diff options
1429 files changed, 18931 insertions, 8217 deletions
@@ -36,6 +36,7 @@ Andrew Morton <akpm@linux-foundation.org> Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk> Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com> Andrew Vasquez <andrew.vasquez@qlogic.com> +Andrey Konovalov <andreyknvl@gmail.com> <andreyknvl@google.com> Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com> Andrey Ryabinin <ryabinin.a.a@gmail.com> <aryabinin@virtuozzo.com> Andy Adamson <andros@citi.umich.edu> @@ -65,6 +66,8 @@ Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com> Changbin Du <changbin.du@intel.com> <changbin.du@intel.com> Chao Yu <chao@kernel.org> <chao2.yu@samsung.com> Chao Yu <chao@kernel.org> <yuchao0@huawei.com> +Chris Chiu <chris.chiu@canonical.com> <chiu@endlessm.com> +Chris Chiu <chris.chiu@canonical.com> <chiu@endlessos.org> Christophe Ricard <christophe.ricard@gmail.com> Christoph Hellwig <hch@lst.de> Corey Minyard <minyard@acm.org> @@ -165,6 +168,7 @@ Johan Hovold <johan@kernel.org> <jhovold@gmail.com> Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> +Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org> <josh@joshtriplett.org> <josh@freedesktop.org> <josh@joshtriplett.org> <josh@kernel.org> <josh@joshtriplett.org> <josht@linux.vnet.ibm.com> @@ -250,8 +254,14 @@ Morten Welinder <welinder@anemone.rentec.com> Morten Welinder <welinder@darter.rentec.com> Morten Welinder <welinder@troll.com> Mythri P K <mythripk@ti.com> +Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com> Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com> Nguyen Anh Quynh <aquynh@gmail.com> +Nicholas Piggin <npiggin@gmail.com> <npiggen@suse.de> +Nicholas Piggin <npiggin@gmail.com> <npiggin@kernel.dk> +Nicholas Piggin <npiggin@gmail.com> <npiggin@suse.de> +Nicholas Piggin <npiggin@gmail.com> <nickpiggin@yahoo.com.au> +Nicholas Piggin <npiggin@gmail.com> <piggin@cyberone.com.au> Nicolas Ferre <nicolas.ferre@microchip.com> <nicolas.ferre@atmel.com> Nicolas Pitre <nico@fluxnic.net> <nicolas.pitre@linaro.org> Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org> diff --git a/Documentation/ABI/testing/debugfs-moxtet b/Documentation/ABI/testing/debugfs-moxtet index 6eee10c3d5a1..637d8587d03d 100644 --- a/Documentation/ABI/testing/debugfs-moxtet +++ b/Documentation/ABI/testing/debugfs-moxtet @@ -1,7 +1,7 @@ What: /sys/kernel/debug/moxtet/input Date: March 2019 KernelVersion: 5.3 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (Read) Read input from the shift registers, in hexadecimal. Returns N+1 bytes, where N is the number of Moxtet connected modules. The first byte is from the CPU board itself. @@ -19,7 +19,7 @@ Description: (Read) Read input from the shift registers, in hexadecimal. What: /sys/kernel/debug/moxtet/output Date: March 2019 KernelVersion: 5.3 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (RW) Read last written value to the shift registers, in hexadecimal, or write values to the shift registers, also in hexadecimal. diff --git a/Documentation/ABI/testing/debugfs-turris-mox-rwtm b/Documentation/ABI/testing/debugfs-turris-mox-rwtm index 326df1b74707..813987d5de4e 100644 --- a/Documentation/ABI/testing/debugfs-turris-mox-rwtm +++ b/Documentation/ABI/testing/debugfs-turris-mox-rwtm @@ -1,7 +1,7 @@ What: /sys/kernel/debug/turris-mox-rwtm/do_sign Date: Jun 2020 KernelVersion: 5.8 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: ======= =========================================================== diff --git a/Documentation/ABI/testing/sysfs-bus-moxtet-devices b/Documentation/ABI/testing/sysfs-bus-moxtet-devices index 4a6d61b44f3f..32dccc00d57d 100644 --- a/Documentation/ABI/testing/sysfs-bus-moxtet-devices +++ b/Documentation/ABI/testing/sysfs-bus-moxtet-devices @@ -1,17 +1,17 @@ What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_description Date: March 2019 KernelVersion: 5.3 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (Read) Moxtet module description. Format: string What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_id Date: March 2019 KernelVersion: 5.3 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (Read) Moxtet module ID. Format: %x What: /sys/bus/moxtet/devices/moxtet-<name>.<addr>/module_name Date: March 2019 KernelVersion: 5.3 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (Read) Moxtet module name. Format: string diff --git a/Documentation/ABI/testing/sysfs-class-led-driver-turris-omnia b/Documentation/ABI/testing/sysfs-class-led-driver-turris-omnia index 795a5de12fc1..c4d46970c1cf 100644 --- a/Documentation/ABI/testing/sysfs-class-led-driver-turris-omnia +++ b/Documentation/ABI/testing/sysfs-class-led-driver-turris-omnia @@ -1,7 +1,7 @@ What: /sys/class/leds/<led>/device/brightness Date: July 2020 KernelVersion: 5.9 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (RW) On the front panel of the Turris Omnia router there is also a button which can be used to control the intensity of all the LEDs at once, so that if they are too bright, user can dim them. diff --git a/Documentation/ABI/testing/sysfs-firmware-sgi_uv b/Documentation/ABI/testing/sysfs-firmware-sgi_uv index 637c668cbe45..12ed843e1d3e 100644 --- a/Documentation/ABI/testing/sysfs-firmware-sgi_uv +++ b/Documentation/ABI/testing/sysfs-firmware-sgi_uv @@ -39,8 +39,8 @@ Description: The uv_type entry contains the hub revision number. This value can be used to identify the UV system version:: - "0.*" = Hubless UV ('*' is subtype) + "0.*" = Hubless UV ('*' is subtype) "3.0" = UV2 "5.0" = UV3 "7.0" = UV4 diff --git a/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm b/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm index b8631f5a29c4..ea5e5b489bc7 100644 --- a/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm +++ b/Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm @@ -1,21 +1,21 @@ What: /sys/firmware/turris-mox-rwtm/board_version Date: August 2019 KernelVersion: 5.4 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (Read) Board version burned into eFuses of this Turris Mox board. Format: %i What: /sys/firmware/turris-mox-rwtm/mac_address* Date: August 2019 KernelVersion: 5.4 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (Read) MAC addresses burned into eFuses of this Turris Mox board. Format: %pM What: /sys/firmware/turris-mox-rwtm/pubkey Date: August 2019 KernelVersion: 5.4 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (Read) ECDSA public key (in pubkey hex compressed form) computed as pair to the ECDSA private key burned into eFuses of this Turris Mox Board. @@ -24,7 +24,7 @@ Description: (Read) ECDSA public key (in pubkey hex compressed form) computed What: /sys/firmware/turris-mox-rwtm/ram_size Date: August 2019 KernelVersion: 5.4 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (Read) RAM size in MiB of this Turris Mox board as was detected during manufacturing and burned into eFuses. Can be 512 or 1024. Format: %i @@ -32,6 +32,6 @@ Description: (Read) RAM size in MiB of this Turris Mox board as was detected What: /sys/firmware/turris-mox-rwtm/serial_number Date: August 2019 KernelVersion: 5.4 -Contact: Marek Behún <marek.behun@nic.cz> +Contact: Marek Behún <kabel@kernel.org> Description: (Read) Serial number burned into eFuses of this Turris Mox device. Format: %016X diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 04545725f187..c8bad1762cba 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5462,6 +5462,18 @@ See Documentation/admin-guide/mm/transhuge.rst for more details. + trusted.source= [KEYS] + Format: <string> + This parameter identifies the trust source as a backend + for trusted keys implementation. Supported trust + sources: + - "tpm" + - "tee" + If not specified then it defaults to iterating through + the trust source list starting with TPM and assigns the + first trust source as a backend which is initialized + successfully during iteration. + tsc= Disable clocksource stability checks for TSC. Format: <string> [x86] reliable: mark tsc clocksource as reliable, this diff --git a/Documentation/arm64/acpi_object_usage.rst b/Documentation/arm64/acpi_object_usage.rst index 377e9d224db0..0609da73970b 100644 --- a/Documentation/arm64/acpi_object_usage.rst +++ b/Documentation/arm64/acpi_object_usage.rst @@ -17,12 +17,12 @@ For ACPI on arm64, tables also fall into the following categories: - Recommended: BERT, EINJ, ERST, HEST, PCCT, SSDT - - Optional: BGRT, CPEP, CSRT, DBG2, DRTM, ECDT, FACS, FPDT, IORT, - MCHI, MPST, MSCT, NFIT, PMTT, RASF, SBST, SLIT, SPMI, SRAT, STAO, - TCPA, TPM2, UEFI, XENV + - Optional: BGRT, CPEP, CSRT, DBG2, DRTM, ECDT, FACS, FPDT, IBFT, + IORT, MCHI, MPST, MSCT, NFIT, PMTT, RASF, SBST, SLIT, SPMI, SRAT, + STAO, TCPA, TPM2, UEFI, XENV - - Not supported: BOOT, DBGP, DMAR, ETDT, HPET, IBFT, IVRS, LPIT, - MSDM, OEMx, PSDT, RSDT, SLIC, WAET, WDAT, WDRT, WPBT + - Not supported: BOOT, DBGP, DMAR, ETDT, HPET, IVRS, LPIT, MSDM, OEMx, + PSDT, RSDT, SLIC, WAET, WDAT, WDRT, WPBT ====== ======================================================================== Table Usage for ARMv8 Linux diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 719510247292..d410a47ffa57 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -130,6 +130,9 @@ stable kernels. | Marvell | ARM-MMU-500 | #582743 | N/A | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ +| NVIDIA | Carmel Core | N/A | NVIDIA_CARMEL_CNP_ERRATUM | ++----------------+-----------------+-----------------+-----------------------------+ ++----------------+-----------------+-----------------+-----------------------------+ | Freescale/NXP | LS2080A/LS1043A | A-008585 | FSL_ERRATUM_A008585 | +----------------+-----------------+-----------------+-----------------------------+ +----------------+-----------------+-----------------+-----------------------------+ diff --git a/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml b/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml index 1d48ac712b23..a410d2cedde6 100644 --- a/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml +++ b/Documentation/devicetree/bindings/crypto/ti,sa2ul.yaml @@ -14,6 +14,7 @@ properties: enum: - ti,j721e-sa2ul - ti,am654-sa2ul + - ti,am64-sa2ul reg: maxItems: 1 @@ -45,6 +46,18 @@ properties: description: Address translation for the possible RNG child node for SA2UL + clocks: + items: + - description: Clock used by PKA + - description: Main Input Clock + - description: Clock used by rng + + clock-names: + items: + - const: pka_in_clk + - const: x1_clk + - const: x2_clk + patternProperties: "^rng@[a-f0-9]+$": type: object @@ -57,7 +70,16 @@ required: - power-domains - dmas - dma-names - - dma-coherent + +if: + properties: + compatible: + enum: + - ti,j721e-sa2ul + - ti,am654-sa2ul +then: + required: + - dma-coherent additionalProperties: false diff --git a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt index 37f18d684f6a..4c5c3712970e 100644 --- a/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt +++ b/Documentation/devicetree/bindings/hwmon/ntc_thermistor.txt @@ -32,7 +32,7 @@ Optional node properties: - "#thermal-sensor-cells" Used to expose itself to thermal fw. Read more about iio bindings at - Documentation/devicetree/bindings/iio/iio-bindings.txt + https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/ Example: ncp15wb473@0 { diff --git a/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml b/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml index ff99344788ab..fd040284561f 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-gpio.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Bindings for GPIO bitbanged I2C maintainers: - - Wolfram Sang <wolfram@the-dreams.de> + - Wolfram Sang <wsa@kernel.org> allOf: - $ref: /schemas/i2c/i2c-controller.yaml# diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx.yaml b/Documentation/devicetree/bindings/i2c/i2c-imx.yaml index f23966b0d6c6..3592d49235e0 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-imx.yaml +++ b/Documentation/devicetree/bindings/i2c/i2c-imx.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Freescale Inter IC (I2C) and High Speed Inter IC (HS-I2C) for i.MX maintainers: - - Wolfram Sang <wolfram@the-dreams.de> + - Oleksij Rempel <o.rempel@pengutronix.de> allOf: - $ref: /schemas/i2c/i2c-controller.yaml# diff --git a/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml b/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml index 9f414dbdae86..433a3fb55a2e 100644 --- a/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml +++ b/Documentation/devicetree/bindings/iio/adc/ingenic,adc.yaml @@ -14,8 +14,9 @@ description: > Industrial I/O subsystem bindings for ADC controller found in Ingenic JZ47xx SoCs. - ADC clients must use the format described in iio-bindings.txt, giving - a phandle and IIO specifier pair ("io-channels") to the ADC controller. + ADC clients must use the format described in + https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml, + giving a phandle and IIO specifier pair ("io-channels") to the ADC controller. properties: compatible: diff --git a/Documentation/devicetree/bindings/input/adc-joystick.yaml b/Documentation/devicetree/bindings/input/adc-joystick.yaml index 054406bbd22b..721878d5b7af 100644 --- a/Documentation/devicetree/bindings/input/adc-joystick.yaml +++ b/Documentation/devicetree/bindings/input/adc-joystick.yaml @@ -24,7 +24,9 @@ properties: description: > List of phandle and IIO specifier pairs. Each pair defines one ADC channel to which a joystick axis is connected. - See Documentation/devicetree/bindings/iio/iio-bindings.txt for details. + See + https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml + for details. '#address-cells': const: 1 diff --git a/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt b/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt index 51456c0e9a27..af5223bb5bdd 100644 --- a/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt +++ b/Documentation/devicetree/bindings/input/touchscreen/resistive-adc-touch.txt @@ -5,7 +5,10 @@ Required properties: - compatible: must be "resistive-adc-touch" The device must be connected to an ADC device that provides channels for position measurement and optional pressure. -Refer to ../iio/iio-bindings.txt for details +Refer to +https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml +for details + - iio-channels: must have at least two channels connected to an ADC device. These should correspond to the channels exposed by the ADC device and should have the right index as the ADC device registers them. These channels diff --git a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml index fe7fa25877fd..c7ed2871da06 100644 --- a/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml +++ b/Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: CZ.NIC's Turris Omnia LEDs driver maintainers: - - Marek Behún <marek.behun@nic.cz> + - Marek Behún <kabel@kernel.org> description: This module adds support for the RGB LEDs found on the front panel of the diff --git a/Documentation/devicetree/bindings/mfd/ab8500.txt b/Documentation/devicetree/bindings/mfd/ab8500.txt index d2a6e835c257..937b3e5505e0 100644 --- a/Documentation/devicetree/bindings/mfd/ab8500.txt +++ b/Documentation/devicetree/bindings/mfd/ab8500.txt @@ -72,7 +72,9 @@ Required child device properties: pwm|regulator|rtc|sysctrl|usb]"; A few child devices require ADC channels from the GPADC node. Those follow the - standard bindings from iio/iio-bindings.txt and iio/adc/adc.txt + standard bindings from + https://github.com/devicetree-org/dt-schema/blob/master/schemas/iio/iio-consumer.yaml + and Documentation/devicetree/bindings/iio/adc/adc.yaml abx500-temp : io-channels "aux1" and "aux2" for measuring external temperatures. diff --git a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt index 5ddcc8f4febc..b52e7a33f0f9 100644 --- a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt +++ b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt @@ -16,14 +16,14 @@ Optional subnodes: The sub-functions of CPCAP get their own node with their own compatible values, which are described in the following files: -- ../power/supply/cpcap-battery.txt -- ../power/supply/cpcap-charger.txt -- ../regulator/cpcap-regulator.txt -- ../phy/phy-cpcap-usb.txt -- ../input/cpcap-pwrbutton.txt -- ../rtc/cpcap-rtc.txt -- ../leds/leds-cpcap.txt -- ../iio/adc/cpcap-adc.txt +- Documentation/devicetree/bindings/power/supply/cpcap-battery.txt +- Documentation/devicetree/bindings/power/supply/cpcap-charger.txt +- Documentation/devicetree/bindings/regulator/cpcap-regulator.txt +- Documentation/devicetree/bindings/phy/phy-cpcap-usb.txt +- Documentation/devicetree/bindings/input/cpcap-pwrbutton.txt +- Documentation/devicetree/bindings/rtc/cpcap-rtc.txt +- Documentation/devicetree/bindings/leds/leds-cpcap.txt +- Documentation/devicetree/bindings/iio/adc/motorola,cpcap-adc.yaml The only exception is the audio codec. Instead of a compatible value its node must be named "audio-codec". diff --git a/Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml b/Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml index 79c38ea14237..13c26f23a820 100644 --- a/Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml +++ b/Documentation/devicetree/bindings/net/brcm,bcm4908-enet.yaml @@ -32,7 +32,7 @@ required: - interrupts - interrupt-names -additionalProperties: false +unevaluatedProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/net/ethernet-controller.yaml b/Documentation/devicetree/bindings/net/ethernet-controller.yaml index 4b7d1e5d003c..e8f04687a3e0 100644 --- a/Documentation/devicetree/bindings/net/ethernet-controller.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-controller.yaml @@ -49,7 +49,7 @@ properties: description: Reference to an nvmem node for the MAC address - nvmem-cells-names: + nvmem-cell-names: const: mac-address phy-connection-type: diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt index b921731cd970..df9e844dd6bc 100644 --- a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt +++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt @@ -65,6 +65,71 @@ KSZ9031: step is 60ps. The default value is the neutral setting, so setting rxc-skew-ps=<0> actually results in -900 picoseconds adjustment. + The KSZ9031 hardware supports a range of skew values from negative to + positive, where the specific range is property dependent. All values + specified in the devicetree are offset by the minimum value so they + can be represented as positive integers in the devicetree since it's + difficult to represent a negative number in the devictree. + + The following 5-bit values table apply to rxc-skew-ps and txc-skew-ps. + + Pad Skew Value Delay (ps) Devicetree Value + ------------------------------------------------------ + 0_0000 -900ps 0 + 0_0001 -840ps 60 + 0_0010 -780ps 120 + 0_0011 -720ps 180 + 0_0100 -660ps 240 + 0_0101 -600ps 300 + 0_0110 -540ps 360 + 0_0111 -480ps 420 + 0_1000 -420ps 480 + 0_1001 -360ps 540 + 0_1010 -300ps 600 + 0_1011 -240ps 660 + 0_1100 -180ps 720 + 0_1101 -120ps 780 + 0_1110 -60ps 840 + 0_1111 0ps 900 + 1_0000 60ps 960 + 1_0001 120ps 1020 + 1_0010 180ps 1080 + 1_0011 240ps 1140 + 1_0100 300ps 1200 + 1_0101 360ps 1260 + 1_0110 420ps 1320 + 1_0111 480ps 1380 + 1_1000 540ps 1440 + 1_1001 600ps 1500 + 1_1010 660ps 1560 + 1_1011 720ps 1620 + 1_1100 780ps 1680 + 1_1101 840ps 1740 + 1_1110 900ps 1800 + 1_1111 960ps 1860 + + The following 4-bit values table apply to the txdX-skew-ps, rxdX-skew-ps + data pads, and the rxdv-skew-ps, txen-skew-ps control pads. + + Pad Skew Value Delay (ps) Devicetree Value + ------------------------------------------------------ + 0000 -420ps 0 + 0001 -360ps 60 + 0010 -300ps 120 + 0011 -240ps 180 + 0100 -180ps 240 + 0101 -120ps 300 + 0110 -60ps 360 + 0111 0ps 420 + 1000 60ps 480 + 1001 120ps 540 + 1010 180ps 600 + 1011 240ps 660 + 1100 300ps 720 + 1101 360ps 780 + 1110 420ps 840 + 1111 480ps 900 + Optional properties: Maximum value of 1860, default value 900: @@ -120,11 +185,21 @@ KSZ9131: Examples: + /* Attach to an Ethernet device with autodetected PHY */ + &enet { + rxc-skew-ps = <1800>; + rxdv-skew-ps = <0>; + txc-skew-ps = <1800>; + txen-skew-ps = <0>; + status = "okay"; + }; + + /* Attach to an explicitly-specified PHY */ mdio { phy0: ethernet-phy@0 { - rxc-skew-ps = <3000>; + rxc-skew-ps = <1800>; rxdv-skew-ps = <0>; - txc-skew-ps = <3000>; + txc-skew-ps = <1800>; txen-skew-ps = <0>; reg = <0>; }; @@ -133,3 +208,20 @@ Examples: phy = <&phy0>; phy-mode = "rgmii-id"; }; + +References + + Micrel ksz9021rl/rn Data Sheet, Revision 1.2. Dated 2/13/2014. + http://www.micrel.com/_PDF/Ethernet/datasheets/ksz9021rl-rn_ds.pdf + + Micrel ksz9031rnx Data Sheet, Revision 2.1. Dated 11/20/2014. + http://www.micrel.com/_PDF/Ethernet/datasheets/KSZ9031RNX.pdf + +Notes: + + Note that a previous version of the Micrel ksz9021rl/rn Data Sheet + was missing extended register 106 (transmit data pad skews), and + incorrectly specified the ps per step as 200ps/step instead of + 120ps/step. The latest update to this document reflects the latest + revision of the Micrel specification even though usage in the kernel + still reflects that incorrect document. diff --git a/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml b/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml index c147900f9041..6da674666d45 100644 --- a/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml +++ b/Documentation/devicetree/bindings/rng/brcm,bcm2835.yaml @@ -28,6 +28,12 @@ properties: clock-names: const: ipsec + resets: + maxItems: 1 + + reset-names: + const: ipsec + interrupts: maxItems: 1 @@ -35,6 +41,18 @@ required: - compatible - reg +if: + properties: + compatible: + enum: + - brcm,bcm6368-rng +then: + required: + - clocks + - clock-names + - resets + - reset-names + additionalProperties: false examples: @@ -58,4 +76,7 @@ examples: clocks = <&periph_clk 18>; clock-names = "ipsec"; + + resets = <&periph_rst 4>; + reset-names = "ipsec"; }; diff --git a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst index 3561a8a29fd2..f8c6469f2bd2 100644 --- a/Documentation/networking/device_drivers/ethernet/amazon/ena.rst +++ b/Documentation/networking/device_drivers/ethernet/amazon/ena.rst @@ -267,7 +267,7 @@ DATA PATH Tx -- -end_start_xmit() is called by the stack. This function does the following: +ena_start_xmit() is called by the stack. This function does the following: - Maps data buffers (skb->data and frags). - Populates ena_buf for the push buffer (if the driver and device are diff --git a/Documentation/networking/devlink/devlink-dpipe.rst b/Documentation/networking/devlink/devlink-dpipe.rst index 468fe1001b74..af37f250df43 100644 --- a/Documentation/networking/devlink/devlink-dpipe.rst +++ b/Documentation/networking/devlink/devlink-dpipe.rst @@ -52,7 +52,7 @@ purposes as a standard complementary tool. The system's view from ``devlink-dpipe`` should change according to the changes done by the standard configuration tools. -For example, it’s quiet common to implement Access Control Lists (ACL) +For example, it’s quite common to implement Access Control Lists (ACL) using Ternary Content Addressable Memory (TCAM). The TCAM memory can be divided into TCAM regions. Complex TC filters can have multiple rules with different priorities and different lookup keys. On the other hand hardware diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index e99b41599465..ab790e7980b8 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -151,7 +151,7 @@ representor netdevice. ------------- A subfunction devlink port is created but it is not active yet. That means the entities are created on devlink side, the e-switch port representor is created, -but the subfunction device itself it not created. A user might use e-switch port +but the subfunction device itself is not created. A user might use e-switch port representor to do settings, putting it into bridge, adding TC rules, etc. A user might as well configure the hardware address (such as MAC address) of the subfunction while subfunction is inactive. @@ -173,7 +173,7 @@ Terms and Definitions * - Term - Definitions * - ``PCI device`` - - A physical PCI device having one or more PCI bus consists of one or + - A physical PCI device having one or more PCI buses consists of one or more PCI controllers. * - ``PCI controller`` - A controller consists of potentially multiple physical functions, diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 05073482db05..dc03ff884541 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -976,9 +976,9 @@ constraints on coalescing parameters and their values. PAUSE_GET -============ +========= -Gets channel counts like ``ETHTOOL_GPAUSE`` ioctl request. +Gets pause frame settings like ``ETHTOOL_GPAUSEPARAM`` ioctl request. Request contents: @@ -1007,7 +1007,7 @@ the statistics in the following structure: Each member has a corresponding attribute defined. PAUSE_SET -============ +========= Sets pause parameters like ``ETHTOOL_GPAUSEPARAM`` ioctl request. @@ -1024,7 +1024,7 @@ Request contents: EEE_GET ======= -Gets channel counts like ``ETHTOOL_GEEE`` ioctl request. +Gets Energy Efficient Ethernet settings like ``ETHTOOL_GEEE`` ioctl request. Request contents: @@ -1054,7 +1054,7 @@ first 32 are provided by the ``ethtool_ops`` callback. EEE_SET ======= -Sets pause parameters like ``ETHTOOL_GEEEPARAM`` ioctl request. +Sets Energy Efficient Ethernet parameters like ``ETHTOOL_SEEE`` ioctl request. Request contents: diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index c7952ac5bd2f..3feb5e565b1a 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1849,21 +1849,6 @@ ip6frag_low_thresh - INTEGER ip6frag_time - INTEGER Time in seconds to keep an IPv6 fragment in memory. -IPv6 Segment Routing: - -seg6_flowlabel - INTEGER - Controls the behaviour of computing the flowlabel of outer - IPv6 header in case of SR T.encaps - - == ======================================================= - -1 set flowlabel to zero. - 0 copy flowlabel from Inner packet in case of Inner IPv6 - (Set flowlabel to 0 in case IPv4/L2) - 1 Compute the flowlabel using seg6_make_flowlabel() - == ======================================================= - - Default is 0. - ``conf/default/*``: Change the interface-specific default settings. diff --git a/Documentation/networking/seg6-sysctl.rst b/Documentation/networking/seg6-sysctl.rst index ec73e1445030..07c20e470baf 100644 --- a/Documentation/networking/seg6-sysctl.rst +++ b/Documentation/networking/seg6-sysctl.rst @@ -24,3 +24,16 @@ seg6_require_hmac - INTEGER * 1 - Drop SR packets without HMAC, validate SR packets with HMAC Default is 0. + +seg6_flowlabel - INTEGER + Controls the behaviour of computing the flowlabel of outer + IPv6 header in case of SR T.encaps + + == ======================================================= + -1 set flowlabel to zero. + 0 copy flowlabel from Inner packet in case of Inner IPv6 + (Set flowlabel to 0 in case IPv4/L2) + 1 Compute the flowlabel using seg6_make_flowlabel() + == ======================================================= + + Default is 0. diff --git a/Documentation/networking/xfrm_device.rst b/Documentation/networking/xfrm_device.rst index da1073acda96..01391dfd37d9 100644 --- a/Documentation/networking/xfrm_device.rst +++ b/Documentation/networking/xfrm_device.rst @@ -50,7 +50,7 @@ Callbacks to implement The NIC driver offering ipsec offload will need to implement these callbacks to make the offload available to the network stack's -XFRM subsytem. Additionally, the feature bits NETIF_F_HW_ESP and +XFRM subsystem. Additionally, the feature bits NETIF_F_HW_ESP and NETIF_F_HW_ESP_TX_CSUM will signal the availability of the offload. diff --git a/Documentation/security/keys/trusted-encrypted.rst b/Documentation/security/keys/trusted-encrypted.rst index 1da879a68640..80d5a5af62a1 100644 --- a/Documentation/security/keys/trusted-encrypted.rst +++ b/Documentation/security/keys/trusted-encrypted.rst @@ -6,30 +6,127 @@ Trusted and Encrypted Keys are two new key types added to the existing kernel key ring service. Both of these new types are variable length symmetric keys, and in both cases all keys are created in the kernel, and user space sees, stores, and loads only encrypted blobs. Trusted Keys require the availability -of a Trusted Platform Module (TPM) chip for greater security, while Encrypted -Keys can be used on any system. All user level blobs, are displayed and loaded -in hex ascii for convenience, and are integrity verified. +of a Trust Source for greater security, while Encrypted Keys can be used on any +system. All user level blobs, are displayed and loaded in hex ASCII for +convenience, and are integrity verified. -Trusted Keys use a TPM both to generate and to seal the keys. Keys are sealed -under a 2048 bit RSA key in the TPM, and optionally sealed to specified PCR -(integrity measurement) values, and only unsealed by the TPM, if PCRs and blob -integrity verifications match. A loaded Trusted Key can be updated with new -(future) PCR values, so keys are easily migrated to new pcr values, such as -when the kernel and initramfs are updated. The same key can have many saved -blobs under different PCR values, so multiple boots are easily supported. -TPM 1.2 -------- +Trust Source +============ -By default, trusted keys are sealed under the SRK, which has the default -authorization value (20 zeros). This can be set at takeownership time with the -trouser's utility: "tpm_takeownership -u -z". +A trust source provides the source of security for Trusted Keys. This +section lists currently supported trust sources, along with their security +considerations. Whether or not a trust source is sufficiently safe depends +on the strength and correctness of its implementation, as well as the threat +environment for a specific use case. Since the kernel doesn't know what the +environment is, and there is no metric of trust, it is dependent on the +consumer of the Trusted Keys to determine if the trust source is sufficiently +safe. -TPM 2.0 -------- + * Root of trust for storage -The user must first create a storage key and make it persistent, so the key is -available after reboot. This can be done using the following commands. + (1) TPM (Trusted Platform Module: hardware device) + + Rooted to Storage Root Key (SRK) which never leaves the TPM that + provides crypto operation to establish root of trust for storage. + + (2) TEE (Trusted Execution Environment: OP-TEE based on Arm TrustZone) + + Rooted to Hardware Unique Key (HUK) which is generally burnt in on-chip + fuses and is accessible to TEE only. + + * Execution isolation + + (1) TPM + + Fixed set of operations running in isolated execution environment. + + (2) TEE + + Customizable set of operations running in isolated execution + environment verified via Secure/Trusted boot process. + + * Optional binding to platform integrity state + + (1) TPM + + Keys can be optionally sealed to specified PCR (integrity measurement) + values, and only unsealed by the TPM, if PCRs and blob integrity + verifications match. A loaded Trusted Key can be updated with new + (future) PCR values, so keys are easily migrated to new PCR values, + such as when the kernel and initramfs are updated. The same key can + have many saved blobs under different PCR values, so multiple boots are + easily supported. + + (2) TEE + + Relies on Secure/Trusted boot process for platform integrity. It can + be extended with TEE based measured boot process. + + * Interfaces and APIs + + (1) TPM + + TPMs have well-documented, standardized interfaces and APIs. + + (2) TEE + + TEEs have well-documented, standardized client interface and APIs. For + more details refer to ``Documentation/staging/tee.rst``. + + + * Threat model + + The strength and appropriateness of a particular TPM or TEE for a given + purpose must be assessed when using them to protect security-relevant data. + + +Key Generation +============== + +Trusted Keys +------------ + +New keys are created from random numbers generated in the trust source. They +are encrypted/decrypted using a child key in the storage key hierarchy. +Encryption and decryption of the child key must be protected by a strong +access control policy within the trust source. + + * TPM (hardware device) based RNG + + Strength of random numbers may vary from one device manufacturer to + another. + + * TEE (OP-TEE based on Arm TrustZone) based RNG + + RNG is customizable as per platform needs. It can either be direct output + from platform specific hardware RNG or a software based Fortuna CSPRNG + which can be seeded via multiple entropy sources. + +Encrypted Keys +-------------- + +Encrypted keys do not depend on a trust source, and are faster, as they use AES +for encryption/decryption. New keys are created from kernel-generated random +numbers, and are encrypted/decrypted using a specified ‘master’ key. The +‘master’ key can either be a trusted-key or user-key type. The main disadvantage +of encrypted keys is that if they are not rooted in a trusted key, they are only +as secure as the user key encrypting them. The master user key should therefore +be loaded in as secure a way as possible, preferably early in boot. + + +Usage +===== + +Trusted Keys usage: TPM +----------------------- + +TPM 1.2: By default, trusted keys are sealed under the SRK, which has the +default authorization value (20 bytes of 0s). This can be set at takeownership +time with the TrouSerS utility: "tpm_takeownership -u -z". + +TPM 2.0: The user must first create a storage key and make it persistent, so the +key is available after reboot. This can be done using the following commands. With the IBM TSS 2 stack:: @@ -78,14 +175,21 @@ TPM_STORED_DATA format. The key length for new keys are always in bytes. Trusted Keys can be 32 - 128 bytes (256 - 1024 bits), the upper limit is to fit within the 2048 bit SRK (RSA) keylength, with all necessary structure/padding. -Encrypted keys do not depend on a TPM, and are faster, as they use AES for -encryption/decryption. New keys are created from kernel generated random -numbers, and are encrypted/decrypted using a specified 'master' key. The -'master' key can either be a trusted-key or user-key type. The main -disadvantage of encrypted keys is that if they are not rooted in a trusted key, -they are only as secure as the user key encrypting them. The master user key -should therefore be loaded in as secure a way as possible, preferably early in -boot. +Trusted Keys usage: TEE +----------------------- + +Usage:: + + keyctl add trusted name "new keylen" ring + keyctl add trusted name "load hex_blob" ring + keyctl print keyid + +"keyctl print" returns an ASCII hex copy of the sealed key, which is in format +specific to TEE device implementation. The key length for new keys is always +in bytes. Trusted Keys can be 32 - 128 bytes (256 - 1024 bits). + +Encrypted Keys usage +-------------------- The decrypted portion of encrypted keys can contain either a simple symmetric key or a more complex structure. The format of the more complex structure is @@ -103,8 +207,8 @@ Where:: format:= 'default | ecryptfs | enc32' key-type:= 'trusted' | 'user' - -Examples of trusted and encrypted key usage: +Examples of trusted and encrypted key usage +------------------------------------------- Create and save a trusted key named "kmk" of length 32 bytes. @@ -150,7 +254,7 @@ Load a trusted key from the saved blob:: f1f8fff03ad0acb083725535636addb08d73dedb9832da198081e5deae84bfaf0409c22b e4a8aea2b607ec96931e6f4d4fe563ba -Reseal a trusted key under new pcr values:: +Reseal (TPM specific) a trusted key under new PCR values:: $ keyctl update 268728824 "update pcrinfo=`cat pcr.blob`" $ keyctl print 268728824 @@ -164,11 +268,12 @@ Reseal a trusted key under new pcr values:: 7ef6a24defe4846104209bf0c3eced7fa1a672ed5b125fc9d8cd88b476a658a4434644ef df8ae9a178e9f83ba9f08d10fa47e4226b98b0702f06b3b8 + The initial consumer of trusted keys is EVM, which at boot time needs a high -quality symmetric key for HMAC protection of file metadata. The use of a +quality symmetric key for HMAC protection of file metadata. The use of a trusted key provides strong guarantees that the EVM key has not been -compromised by a user level problem, and when sealed to specific boot PCR -values, protects against boot and offline attacks. Create and save an +compromised by a user level problem, and when sealed to a platform integrity +state, protects against boot and offline attacks. Create and save an encrypted key "evm" using the above trusted key "kmk": option 1: omitting 'format':: @@ -207,3 +312,61 @@ about the usage can be found in the file Another new format 'enc32' has been defined in order to support encrypted keys with payload size of 32 bytes. This will initially be used for nvdimm security but may expand to other usages that require 32 bytes payload. + + +TPM 2.0 ASN.1 Key Format +------------------------ + +The TPM 2.0 ASN.1 key format is designed to be easily recognisable, +even in binary form (fixing a problem we had with the TPM 1.2 ASN.1 +format) and to be extensible for additions like importable keys and +policy:: + + TPMKey ::= SEQUENCE { + type OBJECT IDENTIFIER + emptyAuth [0] EXPLICIT BOOLEAN OPTIONAL + parent INTEGER + pubkey OCTET STRING + privkey OCTET STRING + } + +type is what distinguishes the key even in binary form since the OID +is provided by the TCG to be unique and thus forms a recognizable +binary pattern at offset 3 in the key. The OIDs currently made +available are:: + + 2.23.133.10.1.3 TPM Loadable key. This is an asymmetric key (Usually + RSA2048 or Elliptic Curve) which can be imported by a + TPM2_Load() operation. + + 2.23.133.10.1.4 TPM Importable Key. This is an asymmetric key (Usually + RSA2048 or Elliptic Curve) which can be imported by a + TPM2_Import() operation. + + 2.23.133.10.1.5 TPM Sealed Data. This is a set of data (up to 128 + bytes) which is sealed by the TPM. It usually + represents a symmetric key and must be unsealed before + use. + +The trusted key code only uses the TPM Sealed Data OID. + +emptyAuth is true if the key has well known authorization "". If it +is false or not present, the key requires an explicit authorization +phrase. This is used by most user space consumers to decide whether +to prompt for a password. + +parent represents the parent key handle, either in the 0x81 MSO space, +like 0x81000001 for the RSA primary storage key. Userspace programmes +also support specifying the primary handle in the 0x40 MSO space. If +this happens the Elliptic Curve variant of the primary key using the +TCG defined template will be generated on the fly into a volatile +object and used as the parent. The current kernel code only supports +the 0x81 MSO form. + +pubkey is the binary representation of TPM2B_PRIVATE excluding the +initial TPM2B header, which can be reconstructed from the ASN.1 octet +string length. + +privkey is the binary representation of TPM2B_PUBLIC excluding the +initial TPM2B header which can be reconstructed from the ASN.1 octed +string length. diff --git a/Documentation/x86/sgx.rst b/Documentation/x86/sgx.rst index eaee1368b4fd..dd0ac96ff9ef 100644 --- a/Documentation/x86/sgx.rst +++ b/Documentation/x86/sgx.rst @@ -209,3 +209,44 @@ An application may be loaded into a container enclave which is specially configured with a library OS and run-time which permits the application to run. The enclave run-time and library OS work together to execute the application when a thread enters the enclave. + +Impact of Potential Kernel SGX Bugs +=================================== + +EPC leaks +--------- + +When EPC page leaks happen, a WARNING like this is shown in dmesg: + +"EREMOVE returned ... and an EPC page was leaked. SGX may become unusable..." + +This is effectively a kernel use-after-free of an EPC page, and due +to the way SGX works, the bug is detected at freeing. Rather than +adding the page back to the pool of available EPC pages, the kernel +intentionally leaks the page to avoid additional errors in the future. + +When this happens, the kernel will likely soon leak more EPC pages, and +SGX will likely become unusable because the memory available to SGX is +limited. However, while this may be fatal to SGX, the rest of the kernel +is unlikely to be impacted and should continue to work. + +As a result, when this happpens, user should stop running any new +SGX workloads, (or just any new workloads), and migrate all valuable +workloads. Although a machine reboot can recover all EPC memory, the bug +should be reported to Linux developers. + + +Virtual EPC +=========== + +The implementation has also a virtual EPC driver to support SGX enclaves +in guests. Unlike the SGX driver, an EPC page allocated by the virtual +EPC driver doesn't have a specific enclave associated with it. This is +because KVM doesn't track how a guest uses EPC pages. + +As a result, the SGX core page reclaimer doesn't support reclaiming EPC +pages allocated to KVM guests through the virtual EPC driver. If the +user wants to deploy SGX applications both on the host and in guests +on the same machine, the user should reserve enough EPC (by taking out +total virtual EPC size of all SGX VMs from the physical EPC size) for +host SGX applications so they can run with acceptable performance. diff --git a/MAINTAINERS b/MAINTAINERS index 9e876927c60d..837457cf70a6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1576,11 +1576,13 @@ R: Jernej Skrabec <jernej.skrabec@siol.net> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/sunxi/linux.git +L: linux-sunxi@lists.linux.dev F: arch/arm/mach-sunxi/ F: arch/arm64/boot/dts/allwinner/ F: drivers/clk/sunxi-ng/ F: drivers/pinctrl/sunxi/ F: drivers/soc/sunxi/ +N: allwinner N: sun[x456789]i N: sun50i @@ -1790,19 +1792,26 @@ F: drivers/net/ethernet/cortina/ F: drivers/pinctrl/pinctrl-gemini.c F: drivers/rtc/rtc-ftrtc010.c -ARM/CZ.NIC TURRIS MOX SUPPORT -M: Marek Behun <marek.behun@nic.cz> +ARM/CZ.NIC TURRIS SUPPORT +M: Marek Behun <kabel@kernel.org> S: Maintained -W: http://mox.turris.cz +W: https://www.turris.cz/ F: Documentation/ABI/testing/debugfs-moxtet F: Documentation/ABI/testing/sysfs-bus-moxtet-devices F: Documentation/ABI/testing/sysfs-firmware-turris-mox-rwtm F: Documentation/devicetree/bindings/bus/moxtet.txt F: Documentation/devicetree/bindings/firmware/cznic,turris-mox-rwtm.txt F: Documentation/devicetree/bindings/gpio/gpio-moxtet.txt +F: Documentation/devicetree/bindings/leds/cznic,turris-omnia-leds.yaml +F: Documentation/devicetree/bindings/watchdog/armada-37xx-wdt.txt F: drivers/bus/moxtet.c F: drivers/firmware/turris-mox-rwtm.c +F: drivers/leds/leds-turris-omnia.c +F: drivers/mailbox/armada-37xx-rwtm-mailbox.c F: drivers/gpio/gpio-moxtet.c +F: drivers/watchdog/armada_37xx_wdt.c +F: include/dt-bindings/bus/moxtet.h +F: include/linux/armada-37xx-rwtm-mailbox.h F: include/linux/moxtet.h ARM/EZX SMARTPHONES (A780, A910, A1200, E680, ROKR E2 and ROKR E6) @@ -2489,7 +2498,7 @@ N: sc27xx N: sc2731 ARM/STI ARCHITECTURE -M: Patrice Chotard <patrice.chotard@st.com> +M: Patrice Chotard <patrice.chotard@foss.st.