@ #define MX8MP_IOMUXC_SAI2_RXC__UART1_DCE_RX 0x1A0 0x400 0x5E8 0x4 0x3 #define MX8MP_IOMUXC_SAI2_RXC__UART1_DTE_TX 0x1A0 0x400 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI2_RXC__GPIO4_IO22 0x1A0 0x400 0x000 0x5 0x0 -#define MX8MP_IOMUXC_SAI2_RXC__AUDIOMIX_BIT_STREAM01 0x1A0 0x400 0x4C4 0x6 0x4 +#define MX8MP_IOMUXC_SAI2_RXC__AUDIOMIX_BIT_STREAM01 0x1A0 0x400 0x4C4 0x6 0x5 #define MX8MP_IOMUXC_SAI2_RXC__SIM_M_HSIZE01 0x1A0 0x400 0x000 0x7 0x0 #define MX8MP_IOMUXC_SAI2_RXD0__AUDIOMIX_SAI2_RX_DATA00 0x1A4 0x404 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI2_RXD0__AUDIOMIX_SAI5_TX_DATA00 0x1A4 0x404 0x000 0x1 0x0 @@ -641,7 +641,7 @@ #define MX8MP_IOMUXC_SAI2_RXD0__UART1_DCE_RTS 0x1A4 0x404 0x5E4 0x4 0x2 #define MX8MP_IOMUXC_SAI2_RXD0__UART1_DTE_CTS 0x1A4 0x404 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI2_RXD0__GPIO4_IO23 0x1A4 0x404 0x000 0x5 0x0 -#define MX8MP_IOMUXC_SAI2_RXD0__AUDIOMIX_BIT_STREAM03 0x1A4 0x404 0x4CC 0x6 0x4 +#define MX8MP_IOMUXC_SAI2_RXD0__AUDIOMIX_BIT_STREAM03 0x1A4 0x404 0x4CC 0x6 0x5 #define MX8MP_IOMUXC_SAI2_RXD0__SIM_M_HSIZE02 0x1A4 0x404 0x000 0x7 0x0 #define MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_SAI2_TX_SYNC 0x1A8 0x408 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_SAI5_TX_DATA01 0x1A8 0x408 0x000 0x1 0x0 @@ -650,13 +650,13 @@ #define MX8MP_IOMUXC_SAI2_TXFS__UART1_DCE_CTS 0x1A8 0x408 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI2_TXFS__UART1_DTE_RTS 0x1A8 0x408 0x5E4 0x4 0x3 #define MX8MP_IOMUXC_SAI2_TXFS__GPIO4_IO24 0x1A8 0x408 0x000 0x5 0x0 -#define MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_BIT_STREAM02 0x1A8 0x408 0x4C8 0x6 0x5 +#define MX8MP_IOMUXC_SAI2_TXFS__AUDIOMIX_BIT_STREAM02 0x1A8 0x408 0x4C8 0x6 0x6 #define MX8MP_IOMUXC_SAI2_TXFS__SIM_M_HWRITE 0x1A8 0x408 0x000 0x7 0x0 #define MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_SAI2_TX_BCLK 0x1AC 0x40C 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_SAI5_TX_DATA02 0x1AC 0x40C 0x000 0x1 0x0 #define MX8MP_IOMUXC_SAI2_TXC__CAN1_RX 0x1AC 0x40C 0x54C 0x3 0x1 #define MX8MP_IOMUXC_SAI2_TXC__GPIO4_IO25 0x1AC 0x40C 0x000 0x5 0x0 -#define MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_BIT_STREAM01 0x1AC 0x40C 0x4C4 0x6 0x5 +#define MX8MP_IOMUXC_SAI2_TXC__AUDIOMIX_BIT_STREAM01 0x1AC 0x40C 0x4C4 0x6 0x6 #define MX8MP_IOMUXC_SAI2_TXC__SIM_M_HREADYOUT 0x1AC 0x40C 0x000 0x7 0x0 #define MX8MP_IOMUXC_SAI2_TXD0__AUDIOMIX_SAI2_TX_DATA00 0x1B0 0x410 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI2_TXD0__AUDIOMIX_SAI5_TX_DATA03 0x1B0 0x410 0x000 0x1 0x0 @@ -680,7 +680,7 @@ #define MX8MP_IOMUXC_SAI3_RXFS__AUDIOMIX_SAI3_RX_DATA01 0x1B8 0x418 0x000 0x3 0x0 #define MX8MP_IOMUXC_SAI3_RXFS__AUDIOMIX_SPDIF_IN 0x1B8 0x418 0x544 0x4 0x2 #define MX8MP_IOMUXC_SAI3_RXFS__GPIO4_IO28 0x1B8 0x418 0x000 0x5 0x0 -#define MX8MP_IOMUXC_SAI3_RXFS__AUDIOMIX_BIT_STREAM00 0x1B8 0x418 0x4C0 0x6 0x4 +#define MX8MP_IOMUXC_SAI3_RXFS__AUDIOMIX_BIT_STREAM00 0x1B8 0x418 0x4C0 0x6 0x5 #define MX8MP_IOMUXC_SAI3_RXFS__TPSMP_HTRANS00 0x1B8 0x418 0x000 0x7 0x0 #define MX8MP_IOMUXC_SAI3_RXC__AUDIOMIX_SAI3_RX_BCLK 0x1BC 0x41C 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI3_RXC__AUDIOMIX_SAI2_RX_DATA02 0x1BC 0x41C 0x000 0x1 0x0 @@ -697,7 +697,7 @@ #define MX8MP_IOMUXC_SAI3_RXD__UART2_DCE_RTS 0x1C0 0x420 0x5EC 0x4 0x3 #define MX8MP_IOMUXC_SAI3_RXD__UART2_DTE_CTS 0x1C0 0x420 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI3_RXD__GPIO4_IO30 0x1C0 0x420 0x000 0x5 0x0 -#define MX8MP_IOMUXC_SAI3_RXD__AUDIOMIX_BIT_STREAM01 0x1C0 0x420 0x4C4 0x6 0x6 +#define MX8MP_IOMUXC_SAI3_RXD__AUDIOMIX_BIT_STREAM01 0x1C0 0x420 0x4C4 0x6 0x7 #define MX8MP_IOMUXC_SAI3_RXD__TPSMP_HDATA00 0x1C0 0x420 0x000 0x7 0x0 #define MX8MP_IOMUXC_SAI3_TXFS__AUDIOMIX_SAI3_TX_SYNC 0x1C4 0x424 0x4EC 0x0 0x1 #define MX8MP_IOMUXC_SAI3_TXFS__AUDIOMIX_SAI2_TX_DATA01 0x1C4 0x424 0x000 0x1 0x0 @@ -706,7 +706,7 @@ #define MX8MP_IOMUXC_SAI3_TXFS__UART2_DCE_RX 0x1C4 0x424 0x5F0 0x4 0x4 #define MX8MP_IOMUXC_SAI3_TXFS__UART2_DTE_TX 0x1C4 0x424 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI3_TXFS__GPIO4_IO31 0x1C4 0x424 0x000 0x5 0x0 -#define MX8MP_IOMUXC_SAI3_TXFS__AUDIOMIX_BIT_STREAM03 0x1C4 0x424 0x4CC 0x6 0x5 +#define MX8MP_IOMUXC_SAI3_TXFS__AUDIOMIX_BIT_STREAM03 0x1C4 0x424 0x4CC 0x6 0x6 #define MX8MP_IOMUXC_SAI3_TXFS__TPSMP_HDATA01 0x1C4 0x424 0x000 0x7 0x0 #define MX8MP_IOMUXC_SAI3_TXC__AUDIOMIX_SAI3_TX_BCLK 0x1C8 0x428 0x4E8 0x0 0x1 #define MX8MP_IOMUXC_SAI3_TXC__AUDIOMIX_SAI2_TX_DATA02 0x1C8 0x428 0x000 0x1 0x0 @@ -715,7 +715,7 @@ #define MX8MP_IOMUXC_SAI3_TXC__UART2_DCE_TX 0x1C8 0x428 0x000 0x4 0x0 #define MX8MP_IOMUXC_SAI3_TXC__UART2_DTE_RX 0x1C8 0x428 0x5F0 0x4 0x5 #define MX8MP_IOMUXC_SAI3_TXC__GPIO5_IO00 0x1C8 0x428 0x000 0x5 0x0 -#define MX8MP_IOMUXC_SAI3_TXC__AUDIOMIX_BIT_STREAM02 0x1C8 0x428 0x4C8 0x6 0x6 +#define MX8MP_IOMUXC_SAI3_TXC__AUDIOMIX_BIT_STREAM02 0x1C8 0x428 0x4C8 0x6 0x7 #define MX8MP_IOMUXC_SAI3_TXC__TPSMP_HDATA02 0x1C8 0x428 0x000 0x7 0x0 #define MX8MP_IOMUXC_SAI3_TXD__AUDIOMIX_SAI3_TX_DATA00 0x1CC 0x42C 0x000 0x0 0x0 #define MX8MP_IOMUXC_SAI3_TXD__AUDIOMIX_SAI2_TX_DATA03 0x1CC 0x42C 0x000 0x1 0x0 diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 9b1616e59d58..9f6ba763238d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -145,7 +145,7 @@ aips1: bus@30000000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x301f0000 0x10000>; + reg = <0x30000000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges; @@ -318,7 +318,7 @@ aips2: bus@30400000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x305f0000 0x400000>; + reg = <0x30400000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges; @@ -378,7 +378,7 @@ aips3: bus@30800000 { compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x309f0000 0x400000>; + reg = <0x30800000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges; diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi index 75b384217a23..bab88369be1b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi @@ -291,7 +291,7 @@ bus@30000000 { /* AIPS1 */ compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x301f0000 0x10000>; + reg = <0x30000000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges = <0x30000000 0x30000000 0x400000>; @@ -696,7 +696,7 @@ bus@30400000 { /* AIPS2 */ compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x305f0000 0x10000>; + reg = <0x30400000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges = <0x30400000 0x30400000 0x400000>; @@ -756,7 +756,7 @@ bus@30800000 { /* AIPS3 */ compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x309f0000 0x10000>; + reg = <0x30800000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges = <0x30800000 0x30800000 0x400000>, @@ -1029,7 +1029,7 @@ bus@32c00000 { /* AIPS4 */ compatible = "fsl,aips-bus", "simple-bus"; - reg = <0x32df0000 0x10000>; + reg = <0x32c00000 0x400000>; #address-cells = <1>; #size-cells = <1>; ranges = <0x32c00000 0x32c00000 0x400000>; diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi index af87350b5547..c4abbccf2bed 100644 --- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi +++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi @@ -658,8 +658,8 @@ s11 { qcom,saw-leader; regulator-always-on; - regulator-min-microvolt = <1230000>; - regulator-max-microvolt = <1230000>; + regulator-min-microvolt = <980000>; + regulator-max-microvolt = <980000>; }; }; @@ -908,10 +908,27 @@ status = "okay"; }; +&q6asmdai { + dai@0 { + reg = <0>; + }; + + dai@1 { + reg = <1>; + }; + + dai@2 { + reg = <2>; + }; +}; + &sound { compatible = "qcom,apq8096-sndcard"; model = "DB820c"; - audio-routing = "RX_BIAS", "MCLK"; + audio-routing = "RX_BIAS", "MCLK", + "MM_DL1", "MultiMedia1 Playback", + "MM_DL2", "MultiMedia2 Playback", + "MultiMedia3 Capture", "MM_UL3"; mm1-dai-link { link-name = "MultiMedia1"; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 14827adebd94..98634d5c4440 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -2066,6 +2066,8 @@ reg = <APR_SVC_ASM>; q6asmdai: dais { compatible = "qcom,q6asm-dais"; + #address-cells = <1>; + #size-cells = <0>; #sound-dai-cells = <1>; iommus = <&lpass_q6_smmu 1>; }; diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index a2e05926b429..21fd6f8d5799 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -442,17 +442,14 @@ &q6asmdai { dai@0 { reg = <0>; - direction = <2>; }; dai@1 { reg = <1>; - direction = <2>; }; dai@2 { reg = <2>; - direction = <1>; }; dai@3 { diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index 3b617a75fafa..51a670ad15b2 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -359,12 +359,10 @@ &q6asmdai { dai@0 { reg = <0>; - direction = <2>; }; dai@1 { reg = <1>; - direction = <1>; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts index 2afb91ec9c8d..ac2156ab3e62 100644 --- a/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts +++ b/arch/arm64/boot/dts/renesas/r8a77970-eagle.dts @@ -137,8 +137,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts index d7c7b9156e08..01c4ba0f7be1 100644 --- a/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts +++ b/arch/arm64/boot/dts/renesas/r8a77970-v3msk.dts @@ -150,8 +150,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts index 3dde028e22a6..ef8350a062af 100644 --- a/arch/arm64/boot/dts/renesas/r8a77980-condor.dts +++ b/arch/arm64/boot/dts/renesas/r8a77980-condor.dts @@ -174,8 +174,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts b/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts index adbfd8f07d06..6dff04693223 100644 --- a/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts +++ b/arch/arm64/boot/dts/renesas/r8a77980-v3hsk.dts @@ -141,8 +141,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/renesas/r8a77980.dtsi b/arch/arm64/boot/dts/renesas/r8a77980.dtsi index e01b0508a18f..d672b320bc14 100644 --- a/arch/arm64/boot/dts/renesas/r8a77980.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77980.dtsi @@ -1318,6 +1318,7 @@ ipmmu_vip0: mmu@e7b00000 { compatible = "renesas,ipmmu-r8a77980"; reg = <0 0xe7b00000 0 0x1000>; + renesas,ipmmu-main = <&ipmmu_mm 4>; power-domains = <&sysc R8A77980_PD_ALWAYS_ON>; #iommu-cells = <1>; }; @@ -1325,6 +1326,7 @@ ipmmu_vip1: mmu@e7960000 { compatible = "renesas,ipmmu-r8a77980"; reg = <0 0xe7960000 0 0x1000>; + renesas,ipmmu-main = <&ipmmu_mm 11>; power-domains = <&sysc R8A77980_PD_ALWAYS_ON>; #iommu-cells = <1>; }; diff --git a/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts b/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts index 4fd2b14fbb8b..dc24cec46ae1 100644 --- a/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts +++ b/arch/arm64/boot/dts/renesas/r8a77990-ebisu.dts @@ -360,8 +360,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/renesas/r8a77995-draak.dts b/arch/arm64/boot/dts/renesas/r8a77995-draak.dts index 67634cb01d6b..79c73a99d2fe 100644 --- a/arch/arm64/boot/dts/renesas/r8a77995-draak.dts +++ b/arch/arm64/boot/dts/renesas/r8a77995-draak.dts @@ -272,8 +272,8 @@ hdmi-encoder@39 { compatible = "adi,adv7511w"; - reg = <0x39>, <0x3f>, <0x38>, <0x3c>; - reg-names = "main", "edid", "packet", "cec"; + reg = <0x39>, <0x3f>, <0x3c>, <0x38>; + reg-names = "main", "edid", "cec", "packet"; interrupt-parent = <&gpio1>; interrupts = <28 IRQ_TYPE_LEVEL_LOW>; @@ -284,8 +284,6 @@ adi,input-depth = <8>; adi,input-colorspace = "rgb"; adi,input-clock = "1x"; - adi,input-style = <1>; - adi,input-justification = "evenly"; ports { #address-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi index f809dd6d5dc3..adc9b8bf5eaa 100644 --- a/arch/arm64/boot/dts/rockchip/px30.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30.dtsi @@ -143,7 +143,7 @@ }; arm-pmu { - compatible = "arm,cortex-a53-pmu"; + compatible = "arm,cortex-a35-pmu"; interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/rockchip/rk3308.dtsi b/arch/arm64/boot/dts/rockchip/rk3308.dtsi index ac43bc3f7031..ac7f694079d0 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3308.dtsi @@ -127,7 +127,7 @@ }; arm-pmu { - compatible = "arm,cortex-a53-pmu"; + compatible = "arm,cortex-a35-pmu"; interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts index 49c4b96da3d4..ac29c2744d08 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-evb.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-evb.dts @@ -82,17 +82,16 @@ &gmac2phy { phy-supply = <&vcc_phy>; clock_in_out = "output"; - assigned-clocks = <&cru SCLK_MAC2PHY_SRC>; assigned-clock-rate = <50000000>; assigned-clocks = <&cru SCLK_MAC2PHY>; assigned-clock-parents = <&cru SCLK_MAC2PHY_SRC>; - + status = "okay"; }; &i2c1 { status = "okay"; - rk805: rk805@18 { + rk805: pmic@18 { compatible = "rockchip,rk805"; reg = <0x18>; interrupt-parent = <&gpio2>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts index bf3e546f5266..ebf3eb222e1f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts @@ -170,7 +170,7 @@ &i2c1 { status = "okay"; - rk805: rk805@18 { + rk805: pmic@18 { compatible = "rockchip,rk805"; reg = <0x18>; interrupt-parent = <&gpio2>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 7e88d88aab98..a4d591d91533 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -299,8 +299,6 @@ grf: syscon@ff100000 { compatible = "rockchip,rk3328-grf", "syscon", "simple-mfd"; reg = <0x0 0xff100000 0x0 0x1000>; - #address-cells = <1>; - #size-cells = <1>; io_domains: io-domains { compatible = "rockchip,rk3328-io-voltage-domain"; @@ -1794,10 +1792,6 @@ }; gmac2phy { - fephyled_speed100: fephyled-speed100 { - rockchip,pins = <0 RK_PD7 1 &pcfg_pull_none>; - }; - fephyled_speed10: fephyled-speed10 { rockchip,pins = <0 RK_PD6 1 &pcfg_pull_none>; }; @@ -1806,18 +1800,6 @@ rockchip,pins = <0 RK_PD6 2 &pcfg_pull_none>; }; - fephyled_rxm0: fephyled-rxm0 { - rockchip,pins = <0 RK_PD5 1 &pcfg_pull_none>; - }; - - fephyled_txm0: fephyled-txm0 { - rockchip,pins = <0 RK_PD5 2 &pcfg_pull_none>; - }; - - fephyled_linkm0: fephyled-linkm0 { - rockchip,pins = <0 RK_PD4 1 &pcfg_pull_none>; - }; - fephyled_rxm1: fephyled-rxm1 { rockchip,pins = <2 RK_PD1 2 &pcfg_pull_none>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index 5ea281b55fe2..c49982dfd8fc 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -147,7 +147,7 @@ "Speaker", "Speaker Amplifier OUTL", "Speaker", "Speaker Amplifier OUTR"; - simple-audio-card,hp-det-gpio = <&gpio0 RK_PB0 GPIO_ACTIVE_LOW>; + simple-audio-card,hp-det-gpio = <&gpio0 RK_PB0 GPIO_ACTIVE_HIGH>; simple-audio-card,aux-devs = <&speaker_amp>; simple-audio-card,pin-switches = "Speaker"; @@ -690,7 +690,8 @@ fusb0: fusb30x@22 { compatible = "fcs,fusb302"; reg = <0x22>; - fcs,int_n = <&gpio1 RK_PA2 GPIO_ACTIVE_HIGH>; + interrupt-parent = <&gpio1>; + interrupts = <RK_PA2 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; pinctrl-0 = <&fusb0_int_gpio>; vbus-supply = <&vbus_typec>; @@ -788,13 +789,13 @@ dc-charger { dc_det_gpio: dc-det-gpio { - rockchip,pins = <4 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>; + rockchip,pins = <4 RK_PD0 RK_FUNC_GPIO &pcfg_pull_up>; }; }; es8316 { hp_det_gpio: hp-det-gpio { - rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_down>; + rockchip,pins = <0 RK_PB0 RK_FUNC_GPIO &pcfg_pull_up>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 74f2c3d49095..1448f358ed0a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -403,7 +403,7 @@ reset-names = "usb3-otg"; status = "disabled"; - usbdrd_dwc3_0: dwc3 { + usbdrd_dwc3_0: usb@fe800000 { compatible = "snps,dwc3"; reg = <0x0 0xfe800000 0x0 0x100000>; interrupts = <GIC_SPI 105 IRQ_TYPE_LEVEL_HIGH 0>; @@ -439,7 +439,7 @@ reset-names = "usb3-otg"; status = "disabled"; - usbdrd_dwc3_1: dwc3 { + usbdrd_dwc3_1: usb@fe900000 { compatible = "snps,dwc3"; reg = <0x0 0xfe900000 0x0 0x100000>; interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_HIGH 0>; @@ -1124,8 +1124,6 @@ pmugrf: syscon@ff320000 { compatible = "rockchip,rk3399-pmugrf", "syscon", "simple-mfd"; reg = <0x0 0xff320000 0x0 0x1000>; - #address-cells = <1>; - #size-cells = <1>; pmu_io_domains: io-domains { compatible = "rockchip,rk3399-pmu-io-voltage-domain"; @@ -1883,10 +1881,10 @@ gpu: gpu@ff9a0000 { compatible = "rockchip,rk3399-mali", "arm,mali-t860"; reg = <0x0 0xff9a0000 0x0 0x10000>; - interrupts = <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>; - interrupt-names = "gpu", "job", "mmu"; + interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH 0>, + <GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH 0>, + <GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH 0>; + interrupt-names = "job", "mmu", "gpu"; clocks = <&cru ACLK_GPU>; #cooling-cells = <2>; power-domains = <&power RK3399_PD_GPU>; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 24e534d85045..03d0189f7d68 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -208,7 +208,7 @@ CONFIG_PCIE_QCOM=y CONFIG_PCIE_ARMADA_8K=y CONFIG_PCIE_KIRIN=y CONFIG_PCIE_HISI_STB=y -CONFIG_PCIE_TEGRA194=m +CONFIG_PCIE_TEGRA194_HOST=m CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_FW_LOADER_USER_HELPER=y @@ -567,6 +567,7 @@ CONFIG_MEDIA_DIGITAL_TV_SUPPORT=y CONFIG_MEDIA_SDR_SUPPORT=y CONFIG_MEDIA_CONTROLLER=y CONFIG_VIDEO_V4L2_SUBDEV_API=y +CONFIG_MEDIA_PLATFORM_SUPPORT=y # CONFIG_DVB_NET is not set CONFIG_MEDIA_USB_SUPPORT=y CONFIG_USB_VIDEO_CLASS=m @@ -610,8 +611,9 @@ CONFIG_DRM_MSM=m CONFIG_DRM_TEGRA=m CONFIG_DRM_PANEL_LVDS=m CONFIG_DRM_PANEL_SIMPLE=m -CONFIG_DRM_DUMB_VGA_DAC=m +CONFIG_DRM_SIMPLE_BRIDGE=m CONFIG_DRM_PANEL_TRULY_NT35597_WQXGA=m +CONFIG_DRM_DISPLAY_CONNECTOR=m CONFIG_DRM_SII902X=m CONFIG_DRM_THINE_THC63LVD1024=m CONFIG_DRM_TI_SN65DSI86=m @@ -848,7 +850,8 @@ CONFIG_QCOM_APR=m CONFIG_ARCH_R8A774A1=y CONFIG_ARCH_R8A774B1=y CONFIG_ARCH_R8A774C0=y -CONFIG_ARCH_R8A7795=y +CONFIG_ARCH_R8A77950=y +CONFIG_ARCH_R8A77951=y CONFIG_ARCH_R8A77960=y CONFIG_ARCH_R8A77961=y CONFIG_ARCH_R8A77965=y diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c index 37ca3e889848..af2bbca38e70 100644 --- a/arch/arm64/crypto/chacha-neon-glue.c +++ b/arch/arm64/crypto/chacha-neon-glue.c @@ -87,9 +87,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, !crypto_simd_usable()) return chacha_crypt_generic(state, dst, src, bytes, nrounds); - kernel_neon_begin(); - chacha_doneon(state, dst, src, bytes, nrounds); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_neon_begin(); + chacha_doneon(state, dst, src, todo, nrounds); + kernel_neon_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c index 895d3727c1fb..c5405e6a6db7 100644 --- a/arch/arm64/crypto/nhpoly1305-neon-glue.c +++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c @@ -30,7 +30,7 @@ static int nhpoly1305_neon_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_neon_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_neon); diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c index e97b092f56b8..f33ada70c4ed 100644 --- a/arch/arm64/crypto/poly1305-glue.c +++ b/arch/arm64/crypto/poly1305-glue.c @@ -143,13 +143,20 @@ void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src, unsigned int len = round_down(nbytes, POLY1305_BLOCK_SIZE); if (static_branch_likely(&have_neon) && crypto_simd_usable()) { - kernel_neon_begin(); - poly1305_blocks_neon(&dctx->h, src, len, 1); - kernel_neon_end(); + do { + unsigned int todo = min_t(unsigned int, len, SZ_4K); + + kernel_neon_begin(); + poly1305_blocks_neon(&dctx->h, src, todo, 1); + kernel_neon_end(); + + len -= todo; + src += todo; + } while (len); } else { poly1305_blocks(&dctx->h, src, len, 1); + src += len; } - src += len; nbytes %= POLY1305_BLOCK_SIZE; } diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 8e9c924423b4..a0b144cfaea7 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -177,6 +177,7 @@ void machine_kexec(struct kimage *kimage) * the offline CPUs. Therefore, we must use the __* variant here. */ __flush_icache_range((uintptr_t)reboot_code_buffer, + (uintptr_t)reboot_code_buffer + arm64_relocate_new_kernel_size); /* Flush the kimage list and its buffers. */ diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 23ebe51410f0..50a279d3ddd7 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -200,6 +200,13 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } memcpy((u32 *)regs + off, valp, KVM_REG_SIZE(reg->id)); + + if (*vcpu_cpsr(vcpu) & PSR_MODE32_BIT) { + int i; + + for (i = 0; i < 16; i++) + *vcpu_reg32(vcpu, i) = (u32)*vcpu_reg32(vcpu, i); + } out: return err; } diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index d22d0534dd60..90186cf6473e 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -18,6 +18,7 @@ #define CPU_GP_REG_OFFSET(x) (CPU_GP_REGS + x) #define CPU_XREG_OFFSET(x) CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x) +#define CPU_SP_EL0_OFFSET (CPU_XREG_OFFSET(30) + 8) .text .pushsection .hyp.text, "ax" @@ -47,6 +48,16 @@ ldp x29, lr, [\ctxt, #CPU_XREG_OFFSET(29)] .endm +.macro save_sp_el0 ctxt, tmp + mrs \tmp, sp_el0 + str \tmp, [\ctxt, #CPU_SP_EL0_OFFSET] +.endm + +.macro restore_sp_el0 ctxt, tmp + ldr \tmp, [\ctxt, #CPU_SP_EL0_OFFSET] + msr sp_el0, \tmp +.endm + /* * u64 __guest_enter(struct kvm_vcpu *vcpu, * struct kvm_cpu_context *host_ctxt); @@ -60,6 +71,9 @@ SYM_FUNC_START(__guest_enter) // Store the host regs save_callee_saved_regs x1 + // Save the host's sp_el0 + save_sp_el0 x1, x2 + // Now the host state is stored if we have a pending RAS SError it must // affect the host. If any asynchronous exception is pending we defer // the guest entry. The DSB isn't necessary before v8.2 as any SError @@ -83,6 +97,9 @@ alternative_else_nop_endif // when this feature is enabled for kernel code. ptrauth_switch_to_guest x29, x0, x1, x2 + // Restore the guest's sp_el0 + restore_sp_el0 x29, x0 + // Restore guest regs x0-x17 ldp x0, x1, [x29, #CPU_XREG_OFFSET(0)] ldp x2, x3, [x29, #CPU_XREG_OFFSET(2)] @@ -130,6 +147,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) // Store the guest regs x18-x29, lr save_callee_saved_regs x1 + // Store the guest's sp_el0 + save_sp_el0 x1, x2 + get_host_ctxt x2, x3 // Macro ptrauth_switch_to_guest format: @@ -139,6 +159,9 @@ SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) // when this feature is enabled for kernel code. ptrauth_switch_to_host x1, x2, x3, x4, x5 + // Restore the hosts's sp_el0 + restore_sp_el0 x2, x3 + // Now restore the host regs restore_callee_saved_regs x2 diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index c2a13ab3c471..9c5cfb04170e 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -198,7 +198,6 @@ SYM_CODE_END(__hyp_panic) .macro invalid_vector label, target = __hyp_panic .align 2 SYM_CODE_START(\label) -\label: b \target SYM_CODE_END(\label) .endm diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c index 75b1925763f1..6d2df9fe0b5d 100644 --- a/arch/arm64/kvm/hyp/sysreg-sr.c +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -15,8 +15,9 @@ /* * Non-VHE: Both host and guest must save everything. * - * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and pstate, - * which are handled as part of the el2 return state) on every switch. + * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and + * pstate, which are handled as part of the el2 return state) on every + * switch (sp_el0 is being dealt with in the assembly code). * tpidr_el0 and tpidrro_el0 only need to be switched when going * to host userspace or a different VCPU. EL1 registers only need to be * switched when potentially going to run a different VCPU. The latter two @@ -26,12 +27,6 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt) { ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1); - - /* - * The host arm64 Linux uses sp_el0 to point to 'current' and it must - * therefore be saved/restored on every entry/exit to/from the guest. - */ - ctxt->gp_regs.regs.sp = read_sysreg(sp_el0); } static void __hyp_text __sysreg_save_user_state(struct kvm_cpu_context *ctxt) @@ -99,12 +94,6 @@ NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) { write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1); - - /* - * The host arm64 Linux uses sp_el0 to point to 'current' and it must - * therefore be saved/restored on every entry/exit to/from the guest. - */ - write_sysreg(ctxt->gp_regs.regs.sp, sp_el0); } static void __hyp_text __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index bbeb6a5a6ba6..0be3355e3499 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -230,6 +230,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, ptep = (pte_t *)pudp; } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); + if (!pmdp) + return NULL; WARN_ON(addr & (sz - 1)); /* diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 94545d50d40f..bd31ab12f77d 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -8,6 +8,7 @@ config CSKY select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_USE_BUILTIN_BSWAP select ARCH_USE_QUEUED_RWLOCKS if NR_CPUS>2 + select ARCH_WANT_FRAME_POINTERS if !CPU_CK610 select COMMON_CLK select CLKSRC_MMIO select CSKY_MPINTC if CPU_CK860 @@ -38,6 +39,7 @@ config CSKY select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_AUDITSYSCALL select HAVE_COPY_THREAD_TLS + select HAVE_DEBUG_BUGVERBOSE select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_FUNCTION_TRACER diff --git a/arch/csky/Makefile b/arch/csky/Makefile index fb1bbbd91954..37f593a4bf53 100644 --- a/arch/csky/Makefile +++ b/arch/csky/Makefile @@ -47,7 +47,7 @@ ifeq ($(CSKYABI),abiv2) KBUILD_CFLAGS += -mno-stack-size endif -ifdef CONFIG_STACKTRACE +ifdef CONFIG_FRAME_POINTER KBUILD_CFLAGS += -mbacktrace endif diff --git a/arch/csky/abiv1/inc/abi/entry.h b/arch/csky/abiv1/inc/abi/entry.h index 5056ebb902d1..61d94ec7dd16 100644 --- a/arch/csky/abiv1/inc/abi/entry.h +++ b/arch/csky/abiv1/inc/abi/entry.h @@ -167,8 +167,8 @@ * BA Reserved C D V */ cprcr r6, cpcr30 - lsri r6, 28 - lsli r6, 28 + lsri r6, 29 + lsli r6, 29 addi r6, 0xe cpwcr r6, cpcr30 diff --git a/arch/csky/abiv2/inc/abi/entry.h b/arch/csky/abiv2/inc/abi/entry.h index a99aff555a0a..ab63c41abcca 100644 --- a/arch/csky/abiv2/inc/abi/entry.h +++ b/arch/csky/abiv2/inc/abi/entry.h @@ -285,8 +285,8 @@ */ mfcr r6, cr<30, 15> /* Get MSA0 */ 2: - lsri r6, 28 - lsli r6, 28 + lsri r6, 29 + lsli r6, 29 addi r6, 0x1ce mtcr r6, cr<30, 15> /* Set MSA0 */ diff --git a/arch/csky/abiv2/mcount.S b/arch/csky/abiv2/mcount.S index 9331c7ed5958..911512bf480f 100644 --- a/arch/csky/abiv2/mcount.S +++ b/arch/csky/abiv2/mcount.S @@ -103,6 +103,8 @@ ENTRY(_mcount) mov a0, lr subi a0, 4 ldw a1, (sp, 24) + lrw a2, function_trace_op + ldw a2, (a2, 0) jsr r26 diff --git a/arch/csky/include/asm/processor.h b/arch/csky/include/asm/processor.h index c6bcd7f7c720..24442d8e86f9 100644 --- a/arch/csky/include/asm/processor.h +++ b/arch/csky/include/asm/processor.h @@ -41,8 +41,7 @@ extern struct cpuinfo_csky cpu_data[]; #define TASK_UNMAPPED_BASE (TASK_SIZE / 3) struct thread_struct { - unsigned long ksp; /* kernel stack pointer */ - unsigned long sr; /* saved status register */ + unsigned long sp; /* kernel stack pointer */ unsigned long trap_no; /* saved status register */ /* FPU regs */ @@ -50,8 +49,7 @@ struct thread_struct { }; #define INIT_THREAD { \ - .ksp = sizeof(init_stack) + (unsigned long) &init_stack, \ - .sr = DEFAULT_PSR_VALUE, \ + .sp = sizeof(init_stack) + (unsigned long) &init_stack, \ } /* diff --git a/arch/csky/include/asm/ptrace.h b/arch/csky/include/asm/ptrace.h index aae5aa96cf54..bcfb7070e48d 100644 --- a/arch/csky/include/asm/ptrace.h +++ b/arch/csky/include/asm/ptrace.h @@ -58,6 +58,16 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) return regs->usp; } +static inline unsigned long frame_pointer(struct pt_regs *regs) +{ + return regs->regs[4]; +} +static inline void frame_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->regs[4] = val; +} + extern int regs_query_register_offset(const char *name); extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n); diff --git a/arch/csky/include/asm/thread_info.h b/arch/csky/include/asm/thread_info.h index 442fedad0260..5c61e84e790f 100644 --- a/arch/csky/include/asm/thread_info.h +++ b/arch/csky/include/asm/thread_info.h @@ -38,7 +38,13 @@ struct thread_info { #define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) #define thread_saved_fp(tsk) \ - ((unsigned long)(((struct switch_stack *)(tsk->thread.ksp))->r8)) + ((unsigned long)(((struct switch_stack *)(tsk->thread.sp))->r8)) + +#define thread_saved_sp(tsk) \ + ((unsigned long)(tsk->thread.sp)) + +#define thread_saved_lr(tsk) \ + ((unsigned long)(((struct switch_stack *)(tsk->thread.sp))->r15)) static inline struct thread_info *current_thread_info(void) { @@ -54,10 +60,10 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SIGPENDING 0 /* signal pending */ #define TIF_NOTIFY_RESUME 1 /* callback before returning to user */ #define TIF_NEED_RESCHED 2 /* rescheduling necessary */ -#define TIF_SYSCALL_TRACE 3 /* syscall trace active */ -#define TIF_SYSCALL_TRACEPOINT 4 /* syscall tracepoint instrumentation */ -#define TIF_SYSCALL_AUDIT 5 /* syscall auditing */ -#define TIF_UPROBE 6 /* uprobe breakpoint or singlestep */ +#define TIF_UPROBE 3 /* uprobe breakpoint or singlestep */ +#define TIF_SYSCALL_TRACE 4 /* syscall trace active */ +#define TIF_SYSCALL_TRACEPOINT 5 /* syscall tracepoint instrumentation */ +#define TIF_SYSCALL_AUDIT 6 /* syscall auditing */ #define TIF_POLLING_NRFLAG 16 /* poll_idle() is TIF_NEED_RESCHED */ #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_RESTORE_SIGMASK 20 /* restore signal mask in do_signal() */ diff --git a/arch/csky/include/asm/uaccess.h b/arch/csky/include/asm/uaccess.h index abefa125b93c..1633ffe5ae15 100644 --- a/arch/csky/include/asm/uaccess.h +++ b/arch/csky/include/asm/uaccess.h @@ -253,7 +253,7 @@ do { \ extern int __get_user_bad(void); -#define __copy_user(to, from, n) \ +#define ___copy_to_user(to, from, n) \ do { \ int w0, w1, w2, w3; \ asm volatile( \ @@ -288,31 +288,34 @@ do { \ " subi %0, 4 \n" \ " br 3b \n" \ "5: cmpnei %0, 0 \n" /* 1B */ \ - " bf 8f \n" \ + " bf 13f \n" \ " ldb %3, (%2, 0) \n" \ "6: stb %3, (%1, 0) \n" \ " addi %2, 1 \n" \ " addi %1, 1 \n" \ " subi %0, 1 \n" \ " br 5b \n" \ - "7: br 8f \n" \ + "7: subi %0, 4 \n" \ + "8: subi %0, 4 \n" \ + "12: subi %0, 4 \n" \ + " br 13f \n" \ ".section __ex_table, \"a\" \n" \ ".align 2 \n" \ - ".long 2b, 7b \n" \ - ".long 9b, 7b \n" \ - ".long 10b, 7b \n" \ + ".long 2b, 13f \n" \ + ".long 4b, 13f \n" \ + ".long 6b, 13f \n" \ + ".long 9b, 12b \n" \ + ".long 10b, 8b \n" \ ".long 11b, 7b \n" \ - ".long 4b, 7b \n" \ - ".long 6b, 7b \n" \ ".previous \n" \ - "8: \n" \ + "13: \n" \ : "=r"(n), "=r"(to), "=r"(from), "=r"(w0), \ "=r"(w1), "=r"(w2), "=r"(w3) \ : "0"(n), "1"(to), "2"(from) \ : "memory"); \ } while (0) -#define __copy_user_zeroing(to, from, n) \ +#define ___copy_from_user(to, from, n) \ do { \ int tmp; \ int nsave; \ @@ -355,22 +358,22 @@ do { \ " addi %1, 1 \n" \ " subi %0, 1 \n" \ " br 5b \n" \ - "8: mov %3, %0 \n" \ - " movi %4, 0 \n" \ - "9: stb %4, (%1, 0) \n" \ - " addi %1, 1 \n" \ - " subi %3, 1 \n" \ - " cmpnei %3, 0 \n" \ - " bt 9b \n" \ - " br 7f \n" \ + "8: stw %3, (%1, 0) \n" \ + " subi %0, 4 \n" \ + " bf 7f \n" \ + "9: subi %0, 8 \n" \ + " bf 7f \n" \ + "13: stw %3, (%1, 8) \n" \ + " subi %0, 12 \n" \ + " bf 7f \n" \ ".section __ex_table, \"a\" \n" \ ".align 2 \n" \ - ".long 2b, 8b \n" \ + ".long 2b, 7f \n" \ + ".long 4b, 7f \n" \ + ".long 6b, 7f \n" \ ".long 10b, 8b \n" \ - ".long 11b, 8b \n" \ - ".long 12b, 8b \n" \ - ".long 4b, 8b \n" \ - ".long 6b, 8b \n" \ + ".long 11b, 9b \n" \ + ".long 12b,13b \n" \ ".previous \n" \ "7: \n" \ : "=r"(n), "=r"(to), "=r"(from), "=r"(nsave), \ diff --git a/arch/csky/kernel/Makefile b/arch/csky/kernel/Makefile index fd6d9dc8b7f3..37f37c0e934a 100644 --- a/arch/csky/kernel/Makefile +++ b/arch/csky/kernel/Makefile @@ -3,7 +3,7 @@ extra-y := head.o vmlinux.lds obj-y += entry.o atomic.o signal.o traps.o irq.o time.o vdso.o obj-y += power.o syscall.o syscall_table.o setup.o -obj-y += process.o cpu-probe.o ptrace.o dumpstack.o +obj-y += process.o cpu-probe.o ptrace.o stacktrace.o obj-y += probes/ obj-$(CONFIG_MODULES) += module.o diff --git a/arch/csky/kernel/asm-offsets.c b/arch/csky/kernel/asm-offsets.c index f8be348df9e4..17479860d43d 100644 --- a/arch/csky/kernel/asm-offsets.c +++ b/arch/csky/kernel/asm-offsets.c @@ -18,8 +18,7 @@ int main(void) DEFINE(TASK_ACTIVE_MM, offsetof(struct task_struct, active_mm)); /* offsets into the thread struct */ - DEFINE(THREAD_KSP, offsetof(struct thread_struct, ksp)); - DEFINE(THREAD_SR, offsetof(struct thread_struct, sr)); + DEFINE(THREAD_KSP, offsetof(struct thread_struct, sp)); DEFINE(THREAD_FESR, offsetof(struct thread_struct, user_fp.fesr)); DEFINE(THREAD_FCR, offsetof(struct thread_struct, user_fp.fcr)); DEFINE(THREAD_FPREG, offsetof(struct thread_struct, user_fp.vr)); diff --git a/arch/csky/kernel/dumpstack.c b/arch/csky/kernel/dumpstack.c deleted file mode 100644 index d67f9777cfd9..000000000000 --- a/arch/csky/kernel/dumpstack.c +++ /dev/null @@ -1,49 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. - -#include <linux/ptrace.h> - -int kstack_depth_to_print = 48; - -void show_trace(unsigned long *stack) -{ - unsigned long *stack_end; - unsigned long *stack_start; - unsigned long *fp; - unsigned long addr; - - addr = (unsigned long) stack & THREAD_MASK; - stack_start = (unsigned long *) addr; - stack_end = (unsigned long *) (addr + THREAD_SIZE); - - fp = stack; - pr_info("\nCall Trace:"); - - while (fp > stack_start && fp < stack_end) { -#ifdef CONFIG_STACKTRACE - addr = fp[1]; - fp = (unsigned long *) fp[0]; -#else - addr = *fp++; -#endif - if (__kernel_text_address(addr)) - pr_cont("\n[<%08lx>] %pS", addr, (void *)addr); - } - pr_cont("\n"); -} - -void show_stack(struct task_struct *task, unsigned long *stack) -{ - if (!stack) { - if (task) - stack = (unsigned long *)thread_saved_fp(task); - else -#ifdef CONFIG_STACKTRACE - asm volatile("mov %0, r8\n":"=r"(stack)::"memory"); -#else - stack = (unsigned long *)&stack; -#endif - } - - show_trace(stack); -} diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S index 364819536f2e..3760397fdd3d 100644 --- a/arch/csky/kernel/entry.S +++ b/arch/csky/kernel/entry.S @@ -330,11 +330,6 @@ ENTRY(__switch_to) lrw a3, TASK_THREAD addu a3, a0 - mfcr a2, psr /* Save PSR value */ - stw a2, (a3, THREAD_SR) /* Save PSR in task struct */ - bclri a2, 6 /* Disable interrupts */ - mtcr a2, psr - SAVE_SWITCH_STACK stw sp, (a3, THREAD_KSP) @@ -345,12 +340,9 @@ ENTRY(__switch_to) ldw sp, (a3, THREAD_KSP) /* Set next kernel sp */ - ldw a2, (a3, THREAD_SR) /* Set next PSR */ - mtcr a2, psr - #if defined(__CSKYABIV2__) - addi r7, a1, TASK_THREAD_INFO - ldw tls, (r7, TINFO_TP_VALUE) + addi a3, a1, TASK_THREAD_INFO + ldw tls, (a3, TINFO_TP_VALUE) #endif RESTORE_SWITCH_STACK diff --git a/arch/csky/kernel/ftrace.c b/arch/csky/kernel/ftrace.c index 44628e3f7fa6..3c425b84e3be 100644 --- a/arch/csky/kernel/ftrace.c +++ b/arch/csky/kernel/ftrace.c @@ -202,6 +202,7 @@ int ftrace_disable_ftrace_graph_caller(void) #endif /* CONFIG_DYNAMIC_FTRACE */ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ +#ifdef CONFIG_DYNAMIC_FTRACE #ifndef CONFIG_CPU_HAS_ICACHE_INS struct ftrace_modify_param { int command; @@ -231,6 +232,7 @@ void arch_ftrace_update_code(int command) stop_machine(__ftrace_modify_code, ¶m, cpu_online_mask); } #endif +#endif /* CONFIG_DYNAMIC_FTRACE */ /* _mcount is defined in abi's mcount.S */ EXPORT_SYMBOL(_mcount); diff --git a/arch/csky/kernel/perf_callchain.c b/arch/csky/kernel/perf_callchain.c index e68ff375c8f8..ab55e98ee8f6 100644 --- a/arch/csky/kernel/perf_callchain.c +++ b/arch/csky/kernel/perf_callchain.c @@ -12,12 +12,17 @@ struct stackframe { static int unwind_frame_kernel(struct stackframe *frame) { - if (kstack_end((void *)frame->fp)) + unsigned long low = (unsigned long)task_stack_page(current); + unsigned long high = low + THREAD_SIZE; + + if (unlikely(frame->fp < low || frame->fp > high)) return -EPERM; - if (frame->fp & 0x3 || frame->fp < TASK_SIZE) + + if (kstack_end((void *)frame->fp) || frame->fp & 0x3) return -EPERM; *frame = *(struct stackframe *)frame->fp; + if (__kernel_text_address(frame->lr)) { int graph = 0; diff --git a/arch/csky/kernel/probes/uprobes.c b/arch/csky/kernel/probes/uprobes.c index b3a56c260e3e..1a9e0961b2b5 100644 --- a/arch/csky/kernel/probes/uprobes.c +++ b/arch/csky/kernel/probes/uprobes.c @@ -11,6 +11,11 @@ #define UPROBE_TRAP_NR UINT_MAX +bool is_swbp_insn(uprobe_opcode_t *insn) +{ + return (*insn & 0xffff) == UPROBE_SWBP_INSN; +} + unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) { return instruction_pointer(regs); diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c index f7b231ca269a..8b3fad062ab2 100644 --- a/arch/csky/kernel/process.c +++ b/arch/csky/kernel/process.c @@ -35,7 +35,7 @@ void flush_thread(void){} */ unsigned long thread_saved_pc(struct task_struct *tsk) { - struct switch_stack *sw = (struct switch_stack *)tsk->thread.ksp; + struct switch_stack *sw = (struct switch_stack *)tsk->thread.sp; return sw->r15; } @@ -56,8 +56,8 @@ int copy_thread_tls(unsigned long clone_flags, childstack = ((struct switch_stack *) childregs) - 1; memset(childstack, 0, sizeof(struct switch_stack)); - /* setup ksp for switch_to !!! */ - p->thread.ksp = (unsigned long)childstack; + /* setup thread.sp for switch_to !!! */ + p->thread.sp = (unsigned long)childstack; if (unlikely(p->flags & PF_KTHREAD)) { memset(childregs, 0, sizeof(struct pt_regs)); @@ -98,37 +98,6 @@ int dump_task_regs(struct task_struct *tsk, elf_gregset_t *pr_regs) return 1; } -unsigned long get_wchan(struct task_struct *p) -{ - unsigned long lr; - unsigned long *fp, *stack_start, *stack_end; - int count = 0; - - if (!p || p == current || p->state == TASK_RUNNING) - return 0; - - stack_start = (unsigned long *)end_of_stack(p); - stack_end = (unsigned long *)(task_stack_page(p) + THREAD_SIZE); - - fp = (unsigned long *) thread_saved_fp(p); - do { - if (fp < stack_start || fp > stack_end) - return 0; -#ifdef CONFIG_STACKTRACE - lr = fp[1]; - fp = (unsigned long *)fp[0]; -#else - lr = *fp++; -#endif - if (!in_sched_functions(lr) && - __kernel_text_address(lr)) - return lr; - } while (count++ < 16); - - return 0; -} -EXPORT_SYMBOL(get_wchan); - #ifndef CONFIG_CPU_PM_NONE void arch_cpu_idle(void) { diff --git a/arch/csky/kernel/ptrace.c b/arch/csky/kernel/ptrace.c index 21ac2608f205..5a82230bddf9 100644 --- a/arch/csky/kernel/ptrace.c +++ b/arch/csky/kernel/ptrace.c @@ -41,6 +41,9 @@ static void singlestep_disable(struct task_struct *tsk) regs = task_pt_regs(tsk); regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_RUN; + + /* Enable irq */ + regs->sr |= BIT(6); } static void singlestep_enable(struct task_struct *tsk) @@ -49,6 +52,9 @@ static void singlestep_enable(struct task_struct *tsk) regs = task_pt_regs(tsk); regs->sr = (regs->sr & TRACE_MODE_MASK) | TRACE_MODE_SI; + + /* Disable irq */ + regs->sr &= ~BIT(6); } /* diff --git a/arch/csky/kernel/stacktrace.c b/arch/csky/kernel/stacktrace.c index fec777a643f1..92809e1da723 100644 --- a/arch/csky/kernel/stacktrace.c +++ b/arch/csky/kernel/stacktrace.c @@ -1,57 +1,159 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd. */ #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> #include <linux/ftrace.h> +#include <linux/ptrace.h> -void save_stack_trace(struct stack_trace *trace) +#ifdef CONFIG_FRAME_POINTER + +struct stackframe { + unsigned long fp; + unsigned long ra; +}; + +void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, + bool (*fn)(unsigned long, void *), void *arg) { - save_stack_trace_tsk(current, trace); + unsigned long fp, sp, pc; + + if (regs) { + fp = frame_pointer(regs); + sp = user_stack_pointer(regs); + pc = instruction_pointer(regs); + } else if (task == NULL || task == current) { + const register unsigned long current_sp __asm__ ("sp"); + const register unsigned long current_fp __asm__ ("r8"); + fp = current_fp; + sp = current_sp; + pc = (unsigned long)walk_stackframe; + } else { + /* task blocked in __switch_to */ + fp = thread_saved_fp(task); + sp = thread_saved_sp(task); + pc = thread_saved_lr(task); + } + + for (;;) { + unsigned long low, high; + struct stackframe *frame; + + if (unlikely(!__kernel_text_address(pc) || fn(pc, arg))) + break; + + /* Validate frame pointer */ + low = sp; + high = ALIGN(sp, THREAD_SIZE); + if (unlikely(fp < low || fp > high || fp & 0x3)) + break; + /* Unwind stack frame */ + frame = (struct stackframe *)fp; + sp = fp; + fp = frame->fp; + pc = ftrace_graph_ret_addr(current, NULL, frame->ra, + (unsigned long *)(fp - 8)); + } } -EXPORT_SYMBOL_GPL(save_stack_trace); -void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +#else /* !CONFIG_FRAME_POINTER */ + +static void notrace walk_stackframe(struct task_struct *task, + struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) { - unsigned long *fp, *stack_start, *stack_end; - unsigned long addr; - int skip = trace->skip; - int savesched; - int graph_idx = 0; + unsigned long sp, pc; + unsigned long *ksp; - if (tsk == current) { - asm volatile("mov %0, r8\n":"=r"(fp)); - savesched = 1; + if (regs) { + sp = user_stack_pointer(regs); + pc = instruction_pointer(regs); + } else if (task == NULL || task == current) { + const register unsigned long current_sp __asm__ ("sp"); + sp = current_sp; + pc = (unsigned long)walk_stackframe; } else { - fp = (unsigned long *)thread_saved_fp(tsk); - savesched = 0; + /* task blocked in __switch_to */ + sp = thread_saved_sp(task); + pc = thread_saved_lr(task); } - addr = (unsigned long) fp & THREAD_MASK; - stack_start = (unsigned long *) addr; - stack_end = (unsigned long *) (addr + THREAD_SIZE); - - while (fp > stack_start && fp < stack_end) { - unsigned long lpp, fpp; + if (unlikely(sp & 0x3)) + return; - fpp = fp[0]; - lpp = fp[1]; - if (!__kernel_text_address(lpp)) + ksp = (unsigned long *)sp; + while (!kstack_end(ksp)) { + if (__kernel_text_address(pc) && unlikely(fn(pc, arg))) break; - else - lpp = ftrace_graph_ret_addr(tsk, &graph_idx, lpp, NULL); - - if (savesched || !in_sched_functions(lpp)) { - if (skip) { - skip--; - } else { - trace->entries[trace->nr_entries++] = lpp; - if (trace->nr_entries >= trace->max_entries) - break; - } - } - fp = (unsigned long *)fpp; + pc = (*ksp++) - 0x4; } } +#endif /* CONFIG_FRAME_POINTER */ + +static bool print_trace_address(unsigned long pc, void *arg) +{ + print_ip_sym(pc); + return false; +} + +void show_stack(struct task_struct *task, unsigned long *sp) +{ + pr_cont("Call Trace:\n"); + walk_stackframe(task, NULL, print_trace_address, NULL); +} + +static bool save_wchan(unsigned long pc, void *arg) +{ + if (!in_sched_functions(pc)) { + unsigned long *p = arg; + *p = pc; + return true; + } + return false; +} + +unsigned long get_wchan(struct task_struct *task) +{ + unsigned long pc = 0; + + if (likely(task && task != current && task->state != TASK_RUNNING)) + walk_stackframe(task, NULL, save_wchan, &pc); + return pc; +} + +#ifdef CONFIG_STACKTRACE +static bool __save_trace(unsigned long pc, void *arg, bool nosched) +{ + struct stack_trace *trace = arg; + + if (unlikely(nosched && in_sched_functions(pc))) + return false; + if (unlikely(trace->skip > 0)) { + trace->skip--; + return false; + } + + trace->entries[trace->nr_entries++] = pc; + return (trace->nr_entries >= trace->max_entries); +} + +static bool save_trace(unsigned long pc, void *arg) +{ + return __save_trace(pc, arg, false); +} + +/* + * Save stack-backtrace addresses into a stack_trace buffer. + */ +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + walk_stackframe(tsk, NULL, save_trace, trace); +} EXPORT_SYMBOL_GPL(save_stack_trace_tsk); + +void save_stack_trace(struct stack_trace *trace) +{ + save_stack_trace_tsk(NULL, trace); +} +EXPORT_SYMBOL_GPL(save_stack_trace); + +#endif /* CONFIG_STACKTRACE */ diff --git a/arch/csky/lib/usercopy.c b/arch/csky/lib/usercopy.c index 647a23986fb5..3c9bd645e643 100644 --- a/arch/csky/lib/usercopy.c +++ b/arch/csky/lib/usercopy.c @@ -7,10 +7,7 @@ unsigned long raw_copy_from_user(void *to, const void *from, unsigned long n) { - if (access_ok(from, n)) - __copy_user_zeroing(to, from, n); - else - memset(to, 0, n); + ___copy_from_user(to, from, n); return n; } EXPORT_SYMBOL(raw_copy_from_user); @@ -18,8 +15,7 @@ EXPORT_SYMBOL(raw_copy_from_user); unsigned long raw_copy_to_user(void *to, const void *from, unsigned long n) { - if (access_ok(to, n)) - __copy_user(to, from, n); + ___copy_to_user(to, from, n); return n; } EXPORT_SYMBOL(raw_copy_to_user); diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h index 3c0ba22dc360..db0a1c281587 100644 --- a/arch/powerpc/include/asm/book3s/32/kup.h +++ b/arch/powerpc/include/asm/book3s/32/kup.h @@ -75,7 +75,7 @@ .macro kuap_check current, gpr #ifdef CONFIG_PPC_KUAP_DEBUG - lwz \gpr2, KUAP(thread) + lwz \gpr, KUAP(thread) 999: twnei \gpr, 0 EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE) #endif diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index e0e71777961f..3a0db7b0b46e 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -250,9 +250,27 @@ static inline bool arch_irqs_disabled(void) } \ } while(0) +static inline bool __lazy_irq_pending(u8 irq_happened) +{ + return !!(irq_happened & ~PACA_IRQ_HARD_DIS); +} + +/* + * Check if a lazy IRQ is pending. Should be called with IRQs hard disabled. + */ static inline bool lazy_irq_pending(void) { - return !!(get_paca()->irq_happened & ~PACA_IRQ_HARD_DIS); + return __lazy_irq_pending(get_paca()->irq_happened); +} + +/* + * Check if a lazy IRQ is pending, with no debugging checks. + * Should be called with IRQs hard disabled. + * For use in RI disabled code or other constrained situations. + */ +static inline bool lazy_irq_pending_nocheck(void) +{ + return __lazy_irq_pending(local_paca->irq_happened); } /* diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 2f500debae21..0969285996cb 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -166,13 +166,17 @@ do { \ ({ \ long __pu_err; \ __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ + __typeof__(*(ptr)) __pu_val = (x); \ + __typeof__(size) __pu_size = (size); \ + \ if (!is_kernel_addr((unsigned long)__pu_addr)) \ might_fault(); \ - __chk_user_ptr(ptr); \ + __chk_user_ptr(__pu_addr); \ if (do_allow) \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ + __put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \ else \ - __put_user_size_allowed((x), __pu_addr, (size), __pu_err); \ + __put_user_size_allowed(__pu_val, __pu_addr, __pu_size, __pu_err); \ + \ __pu_err; \ }) @@ -180,9 +184,13 @@ do { \ ({ \ long __pu_err = -EFAULT; \ __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ + __typeof__(*(ptr)) __pu_val = (x); \ + __typeof__(size) __pu_size = (size); \ + \ might_fault(); \ - if (access_ok(__pu_addr, size)) \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ + if (access_ok(__pu_addr, __pu_size)) \ + __put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \ + \ __pu_err; \ }) @@ -190,8 +198,12 @@ do { \ ({ \ long __pu_err; \ __typeof__(*(ptr)) __user *__pu_addr = (ptr); \ - __chk_user_ptr(ptr); \ - __put_user_size((x), __pu_addr, (size), __pu_err); \ + __typeof__(*(ptr)) __pu_val = (x); \ + __typeof__(size) __pu_size = (size); \ + \ + __chk_user_ptr(__pu_addr); \ + __put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \ + \ __pu_err; \ }) @@ -283,15 +295,18 @@ do { \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ - __chk_user_ptr(ptr); \ + __typeof__(size) __gu_size = (size); \ + \ + __chk_user_ptr(__gu_addr); \ if (!is_kernel_addr((unsigned long)__gu_addr)) \ might_fault(); \ barrier_nospec(); \ if (do_allow) \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + __get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \ else \ - __get_user_size_allowed(__gu_val, __gu_addr, (size), __gu_err); \ + __get_user_size_allowed(__gu_val, __gu_addr, __gu_size, __gu_err); \ (x) = (__typeof__(*(ptr)))__gu_val; \ + \ __gu_err; \ }) @@ -300,12 +315,15 @@ do { \ long __gu_err = -EFAULT; \ __long_type(*(ptr)) __gu_val = 0; \ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ + __typeof__(size) __gu_size = (size); \ + \ might_fault(); \ - if (access_ok(__gu_addr, (size))) { \ + if (access_ok(__gu_addr, __gu_size)) { \ barrier_nospec(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + __get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \ } \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ + \ __gu_err; \ }) @@ -314,10 +332,13 @@ do { \ long __gu_err; \ __long_type(*(ptr)) __gu_val; \ __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ - __chk_user_ptr(ptr); \ + __typeof__(size) __gu_size = (size); \ + \ + __chk_user_ptr(__gu_addr); \ barrier_nospec(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ + __get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ + \ __gu_err; \ }) diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 9a1e5d636dea..b3c9f15089b6 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -472,15 +472,17 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S) #ifdef CONFIG_PPC_BOOK3S /* * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not - * touched, AMR not set, no exit work created, then this can be used. + * touched, no exit work created, then this can be used. */ .balign IFETCH_ALIGN_BYTES .globl fast_interrupt_return fast_interrupt_return: _ASM_NOKPROBE_SYMBOL(fast_interrupt_return) + kuap_check_amr r3, r4 ld r4,_MSR(r1) andi. r0,r4,MSR_PR bne .Lfast_user_interrupt_return + kuap_restore_amr r3 andi. r0,r4,MSR_RI li r3,0 /* 0 return value, no EMULATE_STACK_STORE */ bne+ .Lfast_kernel_interrupt_return diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 728ccb0f560c..b0ad930cbae5 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -971,6 +971,7 @@ EXC_COMMON_BEGIN(system_reset_common) ld r10,SOFTE(r1) stb r10,PACAIRQSOFTMASK(r13) + kuap_restore_amr r10 EXCEPTION_RESTORE_REGS RFI_TO_USER_OR_KERNEL diff --git a/arch/powerpc/kernel/head_40x.S b/arch/powerpc/kernel/head_40x.S index 9bb663977e84..2cec543c38f0 100644 --- a/arch/powerpc/kernel/head_40x.S +++ b/arch/powerpc/kernel/head_40x.S @@ -344,8 +344,9 @@ _ENTRY(saved_ksp_limit) /* 0x0C00 - System Call Exception */ START_EXCEPTION(0x0C00, SystemCall) SYSCALL_ENTRY 0xc00 +/* Trap_0D is commented out to get more space for system call exception */ - EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_STD) +/* EXCEPTION(0x0D00, Trap_0D, unknown_exception, EXC_XFER_STD) */ EXCEPTION(0x0E00, Trap_0E, unknown_exception, EXC_XFER_STD) EXCEPTION(0x0F00, Trap_0F, unknown_exception, EXC_XFER_STD) diff --git a/arch/powerpc/kernel/ima_arch.c b/arch/powerpc/kernel/ima_arch.c index e34116255ced..957abd592075 100644 --- a/arch/powerpc/kernel/ima_arch.c +++ b/arch/powerpc/kernel/ima_arch.c @@ -19,12 +19,12 @@ bool arch_ima_get_secureboot(void) * to be stored as an xattr or as an appended signature. * * To avoid duplicate signature verification as much as possible, the IMA - * policy rule for module appraisal is added only if CONFIG_MODULE_SIG_FORCE + * policy rule for module appraisal is added only if CONFIG_MODULE_SIG * is not enabled. */ static const char *const secure_rules[] = { "appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", -#ifndef CONFIG_MODULE_SIG_FORCE +#ifndef CONFIG_MODULE_SIG "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", #endif NULL @@ -50,7 +50,7 @@ static const char *const secure_and_trusted_rules[] = { "measure func=KEXEC_KERNEL_CHECK template=ima-modsig", "measure func=MODULE_CHECK template=ima-modsig", "appraise func=KEXEC_KERNEL_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", -#ifndef CONFIG_MODULE_SIG_FORCE +#ifndef CONFIG_MODULE_SIG "appraise func=MODULE_CHECK appraise_flag=check_blacklist appraise_type=imasig|modsig", #endif NULL diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c index c74295a7765b..7b7c89cad901 100644 --- a/arch/powerpc/kernel/syscall_64.c +++ b/arch/powerpc/kernel/syscall_64.c @@ -35,6 +35,8 @@ notrace long system_call_exception(long r3, long r4, long r5, BUG_ON(!FULL_REGS(regs)); BUG_ON(regs->softe != IRQS_ENABLED); + kuap_check_amr(); + account_cpu_user_entry(); #ifdef CONFIG_PPC_SPLPAR @@ -47,8 +49,6 @@ notrace long system_call_exception(long r3, long r4, long r5, } #endif - kuap_check_amr(); - /* * This is not required for the syscall exit path, but makes the * stack frame look nicer. If this was initialised in the first stack @@ -117,6 +117,8 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3, unsigned long ti_flags; unsigned long ret = 0; + kuap_check_amr(); + regs->result = r3; /* Check whether the syscall is issued inside a restartable sequence */ @@ -189,7 +191,7 @@ again: /* This pattern matches prep_irq_for_idle */ __hard_EE_RI_disable(); - if (unlikely(lazy_irq_pending())) { + if (unlikely(lazy_irq_pending_nocheck())) { __hard_RI_enable(); trace_hardirqs_off(); local_paca->irq_happened |= PACA_IRQ_HARD_DIS; @@ -204,8 +206,6 @@ again: local_paca->tm_scratch = regs->msr; #endif - kuap_check_amr(); - account_cpu_user_exit(); return ret; @@ -228,6 +228,8 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned BUG_ON(!FULL_REGS(regs)); BUG_ON(regs->softe != IRQS_ENABLED); + kuap_check_amr(); + local_irq_save(flags); again: @@ -264,7 +266,7 @@ again: trace_hardirqs_on(); __hard_EE_RI_disable(); - if (unlikely(lazy_irq_pending())) { + if (unlikely(lazy_irq_pending_nocheck())) { __hard_RI_enable(); trace_hardirqs_off(); local_paca->irq_happened |= PACA_IRQ_HARD_DIS; @@ -292,8 +294,6 @@ again: local_paca->tm_scratch = regs->msr; #endif - kuap_check_amr(); - account_cpu_user_exit(); return ret; @@ -313,6 +313,8 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign BUG_ON(regs->msr & MSR_PR); BUG_ON(!FULL_REGS(regs)); + kuap_check_amr(); + if (unlikely(*ti_flagsp & _TIF_EMULATE_STACK_STORE)) { clear_bits(_TIF_EMULATE_STACK_STORE, ti_flagsp); ret = 1; @@ -334,7 +336,7 @@ again: trace_hardirqs_on(); __hard_EE_RI_disable(); - if (unlikely(lazy_irq_pending())) { + if (unlikely(lazy_irq_pending_nocheck())) { __hard_RI_enable(); irq_soft_mask_set(IRQS_ALL_DISABLED); trace_hardirqs_off(); diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S index a3951567118a..e7f8f9f1b3f4 100644 --- a/arch/powerpc/kernel/vdso32/gettimeofday.S +++ b/arch/powerpc/kernel/vdso32/gettimeofday.S @@ -218,11 +218,11 @@ V_FUNCTION_BEGIN(__kernel_clock_getres) blr /* - * invalid clock + * syscall fallback */ 99: - li r3, EINVAL - crset so + li r0,__NR_clock_getres + sc blr .cfi_endproc V_FUNCTION_END(__kernel_clock_getres) diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index e15166b0a16d..ad2f172c26a6 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -521,6 +521,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_PPC_GUEST_DEBUG_SSTEP: diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 74f82cf4f781..a31e1a41913a 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -54,7 +54,7 @@ config RISCV select GENERIC_ARCH_TOPOLOGY if SMP select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_MMIOWB - select ARCH_HAS_DEBUG_VIRTUAL + select ARCH_HAS_DEBUG_VIRTUAL if MMU select HAVE_EBPF_JIT if MMU select EDAC_SUPPORT select ARCH_HAS_GIGANTIC_PAGE @@ -136,6 +136,7 @@ config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y config SYS_SUPPORTS_HUGETLBFS + depends on MMU def_bool y config STACKTRACE_SUPPORT diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 216286db81c9..d646332e44f1 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -11,14 +11,15 @@ config SOC_SIFIVE This enables support for SiFive SoC platform hardware. config SOC_VIRT - bool "QEMU Virt Machine" - select POWER_RESET_SYSCON - select POWER_RESET_SYSCON_POWEROFF - select GOLDFISH - select RTC_DRV_GOLDFISH - select SIFIVE_PLIC - help - This enables support for QEMU Virt Machine. + bool "QEMU Virt Machine" + select POWER_RESET + select POWER_RESET_SYSCON + select POWER_RESET_SYSCON_POWEROFF + select GOLDFISH + select RTC_DRV_GOLDFISH if RTC_CLASS + select SIFIVE_PLIC + help + This enables support for QEMU Virt Machine. config SOC_KENDRYTE bool "Kendryte K210 SoC" diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h index 8e18d2c64399..cec462e198ce 100644 --- a/arch/riscv/include/asm/csr.h +++ b/arch/riscv/include/asm/csr.h @@ -51,13 +51,10 @@ #define CAUSE_IRQ_FLAG (_AC(1, UL) << (__riscv_xlen - 1)) /* Interrupt causes (minus the high bit) */ -#define IRQ_U_SOFT 0 #define IRQ_S_SOFT 1 #define IRQ_M_SOFT 3 -#define IRQ_U_TIMER 4 #define IRQ_S_TIMER 5 #define IRQ_M_TIMER 7 -#define IRQ_U_EXT 8 #define IRQ_S_EXT 9 #define IRQ_M_EXT 11 diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 1bb0cd04aec3..5ce50468aff1 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -8,6 +8,7 @@ #ifndef _ASM_RISCV_HWCAP_H #define _ASM_RISCV_HWCAP_H +#include <linux/bits.h> #include <uapi/asm/hwcap.h> #ifndef __ASSEMBLY__ @@ -22,6 +23,27 @@ enum { }; extern unsigned long elf_hwcap; + +#define RISCV_ISA_EXT_a ('a' - 'a') +#define RISCV_ISA_EXT_c ('c' - 'a') +#define RISCV_ISA_EXT_d ('d' - 'a') +#define RISCV_ISA_EXT_f ('f' - 'a') +#define RISCV_ISA_EXT_h ('h' - 'a') +#define RISCV_ISA_EXT_i ('i' - 'a') +#define RISCV_ISA_EXT_m ('m' - 'a') +#define RISCV_ISA_EXT_s ('s' - 'a') +#define RISCV_ISA_EXT_u ('u' - 'a') + +#define RISCV_ISA_EXT_MAX 64 + +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); + +#define riscv_isa_extension_mask(ext) BIT_MASK(RISCV_ISA_EXT_##ext) + +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit); +#define riscv_isa_extension_available(isa_bitmap, ext) \ + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext) + #endif #endif /* _ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h index a2c809df2733..56053c9838b2 100644 --- a/arch/riscv/include/asm/mmio.h +++ b/arch/riscv/include/asm/mmio.h @@ -16,6 +16,8 @@ #ifndef CONFIG_MMU #define pgprot_noncached(x) (x) +#define pgprot_writecombine(x) (x) +#define pgprot_device(x) (x) #endif /* CONFIG_MMU */ /* Generic IO read/write. These perform native-endian accesses. */ diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h index bb4091ff4a21..0b2333e71fdc 100644 --- a/arch/riscv/include/asm/mmiowb.h +++ b/arch/riscv/include/asm/mmiowb.h @@ -9,6 +9,7 @@ */ #define mmiowb() __asm__ __volatile__ ("fence o,w" : : : "memory"); +#include <linux/smp.h> #include <asm-generic/mmiowb.h> #endif /* _ASM_RISCV_MMIOWB_H */ diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h index 0234048b12bc..062efd3a1d5d 100644 --- a/arch/riscv/include/asm/perf_event.h +++ b/arch/riscv/include/asm/perf_event.h @@ -12,19 +12,14 @@ #include <linux/ptrace.h> #include <linux/interrupt.h> +#ifdef CONFIG_RISCV_BASE_PMU #define RISCV_BASE_COUNTERS 2 /* * The RISCV_MAX_COUNTERS parameter should be specified. */ -#ifdef CONFIG_RISCV_BASE_PMU #define RISCV_MAX_COUNTERS 2 -#endif - -#ifndef RISCV_MAX_COUNTERS -#error "Please provide a valid RISCV_MAX_COUNTERS for the PMU." -#endif /* * These are the indexes of bits in counteren register *minus* 1, @@ -82,6 +77,7 @@ struct riscv_pmu { int irq; }; +#endif #ifdef CONFIG_PERF_EVENTS #define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs #endif diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 9c188ad2e52d..35b60035b6b0 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -470,12 +470,15 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, #else /* CONFIG_MMU */ +#define PAGE_SHARED __pgprot(0) #define PAGE_KERNEL __pgprot(0) #define swapper_pg_dir NULL #define VMALLOC_START 0 #define TASK_SIZE 0xffffffffUL +static inline void __kernel_map_pages(struct page *page, int numpages, int enable) {} + #endif /* !CONFIG_MMU */ #define kern_addr_valid(addr) (1) /* FIXME */ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index c38df4771c09..4c5bae7ca01c 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -22,14 +22,6 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif -#ifdef CONFIG_STRICT_KERNEL_RWX -void set_kernel_text_ro(void); -void set_kernel_text_rw(void); -#else -static inline void set_kernel_text_ro(void) { } -static inline void set_kernel_text_rw(void) { } -#endif - int set_direct_map_invalid_noflush(struct page *page); int set_direct_map_default_noflush(struct page *page); diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 86c83081044f..d8bbd3207100 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -43,7 +43,7 @@ obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o -obj-$(CONFIG_PERF_EVENTS) += perf_event.o +obj-$(CONFIG_RISCV_BASE_PMU) += perf_event.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o obj-$(CONFIG_RISCV_SBI) += sbi.o diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c index c4c33bf02369..0ec22354018c 100644 --- a/arch/riscv/kernel/cpu_ops.c +++ b/arch/riscv/kernel/cpu_ops.c @@ -15,8 +15,8 @@ const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init; -void *__cpu_up_stack_pointer[NR_CPUS]; -void *__cpu_up_task_pointer[NR_CPUS]; +void *__cpu_up_stack_pointer[NR_CPUS] __section(.data); +void *__cpu_up_task_pointer[NR_CPUS] __section(.data); extern const struct cpu_operations cpu_ops_sbi; extern const struct cpu_operations cpu_ops_spinwait; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index a5ad00043104..ac202f44a670 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -6,6 +6,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/bitmap.h> #include <linux/of.h> #include <asm/processor.h> #include <asm/hwcap.h> @@ -13,15 +14,57 @@ #include <asm/switch_to.h> unsigned long elf_hwcap __read_mostly; + +/* Host ISA bitmap */ +static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; + #ifdef CONFIG_FPU bool has_fpu __read_mostly; #endif +/** + * riscv_isa_extension_base() - Get base extension word + * + * @isa_bitmap: ISA bitmap to use + * Return: base extension word as unsigned long value + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap) +{ + if (!isa_bitmap) + return riscv_isa[0]; + return isa_bitmap[0]; +} +EXPORT_SYMBOL_GPL(riscv_isa_extension_base); + +/** + * __riscv_isa_extension_available() - Check whether given extension + * is available or not + * + * @isa_bitmap: ISA bitmap to use + * @bit: bit position of the desired extension + * Return: true or false + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit) +{ + const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa; + + if (bit >= RISCV_ISA_EXT_MAX) + return false; + + return test_bit(bit, bmap) ? true : false; +} +EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); + void riscv_fill_hwcap(void) { struct device_node *node; const char *isa; - size_t i; + char print_str[BITS_PER_LONG + 1]; + size_t i, j, isa_len; static unsigned long isa2hwcap[256] = {0}; isa2hwcap['i'] = isa2hwcap['I'] = COMPAT_HWCAP_ISA_I; @@ -33,8 +76,11 @@ void riscv_fill_hwcap(void) elf_hwcap = 0; + bitmap_zero(riscv_isa, RISCV_ISA_EXT_MAX); + for_each_of_cpu_node(node) { unsigned long this_hwcap = 0; + unsigned long this_isa = 0; if (riscv_of_processor_hartid(node) < 0) continue; @@ -44,8 +90,24 @@ void riscv_fill_hwcap(void) continue; } - for (i = 0; i < strlen(isa); ++i) + i = 0; + isa_len = strlen(isa); +#if IS_ENABLED(CONFIG_32BIT) + if (!strncmp(isa, "rv32", 4)) + i += 4; +#elif IS_ENABLED(CONFIG_64BIT) + if (!strncmp(isa, "rv64", 4)) + i += 4; +#endif + for (; i < isa_len; ++i) { this_hwcap |= isa2hwcap[(unsigned char)(isa[i])]; + /* + * TODO: X, Y and Z extension parsing for Host ISA + * bitmap will be added in-future. + */ + if ('a' <= isa[i] && isa[i] < 'x') + this_isa |= (1UL << (isa[i] - 'a')); + } /* * All "okay" hart should have same isa. Set HWCAP based on @@ -56,6 +118,11 @@ void riscv_fill_hwcap(void) elf_hwcap &= this_hwcap; else elf_hwcap = this_hwcap; + + if (riscv_isa[0]) + riscv_isa[0] &= this_isa; + else + riscv_isa[0] = this_isa; } /* We don't support systems with F but without D, so mask those out @@ -65,7 +132,17 @@ void riscv_fill_hwcap(void) elf_hwcap &= ~COMPAT_HWCAP_ISA_F; } - pr_info("elf_hwcap is 0x%lx\n", elf_hwcap); + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < BITS_PER_LONG; i++) + if (riscv_isa[0] & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ISA extensions %s\n", print_str); + + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < BITS_PER_LONG; i++) + if (elf_hwcap & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ELF capabilities %s\n", print_str); #ifdef CONFIG_FPU if (elf_hwcap & (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D)) diff --git a/arch/riscv/kernel/perf_event.c b/arch/riscv/kernel/perf_event.c index 91626d9ae5f2..c835f0362d94 100644 --- a/arch/riscv/kernel/perf_event.c +++ b/arch/riscv/kernel/perf_event.c @@ -147,7 +147,7 @@ static int riscv_map_hw_event(u64 config) return riscv_pmu->hw_events[config]; } -int riscv_map_cache_decode(u64 config, unsigned int *type, +static int riscv_map_cache_decode(u64 config, unsigned int *type, unsigned int *op, unsigned int *result) { return -ENOENT; @@ -342,7 +342,7 @@ static void riscv_pmu_del(struct perf_event *event, int flags) static DEFINE_MUTEX(pmc_reserve_mutex); -irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev) +static irqreturn_t riscv_base_pmu_handle_irq(int irq_num, void *dev) { return IRQ_NONE; } @@ -361,7 +361,7 @@ static int reserve_pmc_hardware(void) return err; } -void release_pmc_hardware(void) +static void release_pmc_hardware(void) { mutex_lock(&pmc_reserve_mutex); if (riscv_pmu->irq >= 0) @@ -464,7 +464,7 @@ static const struct of_device_id riscv_pmu_of_ids[] = { { /* sentinel value */ } }; -int __init init_hw_perf_events(void) +static int __init init_hw_perf_events(void) { struct device_node *node = of_find_node_by_type(NULL, "pmu"); const struct of_device_id *of_id; diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c index e0a6293093f1..a65a8fa0c22d 100644 --- a/arch/riscv/kernel/smp.c +++ b/arch/riscv/kernel/smp.c @@ -10,6 +10,7 @@ #include <linux/cpu.h> #include <linux/interrupt.h> +#include <linux/module.h> #include <linux/profile.h> #include <linux/smp.h> #include <linux/sched.h> @@ -63,6 +64,7 @@ void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out) for_each_cpu(cpu, in) cpumask_set_cpu(cpuid_to_hartid_map(cpu), out); } +EXPORT_SYMBOL_GPL(riscv_cpuid_to_hartid_mask); bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 6c854875ac74..837b9b38f825 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -65,7 +65,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, #else /* !CONFIG_FRAME_POINTER */ -static void notrace walk_stackframe(struct task_struct *task, +void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(unsigned long, void *), void *arg) { unsigned long sp, pc; diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index a4ee3a0e7d20..4c8b2a4a6a70 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -12,7 +12,7 @@ vdso-syms += getcpu vdso-syms += flush_icache # Files to link into the vdso -obj-vdso = $(patsubst %, %.o, $(vdso-syms)) +obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o # Build rules targets := $(obj-vdso) vdso.so vdso.so.dbg vdso.lds vdso-dummy.o diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S new file mode 100644 index 000000000000..2a956c942211 --- /dev/null +++ b/arch/riscv/kernel/vdso/note.S @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include <linux/elfnote.h> +#include <linux/version.h> + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index b55be44ff9bd..27a334106708 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -150,7 +150,8 @@ void __init setup_bootmem(void) memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + max_low_pfn = max_pfn; #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); @@ -501,22 +502,6 @@ static inline void setup_vm_final(void) #endif /* CONFIG_MMU */ #ifdef CONFIG_STRICT_KERNEL_RWX -void set_kernel_text_rw(void) -{ - unsigned long text_start = (unsigned long)_text; - unsigned long text_end = (unsigned long)_etext; - - set_memory_rw(text_start, (text_end - text_start) >> PAGE_SHIFT); -} - -void set_kernel_text_ro(void) -{ - unsigned long text_start = (unsigned long)_text; - unsigned long text_end = (unsigned long)_etext; - - set_memory_ro(text_start, (text_end - text_start) >> PAGE_SHIFT); -} - void mark_rodata_ro(void) { unsigned long text_start = (unsigned long)_text; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 5dcf9ff12828..d05bb040fd42 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -545,6 +545,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_AIS: case KVM_CAP_S390_AIS_MIGRATION: case KVM_CAP_S390_VCPU_RESETS: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_S390_HPAGE_1M: diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 69a824f9ef0b..893893642415 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -626,10 +626,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu) * available for the guest are AQIC and TAPQ with the t bit set * since we do not set IC.3 (FIII) we currently will only intercept * the AQIC function code. + * Note: running nested under z/VM can result in intercepts for other + * function codes, e.g. PQAP(QCI). We do not support this and bail out. */ reg0 = vcpu->run->s.regs.gprs[0]; fc = (reg0 >> 24) & 0xff; - if (WARN_ON_ONCE(fc != 0x03)) + if (fc != 0x03) return -EOPNOTSUPP; /* PQAP instruction is allowed for guest kernel only */ diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1197b5596d5a..2d3f963fd6f1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -68,6 +68,7 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c index 06ef2d4a4701..6737bcea1fa1 100644 --- a/arch/x86/crypto/blake2s-glue.c +++ b/arch/x86/crypto/blake2s-glue.c @@ -32,16 +32,16 @@ void blake2s_compress_arch(struct blake2s_state *state, const u32 inc) { /* SIMD disables preemption, so relax after processing each page. */ - BUILD_BUG_ON(PAGE_SIZE / BLAKE2S_BLOCK_SIZE < 8); + BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8); if (!static_branch_likely(&blake2s_use_ssse3) || !crypto_simd_usable()) { blake2s_compress_generic(state, block, nblocks, inc); return; } - for (;;) { + do { const size_t blocks = min_t(size_t, nblocks, - PAGE_SIZE / BLAKE2S_BLOCK_SIZE); + SZ_4K / BLAKE2S_BLOCK_SIZE); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && @@ -52,10 +52,8 @@ void blake2s_compress_arch(struct blake2s_state *state, kernel_fpu_end(); nblocks -= blocks; - if (!nblocks) - break; block += blocks * BLAKE2S_BLOCK_SIZE; - } + } while (nblocks); } EXPORT_SYMBOL(blake2s_compress_arch); diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c index b412c21ee06e..22250091cdbe 100644 --- a/arch/x86/crypto/chacha_glue.c +++ b/arch/x86/crypto/chacha_glue.c @@ -153,9 +153,17 @@ void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes, bytes <= CHACHA_BLOCK_SIZE) return chacha_crypt_generic(state, dst, src, bytes, nrounds); - kernel_fpu_begin(); - chacha_dosimd(state, dst, src, bytes, nrounds); - kernel_fpu_end(); + do { + unsigned int todo = min_t(unsigned int, bytes, SZ_4K); + + kernel_fpu_begin(); + chacha_dosimd(state, dst, src, todo, nrounds); + kernel_fpu_end(); + + bytes -= todo; + src += todo; + dst += todo; + } while (bytes); } EXPORT_SYMBOL(chacha_crypt_arch); diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c index f7567cbd35b6..80fcb85736e1 100644 --- a/arch/x86/crypto/nhpoly1305-avx2-glue.c +++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2); diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c index a661ede3b5cf..cc6b7c1a2705 100644 --- a/arch/x86/crypto/nhpoly1305-sse2-glue.c +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -29,7 +29,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc, return crypto_nhpoly1305_update(desc, src, srclen); do { - unsigned int n = min_t(unsigned int, srclen, PAGE_SIZE); + unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2); diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 6dfec19f7d57..dfe921efa9b2 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -91,8 +91,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, struct poly1305_arch_internal *state = ctx; /* SIMD disables preemption, so relax after processing each page. */ - BUILD_BUG_ON(PAGE_SIZE < POLY1305_BLOCK_SIZE || - PAGE_SIZE % POLY1305_BLOCK_SIZE); + BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE || + SZ_4K % POLY1305_BLOCK_SIZE); if (!static_branch_likely(&poly1305_use_avx) || (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) || @@ -102,8 +102,8 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, return; } - for (;;) { - const size_t bytes = min_t(size_t, len, PAGE_SIZE); + do { + const size_t bytes = min_t(size_t, len, SZ_4K); kernel_fpu_begin(); if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512)) @@ -113,11 +113,10 @@ static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len, else poly1305_blocks_avx(ctx, inp, bytes, padbit); kernel_fpu_end(); + len -= bytes; - if (!len) - break; inp += bytes; - } + } while (len); } static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 0789e13ece90..1c7f13bb6728 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -98,13 +98,6 @@ For 32-bit we have the following conventions - kernel is built with #define SIZEOF_PTREGS 21*8 .macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0 - /* - * Push registers and sanitize registers of values that a - * speculation attack might otherwise want to exploit. The - * lower registers are likely clobbered well before they - * could be put to use in a speculative execution gadget. - * Interleave XOR with PUSH for better uop scheduling: - */ .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -114,34 +107,43 @@ For 32-bit we have the following conventions - kernel is built with pushq %rsi /* pt_regs->si */ .endif pushq \rdx /* pt_regs->dx */ - xorl %edx, %edx /* nospec dx */ pushq %rcx /* pt_regs->cx */ - xorl %ecx, %ecx /* nospec cx */ pushq \rax /* pt_regs->ax */ pushq %r8 /* pt_regs->r8 */ - xorl %r8d, %r8d /* nospec r8 */ pushq %r9 /* pt_regs->r9 */ - xorl %r9d, %r9d /* nospec r9 */ pushq %r10 /* pt_regs->r10 */ - xorl %r10d, %r10d /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ - xorl %r11d, %r11d /* nospec r11*/ pushq %rbx /* pt_regs->rbx */ - xorl %ebx, %ebx /* nospec rbx*/ pushq %rbp /* pt_regs->rbp */ - xorl %ebp, %ebp /* nospec rbp*/ pushq %r12 /* pt_regs->r12 */ - xorl %r12d, %r12d /* nospec r12*/ pushq %r13 /* pt_regs->r13 */ - xorl %r13d, %r13d /* nospec r13*/ pushq %r14 /* pt_regs->r14 */ - xorl %r14d, %r14d /* nospec r14*/ pushq %r15 /* pt_regs->r15 */ - xorl %r15d, %r15d /* nospec r15*/ UNWIND_HINT_REGS + .if \save_ret pushq %rsi /* return address on top of stack */ .endif + + /* + * Sanitize registers of values that a speculation attack might + * otherwise want to exploit. The lower registers are likely clobbered + * well before they could be put to use in a speculative execution + * gadget. + */ + xorl %edx, %edx /* nospec dx */ + xorl %ecx, %ecx /* nospec cx */ + xorl %r8d, %r8d /* nospec r8 */ + xorl %r9d, %r9d /* nospec r9 */ + xorl %r10d, %r10d /* nospec r10 */ + xorl %r11d, %r11d /* nospec r11 */ + xorl %ebx, %ebx /* nospec rbx */ + xorl %ebp, %ebp /* nospec rbp */ + xorl %r12d, %r12d /* nospec r12 */ + xorl %r13d, %r13d /* nospec r13 */ + xorl %r14d, %r14d /* nospec r14 */ + xorl %r15d, %r15d /* nospec r15 */ + .endm .macro POP_REGS pop_rdi=1 skip_r11rcx=0 diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 0e9504fabe52..3063aa9090f9 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -249,7 +249,6 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) */ syscall_return_via_sysret: /* rcx and r11 are already restored (see code above) */ - UNWIND_HINT_EMPTY POP_REGS pop_rdi=0 skip_r11rcx=1 /* @@ -258,6 +257,7 @@ syscall_return_via_sysret: */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY pushq RSP-RDI(%rdi) /* RSP */ pushq (%rdi) /* RDI */ @@ -279,8 +279,7 @@ SYM_CODE_END(entry_SYSCALL_64) * %rdi: prev task * %rsi: next task */ -SYM_CODE_START(__switch_to_asm) - UNWIND_HINT_FUNC +SYM_FUNC_START(__switch_to_asm) /* * Save callee-saved registers * This must match the order in inactive_task_frame @@ -321,7 +320,7 @@ SYM_CODE_START(__switch_to_asm) popq %rbp jmp __switch_to -SYM_CODE_END(__switch_to_asm) +SYM_FUNC_END(__switch_to_asm) /* * A newly forked process directly context switches into this address. @@ -512,7 +511,7 @@ SYM_CODE_END(spurious_entries_start) * +----------------------------------------------------+ */ SYM_CODE_START(interrupt_entry) - UNWIND_HINT_FUNC + UNWIND_HINT_IRET_REGS offset=16 ASM_CLAC cld @@ -544,9 +543,9 @@ SYM_CODE_START(interrupt_entry) pushq 5*8(%rdi) /* regs->eflags */ pushq 4*8(%rdi) /* regs->cs */ pushq 3*8(%rdi) /* regs->ip */ + UNWIND_HINT_IRET_REGS pushq 2*8(%rdi) /* regs->orig_ax */ pushq 8(%rdi) /* return address */ - UNWIND_HINT_FUNC movq (%rdi), %rdi jmp 2f @@ -637,6 +636,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) */ movq %rsp, %rdi movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp + UNWIND_HINT_EMPTY /* Copy the IRET frame to the trampoline stack. */ pushq 6*8(%rdi) /* SS */ @@ -1739,7 +1739,7 @@ SYM_CODE_START(rewind_stack_do_exit) movq PER_CPU_VAR(cpu_current_top_of_stack), %rax leaq -PTREGS_SIZE(%rax), %rsp - UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE + UNWIND_HINT_REGS call do_exit SYM_CODE_END(rewind_stack_do_exit) diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 85be2f506272..84b9449be080 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -56,16 +56,23 @@ struct dyn_arch_ftrace { #ifndef __ASSEMBLY__ +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +extern void set_ftrace_ops_ro(void); +#else +static inline void set_ftrace_ops_ro(void) { } +#endif + #define ARCH_HAS_SYSCALL_MATCH_SYM_NAME static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) { /* * Compare the symbol name with the system call name. Skip the - * "__x64_sys", "__ia32_sys" or simple "sys" prefix. + * "__x64_sys", "__ia32_sys", "__do_sys" or simple "sys" prefix. */ return !strcmp(sym + 3, name + 3) || (!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) || - (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)); + (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)) || + (!strncmp(sym, "__do_sys", 8) && !strcmp(sym + 8, name + 3)); } #ifndef COMPILE_OFFSETS diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 42a2d0d3984a..0a6b35353fc7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -578,6 +578,7 @@ struct kvm_vcpu_arch { unsigned long cr4; unsigned long cr4_guest_owned_bits; unsigned long cr8; + u32 host_pkru; u32 pkru; u32 hflags; u64 efer; @@ -1093,8 +1094,6 @@ struct kvm_x86_ops { void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); - u64 (*get_dr6)(struct kvm_vcpu *vcpu); - void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value); void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); @@ -1449,6 +1448,7 @@ bool kvm_rdpmc(struct kvm_vcpu *vcpu); void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); +void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, unsigned long payload); void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr); void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code); void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault); @@ -1663,8 +1663,8 @@ void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq) { /* We can only post Fixed and LowPrio IRQs */ - return (irq->delivery_mode == dest_Fixed || - irq->delivery_mode == dest_LowestPrio); + return (irq->delivery_mode == APIC_DM_FIXED || + irq->delivery_mode == APIC_DM_LOWEST); } static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 91e29b6a86a5..9804a7957f4e 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -55,8 +55,13 @@ /* * Initialize the stackprotector canary value. * - * NOTE: this must only be called from functions that never return, + * NOTE: this must only be called from functions that never return * and it must always be inlined. + * + * In addition, it should be called from a compilation unit for which + * stack protector is disabled. Alternatively, the caller should not end + * with a function call which gets tail-call optimized as that would + * lead to checking a modified canary value. */ static __always_inline void boot_init_stack_canary(void) { diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 499578f7e6d7..70fc159ebe69 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -19,7 +19,7 @@ struct unwind_state { #if defined(CONFIG_UNWINDER_ORC) bool signal, full_regs; unsigned long sp, bp, ip; - struct pt_regs *regs; + struct pt_regs *regs, *prev_regs; #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 81b9c63dae1b..e53dda210cd7 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -352,8 +352,6 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen) * According to Intel, MFENCE can do the serialization here. */ asm volatile("mfence" : : : "memory"); - - printk_once(KERN_DEBUG "TSC deadline timer enabled\n"); return; } @@ -546,7 +544,7 @@ static struct clock_event_device lapic_clockevent = { }; static DEFINE_PER_CPU(struct clock_event_device, lapic_events); -static u32 hsx_deadline_rev(void) +static __init u32 hsx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x3a; /* EP */ @@ -556,7 +554,7 @@ static u32 hsx_deadline_rev(void) return ~0U; } -static u32 bdx_deadline_rev(void) +static __init u32 bdx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x02: return 0x00000011; @@ -568,7 +566,7 @@ static u32 bdx_deadline_rev(void) return ~0U; } -static u32 skx_deadline_rev(void) +static __init u32 skx_deadline_rev(void) { switch (boot_cpu_data.x86_stepping) { case 0x03: return 0x01000136; @@ -581,7 +579,7 @@ static u32 skx_deadline_rev(void) return ~0U; } -static const struct x86_cpu_id deadline_match[] = { +static const struct x86_cpu_id deadline_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL( HASWELL_X, &hsx_deadline_rev), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_X, 0x0b000020), X86_MATCH_INTEL_FAM6_MODEL( BROADWELL_D, &bdx_deadline_rev), @@ -603,18 +601,19 @@ static const struct x86_cpu_id deadline_match[] = { {}, }; -static void apic_check_deadline_errata(void) +static __init bool apic_validate_deadline_timer(void) { const struct x86_cpu_id *m; u32 rev; - if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER) || - boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return; + if (!boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) + return false; + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; m = x86_match_cpu(deadline_match); if (!m) - return; + return true; /* * Function pointers will have the MSB set due to address layout, @@ -626,11 +625,12 @@ static void apic_check_deadline_errata(void) rev = (u32)m->driver_data; if (boot_cpu_data.microcode >= rev) - return; + return true; setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); pr_err(FW_BUG "TSC_DEADLINE disabled due to Errata; " "please update microcode to version: 0x%x (or later)\n", rev); + return false; } /* @@ -2092,7 +2092,8 @@ void __init init_apic_mappings(void) { unsigned int new_apicid; - apic_check_deadline_errata(); + if (apic_validate_deadline_timer()) + pr_debug("TSC deadline timer available\n"); if (x2apic_mode) { boot_cpu_physical_apicid = read_apic_id(); diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 87b97897a881..460ae7f66818 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -183,7 +183,8 @@ recursion_check: */ if (visit_mask) { if (*visit_mask & (1UL << info->type)) { - printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); + if (task == current) + printk_deferred_once(KERN_WARNING "WARNING: stack recursion on stack type %d\n", info->type); goto unknown; } *visit_mask |= 1UL << info->type; diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 37a0aeaf89e7..b0e641793be4 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -407,7 +407,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) set_vm_flush_reset_perms(trampoline); - set_memory_ro((unsigned long)trampoline, npages); + if (likely(system_state != SYSTEM_BOOTING)) + set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); return (unsigned long)trampoline; fail: @@ -415,6 +416,32 @@ fail: return 0; } +void set_ftrace_ops_ro(void) +{ + struct ftrace_ops *ops; + unsigned long start_offset; + unsigned long end_offset; + unsigned long npages; + unsigned long size; + + do_for_each_ftrace_op(ops, ftrace_ops_list) { + if (!(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP)) + continue; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) { + start_offset = (unsigned long)ftrace_regs_caller; + end_offset = (unsigned long)ftrace_regs_caller_end; + } else { + start_offset = (unsigned long)ftrace_caller; + end_offset = (unsigned long)ftrace_epilogue; + } + size = end_offset - start_offset; + size = size + RET_SIZE + sizeof(void *); + npages = DIV_ROUND_UP(size, PAGE_SIZE); + set_memory_ro((unsigned long)ops->trampoline, npages); + } while_for_each_ftrace_op(ops); +} + static unsigned long calc_trampoline_call_offset(bool save_regs) { unsigned long start_offset; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 8c89e4d9ad28..2f24c334a938 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -266,6 +266,14 @@ static void notrace start_secondary(void *unused) wmb(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + + /* + * Prevent tail call to cpu_startup_entry() because the stack protector + * guard has been changed a couple of function calls up, in + * boot_init_stack_canary() and must not be checked before tail calling + * another function. + */ + prevent_tail_call_optimization(); } /** diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c index a224b5ab103f..54226110bc7f 100644 --- a/arch/x86/kernel/unwind_frame.c +++ b/arch/x86/kernel/unwind_frame.c @@ -344,6 +344,9 @@ bad_address: if (IS_ENABLED(CONFIG_X86_32)) goto the_end; + if (state->task != current) + goto the_end; + if (state->regs) { printk_deferred_once(KERN_WARNING "WARNING: kernel stack regs at %p in %s:%d has bad 'bp' value %p\n", diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index e9cc182aa97e..fa79e4227d3d 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -8,19 +8,21 @@ #include <asm/orc_lookup.h> #define orc_warn(fmt, ...) \ - printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__) + printk_deferred_once(KERN_WARNING "WARNING: " fmt, ##__VA_ARGS__) + +#define orc_warn_current(args...) \ +({ \ + if (state->task == current) \ + orc_warn(args); \ +}) extern int __start_orc_unwind_ip[]; extern int __stop_orc_unwind_ip[]; extern struct orc_entry __start_orc_unwind[]; extern struct orc_entry __stop_orc_unwind[]; -static DEFINE_MUTEX(sort_mutex); -int *cur_orc_ip_table = __start_orc_unwind_ip; -struct orc_entry *cur_orc_table = __start_orc_unwind; - -unsigned int lookup_num_blocks; -bool orc_init; +static bool orc_init __ro_after_init; +static unsigned int lookup_num_blocks __ro_after_init; static inline unsigned long orc_ip(const int *ip) { @@ -142,9 +144,6 @@ static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; - if (!orc_init) - return NULL; - if (ip == 0) return &null_orc_entry; @@ -189,6 +188,10 @@ static struct orc_entry *orc_find(unsigned long ip) #ifdef CONFIG_MODULES +static DEFINE_MUTEX(sort_mutex); +static int *cur_orc_ip_table = __start_orc_unwind_ip; +static struct orc_entry *cur_orc_table = __start_orc_unwind; + static void orc_sort_swap(void *_a, void *_b, int size) { struct orc_entry *orc_a, *orc_b; @@ -381,9 +384,38 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr return true; } +/* + * If state->regs is non-NULL, and points to a full pt_regs, just get the reg + * value from state->regs. + * + * Otherwise, if state->regs just points to IRET regs, and the previous frame + * had full regs, it's safe to get the value from the previous regs. This can + * happen when early/late IRQ entry code gets interrupted by an NMI. + */ +static bool get_reg(struct unwind_state *state, unsigned int reg_off, + unsigned long *val) +{ + unsigned int reg = reg_off/8; + + if (!state->regs) + return false; + + if (state->full_regs) { + *val = ((unsigned long *)state->regs)[reg]; + return true; + } + + if (state->prev_regs) { + *val = ((unsigned long *)state->prev_regs)[reg]; + return true; + } + + return false; +} + bool unwind_next_frame(struct unwind_state *state) { - unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp; + unsigned long ip_p, sp, tmp, orig_ip = state->ip, prev_sp = state->sp; enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; @@ -445,43 +477,39 @@ bool unwind_next_frame(struct unwind_state *state) break; case ORC_REG_R10: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R10 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r10), &sp)) { + orc_warn_current("missing R10 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r10; break; case ORC_REG_R13: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg R13 at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, r13), &sp)) { + orc_warn_current("missing R13 value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->r13; break; case ORC_REG_DI: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DI at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, di), &sp)) { + orc_warn_current("missing RDI value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->di; break; case ORC_REG_DX: - if (!state->regs || !state->full_regs) { - orc_warn("missing regs for base reg DX at ip %pB\n", - (void *)state->ip); + if (!get_reg(state, offsetof(struct pt_regs, dx), &sp)) { + orc_warn_current("missing DX value at %pB\n", + (void *)state->ip); goto err; } - sp = state->regs->dx; break; default: - orc_warn("unknown SP base reg %d for ip %pB\n", + orc_warn("unknown SP base reg %d at %pB\n", orc->sp_reg, (void *)state->ip); goto err; } @@ -504,44 +532,48 @@ bool unwind_next_frame(struct unwind_state *state) state->sp = sp; state->regs = NULL; + state->prev_regs = NULL; state->signal = false; break; case ORC_TYPE_REGS: if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access registers at %pB\n", + (void *)orig_ip); goto err; } state->regs = (struct pt_regs *)sp; + state->prev_regs = NULL; state->full_regs = true; state->signal = true; break; case ORC_TYPE_REGS_IRET: if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) { - orc_warn("can't dereference iret registers at %p for ip %pB\n", - (void *)sp, (void *)orig_ip); + orc_warn_current("can't access iret registers at %pB\n", + (void *)orig_ip); goto err; } + if (state->full_regs) + state->prev_regs = state->regs; state->regs = (void *)sp - IRET_FRAME_OFFSET; state->full_regs = false; state->signal = true; break; default: - orc_warn("unknown .orc_unwind entry type %d for ip %pB\n", + orc_warn("unknown .orc_unwind entry type %d at %pB\n", orc->type, (void *)orig_ip); - break; + goto err; } /* Find BP: */ switch (orc->bp_reg) { case ORC_REG_UNDEFINED: - if (state->regs && state->full_regs) - state->bp = state->regs->bp; + if (get_reg(state, offsetof(struct pt_regs, bp), &tmp)) + state->bp = tmp; break; case ORC_REG_PREV_SP: @@ -564,8 +596,8 @@ bool unwind_next_frame(struct unwind_state *state) if (state->stack_info.type == prev_type && on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) && state->sp <= prev_sp) { - orc_warn("stack going in the wrong direction? ip=%pB\n", - (void *)orig_ip); + orc_warn_current("stack going in the wrong direction? at %pB\n", + (void *)orig_ip); goto err; } @@ -588,17 +620,20 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, memset(state, 0, sizeof(*state)); state->task = task; + if (!orc_init) + goto err; + /* * Refuse to unwind the stack of a task while it's executing on another * CPU. This check is racy, but that's ok: the unwinder has other * checks to prevent it from going off the rails. */ if (task_on_another_cpu(task)) - goto done; + goto err; if (regs) { if (user_mode(regs)) - goto done; + goto the_end; state->ip = regs->ip; state->sp = regs->sp; @@ -631,6 +666,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, * generate some kind of backtrace if this happens. */ void *next_page = (void *)PAGE_ALIGN((unsigned long)state->sp); + state->error = true; if (get_stack_info(next_page, state->task, &state->stack_info, &state->stack_mask)) return; @@ -651,13 +687,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, /* Otherwise, skip ahead to the user-specified starting frame: */ while (!unwind_done(state) && (!on_stack(&state->stack_info, first_frame, sizeof(long)) || - state->sp <= (unsigned long)first_frame)) + state->sp < (unsigned long)first_frame)) unwind_next_frame(state); return; -done: +err: + state->error = true; +the_end: state->stack_info.type = STACK_TYPE_UNKNOWN; - return; } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index bcefa9d4e57e..54d4b98b49e1 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1427,7 +1427,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa, */ kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH | KVM_REQUEST_NO_WAKEUP, - vcpu_mask, &hv_vcpu->tlb_flush); + NULL, vcpu_mask, &hv_vcpu->tlb_flush); ret_success: /* We always do full TLB flush, set rep_done = rep_cnt. */ diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 750ff0b29404..d057376bd3d3 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -225,12 +225,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq, } /* - * AMD SVM AVIC accelerate EOI write and do not trap, - * in-kernel IOAPIC will not be able to receive the EOI. - * In this case, we do lazy update of the pending EOI when - * trying to set IOAPIC irq. + * AMD SVM AVIC accelerate EOI write iff the interrupt is edge + * triggered, in which case the in-kernel IOAPIC will not be able + * to receive the EOI. In this case, we do a lazy update of the + * pending EOI when trying to set IOAPIC irq. */ - if (kvm_apicv_activated(ioapic->kvm)) + if (edge && kvm_apicv_activated(ioapic->kvm)) ioapic_lazy_update_eoi(ioapic, irq); /* diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 90a1ca939627..9a2a62e5afeb 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <asm/msr-index.h> +#include <asm/debugreg.h> #include "kvm_emulate.h" #include "trace.h" @@ -267,7 +268,7 @@ void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa, svm->vmcb->save.rsp = nested_vmcb->save.rsp; svm->vmcb->save.rip = nested_vmcb->save.rip; svm->vmcb->save.dr7 = nested_vmcb->save.dr7; - svm->vmcb->save.dr6 = nested_vmcb->save.dr6; + svm->vcpu.arch.dr6 = nested_vmcb->save.dr6; svm->vmcb->save.cpl = nested_vmcb->save.cpl; svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL; @@ -482,7 +483,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->save.rsp = vmcb->save.rsp; nested_vmcb->save.rax = vmcb->save.rax; nested_vmcb->save.dr7 = vmcb->save.dr7; - nested_vmcb->save.dr6 = vmcb->save.dr6; + nested_vmcb->save.dr6 = svm->vcpu.arch.dr6; nested_vmcb->save.cpl = vmcb->save.cpl; nested_vmcb->control.int_ctl = vmcb->control.int_ctl; @@ -606,26 +607,45 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm) /* DB exceptions for our internal use must not cause vmexit */ static int nested_svm_intercept_db(struct vcpu_svm *svm) { - unsigned long dr6; + unsigned long dr6 = svm->vmcb->save.dr6; + + /* Always catch it and pass it to userspace if debugging. */ + if (svm->vcpu.guest_debug & + (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) + return NESTED_EXIT_HOST; /* if we're not singlestepping, it's not ours */ if (!svm->nmi_singlestep) - return NESTED_EXIT_DONE; + goto reflected_db; /* if it's not a singlestep exception, it's not ours */ - if (kvm_get_dr(&svm->vcpu, 6, &dr6)) - return NESTED_EXIT_DONE; if (!