diff options
586 files changed, 7281 insertions, 3249 deletions
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 6be43781ec7f..baa07b30845e 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1324,15 +1324,26 @@ PAGE_SIZE multiple when read back. pgmajfault Number of major page faults incurred - workingset_refault - Number of refaults of previously evicted pages + workingset_refault_anon + Number of refaults of previously evicted anonymous pages. - workingset_activate - Number of refaulted pages that were immediately activated + workingset_refault_file + Number of refaults of previously evicted file pages. - workingset_restore - Number of restored pages which have been detected as an active - workingset before they got reclaimed. + workingset_activate_anon + Number of refaulted anonymous pages that were immediately + activated. + + workingset_activate_file + Number of refaulted file pages that were immediately activated. + + workingset_restore_anon + Number of restored anonymous pages which have been detected as + an active workingset before they got reclaimed. + + workingset_restore_file + Number of restored file pages which have been detected as an + active workingset before they got reclaimed. workingset_nodereclaim Number of times a shadow node has been reclaimed diff --git a/Documentation/admin-guide/device-mapper/dm-crypt.rst b/Documentation/admin-guide/device-mapper/dm-crypt.rst index 8f4a3f889d43..bc28a9527ee5 100644 --- a/Documentation/admin-guide/device-mapper/dm-crypt.rst +++ b/Documentation/admin-guide/device-mapper/dm-crypt.rst @@ -67,7 +67,7 @@ Parameters:: the value passed in <key_size>. <key_type> - Either 'logon' or 'user' kernel key type. + Either 'logon', 'user' or 'encrypted' kernel key type. <key_description> The kernel keyring key description crypt target should look for @@ -121,6 +121,14 @@ submit_from_crypt_cpus thread because it benefits CFQ to have writes submitted using the same context. +no_read_workqueue + Bypass dm-crypt internal workqueue and process read requests synchronously. + +no_write_workqueue + Bypass dm-crypt internal workqueue and process write requests synchronously. + This option is automatically enabled for host-managed zoned block devices + (e.g. host-managed SMR hard-disks). + integrity:<bytes>:<type> The device requires additional <bytes> metadata per-sector stored in per-bio integrity structure. This metadata must by provided diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst index a96a423e3779..6ebe163f9dfe 100644 --- a/Documentation/admin-guide/pm/cpuidle.rst +++ b/Documentation/admin-guide/pm/cpuidle.rst @@ -690,7 +690,7 @@ which of the two parameters is added to the kernel command line. In the instruction of the CPUs (which, as a rule, suspends the execution of the program and causes the hardware to attempt to enter the shallowest available idle state) for this purpose, and if ``idle=poll`` is used, idle CPUs will execute a -more or less ``lightweight'' sequence of instructions in a tight loop. [Note +more or less "lightweight" sequence of instructions in a tight loop. [Note that using ``idle=poll`` is somewhat drastic in many cases, as preventing idle CPUs from saving almost any energy at all may not be the only effect of it. For example, on Intel hardware it effectively prevents CPUs from using diff --git a/Documentation/bpf/ringbuf.rst b/Documentation/bpf/ringbuf.rst index 75f943f0009d..6a615cd62bda 100644 --- a/Documentation/bpf/ringbuf.rst +++ b/Documentation/bpf/ringbuf.rst @@ -182,9 +182,6 @@ in the order of reservations, but only after all previous records where already committed. It is thus possible for slow producers to temporarily hold off submitted records, that were reserved later. -Reservation/commit/consumer protocol is verified by litmus tests in -Documentation/litmus_tests/bpf-rb/_. - One interesting implementation bit, that significantly simplifies (and thus speeds up as well) implementation of both producers and consumers is how data area is mapped twice contiguously back-to-back in the virtual memory. This @@ -200,7 +197,7 @@ a self-pacing notifications of new data being availability. being available after commit only if consumer has already caught up right up to the record being committed. If not, consumer still has to catch up and thus will see new data anyways without needing an extra poll notification. -Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbuf.c_) show that +Benchmarks (see tools/testing/selftests/bpf/benchs/bench_ringbufs.c) show that this allows to achieve a very high throughput without having to resort to tricks like "notify only every Nth sample", which are necessary with perf buffer. For extreme cases, when BPF program wants more manual control of diff --git a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml index 17e4f20c8d39..6834f5e8df5f 100644 --- a/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml +++ b/Documentation/devicetree/bindings/arm/bcm/raspberrypi,bcm2835-firmware.yaml @@ -23,7 +23,7 @@ properties: compatible: items: - const: raspberrypi,bcm2835-firmware - - const: simple-bus + - const: simple-mfd mboxes: $ref: '/schemas/types.yaml#/definitions/phandle' @@ -57,7 +57,7 @@ required: examples: - | firmware { - compatible = "raspberrypi,bcm2835-firmware", "simple-bus"; + compatible = "raspberrypi,bcm2835-firmware", "simple-mfd"; mboxes = <&mailbox>; firmware_clocks: clocks { diff --git a/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml b/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml index 85ef69ffebed..1465c9ebaf93 100644 --- a/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml +++ b/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml @@ -67,7 +67,7 @@ examples: main_crypto: crypto@4e00000 { compatible = "ti,j721-sa2ul"; - reg = <0x0 0x4e00000 0x0 0x1200>; + reg = <0x4e00000 0x1200>; power-domains = <&k3_pds 264 TI_SCI_PD_EXCLUSIVE>; dmas = <&main_udmap 0xc000>, <&main_udmap 0x4000>, <&main_udmap 0x4001>; diff --git a/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml b/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml index 52a939cade3b..7b9d468c3e52 100644 --- a/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml +++ b/Documentation/devicetree/bindings/display/xlnx/xlnx,zynqmp-dpsub.yaml @@ -145,10 +145,10 @@ examples: display@fd4a0000 { compatible = "xlnx,zynqmp-dpsub-1.7"; - reg = <0x0 0xfd4a0000 0x0 0x1000>, - <0x0 0xfd4aa000 0x0 0x1000>, - <0x0 0xfd4ab000 0x0 0x1000>, - <0x0 0xfd4ac000 0x0 0x1000>; + reg = <0xfd4a0000 0x1000>, + <0xfd4aa000 0x1000>, + <0xfd4ab000 0x1000>, + <0xfd4ac000 0x1000>; reg-names = "dp", "blend", "av_buf", "aud"; interrupts = <0 119 4>; interrupt-parent = <&gic>; diff --git a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml index 5de510f8c88c..2a595b18ff6c 100644 --- a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml +++ b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dpdma.yaml @@ -57,7 +57,7 @@ examples: dma: dma-controller@fd4c0000 { compatible = "xlnx,zynqmp-dpdma"; - reg = <0x0 0xfd4c0000 0x0 0x1000>; + reg = <0xfd4c0000 0x1000>; interrupts = <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&gic>; clocks = <&dpdma_clk>; diff --git a/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt b/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt index d4d83916c09d..be329ea4794f 100644 --- a/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt +++ b/Documentation/devicetree/bindings/gpio/sgpio-aspeed.txt @@ -20,8 +20,9 @@ Required properties: - gpio-controller : Marks the device node as a GPIO controller - interrupts : Interrupt specifier, see interrupt-controller/interrupts.txt - interrupt-controller : Mark the GPIO controller as an interrupt-controller -- ngpios : number of GPIO lines, see gpio.txt - (should be multiple of 8, up to 80 pins) +- ngpios : number of *hardware* GPIO lines, see gpio.txt. This will expose + 2 software GPIOs per hardware GPIO: one for hardware input, one for hardware + output. Up to 80 pins, must be a multiple of 8. - clocks : A phandle to the APB clock for SGPM clock division - bus-frequency : SGPM CLK frequency diff --git a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml index 24ad1446445e..fe7fa25877fd 100644 --- a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml +++ b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml @@ -30,7 +30,7 @@ properties: const: 0 patternProperties: - "^multi-led[0-9a-f]$": + "^multi-led@[0-9a-b]$": type: object allOf: - $ref: leds-class-multicolor.yaml# diff --git a/Documentation/devicetree/bindings/media/i2c/imx274.txt b/Documentation/devicetree/bindings/media/i2c/imx274.txt deleted file mode 100644 index 0727079d2410..000000000000 --- a/Documentation/devicetree/bindings/media/i2c/imx274.txt +++ /dev/null @@ -1,38 +0,0 @@ -* Sony 1/2.5-Inch 8.51Mp CMOS Digital Image Sensor - -The Sony imx274 is a 1/2.5-inch CMOS active pixel digital image sensor with -an active array size of 3864H x 2202V. It is programmable through I2C -interface. The I2C address is fixed to 0x1a as per sensor data sheet. -Image data is sent through MIPI CSI-2, which is configured as 4 lanes -at 1440 Mbps. - - -Required Properties: -- compatible: value should be "sony,imx274" for imx274 sensor -- reg: I2C bus address of the device - -Optional Properties: -- reset-gpios: Sensor reset GPIO -- clocks: Reference to the input clock. -- clock-names: Should be "inck". -- VANA-supply: Sensor 2.8v analog supply. -- VDIG-supply: Sensor 1.8v digital core supply. -- VDDL-supply: Sensor digital IO 1.2v supply. - -The imx274 device node should contain one 'port' child node with -an 'endpoint' subnode. For further reading on port node refer to -Documentation/devicetree/bindings/media/video-interfaces.txt. - -Example: - sensor@1a { - compatible = "sony,imx274"; - reg = <0x1a>; - #address-cells = <1>; - #size-cells = <0>; - reset-gpios = <&gpio_sensor 0 0>; - port { - sensor_out: endpoint { - remote-endpoint = <&csiss_in>; - }; - }; - }; diff --git a/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml new file mode 100644 index 000000000000..f697e1a20beb --- /dev/null +++ b/Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml @@ -0,0 +1,76 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/media/i2c/sony,imx274.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Sony 1/2.5-Inch 8.51MP CMOS Digital Image Sensor + +maintainers: + - Leon Luo <leonl@leopardimaging.com> + +description: | + The Sony IMX274 is a 1/2.5-inch CMOS active pixel digital image sensor with an + active array size of 3864H x 2202V. It is programmable through I2C interface. + Image data is sent through MIPI CSI-2, which is configured as 4 lanes at 1440 + Mbps. + +properties: + compatible: + const: sony,imx274 + + reg: + const: 0x1a + + reset-gpios: + maxItems: 1 + + clocks: + maxItems: 1 + + clock-names: + const: inck + + vana-supply: + description: Sensor 2.8 V analog supply. + maxItems: 1 + + vdig-supply: + description: Sensor 1.8 V digital core supply. + maxItems: 1 + + vddl-supply: + description: Sensor digital IO 1.2 V supply. + maxItems: 1 + + port: + type: object + description: Output video port. See ../video-interfaces.txt. + +required: + - compatible + - reg + - port + +additionalProperties: false + +examples: + - | + i2c0 { + #address-cells = <1>; + #size-cells = <0>; + + imx274: camera-sensor@1a { + compatible = "sony,imx274"; + reg = <0x1a>; + reset-gpios = <&gpio_sensor 0 0>; + + port { + sensor_out: endpoint { + remote-endpoint = <&csiss_in>; + }; + }; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index 032b76f14f4f..9119f1caf391 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -21,6 +21,7 @@ Required properties: - "renesas,etheravb-r8a774a1" for the R8A774A1 SoC. - "renesas,etheravb-r8a774b1" for the R8A774B1 SoC. - "renesas,etheravb-r8a774c0" for the R8A774C0 SoC. + - "renesas,etheravb-r8a774e1" for the R8A774E1 SoC. - "renesas,etheravb-r8a7795" for the R8A7795 SoC. - "renesas,etheravb-r8a7796" for the R8A77960 SoC. - "renesas,etheravb-r8a77961" for the R8A77961 SoC. diff --git a/Documentation/kbuild/llvm.rst b/Documentation/kbuild/llvm.rst index 334df758dce3..dae90c21aed3 100644 --- a/Documentation/kbuild/llvm.rst +++ b/Documentation/kbuild/llvm.rst @@ -39,10 +39,10 @@ which can help simplify cross compiling. :: ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- make CC=clang ``CROSS_COMPILE`` is not used to prefix the Clang compiler binary, instead -``CROSS_COMPILE`` is used to set a command line flag: ``--target <triple>``. For +``CROSS_COMPILE`` is used to set a command line flag: ``--target=<triple>``. For example: :: - clang --target aarch64-linux-gnu foo.c + clang --target=aarch64-linux-gnu foo.c LLVM Utilities -------------- diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d53bcb31645a..b5a79881551f 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -206,6 +206,7 @@ Userspace to kernel: ``ETHTOOL_MSG_TSINFO_GET`` get timestamping info ``ETHTOOL_MSG_CABLE_TEST_ACT`` action start cable test ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT`` action start raw TDR cable test + ``ETHTOOL_MSG_TUNNEL_INFO_GET`` get tunnel offload info ===================================== ================================ Kernel to userspace: @@ -239,6 +240,7 @@ Kernel to userspace: ``ETHTOOL_MSG_TSINFO_GET_REPLY`` timestamping info ``ETHTOOL_MSG_CABLE_TEST_NTF`` Cable test results ``ETHTOOL_MSG_CABLE_TEST_TDR_NTF`` Cable test TDR results + ``ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY`` tunnel offload info ===================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1363,4 +1365,5 @@ are netlink only. ``ETHTOOL_SFECPARAM`` n/a n/a ''ETHTOOL_MSG_CABLE_TEST_ACT'' n/a ''ETHTOOL_MSG_CABLE_TEST_TDR_ACT'' + n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET`` =================================== ===================================== diff --git a/Documentation/userspace-api/media/v4l/buffer.rst b/Documentation/userspace-api/media/v4l/buffer.rst index 57e752aaf414..2044ed13cd9d 100644 --- a/Documentation/userspace-api/media/v4l/buffer.rst +++ b/Documentation/userspace-api/media/v4l/buffer.rst @@ -701,23 +701,6 @@ Memory Consistency Flags :stub-columns: 0 :widths: 3 1 4 - * .. _`V4L2-FLAG-MEMORY-NON-CONSISTENT`: - - - ``V4L2_FLAG_MEMORY_NON_CONSISTENT`` - - 0x00000001 - - A buffer is allocated either in consistent (it will be automatically - coherent between the CPU and the bus) or non-consistent memory. The - latter can provide performance gains, for instance the CPU cache - sync/flush operations can be avoided if the buffer is accessed by the - corresponding device only and the CPU does not read/write to/from that - buffer. However, this requires extra care from the driver -- it must - guarantee memory consistency by issuing a cache flush/sync when - consistency is needed. If this flag is set V4L2 will attempt to - allocate the buffer in non-consistent memory. The flag takes effect - only if the buffer is used for :ref:`memory mapping <mmap>` I/O and the - queue reports the :ref:`V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS - <V4L2-BUF-CAP-SUPPORTS-MMAP-CACHE-HINTS>` capability. - .. c:type:: v4l2_memory enum v4l2_memory diff --git a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst index f2a702870fad..12cf6b44f414 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst @@ -120,13 +120,9 @@ than the number requested. If you want to just query the capabilities without making any other changes, then set ``count`` to 0, ``memory`` to ``V4L2_MEMORY_MMAP`` and ``format.type`` to the buffer type. - * - __u32 - - ``flags`` - - Specifies additional buffer management attributes. - See :ref:`memory-flags`. * - __u32 - - ``reserved``\ [6] + - ``reserved``\ [7] - A place holder for future extensions. Drivers and applications must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst index 75d894d9c36c..0e3e2fde65e8 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst @@ -112,17 +112,10 @@ aborting or finishing any DMA in progress, an implicit ``V4L2_MEMORY_MMAP`` and ``type`` set to the buffer type. This will free any previously allocated buffers, so this is typically something that will be done at the start of the application. - * - union { - - (anonymous) - * - __u32 - - ``flags`` - - Specifies additional buffer management attributes. - See :ref:`memory-flags`. * - __u32 - ``reserved``\ [1] - - Kept for backwards compatibility. Use ``flags`` instead. - * - } - - + - A place holder for future extensions. Drivers and applications + must set the array to zero. .. tabularcolumns:: |p{6.1cm}|p{2.2cm}|p{8.7cm}| @@ -169,7 +162,6 @@ aborting or finishing any DMA in progress, an implicit - This capability is set by the driver to indicate that the queue supports cache and memory management hints. However, it's only valid when the queue is used for :ref:`memory mapping <mmap>` streaming I/O. See - :ref:`V4L2_FLAG_MEMORY_NON_CONSISTENT <V4L2-FLAG-MEMORY-NON-CONSISTENT>`, :ref:`V4L2_BUF_FLAG_NO_CACHE_INVALIDATE <V4L2-BUF-FLAG-NO-CACHE-INVALIDATE>` and :ref:`V4L2_BUF_FLAG_NO_CACHE_CLEAN <V4L2-BUF-FLAG-NO-CACHE-CLEAN>`. diff --git a/MAINTAINERS b/MAINTAINERS index d746519253c3..e83aee101b66 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1460,6 +1460,11 @@ S: Odd Fixes F: drivers/amba/ F: include/linux/amba/bus.h +ARM PRIMECELL CLCD PL110 DRIVER +M: Russell King <linux@armlinux.org.uk> +S: Odd Fixes +F: drivers/video/fbdev/amba-clcd.* + ARM PRIMECELL KMI PL050 DRIVER M: Russell King <linux@armlinux.org.uk> S: Odd Fixes @@ -4408,12 +4413,6 @@ T: git git://git.infradead.org/users/hch/configfs.git F: fs/configfs/ F: include/linux/configfs.h -CONNECTOR -M: Evgeniy Polyakov <zbr@ioremap.net> -L: netdev@vger.kernel.org -S: Maintained -F: drivers/connector/ - CONSOLE SUBSYSTEM M: Greg Kroah-Hartman <gregkh@linuxfoundation.org> S: Supported @@ -8329,8 +8328,9 @@ S: Supported F: drivers/pci/hotplug/rpaphp* IBM Power SRIOV Virtual NIC Device Driver -M: Thomas Falcon <tlfalcon@linux.ibm.com> -M: John Allen <jallen@linux.ibm.com> +M: Dany Madden <drt@linux.ibm.com> +M: Lijun Pan <ljp@linux.ibm.com> +M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmvnic.* @@ -8344,7 +8344,7 @@ F: arch/powerpc/platforms/powernv/copy-paste.h F: arch/powerpc/platforms/powernv/vas* IBM Power Virtual Ethernet Device Driver -M: Thomas Falcon <tlfalcon@linux.ibm.com> +M: Cristobal Forno <cforno12@linux.ibm.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmveth.* @@ -8757,7 +8757,8 @@ F: include/drm/i915* F: include/uapi/drm/i915_drm.h INTEL ETHERNET DRIVERS -M: Jeff Kirsher <jeffrey.t.kirsher@intel.com> +M: Jesse Brandeburg <jesse.brandeburg@intel.com> +M: Tony Nguyen <anthony.l.nguyen@intel.com> L: intel-wired-lan@lists.osuosl.org (moderated for non-subscribers) S: Supported W: http://www.intel.com/support/feedback.htm @@ -11042,6 +11043,7 @@ F: drivers/char/hw_random/mtk-rng.c MEDIATEK SWITCH DRIVER M: Sean Wang <sean.wang@mediatek.com> +M: Landen Chao <Landen.Chao@mediatek.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mt7530.* @@ -12055,6 +12057,7 @@ Q: http://patchwork.ozlabs.org/project/netdev/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git F: Documentation/devicetree/bindings/net/ +F: drivers/connector/ F: drivers/net/ F: include/linux/etherdevice.h F: include/linux/fcdevice.h @@ -12080,6 +12083,7 @@ NETWORKING [DSA] M: Andrew Lunn <andrew@lunn.ch> M: Vivien Didelot <vivien.didelot@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> +M: Vladimir Oltean <olteanv@gmail.com> S: Maintained F: Documentation/devicetree/bindings/net/dsa/ F: drivers/net/dsa/ @@ -13185,6 +13189,7 @@ F: drivers/firmware/pcdp.* PCI DRIVER FOR AARDVARK (Marvell Armada 3700) M: Thomas Petazzoni <thomas.petazzoni@bootlin.com> +M: Pali Rohár <pali@kernel.org> L: linux-pci@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -16157,7 +16162,7 @@ M: Leon Luo <leonl@leopardimaging.com> L: linux-media@vger.kernel.org S: Maintained T: git git://linuxtv.org/media_tree.git -F: Documentation/devicetree/bindings/media/i2c/imx274.txt +F: Documentation/devicetree/bindings/media/i2c/sony,imx274.yaml F: drivers/media/i2c/imx274.c SONY IMX290 SENSOR DRIVER @@ -16727,6 +16732,13 @@ S: Maintained F: Documentation/devicetree/bindings/gpio/snps,dw-apb-gpio.yaml F: drivers/gpio/gpio-dwapb.c +SYNOPSYS DESIGNWARE APB SSI DRIVER +M: Serge Semin <fancer.lancer@gmail.com> +L: linux-spi@vger.kernel.org +S: Supported +F: Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.yaml +F: drivers/spi/spi-dw* + SYNOPSYS DESIGNWARE AXI DMAC DRIVER M: Eugeniy Paltsev <Eugeniy.Paltsev@synopsys.com> S: Maintained @@ -18284,7 +18296,8 @@ F: drivers/gpu/vga/vga_switcheroo.c F: include/linux/vga_switcheroo.h VIA RHINE NETWORK DRIVER -S: Orphan +S: Maintained +M: Kevin Brace <kevinbrace@bracecomputerlab.com> F: drivers/net/ethernet/via/via-rhine.c VIA SD/MMC CARD CONTROLLER DRIVER @@ -18889,10 +18902,10 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm F: arch/x86/mm/ X86 PLATFORM DRIVERS -M: Darren Hart <dvhart@infradead.org> -M: Andy Shevchenko <andy@infradead.org> +M: Hans de Goede <hdegoede@redhat.com> +M: Mark Gross <mgross@linux.intel.com> L: platform-driver-x86@vger.kernel.org -S: Odd Fixes +S: Maintained T: git git://git.infradead.org/linux-platform-drivers-x86.git F: drivers/platform/olpc/ F: drivers/platform/x86/ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 9 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc8 NAME = Kleptomaniac Octopus # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/at91-sama5d2_icp.dts b/arch/arm/boot/dts/at91-sama5d2_icp.dts index 8d19925fc09e..6783cf16ff81 100644 --- a/arch/arm/boot/dts/at91-sama5d2_icp.dts +++ b/arch/arm/boot/dts/at91-sama5d2_icp.dts @@ -116,7 +116,6 @@ switch0: ksz8563@0 { compatible = "microchip,ksz8563"; reg = <0>; - phy-mode = "mii"; reset-gpios = <&pioA PIN_PD4 GPIO_ACTIVE_LOW>; spi-max-frequency = <500000>; @@ -140,6 +139,7 @@ reg = <2>; label = "cpu"; ethernet = <&macb0>; + phy-mode = "mii"; fixed-link { speed = <100>; full-duplex; diff --git a/arch/arm/boot/dts/bcm2835-rpi.dtsi b/arch/arm/boot/dts/bcm2835-rpi.dtsi index f7ae5a4530b8..d94357b21f7e 100644 --- a/arch/arm/boot/dts/bcm2835-rpi.dtsi +++ b/arch/arm/boot/dts/bcm2835-rpi.dtsi @@ -13,7 +13,7 @@ soc { firmware: firmware { - compatible = "raspberrypi,bcm2835-firmware", "simple-bus"; + compatible = "raspberrypi,bcm2835-firmware", "simple-mfd"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c index 24dd5bbe60e4..094337dc1bc7 100644 --- a/arch/arm/mach-imx/cpuidle-imx6q.c +++ b/arch/arm/mach-imx/cpuidle-imx6q.c @@ -24,7 +24,9 @@ static int imx6q_enter_wait(struct cpuidle_device *dev, imx6_set_lpm(WAIT_UNCLOCKED); raw_spin_unlock(&cpuidle_lock); + rcu_idle_enter(); cpu_do_idle(); + rcu_idle_exit(); raw_spin_lock(&cpuidle_lock); if (num_idle_cpus-- == num_online_cpus()) @@ -44,7 +46,7 @@ static struct cpuidle_driver imx6q_cpuidle_driver = { { .exit_latency = 50, .target_residency = 75, - .flags = CPUIDLE_FLAG_TIMER_STOP, + .flags = CPUIDLE_FLAG_TIMER_STOP | CPUIDLE_FLAG_RCU_IDLE, .enter = imx6q_enter_wait, .name = "WAIT", .desc = "Clock off", diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index e93145d72c26..a6ab3689b2f4 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -150,7 +150,7 @@ static int xen_starting_cpu(unsigned int cpu) pr_info("Xen: initializing cpu%d\n", cpu); vcpup = per_cpu_ptr(xen_vcpu_info, cpu); - info.mfn = virt_to_gfn(vcpup); + info.mfn = percpu_to_gfn(vcpup); info.offset = xen_offset_in_page(vcpup); err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, xen_vcpu_nr(cpu), diff --git a/arch/arm64/crypto/aes-neonbs-core.S b/arch/arm64/crypto/aes-neonbs-core.S index b357164379f6..63a52ad9a75c 100644 --- a/arch/arm64/crypto/aes-neonbs-core.S +++ b/arch/arm64/crypto/aes-neonbs-core.S @@ -788,7 +788,7 @@ SYM_FUNC_START_LOCAL(__xts_crypt8) 0: mov bskey, x21 mov rounds, x22 - br x7 + br x16 SYM_FUNC_END(__xts_crypt8) .macro __xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7 @@ -806,7 +806,7 @@ SYM_FUNC_END(__xts_crypt8) uzp1 v30.4s, v30.4s, v25.4s ld1 {v25.16b}, [x24] -99: adr x7, \do8 +99: adr x16, \do8 bl __xts_crypt8 ldp q16, q17, [sp, #.Lframe_local_offset] diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index a85174d05473..cada0b816c8a 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -298,8 +298,21 @@ void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: case EFI_PERSISTENT_MEMORY: - pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys); - return NULL; + if (memblock_is_map_memory(phys) || + !memblock_is_region_memory(phys, size)) { + pr_warn(FW_BUG "requested region covers kernel memory @ %pa\n", &phys); + return NULL; + } + /* + * Mapping kernel memory is permitted if the region in + * question is covered by a single memblock with the + * NOMAP attribute set: this enables the use of ACPI + * table overrides passed via initramfs, which are + * reserved in memory using arch_reserve_mem_area() + * below. As this particular use case only requires + * read access, fall through to the R/O mapping case. + */ + fallthrough; case EFI_RUNTIME_SERVICES_CODE: /* @@ -388,3 +401,8 @@ int apei_claim_sea(struct pt_regs *regs) return err; } + +void arch_reserve_mem_area(acpi_physical_address addr, size_t size) +{ + memblock_mark_nomap(addr, size); +} diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c index 69eae608d670..b15d65a42042 100644 --- a/arch/arm64/kvm/hyp/nvhe/tlb.c +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -31,7 +31,14 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu, isb(); } + /* + * __load_guest_stage2() includes an ISB only when the AT + * workaround is applied. Take care of the opposite condition, + * ensuring that we always have an ISB, but not two ISBs back + * to back. + */ __load_guest_stage2(mmu); + asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT)); } static void __tlb_switch_to_host(struct tlb_inv_context *cxt) diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 0b3fb4c7af29..8e7b8c6c576e 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -538,7 +538,7 @@ virtual_memmap_init(u64 start, u64 end, void *arg) if (map_start < map_end) memmap_init_zone((unsigned long)(map_end - map_start), args->nid, args->zone, page_to_pfn(map_start), - MEMMAP_EARLY, NULL); + MEMINIT_EARLY, NULL); return 0; } @@ -547,8 +547,8 @@ memmap_init (unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { if (!vmem_map) { - memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, - NULL); + memmap_init_zone(size, nid, zone, start_pfn, + MEMINIT_EARLY, NULL); } else { struct page *start; struct memmap_init_callback_data args; diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 82627c264964..01427bde2397 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -148,7 +148,7 @@ void __init plat_mem_setup(void) { struct cpuinfo_mips *c = ¤t_cpu_data; - if ((c->cputype == CPU_74K) || (c->cputype == CPU_1074K)) { + if (c->cputype == CPU_74K) { pr_info("Using bcma bus\n"); #ifdef CONFIG_BCM47XX_BCMA bcm47xx_bus_type = BCM47XX_BUS_TYPE_BCMA; diff --git a/arch/mips/include/asm/cpu-type.h b/arch/mips/include/asm/cpu-type.h index 75a7a382da09..3288cef4b168 100644 --- a/arch/mips/include/asm/cpu-type.h +++ b/arch/mips/include/asm/cpu-type.h @@ -47,6 +47,7 @@ static inline int __pure __get_cpu_type(const int cpu_type) case CPU_34K: case CPU_1004K: case CPU_74K: + case CPU_1074K: case CPU_M14KC: case CPU_M14KEC: case CPU_INTERAPTIV: diff --git a/arch/mips/loongson2ef/Platform b/arch/mips/loongson2ef/Platform index 4ab55f1123a0..ae023b9a1c51 100644 --- a/arch/mips/loongson2ef/Platform +++ b/arch/mips/loongson2ef/Platform @@ -44,6 +44,10 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS endif endif +# Some -march= flags enable MMI instructions, and GCC complains about that +# support being enabled alongside -msoft-float. Thus explicitly disable MMI. +cflags-y += $(call cc-option,-mno-loongson-mmi) + # # Loongson Machines' Support # diff --git a/arch/mips/loongson64/cop2-ex.c b/arch/mips/loongson64/cop2-ex.c index f130f62129b8..00055d4b6042 100644 --- a/arch/mips/loongson64/cop2-ex.c +++ b/arch/mips/loongson64/cop2-ex.c @@ -95,10 +95,8 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, if (res) goto fault; - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rt, value); - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rq, value_next); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0, value); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0, value_next); compute_return_epc(regs); own_fpu(1); } @@ -130,15 +128,13 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, goto sigbus; lose_fpu(1); - value_next = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rq); + value_next = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rq], 0); StoreDW(addr + 8, value_next, res); if (res) goto fault; - value = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lswc2_format.rt); + value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lswc2_format.rt], 0); StoreDW(addr, value, res); if (res) @@ -204,8 +200,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, if (res) goto fault; - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt, value); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value); compute_return_epc(regs); own_fpu(1); @@ -221,8 +216,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, if (res) goto fault; - set_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt, value); + set_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0, value); compute_return_epc(regs); own_fpu(1); break; @@ -286,8 +280,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, goto sigbus; lose_fpu(1); - value = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt); + value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0); StoreW(addr, value, res); if (res) @@ -305,8 +298,7 @@ static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action, goto sigbus; lose_fpu(1); - value = get_fpr64(current->thread.fpu.fpr, - insn.loongson3_lsdc2_format.rt); + value = get_fpr64(¤t->thread.fpu.fpr[insn.loongson3_lsdc2_format.rt], 0); StoreDW(addr, value, res); if (res) diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c index 78d61f97371e..e809cb5a1631 100644 --- a/arch/powerpc/net/bpf_jit_comp.c +++ b/arch/powerpc/net/bpf_jit_comp.c @@ -475,7 +475,6 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: true_cond = COND_NE; - fallthrough; cond_branch: /* same targets, can avoid doing the test :) */ if (filter[i].jt == filter[i].jf) { diff --git a/arch/riscv/include/asm/stackprotector.h b/arch/riscv/include/asm/stackprotector.h index d95f7b2a7f37..5962f8891f06 100644 --- a/arch/riscv/include/asm/stackprotector.h +++ b/arch/riscv/include/asm/stackprotector.h @@ -5,7 +5,6 @@ #include <linux/random.h> #include <linux/version.h> -#include <asm/timex.h> extern unsigned long __stack_chk_guard; @@ -18,12 +17,9 @@ extern unsigned long __stack_chk_guard; static __always_inline void boot_init_stack_canary(void) { unsigned long canary; - unsigned long tsc; /* Try to get a semi random initial value. */ get_random_bytes(&canary, sizeof(canary)); - tsc = get_cycles(); - canary += tsc + (tsc << BITS_PER_LONG/2); canary ^= LINUX_VERSION_CODE; canary &= CANARY_MASK; diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h index 7f659dda0032..ab104905d4db 100644 --- a/arch/riscv/include/asm/timex.h +++ b/arch/riscv/include/asm/timex.h @@ -33,6 +33,19 @@ static inline u32 get_cycles_hi(void) #define get_cycles_hi get_cycles_hi #endif /* CONFIG_64BIT */ +/* + * Much like MIPS, we may not have a viable counter to use at an early point + * in the boot process. Unfortunately we don't have a fallback, so instead + * we just return 0. + */ +static inline unsigned long random_get_entropy(void) +{ + if (unlikely(clint_time_val == NULL)) + return 0; + return get_cycles(); +} +#define random_get_entropy() random_get_entropy() + #else /* CONFIG_RISCV_M_MODE */ static inline cycles_t get_cycles(void) diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index f3586e31ed1e..34d00d9e6eac 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -22,13 +22,11 @@ SECTIONS /* Beginning of code and text segment */ . = LOAD_OFFSET; _start = .; - _stext = .; HEAD_TEXT_SECTION . = ALIGN(PAGE_SIZE); __init_begin = .; INIT_TEXT_SECTION(PAGE_SIZE) - INIT_DATA_SECTION(16) . = ALIGN(8); __soc_early_init_table : { __soc_early_init_table_start = .; @@ -55,6 +53,7 @@ SECTIONS . = ALIGN(SECTION_ALIGN); .text : { _text = .; + _stext = .; TEXT_TEXT SCHED_TEXT CPUIDLE_TEXT @@ -67,6 +66,8 @@ SECTIONS _etext = .; } + INIT_DATA_SECTION(16) + /* Start of data section */ _sdata = .; RO_DATA(SECTION_ALIGN) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index ca03762a3733..f750e012dbe5 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -515,6 +515,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) #else dtb_early_va = (void *)dtb_pa; #endif + dtb_early_pa = dtb_pa; } static inline void setup_vm_final(void) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 7eb01a5459cd..b55561cc8786 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -1260,26 +1260,44 @@ static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address) #define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address) -static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long address) { - if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) - return (p4d_t *) pgd_deref(*pgd) + p4d_index(address); - return (p4d_t *) pgd; + if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1) + return (p4d_t *) pgd_deref(pgd) + p4d_index(address); + return (p4d_t *) pgdp; } +#define p4d_offset_lockless p4d_offset_lockless -static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address) +static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long address) { - if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) - return (pud_t *) p4d_deref(*p4d) + pud_index(address); - return (pud_t *) p4d; + return p4d_offset_lockless(pgdp, *pgdp, address); +} + +static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long address) +{ + if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2) + return (pud_t *) p4d_deref(p4d) + pud_index(address); + return (pud_t *) p4dp; +} +#define pud_offset_lockless pud_offset_lockless + +static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long address) +{ + return pud_offset_lockless(p4dp, *p4dp, address); } #define pud_offset pud_offset -static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) +static inline pmd_t *pmd_offset_lockless(pud_t *pudp, pud_t pud, unsigned long address) +{ + if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) + return (pmd_t *) pud_deref(pud) + pmd_index(address); + return (pmd_t *) pudp; +} +#define pmd_offset_lockless pmd_offset_lockless + +static inline pmd_t *pmd_offset(pud_t *pudp, unsigned long address) { - if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3) - return (pmd_t *) pud_deref(*pud) + pmd_index(address); - return (pmd_t *) pud; + return pmd_offset_lockless(pudp, *pudp, address); } #define pmd_offset pmd_offset diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index c44f3e9140d5..91ea74ae71b8 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2183,6 +2183,12 @@ static int iret_interception(struct vcpu_svm *svm) return 1; } +static int invd_interception(struct vcpu_svm *svm) +{ + /* Treat an INVD instruction as a NOP and just skip it. */ + return kvm_skip_emulated_instruction(&svm->vcpu); +} + static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) @@ -2774,7 +2780,7 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, - [SVM_EXIT_INVD] = emulate_on_interception, + [SVM_EXIT_INVD] = invd_interception, [SVM_EXIT_PAUSE] = pause_interception, [SVM_EXIT_HLT] = halt_interception, [SVM_EXIT_INVLPG] = invlpg_interception, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 8646a797b7a8..96979c09ebd1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -129,6 +129,9 @@ static bool __read_mostly enable_preemption_timer = 1; module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #endif +extern bool __read_mostly allow_smaller_maxphyaddr; +module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); + #define KVM_VM_CR0_ALWAYS_OFF (X86_CR0_NW | X86_CR0_CD) #define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR0_NE #define KVM_VM_CR0_ALWAYS_ON \ @@ -791,6 +794,18 @@ void update_exception_bitmap(struct kvm_vcpu *vcpu) */ if (is_guest_mode(vcpu)) eb |= get_vmcs12(vcpu)->exception_bitmap; + else { + /* + * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched + * between guest and host. In that case we only care about present + * faults. For vmcs02, however, PFEC_MASK and PFEC_MATCH are set in + * prepare_vmcs02_rare. + */ + bool selective_pf_trap = enable_ept && (eb & (1u << PF_VECTOR)); + int mask = selective_pf_trap ? PFERR_PRESENT_MASK : 0; + vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, mask); + vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, mask); + } vmcs_write32(EXCEPTION_BITMAP, eb); } @@ -4352,16 +4367,6 @@ static void init_vmcs(struct vcpu_vmx *vmx) vmx->pt_desc.guest.output_mask = 0x7F; vmcs_write64(GUEST_IA32_RTIT_CTL, 0); } - - /* - * If EPT is enabled, #PF is only trapped if MAXPHYADDR is mismatched - * between guest and host. In that case we only care about present - * faults. - */ - if (enable_ept) { - vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, PFERR_PRESENT_MASK); - vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, PFERR_PRESENT_MASK); - } } static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -4803,6 +4808,7 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) * EPT will cause page fault only if we need to * detect illegal GPAs. */ + WARN_ON_ONCE(!allow_smaller_maxphyaddr); kvm_fixup_and_inject_pf_error(vcpu, cr2, error_code); return 1; } else @@ -5331,7 +5337,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ - if (unlikely(kvm_mmu_is_illegal_gpa(vcpu, gpa))) + if (unlikely(allow_smaller_maxphyaddr && kvm_mmu_is_illegal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -8305,11 +8311,12 @@ static int __init vmx_init(void) vmx_check_vmcs12_offsets(); /* - * Intel processors don't have problems with - * GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable - * it for VMX by default + * Shadow paging doesn't have a (further) performance penalty + * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it + * by default */ - allow_smaller_maxphyaddr = true; + if (!enable_ept) + allow_smaller_maxphyaddr = true; return 0; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index a2f82127c170..a0e47720f60c 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -552,7 +552,10 @@ static inline bool vmx_has_waitpkg(struct vcpu_vmx *vmx) static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) { - return !enable_ept || cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; + if (!enable_ept) + return true; + + return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; } void dump_vmcs(void); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1994602a0851..ce856e0ece84 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -188,7 +188,7 @@ static struct kvm_shared_msrs __percpu *shared_msrs; u64 __read_mostly host_efer; EXPORT_SYMBOL_GPL(host_efer); -bool __read_mostly allow_smaller_maxphyaddr; +bool __read_mostly allow_smaller_maxphyaddr = 0; EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr); static u64 __read_mostly host_xss; @@ -976,6 +976,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_SMEP; + unsigned long mmu_role_bits = pdptr_bits | X86_CR4_SMAP | X86_CR4_PKE; if (kvm_valid_cr4(vcpu, cr4)) return 1; @@ -1003,7 +1004,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (kvm_x86_ops.set_cr4(vcpu, cr4)) return 1; - if (((cr4 ^ old_cr4) & pdptr_bits) || + if (((cr4 ^ old_cr4) & mmu_role_bits) || (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE))) kvm_mmu_reset_context(vcpu); @@ -3221,9 +3222,22 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_POWER_CTL: msr_info->data = vcpu->arch.msr_ia32_power_ctl; break; - case MSR_IA32_TSC: - msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset; + case MSR_IA32_TSC: { + /* + * Intel SDM states that MSR_IA32_TSC read adds the TSC offset + * even when not intercepted. AMD manual doesn't explicitly + * state this but appears to behave the same. + * + * On userspace reads and writes, however, we unconditionally + * operate L1's TSC value to ensure backwards-compatible + * behavior for migration. + */ + u64 tsc_offset = msr_info->host_initiated ? vcpu->arch.l1_tsc_offset : + vcpu->arch.tsc_offset; + + msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + tsc_offset; break; + } case MSR_MTRRcap: case 0x200 ... 0x2ff: return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data); diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index b0dfac3d3df7..1847e993ac63 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -120,7 +120,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size) */ if (size < 8) { if (!IS_ALIGNED(dest, 4) || size != 4) - clean_cache_range(dst, 1); + clean_cache_range(dst, size); } else { if (!IS_ALIGNED(dest, 8)) { dest = ALIGN(dest, boot_cpu_data.x86_clflush_size); diff --git a/block/blk-mq.c b/block/blk-mq.c index b3d2785eefe9..cdced4aca2e8 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1412,6 +1412,11 @@ out: hctx->dispatched[queued_to_index(queued)]++; + /* If we didn't flush the entire list, we could have told the driver + * there was more coming, but that turned out to be a lie. + */ + if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued) + q->mq_ops->commit_rqs(hctx); /* * Any items that need requeuing? Stuff them into hctx->dispatch, * that is where we will continue on next queue run. @@ -1425,14 +1430,6 @@ out: blk_mq_release_budgets(q, nr_budgets); - /* - * If we didn't flush the entire list, we could have told - * the driver there was more coming, but that turned out to - * be a lie. - */ - if (q->mq_ops->commit_rqs && queued) - q->mq_ops->commit_rqs(hctx); - spin_lock(&hctx->lock); list_splice_tail_init(list, &hctx->dispatch); spin_unlock(&hctx->lock); @@ -2079,6 +2076,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, struct list_head *list) { int queued = 0; + int errors = 0; while (!list_empty(list)) { blk_status_t ret; @@ -2095,6 +2093,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, break; } blk_mq_end_request(rq, ret); + errors++; } else queued++; } @@ -2104,7 +2103,8 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, * the driver there was more coming, but that turned out to * be a lie. */ - if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs && queued) + if ((!list_empty(list) || errors) && + hctx->queue->mq_ops->commit_rqs && queued) hctx->queue->mq_ops->commit_rqs(hctx); } diff --git a/block/blk-settings.c b/block/blk-settings.c index 76a7e03bcd6c..34b721a2743a 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -801,6 +801,52 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q, } EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging); +/** + * blk_queue_set_zoned - configure a disk queue zoned model. + * @disk: the gendisk of the queue to configure + * @model: the zoned model to set + * + * Set the zoned model of the request queue of @disk according to @model. + * When @model is BLK_ZONED_HM (host managed), this should be called only + * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option). + * If @model specifies BLK_ZONED_HA (host aware), the effective model used + * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions + * on the disk. + */ +void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) +{ + switch (model) { + case BLK_ZONED_HM: + /* + * Host managed devices are supported only if + * CONFIG_BLK_DEV_ZONED is enabled. + */ + WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)); + break; + case BLK_ZONED_HA: + /* + * Host aware devices can be treated either as regular block + * devices (similar to drive managed devices) or as zoned block + * devices to take advantage of the zone command set, similarly + * to host managed devices. We try the latter if there are no + * partitions and zoned block device support is enabled, else + * we do nothing special as far as the block layer is concerned. + */ + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) || + disk_has_partitions(disk)) + model = BLK_ZONED_NONE; + break; + case BLK_ZONED_NONE: + default: + if (WARN_ON_ONCE(model != BLK_ZONED_NONE)) + model = BLK_ZONED_NONE; + break; + } + + disk->queue->limits.zoned = model; +} +EXPORT_SYMBOL_GPL(blk_queue_set_zoned); + static int __init blk_settings_init(void) { blk_max_low_pfn = max_low_pfn - 1; diff --git a/block/partitions/ibm.c b/block/partitions/ibm.c index d6e18df9c53c..4b044e620d35 100644 --- a/block/partitions/ibm.c +++ b/block/partitions/ibm.c @@ -305,8 +305,6 @@ int ibm_partition(struct parsed_partitions *state) if (!disk->fops->getgeo) goto out_exit; fn = symbol_get(dasd_biodasdinfo); - if (!fn) - goto out_exit; blocksize = bdev_logical_block_size(bdev); if (blocksize <= 0) goto out_symbol; @@ -326,7 +324,7 @@ int ibm_partition(struct parsed_partitions *state) geo->start = get_start_sect(bdev); if (disk->fops->getgeo(bdev, geo)) goto out_freeall; - if (fn(disk, info)) { + if (!fn || fn(disk, info)) { kfree(info); info = NULL; } @@ -370,7 +368,8 @@ out_nolab: out_nogeo: kfree(info); out_symbol: - symbol_put(dasd_biodasdinfo); + if (fn) + symbol_put(dasd_biodasdinfo); out_exit: return res; } diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index ef722f04f88a..72108404718f 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -651,6 +651,7 @@ struct compat_cdrom_generic_command { compat_int_t stat; compat_caddr_t sense; unsigned char data_direction; + unsigned char pad[3]; compat_int_t quiet; compat_int_t timeout; compat_caddr_t reserved[1]; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 7ecb90e90afd..f66236cff69b 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -176,6 +176,7 @@ static void lapic_timer_propagate_broadcast(struct acpi_processor *pr) { } static bool lapic_timer_needs_broadcast(struct acpi_processor *pr, struct acpi_processor_cx *cx) { + return false; } #endif diff --git a/drivers/atm/eni.c b/drivers/atm/eni.c index 39be444534d0..316a9947541f 100644 --- a/drivers/atm/eni.c +++ b/drivers/atm/eni.c @@ -2224,7 +2224,7 @@ static int eni_init_one(struct pci_dev *pci_dev, rc = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(32)); if (rc < 0) - goto out; + goto err_disable; rc = -ENOMEM; eni_dev = kmalloc(sizeof(struct eni_dev), GFP_KERNEL); diff --git a/drivers/base/node.c b/drivers/base/node.c index 508b80f6329b..50af16e68d98 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -761,14 +761,36 @@ static int __ref get_nid_for_pfn(unsigned long pfn) return pfn_to_nid(pfn); } +static int do_register_memory_block_under_node(int nid, + struct memory_block *mem_blk) +{ + int ret; + + /* + * If this memory block spans multiple nodes, we only indicate + * the last processed node. + */ + mem_blk->nid = nid; + + ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj, + &mem_blk->dev.kobj, + kobject_name(&mem_blk->dev.kobj)); + if (ret) + return ret; + + return sysfs_create_link_nowarn(&mem_blk->dev.kobj, + &node_devices[nid]->dev.kobj, + kobject_name(&node_devices[nid]->dev.kobj)); +} + /* register memory section under specified node if it spans that node */ -static int register_mem_sect_under_node(struct memory_block *mem_blk, - void *arg) +static int register_mem_block_under_node_early(struct memory_block *mem_blk, + void *arg) { unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE; unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr); unsigned long end_pfn = start_pfn + memory_block_pfns - 1; - int ret, nid = *(int *)arg; + int nid = *(int *)arg; unsigned long pfn; for (pfn = start_pfn; pfn <= end_pfn; pfn++) { @@ -785,39 +807,34 @@ static int register_mem_sect_under_node(struct memory_block *mem_blk, } /* - * We need to check if page belongs to nid only for the boot - * case, during hotplug we know that all pages in the memory - * block belong to the same node. - */ - if (system_state == SYSTEM_BOOTING) { - page_nid = get_nid_for_pfn(pfn); - if (page_nid < 0) - continue; - if (page_nid != nid) - continue; - } - - /* - * If this memory block spans multiple nodes, we only indicate - * the last processed node. + * We need to check if page belongs to nid only at the boot + * case because node's ranges can be interleaved. */ - mem_blk->nid = nid; - - ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj, - &mem_blk->dev.kobj, - kobject_name(&mem_blk->dev.kobj)); - if (ret) - return ret; + page_nid = get_nid_for_pfn(pfn); + if (page_nid < 0) + continue; + if (page_nid != nid) + continue; - return sysfs_create_link_nowarn(&mem_blk->dev.kobj, - &node_devices[nid]->dev.kobj, - kobject_name(&node_devices[nid]->dev.kobj)); + return do_register_memory_block_under_node(nid, mem_blk); } /* mem section does not span the specified node */ return 0; } /* + * During hotplug we know that all pages in the memory block belong to the same + * node. + */ +static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk, + void *arg) +{ + int nid = *(int *)arg; + + return do_register_memory_block_under_node(nid, mem_blk); +} + +/* * Unregister a memory block device under the node it spans. Memory blocks * with multiple nodes cannot be offlined and therefore also never be removed. */ @@ -832,11 +849,19 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk) kobject_name(&node_devices[mem_blk->nid]->dev.kobj)); } -int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn) +int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, + enum meminit_context context) { + walk_memory_blocks_func_t func; + + if (context == MEMINIT_HOTPLUG) + func = register_mem_block_under_node_hotplug; + else + func = register_mem_block_under_node_early; + return walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn), (void *)&nid, - register_mem_sect_under_node); + func); } #ifdef CONFIG_HUGETLBFS diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h index 3d80c4b43f72..7be2fcfeea52 100644 --- a/drivers/base/regmap/internal.h +++ b/drivers/base/regmap/internal.h @@ -217,7 +217,7 @@ struct regmap_field { #ifdef CONFIG_DEBUG_FS extern void regmap_debugfs_initcall(void); -extern void regmap_debugfs_init(struct regmap *map, const char *name); +extern void regmap_debugfs_init(struct regmap *map); extern void regmap_debugfs_exit(struct regmap *map); static inline void regmap_debugfs_disable(struct regmap *map) @@ -227,7 +227,7 @@ static inline void regmap_debugfs_disable(struct regmap *map) #else static inline void regmap_debugfs_initcall(void) { } -static inline void regmap_debugfs_init(struct regmap *map, const char *name) { } +static inline void regmap_debugfs_init(struct regmap *map) { } static inline void regmap_debugfs_exit(struct regmap *map) { } static inline void regmap_debugfs_disable(struct regmap *map) { } #endif @@ -259,7 +259,7 @@ bool regcache_set_val(struct regmap *map, void *base, unsigned int idx, int regcache_lookup_reg(struct regmap *map, unsigned int reg); int _regmap_raw_write(struct regmap *map, unsigned int reg, - const void *val, size_t val_len); + const void *val, size_t val_len, bool noinc); void regmap_async_complete_cb(struct regmap_async *async, int ret); diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c index a93cafd7be4f..7f4b3b62492c 100644 --- a/drivers/base/regmap/regcache.c +++ b/drivers/base/regmap/regcache.c @@ -717,7 +717,7 @@ static int regcache_sync_block_raw_flush(struct regmap *map, const void **data, map->cache_bypass = true; - ret = _regmap_raw_write(map, base, *data, count * val_bytes); + ret = _regmap_raw_write(map, base, *data, count * val_bytes, false); if (ret) dev_err(map->dev, "Unable to sync registers %#x-%#x. %d\n", base, cur - map->reg_stride, ret); diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c index f58baff2be0a..b6d63ef16b44 100644 --- a/drivers/base/regmap/regmap-debugfs.c +++ b/drivers/base/regmap/regmap-debugfs.c @@ -17,7 +17,6 @@ struct regmap_debugfs_node { struct regmap *map; - const char *name; struct list_head link; }; @@ -544,11 +543,12 @@ static const struct file_operations regmap_cache_bypass_fops = { .write = regmap_cache_bypass_write_file, }; -void regmap_debugfs_init(struct regmap *map, const char *name) +void regmap_debugfs_init(struct regmap *map) { struct rb_node *next; struct regmap_range_node *range_node; const char *devname = "dummy"; + const char *name = map->name; /* * Userspace can initiate reads from the hardware over debugfs. @@ -569,7 +569,6 @@ void regmap_debugfs_init(struct regmap *map, const char *name) if (!node) return; node->map = map; - node->name = name; mutex_lock(®map_debugfs_early_lock); list_add(&node->link, ®map_debugfs_early_list); mutex_unlock(®map_debugfs_early_lock); @@ -679,7 +678,7 @@ void regmap_debugfs_initcall(void) mutex_lock(®map_debugfs_early_lock); list_for_each_entry_safe(node, tmp, ®map_debugfs_early_list, link) { - regmap_debugfs_init(node->map, node->name); + regmap_debugfs_init(node->map); list_del(&node->link); kfree(node); } diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index e93700af7e6e..b71f9ecddff5 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -581,14 +581,34 @@ static void regmap_range_exit(struct regmap *map) kfree(map->selector_work_buf); } +static int regmap_set_name(struct regmap *map, const struct regmap_config *config) +{ + if (config->name) { + const char *name = kstrdup_const(config->name, GFP_KERNEL); + + if (!name) + return -ENOMEM; + + kfree_const(map->name); + map->name = name; + } + + return 0; +} + int regmap_attach_dev(struct device *dev, struct regmap *map, const struct regmap_config *config) { struct regmap **m; + int ret; map->dev = dev; - regmap_debugfs_init(map, config->name); + ret = regmap_set_name(map, config); + if (ret) + return ret; + + regmap_debugfs_init(map); /* Add a devres resource for dev_get_regmap() */ m = devres_alloc(dev_get_regmap_release, sizeof(*m), GFP_KERNEL); @@ -687,13 +707,9 @@ struct regmap *__regmap_init(struct device *dev, goto err; } - if (config->name) { - map->name = kstrdup_const(config->name, GFP_KERNEL); - if (!map->name) { - ret = -ENOMEM; - goto err_map; - } - } + ret = regmap_set_name(map, config); + if (ret) + goto err_map; if (config->disable_locking) { map->lock = map->unlock = regmap_lock_unlock_none; @@ -1137,7 +1153,7 @@ skip_format_initialization: if (ret != 0) goto err_regcache; } else { - regmap_debugfs_init(map, config->name); + regmap_debugfs_init(map); } return map; @@ -1297,6 +1313,8 @@ EXPORT_SYMBOL_GPL(regmap_field_free); */ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) { + int ret; + regcache_exit(map); regmap_debugfs_exit(map); @@ -1309,7 +1327,11 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config) map->readable_noinc_reg = config->readable_noinc_reg; map->cache_type = config->cache_type; - regmap_debugfs_init(map, config->name); + ret = regmap_set_name(map, config); + if (ret) + return ret; + + regmap_debugfs_init(map); map->cache_bypass = false; map->cache_only = false; @@ -1464,7 +1486,7 @@ static void regmap_set_work_buf_flag_mask(struct regmap *map, int max_bytes, } static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, - const void *val, size_t val_len) + const void *val, size_t val_len, bool noinc) { struct regmap_range_node *range; unsigned long flags; @@ -1523,7 +1545,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, win_residue, val_len / map->format.val_bytes); ret = _regmap_raw_write_impl(map, reg, val, win_residue * - map->format.val_bytes); + map->format.val_bytes, noinc); if (ret != 0) return ret; @@ -1537,7 +1559,7 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg, win_residue = range->window_len - win_offset; } - ret = _regmap_select_page(map, ®, range, val_num); + ret = _regmap_select_page(map, ®, range, noinc ? 1 : val_num); if (ret != 0) return ret; } @@ -1745,7 +1767,8 @@ static int _regmap_bus_raw_write(void *context, unsigned int reg, map->work_buf + map->format.reg_bytes + map->format.pad_bytes, - map->format.val_bytes); + map->format.val_bytes, + false); } static inline void *_regmap_map_get_context(struct regmap *map) @@ -1839,7 +1862,7 @@ int regmap_write_async(struct regmap *map, unsigned int reg, unsigned int val) EXPORT_SYMBOL_GPL(regmap_write_async); int _regmap_raw_write(struct regmap *map, unsigned int reg, - const void *val, size_t val_len) + const void *val, size_t val_len, bool noinc) { size_t val_bytes = map->format.val_bytes; size_t val_count = val_len / val_bytes; @@ -1860,7 +1883,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, /* Write as many bytes as possible with chunk_size */ for (i = 0; i < chunk_count; i++) { - ret = _regmap_raw_write_impl(map, reg, val, chunk_bytes); + ret = _regmap_raw_write_impl(map, reg, val, chunk_bytes, noinc); if (ret) return ret; @@ -1871,7 +1894,7 @@ int _regmap_raw_write(struct regmap *map, unsigned int reg, /* Write remaining bytes */ if (val_len) - ret = _regmap_raw_write_impl(map, reg, val, val_len); + ret = _regmap_raw_write_impl(map, reg, val, val_len, noinc); return ret; } @@ -1904,7 +1927,7 @@ int regmap_raw_write(struct regmap *map, unsigned int reg, map->lock(map->lock_arg); - ret = _regmap_raw_write(map, reg, val, val_len); + ret = _regmap_raw_write(map, reg, val, val_len, false); map->unlock(map->lock_arg); @@ -1962,7 +1985,7 @@ int regmap_noinc_write(struct regmap *map, unsigned int reg, write_len = map->max_raw_write; else write_len = val_len; - ret = _regmap_raw_write(map, reg, val, write_len); + ret = _regmap_raw_write(map, reg, val, write_len, true); if (ret) goto out_unlock; val = ((u8 *)val) + write_len; @@ -2439,7 +2462,7 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg, map->async = true; - ret = _regmap_raw_write(map, reg, val, val_len); + ret = _regmap_raw_write(map, reg, val, val_len, false); map->async = false; @@ -2450,7 +2473,7 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg, EXPORT_SYMBOL_GPL(regmap_raw_write_async); static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, - unsigned int val_len) + unsigned int val_len, bool noinc) { struct regmap_range_node *range; int ret; @@ -2463,7 +2486,7 @@ static int _regmap_raw_read(struct regmap *map, unsigned int reg, void *val, range = _regmap_range_lookup(map, reg); if (range) { ret = _regmap_select_page(map, ®, range, - val_len / map->format.val_bytes); + noinc ? 1 : val_len / map->format.val_bytes); if (ret != 0) return ret; } @@ -2501,7 +2524,7 @@ static int _regmap_bus_read(void *context, unsigned int reg, if (!map->format.parse_val) return -EINVAL; - ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes); + ret = _regmap_raw_read(map, reg, work_val, map->format.val_bytes, false); if (ret == 0) *val = map->format.parse_val(work_val); @@ -2617,7 +2640,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, /* Read bytes that fit into whole chunks */ for (i = 0; i < chunk_count; i++) { - ret = _regmap_raw_read(map, reg, val, chunk_bytes); + ret = _regmap_raw_read(map, reg, val, chunk_bytes, false); if (ret != 0) goto out; @@ -2628,7 +2651,7 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val, /* Read remaining bytes */ if (val_len) { - ret = _regmap_raw_read(map, reg, val, val_len); + ret = _regmap_raw_read(map, reg, val, val_len, false); if (ret != 0) goto out; } @@ -2703,7 +2726,7 @@ int regmap_noinc_read(struct regmap *map, unsigned int reg, read_len = map->max_raw_read; else read_len = val_len; - ret = _regmap_raw_read(map, reg, val, read_len); + ret = _regmap_raw_read(map, reg, val, read_len, true); if (ret) goto out_unlock; val = ((u8 *)val) + read_len; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 04b6bde9419d..573dbf6f0c31 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1553,7 +1553,7 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa * put_page(); and would cause either a VM_BUG directly, or * __page_cache_release a page that would actually still be referenced * by someone, leading to some obscure delayed Oops somewhere else. */ - if (drbd_disable_sendpage || (page_count(page) < 1) || PageSlab(page)) + if (drbd_disable_sendpage || !sendpage_ok(page)) return _drbd_no_send_page(peer_device, page, offset, size, msg_flags); msg_flags |= MSG_NOSIGNAL; diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c index 51564fc23c63..f4086287bb71 100644 --- a/drivers/clk/samsung/clk-exynos4.c +++ b/drivers/clk/samsung/clk-exynos4.c @@ -927,7 +927,7 @@ static const struct samsung_gate_clock exynos4210_gate_clks[] __initconst = { GATE(CLK_PCIE, "pcie", "aclk133", GATE_IP_FSYS, 14, 0, 0), GATE(CLK_SMMU_PCIE, "smmu_pcie", "aclk133", GATE_IP_FSYS, 18, 0, 0), GATE(CLK_MODEMIF, "modemif", "aclk100", GATE_IP_PERIL, 28, 0, 0), - GATE(CLK_CHIPID, "chipid", "aclk100", E4210_GATE_IP_PERIR, 0, 0, 0), + GATE(CLK_CHIPID, "chipid", "aclk100", E4210_GATE_IP_PERIR, 0, CLK_IGNORE_UNUSED, 0), GATE(CLK_SYSREG, "sysreg", "aclk100", E4210_GATE_IP_PERIR, 0, CLK_IGNORE_UNUSED, 0), GATE(CLK_HDMI_CEC, "hdmi_cec", "aclk100", E4210_GATE_IP_PERIR, 11, 0, @@ -969,7 +969,7 @@ static const struct samsung_gate_clock exynos4x12_gate_clks[] __initconst = { 0), GATE(CLK_TSADC, "tsadc", "aclk133", E4X12_GATE_BUS_FSYS1, 16, 0, 0), GATE(CLK_MIPI_HSI, "mipi_hsi", "aclk133", GATE_IP_FSYS, 10, 0, 0), - GATE(CLK_CHIPID, "chipid", "aclk100", E4X12_GATE_IP_PERIR, 0, 0, 0), + GATE(CLK_CHIPID, "chipid", "aclk100", E4X12_GATE_IP_PERIR, 0, CLK_IGNORE_UNUSED, 0), GATE(CLK_SYSREG, "sysreg", "aclk100", E4X12_GATE_IP_PERIR, 1, CLK_IGNORE_UNUSED, 0), GATE(CLK_HDMI_CEC, "hdmi_cec", "aclk100", E4X12_GATE_IP_PERIR, 11, 0, diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c index fea33399a632..bd620876544d 100644 --- a/drivers/clk/samsung/clk-exynos5420.c +++ b/drivers/clk/samsung/clk-exynos5420.c @@ -1655,6 +1655,11 @@ static void __init exynos5x_clk_init(struct device_node *np, * main G3D clock enablement status. */ clk_prepare_enable(__clk_lookup("mout_sw_aclk_g3d")); + /* + * Keep top BPLL mux enabled permanently to ensure that DRAM operates + * properly. + */ + clk_prepare_enable(__clk_lookup("mout_bpll")); samsung_clk_of_add_provider(np, ctx); } diff --git a/drivers/clk/socfpga/clk-s10.c b/drivers/clk/socfpga/clk-s10.c index c1dfc9b34e4e..661a8e9bfb9b 100644 --- a/drivers/clk/socfpga/clk-s10.c +++ b/drivers/clk/socfpga/clk-s10.c @@ -209,7 +209,7 @@ static const struct stratix10_perip_cnt_clock s10_main_perip_cnt_clks[] = { { STRATIX10_EMAC_B_FREE_CLK, "emacb_free_clk", NULL, emacb_free_mux, ARRAY_SIZE(emacb_free_mux), 0, 0, 2, 0xB0, 1}, { STRATIX10_EMAC_PTP_FREE_CLK, "emac_ptp_free_clk", NULL, emac_ptp_free_mux, - ARRAY_SIZE(emac_ptp_free_mux), 0, 0, 4, 0xB0, 2}, + ARRAY_SIZE(emac_ptp_free_mux), 0, 0, 2, 0xB0, 2}, { STRATIX10_GPIO_DB_FREE_CLK, "gpio_db_free_clk", NULL, gpio_db_free_mux, ARRAY_SIZE(gpio_db_free_mux), 0, 0, 0, 0xB0, 3}, { STRATIX10_SDMMC_FREE_CLK, "sdmmc_free_clk", NULL, sdmmc_free_mux, diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c index f180c055d33f..c5cc0a2dac6f 100644 --- a/drivers/clk/tegra/clk-pll.c +++ b/drivers/clk/tegra/clk-pll.c @@ -1611,9 +1611,6 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw) unsigned long flags = 0; unsigned long input_rate; - if (clk_pll_is_enabled(hw)) - return 0; - input_rate = clk_hw_get_rate(clk_hw_get_parent(hw)); if (_get_table_rate(hw, &sel, pll->params->fixed_rate, input_rate)) @@ -1673,7 +1670,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw) pll_writel(val, PLLE_SS_CTRL, pll); udelay(1); - /* Enable hw control of xusb brick pll */ + /* Enable HW control of XUSB brick PLL */ val = pll_readl_misc(pll); val &= ~PLLE_MISC_IDDQ_SW_CTRL; pll_writel_misc(val, pll); @@ -1696,7 +1693,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw) val |= XUSBIO_PLL_CFG0_SEQ_ENABLE; pll_writel(val, XUSBIO_PLL_CFG0, pll); - /* Enable hw control of SATA pll */ + /* Enable HW control of SATA PLL */ val = pll_readl(SATA_PLL_CFG0, pll); val &= ~SATA_PLL_CFG0_PADPLL_RESET_SWCTL; val |= SATA_PLL_CFG0_PADPLL_USE_LOCKDET; diff --git a/drivers/clk/tegra/clk-tegra210-emc.c b/drivers/clk/tegra/clk-tegra210-emc.c index 352a2c3fc374..51fd0ec2a2d0 100644 --- a/drivers/clk/tegra/clk-tegra210-emc.c +++ b/drivers/clk/tegra/clk-tegra210-emc.c @@ -12,6 +12,8 @@ #include <linux/io.h> #include <linux/slab.h> +#include "clk.h" + #define CLK_SOURCE_EMC 0x19c #define CLK_SOURCE_EMC_2X_CLK_SRC GENMASK(31, 29) #define CLK_SOURCE_EMC_MC_EMC_SAME_FREQ BIT(16) diff --git a/drivers/clocksource/h8300_timer8.c b/drivers/clocksource/h8300_timer8.c index 1d740a8c42ab..47114c2a7cb5 100644 --- a/drivers/clocksource/h8300_timer8.c +++ b/drivers/clocksource/h8300_timer8.c @@ -169,7 +169,7 @@ static int __init h8300_8timer_init(struct device_node *node) return PTR_ERR(clk); } - ret = ENXIO; + ret = -ENXIO; base = of_iomap(node, 0); if (!base) { pr_err("failed to map registers for clockevent\n"); diff --git a/drivers/clocksource/timer-clint.c b/drivers/clocksource/timer-clint.c index d17367dee02c..6cfe2ab73eb0 100644 --- a/drivers/clocksource/timer-clint.c +++ b/drivers/clocksource/timer-clint.c @@ -38,6 +38,7 @@ static unsigned int clint_timer_irq; #ifdef CONFIG_RISCV_M_MODE u64 __iomem *clint_time_val; +EXPORT_SYMBOL(clint_time_val); #endif static void clint_send_ipi(const struct cpumask *target) diff --git a/drivers/clocksource/timer-gx6605s.c b/drivers/clocksource/timer-gx6605s.c index 80d0939d040b..8d386adbe800 100644 --- a/drivers/clocksource/timer-gx6605s.c +++ b/drivers/clocksource/timer-gx6605s.c @@ -28,6 +28,7 @@ static irqreturn_t gx6605s_timer_interrupt(int irq, void *dev) void __iomem *base = timer_of_base(to_timer_of(ce)); writel_relaxed(GX6605S_STATUS_CLR, base + TIMER_STATUS); + writel_relaxed(0, base + TIMER_INI); ce->event_handler(ce); diff --git a/drivers/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index f6fd1c1cc527..33b3e8aa2cc5 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -69,12 +69,33 @@ static bool dmtimer_systimer_revision1(struct dmtimer_systimer *t) return !(tidr >> 16); } +static void dmtimer_systimer_enable(struct dmtimer_systimer *t) +{ + u32 val; + + if (dmtimer_systimer_revision1(t)) + val = DMTIMER_TYPE1_ENABLE; + else + val = DMTIMER_TYPE2_ENABLE; + + writel_relaxed(val, t->base + t->sysc); +} + +static void dmtimer_systimer_disable(struct dmtimer_systimer *t) +{ + if (!dmtimer_systimer_revision1(t)) + return; + + writel_relaxed(DMTIMER_TYPE1_DISABLE, t->base + t->sysc); +} + static int __init dmtimer_systimer_type1_reset(struct dmtimer_systimer *t) { void __iomem *syss = t->base + OMAP_TIMER_V1_SYS_STAT_OFFSET; int ret; u32 l; + dmtimer_systimer_enable(t); writel_relaxed(BIT(1) | BIT(2), t->base + t->ifctrl); ret = readl_poll_timeout_atomic(syss, l, l & BIT(0), 100, DMTIMER_RESET_WAIT); @@ -88,6 +109,7 @@ static int __init dmtimer_systimer_type2_reset(struct dmtimer_systimer *t) void __iomem *sysc = t->base + t->sysc; u32 l; + dmtimer_systimer_enable(t); l = readl_relaxed(sysc); l |= BIT(0); writel_relaxed(l, sysc); @@ -336,26 +358,6 @@ static int __init dmtimer_systimer_init_clock(struct dmtimer_systimer *t, return 0; } -static void dmtimer_systimer_enable(struct dmtimer_systimer *t) -{ - u32 val; - - if (dmtimer_systimer_revision1(t)) - val = DMTIMER_TYPE1_ENABLE; - else - val = DMTIMER_TYPE2_ENABLE; - - writel_relaxed(val, t->base + t->sysc); -} - -static void dmtimer_systimer_disable(struct dmtimer_systimer *t) -{ - if (!dmtimer_systimer_revision1(t)) - return; - - writel_relaxed(DMTIMER_TYPE1_DISABLE, t->base + t->sysc); -} - static int __init dmtimer_systimer_setup(struct device_node *np, struct dmtimer_systimer *t) { @@ -409,8 +411,8 @@ static int __init dmtimer_systimer_setup(struct device_node *np, t->wakeup = regbase + _OMAP_TIMER_WAKEUP_EN_OFFSET; t->ifctrl = regbase + _OMAP_TIMER_IF_CTRL_OFFSET; - dmtimer_systimer_enable(t); dmtimer_systimer_reset(t); + dmtimer_systimer_enable(t); pr_debug("dmtimer rev %08x sysc %08x\n", readl_relaxed(t->base), readl_relaxed(t->base + t->sysc)); diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index a827b000ef51..9a515c460a00 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -2781,6 +2781,7 @@ static int intel_pstate_update_status(const char *buf, size_t size) cpufreq_unregister_driver(intel_pstate_driver); intel_pstate_driver_cleanup(); + return 0; } if (size == 6 && !strncmp(buf, "active", size)) { diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c index 74463841805f..d928b37718bd 100644 --- a/drivers/cpuidle/cpuidle-psci.c +++ b/drivers/cpuidle/cpuidle-psci.c @@ -66,7 +66,7 @@ static int psci_enter_domain_idle_state(struct cpuidle_device *dev, return -1; /* Do runtime PM to manage a hierarchical CPU toplogy. */ - pm_runtime_put_sync_suspend(pd_dev); + RCU_NONIDLE(pm_runtime_put_sync_suspend(pd_dev)); state = psci_get_domain_state(); if (!state) @@ -74,7 +74,7 @@ static int psci_enter_domain_idle_state(struct cpuidle_device *dev, ret = psci_cpu_suspend_enter(state) ? -1 : idx; - pm_runtime_get_sync(pd_dev); + RCU_NONIDLE(pm_runtime_get_sync(pd_dev)); cpu_pm_exit(); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 6c7e5621cf9a..29e84687f3c3 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -142,11 +142,6 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv, time_start = ns_to_ktime(local_clock()); - /* - * trace_suspend_resume() called by tick_freeze() for the last CPU - * executing it contains RCU usage regarded as invalid in the idle - * context, so tell RCU about that. - */ tick_freeze(); /* * The state used here cannot be a "coupled" one, because the "coupled" @@ -159,11 +154,6 @@ static void enter_s2idle_proper(struct cpuidle_driver *drv, target_state->enter_s2idle(dev, drv, index); if (WARN_ON_ONCE(!irqs_disabled())) local_irq_disable(); - /* - * timekeeping_resume() that will be called by tick_unfreeze() for the - * first CPU executing it calls functions containing RCU read-side - * critical sections, so tell RCU about that. - */ if (!(target_state->flags & CPUIDLE_FLAG_RCU_IDLE)) rcu_idle_exit(); tick_unfreeze(); diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 561d91b2d3bf..071b59fe84d2 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -1766,20 +1766,23 @@ static int devfreq_summary_show(struct seq_file *s, void *data) struct devfreq *p_devfreq = NULL; unsigned long cur_freq, min_freq, max_freq; unsigned int polling_ms; + unsigned int timer; - seq_printf(s, "%-30s %-30s %-15s %10s %12s %12s %12s\n", + seq_printf(s, "%-30s %-30s %-15s %-10s %10s %12s %12s %12s\n", "dev", "parent_dev", "governor", + "timer", "polling_ms", "cur_freq_Hz", "min_freq_Hz", "max_freq_Hz"); - seq_printf(s, "%30s %30s %15s %10s %12s %12s %12s\n", + seq_printf(s, "%30s %30s %15s %10s %10s %12s %12s %12s\n", "------------------------------", "------------------------------", "---------------", "----------", + "----------", "------------", "------------", "------------"); @@ -1803,13 +1806,15 @@ static int devfreq_summary_show(struct seq_file *s, void *data) cur_freq = devfreq->previous_freq; get_freq_range(devfreq, &min_freq, &max_freq); polling_ms = devfreq->profile->polling_ms; + timer = devfreq->profile->timer; mutex_unlock(&devfreq->lock); seq_printf(s, - "%-30s %-30s %-15s %10d %12ld %12ld %12ld\n", + "%-30s %-30s %-15s %-10s %10d %12ld %12ld %12ld\n", dev_name(&devfreq->dev), p_devfreq ? dev_name(&p_devfreq->dev) : "null", devfreq->governor_name, + polling_ms ? timer_name[timer] : "null", polling_ms, cur_freq, min_freq, diff --git a/drivers/devfreq/tegra30-devfreq.c b/drivers/devfreq/tegra30-devfreq.c index e94a27804c20..dedd39de7367 100644 --- a/drivers/devfreq/tegra30-devfreq.c +++ b/drivers/devfreq/tegra30-devfreq.c @@ -836,7 +836,8 @@ static int tegra_devfreq_probe(struct platform_device *pdev) rate = clk_round_rate(tegra->emc_clock, ULONG_MAX); if (rate < 0) { dev_err(&pdev->dev, "Failed to round clock rate: %ld\n", rate); - return rate; + err = rate; + goto disable_clk; } tegra->max_freq = rate / KHZ; @@ -897,6 +898,7 @@ remove_opps: dev_pm_opp_remove_all_dynamic(&pdev->dev); reset_control_reset(tegra->reset); +disable_clk: clk_disable_unprepare(tegra->clock); return err; diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c index 58564d82a3a2..844967f98866 100644 --- a/drivers/dma-buf/dma-buf.c +++ b/drivers/dma-buf/dma-buf.c @@ -59,6 +59,8 @@ static void dma_buf_release(struct dentry *dentry) struct dma_buf *dmabuf; dmabuf = dentry->d_fsdata; + if (unlikely(!dmabuf)) + return; BUG_ON(dmabuf->vmapping_counter); diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 45d4d92e91db..a819611b8892 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -129,6 +129,7 @@ struct dmatest_params { * @nr_channels: number of channels under test * @lock: access protection to the fields of this structure * @did_init: module has been initialized completely + * @last_error: test has faced configuration issues */ static struct dmatest_info { /* Test parameters */ @@ -137,6 +138,7 @@ static struct dmatest_info { /* Internal state */ struct list_head channels; unsigned int nr_channels; + int last_error; struct mutex lock; bool did_init; } test_info = { @@ -1184,10 +1186,22 @@ static int dmatest_run_set(const char *val, const struct kernel_param *kp) return ret; } else if (dmatest_run) { if (!is_threaded_test_pending(info)) { - pr_info("No channels configured, continue with any\n"); - if (!is_threaded_test_run(info)) - stop_threaded_test(info); - add_threaded_test(info); + /* + * We have nothing to run. This can be due to: + */ + ret = info->last_error; + if (ret) { + /* 1) Misconfiguration */ + pr_err("Channel misconfigured, can't continue\n"); + mutex_unlock(&info->lock); + return ret; + } else { + /* 2) We rely on defaults */ + pr_info("No channels configured, continue with any\n"); + if (!is_threaded_test_run(info)) + stop_threaded_test(info); + add_threaded_test(info); + } } start_threaded_tests(info); } else { @@ -1204,7 +1218,7 @@ static int dmatest_chan_set(const char *val, const struct kernel_param *kp) struct dmatest_info *info = &test_info; struct dmatest_chan *dtc; char chan_reset_val[20]; - int ret = 0; + int ret; mutex_lock(&info->lock); ret = param_set_copystring(val, kp); @@ -1259,12 +1273,14 @@ static int dmatest_chan_set(const char *val, const struct kernel_param *kp) goto add_chan_err; } + info->last_error = ret; mutex_unlock(&info->lock); return ret; add_chan_err: param_set_copystring(chan_reset_val, kp); + info->last_error = ret; mutex_unlock(&info->lock); return ret; diff --git a/drivers/gpio/gpio-amd-fch.c b/drivers/gpio/gpio-amd-fch.c index 4e44ba4d7423..2a21354ed6a0 100644 --- a/drivers/gpio/gpio-amd-fch.c +++ b/drivers/gpio/gpio-amd-fch.c @@ -92,7 +92,7 @@ static int amd_fch_gpio_get_direction(struct gpio_chip *gc, unsigned int gpio) ret = (readl_relaxed(ptr) & AMD_FCH_GPIO_FLAG_DIRECTION); spin_unlock_irqrestore(&priv->lock, flags); - return ret ? GPIO_LINE_DIRECTION_IN : GPIO_LINE_DIRECTION_OUT; + return ret ? GPIO_LINE_DIRECTION_OUT : GPIO_LINE_DIRECTION_IN; } static void amd_fch_gpio_set(struct gpio_chip *gc, diff --git a/drivers/gpio/gpio-aspeed-sgpio.c b/drivers/gpio/gpio-aspeed-sgpio.c index 3aa45934d60c..64e54f8c30d2 100644 --- a/drivers/gpio/gpio-aspeed-sgpio.c +++ b/drivers/gpio/gpio-aspeed-sgpio.c @@ -17,7 +17,17 @@ #include <linux/spinlock.h> #include <linux/string.h> -#define MAX_NR_SGPIO 80 +/* + * MAX_NR_HW_GPIO represents the number of actual hardware-supported GPIOs (ie, + * slots within the clocked serial GPIO data). Since each HW GPIO is both an + * input and an output, we provide MAX_NR_HW_GPIO * 2 lines on our gpiochip + * device. + * + * We use SGPIO_OUTPUT_OFFSET to define the split between the inputs and + * outputs; the inputs start at line 0, the outputs start at OUTPUT_OFFSET. + */ +#define MAX_NR_HW_SGPIO 80 +#define SGPIO_OUTPUT_OFFSET MAX_NR_HW_SGPIO #define ASPEED_SGPIO_CTRL 0x54 @@ -30,8 +40,8 @@ struct aspeed_sgpio { struct clk *pclk; spinlock_t lock; void __iomem *base; - uint32_t dir_in[3]; int irq; + int n_sgpio; }; struct aspeed_sgpio_bank { @@ -111,31 +121,69 @@ static void __iomem *bank_reg(struct aspeed_sgpio *gpio, } } -#define GPIO_BANK(x) ((x) >> 5) -#define GPIO_OFFSET(x) ((x) & 0x1f) +#define GPIO_BANK(x) ((x % SGPIO_OUTPUT_OFFSET) >> 5) +#define GPIO_OFFSET(x) ((x % SGPIO_OUTPUT_OFFSET) & 0x1f) #define GPIO_BIT(x) BIT(GPIO_OFFSET(x)) static const struct aspeed_sgpio_bank *to_bank(unsigned int offset) { - unsigned int bank = GPIO_BANK(offset); + unsigned int bank; + + bank = GPIO_BANK(offset); WARN_ON(bank >= ARRAY_SIZE(aspeed_sgpio_banks)); return &aspeed_sgpio_banks[bank]; } +static int aspeed_sgpio_init_valid_mask(struct gpio_chip *gc, + unsigned long *valid_mask, unsigned int ngpios) +{ + struct aspeed_sgpio *sgpio = gpiochip_get_data(gc); + int n = sgpio->n_sgpio; + int c = SGPIO_OUTPUT_OFFSET - n; + + WARN_ON(ngpios < MAX_NR_HW_SGPIO * 2); + + /* input GPIOs in the lower range */ + bitmap_set(valid_mask, 0, n); + bitmap_clear(valid_mask, n, c); + + /* output GPIOS above SGPIO_OUTPUT_OFFSET */ + bitmap_set(valid_mask, SGPIO_OUTPUT_OFFSET, n); + bitmap_clear(valid_mask, SGPIO_OUTPUT_OFFSET + n, c); + + return 0; +} + +static void aspeed_sgpio_irq_init_valid_mask(struct gpio_chip *gc, + unsigned long *valid_mask, unsigned int ngpios) +{ + struct aspeed_sgpio *sgpio = gpiochip_get_data(gc); + int n = sgpio->n_sgpio; + + WARN_ON(ngpios < MAX_NR_HW_SGPIO * 2); + + /* input GPIOs in the lower range */ + bitmap_set(valid_mask, 0, n); + bitmap_clear(valid_mask, n, ngpios - n); +} + +static bool aspeed_sgpio_is_input(unsigned int offset) +{ + return offset < SGPIO_OUTPUT_OFFSET; +} + static int aspeed_sgpio_get(struct gpio_chip *gc, unsigned int offset) { struct aspeed_sgpio *gpio = gpiochip_get_data(gc); const struct aspeed_sgpio_bank *bank = to_bank(offset); unsigned long flags; enum aspeed_sgpio_reg reg; - bool is_input; int rc = 0; spin_lock_irqsave(&gpio->lock, flags); - is_input = gpio->dir_in[GPIO_BANK(offset)] & GPIO_BIT(offset); - reg = is_input ? reg_val : reg_rdata; + reg = aspeed_sgpio_is_input(offset) ? reg_val : reg_rdata; rc = !!(ioread32(bank_reg(gpio, bank, reg)) & GPIO_BIT(offset)); spin_unlock_irqrestore(&gpio->lock, flags); @@ -143,22 +191,31 @@ static int aspeed_sgpio_get(struct gpio_chip *gc, unsigned int offset) return rc; } -static void sgpio_set_value(struct gpio_chip *gc, unsigned int offset, int val) +static int sgpio_set_value(struct gpio_chip *gc, unsigned int offset, int val) { struct aspeed_sgpio *gpio = gpiochip_get_data(gc); const struct aspeed_sgpio_bank *bank = to_bank(offset); - void __iomem *addr; + void __iomem *addr_r, *addr_w; u32 reg = 0; - addr = bank_reg(gpio, bank, reg_val); - reg = ioread32(addr); + if (aspeed_sgpio_is_input(offset)) + return -EINVAL; + + /* Since this is an output, read the cached value from rdata, then + * update val. */ + addr_r = bank_reg(gpio, bank, reg_rdata); + addr_w = bank_reg(gpio, bank, reg_val); + + reg = ioread32(addr_r); if (val) reg |= GPIO_BIT(offset); else reg &= ~GPIO_BIT(offset); - iowrite32(reg, addr); + iowrite32(reg, addr_w); + + return 0; } static void aspeed_sgpio_set(struct gpio_chip *gc, unsigned int offset, int val) @@ -175,43 +232,28 @@ static void aspeed_sgpio_set(struct gpio_chip *gc, unsigned int offset, int val) static int aspeed_sgpio_dir_in(struct gpio_chip *gc, unsigned int offset) { - struct aspeed_sgpio *gpio = gpiochip_get_data(gc); - unsigned long flags; - - spin_lock_irqsave(&gpio->lock, flags); - gpio->dir_in[GPIO_BANK(offset)] |= GPIO_BIT(offset); - spin_unlock_irqrestore(&gpio->lock, flags); - - return 0; + return aspeed_sgpio_is_input(offset) ? 