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained W: http://www.stlinux.com @@ -2522,7 +2531,7 @@ F: include/linux/remoteproc/st_slim_rproc.h ARM/STM32 ARCHITECTURE M: Maxime Coquelin <mcoquelin.stm32@gmail.com> -M: Alexandre Torgue <alexandre.torgue@st.com> +M: Alexandre Torgue <alexandre.torgue@foss.st.com> L: linux-stm32@st-md-mailman.stormreply.com (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -3115,7 +3124,7 @@ C: irc://irc.oftc.net/bcache F: drivers/md/bcache/ BDISP ST MEDIA DRIVER -M: Fabien Dessenne <fabien.dessenne@st.com> +M: Fabien Dessenne <fabien.dessenne@foss.st.com> L: linux-media@vger.kernel.org S: Supported W: https://linuxtv.org @@ -3675,7 +3684,7 @@ M: bcm-kernel-feedback-list@broadcom.com L: linux-pm@vger.kernel.org S: Maintained T: git git://github.com/broadcom/stblinux.git -F: drivers/soc/bcm/bcm-pmb.c +F: drivers/soc/bcm/bcm63xx/bcm-pmb.c F: include/dt-bindings/soc/bcm-pmb.h BROADCOM SPECIFIC AMBA DRIVER (BCMA) @@ -5080,7 +5089,7 @@ S: Maintained F: drivers/platform/x86/dell/dell-wmi.c DELTA ST MEDIA DRIVER -M: Hugues Fruchet <hugues.fruchet@st.com> +M: Hugues Fruchet <hugues.fruchet@foss.st.com> L: linux-media@vger.kernel.org S: Supported W: https://linuxtv.org @@ -6006,7 +6015,6 @@ F: drivers/gpu/drm/rockchip/ DRM DRIVERS FOR STI M: Benjamin Gaignard <benjamin.gaignard@linaro.org> -M: Vincent Abriou <vincent.abriou@st.com> L: dri-devel@lists.freedesktop.org S: Maintained T: git git://anongit.freedesktop.org/drm/drm-misc @@ -6014,10 +6022,9 @@ F: Documentation/devicetree/bindings/display/st,stih4xx.txt F: drivers/gpu/drm/sti DRM DRIVERS FOR STM -M: Yannick Fertre <yannick.fertre@st.com> -M: Philippe Cornu <philippe.cornu@st.com> +M: Yannick Fertre <yannick.fertre@foss.st.com> +M: Philippe Cornu <philippe.cornu@foss.st.com> M: Benjamin Gaignard <benjamin.gaignard@linaro.org> -M: Vincent Abriou <vincent.abriou@st.com> L: dri-devel@lists.freedesktop.org S: Maintained T: git git://anongit.freedesktop.org/drm/drm-misc @@ -7091,7 +7098,7 @@ S: Maintained F: drivers/i2c/busses/i2c-cpm.c FREESCALE IMX / MXC FEC DRIVER -M: Fugang Duan <fugang.duan@nxp.com> +M: Joakim Zhang <qiangqing.zhang@nxp.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/fsl-fec.txt @@ -7476,8 +7483,9 @@ F: include/uapi/asm-generic/ GENERIC PHY FRAMEWORK M: Kishon Vijay Abraham I <kishon@ti.com> M: Vinod Koul <vkoul@kernel.org> -L: linux-kernel@vger.kernel.org +L: linux-phy@lists.infradead.org S: Supported +Q: https://patchwork.kernel.org/project/linux-phy/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy.git F: Documentation/devicetree/bindings/phy/ F: drivers/phy/ @@ -8230,7 +8238,7 @@ F: include/linux/hugetlb.h F: mm/hugetlb.c HVA ST MEDIA DRIVER -M: Jean-Christophe Trotin <jean-christophe.trotin@st.com> +M: Jean-Christophe Trotin <jean-christophe.trotin@foss.st.com> L: linux-media@vger.kernel.org S: Supported W: https://linuxtv.org @@ -8518,8 +8526,9 @@ F: drivers/pci/hotplug/rpaphp* IBM Power SRIOV Virtual NIC Device Driver M: Dany Madden <drt@linux.ibm.com> -M: Lijun Pan <ljp@linux.ibm.com> M: Sukadev Bhattiprolu <sukadev@linux.ibm.com> +R: Thomas Falcon <tlfalcon@linux.ibm.com> +R: Lijun Pan <lijunp213@gmail.com> L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/ibm/ibmvnic.* @@ -8603,9 +8612,8 @@ F: drivers/ide/ F: include/linux/ide.h IDE/ATAPI DRIVERS -M: Borislav Petkov <bp@alien8.de> L: linux-ide@vger.kernel.org -S: Maintained +S: Orphan F: Documentation/cdrom/ide-cd.rst F: drivers/ide/ide-cd* @@ -9273,6 +9281,7 @@ Q: https://patchwork.kernel.org/project/intel-sgx/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/sgx F: Documentation/x86/sgx.rst F: arch/x86/entry/vdso/vsgx.S +F: arch/x86/include/asm/sgx.h F: arch/x86/include/uapi/asm/sgx.h F: arch/x86/kernel/cpu/sgx/* F: tools/testing/selftests/sgx/* @@ -9878,6 +9887,14 @@ F: include/keys/trusted-type.h F: include/keys/trusted_tpm.h F: security/keys/trusted-keys/ +KEYS-TRUSTED-TEE +M: Sumit Garg <sumit.garg@linaro.org> +L: linux-integrity@vger.kernel.org +L: keyrings@vger.kernel.org +S: Supported +F: include/keys/trusted_tee.h +F: security/keys/trusted-keys/trusted_tee.c + KEYS/KEYRINGS M: David Howells <dhowells@redhat.com> M: Jarkko Sakkinen <jarkko@kernel.org> @@ -10029,7 +10046,6 @@ F: scripts/leaking_addresses.pl LED SUBSYSTEM M: Pavel Machek <pavel@ucw.cz> -R: Dan Murphy <dmurphy@ti.com> L: linux-leds@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/pavel/linux-leds.git @@ -10905,7 +10921,6 @@ T: git git://linuxtv.org/media_tree.git F: drivers/media/radio/radio-maxiradio* MCAN MMIO DEVICE DRIVER -M: Dan Murphy <dmurphy@ti.com> M: Pankaj Sharma <pankj.sharma@samsung.com> L: linux-can@vger.kernel.org S: Maintained @@ -11166,7 +11181,7 @@ T: git git://linuxtv.org/media_tree.git F: drivers/media/dvb-frontends/stv6111* MEDIA DRIVERS FOR STM32 - DCMI -M: Hugues Fruchet <hugues.fruchet@st.com> +M: Hugues Fruchet <hugues.fruchet@foss.st.com> L: linux-media@vger.kernel.org S: Supported T: git git://linuxtv.org/media_tree.git @@ -12537,7 +12552,7 @@ NETWORKING [MPTCP] M: Mat Martineau <mathew.j.martineau@linux.intel.com> M: Matthieu Baerts <matthieu.baerts@tessares.net> L: netdev@vger.kernel.org -L: mptcp@lists.01.org +L: mptcp@lists.linux.dev S: Maintained W: https://github.com/multipath-tcp/mptcp_net-next/wiki B: https://github.com/multipath-tcp/mptcp_net-next/issues @@ -14708,15 +14723,11 @@ F: drivers/net/ethernet/qlogic/qlcnic/ QLOGIC QLGE 10Gb ETHERNET DRIVER M: Manish Chopra <manishc@marvell.com> M: GR-Linux-NIC-Dev@marvell.com -L: netdev@vger.kernel.org -S: Supported -F: drivers/staging/qlge/ - -QLOGIC QLGE 10Gb ETHERNET DRIVER M: Coiby Xu <coiby.xu@gmail.com> L: netdev@vger.kernel.org -S: Maintained +S: Supported F: Documentation/networking/device_drivers/qlogic/qlge.rst +F: drivers/staging/qlge/ QM1D1B0004 MEDIA DRIVER M: Akihiro Tsukada <tskd08@gmail.com> @@ -14856,6 +14867,14 @@ L: linux-arm-msm@vger.kernel.org S: Maintained F: drivers/iommu/arm/arm-smmu/qcom_iommu.c +QUALCOMM IPC ROUTER (QRTR) DRIVER +M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> +L: linux-arm-msm@vger.kernel.org +S: Maintained +F: include/trace/events/qrtr.h +F: include/uapi/linux/qrtr.h +F: net/qrtr/ + QUALCOMM IPCC MAILBOX DRIVER M: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> L: linux-arm-msm@vger.kernel.org @@ -15205,6 +15224,7 @@ F: fs/reiserfs/ REMOTE PROCESSOR (REMOTEPROC) SUBSYSTEM M: Ohad Ben-Cohen <ohad@wizery.com> M: Bjorn Andersson <bjorn.andersson@linaro.org> +M: Mathieu Poirier <mathieu.poirier@linaro.org> L: linux-remoteproc@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rproc-next @@ -15218,6 +15238,7 @@ F: include/linux/remoteproc/ REMOTE PROCESSOR MESSAGING (RPMSG) SUBSYSTEM M: Ohad Ben-Cohen <ohad@wizery.com> M: Bjorn Andersson <bjorn.andersson@linaro.org> +M: Mathieu Poirier <mathieu.poirier@linaro.org> L: linux-remoteproc@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/andersson/remoteproc.git rpmsg-next @@ -15634,8 +15655,8 @@ F: Documentation/s390/pci.rst S390 VFIO AP DRIVER M: Tony Krowiak <akrowiak@linux.ibm.com> -M: Pierre Morel <pmorel@linux.ibm.com> M: Halil Pasic <pasic@linux.ibm.com> +M: Jason Herne <jjherne@linux.ibm.com> L: linux-s390@vger.kernel.org S: Supported W: http://www.ibm.com/developerworks/linux/linux390/ @@ -15647,6 +15668,7 @@ F: drivers/s390/crypto/vfio_ap_private.h S390 VFIO-CCW DRIVER M: Cornelia Huck <cohuck@redhat.com> M: Eric Farman <farman@linux.ibm.com> +M: Matthew Rosato <mjrosato@linux.ibm.com> R: Halil Pasic <pasic@linux.ibm.com> L: linux-s390@vger.kernel.org L: kvm@vger.kernel.org @@ -15657,6 +15679,7 @@ F: include/uapi/linux/vfio_ccw.h S390 VFIO-PCI DRIVER M: Matthew Rosato <mjrosato@linux.ibm.com> +M: Eric Farman <farman@linux.ibm.com> L: linux-s390@vger.kernel.org L: kvm@vger.kernel.org S: Supported @@ -16886,8 +16909,10 @@ F: tools/spi/ SPIDERNET NETWORK DRIVER for CELL M: Ishizaki Kou <kou.ishizaki@toshiba.co.jp> +M: Geoff Levand <geoff@infradead.org> L: netdev@vger.kernel.org -S: Supported +L: linuxppc-dev@lists.ozlabs.org +S: Maintained F: Documentation/networking/device_drivers/ethernet/toshiba/spider_net.rst F: drivers/net/ethernet/toshiba/spider_net* @@ -16941,7 +16966,8 @@ F: Documentation/devicetree/bindings/media/i2c/st,st-mipid02.txt F: drivers/media/i2c/st-mipid02.c ST STM32 I2C/SMBUS DRIVER -M: Pierre-Yves MORDRET <pierre-yves.mordret@st.com> +M: Pierre-Yves MORDRET <pierre-yves.mordret@foss.st.com> +M: Alain Volmat <alain.volmat@foss.st.com> L: linux-i2c@vger.kernel.org S: Maintained F: drivers/i2c/busses/i2c-stm32* @@ -17066,7 +17092,7 @@ F: kernel/jump_label.c F: kernel/static_call.c STI AUDIO (ASoC) DRIVERS -M: Arnaud Pouliquen <arnaud.pouliquen@st.com> +M: Arnaud Pouliquen <arnaud.pouliquen@foss.st.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt @@ -17086,15 +17112,15 @@ T: git git://linuxtv.org/media_tree.git F: drivers/media/usb/stk1160/ STM32 AUDIO (ASoC) DRIVERS -M: Olivier Moysan <olivier.moysan@st.com> -M: Arnaud Pouliquen <arnaud.pouliquen@st.com> +M: Olivier Moysan <olivier.moysan@foss.st.com> +M: Arnaud Pouliquen <arnaud.pouliquen@foss.st.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/iio/adc/st,stm32-*.yaml F: sound/soc/stm/ STM32 TIMER/LPTIMER DRIVERS -M: Fabrice Gasnier <fabrice.gasnier@st.com> +M: Fabrice Gasnier <fabrice.gasnier@foss.st.com> S: Maintained F: Documentation/ABI/testing/*timer-stm32 F: Documentation/devicetree/bindings/*/*stm32-*timer* @@ -17104,7 +17130,7 @@ F: include/linux/*/stm32-*tim* STMMAC ETHERNET DRIVER M: Giuseppe Cavallaro <peppe.cavallaro@st.com> -M: Alexandre Torgue <alexandre.torgue@st.com> +M: Alexandre Torgue <alexandre.torgue@foss.st.com> M: Jose Abreu <joabreu@synopsys.com> L: netdev@vger.kernel.org S: Supported @@ -17846,7 +17872,6 @@ S: Maintained F: drivers/thermal/ti-soc-thermal/ TI BQ27XXX POWER SUPPLY DRIVER -R: Dan Murphy <dmurphy@ti.com> F: drivers/power/supply/bq27xxx_battery.c F: drivers/power/supply/bq27xxx_battery_i2c.c F: include/linux/power/bq27xxx_battery.h @@ -17981,7 +18006,6 @@ S: Odd Fixes F: sound/soc/codecs/tas571x* TI TCAN4X5X DEVICE DRIVER -M: Dan Murphy <dmurphy@ti.com> L: linux-can@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/net/can/tcan4x5x.txt @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 12 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = NAME = Frozen Wasteland # *DOCUMENTATION* diff --git a/arch/arc/boot/dts/haps_hs.dts b/arch/arc/boot/dts/haps_hs.dts index 60d578e2781f..76ad527a0847 100644 --- a/arch/arc/boot/dts/haps_hs.dts +++ b/arch/arc/boot/dts/haps_hs.dts @@ -16,7 +16,7 @@ memory { device_type = "memory"; /* CONFIG_LINUX_RAM_BASE needs to match low mem start */ - reg = <0x0 0x80000000 0x0 0x20000000 /* 512 MB low mem */ + reg = <0x0 0x80000000 0x0 0x40000000 /* 1 GB low mem */ 0x1 0x00000000 0x0 0x40000000>; /* 1 GB highmem */ }; diff --git a/arch/arc/kernel/signal.c b/arch/arc/kernel/signal.c index a78d8f745a67..fdbe06c98895 100644 --- a/arch/arc/kernel/signal.c +++ b/arch/arc/kernel/signal.c @@ -96,7 +96,7 @@ stash_usr_regs(struct rt_sigframe __user *sf, struct pt_regs *regs, sizeof(sf->uc.uc_mcontext.regs.scratch)); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(sigset_t)); - return err; + return err ? -EFAULT : 0; } static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) @@ -110,7 +110,7 @@ static int restore_usr_regs(struct pt_regs *regs, struct rt_sigframe __user *sf) &(sf->uc.uc_mcontext.regs.scratch), sizeof(sf->uc.uc_mcontext.regs.scratch)); if (err) - return err; + return -EFAULT; set_current_blocked(&set); regs->bta = uregs.scratch.bta; diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 74ad4256022e..47bab67f8649 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -187,25 +187,26 @@ static void init_unwind_table(struct unwind_table *table, const char *name, const void *table_start, unsigned long table_size, const u8 *header_start, unsigned long header_size) { - const u8 *ptr = header_start + 4; - const u8 *end = header_start + header_size; - table->core.pc = (unsigned long)core_start; table->core.range = core_size; table->init.pc = (unsigned long)init_start; table->init.range = init_size; table->address = table_start; table->size = table_size; - - /* See if the linker provided table looks valid. */ - if (header_size <= 4 - || header_start[0] != 1 - || (void *)read_pointer(&ptr, end, header_start[1]) != table_start - || header_start[2] == DW_EH_PE_omit - || read_pointer(&ptr, end, header_start[2]) <= 0 - || header_start[3] == DW_EH_PE_omit) - header_start = NULL; - + /* To avoid the pointer addition with NULL pointer.*/ + if (header_start != NULL) { + const u8 *ptr = header_start + 4; + const u8 *end = header_start + header_size; + /* See if the linker provided table looks valid. */ + if (header_size <= 4 + || header_start[0] != 1 + || (void *)read_pointer(&ptr, end, header_start[1]) + != table_start + || header_start[2] == DW_EH_PE_omit + || read_pointer(&ptr, end, header_start[2]) <= 0 + || header_start[3] == DW_EH_PE_omit) + header_start = NULL; + } table->hdrsz = header_size; smp_wmb(); table->header = header_start; diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 5da96f5df48f..2fae14857dcf 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1293,9 +1293,15 @@ config KASAN_SHADOW_OFFSET config NR_CPUS int "Maximum number of CPUs (2-32)" - range 2 32 + range 2 16 if DEBUG_KMAP_LOCAL + range 2 32 if !DEBUG_KMAP_LOCAL depends on SMP default "4" + help + The maximum number of CPUs that the kernel can support. + Up to 32 CPUs can be supported, or up to 16 if kmap_local() + debugging is enabled, which uses half of the per-CPU fixmap + slots as guard regions. config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 5b213a1e68bb..5e33d0e88f5b 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -40,6 +40,9 @@ ethernet1 = &cpsw_emac1; spi0 = &spi0; spi1 = &spi1; + mmc0 = &mmc1; + mmc1 = &mmc2; + mmc2 = &mmc3; }; cpus { diff --git a/arch/arm/boot/dts/armada-385-turris-omnia.dts b/arch/arm/boot/dts/armada-385-turris-omnia.dts index 646a06420c77..5bd6a66d2c2b 100644 --- a/arch/arm/boot/dts/armada-385-turris-omnia.dts +++ b/arch/arm/boot/dts/armada-385-turris-omnia.dts @@ -32,7 +32,8 @@ ranges = <MBUS_ID(0xf0, 0x01) 0 0xf1000000 0x100000 MBUS_ID(0x01, 0x1d) 0 0xfff00000 0x100000 MBUS_ID(0x09, 0x19) 0 0xf1100000 0x10000 - MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000>; + MBUS_ID(0x09, 0x15) 0 0xf1110000 0x10000 + MBUS_ID(0x0c, 0x04) 0 0xf1200000 0x100000>; internal-regs { @@ -389,6 +390,7 @@ phy1: ethernet-phy@1 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <1>; + marvell,reg-init = <3 18 0 0x4985>; /* irq is connected to &pcawan pin 7 */ }; diff --git a/arch/arm/boot/dts/at91-sam9x60ek.dts b/arch/arm/boot/dts/at91-sam9x60ek.dts index 73b6b1f89de9..775ceb3acb6c 100644 --- a/arch/arm/boot/dts/at91-sam9x60ek.dts +++ b/arch/arm/boot/dts/at91-sam9x60ek.dts @@ -334,14 +334,6 @@ }; &pinctrl { - atmel,mux-mask = < - /* A B C */ - 0xFFFFFE7F 0xC0E0397F 0xEF00019D /* pioA */ - 0x03FFFFFF 0x02FC7E68 0x00780000 /* pioB */ - 0xffffffff 0xF83FFFFF 0xB800F3FC /* pioC */ - 0x003FFFFF 0x003F8000 0x00000000 /* pioD */ - >; - adc { pinctrl_adc_default: adc_default { atmel,pins = <AT91_PIOB 15 AT91_PERIPH_A AT91_PINCTRL_NONE>; diff --git a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi index 1b1163858b1d..e3251f3e3eaa 100644 --- a/arch/arm/boot/dts/at91-sama5d27_som1.dtsi +++ b/arch/arm/boot/dts/at91-sama5d27_som1.dtsi @@ -84,8 +84,8 @@ pinctrl-0 = <&pinctrl_macb0_default>; phy-mode = "rmii"; - ethernet-phy@0 { - reg = <0x0>; + ethernet-phy@7 { + reg = <0x7>; interrupt-parent = <&pioA>; interrupts = <PIN_PD31 IRQ_TYPE_LEVEL_LOW>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi index 462b1dfb0385..720beec54d61 100644 --- a/arch/arm/boot/dts/bcm2711.dtsi +++ b/arch/arm/boot/dts/bcm2711.dtsi @@ -308,14 +308,6 @@ #reset-cells = <1>; }; - bsc_intr: interrupt-controller@7ef00040 { - compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc"; - reg = <0x7ef00040 0x30>; - interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>; - interrupt-controller; - #interrupt-cells = <1>; - }; - aon_intr: interrupt-controller@7ef00100 { compatible = "brcm,bcm2711-l2-intc", "brcm,l2-intc"; reg = <0x7ef00100 0x30>; @@ -362,8 +354,6 @@ reg = <0x7ef04500 0x100>, <0x7ef00b00 0x300>; reg-names = "bsc", "auto-i2c"; clock-frequency = <97500>; - interrupt-parent = <&bsc_intr>; - interrupts = <0>; status = "disabled"; }; @@ -405,8 +395,6 @@ reg = <0x7ef09500 0x100>, <0x7ef05b00 0x300>; reg-names = "bsc", "auto-i2c"; clock-frequency = <97500>; - interrupt-parent = <&bsc_intr>; - interrupts = <1>; status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi index 7a1e53195785..f28a96fcf23e 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi @@ -433,6 +433,7 @@ pinctrl-0 = <&pinctrl_usdhc2>; cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>; wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>; + vmmc-supply = <&vdd_sd1_reg>; status = "disabled"; }; @@ -442,5 +443,6 @@ &pinctrl_usdhc3_cdwp>; cd-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>; wp-gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>; + vmmc-supply = <&vdd_sd0_reg>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi index c593597b2119..5a1e10def6ef 100644 --- a/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi +++ b/arch/arm/boot/dts/imx6ul-14x14-evk.dtsi @@ -210,9 +210,6 @@ micrel,led-mode = <1>; clocks = <&clks IMX6UL_CLK_ENET_REF>; clock-names = "rmii-ref"; - reset-gpios = <&gpio_spi 1 GPIO_ACTIVE_LOW>; - reset-assert-us = <10000>; - reset-deassert-us = <100>; }; @@ -222,9 +219,6 @@ micrel,led-mode = <1>; clocks = <&clks IMX6UL_CLK_ENET2_REF>; clock-names = "rmii-ref"; - reset-gpios = <&gpio_spi 2 GPIO_ACTIVE_LOW>; - reset-assert-us = <10000>; - reset-deassert-us = <100>; }; }; }; @@ -243,6 +237,22 @@ status = "okay"; }; +&gpio_spi { + eth0-phy-hog { + gpio-hog; + gpios = <1 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "eth0-phy"; + }; + + eth1-phy-hog { + gpio-hog; + gpios = <2 GPIO_ACTIVE_HIGH>; + output-high; + line-name = "eth1-phy"; + }; +}; + &i2c1 { clock-frequency = <100000>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts b/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts index ecbb2cc5b9ab..79cc45728cd2 100644 --- a/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts +++ b/arch/arm/boot/dts/imx6ull-myir-mys-6ulx-eval.dts @@ -14,5 +14,6 @@ }; &gpmi { + fsl,use-minimum-ecc; status = "okay"; }; diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi index 9dcae1f2bc99..c5b9da0d7e6c 100644 --- a/arch/arm/boot/dts/omap3.dtsi +++ b/arch/arm/boot/dts/omap3.dtsi @@ -24,6 +24,9 @@ i2c0 = &i2c1; i2c1 = &i2c2; i2c2 = &i2c3; + mmc0 = &mmc1; + mmc1 = &mmc2; + mmc2 = &mmc3; serial0 = &uart1; serial1 = &uart2; serial2 = &uart3; diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi index 72e4f6481776..4a9f9496a867 100644 --- a/arch/arm/boot/dts/omap4.dtsi +++ b/arch/arm/boot/dts/omap4.dtsi @@ -22,6 +22,11 @@ i2c1 = &i2c2; i2c2 = &i2c3; i2c3 = &i2c4; + mmc0 = &mmc1; + mmc1 = &mmc2; + mmc2 = &mmc3; + mmc3 = &mmc4; + mmc4 = &mmc5; serial0 = &uart1; serial1 = &uart2; serial2 = &uart3; diff --git a/arch/arm/boot/dts/omap44xx-clocks.dtsi b/arch/arm/boot/dts/omap44xx-clocks.dtsi index 532868591107..1f1c04d8f472 100644 --- a/arch/arm/boot/dts/omap44xx-clocks.dtsi +++ b/arch/arm/boot/dts/omap44xx-clocks.dtsi @@ -770,14 +770,6 @@ ti,max-div = <2>; }; - sha2md5_fck: sha2md5_fck@15c8 { - #clock-cells = <0>; - compatible = "ti,gate-clock"; - clocks = <&l3_div_ck>; - ti,bit-shift = <1>; - reg = <0x15c8>; - }; - usb_phy_cm_clk32k: usb_phy_cm_clk32k@640 { #clock-cells = <0>; compatible = "ti,gate-clock"; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index e025b7c9a357..ee821d0ab364 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -25,6 +25,11 @@ i2c2 = &i2c3; i2c3 = &i2c4; i2c4 = &i2c5; + mmc0 = &mmc1; + mmc1 = &mmc2; + mmc2 = &mmc3; + mmc3 = &mmc4; + mmc4 = &mmc5; serial0 = &uart1; serial1 = &uart2; serial2 = &uart3; diff --git a/arch/arm/boot/dts/sam9x60.dtsi b/arch/arm/boot/dts/sam9x60.dtsi index 84066c1298df..ec45ced3cde6 100644 --- a/arch/arm/boot/dts/sam9x60.dtsi +++ b/arch/arm/boot/dts/sam9x60.dtsi @@ -606,6 +606,15 @@ compatible = "microchip,sam9x60-pinctrl", "atmel,at91sam9x5-pinctrl", "atmel,at91rm9200-pinctrl", "simple-bus"; ranges = <0xfffff400 0xfffff400 0x800>; + /* mux-mask corresponding to sam9x60 SoC in TFBGA228L package */ + atmel,mux-mask = < + /* A B C */ + 0xffffffff 0xffe03fff 0xef00019d /* pioA */ + 0x03ffffff 0x02fc7e7f 0x00780000 /* pioB */ + 0xffffffff 0xffffffff 0xf83fffff /* pioC */ + 0x003fffff 0x003f8000 0x00000000 /* pioD */ + >; + pioA: gpio@fffff400 { compatible = "microchip,sam9x60-gpio", "atmel,at91sam9x5-gpio", "atmel,at91rm9200-gpio"; reg = <0xfffff400 0x200>; diff --git a/arch/arm/crypto/aes-cipher-core.S b/arch/arm/crypto/aes-cipher-core.S index 472e56d09eea..1da3f41359aa 100644 --- a/arch/arm/crypto/aes-cipher-core.S +++ b/arch/arm/crypto/aes-cipher-core.S @@ -99,28 +99,6 @@ __hround \out2, \out3, \in2, \in1, \in0, \in3, \in1, \in0, 0, \sz, \op, \oldcpsr .endm - .macro __rev, out, in - .if __LINUX_ARM_ARCH__ < 6 - lsl t0, \in, #24 - and t1, \in, #0xff00 - and t2, \in, #0xff0000 - orr \out, t0, \in, lsr #24 - orr \out, \out, t1, lsl #8 - orr \out, \out, t2, lsr #8 - .else - rev \out, \in - .endif - .endm - - .macro __adrl, out, sym, c - .if __LINUX_ARM_ARCH__ < 7 - ldr\c \out, =\sym - .else - movw\c \out, #:lower16:\sym - movt\c \out, #:upper16:\sym - .endif - .endm - .macro do_crypt, round, ttab, ltab, bsz push {r3-r11, lr} @@ -133,10 +111,10 @@ ldr r7, [in, #12] #ifdef CONFIG_CPU_BIG_ENDIAN - __rev r4, r4 - __rev r5, r5 - __rev r6, r6 - __rev r7, r7 + rev_l r4, t0 + rev_l r5, t0 + rev_l r6, t0 + rev_l r7, t0 #endif eor r4, r4, r8 @@ -144,7 +122,7 @@ eor r6, r6, r10 eor r7, r7, r11 - __adrl ttab, \ttab + mov_l ttab, \ttab /* * Disable interrupts and prefetch the 1024-byte 'ft' or 'it' table into * L1 cache, assuming cacheline size >= 32. This is a hardening measure @@ -180,7 +158,7 @@ 2: .ifb \ltab add ttab, ttab, #1 .else - __adrl ttab, \ltab + mov_l ttab, \ltab // Prefetch inverse S-box for final round; see explanation above .set i, 0 .rept 256 / 64 @@ -194,10 +172,10 @@ \round r4, r5, r6, r7, r8, r9, r10, r11, \bsz, b, rounds #ifdef CONFIG_CPU_BIG_ENDIAN - __rev r4, r4 - __rev r5, r5 - __rev r6, r6 - __rev r7, r7 + rev_l r4, t0 + rev_l r5, t0 + rev_l r6, t0 + rev_l r7, t0 #endif ldr out, [sp] diff --git a/arch/arm/crypto/blake2b-neon-glue.c b/arch/arm/crypto/blake2b-neon-glue.c index 34d73200e7fa..4b59d027ba4a 100644 --- a/arch/arm/crypto/blake2b-neon-glue.c +++ b/arch/arm/crypto/blake2b-neon-glue.c @@ -85,8 +85,8 @@ static int __init blake2b_neon_mod_init(void) static void __exit blake2b_neon_mod_exit(void) { - return crypto_unregister_shashes(blake2b_neon_algs, - ARRAY_SIZE(blake2b_neon_algs)); + crypto_unregister_shashes(blake2b_neon_algs, + ARRAY_SIZE(blake2b_neon_algs)); } module_init(blake2b_neon_mod_init); diff --git a/arch/arm/crypto/blake2s-core.S b/arch/arm/crypto/blake2s-core.S index bed897e9a181..86345751bbf3 100644 --- a/arch/arm/crypto/blake2s-core.S +++ b/arch/arm/crypto/blake2s-core.S @@ -8,6 +8,7 @@ */ #include <linux/linkage.h> +#include <asm/assembler.h> // Registers used to hold message words temporarily. There aren't // enough ARM registers to hold the whole message block, so we have to @@ -38,6 +39,23 @@ #endif .endm +.macro _le32_bswap a, tmp +#ifdef __ARMEB__ + rev_l \a, \tmp +#endif +.endm + +.macro _le32_bswap_8x a, b, c, d, e, f, g, h, tmp + _le32_bswap \a, \tmp + _le32_bswap \b, \tmp + _le32_bswap \c, \tmp + _le32_bswap \d, \tmp + _le32_bswap \e, \tmp + _le32_bswap \f, \tmp + _le32_bswap \g, \tmp + _le32_bswap \h, \tmp +.endm + // Execute a quarter-round of BLAKE2s by mixing two columns or two diagonals. // (a0, b0, c0, d0) and (a1, b1, c1, d1) give the registers containing the two // columns/diagonals. s0-s1 are the word offsets to the message words the first @@ -180,8 +198,10 @@ ENTRY(blake2s_compress_arch) tst r1, #3 bne .Lcopy_block_misaligned ldmia r1!, {r2-r9} + _le32_bswap_8x r2, r3, r4, r5, r6, r7, r8, r9, r14 stmia r12!, {r2-r9} ldmia r1!, {r2-r9} + _le32_bswap_8x r2, r3, r4, r5, r6, r7, r8, r9, r14 stmia r12, {r2-r9} .Lcopy_block_done: str r1, [sp, #68] // Update message pointer @@ -268,6 +288,7 @@ ENTRY(blake2s_compress_arch) 1: #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS ldr r3, [r1], #4 + _le32_bswap r3, r4 #else ldrb r3, [r1, #0] ldrb r4, [r1, #1] diff --git a/arch/arm/crypto/chacha-scalar-core.S b/arch/arm/crypto/chacha-scalar-core.S index 2985b80a45b5..083fe1ab96d0 100644 --- a/arch/arm/crypto/chacha-scalar-core.S +++ b/arch/arm/crypto/chacha-scalar-core.S @@ -41,32 +41,15 @@ X14 .req r12 X15 .req r14 -.macro __rev out, in, t0, t1, t2 -.if __LINUX_ARM_ARCH__ >= 6 - rev \out, \in -.else - lsl \t0, \in, #24 - and \t1, \in, #0xff00 - and \t2, \in, #0xff0000 - orr \out, \t0, \in, lsr #24 - orr \out, \out, \t1, lsl #8 - orr \out, \out, \t2, lsr #8 -.endif -.endm - -.macro _le32_bswap x, t0, t1, t2 +.macro _le32_bswap_4x a, b, c, d, tmp #ifdef __ARMEB__ - __rev \x, \x, \t0, \t1, \t2 + rev_l \a, \tmp + rev_l \b, \tmp + rev_l \c, \tmp + rev_l \d, \tmp #endif .endm -.macro _le32_bswap_4x a, b, c, d, t0, t1, t2 - _le32_bswap \a, \t0, \t1, \t2 - _le32_bswap \b, \t0, \t1, \t2 - _le32_bswap \c, \t0, \t1, \t2 - _le32_bswap \d, \t0, \t1, \t2 -.endm - .macro __ldrd a, b, src, offset #if __LINUX_ARM_ARCH__ >= 6 ldrd \a, \b, [\src, #\offset] @@ -200,7 +183,7 @@ add X1, X1, r9 add X2, X2, r10 add X3, X3, r11 - _le32_bswap_4x X0, X1, X2, X3, r8, r9, r10 + _le32_bswap_4x X0, X1, X2, X3, r8 ldmia r12!, {r8-r11} eor X0, X0, r8 eor X1, X1, r9 @@ -216,7 +199,7 @@ ldmia r12!, {X0-X3} add X6, r10, X6, ror #brot add X7, r11, X7, ror #brot - _le32_bswap_4x X4, X5, X6, X7, r8, r9, r10 + _le32_bswap_4x X4, X5, X6, X7, r8 eor X4, X4, X0 eor X5, X5, X1 eor X6, X6, X2 @@ -231,7 +214,7 @@ add r1, r1, r9 // x9 add r6, r6, r10 // x10 add r7, r7, r11 // x11 - _le32_bswap_4x r0, r1, r6, r7, r8, r9, r10 + _le32_bswap_4x r0, r1, r6, r7, r8 ldmia r12!, {r8-r11} eor r0, r0, r8 // x8 eor r1, r1, r9 // x9 @@ -245,7 +228,7 @@ add r3, r9, r3, ror #drot // x13 add r4, r10, r4, ror #drot // x14 add r5, r11, r5, ror #drot // x15 - _le32_bswap_4x r2, r3, r4, r5, r9, r10, r11 + _le32_bswap_4x r2, r3, r4, r5, r9 ldr r9, [sp, #72] // load LEN eor r2, r2, r0 // x12 eor r3, r3, r1 // x13 @@ -301,7 +284,7 @@ add X1, X1, r9 add X2, X2, r10 add X3, X3, r11 - _le32_bswap_4x X0, X1, X2, X3, r8, r9, r10 + _le32_bswap_4x X0, X1, X2, X3, r8 stmia r14!, {X0-X3} // Save keystream for x4-x7 @@ -311,7 +294,7 @@ add X5, r9, X5, ror #brot add X6, r10, X6, ror #brot add X7, r11, X7, ror #brot - _le32_bswap_4x X4, X5, X6, X7, r8, r9, r10 + _le32_bswap_4x X4, X5, X6, X7, r8 add r8, sp, #64 stmia r14!, {X4-X7} @@ -323,7 +306,7 @@ add r1, r1, r9 // x9 add r6, r6, r10 // x10 add r7, r7, r11 // x11 - _le32_bswap_4x r0, r1, r6, r7, r8, r9, r10 + _le32_bswap_4x r0, r1, r6, r7, r8 stmia r14!, {r0,r1,r6,r7} __ldrd r8, r9, sp, 144 __ldrd r10, r11, sp, 152 @@ -331,7 +314,7 @@ add r3, r9, r3, ror #drot // x13 add r4, r10, r4, ror #drot // x14 add r5, r11, r5, ror #drot // x15 - _le32_bswap_4x r2, r3, r4, r5, r9, r10, r11 + _le32_bswap_4x r2, r3, r4, r5, r9 stmia r14, {r2-r5} // Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN diff --git a/arch/arm/crypto/curve25519-core.S b/arch/arm/crypto/curve25519-core.S index be18af52e7dc..b697fa5d059a 100644 --- a/arch/arm/crypto/curve25519-core.S +++ b/arch/arm/crypto/curve25519-core.S @@ -10,8 +10,8 @@ #include <linux/linkage.h> .text -.fpu neon .arch armv7-a +.fpu neon .align 4 ENTRY(curve25519_neon) diff --git a/arch/arm/crypto/poly1305-glue.c b/arch/arm/crypto/poly1305-glue.c index 3023c1acfa19..c31bd8f7c092 100644 --- a/arch/arm/crypto/poly1305-glue.c +++ b/arch/arm/crypto/poly1305-glue.c @@ -29,7 +29,7 @@ void __weak poly1305_blocks_neon(void *state, const u8 *src, u32 len, u32 hibit) static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); -void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE]) { poly1305_init_arm(&dctx->h, key); dctx->s[0] = get_unaligned_le32(key + 16); diff --git a/arch/arm/include/asm/paravirt.h b/arch/arm/include/asm/paravirt.h index cdbf02d9c1d4..95d5b0d625cd 100644 --- a/arch/arm/include/asm/paravirt.h +++ b/arch/arm/include/asm/paravirt.h @@ -3,23 +3,19 @@ #define _ASM_ARM_PARAVIRT_H #ifdef CONFIG_PARAVIRT +#include <linux/static_call_types.h> + struct static_key; extern struct static_key paravirt_steal_enabled; extern struct static_key paravirt_steal_rq_enabled; -struct pv_time_ops { - unsigned long long (*steal_clock)(int cpu); -}; - -struct paravirt_patch_template { - struct pv_time_ops time; -}; +u64 dummy_steal_clock(int cpu); -extern struct paravirt_patch_template pv_ops; +DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock); static inline u64 paravirt_steal_clock(int cpu) { - return pv_ops.time.steal_clock(cpu); + return static_call(pv_steal_clock)(cpu); } #endif diff --git a/arch/arm/kernel/paravirt.c b/arch/arm/kernel/paravirt.c index 4cfed91fe256..7dd9806369fb 100644 --- a/arch/arm/kernel/paravirt.c +++ b/arch/arm/kernel/paravirt.c @@ -9,10 +9,15 @@ #include <linux/export.h> #include <linux/jump_label.h> #include <linux/types.h> +#include <linux/static_call.h> #include <asm/paravirt.h> struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; -struct paravirt_patch_template pv_ops; -EXPORT_SYMBOL_GPL(pv_ops); +static u64 native_steal_clock(int cpu) +{ + return 0; +} + +DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); diff --git a/arch/arm/mach-footbridge/cats-pci.c b/arch/arm/mach-footbridge/cats-pci.c index 0b2fd7e2e9b4..90b1e9be430e 100644 --- a/arch/arm/mach-footbridge/cats-pci.c +++ b/arch/arm/mach-footbridge/cats-pci.c @@ -15,14 +15,14 @@ #include <asm/mach-types.h> /* cats host-specific stuff */ -static int irqmap_cats[] __initdata = { IRQ_PCI, IRQ_IN0, IRQ_IN1, IRQ_IN3 }; +static int irqmap_cats[] = { IRQ_PCI, IRQ_IN0, IRQ_IN1, IRQ_IN3 }; static u8 cats_no_swizzle(struct pci_dev *dev, u8 *pin) { return 0; } -static int __init cats_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int cats_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { if (dev->irq >= 255) return -1; /* not a valid interrupt. */ diff --git a/arch/arm/mach-footbridge/ebsa285-pci.c b/arch/arm/mach-footbridge/ebsa285-pci.c index 6f28aaa9ca79..c3f280d08fa7 100644 --- a/arch/arm/mach-footbridge/ebsa285-pci.c +++ b/arch/arm/mach-footbridge/ebsa285-pci.c @@ -14,9 +14,9 @@ #include <asm/mach/pci.h> #include <asm/mach-types.h> -static int irqmap_ebsa285[] __initdata = { IRQ_IN3, IRQ_IN1, IRQ_IN0, IRQ_PCI }; +static int irqmap_ebsa285[] = { IRQ_IN3, IRQ_IN1, IRQ_IN0, IRQ_PCI }; -static int __init ebsa285_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int ebsa285_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { if (dev->vendor == PCI_VENDOR_ID_CONTAQ && dev->device == PCI_DEVICE_ID_CONTAQ_82C693) diff --git a/arch/arm/mach-footbridge/netwinder-pci.c b/arch/arm/mach-footbridge/netwinder-pci.c index 9473aa0305e5..e8304392074b 100644 --- a/arch/arm/mach-footbridge/netwinder-pci.c +++ b/arch/arm/mach-footbridge/netwinder-pci.c @@ -18,7 +18,7 @@ * We now use the slot ID instead of the device identifiers to select * which interrupt is routed where. */ -static int __init netwinder_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int netwinder_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { switch (slot) { case 0: /* host bridge */ diff --git a/arch/arm/mach-footbridge/personal-pci.c b/arch/arm/mach-footbridge/personal-pci.c index 4391e433a4b2..9d19aa98a663 100644 --- a/arch/arm/mach-footbridge/personal-pci.c +++ b/arch/arm/mach-footbridge/personal-pci.c @@ -14,13 +14,12 @@ #include <asm/mach/pci.h> #include <asm/mach-types.h> -static int irqmap_personal_server[] __initdata = { +static int irqmap_personal_server[] = { IRQ_IN0, IRQ_IN1, IRQ_IN2, IRQ_IN3, 0, 0, 0, IRQ_DOORBELLHOST, IRQ_DMA1, IRQ_DMA2, IRQ_PCI }; -static int __init personal_server_map_irq(const struct pci_dev *dev, u8 slot, - u8 pin) +static int personal_server_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { unsigned char line; diff --git a/arch/arm/mach-imx/avic.c b/arch/arm/mach-imx/avic.c index 322caa21bcb3..21bce4049cec 100644 --- a/arch/arm/mach-imx/avic.c +++ b/arch/arm/mach-imx/avic.c @@ -7,6 +7,7 @@ #include <linux/module.h> #include <linux/irq.h> #include <linux/irqdomain.h> +#include <linux/irqchip.h> #include <linux/io.h> #include <linux/of.h> #include <linux/of_address.h> @@ -162,7 +163,7 @@ static void __exception_irq_entry avic_handle_irq(struct pt_regs *regs) * interrupts. It registers the interrupt enable and disable functions * to the kernel for each interrupt source. */ -void __init mxc_init_irq(void __iomem *irqbase) +static void __init mxc_init_irq(void __iomem *irqbase) { struct device_node *np; int irq_base; @@ -220,3 +221,16 @@ void __init mxc_init_irq(void __iomem *irqbase) printk(KERN_INFO "MXC IRQ initialized\n"); } + +static int __init imx_avic_init(struct device_node *node, + struct device_node *parent) +{ + void __iomem *avic_base; + + avic_base = of_iomap(node, 0); + BUG_ON(!avic_base); + mxc_init_irq(avic_base); + return 0; +} + +IRQCHIP_DECLARE(imx_avic, "fsl,avic", imx_avic_init); diff --git a/arch/arm/mach-imx/common.h b/arch/arm/mach-imx/common.h index 2b004cc4f95e..474dedb73bc7 100644 --- a/arch/arm/mach-imx/common.h +++ b/arch/arm/mach-imx/common.h @@ -22,7 +22,6 @@ void mx35_map_io(void); void imx21_init_early(void); void imx31_init_early(void); void imx35_init_early(void); -void mxc_init_irq(void __iomem *); void mx31_init_irq(void); void mx35_init_irq(void); void mxc_set_cpu_type(unsigned int type); diff --git a/arch/arm/mach-imx/mach-imx1.c b/arch/arm/mach-imx/mach-imx1.c index 32df3b8012f9..8eca92d66a2e 100644 --- a/arch/arm/mach-imx/mach-imx1.c +++ b/arch/arm/mach-imx/mach-imx1.c @@ -17,16 +17,6 @@ static void __init imx1_init_early(void) mxc_set_cpu_type(MXC_CPU_MX1); } -static void __init imx1_init_irq(void) -{ - void __iomem *avic_addr; - - avic_addr = ioremap(MX1_AVIC_ADDR, SZ_4K); - WARN_ON(!avic_addr); - - mxc_init_irq(avic_addr); -} - static const char * const imx1_dt_board_compat[] __initconst = { "fsl,imx1", NULL @@ -34,7 +24,6 @@ static const char * const imx1_dt_board_compat[] __initconst = { DT_MACHINE_START(IMX1_DT, "Freescale i.MX1 (Device Tree Support)") .init_early = imx1_init_early, - .init_irq = imx1_init_irq, .dt_compat = imx1_dt_board_compat, .restart = mxc_restart, MACHINE_END diff --git a/arch/arm/mach-imx/mach-imx25.c b/arch/arm/mach-imx/mach-imx25.c index 95de48a1aa7d..51927bd08aef 100644 --- a/arch/arm/mach-imx/mach-imx25.c +++ b/arch/arm/mach-imx/mach-imx25.c @@ -22,17 +22,6 @@ static void __init imx25_dt_init(void) imx_aips_allow_unprivileged_access("fsl,imx25-aips"); } -static void __init mx25_init_irq(void) -{ - struct device_node *np; - void __iomem *avic_base; - - np = of_find_compatible_node(NULL, NULL, "fsl,avic"); - avic_base = of_iomap(np, 0); - BUG_ON(!avic_base); - mxc_init_irq(avic_base); -} - static const char * const imx25_dt_board_compat[] __initconst = { "fsl,imx25", NULL @@ -42,6 +31,5 @@ DT_MACHINE_START(IMX25_DT, "Freescale i.MX25 (Device Tree Support)") .init_early = imx25_init_early, .init_machine = imx25_dt_init, .init_late = imx25_pm_init, - .init_irq = mx25_init_irq, .dt_compat = imx25_dt_board_compat, MACHINE_END diff --git a/arch/arm/mach-imx/mach-imx27.c b/arch/arm/mach-imx/mach-imx27.c index 262422a9c196..e325c9468105 100644 --- a/arch/arm/mach-imx/mach-imx27.c +++ b/arch/arm/mach-imx/mach-imx27.c @@ -56,17 +56,6 @@ static void __init imx27_init_early(void) mxc_set_cpu_type(MXC_CPU_MX27); } -static void __init mx27_init_irq(void) -{ - void __iomem *avic_base; - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,avic"); - avic_base = of_iomap(np, 0); - BUG_ON(!avic_base); - mxc_init_irq(avic_base); -} - static const char * const imx27_dt_board_compat[] __initconst = { "fsl,imx27", NULL @@ -75,7 +64,6 @@ static const char * const imx27_dt_board_compat[] __initconst = { DT_MACHINE_START(IMX27_DT, "Freescale i.MX27 (Device Tree Support)") .map_io = mx27_map_io, .init_early = imx27_init_early, - .init_irq = mx27_init_irq, .init_late = imx27_pm_init, .dt_compat = imx27_dt_board_compat, MACHINE_END diff --git a/arch/arm/mach-imx/mach-imx31.c b/arch/arm/mach-imx/mach-imx31.c index dc69dfe600df..e9a1092b6093 100644 --- a/arch/arm/mach-imx/mach-imx31.c +++ b/arch/arm/mach-imx/mach-imx31.c @@ -14,6 +14,5 @@ static const char * const imx31_dt_board_compat[] __initconst = { DT_MACHINE_START(IMX31_DT, "Freescale i.MX31 (Device Tree Support)") .map_io = mx31_map_io, .init_early = imx31_init_early, - .init_irq = mx31_init_irq, .dt_compat = imx31_dt_board_compat, MACHINE_END diff --git a/arch/arm/mach-imx/mach-imx35.c b/arch/arm/mach-imx/mach-imx35.c index ec5c3068715c..0fc08218b77d 100644 --- a/arch/arm/mach-imx/mach-imx35.c +++ b/arch/arm/mach-imx/mach-imx35.c @@ -27,6 +27,5 @@ DT_MACHINE_START(IMX35_DT, "Freescale i.MX35 (Device Tree Support)") .l2c_aux_mask = ~0, .map_io = mx35_map_io, .init_early = imx35_init_early, - .init_irq = mx35_init_irq, .dt_compat = imx35_dt_board_compat, MACHINE_END diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c index 5056438e5b42..28db97289ee8 100644 --- a/arch/arm/mach-imx/mm-imx3.c +++ b/arch/arm/mach-imx/mm-imx3.c @@ -109,18 +109,6 @@ void __init imx31_init_early(void) mx3_ccm_base = of_iomap(np, 0); BUG_ON(!mx3_ccm_base); } - -void __init mx31_init_irq(void) -{ - void __iomem *avic_base; - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,imx31-avic"); - avic_base = of_iomap(np, 0); - BUG_ON(!avic_base); - - mxc_init_irq(avic_base); -} #endif /* ifdef CONFIG_SOC_IMX31 */ #ifdef CONFIG_SOC_IMX35 @@ -158,16 +146,4 @@ void __init imx35_init_early(void) mx3_ccm_base = of_iomap(np, 0); BUG_ON(!mx3_ccm_base); } - -void __init mx35_init_irq(void) -{ - void __iomem *avic_base; - struct device_node *np; - - np = of_find_compatible_node(NULL, NULL, "fsl,imx35-avic"); - avic_base = of_iomap(np, 0); - BUG_ON(!avic_base); - - mxc_init_irq(avic_base); -} #endif /* ifdef CONFIG_SOC_IMX35 */ diff --git a/arch/arm/mach-keystone/keystone.c b/arch/arm/mach-keystone/keystone.c index cd711bfc591f..2c647bdf8d25 100644 --- a/arch/arm/mach-keystone/keystone.c +++ b/arch/arm/mach-keystone/keystone.c @@ -65,7 +65,7 @@ static void __init keystone_init(void) static long long __init keystone_pv_fixup(void) { long long offset; - phys_addr_t mem_start, mem_end; + u64 mem_start, mem_end; mem_start = memblock_start_of_DRAM(); mem_end = memblock_end_of_DRAM(); @@ -78,7 +78,7 @@ static long long __init keystone_pv_fixup(void) if (mem_start < KEYSTONE_HIGH_PHYS_START || mem_end > KEYSTONE_HIGH_PHYS_END) { pr_crit("Invalid address space for memory (%08llx-%08llx)\n", - (u64)mem_start, (u64)mem_end); + mem_start, mem_end); return 0; } diff --git a/arch/arm/mach-omap1/ams-delta-fiq-handler.S b/arch/arm/mach-omap1/ams-delta-fiq-handler.S index 14a6c3eb3298..f745a65d3bd7 100644 --- a/arch/arm/mach-omap1/ams-delta-fiq-handler.S +++ b/arch/arm/mach-omap1/ams-delta-fiq-handler.S @@ -15,6 +15,7 @@ #include <linux/platform_data/gpio-omap.h> #include <asm/assembler.h> +#include <asm/irq.h> #include "ams-delta-fiq.h" #include "board-ams-delta.h" diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c index 7290f033fd2d..1610c567a6a3 100644 --- a/arch/arm/mach-omap2/board-generic.c +++ b/arch/arm/mach-omap2/board-generic.c @@ -33,7 +33,7 @@ static void __init __maybe_unused omap_generic_init(void) } /* Clocks are needed early, see drivers/clocksource for the rest */ -void __init __maybe_unused omap_init_time_of(void) +static void __init __maybe_unused omap_init_time_of(void) { omap_clk_init(); timer_probe(); diff --git a/arch/arm/mach-omap2/omap-secure.c b/arch/arm/mach-omap2/omap-secure.c index f70d561f37f7..0659ab4cb0af 100644 --- a/arch/arm/mach-omap2/omap-secure.c +++ b/arch/arm/mach-omap2/omap-secure.c @@ -9,6 +9,7 @@ */ #include <linux/arm-smccc.h> +#include <linux/cpu_pm.