(dr6 & DR6_BS)) - return NESTED_EXIT_DONE; + goto reflected_db; /* if the guest is singlestepping, it should get the vmexit */ if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) { disable_nmi_singlestep(svm); - return NESTED_EXIT_DONE; + goto reflected_db; } /* it's ours, the nested hypervisor must not see this one */ return NESTED_EXIT_HOST; + +reflected_db: + /* + * Synchronize guest DR6 here just like in kvm_deliver_exception_payload; + * it will be moved into the nested VMCB by nested_svm_vmexit. Once + * exceptions will be moved to svm_check_nested_events, all this stuff + * will just go away and we could just return NESTED_EXIT_HOST + * unconditionally. db_interception will queue the exception, which + * will be processed by svm_check_nested_events if a nested vmexit is + * required, and we will just use kvm_deliver_exception_payload to copy + * the payload to DR6 before vmexit. + */ + WARN_ON(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT); + svm->vcpu.arch.dr6 &= ~(DR_TRAP_BITS | DR6_RTM); + svm->vcpu.arch.dr6 |= dr6 & ~DR6_FIXED_1; + return NESTED_EXIT_DONE; } static int nested_svm_intercept_ioio(struct vcpu_svm *svm) @@ -682,6 +702,9 @@ static int nested_svm_intercept(struct vcpu_svm *svm) if (svm->nested.intercept_exceptions & excp_bits) { if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR) vmexit = nested_svm_intercept_db(svm); + else if (exit_code == SVM_EXIT_EXCP_BASE + BP_VECTOR && + svm->vcpu.guest_debug & KVM_GUESTDBG_USE_SW_BP) + vmexit = NESTED_EXIT_HOST; else vmexit = NESTED_EXIT_DONE; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index cf912b4aaba8..89f7f3aebd31 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -345,7 +345,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, return NULL; /* Pin the user virtual address. */ - npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages); + npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages); if (npinned != npages) { pr_err("SEV: Failure locking %lu pages.\n", npages); goto err; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2f379bacbb26..a862c768fd54 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1672,17 +1672,14 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) mark_dirty(svm->vmcb, VMCB_ASID); } -static u64 svm_get_dr6(struct kvm_vcpu *vcpu) +static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value) { - return to_svm(vcpu)->vmcb->save.dr6; -} - -static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value) -{ - struct vcpu_svm *svm = to_svm(vcpu); + struct vmcb *vmcb = svm->vmcb; - svm->vmcb->save.dr6 = value; - mark_dirty(svm->vmcb, VMCB_DR); + if (unlikely(value != vmcb->save.dr6)) { + vmcb->save.dr6 = value; + mark_dirty(vmcb, VMCB_DR); + } } static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) @@ -1693,9 +1690,12 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) get_debugreg(vcpu->arch.db[1], 1); get_debugreg(vcpu->arch.db[2], 2); get_debugreg(vcpu->arch.db[3], 3); - vcpu->arch.dr6 = svm_get_dr6(vcpu); + /* + * We cannot reset svm->vmcb->save.dr6 to DR6_FIXED_1|DR6_RTM here, + * because db_interception might need it. We can do it before vmentry. + */ + vcpu->arch.dr6 = svm->vmcb->save.dr6; vcpu->arch.dr7 = svm->vmcb->save.dr7; - vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; set_dr_intercepts(svm); } @@ -1739,7 +1739,8 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) && !svm->nmi_singlestep) { - kvm_queue_exception(&svm->vcpu, DB_VECTOR); + u32 payload = (svm->vmcb->save.dr6 ^ DR6_RTM) & ~DR6_FIXED_1; + kvm_queue_exception_p(&svm->vcpu, DB_VECTOR, payload); return 1; } @@ -1752,6 +1753,8 @@ static int db_interception(struct vcpu_svm *svm) if (svm->vcpu.guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) { kvm_run->exit_reason = KVM_EXIT_DEBUG; + kvm_run->debug.arch.dr6 = svm->vmcb->save.dr6; + kvm_run->debug.arch.dr7 = svm->vmcb->save.dr7; kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip; kvm_run->debug.arch.exception = DB_VECTOR; @@ -3315,6 +3318,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) svm->vmcb->save.cr2 = vcpu->arch.cr2; + /* + * Run with all-zero DR6 unless needed, so that we can get the exact cause + * of a #DB. + */ + if (unlikely(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) + svm_set_dr6(svm, vcpu->arch.dr6); + else + svm_set_dr6(svm, DR6_FIXED_1 | DR6_RTM); + clgi(); kvm_load_guest_xsave_state(vcpu); @@ -3929,8 +3941,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, - .get_dr6 = svm_get_dr6, - .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index fd78ffbde644..e44f33c82332 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -5165,7 +5165,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) */ break; default: - BUG_ON(1); + BUG(); break; } diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 87f3f24fef37..51d1a82742fd 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -82,6 +82,9 @@ SYM_FUNC_START(vmx_vmexit) /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ + or $1, %_ASM_AX + pop %_ASM_AX .Lvmexit_skip_rsb: #endif diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c2c6335a998c..89c766fad889 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1372,7 +1372,6 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vmx_vcpu_pi_load(vcpu, cpu); - vmx->host_pkru = read_pkru(); vmx->host_debugctlmsr = get_debugctlmsr(); } @@ -4677,15 +4676,13 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) dr6 = vmcs_readl(EXIT_QUALIFICATION); if (!(vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= dr6 | DR6_RTM; if (is_icebp(intr_info)) WARN_ON(!skip_emulated_instruction(vcpu)); - kvm_queue_exception(vcpu, DB_VECTOR); + kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); return 1; } - kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1; + kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7); /* fall through */ case BP_VECTOR: @@ -4929,16 +4926,14 @@ static int handle_dr(struct kvm_vcpu *vcpu) * guest debugging itself. */ if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { - vcpu->run->debug.arch.dr6 = vcpu->arch.dr6; + vcpu->run->debug.arch.dr6 = DR6_BD | DR6_RTM | DR6_FIXED_1; vcpu->run->debug.arch.dr7 = dr7; vcpu->run->debug.arch.pc = kvm_get_linear_rip(vcpu); vcpu->run->debug.arch.exception = DB_VECTOR; vcpu->run->exit_reason = KVM_EXIT_DEBUG; return 0; } else { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= DR6_BD | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); + kvm_queue_exception_p(vcpu, DB_VECTOR, DR6_BD); return 1; } } @@ -4969,15 +4964,6 @@ static int handle_dr(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } -static u64 vmx_get_dr6(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.dr6; -} - -static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val) -{ -} - static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { get_debugreg(vcpu->arch.db[0], 0); @@ -6577,11 +6563,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_load_guest_xsave_state(vcpu); - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE) && - vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vcpu->arch.pkru); - pt_guest_enter(vmx); if (vcpu_to_pmu(vcpu)->version) @@ -6671,18 +6652,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu) pt_guest_exit(vmx); - /* - * eager fpu is enabled if PKEY is supported and CR4 is switched - * back on host, so it is safe to read guest PKRU from current - * XSAVE. - */ - if (static_cpu_has(X86_FEATURE_PKU) && - kvm_read_cr4_bits(vcpu, X86_CR4_PKE)) { - vcpu->arch.pkru = rdpkru(); - if (vcpu->arch.pkru != vmx->host_pkru) - __write_pkru(vmx->host_pkru); - } - kvm_load_host_xsave_state(vcpu); vmx->nested.nested_run_pending = 0; @@ -7740,8 +7709,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_idt = vmx_set_idt, .get_gdt = vmx_get_gdt, .set_gdt = vmx_set_gdt, - .get_dr6 = vmx_get_dr6, - .set_dr6 = vmx_set_dr6, .set_dr7 = vmx_set_dr7, .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs, .cache_reg = vmx_cache_reg, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c5835f9cb9ad..c17e6eb9ad43 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -572,11 +572,12 @@ void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) } EXPORT_SYMBOL_GPL(kvm_requeue_exception); -static void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, - unsigned long payload) +void kvm_queue_exception_p(struct kvm_vcpu *vcpu, unsigned nr, + unsigned long payload) { kvm_multiple_exception(vcpu, nr, false, 0, true, payload, false); } +EXPORT_SYMBOL_GPL(kvm_queue_exception_p); static void kvm_queue_exception_e_p(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code, unsigned long payload) @@ -836,11 +837,25 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) vcpu->arch.ia32_xss != host_xss) wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } + + if (static_cpu_has(X86_FEATURE_PKU) && + (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || + (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) && + vcpu->arch.pkru != vcpu->arch.host_pkru) + __write_pkru(vcpu->arch.pkru); } EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) { + if (static_cpu_has(X86_FEATURE_PKU) && + (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) || + (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) { + vcpu->arch.pkru = rdpkru(); + if (vcpu->arch.pkru != vcpu->arch.host_pkru) + __write_pkru(vcpu->arch.host_pkru); + } + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { if (vcpu->arch.xcr0 != host_xcr0) @@ -926,19 +941,6 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr); __reserved_bits; \ }) -static u64 kvm_host_cr4_reserved_bits(struct cpuinfo_x86 *c) -{ - u64 reserved_bits = __cr4_reserved_bits(cpu_has, c); - - if (kvm_cpu_cap_has(X86_FEATURE_LA57)) - reserved_bits &= ~X86_CR4_LA57; - - if (kvm_cpu_cap_has(X86_FEATURE_UMIP)) - reserved_bits &= ~X86_CR4_UMIP; - - return reserved_bits; -} - static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { if (cr4 & cr4_reserved_bits) @@ -1058,12 +1060,6 @@ static void kvm_update_dr0123(struct kvm_vcpu *vcpu) } } -static void kvm_update_dr6(struct kvm_vcpu *vcpu) -{ - if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) - kvm_x86_ops.set_dr6(vcpu, vcpu->arch.dr6); -} - static void kvm_update_dr7(struct kvm_vcpu *vcpu) { unsigned long dr7; @@ -1103,7 +1099,6 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) if (val & 0xffffffff00000000ULL) return -1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); - kvm_update_dr6(vcpu); break; case 5: /* fall through */ @@ -1139,10 +1134,7 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) case 4: /* fall through */ case 6: - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - *val = vcpu->arch.dr6; - else - *val = kvm_x86_ops.get_dr6(vcpu); + *val = vcpu->arch.dr6; break; case 5: /* fall through */ @@ -3385,6 +3377,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: + case KVM_CAP_SET_GUEST_DEBUG: r = 1; break; case KVM_CAP_SYNC_REGS: @@ -3570,6 +3563,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) kvm_x86_ops.vcpu_load(vcpu, cpu); + /* Save host pkru register if supported */ + vcpu->arch.host_pkru = read_pkru(); + /* Apply any externally detected TSC adjustments (due to suspend) */ if (unlikely(vcpu->arch.tsc_offset_adjustment)) { adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment); @@ -3763,7 +3759,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, unsigned bank_num = mcg_cap & 0xff, bank; r = -EINVAL; - if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) + if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000)) goto out; @@ -4021,7 +4017,6 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; - kvm_update_dr6(vcpu); vcpu->arch.dr7 = dbgregs->dr7; kvm_update_dr7(vcpu); @@ -6671,7 +6666,7 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM; - kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; return 0; @@ -6731,9 +6726,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) vcpu->arch.db); if (dr6 != 0) { - vcpu->arch.dr6 &= ~DR_TRAP_BITS; - vcpu->arch.dr6 |= dr6 | DR6_RTM; - kvm_queue_exception(vcpu, DB_VECTOR); + kvm_queue_exception_p(vcpu, DB_VECTOR, dr6); *r = 1; return true; } @@ -8054,7 +8047,7 @@ void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, zalloc_cpumask_var(&cpus, GFP_ATOMIC); kvm_make_vcpus_request_mask(kvm, KVM_REQ_SCAN_IOAPIC, - vcpu_bitmap, cpus); + NULL, vcpu_bitmap, cpus); free_cpumask_var(cpus); } @@ -8084,6 +8077,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); */ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) { + struct kvm_vcpu *except; unsigned long old, new, expected; if (!kvm_x86_ops.check_apicv_inhibit_reasons || @@ -8108,7 +8102,17 @@ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) trace_kvm_apicv_update_request(activate, bit); if (kvm_x86_ops.pre_update_apicv_exec_ctrl) kvm_x86_ops.pre_update_apicv_exec_ctrl(kvm, activate); - kvm_make_all_cpus_request(kvm, KVM_REQ_APICV_UPDATE); + + /* + * Sending request to update APICV for all other vcpus, + * while update the calling vcpu immediately instead of + * waiting for another #VMEXIT to handle the request. + */ + except = kvm_get_running_vcpu(); + kvm_make_all_cpus_request_except(kvm, KVM_REQ_APICV_UPDATE, + except); + if (except) + kvm_vcpu_update_apicv(except); } EXPORT_SYMBOL_GPL(kvm_request_apicv_update); @@ -8432,7 +8436,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); kvm_x86_ops.sync_dirty_debug_regs(vcpu); kvm_update_dr0123(vcpu); - kvm_update_dr6(vcpu); kvm_update_dr7(vcpu); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } @@ -9493,7 +9496,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); vcpu->arch.dr6 = DR6_INIT; - kvm_update_dr6(vcpu); vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); @@ -9675,7 +9677,9 @@ int kvm_arch_hardware_setup(void *opaque) if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) supported_xss = 0; - cr4_reserved_bits = kvm_host_cr4_reserved_bits(&boot_cpu_data); +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); +#undef __kvm_cpu_cap_has if (kvm_has_tsc_control) { /* @@ -9707,7 +9711,8 @@ int kvm_arch_check_processor_compat(void *opaque) WARN_ON(!irqs_disabled()); - if (kvm_host_cr4_reserved_bits(c) != cr4_reserved_bits) + if (__cr4_reserved_bits(cpu_has, c) != + __cr4_reserved_bits(cpu_has, &boot_cpu_data)) return -EIO; return ops->check_processor_compatibility(); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3b289c2f75cd..8b5f73f5e207 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -54,6 +54,7 @@ #include <asm/init.h> #include <asm/uv/uv.h> #include <asm/setup.h> +#include <asm/ftrace.h> #include "mm_internal.h" @@ -1291,6 +1292,8 @@ void mark_rodata_ro(void) all_end = roundup((unsigned long)_brk_end, PMD_SIZE); set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT); + set_ftrace_ops_ro(); + #ifdef CONFIG_CPA_DEBUG printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end); set_memory_rw(start, (end-start) >> PAGE_SHIFT); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 59eca6a94ce7..b8c55a2e402d 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -43,7 +43,8 @@ struct cpa_data { unsigned long pfn; unsigned int flags; unsigned int force_split : 1, - force_static_prot : 1; + force_static_prot : 1, + force_flush_all : 1; struct page **pages; }; @@ -355,10 +356,10 @@ static void cpa_flush(struct cpa_data *data, int cache) return; } - if (cpa->numpages <= tlb_single_page_flush_ceiling) - on_each_cpu(__cpa_flush_tlb, cpa, 1); - else + if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling) flush_tlb_all(); + else + on_each_cpu(__cpa_flush_tlb, cpa, 1); if (!cache) return; @@ -1598,6 +1599,8 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; + ret = __change_page_attr_set_clr(&alias_cpa, 0); if (ret) return ret; @@ -1618,6 +1621,7 @@ static int cpa_process_alias(struct cpa_data *cpa) alias_cpa.flags &= ~(CPA_PAGES_ARRAY | CPA_ARRAY); alias_cpa.curpage = 0; + cpa->force_flush_all = 1; /* * The high mapping range is imprecise, so ignore the * return value. diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 8fb8a50a28b4..f2adb63b2d7c 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -93,6 +93,7 @@ asmlinkage __visible void cpu_bringup_and_idle(void) cpu_bringup(); boot_init_stack_canary(); cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); + prevent_tail_call_optimization(); } void xen_smp_intr_free_pv(unsigned int cpu) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 78ba57efd16b..3d411716d7ee 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -123,6 +123,7 @@ #include <linux/ioprio.h> #include <linux/sbitmap.h> #include <linux/delay.h> +#include <linux/backing-dev.h> #include "blk.h" #include "blk-mq.h" @@ -4976,8 +4977,9 @@ bfq_set_next_ioprio_data(struct bfq_queue *bfqq, struct bfq_io_cq *bic) ioprio_class = IOPRIO_PRIO_CLASS(bic->ioprio); switch (ioprio_class) { default: - dev_err(bfqq->bfqd->queue->backing_dev_info->dev, - "bfq: bad prio class %d\n", ioprio_class); + pr_err("bdi %s: bfq: bad prio class %d\n", + bdi_dev_name(bfqq->bfqd->queue->backing_dev_info), + ioprio_class); /* fall through */ case IOPRIO_CLASS_NONE: /* diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c5dc833212e1..930212c1a512 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -496,7 +496,7 @@ const char *blkg_dev_name(struct blkcg_gq *blkg) { /* some drivers (floppy) instantiate a queue w/o disk registered */ if (blkg->q->backing_dev_info->dev) - return dev_name(blkg->q->backing_dev_info->dev); + return bdi_dev_name(blkg->q->backing_dev_info); return NULL; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 3ab0c1c704b6..7c1fe605d0d6 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -466,7 +466,7 @@ struct ioc_gq { */ atomic64_t vtime; atomic64_t done_vtime; - atomic64_t abs_vdebt; + u64 abs_vdebt; u64 last_vtime; /* @@ -1142,7 +1142,7 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) struct iocg_wake_ctx ctx = { .iocg = iocg }; u64 margin_ns = (u64)(ioc->period_us * WAITQ_TIMER_MARGIN_PCT / 100) * NSEC_PER_USEC; - u64 abs_vdebt, vdebt, vshortage, expires, oexpires; + u64 vdebt, vshortage, expires, oexpires; s64 vbudget; u32 hw_inuse; @@ -1152,18 +1152,15 @@ static void iocg_kick_waitq(struct ioc_gq *iocg, struct ioc_now *now) vbudget = now->vnow - atomic64_read(&iocg->vtime); /* pay off debt */ - abs_vdebt = atomic64_read(&iocg->abs_vdebt); - vdebt = abs_cost_to_cost(abs_vdebt, hw_inuse); + vdebt = abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); if (vdebt && vbudget > 0) { u64 delta = min_t(u64, vbudget, vdebt); u64 abs_delta = min(cost_to_abs_cost(delta, hw_inuse), - abs_vdebt); + iocg->abs_vdebt); atomic64_add(delta, &iocg->vtime); atomic64_add(delta, &iocg->done_vtime); - atomic64_sub(abs_delta, &iocg->abs_vdebt); - if (WARN_ON_ONCE(atomic64_read(&iocg->abs_vdebt) < 0)) - atomic64_set(&iocg->abs_vdebt, 0); + iocg->abs_vdebt -= abs_delta; } /* @@ -1219,12 +1216,18 @@ static bool iocg_kick_delay(struct ioc_gq *iocg, struct ioc_now *now, u64 cost) u64 expires, oexpires; u32 hw_inuse; + lockdep_assert_held(&iocg->waitq.lock); + /* debt-adjust vtime */ current_hweight(iocg, NULL, &hw_inuse); - vtime += abs_cost_to_cost(atomic64_read(&iocg->abs_vdebt), hw_inuse); + vtime += abs_cost_to_cost(iocg->abs_vdebt, hw_inuse); - /* clear or maintain depending on the overage */ - if (time_before_eq64(vtime, now->vnow)) { + /* + * Clear or maintain depending on the overage. Non-zero vdebt is what + * guarantees that @iocg is online and future iocg_kick_delay() will + * clear use_delay. Don't leave it on when there's no vdebt. + */ + if (!iocg->abs_vdebt || time_before_eq64(vtime, now->vnow)) { blkcg_clear_delay(blkg); return false; } @@ -1258,9 +1261,12 @@ static enum hrtimer_restart iocg_delay_timer_fn(struct hrtimer *timer) { struct ioc_gq *iocg = container_of(timer, struct ioc_gq, delay_timer); struct ioc_now now; + unsigned long flags; + spin_lock_irqsave(&iocg->waitq.lock, flags); ioc_now(iocg->ioc, &now); iocg_kick_delay(iocg, &now, 0); + spin_unlock_irqrestore(&iocg->waitq.lock, flags); return HRTIMER_NORESTART; } @@ -1368,14 +1374,13 @@ static void ioc_timer_fn(struct timer_list *timer) * should have woken up in the last period and expire idle iocgs. */ list_for_each_entry_safe(iocg, tiocg, &ioc->active_iocgs, active_list) { - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && !iocg_is_idle(iocg)) + if (!waitqueue_active(&iocg->waitq) && iocg->abs_vdebt && + !iocg_is_idle(iocg)) continue; spin_lock(&iocg->waitq.lock); - if (waitqueue_active(&iocg->waitq) || - atomic64_read(&iocg->abs_vdebt)) { + if (waitqueue_active(&iocg->waitq) || iocg->abs_vdebt) { /* might be oversleeping vtime / hweight changes, kick */ iocg_kick_waitq(iocg, &now); iocg_kick_delay(iocg, &now, 0); @@ -1718,28 +1723,49 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * tests are racy but the races aren't systemic - we only miss once * in a while which is fine. */ - if (!waitqueue_active(&iocg->waitq) && - !atomic64_read(&iocg->abs_vdebt) && + if (!waitqueue_active(&iocg->waitq) && !iocg->abs_vdebt && time_before_eq64(vtime + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); return; } /* - * We're over budget. If @bio has to be issued regardless, - * remember the abs_cost instead of advancing vtime. - * iocg_kick_waitq() will pay off the debt before waking more IOs. + * We activated above but w/o any synchronization. Deactivation is + * synchronized with waitq.lock and we won't get deactivated as long + * as we're waiting or has debt, so we're good if we're activated + * here. In the unlikely case that we aren't, just issue the IO. + */ + spin_lock_irq(&iocg->waitq.lock); + + if (unlikely(list_empty(&iocg->active_list))) { + spin_unlock_irq(&iocg->waitq.lock); + iocg_commit_bio(iocg, bio, cost); + return; + } + + /* + * We're over budget. If @bio has to be issued regardless, remember + * the abs_cost instead of advancing vtime. iocg_kick_waitq() will pay + * off the debt before waking more IOs. + * * This way, the debt is continuously paid off each period with the - * actual budget available to the cgroup. If we just wound vtime, - * we would incorrectly use the current hw_inuse for the entire - * amount which, for example, can lead to the cgroup staying - * blocked for a long time even with substantially raised hw_inuse. + * actual budget available to the cgroup. If we just wound vtime, we + * would incorrectly use the current hw_inuse for the entire amount + * which, for example, can lead to the cgroup staying blocked for a + * long time even with substantially raised hw_inuse. + * + * An iocg with vdebt should stay online so that the timer can keep + * deducting its vdebt and [de]activate use_delay mechanism + * accordingly. We don't want to race against the timer trying to + * clear them and leave @iocg inactive w/ dangling use_delay heavily + * penalizing the cgroup and its descendants. */ if (bio_issue_as_root_blkg(bio) || fatal_signal_pending(current)) { - atomic64_add(abs_cost, &iocg->abs_vdebt); + iocg->abs_vdebt += abs_cost; if (iocg_kick_delay(iocg, &now, cost)) blkcg_schedule_throttle(rqos->q, (bio->bi_opf & REQ_SWAP) == REQ_SWAP); + spin_unlock_irq(&iocg->waitq.lock); return; } @@ -1756,20 +1782,6 @@ static void ioc_rqos_throttle(struct rq_qos *rqos, struct bio *bio) * All waiters are on iocg->waitq and the wait states are * synchronized using waitq.lock. */ - spin_lock_irq(&iocg->waitq.lock); - - /* - * We activated above but w/o any synchronization. Deactivation is - * synchronized with waitq.lock and we won't get deactivated as - * long as we're waiting, so we're good if we're activated here. - * In the unlikely case that we are deactivated, just issue the IO. - */ - if (unlikely(list_empty(&iocg->active_list))) { - spin_unlock_irq(&iocg->waitq.lock); - iocg_commit_bio(iocg, bio, cost); - return; - } - init_waitqueue_func_entry(&wait.wait, iocg_wake_fn); wait.wait.private = current; wait.bio = bio; @@ -1801,6 +1813,7 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, struct ioc_now now; u32 hw_inuse; u64 abs_cost, cost; + unsigned long flags; /* bypass if disabled or for root cgroup */ if (!ioc->enabled || !iocg->level) @@ -1820,15 +1833,28 @@ static void ioc_rqos_merge(struct rq_qos *rqos, struct request *rq, iocg->cursor = bio_end; /* - * Charge if there's enough vtime budget and the existing request - * has cost assigned. Otherwise, account it as debt. See debt - * handling in ioc_rqos_throttle() for details. + * Charge if there's enough vtime budget and the existing request has + * cost assigned. */ if (rq->bio && rq->bio->bi_iocost_cost && - time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) + time_before_eq64(atomic64_read(&iocg->vtime) + cost, now.vnow)) { iocg_commit_bio(iocg, bio, cost); - else - atomic64_add(abs_cost, &iocg->abs_vdebt); + return; + } + + /* + * Otherwise, account it as debt if @iocg is online, which it should + * be for the vast majority of cases. See debt handling in + * ioc_rqos_throttle() for details. + */ + spin_lock_irqsave(&iocg->waitq.lock, flags); + if (likely(!list_empty(&iocg->active_list))) { + iocg->abs_vdebt += abs_cost; + iocg_kick_delay(iocg, &now, cost); + } else { + iocg_commit_bio(iocg, bio, cost); + } + spin_unlock_irqrestore(&iocg->waitq.lock, flags); } static void ioc_rqos_done_bio(struct rq_qos *rqos, struct bio *bio) @@ -1998,7 +2024,6 @@ static void ioc_pd_init(struct blkg_policy_data *pd) iocg->ioc = ioc; atomic64_set(&iocg->vtime, now.vnow); atomic64_set(&iocg->done_vtime, now.vnow); - atomic64_set(&iocg->abs_vdebt, 0); atomic64_set(&iocg->active_period, atomic64_read(&ioc->cur_period)); INIT_LIST_HEAD(&iocg->active_list); iocg->hweight_active = HWEIGHT_WHOLE; diff --git a/crypto/lrw.c b/crypto/lrw.c index 376d7ed3f1f8..3c734b81b3a2 100644 --- a/crypto/lrw.c +++ b/crypto/lrw.c @@ -287,7 +287,7 @@ static void exit_tfm(struct crypto_skcipher *tfm) crypto_free_skcipher(ctx->child); } -static void free(struct skcipher_instance *inst) +static void free_inst(struct skcipher_instance *inst) { crypto_drop_skcipher(skcipher_instance_ctx(inst)); kfree(inst); @@ -400,12 +400,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.encrypt = encrypt; inst->alg.decrypt = decrypt; - inst->free = free; + inst->free = free_inst; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: - free(inst); + free_inst(inst); } return err; } diff --git a/crypto/xts.c b/crypto/xts.c index dbdd8af629e6..6d8cea94b3cf 100644 --- a/crypto/xts.c +++ b/crypto/xts.c @@ -322,7 +322,7 @@ static void exit_tfm(struct crypto_skcipher *tfm) crypto_free_cipher(ctx->tweak); } -static void free(struct skcipher_instance *inst) +static void free_inst(struct skcipher_instance *inst) { crypto_drop_skcipher(skcipher_instance_ctx(inst)); kfree(inst); @@ -434,12 +434,12 @@ static int create(struct crypto_template *tmpl, struct rtattr **tb) inst->alg.encrypt = encrypt; inst->alg.decrypt = decrypt; - inst->free = free; + inst->free = free_inst; err = skcipher_register_instance(tmpl, inst); if (err) { err_free_inst: - free(inst); + free_inst(inst); } return err; } diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index b4c0152e92aa..145ec0b6f20b 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1994,23 +1994,31 @@ void acpi_ec_set_gpe_wake_mask(u8 action) acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action); } -bool acpi_ec_other_gpes_active(void) -{ - return acpi_any_gpe_status_set(first_ec ? first_ec->gpe : U32_MAX); -} - bool acpi_ec_dispatch_gpe(void) { u32 ret; if (!first_ec) + return acpi_any_gpe_status_set(U32_MAX); + + /* + * Report wakeup if the status bit is set for any enabled GPE other + * than the EC one. + */ + if (acpi_any_gpe_status_set(first_ec->gpe)) + return true; + + if (ec_no_wakeup) return false; + /* + * Dispatch the EC GPE in-band, but do not report wakeup in any case + * to allow the caller to process events properly after that. + */ ret = acpi_dispatch_gpe(NULL, first_ec->gpe); - if (ret == ACPI_INTERRUPT_HANDLED) { + if (ret == ACPI_INTERRUPT_HANDLED) pm_pr_dbg("EC GPE dispatched\n"); - return true; - } + return false; } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index e387517d3354..43411a7457cd 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -202,7 +202,6 @@ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit); #ifdef CONFIG_PM_SLEEP void acpi_ec_flush_work(void); -bool acpi_ec_other_gpes_active(void); bool acpi_ec_dispatch_gpe(void); #endif diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 4edc8a3ce40f..3850704570c0 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -1013,21 +1013,11 @@ static bool acpi_s2idle_wake(void) if (acpi_check_wakeup_handlers()) return true; - /* - * If the status bit is set for any enabled GPE other than the - * EC one, the wakeup is regarded as a genuine one. - */ - if (acpi_ec_other_gpes_active()) + /* Check non-EC GPE wakeups and dispatch the EC GPE. */ + if (acpi_ec_dispatch_gpe()) return true; /* - * If the EC GPE status bit has not been set, the wakeup is - * regarded as a spurious one. - */ - if (!acpi_ec_dispatch_gpe()) - return false; - - /* * Cancel the wakeup and process all pending events in case * there are any wakeup ones in there. * diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c index fe1523664816..8558b629880b 100644 --- a/drivers/amba/bus.c +++ b/drivers/amba/bus.c @@ -645,6 +645,7 @@ static void amba_device_initialize(struct amba_device *dev, const char *name) dev->dev.release = amba_device_release; dev->dev.bus = &amba_bustype; dev->dev.dma_mask = &dev->dev.coherent_dma_mask; + dev->dev.dma_parms = &dev->dma_parms; dev->res.name = dev_name(&dev->dev); } diff --git a/drivers/base/component.c b/drivers/base/component.c index e97704104784..dcfbe7251dc4 100644 --- a/drivers/base/component.c +++ b/drivers/base/component.c @@ -256,7 +256,8 @@ static int try_to_bring_up_master(struct master *master, ret = master->ops->bind(master->dev); if (ret < 0) { devres_release_group(master->dev, NULL); - dev_info(master->dev, "master bind failed: %d\n", ret); + if (ret != -EPROBE_DEFER) + dev_info(master->dev, "master bind failed: %d\n", ret); return ret; } @@ -611,8 +612,9 @@ static int component_bind(struct component *component, struct master *master, devres_release_group(component->dev, NULL); devres_release_group(master->dev, NULL); - dev_err(master->dev, "failed to bind %s (ops %ps): %d\n", - dev_name(component->dev), component->ops, ret); + if (ret != -EPROBE_DEFER) + dev_err(master->dev, "failed to bind %s (ops %ps): %d\n", + dev_name(component->dev), component->ops, ret); } return ret; diff --git a/drivers/base/core.c b/drivers/base/core.c index 139cdf7e7327..073045cb214e 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -2370,6 +2370,11 @@ u32 fw_devlink_get_flags(void) return fw_devlink_flags; } +static bool fw_devlink_is_permissive(void) +{ + return fw_devlink_flags == DL_FLAG_SYNC_STATE_ONLY; +} + /** * device_add - add device to device hierarchy. * @dev: device. @@ -2524,7 +2529,7 @@ int device_add(struct device *dev) if (fw_devlink_flags && is_fwnode_dev && fwnode_has_op(dev->fwnode, add_links)) { fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev); - if (fw_ret == -ENODEV) + if (fw_ret == -ENODEV && !fw_devlink_is_permissive()) device_link_wait_for_mandatory_supplier(dev); else if (fw_ret) device_link_wait_for_optional_supplier(dev); diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 06ec0e851fa1..94037be7f5d7 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -224,17 +224,9 @@ static int deferred_devs_show(struct seq_file *s, void *data) } DEFINE_SHOW_ATTRIBUTE(deferred_devs); -#ifdef CONFIG_MODULES -/* - * In the case of modules, set the default probe timeout to - * 30 seconds to give userland some time to load needed modules - */ -int driver_deferred_probe_timeout = 30; -#else -/* In the case of !modules, no probe timeout needed */ -int driver_deferred_probe_timeout = -1; -#endif +int driver_deferred_probe_timeout; EXPORT_SYMBOL_GPL(driver_deferred_probe_timeout); +static DECLARE_WAIT_QUEUE_HEAD(probe_timeout_waitqueue); static int __init deferred_probe_timeout_setup(char *str) { @@ -266,8 +258,8 @@ int driver_deferred_probe_check_state(struct device *dev) return -ENODEV; } - if (!driver_deferred_probe_timeout) { - dev_WARN(dev, "deferred probe timeout, ignoring dependency"); + if (!driver_deferred_probe_timeout && initcalls_done) { + dev_warn(dev, "deferred probe timeout, ignoring dependency"); return -ETIMEDOUT; } @@ -284,6 +276,7 @@ static void deferred_probe_timeout_work_func(struct work_struct *work) list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe) dev_info(private->device, "deferred probe pending"); + wake_up(&probe_timeout_waitqueue); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); @@ -658,6 +651,9 @@ int driver_probe_done(void) */ void wait_for_device_probe(void) { + /* wait for probe timeout */ + wait_event(probe_timeout_waitqueue, !driver_deferred_probe_timeout); + /* wait for the deferred probe workqueue to finish */ flush_work(&deferred_probe_work); diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 5255550b7c34..b27d0f6c18c9 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -380,6 +380,8 @@ struct platform_object { */ static void setup_pdev_dma_masks(struct platform_device *pdev) { + pdev->dev.dma_parms = &pdev->dma_parms; + if (!pdev->dev.coherent_dma_mask) pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32); if (!pdev->dev.dma_mask) { diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 93468b7c6701..9d21bf0f155e 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -33,6 +33,15 @@ struct virtio_blk_vq { } ____cacheline_aligned_in_smp; struct virtio_blk { + /* + * This mutex must be held by anything that may run after + * virtblk_remove() sets vblk->vdev to NULL. + * + * blk-mq, virtqueue processing, and sysfs attribute code paths are + * shut down before vblk->vdev is set to NULL and therefore do not need + * to hold this mutex. + */ + struct mutex vdev_mutex; struct virtio_device *vdev; /* The disk structure for the kernel. */ @@ -44,6 +53,13 @@ struct virtio_blk { /* Process context for config space updates */ struct work_struct config_work; + /* + * Tracks references from block_device_operations open/release and + * virtio_driver probe/remove so this object can be freed once no + * longer in use. + */ + refcount_t refs; + /* What host tells us, plus 2 for header & tailer. */ unsigned int sg_elems; @@ -295,10 +311,55 @@ out: return err; } +static void virtblk_get(struct virtio_blk *vblk) +{ + refcount_inc(&vblk->refs); +} + +static void virtblk_put(struct virtio_blk *vblk) +{ + if (refcount_dec_and_test(&vblk->refs)) { + ida_simple_remove(&vd_index_ida, vblk->index); + mutex_destroy(&vblk->vdev_mutex); + kfree(vblk); + } +} + +static int virtblk_open(struct block_device *bd, fmode_t mode) +{ + struct virtio_blk *vblk = bd->bd_disk->private_data; + int ret = 0; + + mutex_lock(&vblk->vdev_mutex); + + if (vblk->vdev) + virtblk_get(vblk); + else + ret = -ENXIO; + + mutex_unlock(&vblk->vdev_mutex); + return ret; +} + +static void virtblk_release(struct gendisk *disk, fmode_t mode) +{ + struct virtio_blk *vblk = disk->private_data; + + virtblk_put(vblk); +} + /* We provide getgeo only to please some old bootloader/partitioning tools */ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) { struct virtio_blk *vblk = bd->bd_disk->private_data; + int ret = 0; + + mutex_lock(&vblk->vdev_mutex); + + if (!vblk->vdev) { + ret = -ENXIO; + goto out; + } /* see if the host passed in geometry config */ if (virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_GEOMETRY)) { @@ -314,11 +375,15 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo) geo->sectors = 1 << 5; geo->cylinders = get_capacity(bd->bd_disk) >> 11; } - return 0; +out: + mutex_unlock(&vblk->vdev_mutex); + return ret; } static const struct block_device_operations virtblk_fops = { .owner = THIS_MODULE, + .open = virtblk_open, + .release = virtblk_release, .getgeo = virtblk_getgeo, }; @@ -655,6 +720,10 @@ static int virtblk_probe(struct virtio_device *vdev) goto out_free_index; } + /* This reference is dropped in virtblk_remove(). */ + refcount_set(&vblk->refs, 1); + mutex_init(&vblk->vdev_mutex); + vblk->vdev = vdev; vblk->sg_elems = sg_elems; @@ -820,8 +889,6 @@ out: static void virtblk_remove(struct virtio_device *vdev) { struct virtio_blk *vblk = vdev->priv; - int index = vblk->index; - int refc; /* Make sure no work handler is accessing the device. */ flush_work(&vblk->config_work); @@ -831,18 +898,21 @@ static void virtblk_remove(struct virtio_device *vdev) blk_mq_free_tag_set(&vblk->tag_set); + mutex_lock(&vblk->vdev_mutex); + /* Stop all the virtqueues. */ vdev->config->reset(vdev); - refc = kref_read(&disk_to_dev(vblk->disk)->kobj.kref); + /* Virtqueues are stopped, nothing can use vblk->vdev anymore. */ + vblk->vdev = NULL; + put_disk(vblk->disk); vdev->config->del_vqs(vdev); kfree(vblk->vqs); - kfree(vblk); - /* Only free device id if we don't have any users */ - if (refc == 1) - ida_simple_remove(&vd_index_ida, index); + mutex_unlock(&vblk->vdev_mutex); + + virtblk_put(vblk); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/bus/mhi/core/init.c b/drivers/bus/mhi/core/init.c index b38359c480ea..eb2ab058a01d 100644 --- a/drivers/bus/mhi/core/init.c +++ b/drivers/bus/mhi/core/init.c @@ -812,10 +812,9 @@ int mhi_register_controller(struct mhi_controller *mhi_cntrl, if (!mhi_cntrl) return -EINVAL; - if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put) - return -EINVAL; - - if (!mhi_cntrl->status_cb || !mhi_cntrl->link_status) + if (!mhi_cntrl->runtime_get || !mhi_cntrl->runtime_put || + !mhi_cntrl->status_cb || !mhi_cntrl->read_reg || + !mhi_cntrl->write_reg) return -EINVAL; ret = parse_config(mhi_cntrl, config); diff --git a/drivers/bus/mhi/core/internal.h b/drivers/bus/mhi/core/internal.h index 5deadfaa053a..095d95bc0e37 100644 --- a/drivers/bus/mhi/core/internal.h +++ b/drivers/bus/mhi/core/internal.h @@ -11,9 +11,6 @@ extern struct bus_type mhi_bus_type; -/* MHI MMIO register mapping */ -#define PCI_INVALID_READ(val) (val == U32_MAX) - #define MHIREGLEN (0x0) #define MHIREGLEN_MHIREGLEN_MASK (0xFFFFFFFF) #define MHIREGLEN_MHIREGLEN_SHIFT (0) diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index eb4256b81406..97e06cc586e4 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -18,16 +18,7 @@ int __must_check mhi_read_reg(struct mhi_controller *mhi_cntrl, void __iomem *base, u32 offset, u32 *out) { - u32 tmp = readl(base + offset); - - /* If there is any unexpected value, query the link status */ - if (PCI_INVALID_READ(tmp) && - mhi_cntrl->link_status(mhi_cntrl)) - return -EIO; - - *out = tmp; - - return 0; + return mhi_cntrl->read_reg(mhi_cntrl, base + offset, out); } int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl, @@ -49,7 +40,7 @@ int __must_check mhi_read_reg_field(struct mhi_controller *mhi_cntrl, void mhi_write_reg(struct mhi_controller *mhi_cntrl, void __iomem *base, u32 offset, u32 val) { - writel(val, base + offset); + mhi_cntrl->write_reg(mhi_cntrl, base + offset, val); } void mhi_write_reg_field(struct mhi_controller *mhi_cntrl, void __iomem *base, @@ -294,7 +285,7 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl) !(mhi_chan->ee_mask & BIT(mhi_cntrl->ee))) continue; mhi_dev = mhi_alloc_device(mhi_cntrl); - if (!mhi_dev) + if (IS_ERR(mhi_dev)) return; mhi_dev->dev_type = MHI_DEVICE_XFER; @@ -336,7 +327,8 @@ void mhi_create_devices(struct mhi_controller *mhi_cntrl) /* Channel name is same for both UL and DL */ mhi_dev->chan_name = mhi_chan->name; - dev_set_name(&mhi_dev->dev, "%04x_%s", mhi_chan->chan, + dev_set_name(&mhi_dev->dev, "%s_%s", + dev_name(mhi_cntrl->cntrl_dev), mhi_dev->chan_name); /* Init wakeup source if available */ diff --git a/drivers/bus/mhi/core/pm.c b/drivers/bus/mhi/core/pm.c index 52690cb5c89c..dc83d65f7784 100644 --- a/drivers/bus/mhi/core/pm.c +++ b/drivers/bus/mhi/core/pm.c @@ -902,7 +902,11 @@ int mhi_sync_power_up(struct mhi_controller *mhi_cntrl) MHI_PM_IN_ERROR_STATE(mhi_cntrl->pm_state), msecs_to_jiffies(mhi_cntrl->timeout_ms)); - return (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -EIO; + ret = (MHI_IN_MISSION_MODE(mhi_cntrl->ee)) ? 0 : -ETIMEDOUT; + if (ret) + mhi_power_down(mhi_cntrl, false); + + return ret; } EXPORT_SYMBOL(mhi_sync_power_up); diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index b7145f370d3b..2704470e021d 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -1947,8 +1947,8 @@ static int ssif_adapter_handler(struct device *adev, void *opaque) if (adev->type != &i2c_adapter_type) return 0; - addr_info->added_client = i2c_new_device(to_i2c_adapter(adev), - &addr_info->binfo); + addr_info->added_client = i2c_new_client_device(to_i2c_adapter(adev), + &addr_info->binfo); if (!addr_info->adapter_name) return 1; /* Only try the first I2C adapter by default. */ diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 39c59f063aa0..2dfb30b963c4 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -3519,6 +3519,9 @@ static int __clk_core_init(struct clk_core *core) out: clk_pm_runtime_put(core); unlock: + if (ret) + hlist_del_init(&core->child_node); + clk_prepare_unlock(); if (!ret) diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c index d17cfb7a3ff4..d7243c09cc84 100644 --- a/drivers/clk/rockchip/clk-rk3228.c +++ b/drivers/clk/rockchip/clk-rk3228.c @@ -156,8 +156,6 @@ PNAME(mux_i2s_out_p) = { "i2s1_pre", "xin12m" }; PNAME(mux_i2s2_p) = { "i2s2_src", "i2s2_frac", "xin12m" }; PNAME(mux_sclk_spdif_p) = { "sclk_spdif_src", "spdif_frac", "xin12m" }; -PNAME(mux_aclk_gpu_pre_p) = { "cpll_gpu", "gpll_gpu", "hdmiphy_gpu", "usb480m_gpu" }; - PNAME(mux_uart0_p) = { "uart0_src", "uart0_frac", "xin24m" }; PNAME(mux_uart1_p) = { "uart1_src", "uart1_frac", "xin24m" }; PNAME(mux_uart2_p) = { "uart2_src", "uart2_frac", "xin24m" }; @@ -468,16 +466,9 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { RK2928_CLKSEL_CON(24), 6, 10, DFLAGS, RK2928_CLKGATE_CON(2), 8, GFLAGS), - GATE(0, "cpll_gpu", "cpll", 0, - RK2928_CLKGATE_CON(3), 13, GFLAGS), - GATE(0, "gpll_gpu", "gpll", 0, - RK2928_CLKGATE_CON(3), 13, GFLAGS), - GATE(0, "hdmiphy_gpu", "hdmiphy", 0, - RK2928_CLKGATE_CON(3), 13, GFLAGS), - GATE(0, "usb480m_gpu", "usb480m", 0, + COMPOSITE(0, "aclk_gpu_pre", mux_pll_src_4plls_p, 0, + RK2928_CLKSEL_CON(34), 5, 2, MFLAGS, 0, 5, DFLAGS, RK2928_CLKGATE_CON(3), 13, GFLAGS), - COMPOSITE_NOGATE(0, "aclk_gpu_pre", mux_aclk_gpu_pre_p, 0, - RK2928_CLKSEL_CON(34), 5, 2, MFLAGS, 0, 5, DFLAGS), COMPOSITE(SCLK_SPI0, "sclk_spi0", mux_pll_src_2plls_p, 0, RK2928_CLKSEL_CON(25), 8, 1, MFLAGS, 0, 7, DFLAGS, @@ -582,8 +573,8 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { GATE(0, "pclk_peri_noc", "pclk_peri", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(12), 2, GFLAGS), /* PD_GPU */ - GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 14, GFLAGS), - GATE(0, "aclk_gpu_noc", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(13), 15, GFLAGS), + GATE(ACLK_GPU, "aclk_gpu", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(7), 14, GFLAGS), + GATE(0, "aclk_gpu_noc", "aclk_gpu_pre", 0, RK2928_CLKGATE_CON(7), 15, GFLAGS), /* PD_BUS */ GATE(0, "sclk_initmem_mbist", "aclk_cpu", 0, RK2928_CLKGATE_CON(8), 1, GFLAGS), diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c index 64e229ddf2a5..e931319dcc9d 100644 --- a/drivers/clk/tegra/clk-tegra124.c +++ b/drivers/clk/tegra/clk-tegra124.c @@ -1292,7 +1292,7 @@ static struct tegra_clk_init_table common_init_table[] __initdata = { { TEGRA124_CLK_UARTB, TEGRA124_CLK_PLL_P, 408000000, 0 }, { TEGRA124_CLK_UARTC, TEGRA124_CLK_PLL_P, 408000000, 0 }, { TEGRA124_CLK_UARTD, TEGRA124_CLK_PLL_P, 408000000, 0 }, - { TEGRA124_CLK_PLL_A, TEGRA124_CLK_CLK_MAX, 564480000, 0 }, + { TEGRA124_CLK_PLL_A, TEGRA124_CLK_CLK_MAX, 282240000, 0 }, { TEGRA124_CLK_PLL_A_OUT0, TEGRA124_CLK_CLK_MAX, 11289600, 0 }, { TEGRA124_CLK_I2S0, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 }, { TEGRA124_CLK_I2S1, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 }, diff --git a/drivers/clk/ti/clk-33xx.c b/drivers/clk/ti/clk-33xx.c index e001b9bcb6bf..7dc30dd6c8d5 100644 --- a/drivers/clk/ti/clk-33xx.c +++ b/drivers/clk/ti/clk-33xx.c @@ -212,7 +212,7 @@ static const struct omap_clkctrl_reg_data am3_mpu_clkctrl_regs[] __initconst = { }; static const struct omap_clkctrl_reg_data am3_l4_rtc_clkctrl_regs[] __initconst = { - { AM3_L4_RTC_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clk_32768_ck" }, + { AM3_L4_RTC_RTC_CLKCTRL, NULL, CLKF_SW_SUP, "clk-24mhz-clkctrl:0000:0" }, { 0 }, }; diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index 062266034d84..864c484bde1b 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -255,24 +255,53 @@ static struct clk_hw *_ti_omap4_clkctrl_xlate(struct of_phandle_args *clkspec, return entry->clk; } +/* Get clkctrl clock base name based on clkctrl_name or dts node */ +static const char * __init clkctrl_get_clock_name(struct device_node *np, + const char *clkctrl_name, + int offset, int index, + bool legacy_naming) +{ + char *clock_name; + + /* l4per-clkctrl:1234:0 style naming based on clkctrl_name */ + if (clkctrl_name && !legacy_naming) { + clock_name = kasprintf(GFP_KERNEL, "%s-clkctrl:%04x:%d", + clkctrl_name, offset, index); + strreplace(clock_name, '_', '-'); + + return clock_name; + } + + /* l4per:1234:0 old style naming based on clkctrl_name */ + if (clkctrl_name) + return kasprintf(GFP_KERNEL, "%s_cm:clk:%04x:%d", + clkctrl_name, offset, index); + + /* l4per_cm:1234:0 old style naming based on parent node name */ + if (legacy_naming) + return kasprintf(GFP_KERNEL, "%pOFn:clk:%04x:%d", + np->parent, offset, index); + + /* l4per-clkctrl:1234:0 style naming based on node name */ + return kasprintf(GFP_KERNEL, "%pOFn:%04x:%d", np, offset, index); +} + static int __init _ti_clkctrl_clk_register(struct omap_clkctrl_provider *provider, struct device_node *node, struct clk_hw *clk_hw, u16 offset, u8 bit, const char * const *parents, - int num_parents, const struct clk_ops *ops) + int num_parents, const struct clk_ops *ops, + const char *clkctrl_name) { struct clk_init_data init = { NULL }; struct clk *clk; struct omap_clkctrl_clk *clkctrl_clk; int ret = 0; - if (ti_clk_get_features()->flags & TI_CLK_CLKCTRL_COMPAT) - init.name = kasprintf(GFP_KERNEL, "%pOFn:%pOFn:%04x:%d", - node->parent, node, offset, - bit); - else - init.name = kasprintf(GFP_KERNEL, "%pOFn:%04x:%d", node, - offset, bit); + init.name = clkctrl_get_clock_name(node, clkctrl_name, offset, bit, + ti_clk_get_features()->flags & + TI_CLK_CLKCTRL_COMPAT); + clkctrl_clk = kzalloc(sizeof(*clkctrl_clk), GFP_KERNEL); if (!init.name || !clkctrl_clk) { ret = -ENOMEM; @@ -309,7 +338,7 @@ static void __init _ti_clkctrl_setup_gate(struct omap_clkctrl_provider *provider, struct device_node *node, u16 offset, const struct omap_clkctrl_bit_data *data, - void __iomem *reg) + void __iomem *reg, const char *clkctrl_name) { struct clk_hw_omap *clk_hw; @@ -322,7 +351,7 @@ _ti_clkctrl_setup_gate(struct omap_clkctrl_provider *provider, if (_ti_clkctrl_clk_register(provider, node, &clk_hw->hw, offset, data->bit, data->parents, 1, - &omap_gate_clk_ops)) + &omap_gate_clk_ops, clkctrl_name)) kfree(clk_hw); } @@ -330,7 +359,7 @@ static void __init _ti_clkctrl_setup_mux(struct omap_clkctrl_provider *provider, struct device_node *node, u16 offset, const struct omap_clkctrl_bit_data *data, - void __iomem *reg) + void __iomem *reg, const char *clkctrl_name) { struct clk_omap_mux *mux; int num_parents = 0; @@ -357,7 +386,7 @@ _ti_clkctrl_setup_mux(struct omap_clkctrl_provider *provider, if (_ti_clkctrl_clk_register(provider, node, &mux->hw, offset, data->bit, data->parents, num_parents, - &ti_clk_mux_ops)) + &ti_clk_mux_ops, clkctrl_name)) kfree(mux); } @@ -365,7 +394,7 @@ static void __init _ti_clkctrl_setup_div(struct omap_clkctrl_provider *provider, struct device_node *node, u16 offset, const struct omap_clkctrl_bit_data *data, - void __iomem *reg) + void __iomem *reg, const char *clkctrl_name) { struct clk_omap_divider *div; const struct omap_clkctrl_div_data *div_data = data->data; @@ -393,7 +422,7 @@ _ti_clkctrl_setup_div(struct omap_clkctrl_provider *provider, if (_ti_clkctrl_clk_register(provider, node, &div->hw, offset, data->bit, data->parents, 1, - &ti_clk_divider_ops)) + &ti_clk_divider_ops, clkctrl_name)) kfree(div); } @@ -401,7 +430,7 @@ static void __init _ti_clkctrl_setup_subclks(struct omap_clkctrl_provider *provider, struct device_node *node, const struct omap_clkctrl_reg_data *data, - void __iomem *reg) + void __iomem *reg, const char *clkctrl_name) { const struct omap_clkctrl_bit_data *bits = data->bit_data; @@ -412,17 +441,17 @@ _ti_clkctrl_setup_subclks(struct omap_clkctrl_provider *provider, switch (bits->type) { case TI_CLK_GATE: _ti_clkctrl_setup_gate(provider, node, data->offset, - bits, reg); + bits, reg, clkctrl_name); break; case TI_CLK_DIVIDER: _ti_clkctrl_setup_div(provider, node, data->offset, - bits, reg); + bits, reg, clkctrl_name); break; case TI_CLK_MUX: _ti_clkctrl_setup_mux(provider, node, data->offset, - bits, reg); + bits, reg, clkctrl_name); break; default: @@ -461,42 +490,10 @@ static char * __init clkctrl_get_name(struct device_node *np) return name; } } - of_node_put(np); return NULL; } -/* Get clkctrl clock base name based on clkctrl_name or dts node */ -static const char * __init clkctrl_get_clock_name(struct device_node *np, - const char *clkctrl_name, - int offset, int index, - bool legacy_naming) -{ - char *clock_name; - - /* l4per-clkctrl:1234:0 style naming based on clkctrl_name */ - if (clkctrl_name && !legacy_naming) { - clock_name = kasprintf(GFP_KERNEL, "%s-clkctrl:%04x:%d", - clkctrl_name, offset, index); - strreplace(clock_name, '_', '-'); - - return clock_name; - } - - /* l4per:1234:0 old style naming based on clkctrl_name */ - if (clkctrl_name) - return kasprintf(GFP_KERNEL, "%s_cm:clk:%04x:%d", - clkctrl_name, offset, index); - - /* l4per_cm:1234:0 old style naming based on parent node name */ - if (legacy_naming) - return kasprintf(GFP_KERNEL, "%pOFn:clk:%04x:%d", - np->parent, offset, index); - - /* l4per-clkctrl:1234:0 style naming based on node name */ - return kasprintf(GFP_KERNEL, "%pOFn:%04x:%d", np, offset, index); -} - static void __init _ti_omap4_clkctrl_setup(struct device_node *node) { struct omap_clkctrl_provider *provider; @@ -664,7 +661,7 @@ clkdm_found: hw->enable_reg.ptr = provider->base + reg_data->offset; _ti_clkctrl_setup_subclks(provider, node, reg_data, - hw->enable_reg.ptr); + hw->enable_reg.ptr, clkctrl_name); if (reg_data->flags & CLKF_SW_SUP) hw->enable_bit = MODULEMODE_SWCTRL; diff --git a/drivers/clk/versatile/clk-impd1.c b/drivers/clk/versatile/clk-impd1.c index b05da8516d4c..f9f4babe3ca6 100644 --- a/drivers/clk/versatile/clk-impd1.c +++ b/drivers/clk/versatile/clk-impd1.c @@ -206,6 +206,7 @@ static int integrator_impd1_clk_spawn(struct device *dev, return -ENODEV; } + of_property_read_string(np, "clock-output-names", &name); parent_name = of_clk_get_parent_name(np, 0); clk = icst_clk_setup(NULL, desc, name, parent_name, map, ICST_INTEGRATOR_IM_PD1); diff --git a/drivers/crypto/chelsio/chcr_ktls.c b/drivers/crypto/chelsio/chcr_ktls.c index e92b352fb0ad..43d9e2420110 100644 --- a/drivers/crypto/chelsio/chcr_ktls.c +++ b/drivers/crypto/chelsio/chcr_ktls.c @@ -673,41 +673,14 @@ int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input) return 0; } -/* - * chcr_write_cpl_set_tcb_ulp: update tcb values. - * TCB is responsible to create tcp headers, so all the related values - * should be correctly updated. - * @tx_info - driver specific tls info. - * @q - tx queue on which packet is going out. - * @tid - TCB identifier. - * @pos - current index where should we start writing. - * @word - TCB word. - * @mask - TCB word related mask. - * @val - TCB word related value. - * @reply - set 1 if looking for TP response. - * return - next position to write. - */ -static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, - struct sge_eth_txq *q, u32 tid, - void *pos, u16 word, u64 mask, +static void *__chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, + u32 tid, void *pos, u16 word, u64 mask, u64 val, u32 reply) { struct cpl_set_tcb_field_core *cpl; struct ulptx_idata *idata; struct ulp_txpkt *txpkt; - void *save_pos = NULL; - u8 buf[48] = {0}; - int left; - left = (void *)q->q.stat - pos; - if (unlikely(left < CHCR_SET_TCB_FIELD_LEN)) { - if (!left) { - pos = q->q.desc; - } else { - save_pos = pos; - pos = buf; - } - } /* ULP_TXPKT */ txpkt = pos; txpkt->cmd_dest = htonl(ULPTX_CMD_V(ULP_TX_PKT) | ULP_TXPKT_DEST_V(0)); @@ -732,18 +705,54 @@ static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, idata = (struct ulptx_idata *)(cpl + 1); idata->cmd_more = htonl(ULPTX_CMD_V(ULP_TX_SC_NOOP)); idata->len = htonl(0); + pos = idata + 1; - if (save_pos) { - pos = chcr_copy_to_txd(buf, &q->q, save_pos, - CHCR_SET_TCB_FIELD_LEN); - } else { - /* check again if we are at the end of the queue */ - if (left == CHCR_SET_TCB_FIELD_LEN) + return pos; +} + + +/* + * chcr_write_cpl_set_tcb_ulp: update tcb values. + * TCB is responsible to create tcp headers, so all the related values + * should be correctly updated. + * @tx_info - driver specific tls info. + * @q - tx queue on which packet is going out. + * @tid - TCB identifier. + * @pos - current index where should we start writing. + * @word - TCB word. + * @mask - TCB word related mask. + * @val - TCB word related value. + * @reply - set 1 if looking for TP response. + * return - next position to write. + */ +static void *chcr_write_cpl_set_tcb_ulp(struct chcr_ktls_info *tx_info, + struct sge_eth_txq *q, u32 tid, + void *pos, u16 word, u64 mask, + u64 val, u32 reply) +{ + int left = (void *)q->q.stat - pos; + + if (unlikely(left < CHCR_SET_TCB_FIELD_LEN)) { + if (!left) { pos = q->q.desc; - else - pos = idata + 1; + } else { + u8 buf[48] = {0}; + + __chcr_write_cpl_set_tcb_ulp(tx_info, tid, buf, word, + mask, val, reply); + + return chcr_copy_to_txd(buf, &q->q, pos, + CHCR_SET_TCB_FIELD_LEN); + } } + pos = __chcr_write_cpl_set_tcb_ulp(tx_info, tid, pos, word, + mask, val, reply); + + /* check again if we are at the end of the queue */ + if (left == CHCR_SET_TCB_FIELD_LEN) + pos = q->q.desc; + return pos; } diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 31f9f0e369b9..55b031d2c989 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -16,7 +16,7 @@ int efi_tpm_final_log_size; EXPORT_SYMBOL(efi_tpm_final_log_size); -static int tpm2_calc_event_log_size(void *data, int count, void *size_info) +static int __init tpm2_calc_event_log_size(void *data, int count, void *size_info) { struct tcg_pcr_event2_head *header; int event_size, size = 0; diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index 5638b4e5355f..4269ea9a817e 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -531,7 +531,7 @@ static int pca953x_gpio_set_config(struct gpio_chip *gc, unsigned int offset, { struct pca953x_chip *chip = gpiochip_get_data(gc); - switch (config) { + switch (pinconf_to_config_param(config)) { case PIN_CONFIG_BIAS_PULL_UP: case PIN_CONFIG_BIAS_PULL_DOWN: return pca953x_gpio_set_pull_up_down(chip, offset, config); diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c index acb99eff9939..86568154cdb3 100644 --- a/drivers/gpio/gpio-tegra.c +++ b/drivers/gpio/gpio-tegra.c @@ -368,6 +368,7 @@ static void tegra_gpio_irq_shutdown(struct irq_data *d) struct tegra_gpio_info *tgi = bank->tgi; unsigned int gpio = d->hwirq; + tegra_gpio_irq_mask(d); gpiochip_unlock_as_irq(&tgi->gc, gpio); } diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 40f2d7f69be2..182136d98b97 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1158,8 +1158,19 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, struct gpioline_info *info) { struct gpio_chip *gc = desc->gdev->chip; + bool ok_for_pinctrl; unsigned long flags; + /* + * This function takes a mutex so we must check this before taking + * the spinlock. + * + * FIXME: find a non-racy way to retrieve this information. Maybe a + * lock common to both frameworks? + */ + ok_for_pinctrl = + pinctrl_gpio_can_use_line(gc->base + info->line_offset); + spin_lock_irqsave(&gpio_lock, flags); if (desc->name) { @@ -1186,7 +1197,7 @@ static void gpio_desc_to_lineinfo(struct gpio_desc *desc, test_bit(FLAG_USED_AS_IRQ, &desc->flags) || test_bit(FLAG_EXPORT, &desc->flags) || test_bit(FLAG_SYSFS, &desc->flags) || - !pinctrl_gpio_can_use_line(gc->base + info->line_offset)) + !ok_for_pinctrl) info->flags |= GPIOLINE_FLAG_KERNEL; if (test_bit(FLAG_IS_OUT, &desc->flags)) info->flags |= GPIOLINE_FLAG_IS_OUT; @@ -1227,6 +1238,7 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) void __user *ip = (void __user *)arg; struct gpio_desc *desc; __u32 offset; + int hwgpio; /* We fail any subsequent ioctl():s when the chip is gone */ if (!gc) @@ -1259,13 +1271,19 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (IS_ERR(desc)) return PTR_ERR(desc); + hwgpio = gpio_chip_hwgpio(desc); + + if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL && + test_bit(hwgpio, priv->watched_lines)) + return -EBUSY; + gpio_desc_to_lineinfo(desc, &lineinfo); if (copy_to_user(ip, &lineinfo, sizeof(lineinfo))) return -EFAULT; if (cmd == GPIO_GET_LINEINFO_WATCH_IOCTL) - set_bit(gpio_chip_hwgpio(desc), priv->watched_lines); + set_bit(hwgpio, priv->watched_lines); return 0; } else if (cmd == GPIO_GET_LINEHANDLE_IOCTL) { @@ -1280,7 +1298,12 @@ static long gpio_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (IS_ERR(desc)) return PTR_ERR(desc); - clear_bit(gpio_chip_hwgpio(desc), priv->watched_lines); + hwgpio = gpio_chip_hwgpio(desc); + + if (!test_bit(hwgpio, priv->watched_lines)) + return -EBUSY; + + clear_bit(hwgpio, priv->watched_lines); return 0; } return -EINVAL; @@ -5289,8 +5312,9 @@ static int __init gpiolib_dev_init(void) gpiolib_initialized = true; gpiochip_setup_devs(); - if (IS_ENABLED(CONFIG_OF_DYNAMIC)) - WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier)); +#if IS_ENABLED(CONFIG_OF_DYNAMIC) && IS_ENABLED(CONFIG_OF_GPIO) + WARN_ON(of_reconfig_notifier_register(&gpio_of_notifier)); +#endif /* CONFIG_OF_DYNAMIC && CONFIG_OF_GPIO */ return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 2992a49ad4a5..8ac1581a6b53 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -945,6 +945,7 @@ struct amdgpu_device { /* s3/s4 mask */ bool in_suspend; + bool in_hibernate; /* record last mm index being written through WREG32*/ unsigned long last_mm_index; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 9dff792c9290..6a5b91d23fd9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -1343,7 +1343,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( } /* Free the BO*/ - amdgpu_bo_unref(&mem->bo); + drm_gem_object_put_unlocked(&mem->bo->tbo.base); mutex_destroy(&mem->lock); kfree(mem); @@ -1688,7 +1688,8 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd, | KFD_IOC_ALLOC_MEM_FLAGS_WRITABLE | KFD_IOC_ALLOC_MEM_FLAGS_EXECUTABLE; - (*mem)->bo = amdgpu_bo_ref(bo); + drm_gem_object_get(&bo->tbo.base); + (*mem)->bo = bo; (*mem)->va = va; (*mem)->domain = (bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ? AMDGPU_GEM_DOMAIN_VRAM : AMDGPU_GEM_DOMAIN_GTT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index f84f9e35a73b..affde2de2a0d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3372,15 +3372,12 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) } } - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); - - amdgpu_amdkfd_suspend(adev, !fbcon); - amdgpu_ras_suspend(adev); r = amdgpu_device_ip_suspend_phase1(adev); + amdgpu_amdkfd_suspend(adev, !fbcon); + /* evict vram memory */ amdgpu_bo_evict_vram(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 466bfe541e45..a735d79a717b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1181,7 +1181,9 @@ static int amdgpu_pmops_freeze(struct device *dev) struct amdgpu_device *adev = drm_dev->dev_private; int r; + adev->in_hibernate = true; r = amdgpu_device_suspend(drm_dev, true); + adev->in_hibernate = false; if (r) return r; return amdgpu_asic_reset(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c index 9ae7b61f696a..25ddb482466a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c @@ -133,8 +133,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev, u32 cpp; u64 flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED | AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS | - AMDGPU_GEM_CREATE_VRAM_CLEARED | - AMDGPU_GEM_CREATE_CPU_GTT_USWC; + AMDGPU_GEM_CREATE_VRAM_CLEARED; info = drm_get_format_info(adev->ddev, mode_cmd); cpp = info->cpp[0]; diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index f92c158d89a1..0e0daf0021b6 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -4273,7 +4273,7 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, /* === CGCG /CGLS for GFX 3D Only === */ gfx_v10_0_update_3d_clock_gating(adev, enable); /* === MGCG + MGLS === */ - /* gfx_v10_0_update_medium_grain_clock_gating(adev, enable); */ + gfx_v10_0_update_medium_grain_clock_gating(adev, enable); } if (adev->cg_flags & @@ -4353,11 +4353,7 @@ static int gfx_v10_0_set_powergating_state(void *handle, switch (adev->asic_type) { case CHIP_NAVI10: case CHIP_NAVI14: - if (!enable) { - amdgpu_gfx_off_ctrl(adev, false); - cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); - } else - amdgpu_gfx_off_ctrl(adev, true); + amdgpu_gfx_off_ctrl(adev, enable); break; default: break; @@ -4918,6 +4914,19 @@ static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring, ref, mask); } +static void gfx_v10_0_ring_soft_recovery(struct amdgpu_ring *ring, + unsigned vmid) +{ + struct amdgpu_device *adev = ring->adev; + uint32_t value = 0; + + value = REG_SET_FIELD(value, SQ_CMD, CMD, 0x03); + value = REG_SET_FIELD(value, SQ_CMD, MODE, 0x01); + value = REG_SET_FIELD(value, SQ_CMD, CHECK_VMID, 1); + value = REG_SET_FIELD(value, SQ_CMD, VM_ID, vmid); + WREG32_SOC15(GC, 0, mmSQ_CMD, value); +} + static void gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev, uint32_t me, uint32_t pipe, @@ -5309,6 +5318,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = { .emit_wreg = gfx_v10_0_ring_emit_wreg, .emit_reg_wait = gfx_v10_0_ring_emit_reg_wait, .emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait, + .soft_recovery = gfx_v10_0_ring_soft_recovery, }; static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 0c390485bc10..d2d9dce68c2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1236,6 +1236,8 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc8 }, /* https://bugzilla.kernel.org/show_bug.cgi?id=207171 */ { 0x1002, 0x15dd, 0x103c, 0x83e7, 0xd3 }, + /* GFXOFF is unstable on C6 parts with a VBIOS 113-RAVEN-114 */ + { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 }, { 0, 0, 0, 0, 0 }, }; @@ -5025,10 +5027,9 @@ static int gfx_v9_0_set_powergating_state(void *handle, switch (adev->asic_type) { case CHIP_RAVEN: case CHIP_RENOIR: - if (!enable) { + if (!enable) amdgpu_gfx_off_ctrl(adev, false); - cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); - } + if (adev->pg_flags & AMD_PG_SUPPORT_RLC_SMU_HS) { gfx_v9_0_enable_sck_slow_down_on_power_up(adev, true); gfx_v9_0_enable_sck_slow_down_on_power_down(adev, true); @@ -5052,12 +5053,7 @@ static int gfx_v9_0_set_powergating_state(void *handle, amdgpu_gfx_off_ctrl(adev, true); break; case CHIP_VEGA12: - if (!enable) { - amdgpu_gfx_off_ctrl(adev, false); - cancel_delayed_work_sync(&adev->gfx.gfx_off_delay_work); - } else { - amdgpu_gfx_off_ctrl(adev, true); - } + amdgpu_gfx_off_ctrl(adev, enable); break; default: break; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 94c29b74c086..28e651b173ab 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -441,7 +441,7 @@ static void dm_vupdate_high_irq(void *interrupt_params) /** * dm_crtc_high_irq() - Handles CRTC interrupt - * @interrupt_params: ignored + * @interrupt_params: used for determining the CRTC instance * * Handles the CRTC/VSYNC interrupt by notfying DRM's VBLANK * event handler. @@ -455,70 +455,6 @@ static void dm_crtc_high_irq(void *interrupt_params) unsigned long flags; acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); - - if (acrtc) { - acrtc_state = to_dm_crtc_state(acrtc->base.state); - - DRM_DEBUG_VBL("crtc:%d, vupdate-vrr:%d\n", - acrtc->crtc_id, - amdgpu_dm_vrr_active(acrtc_state)); - - /* Core vblank handling at start of front-porch is only possible - * in non-vrr mode, as only there vblank timestamping will give - * valid results while done in front-porch. Otherwise defer it - * to dm_vupdate_high_irq after end of front-porch. - */ - if (!amdgpu_dm_vrr_active(acrtc_state)) - drm_crtc_handle_vblank(&acrtc->base); - - /* Following stuff must happen at start of vblank, for crc - * computation and below-the-range btr support in vrr mode. - */ - amdgpu_dm_crtc_handle_crc_irq(&acrtc->base); - - if (acrtc_state->stream && adev->family >= AMDGPU_FAMILY_AI && - acrtc_state->vrr_params.supported && - acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) { - spin_lock_irqsave(&adev->ddev->event_lock, flags); - mod_freesync_handle_v_update( - adev->dm.freesync_module, - acrtc_state->stream, - &acrtc_state->vrr_params); - - dc_stream_adjust_vmin_vmax( - adev->dm.dc, - acrtc_state->stream, - &acrtc_state->vrr_params.adjust); - spin_unlock_irqrestore(&adev->ddev->event_lock, flags); - } - } -} - -#if defined(CONFIG_DRM_AMD_DC_DCN) -/** - * dm_dcn_crtc_high_irq() - Handles VStartup interrupt for DCN generation ASICs - * @interrupt params - interrupt parameters - * - * Notify DRM's vblank event handler at VSTARTUP - * - * Unlike DCE hardware, we trigger the handler at VSTARTUP. at which: - * * We are close enough to VUPDATE - the point of no return for hw - * * We are in the fixed portion of variable front porch when vrr is enabled - * * We are before VUPDATE, where double-buffered vrr registers are swapped - * - * It is therefore the correct place to signal vblank, send user flip events, - * and update VRR. - */ -static void dm_dcn_crtc_high_irq(void *interrupt_params) -{ - struct common_irq_params *irq_params = interrupt_params; - struct amdgpu_device *adev = irq_params->adev; - struct amdgpu_crtc *acrtc; - struct dm_crtc_state *acrtc_state; - unsigned long flags; - - acrtc = get_crtc_by_otg_inst(adev, irq_params->irq_src - IRQ_TYPE_VBLANK); - if (!acrtc) return; @@ -528,22 +464,35 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) amdgpu_dm_vrr_active(acrtc_state), acrtc_state->active_planes); + /** + * Core vblank handling at start of front-porch is only possible + * in non-vrr mode, as only there vblank timestamping will give + * valid results while done in front-porch. Otherwise defer it + * to dm_vupdate_high_irq after end of front-porch. + */ + if (!amdgpu_dm_vrr_active(acrtc_state)) + drm_crtc_handle_vblank(&acrtc->base); + + /** + * Following stuff must happen at start of vblank, for crc + * computation and below-the-range btr support in vrr mode. + */ amdgpu_dm_crtc_handle_crc_irq(&acrtc->base); - drm_crtc_handle_vblank(&acrtc->base); + + /* BTR updates need to happen before VUPDATE on Vega and above. */ + if (adev->family < AMDGPU_FAMILY_AI) + return; spin_lock_irqsave(&adev->ddev->event_lock, flags); - if (acrtc_state->vrr_params.supported && + if (acrtc_state->stream && acrtc_state->vrr_params.supported && acrtc_state->freesync_config.state == VRR_STATE_ACTIVE_VARIABLE) { - mod_freesync_handle_v_update( - adev->dm.freesync_module, - acrtc_state->stream, - &acrtc_state->vrr_params); + mod_freesync_handle_v_update(adev->dm.freesync_module, + acrtc_state->stream, + &acrtc_state->vrr_params); - dc_stream_adjust_vmin_vmax( - adev->dm.dc, - acrtc_state->stream, - &acrtc_state->vrr_params.adjust); + dc_stream_adjust_vmin_vmax(adev->dm.dc, acrtc_state->stream, + &acrtc_state->vrr_params.adjust); } /* @@ -556,7 +505,8 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) * avoid race conditions between flip programming and completion, * which could cause too early flip completion events. */ - if (acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && + if (adev->family >= AMDGPU_FAMILY_RV && + acrtc->pflip_status == AMDGPU_FLIP_SUBMITTED && acrtc_state->active_planes == 0) { if (acrtc->event) { drm_crtc_send_vblank_event(&acrtc->base, acrtc->event); @@ -568,7 +518,6 @@ static void dm_dcn_crtc_high_irq(void *interrupt_params) spin_unlock_irqrestore(&adev->ddev->event_lock, flags); } -#endif static int dm_set_clockgating_state(void *handle, enum amd_clockgating_state state) @@ -2008,17 +1957,22 @@ void amdgpu_dm_update_connector_after_detect( dc_sink_retain(aconnector->dc_sink); if (sink->dc_edid.length == 0) { aconnector->edid = NULL; - drm_dp_cec_unset_edid(&aconnector->dm_dp_aux.aux); + if (aconnector->dc_link->aux_mode) { + drm_dp_cec_unset_edid( + &aconnector->dm_dp_aux.aux); + } } else { aconnector->edid = - (struct edid *) sink->dc_edid.raw_edid; - + (struct edid *)sink->dc_edid.raw_edid; drm_connector_update_edid_property(connector, - aconnector->edid); - drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, - aconnector->edid); + aconnector->edid); + + if (aconnector->dc_link->aux_mode) + drm_dp_cec_set_edid(&aconnector->dm_dp_aux.aux, + aconnector->edid); } + amdgpu_dm_update_freesync_caps(connector, aconnector->edid); update_connector_ext_caps(aconnector); } else { @@ -2440,8 +2394,36 @@ static int dcn10_register_irq_handlers(struct amdgpu_device *adev) c_irq_params->adev = adev; c_irq_params->irq_src = int_params.irq_source; + amdgpu_dm_irq_register_interrupt( + adev, &int_params, dm_crtc_high_irq, c_irq_params); + } + + /* Use VUPDATE_NO_LOCK interrupt on DCN, which seems to correspond to + * the regular VUPDATE interrupt on DCE. We want DC_IRQ_SOURCE_VUPDATEx + * to trigger at end of each vblank, regardless of state of the lock, + * matching DCE behaviour. + */ + for (i = DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT; + i <= DCN_1_0__SRCID__OTG0_IHC_V_UPDATE_NO_LOCK_INTERRUPT + adev->mode_info.num_crtc - 1; + i++) { + r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_DCE, i, &adev->vupdate_irq); + + if (r) { + DRM_ERROR("Failed to add vupdate irq id!\n"); + return r; + } + + int_params.int_context = INTERRUPT_HIGH_IRQ_CONTEXT; + int_params.irq_source = + dc_interrupt_to_irq_source(dc, i, 0); + + c_irq_params = &adev->dm.vupdate_params[int_params.irq_source - DC_IRQ_SOURCE_VUPDATE1]; + + c_irq_params->adev = adev; + c_irq_params->irq_src = int_params.irq_source; + amdgpu_dm_irq_register_interrupt(adev, &int_params, - dm_dcn_crtc_high_irq, c_irq_params); + dm_vupdate_high_irq, c_irq_params); } /* Use GRPH_PFLIP interrupt */ @@ -4448,10 +4430,6 @@ static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable) struct amdgpu_device *adev = crtc->dev->dev_private; int rc; - /* Do not set vupdate for DCN hardware */ - if (adev->family > AMDGPU_FAMILY_AI) - return 0; - irq_source = IRQ_TYPE_VUPDATE + acrtc->otg_inst; rc = dc_interrupt_set(adev->dm.dc, irq_source, enable) ? 0 : -EBUSY; @@ -7877,6 +7855,7 @@ static int dm_update_plane_state(struct dc *dc, struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct dm_crtc_state *dm_new_crtc_state, *dm_old_crtc_state; struct dm_plane_state *dm_new_plane_state, *dm_old_plane_state; + struct amdgpu_crtc *new_acrtc; bool needs_reset; int ret = 0; @@ -7886,9 +7865,30 @@ static int dm_update_plane_state(struct dc *dc, dm_new_plane_state = to_dm_plane_state(new_plane_state); dm_old_plane_state = to_dm_plane_state(old_plane_state); - /*TODO Implement atomic check for cursor plane */ - if (plane->type == DRM_PLANE_TYPE_CURSOR) + /*TODO Implement better atomic check for cursor plane */ + if (plane->type == DRM_PLANE_TYPE_CURSOR) { + if (!enable || !new_plane_crtc || + drm_atomic_plane_disabling(plane->state, new_plane_state)) + return 0; + + new_acrtc = to_amdgpu_crtc(new_plane_crtc); + + if ((new_plane_state->crtc_w > new_acrtc->max_cursor_width) || + (new_plane_state->crtc_h > new_acrtc->max_cursor_height)) { + DRM_DEBUG_ATOMIC("Bad cursor size %d x %d\n", + new_plane_state->crtc_w, new_plane_state->crtc_h); + return -EINVAL; + } + + if (new_plane_state->crtc_x <= -new_acrtc->max_cursor_width || + new_plane_state->crtc_y <= -new_acrtc->max_cursor_height) { + DRM_DEBUG_ATOMIC("Bad cursor position %d, %d\n", + new_plane_state->crtc_x, new_plane_state->crtc_y); + return -EINVAL; + } + return 0; + } needs_reset = should_reset_plane(state, plane, old_plane_state, new_plane_state); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 78e1c11d4ae5..dcf84a61de37 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -398,15 +398,15 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) struct mod_hdcp_display *display = &hdcp_work[link_index].display; struct mod_hdcp_link *link = &hdcp_work[link_index].link; - memset(display, 0, sizeof(*display)); - memset(link, 0, sizeof(*link)); - - display->index = aconnector->base.index; - if (config->dpms_off) { hdcp_remove_display(hdcp_work, link_index, aconnector); return; } + + memset(display, 0, sizeof(*display)); + memset(link, 0, sizeof(*link)); + + display->index = aconnector->base.index; display->state = MOD_HDCP_DISPLAY_ACTIVE; if (aconnector->dc_sink != NULL) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 8489f1e56892..47431ca6986d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -834,11 +834,10 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context) static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context) { int i; - int count = 0; - struct pipe_ctx *pipe; PERF_TRACE(); for (i = 0; i < MAX_PIPES; i++) { - pipe = &context->res_ctx.pipe_ctx[i]; + int count = 0; + struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i]; if (!pipe->plane_state) continue; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index c3535bd3965b..e4348e3b6389 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3068,25 +3068,32 @@ validate_out: return out; } - -bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, - bool fast_validate) +/* + * This must be noinline to ensure anything that deals with FP registers + * is contained within this call; previously our compiling with hard-float + * would result in fp instructions being emitted outside of the boundaries + * of the DC_FP_START/END macros, which makes sense as the compiler has no + * idea about what is wrapped and what is not + * + * This is largely just a workaround to avoid breakage introduced with 5.6, + * ideally all fp-using code should be moved into its own file, only that + * should be compiled with hard-float, and all code exported from there + * should be strictly wrapped with DC_FP_START/END + */ +static noinline bool dcn20_validate_bandwidth_fp(struct dc *dc, + struct dc_state *context, bool fast_validate) { bool voltage_supported = false; bool full_pstate_supported = false; bool dummy_pstate_supported = false; double p_state_latency_us; - DC_FP_START(); p_state_latency_us = context->bw_ctx.dml.soc.dram_clock_change_latency_us; context->bw_ctx.dml.soc.disable_dram_clock_change_vactive_support = dc->debug.disable_dram_clock_change_vactive_support; if (fast_validate) { - voltage_supported = dcn20_validate_bandwidth_internal(dc, context, true); - - DC_FP_END(); - return voltage_supported; + return dcn20_validate_bandwidth_internal(dc, context, true); } // Best case, we support full UCLK switch latency @@ -3115,7 +3122,15 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, restore_dml_state: context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us; + return voltage_supported; +} +bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, + bool fast_validate) +{ + bool voltage_supported = false; + DC_FP_START(); + voltage_supported = dcn20_validate_bandwidth_fp(dc, context, fast_validate); DC_FP_END(); return voltage_supported; } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index a38baa73d484..b8ec08e3b7a3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -1200,7 +1200,7 @@ static void dml_rq_dlg_get_dlg_params( min_hratio_fact_l = 1.0; min_hratio_fact_c = 1.0; - if (htaps_l <= 1) + if (hratio_l <= 1) min_hratio_fact_l = 2.0; else if (htaps_l <= 6) { if ((hratio_l * 2.0) > 4.0) @@ -1216,7 +1216,7 @@ static void dml_rq_dlg_get_dlg_params( hscale_pixel_rate_l = min_hratio_fact_l * dppclk_freq_in_mhz; - if (htaps_c <= 1) + if (hratio_c <= 1) min_hratio_fact_c = 2.0; else if (htaps_c <= 6) { if ((hratio_c * 2.0) > 4.0) @@ -1522,8 +1522,8 @@ static void dml_rq_dlg_get_dlg_params( disp_dlg_regs->refcyc_per_vm_group_vblank = get_refcyc_per_vm_group_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; disp_dlg_regs->refcyc_per_vm_group_flip = get_refcyc_per_vm_group_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; - disp_dlg_regs->refcyc_per_vm_req_vblank = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; - disp_dlg_regs->refcyc_per_vm_req_flip = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz; + disp_dlg_regs->refcyc_per_vm_req_vblank = get_refcyc_per_vm_req_vblank(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10); + disp_dlg_regs->refcyc_per_vm_req_flip = get_refcyc_per_vm_req_flip(mode_lib, e2e_pipe_param, num_pipes, pipe_idx) * refclk_freq_in_mhz * dml_pow(2, 10); // Clamp to max for now if (disp_dlg_regs->refcyc_per_vm_group_vblank >= (unsigned int)dml_pow(2, 23)) diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h index c34eba19860a..6d7bca562eec 100644 --- a/drivers/gpu/drm/amd/display/dc/os_types.h +++ b/drivers/gpu/drm/amd/display/dc/os_types.h @@ -108,7 +108,7 @@ #define ASSERT(expr) ASSERT_CRITICAL(expr) #else -#define ASSERT(expr) WARN_ON(!(expr)) +#define ASSERT(expr) WARN_ON_ONCE(!(expr)) #endif #define BREAK_TO_DEBUGGER() ASSERT(0) diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c index e4e5a53b2b4e..8e2acb4df860 100644 --- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c @@ -319,12 +319,12 @@ static void pp_dpm_en_umd_pstate(struct pp_hwmgr *hwmgr, if (*level & profile_mode_mask) { hwmgr->saved_dpm_level = hwmgr->dpm_level; hwmgr->en_umd_pstate = true; - amdgpu_device_ip_set_clockgating_state(hwmgr->adev, - AMD_IP_BLOCK_TYPE_GFX, - AMD_CG_STATE_UNGATE); amdgpu_device_ip_set_powergating_state(hwmgr->adev, AMD_IP_BLOCK_TYPE_GFX, AMD_PG_STATE_UNGATE); + amdgpu_device_ip_set_clockgating_state(hwmgr->adev, + AMD_IP_BLOCK_TYPE_GFX, + AMD_CG_STATE_UNGATE); } } else { /* exit umd pstate, restore level, enable gfx cg*/ diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index e8b27fab6aa1..e77046931e4c 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -1476,7 +1476,7 @@ static int smu_disable_dpm(struct smu_context *smu) bool use_baco = !smu->is_apu && ((adev->in_gpu_reset && (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) || - (adev->in_runpm && amdgpu_asic_supports_baco(adev))); + ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev))); ret = smu_get_smc_version(smu, NULL, &smu_version); if (ret) { @@ -1744,12 +1744,12 @@ static int smu_enable_umd_pstate(void *handle, if (*level & profile_mode_mask) { smu_dpm_ctx->saved_dpm_level = smu_dpm_ctx->dpm_level; smu_dpm_ctx->enable_umd_pstate = true; - amdgpu_device_ip_set_clockgating_state(smu->adev, - AMD_IP_BLOCK_TYPE_GFX, - AMD_CG_STATE_UNGATE); amdgpu_device_ip_set_powergating_state(smu->adev, AMD_IP_BLOCK_TYPE_GFX, AMD_PG_STATE_UNGATE); + amdgpu_device_ip_set_clockgating_state(smu->adev, + AMD_IP_BLOCK_TYPE_GFX, + AMD_CG_STATE_UNGATE); } } else { /* exit umd pstate, restore level, enable gfx cg*/ diff --git a/drivers/gpu/drm/drm_hdcp.c b/drivers/gpu/drm/drm_hdcp.c index 7f386adcf872..910108ccaae1 100644 --- a/drivers/gpu/drm/drm_hdcp.c +++ b/drivers/gpu/drm/drm_hdcp.c @@ -241,8 +241,12 @@ static int drm_hdcp_request_srm(struct drm_device *drm_dev, ret = request_firmware_direct(&fw, (const char *)fw_name, drm_dev->dev); - if (ret < 0) + if (ret < 0) { + *revoked_ksv_cnt = 0; + *revoked_ksv_list = NULL; + ret = 0; goto exit; + } if (fw->size && fw->data) ret = drm_hdcp_srm_update(fw->data, fw->size, revoked_ksv_list, @@ -287,6 +291,8 @@ int drm_hdcp_check_ksvs_revoked(struct drm_device *drm_dev, u8 *ksvs, ret = drm_hdcp_request_srm(drm_dev, &revoked_ksv_list, &revoked_ksv_cnt); + if (ret) + return ret; /* revoked_ksv_cnt will be zero when above function failed */ for (i = 0; i < revoked_ksv_cnt; i++) diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 2e5d835a9eaa..c125ca9ab9b3 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -485,8 +485,7 @@ static int intel_fbc_alloc_cfb(struct drm_i915_private *dev_priv, if (!ret) goto err_llb; else if (ret > 1) { - DRM_INFO("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); - + DRM_INFO_ONCE("Reducing the compressed framebuffer size. This may lead to less power savings than a non-reduced-size. Try to increase stolen memory size if available in BIOS.\n"); } fbc->threshold = ret; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index 0cc40e77bbd2..4f96c8788a2e 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -368,7 +368,6 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) struct drm_i915_private *i915 = to_i915(obj->base.dev); struct i915_vma *vma; - GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj)); if (!atomic_read(&obj->bind_count)) return; @@ -400,12 +399,8 @@ static void i915_gem_object_bump_inactive_ggtt(struct drm_i915_gem_object *obj) void i915_gem_object_unpin_from_display_plane(struct i915_vma *vma) { - struct drm_i915_gem_object *obj = vma->obj; - - assert_object_held(obj); - /* Bump the LRU to try and avoid premature eviction whilst flipping */ - i915_gem_object_bump_inactive_ggtt(obj); + i915_gem_object_bump_inactive_ggtt(vma->obj); i915_vma_unpin(vma); } diff --git a/drivers/gpu/drm/i915/gt/intel_context_types.h b/drivers/gpu/drm/i915/gt/intel_context_types.h index 07cb83a0d017..ca0d4f4f3615 100644 --- a/drivers/gpu/drm/i915/gt/intel_context_types.h +++ b/drivers/gpu/drm/i915/gt/intel_context_types.h @@ -69,7 +69,13 @@ struct intel_context { #define CONTEXT_NOPREEMPT 7 u32 *lrc_reg_state; - u64 lrc_desc; + union { + struct { + u32 lrca; + u32 ccid; + }; + u64 desc; + } lrc; u32 tag; /* cookie passed to HW to track this context on submission */ /* Time on GPU as tracked by the hw. */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index b469de0dd9b6..a1aa0d3e8be1 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -333,13 +333,4 @@ intel_engine_has_preempt_reset(const struct intel_engine_cs *engine) return intel_engine_has_preemption(engine); } -static inline bool -intel_engine_has_timeslices(const struct intel_engine_cs *engine) -{ - if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) - return false; - - return intel_engine_has_semaphores(engine); -} - #endif /* _INTEL_RINGBUFFER_H_ */ diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 3aa8a652c16d..883a9b7fe88d 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -1295,6 +1295,12 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine, if (engine->id == RENDER_CLASS && IS_GEN_RANGE(dev_priv, 4, 7)) drm_printf(m, "\tCCID: 0x%08x\n", ENGINE_READ(engine, CCID)); + if (HAS_EXECLISTS(dev_priv)) { + drm_printf(m, "\tEL_STAT_HI: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_HI)); + drm_printf(m, "\tEL_STAT_LO: 0x%08x\n", + ENGINE_READ(engine, RING_EXECLIST_STATUS_LO)); + } drm_printf(m, "\tRING_START: 0x%08x\n", ENGINE_READ(engine, RING_START)); drm_printf(m, "\tRING_HEAD: 0x%08x\n", diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 80cdde712842..0be674ae1cf6 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -157,6 +157,20 @@ struct intel_engine_execlists { struct i915_priolist default_priolist; /** + * @ccid: identifier for contexts submitted to this engine + */ + u32 ccid; + + /** + * @yield: CCID at the time of the last semaphore-wait interrupt. + * + * Instead of leaving a semaphore busy-spinning on an engine, we would + * like to switch to another ready context, i.e. yielding the semaphore + * timeslice. + */ + u32 yield; + + /** * @error_interrupt: CS Master EIR * * The CS generates an interrupt when it detects an error. We capture @@ -295,8 +309,7 @@ struct intel_engine_cs { u32 context_size; u32 mmio_base; - unsigned int context_tag; -#define NUM_CONTEXT_TAG roundup_pow_of_two(2 * EXECLIST_MAX_PORTS) + unsigned long context_tag; struct rb_node uabi_node; @@ -483,10 +496,11 @@ struct intel_engine_cs { #define I915_ENGINE_SUPPORTS_STATS BIT(1) #define I915_ENGINE_HAS_PREEMPTION BIT(2) #define I915_ENGINE_HAS_SEMAPHORES BIT(3) -#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4) -#define I915_ENGINE_IS_VIRTUAL BIT(5) -#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6) -#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7) +#define I915_ENGINE_HAS_TIMESLICES BIT(4) +#define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(5) +#define I915_ENGINE_IS_VIRTUAL BIT(6) +#define I915_ENGINE_HAS_RELATIVE_MMIO BIT(7) +#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(8) unsigned int flags; /* @@ -585,6 +599,15 @@ intel_engine_has_semaphores(const struct intel_engine_cs *engine) } static inline bool +intel_engine_has_timeslices(const struct intel_engine_cs *engine) +{ + if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + return false; + + return engine->flags & I915_ENGINE_HAS_TIMESLICES; +} + +static inline bool intel_engine_needs_breadcrumb_tasklet(const struct intel_engine_cs *engine) { return engine->flags & I915_ENGINE_NEEDS_BREADCRUMB_TASKLET; diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index f0e7fd95165a..0cc7dd54f4f9 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -39,6 +39,15 @@ cs_irq_handler(struct intel_engine_cs *engine, u32 iir) } } + if (iir & GT_WAIT_SEMAPHORE_INTERRUPT) { + WRITE_ONCE(engine->execlists.yield, + ENGINE_READ_FW(engine, RING_EXECLIST_STATUS_HI)); + ENGINE_TRACE(engine, "semaphore yield: %08x\n", + engine->execlists.yield); + if (del_timer(&engine->execlists.timer)) + tasklet = true; + } + if (iir & GT_CONTEXT_SWITCH_INTERRUPT) tasklet = true; @@ -228,7 +237,8 @@ void gen11_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; struct intel_uncore *uncore = gt->uncore; const u32 dmask = irqs << 16 | irqs; const u32 smask = irqs << 16; @@ -366,7 +376,8 @@ void gen8_gt_irq_postinstall(struct intel_gt *gt) const u32 irqs = GT_CS_MASTER_ERROR_INTERRUPT | GT_RENDER_USER_INTERRUPT | - GT_CONTEXT_SWITCH_INTERRUPT; + GT_CONTEXT_SWITCH_INTERRUPT | + GT_WAIT_SEMAPHORE_INTERRUPT; const u32 gt_interrupts[] = { irqs << GEN8_RCS_IRQ_SHIFT | irqs << GEN8_BCS_IRQ_SHIFT, irqs << GEN8_VCS0_IRQ_SHIFT | irqs << GEN8_VCS1_IRQ_SHIFT, diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 683014e7bc51..2dfaddb8811e 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -456,10 +456,10 @@ assert_priority_queue(const struct i915_request *prev, * engine info, SW context ID and SW counter need to form a unique number * (Context ID) per lrc. */ -static u64 +static u32 lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine) { - u64 desc; + u32 desc; desc = INTEL_LEGACY_32B_CONTEXT; if (i915_vm_is_4lvl(ce->vm)) @@ -470,21 +470,7 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine) if (IS_GEN(engine->i915, 8)) desc |= GEN8_CTX_L3LLC_COHERENT; - desc |= i915_ggtt_offset(ce->state); /* bits 12-31 */ - /* - * The following 32bits are copied into the OA reports (dword 2). - * Consider updating oa_get_render_ctx_id in i915_perf.c when changing - * anything below. - */ - if (INTEL_GEN(engine->i915) >= 11) { - desc |= (u64)engine->instance << GEN11_ENGINE_INSTANCE_SHIFT; - /* bits 48-53 */ - - desc |= (u64)engine->class << GEN11_ENGINE_CLASS_SHIFT; - /* bits 61-63 */ - } - - return desc; + return i915_ggtt_offset(ce->state) | desc; } static inline unsigned int dword_in_page(void *addr) @@ -1192,7 +1178,7 @@ static void reset_active(struct i915_request *rq, __execlists_update_reg_state(ce, engine, head); /* We've switched away, so this should be a no-op, but intent matters */ - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; } static u32 intel_context_get_runtime(const struct intel_context *ce) @@ -1251,18 +1237,23 @@ __execlists_schedule_in(struct i915_request *rq) if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)) execlists_check_context(ce, engine); - ce->lrc_desc &= ~GENMASK_ULL(47, 37); if (ce->tag) { /* Use a fixed tag for OA and friends */ - ce->lrc_desc |= (u64)ce->tag << 32; + GEM_BUG_ON(ce->tag <= BITS_PER_LONG); + ce->lrc.ccid = ce->tag; } else { /* We don't need a strict matching tag, just different values */ - ce->lrc_desc |= - (u64)(++engine->context_tag % NUM_CONTEXT_TAG) << - GEN11_SW_CTX_ID_SHIFT; - BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID); + unsigned int tag = ffs(engine->context_tag); + + GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG); + clear_bit(tag - 1, &engine->context_tag); + ce->lrc.ccid = tag << (GEN11_SW_CTX_ID_SHIFT - 32); + + BUILD_BUG_ON(BITS_PER_LONG > GEN12_MAX_CONTEXT_HW_ID); } + ce->lrc.ccid |= engine->execlists.ccid; + __intel_gt_pm_get(engine->gt); execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN); intel_engine_context_in(engine); @@ -1302,7 +1293,8 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce) static inline void __execlists_schedule_out(struct i915_request *rq, - struct intel_engine_cs * const engine) + struct intel_engine_cs * const engine, + unsigned int ccid) { struct intel_context * const ce = rq->context; @@ -1320,6 +1312,14 @@ __execlists_schedule_out(struct i915_request *rq, i915_request_completed(rq)) intel_engine_add_retire(engine, ce->timeline); + ccid >>= GEN11_SW_CTX_ID_SHIFT - 32; + ccid &= GEN12_MAX_CONTEXT_HW_ID; + if (ccid < BITS_PER_LONG) { + GEM_BUG_ON(ccid == 0); + GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag)); + set_bit(ccid - 1, &engine->context_tag); + } + intel_context_update_runtime(ce); intel_engine_context_out(engine); execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT); @@ -1345,15 +1345,17 @@ execlists_schedule_out(struct i915_request *rq) { struct intel_context * const ce = rq->context; struct intel_engine_cs *cur, *old; + u32 ccid; trace_i915_request_out(rq); + ccid = rq->context->lrc.ccid; old = READ_ONCE(ce->inflight); do cur = ptr_unmask_bits(old, 2) ? ptr_dec(old) : NULL; while (!try_cmpxchg(&ce->inflight, &old, cur)); if (!cur) - __execlists_schedule_out(rq, old); + __execlists_schedule_out(rq, old, ccid); i915_request_put(rq); } @@ -1361,7 +1363,7 @@ execlists_schedule_out(struct i915_request *rq) static u64 execlists_update_context(struct i915_request *rq) { struct intel_context *ce = rq->context; - u64 desc = ce->lrc_desc; + u64 desc = ce->lrc.desc; u32 tail, prev; /* @@ -1400,7 +1402,7 @@ static u64 execlists_update_context(struct i915_request *rq) */ wmb(); - ce->lrc_desc &= ~CTX_DESC_FORCE_RESTORE; + ce->lrc.desc &= ~CTX_DESC_FORCE_RESTORE; return desc; } @@ -1719,6 +1721,9 @@ static void defer_request(struct i915_request *rq, struct list_head * const pl) struct i915_request *w = container_of(p->waiter, typeof(*w), sched); + if (p->flags & I915_DEPENDENCY_WEAK) + continue; + /* Leave semaphores spinning on the other engines */ if (w->engine != rq->engine) continue; @@ -1754,7 +1759,8 @@ static void defer_active(struct intel_engine_cs *engine) } static bool -need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) +need_timeslice(const struct intel_engine_cs *engine, + const struct i915_request *rq) { int hint; @@ -1768,6 +1774,32 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq) return hint >= effective_prio(rq); } +static bool +timeslice_yield(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + /* + * Once bitten, forever smitten! + * + * If the active context ever busy-waited on a semaphore, + * it will be treated as a hog until the end of its timeslice (i.e. + * until it is scheduled out and replaced by a new submission, + * possibly even its own lite-restore). The HW only sends an interrupt + * on the first miss, and we do know if that semaphore has been + * signaled, or even if it is now stuck on another semaphore. Play + * safe, yield if it might be stuck -- it will be given a fresh + * timeslice in the near future. + */ + return rq->context->lrc.ccid == READ_ONCE(el->yield); +} + +static bool +timeslice_expired(const struct intel_engine_execlists *el, + const struct i915_request *rq) +{ + return timer_expired(&el->timer) || timeslice_yield(el, rq); +} + static int switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq) { @@ -1783,8 +1815,7 @@ timeslice(const struct intel_engine_cs *engine) return READ_ONCE(engine->props.timeslice_duration_ms); } -static unsigned long -active_timeslice(const struct intel_engine_cs *engine) +static unsigned long active_timeslice(const struct intel_engine_cs *engine) { const struct intel_engine_execlists *execlists = &engine->execlists; const struct i915_request *rq = *execlists->active; @@ -1946,13 +1977,14 @@ static void execlists_dequeue(struct intel_engine_cs *engine) last = NULL; } else if (need_timeslice(engine, last) && - timer_expired(&engine->execlists.timer)) { + timeslice_expired(execlists, last)) { ENGINE_TRACE(engine, - "expired last=%llx:%lld, prio=%d, hint=%d\n", + "expired last=%llx:%lld, prio=%d, hint=%d, yield?