0 : -EINVAL; } static int aspeed_sgpio_dir_out(struct gpio_chip *gc, unsigned int offset, int val) { struct aspeed_sgpio *gpio = gpiochip_get_data(gc); unsigned long flags; + int rc; - spin_lock_irqsave(&gpio->lock, flags); - - gpio->dir_in[GPIO_BANK(offset)] &= ~GPIO_BIT(offset); - sgpio_set_value(gc, offset, val); + /* No special action is required for setting the direction; we'll + * error-out in sgpio_set_value if this isn't an output GPIO */ + spin_lock_irqsave(&gpio->lock, flags); + rc = sgpio_set_value(gc, offset, val); spin_unlock_irqrestore(&gpio->lock, flags); - return 0; + return rc; } static int aspeed_sgpio_get_direction(struct gpio_chip *gc, unsigned int offset) { - int dir_status; - struct aspeed_sgpio *gpio = gpiochip_get_data(gc); - unsigned long flags; - - spin_lock_irqsave(&gpio->lock, flags); - dir_status = gpio->dir_in[GPIO_BANK(offset)] & GPIO_BIT(offset); - spin_unlock_irqrestore(&gpio->lock, flags); - - return dir_status; - + return !!aspeed_sgpio_is_input(offset); } static void irqd_to_aspeed_sgpio_data(struct irq_data *d, @@ -402,6 +444,7 @@ static int aspeed_sgpio_setup_irqs(struct aspeed_sgpio *gpio, irq = &gpio->chip.irq; irq->chip = &aspeed_sgpio_irqchip; + irq->init_valid_mask = aspeed_sgpio_irq_init_valid_mask; irq->handler = handle_bad_irq; irq->default_type = IRQ_TYPE_NONE; irq->parent_handler = aspeed_sgpio_irq_handler; @@ -409,17 +452,15 @@ static int aspeed_sgpio_setup_irqs(struct aspeed_sgpio *gpio, irq->parents = &gpio->irq; irq->num_parents = 1; - /* set IRQ settings and Enable Interrupt */ + /* Apply default IRQ settings */ for (i = 0; i < ARRAY_SIZE(aspeed_sgpio_banks); i++) { bank = &aspeed_sgpio_banks[i]; /* set falling or level-low irq */ iowrite32(0x00000000, bank_reg(gpio, bank, reg_irq_type0)); /* trigger type is edge */ iowrite32(0x00000000, bank_reg(gpio, bank, reg_irq_type1)); - /* dual edge trigger mode. */ - iowrite32(0xffffffff, bank_reg(gpio, bank, reg_irq_type2)); - /* enable irq */ - iowrite32(0xffffffff, bank_reg(gpio, bank, reg_irq_enable)); + /* single edge trigger */ + iowrite32(0x00000000, bank_reg(gpio, bank, reg_irq_type2)); } return 0; @@ -452,11 +493,12 @@ static int __init aspeed_sgpio_probe(struct platform_device *pdev) if (rc < 0) { dev_err(&pdev->dev, "Could not read ngpios property\n"); return -EINVAL; - } else if (nr_gpios > MAX_NR_SGPIO) { + } else if (nr_gpios > MAX_NR_HW_SGPIO) { dev_err(&pdev->dev, "Number of GPIOs exceeds the maximum of %d: %d\n", - MAX_NR_SGPIO, nr_gpios); + MAX_NR_HW_SGPIO, nr_gpios); return -EINVAL; } + gpio->n_sgpio = nr_gpios; rc = of_property_read_u32(pdev->dev.of_node, "bus-frequency", &sgpio_freq); if (rc < 0) { @@ -497,7 +539,8 @@ static int __init aspeed_sgpio_probe(struct platform_device *pdev) spin_lock_init(&gpio->lock); gpio->chip.parent = &pdev->dev; - gpio->chip.ngpio = nr_gpios; + gpio->chip.ngpio = MAX_NR_HW_SGPIO * 2; + gpio->chip.init_valid_mask = aspeed_sgpio_init_valid_mask; gpio->chip.direction_input = aspeed_sgpio_dir_in; gpio->chip.direction_output = aspeed_sgpio_dir_out; gpio->chip.get_direction = aspeed_sgpio_get_direction; @@ -509,9 +552,6 @@ static int __init aspeed_sgpio_probe(struct platform_device *pdev) gpio->chip.label = dev_name(&pdev->dev); gpio->chip.base = -1; - /* set all SGPIO pins as input (1). */ - memset(gpio->dir_in, 0xff, sizeof(gpio->dir_in)); - aspeed_sgpio_setup_irqs(gpio, pdev); rc = devm_gpiochip_add_data(&pdev->dev, &gpio->chip, gpio); diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index bf08b4561f36..e44d5de2a120 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -1114,8 +1114,8 @@ static const struct aspeed_gpio_config ast2500_config = static const struct aspeed_bank_props ast2600_bank_props[] = { /* input output */ - {5, 0xffffffff, 0x0000ffff}, /* U/V/W/X */ - {6, 0xffff0000, 0x0fff0000}, /* Y/Z */ + {5, 0xffffffff, 0xffffff00}, /* U/V/W/X */ + {6, 0x0000ffff, 0x0000ffff}, /* Y/Z */ { }, }; diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c index bc345185db26..1652897fdf90 100644 --- a/drivers/gpio/gpio-mockup.c +++ b/drivers/gpio/gpio-mockup.c @@ -552,6 +552,7 @@ static int __init gpio_mockup_init(void) err = platform_driver_register(&gpio_mockup_driver); if (err) { gpio_mockup_err("error registering platform driver\n"); + debugfs_remove_recursive(gpio_mockup_dbg_dir); return err; } @@ -582,6 +583,7 @@ static int __init gpio_mockup_init(void) gpio_mockup_err("error registering device"); platform_driver_unregister(&gpio_mockup_driver); gpio_mockup_unregister_pdevs(); + debugfs_remove_recursive(gpio_mockup_dbg_dir); return PTR_ERR(pdev); } diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 7fbe0c9e1fc1..0ea640fb636c 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -1516,7 +1516,7 @@ static int __maybe_unused omap_gpio_runtime_resume(struct device *dev) return 0; } -static int omap_gpio_suspend(struct device *dev) +static int __maybe_unused omap_gpio_suspend(struct device *dev) { struct gpio_bank *bank = dev_get_drvdata(dev); @@ -1528,7 +1528,7 @@ static int omap_gpio_suspend(struct device *dev) return omap_gpio_runtime_suspend(dev); } -static int omap_gpio_resume(struct device *dev) +static int __maybe_unused omap_gpio_resume(struct device *dev) { struct gpio_bank *bank = dev_get_drvdata(dev); diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index bd2e96c34f82..c2d6121c48c9 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -818,12 +818,27 @@ static irqreturn_t pca953x_irq_handler(int irq, void *devid) int level; bool ret; + bitmap_zero(pending, MAX_LINE); + mutex_lock(&chip->i2c_lock); ret = pca953x_irq_pending(chip, pending); mutex_unlock(&chip->i2c_lock); - for_each_set_bit(level, pending, gc->ngpio) - handle_nested_irq(irq_find_mapping(gc->irq.domain, level)); + if (ret) { + ret = 0; + + for_each_set_bit(level, pending, gc->ngpio) { + int nested_irq = irq_find_mapping(gc->irq.domain, level); + + if (unlikely(nested_irq <= 0)) { + dev_warn_ratelimited(gc->parent, "unmapped interrupt %d\n", level); + continue; + } + + handle_nested_irq(nested_irq); + ret = 1; + } + } return IRQ_RETVAL(ret); } @@ -940,6 +955,7 @@ out: static int device_pca957x_init(struct pca953x_chip *chip, u32 invert) { DECLARE_BITMAP(val, MAX_LINE); + unsigned int i; int ret; ret = device_pca95xx_init(chip, invert); @@ -947,7 +963,9 @@ static int device_pca957x_init(struct pca953x_chip *chip, u32 invert) goto out; /* To enable register 6, 7 to control pull up and pull down */ - memset(val, 0x02, NBANK(chip)); + for (i = 0; i < NBANK(chip); i++) + bitmap_set_value8(val, 0x02, i * BANK_SZ); + ret = pca953x_write_regs(chip, PCA957X_BKEN, val); if (ret) goto out; diff --git a/drivers/gpio/gpio-siox.c b/drivers/gpio/gpio-siox.c index 26e1fe092304..f8c5e9fc4bac 100644 --- a/drivers/gpio/gpio-siox.c +++ b/drivers/gpio/gpio-siox.c @@ -245,6 +245,7 @@ static int gpio_siox_probe(struct siox_device *sdevice) girq->chip = &ddata->ichip; girq->default_type = IRQ_TYPE_NONE; girq->handler = handle_level_irq; + girq->threaded = true; ret = devm_gpiochip_add_data(dev, &ddata->gchip, NULL); if (ret) diff --git a/drivers/gpio/gpio-sprd.c b/drivers/gpio/gpio-sprd.c index d7314d39ab65..36ea8a3bd451 100644 --- a/drivers/gpio/gpio-sprd.c +++ b/drivers/gpio/gpio-sprd.c @@ -149,17 +149,20 @@ static int sprd_gpio_irq_set_type(struct irq_data *data, sprd_gpio_update(chip, offset, SPRD_GPIO_IS, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IBE, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IEV, 1); + sprd_gpio_update(chip, offset, SPRD_GPIO_IC, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_gpio_update(chip, offset, SPRD_GPIO_IS, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IBE, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IEV, 0); + sprd_gpio_update(chip, offset, SPRD_GPIO_IC, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_gpio_update(chip, offset, SPRD_GPIO_IS, 0); sprd_gpio_update(chip, offset, SPRD_GPIO_IBE, 1); + sprd_gpio_update(chip, offset, SPRD_GPIO_IC, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c index 58b0da9eb76f..ea3f68a28fea 100644 --- a/drivers/gpio/gpio-tc3589x.c +++ b/drivers/gpio/gpio-tc3589x.c @@ -212,7 +212,7 @@ static void tc3589x_gpio_irq_sync_unlock(struct irq_data *d) continue; tc3589x_gpio->oldregs[i][j] = new; - tc3589x_reg_write(tc3589x, regmap[i] + j * 8, new); + tc3589x_reg_write(tc3589x, regmap[i] + j, new); } } diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index e6c9b78adfc2..fed5a3b2172f 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -423,6 +423,21 @@ static __poll_t lineevent_poll(struct file *file, return events; } +static ssize_t lineevent_get_size(void) +{ +#if defined(CONFIG_X86_64) && !defined(CONFIG_UML) + /* i386 has no padding after 'id' */ + if (in_ia32_syscall()) { + struct compat_gpioeevent_data { + compat_u64 timestamp; + u32 id; + }; + + return sizeof(struct compat_gpioeevent_data); + } +#endif + return sizeof(struct gpioevent_data); +} static ssize_t lineevent_read(struct file *file, char __user *buf, @@ -432,9 +447,20 @@ static ssize_t lineevent_read(struct file *file, struct lineevent_state *le = file->private_data; struct gpioevent_data ge; ssize_t bytes_read = 0; + ssize_t ge_size; int ret; - if (count < sizeof(ge)) + /* + * When compatible system call is being used the struct gpioevent_data, + * in case of at least ia32, has different size due to the alignment + * differences. Because we have first member 64 bits followed by one of + * 32 bits there is no gap between them. The only difference is the + * padding at the end of the data structure. Hence, we calculate the + * actual sizeof() and pass this as an argument to copy_to_user() to + * drop unneeded bytes from the output. + */ + ge_size = lineevent_get_size(); + if (count < ge_size) return -EINVAL; do { @@ -470,10 +496,10 @@ static ssize_t lineevent_read(struct file *file, break; } - if (copy_to_user(buf + bytes_read, &ge, sizeof(ge))) + if (copy_to_user(buf + bytes_read, &ge, ge_size)) return -EFAULT; - bytes_read += sizeof(ge); - } while (count >= bytes_read + sizeof(ge)); + bytes_read += ge_size; + } while (count >= bytes_read + ge_size); return bytes_read; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index eb7cfe87042e..d0b8d0d341af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -80,8 +80,6 @@ MODULE_FIRMWARE("amdgpu/renoir_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/sienna_cichlid_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/navy_flounder_gpu_info.bin"); #define AMDGPU_RESUME_MS 2000 @@ -1600,6 +1598,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) case CHIP_CARRIZO: case CHIP_STONEY: case CHIP_VEGA20: + case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: default: return 0; case CHIP_VEGA10: @@ -1631,12 +1631,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) case CHIP_NAVI12: chip_name = "navi12"; break; - case CHIP_SIENNA_CICHLID: - chip_name = "sienna_cichlid"; - break; - case CHIP_NAVY_FLOUNDER: - chip_name = "navy_flounder"; - break; } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_gpu_info.bin", chip_name); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index d76172965199..44c1f6e00635 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -297,7 +297,7 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set, take the current one */ if (active && !adev->have_disp_power_ref) { adev->have_disp_power_ref = true; - goto out; + return ret; } /* if we have no active crtcs, then drop the power ref we got before */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 26127c7d2f32..321032d3a51a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1044,8 +1044,16 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, /* Navi12 */ - {0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12}, + {0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12}, + + /* Sienna_Cichlid */ + {0x1002, 0x73A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0, 0, 0} }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index e11c5d69843d..978bae731398 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1076,6 +1076,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm) release_sg: kfree(ttm->sg); + ttm->sg = NULL; return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 037a187aa42f..f73ce9721233 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3595,6 +3595,9 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev) if (!gfx_v10_0_navi10_gfxoff_should_enable(adev)) adev->pm.pp_feature &= ~PP_GFXOFF_MASK; break; + case CHIP_NAVY_FLOUNDER: + adev->pm.pp_feature &= ~PP_GFXOFF_MASK; + break; default: break; } diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 84d811b6e48b..c28ebf41530a 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -694,12 +694,12 @@ static void soc15_reg_base_init(struct amdgpu_device *adev) * it doesn't support SRIOV. */ if (amdgpu_discovery) { r = amdgpu_discovery_reg_base_init(adev); - if (r) { - DRM_WARN("failed to init reg base from ip discovery table, " - "fallback to legacy init method\n"); - vega10_reg_base_init(adev); - } + if (r == 0) + break; + DRM_WARN("failed to init reg base from ip discovery table, " + "fallback to legacy init method\n"); } + vega10_reg_base_init(adev); break; case CHIP_VEGA20: vega20_reg_base_init(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 63e5547cfb16..3a805eaf6f11 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -746,18 +746,18 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) | UVD_SUVD_CGC_GATE__IME_HEVC_MASK | UVD_SUVD_CGC_GATE__EFC_MASK | UVD_SUVD_CGC_GATE__SAOE_MASK - | 0x08000000 + | UVD_SUVD_CGC_GATE__SRE_AV1_MASK | UVD_SUVD_CGC_GATE__FBC_PCLK_MASK | UVD_SUVD_CGC_GATE__FBC_CCLK_MASK - | 0x40000000 + | UVD_SUVD_CGC_GATE__SCM_AV1_MASK | UVD_SUVD_CGC_GATE__SMPA_MASK); WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE, data); data = RREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE2); data |= (UVD_SUVD_CGC_GATE2__MPBE0_MASK | UVD_SUVD_CGC_GATE2__MPBE1_MASK - | 0x00000004 - | 0x00000008 + | UVD_SUVD_CGC_GATE2__SIT_AV1_MASK + | UVD_SUVD_CGC_GATE2__SDB_AV1_MASK | UVD_SUVD_CGC_GATE2__MPC1_MASK); WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE2, data); @@ -776,8 +776,8 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) | UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK - | 0x00008000 - | 0x00010000 + | UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK + | UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK | UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK | UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK | UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK); @@ -892,8 +892,8 @@ static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst) | UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK - | 0x00008000 - | 0x00010000 + | UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK + | UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK | UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK | UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK | UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK); 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 4ba8b54a2695..a717a4904268 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1409,7 +1409,7 @@ static int dm_late_init(void *handle) if (dmcu) ret = dmcu_load_iram(dmcu, params); else if (adev->dm.dc->ctx->dmub_srv) - ret = dmub_init_abm_config(adev->dm.dc->res_pool->abm, params); + ret = dmub_init_abm_config(adev->dm.dc->res_pool, params); if (!ret) return -EINVAL; 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 694c5bc93665..c2cd184f0bbd 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 @@ -604,7 +604,7 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev, struct int i = 0; hdcp_work = kcalloc(max_caps, sizeof(*hdcp_work), GFP_KERNEL); - if (hdcp_work == NULL) + if (ZERO_OR_NULL_PTR(hdcp_work)) return NULL; hdcp_work->srm = kcalloc(PSP_HDCP_SRM_FIRST_GEN_MAX_SIZE, sizeof(*hdcp_work->srm), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 543afa34d87a..21a3073c8929 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -783,7 +783,6 @@ void rn_clk_mgr_construct( } else { struct clk_log_info log_info = {0}; - clk_mgr->smu_ver = rn_vbios_smu_get_smu_version(clk_mgr); clk_mgr->periodic_retraining_disabled = rn_vbios_smu_is_periodic_retraining_disabled(clk_mgr); /* SMU Version 55.51.0 and up no longer have an issue diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile index 025637a83c3b..bd2a068f9863 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile @@ -31,9 +31,21 @@ DCN30 = dcn30_init.o dcn30_hubbub.o dcn30_hubp.o dcn30_dpp.o dcn30_optc.o \ dcn30_dio_link_encoder.o dcn30_resource.o -CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse -mpreferred-stack-boundary=4 - +ifdef CONFIG_X86 CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -msse +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse +endif + +ifdef CONFIG_PPC64 +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -maltivec +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -maltivec +endif + +ifdef CONFIG_ARM64 +CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mgeneral-regs-only +CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mgeneral-regs-only +endif + ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) IS_OLD_GCC = 1 @@ -45,8 +57,10 @@ ifdef IS_OLD_GCC # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 # (8B stack alignment). CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -mpreferred-stack-boundary=4 +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -mpreferred-stack-boundary=4 else CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -msse2 +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -msse2 endif AMD_DAL_DCN30 = $(addprefix $(AMDDALPATH)/dc/dcn30/,$(DCN30)) diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 859724771a75..61497954e67e 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -657,7 +657,7 @@ void fill_iram_v_2_3(struct iram_table_v_2_2 *ram_table, struct dmcu_iram_parame params, ram_table, big_endian); } -bool dmub_init_abm_config(struct abm *abm, +bool dmub_init_abm_config(struct resource_pool *res_pool, struct dmcu_iram_parameters params) { struct iram_table_v_2_2 ram_table; @@ -665,8 +665,13 @@ bool dmub_init_abm_config(struct abm *abm, bool result = false; uint32_t i, j = 0; - if (abm == NULL) +#if defined(CONFIG_DRM_AMD_DC_DCN3_0) + if (res_pool->abm == NULL && res_pool->multiple_abms[0] == NULL) return false; +#else + if (res_pool->abm == NULL) + return false; +#endif memset(&ram_table, 0, sizeof(ram_table)); memset(&config, 0, sizeof(config)); @@ -707,8 +712,14 @@ bool dmub_init_abm_config(struct abm *abm, config.min_abm_backlight = ram_table.min_abm_backlight; - result = abm->funcs->init_abm_config( - abm, (char *)(&config), sizeof(struct abm_config_table)); +#if defined(CONFIG_DRM_AMD_DC_DCN3_0) + if (res_pool->multiple_abms[0]) { + result = res_pool->multiple_abms[0]->funcs->init_abm_config( + res_pool->multiple_abms[0], (char *)(&config), sizeof(struct abm_config_table)); + } else +#endif + result = res_pool->abm->funcs->init_abm_config( + res_pool->abm, (char *)(&config), sizeof(struct abm_config_table)); return result; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h index 46fbca2e2cd1..fa4728d88092 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h @@ -28,6 +28,8 @@ #include "dc/inc/hw/dmcu.h" #include "dc/inc/hw/abm.h" +struct resource_pool; + enum abm_defines { abm_defines_max_level = 4, @@ -45,7 +47,7 @@ struct dmcu_iram_parameters { bool dmcu_load_iram(struct dmcu *dmcu, struct dmcu_iram_parameters params); -bool dmub_init_abm_config(struct abm *abm, +bool dmub_init_abm_config(struct resource_pool *res_pool, struct dmcu_iram_parameters params); #endif /* MODULES_POWER_POWER_HELPERS_H_ */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h index 1116779252e6..e245e912535e 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h @@ -2727,6 +2727,7 @@ #define mmDB_STENCIL_WRITE_BASE_DEFAULT 0x00000000 #define mmDB_RESERVED_REG_1_DEFAULT 0x00000000 #define mmDB_RESERVED_REG_3_DEFAULT 0x00000000 +#define mmDB_VRS_OVERRIDE_CNTL_DEFAULT 0x00000000 #define mmDB_Z_READ_BASE_HI_DEFAULT 0x00000000 #define mmDB_STENCIL_READ_BASE_HI_DEFAULT 0x00000000 #define mmDB_Z_WRITE_BASE_HI_DEFAULT 0x00000000 @@ -3062,6 +3063,7 @@ #define mmPA_SU_OVER_RASTERIZATION_CNTL_DEFAULT 0x00000000 #define mmPA_STEREO_CNTL_DEFAULT 0x00000000 #define mmPA_STATE_STEREO_X_DEFAULT 0x00000000 +#define mmPA_CL_VRS_CNTL_DEFAULT 0x00000000 #define mmPA_SU_POINT_SIZE_DEFAULT 0x00000000 #define mmPA_SU_POINT_MINMAX_DEFAULT 0x00000000 #define mmPA_SU_LINE_CNTL_DEFAULT 0x00000000 diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h index 05d1b0a5f6d2..644a9fa71bb2 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h @@ -5379,6 +5379,8 @@ #define mmDB_RESERVED_REG_1_BASE_IDX 1 #define mmDB_RESERVED_REG_3 0x0017 #define mmDB_RESERVED_REG_3_BASE_IDX 1 +#define mmDB_VRS_OVERRIDE_CNTL 0x0019 +#define mmDB_VRS_OVERRIDE_CNTL_BASE_IDX 1 #define mmDB_Z_READ_BASE_HI 0x001a #define mmDB_Z_READ_BASE_HI_BASE_IDX 1 #define mmDB_STENCIL_READ_BASE_HI 0x001b @@ -6049,6 +6051,8 @@ #define mmPA_STEREO_CNTL_BASE_IDX 1 #define mmPA_STATE_STEREO_X 0x0211 #define mmPA_STATE_STEREO_X_BASE_IDX 1 +#define mmPA_CL_VRS_CNTL 0x0212 +#define mmPA_CL_VRS_CNTL_BASE_IDX 1 #define mmPA_SU_POINT_SIZE 0x0280 #define mmPA_SU_POINT_SIZE_BASE_IDX 1 #define mmPA_SU_POINT_MINMAX 0x0281 diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h index aac57f714cf1..2e449fcff893 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h @@ -9777,6 +9777,7 @@ #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_HTILE__SHIFT 0x3 #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_QUAD__SHIFT 0x4 #define DB_EXCEPTION_CONTROL__FORCE_SUMMARIZE__SHIFT 0x8 +#define DB_EXCEPTION_CONTROL__FORCE_VRS_RATE_FINE__SHIFT 0x10 #define DB_EXCEPTION_CONTROL__DTAG_WATERMARK__SHIFT 0x18 #define DB_EXCEPTION_CONTROL__EARLY_Z_PANIC_DISABLE_MASK 0x00000001L #define DB_EXCEPTION_CONTROL__LATE_Z_PANIC_DISABLE_MASK 0x00000002L @@ -9784,6 +9785,7 @@ #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_HTILE_MASK 0x00000008L #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_QUAD_MASK 0x00000010L #define DB_EXCEPTION_CONTROL__FORCE_SUMMARIZE_MASK 0x00000F00L +#define DB_EXCEPTION_CONTROL__FORCE_VRS_RATE_FINE_MASK 0x00FF0000L #define DB_EXCEPTION_CONTROL__DTAG_WATERMARK_MASK 0x7F000000L //DB_DFSM_CONFIG #define DB_DFSM_CONFIG__BYPASS_DFSM__SHIFT 0x0 @@ -10076,6 +10078,7 @@ #define CB_HW_CONTROL_3__DISABLE_NACK_PROCESSING_CM__SHIFT 0x18 #define CB_HW_CONTROL_3__DISABLE_NACK_COLOR_RD_WR_OPT__SHIFT 0x19 #define CB_HW_CONTROL_3__DISABLE_BLENDER_CLOCK_GATING__SHIFT 0x1a +#define CB_HW_CONTROL_3__DISABLE_DCC_VRS_OPT__SHIFT 0x1c #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT__SHIFT 0x1e #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_BC__SHIFT 0x1f #define CB_HW_CONTROL_3__DISABLE_SLOW_MODE_EMPTY_HALF_QUAD_KILL_MASK 0x00000001L @@ -10103,12 +10106,15 @@ #define CB_HW_CONTROL_3__DISABLE_NACK_PROCESSING_CM_MASK 0x01000000L #define CB_HW_CONTROL_3__DISABLE_NACK_COLOR_RD_WR_OPT_MASK 0x02000000L #define CB_HW_CONTROL_3__DISABLE_BLENDER_CLOCK_GATING_MASK 0x04000000L +#define CB_HW_CONTROL_3__DISABLE_DCC_VRS_OPT_MASK 0x10000000L #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_MASK 0x40000000L #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_BC_MASK 0x80000000L //CB_HW_CONTROL #define CB_HW_CONTROL__ALLOW_MRT_WITH_DUAL_SOURCE__SHIFT 0x0 +#define CB_HW_CONTROL__DISABLE_VRS_FILLRATE_OPTIMIZATION__SHIFT 0x1 #define CB_HW_CONTROL__DISABLE_FILLRATE_OPT_FIX_WITH_CFC__SHIFT 0x3 #define CB_HW_CONTROL__DISABLE_POST_DCC_WITH_CFC_FIX__SHIFT 0x4 +#define CB_HW_CONTROL__DISABLE_COMPRESS_1FRAG_WHEN_VRS_RATE_HINT_EN__SHIFT 0x5 #define CB_HW_CONTROL__RMI_CREDITS__SHIFT 0x6 #define CB_HW_CONTROL__CHICKEN_BITS__SHIFT 0xc #define CB_HW_CONTROL__DISABLE_FMASK_MULTI_MGCG_DOMAINS__SHIFT 0xf @@ -10129,8 +10135,10 @@ #define CB_HW_CONTROL__DISABLE_CC_IB_SERIALIZER_STATE_OPT__SHIFT 0x1e #define CB_HW_CONTROL__DISABLE_PIXEL_IN_QUAD_FIX_FOR_LINEAR_SURFACE__SHIFT 0x1f #define CB_HW_CONTROL__ALLOW_MRT_WITH_DUAL_SOURCE_MASK 0x00000001L +#define CB_HW_CONTROL__DISABLE_VRS_FILLRATE_OPTIMIZATION_MASK 0x00000002L #define CB_HW_CONTROL__DISABLE_FILLRATE_OPT_FIX_WITH_CFC_MASK 0x00000008L #define CB_HW_CONTROL__DISABLE_POST_DCC_WITH_CFC_FIX_MASK 0x00000010L +#define CB_HW_CONTROL__DISABLE_COMPRESS_1FRAG_WHEN_VRS_RATE_HINT_EN_MASK 0x00000020L #define CB_HW_CONTROL__RMI_CREDITS_MASK 0x00000FC0L #define CB_HW_CONTROL__CHICKEN_BITS_MASK 0x00007000L #define CB_HW_CONTROL__DISABLE_FMASK_MULTI_MGCG_DOMAINS_MASK 0x00008000L @@ -19881,6 +19889,7 @@ #define DB_RENDER_OVERRIDE2__PRESERVE_SRESULTS__SHIFT 0x16 #define DB_RENDER_OVERRIDE2__DISABLE_FAST_PASS__SHIFT 0x17 #define DB_RENDER_OVERRIDE2__ALLOW_PARTIAL_RES_HIER_KILL__SHIFT 0x19 +#define DB_RENDER_OVERRIDE2__FORCE_VRS_RATE_FINE__SHIFT 0x1a #define DB_RENDER_OVERRIDE2__CENTROID_COMPUTATION_MODE__SHIFT 0x1b #define DB_RENDER_OVERRIDE2__PARTIAL_SQUAD_LAUNCH_CONTROL_MASK 0x00000003L #define DB_RENDER_OVERRIDE2__PARTIAL_SQUAD_LAUNCH_COUNTDOWN_MASK 0x0000001CL @@ -19898,6 +19907,7 @@ #define DB_RENDER_OVERRIDE2__PRESERVE_SRESULTS_MASK 0x00400000L #define DB_RENDER_OVERRIDE2__DISABLE_FAST_PASS_MASK 0x00800000L #define DB_RENDER_OVERRIDE2__ALLOW_PARTIAL_RES_HIER_KILL_MASK 0x02000000L +#define DB_RENDER_OVERRIDE2__FORCE_VRS_RATE_FINE_MASK 0x04000000L #define DB_RENDER_OVERRIDE2__CENTROID_COMPUTATION_MODE_MASK 0x18000000L //DB_HTILE_DATA_BASE #define DB_HTILE_DATA_BASE__BASE_256B__SHIFT 0x0 @@ -20021,6 +20031,13 @@ //DB_RESERVED_REG_3 #define DB_RESERVED_REG_3__FIELD_1__SHIFT 0x0 #define DB_RESERVED_REG_3__FIELD_1_MASK 0x003FFFFFL +//DB_VRS_OVERRIDE_CNTL +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_COMBINER_MODE__SHIFT 0x0 +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_X__SHIFT 0x4 +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_Y__SHIFT 0x6 +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_COMBINER_MODE_MASK 0x00000007L +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_X_MASK 0x00000030L +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_Y_MASK 0x000000C0L //DB_Z_READ_BASE_HI #define DB_Z_READ_BASE_HI__BASE_HI__SHIFT 0x0 #define DB_Z_READ_BASE_HI__BASE_HI_MASK 0x000000FFL @@ -22598,6 +22615,7 @@ #define PA_CL_VS_OUT_CNTL__VS_OUT_MISC_SIDE_BUS_ENA__SHIFT 0x18 #define PA_CL_VS_OUT_CNTL__USE_VTX_GS_CUT_FLAG__SHIFT 0x19 #define PA_CL_VS_OUT_CNTL__USE_VTX_LINE_WIDTH__SHIFT 0x1b +#define PA_CL_VS_OUT_CNTL__USE_VTX_VRS_RATE__SHIFT 0x1c #define PA_CL_VS_OUT_CNTL__BYPASS_VTX_RATE_COMBINER__SHIFT 0x1d #define PA_CL_VS_OUT_CNTL__BYPASS_PRIM_RATE_COMBINER__SHIFT 0x1e #define PA_CL_VS_OUT_CNTL__CLIP_DIST_ENA_0_MASK 0x00000001L @@ -22627,6 +22645,7 @@ #define PA_CL_VS_OUT_CNTL__VS_OUT_MISC_SIDE_BUS_ENA_MASK 0x01000000L #define PA_CL_VS_OUT_CNTL__USE_VTX_GS_CUT_FLAG_MASK 0x02000000L #define PA_CL_VS_OUT_CNTL__USE_VTX_LINE_WIDTH_MASK 0x08000000L +#define PA_CL_VS_OUT_CNTL__USE_VTX_VRS_RATE_MASK 0x10000000L #define PA_CL_VS_OUT_CNTL__BYPASS_VTX_RATE_COMBINER_MASK 0x20000000L #define PA_CL_VS_OUT_CNTL__BYPASS_PRIM_RATE_COMBINER_MASK 0x40000000L //PA_CL_NANINF_CNTL @@ -22740,6 +22759,19 @@ //PA_STATE_STEREO_X #define PA_STATE_STEREO_X__STEREO_X_OFFSET__SHIFT 0x0 #define PA_STATE_STEREO_X__STEREO_X_OFFSET_MASK 0xFFFFFFFFL +//PA_CL_VRS_CNTL +#define PA_CL_VRS_CNTL__VERTEX_RATE_COMBINER_MODE__SHIFT 0x0 +#define PA_CL_VRS_CNTL__PRIMITIVE_RATE_COMBINER_MODE__SHIFT 0x3 +#define PA_CL_VRS_CNTL__HTILE_RATE_COMBINER_MODE__SHIFT 0x6 +#define PA_CL_VRS_CNTL__SAMPLE_ITER_COMBINER_MODE__SHIFT 0x9 +#define PA_CL_VRS_CNTL__EXPOSE_VRS_PIXELS_MASK__SHIFT 0xd +#define PA_CL_VRS_CNTL__CMASK_RATE_HINT_FORCE_ZERO__SHIFT 0xe +#define PA_CL_VRS_CNTL__VERTEX_RATE_COMBINER_MODE_MASK 0x00000007L +#define PA_CL_VRS_CNTL__PRIMITIVE_RATE_COMBINER_MODE_MASK 0x00000038L +#define PA_CL_VRS_CNTL__HTILE_RATE_COMBINER_MODE_MASK 0x000001C0L +#define PA_CL_VRS_CNTL__SAMPLE_ITER_COMBINER_MODE_MASK 0x00000E00L +#define PA_CL_VRS_CNTL__EXPOSE_VRS_PIXELS_MASK_MASK 0x00002000L +#define PA_CL_VRS_CNTL__CMASK_RATE_HINT_FORCE_ZERO_MASK 0x00004000L //PA_SU_POINT_SIZE #define PA_SU_POINT_SIZE__HEIGHT__SHIFT 0x0 #define PA_SU_POINT_SIZE__WIDTH__SHIFT 0x10 @@ -23088,6 +23120,7 @@ #define DB_HTILE_SURFACE__DST_OUTSIDE_ZERO_TO_ONE__SHIFT 0x10 #define DB_HTILE_SURFACE__RESERVED_FIELD_6__SHIFT 0x11 #define DB_HTILE_SURFACE__PIPE_ALIGNED__SHIFT 0x12 +#define DB_HTILE_SURFACE__VRS_HTILE_ENCODING__SHIFT 0x13 #define DB_HTILE_SURFACE__RESERVED_FIELD_1_MASK 0x00000001L #define DB_HTILE_SURFACE__FULL_CACHE_MASK 0x00000002L #define DB_HTILE_SURFACE__RESERVED_FIELD_2_MASK 0x00000004L @@ -23097,6 +23130,7 @@ #define DB_HTILE_SURFACE__DST_OUTSIDE_ZERO_TO_ONE_MASK 0x00010000L #define DB_HTILE_SURFACE__RESERVED_FIELD_6_MASK 0x00020000L #define DB_HTILE_SURFACE__PIPE_ALIGNED_MASK 0x00040000L +#define DB_HTILE_SURFACE__VRS_HTILE_ENCODING_MASK 0x00180000L //DB_SRESULTS_COMPARE_STATE0 #define DB_SRESULTS_COMPARE_STATE0__COMPAREFUNC0__SHIFT 0x0 #define DB_SRESULTS_COMPARE_STATE0__COMPAREVALUE0__SHIFT 0x4 @@ -24954,6 +24988,7 @@ #define CB_COLOR0_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR0_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR0_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR0_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR0_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR0_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR0_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -24962,6 +24997,7 @@ #define CB_COLOR0_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR0_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR0_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR0_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR1_ATTRIB3 #define CB_COLOR1_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR1_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -24971,6 +25007,7 @@ #define CB_COLOR1_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR1_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR1_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR1_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR1_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR1_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR1_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -24979,6 +25016,7 @@ #define CB_COLOR1_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR1_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR1_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR1_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR2_ATTRIB3 #define CB_COLOR2_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR2_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -24988,6 +25026,7 @@ #define CB_COLOR2_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR2_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR2_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR2_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR2_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR2_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR2_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -24996,6 +25035,7 @@ #define CB_COLOR2_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR2_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR2_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR2_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR3_ATTRIB3 #define CB_COLOR3_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR3_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25005,6 +25045,7 @@ #define CB_COLOR3_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR3_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR3_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR3_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR3_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR3_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR3_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25013,6 +25054,7 @@ #define CB_COLOR3_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR3_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR3_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR3_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR4_ATTRIB3 #define CB_COLOR4_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR4_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25022,6 +25064,7 @@ #define CB_COLOR4_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR4_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR4_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR4_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR4_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR4_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR4_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25030,6 +25073,7 @@ #define CB_COLOR4_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR4_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR4_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR4_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR5_ATTRIB3 #define CB_COLOR5_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR5_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25039,6 +25083,7 @@ #define CB_COLOR5_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR5_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR5_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR5_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR5_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR5_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR5_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25047,6 +25092,7 @@ #define CB_COLOR5_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR5_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR5_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR5_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR6_ATTRIB3 #define CB_COLOR6_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR6_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25056,6 +25102,7 @@ #define CB_COLOR6_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR6_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR6_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR6_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR6_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR6_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR6_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25064,6 +25111,7 @@ #define CB_COLOR6_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR6_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR6_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR6_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR7_ATTRIB3 #define CB_COLOR7_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR7_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25073,6 +25121,7 @@ #define CB_COLOR7_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR7_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR7_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR7_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR7_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR7_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR7_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25081,6 +25130,7 @@ #define CB_COLOR7_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR7_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR7_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR7_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L // addressBlock: gc_gfxudec diff --git a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h index c0efd90808f2..58cf7adb9d54 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h @@ -2393,6 +2393,7 @@ #define VCN_FEATURES__HAS_MJPEG2_IDCT_DEC__SHIFT 0x7 #define VCN_FEATURES__HAS_SCLR_DEC__SHIFT 0x8 #define VCN_FEATURES__HAS_VP9_DEC__SHIFT 0x9 +#define VCN_FEATURES__HAS_AV1_DEC__SHIFT 0xa #define VCN_FEATURES__HAS_EFC_ENC__SHIFT 0xb #define VCN_FEATURES__HAS_EFC_HDR2SDR_ENC__SHIFT 0xc #define VCN_FEATURES__HAS_DUAL_MJPEG_DEC__SHIFT 0xd @@ -2407,6 +2408,7 @@ #define VCN_FEATURES__HAS_MJPEG2_IDCT_DEC_MASK 0x00000080L #define VCN_FEATURES__HAS_SCLR_DEC_MASK 0x00000100L #define VCN_FEATURES__HAS_VP9_DEC_MASK 0x00000200L +#define VCN_FEATURES__HAS_AV1_DEC_MASK 0x00000400L #define VCN_FEATURES__HAS_EFC_ENC_MASK 0x00000800L #define VCN_FEATURES__HAS_EFC_HDR2SDR_ENC_MASK 0x00001000L #define VCN_FEATURES__HAS_DUAL_MJPEG_DEC_MASK 0x00002000L @@ -2809,8 +2811,10 @@ #define UVD_SUVD_CGC_GATE__IME_HEVC__SHIFT 0x18 #define UVD_SUVD_CGC_GATE__EFC__SHIFT 0x19 #define UVD_SUVD_CGC_GATE__SAOE__SHIFT 0x1a +#define UVD_SUVD_CGC_GATE__SRE_AV1__SHIFT 0x1b #define UVD_SUVD_CGC_GATE__FBC_PCLK__SHIFT 0x1c #define UVD_SUVD_CGC_GATE__FBC_CCLK__SHIFT 0x1d +#define UVD_SUVD_CGC_GATE__SCM_AV1__SHIFT 0x1e #define UVD_SUVD_CGC_GATE__SMPA__SHIFT 0x1f #define UVD_SUVD_CGC_GATE__SRE_MASK 0x00000001L #define UVD_SUVD_CGC_GATE__SIT_MASK 0x00000002L @@ -2839,8 +2843,10 @@ #define UVD_SUVD_CGC_GATE__IME_HEVC_MASK 0x01000000L #define UVD_SUVD_CGC_GATE__EFC_MASK 0x02000000L #define UVD_SUVD_CGC_GATE__SAOE_MASK 0x04000000L +#define UVD_SUVD_CGC_GATE__SRE_AV1_MASK 0x08000000L #define UVD_SUVD_CGC_GATE__FBC_PCLK_MASK 0x10000000L #define UVD_SUVD_CGC_GATE__FBC_CCLK_MASK 0x20000000L +#define UVD_SUVD_CGC_GATE__SCM_AV1_MASK 0x40000000L #define UVD_SUVD_CGC_GATE__SMPA_MASK 0x80000000L //UVD_SUVD_CGC_STATUS #define UVD_SUVD_CGC_STATUS__SRE_VCLK__SHIFT 0x0 @@ -2873,6 +2879,8 @@ #define UVD_SUVD_CGC_STATUS__IME_HEVC_DCLK__SHIFT 0x1b #define UVD_SUVD_CGC_STATUS__EFC_DCLK__SHIFT 0x1c #define UVD_SUVD_CGC_STATUS__SAOE_DCLK__SHIFT 0x1d +#define UVD_SUVD_CGC_STATUS__SRE_AV1_VCLK__SHIFT 0x1e +#define UVD_SUVD_CGC_STATUS__SCM_AV1_DCLK__SHIFT 0x1f #define UVD_SUVD_CGC_STATUS__SRE_VCLK_MASK 0x00000001L #define UVD_SUVD_CGC_STATUS__SRE_DCLK_MASK 0x00000002L #define UVD_SUVD_CGC_STATUS__SIT_DCLK_MASK 0x00000004L @@ -2903,6 +2911,8 @@ #define UVD_SUVD_CGC_STATUS__IME_HEVC_DCLK_MASK 0x08000000L #define UVD_SUVD_CGC_STATUS__EFC_DCLK_MASK 0x10000000L #define UVD_SUVD_CGC_STATUS__SAOE_DCLK_MASK 0x20000000L +#define UVD_SUVD_CGC_STATUS__SRE_AV1_VCLK_MASK 0x40000000L +#define UVD_SUVD_CGC_STATUS__SCM_AV1_DCLK_MASK 0x80000000L //UVD_SUVD_CGC_CTRL #define UVD_SUVD_CGC_CTRL__SRE_MODE__SHIFT 0x0 #define UVD_SUVD_CGC_CTRL__SIT_MODE__SHIFT 0x1 @@ -2919,6 +2929,8 @@ #define UVD_SUVD_CGC_CTRL__SMPA_MODE__SHIFT 0xc #define UVD_SUVD_CGC_CTRL__MPBE0_MODE__SHIFT 0xd #define UVD_SUVD_CGC_CTRL__MPBE1_MODE__SHIFT 0xe +#define UVD_SUVD_CGC_CTRL__SIT_AV1_MODE__SHIFT 0xf +#define UVD_SUVD_CGC_CTRL__SDB_AV1_MODE__SHIFT 0x10 #define UVD_SUVD_CGC_CTRL__MPC1_MODE__SHIFT 0x11 #define UVD_SUVD_CGC_CTRL__FBC_PCLK__SHIFT 0x1c #define UVD_SUVD_CGC_CTRL__FBC_CCLK__SHIFT 0x1d @@ -2937,6 +2949,8 @@ #define UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK 0x00001000L #define UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK 0x00002000L #define UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK 0x00004000L +#define UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK 0x00008000L +#define UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK 0x00010000L #define UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK 0x00020000L #define UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK 0x10000000L #define UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK 0x20000000L @@ -3658,6 +3672,8 @@ #define UVD_SUVD_CGC_STATUS2__SMPA_VCLK__SHIFT 0x0 #define UVD_SUVD_CGC_STATUS2__SMPA_DCLK__SHIFT 0x1 #define UVD_SUVD_CGC_STATUS2__MPBE1_DCLK__SHIFT 0x3 +#define UVD_SUVD_CGC_STATUS2__SIT_AV1_DCLK__SHIFT 0x4 +#define UVD_SUVD_CGC_STATUS2__SDB_AV1_DCLK__SHIFT 0x5 #define UVD_SUVD_CGC_STATUS2__MPC1_DCLK__SHIFT 0x6 #define UVD_SUVD_CGC_STATUS2__MPC1_SCLK__SHIFT 0x7 #define UVD_SUVD_CGC_STATUS2__MPC1_VCLK__SHIFT 0x8 @@ -3666,6 +3682,8 @@ #define UVD_SUVD_CGC_STATUS2__SMPA_VCLK_MASK 0x00000001L #define UVD_SUVD_CGC_STATUS2__SMPA_DCLK_MASK 0x00000002L #define UVD_SUVD_CGC_STATUS2__MPBE1_DCLK_MASK 0x00000008L +#define UVD_SUVD_CGC_STATUS2__SIT_AV1_DCLK_MASK 0x00000010L +#define UVD_SUVD_CGC_STATUS2__SDB_AV1_DCLK_MASK 0x00000020L #define UVD_SUVD_CGC_STATUS2__MPC1_DCLK_MASK 0x00000040L #define UVD_SUVD_CGC_STATUS2__MPC1_SCLK_MASK 0x00000080L #define UVD_SUVD_CGC_STATUS2__MPC1_VCLK_MASK 0x00000100L @@ -3674,25 +3692,41 @@ //UVD_SUVD_CGC_GATE2 #define UVD_SUVD_CGC_GATE2__MPBE0__SHIFT 0x0 #define UVD_SUVD_CGC_GATE2__MPBE1__SHIFT 0x1 +#define UVD_SUVD_CGC_GATE2__SIT_AV1__SHIFT 0x2 +#define UVD_SUVD_CGC_GATE2__SDB_AV1__SHIFT 0x3 #define UVD_SUVD_CGC_GATE2__MPC1__SHIFT 0x4 #define UVD_SUVD_CGC_GATE2__MPBE0_MASK 0x00000001L #define UVD_SUVD_CGC_GATE2__MPBE1_MASK 0x00000002L +#define UVD_SUVD_CGC_GATE2__SIT_AV1_MASK 0x00000004L +#define UVD_SUVD_CGC_GATE2__SDB_AV1_MASK 0x00000008L #define UVD_SUVD_CGC_GATE2__MPC1_MASK 0x00000010L //UVD_SUVD_INT_STATUS2 #define UVD_SUVD_INT_STATUS2__SMPA_FUNC_INT__SHIFT 0x0 #define UVD_SUVD_INT_STATUS2__SMPA_ERR_INT__SHIFT 0x5 +#define UVD_SUVD_INT_STATUS2__SDB_AV1_FUNC_INT__SHIFT 0x6 +#define UVD_SUVD_INT_STATUS2__SDB_AV1_ERR_INT__SHIFT 0xb #define UVD_SUVD_INT_STATUS2__SMPA_FUNC_INT_MASK 0x0000001FL #define UVD_SUVD_INT_STATUS2__SMPA_ERR_INT_MASK 0x00000020L +#define UVD_SUVD_INT_STATUS2__SDB_AV1_FUNC_INT_MASK 0x000007C0L +#define UVD_SUVD_INT_STATUS2__SDB_AV1_ERR_INT_MASK 0x00000800L //UVD_SUVD_INT_EN2 #define UVD_SUVD_INT_EN2__SMPA_FUNC_INT_EN__SHIFT 0x0 #define UVD_SUVD_INT_EN2__SMPA_ERR_INT_EN__SHIFT 0x5 +#define UVD_SUVD_INT_EN2__SDB_AV1_FUNC_INT_EN__SHIFT 0x6 +#define UVD_SUVD_INT_EN2__SDB_AV1_ERR_INT_EN__SHIFT 0xb #define UVD_SUVD_INT_EN2__SMPA_FUNC_INT_EN_MASK 0x0000001FL #define UVD_SUVD_INT_EN2__SMPA_ERR_INT_EN_MASK 0x00000020L +#define UVD_SUVD_INT_EN2__SDB_AV1_FUNC_INT_EN_MASK 0x000007C0L +#define UVD_SUVD_INT_EN2__SDB_AV1_ERR_INT_EN_MASK 0x00000800L //UVD_SUVD_INT_ACK2 #define UVD_SUVD_INT_ACK2__SMPA_FUNC_INT_ACK__SHIFT 0x0 #define UVD_SUVD_INT_ACK2__SMPA_ERR_INT_ACK__SHIFT 0x5 +#define UVD_SUVD_INT_ACK2__SDB_AV1_FUNC_INT_ACK__SHIFT 0x6 +#define UVD_SUVD_INT_ACK2__SDB_AV1_ERR_INT_ACK__SHIFT 0xb #define UVD_SUVD_INT_ACK2__SMPA_FUNC_INT_ACK_MASK 0x0000001FL #define UVD_SUVD_INT_ACK2__SMPA_ERR_INT_ACK_MASK 0x00000020L +#define UVD_SUVD_INT_ACK2__SDB_AV1_FUNC_INT_ACK_MASK 0x000007C0L +#define UVD_SUVD_INT_ACK2__SDB_AV1_ERR_INT_ACK_MASK 0x00000800L // addressBlock: uvd0_ecpudec diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 63f945f9f331..8dc5abb6931e 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -479,17 +479,6 @@ static int smu_late_init(void *handle) return ret; } - /* - * Set initialized values (get from vbios) to dpm tables context such as - * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each - * type of clks. - */ - ret = smu_set_default_dpm_table(smu); - if (ret) { - dev_err(adev->dev, "Failed to setup default dpm clock tables!\n"); - return ret; - } - ret = smu_populate_umd_state_clk(smu); if (ret) { dev_err(adev->dev, "Failed to populate UMD state clocks!\n"); @@ -984,6 +973,17 @@ static int smu_smc_hw_setup(struct smu_context *smu) return ret; } + /* + * Set initialized values (get from vbios) to dpm tables context such as + * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each + * type of clks. + */ + ret = smu_set_default_dpm_table(smu); + if (ret) { + dev_err(adev->dev, "Failed to setup default dpm clock tables!\n"); + return ret; + } + ret = smu_notify_display_change(smu); if (ret) return ret; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index 9ee8cf8267c8..43f7adff6cb7 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -563,6 +563,8 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, struct smu10_hwmgr *data = hwmgr->backend; uint32_t min_sclk = hwmgr->display_config->min_core_set_clock; uint32_t min_mclk = hwmgr->display_config->min_mem_set_clock/100; + uint32_t index_fclk = data->clock_vol_info.vdd_dep_on_fclk->count - 1; + uint32_t index_socclk = data->clock_vol_info.vdd_dep_on_socclk->count - 1; if (hwmgr->smu_version < 0x1E3700) { pr_info("smu firmware version too old, can not set dpm level\n"); @@ -676,13 +678,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, hwmgr->display_config->num_display > 3 ? - SMU10_UMD_PSTATE_PEAK_FCLK : + data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk : min_mclk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinSocclkByFreq, - SMU10_UMD_PSTATE_MIN_SOCCLK, + data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, @@ -695,11 +697,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxFclkByFreq, - SMU10_UMD_PSTATE_PEAK_FCLK, + data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxSocclkByFreq, - SMU10_UMD_PSTATE_PEAK_SOCCLK, + data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 3d5eae956a23..b1547a83e721 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -2265,8 +2265,6 @@ static void navi10_fill_i2c_req(SwI2cRequest_t *req, bool write, { int i; - BUG_ON(numbytes > MAX_SW_I2C_COMMANDS); - req->I2CcontrollerPort = 0; req->I2CSpeed = 2; req->SlaveAddress = address; @@ -2304,6 +2302,12 @@ static int navi10_i2c_read_data(struct i2c_adapter *control, struct smu_table_context *smu_table = &adev->smu.smu_table; struct smu_table *table = &smu_table->driver_table; + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); navi10_fill_i2c_req(&req, false, address, numbytes, data); @@ -2340,6 +2344,12 @@ static int navi10_i2c_write_data(struct i2c_adapter *control, SwI2cRequest_t req; struct amdgpu_device *adev = to_amdgpu_device(control); + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); navi10_fill_i2c_req(&req, true, address, numbytes, data); diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index dbb676c482fd..15263cf210d5 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -232,14 +232,16 @@ static int renoir_get_profiling_clk_mask(struct smu_context *smu, *sclk_mask = 0; } else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) { if (mclk_mask) - *mclk_mask = 0; + /* mclk levels are in reverse order */ + *mclk_mask = NUM_MEMCLK_DPM_LEVELS - 1; } else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) { if(sclk_mask) /* The sclk as gfxclk and has three level about max/min/current */ *sclk_mask = 3 - 1; if(mclk_mask) - *mclk_mask = NUM_MEMCLK_DPM_LEVELS - 1; + /* mclk levels are in reverse order */ + *mclk_mask = 0; if(soc_mask) *soc_mask = NUM_SOCCLK_DPM_LEVELS - 1; @@ -333,7 +335,7 @@ static int renoir_get_dpm_ultimate_freq(struct smu_context *smu, case SMU_UCLK: case SMU_FCLK: case SMU_MCLK: - ret = renoir_get_dpm_clk_limited(smu, clk_type, 0, min); + ret = renoir_get_dpm_clk_limited(smu, clk_type, NUM_MEMCLK_DPM_LEVELS - 1, min); if (ret) goto failed; break; diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c index 61f4ddae262d..ace682fde22f 100644 --- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c @@ -2445,8 +2445,6 @@ static void sienna_cichlid_fill_i2c_req(SwI2cRequest_t *req, bool write, { int i; - BUG_ON(numbytes > MAX_SW_I2C_COMMANDS); - req->I2CcontrollerPort = 0; req->I2CSpeed = 2; req->SlaveAddress = address; @@ -2484,6 +2482,12 @@ static int sienna_cichlid_i2c_read_data(struct i2c_adapter *control, struct smu_table_context *smu_table = &adev->smu.smu_table; struct smu_table *table = &smu_table->driver_table; + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); sienna_cichlid_fill_i2c_req(&req, false, address, numbytes, data); @@ -2520,6 +2524,12 @@ static int sienna_cichlid_i2c_write_data(struct i2c_adapter *control, SwI2cRequest_t req; struct amdgpu_device *adev = to_amdgpu_device(control); + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); sienna_cichlid_fill_i2c_req(&req, true, address, numbytes, data); diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 8fa9b31a2484..f6d7e33c7099 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -368,6 +368,7 @@ void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu) static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, struct intel_vgpu_creation_params *param) { + struct drm_i915_private *dev_priv = gvt->gt->i915; struct intel_vgpu *vgpu; int ret; @@ -436,7 +437,10 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_clean_sched_policy; - ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); + if (IS_BROADWELL(dev_priv)) + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); + else + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index f127e633f7ca..397c313a8b69 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -118,11 +118,11 @@ static struct dev_pm_domain pm_domain = { struct drm_i915_private *mock_gem_device(void) { - struct drm_i915_private *i915; - struct pci_dev *pdev; #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - struct dev_iommu iommu; + static struct dev_iommu fake_iommu = { .priv = (void *)-1 }; #endif + struct drm_i915_private *i915; + struct pci_dev *pdev; int err; pdev = kzalloc(sizeof(*pdev), GFP_KERNEL); @@ -141,10 +141,8 @@ struct drm_i915_private *mock_gem_device(void) dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - /* HACK HACK HACK to disable iommu for the fake device; force identity mapping */ - memset(&iommu, 0, sizeof(iommu)); - iommu.priv = (void *)-1; - pdev->dev.iommu = &iommu; + /* HACK to disable iommu for the fake device; force identity mapping */ + pdev->dev.iommu = &fake_iommu; #endif pci_set_drvdata(pdev, i915); diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index b1bb542d3115..e5fae57fffbd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -176,6 +176,8 @@ void nouveau_mem_del(struct ttm_mem_reg *reg) { struct nouveau_mem *mem = nouveau_mem(reg); + if (!mem) + return; nouveau_mem_fini(mem); kfree(reg->mm_node); reg->mm_node = NULL; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 9f4ac2672cf2..dcb70677d0ac 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -3149,6 +3149,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x168: device->chip = &nv168_chipset; break; default: nvdev_error(device, "unknown chipset (%08x)\n", boot0); + ret = -ENODEV; goto done; } diff --git a/drivers/gpu/drm/sun4i/sun8i_csc.h b/drivers/gpu/drm/sun4i/sun8i_csc.h index f42441b1b14d..a55a38ad849c 100644 --- a/drivers/gpu/drm/sun4i/sun8i_csc.h +++ b/drivers/gpu/drm/sun4i/sun8i_csc.h @@ -12,7 +12,7 @@ struct sun8i_mixer; /* VI channel CSC units offsets */ #define CCSC00_OFFSET 0xAA050 -#define CCSC01_OFFSET 0xFA000 +#define CCSC01_OFFSET 0xFA050 #define CCSC10_OFFSET 0xA0000 #define CCSC11_OFFSET 0xF0000 diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c index cc4fb916318f..c3304028e3dc 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.c +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c @@ -307,7 +307,7 @@ static struct regmap_config sun8i_mixer_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = 0xbfffc, /* guessed */ + .max_register = 0xffffc, /* guessed */ }; static int sun8i_mixer_of_get_id(struct device_node *node) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 15a11cd4de25..6339c6f0f571 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1117,6 +1117,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *hdmi) card->num_links = 1; card->name = "vc4-hdmi"; card->dev = dev; + card->owner = THIS_MODULE; /* * Be careful, snd_soc_register_card() calls dev_set_drvdata() and diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index 4a76fc7114ad..f8bdd4ea294a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -55,7 +55,7 @@ static int vmw_gmrid_man_get_node(struct ttm_mem_type_manager *man, id = ida_alloc_max(&gman->gmr_ida, gman->max_gmr_ids - 1, GFP_KERNEL); if (id < 0) - return (id != -ENOMEM ? 0 : id); + return id; spin_lock(&gman->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c index b7c816ba7166..c8b9335bccd8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c @@ -95,7 +95,7 @@ found_unlock: mem->start = node->start; } - return 0; + return ret; } diff --git a/drivers/i2c/busses/i2c-cpm.c b/drivers/i2c/busses/i2c-cpm.c index 1213e1932ccb..24d584a1c9a7 100644 --- a/drivers/i2c/busses/i2c-cpm.c +++ b/drivers/i2c/busses/i2c-cpm.c @@ -65,6 +65,9 @@ struct i2c_ram { char res1[4]; /* Reserved */ ushort rpbase; /* Relocation pointer */ char res2[2]; /* Reserved */ + /* The following elements are only for CPM2 */ + char res3[4]; /* Reserved */ + uint sdmatmp; /* Internal */ }; #define I2COM_START 0x80 diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index ebb4c0b03057..bffca729e1c7 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1917,6 +1917,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) pci_set_drvdata(dev, priv); + dev_pm_set_driver_flags(&dev->dev, DPM_FLAG_NO_DIRECT_COMPLETE); pm_runtime_set_autosuspend_delay(&dev->dev, 1000); pm_runtime_use_autosuspend(&dev->dev); pm_runtime_put_autosuspend(&dev->dev); diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c index c5dec572fc48..ef73a42577cc 100644 --- a/drivers/i2c/busses/i2c-meson.c +++ b/drivers/i2c/busses/i2c-meson.c @@ -5,6 +5,7 @@ * Copyright (C) 2014 Beniamino Galvani <b.galvani@gmail.com> */ +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/completion.h> #include <linux/i2c.h> @@ -33,12 +34,17 @@ #define REG_CTRL_ACK_IGNORE BIT(1) #define REG_CTRL_STATUS BIT(2) #define REG_CTRL_ERROR BIT(3) -#define REG_CTRL_CLKDIV_SHIFT 12 -#define REG_CTRL_CLKDIV_MASK GENMASK(21, 12) -#define REG_CTRL_CLKDIVEXT_SHIFT 28 -#define REG_CTRL_CLKDIVEXT_MASK GENMASK(29, 28) +#define REG_CTRL_CLKDIV GENMASK(21, 12) +#define REG_CTRL_CLKDIVEXT GENMASK(29, 28) + +#define REG_SLV_ADDR GENMASK(7, 0) +#define REG_SLV_SDA_FILTER GENMASK(10, 8) +#define REG_SLV_SCL_FILTER GENMASK(13, 11) +#define REG_SLV_SCL_LOW GENMASK(27, 16) +#define REG_SLV_SCL_LOW_EN BIT(28) #define I2C_TIMEOUT_MS 500 +#define FILTER_DELAY 15 enum { TOKEN_END = 0, @@ -133,19 +139,24 @@ static void meson_i2c_set_clk_div(struct meson_i2c *i2c, unsigned int freq) unsigned long clk_rate = clk_get_rate(i2c->clk); unsigned int div; - div = DIV_ROUND_UP(clk_rate, freq * i2c->data->div_factor); + div = DIV_ROUND_UP(clk_rate, freq); + div -= FILTER_DELAY; + div = DIV_ROUND_UP(div, i2c->data->div_factor); /* clock divider has 12 bits */ - if (div >= (1 << 12)) { + if (div > GENMASK(11, 0)) { dev_err(i2c->dev, "requested bus frequency too low\n"); - div = (1 << 12) - 1; + div = GENMASK(11, 0); } - meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIV_MASK, - (div & GENMASK(9, 0)) << REG_CTRL_CLKDIV_SHIFT); + meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIV, + FIELD_PREP(REG_CTRL_CLKDIV, div & GENMASK(9, 0))); + + meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIVEXT, + FIELD_PREP(REG_CTRL_CLKDIVEXT, div >> 10)); - meson_i2c_set_mask(i2c, REG_CTRL, REG_CTRL_CLKDIVEXT_MASK, - (div >> 10) << REG_CTRL_CLKDIVEXT_SHIFT); + /* Disable HIGH/LOW mode */ + meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, REG_SLV_SCL_LOW_EN, 0); dev_dbg(i2c->dev, "%s: clk %lu, freq %u, div %u\n", __func__, clk_rate, freq, div); @@ -280,7 +291,10 @@ static void meson_i2c_do_start(struct meson_i2c *i2c, struct i2c_msg *msg) token = (msg->flags & I2C_M_RD) ? TOKEN_SLAVE_ADDR_READ : TOKEN_SLAVE_ADDR_WRITE; - writel(msg->addr << 1, i2c->regs + REG_SLAVE_ADDR); + + meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, REG_SLV_ADDR, + FIELD_PREP(REG_SLV_ADDR, msg->addr << 1)); + meson_i2c_add_token(i2c, TOKEN_START); meson_i2c_add_token(i2c, token); } @@ -357,16 +371,12 @@ static int meson_i2c_xfer_messages(struct i2c_adapter *adap, struct meson_i2c *i2c = adap->algo_data; int i, ret = 0; - clk_enable(i2c->clk); - for (i = 0; i < num; i++) { ret = meson_i2c_xfer_msg(i2c, msgs + i, i == num - 1, atomic); if (ret) break; } - clk_disable(i2c->clk); - return ret ?: i; } @@ -435,7 +445,7 @@ static int meson_i2c_probe(struct platform_device *pdev) return ret; } - ret = clk_prepare(i2c->clk); + ret = clk_prepare_enable(i2c->clk); if (ret < 0) { dev_err(&pdev->dev, "can't prepare clock\n"); return ret; @@ -457,10 +467,14 @@ static int meson_i2c_probe(struct platform_device *pdev) ret = i2c_add_adapter(&i2c->adap); if (ret < 0) { - clk_unprepare(i2c->clk); + clk_disable_unprepare(i2c->clk); return ret; } + /* Disable filtering */ + meson_i2c_set_mask(i2c, REG_SLAVE_ADDR, + REG_SLV_SDA_FILTER | REG_SLV_SCL_FILTER, 0); + meson_i2c_set_clk_div(i2c, timings.bus_freq_hz); return 0; @@ -471,7 +485,7 @@ static int meson_i2c_remove(struct platform_device *pdev) struct meson_i2c *i2c = platform_get_drvdata(pdev); i2c_del_adapter(&i2c->adap); - clk_unprepare(i2c->clk); + clk_disable_unprepare(i2c->clk); return 0; } diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c index dfcf04e1967f..2ad166355ec9 100644 --- a/drivers/i2c/busses/i2c-npcm7xx.c +++ b/drivers/i2c/busses/i2c-npcm7xx.c @@ -2163,6 +2163,15 @@ static int npcm_i2c_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, if (bus->cmd_err == -EAGAIN) ret = i2c_recover_bus(adap); + /* + * After any type of error, check if LAST bit is still set, + * due to a HW issue. + * It cannot be cleared without resetting the module. + */ + if (bus->cmd_err && + (NPCM_I2CRXF_CTL_LAST_PEC & ioread8(bus->reg + NPCM_I2CRXF_CTL))) + npcm_i2c_reset(bus); + #if IS_ENABLED(CONFIG_I2C_SLAVE) /* reenable slave if it was enabled */ if (bus->slave) diff --git a/drivers/i2c/busses/i2c-owl.c b/drivers/i2c/busses/i2c-owl.c index 672f1f239bd6..a163b8f308c1 100644 --- a/drivers/i2c/busses/i2c-owl.c +++ b/drivers/i2c/busses/i2c-owl.c @@ -176,6 +176,9 @@ static irqreturn_t owl_i2c_interrupt(int irq, void *_dev) fifostat = readl(i2c_dev->base + OWL_I2C_REG_FIFOSTAT); if (fifostat & OWL_I2C_FIFOSTAT_RNB) { i2c_dev->err = -ENXIO; + /* Clear NACK error bit by writing "1" */ + owl_i2c_update_reg(i2c_dev->base + OWL_I2C_REG_FIFOSTAT, + OWL_I2C_FIFOSTAT_RNB, true); goto stop; } @@ -183,6 +186,9 @@ static irqreturn_t owl_i2c_interrupt(int irq, void *_dev) stat = readl(i2c_dev->base + OWL_I2C_REG_STAT); if (stat & OWL_I2C_STAT_BEB) { i2c_dev->err = -EIO; + /* Clear BUS error bit by writing "1" */ + owl_i2c_update_reg(i2c_dev->base + OWL_I2C_REG_STAT, + OWL_I2C_STAT_BEB, true); goto stop; } diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index 8dce06e9e69c..766c73333604 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -177,12 +177,12 @@ static const struct iio_chan_spec ad7124_channel_template = { static struct ad7124_chip_info ad7124_chip_info_tbl[] = { [ID_AD7124_4] = { - .name = "ad7127-4", + .name = "ad7124-4", .chip_id = CHIPID_AD7124_4, .num_inputs = 8, }, [ID_AD7124_8] = { - .name = "ad7127-8", + .name = "ad7124-8", .chip_id = CHIPID_AD7124_8, .num_inputs = 16, }, diff --git a/drivers/iio/adc/qcom-spmi-adc5.c b/drivers/iio/adc/qcom-spmi-adc5.c index b4b73c9920b4..c10aa28be70a 100644 --- a/drivers/iio/adc/qcom-spmi-adc5.c +++ b/drivers/iio/adc/qcom-spmi-adc5.c @@ -982,7 +982,7 @@ static int adc5_probe(struct platform_device *pdev) static struct platform_driver adc5_driver = { .driver = { - .name = "qcom-spmi-adc5.c", + .name = "qcom-spmi-adc5", .of_match_table = adc5_match_table, }, .probe = adc5_probe, diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c index ffad73bb40ff..5a76611e684a 100644 --- a/drivers/infiniband/core/cache.c +++ b/drivers/infiniband/core/cache.c @@ -1320,9 +1320,10 @@ struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr) } EXPORT_SYMBOL(rdma_read_gid_attr_ndev_rcu); -static int get_lower_dev_vlan(struct net_device *lower_dev, void *data) +static int get_lower_dev_vlan(struct net_device *lower_dev, + struct netdev_nested_priv *priv) { - u16 *vlan_id = data; + u16 *vlan_id = (u16 *)priv->data; if (is_vlan_dev(lower_dev)) *vlan_id = vlan_dev_vlan_id(lower_dev); @@ -1348,6 +1349,9 @@ static int get_lower_dev_vlan(struct net_device *lower_dev, void *data) int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr, u16 *vlan_id, u8 *smac) { + struct netdev_nested_priv priv = { + .data = (void *)vlan_id, + }; struct net_device *ndev; rcu_read_lock(); @@ -1368,7 +1372,7 @@ int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr, * the lower vlan device for this gid entry. */ netdev_walk_all_lower_dev_rcu(attr->ndev, - get_lower_dev_vlan, vlan_id); + get_lower_dev_vlan, &priv); } } rcu_read_unlock(); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 7f0e91e92968..5888311b2119 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2865,9 +2865,10 @@ struct iboe_prio_tc_map { bool found; }; -static int get_lower_vlan_dev_tc(struct net_device *dev, void *data) +static int get_lower_vlan_dev_tc(struct net_device *dev, + struct netdev_nested_priv *priv) { - struct iboe_prio_tc_map *map = data; + struct iboe_prio_tc_map *map = (struct iboe_prio_tc_map *)priv->data; if (is_vlan_dev(dev)) map->output_tc = get_vlan_ndev_tc(dev, map->input_prio); @@ -2886,16 +2887,18 @@ static int iboe_tos_to_sl(struct net_device *ndev, int tos) { struct iboe_prio_tc_map prio_tc_map = {}; int prio = rt_tos2priority(tos); + struct netdev_nested_priv priv; /* If VLAN device, get it directly from the VLAN netdev */ if (is_vlan_dev(ndev)) return get_vlan_ndev_tc(ndev, prio); prio_tc_map.input_prio = prio; + priv.data = (void *)&prio_tc_map; rcu_read_lock(); netdev_walk_all_lower_dev_rcu(ndev, get_lower_vlan_dev_tc, - &prio_tc_map); + &priv); rcu_read_unlock(); /* If map is found from lower device, use it; Otherwise * continue with the current netdevice to get priority to tc map. diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index c36b4d2b61e0..23ee65a9185f 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -1285,6 +1285,8 @@ static void disable_device(struct ib_device *device) remove_client_context(device, cid); } + ib_cq_pool_destroy(device); + /* Pairs with refcount_set in enable_device */ ib_device_put(device); wait_for_completion(&device->unreg_completion); @@ -1328,6 +1330,8 @@ static int enable_device_and_get(struct ib_device *device) goto out; } + ib_cq_pool_init(device); + down_read(&clients_rwsem); xa_for_each_marked (&clients, index, client, CLIENT_REGISTERED) { ret = add_client_context(device, client); @@ -1400,7 +1404,6 @@ int ib_register_device(struct ib_device *device, const char *name) goto dev_cleanup; } - ib_cq_pool_init(device); ret = enable_device_and_get(device); dev_set_uevent_suppress(&device->dev, false); /* Mark for userspace that device is ready */ @@ -1455,7 +1458,6 @@ static void __ib_unregister_device(struct ib_device *ib_dev) goto out; disable_device(ib_dev); - ib_cq_pool_destroy(ib_dev); /* Expedite removing unregistered pointers from the hash table */ free_netdevs(ib_dev); diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c index 2860def84f4d..6b8364bb032d 100644 --- a/drivers/infiniband/core/roce_gid_mgmt.c +++ b/drivers/infiniband/core/roce_gid_mgmt.c @@ -531,10 +531,11 @@ struct upper_list { struct net_device *upper; }; -static int netdev_upper_walk(struct net_device *upper, void *data) +static int netdev_upper_walk(struct net_device *upper, + struct netdev_nested_priv *priv) { struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC); - struct list_head *upper_list = data; + struct list_head *upper_list = (struct list_head *)priv->data; if (!entry) return 0; @@ -553,12 +554,14 @@ static void handle_netdev_upper(struct ib_device *ib_dev, u8 port, struct net_device *ndev)) { struct net_device *ndev = cookie; + struct netdev_nested_priv priv; struct upper_list *upper_iter; struct upper_list *upper_temp; LIST_HEAD(upper_list); + priv.data = &upper_list; rcu_read_lock(); - netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &upper_list); + netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &priv); rcu_read_unlock(); handle_netdev(ib_dev, port, ndev); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index ab75b7f745d4..f772fe8c5b66 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -342,9 +342,10 @@ struct ipoib_walk_data { struct net_device *result; }; -static int ipoib_upper_walk(struct net_device *upper, void *_data) +static int ipoib_upper_walk(struct net_device *upper, + struct netdev_nested_priv *priv) { - struct ipoib_walk_data *data = _data; + struct ipoib_walk_data *data = (struct ipoib_walk_data *)priv->data; int ret = 0; if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) { @@ -368,10 +369,12 @@ static int ipoib_upper_walk(struct net_device *upper, void *_data) static struct net_device *ipoib_get_net_dev_match_addr( const struct sockaddr *addr, struct net_device *dev) { + struct netdev_nested_priv priv; struct ipoib_walk_data data = { .addr = addr, }; + priv.data = (void *)&data; rcu_read_lock(); if (ipoib_is_dev_match_addr_rcu(addr, dev)) { dev_hold(dev); @@ -379,7 +382,7 @@ static struct net_device *ipoib_get_net_dev_match_addr( goto out; } - netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &data); + netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &priv); out: rcu_read_unlock(); return data.result; diff --git a/drivers/input/mouse/trackpoint.c b/drivers/input/mouse/trackpoint.c index 854d5e758724..ef2fa0905208 100644 --- a/drivers/input/mouse/trackpoint.c +++ b/drivers/input/mouse/trackpoint.c @@ -282,6 +282,8 @@ static int trackpoint_start_protocol(struct psmouse *psmouse, case TP_VARIANT_ALPS: case TP_VARIANT_ELAN: case TP_VARIANT_NXP: + case TP_VARIANT_JYT_SYNAPTICS: + case TP_VARIANT_SYNAPTICS: if (variant_id) *variant_id = param[0]; if (firmware_id) diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 37fb9aa88f9c..a4c9b9652560 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -721,6 +721,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nopnp_table[] = { DMI_MATCH(DMI_BOARD_VENDOR, "MICRO-STAR INTERNATIONAL CO., LTD"), }, }, + { + /* Acer Aspire 5 A515 */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "Grumpy_PK"), + DMI_MATCH(DMI_BOARD_VENDOR, "PK"), + }, + }, { } }; diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index 445a08d23fed..1ba6b4cc56e8 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -1104,25 +1104,6 @@ static int __init add_early_maps(void) } /* - * Reads the device exclusion range from ACPI and initializes the IOMMU with - * it - */ -static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m) -{ - if (!(m->flags & IVMD_FLAG_EXCL_RANGE)) - return; - - /* - * Treat per-device exclusion ranges as r/w unity-mapped regions - * since some buggy BIOSes might lead to the overwritten exclusion - * range (exclusion_start and exclusion_length members). This - * happens when there are multiple exclusion ranges (IVMD entries) - * defined in ACPI table. - */ - m->flags = (IVMD_FLAG_IW | IVMD_FLAG_IR | IVMD_FLAG_UNITY_MAP); -} - -/* * Takes a pointer to an AMD IOMMU entry in the ACPI table and * initializes the hardware and our data structures with it. */ @@ -2073,30 +2054,6 @@ static void __init free_unity_maps(void) } } -/* called when we find an exclusion range definition in ACPI */ -static int __init init_exclusion_range(struct ivmd_header *m) -{ - int i; - - switch (m->type) { - case ACPI_IVMD_TYPE: - set_device_exclusion_range(m->devid, m); - break; - case ACPI_IVMD_TYPE_ALL: - for (i = 0; i <= amd_iommu_last_bdf; ++i) - set_device_exclusion_range(i, m); - break; - case ACPI_IVMD_TYPE_RANGE: - for (i = m->devid; i <= m->aux; ++i) - set_device_exclusion_range(i, m); - break; - default: - break; - } - - return 0; -} - /* called for unity map ACPI definition */ static int __init init_unity_map_range(struct ivmd_header *m) { @@ -2107,9 +2064,6 @@ static int __init init_unity_map_range(struct ivmd_header *m) if (e == NULL) return -ENOMEM; - if (m->flags & IVMD_FLAG_EXCL_RANGE) - init_exclusion_range(m); - switch (m->type) { default: kfree(e); @@ -2133,6 +2087,16 @@ static int __init init_unity_map_range(struct ivmd_header *m) e->address_end = e->address_start + PAGE_ALIGN(m->range_length); e->prot = m->flags >> 1; + /* + * Treat per-device exclusion ranges as r/w unity-mapped regions + * since some buggy BIOSes might lead to the overwritten exclusion + * range (exclusion_start and exclusion_length members). This + * happens when there are multiple exclusion ranges (IVMD entries) + * defined in ACPI table. + */ + if (m->flags & IVMD_FLAG_EXCL_RANGE) + e->prot = (IVMD_FLAG_IW | IVMD_FLAG_IR) >> 1; + DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x" " range_start: %016llx range_end: %016llx flags: %x\n", s, PCI_BUS_NUM(e->devid_start), PCI_SLOT(e->devid_start), diff --git a/drivers/iommu/exynos-iommu.c b/drivers/iommu/exynos-iommu.c index bad3c0ce10cb..de324b4eedfe 100644 --- a/drivers/iommu/exynos-iommu.c +++ b/drivers/iommu/exynos-iommu.c @@ -1295,13 +1295,17 @@ static int exynos_iommu_of_xlate(struct device *dev, return -ENODEV; data = platform_get_drvdata(sysmmu); - if (!data) + if (!data) { + put_device(&sysmmu->dev); return -ENODEV; + } if (!owner) { owner = kzalloc(sizeof(*owner), GFP_KERNEL); - if (!owner) + if (!owner) { + put_device(&sysmmu->dev); return -ENOMEM; + } INIT_LIST_HEAD(&owner->controllers); mutex_init(&owner->rpm_lock); diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 87b17bac04c2..2239c211178b 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2664,7 +2664,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, } /* Setup the PASID entry for requests without PASID: */ - spin_lock(&iommu->lock); + spin_lock_irqsave(&iommu->lock, flags); if (hw_pass_through && domain_type_is_si(domain)) ret = intel_pasid_setup_pass_through(iommu, domain, dev, PASID_RID2PASID); @@ -2674,7 +2674,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, else ret = intel_pasid_setup_second_level(iommu, domain, dev, PASID_RID2PASID); - spin_unlock(&iommu->lock); + spin_unlock_irqrestore(&iommu->lock, flags); if (ret) { dev_err(dev, "Setup RID2PASID failed\n"); dmar_remove_one_dev_info(dev); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 4a40df8af7d3..6ed05ca65a0f 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1724,23 +1724,6 @@ out: return ret; } -static void dm_queue_split(struct mapped_device *md, struct dm_target *ti, struct bio **bio) -{ - unsigned len, sector_count; - - sector_count = bio_sectors(*bio); - len = min_t(sector_t, max_io_len((*bio)->bi_iter.bi_sector, ti), sector_count); - - if (sector_count > len) { - struct bio *split = bio_split(*bio, len, GFP_NOIO, &md->queue->bio_split); - - bio_chain(split, *bio); - trace_block_split(md->queue, split, (*bio)->bi_iter.bi_sector); - submit_bio_noacct(*bio); - *bio = split; - } -} - static blk_qc_t dm_process_bio(struct mapped_device *md, struct dm_table *map, struct bio *bio) { @@ -1761,21 +1744,21 @@ static blk_qc_t dm_process_bio(struct mapped_device *md, } /* - * If in ->queue_bio we need to use blk_queue_split(), otherwise + * If in ->submit_bio we need to use blk_queue_split(), otherwise * queue_limits for abnormal requests (e.g. discard, writesame, etc) * won't be imposed. + * If called from dm_wq_work() for deferred bio processing, bio + * was already handled by following code with previous ->submit_bio. */ if (current->bio_list) { if (is_abnormal_io(bio)) blk_queue_split(&bio); - else - dm_queue_split(md, ti, &bio); + /* regular IO is split by __split_and_process_bio */ } if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED) return __process_bio(md, map, bio, ti); - else - return __split_and_process_bio(md, map, bio); + return __split_and_process_bio(md, map, bio); } static blk_qc_t dm_submit_bio(struct bio *bio) diff --git a/drivers/media/cec/core/cec-adap.c b/drivers/media/cec/core/cec-adap.c index 4efe8014445e..926d65db6d3e 100644 --- a/drivers/media/cec/core/cec-adap.c +++ b/drivers/media/cec/core/cec-adap.c @@ -1199,7 +1199,7 @@ void cec_received_msg_ts(struct cec_adapter *adap, /* Cancel the pending timeout work */ if (!cancel_delayed_work(&data->work)) { mutex_unlock(&adap->lock); - flush_scheduled_work(); + cancel_delayed_work_sync(&data->work); mutex_lock(&adap->lock); } /* diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index f544d3393e9d..4eab6d81cce1 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -721,39 +721,14 @@ int vb2_verify_memory_type(struct vb2_queue *q, } EXPORT_SYMBOL(vb2_verify_memory_type); -static void set_queue_consistency(struct vb2_queue *q, bool consistent_mem) -{ - q->dma_attrs &= ~DMA_ATTR_NON_CONSISTENT; - - if (!vb2_queue_allows_cache_hints(q)) - return; - if (!consistent_mem) - q->dma_attrs |= DMA_ATTR_NON_CONSISTENT; -} - -static bool verify_consistency_attr(struct vb2_queue *q, bool consistent_mem) -{ - bool queue_is_consistent = !(q->dma_attrs & DMA_ATTR_NON_CONSISTENT); - - if (consistent_mem != queue_is_consistent) { - dprintk(q, 1, "memory consistency model mismatch\n"); - return false; - } - return true; -} - int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count) + unsigned int *count) { unsigned int num_buffers, allocated_buffers, num_planes = 0; unsigned plane_sizes[VB2_MAX_PLANES] = { }; - bool consistent_mem = true; unsigned int i; int ret; - if (flags & V4L2_FLAG_MEMORY_NON_CONSISTENT) - consistent_mem = false; - if (q->streaming) { dprintk(q, 1, "streaming active\n"); return -EBUSY; @@ -765,8 +740,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, } if (*count == 0 || q->num_buffers != 0 || - (q->memory != VB2_MEMORY_UNKNOWN && q->memory != memory) || - !verify_consistency_attr(q, consistent_mem)) { + (q->memory != VB2_MEMORY_UNKNOWN && q->memory != memory)) { /* * We already have buffers allocated, so first check if they * are not in use and can be freed. @@ -803,7 +777,6 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, num_buffers = min_t(unsigned int, num_buffers, VB2_MAX_FRAME); memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); q->memory = memory; - set_queue_consistency(q, consistent_mem); /* * Ask the driver how many buffers and planes per buffer it requires. @@ -888,18 +861,14 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, EXPORT_SYMBOL_GPL(vb2_core_reqbufs); int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count, + unsigned int *count, unsigned int requested_planes, const unsigned int requested_sizes[]) { unsigned int num_planes = 0, num_buffers, allocated_buffers; unsigned plane_sizes[VB2_MAX_PLANES] = { }; - bool consistent_mem = true; int ret; - if (flags & V4L2_FLAG_MEMORY_NON_CONSISTENT) - consistent_mem = false; - if (q->num_buffers == VB2_MAX_FRAME) { dprintk(q, 1, "maximum number of buffers already allocated\n"); return -ENOBUFS; @@ -912,15 +881,12 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, } memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); q->memory = memory; - set_queue_consistency(q, consistent_mem); q->waiting_for_buffers = !q->is_output; } else { if (q->memory != memory) { dprintk(q, 1, "memory model mismatch\n"); return -EINVAL; } - if (!verify_consistency_attr(q, consistent_mem)) - return -EINVAL; } num_buffers = min(*count, VB2_MAX_FRAME - q->num_buffers); @@ -2581,7 +2547,7 @@ static int __vb2_init_fileio(struct vb2_queue *q, int read) fileio->memory = VB2_MEMORY_MMAP; fileio->type = q->type; q->fileio = fileio; - ret = vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count); + ret = vb2_core_reqbufs(q, fileio->memory, &fileio->count); if (ret) goto err_kfree; @@ -2638,7 +2604,7 @@ static int __vb2_init_fileio(struct vb2_queue *q, int read) err_reqbufs: fileio->count = 0; - vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count); + vb2_core_reqbufs(q, fileio->memory, &fileio->count); err_kfree: q->fileio = NULL; @@ -2658,7 +2624,7 @@ static int __vb2_cleanup_fileio(struct vb2_queue *q) vb2_core_streamoff(q, q->type); q->fileio = NULL; fileio->count = 0; - vb2_core_reqbufs(q, fileio->memory, 0, &fileio->count); + vb2_core_reqbufs(q, fileio->memory, &fileio->count); kfree(fileio); dprintk(q, 3, "file io emulator closed\n"); } diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c index ec3446cc45b8..7b1b86ec942d 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c @@ -42,11 +42,6 @@ struct vb2_dc_buf { struct dma_buf_attachment *db_attach; }; -static inline bool vb2_dc_buffer_consistent(unsigned long attr) -{ - return !(attr & DMA_ATTR_NON_CONSISTENT); -} - /*********************************************/ /* scatterlist table functions */ /*********************************************/ @@ -341,13 +336,6 @@ static int vb2_dc_dmabuf_ops_begin_cpu_access(struct dma_buf *dbuf, enum dma_data_direction direction) { - struct vb2_dc_buf *buf = dbuf->priv; - struct sg_table *sgt = buf->dma_sgt; - - if (vb2_dc_buffer_consistent(buf->attrs)) - return 0; - - dma_sync_sg_for_cpu(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir); return 0; } @@ -355,13 +343,6 @@ static int vb2_dc_dmabuf_ops_end_cpu_access(struct dma_buf *dbuf, enum dma_data_direction direction) { - struct vb2_dc_buf *buf = dbuf->priv; - struct sg_table *sgt = buf->dma_sgt; - - if (vb2_dc_buffer_consistent(buf->attrs)) - return 0; - - dma_sync_sg_for_device(buf->dev, sgt->sgl, sgt->nents, buf->dma_dir); return 0; } diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c index 0a40e00f0d7e..a86fce5d8ea8 100644 --- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c +++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c @@ -123,8 +123,7 @@ static void *vb2_dma_sg_alloc(struct device *dev, unsigned long dma_attrs, /* * NOTE: dma-sg allocates memory using the page allocator directly, so * there is no memory consistency guarantee, hence dma-sg ignores DMA - * attributes passed from the upper layer. That means that - * V4L2_FLAG_MEMORY_NON_CONSISTENT has no effect on dma-sg buffers. + * attributes passed from the upper layer. */ buf->pages = kvmalloc_array(buf->num_pages, sizeof(struct page *), GFP_KERNEL | __GFP_ZERO); diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index 30caad27281e..cfe197df970d 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -722,22 +722,12 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps) #endif } -static void clear_consistency_attr(struct vb2_queue *q, - int memory, - unsigned int *flags) -{ - if (!q->allow_cache_hints || memory != V4L2_MEMORY_MMAP) - *flags &= ~V4L2_FLAG_MEMORY_NON_CONSISTENT; -} - int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) { int ret = vb2_verify_memory_type(q, req->memory, req->type); fill_buf_caps(q, &req->capabilities); - clear_consistency_attr(q, req->memory, &req->flags); - return ret ? ret : vb2_core_reqbufs(q, req->memory, - req->flags, &req->count); + return ret ? ret : vb2_core_reqbufs(q, req->memory, &req->count); } EXPORT_SYMBOL_GPL(vb2_reqbufs); @@ -769,7 +759,6 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) unsigned i; fill_buf_caps(q, &create->capabilities); - clear_consistency_attr(q, create->memory, &create->flags); create->index = q->num_buffers; if (create->count == 0) return ret != -EBUSY ? ret : 0; @@ -813,7 +802,6 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) if (requested_sizes[i] == 0) return -EINVAL; return ret ? ret : vb2_core_create_bufs(q, create->memory, - create->flags, &create->count, requested_planes, requested_sizes); @@ -998,12 +986,11 @@ int vb2_ioctl_reqbufs(struct file *file, void *priv, int res = vb2_verify_memory_type(vdev->queue, p->memory, p->type); fill_buf_caps(vdev->queue, &p->capabilities); - clear_consistency_attr(vdev->queue, p->memory, &p->flags); if (res) return res; if (vb2_queue_is_busy(vdev, file)) return -EBUSY; - res = vb2_core_reqbufs(vdev->queue, p->memory, p->flags, &p->count); + res = vb2_core_reqbufs(vdev->queue, p->memory, &p->count); /* If count == 0, then the owner has released all buffers and he is no longer owner of the queue. Otherwise we have a new owner. */ if (res == 0) @@ -1021,7 +1008,6 @@ int vb2_ioctl_create_bufs(struct file *file, void *priv, p->index = vdev->queue->num_buffers; fill_buf_caps(vdev->queue, &p->capabilities); - clear_consistency_attr(vdev->queue, p->memory, &p->flags); /* * If count == 0, then just check if memory and type are valid. * Any -EBUSY result from vb2_verify_memory_type can be mapped to 0. diff --git a/drivers/media/dvb-core/dvb_vb2.c b/drivers/media/dvb-core/dvb_vb2.c index 959d110407a4..6974f1731529 100644 --- a/drivers/media/dvb-core/dvb_vb2.c +++ b/drivers/media/dvb-core/dvb_vb2.c @@ -342,7 +342,7 @@ int dvb_vb2_reqbufs(struct dvb_vb2_ctx *ctx, struct dmx_requestbuffers *req) ctx->buf_siz = req->size; ctx->buf_cnt = req->count; - ret = vb2_core_reqbufs(&ctx->vb_q, VB2_MEMORY_MMAP, 0, &req->count); + ret = vb2_core_reqbufs(&ctx->vb_q, VB2_MEMORY_MMAP, &req->count); if (ret) { ctx->state = DVB_VB2_STATE_NONE; dprintk(1, "[%s] count=%d size=%d errno=%d\n", ctx->name, diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index 593bcf6c3735..a99e82ec9ab6 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -246,9 +246,6 @@ struct v4l2_format32 { * @memory: buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. - * @flags: additional buffer management attributes (ignored unless the - * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability and - * configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers32 { @@ -257,8 +254,7 @@ struct v4l2_create_buffers32 { __u32 memory; /* enum v4l2_memory */ struct v4l2_format32 format; __u32 capabilities; - __u32 flags; - __u32 reserved[6]; + __u32 reserved[7]; }; static int __bufsize_v4l2_format(struct v4l2_format32 __user *p32, u32 *size) @@ -359,8 +355,7 @@ static int get_v4l2_create32(struct v4l2_create_buffers __user *p64, { if (!access_ok(p32, sizeof(*p32)) || copy_in_user(p64, p32, - offsetof(struct v4l2_create_buffers32, format)) || - assign_in_user(&p64->flags, &p32->flags)) + offsetof(struct v4l2_create_buffers32, format))) return -EFAULT; return __get_v4l2_format32(&p64->format, &p32->format, aux_buf, aux_space); @@ -422,7 +417,6 @@ static int put_v4l2_create32(struct v4l2_create_buffers __user *p64, copy_in_user(p32, p64, offsetof(struct v4l2_create_buffers32, format)) || assign_in_user(&p32->capabilities, &p64->capabilities) || - assign_in_user(&p32->flags, &p64->flags) || copy_in_user(p32->reserved, p64->reserved, sizeof(p64->reserved))) return -EFAULT; return __put_v4l2_format32(&p64->format, &p32->format); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index f74b42280892..eeff398fbdcc 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2042,6 +2042,9 @@ static int v4l_reqbufs(const struct v4l2_ioctl_ops *ops, if (ret) return ret; + + CLEAR_AFTER_FIELD(p, capabilities); + return ops->vidioc_reqbufs(file, fh, p); } @@ -2081,7 +2084,7 @@ static int v4l_create_bufs(const struct v4l2_ioctl_ops *ops, if (ret) return ret; - CLEAR_AFTER_FIELD(create, flags); + CLEAR_AFTER_FIELD(create, capabilities); v4l_sanitize_format(&create->format); diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c index 693ee73eb291..ef03d6fafc5c 100644 --- a/drivers/memstick/core/memstick.c +++ b/drivers/memstick/core/memstick.c @@ -441,6 +441,9 @@ static void memstick_check(struct work_struct *work) } else if (host->card->stop) host->card->stop(host->card); + if (host->removing) + goto out_power_off; + card = memstick_alloc_card(host); if (!card) { @@ -545,6 +548,7 @@ EXPORT_SYMBOL(memstick_add_host); */ void memstick_remove_host(struct memstick_host *host) { + host->removing = 1; flush_workqueue(workqueue); mutex_lock(&host->lock); if (host->card) diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 6c022ef0f84d..350d0cc4ee62 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -190,7 +190,7 @@ static void mmc_queue_setup_discard(struct request_queue *q, q->limits.discard_granularity = card->pref_erase << 9; /* granularity must not be greater than max. discard */ if (card->pref_erase > max_discard) - q->limits.discard_granularity = 0; + q->limits.discard_granularity = SECTOR_SIZE; if (mmc_can_secure_erase_trim(card)) blk_queue_flag_set(QUEUE_FLAG_SECERASE, q); } diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c index 5055a7eb134a..18a850f37ddc 100644 --- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -1320,7 +1320,7 @@ static void mmc_spi_dma_free(struct mmc_spi_host *host) DMA_BIDIRECTIONAL); } #else -static inline mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; } +static inline int mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; } static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {} #endif diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c index af413805bbf1..914f5184295f 100644 --- a/drivers/mmc/host/sdhci-pci-core.c +++ b/drivers/mmc/host/sdhci-pci-core.c @@ -794,7 +794,8 @@ static int byt_emmc_probe_slot(struct sdhci_pci_slot *slot) static bool glk_broken_cqhci(struct sdhci_pci_slot *slot) { return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_GLK_EMMC && - dmi_match(DMI_BIOS_VENDOR, "LENOVO"); + (dmi_match(DMI_BIOS_VENDOR, "LENOVO") || + dmi_match(DMI_SYS_VENDOR, "IRBIS")); } static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 4e1b7deb724b..c3091e00dd5f 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -942,9 +942,10 @@ struct alb_walk_data { bool strict_match; }; -static int alb_upper_dev_walk(struct net_device *upper, void *_data) +static int alb_upper_dev_walk(struct net_device *upper, + struct netdev_nested_priv *priv) { - struct alb_walk_data *data = _data; + struct alb_walk_data *data = (struct alb_walk_data *)priv->data; bool strict_match = data->strict_match; struct bonding *bond = data->bond; struct slave *slave = data->slave; @@ -983,6 +984,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], bool strict_match) { struct bonding *bond = bond_get_bond_by_slave(slave); + struct netdev_nested_priv priv; struct alb_walk_data data = { .strict_match = strict_match, .mac_addr = mac_addr, @@ -990,6 +992,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], .bond = bond, }; + priv.data = (void *)&data; /* send untagged */ alb_send_lp_vid(slave, mac_addr, 0, 0); @@ -997,7 +1000,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[], * for that device. */ rcu_read_lock(); - netdev_walk_all_upper_dev_rcu(bond->dev, alb_upper_dev_walk, &data); + netdev_walk_all_upper_dev_rcu(bond->dev, alb_upper_dev_walk, &priv); rcu_read_unlock(); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 42ef25ec0af5..84ecbc6fa0ff 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1315,6 +1315,7 @@ static void bond_setup_by_slave(struct net_device *bond_dev, bond_dev->type = slave_dev->type; bond_dev->hard_header_len = slave_dev->hard_header_len; + bond_dev->needed_headroom = slave_dev->needed_headroom; bond_dev->addr_len = slave_dev->addr_len; memcpy(bond_dev->broadcast, slave_dev->broadcast, @@ -2510,22 +2511,26 @@ re_arm: } } -static int bond_upper_dev_walk(struct net_device *upper, void *data) +static int bond_upper_dev_walk(struct net_device *upper, + struct netdev_nested_priv *priv) { - __be32 ip = *((__be32 *)data); + __be32 ip = *(__be32 *)priv->data; return ip == bond_confirm_addr(upper, 0, ip); } static bool bond_has_this_ip(struct bonding *bond, __be32 ip) { + struct netdev_nested_priv priv = { + .data = (void *)&ip, + }; bool ret = false; if (ip == bond_confirm_addr(bond->dev, 0, ip)) return true; rcu_read_lock(); - if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &ip)) + if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &priv)) ret = true; rcu_read_unlock(); diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 8f1d15ea15d9..f5779e152377 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -932,11 +932,19 @@ static void ksz8795_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz_port_cfg(dev, port, P_PRIO_CTRL, PORT_802_1P_ENABLE, true); if (cpu_port) { + if (!p->interface && dev->compat_interface) { + dev_warn(dev->dev, + "Using legacy switch \"phy-mode\" property, because it is missing on port %d node. " + "Please update your device tree.\n", + port); + p->interface = dev->compat_interface; + } + /* Configure MII interface for proper network communication. */ ksz_read8(dev, REG_PORT_5_CTRL_6, &data8); data8 &= ~PORT_INTERFACE_TYPE; data8 &= ~PORT_GMII_1GPS_MODE; - switch (dev->interface) { + switch (p->interface) { case PHY_INTERFACE_MODE_MII: p->phydev.speed = SPEED_100; break; @@ -952,11 +960,11 @@ static void ksz8795_port_setup(struct ksz_device *dev, int port, bool cpu_port) default: data8 &= ~PORT_RGMII_ID_IN_ENABLE; data8 &= ~PORT_RGMII_ID_OUT_ENABLE; - if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || - dev->interface == PHY_INTERFACE_MODE_RGMII_RXID) + if (p->interface == PHY_INTERFACE_MODE_RGMII_ID || + p->interface == PHY_INTERFACE_MODE_RGMII_RXID) data8 |= PORT_RGMII_ID_IN_ENABLE; - if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || - dev->interface == PHY_INTERFACE_MODE_RGMII_TXID) + if (p->interface == PHY_INTERFACE_MODE_RGMII_ID || + p->interface == PHY_INTERFACE_MODE_RGMII_TXID) data8 |= PORT_RGMII_ID_OUT_ENABLE; data8 |= PORT_GMII_1GPS_MODE; data8 |= PORT_INTERFACE_RGMII; @@ -1252,7 +1260,7 @@ static int ksz8795_switch_init(struct ksz_device *dev) } /* set the real number of ports */ - dev->ds->num_ports = dev->port_cnt; + dev->ds->num_ports = dev->port_cnt + 1; return 0; } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 3cb22d149813..2f5506ac7d19 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -1208,7 +1208,7 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) /* configure MAC to 1G & RGMII mode */ ksz_pread8(dev, port, REG_PORT_XMII_CTRL_1, &data8); - switch (dev->interface) { + switch (p->interface) { case PHY_INTERFACE_MODE_MII: ksz9477_set_xmii(dev, 0, &data8); ksz9477_set_gbit(dev, false, &data8); @@ -1229,11 +1229,11 @@ static void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz9477_set_gbit(dev, true, &data8); data8 &= ~PORT_RGMII_ID_IG_ENABLE; data8 &= ~PORT_RGMII_ID_EG_ENABLE; - if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || - dev->interface == PHY_INTERFACE_MODE_RGMII_RXID) + if (p->interface == PHY_INTERFACE_MODE_RGMII_ID || + p->interface == PHY_INTERFACE_MODE_RGMII_RXID) data8 |= PORT_RGMII_ID_IG_ENABLE; - if (dev->interface == PHY_INTERFACE_MODE_RGMII_ID || - dev->interface == PHY_INTERFACE_MODE_RGMII_TXID) + if (p->interface == PHY_INTERFACE_MODE_RGMII_ID || + p->interface == PHY_INTERFACE_MODE_RGMII_TXID) data8 |= PORT_RGMII_ID_EG_ENABLE; p->phydev.speed = SPEED_1000; break; @@ -1269,23 +1269,32 @@ static void ksz9477_config_cpu_port(struct dsa_switch *ds) dev->cpu_port = i; dev->host_mask = (1 << dev->cpu_port); dev->port_mask |= dev->host_mask; + p = &dev->ports[i]; /* Read from XMII register to determine host port * interface. If set specifically in device tree * note the difference to help debugging. */ interface = ksz9477_get_interface(dev, i); - if (!dev->interface) - dev->interface = interface; - if (interface && interface != dev->interface) + if (!p->interface) { + if (dev->compat_interface) { + dev_warn(dev->dev, + "Using legacy switch \"phy-mode\" property, because it is missing on port %d node. " + "Please update your device tree.\n", + i); + p->interface = dev->compat_interface; + } else { + p->interface = interface; + } + } + if (interface && interface != p->interface) dev_info(dev->dev, "use %s instead of %s\n", - phy_modes(dev->interface), + phy_modes(p->interface), phy_modes(interface)); /* enable cpu port */ ksz9477_port_setup(dev, i, true); - p = &dev->ports[dev->cpu_port]; p->vid_member = dev->port_mask; p->on = 1; } diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 8d53b12d40a8..c796d42730ba 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -387,7 +387,9 @@ EXPORT_SYMBOL(ksz_switch_alloc); int ksz_switch_register(struct ksz_device *dev, const struct ksz_dev_ops *ops) { + struct device_node *port, *ports; phy_interface_t interface; + unsigned int port_num; int ret; if (dev->pdata) @@ -421,10 +423,23 @@ int ksz_switch_register(struct ksz_device *dev, /* Host port interface will be self detected, or specifically set in * device tree. */ + for (port_num = 0; port_num < dev->port_cnt; ++port_num) + dev->ports[port_num].interface = PHY_INTERFACE_MODE_NA; if (dev->dev->of_node) { ret = of_get_phy_mode(dev->dev->of_node, &interface); if (ret == 0) - dev->interface = interface; + dev->compat_interface = interface; + ports = of_get_child_by_name(dev->dev->of_node, "ports"); + if (ports) + for_each_available_child_of_node(ports, port) { + if (of_property_read_u32(port, "reg", + &port_num)) + continue; + if (port_num >= dev->port_cnt) + return -EINVAL; + of_get_phy_mode(port, + &dev->ports[port_num].interface); + } dev->synclko_125 = of_property_read_bool(dev->dev->of_node, "microchip,synclko-125"); } diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 206838160f49..cf866e48ff66 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -39,6 +39,7 @@ struct ksz_port { u32 freeze:1; /* MIB counter freeze is enabled */ struct ksz_port_mib mib; + phy_interface_t interface; }; struct ksz_device { @@ -72,7 +73,7 @@ struct ksz_device { int mib_cnt; int mib_port_cnt; int last_port; /* ports after that not used */ - phy_interface_t interface; + phy_interface_t compat_interface; u32 regs_size; bool phy_errata_9477; bool synclko_125; diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 04bfa6e465ff..01427cd08448 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -585,7 +585,10 @@ static int felix_setup(struct dsa_switch *ds) if (err) return err; - ocelot_init(ocelot); + err = ocelot_init(ocelot); + if (err) + return err; + if (ocelot->ptp) { err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info); if (err) { @@ -640,10 +643,13 @@ static void felix_teardown(struct dsa_switch *ds) { struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); + int port; if (felix->info->mdio_bus_free) felix->info->mdio_bus_free(ocelot); + for (port = 0; port < ocelot->num_phys_ports; port++) + ocelot_deinit_port(ocelot, port); ocelot_deinit_timestamp(ocelot); /* stop workqueue thread */ ocelot_deinit(ocelot); diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 9b720c8ddfc3..3a9637496407 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -645,17 +645,17 @@ static struct vcap_field vsc9959_vcap_is2_keys[] = { [VCAP_IS2_HK_DIP_EQ_SIP] = {118, 1}, /* IP4_TCP_UDP (TYPE=100) */ [VCAP_IS2_HK_TCP] = {119, 1}, - [VCAP_IS2_HK_L4_SPORT] = {120, 16}, - [VCAP_IS2_HK_L4_DPORT] = {136, 16}, + [VCAP_IS2_HK_L4_DPORT] = {120, 16}, + [VCAP_IS2_HK_L4_SPORT] = {136, 16}, [VCAP_IS2_HK_L4_RNG] = {152, 8}, [VCAP_IS2_HK_L4_SPORT_EQ_DPORT] = {160, 1}, [VCAP_IS2_HK_L4_SEQUENCE_EQ0] = {161, 1}, - [VCAP_IS2_HK_L4_URG] = {162, 1}, - [VCAP_IS2_HK_L4_ACK] = {163, 1}, - [VCAP_IS2_HK_L4_PSH] = {164, 1}, - [VCAP_IS2_HK_L4_RST] = {165, 1}, - [VCAP_IS2_HK_L4_SYN] = {166, 1}, - [VCAP_IS2_HK_L4_FIN] = {167, 1}, + [VCAP_IS2_HK_L4_FIN] = {162, 1}, + [VCAP_IS2_HK_L4_SYN] = {163, 1}, + [VCAP_IS2_HK_L4_RST] = {164, 1}, + [VCAP_IS2_HK_L4_PSH] = {165, 1}, + [VCAP_IS2_HK_L4_ACK] = {166, 1}, + [VCAP_IS2_HK_L4_URG] = {167, 1}, [VCAP_IS2_HK_L4_1588_DOM] = {168, 8}, [VCAP_IS2_HK_L4_1588_VER] = {176, 4}, /* IP4_OTHER (TYPE=101) */ @@ -685,12 +685,12 @@ static struct vcap_field vsc9959_vcap_is2_actions[] = { [VCAP_IS2_ACT_POLICE_ENA] = { 9, 1}, [VCAP_IS2_ACT_POLICE_IDX] = { 10, 9}, [VCAP_IS2_ACT_POLICE_VCAP_ONLY] = { 19, 1}, - [VCAP_IS2_ACT_PORT_MASK] = { 20, 11}, - [VCAP_IS2_ACT_REW_OP] = { 31, 9}, - [VCAP_IS2_ACT_SMAC_REPLACE_ENA] = { 40, 1}, - [VCAP_IS2_ACT_RSV] = { 41, 2}, - [VCAP_IS2_ACT_ACL_ID] = { 43, 6}, - [VCAP_IS2_ACT_HIT_CNT] = { 49, 32}, + [VCAP_IS2_ACT_PORT_MASK] = { 20, 6}, + [VCAP_IS2_ACT_REW_OP] = { 26, 9}, + [VCAP_IS2_ACT_SMAC_REPLACE_ENA] = { 35, 1}, + [VCAP_IS2_ACT_RSV] = { 36, 2}, + [VCAP_IS2_ACT_ACL_ID] = { 38, 6}, + [VCAP_IS2_ACT_HIT_CNT] = { 44, 32}, }; static const struct vcap_props vsc9959_vcap_props[] = { @@ -1171,6 +1171,8 @@ static int vsc9959_prevalidate_phy_mode(struct ocelot *ocelot, int port, */ static u16 vsc9959_wm_enc(u16 value) { + WARN_ON(value >= 16 * BIT(8)); + if (value >= BIT(8)) return BIT(8) | (value / 16); @@ -1284,8 +1286,28 @@ void vsc9959_mdio_bus_free(struct ocelot *ocelot) static void vsc9959_sched_speed_set(struct ocelot *ocelot, int port, u32 speed) { + u8 tas_speed; + + switch (speed) { + case SPEED_10: + tas_speed = OCELOT_SPEED_10; + break; + case SPEED_100: + tas_speed = OCELOT_SPEED_100; + break; + case SPEED_1000: + tas_speed = OCELOT_SPEED_1000; + break; + case SPEED_2500: + tas_speed = OCELOT_SPEED_2500; + break; + default: + tas_speed = OCELOT_SPEED_1000; + break; + } + ocelot_rmw_rix(ocelot, - QSYS_TAG_CONFIG_LINK_SPEED(speed), + QSYS_TAG_CONFIG_LINK_SPEED(tas_speed), QSYS_TAG_CONFIG_LINK_SPEED_M, QSYS_TAG_CONFIG, port); } diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 625b1891d955..9e9fd19e1d00 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -659,17 +659,17 @@ static struct vcap_field vsc9953_vcap_is2_keys[] = { [VCAP_IS2_HK_DIP_EQ_SIP] = {122, 1}, /* IP4_TCP_UDP (TYPE=100) */ [VCAP_IS2_HK_TCP] = {123, 1}, - [VCAP_IS2_HK_L4_SPORT] = {124, 16}, - [VCAP_IS2_HK_L4_DPORT] = {140, 16}, + [VCAP_IS2_HK_L4_DPORT] = {124, 16}, + [VCAP_IS2_HK_L4_SPORT] = {140, 16}, [VCAP_IS2_HK_L4_RNG] = {156, 8}, [VCAP_IS2_HK_L4_SPORT_EQ_DPORT] = {164, 1}, [VCAP_IS2_HK_L4_SEQUENCE_EQ0] = {165, 1}, - [VCAP_IS2_HK_L4_URG] = {166, 1}, - [VCAP_IS2_HK_L4_ACK] = {167, 1}, - [VCAP_IS2_HK_L4_PSH] = {168, 1}, - [VCAP_IS2_HK_L4_RST] = {169, 1}, - [VCAP_IS2_HK_L4_SYN] = {170, 1}, - [VCAP_IS2_HK_L4_FIN] = {171, 1}, + [VCAP_IS2_HK_L4_FIN] = {166, 1}, + [VCAP_IS2_HK_L4_SYN] = {167, 1}, + [VCAP_IS2_HK_L4_RST] = {168, 1}, + [VCAP_IS2_HK_L4_PSH] = {169, 1}, + [VCAP_IS2_HK_L4_ACK] = {170, 1}, + [VCAP_IS2_HK_L4_URG] = {171, 1}, /* IP4_OTHER (TYPE=101) */ [VCAP_IS2_HK_IP4_L3_PROTO] = {123, 8}, [VCAP_IS2_HK_L3_PAYLOAD] = {131, 56}, @@ -706,7 +706,7 @@ static const struct vcap_props vsc9953_vcap_props[] = { .action_type_width = 1, .action_table = { [IS2_ACTION_TYPE_NORMAL] = { - .width = 44, + .width = 50, /* HIT_CNT not included */ .count = 2 }, [IS2_ACTION_TYPE_SMAC_SIP] = { @@ -911,6 +911,8 @@ static int vsc9953_prevalidate_phy_mode(struct ocelot *ocelot, int port, */ static u16 vsc9953_wm_enc(u16 value) { + WARN_ON(value >= 16 * BIT(9)); + if (value >= BIT(9)) return BIT(9) | (value / 16); @@ -1008,7 +1010,7 @@ static const struct felix_info seville_info_vsc9953 = { .vcap_is2_keys = vsc9953_vcap_is2_keys, .vcap_is2_actions = vsc9953_vcap_is2_actions, .vcap = vsc9953_vcap_props, - .shared_queue_sz = 128 * 1024, + .shared_queue_sz = 2048 * 1024, .num_mact_rows = 2048, .num_ports = 10, .mdio_bus_alloc = vsc9953_mdio_bus_alloc, diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c index 8f40fbf70a82..a8c5a934c3d3 100644 --- a/drivers/net/dsa/rtl8366.c +++ b/drivers/net/dsa/rtl8366.c @@ -452,13 +452,19 @@ int rtl8366_vlan_del(struct dsa_switch *ds, int port, return ret; if (vid == vlanmc.vid) { - /* clear VLAN member configurations */ - vlanmc.vid = 0; - vlanmc.priority = 0; - vlanmc.member = 0; - vlanmc.untag = 0; - vlanmc.fid = 0; - + /* Remove this port from the VLAN */ + vlanmc.member &= ~BIT(port); + vlanmc.untag &= ~BIT(port); + /* + * If no ports are members of this VLAN + * anymore then clear the whole member + * config so it can be reused. + */ + if (!vlanmc.member && vlanmc.untag) { + vlanmc.vid = 0; + vlanmc.priority = 0; + vlanmc.fid = 0; + } ret = smi->ops->set_vlan_mc(smi, i, &vlanmc); if (ret) { dev_err(smi->dev, diff --git a/drivers/net/ethernet/3com/typhoon.h b/drivers/net/ethernet/3com/typhoon.h index 2f634c64d5d1..38e6dcab4e94 100644 --- a/drivers/net/ethernet/3com/typhoon.h +++ b/drivers/net/ethernet/3com/typhoon.h @@ -33,7 +33,7 @@ struct basic_ring { u32 lastWrite; }; -/* The Typoon transmit ring -- same as a basic ring, plus: +/* The Typhoon transmit ring -- same as a basic ring, plus: * lastRead: where we're at in regard to cleaning up the ring * writeRegister: register to use for writing (different for Hi & Lo rings) */ diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile index 130a105d03f3..8ebcc68e807f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/Makefile +++ b/drivers/net/ethernet/aquantia/atlantic/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_AQTION) += atlantic.o -ccflags-y += -I$(src) +ccflags-y += -I$(srctree)/$(src) atlantic-objs := aq_main.o \ aq_nic.o \ @@ -33,4 +33,4 @@ atlantic-objs := aq_main.o \ atlantic-$(CONFIG_MACSEC) += aq_macsec.o -atlantic-$(CONFIG_PTP_1588_CLOCK) += aq_ptp.o