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/io.h> @@ -20,6 +21,7 @@ #include "common.h" #include "omap-secure.h" +#include "soc.h" static phys_addr_t omap_secure_memblock_base; @@ -213,3 +215,40 @@ void __init omap_secure_init(void) { omap_optee_init_check(); } + +/* + * Dummy dispatcher call after core OSWR and MPU off. Updates the ROM return + * address after MMU has been re-enabled after CPU1 has been woken up again. + * Otherwise the ROM code will attempt to use the earlier physical return + * address that got set with MMU off when waking up CPU1. Only used on secure + * devices. + */ +static int cpu_notifier(struct notifier_block *nb, unsigned long cmd, void *v) +{ + switch (cmd) { + case CPU_CLUSTER_PM_EXIT: + omap_secure_dispatcher(OMAP4_PPA_SERVICE_0, + FLAG_START_CRITICAL, + 0, 0, 0, 0, 0); + break; + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block secure_notifier_block = { + .notifier_call = cpu_notifier, +}; + +static int __init secure_pm_init(void) +{ + if (omap_type() == OMAP2_DEVICE_TYPE_GP || !soc_is_omap44xx()) + return 0; + + cpu_pm_register_notifier(&secure_notifier_block); + + return 0; +} +omap_arch_initcall(secure_pm_init); diff --git a/arch/arm/mach-omap2/omap-secure.h b/arch/arm/mach-omap2/omap-secure.h index 4aaa95706d39..172069f31616 100644 --- a/arch/arm/mach-omap2/omap-secure.h +++ b/arch/arm/mach-omap2/omap-secure.h @@ -50,6 +50,7 @@ #define OMAP5_DRA7_MON_SET_ACR_INDEX 0x107 /* Secure PPA(Primary Protected Application) APIs */ +#define OMAP4_PPA_SERVICE_0 0x21 #define OMAP4_PPA_L2_POR_INDEX 0x23 #define OMAP4_PPA_CPU_ACTRL_SMP_INDEX 0x25 diff --git a/arch/arm/mach-omap2/pmic-cpcap.c b/arch/arm/mach-omap2/pmic-cpcap.c index 09076ad0576d..668dc84fd31e 100644 --- a/arch/arm/mach-omap2/pmic-cpcap.c +++ b/arch/arm/mach-omap2/pmic-cpcap.c @@ -246,10 +246,10 @@ int __init omap4_cpcap_init(void) omap_voltage_register_pmic(voltdm, &omap443x_max8952_mpu); if (of_machine_is_compatible("motorola,droid-bionic")) { - voltdm = voltdm_lookup("mpu"); + voltdm = voltdm_lookup("core"); omap_voltage_register_pmic(voltdm, &omap_cpcap_core); - voltdm = voltdm_lookup("mpu"); + voltdm = voltdm_lookup("iva"); omap_voltage_register_pmic(voltdm, &omap_cpcap_iva); } else { voltdm = voltdm_lookup("core"); diff --git a/arch/arm/mach-omap2/sr_device.c b/arch/arm/mach-omap2/sr_device.c index 62df666c2bd0..605925684b0a 100644 --- a/arch/arm/mach-omap2/sr_device.c +++ b/arch/arm/mach-omap2/sr_device.c @@ -88,34 +88,26 @@ static void __init sr_set_nvalues(struct omap_volt_data *volt_data, extern struct omap_sr_data omap_sr_pdata[]; -static int __init sr_dev_init(struct omap_hwmod *oh, void *user) +static int __init sr_init_by_name(const char *name, const char *voltdm) { struct omap_sr_data *sr_data = NULL; struct omap_volt_data *volt_data; - struct omap_smartreflex_dev_attr *sr_dev_attr; static int i; - if (!strncmp(oh->name, "smartreflex_mpu_iva", 20) || - !strncmp(oh->name, "smartreflex_mpu", 16)) + if (!strncmp(name, "smartreflex_mpu_iva", 20) || + !strncmp(name, "smartreflex_mpu", 16)) sr_data = &omap_sr_pdata[OMAP_SR_MPU]; - else if (!strncmp(oh->name, "smartreflex_core", 17)) + else if (!strncmp(name, "smartreflex_core", 17)) sr_data = &omap_sr_pdata[OMAP_SR_CORE]; - else if (!strncmp(oh->name, "smartreflex_iva", 16)) + else if (!strncmp(name, "smartreflex_iva", 16)) sr_data = &omap_sr_pdata[OMAP_SR_IVA]; if (!sr_data) { - pr_err("%s: Unknown instance %s\n", __func__, oh->name); + pr_err("%s: Unknown instance %s\n", __func__, name); return -EINVAL; } - sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr; - if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) { - pr_err("%s: No voltage domain specified for %s. Cannot initialize\n", - __func__, oh->name); - goto exit; - } - - sr_data->name = oh->name; + sr_data->name = name; if (cpu_is_omap343x()) sr_data->ip_type = 1; else @@ -136,10 +128,10 @@ static int __init sr_dev_init(struct omap_hwmod *oh, void *user) } } - sr_data->voltdm = voltdm_lookup(sr_dev_attr->sensor_voltdm_name); + sr_data->voltdm = voltdm_lookup(voltdm); if (!sr_data->voltdm) { pr_err("%s: Unable to get voltage domain pointer for VDD %s\n", - __func__, sr_dev_attr->sensor_voltdm_name); + __func__, voltdm); goto exit; } @@ -160,6 +152,20 @@ exit: return 0; } +static int __init sr_dev_init(struct omap_hwmod *oh, void *user) +{ + struct omap_smartreflex_dev_attr *sr_dev_attr; + + sr_dev_attr = (struct omap_smartreflex_dev_attr *)oh->dev_attr; + if (!sr_dev_attr || !sr_dev_attr->sensor_voltdm_name) { + pr_err("%s: No voltage domain specified for %s. Cannot initialize\n", + __func__, oh->name); + return 0; + } + + return sr_init_by_name(oh->name, sr_dev_attr->sensor_voltdm_name); +} + /* * API to be called from board files to enable smartreflex * autocompensation at init. @@ -169,7 +175,42 @@ void __init omap_enable_smartreflex_on_init(void) sr_enable_on_init = true; } +static const char * const omap4_sr_instances[] = { + "mpu", + "iva", + "core", +}; + +static const char * const dra7_sr_instances[] = { + "mpu", + "core", +}; + int __init omap_devinit_smartreflex(void) { + const char * const *sr_inst = NULL; + int i, nr_sr = 0; + + if (soc_is_omap44xx()) { + sr_inst = omap4_sr_instances; + nr_sr = ARRAY_SIZE(omap4_sr_instances); + + } else if (soc_is_dra7xx()) { + sr_inst = dra7_sr_instances; + nr_sr = ARRAY_SIZE(dra7_sr_instances); + } + + if (nr_sr) { + const char *name, *voltdm; + + for (i = 0; i < nr_sr; i++) { + name = kasprintf(GFP_KERNEL, "smartreflex_%s", sr_inst[i]); + voltdm = sr_inst[i]; + sr_init_by_name(name, voltdm); + } + + return 0; + } + return omap_hwmod_for_each_by_class("smartreflex", sr_dev_init, NULL); } diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c index d1010ec26e9f..d237bd030238 100644 --- a/arch/arm/mach-pxa/mainstone.c +++ b/arch/arm/mach-pxa/mainstone.c @@ -502,16 +502,20 @@ static inline void mainstone_init_keypad(void) {} #endif static int mst_pcmcia0_irqs[11] = { - [0 ... 10] = -1, + [0 ... 4] = -1, [5] = MAINSTONE_S0_CD_IRQ, + [6 ... 7] = -1, [8] = MAINSTONE_S0_STSCHG_IRQ, + [9] = -1, [10] = MAINSTONE_S0_IRQ, }; static int mst_pcmcia1_irqs[11] = { - [0 ... 10] = -1, + [0 ... 4] = -1, [5] = MAINSTONE_S1_CD_IRQ, + [6 ... 7] = -1, [8] = MAINSTONE_S1_STSCHG_IRQ, + [9] = -1, [10] = MAINSTONE_S1_IRQ, }; diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index a25b660c3017..c1e12aab67b8 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -387,8 +387,7 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) pte_t *pte = pte_offset_fixmap(pmd_off_k(vaddr), vaddr); /* Make sure fixmap region does not exceed available allocation. */ - BUILD_BUG_ON(FIXADDR_START + (__end_of_fixed_addresses * PAGE_SIZE) > - FIXADDR_END); + BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) < FIXADDR_START); BUG_ON(idx >= __end_of_fixed_addresses); /* we only support device mappings until pgprot_kernel has been set */ diff --git a/arch/arm/mm/pmsa-v7.c b/arch/arm/mm/pmsa-v7.c index 88950e41a3a9..59d916ccdf25 100644 --- a/arch/arm/mm/pmsa-v7.c +++ b/arch/arm/mm/pmsa-v7.c @@ -235,6 +235,7 @@ void __init pmsav7_adjust_lowmem_bounds(void) phys_addr_t mem_end; phys_addr_t reg_start, reg_end; unsigned int mem_max_regions; + bool first = true; int num; u64 i; @@ -263,7 +264,7 @@ void __init pmsav7_adjust_lowmem_bounds(void) #endif for_each_mem_range(i, ®_start, ®_end) { - if (i == 0) { + if (first) { phys_addr_t phys_offset = PHYS_OFFSET; /* @@ -275,6 +276,7 @@ void __init pmsav7_adjust_lowmem_bounds(void) mem_start = reg_start; mem_end = reg_end; specified_mem_size = mem_end - mem_start; + first = false; } else { /* * memblock auto merges contiguous blocks, remove diff --git a/arch/arm/mm/pmsa-v8.c b/arch/arm/mm/pmsa-v8.c index 2de019f7503e..8359748a19a1 100644 --- a/arch/arm/mm/pmsa-v8.c +++ b/arch/arm/mm/pmsa-v8.c @@ -95,10 +95,11 @@ void __init pmsav8_adjust_lowmem_bounds(void) { phys_addr_t mem_end; phys_addr_t reg_start, reg_end; + bool first = true; u64 i; for_each_mem_range(i, ®_start, ®_end) { - if (i == 0) { + if (first) { phys_addr_t phys_offset = PHYS_OFFSET; /* @@ -107,6 +108,7 @@ void __init pmsav8_adjust_lowmem_bounds(void) if (reg_start != phys_offset) panic("First memory bank must be contiguous from PHYS_OFFSET"); mem_end = reg_end; + first = false; } else { /* * memblock auto merges contiguous blocks, remove diff --git a/arch/arm/probes/uprobes/core.c b/arch/arm/probes/uprobes/core.c index c4b49b322e8a..f5f790c6e5f8 100644 --- a/arch/arm/probes/uprobes/core.c +++ b/arch/arm/probes/uprobes/core.c @@ -204,7 +204,7 @@ unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) static struct undef_hook uprobes_arm_break_hook = { .instr_mask = 0x0fffffff, .instr_val = (UPROBE_SWBP_ARM_INSN & 0x0fffffff), - .cpsr_mask = MODE_MASK, + .cpsr_mask = (PSR_T_BIT | MODE_MASK), .cpsr_val = USR_MODE, .fn = uprobe_trap_handler, }; @@ -212,7 +212,7 @@ static struct undef_hook uprobes_arm_break_hook = { static struct undef_hook uprobes_arm_ss_hook = { .instr_mask = 0x0fffffff, .instr_val = (UPROBE_SS_ARM_INSN & 0x0fffffff), - .cpsr_mask = MODE_MASK, + .cpsr_mask = (PSR_T_BIT | MODE_MASK), .cpsr_val = USR_MODE, .fn = uprobe_trap_handler, }; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 5656e7aacd69..dfdc3e0af5e1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -810,6 +810,16 @@ config QCOM_FALKOR_ERRATUM_E1041 If unsure, say Y. +config NVIDIA_CARMEL_CNP_ERRATUM + bool "NVIDIA Carmel CNP: CNP on Carmel semantically different than ARM cores" + default y + help + If CNP is enabled on Carmel cores, non-sharable TLBIs on a core will not + invalidate shared TLB entries installed by a different core, as it would + on standard ARM cores. + + If unsure, say Y. + config SOCIONEXT_SYNQUACER_PREITS bool "Socionext Synquacer: Workaround for GICv3 pre-ITS" default y @@ -1396,10 +1406,13 @@ config ARM64_PAN config AS_HAS_LDAPR def_bool $(as-instr,.arch_extension rcpc) +config AS_HAS_LSE_ATOMICS + def_bool $(as-instr,.arch_extension lse) + config ARM64_LSE_ATOMICS bool default ARM64_USE_LSE_ATOMICS - depends on $(as-instr,.arch_extension lse) + depends on AS_HAS_LSE_ATOMICS config ARM64_USE_LSE_ATOMICS bool "Atomic instructions" @@ -1656,6 +1669,7 @@ config ARM64_MTE default y depends on ARM64_AS_HAS_MTE && ARM64_TAGGED_ADDR_ABI depends on AS_HAS_ARMV8_5 + depends on AS_HAS_LSE_ATOMICS # Required for tag checking in the uaccess routines depends on ARM64_PAN select ARCH_USES_HIGH_VMA_FLAGS diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-lts.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-lts.dts index 437ffe3628a5..596a25907432 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-lts.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-lts.dts @@ -19,3 +19,7 @@ }; }; }; + +&mmc0 { + broken-cd; /* card detect is broken on *some* boards */ +}; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi index 3402cec87035..df62044ff7a7 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine.dtsi @@ -34,7 +34,7 @@ vmmc-supply = <®_dcdc1>; disable-wp; bus-width = <4>; - cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */ + cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; /* PF6 push-pull switch */ status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts index 4f4755152fce..b5808047d6e4 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-beelink-gs1.dts @@ -289,10 +289,6 @@ vcc-pm-supply = <®_aldo1>; }; -&rtc { - clocks = <&ext_osc32k>; -}; - &spdif { status = "okay"; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi index 49e979794094..af8b7d0ef750 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6.dtsi @@ -995,9 +995,9 @@ compatible = "allwinner,sun8i-a23-rsb"; reg = <0x07083000 0x400>; interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&r_ccu 13>; + clocks = <&r_ccu CLK_R_APB2_RSB>; clock-frequency = <3000000>; - resets = <&r_ccu 7>; + resets = <&r_ccu RST_R_APB2_RSB>; pinctrl-names = "default"; pinctrl-0 = <&r_rsb_pins>; status = "disabled"; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi index 7de6b376d792..9058cfa4980f 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a.dtsi @@ -198,6 +198,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi index 5a8a1dc4262d..28c51e521cb2 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi @@ -348,6 +348,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <0 75 0x4>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index 1d6dfd189c7f..39458305e333 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -354,6 +354,7 @@ ranges = <0x0 0x00 0x1700000 0x100000>; reg = <0x00 0x1700000 0x0 0x100000>; interrupts = <GIC_SPI 75 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent; sec_jr0: jr@10000 { compatible = "fsl,sec-v5.4-job-ring", diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h index 5ccc4cc91959..a003e6af3353 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h @@ -124,7 +124,7 @@ #define MX8MM_IOMUXC_SD1_CMD_USDHC1_CMD 0x0A4 0x30C 0x000 0x0 0x0 #define MX8MM_IOMUXC_SD1_CMD_GPIO2_IO1 0x0A4 0x30C 0x000 0x5 0x0 #define MX8MM_IOMUXC_SD1_DATA0_USDHC1_DATA0 0x0A8 0x310 0x000 0x0 0x0 -#define MX8MM_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x31 0x000 0x5 0x0 +#define MX8MM_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x310 0x000 0x5 0x0 #define MX8MM_IOMUXC_SD1_DATA1_USDHC1_DATA1 0x0AC 0x314 0x000 0x0 0x0 #define MX8MM_IOMUXC_SD1_DATA1_GPIO2_IO3 0x0AC 0x314 0x000 0x5 0x0 #define MX8MM_IOMUXC_SD1_DATA2_USDHC1_DATA2 0x0B0 0x318 0x000 0x0 0x0 diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts index 0e1a6d953389..122c95ddad30 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-phyboard-pollux-rdk.dts @@ -35,7 +35,7 @@ &i2c2 { clock-frequency = <400000>; - pinctrl-names = "default"; + pinctrl-names = "default", "gpio"; pinctrl-0 = <&pinctrl_i2c2>; pinctrl-1 = <&pinctrl_i2c2_gpio>; sda-gpios = <&gpio5 17 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi index 44a8c2337cee..f3965ec5b31d 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi @@ -67,7 +67,7 @@ &i2c1 { clock-frequency = <400000>; - pinctrl-names = "default"; + pinctrl-names = "default", "gpio"; pinctrl-0 = <&pinctrl_i2c1>; pinctrl-1 = <&pinctrl_i2c1_gpio>; sda-gpios = <&gpio5 15 (GPIO_ACTIVE_HIGH | GPIO_OPEN_DRAIN)>; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h index b94b02080a34..68e8fa172974 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mq-pinfunc.h @@ -130,7 +130,7 @@ #define MX8MQ_IOMUXC_SD1_CMD_USDHC1_CMD 0x0A4 0x30C 0x000 0x0 0x0 #define MX8MQ_IOMUXC_SD1_CMD_GPIO2_IO1 0x0A4 0x30C 0x000 0x5 0x0 #define MX8MQ_IOMUXC_SD1_DATA0_USDHC1_DATA0 0x0A8 0x310 0x000 0x0 0x0 -#define MX8MQ_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x31 0x000 0x5 0x0 +#define MX8MQ_IOMUXC_SD1_DATA0_GPIO2_IO2 0x0A8 0x310 0x000 0x5 0x0 #define MX8MQ_IOMUXC_SD1_DATA1_USDHC1_DATA1 0x0AC 0x314 0x000 0x0 0x0 #define MX8MQ_IOMUXC_SD1_DATA1_GPIO2_IO3 0x0AC 0x314 0x000 0x5 0x0 #define MX8MQ_IOMUXC_SD1_DATA2_USDHC1_DATA2 0x0B0 0x318 0x000 0x0 0x0 diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts index d239ab70ed99..53e817c5f6f3 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts @@ -1,7 +1,7 @@ // SPDX-License-Identifier: (GPL-2.0+ OR MIT) /* * Device Tree file for CZ.NIC Turris Mox Board - * 2019 by Marek Behun <marek.behun@nic.cz> + * 2019 by Marek Behún <kabel@kernel.org> */ /dts-v1/; diff --git a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi index 64179a372ecf..c6f5df2deccf 100644 --- a/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-cp11x.dtsi @@ -310,9 +310,11 @@ }; CP11X_LABEL(sata0): sata@540000 { - compatible = "marvell,armada-8k-ahci"; + compatible = "marvell,armada-8k-ahci", + "generic-ahci"; reg = <0x540000 0x30000>; dma-coherent; + interrupts = <107 IRQ_TYPE_LEVEL_HIGH>; clocks = <&CP11X_LABEL(clk) 1 15>, <&CP11X_LABEL(clk) 1 16>; #address-cells = <1>; @@ -320,12 +322,10 @@ status = "disabled"; sata-port@0 { - interrupts = <109 IRQ_TYPE_LEVEL_HIGH>; reg = <0>; }; sata-port@1 { - interrupts = <107 IRQ_TYPE_LEVEL_HIGH>; reg = <1>; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts index 9f5f5e1fa82e..683743f81849 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra186-p2771-0000.dts @@ -10,7 +10,7 @@ model = "NVIDIA Jetson TX2 Developer Kit"; compatible = "nvidia,p2771-0000", "nvidia,tegra186"; - aconnect { + aconnect@2900000 { status = "okay"; dma-controller@2930000 { diff --git a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi index fd9177447711..fcd71bfc6707 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186-p3310.dtsi @@ -23,7 +23,7 @@ }; chosen { - bootargs = "earlycon console=ttyS0,115200n8"; + bootargs = "earlycon console=ttyS0,115200n8 fw_devlink=on"; stdout-path = "serial0:115200n8"; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi index 02b26b39cedc..9f75bbf00cf7 100644 --- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi @@ -73,7 +73,7 @@ snps,rxpbl = <8>; }; - aconnect { + aconnect@2900000 { compatible = "nvidia,tegra186-aconnect", "nvidia,tegra210-aconnect"; clocks = <&bpmp TEGRA186_CLK_APE>, diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p2972-0000.dts b/arch/arm64/boot/dts/nvidia/tegra194-p2972-0000.dts index 2888efc42ba1..d618f197a1d3 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p2972-0000.dts +++ b/arch/arm64/boot/dts/nvidia/tegra194-p2972-0000.dts @@ -651,6 +651,8 @@ reg = <0x1a>; interrupt-parent = <&gpio>; interrupts = <TEGRA194_MAIN_GPIO(S, 5) GPIO_ACTIVE_HIGH>; + clocks = <&bpmp TEGRA194_CLK_AUD_MCLK>; + clock-names = "mclk"; realtek,jd-src = <2>; sound-name-prefix = "CVB-RT"; @@ -658,7 +660,6 @@ rt5658_ep: endpoint { remote-endpoint = <&i2s1_dap_ep>; mclk-fs = <256>; - clocks = <&bpmp TEGRA194_CLK_AUD_MCLK>; }; }; }; diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi index 7da3d48cb410..14da4206ea66 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0000.dtsi @@ -5,6 +5,10 @@ model = "NVIDIA Jetson Xavier NX (SD-card)"; compatible = "nvidia,p3668-0000", "nvidia,tegra194"; + aliases { + mmc0 = "/bus@0/mmc@3400000"; + }; + bus@0 { /* SDMMC1 (SD/MMC) */ mmc@3400000 { diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0001.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0001.dtsi index b7808648cfe4..f5a9ebbfb12f 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668-0001.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668-0001.dtsi @@ -5,6 +5,10 @@ model = "NVIDIA Jetson Xavier NX (eMMC)"; compatible = "nvidia,p3668-0001", "nvidia,tegra194"; + aliases { + mmc0 = "/bus@0/mmc@3460000"; + }; + bus@0 { /* SDMMC4 (eMMC) */ mmc@3460000 { diff --git a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi index 4f12721c332b..f16b0aa8a374 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194-p3668.dtsi @@ -14,7 +14,6 @@ i2c5 = "/bus@0/i2c@31c0000"; i2c6 = "/bus@0/i2c@c250000"; i2c7 = "/bus@0/i2c@31e0000"; - mmc0 = "/bus@0/mmc@3460000"; rtc0 = "/bpmp/i2c/pmic@3c"; rtc1 = "/bus@0/rtc@c2a0000"; serial0 = &tcu; diff --git a/arch/arm64/crypto/aes-modes.S b/arch/arm64/crypto/aes-modes.S index bbdb54702aa7..247011356d11 100644 --- a/arch/arm64/crypto/aes-modes.S +++ b/arch/arm64/crypto/aes-modes.S @@ -359,6 +359,7 @@ ST5( mov v4.16b, vctr.16b ) ins vctr.d[0], x8 /* apply carry to N counter blocks for N := x12 */ + cbz x12, 2f adr x16, 1f sub x16, x16, x12, lsl #3 br x16 diff --git a/arch/arm64/crypto/poly1305-glue.c b/arch/arm64/crypto/poly1305-glue.c index 683de671741a..9c3d86e397bf 100644 --- a/arch/arm64/crypto/poly1305-glue.c +++ b/arch/arm64/crypto/poly1305-glue.c @@ -25,7 +25,7 @@ asmlinkage void poly1305_emit(void *state, u8 *digest, const u32 *nonce); static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_neon); -void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE]) { poly1305_init_arm64(&dctx->h, key); dctx->s[0] = get_unaligned_le32(key + 16); diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 5df500dcc627..8a078fc662ac 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -97,9 +97,9 @@ .popsection .subsection 1 663: \insn2 -664: .previous - .org . - (664b-663b) + (662b-661b) +664: .org . - (664b-663b) + (662b-661b) .org . - (662b-661b) + (664b-663b) + .previous .endif .endm @@ -169,11 +169,11 @@ */ .macro alternative_endif 664: + .org . - (664b-663b) + (662b-661b) + .org . - (662b-661b) + (664b-663b) .if .Lasm_alt_mode==0 .previous .endif - .org . - (664b-663b) + (662b-661b) - .org . - (662b-661b) + (664b-663b) .endm /* diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h index 93a161b3bf3f..dc52b733675d 100644 --- a/arch/arm64/include/asm/checksum.h +++ b/arch/arm64/include/asm/checksum.h @@ -37,7 +37,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) } while (--n > 0); sum += ((sum >> 32) | (sum << 32)); - return csum_fold((__force u32)(sum >> 32)); + return csum_fold((__force __wsum)(sum >> 32)); } #define ip_fast_csum ip_fast_csum diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index b77d997b173b..c40f2490cd7b 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -66,7 +66,8 @@ #define ARM64_WORKAROUND_1508412 58 #define ARM64_HAS_LDAPR 59 #define ARM64_KVM_PROTECTED_MODE 60 +#define ARM64_WORKAROUND_NVIDIA_CARMEL_CNP 61 -#define ARM64_NCAPS 61 +#define ARM64_NCAPS 62 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 4e90c2debf70..94d4025acc0b 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -278,6 +278,7 @@ #define CPTR_EL2_DEFAULT CPTR_EL2_RES1 /* Hyp Debug Configuration Register bits */ +#define MDCR_EL2_TTRF (1 << 19) #define MDCR_EL2_TPMS (1 << 14) #define MDCR_EL2_E2PB_MASK (UL(0x3)) #define MDCR_EL2_E2PB_SHIFT (UL(12)) diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h index cf3a0fd7c1a7..9aa193e0e8f2 100644 --- a/arch/arm64/include/asm/paravirt.h +++ b/arch/arm64/include/asm/paravirt.h @@ -3,23 +3,19 @@ #define _ASM_ARM64_PARAVIRT_H #ifdef CONFIG_PARAVIRT +#include <linux/static_call_types.h> + struct static_key; extern struct static_key paravirt_steal_enabled; extern struct static_key paravirt_steal_rq_enabled; -struct pv_time_ops { - unsigned long long (*steal_clock)(int cpu); -}; - -struct paravirt_patch_template { - struct pv_time_ops time; -}; +u64 dummy_steal_clock(int cpu); -extern struct paravirt_patch_template pv_ops; +DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock); static inline u64 paravirt_steal_clock(int cpu) { - return pv_ops.time.steal_clock(cpu); + return static_call(pv_steal_clock)(cpu); } int __init pv_time_init(void); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index ca2cd75d3286..efc10e9041a0 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -251,6 +251,8 @@ unsigned long get_wchan(struct task_struct *p); extern struct task_struct *cpu_switch_to(struct task_struct *prev, struct task_struct *next); +asmlinkage void arm64_preempt_schedule_irq(void); + #define task_pt_regs(p) \ ((struct pt_regs *)(THREAD_SIZE + task_stack_page(p)) - 1) diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 9f4e3b266f21..6623c99f0984 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -55,6 +55,8 @@ void arch_setup_new_exec(void); #define arch_setup_new_exec arch_setup_new_exec void arch_release_task_struct(struct task_struct *tsk); +int arch_dup_task_struct(struct task_struct *dst, + struct task_struct *src); #endif diff --git a/arch/arm64/include/asm/word-at-a-time.h b/arch/arm64/include/asm/word-at-a-time.h index 3333950b5909..ea487218db79 100644 --- a/arch/arm64/include/asm/word-at-a-time.h +++ b/arch/arm64/include/asm/word-at-a-time.h @@ -53,7 +53,7 @@ static inline unsigned long find_zero(unsigned long mask) */ static inline unsigned long load_unaligned_zeropad(const void *addr) { - unsigned long ret, offset; + unsigned long ret, tmp; /* Load word from unaligned pointer addr */ asm( @@ -61,9 +61,9 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) "2:\n" " .pushsection .fixup,\"ax\"\n" " .align 2\n" - "3: and %1, %2, #0x7\n" - " bic %2, %2, #0x7\n" - " ldr %0, [%2]\n" + "3: bic %1, %2, #0x7\n" + " ldr %0, [%1]\n" + " and %1, %2, #0x7\n" " lsl %1, %1, #0x3\n" #ifndef __AARCH64EB__ " lsr %0, %0, %1\n" @@ -73,7 +73,7 @@ static inline unsigned long load_unaligned_zeropad(const void *addr) " b 2b\n" " .popsection\n" _ASM_EXTABLE(1b, 