=%s\n", last->fence.context, last->fence.seqno, last->sched.attr.priority, - execlists->queue_priority_hint); + execlists->queue_priority_hint, + yesno(timeslice_yield(execlists, last))); ring_set_paused(engine, 1); defer_active(engine); @@ -2213,6 +2245,7 @@ done: } clear_ports(port + 1, last_port - port); + WRITE_ONCE(execlists->yield, -1); execlists_submit_ports(engine); set_preempt_timeout(engine, *active); } else { @@ -3043,7 +3076,7 @@ __execlists_context_pin(struct intel_context *ce, if (IS_ERR(vaddr)) return PTR_ERR(vaddr); - ce->lrc_desc = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; + ce->lrc.lrca = lrc_descriptor(ce, engine) | CTX_DESC_FORCE_RESTORE; ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE; __execlists_update_reg_state(ce, engine, ce->ring->tail); @@ -3072,7 +3105,7 @@ static void execlists_context_reset(struct intel_context *ce) ce, ce->engine, ce->ring, true); __execlists_update_reg_state(ce, ce->engine, ce->ring->tail); - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; } static const struct intel_context_ops execlists_context_ops = { @@ -3541,7 +3574,7 @@ static void enable_execlists(struct intel_engine_cs *engine) enable_error_interrupt(engine); - engine->context_tag = 0; + engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0); } static bool unexpected_starting_state(struct intel_engine_cs *engine) @@ -3753,7 +3786,7 @@ out_replay: head, ce->ring->tail); __execlists_reset_reg_state(ce, engine); __execlists_update_reg_state(ce, engine, head); - ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ + ce->lrc.desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */ unwind: /* Push back any incomplete requests for replay after the reset. */ @@ -4369,8 +4402,11 @@ void intel_execlists_set_default_submission(struct intel_engine_cs *engine) engine->flags |= I915_ENGINE_SUPPORTS_STATS; if (!intel_vgpu_active(engine->i915)) { engine->flags |= I915_ENGINE_HAS_SEMAPHORES; - if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) + if (HAS_LOGICAL_RING_PREEMPTION(engine->i915)) { engine->flags |= I915_ENGINE_HAS_PREEMPTION; + if (IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION)) + engine->flags |= I915_ENGINE_HAS_TIMESLICES; + } } if (INTEL_GEN(engine->i915) >= 12) @@ -4449,6 +4485,7 @@ logical_ring_default_irqs(struct intel_engine_cs *engine) engine->irq_enable_mask = GT_RENDER_USER_INTERRUPT << shift; engine->irq_keep_mask = GT_CONTEXT_SWITCH_INTERRUPT << shift; engine->irq_keep_mask |= GT_CS_MASTER_ERROR_INTERRUPT << shift; + engine->irq_keep_mask |= GT_WAIT_SEMAPHORE_INTERRUPT << shift; } static void rcs_submission_override(struct intel_engine_cs *engine) @@ -4516,6 +4553,11 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) else execlists->csb_size = GEN11_CSB_ENTRIES; + if (INTEL_GEN(engine->i915) >= 11) { + execlists->ccid |= engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32); + execlists->ccid |= engine->class << (GEN11_ENGINE_CLASS_SHIFT - 32); + } + reset_csb_pointers(engine); /* Finally, take ownership and responsibility for cleanup! */ diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 6f06ba750a0a..f95ae15ce865 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -929,7 +929,7 @@ create_rewinder(struct intel_context *ce, goto err; } - cs = intel_ring_begin(rq, 10); + cs = intel_ring_begin(rq, 14); if (IS_ERR(cs)) { err = PTR_ERR(cs); goto err; @@ -941,8 +941,8 @@ create_rewinder(struct intel_context *ce, *cs++ = MI_SEMAPHORE_WAIT | MI_SEMAPHORE_GLOBAL_GTT | MI_SEMAPHORE_POLL | - MI_SEMAPHORE_SAD_NEQ_SDD; - *cs++ = 0; + MI_SEMAPHORE_SAD_GTE_SDD; + *cs++ = idx; *cs++ = offset; *cs++ = 0; @@ -951,6 +951,11 @@ create_rewinder(struct intel_context *ce, *cs++ = offset + idx * sizeof(u32); *cs++ = 0; + *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; + *cs++ = offset; + *cs++ = 0; + *cs++ = idx + 1; + intel_ring_advance(rq, cs); rq->sched.attr.priority = I915_PRIORITY_MASK; @@ -984,7 +989,7 @@ static int live_timeslice_rewind(void *arg) for_each_engine(engine, gt, id) { enum { A1, A2, B1 }; - enum { X = 1, Y, Z }; + enum { X = 1, Z, Y }; struct i915_request *rq[3] = {}; struct intel_context *ce; unsigned long heartbeat; @@ -1017,13 +1022,13 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[0] = create_rewinder(ce, NULL, slot, 1); + rq[0] = create_rewinder(ce, NULL, slot, X); if (IS_ERR(rq[0])) { intel_context_put(ce); goto err; } - rq[1] = create_rewinder(ce, NULL, slot, 2); + rq[1] = create_rewinder(ce, NULL, slot, Y); intel_context_put(ce); if (IS_ERR(rq[1])) goto err; @@ -1041,7 +1046,7 @@ static int live_timeslice_rewind(void *arg) goto err; } - rq[2] = create_rewinder(ce, rq[0], slot, 3); + rq[2] = create_rewinder(ce, rq[0], slot, Z); intel_context_put(ce); if (IS_ERR(rq[2])) goto err; @@ -1055,15 +1060,12 @@ static int live_timeslice_rewind(void *arg) GEM_BUG_ON(!timer_pending(&engine->execlists.timer)); /* ELSP[] = { { A:rq1, A:rq2 }, { B:rq1 } } */ - GEM_BUG_ON(!i915_request_is_active(rq[A1])); - GEM_BUG_ON(!i915_request_is_active(rq[A2])); - GEM_BUG_ON(!i915_request_is_active(rq[B1])); - - /* Wait for the timeslice to kick in */ - del_timer(&engine->execlists.timer); - tasklet_hi_schedule(&engine->execlists.tasklet); - intel_engine_flush_submission(engine); - + if (i915_request_is_active(rq[A2])) { /* semaphore yielded! */ + /* Wait for the timeslice to kick in */ + del_timer(&engine->execlists.timer); + tasklet_hi_schedule(&engine->execlists.tasklet); + intel_engine_flush_submission(engine); + } /* -> ELSP[] = { { A:rq1 }, { B:rq1 } } */ GEM_BUG_ON(!i915_request_is_active(rq[A1])); GEM_BUG_ON(!i915_request_is_active(rq[B1])); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index fe7778c28d2d..aa6d56e25a10 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -217,7 +217,7 @@ static void guc_wq_item_append(struct intel_guc *guc, static void guc_add_request(struct intel_guc *guc, struct i915_request *rq) { struct intel_engine_cs *engine = rq->engine; - u32 ctx_desc = lower_32_bits(rq->context->lrc_desc); + u32 ctx_desc = rq->context->lrc.ccid; u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64); guc_wq_item_append(guc, engine->guc_id, ctx_desc, diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index a83df2f84eb9..a1696e9ce4b6 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -208,14 +208,41 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) SKL_FUSE_PG_DIST_STATUS(SKL_PG0) | SKL_FUSE_PG_DIST_STATUS(SKL_PG1) | SKL_FUSE_PG_DIST_STATUS(SKL_PG2); - vgpu_vreg_t(vgpu, LCPLL1_CTL) |= - LCPLL_PLL_ENABLE | - LCPLL_PLL_LOCK; - vgpu_vreg_t(vgpu, LCPLL2_CTL) |= LCPLL_PLL_ENABLE; - + /* + * Only 1 PIPE enabled in current vGPU display and PIPE_A is + * tied to TRANSCODER_A in HW, so it's safe to assume PIPE_A, + * TRANSCODER_A can be enabled. PORT_x depends on the input of + * setup_virtual_dp_monitor, we can bind DPLL0 to any PORT_x + * so we fixed to DPLL0 here. + * Setup DPLL0: DP link clk 1620 MHz, non SSC, DP Mode + */ + vgpu_vreg_t(vgpu, DPLL_CTRL1) = + DPLL_CTRL1_OVERRIDE(DPLL_ID_SKL_DPLL0); + vgpu_vreg_t(vgpu, DPLL_CTRL1) |= + DPLL_CTRL1_LINK_RATE(DPLL_CTRL1_LINK_RATE_1620, DPLL_ID_SKL_DPLL0); + vgpu_vreg_t(vgpu, LCPLL1_CTL) = + LCPLL_PLL_ENABLE | LCPLL_PLL_LOCK; + vgpu_vreg_t(vgpu, DPLL_STATUS) = DPLL_LOCK(DPLL_ID_SKL_DPLL0); + /* + * Golden M/N are calculated based on: + * 24 bpp, 4 lanes, 154000 pixel clk (from virtual EDID), + * DP link clk 1620 MHz and non-constant_n. + * TODO: calculate DP link symbol clk and stream clk m/n. + */ + vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) = 63 << TU_SIZE_SHIFT; + vgpu_vreg_t(vgpu, PIPE_DATA_M1(TRANSCODER_A)) |= 0x5b425e; + vgpu_vreg_t(vgpu, PIPE_DATA_N1(TRANSCODER_A)) = 0x800000; + vgpu_vreg_t(vgpu, PIPE_LINK_M1(TRANSCODER_A)) = 0x3cd6e; + vgpu_vreg_t(vgpu, PIPE_LINK_N1(TRANSCODER_A)) = 0x80000; } if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) { + vgpu_vreg_t(vgpu, DPLL_CTRL2) &= + ~DPLL_CTRL2_DDI_CLK_OFF(PORT_B); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_B); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_B); vgpu_vreg_t(vgpu, SFUSE_STRAP) |= SFUSE_STRAP_DDIB_DETECTED; vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &= ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | @@ -236,6 +263,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) } if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) { + vgpu_vreg_t(vgpu, DPLL_CTRL2) &= + ~DPLL_CTRL2_DDI_CLK_OFF(PORT_C); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_C); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_C); vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTC_HOTPLUG_CPT; vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &= ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | @@ -256,6 +289,12 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu) } if (intel_vgpu_has_monitor_on_port(vgpu, PORT_D)) { + vgpu_vreg_t(vgpu, DPLL_CTRL2) &= + ~DPLL_CTRL2_DDI_CLK_OFF(PORT_D); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_CLK_SEL(DPLL_ID_SKL_DPLL0, PORT_D); + vgpu_vreg_t(vgpu, DPLL_CTRL2) |= + DPLL_CTRL2_DDI_SEL_OVERRIDE(PORT_D); vgpu_vreg_t(vgpu, SDEISR) |= SDE_PORTD_HOTPLUG_CPT; vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) &= ~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK | diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index cb11c3184085..e92ed96c9b23 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -290,7 +290,7 @@ static void shadow_context_descriptor_update(struct intel_context *ce, struct intel_vgpu_workload *workload) { - u64 desc = ce->lrc_desc; + u64 desc = ce->lrc.desc; /* * Update bits 0-11 of the context descriptor which includes flags @@ -300,7 +300,7 @@ shadow_context_descriptor_update(struct intel_context *ce, desc |= (u64)workload->ctx_desc.addressing_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT; - ce->lrc_desc = desc; + ce->lrc.desc = desc; } static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload) @@ -379,7 +379,11 @@ static void set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload, for (i = 0; i < GVT_RING_CTX_NR_PDPS; i++) { struct i915_page_directory * const pd = i915_pd_entry(ppgtt->pd, i); - + /* skip now as current i915 ppgtt alloc won't allocate + top level pdp for non 4-level table, won't impact + shadow ppgtt. */ + if (!pd) + break; px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i]; } } diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c index 4518b9b35c3d..02ad1acd117c 100644 --- a/drivers/gpu/drm/i915/i915_gem_evict.c +++ b/drivers/gpu/drm/i915/i915_gem_evict.c @@ -128,6 +128,13 @@ search_again: active = NULL; INIT_LIST_HEAD(&eviction_list); list_for_each_entry_safe(vma, next, &vm->bound_list, vm_link) { + if (vma == active) { /* now seen this vma twice */ + if (flags & PIN_NONBLOCK) + break; + + active = ERR_PTR(-EAGAIN); + } + /* * We keep this list in a rough least-recently scanned order * of active elements (inactive elements are cheap to reap). @@ -143,21 +150,12 @@ search_again: * To notice when we complete one full cycle, we record the * first active element seen, before moving it to the tail. */ - if (i915_vma_is_active(vma)) { - if (vma == active) { - if (flags & PIN_NONBLOCK) - break; - - active = ERR_PTR(-EAGAIN); - } - - if (active != ERR_PTR(-EAGAIN)) { - if (!active) - active = vma; + if (active != ERR_PTR(-EAGAIN) && i915_vma_is_active(vma)) { + if (!active) + active = vma; - list_move_tail(&vma->vm_link, &vm->bound_list); - continue; - } + list_move_tail(&vma->vm_link, &vm->bound_list); + continue; } if (mark_free(&scan, vma, flags, &eviction_list)) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 2a4cd0ba5464..5c8e51d2ba5b 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1207,8 +1207,6 @@ static void engine_record_registers(struct intel_engine_coredump *ee) static void record_request(const struct i915_request *request, struct i915_request_coredump *erq) { - const struct i915_gem_context *ctx; - erq->flags = request->fence.flags; erq->context = request->fence.context; erq->seqno = request->fence.seqno; @@ -1219,9 +1217,13 @@ static void record_request(const struct i915_request *request, erq->pid = 0; rcu_read_lock(); - ctx = rcu_dereference(request->context->gem_context); - if (ctx) - erq->pid = pid_nr(ctx->pid); + if (!intel_context_is_closed(request->context)) { + const struct i915_gem_context *ctx; + + ctx = rcu_dereference(request->context->gem_context); + if (ctx) + erq->pid = pid_nr(ctx->pid); + } rcu_read_unlock(); } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index d91557d842dc..8a2b83807ffc 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -3361,7 +3361,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) u32 de_pipe_masked = gen8_de_pipe_fault_mask(dev_priv) | GEN8_PIPE_CDCLK_CRC_DONE; u32 de_pipe_enables; - u32 de_port_masked = GEN8_AUX_CHANNEL_A; + u32 de_port_masked = gen8_de_port_aux_mask(dev_priv); u32 de_port_enables; u32 de_misc_masked = GEN8_DE_EDP_PSR; enum pipe pipe; @@ -3369,18 +3369,8 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv) if (INTEL_GEN(dev_priv) <= 10) de_misc_masked |= GEN8_DE_MISC_GSE; - if (INTEL_GEN(dev_priv) >= 9) { - de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C | - GEN9_AUX_CHANNEL_D; - if (IS_GEN9_LP(dev_priv)) - de_port_masked |= BXT_DE_PORT_GMBUS; - } - - if (INTEL_GEN(dev_priv) >= 11) - de_port_masked |= ICL_AUX_CHANNEL_E; - - if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11) - de_port_masked |= CNL_AUX_CHANNEL_F; + if (IS_GEN9_LP(dev_priv)) + de_port_masked |= BXT_DE_PORT_GMBUS; de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK | GEN8_PIPE_FIFO_UNDERRUN; diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 66a46e41d5ef..cf2c01f17da8 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1310,8 +1310,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) * dropped by GuC. They won't be part of the context * ID in the OA reports, so squash those lower bits. */ - stream->specific_ctx_id = - lower_32_bits(ce->lrc_desc) >> 12; + stream->specific_ctx_id = ce->lrc.lrca >> 12; /* * GuC uses the top bit to signal proxy submission, so @@ -1328,11 +1327,10 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream) ((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); /* * Pick an unused context id - * 0 - (NUM_CONTEXT_TAG - 1) are used by other contexts + * 0 - BITS_PER_LONG are used by other contexts * GEN12_MAX_CONTEXT_HW_ID (0x7ff) is used by idle context */ stream->specific_ctx_id = (GEN12_MAX_CONTEXT_HW_ID - 1) << (GEN11_SW_CTX_ID_SHIFT - 32); - BUILD_BUG_ON((GEN12_MAX_CONTEXT_HW_ID - 1) < NUM_CONTEXT_TAG); break; } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index e0c6021fdaf9..6e12000c4b6b 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3094,6 +3094,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg) #define GT_BSD_CS_ERROR_INTERRUPT (1 << 15) #define GT_BSD_USER_INTERRUPT (1 << 12) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 (1 << 11) /* hsw+; rsvd on snb, ivb, vlv */ +#define GT_WAIT_SEMAPHORE_INTERRUPT REG_BIT(11) /* bdw+ */ #define GT_CONTEXT_SWITCH_INTERRUPT (1 << 8) #define GT_RENDER_L3_PARITY_ERROR_INTERRUPT (1 << 5) /* !snb */ #define GT_RENDER_PIPECTL_NOTIFY_INTERRUPT (1 << 4) diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index c0df71d7d0ff..e2b78db685ea 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -1017,11 +1017,15 @@ i915_request_await_request(struct i915_request *to, struct i915_request *from) GEM_BUG_ON(to == from); GEM_BUG_ON(to->timeline == from->timeline); - if (i915_request_completed(from)) + if (i915_request_completed(from)) { + i915_sw_fence_set_error_once(&to->submit, from->fence.error); return 0; + } if (to->engine->schedule) { - ret = i915_sched_node_add_dependency(&to->sched, &from->sched); + ret = i915_sched_node_add_dependency(&to->sched, + &from->sched, + I915_DEPENDENCY_EXTERNAL); if (ret < 0) return ret; } @@ -1183,7 +1187,9 @@ __i915_request_await_execution(struct i915_request *to, /* Couple the dependency tree for PI on this exposed to->fence */ if (to->engine->schedule) { - err = i915_sched_node_add_dependency(&to->sched, &from->sched); + err = i915_sched_node_add_dependency(&to->sched, + &from->sched, + I915_DEPENDENCY_WEAK); if (err < 0) return err; } diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c index 68b06a7ba667..f0a9e8958ca0 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.c +++ b/drivers/gpu/drm/i915/i915_scheduler.c @@ -456,7 +456,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, } int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal) + struct i915_sched_node *signal, + unsigned long flags) { struct i915_dependency *dep; @@ -465,8 +466,7 @@ int i915_sched_node_add_dependency(struct i915_sched_node *node, return -ENOMEM; if (!__i915_sched_node_add_dependency(node, signal, dep, - I915_DEPENDENCY_EXTERNAL | - I915_DEPENDENCY_ALLOC)) + flags | I915_DEPENDENCY_ALLOC)) i915_dependency_free(dep); return 0; diff --git a/drivers/gpu/drm/i915/i915_scheduler.h b/drivers/gpu/drm/i915/i915_scheduler.h index d1dc4efef77b..6f0bf00fc569 100644 --- a/drivers/gpu/drm/i915/i915_scheduler.h +++ b/drivers/gpu/drm/i915/i915_scheduler.h @@ -34,7 +34,8 @@ bool __i915_sched_node_add_dependency(struct i915_sched_node *node, unsigned long flags); int i915_sched_node_add_dependency(struct i915_sched_node *node, - struct i915_sched_node *signal); + struct i915_sched_node *signal, + unsigned long flags); void i915_sched_node_fini(struct i915_sched_node *node); diff --git a/drivers/gpu/drm/i915/i915_scheduler_types.h b/drivers/gpu/drm/i915/i915_scheduler_types.h index d18e70550054..7186875088a0 100644 --- a/drivers/gpu/drm/i915/i915_scheduler_types.h +++ b/drivers/gpu/drm/i915/i915_scheduler_types.h @@ -78,6 +78,7 @@ struct i915_dependency { unsigned long flags; #define I915_DEPENDENCY_ALLOC BIT(0) #define I915_DEPENDENCY_EXTERNAL BIT(1) +#define I915_DEPENDENCY_WEAK BIT(2) }; #endif /* _I915_SCHEDULER_TYPES_H_ */ diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 82e3bc280622..2cd7a7e87c0a 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -1228,18 +1228,6 @@ int __i915_vma_unbind(struct i915_vma *vma) lockdep_assert_held(&vma->vm->mutex); - /* - * First wait upon any activity as retiring the request may - * have side-effects such as unpinning or even unbinding this vma. - * - * XXX Actually waiting under the vm->mutex is a hinderance and - * should be pipelined wherever possible. In cases where that is - * unavoidable, we should lift the wait to before the mutex. - */ - ret = i915_vma_sync(vma); - if (ret) - return ret; - if (i915_vma_is_pinned(vma)) { vma_print_allocator(vma, "is pinned"); return -EAGAIN; @@ -1313,15 +1301,20 @@ int i915_vma_unbind(struct i915_vma *vma) if (!drm_mm_node_allocated(&vma->node)) return 0; - if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) - /* XXX not always required: nop_clear_range */ - wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); - /* Optimistic wait before taking the mutex */ err = i915_vma_sync(vma); if (err) goto out_rpm; + if (i915_vma_is_pinned(vma)) { + vma_print_allocator(vma, "is pinned"); + return -EAGAIN; + } + + if (i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND)) + /* XXX not always required: nop_clear_range */ + wakeref = intel_runtime_pm_get(&vm->i915->runtime_pm); + err = mutex_lock_interruptible(&vm->mutex); if (err) goto out_rpm; diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 8375054ba27d..a52986a9e7a6 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4992,7 +4992,7 @@ static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, * WaIncreaseLatencyIPCEnabled: kbl,cfl * Display WA #1141: kbl,cfl */ - if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) || + if ((IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) && dev_priv->ipc_enabled) latency += 4; diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c index 58b5f40a07dd..af89c7fc8f59 100644 --- a/drivers/gpu/drm/i915/selftests/i915_vma.c +++ b/drivers/gpu/drm/i915/selftests/i915_vma.c @@ -173,7 +173,7 @@ static int igt_vma_create(void *arg) } nc = 0; - for_each_prime_number(num_ctx, 2 * NUM_CONTEXT_TAG) { + for_each_prime_number(num_ctx, 2 * BITS_PER_LONG) { for (; nc < num_ctx; nc++) { ctx = mock_context(i915, "mock"); if (!ctx) diff --git a/drivers/gpu/drm/ingenic/ingenic-drm.c b/drivers/gpu/drm/ingenic/ingenic-drm.c index 9dfe7cb530e1..1754c0547069 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm.c @@ -843,6 +843,7 @@ static const struct of_device_id ingenic_drm_of_match[] = { { .compatible = "ingenic,jz4770-lcd", .data = &jz4770_soc_info }, { /* sentinel */ }, }; +MODULE_DEVICE_TABLE(of, ingenic_drm_of_match); static struct platform_driver ingenic_drm_driver = { .driver = { diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index b5f5eb7b4bb9..8c2e1b47e81a 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -412,9 +412,7 @@ static int __maybe_unused meson_drv_pm_resume(struct device *dev) if (priv->afbcd.ops) priv->afbcd.ops->init(priv); - drm_mode_config_helper_resume(priv->drm); - - return 0; + return drm_mode_config_helper_resume(priv->drm); } static int compare_of(struct device *dev, void *data) diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 059939789730..3eb89f1eb0e1 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -717,7 +717,7 @@ static void sun6i_dsi_encoder_enable(struct drm_encoder *encoder) struct drm_display_mode *mode = &encoder->crtc->state->adjusted_mode; struct sun6i_dsi *dsi = encoder_to_sun6i_dsi(encoder); struct mipi_dsi_device *device = dsi->device; - union phy_configure_opts opts = { 0 }; + union phy_configure_opts opts = { }; struct phy_configure_opts_mipi_dphy *cfg = &opts.mipi_dphy; u16 delay; int err; diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c index bd268028fb3d..583cd6e0ae27 100644 --- a/drivers/gpu/drm/tegra/drm.c +++ b/drivers/gpu/drm/tegra/drm.c @@ -1039,6 +1039,7 @@ void tegra_drm_free(struct tegra_drm *tegra, size_t size, void *virt, static bool host1x_drm_wants_iommu(struct host1x_device *dev) { + struct host1x *host1x = dev_get_drvdata(dev->dev.parent); struct iommu_domain *domain; /* @@ -1076,7 +1077,7 @@ static bool host1x_drm_wants_iommu(struct host1x_device *dev) * sufficient and whether or not the host1x is attached to an IOMMU * doesn't matter. */ - if (!domain && dma_get_mask(dev->dev.parent) <= DMA_BIT_MASK(32)) + if (!domain && host1x_get_dma_mask(host1x) <= DMA_BIT_MASK(32)) return true; return domain != NULL; diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index c1824bdf2418..7879ff58236f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -221,6 +221,7 @@ struct virtio_gpu_fpriv { /* virtio_ioctl.c */ #define DRM_VIRTIO_NUM_IOCTLS 10 extern struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; +void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file); /* virtio_kms.c */ int virtio_gpu_init(struct drm_device *dev); diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index 0d6152c99a27..f0d5a8974677 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -39,6 +39,9 @@ int virtio_gpu_gem_create(struct drm_file *file, int ret; u32 handle; + if (vgdev->has_virgl_3d) + virtio_gpu_create_context(dev, file); + ret = virtio_gpu_object_create(vgdev, params, &obj, NULL); if (ret < 0) return ret; diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 3f60bf2fe05a..512daff92038 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -34,8 +34,7 @@ #include "virtgpu_drv.h" -static void virtio_gpu_create_context(struct drm_device *dev, - struct drm_file *file) +void virtio_gpu_create_context(struct drm_device *dev, struct drm_file *file) { struct virtio_gpu_device *vgdev = dev->dev_private; struct virtio_gpu_fpriv *vfpriv = file->driver_priv; diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c index 388bcc2889aa..d24344e91922 100644 --- a/drivers/gpu/host1x/dev.c +++ b/drivers/gpu/host1x/dev.c @@ -192,17 +192,55 @@ static void host1x_setup_sid_table(struct host1x *host) } } +static bool host1x_wants_iommu(struct host1x *host1x) +{ + /* + * If we support addressing a maximum of 32 bits of physical memory + * and if the host1x firewall is enabled, there's no need to enable + * IOMMU support. This can happen for example on Tegra20, Tegra30 + * and Tegra114. + * + * Tegra124 and later can address up to 34 bits of physical memory and + * many platforms come equipped with more than 2 GiB of system memory, + * which requires crossing the 4 GiB boundary. But there's a catch: on + * SoCs before Tegra186 (i.e. Tegra124 and Tegra210), the host1x can + * only address up to 32 bits of memory in GATHER opcodes, which means + * that command buffers need to either be in the first 2 GiB of system + * memory (which could quickly lead to memory exhaustion), or command + * buffers need to be treated differently from other buffers (which is + * not possible with the current ABI). + * + * A third option is to use the IOMMU in these cases to make sure all + * buffers will be mapped into a 32-bit IOVA space that host1x can + * address. This allows all of the system memory to be used and works + * within the limitations of the host1x on these SoCs. + * + * In summary, default to enable IOMMU on Tegra124 and later. For any + * of the earlier SoCs, only use the IOMMU for additional safety when + * the host1x firewall is disabled. + */ + if (host1x->info->dma_mask <= DMA_BIT_MASK(32)) { + if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL)) + return false; + } + + return true; +} + static struct iommu_domain *host1x_iommu_attach(struct host1x *host) { struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev); int err; /* - * If the host1x firewall is enabled, there's no need to enable IOMMU - * support. Similarly, if host1x is already attached to an IOMMU (via - * the DMA API), don't try to attach again. + * We may not always want to enable IOMMU support (for example if the + * host1x firewall is already enabled and we don't support addressing + * more than 32 bits of physical memory), so check for that first. + * + * Similarly, if host1x is already attached to an IOMMU (via the DMA + * API), don't try to attach again. */ - if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) || domain) + if (!host1x_wants_iommu(host) || domain) return domain; host->group = iommu_group_get(host->dev); @@ -502,6 +540,19 @@ static void __exit tegra_host1x_exit(void) } module_exit(tegra_host1x_exit); +/** + * host1x_get_dma_mask() - query the supported DMA mask for host1x + * @host1x: host1x instance + * + * Note that this returns the supported DMA mask for host1x, which can be + * different from the applicable DMA mask under certain circumstances. + */ +u64 host1x_get_dma_mask(struct host1x *host1x) +{ + return host1x->info->dma_mask; +} +EXPORT_SYMBOL(host1x_get_dma_mask); + MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>"); MODULE_AUTHOR("Terje Bergstrom <tbergstrom@nvidia.com>"); MODULE_DESCRIPTION("Host1x driver for Tegra products"); diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 7c89edbd6c5a..34f07371716d 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -1155,6 +1155,7 @@ config HID_ALPS config HID_MCP2221 tristate "Microchip MCP2221 HID USB-to-I2C/SMbus host support" depends on USB_HID && I2C + depends on GPIOLIB ---help--- Provides I2C and SMBUS host adapter functionality over USB-HID through MCP2221 device. diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index fa704153cb00..b2ad319a74b9 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -802,6 +802,7 @@ static int alps_probe(struct hid_device *hdev, const struct hid_device_id *id) break; case HID_DEVICE_ID_ALPS_U1_DUAL: case HID_DEVICE_ID_ALPS_U1: + case HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY: data->dev_type = U1; break; default: diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index b18b13147a6f..1c71a1aa76b2 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -79,10 +79,10 @@ #define HID_DEVICE_ID_ALPS_U1_DUAL_PTP 0x121F #define HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP 0x1220 #define HID_DEVICE_ID_ALPS_U1 0x1215 +#define HID_DEVICE_ID_ALPS_U1_UNICORN_LEGACY 0x121E #define HID_DEVICE_ID_ALPS_T4_BTNLESS 0x120C #define HID_DEVICE_ID_ALPS_1222 0x1222 - #define USB_VENDOR_ID_AMI 0x046b #define USB_DEVICE_ID_AMI_VIRT_KEYBOARD_AND_MOUSE 0xff10 @@ -385,6 +385,7 @@ #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_7349 0x7349 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_73F7 0x73f7 #define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001 0xa001 +#define USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002 0xc002 #define USB_VENDOR_ID_ELAN 0x04f3 #define USB_DEVICE_ID_TOSHIBA_CLICK_L9W 0x0401 @@ -759,6 +760,7 @@ #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2 0xc218 #define USB_DEVICE_ID_LOGITECH_RUMBLEPAD2_2 0xc219 #define USB_DEVICE_ID_LOGITECH_G15_LCD 0xc222 +#define USB_DEVICE_ID_LOGITECH_G11 0xc225 #define USB_DEVICE_ID_LOGITECH_G15_V2_LCD 0xc227 #define USB_DEVICE_ID_LOGITECH_G510 0xc22d #define USB_DEVICE_ID_LOGITECH_G510_USB_AUDIO 0xc22e @@ -1097,6 +1099,9 @@ #define USB_DEVICE_ID_SYMBOL_SCANNER_2 0x1300 #define USB_DEVICE_ID_SYMBOL_SCANNER_3 0x1200 +#define I2C_VENDOR_ID_SYNAPTICS 0x06cb +#define I2C_PRODUCT_ID_SYNAPTICS_SYNA2393 0x7a13 + #define USB_VENDOR_ID_SYNAPTICS 0x06cb #define USB_DEVICE_ID_SYNAPTICS_TP 0x0001 #define USB_DEVICE_ID_SYNAPTICS_INT_TP 0x0002 @@ -1111,6 +1116,7 @@ #define USB_DEVICE_ID_SYNAPTICS_LTS2 0x1d10 #define USB_DEVICE_ID_SYNAPTICS_HD 0x0ac3 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD 0x1ac3 +#define USB_DEVICE_ID_SYNAPTICS_DELL_K12A 0x2819 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5_012 0x2968 #define USB_DEVICE_ID_SYNAPTICS_TP_V103 0x5710 #define USB_DEVICE_ID_SYNAPTICS_ACER_SWITCH5 0x81a7 diff --git a/drivers/hid/hid-lg-g15.c b/drivers/hid/hid-lg-g15.c index ad4b5412a9f4..ef0cbcd7540d 100644 --- a/drivers/hid/hid-lg-g15.c +++ b/drivers/hid/hid-lg-g15.c @@ -872,6 +872,10 @@ error_hw_stop: } static const struct hid_device_id lg_g15_devices[] = { + /* The G11 is a G15 without the LCD, treat it as a G15 */ + { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, + USB_DEVICE_ID_LOGITECH_G11), + .driver_data = LG_G15 }, { HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_G15_LCD), .driver_data = LG_G15 }, diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 362805ddf377..03c720b47306 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1922,6 +1922,9 @@ static const struct hid_device_id mt_devices[] = { { .driver_data = MT_CLS_EGALAX_SERIAL, MT_USB_DEVICE(USB_VENDOR_ID_DWAV, USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_A001) }, + { .driver_data = MT_CLS_EGALAX, + MT_USB_DEVICE(USB_VENDOR_ID_DWAV, + USB_DEVICE_ID_DWAV_EGALAX_MULTITOUCH_C002) }, /* Elitegroup panel */ { .driver_data = MT_CLS_SERIAL, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index ebec818344af..e4cb543de0cd 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -163,6 +163,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_LTS2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_QUAD_HD), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_TP_V103), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_SYNAPTICS, USB_DEVICE_ID_SYNAPTICS_DELL_K12A), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_TOPMAX, USB_DEVICE_ID_TOPMAX_COBRAPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_TOUCHPACK, USB_DEVICE_ID_TOUCHPACK_RTS), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_TPV, USB_DEVICE_ID_TPV_OPTICAL_TOUCHSCREEN_8882), HID_QUIRK_NOGET }, diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c index 009000c5d55c..294c84e136d7 100644 --- a/drivers/hid/i2c-hid/i2c-hid-core.c +++ b/drivers/hid/i2c-hid/i2c-hid-core.c @@ -177,6 +177,8 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_BOGUS_IRQ }, { USB_VENDOR_ID_ALPS_JP, HID_ANY_ID, I2C_HID_QUIRK_RESET_ON_RESUME }, + { I2C_VENDOR_ID_SYNAPTICS, I2C_PRODUCT_ID_SYNAPTICS_SYNA2393, + I2C_HID_QUIRK_RESET_ON_RESUME }, { USB_VENDOR_ID_ITE, I2C_DEVICE_ID_ITE_LENOVO_LEGION_Y720, I2C_HID_QUIRK_BAD_INPUT_SIZE }, { 0, 0 } diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c index c7bc9db5b192..17a638f15082 100644 --- a/drivers/hid/usbhid/hid-core.c +++ b/drivers/hid/usbhid/hid-core.c @@ -682,16 +682,21 @@ static int usbhid_open(struct hid_device *hid) struct usbhid_device *usbhid = hid->driver_data; int res; + mutex_lock(&usbhid->mutex); + set_bit(HID_OPENED, &usbhid->iofl); - if (hid->quirks & HID_QUIRK_ALWAYS_POLL) - return 0; + if (hid->quirks & HID_QUIRK_ALWAYS_POLL) { + res = 0; + goto Done; + } res = usb_autopm_get_interface(usbhid->intf); /* the device must be awake to reliably request remote wakeup */ if (res < 0) { clear_bit(HID_OPENED, &usbhid->iofl); - return -EIO; + res = -EIO; + goto Done; } usbhid->intf->needs_remote_wakeup = 1; @@ -725,6 +730,9 @@ static int usbhid_open(struct hid_device *hid) msleep(50); clear_bit(HID_RESUME_RUNNING, &usbhid->iofl); + + Done: + mutex_unlock(&usbhid->mutex); return res; } @@ -732,6 +740,8 @@ static void usbhid_close(struct hid_device *hid) { struct usbhid_device *usbhid = hid->driver_data; + mutex_lock(&usbhid->mutex); + /* * Make sure we don't restart data acquisition due to * a resumption we no longer care about by avoiding racing @@ -743,12 +753,13 @@ static void usbhid_close(struct hid_device *hid) clear_bit(HID_IN_POLLING, &usbhid->iofl); spin_unlock_irq(&usbhid->lock); - if (hid->quirks & HID_QUIRK_ALWAYS_POLL) - return; + if (!(hid->quirks & HID_QUIRK_ALWAYS_POLL)) { + hid_cancel_delayed_stuff(usbhid); + usb_kill_urb(usbhid->urbin); + usbhid->intf->needs_remote_wakeup = 0; + } - hid_cancel_delayed_stuff(usbhid); - usb_kill_urb(usbhid->urbin); - usbhid->intf->needs_remote_wakeup = 0; + mutex_unlock(&usbhid->mutex); } /* @@ -1057,6 +1068,8 @@ static int usbhid_start(struct hid_device *hid) unsigned int n, insize = 0; int ret; + mutex_lock(&usbhid->mutex); + clear_bit(HID_DISCONNECTED, &usbhid->iofl); usbhid->bufsize = HID_MIN_BUFFER_SIZE; @@ -1177,6 +1190,8 @@ static int usbhid_start(struct hid_device *hid) usbhid_set_leds(hid); device_set_wakeup_enable(&dev->dev, 1); } + + mutex_unlock(&usbhid->mutex); return 0; fail: @@ -1187,6 +1202,7 @@ fail: usbhid->urbout = NULL; usbhid->urbctrl = NULL; hid_free_buffers(dev, hid); + mutex_unlock(&usbhid->mutex); return ret; } @@ -1202,6 +1218,8 @@ static void usbhid_stop(struct hid_device *hid) usbhid->intf->needs_remote_wakeup = 0; } + mutex_lock(&usbhid->mutex); + clear_bit(HID_STARTED, &usbhid->iofl); spin_lock_irq(&usbhid->lock); /* Sync with error and led handlers */ set_bit(HID_DISCONNECTED, &usbhid->iofl); @@ -1222,6 +1240,8 @@ static void usbhid_stop(struct hid_device *hid) usbhid->urbout = NULL; hid_free_buffers(hid_to_usb_dev(hid), hid); + + mutex_unlock(&usbhid->mutex); } static int usbhid_power(struct hid_device *hid, int lvl) @@ -1382,6 +1402,7 @@ static int usbhid_probe(struct usb_interface *intf, const struct usb_device_id * INIT_WORK(&usbhid->reset_work, hid_reset); timer_setup(&usbhid->io_retry, hid_retry_timeout, 0); spin_lock_init(&usbhid->lock); + mutex_init(&usbhid->mutex); ret = hid_add_device(hid); if (ret) { diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h index 8620408bd7af..75fe85d3d27a 100644 --- a/drivers/hid/usbhid/usbhid.h +++ b/drivers/hid/usbhid/usbhid.h @@ -80,6 +80,7 @@ struct usbhid_device { dma_addr_t outbuf_dma; /* Output buffer dma */ unsigned long last_out; /* record of last output for timeouts */ + struct mutex mutex; /* start/stop/open/close */ spinlock_t lock; /* fifo spinlock */ unsigned long iofl; /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */ struct timer_list io_retry; /* Retry timer */ diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c index 5ded94b7bf68..cd71e7133944 100644 --- a/drivers/hid/wacom_sys.c +++ b/drivers/hid/wacom_sys.c @@ -319,9 +319,11 @@ static void wacom_feature_mapping(struct hid_device *hdev, data[0] = field->report->id; ret = wacom_get_report(hdev, HID_FEATURE_REPORT, data, n, WAC_CMD_RETRIES); - if (ret == n) { + if (ret == n && features->type == HID_GENERIC) { ret = hid_report_raw_event(hdev, HID_FEATURE_REPORT, data, n, 0); + } else if (ret == 2 && features->type != HID_GENERIC) { + features->touch_max = data[1]; } else { features->touch_max = 16; hid_warn(hdev, "wacom_feature_mapping: " diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index d99a9d407671..1c96809b51c9 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -1427,11 +1427,13 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) { struct input_dev *pad_input = wacom->pad_input; unsigned char *data = wacom->data; + int nbuttons = wacom->features.numbered_buttons; - int buttons = data[282] | ((data[281] & 0x40) << 2); + int expresskeys = data[282]; + int center = (data[281] & 0x40) >> 6; int ring = data[285] & 0x7F; bool ringstatus = data[285] & 0x80; - bool prox = buttons || ringstatus; + bool prox = expresskeys || center || ringstatus; /* Fix touchring data: userspace expects 0 at left and increasing clockwise */ ring = 71 - ring; @@ -1439,7 +1441,8 @@ static void wacom_intuos_pro2_bt_pad(struct wacom_wac *wacom) if (ring > 71) ring -= 72; - wacom_report_numbered_buttons(pad_input, 9, buttons); + wacom_report_numbered_buttons(pad_input, nbuttons, + expresskeys | (center << (nbuttons - 1))); input_report_abs(pad_input, ABS_WHEEL, ringstatus ? ring : 0); @@ -2637,9 +2640,25 @@ static void wacom_wac_finger_pre_report(struct hid_device *hdev, case HID_DG_TIPSWITCH: hid_data->last_slot_field = equivalent_usage; break; + case HID_DG_CONTACTCOUNT: + hid_data->cc_report = report->id; + hid_data->cc_index = i; + hid_data->cc_value_index = j; + break; } } } + + if (hid_data->cc_report != 0 && + hid_data->cc_index >= 0) { + struct hid_field *field = report->field[hid_data->cc_index]; + int value = field->value[hid_data->cc_value_index]; + if (value) + hid_data->num_expected = value; + } + else { + hid_data->num_expected = wacom_wac->features.touch_max; + } } static void wacom_wac_finger_report(struct hid_device *hdev, @@ -2649,7 +2668,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev, struct wacom_wac *wacom_wac = &wacom->wacom_wac; struct input_dev *input = wacom_wac->touch_input; unsigned touch_max = wacom_wac->features.touch_max; - struct hid_data *hid_data = &wacom_wac->hid_data; /* If more packets of data are expected, give us a chance to * process them rather than immediately syncing a partial @@ -2663,7 +2681,6 @@ static void wacom_wac_finger_report(struct hid_device *hdev, input_sync(input); wacom_wac->hid_data.num_received = 0; - hid_data->num_expected = 0; /* keep touch state for pen event */ wacom_wac->shared->touch_down = wacom_wac_finger_count_touches(wacom_wac); @@ -2738,73 +2755,12 @@ static void wacom_report_events(struct hid_device *hdev, } } -static void wacom_set_num_expected(struct hid_device *hdev, - struct hid_report *report, - int collection_index, - struct hid_field *field, - int field_index) -{ - struct wacom *wacom = hid_get_drvdata(hdev); - struct wacom_wac *wacom_wac = &wacom->wacom_wac; - struct hid_data *hid_data = &wacom_wac->hid_data; - unsigned int original_collection_level = - hdev->collection[collection_index].level; - bool end_collection = false; - int i; - - if (hid_data->num_expected) - return; - - // find the contact count value for this segment - for (i = field_index; i < report->maxfield && !end_collection; i++) { - struct hid_field *field = report->field[i]; - unsigned int field_level = - hdev->collection[field->usage[0].collection_index].level; - unsigned int j; - - if (field_level != original_collection_level) - continue; - - for (j = 0; j < field->maxusage; j++) { - struct hid_usage *usage = &field->usage[j]; - - if (usage->collection_index != collection_index) { - end_collection = true; - break; - } - if (wacom_equivalent_usage(usage->hid) == HID_DG_CONTACTCOUNT) { - hid_data->cc_report = report->id; - hid_data->cc_index = i; - hid_data->cc_value_index = j; - - if (hid_data->cc_report != 0 && - hid_data->cc_index >= 0) { - - struct hid_field *field = - report->field[hid_data->cc_index]; - int value = - field->value[hid_data->cc_value_index]; - - if (value) - hid_data->num_expected = value; - } - } - } - } - - if (hid_data->cc_report == 0 || hid_data->cc_index < 0) - hid_data->num_expected = wacom_wac->features.touch_max; -} - static int wacom_wac_collection(struct hid_device *hdev, struct hid_report *report, int collection_index, struct hid_field *field, int field_index) { struct wacom *wacom = hid_get_drvdata(hdev); - if (WACOM_FINGER_FIELD(field)) - wacom_set_num_expected(hdev, report, collection_index, field, - field_index); wacom_report_events(hdev, report, collection_index, field_index); /* diff --git a/drivers/hwmon/da9052-hwmon.c b/drivers/hwmon/da9052-hwmon.c index 53b517dbe7e6..4af2fc309c28 100644 --- a/drivers/hwmon/da9052-hwmon.c +++ b/drivers/hwmon/da9052-hwmon.c @@ -244,9 +244,9 @@ static ssize_t da9052_tsi_show(struct device *dev, int channel = to_sensor_dev_attr(devattr)->index; int ret; - mutex_lock(&hwmon->hwmon_lock); + mutex_lock(&hwmon->da9052->auxadc_lock); ret = __da9052_read_tsi(dev, channel); - mutex_unlock(&hwmon->hwmon_lock); + mutex_unlock(&hwmon->da9052->auxadc_lock); if (ret < 0) return ret; diff --git a/drivers/hwmon/drivetemp.c b/drivers/hwmon/drivetemp.c index 9179460c2d9d..0d4f3d97ffc6 100644 --- a/drivers/hwmon/drivetemp.c +++ b/drivers/hwmon/drivetemp.c @@ -346,7 +346,7 @@ static int drivetemp_identify_sata(struct drivetemp_data *st) st->have_temp_highest = temp_is_valid(buf[SCT_STATUS_TEMP_HIGHEST]); if (!have_sct_data_table) - goto skip_sct; + goto skip_sct_data; /* Request and read temperature history table */ memset(buf, '\0', sizeof(st->smartdata)); diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c index 1f5743d68984..a7eb10d2a053 100644 --- a/drivers/hwmon/nct7904.c +++ b/drivers/hwmon/nct7904.c @@ -41,6 +41,7 @@ #define FANCTL_MAX 4 /* Counted from 1 */ #define TCPU_MAX 8 /* Counted from 1 */ #define TEMP_MAX 4 /* Counted from 1 */ +#define SMI_STS_MAX 10 /* Counted from 1 */ #define VT_ADC_CTRL0_REG 0x20 /* Bank 0 */ #define VT_ADC_CTRL1_REG 0x21 /* Bank 0 */ @@ -361,6 +362,7 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel, struct nct7904_data *data = dev_get_drvdata(dev); int ret, temp; unsigned int reg1, reg2, reg3; + s8 temps; switch (attr) { case hwmon_temp_input: @@ -466,7 +468,8 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel, if (ret < 0) return ret; - *val = ret * 1000; + temps = ret; + *val = temps * 1000; return 0; } @@ -1009,6 +1012,13 @@ static int nct7904_probe(struct i2c_client *client, data->fan_mode[i] = ret; } + /* Read all of SMI status register to clear alarms */ + for (i = 0; i < SMI_STS_MAX; i++) { + ret = nct7904_read_reg(data, BANK_0, SMI_STS1_REG + i); + if (ret < 0) + return ret; + } + hwmon_dev = devm_hwmon_device_register_with_info(dev, client->name, data, &nct7904_chip_info, NULL); diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index 717b798cddad..a670209bbce6 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -1553,8 +1553,11 @@ int ib_cache_setup_one(struct ib_device *device) if (err) return err; - rdma_for_each_port (device, p) - ib_cache_update(device, p, true); + rdma_for_each_port (device, p) { + err = ib_cache_update(device, p, true); + if (err) + return err; + } return 0; } diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index 9eec26d10d7b..e16105be2eb2 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -1292,11 +1292,10 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh, has_cap_net_admin = netlink_capable(skb, CAP_NET_ADMIN); ret = fill_func(msg, has_cap_net_admin, res, port); - - rdma_restrack_put(res); if (ret) goto err_free; + rdma_restrack_put(res); nlmsg_end(msg, nlh); ib_device_put(device); return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid); diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 177333d8bcda..bf8e149d3191 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -459,7 +459,8 @@ alloc_begin_fd_uobject(const struct uverbs_api_object *obj, struct ib_uobject *uobj; struct file *filp; - if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release)) + if (WARN_ON(fd_type->fops->release != &uverbs_uobject_fd_release && + fd_type->fops->release != &uverbs_async_event_release)) return ERR_PTR(-EINVAL); new_fd = get_unused_fd_flags(O_CLOEXEC); diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index 7df71983212d..3d189c7ee59e 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -219,6 +219,7 @@ void ib_uverbs_init_event_queue(struct ib_uverbs_event_queue *ev_queue); void ib_uverbs_init_async_event_file(struct ib_uverbs_async_event_file *ev_file); void ib_uverbs_free_event_queue(struct ib_uverbs_event_queue *event_queue); void ib_uverbs_flow_resources_free(struct ib_uflow_resources *uflow_res); +int uverbs_async_event_release(struct inode *inode, struct file *filp); int ib_alloc_ucontext(struct uverbs_attr_bundle *attrs); int ib_init_ucontext(struct uverbs_attr_bundle *attrs); @@ -227,6 +228,9 @@ void ib_uverbs_release_ucq(struct ib_uverbs_completion_event_file *ev_file, struct ib_ucq_object *uobj); void ib_uverbs_release_uevent(struct ib_uevent_object *uobj); void ib_uverbs_release_file(struct kref *ref); +void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, + __u64 element, __u64 event, + struct list_head *obj_list, u32 *counter); void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context); void ib_uverbs_cq_event_handler(struct ib_event *event, void *context_ptr); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 17fc25db0311..1bab8de14757 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -346,7 +346,7 @@ const struct file_operations uverbs_async_event_fops = { .owner = THIS_MODULE, .read = ib_uverbs_async_event_read, .poll = ib_uverbs_async_event_poll, - .release = uverbs_uobject_fd_release, + .release = uverbs_async_event_release, .fasync = ib_uverbs_async_event_fasync, .llseek = no_llseek, }; @@ -386,10 +386,9 @@ void ib_uverbs_comp_handler(struct ib_cq *cq, void *cq_context) kill_fasync(&ev_queue->async_queue, SIGIO, POLL_IN); } -static void -ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, - __u64 element, __u64 event, struct list_head *obj_list, - u32 *counter) +void ib_uverbs_async_handler(struct ib_uverbs_async_event_file *async_file, + __u64 element, __u64 event, + struct list_head *obj_list, u32 *counter) { struct ib_uverbs_event *entry; unsigned long flags; @@ -1187,9 +1186,6 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev, */ mutex_unlock(&uverbs_dev->lists_mutex); - ib_uverbs_async_handler(READ_ONCE(file->async_file), 0, - IB_EVENT_DEVICE_FATAL, NULL, NULL); - uverbs_destroy_ufile_hw(file, RDMA_REMOVE_DRIVER_REMOVE); kref_put(&file->ref, ib_uverbs_release_file); diff --git a/drivers/infiniband/core/uverbs_std_types_async_fd.c b/drivers/infiniband/core/uverbs_std_types_async_fd.c index 82ec0806b34b..61899eaf1f91 100644 --- a/drivers/infiniband/core/uverbs_std_types_async_fd.c +++ b/drivers/infiniband/core/uverbs_std_types_async_fd.c @@ -26,10 +26,38 @@ static int uverbs_async_event_destroy_uobj(struct ib_uobject *uobj, container_of(uobj, struct ib_uverbs_async_event_file, uobj); ib_unregister_event_handler(&event_file->event_handler); - ib_uverbs_free_event_queue(&event_file->ev_queue); + + if (why == RDMA_REMOVE_DRIVER_REMOVE) + ib_uverbs_async_handler(event_file, 0, IB_EVENT_DEVICE_FATAL, + NULL, NULL); return 0; } +int uverbs_async_event_release(struct inode *inode, struct file *filp) +{ + struct ib_uverbs_async_event_file *event_file; + struct ib_uobject *uobj = filp->private_data; + int ret; + + if (!uobj) + return uverbs_uobject_fd_release(inode, filp); + + event_file = + container_of(uobj, struct ib_uverbs_async_event_file, uobj); + + /* + * The async event FD has to deliver IB_EVENT_DEVICE_FATAL even after + * disassociation, so cleaning the event list must only happen after + * release. The user knows it has reached the end of the event stream + * when it sees IB_EVENT_DEVICE_FATAL. + */ + uverbs_uobject_get(uobj); + ret = uverbs_uobject_fd_release(inode, filp); + ib_uverbs_free_event_queue(&event_file->ev_queue); + uverbs_uobject_put(uobj); + return ret; +} + DECLARE_UVERBS_NAMED_METHOD( UVERBS_METHOD_ASYNC_EVENT_ALLOC, UVERBS_ATTR_FD(UVERBS_ATTR_ASYNC_EVENT_ALLOC_FD_HANDLE, diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index d69dece3b1d5..30e08bcc9afb 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -2891,8 +2891,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb) srqidx = ABORT_RSS_SRQIDX_G( be32_to_cpu(req->srqidx_status)); if (srqidx) { - complete_cached_srq_buffers(ep, - req->srqidx_status); + complete_cached_srq_buffers(ep, srqidx); } else { /* Hold ep ref until finish_peer_abort() */ c4iw_get_ep(&ep->com); @@ -3878,8 +3877,8 @@ static int read_tcb_rpl(struct c4iw_dev *dev, struct sk_buff *skb) return 0; } - ep->srqe_idx = t4_tcb_get_field32(tcb, TCB_RQ_START_W, TCB_RQ_START_W, - TCB_RQ_START_S); + ep->srqe_idx = t4_tcb_get_field32(tcb, TCB_RQ_START_W, TCB_RQ_START_M, + TCB_RQ_START_S); cleanup: pr_debug("ep %p tid %u %016x\n", ep, ep->hwtid, ep->srqe_idx); diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c index 13e4203497b3..a92346e88628 100644 --- a/drivers/infiniband/hw/hfi1/user_sdma.c +++ b/drivers/infiniband/hw/hfi1/user_sdma.c @@ -589,10 +589,6 @@ int hfi1_user_sdma_process_request(struct hfi1_filedata *fd, set_comp_state(pq, cq, info.comp_idx, QUEUED, 0); pq->state = SDMA_PKT_Q_ACTIVE; - /* Send the first N packets in the request to buy us some time */ - ret = user_sdma_send_pkts(req, pcount); - if (unlikely(ret < 0 && ret != -EBUSY)) - goto free_req; /* * This is a somewhat blocking send implementation. diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index bb78d3280acc..fa7a5ff498c7 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -1987,7 +1987,6 @@ static int i40iw_addr_resolve_neigh(struct i40iw_device *iwdev, struct rtable *rt; struct neighbour *neigh; int rc = arpindex; - struct net_device *netdev = iwdev->netdev; __be32 dst_ipaddr = htonl(dst_ip); __be32 src_ipaddr = htonl(src_ip); @@ -1997,9 +1996,6 @@ static int i40iw_addr_resolve_neigh(struct i40iw_device *iwdev, return rc; } - if (netif_is_bond_slave(netdev)) - netdev = netdev_master_upper_dev_get(netdev); - neigh = dst_neigh_lookup(&rt->dst, &dst_ipaddr); rcu_read_lock(); @@ -2065,7 +2061,6 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev, { struct neighbour *neigh; int rc = arpindex; - struct net_device *netdev = iwdev->netdev; struct dst_entry *dst; struct sockaddr_in6 dst_addr; struct sockaddr_in6 src_addr; @@ -2086,9 +2081,6 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev, return rc; } - if (netif_is_bond_slave(netdev)) - netdev = netdev_master_upper_dev_get(netdev); - neigh = dst_neigh_lookup(dst, dst_addr.sin6_addr.in6_u.u6_addr32); rcu_read_lock(); diff --git a/drivers/infiniband/hw/i40iw/i40iw_hw.c b/drivers/infiniband/hw/i40iw/i40iw_hw.c index 55a1fbf0e670..ae8b97c30665 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_hw.c +++ b/drivers/infiniband/hw/i40iw/i40iw_hw.c @@ -534,7 +534,7 @@ void i40iw_manage_arp_cache(struct i40iw_device *iwdev, int arp_index; arp_index = i40iw_arp_table(iwdev, ip_addr, ipv4, mac_addr, action); - if (arp_index == -1) + if (arp_index < 0) return; cqp_request = i40iw_get_cqp_request(&iwdev->cqp, false); if (!cqp_request) diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 2f9f78912267..cf51e3cbd969 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -2891,6 +2891,7 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp, int send_size; int header_size; int spc; + int err; int i; if (wr->wr.opcode != IB_WR_SEND) @@ -2925,7 +2926,9 @@ static int build_sriov_qp0_header(struct mlx4_ib_sqp *sqp, sqp->ud_header.lrh.virtual_lane = 0; sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED); - ib_get_cached_pkey(ib_dev, sqp->qp.port, 0, &pkey); + err = ib_get_cached_pkey(ib_dev, sqp->qp.port, 0, &pkey); + if (err) + return err; sqp->ud_header.bth.pkey = cpu_to_be16(pkey); if (sqp->qp.mlx4_ib_qp_type == MLX4_IB_QPT_TUN_SMI_OWNER) sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn); @@ -3212,9 +3215,14 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, const struct ib_ud_wr *wr, } sqp->ud_header.bth.solicited_event = !!(wr->wr.send_flags & IB_SEND_SOLICITED); if (!sqp->qp.ibqp.qp_num) - ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index, &pkey); + err = ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index, + &pkey); else - ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index, &pkey); + err = ib_get_cached_pkey(ib_dev, sqp->qp.port, wr->pkey_index, + &pkey); + if (err) + return err; + sqp->ud_header.bth.pkey = cpu_to_be16(pkey); sqp->ud_header.bth.destination_qpn = cpu_to_be32(wr->remote_qpn); sqp->ud_header.bth.psn = cpu_to_be32((sqp->send_psn++) & ((1 << 24) - 1)); diff --git a/drivers/infiniband/sw/rxe/rxe_mmap.c b/drivers/infiniband/sw/rxe/rxe_mmap.c index 48f48122ddcb..6a413d73b95d 100644 --- a/drivers/infiniband/sw/rxe/rxe_mmap.c +++ b/drivers/infiniband/sw/rxe/rxe_mmap.c @@ -151,7 +151,7 @@ struct rxe_mmap_info *rxe_create_mmap_info(struct rxe_dev *rxe, u32 size, ip = kmalloc(sizeof(*ip), GFP_KERNEL); if (!ip) - return NULL; + return ERR_PTR(-ENOMEM); size = PAGE_ALIGN(size); diff --git a/drivers/infiniband/sw/rxe/rxe_queue.c b/drivers/infiniband/sw/rxe/rxe_queue.c index ff92704de32f..245040c3a35d 100644 --- a/drivers/infiniband/sw/rxe/rxe_queue.c +++ b/drivers/infiniband/sw/rxe/rxe_queue.c @@ -45,12 +45,15 @@ int do_mmap_info(struct rxe_dev *rxe, struct mminfo __user *outbuf, if (outbuf) { ip = rxe_create_mmap_info(rxe, buf_size, udata, buf); - if (!ip) + if (IS_ERR(ip)) { + err = PTR_ERR(ip); goto err1; + } - err = copy_to_user(outbuf, &ip->info, sizeof(ip->info)); - if (err) + if (copy_to_user(outbuf, &ip->info, sizeof(ip->info))) { + err = -EFAULT; goto err2; + } spin_lock_bh(&rxe->pending_lock); list_add(&ip->pending_mmaps, &rxe->pending_mmaps); @@ -64,7 +67,7 @@ int do_mmap_info(struct rxe_dev *rxe, struct mminfo __user *outbuf, err2: kfree(ip); err1: - return -EINVAL; + return err; } inline void rxe_queue_reset(struct rxe_queue *q) diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c index a03c6d6833df..96fb9ff5ff2e 100644 --- a/drivers/interconnect/qcom/osm-l3.c +++ b/drivers/interconnect/qcom/osm-l3.c @@ -78,7 +78,7 @@ static struct qcom_icc_node *sdm845_osm_l3_nodes[] = { [SLAVE_OSM_L3] = &sdm845_osm_l3, }; -const static struct qcom_icc_desc sdm845_icc_osm_l3 = { +static const struct qcom_icc_desc sdm845_icc_osm_l3 = { .nodes = sdm845_osm_l3_nodes, .num_nodes = ARRAY_SIZE(sdm845_osm_l3_nodes), }; @@ -91,7 +91,7 @@ static struct qcom_icc_node *sc7180_osm_l3_nodes[] = { [SLAVE_OSM_L3] = &sc7180_osm_l3, }; -const static struct qcom_icc_desc sc7180_icc_osm_l3 = { +static const struct qcom_icc_desc sc7180_icc_osm_l3 = { .nodes = sc7180_osm_l3_nodes, .num_nodes = ARRAY_SIZE(sc7180_osm_l3_nodes), }; diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c index b013b80caa45..f6c7b969520d 100644 --- a/drivers/interconnect/qcom/sdm845.c +++ b/drivers/interconnect/qcom/sdm845.c @@ -192,7 +192,7 @@ static struct qcom_icc_node *aggre1_noc_nodes[] = { [SLAVE_ANOC_PCIE_A1NOC_SNOC] = &qns_pcie_a1noc_snoc, }; -const static struct qcom_icc_desc sdm845_aggre1_noc = { +static const struct qcom_icc_desc sdm845_aggre1_noc = { .nodes = aggre1_noc_nodes, .num_nodes = ARRAY_SIZE(aggre1_noc_nodes), .bcms = aggre1_noc_bcms, @@ -220,7 +220,7 @@ static struct qcom_icc_node *aggre2_noc_nodes[] = { [SLAVE_SERVICE_A2NOC] = &srvc_aggre2_noc, }; -const static struct qcom_icc_desc sdm845_aggre2_noc = { +static const struct qcom_icc_desc sdm845_aggre2_noc = { .nodes = aggre2_noc_nodes, .num_nodes = ARRAY_SIZE(aggre2_noc_nodes), .bcms = aggre2_noc_bcms, @@ -281,7 +281,7 @@ static struct qcom_icc_node *config_noc_nodes[] = { [SLAVE_SERVICE_CNOC] = &srvc_cnoc, }; -const static struct qcom_icc_desc sdm845_config_noc = { +static const struct qcom_icc_desc sdm845_config_noc = { .nodes = config_noc_nodes, .num_nodes = ARRAY_SIZE(config_noc_nodes), .bcms = config_noc_bcms, @@ -297,7 +297,7 @@ static struct qcom_icc_node *dc_noc_nodes[] = { [SLAVE_MEM_NOC_CFG] = &qhs_memnoc, }; -const static struct qcom_icc_desc sdm845_dc_noc = { +static const struct qcom_icc_desc sdm845_dc_noc = { .nodes = dc_noc_nodes, .num_nodes = ARRAY_SIZE(dc_noc_nodes), .bcms = dc_noc_bcms, @@ -315,7 +315,7 @@ static struct qcom_icc_node *gladiator_noc_nodes[] = { [SLAVE_SERVICE_GNOC] = &srvc_gnoc, }; -const static struct qcom_icc_desc sdm845_gladiator_noc = { +static const struct qcom_icc_desc sdm845_gladiator_noc = { .nodes = gladiator_noc_nodes, .num_nodes = ARRAY_SIZE(gladiator_noc_nodes), .bcms = gladiator_noc_bcms, @@ -350,7 +350,7 @@ static struct qcom_icc_node *mem_noc_nodes[] = { [SLAVE_EBI1] = &ebi, }; -const static struct qcom_icc_desc sdm845_mem_noc = { +static const struct qcom_icc_desc sdm845_mem_noc = { .nodes = mem_noc_nodes, .num_nodes = ARRAY_SIZE(mem_noc_nodes), .bcms = mem_noc_bcms, @@ -384,7 +384,7 @@ static struct qcom_icc_node *mmss_noc_nodes[] = { [SLAVE_CAMNOC_UNCOMP] = &qns_camnoc_uncomp, }; -const static struct qcom_icc_desc sdm845_mmss_noc = { +static const struct qcom_icc_desc sdm845_mmss_noc = { .nodes = mmss_noc_nodes, .num_nodes = ARRAY_SIZE(mmss_noc_nodes), .bcms = mmss_noc_bcms, @@ -430,7 +430,7 @@ static struct qcom_icc_node *system_noc_nodes[] = { [SLAVE_TCU] = &xs_sys_tcu_cfg, }; -const static struct qcom_icc_desc sdm845_system_noc = { +static const struct qcom_icc_desc sdm845_system_noc = { .nodes = system_noc_nodes, .num_nodes = ARRAY_SIZE(system_noc_nodes), .bcms = system_noc_bcms, diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 20cce366e951..1dc3718560d0 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -101,6 +101,8 @@ struct kmem_cache *amd_iommu_irq_cache; static void update_domain(struct protection_domain *domain); static int protection_domain_init(struct protection_domain *domain); static void detach_device(struct device *dev); +static void update_and_flush_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable); /**************************************************************************** * @@ -151,6 +153,26 @@ static struct protection_domain *to_pdomain(struct iommu_domain *dom) return container_of(dom, struct protection_domain, domain); } +static void amd_iommu_domain_get_pgtable(struct protection_domain *domain, + struct domain_pgtable *pgtable) +{ + u64 pt_root = atomic64_read(&domain->pt_root); + + pgtable->root = (u64 *)(pt_root & PAGE_MASK); + pgtable->mode = pt_root & 7; /* lowest 3 bits encode pgtable mode */ +} + +static u64 amd_iommu_domain_encode_pgtable(u64 *root, int mode) +{ + u64 pt_root; + + /* lowest 3 bits encode pgtable mode */ + pt_root = mode & 7; + pt_root |= (u64)root; + + return pt_root; +} + static struct iommu_dev_data *alloc_dev_data(u16 devid) { struct iommu_dev_data *dev_data; @@ -1397,13 +1419,18 @@ static struct page *free_sub_pt(unsigned long root, int mode, static void free_pagetable(struct protection_domain *domain) { - unsigned long root = (unsigned long)domain->pt_root; + struct domain_pgtable pgtable; struct page *freelist = NULL; + unsigned long root; - BUG_ON(domain->mode < PAGE_MODE_NONE || - domain->mode > PAGE_MODE_6_LEVEL); + amd_iommu_domain_get_pgtable(domain, &pgtable); + atomic64_set(&domain->pt_root, 0); - freelist = free_sub_pt(root, domain->mode, freelist); + BUG_ON(pgtable.mode < PAGE_MODE_NONE || + pgtable.mode > PAGE_MODE_6_LEVEL); + + root = (unsigned long)pgtable.root; + freelist = free_sub_pt(root, pgtable.mode, freelist); free_page_list(freelist); } @@ -1417,24 +1444,39 @@ static bool increase_address_space(struct protection_domain *domain, unsigned long address, gfp_t gfp) { + struct domain_pgtable pgtable; unsigned long flags; - bool ret = false; - u64 *pte; + bool ret = true; + u64 *pte, root; spin_lock_irqsave(&domain->lock, flags); - if (address <= PM_LEVEL_SIZE(domain->mode) || - WARN_ON_ONCE(domain->mode == PAGE_MODE_6_LEVEL)) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (address <= PM_LEVEL_SIZE(pgtable.mode)) + goto out; + + ret = false; + if (WARN_ON_ONCE(pgtable.mode == PAGE_MODE_6_LEVEL)) goto out; pte = (void *)get_zeroed_page(gfp); if (!pte) goto out; - *pte = PM_LEVEL_PDE(domain->mode, - iommu_virt_to_phys(domain->pt_root)); - domain->pt_root = pte; - domain->mode += 1; + *pte = PM_LEVEL_PDE(pgtable.mode, iommu_virt_to_phys(pgtable.root)); + + pgtable.root = pte; + pgtable.mode += 1; + update_and_flush_device_table(domain, &pgtable); + domain_flush_complete(domain); + + /* + * Device Table needs to be updated and flushed before the new root can + * be published. + */ + root = amd_iommu_domain_encode_pgtable(pte, pgtable.mode); + atomic64_set(&domain->pt_root, root); ret = true; @@ -1451,16 +1493,29 @@ static u64 *alloc_pte(struct protection_domain *domain, gfp_t gfp, bool *updated) { + struct domain_pgtable pgtable; int level, end_lvl; u64 *pte, *page; BUG_ON(!is_power_of_2(page_size)); - while (address > PM_LEVEL_SIZE(domain->mode)) - *updated = increase_address_space(domain, address, gfp) || *updated; + amd_iommu_domain_get_pgtable(domain, &pgtable); + + while (address > PM_LEVEL_SIZE(pgtable.mode)) { + /* + * Return an error if there is no memory to update the + * page-table. + */ + if (!increase_address_space(domain, address, gfp)) + return NULL; + + /* Read new values to check if update was successful */ + amd_iommu_domain_get_pgtable(domain, &pgtable); + } + - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + level = pgtable.mode - 1; + pte = &pgtable.root[PM_LEVEL_INDEX(level, address)]; address = PAGE_SIZE_ALIGN(address, page_size); end_lvl = PAGE_SIZE_LEVEL(page_size); @@ -1536,16 +1591,19 @@ static u64 *fetch_pte(struct protection_domain *domain, unsigned long address, unsigned long *page_size) { + struct domain_pgtable pgtable; int level; u64 *pte; *page_size = 0; - if (address > PM_LEVEL_SIZE(domain->mode)) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (address > PM_LEVEL_SIZE(pgtable.mode)) return NULL; - level = domain->mode - 1; - pte = &domain->pt_root[PM_LEVEL_INDEX(level, address)]; + level = pgtable.mode - 1; + pte = &pgtable.root[PM_LEVEL_INDEX(level, address)]; *page_size = PTE_LEVEL_PAGE_SIZE(level); while (level > 0) { @@ -1660,7 +1718,13 @@ out: unsigned long flags; spin_lock_irqsave(&dom->lock, flags); - update_domain(dom); + /* + * Flush domain TLB(s) and wait for completion. Any Device-Table + * Updates and flushing already happened in + * increase_address_space(). + */ + domain_flush_tlb_pde(dom); + domain_flush_complete(dom); spin_unlock_irqrestore(&dom->lock, flags); } @@ -1806,6 +1870,7 @@ static void dma_ops_domain_free(struct protection_domain *domain) static struct protection_domain *dma_ops_domain_alloc(void) { struct protection_domain *domain; + u64 *pt_root, root; domain = kzalloc(sizeof(struct protection_domain), GFP_KERNEL); if (!domain) @@ -1814,12 +1879,14 @@ static struct protection_domain *dma_ops_domain_alloc(void) if (protection_domain_init(domain)) goto free_domain; - domain->mode = PAGE_MODE_3_LEVEL; - domain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - domain->flags = PD_DMA_OPS_MASK; - if (!domain->pt_root) + pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pt_root) goto free_domain; + root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL); + atomic64_set(&domain->pt_root, root); + domain->flags = PD_DMA_OPS_MASK; + if (iommu_get_dma_cookie(&domain->domain) == -ENOMEM) goto free_domain; @@ -1841,16 +1908,17 @@ static bool dma_ops_domain(struct protection_domain *domain) } static void set_dte_entry(u16 devid, struct protection_domain *domain, + struct domain_pgtable *pgtable, bool ats, bool ppr) { u64 pte_root = 0; u64 flags = 0; u32 old_domid; - if (domain->mode != PAGE_MODE_NONE) - pte_root = iommu_virt_to_phys(domain->pt_root); + if (pgtable->mode != PAGE_MODE_NONE) + pte_root = iommu_virt_to_phys(pgtable->root); - pte_root |= (domain->mode & DEV_ENTRY_MODE_MASK) + pte_root |= (pgtable->mode & DEV_ENTRY_MODE_MASK) << DEV_ENTRY_MODE_SHIFT; pte_root |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V | DTE_FLAG_TV; @@ -1923,6 +1991,7 @@ static void clear_dte_entry(u16 devid) static void do_attach(struct iommu_dev_data *dev_data, struct protection_domain *domain) { + struct domain_pgtable pgtable; struct amd_iommu *iommu; bool ats; @@ -1938,7 +2007,9 @@ static void do_attach(struct iommu_dev_data *dev_data, domain->dev_cnt += 1; /* Update device table */ - set_dte_entry(dev_data->devid, domain, ats, dev_data->iommu_v2); + amd_iommu_domain_get_pgtable(domain, &pgtable); + set_dte_entry(dev_data->devid, domain, &pgtable, + ats, dev_data->iommu_v2); clone_aliases(dev_data->pdev); device_flush_dte(dev_data); @@ -2249,23 +2320,36 @@ static int amd_iommu_domain_get_attr(struct iommu_domain *domain, * *****************************************************************************/ -static void update_device_table(struct protection_domain *domain) +static void update_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable) { struct iommu_dev_data *dev_data; list_for_each_entry(dev_data, &domain->dev_list, list) { - set_dte_entry(dev_data->devid, domain, dev_data->ats.enabled, - dev_data->iommu_v2); + set_dte_entry(dev_data->devid, domain, pgtable, + dev_data->ats.enabled, dev_data->iommu_v2); clone_aliases(dev_data->pdev); } } +static void update_and_flush_device_table(struct protection_domain *domain, + struct domain_pgtable *pgtable) +{ + update_device_table(domain, pgtable); + domain_flush_devices(domain); +} + static void update_domain(struct protection_domain *domain) { - update_device_table(domain); + struct domain_pgtable pgtable; - domain_flush_devices(domain); + /* Update device table */ + amd_iommu_domain_get_pgtable(domain, &pgtable); + update_and_flush_device_table(domain, &pgtable); + + /* Flush domain TLB(s) and wait for completion */ domain_flush_tlb_pde(domain); + domain_flush_complete(domain); } int __init amd_iommu_init_api(void) @@ -2375,6 +2459,7 @@ out_err: static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) { struct protection_domain *pdomain; + u64 *pt_root, root; switch (type) { case IOMMU_DOMAIN_UNMANAGED: @@ -2382,13 +2467,15 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) if (!pdomain) return NULL; - pdomain->mode = PAGE_MODE_3_LEVEL; - pdomain->pt_root = (void *)get_zeroed_page(GFP_KERNEL); - if (!pdomain->pt_root) { + pt_root = (void *)get_zeroed_page(GFP_KERNEL); + if (!pt_root) { protection_domain_free(pdomain); return NULL; } + root = amd_iommu_domain_encode_pgtable(pt_root, PAGE_MODE_3_LEVEL); + atomic64_set(&pdomain->pt_root, root); + pdomain->domain.geometry.aperture_start = 0; pdomain->domain.geometry.aperture_end = ~0ULL; pdomain->domain.geometry.force_aperture = true; @@ -2406,7 +2493,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) if (!pdomain) return NULL; - pdomain->mode = PAGE_MODE_NONE; + atomic64_set(&pdomain->pt_root, PAGE_MODE_NONE); break; default: return NULL; @@ -2418,6 +2505,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type) static void amd_iommu_domain_free(struct iommu_domain *dom) { struct protection_domain *domain; + struct domain_pgtable pgtable; domain = to_pdomain(dom); @@ -2435,7 +2523,9 @@ static void amd_iommu_domain_free(struct iommu_domain *dom) dma_ops_domain_free(domain); break; default: - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + + if (pgtable.mode != PAGE_MODE_NONE) free_pagetable(domain); if (domain->flags & PD_IOMMUV2_MASK) @@ -2518,10 +2608,12 @@ static int amd_iommu_map(struct iommu_domain *dom, unsigned long iova, gfp_t gfp) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; int prot = 0; int ret; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return -EINVAL; if (iommu_prot & IOMMU_READ) @@ -2541,8 +2633,10 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova, struct iommu_iotlb_gather *gather) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return 0; return iommu_unmap_page(domain, iova, page_size); @@ -2553,9 +2647,11 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom, { struct protection_domain *domain = to_pdomain(dom); unsigned long offset_mask, pte_pgsize; + struct domain_pgtable pgtable; u64 *pte, __pte; - if (domain->mode == PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode == PAGE_MODE_NONE) return iova; pte = fetch_pte(domain, iova, &pte_pgsize); @@ -2708,16 +2804,26 @@ EXPORT_SYMBOL(amd_iommu_unregister_ppr_notifier); void amd_iommu_domain_direct_map(struct iommu_domain *dom) { struct protection_domain *domain = to_pdomain(dom); + struct domain_pgtable pgtable; unsigned long flags; + u64 pt_root; spin_lock_irqsave(&domain->lock, flags); + /* First save pgtable configuration*/ + amd_iommu_domain_get_pgtable(domain, &pgtable); + /* Update data structure */ - domain->mode = PAGE_MODE_NONE; + pt_root = amd_iommu_domain_encode_pgtable(NULL, PAGE_MODE_NONE); + atomic64_set(&domain->pt_root, pt_root); /* Make changes visible to IOMMUs */ update_domain(domain); + /* Restore old pgtable in domain->ptroot to free page-table */ + pt_root = amd_iommu_domain_encode_pgtable(pgtable.root, pgtable.mode); + atomic64_set(&domain->pt_root, pt_root); + /* Page-table is not visible to IOMMU anymore, so free it */ free_pagetable(domain); @@ -2908,9 +3014,11 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc) static int __set_gcr3(struct protection_domain *domain, int pasid, unsigned long cr3) { + struct domain_pgtable pgtable; u64 *pte; - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode != PAGE_MODE_NONE) return -EINVAL; pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, true); @@ -2924,9 +3032,11 @@ static int __set_gcr3(struct protection_domain *domain, int pasid, static int __clear_gcr3(struct protection_domain *domain, int pasid) { + struct domain_pgtable pgtable; u64 *pte; - if (domain->mode != PAGE_MODE_NONE) + amd_iommu_domain_get_pgtable(domain, &pgtable); + if (pgtable.mode != PAGE_MODE_NONE) return -EINVAL; pte = __get_gcr3_pte(domain->gcr3_tbl, domain->glx, pasid, false); diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h index ca8c4522045b..7a8fdec138bd 100644 --- a/drivers/iommu/amd_iommu_types.h +++ b/drivers/iommu/amd_iommu_types.h @@ -468,8 +468,7 @@ struct protection_domain { iommu core code */ spinlock_t lock; /* mostly used to lock the page table*/ u16 id; /* the domain id written to the device table */ - int mode; /* paging mode (0-6 levels) */ - u64 *pt_root; /* page table root pointer */ + atomic64_t pt_root; /* pgtable root and pgtable mode */ int glx; /* Number of levels for GCR3 table */ u64 *gcr3_tbl; /* Guest CR3 table */ unsigned long flags; /* flags to find out type of domain */ @@ -477,6 +476,12 @@ struct protection_domain { unsigned dev_iommu[MAX_IOMMUS]; /* per-IOMMU reference count */ }; +/* For decocded pt_root */ +struct domain_pgtable { + int mode; + u64 *root; +}; + /* * Structure where we save information about one hardware AMD IOMMU in the * system. diff --git a/drivers/iommu/virtio-iommu.c b/drivers/iommu/virtio-iommu.c index d5cac4f46ca5..4e1d11af23c8 100644 --- a/drivers/iommu/virtio-iommu.c +++ b/drivers/iommu/virtio-iommu.c @@ -453,7 +453,7 @@ static int viommu_add_resv_mem(struct viommu_endpoint *vdev, if (!region) return -ENOMEM; - list_add(&vdev->resv_regions, ®ion->list); + list_add(®ion->list, &vdev->resv_regions); return 0; } diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 668418d7ea77..f620442addf5 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1465,6 +1465,13 @@ static const struct mei_cfg mei_me_pch12_cfg = { MEI_CFG_DMA_128, }; +/* LBG with quirk for SPS Firmware exclusion */ +static const struct mei_cfg mei_me_pch12_sps_cfg = { + MEI_CFG_PCH8_HFS, + MEI_CFG_FW_VER_SUPP, + MEI_CFG_FW_SPS, +}; + /* Tiger Lake and newer devices */ static const struct mei_cfg mei_me_pch15_cfg = { MEI_CFG_PCH8_HFS, @@ -1487,6 +1494,7 @@ static const struct mei_cfg *const mei_cfg_list[] = { [MEI_ME_PCH8_CFG] = &mei_me_pch8_cfg, [MEI_ME_PCH8_SPS_CFG] = &mei_me_pch8_sps_cfg, [MEI_ME_PCH12_CFG] = &mei_me_pch12_cfg, + [MEI_ME_PCH12_SPS_CFG] = &mei_me_pch12_sps_cfg, [MEI_ME_PCH15_CFG] = &mei_me_pch15_cfg, }; diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index 4a8d4dcd5a91..b6b94e211464 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -80,6 +80,9 @@ struct mei_me_hw { * servers platforms with quirk for * SPS firmware exclusion. * @MEI_ME_PCH12_CFG: Platform Controller Hub Gen12 and newer + * @MEI_ME_PCH12_SPS_CFG: Platform Controller Hub Gen12 and newer + * servers platforms with quirk for + * SPS firmware exclusion. * @MEI_ME_PCH15_CFG: Platform Controller Hub Gen15 and newer * @MEI_ME_NUM_CFG: Upper Sentinel. */ @@ -93,6 +96,7 @@ enum mei_cfg_idx { MEI_ME_PCH8_CFG, MEI_ME_PCH8_SPS_CFG, MEI_ME_PCH12_CFG, + MEI_ME_PCH12_SPS_CFG, MEI_ME_PCH15_CFG, MEI_ME_NUM_CFG, }; diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 0c390fe421ad..a1ed375fed37 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -70,7 +70,7 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_2, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H, MEI_ME_PCH8_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_SPT_H_2, MEI_ME_PCH8_SPS_CFG)}, - {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_LBG, MEI_ME_PCH12_SPS_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_BXT_M, MEI_ME_PCH8_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_APL_I, MEI_ME_PCH8_CFG)}, diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index 8499b56a15a8..c5367e2c8487 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1370,6 +1370,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req) struct mmc_request *mrq = &mqrq->brq.mrq; struct request_queue *q = req->q; struct mmc_host *host = mq->card->host; + enum mmc_issue_type issue_type = mmc_issue_type(mq, req); unsigned long flags; bool put_card; int err; @@ -1399,7 +1400,7 @@ static void mmc_blk_cqe_complete_rq(struct mmc_queue *mq, struct request *req) spin_lock_irqsave(&mq->lock, flags); - mq->in_flight[mmc_issue_type(mq, req)] -= 1; + mq->in_flight[issue_type] -= 1; put_card = (mmc_tot_in_flight(mq) == 0); diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 25bee3daf9e2..4b1eb89b401d 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -107,11 +107,10 @@ static enum blk_eh_timer_return mmc_cqe_timed_out(struct request *req) case MMC_ISSUE_DCMD: if (host->cqe_ops->cqe_timeout(host, mrq, &recovery_needed)) { if (recovery_needed) - __mmc_cqe_recovery_notifier(mq); + mmc_cqe_recovery_notifier(mrq); return BLK_EH_RESET_TIMER; } - /* No timeout (XXX: huh? comment doesn't make much sense) */ - blk_mq_complete_request(req); + /* The request has gone already */ return BLK_EH_DONE; default: /* Timeout is handled by mmc core */ @@ -127,18 +126,13 @@ static enum blk_eh_timer_return mmc_mq_timed_out(struct request *req, struct mmc_card *card = mq->card; struct mmc_host *host = card->host; unsigned long flags; - int ret; + bool ignore_tout; spin_lock_irqsave(&mq->lock, flags); - - if (mq->recovery_needed || !mq->use_cqe || host->hsq_enabled) - ret = BLK_EH_RESET_TIMER; - else - ret = mmc_cqe_timed_out(req); - + ignore_tout = mq->recovery_needed || !mq->use_cqe || host->hsq_enabled; spin_unlock_irqrestore(&mq->lock, flags); - return ret; + return ignore_tout ? BLK_EH_RESET_TIMER : mmc_cqe_timed_out(req); } static void mmc_mq_recovery_handler(struct work_struct *work) diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c index 1aee485d56d4..026ca9194ce5 100644 --- a/drivers/mmc/host/alcor.c +++ b/drivers/mmc/host/alcor.c @@ -1104,7 +1104,7 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev) if (ret) { dev_err(&pdev->dev, "Failed to get irq for data line\n"); - return ret; + goto free_host; } mutex_init(&host->cmd_mutex); @@ -1116,6 +1116,10 @@ static int alcor_pci_sdmmc_drv_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, host); mmc_add_host(mmc); return 0; + +free_host: + mmc_free_host(mmc); + return ret; } static int alcor_pci_sdmmc_drv_remove(struct platform_device *pdev) diff --git a/drivers/mmc/host/sdhci-acpi.c b/drivers/mmc/host/sdhci-acpi.c index faba53cf139b..d8b76cb8698a 100644 --- a/drivers/mmc/host/sdhci-acpi.c +++ b/drivers/mmc/host/sdhci-acpi.c @@ -605,10 +605,12 @@ static int sdhci_acpi_emmc_amd_probe_slot(struct platform_device *pdev, } static const struct sdhci_acpi_slot sdhci_acpi_slot_amd_emmc = { - .chip = &sdhci_acpi_chip_amd, - .caps = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE, - .quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | SDHCI_QUIRK_32BIT_DMA_SIZE | - SDHCI_QUIRK_32BIT_ADMA_SIZE, + .chip = &sdhci_acpi_chip_amd, + .caps = MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE, + .quirks = SDHCI_QUIRK_32BIT_DMA_ADDR | + SDHCI_QUIRK_32BIT_DMA_SIZE | + SDHCI_QUIRK_32BIT_ADMA_SIZE, + .quirks2 = SDHCI_QUIRK2_BROKEN_64_BIT_DMA, .probe_slot = sdhci_acpi_emmc_amd_probe_slot, }; diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index ce15a05f23d4..fd76aa672e02 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -26,6 +26,9 @@ #define SDHCI_GLI_9750_DRIVING_2 GENMASK(27, 26) #define GLI_9750_DRIVING_1_VALUE 0xFFF #define GLI_9750_DRIVING_2_VALUE 0x3 +#define SDHCI_GLI_9750_SEL_1 BIT(29) +#define SDHCI_GLI_9750_SEL_2 BIT(31) +#define SDHCI_GLI_9750_ALL_RST (BIT(24)|BIT(25)|BIT(28)|BIT(30)) #define SDHCI_GLI_9750_PLL 0x864 #define SDHCI_GLI_9750_PLL_TX2_INV BIT(23) @@ -122,6 +125,8 @@ static void gli_set_9750(struct sdhci_host *host) GLI_9750_DRIVING_1_VALUE); driving_value |= FIELD_PREP(SDHCI_GLI_9750_DRIVING_2, GLI_9750_DRIVING_2_VALUE); + driving_value &= ~(SDHCI_GLI_9750_SEL_1|SDHCI_GLI_9750_SEL_2|SDHCI_GLI_9750_ALL_RST); + driving_value |= SDHCI_GLI_9750_SEL_2; sdhci_writel(host, driving_value, SDHCI_GLI_9750_DRIVING); sw_ctrl_value &= ~SDHCI_GLI_9750_SW_CTRL_4; @@ -334,6 +339,18 @@ static u32 sdhci_gl9750_readl(struct sdhci_host *host, int reg) return value; } +#ifdef CONFIG_PM_SLEEP +static int sdhci_pci_gli_resume(struct sdhci_pci_chip *chip) +{ + struct sdhci_pci_slot *slot = chip->slots[0]; + + pci_free_irq_vectors(slot->chip->pdev); + gli_pcie_enable_msi(slot); + + return sdhci_pci_resume_host(chip); +} +#endif + static const struct sdhci_ops sdhci_gl9755_ops = { .set_clock = sdhci_set_clock, .enable_dma = sdhci_pci_enable_dma, @@ -348,6 +365,9 @@ const struct sdhci_pci_fixes sdhci_gl9755 = { .quirks2 = SDHCI_QUIRK2_BROKEN_DDR50, .probe_slot = gli_probe_slot_gl9755, .ops = &sdhci_gl9755_ops, +#ifdef CONFIG_PM_SLEEP + .resume = sdhci_pci_gli_resume, +#endif }; static const struct sdhci_ops sdhci_gl9750_ops = { @@ -366,4 +386,7 @@ const struct sdhci_pci_fixes sdhci_gl9750 = { .quirks2 = SDHCI_QUIRK2_BROKEN_DDR50, .probe_slot = gli_probe_slot_gl9750, .ops = &sdhci_gl9750_ops, +#ifdef CONFIG_PM_SLEEP + .resume = sdhci_pci_gli_resume, +#endif }; diff --git a/drivers/most/core.c b/drivers/most/core.c index 06426fc5c990..f781c46cd4af 100644 --- a/drivers/most/core.c +++ b/drivers/most/core.c @@ -1483,7 +1483,7 @@ static void __exit most_exit(void) ida_destroy(&mdev_id); } -module_init(most_init); +subsys_initcall(most_init); module_exit(most_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Christian Gromm <christian.gromm@microchip.com>"); diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index cc0703c3d57f..efd1a1d1f35e 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -136,25 +136,21 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) oiph = skb_network_header(skb); skb_reset_network_header(skb); - if (family == AF_INET) + if (!IS_ENABLED(CONFIG_IPV6) || family == AF_INET) err = IP_ECN_decapsulate(oiph, skb); -#if IS_ENABLED(CONFIG_IPV6) else err = IP6_ECN_decapsulate(oiph, skb); -#endif if (unlikely(err)) { if (log_ecn_error) { - if (family == AF_INET) + if (!IS_ENABLED(CONFIG_IPV6) || family == AF_INET) net_info_ratelimited("non-ECT from %pI4 " "with TOS=%#x\n", &((struct iphdr *)oiph)->saddr, ((struct iphdr *)oiph)->tos); -#if IS_ENABLED(CONFIG_IPV6) else net_info_ratelimited("non-ECT from %pI6\n", &((struct ipv6hdr *)oiph)->saddr); -#endif } if (err > 1) { ++bareudp->dev->stats.rx_frame_errors; @@ -350,7 +346,6 @@ free_dst: return err; } -#if IS_ENABLED(CONFIG_IPV6) static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct bareudp_dev *bareudp, const struct ip_tunnel_info *info) @@ -411,7 +406,6 @@ free_dst: dst_release(dst); return err; } -#endif static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -435,11 +429,9 @@ static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev) } rcu_read_lock(); -#if IS_ENABLED(CONFIG_IPV6) - if (info->mode & IP_TUNNEL_INFO_IPV6) + if (IS_ENABLED(CONFIG_IPV6) && info->mode & IP_TUNNEL_INFO_IPV6) err = bareudp6_xmit_skb(skb, dev, bareudp, info); else -#endif err = bareudp_xmit_skb(skb, dev, bareudp, info); rcu_read_unlock(); @@ -467,7 +459,7 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, use_cache = ip_tunnel_dst_cache_usable(skb, info); - if (ip_tunnel_info_af(info) == AF_INET) { + if (!IS_ENABLED(CONFIG_IPV6) || ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; __be32 saddr; @@ -478,7 +470,6 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, ip_rt_put(rt); info->key.u.ipv4.src = saddr; -#if IS_ENABLED(CONFIG_IPV6) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct in6_addr saddr; @@ -492,7 +483,6 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, dst_release(dst); info->key.u.ipv6.src = saddr; -#endif } else { return -EINVAL; } diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index fdcb70b9f0e4..400207c5c7de 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -360,6 +360,7 @@ static void __exit dsa_loop_exit(void) } module_exit(dsa_loop_exit); +MODULE_SOFTDEP("pre: dsa_loop_bdinfo"); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Florian Fainelli"); MODULE_DESCRIPTION("DSA loopback driver"); diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig index 6435020d690d..51185e4d7d15 100644 --- a/drivers/net/dsa/mv88e6xxx/Kconfig +++ b/drivers/net/dsa/mv88e6xxx/Kconfig @@ -24,8 +24,8 @@ config NET_DSA_MV88E6XXX_PTP bool "PTP support for Marvell 88E6xxx" default n depends on NET_DSA_MV88E6XXX_GLOBAL2 + depends on PTP_1588_CLOCK imply NETWORK_PHY_TIMESTAMPING - imply PTP_1588_CLOCK help Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch chips that support it. diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index dd8a5666a584..2b4a723c8306 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3962,7 +3962,6 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6390_phylink_validate, }; @@ -4021,7 +4020,6 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6390x_phylink_validate, }; @@ -4079,7 +4077,6 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, .phylink_validate = mv88e6390_phylink_validate, @@ -4235,7 +4232,6 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .serdes_get_stats = mv88e6390_serdes_get_stats, .serdes_get_regs_len = mv88e6390_serdes_get_regs_len, .serdes_get_regs = mv88e6390_serdes_get_regs, - .phylink_validate = mv88e6390_phylink_validate, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6390_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index d0a3764ff0cf..e2c6bf0e430e 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -400,6 +400,7 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) ocelot->stats_layout = felix->info->stats_layout; ocelot->num_stats = felix->info->num_stats; ocelot->shared_queue_sz = felix->info->shared_queue_sz; + ocelot->num_mact_rows = felix->info->num_mact_rows; ocelot->vcap_is2_keys = felix->info->vcap_is2_keys; ocelot->vcap_is2_actions= felix->info->vcap_is2_actions; ocelot->vcap = felix->info->vcap; diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 82d46f260041..9af106513e53 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -15,6 +15,7 @@ struct felix_info { const u32 *const *map; const struct ocelot_ops *ops; int shared_queue_sz; + int num_mact_rows; const struct ocelot_stat_layout *stats_layout; unsigned int num_stats; int num_ports; diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index b4078f3c5c38..8bf395f12b47 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1220,6 +1220,7 @@ struct felix_info felix_info_vsc9959 = { .vcap_is2_actions = vsc9959_vcap_is2_actions, .vcap = vsc9959_vcap_props, .shared_queue_sz = 128 * 1024, + .num_mact_rows = 2048, .num_ports = 6, .switch_pci_bar = 4, .imdio_pci_bar = 0, diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig index 0fe1ae173aa1..68c3086af9af 100644 --- a/drivers/net/dsa/sja1105/Kconfig +++ b/drivers/net/dsa/sja1105/Kconfig @@ -20,6 +20,7 @@ tristate "NXP SJA1105 Ethernet switch family support" config NET_DSA_SJA1105_PTP bool "Support for the PTP clock on the NXP SJA1105 Ethernet switch" depends on NET_DSA_SJA1105 + depends on PTP_1588_CLOCK help This enables support for timestamping and PTP clock manipulations in the SJA1105 DSA driver. diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index a22f8e3fc06b..bc0e47c1dbb9 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -16,14 +16,15 @@ /* PTPSYNCTS has no interrupt or update mechanism, because the intended * hardware use case is for the timestamp to be collected synchronously, - * immediately after the CAS_MASTER SJA1105 switch has triggered a CASSYNC - * pulse on the PTP_CLK pin. When used as a generic extts source, it needs - * polling and a comparison with the old value. The polling interval is just - * the Nyquist rate of a canonical PPS input (e.g. from a GPS module). - * Anything of higher frequency than 1 Hz will be lost, since there is no - * timestamp FIFO. + * immediately after the CAS_MASTER SJA1105 switch has performed a CASSYNC + * one-shot toggle (no return to level) on the PTP_CLK pin. When used as a + * generic extts source, the PTPSYNCTS register needs polling and a comparison + * with the old value. The polling interval is configured as the Nyquist rate + * of a signal with 50% duty cycle and 1Hz frequency, which is sadly all that + * this hardware can do (but may be enough for some setups). Anything of higher + * frequency than 1 Hz will be lost, since there is no timestamp FIFO. */ -#define SJA1105_EXTTS_INTERVAL (HZ / 2) +#define SJA1105_EXTTS_INTERVAL (HZ / 4) /* This range is actually +/- SJA1105_MAX_ADJ_PPB * divided by 1000 (ppb -> ppm) and with a 16-bit @@ -754,7 +755,16 @@ static int sja1105_extts_enable(struct sja1105_private *priv, return -EOPNOTSUPP; /* Reject requests with unsupported flags */ - if (extts->flags) + if (extts->flags & ~(PTP_ENABLE_FEATURE | + PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS)) + return -EOPNOTSUPP; + + /* We can only enable time stamping on both edges, sadly. */ + if ((extts->flags & PTP_STRICT_FLAGS) && + (extts->flags & PTP_ENABLE_FEATURE) && + (extts->flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES) return -EOPNOTSUPP; rc = sja1105_change_ptp_clk_pin_func(priv, PTP_PF_EXTTS); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index 97dfd0c67e84..9e1860d81908 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -69,7 +69,7 @@ * 16kB. */ #if PAGE_SIZE > SZ_16K -#define ENA_PAGE_SIZE SZ_16K +#define ENA_PAGE_SIZE (_AC(SZ_16K, UL)) #else #define ENA_PAGE_SIZE PAGE_SIZE #endif diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 2edf137a7030..8a70ffe1d326 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -57,7 +57,7 @@ static const struct aq_board_revision_s hw_atl_boards[] = { { AQ_DEVICE_ID_D108, AQ_HWREV_2, &hw_atl_ops_b0, &hw_atl_b0_caps_aqc108, }, { AQ_DEVICE_ID_D109, AQ_HWREV_2, &hw_atl_ops_b0, &hw_atl_b0_caps_aqc109, }, - { AQ_DEVICE_ID_AQC100, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, }, + { AQ_DEVICE_ID_AQC100, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc100, }, { AQ_DEVICE_ID_AQC107, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc107, }, { AQ_DEVICE_ID_AQC108, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc108, }, { AQ_DEVICE_ID_AQC109, AQ_HWREV_ANY, &hw_atl_ops_b1, &hw_atl_b0_caps_aqc109, }, diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 53055ce5dfd6..2a69c0d06f3c 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -69,6 +69,7 @@ config BCMGENET select BCM7XXX_PHY select MDIO_BCM_UNIMAC select DIMLIB + select BROADCOM_PHY if ARCH_BCM2835 help This driver supports the built-in Ethernet MACs found in the Broadcom BCM7xxx Set Top Box family chipset. diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index a5d1a6cb9ce3..6795b6d95f54 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -172,6 +172,7 @@ static int bgmac_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; struct bgmac *bgmac; + struct resource *regs; const u8 *mac_addr; bgmac = bgmac_alloc(&pdev->dev); @@ -206,16 +207,21 @@ static int bgmac_probe(struct platform_device *pdev) if (IS_ERR(bgmac->plat.base)) return PTR_ERR(bgmac->plat.base); - bgmac->plat.idm_base = - devm_platform_ioremap_resource_byname(pdev, "idm_base"); - if (IS_ERR(bgmac->plat.idm_base)) - return PTR_ERR(bgmac->plat.idm_base); - bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "idm_base"); + if (regs) { + bgmac->plat.idm_base = devm_ioremap_resource(&pdev->dev, regs); + if (IS_ERR(bgmac->plat.idm_base)) + return PTR_ERR(bgmac->plat.idm_base); + bgmac->feature_flags &= ~BGMAC_FEAT_IDM_MASK; + } - bgmac->plat.nicpm_base = - devm_platform_ioremap_resource_byname(pdev, "nicpm_base"); - if (IS_ERR(bgmac->plat.nicpm_base)) - return PTR_ERR(bgmac->plat.nicpm_base); + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nicpm_base"); + if (regs) { + bgmac->plat.nicpm_base = devm_ioremap_resource(&pdev->dev, + regs); + if (IS_ERR(bgmac->plat.nicpm_base)) + return PTR_ERR(bgmac->plat.nicpm_base); + } bgmac->read = platform_bgmac_read; bgmac->write = platform_bgmac_write; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index fead64f1ad90..d1a83716d934 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6642,7 +6642,7 @@ static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp, int rc; if (!mem_size) - return 0; + return -EINVAL; ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE); if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) { @@ -9780,6 +9780,7 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, netdev_features_t features) { struct bnxt *bp = netdev_priv(dev); + netdev_features_t vlan_features; if ((features & NETIF_F_NTUPLE) && !bnxt_rfs_capable(bp)) features &= ~NETIF_F_NTUPLE; @@ -9796,12 +9797,14 @@ static netdev_features_t bnxt_fix_features(struct net_device *dev, /* Both CTAG and STAG VLAN accelaration on the RX side have to be * turned on or off together. */ - if ((features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) != - (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX)) { + vlan_features = features & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX); + if (vlan_features != (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_RX)) { if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) features &= ~(NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); - else + else if (vlan_features) features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; } @@ -12212,12 +12215,15 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) bnxt_ulp_start(bp, err); } - if (result != PCI_ERS_RESULT_RECOVERED && netif_running(netdev)) - dev_close(netdev); + if (result != PCI_ERS_RESULT_RECOVERED) { + if (netif_running(netdev)) + dev_close(netdev); + pci_disable_device(pdev); + } rtnl_unlock(); - return PCI_ERS_RESULT_RECOVERED; + return result; } /** diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index f2caa2756f5b..f6a3250ef1c5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1066,7 +1066,6 @@ struct bnxt_vf_info { #define BNXT_VF_LINK_FORCED 0x4 #define BNXT_VF_LINK_UP 0x8 #define BNXT_VF_TRUST 0x10 - u32 func_flags; /* func cfg flags */ u32 min_tx_rate; u32 max_tx_rate; void *hwrm_cmd_req_addr; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 95f893f2a74d..d5c8bd49383a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -43,7 +43,7 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl) #define BNXT_NVM_CFG_VER_BITS 24 #define BNXT_NVM_CFG_VER_BYTES 4 -#define BNXT_MSIX_VEC_MAX 1280 +#define BNXT_MSIX_VEC_MAX 512 #define BNXT_MSIX_VEC_MIN_MAX 128 enum bnxt_nvm_dir_type { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 6ea3df6da18c..cea2f9958a1d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -85,11 +85,10 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) if (old_setting == setting) return 0; - func_flags = vf->func_flags; if (setting) - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE; else - func_flags |= FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; + func_flags = FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE; /*TODO: if the driver supports VLAN filter on guest VLAN, * the spoof check should also include vlan anti-spoofing */ @@ -98,7 +97,6 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting) req.flags = cpu_to_le32(func_flags); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) { - vf->func_flags = func_flags; if (setting) vf->flags |= BNXT_VF_SPOOFCHK; else @@ -228,7 +226,6 @@ int bnxt_set_vf_mac(struct net_device *dev, int vf_id, u8 *mac) memcpy(vf->mac_addr, mac, ETH_ALEN); bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); memcpy(req.dflt_mac_addr, mac, ETH_ALEN); return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -266,7 +263,6 @@ int bnxt_set_vf_vlan(struct net_device *dev, int vf_id, u16 vlan_id, u8 qos, bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.dflt_vlan = cpu_to_le16(vlan_tag); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -305,7 +301,6 @@ int bnxt_set_vf_bw(struct net_device *dev, int vf_id, int min_tx_rate, return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); req.enables = cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW); req.max_bw = cpu_to_le32(max_tx_rate); req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW); @@ -477,7 +472,6 @@ static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id) vf = &bp->pf.vf[vf_id]; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); req.fid = cpu_to_le16(vf->fw_fid); - req.flags = cpu_to_le32(vf->func_flags); if (is_valid_ether_addr(vf->mac_addr)) { req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig index 53b50c24d9c9..2c4c12b03502 100644 --- a/drivers/net/ethernet/cadence/Kconfig +++ b/drivers/net/ethernet/cadence/Kconfig @@ -35,8 +35,8 @@ config MACB config MACB_USE_HWSTAMP bool "Use IEEE 1588 hwstamp" depends on MACB + depends on PTP_1588_CLOCK default y - imply PTP_1588_CLOCK ---help--- Enable IEEE 1588 Precision Time Protocol (PTP) support for MACB. diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index a0e8c5bbabc0..36290a8e2a84 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -334,8 +334,10 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum) int status; status = pm_runtime_get_sync(&bp->pdev->dev); - if (status < 0) + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); goto mdio_pm_exit; + } status = macb_mdio_wait_for_idle(bp); if (status < 0) @@ -386,8 +388,10 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum, int status; status = pm_runtime_get_sync(&bp->pdev->dev); - if (status < 0) + if (status < 0) { + pm_runtime_put_noidle(&bp->pdev->dev); goto mdio_pm_exit; + } status = macb_mdio_wait_for_idle(bp); if (status < 0) @@ -3816,8 +3820,10 @@ static int at91ether_open(struct net_device *dev) int ret; ret = pm_runtime_get_sync(&lp->pdev->dev); - if (ret < 0) + if (ret < 0) { + pm_runtime_put_noidle(&lp->pdev->dev); return ret; + } /* Clear internal statistics */ ctl = macb_readl(lp, NCR); @@ -4172,15 +4178,9 @@ static int fu540_c000_clk_init(struct platform_device *pdev, struct clk **pclk, static int fu540_c000_init(struct platform_device *pdev) { - struct resource *res; - - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - if (!res) - return -ENODEV; - - mgmt->reg = ioremap(res->start, resource_size(res)); - if (!mgmt->reg) - return -ENOMEM; + mgmt->reg = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(mgmt->reg)) + return PTR_ERR(mgmt->reg); return macb_init(pdev); } diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 6a700d34019e..4520e7ee00fe 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -54,7 +54,7 @@ config THUNDER_NIC_RGX config CAVIUM_PTP tristate "Cavium PTP coprocessor as PTP clock" depends on 64BIT && PCI - imply PTP_1588_CLOCK + depends on PTP_1588_CLOCK ---help--- This driver adds support for the Precision Time Protocol Clocks and Timestamping coprocessor (PTP) found on Cavium processors. diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index f5dd34db4b54..6516c45864b3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2207,6 +2207,9 @@ static void ethofld_hard_xmit(struct net_device *dev, if (unlikely(skip_eotx_wr)) { start = (u64 *)wr; eosw_txq->state = next_state; + eosw_txq->cred -= wrlen16; + eosw_txq->ncompl++; + eosw_txq->last_compl = 0; goto write_wr_headers; } @@ -2365,6 +2368,34 @@ netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev) return cxgb4_eth_xmit(skb, dev); } +static void eosw_txq_flush_pending_skbs(struct sge_eosw_txq *eosw_txq) +{ + int pktcount = eosw_txq->pidx - eosw_txq->last_pidx; + int pidx = eosw_txq->pidx; + struct sk_buff *skb; + + if (!pktcount) + return; + + if (pktcount < 0) + pktcount += eosw_txq->ndesc; + + while (pktcount--) { + pidx--; + if (pidx < 0) + pidx += eosw_txq->ndesc; + + skb = eosw_txq->desc[pidx].skb; + if (skb) { + dev_consume_skb_any(skb); + eosw_txq->desc[pidx].skb = NULL; + eosw_txq->inuse--; + } + } + + eosw_txq->pidx = eosw_txq->last_pidx + 1; +} + /** * cxgb4_ethofld_send_flowc - Send ETHOFLD flowc request to bind eotid to tc. * @dev - netdevice @@ -2440,9 +2471,11 @@ int cxgb4_ethofld_send_flowc(struct net_device *dev, u32 eotid, u32 tc) FW_FLOWC_MNEM_EOSTATE_CLOSING : FW_FLOWC_MNEM_EOSTATE_ESTABLISHED); - eosw_txq->cred -= len16; - eosw_txq->ncompl++; - eosw_txq->last_compl = 0; + /* Free up any pending skbs to ensure there's room for + * termination FLOWC. + */ + if (tc == FW_SCHED_CLS_NONE) + eosw_txq_flush_pending_skbs(eosw_txq); ret = eosw_txq_enqueue(eosw_txq, skb); if (ret) { @@ -2695,6 +2728,7 @@ static void ofldtxq_stop(struct sge_uld_txq *q, struct fw_wr_hdr *wr) * is ever running at a time ... */ static void service_ofldq(struct sge_uld_txq *q) + __must_hold(&q->sendq.lock) { u64 *pos, *before, *end; int credits; diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index 2bd7ace0a953..bfc6bfe94d0a 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -77,6 +77,7 @@ config UCC_GETH depends on QUICC_ENGINE && PPC32 select FSL_PQ_MDIO select PHYLIB + select FIXED_PHY ---help--- This driver supports the Gigabit Ethernet mode of the QUICC Engine, which is available on some Freescale SOCs. @@ -90,6 +91,7 @@ config GIANFAR depends on HAS_DMA select FSL_PQ_MDIO select PHYLIB + select FIXED_PHY select CRC32 ---help--- This driver supports the Gigabit TSEC on the MPC83xx, MPC85xx, diff --git a/drivers/net/ethernet/freescale/dpaa/Kconfig b/drivers/net/ethernet/freescale/dpaa/Kconfig index 3b325733a4f8..0a54c7e0e4ae 100644 --- a/drivers/net/ethernet/freescale/dpaa/Kconfig +++ b/drivers/net/ethernet/freescale/dpaa/Kconfig @@ -3,6 +3,7 @@ menuconfig FSL_DPAA_ETH tristate "DPAA Ethernet" depends on FSL_DPAA && FSL_FMAN select PHYLIB + select FIXED_PHY select FSL_FMAN_MAC ---help--- Data Path Acceleration Architecture Ethernet driver, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index b6c46639aa4c..d97c320a2dc0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -86,7 +86,7 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv, for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) { addr = dpaa2_sg_get_addr(&sgt[i]); sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr); - dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); free_pages((unsigned long)sg_vaddr, 0); @@ -144,7 +144,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv, /* Get the address and length from the S/G entry */ sg_addr = dpaa2_sg_get_addr(sge); sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr); - dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, sg_addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); sg_length = dpaa2_sg_get_len(sge); @@ -185,7 +185,7 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv, (page_address(page) - page_address(head_page)); skb_add_rx_frag(skb, i - 1, head_page, page_offset, - sg_length, DPAA2_ETH_RX_BUF_SIZE); + sg_length, priv->rx_buf_size); } if (dpaa2_sg_is_final(sge)) @@ -211,7 +211,7 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count) for (i = 0; i < count; i++) { vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]); - dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, buf_array[i], priv->rx_buf_size, DMA_BIDIRECTIONAL); free_pages((unsigned long)vaddr, 0); } @@ -335,7 +335,7 @@ static u32 run_xdp(struct dpaa2_eth_priv *priv, break; case XDP_REDIRECT: dma_unmap_page(priv->net_dev->dev.parent, addr, - DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL); + priv->rx_buf_size, DMA_BIDIRECTIONAL); ch->buf_count--; xdp.data_hard_start = vaddr; err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog); @@ -374,7 +374,7 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, trace_dpaa2_rx_fd(priv->net_dev, fd); vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr); - dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_sync_single_for_cpu(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); fas = dpaa2_get_fas(vaddr, false); @@ -393,13 +393,13 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, return; } - dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); skb = build_linear_skb(ch, fd, vaddr); } else if (fd_format == dpaa2_fd_sg) { WARN_ON(priv->xdp_prog); - dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + dma_unmap_page(dev, addr, priv->rx_buf_size, DMA_BIDIRECTIONAL); skb = build_frag_skb(priv, ch, buf_data); free_pages((unsigned long)vaddr, 0); @@ -974,7 +974,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv, if (!page) goto err_alloc; - addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE, + addr = dma_map_page(dev, page, 0, priv->rx_buf_size, DMA_BIDIRECTIONAL); if (unlikely(dma_mapping_error(dev, addr))) goto err_map; @@ -984,7 +984,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv, /* tracing point */ trace_dpaa2_eth_buf_seed(priv->net_dev, page, DPAA2_ETH_RX_BUF_RAW_SIZE, - addr, DPAA2_ETH_RX_BUF_SIZE, + addr, priv->rx_buf_size, bpid); } @@ -1720,7 +1720,7 @@ static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu) int mfl, linear_mfl; mfl = DPAA2_ETH_L2_MAX_FRM(mtu); - linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE - + linear_mfl = priv->rx_buf_size - DPAA2_ETH_RX_HWA_SIZE - dpaa2_eth_rx_head_room(priv) - XDP_PACKET_HEADROOM; if (mfl > linear_mfl) { @@ -2462,6 +2462,11 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv) else rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN; + /* We need to ensure that the buffer size seen by WRIOP is a multiple + * of 64 or 256 bytes depending on the WRIOP version. + */ + priv->rx_buf_size = ALIGN_DOWN(DPAA2_ETH_RX_BUF_SIZE, rx_buf_align); + /* tx buffer */ buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE; buf_layout.pass_timestamp = true; @@ -3126,7 +3131,7 @@ static int bind_dpni(struct dpaa2_eth_priv *priv) pools_params.num_dpbp = 1; pools_params.pools[0].dpbp_id = priv->dpbp_dev->obj_desc.id; pools_params.pools[0].backup_pool = 0; - pools_params.pools[0].buffer_size = DPAA2_ETH_RX_BUF_SIZE; + pools_params.pools[0].buffer_size = priv->rx_buf_size; err = dpni_set_pools(priv->mc_io, 0, priv->mc_token, &pools_params); if (err) { dev_err(dev, "dpni_set_pools() failed\n"); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 7635db3ef903..13242bf5b427 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -382,6 +382,7 @@ struct dpaa2_eth_priv { u16 tx_data_offset; struct fsl_mc_device *dpbp_dev; + u16 rx_buf_size; u16 bpid; struct iommu_domain *iommu_domain; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 94347c695233..b7141fdc279e 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -635,7 +635,7 @@ static int num_rules(struct dpaa2_eth_priv *priv) static int update_cls_rule(struct net_device *net_dev, struct ethtool_rx_flow_spec *new_fs, - int location) + unsigned int location) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct dpaa2_eth_cls_rule *rule; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c index ebc635f8a4cc..15f37c5b8dc1 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c @@ -74,8 +74,8 @@ err_pci_mem_reg: pci_disable_device(pdev); err_pci_enable: err_mdiobus_alloc: - iounmap(port_regs); err_hw_alloc: + iounmap(port_regs); err_ioremap: return err; } diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 3892a2062404..2fff43509098 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -64,7 +64,7 @@ config HNS_MDIO the PHY config HNS - tristate "Hisilicon Network Subsystem Support (Framework)" + tristate ---help--- This selects the framework support for Hisilicon Network Subsystem. It is needed by any driver which provides HNS acceleration engine or make diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c index 8995e32dd1c0..992908e6eebf 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -45,6 +45,8 @@ #define MGMT_MSG_TIMEOUT 5000 +#define SET_FUNC_PORT_MGMT_TIMEOUT 25000 + #define mgmt_to_pfhwdev(pf_mgmt) \ container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt) @@ -238,12 +240,13 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt, u8 *buf_in, u16 in_size, u8 *buf_out, u16 *out_size, enum mgmt_direction_type direction, - u16 resp_msg_id) + u16 resp_msg_id, u32 timeout) { struct hinic_hwif *hwif = pf_to_mgmt->hwif; struct pci_dev *pdev = hwif->pdev; struct hinic_recv_msg *recv_msg; struct completion *recv_done; + unsigned long timeo; u16 msg_id; int err; @@ -267,8 +270,9 @@ static int msg_to_mgmt_sync(struct hinic_pf_to_mgmt *pf_to_mgmt, goto unlock_sync_msg; } - if (!wait_for_completion_timeout(recv_done, - msecs_to_jiffies(MGMT_MSG_TIMEOUT))) { + timeo = msecs_to_jiffies(timeout ? timeout : MGMT_MSG_TIMEOUT); + + if (!wait_for_completion_timeout(recv_done, timeo)) { dev_err(&pdev->dev, "MGMT timeout, MSG id = %d\n", msg_id); err = -ETIMEDOUT; goto unlock_sync_msg; @@ -342,6 +346,7 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, { struct hinic_hwif *hwif = pf_to_mgmt->hwif; struct pci_dev *pdev = hwif->pdev; + u32 timeout = 0; if (sync != HINIC_MGMT_MSG_SYNC) { dev_err(&pdev->dev, "Invalid MGMT msg type\n"); @@ -353,9 +358,12 @@ int hinic_msg_to_mgmt(struct hinic_pf_to_mgmt *pf_to_mgmt, return -EINVAL; } + if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE) + timeout = SET_FUNC_PORT_MGMT_TIMEOUT; + return msg_to_mgmt_sync(pf_to_mgmt, mod, cmd, buf_in, in_size, buf_out, out_size, MGMT_DIRECT_SEND, - MSG_NOT_RESP); + MSG_NOT_RESP, timeout); } /** diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 13560975c103..63b92f6cc856 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -483,7 +483,6 @@ static int hinic_close(struct net_device *netdev) { struct hinic_dev *nic_dev = netdev_priv(netdev); unsigned int flags; - int err; down(&nic_dev->mgmt_lock); @@ -497,20 +496,9 @@ static int hinic_close(struct net_device *netdev) up(&nic_dev->mgmt_lock); - err = hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); - if (err) { - netif_err(nic_dev, drv, netdev, - "Failed to set func port state\n"); - nic_dev->flags |= (flags & HINIC_INTF_UP); - return err; - } + hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); - err = hinic_port_set_state(nic_dev, HINIC_PORT_DISABLE); - if (err) { - netif_err(nic_dev, drv, netdev, "Failed to set port state\n"); - nic_dev->flags |= (flags & HINIC_INTF_UP); - return err; - } + hinic_port_set_func_state(nic_dev, HINIC_FUNC_PORT_DISABLE); if (nic_dev->flags & HINIC_RSS_ENABLE) { hinic_rss_deinit(nic_dev); diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 4bd33245bad6..3de549c6c693 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2189,7 +2189,8 @@ static void __ibmvnic_reset(struct work_struct *work) rc = do_hard_reset(adapter, rwi, reset_state); rtnl_unlock(); } - } else { + } else if (!(rwi->reset_reason == VNIC_RESET_FATAL && + adapter->from_passive_init)) { rc = do_reset(adapter, rwi, reset_state); } kfree(rwi); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c index 8972cdd559e8..7352244c5e68 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c @@ -1428,6 +1428,9 @@ int mvpp2_ethtool_cls_rule_del(struct mvpp2_port *port, struct mvpp2_ethtool_fs *efs; int ret; + if (info->fs.location >= MVPP2_N_RFS_ENTRIES_PER_FLOW) + return -EINVAL; + efs = port->rfs_rules[info->fs.location]; if (!efs) return -EINVAL; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 1fa60e985b43..2b5dad2ec650 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4329,6 +4329,8 @@ static int mvpp2_ethtool_get_rxfh_context(struct net_device *dev, u32 *indir, if (!mvpp22_rss_is_supported()) return -EOPNOTSUPP; + if (rss_context >= MVPP22_N_RSS_TABLES) + return -EINVAL; if (hfunc) *hfunc = ETH_RSS_HASH_CRC32; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 187c633a7af5..f4227517dc8e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -497,13 +497,17 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) hw->irq_name = devm_kmalloc_array(&hw->pdev->dev, num_vec, NAME_SIZE, GFP_KERNEL); - if (!hw->irq_name) + if (!hw->irq_name) { + err = -ENOMEM; goto err_free_netdev; + } hw->affinity_mask = devm_kcalloc(&hw->pdev->dev, num_vec, sizeof(cpumask_var_t), GFP_KERNEL); - if (!hw->affinity_mask) + if (!hw->affinity_mask) { + err = -ENOMEM; goto err_free_netdev; + } err = pci_alloc_irq_vectors(hw->pdev, num_vec, num_vec, PCI_IRQ_MSIX); if (err < 0) { diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 5716c3d2bb86..c72c4e1ea383 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2550,6 +2550,7 @@ static int mlx4_allocate_default_counters(struct mlx4_dev *dev) if (!err || err == -ENOSPC) { priv->def_counter[port] = idx; + err = 0; } else if (err == -ENOENT) { err = 0; continue; @@ -2600,7 +2601,8 @@ int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx, u8 usage) MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED); if (!err) *idx = get_param_l(&out_param); - + if (WARN_ON(err == -ENOSPC)) + err = -EINVAL; return err; } return __mlx4_counter_alloc(dev, idx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 34cba97f7bf4..cede5bdfd598 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -888,7 +888,6 @@ static void cmd_work_handler(struct work_struct *work) } cmd->ent_arr[ent->idx] = ent; - set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); lay = get_inst(cmd, ent->idx); ent->lay = lay; memset(lay, 0, sizeof(*lay)); @@ -910,6 +909,7 @@ static void cmd_work_handler(struct work_struct *work) if (ent->callback) schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); /* Skip sending command to fw if internal error */ if (pci_channel_offline(dev->pdev) || @@ -922,6 +922,10 @@ static void cmd_work_handler(struct work_struct *work) MLX5_SET(mbox_out, ent->out, syndrome, drv_synd); mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + /* no doorbell, no need to keep the entry */ + free_ent(cmd, ent->idx); + if (ent->callback) + free_cmd(ent); return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 55457f268495..f372e94948fd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1773,19 +1773,14 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) static int mlx5e_init_ul_rep_rx(struct mlx5e_priv *priv) { - int err = mlx5e_init_rep_rx(priv); - - if (err) - return err; - mlx5e_create_q_counters(priv); - return 0; + return mlx5e_init_rep_rx(priv); } static void mlx5e_cleanup_ul_rep_rx(struct mlx5e_priv *priv) { - mlx5e_destroy_q_counters(priv); mlx5e_cleanup_rep_rx(priv); + mlx5e_destroy_q_counters(priv); } static int mlx5e_init_uplink_rep_tx(struct mlx5e_rep_priv *rpriv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index b2e38e0cde97..5d9def18ae3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1550,9 +1550,9 @@ static int esw_create_restore_table(struct mlx5_eswitch *esw) MLX5_FLOW_NAMESPACE_KERNEL, 1, modact); if (IS_ERR(mod_hdr)) { + err = PTR_ERR(mod_hdr); esw_warn(dev, "Failed to create restore mod header, err: %d\n", err); - err = PTR_ERR(mod_hdr); goto err_mod_hdr; } @@ -2219,10 +2219,12 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev); memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb)); + mutex_init(&esw->fdb_table.offloads.vports.lock); + hash_init(esw->fdb_table.offloads.vports.table); err = esw_create_uplink_offloads_acl_tables(esw); if (err) - return err; + goto create_acl_err; err = esw_create_offloads_table(esw, total_vports); if (err) @@ -2240,9 +2242,6 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) if (err) goto create_fg_err; - mutex_init(&esw->fdb_table.offloads.vports.lock); - hash_init(esw->fdb_table.offloads.vports.table); - return 0; create_fg_err: @@ -2253,18 +2252,19 @@ create_restore_err: esw_destroy_offloads_table(esw); create_offloads_err: esw_destroy_uplink_offloads_acl_tables(esw); - +create_acl_err: + mutex_destroy(&esw->fdb_table.offloads.vports.lock); return err; } static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) { - mutex_destroy(&esw->fdb_table.offloads.vports.lock); esw_destroy_vport_rx_group(esw); esw_destroy_offloads_fdb_tables(esw); esw_destroy_restore_table(esw); esw_destroy_offloads_table(esw); esw_destroy_uplink_offloads_acl_tables(esw); + mutex_destroy(&esw->fdb_table.offloads.vports.lock); } static void @@ -2377,9 +2377,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) err_vports: esw_offloads_unload_rep(esw, MLX5_VPORT_UPLINK); err_uplink: - esw_set_passing_vport_metadata(esw, false); -err_steering_init: esw_offloads_steering_cleanup(esw); +err_steering_init: + esw_set_passing_vport_metadata(esw, false); err_vport_metadata: mlx5_rdma_disable_roce(esw->dev); mutex_destroy(&esw->offloads.termtbl_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index c0ab9cf74929..18719acb7e54 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -695,6 +695,12 @@ static void dr_cq_event(struct mlx5_core_cq *mcq, pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn); } +static void dr_cq_complete(struct mlx5_core_cq *mcq, + struct mlx5_eqe *eqe) +{ + pr_err("CQ completion CQ: #%u\n", mcq->cqn); +} + static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, struct mlx5_uars_page *uar, size_t ncqe) @@ -756,6 +762,7 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas); cq->mcq.event = dr_cq_event; + cq->mcq.comp = dr_cq_complete; err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out)); kvfree(in); @@ -767,7 +774,12 @@ static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, cq->mcq.set_ci_db = cq->wq_ctrl.db.db; cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; *cq->mcq.set_ci_db = 0; - *cq->mcq.arm_db = 0; + + /* set no-zero value, in order to avoid the HW to run db-recovery on + * CQ that used in polling mode. + */ + *cq->mcq.arm_db = cpu_to_be32(2 << 28); + cq->mcq.vector = 0; cq->mcq.irqn = irqn; cq->mcq.uar = uar; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 430da69003d8..a6e30e020b5c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -986,8 +986,9 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, unsigned int priority, struct mlxsw_afk_element_usage *elusage) { + struct mlxsw_sp_acl_tcam_vchunk *vchunk, *vchunk2; struct mlxsw_sp_acl_tcam_vregion *vregion; - struct mlxsw_sp_acl_tcam_vchunk *vchunk; + struct list_head *pos; int err; if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO) @@ -1025,7 +1026,14 @@ mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, } mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion); - list_add_tail(&vchunk->list, &vregion->vchunk_list); + + /* Position the vchunk inside the list according to priority */ + list_for_each(pos, &vregion->vchunk_list) { + vchunk2 = list_entry(pos, typeof(*vchunk2), list); + if (vchunk2->priority > priority) + break; + } + list_add_tail(&vchunk->list, pos); mutex_unlock(&vregion->lock); return vchunk; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 51117a5a6bbf..890b078851c9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -36,7 +36,8 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack); if (err) return err; - } else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED) { + } else if (act->hw_stats != FLOW_ACTION_HW_STATS_DISABLED && + act->hw_stats != FLOW_ACTION_HW_STATS_DONT_CARE) { NL_SET_ERR_MSG_MOD(extack, "Unsupported action HW stats type"); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/microchip/encx24j600.c b/drivers/net/ethernet/microchip/encx24j600.c index 39925e4bf2ec..b25a13da900a 100644 --- a/drivers/net/ethernet/microchip/encx24j600.c +++ b/drivers/net/ethernet/microchip/encx24j600.c @@ -1070,7 +1070,7 @@ static int encx24j600_spi_probe(struct spi_device *spi) if (unlikely(ret)) { netif_err(priv, probe, ndev, "Error %d initializing card encx24j600 card\n", ret); - goto out_free; + goto out_stop; } eidled = encx24j600_read_reg(priv, EIDLED); @@ -1088,6 +1088,8 @@ static int encx24j600_spi_probe(struct spi_device *spi) out_unregister: unregister_netdev(priv->ndev); +out_stop: + kthread_stop(priv->kworker_task); out_free: free_netdev(ndev); @@ -1100,6 +1102,7 @@ static int encx24j600_spi_remove(struct spi_device *spi) struct encx24j600_priv *priv = dev_get_drvdata(&spi->dev); unregister_netdev(priv->ndev); + kthread_stop(priv->kworker_task); free_netdev(priv->ndev); diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index e1651756bf9d..f70bb81e1ed6 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -564,7 +564,7 @@ static int moxart_remove(struct platform_device *pdev) struct net_device *ndev = platform_get_drvdata(pdev); unregister_netdev(ndev); - free_irq(ndev->irq, ndev); + devm_free_irq(&pdev->dev, ndev->irq, ndev); moxart_mac_free_memory(ndev); free_netdev(ndev); diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index a8c48a4a708f..02350c3d9d01 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -1031,10 +1031,8 @@ int ocelot_fdb_dump(struct ocelot *ocelot, int port, { int i, j; - /* Loop through all the mac tables entries. There are 1024 rows of 4 - * entries. - */ - for (i = 0; i < 1024; i++) { + /* Loop through all the mac tables entries. */ + for (i = 0; i < ocelot->num_mact_rows; i++) { for (j = 0; j < 4; j++) { struct ocelot_mact_entry entry; bool is_static; @@ -1453,8 +1451,15 @@ static void ocelot_port_attr_stp_state_set(struct ocelot *ocelot, int port, void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs) { - ocelot_write(ocelot, ANA_AUTOAGE_AGE_PERIOD(msecs / 2), - ANA_AUTOAGE); + unsigned int age_period = ANA_AUTOAGE_AGE_PERIOD(msecs / 2000); + + /* Setting AGE_PERIOD to zero effectively disables automatic aging, + * which is clearly not what our intention is. So avoid that. + */ + if (!age_period) + age_period = 1; + + ocelot_rmw(ocelot, age_period, ANA_AUTOAGE_AGE_PERIOD_M, ANA_AUTOAGE); } EXPORT_SYMBOL(ocelot_set_ageing_time); diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c index b88b5899b227..7d4fd1b6adda 100644 --- a/drivers/net/ethernet/mscc/ocelot_regs.c +++ b/drivers/net/ethernet/mscc/ocelot_regs.c @@ -431,6 +431,7 @@ int ocelot_chip_init(struct ocelot *ocelot, const struct ocelot_ops *ops) ocelot->stats_layout = ocelot_stats_layout; ocelot->num_stats = ARRAY_SIZE(ocelot_stats_layout); ocelot->shared_queue_sz = 224 * 1024; + ocelot->num_mact_rows = 1024; ocelot->ops = ops; ret = ocelot_regfields_init(ocelot, ocelot_regfields); diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c index bfa0c0d39600..8b018ed37b1b 100644 --- a/drivers/net/ethernet/natsemi/jazzsonic.c +++ b/drivers/net/ethernet/natsemi/jazzsonic.c @@ -208,11 +208,13 @@ static int jazz_sonic_probe(struct platform_device *pdev) err = register_netdev(dev); if (err) - goto out1; + goto undo_probe1; return 0; -out1: +undo_probe1: + dma_free_coherent(lp->device, SIZEOF_SONIC_DESC * SONIC_BUS_SCALE(lp->dma_bitmode), + lp->descriptors, lp->descriptors_laddr); release_mem_region(dev->base_addr, SONIC_MEM_SIZE); out: free_netdev(dev); diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c index 9183b3e85d21..bdbf0726145e 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/main.c +++ b/drivers/net/ethernet/netronome/nfp/abm/main.c @@ -283,6 +283,7 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn, if (!nfp_nsp_has_hwinfo_lookup(nsp)) { nfp_warn(pf->cpp, "NSP doesn't support PF MAC generation\n"); eth_hw_addr_random(nn->dp.netdev); + nfp_nsp_close(nsp); return; } @@ -332,8 +333,10 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) goto err_free_alink; alink->prio_map = kzalloc(abm->prio_map_len, GFP_KERNEL); - if (!alink->prio_map) + if (!alink->prio_map) { + err = -ENOMEM; goto err_free_alink; + } /* This is a multi-host app, make sure MAC/PHY is up, but don't * make the MAC/PHY state follow the state of any of the ports. diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c index 5f8fc58d42b3..11621ccc1faf 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -170,8 +170,7 @@ void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) debugfs_create_x64("base_pa", 0400, cq_dentry, &cq->base_pa); debugfs_create_u32("num_descs", 0400, cq_dentry, &cq->num_descs); debugfs_create_u32("desc_size", 0400, cq_dentry, &cq->desc_size); - debugfs_create_u8("done_color", 0400, cq_dentry, - (u8 *)&cq->done_color); + debugfs_create_bool("done_color", 0400, cq_dentry, &cq->done_color); debugfs_create_file("tail", 0400, cq_dentry, cq, &cq_tail_fops); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index 5acf4f46c268..f8a9c1bcffc9 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2101,6 +2101,7 @@ static void ionic_lif_handle_fw_down(struct ionic_lif *lif) ionic_txrx_free(lif); } ionic_lifs_deinit(ionic); + ionic_reset(ionic); ionic_qcqs_free(lif); dev_info(ionic->dev, "FW Down: LIFs stopped\n"); @@ -2116,6 +2117,8 @@ static void ionic_lif_handle_fw_up(struct ionic_lif *lif) dev_info(ionic->dev, "FW Up: restarting LIFs\n"); + ionic_init_devinfo(ionic); + ionic_port_init(ionic); err = ionic_qcqs_alloc(lif); if (err) goto err_out; @@ -2346,7 +2349,17 @@ static int ionic_station_set(struct ionic_lif *lif) if (is_zero_ether_addr(ctx.comp.lif_getattr.mac)) return 0; - if (!ether_addr_equal(ctx.comp.lif_getattr.mac, netdev->dev_addr)) { + if (!is_zero_ether_addr(netdev->dev_addr)) { + /* If the netdev mac is non-zero and doesn't match the default + * device address, it was set by something earlier and we're + * likely here again after a fw-upgrade reset. We need to be + * sure the netdev mac is in our filter list. + */ + if (!ether_addr_equal(ctx.comp.lif_getattr.mac, + netdev->dev_addr)) + ionic_lif_addr(lif, netdev->dev_addr, true); + } else { + /* Update the netdev mac with the device's mac */ memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); addr.sa_family = AF_INET; err = eth_prepare_mac_addr_change(netdev, &addr); @@ -2356,12 +2369,6 @@ static int ionic_station_set(struct ionic_lif *lif) return 0; } - if (!is_zero_ether_addr(netdev->dev_addr)) { - netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n", - netdev->dev_addr); - ionic_lif_addr(lif, netdev->dev_addr, false); - } - eth_commit_mac_addr_change(netdev, &addr); } @@ -2549,8 +2556,6 @@ int ionic_lifs_register(struct ionic *ionic) dev_err(ionic->dev, "Cannot register net device, aborting\n"); return err; } - - ionic_link_status_check_request(ionic->master_lif); ionic->master_lif->registered = true; return 0; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c index 588c62e9add7..3344bc1f7671 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -509,16 +509,16 @@ int ionic_port_init(struct ionic *ionic) size_t sz; int err; - if (idev->port_info) - return 0; - - idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE); - idev->port_info = dma_alloc_coherent(ionic->dev, idev->port_info_sz, - &idev->port_info_pa, - GFP_KERNEL); if (!idev->port_info) { - dev_err(ionic->dev, "Failed to allocate port info, aborting\n"); - return -ENOMEM; + idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE); + idev->port_info = dma_alloc_coherent(ionic->dev, + idev->port_info_sz, + &idev->port_info_pa, + GFP_KERNEL); + if (!idev->port_info) { + dev_err(ionic->dev, "Failed to allocate port info\n"); + return -ENOMEM; + } } sz = min(sizeof(ident->port.config), sizeof(idev->dev_cmd_regs->data)); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index bf5bf05970a2..78e15cc00e0a 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2127,6 +2127,8 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) { 0x7cf, 0x348, RTL_GIGA_MAC_VER_07 }, { 0x7cf, 0x248, RTL_GIGA_MAC_VER_07 }, { 0x7cf, 0x340, RTL_GIGA_MAC_VER_13 }, + /* RTL8401, reportedly works if treated as RTL8101e */ + { 0x7cf, 0x240, RTL_GIGA_MAC_VER_13 }, { 0x7cf, 0x343, RTL_GIGA_MAC_VER_10 }, { 0x7cf, 0x342, RTL_GIGA_MAC_VER_16 }, { 0x7c8, 0x348, RTL_GIGA_MAC_VER_09 }, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index e0a5fe83d8e0..bfc4a92f1d92 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -75,6 +75,11 @@ struct ethqos_emac_por { unsigned int value; }; +struct ethqos_emac_driver_data { + const struct ethqos_emac_por *por; + unsigned int num_por; +}; + struct qcom_ethqos { struct platform_device *pdev; void __iomem *rgmii_base; @@ -171,6 +176,11 @@ static const struct ethqos_emac_por emac_v2_3_0_por[] = { { .offset = RGMII_IO_MACRO_CONFIG2, .value = 0x00002060 }, }; +static const struct ethqos_emac_driver_data emac_v2_3_0_data = { + .por = emac_v2_3_0_por, + .num_por = ARRAY_SIZE(emac_v2_3_0_por), +}; + static int ethqos_dll_configure(struct qcom_ethqos *ethqos) { unsigned int val; @@ -442,6 +452,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; + const struct ethqos_emac_driver_data *data; struct qcom_ethqos *ethqos; struct resource *res; int ret; @@ -471,7 +482,9 @@ static int qcom_ethqos_probe(struct platform_device *pdev) goto err_mem; } - ethqos->por = of_device_get_match_data(&pdev->dev); + data = of_device_get_match_data(&pdev->dev); + ethqos->por = data->por; + ethqos->num_por = data->num_por; ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii"); if (IS_ERR(ethqos->rgmii_clk)) { @@ -526,7 +539,7 @@ static int qcom_ethqos_remove(struct platform_device *pdev) } static const struct of_device_id qcom_ethqos_match[] = { - { .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_por}, + { .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_data}, { } }; MODULE_DEVICE_TABLE(of, qcom_ethqos_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index 494c859b4ade..67ba67ed0cb9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -624,7 +624,7 @@ int dwmac5_est_configure(void __iomem *ioaddr, struct stmmac_est *cfg, total_offset += offset; } - total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000; + total_ctr = cfg->ctr[0] + cfg->ctr[1] * 1000000000ULL; total_ctr += total_offset; ctr_low = do_div(total_ctr, 1000000000); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 565da6498c84..a999d6b33a64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4060,7 +4060,7 @@ static int stmmac_set_features(struct net_device *netdev, /** * stmmac_interrupt - main ISR * @irq: interrupt number. - * @dev_id: to pass the net device pointer. + * @dev_id: to pass the net device pointer (must be valid). * Description: this is the main driver interrupt service routine. * It can call: * o DMA service routine (to manage incoming frame reception and transmission @@ -4084,11 +4084,6 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) if (priv->irq_wake) pm_wakeup_event(priv->device, 0); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -4991,7 +4986,7 @@ int stmmac_dvr_probe(struct device *device, priv->plat->bsp_priv); if (ret < 0) - return ret; + goto error_serdes_powerup; } #ifdef CONFIG_DEBUG_FS @@ -5000,6 +4995,8 @@ int stmmac_dvr_probe(struct device *device, return ret; +error_serdes_powerup: + unregister_netdev(ndev); error_netdev_register: phylink_destroy(priv->phylink); error_phy_setup: diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 89cec778cf2d..62f809b67469 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -49,6 +49,7 @@ config TI_CPSW_PHY_SEL config TI_CPSW tristate "TI CPSW Switch Support" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST + depends on TI_CPTS || !TI_CPTS select TI_DAVINCI_MDIO select MFD_SYSCON select PAGE_POOL @@ -64,6 +65,7 @@ config TI_CPSW_SWITCHDEV tristate "TI CPSW Switch Support with switchdev" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST depends on NET_SWITCHDEV + depends on TI_CPTS || !TI_CPTS select PAGE_POOL select TI_DAVINCI_MDIO select MFD_SYSCON @@ -77,24 +79,16 @@ config TI_CPSW_SWITCHDEV will be called cpsw_new. config TI_CPTS - bool "TI Common Platform Time Sync (CPTS) Support" - depends on TI_CPSW || TI_KEYSTONE_NETCP || TI_CPSW_SWITCHDEV || COMPILE_TEST + tristate "TI Common Platform Time Sync (CPTS) Support" + depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST depends on COMMON_CLK - depends on POSIX_TIMERS + depends on PTP_1588_CLOCK ---help--- This driver supports the Common Platform Time Sync unit of the CPSW Ethernet Switch and Keystone 2 1g/10g Switch Subsystem. The unit can time stamp PTP UDP/IPv4 and Layer 2 packets, and the driver offers a PTP Hardware Clock. -config TI_CPTS_MOD - tristate - depends on TI_CPTS - default y if TI_CPSW=y || TI_KEYSTONE_NETCP=y || TI_CPSW_SWITCHDEV=y - select NET_PTP_CLASSIFY - imply PTP_1588_CLOCK - default m - config TI_K3_AM65_CPSW_NUSS tristate "TI K3 AM654x/J721E CPSW Ethernet driver" depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER @@ -115,6 +109,7 @@ config TI_KEYSTONE_NETCP select TI_DAVINCI_MDIO depends on OF depends on KEYSTONE_NAVIGATOR_DMA && KEYSTONE_NAVIGATOR_QMSS + depends on TI_CPTS || !TI_CPTS ---help--- This driver supports TI's Keystone NETCP Core. diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index 53792190e9c2..cb26a9d21869 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_TI_DAVINCI_EMAC) += ti_davinci_emac.o ti_davinci_emac-y := davinci_emac.o davinci_cpdma.o obj-$(CONFIG_TI_DAVINCI_MDIO) += davinci_mdio.o obj-$(CONFIG_TI_CPSW_PHY_SEL) += cpsw-phy-sel.o -obj-$(CONFIG_TI_CPTS_MOD) += cpts.o +obj-$(CONFIG_TI_CPTS) += cpts.o obj-$(CONFIG_TI_CPSW) += ti_cpsw.o ti_cpsw-y := cpsw.o davinci_cpdma.o cpsw_ale.o cpsw_priv.o cpsw_sl.o cpsw_ethtool.o obj-$(CONFIG_TI_CPSW_SWITCHDEV) += ti_cpsw_new.o diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 2bf56733ba94..2517ffba8178 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1719,7 +1719,8 @@ static int am65_cpsw_nuss_ndev_add_napi_2g(struct am65_cpsw_common *common) ret = devm_request_irq(dev, tx_chn->irq, am65_cpsw_nuss_tx_irq, - 0, tx_chn->tx_chn_name, tx_chn); + IRQF_TRIGGER_HIGH, + tx_chn->tx_chn_name, tx_chn); if (ret) { dev_err(dev, "failure requesting tx%u irq %u, %d\n", tx_chn->id, tx_chn->irq, ret); @@ -1744,7 +1745,7 @@ static int am65_cpsw_nuss_ndev_reg_2g(struct am65_cpsw_common *common) ret = devm_request_irq(dev, common->rx_chns.irq, am65_cpsw_nuss_rx_irq, - 0, dev_name(dev), common); + IRQF_TRIGGER_HIGH, dev_name(dev), common); if (ret) { dev_err(dev, "failure requesting rx irq %u, %d\n", common->rx_chns.irq, ret); diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index b50c3ec3495b..6bcda20ed7e7 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -643,7 +643,7 @@ static int tc_mii_probe(struct net_device *dev) linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask); linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask); } - linkmode_and(phydev->supported, phydev->supported, mask); + linkmode_andnot(phydev->supported, phydev->supported, mask); linkmode_copy(phydev->advertising, phydev->supported); lp->link = 0; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 672cd2caf2fb..21640a035d7d 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1169,11 +1169,11 @@ out_unlock: static struct genl_family gtp_genl_family; static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq, - u32 type, struct pdp_ctx *pctx) + int flags, u32 type, struct pdp_ctx *pctx) { void *genlh; - genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, 0, + genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, flags, type); if (genlh == NULL) goto nlmsg_failure; @@ -1227,8 +1227,8 @@ static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info) goto err_unlock; } - err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid, - info->snd_seq, info->nlhdr->nlmsg_type, pctx); + err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid, info->snd_seq, + 0, info->nlhdr->nlmsg_type, pctx); if (err < 0) goto err_unlock_free; @@ -1271,6 +1271,7 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb, gtp_genl_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + NLM_F_MULTI, cb->nlh->nlmsg_type, pctx)) { cb->args[0] = i; cb->args[1] = j; diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index fbea6f232819..e2ad3c2e8df5 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -127,7 +127,8 @@ static inline struct net_device *bpq_get_ax25_dev(struct net_device *dev) { struct bpqdev *bpq; - list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list) { + list_for_each_entry_rcu(bpq, &bpq_devices, bpq_list, + lockdep_rtnl_is_held()) { if (bpq->ethdev == dev) return bpq->axdev; } diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index d8e86bdbfba1..ebcfbae05690 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -707,7 +707,8 @@ no_memory: goto drop; } -static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t netvsc_start_xmit(struct sk_buff *skb, + struct net_device *ndev) { return netvsc_xmit(skb, ndev, false); } diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index 845478a19a4f..b671bea0aa7c 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -1041,6 +1041,7 @@ static void gsi_isr_gp_int1(struct gsi *gsi) complete(&gsi->completion); } + /* Inter-EE interrupt handler */ static void gsi_isr_glob_ee(struct gsi *gsi) { @@ -1493,6 +1494,12 @@ static int gsi_generic_command(struct gsi *gsi, u32 channel_id, struct completion *completion = &gsi->completion; u32 val; + /* First zero the result code field */ + val = ioread32(gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET); + val &= ~GENERIC_EE_RESULT_FMASK; + iowrite32(val, gsi->virt + GSI_CNTXT_SCRATCH_0_OFFSET); + + /* Now issue the command */ val = u32_encode_bits(opcode, GENERIC_OPCODE_FMASK); val |= u32_encode_bits(channel_id, GENERIC_CHID_FMASK); val |= u32_encode_bits(GSI_EE_MODEM, GENERIC_EE_FMASK); @@ -1798,9 +1805,9 @@ static int gsi_channel_init_one(struct gsi *gsi, /* Worst case we need an event for every outstanding TRE */ if (data->channel.tre_count > data->channel.event_count) { - dev_warn(gsi->dev, "channel %u limited to %u TREs\n", - data->channel_id, data->channel.tre_count); tre_count = data->channel.event_count; + dev_warn(gsi->dev, "channel %u limited to %u TREs\n", + data->channel_id, tre_count); } else { tre_count = data->channel.tre_count; } diff --git a/drivers/net/ipa/gsi_reg.h b/drivers/net/ipa/gsi_reg.h index 7613b9cc7cf6..acc9e744c67d 100644 --- a/drivers/net/ipa/gsi_reg.h +++ b/drivers/net/ipa/gsi_reg.h @@ -410,6 +410,8 @@ #define INTER_EE_RESULT_FMASK GENMASK(2, 0) #define GENERIC_EE_RESULT_FMASK GENMASK(7, 5) #define GENERIC_EE_SUCCESS_FVAL 1 +#define GENERIC_EE_INCORRECT_DIRECTION_FVAL 3 +#define GENERIC_EE_INCORRECT_CHANNEL_FVAL 5 #define GENERIC_EE_NO_RESOURCES_FVAL 7 #define USB_MAX_PACKET_FMASK GENMASK(15, 15) /* 0: HS; 1: SS */ #define MHI_BASE_CHANNEL_FMASK GENMASK(31, 24) diff --git a/drivers/net/ipa/gsi_trans.c b/drivers/net/ipa/gsi_trans.c index 2fd21d75367d..bdbfeed359db 100644 --- a/drivers/net/ipa/gsi_trans.c +++ b/drivers/net/ipa/gsi_trans.c @@ -399,13 +399,14 @@ void gsi_trans_cmd_add(struct gsi_trans *trans, void *buf, u32 size, /* assert(which < trans->tre_count); */ /* Set the page information for the buffer. We also need to fill in - * the DMA address for the buffer (something dma_map_sg() normally - * does). + * the DMA address and length for the buffer (something dma_map_sg() + * normally does). */ sg = &trans->sgl[which]; sg_set_buf(sg, buf, size); sg_dma_address(sg) = addr; + sg_dma_len(sg) = sg->length; info = &trans->info[which]; info->opcode = opcode; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index d226b858742d..cee417181f98 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -628,23 +628,15 @@ static void ipa_cmd_transfer_add(struct gsi_trans *trans, u16 size) void ipa_cmd_tag_process_add(struct gsi_trans *trans) { - ipa_cmd_register_write_add(trans, 0, 0, 0, true); -#if 1 - /* Reference these functions to avoid a compile error */ - (void)ipa_cmd_ip_packet_init_add; - (void)ipa_cmd_ip_tag_status_add; - (void) ipa_cmd_transfer_add; -#else struct ipa *ipa = container_of(trans->gsi, struct ipa, gsi); - struct gsi_endpoint *endpoint; + struct ipa_endpoint *endpoint; endpoint = ipa->name_map[IPA_ENDPOINT_AP_LAN_RX]; - ipa_cmd_ip_packet_init_add(trans, endpoint->endpoint_id); + ipa_cmd_register_write_add(trans, 0, 0, 0, true); + ipa_cmd_ip_packet_init_add(trans, endpoint->endpoint_id); ipa_cmd_ip_tag_status_add(trans, 0xcba987654321); - ipa_cmd_transfer_add(trans, 4); -#endif } /* Returns the number of commands required for the tag process */ diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index 6de03be28784..a21534f1462f 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -1283,7 +1283,7 @@ static int ipa_endpoint_stop_rx_dma(struct ipa *ipa) */ int ipa_endpoint_stop(struct ipa_endpoint *endpoint) { - u32 retries = endpoint->toward_ipa ? 0 : IPA_ENDPOINT_STOP_RX_RETRIES; + u32 retries = IPA_ENDPOINT_STOP_RX_RETRIES; int ret; do { @@ -1291,12 +1291,9 @@ int ipa_endpoint_stop(struct ipa_endpoint *endpoint) struct gsi *gsi = &ipa->gsi; ret = gsi_channel_stop(gsi, endpoint->channel_id); - if (ret != -EAGAIN) + if (ret != -EAGAIN || endpoint->toward_ipa) break; - if (endpoint->toward_ipa) - continue; - /* For IPA v3.5.1, send a DMA read task and check again */ if (ipa->version == IPA_VERSION_3_5_1) { ret = ipa_endpoint_stop_rx_dma(ipa); diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index 4d33aa7ebfbb..a5f7a79a1923 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -53,7 +53,7 @@ * @clock_on: Whether IPA clock is on * @notified: Whether modem has been notified of clock state * @disabled: Whether setup ready interrupt handling is disabled - * @mutex mutex: Motex protecting ready interrupt/shutdown interlock + * @mutex: Mutex protecting ready-interrupt/shutdown interlock * @panic_notifier: Panic notifier structure */ struct ipa_smp2p { diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 758baf7cb8a1..d0d31cb99180 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1305,7 +1305,8 @@ static struct crypto_aead *macsec_alloc_tfm(char *key, int key_len, int icv_len) struct crypto_aead *tfm; int ret; - tfm = crypto_alloc_aead("gcm(aes)", 0, 0); + /* Pick a sync gcm(aes) cipher to ensure order is preserved. */ + tfm = crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); if (IS_ERR(tfm)) return tfm; @@ -2640,11 +2641,12 @@ static int macsec_upd_offload(struct sk_buff *skb, struct genl_info *info) if (ret) goto rollback; - rtnl_unlock(); /* Force features update, since they are different for SW MACSec and * HW offloading cases. */ netdev_update_features(dev); + + rtnl_unlock(); return 0; rollback: diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index ae4873f2f86e..d14d91b759b7 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -225,8 +225,12 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev) else val |= BCM54XX_SHD_SCR3_DLLAPD_DIS; - if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) - val |= BCM54XX_SHD_SCR3_TRDDAPD; + if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) { + if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54810) + val |= BCM54810_SHD_SCR3_TRDDAPD; + else + val |= BCM54XX_SHD_SCR3_TRDDAPD; + } if (orig != val) bcm_phy_write_shadow(phydev, BCM54XX_SHD_SCR3, val); diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 415c27310982..ecbd5e0d685c 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -1120,7 +1120,7 @@ static struct dp83640_clock *dp83640_clock_get_bus(struct mii_bus *bus) goto out; } dp83640_clock_init(clock, bus); - list_add_tail(&phyter_clocks, &clock->list); + list_add_tail(&clock->list, &phyter_clocks); out: mutex_unlock(&phyter_clocks_lock); diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index fe9aa3ad52a7..1dd19d0cb269 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -137,19 +137,18 @@ static int dp83822_set_wol(struct phy_device *phydev, value &= ~DP83822_WOL_SECURE_ON; } - value |= (DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL | - DP83822_WOL_CLR_INDICATION); - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, - value); + /* Clear any pending WoL interrupt */ + phy_read(phydev, MII_DP83822_MISR2); + + value |= DP83822_WOL_EN | DP83822_WOL_INDICATION_SEL | + DP83822_WOL_CLR_INDICATION; + + return phy_write_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG, value); } else { - value = phy_read_mmd(phydev, DP83822_DEVADDR, - MII_DP83822_WOL_CFG); - value &= ~DP83822_WOL_EN; - phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, - value); + return phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG, DP83822_WOL_EN); } - - return 0; } static void dp83822_get_wol(struct phy_device *phydev, @@ -258,12 +257,11 @@ static int dp83822_config_intr(struct phy_device *phydev) static int dp83822_config_init(struct phy_device *phydev) { - int value; - - value = DP83822_WOL_MAGIC_EN | DP83822_WOL_SECURE_ON | DP83822_WOL_EN; + int value = DP83822_WOL_EN | DP83822_WOL_MAGIC_EN | + DP83822_WOL_SECURE_ON; - return phy_write_mmd(phydev, DP83822_DEVADDR, MII_DP83822_WOL_CFG, - value); + return phy_clear_bits_mmd(phydev, DP83822_DEVADDR, + MII_DP83822_WOL_CFG, value); } static int dp83822_phy_reset(struct phy_device *phydev) diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index 06f08832ebcd..d73725312c7c 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -139,16 +139,19 @@ static int dp83811_set_wol(struct phy_device *phydev, value &= ~DP83811_WOL_SECURE_ON; } - value |= (DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL | - DP83811_WOL_CLR_INDICATION); - phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - value); + /* Clear any pending WoL interrupt */ + phy_read(phydev, MII_DP83811_INT_STAT1); + + value |= DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL | + DP83811_WOL_CLR_INDICATION; + + return phy_write_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_WOL_CFG, value); } else { - phy_clear_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - DP83811_WOL_EN); + return phy_clear_bits_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_WOL_CFG, DP83811_WOL_EN); } - return 0; } static void dp83811_get_wol(struct phy_device *phydev, @@ -292,8 +295,8 @@ static int dp83811_config_init(struct phy_device *phydev) value = DP83811_WOL_MAGIC_EN | DP83811_WOL_SECURE_ON | DP83811_WOL_EN; - return phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - value); + return phy_clear_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, + value); } static int dp83811_phy_reset(struct phy_device *phydev) diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index ff12492771ab..1f1a01c98e44 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -66,6 +66,9 @@ enum { MV_PCS_CSSR1_SPD2_2500 = 0x0004, MV_PCS_CSSR1_SPD2_10000 = 0x0000, + /* Temperature read register (88E2110 only) */ + MV_PCS_TEMP = 0x8042, + /* These registers appear at 0x800X and 0xa00X - the 0xa00X control * registers appear to set themselves to the 0x800X when AN is * restarted, but status registers appear readable from either. @@ -77,6 +80,7 @@ enum { MV_V2_PORT_CTRL = 0xf001, MV_V2_PORT_CTRL_SWRST = BIT(15), MV_V2_PORT_CTRL_PWRDOWN = BIT(11), + /* Temperature control/read registers (88X3310 only) */ MV_V2_TEMP_CTRL = 0xf08a, MV_V2_TEMP_CTRL_MASK = 0xc000, MV_V2_TEMP_CTRL_SAMPLE = 0x0000, @@ -104,6 +108,24 @@ static umode_t mv3310_hwmon_is_visible(const void *data, return 0; } +static int mv3310_hwmon_read_temp_reg(struct phy_device *phydev) +{ + return phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP); +} + +static int mv2110_hwmon_read_temp_reg(struct phy_device *phydev) +{ + return phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_TEMP); +} + +static int mv10g_hwmon_read_temp_reg(struct phy_device *phydev) +{ + if (phydev->drv->phy_id == MARVELL_PHY_ID_88X3310) + return mv3310_hwmon_read_temp_reg(phydev); + else /* MARVELL_PHY_ID_88E2110 */ + return mv2110_hwmon_read_temp_reg(phydev); +} + static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, long *value) { @@ -116,7 +138,7 @@ static int mv3310_hwmon_read(struct device *dev, enum hwmon_sensor_types type, } if (type == hwmon_temp && attr == hwmon_temp_input) { - temp = phy_read_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP); + temp = mv10g_hwmon_read_temp_reg(phydev); if (temp < 0) return temp; @@ -169,6 +191,9 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable) u16 val; int ret; + if (phydev->drv->phy_id != MARVELL_PHY_ID_88X3310) + return 0; + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP, MV_V2_TEMP_UNKNOWN); if (ret < 0) diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 72c69a9c8a98..20ca6418f7bc 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1132,9 +1132,11 @@ int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data) /* Restart autonegotiation so the new modes get sent to the * link partner. */ - ret = phy_restart_aneg(phydev); - if (ret < 0) - return ret; + if (phydev->autoneg == AUTONEG_ENABLE) { + ret = phy_restart_aneg(phydev); + if (ret < 0) + return ret; + } } return 0; diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index d760a36db28c..beedaad08255 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -490,6 +490,9 @@ static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) goto out; + if (skb->pkt_type != PACKET_HOST) + goto abort; + if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) goto abort; diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 417e42c9fd03..bb8c34d746ab 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -2659,7 +2659,7 @@ static struct hso_device *hso_create_bulk_serial_device( if (! (serial->out_endp = hso_get_ep(interface, USB_ENDPOINT_XFER_BULK, USB_DIR_OUT))) { - dev_err(&interface->dev, "Failed to find BULK IN ep\n"); + dev_err(&interface->dev, "Failed to find BULK OUT ep\n"); goto exit2; } diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 6c738a271257..4bb8552a00d3 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1359,6 +1359,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x413c, 0x81b3, 8)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {QMI_FIXED_INTF(0x413c, 0x81b6, 8)}, /* Dell Wireless 5811e */ {QMI_FIXED_INTF(0x413c, 0x81b6, 10)}, /* Dell Wireless 5811e */ + {QMI_FIXED_INTF(0x413c, 0x81cc, 8)}, /* Dell Wireless 5816e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 0)}, /* Dell Wireless 5821e */ {QMI_FIXED_INTF(0x413c, 0x81d7, 1)}, /* Dell Wireless 5821e preproduction config */ {QMI_FIXED_INTF(0x413c, 0x81e0, 0)}, /* Dell Wireless 5821e with eSIM support*/ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 11f722460513..ce07f52d89e7 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1243,9 +1243,11 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq, break; } while (rq->vq->num_free); if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) { - u64_stats_update_begin(&rq->stats.syncp); + unsigned long flags; + + flags = u64_stats_update_begin_irqsave(&rq->stats.syncp); rq->stats.kicks++; - u64_stats_update_end(&rq->stats.syncp); + u64_stats_update_end_irqrestore(&rq->stats.syncp, flags); } return !oom; diff --git a/drivers/net/wireguard/queueing.c b/drivers/net/wireguard/queueing.c index 5c964fcb994e..71b8e80b58e1 100644 --- a/drivers/net/wireguard/queueing.c +++ b/drivers/net/wireguard/queueing.c @@ -35,8 +35,10 @@ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, if (multicore) { queue->worker = wg_packet_percpu_multicore_worker_alloc( function, queue); - if (!queue->worker) + if (!queue->worker) { + ptr_ring_cleanup(&queue->ring, NULL); return -ENOMEM; + } } else { INIT_WORK(&queue->work, function); } diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index da3b782ab7d3..3bb5b9ae7cd1 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -226,21 +226,20 @@ void wg_packet_handshake_receive_worker(struct work_struct *work) static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; - bool send = false; + bool send; if (peer->sent_lastminute_handshake) return; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); - if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && - keypair->i_am_the_initiator && - unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, - REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT))) - send = true; + send = keypair && READ_ONCE(keypair->sending.is_valid) && + keypair->i_am_the_initiator && + wg_birthdate_has_expired(keypair->sending.birthdate, + REJECT_AFTER_TIME - KEEPALIVE_TIMEOUT - REKEY_TIMEOUT); rcu_read_unlock_bh(); - if (send) { + if (unlikely(send)) { peer->sent_lastminute_handshake = true; wg_packet_send_queued_handshake_initiation(peer, false); } @@ -393,13 +392,11 @@ static void wg_packet_consume_data_done(struct wg_peer *peer, len = ntohs(ip_hdr(skb)->tot_len); if (unlikely(len < sizeof(struct iphdr))) goto dishonest_packet_size; - if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) - IP_ECN_set_ce(ip_hdr(skb)); + INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ip_hdr(skb)->tos); } else if (skb->protocol == htons(ETH_P_IPV6)) { len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); - if (INET_ECN_is_ce(PACKET_CB(skb)->ds)) - IP6_ECN_set_ce(skb, ipv6_hdr(skb)); + INET_ECN_decapsulate(skb, PACKET_CB(skb)->ds, ipv6_get_dsfield(ipv6_hdr(skb))); } else { goto dishonest_packet_type; } @@ -518,6 +515,8 @@ void wg_packet_decrypt_worker(struct work_struct *work) &PACKET_CB(skb)->keypair->receiving)) ? PACKET_STATE_CRYPTED : PACKET_STATE_DEAD; wg_queue_enqueue_per_peer_napi(skb, state); + if (need_resched()) + cond_resched(); } } diff --git a/drivers/net/wireguard/selftest/ratelimiter.c b/drivers/net/wireguard/selftest/ratelimiter.c index bcd6462e4540..007cd4457c5f 100644 --- a/drivers/net/wireguard/selftest/ratelimiter.c +++ b/drivers/net/wireguard/selftest/ratelimiter.c @@ -120,9 +120,9 @@ bool __init wg_ratelimiter_selftest(void) enum { TRIALS_BEFORE_GIVING_UP = 5000 }; bool success = false; int test = 0, trials; - struct sk_buff *skb4, *skb6; + struct sk_buff *skb4, *skb6 = NULL; struct iphdr *hdr4; - struct ipv6hdr *hdr6; + struct ipv6hdr *hdr6 = NULL; if (IS_ENABLED(CONFIG_KASAN) || IS_ENABLED(CONFIG_UBSAN)) return true; diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 7348c10cbae3..6687db699803 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -124,20 +124,17 @@ void wg_packet_send_handshake_cookie(struct wg_device *wg, static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; - bool send = false; + bool send; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); - if (likely(keypair && READ_ONCE(keypair->sending.is_valid)) && - (unlikely(atomic64_read(&keypair->sending.counter.counter) > - REKEY_AFTER_MESSAGES) || - (keypair->i_am_the_initiator && - unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, - REKEY_AFTER_TIME))))) - send = true; + send = keypair && READ_ONCE(keypair->sending.is_valid) && + (atomic64_read(&keypair->sending.counter.counter) > REKEY_AFTER_MESSAGES || + (keypair->i_am_the_initiator && + wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); rcu_read_unlock_bh(); - if (send) + if (unlikely(send)) wg_packet_send_queued_handshake_initiation(peer, false); } @@ -281,6 +278,8 @@ void wg_packet_tx_worker(struct work_struct *work) wg_noise_keypair_put(keypair, false); wg_peer_put(peer); + if (need_resched()) + cond_resched(); } } @@ -304,7 +303,8 @@ void wg_packet_encrypt_worker(struct work_struct *work) } wg_queue_enqueue_per_peer(&PACKET_PEER(first)->tx_queue, first, state); - + if (need_resched()) + cond_resched(); } } diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index b0d6541582d3..f9018027fc13 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -76,12 +76,6 @@ static int send4(struct wg_device *wg, struct sk_buff *skb, net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; - } else if (unlikely(rt->dst.dev == skb->dev)) { - ip_rt_put(rt); - ret = -ELOOP; - net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", - wg->dev->name, &endpoint->addr); - goto err; } if (cache) dst_cache_set_ip4(cache, &rt->dst, fl.saddr); @@ -149,12 +143,6 @@ static int send6(struct wg_device *wg, struct sk_buff *skb, net_dbg_ratelimited("%s: No route to %pISpfsc, error %d\n", wg->dev->name, &endpoint->addr, ret); goto err; - } else if (unlikely(dst->dev == skb->dev)) { - dst_release(dst); - ret = -ELOOP; - net_dbg_ratelimited("%s: Avoiding routing loop to %pISpfsc\n", - wg->dev->name, &endpoint->addr); - goto err; } if (cache) dst_cache_set_ip6(cache, dst, &fl.saddr); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f2adea96b04c..f3c037f5a9ba 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1110,7 +1110,7 @@ static int nvme_identify_ns_descs(struct nvme_ctrl *ctrl, unsigned nsid, * Don't treat an error as fatal, as we potentially already * have a NGUID or EUI-64. */ - if (status > 0) + if (status > 0 && !(status & NVME_SC_DNR)) status = 0; goto free_data; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 4e79e412b276..3726dc780d15 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -973,9 +973,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) { - if (++nvmeq->cq_head == nvmeq->q_depth) { + u16 tmp = nvmeq->cq_head + 1; + + if (tmp == nvmeq->q_depth) { nvmeq->cq_head = 0; nvmeq->cq_phase ^= 1; + } else { + nvmeq->cq_head = tmp; } } @@ -985,6 +989,11 @@ static inline int nvme_process_cq(struct nvme_queue *nvmeq) while (nvme_cqe_pending(nvmeq)) { found++; + /* + * load-load control dependency between phase and the rest of + * the cqe requires a full read memory barrier + */ + dma_rmb(); nvme_handle_cqe(nvmeq, nvmeq->cq_head); nvme_update_cq_head(nvmeq); } diff --git a/drivers/phy/qualcomm/phy-qcom-qusb2.c b/drivers/phy/qualcomm/phy-qcom-qusb2.c index 3708d43b7508..393011a05b48 100644 --- a/drivers/phy/qualcomm/phy-qcom-qusb2.c +++ b/drivers/phy/qualcomm/phy-qcom-qusb2.c @@ -816,6 +816,13 @@ static const struct of_device_id qusb2_phy_of_match_table[] = { .compatible = "qcom,msm8998-qusb2-phy", .data = &msm8998_phy_cfg, }, { + /* + * Deprecated. Only here to support legacy device + * trees that didn't include "qcom,qusb2-v2-phy" + */ + .compatible = "qcom,sdm845-qusb2-phy", + .data = &qusb2_v2_phy_cfg, + }, { .compatible = "qcom,qusb2-v2-phy", .data = &qusb2_v2_phy_cfg, }, diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c index d998e65c89c8..a52a9bf13b75 100644 --- a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c +++ b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c @@ -160,18 +160,11 @@ static int qcom_snps_hsphy_power_on(struct phy *phy) ret = regulator_bulk_enable(VREG_NUM, priv->vregs); if (ret) return ret; - ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks); - if (ret) - goto err_disable_regulator; + qcom_snps_hsphy_disable_hv_interrupts(priv); qcom_snps_hsphy_exit_retention(priv); return 0; - -err_disable_regulator: - regulator_bulk_disable(VREG_NUM, priv->vregs); - - return ret; } static int qcom_snps_hsphy_power_off(struct phy *phy) @@ -180,7 +173,6 @@ static int qcom_snps_hsphy_power_off(struct phy *phy) qcom_snps_hsphy_enter_retention(priv); qcom_snps_hsphy_enable_hv_interrupts(priv); - clk_bulk_disable_unprepare(priv->num_clks, priv->clks); regulator_bulk_disable(VREG_NUM, priv->vregs); return 0; @@ -266,21 +258,39 @@ static int qcom_snps_hsphy_init(struct phy *phy) struct hsphy_priv *priv = phy_get_drvdata(phy); int ret; - ret = qcom_snps_hsphy_reset(priv); + ret = clk_bulk_prepare_enable(priv->num_clks, priv->clks); if (ret) return ret; + ret = qcom_snps_hsphy_reset(priv); + if (ret) + goto disable_clocks; + qcom_snps_hsphy_init_sequence(priv); ret = qcom_snps_hsphy_por_reset(priv); if (ret) - return ret; + goto disable_clocks; + + return 0; + +disable_clocks: + clk_bulk_disable_unprepare(priv->num_clks, priv->clks); + return ret; +} + +static int qcom_snps_hsphy_exit(struct phy *phy) +{ + struct hsphy_priv *priv = phy_get_drvdata(phy); + + clk_bulk_disable_unprepare(priv->num_clks, priv->clks); return 0; } static const struct phy_ops qcom_snps_hsphy_ops = { .init = qcom_snps_hsphy_init, + .exit = qcom_snps_hsphy_exit, .power_on = qcom_snps_hsphy_power_on, .power_off = qcom_snps_hsphy_power_off, .set_mode = qcom_snps_hsphy_set_mode, diff --git a/drivers/pinctrl/actions/pinctrl-s700.c b/drivers/pinctrl/actions/pinctrl-s700.c index 47a4ccd9fed4..f579a6593f37 100644 --- a/drivers/pinctrl/actions/pinctrl-s700.c +++ b/drivers/pinctrl/actions/pinctrl-s700.c @@ -1435,7 +1435,7 @@ static const char * const sd2_groups[] = { static const char * const i2c0_groups[] = { "uart0_rx_mfp", "uart0_tx_mfp", - "i2c0_mfp_mfp", + "i2c0_mfp", }; static const char * const i2c1_groups[] = { diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c index b409642f168d..9b821c9cbd16 100644 --- a/drivers/pinctrl/intel/pinctrl-baytrail.c +++ b/drivers/pinctrl/intel/pinctrl-baytrail.c @@ -1286,6 +1286,7 @@ static const struct gpio_chip byt_gpio_chip = { .direction_output = byt_gpio_direction_output, .get = byt_gpio_get, .set = byt_gpio_set, + .set_config = gpiochip_generic_config, .dbg_show = byt_gpio_dbg_show, }; diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 4c74fdde576d..1093a6105d40 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1479,11 +1479,15 @@ static void chv_gpio_irq_handler(struct irq_desc *desc) struct chv_pinctrl *pctrl = gpiochip_get_data(gc); struct irq_chip *chip = irq_desc_get_chip(desc); unsigned long pending; + unsigned long flags; u32 intr_line; chained_irq_enter(chip, desc); + raw_spin_lock_irqsave(&chv_lock, flags); pending = readl(pctrl->regs + CHV_INTSTAT); + raw_spin_unlock_irqrestore(&chv_lock, flags); + for_each_set_bit(intr_line, &pending, pctrl->community->nirqs) { unsigned int irq, offset; diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c index 330c8f077b73..4d7a86a5a37b 100644 --- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c +++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c @@ -15,17 +15,18 @@ #include "pinctrl-intel.h" -#define SPT_PAD_OWN 0x020 -#define SPT_PADCFGLOCK 0x0a0 -#define SPT_HOSTSW_OWN 0x0d0 -#define SPT_GPI_IS 0x100 -#define SPT_GPI_IE 0x120 +#define SPT_PAD_OWN 0x020 +#define SPT_H_PADCFGLOCK 0x090 +#define SPT_LP_PADCFGLOCK 0x0a0 +#define SPT_HOSTSW_OWN 0x0d0 +#define SPT_GPI_IS 0x100 +#define SPT_GPI_IE 0x120 #define SPT_COMMUNITY(b, s, e) \ { \ .barno = (b), \ .padown_offset = SPT_PAD_OWN, \ - .padcfglock_offset = SPT_PADCFGLOCK, \ + .padcfglock_offset = SPT_LP_PADCFGLOCK, \ .hostown_offset = SPT_HOSTSW_OWN, \ .is_offset = SPT_GPI_IS, \ .ie_offset = SPT_GPI_IE, \ @@ -47,7 +48,7 @@ { \ .barno = (b), \ .padown_offset = SPT_PAD_OWN, \ - .padcfglock_offset = SPT_PADCFGLOCK, \ + .padcfglock_offset = SPT_H_PADCFGLOCK, \ .hostown_offset = SPT_HOSTSW_OWN, \ .is_offset = SPT_GPI_IS, \ .ie_offset = SPT_GPI_IE, \ diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c index 3853ec3a2a8e..ee305f140400 100644 --- a/drivers/pinctrl/mediatek/pinctrl-paris.c +++ b/drivers/pinctrl/mediatek/pinctrl-paris.c @@ -164,8 +164,6 @@ static int mtk_pinconf_get(struct pinctrl_dev *pctldev, case MTK_PIN_CONFIG_PU_ADV: case MTK_PIN_CONFIG_PD_ADV: if (hw->soc->adv_pull_get) { - bool pullup; - pullup = param == MTK_PIN_CONFIG_PU_ADV; err = hw->soc->adv_pull_get(hw, desc, pullup, &ret); } else diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 9a398a211d30..85858c1d56d0 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -697,7 +697,7 @@ static void msm_gpio_update_dual_edge_pos(struct msm_pinctrl *pctrl, pol = msm_readl_intr_cfg(pctrl, g); pol ^= BIT(g->intr_polarity_bit); - msm_writel_intr_cfg(val, pctrl, g); + msm_writel_intr_cfg(pol, pctrl, g); val2 = msm_readl_io(pctrl, g) & BIT(g->in_bit); intstat = msm_readl_intr_status(pctrl, g); @@ -1034,6 +1034,29 @@ static void msm_gpio_irq_relres(struct irq_data *d) module_put(gc->owner); } +static int msm_gpio_irq_set_affinity(struct irq_data *d, + const struct cpumask *dest, bool force) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return irq_chip_set_affinity_parent(d, dest, force); + + return 0; +} + +static int msm_gpio_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu_info) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct msm_pinctrl *pctrl = gpiochip_get_data(gc); + + if (d->parent_data && test_bit(d->hwirq, pctrl->skip_wake_irqs)) + return irq_chip_set_vcpu_affinity_parent(d, vcpu_info); + + return 0; +} + static void msm_gpio_irq_handler(struct irq_desc *desc) { struct gpio_chip *gc = irq_desc_get_handler_data(desc); @@ -1132,6 +1155,8 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl) pctrl->irq_chip.irq_set_wake = msm_gpio_irq_set_wake; pctrl->irq_chip.irq_request_resources = msm_gpio_irq_reqres; pctrl->irq_chip.irq_release_resources = msm_gpio_irq_relres; + pctrl->irq_chip.irq_set_affinity = msm_gpio_irq_set_affinity; + pctrl->irq_chip.irq_set_vcpu_affinity = msm_gpio_irq_set_vcpu_affinity; np = of_parse_phandle(pctrl->dev->of_node, "wakeup-parent", 0); if (np) { diff --git a/drivers/platform/chrome/cros_ec_sensorhub.c b/drivers/platform/chrome/cros_ec_sensorhub.c index b7f2c00db5e1..9c4af76a9956 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub.c +++ b/drivers/platform/chrome/cros_ec_sensorhub.c @@ -52,28 +52,15 @@ static int cros_ec_sensorhub_register(struct device *dev, int sensor_type[MOTIONSENSE_TYPE_MAX] = { 0 }; struct cros_ec_command *msg = sensorhub->msg; struct cros_ec_dev *ec = sensorhub->ec; - int ret, i, sensor_num; + int ret, i; char *name; - sensor_num = cros_ec_get_sensor_count(ec); - if (sensor_num < 0) { - dev_err(dev, - "Unable to retrieve sensor information (err:%d)\n", - sensor_num); - return sensor_num; - } - - sensorhub->sensor_num = sensor_num; - if (sensor_num == 0) { - dev_err(dev, "Zero sensors reported.\n"); - return -EINVAL; - } msg->version = 1; msg->insize = sizeof(struct ec_response_motion_sense); msg->outsize = sizeof(struct ec_params_motion_sense); - for (i = 0; i < sensor_num; i++) { + for (i = 0; i < sensorhub->sensor_num; i++) { sensorhub->params->cmd = MOTIONSENSE_CMD_INFO; sensorhub->params->info.sensor_num = i; @@ -140,8 +127,7 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) struct cros_ec_dev *ec = dev_get_drvdata(dev->parent); struct cros_ec_sensorhub *data; struct cros_ec_command *msg; - int ret; - int i; + int ret, i, sensor_num; msg = devm_kzalloc(dev, sizeof(struct cros_ec_command) + max((u16)sizeof(struct ec_params_motion_sense), @@ -166,10 +152,52 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) dev_set_drvdata(dev, data); /* Check whether this EC is a sensor hub. */ - if (cros_ec_check_features(data->ec, EC_FEATURE_MOTION_SENSE)) { + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE)) { + sensor_num = cros_ec_get_sensor_count(ec); + if (sensor_num < 0) { + dev_err(dev, + "Unable to retrieve sensor information (err:%d)\n", + sensor_num); + return sensor_num; + } + if (sensor_num == 0) { + dev_err(dev, "Zero sensors reported.\n"); + return -EINVAL; + } + data->sensor_num = sensor_num; + + /* + * Prepare the ring handler before enumering the + * sensors. + */ + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { + ret = cros_ec_sensorhub_ring_allocate(data); + if (ret) + return ret; + } + + /* Enumerate the sensors.*/ ret = cros_ec_sensorhub_register(dev, data); if (ret) return ret; + + /* + * When the EC does not have a FIFO, the sensors will query + * their data themselves via sysfs or a software trigger. + */ + if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { + ret = cros_ec_sensorhub_ring_add(data); + if (ret) + return ret; + /* + * The msg and its data is not under the control of the + * ring handler. + */ + return devm_add_action_or_reset(dev, + cros_ec_sensorhub_ring_remove, + data); + } + } else { /* * If the device has sensors but does not claim to @@ -184,22 +212,6 @@ static int cros_ec_sensorhub_probe(struct platform_device *pdev) } } - /* - * If the EC does not have a FIFO, the sensors will query their data - * themselves via sysfs or a software trigger. - */ - if (cros_ec_check_features(ec, EC_FEATURE_MOTION_SENSE_FIFO)) { - ret = cros_ec_sensorhub_ring_add(data); - if (ret) - return ret; - /* - * The msg and its data is not under the control of the ring - * handler. - */ - return devm_add_action_or_reset(dev, - cros_ec_sensorhub_ring_remove, - data); - } return 0; } diff --git a/drivers/platform/chrome/cros_ec_sensorhub_ring.c b/drivers/platform/chrome/cros_ec_sensorhub_ring.c index c48e5b38a441..24e48d96ed76 100644 --- a/drivers/platform/chrome/cros_ec_sensorhub_ring.c +++ b/drivers/platform/chrome/cros_ec_sensorhub_ring.c @@ -957,17 +957,15 @@ static int cros_ec_sensorhub_event(struct notifier_block *nb, } /** - * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC - * supports it. + * cros_ec_sensorhub_ring_allocate() - Prepare the FIFO functionality if the EC + * supports it. * * @sensorhub : Sensor Hub object. * * Return: 0 on success. */ -int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) +int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub) { - struct cros_ec_dev *ec = sensorhub->ec; - int ret; int fifo_info_length = sizeof(struct ec_response_motion_sense_fifo_info) + sizeof(u16) * sensorhub->sensor_num; @@ -978,6 +976,49 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) if (!sensorhub->fifo_info) return -ENOMEM; + /* + * Allocate the callback area based on the number of sensors. + * Add one for the sensor ring. + */ + sensorhub->push_data = devm_kcalloc(sensorhub->dev, + sensorhub->sensor_num, + sizeof(*sensorhub->push_data), + GFP_KERNEL); + if (!sensorhub->push_data) + return -ENOMEM; + + sensorhub->tight_timestamps = cros_ec_check_features( + sensorhub->ec, + EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS); + + if (sensorhub->tight_timestamps) { + sensorhub->batch_state = devm_kcalloc(sensorhub->dev, + sensorhub->sensor_num, + sizeof(*sensorhub->batch_state), + GFP_KERNEL); + if (!sensorhub->batch_state) + return -ENOMEM; + } + + return 0; +} + +/** + * cros_ec_sensorhub_ring_add() - Add the FIFO functionality if the EC + * supports it. + * + * @sensorhub : Sensor Hub object. + * + * Return: 0 on success. + */ +int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) +{ + struct cros_ec_dev *ec = sensorhub->ec; + int ret; + int fifo_info_length = + sizeof(struct ec_response_motion_sense_fifo_info) + + sizeof(u16) * sensorhub->sensor_num; + /* Retrieve FIFO information */ sensorhub->msg->version = 2; sensorhub->params->cmd = MOTIONSENSE_CMD_FIFO_INFO; @@ -998,31 +1039,9 @@ int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub) if (!sensorhub->ring) return -ENOMEM; - /* - * Allocate the callback area based on the number of sensors. - */ - sensorhub->push_data = devm_kcalloc( - sensorhub->dev, sensorhub->sensor_num, - sizeof(*sensorhub->push_data), - GFP_KERNEL); - if (!sensorhub->push_data) - return -ENOMEM; - sensorhub->fifo_timestamp[CROS_EC_SENSOR_LAST_TS] = cros_ec_get_time_ns(); - sensorhub->tight_timestamps = cros_ec_check_features( - ec, EC_FEATURE_MOTION_SENSE_TIGHT_TIMESTAMPS); - - if (sensorhub->tight_timestamps) { - sensorhub->batch_state = devm_kcalloc(sensorhub->dev, - sensorhub->sensor_num, - sizeof(*sensorhub->batch_state), - GFP_KERNEL); - if (!sensorhub->batch_state) - return -ENOMEM; - } - /* Register the notifier that will act as a top half interrupt. */ sensorhub->notifier.notifier_call = cros_ec_sensorhub_event; ret = blocking_notifier_chain_register(&ec->ec_dev->event_notifier, diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index 6f12747a359a..c4404d9c1de4 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -515,9 +515,33 @@ static struct asus_wmi_driver asus_nb_wmi_driver = { .detect_quirks = asus_nb_wmi_quirks, }; +static const struct dmi_system_id asus_nb_wmi_blacklist[] __initconst = { + { + /* + * asus-nb-wm adds no functionality. The T100TA has a detachable + * USB kbd, so no hotkeys and it has no WMI rfkill; and loading + * asus-nb-wm causes the camera LED to turn and _stay_ on. + */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T100TA"), + }, + }, + { + /* The Asus T200TA has the same issue as the T100TA */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T200TA"), + }, + }, + {} /* Terminating entry */ +}; static int __init asus_nb_wmi_init(void) { + if (dmi_check_system(asus_nb_wmi_blacklist)) + return -ENODEV; + return asus_wmi_register_driver(&asus_nb_wmi_driver); } diff --git a/drivers/platform/x86/intel-uncore-frequency.c b/drivers/platform/x86/intel-uncore-frequency.c index b96d172eb2c1..12d5ab7e1f5d 100644 --- a/drivers/platform/x86/intel-uncore-frequency.c +++ b/drivers/platform/x86/intel-uncore-frequency.c @@ -53,7 +53,7 @@ static int uncore_max_entries __read_mostly; /* Storage for uncore data for all instances */ static struct uncore_data *uncore_instances; /* Root of the all uncore sysfs kobjs */ -struct kobject *uncore_root_kobj; +static struct kobject *uncore_root_kobj; /* Stores the CPU mask of the target CPUs to use during uncore read/write */ static cpumask_t uncore_cpu_mask; /* CPU online callback register instance */ diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index d2a5d4c36715..7c8bdab078cf 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -255,7 +255,7 @@ static const struct pmc_bit_map *ext_cnp_pfear_map[] = { }; static const struct pmc_bit_map icl_pfear_map[] = { - /* Ice Lake generation onwards only */ + /* Ice Lake and Jasper Lake generation onwards only */ {"RES_65", BIT(0)}, {"RES_66", BIT(1)}, {"RES_67", BIT(2)}, @@ -274,7 +274,7 @@ static const struct pmc_bit_map *ext_icl_pfear_map[] = { }; static const struct pmc_bit_map tgl_pfear_map[] = { - /* Tiger Lake, Elkhart Lake and Jasper Lake generation onwards only */ + /* Tiger Lake and Elkhart Lake generation onwards only */ {"PSF9", BIT(0)}, {"RES_66", BIT(1)}, {"RES_67", BIT(2)}, @@ -692,7 +692,6 @@ static void pmc_core_lpm_display(struct pmc_dev *pmcdev, struct device *dev, kfree(lpm_regs); } -#if IS_ENABLED(CONFIG_DEBUG_FS) static bool slps0_dbg_latch; static inline u8 pmc_core_reg_read_byte(struct pmc_dev *pmcdev, int offset) @@ -1133,15 +1132,6 @@ static void pmc_core_dbgfs_register(struct pmc_dev *pmcdev) &pmc_core_substate_l_sts_regs_fops); } } -#else -static inline void pmc_core_dbgfs_register(struct pmc_dev *pmcdev) -{ -} - -static inline void pmc_core_dbgfs_unregister(struct pmc_dev *pmcdev) -{ -} -#endif /* CONFIG_DEBUG_FS */ static const struct x86_cpu_id intel_pmc_core_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_L, &spt_reg_map), @@ -1156,7 +1146,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &tgl_reg_map), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &tgl_reg_map), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &tgl_reg_map), - X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &tgl_reg_map), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &icl_reg_map), {} }; @@ -1260,13 +1250,11 @@ static int pmc_core_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM_SLEEP - static bool warn_on_s0ix_failures; module_param(warn_on_s0ix_failures, bool, 0644); MODULE_PARM_DESC(warn_on_s0ix_failures, "Check and warn for S0ix failures"); -static int pmc_core_suspend(struct device *dev) +static __maybe_unused int pmc_core_suspend(struct device *dev) { struct pmc_dev *pmcdev = dev_get_drvdata(dev); @@ -1318,7 +1306,7 @@ static inline bool pmc_core_is_s0ix_failed(struct pmc_dev *pmcdev) return false; } -static int pmc_core_resume(struct device *dev) +static __maybe_unused int pmc_core_resume(struct device *dev) { struct pmc_dev *pmcdev = dev_get_drvdata(dev); const struct pmc_bit_map **maps = pmcdev->map->lpm_sts; @@ -1348,8 +1336,6 @@ static int pmc_core_resume(struct device *dev) return 0; } -#endif - static const struct dev_pm_ops pmc_core_pm_ops = { SET_LATE_SYSTEM_SLEEP_PM_OPS(pmc_core_suspend, pmc_core_resume) }; diff --git a/drivers/platform/x86/intel_pmc_core.h b/drivers/platform/x86/intel_pmc_core.h index 0d50b2402abe..5eae55d80226 100644 --- a/drivers/platform/x86/intel_pmc_core.h +++ b/drivers/platform/x86/intel_pmc_core.h @@ -282,9 +282,7 @@ struct pmc_dev { u32 base_addr; void __iomem *regbase; const struct pmc_reg_map *map; -#if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbgfs_dir; -#endif /* CONFIG_DEBUG_FS */ int pmc_xram_read_bit; struct mutex lock; /* generic mutex lock for PMC Core */ diff --git a/drivers/platform/x86/surface3_power.c b/drivers/platform/x86/surface3_power.c index 946ac2dc08ae..cc4f9cba6856 100644 --- a/drivers/platform/x86/surface3_power.c +++ b/drivers/platform/x86/surface3_power.c @@ -522,8 +522,8 @@ static int mshw0011_probe(struct i2c_client *client) strlcpy(board_info.type, "MSHW0011-bat0", I2C_NAME_SIZE); bat0 = i2c_acpi_new_device(dev, 1, &board_info); - if (!bat0) - return -ENOMEM; + if (IS_ERR(bat0)) + return PTR_ERR(bat0); data->bat0 = bat0; i2c_set_clientdata(bat0, data); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 8eaadbaf8ffa..0f704484ae1d 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -9548,7 +9548,7 @@ static ssize_t tpacpi_battery_store(int what, if (!battery_info.batteries[battery].start_support) return -ENODEV; /* valid values are [0, 99] */ - if (value < 0 || value > 99) + if (value > 99) return -EINVAL; if (value > battery_info.batteries[battery].charge_stop) return -EINVAL; diff --git a/drivers/platform/x86/xiaomi-wmi.c b/drivers/platform/x86/xiaomi-wmi.c index 601cbb282f54..54a2546bb93b 100644 --- a/drivers/platform/x86/xiaomi-wmi.c +++ b/drivers/platform/x86/xiaomi-wmi.c @@ -23,7 +23,7 @@ struct xiaomi_wmi { unsigned int key_code; }; -int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) +static int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) { struct xiaomi_wmi *data; @@ -48,7 +48,7 @@ int xiaomi_wmi_probe(struct wmi_device *wdev, const void *context) return input_register_device(data->input_dev); } -void xiaomi_wmi_notify(struct wmi_device *wdev, union acpi_object *dummy) +static void xiaomi_wmi_notify(struct wmi_device *wdev, union acpi_object *dummy) { struct xiaomi_wmi *data; diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c index c340505150b6..7486f6e4e613 100644 --- a/drivers/regulator/core.c +++ b/drivers/regulator/core.c @@ -5754,10 +5754,6 @@ static DECLARE_DELAYED_WORK(regulator_init_complete_work, static int __init regulator_init_complete(void) { - int delay = driver_deferred_probe_timeout; - - if (delay < 0) - delay = 0; /* * Since DT doesn't provide an idiomatic mechanism for * enabling full constraints and since it's much more natural @@ -5768,17 +5764,18 @@ static int __init regulator_init_complete(void) has_full_constraints = true; /* - * If driver_deferred_probe_timeout is set, we punt - * completion for that many seconds since systems like - * distros will load many drivers from userspace so consumers - * might not always be ready yet, this is particularly an - * issue with laptops where this might bounce the display off - * then on. Ideally we'd get a notification from userspace - * when this happens but we don't so just wait a bit and hope - * we waited long enough. It'd be better if we'd only do - * this on systems that need it. + * We punt completion for an arbitrary amount of time since + * systems like distros will load many drivers from userspace + * so consumers might not always be ready yet, this is + * particularly an issue with laptops where this might bounce + * the display off then on. Ideally we'd get a notification + * from userspace when this happens but we don't so just wait + * a bit and hope we waited long enough. It'd be better if + * we'd only do this on systems that need it, and a kernel + * command line option might be useful. */ - schedule_delayed_work(®ulator_init_complete_work, delay * HZ); + schedule_delayed_work(®ulator_init_complete_work, + msecs_to_jiffies(30000)); return 0; } diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index c75112ee7b97..c7fade836d83 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -521,8 +521,10 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops, ISM_NR_DMBS); - if (!ism->smcd) + if (!ism->smcd) { + ret = -ENOMEM; goto err_resource; + } ism->smcd->priv = ism; ret = ism_dev_init(ism); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index f7689461c242..569966bdc513 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -6717,17 +6717,17 @@ int qeth_stop(struct net_device *dev) unsigned int i; /* Quiesce the NAPI instances: */ - qeth_for_each_output_queue(card, queue, i) { + qeth_for_each_output_queue(card, queue, i) napi_disable(&queue->napi); - del_timer_sync(&queue->timer); - } /* Stop .ndo_start_xmit, might still access queue->napi. */ netif_tx_disable(dev); - /* Queues may get re-allocated, so remove the NAPIs here. */ - qeth_for_each_output_queue(card, queue, i) + qeth_for_each_output_queue(card, queue, i) { + del_timer_sync(&queue->timer); + /* Queues may get re-allocated, so remove the NAPIs. */ netif_napi_del(&queue->napi); + } } else { netif_tx_disable(dev); } diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index 7da9e060b270..635f6f9cffc4 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -3640,6 +3640,11 @@ static void ibmvfc_tgt_implicit_logout_and_del(struct ibmvfc_target *tgt) struct ibmvfc_host *vhost = tgt->vhost; struct ibmvfc_event *evt; + if (!vhost->logged_in) { + ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT); + return; + } + if (vhost->discovery_threads >= disc_threads) return; diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c index 7f66a7783209..59f0f1030c54 100644 --- a/drivers/scsi/ibmvscsi/ibmvscsi.c +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c @@ -2320,16 +2320,12 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id) static int ibmvscsi_remove(struct vio_dev *vdev) { struct ibmvscsi_host_data *hostdata = dev_get_drvdata(&vdev->dev); - unsigned long flags; srp_remove_host(hostdata->host); scsi_remove_host(hostdata->host); purge_requests(hostdata, DID_ERROR); - - spin_lock_irqsave(hostdata->host->host_lock, flags); release_event_pool(&hostdata->pool, hostdata); - spin_unlock_irqrestore(hostdata->host->host_lock, flags); ibmvscsi_release_crq_queue(&hostdata->queue, hostdata, max_events); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index 97cabd7e0014..33255968f03a 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -3031,11 +3031,11 @@ qla24xx_vport_delete(struct fc_vport *fc_vport) test_bit(FCPORT_UPDATE_NEEDED, &vha->dpc_flags)) msleep(1000); - qla_nvme_delete(vha); qla24xx_disable_vp(vha); qla2x00_wait_for_sess_deletion(vha); + qla_nvme_delete(vha); vha->flags.delete_progress = 1; qlt_remove_target(ha, vha); diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 4ed90437e8c4..d6c991bd1bde 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -3153,7 +3153,7 @@ qla24xx_abort_command(srb_t *sp) ql_dbg(ql_dbg_mbx + ql_dbg_verbose, vha, 0x108c, "Entered %s.