\ No newline at end of file +atlantic-$(CONFIG_PTP_1588_CLOCK) += aq_ptp.o diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index bfc0e45d4a2b..5caa75b41b73 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -284,12 +284,12 @@ #define CCM_REG_GR_ARB_TYPE 0xd015c /* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed; that the Store channel priority is - the compliment to 4 of the rest priorities - Aggregation channel; Load + the complement to 4 of the rest priorities - Aggregation channel; Load (FIC0) channel and Load (FIC1). */ #define CCM_REG_GR_LD0_PR 0xd0164 /* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed; that the Store channel priority is - the compliment to 4 of the rest priorities - Aggregation channel; Load + the complement to 4 of the rest priorities - Aggregation channel; Load (FIC0) channel and Load (FIC1). */ #define CCM_REG_GR_LD1_PR 0xd0168 /* [RW 2] General flags index. */ @@ -4489,11 +4489,11 @@ #define TCM_REG_GR_ARB_TYPE 0x50114 /* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Store channel is the - compliment of the other 3 groups. */ + complement of the other 3 groups. */ #define TCM_REG_GR_LD0_PR 0x5011c /* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Store channel is the - compliment of the other 3 groups. */ + complement of the other 3 groups. */ #define TCM_REG_GR_LD1_PR 0x50120 /* [RW 4] The number of double REG-pairs; loaded from the STORM context and sent to STORM; for a specific connection type. The double REG-pairs are @@ -5020,11 +5020,11 @@ #define UCM_REG_GR_ARB_TYPE 0xe0144 /* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Store channel group is - compliment to the others. */ + complement to the others. */ #define UCM_REG_GR_LD0_PR 0xe014c /* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Store channel group is - compliment to the others. */ + complement to the others. */ #define UCM_REG_GR_LD1_PR 0xe0150 /* [RW 2] The queue index for invalidate counter flag decision. */ #define UCM_REG_INV_CFLG_Q 0xe00e4 @@ -5523,11 +5523,11 @@ #define XCM_REG_GR_ARB_TYPE 0x2020c /* [RW 2] Load (FIC0) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Channel group is the - compliment of the other 3 groups. */ + complement of the other 3 groups. */ #define XCM_REG_GR_LD0_PR 0x20214 /* [RW 2] Load (FIC1) channel group priority. The lowest priority is 0; the highest priority is 3. It is supposed that the Channel group is the - compliment of the other 3 groups. */ + complement of the other 3 groups. */ #define XCM_REG_GR_LD1_PR 0x20218 /* [RW 1] Input nig0 Interface enable. If 0 - the valid input is disregarded; acknowledge output is deasserted; all other signals are diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index b167066af450..7b7e8b7883c8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3782,6 +3782,7 @@ static int bnxt_hwrm_func_qstat_ext(struct bnxt *bp, return -EOPNOTSUPP; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QSTATS_EXT, -1, -1); + req.fid = cpu_to_le16(0xffff); req.flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); @@ -3852,7 +3853,7 @@ static void bnxt_init_stats(struct bnxt *bp) tx_masks = stats->hw_masks; tx_count = sizeof(struct tx_port_stats_ext) / 8; - flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; + flags = PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; rc = bnxt_hwrm_port_qstats_ext(bp, flags); if (rc) { mask = (1ULL << 40) - 1; @@ -4305,7 +4306,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM; u16 dst = BNXT_HWRM_CHNL_CHIMP; - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + if (BNXT_NO_FW_ACCESS(bp)) return -EBUSY; if (msg_len > BNXT_HWRM_MAX_REQ_LEN) { @@ -5723,7 +5724,7 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp, struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr; u16 error_code; - if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + if (BNXT_NO_FW_ACCESS(bp)) return 0; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1); @@ -7817,7 +7818,7 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa) if (set_tpa) tpa_flags = bp->flags & BNXT_FLAG_TPA; - else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + else if (BNXT_NO_FW_ACCESS(bp)) return 0; for (i = 0; i < bp->nr_vnics; i++) { rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags); @@ -9311,18 +9312,16 @@ static ssize_t bnxt_show_temp(struct device *dev, struct hwrm_temp_monitor_query_output *resp; struct bnxt *bp = dev_get_drvdata(dev); u32 len = 0; + int rc; resp = bp->hwrm_cmd_resp_addr; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); mutex_lock(&bp->hwrm_cmd_lock); - if (!_hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT)) + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (!rc) len = sprintf(buf, "%u\n", resp->temp * 1000); /* display millidegree */ mutex_unlock(&bp->hwrm_cmd_lock); - - if (len) - return len; - - return sprintf(buf, "unknown\n"); + return rc ?: len; } static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0); @@ -9342,7 +9341,16 @@ static void bnxt_hwmon_close(struct bnxt *bp) static void bnxt_hwmon_open(struct bnxt *bp) { + struct hwrm_temp_monitor_query_input req = {0}; struct pci_dev *pdev = bp->pdev; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1); + rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc == -EACCES || rc == -EOPNOTSUPP) { + bnxt_hwmon_close(bp); + return; + } if (bp->hwmon_dev) return; @@ -11779,6 +11787,10 @@ static void bnxt_remove_one(struct pci_dev *pdev) if (BNXT_PF(bp)) bnxt_sriov_disable(bp); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + bnxt_cancel_sp_work(bp); + bp->sp_event = 0; + bnxt_dl_fw_reporters_destroy(bp, true); if (BNXT_PF(bp)) devlink_port_type_clear(&bp->dl_port); @@ -11786,9 +11798,6 @@ static void bnxt_remove_one(struct pci_dev *pdev) unregister_netdev(dev); bnxt_dl_unregister(bp); bnxt_shutdown_tc(bp); - clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); - bnxt_cancel_sp_work(bp); - bp->sp_event = 0; bnxt_clear_int_mode(bp); bnxt_hwrm_func_drv_unrgtr(bp); @@ -12089,7 +12098,7 @@ static int bnxt_init_mac_addr(struct bnxt *bp) static void bnxt_vpd_read_info(struct bnxt *bp) { struct pci_dev *pdev = bp->pdev; - int i, len, pos, ro_size; + int i, len, pos, ro_size, size; ssize_t vpd_size; u8 *vpd_data; @@ -12124,7 +12133,8 @@ static void bnxt_vpd_read_info(struct bnxt *bp) if (len + pos > vpd_size) goto read_sn; - strlcpy(bp->board_partno, &vpd_data[pos], min(len, BNXT_VPD_FLD_LEN)); + size = min(len, BNXT_VPD_FLD_LEN - 1); + memcpy(bp->board_partno, &vpd_data[pos], size); read_sn: pos = pci_vpd_find_info_keyword(vpd_data, i, ro_size, @@ -12137,7 +12147,8 @@ read_sn: if (len + pos > vpd_size) goto exit; - strlcpy(bp->board_serialno, &vpd_data[pos], min(len, BNXT_VPD_FLD_LEN)); + size = min(len, BNXT_VPD_FLD_LEN - 1); + memcpy(bp->board_serialno, &vpd_data[pos], size); exit: kfree(vpd_data); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 5a13eb66beda..0ef89dabfd61 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1737,6 +1737,10 @@ struct bnxt { #define BNXT_STATE_FW_FATAL_COND 6 #define BNXT_STATE_DRV_REGISTERED 7 +#define BNXT_NO_FW_ACCESS(bp) \ + (test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) || \ + pci_channel_offline((bp)->pdev)) + struct bnxt_irq *irq_tbl; int total_irqs; u8 mac_addr[ETH_ALEN]; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index d0928334bdc8..fecdfd875af1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -1322,6 +1322,9 @@ static int bnxt_get_regs_len(struct net_device *dev) struct bnxt *bp = netdev_priv(dev); int reg_len; + if (!BNXT_PF(bp)) + return -EOPNOTSUPP; + reg_len = BNXT_PXP_REG_LEN; if (bp->fw_cap & BNXT_FW_CAP_PCIE_STATS_SUPPORTED) @@ -1788,9 +1791,12 @@ static int bnxt_set_pauseparam(struct net_device *dev, if (!BNXT_PHY_CFG_ABLE(bp)) return -EOPNOTSUPP; + mutex_lock(&bp->link_lock); if (epause->autoneg) { - if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) - return -EINVAL; + if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) { + rc = -EINVAL; + goto pause_exit; + } link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL; if (bp->hwrm_spec_code >= 0x10201) @@ -1811,11 +1817,11 @@ static int bnxt_set_pauseparam(struct net_device *dev, if (epause->tx_pause) link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_TX; - if (netif_running(dev)) { - mutex_lock(&bp->link_lock); + if (netif_running(dev)) rc = bnxt_hwrm_set_pause(bp); - mutex_unlock(&bp->link_lock); - } + +pause_exit: + mutex_unlock(&bp->link_lock); return rc; } @@ -2552,8 +2558,7 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata) struct bnxt *bp = netdev_priv(dev); struct ethtool_eee *eee = &bp->eee; struct bnxt_link_info *link_info = &bp->link_info; - u32 advertising = - _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0); + u32 advertising; int rc = 0; if (!BNXT_PHY_CFG_ABLE(bp)) @@ -2562,19 +2567,23 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata) if (!(bp->flags & BNXT_FLAG_EEE_CAP)) return -EOPNOTSUPP; + mutex_lock(&bp->link_lock); + advertising = _bnxt_fw_to_ethtool_adv_spds(link_info->advertising, 0); if (!edata->eee_enabled) goto eee_ok; if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) { netdev_warn(dev, "EEE requires autoneg\n"); - return -EINVAL; + rc = -EINVAL; + goto eee_exit; } if (edata->tx_lpi_enabled) { if (bp->lpi_tmr_hi && (edata->tx_lpi_timer > bp->lpi_tmr_hi || edata->tx_lpi_timer < bp->lpi_tmr_lo)) { netdev_warn(dev, "Valid LPI timer range is %d and %d microsecs\n", bp->lpi_tmr_lo, bp->lpi_tmr_hi); - return -EINVAL; + rc = -EINVAL; + goto eee_exit; } else if (!bp->lpi_tmr_hi) { edata->tx_lpi_timer = eee->tx_lpi_timer; } @@ -2584,7 +2593,8 @@ static int bnxt_set_eee(struct net_device *dev, struct ethtool_eee *edata) } else if (edata->advertised & ~advertising) { netdev_warn(dev, "EEE advertised %x must be a subset of autoneg advertised speeds %x\n", edata->advertised, advertising); - return -EINVAL; + rc = -EINVAL; + goto eee_exit; } eee->advertised = edata->advertised; @@ -2596,6 +2606,8 @@ eee_ok: if (netif_running(dev)) rc = bnxt_hwrm_set_link_setting(bp, false, true); +eee_exit: + mutex_unlock(&bp->link_lock); return rc; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 6761f404b8aa..9179f7b0b900 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -647,8 +647,7 @@ static void macb_mac_link_up(struct phylink_config *config, ctrl |= GEM_BIT(GBE); } - /* We do not support MLO_PAUSE_RX yet */ - if (tx_pause) + if (rx_pause) ctrl |= MACB_BIT(PAE); macb_set_tx_clk(bp->tx_clk, speed, ndev); diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 3e17ce0d2314..6cb2162a75d4 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -1219,7 +1219,7 @@ static int octeon_mgmt_open(struct net_device *netdev) */ if (netdev->phydev) { netif_carrier_off(netdev); - phy_start_aneg(netdev->phydev); + phy_start(netdev->phydev); } netif_wake_queue(netdev); @@ -1247,8 +1247,10 @@ static int octeon_mgmt_stop(struct net_device *netdev) napi_disable(&p->napi); netif_stop_queue(netdev); - if (netdev->phydev) + if (netdev->phydev) { + phy_stop(netdev->phydev); phy_disconnect(netdev->phydev); + } netif_carrier_off(netdev); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index 650db92cb11c..481498585ead 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -1911,13 +1911,16 @@ out: static int configure_filter_tcb(struct adapter *adap, unsigned int tid, struct filter_entry *f) { - if (f->fs.hitcnts) + if (f->fs.hitcnts) { set_tcb_field(adap, f, tid, TCB_TIMESTAMP_W, - TCB_TIMESTAMP_V(TCB_TIMESTAMP_M) | + TCB_TIMESTAMP_V(TCB_TIMESTAMP_M), + TCB_TIMESTAMP_V(0ULL), + 1); + set_tcb_field(adap, f, tid, TCB_RTT_TS_RECENT_AGE_W, TCB_RTT_TS_RECENT_AGE_V(TCB_RTT_TS_RECENT_AGE_M), - TCB_TIMESTAMP_V(0ULL) | TCB_RTT_TS_RECENT_AGE_V(0ULL), 1); + } if (f->fs.newdmac) set_tcb_tflag(adap, f, tid, TF_CCTRL_ECE_S, 1, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c index b1a073eea60b..a020e8490681 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_mps.c @@ -229,7 +229,7 @@ void cxgb4_free_mps_ref_entries(struct adapter *adap) { struct mps_entries_ref *mps_entry, *tmp; - if (!list_empty(&adap->mps_ref)) + if (list_empty(&adap->mps_ref)) return; spin_lock(&adap->mps_ref_lock); diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index cb116b530f5e..2610efe4f873 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -85,7 +85,7 @@ MODULE_PARM_DESC (rx_copybreak, "de2104x Breakpoint at which Rx packets are copi #define DSL CONFIG_DE2104X_DSL #endif -#define DE_RX_RING_SIZE 64 +#define DE_RX_RING_SIZE 128 #define DE_TX_RING_SIZE 64 #define DE_RING_BYTES \ ((sizeof(struct de_desc) * DE_RX_RING_SIZE) + \ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h index 3ea51dd9374b..a24b20f76938 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpmac-cmd.h @@ -66,8 +66,8 @@ struct dpmac_cmd_get_counter { }; struct dpmac_rsp_get_counter { - u64 pad; - u64 counter; + __le64 pad; + __le64 counter; }; #endif /* _FSL_DPMAC_CMD_H */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h index 593e3812af93..3c06f5fb5759 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h @@ -11,9 +11,11 @@ #define DPNI_VER_MAJOR 7 #define DPNI_VER_MINOR 0 #define DPNI_CMD_BASE_VERSION 1 +#define DPNI_CMD_2ND_VERSION 2 #define DPNI_CMD_ID_OFFSET 4 #define DPNI_CMD(id) (((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_BASE_VERSION) +#define DPNI_CMD_V2(id) (((id) << DPNI_CMD_ID_OFFSET) | DPNI_CMD_2ND_VERSION) #define DPNI_CMDID_OPEN DPNI_CMD(0x801) #define DPNI_CMDID_CLOSE DPNI_CMD(0x800) @@ -45,7 +47,7 @@ #define DPNI_CMDID_SET_MAX_FRAME_LENGTH DPNI_CMD(0x216) #define DPNI_CMDID_GET_MAX_FRAME_LENGTH DPNI_CMD(0x217) #define DPNI_CMDID_SET_LINK_CFG DPNI_CMD(0x21A) -#define DPNI_CMDID_SET_TX_SHAPING DPNI_CMD(0x21B) +#define DPNI_CMDID_SET_TX_SHAPING DPNI_CMD_V2(0x21B) #define DPNI_CMDID_SET_MCAST_PROMISC DPNI_CMD(0x220) #define DPNI_CMDID_GET_MCAST_PROMISC DPNI_CMD(0x221) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 26d5981b798f..177334f0adb1 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -1053,7 +1053,6 @@ static int enetc_pf_probe(struct pci_dev *pdev, err_reg_netdev: enetc_teardown_serdes(priv); - enetc_mdio_remove(pf); enetc_free_msix(priv); err_alloc_msix: enetc_free_si_resources(priv); @@ -1061,6 +1060,7 @@ err_alloc_si_res: si->ndev = NULL; free_netdev(ndev); err_alloc_netdev: + enetc_mdio_remove(pf); enetc_of_put_phy(pf); err_map_pf_space: enetc_pci_remove(pdev); diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index 98be51d8b08c..bfa2826c5545 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -229,7 +229,7 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) /* Return all Fs if nothing was there */ if ((xgmac_read32(®s->mdio_stat, endian) & MDIO_STAT_RD_ER) && !priv->has_a011043) { - dev_err(&bus->dev, + dev_dbg(&bus->dev, "Error while reading PHY%d reg at %d.%hhu\n", phy_id, dev_addr, regnum); return 0xffff; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c index ed3829ae4ef1..a769273b36f7 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -334,7 +334,7 @@ static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev, * bit6-11 for ppe0-5 * bit12-17 for roce0-5 * bit18-19 for com/dfx - * @enable: false - request reset , true - drop reset + * @dereset: false - request reset , true - drop reset */ static void hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) @@ -357,7 +357,7 @@ hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) * bit6-11 for ppe0-5 * bit12-17 for roce0-5 * bit18-19 for com/dfx - * @enable: false - request reset , true - drop reset + * @dereset: false - request reset , true - drop reset */ static void hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset) diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 4eb50296f653..14e60c9e491d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -463,8 +463,8 @@ static int __lb_clean_rings(struct hns_nic_priv *priv, /** * nic_run_loopback_test - run loopback test - * @nic_dev: net device - * @loopback_type: loopback type + * @ndev: net device + * @loop_mode: loopback mode */ static int __lb_run_test(struct net_device *ndev, enum hnae_loop loop_mode) @@ -572,7 +572,7 @@ static int __lb_down(struct net_device *ndev, enum hnae_loop loop) /** * hns_nic_self_test - self test - * @dev: net device + * @ndev: net device * @eth_test: test cmd * @data: test result */ @@ -633,7 +633,7 @@ static void hns_nic_self_test(struct net_device *ndev, /** * hns_nic_get_drvinfo - get net driver info - * @dev: net device + * @net_dev: net device * @drvinfo: driver info */ static void hns_nic_get_drvinfo(struct net_device *net_dev, @@ -658,7 +658,7 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev, /** * hns_get_ringparam - get ring parameter - * @dev: net device + * @net_dev: net device * @param: ethtool parameter */ static void hns_get_ringparam(struct net_device *net_dev, @@ -683,7 +683,7 @@ static void hns_get_ringparam(struct net_device *net_dev, /** * hns_get_pauseparam - get pause parameter - * @dev: net device + * @net_dev: net device * @param: pause parameter */ static void hns_get_pauseparam(struct net_device *net_dev, @@ -701,7 +701,7 @@ static void hns_get_pauseparam(struct net_device *net_dev, /** * hns_set_pauseparam - set pause parameter - * @dev: net device + * @net_dev: net device * @param: pause parameter * * Return 0 on success, negative on failure @@ -725,7 +725,7 @@ static int hns_set_pauseparam(struct net_device *net_dev, /** * hns_get_coalesce - get coalesce info. - * @dev: net device + * @net_dev: net device * @ec: coalesce info. * * Return 0 on success, negative on failure. @@ -769,7 +769,7 @@ static int hns_get_coalesce(struct net_device *net_dev, /** * hns_set_coalesce - set coalesce info. - * @dev: net device + * @net_dev: net device * @ec: coalesce info. * * Return 0 on success, negative on failure. @@ -808,7 +808,7 @@ static int hns_set_coalesce(struct net_device *net_dev, /** * hns_get_channels - get channel info. - * @dev: net device + * @net_dev: net device * @ch: channel info. */ static void @@ -825,7 +825,7 @@ hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch) /** * get_ethtool_stats - get detail statistics. - * @dev: net device + * @netdev: net device * @stats: statistics info. * @data: statistics data. */ @@ -883,8 +883,8 @@ static void hns_get_ethtool_stats(struct net_device *netdev, /** * get_strings: Return a set of strings that describe the requested objects - * @dev: net device - * @stats: string set ID. + * @netdev: net device + * @stringset: string set ID. * @data: objects data. */ static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) @@ -972,7 +972,7 @@ static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) /** * nic_get_sset_count - get string set count witch returned by nic_get_strings. - * @dev: net device + * @netdev: net device * @stringset: string set index, 0: self test string; 1: statistics string. * * Return string set count. @@ -1006,7 +1006,7 @@ static int hns_get_sset_count(struct net_device *netdev, int stringset) /** * hns_phy_led_set - set phy LED status. - * @dev: net device + * @netdev: net device * @value: LED state. * * Return 0 on success, negative on failure. @@ -1028,7 +1028,7 @@ static int hns_phy_led_set(struct net_device *netdev, int value) /** * nic_set_phys_id - set phy identify LED. - * @dev: net device + * @netdev: net device * @state: LED state. * * Return 0 on success, negative on failure. @@ -1104,9 +1104,9 @@ hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) /** * hns_get_regs - get net device register - * @dev: net device + * @net_dev: net device * @cmd: ethtool cmd - * @date: register data + * @data: register data */ static void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd, void *data) @@ -1126,7 +1126,7 @@ static void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd, /** * nic_get_regs_len - get total register len. - * @dev: net device + * @net_dev: net device * * Return total register len. */ @@ -1151,7 +1151,7 @@ static int hns_get_regs_len(struct net_device *net_dev) /** * hns_nic_nway_reset - nway reset - * @dev: net device + * @netdev: net device * * Return 0 on success, negative on failure */ diff --git a/drivers/net/ethernet/huawei/hinic/Kconfig b/drivers/net/ethernet/huawei/hinic/Kconfig index 936e2dd3bb13..b47bd5440c5f 100644 --- a/drivers/net/ethernet/huawei/hinic/Kconfig +++ b/drivers/net/ethernet/huawei/hinic/Kconfig @@ -6,6 +6,7 @@ config HINIC tristate "Huawei Intelligent PCIE Network Interface Card" depends on (PCI_MSI && (X86 || ARM64)) + select NET_DEVLINK help This driver supports HiNIC PCIE Ethernet cards. To compile this driver as part of the kernel, choose Y here. diff --git a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c index 6bb65ade1d77..c340d9acba80 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_ethtool.c @@ -1654,6 +1654,7 @@ static void hinic_diag_test(struct net_device *netdev, } netif_carrier_off(netdev); + netif_tx_disable(netdev); err = do_lp_test(nic_dev, eth_test->flags, LP_DEFAULT_TIME, &test_index); @@ -1662,9 +1663,12 @@ static void hinic_diag_test(struct net_device *netdev, data[test_index] = 1; } + netif_tx_wake_all_queues(netdev); + err = hinic_port_link_state(nic_dev, &link_state); if (!err && link_state == HINIC_LINK_STATE_UP) netif_carrier_on(netdev); + } static int hinic_set_phys_id(struct net_device *netdev, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c index c6ce5966284c..2ebae6cb5db5 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_mgmt.c @@ -47,8 +47,12 @@ #define MGMT_MSG_TIMEOUT 5000 +#define SET_FUNC_PORT_MBOX_TIMEOUT 30000 + #define SET_FUNC_PORT_MGMT_TIMEOUT 25000 +#define UPDATE_FW_MGMT_TIMEOUT 20000 + #define mgmt_to_pfhwdev(pf_mgmt) \ container_of(pf_mgmt, struct hinic_pfhwdev, pf_to_mgmt) @@ -361,16 +365,22 @@ 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; + if (HINIC_IS_VF(hwif)) { + if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE) + timeout = SET_FUNC_PORT_MBOX_TIMEOUT; - if (HINIC_IS_VF(hwif)) return hinic_mbox_to_pf(pf_to_mgmt->hwdev, mod, cmd, buf_in, - in_size, buf_out, out_size, 0); - else + in_size, buf_out, out_size, timeout); + } else { + if (cmd == HINIC_PORT_CMD_SET_FUNC_STATE) + timeout = SET_FUNC_PORT_MGMT_TIMEOUT; + else if (cmd == HINIC_PORT_CMD_UPDATE_FW) + timeout = UPDATE_FW_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, timeout); + } } static void recv_mgmt_msg_work_handler(struct work_struct *work) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index 501056fd32ee..28581bd8ce07 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -174,6 +174,24 @@ err_init_txq: return err; } +static void enable_txqs_napi(struct hinic_dev *nic_dev) +{ + int num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev); + int i; + + for (i = 0; i < num_txqs; i++) + napi_enable(&nic_dev->txqs[i].napi); +} + +static void disable_txqs_napi(struct hinic_dev *nic_dev) +{ + int num_txqs = hinic_hwdev_num_qps(nic_dev->hwdev); + int i; + + for (i = 0; i < num_txqs; i++) + napi_disable(&nic_dev->txqs[i].napi); +} + /** * free_txqs - Free the Logical Tx Queues of specific NIC device * @nic_dev: the specific NIC device @@ -400,6 +418,8 @@ int hinic_open(struct net_device *netdev) goto err_create_txqs; } + enable_txqs_napi(nic_dev); + err = create_rxqs(nic_dev); if (err) { netif_err(nic_dev, drv, netdev, @@ -484,6 +504,7 @@ err_port_state: } err_create_rxqs: + disable_txqs_napi(nic_dev); free_txqs(nic_dev); err_create_txqs: @@ -497,6 +518,9 @@ int hinic_close(struct net_device *netdev) struct hinic_dev *nic_dev = netdev_priv(netdev); unsigned int flags; + /* Disable txq napi firstly to aviod rewaking txq in free_tx_poll */ + disable_txqs_napi(nic_dev); + down(&nic_dev->mgmt_lock); flags = nic_dev->flags; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c index 02cd635d6914..eb97f2d6b1ad 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_port.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c @@ -58,9 +58,9 @@ static int change_mac(struct hinic_dev *nic_dev, const u8 *addr, sizeof(port_mac_cmd), &port_mac_cmd, &out_size); if (err || out_size != sizeof(port_mac_cmd) || - (port_mac_cmd.status && - port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY && - port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) { + (port_mac_cmd.status && + (port_mac_cmd.status != HINIC_PF_SET_VF_ALREADY || !HINIC_IS_VF(hwif)) && + port_mac_cmd.status != HINIC_MGMT_STATUS_EXIST)) { dev_err(&pdev->dev, "Failed to change MAC, err: %d, status: 0x%x, out size: 0x%x\n", err, port_mac_cmd.status, out_size); return -EFAULT; diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index 5bee951fe9d4..d0072f5e7efc 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -543,18 +543,25 @@ static int rx_request_irq(struct hinic_rxq *rxq) if (err) { netif_err(nic_dev, drv, rxq->netdev, "Failed to set RX interrupt coalescing attribute\n"); - rx_del_napi(rxq); - return err; + goto err_req_irq; } err = request_irq(rq->irq, rx_irq, 0, rxq->irq_name, rxq); - if (err) { - rx_del_napi(rxq); - return err; - } + if (err) + goto err_req_irq; cpumask_set_cpu(qp->q_id % num_online_cpus(), &rq->affinity_mask); - return irq_set_affinity_hint(rq->irq, &rq->affinity_mask); + err = irq_set_affinity_hint(rq->irq, &rq->affinity_mask); + if (err) + goto err_irq_affinity; + + return 0; + +err_irq_affinity: + free_irq(rq->irq, rxq); +err_req_irq: + rx_del_napi(rxq); + return err; } static void rx_free_irq(struct hinic_rxq *rxq) diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c index 4d63680f2143..f8a26459ff65 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c @@ -38,8 +38,7 @@ static int hinic_set_mac(struct hinic_hwdev *hwdev, const u8 *mac_addr, err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_MAC, &mac_info, sizeof(mac_info), &mac_info, &out_size); if (err || out_size != sizeof(mac_info) || - (mac_info.status && mac_info.status != HINIC_PF_SET_VF_ALREADY && - mac_info.status != HINIC_MGMT_STATUS_EXIST)) { + (mac_info.status && mac_info.status != HINIC_MGMT_STATUS_EXIST)) { dev_err(&hwdev->func_to_io.hwif->pdev->dev, "Failed to set MAC, err: %d, status: 0x%x, out size: 0x%x\n", err, mac_info.status, out_size); return -EIO; @@ -503,8 +502,7 @@ struct hinic_sriov_info *hinic_get_sriov_info_by_pcidev(struct pci_dev *pdev) static int hinic_check_mac_info(u8 status, u16 vlan_id) { - if ((status && status != HINIC_MGMT_STATUS_EXIST && - status != HINIC_PF_SET_VF_ALREADY) || + if ((status && status != HINIC_MGMT_STATUS_EXIST) || (vlan_id & CHECK_IPSU_15BIT && status == HINIC_MGMT_STATUS_EXIST)) return -EINVAL; @@ -546,12 +544,6 @@ static int hinic_update_mac(struct hinic_hwdev *hwdev, u8 *old_mac, return -EINVAL; } - if (mac_info.status == HINIC_PF_SET_VF_ALREADY) { - dev_warn(&hwdev->hwif->pdev->dev, - "PF has already set VF MAC. Ignore update operation\n"); - return HINIC_PF_SET_VF_ALREADY; - } - if (mac_info.status == HINIC_MGMT_STATUS_EXIST) dev_warn(&hwdev->hwif->pdev->dev, "MAC is repeated. Ignore update operation\n"); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index a97498ee6914..c1f81e9144a1 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -717,8 +717,8 @@ static int free_tx_poll(struct napi_struct *napi, int budget) netdev_txq = netdev_get_tx_queue(txq->netdev, qp->q_id); __netif_tx_lock(netdev_txq, smp_processor_id()); - - netif_wake_subqueue(nic_dev->netdev, qp->q_id); + if (!netif_testing(nic_dev->netdev)) + netif_wake_subqueue(nic_dev->netdev, qp->q_id); __netif_tx_unlock(netdev_txq); @@ -745,18 +745,6 @@ static int free_tx_poll(struct napi_struct *napi, int budget) return budget; } -static void tx_napi_add(struct hinic_txq *txq, int weight) -{ - netif_napi_add(txq->netdev, &txq->napi, free_tx_poll, weight); - napi_enable(&txq->napi); -} - -static void tx_napi_del(struct hinic_txq *txq) -{ - napi_disable(&txq->napi); - netif_napi_del(&txq->napi); -} - static irqreturn_t tx_irq(int irq, void *data) { struct hinic_txq *txq = data; @@ -790,7 +778,7 @@ static int tx_request_irq(struct hinic_txq *txq) qp = container_of(sq, struct hinic_qp, sq); - tx_napi_add(txq, nic_dev->tx_weight); + netif_napi_add(txq->netdev, &txq->napi, free_tx_poll, nic_dev->tx_weight); hinic_hwdev_msix_set(nic_dev->hwdev, sq->msix_entry, TX_IRQ_NO_PENDING, TX_IRQ_NO_COALESC, @@ -807,14 +795,14 @@ static int tx_request_irq(struct hinic_txq *txq) if (err) { netif_err(nic_dev, drv, txq->netdev, "Failed to set TX interrupt coalescing attribute\n"); - tx_napi_del(txq); + netif_napi_del(&txq->napi); return err; } err = request_irq(sq->irq, tx_irq, 0, txq->irq_name, txq); if (err) { dev_err(&pdev->dev, "Failed to request Tx irq\n"); - tx_napi_del(txq); + netif_napi_del(&txq->napi); return err; } @@ -826,7 +814,7 @@ static void tx_free_irq(struct hinic_txq *txq) struct hinic_sq *sq = txq->sq; free_irq(sq->irq, txq); - tx_napi_del(txq); + netif_napi_del(&txq->napi); } /** diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index d3a774331afc..1b702a43a5d0 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2032,16 +2032,18 @@ static int do_reset(struct ibmvnic_adapter *adapter, } else { rc = reset_tx_pools(adapter); - if (rc) + if (rc) { netdev_dbg(adapter->netdev, "reset tx pools failed (%d)\n", rc); goto out; + } rc = reset_rx_pools(adapter); - if (rc) + if (rc) { netdev_dbg(adapter->netdev, "reset rx pools failed (%d)\n", rc); goto out; + } } ibmvnic_disable_irqs(adapter); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 8e133d6545bd..47bfb2e95e2d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1115,7 +1115,7 @@ static int i40e_quiesce_vf_pci(struct i40e_vf *vf) static int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi) { struct i40e_mac_filter *f; - int num_vlans = 0, bkt; + u16 num_vlans = 0, bkt; hash_for_each(vsi->mac_filter_hash, bkt, f, hlist) { if (f->vlan >= 0 && f->vlan <= I40E_MAX_VLANID) @@ -1134,8 +1134,8 @@ static int i40e_getnum_vf_vsi_vlan_filters(struct i40e_vsi *vsi) * * Called to get number of VLANs and VLAN list present in mac_filter_hash. **/ -static void i40e_get_vlan_list_sync(struct i40e_vsi *vsi, int *num_vlans, - s16 **vlan_list) +static void i40e_get_vlan_list_sync(struct i40e_vsi *vsi, u16 *num_vlans, + s16 **vlan_list) { struct i40e_mac_filter *f; int i = 0; @@ -1169,11 +1169,11 @@ err: **/ static i40e_status i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, - bool unicast_enable, s16 *vl, int num_vlans) + bool unicast_enable, s16 *vl, u16 num_vlans) { + i40e_status aq_ret, aq_tmp = 0; struct i40e_pf *pf = vf->pf; struct i40e_hw *hw = &pf->hw; - i40e_status aq_ret; int i; /* No VLAN to set promisc on, set on VSI */ @@ -1222,6 +1222,9 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, vf->vf_id, i40e_stat_str(&pf->hw, aq_ret), i40e_aq_str(&pf->hw, aq_err)); + + if (!aq_tmp) + aq_tmp = aq_ret; } aq_ret = i40e_aq_set_vsi_uc_promisc_on_vlan(hw, seid, @@ -1235,8 +1238,15 @@ i40e_set_vsi_promisc(struct i40e_vf *vf, u16 seid, bool multi_enable, vf->vf_id, i40e_stat_str(&pf->hw, aq_ret), i40e_aq_str(&pf->hw, aq_err)); + + if (!aq_tmp) + aq_tmp = aq_ret; } } + + if (aq_tmp) + aq_ret = aq_tmp; + return aq_ret; } @@ -1258,7 +1268,7 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, i40e_status aq_ret = I40E_SUCCESS; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi; - int num_vlans; + u16 num_vlans; s16 *vl; vsi = i40e_find_vsi_from_id(pf, vsi_id); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index d870343cf689..cf539db79af9 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -3806,8 +3806,8 @@ static int __maybe_unused iavf_suspend(struct device *dev_d) static int __maybe_unused iavf_resume(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); - struct iavf_adapter *adapter = pci_get_drvdata(pdev); - struct net_device *netdev = adapter->netdev; + struct net_device *netdev = pci_get_drvdata(pdev); + struct iavf_adapter *adapter = netdev_priv(netdev); u32 err; pci_set_master(pdev); diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 34abfcea9858..7db5fd977367 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -2288,26 +2288,28 @@ void ice_set_safe_mode_caps(struct ice_hw *hw) { struct ice_hw_func_caps *func_caps = &hw->func_caps; struct ice_hw_dev_caps *dev_caps = &hw->dev_caps; - u32 valid_func, rxq_first_id, txq_first_id; - u32 msix_vector_first_id, max_mtu; + struct ice_hw_common_caps cached_caps; u32 num_funcs; /* cache some func_caps values that should be restored after memset */ - valid_func = func_caps->common_cap.valid_functions; - txq_first_id = func_caps->common_cap.txq_first_id; - rxq_first_id = func_caps->common_cap.rxq_first_id; - msix_vector_first_id = func_caps->common_cap.msix_vector_first_id; - max_mtu = func_caps->common_cap.max_mtu; + cached_caps = func_caps->common_cap; /* unset func capabilities */ memset(func_caps, 0, sizeof(*func_caps)); +#define ICE_RESTORE_FUNC_CAP(name) \ + func_caps->common_cap.name = cached_caps.name + /* restore cached values */ - func_caps->common_cap.valid_functions = valid_func; - func_caps->common_cap.txq_first_id = txq_first_id; - func_caps->common_cap.rxq_first_id = rxq_first_id; - func_caps->common_cap.msix_vector_first_id = msix_vector_first_id; - func_caps->common_cap.max_mtu = max_mtu; + ICE_RESTORE_FUNC_CAP(valid_functions); + ICE_RESTORE_FUNC_CAP(txq_first_id); + ICE_RESTORE_FUNC_CAP(rxq_first_id); + ICE_RESTORE_FUNC_CAP(msix_vector_first_id); + ICE_RESTORE_FUNC_CAP(max_mtu); + ICE_RESTORE_FUNC_CAP(nvm_unified_update); + ICE_RESTORE_FUNC_CAP(nvm_update_pending_nvm); + ICE_RESTORE_FUNC_CAP(nvm_update_pending_orom); + ICE_RESTORE_FUNC_CAP(nvm_update_pending_netlist); /* one Tx and one Rx queue in safe mode */ func_caps->common_cap.num_rxq = 1; @@ -2318,22 +2320,25 @@ void ice_set_safe_mode_caps(struct ice_hw *hw) func_caps->guar_num_vsi = 1; /* cache some dev_caps values that should be restored after memset */ - valid_func = dev_caps->common_cap.valid_functions; - txq_first_id = dev_caps->common_cap.txq_first_id; - rxq_first_id = dev_caps->common_cap.rxq_first_id; - msix_vector_first_id = dev_caps->common_cap.msix_vector_first_id; - max_mtu = dev_caps->common_cap.max_mtu; + cached_caps = dev_caps->common_cap; num_funcs = dev_caps->num_funcs; /* unset dev capabilities */ memset(dev_caps, 0, sizeof(*dev_caps)); +#define ICE_RESTORE_DEV_CAP(name) \ + dev_caps->common_cap.name = cached_caps.name + /* restore cached values */ - dev_caps->common_cap.valid_functions = valid_func; - dev_caps->common_cap.txq_first_id = txq_first_id; - dev_caps->common_cap.rxq_first_id = rxq_first_id; - dev_caps->common_cap.msix_vector_first_id = msix_vector_first_id; - dev_caps->common_cap.max_mtu = max_mtu; + ICE_RESTORE_DEV_CAP(valid_functions); + ICE_RESTORE_DEV_CAP(txq_first_id); + ICE_RESTORE_DEV_CAP(rxq_first_id); + ICE_RESTORE_DEV_CAP(msix_vector_first_id); + ICE_RESTORE_DEV_CAP(max_mtu); + ICE_RESTORE_DEV_CAP(nvm_unified_update); + ICE_RESTORE_DEV_CAP(nvm_update_pending_nvm); + ICE_RESTORE_DEV_CAP(nvm_update_pending_orom); + ICE_RESTORE_DEV_CAP(nvm_update_pending_netlist); dev_caps->num_funcs = num_funcs; /* one Tx and one Rx queue per function in safe mode */ diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c index deaefe00c9c0..8968fdd4816b 100644 --- a/drivers/net/ethernet/intel/ice/ice_fw_update.c +++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c @@ -289,7 +289,13 @@ ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset, return -EIO; } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, HZ, &event); + /* In most cases, firmware reports a write completion within a few + * milliseconds. However, it has been observed that a completion might + * take more than a second to complete in some cases. The timeout here + * is conservative and is intended to prevent failure to update when + * firmware is slow to respond. + */ + err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write, 15 * HZ, &event); if (err) { dev_err(dev, "Timed out waiting for firmware write completion for module 0x%02x, err %d\n", module, err); @@ -513,7 +519,7 @@ static int ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags, return -EIO; } - err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, HZ, + err = ice_aq_wait_for_event(pf, ice_aqc_opc_nvm_write_activate, 30 * HZ, &event); if (err) { dev_err(dev, "Timed out waiting for firmware to switch active flash banks, err %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index f2682776f8c8..ebbb8f54871c 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -246,7 +246,7 @@ static int ice_get_free_slot(void *array, int size, int curr) * ice_vsi_delete - delete a VSI from the switch * @vsi: pointer to VSI being removed */ -void ice_vsi_delete(struct ice_vsi *vsi) +static void ice_vsi_delete(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; struct ice_vsi_ctx *ctxt; @@ -313,7 +313,7 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) * * Returns 0 on success, negative on failure */ -int ice_vsi_clear(struct ice_vsi *vsi) +static int ice_vsi_clear(struct ice_vsi *vsi) { struct ice_pf *pf = NULL; struct device *dev; @@ -563,7 +563,7 @@ static int ice_vsi_get_qs(struct ice_vsi *vsi) * ice_vsi_put_qs - Release queues from VSI to PF * @vsi: the VSI that is going to release queues */ -void ice_vsi_put_qs(struct ice_vsi *vsi) +static void ice_vsi_put_qs(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; int i; @@ -1196,6 +1196,18 @@ static void ice_vsi_clear_rings(struct ice_vsi *vsi) { int i; + /* Avoid stale references by clearing map from vector to ring */ + if (vsi->q_vectors) { + ice_for_each_q_vector(vsi, i) { + struct ice_q_vector *q_vector = vsi->q_vectors[i]; + + if (q_vector) { + q_vector->tx.ring = NULL; + q_vector->rx.ring = NULL; + } + } + } + if (vsi->tx_rings) { for (i = 0; i < vsi->alloc_txq; i++) { if (vsi->tx_rings[i]) { @@ -2291,7 +2303,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (status) { dev_err(dev, "VSI %d failed lan queue config, error %s\n", vsi->vsi_num, ice_stat_str(status)); - goto unroll_vector_base; + goto unroll_clear_rings; } /* Add switch rule to drop all Tx Flow Control Frames, of look up diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 981f3a156c24..3da17895a2b1 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -45,10 +45,6 @@ int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena, bool vlan_promisc); void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create); -void ice_vsi_delete(struct ice_vsi *vsi); - -int ice_vsi_clear(struct ice_vsi *vsi); - #ifdef CONFIG_DCB int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc); #endif /* CONFIG_DCB */ @@ -79,8 +75,6 @@ bool ice_is_reset_in_progress(unsigned long *state); void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio); -void ice_vsi_put_qs(struct ice_vsi *vsi); - void ice_vsi_dis_irq(struct ice_vsi *vsi); void ice_vsi_free_irq(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 4634b48949bb..54a7f55eb8c1 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3169,10 +3169,8 @@ static int ice_setup_pf_sw(struct ice_pf *pf) return -EBUSY; vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); - if (!vsi) { - status = -ENOMEM; - goto unroll_vsi_setup; - } + if (!vsi) + return -ENOMEM; status = ice_cfg_netdev(vsi); if (status) { @@ -3219,12 +3217,7 @@ unroll_napi_add: } unroll_vsi_setup: - if (vsi) { - ice_vsi_free_q_vectors(vsi); - ice_vsi_delete(vsi); - ice_vsi_put_qs(vsi); - ice_vsi_clear(vsi); - } + ice_vsi_release(vsi); return status; } @@ -4522,6 +4515,7 @@ static int __maybe_unused ice_suspend(struct device *dev) } ice_clear_interrupt_scheme(pf); + pci_save_state(pdev); pci_wake_from_d3(pdev, pf->wol_ena); pci_set_power_state(pdev, PCI_D3hot); return 0; diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 3070dfdb7eb4..2d566f3c827b 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -299,18 +299,14 @@ extern char igc_driver_name[]; #define IGC_RX_HDR_LEN IGC_RXBUFFER_256 /* Transmit and receive latency (for PTP timestamps) */ -/* FIXME: These values were estimated using the ones that i225 has as - * basis, they seem to provide good numbers with ptp4l/phc2sys, but we - * need to confirm them. - */ -#define IGC_I225_TX_LATENCY_10 9542 -#define IGC_I225_TX_LATENCY_100 1024 -#define IGC_I225_TX_LATENCY_1000 178 -#define IGC_I225_TX_LATENCY_2500 64 -#define IGC_I225_RX_LATENCY_10 20662 -#define IGC_I225_RX_LATENCY_100 2213 -#define IGC_I225_RX_LATENCY_1000 448 -#define IGC_I225_RX_LATENCY_2500 160 +#define IGC_I225_TX_LATENCY_10 240 +#define IGC_I225_TX_LATENCY_100 58 +#define IGC_I225_TX_LATENCY_1000 80 +#define IGC_I225_TX_LATENCY_2500 1325 +#define IGC_I225_RX_LATENCY_10 6450 +#define IGC_I225_RX_LATENCY_100 185 +#define IGC_I225_RX_LATENCY_1000 300 +#define IGC_I225_RX_LATENCY_2500 1485 /* RX and TX descriptor control thresholds. * PTHRESH - MAC will consider prefetch if it has fewer than this number of diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 36c999250fcc..6a9b5102aa55 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -364,6 +364,7 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) struct sk_buff *skb = adapter->ptp_tx_skb; struct skb_shared_hwtstamps shhwtstamps; struct igc_hw *hw = &adapter->hw; + int adjust = 0; u64 regval; if (WARN_ON_ONCE(!skb)) @@ -373,6 +374,24 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) regval |= (u64)rd32(IGC_TXSTMPH) << 32; igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGC_I225_TX_LATENCY_10; + break; + case SPEED_100: + adjust = IGC_I225_TX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGC_I225_TX_LATENCY_1000; + break; + case SPEED_2500: + adjust = IGC_I225_TX_LATENCY_2500; + break; + } + + shhwtstamps.hwtstamp = + ktime_add_ns(shhwtstamps.hwtstamp, adjust); + /* Clear the lock early before calling skb_tstamp_tx so that * applications are not woken up before the lock bit is clear. We use * a copy of the skb pointer to ensure other threads can't change it diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 2f8a4cfc5fa1..86ca8b9ea1b8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5396,9 +5396,10 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter, return err; } -static int ixgbe_macvlan_up(struct net_device *vdev, void *data) +static int ixgbe_macvlan_up(struct net_device *vdev, + struct netdev_nested_priv *priv) { - struct ixgbe_adapter *adapter = data; + struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data; struct ixgbe_fwd_adapter *accel; if (!netif_is_macvlan(vdev)) @@ -5415,8 +5416,12 @@ static int ixgbe_macvlan_up(struct net_device *vdev, void *data) static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) { + struct netdev_nested_priv priv = { + .data = (void *)adapter, + }; + netdev_walk_all_upper_dev_rcu(adapter->netdev, - ixgbe_macvlan_up, adapter); + ixgbe_macvlan_up, &priv); } static void ixgbe_configure(struct ixgbe_adapter *adapter) @@ -9023,9 +9028,10 @@ static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter) } #endif /* CONFIG_IXGBE_DCB */ -static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data) +static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, + struct netdev_nested_priv *priv) { - struct ixgbe_adapter *adapter = data; + struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data; struct ixgbe_fwd_adapter *accel; int pool; @@ -9062,13 +9068,16 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data) static void ixgbe_defrag_macvlan_pools(struct net_device *dev) { struct ixgbe_adapter *adapter = netdev_priv(dev); + struct netdev_nested_priv priv = { + .data = (void *)adapter, + }; /* flush any stale bits out of the fwd bitmask */ bitmap_clear(adapter->fwd_bitmask, 1, 63); /* walk through upper devices reassigning pools */ netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool, - adapter); + &priv); } /** @@ -9242,14 +9251,18 @@ struct upper_walk_data { u8 queue; }; -static int get_macvlan_queue(struct net_device *upper, void *_data) +static int get_macvlan_queue(struct net_device *upper, + struct netdev_nested_priv *priv) { if (netif_is_macvlan(upper)) { struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper); - struct upper_walk_data *data = _data; - struct ixgbe_adapter *adapter = data->adapter; - int ifindex = data->ifindex; + struct ixgbe_adapter *adapter; + struct upper_walk_data *data; + int ifindex; + data = (struct upper_walk_data *)priv->data; + ifindex = data->ifindex; + adapter = data->adapter; if (vadapter && upper->ifindex == ifindex) { data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx; data->action = data->queue; @@ -9265,6 +9278,7 @@ static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex, { struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; unsigned int num_vfs = adapter->num_vfs, vf; + struct netdev_nested_priv priv; struct upper_walk_data data; struct net_device *upper; @@ -9284,8 +9298,9 @@ static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex, data.ifindex = ifindex; data.action = 0; data.queue = 0; + priv.data = (void *)&data; if (netdev_walk_all_upper_dev_rcu(adapter->netdev, - get_macvlan_queue, &data)) { + get_macvlan_queue, &priv)) { *action = data.action; *queue = data.queue; diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 1645e4e7ebdb..51ed8a54d380 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -230,8 +230,8 @@ static int xrx200_poll_rx(struct napi_struct *napi, int budget) } if (rx < budget) { - napi_complete(&ch->napi); - ltq_dma_enable_irq(&ch->dma); + if (napi_complete_done(&ch->napi, rx)) + ltq_dma_enable_irq(&ch->dma); } return rx; @@ -245,6 +245,7 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget) int pkts = 0; int bytes = 0; + netif_tx_lock(net_dev); while (pkts < budget) { struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->tx_free]; @@ -268,9 +269,13 @@ static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget) net_dev->stats.tx_bytes += bytes; netdev_completed_queue(ch->priv->net_dev, pkts, bytes); + netif_tx_unlock(net_dev); + if (netif_queue_stopped(net_dev)) + netif_wake_queue(net_dev); + if (pkts < budget) { - napi_complete(&ch->napi); - ltq_dma_enable_irq(&ch->dma); + if (napi_complete_done(&ch->napi, pkts)) + ltq_dma_enable_irq(&ch->dma); } return pkts; @@ -342,10 +347,12 @@ static irqreturn_t xrx200_dma_irq(int irq, void *ptr) { struct xrx200_chan *ch = ptr; - ltq_dma_disable_irq(&ch->dma); - ltq_dma_ack_irq(&ch->dma); + if (napi_schedule_prep(&ch->napi)) { + __napi_schedule(&ch->napi); + ltq_dma_disable_irq(&ch->dma); + } - napi_schedule(&ch->napi); + ltq_dma_ack_irq(&ch->dma); return IRQ_HANDLED; } @@ -499,7 +506,7 @@ static int xrx200_probe(struct platform_device *pdev) /* setup NAPI */ netif_napi_add(net_dev, &priv->chan_rx.napi, xrx200_poll_rx, 32); - netif_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32); + netif_tx_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32); platform_set_drvdata(pdev, priv); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index dfcb1767acbb..5bf0409f5d42 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2029,11 +2029,11 @@ mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq, struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i; - page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data), - sync_len, napi); for (i = 0; i < sinfo->nr_frags; i++) page_pool_put_full_page(rxq->page_pool, skb_frag_page(&sinfo->frags[i]), napi); + page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data), + sync_len, napi); } static int @@ -2383,8 +2383,12 @@ static int mvneta_rx_swbm(struct napi_struct *napi, mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf, &size, page, &ps); } else { - if (unlikely(!xdp_buf.data_hard_start)) + if (unlikely(!xdp_buf.data_hard_start)) { + rx_desc->buf_phys_addr = 0; + page_pool_put_full_page(rxq->page_pool, page, + true); continue; + } mvneta_swbm_add_rx_fragment(pp, rx_desc, rxq, &xdp_buf, &size, page); @@ -3396,24 +3400,15 @@ static int mvneta_txq_sw_init(struct mvneta_port *pp, txq->last_desc = txq->size - 1; txq->buf = kmalloc_array(txq->size, sizeof(*txq->buf), GFP_KERNEL); - if (!txq->buf) { - dma_free_coherent(pp->dev->dev.parent, - txq->size * MVNETA_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); + if (!txq->buf) return -ENOMEM; - } /* Allocate DMA buffers for TSO MAC/IP/TCP headers */ txq->tso_hdrs = dma_alloc_coherent(pp->dev->dev.parent, txq->size * TSO_HEADER_SIZE, &txq->tso_hdrs_phys, GFP_KERNEL); - if (!txq->tso_hdrs) { - kfree(txq->buf); - dma_free_coherent(pp->dev->dev.parent, - txq->size * MVNETA_DESC_ALIGNED_SIZE, - txq->descs, txq->descs_phys); + if (!txq->tso_hdrs) return -ENOMEM; - } /* Setup XPS mapping */ if (txq_number > 1) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c index 387e33fa417a..2718fe201c14 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c @@ -17,7 +17,7 @@ static const u16 msgs_offset = ALIGN(sizeof(struct mbox_hdr), MBOX_MSG_ALIGN); -void otx2_mbox_reset(struct otx2_mbox *mbox, int devid) +void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid) { void *hw_mbase = mbox->hwbase + (devid * MBOX_SIZE); struct otx2_mbox_dev *mdev = &mbox->dev[devid]; @@ -26,13 +26,21 @@ void otx2_mbox_reset(struct otx2_mbox *mbox, int devid) tx_hdr = hw_mbase + mbox->tx_start; rx_hdr = hw_mbase + mbox->rx_start; - spin_lock(&mdev->mbox_lock); mdev->msg_size = 0; mdev->rsp_size = 0; tx_hdr->num_msgs = 0; tx_hdr->msg_size = 0; rx_hdr->num_msgs = 0; rx_hdr->msg_size = 0; +} +EXPORT_SYMBOL(__otx2_mbox_reset); + +void otx2_mbox_reset(struct otx2_mbox *mbox, int devid) +{ + struct otx2_mbox_dev *mdev = &mbox->dev[devid]; + + spin_lock(&mdev->mbox_lock); + __otx2_mbox_reset(mbox, devid); spin_unlock(&mdev->mbox_lock); } EXPORT_SYMBOL(otx2_mbox_reset); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 6dfd0f90cd70..ab433789d2c3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -93,6 +93,7 @@ struct mbox_msghdr { }; void otx2_mbox_reset(struct otx2_mbox *mbox, int devid); +void __otx2_mbox_reset(struct otx2_mbox *mbox, int devid); void otx2_mbox_destroy(struct otx2_mbox *mbox); int otx2_mbox_init(struct otx2_mbox *mbox, void __force *hwbase, struct pci_dev *pdev, void __force *reg_base, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index dcf25a092008..b89dde2c8b08 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -463,6 +463,7 @@ void rvu_nix_freemem(struct rvu *rvu); int rvu_get_nixlf_count(struct rvu *rvu); void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf); int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr); +int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add); /* NPC APIs */ int rvu_npc_init(struct rvu *rvu); @@ -477,7 +478,7 @@ void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan); -void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc); +void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable); int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 01a793105599..0fc70824fd6b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -17,7 +17,6 @@ #include "npc.h" #include "cgx.h" -static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add); static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req, int type, int chan_id); @@ -2020,7 +2019,7 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list, return 0; } -static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) +int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) { int err = 0, idx, next_idx, last_idx; struct nix_mce_list *mce_list; @@ -2065,7 +2064,7 @@ static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) /* Disable MCAM entry in NPC */ if (!mce_list->count) { - rvu_npc_disable_bcast_entry(rvu, pcifunc); + rvu_npc_enable_bcast_entry(rvu, pcifunc, false); goto end; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 0a214084406a..fbaf9bcd83f2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -530,7 +530,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, NIX_INTF_RX, &entry, true); } -void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc) +void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable) { struct npc_mcam *mcam = &rvu->hw->mcam; int blkaddr, index; @@ -543,7 +543,7 @@ void rvu_npc_disable_bcast_entry(struct rvu *rvu, u16 pcifunc) pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; index = npc_get_nixlf_mcam_index(mcam, pcifunc, 0, NIXLF_BCAST_ENTRY); - npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false); + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); } void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, @@ -622,23 +622,35 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc, nixlf, NIXLF_UCAST_ENTRY); npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); - /* For PF, ena/dis promisc and bcast MCAM match entries */ - if (pcifunc & RVU_PFVF_FUNC_MASK) + /* For PF, ena/dis promisc and bcast MCAM match entries. + * For VFs add/delete from bcast list when RX multicast + * feature is present. + */ + if (pcifunc & RVU_PFVF_FUNC_MASK && !rvu->hw->cap.nix_rx_multicast) return; /* For bcast, enable/disable only if it's action is not * packet replication, incase if action is replication - * then this PF's nixlf is removed from bcast replication + * then this PF/VF's nixlf is removed from bcast replication * list. */ - index = npc_get_nixlf_mcam_index(mcam, pcifunc, + index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK, nixlf, NIXLF_BCAST_ENTRY); bank = npc_get_bank(mcam, index); *(u64 *)&action = rvu_read64(rvu, blkaddr, NPC_AF_MCAMEX_BANKX_ACTION(index & (mcam->banksize - 1), bank)); - if (action.op != NIX_RX_ACTIONOP_MCAST) + + /* VFs will not have BCAST entry */ + if (action.op != NIX_RX_ACTIONOP_MCAST && + !(pcifunc & RVU_PFVF_FUNC_MASK)) { npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); + } else { + nix_update_bcast_mce_list(rvu, pcifunc, enable); + /* Enable PF's BCAST entry for packet replication */ + rvu_npc_enable_bcast_entry(rvu, pcifunc, enable); + } + if (enable) rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf); else diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 75a8c407e815..2fb45670aca4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -370,8 +370,8 @@ static int otx2_forward_vf_mbox_msgs(struct otx2_nic *pf, dst_mbox = &pf->mbox; dst_size = dst_mbox->mbox.tx_size - ALIGN(sizeof(*mbox_hdr), MBOX_MSG_ALIGN); - /* Check if msgs fit into destination area */ - if (mbox_hdr->msg_size > dst_size) + /* Check if msgs fit into destination area and has valid size */ + if (mbox_hdr->msg_size > dst_size || !mbox_hdr->msg_size) return -EINVAL; dst_mdev = &dst_mbox->mbox.dev[0]; @@ -526,10 +526,10 @@ static void otx2_pfvf_mbox_up_handler(struct work_struct *work) end: offset = mbox->rx_start + msg->next_msgoff; + if (mdev->msgs_acked == (vf_mbox->up_num_msgs - 1)) + __otx2_mbox_reset(mbox, 0); mdev->msgs_acked++; } - - otx2_mbox_reset(mbox, vf_idx); } static irqreturn_t otx2_pfvf_mbox_intr_handler(int irq, void *pf_irq) @@ -803,10 +803,11 @@ static void otx2_pfaf_mbox_handler(struct work_struct *work) msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2_process_pfaf_mbox_msg(pf, msg); offset = mbox->rx_start + msg->next_msgoff; + if (mdev->msgs_acked == (af_mbox->num_msgs - 1)) + __otx2_mbox_reset(mbox, 0); mdev->msgs_acked++; } - otx2_mbox_reset(mbox, 0); } static void otx2_handle_link_event(struct otx2_nic *pf) @@ -1560,10 +1561,13 @@ int otx2_open(struct net_device *netdev) err = otx2_rxtx_enable(pf, true); if (err) - goto err_free_cints; + goto err_tx_stop_queues; return 0; +err_tx_stop_queues: + netif_tx_stop_all_queues(netdev); + netif_carrier_off(netdev); err_free_cints: otx2_free_cints(pf, qidx); vec = pci_irq_vector(pf->pdev, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index 3a5b34a2a7a6..e46834e043be 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -524,6 +524,7 @@ static void otx2_sqe_add_hdr(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, sqe_hdr->ol3type = NIX_SENDL3TYPE_IP4_CKSUM; } else if (skb->protocol == htons(ETH_P_IPV6)) { proto = ipv6_hdr(skb)->nexthdr; + sqe_hdr->ol3type = NIX_SENDL3TYPE_IP6; } if (proto == IPPROTO_TCP) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 92a3db69a6cd..2f90f1721441 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -99,10 +99,10 @@ static void otx2vf_vfaf_mbox_handler(struct work_struct *work) msg = (struct mbox_msghdr *)(mdev->mbase + offset); otx2vf_process_vfaf_mbox_msg(af_mbox->pfvf, msg); offset = mbox->rx_start + msg->next_msgoff; + if (mdev->msgs_acked == (af_mbox->num_msgs - 1)) + __otx2_mbox_reset(mbox, 0); mdev->msgs_acked++; } - - otx2_mbox_reset(mbox, 0); } static int otx2vf_process_mbox_msg_up(struct otx2_nic *vf, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 1d91a0d0ab1d..2d1f4b3be9bf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -69,12 +69,10 @@ enum { MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR = 0x10, }; -static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, - struct mlx5_cmd_msg *in, - struct mlx5_cmd_msg *out, - void *uout, int uout_size, - mlx5_cmd_cbk_t cbk, - void *context, int page_queue) +static struct mlx5_cmd_work_ent * +cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in, + struct mlx5_cmd_msg *out, void *uout, int uout_size, + mlx5_cmd_cbk_t cbk, void *context, int page_queue) { gfp_t alloc_flags = cbk ? GFP_ATOMIC : GFP_KERNEL; struct mlx5_cmd_work_ent *ent; @@ -83,6 +81,7 @@ static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, if (!ent) return ERR_PTR(-ENOMEM); + ent->idx = -EINVAL; ent->in = in; ent->out = out; ent->uout = uout; @@ -91,10 +90,16 @@ static struct mlx5_cmd_work_ent *alloc_cmd(struct mlx5_cmd *cmd, ent->context = context; ent->cmd = cmd; ent->page_queue = page_queue; + refcount_set(&ent->refcnt, 1); return ent; } +static void cmd_free_ent(struct mlx5_cmd_work_ent *ent) +{ + kfree(ent); +} + static u8 alloc_token(struct mlx5_cmd *cmd) { u8 token; @@ -109,7 +114,7 @@ static u8 alloc_token(struct mlx5_cmd *cmd) return token; } -static int alloc_ent(struct mlx5_cmd *cmd) +static int cmd_alloc_index(struct mlx5_cmd *cmd) { unsigned long flags; int ret; @@ -123,7 +128,7 @@ static int alloc_ent(struct mlx5_cmd *cmd) return ret < cmd->max_reg_cmds ? ret : -ENOMEM; } -static void free_ent(struct mlx5_cmd *cmd, int idx) +static void cmd_free_index(struct mlx5_cmd *cmd, int idx) { unsigned long flags; @@ -132,6 +137,22 @@ static void free_ent(struct mlx5_cmd *cmd, int idx) spin_unlock_irqrestore(&cmd->alloc_lock, flags); } +static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) +{ + refcount_inc(&ent->refcnt); +} + +static void cmd_ent_put(struct mlx5_cmd_work_ent *ent) +{ + if (!refcount_dec_and_test(&ent->refcnt)) + return; + + if (ent->idx >= 0) + cmd_free_index(ent->cmd, ent->idx); + + cmd_free_ent(ent); +} + static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) { return cmd->cmd_buf + (idx << cmd->log_stride); @@ -219,11 +240,6 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent) ent->ret = -ETIMEDOUT; } -static void free_cmd(struct mlx5_cmd_work_ent *ent) -{ - kfree(ent); -} - static int verify_signature(struct mlx5_cmd_work_ent *ent) { struct mlx5_cmd_mailbox *next = ent->out->next; @@ -837,11 +853,22 @@ static void cb_timeout_handler(struct work_struct *work) struct mlx5_core_dev *dev = container_of(ent->cmd, struct mlx5_core_dev, cmd); + mlx5_cmd_eq_recover(dev); + + /* Maybe got handled by eq recover ? */ + if (!test_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state)) { + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, recovered after timeout\n", ent->idx, + mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + goto out; /* phew, already handled */ + } + ent->ret = -ETIMEDOUT; - mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n", - mlx5_command_str(msg_to_opcode(ent->in)), - msg_to_opcode(ent->in)); + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n", + ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); + +out: + cmd_ent_put(ent); /* for the cmd_ent_get() took on schedule delayed work */ } static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg); @@ -856,6 +883,32 @@ static bool opcode_allowed(struct mlx5_cmd *cmd, u16 opcode) return cmd->allowed_opcode == opcode; } +static int cmd_alloc_index_retry(struct mlx5_cmd *cmd) +{ + unsigned long alloc_end = jiffies + msecs_to_jiffies(1000); + int idx; + +retry: + idx = cmd_alloc_index(cmd); + if (idx < 0 && time_before(jiffies, alloc_end)) { + /* Index allocation can fail on heavy load of commands. This is a temporary + * situation as the current command already holds the semaphore, meaning that + * another command completion is being handled and it is expected to release + * the entry index soon. + */ + cpu_relax(); + goto retry; + } + return idx; +} + +bool mlx5_cmd_is_down(struct mlx5_core_dev *dev) +{ + return pci_channel_offline(dev->pdev) || + dev->cmd.state != MLX5_CMDIF_STATE_UP || + dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR; +} + static void cmd_work_handler(struct work_struct *work) { struct mlx5_cmd_work_ent *ent = container_of(work, struct mlx5_cmd_work_ent, work); @@ -873,14 +926,14 @@ static void cmd_work_handler(struct work_struct *work) sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem; down(sem); if (!ent->page_queue) { - alloc_ret = alloc_ent(cmd); + alloc_ret = cmd_alloc_index_retry(cmd); if (alloc_ret < 0) { mlx5_core_err_rl(dev, "failed to allocate command entry\n"); if (ent->callback) { ent->callback(-EAGAIN, ent->context); mlx5_free_cmd_msg(dev, ent->out); free_msg(dev, ent->in); - free_cmd(ent); + cmd_ent_put(ent); } else { ent->ret = -EAGAIN; complete(&ent->done); @@ -916,15 +969,12 @@ static void cmd_work_handler(struct work_struct *work) ent->ts1 = ktime_get_ns(); cmd_mode = cmd->mode; - if (ent->callback) - schedule_delayed_work(&ent->cb_timeout_work, cb_timeout); + if (ent->callback && schedule_delayed_work(&ent->cb_timeout_work, cb_timeout)) + cmd_ent_get(ent); set_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state); /* Skip sending command to fw if internal error */ - if (pci_channel_offline(dev->pdev) || - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR || - cmd->state != MLX5_CMDIF_STATE_UP || - !opcode_allowed(&dev->cmd, ent->op)) { + if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, ent->op)) { u8 status = 0; u32 drv_synd; @@ -933,13 +983,10 @@ 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; } + cmd_ent_get(ent); /* for the _real_ FW event on completion */ /* ring doorbell after the descriptor is valid */ mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); @@ -983,6 +1030,35 @@ static const char *deliv_status_to_str(u8 status) } } +enum { + MLX5_CMD_TIMEOUT_RECOVER_MSEC = 5 * 1000, +}; + +static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev, + struct mlx5_cmd_work_ent *ent) +{ + unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_RECOVER_MSEC); + + mlx5_cmd_eq_recover(dev); + + /* Re-wait on the ent->done after executing the recovery flow. If the + * recovery flow (or any other recovery flow running simultaneously) + * has recovered an EQE, it should cause the entry to be completed by + * the command interface. + */ + if (wait_for_completion_timeout(&ent->done, timeout)) { + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) recovered after timeout\n", ent->idx, + mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + return; + } + + mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) No done completion\n", ent->idx, + mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in)); + + ent->ret = -ETIMEDOUT; + mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); +} + static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) { unsigned long timeout = msecs_to_jiffies(MLX5_CMD_TIMEOUT_MSEC); @@ -994,12 +1070,10 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent) ent->ret = -ECANCELED; goto out_err; } - if (cmd->mode == CMD_MODE_POLLING || ent->polling) { + if (cmd->mode == CMD_MODE_POLLING || ent->polling) wait_for_completion(&ent->done); - } else if (!wait_for_completion_timeout(&ent->done, timeout)) { - ent->ret = -ETIMEDOUT; - mlx5_cmd_comp_handler(dev, 1UL << ent->idx, true); - } + else if (!wait_for_completion_timeout(&ent->done, timeout)) + wait_func_handle_exec_timeout(dev, ent); out_err: err = ent->ret; @@ -1039,11 +1113,16 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, if (callback && page_queue) return -EINVAL; - ent = alloc_cmd(cmd, in, out, uout, uout_size, callback, context, - page_queue); + ent = cmd_alloc_ent(cmd, in, out, uout, uout_size, + callback, context, page_queue); if (IS_ERR(ent)) return PTR_ERR(ent); + /* put for this ent is when consumed, depending on the use case + * 1) (!callback) blocking flow: by caller after wait_func completes + * 2) (callback) flow: by mlx5_cmd_comp_handler() when ent is handled + */ + ent->token = token; ent->polling = force_polling; @@ -1062,12 +1141,10 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, } if (callback) - goto out; + goto out; /* mlx5_cmd_comp_handler() will put(ent) */ err = wait_func(dev, ent); - if (err == -ETIMEDOUT) - goto out; - if (err == -ECANCELED) + if (err == -ETIMEDOUT || err == -ECANCELED) goto out_free; ds = ent->ts2 - ent->ts1; @@ -1085,7 +1162,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in, *status = ent->status; out_free: - free_cmd(ent); + cmd_ent_put(ent); out: return err; } @@ -1516,14 +1593,19 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force if (!forced) { mlx5_core_err(dev, "Command completion arrived after timeout (entry idx = %d).\n", ent->idx); - free_ent(cmd, ent->idx); - free_cmd(ent); + cmd_ent_put(ent); } continue; } - if (ent->callback) - cancel_delayed_work(&ent->cb_timeout_work); + if (ent->callback && cancel_delayed_work(&ent->cb_timeout_work)) + cmd_ent_put(ent); /* timeout work was canceled */ + + if (!forced || /* Real FW completion */ + pci_channel_offline(dev->pdev) || /* FW is inaccessible */ + dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + cmd_ent_put(ent); + if (ent->page_queue) sem = &cmd->pages_sem; else @@ -1545,10 +1627,6 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force ent->ret, deliv_status_to_str(ent->status), ent->status); } - /* only real completion will free the entry slot */ - if (!forced) - free_ent(cmd, ent->idx); - if (ent->callback) { ds = ent->ts2 - ent->ts1; if (ent->op < MLX5_CMD_OP_MAX) { @@ -1576,10 +1654,13 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force free_msg(dev, ent->in); err = err ? err : ent->status; - if (!forced) - free_cmd(ent); + /* final consumer is done, release ent */ + cmd_ent_put(ent); callback(err, context); } else { + /* release wait_func() so mlx5_cmd_invoke() + * can make the final ent_put() + */ complete(&ent->done); } up(sem); @@ -1589,8 +1670,11 @@ static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool force void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) { + struct mlx5_cmd *cmd = &dev->cmd; + unsigned long bitmask; unsigned long flags; u64 vector; + int i; /* wait for pending handlers to complete */ mlx5_eq_synchronize_cmd_irq(dev); @@ -1599,11 +1683,20 @@ void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev) if (!vector) goto no_trig; + bitmask = vector; + /* we must increment the allocated entries refcount before triggering the completions + * to guarantee pending commands will not get freed in the meanwhile. + * For that reason, it also has to be done inside the alloc_lock. + */ + for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + cmd_ent_get(cmd->ent_arr[i]); vector |= MLX5_TRIGGERED_CMD_COMP; spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); mlx5_core_dbg(dev, "vector 0x%llx\n", vector); mlx5_cmd_comp_handler(dev, vector, true); + for_each_set_bit(i, &bitmask, (1 << cmd->log_sz)) + cmd_ent_put(cmd->ent_arr[i]); return; no_trig: @@ -1711,10 +1804,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, u8 token; opcode = MLX5_GET(mbox_in, in, opcode); - if (pci_channel_offline(dev->pdev) || - dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR || - dev->cmd.state != MLX5_CMDIF_STATE_UP || - !opcode_allowed(&dev->cmd, opcode)) { + if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode)) { err = mlx5_internal_err_ret_value(dev, opcode, &drv_synd, &status); MLX5_SET(mbox_out, out, status, status); MLX5_SET(mbox_out, out, syndrome, drv_synd); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 0cc2080fd847..356f5852955f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -91,7 +91,12 @@ struct page_pool; #define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER) #define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2) -#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE, 8)) +/* Add another page to MLX5E_REQUIRED_WQE_MTTS as a buffer between + * WQEs, This page will absorb write overflow by the hardware, when + * receiving packets larger than MTU. These oversize packets are + * dropped by the driver at a later stage. + */ +#define MLX5E_REQUIRED_WQE_MTTS (ALIGN(MLX5_MPWRQ_PAGES_PER_WQE + 1, 8)) #define MLX5E_LOG_ALIGNED_MPWQE_PPW (ilog2(MLX5E_REQUIRED_WQE_MTTS)) #define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS) #define MLX5E_MAX_RQ_NUM_MTTS \ @@ -600,7 +605,7 @@ struct mlx5e_rq { struct dim dim; /* Dynamic Interrupt Moderation */ /* XDP */ - struct bpf_prog *xdp_prog; + struct bpf_prog __rcu *xdp_prog; struct mlx5e_xdpsq *xdpsq; DECLARE_BITMAP(flags, 8); struct page_pool *page_pool; @@ -617,6 +622,7 @@ struct mlx5e_rq { u32 rqn; struct mlx5_core_dev *mdev; struct mlx5_core_mkey umr_mkey; + struct mlx5e_dma_info wqe_overflow; /* XDP read-mostly */ struct xdp_rxq_info xdp_rxq; @@ -1005,7 +1011,6 @@ int mlx5e_update_nic_rx(struct mlx5e_priv *priv); void mlx5e_update_carrier(struct mlx5e_priv *priv); int mlx5e_close(struct net_device *netdev); int mlx5e_open(struct net_device *netdev); -void mlx5e_update_ndo_stats(struct mlx5e_priv *priv); void mlx5e_queue_update_stats(struct mlx5e_priv *priv); int mlx5e_bits_invert(unsigned long a, int size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c index 8fe8b4d6ad1c..254c84739046 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c @@ -51,7 +51,7 @@ static void mlx5e_monitor_counters_work(struct work_struct *work) monitor_counters_work); mutex_lock(&priv->state_lock); - mlx5e_update_ndo_stats(priv); + mlx5e_stats_update_ndo_stats(priv); mutex_unlock(&priv->state_lock); mlx5e_monitor_counter_arm(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 5de1cb9f5330..308fd279669e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -490,11 +490,8 @@ bool mlx5e_fec_in_caps(struct mlx5_core_dev *dev, int fec_policy) int err; int i; - if (!MLX5_CAP_GEN(dev, pcam_reg)) - return -EOPNOTSUPP; - - if (!MLX5_CAP_PCAM_REG(dev, pplm)) - return -EOPNOTSUPP; + if (!MLX5_CAP_GEN(dev, pcam_reg) || !MLX5_CAP_PCAM_REG(dev, pplm)) + return false; MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); @@ -572,6 +569,9 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy) if (fec_policy >= (1 << MLX5E_FEC_LLRS_272_257_1) && !fec_50g_per_lane) return -EOPNOTSUPP; + if (fec_policy && !mlx5e_fec_in_caps(dev, fec_policy)) + return -EOPNOTSUPP; + MLX5_SET(pplm_reg, in, local_port, 1); err = mlx5_core_access_reg(dev, in, sz, out, sz, MLX5_REG_PPLM, 0, 0); if (err) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c index 906292035088..58e27038c947 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/neigh.c @@ -110,11 +110,25 @@ static void mlx5e_rep_neigh_stats_work(struct work_struct *work) rtnl_unlock(); } +struct neigh_update_work { + struct work_struct work; + struct neighbour *n; + struct mlx5e_neigh_hash_entry *nhe; +}; + +static void mlx5e_release_neigh_update_work(struct neigh_update_work *update_work) +{ + neigh_release(update_work->n); + mlx5e_rep_neigh_entry_release(update_work->nhe); + kfree(update_work); +} + static void mlx5e_rep_neigh_update(struct work_struct *work) { - struct mlx5e_neigh_hash_entry *nhe = - container_of(work, struct mlx5e_neigh_hash_entry, neigh_update_work); - struct neighbour *n = nhe->n; + struct neigh_update_work *update_work = container_of(work, struct neigh_update_work, + work); + struct mlx5e_neigh_hash_entry *nhe = update_work->nhe; + struct neighbour *n = update_work->n; struct mlx5e_encap_entry *e; unsigned char ha[ETH_ALEN]; struct mlx5e_priv *priv; @@ -146,30 +160,42 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) mlx5e_rep_update_flows(priv, e, neigh_connected, ha); mlx5e_encap_put(priv, e); } - mlx5e_rep_neigh_entry_release(nhe); rtnl_unlock(); - neigh_release(n); + mlx5e_release_neigh_update_work(update_work); } -static void mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv, - struct mlx5e_neigh_hash_entry *nhe, - struct neighbour *n) +static struct neigh_update_work *mlx5e_alloc_neigh_update_work(struct mlx5e_priv *priv, + struct neighbour *n) { - /* Take a reference to ensure the neighbour and mlx5 encap - * entry won't be destructed until we drop the reference in - * delayed work. - */ - neigh_hold(n); + struct neigh_update_work *update_work; + struct mlx5e_neigh_hash_entry *nhe; + struct mlx5e_neigh m_neigh = {}; - /* This assignment is valid as long as the the neigh reference - * is taken - */ - nhe->n = n; + update_work = kzalloc(sizeof(*update_work), GFP_ATOMIC); + if (WARN_ON(!update_work)) + return NULL; - if (!queue_work(priv->wq, &nhe->neigh_update_work)) { - mlx5e_rep_neigh_entry_release(nhe); - neigh_release(n); + m_neigh.dev = n->dev; + m_neigh.family = n->ops->family; + memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len); + + /* Obtain reference to nhe as last step in order not to release it in + * atomic context. + */ + rcu_read_lock(); + nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh); + rcu_read_unlock(); + if (!nhe) { + kfree(update_work); + return NULL; } + + INIT_WORK(&update_work->work, mlx5e_rep_neigh_update); + neigh_hold(n); + update_work->n = n; + update_work->nhe = nhe; + + return update_work; } static int mlx5e_rep_netevent_event(struct notifier_block *nb, @@ -181,7 +207,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_neigh_hash_entry *nhe = NULL; - struct mlx5e_neigh m_neigh = {}; + struct neigh_update_work *update_work; struct neigh_parms *p; struct neighbour *n; bool found = false; @@ -196,17 +222,11 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, #endif return NOTIFY_DONE; - m_neigh.dev = n->dev; - m_neigh.family = n->ops->family; - memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len); - - rcu_read_lock(); - nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh); - rcu_read_unlock(); - if (!nhe) + update_work = mlx5e_alloc_neigh_update_work(priv, n); + if (!update_work) return NOTIFY_DONE; - mlx5e_rep_queue_neigh_update_work(priv, nhe, n); + queue_work(priv->wq, &update_work->work); break; case NETEVENT_DELAY_PROBE_TIME_UPDATE: @@ -352,7 +372,6 @@ int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv, (*nhe)->priv = priv; memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh)); - INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update); spin_lock_init(&(*nhe)->encap_list_lock); INIT_LIST_HEAD(&(*nhe)->encap_list); refcount_set(&(*nhe)->refcnt, 1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index c6bc9224c3b1..a8be40cbe325 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -246,8 +246,10 @@ mlx5_tc_ct_rule_to_tuple_nat(struct mlx5_ct_tuple *tuple, case FLOW_ACT_MANGLE_HDR_TYPE_IP6: ip6_offset = (offset - offsetof(struct ipv6hdr, saddr)); ip6_offset /= 4; - if (ip6_offset < 8) + if (ip6_offset < 4) tuple->ip.src_v6.s6_addr32[ip6_offset] = cpu_to_be32(val); + else if (ip6_offset < 8) + tuple->ip.dst_v6.s6_addr32[ip6_offset - 4] = cpu_to_be32(val); else return -EOPNOTSUPP; break; @@ -699,6 +701,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, err_rule: mlx5e_mod_hdr_detach(ct_priv->esw->dev, &esw->offloads.mod_hdr, zone_rule->mh); + mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id); err_mod_hdr: kfree(spec); return err; @@ -958,12 +961,22 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv, return 0; } +void mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr) +{ + struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv); + + if (!ct_priv || !ct_attr->ct_labels_id) + return; + + mapping_remove(ct_priv->labels_mapping, ct_attr->ct_labels_id); +} + int -mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct flow_cls_offload *f, - struct mlx5_ct_attr *ct_attr, - struct netlink_ext_ack *extack) +mlx5_tc_ct_match_add(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct flow_cls_offload *f, + struct mlx5_ct_attr *ct_attr, + struct netlink_ext_ack *extack) { struct mlx5_tc_ct_priv *ct_priv = mlx5_tc_ct_get_ct_priv(priv); struct flow_rule *rule = flow_cls_offload_flow_rule(f); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h index 3baef917a677..708c216325d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h @@ -87,12 +87,15 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv); void mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv); +void +mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr); + int -mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct flow_cls_offload *f, - struct mlx5_ct_attr *ct_attr, - struct netlink_ext_ack *extack); +mlx5_tc_ct_match_add(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct flow_cls_offload *f, + struct mlx5_ct_attr *ct_attr, + struct netlink_ext_ack *extack); int mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec); @@ -130,12 +133,15 @@ mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv) { } +static inline void +mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr) {} + static inline int -mlx5_tc_ct_parse_match(struct mlx5e_priv *priv, - struct mlx5_flow_spec *spec, - struct flow_cls_offload *f, - struct mlx5_ct_attr *ct_attr, - struct netlink_ext_ack *extack) +mlx5_tc_ct_match_add(struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec, + struct flow_cls_offload *f, + struct mlx5_ct_attr *ct_attr, + struct netlink_ext_ack *extack) { struct flow_rule *rule = flow_cls_offload_flow_rule(f); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 9334c9c3e208..24336c60123a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -20,6 +20,11 @@ enum mlx5e_icosq_wqe_type { }; /* General */ +static inline bool mlx5e_skb_is_multicast(struct sk_buff *skb) +{ + return skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST; +} + void mlx5e_trigger_irq(struct mlx5e_icosq *sq); void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe); void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 0e6946fc121f..b28df21981a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -122,7 +122,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, u32 *len, struct xdp_buff *xdp) { - struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); + struct bpf_prog *prog = rcu_dereference(rq->xdp_prog); u32 act; int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index a33a1f762c70..40db27bf790b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -31,7 +31,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, { struct xdp_buff *xdp = wi->umr.dma_info[page_idx].xsk; u32 cqe_bcnt32 = cqe_bcnt; - bool consumed; /* Check packet size. Note LRO doesn't use linear SKB */ if (unlikely(cqe_bcnt > rq->hw_mtu)) { @@ -51,10 +50,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, xsk_buff_dma_sync_for_cpu(xdp); prefetch(xdp->data); - rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp); - rcu_read_unlock(); - /* Possible flows: * - XDP_REDIRECT to XSKMAP: * The page is owned by the userspace from now. @@ -70,7 +65,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, * allocated first from the Reuse Ring, so it has enough space. */ - if (likely(consumed)) { + if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt32, xdp))) { if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))) __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */ return NULL; /* page/packet was consumed by XDP */ @@ -88,7 +83,6 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, u32 cqe_bcnt) { struct xdp_buff *xdp = wi->di->xsk; - bool consumed; /* wi->offset is not used in this function, because xdp->data and the * DMA address point directly to the necessary place. Furthermore, the @@ -107,11 +101,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, return NULL; } - rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp); - rcu_read_unlock(); - - if (likely(consumed)) + if (likely(mlx5e_xdp_handle(rq, NULL, &cqe_bcnt, xdp))) return NULL; /* page/packet was consumed by XDP */ /* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index dd9df519d383..55e65a438de7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -106,8 +106,7 @@ err_free_cparam: void mlx5e_close_xsk(struct mlx5e_channel *c) { clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state); - napi_synchronize(&c->napi); - synchronize_rcu(); /* Sync with the XSK wakeup. */ + synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */ mlx5e_close_rq(&c->xskrq); mlx5e_close_cq(&c->xskrq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c index acf6d80a6bb7..6bbfcf18107d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_rx.c @@ -234,7 +234,7 @@ mlx5e_get_ktls_rx_priv_ctx(struct tls_context *tls_ctx) /* Re-sync */ /* Runs in work context */ -static struct mlx5_wqe_ctrl_seg * +static int resync_post_get_progress_params(struct mlx5e_icosq *sq, struct mlx5e_ktls_offload_context_rx *priv_rx) { @@ -258,15 +258,19 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(pdev, buf->dma_addr))) { err = -ENOMEM; - goto err_out; + goto err_free; } buf->priv_rx = priv_rx; BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1); + + spin_lock(&sq->channel->async_icosq_lock); + if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { + spin_unlock(&sq->channel->async_icosq_lock); err = -ENOSPC; - goto err_out; + goto err_dma_unmap; } pi = mlx5e_icosq_get_next_pi(sq, 1); @@ -294,12 +298,18 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, }; icosq_fill_wi(sq, pi, &wi); sq->pc++; + mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); + spin_unlock(&sq->channel->async_icosq_lock); - return cseg; + return 0; +err_dma_unmap: + dma_unmap_single(pdev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); +err_free: + kfree(buf); err_out: priv_rx->stats->tls_resync_req_skip++; - return ERR_PTR(err); + return err; } /* Function is called with elevated refcount. @@ -309,10 +319,8 @@ static void resync_handle_work(struct work_struct *work) { struct mlx5e_ktls_offload_context_rx *priv_rx; struct mlx5e_ktls_rx_resync_ctx *resync; - struct mlx5_wqe_ctrl_seg *cseg; struct mlx5e_channel *c; struct mlx5e_icosq *sq; - struct mlx5_wq_cyc *wq; resync = container_of(work, struct mlx5e_ktls_rx_resync_ctx, work); priv_rx = container_of(resync, struct mlx5e_ktls_offload_context_rx, resync); @@ -324,18 +332,9 @@ static void resync_handle_work(struct work_struct *work) c = resync->priv->channels.c[priv_rx->rxq]; sq = &c->async_icosq; - wq = &sq->wq; - - spin_lock(&c->async_icosq_lock); - cseg = resync_post_get_progress_params(sq, priv_rx); - if (IS_ERR(cseg)) { + if (resync_post_get_progress_params(sq, priv_rx)) refcount_dec(&resync->refcnt); - goto unlock; - } - mlx5e_notify_hw(wq, sq->pc, sq->uar_map, cseg); -unlock: - spin_unlock(&c->async_icosq_lock); } static void resync_init(struct mlx5e_ktls_rx_resync_ctx *resync, @@ -386,16 +385,17 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, struct mlx5e_ktls_offload_context_rx *priv_rx; struct mlx5e_ktls_rx_resync_ctx *resync; u8 tracker_state, auth_state, *ctx; + struct device *dev; u32 hw_seq; priv_rx = buf->priv_rx; resync = &priv_rx->resync; - + dev = resync->priv->mdev->device; if (unlikely(test_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags))) goto out; - dma_sync_single_for_cpu(resync->priv->mdev->device, buf->dma_addr, - PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, + DMA_FROM_DEVICE); ctx = buf->progress.ctx; tracker_state = MLX5_GET(tls_progress_params, ctx, record_tracker_state); @@ -411,6 +411,7 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, priv_rx->stats->tls_resync_req_end++; out: refcount_dec(&resync->refcnt); + dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); kfree(buf); } @@ -659,7 +660,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx) priv_rx = mlx5e_get_ktls_rx_priv_ctx(tls_ctx); set_bit(MLX5E_PRIV_RX_FLAG_DELETING, priv_rx->flags); mlx5e_set_ktls_rx_priv_ctx(tls_ctx, NULL); - napi_synchronize(&priv->channels.c[priv_rx->rxq]->napi); + synchronize_rcu(); /* Sync with NAPI */ if (!cancel_work_sync(&priv_rx->rule.work)) /* completion is needed, as the priv_rx in the add flow * is maintained on the wqe info (wi), not on the socket. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c index 01468ec27446..b949b9a7538b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c @@ -35,7 +35,6 @@ #include <net/sock.h> #include "en.h" -#include "accel/tls.h" #include "fpga/sdk.h" #include "en_accel/tls.h" @@ -51,9 +50,14 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = { #define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc) +static bool is_tls_atomic_stats(struct mlx5e_priv *priv) +{ + return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev); +} + int mlx5e_tls_get_count(struct mlx5e_priv *priv) { - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0; return NUM_TLS_SW_COUNTERS; @@ -63,7 +67,7 @@ int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { unsigned int i, idx = 0; - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0; for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) @@ -77,7 +81,7 @@ int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { int i, idx = 0; - if (!priv->tls) + if (!is_tls_atomic_stats(priv)) return 0; for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 64d002d92250..1f48f99c0997 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -217,6 +217,9 @@ static int __mlx5e_add_vlan_rule(struct mlx5e_priv *priv, break; } + if (WARN_ONCE(*rule_p, "VLAN rule already exists type %d", rule_type)) + return 0; + *rule_p = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(*rule_p)) { @@ -397,8 +400,7 @@ static void mlx5e_add_vlan_rules(struct mlx5e_priv *priv) for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID) mlx5e_add_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i); - if (priv->fs.vlan.cvlan_filter_disabled && - !(priv->netdev->flags & IFF_PROMISC)) + if (priv->fs.vlan.cvlan_filter_disabled) mlx5e_add_any_vid_rules(priv); } @@ -415,8 +417,12 @@ static void mlx5e_del_vlan_rules(struct mlx5e_priv *priv) for_each_set_bit(i, priv->fs.vlan.active_svlans, VLAN_N_VID) mlx5e_del_vlan_rule(priv, MLX5E_VLAN_RULE_TYPE_MATCH_STAG_VID, i); - if (priv->fs.vlan.cvlan_filter_disabled && - !(priv->netdev->flags & IFF_PROMISC)) + WARN_ON_ONCE(!(test_bit(MLX5E_STATE_DESTROYING, &priv->state))); + + /* must be called after DESTROY bit is set and + * set_rx_mode is called and flushed + */ + if (priv->fs.vlan.cvlan_filter_disabled) mlx5e_del_any_vid_rules(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index aebcf73f8546..42ec28e29834 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -158,16 +158,6 @@ static void mlx5e_update_carrier_work(struct work_struct *work) mutex_unlock(&priv->state_lock); } -void mlx5e_update_ndo_stats(struct mlx5e_priv *priv) -{ - int i; - - for (i = mlx5e_nic_stats_grps_num(priv) - 1; i >= 0; i--) - if (mlx5e_nic_stats_grps[i]->update_stats_mask & - MLX5E_NDO_UPDATE_STATS) - mlx5e_nic_stats_grps[i]->update_stats(priv); -} - static void mlx5e_update_stats_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, @@ -256,12 +246,17 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, u64 npages, u8 page_shift, - struct mlx5_core_mkey *umr_mkey) + struct mlx5_core_mkey *umr_mkey, + dma_addr_t filler_addr) { - int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); + struct mlx5_mtt *mtt; + int inlen; void *mkc; u32 *in; int err; + int i; + + inlen = MLX5_ST_SZ_BYTES(create_mkey_in) + sizeof(*mtt) * npages; in = kvzalloc(inlen, GFP_KERNEL); if (!in) @@ -281,6 +276,18 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev, MLX5_SET(mkc, mkc, translations_octword_size, MLX5_MTT_OCTW(npages)); MLX5_SET(mkc, mkc, log_page_size, page_shift); + MLX5_SET(create_mkey_in, in, translations_octword_actual_size, + MLX5_MTT_OCTW(npages)); + + /* Initialize the mkey with all MTTs pointing to a default + * page (filler_addr). When the channels are activated, UMR + * WQEs will redirect the RX WQEs to the actual memory from + * the RQ's pool, while the gaps (wqe_overflow) remain mapped + * to the default page. + */ + mtt = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); + for (i = 0 ; i < npages ; i++) + mtt[i].ptag = cpu_to_be64(filler_addr); err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen); @@ -292,7 +299,8 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq { u64 num_mtts = MLX5E_REQUIRED_MTTS(mlx5_wq_ll_get_size(&rq->mpwqe.wq)); - return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey); + return mlx5e_create_umr_mkey(mdev, num_mtts, PAGE_SHIFT, &rq->umr_mkey, + rq->wqe_overflow.addr); } static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) @@ -360,6 +368,28 @@ static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work) mlx5e_reporter_rq_cqe_err(rq); } +static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq) +{ + rq->wqe_overflow.page = alloc_page(GFP_KERNEL); + if (!rq->wqe_overflow.page) + return -ENOMEM; + + rq->wqe_overflow.addr = dma_map_page(rq->pdev, rq->wqe_overflow.page, 0, + PAGE_SIZE, rq->buff.map_dir); + if (dma_mapping_error(rq->pdev, rq->wqe_overflow.addr)) { + __free_page(rq->wqe_overflow.page); + return -ENOMEM; + } + return 0; +} + +static void mlx5e_free_mpwqe_rq_drop_page(struct mlx5e_rq *rq) +{ + dma_unmap_page(rq->pdev, rq->wqe_overflow.addr, PAGE_SIZE, + rq->buff.map_dir); + __free_page(rq->wqe_overflow.page); +} + static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, @@ -399,16 +429,16 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (params->xdp_prog) bpf_prog_inc(params->xdp_prog); - rq->xdp_prog = params->xdp_prog; + RCU_INIT_POINTER(rq->xdp_prog, params->xdp_prog); rq_xdp_ix = rq->ix; if (xsk) rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK; err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix); if (err < 0) - goto err_rq_wq_destroy; + goto err_rq_xdp_prog; - rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; + rq->buff.map_dir = params->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk); pool_size = 1 << params->log_rq_mtu_frames; @@ -417,6 +447,10 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->mpwqe.wq, &rq->wq_ctrl); if (err) + goto err_rq_xdp; + + err = mlx5e_alloc_mpwqe_rq_drop_page(rq); + if (err) goto err_rq_wq_destroy; rq->mpwqe.wq.db = &rq->mpwqe.wq.db[MLX5_RCV_DBR]; @@ -434,18 +468,18 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5e_create_rq_umr_mkey(mdev, rq); if (err) - goto err_rq_wq_destroy; + goto err_rq_drop_page; rq->mkey_be = cpu_to_be32(rq->umr_mkey.key); err = mlx5e_rq_alloc_mpwqe_info(rq, c); if (err) - goto err_free; + goto err_rq_mkey; break; default: /* MLX5_WQ_TYPE_CYCLIC */ err = mlx5_wq_cyc_create(mdev, &rqp->wq, rqc_wq, &rq->wqe.wq, &rq->wq_ctrl); if (err) - goto err_rq_wq_destroy; + goto err_rq_xdp; rq->wqe.wq.db = &rq->wqe.wq.db[MLX5_RCV_DBR]; @@ -460,19 +494,19 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, GFP_KERNEL, cpu_to_node(c->cpu)); if (!rq->wqe.frags) { err = -ENOMEM; - goto err_free; + goto err_rq_wq_destroy; } err = mlx5e_init_di_list(rq, wq_sz, c->cpu); if (err) - goto err_free; + goto err_rq_frags; rq->mkey_be = c->mkey_be; } err = mlx5e_rq_set_handlers(rq, params, xsk); if (err) - goto err_free; + goto err_free_by_rq_type; if (xsk) { err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, @@ -496,13 +530,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, if (IS_ERR(rq->page_pool)) { err = PTR_ERR(rq->page_pool); rq->page_pool = NULL; - goto err_free; + goto err_free_by_rq_type; } err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_POOL, rq->page_pool); } if (err) - goto err_free; + goto err_free_by_rq_type; for (i = 0; i < wq_sz; i++) { if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { @@ -552,38 +586,49 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, return 0; -err_free: +err_free_by_rq_type: switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); +err_rq_mkey: mlx5_core_destroy_mkey(mdev, &rq->umr_mkey); +err_rq_drop_page: + mlx5e_free_mpwqe_rq_drop_page(rq); break; default: /* MLX5_WQ_TYPE_CYCLIC */ - kvfree(rq->wqe.frags); mlx5e_free_di_list(rq); +err_rq_frags: + kvfree(rq->wqe.frags); } - err_rq_wq_destroy: - if (rq->xdp_prog) - bpf_prog_put(rq->xdp_prog); - xdp_rxq_info_unreg(&rq->xdp_rxq); - page_pool_destroy(rq->page_pool); mlx5_wq_destroy(&rq->wq_ctrl); +err_rq_xdp: + xdp_rxq_info_unreg(&rq->xdp_rxq); +err_rq_xdp_prog: + if (params->xdp_prog) + bpf_prog_put(params->xdp_prog); return err; } static void mlx5e_free_rq(struct mlx5e_rq *rq) { + struct mlx5e_channel *c = rq->channel; + struct bpf_prog *old_prog = NULL; int i; - if (rq->xdp_prog) - bpf_prog_put(rq->xdp_prog); + /* drop_rq has neither channel nor xdp_prog. */ + if (c) + old_prog = rcu_dereference_protected(rq->xdp_prog, + lockdep_is_held(&c->priv->state_lock)); + if (old_prog) + bpf_prog_put(old_prog); switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: kvfree(rq->mpwqe.info); mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey); + mlx5e_free_mpwqe_rq_drop_page(rq); break; default: /* MLX5_WQ_TYPE_CYCLIC */ kvfree(rq->wqe.frags); @@ -867,7 +912,7 @@ void mlx5e_activate_rq(struct mlx5e_rq *rq) void mlx5e_deactivate_rq(struct mlx5e_rq *rq) { clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); - napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ + synchronize_rcu(); /* Sync with NAPI to prevent mlx5e_post_rx_wqes. */ } void mlx5e_close_rq(struct mlx5e_rq *rq) @@ -1312,12 +1357,10 @@ void mlx5e_tx_disable_queue(struct netdev_queue *txq) static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) { - struct mlx5e_channel *c = sq->channel; struct mlx5_wq_cyc *wq = &sq->wq; clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - /* prevent netif_tx_wake_queue */ - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI to prevent netif_tx_wake_queue. */ mlx5e_tx_disable_queue(sq->txq); @@ -1392,10 +1435,8 @@ void mlx5e_activate_icosq(struct mlx5e_icosq *icosq) void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq) { - struct mlx5e_channel *c = icosq->channel; - clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state); - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI. */ } void mlx5e_close_icosq(struct mlx5e_icosq *sq) @@ -1474,7 +1515,7 @@ void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq) struct mlx5e_channel *c = sq->channel; clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - napi_synchronize(&c->napi); + synchronize_rcu(); /* Sync with NAPI. */ mlx5e_destroy_sq(c->mdev, sq->sqn); mlx5e_free_xdpsq_descs(sq); @@ -3567,6 +3608,7 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) s->rx_packets += rq_stats->packets + xskrq_stats->packets; s->rx_bytes += rq_stats->bytes + xskrq_stats->bytes; + s->multicast += rq_stats->mcast_packets + xskrq_stats->mcast_packets; for (j = 0; j < priv->max_opened_tc; j++) { struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; @@ -3582,7 +3624,6 @@ void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) { struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_vport_stats *vstats = &priv->stats.vport; struct mlx5e_pport_stats *pstats = &priv->stats.pport; /* In switchdev mode, monitor counters doesn't monitor @@ -3617,12 +3658,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors + stats->rx_frame_errors; stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors; - - /* vport multicast also counts packets that are dropped due to steering - * or rx out of buffer - */ - stats->multicast = - VPORT_COUNTER_GET(vstats, received_eth_multicast.packets); } static void mlx5e_set_rx_mode(struct net_device *dev) @@ -4191,6 +4226,21 @@ int mlx5e_get_vf_stats(struct net_device *dev, } #endif +static bool mlx5e_gre_tunnel_inner_proto_offload_supported(struct mlx5_core_dev *mdev, + struct sk_buff *skb) +{ + switch (skb->inner_protocol) { + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + case htons(ETH_P_TEB): + return true; + case htons(ETH_P_MPLS_UC): + case htons(ETH_P_MPLS_MC): + return MLX5_CAP_ETH(mdev, tunnel_stateless_mpls_over_gre); + } + return false; +} + static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, struct sk_buff *skb, netdev_features_t features) @@ -4213,7 +4263,9 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, switch (proto) { case IPPROTO_GRE: - return features; + if (mlx5e_gre_tunnel_inner_proto_offload_supported(priv->mdev, skb)) + return features; + break; case IPPROTO_IPIP: case IPPROTO_IPV6: if (mlx5e_tunnel_proto_supported(priv->mdev, IPPROTO_IPIP)) @@ -4330,6 +4382,16 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) return 0; } +static void mlx5e_rq_replace_xdp_prog(struct mlx5e_rq *rq, struct bpf_prog *prog) +{ + struct bpf_prog *old_prog; + + old_prog = rcu_replace_pointer(rq->xdp_prog, prog, + lockdep_is_held(&rq->channel->priv->state_lock)); + if (old_prog) + bpf_prog_put(old_prog); +} + static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -4388,29 +4450,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) */ for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; - bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); - - clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); - if (xsk_open) - clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); - napi_synchronize(&c->napi); - /* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */ - - old_prog = xchg(&c->rq.xdp_prog, prog); - if (old_prog) - bpf_prog_put(old_prog); - - if (xsk_open) { - old_prog = xchg(&c->xskrq.xdp_prog, prog); - if (old_prog) - bpf_prog_put(old_prog); - } - set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); - if (xsk_open) - set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); - /* napi_schedule in case we have missed anything */ - napi_schedule(&c->napi); + mlx5e_rq_replace_xdp_prog(&c->rq, prog); + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + mlx5e_rq_replace_xdp_prog(&c->xskrq, prog); } unlock: @@ -5200,7 +5243,7 @@ static const struct mlx5e_profile mlx5e_nic_profile = { .enable = mlx5e_nic_enable, .disable = mlx5e_nic_disable, .update_rx = mlx5e_update_nic_rx, - .update_stats = mlx5e_update_ndo_stats, + .update_stats = mlx5e_stats_update_ndo_stats, .update_carrier = mlx5e_update_carrier, .rx_handlers = &mlx5e_rx_handlers_nic, .max_tc = MLX5E_MAX_NUM_TC, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index e13e5d1b3eae..e979bff64c49 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1171,7 +1171,7 @@ static const struct mlx5e_profile mlx5e_rep_profile = { .cleanup_tx = mlx5e_cleanup_rep_tx, .enable = mlx5e_rep_enable, .update_rx = mlx5e_update_rep_rx, - .update_stats = mlx5e_update_ndo_stats, + .update_stats = mlx5e_stats_update_ndo_stats, .rx_handlers = &mlx5e_rx_handlers_rep, .max_tc = 1, .rq_groups = MLX5E_NUM_RQ_GROUPS(REGULAR), @@ -1189,7 +1189,7 @@ static const struct mlx5e_profile mlx5e_uplink_rep_profile = { .enable = mlx5e_uplink_rep_enable, .disable = mlx5e_uplink_rep_disable, .update_rx = mlx5e_update_rep_rx, - .update_stats = mlx5e_update_ndo_stats, + .update_stats = mlx5e_stats_update_ndo_stats, .update_carrier = mlx5e_update_carrier, .rx_handlers = &mlx5e_rx_handlers_rep, .max_tc = MLX5E_MAX_NUM_TC, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index 622c27ae4ac7..0d1562e20118 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -135,12 +135,6 @@ struct mlx5e_neigh_hash_entry { /* encap list sharing the same neigh */ struct list_head encap_list; - /* valid only when the neigh reference is taken during - * neigh_update_work workqueue callback. - */ - struct neighbour *n; - struct work_struct neigh_update_work; - /* neigh hash entry can be deleted only when the refcount is zero. * refcount is needed to avoid neigh hash entry removal by TC, while * it's used by the neigh notification call. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 65828af120b7..64c8ac5eabf6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -53,6 +53,7 @@ #include "en/xsk/rx.h" #include "en/health.h" #include "en/params.h" +#include "en/txrx.h" static struct sk_buff * mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, @@ -1080,6 +1081,9 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, mlx5e_enable_ecn(rq, skb); skb->protocol = eth_type_trans(skb, netdev); + + if (unlikely(mlx5e_skb_is_multicast(skb))) + stats->mcast_packets++; } static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq, @@ -1132,7 +1136,6 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, struct xdp_buff xdp; struct sk_buff *skb; void *va, *data; - bool consumed; u32 frag_size; va = page_address(di->page) + wi->offset; @@ -1144,11 +1147,8 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, prefetchw(va); /* xdp_frame data area */ prefetch(data); - rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt, &xdp); - consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp); - rcu_read_unlock(); - if (consumed) + if (mlx5e_xdp_handle(rq, di, &cqe_bcnt, &xdp)) return NULL; /* page/packet was consumed by XDP */ rx_headroom = xdp.data - xdp.data_hard_start; @@ -1438,7 +1438,6 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, struct sk_buff *skb; void *va, *data; u32 frag_size; - bool consumed; /* Check packet size. Note LRO doesn't use linear SKB */ if (unlikely(cqe_bcnt > rq->hw_mtu)) { @@ -1455,11 +1454,8 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, prefetchw(va); /* xdp_frame data area */ prefetch(data); - rcu_read_lock(); mlx5e_fill_xdp_buff(rq, va, rx_headroom, cqe_bcnt32, &xdp); - consumed = mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp); - rcu_read_unlock(); - if (consumed) { + if (mlx5e_xdp_handle(rq, di, &cqe_bcnt32, &xdp)) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */ return NULL; /* page/packet was consumed by XDP */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index e3b2f59408e6..f6383bc2bc3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -54,6 +54,18 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv) return total; } +void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv) +{ + mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps; + const unsigned int num_stats_grps = stats_grps_num(priv); + int i; + + for (i = num_stats_grps - 1; i >= 0; i--) + if (stats_grps[i]->update_stats && + stats_grps[i]->update_stats_mask & MLX5E_NDO_UPDATE_STATS) + stats_grps[i]->update_stats(priv); +} + void mlx5e_stats_update(struct mlx5e_priv *priv) { mlx5e_stats_grp_t *stats_grps = priv->profile->stats_grps; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 2e1cca1923b9..562263d62141 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -103,6 +103,7 @@ unsigned int mlx5e_stats_total_num(struct mlx5e_priv *priv); void mlx5e_stats_update(struct mlx5e_priv *priv); void mlx5e_stats_fill(struct mlx5e_priv *priv, u64 *data, int idx); void mlx5e_stats_fill_strings(struct mlx5e_priv *priv, u8 *data); +void mlx5e_stats_update_ndo_stats(struct mlx5e_priv *priv); /* Concrete NIC Stats */ @@ -119,6 +120,7 @@ struct mlx5e_sw_stats { u64 tx_nop; u64 rx_lro_packets; u64 rx_lro_bytes; + u64 rx_mcast_packets; u64 rx_ecn_mark; u64 rx_removed_vlan_packets; u64 rx_csum_unnecessary; @@ -298,6 +300,7 @@ struct mlx5e_rq_stats { u64 csum_none; u64 lro_packets; u64 lro_bytes; + u64 mcast_packets; u64 ecn_mark; u64 removed_vlan_packets; u64 xdp_drop; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index fd53d101d8fd..1c93f92d9210 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1290,11 +1290,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, mlx5e_put_flow_tunnel_id(flow); - if (flow_flag_test(flow, NOT_READY)) { + if (flow_flag_test(flow, NOT_READY)) remove_unready_flow(flow); - kvfree(attr->parse_attr); - return; - } if (mlx5e_is_offloaded_flow(flow)) { if (flow_flag_test(flow, SLOW)) @@ -1315,6 +1312,8 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, } kvfree(attr->parse_attr); + mlx5_tc_ct_match_del(priv, &flow->esw_attr->ct_attr); + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) mlx5e_detach_mod_hdr(priv, flow); @@ -2625,6 +2624,22 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest, 0, udp_dport), }; +static unsigned long mask_to_le(unsigned long mask, int size) +{ + __be32 mask_be32; + __be16 mask_be16; + + if (size == 32) { + mask_be32 = (__force __be32)(mask); + mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); + } else if (size == 16) { + mask_be32 = (__force __be32)(mask); + mask_be16 = *(__be16 *)&mask_be32; + mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); + } + + return mask; +} static int offload_pedit_fields(struct mlx5e_priv *priv, int namespace, struct pedit_headers_action *hdrs, @@ -2638,9 +2653,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, u32 *s_masks_p, *a_masks_p, s_mask, a_mask; struct mlx5e_tc_mod_hdr_acts *mod_acts; struct mlx5_fields *f; - unsigned long mask; - __be32 mask_be32; - __be16 mask_be16; + unsigned long mask, field_mask; int err; u8 cmd; @@ -2706,14 +2719,7 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (skip) continue; - if (f->field_bsize == 32) { - mask_be32 = (__force __be32)(mask); - mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32)); - } else if (f->field_bsize == 16) { - mask_be32 = (__force __be32)(mask); - mask_be16 = *(__be16 *)&mask_be32; - mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16)); - } + mask = mask_to_le(mask, f->field_bsize); first = find_first_bit(&mask, f->field_bsize); next_z = find_next_zero_bit(&mask, f->field_bsize, first); @@ -2744,9 +2750,10 @@ static int offload_pedit_fields(struct mlx5e_priv *priv, if (cmd == MLX5_ACTION_TYPE_SET) { int start; + field_mask = mask_to_le(f->field_mask, f->field_bsize); + /* if field is bit sized it can start not from first bit */ - start = find_first_bit((unsigned long *)&f->field_mask, - f->field_bsize); + start = find_first_bit(&field_mask, f->field_bsize); MLX5_SET(set_action_in, action, offset, first - start); /* length is num of bits to be written, zero means length of 32 */ @@ -4402,8 +4409,8 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, goto err_free; /* actions validation depends on parsing the ct matches first */ - err = mlx5_tc_ct_parse_match(priv, &parse_attr->spec, f, - &flow->esw_attr->ct_attr, extack); + err = mlx5_tc_ct_match_add(priv, &parse_attr->spec, f, + &flow->esw_attr->ct_attr, extack); if (err) goto err_free; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index de10b06bade5..d5868670f8a5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -121,13 +121,17 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) struct mlx5e_xdpsq *xsksq = &c->xsksq; struct mlx5e_rq *xskrq = &c->xskrq; struct mlx5e_rq *rq = &c->rq; - bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); bool aff_change = false; bool busy_xsk = false; bool busy = false; int work_done = 0; + bool xsk_open; int i; + rcu_read_lock(); + + xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); + ch_stats->poll++; for (i = 0; i < c->num_tc; i++) @@ -167,8 +171,10 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) busy |= busy_xsk; if (busy) { - if (likely(mlx5e_channel_no_affinity_change(c))) - return budget; + if (likely(mlx5e_channel_no_affinity_change(c))) { + work_done = budget; + goto out; + } ch_stats->aff_change++; aff_change = true; if (budget && work_done == budget) @@ -176,7 +182,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) } if (unlikely(!napi_complete_done(napi, work_done))) - return work_done; + goto out; ch_stats->arm++; @@ -203,6 +209,9 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) ch_stats->force_irq++; } +out: + rcu_read_unlock(); + return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 31ef9f8420c8..22a19d391e17 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -189,6 +189,29 @@ u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq) return count_eqe; } +static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, unsigned long *flags) + __acquires(&eq->lock) +{ + if (in_irq()) + spin_lock(&eq->lock); + else + spin_lock_irqsave(&eq->lock, *flags); +} + +static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, unsigned long *flags) + __releases(&eq->lock) +{ + if (in_irq()) + spin_unlock(&eq->lock); + else + spin_unlock_irqrestore(&eq->lock, *flags); +} + +enum async_eq_nb_action { + ASYNC_EQ_IRQ_HANDLER = 0, + ASYNC_EQ_RECOVER = 1, +}; + static int mlx5_eq_async_int(struct notifier_block *nb, unsigned long action, void *data) { @@ -198,11 +221,14 @@ static int mlx5_eq_async_int(struct notifier_block *nb, struct mlx5_eq_table *eqt; struct mlx5_core_dev *dev; struct mlx5_eqe *eqe; + unsigned long flags; int num_eqes = 0; dev = eq->dev; eqt = dev->priv.eq_table; + mlx5_eq_async_int_lock(eq_async, &flags); + eqe = next_eqe_sw(eq); if (!eqe) goto out; @@ -223,8 +249,19 @@ static int mlx5_eq_async_int(struct notifier_block *nb, out: eq_update_ci(eq, 1); + mlx5_eq_async_int_unlock(eq_async, &flags); - return 0; + return unlikely(action == ASYNC_EQ_RECOVER) ? num_eqes : 0; +} + +void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev) +{ + struct mlx5_eq_async *eq = &dev->priv.eq_table->cmd_eq; + int eqes; + + eqes = mlx5_eq_async_int(&eq->irq_nb, ASYNC_EQ_RECOVER, NULL); + if (eqes) + mlx5_core_warn(dev, "Recovered %d EQEs on cmd_eq\n", eqes); } static void init_eq_buf(struct mlx5_eq *eq) @@ -569,6 +606,7 @@ setup_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq_async *eq, int err; eq->irq_nb.notifier_call = mlx5_eq_async_int; + spin_lock_init(&eq->lock); err = create_async_eq(dev, &eq->core, param); if (err) { @@ -656,8 +694,10 @@ static void destroy_async_eqs(struct mlx5_core_dev *dev) cleanup_async_eq(dev, &table->pages_eq, "pages"); cleanup_async_eq(dev, &table->async_eq, "async"); + mlx5_cmd_allowed_opcode(dev, MLX5_CMD_OP_DESTROY_EQ); mlx5_cmd_use_polling(dev); cleanup_async_eq(dev, &table->cmd_eq, "cmd"); + mlx5_cmd_allowed_opcode(dev, CMD_ALLOWED_OPCODE_ALL); mlx5_eq_notifier_unregister(dev, &table->cq_err_nb); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index d2516922d867..1bcf2609dca8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1219,35 +1219,37 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) } esw->fdb_table.offloads.send_to_vport_grp = g; - /* create peer esw miss group */ - memset(flow_group_in, 0, inlen); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { + /* create peer esw miss group */ + memset(flow_group_in, 0, inlen); - esw_set_flow_group_source_port(esw, flow_group_in); + esw_set_flow_group_source_port(esw, flow_group_in); - if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) { - match_criteria = MLX5_ADDR_OF(create_flow_group_in, - flow_group_in, - match_criteria); + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) { + match_criteria = MLX5_ADDR_OF(create_flow_group_in, + flow_group_in, + match_criteria); - MLX5_SET_TO_ONES(fte_match_param, match_criteria, - misc_parameters.source_eswitch_owner_vhca_id); + MLX5_SET_TO_ONES(fte_match_param, match_criteria, + misc_parameters.source_eswitch_owner_vhca_id); - MLX5_SET(create_flow_group_in, flow_group_in, - source_eswitch_owner_vhca_id_valid, 1); - } + MLX5_SET(create_flow_group_in, flow_group_in, + source_eswitch_owner_vhca_id_valid, 1); + } - MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, - ix + esw->total_vports - 1); - ix += esw->total_vports; + MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, + ix + esw->total_vports - 1); + ix += esw->total_vports; - g = mlx5_create_flow_group(fdb, flow_group_in); - if (IS_ERR(g)) { - err = PTR_ERR(g); - esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err); - goto peer_miss_err; + g = mlx5_create_flow_group(fdb, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err); + goto peer_miss_err; + } + esw->fdb_table.offloads.peer_miss_grp = g; } - esw->fdb_table.offloads.peer_miss_grp = g; /* create miss group */ memset(flow_group_in, 0, inlen); @@ -1281,7 +1283,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) miss_rule_err: mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp); miss_err: - mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); peer_miss_err: mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); send_vport_err: @@ -1305,7 +1308,8 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi); mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni); mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp); - mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); + if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) + mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp); mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp); mlx5_esw_chains_destroy(esw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 9ccec5f8b92a..75fa44eee434 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -654,7 +654,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft, fte->action = *flow_act; fte->flow_context = spec->flow_context; - tree_init_node(&fte->node, NULL, del_sw_fte); + tree_init_node(&fte->node, del_hw_fte, del_sw_fte); return fte; } @@ -1792,7 +1792,6 @@ skip_search: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); - tree_put_node(&fte->node, false); return rule; } rule = ERR_PTR(-ENOENT); @@ -1891,7 +1890,6 @@ search_again_locked: up_write_ref_node(&g->node, false); rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node, false); - tree_put_node(&fte->node, false); tree_put_node(&g->node, false); return rule; @@ -2001,7 +1999,9 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle) up_write_ref_node(&fte->node, false); } else { del_hw_fte(&fte->node); - up_write(&fte->node.lock); + /* Avoid double call to del_hw_fte */ + fte->node.del_hw_func = NULL; + up_write_ref_node(&fte->node, false); tree_put_node(&fte->node, false); } kfree(handle); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 4aaca7400fb2..5c681e31983b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -37,6 +37,7 @@ struct mlx5_eq { struct mlx5_eq_async { struct mlx5_eq core; struct notifier_block irq_nb; + spinlock_t lock; /* To avoid irq EQ handle races with resiliency flows */ }; struct mlx5_eq_comp { @@ -81,6 +82,7 @@ void mlx5_cq_tasklet_cb(unsigned long data); struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix); u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq); +void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev); void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev); void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index f9b798af6335..c0e18f2ade99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -432,7 +432,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, u32 npages; u32 i = 0; - if (dev->state != MLX5_DEVICE_STATE_INTERNAL_ERROR) + if (!mlx5_cmd_is_down(dev)) return mlx5_cmd_exec(dev, in, in_size, out, out_size); /* No hard feelings, we want our pages back! */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c index 373981a659c7..6fd974920394 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c @@ -115,7 +115,7 @@ static int request_irqs(struct mlx5_core_dev *dev, int nvec) return 0; err_request_irq: - for (; i >= 0; i--) { + while (i--) { struct mlx5_irq *irq = mlx5_irq_get(dev, i); int irqn = pci_irq_vector(dev->pdev, i); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 4186e29119c2..f3c0e241e1b4 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -3690,13 +3690,13 @@ bool mlxsw_sp_port_dev_check(const struct net_device *dev) return dev->netdev_ops == &mlxsw_sp_port_netdev_ops; } -static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data) +static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) { - struct mlxsw_sp_port **p_mlxsw_sp_port = data; int ret = 0; if (mlxsw_sp_port_dev_check(lower_dev)) { - *p_mlxsw_sp_port = netdev_priv(lower_dev); + priv->data = (void *)netdev_priv(lower_dev); ret = 1; } @@ -3705,15 +3705,16 @@ static int mlxsw_sp_lower_dev_walk(struct net_device *lower_dev, void *data) struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev) { - struct mlxsw_sp_port *mlxsw_sp_port; + struct netdev_nested_priv priv = { + .data = NULL, + }; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - mlxsw_sp_port = NULL; - netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &mlxsw_sp_port); + netdev_walk_all_lower_dev(dev, mlxsw_sp_lower_dev_walk, &priv); - return mlxsw_sp_port; + return (struct mlxsw_sp_port *)priv.data; } struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) @@ -3726,16 +3727,17 @@ struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev) struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev) { - struct mlxsw_sp_port *mlxsw_sp_port; + struct netdev_nested_priv priv = { + .data = NULL, + }; if (mlxsw_sp_port_dev_check(dev)) return netdev_priv(dev); - mlxsw_sp_port = NULL; netdev_walk_all_lower_dev_rcu(dev, mlxsw_sp_lower_dev_walk, - &mlxsw_sp_port); + &priv); - return mlxsw_sp_port; + return (struct mlxsw_sp_port *)priv.data; } struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 5c020403342f..7cccc41dd69c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -292,13 +292,14 @@ mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp_acl_tcam *tcam, int err; group->tcam = tcam; - mutex_init(&group->lock); INIT_LIST_HEAD(&group->region_list); err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id); if (err) return err; + mutex_init(&group->lock); + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 24f1fd1f8d56..460cb523312f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -7351,9 +7351,10 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event, return err; } -static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data) +static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, + struct netdev_nested_priv *priv) { - struct mlxsw_sp_rif *rif = data; + struct mlxsw_sp_rif *rif = (struct mlxsw_sp_rif *)priv->data; if (!netif_is_macvlan(dev)) return 0; @@ -7364,12 +7365,16 @@ static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data) static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif) { + struct netdev_nested_priv priv = { + .data = (void *)rif, + }; + if (!netif_is_macvlan_port(rif->dev)) return 0; netdev_warn(rif->dev, "Router interface is deleted. Upper macvlans will not work\n"); return netdev_walk_all_upper_dev_rcu(rif->dev, - __mlxsw_sp_rif_macvlan_flush, rif); + __mlxsw_sp_rif_macvlan_flush, &priv); } static void mlxsw_sp_rif_subport_setup(struct mlxsw_sp_rif *rif, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 72912afa6f72..6501ce94ace5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -136,9 +136,9 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev, - void *data) + struct netdev_nested_priv *priv) { - struct mlxsw_sp *mlxsw_sp = data; + struct mlxsw_sp *mlxsw_sp = priv->data; mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev); return 0; @@ -147,10 +147,14 @@ static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev, static void mlxsw_sp_bridge_device_rifs_destroy(struct mlxsw_sp *mlxsw_sp, struct net_device *dev) { + struct netdev_nested_priv priv = { + .data = (void *)mlxsw_sp, + }; + mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev); netdev_walk_all_upper_dev_rcu(dev, mlxsw_sp_bridge_device_upper_rif_destroy, - mlxsw_sp); + &priv); } static int mlxsw_sp_bridge_device_vxlan_init(struct mlxsw_sp_bridge *bridge, diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 5abb7d2b0a9e..aa002db04250 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -421,10 +421,15 @@ int ocelot_port_add_txtstamp_skb(struct ocelot_port *ocelot_port, if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP && ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) { + spin_lock(&ocelot_port->ts_id_lock); + shinfo->tx_flags |= SKBTX_IN_PROGRESS; /* Store timestamp ID in cb[0] of sk_buff */ - skb->cb[0] = ocelot_port->ts_id % 4; + skb->cb[0] = ocelot_port->ts_id; + ocelot_port->ts_id = (ocelot_port->ts_id + 1) % 4; skb_queue_tail(&ocelot_port->tx_skbs, skb); + + spin_unlock(&ocelot_port->ts_id_lock); return 0; } return -ENODATA; @@ -1248,7 +1253,7 @@ void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu) struct ocelot_port *ocelot_port = ocelot->ports[port]; int maxlen = sdu + ETH_HLEN + ETH_FCS_LEN; int pause_start, pause_stop; - int atop_wm; + int atop, atop_tot; if (port == ocelot->npi) { maxlen += OCELOT_TAG_LEN; @@ -1269,12 +1274,12 @@ void ocelot_port_set_maxlen(struct ocelot *ocelot, int port, size_t sdu) ocelot_fields_write(ocelot, port, SYS_PAUSE_CFG_PAUSE_STOP, pause_stop); - /* Tail dropping watermark */ - atop_wm = (ocelot->shared_queue_sz - 9 * maxlen) / + /* Tail dropping watermarks */ + atop_tot = (ocelot->shared_queue_sz - 9 * maxlen) / OCELOT_BUFFER_CELL_SZ; - ocelot_write_rix(ocelot, ocelot->ops->wm_enc(9 * maxlen), - SYS_ATOP, port); - ocelot_write(ocelot, ocelot->ops->wm_enc(atop_wm), SYS_ATOP_TOT_CFG); + atop = (9 * maxlen) / OCELOT_BUFFER_CELL_SZ; + ocelot_write_rix(ocelot, ocelot->ops->wm_enc(atop), SYS_ATOP, port); + ocelot_write(ocelot, ocelot->ops->wm_enc(atop_tot), SYS_ATOP_TOT_CFG); } EXPORT_SYMBOL(ocelot_port_set_maxlen); @@ -1300,6 +1305,7 @@ void ocelot_init_port(struct ocelot *ocelot, int port) struct ocelot_port *ocelot_port = ocelot->ports[port]; skb_queue_head_init(&ocelot_port->tx_skbs); + spin_lock_init(&ocelot_port->ts_id_lock); /* Basic L2 initialization */ @@ -1544,18 +1550,18 @@ EXPORT_SYMBOL(ocelot_init); void ocelot_deinit(struct ocelot *ocelot) { - struct ocelot_port *port; - int i; - cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); mutex_destroy(&ocelot->stats_lock); - - for (i = 0; i < ocelot->num_phys_ports; i++) { - port = ocelot->ports[i]; - skb_queue_purge(&port->tx_skbs); - } } EXPORT_SYMBOL(ocelot_deinit); +void ocelot_deinit_port(struct ocelot *ocelot, int port) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + + skb_queue_purge(&ocelot_port->tx_skbs); +} +EXPORT_SYMBOL(ocelot_deinit_port); + MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 0668d23cdbfa..8490e42e9e2d 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -330,6 +330,7 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) u8 grp = 0; /* Send everything on CPU group 0 */ unsigned int i, count, last; int port = priv->chip_port; + bool do_tstamp; val = ocelot_read(ocelot, QS_INJ_STATUS); if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp))) || @@ -344,10 +345,12 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) info.vid = skb_vlan_tag_get(skb); /* Check if timestamping is needed */ + do_tstamp = (ocelot_port_add_txtstamp_skb(ocelot_port, skb) == 0); + if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP) { info.rew_op = ocelot_port->ptp_cmd; if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) - info.rew_op |= (ocelot_port->ts_id % 4) << 3; + info.rew_op |= skb->cb[0] << 3; } ocelot_gen_ifh(ifh, &info); @@ -380,12 +383,9 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - if (!ocelot_port_add_txtstamp_skb(ocelot_port, skb)) { - ocelot_port->ts_id++; - return NETDEV_TX_OK; - } + if (!do_tstamp) + dev_kfree_skb_any(skb); - dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c index 65408bc994c4..8a6917691ba6 100644 --- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c +++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c @@ -745,6 +745,8 @@ static int ocelot_reset(struct ocelot *ocelot) */ static u16 ocelot_wm_enc(u16 value) { + WARN_ON(value >= 16 * BIT(8)); + if (value >= BIT(8)) return BIT(8) | (value / 16); @@ -806,17 +808,17 @@ static const struct vcap_field vsc7514_vcap_is2_keys[] = { [VCAP_IS2_HK_DIP_EQ_SIP] = {123, 1}, /* IP4_TCP_UDP (TYPE=100) */ [VCAP_IS2_HK_TCP] = {124, 1}, - [VCAP_IS2_HK_L4_SPORT] = {125, 16}, - [VCAP_IS2_HK_L4_DPORT] = {141, 16}, + [VCAP_IS2_HK_L4_DPORT] = {125, 16}, + [VCAP_IS2_HK_L4_SPORT] = {141, 16}, [VCAP_IS2_HK_L4_RNG] = {157, 8}, [VCAP_IS2_HK_L4_SPORT_EQ_DPORT] = {165, 1}, [VCAP_IS2_HK_L4_SEQUENCE_EQ0] = {166, 1}, - [VCAP_IS2_HK_L4_URG] = {167, 1}, - [VCAP_IS2_HK_L4_ACK] = {168, 1}, - [VCAP_IS2_HK_L4_PSH] = {169, 1}, - [VCAP_IS2_HK_L4_RST] = {170, 1}, - [VCAP_IS2_HK_L4_SYN] = {171, 1}, - [VCAP_IS2_HK_L4_FIN] = {172, 1}, + [VCAP_IS2_HK_L4_FIN] = {167, 1}, + [VCAP_IS2_HK_L4_SYN] = {168, 1}, + [VCAP_IS2_HK_L4_RST] = {169, 1}, + [VCAP_IS2_HK_L4_PSH] = {170, 1}, + [VCAP_IS2_HK_L4_ACK] = {171, 1}, + [VCAP_IS2_HK_L4_URG] = {172, 1}, [VCAP_IS2_HK_L4_1588_DOM] = {173, 8}, [VCAP_IS2_HK_L4_1588_VER] = {181, 4}, /* IP4_OTHER (TYPE=101) */ @@ -896,11 +898,137 @@ static struct ptp_clock_info ocelot_ptp_clock_info = { .enable = ocelot_ptp_enable, }; +static void mscc_ocelot_release_ports(struct ocelot *ocelot) +{ + int port; + + for (port = 0; port < ocelot->num_phys_ports; port++) { + struct ocelot_port_private *priv; + struct ocelot_port *ocelot_port; + + ocelot_port = ocelot->ports[port]; + if (!ocelot_port) + continue; + + ocelot_deinit_port(ocelot, port); + + priv = container_of(ocelot_port, struct ocelot_port_private, + port); + + unregister_netdev(priv->dev); + free_netdev(priv->dev); + } +} + +static int mscc_ocelot_init_ports(struct platform_device *pdev, + struct device_node *ports) +{ + struct ocelot *ocelot = platform_get_drvdata(pdev); + struct device_node *portnp; + int err; + + ocelot->ports = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports, + sizeof(struct ocelot_port *), GFP_KERNEL); + if (!ocelot->ports) + return -ENOMEM; + + /* No NPI port */ + ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE, + OCELOT_TAG_PREFIX_NONE); + + for_each_available_child_of_node(ports, portnp) { + struct ocelot_port_private *priv; + struct ocelot_port *ocelot_port; + struct device_node *phy_node; + phy_interface_t phy_mode; + struct phy_device *phy; + struct regmap *target; + struct resource *res; + struct phy *serdes; + char res_name[8]; + u32 port; + + if (of_property_read_u32(portnp, "reg", &port)) + continue; + + snprintf(res_name, sizeof(res_name), "port%d", port); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + res_name); + target = ocelot_regmap_init(ocelot, res); + if (IS_ERR(target)) + continue; + + phy_node = of_parse_phandle(portnp, "phy-handle", 0); + if (!phy_node) + continue; + + phy = of_phy_find_device(phy_node); + of_node_put(phy_node); + if (!phy) + continue; + + err = ocelot_probe_port(ocelot, port, target, phy); + if (err) { + of_node_put(portnp); + return err; + } + + ocelot_port = ocelot->ports[port]; + priv = container_of(ocelot_port, struct ocelot_port_private, + port); + + of_get_phy_mode(portnp, &phy_mode); + + ocelot_port->phy_mode = phy_mode; + + switch (ocelot_port->phy_mode) { + case PHY_INTERFACE_MODE_NA: + continue; + case PHY_INTERFACE_MODE_SGMII: + break; + case PHY_INTERFACE_MODE_QSGMII: + /* Ensure clock signals and speed is set on all + * QSGMII links + */ + ocelot_port_writel(ocelot_port, + DEV_CLOCK_CFG_LINK_SPEED + (OCELOT_SPEED_1000), + DEV_CLOCK_CFG); + break; + default: + dev_err(ocelot->dev, + "invalid phy mode for port%d, (Q)SGMII only\n", + port); + of_node_put(portnp); + return -EINVAL; + } + + serdes = devm_of_phy_get(ocelot->dev, portnp, NULL); + if (IS_ERR(serdes)) { + err = PTR_ERR(serdes); + if (err == -EPROBE_DEFER) + dev_dbg(ocelot->dev, "deferring probe\n"); + else + dev_err(ocelot->dev, + "missing SerDes phys for port%d\n", + port); + + of_node_put(portnp); + return err; + } + + priv->serdes = serdes; + } + + return 0; +} + static int mscc_ocelot_probe(struct platform_device *pdev) { struct device_node *np = pdev->dev.of_node; - struct device_node *ports, *portnp; int err, irq_xtr, irq_ptp_rdy; + struct device_node *ports; struct ocelot *ocelot; struct regmap *hsio; unsigned int i; @@ -985,20 +1113,24 @@ static int mscc_ocelot_probe(struct platform_device *pdev) ports = of_get_child_by_name(np, "ethernet-ports"); if (!ports) { - dev_err(&pdev->dev, "no ethernet-ports child node found\n"); + dev_err(ocelot->dev, "no ethernet-ports child node found\n"); return -ENODEV; } ocelot->num_phys_ports = of_get_child_count(ports); - ocelot->ports = devm_kcalloc(&pdev->dev, ocelot->num_phys_ports, - sizeof(struct ocelot_port *), GFP_KERNEL); - ocelot->vcap_is2_keys = vsc7514_vcap_is2_keys; ocelot->vcap_is2_actions = vsc7514_vcap_is2_actions; ocelot->vcap = vsc7514_vcap_props; - ocelot_init(ocelot); + err = ocelot_init(ocelot); + if (err) + goto out_put_ports; + + err = mscc_ocelot_init_ports(pdev, ports); + if (err) + goto out_put_ports; + if (ocelot->ptp) { err = ocelot_init_timestamp(ocelot, &ocelot_ptp_clock_info); if (err) { @@ -1008,96 +1140,6 @@ static int mscc_ocelot_probe(struct platform_device *pdev) } } - /* No NPI port */ - ocelot_configure_cpu(ocelot, -1, OCELOT_TAG_PREFIX_NONE, - OCELOT_TAG_PREFIX_NONE); - - for_each_available_child_of_node(ports, portnp) { - struct ocelot_port_private *priv; - struct ocelot_port *ocelot_port; - struct device_node *phy_node; - phy_interface_t phy_mode; - struct phy_device *phy; - struct regmap *target; - struct resource *res; - struct phy *serdes; - char res_name[8]; - u32 port; - - if (of_property_read_u32(portnp, "reg", &port)) - continue; - - snprintf(res_name, sizeof(res_name), "port%d", port); - - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, - res_name); - target = ocelot_regmap_init(ocelot, res); - if (IS_ERR(target)) - continue; - - phy_node = of_parse_phandle(portnp, "phy-handle", 0); - if (!phy_node) - continue; - - phy = of_phy_find_device(phy_node); - of_node_put(phy_node); - if (!phy) - continue; - - err = ocelot_probe_port(ocelot, port, target, phy); - if (err) { - of_node_put(portnp); - goto out_put_ports; - } - - ocelot_port = ocelot->ports[port]; - priv = container_of(ocelot_port, struct ocelot_port_private, - port); - - of_get_phy_mode(portnp, &phy_mode); - - ocelot_port->phy_mode = phy_mode; - - switch (ocelot_port->phy_mode) { - case PHY_INTERFACE_MODE_NA: - continue; - case PHY_INTERFACE_MODE_SGMII: - break; - case PHY_INTERFACE_MODE_QSGMII: - /* Ensure clock signals and speed is set on all - * QSGMII links - */ - ocelot_port_writel(ocelot_port, - DEV_CLOCK_CFG_LINK_SPEED - (OCELOT_SPEED_1000), - DEV_CLOCK_CFG); - break; - default: - dev_err(ocelot->dev, - "invalid phy mode for port%d, (Q)SGMII only\n", - port); - of_node_put(portnp); - err = -EINVAL; - goto out_put_ports; - } - - serdes = devm_of_phy_get(ocelot->dev, portnp, NULL); - if (IS_ERR(serdes)) { - err = PTR_ERR(serdes); - if (err == -EPROBE_DEFER) - dev_dbg(ocelot->dev, "deferring probe\n"); - else - dev_err(ocelot->dev, - "missing SerDes phys for port%d\n", - port); - - of_node_put(portnp); - goto out_put_ports; - } - - priv->serdes = serdes; - } - register_netdevice_notifier(&ocelot_netdevice_nb); register_switchdev_notifier(&ocelot_switchdev_nb); register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb); @@ -1114,6 +1156,7 @@ static int mscc_ocelot_remove(struct platform_device *pdev) struct ocelot *ocelot = platform_get_drvdata(pdev); ocelot_deinit_timestamp(ocelot); + mscc_ocelot_release_ports(ocelot); ocelot_deinit(ocelot); unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb); unregister_switchdev_notifier(&ocelot_switchdev_nb); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index 6eb9fb9a1814..9c9ae33d84ce 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -829,8 +829,8 @@ nfp_port_get_fecparam(struct net_device *netdev, struct nfp_eth_table_port *eth_port; struct nfp_port *port; - param->active_fec = ETHTOOL_FEC_NONE_BIT; - param->fec = ETHTOOL_FEC_NONE_BIT; + param->active_fec = ETHTOOL_FEC_NONE; + param->fec = ETHTOOL_FEC_NONE; port = nfp_port_from_netdev(netdev); eth_port = nfp_port_get_eth_port(port); diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index b8f076e4e6b8..3db181f3617a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -4253,7 +4253,8 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) | BIT(QED_MF_LLH_PROTO_CLSS) | BIT(QED_MF_LL2_NON_UNICAST) | - BIT(QED_MF_INTER_PF_SWITCH); + BIT(QED_MF_INTER_PF_SWITCH) | + BIT(QED_MF_DISABLE_ARFS); break; case NVM_CFG1_GLOB_MF_MODE_DEFAULT: cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) | @@ -4266,6 +4267,14 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n", cdev->mf_bits); + + /* In CMT the PF is unknown when the GFS block processes the + * packet. Therefore cannot use searcher as it has a per PF + * database, and thus ARFS must be disabled. + * + */ + if (QED_IS_CMT(cdev)) + cdev->mf_bits |= BIT(QED_MF_DISABLE_ARFS); } DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n", diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 4c6ac8862744..07824bf9d68d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1980,6 +1980,9 @@ void qed_arfs_mode_configure(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_arfs_config_params *p_cfg_params) { + if (test_bit(QED_MF_DISABLE_ARFS, &p_hwfn->cdev->mf_bits)) + return; + if (p_cfg_params->mode != QED_FILTER_CONFIG_MODE_DISABLE) { qed_gft_config(p_hwfn, p_ptt, p_hwfn->rel_pf_id, p_cfg_params->tcp, diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index f39f629242a1..50e5eb22e60a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -444,6 +444,8 @@ int qed_fill_dev_info(struct qed_dev *cdev, dev_info->fw_eng = FW_ENGINEERING_VERSION; dev_info->b_inter_pf_switch = test_bit(QED_MF_INTER_PF_SWITCH, &cdev->mf_bits); + if (!test_bit(QED_MF_DISABLE_ARFS, &cdev->mf_bits)) + dev_info->b_arfs_capable = true; dev_info->tx_switching = true; if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index f1f75b6d0421..b8dc5c4591ef 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -71,6 +71,7 @@ static int qed_sp_vf_start(struct qed_hwfn *p_hwfn, struct qed_vf_info *p_vf) p_ramrod->personality = PERSONALITY_ETH; break; case QED_PCI_ETH_ROCE: + case QED_PCI_ETH_IWARP: p_ramrod->personality = PERSONALITY_RDMA_AND_ETH; break; default: diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index f961f65d9372..c59b72c90293 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -311,6 +311,9 @@ int qede_alloc_arfs(struct qede_dev *edev) { int i; + if (!edev->dev_info.common.b_arfs_capable) + return -EINVAL; + edev->arfs = vzalloc(sizeof(*edev->arfs)); if (!edev->arfs) return -ENOMEM; diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 140a392a81bb..9e1f41ba766c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -804,7 +804,7 @@ static void qede_init_ndev(struct qede_dev *edev) NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_TC; - if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) + if (edev->dev_info.common.b_arfs_capable) hw_features |= NETIF_F_NTUPLE; if (edev->dev_info.common.vxlan_enable || @@ -2274,7 +2274,7 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode, qede_vlan_mark_nonconfigured(edev); edev->ops->fastpath_stop(edev->cdev); - if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { + if (edev->dev_info.common.b_arfs_capable) { qede_poll_for_freeing_arfs_filters(edev); qede_free_arfs(edev); } @@ -2341,10 +2341,9 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode, if (rc) goto err2; - if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1) { - rc = qede_alloc_arfs(edev); - if (rc) - DP_NOTICE(edev, "aRFS memory allocation failed\n"); + if (qede_alloc_arfs(edev)) { + edev->ndev->features &= ~NETIF_F_NTUPLE; + edev->dev_info.common.b_arfs_capable = false; } qede_napi_add_enable(edev); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index fc9e6626db55..11e6962a18e4 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2058,11 +2058,18 @@ static void rtl_release_firmware(struct rtl8169_private *tp) void r8169_apply_firmware(struct rtl8169_private *tp) { + int val; + /* TODO: release firmware if rtl_fw_write_firmware signals failure. */ if (tp->rtl_fw) { rtl_fw_write_firmware(tp, tp->rtl_fw); /* At least one firmware doesn't reset tp->ocp_base. */ tp->ocp_base = OCP_STD_PHY_BASE; + + /* PHY soft reset may still be in progress */ + phy_read_poll_timeout(tp->phydev, MII_BMCR, val, + !(val & BMCR_RESET), + 50000, 600000, true); } } @@ -2239,14 +2246,10 @@ static void rtl_pll_power_down(struct rtl8169_private *tp) default: break; } - - clk_disable_unprepare(tp->clk); } static void rtl_pll_power_up(struct rtl8169_private *tp) { - clk_prepare_enable(tp->clk); - switch (tp->mac_version) { case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33: case RTL_GIGA_MAC_VER_37: @@ -2904,7 +2907,7 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) { 0x08, 0x0001, 0x0002 }, { 0x09, 0x0000, 0x0080 }, { 0x19, 0x0000, 0x0224 }, - { 0x00, 0x0000, 0x0004 }, + { 0x00, 0x0000, 0x0008 }, { 0x0c, 0x3df0, 0x0200 }, }; @@ -2921,7 +2924,7 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp) { 0x06, 0x00c0, 0x0020 }, { 0x0f, 0xffff, 0x5200 }, { 0x19, 0x0000, 0x0224 }, - { 0x00, 0x0000, 0x0004 }, + { 0x00, 0x0000, 0x0008 }, { 0x0c, 0x3df0, 0x0200 }, }; @@ -4826,29 +4829,43 @@ static void rtl8169_net_suspend(struct rtl8169_private *tp) #ifdef CONFIG_PM +static int rtl8169_net_resume(struct rtl8169_private *tp) +{ + rtl_rar_set(tp, tp->dev->dev_addr); + + if (tp->TxDescArray) + rtl8169_up(tp); + + netif_device_attach(tp->dev); + + return 0; +} + static int __maybe_unused rtl8169_suspend(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); rtnl_lock(); rtl8169_net_suspend(tp); + if (!device_may_wakeup(tp_to_dev(tp))) + clk_disable_unprepare(tp->clk); rtnl_unlock(); return 0; } -static int rtl8169_resume(struct device *device) +static int __maybe_unused rtl8169_resume(struct device *device) { struct rtl8169_private *tp = dev_get_drvdata(device); - rtl_rar_set(tp, tp->dev->dev_addr); + if (!device_may_wakeup(tp_to_dev(tp))) + clk_prepare_enable(tp->clk); - if (tp->TxDescArray) - rtl8169_up(tp); + /* Reportedly at least Asus X453MA truncates packets otherwise */ + if (tp->mac_version == RTL_GIGA_MAC_VER_37) + rtl_init_rxcfg(tp); - netif_device_attach(tp->dev); - - return 0; + return rtl8169_net_resume(tp); } static int rtl8169_runtime_suspend(struct device *device) @@ -4874,7 +4891,7 @@ static int rtl8169_runtime_resume(struct device *device) __rtl8169_set_wol(tp, tp->saved_wolopts); - return rtl8169_resume(device); + return rtl8169_net_resume(tp); } static int rtl8169_runtime_idle(struct device *device) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index df89d09b253e..99f7aae102ce 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1342,51 +1342,6 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler, return error; } -/* MDIO bus init function */ -static int ravb_mdio_init(struct ravb_private *priv) -{ - struct platform_device *pdev = priv->pdev; - struct device *dev = &pdev->dev; - int error; - - /* Bitbang init */ - priv->mdiobb.ops = &bb_ops; - - /* MII controller setting */ - priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); - if (!priv->mii_bus) - return -ENOMEM; - - /* Hook up MII support for ethtool */ - priv->mii_bus->name = "ravb_mii"; - priv->mii_bus->parent = dev; - snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", - pdev->name, pdev->id); - - /* Register MDIO bus */ - error = of_mdiobus_register(priv->mii_bus, dev->of_node); - if (error) - goto out_free_bus; - - return 0; - -out_free_bus: - free_mdio_bitbang(priv->mii_bus); - return error; -} - -/* MDIO bus release function */ -static int ravb_mdio_release(struct ravb_private *priv) -{ - /* Unregister mdio bus */ - mdiobus_unregister(priv->mii_bus); - - /* Free bitbang info */ - free_mdio_bitbang(priv->mii_bus); - - return 0; -} - /* Network device open function for Ethernet AVB */ static int ravb_open(struct net_device *ndev) { @@ -1395,13 +1350,6 @@ static int ravb_open(struct net_device *ndev) struct device *dev = &pdev->dev; int error; - /* MDIO bus init */ - error = ravb_mdio_init(priv); - if (error) { - netdev_err(ndev, "failed to initialize MDIO\n"); - return error; - } - napi_enable(&priv->napi[RAVB_BE]); napi_enable(&priv->napi[RAVB_NC]); @@ -1479,7 +1427,6 @@ out_free_irq: out_napi_off: napi_disable(&priv->napi[RAVB_NC]); napi_disable(&priv->napi[RAVB_BE]); - ravb_mdio_release(priv); return error; } @@ -1789,8 +1736,6 @@ static int ravb_close(struct net_device *ndev) ravb_ring_free(ndev, RAVB_BE); ravb_ring_free(ndev, RAVB_NC); - ravb_mdio_release(priv); - return 0; } @@ -1942,6 +1887,51 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_set_features = ravb_set_features, }; +/* MDIO bus init function */ +static int ravb_mdio_init(struct ravb_private *priv) +{ + struct platform_device *pdev = priv->pdev; + struct device *dev = &pdev->dev; + int error; + + /* Bitbang init */ + priv->mdiobb.ops = &bb_ops; + + /* MII controller setting */ + priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); + if (!priv->mii_bus) + return -ENOMEM; + + /* Hook up MII support for ethtool */ + priv->mii_bus->name = "ravb_mii"; + priv->mii_bus->parent = dev; + snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", + pdev->name, pdev->id); + + /* Register MDIO bus */ + error = of_mdiobus_register(priv->mii_bus, dev->of_node); + if (error) + goto out_free_bus; + + return 0; + +out_free_bus: + free_mdio_bitbang(priv->mii_bus); + return error; +} + +/* MDIO bus release function */ +static int ravb_mdio_release(struct ravb_private *priv) +{ + /* Unregister mdio bus */ + mdiobus_unregister(priv->mii_bus); + + /* Free bitbang info */ + free_mdio_bitbang(priv->mii_bus); + + return 0; +} + static const struct of_device_id ravb_match_table[] = { { .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 }, { .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 }, @@ -2184,6 +2174,13 @@ static int ravb_probe(struct platform_device *pdev) eth_hw_addr_random(ndev); } + /* MDIO bus init */ + error = ravb_mdio_init(priv); + if (error) { + dev_err(&pdev->dev, "failed to initialize MDIO\n"); + goto out_dma_free; + } + netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64); netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64); @@ -2205,6 +2202,8 @@ static int ravb_probe(struct platform_device *pdev) out_napi_del: netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); + ravb_mdio_release(priv); +out_dma_free: dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, priv->desc_bat_dma); @@ -2236,6 +2235,7 @@ static int ravb_remove(struct platform_device *pdev) unregister_netdev(ndev); netif_napi_del(&priv->napi[RAVB_NC]); netif_napi_del(&priv->napi[RAVB_BE]); + ravb_mdio_release(priv); pm_runtime_disable(&pdev->dev); free_netdev(ndev); platform_set_drvdata(pdev, NULL); diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 42458a46ffaf..9cc31f7e0df1 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -3099,9 +3099,10 @@ struct rocker_walk_data { struct rocker_port *port; }; -static int rocker_lower_dev_walk(struct net_device *lower_dev, void *_data) +static int rocker_lower_dev_walk(struct net_device *lower_dev, + struct netdev_nested_priv *priv) { - struct rocker_walk_data *data = _data; + struct rocker_walk_data *data = (struct rocker_walk_data *)priv->data; int ret = 0; if (rocker_port_dev_check_under(lower_dev, data->rocker)) { @@ -3115,6 +3116,7 @@ static int rocker_lower_dev_walk(struct net_device *lower_dev, void *_data) struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev, struct rocker *rocker) { + struct netdev_nested_priv priv; struct rocker_walk_data data; if (rocker_port_dev_check_under(dev, rocker)) @@ -3122,7 +3124,8 @@ struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev, data.rocker = rocker; data.port = NULL; - netdev_walk_all_lower_dev(dev, rocker_lower_dev_walk, &data); + priv.data = (void *)&data; + netdev_walk_all_lower_dev(dev, rocker_lower_dev_walk, &priv); return data.port; } diff --git a/drivers/net/ethernet/sfc/ef100.c b/drivers/net/ethernet/sfc/ef100.c index c54b7f8243f3..ffdb36715a49 100644 --- a/drivers/net/ethernet/sfc/ef100.c +++ b/drivers/net/ethernet/sfc/ef100.c @@ -490,6 +490,7 @@ static int ef100_pci_probe(struct pci_dev *pci_dev, if (fcw.offset > pci_resource_len(efx->pci_dev, fcw.bar) - ESE_GZ_FCW_LEN) { netif_err(efx, probe, efx->net_dev, "Func control window overruns BAR\n"); + rc = -EIO; goto fail; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 2ac9dfb3462c..9e6d60e75f85 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -653,7 +653,6 @@ static void intel_eth_pci_remove(struct pci_dev *pdev) pci_free_irq_vectors(pdev); - clk_disable_unprepare(priv->plat->stmmac_clk); clk_unregister_fixed_rate(priv->plat->stmmac_clk); pcim_iounmap_regions(pdev, BIT(0)); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 9c02fc754bf1..545696971f65 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -203,6 +203,8 @@ struct stmmac_priv { int eee_enabled; int eee_active; int tx_lpi_timer; + int tx_lpi_enabled; + int eee_tw_timer; unsigned int mode; unsigned int chain_mode; int extend_desc; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index ac5e8cc5fb9f..814879f91f76 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -665,6 +665,7 @@ static int stmmac_ethtool_op_get_eee(struct net_device *dev, edata->eee_enabled = priv->eee_enabled; edata->eee_active = priv->eee_active; edata->tx_lpi_timer = priv->tx_lpi_timer; + edata->tx_lpi_enabled = priv->tx_lpi_enabled; return phylink_ethtool_get_eee(priv->phylink, edata); } @@ -675,24 +676,26 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev, struct stmmac_priv *priv = netdev_priv(dev); int ret; - if (!edata->eee_enabled) { + if (!priv->dma_cap.eee) + return -EOPNOTSUPP; + + if (priv->tx_lpi_enabled != edata->tx_lpi_enabled) + netdev_warn(priv->dev, + "Setting EEE tx-lpi is not supported\n"); + + if (!edata->eee_enabled) stmmac_disable_eee_mode(priv); - } else { - /* We are asking for enabling the EEE but it is safe - * to verify all by invoking the eee_init function. - * In case of failure it will return an error. - */ - edata->eee_enabled = stmmac_eee_init(priv); - if (!edata->eee_enabled) - return -EOPNOTSUPP; - } ret = phylink_ethtool_set_eee(priv->phylink, edata); if (ret) return ret; - priv->eee_enabled = edata->eee_enabled; - priv->tx_lpi_timer = edata->tx_lpi_timer; + if (edata->eee_enabled && + priv->tx_lpi_timer != edata->tx_lpi_timer) { + priv->tx_lpi_timer = edata->tx_lpi_timer; + stmmac_eee_init(priv); + } + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 89b2b3472852..b56b13d64ab4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -94,7 +94,7 @@ static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE | static int eee_timer = STMMAC_DEFAULT_LPI_TIMER; module_param(eee_timer, int, 0644); MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec"); -#define STMMAC_LPI_T(x) (jiffies + msecs_to_jiffies(x)) +#define STMMAC_LPI_T(x) (jiffies + usecs_to_jiffies(x)) /* By default the driver will use the ring mode to manage tx and rx descriptors, * but allow user to force to use the chain instead of the ring @@ -370,7 +370,7 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t) struct stmmac_priv *priv = from_timer(priv, t, eee_ctrl_timer); stmmac_enable_eee_mode(priv); - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); } /** @@ -383,7 +383,7 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t) */ bool stmmac_eee_init(struct stmmac_priv *priv) { - int tx_lpi_timer = priv->tx_lpi_timer; + int eee_tw_timer = priv->eee_tw_timer; /* Using PCS we cannot dial with the phy registers at this stage * so we do not support extra feature like EEE. @@ -403,7 +403,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv) if (priv->eee_enabled) { netdev_dbg(priv->dev, "disable EEE\n"); del_timer_sync(&priv->eee_ctrl_timer); - stmmac_set_eee_timer(priv, priv->hw, 0, tx_lpi_timer); + stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer); } mutex_unlock(&priv->lock); return false; @@ -411,11 +411,12 @@ bool stmmac_eee_init(struct stmmac_priv *priv) if (priv->eee_active && !priv->eee_enabled) { timer_setup(&priv->eee_ctrl_timer, stmmac_eee_ctrl_timer, 0); - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS, - tx_lpi_timer); + eee_tw_timer); } + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); + mutex_unlock(&priv->lock); netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n"); return true; @@ -930,6 +931,7 @@ static void stmmac_mac_link_down(struct phylink_config *config, stmmac_mac_set(priv, priv->ioaddr, false); priv->eee_active = false; + priv->tx_lpi_enabled = false; stmmac_eee_init(priv); stmmac_set_eee_pls(priv, priv->hw, false); } @@ -1027,6 +1029,7 @@ static void stmmac_mac_link_up(struct phylink_config *config, if (phy && priv->dma_cap.eee) { priv->eee_active = phy_init_eee(phy, 1) >= 0; priv->eee_enabled = stmmac_eee_init(priv); + priv->tx_lpi_enabled = priv->eee_enabled; stmmac_set_eee_pls(priv, priv->hw, true); } } @@ -2061,7 +2064,7 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) { stmmac_enable_eee_mode(priv); - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); + mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); } /* We still have pending packets, let's call for a new scheduling */ @@ -2694,7 +2697,11 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) netdev_warn(priv->dev, "PTP init failed\n"); } - priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS; + priv->eee_tw_timer = STMMAC_DEFAULT_TWT_LS; + + /* Convert the timer from msec to usec */ + if (!priv->tx_lpi_timer) + priv->tx_lpi_timer = eee_timer * 1000; if (priv->use_riwt) { if (!priv->rx_riwt) diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 8ed78577cded..15672d0a4de6 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -17,6 +17,7 @@ #include <linux/phy.h> #include <linux/phy/phy.h> #include <linux/delay.h> +#include <linux/pinctrl/consumer.h> #include <linux/pm_runtime.h> #include <linux/gpio/consumer.h> #include <linux/of.h> @@ -2070,9 +2071,61 @@ static int cpsw_remove(struct platform_device *pdev) return 0; } +static int __maybe_unused cpsw_suspend(struct device *dev) +{ + struct cpsw_common *cpsw = dev_get_drvdata(dev); + int i; + + rtnl_lock(); + + for (i = 0; i < cpsw->data.slaves; i++) { + struct net_device *ndev = cpsw->slaves[i].ndev; + + if (!(ndev && netif_running(ndev))) + continue; + + cpsw_ndo_stop(ndev); + } + + rtnl_unlock(); + + /* Select sleep pin state */ + pinctrl_pm_select_sleep_state(dev); + + return 0; +} + +static int __maybe_unused cpsw_resume(struct device *dev) +{ + struct cpsw_common *cpsw = dev_get_drvdata(dev); + int i; + + /* Select default pin state */ + pinctrl_pm_select_default_state(dev); + + /* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */ + rtnl_lock(); + + for (i = 0; i < cpsw->data.slaves; i++) { + struct net_device *ndev = cpsw->slaves[i].ndev; + + if (!(ndev && netif_running(ndev))) + continue; + + cpsw_ndo_open(ndev); + } + + rtnl_unlock(); + + return 0; +} + +static SIMPLE_DEV_PM_OPS(cpsw_pm_ops, cpsw_suspend, cpsw_resume); + static struct platform_driver cpsw_driver = { .driver = { .name = "cpsw-switch", + .pm = &cpsw_pm_ops, .of_match_table = cpsw_of_mtable, }, .probe = cpsw_probe, diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 803247d51fe9..55b0ddab1776 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -2,7 +2,7 @@ /* Written 1998-2001 by Donald Becker. - Current Maintainer: Roger Luethi <rl@hellgate.ch> + Current Maintainer: Kevin Brace <kevinbrace@bracecomputerlab.com> This software may be used and distributed according to the terms of the GNU General Public License (GPL), incorporated herein by reference. @@ -32,8 +32,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #define DRV_NAME "via-rhine" -#define DRV_VERSION "1.5.1" -#define DRV_RELDATE "2010-10-09" #include <linux/types.h> @@ -117,10 +115,6 @@ static const int multicast_filter_limit = 32; #include <linux/uaccess.h> #include <linux/dmi.h> -/* These identify the driver base version and may not be removed. */ -static const char version[] = - "v1.10-LK" DRV_VERSION " " DRV_RELDATE " Written by Donald Becker"; - MODULE_AUTHOR("Donald Becker <becker@scyld.com>"); MODULE_DESCRIPTION("VIA Rhine PCI Fast Ethernet driver"); MODULE_LICENSE("GPL"); @@ -243,7 +237,7 @@ enum rhine_revs { VT8233 = 0x60, /* Integrated MAC */ VT8235 = 0x74, /* Integrated MAC */ VT8237 = 0x78, /* Integrated MAC */ - VTunknown1 = 0x7C, + VT8251 = 0x7C, /* Integrated MAC */ VT6105 = 0x80, VT6105_B0 = 0x83, VT6105L = 0x8A, @@ -1051,11 +1045,6 @@ static int rhine_init_one_pci(struct pci_dev *pdev, u32 quirks = 0; #endif -/* when built into the kernel, we only print version if device is found */ -#ifndef MODULE - pr_info_once("%s\n", version); -#endif - rc = pci_enable_device(pdev); if (rc) goto err_out; @@ -1706,6 +1695,8 @@ static int rhine_open(struct net_device *dev) goto out_free_ring; alloc_tbufs(dev); + enable_mmio(rp->pioaddr, rp->quirks); + rhine_power_init(dev); rhine_chip_reset(dev); rhine_task_enable(rp); init_registers(dev); @@ -2294,7 +2285,6 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i struct device *hwdev = dev->dev.parent; strlcpy(info->driver, DRV_NAME, sizeof(info->driver)); - strlcpy(info->version, DRV_VERSION, sizeof(info->version)); strlcpy(info->bus_info, dev_name(hwdev), sizeof(info->bus_info)); } @@ -2616,9 +2606,6 @@ static int __init rhine_init(void) int ret_pci, ret_platform; /* when a module, this is printed whether or not devices are found in probe */ -#ifdef MODULE - pr_info("%s\n", version); -#endif if (dmi_check_system(rhine_dmi_table)) { /* these BIOSes fail at PXE boot if chip is in D3 */ avoid_D3 = true; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index c71f994fbc73..974a244f45ba 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -777,7 +777,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, struct net_device *dev, struct geneve_sock *gs4, struct flowi4 *fl4, - const struct ip_tunnel_info *info) + const struct ip_tunnel_info *info, + __be16 dport, __be16 sport) { bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct geneve_dev *geneve = netdev_priv(dev); @@ -793,6 +794,8 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, fl4->flowi4_proto = IPPROTO_UDP; fl4->daddr = info->key.u.ipv4.dst; fl4->saddr = info->key.u.ipv4.src; + fl4->fl4_dport = dport; + fl4->fl4_sport = sport; tos = info->key.tos; if ((tos == 1) && !geneve->cfg.collect_md) { @@ -827,7 +830,8 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, struct net_device *dev, struct geneve_sock *gs6, struct flowi6 *fl6, - const struct ip_tunnel_info *info) + const struct ip_tunnel_info *info, + __be16 dport, __be16 sport) { bool use_cache = ip_tunnel_dst_cache_usable(skb, info); struct geneve_dev *geneve = netdev_priv(dev); @@ -843,6 +847,9 @@ static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, fl6->flowi6_proto = IPPROTO_UDP; fl6->daddr = info->key.u.ipv6.dst; fl6->saddr = info->key.u.ipv6.src; + fl6->fl6_dport = dport; + fl6->fl6_sport = sport; + prio = info->key.tos; if ((prio == 1) && !geneve->cfg.collect_md) { prio = ip_tunnel_get_dsfield(ip_hdr(skb), skb); @@ -889,7 +896,9 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info); + sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); + rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info, + geneve->cfg.info.key.tp_dst, sport); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -919,7 +928,6 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, return -EMSGSIZE; } - sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); if (geneve->cfg.collect_md) { tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; @@ -974,7 +982,9 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; - dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info); + sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); + dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info, + geneve->cfg.info.key.tp_dst, sport); if (IS_ERR(dst)) return PTR_ERR(dst); @@ -1003,7 +1013,6 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, return -EMSGSIZE; } - sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); if (geneve->cfg.collect_md) { prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; @@ -1085,13 +1094,18 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); struct geneve_dev *geneve = netdev_priv(dev); + __be16 sport; if (ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; struct flowi4 fl4; + struct geneve_sock *gs4 = rcu_dereference(geneve->sock4); + sport = udp_flow_src_port(geneve->net, skb, + 1, USHRT_MAX, true); - rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info); + rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info, + geneve->cfg.info.key.tp_dst, sport); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -1101,9 +1115,13 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; struct flowi6 fl6; + struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); + sport = udp_flow_src_port(geneve->net, skb, + 1, USHRT_MAX, true); - dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info); + dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info, + geneve->cfg.info.key.tp_dst, sport); if (IS_ERR(dst)) return PTR_ERR(dst); @@ -1114,8 +1132,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) return -EINVAL; } - info->key.tp_src = udp_flow_src_port(geneve->net, skb, - 1, USHRT_MAX, true); + info->key.tp_src = sport; info->key.tp_dst = geneve->cfg.info.key.tp_dst; return 0; } diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 2181d4538ab7..a0f338cf1424 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -847,6 +847,10 @@ struct nvsp_message { #define NETVSC_XDP_HDRM 256 +#define NETVSC_XFER_HEADER_SIZE(rng_cnt) \ + (offsetof(struct vmtransfer_page_packet_header, ranges) + \ + (rng_cnt) * sizeof(struct vmtransfer_page_range)) + struct multi_send_data { struct sk_buff *skb; /* skb containing the pkt */ struct hv_netvsc_packet *pkt; /* netvsc pkt pending */ @@ -974,6 +978,9 @@ struct net_device_context { /* Serial number of the VF to team with */ u32 vf_serial; + /* Is the current data path through the VF NIC? */ + bool data_path_is_vf; + /* Used to temporarily save the config info across hibernation */ struct netvsc_device_info *saved_netvsc_dev_info; }; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 41f5cf0bb997..5a57d1985bae 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -388,6 +388,15 @@ static int netvsc_init_buf(struct hv_device *device, net_device->recv_section_size = resp->sections[0].sub_alloc_size; net_device->recv_section_cnt = resp->sections[0].num_sub_allocs; + /* Ensure buffer will not overflow */ + if (net_device->recv_section_size < NETVSC_MTU_MIN || (u64)net_device->recv_section_size * + (u64)net_device->recv_section_cnt > (u64)buf_size) { + netdev_err(ndev, "invalid recv_section_size %u\n", + net_device->recv_section_size); + ret = -EINVAL; + goto cleanup; + } + /* Setup receive completion ring. * Add 1 to the recv_section_cnt because at least one entry in a * ring buffer has to be empty. @@ -460,6 +469,12 @@ static int netvsc_init_buf(struct hv_device *device, /* Parse the response */ net_device->send_section_size = init_packet->msg. v1_msg.send_send_buf_complete.section_size; + if (net_device->send_section_size < NETVSC_MTU_MIN) { + netdev_err(ndev, "invalid send_section_size %u\n", + net_device->send_section_size); + ret = -EINVAL; + goto cleanup; + } /* Section count is simply the size divided by the section size. */ net_device->send_section_cnt = buf_size / net_device->send_section_size; @@ -731,12 +746,49 @@ static void netvsc_send_completion(struct net_device *ndev, int budget) { const struct nvsp_message *nvsp_packet = hv_pkt_data(desc); + u32 msglen = hv_pkt_datalen(desc); + + /* Ensure packet is big enough to read header fields */ + if (msglen < sizeof(struct nvsp_message_header)) { + netdev_err(ndev, "nvsp_message length too small: %u\n", msglen); + return; + } switch (nvsp_packet->hdr.msg_type) { case NVSP_MSG_TYPE_INIT_COMPLETE: + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_message_init_complete)) { + netdev_err(ndev, "nvsp_msg length too small: %u\n", + msglen); + return; + } + fallthrough; + case NVSP_MSG1_TYPE_SEND_RECV_BUF_COMPLETE: + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_1_message_send_receive_buffer_complete)) { + netdev_err(ndev, "nvsp_msg1 length too small: %u\n", + msglen); + return; + } + fallthrough; + case NVSP_MSG1_TYPE_SEND_SEND_BUF_COMPLETE: + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_1_message_send_send_buffer_complete)) { + netdev_err(ndev, "nvsp_msg1 length too small: %u\n", + msglen); + return; + } + fallthrough; + case NVSP_MSG5_TYPE_SUBCHANNEL: + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_5_subchannel_complete)) { + netdev_err(ndev, "nvsp_msg5 length too small: %u\n", + msglen); + return; + } /* Copy the response back */ memcpy(&net_device->channel_init_pkt, nvsp_packet, sizeof(struct nvsp_message)); @@ -1117,19 +1169,28 @@ static void enq_receive_complete(struct net_device *ndev, static int netvsc_receive(struct net_device *ndev, struct netvsc_device *net_device, struct netvsc_channel *nvchan, - const struct vmpacket_descriptor *desc, - const struct nvsp_message *nvsp) + const struct vmpacket_descriptor *desc) { struct net_device_context *net_device_ctx = netdev_priv(ndev); struct vmbus_channel *channel = nvchan->channel; const struct vmtransfer_page_packet_header *vmxferpage_packet = container_of(desc, const struct vmtransfer_page_packet_header, d); + const struct nvsp_message *nvsp = hv_pkt_data(desc); + u32 msglen = hv_pkt_datalen(desc); u16 q_idx = channel->offermsg.offer.sub_channel_index; char *recv_buf = net_device->recv_buf; u32 status = NVSP_STAT_SUCCESS; int i; int count = 0; + /* Ensure packet is big enough to read header fields */ + if (msglen < sizeof(struct nvsp_message_header)) { + netif_err(net_device_ctx, rx_err, ndev, + "invalid nvsp header, length too small: %u\n", + msglen); + return 0; + } + /* Make sure this is a valid nvsp packet */ if (unlikely(nvsp->hdr.msg_type != NVSP_MSG1_TYPE_SEND_RNDIS_PKT)) { netif_err(net_device_ctx, rx_err, ndev, @@ -1138,6 +1199,14 @@ static int netvsc_receive(struct net_device *ndev, return 0; } + /* Validate xfer page pkt header */ + if ((desc->offset8 << 3) < sizeof(struct vmtransfer_page_packet_header)) { + netif_err(net_device_ctx, rx_err, ndev, + "Invalid xfer page pkt, offset too small: %u\n", + desc->offset8 << 3); + return 0; + } + if (unlikely(vmxferpage_packet->xfer_pageset_id != NETVSC_RECEIVE_BUFFER_ID)) { netif_err(net_device_ctx, rx_err, ndev, "Invalid xfer page set id - expecting %x got %x\n", @@ -1148,6 +1217,14 @@ static int netvsc_receive(struct net_device *ndev, count = vmxferpage_packet->range_cnt; + /* Check count for a valid value */ + if (NETVSC_XFER_HEADER_SIZE(count) > desc->offset8 << 3) { + netif_err(net_device_ctx, rx_err, ndev, + "Range count is not valid: %d\n", + count); + return 0; + } + /* Each range represents 1 RNDIS pkt that contains 1 ethernet frame */ for (i = 0; i < count; i++) { u32 offset = vmxferpage_packet->ranges[i].byte_offset; @@ -1155,7 +1232,8 @@ static int netvsc_receive(struct net_device *ndev, void *data; int ret; - if (unlikely(offset + buflen > net_device->recv_buf_size)) { + if (unlikely(offset > net_device->recv_buf_size || + buflen > net_device->recv_buf_size - offset)) { nvchan->rsc.cnt = 0; status = NVSP_STAT_FAIL; netif_err(net_device_ctx, rx_err, ndev, @@ -1194,6 +1272,13 @@ static void netvsc_send_table(struct net_device *ndev, u32 count, offset, *tab; int i; + /* Ensure packet is big enough to read send_table fields */ + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_5_send_indirect_table)) { + netdev_err(ndev, "nvsp_v5_msg length too small: %u\n", msglen); + return; + } + count = nvmsg->msg.v5_msg.send_table.count; offset = nvmsg->msg.v5_msg.send_table.offset; @@ -1225,10 +1310,18 @@ static void netvsc_send_table(struct net_device *ndev, } static void netvsc_send_vf(struct net_device *ndev, - const struct nvsp_message *nvmsg) + const struct nvsp_message *nvmsg, + u32 msglen) { struct net_device_context *net_device_ctx = netdev_priv(ndev); + /* Ensure packet is big enough to read its fields */ + if (msglen < sizeof(struct nvsp_message_header) + + sizeof(struct nvsp_4_send_vf_association)) { + netdev_err(ndev, "nvsp_v4_msg length too small: %u\n", msglen); + return; + } + net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; netdev_info(ndev, "VF slot %u %s\n", @@ -1238,16 +1331,24 @@ static void netvsc_send_vf(struct net_device *ndev, static void netvsc_receive_inband(struct net_device *ndev, struct netvsc_device *nvscdev, - const struct nvsp_message *nvmsg, - u32 msglen) + const struct vmpacket_descriptor *desc) { + const struct nvsp_message *nvmsg = hv_pkt_data(desc); + u32 msglen = hv_pkt_datalen(desc); + + /* Ensure packet is big enough to read header fields */ + if (msglen < sizeof(struct nvsp_message_header)) { + netdev_err(ndev, "inband nvsp_message length too small: %u\n", msglen); + return; + } + switch (nvmsg->hdr.msg_type) { case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE: netvsc_send_table(ndev, nvscdev, nvmsg, msglen); break; case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION: - netvsc_send_vf(ndev, nvmsg); + netvsc_send_vf(ndev, nvmsg, msglen); break; } } @@ -1261,23 +1362,20 @@ static int netvsc_process_raw_pkt(struct hv_device *device, { struct vmbus_channel *channel = nvchan->channel; const struct nvsp_message *nvmsg = hv_pkt_data(desc); - u32 msglen = hv_pkt_datalen(desc); trace_nvsp_recv(ndev, channel, nvmsg); switch (desc->type) { case VM_PKT_COMP: - netvsc_send_completion(ndev, net_device, channel, - desc, budget); + netvsc_send_completion(ndev, net_device, channel, desc, budget); break; case VM_PKT_DATA_USING_XFER_PAGES: - return netvsc_receive(ndev, net_device, nvchan, - desc, nvmsg); + return netvsc_receive(ndev, net_device, nvchan, desc); break; case VM_PKT_DATA_INBAND: - netvsc_receive_inband(ndev, net_device, nvmsg, msglen); + netvsc_receive_inband(ndev, net_device, desc); break; default: diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 64b0a74c1523..9869e390875e 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -748,6 +748,13 @@ void netvsc_linkstatus_callback(struct net_device *net, struct netvsc_reconfig *event; unsigned long flags; + /* Ensure the packet is big enough to access its fields */ + if (resp->msg_len - RNDIS_HEADER_SIZE < sizeof(struct rndis_indicate_status)) { + netdev_err(net, "invalid rndis_indicate_status packet, len: %u\n", + resp->msg_len); + return; + } + /* Update the physical link speed when changing to another vSwitch */ if (indicate->status == RNDIS_STATUS_LINK_SPEED_CHANGE) { u32 speed; @@ -2366,7 +2373,16 @@ static int netvsc_register_vf(struct net_device *vf_netdev) return NOTIFY_OK; } -/* VF up/down change detected, schedule to change data path */ +/* Change the data path when VF UP/DOWN/CHANGE are detected. + * + * Typically a UP or DOWN event is followed by a CHANGE event, so + * net_device_ctx->data_path_is_vf is used to cache the current data path + * to avoid the duplicate call of netvsc_switch_datapath() and the duplicate + * message. + * + * During hibernation, if a VF NIC driver (e.g. mlx5) preserves the network + * interface, there is only the CHANGE event and no UP or DOWN event. + */ static int netvsc_vf_changed(struct net_device *vf_netdev) { struct net_device_context *net_device_ctx; @@ -2383,6 +2399,10 @@ static int netvsc_vf_changed(struct net_device *vf_netdev) if (!netvsc_dev) return NOTIFY_DONE; + if (net_device_ctx->data_path_is_vf == vf_is_up) + return NOTIFY_OK; + net_device_ctx->data_path_is_vf = vf_is_up; + netvsc_switch_datapath(ndev, vf_is_up); netdev_info(ndev, "Data path switched %s VF: %s\n", vf_is_up ? "to" : "from", vf_netdev->name); @@ -2587,8 +2607,8 @@ static int netvsc_remove(struct hv_device *dev) static int netvsc_suspend(struct hv_device *dev) { struct net_device_context *ndev_ctx; - struct net_device *vf_netdev, *net; struct netvsc_device *nvdev; + struct net_device *net; int ret; net = hv_get_drvdata(dev); @@ -2604,10 +2624,6 @@ static int netvsc_suspend(struct hv_device *dev) goto out; } - vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); - if (vf_netdev) - netvsc_unregister_vf(vf_netdev); - /* Save the current config info */ ndev_ctx->saved_netvsc_dev_info = netvsc_devinfo_get(nvdev); @@ -2628,6 +2644,12 @@ static int netvsc_resume(struct hv_device *dev) rtnl_lock(); net_device_ctx = netdev_priv(net); + + /* Reset the data path to the netvsc NIC before re-opening the vmbus + * channel. Later netvsc_netdev_event() will switch the data path to + * the VF upon the UP or CHANGE event. + */ + net_device_ctx->data_path_is_vf = false; device_info = net_device_ctx->saved_netvsc_dev_info; ret = netvsc_attach(net, device_info); @@ -2695,6 +2717,7 @@ static int netvsc_netdev_event(struct notifier_block *this, return netvsc_unregister_vf(event_dev); case NETDEV_UP: case NETDEV_DOWN: + case NETDEV_CHANGE: return netvsc_vf_changed(event_dev); default: return NOTIFY_DONE; diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index b81ceba38218..12ad471ac5e1 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -275,6 +275,16 @@ static void rndis_filter_receive_response(struct net_device *ndev, return; } + /* Ensure the packet is big enough to read req_id. Req_id is the 1st + * field in any request/response message, so the payload should have at + * least sizeof(u32) bytes + */ + if (resp->msg_len - RNDIS_HEADER_SIZE < sizeof(u32)) { + netdev_err(ndev, "rndis msg_len too small: %u\n", + resp->msg_len); + return; + } + spin_lock_irqsave(&dev->request_lock, flags); list_for_each_entry(request, &dev->req_list, list_ent) { /* @@ -331,8 +341,9 @@ static void rndis_filter_receive_response(struct net_device *ndev, * Get the Per-Packet-Info with the specified type * return NULL if not found. */ -static inline void *rndis_get_ppi(struct rndis_packet *rpkt, - u32 type, u8 internal) +static inline void *rndis_get_ppi(struct net_device *ndev, + struct rndis_packet *rpkt, + u32 rpkt_len, u32 type, u8 internal) { struct rndis_per_packet_info *ppi; int len; @@ -340,11 +351,36 @@ static inline void *rndis_get_ppi(struct rndis_packet *rpkt, if (rpkt->per_pkt_info_offset == 0) return NULL; + /* Validate info_offset and info_len */ + if (rpkt->per_pkt_info_offset < sizeof(struct rndis_packet) || + rpkt->per_pkt_info_offset > rpkt_len) { + netdev_err(ndev, "Invalid per_pkt_info_offset: %u\n", + rpkt->per_pkt_info_offset); + return NULL; + } + + if (rpkt->per_pkt_info_len > rpkt_len - rpkt->per_pkt_info_offset) { + netdev_err(ndev, "Invalid per_pkt_info_len: %u\n", + rpkt->per_pkt_info_len); + return NULL; + } + ppi = (struct rndis_per_packet_info *)((ulong)rpkt + rpkt->per_pkt_info_offset); len = rpkt->per_pkt_info_len; while (len > 0) { + /* Validate ppi_offset and ppi_size */ + if (ppi->size > len) { + netdev_err(ndev, "Invalid ppi size: %u\n", ppi->size); + continue; + } + + if (ppi->ppi_offset >= ppi->size) { + netdev_err(ndev, "Invalid ppi_offset: %u\n", ppi->ppi_offset); + continue; + } + if (ppi->type == type && ppi->internal == internal) return (void *)((ulong)ppi + ppi->ppi_offset); len -= ppi->size; @@ -388,14 +424,29 @@ static int rndis_filter_receive_data(struct net_device *ndev, const struct ndis_pkt_8021q_info *vlan; const struct rndis_pktinfo_id *pktinfo_id; const u32 *hash_info; - u32 data_offset; + u32 data_offset, rpkt_len; void *data; bool rsc_more = false; int ret; + /* Ensure data_buflen is big enough to read header fields */ + if (data_buflen < RNDIS_HEADER_SIZE + sizeof(struct rndis_packet)) { + netdev_err(ndev, "invalid rndis pkt, data_buflen too small: %u\n", + data_buflen); + return NVSP_STAT_FAIL; + } + + /* Validate rndis_pkt offset */ + if (rndis_pkt->data_offset >= data_buflen - RNDIS_HEADER_SIZE) { + netdev_err(ndev, "invalid rndis packet offset: %u\n", + rndis_pkt->data_offset); + return NVSP_STAT_FAIL; + } + /* Remove the rndis header and pass it back up the stack */ data_offset = RNDIS_HEADER_SIZE + rndis_pkt->data_offset; + rpkt_len = data_buflen - RNDIS_HEADER_SIZE; data_buflen -= data_offset; /* @@ -410,13 +461,13 @@ static int rndis_filter_receive_data(struct net_device *ndev, return NVSP_STAT_FAIL; } - vlan = rndis_get_ppi(rndis_pkt, IEEE_8021Q_INFO, 0); + vlan = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, IEEE_8021Q_INFO, 0); - csum_info = rndis_get_ppi(rndis_pkt, TCPIP_CHKSUM_PKTINFO, 0); + csum_info = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, TCPIP_CHKSUM_PKTINFO, 0); - hash_info = rndis_get_ppi(rndis_pkt, NBL_HASH_VALUE, 0); + hash_info = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, NBL_HASH_VALUE, 0); - pktinfo_id = rndis_get_ppi(rndis_pkt, RNDIS_PKTINFO_ID, 1); + pktinfo_id = rndis_get_ppi(ndev, rndis_pkt, rpkt_len, RNDIS_PKTINFO_ID, 1); data = (void *)msg + data_offset; @@ -474,6 +525,14 @@ int rndis_filter_receive(struct net_device *ndev, if (netif_msg_rx_status(net_device_ctx)) dump_rndis_message(ndev, rndis_msg); + /* Validate incoming rndis_message packet */ + if (buflen < RNDIS_HEADER_SIZE || rndis_msg->msg_len < RNDIS_HEADER_SIZE || + buflen < rndis_msg->msg_len) { + netdev_err(ndev, "Invalid rndis_msg (buflen: %u, msg_len: %u)\n", + buflen, rndis_msg->msg_len); + return NVSP_STAT_FAIL; + } + switch (rndis_msg->ndis_msg_type) { case RNDIS_MSG_PACKET: return rndis_filter_receive_data(ndev, net_dev, nvchan, diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index c11f32f644db..7db9cbd0f5de 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -882,7 +882,9 @@ static int adf7242_rx(struct adf7242_local *lp) int ret; u8 lqi, len_u8, *data; - adf7242_read_reg(lp, 0, &len_u8); + ret = adf7242_read_reg(lp, 0, &len_u8); + if (ret) + return ret; len = len_u8; diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index e04c3b60cae7..4eb64709d44c 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -2925,6 +2925,7 @@ static int ca8210_dev_com_init(struct ca8210_priv *priv) ); if (!priv->irq_workqueue) { dev_crit(&priv->spi->dev, "alloc of irq_workqueue failed!\n"); + destroy_workqueue(priv->mlme_workqueue); return -ENOMEM; } diff --git a/drivers/net/ipa/ipa_table.c b/drivers/net/ipa/ipa_table.c index 2098ca2f2c90..b3790aa952a1 100644 --- a/drivers/net/ipa/ipa_table.c +++ b/drivers/net/ipa/ipa_table.c @@ -521,7 +521,7 @@ static void ipa_filter_tuple_zero(struct ipa_endpoint *endpoint) val = ioread32(endpoint->ipa->reg_virt + offset); /* Zero all filter-related fields, preserving the rest */ - u32_replace_bits(val, 0, IPA_REG_ENDP_FILTER_HASH_MSK_ALL); + u32p_replace_bits(&val, 0, IPA_REG_ENDP_FILTER_HASH_MSK_ALL); iowrite32(val, endpoint->ipa->reg_virt + offset); } @@ -573,7 +573,7 @@ static void ipa_route_tuple_zero(struct ipa *ipa, u32 route_id) val = ioread32(ipa->reg_virt + offset); /* Zero all route-related fields, preserving the rest */ - u32_replace_bits(val, 0, IPA_REG_ENDP_ROUTER_HASH_MSK_ALL); + u32p_replace_bits(&val, 0, IPA_REG_ENDP_ROUTER_HASH_MSK_ALL); iowrite32(val, ipa->reg_virt + offset); } diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 9159846b8b93..787ac2c8e74e 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1077,6 +1077,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb) struct macsec_rx_sa *rx_sa; struct macsec_rxh_data *rxd; struct macsec_dev *macsec; + unsigned int len; sci_t sci; u32 hdr_pn; bool cbit; @@ -1232,9 +1233,10 @@ deliver: macsec_rxsc_put(rx_sc); skb_orphan(skb); + len = skb->len; ret = gro_cells_receive(&macsec->gro_cells, skb); if (ret == NET_RX_SUCCESS) - count_rx(dev, skb->len); + count_rx(dev, len); else macsec->secy.netdev->stats.rx_dropped++; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 726e4b240e7e..1c5a10b672fc 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -222,6 +222,7 @@ config MDIO_THUNDER depends on 64BIT depends on PCI select MDIO_CAVIUM + select MDIO_DEVRES help This driver supports the MDIO interfaces found on Cavium ThunderX SoCs when the MDIO bus device appears as a PCI diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 735a806045ac..8947d58f2a25 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -996,7 +996,7 @@ void phy_stop(struct phy_device *phydev) { struct net_device *dev = phydev->attached_dev; - if (!phy_is_started(phydev)) { + if (!phy_is_started(phydev) && phydev->state != PHY_DOWN) { WARN(1, "called from state %s\n", phy_state_to_str(phydev->state)); return; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8adfbad0a1e8..5dab6be6fc38 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1143,10 +1143,6 @@ int phy_init_hw(struct phy_device *phydev) if (ret < 0) return ret; - ret = phy_disable_interrupts(phydev); - if (ret) - return ret; - if (phydev->drv->config_init) ret = phydev->drv->config_init(phydev); @@ -1423,6 +1419,10 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, if (err) goto error; + err = phy_disable_interrupts(phydev); + if (err) + return err; + phy_resume(phydev); phy_led_triggers_register(phydev); @@ -1682,7 +1682,8 @@ void phy_detach(struct phy_device *phydev) phy_led_triggers_unregister(phydev); - module_put(phydev->mdio.dev.driver->owner); + if (phydev->mdio.dev.driver) + module_put(phydev->mdio.dev.driver->owner); /* If the device had no specific driver before (i.e. - it * was using the generic driver), we unbind the device diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 95dbe5e8e1d8..0f0960971800 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0+ -/* - * drivers/net/phy/realtek.c +/* drivers/net/phy/realtek.c * * Driver for Realtek PHYs * @@ -32,9 +31,9 @@ #define RTL8211F_TX_DELAY BIT(8) #define RTL8211F_RX_DELAY BIT(3) -#define RTL8211E_TX_DELAY BIT(1) -#define RTL8211E_RX_DELAY BIT(2) -#define RTL8211E_MODE_MII_GMII BIT(3) +#define RTL8211E_CTRL_DELAY BIT(13) +#define RTL8211E_TX_DELAY BIT(12) +#define RTL8211E_RX_DELAY BIT(11) #define RTL8201F_ISR 0x1e #define RTL8201F_IER 0x13 @@ -246,16 +245,16 @@ static int rtl8211e_config_init(struct phy_device *phydev) /* enable TX/RX delay for rgmii-* modes, and disable them for rgmii. */ switch (phydev->interface) { case PHY_INTERFACE_MODE_RGMII: - val = 0; + val = RTL8211E_CTRL_DELAY | 0; break; case PHY_INTERFACE_MODE_RGMII_ID: - val = RTL8211E_TX_DELAY | RTL8211E_RX_DELAY; + val = RTL8211E_CTRL_DELAY | RTL8211E_TX_DELAY | RTL8211E_RX_DELAY; break; case PHY_INTERFACE_MODE_RGMII_RXID: - val = RTL8211E_RX_DELAY; + val = RTL8211E_CTRL_DELAY | RTL8211E_RX_DELAY; break; case PHY_INTERFACE_MODE_RGMII_TXID: - val = RTL8211E_TX_DELAY; + val = RTL8211E_CTRL_DELAY | RTL8211E_TX_DELAY; break; default: /* the rest of the modes imply leaving delays as is. */ return 0; @@ -263,11 +262,12 @@ static int rtl8211e_config_init(struct phy_device *phydev) /* According to a sample driver there is a 0x1c config register on the * 0xa4 extension page (0x7) layout. It can be used to disable/enable - * the RX/TX delays otherwise controlled by RXDLY/TXDLY pins. It can - * also be used to customize the whole configuration register: - * 8:6 = PHY Address, 5:4 = Auto-Negotiation, 3 = Interface Mode Select, - * 2 = RX Delay, 1 = TX Delay, 0 = SELRGV (see original PHY datasheet - * for details). + * the RX/TX delays otherwise controlled by RXDLY/TXDLY pins. + * The configuration register definition: + * 14 = reserved + * 13 = Force Tx RX Delay controlled by bit12 bit11, + * 12 = RX Delay, 11 = TX Delay + * 10:0 = Test && debug settings reserved by realtek */ oldpage = phy_select_page(phydev, 0x7); if (oldpage < 0) @@ -277,7 +277,8 @@ static int rtl8211e_config_init(struct phy_device *phydev) if (ret) goto err_restore_page; - ret = __phy_modify(phydev, 0x1c, RTL8211E_TX_DELAY | RTL8211E_RX_DELAY, + ret = __phy_modify(phydev, 0x1c, RTL8211E_CTRL_DELAY + | RTL8211E_TX_DELAY | RTL8211E_RX_DELAY, val); err_restore_page: diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 8c1e02752ff6..bcc4a4c011f1 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -287,7 +287,7 @@ inst_rollback: for (i--; i >= 0; i--) __team_option_inst_del_option(team, dst_opts[i]); - i = option_count - 1; + i = option_count; alloc_rollback: for (i--; i >= 0; i--) kfree(dst_opts[i]); @@ -2112,6 +2112,7 @@ static void team_setup_by_port(struct net_device *dev, dev->header_ops = port_dev->header_ops; dev->type = port_dev->type; dev->hard_header_len = port_dev->hard_header_len; + dev->needed_headroom = port_dev->needed_headroom; dev->addr_len = port_dev->addr_len; dev->mtu = port_dev->mtu; memcpy(dev->broadcast, port_dev->broadcast, port_dev->addr_len); diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index a38e868e44d4..5541f3faedbc 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1823,6 +1823,33 @@ static const struct driver_info belkin_info = { .status = ax88179_status, .link_reset = ax88179_link_reset, .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + +static const struct driver_info toshiba_info = { + .description = "Toshiba USB Ethernet Adapter", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, + .flags = FLAG_ETHER | FLAG_FRAMING_AX, + .rx_fixup = ax88179_rx_fixup, + .tx_fixup = ax88179_tx_fixup, +}; + +static const struct driver_info mct_info = { + .description = "MCT USB 3.0 Gigabit Ethernet Adapter", + .bind = ax88179_bind, + .unbind = ax88179_unbind, + .status = ax88179_status, + .link_reset = ax88179_link_reset, + .reset = ax88179_reset, + .stop = ax88179_stop, .flags = FLAG_ETHER | FLAG_FRAMING_AX, .rx_fixup = ax88179_rx_fixup, .tx_fixup = ax88179_tx_fixup, @@ -1861,6 +1888,14 @@ static const struct usb_device_id products[] = { /* Belkin B2B128 USB 3.0 Hub + Gigabit Ethernet Adapter */ USB_DEVICE(0x050d, 0x0128), .driver_info = (unsigned long)&belkin_info, +}, { + /* Toshiba USB 3.0 GBit Ethernet Adapter */ + USB_DEVICE(0x0930, 0x0a13), + .driver_info = (unsigned long)&toshiba_info, +}, { + /* Magic Control Technology U3-A9003 USB 3.0 Gigabit Ethernet Adapter */ + USB_DEVICE(0x0711, 0x0179), + .driver_info = (unsigned long)&mct_info, }, { }, }; diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index e92cb51a2c77..060a8a03e6c4 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -360,28 +360,47 @@ fail: } #endif /* PEGASUS_WRITE_EEPROM */ -static inline void get_node_id(pegasus_t *pegasus, __u8 *id) +static inline int get_node_id(pegasus_t *pegasus, u8 *id) { - int i; - __u16 w16; + int i, ret; + u16 w16; for (i = 0; i < 3; i++) { - read_eprom_word(pegasus, i, &w16); + ret = read_eprom_word(pegasus, i, &w16); + if (ret < 0) + return ret; ((__le16 *) id)[i] = cpu_to_le16(w16); } + + return 0; } static void set_ethernet_addr(pegasus_t *pegasus) { - __u8 node_id[6]; + int ret; + u8 node_id[6]; if (pegasus->features & PEGASUS_II) { - get_registers(pegasus, 0x10, sizeof(node_id), node_id); + ret = get_registers(pegasus, 0x10, sizeof(node_id), node_id); + if (ret < 0) + goto err; } else { - get_node_id(pegasus, node_id); - set_registers(pegasus, EthID, sizeof(node_id), node_id); + ret = get_node_id(pegasus, node_id); + if (ret < 0) + goto err; + ret = set_registers(pegasus, EthID, sizeof(node_id), node_id); + if (ret < 0) + goto err; } + memcpy(pegasus->net->dev_addr, node_id, sizeof(node_id)); + + return; +err: + eth_hw_addr_random(pegasus->net); + dev_info(&pegasus->intf->dev, "software assigned MAC address.\n"); + + return; } static inline int reset_mac(pegasus_t *pegasus) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 07c42c0719f5..5ca1356b8656 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1375,6 +1375,7 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2cb7, 0x0104, 4)}, /* Fibocom NL678 series */ {QMI_FIXED_INTF(0x0489, 0xe0b4, 0)}, /* Foxconn T77W968 LTE */ {QMI_FIXED_INTF(0x0489, 0xe0b5, 0)}, /* Foxconn T77W968 LTE with eSIM support*/ + {QMI_FIXED_INTF(0x2692, 0x9025, 4)}, /* Cellient MPL200 (rebranded Qualcomm 05c6:9025) */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c index bd9c07888ebb..6fa7a009a24a 100644 --- a/drivers/net/usb/rndis_host.c +++ b/drivers/net/usb/rndis_host.c @@ -201,7 +201,7 @@ int rndis_command(struct usbnet *dev, struct rndis_msg_hdr *buf, int buflen) dev_dbg(&info->control->dev, "rndis response error, code %d\n", retval); } - msleep(20); + msleep(40); } dev_dbg(&info->control->dev, "rndis response timeout\n"); return -ETIMEDOUT; diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 733f120c852b..9d079dc2a535 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -274,12 +274,20 @@ static int write_mii_word(rtl8150_t * dev, u8 phy, __u8 indx, u16 reg) return 1; } -static inline void set_ethernet_addr(rtl8150_t * dev) +static void set_ethernet_addr(rtl8150_t *dev) { - u8 node_id[6]; + u8 node_id[ETH_ALEN]; + int ret; + + ret = get_registers(dev, IDR, sizeof(node_id), node_id); - get_registers(dev, IDR, sizeof(node_id), node_id); - memcpy(dev->netdev->dev_addr, node_id, sizeof(node_id)); + if (ret == sizeof(node_id)) { + ether_addr_copy(dev->netdev->dev_addr, node_id); + } else { + eth_hw_addr_random(dev->netdev); + netdev_notice(dev->netdev, "Assigned a random MAC address: %pM\n", + dev->netdev->dev_addr); + } } static int rtl8150_set_mac_address(struct net_device *netdev, void *p) diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 263b005981bd..668685c09e65 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -63,6 +63,11 @@ static const unsigned long guest_offloads[] = { VIRTIO_NET_F_GUEST_CSUM }; +#define GUEST_OFFLOAD_LRO_MASK ((1ULL << VIRTIO_NET_F_GUEST_TSO4) | \ + (1ULL << VIRTIO_NET_F_GUEST_TSO6) | \ + (1ULL << VIRTIO_NET_F_GUEST_ECN) | \ + (1ULL << VIRTIO_NET_F_GUEST_UFO)) + struct virtnet_stat_desc { char desc[ETH_GSTRING_LEN]; size_t offset; @@ -2531,7 +2536,8 @@ static int virtnet_set_features(struct net_device *dev, if (features & NETIF_F_LRO) offloads = vi->guest_offloads_capable; else - offloads = 0; + offloads = vi->guest_offloads_capable & + ~GUEST_OFFLOAD_LRO_MASK; err = virtnet_set_guest_offloads(vi, offloads); if (err) diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 2818015324b8..336504b7531d 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -1032,7 +1032,6 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, /* Use temporary descriptor to avoid touching bits multiple times */ union Vmxnet3_GenericDesc tempTxDesc; #endif - struct udphdr *udph; count = txd_estimate(skb); @@ -1135,8 +1134,7 @@ vmxnet3_tq_xmit(struct sk_buff *skb, struct vmxnet3_tx_queue *tq, gdesc->txd.om = VMXNET3_OM_ENCAP; gdesc->txd.msscof = ctx.mss; - udph = udp_hdr(skb); - if (udph->check) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM) gdesc->txd.oco = 1; } else { gdesc->txd.hlen = ctx.l4_offset + ctx.l4_hdr_size; @@ -3371,6 +3369,7 @@ vmxnet3_probe_device(struct pci_dev *pdev, .ndo_change_mtu = vmxnet3_change_mtu, .ndo_fix_features = vmxnet3_fix_features, .ndo_set_features = vmxnet3_set_features, + .ndo_features_check = vmxnet3_features_check, .ndo_get_stats64 = vmxnet3_get_stats64, .ndo_tx_timeout = vmxnet3_tx_timeout, .ndo_set_rx_mode = vmxnet3_set_mc, diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index 1014693a5ceb..7ec8652f2c26 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -267,6 +267,34 @@ netdev_features_t vmxnet3_fix_features(struct net_device *netdev, return features; } +netdev_features_t vmxnet3_features_check(struct sk_buff *skb, + struct net_device *netdev, + netdev_features_t features) +{ + struct vmxnet3_adapter *adapter = netdev_priv(netdev); + + /* Validate if the tunneled packet is being offloaded by the device */ + if (VMXNET3_VERSION_GE_4(adapter) && + skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) { + u8 l4_proto = 0; + + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_IP): + l4_proto = ip_hdr(skb)->protocol; + break; + case htons(ETH_P_IPV6): + l4_proto = ipv6_hdr(skb)->nexthdr; + break; + default: + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + + if (l4_proto != IPPROTO_UDP) + return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); + } + return features; +} + static void vmxnet3_enable_encap_offloads(struct net_device *netdev) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 5d2b062215a2..d958b92c9429 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -470,6 +470,10 @@ vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter); netdev_features_t vmxnet3_fix_features(struct net_device *netdev, netdev_features_t features); +netdev_features_t +vmxnet3_features_check(struct sk_buff *skb, + struct net_device *netdev, netdev_features_t features); + int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features); diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index 444130655d8e..cb5898f7d68c 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -118,6 +118,7 @@ static void cisco_keepalive_send(struct net_device *dev, u32 type, skb_put(skb, sizeof(struct cisco_packet)); skb->priority = TC_PRIO_CONTROL; skb->dev = dev; + skb->protocol = htons(ETH_P_HDLC); skb_reset_network_header(skb); dev_queue_xmit(skb); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 9acad651ea1f..d6cfd51613ed 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -433,6 +433,8 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev) if (pvc->state.fecn) /* TX Congestion counter */ dev->stats.tx_compressed++; skb->dev = pvc->frad; + skb->protocol = htons(ETH_P_HDLC); + skb_reset_network_header(skb); dev_queue_xmit(skb); return NETDEV_TX_OK; } @@ -555,6 +557,7 @@ static void fr_lmi_send(struct net_device *dev, int fullrep) skb_put(skb, i); skb->priority = TC_PRIO_CONTROL; skb->dev = dev; + skb->protocol = htons(ETH_P_HDLC); skb_reset_network_header(skb); dev_queue_xmit(skb); @@ -1041,7 +1044,7 @@ static void pvc_setup(struct net_device *dev) { dev->type = ARPHRD_DLCI; dev->flags = IFF_POINTOPOINT; - dev->hard_header_len = 10; + dev->hard_header_len = 0; dev->addr_len = 2; netif_keep_dst(dev); } @@ -1093,6 +1096,7 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) dev->mtu = HDLC_MAX_MTU; dev->min_mtu = 68; dev->max_mtu = HDLC_MAX_MTU; + dev->needed_headroom = 10; dev->priv_flags |= IFF_NO_QUEUE; dev->ml_priv = pvc; diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 48ced3912576..64f855651336 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -251,6 +251,7 @@ static void ppp_tx_cp(struct net_device *dev, u16 pid, u8 code, skb->priority = TC_PRIO_CONTROL; skb->dev = dev; + skb->protocol = htons(ETH_P_HDLC); skb_reset_network_header(skb); skb_queue_tail(&tx_queue, skb); } @@ -383,11 +384,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, } for (opt = data; len; len -= opt[1], opt += opt[1]) { - if (len < 2 || len < opt[1]) { - dev->stats.rx_errors++; - kfree(out); - return; /* bad packet, drop silently */ - } + if (len < 2 || opt[1] < 2 || len < opt[1]) + goto err_out; if (pid == PID_LCP) switch (opt[0]) { @@ -395,6 +393,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, continue; /* MRU always OK and > 1500 bytes? */ case LCP_OPTION_ACCM: /* async control character map */ + if (opt[1] < sizeof(valid_accm)) + goto err_out; if (!memcmp(opt, valid_accm, sizeof(valid_accm))) continue; @@ -406,6 +406,8 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, } break; case LCP_OPTION_MAGIC: + if (len < 6) + goto err_out; if (opt[1] != 6 || (!opt[2] && !opt[3] && !opt[4] && !opt[5])) break; /* reject invalid magic number */ @@ -424,6 +426,11 @@ static void ppp_cp_parse_cr(struct net_device *dev, u16 pid, u8 id, ppp_cp_event(dev, pid, RCR_GOOD, CP_CONF_ACK, id, req_len, data); kfree(out); + return; + +err_out: + dev->stats.rx_errors++; + kfree(out); } static int ppp_rx(struct sk_buff *skb) diff --git a/drivers/net/wan/lapbether.c b/drivers/net/wan/lapbether.c index 732a6c1851f5..b6be2454b8bd 100644 --- a/drivers/net/wan/lapbether.c +++ b/drivers/net/wan/lapbether.c @@ -198,8 +198,6 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) struct net_device *dev; int size = skb->len; - skb->protocol = htons(ETH_P_X25); - ptr = skb_push(skb, 2); *ptr++ = size % 256; @@ -210,6 +208,8 @@ static void lapbeth_data_transmit(struct net_device *ndev, struct sk_buff *skb) skb->dev = dev = lapbeth->ethdev; + skb->protocol = htons(ETH_P_DEC); + skb_reset_network_header(skb); dev_hard_header(skb, dev, ETH_P_DEC, bcast_addr, NULL, 0); diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c index 7ee980575208..c418767a890a 100644 --- a/drivers/net/wan/x25_asy.c +++ b/drivers/net/wan/x25_asy.c @@ -464,7 +464,6 @@ static int x25_asy_open(struct net_device *dev) { struct x25_asy *sl = netdev_priv(dev); unsigned long len; - int err; if (sl->tty == NULL) return -ENODEV; @@ -490,14 +489,7 @@ static int x25_asy_open(struct net_device *dev) sl->xleft = 0; sl->flags &= (1 << SLF_INUSE); /* Clear ESCAPE & ERROR flags */ - netif_start_queue(dev); - - /* - * Now attach LAPB - */ - err = lapb_register(dev, &x25_asy_callbacks); - if (err == LAPB_OK) - return 0; + return 0; /* Cleanup */ kfree(sl->xbuff); @@ -519,7 +511,6 @@ static int x25_asy_close(struct net_device *dev) if (sl->tty) clear_bit(TTY_DO_WRITE_WAKEUP, &sl->tty->flags); - netif_stop_queue(dev); sl->rcount = 0; sl->xleft = 0; spin_unlock(&sl->lock); @@ -604,7 +595,6 @@ static int x25_asy_open_tty(struct tty_struct *tty) static void x25_asy_close_tty(struct tty_struct *tty) { struct x25_asy *sl = tty->disc_data; - int err; /* First make sure we're connected. */ if (!sl || sl->magic != X25_ASY_MAGIC) @@ -615,11 +605,6 @@ static void x25_asy_close_tty(struct tty_struct *tty) dev_close(sl->dev); rtnl_unlock(); - err = lapb_unregister(sl->dev); - if (err != LAPB_OK) - pr_err("%s: lapb_unregister error: %d\n", - __func__, err); - tty->disc_data = NULL; sl->tty = NULL; x25_asy_free(sl); @@ -722,15 +707,39 @@ static int x25_asy_ioctl(struct tty_struct *tty, struct file *file, static int x25_asy_open_dev(struct net_device *dev) { + int err; struct x25_asy *sl = netdev_priv(dev); if (sl->tty == NULL) return -ENODEV; + + err = lapb_register(dev, &x25_asy_callbacks); + if (err != LAPB_OK) + return -ENOMEM; + + netif_start_queue(dev); + + return 0; +} + +static int x25_asy_close_dev(struct net_device *dev) +{ + int err; + + netif_stop_queue(dev); + + err = lapb_unregister(dev); + if (err != LAPB_OK) + pr_err("%s: lapb_unregister error: %d\n", + __func__, err); + + x25_asy_close(dev); + return 0; } static const struct net_device_ops x25_asy_netdev_ops = { .ndo_open = x25_asy_open_dev, - .ndo_stop = x25_asy_close, + .ndo_stop = x25_asy_close_dev, .ndo_start_xmit = x25_asy_xmit, .ndo_tx_timeout = x25_asy_timeout, .ndo_change_mtu = x25_asy_change_mtu, diff --git a/drivers/net/wireguard/noise.c b/drivers/net/wireguard/noise.c index 3dd3b76790d0..c0cfd9b36c0b 100644 --- a/drivers/net/wireguard/noise.c +++ b/drivers/net/wireguard/noise.c @@ -87,15 +87,12 @@ static void handshake_zero(struct noise_handshake *handshake) void wg_noise_handshake_clear(struct noise_handshake *handshake) { + down_write(&handshake->lock); wg_index_hashtable_remove( handshake->entry.peer->device->index_hashtable, &handshake->entry); - down_write(&handshake->lock); handshake_zero(handshake); up_write(&handshake->lock); - wg_index_hashtable_remove( - handshake->entry.peer->device->index_hashtable, - &handshake->entry); } static struct noise_keypair *keypair_create(struct wg_peer *peer) diff --git a/drivers/net/wireguard/peerlookup.c b/drivers/net/wireguard/peerlookup.c index e4deb331476b..f2783aa7a88f 100644 --- a/drivers/net/wireguard/peerlookup.c +++ b/drivers/net/wireguard/peerlookup.c @@ -167,9 +167,13 @@ bool wg_index_hashtable_replace(struct index_hashtable *table, struct index_hashtable_entry *old, struct index_hashtable_entry *new) { - if (unlikely(hlist_unhashed(&old->index_hash))) - return false; + bool ret; + spin_lock_bh(&table->lock); + ret = !hlist_unhashed(&old->index_hash); + if (unlikely(!ret)) + goto out; + new->index = old->index; hlist_replace_rcu(&old->index_hash, &new->index_hash); @@ -180,8 +184,9 @@ bool wg_index_hashtable_replace(struct index_hashtable *table, * simply gets dropped, which isn't terrible. */ INIT_HLIST_NODE(&old->index_hash); +out: spin_unlock_bh(&table->lock); - return true; + return ret; } void wg_index_hashtable_remove(struct index_hashtable *table, diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index e8712ad3ac45..3c07d1bbe1c6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -664,9 +664,15 @@ static void pkt_align(struct sk_buff *p, int len, int align) /* To check if there's window offered */ static bool data_ok(struct brcmf_sdio *bus) { - /* Reserve TXCTL_CREDITS credits for txctl */ - return (bus->tx_max - bus->tx_seq) > TXCTL_CREDITS && - ((bus->tx_max - bus->tx_seq) & 0x80) == 0; + u8 tx_rsv = 0; + + /* Reserve TXCTL_CREDITS credits for txctl when it is ready to send */ + if (bus->ctrl_frame_stat) + tx_rsv = TXCTL_CREDITS; + + return (bus->tx_max - bus->tx_seq - tx_rsv) != 0 && + ((bus->tx_max - bus->tx_seq - tx_rsv) & 0x80) == 0; + } /* To check if there's window offered */ diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h index 8047e307892e..d9f8bdbc817b 100644 --- a/drivers/net/wireless/marvell/mwifiex/fw.h +++ b/drivers/net/wireless/marvell/mwifiex/fw.h @@ -954,7 +954,7 @@ struct mwifiex_tkip_param { struct mwifiex_aes_param { u8 pn[WPA_PN_SIZE]; __le16 key_len; - u8 key[WLAN_KEY_LEN_CCMP]; + u8 key[WLAN_KEY_LEN_CCMP_256]; } __packed; struct mwifiex_wapi_param { diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c index 962d8bfe6f10..119ccacd1fcc 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_cmdresp.c @@ -619,7 +619,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv, key_v2 = &resp->params.key_material_v2; len = le16_to_cpu(key_v2->key_param_set.key_params.aes.key_len); - if (len > WLAN_KEY_LEN_CCMP) + if (len > sizeof(key_v2->key_param_set.key_params.aes.key)) return -EINVAL; if (le16_to_cpu(key_v2->action) == HostCmd_ACT_GEN_SET) { @@ -635,7 +635,7 @@ static int mwifiex_ret_802_11_key_material_v2(struct mwifiex_private *priv, return 0; memset(priv->aes_key_v2.key_param_set.key_params.aes.key, 0, - WLAN_KEY_LEN_CCMP); + sizeof(key_v2->key_param_set.key_params.aes.key)); priv->aes_key_v2.key_param_set.key_params.aes.key_len = cpu_to_le16(len); memcpy(priv->aes_key_v2.key_param_set.key_params.aes.key, diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c index fc1ebabfebac..1f57b43693bc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c @@ -460,7 +460,7 @@ void mt7615_init_device(struct mt7615_dev *dev) dev->mphy.