3b) - : "=&r" (ret), "=&r" (offset) + : "=&r" (ret), "=&r" (tmp) : "r" (addr), "Q" (*(unsigned long *)addr)); return ret; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 506a1cd37973..e2c20c036442 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -526,6 +526,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = { 1, 0), }, #endif +#ifdef CONFIG_NVIDIA_CARMEL_CNP_ERRATUM + { + /* NVIDIA Carmel */ + .desc = "NVIDIA Carmel CNP erratum", + .capability = ARM64_WORKAROUND_NVIDIA_CARMEL_CNP, + ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_CARMEL), + }, +#endif { } }; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 066030717a4c..e5281e1c8f1d 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -383,7 +383,6 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { * of support. */ S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_EXACT, ID_AA64DFR0_PMUVER_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_TRACEVER_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_EXACT, ID_AA64DFR0_DEBUGVER_SHIFT, 4, 0x6), ARM64_FTR_END, }; @@ -1321,7 +1320,10 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) * may share TLB entries with a CPU stuck in the crashed * kernel. */ - if (is_kdump_kernel()) + if (is_kdump_kernel()) + return false; + + if (cpus_have_const_cap(ARM64_WORKAROUND_NVIDIA_CARMEL_CNP)) return false; return has_cpuid_feature(entry, scope); diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 77605aec25fe..51fcf99d5351 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -353,7 +353,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) * with the CLIDR_EL1 fields to avoid triggering false warnings * when there is a mismatch across the CPUs. Keep track of the * effective value of the CTR_EL0 in our internal records for - * acurate sanity check and feature enablement. + * accurate sanity check and feature enablement. */ info->reg_ctr = read_cpuid_effective_cachetype(); info->reg_dczid = read_cpuid(DCZID_EL0); diff --git a/arch/arm64/kernel/crash_dump.c b/arch/arm64/kernel/crash_dump.c index e6e284265f19..58303a9ec32c 100644 --- a/arch/arm64/kernel/crash_dump.c +++ b/arch/arm64/kernel/crash_dump.c @@ -64,5 +64,7 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf, ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) { memcpy(buf, phys_to_virt((phys_addr_t)*ppos), count); + *ppos += count; + return count; } diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index a31a0a713c85..6acfc5e6b5e0 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -148,16 +148,18 @@ alternative_cb_end .endm /* Check for MTE asynchronous tag check faults */ - .macro check_mte_async_tcf, flgs, tmp + .macro check_mte_async_tcf, tmp, ti_flags #ifdef CONFIG_ARM64_MTE + .arch_extension lse alternative_if_not ARM64_MTE b 1f alternative_else_nop_endif mrs_s \tmp, SYS_TFSRE0_EL1 tbz \tmp, #SYS_TFSR_EL1_TF0_SHIFT, 1f /* Asynchronous TCF occurred for TTBR0 access, set the TI flag */ - orr \flgs, \flgs, #_TIF_MTE_ASYNC_FAULT - str \flgs, [tsk, #TSK_TI_FLAGS] + mov \tmp, #_TIF_MTE_ASYNC_FAULT + add \ti_flags, tsk, #TSK_TI_FLAGS + stset \tmp, [\ti_flags] msr_s SYS_TFSRE0_EL1, xzr 1: #endif @@ -244,7 +246,7 @@ alternative_else_nop_endif disable_step_tsk x19, x20 /* Check for asynchronous tag check faults in user space */ - check_mte_async_tcf x19, x22 + check_mte_async_tcf x22, x23 apply_ssbd 1, x22, x23 ptrauth_keys_install_kernel tsk, x20, x22, x23 diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index c07d7a034941..75fed4460407 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -18,6 +18,7 @@ #include <linux/reboot.h> #include <linux/slab.h> #include <linux/types.h> +#include <linux/static_call.h> #include <asm/paravirt.h> #include <asm/pvclock-abi.h> @@ -26,8 +27,12 @@ struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; -struct paravirt_patch_template pv_ops; -EXPORT_SYMBOL_GPL(pv_ops); +static u64 native_steal_clock(int cpu) +{ + return 0; +} + +DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); struct pv_time_stolen_time_region { struct pvclock_vcpu_stolen_time *kaddr; @@ -45,7 +50,7 @@ static int __init parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); /* return stolen time in ns by asking the hypervisor */ -static u64 pv_steal_clock(int cpu) +static u64 para_steal_clock(int cpu) { struct pv_time_stolen_time_region *reg; @@ -150,7 +155,7 @@ int __init pv_time_init(void) if (ret) return ret; - pv_ops.time.steal_clock = pv_steal_clock; + static_call_update(pv_steal_clock, para_steal_clock); static_key_slow_inc(¶virt_steal_enabled); if (steal_acc) diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 66aac2881ba8..85645b2b0c7a 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -267,10 +267,12 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr) if (!instruction_pointer(regs)) BUG(); - if (kcb->kprobe_status == KPROBE_REENTER) + if (kcb->kprobe_status == KPROBE_REENTER) { restore_previous_kprobe(kcb); - else + } else { + kprobes_restore_local_irqflag(kcb, regs); reset_current_kprobe(); + } break; case KPROBE_HIT_ACTIVE: diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 325c83b1a24d..6e60aa3b5ea9 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -57,6 +57,8 @@ #include <asm/processor.h> #include <asm/pointer_auth.h> #include <asm/stacktrace.h> +#include <asm/switch_to.h> +#include <asm/system_misc.h> #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) #include <linux/stackprotector.h> diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 5bfd9b87f85d..4ea9392f86e0 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -134,7 +134,7 @@ SYM_FUNC_START(_cpu_resume) */ bl cpu_do_resume -#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) mov x0, sp bl kasan_unpoison_task_stack_below #endif diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index ad20981dfda4..d55bdfb7789c 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -194,8 +194,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) #ifdef CONFIG_STACKTRACE -void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, - struct task_struct *task, struct pt_regs *regs) +noinline void arch_stack_walk(stack_trace_consume_fn consume_entry, + void *cookie, struct task_struct *task, + struct pt_regs *regs) { struct stackframe frame; @@ -203,8 +204,8 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, start_backtrace(&frame, regs->regs[29], regs->pc); else if (task == current) start_backtrace(&frame, - (unsigned long)__builtin_frame_address(0), - (unsigned long)arch_stack_walk); + (unsigned long)__builtin_frame_address(1), + (unsigned long)__builtin_return_address(0)); else start_backtrace(&frame, thread_saved_fp(task), thread_saved_pc(task)); diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index 7a7e425616b5..dbc890511631 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -89,6 +89,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) * - Debug ROM Address (MDCR_EL2_TDRA) * - OS related registers (MDCR_EL2_TDOSA) * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) + * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) * * Additionally, KVM only traps guest accesses to the debug registers if * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY @@ -112,6 +113,7 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | MDCR_EL2_TPMS | + MDCR_EL2_TTRF | MDCR_EL2_TPMCR | MDCR_EL2_TDRA | MDCR_EL2_TDOSA); diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index ee3682b9873c..39f8f7f9227c 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -429,6 +429,13 @@ u64 __vgic_v3_get_gic_config(void) if (has_vhe()) flags = local_daif_save(); + /* + * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates + * that to be able to set ICC_SRE_EL1.SRE to 0, all the + * interrupt overrides must be set. You've got to love this. + */ + sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO); + isb(); write_gicreg(0, ICC_SRE_EL1); isb(); @@ -436,6 +443,8 @@ u64 __vgic_v3_get_gic_config(void) write_gicreg(sre, ICC_SRE_EL1); isb(); + sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0); + isb(); if (has_vhe()) local_daif_restore(flags); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 7484ea4f6ba0..5d9550fdb9cf 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1448,6 +1448,22 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size) struct range arch_get_mappable_range(void) { struct range mhp_range; + u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual)); + u64 end_linear_pa = __pa(PAGE_END - 1); + + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + /* + * Check for a wrap, it is possible because of randomized linear + * mapping the start physical address is actually bigger than + * the end physical address. In this case set start to zero + * because [0, end_linear_pa] range must still be able to cover + * all addressable physical addresses. + */ + if (start_linear_pa > end_linear_pa) + start_linear_pa = 0; + } + + WARN_ON(start_linear_pa > end_linear_pa); /* * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)] @@ -1455,8 +1471,9 @@ struct range arch_get_mappable_range(void) * range which can be mapped inside this linear mapping range, must * also be derived from its end points. */ - mhp_range.start = __pa(_PAGE_OFFSET(vabits_actual)); - mhp_range.end = __pa(PAGE_END - 1); + mhp_range.start = start_linear_pa; + mhp_range.end = end_linear_pa; + return mhp_range; } diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 34e91224adc3..8de5b987edb9 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -314,7 +314,7 @@ config FORCE_MAX_ZONEORDER int "Maximum zone order" default "11" -config RAM_BASE +config DRAM_BASE hex "DRAM start addr (the same with memory-section in dts)" default 0x0 diff --git a/arch/csky/include/asm/page.h b/arch/csky/include/asm/page.h index 3b91fc3cf36f..ed7451478b1b 100644 --- a/arch/csky/include/asm/page.h +++ b/arch/csky/include/asm/page.h @@ -28,7 +28,7 @@ #define SSEG_SIZE 0x20000000 #define LOWMEM_LIMIT (SSEG_SIZE * 2) -#define PHYS_OFFSET_OFFSET (CONFIG_RAM_BASE & (SSEG_SIZE - 1)) +#define PHYS_OFFSET_OFFSET (CONFIG_DRAM_BASE & (SSEG_SIZE - 1)) #ifndef __ASSEMBLY__ diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig index ca0d596c800d..8916a2850c48 100644 --- a/arch/ia64/configs/generic_defconfig +++ b/arch/ia64/configs/generic_defconfig @@ -55,8 +55,6 @@ CONFIG_CHR_DEV_SG=m CONFIG_SCSI_FC_ATTRS=y CONFIG_SCSI_SYM53C8XX_2=y CONFIG_SCSI_QLOGIC_1280=y -CONFIG_ATA=y -CONFIG_ATA_PIIX=y CONFIG_SATA_VITESSE=y CONFIG_MD=y CONFIG_BLK_DEV_MD=m diff --git a/arch/ia64/include/asm/ptrace.h b/arch/ia64/include/asm/ptrace.h index b3aa46090101..08179135905c 100644 --- a/arch/ia64/include/asm/ptrace.h +++ b/arch/ia64/include/asm/ptrace.h @@ -54,8 +54,7 @@ static inline unsigned long user_stack_pointer(struct pt_regs *regs) { - /* FIXME: should this be bspstore + nr_dirty regs? */ - return regs->ar_bspstore; + return regs->r12; } static inline int is_syscall_success(struct pt_regs *regs) @@ -79,11 +78,6 @@ static inline long regs_return_value(struct pt_regs *regs) unsigned long __ip = instruction_pointer(regs); \ (__ip & ~3UL) + ((__ip & 3UL) << 2); \ }) -/* - * Why not default? Because user_stack_pointer() on ia64 gives register - * stack backing store instead... - */ -#define current_user_stack_pointer() (current_pt_regs()->r12) /* given a pointer to a task_struct, return the user's pt_regs */ # define task_pt_regs(t) (((struct pt_regs *) ((char *) (t) + IA64_STK_OFFSET)) - 1) diff --git a/arch/ia64/kernel/err_inject.c b/arch/ia64/kernel/err_inject.c index 8b5b8e6bc9d9..dd5bfed52031 100644 --- a/arch/ia64/kernel/err_inject.c +++ b/arch/ia64/kernel/err_inject.c @@ -59,7 +59,7 @@ show_##name(struct device *dev, struct device_attribute *attr, \ char *buf) \ { \ u32 cpu=dev->id; \ - return sprintf(buf, "%lx\n", name[cpu]); \ + return sprintf(buf, "%llx\n", name[cpu]); \ } #define store(name) \ @@ -86,9 +86,9 @@ store_call_start(struct device *dev, struct device_attribute *attr, #ifdef ERR_INJ_DEBUG printk(KERN_DEBUG "pal_mc_err_inject for cpu%d:\n", cpu); - printk(KERN_DEBUG "err_type_info=%lx,\n", err_type_info[cpu]); - printk(KERN_DEBUG "err_struct_info=%lx,\n", err_struct_info[cpu]); - printk(KERN_DEBUG "err_data_buffer=%lx, %lx, %lx.\n", + printk(KERN_DEBUG "err_type_info=%llx,\n", err_type_info[cpu]); + printk(KERN_DEBUG "err_struct_info=%llx,\n", err_struct_info[cpu]); + printk(KERN_DEBUG "err_data_buffer=%llx, %llx, %llx.\n", err_data_buffer[cpu].data1, err_data_buffer[cpu].data2, err_data_buffer[cpu].data3); @@ -117,8 +117,8 @@ store_call_start(struct device *dev, struct device_attribute *attr, #ifdef ERR_INJ_DEBUG printk(KERN_DEBUG "Returns: status=%d,\n", (int)status[cpu]); - printk(KERN_DEBUG "capabilities=%lx,\n", capabilities[cpu]); - printk(KERN_DEBUG "resources=%lx\n", resources[cpu]); + printk(KERN_DEBUG "capabilities=%llx,\n", capabilities[cpu]); + printk(KERN_DEBUG "resources=%llx\n", resources[cpu]); #endif return size; } @@ -131,7 +131,7 @@ show_virtual_to_phys(struct device *dev, struct device_attribute *attr, char *buf) { unsigned int cpu=dev->id; - return sprintf(buf, "%lx\n", phys_addr[cpu]); + return sprintf(buf, "%llx\n", phys_addr[cpu]); } static ssize_t @@ -145,7 +145,7 @@ store_virtual_to_phys(struct device *dev, struct device_attribute *attr, ret = get_user_pages_fast(virt_addr, 1, FOLL_WRITE, NULL); if (ret<=0) { #ifdef ERR_INJ_DEBUG - printk("Virtual address %lx is not existing.\n",virt_addr); + printk("Virtual address %llx is not existing.\n", virt_addr); #endif return -EINVAL; } @@ -163,7 +163,7 @@ show_err_data_buffer(struct device *dev, { unsigned int cpu=dev->id; - return sprintf(buf, "%lx, %lx, %lx\n", + return sprintf(buf, "%llx, %llx, %llx\n", err_data_buffer[cpu].data1, err_data_buffer[cpu].data2, err_data_buffer[cpu].data3); @@ -178,13 +178,13 @@ store_err_data_buffer(struct device *dev, int ret; #ifdef ERR_INJ_DEBUG - printk("write err_data_buffer=[%lx,%lx,%lx] on cpu%d\n", + printk("write err_data_buffer=[%llx,%llx,%llx] on cpu%d\n", err_data_buffer[cpu].data1, err_data_buffer[cpu].data2, err_data_buffer[cpu].data3, cpu); #endif - ret=sscanf(buf, "%lx, %lx, %lx", + ret = sscanf(buf, "%llx, %llx, %llx", &err_data_buffer[cpu].data1, &err_data_buffer[cpu].data2, &err_data_buffer[cpu].data3); diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index d4cae2fc69ca..adf6521525f4 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -1824,7 +1824,7 @@ ia64_mca_cpu_init(void *cpu_data) data = mca_bootmem(); first_time = 0; } else - data = (void *)__get_free_pages(GFP_KERNEL, + data = (void *)__get_free_pages(GFP_ATOMIC, get_order(sz)); if (!data) panic("Could not allocate MCA memory for cpu %d\n", diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 03b3a02375ff..c310b4c99fb3 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -95,7 +95,7 @@ static int __init build_node_maps(unsigned long start, unsigned long len, * acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been * called yet. Note that node 0 will also count all non-existent cpus. */ -static int __meminit early_nr_cpus_node(int node) +static int early_nr_cpus_node(int node) { int cpu, n = 0; @@ -110,7 +110,7 @@ static int __meminit early_nr_cpus_node(int node) * compute_pernodesize - compute size of pernode data * @node: the node id. */ -static unsigned long __meminit compute_pernodesize(int node) +static unsigned long compute_pernodesize(int node) { unsigned long pernodesize = 0, cpus; @@ -367,7 +367,7 @@ static void __init reserve_pernode_space(void) } } -static void __meminit scatter_node_data(void) +static void scatter_node_data(void) { pg_data_t **dst; int node; diff --git a/arch/m68k/include/asm/page_mm.h b/arch/m68k/include/asm/page_mm.h index 9e8f0cc30a2c..2411ea9ef578 100644 --- a/arch/m68k/include/asm/page_mm.h +++ b/arch/m68k/include/asm/page_mm.h @@ -167,7 +167,7 @@ static inline __attribute_const__ int __virt_to_node_shift(void) ((__p) - pgdat->node_mem_map) + pgdat->node_start_pfn; \ }) #else -#define ARCH_PFN_OFFSET (m68k_memory[0].addr) +#define ARCH_PFN_OFFSET (m68k_memory[0].addr >> PAGE_SHIFT) #include <asm-generic/memory_model.h> #endif diff --git a/arch/mips/crypto/poly1305-glue.c b/arch/mips/crypto/poly1305-glue.c index fc881b46d911..bc6110fb98e0 100644 --- a/arch/mips/crypto/poly1305-glue.c +++ b/arch/mips/crypto/poly1305-glue.c @@ -17,7 +17,7 @@ asmlinkage void poly1305_init_mips(void *state, const u8 *key); asmlinkage void poly1305_blocks_mips(void *state, const u8 *src, u32 len, u32 hibit); asmlinkage void poly1305_emit_mips(void *state, u8 *digest, const u32 *nonce); -void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE]) { poly1305_init_mips(&dctx->h, key); dctx->s[0] = get_unaligned_le32(key + 16); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 279be0153f8b..23a140327a0b 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -43,7 +43,7 @@ #include <asm/prom.h> #ifdef CONFIG_MIPS_ELF_APPENDED_DTB -const char __section(".appended_dtb") __appended_dtb[0x100000]; +char __section(".appended_dtb") __appended_dtb[0x100000]; #endif /* CONFIG_MIPS_ELF_APPENDED_DTB */ struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly; diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c index 6eb98a7ad27d..ad5344ef5d33 100644 --- a/arch/nds32/mm/cacheflush.c +++ b/arch/nds32/mm/cacheflush.c @@ -238,7 +238,7 @@ void flush_dcache_page(struct page *page) { struct address_space *mapping; - mapping = page_mapping(page); + mapping = page_mapping_file(page); if (mapping && !mapping_mapped(mapping)) set_bit(PG_dcache_dirty, &page->flags); else { diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h index cf5ee9b0b393..84ee232278a6 100644 --- a/arch/parisc/include/asm/cmpxchg.h +++ b/arch/parisc/include/asm/cmpxchg.h @@ -72,7 +72,7 @@ __cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size) #endif case 4: return __cmpxchg_u32((unsigned int *)ptr, (unsigned int)old, (unsigned int)new_); - case 1: return __cmpxchg_u8((u8 *)ptr, (u8)old, (u8)new_); + case 1: return __cmpxchg_u8((u8 *)ptr, old & 0xff, new_ & 0xff); } __cmpxchg_called_with_bad_pointer(); return old; diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index 11ece0d07374..b5fbcd2c1780 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -272,7 +272,6 @@ on downward growing arches, it looks like this: regs->gr[23] = 0; \ } while(0) -struct task_struct; struct mm_struct; /* Free all resources held by a thread. */ diff --git a/arch/parisc/math-emu/fpu.h b/arch/parisc/math-emu/fpu.h index 853c19c03828..dec951d40286 100644 --- a/arch/parisc/math-emu/fpu.h +++ b/arch/parisc/math-emu/fpu.h @@ -5,34 +5,10 @@ * Floating-point emulation code * Copyright (C) 2001 Hewlett-Packard (Paul Bame) <bame@debian.org> */ -/* - * BEGIN_DESC - * - * File: - * @(#) pa/fp/fpu.h $Revision: 1.1 $ - * - * Purpose: - * <<please update with a synopis of the functionality provided by this file>> - * - * - * END_DESC -*/ - -#ifdef __NO_PA_HDRS - PA header file -- do not include this header file for non-PA builds. -#endif - #ifndef _MACHINE_FPU_INCLUDED /* allows multiple inclusion */ #define _MACHINE_FPU_INCLUDED -#if 0 -#ifndef _SYS_STDSYMS_INCLUDED -# include <sys/stdsyms.h> -#endif /* _SYS_STDSYMS_INCLUDED */ -#include <machine/pdc/pdc_rqsts.h> -#endif - #define PA83_FPU_FLAG 0x00000001 #define PA89_FPU_FLAG 0x00000002 #define PA2_0_FPU_FLAG 0x00000010 @@ -43,21 +19,19 @@ #define COPR_FP 0x00000080 /* Floating point -- Coprocessor 0 */ #define SFU_MPY_DIVIDE 0x00008000 /* Multiply/Divide __ SFU 0 */ - #define EM_FPU_TYPE_OFFSET 272 /* version of EMULATION software for COPR,0,0 instruction */ #define EMULATION_VERSION 4 /* - * The only was to differeniate between TIMEX and ROLEX (or PCX-S and PCX-T) - * is thorough the potential type field from the PDC_MODEL call. The - * following flags are used at assist this differeniation. + * The only way to differentiate between TIMEX and ROLEX (or PCX-S and PCX-T) + * is through the potential type field from the PDC_MODEL call. + * The following flags are used to assist this differentiation. */ #define ROLEX_POTENTIAL_KEY_FLAGS PDC_MODEL_CPU_KEY_WORD_TO_IO #define TIMEX_POTENTIAL_KEY_FLAGS (PDC_MODEL_CPU_KEY_QUAD_STORE | \ PDC_MODEL_CPU_KEY_RECIP_SQRT) - #endif /* ! _MACHINE_FPU_INCLUDED */ diff --git a/arch/powerpc/crypto/sha1-spe-glue.c b/arch/powerpc/crypto/sha1-spe-glue.c index b1e577cbf00c..88e8ea73bfa7 100644 --- a/arch/powerpc/crypto/sha1-spe-glue.c +++ b/arch/powerpc/crypto/sha1-spe-glue.c @@ -107,7 +107,7 @@ static int ppc_spe_sha1_update(struct shash_desc *desc, const u8 *data, src += bytes; len -= bytes; - }; + } memcpy((char *)sctx->buffer, src, len); return 0; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index 6084fa499aa3..f66b63e81c3b 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -191,3 +191,7 @@ $(obj)/prom_init_check: $(src)/prom_init_check.sh $(obj)/prom_init.o FORCE targets += prom_init_check clean-files := vmlinux.lds + +# Force dependency (incbin is bad) +$(obj)/vdso32_wrapper.o : $(obj)/vdso32/vdso32.so.dbg +$(obj)/vdso64_wrapper.o : $(obj)/vdso64/vdso64.so.dbg diff --git a/arch/powerpc/kernel/ptrace/Makefile b/arch/powerpc/kernel/ptrace/Makefile index 8ebc11d1168d..77abd1a5a508 100644 --- a/arch/powerpc/kernel/ptrace/Makefile +++ b/arch/powerpc/kernel/ptrace/Makefile @@ -6,11 +6,11 @@ CFLAGS_ptrace-view.o += -DUTS_MACHINE='"$(UTS_MACHINE)"' obj-y += ptrace.o ptrace-view.o -obj-$(CONFIG_PPC_FPU_REGS) += ptrace-fpu.o +obj-y += ptrace-fpu.o obj-$(CONFIG_COMPAT) += ptrace32.o