\n", __func__); - if (vha->flags.qpairs_available && sp->qpair) + if (sp->qpair) req = sp->qpair->req; else return QLA_FUNCTION_FAILED; diff --git a/drivers/staging/gasket/gasket_core.c b/drivers/staging/gasket/gasket_core.c index 8e0575fcb4c8..67325fbaf760 100644 --- a/drivers/staging/gasket/gasket_core.c +++ b/drivers/staging/gasket/gasket_core.c @@ -925,6 +925,10 @@ do_map_region(const struct gasket_dev *gasket_dev, struct vm_area_struct *vma, gasket_get_bar_index(gasket_dev, (vma->vm_pgoff << PAGE_SHIFT) + driver_desc->legacy_mmap_address_offset); + + if (bar_index < 0) + return DO_MAP_REGION_INVALID; + phys_base = gasket_dev->bar_data[bar_index].phys_base + phys_offset; while (mapped_bytes < map_length) { /* diff --git a/drivers/staging/ks7010/TODO b/drivers/staging/ks7010/TODO index 87a6dac4890d..ab6f39175d99 100644 --- a/drivers/staging/ks7010/TODO +++ b/drivers/staging/ks7010/TODO @@ -30,5 +30,4 @@ Now the TODOs: Please send any patches to: Greg Kroah-Hartman <gregkh@linuxfoundation.org> -Wolfram Sang <wsa@the-dreams.de> Linux Driver Project Developer List <driverdev-devel@linuxdriverproject.org> diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 3d084cec136f..50c7534ba31e 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -182,6 +182,9 @@ static int usb4_switch_op(struct tb_switch *sw, u16 opcode, u8 *status) return ret; ret = tb_sw_read(sw, &val, TB_CFG_SWITCH, ROUTER_CS_26, 1); + if (ret) + return ret; + if (val & ROUTER_CS_26_ONS) return -EOPNOTSUPP; diff --git a/drivers/tty/serial/bcm63xx_uart.c b/drivers/tty/serial/bcm63xx_uart.c index ed0aa5c0d9b7..5674da2b76f0 100644 --- a/drivers/tty/serial/bcm63xx_uart.c +++ b/drivers/tty/serial/bcm63xx_uart.c @@ -843,10 +843,8 @@ static int bcm_uart_probe(struct platform_device *pdev) if (IS_ERR(clk) && pdev->dev.of_node) clk = of_clk_get(pdev->dev.of_node, 0); - if (IS_ERR(clk)) { - clk_put(clk); + if (IS_ERR(clk)) return -ENODEV; - } port->iotype = UPIO_MEM; port->irq = res_irq->start; diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index ac137b6a1dc1..35e9e8faf8de 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -1459,6 +1459,7 @@ static int cdns_uart_probe(struct platform_device *pdev) cdns_uart_uart_driver.nr = CDNS_UART_NR_PORTS; #ifdef CONFIG_SERIAL_XILINX_PS_UART_CONSOLE cdns_uart_uart_driver.cons = &cdns_uart_console; + cdns_uart_console.index = id; #endif rc = uart_register_driver(&cdns_uart_uart_driver); diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index e5ffed795e4c..48a8199f7845 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -365,9 +365,14 @@ static struct uni_screen *vc_uniscr_alloc(unsigned int cols, unsigned int rows) return uniscr; } +static void vc_uniscr_free(struct uni_screen *uniscr) +{ + vfree(uniscr); +} + static void vc_uniscr_set(struct vc_data *vc, struct uni_screen *new_uniscr) { - vfree(vc->vc_uni_screen); + vc_uniscr_free(vc->vc_uni_screen); vc->vc_uni_screen = new_uniscr; } @@ -1230,7 +1235,7 @@ static int vc_do_resize(struct tty_struct *tty, struct vc_data *vc, err = resize_screen(vc, new_cols, new_rows, user); if (err) { kfree(newscreen); - kfree(new_uniscr); + vc_uniscr_free(new_uniscr); return err; } diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 372460ea4df9..4d43f3b28309 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -82,7 +82,7 @@ static int cdns3_ep_run_stream_transfer(struct cdns3_endpoint *priv_ep, * @ptr: address of device controller register to be read and changed * @mask: bits requested to clar */ -void cdns3_clear_register_bit(void __iomem *ptr, u32 mask) +static void cdns3_clear_register_bit(void __iomem *ptr, u32 mask) { mask = readl(ptr) & ~mask; writel(mask, ptr); @@ -137,7 +137,7 @@ struct usb_request *cdns3_next_request(struct list_head *list) * * Returns buffer or NULL if no buffers in list */ -struct cdns3_aligned_buf *cdns3_next_align_buf(struct list_head *list) +static struct cdns3_aligned_buf *cdns3_next_align_buf(struct list_head *list) { return list_first_entry_or_null(list, struct cdns3_aligned_buf, list); } @@ -148,7 +148,7 @@ struct cdns3_aligned_buf *cdns3_next_align_buf(struct list_head *list) * * Returns request or NULL if no requests in list */ -struct cdns3_request *cdns3_next_priv_request(struct list_head *list) +static struct cdns3_request *cdns3_next_priv_request(struct list_head *list) { return list_first_entry_or_null(list, struct cdns3_request, list); } @@ -190,7 +190,7 @@ dma_addr_t cdns3_trb_virt_to_dma(struct cdns3_endpoint *priv_ep, return priv_ep->trb_pool_dma + offset; } -int cdns3_ring_size(struct cdns3_endpoint *priv_ep) +static int cdns3_ring_size(struct cdns3_endpoint *priv_ep) { switch (priv_ep->type) { case USB_ENDPOINT_XFER_ISOC: @@ -345,7 +345,7 @@ static void cdns3_ep_inc_deq(struct cdns3_endpoint *priv_ep) cdns3_ep_inc_trb(&priv_ep->dequeue, &priv_ep->ccs, priv_ep->num_trbs); } -void cdns3_move_deq_to_next_trb(struct cdns3_request *priv_req) +static void cdns3_move_deq_to_next_trb(struct cdns3_request *priv_req) { struct cdns3_endpoint *priv_ep = priv_req->priv_ep; int current_trb = priv_req->start_trb; @@ -511,7 +511,7 @@ static void cdns3_wa2_descmiss_copy_data(struct cdns3_endpoint *priv_ep, } } -struct usb_request *cdns3_wa2_gadget_giveback(struct cdns3_device *priv_dev, +static struct usb_request *cdns3_wa2_gadget_giveback(struct cdns3_device *priv_dev, struct cdns3_endpoint *priv_ep, struct cdns3_request *priv_req) { @@ -551,7 +551,7 @@ struct usb_request *cdns3_wa2_gadget_giveback(struct cdns3_device *priv_dev, return &priv_req->request; } -int cdns3_wa2_gadget_ep_queue(struct cdns3_device *priv_dev, +static int cdns3_wa2_gadget_ep_queue(struct cdns3_device *priv_dev, struct cdns3_endpoint *priv_ep, struct cdns3_request *priv_req) { @@ -836,7 +836,7 @@ void cdns3_gadget_giveback(struct cdns3_endpoint *priv_ep, cdns3_gadget_ep_free_request(&priv_ep->endpoint, request); } -void cdns3_wa1_restore_cycle_bit(struct cdns3_endpoint *priv_ep) +static void cdns3_wa1_restore_cycle_bit(struct cdns3_endpoint *priv_ep) { /* Work around for stale data address in TRB*/ if (priv_ep->wa1_set) { @@ -1904,7 +1904,7 @@ static int cdns3_ep_onchip_buffer_reserve(struct cdns3_device *priv_dev, return 0; } -void cdns3_stream_ep_reconfig(struct cdns3_device *priv_dev, +static void cdns3_stream_ep_reconfig(struct cdns3_device *priv_dev, struct cdns3_endpoint *priv_ep) { if (!priv_ep->use_streams || priv_dev->gadget.speed < USB_SPEED_SUPER) @@ -1925,7 +1925,7 @@ void cdns3_stream_ep_reconfig(struct cdns3_device *priv_dev, EP_CFG_TDL_CHK | EP_CFG_SID_CHK); } -void cdns3_configure_dmult(struct cdns3_device *priv_dev, +static void cdns3_configure_dmult(struct cdns3_device *priv_dev, struct cdns3_endpoint *priv_ep) { struct cdns3_usb_regs __iomem *regs = priv_dev->regs; @@ -2548,7 +2548,7 @@ found: link_trb = priv_req->trb; /* Update ring only if removed request is on pending_req_list list */ - if (req_on_hw_ring) { + if (req_on_hw_ring && link_trb) { link_trb->buffer = TRB_BUFFER(priv_ep->trb_pool_dma + ((priv_req->end_trb + 1) * TRB_SIZE)); link_trb->control = (link_trb->control & TRB_CYCLE) | diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c index af648ba6544d..46105457e1ca 100644 --- a/drivers/usb/chipidea/ci_hdrc_msm.c +++ b/drivers/usb/chipidea/ci_hdrc_msm.c @@ -114,7 +114,7 @@ static int ci_hdrc_msm_notify_event(struct ci_hdrc *ci, unsigned event) hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_ULPI_TX_PKT_EN_CLR_FIX, 0); - if (!IS_ERR(ci->platdata->vbus_extcon.edev)) { + if (!IS_ERR(ci->platdata->vbus_extcon.edev) || ci->role_switch) { hw_write_id_reg(ci, HS_PHY_GENCONFIG_2, HS_PHY_SESS_VLD_CTRL_EN, HS_PHY_SESS_VLD_CTRL_EN); diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 6833c918abce..d93d94d7ff50 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -217,6 +217,7 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) { struct usb_memory *usbm = NULL; struct usb_dev_state *ps = file->private_data; + struct usb_hcd *hcd = bus_to_hcd(ps->dev->bus); size_t size = vma->vm_end - vma->vm_start; void *mem; unsigned long flags; @@ -250,11 +251,19 @@ static int usbdev_mmap(struct file *file, struct vm_area_struct *vma) usbm->vma_use_count = 1; INIT_LIST_HEAD(&usbm->memlist); - if (remap_pfn_range(vma, vma->vm_start, - virt_to_phys(usbm->mem) >> PAGE_SHIFT, - size, vma->vm_page_prot) < 0) { - dec_usb_memory_use_count(usbm, &usbm->vma_use_count); - return -EAGAIN; + if (hcd->localmem_pool || !hcd_uses_dma(hcd)) { + if (remap_pfn_range(vma, vma->vm_start, + virt_to_phys(usbm->mem) >> PAGE_SHIFT, + size, vma->vm_page_prot) < 0) { + dec_usb_memory_use_count(usbm, &usbm->vma_use_count); + return -EAGAIN; + } + } else { + if (dma_mmap_coherent(hcd->self.sysdev, vma, mem, dma_handle, + size)) { + dec_usb_memory_use_count(usbm, &usbm->vma_use_count); + return -EAGAIN; + } } vma->vm_flags |= VM_IO; diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 2b6565c06c23..fc748c731832 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -39,6 +39,7 @@ #define USB_VENDOR_GENESYS_LOGIC 0x05e3 #define USB_VENDOR_SMSC 0x0424 +#define USB_PRODUCT_USB5534B 0x5534 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 #define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02 @@ -5621,8 +5622,11 @@ out_hdev_lock: } static const struct usb_device_id hub_id_table[] = { - { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT + | USB_DEVICE_ID_MATCH_INT_CLASS, .idVendor = USB_VENDOR_SMSC, + .idProduct = USB_PRODUCT_USB5534B, .bInterfaceClass = USB_CLASS_HUB, .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, { .match_flags = USB_DEVICE_ID_MATCH_VENDOR diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index a48678a0c83a..6197938dcc2d 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1144,11 +1144,11 @@ void usb_disable_endpoint(struct usb_device *dev, unsigned int epaddr, if (usb_endpoint_out(epaddr)) { ep = dev->ep_out[epnum]; - if (reset_hardware) + if (reset_hardware && epnum != 0) dev->ep_out[epnum] = NULL; } else { ep = dev->ep_in[epnum]; - if (reset_hardware) + if (reset_hardware && epnum != 0) dev->ep_in[epnum] = NULL; } if (ep) { diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig index 206caa0ea1c6..7a2304565a73 100644 --- a/drivers/usb/dwc3/Kconfig +++ b/drivers/usb/dwc3/Kconfig @@ -4,6 +4,7 @@ config USB_DWC3 tristate "DesignWare USB3 DRD Core Support" depends on (USB || USB_GADGET) && HAS_DMA select USB_XHCI_PLATFORM if USB_XHCI_HCD + select USB_ROLE_SWITCH if USB_DWC3_DUAL_ROLE help Say Y or M here if your system has a Dual Role SuperSpeed USB controller based on the DesignWare USB3 IP Core. diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 7051611229c9..b67372737dc9 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -114,6 +114,7 @@ static const struct property_entry dwc3_pci_intel_properties[] = { static const struct property_entry dwc3_pci_mrfld_properties[] = { PROPERTY_ENTRY_STRING("dr_mode", "otg"), + PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"), PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"), {} }; diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 00746c2848c0..585cb3deea7a 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2483,9 +2483,6 @@ static int dwc3_gadget_ep_reclaim_trb_sg(struct dwc3_ep *dep, for_each_sg(sg, s, pending, i) { trb = &dep->trb_pool[dep->trb_dequeue]; - if (trb->ctrl & DWC3_TRB_CTRL_HWO) - break; - req->sg = sg_next(s); req->num_pending_sgs--; diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 32b637e3e1fa..6a9aa4413d64 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -260,6 +260,9 @@ static ssize_t gadget_dev_desc_UDC_store(struct config_item *item, char *name; int ret; + if (strlen(page) < len) + return -EOVERFLOW; + name = kstrdup(page, GFP_KERNEL); if (!name) return -ENOMEM; diff --git a/drivers/usb/gadget/legacy/audio.c b/drivers/usb/gadget/legacy/audio.c index dd81fd538cb8..a748ed0842e8 100644 --- a/drivers/usb/gadget/legacy/audio.c +++ b/drivers/usb/gadget/legacy/audio.c @@ -300,8 +300,10 @@ static int audio_bind(struct usb_composite_dev *cdev) struct usb_descriptor_header *usb_desc; usb_desc = usb_otg_descriptor_alloc(cdev->gadget); - if (!usb_desc) + if (!usb_desc) { + status = -ENOMEM; goto fail; + } usb_otg_descriptor_init(cdev->gadget, usb_desc); otg_desc[0] = usb_desc; otg_desc[1] = NULL; diff --git a/drivers/usb/gadget/legacy/cdc2.c b/drivers/usb/gadget/legacy/cdc2.c index 8d7a556ece30..563363aba48f 100644 --- a/drivers/usb/gadget/legacy/cdc2.c +++ b/drivers/usb/gadget/legacy/cdc2.c @@ -179,8 +179,10 @@ static int cdc_bind(struct usb_composite_dev *cdev) struct usb_descriptor_header *usb_desc; usb_desc = usb_otg_descriptor_alloc(gadget); - if (!usb_desc) + if (!usb_desc) { + status = -ENOMEM; goto fail1; + } usb_otg_descriptor_init(gadget, usb_desc); otg_desc[0] = usb_desc; otg_desc[1] = NULL; diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index aa0de9e35afa..3afddd3bea6e 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -1361,7 +1361,6 @@ gadgetfs_setup (struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) req->buf = dev->rbuf; req->context = NULL; - value = -EOPNOTSUPP; switch (ctrl->bRequest) { case USB_REQ_GET_DESCRIPTOR: @@ -1784,7 +1783,7 @@ static ssize_t dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) { struct dev_data *dev = fd->private_data; - ssize_t value = len, length = len; + ssize_t value, length = len; unsigned total; u32 tag; char *kbuf; diff --git a/drivers/usb/gadget/legacy/ncm.c b/drivers/usb/gadget/legacy/ncm.c index c61e71ba7045..0f1b45e3abd1 100644 --- a/drivers/usb/gadget/legacy/ncm.c +++ b/drivers/usb/gadget/legacy/ncm.c @@ -156,8 +156,10 @@ static int gncm_bind(struct usb_composite_dev *cdev) struct usb_descriptor_header *usb_desc; usb_desc = usb_otg_descriptor_alloc(gadget); - if (!usb_desc) + if (!usb_desc) { + status = -ENOMEM; goto fail; + } usb_otg_descriptor_init(gadget, usb_desc); otg_desc[0] = usb_desc; otg_desc[1] = NULL; diff --git a/drivers/usb/gadget/legacy/raw_gadget.c b/drivers/usb/gadget/legacy/raw_gadget.c index ca7d95bf7397..e01e366d89cd 100644 --- a/drivers/usb/gadget/legacy/raw_gadget.c +++ b/drivers/usb/gadget/legacy/raw_gadget.c @@ -7,6 +7,7 @@ */ #include <linux/compiler.h> +#include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/kref.h> @@ -123,8 +124,6 @@ static void raw_event_queue_destroy(struct raw_event_queue *queue) struct raw_dev; -#define USB_RAW_MAX_ENDPOINTS 32 - enum ep_state { STATE_EP_DISABLED, STATE_EP_ENABLED, @@ -134,6 +133,7 @@ struct raw_ep { struct raw_dev *dev; enum ep_state state; struct usb_ep *ep; + u8 addr; struct usb_request *req; bool urb_queued; bool disabling; @@ -168,7 +168,8 @@ struct raw_dev { bool ep0_out_pending; bool ep0_urb_queued; ssize_t ep0_status; - struct raw_ep eps[USB_RAW_MAX_ENDPOINTS]; + struct raw_ep eps[USB_RAW_EPS_NUM_MAX]; + int eps_num; struct completion ep0_done; struct raw_event_queue queue; @@ -202,8 +203,8 @@ static void dev_free(struct kref *kref) usb_ep_free_request(dev->gadget->ep0, dev->req); } raw_event_queue_destroy(&dev->queue); - for (i = 0; i < USB_RAW_MAX_ENDPOINTS; i++) { - if (dev->eps[i].state != STATE_EP_ENABLED) + for (i = 0; i < dev->eps_num; i++) { + if (dev->eps[i].state == STATE_EP_DISABLED) continue; usb_ep_disable(dev->eps[i].ep); usb_ep_free_request(dev->eps[i].ep, dev->eps[i].req); @@ -249,12 +250,26 @@ static void gadget_ep0_complete(struct usb_ep *ep, struct usb_request *req) complete(&dev->ep0_done); } +static u8 get_ep_addr(const char *name) +{ + /* If the endpoint has fixed function (named as e.g. "ep12out-bulk"), + * parse the endpoint address from its name. We deliberately use + * deprecated simple_strtoul() function here, as the number isn't + * followed by '\0' nor '\n'. + */ + if (isdigit(name[2])) + return simple_strtoul(&name[2], NULL, 10); + /* Otherwise the endpoint is configurable (named as e.g. "ep-a"). */ + return USB_RAW_EP_ADDR_ANY; +} + static int gadget_bind(struct usb_gadget *gadget, struct usb_gadget_driver *driver) { - int ret = 0; + int ret = 0, i = 0; struct raw_dev *dev = container_of(driver, struct raw_dev, driver); struct usb_request *req; + struct usb_ep *ep; unsigned long flags; if (strcmp(gadget->name, dev->udc_name) != 0) @@ -273,6 +288,13 @@ static int gadget_bind(struct usb_gadget *gadget, dev->req->context = dev; dev->req->complete = gadget_ep0_complete; dev->gadget = gadget; + gadget_for_each_ep(ep, dev->gadget) { + dev->eps[i].ep = ep; + dev->eps[i].addr = get_ep_addr(ep->name); + dev->eps[i].state = STATE_EP_DISABLED; + i++; + } + dev->eps_num = i; spin_unlock_irqrestore(&dev->lock, flags); /* Matches kref_put() in gadget_unbind(). */ @@ -555,7 +577,7 @@ static void *raw_alloc_io_data(struct usb_raw_ep_io *io, void __user *ptr, if (copy_from_user(io, ptr, sizeof(*io))) return ERR_PTR(-EFAULT); - if (io->ep >= USB_RAW_MAX_ENDPOINTS) + if (io->ep >= USB_RAW_EPS_NUM_MAX) return ERR_PTR(-EINVAL); if (!usb_raw_io_flags_valid(io->flags)) return ERR_PTR(-EINVAL); @@ -669,43 +691,61 @@ static int raw_ioctl_ep0_read(struct raw_dev *dev, unsigned long value) if (IS_ERR(data)) return PTR_ERR(data); ret = raw_process_ep0_io(dev, &io, data, false); - if (ret) + if (ret < 0) goto free; length = min(io.length, (unsigned int)ret); if (copy_to_user((void __user *)(value + sizeof(io)), data, length)) ret = -EFAULT; + else + ret = length; free: kfree(data); return ret; } -static bool check_ep_caps(struct usb_ep *ep, - struct usb_endpoint_descriptor *desc) +static int raw_ioctl_ep0_stall(struct raw_dev *dev, unsigned long value) { - switch (usb_endpoint_type(desc)) { - case USB_ENDPOINT_XFER_ISOC: - if (!ep->caps.type_iso) - return false; - break; - case USB_ENDPOINT_XFER_BULK: - if (!ep->caps.type_bulk) - return false; - break; - case USB_ENDPOINT_XFER_INT: - if (!ep->caps.type_int) - return false; - break; - default: - return false; + int ret = 0; + unsigned long flags; + + if (value) + return -EINVAL; + spin_lock_irqsave(&dev->lock, flags); + if (dev->state != STATE_DEV_RUNNING) { + dev_dbg(dev->dev, "fail, device is not running\n"); + ret = -EINVAL; + goto out_unlock; + } + if (!dev->gadget) { + dev_dbg(dev->dev, "fail, gadget is not bound\n"); + ret = -EBUSY; + goto out_unlock; + } + if (dev->ep0_urb_queued) { + dev_dbg(&dev->gadget->dev, "fail, urb already queued\n"); + ret = -EBUSY; + goto out_unlock; + } + if (!dev->ep0_in_pending && !dev->ep0_out_pending) { + dev_dbg(&dev->gadget->dev, "fail, no request pending\n"); + ret = -EBUSY; + goto out_unlock; } - if (usb_endpoint_dir_in(desc) && !ep->caps.dir_in) - return false; - if (usb_endpoint_dir_out(desc) && !ep->caps.dir_out) - return false; + ret = usb_ep_set_halt(dev->gadget->ep0); + if (ret < 0) + dev_err(&dev->gadget->dev, + "fail, usb_ep_set_halt returned %d\n", ret); + + if (dev->ep0_in_pending) + dev->ep0_in_pending = false; + else + dev->ep0_out_pending = false; - return true; +out_unlock: + spin_unlock_irqrestore(&dev->lock, flags); + return ret; } static int raw_ioctl_ep_enable(struct raw_dev *dev, unsigned long value) @@ -713,7 +753,7 @@ static int raw_ioctl_ep_enable(struct raw_dev *dev, unsigned long value) int ret = 0, i; unsigned long flags; struct usb_endpoint_descriptor *desc; - struct usb_ep *ep = NULL; + struct raw_ep *ep; desc = memdup_user((void __user *)value, sizeof(*desc)); if (IS_ERR(desc)) @@ -741,41 +781,32 @@ static int raw_ioctl_ep_enable(struct raw_dev *dev, unsigned long value) goto out_free; } - for (i = 0; i < USB_RAW_MAX_ENDPOINTS; i++) { - if (dev->eps[i].state == STATE_EP_ENABLED) + for (i = 0; i < dev->eps_num; i++) { + ep = &dev->eps[i]; + if (ep->state != STATE_EP_DISABLED) continue; - break; - } - if (i == USB_RAW_MAX_ENDPOINTS) { - dev_dbg(&dev->gadget->dev, - "fail, no device endpoints available\n"); - ret = -EBUSY; - goto out_free; - } - - gadget_for_each_ep(ep, dev->gadget) { - if (ep->enabled) + if (ep->addr != usb_endpoint_num(desc) && + ep->addr != USB_RAW_EP_ADDR_ANY) continue; - if (!check_ep_caps(ep, desc)) + if (!usb_gadget_ep_match_desc(dev->gadget, ep->ep, desc, NULL)) continue; - ep->desc = desc; - ret = usb_ep_enable(ep); + ep->ep->desc = desc; + ret = usb_ep_enable(ep->ep); if (ret < 0) { dev_err(&dev->gadget->dev, "fail, usb_ep_enable returned %d\n", ret); goto out_free; } - dev->eps[i].req = usb_ep_alloc_request(ep, GFP_ATOMIC); - if (!dev->eps[i].req) { + ep->req = usb_ep_alloc_request(ep->ep, GFP_ATOMIC); + if (!ep->req) { dev_err(&dev->gadget->dev, "fail, usb_ep_alloc_request failed\n"); - usb_ep_disable(ep); + usb_ep_disable(ep->ep); ret = -ENOMEM; goto out_free; } - dev->eps[i].ep = ep; - dev->eps[i].state = STATE_EP_ENABLED; - ep->driver_data = &dev->eps[i]; + ep->state = STATE_EP_ENABLED; + ep->ep->driver_data = ep; ret = i; goto out_unlock; } @@ -794,10 +825,6 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value) { int ret = 0, i = value; unsigned long flags; - const void *desc; - - if (i < 0 || i >= USB_RAW_MAX_ENDPOINTS) - return -EINVAL; spin_lock_irqsave(&dev->lock, flags); if (dev->state != STATE_DEV_RUNNING) { @@ -810,7 +837,12 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value) ret = -EBUSY; goto out_unlock; } - if (dev->eps[i].state != STATE_EP_ENABLED) { + if (i < 0 || i >= dev->eps_num) { + dev_dbg(dev->dev, "fail, invalid endpoint\n"); + ret = -EBUSY; + goto out_unlock; + } + if (dev->eps[i].state == STATE_EP_DISABLED) { dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n"); ret = -EINVAL; goto out_unlock; @@ -834,10 +866,8 @@ static int raw_ioctl_ep_disable(struct raw_dev *dev, unsigned long value) spin_lock_irqsave(&dev->lock, flags); usb_ep_free_request(dev->eps[i].ep, dev->eps[i].req); - desc = dev->eps[i].ep->desc; - dev->eps[i].ep = NULL; + kfree(dev->eps[i].ep->desc); dev->eps[i].state = STATE_EP_DISABLED; - kfree(desc); dev->eps[i].disabling = false; out_unlock: @@ -845,6 +875,74 @@ out_unlock: return ret; } +static int raw_ioctl_ep_set_clear_halt_wedge(struct raw_dev *dev, + unsigned long value, bool set, bool halt) +{ + int ret = 0, i = value; + unsigned long flags; + + spin_lock_irqsave(&dev->lock, flags); + if (dev->state != STATE_DEV_RUNNING) { + dev_dbg(dev->dev, "fail, device is not running\n"); + ret = -EINVAL; + goto out_unlock; + } + if (!dev->gadget) { + dev_dbg(dev->dev, "fail, gadget is not bound\n"); + ret = -EBUSY; + goto out_unlock; + } + if (i < 0 || i >= dev->eps_num) { + dev_dbg(dev->dev, "fail, invalid endpoint\n"); + ret = -EBUSY; + goto out_unlock; + } + if (dev->eps[i].state == STATE_EP_DISABLED) { + dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n"); + ret = -EINVAL; + goto out_unlock; + } + if (dev->eps[i].disabling) { + dev_dbg(&dev->gadget->dev, + "fail, disable is in progress\n"); + ret = -EINVAL; + goto out_unlock; + } + if (dev->eps[i].urb_queued) { + dev_dbg(&dev->gadget->dev, + "fail, waiting for urb completion\n"); + ret = -EINVAL; + goto out_unlock; + } + if (usb_endpoint_xfer_isoc(dev->eps[i].ep->desc)) { + dev_dbg(&dev->gadget->dev, + "fail, can't halt/wedge ISO endpoint\n"); + ret = -EINVAL; + goto out_unlock; + } + + if (set && halt) { + ret = usb_ep_set_halt(dev->eps[i].ep); + if (ret < 0) + dev_err(&dev->gadget->dev, + "fail, usb_ep_set_halt returned %d\n", ret); + } else if (!set && halt) { + ret = usb_ep_clear_halt(dev->eps[i].ep); + if (ret < 0) + dev_err(&dev->gadget->dev, + "fail, usb_ep_clear_halt returned %d\n", ret); + } else if (set && !halt) { + ret = usb_ep_set_wedge(dev->eps[i].ep); + if (ret < 0) + dev_err(&dev->gadget->dev, + "fail, usb_ep_set_wedge returned %d\n", ret); + } + +out_unlock: + spin_unlock_irqrestore(&dev->lock, flags); + return ret; +} + static void gadget_ep_complete(struct usb_ep *ep, struct usb_request *req) { struct raw_ep *r_ep = (struct raw_ep *)ep->driver_data; @@ -866,7 +964,7 @@ static int raw_process_ep_io(struct raw_dev *dev, struct usb_raw_ep_io *io, { int ret = 0; unsigned long flags; - struct raw_ep *ep = &dev->eps[io->ep]; + struct raw_ep *ep; DECLARE_COMPLETION_ONSTACK(done); spin_lock_irqsave(&dev->lock, flags); @@ -880,6 +978,12 @@ static int raw_process_ep_io(struct raw_dev *dev, struct usb_raw_ep_io *io, ret = -EBUSY; goto out_unlock; } + if (io->ep >= dev->eps_num) { + dev_dbg(&dev->gadget->dev, "fail, invalid endpoint\n"); + ret = -EINVAL; + goto out_unlock; + } + ep = &dev->eps[io->ep]; if (ep->state != STATE_EP_ENABLED) { dev_dbg(&dev->gadget->dev, "fail, endpoint is not enabled\n"); ret = -EBUSY; @@ -964,12 +1068,14 @@ static int raw_ioctl_ep_read(struct raw_dev *dev, unsigned long value) if (IS_ERR(data)) return PTR_ERR(data); ret = raw_process_ep_io(dev, &io, data, false); - if (ret) + if (ret < 0) goto free; length = min(io.length, (unsigned int)ret); if (copy_to_user((void __user *)(value + sizeof(io)), data, length)) ret = -EFAULT; + else + ret = length; free: kfree(data); return ret; @@ -1023,6 +1129,71 @@ out_unlock: return ret; } +static void fill_ep_caps(struct usb_ep_caps *caps, + struct usb_raw_ep_caps *raw_caps) +{ + raw_caps->type_control = caps->type_control; + raw_caps->type_iso = caps->type_iso; + raw_caps->type_bulk = caps->type_bulk; + raw_caps->type_int = caps->type_int; + raw_caps->dir_in = caps->dir_in; + raw_caps->dir_out = caps->dir_out; +} + +static void fill_ep_limits(struct usb_ep *ep, struct usb_raw_ep_limits *limits) +{ + limits->maxpacket_limit = ep->maxpacket_limit; + limits->max_streams = ep->max_streams; +} + +static int raw_ioctl_eps_info(struct raw_dev *dev, unsigned long value) +{ + int ret = 0, i; + unsigned long flags; + struct usb_raw_eps_info *info; + struct raw_ep *ep; + + info = kmalloc(sizeof(*info), GFP_KERNEL); + if (!info) { + ret = -ENOMEM; + goto out; + } + + spin_lock_irqsave(&dev->lock, flags); + if (dev->state != STATE_DEV_RUNNING) { + dev_dbg(dev->dev, "fail, device is not running\n"); + ret = -EINVAL; + spin_unlock_irqrestore(&dev->lock, flags); + goto out_free; + } + if (!dev->gadget) { + dev_dbg(dev->dev, "fail, gadget is not bound\n"); + ret = -EBUSY; + spin_unlock_irqrestore(&dev->lock, flags); + goto out_free; + } + + memset(info, 0, sizeof(*info)); + for (i = 0; i < dev->eps_num; i++) { + ep = &dev->eps[i]; + strscpy(&info->eps[i].name[0], ep->ep->name, + USB_RAW_EP_NAME_MAX); + info->eps[i].addr = ep->addr; + fill_ep_caps(&ep->ep->caps, &info->eps[i].caps); + fill_ep_limits(ep->ep, &info->eps[i].limits); + } + ret = dev->eps_num; + spin_unlock_irqrestore(&dev->lock, flags); + + if (copy_to_user((void __user *)value, info, sizeof(*info))) + ret = -EFAULT; + +out_free: + kfree(info); +out: + return ret; +} + static long raw_ioctl(struct file *fd, unsigned int cmd, unsigned long value) { struct raw_dev *dev = fd->private_data; @@ -1065,6 +1236,24 @@ static long raw_ioctl(struct file *fd, unsigned int cmd, unsigned long value) case USB_RAW_IOCTL_VBUS_DRAW: ret = raw_ioctl_vbus_draw(dev, value); break; + case USB_RAW_IOCTL_EPS_INFO: + ret = raw_ioctl_eps_info(dev, value); + break; + case USB_RAW_IOCTL_EP0_STALL: + ret = raw_ioctl_ep0_stall(dev, value); + break; + case USB_RAW_IOCTL_EP_SET_HALT: + ret = raw_ioctl_ep_set_clear_halt_wedge( + dev, value, true, true); + break; + case USB_RAW_IOCTL_EP_CLEAR_HALT: + ret = raw_ioctl_ep_set_clear_halt_wedge( + dev, value, false, true); + break; + case USB_RAW_IOCTL_EP_SET_WEDGE: + ret = raw_ioctl_ep_set_clear_halt_wedge( + dev, value, true, false); + break; default: ret = -EINVAL; } diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c index 22200341c8ec..b771a854e29c 100644 --- a/drivers/usb/gadget/udc/atmel_usba_udc.c +++ b/drivers/usb/gadget/udc/atmel_usba_udc.c @@ -185,7 +185,7 @@ static int regs_dbg_release(struct inode *inode, struct file *file) return 0; } -const struct file_operations queue_dbg_fops = { +static const struct file_operations queue_dbg_fops = { .owner = THIS_MODULE, .open = queue_dbg_open, .llseek = no_llseek, @@ -193,7 +193,7 @@ const struct file_operations queue_dbg_fops = { .release = queue_dbg_release, }; -const struct file_operations regs_dbg_fops = { +static const struct file_operations regs_dbg_fops = { .owner = THIS_MODULE, .open = regs_dbg_open, .llseek = generic_file_llseek, diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index a8273b589456..5af0fe9c61d7 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -2647,6 +2647,8 @@ net2272_plat_probe(struct platform_device *pdev) err_req: release_mem_region(base, len); err: + kfree(dev); + return ret; } diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index 52a6add961f4..dfabc54cdc27 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -3840,11 +3840,11 @@ static int __maybe_unused tegra_xudc_suspend(struct device *dev) flush_work(&xudc->usb_role_sw_work); - /* Forcibly disconnect before powergating. */ - tegra_xudc_device_mode_off(xudc); - - if (!pm_runtime_status_suspended(dev)) + if (!pm_runtime_status_suspended(dev)) { + /* Forcibly disconnect before powergating. */ + tegra_xudc_device_mode_off(xudc); tegra_xudc_powergate(xudc); + } pm_runtime_disable(dev); diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 1d4f6f85f0fe..ea460b9682d5 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -362,6 +362,7 @@ static int xhci_plat_remove(struct platform_device *dev) struct clk *reg_clk = xhci->reg_clk; struct usb_hcd *shared_hcd = xhci->shared_hcd; + pm_runtime_get_sync(&dev->dev); xhci->xhc_state |= XHCI_STATE_REMOVING; usb_remove_hcd(shared_hcd); @@ -375,8 +376,9 @@ static int xhci_plat_remove(struct platform_device *dev) clk_disable_unprepare(reg_clk); usb_put_hcd(hcd); - pm_runtime_set_suspended(&dev->dev); pm_runtime_disable(&dev->dev); + pm_runtime_put_noidle(&dev->dev); + pm_runtime_set_suspended(&dev->dev); return 0; } diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 0fda0c0f4d31..2c255d0620b0 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -3433,8 +3433,8 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags, /* New sg entry */ --num_sgs; sent_len -= block_len; - if (num_sgs != 0) { - sg = sg_next(sg); + sg = sg_next(sg); + if (num_sgs != 0 && sg) { block_len = sg_dma_len(sg); addr = (u64) sg_dma_address(sg); addr += sent_len; diff --git a/drivers/usb/mtu3/mtu3_debugfs.c b/drivers/usb/mtu3/mtu3_debugfs.c index c96e5dab0a48..fdeade6254ae 100644 --- a/drivers/usb/mtu3/mtu3_debugfs.c +++ b/drivers/usb/mtu3/mtu3_debugfs.c @@ -276,7 +276,7 @@ static const struct file_operations mtu3_ep_fops = { .release = single_release, }; -static struct debugfs_reg32 mtu3_prb_regs[] = { +static const struct debugfs_reg32 mtu3_prb_regs[] = { dump_prb_reg("enable", U3D_SSUSB_PRB_CTRL0), dump_prb_reg("byte-sell", U3D_SSUSB_PRB_CTRL1), dump_prb_reg("byte-selh", U3D_SSUSB_PRB_CTRL2), @@ -349,7 +349,7 @@ static const struct file_operations mtu3_probe_fops = { static void mtu3_debugfs_create_prb_files(struct mtu3 *mtu) { struct ssusb_mtk *ssusb = mtu->ssusb; - struct debugfs_reg32 *regs; + const struct debugfs_reg32 *regs; struct dentry *dir_prb; int i; diff --git a/drivers/usb/phy/phy-twl6030-usb.c b/drivers/usb/phy/phy-twl6030-usb.c index bfebf1f2e991..9a7e655d5280 100644 --- a/drivers/usb/phy/phy-twl6030-usb.c +++ b/drivers/usb/phy/phy-twl6030-usb.c @@ -377,7 +377,7 @@ static int twl6030_usb_probe(struct platform_device *pdev) if (status < 0) { dev_err(&pdev->dev, "can't get IRQ %d, err %d\n", twl->irq1, status); - return status; + goto err_put_regulator; } status = request_threaded_irq(twl->irq2, NULL, twl6030_usb_irq, @@ -386,8 +386,7 @@ static int twl6030_usb_probe(struct platform_device *pdev) if (status < 0) { dev_err(&pdev->dev, "can't get IRQ %d, err %d\n", twl->irq2, status); - free_irq(twl->irq1, twl); - return status; + goto err_free_irq1; } twl->asleep = 0; @@ -396,6 +395,13 @@ static int twl6030_usb_probe(struct platform_device *pdev) dev_info(&pdev->dev, "Initialized TWL6030 USB module\n"); return 0; + +err_free_irq1: + free_irq(twl->irq1, twl); +err_put_regulator: + regulator_put(twl->usb3v3); + + return status; } static int twl6030_usb_remove(struct platform_device *pdev) diff --git a/drivers/usb/serial/garmin_gps.c b/drivers/usb/serial/garmin_gps.c index ffd984142171..d63072fee099 100644 --- a/drivers/usb/serial/garmin_gps.c +++ b/drivers/usb/serial/garmin_gps.c @@ -1138,8 +1138,8 @@ static void garmin_read_process(struct garmin_data *garmin_data_p, send it directly to the tty port */ if (garmin_data_p->flags & FLAGS_QUEUING) { pkt_add(garmin_data_p, data, data_length); - } else if (bulk_data || - getLayerId(data) == GARMIN_LAYERID_APPL) { + } else if (bulk_data || (data_length >= sizeof(u32) && + getLayerId(data) == GARMIN_LAYERID_APPL)) { spin_lock_irqsave(&garmin_data_p->lock, flags); garmin_data_p->flags |= APP_RESP_SEEN; diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c index 613f91add03d..ce0401d3137f 100644 --- a/drivers/usb/serial/qcserial.c +++ b/drivers/usb/serial/qcserial.c @@ -173,6 +173,7 @@ static const struct usb_device_id id_table[] = { {DEVICE_SWI(0x413c, 0x81b3)}, /* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */ {DEVICE_SWI(0x413c, 0x81b5)}, /* Dell Wireless 5811e QDL */ {DEVICE_SWI(0x413c, 0x81b6)}, /* Dell Wireless 5811e QDL */ + {DEVICE_SWI(0x413c, 0x81cc)}, /* Dell Wireless 5816e */ {DEVICE_SWI(0x413c, 0x81cf)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d0)}, /* Dell Wireless 5819 */ {DEVICE_SWI(0x413c, 0x81d1)}, /* Dell Wireless 5818 */ diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 1b23741036ee..37157ed9a881 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -28,6 +28,13 @@ * and don't forget to CC: the USB development list <linux-usb@vger.kernel.org> */ +/* Reported-by: Julian Groß <julian.g@posteo.de> */ +UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999, + "LaCie", + "2Big Quadra USB3", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_REPORT_OPCODES), + /* * Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI * commands in UAS mode. Observed with the 1.28 firmware; are there others? diff --git a/drivers/usb/typec/mux/intel_pmc_mux.c b/drivers/usb/typec/mux/intel_pmc_mux.c index f5c5e0aef66f..c22e5c4bbf1a 100644 --- a/drivers/usb/typec/mux/intel_pmc_mux.c +++ b/drivers/usb/typec/mux/intel_pmc_mux.c @@ -63,6 +63,7 @@ enum { #define PMC_USB_ALTMODE_DP_MODE_SHIFT 8 /* TBT specific Mode Data bits */ +#define PMC_USB_ALTMODE_HPD_HIGH BIT(14) #define PMC_USB_ALTMODE_TBT_TYPE BIT(17) #define PMC_USB_ALTMODE_CABLE_TYPE BIT(18) #define PMC_USB_ALTMODE_ACTIVE_LINK BIT(20) @@ -74,8 +75,8 @@ enum { #define PMC_USB_ALTMODE_TBT_GEN(_g_) (((_g_) & GENMASK(1, 0)) << 28) /* Display HPD Request bits */ +#define PMC_USB_DP_HPD_LVL BIT(4) #define PMC_USB_DP_HPD_IRQ BIT(5) -#define PMC_USB_DP_HPD_LVL BIT(6) struct pmc_usb; @@ -157,6 +158,9 @@ pmc_usb_mux_dp(struct pmc_usb_port *port, struct typec_mux_state *state) req.mode_data |= (state->mode - TYPEC_STATE_MODAL) << PMC_USB_ALTMODE_DP_MODE_SHIFT; + if (data->status & DP_STATUS_HPD_STATE) + req.mode_data |= PMC_USB_ALTMODE_HPD_HIGH; + return pmc_usb_command(port, (void *)&req, sizeof(req)); } @@ -298,11 +302,11 @@ static int pmc_usb_register_port(struct pmc_usb *pmc, int index, struct typec_mux_desc mux_desc = { }; int ret; - ret = fwnode_property_read_u8(fwnode, "usb2-port", &port->usb2_port); + ret = fwnode_property_read_u8(fwnode, "usb2-port-number", &port->usb2_port); if (ret) return ret; - ret = fwnode_property_read_u8(fwnode, "usb3-port", &port->usb3_port); + ret = fwnode_property_read_u8(fwnode, "usb3-port-number", &port->usb3_port); if (ret) return ret; diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index e36aaf9ba7bd..fb4e944c4d0d 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -181,14 +181,14 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, break; } - vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); - added = true; - - /* Deliver to monitoring devices all correctly transmitted - * packets. + /* Deliver to monitoring devices all packets that we + * will transmit. */ virtio_transport_deliver_tap_pkt(pkt); + vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len); + added = true; + pkt->off += payload_len; total_len += payload_len; @@ -196,6 +196,12 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, * to send it with the next available buffer. */ if (pkt->off < pkt->len) { + /* We are queueing the same virtio_vsock_pkt to handle + * the remaining bytes, and we want to deliver it + * to monitoring devices in the next iteration. + */ + pkt->tap_delivered = false; + spin_lock_bh(&vsock->send_pkt_list_lock); list_add(&pkt->list, &vsock->send_pkt_list); spin_unlock_bh(&vsock->send_pkt_list_lock); @@ -543,6 +549,11 @@ static int vhost_vsock_start(struct vhost_vsock *vsock) mutex_unlock(&vq->mutex); } + /* Some packets may have been queued before the device was started, + * let's kick the send worker to send them. + */ + vhost_work_queue(&vsock->dev, &vsock->send_pkt_work); + mutex_unlock(&vsock->dev.mutex); return 0; diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index 1dc97f2d6201..e7726f5f1241 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -60,9 +60,9 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, object = container_of(op->op.object, struct cachefiles_object, fscache); spin_lock(&object->work_lock); list_add_tail(&monitor->op_link, &op->to_do); + fscache_enqueue_retrieval(op); spin_unlock(&object->work_lock); - fscache_enqueue_retrieval(op); fscache_put_retrieval(op); return 0; } @@ -398,7 +398,7 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, struct inode *inode; sector_t block; unsigned shift; - int ret; + int ret, ret2; object = container_of(op->op.object, struct cachefiles_object, fscache); @@ -430,8 +430,8 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op, block = page->index; block <<= shift; - ret = bmap(inode, &block); - ASSERT(ret < 0); + ret2 = bmap(inode, &block); + ASSERT(ret2 == 0); _debug("%llx -> %llx", (unsigned long long) (page->index << shift), @@ -739,8 +739,8 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op, block = page->index; block <<= shift; - ret = bmap(inode, &block); - ASSERT(!ret); + ret2 = bmap(inode, &block); + ASSERT(ret2 == 0); _debug("%llx -> %llx", (unsigned long long) (page->index << shift), diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 185db76300b3..5f3aa4d607de 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2749,7 +2749,7 @@ int ceph_try_get_caps(struct inode *inode, int need, int want, ret = try_get_cap_refs(inode, need, want, 0, flags, got); /* three special error codes */ - if (ret == -EAGAIN || ret == -EFBIG || ret == -EAGAIN) + if (ret == -EAGAIN || ret == -EFBIG || ret == -ESTALE) ret = 0; return ret; } @@ -3746,6 +3746,7 @@ retry: WARN_ON(1); tsession = NULL; target = -1; + mutex_lock(&session->s_mutex); } goto retry; diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index 481ac97b4d25..dcaed75de9e6 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -271,7 +271,7 @@ void ceph_fs_debugfs_init(struct ceph_fs_client *fsc) &congestion_kb_fops); snprintf(name, sizeof(name), "../../bdi/%s", - dev_name(fsc->sb->s_bdi->dev)); + bdi_dev_name(fsc->sb->s_bdi)); fsc->debugfs_bdi = debugfs_create_symlink("bdi", fsc->client->debugfs_dir, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 486f91f9685b..7c63abf5bea9 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -3251,8 +3251,7 @@ static void handle_session(struct ceph_mds_session *session, void *end = p + msg->front.iov_len; struct ceph_mds_session_head *h; u32 op; - u64 seq; - unsigned long features = 0; + u64 seq, features = 0; int wake = 0; bool blacklisted = false; @@ -3271,9 +3270,8 @@ static void handle_session(struct ceph_mds_session *session, goto bad; /* version >= 3, feature bits */ ceph_decode_32_safe(&p, end, len, bad); - ceph_decode_need(&p, end, len, bad); - memcpy(&features, p, min_t(size_t, len, sizeof(features))); - p += len; + ceph_decode_64_safe(&p, end, features, bad); + p += len - sizeof(features); } mutex_lock(&mdsc->mutex); diff --git a/fs/ceph/quota.c b/fs/ceph/quota.c index de56dee60540..19507e2fdb57 100644 --- a/fs/ceph/quota.c +++ b/fs/ceph/quota.c @@ -159,8 +159,8 @@ static struct inode *lookup_quotarealm_inode(struct ceph_mds_client *mdsc, } if (IS_ERR(in)) { - pr_warn("Can't lookup inode %llx (err: %ld)\n", - realm->ino, PTR_ERR(in)); + dout("Can't lookup inode %llx (err: %ld)\n", + realm->ino, PTR_ERR(in)); qri->timeout = jiffies + msecs_to_jiffies(60 * 1000); /* XXX */ } else { qri->timeout = 0; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 182b864b3075..5014a82391ff 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -2152,8 +2152,8 @@ cifs_writev_requeue(struct cifs_writedata *wdata) } } + kref_put(&wdata2->refcount, cifs_writedata_release); if (rc) { - kref_put(&wdata2->refcount, cifs_writedata_release); if (is_retryable_error(rc)) continue; i += nr_pages; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 0b1528edebcf..75ddce8ef456 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4060,7 +4060,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset) * than it negotiated since it will refuse the read * then. */ - if ((tcon->ses) && !(tcon->ses->capabilities & + if (!(tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files)) { current_read_size = min_t(uint, current_read_size, CIFSMaxBufSize); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 390d2b15ef6e..5d2965a23730 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -730,7 +730,7 @@ static __u64 simple_hashstr(const char *str) * cifs_backup_query_path_info - SMB1 fallback code to get ino * * Fallback code to get file metadata when we don't have access to - * @full_path (EACCESS) and have backup creds. + * @full_path (EACCES) and have backup creds. * * @data will be set to search info result buffer * @resp_buf will be set to cifs resp buf and needs to be freed with diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index cf7b7e1d5bd7..cb733652ecca 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1519,6 +1519,7 @@ static int configfs_rmdir(struct inode *dir, struct dentry *dentry) spin_lock(&configfs_dirent_lock); configfs_detach_rollback(dentry); spin_unlock(&configfs_dirent_lock); + config_item_put(parent_item); return -EINTR; } frag->frag_dead = true; diff --git a/fs/coredump.c b/fs/coredump.c index 408418e6aa13..478a0d810136 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -788,6 +788,14 @@ void do_coredump(const kernel_siginfo_t *siginfo) if (displaced) put_files_struct(displaced); if (!dump_interrupted()) { + /* + * umh disabled with CONFIG_STATIC_USERMODEHELPER_PATH="" would + * have this set to NULL. + */ + if (!cprm.file) { + pr_info("Core dump to |%s disabled\n", cn.corename); + goto close_fail; + } file_start_write(cprm.file); core_dumped = binfmt->core_dump(&cprm); file_end_write(cprm.file); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 8c596641a72b..12eebcdea9c8 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1171,6 +1171,10 @@ static inline bool chain_epi_lockless(struct epitem *epi) { struct eventpoll *ep = epi->ep; + /* Fast preliminary check */ + if (epi->next != EP_UNACTIVE_PTR) + return false; + /* Check that the same epi has not been just chained from another CPU */ if (cmpxchg(&epi->next, EP_UNACTIVE_PTR, NULL) != EP_UNACTIVE_PTR) return false; @@ -1237,16 +1241,12 @@ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, v * chained in ep->ovflist and requeued later on. */ if (READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR) { - if (epi->next == EP_UNACTIVE_PTR && - chain_epi_lockless(epi)) + if (chain_epi_lockless(epi)) + ep_pm_stay_awake_rcu(epi); + } else if (!ep_is_linked(epi)) { + /* In the usual case, add event to ready list. */ + if (list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) ep_pm_stay_awake_rcu(epi); - goto out_unlock; - } - - /* If this file is already in the ready list we exit soon */ - if (!ep_is_linked(epi) && - list_add_tail_lockless(&epi->rdllink, &ep->rdllist)) { - ep_pm_stay_awake_rcu(epi); } /* @@ -1822,7 +1822,6 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, { int res = 0, eavail, timed_out = 0; u64 slack = 0; - bool waiter = false; wait_queue_entry_t wait; ktime_t expires, *to = NULL; @@ -1867,55 +1866,75 @@ fetch_events: */ ep_reset_busy_poll_napi_id(ep); - /* - * We don't have any available event to return to the caller. We need - * to sleep here, and we will be woken by ep_poll_callback() when events - * become available. - */ - if (!waiter) { - waiter = true; - init_waitqueue_entry(&wait, current); + do { + /* + * Internally init_wait() uses autoremove_wake_function(), + * thus wait entry is removed from the wait queue on each + * wakeup. Why it is important? In case of several waiters + * each new wakeup will hit the next waiter, giving it the + * chance to harvest new event. Otherwise wakeup can be + * lost. This is also good performance-wise, because on + * normal wakeup path no need to call __remove_wait_queue() + * explicitly, thus ep->lock is not taken, which halts the + * event delivery. + */ + init_wait(&wait); write_lock_irq(&ep->lock); - __add_wait_queue_exclusive(&ep->wq, &wait); - write_unlock_irq(&ep->lock); - } - - for (;;) { /* - * We don't want to sleep if the ep_poll_callback() sends us - * a wakeup in between. That's why we set the task state - * to TASK_INTERRUPTIBLE before doing the checks. + * Barrierless variant, waitqueue_active() is called under + * the same lock on wakeup ep_poll_callback() side, so it + * is safe to avoid an explicit barrier. */ - set_current_state(TASK_INTERRUPTIBLE); + __set_current_state(TASK_INTERRUPTIBLE); + /* - * Always short-circuit for fatal signals to allow - * threads to make a timely exit without the chance of - * finding more events available and fetching - * repeatedly. + * Do the final check under the lock. ep_scan_ready_list() + * plays with two lists (->rdllist and ->ovflist) and there + * is always a race when both lists are empty for short + * period of time although events are pending, so lock is + * important. */ - if (fatal_signal_pending(current)) { - res = -EINTR; - break; + eavail = ep_events_available(ep); + if (!eavail) { + if (signal_pending(current)) + res = -EINTR; + else + __add_wait_queue_exclusive(&ep->wq, &wait); } + write_unlock_irq(&ep->lock); - eavail = ep_events_available(ep); - if (eavail) + if (eavail || res) break; - if (signal_pending(current)) { - res = -EINTR; - break; - } if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) { timed_out = 1; break; } - } + + /* We were woken up, thus go and try to harvest some events */ + eavail = 1; + + } while (0); __set_current_state(TASK_RUNNING); + if (!list_empty_careful(&wait.entry)) { + write_lock_irq(&ep->lock); + __remove_wait_queue(&ep->wq, &wait); + write_unlock_irq(&ep->lock); + } + send_events: + if (fatal_signal_pending(current)) { + /* + * Always short-circuit for fatal signals to allow + * threads to make a timely exit without the chance of + * finding more events available and fetching + * repeatedly. + */ + res = -EINTR; + } /* * Try to transfer events to user space. In case we get 0 events and * there's still timeout left over, we go trying again in search of @@ -1925,12 +1944,6 @@ send_events: !(res = ep_send_events(ep, events, maxevents)) && !timed_out) goto fetch_events; - if (waiter) { - write_lock_irq(&ep->lock); - __remove_wait_queue(&ep->wq, &wait); - write_unlock_irq(&ep->lock); - } - return res; } diff --git a/fs/exec.c b/fs/exec.c index 06b4c550af5d..2c465119affc 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1317,6 +1317,8 @@ int flush_old_exec(struct linux_binprm * bprm) */ set_mm_exe_file(bprm->mm, bprm->file); + would_dump(bprm, bprm->file); + /* * Release all of the old mmap stuff */ @@ -1876,8 +1878,6 @@ static int __do_execve_file(int fd, struct filename *filename, if (retval < 0) goto out; - would_dump(bprm, bprm->file); - retval = exec_binprm(bprm); if (retval < 0) goto out; diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c index 936a8ec6b48e..6306eaae378b 100644 --- a/fs/gfs2/bmap.c +++ b/fs/gfs2/bmap.c @@ -528,10 +528,12 @@ lower_metapath: /* Advance in metadata tree. */ (mp->mp_list[hgt])++; - if (mp->mp_list[hgt] >= sdp->sd_inptrs) { - if (!hgt) + if (hgt) { + if (mp->mp_list[hgt] >= sdp->sd_inptrs) + goto lower_metapath; + } else { + if (mp->mp_list[hgt] >= sdp->sd_diptrs) break; - goto lower_metapath; } fill_up_metapath: @@ -876,10 +878,9 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length, ret = -ENOENT; goto unlock; } else { - /* report a hole */ iomap->offset = pos; iomap->length = length; - goto do_alloc; + goto hole_found; } } iomap->length = size; @@ -933,8 +934,6 @@ unlock: return ret; do_alloc: - iomap->addr = IOMAP_NULL_ADDR; - iomap->type = IOMAP_HOLE; if (flags & IOMAP_REPORT) { if (pos >= size) ret = -ENOENT; @@ -956,6 +955,9 @@ do_alloc: if (pos < size && height == ip->i_height) ret = gfs2_hole_size(inode, lblock, len, mp, iomap); } +hole_found: + iomap->addr = IOMAP_NULL_ADDR; + iomap->type = IOMAP_HOLE; goto out; } diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c index 29f9b6684b74..bf70e3b14938 100644 --- a/fs/gfs2/glock.c +++ b/fs/gfs2/glock.c @@ -613,7 +613,7 @@ __acquires(&gl->gl_lockref.lock) fs_err(sdp, "Error %d syncing glock \n", ret); gfs2_dump_glock(NULL, gl, true); } - return; + goto skip_inval; } } if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags)) { @@ -633,6 +633,7 @@ __acquires(&gl->gl_lockref.lock) clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags); } +skip_inval: gfs2_glock_hold(gl); /* * Check for an error encountered since we called go_sync and go_inval. @@ -722,9 +723,6 @@ __acquires(&gl->gl_lockref.lock) goto out_unlock; if (nonblock) goto out_sched; - smp_mb(); - if (atomic_read(&gl->gl_revokes) != 0) - goto out_sched; set_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags); GLOCK_BUG_ON(gl, gl->gl_demote_state == LM_ST_EXCLUSIVE); gl->gl_target = gl->gl_demote_state; diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 70b2d3a1e866..5acd3ce30759 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -622,7 +622,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = finish_no_open(file, NULL); } gfs2_glock_dq_uninit(ghs); - return error; + goto fail; } else if (error != -ENOENT) { goto fail_gunlock; } @@ -764,9 +764,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, error = finish_open(file, dentry, gfs2_open_common); } gfs2_glock_dq_uninit(ghs); + gfs2_qa_put(ip); gfs2_glock_dq_uninit(ghs + 1); clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); gfs2_glock_put(io_gl); + gfs2_qa_put(dip); return error; fail_gunlock3: @@ -776,7 +778,6 @@ fail_gunlock2: clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); gfs2_glock_put(io_gl); fail_free_inode: - gfs2_qa_put(ip); if (ip->i_gl) { glock_clear_object(ip->i_gl, ip); gfs2_glock_put(ip->i_gl); @@ -1005,7 +1006,7 @@ out_gunlock: out_child: gfs2_glock_dq(ghs); out_parent: - gfs2_qa_put(ip); + gfs2_qa_put(dip); gfs2_holder_uninit(ghs); gfs2_holder_uninit(ghs + 1); return error; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 3a75843ae580..0644e58c6191 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -669,13 +669,13 @@ void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd) struct buffer_head *bh = bd->bd_bh; struct gfs2_glock *gl = bd->bd_gl; + sdp->sd_log_num_revoke++; + if (atomic_inc_return(&gl->gl_revokes) == 1) + gfs2_glock_hold(gl); bh->b_private = NULL; bd->bd_blkno = bh->b_blocknr; gfs2_remove_from_ail(bd); /* drops ref on bh */ bd->bd_bh = NULL; - sdp->sd_log_num_revoke++; - if (atomic_inc_return(&gl->gl_revokes) == 1) - gfs2_glock_hold(gl); set_bit(GLF_LFLUSH, &gl->gl_flags); list_add(&bd->bd_list, &sdp->sd_log_revokes); } @@ -1131,6 +1131,10 @@ int gfs2_logd(void *data) while (!kthread_should_stop()) { + if (gfs2_withdrawn(sdp)) { + msleep_interruptible(HZ); + continue; + } /* Check for errors writing to the journal */ if (sdp->sd_log_error) { gfs2_lm(sdp, @@ -1139,6 +1143,7 @@ int gfs2_logd(void *data) "prevent further damage.\n", sdp->sd_fsname, sdp->sd_log_error); gfs2_withdraw(sdp); + continue; } did_flush = false; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 5ea96757afc4..48b54ec1c793 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -263,7 +263,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno, struct super_block *sb = sdp->sd_vfs; struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); - bio->bi_iter.bi_sector = blkno << (sb->s_blocksize_bits - 9); + bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift; bio_set_dev(bio, sb->s_bdev); bio->bi_end_io = end_io; bio->bi_private = sdp; @@ -509,7 +509,7 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, unsigned int bsize = sdp->sd_sb.sb_bsize, off; unsigned int bsize_shift = sdp->sd_sb.sb_bsize_shift; unsigned int shift = PAGE_SHIFT - bsize_shift; - unsigned int readahead_blocks = BIO_MAX_PAGES << shift; + unsigned int max_bio_size = 2 * 1024 * 1024; struct gfs2_journal_extent *je; int sz, ret = 0; struct bio *bio = NULL; @@ -537,12 +537,17 @@ int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head, off = 0; } - if (!bio || (bio_chained && !off)) { + if (!bio || (bio_chained && !off) || + bio->bi_iter.bi_size >= max_bio_size) { /* start new bio */ } else { - sz = bio_add_page(bio, page, bsize, off); - if (sz == bsize) - goto block_added; + sector_t sector = dblock << sdp->sd_fsb2bb_shift; + + if (bio_end_sector(bio) == sector) { + sz = bio_add_page(bio, page, bsize, off); + if (sz == bsize) + goto block_added; + } if (off) { unsigned int blocks = (PAGE_SIZE - off) >> bsize_shift; @@ -568,7 +573,7 @@ block_added: off += bsize; if (off == PAGE_SIZE) page = NULL; - if (blocks_submitted < blocks_read + readahead_blocks) { + if (blocks_submitted < 2 * max_bio_size >> bsize_shift) { /* Keep at least one bio in flight */ continue; } diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 4b72abcf83b2..9856cc2e0795 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -252,7 +252,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags, int num = 0; if (unlikely(gfs2_withdrawn(sdp)) && - (!sdp->sd_jdesc || (blkno != sdp->sd_jdesc->jd_no_addr))) { + (!sdp->sd_jdesc || gl != sdp->sd_jinode_gl)) { *bhp = NULL; return -EIO; } diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c index cc0c4b5800be..8259fef3f986 100644 --- a/fs/gfs2/quota.c +++ b/fs/gfs2/quota.c @@ -1051,8 +1051,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid) u32 x; int error = 0; - if (capable(CAP_SYS_RESOURCE) || - sdp->sd_args.ar_quota != GFS2_QUOTA_ON) + if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) return 0; error = gfs2_quota_hold(ip, uid, gid); @@ -1125,7 +1124,7 @@ void gfs2_quota_unlock(struct gfs2_inode *ip) int found; if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags)) - goto out; + return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { struct gfs2_quota_data *qd; @@ -1162,7 +1161,6 @@ void gfs2_quota_unlock(struct gfs2_inode *ip) qd_unlock(qda[x]); } -out: gfs2_quota_unhold(ip); } @@ -1210,9 +1208,6 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid, if (!test_bit(GIF_QD_LOCKED, &ip->i_flags)) return 0; - if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON) - return 0; - for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; @@ -1270,7 +1265,9 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change, if (ip->i_diskflags & GFS2_DIF_SYSTEM) return; - BUG_ON(ip->i_qadata->qa_ref <= 0); + if (gfs2_assert_withdraw(sdp, ip->i_qadata && + ip->i_qadata->qa_ref > 0)) + return; for (x = 0; x < ip->i_qadata->qa_qd_num; x++) { qd = ip->i_qadata->qa_qd[x]; diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h index 7f9ca8ef40fc..21ada332d555 100644 --- a/fs/gfs2/quota.h +++ b/fs/gfs2/quota.h @@ -44,7 +44,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip, int ret; ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */ - if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) + if (capable(CAP_SYS_RESOURCE) || + sdp->sd_args.ar_quota == GFS2_QUOTA_OFF) return 0; ret = gfs2_quota_lock(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE); if (ret) diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 37fc41632aa2..956fced0a8ec 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -1404,7 +1404,6 @@ out: if (ip->i_qadata) gfs2_assert_warn(sdp, ip->i_qadata->qa_ref == 0); gfs2_rs_delete(ip, NULL); - gfs2_qa_put(ip); gfs2_ordered_del_inode(ip); clear_inode(inode); gfs2_dir_hash_inval(ip); diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c index 9b64d40ab379..aa087a5675af 100644 --- a/fs/gfs2/util.c +++ b/fs/gfs2/util.c @@ -119,6 +119,12 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) if (!sb_rdonly(sdp->sd_vfs)) ret = gfs2_make_fs_ro(sdp); + if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */ + if (!ret) + ret = -EIO; + clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags); + goto skip_recovery; + } /* * Drop the glock for our journal so another node can recover it. */ @@ -159,10 +165,6 @@ static void signal_our_withdraw(struct gfs2_sbd *sdp) wait_on_bit(&gl->gl_flags, GLF_FREEING, TASK_UNINTERRUPTIBLE); } - if (sdp->sd_lockstruct.ls_ops->lm_lock == NULL) { /* lock_nolock */ - clear_bit(SDF_WITHDRAW_RECOVERY, &sdp->sd_flags); - goto skip_recovery; - } /* * Dequeue the "live" glock, but keep a reference so it's never freed. */ diff --git a/fs/io_uring.c b/fs/io_uring.c index 0b91b0631173..70ae7e840c85 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -680,8 +680,6 @@ struct io_op_def { unsigned needs_mm : 1; /* needs req->file assigned */ unsigned needs_file : 1; - /* needs req->file assigned IFF fd is >= 0 */ - unsigned fd_non_neg : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ @@ -784,8 +782,6 @@ static const struct io_op_def io_op_defs[] = { .needs_file = 1, }, [IORING_OP_OPENAT] = { - .needs_file = 1, - .fd_non_neg = 1, .file_table = 1, .needs_fs = 1, }, @@ -799,8 +795,6 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_STATX] = { .needs_mm = 1, - .needs_file = 1, - .fd_non_neg = 1, .needs_fs = 1, .file_table = 1, }, @@ -837,8 +831,6 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, }, [IORING_OP_OPENAT2] = { - .needs_file = 1, - .fd_non_neg = 1, .file_table = 1, .needs_fs = 1, }, @@ -1402,10 +1394,6 @@ static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb) for (i = 0; i < rb->to_free; i++) { struct io_kiocb *req = rb->reqs[i]; - if (req->flags & REQ_F_FIXED_FILE) { - req->file = NULL; - percpu_ref_put(req->fixed_file_refs); - } if (req->flags & REQ_F_INFLIGHT) inflight++; __io_req_aux_free(req); @@ -1678,7 +1666,7 @@ static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req) if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req)) return false; - if (!(req->flags & REQ_F_FIXED_FILE) || req->io) + if (req->file || req->io) rb->need_iter++; rb->reqs[rb->to_free++] = req; @@ -2775,16 +2763,19 @@ static int io_splice(struct io_kiocb *req, bool force_nonblock) struct file *out = sp->file_out; unsigned int flags = sp->flags & ~SPLICE_F_FD_IN_FIXED; loff_t *poff_in, *poff_out; - long ret; + long ret = 0; if (force_nonblock) return -EAGAIN; poff_in = (sp->off_in == -1) ? NULL : &sp->off_in; poff_out = (sp->off_out == -1) ? NULL : &sp->off_out; - ret = do_splice(in, poff_in, out, poff_out, sp->len, flags); - if (force_nonblock && ret == -EAGAIN) - return -EAGAIN; + + if (sp->len) { + ret = do_splice(in, poff_in, out, poff_out, sp->len, flags); + if (force_nonblock && ret == -EAGAIN) + return -EAGAIN; + } io_put_file(req, in, (sp->flags & SPLICE_F_FD_IN_FIXED)); req->flags &= ~REQ_F_NEED_CLEANUP; @@ -5368,15 +5359,6 @@ static void io_wq_submit_work(struct io_wq_work **workptr) io_steal_work(req, workptr); } -static int io_req_needs_file(struct io_kiocb *req, int fd) -{ - if (!io_op_defs[req->opcode].needs_file) - return 0; - if ((fd == -1 || fd == AT_FDCWD) && io_op_defs[req->opcode].fd_non_neg) - return 0; - return 1; -} - static inline struct file *io_file_from_index(struct io_ring_ctx *ctx, int index) { @@ -5414,14 +5396,11 @@ static int io_file_get(struct io_submit_state *state, struct io_kiocb *req, } static int io_req_set_file(struct io_submit_state *state, struct io_kiocb *req, - int fd, unsigned int flags) + int fd) { bool fixed; - if (!io_req_needs_file(req, fd)) - return 0; - - fixed = (flags & IOSQE_FIXED_FILE); + fixed = (req->flags & REQ_F_FIXED_FILE) != 0; if (unlikely(!fixed && req->needs_fixed_file)) return -EBADF; @@ -5798,7 +5777,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, struct io_submit_state *state, bool async) { unsigned int sqe_flags; - int id, fd; + int id; /* * All io need record the previous position, if LINK vs DARIN, @@ -5850,8 +5829,10 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, IOSQE_ASYNC | IOSQE_FIXED_FILE | IOSQE_BUFFER_SELECT | IOSQE_IO_LINK); - fd = READ_ONCE(sqe->fd); - return io_req_set_file(state, req, fd, sqe_flags); + if (!io_op_defs[req->opcode].needs_file) + return 0; + + return io_req_set_file(state, req, READ_ONCE(sqe->fd)); } static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr, @@ -7360,11 +7341,9 @@ static int io_uring_release(struct inode *inode, struct file *file) static void io_uring_cancel_files(struct io_ring_ctx *ctx, struct files_struct *files) { - struct io_kiocb *req; - DEFINE_WAIT(wait); - while (!list_empty_careful(&ctx->inflight_list)) { - struct io_kiocb *cancel_req = NULL; + struct io_kiocb *cancel_req = NULL, *req; + DEFINE_WAIT(wait); spin_lock_irq(&ctx->inflight_lock); list_for_each_entry(req, &ctx->inflight_list, inflight_entry) { @@ -7404,6 +7383,7 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, */ if (refcount_sub_and_test(2, &cancel_req->refs)) { io_put_req(cancel_req); + finish_wait(&ctx->inflight_wait, &wait); continue; } } @@ -7411,8 +7391,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, io_wq_cancel_work(ctx->io_wq, &cancel_req->work); io_put_req(cancel_req); schedule(); + finish_wait(&ctx->inflight_wait, &wait); } - finish_wait(&ctx->inflight_wait, &wait); } static int io_uring_flush(struct file *file, void *data) @@ -7761,7 +7741,8 @@ err: return ret; } -static int io_uring_create(unsigned entries, struct io_uring_params *p) +static int io_uring_create(unsigned entries, struct io_uring_params *p, + struct io_uring_params __user *params) { struct user_struct *user = NULL; struct io_ring_ctx *ctx; @@ -7853,6 +7834,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) p->cq_off.overflow = offsetof(struct io_rings, cq_overflow); p->cq_off.cqes = offsetof(struct io_rings, cqes); + p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | + IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | + IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL; + + if (copy_to_user(params, p, sizeof(*p))) { + ret = -EFAULT; + goto err; + } /* * Install ring fd as the very last thing, so we don't risk someone * having closed it before we finish setup @@ -7861,9 +7850,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p) if (ret < 0) goto err; - p->features = IORING_FEAT_SINGLE_MMAP | IORING_FEAT_NODROP | - IORING_FEAT_SUBMIT_STABLE | IORING_FEAT_RW_CUR_POS | - IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL; trace_io_uring_create(ret, ctx, p->sq_entries, p->cq_entries, p->flags); return ret; err: @@ -7879,7 +7865,6 @@ err: static long io_uring_setup(u32 entries, struct io_uring_params __user *params) { struct io_uring_params p; - long ret; int i; if (copy_from_user(&p, params, sizeof(p))) @@ -7894,14 +7879,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params) IORING_SETUP_CLAMP | IORING_SETUP_ATTACH_WQ)) return -EINVAL; - ret = io_uring_create(entries, &p); - if (ret < 0) - return ret; - - if (copy_to_user(params, &p, sizeof(p))) - return -EFAULT; - - return ret; + return io_uring_create(entries, &p, params); } SYSCALL_DEFINE2(io_uring_setup, u32, entries, diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index 1abf126c2df4..a60df88efc40 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -118,8 +118,6 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int nfss->fscache_key = NULL; nfss->fscache = NULL; - if (!(nfss->options & NFS_OPTION_FSCACHE)) - return; if (!uniq) { uniq = ""; ulen = 1; @@ -188,7 +186,8 @@ void nfs_fscache_get_super_cookie(struct super_block *sb, const char *uniq, int /* create a cache index for looking up filehandles */ nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache, &nfs_fscache_super_index_def, - key, sizeof(*key) + ulen, + &key->key, + sizeof(key->key) + ulen, NULL, 0, nfss, 0, true); dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n", @@ -226,6 +225,19 @@ void nfs_fscache_release_super_cookie(struct super_block *sb) } } +static void nfs_fscache_update_auxdata(struct nfs_fscache_inode_auxdata *auxdata, + struct nfs_inode *nfsi) +{ + memset(auxdata, 0, sizeof(*auxdata)); + auxdata->mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; + auxdata->mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; + auxdata->ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; + auxdata->ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; + + if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) + auxdata->change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); +} + /* * Initialise the per-inode cache cookie pointer for an NFS inode. */ @@ -239,14 +251,7 @@ void nfs_fscache_init_inode(struct inode *inode) if (!(nfss->fscache && S_ISREG(inode->i_mode))) return; - memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; - - if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) - auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); + nfs_fscache_update_auxdata(&auxdata, nfsi); nfsi->fscache = fscache_acquire_cookie(NFS_SB(inode->i_sb)->fscache, &nfs_fscache_inode_object_def, @@ -266,11 +271,7 @@ void nfs_fscache_clear_inode(struct inode *inode) dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie); - memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; + nfs_fscache_update_auxdata(&auxdata, nfsi); fscache_relinquish_cookie(cookie, &auxdata, false); nfsi->fscache = NULL; } @@ -310,11 +311,7 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp) if (!fscache_cookie_valid(cookie)) return; - memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime_sec = nfsi->vfs_inode.i_mtime.tv_sec; - auxdata.mtime_nsec = nfsi->vfs_inode.i_mtime.tv_nsec; - auxdata.ctime_sec = nfsi->vfs_inode.i_ctime.tv_sec; - auxdata.ctime_nsec = nfsi->vfs_inode.i_ctime.tv_nsec; + nfs_fscache_update_auxdata(&auxdata, nfsi); if (inode_is_open_for_write(inode)) { dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi); diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 35c8cb2d7637..dda5c3e65d8d 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -30,6 +30,7 @@ #define encode_dirpath_sz (1 + XDR_QUADLEN(MNTPATHLEN)) #define MNT_status_sz (1) #define MNT_fhandle_sz XDR_QUADLEN(NFS2_FHSIZE) +#define MNT_fhandlev3_sz XDR_QUADLEN(NFS3_FHSIZE) #define MNT_authflav3_sz (1 + NFS_MAX_SECFLAVORS) /* @@ -37,7 +38,7 @@ */ #define MNT_enc_dirpath_sz encode_dirpath_sz #define MNT_dec_mountres_sz (MNT_status_sz + MNT_fhandle_sz) -#define MNT_dec_mountres3_sz (MNT_status_sz + MNT_fhandle_sz + \ +#define MNT_dec_mountres3_sz (MNT_status_sz + MNT_fhandlev3_sz + \ MNT_authflav3_sz) /* diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a0c1e653a935..9056f3dd380e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -6347,7 +6347,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, .rpc_client = server->client, .rpc_message = &msg, .callback_ops = &nfs4_delegreturn_ops, - .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | RPC_TASK_TIMEOUT, + .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT, }; int status = 0; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index ac93715c05a4..a8dc25ce48bb 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -734,9 +734,9 @@ nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner) state = new; state->owner = owner; atomic_inc(&owner->so_count); - list_add_rcu(&state->inode_states, &nfsi->open_states); ihold(inode); state->inode = inode; + list_add_rcu(&state->inode_states, &nfsi->open_states); spin_unlock(&inode->i_lock); /* Note: The reclaim code dictates that we add stateless * and read-only stateids to the end of the list */ diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index f61f96603df7..6ca421cbe19c 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -752,7 +752,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr, .callback_ops = call_ops, .callback_data = hdr, .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | flags, + .flags = RPC_TASK_ASYNC | flags, }; hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how); @@ -950,7 +950,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc) hdr->cred, NFS_PROTO(hdr->inode), desc->pg_rpc_callops, - desc->pg_ioflags, 0); + desc->pg_ioflags, + RPC_TASK_CRED_NOREF); return ret; } diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index e7ddbce48321..679767ac258d 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -536,7 +536,8 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages, nfs_init_commit(data, NULL, NULL, cinfo); nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(data->inode), - data->mds_ops, how, 0); + data->mds_ops, how, + RPC_TASK_CRED_NOREF); } else { nfs_init_commit(data, NULL, data->lseg, cinfo); initiate_commit(data, how); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index bdb6d0c2e755..7a70287f21a2 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1189,7 +1189,6 @@ static void nfs_get_cache_cookie(struct super_block *sb, uniq = ctx->fscache_uniq; ulen = strlen(ctx->fscache_uniq); } - return; } nfs_fscache_get_super_cookie(sb, uniq, ulen); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index df4b87c30ac9..1e767f779c49 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1695,7 +1695,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data, .callback_ops = call_ops, .callback_data = data, .workqueue = nfsiod_workqueue, - .flags = RPC_TASK_ASYNC | RPC_TASK_CRED_NOREF | flags, + .flags = RPC_TASK_ASYNC | flags, .priority = priority, }; /* Set up the initial task struct. */ @@ -1813,7 +1813,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how, nfs_init_commit(data, head, NULL, cinfo); atomic_inc(&cinfo->mds->rpcs_out); return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode), - data->mds_ops, how, 0); + data->mds_ops, how, RPC_TASK_CRED_NOREF); } /* diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 5cf91322de0f..966ca75418c8 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -38,6 +38,7 @@ #include "nfsd.h" #include "state.h" #include "netns.h" +#include "trace.h" #include "xdr4cb.h" #include "xdr4.h" @@ -904,16 +905,20 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c if (clp->cl_minorversion == 0) { if (!clp->cl_cred.cr_principal && - (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5)) + (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5)) { + trace_nfsd_cb_setup_err(clp, -EINVAL); return -EINVAL; + } args.client_name = clp->cl_cred.cr_principal; args.prognumber = conn->cb_prog; args.protocol = XPRT_TRANSPORT_TCP; args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { - if (!conn->cb_xprt) + if (!conn->cb_xprt) { + trace_nfsd_cb_setup_err(clp, -EINVAL); return -EINVAL; + } clp->cl_cb_conn.cb_xprt = conn->cb_xprt; clp->cl_cb_session = ses; args.bc_xprt = conn->cb_xprt; @@ -925,32 +930,27 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c /* Create RPC client */ client = rpc_create(&args); if (IS_ERR(client)) { - dprintk("NFSD: couldn't create callback client: %ld\n", - PTR_ERR(client)); + trace_nfsd_cb_setup_err(clp, PTR_ERR(client)); return PTR_ERR(client); } cred = get_backchannel_cred(clp, client, ses); if (!cred) { + trace_nfsd_cb_setup_err(clp, -ENOMEM); rpc_shutdown_client(client); return -ENOMEM; } clp->cl_cb_client = client; clp->cl_cb_cred = cred; + trace_nfsd_cb_setup(clp); return 0; } -static void warn_no_callback_path(struct nfs4_client *clp, int reason) -{ - dprintk("NFSD: warning: no callback path to client %.*s: error %d\n", - (int)clp->cl_name.len, clp->cl_name.data, reason); -} - static void nfsd4_mark_cb_down(struct nfs4_client *clp, int reason) { if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) return; clp->cl_cb_state = NFSD4_CB_DOWN; - warn_no_callback_path(clp, reason); + trace_nfsd_cb_state(clp); } static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason) @@ -958,17 +958,20 @@ static void nfsd4_mark_cb_fault(struct nfs4_client *clp, int reason) if (test_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags)) return; clp->cl_cb_state = NFSD4_CB_FAULT; - warn_no_callback_path(clp, reason); + trace_nfsd_cb_state(clp); } static void nfsd4_cb_probe_done(struct rpc_task *task, void *calldata) { struct nfs4_client *clp = container_of(calldata, struct nfs4_client, cl_cb_null); + trace_nfsd_cb_done(clp, task->tk_status); if (task->tk_status) nfsd4_mark_cb_down(clp, task->tk_status); - else + else { clp->cl_cb_state = NFSD4_CB_UP; + trace_nfsd_cb_state(clp); + } } static void nfsd4_cb_probe_release(void *calldata) @@ -993,6 +996,7 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = { void nfsd4_probe_callback(struct nfs4_client *clp) { clp->cl_cb_state = NFSD4_CB_UNKNOWN; + trace_nfsd_cb_state(clp); set_bit(NFSD4_CLIENT_CB_UPDATE, &clp->cl_flags); nfsd4_run_cb(&clp->cl_cb_null); } @@ -1009,6 +1013,7 @@ void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *conn) spin_lock(&clp->cl_lock); memcpy(&clp->cl_cb_conn, conn, sizeof(struct nfs4_cb_conn)); spin_unlock(&clp->cl_lock); + trace_nfsd_cb_state(clp); } /* @@ -1165,8 +1170,7 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata) struct nfsd4_callback *cb = calldata; struct nfs4_client *clp = cb->cb_clp; - dprintk("%s: minorversion=%d\n", __func__, - clp->cl_minorversion); + trace_nfsd_cb_done(clp, task->tk_status); if (!nfsd4_cb_sequence_done(task, cb)) return; @@ -1271,6 +1275,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb) * kill the old client: */ if (clp->cl_cb_client) { + trace_nfsd_cb_shutdown(clp); rpc_shutdown_client(clp->cl_cb_client); clp->cl_cb_client = NULL; put_cred(clp->cl_cb_cred); @@ -1314,6 +1319,8 @@ nfsd4_run_cb_work(struct work_struct *work) struct rpc_clnt *clnt; int flags; + trace_nfsd_cb_work(clp, cb->cb_msg.rpc_proc->p_name); + if (cb->cb_need_restart) { cb->cb_need_restart = false; } else { diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index a6d73aa51ce4..a09c35f0f6f0 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1155,7 +1155,7 @@ extern void nfs_sb_deactive(struct super_block *sb); #define NFSD42_INTERSSC_MOUNTOPS "vers=4.2,addr=%s,sec=sys" -/** +/* * Support one copy source server for now. */ static __be32 @@ -1245,10 +1245,9 @@ nfsd4_interssc_disconnect(struct vfsmount *ss_mnt) mntput(ss_mnt); } -/** - * nfsd4_setup_inter_ssc - * +/* * Verify COPY destination stateid. + * * Connect to the source server with NFSv4.1. * Create the source struct file for nfsd_copy_range. * Called with COPY cstate: diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 31388046c6fe..bb3d2c32664a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -51,6 +51,7 @@ #include "netns.h" #include "pnfs.h" #include "filecache.h" +#include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_PROC @@ -167,9 +168,6 @@ renew_client_locked(struct nfs4_client *clp) return; } - dprintk("renewing client (clientid %08x/%08x)\n", - clp->cl_clientid.cl_boot, - clp->cl_clientid.cl_id); list_move_tail(&clp->cl_lru, &nn->client_lru); clp->cl_time = ktime_get_boottime_seconds(); } @@ -1922,8 +1920,7 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) */ if (clid->cl_boot == (u32)nn->boot_time) return 0; - dprintk("NFSD stale clientid (%08x/%08x) boot_time %08llx\n", - clid->cl_boot, clid->cl_id, nn->boot_time); + trace_nfsd_clid_stale(clid); return 1; } @@ -2872,14 +2869,12 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_r conn->cb_prog = se->se_callback_prog; conn->cb_ident = se->se_callback_ident; memcpy(&conn->cb_saddr, &rqstp->rq_daddr, rqstp->rq_daddrlen); + trace_nfsd_cb_args(clp, conn); return; out_err: conn->cb_addr.ss_family = AF_UNSPEC; conn->cb_addrlen = 0; - dprintk("NFSD: this client (clientid %08x/%08x) " - "will not receive delegations\n", - clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); - + trace_nfsd_cb_nodelegs(clp); return; } @@ -3936,23 +3931,18 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (clp_used_exchangeid(conf)) goto out; if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) { - char addr_str[INET6_ADDRSTRLEN]; - rpc_ntop((struct sockaddr *) &conf->cl_addr, addr_str, - sizeof(addr_str)); - dprintk("NFSD: setclientid: string in use by client " - "at %s\n", addr_str); + trace_nfsd_clid_inuse_err(conf); goto out; } } unconf = find_unconfirmed_client_by_name(&clname, nn); if (unconf) unhash_client_locked(unconf); + /* We need to handle only case 1: probable callback update */ if (conf && same_verf(&conf->cl_verifier, &clverifier)) { - /* case 1: probable callback update */ copy_clid(new, conf); gen_confirm(new, nn); - } else /* case 4 (new client) or cases 2, 3 (client reboot): */ - ; + } new->cl_minorversion = 0; gen_callback(new, setclid, rqstp); add_to_unconfirmed(new); @@ -4133,7 +4123,6 @@ out_free_openowner_slab: out_free_client_slab: kmem_cache_destroy(client_slab); out: - dprintk("nfsd4: out of memory while initializing nfsv4\n"); return -ENOMEM; } @@ -4565,6 +4554,8 @@ nfsd_break_deleg_cb(struct file_lock *fl) struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner; struct nfs4_file *fp = dp->dl_stid.sc_file; + trace_nfsd_deleg_break(&dp->dl_stid.sc_stateid); + /* * We don't want the locks code to timeout the lease for us; * we'll remove it ourself if a delegation isn't returned @@ -5089,8 +5080,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid)); - dprintk("NFSD: delegation stateid=" STATEID_FMT "\n", - STATEID_VAL(&dp->dl_stid.sc_stateid)); + trace_nfsd_deleg_open(&dp->dl_stid.sc_stateid); open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; nfs4_put_stid(&dp->dl_stid); return; @@ -5207,9 +5197,7 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf nfs4_open_delegation(current_fh, open, stp); nodeleg: status = nfs_ok; - - dprintk("%s: stateid=" STATEID_FMT "\n", __func__, - STATEID_VAL(&stp->st_stid.sc_stateid)); + trace_nfsd_deleg_none(&stp->st_stid.sc_stateid); out: /* 4.1 client trying to upgrade/downgrade delegation? */ if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp && @@ -5263,8 +5251,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - dprintk("process_renew(%08x/%08x): starting\n", - clid->cl_boot, clid->cl_id); + trace_nfsd_clid_renew(clid); status = lookup_clientid(clid, cstate, nn, false); if (status) goto out; @@ -5285,6 +5272,7 @@ nfsd4_end_grace(struct nfsd_net *nn) if (nn->grace_ended) return; + trace_nfsd_grace_complete(nn); nn->grace_ended = true; /* * If the server goes down again right now, an NFSv4 @@ -5350,13 +5338,10 @@ nfs4_laundromat(struct nfsd_net *nn) copy_stateid_t *cps_t; int i; - dprintk("NFSD: laundromat service - starting\n"); - if (clients_still_reclaiming(nn)) { new_timeo = 0; goto out; } - dprintk("NFSD: end of grace period\n"); nfsd4_end_grace(nn); INIT_LIST_HEAD(&reaplist); @@ -5378,8 +5363,7 @@ nfs4_laundromat(struct nfsd_net *nn) break; } if (mark_client_expired_locked(clp)) { - dprintk("NFSD: client in use (clientid %08x)\n", - clp->cl_clientid.cl_id); + trace_nfsd_clid_expired(&clp->cl_clientid); continue; } list_add(&clp->cl_lru, &reaplist); @@ -5387,8 +5371,7 @@ nfs4_laundromat(struct nfsd_net *nn) spin_unlock(&nn->client_lock); list_for_each_safe(pos, next, &reaplist) { clp = list_entry(pos, struct nfs4_client, cl_lru); - dprintk("NFSD: purging unused client (clientid %08x)\n", - clp->cl_clientid.cl_id); + trace_nfsd_clid_purged(&clp->cl_clientid); list_del_init(&clp->cl_lru); expire_client(clp); } @@ -5478,7 +5461,6 @@ laundromat_main(struct work_struct *laundry) laundromat_work); t = nfs4_laundromat(nn); - dprintk("NFSD: laundromat_main - sleeping for %lld seconds\n", t); queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } @@ -6019,8 +6001,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, struct nfs4_stid *s; struct nfs4_ol_stateid *stp = NULL; - dprintk("NFSD: %s: seqid=%d stateid = " STATEID_FMT "\n", __func__, - seqid, STATEID_VAL(stateid)); + trace_nfsd_preprocess(seqid, stateid); *stpp = NULL; status = nfsd4_lookup_stateid(cstate, stateid, typemask, &s, nn); @@ -6089,9 +6070,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, oo->oo_flags |= NFS4_OO_CONFIRMED; nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid); mutex_unlock(&stp->st_mutex); - dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", - __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid)); - + trace_nfsd_open_confirm(oc->oc_seqid, &stp->st_stid.sc_stateid); nfsd4_client_record_create(oo->oo_owner.so_client); status = nfs_ok; put_stateid: @@ -7143,7 +7122,7 @@ nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, unsigned int strhashval; struct nfs4_client_reclaim *crp; - dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", name.len, name.data); + trace_nfsd_clid_reclaim(nn, name.len, name.data); crp = alloc_reclaim(); if (crp) { strhashval = clientstr_hashval(name); @@ -7193,7 +7172,7 @@ nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn) unsigned int strhashval; struct nfs4_client_reclaim *crp = NULL; - dprintk("NFSD: nfs4_find_reclaim_client for name %.*s\n", name.len, name.data); + trace_nfsd_clid_find(nn, name.len, name.data); strhashval = clientstr_hashval(name); list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) { @@ -7757,6 +7736,9 @@ nfsd_recall_delegations(struct list_head *reaplist) list_for_each_entry_safe(dp, next, reaplist, dl_recall_lru) { list_del_init(&dp->dl_recall_lru); clp = dp->dl_stid.sc_client; + + trace_nfsd_deleg_recall(&dp->dl_stid.sc_stateid); + /* * We skipped all entries that had a zero dl_time before, * so we can now reset the dl_time back to 0. If a delegation @@ -7939,6 +7921,7 @@ nfs4_state_start_net(struct net *net) goto skip_grace; printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", nn->nfsd4_grace, net->ns.inum); + trace_nfsd_grace_start(nn); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ); return 0; diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 96352ab7bd81..945d2f5e760e 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -20,8 +20,7 @@ #include "nfsd.h" #include "cache.h" - -#define NFSDDBG_FACILITY NFSDDBG_REPCACHE +#include "trace.h" /* * We use this value to determine the number of hash buckets from the max @@ -323,8 +322,10 @@ nfsd_cache_key_cmp(const struct svc_cacherep *key, const struct svc_cacherep *rp, struct nfsd_net *nn) { if (key->c_key.k_xid == rp->c_key.k_xid && - key->c_key.k_csum != rp->c_key.k_csum) + key->c_key.k_csum != rp->c_key.k_csum) { ++nn->payload_misses; + trace_nfsd_drc_mismatch(nn, key, rp); + } return memcmp(&key->c_key, &rp->c_key, sizeof(key->c_key)); } @@ -377,15 +378,22 @@ out: return ret; } -/* +/** + * nfsd_cache_lookup - Find an entry in the duplicate reply cache + * @rqstp: Incoming Call to find + * * Try to find an entry matching the current call in the cache. When none * is found, we try to grab the oldest expired entry off the LRU list. If * a suitable one isn't there, then drop the cache_lock and allocate a * new one, then search again in case one got inserted while this thread * didn't hold the lock. + * + * Return values: + * %RC_DOIT: Process the request normally + * %RC_REPLY: Reply from cache + * %RC_DROPIT: Do not process the request further */ -int -nfsd_cache_lookup(struct svc_rqst *rqstp) +int nfsd_cache_lookup(struct svc_rqst *rqstp) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct svc_cacherep *rp, *found; @@ -399,7 +407,7 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) rqstp->rq_cacherep = NULL; if (type == RC_NOCACHE) { nfsdstats.rcnocache++; - return rtn; + goto out; } csum = nfsd_cache_csum(rqstp); @@ -409,10 +417,8 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) * preallocate an entry. */ rp = nfsd_reply_cache_alloc(rqstp, csum, nn); - if (!rp) { - dprintk("nfsd: unable to allocate DRC entry!\n"); - return rtn; - } + if (!rp) + goto out; spin_lock(&b->cache_lock); found = nfsd_cache_insert(b, rp, nn); @@ -431,8 +437,10 @@ nfsd_cache_lookup(struct svc_rqst *rqstp) /* go ahead and prune the cache */ prune_bucket(b, nn); - out: + +out_unlock: spin_unlock(&b->cache_lock); +out: return rtn; found_entry: @@ -442,13 +450,13 @@ found_entry: /* Request being processed */ if (rp->c_state == RC_INPROG) - goto out; + goto out_trace; /* From the hall of fame of impractical attacks: * Is this a user who tries to snoop on the cache? */ rtn = RC_DOIT; if (!test_bit(RQ_SECURE, &rqstp->rq_flags) && rp->c_secure) - goto out; + goto out_trace; /* Compose RPC reply header */ switch (rp->c_type) { @@ -460,7 +468,7 @@ found_entry: break; case RC_REPLBUFF: if (!nfsd_cache_append(rqstp, &rp->c_replvec)) - goto out; /* should not happen */ + goto out_unlock; /* should not happen */ rtn = RC_REPLY; break; default: @@ -468,13 +476,19 @@ found_entry: nfsd_reply_cache_free_locked(b, rp, nn); } - goto out; +out_trace: + trace_nfsd_drc_found(nn, rqstp, rtn); + goto out_unlock; } -/* - * Update a cache entry. This is called from nfsd_dispatch when - * the procedure has been executed and the complete reply is in - * rqstp->rq_res. +/** + * nfsd_cache_update - Update an entry in the duplicate reply cache. + * @rqstp: svc_rqst with a finished Reply + * @cachetype: which cache to update + * @statp: Reply's status code + * + * This is called from nfsd_dispatch when the procedure has been + * executed and the complete reply is in rqstp->rq_res. * * We're copying around data here rather than swapping buffers because * the toplevel loop requires max-sized buffers, which would be a waste @@ -487,8 +501,7 @@ found_entry: * nfsd failed to encode a reply that otherwise would have been cached. * In this case, nfsd_cache_update is called with statp == NULL. */ -void -nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) +void nfsd_cache_update(struct svc_rqst *rqstp, int cachetype, __be32 *statp) { struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); struct svc_cacherep *rp = rqstp->rq_cacherep; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 3bb2db947d29..b48eac3bb72b 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -238,7 +238,7 @@ static inline struct net *netns(struct file *file) return file_inode(file)->i_sb->s_fs_info; } -/** +/* * write_unlock_ip - Release all locks used by a client * * Experimental. @@ -277,7 +277,7 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size) return nlmsvc_unlock_all_by_ip(sap); } -/** +/* * write_unlock_fs - Release all locks on a local file system * * Experimental. @@ -327,7 +327,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) return error; } -/** +/* * write_filehandle - Get a variable-length NFS file handle by path * * On input, the buffer contains a '\n'-terminated C string comprised of @@ -402,7 +402,7 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size) return mesg - buf; } -/** +/* * write_threads - Start NFSD, or report the current number of running threads * * Input: @@ -452,7 +452,7 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size) return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", rv); } -/** +/* * write_pool_threads - Set or report the current number of threads per pool * * Input: @@ -661,7 +661,7 @@ out: return tlen + len; } -/** +/* * write_versions - Set or report the available NFS protocol versions * * Input: @@ -811,7 +811,7 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size, return -EINVAL; } -/** +/* * write_ports - Pass a socket file descriptor or transport name to listen on * * Input: @@ -867,7 +867,7 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size) int nfsd_max_blksize; -/** +/* * write_maxblksize - Set or report the current NFS blksize * * Input: @@ -917,7 +917,7 @@ static ssize_t write_maxblksize(struct file *file, char *buf, size_t size) nfsd_max_blksize); } -/** +/* * write_maxconn - Set or report the current max number of connections * * Input: @@ -998,7 +998,7 @@ static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size, return rv; } -/** +/* * write_leasetime - Set or report the current NFSv4 lease time * * Input: @@ -1025,7 +1025,7 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size) return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn); } -/** +/* * write_gracetime - Set or report current NFSv4 grace period time * * As above, but sets the time of the NFSv4 grace period. @@ -1069,7 +1069,7 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size, nfs4_recoverydir()); } -/** +/* * write_recoverydir - Set or report the pathname of the recovery directory * * Input: @@ -1101,7 +1101,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size) return rv; } -/** +/* * write_v4_end_grace - release grace period for nfsd's v4.x lock manager * * Input: diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index 68d3f30ee760..3b408532a5dc 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -64,13 +64,6 @@ typedef struct { refcount_t sc_count; } copy_stateid_t; -#define STATEID_FMT "(%08x/%08x/%08x/%08x)" -#define STATEID_VAL(s) \ - (s)->si_opaque.so_clid.cl_boot, \ - (s)->si_opaque.so_clid.cl_id, \ - (s)->si_opaque.so_id, \ - (s)->si_generation - struct nfsd4_callback { struct nfs4_client *cb_clp; struct rpc_message cb_msg; diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index 78c574251c60..1861db1bdc67 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -277,6 +277,7 @@ DECLARE_EVENT_CLASS(nfsd_stateid_class, DEFINE_EVENT(nfsd_stateid_class, nfsd_##name, \ TP_PROTO(stateid_t *stp), \ TP_ARGS(stp)) + DEFINE_STATEID_EVENT(layoutstate_alloc); DEFINE_STATEID_EVENT(layoutstate_unhash); DEFINE_STATEID_EVENT(layoutstate_free); @@ -288,6 +289,138 @@ DEFINE_STATEID_EVENT(layout_recall_done); DEFINE_STATEID_EVENT(layout_recall_fail); DEFINE_STATEID_EVENT(layout_recall_release); +DEFINE_STATEID_EVENT(deleg_open); +DEFINE_STATEID_EVENT(deleg_none); +DEFINE_STATEID_EVENT(deleg_break); +DEFINE_STATEID_EVENT(deleg_recall); + +DECLARE_EVENT_CLASS(nfsd_stateseqid_class, + TP_PROTO(u32 seqid, const stateid_t *stp), + TP_ARGS(seqid, stp), + TP_STRUCT__entry( + __field(u32, seqid) + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, si_id) + __field(u32, si_generation) + ), + TP_fast_assign( + __entry->seqid = seqid; + __entry->cl_boot = stp->si_opaque.so_clid.cl_boot; + __entry->cl_id = stp->si_opaque.so_clid.cl_id; + __entry->si_id = stp->si_opaque.so_id; + __entry->si_generation = stp->si_generation; + ), + TP_printk("seqid=%u client %08x:%08x stateid %08x:%08x", + __entry->seqid, __entry->cl_boot, __entry->cl_id, + __entry->si_id, __entry->si_generation) +) + +#define DEFINE_STATESEQID_EVENT(name) \ +DEFINE_EVENT(nfsd_stateseqid_class, nfsd_##name, \ + TP_PROTO(u32 seqid, const stateid_t *stp), \ + TP_ARGS(seqid, stp)) + +DEFINE_STATESEQID_EVENT(preprocess); +DEFINE_STATESEQID_EVENT(open_confirm); + +DECLARE_EVENT_CLASS(nfsd_clientid_class, + TP_PROTO(const clientid_t *clid), + TP_ARGS(clid), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + ), + TP_fast_assign( + __entry->cl_boot = clid->cl_boot; + __entry->cl_id = clid->cl_id; + ), + TP_printk("client %08x:%08x", __entry->cl_boot, __entry->cl_id) +) + +#define DEFINE_CLIENTID_EVENT(name) \ +DEFINE_EVENT(nfsd_clientid_class, nfsd_clid_##name, \ + TP_PROTO(const clientid_t *clid), \ + TP_ARGS(clid)) + +DEFINE_CLIENTID_EVENT(expired); +DEFINE_CLIENTID_EVENT(purged); +DEFINE_CLIENTID_EVENT(renew); +DEFINE_CLIENTID_EVENT(stale); + +DECLARE_EVENT_CLASS(nfsd_net_class, + TP_PROTO(const struct nfsd_net *nn), + TP_ARGS(nn), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + ), + TP_printk("boot_time=%16llx", __entry->boot_time) +) + +#define DEFINE_NET_EVENT(name) \ +DEFINE_EVENT(nfsd_net_class, nfsd_##name, \ + TP_PROTO(const struct nfsd_net *nn), \ + TP_ARGS(nn)) + +DEFINE_NET_EVENT(grace_start); +DEFINE_NET_EVENT(grace_complete); + +DECLARE_EVENT_CLASS(nfsd_clid_class, + TP_PROTO(const struct nfsd_net *nn, + unsigned int namelen, + const unsigned char *namedata), + TP_ARGS(nn, namelen, namedata), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + __field(unsigned int, namelen) + __dynamic_array(unsigned char, name, namelen) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + __entry->namelen = namelen; + memcpy(__get_dynamic_array(name), namedata, namelen); + ), + TP_printk("boot_time=%16llx nfs4_clientid=%.*s", + __entry->boot_time, __entry->namelen, __get_str(name)) +) + +#define DEFINE_CLID_EVENT(name) \ +DEFINE_EVENT(nfsd_clid_class, nfsd_clid_##name, \ + TP_PROTO(const struct nfsd_net *nn, \ + unsigned int namelen, \ + const unsigned char *namedata), \ + TP_ARGS(nn, namelen, namedata)) + +DEFINE_CLID_EVENT(find); +DEFINE_CLID_EVENT(reclaim); + +TRACE_EVENT(nfsd_clid_inuse_err, + TP_PROTO(const struct nfs4_client *clp), + TP_ARGS(clp), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + __field(unsigned int, namelen) + __dynamic_array(unsigned char, name, clp->cl_name.len) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + memcpy(__entry->addr, &clp->cl_addr, + sizeof(struct sockaddr_in6)); + __entry->namelen = clp->cl_name.len; + memcpy(__get_dynamic_array(name), clp->cl_name.data, + clp->cl_name.len); + ), + TP_printk("nfs4_clientid %.