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING; dev->mphy.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING; dev->mphy.sband_5g.sband.vht_cap.cap |= - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | + IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; mt7615_cap_dbdc_disable(dev); dev->phy.dfs_state = -1; diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c index d0cbb283982f..bd316dbd9041 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/mcu.c @@ -2128,7 +2128,8 @@ static int mt7615_load_n9(struct mt7615_dev *dev, const char *name) sizeof(dev->mt76.hw->wiphy->fw_version), "%.10s-%.15s", hdr->fw_ver, hdr->build_date); - if (!strncmp(hdr->fw_ver, "2.0", sizeof(hdr->fw_ver))) { + if (!is_mt7615(&dev->mt76) && + !strncmp(hdr->fw_ver, "2.0", sizeof(hdr->fw_ver))) { dev->fw_ver = MT7615_FIRMWARE_V2; dev->mcu_ops = &sta_update_ops; } else { diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c index e90d0087e377..8d6ceb3b67b4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c @@ -699,8 +699,12 @@ void mt7915_unregister_device(struct mt7915_dev *dev) spin_lock_bh(&dev->token_lock); idr_for_each_entry(&dev->token, txwi, id) { mt7915_txp_skb_unmap(&dev->mt76, txwi); - if (txwi->skb) - dev_kfree_skb_any(txwi->skb); + if (txwi->skb) { + struct ieee80211_hw *hw; + + hw = mt76_tx_status_get_hw(&dev->mt76, txwi->skb); + ieee80211_free_txskb(hw, txwi->skb); + } mt76_put_txwi(&dev->mt76, txwi); } spin_unlock_bh(&dev->token_lock); diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 6825afca1efb..036207f828f3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -841,7 +841,7 @@ mt7915_tx_complete_status(struct mt76_dev *mdev, struct sk_buff *skb, if (sta || !(info->flags & IEEE80211_TX_CTL_NO_ACK)) mt7915_tx_status(sta, hw, info, NULL); - dev_kfree_skb(skb); + ieee80211_free_txskb(hw, skb); } void mt7915_txp_skb_unmap(struct mt76_dev *dev, diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.c b/drivers/net/wireless/quantenna/qtnfmac/core.c index 6aafff9d4231..e013ebe3079c 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/core.c +++ b/drivers/net/wireless/quantenna/qtnfmac/core.c @@ -671,9 +671,10 @@ bool qtnf_netdev_is_qtn(const struct net_device *ndev) return ndev->netdev_ops == &qtnf_netdev_ops; } -static int qtnf_check_br_ports(struct net_device *dev, void *data) +static int qtnf_check_br_ports(struct net_device *dev, + struct netdev_nested_priv *priv) { - struct net_device *ndev = data; + struct net_device *ndev = (struct net_device *)priv->data; if (dev != ndev && netdev_port_same_parent_id(dev, ndev)) return -ENOTSUPP; @@ -686,6 +687,9 @@ static int qtnf_core_netdevice_event(struct notifier_block *nb, { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); const struct netdev_notifier_changeupper_info *info; + struct netdev_nested_priv priv = { + .data = (void *)ndev, + }; struct net_device *brdev; struct qtnf_vif *vif; struct qtnf_bus *bus; @@ -725,7 +729,7 @@ static int qtnf_core_netdevice_event(struct notifier_block *nb, } else { ret = netdev_walk_all_lower_dev(brdev, qtnf_check_br_ports, - ndev); + &priv); } break; diff --git a/drivers/net/wireless/ti/wlcore/cmd.h b/drivers/net/wireless/ti/wlcore/cmd.h index 9acd8a41ea61..f2609d5b6bf7 100644 --- a/drivers/net/wireless/ti/wlcore/cmd.h +++ b/drivers/net/wireless/ti/wlcore/cmd.h @@ -458,7 +458,6 @@ enum wl1271_cmd_key_type { KEY_TKIP = 2, KEY_AES = 3, KEY_GEM = 4, - KEY_IGTK = 5, }; struct wl1271_cmd_set_keys { diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 821ad1acd505..d2bbd5108f7e 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -3559,9 +3559,6 @@ int wlcore_set_key(struct wl1271 *wl, enum set_key_cmd cmd, case WL1271_CIPHER_SUITE_GEM: key_type = KEY_GEM; break; - case WLAN_CIPHER_SUITE_AES_CMAC: - key_type = KEY_IGTK; - break; default: wl1271_error("Unknown key algo 0x%x", key_conf->cipher); @@ -6231,7 +6228,6 @@ static int wl1271_init_ieee80211(struct wl1271 *wl) WLAN_CIPHER_SUITE_TKIP, WLAN_CIPHER_SUITE_CCMP, WL1271_CIPHER_SUITE_GEM, - WLAN_CIPHER_SUITE_AES_CMAC, }; /* The tx descriptor buffer */ diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 3ed9786b88d8..a44d49d63968 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -73,6 +73,7 @@ config NVME_TCP depends on INET depends on BLK_DEV_NVME select NVME_FABRICS + select CRYPTO select CRYPTO_CRC32C help This provides support for the NVMe over Fabrics protocol using diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index f3a61a24d45f..893e29624c16 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3041,7 +3041,7 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi, if (!cel) return -ENOMEM; - ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0, csi, + ret = nvme_get_log(ctrl, 0x00, NVME_LOG_CMD_EFFECTS, 0, csi, &cel->log, sizeof(cel->log), 0); if (ret) { kfree(cel); @@ -3236,8 +3236,11 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) if (ret < 0) return ret; - if (!ctrl->identified) - nvme_hwmon_init(ctrl); + if (!ctrl->identified) { + ret = nvme_hwmon_init(ctrl); + if (ret < 0) + return ret; + } ctrl->identified = true; @@ -3261,10 +3264,26 @@ static int nvme_dev_open(struct inode *inode, struct file *file) return -EWOULDBLOCK; } + nvme_get_ctrl(ctrl); + if (!try_module_get(ctrl->ops->module)) { + nvme_put_ctrl(ctrl); + return -EINVAL; + } + file->private_data = ctrl; return 0; } +static int nvme_dev_release(struct inode *inode, struct file *file) +{ + struct nvme_ctrl *ctrl = + container_of(inode->i_cdev, struct nvme_ctrl, cdev); + + module_put(ctrl->ops->module); + nvme_put_ctrl(ctrl); + return 0; +} + static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp) { struct nvme_ns *ns; @@ -3327,6 +3346,7 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd, static const struct file_operations nvme_dev_fops = { .owner = THIS_MODULE, .open = nvme_dev_open, + .release = nvme_dev_release, .unlocked_ioctl = nvme_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, }; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index e8ef42b9d50c..e2e09e25c056 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3671,12 +3671,14 @@ nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts) spin_lock_irqsave(&nvme_fc_lock, flags); list_for_each_entry(lport, &nvme_fc_lport_list, port_list) { if (lport->localport.node_name != laddr.nn || - lport->localport.port_name != laddr.pn) + lport->localport.port_name != laddr.pn || + lport->localport.port_state != FC_OBJSTATE_ONLINE) continue; list_for_each_entry(rport, &lport->endp_list, endp_list) { if (rport->remoteport.node_name != raddr.nn || - rport->remoteport.port_name != raddr.pn) + rport->remoteport.port_name != raddr.pn || + rport->remoteport.port_state != FC_OBJSTATE_ONLINE) continue; /* if fail to get reference fall through. Will error */ diff --git a/drivers/nvme/host/hwmon.c b/drivers/nvme/host/hwmon.c index 412a6c97c0d8..552dbc04567b 100644 --- a/drivers/nvme/host/hwmon.c +++ b/drivers/nvme/host/hwmon.c @@ -59,12 +59,8 @@ static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under, static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data) { - int ret; - - ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0, + return nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0, NVME_CSI_NVM, &data->log, sizeof(data->log), 0); - - return ret <= 0 ? ret : -EIO; } static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type, @@ -225,7 +221,7 @@ static const struct hwmon_chip_info nvme_hwmon_chip_info = { .info = nvme_hwmon_info, }; -void nvme_hwmon_init(struct nvme_ctrl *ctrl) +int nvme_hwmon_init(struct nvme_ctrl *ctrl) { struct device *dev = ctrl->dev; struct nvme_hwmon_data *data; @@ -234,7 +230,7 @@ void nvme_hwmon_init(struct nvme_ctrl *ctrl) data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) - return; + return 0; data->ctrl = ctrl; mutex_init(&data->read_lock); @@ -244,7 +240,7 @@ void nvme_hwmon_init(struct nvme_ctrl *ctrl) dev_warn(ctrl->device, "Failed to read smart log (error %d)\n", err); devm_kfree(dev, data); - return; + return err; } hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data, @@ -254,4 +250,6 @@ void nvme_hwmon_init(struct nvme_ctrl *ctrl) dev_warn(dev, "Failed to instantiate hwmon device\n"); devm_kfree(dev, data); } + + return 0; } diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 9fd45ff656da..2aaedfa43ed8 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -827,9 +827,12 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) } #ifdef CONFIG_NVME_HWMON -void nvme_hwmon_init(struct nvme_ctrl *ctrl); +int nvme_hwmon_init(struct nvme_ctrl *ctrl); #else -static inline void nvme_hwmon_init(struct nvme_ctrl *ctrl) { } +static inline int nvme_hwmon_init(struct nvme_ctrl *ctrl) +{ + return 0; +} #endif u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 899d2f4d7ab6..8984796db0c8 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -940,13 +940,6 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) struct nvme_completion *cqe = &nvmeq->cqes[idx]; struct request *req; - if (unlikely(cqe->command_id >= nvmeq->q_depth)) { - dev_warn(nvmeq->dev->ctrl.device, - "invalid id %d completed on queue %d\n", - cqe->command_id, le16_to_cpu(cqe->sq_id)); - return; - } - /* * AEN requests are special as they don't time out and can * survive any kind of queue freeze and often don't respond to @@ -960,6 +953,13 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq, u16 idx) } req = blk_mq_tag_to_rq(nvme_queue_tagset(nvmeq), cqe->command_id); + if (unlikely(!req)) { + dev_warn(nvmeq->dev->ctrl.device, + "invalid id %d completed on queue %d\n", + cqe->command_id, le16_to_cpu(cqe->sq_id)); + return; + } + trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail); if (!nvme_try_complete_req(req, cqe->status, cqe->result)) nvme_pci_complete_rq(req); @@ -3153,7 +3153,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(INTEL, 0xf1a5), /* Intel 600P/P3100 */ .driver_data = NVME_QUIRK_NO_DEEPEST_PS | NVME_QUIRK_MEDIUM_PRIO_SQ | - NVME_QUIRK_NO_TEMP_THRESH_CHANGE }, + NVME_QUIRK_NO_TEMP_THRESH_CHANGE | + NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_VDEVICE(INTEL, 0xf1a6), /* Intel 760p/Pro 7600p */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */ diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 8f4f29f18b8c..d6a3e1487354 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -913,12 +913,11 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) else flags |= MSG_MORE | MSG_SENDPAGE_NOTLAST; - /* can't zcopy slab pages */ - if (unlikely(PageSlab(page))) { - ret = sock_no_sendpage(queue->sock, page, offset, len, + if (sendpage_ok(page)) { + ret = kernel_sendpage(queue->sock, page, offset, len, flags); } else { - ret = kernel_sendpage(queue->sock, page, offset, len, + ret = sock_no_sendpage(queue->sock, page, offset, len, flags); } if (ret <= 0) diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 8bd7f656e240..dacfa7435d0b 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -517,6 +517,7 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys) subsys->ver = NVME_VS(1, 2, 1); } + __module_get(subsys->passthru_ctrl->ops->module); mutex_unlock(&subsys->lock); return 0; @@ -531,6 +532,7 @@ static void __nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys) { if (subsys->passthru_ctrl) { xa_erase(&passthru_subsystems, subsys->passthru_ctrl->cntlid); + module_put(subsys->passthru_ctrl->ops->module); nvme_put_ctrl(subsys->passthru_ctrl); } subsys->passthru_ctrl = NULL; diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c index 0bb2fb3e8a0b..9705059523a6 100644 --- a/drivers/pci/controller/pcie-rockchip-host.c +++ b/drivers/pci/controller/pcie-rockchip-host.c @@ -71,16 +71,13 @@ static void rockchip_pcie_update_txcredit_mui(struct rockchip_pcie *rockchip) static int rockchip_pcie_valid_device(struct rockchip_pcie *rockchip, struct pci_bus *bus, int dev) { - /* access only one slot on each root port */ - if (pci_is_root_bus(bus) && dev > 0) - return 0; - /* - * do not read more than one device on the bus directly attached + * Access only one slot on each root port. + * Do not read more than one device on the bus directly attached * to RC's downstream side. */ - if (pci_is_root_bus(bus->parent) && dev > 0) - return 0; + if (pci_is_root_bus(bus) || pci_is_root_bus(bus->parent)) + return dev == 0; return 1; } diff --git a/drivers/phy/ti/phy-am654-serdes.c b/drivers/phy/ti/phy-am654-serdes.c index a174b3c3f010..819c49af169a 100644 --- a/drivers/phy/ti/phy-am654-serdes.c +++ b/drivers/phy/ti/phy-am654-serdes.c @@ -725,8 +725,10 @@ static int serdes_am654_probe(struct platform_device *pdev) pm_runtime_enable(dev); phy = devm_phy_create(dev, NULL, &ops); - if (IS_ERR(phy)) - return PTR_ERR(phy); + if (IS_ERR(phy)) { + ret = PTR_ERR(phy); + goto clk_err; + } phy_set_drvdata(phy, am654_phy); phy_provider = devm_of_phy_provider_register(dev, serdes_am654_xlate); diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 9ef246145bde..06521097513a 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -58,6 +58,7 @@ #define CHV_PADCTRL1_CFGLOCK BIT(31) #define CHV_PADCTRL1_INVRXTX_SHIFT 4 #define CHV_PADCTRL1_INVRXTX_MASK GENMASK(7, 4) +#define CHV_PADCTRL1_INVRXTX_TXDATA BIT(7) #define CHV_PADCTRL1_INVRXTX_RXDATA BIT(6) #define CHV_PADCTRL1_INVRXTX_TXENABLE BIT(5) #define CHV_PADCTRL1_ODEN BIT(3) @@ -792,11 +793,22 @@ static int chv_pinmux_set_mux(struct pinctrl_dev *pctldev, static void chv_gpio_clear_triggering(struct chv_pinctrl *pctrl, unsigned int offset) { + u32 invrxtx_mask = CHV_PADCTRL1_INVRXTX_MASK; u32 value; + /* + * One some devices the GPIO should output the inverted value from what + * device-drivers / ACPI code expects (inverted external buffer?). The + * BIOS makes this work by setting the CHV_PADCTRL1_INVRXTX_TXDATA flag, + * preserve this flag if the pin is already setup as GPIO. + */ + value = chv_readl(pctrl, offset, CHV_PADCTRL0); + if (value & CHV_PADCTRL0_GPIOEN) + invrxtx_mask &= ~CHV_PADCTRL1_INVRXTX_TXDATA; + value = chv_readl(pctrl, offset, CHV_PADCTRL1); value &= ~CHV_PADCTRL1_INTWAKECFG_MASK; - value &= ~CHV_PADCTRL1_INVRXTX_MASK; + value &= ~invrxtx_mask; chv_writel(pctrl, offset, CHV_PADCTRL1, value); } diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c index 2f3dfb56c3fa..35bbe5935708 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c @@ -259,6 +259,10 @@ bool mtk_is_virt_gpio(struct mtk_pinctrl *hw, unsigned int gpio_n) desc = (const struct mtk_pin_desc *)&hw->soc->pins[gpio_n]; + /* if the GPIO is not supported for eint mode */ + if (desc->eint.eint_m == NO_EINT_SUPPORT) + return virt_gpio; + if (desc->funcs && !desc->funcs[desc->eint.eint_m].name) virt_gpio = true; diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c index a767a05fa3a0..48e2a6c56a83 100644 --- a/drivers/pinctrl/mvebu/pinctrl-armada-xp.c +++ b/drivers/pinctrl/mvebu/pinctrl-armada-xp.c @@ -414,7 +414,7 @@ static struct mvebu_mpp_mode mv98dx3236_mpp_modes[] = { MPP_VAR_FUNCTION(0x1, "i2c0", "sck", V_98DX3236_PLUS)), MPP_MODE(15, MPP_VAR_FUNCTION(0x0, "gpio", NULL, V_98DX3236_PLUS), - MPP_VAR_FUNCTION(0x4, "i2c0", "sda", V_98DX3236_PLUS)), + MPP_VAR_FUNCTION(0x1, "i2c0", "sda", V_98DX3236_PLUS)), MPP_MODE(16, MPP_VAR_FUNCTION(0x0, "gpo", NULL, V_98DX3236_PLUS), MPP_VAR_FUNCTION(0x4, "dev", "oe", V_98DX3236_PLUS)), diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c index a660f1274b66..826df0d637ea 100644 --- a/drivers/pinctrl/qcom/pinctrl-sm8250.c +++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c @@ -1308,7 +1308,7 @@ static const struct msm_pingroup sm8250_groups[] = { [178] = PINGROUP(178, WEST, _, _, _, _, _, _, _, _, _), [179] = PINGROUP(179, WEST, _, _, _, _, _, _, _, _, _), [180] = UFS_RESET(ufs_reset, 0xb8000), - [181] = SDC_PINGROUP(sdc2_clk, 0x7000, 14, 6), + [181] = SDC_PINGROUP(sdc2_clk, 0xb7000, 14, 6), [182] = SDC_PINGROUP(sdc2_cmd, 0xb7000, 11, 3), [183] = SDC_PINGROUP(sdc2_data, 0xb7000, 9, 0), }; diff --git a/drivers/platform/olpc/olpc-ec.c b/drivers/platform/olpc/olpc-ec.c index 190e4a6186ef..f64b82824db2 100644 --- a/drivers/platform/olpc/olpc-ec.c +++ b/drivers/platform/olpc/olpc-ec.c @@ -439,7 +439,9 @@ static int olpc_ec_probe(struct platform_device *pdev) &config); if (IS_ERR(ec->dcon_rdev)) { dev_err(&pdev->dev, "failed to register DCON regulator\n"); - return PTR_ERR(ec->dcon_rdev); + err = PTR_ERR(ec->dcon_rdev); + kfree(ec); + return err; } ec->dbgfs_dir = olpc_ec_setup_debugfs(); diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 40219bba6801..0d91d136bc3b 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -469,6 +469,7 @@ config FUJITSU_LAPTOP depends on BACKLIGHT_CLASS_DEVICE depends on ACPI_VIDEO || ACPI_VIDEO = n select INPUT_SPARSEKMAP + select NEW_LEDS select LEDS_CLASS help This is a driver for laptops built by Fujitsu: @@ -1112,6 +1113,7 @@ config LG_LAPTOP depends on ACPI_WMI depends on INPUT select INPUT_SPARSEKMAP + select NEW_LEDS select LEDS_CLASS help This driver adds support for hotkeys as well as control of keyboard diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index b2e3d1e3b3e9..1d9fbabd02fb 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -115,6 +115,10 @@ static struct quirk_entry quirk_asus_vendor_backlight = { .wmi_backlight_set_devstate = true, }; +static struct quirk_entry quirk_asus_use_kbd_dock_devid = { + .use_kbd_dock_devid = true, +}; + static int dmi_matched(const struct dmi_system_id *dmi) { pr_info("Identified laptop model '%s'\n", dmi->ident); @@ -488,6 +492,34 @@ static const struct dmi_system_id asus_quirks[] = { }, .driver_data = &quirk_asus_vendor_backlight, }, + { + .callback = dmi_matched, + .ident = "Asus Transformer T100TA / T100HA / T100CHI", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + /* Match *T100* */ + DMI_MATCH(DMI_PRODUCT_NAME, "T100"), + }, + .driver_data = &quirk_asus_use_kbd_dock_devid, + }, + { + .callback = dmi_matched, + .ident = "Asus Transformer T101HA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "T101HA"), + }, + .driver_data = &quirk_asus_use_kbd_dock_devid, + }, + { + .callback = dmi_matched, + .ident = "Asus Transformer T200TA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "T200TA"), + }, + .driver_data = &quirk_asus_use_kbd_dock_devid, + }, {}, }; @@ -593,33 +625,9 @@ 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/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 8f4acdc06b13..39e1a6396e08 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -365,12 +365,14 @@ static int asus_wmi_input_init(struct asus_wmi *asus) if (err) goto err_free_dev; - result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK); - if (result >= 0) { - input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE); - input_report_switch(asus->inputdev, SW_TABLET_MODE, !result); - } else if (result != -ENODEV) { - pr_err("Error checking for keyboard-dock: %d\n", result); + if (asus->driver->quirks->use_kbd_dock_devid) { + result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK); + if (result >= 0) { + input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE); + input_report_switch(asus->inputdev, SW_TABLET_MODE, !result); + } else if (result != -ENODEV) { + pr_err("Error checking for keyboard-dock: %d\n", result); + } } err = input_register_device(asus->inputdev); @@ -442,6 +444,7 @@ static int asus_wmi_battery_add(struct power_supply *battery) */ if (strcmp(battery->desc->name, "BAT0") != 0 && strcmp(battery->desc->name, "BAT1") != 0 && + strcmp(battery->desc->name, "BATC") != 0 && strcmp(battery->desc->name, "BATT") != 0) return -ENODEV; @@ -2114,7 +2117,7 @@ static void asus_wmi_handle_event_code(int code, struct asus_wmi *asus) return; } - if (code == NOTIFY_KBD_DOCK_CHANGE) { + if (asus->driver->quirks->use_kbd_dock_devid && code == NOTIFY_KBD_DOCK_CHANGE) { result = asus_wmi_get_devstate_simple(asus, ASUS_WMI_DEVID_KBD_DOCK); if (result >= 0) { diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h index 4f31b68642a0..1a95c172f94b 100644 --- a/drivers/platform/x86/asus-wmi.h +++ b/drivers/platform/x86/asus-wmi.h @@ -33,6 +33,7 @@ struct quirk_entry { bool wmi_backlight_native; bool wmi_backlight_set_devstate; bool wmi_force_als_set; + bool use_kbd_dock_devid; int wapf; /* * For machines with AMD graphic chips, it will send out WMI event diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index e85d8e58320c..f5901b0b07cd 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -167,20 +167,54 @@ static bool intel_vbtn_has_buttons(acpi_handle handle) return ACPI_SUCCESS(status); } +/* + * There are several laptops (non 2-in-1) models out there which support VGBS, + * but simply always return 0, which we translate to SW_TABLET_MODE=1. This in + * turn causes userspace (libinput) to suppress events from the builtin + * keyboard and touchpad, making the laptop essentially unusable. + * + * Since the problem of wrongly reporting SW_TABLET_MODE=1 in combination + * with libinput, leads to a non-usable system. Where as OTOH many people will + * not even notice when SW_TABLET_MODE is not being reported, a DMI based allow + * list is used here. This list mainly matches on the chassis-type of 2-in-1s. + * + * There are also some 2-in-1s which use the intel-vbtn ACPI interface to report + * SW_TABLET_MODE with a chassis-type of 8 ("Portable") or 10 ("Notebook"), + * these are matched on a per model basis, since many normal laptops with a + * possible broken VGBS ACPI-method also use these chassis-types. + */ +static const struct dmi_system_id dmi_switches_allow_list[] = { + { + .matches = { + DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "31" /* Convertible */), + }, + }, + { + .matches = { + DMI_EXACT_MATCH(DMI_CHASSIS_TYPE, "32" /* Detachable */), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Stream x360 Convertible PC 11"), + }, + }, + {} /* Array terminator */ +}; + static bool intel_vbtn_has_switches(acpi_handle handle) { - const char *chassis_type = dmi_get_system_info(DMI_CHASSIS_TYPE); unsigned long long vgbs; acpi_status status; - /* - * Some normal laptops have a VGBS method despite being non-convertible - * and their VGBS method always returns 0, causing detect_tablet_mode() - * to report SW_TABLET_MODE=1 to userspace, which causes issues. - * These laptops have a DMI chassis_type of 9 ("Laptop"), do not report - * switches on any devices with a DMI chassis_type of 9. - */ - if (chassis_type && strcmp(chassis_type, "9") == 0) + if (!dmi_check_system(dmi_switches_allow_list)) return false; status = acpi_evaluate_integer(handle, "VGBS", NULL, &vgbs); diff --git a/drivers/platform/x86/intel_pmc_core_pltdrv.c b/drivers/platform/x86/intel_pmc_core_pltdrv.c index 731281855cc8..73797680b895 100644 --- a/drivers/platform/x86/intel_pmc_core_pltdrv.c +++ b/drivers/platform/x86/intel_pmc_core_pltdrv.c @@ -20,15 +20,10 @@ static void intel_pmc_core_release(struct device *dev) { - /* Nothing to do. */ + kfree(dev); } -static struct platform_device pmc_core_device = { - .name = "intel_pmc_core", - .dev = { - .release = intel_pmc_core_release, - }, -}; +static struct platform_device *pmc_core_device; /* * intel_pmc_core_platform_ids is the list of platforms where we want to @@ -52,6 +47,8 @@ MODULE_DEVICE_TABLE(x86cpu, intel_pmc_core_platform_ids); static int __init pmc_core_platform_init(void) { + int retval; + /* Skip creating the platform device if ACPI already has a device */ if (acpi_dev_present("INT33A1", NULL, -1)) return -ENODEV; @@ -59,12 +56,23 @@ static int __init pmc_core_platform_init(void) if (!x86_match_cpu(intel_pmc_core_platform_ids)) return -ENODEV; - return platform_device_register(&pmc_core_device); + pmc_core_device = kzalloc(sizeof(*pmc_core_device), GFP_KERNEL); + if (!pmc_core_device) + return -ENOMEM; + + pmc_core_device->name = "intel_pmc_core"; + pmc_core_device->dev.release = intel_pmc_core_release; + + retval = platform_device_register(pmc_core_device); + if (retval) + kfree(pmc_core_device); + + return retval; } static void __exit pmc_core_platform_exit(void) { - platform_device_unregister(&pmc_core_device); + platform_device_unregister(pmc_core_device); } module_init(pmc_core_platform_init); diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index 8cf8c1be2666..1506ec0a4777 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -171,7 +171,6 @@ #define MLXPLAT_CPLD_NR_NONE -1 #define MLXPLAT_CPLD_PSU_DEFAULT_NR 10 #define MLXPLAT_CPLD_PSU_MSNXXXX_NR 4 -#define MLXPLAT_CPLD_PSU_MSNXXXX_NR2 3 #define MLXPLAT_CPLD_FAN1_DEFAULT_NR 11 #define MLXPLAT_CPLD_FAN2_DEFAULT_NR 12 #define MLXPLAT_CPLD_FAN3_DEFAULT_NR 13 @@ -347,6 +346,15 @@ static struct i2c_board_info mlxplat_mlxcpld_pwr[] = { }, }; +static struct i2c_board_info mlxplat_mlxcpld_ext_pwr[] = { + { + I2C_BOARD_INFO("dps460", 0x5b), + }, + { + I2C_BOARD_INFO("dps460", 0x5a), + }, +}; + static struct i2c_board_info mlxplat_mlxcpld_fan[] = { { I2C_BOARD_INFO("24c32", 0x50), @@ -921,15 +929,15 @@ static struct mlxreg_core_data mlxplat_mlxcpld_ext_pwr_items_data[] = { .label = "pwr3", .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, .mask = BIT(2), - .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[0], - .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR2, + .hpdev.brdinfo = &mlxplat_mlxcpld_ext_pwr[0], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, }, { .label = "pwr4", .reg = MLXPLAT_CPLD_LPC_REG_PWR_OFFSET, .mask = BIT(3), - .hpdev.brdinfo = &mlxplat_mlxcpld_pwr[1], - .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR2, + .hpdev.brdinfo = &mlxplat_mlxcpld_ext_pwr[1], + .hpdev.nr = MLXPLAT_CPLD_PSU_MSNXXXX_NR, }, }; diff --git a/drivers/platform/x86/pcengines-apuv2.c b/drivers/platform/x86/pcengines-apuv2.c index 6aff6cf41414..c37349f97bb8 100644 --- a/drivers/platform/x86/pcengines-apuv2.c +++ b/drivers/platform/x86/pcengines-apuv2.c @@ -32,7 +32,7 @@ #define APU2_GPIO_REG_LED3 AMD_FCH_GPIO_REG_GPIO59_DEVSLP1 #define APU2_GPIO_REG_MODESW AMD_FCH_GPIO_REG_GPIO32_GE1 #define APU2_GPIO_REG_SIMSWAP AMD_FCH_GPIO_REG_GPIO33_GE2 -#define APU2_GPIO_REG_MPCIE2 AMD_FCH_GPIO_REG_GPIO59_DEVSLP0 +#define APU2_GPIO_REG_MPCIE2 AMD_FCH_GPIO_REG_GPIO55_DEVSLP0 #define APU2_GPIO_REG_MPCIE3 AMD_FCH_GPIO_REG_GPIO51 /* Order in which the GPIO lines are defined in the register list */ diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 9c4df41687a3..eae3579f106f 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -2569,7 +2569,7 @@ static void hotkey_compare_and_issue_event(struct tp_nvram_state *oldn, */ static int hotkey_kthread(void *data) { - struct tp_nvram_state s[2]; + struct tp_nvram_state s[2] = { 0 }; u32 poll_mask, event_mask; unsigned int si, so; unsigned long t; @@ -6829,8 +6829,10 @@ static int __init tpacpi_query_bcl_levels(acpi_handle handle) list_for_each_entry(child, &device->children, node) { acpi_status status = acpi_evaluate_object(child->handle, "_BCL", NULL, &buffer); - if (ACPI_FAILURE(status)) + if (ACPI_FAILURE(status)) { + buffer.length = ACPI_ALLOCATE_BUFFER; continue; + } obj = (union acpi_object *)buffer.pointer; if (!obj || (obj->type != ACPI_TYPE_PACKAGE)) { diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 5c223015ee71..dda60f89c951 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -373,6 +373,23 @@ static const struct ts_dmi_data jumper_ezpad_mini3_data = { .properties = jumper_ezpad_mini3_props, }; +static const struct property_entry mpman_converter9_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 8), + PROPERTY_ENTRY_U32("touchscreen-min-y", 8), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1664), + PROPERTY_ENTRY_U32("touchscreen-size-y", 880), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-mpman-converter9.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data mpman_converter9_data = { + .acpi_name = "MSSL1680:00", + .properties = mpman_converter9_props, +}; + static const struct property_entry mpman_mpwin895cl_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 3), PROPERTY_ENTRY_U32("touchscreen-min-y", 9), @@ -977,6 +994,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* MP Man Converter 9 */ + .driver_data = (void *)&mpman_converter9_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MPMAN"), + DMI_MATCH(DMI_PRODUCT_NAME, "Converter9"), + }, + }, + { /* MP Man MPWIN895CL */ .driver_data = (void *)&mpman_mpwin895cl_data, .matches = { diff --git a/drivers/power/supply/sbs-battery.c b/drivers/power/supply/sbs-battery.c index 49c3508a6b79..7439753fac87 100644 --- a/drivers/power/supply/sbs-battery.c +++ b/drivers/power/supply/sbs-battery.c @@ -280,6 +280,12 @@ static int sbs_update_presence(struct sbs_info *chip, bool is_present) else client->flags &= ~I2C_CLIENT_PEC; + if (of_device_is_compatible(client->dev.parent->of_node, "google,cros-ec-i2c-tunnel") + && client->flags & I2C_CLIENT_PEC) { + dev_info(&client->dev, "Disabling PEC because of broken Cros-EC implementation\n"); + client->flags &= ~I2C_CLIENT_PEC; + } + dev_dbg(&client->dev, "PEC: %s\n", (client->flags & I2C_CLIENT_PEC) ? "enabled" : "disabled"); diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c index 1bacb37e8a99..cd1224182ad7 100644 --- a/drivers/regulator/axp20x-regulator.c +++ b/drivers/regulator/axp20x-regulator.c @@ -42,8 +42,9 @@ #define AXP20X_DCDC2_V_OUT_MASK GENMASK(5, 0) #define AXP20X_DCDC3_V_OUT_MASK GENMASK(7, 0) -#define AXP20X_LDO24_V_OUT_MASK GENMASK(7, 4) +#define AXP20X_LDO2_V_OUT_MASK GENMASK(7, 4) #define AXP20X_LDO3_V_OUT_MASK GENMASK(6, 0) +#define AXP20X_LDO4_V_OUT_MASK GENMASK(3, 0) #define AXP20X_LDO5_V_OUT_MASK GENMASK(7, 4) #define AXP20X_PWR_OUT_EXTEN_MASK BIT_MASK(0) @@ -542,14 +543,14 @@ static const struct regulator_desc axp20x_regulators[] = { AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_DCDC3_MASK), AXP_DESC_FIXED(AXP20X, LDO1, "ldo1", "acin", 1300), AXP_DESC(AXP20X, LDO2, "ldo2", "ldo24in", 1800, 3300, 100, - AXP20X_LDO24_V_OUT, AXP20X_LDO24_V_OUT_MASK, + AXP20X_LDO24_V_OUT, AXP20X_LDO2_V_OUT_MASK, AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO2_MASK), AXP_DESC(AXP20X, LDO3, "ldo3", "ldo3in", 700, 3500, 25, AXP20X_LDO3_V_OUT, AXP20X_LDO3_V_OUT_MASK, AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO3_MASK), AXP_DESC_RANGES(AXP20X, LDO4, "ldo4", "ldo24in", axp20x_ldo4_ranges, AXP20X_LDO4_V_OUT_NUM_VOLTAGES, - AXP20X_LDO24_V_OUT, AXP20X_LDO24_V_OUT_MASK, + AXP20X_LDO24_V_OUT, AXP20X_LDO4_V_OUT_MASK, AXP20X_PWR_OUT_CTRL, AXP20X_PWR_OUT_LDO4_MASK), AXP_DESC_IO(AXP20X, LDO5, "ldo5", "ldo5in", 1800, 3300, 100, AXP20X_LDO5_V_OUT, AXP20X_LDO5_V_OUT_MASK, diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c index cbb770824226..1a44e321b54e 100644 --- a/drivers/s390/block/dasd_fba.c +++ b/drivers/s390/block/dasd_fba.c @@ -40,6 +40,7 @@ MODULE_LICENSE("GPL"); static struct dasd_discipline dasd_fba_discipline; +static void *dasd_fba_zero_page; struct dasd_fba_private { struct dasd_fba_characteristics rdc_data; @@ -270,7 +271,7 @@ static void ccw_write_zero(struct ccw1 *ccw, int count) ccw->cmd_code = DASD_FBA_CCW_WRITE; ccw->flags |= CCW_FLAG_SLI; ccw->count = count; - ccw->cda = (__u32) (addr_t) page_to_phys(ZERO_PAGE(0)); + ccw->cda = (__u32) (addr_t) dasd_fba_zero_page; } /* @@ -830,6 +831,11 @@ dasd_fba_init(void) int ret; ASCEBC(dasd_fba_discipline.ebcname, 4); + + dasd_fba_zero_page = (void *)get_zeroed_page(GFP_KERNEL | GFP_DMA); + if (!dasd_fba_zero_page) + return -ENOMEM; + ret = ccw_driver_register(&dasd_fba_driver); if (!ret) wait_for_device_probe(); @@ -841,6 +847,7 @@ static void __exit dasd_fba_cleanup(void) { ccw_driver_unregister(&dasd_fba_driver); + free_page((unsigned long)dasd_fba_zero_page); } module_init(dasd_fba_init); diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c index 4dbbfd88262c..f314936b5462 100644 --- a/drivers/s390/crypto/zcrypt_api.c +++ b/drivers/s390/crypto/zcrypt_api.c @@ -1449,7 +1449,8 @@ static long zcrypt_unlocked_ioctl(struct file *filp, unsigned int cmd, if (!reqcnt) return -ENOMEM; zcrypt_perdev_reqcnt(reqcnt, AP_DEVICES); - if (copy_to_user((int __user *) arg, reqcnt, sizeof(reqcnt))) + if (copy_to_user((int __user *) arg, reqcnt, + sizeof(u32) * AP_DEVICES)) rc = -EFAULT; kfree(reqcnt); return rc; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 3a94f6cad167..6384f7adba66 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -284,11 +284,11 @@ static void qeth_l2_stop_card(struct qeth_card *card) if (card->state == CARD_STATE_SOFTSETUP) { qeth_clear_ipacmd_list(card); - qeth_drain_output_queues(card); card->state = CARD_STATE_DOWN; } qeth_qdio_clear_card(card, 0); + qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); flush_workqueue(card->event_wq); qeth_flush_local_addrs(card); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 4d461960370d..09ef518ca1ea 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1168,11 +1168,11 @@ static void qeth_l3_stop_card(struct qeth_card *card) if (card->state == CARD_STATE_SOFTSETUP) { qeth_l3_clear_ip_htable(card, 1); qeth_clear_ipacmd_list(card); - qeth_drain_output_queues(card); card->state = CARD_STATE_DOWN; } qeth_qdio_clear_card(card, 0); + qeth_drain_output_queues(card); qeth_clear_working_pool_list(card); flush_workqueue(card->event_wq); qeth_flush_local_addrs(card); diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index b5dd1caae5e9..d10efb66cf19 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -736,6 +736,7 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, struct iscsi_tcp_conn *tcp_conn = conn->dd_data; struct iscsi_sw_tcp_conn *tcp_sw_conn = tcp_conn->dd_data; struct sockaddr_in6 addr; + struct socket *sock; int rc; switch(param) { @@ -747,13 +748,17 @@ static int iscsi_sw_tcp_conn_get_param(struct iscsi_cls_conn *cls_conn, spin_unlock_bh(&conn->session->frwd_lock); return -ENOTCONN; } + sock = tcp_sw_conn->sock; + sock_hold(sock->sk); + spin_unlock_bh(&conn->session->frwd_lock); + if (param == ISCSI_PARAM_LOCAL_PORT) - rc = kernel_getsockname(tcp_sw_conn->sock, + rc = kernel_getsockname(sock, (struct sockaddr *)&addr); else - rc = kernel_getpeername(tcp_sw_conn->sock, + rc = kernel_getpeername(sock, (struct sockaddr *)&addr); - spin_unlock_bh(&conn->session->frwd_lock); + sock_put(sock->sk); if (rc < 0) return rc; @@ -775,6 +780,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, struct iscsi_tcp_conn *tcp_conn; struct iscsi_sw_tcp_conn *tcp_sw_conn; struct sockaddr_in6 addr; + struct socket *sock; int rc; switch (param) { @@ -789,16 +795,18 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, return -ENOTCONN; } tcp_conn = conn->dd_data; - tcp_sw_conn = tcp_conn->dd_data; - if (!tcp_sw_conn->sock) { + sock = tcp_sw_conn->sock; + if (!sock) { spin_unlock_bh(&session->frwd_lock); return -ENOTCONN; } + sock_hold(sock->sk); + spin_unlock_bh(&session->frwd_lock); - rc = kernel_getsockname(tcp_sw_conn->sock, + rc = kernel_getsockname(sock, (struct sockaddr *)&addr); - spin_unlock_bh(&session->frwd_lock); + sock_put(sock->sk); if (rc < 0) return rc; diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c index 37e5d4e48c2f..83f14b2c8804 100644 --- a/drivers/scsi/libiscsi_tcp.c +++ b/drivers/scsi/libiscsi_tcp.c @@ -128,7 +128,7 @@ static void iscsi_tcp_segment_map(struct iscsi_segment *segment, int recv) * coalescing neighboring slab objects into a single frag which * triggers one of hardened usercopy checks. */ - if (!recv && page_count(sg_page(sg)) >= 1 && !PageSlab(sg_page(sg))) + if (!recv && sendpage_ok(sg_page(sg))) return; if (recv) { diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index d32c7e7ab09d..bb02fd8bc2dd 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -71,6 +71,7 @@ static void lpfc_disc_timeout_handler(struct lpfc_vport *); static void lpfc_disc_flush_list(struct lpfc_vport *vport); static void lpfc_unregister_fcfi_cmpl(struct lpfc_hba *, LPFC_MBOXQ_t *); static int lpfc_fcf_inuse(struct lpfc_hba *); +static void lpfc_mbx_cmpl_read_sparam(struct lpfc_hba *, LPFC_MBOXQ_t *); void lpfc_terminate_rport_io(struct fc_rport *rport) @@ -1138,11 +1139,13 @@ out: return; } - void lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) { struct lpfc_vport *vport = pmb->vport; + LPFC_MBOXQ_t *sparam_mb; + struct lpfc_dmabuf *sparam_mp; + int rc; if (pmb->u.mb.mbxStatus) goto out; @@ -1167,12 +1170,42 @@ lpfc_mbx_cmpl_local_config_link(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb) } /* Start discovery by sending a FLOGI. port_state is identically - * LPFC_FLOGI while waiting for FLOGI cmpl. Check if sending - * the FLOGI is being deferred till after MBX_READ_SPARAM completes. + * LPFC_FLOGI while waiting for FLOGI cmpl. */ if (vport->port_state != LPFC_FLOGI) { - if (!(phba->hba_flag & HBA_DEFER_FLOGI)) + /* Issue MBX_READ_SPARAM to update CSPs before FLOGI if + * bb-credit recovery is in place. + */ + if (phba->bbcredit_support && phba->cfg_enable_bbcr && + !(phba->link_flag & LS_LOOPBACK_MODE)) { + sparam_mb = mempool_alloc(phba->mbox_mem_pool, + GFP_KERNEL); + if (!sparam_mb) + goto sparam_out; + + rc = lpfc_read_sparam(phba, sparam_mb, 0); + if (rc) { + mempool_free(sparam_mb, phba->mbox_mem_pool); + goto sparam_out; + } + sparam_mb->vport = vport; + sparam_mb->mbox_cmpl = lpfc_mbx_cmpl_read_sparam; + rc = lpfc_sli_issue_mbox(phba, sparam_mb, MBX_NOWAIT); + if (rc == MBX_NOT_FINISHED) { + sparam_mp = (struct lpfc_dmabuf *) + sparam_mb->ctx_buf; + lpfc_mbuf_free(phba, sparam_mp->virt, + sparam_mp->phys); + kfree(sparam_mp); + sparam_mb->ctx_buf = NULL; + mempool_free(sparam_mb, phba->mbox_mem_pool); + goto sparam_out; + } + + phba->hba_flag |= HBA_DEFER_FLOGI; + } else { lpfc_initial_flogi(vport); + } } else { if (vport->fc_flag & FC_PT2PT) lpfc_disc_start(vport); @@ -1184,6 +1217,7 @@ out: "0306 CONFIG_LINK mbxStatus error x%x " "HBA state x%x\n", pmb->u.mb.mbxStatus, vport->port_state); +sparam_out: mempool_free(pmb, phba->mbox_mem_pool); lpfc_linkdown(phba); @@ -3239,21 +3273,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) lpfc_linkup(phba); sparam_mbox = NULL; - if (!(phba->hba_flag & HBA_FCOE_MODE)) { - cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); - if (!cfglink_mbox) - goto out; - vport->port_state = LPFC_LOCAL_CFG_LINK; - lpfc_config_link(phba, cfglink_mbox); - cfglink_mbox->vport = vport; - cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link; - rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT); - if (rc == MBX_NOT_FINISHED) { - mempool_free(cfglink_mbox, phba->mbox_mem_pool); - goto out; - } - } - sparam_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); if (!sparam_mbox) goto out; @@ -3274,7 +3293,20 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) goto out; } - if (phba->hba_flag & HBA_FCOE_MODE) { + if (!(phba->hba_flag & HBA_FCOE_MODE)) { + cfglink_mbox = mempool_alloc(phba->mbox_mem_pool, GFP_KERNEL); + if (!cfglink_mbox) + goto out; + vport->port_state = LPFC_LOCAL_CFG_LINK; + lpfc_config_link(phba, cfglink_mbox); + cfglink_mbox->vport = vport; + cfglink_mbox->mbox_cmpl = lpfc_mbx_cmpl_local_config_link; + rc = lpfc_sli_issue_mbox(phba, cfglink_mbox, MBX_NOWAIT); + if (rc == MBX_NOT_FINISHED) { + mempool_free(cfglink_mbox, phba->mbox_mem_pool); + goto out; + } + } else { vport->port_state = LPFC_VPORT_UNKNOWN; /* * Add the driver's default FCF record at FCF index 0 now. This @@ -3331,10 +3363,6 @@ lpfc_mbx_process_link_up(struct lpfc_hba *phba, struct lpfc_mbx_read_top *la) } /* Reset FCF roundrobin bmask for new discovery */ lpfc_sli4_clear_fcf_rr_bmask(phba); - } else { - if (phba->bbcredit_support && phba->cfg_enable_bbcr && - !(phba->link_flag & LS_LOOPBACK_MODE)) - phba->hba_flag |= HBA_DEFER_FLOGI; } /* Prepare for LINK up registrations */ diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 95018e650f2d..16503e22691e 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2964,26 +2964,32 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) if (sdkp->device->type == TYPE_ZBC) { /* Host-managed */ - q->limits.zoned = BLK_ZONED_HM; + blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HM); } else { sdkp->zoned = (buffer[8] >> 4) & 3; - if (sdkp->zoned == 1 && !disk_has_partitions(sdkp->disk)) { + if (sdkp->zoned == 1) { /* Host-aware */ - q->limits.zoned = BLK_ZONED_HA; + blk_queue_set_zoned(sdkp->disk, BLK_ZONED_HA); } else { - /* - * Treat drive-managed devices and host-aware devices - * with partitions as regular block devices. - */ - q->limits.zoned = BLK_ZONED_NONE; - if (sdkp->zoned == 2 && sdkp->first_scan) - sd_printk(KERN_NOTICE, sdkp, - "Drive-managed SMR disk\n"); + /* Regular disk or drive managed disk */ + blk_queue_set_zoned(sdkp->disk, BLK_ZONED_NONE); } } - if (blk_queue_is_zoned(q) && sdkp->first_scan) + + if (!sdkp->first_scan) + goto out; + + if (blk_queue_is_zoned(q)) { sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n", q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware"); + } else { + if (sdkp->zoned == 1) + sd_printk(KERN_NOTICE, sdkp, + "Host-aware SMR disk used as regular disk\n"); + else if (sdkp->zoned == 2) + sd_printk(KERN_NOTICE, sdkp, + "Drive-managed SMR disk\n"); + } out: kfree(buffer); @@ -3404,10 +3410,6 @@ static int sd_probe(struct device *dev) sdkp->first_scan = 1; sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS; - error = sd_zbc_init_disk(sdkp); - if (error) - goto out_free_index; - sd_revalidate_disk(gd); gd->flags = GENHD_FL_EXT_DEVT; diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index 4933e7daf17d..a3aad608bc38 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -215,7 +215,6 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp) #ifdef CONFIG_BLK_DEV_ZONED -int sd_zbc_init_disk(struct scsi_disk *sdkp); void sd_zbc_release_disk(struct scsi_disk *sdkp); int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buffer); int sd_zbc_revalidate_zones(struct scsi_disk *sdkp); @@ -231,11 +230,6 @@ blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba, #else /* CONFIG_BLK_DEV_ZONED */ -static inline int sd_zbc_init_disk(struct scsi_disk *sdkp) -{ - return 0; -} - static inline void sd_zbc_release_disk(struct scsi_disk *sdkp) {} static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, @@ -259,7 +253,7 @@ static inline blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd, static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes, struct scsi_sense_hdr *sshdr) { - return 0; + return good_bytes; } static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 0e94ff056bff..cf07b7f93579 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -651,6 +651,28 @@ static void sd_zbc_print_zones(struct scsi_disk *sdkp) sdkp->zone_blocks); } +static int sd_zbc_init_disk(struct scsi_disk *sdkp) +{ + sdkp->zones_wp_offset = NULL; + spin_lock_init(&sdkp->zones_wp_offset_lock); + sdkp->rev_wp_offset = NULL; + mutex_init(&sdkp->rev_mutex); + INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn); + sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL); + if (!sdkp->zone_wp_update_buf) + return -ENOMEM; + + return 0; +} + +void sd_zbc_release_disk(struct scsi_disk *sdkp) +{ + kvfree(sdkp->zones_wp_offset); + sdkp->zones_wp_offset = NULL; + kfree(sdkp->zone_wp_update_buf); + sdkp->zone_wp_update_buf = NULL; +} + static void sd_zbc_revalidate_zones_cb(struct gendisk *disk) { struct scsi_disk *sdkp = scsi_disk(disk); @@ -667,7 +689,24 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) u32 max_append; int ret = 0; - if (!sd_is_zoned(sdkp)) + /* + * For all zoned disks, initialize zone append emulation data if not + * already done. This is necessary also for host-aware disks used as + * regular disks due to the presence of partitions as these partitions + * may be deleted and the disk zoned model changed back from + * BLK_ZONED_NONE to BLK_ZONED_HA. + */ + if (sd_is_zoned(sdkp) && !sdkp->zone_wp_update_buf) { + ret = sd_zbc_init_disk(sdkp); + if (ret) + return ret; + } + + /* + * There is nothing to do for regular disks, including host-aware disks + * that have partitions. + */ + if (!blk_queue_is_zoned(q)) return 0; /* @@ -764,28 +803,3 @@ err: return ret; } - -int sd_zbc_init_disk(struct scsi_disk *sdkp) -{ - if (!sd_is_zoned(sdkp)) - return 0; - - sdkp->zones_wp_offset = NULL; - spin_lock_init(&sdkp->zones_wp_offset_lock); - sdkp->rev_wp_offset = NULL; - mutex_init(&sdkp->rev_mutex); - INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn); - sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL); - if (!sdkp->zone_wp_update_buf) - return -ENOMEM; - - return 0; -} - -void sd_zbc_release_disk(struct scsi_disk *sdkp) -{ - kvfree(sdkp->zones_wp_offset); - sdkp->zones_wp_offset = NULL; - kfree(sdkp->zone_wp_update_buf); - sdkp->zone_wp_update_buf = NULL; -} diff --git a/drivers/spi/spi-bcm-qspi.c b/drivers/spi/spi-bcm-qspi.c index 681d09085175..9cfa15ec8b08 100644 --- a/drivers/spi/spi-bcm-qspi.c +++ b/drivers/spi/spi-bcm-qspi.c @@ -1295,7 +1295,7 @@ static const struct of_device_id bcm_qspi_of_match[] = { }, { .compatible = "brcm,spi-bcm-qspi", - .data = &bcm_qspi_rev_data, + .data = &bcm_qspi_no_rev_data, }, { .compatible = "brcm,spi-bcm7216-qspi", diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c index c45d76c848c8..41986ac0fbfb 100644 --- a/drivers/spi/spi-bcm2835.c +++ b/drivers/spi/spi-bcm2835.c @@ -75,7 +75,7 @@ #define DRV_NAME "spi-bcm2835" /* define polling limits */ -unsigned int polling_limit_us = 30; +static unsigned int polling_limit_us = 30; module_param(polling_limit_us, uint, 0664); MODULE_PARM_DESC(polling_limit_us, "time in us to run a transfer in polling mode\n"); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 91c6affe139c..108a7d50d2c3 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -174,17 +174,17 @@ static const struct fsl_dspi_devtype_data devtype_data[] = { .fifo_size = 16, }, [LS2080A] = { - .trans_mode = DSPI_DMA_MODE, + .trans_mode = DSPI_XSPI_MODE, .max_clock_factor = 8, .fifo_size = 4, }, [LS2085A] = { - .trans_mode = DSPI_DMA_MODE, + .trans_mode = DSPI_XSPI_MODE, .max_clock_factor = 8, .fifo_size = 4, }, [LX2160A] = { - .trans_mode = DSPI_DMA_MODE, + .trans_mode = DSPI_XSPI_MODE, .max_clock_factor = 8, .fifo_size = 4, }, @@ -1273,11 +1273,17 @@ static int dspi_probe(struct platform_device *pdev) void __iomem *base; bool big_endian; - ctlr = spi_alloc_master(&pdev->dev, sizeof(struct fsl_dspi)); + dspi = devm_kzalloc(&pdev->dev, sizeof(*dspi), GFP_KERNEL); + if (!dspi) + return -ENOMEM; + + ctlr = spi_alloc_master(&pdev->dev, 0); if (!ctlr) return -ENOMEM; - dspi = spi_controller_get_devdata(ctlr); + spi_controller_set_devdata(ctlr, dspi); + platform_set_drvdata(pdev, dspi); + dspi->pdev = pdev; dspi->ctlr = ctlr; @@ -1414,8 +1420,6 @@ poll_mode: if (dspi->devtype_data->trans_mode != DSPI_DMA_MODE) ctlr->ptp_sts_supported = true; - platform_set_drvdata(pdev, ctlr); - ret = spi_register_controller(ctlr); if (ret != 0) { dev_err(&pdev->dev, "Problem registering DSPI ctlr\n"); @@ -1437,8 +1441,7 @@ out_ctlr_put: static int dspi_remove(struct platform_device *pdev) { - struct spi_controller *ctlr = platform_get_drvdata(pdev); - struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr); + struct fsl_dspi *dspi = platform_get_drvdata(pdev); /* Disconnect from the SPI framework */ spi_unregister_controller(dspi->ctlr); diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c index e60581283a24..6d148ab70b93 100644 --- a/drivers/spi/spi-fsl-espi.c +++ b/drivers/spi/spi-fsl-espi.c @@ -564,13 +564,14 @@ static void fsl_espi_cpu_irq(struct fsl_espi *espi, u32 events) static irqreturn_t fsl_espi_irq(s32 irq, void *context_data) { struct fsl_espi *espi = context_data; - u32 events; + u32 events, mask; spin_lock(&espi->lock); /* Get interrupt events(tx/rx) */ events = fsl_espi_read_reg(espi, ESPI_SPIE); - if (!events) { + mask = fsl_espi_read_reg(espi, ESPI_SPIM); + if (!(events & mask)) { spin_unlock(&espi->lock); return IRQ_NONE; } diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c index 590eac2df909..ff26ab0a5f60 100644 --- a/drivers/target/target_core_transport.c +++ b/drivers/target/target_core_transport.c @@ -1840,7 +1840,8 @@ int target_submit_tmr(struct se_cmd *se_cmd, struct se_session *se_sess, * out unpacked_lun for the original se_cmd. */ if (tm_type == TMR_ABORT_TASK && (flags & TARGET_SCF_LOOKUP_LUN_FROM_TAG)) { - if (!target_lookup_lun_from_tag(se_sess, tag, &unpacked_lun)) + if (!target_lookup_lun_from_tag(se_sess, tag, + &se_cmd->orig_fe_lun)) goto failure; } diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index 7e73e989645b..b351962279e4 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -269,8 +269,30 @@ static int usb_probe_device(struct device *dev) if (error) return error; + /* Probe the USB device with the driver in hand, but only + * defer to a generic driver in case the current USB + * device driver has an id_table or a match function; i.e., + * when the device driver was explicitly matched against + * a device. + * + * If the device driver does not have either of these, + * then we assume that it can bind to any device and is + * not truly a more specialized/non-generic driver, so a + * return value of -ENODEV should not force the device + * to be handled by the generic USB driver, as there + * can still be another, more specialized, device driver. + * + * This accommodates the usbip driver. + * + * TODO: What if, in the future, there are multiple + * specialized USB device drivers for a particular device? + * In such cases, there is a need to try all matching + * specialised device drivers prior to setting the + * use_generic_driver bit. + */ error = udriver->probe(udev); - if (error == -ENODEV && udriver != &usb_generic_driver) { + if (error == -ENODEV && udriver != &usb_generic_driver && + (udriver->id_table || udriver->match)) { udev->use_generic_driver = 1; return -EPROBE_DEFER; } @@ -831,14 +853,17 @@ static int usb_device_match(struct device *dev, struct device_driver *drv) udev = to_usb_device(dev); udrv = to_usb_device_driver(drv); - if (udrv->id_table && - usb_device_match_id(udev, udrv->id_table) != NULL) { - return 1; - } + if (udrv->id_table) + return usb_device_match_id(udev, udrv->id_table) != NULL; if (udrv->match) return udrv->match(udev); - return 0; + + /* If the device driver under consideration does not have a + * id_table or a match function, then let the driver's probe + * function decide. + */ + return 1; } else if (is_usb_interface(dev)) { struct usb_interface *intf; @@ -905,26 +930,19 @@ static int usb_uevent(struct device *dev, struct kobj_uevent_env *env) return 0; } -static bool is_dev_usb_generic_driver(struct device *dev) -{ - struct usb_device_driver *udd = dev->driver ? - to_usb_device_driver(dev->driver) : NULL; - - return udd == &usb_generic_driver; -} - static int __usb_bus_reprobe_drivers(struct device *dev, void *data) { struct usb_device_driver *new_udriver = data; struct usb_device *udev; int ret; - if (!is_dev_usb_generic_driver(dev)) + /* Don't reprobe if current driver isn't usb_generic_driver */ + if (dev->driver != &usb_generic_driver.drvwrap.driver) return 0; udev = to_usb_device(dev); if (usb_device_match_id(udev, new_udriver->id_table) == NULL && - (!new_udriver->match || new_udriver->match(udev) != 0)) + (!new_udriver->match || new_udriver->match(udev) == 0)) return 0; ret = device_reprobe(dev); diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index b4206b0dede5..1f638759a953 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1189,7 +1189,6 @@ static int ncm_unwrap_ntb(struct gether *port, const struct ndp_parser_opts *opts = ncm->parser_opts; unsigned crc_len = ncm->is_crc ? sizeof(uint32_t) : 0; int dgram_counter; - bool ndp_after_header; /* dwSignature */ if (get_unaligned_le32(tmp) != opts->nth_sign) { @@ -1216,7 +1215,6 @@ static int ncm_unwrap_ntb(struct gether *port, } ndp_index = get_ncm(&tmp, opts->ndp_index); - ndp_after_header = false; /* Run through all the NDP's in the NTB */ do { @@ -1232,8 +1230,6 @@ static int ncm_unwrap_ntb(struct gether *port, ndp_index); goto err; } - if (ndp_index == opts->nth_size) - ndp_after_header = true; /* * walk through NDP @@ -1312,37 +1308,13 @@ static int ncm_unwrap_ntb(struct gether *port, index2 = get_ncm(&tmp, opts->dgram_item_len); dg_len2 = get_ncm(&tmp, opts->dgram_item_len); - if (index2 == 0 || dg_len2 == 0) - break; - /* wDatagramIndex[1] */ - if (ndp_after_header) { - if (index2 < opts->nth_size + opts->ndp_size) { - INFO(port->func.config->cdev, - "Bad index: %#X\n", index2); - goto err; - } - } else { - if (index2 < opts->nth_size + opts->dpe_size) { - INFO(port->func.config->cdev, - "Bad index: %#X\n", index2); - goto err; - } - } if (index2 > block_len - opts->dpe_size) { INFO(port->func.config->cdev, "Bad index: %#X\n", index2); goto err; } - /* wDatagramLength[1] */ - if ((dg_len2 < 14 + crc_len) || - (dg_len2 > frame_max)) { - INFO(port->func.config->cdev, - "Bad dgram length: %#X\n", dg_len); - goto err; - } - /* * Copy the data into a new skb. * This ensures the truesize is correct @@ -1359,6 +1331,8 @@ static int ncm_unwrap_ntb(struct gether *port, ndp_len -= 2 * (opts->dgram_item_len * 2); dgram_counter++; + if (index2 == 0 || dg_len2 == 0) + break; } while (ndp_len > 2 * (opts->dgram_item_len * 2)); } while (ndp_index); diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c index 9d7d642022d1..2305d425e6c9 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -461,11 +461,6 @@ static void stub_disconnect(struct usb_device *udev) return; } -static bool usbip_match(struct usb_device *udev) -{ - return true; -} - #ifdef CONFIG_PM /* These functions need usb_port_suspend and usb_port_resume, @@ -491,7 +486,6 @@ struct usb_device_driver stub_driver = { .name = "usbip-host", .probe = stub_probe, .disconnect = stub_disconnect, - .match = usbip_match, #ifdef CONFIG_PM .suspend = stub_suspend, .resume = stub_resume, diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig index 4271c408103e..d7d32b656102 100644 --- a/drivers/vdpa/Kconfig +++ b/drivers/vdpa/Kconfig @@ -30,9 +30,7 @@ config IFCVF be called ifcvf. config MLX5_VDPA - bool "MLX5 VDPA support library for ConnectX devices" - depends on MLX5_CORE - default n + bool help Support library for Mellanox VDPA drivers. Provides code that is common for all types of VDPA drivers. The following drivers are planned: @@ -40,7 +38,8 @@ config MLX5_VDPA config MLX5_VDPA_NET tristate "vDPA driver for ConnectX devices" - depends on MLX5_VDPA + select MLX5_VDPA + depends on MLX5_CORE default n help VDPA network driver for ConnectX6 and newer. Provides offloading diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 70676a6d1691..74264e590695 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1133,15 +1133,17 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m if (!mvq->initialized) return; - if (query_virtqueue(ndev, mvq, &attr)) { - mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n"); - return; - } if (mvq->fw_state != MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY) return; if (modify_virtqueue(ndev, mvq, MLX5_VIRTIO_NET_Q_OBJECT_STATE_SUSPEND)) mlx5_vdpa_warn(&ndev->mvdev, "modify to suspend failed\n"); + + if (query_virtqueue(ndev, mvq, &attr)) { + mlx5_vdpa_warn(&ndev->mvdev, "failed to query virtqueue\n"); + return; + } + mvq->avail_idx = attr.available_index; } static void suspend_vqs(struct mlx5_vdpa_net *ndev) @@ -1411,8 +1413,14 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa struct mlx5_virtq_attr attr; int err; - if (!mvq->initialized) - return -EAGAIN; + /* If the virtq object was destroyed, use the value saved at + * the last minute of suspend_vq. This caters for userspace + * that cares about emulating the index after vq is stopped. + */ + if (!mvq->initialized) { + state->avail_index = mvq->avail_idx; + return 0; + } err = query_virtqueue(ndev, mvq, &attr); if (err) { diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c index 34aec4ba331e..0fd3f87e913c 100644 --- a/drivers/vhost/iotlb.c +++ b/drivers/vhost/iotlb.c @@ -149,7 +149,7 @@ EXPORT_SYMBOL_GPL(vhost_iotlb_free); * vhost_iotlb_itree_first - return the first overlapped range * @iotlb: the IOTLB * @start: start of IOVA range - * @end: end of IOVA range + * @last: last byte in IOVA range */ struct vhost_iotlb_map * vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last) @@ -162,7 +162,7 @@ EXPORT_SYMBOL_GPL(vhost_iotlb_itree_first); * vhost_iotlb_itree_next - return the next overlapped range * @map: the starting map node * @start: start of IOVA range - * @end: end of IOVA range + * @last: last byte IOVA range */ struct vhost_iotlb_map * vhost_iotlb_itree_next(struct vhost_iotlb_map *map, u64 start, u64 last) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 3fab94f88894..62a9bb0efc55 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -353,8 +353,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, struct vdpa_callback cb; struct vhost_virtqueue *vq; struct vhost_vring_state s; - u64 __user *featurep = argp; - u64 features; u32 idx; long r; @@ -381,18 +379,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd, vq->last_avail_idx = vq_state.avail_index; break; - case VHOST_GET_BACKEND_FEATURES: - features = VHOST_VDPA_BACKEND_FEATURES; - if (copy_to_user(featurep, &features, sizeof(features))) - return -EFAULT; - return 0; - case VHOST_SET_BACKEND_FEATURES: - if (copy_from_user(&features, featurep, sizeof(features))) - return -EFAULT; - if (features & ~VHOST_VDPA_BACKEND_FEATURES) - return -EOPNOTSUPP; - vhost_set_backend_features(&v->vdev, features); - return 0; } r = vhost_vring_ioctl(&v->vdev, cmd, argp); @@ -440,8 +426,20 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, struct vhost_vdpa *v = filep->private_data; struct vhost_dev *d = &v->vdev; void __user *argp = (void __user *)arg; + u64 __user *featurep = argp; + u64 features; long r; + if (cmd == VHOST_SET_BACKEND_FEATURES) { + r = copy_from_user(&features, featurep, sizeof(features)); + if (r) + return r; + if (features & ~VHOST_VDPA_BACKEND_FEATURES) + return -EOPNOTSUPP; + vhost_set_backend_features(&v->vdev, features); + return 0; + } + mutex_lock(&d->mutex); switch (cmd) { @@ -476,6 +474,10 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep, case VHOST_VDPA_SET_CONFIG_CALL: r = vhost_vdpa_set_config_call(v, argp); break; + case VHOST_GET_BACKEND_FEATURES: + features = VHOST_VDPA_BACKEND_FEATURES; + r = copy_to_user(featurep, &features, sizeof(features)); + break; default: r = vhost_dev_ioctl(&v->vdev, cmd, argp); if (r == -ENOIOCTLCMD) @@ -563,6 +565,9 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, perm_to_iommu_flags(perm)); } + if (r) + vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1); + return r; } @@ -590,21 +595,19 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, struct vhost_dev *dev = &v->vdev; struct vhost_iotlb *iotlb = dev->iotlb; struct page **page_list; - unsigned long list_size = PAGE_SIZE / sizeof(struct page *); + struct vm_area_struct **vmas; unsigned int gup_flags = FOLL_LONGTERM; - unsigned long npages, cur_base, map_pfn, last_pfn = 0; - unsigned long locked, lock_limit, pinned, i; + unsigned long map_pfn, last_pfn = 0; + unsigned long npages, lock_limit; + unsigned long i, nmap = 0; u64 iova = msg->iova; + long pinned; int ret = 0; if (vhost_iotlb_itree_first(iotlb, msg->iova, msg->iova + msg->size - 1)) return -EEXIST; - page_list = (struct page **) __get_free_page(GFP_KERNEL); - if (!page_list) - return -ENOMEM; - if (msg->perm & VHOST_ACCESS_WO) gup_flags |= FOLL_WRITE; @@ -612,61 +615,86 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v, if (!npages) return -EINVAL; + page_list = kvmalloc_array(npages, sizeof(struct page *), GFP_KERNEL); + vmas = kvmalloc_array(npages, sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!page_list || !vmas) { + ret = -ENOMEM; + goto free; + } + mmap_read_lock(dev->mm); - locked = atomic64_add_return(npages, &dev->mm->pinned_vm); lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - if (locked > lock_limit) { + if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) { ret = -ENOMEM; - goto out; + goto unlock; } - cur_base = msg->uaddr & PAGE_MASK; - iova &= PAGE_MASK; + pinned = pin_user_pages(msg->uaddr & PAGE_MASK, npages, gup_flags, + page_list, vmas); + if (npages != pinned) { + if (pinned < 0) { + ret = pinned; + } else { + unpin_user_pages(page_list, pinned); + ret = -ENOMEM; + } + goto unlock; + } - while (npages) { - pinned = min_t(unsigned long, npages, list_size); - ret = pin_user_pages(cur_base, pinned, - gup_flags, page_list, NULL); - if (ret != pinned) - goto out; - - if (!last_pfn) - map_pfn = page_to_pfn(page_list[0]); - - for (i = 0; i < ret; i++) { - unsigned long this_pfn = page_to_pfn(page_list[i]); - u64 csize; - - if (last_pfn && (this_pfn != last_pfn + 1)) { - /* Pin a contiguous chunk of memory */ - csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT; - if (vhost_vdpa_map(v, iova, csize, - map_pfn << PAGE_SHIFT, - msg->perm)) - goto out; - map_pfn = this_pfn; - iova += csize; + iova &= PAGE_MASK; + map_pfn = page_to_pfn(page_list[0]); + + /* One more iteration to avoid extra vdpa_map() call out of loop. */ + for (i = 0; i <= npages; i++) { + unsigned long this_pfn; + u64 csize; + + /* The last chunk may have no valid PFN next to it */ + this_pfn = i < npages ? page_to_pfn(page_list[i]) : -1UL; + + if (last_pfn && (this_pfn == -1UL || + this_pfn != last_pfn + 1)) { + /* Pin a contiguous chunk of memory */ + csize = last_pfn - map_pfn + 1; + ret = vhost_vdpa_map(v, iova, csize << PAGE_SHIFT, + map_pfn << PAGE_SHIFT, + msg->perm); + if (ret) { + /* + * Unpin the rest chunks of memory on the + * flight with no corresponding vdpa_map() + * calls having been made yet. On the other + * hand, vdpa_unmap() in the failure path + * is in charge of accounting the number of + * pinned pages for its own. + * This asymmetrical pattern of accounting + * is for efficiency to pin all pages at + * once, while there is no other callsite + * of vdpa_map() than here above. + */ + unpin_user_pages(&page_list[nmap], + npages - nmap); + goto out; } - - last_pfn = this_pfn; + atomic64_add(csize, &dev->mm->pinned_vm); + nmap += csize; + iova += csize << PAGE_SHIFT; + map_pfn = this_pfn; } - - cur_base += ret << PAGE_SHIFT; - npages -= ret; + last_pfn = this_pfn; } - /* Pin the rest chunk */ - ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT, - map_pfn << PAGE_SHIFT, msg->perm); + WARN_ON(nmap != npages); out: - if (ret) { + if (ret) vhost_vdpa_unmap(v, msg->iova, msg->size); - atomic64_sub(npages, &dev->mm->pinned_vm); - } +unlock: mmap_read_unlock(dev->mm); - free_page((unsigned long)page_list); +free: + kvfree(vmas); + kvfree(page_list); return ret; } @@ -808,6 +836,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep) err_init_iotlb: vhost_dev_cleanup(&v->vdev); + kfree(vqs); err: atomic_dec(&v->opened); return r; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index b45519ca66a7..9ad45e1d27f0 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1290,6 +1290,11 @@ static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num, vring_used_t __user *used) { + /* If an IOTLB device is present, the vring addresses are + * GIOVAs. Access validation occurs at prefetch time. */ + if (vq->iotlb) + return true; + return access_ok(desc, vhost_get_desc_size(vq, num)) && access_ok(avail, vhost_get_avail_size(vq, num)) && access_ok(used, vhost_get_used_size(vq, num)); @@ -1365,6 +1370,20 @@ bool vhost_log_access_ok(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_log_access_ok); +static bool vq_log_used_access_ok(struct vhost_virtqueue *vq, + void __user *log_base, + bool log_used, + u64 log_addr) +{ + /* If an IOTLB device is present, log_addr is a GIOVA that + * will never be logged by log_used(). */ + if (vq->iotlb) + return true; + + return !log_used || log_access_ok(log_base, log_addr, + vhost_get_used_size(vq, vq->num)); +} + /* Verify access for write logging. */ /* Caller should have vq mutex and device mutex */ static bool vq_log_access_ok(struct vhost_virtqueue *vq, @@ -1372,8 +1391,7 @@ static bool vq_log_access_ok(struct vhost_virtqueue *vq, { return vq_memory_access_ok(log_base, vq->umem, vhost_has_feature(vq, VHOST_F_LOG_ALL)) && - (!vq->log_used || log_access_ok(log_base, vq->log_addr, - vhost_get_used_size(vq, vq->num))); + vq_log_used_access_ok(vq, log_base, vq->log_used, vq->log_addr); } /* Can we start vq? */ @@ -1383,10 +1401,6 @@ bool vhost_vq_access_ok(struct vhost_virtqueue *vq) if (!vq_log_access_ok(vq, vq->log_base)) return false; - /* Access validation occurs at prefetch time with IOTLB */ - if (vq->iotlb) - return true; - return vq_access_ok(vq, vq->num, vq->desc, vq->avail, vq->used); } EXPORT_SYMBOL_GPL(vhost_vq_access_ok); @@ -1516,10 +1530,9 @@ static long vhost_vring_set_addr(struct vhost_dev *d, return -EINVAL; /* Also validate log access for used ring if enabled. */ - if ((a.flags & (0x1 << VHOST_VRING_F_LOG)) && - !log_access_ok(vq->log_base, a.log_guest_addr, - sizeof *vq->used + - vq->num * sizeof *vq->used->ring)) + if (!vq_log_used_access_ok(vq, vq->log_base, + a.flags & (0x1 << VHOST_VRING_F_LOG), + a.log_guest_addr)) return -EINVAL; } diff --git a/drivers/video/console/newport_con.c b/drivers/video/console/newport_con.c index 72f146d047d9..cd51b7a17a21 100644 --- a/drivers/video/console/newport_con.c +++ b/drivers/video/console/newport_con.c @@ -35,12 +35,6 @@ #define FONT_DATA ((unsigned char *)font_vga_8x16.data) -/* borrowed from fbcon.c */ -#define REFCOUNT(fd) (((int *)(fd))[-1]) -#define FNTSIZE(fd) (((int *)(fd))[-2]) -#define FNTCHARCNT(fd) (((int *)(fd))[-3]) -#define FONT_EXTRA_WORDS 3 - static unsigned char *font_data[MAX_NR_CONSOLES]; static struct newport_regs *npregs; @@ -522,6 +516,7 @@ static int newport_set_font(int unit, struct console_font *op) FNTSIZE(new_data) = size; FNTCHARCNT(new_data) = op->charcount; REFCOUNT(new_data) = 0; /* usage counter */ + FNTSUM(new_data) = 0; p = new_data; for (i = 0; i < op->charcount; i++) { diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig index b2c9dd4f0cb5..402e85450bb5 100644 --- a/drivers/video/fbdev/Kconfig +++ b/drivers/video/fbdev/Kconfig @@ -272,6 +272,26 @@ config FB_PM2_FIFO_DISCONNECT help Support the Permedia2 FIFO disconnect feature. +config FB_ARMCLCD + tristate "ARM PrimeCell PL110 support" + depends on ARM || ARM64 || COMPILE_TEST + depends on FB && ARM_AMBA && HAS_IOMEM + select FB_CFB_FILLRECT + select FB_CFB_COPYAREA + select FB_CFB_IMAGEBLIT + select FB_MODE_HELPERS if OF + select VIDEOMODE_HELPERS if OF + select BACKLIGHT_CLASS_DEVICE if OF + help + This framebuffer device driver is for the ARM PrimeCell PL110 + Colour LCD controller. ARM PrimeCells provide the building + blocks for System on a Chip devices. + + If you want to compile this as a module (=code which can be + inserted into and removed from the running kernel), say M + here and read <file:Documentation/kbuild/modules.rst>. The module + will be called amba-clcd. + config FB_ACORN bool "Acorn VIDC support" depends on (FB = y) && ARM && ARCH_ACORN diff --git a/drivers/video/fbdev/Makefile b/drivers/video/fbdev/Makefile index cad4fb64442a..a0705b99e643 100644 --- a/drivers/video/fbdev/Makefile +++ b/drivers/video/fbdev/Makefile @@ -75,6 +75,7 @@ obj-$(CONFIG_FB_HIT) += hitfb.o obj-$(CONFIG_FB_ATMEL) += atmel_lcdfb.o obj-$(CONFIG_FB_PVR2) += pvr2fb.o obj-$(CONFIG_FB_VOODOO1) += sstfb.o +obj-$(CONFIG_FB_ARMCLCD) += amba-clcd.o obj-$(CONFIG_FB_GOLDFISH) += goldfishfb.o obj-$(CONFIG_FB_68328) += 68328fb.o obj-$(CONFIG_FB_GBE) += gbefb.o diff --git a/drivers/video/fbdev/amba-clcd.c b/drivers/video/fbdev/amba-clcd.c new file mode 100644 index 000000000000..b7682de412d8 --- /dev/null +++ b/drivers/video/fbdev/amba-clcd.c @@ -0,0 +1,986 @@ +/* + * linux/drivers/video/amba-clcd.c + * + * Copyright (C) 2001 ARM Limited, by David A Rusling + * Updated to 2.5, Deep Blue Solutions Ltd. + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + * + * ARM PrimeCell PL110 Color LCD Controller + */ +#include <linux/amba/bus.h> +#include <linux/amba/clcd.h> +#include <linux/backlight.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/dma-mapping.h> +#include <linux/fb.h> +#include <linux/init.h> +#include <linux/ioport.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_graph.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <video/display_timing.h> +#include <video/of_display_timing.h> +#include <video/videomode.h> + +#define to_clcd(info) container_of(info, struct clcd_fb, fb) + +/* This is limited to 16 characters when displayed by X startup */ +static const char *clcd_name = "CLCD FB"; + +/* + * Unfortunately, the enable/disable functions may be called either from + * process or IRQ context, and we _need_ to delay. This is _not_ good. + */ +static inline void clcdfb_sleep(unsigned int ms) +{ + if (in_atomic()) { + mdelay(ms); + } else { + msleep(ms); + } +} + +static inline void clcdfb_set_start(struct clcd_fb *fb) +{ + unsigned long ustart = fb->fb.fix.smem_start; + unsigned long lstart; + + ustart += fb->fb.var.yoffset * fb->fb.fix.line_length; + lstart = ustart + fb->fb.var.yres * fb->fb.fix.line_length / 2; + + writel(ustart, fb->regs + CLCD_UBAS); + writel(lstart, fb->regs + CLCD_LBAS); +} + +static void clcdfb_disable(struct clcd_fb *fb) +{ + u32 val; + + if (fb->board->disable) + fb->board->disable(fb); + + if (fb->panel->backlight) { + fb->panel->backlight->props.power = FB_BLANK_POWERDOWN; + backlight_update_status(fb->panel->backlight); + } + + val = readl(fb->regs + fb->off_cntl); + if (val & CNTL_LCDPWR) { + val &= ~CNTL_LCDPWR; + writel(val, fb->regs + fb->off_cntl); + + clcdfb_sleep(20); + } + if (val & CNTL_LCDEN) { + val &= ~CNTL_LCDEN; + writel(val, fb->regs + fb->off_cntl); + } + + /* + * Disable CLCD clock source. + */ + if (fb->clk_enabled) { + fb->clk_enabled = false; + clk_disable(fb->clk); + } +} + +static void clcdfb_enable(struct clcd_fb *fb, u32 cntl) +{ + /* + * Enable the CLCD clock source. + */ + if (!fb->clk_enabled) { + fb->clk_enabled = true; + clk_enable(fb->clk); + } + + /* + * Bring up by first enabling.. + */ + cntl |= CNTL_LCDEN; + writel(cntl, fb->regs + fb->off_cntl); + + clcdfb_sleep(20); + + /* + * and now apply power. + */ + cntl |= CNTL_LCDPWR; + writel(cntl, fb->regs + fb->off_cntl); + + /* + * Turn on backlight + */ + if (fb->panel->backlight) { + fb->panel->backlight->props.power = FB_BLANK_UNBLANK; + backlight_update_status(fb->panel->backlight); + } + + /* + * finally, enable the interface. + */ + if (fb->board->enable) + fb->board->enable(fb); +} + +static int +clcdfb_set_bitfields(struct clcd_fb *fb, struct fb_var_screeninfo *var) +{ + u32 caps; + int ret = 0; + + if (fb->panel->caps && fb->board->caps) + caps = fb->panel->caps & fb->board->caps; + else { + /* Old way of specifying what can be used */ + caps = fb->panel->cntl & CNTL_BGR ? + CLCD_CAP_BGR : CLCD_CAP_RGB; + /* But mask out 444 modes as they weren't supported */ + caps &= ~CLCD_CAP_444; + } + + /* Only TFT panels can do RGB888/BGR888 */ + if (!(fb->panel->cntl & CNTL_LCDTFT)) + caps &= ~CLCD_CAP_888; + + memset(&var->transp, 0, sizeof(var->transp)); + + var->red.msb_right = 0; + var->green.msb_right = 0; + var->blue.msb_right = 0; + + switch (var->bits_per_pixel) { + case 1: + case 2: + case 4: + case 8: + /* If we can't do 5551, reject */ + caps &= CLCD_CAP_5551; + if (!caps) { + ret = -EINVAL; + break; + } + + var->red.length = var->bits_per_pixel; + var->red.offset = 0; + var->green.length = var->bits_per_pixel; + var->green.offset = 0; + var->blue.length = var->bits_per_pixel; + var->blue.offset = 0; + break; + + case 16: + /* If we can't do 444, 5551 or 565, reject */ + if (!(caps & (CLCD_CAP_444 | CLCD_CAP_5551 | CLCD_CAP_565))) { + ret = -EINVAL; + break; + } + + /* + * Green length can be 4, 5 or 6 depending whether + * we're operating in 444, 5551 or 565 mode. + */ + if (var->green.length == 4 && caps & CLCD_CAP_444) + caps &= CLCD_CAP_444; + if (var->green.length == 5 && caps & CLCD_CAP_5551) + caps &= CLCD_CAP_5551; + else if (var->green.length == 6 && caps & CLCD_CAP_565) + caps &= CLCD_CAP_565; + else { + /* + * PL110 officially only supports RGB555, + * but may be wired up to allow RGB565. + */ + if (caps & CLCD_CAP_565) { + var->green.length = 6; + caps &= CLCD_CAP_565; + } else if (caps & CLCD_CAP_5551) { + var->green.length = 5; + caps &= CLCD_CAP_5551; + } else { + var->green.length = 4; + caps &= CLCD_CAP_444; + } + } + + if (var->green.length >= 5) { + var->red.length = 5; + var->blue.length = 5; + } else { + var->red.length = 4; + var->blue.length = 4; + } + break; + case 32: + /* If we can't do 888, reject */ + caps &= CLCD_CAP_888; + if (!caps) { + ret = -EINVAL; + break; + } + + var->red.length = 8; + var->green.length = 8; + var->blue.length = 8; + break; + default: + ret = -EINVAL; + break; + } + + /* + * >= 16bpp displays have separate colour component bitfields + * encoded in the pixel data. Calculate their position from + * the bitfield length defined above. + */ + if (ret == 0 && var->bits_per_pixel >= 16) { + bool bgr, rgb; + + bgr = caps & CLCD_CAP_BGR && var->blue.offset == 0; + rgb = caps & CLCD_CAP_RGB && var->red.offset == 0; + + if (!bgr && !rgb) + /* + * The requested format was not possible, try just + * our capabilities. One of BGR or RGB must be + * supported. + */ + bgr = caps & CLCD_CAP_BGR; + + if (bgr) { + var->blue.offset = 0; + var->green.offset = var->blue.offset + var->blue.length; + var->red.offset = var->green.offset + var->green.length; + } else { + var->red.offset = 0; + var->green.offset = var->red.offset + var->red.length; + var->blue.offset = var->green.offset + var->green.length; + } + } + + return ret; +} + +static int clcdfb_check_var(struct fb_var_screeninfo *var, struct fb_info *info) +{ + struct clcd_fb *fb = to_clcd(info); + int ret = -EINVAL; + + if (fb->board->check) + ret = fb->board->check(fb, var); + + if (ret == 0 && + var->xres_virtual * var->bits_per_pixel / 8 * + var->yres_virtual > fb->fb.fix.smem_len) + ret = -EINVAL; + + if (ret == 0) + ret = clcdfb_set_bitfields(fb, var); + + return ret; +} + +static int clcdfb_set_par(struct fb_info *info) +{ + struct clcd_fb *fb = to_clcd(info); + struct clcd_regs regs; + + fb->fb.fix.line_length = fb->fb.var.xres_virtual * + fb->fb.var.bits_per_pixel / 8; + + if (fb->fb.var.bits_per_pixel <= 8) + fb->fb.fix.visual = FB_VISUAL_PSEUDOCOLOR; + else + fb->fb.fix.visual = FB_VISUAL_TRUECOLOR; + + fb->board->decode(fb, ®s); + + clcdfb_disable(fb); + + writel(regs.tim0, fb->regs + CLCD_TIM0); + writel(regs.tim1, fb->regs + CLCD_TIM1); + writel(regs.tim2, fb->regs + CLCD_TIM2); + writel(regs.tim3, fb->regs + CLCD_TIM3); + + clcdfb_set_start(fb); + + clk_set_rate(fb->clk, (1000000000 / regs.pixclock) * 1000); + + fb->clcd_cntl = regs.cntl; + + clcdfb_enable(fb, regs.cntl); + +#ifdef DEBUG + printk(KERN_INFO + "CLCD: Registers set to\n" + " %08x %08x %08x %08x\n" + " %08x %08x %08x %08x\n", + readl(fb->regs + CLCD_TIM0), readl(fb->regs + CLCD_TIM1), + readl(fb->regs + CLCD_TIM2), readl(fb->regs + CLCD_TIM3), + readl(fb->regs + CLCD_UBAS), readl(fb->regs + CLCD_LBAS), + readl(fb->regs + fb->off_ienb), readl(fb->regs + fb->off_cntl)); +#endif + + return 0; +} + +static inline u32 convert_bitfield(int val, struct fb_bitfield *bf) +{ + unsigned int mask = (1 << bf->length) - 1; + + return (val >> (16 - bf->length) & mask) << bf->offset; +} + +/* + * Set a single color register. The values supplied have a 16 bit + * magnitude. Return != 0 for invalid regno. + */ +static int +clcdfb_setcolreg(unsigned int regno, unsigned int red, unsigned int green, + unsigned int blue, unsigned int transp, struct fb_info *info) +{ + struct clcd_fb *fb = to_clcd(info); + + if (regno < 16) + fb->cmap[regno] = convert_bitfield(transp, &fb->fb.var.transp) | + convert_bitfield(blue, &fb->fb.var.blue) | + convert_bitfield(green, &fb->fb.var.green) | + convert_bitfield(red, &fb->fb.var.red); + + if (fb->fb.fix.visual == FB_VISUAL_PSEUDOCOLOR && regno < 256) { + int hw_reg = CLCD_PALETTE + ((regno * 2) & ~3); + u32 val, mask, newval; + + newval = (red >> 11) & 0x001f; + newval |= (green >> 6) & 0x03e0; + newval |= (blue >> 1) & 0x7c00; + + /* + * 3.2.11: if we're configured for big endian + * byte order, the palette entries are swapped. + */ + if (fb->clcd_cntl & CNTL_BEBO) + regno ^= 1; + + if (regno & 1) { + newval <<= 16; + mask = 0x0000ffff; + } else { + mask = 0xffff0000; + } + + val = readl(fb->regs + hw_reg) & mask; + writel(val | newval, fb->regs + hw_reg); + } + + return regno > 255; +} + +/* + * Blank the screen if blank_mode != 0, else unblank. If blank == NULL + * then the caller blanks by setting the CLUT (Color Look Up Table) to all + * black. Return 0 if blanking succeeded, != 0 if un-/blanking failed due + * to e.g. a video mode which doesn't support it. Implements VESA suspend + * and powerdown modes on hardware that supports disabling hsync/vsync: + * blank_mode == 2: suspend vsync + * blank_mode == 3: suspend hsync + * blank_mode == 4: powerdown + */ +static int clcdfb_blank(int blank_mode, struct fb_info *info) +{ + struct clcd_fb *fb = to_clcd(info); + + if (blank_mode != 0) { + clcdfb_disable(fb); + } else { + clcdfb_enable(fb, fb->clcd_cntl); + } + return 0; +} + +static int clcdfb_mmap(struct fb_info *info, + struct vm_area_struct *vma) +{ + struct clcd_fb *fb = to_clcd(info); + unsigned long len, off = vma->vm_pgoff << PAGE_SHIFT; + int ret = -EINVAL; + + len = info->fix.smem_len; + + if (off <= len && vma->vm_end - vma->vm_start <= len - off && + fb->board->mmap) + ret = fb->board->mmap(fb, vma); + + return ret; +} + +static const struct fb_ops clcdfb_ops = { + .owner = THIS_MODULE, + .fb_check_var = clcdfb_check_var, + .fb_set_par = clcdfb_set_par, + .fb_setcolreg = clcdfb_setcolreg, + .fb_blank = clcdfb_blank, + .fb_fillrect = cfb_fillrect, + .fb_copyarea = cfb_copyarea, + .fb_imageblit = cfb_imageblit, + .fb_mmap = clcdfb_mmap, +}; + +static int clcdfb_register(struct clcd_fb *fb) +{ + int ret; + + /* + * ARM PL111 always has IENB at 0x1c; it's only PL110 + * which is reversed on some platforms. + */ + if (amba_manf(fb->dev) == 0x41 && amba_part(fb->dev) == 0x111) { + fb->off_ienb = CLCD_PL111_IENB; + fb->off_cntl = CLCD_PL111_CNTL; + } else { + fb->off_ienb = CLCD_PL110_IENB; + fb->off_cntl = CLCD_PL110_CNTL; + } + + fb->clk = clk_get(&fb->dev->dev, NULL); + if (IS_ERR(fb->clk)) { + ret = PTR_ERR(fb->clk); + goto out; + } + + ret = clk_prepare(fb->clk); + if (ret) + goto free_clk; + + fb->fb.device = &fb->dev->dev; + + fb->fb.fix.mmio_start = fb->dev->res.start; + fb->fb.fix.mmio_len = resource_size(&fb->dev->res); + + fb->regs = ioremap(fb->fb.fix.mmio_start, fb->fb.fix.mmio_len); + if (!fb->regs) { + printk(KERN_ERR "CLCD: unable to remap registers\n"); + ret = -ENOMEM; + goto clk_unprep; + } + + fb->fb.fbops = &clcdfb_ops; + fb->fb.flags = FBINFO_FLAG_DEFAULT; + fb->fb.pseudo_palette = fb->cmap; + + strncpy(fb->fb.fix.id, clcd_name, sizeof(fb->fb.fix.id)); + fb->fb.fix.type = FB_TYPE_PACKED_PIXELS; + fb->fb.fix.type_aux = 0; + fb->fb.fix.xpanstep = 0; + fb->fb.fix.ypanstep = 0; + fb->fb.fix.ywrapstep = 0; + fb->fb.fix.accel = FB_ACCEL_NONE; + + fb->fb.var.xres = fb->panel->mode.xres; + fb->fb.var.yres = fb->panel->mode.yres; + fb->fb.var.xres_virtual = fb->panel->mode.xres; + fb->fb.var.yres_virtual = fb->panel->mode.yres; + fb->fb.var.bits_per_pixel = fb->panel->bpp; + fb->fb.var.grayscale = fb->panel->grayscale; + fb->fb.var.pixclock = fb->panel->mode.pixclock; + fb->fb.var.left_margin = fb->panel->mode.left_margin; + fb->fb.var.right_margin = fb->panel->mode.right_margin; + fb->fb.var.upper_margin = fb->panel->mode.upper_margin; + fb->fb.var.lower_margin = fb->panel->mode.lower_margin; + fb->fb.var.hsync_len = fb->panel->mode.hsync_len; + fb->fb.var.vsync_len = fb->panel->mode.vsync_len; + fb->fb.var.sync = fb->panel->mode.sync; + fb->fb.var.vmode = fb->panel->mode.vmode; + fb->fb.var.activate = FB_ACTIVATE_NOW; + fb->fb.var.nonstd = 0; + fb->fb.var.height = fb->panel->height; + fb->fb.var.width = fb->panel->width; + fb->fb.var.accel_flags = 0; + + fb->fb.monspecs.hfmin = 0; + fb->fb.monspecs.hfmax = 100000; + fb->fb.monspecs.vfmin = 0; + fb->fb.monspecs.vfmax = 400; + fb->fb.monspecs.dclkmin = 1000000; + fb->fb.monspecs.dclkmax = 100000000; + + /* + * Make sure that the bitfields are set appropriately. + */ + clcdfb_set_bitfields(fb, &fb->fb.var); + + /* + * Allocate colourmap. + */ + ret = fb_alloc_cmap(&fb->fb.cmap, 256, 0); + if (ret) + goto unmap; + + /* + * Ensure interrupts are disabled. + */ + writel(0, fb->regs + fb->off_ienb); + + fb_set_var(&fb->fb, &fb->fb.var); + + dev_info(&fb->dev->dev, "%s hardware, %s display\n", + fb->board->name, fb->panel->mode.name); + + ret = register_framebuffer(&fb->fb); + if (ret == 0) + goto out; + + printk(KERN_ERR "CLCD: cannot register framebuffer (%d)\n", ret); + + fb_dealloc_cmap(&fb->fb.cmap); + unmap: + iounmap(fb->regs); + clk_unprep: + clk_unprepare(fb->clk); + free_clk: + clk_put(fb->clk); + out: + return ret; +} + +#ifdef CONFIG_OF +static int clcdfb_of_get_dpi_panel_mode(struct device_node *node, + struct clcd_panel *clcd_panel) +{ + int err; + struct display_timing timing; + struct videomode video; + + err = of_get_display_timing(node, "panel-timing", &timing); + if (err) { + pr_err("%pOF: problems parsing panel-timing (%d)\n", node, err); + return err; + } + + videomode_from_timing(&timing, &video); + + err = fb_videomode_from_videomode(&video, &clcd_panel->mode); + if (err) + return err; + + /* Set up some inversion flags */ + if (timing.flags & DISPLAY_FLAGS_PIXDATA_NEGEDGE) + clcd_panel->tim2 |= TIM2_IPC; + else if (!(timing.flags & DISPLAY_FLAGS_PIXDATA_POSEDGE)) + /* + * To preserve backwards compatibility, the IPC (inverted + * pixel clock) flag needs to be set on any display that + * doesn't explicitly specify that the pixel clock is + * active on the negative or positive edge. + */ + clcd_panel->tim2 |= TIM2_IPC; + + if (timing.flags & DISPLAY_FLAGS_HSYNC_LOW) + clcd_panel->tim2 |= TIM2_IHS; + + if (timing.flags & DISPLAY_FLAGS_VSYNC_LOW) + clcd_panel->tim2 |= TIM2_IVS; + + if (timing.flags & DISPLAY_FLAGS_DE_LOW) + clcd_panel->tim2 |= TIM2_IOE; + + return 0; +} + +static int clcdfb_snprintf_mode(char *buf, int size, struct fb_videomode *mode) +{ + return snprintf(buf, size, "%ux%u@%u", mode->xres, mode->yres, + mode->refresh); +} + +static int clcdfb_of_get_backlight(struct device *dev, + struct clcd_panel *clcd_panel) +{ + struct backlight_device *backlight; + + /* Look up the optional backlight device */ + backlight = devm_of_find_backlight(dev); + if (IS_ERR(backlight)) + return PTR_ERR(backlight); + + clcd_panel->backlight = backlight; + return 0; +} + +static int clcdfb_of_get_mode(struct device *dev, struct device_node *panel, + struct clcd_panel *clcd_panel) +{ + int err; + struct fb_videomode *mode; + char *name; + int len; + + /* Only directly connected DPI panels supported for now */ + if (of_device_is_compatible(panel, "panel-dpi")) + err = clcdfb_of_get_dpi_panel_mode(panel, clcd_panel); + else + err = -ENOENT; + if (err) + return err; + mode = &clcd_panel->mode; + + len = clcdfb_snprintf_mode(NULL, 0, mode); + name = devm_kzalloc(dev, len + 1, GFP_KERNEL); + if (!name) + return -ENOMEM; + + clcdfb_snprintf_mode(name, len + 1, mode); + mode->name = name; + + return 0; +} + +static int clcdfb_of_init_tft_panel(struct clcd_fb *fb, u32 r0, u32 g0, u32 b0) +{ + static struct { + unsigned int part; + u32 r0, g0, b0; + u32 caps; + } panels[] = { + { 0x110, 1, 7, 13, CLCD_CAP_5551 }, + { 0x110, 0, 8, 16, CLCD_CAP_888 }, + { 0x110, 16, 8, 0, CLCD_CAP_888 }, + { 0x111, 4, 14, 20, CLCD_CAP_444 }, + { 0x111, 3, 11, 19, CLCD_CAP_444 | CLCD_CAP_5551 }, + { 0x111, 3, 10, 19, CLCD_CAP_444 | CLCD_CAP_5551 | + CLCD_CAP_565 }, + { 0x111, 0, 8, 16, CLCD_CAP_444 | CLCD_CAP_5551 | + CLCD_CAP_565 | CLCD_CAP_888 }, + }; + int i; + + /* Bypass pixel clock divider */ + fb->panel->tim2 |= TIM2_BCD; + + /* TFT display, vert. comp. interrupt at the start of the back porch */ + fb->panel->cntl |= CNTL_LCDTFT | CNTL_LCDVCOMP(1); + + fb->panel->caps = 0; + + /* Match the setup with known variants */ + for (i = 0; i < ARRAY_SIZE(panels) && !fb->panel->caps; i++) { + if (amba_part(fb->dev) != panels[i].part) + continue; + if (g0 != panels[i].g0) + continue; + if (r0 == panels[i].r0 && b0 == panels[i].b0) + fb->panel->caps = panels[i].caps; + } + + /* + * If we actually physically connected the R lines to B and + * vice versa + */ + if (r0 != 0 && b0 == 0) + fb->panel->bgr_connection = true; + + return fb->panel->caps ? 