obj-$(CONFIG_VSX) += ptrace-vsx.o ifneq ($(CONFIG_VSX),y) -obj-$(CONFIG_PPC_FPU_REGS) += ptrace-novsx.o +obj-y += ptrace-novsx.o endif obj-$(CONFIG_ALTIVEC) += ptrace-altivec.o obj-$(CONFIG_SPE) += ptrace-spe.o diff --git a/arch/powerpc/kernel/ptrace/ptrace-decl.h b/arch/powerpc/kernel/ptrace/ptrace-decl.h index 3487f2c9735c..eafe5f0f6289 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-decl.h +++ b/arch/powerpc/kernel/ptrace/ptrace-decl.h @@ -165,22 +165,8 @@ int ptrace_put_reg(struct task_struct *task, int regno, unsigned long data); extern const struct user_regset_view user_ppc_native_view; /* ptrace-fpu */ -#ifdef CONFIG_PPC_FPU_REGS int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data); int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data); -#else -static inline int -ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data) -{ - return -EIO; -} - -static inline int -ptrace_put_fpr(struct task_struct *child, int index, unsigned long data) -{ - return -EIO; -} -#endif /* ptrace-(no)adv */ void ppc_gethwdinfo(struct ppc_debug_info *dbginfo); diff --git a/arch/powerpc/kernel/ptrace/ptrace-fpu.c b/arch/powerpc/kernel/ptrace/ptrace-fpu.c index 8301cb52dd99..5dca19361316 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-fpu.c +++ b/arch/powerpc/kernel/ptrace/ptrace-fpu.c @@ -8,32 +8,42 @@ int ptrace_get_fpr(struct task_struct *child, int index, unsigned long *data) { +#ifdef CONFIG_PPC_FPU_REGS unsigned int fpidx = index - PT_FPR0; +#endif if (index > PT_FPSCR) return -EIO; +#ifdef CONFIG_PPC_FPU_REGS flush_fp_to_thread(child); if (fpidx < (PT_FPSCR - PT_FPR0)) memcpy(data, &child->thread.TS_FPR(fpidx), sizeof(long)); else *data = child->thread.fp_state.fpscr; +#else + *data = 0; +#endif return 0; } int ptrace_put_fpr(struct task_struct *child, int index, unsigned long data) { +#ifdef CONFIG_PPC_FPU_REGS unsigned int fpidx = index - PT_FPR0; +#endif if (index > PT_FPSCR) return -EIO; +#ifdef CONFIG_PPC_FPU_REGS flush_fp_to_thread(child); if (fpidx < (PT_FPSCR - PT_FPR0)) memcpy(&child->thread.TS_FPR(fpidx), &data, sizeof(long)); else child->thread.fp_state.fpscr = data; +#endif return 0; } diff --git a/arch/powerpc/kernel/ptrace/ptrace-novsx.c b/arch/powerpc/kernel/ptrace/ptrace-novsx.c index b3b36835658a..7433f3db979a 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-novsx.c +++ b/arch/powerpc/kernel/ptrace/ptrace-novsx.c @@ -21,12 +21,16 @@ int fpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { +#ifdef CONFIG_PPC_FPU_REGS BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); flush_fp_to_thread(target); return membuf_write(&to, &target->thread.fp_state, 33 * sizeof(u64)); +#else + return membuf_write(&to, &empty_zero_page, 33 * sizeof(u64)); +#endif } /* @@ -46,6 +50,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { +#ifdef CONFIG_PPC_FPU_REGS BUILD_BUG_ON(offsetof(struct thread_fp_state, fpscr) != offsetof(struct thread_fp_state, fpr[32])); @@ -53,4 +58,7 @@ int fpr_set(struct task_struct *target, const struct user_regset *regset, return user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.fp_state, 0, -1); +#else + return 0; +#endif } diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c index 2bad8068f598..6ccffc65ac97 100644 --- a/arch/powerpc/kernel/ptrace/ptrace-view.c +++ b/arch/powerpc/kernel/ptrace/ptrace-view.c @@ -522,13 +522,11 @@ static const struct user_regset native_regsets[] = { .size = sizeof(long), .align = sizeof(long), .regset_get = gpr_get, .set = gpr_set }, -#ifdef CONFIG_PPC_FPU_REGS [REGSET_FPR] = { .core_note_type = NT_PRFPREG, .n = ELF_NFPREG, .size = sizeof(double), .align = sizeof(double), .regset_get = fpr_get, .set = fpr_set }, -#endif #ifdef CONFIG_ALTIVEC [REGSET_VMX] = { .core_note_type = NT_PPC_VMX, .n = 34, diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c index 75ee918a120a..f651b992fe01 100644 --- a/arch/powerpc/kernel/signal_32.c +++ b/arch/powerpc/kernel/signal_32.c @@ -775,7 +775,7 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, else prepare_save_user_regs(1); - if (!user_write_access_begin(frame, sizeof(*frame))) + if (!user_access_begin(frame, sizeof(*frame))) goto badframe; /* Put the siginfo & fill in most of the ucontext */ @@ -809,17 +809,15 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, unsafe_put_user(PPC_INST_ADDI + __NR_rt_sigreturn, &mctx->mc_pad[0], failed); unsafe_put_user(PPC_INST_SC, &mctx->mc_pad[1], failed); + asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0])); } unsafe_put_sigset_t(&frame->uc.uc_sigmask, oldset, failed); - user_write_access_end(); + user_access_end(); if (copy_siginfo_to_user(&frame->info, &ksig->info)) goto badframe; - if (tramp == (unsigned long)mctx->mc_pad) - flush_icache_range(tramp, tramp + 2 * sizeof(unsigned long)); - regs->link = tramp; #ifdef CONFIG_PPC_FPU_REGS @@ -844,7 +842,7 @@ int handle_rt_signal32(struct ksignal *ksig, sigset_t *oldset, return 0; failed: - user_write_access_end(); + user_access_end(); badframe: signal_fault(tsk, regs, "handle_rt_signal32", frame); @@ -879,7 +877,7 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, else prepare_save_user_regs(1); - if (!user_write_access_begin(frame, sizeof(*frame))) + if (!user_access_begin(frame, sizeof(*frame))) goto badframe; sc = (struct sigcontext __user *) &frame->sctx; @@ -908,11 +906,9 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, /* Set up the sigreturn trampoline: li r0,sigret; sc */ unsafe_put_user(PPC_INST_ADDI + __NR_sigreturn, &mctx->mc_pad[0], failed); unsafe_put_user(PPC_INST_SC, &mctx->mc_pad[1], failed); + asm("dcbst %y0; sync; icbi %y0; sync" :: "Z" (mctx->mc_pad[0])); } - user_write_access_end(); - - if (tramp == (unsigned long)mctx->mc_pad) - flush_icache_range(tramp, tramp + 2 * sizeof(unsigned long)); + user_access_end(); regs->link = tramp; @@ -935,7 +931,7 @@ int handle_signal32(struct ksignal *ksig, sigset_t *oldset, return 0; failed: - user_write_access_end(); + user_access_end(); badframe: signal_fault(tsk, regs, "handle_signal32", frame); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 764170fdb0f7..3805519a6469 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -887,7 +887,8 @@ static long pSeries_lpar_hpte_updatepp(unsigned long slot, want_v = hpte_encode_avpn(vpn, psize, ssize); - flags = (newpp & 7) | H_AVPN; + flags = (newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_KEY_LO)) | H_AVPN; + flags |= (newpp & HPTE_R_KEY_HI) >> 48; if (mmu_has_feature(MMU_FTR_KERNEL_RO)) /* Move pp0 into bit 8 (IBM 55) */ flags |= (newpp & HPTE_R_PP0) >> 55; diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c index ea4d6a660e0d..e83e0891272d 100644 --- a/arch/powerpc/platforms/pseries/mobility.c +++ b/arch/powerpc/platforms/pseries/mobility.c @@ -452,12 +452,28 @@ static int do_suspend(void) return ret; } +/** + * struct pseries_suspend_info - State shared between CPUs for join/suspend. + * @counter: Threads are to increment this upon resuming from suspend + * or if an error is received from H_JOIN. The thread which performs + * the first increment (i.e. sets it to 1) is responsible for + * waking the other threads. + * @done: False if join/suspend is in progress. True if the operation is + * complete (successful or not). + */ +struct pseries_suspend_info { + atomic_t counter; + bool done; +}; + static int do_join(void *arg) { - atomic_t *counter = arg; + struct pseries_suspend_info *info = arg; + atomic_t *counter = &info->counter; long hvrc; int ret; +retry: /* Must ensure MSR.EE off for H_JOIN. */ hard_irq_disable(); hvrc = plpar_hcall_norets(H_JOIN); @@ -473,8 +489,20 @@ static int do_join(void *arg) case H_SUCCESS: /* * The suspend is complete and this cpu has received a - * prod. + * prod, or we've received a stray prod from unrelated + * code (e.g. paravirt spinlocks) and we need to join + * again. + * + * This barrier orders the return from H_JOIN above vs + * the load of info->done. It pairs with the barrier + * in the wakeup/prod path below. */ + smp_mb(); + if (READ_ONCE(info->done) == false) { + pr_info_ratelimited("premature return from H_JOIN on CPU %i, retrying", + smp_processor_id()); + goto retry; + } ret = 0; break; case H_BAD_MODE: @@ -488,6 +516,13 @@ static int do_join(void *arg) if (atomic_inc_return(counter) == 1) { pr_info("CPU %u waking all threads\n", smp_processor_id()); + WRITE_ONCE(info->done, true); + /* + * This barrier orders the store to info->done vs subsequent + * H_PRODs to wake the other CPUs. It pairs with the barrier + * in the H_SUCCESS case above. + */ + smp_mb(); prod_others(); } /* @@ -535,11 +570,16 @@ static int pseries_suspend(u64 handle) int ret; while (true) { - atomic_t counter = ATOMIC_INIT(0); + struct pseries_suspend_info info; unsigned long vasi_state; int vasi_err; - ret = stop_machine(do_join, &counter, cpu_online_mask); + info = (struct pseries_suspend_info) { + .counter = ATOMIC_INIT(0), + .done = false, + }; + + ret = stop_machine(do_join, &info, cpu_online_mask); if (ret == 0) break; /* diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 87d7b52f278f..4515a10c5d22 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -153,7 +153,7 @@ config ARCH_FLATMEM_ENABLE config ARCH_SPARSEMEM_ENABLE def_bool y depends on MMU - select SPARSEMEM_STATIC if 32BIT && SPARSMEM + select SPARSEMEM_STATIC if 32BIT && SPARSEMEM select SPARSEMEM_VMEMMAP_ENABLE if 64BIT config ARCH_SELECT_MEMORY_MODEL @@ -314,7 +314,7 @@ endchoice # Common NUMA Features config NUMA bool "NUMA Memory Allocation and Scheduler Support" - depends on SMP + depends on SMP && MMU select GENERIC_ARCH_NUMA select OF_NUMA select ARCH_SUPPORTS_NUMA_BALANCING diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index 824b2c9da75b..f944062c9d99 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -306,7 +306,9 @@ do { \ * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable - * to the result of dereferencing @ptr. + * to the result of dereferencing @ptr. The value of @x is copied to avoid + * re-ordering where @x is evaluated inside the block that enables user-space + * access (thus bypassing user space protection if @x is a function). * * Caller must check the pointer with access_ok() before calling this * function. @@ -316,12 +318,13 @@ do { \ #define __put_user(x, ptr) \ ({ \ __typeof__(*(ptr)) __user *__gu_ptr = (ptr); \ + __typeof__(*__gu_ptr) __val = (x); \ long __pu_err = 0; \ \ __chk_user_ptr(__gu_ptr); \ \ __enable_user_access(); \ - __put_user_nocheck(x, __gu_ptr, __pu_err); \ + __put_user_nocheck(__val, __gu_ptr, __pu_err); \ __disable_user_access(); \ \ __pu_err; \ diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 744f3209c48d..83095faa680e 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -130,6 +130,9 @@ skip_context_tracking: */ andi t0, s1, SR_PIE beqz t0, 1f + /* kprobes, entered via ebreak, must have interrupts disabled. */ + li t0, EXC_BREAKPOINT + beq s4, t0, 1f #ifdef CONFIG_TRACE_IRQFLAGS call trace_hardirqs_on #endif @@ -447,6 +450,7 @@ ENDPROC(__switch_to) #endif .section ".rodata" + .align LGREG /* Exception vector table */ ENTRY(excp_vect_table) RISCV_PTR do_trap_insn_misaligned diff --git a/arch/riscv/kernel/probes/ftrace.c b/arch/riscv/kernel/probes/ftrace.c index 17ca5e923bb0..aab85a82f419 100644 --- a/arch/riscv/kernel/probes/ftrace.c +++ b/arch/riscv/kernel/probes/ftrace.c @@ -9,10 +9,16 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe *p; struct pt_regs *regs; struct kprobe_ctlblk *kcb; + int bit; + bit = ftrace_test_recursion_trylock(ip, parent_ip); + if (bit < 0) + return; + + preempt_disable_notrace(); p = get_kprobe((kprobe_opcode_t *)ip); if (unlikely(!p) || kprobe_disabled(p)) - return; + goto out; regs = ftrace_get_regs(fregs); kcb = get_kprobe_ctlblk(); @@ -45,6 +51,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, */ __this_cpu_write(current_kprobe, NULL); } +out: + preempt_enable_notrace(); + ftrace_test_recursion_unlock(bit); } NOKPROBE_SYMBOL(kprobe_ftrace_handler); diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 3f893c9d9d85..2b3e0cb90d78 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -14,7 +14,7 @@ #include <asm/stacktrace.h> -register const unsigned long sp_in_global __asm__("sp"); +register unsigned long sp_in_global __asm__("sp"); #ifdef CONFIG_FRAME_POINTER diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 0879b5df11b9..1357abf79570 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -178,6 +178,7 @@ asmlinkage __visible void do_trap_break(struct pt_regs *regs) else die(regs, "Kernel BUG"); } +NOKPROBE_SYMBOL(do_trap_break); #ifdef CONFIG_GENERIC_BUG int is_valid_bugaddr(unsigned long pc) diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 8f17519208c7..c5dbd55cbf7c 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -328,3 +328,4 @@ good_area: } return; } +NOKPROBE_SYMBOL(do_page_fault); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 4f85c6d0ddf8..937d13ce9ab8 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -216,7 +216,7 @@ void __init kasan_init(void) break; kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); - }; + } for (i = 0; i < PTRS_PER_PTE; i++) set_pte(&kasan_early_shadow_pte[i], diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index ee056f4a4fa3..2b543163d90a 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -12,6 +12,7 @@ enum stack_type { STACK_TYPE_IRQ, STACK_TYPE_NODAT, STACK_TYPE_RESTART, + STACK_TYPE_MCCK, }; struct stack_info { diff --git a/arch/s390/include/asm/vdso/data.h b/arch/s390/include/asm/vdso/data.h index 7b3cdb4a5f48..73ee89142666 100644 --- a/arch/s390/include/asm/vdso/data.h +++ b/arch/s390/include/asm/vdso/data.h @@ -6,7 +6,7 @@ #include <vdso/datapage.h> struct arch_vdso_data { - __u64 tod_steering_delta; + __s64 tod_steering_delta; __u64 tod_steering_end; }; diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c index af013b4244d3..2da027359798 100644 --- a/arch/s390/kernel/cpcmd.c +++ b/arch/s390/kernel/cpcmd.c @@ -37,10 +37,12 @@ static int diag8_noresponse(int cmdlen) static int diag8_response(int cmdlen, char *response, int *rlen) { + unsigned long _cmdlen = cmdlen | 0x40000000L; + unsigned long _rlen = *rlen; register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf; register unsigned long reg3 asm ("3") = (addr_t) response; - register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L; - register unsigned long reg5 asm ("5") = *rlen; + register unsigned long reg4 asm ("4") = _cmdlen; + register unsigned long reg5 asm ("5") = _rlen; asm volatile( " diag %2,%0,0x8\n" diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 0dc4b258b98d..db1bc00229ca 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -79,6 +79,15 @@ static bool in_nodat_stack(unsigned long sp, struct stack_info *info) return in_stack(sp, info, STACK_TYPE_NODAT, top - THREAD_SIZE, top); } +static bool in_mcck_stack(unsigned long sp, struct stack_info *info) +{ + unsigned long frame_size, top; + + frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + top = S390_lowcore.mcck_stack + frame_size; + return in_stack(sp, info, STACK_TYPE_MCCK, top - THREAD_SIZE, top); +} + static bool in_restart_stack(unsigned long sp, struct stack_info *info) { unsigned long frame_size, top; @@ -108,7 +117,8 @@ int get_stack_info(unsigned long sp, struct task_struct *task, /* Check per-cpu stacks */ if (!in_irq_stack(sp, info) && !in_nodat_stack(sp, info) && - !in_restart_stack(sp, info)) + !in_restart_stack(sp, info) && + !in_mcck_stack(sp, info)) goto unknown; recursion_check: diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index c10b9f31eef7..12de7a9c85b3 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -401,15 +401,13 @@ ENTRY(\name) brasl %r14,.Lcleanup_sie_int #endif 0: CHECK_STACK __LC_SAVE_AREA_ASYNC - lgr %r11,%r15 aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) - stg %r11,__SF_BACKCHAIN(%r15) j 2f 1: BPENTER __TI_flags(%r12),_TIF_ISOLATE_BP lctlg %c1,%c1,__LC_KERNEL_ASCE lg %r15,__LC_KERNEL_STACK - xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) -2: la %r11,STACK_FRAME_OVERHEAD(%r15) +2: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) + la %r11,STACK_FRAME_OVERHEAD(%r15) stmg %r0,%r7,__PT_R0(%r11) # clear user controlled registers to prevent speculative use xgr %r0,%r0 @@ -445,6 +443,7 @@ INT_HANDLER io_int_handler,__LC_IO_OLD_PSW,do_io_irq * Load idle PSW. */ ENTRY(psw_idle) + stg %r14,(__SF_GPRS+8*8)(%r15) stg %r3,__SF_EMPTY(%r15) larl %r1,psw_idle_exit stg %r1,__SF_EMPTY+8(%r15) diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 601c21791338..714269e10eec 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -174,7 +174,7 @@ void noinstr do_ext_irq(struct pt_regs *regs) memcpy(®s->int_code, &S390_lowcore.ext_cpu_addr, 4); regs->int_parm = S390_lowcore.ext_params; - regs->int_parm_long = *(unsigned long *)S390_lowcore.ext_params2; + regs->int_parm_long = S390_lowcore.ext_params2; from_idle = !user_mode(regs) && regs->psw.addr == (unsigned long)psw_idle_exit; if (from_idle) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 60da976eee6f..72134f9f6ff5 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -354,7 +354,7 @@ static int __init stack_realloc(void) if (!new) panic("Couldn't allocate machine check stack"); WRITE_ONCE(S390_lowcore.mcck_stack, new + STACK_INIT_OFFSET); - memblock_free(old, THREAD_SIZE); + memblock_free_late(old, THREAD_SIZE); return 0; } early_initcall(stack_realloc); diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 7f1266c24f6b..101477b3e263 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -24,12 +24,6 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, } } -/* - * This function returns an error if it detects any unreliable features of the - * stack. Otherwise it guarantees that the stack trace is reliable. - * - * If the task is not 'current', the caller *must* ensure the task is inactive. - */ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task) { diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 165da961f901..326cb8f75f58 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -80,10 +80,12 @@ void __init time_early_init(void) { struct ptff_qto qto; struct ptff_qui qui; + int cs; /* Initialize TOD steering parameters */ tod_steering_end = tod_clock_base.tod; - vdso_data->arch_data.tod_steering_end = tod_steering_end; + for (cs = 0; cs < CS_BASES; cs++) + vdso_data[cs].arch_data.tod_steering_end = tod_steering_end; if (!test_facility(28)) return; @@ -366,6 +368,7 @@ static void clock_sync_global(unsigned long delta) { unsigned long now, adj; struct ptff_qto qto; + int cs; /* Fixup the monotonic sched clock. */ tod_clock_base.eitod += delta; @@ -381,7 +384,10 @@ static void clock_sync_global(unsigned long delta) panic("TOD clock sync offset %li is too large to drift\n", tod_steering_delta); tod_steering_end = now + (abs(tod_steering_delta) << 15); - vdso_data->arch_data.tod_steering_end = tod_steering_end; + for (cs = 0; cs < CS_BASES; cs++) { + vdso_data[cs].arch_data.tod_steering_end = tod_steering_end; + vdso_data[cs].arch_data.tod_steering_delta = tod_steering_delta; + } /* Update LPAR offset. */ if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 2792879d398e..6e0b08310949 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -571,6 +571,7 @@ config X86_UV depends on X86_EXTENDED_PLATFORM depends on NUMA depends on EFI + depends on KEXEC_CORE depends on X86_X2APIC depends on PCI help @@ -777,6 +778,7 @@ if HYPERVISOR_GUEST config PARAVIRT bool "Enable paravirtualization code" + depends on HAVE_STATIC_CALL help This changes the kernel so it can modify itself when it is run under a hypervisor, potentially improving performance significantly @@ -1406,7 +1408,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 + depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6 select X86_PAE help Select this if you have a 32-bit processor and more than 4 @@ -1518,6 +1520,7 @@ config AMD_MEM_ENCRYPT select ARCH_USE_MEMREMAP_PROT select ARCH_HAS_FORCE_DMA_UNENCRYPTED select INSTRUCTION_DECODER + select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS help Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory @@ -1931,6 +1934,7 @@ config X86_SGX depends on CRYPTO_SHA256=y select SRCU select MMU_NOTIFIER + select NUMA_KEEP_MEMINFO if NUMA help Intel(R) Software Guard eXtensions (SGX) is a set of CPU instructions that can be used by applications to set aside private regions of code diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 2d6d5a28c3bf..78faf9c7e3ae 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -27,12 +27,13 @@ endif REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING \ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ - -mno-mmx -mno-sse + -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none) REALMODE_CFLAGS += -ffreestanding REALMODE_CFLAGS += -fno-stack-protector REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member) REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4)) +REALMODE_CFLAGS += $(CLANG_FLAGS) export REALMODE_CFLAGS # BITS is used as extension for files which are available in a 32 bit diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index e0bc3988c3fa..6e5522aebbbd 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -46,6 +46,7 @@ KBUILD_CFLAGS += -D__DISABLE_EXPORTS # Disable relocation relaxation in case the link is not PIE. KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mrelax-relocations=no) KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h +KBUILD_CFLAGS += $(CLANG_FLAGS) # sev-es.c indirectly