*s already in use by %pISpc, client %08x:%08x", + __entry->namelen, __get_str(name), __entry->addr, + __entry->cl_boot, __entry->cl_id) +) + TRACE_DEFINE_ENUM(NFSD_FILE_HASHED); TRACE_DEFINE_ENUM(NFSD_FILE_PENDING); TRACE_DEFINE_ENUM(NFSD_FILE_BREAK_READ); @@ -432,6 +565,218 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event, __entry->nlink, __entry->mode, __entry->mask) ); +#include "cache.h" + +TRACE_DEFINE_ENUM(RC_DROPIT); +TRACE_DEFINE_ENUM(RC_REPLY); +TRACE_DEFINE_ENUM(RC_DOIT); + +#define show_drc_retval(x) \ + __print_symbolic(x, \ + { RC_DROPIT, "DROPIT" }, \ + { RC_REPLY, "REPLY" }, \ + { RC_DOIT, "DOIT" }) + +TRACE_EVENT(nfsd_drc_found, + TP_PROTO( + const struct nfsd_net *nn, + const struct svc_rqst *rqstp, + int result + ), + TP_ARGS(nn, rqstp, result), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + __field(unsigned long, result) + __field(u32, xid) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + __entry->result = result; + __entry->xid = be32_to_cpu(rqstp->rq_xid); + ), + TP_printk("boot_time=%16llx xid=0x%08x result=%s", + __entry->boot_time, __entry->xid, + show_drc_retval(__entry->result)) + +); + +TRACE_EVENT(nfsd_drc_mismatch, + TP_PROTO( + const struct nfsd_net *nn, + const struct svc_cacherep *key, + const struct svc_cacherep *rp + ), + TP_ARGS(nn, key, rp), + TP_STRUCT__entry( + __field(unsigned long long, boot_time) + __field(u32, xid) + __field(u32, cached) + __field(u32, ingress) + ), + TP_fast_assign( + __entry->boot_time = nn->boot_time; + __entry->xid = be32_to_cpu(key->c_key.k_xid); + __entry->cached = (__force u32)key->c_key.k_csum; + __entry->ingress = (__force u32)rp->c_key.k_csum; + ), + TP_printk("boot_time=%16llx xid=0x%08x cached-csum=0x%08x ingress-csum=0x%08x", + __entry->boot_time, __entry->xid, __entry->cached, + __entry->ingress) +); + +TRACE_EVENT(nfsd_cb_args, + TP_PROTO( + const struct nfs4_client *clp, + const struct nfs4_cb_conn *conn + ), + TP_ARGS(clp, conn), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(u32, prog) + __field(u32, ident) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __entry->prog = conn->cb_prog; + __entry->ident = conn->cb_ident; + memcpy(__entry->addr, &conn->cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("client %08x:%08x callback addr=%pISpc prog=%u ident=%u", + __entry->cl_boot, __entry->cl_id, + __entry->addr, __entry->prog, __entry->ident) +); + +TRACE_EVENT(nfsd_cb_nodelegs, + TP_PROTO(const struct nfs4_client *clp), + TP_ARGS(clp), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + ), + TP_printk("client %08x:%08x", __entry->cl_boot, __entry->cl_id) +) + +TRACE_DEFINE_ENUM(NFSD4_CB_UP); +TRACE_DEFINE_ENUM(NFSD4_CB_UNKNOWN); +TRACE_DEFINE_ENUM(NFSD4_CB_DOWN); +TRACE_DEFINE_ENUM(NFSD4_CB_FAULT); + +#define show_cb_state(val) \ + __print_symbolic(val, \ + { NFSD4_CB_UP, "UP" }, \ + { NFSD4_CB_UNKNOWN, "UNKNOWN" }, \ + { NFSD4_CB_DOWN, "DOWN" }, \ + { NFSD4_CB_FAULT, "FAULT"}) + +DECLARE_EVENT_CLASS(nfsd_cb_class, + TP_PROTO(const struct nfs4_client *clp), + TP_ARGS(clp), + TP_STRUCT__entry( + __field(unsigned long, state) + __field(u32, cl_boot) + __field(u32, cl_id) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->state = clp->cl_cb_state; + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc client %08x:%08x state=%s", + __entry->addr, __entry->cl_boot, __entry->cl_id, + show_cb_state(__entry->state)) +); + +#define DEFINE_NFSD_CB_EVENT(name) \ +DEFINE_EVENT(nfsd_cb_class, nfsd_cb_##name, \ + TP_PROTO(const struct nfs4_client *clp), \ + TP_ARGS(clp)) + +DEFINE_NFSD_CB_EVENT(setup); +DEFINE_NFSD_CB_EVENT(state); +DEFINE_NFSD_CB_EVENT(shutdown); + +TRACE_EVENT(nfsd_cb_setup_err, + TP_PROTO( + const struct nfs4_client *clp, + long error + ), + TP_ARGS(clp, error), + TP_STRUCT__entry( + __field(long, error) + __field(u32, cl_boot) + __field(u32, cl_id) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->error = error; + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc client %08x:%08x error=%ld", + __entry->addr, __entry->cl_boot, __entry->cl_id, __entry->error) +); + +TRACE_EVENT(nfsd_cb_work, + TP_PROTO( + const struct nfs4_client *clp, + const char *procedure + ), + TP_ARGS(clp, procedure), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __string(procedure, procedure) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __assign_str(procedure, procedure) + memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc client %08x:%08x procedure=%s", + __entry->addr, __entry->cl_boot, __entry->cl_id, + __get_str(procedure)) +); + +TRACE_EVENT(nfsd_cb_done, + TP_PROTO( + const struct nfs4_client *clp, + int status + ), + TP_ARGS(clp, status), + TP_STRUCT__entry( + __field(u32, cl_boot) + __field(u32, cl_id) + __field(int, status) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + TP_fast_assign( + __entry->cl_boot = clp->cl_clientid.cl_boot; + __entry->cl_id = clp->cl_clientid.cl_id; + __entry->status = status; + memcpy(__entry->addr, &clp->cl_cb_conn.cb_addr, + sizeof(struct sockaddr_in6)); + ), + TP_printk("addr=%pISpc client %08x:%08x status=%d", + __entry->addr, __entry->cl_boot, __entry->cl_id, + __entry->status) +); + #endif /* _NFSD_TRACE_H */ #undef TRACE_INCLUDE_PATH diff --git a/fs/splice.c b/fs/splice.c index 4735defc46ee..fd0a1e7e5959 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1118,6 +1118,10 @@ long do_splice(struct file *in, loff_t __user *off_in, loff_t offset; long ret; + if (unlikely(!(in->f_mode & FMODE_READ) || + !(out->f_mode & FMODE_WRITE))) + return -EBADF; + ipipe = get_pipe_info(in); opipe = get_pipe_info(out); @@ -1125,12 +1129,6 @@ long do_splice(struct file *in, loff_t __user *off_in, if (off_in || off_out) return -ESPIPE; - if (!(in->f_mode & FMODE_READ)) - return -EBADF; - - if (!(out->f_mode & FMODE_WRITE)) - return -EBADF; - /* Splicing to self would be fun, but... */ if (ipipe == opipe) return -EINVAL; @@ -1153,9 +1151,6 @@ long do_splice(struct file *in, loff_t __user *off_in, offset = out->f_pos; } - if (unlikely(!(out->f_mode & FMODE_WRITE))) - return -EBADF; - if (unlikely(out->f_flags & O_APPEND)) return -EINVAL; @@ -1440,15 +1435,11 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in, error = -EBADF; in = fdget(fd_in); if (in.file) { - if (in.file->f_mode & FMODE_READ) { - out = fdget(fd_out); - if (out.file) { - if (out.file->f_mode & FMODE_WRITE) - error = do_splice(in.file, off_in, - out.file, off_out, - len, flags); - fdput(out); - } + out = fdget(fd_out); + if (out.file) { + error = do_splice(in.file, off_in, out.file, off_out, + len, flags); + fdput(out); } fdput(in); } @@ -1770,6 +1761,10 @@ static long do_tee(struct file *in, struct file *out, size_t len, struct pipe_inode_info *opipe = get_pipe_info(out); int ret = -EINVAL; + if (unlikely(!(in->f_mode & FMODE_READ) || + !(out->f_mode & FMODE_WRITE))) + return -EBADF; + /* * Duplicate the contents of ipipe to opipe without actually * copying the data. @@ -1795,7 +1790,7 @@ static long do_tee(struct file *in, struct file *out, size_t len, SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) { - struct fd in; + struct fd in, out; int error; if (unlikely(flags & ~SPLICE_F_ALL)) @@ -1807,14 +1802,10 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags) error = -EBADF; in = fdget(fdin); if (in.file) { - if (in.file->f_mode & FMODE_READ) { - struct fd out = fdget(fdout); - if (out.file) { - if (out.file->f_mode & FMODE_WRITE) - error = do_tee(in.file, out.file, - len, flags); - fdput(out); - } + out = fdget(fdout); + if (out.file) { + error = do_tee(in.file, out.file, len, flags); + fdput(out); } fdput(in); } diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 675e26989376..8fe03b4a0d2b 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -164,7 +164,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc) goto fail_free; } - err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id); + err = super_setup_bdi_name(sb, "vboxsf-%d", sbi->bdi_id); if (err) goto fail_free; diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h index 99134d4f35eb..320f8112a0f8 100644 --- a/include/drm/drm_modes.h +++ b/include/drm/drm_modes.h @@ -48,7 +48,7 @@ struct videomode; * @MODE_HSYNC: hsync out of range * @MODE_VSYNC: vsync out of range * @MODE_H_ILLEGAL: mode has illegal horizontal timings - * @MODE_V_ILLEGAL: mode has illegal horizontal timings + * @MODE_V_ILLEGAL: mode has illegal vertical timings * @MODE_BAD_WIDTH: requires an unsupported linepitch * @MODE_NOMODE: no mode with a matching name * @MODE_NO_INTERLACE: interlaced mode not supported diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h index 26f0ecf401ea..0bbfd647f5c6 100644 --- a/include/linux/amba/bus.h +++ b/include/linux/amba/bus.h @@ -65,6 +65,7 @@ struct amba_device { struct device dev; struct resource res; struct clk *pclk; + struct device_dma_parameters dma_parms; unsigned int periphid; unsigned int cid; struct amba_cs_uci_id uci; diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index ee577a83cfe6..7367150f962a 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -219,6 +219,7 @@ struct backing_dev_info { wait_queue_head_t wb_waitq; struct device *dev; + char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index f88197c1ffc2..c9ad5c3b7b4b 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -505,13 +505,6 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi) (1 << WB_async_congested)); } -extern const char *bdi_unknown_name; - -static inline const char *bdi_dev_name(struct backing_dev_info *bdi) -{ - if (!bdi || !bdi->dev) - return bdi_unknown_name; - return dev_name(bdi->dev); -} +const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 6462c5447872..f4b77018c625 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -245,6 +245,7 @@ #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN (1 << 0) #define BCM54810_SHD_CLK_CTL 0x3 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN (1 << 9) +#define BCM54810_SHD_SCR3_TRDDAPD 0x0100 /* BCM54612E Registers */ #define BCM54612E_EXP_SPARE0 (MII_BCM54XX_EXP_SEL_ETC + 0x34) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 034b0a644efc..448c91bf543b 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -356,4 +356,10 @@ static inline void *offset_to_ptr(const int *off) /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +/* + * This is needed in functions which generate the stack canary, see + * arch/x86/kernel/smpboot.c::start_secondary() for an example. + */ +#define prevent_tail_call_optimization() mb() + #endif /* __LINUX_COMPILER_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 4b784560ffaf..70a0ac7b8f66 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -983,7 +983,7 @@ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ - unsigned char f_handle[0]; + unsigned char f_handle[]; }; static inline struct file *get_file(struct file *f) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index db95244a62d4..ab4bd15cbcdb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -210,6 +210,29 @@ struct ftrace_ops { #endif }; +extern struct ftrace_ops __rcu *ftrace_ops_list; +extern struct ftrace_ops ftrace_list_end; + +/* + * Traverse the ftrace_global_list, invoking all entries. The reason that we + * can use rcu_dereference_raw_check() is that elements removed from this list + * are simply leaked, so there is no need to interact with a grace-period + * mechanism. The rcu_dereference_raw_check() calls are needed to handle + * concurrent insertions into the ftrace_global_list. + * + * Silly Alpha and silly pointer-speculation compiler optimizations! + */ +#define do_for_each_ftrace_op(op, list) \ + op = rcu_dereference_raw_check(list); \ + do + +/* + * Optimized for just a single item in the list (as that is the normal case). + */ +#define while_for_each_ftrace_op(op) \ + while (likely(op = rcu_dereference_raw_check((op)->next)) && \ + unlikely((op) != &ftrace_list_end)) + /* * Type of the current tracing. */ diff --git a/include/linux/host1x.h b/include/linux/host1x.h index 62d216ff1097..c230b4e70d75 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -17,9 +17,12 @@ enum host1x_class { HOST1X_CLASS_GR3D = 0x60, }; +struct host1x; struct host1x_client; struct iommu_group; +u64 host1x_get_dma_mask(struct host1x *host1x); + /** * struct host1x_client_ops - host1x client operations * @init: host1x client initialization code diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 01276e3d01b9..131cc1527d68 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -813,8 +813,11 @@ void kvm_flush_remote_tlbs(struct kvm *kvm); void kvm_reload_remote_mmus(struct kvm *kvm); bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + struct kvm_vcpu *except, unsigned long *vcpu_bitmap, cpumask_var_t tmp); bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req); +bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, + struct kvm_vcpu *except); bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap); diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index 9cd4455528e5..5616b2567aa7 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -55,7 +55,7 @@ LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm) LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm) LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc, struct fs_context *src_sc) -LSM_HOOK(int, 0, fs_context_parse_param, struct fs_context *fc, +LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc, struct fs_parameter *param) LSM_HOOK(int, 0, sb_alloc_security, struct super_block *sb) LSM_HOOK(void, LSM_RET_VOID, sb_free_security, struct super_block *sb) @@ -243,7 +243,7 @@ LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, char *name, char **value) LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size) LSM_HOOK(int, 0, ismaclabel, const char *name) -LSM_HOOK(int, 0, secid_to_secctx, u32 secid, char **secdata, +LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata, u32 *seclen) LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid) LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d275c72c4f8e..977edd3b7bd8 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -783,6 +783,8 @@ static inline void memcg_memory_event(struct mem_cgroup *memcg, atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && diff --git a/include/linux/mhi.h b/include/linux/mhi.h index ad1996001965..3d7c3c26eeb9 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -53,9 +53,9 @@ enum mhi_callback { * @MHI_CHAIN: Linked transfer */ enum mhi_flags { - MHI_EOB, - MHI_EOT, - MHI_CHAIN, + MHI_EOB = BIT(0), + MHI_EOT = BIT(1), + MHI_CHAIN = BIT(2), }; /** @@ -335,14 +335,15 @@ struct mhi_controller_config { * @syserr_worker: System error worker * @state_event: State change event * @status_cb: CB function to notify power states of the device (required) - * @link_status: CB function to query link status of the device (required) * @wake_get: CB function to assert device wake (optional) * @wake_put: CB function to de-assert device wake (optional) * @wake_toggle: CB function to assert and de-assert device wake (optional) * @runtime_get: CB function to controller runtime resume (required) - * @runtimet_put: CB function to decrement pm usage (required) + * @runtime_put: CB function to decrement pm usage (required) * @map_single: CB function to create TRE buffer * @unmap_single: CB function to destroy TRE buffer + * @read_reg: Read a MHI register via the physical link (required) + * @write_reg: Write a MHI register via the physical link (required) * @buffer_len: Bounce buffer length * @bounce_buf: Use of bounce buffer * @fbc_download: MHI host needs to do complete image transfer (optional) @@ -417,7 +418,6 @@ struct mhi_controller { void (*status_cb)(struct mhi_controller *mhi_cntrl, enum mhi_callback cb); - int (*link_status)(struct mhi_controller *mhi_cntrl); void (*wake_get)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_put)(struct mhi_controller *mhi_cntrl, bool override); void (*wake_toggle)(struct mhi_controller *mhi_cntrl); @@ -427,6 +427,10 @@ struct mhi_controller { struct mhi_buf_info *buf); void (*unmap_single)(struct mhi_controller *mhi_cntrl, struct mhi_buf_info *buf); + int (*read_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 *out); + void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr, + u32 val); size_t buffer_len; bool bounce_buf; diff --git a/include/linux/platform_data/cros_ec_sensorhub.h b/include/linux/platform_data/cros_ec_sensorhub.h index c588be843f61..0ecce6aa69d5 100644 --- a/include/linux/platform_data/cros_ec_sensorhub.h +++ b/include/linux/platform_data/cros_ec_sensorhub.h @@ -185,6 +185,7 @@ int cros_ec_sensorhub_register_push_data(struct cros_ec_sensorhub *sensorhub, void cros_ec_sensorhub_unregister_push_data(struct cros_ec_sensorhub *sensorhub, u8 sensor_num); +int cros_ec_sensorhub_ring_allocate(struct cros_ec_sensorhub *sensorhub); int cros_ec_sensorhub_ring_add(struct cros_ec_sensorhub *sensorhub); void cros_ec_sensorhub_ring_remove(void *arg); int cros_ec_sensorhub_ring_fifo_enable(struct cros_ec_sensorhub *sensorhub, diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index bdc35753ef7c..77a2aada106d 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -25,6 +25,7 @@ struct platform_device { bool id_auto; struct device dev; u64 platform_dma_mask; + struct device_dma_parameters dma_parms; u32 num_resources; struct resource *resource; diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 121a7eda4593..c602670bbffb 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -105,10 +105,10 @@ struct ptp_system_timestamp { * parameter func: the desired function to use. * parameter chan: the function channel index to use. * - * @do_work: Request driver to perform auxiliary (periodic) operations - * Driver should return delay of the next auxiliary work scheduling - * time (>=0) or negative value in case further scheduling - * is not required. + * @do_aux_work: Request driver to perform auxiliary (periodic) operations + * Driver should return delay of the next auxiliary work + * scheduling time (>=0) or negative value in case further + * scheduling is not required. * * Drivers should embed their ptp_clock_info within a private * structure, obtaining a reference to it using container_of(). diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 8a709f63c5e5..ad31c9fb7158 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -187,6 +187,7 @@ static inline void sk_msg_xfer(struct sk_msg *dst, struct sk_msg *src, dst->sg.data[which] = src->sg.data[which]; dst->sg.data[which].length = size; dst->sg.size += size; + src->sg.size -= size; src->sg.data[which].length -= size; src->sg.data[which].offset += size; } diff --git a/include/linux/sunrpc/gss_api.h b/include/linux/sunrpc/gss_api.h index 48c1b1674cbf..bc07e51f20d1 100644 --- a/include/linux/sunrpc/gss_api.h +++ b/include/linux/sunrpc/gss_api.h @@ -21,6 +21,7 @@ struct gss_ctx { struct gss_api_mech *mech_type; void *internal_ctx_id; + unsigned int slack, align; }; #define GSS_C_NO_BUFFER ((struct xdr_netobj) 0) @@ -66,6 +67,7 @@ u32 gss_wrap( u32 gss_unwrap( struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *inbuf); u32 gss_delete_sec_context( struct gss_ctx **ctx_id); @@ -126,6 +128,7 @@ struct gss_api_ops { u32 (*gss_unwrap)( struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *buf); void (*gss_delete_sec_context)( void *internal_ctx_id); diff --git a/include/linux/sunrpc/gss_krb5.h b/include/linux/sunrpc/gss_krb5.h index c1d77dd8ed41..e8f8ffe7448b 100644 --- a/include/linux/sunrpc/gss_krb5.h +++ b/include/linux/sunrpc/gss_krb5.h @@ -83,7 +83,7 @@ struct gss_krb5_enctype { u32 (*encrypt_v2) (struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages); /* v2 encryption function */ - u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, + u32 (*decrypt_v2) (struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *headskip, u32 *tailskip); /* v2 decryption function */ }; @@ -255,7 +255,7 @@ gss_wrap_kerberos(struct gss_ctx *ctx_id, int offset, struct xdr_buf *outbuf, struct page **pages); u32 -gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, +gss_unwrap_kerberos(struct gss_ctx *ctx_id, int offset, int len, struct xdr_buf *buf); @@ -312,7 +312,7 @@ gss_krb5_aes_encrypt(struct krb5_ctx *kctx, u32 offset, struct page **pages); u32 -gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, +gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, struct xdr_buf *buf, u32 *plainoffset, u32 *plainlen); diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index abf4a57ce4a7..386628b36bc7 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -254,6 +254,7 @@ struct svc_rqst { struct page * *rq_page_end; /* one past the last page */ struct kvec rq_vec[RPCSVC_MAXPAGES]; /* generally useful.. */ + struct bio_vec rq_bvec[RPCSVC_MAXPAGES]; __be32 rq_xid; /* transmission id */ u32 rq_prog; /* program number */ diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h index cbcfbd0521e3..7ed82625dc0b 100644 --- a/include/linux/sunrpc/svc_rdma.h +++ b/include/linux/sunrpc/svc_rdma.h @@ -48,7 +48,6 @@ #include <linux/sunrpc/rpc_rdma.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> -#define SVCRDMA_DEBUG /* Default and maximum inline threshold sizes */ enum { @@ -160,9 +159,8 @@ struct svc_rdma_send_ctxt { }; /* svc_rdma_backchannel.c */ -extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, - __be32 *rdma_resp, - struct xdr_buf *rcvbuf); +extern void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *rctxt); /* svc_rdma_recvfrom.c */ extern void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma); diff --git a/include/linux/sunrpc/svc_xprt.h b/include/linux/sunrpc/svc_xprt.h index 9e1e046de176..aca35ab5cff2 100644 --- a/include/linux/sunrpc/svc_xprt.h +++ b/include/linux/sunrpc/svc_xprt.h @@ -117,6 +117,12 @@ static inline int register_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u return 0; } +static inline bool svc_xprt_is_dead(const struct svc_xprt *xprt) +{ + return (test_bit(XPT_DEAD, &xprt->xpt_flags) != 0) || + (test_bit(XPT_CLOSE, &xprt->xpt_flags) != 0); +} + int svc_reg_xprt_class(struct svc_xprt_class *); void svc_unreg_xprt_class(struct svc_xprt_class *); void svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *, diff --git a/include/linux/sunrpc/svcsock.h b/include/linux/sunrpc/svcsock.h index 771baadaee9d..b7ac7fe68306 100644 --- a/include/linux/sunrpc/svcsock.h +++ b/include/linux/sunrpc/svcsock.h @@ -28,7 +28,7 @@ struct svc_sock { /* private TCP part */ /* On-the-wire fragment header: */ - __be32 sk_reclen; + __be32 sk_marker; /* As we receive a record, this includes the length received so * far (including the fragment header): */ u32 sk_tcplen; @@ -41,12 +41,12 @@ struct svc_sock { static inline u32 svc_sock_reclen(struct svc_sock *svsk) { - return ntohl(svsk->sk_reclen) & RPC_FRAGMENT_SIZE_MASK; + return be32_to_cpu(svsk->sk_marker) & RPC_FRAGMENT_SIZE_MASK; } static inline u32 svc_sock_final_rec(struct svc_sock *svsk) { - return ntohl(svsk->sk_reclen) & RPC_LAST_STREAM_FRAGMENT; + return be32_to_cpu(svsk->sk_marker) & RPC_LAST_STREAM_FRAGMENT; } /* diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 01bb41908c93..22c207b2425f 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -184,6 +184,7 @@ xdr_adjust_iovec(struct kvec *iov, __be32 *p) extern void xdr_shift_buf(struct xdr_buf *, size_t); extern void xdr_buf_from_iov(struct kvec *, struct xdr_buf *); extern int xdr_buf_subsegment(struct xdr_buf *, struct xdr_buf *, unsigned int, unsigned int); +extern void xdr_buf_trim(struct xdr_buf *, unsigned int); extern int read_bytes_from_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); extern int write_bytes_to_xdr_buf(struct xdr_buf *, unsigned int, void *, unsigned int); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 421c99c12291..4f8159e90ce1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -78,47 +78,6 @@ struct tcp_sack_block { #define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */ #define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/ -#if IS_ENABLED(CONFIG_MPTCP) -struct mptcp_options_received { - u64 sndr_key; - u64 rcvr_key; - u64 data_ack; - u64 data_seq; - u32 subflow_seq; - u16 data_len; - u16 mp_capable : 1, - mp_join : 1, - dss : 1, - add_addr : 1, - rm_addr : 1, - family : 4, - echo : 1, - backup : 1; - u32 token; - u32 nonce; - u64 thmac; - u8 hmac[20]; - u8 join_id; - u8 use_map:1, - dsn64:1, - data_fin:1, - use_ack:1, - ack64:1, - mpc_map:1, - __unused:2; - u8 addr_id; - u8 rm_id; - union { - struct in_addr addr; -#if IS_ENABLED(CONFIG_MPTCP_IPV6) - struct in6_addr addr6; -#endif - }; - u64 ahmac; - u16 port; -}; -#endif - struct tcp_options_received { /* PAWS/RTTM data */ int ts_recent_stamp;/* Time we stored ts_recent (for aging) */ @@ -136,9 +95,6 @@ struct tcp_options_received { u8 num_sacks; /* Number of SACK blocks */ u16 user_mss; /* mss requested by user in ioctl */ u16 mss_clamp; /* Maximal mss, negotiated at connection setup */ -#if IS_ENABLED(CONFIG_MPTCP) - struct mptcp_options_received mptcp; -#endif }; static inline void tcp_clear_options(struct tcp_options_received *rx_opt) @@ -148,13 +104,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) #if IS_ENABLED(CONFIG_SMC) rx_opt->smc_ok = 0; #endif -#if IS_ENABLED(CONFIG_MPTCP) - rx_opt->mptcp.mp_capable = 0; - rx_opt->mptcp.mp_join = 0; - rx_opt->mptcp.add_addr = 0; - rx_opt->mptcp.rm_addr = 0; - rx_opt->mptcp.dss = 0; -#endif } /* This is the max number of SACKS that we'll generate and process. It's safe diff --git a/include/linux/tty.h b/include/linux/tty.h index bd5fe0e907e8..a99e9b8e4e31 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -66,7 +66,7 @@ struct tty_buffer { int read; int flags; /* Data points here */ - unsigned long data[0]; + unsigned long data[]; }; /* Values for .flags field of tty_buffer */ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 0d1fe9297ac6..6f6ade63b04c 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -3,6 +3,8 @@ #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/udp.h> #include <uapi/linux/virtio_net.h> static inline int virtio_net_hdr_set_proto(struct sk_buff *skb, @@ -28,17 +30,25 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, bool little_endian) { unsigned int gso_type = 0; + unsigned int thlen = 0; + unsigned int ip_proto; if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { case VIRTIO_NET_HDR_GSO_TCPV4: gso_type = SKB_GSO_TCPV4; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_TCPV6: gso_type = SKB_GSO_TCPV6; + ip_proto = IPPROTO_TCP; + thlen = sizeof(struct tcphdr); break; case VIRTIO_NET_HDR_GSO_UDP: gso_type = SKB_GSO_UDP; + ip_proto = IPPROTO_UDP; + thlen = sizeof(struct udphdr); break; default: return -EINVAL; @@ -57,16 +67,22 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; + + if (skb_transport_offset(skb) + thlen > skb_headlen(skb)) + return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. * probe and drop if does not match one of the above types. */ if (gso_type && skb->network_header) { + struct flow_keys_basic keys; + if (!skb->protocol) virtio_net_hdr_set_proto(skb, hdr); retry: - skb_probe_transport_header(skb); - if (!skb_transport_header_was_set(skb)) { + if (!skb_flow_dissect_flow_keys_basic(NULL, skb, &keys, + NULL, 0, 0, 0, + 0)) { /* UFO does not specify ipv4 or 6: try both */ if (gso_type & SKB_GSO_UDP && skb->protocol == htons(ETH_P_IP)) { @@ -75,6 +91,12 @@ retry: } return -EINVAL; } + + if (keys.control.thoff + thlen > skb_headlen(skb) || + keys.basic.ip_proto != ip_proto) + return -EINVAL; + + skb_set_transport_header(skb, keys.control.thoff); } } diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index 71c81e0dc8f2..dc636b727179 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -48,6 +48,7 @@ struct virtio_vsock_pkt { u32 len; u32 off; bool reply; + bool tap_delivered; }; struct virtio_vsock_pkt_info { diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 3619c6acf60f..efc8350b42fb 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -166,15 +166,18 @@ enum flow_action_mangle_base { enum flow_action_hw_stats_bit { FLOW_ACTION_HW_STATS_IMMEDIATE_BIT, FLOW_ACTION_HW_STATS_DELAYED_BIT, + FLOW_ACTION_HW_STATS_DISABLED_BIT, }; enum flow_action_hw_stats { - FLOW_ACTION_HW_STATS_DISABLED = 0, + FLOW_ACTION_HW_STATS_DONT_CARE = 0, FLOW_ACTION_HW_STATS_IMMEDIATE = BIT(FLOW_ACTION_HW_STATS_IMMEDIATE_BIT), FLOW_ACTION_HW_STATS_DELAYED = BIT(FLOW_ACTION_HW_STATS_DELAYED_BIT), FLOW_ACTION_HW_STATS_ANY = FLOW_ACTION_HW_STATS_IMMEDIATE | FLOW_ACTION_HW_STATS_DELAYED, + FLOW_ACTION_HW_STATS_DISABLED = + BIT(FLOW_ACTION_HW_STATS_DISABLED_BIT), }; typedef void (*action_destr)(void *priv); @@ -325,7 +328,11 @@ __flow_action_hw_stats_check(const struct flow_action *action, return true; if (!flow_action_mixed_hw_stats_check(action, extack)) return false; + action_entry = flow_action_first_entry_get(action); + if (action_entry->hw_stats == FLOW_ACTION_HW_STATS_DONT_CARE) + return true; + if (!check_allow_bit && action_entry->hw_stats != FLOW_ACTION_HW_STATS_ANY) { NL_SET_ERR_MSG_MOD(extack, "Driver supports only default HW stats type \"any\""); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index c8e2bebd8d93..0f0d1efe06dd 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -99,6 +99,20 @@ static inline int IP_ECN_set_ce(struct iphdr *iph) return 1; } +static inline int IP_ECN_set_ect1(struct iphdr *iph) +{ + u32 check = (__force u32)iph->check; + + if ((iph->tos & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + check += (__force u16)htons(0x100); + + iph->check = (__force __sum16)(check + (check>=0xFFFF)); + iph->tos ^= INET_ECN_MASK; + return 1; +} + static inline void IP_ECN_clear(struct iphdr *iph) { iph->tos &= ~INET_ECN_MASK; @@ -134,6 +148,22 @@ static inline int IP6_ECN_set_ce(struct sk_buff *skb, struct ipv6hdr *iph) return 1; } +static inline int IP6_ECN_set_ect1(struct sk_buff *skb, struct ipv6hdr *iph) +{ + __be32 from, to; + + if ((ipv6_get_dsfield(iph) & INET_ECN_MASK) != INET_ECN_ECT_0) + return 0; + + from = *(__be32 *)iph; + to = from ^ htonl(INET_ECN_MASK << 20); + *(__be32 *)iph = to; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_add(csum_sub(skb->csum, (__force __wsum)from), + (__force __wsum)to); + return 1; +} + static inline void ipv6_copy_dscp(unsigned int dscp, struct ipv6hdr *inner) { dscp &= ~INET_ECN_MASK; @@ -159,6 +189,25 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) return 0; } +static inline int INET_ECN_set_ect1(struct sk_buff *skb) +{ + switch (skb->protocol) { + case cpu_to_be16(ETH_P_IP): + if (skb_network_header(skb) + sizeof(struct iphdr) <= + skb_tail_pointer(skb)) + return IP_ECN_set_ect1(ip_hdr(skb)); + break; + + case cpu_to_be16(ETH_P_IPV6): + if (skb_network_header(skb) + sizeof(struct ipv6hdr) <= + skb_tail_pointer(skb)) + return IP6_ECN_set_ect1(skb, ipv6_hdr(skb)); + break; + } + + return 0; +} + /* * RFC 6040 4.2 * To decapsulate the inner header at the tunnel egress, a compliant @@ -208,8 +257,12 @@ static inline int INET_ECN_decapsulate(struct sk_buff *skb, int rc; rc = __INET_ECN_decapsulate(outer, inner, &set_ce); - if (!rc && set_ce) - INET_ECN_set_ce(skb); + if (!rc) { + if (set_ce) + INET_ECN_set_ce(skb); + else if ((outer & INET_ECN_MASK) == INET_ECN_ECT_1) + INET_ECN_set_ect1(skb); + } return rc; } diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 80262d2980f5..1d98828c6649 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -203,6 +203,7 @@ struct fib6_info { struct rt6_info { struct dst_entry dst; struct fib6_info __rcu *from; + int sernum; struct rt6key rt6i_dst; struct rt6key rt6i_src; @@ -291,6 +292,9 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt) struct fib6_info *from; u32 cookie = 0; + if (rt->sernum) + return rt->sernum; + rcu_read_lock(); from = rcu_dereference(rt->from); diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 0e7c5471010b..3bce2019e4da 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -68,11 +68,8 @@ static inline bool rsk_is_mptcp(const struct request_sock *req) return tcp_rsk(req)->is_mptcp; } -void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, - int opsize, struct tcp_options_received *opt_rx); bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, unsigned int *size, struct mptcp_out_options *opts); -void mptcp_rcv_synsent(struct sock *sk); bool mptcp_synack_options(const struct request_sock *req, unsigned int *size, struct mptcp_out_options *opts); bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index ab96fb59131c..8e001e049497 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -437,6 +437,13 @@ static inline int rt_genid_ipv4(const struct net *net) return atomic_read(&net->ipv4.rt_genid); } +#if IS_ENABLED(CONFIG_IPV6) +static inline int rt_genid_ipv6(const struct net *net) +{ + return atomic_read(&net->ipv6.fib6_sernum); +} +#endif + static inline void rt_genid_bump_ipv4(struct net *net) { atomic_inc(&net->ipv4.rt_genid); diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 9f551f3b69c6..90690e37a56f 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -87,7 +87,7 @@ struct nf_conn { struct hlist_node nat_bysource; #endif /* all members below initialized via memset */ - u8 __nfct_init_offset[0]; + struct { } __nfct_init_offset; /* If we were expected by an expectation, this will be it */ struct nf_conn *master; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 6bf69652f57d..c54a7f707e50 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -127,6 +127,7 @@ enum nf_flow_flags { NF_FLOW_HW_DYING, NF_FLOW_HW_DEAD, NF_FLOW_HW_REFRESH, + NF_FLOW_HW_PENDING, }; enum flow_offload_type { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 25d2ec4c8f00..8428aa614265 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -407,6 +407,7 @@ struct tcf_block { struct mutex lock; struct list_head chain_list; u32 index; /* block index for shared blocks */ + u32 classid; /* which class this block belongs to */ refcount_t refcnt; struct net *net; struct Qdisc *q; diff --git a/include/net/tcp.h b/include/net/tcp.h index dcf9a72eeaa6..6f8e60c6fbc7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1376,7 +1376,6 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt) rx_opt->num_sacks = 0; } -u32 tcp_default_init_rwnd(u32 mss); void tcp_cwnd_restart(struct sock *sk, s32 delta); static inline void tcp_slow_start_after_idle_check(struct sock *sk) @@ -1421,6 +1420,19 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf)); } +/* We provision sk_rcvbuf around 200% of sk_rcvlowat. + * If 87.5 % (7/8) of the space has been consumed, we want to override + * SO_RCVLOWAT constraint, since we are receiving skbs with too small + * len/truesize ratio. + */ +static inline bool tcp_rmem_pressure(const struct sock *sk) +{ + int rcvbuf = READ_ONCE(sk->sk_rcvbuf); + int threshold = rcvbuf - (rcvbuf >> 3); + + return atomic_read(&sk->sk_rmem_alloc) > threshold; +} + extern void tcp_openreq_init_rwin(struct request_sock *req, const struct sock *sk_listener, const struct dst_entry *dst); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 4b1f95e08307..e7312ceb2794 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -143,14 +143,12 @@ void udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb __be16 df, __be16 src_port, __be16 dst_port, bool xnet, bool nocheck); -#if IS_ENABLED(CONFIG_IPV6) int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck); -#endif void udp_tunnel_sock_release(struct socket *sock); diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 6d6a3947c8b7..efc8b613d486 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -502,6 +502,7 @@ struct ocelot { unsigned int num_stats; int shared_queue_sz; + int num_mact_rows; struct net_device *hw_bridge_dev; u16 bridge_mask; diff --git a/include/sound/rawmidi.h b/include/sound/rawmidi.h index a36b7227a15a..334842daa904 100644 --- a/include/sound/rawmidi.h +++ b/include/sound/rawmidi.h @@ -61,6 +61,7 @@ struct snd_rawmidi_runtime { size_t avail_min; /* min avail for wakeup */ size_t avail; /* max used buffer for wakeup */ size_t xruns; /* over/underruns counter */ + int buffer_ref; /* buffer reference count */ /* misc */ spinlock_t lock; wait_queue_head_t sleep; diff --git a/include/trace/events/gpu_mem.h b/include/trace/events/gpu_mem.h index 1897822a9150..26d871f96e94 100644 --- a/include/trace/events/gpu_mem.h +++ b/include/trace/events/gpu_mem.h @@ -24,7 +24,7 @@ * * @pid: Put 0 for global total, while positive pid for process total. * - * @size: Virtual size of the allocation in bytes. + * @size: Size of the allocation in bytes. * */ TRACE_EVENT(gpu_mem_total, diff --git a/include/trace/events/rpcrdma.h b/include/trace/events/rpcrdma.h index 132c3c778a43..bdcde7d33f14 100644 --- a/include/trace/events/rpcrdma.h +++ b/include/trace/events/rpcrdma.h @@ -1279,38 +1279,42 @@ TRACE_EVENT(xprtrdma_leaked_rep, ** Server-side RPC/RDMA events **/ -DECLARE_EVENT_CLASS(svcrdma_xprt_event, +DECLARE_EVENT_CLASS(svcrdma_accept_class, TP_PROTO( - const struct svc_xprt *xprt + const struct svcxprt_rdma *rdma, + long status ), - TP_ARGS(xprt), + TP_ARGS(rdma, status), TP_STRUCT__entry( - __field(const void *, xprt) - __string(addr, xprt->xpt_remotebuf) + __field(long, status) + __string(addr, rdma->sc_xprt.xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = xprt; - __assign_str(addr, xprt->xpt_remotebuf); + __entry->status = status; + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s", - __entry->xprt, __get_str(addr) + TP_printk("addr=%s status=%ld", + __get_str(addr), __entry->status ) ); -#define DEFINE_XPRT_EVENT(name) \ - DEFINE_EVENT(svcrdma_xprt_event, svcrdma_xprt_##name, \ - TP_PROTO( \ - const struct svc_xprt *xprt \ - ), \ - TP_ARGS(xprt)) +#define DEFINE_ACCEPT_EVENT(name) \ + DEFINE_EVENT(svcrdma_accept_class, svcrdma_##name##_err, \ + TP_PROTO( \ + const struct svcxprt_rdma *rdma, \ + long status \ + ), \ + TP_ARGS(rdma, status)) -DEFINE_XPRT_EVENT(accept); -DEFINE_XPRT_EVENT(fail); -DEFINE_XPRT_EVENT(free); +DEFINE_ACCEPT_EVENT(pd); +DEFINE_ACCEPT_EVENT(qp); +DEFINE_ACCEPT_EVENT(fabric); +DEFINE_ACCEPT_EVENT(initdepth); +DEFINE_ACCEPT_EVENT(accept); TRACE_DEFINE_ENUM(RDMA_MSG); TRACE_DEFINE_ENUM(RDMA_NOMSG); @@ -1355,7 +1359,7 @@ TRACE_EVENT(svcrdma_decode_rqst, show_rpcrdma_proc(__entry->proc), __entry->hdrlen) ); -TRACE_EVENT(svcrdma_decode_short, +TRACE_EVENT(svcrdma_decode_short_err, TP_PROTO( unsigned int hdrlen ), @@ -1399,7 +1403,8 @@ DECLARE_EVENT_CLASS(svcrdma_badreq_event, ); #define DEFINE_BADREQ_EVENT(name) \ - DEFINE_EVENT(svcrdma_badreq_event, svcrdma_decode_##name,\ + DEFINE_EVENT(svcrdma_badreq_event, \ + svcrdma_decode_##name##_err, \ TP_PROTO( \ __be32 *p \ ), \ @@ -1583,28 +1588,117 @@ DECLARE_EVENT_CLASS(svcrdma_dma_map_class, DEFINE_SVC_DMA_EVENT(dma_map_page); DEFINE_SVC_DMA_EVENT(dma_unmap_page); -TRACE_EVENT(svcrdma_dma_map_rwctx, +TRACE_EVENT(svcrdma_dma_map_rw_err, TP_PROTO( const struct svcxprt_rdma *rdma, + unsigned int nents, int status ), - TP_ARGS(rdma, status), + TP_ARGS(rdma, nents, status), TP_STRUCT__entry( __field(int, status) + __field(unsigned int, nents) __string(device, rdma->sc_cm_id->device->name) __string(addr, rdma->sc_xprt.xpt_remotebuf) ), TP_fast_assign( __entry->status = status; + __entry->nents = nents; + __assign_str(device, rdma->sc_cm_id->device->name); + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s device=%s nents=%u status=%d", + __get_str(addr), __get_str(device), __entry->nents, + __entry->status + ) +); + +TRACE_EVENT(svcrdma_no_rwctx_err, + TP_PROTO( + const struct svcxprt_rdma *rdma, + unsigned int num_sges + ), + + TP_ARGS(rdma, num_sges), + + TP_STRUCT__entry( + __field(unsigned int, num_sges) + __string(device, rdma->sc_cm_id->device->name) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->num_sges = num_sges; + __assign_str(device, rdma->sc_cm_id->device->name); + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s device=%s num_sges=%d", + __get_str(addr), __get_str(device), __entry->num_sges + ) +); + +TRACE_EVENT(svcrdma_page_overrun_err, + TP_PROTO( + const struct svcxprt_rdma *rdma, + const struct svc_rqst *rqst, + unsigned int pageno + ), + + TP_ARGS(rdma, rqst, pageno), + + TP_STRUCT__entry( + __field(unsigned int, pageno) + __field(u32, xid) + __string(device, rdma->sc_cm_id->device->name) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->pageno = pageno; + __entry->xid = __be32_to_cpu(rqst->rq_xid); + __assign_str(device, rdma->sc_cm_id->device->name); + __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); + ), + + TP_printk("addr=%s device=%s xid=0x%08x pageno=%u", __get_str(addr), + __get_str(device), __entry->xid, __entry->pageno + ) +); + +TRACE_EVENT(svcrdma_small_wrch_err, + TP_PROTO( + const struct svcxprt_rdma *rdma, + unsigned int remaining, + unsigned int seg_no, + unsigned int num_segs + ), + + TP_ARGS(rdma, remaining, seg_no, num_segs), + + TP_STRUCT__entry( + __field(unsigned int, remaining) + __field(unsigned int, seg_no) + __field(unsigned int, num_segs) + __string(device, rdma->sc_cm_id->device->name) + __string(addr, rdma->sc_xprt.xpt_remotebuf) + ), + + TP_fast_assign( + __entry->remaining = remaining; + __entry->seg_no = seg_no; + __entry->num_segs = num_segs; __assign_str(device, rdma->sc_cm_id->device->name); __assign_str(addr, rdma->sc_xprt.xpt_remotebuf); ), - TP_printk("addr=%s device=%s status=%d", - __get_str(addr), __get_str(device), __entry->status + TP_printk("addr=%s device=%s remaining=%u seg_no=%u num_segs=%u", + __get_str(addr), __get_str(device), __entry->remaining, + __entry->seg_no, __entry->num_segs ) ); diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h index ffd2215950dc..852413cbb7d9 100644 --- a/include/trace/events/sunrpc.h +++ b/include/trace/events/sunrpc.h @@ -14,6 +14,39 @@ #include <linux/net.h> #include <linux/tracepoint.h> +TRACE_DEFINE_ENUM(SOCK_STREAM); +TRACE_DEFINE_ENUM(SOCK_DGRAM); +TRACE_DEFINE_ENUM(SOCK_RAW); +TRACE_DEFINE_ENUM(SOCK_RDM); +TRACE_DEFINE_ENUM(SOCK_SEQPACKET); +TRACE_DEFINE_ENUM(SOCK_DCCP); +TRACE_DEFINE_ENUM(SOCK_PACKET); + +#define show_socket_type(type) \ + __print_symbolic(type, \ + { SOCK_STREAM, "STREAM" }, \ + { SOCK_DGRAM, "DGRAM" }, \ + { SOCK_RAW, "RAW" }, \ + { SOCK_RDM, "RDM" }, \ + { SOCK_SEQPACKET, "SEQPACKET" }, \ + { SOCK_DCCP, "DCCP" }, \ + { SOCK_PACKET, "PACKET" }) + +/* This list is known to be incomplete, add new enums as needed. */ +TRACE_DEFINE_ENUM(AF_UNSPEC); +TRACE_DEFINE_ENUM(AF_UNIX); +TRACE_DEFINE_ENUM(AF_LOCAL); +TRACE_DEFINE_ENUM(AF_INET); +TRACE_DEFINE_ENUM(AF_INET6); + +#define rpc_show_address_family(family) \ + __print_symbolic(family, \ + { AF_UNSPEC, "AF_UNSPEC" }, \ + { AF_UNIX, "AF_UNIX" }, \ + { AF_LOCAL, "AF_LOCAL" }, \ + { AF_INET, "AF_INET" }, \ + { AF_INET6, "AF_INET6" }) + DECLARE_EVENT_CLASS(xdr_buf_class, TP_PROTO( const struct xdr_buf *xdr @@ -1024,6 +1057,17 @@ TRACE_EVENT(svc_recv, show_rqstp_flags(__entry->flags)) ); +TRACE_DEFINE_ENUM(SVC_GARBAGE); +TRACE_DEFINE_ENUM(SVC_SYSERR); +TRACE_DEFINE_ENUM(SVC_VALID); +TRACE_DEFINE_ENUM(SVC_NEGATIVE); +TRACE_DEFINE_ENUM(SVC_OK); +TRACE_DEFINE_ENUM(SVC_DROP); +TRACE_DEFINE_ENUM(SVC_CLOSE); +TRACE_DEFINE_ENUM(SVC_DENIED); +TRACE_DEFINE_ENUM(SVC_PENDING); +TRACE_DEFINE_ENUM(SVC_COMPLETE); + #define svc_show_status(status) \ __print_symbolic(status, \ { SVC_GARBAGE, "SVC_GARBAGE" }, \ @@ -1167,28 +1211,54 @@ DEFINE_EVENT(svc_rqst_status, svc_send, { (1UL << XPT_KILL_TEMP), "XPT_KILL_TEMP"}, \ { (1UL << XPT_CONG_CTRL), "XPT_CONG_CTRL"}) +TRACE_EVENT(svc_xprt_create_err, + TP_PROTO( + const char *program, + const char *protocol, + struct sockaddr *sap, + const struct svc_xprt *xprt + ), + + TP_ARGS(program, protocol, sap, xprt), + + TP_STRUCT__entry( + __field(long, error) + __string(program, program) + __string(protocol, protocol) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + + TP_fast_assign( + __entry->error = PTR_ERR(xprt); + __assign_str(program, program); + __assign_str(protocol, protocol); + memcpy(__entry->addr, sap, sizeof(__entry->addr)); + ), + + TP_printk("addr=%pISpc program=%s protocol=%s error=%ld", + __entry->addr, __get_str(program), __get_str(protocol), + __entry->error) +); + TRACE_EVENT(svc_xprt_do_enqueue, TP_PROTO(struct svc_xprt *xprt, struct svc_rqst *rqst), TP_ARGS(xprt, rqst), TP_STRUCT__entry( - __field(struct svc_xprt *, xprt) __field(int, pid) __field(unsigned long, flags) __string(addr, xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = xprt; __entry->pid = rqst? rqst->rq_task->pid : 0; __entry->flags = xprt->xpt_flags; __assign_str(addr, xprt->xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s pid=%d flags=%s", - __entry->xprt, __get_str(addr), - __entry->pid, show_svc_xprt_flags(__entry->flags)) + TP_printk("addr=%s pid=%d flags=%s", __get_str(addr), + __entry->pid, show_svc_xprt_flags(__entry->flags)) ); DECLARE_EVENT_CLASS(svc_xprt_event, @@ -1197,25 +1267,55 @@ DECLARE_EVENT_CLASS(svc_xprt_event, TP_ARGS(xprt), TP_STRUCT__entry( - __field(struct svc_xprt *, xprt) __field(unsigned long, flags) __string(addr, xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = xprt; __entry->flags = xprt->xpt_flags; __assign_str(addr, xprt->xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s flags=%s", - __entry->xprt, __get_str(addr), - show_svc_xprt_flags(__entry->flags)) + TP_printk("addr=%s flags=%s", __get_str(addr), + show_svc_xprt_flags(__entry->flags)) ); -DEFINE_EVENT(svc_xprt_event, svc_xprt_no_write_space, - TP_PROTO(struct svc_xprt *xprt), - TP_ARGS(xprt)); +#define DEFINE_SVC_XPRT_EVENT(name) \ + DEFINE_EVENT(svc_xprt_event, svc_xprt_##name, \ + TP_PROTO( \ + struct svc_xprt *xprt \ + ), \ + TP_ARGS(xprt)) + +DEFINE_SVC_XPRT_EVENT(no_write_space); +DEFINE_SVC_XPRT_EVENT(close); +DEFINE_SVC_XPRT_EVENT(detach); +DEFINE_SVC_XPRT_EVENT(free); + +TRACE_EVENT(svc_xprt_accept, + TP_PROTO( + const struct svc_xprt *xprt, + const char *service + ), + + TP_ARGS(xprt, service), + + TP_STRUCT__entry( + __string(addr, xprt->xpt_remotebuf) + __string(protocol, xprt->xpt_class->xcl_name) + __string(service, service) + ), + + TP_fast_assign( + __assign_str(addr, xprt->xpt_remotebuf); + __assign_str(protocol, xprt->xpt_class->xcl_name) + __assign_str(service, service); + ), + + TP_printk("addr=%s protocol=%s service=%s", + __get_str(addr), __get_str(protocol), __get_str(service) + ) +); TRACE_EVENT(svc_xprt_dequeue, TP_PROTO(struct svc_rqst *rqst), @@ -1223,24 +1323,20 @@ TRACE_EVENT(svc_xprt_dequeue, TP_ARGS(rqst), TP_STRUCT__entry( - __field(struct svc_xprt *, xprt) __field(unsigned long, flags) __field(unsigned long, wakeup) __string(addr, rqst->rq_xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = rqst->rq_xprt; __entry->flags = rqst->rq_xprt->xpt_flags; __entry->wakeup = ktime_to_us(ktime_sub(ktime_get(), rqst->rq_qtime)); __assign_str(addr, rqst->rq_xprt->xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s flags=%s wakeup-us=%lu", - __entry->xprt, __get_str(addr), - show_svc_xprt_flags(__entry->flags), - __entry->wakeup) + TP_printk("addr=%s flags=%s wakeup-us=%lu", __get_str(addr), + show_svc_xprt_flags(__entry->flags), __entry->wakeup) ); TRACE_EVENT(svc_wake_up, @@ -1265,21 +1361,18 @@ TRACE_EVENT(svc_handle_xprt, TP_ARGS(xprt, len), TP_STRUCT__entry( - __field(struct svc_xprt *, xprt) __field(int, len) __field(unsigned long, flags) __string(addr, xprt->xpt_remotebuf) ), TP_fast_assign( - __entry->xprt = xprt; __entry->len = len; __entry->flags = xprt->xpt_flags; __assign_str(addr, xprt->xpt_remotebuf); ), - TP_printk("xprt=%p addr=%s len=%d flags=%s", - __entry->xprt, __get_str(addr), + TP_printk("addr=%s len=%d flags=%s", __get_str(addr), __entry->len, show_svc_xprt_flags(__entry->flags)) ); @@ -1313,27 +1406,221 @@ DECLARE_EVENT_CLASS(svc_deferred_event, TP_ARGS(dr), TP_STRUCT__entry( + __field(const void *, dr) __field(u32, xid) __string(addr, dr->xprt->xpt_remotebuf) ), TP_fast_assign( + __entry->dr = dr; __entry->xid = be32_to_cpu(*(__be32 *)(dr->args + (dr->xprt_hlen>>2))); __assign_str(addr, dr->xprt->xpt_remotebuf); ), - TP_printk("addr=%s xid=0x%08x", __get_str(addr), __entry->xid) + TP_printk("addr=%s dr=%p xid=0x%08x", __get_str(addr), __entry->dr, + __entry->xid) ); + #define DEFINE_SVC_DEFERRED_EVENT(name) \ - DEFINE_EVENT(svc_deferred_event, svc_##name##_deferred, \ + DEFINE_EVENT(svc_deferred_event, svc_defer_##name, \ TP_PROTO( \ const struct svc_deferred_req *dr \ ), \ TP_ARGS(dr)) DEFINE_SVC_DEFERRED_EVENT(drop); -DEFINE_SVC_DEFERRED_EVENT(revisit); +DEFINE_SVC_DEFERRED_EVENT(queue); +DEFINE_SVC_DEFERRED_EVENT(recv); + +TRACE_EVENT(svcsock_new_socket, + TP_PROTO( + const struct socket *socket + ), + + TP_ARGS(socket), + + TP_STRUCT__entry( + __field(unsigned long, type) + __field(unsigned long, family) + __field(bool, listener) + ), + + TP_fast_assign( + __entry->type = socket->type; + __entry->family = socket->sk->sk_family; + __entry->listener = (socket->sk->sk_state == TCP_LISTEN); + ), + + TP_printk("type=%s family=%s%s", + show_socket_type(__entry->type), + rpc_show_address_family(__entry->family), + __entry->listener ? " (listener)" : "" + ) +); + +TRACE_EVENT(svcsock_marker, + TP_PROTO( + const struct svc_xprt *xprt, + __be32 marker + ), + + TP_ARGS(xprt, marker), + + TP_STRUCT__entry( + __field(unsigned int, length) + __field(bool, last) + __string(addr, xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->length = be32_to_cpu(marker) & RPC_FRAGMENT_SIZE_MASK; + __entry->last = be32_to_cpu(marker) & RPC_LAST_STREAM_FRAGMENT; + __assign_str(addr, xprt->xpt_remotebuf); + ), + + TP_printk("addr=%s length=%u%s", __get_str(addr), + __entry->length, __entry->last ? " (last)" : "") +); + +DECLARE_EVENT_CLASS(svcsock_class, + TP_PROTO( + const struct svc_xprt *xprt, + ssize_t result + ), + + TP_ARGS(xprt, result), + + TP_STRUCT__entry( + __field(ssize_t, result) + __field(unsigned long, flags) + __string(addr, xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->result = result; + __entry->flags = xprt->xpt_flags; + __assign_str(addr, xprt->xpt_remotebuf); + ), + + TP_printk("addr=%s result=%zd flags=%s", __get_str(addr), + __entry->result, show_svc_xprt_flags(__entry->flags) + ) +); + +#define DEFINE_SVCSOCK_EVENT(name) \ + DEFINE_EVENT(svcsock_class, svcsock_##name, \ + TP_PROTO( \ + const struct svc_xprt *xprt, \ + ssize_t result \ + ), \ + TP_ARGS(xprt, result)) + +DEFINE_SVCSOCK_EVENT(udp_send); +DEFINE_SVCSOCK_EVENT(udp_recv); +DEFINE_SVCSOCK_EVENT(udp_recv_err); +DEFINE_SVCSOCK_EVENT(tcp_send); +DEFINE_SVCSOCK_EVENT(tcp_recv); +DEFINE_SVCSOCK_EVENT(tcp_recv_eagain); +DEFINE_SVCSOCK_EVENT(tcp_recv_err); +DEFINE_SVCSOCK_EVENT(data_ready); +DEFINE_SVCSOCK_EVENT(write_space); + +TRACE_EVENT(svcsock_tcp_recv_short, + TP_PROTO( + const struct svc_xprt *xprt, + u32 expected, + u32 received + ), + + TP_ARGS(xprt, expected, received), + + TP_STRUCT__entry( + __field(u32, expected) + __field(u32, received) + __field(unsigned long, flags) + __string(addr, xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->expected = expected; + __entry->received = received; + __entry->flags = xprt->xpt_flags; + __assign_str(addr, xprt->xpt_remotebuf); + ), + + TP_printk("addr=%s flags=%s expected=%u received=%u", + __get_str(addr), show_svc_xprt_flags(__entry->flags), + __entry->expected, __entry->received + ) +); + +TRACE_EVENT(svcsock_tcp_state, + TP_PROTO( + const struct svc_xprt *xprt, + const struct socket *socket + ), + + TP_ARGS(xprt, socket), + + TP_STRUCT__entry( + __field(unsigned long, socket_state) + __field(unsigned long, sock_state) + __field(unsigned long, flags) + __string(addr, xprt->xpt_remotebuf) + ), + + TP_fast_assign( + __entry->socket_state = socket->state; + __entry->sock_state = socket->sk->sk_state; + __entry->flags = xprt->xpt_flags; + __assign_str(addr, xprt->xpt_remotebuf); + ), + + TP_printk("addr=%s state=%s sk_state=%s flags=%s", __get_str(addr), + rpc_show_socket_state(__entry->socket_state), + rpc_show_sock_state(__entry->sock_state), + show_svc_xprt_flags(__entry->flags) + ) +); + +DECLARE_EVENT_CLASS(svcsock_accept_class, + TP_PROTO( + const struct svc_xprt *xprt, + const char *service, + long status + ), + + TP_ARGS(xprt, service, status), + + TP_STRUCT__entry( + __field(long, status) + __string(service, service) + __array(unsigned char, addr, sizeof(struct sockaddr_in6)) + ), + + TP_fast_assign( + __entry->status = status; + __assign_str(service, service); + memcpy(__entry->addr, &xprt->xpt_local, sizeof(__entry->addr)); + ), + + TP_printk("listener=%pISpc service=%s status=%ld", + __entry->addr, __get_str(service), __entry->status + ) +); + +#define DEFINE_ACCEPT_EVENT(name) \ + DEFINE_EVENT(svcsock_accept_class, svcsock_##name##_err, \ + TP_PROTO( \ + const struct svc_xprt *xprt, \ + const char *service, \ + long status \ + ), \ + TP_ARGS(xprt, service, status)) + +DEFINE_ACCEPT_EVENT(accept); +DEFINE_ACCEPT_EVENT(getpeername); DECLARE_EVENT_CLASS(cache_event, TP_PROTO( @@ -1368,6 +1655,86 @@ DEFINE_CACHE_EVENT(cache_entry_update); DEFINE_CACHE_EVENT(cache_entry_make_negative); DEFINE_CACHE_EVENT(cache_entry_no_listener); +DECLARE_EVENT_CLASS(register_class, + TP_PROTO( + const char *program, + const u32 version, + const int family, + const unsigned short protocol, + const unsigned short port, + int error + ), + + TP_ARGS(program, version, family, protocol, port, error), + + TP_STRUCT__entry( + __field(u32, version) + __field(unsigned long, family) + __field(unsigned short, protocol) + __field(unsigned short, port) + __field(int, error) + __string(program, program) + ), + + TP_fast_assign( + __entry->version = version; + __entry->family = family; + __entry->protocol = protocol; + __entry->port = port; + __entry->error = error; + __assign_str(program, program); + ), + + TP_printk("program=%sv%u proto=%s port=%u family=%s error=%d", + __get_str(program), __entry->version, + __entry->protocol == IPPROTO_UDP ? "udp" : "tcp", + __entry->port, rpc_show_address_family(__entry->family), + __entry->error + ) +); + +#define DEFINE_REGISTER_EVENT(name) \ + DEFINE_EVENT(register_class, svc_##name, \ + TP_PROTO( \ + const char *program, \ + const u32 version, \ + const int family, \ + const unsigned short protocol, \ + const unsigned short port, \ + int error \ + ), \ + TP_ARGS(program, version, family, protocol, \ + port, error)) + +DEFINE_REGISTER_EVENT(register); +DEFINE_REGISTER_EVENT(noregister); + +TRACE_EVENT(svc_unregister, + TP_PROTO( + const char *program, + const u32 version, + int error + ), + + TP_ARGS(program, version, error), + + TP_STRUCT__entry( + __field(u32, version) + __field(int, error) + __string(program, program) + ), + + TP_fast_assign( + __entry->version = version; + __entry->error = error; + __assign_str(program, program); + ), + + TP_printk("program=%sv%u error=%d", + __get_str(program), __entry->version, __entry->error + ) +); + #endif /* _TRACE_SUNRPC_H */ #include <trace/define_trace.h> diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h index 784814160197..9c66e59d859c 100644 --- a/include/trace/events/wbt.h +++ b/include/trace/events/wbt.h @@ -33,7 +33,7 @@ TRACE_EVENT(wbt_stat, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->rmean = stat[0].mean; __entry->rmin = stat[0].min; @@ -68,7 +68,7 @@ TRACE_EVENT(wbt_lat, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->lat = div_u64(lat, 1000); ), @@ -105,7 +105,7 @@ TRACE_EVENT(wbt_step, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->msg = msg; __entry->step = step; @@ -141,7 +141,7 @@ TRACE_EVENT(wbt_timer, ), TP_fast_assign( - strlcpy(__entry->name, dev_name(bdi->dev), + strlcpy(__entry->name, bdi_dev_name(bdi), ARRAY_SIZE(__entry->name)); __entry->status = status; __entry->step = step; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7bbf1b65be10..f9b7fdd951e4 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -73,7 +73,7 @@ struct bpf_insn { /* Key of an a BPF_MAP_TYPE_LPM_TRIE entry */ struct bpf_lpm_trie_key { __u32 prefixlen; /* up to 32 for AF_INET, 128 for AF_INET6 */ - __u8 data[]; /* Arbitrary size */ + __u8 data[0]; /* Arbitrary size */ }; struct bpf_cgroup_storage_key { diff --git a/include/uapi/linux/dlm_device.h b/include/uapi/linux/dlm_device.h index e83954c69fff..f880d2831160 100644 --- a/include/uapi/linux/dlm_device.h +++ b/include/uapi/linux/dlm_device.h @@ -45,13 +45,13 @@ struct dlm_lock_params { void __user *bastaddr; struct dlm_lksb __user *lksb; char lvb[DLM_USER_LVB_LEN]; - char name[]; + char name[0]; }; struct dlm_lspace_params { __u32 flags; __u32 minor; - char name[]; + char name[0]; }; struct dlm_purge_params { diff --git a/include/uapi/linux/fiemap.h b/include/uapi/linux/fiemap.h index 7a900b2377b6..8c0bc24d5d95 100644 --- a/include/uapi/linux/fiemap.h +++ b/include/uapi/linux/fiemap.h @@ -34,7 +34,7 @@ struct fiemap { __u32 fm_mapped_extents;/* number of extents that were mapped (out) */ __u32 fm_extent_count; /* size of fm_extents array (in) */ __u32 fm_reserved; - struct fiemap_extent fm_extents[]; /* array of mapped extents (out) */ + struct fiemap_extent fm_extents[0]; /* array of mapped extents (out) */ }; #define FIEMAP_MAX_OFFSET (~0ULL) diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index b122cfac7128..683878036d76 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -60,7 +60,7 @@ struct arc_rfc1201 { __u8 proto; /* protocol ID field - varies */ __u8 split_flag; /* for use with split packets */ __be16 sequence; /* sequence number */ - __u8 payload[]; /* space remaining in packet (504 bytes)*/ + __u8 payload[0]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 @@ -69,7 +69,7 @@ struct arc_rfc1201 { */ struct arc_rfc1051 { __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - __u8 payload[]; /* 507 bytes */ + __u8 payload[0]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 @@ -80,7 +80,7 @@ struct arc_rfc1051 { struct arc_eth_encap { __u8 proto; /* Always ARC_P_ETHER */ struct ethhdr eth; /* standard ethernet header (yuck!) */ - __u8 payload[]; /* 493 bytes */ + __u8 payload[0]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h index 98e29e7f54ac..00c08120f3ba 100644 --- a/include/uapi/linux/mmc/ioctl.h +++ b/include/uapi/linux/mmc/ioctl.h @@ -57,7 +57,7 @@ struct mmc_ioc_cmd { */ struct mmc_ioc_multi_cmd { __u64 num_of_cmds; - struct mmc_ioc_cmd cmds[]; + struct mmc_ioc_cmd cmds[0]; }; #define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd) diff --git a/include/uapi/linux/net_dropmon.h b/include/uapi/linux/net_dropmon.h index 67e31f329190..66048cc5d7b3 100644 --- a/include/uapi/linux/net_dropmon.h +++ b/include/uapi/linux/net_dropmon.h @@ -29,12 +29,12 @@ struct net_dm_config_entry { struct net_dm_config_msg { __u32 entries; - struct net_dm_config_entry options[]; + struct net_dm_config_entry options[0]; }; struct net_dm_alert_msg { __u32 entries; - struct net_dm_drop_point points[]; + struct net_dm_drop_point points[0]; }; struct net_dm_user_msg { diff --git a/include/uapi/linux/netfilter_bridge/ebt_among.h b/include/uapi/linux/netfilter_bridge/ebt_among.h index 73b26a280c4f..9acf757bc1f7 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_among.h +++ b/include/uapi/linux/netfilter_bridge/ebt_among.h @@ -40,7 +40,7 @@ struct ebt_mac_wormhash_tuple { struct ebt_mac_wormhash { int table[257]; int poolsize; - struct ebt_mac_wormhash_tuple pool[]; + struct ebt_mac_wormhash_tuple pool[0]; }; #define ebt_mac_wormhash_size(x) ((x) ? sizeof(struct ebt_mac_wormhash) \ diff --git a/include/uapi/linux/usb/raw_gadget.h b/include/uapi/linux/usb/raw_gadget.h index ea375082b3ac..0be685272eb1 100644 --- a/include/uapi/linux/usb/raw_gadget.h +++ b/include/uapi/linux/usb/raw_gadget.h @@ -93,6 +93,64 @@ struct usb_raw_ep_io { __u8 data[0]; }; +/* Maximum number of non-control endpoints in struct usb_raw_eps_info. */ +#define USB_RAW_EPS_NUM_MAX 30 + +/* Maximum length of UDC endpoint name in struct usb_raw_ep_info. */ +#define USB_RAW_EP_NAME_MAX 16 + +/* Used as addr in struct usb_raw_ep_info if endpoint accepts any address. */ +#define USB_RAW_EP_ADDR_ANY 0xff + +/* + * struct usb_raw_ep_caps - exposes endpoint capabilities from struct usb_ep + * (technically from its member struct usb_ep_caps). + */ +struct usb_raw_ep_caps { + __u32 type_control : 1; + __u32 type_iso : 1; + __u32 type_bulk : 1; + __u32 type_int : 1; + __u32 dir_in : 1; + __u32 dir_out : 1; +}; + +/* + * struct usb_raw_ep_limits - exposes endpoint limits from struct usb_ep. + * @maxpacket_limit: Maximum packet size value supported by this endpoint. + * @max_streams: maximum number of streams supported by this endpoint + * (actual number is 2^n). + * @reserved: Empty, reserved for potential future extensions. + */ +struct usb_raw_ep_limits { + __u16 maxpacket_limit; + __u16 max_streams; + __u32 reserved; +}; + +/* + * struct usb_raw_ep_info - stores information about a gadget endpoint. + * @name: Name of the endpoint as it is defined in the UDC driver. + * @addr: Address of the endpoint that must be specified in the endpoint + * descriptor passed to USB_RAW_IOCTL_EP_ENABLE ioctl. + * @caps: Endpoint capabilities. + * @limits: Endpoint limits. + */ +struct usb_raw_ep_info { + __u8 name[USB_RAW_EP_NAME_MAX]; + __u32 addr; + struct usb_raw_ep_caps caps; + struct usb_raw_ep_limits limits; +}; + +/* + * struct usb_raw_eps_info - argument for USB_RAW_IOCTL_EPS_INFO ioctl. + * eps: Structures that store information about non-control endpoints. + */ +struct usb_raw_eps_info { + struct usb_raw_ep_info eps[USB_RAW_EPS_NUM_MAX]; +}; + /* * Initializes a Raw Gadget instance. * Accepts a pointer to the usb_raw_init struct as an argument. @@ -115,37 +173,38 @@ struct usb_raw_ep_io { #define USB_RAW_IOCTL_EVENT_FETCH _IOR('U', 2, struct usb_raw_event) /* - * Queues an IN (OUT for READ) urb as a response to the last control request - * received on endpoint 0, provided that was an IN (OUT for READ) request and - * waits until the urb is completed. Copies received data to user for READ. + * Queues an IN (OUT for READ) request as a response to the last setup request + * received on endpoint 0 (provided that was an IN (OUT for READ) request), and + * waits until the request is completed. Copies received data to user for READ. * Accepts a pointer to the usb_raw_ep_io struct as an argument. - * Returns length of trasferred data on success or negative error code on + * Returns length of transferred data on success or negative error code on * failure. */ #define USB_RAW_IOCTL_EP0_WRITE _IOW('U', 3, struct usb_raw_ep_io) #define USB_RAW_IOCTL_EP0_READ _IOWR('U', 4, struct usb_raw_ep_io) /* - * Finds an endpoint that supports the transfer type specified in the - * descriptor and enables it. - * Accepts a pointer to the usb_endpoint_descriptor struct as an argument. + * Finds an endpoint that satisfies the parameters specified in the provided + * descriptors (address, transfer type, etc.) and enables it. + * Accepts a pointer to the usb_raw_ep_descs struct as an argument. * Returns enabled endpoint handle on success or negative error code on failure. */ #define USB_RAW_IOCTL_EP_ENABLE _IOW('U', 5, struct usb_endpoint_descriptor) -/* Disables specified endpoint. +/* + * Disables specified endpoint. * Accepts endpoint handle as an argument. * Returns 0 on success or negative error code on failure. */ #define USB_RAW_IOCTL_EP_DISABLE _IOW('U', 6, __u32) /* - * Queues an IN (OUT for READ) urb as a response to the last control request - * received on endpoint usb_raw_ep_io.ep, provided that was an IN (OUT for READ) - * request and waits until the urb is completed. Copies received data to user - * for READ. + * Queues an IN (OUT for READ) request as a response to the last setup request + * received on endpoint usb_raw_ep_io.ep (provided that was an IN (OUT for READ) + * request), and waits until the request is completed. Copies received data to + * user for READ. * Accepts a pointer to the usb_raw_ep_io struct as an argument. - * Returns length of trasferred data on success or negative error code on + * Returns length of transferred data on success or negative error code on * failure. */ #define USB_RAW_IOCTL_EP_WRITE _IOW('U', 7, struct usb_raw_ep_io) @@ -164,4 +223,27 @@ struct usb_raw_ep_io { */ #define USB_RAW_IOCTL_VBUS_DRAW _IOW('U', 10, __u32) +/* + * Fills in the usb_raw_eps_info structure with information about non-control + * endpoints available for the currently connected UDC. + * Returns the number of available endpoints on success or negative error code + * on failure. + */ +#define USB_RAW_IOCTL_EPS_INFO _IOR('U', 11, struct usb_raw_eps_info) + +/* + * Stalls a pending control request on endpoint 0. + * Returns 0 on success or negative error code on failure. + */ +#define USB_RAW_IOCTL_EP0_STALL _IO('U', 12) + +/* + * Sets or clears halt or wedge status of the endpoint. + * Accepts endpoint handle as an argument. + * Returns 0 on success or negative error code on failure. + */ +#define USB_RAW_IOCTL_EP_SET_HALT _IOW('U', 13, __u32) +#define USB_RAW_IOCTL_EP_CLEAR_HALT _IOW('U', 14, __u32) +#define USB_RAW_IOCTL_EP_SET_WEDGE _IOW('U', 15, __u32) + #endif /* _UAPI__LINUX_USB_RAW_GADGET_H */ diff --git a/include/uapi/scsi/scsi_bsg_fc.h b/include/uapi/scsi/scsi_bsg_fc.h index 7f5930801f72..3ae65e93235c 100644 --- a/include/uapi/scsi/scsi_bsg_fc.h +++ b/include/uapi/scsi/scsi_bsg_fc.h @@ -209,7 +209,7 @@ struct fc_bsg_host_vendor { __u64 vendor_id; /* start of vendor command area */ - __u32 vendor_cmd[]; + __u32 vendor_cmd[0]; }; /* Response: diff --git a/init/Kconfig b/init/Kconfig index 9e22ee8fbd75..74a5ac65644f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -39,22 +39,6 @@ config TOOLS_SUPPORT_RELR config CC_HAS_ASM_INLINE def_bool $(success,echo 'void foo(void) { asm inline (""); }' | $(CC) -x c - -c -o /dev/null) -config CC_HAS_WARN_MAYBE_UNINITIALIZED - def_bool $(cc-option,-Wmaybe-uninitialized) - help - GCC >= 4.7 supports this option. - -config CC_DISABLE_WARN_MAYBE_UNINITIALIZED - bool - depends on CC_HAS_WARN_MAYBE_UNINITIALIZED - default CC_IS_GCC && GCC_VERSION < 40900 # unreliable for GCC < 4.9 - help - GCC's -Wmaybe-uninitialized is not reliable by definition. - Lots of false positive warnings are produced in some cases. - - If this option is enabled, -Wno-maybe-uninitialzed is passed - to the compiler to suppress maybe-uninitialized warnings. - config CONSTRUCTORS bool depends on !UML @@ -1257,14 +1241,12 @@ config CC_OPTIMIZE_FOR_PERFORMANCE config CC_OPTIMIZE_FOR_PERFORMANCE_O3 bool "Optimize more for performance (-O3)" depends on ARC - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Choosing this option will pass "-O3" to your compiler to optimize the kernel yet more for performance. config CC_OPTIMIZE_FOR_SIZE bool "Optimize for size (-Os)" - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help Choosing this option will pass "-Os" to your compiler resulting in a smaller kernel. @@ -2279,6 +2261,9 @@ config ASN1 source "kernel/Kconfig.locks" +config ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + bool + config ARCH_HAS_SYNC_CORE_BEFORE_USERMODE bool diff --git a/init/initramfs.c b/init/initramfs.c index 8ec1be4d7d51..7a38012e1af7 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -542,7 +542,7 @@ void __weak free_initrd_mem(unsigned long start, unsigned long end) } #ifdef CONFIG_KEXEC_CORE -static bool kexec_free_initrd(void) +static bool __init kexec_free_initrd(void) { unsigned long crashk_start = (unsigned long)__va(crashk_res.start); unsigned long crashk_end = (unsigned long)__va(crashk_res.end); diff --git a/init/main.c b/init/main.c index a48617f2e5e5..03371976d387 100644 --- a/init/main.c +++ b/init/main.c @@ -257,6 +257,47 @@ static int __init loglevel(char *str) early_param("loglevel", loglevel); +#ifdef CONFIG_BLK_DEV_INITRD +static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) +{ + u32 size, csum; + char *data; + u32 *hdr; + + if (!initrd_end) + return NULL; + + data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; + if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) + return NULL; + + hdr = (u32 *)(data - 8); + size = hdr[0]; + csum = hdr[1]; + + data = ((void *)hdr) - size; + if ((unsigned long)data < initrd_start) { + pr_err("bootconfig size %d is greater than initrd size %ld\n", + size, initrd_end - initrd_start); + return NULL; + } + + /* Remove bootconfig from initramfs/initrd */ + initrd_end = (unsigned long)data; + if (_size) + *_size = size; + if (_csum) + *_csum = csum; + + return data; +} +#else +static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) +{ + return NULL; +} +#endif + #ifdef CONFIG_BOOT_CONFIG char xbc_namebuf[XBC_KEYLEN_MAX] __initdata; @@ -357,9 +398,11 @@ static void __init setup_boot_config(const char *cmdline) int pos; u32 size, csum; char *data, *copy; - u32 *hdr; int ret; + /* Cut out the bootconfig data even if we have no bootconfig option */ + data = get_boot_config_from_initrd(&size, &csum); + strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE); parse_args("bootconfig", tmp_cmdline, NULL, 0, 0, 0, NULL, bootconfig_params); @@ -367,16 +410,10 @@ static void __init setup_boot_config(const char *cmdline) if (!bootconfig_found) return; - if (!initrd_end) - goto not_found; - - data = (char *)initrd_end - BOOTCONFIG_MAGIC_LEN; - if (memcmp(data, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN)) - goto not_found; - - hdr = (u32 *)(data - 8); - size = hdr[0]; - csum = hdr[1]; + if (!data) { + pr_err("'bootconfig' found on command line, but no bootconfig found\n"); + return; + } if (size >= XBC_DATA_MAX) { pr_err("bootconfig size %d greater than max size %d\n", @@ -384,10 +421,6 @@ static void __init setup_boot_config(const char *cmdline) return; } - data = ((void *)hdr) - size; - if ((unsigned long)data < initrd_start) - goto not_found; - if (boot_config_checksum((unsigned char *)data, size) != csum) { pr_err("bootconfig checksum failed\n"); return; @@ -417,11 +450,15 @@ static void __init setup_boot_config(const char *cmdline) extra_init_args = xbc_make_cmdline("init"); } return; -not_found: - pr_err("'bootconfig' found on command line, but no bootconfig found\n"); } + #else -#define setup_boot_config(cmdline) do { } while (0) + +static void __init setup_boot_config(const char *cmdline) +{ + /* Remove bootconfig data from initrd */ + get_boot_config_from_initrd(NULL, NULL); +} static int __init warn_bootconfig(char *str) { @@ -1001,6 +1038,8 @@ asmlinkage __visible void __init start_kernel(void) /* Do the rest non-__init'ed, we're now alive */ arch_call_rest_init(); + + prevent_tail_call_optimization(); } /* Call all constructor functions linked into the kernel. */ diff --git a/ipc/mqueue.c b/ipc/mqueue.c index dc8307bf2d74..beff0cfcd1e8 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -142,6 +142,7 @@ struct mqueue_inode_info { struct sigevent notify; struct pid *notify_owner; + u32 notify_self_exec_id; struct user_namespace *notify_user_ns; struct user_struct *user; /* user who created, for accounting */ struct sock *notify_sock; @@ -773,28 +774,44 @@ static void __do_notify(struct mqueue_inode_info *info) * synchronously. */ if (info->notify_owner && info->attr.mq_curmsgs == 1) { - struct kernel_siginfo sig_i; switch (info->notify.sigev_notify) { case SIGEV_NONE: break; - case SIGEV_SIGNAL: - /* sends signal */ + case SIGEV_SIGNAL: { + struct kernel_siginfo sig_i; + struct task_struct *task; + + /* do_mq_notify() accepts sigev_signo == 0, why?? */ + if (!info->notify.sigev_signo) + break; clear_siginfo(&sig_i); sig_i.si_signo = info->notify.sigev_signo; sig_i.si_errno = 0; sig_i.si_code = SI_MESGQ; sig_i.si_value = info->notify.sigev_value; - /* map current pid/uid into info->owner's namespaces */ rcu_read_lock(); + /* map current pid/uid into info->owner's namespaces */ sig_i.si_pid = task_tgid_nr_ns(current, ns_of_pid(info->notify_owner)); - sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid()); + sig_i.si_uid = from_kuid_munged(info->notify_user_ns, + current_uid()); + /* + * We can't use kill_pid_info(), this signal should + * bypass check_kill_permission(). It is from kernel + * but si_fromuser() can't know this. + * We do check the self_exec_id, to avoid sending + * signals to programs that don't expect them. + */ + task = pid_task(info->notify_owner, PIDTYPE_TGID); + if (task && task->self_exec_id == + info->notify_self_exec_id) { + do_send_sig_info(info->notify.sigev_signo, + &sig_i, task, PIDTYPE_TGID); + } rcu_read_unlock(); - - kill_pid_info(info->notify.sigev_signo, - &sig_i, info->notify_owner); break; + } case SIGEV_THREAD: set_cookie(info->notify_cookie, NOTIFY_WOKENUP); netlink_sendskb(info->notify_sock, info->notify_cookie); @@ -1383,6 +1400,7 @@ retry: info->notify.sigev_signo = notification->sigev_signo; info->notify.sigev_value = notification->sigev_value; info->notify.sigev_notify = SIGEV_SIGNAL; + info->notify_self_exec_id = current->self_exec_id; break; } diff --git a/ipc/util.c b/ipc/util.c index 7acccfded7cb..cfa0045e748d 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -764,21 +764,21 @@ static struct kern_ipc_perm *sysvipc_find_ipc(struct ipc_ids *ids, loff_t pos, total++; } - *new_pos = pos + 1; + ipc = NULL; if (total >= ids->in_use) - return NULL; + goto out; for (; pos < ipc_mni; pos++) { ipc = idr_find(&ids->ipcs_idr, pos); if (ipc != NULL) { rcu_read_lock(); ipc_lock_object(ipc); - return ipc; + break; } } - - /* Out of range - return NULL to terminate iteration */ - return NULL; +out: + *new_pos = pos + 1; + return ipc; } static void *sysvipc_proc_next(struct seq_file *s, void *it, loff_t *pos) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 95d77770353c..1d6120fd5ba6 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -486,7 +486,12 @@ static int array_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) if (!(map->map_flags & BPF_F_MMAPABLE)) return -EINVAL; - return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), pgoff); + if (vma->vm_pgoff * PAGE_SIZE + (vma->vm_end - vma->vm_start) > + PAGE_ALIGN((u64)array->map.max_entries * array->elem_size)) + return -EINVAL; + + return remap_vmalloc_range(vma, array_map_vmalloc_addr(array), + vma->vm_pgoff + pgoff); } const struct bpf_map_ops array_map_ops = { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7626b8024471..2843bbba9ca1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1485,8 +1485,10 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr) if (err) goto free_value; - if (copy_to_user(uvalue, value, value_size) != 0) + if (copy_to_user(uvalue, value, value_size) != 0) { + err = -EFAULT; goto free_value; + } err = 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fa1d8245b925..8d7ee40e2748 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -4340,7 +4340,9 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, if (ret_type != RET_INTEGER || (func_id != BPF_FUNC_get_stack && - func_id != BPF_FUNC_probe_read_str)) + func_id != BPF_FUNC_probe_read_str && + func_id != BPF_FUNC_probe_read_kernel_str && + func_id != BPF_FUNC_probe_read_user_str)) return; ret_reg->smax_value = meta->msize_max_value; @@ -7059,6 +7061,23 @@ static int check_return_code(struct bpf_verifier_env *env) return 0; range = tnum_const(0); break; + case BPF_PROG_TYPE_TRACING: + switch (env->prog->expected_attach_type) { + case BPF_TRACE_FENTRY: + case BPF_TRACE_FEXIT: + range = tnum_const(0); + break; + case BPF_TRACE_RAW_TP: + case BPF_MODIFY_RETURN: + return 0; + default: + return -ENOTSUPP; + } + break; + case BPF_PROG_TYPE_EXT: + /* freplace program can return anything as its return value + * depends on the to-be-replaced kernel func or bpf program. + */ default: return 0; } diff --git a/kernel/fork.c b/kernel/fork.c index 8c700f881d92..48ed22774efa 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2486,11 +2486,11 @@ long do_fork(unsigned long clone_flags, int __user *child_tidptr) { struct kernel_clone_args args = { - .flags = (clone_flags & ~CSIGNAL), + .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, - .exit_signal = (clone_flags & CSIGNAL), + .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = stack_start, .stack_size = stack_size, }; @@ -2508,8 +2508,9 @@ long do_fork(unsigned long clone_flags, pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { - .flags = ((flags | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), - .exit_signal = (flags & CSIGNAL), + .flags = ((lower_32_bits(flags) | CLONE_VM | + CLONE_UNTRACED) & ~CSIGNAL), + .exit_signal = (lower_32_bits(flags) & CSIGNAL), .stack = (unsigned long)fn, .stack_size = (unsigned long)arg, }; @@ -2570,11 +2571,11 @@ SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, #endif { struct kernel_clone_args args = { - .flags = (clone_flags & ~CSIGNAL), + .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, - .exit_signal = (clone_flags & CSIGNAL), + .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; diff --git a/kernel/kcov.c b/kernel/kcov.c index f50354202dbe..8accc9722a81 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -740,8 +740,8 @@ static const struct file_operations kcov_fops = { * kcov_remote_handle() with KCOV_SUBSYSTEM_COMMON as the subsystem id and an * arbitrary 4-byte non-zero number as the instance id). This common handle * then gets saved into the task_struct of the process that issued the - * KCOV_REMOTE_ENABLE ioctl. When this proccess issues system calls that spawn - * kernel threads, the common handle must be retrived via kcov_common_handle() + * KCOV_REMOTE_ENABLE ioctl. When this process issues system calls that spawn + * kernel threads, the common handle must be retrieved via kcov_common_handle() * and passed to the spawned threads via custom annotations. Those kernel * threads must in turn be annotated with kcov_remote_start(common_handle) and * kcov_remote_stop(). All of the threads that are spawned by the same process diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 402eef84c859..743647005f64 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -466,7 +466,6 @@ config PROFILE_ANNOTATED_BRANCHES config PROFILE_ALL_BRANCHES bool "Profile all if conditionals" if !FORTIFY_SOURCE select TRACE_BRANCH_PROFILING - imply CC_DISABLE_WARN_MAYBE_UNINITIALIZED # avoid false positives help This tracer profiles all branch conditions. Every if () taken in the kernel is recorded whether it hit or miss. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index ca1796747a77..a010edc37ee0 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -323,17 +323,15 @@ static const struct bpf_func_proto *bpf_get_probe_write_proto(void) /* * Only limited trace_printk() conversion specifiers allowed: - * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %s + * %d %i %u %x %ld %li %lu %lx %lld %lli %llu %llx %p %pks %pus %s */ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, u64, arg2, u64, arg3) { + int i, mod[3] = {}, fmt_cnt = 0; + char buf[64], fmt_ptype; + void *unsafe_ptr = NULL; bool str_seen = false; - int mod[3] = {}; - int fmt_cnt = 0; - u64 unsafe_addr; - char buf[64]; - int i; /* * bpf_check()->check_func_arg()->check_stack_boundary() @@ -359,40 +357,71 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, if (fmt[i] == 'l') { mod[fmt_cnt]++; i++; - } else if (fmt[i] == 'p' || fmt[i] == 's') { + } else if (fmt[i] == 'p') { mod[fmt_cnt]++; + if ((fmt[i + 1] == 'k' || + fmt[i + 1] == 'u') && + fmt[i + 2] == 's') { + fmt_ptype = fmt[i + 1]; + i += 2; + goto fmt_str; + } + /* disallow any further format extensions */ if (fmt[i + 1] != 0 && !isspace(fmt[i + 1]) && !ispunct(fmt[i + 1])) return -EINVAL; - fmt_cnt++; - if (fmt[i] == 's') { - if (str_seen) - /* allow only one '%s' per fmt string */ - return -EINVAL; - str_seen = true; - - switch (fmt_cnt) { - case 1: - unsafe_addr = arg1; - arg1 = (long) buf; - break; - case 2: - unsafe_addr = arg2; - arg2 = (long) buf; - break; - case 3: - unsafe_addr = arg3; - arg3 = (long) buf; - break; - } - buf[0] = 0; - strncpy_from_unsafe(buf, - (void *) (long) unsafe_addr, + + goto fmt_next; + } else if (fmt[i] == 's') { + mod[fmt_cnt]++; + fmt_ptype = fmt[i]; +fmt_str: + if (str_seen) + /* allow only one '%s' per fmt string */ + return -EINVAL; + str_seen = true; + + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) + return -EINVAL; + + switch (fmt_cnt) { + case 0: + unsafe_ptr = (void *)(long)arg1; + arg1 = (long)buf; + break; + case 1: + unsafe_ptr = (void *)(long)arg2; + arg2 = (long)buf; + break; + case 2: + unsafe_ptr = (void *)(long)arg3; + arg3 = (long)buf; + break; + } + + buf[0] = 0; + switch (fmt_ptype) { + case 's': +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + strncpy_from_unsafe(buf, unsafe_ptr, sizeof(buf)); + break; +#endif + case 'k': + strncpy_from_unsafe_strict(buf, unsafe_ptr, + sizeof(buf)); + break; + case 'u': + strncpy_from_unsafe_user(buf, + (__force void __user *)unsafe_ptr, + sizeof(buf)); + break; } - continue; + goto fmt_next; } if (fmt[i] == 'l') { @@ -403,6 +432,7 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' && fmt[i] != 'x') return -EINVAL; +fmt_next: fmt_cnt++; } @@ -825,14 +855,16 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_probe_read_user_proto; case BPF_FUNC_probe_read_kernel: return &bpf_probe_read_kernel_proto; - case BPF_FUNC_probe_read: - return &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_user_str: return &bpf_probe_read_user_str_proto; case BPF_FUNC_probe_read_kernel_str: return &bpf_probe_read_kernel_str_proto; +#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + case BPF_FUNC_probe_read: + return &bpf_probe_read_compat_proto; case BPF_FUNC_probe_read_str: return &bpf_probe_read_compat_str_proto; +#endif #ifdef CONFIG_CGROUPS case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; diff --git a/kernel/trace/ftrace_internal.h b/kernel/trace/ftrace_internal.h index 0456e0a3dab1..382775edf690 100644 --- a/kernel/trace/ftrace_internal.h +++ b/kernel/trace/ftrace_internal.h @@ -4,28 +4,6 @@ #ifdef CONFIG_FUNCTION_TRACER -/* - * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw_check() is that elements removed from this list - * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw_check() calls are needed to handle - * concurrent insertions into the ftrace_global_list. - * - * Silly Alpha and silly pointer-speculation compiler optimizations! - */ -#define do_for_each_ftrace_op(op, list) \ - op = rcu_dereference_raw_check(list); \ - do - -/* - * Optimized for just a single item in the list (as that is the normal case). - */ -#define while_for_each_ftrace_op(op) \ - while (likely(op = rcu_dereference_raw_check((op)->next)) && \ - unlikely((op) != &ftrace_list_end)) - -extern struct ftrace_ops __rcu *ftrace_ops_list; -extern struct ftrace_ops ftrace_list_end; extern struct mutex ftrace_lock; extern struct ftrace_ops global_ops; diff --git a/kernel/trace/preemptirq_delay_test.c b/kernel/trace/preemptirq_delay_test.c index 31c0fad4cb9e..312d1a0ca3b6 100644 --- a/kernel/trace/preemptirq_delay_test.c +++ b/kernel/trace/preemptirq_delay_test.c @@ -16,6 +16,7 @@ #include <linux/printk.h> #include <linux/string.h> #include <linux/sysfs.h> +#include <linux/completion.h> static ulong delay = 100; static char test_mode[12] = "irq"; @@ -28,6 +29,8 @@ MODULE_PARM_DESC(delay, "Period in microseconds (100 us default)"); MODULE_PARM_DESC(test_mode, "Mode of the test such as preempt, irq, or alternate (default irq)"); MODULE_PARM_DESC(burst_size, "The size of a burst (default 1)"); +static struct completion done; + #define MIN(x, y) ((x) < (y) ? (x) : (y)) static void busy_wait(ulong time) @@ -113,22 +116,47 @@ static int preemptirq_delay_run(void *data) for (i = 0; i < s; i++) (testfuncs[i])(i); + + complete(&done); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + + __set_current_state(TASK_RUNNING); + return 0; } -static struct task_struct *preemptirq_start_test(void) +static int preemptirq_run_test(void) { + struct task_struct *task; char task_name[50]; + init_completion(&done); + snprintf(task_name, sizeof(task_name), "%s_test", test_mode); - return kthread_run(preemptirq_delay_run, NULL, task_name); + task = kthread_run(preemptirq_delay_run, NULL, task_name); + if (IS_ERR(task)) + return PTR_ERR(task); + if (task) { + wait_for_completion(&done); + kthread_stop(task); + } + return 0; } static ssize_t trigger_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { - preemptirq_start_test(); + ssize_t ret; + + ret = preemptirq_run_test(); + if (ret) + return ret; return count; } @@ -148,11 +176,9 @@ static struct kobject *preemptirq_delay_kobj; static int __init preemptirq_delay_init(void) { - struct task_struct *test_task; int retval; - test_task = preemptirq_start_test(); - retval = PTR_ERR_OR_ZERO(test_task); + retval = preemptirq_run_test(); if (retval != 0) return retval; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 6f0b42ceeb00..b8e1ca48be50 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -193,7 +193,7 @@ rb_event_length(struct ring_buffer_event *event) case RINGBUF_TYPE_DATA: return rb_event_data_length(event); default: - BUG(); + WARN_ON_ONCE(1); } /* not hit */ return 0; @@ -249,7 +249,7 @@ rb_event_data(struct ring_buffer_event *event) { if (extended_time(event)) event = skip_time_extend(event); - BUG_ON(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX); + WARN_ON_ONCE(event->type_len > RINGBUF_TYPE_DATA_TYPE_LEN_MAX); /* If length is in len field, then array[0] has the data */ if (event->type_len) return (void *)&event->array[0]; @@ -3727,7 +3727,7 @@ rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer, return; default: - BUG(); + RB_WARN_ON(cpu_buffer, 1); } return; } @@ -3757,7 +3757,7 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter, return; default: - BUG(); + RB_WARN_ON(iter->cpu_buffer, 1); } return; } @@ -4020,7 +4020,7 @@ rb_buffer_peek(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts, return event; default: - BUG(); + RB_WARN_ON(cpu_buffer, 1); } return NULL; @@ -4034,7 +4034,6 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) struct ring_buffer_per_cpu *cpu_buffer; struct ring_buffer_event *event; int nr_loops = 0; - bool failed = false; if (ts) *ts = 0; @@ -4056,19 +4055,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return NULL; /* - * We repeat when a time extend is encountered or we hit - * the end of the page. Since the time extend is always attached - * to a data event, we should never loop more than three times. - * Once for going to next page, once on time extend, and - * finally once to get the event. - * We should never hit the following condition more than thrice, - * unless the buffer is very small, and there's a writer - * that is causing the reader to fail getting an event. + * As the writer can mess with what the iterator is trying + * to read, just give up if we fail to get an event after + * three tries. The iterator is not as reliable when reading + * the ring buffer with an active write as the consumer is. + * Do not warn if the three failures is reached. */ - if (++nr_loops > 3) { - RB_WARN_ON(cpu_buffer, !failed); + if (++nr_loops > 3) return NULL; - } if (rb_per_cpu_empty(cpu_buffer)) return NULL; @@ -4079,10 +4073,8 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) } event = rb_iter_head_event(iter); - if (!event) { - failed = true; + if (!event) goto again; - } switch (event->type_len) { case RINGBUF_TYPE_PADDING: @@ -4117,7 +4109,7 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) return event; default: - BUG(); + RB_WARN_ON(cpu_buffer, 1); } return NULL; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 8d2b98812625..29615f15a820 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -947,7 +947,8 @@ int __trace_bputs(unsigned long ip, const char *str) EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT -void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data) +static void tracing_snapshot_instance_cond(struct trace_array *tr, + void *cond_data) { struct tracer *tracer = tr->current_trace; unsigned long flags; @@ -8525,6 +8526,19 @@ static int allocate_trace_buffers(struct trace_array *tr, int size) */ allocate_snapshot = false; #endif + + /* + * Because of some magic with the way alloc_percpu() works on + * x86_64, we need to synchronize the pgd of all the tables, + * otherwise the trace events that happen in x86_64 page fault + * handlers can't cope with accessing the chance that a + * alloc_percpu()'d memory might be touched in the page fault trace + * event. Oh, and we need to audit all other alloc_percpu() and vmalloc() + * calls in tracing, because something might get triggered within a + * page fault trace event! + */ + vmalloc_sync_mappings(); + return 0; } diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c index 06d7feb5255f..9de29bb45a27 100644 --- a/kernel/trace/trace_boot.c +++ b/kernel/trace/trace_boot.c @@ -95,24 +95,20 @@ trace_boot_add_kprobe_event(struct xbc_node *node, const char *event) struct xbc_node *anode; char buf[MAX_BUF_LEN]; const char *val; - int ret; + int ret = 0; - kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); + xbc_node_for_each_array_value(node, "probes", anode, val) { + kprobe_event_cmd_init(&cmd, buf, MAX_BUF_LEN); - ret = kprobe_event_gen_cmd_start(&cmd, event, NULL); - if (ret) - return ret; + ret = kprobe_event_gen_cmd_start(&cmd, event, val); + if (ret) + break; - xbc_node_for_each_array_value(node, "probes", anode, val) { - ret = kprobe_event_add_field(&cmd, val); + ret = kprobe_event_gen_cmd_end(&cmd); if (ret) - return ret; + pr_err("Failed to add probe: %s\n", buf); } - ret = kprobe_event_gen_cmd_end(&cmd); - if (ret) - pr_err("Failed to add probe: %s\n", buf); - return ret; } #else diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index d0568af4a0ef..35989383ae11 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -453,7 +453,7 @@ static bool __within_notrace_func(unsigned long addr) static bool within_notrace_func(struct trace_kprobe *tk) { - unsigned long addr = addr = trace_kprobe_address(tk); + unsigned long addr = trace_kprobe_address(tk); char symname[KSYM_NAME_LEN], *p; if (!__within_notrace_func(addr)) @@ -940,6 +940,9 @@ EXPORT_SYMBOL_GPL(kprobe_event_cmd_init); * complete command or only the first part of it; in the latter case, * kprobe_event_add_fields() can be used to add more fields following this. * + * Unlikely the synth_event_gen_cmd_start(), @loc must be specified. This + * returns -EINVAL if @loc == NULL. + * * Return: 0 if successful, error otherwise. */ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, @@ -953,6 +956,9 @@ int __kprobe_event_gen_cmd_start(struct dynevent_cmd *cmd, bool kretprobe, if (cmd->type != DYNEVENT_TYPE_KPROBE) return -EINVAL; + if (!loc) + return -EINVAL; + if (kretprobe) snprintf(buf, MAX_EVENT_NAME_LEN, "r:kprobes/%s", name); else diff --git a/kernel/umh.c b/kernel/umh.c index 7f255b5a8845..3474d6aa55d8 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -475,6 +475,12 @@ static void umh_clean_and_save_pid(struct subprocess_info *info) { struct umh_info *umh_info = info->data; + /* cleanup if umh_pipe_setup() was successful but exec failed */ + if (info->pid && info->retval) { + fput(umh_info->pipe_to_umh); + fput(umh_info->pipe_from_umh); + } + argv_free(info->argv); umh_info->pid = info->pid; } @@ -544,6 +550,11 @@ EXPORT_SYMBOL_GPL(fork_usermode_blob); * Runs a user-space application. The application is started * asynchronously if wait is not set, and runs as a child of system workqueues. * (ie. it runs with full root capabilities and optimized affinity). + * + * Note: successful return value does not guarantee the helper was called at + * all. You can't rely on sub_info->{init,cleanup} being called even for + * UMH_WAIT_* wait modes as STATIC_USERMODEHELPER_PATH="" turns all helpers + * into a successful no-op. */ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) { diff --git a/lib/Kconfig.ubsan b/lib/Kconfig.ubsan index 48469c95d78e..929211039bac 100644 --- a/lib/Kconfig.ubsan +++ b/lib/Kconfig.ubsan @@ -60,18 +60,15 @@ config UBSAN_SANITIZE_ALL Enabling this option will get kernel image size increased significantly. -config UBSAN_NO_ALIGNMENT - bool "Disable checking of pointers alignment" - default y if HAVE_EFFICIENT_UNALIGNED_ACCESS +config UBSAN_ALIGNMENT + bool "Enable checks for pointers alignment" + default !HAVE_EFFICIENT_UNALIGNED_ACCESS + depends on !X86 || !COMPILE_TEST help - This option disables the check of unaligned memory accesses. - This option should be used when building allmodconfig. - Disabling this option on architectures that support unaligned + This option enables the check of unaligned memory accesses. + Enabling this option on architectures that support unaligned accesses may produce a lot of false positives. -config UBSAN_ALIGNMENT - def_bool !UBSAN_NO_ALIGNMENT - config TEST_UBSAN tristate "Module for testing for undefined behavior detection" depends on m diff --git a/lib/vsprintf.c b/lib/vsprintf.c index 7c488a1ce318..532b6606a18a 100644 --- a/lib/vsprintf.c +++ b/lib/vsprintf.c @@ -2168,6 +2168,10 @@ char *fwnode_string(char *buf, char *end, struct fwnode_handle *fwnode, * f full name * P node name, including a possible unit address * - 'x' For printing the address. Equivalent to "%lx". + * - '[ku]s' For a BPF/tracing related format specifier, e.g. used out of + * bpf_trace_printk() where [ku] prefix specifies either kernel (k) + * or user (u) memory to probe, and: + * s a string, equivalent to "%s" on direct vsnprintf() use * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst @@ -2251,6 +2255,14 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr, if (!IS_ERR(ptr)) break; return err_ptr(buf, end, ptr, spec); + case 'u': + case 'k': + switch (fmt[1]) { + case 's': + return string(buf, end, ptr, spec); + default: + return error_string(buf, end, "(einval)", spec); + } } /* default is to _not_ leak addresses, hash before printing */ diff --git a/mm/backing-dev.c b/mm/backing-dev.c index c81b4f3a7268..efc5b83acd2d 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -21,7 +21,7 @@ struct backing_dev_info noop_backing_dev_info = { EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; -const char *bdi_unknown_name = "(unknown)"; +static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU @@ -938,7 +938,8 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; - dev = device_create_vargs(bdi_class, NULL, MKDEV(0, 0), bdi, fmt, args); + vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); + dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); @@ -1043,6 +1044,14 @@ void bdi_put(struct backing_dev_info *bdi) } EXPORT_SYMBOL(bdi_put); +const char *bdi_dev_name(struct backing_dev_info *bdi) +{ + if (!bdi || !bdi->dev) + return bdi_unknown_name; + return bdi->dev_name; +} +EXPORT_SYMBOL_GPL(bdi_dev_name); + static wait_queue_head_t congestion_wqh[2] = { __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) @@ -1218,6 +1218,10 @@ retry: if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; + if ((fault_flags & FAULT_FLAG_KILLABLE) && + fatal_signal_pending(current)) + return -EINTR; + ret = handle_mm_fault(vma, address, fault_flags); major |= ret & VM_FAULT_MAJOR; if (ret & VM_FAULT_ERROR) { @@ -1230,11 +1234,9 @@ retry: if (ret & VM_FAULT_RETRY) { down_read(&mm->mmap_sem); - if (!