0 : -EINVAL; +} + +static int clcdfb_of_init_display(struct clcd_fb *fb) +{ + struct device_node *endpoint, *panel; + int err; + unsigned int bpp; + u32 max_bandwidth; + u32 tft_r0b0g0[3]; + + fb->panel = devm_kzalloc(&fb->dev->dev, sizeof(*fb->panel), GFP_KERNEL); + if (!fb->panel) + return -ENOMEM; + + /* + * Fetch the panel endpoint. + */ + endpoint = of_graph_get_next_endpoint(fb->dev->dev.of_node, NULL); + if (!endpoint) + return -ENODEV; + + panel = of_graph_get_remote_port_parent(endpoint); + if (!panel) + return -ENODEV; + + err = clcdfb_of_get_backlight(&fb->dev->dev, fb->panel); + if (err) + return err; + + err = clcdfb_of_get_mode(&fb->dev->dev, panel, fb->panel); + if (err) + return err; + + err = of_property_read_u32(fb->dev->dev.of_node, "max-memory-bandwidth", + &max_bandwidth); + if (!err) { + /* + * max_bandwidth is in bytes per second and pixclock in + * pico-seconds, so the maximum allowed bits per pixel is + * 8 * max_bandwidth / (PICOS2KHZ(pixclock) * 1000) + * Rearrange this calculation to avoid overflow and then ensure + * result is a valid format. + */ + bpp = max_bandwidth / (1000 / 8) + / PICOS2KHZ(fb->panel->mode.pixclock); + bpp = rounddown_pow_of_two(bpp); + if (bpp > 32) + bpp = 32; + } else + bpp = 32; + fb->panel->bpp = bpp; + +#ifdef CONFIG_CPU_BIG_ENDIAN + fb->panel->cntl |= CNTL_BEBO; +#endif + fb->panel->width = -1; + fb->panel->height = -1; + + if (of_property_read_u32_array(endpoint, + "arm,pl11x,tft-r0g0b0-pads", + tft_r0b0g0, ARRAY_SIZE(tft_r0b0g0)) != 0) + return -ENOENT; + + return clcdfb_of_init_tft_panel(fb, tft_r0b0g0[0], + tft_r0b0g0[1], tft_r0b0g0[2]); +} + +static int clcdfb_of_vram_setup(struct clcd_fb *fb) +{ + int err; + struct device_node *memory; + u64 size; + + err = clcdfb_of_init_display(fb); + if (err) + return err; + + memory = of_parse_phandle(fb->dev->dev.of_node, "memory-region", 0); + if (!memory) + return -ENODEV; + + fb->fb.screen_base = of_iomap(memory, 0); + if (!fb->fb.screen_base) + return -ENOMEM; + + fb->fb.fix.smem_start = of_translate_address(memory, + of_get_address(memory, 0, &size, NULL)); + fb->fb.fix.smem_len = size; + + return 0; +} + +static int clcdfb_of_vram_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) +{ + unsigned long off, user_size, kernel_size; + + + off = vma->vm_pgoff << PAGE_SHIFT; + user_size = vma->vm_end - vma->vm_start; + kernel_size = fb->fb.fix.smem_len; + + if (off >= kernel_size || user_size > (kernel_size - off)) + return -ENXIO; + + return remap_pfn_range(vma, vma->vm_start, + __phys_to_pfn(fb->fb.fix.smem_start) + vma->vm_pgoff, + user_size, + pgprot_writecombine(vma->vm_page_prot)); +} + +static void clcdfb_of_vram_remove(struct clcd_fb *fb) +{ + iounmap(fb->fb.screen_base); +} + +static int clcdfb_of_dma_setup(struct clcd_fb *fb) +{ + unsigned long framesize; + dma_addr_t dma; + int err; + + err = clcdfb_of_init_display(fb); + if (err) + return err; + + framesize = PAGE_ALIGN(fb->panel->mode.xres * fb->panel->mode.yres * + fb->panel->bpp / 8); + fb->fb.screen_base = dma_alloc_coherent(&fb->dev->dev, framesize, + &dma, GFP_KERNEL); + if (!fb->fb.screen_base) + return -ENOMEM; + + fb->fb.fix.smem_start = dma; + fb->fb.fix.smem_len = framesize; + + return 0; +} + +static int clcdfb_of_dma_mmap(struct clcd_fb *fb, struct vm_area_struct *vma) +{ + return dma_mmap_wc(&fb->dev->dev, vma, fb->fb.screen_base, + fb->fb.fix.smem_start, fb->fb.fix.smem_len); +} + +static void clcdfb_of_dma_remove(struct clcd_fb *fb) +{ + dma_free_coherent(&fb->dev->dev, fb->fb.fix.smem_len, + fb->fb.screen_base, fb->fb.fix.smem_start); +} + +static struct clcd_board *clcdfb_of_get_board(struct amba_device *dev) +{ + struct clcd_board *board = devm_kzalloc(&dev->dev, sizeof(*board), + GFP_KERNEL); + struct device_node *node = dev->dev.of_node; + + if (!board) + return NULL; + + board->name = of_node_full_name(node); + board->caps = CLCD_CAP_ALL; + board->check = clcdfb_check; + board->decode = clcdfb_decode; + if (of_find_property(node, "memory-region", NULL)) { + board->setup = clcdfb_of_vram_setup; + board->mmap = clcdfb_of_vram_mmap; + board->remove = clcdfb_of_vram_remove; + } else { + board->setup = clcdfb_of_dma_setup; + board->mmap = clcdfb_of_dma_mmap; + board->remove = clcdfb_of_dma_remove; + } + + return board; +} +#else +static struct clcd_board *clcdfb_of_get_board(struct amba_device *dev) +{ + return NULL; +} +#endif + +static int clcdfb_probe(struct amba_device *dev, const struct amba_id *id) +{ + struct clcd_board *board = dev_get_platdata(&dev->dev); + struct clcd_fb *fb; + int ret; + + if (!board) + board = clcdfb_of_get_board(dev); + + if (!board) + return -EINVAL; + + ret = dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32)); + if (ret) + goto out; + + ret = amba_request_regions(dev, NULL); + if (ret) { + printk(KERN_ERR "CLCD: unable to reserve regs region\n"); + goto out; + } + + fb = kzalloc(sizeof(*fb), GFP_KERNEL); + if (!fb) { + ret = -ENOMEM; + goto free_region; + } + + fb->dev = dev; + fb->board = board; + + dev_info(&fb->dev->dev, "PL%03x designer %02x rev%u at 0x%08llx\n", + amba_part(dev), amba_manf(dev), amba_rev(dev), + (unsigned long long)dev->res.start); + + ret = fb->board->setup(fb); + if (ret) + goto free_fb; + + ret = clcdfb_register(fb); + if (ret == 0) { + amba_set_drvdata(dev, fb); + goto out; + } + + fb->board->remove(fb); + free_fb: + kfree(fb); + free_region: + amba_release_regions(dev); + out: + return ret; +} + +static int clcdfb_remove(struct amba_device *dev) +{ + struct clcd_fb *fb = amba_get_drvdata(dev); + + clcdfb_disable(fb); + unregister_framebuffer(&fb->fb); + if (fb->fb.cmap.len) + fb_dealloc_cmap(&fb->fb.cmap); + iounmap(fb->regs); + clk_unprepare(fb->clk); + clk_put(fb->clk); + + fb->board->remove(fb); + + kfree(fb); + + amba_release_regions(dev); + + return 0; +} + +static const struct amba_id clcdfb_id_table[] = { + { + .id = 0x00041110, + .mask = 0x000ffffe, + }, + { 0, 0 }, +}; + +MODULE_DEVICE_TABLE(amba, clcdfb_id_table); + +static struct amba_driver clcd_driver = { + .drv = { + .name = "clcd-pl11x", + }, + .probe = clcdfb_probe, + .remove = clcdfb_remove, + .id_table = clcdfb_id_table, +}; + +static int __init amba_clcdfb_init(void) +{ + if (fb_get_options("ambafb", NULL)) + return -ENODEV; + + return amba_driver_register(&clcd_driver); +} + +module_init(amba_clcdfb_init); + +static void __exit amba_clcdfb_exit(void) +{ + amba_driver_unregister(&clcd_driver); +} + +module_exit(amba_clcdfb_exit); + +MODULE_DESCRIPTION("ARM PrimeCell PL110 CLCD core driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 41f3fa3db6d4..8c7bd0a29eaa 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2299,6 +2299,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) if (font->width <= 8) { j = vc->vc_font.height; + if (font->charcount * j > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 32 - j); @@ -2307,6 +2310,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) } } else if (font->width <= 16) { j = vc->vc_font.height * 2; + if (font->charcount * j > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 64 - j); @@ -2314,6 +2320,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) fontdata += j; } } else if (font->width <= 24) { + if (font->charcount * (vc->vc_font.height * sizeof(u32)) > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { for (j = 0; j < vc->vc_font.height; j++) { *data++ = fontdata[0]; @@ -2326,6 +2335,9 @@ static int fbcon_get_font(struct vc_data *vc, struct console_font *font) } } else { j = vc->vc_font.height * 4; + if (font->charcount * j > FNTSIZE(fontdata)) + return -EINVAL; + for (i = 0; i < font->charcount; i++) { memcpy(data, fontdata, j); memset(data + j, 0, 128 - j); diff --git a/drivers/video/fbdev/core/fbcon.h b/drivers/video/fbdev/core/fbcon.h index 78bb14c03643..9315b360c898 100644 --- a/drivers/video/fbdev/core/fbcon.h +++ b/drivers/video/fbdev/core/fbcon.h @@ -152,13 +152,6 @@ static inline int attr_col_ec(int shift, struct vc_data *vc, #define attr_bgcol_ec(bgshift, vc, info) attr_col_ec(bgshift, vc, info, 0) #define attr_fgcol_ec(fgshift, vc, info) attr_col_ec(fgshift, vc, info, 1) -/* Font */ -#define REFCOUNT(fd) (((int *)(fd))[-1]) -#define FNTSIZE(fd) (((int *)(fd))[-2]) -#define FNTCHARCNT(fd) (((int *)(fd))[-3]) -#define FNTSUM(fd) (((int *)(fd))[-4]) -#define FONT_EXTRA_WORDS 4 - /* * Scroll Method */ diff --git a/drivers/video/fbdev/core/fbcon_rotate.c b/drivers/video/fbdev/core/fbcon_rotate.c index c0d445294aa7..ac72d4f85f7d 100644 --- a/drivers/video/fbdev/core/fbcon_rotate.c +++ b/drivers/video/fbdev/core/fbcon_rotate.c @@ -14,6 +14,7 @@ #include <linux/fb.h> #include <linux/vt_kern.h> #include <linux/console.h> +#include <linux/font.h> #include <asm/types.h> #include "fbcon.h" #include "fbcon_rotate.h" diff --git a/drivers/video/fbdev/core/tileblit.c b/drivers/video/fbdev/core/tileblit.c index 31b85b71cc37..628fe5e010c0 100644 --- a/drivers/video/fbdev/core/tileblit.c +++ b/drivers/video/fbdev/core/tileblit.c @@ -13,6 +13,7 @@ #include <linux/fb.h> #include <linux/vt_kern.h> #include <linux/console.h> +#include <linux/font.h> #include <asm/types.h> #include "fbcon.h" diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 90b8f56fbadb..6f02c18fa65c 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -92,6 +92,8 @@ static bool (*pirq_needs_eoi)(unsigned irq); /* Xen will never allocate port zero for any purpose. */ #define VALID_EVTCHN(chn) ((chn) != 0) +static struct irq_info *legacy_info_ptrs[NR_IRQS_LEGACY]; + static struct irq_chip xen_dynamic_chip; static struct irq_chip xen_percpu_chip; static struct irq_chip xen_pirq_chip; @@ -156,7 +158,18 @@ int get_evtchn_to_irq(evtchn_port_t evtchn) /* Get info for IRQ */ struct irq_info *info_for_irq(unsigned irq) { - return irq_get_chip_data(irq); + if (irq < nr_legacy_irqs()) + return legacy_info_ptrs[irq]; + else + return irq_get_chip_data(irq); +} + +static void set_info_for_irq(unsigned int irq, struct irq_info *info) +{ + if (irq < nr_legacy_irqs()) + legacy_info_ptrs[irq] = info; + else + irq_set_chip_data(irq, info); } /* Constructors for packed IRQ information. */ @@ -377,7 +390,7 @@ static void xen_irq_init(unsigned irq) info->type = IRQT_UNBOUND; info->refcnt = -1; - irq_set_chip_data(irq, info); + set_info_for_irq(irq, info); list_add_tail(&info->list, &xen_irq_list_head); } @@ -426,14 +439,14 @@ static int __must_check xen_allocate_irq_gsi(unsigned gsi) static void xen_free_irq(unsigned irq) { - struct irq_info *info = irq_get_chip_data(irq); + struct irq_info *info = info_for_irq(irq); if (WARN_ON(!info)) return; list_del(&info->list); - irq_set_chip_data(irq, NULL); + set_info_for_irq(irq, NULL); WARN_ON(info->refcnt > 0); @@ -603,7 +616,7 @@ EXPORT_SYMBOL_GPL(xen_irq_from_gsi); static void __unbind_from_irq(unsigned int irq) { evtchn_port_t evtchn = evtchn_from_irq(irq); - struct irq_info *info = irq_get_chip_data(irq); + struct irq_info *info = info_for_irq(irq); if (info->refcnt > 0) { info->refcnt--; @@ -1108,7 +1121,7 @@ int bind_ipi_to_irqhandler(enum ipi_vector ipi, void unbind_from_irqhandler(unsigned int irq, void *dev_id) { - struct irq_info *info = irq_get_chip_data(irq); + struct irq_info *info = info_for_irq(irq); if (WARN_ON(!info)) return; @@ -1142,7 +1155,7 @@ int evtchn_make_refcounted(evtchn_port_t evtchn) if (irq == -1) return -ENOENT; - info = irq_get_chip_data(irq); + info = info_for_irq(irq); if (!info) return -ENOENT; @@ -1170,7 +1183,7 @@ int evtchn_get(evtchn_port_t evtchn) if (irq == -1) goto done; - info = irq_get_chip_data(irq); + info = info_for_irq(irq); if (!info) goto done; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index 1d13d2e882ad..0fe8844b4bee 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -810,14 +810,32 @@ void afs_evict_inode(struct inode *inode) static void afs_setattr_success(struct afs_operation *op) { - struct inode *inode = &op->file[0].vnode->vfs_inode; + struct afs_vnode_param *vp = &op->file[0]; + struct inode *inode = &vp->vnode->vfs_inode; + loff_t old_i_size = i_size_read(inode); + + op->setattr.old_i_size = old_i_size; + afs_vnode_commit_status(op, vp); + /* inode->i_size has now been changed. */ + + if (op->setattr.attr->ia_valid & ATTR_SIZE) { + loff_t size = op->setattr.attr->ia_size; + if (size > old_i_size) + pagecache_isize_extended(inode, old_i_size, size); + } +} + +static void afs_setattr_edit_file(struct afs_operation *op) +{ + struct afs_vnode_param *vp = &op->file[0]; + struct inode *inode = &vp->vnode->vfs_inode; - afs_vnode_commit_status(op, &op->file[0]); if (op->setattr.attr->ia_valid & ATTR_SIZE) { - loff_t i_size = inode->i_size, size = op->setattr.attr->ia_size; - if (size > i_size) - pagecache_isize_extended(inode, i_size, size); - truncate_pagecache(inode, size); + loff_t size = op->setattr.attr->ia_size; + loff_t i_size = op->setattr.old_i_size; + + if (size < i_size) + truncate_pagecache(inode, size); } } @@ -825,6 +843,7 @@ static const struct afs_operation_ops afs_setattr_operation = { .issue_afs_rpc = afs_fs_setattr, .issue_yfs_rpc = yfs_fs_setattr, .success = afs_setattr_success, + .edit_dir = afs_setattr_edit_file, }; /* @@ -863,11 +882,16 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) if (S_ISREG(vnode->vfs_inode.i_mode)) filemap_write_and_wait(vnode->vfs_inode.i_mapping); + /* Prevent any new writebacks from starting whilst we do this. */ + down_write(&vnode->validate_lock); + op = afs_alloc_operation(((attr->ia_valid & ATTR_FILE) ? afs_file_key(attr->ia_file) : NULL), vnode->volume); - if (IS_ERR(op)) - return PTR_ERR(op); + if (IS_ERR(op)) { + ret = PTR_ERR(op); + goto out_unlock; + } afs_op_set_vnode(op, 0, vnode); op->setattr.attr = attr; @@ -880,5 +904,10 @@ int afs_setattr(struct dentry *dentry, struct iattr *attr) op->file[0].update_ctime = 1; op->ops = &afs_setattr_operation; - return afs_do_sync_operation(op); + ret = afs_do_sync_operation(op); + +out_unlock: + up_write(&vnode->validate_lock); + _leave(" = %d", ret); + return ret; } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 18042b7dab6a..e5f0446f27e5 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -812,6 +812,7 @@ struct afs_operation { } store; struct { struct iattr *attr; + loff_t old_i_size; } setattr; struct afs_acl *acl; struct yfs_acl *yacl; diff --git a/fs/afs/write.c b/fs/afs/write.c index 4b2265cb1891..da12abd6db21 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -738,11 +738,21 @@ static int afs_writepages_region(struct address_space *mapping, int afs_writepages(struct address_space *mapping, struct writeback_control *wbc) { + struct afs_vnode *vnode = AFS_FS_I(mapping->host); pgoff_t start, end, next; int ret; _enter(""); + /* We have to be careful as we can end up racing with setattr() + * truncating the pagecache since the caller doesn't take a lock here + * to prevent it. + */ + if (wbc->sync_mode == WB_SYNC_ALL) + down_read(&vnode->validate_lock); + else if (!down_read_trylock(&vnode->validate_lock)) + return 0; + if (wbc->range_cyclic) { start = mapping->writeback_index; end = -1; @@ -762,6 +772,7 @@ int afs_writepages(struct address_space *mapping, ret = afs_writepages_region(mapping, wbc, start, end, &next); } + up_read(&vnode->validate_lock); _leave(" = %d", ret); return ret; } diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c index 74c886f7c51c..5ced859dac53 100644 --- a/fs/autofs/waitq.c +++ b/fs/autofs/waitq.c @@ -53,7 +53,7 @@ static int autofs_write(struct autofs_sb_info *sbi, mutex_lock(&sbi->pipe_mutex); while (bytes) { - wr = kernel_write(file, data, bytes, &file->f_pos); + wr = __kernel_write(file, data, bytes, NULL); if (wr <= 0) break; data += wr; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index db93909b25e0..e4a1c6afe35d 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -599,6 +599,37 @@ static void btrfs_rm_dev_replace_unblocked(struct btrfs_fs_info *fs_info) wake_up(&fs_info->dev_replace.replace_wait); } +/* + * When finishing the device replace, before swapping the source device with the + * target device we must update the chunk allocation state in the target device, + * as it is empty because replace works by directly copying the chunks and not + * through the normal chunk allocation path. + */ +static int btrfs_set_target_alloc_state(struct btrfs_device *srcdev, + struct btrfs_device *tgtdev) +{ + struct extent_state *cached_state = NULL; + u64 start = 0; + u64 found_start; + u64 found_end; + int ret = 0; + + lockdep_assert_held(&srcdev->fs_info->chunk_mutex); + + while (!find_first_extent_bit(&srcdev->alloc_state, start, + &found_start, &found_end, + CHUNK_ALLOCATED, &cached_state)) { + ret = set_extent_bits(&tgtdev->alloc_state, found_start, + found_end, CHUNK_ALLOCATED); + if (ret) + break; + start = found_end + 1; + } + + free_extent_state(cached_state); + return ret; +} + static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, int scrub_ret) { @@ -673,8 +704,14 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, dev_replace->time_stopped = ktime_get_real_seconds(); dev_replace->item_needs_writeback = 1; - /* replace old device with new one in mapping tree */ + /* + * Update allocation state in the new device and replace the old device + * with the new one in the mapping tree. + */ if (!scrub_ret) { + scrub_ret = btrfs_set_target_alloc_state(src_device, tgt_device); + if (scrub_ret) + goto error; btrfs_dev_replace_update_device_in_mapping_tree(fs_info, src_device, tgt_device); @@ -685,6 +722,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, btrfs_dev_name(src_device), src_device->devid, rcu_str_deref(tgt_device->name), scrub_ret); +error: up_write(&dev_replace->rwsem); mutex_unlock(&fs_info->chunk_mutex); mutex_unlock(&fs_info->fs_devices->device_list_mutex); @@ -745,7 +783,9 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, /* replace the sysfs entry */ btrfs_sysfs_remove_devices_dir(fs_info->fs_devices, src_device); btrfs_sysfs_update_devid(tgt_device); - btrfs_rm_dev_replace_free_srcdev(src_device); + if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &src_device->dev_state)) + btrfs_scratch_superblocks(fs_info, src_device->bdev, + src_device->name->str); /* write back the superblocks */ trans = btrfs_start_transaction(root, 0); @@ -754,6 +794,8 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); + btrfs_rm_dev_replace_free_srcdev(src_device); + return 0; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index abf86b202b43..9f72b092bc22 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -636,16 +636,15 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio, csum_tree_block(eb, result); if (memcmp_extent_buffer(eb, result, 0, csum_size)) { - u32 val; - u32 found = 0; - - memcpy(&found, result, csum_size); + u8 val[BTRFS_CSUM_SIZE] = { 0 }; read_extent_buffer(eb, &val, 0, csum_size); btrfs_warn_rl(fs_info, - "%s checksum verify failed on %llu wanted %x found %x level %d", + "%s checksum verify failed on %llu wanted " CSUM_FMT " found " CSUM_FMT " level %d", fs_info->sb->s_id, eb->start, - val, found, btrfs_header_level(eb)); + CSUM_FMT_VALUE(csum_size, val), + CSUM_FMT_VALUE(csum_size, result), + btrfs_header_level(eb)); ret = -EUCLEAN; goto err; } diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index c8df2edafd85..5be30066563c 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1170,10 +1170,12 @@ int btrfs_sysfs_remove_devices_dir(struct btrfs_fs_devices *fs_devices, disk_kobj->name); } - kobject_del(&one_device->devid_kobj); - kobject_put(&one_device->devid_kobj); + if (one_device->devid_kobj.state_initialized) { + kobject_del(&one_device->devid_kobj); + kobject_put(&one_device->devid_kobj); - wait_for_completion(&one_device->kobj_unregister); + wait_for_completion(&one_device->kobj_unregister); + } return 0; } @@ -1186,10 +1188,12 @@ int btrfs_sysfs_remove_devices_dir(struct btrfs_fs_devices *fs_devices, sysfs_remove_link(fs_devices->devices_kobj, disk_kobj->name); } - kobject_del(&one_device->devid_kobj); - kobject_put(&one_device->devid_kobj); + if (one_device->devid_kobj.state_initialized) { + kobject_del(&one_device->devid_kobj); + kobject_put(&one_device->devid_kobj); - wait_for_completion(&one_device->kobj_unregister); + wait_for_completion(&one_device->kobj_unregister); + } } return 0; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 117b43367629..1997a7d67f22 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1999,9 +1999,9 @@ static u64 btrfs_num_devices(struct btrfs_fs_info *fs_info) return num_devices; } -static void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, - struct block_device *bdev, - const char *device_path) +void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, + struct block_device *bdev, + const char *device_path) { struct btrfs_super_block *disk_super; int copy_num; @@ -2224,11 +2224,7 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev) struct btrfs_fs_info *fs_info = srcdev->fs_info; struct btrfs_fs_devices *fs_devices = srcdev->fs_devices; - if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &srcdev->dev_state)) { - /* zero out the old super if it is writable */ - btrfs_scratch_superblocks(fs_info, srcdev->bdev, - srcdev->name->str); - } + mutex_lock(&uuid_mutex); btrfs_close_bdev(srcdev); synchronize_rcu(); @@ -2258,6 +2254,7 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_device *srcdev) close_fs_devices(fs_devices); free_fs_devices(fs_devices); } + mutex_unlock(&uuid_mutex); } void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev) diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 5eea93916fbf..302c9234f7d0 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -573,6 +573,9 @@ void btrfs_set_fs_info_ptr(struct btrfs_fs_info *fs_info); void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info); bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info, struct btrfs_device *failing_dev); +void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, + struct block_device *bdev, + const char *device_path); int btrfs_bg_type_to_factor(u64 flags); const char *btrfs_bg_type_to_raid_name(u64 flags); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 32f90dc82c84..d44df8f95bcd 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -1208,7 +1208,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, rqst[1].rq_iov = si_iov; rqst[1].rq_nvec = 1; - len = sizeof(ea) + ea_name_len + ea_value_len + 1; + len = sizeof(*ea) + ea_name_len + ea_value_len + 1; ea = kzalloc(len, GFP_KERNEL); if (ea == NULL) { rc = -ENOMEM; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 8107e06d7f6f..4df61129566d 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -218,8 +218,7 @@ struct eventpoll { struct file *file; /* used to optimize loop detection check */ - struct list_head visited_list_link; - int visited; + u64 gen; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ @@ -274,6 +273,8 @@ static long max_user_watches __read_mostly; */ static DEFINE_MUTEX(epmutex); +static u64 loop_check_gen = 0; + /* Used to check for epoll file descriptor inclusion loops */ static struct nested_calls poll_loop_ncalls; @@ -283,9 +284,6 @@ static struct kmem_cache *epi_cache __read_mostly; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __read_mostly; -/* Visited nodes during ep_loop_check(), so we can unset them when we finish */ -static LIST_HEAD(visited_list); - /* * List of files with newly added links, where we may need to limit the number * of emanating paths. Protected by the epmutex. @@ -1450,7 +1448,7 @@ static int reverse_path_check(void) static int ep_create_wakeup_source(struct epitem *epi) { - const char *name; + struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { @@ -1459,8 +1457,9 @@ static int ep_create_wakeup_source(struct epitem *epi) return -ENOMEM; } - name = epi->ffd.file->f_path.dentry->d_name.name; - ws = wakeup_source_register(NULL, name); + take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); + ws = wakeup_source_register(NULL, n.name.name); + release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; @@ -1522,6 +1521,22 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, RCU_INIT_POINTER(epi->ws, NULL); } + /* Add the current item to the list of active epoll hook for this file */ + spin_lock(&tfile->f_lock); + list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); + spin_unlock(&tfile->f_lock); + + /* + * Add the current item to the RB tree. All RB tree operations are + * protected by "mtx", and ep_insert() is called with "mtx" held. + */ + ep_rbtree_insert(ep, epi); + + /* now check if we've created too many backpaths */ + error = -EINVAL; + if (full_check && reverse_path_check()) + goto error_remove_epi; + /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); @@ -1544,22 +1559,6 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, if (epi->nwait < 0) goto error_unregister; - /* Add the current item to the list of active epoll hook for this file */ - spin_lock(&tfile->f_lock); - list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links); - spin_unlock(&tfile->f_lock); - - /* - * Add the current item to the RB tree. All RB tree operations are - * protected by "mtx", and ep_insert() is called with "mtx" held. - */ - ep_rbtree_insert(ep, epi); - - /* now check if we've created too many backpaths */ - error = -EINVAL; - if (full_check && reverse_path_check()) - goto error_remove_epi; - /* We have to drop the new item inside our item list to keep track of it */ write_lock_irq(&ep->lock); @@ -1588,6 +1587,8 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, return 0; +error_unregister: + ep_unregister_pollwait(ep, epi); error_remove_epi: spin_lock(&tfile->f_lock); list_del_rcu(&epi->fllink); @@ -1595,9 +1596,6 @@ error_remove_epi: rb_erase_cached(&epi->rbn, &ep->rbr); -error_unregister: - ep_unregister_pollwait(ep, epi); - /* * We need to do this because an event could have been arrived on some * allocated wait queue. Note that we don't care about the ep->ovflist @@ -1972,13 +1970,12 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) struct epitem *epi; mutex_lock_nested(&ep->mtx, call_nests + 1); - ep->visited = 1; - list_add(&ep->visited_list_link, &visited_list); + ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { ep_tovisit = epi->ffd.file->private_data; - if (ep_tovisit->visited) + if (ep_tovisit->gen == loop_check_gen) continue; error = ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, epi->ffd.file, @@ -2019,18 +2016,8 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) */ static int ep_loop_check(struct eventpoll *ep, struct file *file) { - int ret; - struct eventpoll *ep_cur, *ep_next; - - ret = ep_call_nested(&poll_loop_ncalls, + return ep_call_nested(&poll_loop_ncalls, ep_loop_check_proc, file, ep, current); - /* clear visited list */ - list_for_each_entry_safe(ep_cur, ep_next, &visited_list, - visited_list_link) { - ep_cur->visited = 0; - list_del(&ep_cur->visited_list_link); - } - return ret; } static void clear_tfile_check_list(void) @@ -2195,11 +2182,13 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, goto error_tgt_fput; if (op == EPOLL_CTL_ADD) { if (!list_empty(&f.file->f_ep_links) || + ep->gen == loop_check_gen || is_file_epoll(tf.file)) { mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epmutex, 0, nonblock); if (error) goto error_tgt_fput; + loop_check_gen++; full_check = 1; if (is_file_epoll(tf.file)) { error = -ELOOP; @@ -2263,6 +2252,7 @@ int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, error_tgt_fput: if (full_check) { clear_tfile_check_list(); + loop_check_gen++; mutex_unlock(&epmutex); } diff --git a/fs/exfat/cache.c b/fs/exfat/cache.c index 03d0824fc368..5a2f119b7e8c 100644 --- a/fs/exfat/cache.c +++ b/fs/exfat/cache.c @@ -17,7 +17,6 @@ #include "exfat_raw.h" #include "exfat_fs.h" -#define EXFAT_CACHE_VALID 0 #define EXFAT_MAX_CACHE 16 struct exfat_cache { @@ -61,16 +60,6 @@ void exfat_cache_shutdown(void) kmem_cache_destroy(exfat_cachep); } -void exfat_cache_init_inode(struct inode *inode) -{ - struct exfat_inode_info *ei = EXFAT_I(inode); - - spin_lock_init(&ei->cache_lru_lock); - ei->nr_caches = 0; - ei->cache_valid_id = EXFAT_CACHE_VALID + 1; - INIT_LIST_HEAD(&ei->cache_lru); -} - static inline struct exfat_cache *exfat_cache_alloc(void) { return kmem_cache_alloc(exfat_cachep, GFP_NOFS); diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h index 95d717f8620c..c013fe931d9c 100644 --- a/fs/exfat/exfat_fs.h +++ b/fs/exfat/exfat_fs.h @@ -248,6 +248,8 @@ struct exfat_sb_info { struct rcu_head rcu; }; +#define EXFAT_CACHE_VALID 0 + /* * EXFAT file system inode in-memory data */ @@ -428,7 +430,6 @@ extern const struct dentry_operations exfat_utf8_dentry_ops; /* cache.c */ int exfat_cache_init(void); void exfat_cache_shutdown(void); -void exfat_cache_init_inode(struct inode *inode); void exfat_cache_inval_inode(struct inode *inode); int exfat_get_cluster(struct inode *inode, unsigned int cluster, unsigned int *fclus, unsigned int *dclus, diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c index 7f90204adef5..a6de17cac3df 100644 --- a/fs/exfat/inode.c +++ b/fs/exfat/inode.c @@ -611,8 +611,6 @@ static int exfat_fill_inode(struct inode *inode, struct exfat_dir_entry *info) ei->i_crtime = info->crtime; inode->i_atime = info->atime; - exfat_cache_init_inode(inode); - return 0; } diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c index e73f20f66cb2..c94ac239f740 100644 --- a/fs/exfat/namei.c +++ b/fs/exfat/namei.c @@ -578,7 +578,8 @@ static int exfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, i_pos = exfat_make_i_pos(&info); inode = exfat_build_inode(sb, &info, i_pos); - if (IS_ERR(inode)) + err = PTR_ERR_OR_ZERO(inode); + if (err) goto unlock; inode_inc_iversion(inode); @@ -745,10 +746,9 @@ static struct dentry *exfat_lookup(struct inode *dir, struct dentry *dentry, i_pos = exfat_make_i_pos(&info); inode = exfat_build_inode(sb, &info, i_pos); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); + err = PTR_ERR_OR_ZERO(inode); + if (err) goto unlock; - } i_mode = inode->i_mode; alias = d_find_alias(inode); @@ -890,10 +890,9 @@ static int exfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) i_pos = exfat_make_i_pos(&info); inode = exfat_build_inode(sb, &info, i_pos); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); + err = PTR_ERR_OR_ZERO(inode); + if (err) goto unlock; - } inode_inc_iversion(inode); inode->i_mtime = inode->i_atime = inode->i_ctime = diff --git a/fs/exfat/super.c b/fs/exfat/super.c index 3b6a1659892f..60b941ba557b 100644 --- a/fs/exfat/super.c +++ b/fs/exfat/super.c @@ -376,7 +376,6 @@ static int exfat_read_root(struct inode *inode) inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime = current_time(inode); exfat_truncate_atime(&inode->i_atime); - exfat_cache_init_inode(inode); return 0; } @@ -763,6 +762,10 @@ static void exfat_inode_init_once(void *foo) { struct exfat_inode_info *ei = (struct exfat_inode_info *)foo; + spin_lock_init(&ei->cache_lru_lock); + ei->nr_caches = 0; + ei->cache_valid_id = EXFAT_CACHE_VALID + 1; + INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_hash_fat); inode_init_once(&ei->vfs_inode); } diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 6611ef3269a8..43c165e796da 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3091,11 +3091,10 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) ssize_t ret = 0; struct file *file = iocb->ki_filp; struct fuse_file *ff = file->private_data; - bool async_dio = ff->fc->async_dio; loff_t pos = 0; struct inode *inode; loff_t i_size; - size_t count = iov_iter_count(iter); + size_t count = iov_iter_count(iter), shortened = 0; loff_t offset = iocb->ki_pos; struct fuse_io_priv *io; @@ -3103,17 +3102,9 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) inode = file->f_mapping->host; i_size = i_size_read(inode); - if ((iov_iter_rw(iter) == READ) && (offset > i_size)) + if ((iov_iter_rw(iter) == READ) && (offset >= i_size)) return 0; - /* optimization for short read */ - if (async_dio && iov_iter_rw(iter) != WRITE && offset + count > i_size) { - if (offset >= i_size) - return 0; - iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset)); - count = iov_iter_count(iter); - } - io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL); if (!io) return -ENOMEM; @@ -3129,15 +3120,22 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) * By default, we want to optimize all I/Os with async request * submission to the client filesystem if supported. */ - io->async = async_dio; + io->async = ff->fc->async_dio; io->iocb = iocb; io->blocking = is_sync_kiocb(iocb); + /* optimization for short read */ + if (io->async && !io->write && offset + count > i_size) { + iov_iter_truncate(iter, fuse_round_up(ff->fc, i_size - offset)); + shortened = count - iov_iter_count(iter); + count -= shortened; + } + /* * We cannot asynchronously extend the size of a file. * In such case the aio will behave exactly like sync io. */ - if ((offset + count > i_size) && iov_iter_rw(iter) == WRITE) + if ((offset + count > i_size) && io->write) io->blocking = true; if (io->async && io->blocking) { @@ -3155,6 +3153,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } else { ret = __fuse_direct_read(io, iter, &pos); } + iov_iter_reexpand(iter, iov_iter_count(iter) + shortened); if (io->async) { bool blocking = io->blocking; diff --git a/fs/io_uring.c b/fs/io_uring.c index 3790c7fe9fee..aae0ef2ec34d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1753,6 +1753,9 @@ static int io_req_task_work_add(struct io_kiocb *req, struct callback_head *cb, struct io_ring_ctx *ctx = req->ctx; int ret, notify; + if (tsk->flags & PF_EXITING) + return -ESRCH; + /* * SQPOLL kernel thread doesn't need notification, just a wakeup. For * all other cases, use TWA_SIGNAL unconditionally to ensure we're @@ -1787,8 +1790,10 @@ static void __io_req_task_cancel(struct io_kiocb *req, int error) static void io_req_task_cancel(struct callback_head *cb) { struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); + struct io_ring_ctx *ctx = req->ctx; __io_req_task_cancel(req, -ECANCELED); + percpu_ref_put(&ctx->refs); } static void __io_req_task_submit(struct io_kiocb *req) @@ -2010,6 +2015,12 @@ static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) static inline bool io_run_task_work(void) { + /* + * Not safe to run on exiting task, and the task_work handling will + * not add work to such a task. + */ + if (unlikely(current->flags & PF_EXITING)) + return false; if (current->task_works) { __set_current_state(TASK_RUNNING); task_work_run(); @@ -2283,13 +2294,17 @@ static bool io_resubmit_prep(struct io_kiocb *req, int error) goto end_req; } - ret = io_import_iovec(rw, req, &iovec, &iter, false); - if (ret < 0) - goto end_req; - ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false); - if (!ret) + if (!req->io) { + ret = io_import_iovec(rw, req, &iovec, &iter, false); + if (ret < 0) + goto end_req; + ret = io_setup_async_rw(req, iovec, inline_vecs, &iter, false); + if (!ret) + return true; + kfree(iovec); + } else { return true; - kfree(iovec); + } end_req: req_set_fail_links(req); io_req_complete(req, ret); @@ -3034,6 +3049,7 @@ static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode, if (!wake_page_match(wpq, key)) return 0; + req->rw.kiocb.ki_flags &= ~IOCB_WAITQ; list_del_init(&wait->entry); init_task_work(&req->task_work, io_req_task_submit); @@ -3091,6 +3107,7 @@ static bool io_rw_should_retry(struct io_kiocb *req) wait->wait.flags = 0; INIT_LIST_HEAD(&wait->wait.entry); kiocb->ki_flags |= IOCB_WAITQ; + kiocb->ki_flags &= ~IOCB_NOWAIT; kiocb->ki_waitq = wait; io_get_req_task(req); @@ -3115,6 +3132,7 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, struct iov_iter __iter, *iter = &__iter; ssize_t io_size, ret, ret2; size_t iov_count; + bool no_async; if (req->io) iter = &req->io->rw.iter; @@ -3132,7 +3150,8 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, kiocb->ki_flags &= ~IOCB_NOWAIT; /* If the file doesn't support async, just async punt */ - if (force_nonblock && !io_file_supports_async(req->file, READ)) + no_async = force_nonblock && !io_file_supports_async(req->file, READ); + if (no_async) goto copy_iov; ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), iov_count); @@ -3155,10 +3174,8 @@ static int io_read(struct io_kiocb *req, bool force_nonblock, goto done; /* some cases will consume bytes even on error returns */ iov_iter_revert(iter, iov_count - iov_iter_count(iter)); - ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); - if (ret) - goto out_free; - return -EAGAIN; + ret = 0; + goto copy_iov; } else if (ret < 0) { /* make sure -ERESTARTSYS -> -EINTR is done */ goto done; @@ -3176,6 +3193,8 @@ copy_iov: ret = ret2; goto out_free; } + if (no_async) + return -EAGAIN; /* it's copied and will be cleaned with ->io */ iovec = NULL; /* now use our persistent iterator, if we aren't already */ @@ -3508,8 +3527,6 @@ static int __io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe const char __user *fname; int ret; - if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) - return -EINVAL; if (unlikely(sqe->ioprio || sqe->buf_index)) return -EINVAL; if (unlikely(req->flags & REQ_F_FIXED_FILE)) @@ -3536,6 +3553,8 @@ static int io_openat_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { u64 flags, mode; + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + return -EINVAL; if (req->flags & REQ_F_NEED_CLEANUP) return 0; mode = READ_ONCE(sqe->len); @@ -3550,6 +3569,8 @@ static int io_openat2_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) size_t len; int ret; + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL|IORING_SETUP_SQPOLL))) + return -EINVAL; if (req->flags & REQ_F_NEED_CLEANUP) return 0; how = u64_to_user_ptr(READ_ONCE(sqe->addr2)); @@ -3767,7 +3788,7 @@ static int io_epoll_ctl_prep(struct io_kiocb *req, #if defined(CONFIG_EPOLL) if (sqe->ioprio || sqe->buf_index) return -EINVAL; - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) return -EINVAL; req->epoll.epfd = READ_ONCE(sqe->fd); @@ -3882,7 +3903,7 @@ static int io_fadvise(struct io_kiocb *req, bool force_nonblock) static int io_statx_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { - if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL)) + if (unlikely(req->ctx->flags & (IORING_SETUP_IOPOLL | IORING_SETUP_SQPOLL))) return -EINVAL; if (sqe->ioprio || sqe->buf_index) return -EINVAL; @@ -4724,6 +4745,8 @@ static int io_poll_double_wake(struct wait_queue_entry *wait, unsigned mode, if (mask && !(mask & poll->events)) return 0; + list_del_init(&wait->entry); + if (poll && poll->head) { bool done; @@ -5399,6 +5422,8 @@ static int io_async_cancel(struct io_kiocb *req) static int io_files_update_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + if (unlikely(req->ctx->flags & IORING_SETUP_SQPOLL)) + return -EINVAL; if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT))) return -EINVAL; if (sqe->ioprio || sqe->rw_flags) @@ -5449,6 +5474,8 @@ static int io_req_defer_prep(struct io_kiocb *req, if (unlikely(ret)) return ret; + io_prep_async_work(req); + switch (req->opcode) { case IORING_OP_NOP: break; @@ -5646,6 +5673,11 @@ static void __io_clean_op(struct io_kiocb *req) io_put_file(req, req->splice.file_in, (req->splice.flags & SPLICE_F_FD_IN_FIXED)); break; + case IORING_OP_OPENAT: + case IORING_OP_OPENAT2: + if (req->open.filename) + putname(req->open.filename); + break; } req->flags &= ~REQ_F_NEED_CLEANUP; } @@ -6323,9 +6355,6 @@ static void io_submit_state_start(struct io_submit_state *state, struct io_ring_ctx *ctx, unsigned int max_ios) { blk_start_plug(&state->plug); -#ifdef CONFIG_BLOCK - state->plug.nowait = true; -#endif state->comp.nr = 0; INIT_LIST_HEAD(&state->comp.list); state->comp.ctx = ctx; @@ -8180,6 +8209,8 @@ static void io_uring_cancel_files(struct io_ring_ctx *ctx, /* cancel this request, or head link requests */ io_attempt_cancel(ctx, cancel_req); io_put_req(cancel_req); + /* cancellations _may_ trigger task work */ + io_run_task_work(); schedule(); finish_wait(&ctx->inflight_wait, &wait); } @@ -8385,11 +8416,19 @@ static int io_uring_show_cred(int id, void *p, void *data) static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) { + bool has_lock; int i; - mutex_lock(&ctx->uring_lock); + /* + * Avoid ABBA deadlock between the seq lock and the io_uring mutex, + * since fdinfo case grabs it in the opposite direction of normal use + * cases. If we fail to get the lock, we just don't iterate any + * structures that could be going away outside the io_uring mutex. + */ + has_lock = mutex_trylock(&ctx->uring_lock); + seq_printf(m, "UserFiles:\t%u\n", ctx->nr_user_files); - for (i = 0; i < ctx->nr_user_files; i++) { + for (i = 0; has_lock && i < ctx->nr_user_files; i++) { struct fixed_file_table *table; struct file *f; @@ -8401,13 +8440,13 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) seq_printf(m, "%5u: <none>\n", i); } seq_printf(m, "UserBufs:\t%u\n", ctx->nr_user_bufs); - for (i = 0; i < ctx->nr_user_bufs; i++) { + for (i = 0; has_lock && i < ctx->nr_user_bufs; i++) { struct io_mapped_ubuf *buf = &ctx->user_bufs[i]; seq_printf(m, "%5u: 0x%llx/%u\n", i, buf->ubuf, (unsigned int) buf->len); } - if (!idr_is_empty(&ctx->personality_idr)) { + if (has_lock && !idr_is_empty(&ctx->personality_idr)) { seq_printf(m, "Personalities:\n"); idr_for_each(&ctx->personality_idr, io_uring_show_cred, m); } @@ -8422,7 +8461,8 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) req->task->task_works != NULL); } spin_unlock_irq(&ctx->completion_lock); - mutex_unlock(&ctx->uring_lock); + if (has_lock) + mutex_unlock(&ctx->uring_lock); } static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e732580fe47b..cb52db9a0cfb 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -579,6 +579,9 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE); do { + if (entry->label) + entry->label->len = NFS4_MAXLABELLEN; + status = xdr_decode(desc, entry, &stream); if (status != 0) { if (status == -EAGAIN) diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index ff8965d1a4d4..a163533446fa 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -715,7 +715,7 @@ nfs4_ff_layout_stat_io_end_write(struct rpc_task *task, } static void -ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx) +ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, u32 idx) { struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); @@ -724,7 +724,7 @@ ff_layout_mark_ds_unreachable(struct pnfs_layout_segment *lseg, int idx) } static void -ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx) +ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, u32 idx) { struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); @@ -734,14 +734,14 @@ ff_layout_mark_ds_reachable(struct pnfs_layout_segment *lseg, int idx) static struct nfs4_pnfs_ds * ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, - int start_idx, int *best_idx, + u32 start_idx, u32 *best_idx, bool check_device) { struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg); struct nfs4_ff_layout_mirror *mirror; struct nfs4_pnfs_ds *ds; bool fail_return = false; - int idx; + u32 idx; /* mirrors are initially sorted by efficiency */ for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) { @@ -766,21 +766,21 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, static struct nfs4_pnfs_ds * ff_layout_choose_any_ds_for_read(struct pnfs_layout_segment *lseg, - int start_idx, int *best_idx) + u32 start_idx, u32 *best_idx) { return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, false); } static struct nfs4_pnfs_ds * ff_layout_choose_valid_ds_for_read(struct pnfs_layout_segment *lseg, - int start_idx, int *best_idx) + u32 start_idx, u32 *best_idx) { return ff_layout_choose_ds_for_read(lseg, start_idx, best_idx, true); } static struct nfs4_pnfs_ds * ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, - int start_idx, int *best_idx) + u32 start_idx, u32 *best_idx) { struct nfs4_pnfs_ds *ds; @@ -791,7 +791,8 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, } static struct nfs4_pnfs_ds * -ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, int *best_idx) +ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, + u32 *best_idx) { struct pnfs_layout_segment *lseg = pgio->pg_lseg; struct nfs4_pnfs_ds *ds; @@ -837,7 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_pgio_mirror *pgm; struct nfs4_ff_layout_mirror *mirror; struct nfs4_pnfs_ds *ds; - int ds_idx; + u32 ds_idx, i; retry: ff_layout_pg_check_layout(pgio, req); @@ -863,14 +864,14 @@ retry: goto retry; } - mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx); + for (i = 0; i < pgio->pg_mirror_count; i++) { + mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i); + pgm = &pgio->pg_mirrors[i]; + pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; + } pgio->pg_mirror_idx = ds_idx; - /* read always uses only one mirror - idx 0 for pgio layer */ - pgm = &pgio->pg_mirrors[0]; - pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize; - if (NFS_SERVER(pgio->pg_inode)->flags & (NFS_MOUNT_SOFT|NFS_MOUNT_SOFTERR)) pgio->pg_maxretrans = io_maxretrans; @@ -894,7 +895,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs4_ff_layout_mirror *mirror; struct nfs_pgio_mirror *pgm; struct nfs4_pnfs_ds *ds; - int i; + u32 i; retry: ff_layout_pg_check_layout(pgio, req); @@ -1038,7 +1039,7 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr) { u32 idx = hdr->pgio_mirror_idx + 1; - int new_idx = 0; + u32 new_idx = 0; if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx + 1, &new_idx)) ff_layout_send_layouterror(hdr->lseg); @@ -1075,7 +1076,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task, struct nfs4_state *state, struct nfs_client *clp, struct pnfs_layout_segment *lseg, - int idx) + u32 idx) { struct pnfs_layout_hdr *lo = lseg->pls_layout; struct inode *inode = lo->plh_inode; @@ -1149,7 +1150,7 @@ reset: /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */ static int ff_layout_async_handle_error_v3(struct rpc_task *task, struct pnfs_layout_segment *lseg, - int idx) + u32 idx) { struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx); @@ -1184,7 +1185,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task, struct nfs4_state *state, struct nfs_client *clp, struct pnfs_layout_segment *lseg, - int idx) + u32 idx) { int vers = clp->cl_nfs_mod->rpc_vers->number; @@ -1211,7 +1212,7 @@ static int ff_layout_async_handle_error(struct rpc_task *task, } static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg, - int idx, u64 offset, u64 length, + u32 idx, u64 offset, u64 length, u32 *op_status, int opnum, int error) { struct nfs4_ff_layout_mirror *mirror; @@ -1809,7 +1810,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) loff_t offset = hdr->args.offset; int vers; struct nfs_fh *fh; - int idx = hdr->pgio_mirror_idx; + u32 idx = hdr->pgio_mirror_idx; mirror = FF_LAYOUT_COMP(lseg, idx); ds = nfs4_ff_layout_prepare_ds(lseg, mirror, true); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 142225f0af59..2b2211d1234e 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -356,7 +356,15 @@ static ssize_t _nfs42_proc_copy(struct file *src, truncate_pagecache_range(dst_inode, pos_dst, pos_dst + res->write_res.count); - + spin_lock(&dst_inode->i_lock); + NFS_I(dst_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE | + NFS_INO_REVAL_FORCED | NFS_INO_INVALID_SIZE | + NFS_INO_INVALID_ATTR | NFS_INO_INVALID_DATA); + spin_unlock(&dst_inode->i_lock); + spin_lock(&src_inode->i_lock); + NFS_I(src_inode)->cache_validity |= (NFS_INO_REVAL_PAGECACHE | + NFS_INO_REVAL_FORCED | NFS_INO_INVALID_ATIME); + spin_unlock(&src_inode->i_lock); status = res->write_res.count; out: if (args->sync) diff --git a/fs/pipe.c b/fs/pipe.c index 60dbee457143..117db82b10af 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -106,25 +106,6 @@ void pipe_double_lock(struct pipe_inode_info *pipe1, } } -/* Drop the inode semaphore and wait for a pipe event, atomically */ -void pipe_wait(struct pipe_inode_info *pipe) -{ - DEFINE_WAIT(rdwait); - DEFINE_WAIT(wrwait); - - /* - * Pipes are system-local resources, so sleeping on them - * is considered a noninteractive wait: - */ - prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); - prepare_to_wait(&pipe->wr_wait, &wrwait, TASK_INTERRUPTIBLE); - pipe_unlock(pipe); - schedule(); - finish_wait(&pipe->rd_wait, &rdwait); - finish_wait(&pipe->wr_wait, &wrwait); - pipe_lock(pipe); -} - static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { @@ -1035,12 +1016,52 @@ SYSCALL_DEFINE1(pipe, int __user *, fildes) return do_pipe2(fildes, 0); } +/* + * This is the stupid "wait for pipe to be readable or writable" + * model. + * + * See pipe_read/write() for the proper kind of exclusive wait, + * but that requires that we wake up any other readers/writers + * if we then do not end up reading everything (ie the whole + * "wake_next_reader/writer" logic in pipe_read/write()). + */ +void pipe_wait_readable(struct pipe_inode_info *pipe) +{ + pipe_unlock(pipe); + wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); + pipe_lock(pipe); +} + +void pipe_wait_writable(struct pipe_inode_info *pipe) +{ + pipe_unlock(pipe); + wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); + pipe_lock(pipe); +} + +/* + * This depends on both the wait (here) and the wakeup (wake_up_partner) + * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot + * race with the count check and waitqueue prep. + * + * Normally in order to avoid races, you'd do the prepare_to_wait() first, + * then check the condition you're waiting for, and only then sleep. But + * because of the pipe lock, we can check the condition before being on + * the wait queue. + * + * We use the 'rd_wait' waitqueue for pipe partner waiting. + */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { + DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { - pipe_wait(pipe); + prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); + pipe_unlock(pipe); + schedule(); + finish_wait(&pipe->rd_wait, &rdwait); + pipe_lock(pipe); if (signal_pending(current)) break; } @@ -1050,7 +1071,6 @@ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_wait); - wake_up_interruptible_all(&pipe->wr_wait); } static int fifo_open(struct inode *inode, struct file *filp) diff --git a/fs/read_write.c b/fs/read_write.c index 5db58b8c78d0..d3428189f36b 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -538,6 +538,14 @@ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t inc_syscw(current); return ret; } +/* + * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", + * but autofs is one of the few internal kernel users that actually + * wants this _and_ can be built as a module. So we need to export + * this symbol for autofs, even though it really isn't appropriate + * for any other kernel modules. + */ +EXPORT_SYMBOL_GPL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) diff --git a/fs/splice.c b/fs/splice.c index d7c8a7c4db07..ce75aec52274 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -526,6 +526,22 @@ static int splice_from_pipe_feed(struct pipe_inode_info *pipe, struct splice_des return 1; } +/* We know we have a pipe buffer, but maybe it's empty? */ +static inline bool eat_empty_buffer(struct pipe_inode_info *pipe) +{ + unsigned int tail = pipe->tail; + unsigned int mask = pipe->ring_size - 1; + struct pipe_buffer *buf = &pipe->bufs[tail & mask]; + + if (unlikely(!buf->len)) { + pipe_buf_release(pipe, buf); + pipe->tail = tail+1; + return true; + } + + return false; +} + /** * splice_from_pipe_next - wait for some data to splice from * @pipe: pipe to splice from @@ -545,6 +561,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des if (signal_pending(current)) return -ERESTARTSYS; +repeat: while (pipe_empty(pipe->head, pipe->tail)) { if (!pipe->writers) return 0; @@ -563,9 +580,12 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des sd->need_wakeup = false; } - pipe_wait(pipe); + pipe_wait_readable(pipe); } + if (eat_empty_buffer(pipe)) + goto repeat; + return 1; } @@ -1077,7 +1097,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags) return -EAGAIN; if (signal_pending(current)) return -ERESTARTSYS; - pipe_wait(pipe); + pipe_wait_writable(pipe); } } @@ -1454,7 +1474,7 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags) ret = -EAGAIN; break; } - pipe_wait(pipe); + pipe_wait_readable(pipe); } pipe_unlock(pipe); @@ -1493,7 +1513,7 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags) ret = -ERESTARTSYS; break; } - pipe_wait(pipe); + pipe_wait_writable(pipe); } pipe_unlock(pipe); diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c index 8fe03b4a0d2b..25aade344192 100644 --- a/fs/vboxsf/super.c +++ b/fs/vboxsf/super.c @@ -384,7 +384,7 @@ fail_nomem: static int vboxsf_parse_monolithic(struct fs_context *fc, void *data) { - char *options = data; + unsigned char *options = data; if (options && options[0] == VBSF_MOUNT_SIGNATURE_BYTE_0 && options[1] == VBSF_MOUNT_SIGNATURE_BYTE_1 && diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 5430febd34be..7636bc71c71f 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -661,7 +661,7 @@ #define BTF \ .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { \ __start_BTF = .; \ - *(.BTF) \ + KEEP(*(.BTF)) \ __stop_BTF = .; \ } \ . = ALIGN(4); \ diff --git a/include/drm/drm_dsc.h b/include/drm/drm_dsc.h index 887954cbfc60..732f32740c86 100644 --- a/include/drm/drm_dsc.h +++ b/include/drm/drm_dsc.h @@ -588,7 +588,7 @@ struct drm_dsc_picture_parameter_set { * This structure represents the DSC PPS infoframe required to send the Picture * Parameter Set metadata required before enabling VESA Display Stream * Compression. This is based on the DP Secondary Data Packet structure and - * comprises of SDP Header as defined &struct struct dp_sdp_header in drm_dp_helper.h + * comprises of SDP Header as defined &struct dp_sdp_header in drm_dp_helper.h * and PPS payload defined in &struct drm_dsc_picture_parameter_set. * * @pps_header: Header for PPS as per DP SDP header format of type diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 1e4cdc6c7ae2..64ae25c59d55 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -958,7 +958,7 @@ void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); -#ifdef CONFIG_X86 +#ifndef CONFIG_IA64 void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else static inline void arch_reserve_mem_area(acpi_physical_address addr, diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h new file mode 100644 index 000000000000..421b0fa90d6a --- /dev/null +++ b/include/linux/amba/clcd-regs.h @@ -0,0 +1,87 @@ +/* + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ + +#ifndef AMBA_CLCD_REGS_H +#define AMBA_CLCD_REGS_H + +/* + * CLCD Controller Internal Register addresses + */ +#define CLCD_TIM0 0x00000000 +#define CLCD_TIM1 0x00000004 +#define CLCD_TIM2 0x00000008 +#define CLCD_TIM3 0x0000000c +#define CLCD_UBAS 0x00000010 +#define CLCD_LBAS 0x00000014 + +#define CLCD_PL110_IENB 0x00000018 +#define CLCD_PL110_CNTL 0x0000001c +#define CLCD_PL110_STAT 0x00000020 +#define CLCD_PL110_INTR 0x00000024 +#define CLCD_PL110_UCUR 0x00000028 +#define CLCD_PL110_LCUR 0x0000002C + +#define CLCD_PL111_CNTL 0x00000018 +#define CLCD_PL111_IENB 0x0000001c +#define CLCD_PL111_RIS 0x00000020 +#define CLCD_PL111_MIS 0x00000024 +#define CLCD_PL111_ICR 0x00000028 +#define CLCD_PL111_UCUR 0x0000002c +#define CLCD_PL111_LCUR 0x00000030 + +#define CLCD_PALL 0x00000200 +#define CLCD_PALETTE 0x00000200 + +#define TIM2_PCD_LO_MASK GENMASK(4, 0) +#define TIM2_PCD_LO_BITS 5 +#define TIM2_CLKSEL (1 << 5) +#define TIM2_ACB_MASK GENMASK(10, 6) +#define TIM2_IVS (1 << 11) +#define TIM2_IHS (1 << 12) +#define TIM2_IPC (1 << 13) +#define TIM2_IOE (1 << 14) +#define TIM2_BCD (1 << 26) +#define TIM2_PCD_HI_MASK GENMASK(31, 27) +#define TIM2_PCD_HI_BITS 5 +#define TIM2_PCD_HI_SHIFT 27 + +#define CNTL_LCDEN (1 << 0) +#define CNTL_LCDBPP1 (0 << 1) +#define CNTL_LCDBPP2 (1 << 1) +#define CNTL_LCDBPP4 (2 << 1) +#define CNTL_LCDBPP8 (3 << 1) +#define CNTL_LCDBPP16 (4 << 1) +#define CNTL_LCDBPP16_565 (6 << 1) +#define CNTL_LCDBPP16_444 (7 << 1) +#define CNTL_LCDBPP24 (5 << 1) +#define CNTL_LCDBW (1 << 4) +#define CNTL_LCDTFT (1 << 5) +#define CNTL_LCDMONO8 (1 << 6) +#define CNTL_LCDDUAL (1 << 7) +#define CNTL_BGR (1 << 8) +#define CNTL_BEBO (1 << 9) +#define CNTL_BEPO (1 << 10) +#define CNTL_LCDPWR (1 << 11) +#define CNTL_LCDVCOMP(x) ((x) << 12) +#define CNTL_LDMAFIFOTIME (1 << 15) +#define CNTL_WATERMARK (1 << 16) + +/* ST Microelectronics variant bits */ +#define CNTL_ST_1XBPP_444 0x0 +#define CNTL_ST_1XBPP_5551 (1 << 17) +#define CNTL_ST_1XBPP_565 (1 << 18) +#define CNTL_ST_CDWID_12 0x0 +#define CNTL_ST_CDWID_16 (1 << 19) +#define CNTL_ST_CDWID_18 (1 << 20) +#define CNTL_ST_CDWID_24 ((1 << 19)|(1 << 20)) +#define CNTL_ST_CEAEN (1 << 21) +#define CNTL_ST_LCDBPP24_PACKED (6 << 1) + +#endif /* AMBA_CLCD_REGS_H */ diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h new file mode 100644 index 000000000000..b6e0cbeaf533 --- /dev/null +++ b/include/linux/amba/clcd.h @@ -0,0 +1,290 @@ +/* + * linux/include/asm-arm/hardware/amba_clcd.h -- Integrator LCD panel. + * + * David A Rusling + * + * Copyright (C) 2001 ARM Limited + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file COPYING in the main directory of this archive + * for more details. + */ +#include <linux/fb.h> +#include <linux/amba/clcd-regs.h> + +enum { + /* individual formats */ + CLCD_CAP_RGB444 = (1 << 0), + CLCD_CAP_RGB5551 = (1 << 1), + CLCD_CAP_RGB565 = (1 << 2), + CLCD_CAP_RGB888 = (1 << 3), + CLCD_CAP_BGR444 = (1 << 4), + CLCD_CAP_BGR5551 = (1 << 5), + CLCD_CAP_BGR565 = (1 << 6), + CLCD_CAP_BGR888 = (1 << 7), + + /* connection layouts */ + CLCD_CAP_444 = CLCD_CAP_RGB444 | CLCD_CAP_BGR444, + CLCD_CAP_5551 = CLCD_CAP_RGB5551 | CLCD_CAP_BGR5551, + CLCD_CAP_565 = CLCD_CAP_RGB565 | CLCD_CAP_BGR565, + CLCD_CAP_888 = CLCD_CAP_RGB888 | CLCD_CAP_BGR888, + + /* red/blue ordering */ + CLCD_CAP_RGB = CLCD_CAP_RGB444 | CLCD_CAP_RGB5551 | + CLCD_CAP_RGB565 | CLCD_CAP_RGB888, + CLCD_CAP_BGR = CLCD_CAP_BGR444 | CLCD_CAP_BGR5551 | + CLCD_CAP_BGR565 | CLCD_CAP_BGR888, + + CLCD_CAP_ALL = CLCD_CAP_BGR | CLCD_CAP_RGB, +}; + +struct backlight_device; + +struct clcd_panel { + struct fb_videomode mode; + signed short width; /* width in mm */ + signed short height; /* height in mm */ + u32 tim2; + u32 tim3; + u32 cntl; + u32 caps; + unsigned int bpp:8, + fixedtimings:1, + grayscale:1; + unsigned int connector; + struct backlight_device *backlight; + /* + * If the B/R lines are switched between the CLCD + * and the panel we need to know this and not try to + * compensate with the BGR bit in the control register. + */ + bool bgr_connection; +}; + +struct clcd_regs { + u32 tim0; + u32 tim1; + u32 tim2; + u32 tim3; + u32 cntl; + unsigned long pixclock; +}; + +struct clcd_fb; + +/* + * the board-type specific routines + */ +struct clcd_board { + const char *name; + + /* + * Optional. Hardware capability flags. + */ + u32 caps; + + /* + * Optional. Check whether the var structure is acceptable + * for this display. + */ + int (*check)(struct clcd_fb *fb, struct fb_var_screeninfo *var); + + /* + * Compulsory. Decode fb->fb.var into regs->*. In the case of + * fixed timing, set regs->* to the register values required. + */ + void (*decode)(struct clcd_fb *fb, struct clcd_regs *regs); + + /* + * Optional. Disable any extra display hardware. + */ + void (*disable)(struct clcd_fb *); + + /* + * Optional. Enable any extra display hardware. + */ + void (*enable)(struct clcd_fb *); + + /* + * Setup platform specific parts of CLCD driver + */ + int (*setup)(struct clcd_fb *); + + /* + * mmap the framebuffer memory + */ + int (*mmap)(struct clcd_fb *, struct vm_area_struct *); + + /* + * Remove platform specific parts of CLCD driver + */ + void (*remove)(struct clcd_fb *); +}; + +struct amba_device; +struct clk; + +/* this data structure describes each frame buffer device we find */ +struct clcd_fb { + struct fb_info fb; + struct amba_device *dev; + struct clk *clk; + struct clcd_panel *panel; + struct clcd_board *board; + void *board_data; + void __iomem *regs; + u16 off_ienb; + u16 off_cntl; + u32 clcd_cntl; + u32 cmap[16]; + bool clk_enabled; +}; + +static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs) +{ + struct fb_var_screeninfo *var = &fb->fb.var; + u32 val, cpl; + + /* + * Program the CLCD controller registers and start the CLCD + */ + val = ((var->xres / 16) - 1) << 2; + val |= (var->hsync_len - 1) << 8; + val |= (var->right_margin - 1) << 16; + val |= (var->left_margin - 1) << 24; + regs->tim0 = val; + + val = var->yres; + if (fb->panel->cntl & CNTL_LCDDUAL) + val /= 2; + val -= 1; + val |= (var->vsync_len - 1) << 10; + val |= var->lower_margin << 16; + val |= var->upper_margin << 24; + regs->tim1 = val; + + val = fb->panel->tim2; + val |= var->sync & FB_SYNC_HOR_HIGH_ACT ? 0 : TIM2_IHS; + val |= var->sync & FB_SYNC_VERT_HIGH_ACT ? 0 : TIM2_IVS; + + cpl = var->xres_virtual; + if (fb->panel->cntl & CNTL_LCDTFT) /* TFT */ + /* / 1 */; + else if (!var->grayscale) /* STN color */ + cpl = cpl * 8 / 3; + else if (fb->panel->cntl & CNTL_LCDMONO8) /* STN monochrome, 8bit */ + cpl /= 8; + else /* STN monochrome, 4bit */ + cpl /= 4; + + regs->tim2 = val | ((cpl - 1) << 16); + + regs->tim3 = fb->panel->tim3; + + val = fb->panel->cntl; + if (var->grayscale) + val |= CNTL_LCDBW; + + if (fb->panel->caps && fb->board->caps && var->bits_per_pixel >= 16) { + /* + * if board and panel supply capabilities, we can support + * changing BGR/RGB depending on supplied parameters. Here + * we switch to what the framebuffer is providing if need + * be, so if the framebuffer is BGR but the display connection + * is RGB (first case) we switch it around. Vice versa mutatis + * mutandis if the framebuffer is RGB but the display connection + * is BGR, we flip it around. + */ + if (var->red.offset == 0) + val &= ~CNTL_BGR; + else + val |= CNTL_BGR; + if (fb->panel->bgr_connection) + val ^= CNTL_BGR; + } + + switch (var->bits_per_pixel) { + case 1: + val |= CNTL_LCDBPP1; + break; + case 2: + val |= CNTL_LCDBPP2; + break; + case 4: + val |= CNTL_LCDBPP4; + break; + case 8: + val |= CNTL_LCDBPP8; + break; + case 16: + /* + * PL110 cannot choose between 5551 and 565 modes in its + * control register. It is possible to use 565 with + * custom external wiring. + */ + if (amba_part(fb->dev) == 0x110 || + var->green.length == 5) + val |= CNTL_LCDBPP16; + else if (var->green.length == 6) + val |= CNTL_LCDBPP16_565; + else + val |= CNTL_LCDBPP16_444; + break; + case 32: + val |= CNTL_LCDBPP24; + break; + } + + regs->cntl = val; + regs->pixclock = var->pixclock; +} + +static inline int clcdfb_check(struct clcd_fb *fb, struct fb_var_screeninfo *var) +{ + var->xres_virtual = var->xres = (var->xres + 15) & ~15; + var->yres_virtual = var->yres = (var->yres + 1) & ~1; + +#define CHECK(e,l,h) (var->e < l || var->e > h) + if (CHECK(right_margin, (5+1), 256) || /* back porch */ + CHECK(left_margin, (5+1), 256) || /* front porch */ + CHECK(hsync_len, (5+1), 256) || + var->xres > 4096 || + var->lower_margin > 255 || /* back porch */ + var->upper_margin > 255 || /* front porch */ + var->vsync_len > 32 || + var->yres > 1024) + return -EINVAL; +#undef CHECK + + /* single panel mode: PCD = max(PCD, 1) */ + /* dual panel mode: PCD = max(PCD, 5) */ + + /* + * You can't change the grayscale setting, and + * we can only do non-interlaced video. + */ + if (var->grayscale != fb->fb.var.grayscale || + (var->vmode & FB_VMODE_MASK) != FB_VMODE_NONINTERLACED) + return -EINVAL; + +#define CHECK(e) (var->e != fb->fb.var.e) + if (fb->panel->fixedtimings && + (CHECK(xres) || + CHECK(yres) || + CHECK(bits_per_pixel) || + CHECK(pixclock) || + CHECK(left_margin) || + CHECK(right_margin) || + CHECK(upper_margin) || + CHECK(lower_margin) || + CHECK(hsync_len) || + CHECK(vsync_len) || + CHECK(sync))) + return -EINVAL; +#undef CHECK + + var->nonstd = 0; + var->accel_flags = 0; + + return 0; +} diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 4ecf4fed171f..b3fc5d3dd8ea 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -497,13 +497,12 @@ static inline int op_stat_group(unsigned int op) typedef unsigned int blk_qc_t; #define BLK_QC_T_NONE -1U -#define BLK_QC_T_EAGAIN -2U #define BLK_QC_T_SHIFT 16 #define BLK_QC_T_INTERNAL (1U << 31) static inline bool blk_qc_t_valid(blk_qc_t cookie) { - return cookie != BLK_QC_T_NONE && cookie != BLK_QC_T_EAGAIN; + return cookie != BLK_QC_T_NONE; } static inline unsigned int blk_qc_t_to_queue_num(blk_qc_t cookie) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bb5636cc17b9..868e11face00 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -352,6 +352,8 @@ struct queue_limits { typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); +void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model); + #ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) diff --git a/include/linux/font.h b/include/linux/font.h index 51b91c8b69d5..59faa80f586d 100644 --- a/include/linux/font.h +++ b/include/linux/font.h @@ -59,4 +59,17 @@ extern const struct font_desc *get_default_font(int xres, int yres, /* Max. length for the name of a predefined font */ #define MAX_FONT_NAME 32 +/* Extra word getters */ +#define REFCOUNT(fd) (((int *)(fd))[-1]) +#define FNTSIZE(fd) (((int *)(fd))[-2]) +#define FNTCHARCNT(fd) (((int *)(fd))[-3]) +#define FNTSUM(fd) (((int *)(fd))[-4]) + +#define FONT_EXTRA_WORDS 4 + +struct font_data { + unsigned int extra[FONT_EXTRA_WORDS]; + const unsigned char data[]; +} __packed; + #endif /* _VIDEO_FONT_H */ diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h index 2eab6d5f6736..aab0ffc6bac6 100644 --- a/include/linux/fs_parser.h +++ b/include/linux/fs_parser.h @@ -120,7 +120,7 @@ static inline bool fs_validate_description(const char *name, #define fsparam_u32oct(NAME, OPT) \ __fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8) #define fsparam_u32hex(NAME, OPT) \ - __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *16)) + __fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16) #define fsparam_s32(NAME, OPT) __fsparam(fs_param_is_s32, NAME, OPT, 0, NULL) #define fsparam_u64(NAME, OPT) __fsparam(fs_param_is_u64, NAME, OPT, 0, NULL) #define fsparam_enum(NAME, OPT, array) __fsparam(fs_param_is_enum, NAME, OPT, 0, array) diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 9be1bff4f586..8aab327b5539 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -373,6 +373,8 @@ void unregister_kretprobes(struct kretprobe **rps, int num); void kprobe_flush_task(struct task_struct *tk); void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); +void kprobe_free_init_mem(void); + int disable_kprobe(struct kprobe *kp); int enable_kprobe(struct kprobe *kp); @@ -435,6 +437,9 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num) static inline void kprobe_flush_task(struct task_struct *tk) { } +static inline void kprobe_free_init_mem(void) +{ +} static inline int disable_kprobe(struct kprobe *kp) { return -ENOSYS; diff --git a/include/linux/memstick.h b/include/linux/memstick.h index da4c65f9435f..ebf73d4ee969 100644 --- a/include/linux/memstick.h +++ b/include/linux/memstick.h @@ -281,6 +281,7 @@ struct memstick_host { struct memstick_dev *card; unsigned int retries; + bool removing; /* Notify the host that some requests are pending. */ void (*request)(struct memstick_host *host); diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index c145de0473bc..372100c755e7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -767,6 +767,8 @@ struct mlx5_cmd_work_ent { u64 ts2; u16 op; bool polling; + /* Track the max comp handlers */ + refcount_t refcnt; }; struct mlx5_pas { @@ -933,6 +935,7 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); +bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type); int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn); diff --git a/include/linux/mm.h b/include/linux/mm.h index b2f370f0b420..16b799a0522c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1646,7 +1646,7 @@ struct mmu_notifier_range; void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, - struct vm_area_struct *vma); + struct vm_area_struct *vma, struct vm_area_struct *new); int follow_pte_pmd(struct mm_struct *mm, unsigned long address, struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); @@ -2416,7 +2416,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, - enum memmap_context, struct vmem_altmap *); + enum meminit_context, struct vmem_altmap *); extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 496c3ff97cce..ed028af3cb19 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -436,6 +436,16 @@ struct mm_struct { */ atomic_t mm_count; + /** + * @has_pinned: Whether this mm has pinned any pages. This can + * be either replaced in the future by @pinned_vm when it + * becomes stable, or grow into a counter on its own. We're + * aggresive on this bit now - even if the pinned pages were + * unpinned later on, we'll still keep this bit set for the + * lifecycle of this mm just for simplicity. + */ + atomic_t has_pinned; + #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* PTE page table pages */ #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 8379432f4f2f..0f7a4ff4b059 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -824,10 +824,15 @@ bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned int alloc_flags); bool zone_watermark_ok_safe(struct zone *z, unsigned int order, unsigned long mark, int highest_zoneidx); -enum memmap_context { - MEMMAP_EARLY, - MEMMAP_HOTPLUG, +/* + * Memory initialization context, use to differentiate memory added by + * the platform statically or via memory hotplug interface. + */ +enum meminit_context { + MEMINIT_EARLY, + MEMINIT_HOTPLUG, }; + extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn, unsigned long size); diff --git a/include/linux/net.h b/include/linux/net.h index d48ff1180879..ae713c851342 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -21,6 +21,7 @@ #include <linux/rcupdate.h> #include <linux/once.h> #include <linux/fs.h> +#include <linux/mm.h> #include <linux/sockptr.h> #include <uapi/linux/net.h> @@ -286,6 +287,21 @@ do { \ #define net_get_random_once_wait(buf, nbytes) \ get_random_once_wait((buf), (nbytes)) +/* + * E.g. XFS meta- & log-data is in slab pages, or bcache meta + * data pages, or other high order pages allocated by + * __get_free_pages() without __GFP_COMP, which have a page_count + * of 0 and/or have PageSlab() set. We cannot use send_page for + * those, as that does get_page(); put_page(); and would cause + * either a VM_BUG directly, or __page_cache_release a page that + * would actually still be referenced by someone, leading to some + * obscure delayed Oops somewhere else. + */ +static inline bool sendpage_ok(struct page *page) +{ + return !PageSlab(page) && page_count(page) >= 1; +} + int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len); int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 2cc3cf80b49a..0b17c4322b09 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -193,7 +193,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) #define NETIF_F_GSO_MASK (__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \ __NETIF_F_BIT(NETIF_F_GSO_SHIFT)) -/* List of IP checksum features. Note that NETIF_F_ HW_CSUM should not be +/* List of IP checksum features. Note that NETIF_F_HW_CSUM should not be * set in features when NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM are set-- * this would be contradictory */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b0e303f6603f..18dec08439f9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1784,6 +1784,7 @@ enum netdev_priv_flags { * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers * + * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one @@ -1848,6 +1849,12 @@ enum netdev_priv_flags { * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state + * @xdp_state: stores info on attached XDP BPF programs + * + * @nested_level: Used as as a parameter of spin_lock_nested() of + * dev->addr_list_lock. + * @unlink_list: As netif_addr_lock() can be called recursively, + * keep a list of interfaces to be deleted. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -1953,6 +1960,7 @@ struct net_device { unsigned short type; unsigned short hard_header_len; unsigned char min_header_len; + unsigned char name_assign_type; unsigned short needed_headroom; unsigned short needed_tailroom; @@ -1963,12 +1971,12 @@ struct net_device { unsigned char addr_len; unsigned char upper_level; unsigned char lower_level; + unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; spinlock_t addr_list_lock; - unsigned char name_assign_type; - bool uc_promisc; + struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; struct netdev_hw_addr_list dev_addrs; @@ -1976,8 +1984,15 @@ struct net_device { #ifdef CONFIG_SYSFS struct kset *queues_kset; #endif +#ifdef CONFIG_LOCKDEP + struct list_head unlink_list; +#endif unsigned int promiscuity; unsigned int allmulti; + bool uc_promisc; +#ifdef CONFIG_LOCKDEP + unsigned char nested_level; +#endif /* Protocol-specific pointers */ @@ -4258,17 +4273,23 @@ static inline void netif_tx_disable(struct net_device *dev) static inline void netif_addr_lock(struct net_device *dev) { - spin_lock(&dev->addr_list_lock); -} + unsigned char nest_level = 0; -static inline void netif_addr_lock_nested(struct net_device *dev) -{ - spin_lock_nested(&dev->addr_list_lock, dev->lower_level); +#ifdef CONFIG_LOCKDEP + nest_level = dev->nested_level; +#endif + spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_lock_bh(struct net_device *dev) { - spin_lock_bh(&dev->addr_list_lock); + unsigned char nest_level = 0; + +#ifdef CONFIG_LOCKDEP + nest_level = dev->nested_level; +#endif + local_bh_disable(); + spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_unlock(struct net_device *dev) @@ -4453,12 +4474,38 @@ extern int dev_rx_weight; extern int dev_tx_weight; extern int gro_normal_batch; +enum { + NESTED_SYNC_IMM_BIT, + NESTED_SYNC_TODO_BIT, +}; + +#define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit)) +#define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT) + +#define NESTED_SYNC_IMM __NESTED_SYNC(IMM) +#define NESTED_SYNC_TODO __NESTED_SYNC(TODO) + +struct netdev_nested_priv { + unsigned char flags; + void *data; +}; + bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); +#ifdef CONFIG_LOCKDEP +static LIST_HEAD(net_unlink_list); + +static inline void net_unlink_todo(struct net_device *dev) +{ + if (list_empty(&dev->unlink_list)) + list_add_tail(&dev->unlink_list, &net_unlink_list); +} +#endif + /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ @@ -4468,8 +4515,8 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev, int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *upper_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); @@ -4506,12 +4553,12 @@ struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *lower_dev, - void *data), - void *data); + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv); void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 9408f3252c8e..69cb46f7b8d2 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1611,8 +1611,8 @@ struct nfs_pgio_header { __u64 mds_offset; /* Filelayout dense stripe */ struct nfs_page_array page_array; struct nfs_client *ds_clp; /* pNFS data server */ - int ds_commit_idx; /* ds index if ds_clp is set */ - int pgio_mirror_idx;/* mirror index in pgio layer */ + u32 ds_commit_idx; /* ds index if ds_clp is set */ + u32 pgio_mirror_idx;/* mirror index in pgio layer */ }; struct nfs_mds_commit_info { diff --git a/include/linux/node.h b/include/linux/node.h index 4866f32a02d8..014ba3ab2efd 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -99,11 +99,13 @@ extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) -extern int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn); +int link_mem_sections(int nid, unsigned long start_pfn, + unsigned long end_pfn, + enum meminit_context context); #else static inline int link_mem_sections(int nid, unsigned long start_pfn, - unsigned long end_pfn) + unsigned long end_pfn, + enum meminit_context context) { return 0; } @@ -128,7 +130,8 @@ static inline int register_one_node(int nid) if (error) return error; /* link memory sections under this node */ - error = link_mem_sections(nid, start_pfn, end_pfn); + error = link_mem_sections(nid, start_pfn, end_pfn, + MEMINIT_EARLY); } return error; diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e8cbc2e795d5..90654cb63e9e 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1427,6 +1427,16 @@ typedef unsigned int pgtbl_mod_mask; #define mm_pmd_folded(mm) __is_defined(__PAGETABLE_PMD_FOLDED) #endif +#ifndef p4d_offset_lockless +#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address) +#endif +#ifndef pud_offset_lockless +#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address) +#endif +#ifndef pmd_offset_lockless +#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address) +#endif + /* * p?d_leaf() - true if this entry is a final mapping to a physical address. * This differs from p?d_huge() by the fact that they are always available (if diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 50afd0d0084c..5d2705f1d01c 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -240,8 +240,9 @@ extern unsigned int pipe_max_size; extern unsigned long pipe_user_pages_hard; extern unsigned long pipe_user_pages_soft; -/* Drop the inode semaphore and wait for a pipe event, atomically */ -void pipe_wait(struct pipe_inode_info *pipe); +/* Wait for a pipe to be readable/writable while dropping the pipe lock */ +void pipe_wait_readable(struct pipe_inode_info *); +void pipe_wait_writable(struct pipe_inode_info *); struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); diff --git a/include/linux/platform_data/gpio/gpio-amd-fch.h b/include/linux/platform_data/gpio/gpio-amd-fch.h index 9e46678edb2a..255d51c9d36d 100644 --- a/include/linux/platform_data/gpio/gpio-amd-fch.h +++ b/include/linux/platform_data/gpio/gpio-amd-fch.h @@ -19,7 +19,7 @@ #define AMD_FCH_GPIO_REG_GPIO49 0x40 #define AMD_FCH_GPIO_REG_GPIO50 0x41 #define AMD_FCH_GPIO_REG_GPIO51 0x42 -#define AMD_FCH_GPIO_REG_GPIO59_DEVSLP0 0x43 +#define AMD_FCH_GPIO_REG_GPIO55_DEVSLP0 0x43 #define AMD_FCH_GPIO_REG_GPIO57 0x44 #define AMD_FCH_GPIO_REG_GPIO58 0x45 #define AMD_FCH_GPIO_REG_GPIO59_DEVSLP1 0x46 diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index cd6a5c7e56eb..cdd73afc4c46 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -623,6 +623,7 @@ struct qed_dev_info { #define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; + bool b_arfs_capable; bool b_inter_pf_switch; bool tx_switching; bool rdma_supported; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ed9bea924dc3..04a18e01b362 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3223,8 +3223,9 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error if @free_on_error is true. */ -static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, - bool free_on_error) +static inline int __must_check __skb_put_padto(struct sk_buff *skb, + unsigned int len, + bool free_on_error) { unsigned int size = skb->len; @@ -3247,7 +3248,7 @@ static inline int __skb_put_padto(struct sk_buff *skb, unsigned int len, * is untouched. Otherwise it is extended. Returns zero on * success. The skb is freed on error. */ -static inline int skb_put_padto(struct sk_buff *skb, unsigned int len) +static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int len) { return __skb_put_padto(skb, len, true); } diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 91220ace31da..7557c1070fd7 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -312,6 +312,11 @@ static inline void __mod_zone_page_state(struct zone *zone, static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { + if (vmstat_item_in_bytes(item)) { + VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1)); + delta >>= PAGE_SHIFT; + } + node_page_state_add(delta, pgdat, item); } diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h index 52ef92049073..bbb3f26fbde9 100644 --- a/include/media/videobuf2-core.h +++ b/include/media/videobuf2-core.h @@ -744,8 +744,6 @@ void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb); * vb2_core_reqbufs() - Initiate streaming. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @memory: memory type, as defined by &enum vb2_memory. - * @flags: auxiliary queue/buffer management flags. Currently, the only - * used flag is %V4L2_FLAG_MEMORY_NON_CONSISTENT. * @count: requested buffer count. * * Videobuf2 core helper to implement VIDIOC_REQBUF() operation. It is called @@ -770,13 +768,12 @@ void vb2_core_querybuf(struct vb2_queue *q, unsigned int index, void *pb); * Return: returns zero on success; an error code otherwise. */ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count); + unsigned int *count); /** * vb2_core_create_bufs() - Allocate buffers and any required auxiliary structs * @q: pointer to &struct vb2_queue with videobuf2 queue. * @memory: memory type, as defined by &enum vb2_memory. - * @flags: auxiliary queue/buffer management flags. * @count: requested buffer count. * @requested_planes: number of planes requested. * @requested_sizes: array with the size of the planes. @@ -794,7 +791,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, * Return: returns zero on success; an error code otherwise. */ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, - unsigned int flags, unsigned int *count, + unsigned int *count, unsigned int requested_planes, const unsigned int requested_sizes[]); diff --git a/include/net/act_api.h b/include/net/act_api.h index cb382a89ea58..87214927314a 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -166,8 +166,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, u32 flags); -void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a); - void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); diff --git a/include/net/flow.h b/include/net/flow.h index 929d3ca614d0..b2531df3f65f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -116,6 +116,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif, fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = sport; + fl4->flowi4_multipath_hash = 0; } /* Reset some input parameters after previous lookup */ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 6e5f1e1aa822..8899d7429ccb 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -138,6 +138,7 @@ genl_dumpit_info(struct netlink_callback *cb) * @cmd: command identifier * @internal_flags: flags used by the family * @flags: flags + * @validate: validation flags from enum genl_validate_flags * @doit: standard command callback * @start: start callback for dumps * @dumpit: callback for dumpers diff --git a/include/net/ip.h b/include/net/ip.h index b09c48d862cc..2a52787db64a 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -436,12 +436,18 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst, bool forwarding) { struct net *net = dev_net(dst->dev); + unsigned int mtu; if (net->ipv4.sysctl_ip_fwd_use_pmtu || ip_mtu_locked(dst) || !forwarding) return dst_mtu(dst); + /* 'forwarding = true' case should always honour route mtu */ + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + return mtu; + return min(READ_ONCE(dst->dev->mtu), IP_MAX_MTU); } diff --git a/include/net/netlink.h b/include/net/netlink.h index c0411f14fb53..271620f6bc7f 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -726,7 +726,6 @@ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected - * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() @@ -824,7 +823,6 @@ static inline int nla_validate_deprecated(const struct nlattr *head, int len, * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy - * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the @@ -1936,7 +1934,8 @@ void nla_get_range_signed(const struct nla_policy *pt, int netlink_policy_dump_start(const struct nla_policy *policy, unsigned int maxtype, unsigned long *state); -bool netlink_policy_dump_loop(unsigned long *state); +bool netlink_policy_dump_loop(unsigned long state); int netlink_policy_dump_write(struct sk_buff *skb, unsigned long state); +void netlink_policy_dump_free(unsigned long state); #endif diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index a1a8d45adb42..6c0806bd8d1e 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -8,6 +8,7 @@ struct netns_nftables { struct list_head tables; struct list_head commit_list; struct list_head module_list; + struct list_head notify_list; struct mutex commit_mutex; unsigned int base_seq; u8 gencursor; diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index b33f1aefad09..0bdff38eb4bb 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -226,12 +226,14 @@ struct sctp_sock { data_ready_signalled:1; atomic_t pd_mode; + + /* Fields after this point will be skipped on copies, like on accept + * and peeloff operations + */ + /* Receive to here while partial delivery is in effect. */ struct sk_buff_head pd_lobby; - /* These must be the last fields, as they will skipped on copies, - * like on accept and peeloff operations - */ struct list_head auto_asconf_list; int do_auto_asconf; }; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 3a41627cbdfe..08537aa14f7c 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -121,6 +121,9 @@ struct vxlanhdr_gbp { #define VXLAN_GBP_POLICY_APPLIED (BIT(3) << 16) #define VXLAN_GBP_ID_MASK (0xFFFF) +#define VXLAN_GBP_MASK (VXLAN_GBP_DONT_LEARN | VXLAN_GBP_POLICY_APPLIED | \ + VXLAN_GBP_ID_MASK) + /* * VXLAN Generic Protocol Extension (VXLAN_F_GPE): * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 2737d24ec244..9e806c781025 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1773,21 +1773,17 @@ static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_es static inline int xfrm_replay_clone(struct xfrm_state *x, struct xfrm_state *orig) { - x->replay_esn = kzalloc(xfrm_replay_state_esn_len(orig->replay_esn), + + x->replay_esn = kmemdup(orig->replay_esn, + xfrm_replay_state_esn_len(orig->replay_esn), GFP_KERNEL); if (!x->replay_esn) return -ENOMEM; - - x->replay_esn->bmp_len = orig->replay_esn->bmp_len; - x->replay_esn->replay_window = orig->replay_esn->replay_window; - - x->preplay_esn = kmemdup(x->replay_esn, - xfrm_replay_state_esn_len(x->replay_esn), + x->preplay_esn = kmemdup(orig->preplay_esn, + xfrm_replay_state_esn_len(orig->preplay_esn), GFP_KERNEL); - if (!x->preplay_esn) { - kfree(x->replay_esn); + if (!x->preplay_esn) return -ENOMEM; - } return 0; } diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index da369b12005f..0ac4e7fba086 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -566,6 +566,7 @@ struct ocelot_port { u8 ptp_cmd; struct sk_buff_head tx_skbs; u8 ts_id; + spinlock_t ts_id_lock; phy_interface_t phy_mode; @@ -677,6 +678,7 @@ void ocelot_configure_cpu(struct ocelot *ocelot, int npi, int ocelot_init(struct ocelot *ocelot); void ocelot_deinit(struct ocelot *ocelot); void ocelot_init_port(struct ocelot *ocelot, int port); +void ocelot_deinit_port(struct ocelot *ocelot, int port); /* DSA callbacks */ void ocelot_port_enable(struct ocelot *ocelot, int port, diff --git a/include/soc/mscc/ocelot_ana.h b/include/soc/mscc/ocelot_ana.h index 841c6ec22b64..1669481d9779 100644 --- a/include/soc/mscc/ocelot_ana.h +++ b/include/soc/mscc/ocelot_ana.h @@ -252,10 +252,10 @@ #define ANA_SG_CONFIG_REG_3_LIST_LENGTH_M GENMASK(18, 16) #define ANA_SG_CONFIG_REG_3_LIST_LENGTH_X(x) (((x) & GENMASK(18, 16)) >> 16) #define ANA_SG_CONFIG_REG_3_GATE_ENABLE BIT(20) -#define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 24) & GENMASK(27, 24)) -#define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(27, 24) -#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(27, 24)) >> 24) -#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(28) +#define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 21) & GENMASK(24, 21)) +#define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(24, 21) +#define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(24, 21)) >> 21) +#define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(25) #define ANA_SG_GCL_GS_CONFIG_RSZ 0x4 diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 5dcd24cb33ea..72ba36be9655 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -79,6 +79,7 @@ enum { ETHTOOL_MSG_TSINFO_GET_REPLY, ETHTOOL_MSG_CABLE_TEST_NTF, ETHTOOL_MSG_CABLE_TEST_TDR_NTF, + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, diff --git a/include/uapi/linux/rxrpc.h b/include/uapi/linux/rxrpc.h index 4accfa7e266d..8f8dc7a937a4 100644 --- a/include/uapi/linux/rxrpc.h +++ b/include/uapi/linux/rxrpc.h @@ -51,11 +51,11 @@ enum rxrpc_cmsg_type { RXRPC_BUSY = 6, /* -r: server busy received [terminal] */ RXRPC_LOCAL_ERROR = 7, /* -r: local error generated [terminal] */ RXRPC_NEW_CALL = 8, /* -r: [Service] new incoming call notification */ - RXRPC_ACCEPT = 9, /* s-: [Service] accept request */ RXRPC_EXCLUSIVE_CALL = 10, /* s-: Call should be on exclusive connection */ RXRPC_UPGRADE_SERVICE = 11, /* s-: Request service upgrade for client call */ RXRPC_TX_LENGTH = 12, /* s-: Total length of Tx data */ RXRPC_SET_CALL_TIMEOUT = 13, /* s-: Set one or more call timeouts */ + RXRPC_CHARGE_ACCEPT = 14, /* s-: Charge the accept pool with a user call ID */ RXRPC__SUPPORTED }; diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index cee9f8e6fce3..f84e7bcad6de 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -288,6 +288,7 @@ enum LINUX_MIB_TCPTIMEOUTREHASH, /* TCPTimeoutRehash */ LINUX_MIB_TCPDUPLICATEDATAREHASH, /* TCPDuplicateDataRehash */ LINUX_MIB_TCPDSACKRECVSEGS, /* TCPDSACKRecvSegs */ + LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c7b70ff53bc1..235db7754606 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -191,8 +191,6 @@ enum v4l2_memory { V4L2_MEMORY_DMABUF = 4, }; -#define V4L2_FLAG_MEMORY_NON_CONSISTENT (1 << 0) - /* see also http://vektor.theorem.ca/graphics/ycbcr/ */ enum v4l2_colorspace { /* @@ -949,10 +947,7 @@ struct v4l2_requestbuffers { __u32 type; /* enum v4l2_buf_type */ __u32 memory; /* enum v4l2_memory */ __u32 capabilities; - union { - __u32 flags; - __u32 reserved[1]; - }; + __u32 reserved[1]; }; /* capabilities for struct v4l2_requestbuffers and v4l2_create_buffers */ @@ -2456,9 +2451,6 @@ struct v4l2_dbg_chip_info { * @memory: enum v4l2_memory; buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. - * @flags: additional buffer management attributes (ignored unless the - * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability - * and configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers { @@ -2467,8 +2459,7 @@ struct v4l2_create_buffers { __u32 memory; struct v4l2_format format; __u32 capabilities; - __u32 flags; - __u32 reserved[6]; + __u32 reserved[7]; }; /* diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h index 39df751d0dc4..ac1b65470563 100644 --- a/include/xen/arm/page.h +++ b/include/xen/arm/page.h @@ -83,6 +83,9 @@ static inline unsigned long bfn_to_pfn(unsigned long bfn) }) #define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) +#define percpu_to_gfn(v) \ + (pfn_to_gfn(per_cpu_ptr_to_phys(v) >> XEN_PAGE_SHIFT)) + /* Only used in PV code. But ARM guests are always HVM. */ static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr) { diff --git a/init/main.c b/init/main.c index ae78fb68d231..e880b4ecb314 100644 --- a/init/main.c +++ b/init/main.c @@ -33,6 +33,7 @@ #include <linux/nmi.h> #include <linux/percpu.h> #include <linux/kmod.h> +#include <linux/kprobes.h> #include <linux/vmalloc.h> #include <linux/kernel_stat.h> #include <linux/start_kernel.h> @@ -303,7 +304,7 @@ static void * __init get_boot_config_from_initrd(u32 *_size, u32 *_csum) #ifdef CONFIG_BOOT_CONFIG -char xbc_namebuf[XBC_KEYLEN_MAX] __initdata; +static char xbc_namebuf[XBC_KEYLEN_MAX] __initdata; #define rest(dst, end) ((end) > (dst) ? (end) - (dst) : 0) @@ -1402,6 +1403,7 @@ static int __ref kernel_init(void *unused) kernel_init_freeable(); /* need to finish all async __init code before freeing the memory */ async_synchronize_full(); + kprobe_free_init_mem(); ftrace_free_init_mem(); free_initmem(); mark_readonly(); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 78dfff6a501b..7df28a45c66b 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1622,7 +1622,6 @@ struct bpf_iter_seq_hash_map_info { struct bpf_map *map; struct bpf_htab *htab; void *percpu_value_buf; // non-zero means percpu hash - unsigned long flags; u32 bucket_id; u32 skip_elems; }; @@ -1632,7 +1631,6 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, struct htab_elem *prev_elem) { const struct bpf_htab *htab = info->htab; - unsigned long flags = info->flags; u32 skip_elems = info->skip_elems; u32 bucket_id = info->bucket_id; struct hlist_nulls_head *head; @@ -1656,19 +1654,18 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, /* not found, unlock and go to the next bucket */ b = &htab->buckets[bucket_id++]; - htab_unlock_bucket(htab, b, flags); + rcu_read_unlock(); skip_elems = 0; } for (i = bucket_id; i < htab->n_buckets; i++) { b = &htab->buckets[i]; - flags = htab_lock_bucket(htab, b); + rcu_read_lock(); count = 0; head = &b->head; hlist_nulls_for_each_entry_rcu(elem, n, head, hash_node) { if (count >= skip_elems) { - info->flags = flags; info->bucket_id = i; info->skip_elems = count; return elem; @@ -1676,7 +1673,7 @@ bpf_hash_map_seq_find_next(struct bpf_iter_seq_hash_map_info *info, count++; } - htab_unlock_bucket(htab, b, flags); + rcu_read_unlock(); skip_elems = 0; } @@ -1754,14 +1751,10 @@ static int bpf_hash_map_seq_show(struct seq_file *seq, void *v) static void bpf_hash_map_seq_stop(struct seq_file *seq, void *v) { - struct bpf_iter_seq_hash_map_info *info = seq->private; - if (!v) (void)__bpf_hash_map_seq_show(seq, NULL); else - htab_unlock_bucket(info->htab, - &info->htab->buckets[info->bucket_id], - info->flags); + rcu_read_unlock(); } static int bpf_iter_init_hash_map(void *priv_data, diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index fb878ba3f22f..18f4969552ac 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -226,10 +226,12 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) else prev_key = key; + rcu_read_lock(); if (map->ops->map_get_next_key(map, prev_key, key)) { map_iter(m)->done = true; - return NULL; + key = NULL; } + rcu_read_unlock(); return key; } diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c index 3b495773de5a..11b3380887fa 100644 --- a/kernel/bpf/sysfs_btf.c +++ b/kernel/bpf/sysfs_btf.c @@ -30,15 +30,15 @@ static struct kobject *btf_kobj; static int __init btf_vmlinux_init(void) { - if (!__start_BTF) + bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; + + if (!__start_BTF || bin_attr_btf_vmlinux.size == 0) return 0; btf_kobj = kobject_create_and_add("btf", kernel_kobj); if (!btf_kobj) return -ENOMEM; - bin_attr_btf_vmlinux.size = __stop_BTF - __start_BTF; - return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_vmlinux); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 47e74f09fa37..fba52d9ec8fc 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5667,8 +5667,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, bool src_known = tnum_subreg_is_const(src_reg->var_off); bool dst_known = tnum_subreg_is_const(dst_reg->var_off); struct tnum var32_off = tnum_subreg(dst_reg->var_off); - s32 smin_val = src_reg->smin_value; - u32 umin_val = src_reg->umin_value; + s32 smin_val = src_reg->s32_min_value; + u32 umin_val = src_reg->u32_min_value; /* Assuming scalar64_min_max_or will be called so it is safe * to skip updating register for known case. @@ -5691,8 +5691,8 @@ static void scalar32_min_max_or(struct bpf_reg_state *dst_reg, /* ORing two positives gives a positive, so safe to * cast result into s64. */ - dst_reg->s32_min_value = dst_reg->umin_value; - dst_reg->s32_max_value = dst_reg->umax_value; + dst_reg->s32_min_value = dst_reg->u32_min_value; + dst_reg->s32_max_value = dst_reg->u32_max_value; } } diff --git a/kernel/events/core.c b/kernel/events/core.c index 7ed5248f0445..e8bf92202542 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -99,7 +99,7 @@ static void remote_function(void *data) * retry due to any failures in smp_call_function_single(), such as if the * task_cpu() goes offline concurrently. * - * returns @func return value or -ESRCH when the process isn't running + * returns @func return value or -ESRCH or -ENXIO when the process isn't running */ static int task_function_call(struct task_struct *p, remote_function_f func, void *info) @@ -115,7 +115,8 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info) for (;;) { ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1); - ret = !ret ? data.ret : -EAGAIN; + if (!ret) + ret = data.ret; if (ret != -EAGAIN) break; diff --git a/kernel/fork.c b/kernel/fork.c index 49677d668de4..da8d360fb032 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -589,7 +589,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) - retval = copy_page_range(mm, oldmm, mpnt); + retval = copy_page_range(mm, oldmm, mpnt, tmp); if (tmp->vm_ops && tmp->vm_ops->open) tmp->vm_ops->open(tmp); @@ -1011,6 +1011,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; + atomic_set(&mm->has_pinned, 0); atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 049da84e1952..e995541d277d 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2162,9 +2162,10 @@ static void kill_kprobe(struct kprobe *p) /* * The module is going away. We should disarm the kprobe which - * is using ftrace. + * is using ftrace, because ftrace framework is still available at + * MODULE_STATE_GOING notification. */ - if (kprobe_ftrace(p)) + if (kprobe_ftrace(p) && !kprobe_disabled(p) && !kprobes_all_disarmed) disarm_kprobe_ftrace(p); } @@ -2459,6 +2460,28 @@ static struct notifier_block kprobe_module_nb = { extern unsigned long __start_kprobe_blacklist[]; extern unsigned long __stop_kprobe_blacklist[]; +void kprobe_free_init_mem(void) +{ + void *start = (void *)(&__init_begin); + void *end = (void *)(&__init_end); + struct hlist_head *head; + struct kprobe *p; + int i; + + mutex_lock(&kprobe_mutex); + + /* Kill all kprobes on initmem */ + for (i = 0; i < KPROBE_TABLE_SIZE; i++) { + head = &kprobe_table[i]; + hlist_for_each_entry(p, head, hlist) { + if (start <= (void *)p->addr && (void *)p->addr < end) + kill_kprobe(p); + } + } + + mutex_unlock(&kprobe_mutex); +} + static int __init init_kprobes(void) { int i, err = 0; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 8ce77d9ac716..f78ee759af9c 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -673,6 +673,7 @@ void rcu_idle_enter(void) lockdep_assert_irqs_disabled(); rcu_eqs_enter(false); } +EXPORT_SYMBOL_GPL(rcu_idle_enter); #ifdef CONFIG_NO_HZ_FULL /** @@ -886,6 +887,7 @@ void rcu_idle_exit(void) rcu_eqs_exit(false); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_idle_exit); #ifdef CONFIG_NO_HZ_FULL /** diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e9fa580f3083..541453927c82 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2782,6 +2782,7 @@ static void ftrace_remove_trampoline_from_kallsyms(struct ftrace_ops *ops) { lockdep_assert_held(&ftrace_lock); list_del_rcu(&ops->list); + synchronize_rcu(); } /* @@ -2862,6 +2863,8 @@ int ftrace_startup(struct ftrace_ops *ops, int command) __unregister_ftrace_function(ops); ftrace_start_up--; ops->flags &= ~FTRACE_OPS_FL_ENABLED; + if (ops->flags & FTRACE_OPS_FL_DYNAMIC) + ftrace_trampoline_free(ops); return ret; } @@ -6990,16 +6993,14 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip, { int bit; - if ((op->flags & FTRACE_OPS_FL_RCU) && !rcu_is_watching()) - return; - bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX); if (bit < 0) return; preempt_disable_notrace(); - op->func(ip, parent_ip, op, regs); + if (!(op->flags & FTRACE_OPS_FL_RCU) || rcu_is_watching()) + op->func(ip, parent_ip, op, regs); preempt_enable_notrace(); trace_clear_recursion(bit); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f40d850ebabc..d3e5de717df2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3546,13 +3546,15 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, if (iter->ent && iter->ent != iter->temp) { if ((!iter->temp || iter->temp_size < iter->ent_size) && !WARN_ON_ONCE(iter->temp == static_temp_buf)) { - kfree(iter->temp); - iter->temp = kmalloc(iter->ent_size, GFP_KERNEL); - if (!iter->temp) + void *temp; + temp = kmalloc(iter->ent_size, GFP_KERNEL); + if (!temp) return NULL; + kfree(iter->temp); + iter->temp = temp; + iter->temp_size = iter->ent_size; } memcpy(iter->temp, iter->ent, iter->ent_size); - iter->temp_size = iter->ent_size; iter->ent = iter->temp; } entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts); @@ -3782,14 +3784,14 @@ unsigned long trace_total_entries(struct trace_array *tr) static void print_lat_help_header(struct seq_file *m) { - seq_puts(m, "# _------=> CPU# \n" - "# / _-----=> irqs-off \n" - "# | / _----=> need-resched \n" - "# || / _---=> hardirq/softirq \n" - "# ||| / _--=> preempt-depth \n" - "# |||| / delay \n" - "# cmd pid ||||| time | caller \n" - "# \\ / ||||| \\ | / \n"); + seq_puts(m, "# _------=> CPU# \n" + "# / _-----=> irqs-off \n" + "# | / _----=> need-resched \n" + "# || / _---=> hardirq/softirq \n" + "# ||| / _--=> preempt-depth \n" + "# |||| / delay \n" + "# cmd pid ||||| time | caller \n" + "# \\ / ||||| \\ | / \n"); } static void print_event_info(struct array_buffer *buf, struct seq_file *m) @@ -3810,26 +3812,26 @@ static void print_func_help_header(struct array_buffer *buf, struct seq_file *m, print_event_info(buf, m); - seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : ""); - seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); + seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? " TGID " : ""); + seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); } static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; - const char *space = " "; - int prec = tgid ? 10 : 2; + const char *space = " "; + int prec = tgid ? 12 : 2; print_event_info(buf, m); - seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space); - seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); - seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); - seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); - seq_printf(m, "# %.*s||| / delay\n", prec, space); - seq_printf(m, "# TASK-PID %.*sCPU# |||| TIMESTAMP FUNCTION\n", prec, " TGID "); - seq_printf(m, "# | | %.*s | |||| | |\n", prec, " | "); + seq_printf(m, "# %.*s _-----=> irqs-off\n", prec, space); + seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); + seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); + seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); + seq_printf(m, "# %.*s||| / delay\n", prec, space); + seq_printf(m, "# TASK-PID %.*s CPU# |||| TIMESTAMP FUNCTION\n", prec, " TGID "); + seq_printf(m, "# | | %.*s | |||| | |\n", prec, " | "); } void diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 0b933546142e..1b2ef6490229 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3865,7 +3865,6 @@ static int parse_var_defs(struct hist_trigger_data *hist_data) s = kstrdup(field_str, GFP_KERNEL); if (!s) { - kfree(hist_data->attrs->var_defs.name[n_vars]); ret = -ENOMEM; goto free; } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 4d1893564912..000e9dc224c6 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -497,7 +497,7 @@ lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) trace_find_cmdline(entry->pid, comm); - trace_seq_printf(s, "%8.8s-%-5d %3d", + trace_seq_printf(s, "%8.8s-%-7d %3d", comm, entry->pid, cpu); return trace_print_lat_fmt(s, entry); @@ -588,15 +588,15 @@ int trace_print_context(struct trace_iterator *iter) trace_find_cmdline(entry->pid, comm); - trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); + trace_seq_printf(s, "%16s-%-7d ", comm, entry->pid); if (tr->trace_flags & TRACE_ITER_RECORD_TGID) { unsigned int tgid = trace_find_tgid(entry->pid); if (!tgid) - trace_seq_printf(s, "(-----) "); + trace_seq_printf(s, "(-------) "); else - trace_seq_printf(s, "(%5d) ", tgid); + trace_seq_printf(s, "(%7d) ", tgid); } trace_seq_printf(s, "[%03d] ", iter->cpu); @@ -636,7 +636,7 @@ int trace_print_lat_context(struct trace_iterator *iter) trace_find_cmdline(entry->pid, comm); trace_seq_printf( - s, "%16s %5d %3d %d %08x %08lx ", + s, "%16s %7d %3d %d %08x %08lx ", comm, entry->pid, iter->cpu, entry->flags, entry->preempt_count, iter->idx); } else { @@ -917,7 +917,7 @@ static enum print_line_t trace_ctxwake_print(struct trace_iterator *iter, S = task_index_to_char(field->prev_state); trace_find_cmdline(field->next_pid, comm); trace_seq_printf(&iter->seq, - " %5d:%3d:%c %s [%03d] %5d:%3d:%c %s\n", + " %7d:%3d:%c %s [%03d] %7d:%3d:%c %s\n", field->prev_pid, field->prev_prio, S, delim, diff --git a/kernel/umh.c b/kernel/umh.c index fcf3ee803630..3f646613a9d3 100644 --- a/kernel/umh.c +++ b/kernel/umh.c @@ -14,6 +14,7 @@ #include <linux/cred.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/fs_struct.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/mount.h> @@ -72,6 +73,14 @@ static int call_usermodehelper_exec_async(void *data) spin_unlock_irq(¤t->sighand->siglock); /* + * Initial kernel threads share ther FS with init, in order to + * get the init root directory. But we've now created a new + * thread that is going to execve a user process and has its own + * 'struct fs_struct'. Reset umask to the default. + */ + current->fs->umask = 0022; + + /* * Our parent (unbound workqueue) runs with elevated scheduling * priority. Avoid propagating that into the userspace child. */ diff --git a/lib/bootconfig.c b/lib/bootconfig.c index 2c905a91d4eb..649ed44f199c 100644 --- a/lib/bootconfig.c +++ b/lib/bootconfig.c @@ -31,6 +31,8 @@ static size_t xbc_data_size __initdata; static struct xbc_node *last_parent __initdata; static const char *xbc_err_msg __initdata; static int xbc_err_pos __initdata; +static int open_brace[XBC_DEPTH_MAX] __initdata; +static int brace_index __initdata; static int __init xbc_parse_error(const char *msg, const char *p) { @@ -431,27 +433,27 @@ static char *skip_spaces_until_newline(char *p) return p; } -static int __init __xbc_open_brace(void) +static int __init __xbc_open_brace(char *p) { - /* Mark the last key as open brace */ - last_parent->next = XBC_NODE_MAX; + /* Push the last key as open brace */ + open_brace[brace_index++] = xbc_node_index(last_parent); + if (brace_index >= XBC_DEPTH_MAX) + return xbc_parse_error("Exceed max depth of braces", p); return 0; } static int __init __xbc_close_brace(char *p) { - struct xbc_node *node; - - if (!last_parent || last_parent->next != XBC_NODE_MAX) + brace_index--; + if (!last_parent || brace_index < 0 || + (open_brace[brace_index] != xbc_node_index(last_parent))) return xbc_parse_error("Unexpected closing brace", p); - node = last_parent; - node->next = 0; - do { - node = xbc_node_get_parent(node); - } while (node && node->next != XBC_NODE_MAX); - last_parent = node; + if (brace_index == 0) + last_parent = NULL; + else + last_parent = &xbc_nodes[open_brace[brace_index - 1]]; return 0; } @@ -492,8 +494,8 @@ static int __init __xbc_parse_value(char **__v, char **__n) break; } if (strchr(",;\n#}", c)) { - v = strim(v); *p++ = '\0'; + v = strim(v); break; } } @@ -661,7 +663,7 @@ static int __init xbc_open_brace(char **k, char *n) return ret; *k = n; - return __xbc_open_brace(); + return __xbc_open_brace(n - 1); } static int __init xbc_close_brace(char **k, char *n) @@ -681,6 +683,13 @@ static int __init xbc_verify_tree(void) int i, depth, len, wlen; struct xbc_node *n, *m; + /* Brace closing */ + if (brace_index) { + n = &xbc_nodes[open_brace[brace_index]]; + return xbc_parse_error("Brace is not closed", + xbc_node_get_data(n)); + } + /* Empty tree */ if (xbc_node_num == 0) { xbc_parse_error("Empty config", xbc_data); @@ -745,6 +754,7 @@ void __init xbc_destroy_all(void) xbc_node_num = 0; memblock_free(__pa(xbc_nodes), sizeof(struct xbc_node) * XBC_NODE_MAX); xbc_nodes = NULL; + brace_index = 0; } /** diff --git a/lib/fonts/font_10x18.c b/lib/fonts/font_10x18.c index 532f0ff89a96..0e2deac97da0 100644 --- a/lib/fonts/font_10x18.c +++ b/lib/fonts/font_10x18.c @@ -8,8 +8,8 @@ #define FONTDATAMAX 9216 -static const unsigned char fontdata_10x18[FONTDATAMAX] = { - +static struct font_data fontdata_10x18 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, 0x00, /* 0000000000 */ 0x00, 0x00, /* 0000000000 */ @@ -5129,8 +5129,7 @@ static const unsigned char fontdata_10x18[FONTDATAMAX] = { 0x00, 0x00, /* 0000000000 */ 0x00, 0x00, /* 0000000000 */ 0x00, 0x00, /* 0000000000 */ - -}; +} }; const struct font_desc font_10x18 = { @@ -5138,7 +5137,7 @@ const struct font_desc font_10x18 = { .name = "10x18", .width = 10, .height = 18, - .data = fontdata_10x18, + .data = fontdata_10x18.data, #ifdef __sparc__ .pref = 5, #else diff --git a/lib/fonts/font_6x10.c b/lib/fonts/font_6x10.c index 09b2cc03435b..87da8acd07db 100644 --- a/lib/fonts/font_6x10.c +++ b/lib/fonts/font_6x10.c @@ -1,8 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/font.h> -static const unsigned char fontdata_6x10[] = { +#define FONTDATAMAX 2560 +static struct font_data fontdata_6x10 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -3074,14 +3076,13 @@ static const unsigned char fontdata_6x10[] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_6x10 = { .idx = FONT6x10_IDX, .name = "6x10", .width = 6, .height = 10, - .data = fontdata_6x10, + .data = fontdata_6x10.data, .pref = 0, }; diff --git a/lib/fonts/font_6x11.c b/lib/fonts/font_6x11.c index d7136c33f1f0..5e975dfa10a5 100644 --- a/lib/fonts/font_6x11.c +++ b/lib/fonts/font_6x11.c @@ -9,8 +9,8 @@ #define FONTDATAMAX (11*256) -static const unsigned char fontdata_6x11[FONTDATAMAX] = { - +static struct font_data fontdata_6x11 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -3338,8 +3338,7 @@ static const unsigned char fontdata_6x11[FONTDATAMAX] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_vga_6x11 = { @@ -3347,7 +3346,7 @@ const struct font_desc font_vga_6x11 = { .name = "ProFont6x11", .width = 6, .height = 11, - .data = fontdata_6x11, + .data = fontdata_6x11.data, /* Try avoiding this font if possible unless on MAC */ .pref = -2000, }; diff --git a/lib/fonts/font_7x14.c b/lib/fonts/font_7x14.c index 89752d0b23e8..86d298f38505 100644 --- a/lib/fonts/font_7x14.c +++ b/lib/fonts/font_7x14.c @@ -8,8 +8,8 @@ #define FONTDATAMAX 3584 -static const unsigned char fontdata_7x14[FONTDATAMAX] = { - +static struct font_data fontdata_7x14 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 0000000 */ 0x00, /* 0000000 */ @@ -4105,8 +4105,7 @@ static const unsigned char fontdata_7x14[FONTDATAMAX] = { 0x00, /* 0000000 */ 0x00, /* 0000000 */ 0x00, /* 0000000 */ - -}; +} }; const struct font_desc font_7x14 = { @@ -4114,6 +4113,6 @@ const struct font_desc font_7x14 = { .name = "7x14", .width = 7, .height = 14, - .data = fontdata_7x14, + .data = fontdata_7x14.data, .pref = 0, }; diff --git a/lib/fonts/font_8x16.c b/lib/fonts/font_8x16.c index b7ab1f5fbdb8..37cedd36ca5e 100644 --- a/lib/fonts/font_8x16.c +++ b/lib/fonts/font_8x16.c @@ -10,8 +10,8 @@ #define FONTDATAMAX 4096 -static const unsigned char fontdata_8x16[FONTDATAMAX] = { - +static struct font_data fontdata_8x16 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -4619,8 +4619,7 @@ static const unsigned char fontdata_8x16[FONTDATAMAX] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_vga_8x16 = { @@ -4628,7 +4627,7 @@ const struct font_desc font_vga_8x16 = { .name = "VGA8x16", .width = 8, .height = 16, - .data = fontdata_8x16, + .data = fontdata_8x16.data, .pref = 0, }; EXPORT_SYMBOL(font_vga_8x16); diff --git a/lib/fonts/font_8x8.c b/lib/fonts/font_8x8.c index 2328ebc8bab5..8ab695538395 100644 --- a/lib/fonts/font_8x8.c +++ b/lib/fonts/font_8x8.c @@ -9,8 +9,8 @@ #define FONTDATAMAX 2048 -static const unsigned char fontdata_8x8[FONTDATAMAX] = { - +static struct font_data fontdata_8x8 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -2570,8 +2570,7 @@ static const unsigned char fontdata_8x8[FONTDATAMAX] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_vga_8x8 = { @@ -2579,6 +2578,6 @@ const struct font_desc font_vga_8x8 = { .name = "VGA8x8", .width = 8, .height = 8, - .data = fontdata_8x8, + .data = fontdata_8x8.data, .pref = 0, }; diff --git a/lib/fonts/font_acorn_8x8.c b/lib/fonts/font_acorn_8x8.c index 0ff0e85d4481..069b3e80c434 100644 --- a/lib/fonts/font_acorn_8x8.c +++ b/lib/fonts/font_acorn_8x8.c @@ -3,7 +3,10 @@ #include <linux/font.h> -static const unsigned char acorndata_8x8[] = { +#define FONTDATAMAX 2048 + +static struct font_data acorndata_8x8 = { +{ 0, 0, FONTDATAMAX, 0 }, { /* 00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* ^@ */ /* 01 */ 0x7e, 0x81, 0xa5, 0x81, 0xbd, 0x99, 0x81, 0x7e, /* ^A */ /* 02 */ 0x7e, 0xff, 0xbd, 0xff, 0xc3, 0xe7, 0xff, 0x7e, /* ^B */ @@ -260,14 +263,14 @@ static const unsigned char acorndata_8x8[] = { /* FD */ 0x38, 0x04, 0x18, 0x20, 0x3c, 0x00, 0x00, 0x00, /* FE */ 0x00, 0x00, 0x3c, 0x3c, 0x3c, 0x3c, 0x00, 0x00, /* FF */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 -}; +} }; const struct font_desc font_acorn_8x8 = { .idx = ACORN8x8_IDX, .name = "Acorn8x8", .width = 8, .height = 8, - .data = acorndata_8x8, + .data = acorndata_8x8.data, #ifdef CONFIG_ARCH_ACORN .pref = 20, #else diff --git a/lib/fonts/font_mini_4x6.c b/lib/fonts/font_mini_4x6.c index 838caa1cfef7..1449876c6a27 100644 --- a/lib/fonts/font_mini_4x6.c +++ b/lib/fonts/font_mini_4x6.c @@ -43,8 +43,8 @@ __END__; #define FONTDATAMAX 1536 -static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = { - +static struct font_data fontdata_mini_4x6 = { + { 0, 0, FONTDATAMAX, 0 }, { /*{*/ /* Char 0: ' ' */ 0xee, /*= [*** ] */ @@ -2145,14 +2145,14 @@ static const unsigned char fontdata_mini_4x6[FONTDATAMAX] = { 0xee, /*= [*** ] */ 0x00, /*= [ ] */ /*}*/ -}; +} }; const struct font_desc font_mini_4x6 = { .idx = MINI4x6_IDX, .name = "MINI4x6", .width = 4, .height = 6, - .data = fontdata_mini_4x6, + .data = fontdata_mini_4x6.data, .pref = 3, }; diff --git a/lib/fonts/font_pearl_8x8.c b/lib/fonts/font_pearl_8x8.c index b15d3c342c5b..32d65551e7ed 100644 --- a/lib/fonts/font_pearl_8x8.c +++ b/lib/fonts/font_pearl_8x8.c @@ -14,8 +14,8 @@ #define FONTDATAMAX 2048 -static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = { - +static struct font_data fontdata_pearl8x8 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ @@ -2575,14 +2575,13 @@ static const unsigned char fontdata_pearl8x8[FONTDATAMAX] = { 0x00, /* 00000000 */ 0x00, /* 00000000 */ 0x00, /* 00000000 */ - -}; +} }; const struct font_desc font_pearl_8x8 = { .idx = PEARL8x8_IDX, .name = "PEARL8x8", .width = 8, .height = 8, - .data = fontdata_pearl8x8, + .data = fontdata_pearl8x8.data, .pref = 2, }; diff --git a/lib/fonts/font_sun12x22.c b/lib/fonts/font_sun12x22.c index 955d6eee3959..641a6b4dca42 100644 --- a/lib/fonts/font_sun12x22.c +++ b/lib/fonts/font_sun12x22.c @@ -3,8 +3,8 @@ #define FONTDATAMAX 11264 -static const unsigned char fontdata_sun12x22[FONTDATAMAX] = { - +static struct font_data fontdata_sun12x22 = { + { 0, 0, FONTDATAMAX, 0 }, { /* 0 0x00 '^@' */ 0x00, 0x00, /* 000000000000 */ 0x00, 0x00, /* 000000000000 */ @@ -6148,8 +6148,7 @@ static const unsigned char fontdata_sun12x22[FONTDATAMAX] = { 0x00, 0x00, /* 000000000000 */ 0x00, 0x00, /* 000000000000 */ 0x00, 0x00, /* 000000000000 */ - -}; +} }; const struct font_desc font_sun_12x22 = { @@ -6157,7 +6156,7 @@ const struct font_desc font_sun_12x22 = { .name = "SUN12x22", .width = 12, .height = 22, - .data = fontdata_sun12x22, + .data = fontdata_sun12x22.data, #ifdef __sparc__ .pref = 5, #else diff --git a/lib/fonts/font_sun8x16.c b/lib/fonts/font_sun8x16.c index 03d71e53954a..193fe6d988e0 100644 --- a/lib/fonts/font_sun8x16.c +++ b/lib/fonts/font_sun8x16.c @@ -3,7 +3,8 @@ #define FONTDATAMAX 4096 -static const unsigned char fontdata_sun8x16[FONTDATAMAX] = { +static struct font_data fontdata_sun8x16 = { +{ 0, 0, FONTDATAMAX, 0 }, { /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x7e,0x81,0xa5,0x81,0x81,0xbd,0x99,0x81,0x81,0x7e,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x7e,0xff,0xdb,0xff,0xff,0xc3,0xe7,0xff,0xff,0x7e,0x00,0x00,0x00,0x00, @@ -260,14 +261,14 @@ static const unsigned char fontdata_sun8x16[FONTDATAMAX] = { /* */ 0x00,0x70,0xd8,0x30,0x60,0xc8,0xf8,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x00,0x00,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x7c,0x00,0x00,0x00,0x00,0x00, /* */ 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, -}; +} }; const struct font_desc font_sun_8x16 = { .idx = SUN8x16_IDX, .name = "SUN8x16", .width = 8, .height = 16, - .data = fontdata_sun8x16, + .data = fontdata_sun8x16.data, #ifdef __sparc__ .pref = 10, #else diff --git a/lib/fonts/font_ter16x32.c b/lib/fonts/font_ter16x32.c index 3f0cf1ccdf3a..91b9c283bd9c 100644 --- a/lib/fonts/font_ter16x32.c +++ b/lib/fonts/font_ter16x32.c @@ -4,8 +4,8 @@ #define FONTDATAMAX 16384 -static const unsigned char fontdata_ter16x32[FONTDATAMAX] = { - +static struct font_data fontdata_ter16x32 = { + { 0, 0, FONTDATAMAX, 0 }, { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x7f, 0xfc, 0x7f, 0xfc, 0x70, 0x1c, 0x70, 0x1c, 0x70, 0x1c, 0x70, 0x1c, @@ -2054,8 +2054,7 @@ static const unsigned char fontdata_ter16x32[FONTDATAMAX] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 255 */ - -}; +} }; const struct font_desc font_ter_16x32 = { @@ -2063,7 +2062,7 @@ const struct font_desc font_ter_16x32 = { .name = "TER16x32", .width = 16, .height = 32, - .data = fontdata_ter16x32, + .data = fontdata_ter16x32.data, #ifdef __sparc__ .pref = 5, #else diff --git a/lib/memregion.c b/lib/memregion.c index 77c85b5251da..be5cfa5a3b57 100644 --- a/lib/memregion.c +++ b/lib/memregion.c @@ -2,6 +2,7 @@ /* identifiers for device / performance-differentiated memory regions */ #include <linux/idr.h> #include <linux/types.h> +#include <linux/memregion.h> static DEFINE_IDA(memregion_ids); diff --git a/lib/random32.c b/lib/random32.c index 932345323af0..dfb9981ab798 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -49,7 +49,7 @@ static inline void prandom_state_selftest(void) } #endif -DEFINE_PER_CPU(struct rnd_state, net_rand_state); +DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; /** * prandom_u32_state - seeded pseudo-random number generator. diff --git a/lib/string.c b/lib/string.c index 6012c385fb31..4288e0158d47 100644 --- a/lib/string.c +++ b/lib/string.c @@ -272,6 +272,30 @@ ssize_t strscpy_pad(char *dest, const char *src, size_t count) } EXPORT_SYMBOL(strscpy_pad); +/** + * stpcpy - copy a string from src to dest returning a pointer to the new end + * of dest, including src's %NUL-terminator. May overrun dest. + * @dest: pointer to end of string being copied into. Must be large enough + * to receive copy. + * @src: pointer to the beginning of string being copied from. Must not overlap + * dest. + * + * stpcpy differs from strcpy in a key way: the return value is a pointer + * to the new %NUL-terminating character in @dest. (For strcpy, the return + * value is a pointer to the start of @dest). This interface is considered + * unsafe as it doesn't perform bounds checking of the inputs. As such it's + * not recommended for usage. Instead, its definition is provided in case + * the compiler lowers other libcalls to stpcpy. + */ +char *stpcpy(char *__restrict__ dest, const char *__restrict__ src); +char *stpcpy(char *__restrict__ dest, const char *__restrict__ src) +{ + while ((*dest++ = *src++) != '\0') + /* nothing */; + return --dest; +} +EXPORT_SYMBOL(stpcpy); + #ifndef __HAVE_ARCH_STRCAT /** * strcat - Append one %NUL-terminated string to another diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index c5a6fef7b45d..76c607ee6db5 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -434,7 +434,7 @@ static int __init test_rhltable(unsigned int entries) } else { if (WARN(err != -ENOENT, "removed non-existent element, error %d not %d", err, -ENOENT)) - continue; + continue; } } diff --git a/mm/filemap.c b/mm/filemap.c index 5202e38ab79e..99c49eeae71b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2365,7 +2365,11 @@ readpage: } if (!PageUptodate(page)) { - error = lock_page_killable(page); + if (iocb->ki_flags & IOCB_WAITQ) + error = lock_page_async(page, iocb->ki_waitq); + else + error = lock_page_killable(page); + if (unlikely(error)) goto readpage_error; if (!PageUptodate(page)) { @@ -1255,6 +1255,9 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, BUG_ON(*locked != 1); } + if (flags & FOLL_PIN) + atomic_set(&mm->has_pinned, 1); + /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior * is to set FOLL_GET if the caller wants pages[] filled in (but has @@ -2485,13 +2488,13 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 1; } -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, +static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; - pmdp = pmd_offset(&pud, addr); + pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = READ_ONCE(*pmdp); @@ -2528,13 +2531,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, return 1; } -static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&p4d, addr); + pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); @@ -2549,20 +2552,20 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(pud_val(pud)), addr, PUD_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pmd_range(pud, addr, next, flags, pages, nr)) + } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } -static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; - p4dp = p4d_offset(&pgd, addr); + p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); @@ -2574,7 +2577,7 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, P4D_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pud_range(p4d, addr, next, flags, pages, nr)) + } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); @@ -2602,7 +2605,7 @@ static void gup_pgd_range(unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, flags, pages, nr)) return; - } else if (!gup_p4d_range(pgd, addr, next, flags, pages, nr)) + } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } @@ -2660,6 +2663,9 @@ static int internal_get_user_pages_fast(unsigned long start, int nr_pages, FOLL_FAST_ONLY))) return -EINVAL; + if (gup_flags & FOLL_PIN) + atomic_set(¤t->mm->has_pinned, 1); + if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index faadc449cca5..da397779a6d4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1074,6 +1074,24 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); + + /* + * If this page is a potentially pinned page, split and retry the fault + * with smaller page size. Normally this should not happen because the + * userspace should use MADV_DONTFORK upon pinned regions. This is a + * best effort that the pinned pages won't be replaced by another + * random page during the coming copy-on-write. + */ + if (unlikely(is_cow_mapping(vma->vm_flags) && + atomic_read(&src_mm->has_pinned) && + page_maybe_dma_pinned(src_page))) { + pte_free(dst_mm, pgtable); + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + __split_huge_pmd(vma, src_pmd, addr, false, NULL); + return -EAGAIN; + } + get_page(src_page); page_dup_rmap(src_page, true); add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); @@ -1177,6 +1195,16 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* No huge zero pud yet */ } + /* Please refer to comments in copy_huge_pmd() */ + if (unlikely(is_cow_mapping(vma->vm_flags) && + atomic_read(&src_mm->has_pinned) && + page_maybe_dma_pinned(pud_page(pud)))) { + spin_unlock(src_ptl); + spin_unlock(dst_ptl); + __split_huge_pud(vma, src_pud, addr); + return -EAGAIN; + } + pudp_set_wrprotect(src_mm, addr, src_pud); pud = pud_mkold(pud_wrprotect(pud)); set_pud_at(dst_mm, addr, dst_pud, pud); diff --git a/mm/khugepaged.c b/mm/khugepaged.c index cfa0dba5fd3b..3a494cfa56d2 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -914,6 +914,18 @@ static struct page *khugepaged_alloc_hugepage(bool *wait) static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { + /* + * If the hpage allocated earlier was briefly exposed in page cache + * before collapse_file() failed, it is possible that racing lookups + * have not yet completed, and would then be unpleasantly surprised by + * finding the hpage reused for the same mapping at a different offset. + * Just release the previous allocation if there is any danger of that. + */ + if (*hpage && page_count(*hpage) > 1) { + put_page(*hpage); + *hpage = NULL; + } + if (!*hpage) *hpage = khugepaged_alloc_hugepage(wait); diff --git a/mm/madvise.c b/mm/madvise.c index d4aa5f776543..0e0d61003fc6 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -381,9 +381,9 @@ huge_unlock: return 0; } +regular_page: if (pmd_trans_unstable(pmd)) return 0; -regular_page: #endif tlb_change_page_size(tlb, PAGE_SIZE); orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cfa6cbad21d5..6877c765b8d0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1538,9 +1538,9 @@ static char *memory_stat_format(struct mem_cgroup *memcg) memcg_page_state(memcg, WORKINGSET_ACTIVATE_ANON)); seq_buf_printf(&s, "workingset_activate_file %lu\n", memcg_page_state(memcg, WORKINGSET_ACTIVATE_FILE)); - seq_buf_printf(&s, "workingset_restore %lu\n", + seq_buf_printf(&s, "workingset_restore_anon %lu\n", memcg_page_state(memcg, WORKINGSET_RESTORE_ANON)); - seq_buf_printf(&s, "workingset_restore %lu\n", + seq_buf_printf(&s, "workingset_restore_file %lu\n", memcg_page_state(memcg, WORKINGSET_RESTORE_FILE)); seq_buf_printf(&s, "workingset_nodereclaim %lu\n", memcg_page_state(memcg, WORKINGSET_NODERECLAIM)); diff --git a/mm/memory.c b/mm/memory.c index 469af373ae76..eeae590e526a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -695,84 +695,185 @@ out: * covered by this vma. */ -static inline unsigned long -copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, +static unsigned long +copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, unsigned long addr, int *rss) { unsigned long vm_flags = vma->vm_flags; pte_t pte = *src_pte; struct page *page; + swp_entry_t entry = pte_to_swp_entry(pte); + + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + rss[MM_SWAPENTS]++; + } else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); - /* pte contains position in swap or file, so copy. */ - if (unlikely(!pte_present(pte))) { - swp_entry_t entry = pte_to_swp_entry(pte); - - if (likely(!non_swap_entry(entry))) { - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - rss[MM_SWAPENTS]++; - } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - - rss[mm_counter(page)]++; - - if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both - * parent and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_soft_dirty(*src_pte)) - pte = pte_swp_mksoft_dirty(pte); - if (pte_swp_uffd_wp(*src_pte)) - pte = pte_swp_mkuffd_wp(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } - } else if (is_device_private_entry(entry)) { - page = device_private_entry_to_page(entry); + rss[mm_counter(page)]++; + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { /* - * Update rss count even for unaddressable pages, as - * they should treated just like normal pages in this - * respect. - * - * We will likely want to have some new rss counters - * for unaddressable pages, at some point. But for now - * keep things as they are. + * COW mappings require pages in both + * parent and child to be set to read. */ - get_page(page); - rss[mm_counter(page)]++; - page_dup_rmap(page, false); + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + if (pte_swp_uffd_wp(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); + } + } else if (is_device_private_entry(entry)) { + page = device_private_entry_to_page(entry); - /* - * We do not preserve soft-dirty information, because so - * far, checkpoint/restore is the only feature that - * requires that. And checkpoint/restore does not work - * when a device driver is involved (you cannot easily - * save and restore device driver state). - */ - if (is_write_device_private_entry(entry) && - is_cow_mapping(vm_flags)) { - make_device_private_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_uffd_wp(*src_pte)) - pte = pte_swp_mkuffd_wp(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } + /* + * Update rss count even for unaddressable pages, as + * they should treated just like normal pages in this + * respect. + * + * We will likely want to have some new rss counters + * for unaddressable pages, at some point. But for now + * keep things as they are. + */ + get_page(page); + rss[mm_counter(page)]++; + page_dup_rmap(page, false); + + /* + * We do not preserve soft-dirty information, because so + * far, checkpoint/restore is the only feature that + * requires that. And checkpoint/restore does not work + * when a device driver is involved (you cannot easily + * save and restore device driver state). + */ + if (is_write_device_private_entry(entry) && + is_cow_mapping(vm_flags)) { + make_device_private_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_uffd_wp(*src_pte)) + pte = pte_swp_mkuffd_wp(pte); + set_pte_at(src_mm, addr, src_pte, pte); } - goto out_set_pte; + } + set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy a present and normal page if necessary. + * + * NOTE! The usual case is that this doesn't need to do + * anything, and can just return a positive value. That + * will let the caller know that it can just increase + * the page refcount and re-use the pte the traditional + * way. + * + * But _if_ we need to copy it because it needs to be + * pinned in the parent (and the child should get its own + * copy rather than just a reference to the same page), + * we'll do that here and return zero to let the caller + * know we're done. + * + * And if we need a pre-allocated page but don't yet have + * one, return a negative error to let the preallocation + * code know so that it can do so outside the page table + * lock. + */ +static inline int +copy_present_page(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pte_t *dst_pte, pte_t *src_pte, + struct vm_area_struct *vma, struct vm_area_struct *new, + unsigned long addr, int *rss, struct page **prealloc, + pte_t pte, struct page *page) +{ + struct page *new_page; + + if (!is_cow_mapping(vma->vm_flags)) + return 1; + + /* + * What we want to do is to check whether this page may + * have been pinned by the parent process. If so, + * instead of wrprotect the pte on both sides, we copy + * the page immediately so that we'll always guarantee + * the pinned page won't be randomly replaced in the + * future. + * + * The page pinning checks are just "has this mm ever + * seen pinning", along with the (inexact) check of + * the page count. That might give false positives for + * for pinning, but it will work correctly. + */ + if (likely(!atomic_read(&src_mm->has_pinned))) + return 1; + if (likely(!page_maybe_dma_pinned(page))) + return 1; + + new_page = *prealloc; + if (!new_page) + return -EAGAIN; + + /* + * We have a prealloc page, all good! Take it + * over and copy the page & arm it. + */ + *prealloc = NULL; + copy_user_highpage(new_page, page, addr, vma); + __SetPageUptodate(new_page); + page_add_new_anon_rmap(new_page, new, addr, false); + lru_cache_add_inactive_or_unevictable(new_page, new); + rss[mm_counter(new_page)]++; + + /* All done, just insert the new page copy in the child */ + pte = mk_pte(new_page, new->vm_page_prot); + pte = maybe_mkwrite(pte_mkdirty(pte), new); + set_pte_at(dst_mm, addr, dst_pte, pte); + return 0; +} + +/* + * Copy one pte. Returns 0 if succeeded, or -EAGAIN if one preallocated page + * is required to copy this pte. + */ +static inline int +copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, + struct vm_area_struct *new, + unsigned long addr, int *rss, struct page **prealloc) +{ + unsigned long vm_flags = vma->vm_flags; + pte_t pte = *src_pte; + struct page *page; + + page = vm_normal_page(vma, addr, pte); + if (page) { + int retval; + + retval = copy_present_page(dst_mm, src_mm, + dst_pte, src_pte, + vma, new, + addr, rss, prealloc, + pte, page); + if (retval <= 0) + return retval; + + get_page(page); + page_dup_rmap(page, false); + rss[mm_counter(page)]++; } /* @@ -800,35 +901,51 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (!(vm_flags & VM_UFFD_WP)) pte = pte_clear_uffd_wp(pte); - page = vm_normal_page(vma, addr, pte); - if (page) { - get_page(page); - page_dup_rmap(page, false); - rss[mm_counter(page)]++; - } - -out_set_pte: set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } +static inline struct page * +page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma, + unsigned long addr) +{ + struct page *new_page; + + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, addr); + if (!new_page) + return NULL; + + if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) { + put_page(new_page); + return NULL; + } + cgroup_throttle_swaprate(new_page, GFP_KERNEL); + + return new_page; +} + static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, + struct vm_area_struct *new, unsigned long addr, unsigned long end) { pte_t *orig_src_pte, *orig_dst_pte; pte_t *src_pte, *dst_pte; spinlock_t *src_ptl, *dst_ptl; - int progress = 0; + int progress, ret = 0; int rss[NR_MM_COUNTERS]; swp_entry_t entry = (swp_entry_t){0}; + struct page *prealloc = NULL; again: + progress = 0; init_rss_vec(rss); dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); - if (!dst_pte) - return -ENOMEM; + if (!dst_pte) { + ret = -ENOMEM; + goto out; + } src_pte = pte_offset_map(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); @@ -851,10 +968,34 @@ again: progress++; continue; } - entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, + if (unlikely(!pte_present(*src_pte))) { + entry.val = copy_nonpresent_pte(dst_mm, src_mm, + dst_pte, src_pte, vma, addr, rss); - if (entry.val) + if (entry.val) + break; + progress += 8; + continue; + } + /* copy_present_pte() will clear `*prealloc' if consumed */ + ret = copy_present_pte(dst_mm, src_mm, dst_pte, src_pte, + vma, new, addr, rss, &prealloc); + /* + * If we need a pre-allocated page for this pte, drop the + * locks, allocate, and try again. + */ + if (unlikely(ret == -EAGAIN)) break; + if (unlikely(prealloc)) { + /* + * pre-alloc page cannot be reused by next time so as + * to strictly follow mempolicy (e.g., alloc_page_vma() + * will allocate page according to address). This + * could only happen if one pinned pte changed. + */ + put_page(prealloc); + prealloc = NULL; + } progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); @@ -866,17 +1007,30 @@ again: cond_resched(); if (entry.val) { - if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) + if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) { + ret = -ENOMEM; + goto out; + } + entry.val = 0; + } else if (ret) { + WARN_ON_ONCE(ret != -EAGAIN); + prealloc = page_copy_prealloc(src_mm, vma, addr); + if (!prealloc) return -ENOMEM; - progress = 0; + /* We've captured and resolved the error. Reset, try again. */ + ret = 0; } if (addr != end) goto again; - return 0; +out: + if (unlikely(prealloc)) + put_page(prealloc); + return ret; } static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma, + struct vm_area_struct *new, unsigned long addr, unsigned long end) { pmd_t *src_pmd, *dst_pmd; @@ -903,7 +1057,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src if (pmd_none_or_clear_bad(src_pmd)) continue; if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, - vma, addr, next)) + vma, new, addr, next)) return -ENOMEM; } while (dst_pmd++, src_pmd++, addr = next, addr != end); return 0; @@ -911,6 +1065,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma, + struct vm_area_struct *new, unsigned long addr, unsigned long end) { pud_t *src_pud, *dst_pud; @@ -937,7 +1092,7 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src if (pud_none_or_clear_bad(src_pud)) continue; if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud, - vma, addr, next)) + vma, new, addr, next)) return -ENOMEM; } while (dst_pud++, src_pud++, addr = next, addr != end); return 0; @@ -945,6 +1100,7 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + struct vm_area_struct *new, unsigned long addr, unsigned long end) { p4d_t *src_p4d, *dst_p4d; @@ -959,14 +1115,14 @@ static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src if (p4d_none_or_clear_bad(src_p4d)) continue; if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d, - vma, addr, next)) + vma, new, addr, next)) return -ENOMEM; } while (dst_p4d++, src_p4d++, addr = next, addr != end); return 0; } int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - struct vm_area_struct *vma) + struct vm_area_struct *vma, struct vm_area_struct *new) { pgd_t *src_pgd, *dst_pgd; unsigned long next; @@ -1021,7 +1177,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, if (pgd_none_or_clear_bad(src_pgd)) continue; if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd, - vma, addr, next))) { + vma, new, addr, next))) { ret = -ENOMEM; break; } @@ -2955,8 +3111,8 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf) * page count reference, and the page is locked, * it's dark out, and we're wearing sunglasses. Hit it. */ - wp_page_reuse(vmf); unlock_page(page); + wp_page_reuse(vmf); return VM_FAULT_WRITE; } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b11a269e2356..ce3e73e3a5c1 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -729,7 +729,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, * are reserved so nobody should be touching them so we should be safe */ memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, - MEMMAP_HOTPLUG, altmap); + MEMINIT_HOTPLUG, altmap); set_zone_contiguous(zone); } @@ -1080,7 +1080,8 @@ int __ref add_memory_resource(int nid, struct resource *res) } /* link memory sections under this node.*/ - ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1)); + ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1), + MEMINIT_HOTPLUG); BUG_ON(ret); /* create new memmap entry */ diff --git a/mm/migrate.c b/mm/migrate.c index aecb1433cf3c..04a98bb2f568 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1446,7 +1446,7 @@ retry: * Capture required information that might get lost * during migration. */ - is_thp = PageTransHuge(page); + is_thp = PageTransHuge(page) && !PageHuge(page); nr_subpages = thp_nr_pages(page); cond_resched(); @@ -1472,7 +1472,7 @@ retry: * we encounter them after the rest of the list * is processed. */ - if (PageTransHuge(page) && !PageHuge(page)) { + if (is_thp) { lock_page(page); rc = split_huge_page_to_list(page, from); unlock_page(page); @@ -1481,8 +1481,7 @@ retry: nr_thp_split++; goto retry; } - } - if (is_thp) { + nr_thp_failed++; nr_failed += nr_subpages; goto out; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index fab5e97dc9ca..6866533de8e6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3367,9 +3367,16 @@ struct page *rmqueue(struct zone *preferred_zone, struct page *page; if (likely(order == 0)) { - page = rmqueue_pcplist(preferred_zone, zone, gfp_flags, + /* + * MIGRATE_MOVABLE pcplist could have the pages on CMA area and + * we need to skip it when CMA area isn't allowed. + */ + if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA || + migratetype != MIGRATE_MOVABLE) { + page = rmqueue_pcplist(preferred_zone, zone, gfp_flags, migratetype, alloc_flags); - goto out; + goto out; + } } /* @@ -3381,7 +3388,13 @@ struct page *rmqueue(struct zone *preferred_zone, do { page = NULL; - if (alloc_flags & ALLOC_HARDER) { + /* + * order-0 request can reach here when the pcplist is skipped + * due to non-CMA allocation context. HIGHATOMIC area is + * reserved for high-order atomic allocation, so order-0 + * request should skip it. + */ + if (order > 0 && alloc_flags & ALLOC_HARDER) { page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC); if (page) trace_mm_page_alloc_zone_locked(page, order, migratetype); @@ -5975,7 +5988,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) * done. Non-atomic initialization, single-pass. */ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn, enum memmap_context context, + unsigned long start_pfn, enum meminit_context context, struct vmem_altmap *altmap) { unsigned long pfn, end_pfn = start_pfn + size; @@ -6007,7 +6020,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * There can be holes in boot-time mem_map[]s handed to this * function. They do not exist on hotplugged memory. */ - if (context == MEMMAP_EARLY) { + if (context == MEMINIT_EARLY) { if (overlap_memmap_init(zone, &pfn)) continue; if (defer_init(nid, pfn, end_pfn)) @@ -6016,7 +6029,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); - if (context == MEMMAP_HOTPLUG) + if (context == MEMINIT_HOTPLUG) __SetPageReserved(page); /* @@ -6099,7 +6112,7 @@ void __ref memmap_init_zone_device(struct zone *zone, * check here not to call set_pageblock_migratetype() against * pfn out of zone. * - * Please note that MEMMAP_HOTPLUG path doesn't clear memmap + * Please note that MEMINIT_HOTPLUG path doesn't clear memmap * because this is done early in section_activate() */ if (!(pfn & (pageblock_nr_pages - 1))) { @@ -6137,7 +6150,7 @@ void __meminit __weak memmap_init(unsigned long size, int nid, if (end_pfn > start_pfn) { size = end_pfn - start_pfn; memmap_init_zone(size, nid, zone, start_pfn, - MEMMAP_EARLY, NULL); + MEMINIT_EARLY, NULL); } } } diff --git a/mm/slab.c b/mm/slab.c index 3160dff6fd76..f658e86ec8ce 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1632,6 +1632,10 @@ static void slab_destroy(struct kmem_cache *cachep, struct page *page) kmem_cache_free(cachep->freelist_cache, freelist); } +/* + * Update the size of the caches before calling slabs_destroy as it may + * recursively call kfree. + */ static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list) { struct page *page, *n; @@ -2153,8 +2157,8 @@ static void do_drain(void *arg) spin_lock(&n->list_lock); free_block(cachep, ac->entry, ac->avail, node, &list); spin_unlock(&n->list_lock); - slabs_destroy(cachep, &list); ac->avail = 0; + slabs_destroy(cachep, &list); } static void drain_cpu_caches(struct kmem_cache *cachep) @@ -3402,9 +3406,9 @@ free_done: } #endif spin_unlock(&n->list_lock); - slabs_destroy(cachep, &list); ac->avail -= batchcount; memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail); + slabs_destroy(cachep, &list); } /* diff --git a/mm/slub.c b/mm/slub.c index d4177aecedf6..6d3574013b2f 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1413,10 +1413,6 @@ slab_flags_t kmem_cache_flags(unsigned int object_size, char *next_block; slab_flags_t block_flags; - /* If slub_debug = 0, it folds into the if conditional. */ - if (!slub_debug_string) - return flags | slub_debug; - len = strlen(name); next_block = slub_debug_string; /* Go through all blocks of debug options, see if any matches our slab's name */ @@ -1450,7 +1446,7 @@ slab_flags_t kmem_cache_flags(unsigned int object_size, } } - return slub_debug; + return flags | slub_debug; } #else /* !CONFIG_SLUB_DEBUG */ static inline void setup_object_debug(struct kmem_cache *s, diff --git a/mm/swapfile.c b/mm/swapfile.c index 12f59e641b5e..debc94155f74 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1078,7 +1078,7 @@ start_over: goto nextsi; } if (size == SWAPFILE_CLUSTER) { - if (!(si->flags & SWP_FS)) + if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 8500f56cbd10..c350ab63cd54 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -25,6 +25,7 @@ #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/netlink.h> +#include <linux/preempt.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> @@ -83,11 +84,12 @@ static inline u32 batadv_choose_claim(const void *data, u32 size) */ static inline u32 batadv_choose_backbone_gw(const void *data, u32 size) { - const struct batadv_bla_claim *claim = (struct batadv_bla_claim *)data; + const struct batadv_bla_backbone_gw *gw; u32 hash = 0; - hash = jhash(&claim->addr, sizeof(claim->addr), hash); - hash = jhash(&claim->vid, sizeof(claim->vid), hash); + gw = (struct batadv_bla_backbone_gw *)data; + hash = jhash(&gw->orig, sizeof(gw->orig), hash); + hash = jhash(&gw->vid, sizeof(gw->vid), hash); return hash % size; } @@ -1579,13 +1581,16 @@ int batadv_bla_init(struct batadv_priv *bat_priv) } /** - * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. + * batadv_bla_check_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the soft interface information - * @skb: contains the bcast_packet to be checked + * @skb: contains the multicast packet to be checked + * @payload_ptr: pointer to position inside the head buffer of the skb + * marking the start of the data to be CRC'ed + * @orig: originator mac address, NULL if unknown * - * check if it is on our broadcast list. Another gateway might - * have sent the same packet because it is connected to the same backbone, - * so we have to remove this duplicate. + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. * * This is performed by checking the CRC, which will tell us * with a good chance that it is the same packet. If it is furthermore @@ -1594,19 +1599,17 @@ int batadv_bla_init(struct batadv_priv *bat_priv) * * Return: true if a packet is in the duplicate list, false otherwise. */ -bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, - struct sk_buff *skb) +static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb, u8 *payload_ptr, + const u8 *orig) { - int i, curr; - __be32 crc; - struct batadv_bcast_packet *bcast_packet; struct batadv_bcast_duplist_entry *entry; bool ret = false; - - bcast_packet = (struct batadv_bcast_packet *)skb->data; + int i, curr; + __be32 crc; /* calculate the crc ... */ - crc = batadv_skb_crc32(skb, (u8 *)(bcast_packet + 1)); + crc = batadv_skb_crc32(skb, payload_ptr); spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); @@ -1625,8 +1628,21 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, if (entry->crc != crc) continue; - if (batadv_compare_eth(entry->orig, bcast_packet->orig)) - continue; + /* are the originators both known and not anonymous? */ + if (orig && !is_zero_ether_addr(orig) && + !is_zero_ether_addr(entry->orig)) { + /* If known, check if the new frame came from + * the same originator: + * We are safe to take identical frames from the + * same orig, if known, as multiplications in + * the mesh are detected via the (orig, seqno) pair. + * So we can be a bit more liberal here and allow + * identical frames from the same orig which the source + * host might have sent multiple times on purpose. + */ + if (batadv_compare_eth(entry->orig, orig)) + continue; + } /* this entry seems to match: same crc, not too old, * and from another gw. therefore return true to forbid it. @@ -1642,7 +1658,14 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, entry = &bat_priv->bla.bcast_duplist[curr]; entry->crc = crc; entry->entrytime = jiffies; - ether_addr_copy(entry->orig, bcast_packet->orig); + + /* known originator */ + if (orig) + ether_addr_copy(entry->orig, orig); + /* anonymous originator */ + else + eth_zero_addr(entry->orig); + bat_priv->bla.bcast_duplist_curr = curr; out: @@ -1652,6 +1675,48 @@ out: } /** + * batadv_bla_check_ucast_duplist() - Check if a frame is in the broadcast dup. + * @bat_priv: the bat priv with all the soft interface information + * @skb: contains the multicast packet to be checked, decapsulated from a + * unicast_packet + * + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. + * + * Return: true if a packet is in the duplicate list, false otherwise. + */ +static bool batadv_bla_check_ucast_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + return batadv_bla_check_duplist(bat_priv, skb, (u8 *)skb->data, NULL); +} + +/** + * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup. + * @bat_priv: the bat priv with all the soft interface information + * @skb: contains the bcast_packet to be checked + * + * Check if it is on our broadcast list. Another gateway might have sent the + * same packet because it is connected to the same backbone, so we have to + * remove this duplicate. + * + * Return: true if a packet is in the duplicate list, false otherwise. + */ +bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, + struct sk_buff *skb) +{ + struct batadv_bcast_packet *bcast_packet; + u8 *payload_ptr; + + bcast_packet = (struct batadv_bcast_packet *)skb->data; + payload_ptr = (u8 *)(bcast_packet + 1); + + return batadv_bla_check_duplist(bat_priv, skb, payload_ptr, + bcast_packet->orig); +} + +/** * batadv_bla_is_backbone_gw_orig() - Check if the originator is a gateway for * the VLAN identified by vid. * @bat_priv: the bat priv with all the soft interface information @@ -1812,7 +1877,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, * @bat_priv: the bat priv with all the soft interface information * @skb: the frame to be checked * @vid: the VLAN ID of the frame - * @is_bcast: the packet came in a broadcast packet type. + * @packet_type: the batman packet type this frame came in * * batadv_bla_rx avoidance checks if: * * we have to race for a claim @@ -1824,7 +1889,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb, * further process the skb. */ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid, bool is_bcast) + unsigned short vid, int packet_type) { struct batadv_bla_backbone_gw *backbone_gw; struct ethhdr *ethhdr; @@ -1846,9 +1911,32 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto handled; if (unlikely(atomic_read(&bat_priv->bla.num_requests))) - /* don't allow broadcasts while requests are in flight */ - if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) - goto handled; + /* don't allow multicast packets while requests are in flight */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + /* Both broadcast flooding or multicast-via-unicasts + * delivery might send to multiple backbone gateways + * sharing the same LAN and therefore need to coordinate + * which backbone gateway forwards into the LAN, + * by claiming the payload source address. + * + * Broadcast flooding and multicast-via-unicasts + * delivery use the following two batman packet types. + * Note: explicitly exclude BATADV_UNICAST_4ADDR, + * as the DHCP gateway feature will send explicitly + * to only one BLA gateway, so the claiming process + * should be avoided there. + */ + if (packet_type == BATADV_BCAST || + packet_type == BATADV_UNICAST) + goto handled; + + /* potential duplicates from foreign BLA backbone gateways via + * multicast-in-unicast packets + */ + if (is_multicast_ether_addr(ethhdr->h_dest) && + packet_type == BATADV_UNICAST && + batadv_bla_check_ucast_duplist(bat_priv, skb)) + goto handled; ether_addr_copy(search_claim.addr, ethhdr->h_source); search_claim.vid = vid; @@ -1883,13 +1971,14 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, goto allow; } - /* if it is a broadcast ... */ - if (is_multicast_ether_addr(ethhdr->h_dest) && is_bcast) { + /* if it is a multicast ... */ + if (is_multicast_ether_addr(ethhdr->h_dest) && + (packet_type == BATADV_BCAST || packet_type == BATADV_UNICAST)) { /* ... drop it. the responsible gateway is in charge. * - * We need to check is_bcast because with the gateway + * We need to check packet type because with the gateway * feature, broadcasts (like DHCP requests) may be sent - * using a unicast packet type. + * using a unicast 4 address packet type. See comment above. */ goto handled; } else { diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 41edb2c4a327..a81c41b636f9 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -35,7 +35,7 @@ static inline bool batadv_bla_is_loopdetect_mac(const uint8_t *mac) #ifdef CONFIG_BATMAN_ADV_BLA bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, - unsigned short vid, bool is_bcast); + unsigned short vid, int packet_type); bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); bool batadv_bla_is_backbone_gw(struct sk_buff *skb, @@ -66,7 +66,7 @@ bool batadv_bla_check_claim(struct batadv_priv *bat_priv, u8 *addr, static inline bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid, - bool is_bcast) + int packet_type) { return false; } diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index bdc4a1fba1c6..ca24a2e522b7 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -51,6 +51,7 @@ #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> +#include "bridge_loop_avoidance.h" #include "hard-interface.h" #include "hash.h" #include "log.h" @@ -1435,6 +1436,35 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, } /** + * batadv_mcast_forw_send_orig() - send a multicast packet to an originator + * @bat_priv: the bat priv with all the soft interface information + * @skb: the multicast packet to send + * @vid: the vlan identifier + * @orig_node: the originator to send the packet to + * + * Return: NET_XMIT_DROP in case of error or NET_XMIT_SUCCESS otherwise. + */ +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + /* Avoid sending multicast-in-unicast packets to other BLA + * gateways - they already got the frame from the LAN side + * we share with them. + * TODO: Refactor to take BLA into account earlier, to avoid + * reducing the mcast_fanout count. + */ + if (batadv_bla_is_backbone_gw_orig(bat_priv, orig_node->orig, vid)) { + dev_kfree_skb(skb); + return NET_XMIT_SUCCESS; + } + + return batadv_send_skb_unicast(bat_priv, skb, BATADV_UNICAST, 0, + orig_node, vid); +} + +/** * batadv_mcast_forw_tt() - forwards a packet to multicast listeners * @bat_priv: the bat priv with all the soft interface information * @skb: the multicast packet to transmit @@ -1471,8 +1501,8 @@ batadv_mcast_forw_tt(struct batadv_priv *bat_priv, struct sk_buff *skb, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_entry->orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, + orig_entry->orig_node); } rcu_read_unlock(); @@ -1513,8 +1543,7 @@ batadv_mcast_forw_want_all_ipv4(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1551,8 +1580,7 @@ batadv_mcast_forw_want_all_ipv6(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1618,8 +1646,7 @@ batadv_mcast_forw_want_all_rtr4(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; @@ -1656,8 +1683,7 @@ batadv_mcast_forw_want_all_rtr6(struct batadv_priv *bat_priv, break; } - batadv_send_skb_unicast(bat_priv, newskb, BATADV_UNICAST, 0, - orig_node, vid); + batadv_mcast_forw_send_orig(bat_priv, newskb, vid, orig_node); } rcu_read_unlock(); return ret; diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index ebf825991ecd..3e114bc5ca3b 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -46,6 +46,11 @@ enum batadv_forw_mode batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, struct batadv_orig_node **mcast_single_orig); +int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node); + int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid); @@ -72,6 +77,16 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb, } static inline int +batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv, + struct sk_buff *skb, + unsigned short vid, + struct batadv_orig_node *orig_node) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} + +static inline int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb, unsigned short vid) { diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index 27cdf5e4349a..9e5c71e406ff 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -826,6 +826,10 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv, vid = batadv_get_vid(skb, hdr_len); ethhdr = (struct ethhdr *)(skb->data + hdr_len); + /* do not reroute multicast frames in a unicast header */ + if (is_multicast_ether_addr(ethhdr->h_dest)) + return true; + /* check if the destination client was served by this node and it is now * roaming. In this case, it means that the node has got a ROAM_ADV * message and that it knows the new destination in the mesh to re-route diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 23833a0ba5e6..cdde943c1b83 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -364,9 +364,8 @@ send: goto dropped; ret = batadv_send_skb_via_gw(bat_priv, skb, vid); } else if (mcast_single_orig) { - ret = batadv_send_skb_unicast(bat_priv, skb, - BATADV_UNICAST, 0, - mcast_single_orig, vid); + ret = batadv_mcast_forw_send_orig(bat_priv, skb, vid, + mcast_single_orig); } else if (forw_mode == BATADV_FORW_SOME) { ret = batadv_mcast_forw_send(bat_priv, skb, vid); } else { @@ -425,10 +424,10 @@ void batadv_interface_rx(struct net_device *soft_iface, struct vlan_ethhdr *vhdr; struct ethhdr *ethhdr; unsigned short vid; - bool is_bcast; + int packet_type; batadv_bcast_packet = (struct batadv_bcast_packet *)skb->data; - is_bcast = (batadv_bcast_packet->packet_type == BATADV_BCAST); + packet_type = batadv_bcast_packet->packet_type; skb_pull_rcsum(skb, hdr_size); skb_reset_mac_header(skb); @@ -471,7 +470,7 @@ void batadv_interface_rx(struct net_device *soft_iface, /* Let the bridge loop avoidance check the packet. If will * not handle it, we can safely push it up. */ - if (batadv_bla_rx(bat_priv, skb, vid, is_bcast)) + if (batadv_bla_rx(bat_priv, skb, vid, packet_type)) goto out; if (orig_node) diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index b18cdf03edb3..dfec65eca8a6 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -88,9 +88,10 @@ static void br_arp_send(struct net_bridge *br, struct net_bridge_port *p, } } -static int br_chk_addr_ip(struct net_device *dev, void *data) +static int br_chk_addr_ip(struct net_device *dev, + struct netdev_nested_priv *priv) { - __be32 ip = *(__be32 *)data; + __be32 ip = *(__be32 *)priv->data; struct in_device *in_dev; __be32 addr = 0; @@ -107,11 +108,15 @@ static int br_chk_addr_ip(struct net_device *dev, void *data) static bool br_is_local_ip(struct net_device *dev, __be32 ip) { - if (br_chk_addr_ip(dev, &ip)) + struct netdev_nested_priv priv = { + .data = (void *)&ip, + }; + + if (br_chk_addr_ip(dev, &priv)) return true; /* check if ip is configured on upper dev */ - if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &ip)) + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip, &priv)) return true; return false; @@ -361,9 +366,10 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, } } -static int br_chk_addr_ip6(struct net_device *dev, void *data) +static int br_chk_addr_ip6(struct net_device *dev, + struct netdev_nested_priv *priv) { - struct in6_addr *addr = (struct in6_addr *)data; + struct in6_addr *addr = (struct in6_addr *)priv->data; if (ipv6_chk_addr(dev_net(dev), addr, dev, 0)) return 1; @@ -374,11 +380,15 @@ static int br_chk_addr_ip6(struct net_device *dev, void *data) static bool br_is_local_ip6(struct net_device *dev, struct in6_addr *addr) { - if (br_chk_addr_ip6(dev, addr)) + struct netdev_nested_priv priv = { + .data = (void *)addr, + }; + + if (br_chk_addr_ip6(dev, &priv)) return true; /* check if ip is configured on upper dev */ - if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, addr)) + if (netdev_walk_all_upper_dev_rcu(dev, br_chk_addr_ip6, &priv)) return true; return false; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 9db504baa094..32ac8343b0ba 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -413,6 +413,8 @@ void br_fdb_delete_by_port(struct net_bridge *br, if (!do_all) if (test_bit(BR_FDB_STATIC, &f->flags) || + (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &f->flags) && + !test_bit(BR_FDB_OFFLOADED, &f->flags)) || (vid && f->key.vlan_id != vid)) continue; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 147d52596e17..da310f0ca725 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -380,6 +380,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, u32 filter_mask, const struct net_device *dev) { u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; + struct nlattr *af = NULL; struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; @@ -423,11 +424,18 @@ static int br_fill_ifinfo(struct sk_buff *skb, nla_nest_end(skb, nest); } + if (filter_mask & (RTEXT_FILTER_BRVLAN | + RTEXT_FILTER_BRVLAN_COMPRESSED | + RTEXT_FILTER_MRP)) { + af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); + if (!af) + goto nla_put_failure; + } + /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { struct net_bridge_vlan_group *vg; - struct nlattr *af; int err; /* RCU needed because of the VLAN locking rules (rcu || rtnl) */ @@ -441,11 +449,6 @@ static int br_fill_ifinfo(struct sk_buff *skb, rcu_read_unlock(); goto done; } - af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); - if (!af) { - rcu_read_unlock(); - goto nla_put_failure; - } if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) err = br_fill_ifvlaninfo_compressed(skb, vg); else @@ -456,32 +459,25 @@ static int br_fill_ifinfo(struct sk_buff *skb, rcu_read_unlock(); if (err) goto nla_put_failure; - - nla_nest_end(skb, af); } if (filter_mask & RTEXT_FILTER_MRP) { - struct nlattr *af; int err; if (!br_mrp_enabled(br) || port) goto done; - af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); - if (!af) - goto nla_put_failure; - rcu_read_lock(); err = br_mrp_fill_info(skb, br); rcu_read_unlock(); if (err) goto nla_put_failure; - - nla_nest_end(skb, af); } done: + if (af) + nla_nest_end(skb, af); nlmsg_end(skb, nlh); return 0; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index f9092c71225f..ee8780080be5 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1288,11 +1288,13 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, } } -static int __br_vlan_get_pvid(const struct net_device *dev, - struct net_bridge_port *p, u16 *p_pvid) +int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) { struct net_bridge_vlan_group *vg; + struct net_bridge_port *p; + ASSERT_RTNL(); + p = br_port_get_check_rtnl(dev); if (p) vg = nbp_vlan_group(p); else if (netif_is_bridge_master(dev)) @@ -1303,18 +1305,23 @@ static int __br_vlan_get_pvid(const struct net_device *dev, *p_pvid = br_get_pvid(vg); return 0; } - -int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) -{ - ASSERT_RTNL(); - - return __br_vlan_get_pvid(dev, br_port_get_check_rtnl(dev), p_pvid); -} EXPORT_SYMBOL_GPL(br_vlan_get_pvid); int br_vlan_get_pvid_rcu(const struct net_device *dev, u16 *p_pvid) { - return __br_vlan_get_pvid(dev, br_port_get_check_rcu(dev), p_pvid); + struct net_bridge_vlan_group *vg; + struct net_bridge_port *p; + + p = br_port_get_check_rcu(dev); + if (p) + vg = nbp_vlan_group_rcu(p); + else if (netif_is_bridge_master(dev)) + vg = br_vlan_group_rcu(netdev_priv(dev)); + else + return -EINVAL; + + *p_pvid = br_get_pvid(vg); + return 0; } EXPORT_SYMBOL_GPL(br_vlan_get_pvid_rcu); @@ -1353,7 +1360,7 @@ static int br_vlan_is_bind_vlan_dev(const struct net_device *dev) } static int br_vlan_is_bind_vlan_dev_fn(struct net_device *dev, - __always_unused void *data) + __always_unused struct netdev_nested_priv *priv) { return br_vlan_is_bind_vlan_dev(dev); } @@ -1376,9 +1383,9 @@ struct br_vlan_bind_walk_data { }; static int br_vlan_match_bind_vlan_dev_fn(struct net_device *dev, - void *data_in) + struct netdev_nested_priv *priv) { - struct br_vlan_bind_walk_data *data = data_in; + struct br_vlan_bind_walk_data *data = priv->data; int found = 0; if (br_vlan_is_bind_vlan_dev(dev) && @@ -1396,10 +1403,13 @@ br_vlan_get_upper_bind_vlan_dev(struct net_device *dev, u16 vid) struct br_vlan_bind_walk_data data = { .vid = vid, }; + struct netdev_nested_priv priv = { + .data = (void *)&data, + }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_match_bind_vlan_dev_fn, - &data); + &priv); rcu_read_unlock(); return data.result; @@ -1480,9 +1490,9 @@ struct br_vlan_link_state_walk_data { }; static int br_vlan_link_state_change_fn(struct net_device *vlan_dev, - void *data_in) + struct netdev_nested_priv *priv) { - struct br_vlan_link_state_walk_data *data = data_in; + struct br_vlan_link_state_walk_data *data = priv->data; if (br_vlan_is_bind_vlan_dev(vlan_dev)) br_vlan_set_vlan_dev_state(data->br, vlan_dev); @@ -1496,10 +1506,13 @@ static void br_vlan_link_state_change(struct net_device *dev, struct br_vlan_link_state_walk_data data = { .br = br }; + struct netdev_nested_priv priv = { + .data = (void *)&data, + }; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(dev, br_vlan_link_state_change_fn, - &data); + &priv); rcu_read_unlock(); } diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index bdfd66ba3843..d4d7a0e52491 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -575,7 +575,7 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, * coalescing neighboring slab objects into a single frag which * triggers one of hardened usercopy checks. */ - if (page_count(page) >= 1 && !PageSlab(page)) + if (sendpage_ok(page)) sendpage = sock->ops->sendpage; else sendpage = sock_no_sendpage; diff --git a/net/core/dev.c b/net/core/dev.c index 4086d335978c..4906b44af850 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6812,9 +6812,10 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, return NULL; } -static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data) +static int ____netdev_has_upper_dev(struct net_device *upper_dev, + struct netdev_nested_priv *priv) { - struct net_device *dev = data; + struct net_device *dev = (struct net_device *)priv->data; return upper_dev == dev; } @@ -6831,10 +6832,14 @@ static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data) bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_nested_priv priv = { + .data = (void *)upper_dev, + }; + ASSERT_RTNL(); return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, - upper_dev); + &priv); } EXPORT_SYMBOL(netdev_has_upper_dev); @@ -6851,8 +6856,12 @@ EXPORT_SYMBOL(netdev_has_upper_dev); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_nested_priv priv = { + .data = (void *)upper_dev, + }; + return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, - upper_dev); + &priv); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); @@ -6997,8 +7006,8 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, static int __netdev_walk_all_upper_dev(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7010,7 +7019,7 @@ static int __netdev_walk_all_upper_dev(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7046,8 +7055,8 @@ static int __netdev_walk_all_upper_dev(struct net_device *dev, int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7058,7 +7067,7 @@ int netdev_walk_all_upper_dev_rcu(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7094,10 +7103,15 @@ EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); static bool __netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { + struct netdev_nested_priv priv = { + .flags = 0, + .data = (void *)upper_dev, + }; + ASSERT_RTNL(); return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, - upper_dev); + &priv); } /** @@ -7215,8 +7229,8 @@ static struct net_device *__netdev_next_lower_dev(struct net_device *dev, int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7227,7 +7241,7 @@ int netdev_walk_all_lower_dev(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7262,8 +7276,8 @@ EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); static int __netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7275,7 +7289,7 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7364,22 +7378,34 @@ static u8 __netdev_lower_depth(struct net_device *dev) return max_depth; } -static int __netdev_update_upper_level(struct net_device *dev, void *data) +static int __netdev_update_upper_level(struct net_device *dev, + struct netdev_nested_priv *__unused) { dev->upper_level = __netdev_upper_depth(dev) + 1; return 0; } -static int __netdev_update_lower_level(struct net_device *dev, void *data) +static int __netdev_update_lower_level(struct net_device *dev, + struct netdev_nested_priv *priv) { dev->lower_level = __netdev_lower_depth(dev) + 1; + +#ifdef CONFIG_LOCKDEP + if (!priv) + return 0; + + if (priv->flags & NESTED_SYNC_IMM) + dev->nested_level = dev->lower_level - 1; + if (priv->flags & NESTED_SYNC_TODO) + net_unlink_todo(dev); +#endif return 0; } int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, - void *data), - void *data) + struct netdev_nested_priv *priv), + struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; @@ -7390,7 +7416,7 @@ int netdev_walk_all_lower_dev_rcu(struct net_device *dev, while (1) { if (now != dev) { - ret = fn(now, data); + ret = fn(now, priv); if (ret) return ret; } @@ -7650,6 +7676,7 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info, + struct netdev_nested_priv *priv, struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { @@ -7706,9 +7733,9 @@ static int __netdev_upper_dev_link(struct net_device *dev, __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); - __netdev_update_lower_level(upper_dev, NULL); + __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, - NULL); + priv); return 0; @@ -7733,8 +7760,13 @@ int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, + .data = NULL, + }; + return __netdev_upper_dev_link(dev, upper_dev, false, - NULL, NULL, extack); + NULL, NULL, &priv, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); @@ -7757,21 +7789,19 @@ int netdev_master_upper_dev_link(struct net_device *dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack) { + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, + .data = NULL, + }; + return __netdev_upper_dev_link(dev, upper_dev, true, - upper_priv, upper_info, extack); + upper_priv, upper_info, &priv, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); -/** - * netdev_upper_dev_unlink - Removes a link to upper device - * @dev: device - * @upper_dev: new upper device - * - * Removes a link to device which is upper to this one. The caller must hold - * the RTNL lock. - */ -void netdev_upper_dev_unlink(struct net_device *dev, - struct net_device *upper_dev) +static void __netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev, + struct netdev_nested_priv *priv) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { @@ -7796,9 +7826,28 @@ void netdev_upper_dev_unlink(struct net_device *dev, __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); - __netdev_update_lower_level(upper_dev, NULL); + __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, - NULL); + priv); +} + +/** + * netdev_upper_dev_unlink - Removes a link to upper device + * @dev: device + * @upper_dev: new upper device + * + * Removes a link to device which is upper to this one. The caller must hold + * the RTNL lock. + */ +void netdev_upper_dev_unlink(struct net_device *dev, + struct net_device *upper_dev) +{ + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_TODO, + .data = NULL, + }; + + __netdev_upper_dev_unlink(dev, upper_dev, &priv); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -7834,6 +7883,10 @@ int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *dev, struct netlink_ext_ack *extack) { + struct netdev_nested_priv priv = { + .flags = 0, + .data = NULL, + }; int err; if (!new_dev) @@ -7841,8 +7894,8 @@ int netdev_adjacent_change_prepare(struct net_device *old_dev, if (old_dev && new_dev != old_dev) netdev_adjacent_dev_disable(dev, old_dev); - - err = netdev_upper_dev_link(new_dev, dev, extack); + err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv, + extack); if (err) { if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); @@ -7857,6 +7910,11 @@ void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { + struct netdev_nested_priv priv = { + .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, + .data = NULL, + }; + if (!new_dev || !old_dev) return; @@ -7864,7 +7922,7 @@ void netdev_adjacent_change_commit(struct net_device *old_dev, return; netdev_adjacent_dev_enable(dev, old_dev); - netdev_upper_dev_unlink(old_dev, dev); + __netdev_upper_dev_unlink(old_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_commit); @@ -7872,13 +7930,18 @@ void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { + struct netdev_nested_priv priv = { + .flags = 0, + .data = NULL, + }; + if (!new_dev) return; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); - netdev_upper_dev_unlink(new_dev, dev); + __netdev_upper_dev_unlink(new_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_abort); @@ -8647,7 +8710,7 @@ int dev_get_port_parent_id(struct net_device *dev, if (!first.id_len) first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid))) - return -ENODATA; + return -EOPNOTSUPP; } return err; @@ -10062,6 +10125,19 @@ static void netdev_wait_allrefs(struct net_device *dev) void netdev_run_todo(void) { struct list_head list; +#ifdef CONFIG_LOCKDEP + struct list_head unlink_list; + + list_replace_init(&net_unlink_list, &unlink_list); + + while (!list_empty(&unlink_list)) { + struct net_device *dev = list_first_entry(&unlink_list, + struct net_device, + unlink_list); + list_del(&dev->unlink_list); + dev->nested_level = dev->lower_level - 1; + } +#endif /* Snapshot list, allow later requests */ list_replace_init(&net_todo_list, &list); @@ -10274,6 +10350,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_segs = GSO_MAX_SEGS; dev->upper_level = 1; dev->lower_level = 1; +#ifdef CONFIG_LOCKDEP + dev->nested_level = 0; + INIT_LIST_HEAD(&dev->unlink_list); +#endif INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c index 54cd568e7c2f..fa1c37ec40c9 100644 --- a/net/core/dev_addr_lists.c +++ b/net/core/dev_addr_lists.c @@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -700,7 +700,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from) * larger. */ netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->uc, &from->uc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); @@ -867,7 +867,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -897,7 +897,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from) if (to->addr_len != from->addr_len) return -EINVAL; - netif_addr_lock_nested(to); + netif_addr_lock(to); err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len); if (!err) __dev_set_rx_mode(to); @@ -922,7 +922,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from) /* See the above comments inside dev_uc_unsync(). */ netif_addr_lock_bh(from); - netif_addr_lock_nested(to); + netif_addr_lock(to); __hw_addr_unsync(&to->mc, &from->mc, to->addr_len); __dev_set_rx_mode(to); netif_addr_unlock(to); diff --git a/net/core/dst.c b/net/core/dst.c index d6b6ced0d451..0c01bd8d9d81 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -144,7 +144,7 @@ static void dst_destroy_rcu(struct rcu_head *head) /* Operations to mark dst as DEAD and clean up the net device referenced * by dst: - * 1. put the dst under loopback interface and discard all tx/rx packets + * 1. put the dst under blackhole interface and discard all tx/rx packets * on this route. * 2. release the net_device * This function should be called when removing routes from the fib tree diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 51678a528f85..7bcfb16854cb 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -16,7 +16,7 @@ #include <net/ip_tunnels.h> #include <linux/indirect_call_wrapper.h> -#ifdef CONFIG_IPV6_MULTIPLE_TABLES +#if defined(CONFIG_IPV6) && defined(CONFIG_IPV6_MULTIPLE_TABLES) #ifdef CONFIG_IP_MULTIPLE_TABLES #define INDIRECT_CALL_MT(f, f2, f1, ...) \ INDIRECT_CALL_INET(f, f2, f1, __VA_ARGS__) diff --git a/net/core/filter.c b/net/core/filter.c index 1f647ab986b6..b5f3faac5e3b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4838,6 +4838,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, fl4.saddr = params->ipv4_src; fl4.fl4_sport = params->sport; fl4.fl4_dport = params->dport; + fl4.flowi4_multipath_hash = 0; if (flags & BPF_FIB_LOOKUP_DIRECT) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; @@ -7065,8 +7066,6 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig, bool indirect = BPF_MODE(orig->code) == BPF_IND; struct bpf_insn *insn = insn_buf; - /* We're guaranteed here that CTX is in R6. */ - *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); if (!indirect) { *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); } else { @@ -7074,6 +7073,8 @@ static int bpf_gen_ld_abs(const struct bpf_insn *orig, if (orig->imm) *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); } + /* We're guaranteed here that CTX is in R6. */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); switch (BPF_SIZE(orig->code)) { case BPF_B: @@ -9522,7 +9523,7 @@ BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct tcp6_sock); - if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && + if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP && sk->sk_family == AF_INET6) return (unsigned long)sk; @@ -9540,7 +9541,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { BPF_CALL_1(bpf_skc_to_tcp_sock, struct sock *, sk) { - if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) + if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) return (unsigned long)sk; return (unsigned long)NULL; @@ -9557,13 +9558,19 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { BPF_CALL_1(bpf_skc_to_tcp_timewait_sock, struct sock *, sk) { + /* BTF types for tcp_timewait_sock and inet_timewait_sock are not + * generated if CONFIG_INET=n. Trigger an explicit generation here. + */ + BTF_TYPE_EMIT(struct inet_timewait_sock); + BTF_TYPE_EMIT(struct tcp_timewait_sock); + #ifdef CONFIG_INET - if (sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) + if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) - if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) + if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_TIME_WAIT) return (unsigned long)sk; #endif @@ -9582,12 +9589,12 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { BPF_CALL_1(bpf_skc_to_tcp_request_sock, struct sock *, sk) { #ifdef CONFIG_INET - if (sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) + if (sk && sk->sk_prot == &tcp_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif #if IS_BUILTIN(CONFIG_IPV6) - if (sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) + if (sk && sk->sk_prot == &tcpv6_prot && sk->sk_state == TCP_NEW_SYN_RECV) return (unsigned long)sk; #endif @@ -9609,7 +9616,7 @@ BPF_CALL_1(bpf_skc_to_udp6_sock, struct sock *, sk) * trigger an explicit type generation here. */ BTF_TYPE_EMIT(struct udp6_sock); - if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && + if (sk && sk_fullsock(sk) && sk->sk_protocol == IPPROTO_UDP && sk->sk_type == SOCK_DGRAM && sk->sk_family == AF_INET6) return (unsigned long)sk; diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index dcd61aca343e..944ab214e5ae 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -251,10 +251,10 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) if (refcount_read(&net->count) == 0) return NETNSA_NSID_NOT_ASSIGNED; - spin_lock(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); id = __peernet2id(net, peer); if (id >= 0) { - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); return id; } @@ -264,12 +264,12 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) * just been idr_remove()'d from there in cleanup_net(). */ if (!maybe_get_net(peer)) { - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); return NETNSA_NSID_NOT_ASSIGNED; } id = alloc_netid(net, peer, -1); - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); put_net(peer); if (id < 0) @@ -534,20 +534,20 @@ static void unhash_nsid(struct net *net, struct net *last) for_each_net(tmp) { int id; - spin_lock(&tmp->nsid_lock); + spin_lock_bh(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); - spin_unlock(&tmp->nsid_lock); + spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } - spin_lock(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); idr_destroy(&net->netns_ids); - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); } static LLIST_HEAD(cleanup_list); @@ -760,9 +760,9 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, return PTR_ERR(peer); } - spin_lock(&net->nsid_lock); + spin_lock_bh(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, @@ -771,7 +771,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, } err = alloc_netid(net, peer, nsid); - spin_unlock(&net->nsid_lock); + spin_unlock_bh(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6faf73d6a0f7..2b48cb0cc684 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5622,7 +5622,7 @@ int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, lse->label_stack_entry = mpls_lse; skb_postpush_rcsum(skb, lse, MPLS_HLEN); - if (ethernet) + if (ethernet && mac_len >= ETH_HLEN) skb_mod_eth_type(skb, eth_hdr(skb), mpls_proto); skb->protocol = mpls_proto; @@ -5662,7 +5662,7 @@ int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len, skb_reset_mac_header(skb); skb_set_network_header(skb, mac_len); - if (ethernet) { + if (ethernet && mac_len >= ETH_HLEN) { struct ethhdr *hdr; /* use mpls_hdr() to get ethertype to account for VLANs. */ diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 84dde5a2066e..16014ad19406 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1426,6 +1426,7 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; + int prio; int err; if (!ops) @@ -1475,6 +1476,13 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, struct dcbnl_buffer *buffer = nla_data(ieee[DCB_ATTR_DCB_BUFFER]); + for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) { + if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) { + err = -EINVAL; + goto err; + } + } + err = ops->dcbnl_setbuffer(netdev, buffer); if (err) goto err; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 9af1a2d0cec4..16e5f98d4882 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1799,15 +1799,27 @@ int dsa_slave_create(struct dsa_port *port) dsa_slave_notify(slave_dev, DSA_PORT_REGISTER); - ret = register_netdev(slave_dev); + rtnl_lock(); + + ret = register_netdevice(slave_dev); if (ret) { netdev_err(master, "error %d registering interface %s\n", ret, slave_dev->name); + rtnl_unlock(); goto out_phy; } + ret = netdev_upper_dev_link(master, slave_dev, NULL); + + rtnl_unlock(); + + if (ret) + goto out_unregister; + return 0; +out_unregister: + unregister_netdev(slave_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); @@ -1824,16 +1836,18 @@ out_free: void dsa_slave_destroy(struct net_device *slave_dev) { + struct net_device *master = dsa_slave_to_master(slave_dev); struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); netif_carrier_off(slave_dev); rtnl_lock(); + netdev_upper_dev_unlink(master, slave_dev); + unregister_netdevice(slave_dev); phylink_disconnect_phy(dp->pl); rtnl_unlock(); dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); - unregister_netdev(slave_dev); phylink_destroy(dp->pl); gro_cells_destroy(&p->gcells); free_percpu(p->stats64); diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 42f327c06dca..b4fc05cafaa6 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -160,11 +160,14 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, packing(injection, &qos_class, 19, 17, OCELOT_TAG_LEN, PACK, 0); if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + struct sk_buff *clone = DSA_SKB_CB(skb)->clone; + rew_op = ocelot_port->ptp_cmd; - if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) { - rew_op |= (ocelot_port->ts_id % 4) << 3; - ocelot_port->ts_id++; - } + /* Retrieve timestamp ID populated inside skb->cb[0] of the + * clone by ocelot_port_add_txtstamp_skb + */ + if (ocelot_port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + rew_op |= clone->cb[0] << 3; packing(injection, &rew_op, 125, 117, OCELOT_TAG_LEN, PACK, 0); } diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 5c2072765be7..0c3f54baec4e 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -866,7 +866,7 @@ static const struct genl_multicast_group ethtool_nl_mcgrps[] = { [ETHNL_MCGRP_MONITOR] = { .name = ETHTOOL_MCGRP_MONITOR_NAME }, }; -static struct genl_family ethtool_genl_family = { +static struct genl_family ethtool_genl_family __ro_after_init = { .name = ETHTOOL_GENL_NAME, .version = ETHTOOL_GENL_VERSION, .netnsok = true, diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c index 84f23289475b..d93bf2da0f34 100644 --- a/net/ethtool/tunnels.c +++ b/net/ethtool/tunnels.c @@ -200,7 +200,7 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info) reply_len = ret + ethnl_reply_header_size(); rskb = ethnl_reply_init(reply_len, req_info.dev, - ETHTOOL_MSG_TUNNEL_INFO_GET, + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY, ETHTOOL_A_TUNNEL_INFO_HEADER, info, &reply_payload); if (!rskb) { @@ -273,7 +273,7 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb) goto cont; ehdr = ethnl_dump_put(skb, cb, - ETHTOOL_MSG_TUNNEL_INFO_GET); + ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY); if (!ehdr) { ret = -EMSGSIZE; goto out; diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 06c3cd988760..0e4681cf71db 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -76,7 +76,7 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, proto = nla_get_u8(data[IFLA_HSR_PROTOCOL]); if (proto >= HSR_PROTOCOL_MAX) { - NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol\n"); + NL_SET_ERR_MSG_MOD(extack, "Unsupported protocol"); return -EINVAL; } @@ -84,14 +84,14 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, proto_version = HSR_V0; } else { if (proto == HSR_PROTOCOL_PRP) { - NL_SET_ERR_MSG_MOD(extack, "PRP version unsupported\n"); + NL_SET_ERR_MSG_MOD(extack, "PRP version unsupported"); return -EINVAL; } proto_version = nla_get_u8(data[IFLA_HSR_VERSION]); if (proto_version > HSR_V1) { NL_SET_ERR_MSG_MOD(extack, - "Only HSR version 0/1 supported\n"); + "Only HSR version 0/1 supported"); return -EINVAL; } } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 41079490a118..86a23e4a6a50 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -362,6 +362,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); + fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 4a98dd736270..f1bd95f243b3 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -186,8 +186,8 @@ errout: } EXPORT_SYMBOL_GPL(inet_diag_msg_attrs_fill); -static void inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen, - struct nlattr **req_nlas) +static int inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen, + struct nlattr **req_nlas) { struct nlattr *nla; int remaining; @@ -195,9 +195,13 @@ static void inet_diag_parse_attrs(const struct nlmsghdr *nlh, int hdrlen, nlmsg_for_each_attr(nla, nlh, hdrlen, remaining) { int type = nla_type(nla); + if (type == INET_DIAG_REQ_PROTOCOL && nla_len(nla) != sizeof(u32)) + return -EINVAL; + if (type < __INET_DIAG_REQ_MAX) req_nlas[type] = nla; } + return 0; } static int inet_diag_get_protocol(const struct inet_diag_req_v2 *req, @@ -574,7 +578,10 @@ static int inet_diag_cmd_exact(int cmd, struct sk_buff *in_skb, int err, protocol; memset(&dump_data, 0, sizeof(dump_data)); - inet_diag_parse_attrs(nlh, hdrlen, dump_data.req_nlas); + err = inet_diag_parse_attrs(nlh, hdrlen, dump_data.req_nlas); + if (err) + return err; + protocol = inet_diag_get_protocol(req, &dump_data); handler = inet_diag_lock_handler(protocol); @@ -1180,8 +1187,11 @@ static int __inet_diag_dump_start(struct netlink_callback *cb, int hdrlen) if (!cb_data) return -ENOMEM; - inet_diag_parse_attrs(nlh, hdrlen, cb_data->req_nlas); - + err = inet_diag_parse_attrs(nlh, hdrlen, cb_data->req_nlas); + if (err) { + kfree(cb_data); + return err; + } nla = cb_data->inet_diag_nla_bc; if (nla) { err = inet_diag_bc_audit(nla, skb); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 61f802d5350c..e6f2ada9e7d5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -74,6 +74,7 @@ #include <net/icmp.h> #include <net/checksum.h> #include <net/inetpeer.h> +#include <net/inet_ecn.h> #include <net/lwtunnel.h> #include <linux/bpf-cgroup.h> #include <linux/igmp.h> @@ -1703,7 +1704,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, if (IS_ERR(rt)) return; - inet_sk(sk)->tos = arg->tos; + inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 75c6013ff9a4..b2ea1a8c5fd6 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -554,6 +554,7 @@ static int ip_tun_parse_opts_vxlan(struct nlattr *attr, attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP]; md->gbp = nla_get_u32(attr); + md->gbp &= VXLAN_GBP_MASK; info->key.tun_flags |= TUNNEL_VXLAN_OPT; } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 49daaed89764..f687abb069fa 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -490,6 +490,7 @@ static struct xfrm_tunnel vti_ipip_handler __read_mostly = { .priority = 0, }; +#if IS_ENABLED(CONFIG_IPV6) static struct xfrm_tunnel vti_ipip6_handler __read_mostly = { .handler = vti_rcv_tunnel, .cb_handler = vti_rcv_cb, @@ -497,6 +498,7 @@ static struct xfrm_tunnel vti_ipip6_handler __read_mostly = { .priority = 0, }; #endif +#endif static int __net_init vti_init_net(struct net *net) { diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 1074df726ec0..8d5e1695b9aa 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -293,6 +293,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TcpTimeoutRehash", LINUX_MIB_TCPTIMEOUTREHASH), SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH), SNMP_MIB_ITEM("TCPDSACKRecvSegs", LINUX_MIB_TCPDSACKRECVSEGS), + SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8ca6bcab7b03..58642b29a499 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -786,8 +786,10 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { - struct fib_nh_common *nhc = FIB_RES_NHC(res); + struct fib_nh_common *nhc; + fib_select_path(net, &res, fl4, skb); + nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); @@ -1013,6 +1015,7 @@ out: kfree_skb(skb); static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; + struct net *net = dev_net(dst->dev); u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; @@ -1033,9 +1036,11 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) return; rcu_read_lock(); - if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) { - struct fib_nh_common *nhc = FIB_RES_NHC(res); + if (fib_lookup(net, fl4, &res, 0) == 0) { + struct fib_nh_common *nhc; + fib_select_path(net, &res, fl4, NULL); + nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } @@ -2147,6 +2152,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); + fl4.flowi4_multipath_hash = 0; if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; @@ -2667,8 +2673,6 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, fib_select_path(net, res, fl4, skb); dev_out = FIB_RES_DEV(*res); - fl4->flowi4_oif = dev_out->ifindex; - make_route: rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index f0794f0232ba..e03756631541 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -214,7 +214,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb, sock_rps_save_rxhash(child, skb); if (rsk_drop_req(req)) { - refcount_set(&req->rsk_refcnt, 2); + reqsk_put(req); return child; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 31f3b858db81..2135ee7c806d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -970,7 +970,8 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); if (IS_ENABLED(CONFIG_DEBUG_VM) && - WARN_ONCE(PageSlab(page), "page must not be a Slab one")) + WARN_ONCE(!sendpage_ok(page), + "page must not be a Slab one and have page_count > 0")) return -EINVAL; /* Wait for a connection to finish. One exception is TCP Fast Open diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 184ea556f50e..b1ce2054291d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -885,21 +885,34 @@ struct tcp_sacktag_state { struct rate_sample *rate; }; -/* Take a notice that peer is sending D-SACKs */ +/* Take a notice that peer is sending D-SACKs. Skip update of data delivery + * and spurious retransmission information if this DSACK is unlikely caused by + * sender's action: + * - DSACKed sequence range is larger than maximum receiver's window. + * - Total no. of DSACKed segments exceed the total no. of retransmitted segs. + */ static u32 tcp_dsack_seen(struct tcp_sock *tp, u32 start_seq, u32 end_seq, struct tcp_sacktag_state *state) { u32 seq_len, dup_segs = 1; - if (before(start_seq, end_seq)) { - seq_len = end_seq - start_seq; - if (seq_len > tp->mss_cache) - dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache); - } + if (!before(start_seq, end_seq)) + return 0; + + seq_len = end_seq - start_seq; + /* Dubious DSACK: DSACKed range greater than maximum advertised rwnd */ + if (seq_len > tp->max_window) + return 0; + if (seq_len > tp->mss_cache) + dup_segs = DIV_ROUND_UP(seq_len, tp->mss_cache); + + tp->dsack_dups += dup_segs; + /* Skip the DSACK if dup segs weren't retransmitted by sender */ + if (tp->dsack_dups > tp->total_retrans) + return 0; tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; tp->rack.dsack_seen = 1; - tp->dsack_dups += dup_segs; state->flag |= FLAG_DSACKING_ACK; /* A spurious retransmission is delivered */ @@ -1153,6 +1166,11 @@ static bool tcp_check_dsack(struct sock *sk, const struct sk_buff *ack_skb, } dup_segs = tcp_dsack_seen(tp, start_seq_0, end_seq_0, state); + if (!dup_segs) { /* Skip dubious DSACK */ + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDSACKIGNOREDDUBIOUS); + return false; + } + NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPDSACKRECVSEGS, dup_segs); /* D-SACK for already forgotten data... Do dumb counting. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5084333b5ab6..592c73962723 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1788,12 +1788,12 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, hdrlen); if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) { - thtail->window = th->window; - TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq; - if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq)) + if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) { TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq; + thtail->window = th->window; + } /* We have to update both TCP_SKB_CB(tail)->tcp_flags and * thtail->fin, so that the fast path in tcp_rcv_established() diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 76bff79d6fed..747f56e0c636 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -303,6 +303,7 @@ config IPV6_SEG6_LWTUNNEL config IPV6_SEG6_HMAC bool "IPv6: Segment Routing HMAC support" depends on IPV6 + select CRYPTO select CRYPTO_HMAC select CRYPTO_SHA1 select CRYPTO_SHA256 diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 25a90f3f705c..4a664ad4f4d4 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1993,14 +1993,19 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, /* Need to own table->tb6_lock */ int fib6_del(struct fib6_info *rt, struct nl_info *info) { - struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, - lockdep_is_held(&rt->fib6_table->tb6_lock)); - struct fib6_table *table = rt->fib6_table; struct net *net = info->nl_net; struct fib6_info __rcu **rtp; struct fib6_info __rcu **rtp_next; + struct fib6_table *table; + struct fib6_node *fn; + + if (rt == net->ipv6.fib6_null_entry) + return -ENOENT; - if (!fn || rt == net->ipv6.fib6_null_entry) + table = rt->fib6_table; + fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&table->tb6_lock)); + if (!fn) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5e7e25e2523a..fb075d9545b9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4202,7 +4202,7 @@ static struct fib6_info *rt6_add_route_info(struct net *net, .fc_nlinfo.nl_net = net, }; - cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO, + cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; diff --git a/net/mac80211/airtime.c b/net/mac80211/airtime.c index 314973033d03..26d2f8ba7029 100644 --- a/net/mac80211/airtime.c +++ b/net/mac80211/airtime.c @@ -560,7 +560,9 @@ static int ieee80211_fill_rx_status(struct ieee80211_rx_status *stat, if (rate->idx < 0 || !rate->count) return -1; - if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) + if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH) + stat->bw = RATE_INFO_BW_160; + else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) stat->bw = RATE_INFO_BW_80; else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) stat->bw = RATE_INFO_BW_40; @@ -668,20 +670,26 @@ u32 ieee80211_calc_expected_tx_airtime(struct ieee80211_hw *hw, * This will not be very accurate, but much better than simply * assuming un-aggregated tx in all cases. */ - if (duration > 400) /* <= VHT20 MCS2 1S */ + if (duration > 400 * 1024) /* <= VHT20 MCS2 1S */ agg_shift = 1; - else if (duration > 250) /* <= VHT20 MCS3 1S or MCS1 2S */ + else if (duration > 250 * 1024) /* <= VHT20 MCS3 1S or MCS1 2S */ agg_shift = 2; - else if (duration > 150) /* <= VHT20 MCS5 1S or MCS3 2S */ + else if (duration > 150 * 1024) /* <= VHT20 MCS5 1S or MCS2 2S */ agg_shift = 3; - else + else if (duration > 70 * 1024) /* <= VHT20 MCS5 2S */ agg_shift = 4; + else if (stat.encoding != RX_ENC_HE || + duration > 20 * 1024) /* <= HE40 MCS6 2S */ + agg_shift = 5; + else + agg_shift = 6; duration *= len; duration /= AVG_PKT_SIZE; duration /= 1024; + duration += (overhead >> agg_shift); - return duration + (overhead >> agg_shift); + return max_t(u32, duration, 4); } if (!conf) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index ac870309b911..2e400b0ff696 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4861,6 +4861,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_supported_band *sband; struct cfg80211_chan_def chandef; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; + bool is_5ghz = cbss->channel->band == NL80211_BAND_5GHZ; struct ieee80211_bss *bss = (void *)cbss->priv; int ret; u32 i; @@ -4879,7 +4880,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } - if (!sband->vht_cap.vht_supported && !is_6ghz) { + if (!sband->vht_cap.vht_supported && is_5ghz) { ifmgd->flags |= IEEE80211_STA_DISABLE_VHT; ifmgd->flags |= IEEE80211_STA_DISABLE_HE; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 836cde516a18..a959ebf56852 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -451,7 +451,8 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, else if (status->bw == RATE_INFO_BW_5) channel_flags |= IEEE80211_CHAN_QUARTER; - if (status->band == NL80211_BAND_5GHZ) + if (status->band == NL80211_BAND_5GHZ || + status->band == NL80211_BAND_6GHZ) channel_flags |= IEEE80211_CHAN_OFDM | IEEE80211_CHAN_5GHZ; else if (status->encoding != RX_ENC_LEGACY) channel_flags |= IEEE80211_CHAN_DYN | IEEE80211_CHAN_2GHZ; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index c8504ffc71a1..8d3bfc0fe176 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3353,9 +3353,10 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, he_chandef.center_freq1 = ieee80211_channel_to_frequency(he_6ghz_oper->ccfs0, NL80211_BAND_6GHZ); - he_chandef.center_freq2 = - ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1, - NL80211_BAND_6GHZ); + if (support_80_80 || support_160) + he_chandef.center_freq2 = + ieee80211_channel_to_frequency(he_6ghz_oper->ccfs1, + NL80211_BAND_6GHZ); } if (!cfg80211_chandef_valid(&he_chandef)) { diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 9c6045f9c24d..d1b64d0751f2 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -168,10 +168,7 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, /* take some capabilities as-is */ cap_info = le32_to_cpu(vht_cap_ie->vht_cap_info); vht_cap->cap = cap_info; - vht_cap->cap &= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 | - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 | - IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 | - IEEE80211_VHT_CAP_RXLDPC | + vht_cap->cap &= IEEE80211_VHT_CAP_RXLDPC | IEEE80211_VHT_CAP_VHT_TXOP_PS | IEEE80211_VHT_CAP_HTC_VHT | IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK | @@ -180,6 +177,9 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN | IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN; + vht_cap->cap |= min_t(u32, cap_info & IEEE80211_VHT_CAP_MAX_MPDU_MASK, + own_cap.cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK); + /* and some based on our own capabilities */ switch (own_cap.cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK) { case IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ: diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c index ab52811523e9..c829e4a75325 100644 --- a/net/mac802154/tx.c +++ b/net/mac802154/tx.c @@ -34,11 +34,11 @@ void ieee802154_xmit_worker(struct work_struct *work) if (res) goto err_tx; - ieee802154_xmit_complete(&local->hw, skb, false); - dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; + ieee802154_xmit_complete(&local->hw, skb, false); + return; err_tx: @@ -78,6 +78,8 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) /* async is priority, otherwise sync is fallback */ if (local->ops->xmit_async) { + unsigned int len = skb->len; + ret = drv_xmit_async(local, skb); if (ret) { ieee802154_wake_queue(&local->hw); @@ -85,7 +87,7 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb) } dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; + dev->stats.tx_bytes += len; } else { local->tx_skb = skb; queue_work(local->workqueue, &local->tx_work); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 7fa822b55c34..888bbbbb3e8a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -451,7 +451,10 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, struct sk_buff *skb, struct mptcp_ext *ext) { - u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq); + /* The write_seq value has already been incremented, so the actual + * sequence number for the DATA_FIN is one less. + */ + u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq) - 1; if (!ext->use_map || !skb->len) { /* RFC6824 requires a DSS mapping with specific values @@ -460,10 +463,7 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow, ext->data_fin = 1; ext->use_map = 1; ext->dsn64 = 1; - /* The write_seq value has already been incremented, so - * the actual sequence number for the DATA_FIN is one less. - */ - ext->data_seq = data_fin_tx_seq - 1; + ext->data_seq = data_fin_tx_seq; ext->subflow_seq = 0; ext->data_len = 1; } else if (ext->data_seq + ext->data_len == data_fin_tx_seq) { @@ -518,11 +518,11 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, if (subflow->use_64bit_ack) { ack_size = TCPOLEN_MPTCP_DSS_ACK64; - opts->ext_copy.data_ack = msk->ack_seq; + opts->ext_copy.data_ack = READ_ONCE(msk->ack_seq); opts->ext_copy.ack64 = 1; } else { ack_size = TCPOLEN_MPTCP_DSS_ACK32; - opts->ext_copy.data_ack32 = (uint32_t)(msk->ack_seq); + opts->ext_copy.data_ack32 = (uint32_t)READ_ONCE(msk->ack_seq); opts->ext_copy.ack64 = 0; } opts->ext_copy.use_ack = 1; @@ -782,7 +782,7 @@ static void update_una(struct mptcp_sock *msk, } } -bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq) +bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit) { /* Skip if DATA_FIN was already received. * If updating simultaneously with the recvmsg loop, values @@ -792,7 +792,8 @@ bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq) if (READ_ONCE(msk->rcv_data_fin) || !READ_ONCE(msk->first)) return false; - WRITE_ONCE(msk->rcv_data_fin_seq, data_fin_seq); + WRITE_ONCE(msk->rcv_data_fin_seq, + expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit)); WRITE_ONCE(msk->rcv_data_fin, 1); return true; @@ -875,7 +876,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb, */ if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { if (mp_opt.data_fin && mp_opt.data_len == 1 && - mptcp_update_rcv_data_fin(msk, mp_opt.data_seq) && + mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) && schedule_work(&msk->work)) sock_hold(subflow->conn); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index c8820c4156e6..770da3627848 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -66,6 +66,16 @@ static bool addresses_equal(const struct mptcp_addr_info *a, return a->port == b->port; } +static bool address_zero(const struct mptcp_addr_info *addr) +{ + struct mptcp_addr_info zero; + + memset(&zero, 0, sizeof(zero)); + zero.family = addr->family; + + return addresses_equal(addr, &zero, false); +} + static void local_address(const struct sock_common *skc, struct mptcp_addr_info *addr) { @@ -171,9 +181,9 @@ static void check_work_pending(struct mptcp_sock *msk) static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { + struct mptcp_addr_info remote = { 0 }; struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *local; - struct mptcp_addr_info remote; struct pm_nl_pernet *pernet; pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); @@ -323,10 +333,13 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) * addr */ local_address((struct sock_common *)msk, &msk_local); - local_address((struct sock_common *)msk, &skc_local); + local_address((struct sock_common *)skc, &skc_local); if (addresses_equal(&msk_local, &skc_local, false)) return 0; + if (address_zero(&skc_local)) + return 0; + pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); rcu_read_lock(); @@ -341,7 +354,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return ret; /* address not found, add to local list */ - entry = kmalloc(sizeof(*entry), GFP_KERNEL); + entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return -ENOMEM; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 365ba96c84b0..5d747c6a610e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -123,7 +123,7 @@ static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_ext_reset(skb); skb_orphan(skb); - msk->ack_seq += copy_len; + WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); tail = skb_peek_tail(&sk->sk_receive_queue); if (offset == 0 && tail) { @@ -261,7 +261,7 @@ static void mptcp_check_data_fin(struct sock *sk) if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) { struct mptcp_subflow_context *subflow; - msk->ack_seq++; + WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1); WRITE_ONCE(msk->rcv_data_fin, 0); sk->sk_shutdown |= RCV_SHUTDOWN; @@ -1720,7 +1720,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk, msk->remote_key = mp_opt->sndr_key; mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq); ack_seq++; - msk->ack_seq = ack_seq; + WRITE_ONCE(msk->ack_seq, ack_seq); } sock_reset_flag(nsk, SOCK_RCU_FREE); @@ -2072,7 +2072,7 @@ bool mptcp_finish_join(struct sock *sk) parent_sock = READ_ONCE(parent->sk_socket); if (parent_sock && !sk->sk_socket) mptcp_sock_graft(sk, parent_sock); - subflow->map_seq = msk->ack_seq; + subflow->map_seq = READ_ONCE(msk->ack_seq); return true; } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 60b27d44c184..20f04ac85409 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -387,7 +387,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk); bool mptcp_finish_join(struct sock *sk); void mptcp_data_acked(struct sock *sk); void mptcp_subflow_eof(struct sock *sk); -bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq); +bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit); void __init mptcp_token_init(void); static inline void mptcp_token_init_request(struct request_sock *req) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index e8cac2655c82..6f035af1c9d2 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -731,7 +731,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk, if (mpext->data_fin == 1) { if (data_len == 1) { - mptcp_update_rcv_data_fin(msk, mpext->data_seq); + bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq, + mpext->dsn64); pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq); if (subflow->map_valid) { /* A DATA_FIN might arrive in a DSS @@ -742,11 +743,23 @@ static enum mapping_status get_mapping_status(struct sock *ssk, skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; } else { + if (updated && schedule_work(&msk->work)) + sock_hold((struct sock *)msk); + return MAPPING_DATA_FIN; } } else { - mptcp_update_rcv_data_fin(msk, mpext->data_seq + data_len); - pr_debug("DATA_FIN with mapping seq=%llu", mpext->data_seq + data_len); + u64 data_fin_seq = mpext->data_seq + data_len - 1; + + /* If mpext->data_seq is a 32-bit value, data_fin_seq + * must also be limited to 32 bits. + */ + if (!mpext->dsn64) + data_fin_seq &= GENMASK_ULL(31, 0); + + mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64); + pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d", + data_fin_seq, mpext->dsn64); } /* Adjust for DATA_FIN using 1 byte of sequence space */ @@ -1063,6 +1076,7 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex, struct mptcp_sock *msk = mptcp_sk(sk); struct mptcp_subflow_context *subflow; struct sockaddr_storage addr; + int remote_id = remote->id; int local_id = loc->id; struct socket *sf; struct sock *ssk; @@ -1107,10 +1121,11 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex, goto failed; mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL); - pr_debug("msk=%p remote_token=%u local_id=%d", msk, remote_token, - local_id); + pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, + remote_token, local_id, remote_id); subflow->remote_token = remote_token; subflow->local_id = local_id; + subflow->remote_id = remote_id; subflow->request_join = 1; subflow->request_bkup = 1; mptcp_info2sockaddr(remote, &addr); @@ -1347,6 +1362,7 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->fully_established = 1; new_ctx->backup = subflow_req->backup; new_ctx->local_id = subflow_req->local_id; + new_ctx->remote_id = subflow_req->remote_id; new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 832eabecfbdd..c3a4214dc958 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -851,7 +851,6 @@ static int ctnetlink_done(struct netlink_callback *cb) } struct ctnetlink_filter { - u_int32_t cta_flags; u8 family; u_int32_t orig_flags; @@ -906,10 +905,6 @@ static int ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], struct nf_conntrack_zone *zone, u_int32_t flags); -/* applied on filters */ -#define CTA_FILTER_F_CTA_MARK (1 << 0) -#define CTA_FILTER_F_CTA_MARK_MASK (1 << 1) - static struct ctnetlink_filter * ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) { @@ -930,14 +925,10 @@ ctnetlink_alloc_filter(const struct nlattr * const cda[], u8 family) #ifdef CONFIG_NF_CONNTRACK_MARK if (cda[CTA_MARK]) { filter->mark.val = ntohl(nla_get_be32(cda[CTA_MARK])); - filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK); - - if (cda[CTA_MARK_MASK]) { + if (cda[CTA_MARK_MASK]) filter->mark.mask = ntohl(nla_get_be32(cda[CTA_MARK_MASK])); - filter->cta_flags |= CTA_FILTER_FLAG(CTA_MARK_MASK); - } else { + else filter->mark.mask = 0xffffffff; - } } else if (cda[CTA_MARK_MASK]) { err = -EINVAL; goto err_filter; @@ -1117,11 +1108,7 @@ static int ctnetlink_filter_match(struct nf_conn *ct, void *data) } #ifdef CONFIG_NF_CONNTRACK_MARK - if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK_MASK)) && - (ct->mark & filter->mark.mask) != filter->mark.val) - goto ignore_entry; - else if ((filter->cta_flags & CTA_FILTER_FLAG(CTA_MARK)) && - ct->mark != filter->mark.val) + if ((ct->mark & filter->mark.mask) != filter->mark.val) goto ignore_entry; #endif @@ -1404,7 +1391,8 @@ ctnetlink_parse_tuple_filter(const struct nlattr * const cda[], if (err < 0) return err; - + if (l3num != NFPROTO_IPV4 && l3num != NFPROTO_IPV6) + return -EOPNOTSUPP; tuple->src.l3num = l3num; if (flags & CTA_FILTER_FLAG(CTA_IP_DST) || diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 95f79980348c..47e9319d2cf3 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -565,6 +565,7 @@ static int nf_ct_netns_inet_get(struct net *net) int err; err = nf_ct_netns_do_get(net, NFPROTO_IPV4); +#if IS_ENABLED(CONFIG_IPV6) if (err < 0) goto err1; err = nf_ct_netns_do_get(net, NFPROTO_IPV6); @@ -575,6 +576,7 @@ static int nf_ct_netns_inet_get(struct net *net) err2: nf_ct_netns_put(net, NFPROTO_IPV4); err1: +#endif return err; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index b7dc1cbf40ea..4603b667973a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -684,6 +684,18 @@ nla_put_failure: return -1; } +struct nftnl_skb_parms { + bool report; +}; +#define NFT_CB(skb) (*(struct nftnl_skb_parms*)&((skb)->cb)) + +static void nft_notify_enqueue(struct sk_buff *skb, bool report, + struct list_head *notify_list) +{ + NFT_CB(skb).report = report; + list_add_tail(&skb->list, notify_list); +} + static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) { struct sk_buff *skb; @@ -715,8 +727,7 @@ static void nf_tables_table_notify(const struct nft_ctx *ctx, int event) goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -1468,8 +1479,7 @@ static void nf_tables_chain_notify(const struct nft_ctx *ctx, int event) goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -2807,8 +2817,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -3837,8 +3846,7 @@ static void nf_tables_set_notify(const struct nft_ctx *ctx, goto err; } - nfnetlink_send(skb, ctx->net, portid, NFNLGRP_NFTABLES, ctx->report, - gfp_flags); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -4959,8 +4967,7 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, goto err; } - nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, ctx->report, - GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -6275,7 +6282,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, goto err; } - nfnetlink_send(skb, net, portid, NFNLGRP_NFTABLES, report, gfp); + nft_notify_enqueue(skb, report, &net->nft.notify_list); return; err: nfnetlink_set_err(net, portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -7085,8 +7092,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx, goto err; } - nfnetlink_send(skb, ctx->net, ctx->portid, NFNLGRP_NFTABLES, - ctx->report, GFP_KERNEL); + nft_notify_enqueue(skb, ctx->report, &ctx->net->nft.notify_list); return; err: nfnetlink_set_err(ctx->net, ctx->portid, NFNLGRP_NFTABLES, -ENOBUFS); @@ -7695,6 +7701,41 @@ static void nf_tables_commit_release(struct net *net) mutex_unlock(&net->nft.commit_mutex); } +static void nft_commit_notify(struct net *net, u32 portid) +{ + struct sk_buff *batch_skb = NULL, *nskb, *skb; + unsigned char *data; + int len; + + list_for_each_entry_safe(skb, nskb, &net->nft.notify_list, list) { + if (!batch_skb) { +new_batch: + batch_skb = skb; + len = NLMSG_GOODSIZE - skb->len; + list_del(&skb->list); + continue; + } + len -= skb->len; + if (len > 0 && NFT_CB(skb).report == NFT_CB(batch_skb).report) { + data = skb_put(batch_skb, skb->len); + memcpy(data, skb->data, skb->len); + list_del(&skb->list); + kfree_skb(skb); + continue; + } + nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, + NFT_CB(batch_skb).report, GFP_KERNEL); + goto new_batch; + } + + if (batch_skb) { + nfnetlink_send(batch_skb, net, portid, NFNLGRP_NFTABLES, + NFT_CB(batch_skb).report, GFP_KERNEL); + } + + WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); +} + static int nf_tables_commit(struct net *net, struct sk_buff *skb) { struct nft_trans *trans, *next; @@ -7897,6 +7938,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) } } + nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); nf_tables_commit_release(net); @@ -8721,6 +8763,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&net->nft.tables); INIT_LIST_HEAD(&net->nft.commit_list); INIT_LIST_HEAD(&net->nft.module_list); + INIT_LIST_HEAD(&net->nft.notify_list); mutex_init(&net->nft.commit_mutex); net->nft.base_seq = 1; net->nft.validate_state = NFT_VALIDATE_SKIP; @@ -8737,6 +8780,7 @@ static void __net_exit nf_tables_exit_net(struct net *net) mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); WARN_ON_ONCE(!list_empty(&net->nft.module_list)); + WARN_ON_ONCE(!list_empty(&net->nft.notify_list)); } static struct pernet_operations nf_tables_net_ops = { diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 7bc6537f3ccb..b37bd02448d8 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -147,11 +147,11 @@ nft_meta_get_eval_skugid(enum nft_meta_keys key, switch (key) { case NFT_META_SKUID: - *dest = from_kuid_munged(&init_user_ns, + *dest = from_kuid_munged(sock_net(sk)->user_ns, sock->file->f_cred->fsuid); break; case NFT_META_SKGID: - *dest = from_kgid_munged(&init_user_ns, + *dest = from_kgid_munged(sock_net(sk)->user_ns, sock->file->f_cred->fsgid); break; default: diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 1eb65a7a27fd..c4b4d3376227 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1079,7 +1079,7 @@ static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; - while (netlink_policy_dump_loop(&cb->args[1])) { + while (netlink_policy_dump_loop(cb->args[1])) { void *hdr; struct nlattr *nest; @@ -1113,6 +1113,12 @@ nla_put_failure: return skb->len; } +static int ctrl_dumppolicy_done(struct netlink_callback *cb) +{ + netlink_policy_dump_free(cb->args[1]); + return 0; +} + static const struct genl_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETFAMILY, @@ -1123,6 +1129,7 @@ static const struct genl_ops genl_ctrl_ops[] = { { .cmd = CTRL_CMD_GETPOLICY, .dumpit = ctrl_dumppolicy, + .done = ctrl_dumppolicy_done, }, }; diff --git a/net/netlink/policy.c b/net/netlink/policy.c index 641ffbdd977a..0176b59ce530 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -84,7 +84,6 @@ int netlink_policy_dump_start(const struct nla_policy *policy, unsigned int policy_idx; int err; - /* also returns 0 if "*_state" is our ERR_PTR() end marker */ if (*_state) return 0; @@ -140,21 +139,11 @@ static bool netlink_policy_dump_finished(struct nl_policy_dump *state) !state->policies[state->policy_idx].policy; } -bool netlink_policy_dump_loop(unsigned long *_state) +bool netlink_policy_dump_loop(unsigned long _state) { - struct nl_policy_dump *state = (void *)*_state; - - if (IS_ERR(state)) - return false; - - if (netlink_policy_dump_finished(state)) { - kfree(state); - /* store end marker instead of freed state */ - *_state = (unsigned long)ERR_PTR(-ENOENT); - return false; - } + struct nl_policy_dump *state = (void *)_state; - return true; + return !netlink_policy_dump_finished(state); } int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state) @@ -309,3 +298,10 @@ nla_put_failure: nla_nest_cancel(skb, policy); return -ENOBUFS; } + +void netlink_policy_dump_free(unsigned long _state) +{ + struct nl_policy_dump *state = (void *)_state; + + kfree(state); +} diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index a3f1204f1ed2..12d42ab0193b 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -905,15 +905,19 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, } err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype); - if (err == NF_ACCEPT && - ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { - if (maniptype == NF_NAT_MANIP_SRC) - maniptype = NF_NAT_MANIP_DST; - else - maniptype = NF_NAT_MANIP_SRC; - - err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, - maniptype); + if (err == NF_ACCEPT && ct->status & IPS_DST_NAT) { + if (ct->status & IPS_SRC_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, + maniptype); + } else if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) { + err = ovs_ct_nat_execute(skb, ct, ctinfo, NULL, + NF_NAT_MANIP_SRC); + } } /* Mark NAT done if successful and update the flow key. */ diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index d8252fdab851..b8559c882431 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -199,17 +199,30 @@ static int announce_servers(struct sockaddr_qrtr *sq) if (!node) return 0; + rcu_read_lock(); /* Announce the list of servers registered in this node */ radix_tree_for_each_slot(slot, &node->servers, &iter, 0) { srv = radix_tree_deref_slot(slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); ret = service_announce_new(sq, srv); if (ret < 0) { pr_err("failed to announce new service\n"); return ret; } + + rcu_read_lock(); } + rcu_read_unlock(); + return 0; } @@ -344,11 +357,22 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) if (!node) return 0; + rcu_read_lock(); /* Advertise removal of this client to all servers of remote node */ radix_tree_for_each_slot(slot, &node->servers, &iter, 0) { srv = radix_tree_deref_slot(slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); server_del(node, srv->port); + rcu_read_lock(); } + rcu_read_unlock(); /* Advertise the removal of this client to all local servers */ local_node = node_get(qrtr_ns.local_node); @@ -359,8 +383,17 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) pkt.cmd = cpu_to_le32(QRTR_TYPE_BYE); pkt.client.node = cpu_to_le32(from->sq_node); + rcu_read_lock(); radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) { srv = radix_tree_deref_slot(slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); sq.sq_family = AF_QIPCRTR; sq.sq_node = srv->node; @@ -374,8 +407,11 @@ static int ctrl_cmd_bye(struct sockaddr_qrtr *from) pr_err("failed to send bye cmd\n"); return ret; } + rcu_read_lock(); } + rcu_read_unlock(); + return 0; } @@ -434,8 +470,17 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, pkt.client.node = cpu_to_le32(node_id); pkt.client.port = cpu_to_le32(port); + rcu_read_lock(); radix_tree_for_each_slot(slot, &local_node->servers, &iter, 0) { srv = radix_tree_deref_slot(slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + slot = radix_tree_iter_retry(&iter); + continue; + } + slot = radix_tree_iter_resume(slot, &iter); + rcu_read_unlock(); sq.sq_family = AF_QIPCRTR; sq.sq_node = srv->node; @@ -449,8 +494,11 @@ static int ctrl_cmd_del_client(struct sockaddr_qrtr *from, pr_err("failed to send del client cmd\n"); return ret; } + rcu_read_lock(); } + rcu_read_unlock(); + return 0; } @@ -554,20 +602,40 @@ static int ctrl_cmd_new_lookup(struct sockaddr_qrtr *from, filter.service = service; filter.instance = instance; + rcu_read_lock(); radix_tree_for_each_slot(node_slot, &nodes, &node_iter, 0) { node = radix_tree_deref_slot(node_slot); + if (!node) + continue; + if (radix_tree_deref_retry(node)) { + node_slot = radix_tree_iter_retry(&node_iter); + continue; + } + node_slot = radix_tree_iter_resume(node_slot, &node_iter); radix_tree_for_each_slot(srv_slot, &node->servers, &srv_iter, 0) { struct qrtr_server *srv; srv = radix_tree_deref_slot(srv_slot); + if (!srv) + continue; + if (radix_tree_deref_retry(srv)) { + srv_slot = radix_tree_iter_retry(&srv_iter); + continue; + } + if (!server_match(srv, &filter)) continue; + srv_slot = radix_tree_iter_resume(srv_slot, &srv_iter); + + rcu_read_unlock(); lookup_notify(from, srv, true); + rcu_read_lock(); } } + rcu_read_unlock(); /* Empty notification, to indicate end of listing */ lookup_notify(from, NULL, true); diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 90c558f89d46..957aa9263ba4 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -332,8 +332,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, { struct qrtr_hdr_v1 *hdr; size_t len = skb->len; - int rc = -ENODEV; - int confirm_rx; + int rc, confirm_rx; confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type); if (confirm_rx < 0) { @@ -357,15 +356,17 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->size = cpu_to_le32(len); hdr->confirm_rx = !!confirm_rx; - skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); - - mutex_lock(&node->ep_lock); - if (node->ep) - rc = node->ep->xmit(node->ep, skb); - else - kfree_skb(skb); - mutex_unlock(&node->ep_lock); + rc = skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); + if (!rc) { + mutex_lock(&node->ep_lock); + rc = -ENODEV; + if (node->ep) + rc = node->ep->xmit(node->ep, skb); + else + kfree_skb(skb); + mutex_unlock(&node->ep_lock); + } /* Need to ensure that a subsequent message carries the otherwise lost * confirm_rx flag if we dropped this one */ if (rc && confirm_rx) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 884cff7bb169..97aebb5d19db 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -518,7 +518,6 @@ enum rxrpc_call_state { RXRPC_CALL_CLIENT_RECV_REPLY, /* - client receiving reply phase */ RXRPC_CALL_SERVER_PREALLOC, /* - service preallocation */ RXRPC_CALL_SERVER_SECURING, /* - server securing request connection */ - RXRPC_CALL_SERVER_ACCEPTING, /* - server accepting request */ RXRPC_CALL_SERVER_RECV_REQUEST, /* - server receiving request */ RXRPC_CALL_SERVER_ACK_REQUEST, /* - server pending ACK of request */ RXRPC_CALL_SERVER_SEND_REPLY, /* - server sending reply */ @@ -714,8 +713,8 @@ struct rxrpc_ack_summary { enum rxrpc_command { RXRPC_CMD_SEND_DATA, /* send data message */ RXRPC_CMD_SEND_ABORT, /* request abort generation */ - RXRPC_CMD_ACCEPT, /* [server] accept incoming call */ RXRPC_CMD_REJECT_BUSY, /* [server] reject a call as busy */ + RXRPC_CMD_CHARGE_ACCEPT, /* [server] charge accept preallocation */ }; struct rxrpc_call_params { @@ -755,9 +754,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_sock *, struct sk_buff *); void rxrpc_accept_incoming_calls(struct rxrpc_local *); -struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *, unsigned long, - rxrpc_notify_rx_t); -int rxrpc_reject_call(struct rxrpc_sock *); +int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* * call_event.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index ef160566aa9a..8df1964db333 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -39,8 +39,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, unsigned int debug_id) { const void *here = __builtin_return_address(0); - struct rxrpc_call *call; + struct rxrpc_call *call, *xcall; struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); + struct rb_node *parent, **pp; int max, tmp; unsigned int size = RXRPC_BACKLOG_MAX; unsigned int head, tail, call_head, call_tail; @@ -94,7 +95,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, } /* Now it gets complicated, because calls get registered with the - * socket here, particularly if a user ID is preassigned by the user. + * socket here, with a user ID preassigned by the user. */ call = rxrpc_alloc_call(rx, gfp, debug_id); if (!call) @@ -107,34 +108,33 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, here, (const void *)user_call_ID); write_lock(&rx->call_lock); - if (user_attach_call) { - struct rxrpc_call *xcall; - struct rb_node *parent, **pp; - - /* Check the user ID isn't already in use */ - pp = &rx->calls.rb_node; - parent = NULL; - while (*pp) { - parent = *pp; - xcall = rb_entry(parent, struct rxrpc_call, sock_node); - if (user_call_ID < xcall->user_call_ID) - pp = &(*pp)->rb_left; - else if (user_call_ID > xcall->user_call_ID) - pp = &(*pp)->rb_right; - else - goto id_in_use; - } - call->user_call_ID = user_call_ID; - call->notify_rx = notify_rx; + /* Check the user ID isn't already in use */ + pp = &rx->calls.rb_node; + parent = NULL; + while (*pp) { + parent = *pp; + xcall = rb_entry(parent, struct rxrpc_call, sock_node); + if (user_call_ID < xcall->user_call_ID) + pp = &(*pp)->rb_left; + else if (user_call_ID > xcall->user_call_ID) + pp = &(*pp)->rb_right; + else + goto id_in_use; + } + + call->user_call_ID = user_call_ID; + call->notify_rx = notify_rx; + if (user_attach_call) { rxrpc_get_call(call, rxrpc_call_got_kernel); user_attach_call(call, user_call_ID); - rxrpc_get_call(call, rxrpc_call_got_userid); - rb_link_node(&call->sock_node, parent, pp); - rb_insert_color(&call->sock_node, &rx->calls); - set_bit(RXRPC_CALL_HAS_USERID, &call->flags); } + rxrpc_get_call(call, rxrpc_call_got_userid); + rb_link_node(&call->sock_node, parent, pp); + rb_insert_color(&call->sock_node, &rx->calls); + set_bit(RXRPC_CALL_HAS_USERID, &call->flags); + list_add(&call->sock_link, &rx->sock_calls); write_unlock(&rx->call_lock); @@ -157,11 +157,8 @@ id_in_use: } /* - * Preallocate sufficient service connections, calls and peers to cover the - * entire backlog of a socket. When a new call comes in, if we don't have - * sufficient of each available, the call gets rejected as busy or ignored. - * - * The backlog is replenished when a connection is accepted or rejected. + * Allocate the preallocation buffers for incoming service calls. These must + * be charged manually. */ int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp) { @@ -174,13 +171,6 @@ int rxrpc_service_prealloc(struct rxrpc_sock *rx, gfp_t gfp) rx->backlog = b; } - if (rx->discard_new_call) - return 0; - - while (rxrpc_service_prealloc_one(rx, b, NULL, NULL, 0, gfp, - atomic_inc_return(&rxrpc_debug_id)) == 0) - ; - return 0; } @@ -333,6 +323,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, rxrpc_see_call(call); call->conn = conn; call->security = conn->security; + call->security_ix = conn->security_ix; call->peer = rxrpc_get_peer(conn->params.peer); call->cong_cwnd = call->peer->cong_cwnd; return call; @@ -402,8 +393,6 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, if (rx->notify_new_call) rx->notify_new_call(&rx->sk, call, call->user_call_ID); - else - sk_acceptq_added(&rx->sk); spin_lock(&conn->state_lock); switch (conn->state) { @@ -415,12 +404,8 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, case RXRPC_CONN_SERVICE: write_lock(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) { - if (rx->discard_new_call) - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - else - call->state = RXRPC_CALL_SERVER_ACCEPTING; - } + if (call->state < RXRPC_CALL_COMPLETE) + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; write_unlock(&call->state_lock); break; @@ -440,9 +425,6 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, rxrpc_send_ping(call, skb); - if (call->state == RXRPC_CALL_SERVER_ACCEPTING) - rxrpc_notify_socket(call); - /* We have to discard the prealloc queue's ref here and rely on a * combination of the RCU read lock and refs held either by the socket * (recvmsg queue, to-be-accepted queue or user ID tree) or the kernel @@ -460,187 +442,18 @@ no_call: } /* - * handle acceptance of a call by userspace - * - assign the user call ID to the call at the front of the queue - * - called with the socket locked. + * Charge up socket with preallocated calls, attaching user call IDs. */ -struct rxrpc_call *rxrpc_accept_call(struct rxrpc_sock *rx, - unsigned long user_call_ID, - rxrpc_notify_rx_t notify_rx) - __releases(&rx->sk.sk_lock.slock) - __acquires(call->user_mutex) +int rxrpc_user_charge_accept(struct rxrpc_sock *rx, unsigned long user_call_ID) { - struct rxrpc_call *call; - struct rb_node *parent, **pp; - int ret; - - _enter(",%lx", user_call_ID); - - ASSERT(!irqs_disabled()); - - write_lock(&rx->call_lock); - - if (list_empty(&rx->to_be_accepted)) { - write_unlock(&rx->call_lock); - release_sock(&rx->sk); - kleave(" = -ENODATA [empty]"); - return ERR_PTR(-ENODATA); - } - - /* check the user ID isn't already in use */ - pp = &rx->calls.rb_node; - parent = NULL; - while (*pp) { - parent = *pp; - call = rb_entry(parent, struct rxrpc_call, sock_node); - - if (user_call_ID < call->user_call_ID) - pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) - pp = &(*pp)->rb_right; - else - goto id_in_use; - } - - /* Dequeue the first call and check it's still valid. We gain - * responsibility for the queue's reference. - */ - call = list_entry(rx->to_be_accepted.next, - struct rxrpc_call, accept_link); - write_unlock(&rx->call_lock); - - /* We need to gain the mutex from the interrupt handler without - * upsetting lockdep, so we have to release it there and take it here. - * We are, however, still holding the socket lock, so other accepts - * must wait for us and no one can add the user ID behind our backs. - */ - if (mutex_lock_interruptible(&call->user_mutex) < 0) { - release_sock(&rx->sk); - kleave(" = -ERESTARTSYS"); - return ERR_PTR(-ERESTARTSYS); - } - - write_lock(&rx->call_lock); - list_del_init(&call->accept_link); - sk_acceptq_removed(&rx->sk); - rxrpc_see_call(call); - - /* Find the user ID insertion point. */ - pp = &rx->calls.rb_node; - parent = NULL; - while (*pp) { - parent = *pp; - call = rb_entry(parent, struct rxrpc_call, sock_node); - - if (user_call_ID < call->user_call_ID) - pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) - pp = &(*pp)->rb_right; - else - BUG(); - } - - write_lock_bh(&call->state_lock); - switch (call->state) { - case RXRPC_CALL_SERVER_ACCEPTING: - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - break; - case RXRPC_CALL_COMPLETE: - ret = call->error; - goto out_release; - default: - BUG(); - } - - /* formalise the acceptance */ - call->notify_rx = notify_rx; - call->user_call_ID = user_call_ID; - rxrpc_get_call(call, rxrpc_call_got_userid); - rb_link_node(&call->sock_node, parent, pp); - rb_insert_color(&call->sock_node, &rx->calls); - if (test_and_set_bit(RXRPC_CALL_HAS_USERID, &call->flags)) - BUG(); - - write_unlock_bh(&call->state_lock); - write_unlock(&rx->call_lock); - rxrpc_notify_socket(call); - rxrpc_service_prealloc(rx, GFP_KERNEL); - release_sock(&rx->sk); - _leave(" = %p{%d}", call, call->debug_id); - return call; - -out_release: - _debug("release %p", call); - write_unlock_bh(&call->state_lock); - write_unlock(&rx->call_lock); - rxrpc_release_call(rx, call); - rxrpc_put_call(call, rxrpc_call_put); - goto out; - -id_in_use: - ret = -EBADSLT; - write_unlock(&rx->call_lock); -out: - rxrpc_service_prealloc(rx, GFP_KERNEL); - release_sock(&rx->sk); - _leave(" = %d", ret); - return ERR_PTR(ret); -} - -/* - * Handle rejection of a call by userspace - * - reject the call at the front of the queue - */ -int rxrpc_reject_call(struct rxrpc_sock *rx) -{ - struct rxrpc_call *call; - bool abort = false; - int ret; - - _enter(""); - - ASSERT(!irqs_disabled()); - - write_lock(&rx->call_lock); - - if (list_empty(&rx->to_be_accepted)) { - write_unlock(&rx->call_lock); - return -ENODATA; - } - - /* Dequeue the first call and check it's still valid. We gain - * responsibility for the queue's reference. - */ - call = list_entry(rx->to_be_accepted.next, - struct rxrpc_call, accept_link); - list_del_init(&call->accept_link); - sk_acceptq_removed(&rx->sk); - rxrpc_see_call(call); + struct rxrpc_backlog *b = rx->backlog; - write_lock_bh(&call->state_lock); - switch (call->state) { - case RXRPC_CALL_SERVER_ACCEPTING: - __rxrpc_abort_call("REJ", call, 1, RX_USER_ABORT, -ECONNABORTED); - abort = true; - fallthrough; - case RXRPC_CALL_COMPLETE: - ret = call->error; - goto out_discard; - default: - BUG(); - } + if (rx->sk.sk_state == RXRPC_CLOSE) + return -ESHUTDOWN; -out_discard: - write_unlock_bh(&call->state_lock); - write_unlock(&rx->call_lock); - if (abort) { - rxrpc_send_abort_packet(call); - rxrpc_release_call(rx, call); - rxrpc_put_call(call, rxrpc_call_put); - } - rxrpc_service_prealloc(rx, GFP_KERNEL); - _leave(" = %d", ret); - return ret; + return rxrpc_service_prealloc_one(rx, b, NULL, NULL, user_call_ID, + GFP_KERNEL, + atomic_inc_return(&rxrpc_debug_id)); } /* diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index a40fae013942..ed49769b459d 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -23,7 +23,6 @@ const char *const rxrpc_call_states[NR__RXRPC_CALL_STATES] = { [RXRPC_CALL_CLIENT_RECV_REPLY] = "ClRcvRpl", [RXRPC_CALL_SERVER_PREALLOC] = "SvPrealc", [RXRPC_CALL_SERVER_SECURING] = "SvSecure", - [RXRPC_CALL_SERVER_ACCEPTING] = "SvAccept", [RXRPC_CALL_SERVER_RECV_REQUEST] = "SvRcvReq", [RXRPC_CALL_SERVER_ACK_REQUEST] = "SvAckReq", [RXRPC_CALL_SERVER_SEND_REPLY] = "SvSndRpl", @@ -352,9 +351,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, call->call_id = sp->hdr.callNumber; call->service_id = sp->hdr.serviceId; call->cid = sp->hdr.cid; - call->state = RXRPC_CALL_SERVER_ACCEPTING; - if (sp->hdr.securityIndex > 0) - call->state = RXRPC_CALL_SERVER_SECURING; + call->state = RXRPC_CALL_SERVER_SECURING; call->cong_tstamp = skb->tstamp; /* Set the channel for this call. We don't get channel_lock as we're diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 447f55ca6886..64ace2960ecc 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -269,7 +269,7 @@ static void rxrpc_call_is_secure(struct rxrpc_call *call) if (call) { write_lock_bh(&call->state_lock); if (call->state == RXRPC_CALL_SERVER_SECURING) { - call->state = RXRPC_CALL_SERVER_ACCEPTING; + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; rxrpc_notify_socket(call); } write_unlock_bh(&call->state_lock); @@ -340,18 +340,18 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return ret; spin_lock(&conn->channel_lock); - spin_lock(&conn->state_lock); + spin_lock_bh(&conn->state_lock); if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { conn->state = RXRPC_CONN_SERVICE; - spin_unlock(&conn->state_lock); + spin_unlock_bh(&conn->state_lock); for (loop = 0; loop < RXRPC_MAXCALLS; loop++) rxrpc_call_is_secure( rcu_dereference_protected( conn->channels[loop].call, lockdep_is_held(&conn->channel_lock))); } else { - spin_unlock(&conn->state_lock); + spin_unlock_bh(&conn->state_lock); } spin_unlock(&conn->channel_lock); diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index 94c3df392651..2e8bd3b97301 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -903,7 +903,7 @@ int rxrpc_request_key(struct rxrpc_sock *rx, sockptr_t optval, int optlen) _enter(""); - if (optlen <= 0 || optlen > PAGE_SIZE - 1) + if (optlen <= 0 || optlen > PAGE_SIZE - 1 || rx->securities) return -EINVAL; description = memdup_sockptr_nul(optval, optlen); @@ -940,7 +940,7 @@ int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen) if (IS_ERR(description)) return PTR_ERR(description); - key = request_key_net(&key_type_keyring, description, sock_net(&rx->sk), NULL); + key = request_key(&key_type_keyring, description, NULL); if (IS_ERR(key)) { kfree(description); _leave(" = %ld", PTR_ERR(key)); @@ -1072,7 +1072,7 @@ static long rxrpc_read(const struct key *key, switch (token->security_index) { case RXRPC_SECURITY_RXKAD: - toksize += 9 * 4; /* viceid, kvno, key*2 + len, begin, + toksize += 8 * 4; /* viceid, kvno, key*2, begin, * end, primary, tktlen */ toksize += RND(token->kad->ticket_len); break; @@ -1107,7 +1107,8 @@ static long rxrpc_read(const struct key *key, break; default: /* we have a ticket we can't encode */ - BUG(); + pr_err("Unsupported key token type (%u)\n", + token->security_index); continue; } @@ -1138,6 +1139,14 @@ static long rxrpc_read(const struct key *key, memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \ xdr += (_l + 3) >> 2; \ } while(0) +#define ENCODE_BYTES(l, s) \ + do { \ + u32 _l = (l); \ + memcpy(xdr, (s), _l); \ + if (_l & 3) \ + memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \ + xdr += (_l + 3) >> 2; \ + } while(0) #define ENCODE64(x) \ do { \ __be64 y = cpu_to_be64(x); \ @@ -1165,7 +1174,7 @@ static long rxrpc_read(const struct key *key, case RXRPC_SECURITY_RXKAD: ENCODE(token->kad->vice_id); ENCODE(token->kad->kvno); - ENCODE_DATA(8, token->kad->session_key); + ENCODE_BYTES(8, token->kad->session_key); ENCODE(token->kad->start); ENCODE(token->kad->expiry); ENCODE(token->kad->primary_flag); @@ -1215,7 +1224,6 @@ static long rxrpc_read(const struct key *key, break; default: - BUG(); break; } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index c4684dde1f16..2c842851d72e 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -179,37 +179,6 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) } /* - * Pass back notification of a new call. The call is added to the - * to-be-accepted list. This means that the next call to be accepted might not - * be the last call seen awaiting acceptance, but unless we leave this on the - * front of the queue and block all other messages until someone gives us a - * user_ID for it, there's not a lot we can do. - */ -static int rxrpc_recvmsg_new_call(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct msghdr *msg, int flags) -{ - int tmp = 0, ret; - - ret = put_cmsg(msg, SOL_RXRPC, RXRPC_NEW_CALL, 0, &tmp); - - if (ret == 0 && !(flags & MSG_PEEK)) { - _debug("to be accepted"); - write_lock_bh(&rx->recvmsg_lock); - list_del_init(&call->recvmsg_link); - write_unlock_bh(&rx->recvmsg_lock); - - rxrpc_get_call(call, rxrpc_call_got); - write_lock(&rx->call_lock); - list_add_tail(&call->accept_link, &rx->to_be_accepted); - write_unlock(&rx->call_lock); - } - - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_to_be_accepted, 1, 0, 0, ret); - return ret; -} - -/* * End the packet reception phase. */ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) @@ -630,9 +599,6 @@ try_again: } switch (READ_ONCE(call->state)) { - case RXRPC_CALL_SERVER_ACCEPTING: - ret = rxrpc_recvmsg_new_call(rx, call, msg, flags); - break; case RXRPC_CALL_CLIENT_RECV_REPLY: case RXRPC_CALL_SERVER_RECV_REQUEST: case RXRPC_CALL_SERVER_ACK_REQUEST: @@ -728,7 +694,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, call->debug_id, rxrpc_call_states[call->state], iov_iter_count(iter), want_more); - ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING); + ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_SECURING); mutex_lock(&call->user_mutex); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 0824e103d037..d27140c836cc 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -530,10 +530,10 @@ static int rxrpc_sendmsg_cmsg(struct msghdr *msg, struct rxrpc_send_params *p) return -EINVAL; break; - case RXRPC_ACCEPT: + case RXRPC_CHARGE_ACCEPT: if (p->command != RXRPC_CMD_SEND_DATA) return -EINVAL; - p->command = RXRPC_CMD_ACCEPT; + p->command = RXRPC_CMD_CHARGE_ACCEPT; if (len != 0) return -EINVAL; break; @@ -659,16 +659,12 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (ret < 0) goto error_release_sock; - if (p.command == RXRPC_CMD_ACCEPT) { + if (p.command == RXRPC_CMD_CHARGE_ACCEPT) { ret = -EINVAL; if (rx->sk.sk_state != RXRPC_SERVER_LISTENING) goto error_release_sock; - call = rxrpc_accept_call(rx, p.call.user_call_ID, NULL); - /* The socket is now unlocked. */ - if (IS_ERR(call)) - return PTR_ERR(call); - ret = 0; - goto out_put_unlock; + ret = rxrpc_user_charge_accept(rx, p.call.user_call_ID); + goto error_release_sock; } call = rxrpc_find_call_by_user_ID(rx, p.call.user_call_ID); @@ -690,7 +686,6 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) case RXRPC_CALL_CLIENT_AWAIT_CONN: case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: - case RXRPC_CALL_SERVER_ACCEPTING: rxrpc_put_call(call, rxrpc_call_put); ret = -EBUSY; goto error_release_sock; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 063d8aaf2900..798430e1a79f 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -235,6 +235,8 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, index++; if (index < s_i) continue; + if (IS_ERR(p)) + continue; if (jiffy_since && time_after(jiffy_since, @@ -307,6 +309,8 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, mutex_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, tmp, id) { + if (IS_ERR(p)) + continue; ret = tcf_idr_release_unsafe(p); if (ret == ACT_P_DELETED) { module_put(ops->owner); @@ -467,17 +471,6 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index, } EXPORT_SYMBOL(tcf_idr_create_from_flags); -void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a) -{ - struct tcf_idrinfo *idrinfo = tn->idrinfo; - - mutex_lock(&idrinfo->lock); - /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */ - WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index))); - mutex_unlock(&idrinfo->lock); -} -EXPORT_SYMBOL(tcf_idr_insert); - /* Cleanup idr index that was allocated but not initialized. */ void tcf_idr_cleanup(struct tc_action_net *tn, u32 index) @@ -731,13 +724,6 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) return ret; } -static int tcf_action_destroy_1(struct tc_action *a, int bind) -{ - struct tc_action *actions[] = { a, NULL }; - - return tcf_action_destroy(actions, bind); -} - static int tcf_action_put(struct tc_action *p) { return __tcf_action_put(p, false); @@ -902,6 +888,26 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = { [TCA_ACT_HW_STATS] = NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY), }; +static void tcf_idr_insert_many(struct tc_action *actions[]) +{ + int i; + + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { + struct tc_action *a = actions[i]; + struct tcf_idrinfo *idrinfo; + + if (!a) + continue; + idrinfo = a->idrinfo; + mutex_lock(&idrinfo->lock); + /* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if + * it is just created, otherwise this is just a nop. + */ + idr_replace(&idrinfo->action_idr, a, a->tcfa_index); + mutex_unlock(&idrinfo->lock); + } +} + struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, @@ -1002,13 +1008,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (err != ACT_P_CREATED) module_put(a_o->owner); - if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) && - !rcu_access_pointer(a->goto_chain)) { - tcf_action_destroy_1(a, bind); - NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain"); - return ERR_PTR(-EINVAL); - } - return a; err_mod: @@ -1051,6 +1050,11 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, actions[i - 1] = act; } + /* We have to commit them all together, because if any error happened in + * between, we could not handle the failure gracefully. + */ + tcf_idr_insert_many(actions); + *attr_size = tcf_action_full_attrs_size(sz); return i - 1; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 54d5652cfe6c..a4c7ba35a343 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -365,9 +365,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (res == ACT_P_CREATED) { - tcf_idr_insert(tn, *act); - } else { + if (res != ACT_P_CREATED) { /* make sure the program being replaced is no longer executing */ synchronize_rcu(); tcf_bpf_cfg_cleanup(&old); diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index f901421b0634..e19885d7fe2c 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -139,7 +139,6 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, ci->net = net; ci->zone = parm->zone; - tcf_idr_insert(tn, *a); ret = ACT_P_CREATED; } else if (ret > 0) { ci = to_connmark(*a); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index f5826e457679..4fa4fcb842ba 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -110,9 +110,6 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, if (params_new) kfree_rcu(params_new, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 2c3619165680..a780afdf570d 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -1297,8 +1297,6 @@ static int tcf_ct_init(struct net *net, struct nlattr *nla, tcf_chain_put_by_act(goto_ch); if (params) call_rcu(¶ms->rcu, tcf_ct_params_free); - if (res == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return res; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index b5042f3ea079..6084300e51ad 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -269,9 +269,6 @@ static int tcf_ctinfo_init(struct net *net, struct nlattr *nla, if (cp_new) kfree_rcu(cp_new, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; put_chain: diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 410e3bbfb9ca..73c3926358a0 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -140,8 +140,6 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; release_idr: tcf_idr_release(*a, bind); diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c index 1fb8d428d2c1..7c0771dd77a3 100644 --- a/net/sched/act_gate.c +++ b/net/sched/act_gate.c @@ -437,9 +437,6 @@ static int tcf_gate_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; chain_put: diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index c1fcd85719d6..a2ddea04183a 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -436,6 +436,25 @@ static void tcf_ife_cleanup(struct tc_action *a) kfree_rcu(p, rcu); } +static int load_metalist(struct nlattr **tb, bool rtnl_held) +{ + int i; + + for (i = 1; i < max_metacnt; i++) { + if (tb[i]) { + void *val = nla_data(tb[i]); + int len = nla_len(tb[i]); + int rc; + + rc = load_metaops_and_vet(i, val, len, rtnl_held); + if (rc != 0) + return rc; + } + } + + return 0; +} + static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists, bool rtnl_held) { @@ -449,10 +468,6 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = load_metaops_and_vet(i, val, len, rtnl_held); - if (rc != 0) - return rc; - rc = add_metainfo(ife, i, val, len, exists); if (rc) return rc; @@ -509,6 +524,21 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (!p) return -ENOMEM; + if (tb[TCA_IFE_METALST]) { + err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, + tb[TCA_IFE_METALST], NULL, + NULL); + if (err) { + kfree(p); + return err; + } + err = load_metalist(tb2, rtnl_held); + if (err) { + kfree(p); + return err; + } + } + index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) { @@ -570,15 +600,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } if (tb[TCA_IFE_METALST]) { - err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, - tb[TCA_IFE_METALST], NULL, - NULL); - if (err) - goto metadata_parse_err; err = populate_metalist(ife, tb2, exists, rtnl_held); if (err) goto metadata_parse_err; - } else { /* if no passed metadata allow list or passed allow-all * then here we process by adding as many supported metadatum @@ -603,9 +627,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, if (p) kfree_rcu(p, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; metadata_parse_err: if (goto_ch) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 400a2cfe8452..8dc3bec0d325 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -189,8 +189,6 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, ipt->tcfi_t = t; ipt->tcfi_hook = hook; spin_unlock_bh(&ipt->tcf_lock); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; err3: diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index b2705318993b..e24b7e2331cd 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -194,8 +194,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, spin_lock(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); spin_unlock(&mirred_list_lock); - - tcf_idr_insert(tn, *a); } return ret; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 8118e2640979..e298ec3b3c9e 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -273,8 +273,6 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, if (p) kfree_rcu(p, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 855a6fa16a62..1ebd2a86d980 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -93,9 +93,6 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; release_idr: tcf_idr_release(*a, bind); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index c158bfed86d5..b45304446e13 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -238,8 +238,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, spin_unlock_bh(&p->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 0b431d493768..8d8452b1cdd4 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -201,8 +201,6 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (new) kfree_rcu(new, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; failure: diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 5e2df590bb58..3ebf9ede3cf1 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -116,8 +116,6 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 9813ca4006dd..a4f3d0f0daa9 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -157,8 +157,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla, goto release_idr; } - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index d0652386c6e2..e5f3fb8b00e3 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -225,8 +225,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 39e6d94cfafb..81a1c67335be 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -190,8 +190,6 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 536c4bc31be6..a229751ee8c4 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -156,6 +156,7 @@ tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len, struct vxlan_metadata *md = dst; md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]); + md->gbp &= VXLAN_GBP_MASK; } return sizeof(struct vxlan_metadata); @@ -536,9 +537,6 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, if (goto_ch) tcf_chain_put_by_act(goto_ch); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); - return ret; put_chain: diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index a5ff9f68ab02..163b0385fd4c 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -229,8 +229,6 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla, if (p) kfree_rcu(p, rcu); - if (ret == ACT_P_CREATED) - tcf_idr_insert(tn, *a); return ret; put_chain: if (goto_ch) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index a4f7ef1de7e7..fed18fd2c50b 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1175,8 +1175,10 @@ static int fl_set_vxlan_opt(const struct nlattr *nla, struct fl_flow_key *key, return -EINVAL; } - if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) + if (tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]) { md->gbp = nla_get_u32(tb[TCA_FLOWER_KEY_ENC_OPT_VXLAN_GBP]); + md->gbp &= VXLAN_GBP_MASK; + } return sizeof(*md); } @@ -1221,6 +1223,7 @@ static int fl_set_erspan_opt(const struct nlattr *nla, struct fl_flow_key *key, } if (tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]) { nla = tb[TCA_FLOWER_KEY_ENC_OPT_ERSPAN_INDEX]; + memset(&md->u, 0x00, sizeof(md->u)); md->u.index = nla_get_be32(nla); } } else if (md->version == 2) { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 265a61d011df..54c417244642 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1131,24 +1131,10 @@ EXPORT_SYMBOL(dev_activate); static void qdisc_deactivate(struct Qdisc *qdisc) { - bool nolock = qdisc->flags & TCQ_F_NOLOCK; - if (qdisc->flags & TCQ_F_BUILTIN) return; - if (test_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state)) - return; - - if (nolock) - spin_lock_bh(&qdisc->seqlock); - spin_lock_bh(qdisc_lock(qdisc)); set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); - - qdisc_reset(qdisc); - - spin_unlock_bh(qdisc_lock(qdisc)); - if (nolock) - spin_unlock_bh(&qdisc->seqlock); } static void dev_deactivate_queue(struct net_device *dev, @@ -1165,6 +1151,30 @@ static void dev_deactivate_queue(struct net_device *dev, } } +static void dev_reset_queue(struct net_device *dev, + struct netdev_queue *dev_queue, + void *_unused) +{ + struct Qdisc *qdisc; + bool nolock; + + qdisc = dev_queue->qdisc_sleeping; + if (!qdisc) + return; + + nolock = qdisc->flags & TCQ_F_NOLOCK; + + if (nolock) + spin_lock_bh(&qdisc->seqlock); + spin_lock_bh(qdisc_lock(qdisc)); + + qdisc_reset(qdisc); + + spin_unlock_bh(qdisc_lock(qdisc)); + if (nolock) + spin_unlock_bh(&qdisc->seqlock); +} + static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; @@ -1213,12 +1223,20 @@ void dev_deactivate_many(struct list_head *head) dev_watchdog_down(dev); } - /* Wait for outstanding qdisc-less dev_queue_xmit calls. + /* Wait for outstanding qdisc-less dev_queue_xmit calls or + * outstanding qdisc enqueuing calls. * This is avoided if all devices are in dismantle phase : * Caller will call synchronize_net() for us */ synchronize_net(); + list_for_each_entry(dev, head, close_list) { + netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); + + if (dev_ingress_queue(dev)) + dev_reset_queue(dev, dev_ingress_queue(dev), NULL); + } + /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) { diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index fe53c1e38c7d..b0ad7687ee2c 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -777,9 +777,11 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { [TCA_TAPRIO_ATTR_TXTIME_DELAY] = { .type = NLA_U32 }, }; -static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, +static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb, + struct sched_entry *entry, struct netlink_ext_ack *extack) { + int min_duration = length_to_duration(q, ETH_ZLEN); u32 interval = 0; if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) @@ -794,7 +796,10 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, interval = nla_get_u32( tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); - if (interval == 0) { + /* The interval should allow at least the minimum ethernet + * frame to go out. + */ + if (interval < min_duration) { NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); return -EINVAL; } @@ -804,8 +809,9 @@ static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, return 0; } -static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, - int index, struct netlink_ext_ack *extack) +static int parse_sched_entry(struct taprio_sched *q, struct nlattr *n, + struct sched_entry *entry, int index, + struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; int err; @@ -819,10 +825,10 @@ static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, entry->index = index; - return fill_sched_entry(tb, entry, extack); + return fill_sched_entry(q, tb, entry, extack); } -static int parse_sched_list(struct nlattr *list, +static int parse_sched_list(struct taprio_sched *q, struct nlattr *list, struct sched_gate_list *sched, struct netlink_ext_ack *extack) { @@ -847,7 +853,7 @@ static int parse_sched_list(struct nlattr *list, return -ENOMEM; } - err = parse_sched_entry(n, entry, i, extack); + err = parse_sched_entry(q, n, entry, i, extack); if (err < 0) { kfree(entry); return err; @@ -862,7 +868,7 @@ static int parse_sched_list(struct nlattr *list, return i; } -static int parse_taprio_schedule(struct nlattr **tb, +static int parse_taprio_schedule(struct taprio_sched *q, struct nlattr **tb, struct sched_gate_list *new, struct netlink_ext_ack *extack) { @@ -883,8 +889,8 @@ static int parse_taprio_schedule(struct nlattr **tb, new->cycle_time = nla_get_s64(tb[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]); if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) - err = parse_sched_list( - tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], new, extack); + err = parse_sched_list(q, tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], + new, extack); if (err < 0) return err; @@ -1473,7 +1479,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, goto free_sched; } - err = parse_taprio_schedule(tb, new_admin, extack); + err = parse_taprio_schedule(q, tb, new_admin, extack); if (err < 0) goto free_sched; diff --git a/net/sctp/auth.c b/net/sctp/auth.c index 9e289c770574..7e59d8a18f3e 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -494,6 +494,7 @@ int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp) out_err: /* Clean up any successful allocations */ sctp_auth_destroy_hmacs(ep->auth_hmacs); + ep->auth_hmacs = NULL; return -ENOMEM; } diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 836615f71a7d..53d0a4161df3 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -9220,13 +9220,10 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, static inline void sctp_copy_descendant(struct sock *sk_to, const struct sock *sk_from) { - int ancestor_size = sizeof(struct inet_sock) + - sizeof(struct sctp_sock) - - offsetof(struct sctp_sock, pd_lobby); - - if (sk_from->sk_family == PF_INET6) - ancestor_size += sizeof(struct ipv6_pinfo); + size_t ancestor_size = sizeof(struct inet_sock); + ancestor_size += sk_from->sk_prot->obj_size; + ancestor_size -= offsetof(struct sctp_sock, pd_lobby); __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); } diff --git a/net/socket.c b/net/socket.c index 0c0144604f81..58cac2da5f66 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3638,9 +3638,11 @@ EXPORT_SYMBOL(kernel_getpeername); int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { - if (sock->ops->sendpage) + if (sock->ops->sendpage) { + /* Warn in case the improper page to zero-copy send */ + WARN_ONCE(!sendpage_ok(page), "improper page for zero-copy send"); return sock->ops->sendpage(sock, page, offset, size, flags); - + } return sock_no_sendpage(sock, page, offset, size, flags); } EXPORT_SYMBOL(kernel_sendpage); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index d5805fa1d066..c2752e2b9ce3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -228,7 +228,7 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining) static void svc_flush_bvec(const struct bio_vec *bvec, size_t size, size_t seek) { struct bvec_iter bi = { - .bi_size = size, + .bi_size = size + seek, }; struct bio_vec bv; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 865f3e037425..23d868545362 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -404,7 +404,7 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); * @val: value passed unmodified to notifier function * @dev: port device * @info: notifier information data - * + * @extack: netlink extended ack * Call all network notifier blocks. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, diff --git a/net/tipc/group.c b/net/tipc/group.c index 588c2d2b0c69..b1fcd2ad5ecf 100644 --- a/net/tipc/group.c +++ b/net/tipc/group.c @@ -273,8 +273,8 @@ static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, return NULL; } -static void tipc_group_add_to_tree(struct tipc_group *grp, - struct tipc_member *m) +static int tipc_group_add_to_tree(struct tipc_group *grp, + struct tipc_member *m) { u64 nkey, key = (u64)m->node << 32 | m->port; struct rb_node **n, *parent = NULL; @@ -291,10 +291,11 @@ static void tipc_group_add_to_tree(struct tipc_group *grp, else if (key > nkey) n = &(*n)->rb_right; else - return; + return -EEXIST; } rb_link_node(&m->tree_node, parent, n); rb_insert_color(&m->tree_node, &grp->members); + return 0; } static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, @@ -302,6 +303,7 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, u32 instance, int state) { struct tipc_member *m; + int ret; m = kzalloc(sizeof(*m), GFP_ATOMIC); if (!m) @@ -314,8 +316,12 @@ static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, m->port = port; m->instance = instance; m->bc_acked = grp->bc_snd_nxt - 1; + ret = tipc_group_add_to_tree(grp, m); + if (ret < 0) { + kfree(m); + return NULL; + } grp->member_cnt++; - tipc_group_add_to_tree(grp, m); tipc_nlist_add(&grp->dests, m->node); m->state = state; return m; diff --git a/net/tipc/link.c b/net/tipc/link.c index b7362556da95..cef38a910107 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -532,7 +532,8 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id, * tipc_link_bc_create - create new link to be used for broadcast * @net: pointer to associated network namespace * @mtu: mtu to be used initially if no peers - * @window: send window to be used + * @min_win: minimal send window to be used by link + * @max_win: maximal send window to be used by link * @inputq: queue to put messages ready for delivery * @namedq: queue to put binding table update messages ready for delivery * @link: return value, pointer to put the created link diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 848fae674532..52e93ba4d8e2 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -150,7 +150,8 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf) if (fragid == FIRST_FRAGMENT) { if (unlikely(head)) goto err; - if (unlikely(skb_unclone(frag, GFP_ATOMIC))) + frag = skb_unshare(frag, GFP_ATOMIC); + if (unlikely(!frag)) goto err; head = *headbuf = frag; *buf = NULL; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index ebd280e767bd..11b27ddc75ba 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2771,10 +2771,7 @@ static int tipc_shutdown(struct socket *sock, int how) trace_tipc_sk_shutdown(sk, NULL, TIPC_DUMP_ALL, " "); __tipc_shutdown(sock, TIPC_CONN_SHUTDOWN); - if (tipc_sk_type_connectionless(sk)) - sk->sk_shutdown = SHUTDOWN_MASK; - else - sk->sk_shutdown = SEND_SHUTDOWN; + sk->sk_shutdown = SHUTDOWN_MASK; if (sk->sk_state == TIPC_DISCONNECTING) { /* Discard any unreceived messages */ diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9a3d9fedd7aa..95ab5545a931 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2143,10 +2143,15 @@ void tls_sw_release_resources_tx(struct sock *sk) struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct tls_rec *rec, *tmp; + int pending; /* Wait for any pending async encryptions to complete */ - smp_store_mb(ctx->async_notify, true); - if (atomic_read(&ctx->encrypt_pending)) + spin_lock_bh(&ctx->encrypt_compl_lock); + ctx->async_notify = true; + pending = atomic_read(&ctx->encrypt_pending); + spin_unlock_bh(&ctx->encrypt_compl_lock); + + if (pending) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); tls_tx_records(sk, -1); diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig index faf74850a1b5..27026f587fa6 100644 --- a/net/wireless/Kconfig +++ b/net/wireless/Kconfig @@ -217,6 +217,7 @@ config LIB80211_CRYPT_WEP config LIB80211_CRYPT_CCMP tristate + select CRYPTO select CRYPTO_AES select CRYPTO_CCM diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2c9e9a2d1688..7fd45f6ddb05 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4172,6 +4172,9 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info) if (err) return err; + if (key.idx < 0) + return -EINVAL; + if (info->attrs[NL80211_ATTR_MAC]) mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]); diff --git a/net/wireless/util.c b/net/wireless/util.c index 4a9ff9ef513f..6fa99df52f86 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -95,7 +95,7 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) /* see 802.11ax D6.1 27.3.23.2 */ if (chan == 2) return MHZ_TO_KHZ(5935); - if (chan <= 253) + if (chan <= 233) return MHZ_TO_KHZ(5950 + chan * 5); break; case NL80211_BAND_60GHZ: diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index e97db37354e4..b010bfde0149 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -303,10 +303,10 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { + u32 npgs_rem, chunk_size = mr->chunk_size, headroom = mr->headroom; bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; - u32 chunk_size = mr->chunk_size, headroom = mr->headroom; u64 npgs, addr = mr->addr, size = mr->len; - unsigned int chunks, chunks_per_page; + unsigned int chunks, chunks_rem; int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { @@ -336,19 +336,18 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if ((addr + size) < addr) return -EINVAL; - npgs = size >> PAGE_SHIFT; + npgs = div_u64_rem(size, PAGE_SIZE, &npgs_rem); + if (npgs_rem) + npgs++; if (npgs > U32_MAX) return -EINVAL; - chunks = (unsigned int)div_u64(size, chunk_size); + chunks = (unsigned int)div_u64_rem(size, chunk_size, &chunks_rem); if (chunks == 0) return -EINVAL; - if (!unaligned_chunks) { - chunks_per_page = PAGE_SIZE / chunk_size; - if (chunks < chunks_per_page || chunks % chunks_per_page) - return -EINVAL; - } + if (!unaligned_chunks && chunks_rem) + return -EINVAL; if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index c3231620d210..6c5e09e7440a 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -377,15 +377,30 @@ static int xsk_generic_xmit(struct sock *sk) skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr; skb->destructor = xsk_destruct_skb; + /* Hinder dev_direct_xmit from freeing the packet and + * therefore completing it in the destructor + */ + refcount_inc(&skb->users); err = dev_direct_xmit(skb, xs->queue_id); + if (err == NETDEV_TX_BUSY) { + /* Tell user-space to retry the send */ + skb->destructor = sock_wfree; + /* Free skb without triggering the perf drop trace */ + consume_skb(skb); + err = -EAGAIN; + goto out; + } + xskq_cons_release(xs->tx); /* Ignore NET_XMIT_CN as packet might have been sent */ - if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) { + if (err == NET_XMIT_DROP) { /* SKB completed but not sent */ + kfree_skb(skb); err = -EBUSY; goto out; } + consume_skb(skb); sent_frame = true; } diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c index 827ccdf2db57..1f08ebf7d80c 100644 --- a/net/xfrm/espintcp.c +++ b/net/xfrm/espintcp.c @@ -29,8 +29,12 @@ static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, static void handle_esp(struct sk_buff *skb, struct sock *sk) { + struct tcp_skb_cb *tcp_cb = (struct tcp_skb_cb *)skb->cb; + skb_reset_transport_header(skb); - memset(skb->cb, 0, sizeof(skb->cb)); + + /* restore IP CB, we need at least IP6CB->nhoff */ + memmove(skb->cb, &tcp_cb->header, sizeof(tcp_cb->header)); rcu_read_lock(); skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index eb8181987620..a8f66112c52b 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -303,7 +303,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } mtu = dst_mtu(dst); - if (!skb->ignore_df && skb->len > mtu) { + if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 69520ad3d83b..efc89a92961d 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1019,7 +1019,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, */ if (x->km.state == XFRM_STATE_VALID) { if ((x->sel.family && - !xfrm_selector_match(&x->sel, fl, x->sel.family)) || + (x->sel.family != family || + !xfrm_selector_match(&x->sel, fl, family))) || !security_xfrm_state_pol_flow_match(x, pol, fl)) return; @@ -1032,7 +1033,9 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, *acq_in_progress = 1; } else if (x->km.state == XFRM_STATE_ERROR || x->km.state == XFRM_STATE_EXPIRED) { - if (xfrm_selector_match(&x->sel, fl, x->sel.family) && + if ((!x->sel.family || + (x->sel.family == family && + xfrm_selector_match(&x->sel, fl, family))) && security_xfrm_state_pol_flow_match(x, pol, fl)) *error = -ESRCH; } @@ -1072,7 +1075,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, encap_family, + xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } if (best || acquire_in_progress) @@ -1089,7 +1092,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, encap_family, + xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error); } @@ -1441,6 +1444,30 @@ out: EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE +static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security) +{ + struct xfrm_user_sec_ctx *uctx; + int size = sizeof(*uctx) + security->ctx_len; + int err; + + uctx = kmalloc(size, GFP_KERNEL); + if (!uctx) + return -ENOMEM; + + uctx->exttype = XFRMA_SEC_CTX; + uctx->len = size; + uctx->ctx_doi = security->ctx_doi; + uctx->ctx_alg = security->ctx_alg; + uctx->ctx_len = security->ctx_len; + memcpy(uctx + 1, security->ctx_str, security->ctx_len); + err = security_xfrm_state_alloc(x, uctx); + kfree(uctx); + if (err) + return err; + + return 0; +} + static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, struct xfrm_encap_tmpl *encap) { @@ -1497,6 +1524,10 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, goto error; } + if (orig->security) + if (clone_security(x, orig->security)) + goto error; + if (orig->coaddr) { x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr), GFP_KERNEL); @@ -1510,6 +1541,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, } memcpy(&x->mark, &orig->mark, sizeof(x->mark)); + memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark)); if (xfrm_init_state(x) < 0) goto error; @@ -1521,7 +1553,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; - x->curlft.add_time = orig->curlft.add_time; + memcpy(&x->curlft, &orig->curlft, sizeof(x->curlft)); x->km.state = orig->km.state; x->km.seq = orig->km.seq; x->replay = orig->replay; diff --git a/scripts/dtc/Makefile b/scripts/dtc/Makefile index a698ece43fff..4852bf44e913 100644 --- a/scripts/dtc/Makefile +++ b/scripts/dtc/Makefile @@ -9,7 +9,7 @@ dtc-objs := dtc.o flattree.o fstree.o data.o livetree.o treesource.o \ dtc-objs += dtc-lexer.lex.o dtc-parser.tab.o # Source files need to get at the userspace version of libfdt_env.h to compile -HOST_EXTRACFLAGS := -I $(srctree)/$(src)/libfdt +HOST_EXTRACFLAGS += -I $(srctree)/$(src)/libfdt ifeq ($(shell pkg-config --exists yaml-0.1 2>/dev/null && echo yes),) ifneq ($(CHECK_DT_BINDING)$(CHECK_DTBS),) diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index 0096cd965332..7ecd2ccba531 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -82,6 +82,7 @@ static char *sym_name(const struct sym_entry *s) static bool is_ignored_symbol(const char *name, char type) { + /* Symbol names that exactly match to the following are ignored.*/ static const char * const ignored_symbols[] = { /* * Symbols which vary between passes. Passes 1 and 2 must have @@ -104,6 +105,7 @@ static bool is_ignored_symbol(const char *name, char type) NULL }; + /* Symbol names that begin with the following are ignored.*/ static const char * const ignored_prefixes[] = { "$", /* local symbols for ARM, MIPS, etc. */ ".LASANPC", /* s390 kasan local symbols */ @@ -113,6 +115,7 @@ static bool is_ignored_symbol(const char *name, char type) NULL }; + /* Symbol names that end with the following are ignored.*/ static const char * const ignored_suffixes[] = { "_from_arm", /* arm */ "_from_thumb", /* arm */ @@ -120,9 +123,15 @@ static bool is_ignored_symbol(const char *name, char type) NULL }; + /* Symbol names that contain the following are ignored.*/ + static const char * const ignored_matches[] = { + ".long_branch.", /* ppc stub */ + ".plt_branch.", /* ppc stub */ + NULL + }; + const char * const *p; - /* Exclude symbols which vary between passes. */ for (p = ignored_symbols; *p; p++) if (!strcmp(name, *p)) return true; @@ -138,6 +147,11 @@ static bool is_ignored_symbol(const char *name, char type) return true; } + for (p = ignored_matches; *p; p++) { + if (strstr(name, *p)) + return true; + } + if (type == 'U' || type == 'u') return true; /* exclude debugging symbols */ diff --git a/scripts/spelling.txt b/scripts/spelling.txt index f253681e7e2a..feb2efaaa5e6 100644 --- a/scripts/spelling.txt +++ b/scripts/spelling.txt @@ -589,7 +589,7 @@ explictly||explicitly expresion||expression exprimental||experimental extened||extended -exteneded||extended||extended +exteneded||extended extensability||extensibility extention||extension extenstion||extension diff --git a/sound/pci/asihpi/hpioctl.c b/sound/pci/asihpi/hpioctl.c index 496dcde9715d..9790f5108a16 100644 --- a/sound/pci/asihpi/hpioctl.c +++ b/sound/pci/asihpi/hpioctl.c @@ -343,7 +343,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev, struct hpi_message hm; struct hpi_response hr; struct hpi_adapter adapter; - struct hpi_pci pci; + struct hpi_pci pci = { 0 }; memset(&adapter, 0, sizeof(adapter)); @@ -499,7 +499,7 @@ int asihpi_adapter_probe(struct pci_dev *pci_dev, return 0; err: - for (idx = 0; idx < HPI_MAX_ADAPTER_MEM_SPACES; idx++) { + while (--idx >= 0) { if (pci.ap_mem_base[idx]) { iounmap(pci.ap_mem_base[idx]); pci.ap_mem_base[idx] = NULL; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 85e207173f5d..d4f17b465892 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -2475,7 +2475,6 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = { SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD), - SND_PCI_QUIRK(0x1462, 0x9c37, "MSI X570-A PRO", ALC1220_FIXUP_CLEVO_P950), SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS), SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3), SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX), @@ -3428,7 +3427,11 @@ static void alc256_shutup(struct hda_codec *codec) /* 3k pull low control for Headset jack. */ /* NOTE: call this before clearing the pin, otherwise codec stalls */ - alc_update_coef_idx(codec, 0x46, 0, 3 << 12); + /* If disable 3k pulldown control for alc257, the Mic detection will not work correctly + * when booting with headset plugged. So skip setting it for the codec alc257 + */ + if (codec->core.vendor_id != 0x10ec0257) + alc_update_coef_idx(codec, 0x46, 0, 3 << 12); if (!spec->no_shutup_pins) snd_hda_codec_write(codec, hp_pin, 0, @@ -6051,6 +6054,7 @@ static void alc_fixup_thinkpad_acpi(struct hda_codec *codec, #include "hp_x360_helper.c" enum { + ALC269_FIXUP_GPIO2, ALC269_FIXUP_SONY_VAIO, ALC275_FIXUP_SONY_VAIO_GPIO2, ALC269_FIXUP_DELL_M101Z, @@ -6232,6 +6236,10 @@ enum { }; static const struct hda_fixup alc269_fixups[] = { + [ALC269_FIXUP_GPIO2] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_gpio2, + }, [ALC269_FIXUP_SONY_VAIO] = { .type = HDA_FIXUP_PINCTLS, .v.pins = (const struct hda_pintbl[]) { @@ -7051,6 +7059,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC233_FIXUP_LENOVO_MULTI_CODECS] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_alc662_fixup_lenovo_dual_codecs, + .chained = true, + .chain_id = ALC269_FIXUP_GPIO2 }, [ALC233_FIXUP_ACER_HEADSET_MIC] = { .type = HDA_FIXUP_VERBS, diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c index 5b43e9e40e49..c369c81e74c4 100644 --- a/sound/usb/mixer_maps.c +++ b/sound/usb/mixer_maps.c @@ -371,7 +371,6 @@ static const struct usbmix_name_map asus_rog_map[] = { }; static const struct usbmix_name_map lenovo_p620_rear_map[] = { - { 19, NULL, 2 }, /* FU, Volume */ { 19, NULL, 12 }, /* FU, Input Gain Pad */ {} }; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 75bbdc691243..892296df131d 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1678,12 +1678,13 @@ 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, Kingston HyperX needs a tiny - * delay here, otherwise requests like get/set frequency return as - * failed despite actually succeeding. + /* Zoom R16/24, Logitech H650e/H570e, 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(0x046d, 0x0a56) || chip->usb_id == USB_ID(0x0b0e, 0x0349) || chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) diff --git a/tools/bootconfig/test-bootconfig.sh b/tools/bootconfig/test-bootconfig.sh index 56284b98d8f0..d295e406a756 100755 --- a/tools/bootconfig/test-bootconfig.sh +++ b/tools/bootconfig/test-bootconfig.sh @@ -137,6 +137,31 @@ $BOOTCONF $INITRD > $TEMPCONF cat $TEMPCONF xpass grep \'\"string\"\' $TEMPCONF +echo "Repeat same-key tree" +cat > $TEMPCONF << EOF +foo +bar +foo { buz } +EOF +echo > $INITRD + +xpass $BOOTCONF -a $TEMPCONF $INITRD +$BOOTCONF $INITRD > $OUTFILE +xpass grep -q "bar" $OUTFILE + + +echo "Remove/keep tailing spaces" +cat > $TEMPCONF << EOF +foo = val # comment +bar = "val2 " # comment +EOF +echo > $INITRD + +xpass $BOOTCONF -a $TEMPCONF $INITRD +$BOOTCONF $INITRD > $OUTFILE +xfail grep -q val[[:space:]] $OUTFILE +xpass grep -q val2[[:space:]] $OUTFILE + echo "=== expected failure cases ===" for i in samples/bad-* ; do xfail $BOOTCONF -a $i $INITRD diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile index 0a6d09a3e91f..39bb322707b4 100644 --- a/tools/bpf/Makefile +++ b/tools/bpf/Makefile @@ -38,7 +38,7 @@ FEATURE_TESTS = libbfd disassembler-four-args FEATURE_DISPLAY = libbfd disassembler-four-args check_feat := 1 -NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean +NON_CHECK_FEAT_TARGETS := clean bpftool_clean runqslower_clean resolve_btfids_clean ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CHECK_FEAT_TARGETS),$(MAKECMDGOALS)),) check_feat := 0 @@ -89,7 +89,7 @@ $(OUTPUT)bpf_exp.lex.c: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.yacc.o: $(OUTPUT)bpf_exp.yacc.c $(OUTPUT)bpf_exp.lex.o: $(OUTPUT)bpf_exp.lex.c -clean: bpftool_clean runqslower_clean +clean: bpftool_clean runqslower_clean resolve_btfids_clean $(call QUIET_CLEAN, bpf-progs) $(Q)$(RM) -r -- $(OUTPUT)*.o $(OUTPUT)bpf_jit_disasm $(OUTPUT)bpf_dbg \ $(OUTPUT)bpf_asm $(OUTPUT)bpf_exp.yacc.* $(OUTPUT)bpf_exp.lex.* diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 8462690a039b..4828913703b6 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -25,7 +25,7 @@ endif LIBBPF = $(LIBBPF_PATH)libbpf.a -BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion) +BPFTOOL_VERSION ?= $(shell make -rR --no-print-directory -sC ../../.. kernelversion) $(LIBBPF): FORCE $(if $(LIBBPF_OUTPUT),@mkdir -p $(LIBBPF_OUTPUT)) diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile index a88cd4426398..fe8eb537688b 100644 --- a/tools/bpf/resolve_btfids/Makefile +++ b/tools/bpf/resolve_btfids/Makefile @@ -80,6 +80,7 @@ libbpf-clean: clean: libsubcmd-clean libbpf-clean fixdep-clean $(call msg,CLEAN,$(BINARY)) $(Q)$(RM) -f $(BINARY); \ + $(RM) -rf $(if $(OUTPUT),$(OUTPUT),.)/feature; \ find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM) tags: diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c index 0f257139b003..7703f0118385 100644 --- a/tools/io_uring/io_uring-bench.c +++ b/tools/io_uring/io_uring-bench.c @@ -130,7 +130,7 @@ static int io_uring_register_files(struct submitter *s) s->nr_files); } -static int gettid(void) +static int lk_gettid(void) { return syscall(__NR_gettid); } @@ -281,7 +281,7 @@ static void *submitter_fn(void *data) struct io_sq_ring *ring = &s->sq_ring; int ret, prepped; - printf("submitter=%d\n", gettid()); + printf("submitter=%d\n", lk_gettid()); srand48_r(pthread_self(), &s->rand); diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index bf8ed134cb8a..9ae8f4ef0aac 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -59,7 +59,7 @@ FEATURE_USER = .libbpf FEATURE_TESTS = libelf libelf-mmap zlib bpf reallocarray FEATURE_DISPLAY = libelf zlib bpf -INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi +INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi FEATURE_CHECK_CFLAGS-bpf = $(INCLUDES) check_feat := 1 @@ -152,6 +152,7 @@ GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN_SHARED) | \ awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ sort -u | wc -l) VERSIONED_SYM_COUNT = $(shell readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}' | \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l) CMD_TARGETS = $(LIB_TARGET) $(PC_FILE) @@ -219,6 +220,7 @@ check_abi: $(OUTPUT)libbpf.so awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ sort -u > $(OUTPUT)libbpf_global_syms.tmp; \ readelf --dyn-syms --wide $(OUTPUT)libbpf.so | \ + awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {print $$NF}'| \ grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | \ sort -u > $(OUTPUT)libbpf_versioned_syms.tmp; \ diff -u $(OUTPUT)libbpf_global_syms.tmp \ diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 7dfca7016aaa..6bdbc389b493 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -659,6 +659,12 @@ struct btf *btf__parse_raw(const char *path) err = -EIO; goto err_out; } + if (magic == __bswap_16(BTF_MAGIC)) { + /* non-native endian raw BTF */ + pr_warn("non-native BTF endianness is not supported\n"); + err = -LIBBPF_ERRNO__ENDIAN; + goto err_out; + } if (magic != BTF_MAGIC) { /* definitely not a raw BTF */ err = -EPROTO; diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 0ad0b0491e1f..e493d6048143 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -5203,8 +5203,8 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj, int i, j, nrels, new_sz; const struct btf_var_secinfo *vi = NULL; const struct btf_type *sec, *var, *def; + struct bpf_map *map = NULL, *targ_map; const struct btf_member *member; - struct bpf_map *map, *targ_map; const char *name, *mname; Elf_Data *symbols; unsigned int moff; @@ -6925,7 +6925,7 @@ static const struct bpf_sec_def section_defs[] = { BPF_XDP_DEVMAP), BPF_EAPROG_SEC("xdp_cpumap/", BPF_PROG_TYPE_XDP, BPF_XDP_CPUMAP), - BPF_EAPROG_SEC("xdp", BPF_PROG_TYPE_XDP, + BPF_APROG_SEC("xdp", BPF_PROG_TYPE_XDP, BPF_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("lwt_in", BPF_PROG_TYPE_LWT_IN), diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c index 07ddbfdbcab7..6dfce3fd68bc 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_hash_map.c @@ -47,7 +47,10 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) __u32 seq_num = ctx->meta->seq_num; struct bpf_map *map = ctx->map; struct key_t *key = ctx->key; + struct key_t tmp_key; __u64 *val = ctx->value; + __u64 tmp_val = 0; + int ret; if (in_test_mode) { /* test mode is used by selftests to @@ -61,6 +64,18 @@ int dump_bpf_hash_map(struct bpf_iter__bpf_map_elem *ctx) if (key == (void *)0 || val == (void *)0) return 0; + /* update the value and then delete the <key, value> pair. + * it should not impact the existing 'val' which is still + * accessible under rcu. + */ + __builtin_memcpy(&tmp_key, key, sizeof(struct key_t)); + ret = bpf_map_update_elem(&hashmap1, &tmp_key, &tmp_val, 0); + if (ret) + return 0; + ret = bpf_map_delete_elem(&hashmap1, &tmp_key); + if (ret) + return 0; + key_sum_a += key->a; key_sum_b += key->b; key_sum_c += key->c; diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86_64/debug_regs.c index b8d14f9db5f9..2fc6b3af81a1 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86_64/debug_regs.c @@ -73,7 +73,7 @@ int main(void) int i; /* Instruction lengths starting at ss_start */ int ss_size[4] = { - 3, /* xor */ + 2, /* xor */ 2, /* cpuid */ 5, /* mov */ 2, /* rdmsr */ diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 7c38a909f8b8..8a2fe6d64bf2 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -1175,6 +1175,51 @@ kci_test_neigh_get() echo "PASS: neigh get" } +kci_test_bridge_parent_id() +{ + local ret=0 + sysfsnet=/sys/bus/netdevsim/devices/netdevsim + probed=false + + if [ ! -w /sys/bus/netdevsim/new_device ] ; then + modprobe -q netdevsim + check_err $? + if [ $ret -ne 0 ]; then + echo "SKIP: bridge_parent_id can't load netdevsim" + return $ksft_skip + fi + probed=true + fi + + echo "10 1" > /sys/bus/netdevsim/new_device + while [ ! -d ${sysfsnet}10 ] ; do :; done + echo "20 1" > /sys/bus/netdevsim/new_device + while [ ! -d ${sysfsnet}20 ] ; do :; done + udevadm settle + dev10=`ls ${sysfsnet}10/net/` + dev20=`ls ${sysfsnet}20/net/` + + ip link add name test-bond0 type bond mode 802.3ad + ip link set dev $dev10 master test-bond0 + ip link set dev $dev20 master test-bond0 + ip link add name test-br0 type bridge + ip link set dev test-bond0 master test-br0 + check_err $? + + # clean up any leftovers + ip link del dev test-br0 + ip link del dev test-bond0 + echo 20 > /sys/bus/netdevsim/del_device + echo 10 > /sys/bus/netdevsim/del_device + $probed && rmmod netdevsim + + if [ $ret -ne 0 ]; then + echo "FAIL: bridge_parent_id" + return 1 + fi + echo "PASS: bridge_parent_id" +} + kci_test_rtnl() { local ret=0 @@ -1224,6 +1269,8 @@ kci_test_rtnl() check_err $? kci_test_neigh_get check_err $? + kci_test_bridge_parent_id + check_err $? kci_del_dummy return $ret |