(fault_flags & FAULT_FLAG_TRIED)) { - *unlocked = true; - fault_flags |= FAULT_FLAG_TRIED; - goto retry; - } + *unlocked = true; + fault_flags |= FAULT_FLAG_TRIED; + goto retry; } if (tsk) { diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 08b43de2383b..434d503a6525 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -1,23 +1,28 @@ # SPDX-License-Identifier: GPL-2.0 KASAN_SANITIZE := n -UBSAN_SANITIZE_common.o := n -UBSAN_SANITIZE_generic.o := n -UBSAN_SANITIZE_generic_report.o := n -UBSAN_SANITIZE_tags.o := n +UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +# Disable ftrace to avoid recursion. CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_quarantine.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_report.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_tags_report.o = $(CC_FLAGS_FTRACE) # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 - CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_init.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_quarantine.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) +CFLAGS_tags_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) obj-$(CONFIG_KASAN) := common.o init.o report.o obj-$(CONFIG_KASAN_GENERIC) += generic.o generic_report.o quarantine.o diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index e8f37199d885..cfade6413528 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -212,8 +212,6 @@ static inline const void *arch_kasan_set_tag(const void *addr, u8 tag) asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); void __asan_register_globals(struct kasan_global *globals, size_t size); void __asan_unregister_globals(struct kasan_global *globals, size_t size); -void __asan_loadN(unsigned long addr, size_t size); -void __asan_storeN(unsigned long addr, size_t size); void __asan_handle_no_return(void); void __asan_alloca_poison(unsigned long addr, size_t size); void __asan_allocas_unpoison(const void *stack_top, const void *stack_bottom); @@ -228,6 +226,8 @@ void __asan_load8(unsigned long addr); void __asan_store8(unsigned long addr); void __asan_load16(unsigned long addr); void __asan_store16(unsigned long addr); +void __asan_loadN(unsigned long addr, size_t size); +void __asan_storeN(unsigned long addr, size_t size); void __asan_load1_noabort(unsigned long addr); void __asan_store1_noabort(unsigned long addr); @@ -239,6 +239,21 @@ void __asan_load8_noabort(unsigned long addr); void __asan_store8_noabort(unsigned long addr); void __asan_load16_noabort(unsigned long addr); void __asan_store16_noabort(unsigned long addr); +void __asan_loadN_noabort(unsigned long addr, size_t size); +void __asan_storeN_noabort(unsigned long addr, size_t size); + +void __asan_report_load1_noabort(unsigned long addr); +void __asan_report_store1_noabort(unsigned long addr); +void __asan_report_load2_noabort(unsigned long addr); +void __asan_report_store2_noabort(unsigned long addr); +void __asan_report_load4_noabort(unsigned long addr); +void __asan_report_store4_noabort(unsigned long addr); +void __asan_report_load8_noabort(unsigned long addr); +void __asan_report_store8_noabort(unsigned long addr); +void __asan_report_load16_noabort(unsigned long addr); +void __asan_report_store16_noabort(unsigned long addr); +void __asan_report_load_n_noabort(unsigned long addr, size_t size); +void __asan_report_store_n_noabort(unsigned long addr, size_t size); void __asan_set_shadow_00(const void *addr, size_t size); void __asan_set_shadow_f1(const void *addr, size_t size); @@ -247,4 +262,19 @@ void __asan_set_shadow_f3(const void *addr, size_t size); void __asan_set_shadow_f5(const void *addr, size_t size); void __asan_set_shadow_f8(const void *addr, size_t size); +void __hwasan_load1_noabort(unsigned long addr); +void __hwasan_store1_noabort(unsigned long addr); +void __hwasan_load2_noabort(unsigned long addr); +void __hwasan_store2_noabort(unsigned long addr); +void __hwasan_load4_noabort(unsigned long addr); +void __hwasan_store4_noabort(unsigned long addr); +void __hwasan_load8_noabort(unsigned long addr); +void __hwasan_store8_noabort(unsigned long addr); +void __hwasan_load16_noabort(unsigned long addr); +void __hwasan_store16_noabort(unsigned long addr); +void __hwasan_loadN_noabort(unsigned long addr, size_t size); +void __hwasan_storeN_noabort(unsigned long addr, size_t size); + +void __hwasan_tag_memory(unsigned long addr, u8 tag, unsigned long size); + #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 5beea03dd58a..a3b97f103966 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4990,19 +4990,22 @@ static struct mem_cgroup *mem_cgroup_alloc(void) unsigned int size; int node; int __maybe_unused i; + long error = -ENOMEM; size = sizeof(struct mem_cgroup); size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); memcg = kzalloc(size, GFP_KERNEL); if (!memcg) - return NULL; + return ERR_PTR(error); memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX, GFP_KERNEL); - if (memcg->id.id < 0) + if (memcg->id.id < 0) { + error = memcg->id.id; goto fail; + } memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu); if (!memcg->vmstats_local) @@ -5046,7 +5049,7 @@ static struct mem_cgroup *mem_cgroup_alloc(void) fail: mem_cgroup_id_remove(memcg); __mem_cgroup_free(memcg); - return NULL; + return ERR_PTR(error); } static struct cgroup_subsys_state * __ref @@ -5057,8 +5060,8 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) long error = -ENOMEM; memcg = mem_cgroup_alloc(); - if (!memcg) - return ERR_PTR(error); + if (IS_ERR(memcg)) + return ERR_CAST(memcg); WRITE_ONCE(memcg->high, PAGE_COUNTER_MAX); memcg->soft_limit = PAGE_COUNTER_MAX; @@ -5108,7 +5111,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) fail: mem_cgroup_id_remove(memcg); mem_cgroup_free(memcg); - return ERR_PTR(-ENOMEM); + return ERR_PTR(error); } static int mem_cgroup_css_online(struct cgroup_subsys_state *css) diff --git a/mm/mremap.c b/mm/mremap.c index c881abeba0bf..6aa6ea605068 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -794,7 +794,7 @@ out: if (locked && new_len > old_len) mm_populate(new_addr + old_len, new_len - old_len); userfaultfd_unmap_complete(mm, &uf_unmap_early); - mremap_userfaultfd_complete(&uf, addr, new_addr, old_len); + mremap_userfaultfd_complete(&uf, addr, ret, old_len); userfaultfd_unmap_complete(mm, &uf_unmap); return ret; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 69827d4fa052..13cc653122b7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1607,6 +1607,7 @@ void set_zone_contiguous(struct zone *zone) if (!__pageblock_pfn_to_page(block_start_pfn, block_end_pfn, zone)) return; + cond_resched(); } /* We confirm that there is no hole */ @@ -2400,6 +2401,14 @@ static inline void boost_watermark(struct zone *zone) if (!watermark_boost_factor) return; + /* + * Don't bother in zones that are unlikely to produce results. + * On small machines, including kdump capture kernels running + * in a small area, boosting the watermark can cause an out of + * memory situation immediately. + */ + if ((pageblock_nr_pages * 4) > zone_managed_pages(zone)) + return; max_boost = mult_frac(zone->_watermark[WMARK_HIGH], watermark_boost_factor, 10000); diff --git a/mm/percpu.c b/mm/percpu.c index d7e3bc649f4e..7da7d7737dab 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -80,6 +80,7 @@ #include <linux/workqueue.h> #include <linux/kmemleak.h> #include <linux/sched.h> +#include <linux/sched/mm.h> #include <asm/cacheflush.h> #include <asm/sections.h> @@ -1557,10 +1558,9 @@ static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr) static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, gfp_t gfp) { - /* whitelisted flags that can be passed to the backing allocators */ - gfp_t pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; - bool do_warn = !(gfp & __GFP_NOWARN); + gfp_t pcpu_gfp; + bool is_atomic; + bool do_warn; static int warn_limit = 10; struct pcpu_chunk *chunk, *next; const char *err; @@ -1569,6 +1569,12 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, void __percpu *ptr; size_t bits, bit_align; + gfp = current_gfp_context(gfp); + /* whitelisted flags that can be passed to the backing allocators */ + pcpu_gfp = gfp & (GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); + is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL; + do_warn = !(gfp & __GFP_NOWARN); + /* * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE, * therefore alignment must be a minimum of that many bytes. diff --git a/mm/slub.c b/mm/slub.c index 9bf44955c4f1..b762450fc9f0 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -551,15 +551,32 @@ static void print_section(char *level, char *text, u8 *addr, metadata_access_disable(); } +/* + * See comment in calculate_sizes(). + */ +static inline bool freeptr_outside_object(struct kmem_cache *s) +{ + return s->offset >= s->inuse; +} + +/* + * Return offset of the end of info block which is inuse + free pointer if + * not overlapping with object. + */ +static inline unsigned int get_info_end(struct kmem_cache *s) +{ + if (freeptr_outside_object(s)) + return s->inuse + sizeof(void *); + else + return s->inuse; +} + static struct track *get_track(struct kmem_cache *s, void *object, enum track_item alloc) { struct track *p; - if (s->offset) - p = object + s->offset + sizeof(void *); - else - p = object + s->inuse; + p = object + get_info_end(s); return p + alloc; } @@ -686,10 +703,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); - if (s->offset) - off = s->offset + sizeof(void *); - else - off = s->inuse; + off = get_info_end(s); if (s->flags & SLAB_STORE_USER) off += 2 * sizeof(struct track); @@ -782,7 +796,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * object address * Bytes of the object to be managed. * If the freepointer may overlay the object then the free - * pointer is the first word of the object. + * pointer is at the middle of the object. * * Poisoning uses 0x6b (POISON_FREE) and the last byte is * 0xa5 (POISON_END) @@ -816,11 +830,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) { - unsigned long off = s->inuse; /* The end of info */ - - if (s->offset) - /* Freepointer is placed after the object. */ - off += sizeof(void *); + unsigned long off = get_info_end(s); /* The end of info */ if (s->flags & SLAB_STORE_USER) /* We also have user information there */ @@ -907,7 +917,7 @@ static int check_object(struct kmem_cache *s, struct page *page, check_pad_bytes(s, page, p); } - if (!s->offset && val == SLUB_RED_ACTIVE) + if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE) /* * Object and freepointer overlap. Cannot check * freepointer while object is allocated. @@ -3587,6 +3597,11 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * * This is the case if we do RCU, have a constructor or * destructor or are poisoning the objects. + * + * The assumption that s->offset >= s->inuse means free + * pointer is outside of the object is used in the + * freeptr_outside_object() function. If that is no + * longer true, the function needs to be modified. */ s->offset = size; size += sizeof(void *); diff --git a/mm/vmscan.c b/mm/vmscan.c index b06868fc4926..a37c87b5aee2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1625,7 +1625,6 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec, * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. * @sc: The scan_control struct for this reclaim session - * @mode: One of the LRU isolation modes * @lru: LRU list id for isolating * * returns how many pages were moved onto *@dst. diff --git a/net/atm/common.c b/net/atm/common.c index 0ce530af534d..8575f5d52087 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -177,18 +177,18 @@ static void vcc_destroy_socket(struct sock *sk) set_bit(ATM_VF_CLOSE, &vcc->flags); clear_bit(ATM_VF_READY, &vcc->flags); - if (vcc->dev) { - if (vcc->dev->ops->close) - vcc->dev->ops->close(vcc); - if (vcc->push) - vcc->push(vcc, NULL); /* atmarpd has no push */ - module_put(vcc->owner); - - while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { - atm_return(vcc, skb->truesize); - kfree_skb(skb); - } + if (vcc->dev && vcc->dev->ops->close) + vcc->dev->ops->close(vcc); + if (vcc->push) + vcc->push(vcc, NULL); /* atmarpd has no push */ + module_put(vcc->owner); + + while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) { + atm_return(vcc, skb->truesize); + kfree_skb(skb); + } + if (vcc->dev && vcc->dev->ops->owner) { module_put(vcc->dev->ops->owner); atm_dev_put(vcc->dev); } diff --git a/net/atm/lec.c b/net/atm/lec.c index 25fa3a7b72bd..ca37f5a71f5e 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1264,6 +1264,12 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) entry->vcc = NULL; } if (entry->recv_vcc) { + struct atm_vcc *vcc = entry->recv_vcc; + struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); + + kfree(vpriv); + vcc->user_back = NULL; + entry->recv_vcc->push = entry->old_recv_push; vcc_release_async(entry->recv_vcc, -EPIPE); entry->recv_vcc = NULL; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 969466218999..80b87b1f4e3a 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -893,7 +893,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, orig_node = batadv_v_ogm_orig_get(bat_priv, ogm_packet->orig); if (!orig_node) - return; + goto out; neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming, ethhdr->h_source); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 8f0717c3f7b5..b0469d15da0e 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1009,15 +1009,8 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, */ static u8 batadv_nc_random_weight_tq(u8 tq) { - u8 rand_val, rand_tq; - - get_random_bytes(&rand_val, sizeof(rand_val)); - /* randomize the estimated packet loss (max TQ - estimated TQ) */ - rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq); - - /* normalize the randomized packet loss */ - rand_tq /= BATADV_TQ_MAX_VALUE; + u8 rand_tq = prandom_u32_max(BATADV_TQ_MAX_VALUE + 1 - tq); /* convert to (randomized) estimated tq again */ return BATADV_TQ_MAX_VALUE - rand_tq; diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index c45962d8527b..0f962dcd239e 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1150,7 +1150,7 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, ret = batadv_parse_throughput(net_dev, buff, "throughput_override", &tp_override); if (!ret) - return count; + goto out; old_tp_override = atomic_read(&hard_iface->bat_v.throughput_override); if (old_tp_override == tp_override) @@ -1190,6 +1190,7 @@ static ssize_t batadv_show_throughput_override(struct kobject *kobj, tp_override = atomic_read(&hard_iface->bat_v.throughput_override); + batadv_hardif_put(hard_iface); return sprintf(buff, "%u.%u MBit\n", tp_override / 10, tp_override % 10); } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 43dab4066f91..a0f5dbee8f9c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -612,6 +612,7 @@ int br_process_vlan_info(struct net_bridge *br, v - 1, rtm_cmd); v_change_start = 0; } + cond_resched(); } /* v_change_start is set only if the last/whole range changed */ if (v_change_start) diff --git a/net/core/dev.c b/net/core/dev.c index 522288177bbd..6d327b7aa813 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8907,11 +8907,13 @@ static void netdev_sync_lower_features(struct net_device *upper, netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); lower->wanted_features &= ~feature; - netdev_update_features(lower); + __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); + else + netdev_features_change(lower); } } } diff --git a/net/core/devlink.c b/net/core/devlink.c index 80f97722f31f..899edcee7dab 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4283,6 +4283,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); dump = false; + + if (start_offset == end_offset) { + err = 0; + goto nla_put_failure; + } } err = devlink_nl_region_read_snapshot_fill(skb, devlink, @@ -5363,6 +5368,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter, { enum devlink_health_reporter_state prev_health_state; struct devlink *devlink = reporter->devlink; + unsigned long recover_ts_threshold; /* write a log message of the current error */ WARN_ON(!msg); @@ -5373,10 +5379,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter, devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); /* abort if the previous error wasn't recovered */ + recover_ts_threshold = reporter->last_recovery_ts + + msecs_to_jiffies(reporter->graceful_period); if (reporter->auto_recover && (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || - jiffies - reporter->last_recovery_ts < - msecs_to_jiffies(reporter->graceful_period))) { + (reporter->last_recovery_ts && reporter->recovery_count && + time_is_after_jiffies(recover_ts_threshold)))) { trace_devlink_health_recover_aborted(devlink, reporter->ops->name, reporter->health_state, diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 8e33cec9fc4e..2ee7bc4c9e03 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -213,6 +213,7 @@ static void sched_send_work(struct timer_list *t) static void trace_drop_common(struct sk_buff *skb, void *location) { struct net_dm_alert_msg *msg; + struct net_dm_drop_point *point; struct nlmsghdr *nlh; struct nlattr *nla; int i; @@ -231,11 +232,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location) nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); + point = msg->points; for (i = 0; i < msg->entries; i++) { - if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { - msg->points[i].count++; + if (!memcmp(&location, &point->pc, sizeof(void *))) { + point->count++; goto out; } + point++; } if (msg->entries == dm_hit_limit) goto out; @@ -244,8 +247,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location) */ __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); - memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); - msg->points[msg->entries].count = 1; + memcpy(point->pc, &location, sizeof(void *)); + point->count = 1; msg->entries++; if (!timer_pending(&data->send_timer)) { diff --git a/net/core/filter.c b/net/core/filter.c index 7d6ceaa54d21..5cc9276f1023 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2590,8 +2590,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, } pop = 0; } else if (pop >= sge->length - a) { - sge->length = a; pop -= (sge->length - a); + sge->length = a; } } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 39d37d0ef575..116139233d57 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1956,6 +1956,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, NEIGH_UPDATE_F_OVERRIDE_ISROUTER); } + if (protocol) + neigh->protocol = protocol; + if (ndm->ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; @@ -1969,9 +1972,6 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); - if (protocol) - neigh->protocol = protocol; - neigh_release(neigh); out: diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 8881dd943dd0..9bd4cab7d510 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -236,6 +236,8 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct task_struct *p; struct cgroup_subsys_state *css; + cgroup_sk_alloc_disable(); + cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->id; diff --git a/net/core/sock.c b/net/core/sock.c index 90509c37d291..b714162213ae 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2364,7 +2364,6 @@ static void sk_leave_memory_pressure(struct sock *sk) } } -/* On 32bit arches, an skb frag is limited to 2^15 */ #define SKB_FRAG_PAGE_ORDER get_order(32768) DEFINE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 9a271a58a41d..d90665b465b8 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -459,7 +459,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) list_for_each_entry(dp, &dst->ports, list) { err = dsa_port_setup(dp); if (err) - goto teardown; + continue; } return 0; diff --git a/net/dsa/master.c b/net/dsa/master.c index b5c535af63a3..a621367c6e8c 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -289,7 +289,8 @@ static void dsa_master_ndo_teardown(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; - dev->netdev_ops = cpu_dp->orig_ndo_ops; + if (cpu_dp->orig_ndo_ops) + dev->netdev_ops = cpu_dp->orig_ndo_ops; cpu_dp->orig_ndo_ops = NULL; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d1068803cd11..62f4ee3da172 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -856,20 +856,18 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev, struct dsa_port *to_dp; int err; - act = &cls->rule->action.entries[0]; - if (!ds->ops->port_mirror_add) return -EOPNOTSUPP; - if (!act->dev) - return -EINVAL; - if (!flow_action_basic_hw_stats_check(&cls->rule->action, cls->common.extack)) return -EOPNOTSUPP; act = &cls->rule->action.entries[0]; + if (!act->dev) + return -EINVAL; + if (!dsa_slave_dev_check(act->dev)) return -EOPNOTSUPP; diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index f4b9f7a3ce51..25b6ffba26cd 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -18,7 +18,7 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) { struct sk_buff *skb = *pskb; struct hsr_port *port; - u16 protocol; + __be16 protocol; if (!skb_mac_header_was_set(skb)) { WARN_ONCE(1, "%s: skb invalid", __func__); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 0bd10a1f477f..a23094b050f8 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; @@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 9cf83cc85e4a..5c218db2dede 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -109,8 +109,10 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags); static void ipmr_expire_process(struct timer_list *t); #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES -#define ipmr_for_each_table(mrt, net) \ - list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list) +#define ipmr_for_each_table(mrt, net) \ + list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list, \ + lockdep_rtnl_is_held() || \ + list_empty(&net->ipv4.mr_tables)) static struct mr_table *ipmr_mr_table_iter(struct net *net, struct mr_table *mrt) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 788c69d9bfe0..fa829f31a3f5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -915,7 +915,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* Check for load limit; set rate_last to the latest sent * redirect. */ - if (peer->rate_tokens == 0 || + if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6d87de434377..dd401757eea1 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -476,9 +476,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) || - (sk->sk_prot->stream_memory_read ? - sk->sk_prot->stream_memory_read(sk) : false); + int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); + + if (avail > 0) { + if (avail >= target) + return true; + if (tcp_rmem_pressure(sk)) + return true; + } + if (sk->sk_prot->stream_memory_read) + return sk->sk_prot->stream_memory_read(sk); + return false; } /* @@ -1756,10 +1764,11 @@ static int tcp_zerocopy_receive(struct sock *sk, down_read(¤t->mm->mmap_sem); - ret = -EINVAL; vma = find_vma(current->mm, address); - if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) - goto out; + if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) { + up_read(¤t->mm->mmap_sem); + return -EINVAL; + } zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); tp = tcp_sk(sk); @@ -2154,13 +2163,15 @@ skip_copy: tp->urg_data = 0; tcp_fast_path_check(sk); } - if (used + offset < skb->len) - continue; if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); cmsg_flags |= 2; } + + if (used + offset < skb->len) + continue; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 5a05327f97c1..629aaa9a1eb9 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -125,7 +125,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - msg->sg.size -= apply_bytes; sk_psock_queue_msg(psock, tmp); sk_psock_data_ready(sk, psock); } else { @@ -262,14 +261,17 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, struct sk_psock *psock; int copied, ret; + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); if (!skb_queue_empty(&sk->sk_receive_queue) && - sk_psock_queue_empty(psock)) + sk_psock_queue_empty(psock)) { + sk_psock_put(sk, psock); return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + } lock_sock(sk); msg_bytes_ready: copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bf4ced9273e8..29c6fc8c7716 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3926,10 +3926,6 @@ void tcp_parse_options(const struct net *net, */ break; #endif - case TCPOPT_MPTCP: - mptcp_parse_option(skb, ptr, opsize, opt_rx); - break; - case TCPOPT_FASTOPEN: tcp_parse_fastopen_option( opsize - TCPOLEN_FASTOPEN_BASE, @@ -4761,7 +4757,8 @@ void tcp_data_ready(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); int avail = tp->rcv_nxt - tp->copied_seq; - if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE)) + if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && + !sock_flag(sk, SOCK_DONE)) return; sk->sk_data_ready(sk); @@ -5990,9 +5987,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); - if (sk_is_mptcp(sk)) - mptcp_rcv_synsent(sk); - /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 221c81f85cbf..8d3f66c310db 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1047,7 +1047,8 @@ static int calipso_opt_getattr(const unsigned char *calipso, goto getattr_return; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } secattr->type = NETLBL_NLTYPE_CALIPSO; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 310cbddaa533..ff847a324220 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1385,9 +1385,18 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) } ip6_rt_copy_init(pcpu_rt, res); pcpu_rt->rt6i_flags |= RTF_PCPU; + + if (f6i->nh) + pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev)); + return pcpu_rt; } +static bool rt6_is_valid(const struct rt6_info *rt6) +{ + return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev)); +} + /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { @@ -1395,6 +1404,19 @@ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); + if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) { + struct rt6_info *prev, **p; + + p = this_cpu_ptr(res->nh->rt6i_pcpu); + prev = xchg(p, NULL); + if (prev) { + dst_dev_put(&prev->dst); + dst_release(&prev->dst); + } + + pcpu_rt = NULL; + } + return pcpu_rt; } @@ -2593,6 +2615,9 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = container_of(dst, struct rt6_info, dst); + if (rt->sernum) + return rt6_is_valid(rt) ? dst : NULL; + rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value @@ -2697,8 +2722,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = (struct rt6_info *)dst; - if (dst_metric_locked(dst, RTAX_MTU)) - return; + /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) + * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. + * [see also comment in rt6_mtu_change_route()] + */ if (iph) { daddr = &iph->daddr; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 4c7e0a27fa9c..37b434293bda 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -27,8 +27,9 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) { - int trailing; unsigned int tlv_offset; + int max_last_entry; + int trailing; if (srh->type != IPV6_SRCRT_TYPE_4) return false; @@ -36,7 +37,12 @@ bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len) if (((srh->hdrlen + 1) << 3) != len) return false; - if (srh->segments_left > srh->first_segment) + max_last_entry = (srh->hdrlen / 2) - 1; + + if (srh->first_segment > max_last_entry) + return false; + + if (srh->segments_left > srh->first_segment + 1) return false; tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 4a7c467b99db..45497af23906 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -16,10 +16,10 @@ static bool mptcp_cap_flag_sha256(u8 flags) return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256; } -void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, - int opsize, struct tcp_options_received *opt_rx) +static void mptcp_parse_option(const struct sk_buff *skb, + const unsigned char *ptr, int opsize, + struct mptcp_options_received *mp_opt) { - struct mptcp_options_received *mp_opt = &opt_rx->mptcp; u8 subtype = *ptr >> 4; int expected_opsize; u8 version; @@ -283,12 +283,20 @@ void mptcp_parse_option(const struct sk_buff *skb, const unsigned char *ptr, } void mptcp_get_options(const struct sk_buff *skb, - struct tcp_options_received *opt_rx) + struct mptcp_options_received *mp_opt) { - const unsigned char *ptr; const struct tcphdr *th = tcp_hdr(skb); - int length = (th->doff * 4) - sizeof(struct tcphdr); + const unsigned char *ptr; + int length; + + /* initialize option status */ + mp_opt->mp_capable = 0; + mp_opt->mp_join = 0; + mp_opt->add_addr = 0; + mp_opt->rm_addr = 0; + mp_opt->dss = 0; + length = (th->doff * 4) - sizeof(struct tcphdr); ptr = (const unsigned char *)(th + 1); while (length > 0) { @@ -308,7 +316,7 @@ void mptcp_get_options(const struct sk_buff *skb, if (opsize > length) return; /* don't parse partial options */ if (opcode == TCPOPT_MPTCP) - mptcp_parse_option(skb, ptr, opsize, opt_rx); + mptcp_parse_option(skb, ptr, opsize, mp_opt); ptr += opsize - 2; length -= opsize; } @@ -344,28 +352,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, return false; } -void mptcp_rcv_synsent(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - struct tcp_sock *tp = tcp_sk(sk); - - if (subflow->request_mptcp && tp->rx_opt.mptcp.mp_capable) { - subflow->mp_capable = 1; - subflow->can_ack = 1; - subflow->remote_key = tp->rx_opt.mptcp.sndr_key; - pr_debug("subflow=%p, remote_key=%llu", subflow, - subflow->remote_key); - } else if (subflow->request_join && tp->rx_opt.mptcp.mp_join) { - subflow->mp_join = 1; - subflow->thmac = tp->rx_opt.mptcp.thmac; - subflow->remote_nonce = tp->rx_opt.mptcp.nonce; - pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow, - subflow->thmac, subflow->remote_nonce); - } else if (subflow->request_mptcp) { - tcp_sk(sk)->is_mptcp = 0; - } -} - /* MP_JOIN client subflow must wait for 4th ack before sending any data: * TCP can't schedule delack timer before the subflow is fully established. * MPTCP uses the delack timer to do 3rd ack retransmissions @@ -709,7 +695,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) return subflow->mp_capable; - if (mp_opt->use_ack) { + if (mp_opt->dss && mp_opt->use_ack) { /* subflows are fully established as soon as we get any * additional ack. */ @@ -717,8 +703,6 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, goto fully_established; } - WARN_ON_ONCE(subflow->can_ack); - /* If the first established packet does not contain MP_CAPABLE + data * then fallback to TCP */ @@ -728,6 +712,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk, return false; } + if (unlikely(!READ_ONCE(msk->pm.server_side))) + pr_warn_once("bogus mpc option on established client sk"); subflow->fully_established = 1; subflow->remote_key = mp_opt->sndr_key; subflow->can_ack = 1; @@ -819,41 +805,41 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - struct mptcp_options_received *mp_opt; + struct mptcp_options_received mp_opt; struct mptcp_ext *mpext; - mp_opt = &opt_rx->mptcp; - if (!check_fully_established(msk, sk, subflow, skb, mp_opt)) + mptcp_get_options(skb, &mp_opt); + if (!check_fully_established(msk, sk, subflow, skb, &mp_opt)) return; - if (mp_opt->add_addr && add_addr_hmac_valid(msk, mp_opt)) { + if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) { struct mptcp_addr_info addr; - addr.port = htons(mp_opt->port); - addr.id = mp_opt->addr_id; - if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) { + addr.port = htons(mp_opt.port); + addr.id = mp_opt.addr_id; + if (mp_opt.family == MPTCP_ADDR_IPVERSION_4) { addr.family = AF_INET; - addr.addr = mp_opt->addr; + addr.addr = mp_opt.addr; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) - else if (mp_opt->family == MPTCP_ADDR_IPVERSION_6) { + else if (mp_opt.family == MPTCP_ADDR_IPVERSION_6) { addr.family = AF_INET6; - addr.addr6 = mp_opt->addr6; + addr.addr6 = mp_opt.addr6; } #endif - if (!mp_opt->echo) + if (!mp_opt.echo) mptcp_pm_add_addr_received(msk, &addr); - mp_opt->add_addr = 0; + mp_opt.add_addr = 0; } - if (!mp_opt->dss) + if (!mp_opt.dss) return; /* we can't wait for recvmsg() to update the ack_seq, otherwise * monodirectional flows will stuck */ - if (mp_opt->use_ack) - update_una(msk, mp_opt); + if (mp_opt.use_ack) + update_una(msk, &mp_opt); mpext = skb_ext_add(skb, SKB_EXT_MPTCP); if (!mpext) @@ -861,8 +847,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, memset(mpext, 0, sizeof(*mpext)); - if (mp_opt->use_map) { - if (mp_opt->mpc_map) { + if (mp_opt.use_map) { + if (mp_opt.mpc_map) { /* this is an MP_CAPABLE carrying MPTCP data * we know this map the first chunk of data */ @@ -872,13 +858,14 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, mpext->subflow_seq = 1; mpext->dsn64 = 1; mpext->mpc_map = 1; + mpext->data_fin = 0; } else { - mpext->data_seq = mp_opt->data_seq; - mpext->subflow_seq = mp_opt->subflow_seq; - mpext->dsn64 = mp_opt->dsn64; - mpext->data_fin = mp_opt->data_fin; + mpext->data_seq = mp_opt.data_seq; + mpext->subflow_seq = mp_opt.subflow_seq; + mpext->dsn64 = mp_opt.dsn64; + mpext->data_fin = mp_opt.data_fin; } - mpext->data_len = mp_opt->data_len; + mpext->data_len = mp_opt.data_len; mpext->use_map = 1; } } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b22a63ba2348..32ea8d35489a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1316,11 +1316,12 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) static int mptcp_disconnect(struct sock *sk, int flags) { - lock_sock(sk); - __mptcp_clear_xmit(sk); - release_sock(sk); - mptcp_cancel_work(sk); - return tcp_disconnect(sk, flags); + /* Should never be called. + * inet_stream_connect() calls ->disconnect, but that + * refers to the subflow socket, not the mptcp one. + */ + WARN_ON_ONCE(1); + return 0; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -1333,7 +1334,7 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) #endif struct sock *mptcp_sk_clone(const struct sock *sk, - const struct tcp_options_received *opt_rx, + const struct mptcp_options_received *mp_opt, struct request_sock *req) { struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); @@ -1372,9 +1373,9 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->write_seq = subflow_req->idsn + 1; atomic64_set(&msk->snd_una, msk->write_seq); - if (opt_rx->mptcp.mp_capable) { + if (mp_opt->mp_capable) { msk->can_ack = true; - msk->remote_key = opt_rx->mptcp.sndr_key; + msk->remote_key = mp_opt->sndr_key; mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); ack_seq++; msk->ack_seq = ack_seq; @@ -1628,6 +1629,8 @@ bool mptcp_finish_join(struct sock *sk) ret = mptcp_pm_allow_new_subflow(msk); if (ret) { + subflow->map_seq = msk->ack_seq; + /* active connections are already on conn_list */ spin_lock_bh(&msk->join_list_lock); if (!WARN_ON_ONCE(!list_empty(&subflow->node))) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index a2b3048037d0..e4ca6320ce76 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -91,6 +91,45 @@ #define MPTCP_WORK_RTX 2 #define MPTCP_WORK_EOF 3 +struct mptcp_options_received { + u64 sndr_key; + u64 rcvr_key; + u64 data_ack; + u64 data_seq; + u32 subflow_seq; + u16 data_len; + u16 mp_capable : 1, + mp_join : 1, + dss : 1, + add_addr : 1, + rm_addr : 1, + family : 4, + echo : 1, + backup : 1; + u32 token; + u32 nonce; + u64 thmac; + u8 hmac[20]; + u8 join_id; + u8 use_map:1, + dsn64:1, + data_fin:1, + use_ack:1, + ack64:1, + mpc_map:1, + __unused:2; + u8 addr_id; + u8 rm_id; + union { + struct in_addr addr; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + struct in6_addr addr6; +#endif + }; + u64 ahmac; + u16 port; +}; + static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field) { return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) | @@ -331,10 +370,10 @@ int mptcp_proto_v6_init(void); #endif struct sock *mptcp_sk_clone(const struct sock *sk, - const struct tcp_options_received *opt_rx, + const struct mptcp_options_received *mp_opt, struct request_sock *req); void mptcp_get_options(const struct sk_buff *skb, - struct tcp_options_received *opt_rx); + struct mptcp_options_received *mp_opt); void mptcp_finish_connect(struct sock *sk); void mptcp_data_ready(struct sock *sk, struct sock *ssk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index fabd06f2ff45..4931a29a6f08 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -124,12 +124,11 @@ static void subflow_init_req(struct request_sock *req, { struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener); struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req); - struct tcp_options_received rx_opt; + struct mptcp_options_received mp_opt; pr_debug("subflow_req=%p, listener=%p", subflow_req, listener); - memset(&rx_opt.mptcp, 0, sizeof(rx_opt.mptcp)); - mptcp_get_options(skb, &rx_opt); + mptcp_get_options(skb, &mp_opt); subflow_req->mp_capable = 0; subflow_req->mp_join = 0; @@ -142,16 +141,16 @@ static void subflow_init_req(struct request_sock *req, return; #endif - if (rx_opt.mptcp.mp_capable) { + if (mp_opt.mp_capable) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE); - if (rx_opt.mptcp.mp_join) + if (mp_opt.mp_join) return; - } else if (rx_opt.mptcp.mp_join) { + } else if (mp_opt.mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); } - if (rx_opt.mptcp.mp_capable && listener->request_mptcp) { + if (mp_opt.mp_capable && listener->request_mptcp) { int err; err = mptcp_token_new_request(req); @@ -159,13 +158,13 @@ static void subflow_init_req(struct request_sock *req, subflow_req->mp_capable = 1; subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; - } else if (rx_opt.mptcp.mp_join && listener->request_mptcp) { + } else if (mp_opt.mp_join && listener->request_mptcp) { subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq; subflow_req->mp_join = 1; - subflow_req->backup = rx_opt.mptcp.backup; - subflow_req->remote_id = rx_opt.mptcp.join_id; - subflow_req->token = rx_opt.mptcp.token; - subflow_req->remote_nonce = rx_opt.mptcp.nonce; + subflow_req->backup = mp_opt.backup; + subflow_req->remote_id = mp_opt.join_id; + subflow_req->token = mp_opt.token; + subflow_req->remote_nonce = mp_opt.nonce; pr_debug("token=%u, remote_nonce=%u", subflow_req->token, subflow_req->remote_nonce); if (!subflow_token_join_request(req, skb)) { @@ -221,23 +220,47 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow) static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + struct mptcp_options_received mp_opt; struct sock *parent = subflow->conn; + struct tcp_sock *tp = tcp_sk(sk); subflow->icsk_af_ops->sk_rx_dst_set(sk, skb); - if (inet_sk_state_load(parent) != TCP_ESTABLISHED) { + if (inet_sk_state_load(parent) == TCP_SYN_SENT) { inet_sk_state_store(parent, TCP_ESTABLISHED); parent->sk_state_change(parent); } - if (subflow->conn_finished || !tcp_sk(sk)->is_mptcp) + /* be sure no special action on any packet other than syn-ack */ + if (subflow->conn_finished) + return; + + subflow->conn_finished = 1; + + mptcp_get_options(skb, &mp_opt); + if (subflow->request_mptcp && mp_opt.mp_capable) { + subflow->mp_capable = 1; + subflow->can_ack = 1; + subflow->remote_key = mp_opt.sndr_key; + pr_debug("subflow=%p, remote_key=%llu", subflow, + subflow->remote_key); + } else if (subflow->request_join && mp_opt.mp_join) { + subflow->mp_join = 1; + subflow->thmac = mp_opt.thmac; + subflow->remote_nonce = mp_opt.nonce; + pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u", subflow, + subflow->thmac, subflow->remote_nonce); + } else if (subflow->request_mptcp) { + tp->is_mptcp = 0; + } + + if (!tp->is_mptcp) return; if (subflow->mp_capable) { pr_debug("subflow=%p, remote_key=%llu", mptcp_subflow_ctx(sk), subflow->remote_key); mptcp_finish_connect(sk); - subflow->conn_finished = 1; if (skb) { pr_debug("synack seq=%u", TCP_SKB_CB(skb)->seq); @@ -264,7 +287,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) if (!mptcp_finish_join(sk)) goto do_reset; - subflow->conn_finished = 1; MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX); } else { do_reset: @@ -322,7 +344,7 @@ drop: /* validate hmac received in third ACK */ static bool subflow_hmac_valid(const struct request_sock *req, - const struct tcp_options_received *rx_opt) + const struct mptcp_options_received *mp_opt) { const struct mptcp_subflow_request_sock *subflow_req; u8 hmac[MPTCPOPT_HMAC_LEN]; @@ -339,7 +361,7 @@ static bool subflow_hmac_valid(const struct request_sock *req, subflow_req->local_nonce, hmac); ret = true; - if (crypto_memneq(hmac, rx_opt->mptcp.hmac, sizeof(hmac))) + if (crypto_memneq(hmac, mp_opt->hmac, sizeof(hmac))) ret = false; sock_put((struct sock *)msk); @@ -395,7 +417,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, { struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk); struct mptcp_subflow_request_sock *subflow_req; - struct tcp_options_received opt_rx; + struct mptcp_options_received mp_opt; bool fallback_is_fatal = false; struct sock *new_msk = NULL; bool fallback = false; @@ -403,7 +425,10 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); - opt_rx.mptcp.mp_capable = 0; + /* we need later a valid 'mp_capable' value even when options are not + * parsed + */ + mp_opt.mp_capable = 0; if (tcp_rsk(req)->is_mptcp == 0) goto create_child; @@ -418,22 +443,21 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, goto create_msk; } - mptcp_get_options(skb, &opt_rx); - if (!opt_rx.mptcp.mp_capable) { + mptcp_get_options(skb, &mp_opt); + if (!mp_opt.mp_capable) { fallback = true; goto create_child; } create_msk: - new_msk = mptcp_sk_clone(listener->conn, &opt_rx, req); + new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req); if (!new_msk) fallback = true; } else if (subflow_req->mp_join) { fallback_is_fatal = true; - opt_rx.mptcp.mp_join = 0; - mptcp_get_options(skb, &opt_rx); - if (!opt_rx.mptcp.mp_join || - !subflow_hmac_valid(req, &opt_rx)) { + mptcp_get_options(skb, &mp_opt); + if (!mp_opt.mp_join || + !subflow_hmac_valid(req, &mp_opt)) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC); return NULL; } @@ -473,9 +497,9 @@ create_child: /* with OoO packets we can reach here without ingress * mpc option */ - ctx->remote_key = opt_rx.mptcp.sndr_key; - ctx->fully_established = opt_rx.mptcp.mp_capable; - ctx->can_ack = opt_rx.mptcp.mp_capable; + ctx->remote_key = mp_opt.sndr_key; + ctx->fully_established = mp_opt.mp_capable; + ctx->can_ack = mp_opt.mp_capable; } else if (ctx->mp_join) { struct mptcp_sock *owner; @@ -499,7 +523,7 @@ out: /* check for expected invariant - should never trigger, just help * catching eariler subtle bugs */ - WARN_ON_ONCE(*own_req && child && tcp_sk(child)->is_mptcp && + WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp && (!mptcp_subflow_ctx(child) || !mptcp_subflow_ctx(child)->conn)); return child; @@ -988,6 +1012,16 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) if (err) return err; + /* the newly created socket really belongs to the owning MPTCP master + * socket, even if for additional subflows the allocation is performed + * by a kernel workqueue. Adjust inode references, so that the + * procfs/diag interaces really show this one belonging to the correct + * user. + */ + SOCK_INODE(sf)->i_ino = SOCK_INODE(sk->sk_socket)->i_ino; + SOCK_INODE(sf)->i_uid = SOCK_INODE(sk->sk_socket)->i_uid; + SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid; + subflow = mptcp_subflow_ctx(sf->sk); pr_debug("subflow=%p", subflow); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c4582eb71766..1d57b95d3481 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1519,9 +1519,9 @@ __nf_conntrack_alloc(struct net *net, ct->status = 0; ct->timeout = 0; write_pnet(&ct->ct_net, net); - memset(&ct->__nfct_init_offset[0], 0, + memset(&ct->__nfct_init_offset, 0, offsetof(struct nf_conn, proto) - - offsetof(struct nf_conn, __nfct_init_offset[0])); + offsetof(struct nf_conn, __nfct_init_offset)); nf_ct_zone_add(ct, zone); @@ -2139,8 +2139,19 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data), nf_conntrack_lock(lockp); if (*bucket < nf_conntrack_htable_size) { hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) { - if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL) + if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY) continue; + /* All nf_conn objects are added to hash table twice, one + * for original direction tuple, once for the reply tuple. + * + * Exception: In the IPS_NAT_CLASH case, only the reply + * tuple is added (the original tuple already existed for + * a different object). + * + * We only need to call the iterator once for each + * conntrack, so we just use the 'reply' direction + * tuple while iterating. + */ ct = nf_ct_tuplehash_to_ctrack(h); if (iter(ct, data)) goto found; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 4344e572b7f9..42da6e337276 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -284,7 +284,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table, if (nf_flow_has_expired(flow)) flow_offload_fixup_ct(flow->ct); - else if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) + else flow_offload_fixup_ct_timeout(flow->ct); flow_offload_free(flow); @@ -361,8 +361,10 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data) { struct nf_flowtable *flow_table = data; - if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { + if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct)) + set_bit(NF_FLOW_TEARDOWN, &flow->flags); + + if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { if (test_bit(NF_FLOW_HW, &flow->flags)) { if (!test_bit(NF_FLOW_HW_DYING, &flow->flags)) nf_flow_offload_del(flow_table, flow); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index e3b099c14eff..2276a73ccba2 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -817,6 +817,7 @@ static void flow_offload_work_handler(struct work_struct *work) WARN_ON_ONCE(1); } + clear_bit(NF_FLOW_HW_PENDING, &offload->flow->flags); kfree(offload); } @@ -831,9 +832,14 @@ nf_flow_offload_work_alloc(struct nf_flowtable *flowtable, { struct flow_offload_work *offload; + if (test_and_set_bit(NF_FLOW_HW_PENDING, &flow->flags)) + return NULL; + offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); - if (!offload) + if (!offload) { + clear_bit(NF_FLOW_HW_PENDING, &flow->flags); return NULL; + } offload->cmd = cmd; offload->flow = flow; @@ -1056,7 +1062,7 @@ static struct flow_indr_block_entry block_ing_entry = { int nf_flow_table_offload_init(void) { nf_flow_offload_wq = alloc_workqueue("nf_flow_table_offload", - WQ_UNBOUND | WQ_MEM_RECLAIM, 0); + WQ_UNBOUND, 0); if (!nf_flow_offload_wq) return -ENOMEM; diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 3d816a1e5442..59151dc07fdc 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -68,15 +68,13 @@ static bool udp_manip_pkt(struct sk_buff *skb, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; - bool do_csum; if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); - do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL; + __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); - __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, do_csum); return true; } diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 9f5dea0064ea..916a3c7f9eaf 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -165,12 +165,12 @@ static bool nf_osf_match_one(const struct sk_buff *skb, static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx, const struct sk_buff *skb, const struct iphdr *ip, - unsigned char *opts) + unsigned char *opts, + struct tcphdr *_tcph) { const struct tcphdr *tcp; - struct tcphdr _tcph; - tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), _tcph); if (!tcp) return NULL; @@ -205,10 +205,11 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, int fmatch = FMATCH_WRONG; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; @@ -265,10 +266,11 @@ bool nf_osf_find(const struct sk_buff *skb, const struct nf_osf_finger *kf; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 3ffef454d469..62f416bc0579 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -79,6 +79,10 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(parent->rb_left); continue; } + + if (nft_set_elem_expired(&rbe->ext)) + return false; + if (nft_rbtree_interval_end(rbe)) { if (nft_set_is_anonymous(set)) return false; @@ -94,6 +98,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && + !nft_set_elem_expired(&interval->ext) && nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; @@ -154,6 +159,9 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, continue; } + if (nft_set_elem_expired(&rbe->ext)) + return false; + if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == (flags & NFT_SET_ELEM_INTERVAL_END)) { @@ -170,6 +178,7 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && + !nft_set_elem_expired(&interval->ext) && ((!nft_rbtree_interval_end(interval) && !(flags & NFT_SET_ELEM_INTERVAL_END)) || (nft_rbtree_interval_end(interval) && @@ -418,6 +427,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; + if (nft_set_elem_expired(&rbe->ext)) + goto cont; if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 409a3ae47ce2..5e1239cef000 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -734,6 +734,12 @@ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap, if ((off & (BITS_PER_LONG - 1)) != 0) return -EINVAL; + /* a null catmap is equivalent to an empty one */ + if (!catmap) { + *offset = (u32)-1; + return 0; + } + if (off < catmap->startbit) { off = catmap->startbit; *offset = off; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 55bd1429678f..0a7ecc292bd3 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2070,6 +2070,7 @@ replay: err = PTR_ERR(block); goto errout; } + block->classid = parent; chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; if (chain_index > TC_ACT_EXT_VAL_MASK) { @@ -2612,12 +2613,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; parent = tcm->tcm_parent; - if (!parent) { + if (!parent) q = dev->qdisc; - parent = q->handle; - } else { + else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); - } if (!q) goto out; cops = q->ops->cl_ops; @@ -2633,6 +2632,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) block = cops->tcf_block(q, cl, NULL); if (!block) goto out; + parent = block->classid; if (tcf_block_shared(block)) q = NULL; } @@ -3523,6 +3523,16 @@ static void tcf_sample_get_group(struct flow_action_entry *entry, #endif } +static enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats) +{ + if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY)) + return FLOW_ACTION_HW_STATS_DONT_CARE; + else if (!hw_stats) + return FLOW_ACTION_HW_STATS_DISABLED; + + return hw_stats; +} + int tc_setup_flow_action(struct flow_action *flow_action, const struct tcf_exts *exts) { @@ -3546,7 +3556,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, if (err) goto err_out_locked; - entry->hw_stats = act->hw_stats; + entry->hw_stats = tc_act_hw_stats(act->hw_stats); if (is_tcf_gact_ok(act)) { entry->id = FLOW_ACTION_ACCEPT; @@ -3614,7 +3624,7 @@ int tc_setup_flow_action(struct flow_action *flow_action, entry->mangle.mask = tcf_pedit_mask(act, k); entry->mangle.val = tcf_pedit_val(act, k); entry->mangle.offset = tcf_pedit_offset(act, k); - entry->hw_stats = act->hw_stats; + entry->hw_stats = tc_act_hw_stats(act->hw_stats); entry = &flow_action->entries[++j]; } } else if (is_tcf_csum(act)) { diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index a36974e9c601..1bcf8fbfd40e 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -323,7 +323,8 @@ static void choke_reset(struct Qdisc *sch) sch->q.qlen = 0; sch->qstats.backlog = 0; - memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + if (q->tab) + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; red_restart(&q->vars); } diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 968519ff36e9..436160be9c18 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -416,7 +416,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) - q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); + q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); if (tb[TCA_FQ_CODEL_MEMORY_LIMIT]) q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT])); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index c787d4d46017..5a6def5e4e6d 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -637,6 +637,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (ctl->divisor && (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) return -EINVAL; + + /* slot->allot is a short, make sure quantum is not too big. */ + if (ctl->quantum) { + unsigned int scaled = SFQ_ALLOT_SIZE(ctl->quantum); + + if (scaled <= 0 || scaled > SHRT_MAX) + return -EINVAL; + } + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog)) return -EINVAL; diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 0fb10abf7579..7a5e4c454715 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -169,6 +169,9 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, { struct tc_skbprio_qopt *ctl = nla_data(opt); + if (opt->nla_len != nla_attr_size(sizeof(*ctl))) + return -EINVAL; + sch->limit = ctl->limit; return 0; } diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 25fbd8d9de74..ac5cac0dd24b 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -2032,7 +2032,6 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf; struct kvec *head = rqstp->rq_rcv_buf.head; struct rpc_auth *auth = cred->cr_auth; - unsigned int savedlen = rcv_buf->len; u32 offset, opaque_len, maj_stat; __be32 *p; @@ -2043,9 +2042,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, offset = (u8 *)(p) - (u8 *)head->iov_base; if (offset + opaque_len > rcv_buf->len) goto unwrap_failed; - rcv_buf->len = offset + opaque_len; - maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, rcv_buf); + maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, + offset + opaque_len, rcv_buf); if (maj_stat == GSS_S_CONTEXT_EXPIRED) clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); if (maj_stat != GSS_S_COMPLETE) @@ -2059,10 +2058,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, */ xdr_init_decode(xdr, rcv_buf, p, rqstp); - auth->au_rslack = auth->au_verfsize + 2 + - XDR_QUADLEN(savedlen - rcv_buf->len); - auth->au_ralign = auth->au_verfsize + 2 + - XDR_QUADLEN(savedlen - rcv_buf->len); + auth->au_rslack = auth->au_verfsize + 2 + ctx->gc_gss_ctx->slack; + auth->au_ralign = auth->au_verfsize + 2 + ctx->gc_gss_ctx->align; + return 0; unwrap_failed: trace_rpcgss_unwrap_failed(task); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 6f2d30d7b766..e7180da1fc6a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -851,8 +851,8 @@ out_err: } u32 -gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, - u32 *headskip, u32 *tailskip) +gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, + struct xdr_buf *buf, u32 *headskip, u32 *tailskip) { struct xdr_buf subbuf; u32 ret = 0; @@ -881,7 +881,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, /* create a segment skipping the header and leaving out the checksum */ xdr_buf_subsegment(buf, &subbuf, offset + GSS_KRB5_TOK_HDR_LEN, - (buf->len - offset - GSS_KRB5_TOK_HDR_LEN - + (len - offset - GSS_KRB5_TOK_HDR_LEN - kctx->gk5e->cksumlength)); nblocks = (subbuf.len + blocksize - 1) / blocksize; @@ -926,7 +926,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, goto out_err; /* Get the packet's hmac value */ - ret = read_bytes_from_xdr_buf(buf, buf->len - kctx->gk5e->cksumlength, + ret = read_bytes_from_xdr_buf(buf, len - kctx->gk5e->cksumlength, pkt_hmac, kctx->gk5e->cksumlength); if (ret) goto out_err; diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 6c1920eed771..cf0fd170ac18 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -261,7 +261,9 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, } static u32 -gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { int signalg; int sealalg; @@ -279,12 +281,13 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) u32 conflen = kctx->gk5e->conflen; int crypt_offset; u8 *cksumkey; + unsigned int saved_len = buf->len; dprintk("RPC: gss_unwrap_kerberos\n"); ptr = (u8 *)buf->head[0].iov_base + offset; if (g_verify_token_header(&kctx->mech_used, &bodysize, &ptr, - buf->len - offset)) + len - offset)) return GSS_S_DEFECTIVE_TOKEN; if ((ptr[0] != ((KG_TOK_WRAP_MSG >> 8) & 0xff)) || @@ -324,6 +327,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) (!kctx->initiate && direction != 0)) return GSS_S_BAD_SIG; + buf->len = len; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) { struct crypto_sync_skcipher *cipher; int err; @@ -376,11 +380,15 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) data_len = (buf->head[0].iov_base + buf->head[0].iov_len) - data_start; memmove(orig_start, data_start, data_len); buf->head[0].iov_len -= (data_start - orig_start); - buf->len -= (data_start - orig_start); + buf->len = len - (data_start - orig_start); if (gss_krb5_remove_padding(buf, blocksize)) return GSS_S_DEFECTIVE_TOKEN; + /* slack must include room for krb5 padding */ + *slack = XDR_QUADLEN(saved_len - buf->len); + /* The GSS blob always precedes the RPC message payload */ + *align = *slack; return GSS_S_COMPLETE; } @@ -486,7 +494,9 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, } static u32 -gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { time64_t now; u8 *ptr; @@ -532,7 +542,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) if (rrc != 0) rotate_left(offset + 16, buf, rrc); - err = (*kctx->gk5e->decrypt_v2)(kctx, offset, buf, + err = (*kctx->gk5e->decrypt_v2)(kctx, offset, len, buf, &headskip, &tailskip); if (err) return GSS_S_FAILURE; @@ -542,7 +552,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) * it against the original */ err = read_bytes_from_xdr_buf(buf, - buf->len - GSS_KRB5_TOK_HDR_LEN - tailskip, + len - GSS_KRB5_TOK_HDR_LEN - tailskip, decrypted_hdr, GSS_KRB5_TOK_HDR_LEN); if (err) { dprintk("%s: error %u getting decrypted_hdr\n", __func__, err); @@ -568,18 +578,19 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) * Note that buf->head[0].iov_len may indicate the available * head buffer space rather than that actually occupied. */ - movelen = min_t(unsigned int, buf->head[0].iov_len, buf->len); + movelen = min_t(unsigned int, buf->head[0].iov_len, len); movelen -= offset + GSS_KRB5_TOK_HDR_LEN + headskip; - if (offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen > - buf->head[0].iov_len) - return GSS_S_FAILURE; + BUG_ON(offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen > + buf->head[0].iov_len); memmove(ptr, ptr + GSS_KRB5_TOK_HDR_LEN + headskip, movelen); buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip; - buf->len -= GSS_KRB5_TOK_HDR_LEN + headskip; + buf->len = len - GSS_KRB5_TOK_HDR_LEN + headskip; /* Trim off the trailing "extra count" and checksum blob */ - buf->len -= ec + GSS_KRB5_TOK_HDR_LEN + tailskip; + xdr_buf_trim(buf, ec + GSS_KRB5_TOK_HDR_LEN + tailskip); + *align = XDR_QUADLEN(GSS_KRB5_TOK_HDR_LEN + headskip); + *slack = *align + XDR_QUADLEN(ec + GSS_KRB5_TOK_HDR_LEN + tailskip); return GSS_S_COMPLETE; } @@ -603,7 +614,8 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset, } u32 -gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, + int len, struct xdr_buf *buf) { struct krb5_ctx *kctx = gctx->internal_ctx_id; @@ -613,9 +625,11 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) case ENCTYPE_DES_CBC_RAW: case ENCTYPE_DES3_CBC_RAW: case ENCTYPE_ARCFOUR_HMAC: - return gss_unwrap_kerberos_v1(kctx, offset, buf); + return gss_unwrap_kerberos_v1(kctx, offset, len, buf, + &gctx->slack, &gctx->align); case ENCTYPE_AES128_CTS_HMAC_SHA1_96: case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - return gss_unwrap_kerberos_v2(kctx, offset, buf); + return gss_unwrap_kerberos_v2(kctx, offset, len, buf, + &gctx->slack, &gctx->align); } } diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index db550bfc2642..69316ab1b9fa 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -411,10 +411,11 @@ gss_wrap(struct gss_ctx *ctx_id, u32 gss_unwrap(struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *buf) { return ctx_id->mech_type->gm_ops - ->gss_unwrap(ctx_id, offset, buf); + ->gss_unwrap(ctx_id, offset, len, buf); } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 54ae5be62f6a..50d93c49ef1a 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -906,7 +906,7 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g if (svc_getnl(&buf->head[0]) != seq) goto out; /* trim off the mic and padding at the end before returning */ - buf->len -= 4 + round_up_to_quad(mic.len); + xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4); stat = 0; out: kfree(mic.data); @@ -934,7 +934,7 @@ static int unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx) { u32 priv_len, maj_stat; - int pad, saved_len, remaining_len, offset; + int pad, remaining_len, offset; clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); @@ -954,12 +954,8 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs buf->len -= pad; fix_priv_head(buf, pad); - /* Maybe it would be better to give gss_unwrap a length parameter: */ - saved_len = buf->len; - buf->len = priv_len; - maj_stat = gss_unwrap(ctx, 0, buf); + maj_stat = gss_unwrap(ctx, 0, priv_len, buf); pad = priv_len - buf->len; - buf->len = saved_len; buf->len -= pad; /* The upper layers assume the buffer is aligned on 4-byte boundaries. * In the krb5p case, at least, the data ends up offset, so we need to diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8350d3a2e9a7..61b21dafd7c0 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -889,7 +889,9 @@ static void rpc_free_client_work(struct work_struct *work) * here. */ rpc_clnt_debugfs_unregister(clnt); + rpc_free_clid(clnt); rpc_clnt_remove_pipedir(clnt); + xprt_put(rcu_dereference_raw(clnt->cl_xprt)); kfree(clnt); rpciod_down(); @@ -907,10 +909,8 @@ rpc_free_client(struct rpc_clnt *clnt) rpc_unregister_client(clnt); rpc_free_iostats(clnt->cl_metrics); clnt->cl_metrics = NULL; - xprt_put(rcu_dereference_raw(clnt->cl_xprt)); xprt_iter_destroy(&clnt->cl_xpi); put_cred(clnt->cl_cred); - rpc_free_clid(clnt); INIT_WORK(&clnt->cl_work, rpc_free_client_work); schedule_work(&clnt->cl_work); @@ -2433,6 +2433,11 @@ rpc_check_timeout(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; + if (RPC_SIGNALLED(task)) { + rpc_call_rpcerror(task, -ERESTARTSYS); + return; + } + if (xprt_adjust_timeout(task->tk_rqstp) == 0) return; diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index e534f8f082e7..c211b607239e 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -991,6 +991,7 @@ static int __svc_register(struct net *net, const char *progname, #endif } + trace_svc_register(progname, version, protocol, port, family, error); return error; } @@ -1000,11 +1001,6 @@ int svc_rpcbind_set_version(struct net *net, unsigned short proto, unsigned short port) { - dprintk("svc: svc_register(%sv%d, %s, %u, %u)\n", - progp->pg_name, version, - proto == IPPROTO_UDP? "udp" : "tcp", - port, family); - return __svc_register(net, progp->pg_name, progp->pg_prog, version, family, proto, port); @@ -1024,11 +1020,8 @@ int svc_generic_rpcbind_set(struct net *net, return 0; if (vers->vs_hidden) { - dprintk("svc: svc_register(%sv%d, %s, %u, %u)" - " (but not telling portmap)\n", - progp->pg_name, version, - proto == IPPROTO_UDP? "udp" : "tcp", - port, family); + trace_svc_noregister(progp->pg_name, version, proto, + port, family, 0); return 0; } @@ -1106,8 +1099,7 @@ static void __svc_unregister(struct net *net, const u32 program, const u32 versi if (error == -EPROTONOSUPPORT) error = rpcb_register(net, program, version, 0, 0); - dprintk("svc: %s(%sv%u), error %d\n", - __func__, progname, version, error); + trace_svc_unregister(progname, version, error); } /* @@ -1132,9 +1124,6 @@ static void svc_unregister(const struct svc_serv *serv, struct net *net) continue; if (progp->pg_vers[i]->vs_hidden) continue; - - dprintk("svc: attempting to unregister %sv%u\n", - progp->pg_name, i); __svc_unregister(net, progp->pg_prog, i, progp->pg_name); } } diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 2284ff038dad..c1ff8cdb5b2b 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -153,6 +153,7 @@ static void svc_xprt_free(struct kref *kref) xprt_put(xprt->xpt_bc_xprt); if (xprt->xpt_bc_xps) xprt_switch_put(xprt->xpt_bc_xps); + trace_svc_xprt_free(xprt); xprt->xpt_ops->xpo_free(xprt); module_put(owner); } @@ -206,6 +207,7 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, .sin6_port = htons(port), }; #endif + struct svc_xprt *xprt; struct sockaddr *sap; size_t len; @@ -224,7 +226,11 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl, return ERR_PTR(-EAFNOSUPPORT); } - return xcl->xcl_ops->xpo_create(serv, net, sap, len, flags); + xprt = xcl->xcl_ops->xpo_create(serv, net, sap, len, flags); + if (IS_ERR(xprt)) + trace_svc_xprt_create_err(serv->sv_program->pg_name, + xcl->xcl_name, sap, xprt); + return xprt; } /* @@ -304,15 +310,11 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name, { int err; - dprintk("svc: creating transport %s[%d]\n", xprt_name, port); err = _svc_create_xprt(serv, xprt_name, net, family, port, flags, cred); if (err == -EPROTONOSUPPORT) { request_module("svc%s", xprt_name); err = _svc_create_xprt(serv, xprt_name, net, family, port, flags, cred); } - if (err < 0) - dprintk("svc: transport %s not found, err %d\n", - xprt_name, -err); return err; } EXPORT_SYMBOL_GPL(svc_create_xprt); @@ -780,7 +782,6 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) int len = 0; if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) { - dprintk("svc_recv: found XPT_CLOSE\n"); if (test_and_clear_bit(XPT_KILL_TEMP, &xprt->xpt_flags)) xprt->xpt_ops->xpo_kill_temp_xprt(xprt); svc_delete_xprt(xprt); @@ -799,6 +800,7 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt) if (newxpt) { newxpt->xpt_cred = get_cred(xprt->xpt_cred); svc_add_new_temp_xprt(serv, newxpt); + trace_svc_xprt_accept(newxpt, serv->sv_name); } else module_put(xprt->xpt_class->xcl_owner); } else if (svc_xprt_reserve_slot(rqstp, xprt)) { @@ -835,14 +837,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout) struct svc_serv *serv = rqstp->rq_server; int len, err; - dprintk("svc: server %p waiting for data (to = %ld)\n", - rqstp, timeout); - - if (rqstp->rq_xprt) - printk(KERN_ERR - "svc_recv: service %p, transport not NULL!\n", - rqstp); - err = svc_alloc_arg(rqstp); if (err) goto out; @@ -890,7 +884,6 @@ EXPORT_SYMBOL_GPL(svc_recv); void svc_drop(struct svc_rqst *rqstp) { trace_svc_drop(rqstp); - dprintk("svc: xprt %p dropped request\n", rqstp->rq_xprt); svc_xprt_release(rqstp); } EXPORT_SYMBOL_GPL(svc_drop); @@ -914,16 +907,10 @@ int svc_send(struct svc_rqst *rqstp) xb->page_len + xb->tail[0].iov_len; trace_svc_sendto(xb); - - /* Grab mutex to serialize outgoing data. */ - mutex_lock(&xprt->xpt_mutex); trace_svc_stats_latency(rqstp); - if (test_bit(XPT_DEAD, &xprt->xpt_flags) - || test_bit(XPT_CLOSE, &xprt->xpt_flags)) - len = -ENOTCONN; - else - len = xprt->xpt_ops->xpo_sendto(rqstp); - mutex_unlock(&xprt->xpt_mutex); + + len = xprt->xpt_ops->xpo_sendto(rqstp); + trace_svc_send(rqstp, len); svc_xprt_release(rqstp); @@ -1031,11 +1018,10 @@ static void svc_delete_xprt(struct svc_xprt *xprt) struct svc_serv *serv = xprt->xpt_server; struct svc_deferred_req *dr; - /* Only do this once */ if (test_and_set_bit(XPT_DEAD, &xprt->xpt_flags)) - BUG(); + return; - dprintk("svc: svc_delete_xprt(%p)\n", xprt); + trace_svc_xprt_detach(xprt); xprt->xpt_ops->xpo_detach(xprt); if (xprt->xpt_bc_xprt) xprt->xpt_bc_xprt->ops->close(xprt->xpt_bc_xprt); @@ -1056,6 +1042,7 @@ static void svc_delete_xprt(struct svc_xprt *xprt) void svc_close_xprt(struct svc_xprt *xprt) { + trace_svc_xprt_close(xprt); set_bit(XPT_CLOSE, &xprt->xpt_flags); if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) /* someone else will have to effect the close */ @@ -1158,16 +1145,15 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many) set_bit(XPT_DEFERRED, &xprt->xpt_flags); if (too_many || test_bit(XPT_DEAD, &xprt->xpt_flags)) { spin_unlock(&xprt->xpt_lock); - dprintk("revisit canceled\n"); + trace_svc_defer_drop(dr); svc_xprt_put(xprt); - trace_svc_drop_deferred(dr); kfree(dr); return; } - dprintk("revisit queued\n"); dr->xprt = NULL; list_add(&dr->handle.recent, &xprt->xpt_deferred); spin_unlock(&xprt->xpt_lock); + trace_svc_defer_queue(dr); svc_xprt_enqueue(xprt); svc_xprt_put(xprt); } @@ -1213,22 +1199,24 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) memcpy(dr->args, rqstp->rq_arg.head[0].iov_base - skip, dr->argslen << 2); } + trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; set_bit(RQ_DROPME, &rqstp->rq_flags); dr->handle.revisit = svc_revisit; - trace_svc_defer(rqstp); return &dr->handle; } /* * recv data from a deferred request into an active one */ -static int svc_deferred_recv(struct svc_rqst *rqstp) +static noinline int svc_deferred_recv(struct svc_rqst *rqstp) { struct svc_deferred_req *dr = rqstp->rq_deferred; + trace_svc_defer_recv(dr); + /* setup iov_base past transport header */ rqstp->rq_arg.head[0].iov_base = dr->args + (dr->xprt_hlen>>2); /* The iov_len does not include the transport header bytes */ @@ -1259,7 +1247,6 @@ static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt) struct svc_deferred_req, handle.recent); list_del_init(&dr->handle.recent); - trace_svc_revisit_deferred(dr); } else clear_bit(XPT_DEFERRED, &xprt->xpt_flags); spin_unlock(&xprt->xpt_lock); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 023514e392b3..97d2b6f8c791 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -45,7 +45,6 @@ #include <net/tcp_states.h> #include <linux/uaccess.h> #include <asm/ioctls.h> -#include <trace/events/skb.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/clnt.h> @@ -55,6 +54,8 @@ #include <linux/sunrpc/stats.h> #include <linux/sunrpc/xprt.h> +#include <trace/events/sunrpc.h> + #include "socklib.h" #include "sunrpc.h" @@ -108,31 +109,35 @@ static void svc_reclassify_socket(struct socket *sock) } #endif -/* - * Release an skbuff after use +/** + * svc_tcp_release_rqst - Release transport-related resources + * @rqstp: request structure with resources to be released + * */ -static void svc_release_skb(struct svc_rqst *rqstp) +static void svc_tcp_release_rqst(struct svc_rqst *rqstp) { struct sk_buff *skb = rqstp->rq_xprt_ctxt; if (skb) { struct svc_sock *svsk = container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt); - rqstp->rq_xprt_ctxt = NULL; - dprintk("svc: service %p, releasing skb %p\n", rqstp, skb); + rqstp->rq_xprt_ctxt = NULL; skb_free_datagram_locked(svsk->sk_sk, skb); } } -static void svc_release_udp_skb(struct svc_rqst *rqstp) +/** + * svc_udp_release_rqst - Release transport-related resources + * @rqstp: request structure with resources to be released + * + */ +static void svc_udp_release_rqst(struct svc_rqst *rqstp) { struct sk_buff *skb = rqstp->rq_xprt_ctxt; if (skb) { rqstp->rq_xprt_ctxt = NULL; - - dprintk("svc: service %p, releasing skb %p\n", rqstp, skb); consume_skb(skb); } } @@ -218,34 +223,68 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining) return len; } +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +static void svc_flush_bvec(const struct bio_vec *bvec, size_t size, size_t seek) +{ + struct bvec_iter bi = { + .bi_size = size, + }; + struct bio_vec bv; + + bvec_iter_advance(bvec, &bi, seek & PAGE_MASK); + for_each_bvec(bv, bvec, bi, bi) + flush_dcache_page(bv.bv_page); +} +#else +static inline void svc_flush_bvec(const struct bio_vec *bvec, size_t size, + size_t seek) +{ +} +#endif + /* - * Generic recvfrom routine. + * Read from @rqstp's transport socket. The incoming message fills whole + * pages in @rqstp's rq_pages array until the last page of the message + * has been received into a partial page. */ -static ssize_t svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, - unsigned int nr, size_t buflen, unsigned int base) +static ssize_t svc_tcp_read_msg(struct svc_rqst *rqstp, size_t buflen, + size_t seek) { struct svc_sock *svsk = container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt); + struct bio_vec *bvec = rqstp->rq_bvec; struct msghdr msg = { NULL }; + unsigned int i; ssize_t len; + size_t t; rqstp->rq_xprt_hlen = 0; clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen); - if (base != 0) { - iov_iter_advance(&msg.msg_iter, base); - buflen -= base; + + for (i = 0, t = 0; t < buflen; i++, t += PAGE_SIZE) { + bvec[i].bv_page = rqstp->rq_pages[i]; + bvec[i].bv_len = PAGE_SIZE; + bvec[i].bv_offset = 0; + } + rqstp->rq_respages = &rqstp->rq_pages[i]; + rqstp->rq_next_page = rqstp->rq_respages + 1; + + iov_iter_bvec(&msg.msg_iter, READ, bvec, i, buflen); + if (seek) { + iov_iter_advance(&msg.msg_iter, seek); + buflen -= seek; } len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT); + if (len > 0) + svc_flush_bvec(bvec, len, seek); + /* If we read a full record, then assume there may be more * data to read (stream based sockets only!) */ if (len == buflen) set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - dprintk("svc: socket %p recvfrom(%p, %zu) = %zd\n", - svsk, iov[0].iov_base, iov[0].iov_len, len); return len; } @@ -282,13 +321,10 @@ static void svc_data_ready(struct sock *sk) struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; if (svsk) { - dprintk("svc: socket %p(inet %p), busy=%d\n", - svsk, sk, - test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)); - /* Refer to svc_setup_socket() for details. */ rmb(); svsk->sk_odata(sk); + trace_svcsock_data_ready(&svsk->sk_xprt, 0); if (!test_and_set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags)) svc_xprt_enqueue(&svsk->sk_xprt); } @@ -302,11 +338,9 @@ static void svc_write_space(struct sock *sk) struct svc_sock *svsk = (struct svc_sock *)(sk->sk_user_data); if (svsk) { - dprintk("svc: socket %p(inet %p), write_space busy=%d\n", - svsk, sk, test_bit(XPT_BUSY, &svsk->sk_xprt.xpt_flags)); - /* Refer to svc_setup_socket() for details. */ rmb(); + trace_svcsock_write_space(&svsk->sk_xprt, 0); svsk->sk_owspace(sk); svc_xprt_enqueue(&svsk->sk_xprt); } @@ -391,8 +425,15 @@ static int svc_udp_get_dest_address(struct svc_rqst *rqstp, return 0; } -/* - * Receive a datagram from a UDP socket. +/** + * svc_udp_recvfrom - Receive a datagram from a UDP socket. + * @rqstp: request structure into which to receive an RPC Call + * + * Called in a loop when XPT_DATA has been set. + * + * Returns: + * On success, the number of bytes in a received RPC Call, or + * %0 if a complete RPC Call message was not ready to return */ static int svc_udp_recvfrom(struct svc_rqst *rqstp) { @@ -426,20 +467,14 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) svc_sock_setbufsize(svsk, serv->sv_nrthreads + 3); clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - skb = NULL; err = kernel_recvmsg(svsk->sk_sock, &msg, NULL, 0, 0, MSG_PEEK | MSG_DONTWAIT); - if (err >= 0) - skb = skb_recv_udp(svsk->sk_sk, 0, 1, &err); - - if (skb == NULL) { - if (err != -EAGAIN) { - /* possibly an icmp error */ - dprintk("svc: recvfrom returned error %d\n", -err); - set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - } - return 0; - } + if (err < 0) + goto out_recv_err; + skb = skb_recv_udp(svsk->sk_sk, 0, 1, &err); + if (!skb) + goto out_recv_err; + len = svc_addr_len(svc_addr(rqstp)); rqstp->rq_addrlen = len; if (skb->tstamp == 0) { @@ -450,26 +485,21 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) sock_write_timestamp(svsk->sk_sk, skb->tstamp); set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); /* there may be more data... */ - len = skb->len; + len = skb->len; rqstp->rq_arg.len = len; + trace_svcsock_udp_recv(&svsk->sk_xprt, len); rqstp->rq_prot = IPPROTO_UDP; - if (!svc_udp_get_dest_address(rqstp, cmh)) { - net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n", - cmh->cmsg_level, cmh->cmsg_type); - goto out_free; - } + if (!svc_udp_get_dest_address(rqstp, cmh)) + goto out_cmsg_err; rqstp->rq_daddrlen = svc_addr_len(svc_daddr(rqstp)); if (skb_is_nonlinear(skb)) { /* we have to copy */ local_bh_disable(); - if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) { - local_bh_enable(); - /* checksum error */ - goto out_free; - } + if (csum_partial_copy_to_xdr(&rqstp->rq_arg, skb)) + goto out_bh_enable; local_bh_enable(); consume_skb(skb); } else { @@ -497,6 +527,20 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp) serv->sv_stats->netudpcnt++; return len; + +out_recv_err: + if (err != -EAGAIN) { + /* possibly an icmp error */ + set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); + } + trace_svcsock_udp_recv_err(&svsk->sk_xprt, err); + return 0; +out_cmsg_err: + net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n", + cmh->cmsg_level, cmh->cmsg_type); + goto out_free; +out_bh_enable: + local_bh_enable(); out_free: kfree_skb(skb); return 0; @@ -506,6 +550,9 @@ out_free: * svc_udp_sendto - Send out a reply on a UDP socket * @rqstp: completed svc_rqst * + * xpt_mutex ensures @rqstp's whole message is written to the socket + * without interruption. + * * Returns the number of bytes sent, or a negative errno. */ static int svc_udp_sendto(struct svc_rqst *rqstp) @@ -527,10 +574,15 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) unsigned int uninitialized_var(sent); int err; - svc_release_udp_skb(rqstp); + svc_udp_release_rqst(rqstp); svc_set_cmsg_data(rqstp, cmh); + mutex_lock(&xprt->xpt_mutex); + + if (svc_xprt_is_dead(xprt)) + goto out_notconn; + err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); xdr_free_bvec(xdr); if (err == -ECONNREFUSED) { @@ -538,9 +590,16 @@ static int svc_udp_sendto(struct svc_rqst *rqstp) err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, 0, &sent); xdr_free_bvec(xdr); } + trace_svcsock_udp_send(xprt, err); + + mutex_unlock(&xprt->xpt_mutex); if (err < 0) return err; return sent; + +out_notconn: + mutex_unlock(&xprt->xpt_mutex); + return -ENOTCONN; } static int svc_udp_has_wspace(struct svc_xprt *xprt) @@ -584,7 +643,7 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_recvfrom = svc_udp_recvfrom, .xpo_sendto = svc_udp_sendto, .xpo_read_payload = svc_sock_read_payload, - .xpo_release_rqst = svc_release_udp_skb, + .xpo_release_rqst = svc_udp_release_rqst, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_udp_has_wspace, @@ -603,7 +662,7 @@ static struct svc_xprt_class svc_udp_class = { static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) { - int err, level, optname, one = 1; + int level, optname, one = 1; svc_xprt_init(sock_net(svsk->sk_sock->sk), &svc_udp_class, &svsk->sk_xprt, serv); @@ -634,9 +693,8 @@ static void svc_udp_init(struct svc_sock *svsk, struct svc_serv *serv) default: BUG(); } - err = kernel_setsockopt(svsk->sk_sock, level, optname, - (char *)&one, sizeof(one)); - dprintk("svc: kernel_setsockopt returned %d\n", err); + kernel_setsockopt(svsk->sk_sock, level, optname, (char *)&one, + sizeof(one)); } /* @@ -647,9 +705,6 @@ static void svc_tcp_listen_data_ready(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; - dprintk("svc: socket %p TCP (listen) state change %d\n", - sk, sk->sk_state); - if (svsk) { /* Refer to svc_setup_socket() for details. */ rmb(); @@ -670,8 +725,7 @@ static void svc_tcp_listen_data_ready(struct sock *sk) if (svsk) { set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); svc_xprt_enqueue(&svsk->sk_xprt); - } else - printk("svc: socket %p: no user data\n", sk); + } } } @@ -682,15 +736,11 @@ static void svc_tcp_state_change(struct sock *sk) { struct svc_sock *svsk = (struct svc_sock *)sk->sk_user_data; - dprintk("svc: socket %p TCP (connected) state change %d (svsk %p)\n", - sk, sk->sk_state, sk->sk_user_data); - - if (!svsk) - printk("svc: socket %p: no user data\n", sk); - else { + if (svsk) { /* Refer to svc_setup_socket() for details. */ rmb(); svsk->sk_ostate(sk); + trace_svcsock_tcp_state(&svsk->sk_xprt, svsk->sk_sock); if (sk->sk_state != TCP_ESTABLISHED) { set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); svc_xprt_enqueue(&svsk->sk_xprt); @@ -711,9 +761,7 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) struct socket *newsock; struct svc_sock *newsvsk; int err, slen; - RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); - dprintk("svc: tcp_accept %p sock %p\n", svsk, sock); if (!sock) return NULL; @@ -726,30 +774,18 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) else if (err != -EAGAIN) net_warn_ratelimited("%s: accept failed (err %d)!\n", serv->sv_name, -err); + trace_svcsock_accept_err(xprt, serv->sv_name, err); return NULL; } set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); err = kernel_getpeername(newsock, sin); if (err < 0) { - net_warn_ratelimited("%s: peername failed (err %d)!\n", - serv->sv_name, -err); + trace_svcsock_getpeername_err(xprt, serv->sv_name, err); goto failed; /* aborted connection or whatever */ } slen = err; - /* Ideally, we would want to reject connections from unauthorized - * hosts here, but when we get encryption, the IP of the host won't - * tell us anything. For now just warn about unpriv connections. - */ - if (!svc_port_is_privileged(sin)) { - dprintk("%s: connect from unprivileged port: %s\n", - serv->sv_name, - __svc_print_addr(sin, buf, sizeof(buf))); - } - dprintk("%s: connect from %s\n", serv->sv_name, - __svc_print_addr(sin, buf, sizeof(buf))); - /* Reset the inherited callbacks before calling svc_setup_socket */ newsock->sk->sk_state_change = svsk->sk_ostate; newsock->sk->sk_data_ready = svsk->sk_odata; @@ -767,10 +803,8 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt) svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen); err = kernel_getsockname(newsock, sin); slen = err; - if (unlikely(err < 0)) { - dprintk("svc_tcp_accept: kernel_getsockname error %d\n", -err); + if (unlikely(err < 0)) slen = offsetof(struct sockaddr, sa_data); - } svc_xprt_set_local(&newsvsk->sk_xprt, sin, slen); if (sock_is_loopback(newsock->sk)) @@ -787,13 +821,14 @@ failed: return NULL; } -static unsigned int svc_tcp_restore_pages(struct svc_sock *svsk, struct svc_rqst *rqstp) +static size_t svc_tcp_restore_pages(struct svc_sock *svsk, + struct svc_rqst *rqstp) { - unsigned int i, len, npages; + size_t len = svsk->sk_datalen; + unsigned int i, npages; - if (svsk->sk_datalen == 0) + if (!len) return 0; - len = svsk->sk_datalen; npages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT; for (i = 0; i < npages; i++) { if (rqstp->rq_pages[i] != NULL) @@ -842,47 +877,45 @@ out: } /* - * Receive fragment record header. - * If we haven't gotten the record length yet, get the next four bytes. + * Receive fragment record header into sk_marker. */ -static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp) +static ssize_t svc_tcp_read_marker(struct svc_sock *svsk, + struct svc_rqst *rqstp) { - struct svc_serv *serv = svsk->sk_xprt.xpt_server; - unsigned int want; - int len; + ssize_t want, len; + /* If we haven't gotten the record length yet, + * get the next four bytes. + */ if (svsk->sk_tcplen < sizeof(rpc_fraghdr)) { + struct msghdr msg = { NULL }; struct kvec iov; want = sizeof(rpc_fraghdr) - svsk->sk_tcplen; - iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen; + iov.iov_base = ((char *)&svsk->sk_marker) + svsk->sk_tcplen; iov.iov_len = want; - len = svc_recvfrom(rqstp, &iov, 1, want, 0); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, want); + len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT); if (len < 0) - goto error; + return len; svsk->sk_tcplen += len; - if (len < want) { - dprintk("svc: short recvfrom while reading record " - "length (%d of %d)\n", len, want); - return -EAGAIN; + /* call again to read the remaining bytes */ + goto err_short; } - - dprintk("svc: TCP record, %d bytes\n", svc_sock_reclen(svsk)); + trace_svcsock_marker(&svsk->sk_xprt, svsk->sk_marker); if (svc_sock_reclen(svsk) + svsk->sk_datalen > - serv->sv_max_mesg) { - net_notice_ratelimited("RPC: fragment too large: %d\n", - svc_sock_reclen(svsk)); - goto err_delete; - } + svsk->sk_xprt.xpt_server->sv_max_mesg) + goto err_too_large; } - return svc_sock_reclen(svsk); -error: - dprintk("RPC: TCP recv_record got %d\n", len); - return len; -err_delete: + +err_too_large: + net_notice_ratelimited("svc: %s %s RPC fragment too large: %d\n", + __func__, svsk->sk_xprt.xpt_server->sv_name, + svc_sock_reclen(svsk)); set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); +err_short: return -EAGAIN; } @@ -931,87 +964,58 @@ unlock_eagain: return -EAGAIN; } -static int copy_pages_to_kvecs(struct kvec *vec, struct page **pages, int len) -{ - int i = 0; - int t = 0; - - while (t < len) { - vec[i].iov_base = page_address(pages[i]); - vec[i].iov_len = PAGE_SIZE; - i++; - t += PAGE_SIZE; - } - return i; -} - static void svc_tcp_fragment_received(struct svc_sock *svsk) { /* If we have more data, signal svc_xprt_enqueue() to try again */ - dprintk("svc: TCP %s record (%d bytes)\n", - svc_sock_final_rec(svsk) ? "final" : "nonfinal", - svc_sock_reclen(svsk)); svsk->sk_tcplen = 0; - svsk->sk_reclen = 0; + svsk->sk_marker = xdr_zero; } -/* - * Receive data from a TCP socket. +/** + * svc_tcp_recvfrom - Receive data from a TCP socket + * @rqstp: request structure into which to receive an RPC Call + * + * Called in a loop when XPT_DATA has been set. + * + * Read the 4-byte stream record marker, then use the record length + * in that marker to set up exactly the resources needed to receive + * the next RPC message into @rqstp. + * + * Returns: + * On success, the number of bytes in a received RPC Call, or + * %0 if a complete RPC Call message was not ready to return + * + * The zero return case handles partial receives and callback Replies. + * The state of a partial receive is preserved in the svc_sock for + * the next call to svc_tcp_recvfrom. */ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) { struct svc_sock *svsk = container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt); struct svc_serv *serv = svsk->sk_xprt.xpt_server; - int len; - struct kvec *vec; - unsigned int want, base; + size_t want, base; + ssize_t len; __be32 *p; __be32 calldir; - int pnum; - - dprintk("svc: tcp_recv %p data %d conn %d close %d\n", - svsk, test_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags), - test_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags), - test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags)); - len = svc_tcp_recv_record(svsk, rqstp); + clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); + len = svc_tcp_read_marker(svsk, rqstp); if (len < 0) goto error; base = svc_tcp_restore_pages(svsk, rqstp); - want = svc_sock_reclen(svsk) - (svsk->sk_tcplen - sizeof(rpc_fraghdr)); - - vec = rqstp->rq_vec; - - pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], base + want); - - rqstp->rq_respages = &rqstp->rq_pages[pnum]; - rqstp->rq_next_page = rqstp->rq_respages + 1; - - /* Now receive data */ - len = svc_recvfrom(rqstp, vec, pnum, base + want, base); + want = len - (svsk->sk_tcplen - sizeof(rpc_fraghdr)); + len = svc_tcp_read_msg(rqstp, base + want, base); if (len >= 0) { + trace_svcsock_tcp_recv(&svsk->sk_xprt, len); svsk->sk_tcplen += len; svsk->sk_datalen += len; } - if (len != want || !svc_sock_final_rec(svsk)) { - svc_tcp_save_pages(svsk, rqstp); - if (len < 0 && len != -EAGAIN) - goto err_delete; - if (len == want) - svc_tcp_fragment_received(svsk); - else - dprintk("svc: incomplete TCP record (%d of %d)\n", - (int)(svsk->sk_tcplen - sizeof(rpc_fraghdr)), - svc_sock_reclen(svsk)); - goto err_noclose; - } - - if (svsk->sk_datalen < 8) { - svsk->sk_datalen = 0; - goto err_delete; /* client is nuts. */ - } + if (len != want || !svc_sock_final_rec(svsk)) + goto err_incomplete; + if (svsk->sk_datalen < 8) + goto err_nuts; rqstp->rq_arg.len = svsk->sk_datalen; rqstp->rq_arg.page_base = 0; @@ -1046,14 +1050,26 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) return rqstp->rq_arg.len; +err_incomplete: + svc_tcp_save_pages(svsk, rqstp); + if (len < 0 && len != -EAGAIN) + goto err_delete; + if (len == want) + svc_tcp_fragment_received(svsk); + else + trace_svcsock_tcp_recv_short(&svsk->sk_xprt, + svc_sock_reclen(svsk), + svsk->sk_tcplen - sizeof(rpc_fraghdr)); + goto err_noclose; error: if (len != -EAGAIN) goto err_delete; - dprintk("RPC: TCP recvfrom got EAGAIN\n"); + trace_svcsock_tcp_recv_eagain(&svsk->sk_xprt, 0); return 0; +err_nuts: + svsk->sk_datalen = 0; err_delete: - printk(KERN_NOTICE "%s: recvfrom returned errno %d\n", - svsk->sk_xprt.xpt_server->sv_name, -len); + trace_svcsock_tcp_recv_err(&svsk->sk_xprt, len); set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags); err_noclose: return 0; /* record not complete */ @@ -1063,6 +1079,9 @@ err_noclose: * svc_tcp_sendto - Send out a reply on a TCP socket * @rqstp: completed svc_rqst * + * xpt_mutex ensures @rqstp's whole message is written to the socket + * without interruption. + * * Returns the number of bytes sent, or a negative errno. */ static int svc_tcp_sendto(struct svc_rqst *rqstp) @@ -1078,14 +1097,22 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) unsigned int uninitialized_var(sent); int err; - svc_release_skb(rqstp); + svc_tcp_release_rqst(rqstp); + mutex_lock(&xprt->xpt_mutex); + if (svc_xprt_is_dead(xprt)) + goto out_notconn; err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, marker, &sent); xdr_free_bvec(xdr); + trace_svcsock_tcp_send(xprt, err < 0 ? err : sent); if (err < 0 || sent != (xdr->len + sizeof(marker))) goto out_close; + mutex_unlock(&xprt->xpt_mutex); return sent; +out_notconn: + mutex_unlock(&xprt->xpt_mutex); + return -ENOTCONN; out_close: pr_notice("rpc-srv/tcp: %s: %s %d when sending %d bytes - shutting down socket\n", xprt->xpt_server->sv_name, @@ -1093,6 +1120,7 @@ out_close: (err < 0) ? err : sent, xdr->len); set_bit(XPT_CLOSE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); + mutex_unlock(&xprt->xpt_mutex); return -EAGAIN; } @@ -1109,7 +1137,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_recvfrom = svc_tcp_recvfrom, .xpo_sendto = svc_tcp_sendto, .xpo_read_payload = svc_sock_read_payload, - .xpo_release_rqst = svc_release_skb, + .xpo_release_rqst = svc_tcp_release_rqst, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, .xpo_has_wspace = svc_tcp_has_wspace, @@ -1147,18 +1175,16 @@ static void svc_tcp_init(struct svc_sock *svsk, struct svc_serv *serv) set_bit(XPT_CACHE_AUTH, &svsk->sk_xprt.xpt_flags); set_bit(XPT_CONG_CTRL, &svsk->sk_xprt.xpt_flags); if (sk->sk_state == TCP_LISTEN) { - dprintk("setting up TCP socket for listening\n"); strcpy(svsk->sk_xprt.xpt_remotebuf, "listener"); set_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags); sk->sk_data_ready = svc_tcp_listen_data_ready; set_bit(XPT_CONN, &svsk->sk_xprt.xpt_flags); } else { - dprintk("setting up TCP socket for reading\n"); sk->sk_state_change = svc_tcp_state_change; sk->sk_data_ready = svc_data_ready; sk->sk_write_space = svc_write_space; - svsk->sk_reclen = 0; + svsk->sk_marker = xdr_zero; svsk->sk_tcplen = 0; svsk->sk_datalen = 0; memset(&svsk->sk_pages[0], 0, sizeof(svsk->sk_pages)); @@ -1203,7 +1229,6 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, int pmap_register = !(flags & SVC_SOCK_ANONYMOUS); int err = 0; - dprintk("svc: svc_setup_socket %p\n", sock); svsk = kzalloc(sizeof(*svsk), GFP_KERNEL); if (!svsk) return ERR_PTR(-ENOMEM); @@ -1240,12 +1265,7 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv, else svc_tcp_init(svsk, serv); - dprintk("svc: svc_setup_socket created %p (inet %p), " - "listen %d close %d\n", - svsk, svsk->sk_sk, - test_bit(XPT_LISTENER, &svsk->sk_xprt.xpt_flags), - test_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags)); - + trace_svcsock_new_socket(sock); return svsk; } @@ -1338,11 +1358,6 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, int newlen; int family; int val; - RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]); - - dprintk("svc: svc_create_socket(%s, %d, %s)\n", - serv->sv_program->pg_name, protocol, - __svc_print_addr(sin, buf, sizeof(buf))); if (protocol != IPPROTO_UDP && protocol != IPPROTO_TCP) { printk(KERN_WARNING "svc: only UDP and TCP " @@ -1402,7 +1417,6 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, svc_xprt_set_local(&svsk->sk_xprt, newsin, newlen); return (struct svc_xprt *)svsk; bummer: - dprintk("svc: svc_create_socket error = %d\n", -error); sock_release(sock); return ERR_PTR(error); } @@ -1416,8 +1430,6 @@ static void svc_sock_detach(struct svc_xprt *xprt) struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); struct sock *sk = svsk->sk_sk; - dprintk("svc: svc_sock_detach(%p)\n", svsk); - /* put back the old socket callbacks */ lock_sock(sk); sk->sk_state_change = svsk->sk_ostate; @@ -1434,8 +1446,6 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - dprintk("svc: svc_tcp_sock_detach(%p)\n", svsk); - svc_sock_detach(xprt); if (!test_bit(XPT_LISTENER, &xprt->xpt_flags)) { @@ -1450,7 +1460,6 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt) static void svc_sock_free(struct svc_xprt *xprt) { struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt); - dprintk("svc: svc_sock_free(%p)\n", svsk); if (svsk->sk_sock->file) sockfd_put(svsk->sk_sock); diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index 15b58c5144f9..6f7d82fb1eb0 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -1150,6 +1150,47 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, } EXPORT_SYMBOL_GPL(xdr_buf_subsegment); +/** + * xdr_buf_trim - lop at most "len" bytes off the end of "buf" + * @buf: buf to be trimmed + * @len: number of bytes to reduce "buf" by + * + * Trim an xdr_buf by the given number of bytes by fixing up the lengths. Note + * that it's possible that we'll trim less than that amount if the xdr_buf is + * too small, or if (for instance) it's all in the head and the parser has + * already read too far into it. + */ +void xdr_buf_trim(struct xdr_buf *buf, unsigned int len) +{ + size_t cur; + unsigned int trim = len; + + if (buf->tail[0].iov_len) { + cur = min_t(size_t, buf->tail[0].iov_len, trim); + buf->tail[0].iov_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->page_len) { + cur = min_t(unsigned int, buf->page_len, trim); + buf->page_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->head[0].iov_len) { + cur = min_t(size_t, buf->head[0].iov_len, trim); + buf->head[0].iov_len -= cur; + trim -= cur; + } +fix_len: + buf->len -= (len - trim); +} +EXPORT_SYMBOL_GPL(xdr_buf_trim); + static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len) { unsigned int this_len; diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index af7eb8d202ae..1ee73f7cf931 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -10,59 +10,34 @@ #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#define RPCDBG_FACILITY RPCDBG_SVCXPRT - -#undef SVCRDMA_BACKCHANNEL_DEBUG - /** - * svc_rdma_handle_bc_reply - Process incoming backchannel reply - * @xprt: controlling backchannel transport - * @rdma_resp: pointer to incoming transport header - * @rcvbuf: XDR buffer into which to decode the reply + * svc_rdma_handle_bc_reply - Process incoming backchannel Reply + * @rqstp: resources for handling the Reply + * @rctxt: Received message * - * Returns: - * %0 if @rcvbuf is filled in, xprt_complete_rqst called, - * %-EAGAIN if server should call ->recvfrom again. */ -int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, - struct xdr_buf *rcvbuf) +void svc_rdma_handle_bc_reply(struct svc_rqst *rqstp, + struct svc_rdma_recv_ctxt *rctxt) { + struct svc_xprt *sxprt = rqstp->rq_xprt; + struct rpc_xprt *xprt = sxprt->xpt_bc_xprt; struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); + struct xdr_buf *rcvbuf = &rqstp->rq_arg; struct kvec *dst, *src = &rcvbuf->head[0]; + __be32 *rdma_resp = rctxt->rc_recv_buf; struct rpc_rqst *req; u32 credits; - size_t len; - __be32 xid; - __be32 *p; - int ret; - - p = (__be32 *)src->iov_base; - len = src->iov_len; - xid = *rdma_resp; - -#ifdef SVCRDMA_BACKCHANNEL_DEBUG - pr_info("%s: xid=%08x, length=%zu\n", - __func__, be32_to_cpu(xid), len); - pr_info("%s: RPC/RDMA: %*ph\n", - __func__, (int)RPCRDMA_HDRLEN_MIN, rdma_resp); - pr_info("%s: RPC: %*ph\n", - __func__, (int)len, p); -#endif - - ret = -EAGAIN; - if (src->iov_len < 24) - goto out_shortreply; spin_lock(&xprt->queue_lock); - req = xprt_lookup_rqst(xprt, xid); + req = xprt_lookup_rqst(xprt, *rdma_resp); if (!req) - goto out_notfound; + goto out_unlock; dst = &req->rq_private_buf.head[0]; memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf)); - if (dst->iov_len < len) + if (dst->iov_len < src->iov_len) goto out_unlock; - memcpy(dst->iov_base, p, len); + memcpy(dst->iov_base, src->iov_base, src->iov_len); xprt_pin_rqst(req); spin_unlock(&xprt->queue_lock); @@ -71,31 +46,17 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp, credits = 1; /* don't deadlock */ else if (credits > r_xprt->rx_buf.rb_bc_max_requests) credits = r_xprt->rx_buf.rb_bc_max_requests; - spin_lock(&xprt->transport_lock); xprt->cwnd = credits << RPC_CWNDSHIFT; spin_unlock(&xprt->transport_lock); spin_lock(&xprt->queue_lock); - ret = 0; xprt_complete_rqst(req->rq_task, rcvbuf->len); xprt_unpin_rqst(req); rcvbuf->len = 0; out_unlock: spin_unlock(&xprt->queue_lock); -out: - return ret; - -out_shortreply: - dprintk("svcrdma: short bc reply: xprt=%p, len=%zu\n", - xprt, src->iov_len); - goto out; - -out_notfound: - dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n", - xprt, be32_to_cpu(xid)); - goto out_unlock; } /* Send a backwards direction RPC call. @@ -192,10 +153,6 @@ rpcrdma_bc_send_request(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst) *p++ = xdr_zero; *p = xdr_zero; -#ifdef SVCRDMA_BACKCHANNEL_DEBUG - pr_info("%s: %*ph\n", __func__, 64, rqst->rq_buffer); -#endif - rqst->rq_xtime = ktime_get(); rc = svc_rdma_bc_sendto(rdma, rqst, ctxt); if (rc) @@ -206,45 +163,36 @@ put_ctxt: svc_rdma_send_ctxt_put(rdma, ctxt); drop_connection: - dprintk("svcrdma: failed to send bc call\n"); return -ENOTCONN; } -/* Send an RPC call on the passive end of a transport - * connection. +/** + * xprt_rdma_bc_send_request - Send a reverse-direction Call + * @rqst: rpc_rqst containing Call message to be sent + * + * Return values: + * %0 if the message was sent successfully + * %ENOTCONN if the message was not sent */ -static int -xprt_rdma_bc_send_request(struct rpc_rqst *rqst) +static int xprt_rdma_bc_send_request(struct rpc_rqst *rqst) { struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt; - struct svcxprt_rdma *rdma; + struct svcxprt_rdma *rdma = + container_of(sxprt, struct svcxprt_rdma, sc_xprt); int ret; - dprintk("svcrdma: sending bc call with xid: %08x\n", - be32_to_cpu(rqst->rq_xid)); + if (test_bit(XPT_DEAD, &sxprt->xpt_flags)) + return -ENOTCONN; - mutex_lock(&sxprt->xpt_mutex); - - ret = -ENOTCONN; - rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt); - if (!test_bit(XPT_DEAD, &sxprt->xpt_flags)) { - ret = rpcrdma_bc_send_request(rdma, rqst); - if (ret == -ENOTCONN) - svc_close_xprt(sxprt); - } - - mutex_unlock(&sxprt->xpt_mutex); - - if (ret < 0) - return ret; - return 0; + ret = rpcrdma_bc_send_request(rdma, rqst); + if (ret == -ENOTCONN) + svc_close_xprt(sxprt); + return ret; } static void xprt_rdma_bc_close(struct rpc_xprt *xprt) { - dprintk("svcrdma: %s: xprt %p\n", __func__, xprt); - xprt_disconnect_done(xprt); xprt->cwnd = RPC_CWNDSHIFT; } @@ -252,8 +200,6 @@ xprt_rdma_bc_close(struct rpc_xprt *xprt) static void xprt_rdma_bc_put(struct rpc_xprt *xprt) { - dprintk("svcrdma: %s: xprt %p\n", __func__, xprt); - xprt_rdma_free_addresses(xprt); xprt_free(xprt); } @@ -288,19 +234,14 @@ xprt_setup_rdma_bc(struct xprt_create *args) struct rpc_xprt *xprt; struct rpcrdma_xprt *new_xprt; - if (args->addrlen > sizeof(xprt->addr)) { - dprintk("RPC: %s: address too large\n", __func__); + if (args->addrlen > sizeof(xprt->addr)) return ERR_PTR(-EBADF); - } xprt = xprt_alloc(args->net, sizeof(*new_xprt), RPCRDMA_MAX_BC_REQUESTS, RPCRDMA_MAX_BC_REQUESTS); - if (!xprt) { - dprintk("RPC: %s: couldn't allocate rpc_xprt\n", - __func__); + if (!xprt) return ERR_PTR(-ENOMEM); - } xprt->timeout = &xprt_rdma_bc_timeout; xprt_set_bound(xprt); diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index efa5fcb5793f..e426fedb9524 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -665,23 +665,23 @@ static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg, return hdr_len; out_short: - trace_svcrdma_decode_short(rq_arg->len); + trace_svcrdma_decode_short_err(rq_arg->len); return -EINVAL; out_version: - trace_svcrdma_decode_badvers(rdma_argp); + trace_svcrdma_decode_badvers_err(rdma_argp); return -EPROTONOSUPPORT; out_drop: - trace_svcrdma_decode_drop(rdma_argp); + trace_svcrdma_decode_drop_err(rdma_argp); return 0; out_proc: - trace_svcrdma_decode_badproc(rdma_argp); + trace_svcrdma_decode_badproc_err(rdma_argp); return -EINVAL; out_inval: - trace_svcrdma_decode_parse(rdma_argp); + trace_svcrdma_decode_parse_err(rdma_argp); return -EINVAL; } @@ -878,12 +878,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto out_drop; rqstp->rq_xprt_hlen = ret; - if (svc_rdma_is_backchannel_reply(xprt, p)) { - ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p, - &rqstp->rq_arg); - svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); - return ret; - } + if (svc_rdma_is_backchannel_reply(xprt, p)) + goto out_backchannel; + svc_rdma_get_inv_rkey(rdma_xprt, ctxt); p += rpcrdma_fixed_maxsz; @@ -913,6 +910,8 @@ out_postfail: svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); return ret; +out_backchannel: + svc_rdma_handle_bc_reply(rqstp, ctxt); out_drop: svc_rdma_recv_ctxt_put(rdma_xprt, ctxt); return 0; diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 23c2d3ce0dc9..5eb35309ecef 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -9,13 +9,10 @@ #include <linux/sunrpc/rpc_rdma.h> #include <linux/sunrpc/svc_rdma.h> -#include <linux/sunrpc/debug.h> #include "xprt_rdma.h" #include <trace/events/rpcrdma.h> -#define RPCDBG_FACILITY RPCDBG_SVCXPRT - static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc); static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc); @@ -39,7 +36,7 @@ static void svc_rdma_wc_read_done(struct ib_cq *cq, struct ib_wc *wc); struct svc_rdma_rw_ctxt { struct list_head rw_list; struct rdma_rw_ctx rw_ctx; - int rw_nents; + unsigned int rw_nents; struct sg_table rw_sg_table; struct scatterlist rw_first_sgl[]; }; @@ -67,19 +64,22 @@ svc_rdma_get_rw_ctxt(struct svcxprt_rdma *rdma, unsigned int sges) ctxt = kmalloc(struct_size(ctxt, rw_first_sgl, SG_CHUNK_SIZE), GFP_KERNEL); if (!ctxt) - goto out; + goto out_noctx; INIT_LIST_HEAD(&ctxt->rw_list); } ctxt->rw_sg_table.sgl = ctxt->rw_first_sgl; if (sg_alloc_table_chained(&ctxt->rw_sg_table, sges, ctxt->rw_sg_table.sgl, - SG_CHUNK_SIZE)) { - kfree(ctxt); - ctxt = NULL; - } -out: + SG_CHUNK_SIZE)) + goto out_free; return ctxt; + +out_free: + kfree(ctxt); +out_noctx: + trace_svcrdma_no_rwctx_err(rdma, sges); + return NULL; } static void svc_rdma_put_rw_ctxt(struct svcxprt_rdma *rdma, @@ -107,6 +107,34 @@ void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma) } } +/** + * svc_rdma_rw_ctx_init - Prepare a R/W context for I/O + * @rdma: controlling transport instance + * @ctxt: R/W context to prepare + * @offset: RDMA offset + * @handle: RDMA tag/handle + * @direction: I/O direction + * + * Returns on success, the number of WQEs that will be needed + * on the workqueue, or a negative errno. + */ +static int svc_rdma_rw_ctx_init(struct svcxprt_rdma *rdma, + struct svc_rdma_rw_ctxt *ctxt, + u64 offset, u32 handle, + enum dma_data_direction direction) +{ + int ret; + + ret = rdma_rw_ctx_init(&ctxt->rw_ctx, rdma->sc_qp, rdma->sc_port_num, + ctxt->rw_sg_table.sgl, ctxt->rw_nents, + 0, offset, handle, direction); + if (unlikely(ret < 0)) { + svc_rdma_put_rw_ctxt(rdma, ctxt); + trace_svcrdma_dma_map_rw_err(rdma, ctxt->rw_nents, ret); + } + return ret; +} + /* A chunk context tracks all I/O for moving one Read or Write * chunk. This is a a set of rdma_rw's that handle data movement * for all segments of one chunk. @@ -428,15 +456,13 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info, ctxt = svc_rdma_get_rw_ctxt(rdma, (write_len >> PAGE_SHIFT) + 2); if (!ctxt) - goto out_noctx; + return -ENOMEM; constructor(info, write_len, ctxt); - ret = rdma_rw_ctx_init(&ctxt->rw_ctx, rdma->sc_qp, - rdma->sc_port_num, ctxt->rw_sg_table.sgl, - ctxt->rw_nents, 0, seg_offset, - seg_handle, DMA_TO_DEVICE); + ret = svc_rdma_rw_ctx_init(rdma, ctxt, seg_offset, seg_handle, + DMA_TO_DEVICE); if (ret < 0) - goto out_initerr; + return -EIO; trace_svcrdma_send_wseg(seg_handle, write_len, seg_offset); @@ -455,18 +481,9 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info, return 0; out_overflow: - dprintk("svcrdma: inadequate space in Write chunk (%u)\n", - info->wi_nsegs); + trace_svcrdma_small_wrch_err(rdma, remaining, info->wi_seg_no, + info->wi_nsegs); return -E2BIG; - -out_noctx: - dprintk("svcrdma: no R/W ctxs available\n"); - return -ENOMEM; - -out_initerr: - svc_rdma_put_rw_ctxt(rdma, ctxt); - trace_svcrdma_dma_map_rwctx(rdma, ret); - return -EIO; } /* Send one of an xdr_buf's kvecs by itself. To send a Reply @@ -616,7 +633,7 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info, sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT; ctxt = svc_rdma_get_rw_ctxt(cc->cc_rdma, sge_no); if (!ctxt) - goto out_noctx; + return -ENOMEM; ctxt->rw_nents = sge_no; sg = ctxt->rw_sg_table.sgl; @@ -646,29 +663,18 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info, goto out_overrun; } - ret = rdma_rw_ctx_init(&ctxt->rw_ctx, cc->cc_rdma->sc_qp, - cc->cc_rdma->sc_port_num, - ctxt->rw_sg_table.sgl, ctxt->rw_nents, - 0, offset, rkey, DMA_FROM_DEVICE); + ret = svc_rdma_rw_ctx_init(cc->cc_rdma, ctxt, offset, rkey, + DMA_FROM_DEVICE); if (ret < 0) - goto out_initerr; + return -EIO; list_add(&ctxt->rw_list, &cc->cc_rwctxts); cc->cc_sqecount += ret; return 0; -out_noctx: - dprintk("svcrdma: no R/W ctxs available\n"); - return -ENOMEM; - out_overrun: - dprintk("svcrdma: request overruns rq_pages\n"); + trace_svcrdma_page_overrun_err(cc->cc_rdma, rqstp, info->ri_pageno); return -EINVAL; - -out_initerr: - trace_svcrdma_dma_map_rwctx(cc->cc_rdma, ret); - svc_rdma_put_rw_ctxt(cc->cc_rdma, ctxt); - return -EIO; } /* Walk the segments in the Read chunk starting at @p and construct diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index b6c8643867f2..38e7c3c8c4a9 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -868,12 +868,10 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) __be32 *p; int ret; - /* Create the RDMA response header. xprt->xpt_mutex, - * acquired in svc_send(), serializes RPC replies. The - * code path below that inserts the credit grant value - * into each transport header runs only inside this - * critical section. - */ + ret = -ENOTCONN; + if (svc_xprt_is_dead(xprt)) + goto err0; + ret = -ENOMEM; sctxt = svc_rdma_send_ctxt_get(rdma); if (!sctxt) diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index ea54785db4f8..d38be57b00ed 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -211,7 +211,12 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id, newxprt->sc_ord = param->initiator_depth; sa = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr; - svc_xprt_set_remote(&newxprt->sc_xprt, sa, svc_addr_len(sa)); + newxprt->sc_xprt.xpt_remotelen = svc_addr_len(sa); + memcpy(&newxprt->sc_xprt.xpt_remote, sa, + newxprt->sc_xprt.xpt_remotelen); + snprintf(newxprt->sc_xprt.xpt_remotebuf, + sizeof(newxprt->sc_xprt.xpt_remotebuf) - 1, "%pISc", sa); + /* The remote port is arbitrary and not under the control of the * client ULP. Set it to a fixed value so that the DRC continues * to be effective after a reconnect. @@ -309,11 +314,8 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, struct svcxprt_rdma *cma_xprt; int ret; - dprintk("svcrdma: Creating RDMA listener\n"); - if ((sa->sa_family != AF_INET) && (sa->sa_family != AF_INET6)) { - dprintk("svcrdma: Address family %d is not supported.\n", sa->sa_family); + if (sa->sa_family != AF_INET && sa->sa_family != AF_INET6) return ERR_PTR(-EAFNOSUPPORT); - } cma_xprt = svc_rdma_create_xprt(serv, net); if (!cma_xprt) return ERR_PTR(-ENOMEM); @@ -324,7 +326,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, RDMA_PS_TCP, IB_QPT_RC); if (IS_ERR(listen_id)) { ret = PTR_ERR(listen_id); - dprintk("svcrdma: rdma_create_id failed = %d\n", ret); goto err0; } @@ -333,23 +334,17 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, */ #if IS_ENABLED(CONFIG_IPV6) ret = rdma_set_afonly(listen_id, 1); - if (ret) { - dprintk("svcrdma: rdma_set_afonly failed = %d\n", ret); + if (ret) goto err1; - } #endif ret = rdma_bind_addr(listen_id, sa); - if (ret) { - dprintk("svcrdma: rdma_bind_addr failed = %d\n", ret); + if (ret) goto err1; - } cma_xprt->sc_cm_id = listen_id; ret = rdma_listen(listen_id, RPCRDMA_LISTEN_BACKLOG); - if (ret) { - dprintk("svcrdma: rdma_listen failed = %d\n", ret); + if (ret) goto err1; - } /* * We need to use the address from the cm_id in case the @@ -405,9 +400,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) if (!newxprt) return NULL; - dprintk("svcrdma: newxprt from accept queue = %p, cm_id=%p\n", - newxprt, newxprt->sc_cm_id); - dev = newxprt->sc_cm_id->device; newxprt->sc_port_num = newxprt->sc_cm_id->port_num; @@ -443,21 +435,17 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) newxprt->sc_pd = ib_alloc_pd(dev, 0); if (IS_ERR(newxprt->sc_pd)) { - dprintk("svcrdma: error creating PD for connect request\n"); + trace_svcrdma_pd_err(newxprt, PTR_ERR(newxprt->sc_pd)); goto errout; } newxprt->sc_sq_cq = ib_alloc_cq_any(dev, newxprt, newxprt->sc_sq_depth, IB_POLL_WORKQUEUE); - if (IS_ERR(newxprt->sc_sq_cq)) { - dprintk("svcrdma: error creating SQ CQ for connect request\n"); + if (IS_ERR(newxprt->sc_sq_cq)) goto errout; - } newxprt->sc_rq_cq = ib_alloc_cq_any(dev, newxprt, rq_depth, IB_POLL_WORKQUEUE); - if (IS_ERR(newxprt->sc_rq_cq)) { - dprintk("svcrdma: error creating RQ CQ for connect request\n"); + if (IS_ERR(newxprt->sc_rq_cq)) goto errout; - } memset(&qp_attr, 0, sizeof qp_attr); qp_attr.event_handler = qp_event_handler; @@ -481,7 +469,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) ret = rdma_create_qp(newxprt->sc_cm_id, newxprt->sc_pd, &qp_attr); if (ret) { - dprintk("svcrdma: failed to create QP, ret=%d\n", ret); + trace_svcrdma_qp_err(newxprt, ret); goto errout; } newxprt->sc_qp = newxprt->sc_cm_id->qp; @@ -489,8 +477,10 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) if (!(dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS)) newxprt->sc_snd_w_inv = false; if (!rdma_protocol_iwarp(dev, newxprt->sc_port_num) && - !rdma_ib_or_roce(dev, newxprt->sc_port_num)) + !rdma_ib_or_roce(dev, newxprt->sc_port_num)) { + trace_svcrdma_fabric_err(newxprt, -EINVAL); goto errout; + } if (!svc_rdma_post_recvs(newxprt)) goto errout; @@ -512,15 +502,17 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) conn_param.initiator_depth = min_t(int, newxprt->sc_ord, dev->attrs.max_qp_init_rd_atom); if (!conn_param.initiator_depth) { - dprintk("svcrdma: invalid ORD setting\n"); ret = -EINVAL; + trace_svcrdma_initdepth_err(newxprt, ret); goto errout; } conn_param.private_data = &pmsg; conn_param.private_data_len = sizeof(pmsg); ret = rdma_accept(newxprt->sc_cm_id, &conn_param); - if (ret) + if (ret) { + trace_svcrdma_accept_err(newxprt, ret); goto errout; + } #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) dprintk("svcrdma: new connection %p accepted:\n", newxprt); @@ -535,12 +527,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) dprintk(" ord : %d\n", conn_param.initiator_depth); #endif - trace_svcrdma_xprt_accept(&newxprt->sc_xprt); return &newxprt->sc_xprt; errout: - dprintk("svcrdma: failure accepting new connection rc=%d.\n", ret); - trace_svcrdma_xprt_fail(&newxprt->sc_xprt); /* Take a reference in case the DTO handler runs */ svc_xprt_get(&newxprt->sc_xprt); if (newxprt->sc_qp && !IS_ERR(newxprt->sc_qp)) @@ -578,8 +567,6 @@ static void __svc_rdma_free(struct work_struct *work) container_of(work, struct svcxprt_rdma, sc_work); struct svc_xprt *xprt = &rdma->sc_xprt; - trace_svcrdma_xprt_free(xprt); - if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) ib_drain_qp(rdma->sc_qp); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 845d0be805ec..839c49330785 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2548,8 +2548,16 @@ static int bc_sendto(struct rpc_rqst *req) return sent; } -/* - * The send routine. Borrows from svc_send +/** + * bc_send_request - Send a backchannel Call on a TCP socket + * @req: rpc_rqst containing Call message to be sent + * + * xpt_mutex ensures @rqstp's whole message is written to the socket + * without interruption. + * + * Return values: + * %0 if the message was sent successfully + * %ENOTCONN if the message was not sent */ static int bc_send_request(struct rpc_rqst *req) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 87466607097f..e370ad0edd76 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1739,22 +1739,21 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb, return 0; } -static void tipc_sk_send_ack(struct tipc_sock *tsk) +static struct sk_buff *tipc_sk_build_ack(struct tipc_sock *tsk) { struct sock *sk = &tsk->sk; - struct net *net = sock_net(sk); struct sk_buff *skb = NULL; struct tipc_msg *msg; u32 peer_port = tsk_peer_port(tsk); u32 dnode = tsk_peer_node(tsk); if (!tipc_sk_connected(sk)) - return; + return NULL; skb = tipc_msg_create(CONN_MANAGER, CONN_ACK, INT_H_SIZE, 0, dnode, tsk_own_node(tsk), peer_port, tsk->portid, TIPC_OK); if (!skb) - return; + return NULL; msg = buf_msg(skb); msg_set_conn_ack(msg, tsk->rcv_unacked); tsk->rcv_unacked = 0; @@ -1764,7 +1763,19 @@ static void tipc_sk_send_ack(struct tipc_sock *tsk) tsk->rcv_win = tsk_adv_blocks(tsk->sk.sk_rcvbuf); msg_set_adv_win(msg, tsk->rcv_win); } - tipc_node_xmit_skb(net, skb, dnode, msg_link_selector(msg)); + return skb; +} + +static void tipc_sk_send_ack(struct tipc_sock *tsk) +{ + struct sk_buff *skb; + + skb = tipc_sk_build_ack(tsk); + if (!skb) + return; + + tipc_node_xmit_skb(sock_net(&tsk->sk), skb, tsk_peer_node(tsk), + msg_link_selector(buf_msg(skb))); } static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop) @@ -1938,7 +1949,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, bool peek = flags & MSG_PEEK; int offset, required, copy, copied = 0; int hlen, dlen, err, rc; - bool ack = false; long timeout; /* Catch invalid receive attempts */ @@ -1983,7 +1993,6 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Copy data if msg ok, otherwise return error/partial data */ if (likely(!err)) { - ack = msg_ack_required(hdr); offset = skb_cb->bytes_read; copy = min_t(int, dlen - offset, buflen - copied); rc = skb_copy_datagram_msg(skb, hlen + offset, m, copy); @@ -2011,7 +2020,7 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m, /* Send connection flow control advertisement when applicable */ tsk->rcv_unacked += tsk_inc(tsk, hlen + dlen); - if (ack || tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) + if (tsk->rcv_unacked >= tsk->rcv_win / TIPC_ACK_RATE) tipc_sk_send_ack(tsk); /* Exit if all requested data or FIN/error received */ @@ -2105,9 +2114,11 @@ static void tipc_sk_proto_rcv(struct sock *sk, * tipc_sk_filter_connect - check incoming message for a connection-based socket * @tsk: TIPC socket * @skb: pointer to message buffer. + * @xmitq: for Nagle ACK if any * Returns true if message should be added to receive queue, false otherwise */ -static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) +static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb, + struct sk_buff_head *xmitq) { struct sock *sk = &tsk->sk; struct net *net = sock_net(sk); @@ -2171,8 +2182,17 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb) if (!skb_queue_empty(&sk->sk_write_queue)) tipc_sk_push_backlog(tsk); /* Accept only connection-based messages sent by peer */ - if (likely(con_msg && !err && pport == oport && pnode == onode)) + if (likely(con_msg && !err && pport == oport && + pnode == onode)) { + if (msg_ack_required(hdr)) { + struct sk_buff *skb; + + skb = tipc_sk_build_ack(tsk); + if (skb) + __skb_queue_tail(xmitq, skb); + } return true; + } if (!tsk_peer_msg(tsk, hdr)) return false; if (!err) @@ -2267,7 +2287,7 @@ static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb, while ((skb = __skb_dequeue(&inputq))) { hdr = buf_msg(skb); limit = rcvbuf_limit(sk, skb); - if ((sk_conn && !tipc_sk_filter_connect(tsk, skb)) || + if ((sk_conn && !tipc_sk_filter_connect(tsk, skb, xmitq)) || (!sk_conn && msg_connected(hdr)) || (!grp && msg_in_group(hdr))) err = TIPC_ERR_NO_PORT; diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h index aa015c233898..6ebbec1bedd1 100644 --- a/net/tipc/subscr.h +++ b/net/tipc/subscr.h @@ -96,6 +96,16 @@ void tipc_sub_get(struct tipc_subscription *subscription); (swap_ ? swab32(val__) : val__); \ }) +/* tipc_sub_write - write val_ to field_ of struct sub_ in user endian format + */ +#define tipc_sub_write(sub_, field_, val_) \ + ({ \ + struct tipc_subscr *sub__ = sub_; \ + u32 val__ = val_; \ + int swap_ = !((sub__)->filter & TIPC_FILTER_MASK); \ + (sub__)->field_ = swap_ ? swab32(val__) : val__; \ + }) + /* tipc_evt_write - write val_ to field_ of struct evt_ in user endian format */ #define tipc_evt_write(evt_, field_, val_) \ diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 3a12fc18239b..446af7bbd13e 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -237,8 +237,8 @@ static void tipc_conn_delete_sub(struct tipc_conn *con, struct tipc_subscr *s) if (!s || !memcmp(s, &sub->evt.s, sizeof(*s))) { tipc_sub_unsubscribe(sub); atomic_dec(&tn->subscription_count); - } else if (s) { - break; + if (s) + break; } } spin_unlock_bh(&con->sub_lock); @@ -362,9 +362,10 @@ static int tipc_conn_rcv_sub(struct tipc_topsrv *srv, { struct tipc_net *tn = tipc_net(srv->net); struct tipc_subscription *sub; + u32 s_filter = tipc_sub_read(s, filter); - if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) { - s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL); + if (s_filter & TIPC_SUB_CANCEL) { + tipc_sub_write(s, filter, s_filter & ~TIPC_SUB_CANCEL); tipc_conn_delete_sub(con, s); return 0; } @@ -400,12 +401,15 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) return -EWOULDBLOCK; if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); - ret = tipc_conn_rcv_sub(srv, con, &s); + /* RACE: the connection can be closed in the meantime */ + if (likely(connected(con))) + ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); + if (!ret) + return 0; } - if (ret < 0) - tipc_conn_close(con); + tipc_conn_close(con); return ret; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index c98e602a1a2d..e23f94a5549b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -800,6 +800,8 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); } + if (psock) + sk_psock_put(sk, psock); return err; } more_data: @@ -2081,8 +2083,9 @@ static void tls_data_ready(struct sock *sk) strp_data_ready(&ctx->strp); psock = sk_psock_get(sk); - if (psock && !list_empty(&psock->ingress_msg)) { - ctx->saved_data_ready(sk); + if (psock) { + if (!list_empty(&psock->ingress_msg)) + ctx->saved_data_ready(sk); sk_psock_put(sk, psock); } } diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 709038a4783e..69efc891885f 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -157,7 +157,11 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) { + if (pkt->tap_delivered) + return; + vsock_deliver_tap(virtio_transport_build_skb, pkt); + pkt->tap_delivered = true; } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 8aa415a38814..0285aaa1e93c 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -357,6 +357,12 @@ void x25_disconnect(struct sock *sk, int reason, unsigned char cause, sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } + if (x25->neighbour) { + read_lock_bh(&x25_list_lock); + x25_neigh_put(x25->neighbour); + x25->neighbour = NULL; + read_unlock_bh(&x25_list_lock); + } } /* diff --git a/samples/bpf/lwt_len_hist_user.c b/samples/bpf/lwt_len_hist_user.c index 587b68b1f8dd..430a4b7e353e 100644 --- a/samples/bpf/lwt_len_hist_user.c +++ b/samples/bpf/lwt_len_hist_user.c @@ -15,8 +15,6 @@ #define MAX_INDEX 64 #define MAX_STARS 38 -char bpf_log_buf[BPF_LOG_BUF_SIZE]; - static void stars(char *str, long val, long max, int width) { int i; diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h index 80b4a70315b6..13a35f7cbe66 100644 --- a/samples/trace_events/trace-events-sample.h +++ b/samples/trace_events/trace-events-sample.h @@ -416,7 +416,7 @@ TRACE_EVENT_FN(foo_bar_with_fn, * Note, TRACE_EVENT() itself is simply defined as: * * #define TRACE_EVENT(name, proto, args, tstruct, assign, printk) \ - * DEFINE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \ + * DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, printk); \ * DEFINE_EVENT(name, name, proto, args) * * The DEFINE_EVENT() also can be declared with conditions and reg functions: diff --git a/scripts/decodecode b/scripts/decodecode index ba8b8d5834e6..fbdb325cdf4f 100755 --- a/scripts/decodecode +++ b/scripts/decodecode @@ -126,7 +126,7 @@ faultlinenum=$(( $(wc -l $T.oo | cut -d" " -f1) - \ faultline=`cat $T.dis | head -1 | cut -d":" -f2-` faultline=`echo "$faultline" | sed -e 's/\[/\\\[/g; s/\]/\\\]/g'` -cat $T.oo | sed -e "${faultlinenum}s/^\(.*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" +cat $T.oo | sed -e "${faultlinenum}s/^\([^:]*:\)\(.*\)/\1\*\2\t\t<-- trapping instruction/" echo cat $T.aa cleanup diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile index f22858b2c3d6..80f354289eeb 100644 --- a/scripts/gcc-plugins/Makefile +++ b/scripts/gcc-plugins/Makefile @@ -4,6 +4,7 @@ GCC_PLUGINS_DIR := $(shell $(CC) -print-file-name=plugin) HOST_EXTRACXXFLAGS += -I$(GCC_PLUGINS_DIR)/include -I$(src) -std=gnu++98 -fno-rtti HOST_EXTRACXXFLAGS += -fno-exceptions -fasynchronous-unwind-tables -ggdb HOST_EXTRACXXFLAGS += -Wno-narrowing -Wno-unused-variable -Wno-c++11-compat +HOST_EXTRACXXFLAGS += -Wno-format-diag $(obj)/randomize_layout_plugin.o: $(objtree)/$(obj)/randomize_layout_seed.h quiet_cmd_create_randomize_layout_seed = GENSEED $@ diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 17f06079a712..9ad76b7f3f10 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -35,7 +35,9 @@ #include "ggc.h" #include "timevar.h" +#if BUILDING_GCC_VERSION < 10000 #include "params.h" +#endif #if BUILDING_GCC_VERSION <= 4009 #include "pointer-set.h" @@ -847,6 +849,7 @@ static inline gimple gimple_build_assign_with_ops(enum tree_code subcode, tree l return gimple_build_assign(lhs, subcode, op1, op2 PASS_MEM_STAT); } +#if BUILDING_GCC_VERSION < 10000 template <> template <> inline bool is_a_helper<const ggoto *>::test(const_gimple gs) @@ -860,6 +863,7 @@ inline bool is_a_helper<const greturn *>::test(const_gimple gs) { return gs->code == GIMPLE_RETURN; } +#endif static inline gasm *as_a_gasm(gimple stmt) { diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c index dbd37460c573..cc75eeba0be1 100644 --- a/scripts/gcc-plugins/stackleak_plugin.c +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -51,7 +51,6 @@ static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after) gimple stmt; gcall *stackleak_track_stack; cgraph_node_ptr node; - int frequency; basic_block bb; /* Insert call to void stackleak_track_stack(void) */ @@ -68,9 +67,9 @@ static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after) bb = gimple_bb(stackleak_track_stack); node = cgraph_get_create_node(track_function_decl); gcc_assert(node); - frequency = compute_call_stmt_bb_frequency(current_function_decl, bb); cgraph_create_edge(cgraph_get_node(current_function_decl), node, - stackleak_track_stack, bb->count, frequency); + stackleak_track_stack, bb->count, + compute_call_stmt_bb_frequency(current_function_decl, bb)); } static bool is_alloca(gimple stmt) diff --git a/scripts/gdb/linux/rbtree.py b/scripts/gdb/linux/rbtree.py index 39db889b874c..c4b991607917 100644 --- a/scripts/gdb/linux/rbtree.py +++ b/scripts/gdb/linux/rbtree.py @@ -12,7 +12,7 @@ rb_node_type = utils.CachedType("struct rb_node") def rb_first(root): if root.type == rb_root_type.get_type(): - node = node.address.cast(rb_root_type.get_type().pointer()) + node = root.address.cast(rb_root_type.get_type().pointer()) elif root.type != rb_root_type.get_type().pointer(): raise gdb.GdbError("Must be struct rb_root not {}".format(root.type)) @@ -28,7 +28,7 @@ def rb_first(root): def rb_last(root): if root.type == rb_root_type.get_type(): - node = node.address.cast(rb_root_type.get_type().pointer()) + node = root.address.cast(rb_root_type.get_type().pointer()) elif root.type != rb_root_type.get_type().pointer(): raise gdb.GdbError("Must be struct rb_root not {}".format(root.type)) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 3e8dea6e0a95..6dc3078649fa 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -34,7 +34,7 @@ struct sym_entry { unsigned int len; unsigned int start_pos; unsigned int percpu_absolute; - unsigned char sym[0]; + unsigned char sym[]; }; struct addr_range { diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 20dd08e1f675..2a688b711a9a 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -120,6 +120,17 @@ static void snd_rawmidi_input_event_work(struct work_struct *work) runtime->event(runtime->substream); } +/* buffer refcount management: call with runtime->lock held */ +static inline void snd_rawmidi_buffer_ref(struct snd_rawmidi_runtime *runtime) +{ + runtime->buffer_ref++; +} + +static inline void snd_rawmidi_buffer_unref(struct snd_rawmidi_runtime *runtime) +{ + runtime->buffer_ref--; +} + static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream) { struct snd_rawmidi_runtime *runtime; @@ -669,6 +680,11 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime, if (!newbuf) return -ENOMEM; spin_lock_irq(&runtime->lock); + if (runtime->buffer_ref) { + spin_unlock_irq(&runtime->lock); + kvfree(newbuf); + return -EBUSY; + } oldbuf = runtime->buffer; runtime->buffer = newbuf; runtime->buffer_size = params->buffer_size; @@ -1019,8 +1035,10 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, long result = 0, count1; struct snd_rawmidi_runtime *runtime = substream->runtime; unsigned long appl_ptr; + int err = 0; spin_lock_irqsave(&runtime->lock, flags); + snd_rawmidi_buffer_ref(runtime); while (count > 0 && runtime->avail) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) @@ -1039,16 +1057,19 @@ static long snd_rawmidi_kernel_read1(struct snd_rawmidi_substream *substream, if (userbuf) { spin_unlock_irqrestore(&runtime->lock, flags); if (copy_to_user(userbuf + result, - runtime->buffer + appl_ptr, count1)) { - return result > 0 ? result : -EFAULT; - } + runtime->buffer + appl_ptr, count1)) + err = -EFAULT; spin_lock_irqsave(&runtime->lock, flags); + if (err) + goto out; } result += count1; count -= count1; } + out: + snd_rawmidi_buffer_unref(runtime); spin_unlock_irqrestore(&runtime->lock, flags); - return result; + return result > 0 ? result : err; } long snd_rawmidi_kernel_read(struct snd_rawmidi_substream *substream, @@ -1342,6 +1363,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, return -EAGAIN; } } + snd_rawmidi_buffer_ref(runtime); while (count > 0 && runtime->avail > 0) { count1 = runtime->buffer_size - runtime->appl_ptr; if (count1 > count) @@ -1373,6 +1395,7 @@ static long snd_rawmidi_kernel_write1(struct snd_rawmidi_substream *substream, } __end: count1 = runtime->avail < runtime->buffer_size; + snd_rawmidi_buffer_unref(runtime); spin_unlock_irqrestore(&runtime->lock, flags); if (count1) snd_rawmidi_output_trigger(substream, 1); diff --git a/sound/firewire/amdtp-stream-trace.h b/sound/firewire/amdtp-stream-trace.h index 16c7f6605511..26e7cb555d3c 100644 --- a/sound/firewire/amdtp-stream-trace.h +++ b/sound/firewire/amdtp-stream-trace.h @@ -66,8 +66,7 @@ TRACE_EVENT(amdtp_packet, __entry->irq, __entry->index, __print_array(__get_dynamic_array(cip_header), - __get_dynamic_array_len(cip_header), - sizeof(u8))) + __get_dynamic_array_len(cip_header), 1)) ); #endif diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index c16f63957c5a..dc2302171a71 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5856,6 +5856,15 @@ static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec, } } +static void alc225_fixup_s3_pop_noise(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + if (action != HDA_FIXUP_ACT_PRE_PROBE) + return; + + codec->power_save_node = 1; +} + /* Forcibly assign NID 0x03 to HP/LO while NID 0x02 to SPK for EQ */ static void alc274_fixup_bind_dacs(struct hda_codec *codec, const struct hda_fixup *fix, int action) @@ -5960,6 +5969,7 @@ enum { ALC269_FIXUP_HP_LINE1_MIC1_LED, ALC269_FIXUP_INV_DMIC, ALC269_FIXUP_LENOVO_DOCK, + ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST, ALC269_FIXUP_NO_SHUTUP, ALC286_FIXUP_SONY_MIC_NO_PRESENCE, ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT, @@ -6045,6 +6055,7 @@ enum { ALC233_FIXUP_ACER_HEADSET_MIC, ALC294_FIXUP_LENOVO_MIC_LOCATION, ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, + ALC225_FIXUP_S3_POP_NOISE, ALC700_FIXUP_INTEL_REFERENCE, ALC274_FIXUP_DELL_BIND_DACS, ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, @@ -6080,9 +6091,12 @@ enum { ALC294_FIXUP_ASUS_DUAL_SPK, ALC285_FIXUP_THINKPAD_HEADSET_JACK, ALC294_FIXUP_ASUS_HPE, + ALC294_FIXUP_ASUS_COEF_1B, ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_MUTE_LED, + ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET, + ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -6280,6 +6294,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT }, + [ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269_fixup_limit_int_mic_boost, + .chained = true, + .chain_id = ALC269_FIXUP_LENOVO_DOCK, + }, [ALC269_FIXUP_PINCFG_NO_HP_TO_LINEOUT] = { .type = HDA_FIXUP_FUNC, .v.func = alc269_fixup_pincfg_no_hp_to_lineout, @@ -6932,6 +6952,12 @@ static const struct hda_fixup alc269_fixups[] = { { } }, .chained = true, + .chain_id = ALC225_FIXUP_S3_POP_NOISE + }, + [ALC225_FIXUP_S3_POP_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc225_fixup_s3_pop_noise, + .chained = true, .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC }, [ALC700_FIXUP_INTEL_REFERENCE] = { @@ -7204,6 +7230,17 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC294_FIXUP_ASUS_HEADSET_MIC }, + [ALC294_FIXUP_ASUS_COEF_1B] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Set bit 10 to correct noisy output after reboot from + * Windows 10 (due to pop noise reduction?) + */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x1b }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x4e4b }, + { } + }, + }, [ALC285_FIXUP_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_gpio_led, @@ -7216,6 +7253,22 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc236_fixup_hp_mute_led, }, + [ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + { 0x1a, AC_VERB_SET_PIN_WIDGET_CONTROL, 0xc5 }, + { } + }, + }, + [ALC295_FIXUP_ASUS_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -7383,8 +7436,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x18f1, "Asus FX505DT", ALC256_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE), + SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), + SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), @@ -7410,6 +7465,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE), SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE), SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC), + SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), + SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET), SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8), 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), @@ -7426,7 +7483,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21ca, "Thinkpad L412", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x21e9, "Thinkpad Edge 15", ALC269_FIXUP_SKU_IGNORE), - SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK), + SND_PCI_QUIRK(0x17aa, 0x21f6, "Thinkpad T530", ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST), SND_PCI_QUIRK(0x17aa, 0x21fa, "Thinkpad X230", ALC269_FIXUP_LENOVO_DOCK), SND_PCI_QUIRK(0x17aa, 0x21f3, "Thinkpad T430", ALC269_FIXUP_LENOVO_DOCK), SND_PCI_QUIRK(0x17aa, 0x21fb, "Thinkpad T430s", ALC269_FIXUP_LENOVO_DOCK), @@ -7565,6 +7622,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC269_FIXUP_HEADSET_MODE, .name = "headset-mode"}, {.id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC, .name = "headset-mode-no-hp-mic"}, {.id = ALC269_FIXUP_LENOVO_DOCK, .name = "lenovo-dock"}, + {.id = ALC269_FIXUP_LENOVO_DOCK_LIMIT_BOOST, .name = "lenovo-dock-limit-boost"}, {.id = ALC269_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"}, {.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"}, {.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"}, @@ -7993,6 +8051,18 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60130}, {0x17, 0x90170110}, {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60120}, + {0x17, 0x90170110}, + {0x21, 0x04211030}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x17, 0x90170110}, + {0x21, 0x03211020}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE, + {0x12, 0x90a60130}, + {0x17, 0x90170110}, + {0x21, 0x03211020}), SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x14, 0x90170110}, {0x21, 0x04211020}), @@ -8209,8 +8279,6 @@ static int patch_alc269(struct hda_codec *codec) spec->gen.mixer_nid = 0; break; case 0x10ec0225: - codec->power_save_node = 1; - /* fall through */ case 0x10ec0295: case 0x10ec0299: spec->codec_variant = ALC269_TYPE_ALC225; diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 0260c750e156..bfdc6ad52785 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -549,6 +549,11 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = { .map = trx40_mobo_map, .connector_map = trx40_mobo_connector_map, }, + { /* Asrock TRX40 Creator */ + .id = USB_ID(0x26ce, 0x0a01), + .map = trx40_mobo_map, + .connector_map = trx40_mobo_connector_map, + }, { 0 } /* terminator */ }; diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h index a1df4c5b4f8c..6313c30f5c85 100644 --- a/sound/usb/quirks-table.h +++ b/sound/usb/quirks-table.h @@ -3563,6 +3563,7 @@ AU0828_DEVICE(0x2040, 0x7270, "Hauppauge", "HVR-950Q"), ALC1220_VB_DESKTOP(0x0414, 0xa002), /* Gigabyte TRX40 Aorus Pro WiFi */ ALC1220_VB_DESKTOP(0x0db0, 0x0d64), /* MSI TRX40 Creator */ ALC1220_VB_DESKTOP(0x0db0, 0x543d), /* MSI TRX40 */ +ALC1220_VB_DESKTOP(0x26ce, 0x0a01), /* Asrock TRX40 Creator */ #undef ALC1220_VB_DESKTOP #undef USB_DEVICE_VENDOR_SPEC diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 848a4cc25bed..d8a765be5dfe 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1636,13 +1636,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) msleep(20); - /* Zoom R16/24, Logitech H650e, Jabra 550a needs a tiny delay here, - * otherwise requests like get/set frequency return as failed despite - * actually succeeding. + /* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny + * delay here, otherwise requests like get/set frequency return as + * failed despite actually succeeding. */ if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || chip->usb_id == USB_ID(0x046d, 0x0a46) || - chip->usb_id == USB_ID(0x0b0e, 0x0349)) && + chip->usb_id == USB_ID(0x0b0e, 0x0349) || + chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) usleep_range(1000, 2000); } diff --git a/tools/bootconfig/main.c b/tools/bootconfig/main.c index 16b9a420e6fd..0efaf45f7367 100644 --- a/tools/bootconfig/main.c +++ b/tools/bootconfig/main.c @@ -314,6 +314,7 @@ int apply_xbc(const char *path, const char *xbc_path) ret = delete_xbc(path); if (ret < 0) { pr_err("Failed to delete previous boot config: %d\n", ret); + free(data); return ret; } @@ -321,24 +322,27 @@ int apply_xbc(const char *path, const char *xbc_path) fd = open(path, O_RDWR | O_APPEND); if (fd < 0) { pr_err("Failed to open %s: %d\n", path, fd); + free(data); return fd; } /* TODO: Ensure the @path is initramfs/initrd image */ ret = write(fd, data, size + 8); if (ret < 0) { pr_err("Failed to apply a boot config: %d\n", ret); - return ret; + goto out; } /* Write a magic word of the bootconfig */ ret = write(fd, BOOTCONFIG_MAGIC, BOOTCONFIG_MAGIC_LEN); if (ret < 0) { pr_err("Failed to apply a boot config magic: %d\n", ret); - return ret; + goto out; } + ret = 0; +out: close(fd); free(data); - return 0; + return ret; } int usage(void) diff --git a/tools/cgroup/iocost_monitor.py b/tools/cgroup/iocost_monitor.py index 7427a5ee761b..9d8e9613008a 100644 --- a/tools/cgroup/iocost_monitor.py +++ b/tools/cgroup/iocost_monitor.py @@ -159,7 +159,12 @@ class IocgStat: else: self.inflight_pct = 0 - self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + # vdebt used to be an atomic64_t and is now u64, support both + try: + self.debt_ms = iocg.abs_vdebt.counter.value_() / VTIME_PER_USEC / 1000 + except: + self.debt_ms = iocg.abs_vdebt.value_() / VTIME_PER_USEC / 1000 + self.use_delay = blkg.use_delay.counter.value_() self.delay_ms = blkg.delay_nsec.counter.value_() / 1_000_000 diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h index f3f3c3fb98cb..48a9c7c69ef1 100644 --- a/tools/lib/bpf/bpf_tracing.h +++ b/tools/lib/bpf/bpf_tracing.h @@ -148,11 +148,11 @@ struct pt_regs; #define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[4]) #define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[5]) #define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[6]) -#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), grps[14]) +#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[14]) #define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[11]) #define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[2]) #define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), gprs[15]) -#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), pdw.addr) +#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_S390 *)(x), psw.addr) #elif defined(bpf_target_arm) diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4b170fd08a28..3c6da70e6084 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -72,6 +72,17 @@ static struct instruction *next_insn_same_func(struct objtool_file *file, return find_insn(file, func->cfunc->sec, func->cfunc->offset); } +static struct instruction *prev_insn_same_sym(struct objtool_file *file, + struct instruction *insn) +{ + struct instruction *prev = list_prev_entry(insn, list); + + if (&prev->list != &file->insn_list && prev->func == insn->func) + return prev; + + return NULL; +} + #define func_for_each_insn(file, func, insn) \ for (insn = find_insn(file, func->sec, func->offset); \ insn; \ @@ -1050,8 +1061,8 @@ static struct rela *find_jump_table(struct objtool_file *file, * it. */ for (; - &insn->list != &file->insn_list && insn->func && insn->func->pfunc == func; - insn = insn->first_jump_src ?: list_prev_entry(insn, list)) { + insn && insn->func && insn->func->pfunc == func; + insn = insn->first_jump_src ?: prev_insn_same_sym(file, insn)) { if (insn != orig_insn && insn->type == INSN_JUMP_DYNAMIC) break; @@ -1449,7 +1460,7 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s struct cfi_reg *cfa = &state->cfa; struct stack_op *op = &insn->stack_op; - if (cfa->base != CFI_SP) + if (cfa->base != CFI_SP && cfa->base != CFI_SP_INDIRECT) return 0; /* push */ diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h index 0b79c2353a21..12e01ac190ec 100644 --- a/tools/objtool/elf.h +++ b/tools/objtool/elf.h @@ -87,9 +87,10 @@ struct elf { #define OFFSET_STRIDE (1UL << OFFSET_STRIDE_BITS) #define OFFSET_STRIDE_MASK (~(OFFSET_STRIDE - 1)) -#define for_offset_range(_offset, _start, _end) \ - for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ - _offset <= ((_end) & OFFSET_STRIDE_MASK); \ +#define for_offset_range(_offset, _start, _end) \ + for (_offset = ((_start) & OFFSET_STRIDE_MASK); \ + _offset >= ((_start) & OFFSET_STRIDE_MASK) && \ + _offset <= ((_end) & OFFSET_STRIDE_MASK); \ _offset += OFFSET_STRIDE) static inline u32 sec_offset_hash(struct section *sec, unsigned long offset) diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c index 56d80adcf4bd..6b9dce431d41 100644 --- a/tools/testing/selftests/bpf/prog_tests/mmap.c +++ b/tools/testing/selftests/bpf/prog_tests/mmap.c @@ -217,6 +217,14 @@ void test_mmap(void) munmap(tmp2, 4 * page_size); + /* map all 4 pages, but with pg_off=1 page, should fail */ + tmp1 = mmap(NULL, 4 * page_size, PROT_READ, MAP_SHARED | MAP_FIXED, + data_map_fd, page_size /* initial page shift */); + if (CHECK(tmp1 != MAP_FAILED, "adv_mmap7", "unexpected success")) { + munmap(tmp1, 4 * page_size); + goto cleanup; + } + tmp1 = mmap(NULL, map_sz, PROT_READ, MAP_SHARED, data_map_fd, 0); if (CHECK(tmp1 == MAP_FAILED, "last_mmap", "failed %d\n", errno)) goto cleanup; diff --git a/tools/testing/selftests/bpf/progs/test_overhead.c b/tools/testing/selftests/bpf/progs/test_overhead.c index 56a50b25cd33..abb7344b531f 100644 --- a/tools/testing/selftests/bpf/progs/test_overhead.c +++ b/tools/testing/selftests/bpf/progs/test_overhead.c @@ -30,13 +30,13 @@ int prog3(struct bpf_raw_tracepoint_args *ctx) SEC("fentry/__set_task_comm") int BPF_PROG(prog4, struct task_struct *tsk, const char *buf, bool exec) { - return !tsk; + return 0; } SEC("fexit/__set_task_comm") int BPF_PROG(prog5, struct task_struct *tsk, const char *buf, bool exec) { - return !tsk; + return 0; } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index cd5e1f602ac9..909da9cdda97 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -351,6 +351,7 @@ static int test_alloc_errors(char *heap_name) } printf("Expected error checking passed\n"); + ret = 0; out: if (dmabuf_fd >= 0) close(dmabuf_fd); diff --git a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c index 11eee0b60040..d979ff14775a 100644 --- a/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c +++ b/tools/testing/selftests/filesystems/epoll/epoll_wakeup_test.c @@ -3,6 +3,7 @@ #define _GNU_SOURCE #include <poll.h> #include <unistd.h> +#include <assert.h> #include <signal.h> #include <pthread.h> #include <sys/epoll.h> @@ -3136,4 +3137,149 @@ TEST(epoll59) close(ctx.sfd[0]); } +enum { + EPOLL60_EVENTS_NR = 10, +}; + +struct epoll60_ctx { + volatile int stopped; + int ready; + int waiters; + int epfd; + int evfd[EPOLL60_EVENTS_NR]; +}; + +static void *epoll60_wait_thread(void *ctx_) +{ + struct epoll60_ctx *ctx = ctx_; + struct epoll_event e; + sigset_t sigmask; + uint64_t v; + int ret; + + /* Block SIGUSR1 */ + sigemptyset(&sigmask); + sigaddset(&sigmask, SIGUSR1); + sigprocmask(SIG_SETMASK, &sigmask, NULL); + + /* Prepare empty mask for epoll_pwait() */ + sigemptyset(&sigmask); + + while (!ctx->stopped) { + /* Mark we are ready */ + __atomic_fetch_add(&ctx->ready, 1, __ATOMIC_ACQUIRE); + + /* Start when all are ready */ + while (__atomic_load_n(&ctx->ready, __ATOMIC_ACQUIRE) && + !ctx->stopped); + + /* Account this waiter */ + __atomic_fetch_add(&ctx->waiters, 1, __ATOMIC_ACQUIRE); + + ret = epoll_pwait(ctx->epfd, &e, 1, 2000, &sigmask); + if (ret != 1) { + /* We expect only signal delivery on stop */ + assert(ret < 0 && errno == EINTR && "Lost wakeup!\n"); + assert(ctx->stopped); + break; + } + + ret = read(e.data.fd, &v, sizeof(v)); + /* Since we are on ET mode, thus each thread gets its own fd. */ + assert(ret == sizeof(v)); + + __atomic_fetch_sub(&ctx->waiters, 1, __ATOMIC_RELEASE); + } + + return NULL; +} + +static inline unsigned long long msecs(void) +{ + struct timespec ts; + unsigned long long msecs; + + clock_gettime(CLOCK_REALTIME, &ts); + msecs = ts.tv_sec * 1000ull; + msecs += ts.tv_nsec / 1000000ull; + + return msecs; +} + +static inline int count_waiters(struct epoll60_ctx *ctx) +{ + return __atomic_load_n(&ctx->waiters, __ATOMIC_ACQUIRE); +} + +TEST(epoll60) +{ + struct epoll60_ctx ctx = { 0 }; + pthread_t waiters[ARRAY_SIZE(ctx.evfd)]; + struct epoll_event e; + int i, n, ret; + + signal(SIGUSR1, signal_handler); + + ctx.epfd = epoll_create1(0); + ASSERT_GE(ctx.epfd, 0); + + /* Create event fds */ + for (i = 0; i < ARRAY_SIZE(ctx.evfd); i++) { + ctx.evfd[i] = eventfd(0, EFD_NONBLOCK); + ASSERT_GE(ctx.evfd[i], 0); + + e.events = EPOLLIN | EPOLLET; + e.data.fd = ctx.evfd[i]; + ASSERT_EQ(epoll_ctl(ctx.epfd, EPOLL_CTL_ADD, ctx.evfd[i], &e), 0); + } + + /* Create waiter threads */ + for (i = 0; i < ARRAY_SIZE(waiters); i++) + ASSERT_EQ(pthread_create(&waiters[i], NULL, + epoll60_wait_thread, &ctx), 0); + + for (i = 0; i < 300; i++) { + uint64_t v = 1, ms; + + /* Wait for all to be ready */ + while (__atomic_load_n(&ctx.ready, __ATOMIC_ACQUIRE) != + ARRAY_SIZE(ctx.evfd)) + ; + + /* Steady, go */ + __atomic_fetch_sub(&ctx.ready, ARRAY_SIZE(ctx.evfd), + __ATOMIC_ACQUIRE); + + /* Wait all have gone to kernel */ + while (count_waiters(&ctx) != ARRAY_SIZE(ctx.evfd)) + ; + + /* 1ms should be enough to schedule away */ + usleep(1000); + + /* Quickly signal all handles at once */ + for (n = 0; n < ARRAY_SIZE(ctx.evfd); n++) { + ret = write(ctx.evfd[n], &v, sizeof(v)); + ASSERT_EQ(ret, sizeof(v)); + } + + /* Busy loop for 1s and wait for all waiters to wake up */ + ms = msecs(); + while (count_waiters(&ctx) && msecs() < ms + 1000) + ; + + ASSERT_EQ(count_waiters(&ctx), 0); + } + ctx.stopped = 1; + /* Stop waiters */ + for (i = 0; i < ARRAY_SIZE(waiters); i++) + ret = pthread_kill(waiters[i], SIGUSR1); + for (i = 0; i < ARRAY_SIZE(waiters); i++) + pthread_join(waiters[i], NULL); + + for (i = 0; i < ARRAY_SIZE(waiters); i++) + close(ctx.evfd[i]); + close(ctx.epfd); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 063ecb290a5a..a4605b5ee66d 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -17,6 +17,7 @@ echo " -v|--verbose Increase verbosity of test messages" echo " -vv Alias of -v -v (Show all results in stdout)" echo " -vvv Alias of -v -v -v (Show all commands immediately)" echo " --fail-unsupported Treat UNSUPPORTED as a failure" +echo " --fail-unresolved Treat UNRESOLVED as a failure" echo " -d|--debug Debug mode (trace all shell commands)" echo " -l|--logdir <dir> Save logs on the <dir>" echo " If <dir> is -, all logs output in console only" @@ -29,8 +30,25 @@ err_ret=1 # kselftest skip code is 4 err_skip=4 +# cgroup RT scheduling prevents chrt commands from succeeding, which +# induces failures in test wakeup tests. Disable for the duration of +# the tests. + +readonly sched_rt_runtime=/proc/sys/kernel/sched_rt_runtime_us + +sched_rt_runtime_orig=$(cat $sched_rt_runtime) + +setup() { + echo -1 > $sched_rt_runtime +} + +cleanup() { + echo $sched_rt_runtime_orig > $sched_rt_runtime +} + errexit() { # message echo "Error: $1" 1>&2 + cleanup exit $err_ret } @@ -39,6 +57,8 @@ if [ `id -u` -ne 0 ]; then errexit "this must be run by root user" fi +setup + # Utilities absdir() { # file_path (cd `dirname $1`; pwd) @@ -93,6 +113,10 @@ parse_opts() { # opts UNSUPPORTED_RESULT=1 shift 1 ;; + --fail-unresolved) + UNRESOLVED_RESULT=1 + shift 1 + ;; --logdir|-l) LOG_DIR=$2 shift 2 @@ -157,6 +181,7 @@ KEEP_LOG=0 DEBUG=0 VERBOSE=0 UNSUPPORTED_RESULT=0 +UNRESOLVED_RESULT=0 STOP_FAILURE=0 # Parse command-line options parse_opts $* @@ -235,6 +260,7 @@ TOTAL_RESULT=0 INSTANCE= CASENO=0 + testcase() { # testfile CASENO=$((CASENO+1)) desc=`grep "^#[ \t]*description:" $1 | cut -f2 -d:` @@ -260,7 +286,7 @@ eval_result() { # sigval $UNRESOLVED) prlog " [${color_blue}UNRESOLVED${color_reset}]" UNRESOLVED_CASES="$UNRESOLVED_CASES $CASENO" - return 1 # this is a kind of bug.. something happened. + return $UNRESOLVED_RESULT # depends on use case ;; $UNTESTED) prlog " [${color_blue}UNTESTED${color_reset}]" @@ -273,7 +299,7 @@ eval_result() { # sigval return $UNSUPPORTED_RESULT # depends on use case ;; $XFAIL) - prlog " [${color_red}XFAIL${color_reset}]" + prlog " [${color_green}XFAIL${color_reset}]" XFAILED_CASES="$XFAILED_CASES $CASENO" return 0 ;; @@ -406,5 +432,7 @@ prlog "# of unsupported: " `echo $UNSUPPORTED_CASES | wc -w` prlog "# of xfailed: " `echo $XFAILED_CASES | wc -w` prlog "# of undefined(test bug): " `echo $UNDEFINED_CASES | wc -w` +cleanup + # if no error, return 0 exit $TOTAL_RESULT diff --git a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc index cbd174334a48..2b82c80edf69 100644 --- a/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc +++ b/tools/testing/selftests/ftrace/test.d/preemptirq/irqsoff_tracer.tc @@ -17,7 +17,14 @@ unsup() { #msg exit_unsupported } -modprobe $MOD || unsup "$MOD module not available" +unres() { #msg + reset_tracer + rmmod $MOD || true + echo $1 + exit_unresolved +} + +modprobe $MOD || unres "$MOD module not available" rmmod $MOD grep -q "preemptoff" available_tracers || unsup "preemptoff tracer not enabled" diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 712a2ddd2a27..42f4f49f2a48 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -5,8 +5,34 @@ all: top_srcdir = ../../../.. KSFT_KHDR_INSTALL := 1 + +# For cross-builds to work, UNAME_M has to map to ARCH and arch specific +# directories and targets in this Makefile. "uname -m" doesn't map to +# arch specific sub-directory names. +# +# UNAME_M variable to used to run the compiles pointing to the right arch +# directories and build the right targets for these supported architectures. +# +# TEST_GEN_PROGS and LIBKVM are set using UNAME_M variable. +# LINUX_TOOL_ARCH_INCLUDE is set using ARCH variable. +# +# x86_64 targets are named to include x86_64 as a suffix and directories +# for includes are in x86_64 sub-directory. s390x and aarch64 follow the +# same convention. "uname -m" doesn't result in the correct mapping for +# s390x and aarch64. +# +# No change necessary for x86_64 UNAME_M := $(shell uname -m) +# Set UNAME_M for arm64 compile/install to work +ifeq ($(ARCH),arm64) + UNAME_M := aarch64 +endif +# Set UNAME_M s390x compile/install to work +ifeq ($(ARCH),s390) + UNAME_M := s390x +endif + LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c @@ -28,6 +54,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test +TEST_GEN_PROGS_x86_64 += x86_64/debug_regs TEST_GEN_PROGS_x86_64 += clear_dirty_log_test TEST_GEN_PROGS_x86_64 += demand_paging_test TEST_GEN_PROGS_x86_64 += dirty_log_test @@ -53,7 +80,7 @@ LIBKVM += $(LIBKVM_$(UNAME_M)) INSTALL_HDR_PATH = $(top_srcdir)/usr LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include -LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include +LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \ -I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \ @@ -84,6 +111,7 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) $(AR) crs $@ $^ +x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) diff --git a/tools/testing/selftests/kvm/include/evmcs.h b/tools/testing/selftests/kvm/include/evmcs.h index d8f4d6bfe05d..a034438b6266 100644 --- a/tools/testing/selftests/kvm/include/evmcs.h +++ b/tools/testing/selftests/kvm/include/evmcs.h @@ -219,8 +219,8 @@ struct hv_enlightened_vmcs { #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \ (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1)) -struct hv_enlightened_vmcs *current_evmcs; -struct hv_vp_assist_page *current_vp_assist; +extern struct hv_enlightened_vmcs *current_evmcs; +extern struct hv_vp_assist_page *current_vp_assist; int vcpu_enable_evmcs(struct kvm_vm *vm, int vcpu_id); diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index a99b875f50d2..92e184a422ee 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -143,6 +143,8 @@ struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid); void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid); +void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_guest_debug *debug); void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_mp_state *mp_state); void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 8a3523d4434f..9622431069bc 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1201,6 +1201,15 @@ void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid) ret, errno); } +void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid, + struct kvm_guest_debug *debug) +{ + struct vcpu *vcpu = vcpu_find(vm, vcpuid); + int ret = ioctl(vcpu->fd, KVM_SET_GUEST_DEBUG, debug); + + TEST_ASSERT(ret == 0, "KVM_SET_GUEST_DEBUG failed: %d", ret); +} + /* * VM VCPU Set MP State * diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c index 6f17f69394be..4ae104f6ce69 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c @@ -17,6 +17,9 @@ bool enable_evmcs; +struct hv_enlightened_vmcs *current_evmcs; +struct hv_vp_assist_page *current_vp_assist; + struct eptPageTableEntry { uint64_t readable:1; uint64_t writable:1; diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c new file mode 100644 index 000000000000..8162c58a1234 --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -0,0 +1,202 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KVM guest debug register tests + * + * Copyright (C) 2020, Red Hat, Inc. + */ +#include <stdio.h> +#include <string.h> +#include "kvm_util.h" +#include "processor.h" + +#define VCPU_ID 0 + +#define DR6_BD (1 << 13) +#define DR7_GD (1 << 13) + +/* For testing data access debug BP */ +uint32_t guest_value; + +extern unsigned char sw_bp, hw_bp, write_data, ss_start, bd_start; + +static void guest_code(void) +{ + /* + * Software BP tests. + * + * NOTE: sw_bp need to be before the cmd here, because int3 is an + * exception rather than a normal trap for KVM_SET_GUEST_DEBUG (we + * capture it using the vcpu exception bitmap). + */ + asm volatile("sw_bp: int3"); + + /* Hardware instruction BP test */ + asm volatile("hw_bp: nop"); + + /* Hardware data BP test */ + asm volatile("mov $1234,%%rax;\n\t" + "mov %%rax,%0;\n\t write_data:" + : "=m" (guest_value) : : "rax"); + + /* Single step test, covers 2 basic instructions and 2 emulated */ + asm volatile("ss_start: " + "xor %%rax,%%rax\n\t" + "cpuid\n\t" + "movl $0x1a0,%%ecx\n\t" + "rdmsr\n\t" + : : : "rax", "ecx"); + + /* DR6.BD test */ + asm volatile("bd_start: mov %%dr0, %%rax" : : : "rax"); + GUEST_DONE(); +} + +#define CLEAR_DEBUG() memset(&debug, 0, sizeof(debug)) +#define APPLY_DEBUG() vcpu_set_guest_debug(vm, VCPU_ID, &debug) +#define CAST_TO_RIP(v) ((unsigned long long)&(v)) +#define SET_RIP(v) do { \ + vcpu_regs_get(vm, VCPU_ID, ®s); \ + regs.rip = (v); \ + vcpu_regs_set(vm, VCPU_ID, ®s); \ + } while (0) +#define MOVE_RIP(v) SET_RIP(regs.rip + (v)); + +int main(void) +{ + struct kvm_guest_debug debug; + unsigned long long target_dr6, target_rip; + struct kvm_regs regs; + struct kvm_run *run; + struct kvm_vm *vm; + struct ucall uc; + uint64_t cmd; + int i; + /* Instruction lengths starting at ss_start */ + int ss_size[4] = { + 3, /* xor */ + 2, /* cpuid */ + 5, /* mov */ + 2, /* rdmsr */ + }; + + if (!kvm_check_cap(KVM_CAP_SET_GUEST_DEBUG)) { + print_skip("KVM_CAP_SET_GUEST_DEBUG not supported"); + return 0; + } + + vm = vm_create_default(VCPU_ID, 0, guest_code); + vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid()); + run = vcpu_state(vm, VCPU_ID); + + /* Test software BPs - int3 */ + CLEAR_DEBUG(); + debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP; + APPLY_DEBUG(); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && + run->debug.arch.exception == BP_VECTOR && + run->debug.arch.pc == CAST_TO_RIP(sw_bp), + "INT3: exit %d exception %d rip 0x%llx (should be 0x%llx)", + run->exit_reason, run->debug.arch.exception, + run->debug.arch.pc, CAST_TO_RIP(sw_bp)); + MOVE_RIP(1); + + /* Test instruction HW BP over DR[0-3] */ + for (i = 0; i < 4; i++) { + CLEAR_DEBUG(); + debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; + debug.arch.debugreg[i] = CAST_TO_RIP(hw_bp); + debug.arch.debugreg[7] = 0x400 | (1UL << (2*i+1)); + APPLY_DEBUG(); + vcpu_run(vm, VCPU_ID); + target_dr6 = 0xffff0ff0 | (1UL << i); + TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && + run->debug.arch.exception == DB_VECTOR && + run->debug.arch.pc == CAST_TO_RIP(hw_bp) && + run->debug.arch.dr6 == target_dr6, + "INS_HW_BP (DR%d): exit %d exception %d rip 0x%llx " + "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)", + i, run->exit_reason, run->debug.arch.exception, + run->debug.arch.pc, CAST_TO_RIP(hw_bp), + run->debug.arch.dr6, target_dr6); + } + /* Skip "nop" */ + MOVE_RIP(1); + + /* Test data access HW BP over DR[0-3] */ + for (i = 0; i < 4; i++) { + CLEAR_DEBUG(); + debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; + debug.arch.debugreg[i] = CAST_TO_RIP(guest_value); + debug.arch.debugreg[7] = 0x00000400 | (1UL << (2*i+1)) | + (0x000d0000UL << (4*i)); + APPLY_DEBUG(); + vcpu_run(vm, VCPU_ID); + target_dr6 = 0xffff0ff0 | (1UL << i); + TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && + run->debug.arch.exception == DB_VECTOR && + run->debug.arch.pc == CAST_TO_RIP(write_data) && + run->debug.arch.dr6 == target_dr6, + "DATA_HW_BP (DR%d): exit %d exception %d rip 0x%llx " + "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)", + i, run->exit_reason, run->debug.arch.exception, + run->debug.arch.pc, CAST_TO_RIP(write_data), + run->debug.arch.dr6, target_dr6); + /* Rollback the 4-bytes "mov" */ + MOVE_RIP(-7); + } + /* Skip the 4-bytes "mov" */ + MOVE_RIP(7); + + /* Test single step */ + target_rip = CAST_TO_RIP(ss_start); + target_dr6 = 0xffff4ff0ULL; + vcpu_regs_get(vm, VCPU_ID, ®s); + for (i = 0; i < (sizeof(ss_size) / sizeof(ss_size[0])); i++) { + target_rip += ss_size[i]; + CLEAR_DEBUG(); + debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP; + debug.arch.debugreg[7] = 0x00000400; + APPLY_DEBUG(); + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && + run->debug.arch.exception == DB_VECTOR && + run->debug.arch.pc == target_rip && + run->debug.arch.dr6 == target_dr6, + "SINGLE_STEP[%d]: exit %d exception %d rip 0x%llx " + "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)", + i, run->exit_reason, run->debug.arch.exception, + run->debug.arch.pc, target_rip, run->debug.arch.dr6, + target_dr6); + } + + /* Finally test global disable */ + CLEAR_DEBUG(); + debug.control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP; + debug.arch.debugreg[7] = 0x400 | DR7_GD; + APPLY_DEBUG(); + vcpu_run(vm, VCPU_ID); + target_dr6 = 0xffff0ff0 | DR6_BD; + TEST_ASSERT(run->exit_reason == KVM_EXIT_DEBUG && + run->debug.arch.exception == DB_VECTOR && + run->debug.arch.pc == CAST_TO_RIP(bd_start) && + run->debug.arch.dr6 == target_dr6, + "DR7.GD: exit %d exception %d rip 0x%llx " + "(should be 0x%llx) dr6 0x%llx (should be 0x%llx)", + run->exit_reason, run->debug.arch.exception, + run->debug.arch.pc, target_rip, run->debug.arch.dr6, + target_dr6); + + /* Disable all debug controls, run to the end */ + CLEAR_DEBUG(); + APPLY_DEBUG(); + + vcpu_run(vm, VCPU_ID); + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, "KVM_EXIT_IO"); + cmd = get_ucall(vm, VCPU_ID, &uc); + TEST_ASSERT(cmd == UCALL_DONE, "UCALL_DONE"); + + kvm_vm_free(vm); + + return 0; +} diff --git a/tools/testing/selftests/lkdtm/run.sh b/tools/testing/selftests/lkdtm/run.sh index dadf819148a4..ee64ff8df8f4 100755 --- a/tools/testing/selftests/lkdtm/run.sh +++ b/tools/testing/selftests/lkdtm/run.sh @@ -25,13 +25,13 @@ fi # Figure out which test to run from our script name. test=$(basename $0 .sh) # Look up details about the test from master list of LKDTM tests. -line=$(egrep '^#?'"$test"'\b' tests.txt) +line=$(grep -E '^#?'"$test"'\b' tests.txt) if [ -z "$line" ]; then echo "Skipped: missing test '$test' in tests.txt" exit $KSELFTEST_SKIP_TEST fi # Check that the test is known to LKDTM. -if ! egrep -q '^'"$test"'$' "$TRIGGER" ; then +if ! grep -E -q '^'"$test"'$' "$TRIGGER" ; then echo "Skipped: test '$test' missing in $TRIGGER!" exit $KSELFTEST_SKIP_TEST fi @@ -59,30 +59,32 @@ if [ -z "$expect" ]; then expect="call trace:" fi -# Clear out dmesg for output reporting -dmesg -c >/dev/null - # Prepare log for report checking -LOG=$(mktemp --tmpdir -t lkdtm-XXXXXX) +LOG=$(mktemp --tmpdir -t lkdtm-log-XXXXXX) +DMESG=$(mktemp --tmpdir -t lkdtm-dmesg-XXXXXX) cleanup() { - rm -f "$LOG" + rm -f "$LOG" "$DMESG" } trap cleanup EXIT +# Save existing dmesg so we can detect new content below +dmesg > "$DMESG" + # Most shells yell about signals and we're expecting the "cat" process # to usually be killed by the kernel. So we have to run it in a sub-shell # and silence errors. ($SHELL -c 'cat <(echo '"$test"') >'"$TRIGGER" 2>/dev/null) || true # Record and dump the results -dmesg -c >"$LOG" +dmesg | diff --changed-group-format='%>' --unchanged-group-format='' "$DMESG" - > "$LOG" || true + cat "$LOG" # Check for expected output -if egrep -qi "$expect" "$LOG" ; then +if grep -E -qi "$expect" "$LOG" ; then echo "$test: saw '$expect': ok" exit 0 else - if egrep -qi XFAIL: "$LOG" ; then + if grep -E -qi XFAIL: "$LOG" ; then echo "$test: saw 'XFAIL': [SKIP]" exit $KSELFTEST_SKIP_TEST else diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 9172746b6cf0..15f4f46ca3a9 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -30,7 +30,7 @@ ret=0 cleanup() { - rm -f $out + rm -f $err ip netns del $ns1 } diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 35505b31e5cc..4555f88252ba 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -165,9 +165,10 @@ void *child_thread(void *arg) socklen_t zc_len = sizeof(zc); int res; + memset(&zc, 0, sizeof(zc)); zc.address = (__u64)((unsigned long)addr); zc.length = chunk_size; - zc.recv_skip_hint = 0; + res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, &zc, &zc_len); if (res == -1) @@ -281,12 +282,14 @@ static void setup_sockaddr(int domain, const char *str_addr, static void do_accept(int fdlisten) { pthread_attr_t attr; + int rcvlowat; pthread_attr_init(&attr); pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED); + rcvlowat = chunk_size; if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT, - &chunk_size, sizeof(chunk_size)) == -1) { + &rcvlowat, sizeof(rcvlowat)) == -1) { perror("setsockopt SO_RCVLOWAT"); } diff --git a/tools/testing/selftests/nsfs/pidns.c b/tools/testing/selftests/nsfs/pidns.c index e0d86e1668c0..e3c772c6a7c7 100644 --- a/tools/testing/selftests/nsfs/pidns.c +++ b/tools/testing/selftests/nsfs/pidns.c @@ -27,7 +27,7 @@ #define __stack_aligned__ __attribute__((aligned(16))) struct cr_clone_arg { char stack[128] __stack_aligned__; - char stack_ptr[0]; + char stack_ptr[]; }; static int child(void *args) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 936e1ca9410e..17a1f53ceba0 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -48,8 +48,11 @@ cleanup() { exec 2>/dev/null printf "$orig_message_cost" > /proc/sys/net/core/message_cost ip0 link del dev wg0 + ip0 link del dev wg1 ip1 link del dev wg0 + ip1 link del dev wg1 ip2 link del dev wg0 + ip2 link del dev wg1 local to_kill="$(ip netns pids $netns0) $(ip netns pids $netns1) $(ip netns pids $netns2)" [[ -n $to_kill ]] && kill $to_kill pp ip netns del $netns1 @@ -77,18 +80,20 @@ ip0 link set wg0 netns $netns2 key1="$(pp wg genkey)" key2="$(pp wg genkey)" key3="$(pp wg genkey)" +key4="$(pp wg genkey)" pub1="$(pp wg pubkey <<<"$key1")" pub2="$(pp wg pubkey <<<"$key2")" pub3="$(pp wg pubkey <<<"$key3")" +pub4="$(pp wg pubkey <<<"$key4")" psk="$(pp wg genpsk)" [[ -n $key1 && -n $key2 && -n $psk ]] configure_peers() { ip1 addr add 192.168.241.1/24 dev wg0 - ip1 addr add fd00::1/24 dev wg0 + ip1 addr add fd00::1/112 dev wg0 ip2 addr add 192.168.241.2/24 dev wg0 - ip2 addr add fd00::2/24 dev wg0 + ip2 addr add fd00::2/112 dev wg0 n1 wg set wg0 \ private-key <(echo "$key1") \ @@ -230,9 +235,38 @@ n1 ping -W 1 -c 1 192.168.241.2 n1 wg set wg0 private-key <(echo "$key3") n2 wg set wg0 peer "$pub3" preshared-key <(echo "$psk") allowed-ips 192.168.241.1/32 peer "$pub1" remove n1 ping -W 1 -c 1 192.168.241.2 +n2 wg set wg0 peer "$pub3" remove + +# Test that we can route wg through wg +ip1 addr flush dev wg0 +ip2 addr flush dev wg0 +ip1 addr add fd00::5:1/112 dev wg0 +ip2 addr add fd00::5:2/112 dev wg0 +n1 wg set wg0 private-key <(echo "$key1") peer "$pub2" preshared-key <(echo "$psk") allowed-ips fd00::5:2/128 endpoint 127.0.0.1:2 +n2 wg set wg0 private-key <(echo "$key2") listen-port 2 peer "$pub1" preshared-key <(echo "$psk") allowed-ips fd00::5:1/128 endpoint 127.212.121.99:9998 +ip1 link add wg1 type wireguard +ip2 link add wg1 type wireguard +ip1 addr add 192.168.241.1/24 dev wg1 +ip1 addr add fd00::1/112 dev wg1 +ip2 addr add 192.168.241.2/24 dev wg1 +ip2 addr add fd00::2/112 dev wg1 +ip1 link set mtu 1340 up dev wg1 +ip2 link set mtu 1340 up dev wg1 +n1 wg set wg1 listen-port 5 private-key <(echo "$key3") peer "$pub4" allowed-ips 192.168.241.2/32,fd00::2/128 endpoint [fd00::5:2]:5 +n2 wg set wg1 listen-port 5 private-key <(echo "$key4") peer "$pub3" allowed-ips 192.168.241.1/32,fd00::1/128 endpoint [fd00::5:1]:5 +tests +# Try to set up a routing loop between the two namespaces +ip1 link set netns $netns0 dev wg1 +ip0 addr add 192.168.241.1/24 dev wg1 +ip0 link set up dev wg1 +n0 ping -W 1 -c 1 192.168.241.2 +n1 wg set wg0 peer "$pub2" endpoint 192.168.241.2:7 +ip2 link del wg0 +ip2 link del wg1 +! n0 ping -W 1 -c 10 -f 192.168.241.2 || false # Should not crash kernel +ip0 link del wg1 ip1 link del wg0 -ip2 link del wg0 # Test using NAT. We now change the topology to this: # ┌────────────────────────────────────────┐ ┌────────────────────────────────────────────────┐ ┌────────────────────────────────────────┐ @@ -282,6 +316,20 @@ pp sleep 3 n2 ping -W 1 -c 1 192.168.241.1 n1 wg set wg0 peer "$pub2" persistent-keepalive 0 +# Test that onion routing works, even when it loops +n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 +ip1 addr add 192.168.242.1/24 dev wg0 +ip2 link add wg1 type wireguard +ip2 addr add 192.168.242.2/24 dev wg1 +n2 wg set wg1 private-key <(echo "$key3") listen-port 5 peer "$pub1" allowed-ips 192.168.242.1/32 +ip2 link set wg1 up +n1 ping -W 1 -c 1 192.168.242.2 +ip2 link del wg1 +n1 wg set wg0 peer "$pub3" endpoint 192.168.242.2:5 +! n1 ping -W 1 -c 1 192.168.242.2 || false # Should not crash kernel +n1 wg set wg0 peer "$pub3" remove +ip1 addr del 192.168.242.1/24 dev wg0 + # Do a wg-quick(8)-style policy routing for the default route, making sure vethc has a v6 address to tease out bugs. ip1 -6 addr add fc00::9/96 dev vethc ip1 -6 route add default via fc00::1 diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config index 990c510a9cfa..f52f1e2bc7f6 100644 --- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config +++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config @@ -10,3 +10,4 @@ CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="console=hvc0 wg.success=hvc1" CONFIG_SECTION_MISMATCH_WARN_ONLY=y CONFIG_FRAME_WARN=1280 +CONFIG_THREAD_SHIFT=14 diff --git a/tools/testing/selftests/wireguard/qemu/debug.config b/tools/testing/selftests/wireguard/qemu/debug.config index 5909e7ef2a5c..9803dbb54181 100644 --- a/tools/testing/selftests/wireguard/qemu/debug.config +++ b/tools/testing/selftests/wireguard/qemu/debug.config @@ -25,7 +25,6 @@ CONFIG_KASAN=y CONFIG_KASAN_INLINE=y CONFIG_UBSAN=y CONFIG_UBSAN_SANITIZE_ALL=y -CONFIG_UBSAN_NO_ALIGNMENT=y CONFIG_UBSAN_NULL=y CONFIG_DEBUG_KMEMLEAK=y CONFIG_DEBUG_KMEMLEAK_EARLY_LOG_SIZE=8192 diff --git a/virt/kvm/arm/hyp/aarch32.c b/virt/kvm/arm/hyp/aarch32.c index d31f267961e7..25c0e47d57cb 100644 --- a/virt/kvm/arm/hyp/aarch32.c +++ b/virt/kvm/arm/hyp/aarch32.c @@ -125,12 +125,16 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu) */ void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr) { + u32 pc = *vcpu_pc(vcpu); bool is_thumb; is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); if (is_thumb && !is_wide_instr) - *vcpu_pc(vcpu) += 2; + pc += 2; else - *vcpu_pc(vcpu) += 4; + pc += 4; + + *vcpu_pc(vcpu) = pc; + kvm_adjust_itstate(vcpu); } diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c index 14a162e295a9..ae364716ee40 100644 --- a/virt/kvm/arm/psci.c +++ b/virt/kvm/arm/psci.c @@ -186,6 +186,33 @@ static void kvm_psci_system_reset(struct kvm_vcpu *vcpu) kvm_prepare_system_event(vcpu, KVM_SYSTEM_EVENT_RESET); } +static void kvm_psci_narrow_to_32bit(struct kvm_vcpu *vcpu) +{ + int i; + + /* + * Zero the input registers' upper 32 bits. They will be fully + * zeroed on exit, so we're fine changing them in place. + */ + for (i = 1; i < 4; i++) + vcpu_set_reg(vcpu, i, lower_32_bits(vcpu_get_reg(vcpu, i))); +} + +static unsigned long kvm_psci_check_allowed_function(struct kvm_vcpu *vcpu, u32 fn) +{ + switch(fn) { + case PSCI_0_2_FN64_CPU_SUSPEND: + case PSCI_0_2_FN64_CPU_ON: + case PSCI_0_2_FN64_AFFINITY_INFO: + /* Disallow these functions for 32bit guests */ + if (vcpu_mode_is_32bit(vcpu)) + return PSCI_RET_NOT_SUPPORTED; + break; + } + + return 0; +} + static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; @@ -193,6 +220,10 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) unsigned long val; int ret = 1; + val = kvm_psci_check_allowed_function(vcpu, psci_fn); + if (val) + goto out; + switch (psci_fn) { case PSCI_0_2_FN_PSCI_VERSION: /* @@ -210,12 +241,16 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) val = PSCI_RET_SUCCESS; break; case PSCI_0_2_FN_CPU_ON: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; case PSCI_0_2_FN64_CPU_ON: mutex_lock(&kvm->lock); val = kvm_psci_vcpu_on(vcpu); mutex_unlock(&kvm->lock); break; case PSCI_0_2_FN_AFFINITY_INFO: + kvm_psci_narrow_to_32bit(vcpu); + fallthrough; case PSCI_0_2_FN64_AFFINITY_INFO: val = kvm_psci_vcpu_affinity_info(vcpu); break; @@ -256,6 +291,7 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) break; } +out: smccc_set_retval(vcpu, val, 0, 0, 0); return ret; } @@ -273,6 +309,10 @@ static int kvm_psci_1_0_call(struct kvm_vcpu *vcpu) break; case PSCI_1_0_FN_PSCI_FEATURES: feature = smccc_get_arg1(vcpu); + val = kvm_psci_check_allowed_function(vcpu, feature); + if (val) + break; + switch(feature) { case PSCI_0_2_FN_PSCI_VERSION: case PSCI_0_2_FN_CPU_SUSPEND: diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index a963b9d766b7..32e32d67a127 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -294,8 +294,15 @@ int vgic_init(struct kvm *kvm) } } - if (vgic_has_its(kvm)) { + if (vgic_has_its(kvm)) vgic_lpi_translation_cache_init(kvm); + + /* + * If we have GICv4.1 enabled, unconditionnaly request enable the + * v4 support so that we get HW-accelerated vSGIs. Otherwise, only + * enable it if we present a virtual ITS to the guest. + */ + if (vgic_supports_direct_msis(kvm)) { ret = vgic_v4_init(kvm); if (ret) goto out; @@ -348,6 +355,12 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; + /* + * Retire all pending LPIs on this vcpu anyway as we're + * going to destroy it. + */ + vgic_flush_pending_lpis(vcpu); + INIT_LIST_HEAD(&vgic_cpu->ap_list_head); } @@ -359,10 +372,10 @@ static void __kvm_vgic_destroy(struct kvm *kvm) vgic_debug_destroy(kvm); - kvm_vgic_dist_destroy(kvm); - kvm_for_each_vcpu(i, vcpu, kvm) kvm_vgic_vcpu_destroy(vcpu); + + kvm_vgic_dist_destroy(kvm); } void kvm_vgic_destroy(struct kvm *kvm) diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index d53d34a33e35..c012a52b19f5 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -96,14 +96,21 @@ out_unlock: * We "cache" the configuration table entries in our struct vgic_irq's. * However we only have those structs for mapped IRQs, so we read in * the respective config data from memory here upon mapping the LPI. + * + * Should any of these fail, behave as if we couldn't create the LPI + * by dropping the refcount and returning the error. */ ret = update_lpi_config(kvm, irq, NULL, false); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } ret = vgic_v3_lpi_sync_pending_status(kvm, irq); - if (ret) + if (ret) { + vgic_put_irq(kvm, irq); return ERR_PTR(ret); + } return irq; } diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c index 5945f062d749..a016f07adc28 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v2.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c @@ -409,24 +409,28 @@ static const struct vgic_register_region vgic_v2_dist_registers[] = { NULL, vgic_mmio_uaccess_write_v2_group, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_SET, - vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ENABLE_CLEAR, - vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_SET, - vgic_mmio_read_pending, vgic_mmio_write_spending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_spending, + NULL, vgic_uaccess_write_spending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PENDING_CLEAR, - vgic_mmio_read_pending, vgic_mmio_write_cpending, NULL, NULL, 1, + vgic_mmio_read_pending, vgic_mmio_write_cpending, + NULL, vgic_uaccess_write_cpending, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_SET, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_ACTIVE_CLEAR, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ(GIC_DIST_PRI, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c index e72dcc454247..89a14ec8b33b 100644 --- a/virt/kvm/arm/vgic/vgic-mmio-v3.c +++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c @@ -50,7 +50,8 @@ bool vgic_has_its(struct kvm *kvm) bool vgic_supports_direct_msis(struct kvm *kvm) { - return kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm); + return (kvm_vgic_global_state.has_gicv4_1 || + (kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm))); } /* @@ -538,10 +539,12 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { vgic_mmio_read_group, vgic_mmio_write_group, NULL, NULL, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER, - vgic_mmio_read_enable, vgic_mmio_write_senable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER, - vgic_mmio_read_enable, vgic_mmio_write_cenable, NULL, NULL, 1, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR, vgic_mmio_read_pending, vgic_mmio_write_spending, @@ -553,11 +556,11 @@ static const struct vgic_register_region vgic_v3_dist_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, 1, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 1, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR, vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL, @@ -609,11 +612,13 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0, vgic_mmio_read_group, vgic_mmio_write_group, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ISENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_senable, 4, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_senable, + NULL, vgic_uaccess_write_senable, 4, VGIC_ACCESS_32bit), - REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICENABLER0, - vgic_mmio_read_enable, vgic_mmio_write_cenable, 4, + REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICENABLER0, + vgic_mmio_read_enable, vgic_mmio_write_cenable, + NULL, vgic_uaccess_write_cenable, 4, VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0, vgic_mmio_read_pending, vgic_mmio_write_spending, @@ -625,12 +630,12 @@ static const struct vgic_register_region vgic_v3_rd_registers[] = { VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0, vgic_mmio_read_active, vgic_mmio_write_sactive, - NULL, vgic_mmio_uaccess_write_sactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0, vgic_mmio_read_active, vgic_mmio_write_cactive, - NULL, vgic_mmio_uaccess_write_cactive, - 4, VGIC_ACCESS_32bit), + vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4, + VGIC_ACCESS_32bit), REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0, vgic_mmio_read_priority, vgic_mmio_write_priority, 32, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit), diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c index 2199302597fa..b2d73fc0d1ef 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.c +++ b/virt/kvm/arm/vgic/vgic-mmio.c @@ -184,6 +184,48 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, } } +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = true; + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->enabled = false; + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { @@ -219,17 +261,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, return value; } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) -{ - if (is_uaccess) - return; - - irq->pending_latch = true; - vgic_irq_set_phys_active(irq, true); -} - static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { return (vgic_irq_is_sgi(irq->intid) && @@ -240,7 +271,6 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -270,22 +300,48 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, continue; } + irq->pending_latch = true; if (irq->hw) - vgic_hw_irq_spending(vcpu, irq, is_uaccess); - else - irq->pending_latch = true; + vgic_irq_set_phys_active(irq, true); + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } -/* Must be called with irq->irq_lock held */ -static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq, - bool is_uaccess) +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) { - if (is_uaccess) - return; + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + irq->pending_latch = true; + /* + * GICv2 SGIs are terribly broken. We can't restore + * the source of the interrupt, so just pick the vcpu + * itself as the source... + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source |= BIT(vcpu->vcpu_id); + + vgic_queue_irq_unlock(vcpu->kvm, irq, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* Must be called with irq->irq_lock held */ +static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) +{ irq->pending_latch = false; /* @@ -308,7 +364,6 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !kvm_get_running_vcpu(); u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; @@ -339,7 +394,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, } if (irq->hw) - vgic_hw_irq_cpending(vcpu, irq, is_uaccess); + vgic_hw_irq_cpending(vcpu, irq); else irq->pending_latch = false; @@ -348,8 +403,68 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, } } -unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, - gpa_t addr, unsigned int len) +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + int i; + unsigned long flags; + + for_each_set_bit(i, &val, len * 8) { + struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + + raw_spin_lock_irqsave(&irq->irq_lock, flags); + /* + * More fun with GICv2 SGIs! If we're clearing one of them + * from userspace, which source vcpu to clear? Let's not + * even think of it, and blow the whole set. + */ + if (is_vgic_v2_sgi(vcpu, irq)) + irq->source = 0; + + irq->pending_latch = false; + + raw_spin_unlock_irqrestore(&irq->irq_lock, flags); + + vgic_put_irq(vcpu->kvm, irq); + } + + return 0; +} + +/* + * If we are fiddling with an IRQ's active state, we have to make sure the IRQ + * is not queued on some running VCPU's LRs, because then the change to the + * active state can be overwritten when the VCPU's state is synced coming back + * from the guest. + * + * For shared interrupts as well as GICv3 private interrupts, we have to + * stop all the VCPUs because interrupts can be migrated while we don't hold + * the IRQ locks and we don't want to be chasing moving targets. + * + * For GICv2 private interrupts we don't have to do anything because + * userspace accesses to the VGIC state already require all VCPUs to be + * stopped, and only the VCPU itself can modify its private interrupts + * active state, which guarantees that the VCPU is not running. + */ +static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_halt_guest(vcpu->kvm); +} + +/* See vgic_access_active_prepare */ +static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) +{ + if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || + intid >= VGIC_NR_PRIVATE_IRQS) + kvm_arm_resume_guest(vcpu->kvm); +} + +static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; @@ -359,6 +474,10 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); + /* + * Even for HW interrupts, don't evaluate the HW state as + * all the guest is interested in is the virtual state. + */ if (irq->active) value |= (1U << i); @@ -368,6 +487,29 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, return value; } +unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + u32 intid = VGIC_ADDR_TO_INTID(addr, 1); + u32 val; + + mutex_lock(&vcpu->kvm->lock); + vgic_access_active_prepare(vcpu, intid); + + val = __vgic_mmio_read_active(vcpu, addr, len); + + vgic_access_active_finish(vcpu, intid); + mutex_unlock(&vcpu->kvm->lock); + + return val; +} + +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len) +{ + return __vgic_mmio_read_active(vcpu, addr, len); +} + /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active, bool is_uaccess) @@ -426,36 +568,6 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } -/* - * If we are fiddling with an IRQ's active state, we have to make sure the IRQ - * is not queued on some running VCPU's LRs, because then the change to the - * active state can be overwritten when the VCPU's state is synced coming back - * from the guest. - * - * For shared interrupts, we have to stop all the VCPUs because interrupts can - * be migrated while we don't hold the IRQ locks and we don't want to be - * chasing moving targets. - * - * For private interrupts we don't have to do anything because userspace - * accesses to the VGIC state already require all VCPUs to be stopped, and - * only the VCPU itself can modify its private interrupts active state, which - * guarantees that the VCPU is not running. - */ -static void vgic_change_active_prepare(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_halt_guest(vcpu->kvm); -} - -/* See vgic_change_active_prepare */ -static void vgic_change_active_finish(struct kvm_vcpu *vcpu, u32 intid) -{ - if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 || - intid > VGIC_NR_PRIVATE_IRQS) - kvm_arm_resume_guest(vcpu->kvm); -} - static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) @@ -477,11 +589,11 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } @@ -514,11 +626,11 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->lock); - vgic_change_active_prepare(vcpu, intid); + vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); - vgic_change_active_finish(vcpu, intid); + vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->lock); } diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h index 5af2aefad435..fefcca2b14dc 100644 --- a/virt/kvm/arm/vgic/vgic-mmio.h +++ b/virt/kvm/arm/vgic/vgic-mmio.h @@ -138,6 +138,14 @@ void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); +int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); @@ -149,9 +157,20 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); +int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + +int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len, + unsigned long val); + unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len); +unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, + gpa_t addr, unsigned int len); + void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 74bdb7bf3295..731c1e517716 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -259,6 +259,7 @@ static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) } bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, + struct kvm_vcpu *except, unsigned long *vcpu_bitmap, cpumask_var_t tmp) { int i, cpu, me; @@ -268,7 +269,8 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, me = get_cpu(); kvm_for_each_vcpu(i, vcpu, kvm) { - if (vcpu_bitmap && !test_bit(i, vcpu_bitmap)) + if ((vcpu_bitmap && !test_bit(i, vcpu_bitmap)) || + vcpu == except) continue; kvm_make_request(req, vcpu); @@ -288,19 +290,25 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, return called; } -bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) +bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, + struct kvm_vcpu *except) { cpumask_var_t cpus; bool called; zalloc_cpumask_var(&cpus, GFP_ATOMIC); - called = kvm_make_vcpus_request_mask(kvm, req, NULL, cpus); + called = kvm_make_vcpus_request_mask(kvm, req, except, NULL, cpus); free_cpumask_var(cpus); return called; } +bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) +{ + return kvm_make_all_cpus_request_except(kvm, req, NULL); +} + #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) { |