inludes inat-table.h which is generated during # compilation and stored in $(objtree). Add the directory to the includes so diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S index c4bb0f9363f5..95a223b3e56a 100644 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ b/arch/x86/boot/compressed/efi_thunk_64.S @@ -5,7 +5,7 @@ * Early support for invoking 32-bit EFI services from a 64-bit kernel. * * Because this thunking occurs before ExitBootServices() we have to - * restore the firmware's 32-bit GDT before we make EFI serivce calls, + * restore the firmware's 32-bit GDT before we make EFI service calls, * since the firmware's 32-bit IDT is still currently installed and it * needs to be able to service interrupts. * diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index e94874f4bbc1..a2347ded77ea 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -34,6 +34,7 @@ #include <asm/asm-offsets.h> #include <asm/bootparam.h> #include <asm/desc_defs.h> +#include <asm/trapnr.h> #include "pgtable.h" /* @@ -107,9 +108,19 @@ SYM_FUNC_START(startup_32) movl %eax, %gs movl %eax, %ss -/* setup a stack and make sure cpu supports long mode. */ + /* Setup a stack and load CS from current GDT */ leal rva(boot_stack_end)(%ebp), %esp + pushl $__KERNEL32_CS + leal rva(1f)(%ebp), %eax + pushl %eax + lretl +1: + + /* Setup Exception handling for SEV-ES */ + call startup32_load_idt + + /* Make sure cpu supports long mode. */ call verify_cpu testl %eax, %eax jnz .Lno_longmode @@ -172,11 +183,21 @@ SYM_FUNC_START(startup_32) */ call get_sev_encryption_bit xorl %edx, %edx +#ifdef CONFIG_AMD_MEM_ENCRYPT testl %eax, %eax jz 1f subl $32, %eax /* Encryption bit is always above bit 31 */ bts %eax, %edx /* Set encryption mask for page tables */ + /* + * Mark SEV as active in sev_status so that startup32_check_sev_cbit() + * will do a check. The sev_status memory will be fully initialized + * with the contents of MSR_AMD_SEV_STATUS later in + * set_sev_encryption_mask(). For now it is sufficient to know that SEV + * is active. + */ + movl $1, rva(sev_status)(%ebp) 1: +#endif /* Initialize Page tables to 0 */ leal rva(pgtable)(%ebx), %edi @@ -231,7 +252,7 @@ SYM_FUNC_START(startup_32) /* * Setup for the jump to 64bit mode * - * When the jump is performend we will be in long mode but + * When the jump is performed we will be in long mode but * in 32bit compatibility mode with EFER.LME = 1, CS.L = 0, CS.D = 1 * (and in turn EFER.LMA = 1). To jump into 64bit mode we use * the new gdt/idt that has __KERNEL_CS with CS.L = 1. @@ -261,6 +282,9 @@ SYM_FUNC_START(startup_32) movl %esi, %edx 1: #endif + /* Check if the C-bit position is correct when SEV is active */ + call startup32_check_sev_cbit + pushl $__KERNEL_CS pushl %eax @@ -694,6 +718,19 @@ SYM_DATA_START(boot_idt) .endr SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end) +#ifdef CONFIG_AMD_MEM_ENCRYPT +SYM_DATA_START(boot32_idt_desc) + .word boot32_idt_end - boot32_idt - 1 + .long 0 +SYM_DATA_END(boot32_idt_desc) + .balign 8 +SYM_DATA_START(boot32_idt) + .rept 32 + .quad 0 + .endr +SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLOBAL, boot32_idt_end) +#endif + #ifdef CONFIG_EFI_STUB SYM_DATA(image_offset, .long 0) #endif @@ -786,6 +823,137 @@ SYM_DATA_START_LOCAL(loaded_image_proto) SYM_DATA_END(loaded_image_proto) #endif +#ifdef CONFIG_AMD_MEM_ENCRYPT + __HEAD + .code32 +/* + * Write an IDT entry into boot32_idt + * + * Parameters: + * + * %eax: Handler address + * %edx: Vector number + * + * Physical offset is expected in %ebp + */ +SYM_FUNC_START(startup32_set_idt_entry) + push %ebx + push %ecx + + /* IDT entry address to %ebx */ + leal rva(boot32_idt)(%ebp), %ebx + shl $3, %edx + addl %edx, %ebx + + /* Build IDT entry, lower 4 bytes */ + movl %eax, %edx + andl $0x0000ffff, %edx # Target code segment offset [15:0] + movl $__KERNEL32_CS, %ecx # Target code segment selector + shl $16, %ecx + orl %ecx, %edx + + /* Store lower 4 bytes to IDT */ + movl %edx, (%ebx) + + /* Build IDT entry, upper 4 bytes */ + movl %eax, %edx + andl $0xffff0000, %edx # Target code segment offset [31:16] + orl $0x00008e00, %edx # Present, Type 32-bit Interrupt Gate + + /* Store upper 4 bytes to IDT */ + movl %edx, 4(%ebx) + + pop %ecx + pop %ebx + ret +SYM_FUNC_END(startup32_set_idt_entry) +#endif + +SYM_FUNC_START(startup32_load_idt) +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* #VC handler */ + leal rva(startup32_vc_handler)(%ebp), %eax + movl $X86_TRAP_VC, %edx + call startup32_set_idt_entry + + /* Load IDT */ + leal rva(boot32_idt)(%ebp), %eax + movl %eax, rva(boot32_idt_desc+2)(%ebp) + lidt rva(boot32_idt_desc)(%ebp) +#endif + ret +SYM_FUNC_END(startup32_load_idt) + +/* + * Check for the correct C-bit position when the startup_32 boot-path is used. + * + * The check makes use of the fact that all memory is encrypted when paging is + * disabled. The function creates 64 bits of random data using the RDRAND + * instruction. RDRAND is mandatory for SEV guests, so always available. If the + * hypervisor violates that the kernel will crash right here. + * + * The 64 bits of random data are stored to a memory location and at the same + * time kept in the %eax and %ebx registers. Since encryption is always active + * when paging is off the random data will be stored encrypted in main memory. + * + * Then paging is enabled. When the C-bit position is correct all memory is + * still mapped encrypted and comparing the register values with memory will + * succeed. An incorrect C-bit position will map all memory unencrypted, so that + * the compare will use the encrypted random data and fail. + */ +SYM_FUNC_START(startup32_check_sev_cbit) +#ifdef CONFIG_AMD_MEM_ENCRYPT + pushl %eax + pushl %ebx + pushl %ecx + pushl %edx + + /* Check for non-zero sev_status */ + movl rva(sev_status)(%ebp), %eax + testl %eax, %eax + jz 4f + + /* + * Get two 32-bit random values - Don't bail out if RDRAND fails + * because it is better to prevent forward progress if no random value + * can be gathered. + */ +1: rdrand %eax + jnc 1b +2: rdrand %ebx + jnc 2b + + /* Store to memory and keep it in the registers */ + movl %eax, rva(sev_check_data)(%ebp) + movl %ebx, rva(sev_check_data+4)(%ebp) + + /* Enable paging to see if encryption is active */ + movl %cr0, %edx /* Backup %cr0 in %edx */ + movl $(X86_CR0_PG | X86_CR0_PE), %ecx /* Enable Paging and Protected mode */ + movl %ecx, %cr0 + + cmpl %eax, rva(sev_check_data)(%ebp) + jne 3f + cmpl %ebx, rva(sev_check_data+4)(%ebp) + jne 3f + + movl %edx, %cr0 /* Restore previous %cr0 */ + + jmp 4f + +3: /* Check failed - hlt the machine */ + hlt + jmp 3b + +4: + popl %edx + popl %ecx + popl %ebx + popl %eax +#endif + ret +SYM_FUNC_END(startup32_check_sev_cbit) + /* * Stack and heap for uncompression */ diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 804a502ee0d2..9b93567d663a 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -52,3 +52,17 @@ void load_stage2_idt(void) load_boot_idt(&boot_idt_desc); } + +void cleanup_exception_handling(void) +{ + /* + * Flush GHCB from cache and map it encrypted again when running as + * SEV-ES guest. + */ + sev_es_shutdown_ghcb(); + + /* Set a null-idt, disabling #PF and #VC handling */ + boot_idt_desc.size = 0; + boot_idt_desc.address = 0; + load_boot_idt(&boot_idt_desc); +} diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index b92fffbe761f..e36690778497 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -639,9 +639,9 @@ static bool process_mem_region(struct mem_vector *region, if (slot_area_index == MAX_SLOT_AREA) { debug_putstr("Aborted e820/efi memmap scan (slot_areas full)!\n"); - return 1; + return true; } - return 0; + return false; } #if defined(CONFIG_MEMORY_HOTREMOVE) && defined(CONFIG_ACPI) diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index aa561795efd1..c1e81a848b2a 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -23,12 +23,6 @@ SYM_FUNC_START(get_sev_encryption_bit) push %ecx push %edx - /* Check if running under a hypervisor */ - movl $1, %eax - cpuid - bt $31, %ecx /* Check the hypervisor bit */ - jnc .Lno_sev - movl $0x80000000, %eax /* CPUID to check the highest leaf */ cpuid cmpl $0x8000001f, %eax /* See if 0x8000001f is available */ @@ -67,10 +61,132 @@ SYM_FUNC_START(get_sev_encryption_bit) ret SYM_FUNC_END(get_sev_encryption_bit) +/** + * sev_es_req_cpuid - Request a CPUID value from the Hypervisor using + * the GHCB MSR protocol + * + * @%eax: Register to request (0=EAX, 1=EBX, 2=ECX, 3=EDX) + * @%edx: CPUID Function + * + * Returns 0 in %eax on success, non-zero on failure + * %edx returns CPUID value on success + */ +SYM_CODE_START_LOCAL(sev_es_req_cpuid) + shll $30, %eax + orl $0x00000004, %eax + movl $MSR_AMD64_SEV_ES_GHCB, %ecx + wrmsr + rep; vmmcall # VMGEXIT + rdmsr + + /* Check response */ + movl %eax, %ecx + andl $0x3ffff000, %ecx # Bits [12-29] MBZ + jnz 2f + + /* Check return code */ + andl $0xfff, %eax + cmpl $5, %eax + jne 2f + + /* All good - return success */ + xorl %eax, %eax +1: + ret +2: + movl $-1, %eax + jmp 1b +SYM_CODE_END(sev_es_req_cpuid) + +SYM_CODE_START(startup32_vc_handler) + pushl %eax + pushl %ebx + pushl %ecx + pushl %edx + + /* Keep CPUID function in %ebx */ + movl %eax, %ebx + + /* Check if error-code == SVM_EXIT_CPUID */ + cmpl $0x72, 16(%esp) + jne .Lfail + + movl $0, %eax # Request CPUID[fn].EAX + movl %ebx, %edx # CPUID fn + call sev_es_req_cpuid # Call helper + testl %eax, %eax # Check return code + jnz .Lfail + movl %edx, 12(%esp) # Store result + + movl $1, %eax # Request CPUID[fn].EBX + movl %ebx, %edx # CPUID fn + call sev_es_req_cpuid # Call helper + testl %eax, %eax # Check return code + jnz .Lfail + movl %edx, 8(%esp) # Store result + + movl $2, %eax # Request CPUID[fn].ECX + movl %ebx, %edx # CPUID fn + call sev_es_req_cpuid # Call helper + testl %eax, %eax # Check return code + jnz .Lfail + movl %edx, 4(%esp) # Store result + + movl $3, %eax # Request CPUID[fn].EDX + movl %ebx, %edx # CPUID fn + call sev_es_req_cpuid # Call helper + testl %eax, %eax # Check return code + jnz .Lfail + movl %edx, 0(%esp) # Store result + + /* + * Sanity check CPUID results from the Hypervisor. See comment in + * do_vc_no_ghcb() for more details on why this is necessary. + */ + + /* Fail if SEV leaf not available in CPUID[0x80000000].EAX */ + cmpl $0x80000000, %ebx + jne .Lcheck_sev + cmpl $0x8000001f, 12(%esp) + jb .Lfail + jmp .Ldone + +.Lcheck_sev: + /* Fail if SEV bit not set in CPUID[0x8000001f].EAX[1] */ + cmpl $0x8000001f, %ebx + jne .Ldone + btl $1, 12(%esp) + jnc .Lfail + +.Ldone: + popl %edx + popl %ecx + popl %ebx + popl %eax + + /* Remove error code */ + addl $4, %esp + + /* Jump over CPUID instruction */ + addl $2, (%esp) + + iret +.Lfail: + /* Send terminate request to Hypervisor */ + movl $0x100, %eax + xorl %edx, %edx + movl $MSR_AMD64_SEV_ES_GHCB, %ecx + wrmsr + rep; vmmcall + + /* If request fails, go to hlt loop */ + hlt + jmp .Lfail +SYM_CODE_END(startup32_vc_handler) + .code64 #include "../../kernel/sev_verify_cbit.S" - SYM_FUNC_START(set_sev_encryption_mask) #ifdef CONFIG_AMD_MEM_ENCRYPT push %rbp diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 267e7f93050e..dde042f64cca 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -430,8 +430,6 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, error("Destination address too large"); #endif #ifndef CONFIG_RELOCATABLE - if ((unsigned long)output != LOAD_PHYSICAL_ADDR) - error("Destination address does not match LOAD_PHYSICAL_ADDR"); if (virt_addr != LOAD_PHYSICAL_ADDR) error("Destination virtual address changed when not relocatable"); #endif @@ -443,11 +441,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap, handle_relocations(output, output_len, virt_addr); debug_putstr("done.\nBooting the kernel.\n"); - /* - * Flush GHCB from cache and map it encrypted again when running as - * SEV-ES guest. - */ - sev_es_shutdown_ghcb(); + /* Disable exception handling before booting the kernel */ + cleanup_exception_handling(); return output; } diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 901ea5ebec22..e5612f035498 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -155,6 +155,12 @@ extern pteval_t __default_kernel_pte_mask; extern gate_desc boot_idt[BOOT_IDT_ENTRIES]; extern struct desc_ptr boot_idt_desc; +#ifdef CONFIG_X86_64 +void cleanup_exception_handling(void); +#else +static inline void cleanup_exception_handling(void) { } +#endif + /* IDT Entry Points */ void boot_page_fault(void); void boot_stage1_vc(void); diff --git a/arch/x86/boot/compressed/sev-es.c b/arch/x86/boot/compressed/sev-es.c index 27826c265aab..d904bd56b3e3 100644 --- a/arch/x86/boot/compressed/sev-es.c +++ b/arch/x86/boot/compressed/sev-es.c @@ -200,14 +200,8 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) } finish: - if (result == ES_OK) { + if (result == ES_OK) vc_finish_insn(&ctxt); - } else if (result != ES_RETRY) { - /* - * For now, just halt the machine. That makes debugging easier, - * later we just call sev_es_terminate() here. - */ - while (true) - asm volatile("hlt\n"); - } + else if (result != ES_RETRY) + sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); } diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c index 7c4c7b2fbf05..98cf3b4e4c9f 100644 --- a/arch/x86/crypto/crc32-pclmul_glue.c +++ b/arch/x86/crypto/crc32-pclmul_glue.c @@ -24,7 +24,7 @@ /* * Copyright 2012 Xyratex Technology Limited * - * Wrappers for kernel crypto shash api to pclmulqdq crc32 imlementation. + * Wrappers for kernel crypto shash api to pclmulqdq crc32 implementation. */ #include <linux/init.h> #include <linux/module.h> diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c index 5af8021b98ce..6706b6cb1d0f 100644 --- a/arch/x86/crypto/curve25519-x86_64.c +++ b/arch/x86/crypto/curve25519-x86_64.c @@ -114,11 +114,11 @@ static inline void fadd(u64 *out, const u64 *f1, const u64 *f2) ); } -/* Computes the field substraction of two field elements */ +/* Computes the field subtraction of two field elements */ static inline void fsub(u64 *out, const u64 *f1, const u64 *f2) { asm volatile( - /* Compute the raw substraction of f1-f2 */ + /* Compute the raw subtraction of f1-f2 */ " movq 0(%1), %%r8;" " subq 0(%2), %%r8;" " movq 8(%1), %%r9;" @@ -135,7 +135,7 @@ static inline void fsub(u64 *out, const u64 *f1, const u64 *f2) " mov $38, %%rcx;" " cmovc %%rcx, %%rax;" - /* Step 2: Substract carry*38 from the original difference */ + /* Step 2: Subtract carry*38 from the original difference */ " sub %%rax, %%r8;" " sbb $0, %%r9;" " sbb $0, %%r10;" diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c index 646da46e8d10..1dfb8af48a3c 100644 --- a/arch/x86/crypto/poly1305_glue.c +++ b/arch/x86/crypto/poly1305_glue.c @@ -16,7 +16,7 @@ #include <asm/simd.h> asmlinkage void poly1305_init_x86_64(void *ctx, - const u8 key[POLY1305_KEY_SIZE]); + const u8 key[POLY1305_BLOCK_SIZE]); asmlinkage void poly1305_blocks_x86_64(void *ctx, const u8 *inp, const size_t len, const u32 padbit); asmlinkage void poly1305_emit_x86_64(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], @@ -81,7 +81,7 @@ static void convert_to_base2_64(void *ctx) state->is_base2_26 = 0; } -static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_KEY_SIZE]) +static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_BLOCK_SIZE]) { poly1305_init_x86_64(ctx, key); } @@ -129,7 +129,7 @@ static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE], poly1305_emit_avx(ctx, mac, nonce); } -void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 *key) +void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE]) { poly1305_simd_init(&dctx->h, key); dctx->s[0] = get_unaligned_le32(&key[16]); diff --git a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S index fc23552afe37..bca4cea757ce 100644 --- a/arch/x86/crypto/twofish-x86_64-asm_64-3way.S +++ b/arch/x86/crypto/twofish-x86_64-asm_64-3way.S @@ -88,7 +88,7 @@ /* * Combined G1 & G2 function. Reordered with help of rotates to have moves - * at begining. + * at beginning. */ #define g1g2_3(ab, cd, Tx0, Tx1, Tx2, Tx3, Ty0, Ty1, Ty2, Ty3, x, y) \ /* G1,1 && G2,1 */ \ diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c index 03725696397c..3507cf2064f1 100644 --- a/arch/x86/crypto/twofish_glue_3way.c +++ b/arch/x86/crypto/twofish_glue_3way.c @@ -117,7 +117,7 @@ static bool is_blacklisted_cpu(void) * storing blocks in 64bit registers to allow three blocks to * be processed parallel. Parallel operation then allows gaining * more performance than was trade off, on out-of-order CPUs. - * However Atom does not benefit from this parallellism and + * However Atom does not benefit from this parallelism and * should be blacklisted. */ return true; diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index df8c017e6161..ff0034740900 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -40,7 +40,7 @@ #include <asm/processor-flags.h> #include <asm/irq_vectors.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/asm.h> #include <asm/smap.h> #include <asm/frame.h> @@ -209,7 +209,7 @@ * * Lets build a 5 entry IRET frame after that, such that struct pt_regs * is complete and in particular regs->sp is correct. This gives us - * the original 6 enties as gap: + * the original 6 entries as gap: * * 14*4(%esp) - <previous context> * 13*4(%esp) - gap / flags @@ -430,7 +430,7 @@ * will soon execute iret and the tracer was already set to * the irqstate after the IRET: */ - DISABLE_INTERRUPTS(CLBR_ANY) + cli lss (%esp), %esp /* switch to espfix segment */ .Lend_\@: #endif /* CONFIG_X86_ESPFIX32 */ @@ -1077,7 +1077,7 @@ restore_all_switch_stack: * when returning from IPI handler and when returning from * scheduler to user-space. */ - INTERRUPT_RETURN + iret .section .fixup, "ax" SYM_CODE_START(asm_iret_error) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 400908dff42e..a16a5294d55f 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -305,7 +305,7 @@ SYM_CODE_END(ret_from_fork) .macro DEBUG_ENTRY_ASSERT_IRQS_OFF #ifdef CONFIG_DEBUG_ENTRY pushq %rax - SAVE_FLAGS(CLBR_RAX) + SAVE_FLAGS testl $X86_EFLAGS_IF, %eax jz .Lokay_\@ ud2 @@ -511,7 +511,7 @@ SYM_CODE_START(\asmsym) /* * No need to switch back to the IST stack. The current stack is either * identical to the stack in the IRET frame or the VC fall-back stack, - * so it is definitly mapped even with PTI enabled. + * so it is definitely mapped even with PTI enabled. */ jmp paranoid_exit diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 2d0f3d8bcc25..edfe9780f6d1 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -218,7 +218,7 @@ int main(int argc, char **argv) /* * Figure out the struct name. If we're writing to a .so file, - * generate raw output insted. + * generate raw output instead. */ name = strdup(argv[3]); namelen = strlen(name); diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S index de1fff7188aa..6ddd7a937b3e 100644 --- a/arch/x86/entry/vdso/vdso32/system_call.S +++ b/arch/x86/entry/vdso/vdso32/system_call.S @@ -6,7 +6,7 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> .text .globl __kernel_vsyscall @@ -29,7 +29,7 @@ __kernel_vsyscall: * anyone with an AMD CPU, for example). Nonetheless, we try to keep * it working approximately as well as it ever worked. * - * This link may eludicate some of the history: + * This link may elucidate some of the history: * https://android-review.googlesource.com/#/q/Iac3295376d61ef83e713ac9b528f3b50aa780cd7 * personally, I find it hard to understand what's going on there. * diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 825e829ffff1..235a5794296a 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -358,7 +358,7 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr) mmap_write_lock(mm); /* * Check if we have already mapped vdso blob - fail to prevent - * abusing from userspace install_speciall_mapping, which may + * abusing from userspace install_special_mapping, which may * not do accounting and rlimit right. * We could search vma near context.vdso, but it's a slowpath, * so let's explicitly check all VMAs to be completely sure. diff --git a/arch/x86/entry/vdso/vsgx.S b/arch/x86/entry/vdso/vsgx.S index 86a0e94f68df..99dafac992e2 100644 --- a/arch/x86/entry/vdso/vsgx.S +++ b/arch/x86/entry/vdso/vsgx.S @@ -137,7 +137,7 @@ SYM_FUNC_START(__vdso_sgx_enter_enclave) /* * If the return from callback is zero or negative, return immediately, - * else re-execute ENCLU with the postive return value interpreted as + * else re-execute ENCLU with the positive return value interpreted as * the requested ENCLU function. */ cmp $0, %eax diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index 2c1791c4a518..9687a8aef01c 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -623,7 +623,7 @@ static void amd_pmu_disable_all(void) /* * Check each counter for overflow and wait for it to be reset by the * NMI if it has overflowed. This relies on the fact that all active - * counters are always enabled when this function is caled and + * counters are always enabled when this function is called and * ARCH_PERFMON_EVENTSEL_INT is always set. */ for (idx = 0; idx < x86_pmu.num_counters; idx++) { diff --git a/arch/x86/events/amd/iommu.h b/arch/x86/events/amd/iommu.h index 0e5c036fd7be..e6493a67f1c6 100644 --- a/arch/x86/events/amd/iommu.h +++ b/arch/x86/events/amd/iommu.h @@ -17,7 +17,7 @@ #define IOMMU_PC_DEVID_MATCH_REG 0x20 #define IOMMU_PC_COUNTER_REPORT_REG 0x28 -/* maximun specified bank/counters */ +/* maximum specified bank/counters */ #define PC_MAX_SPEC_BNKS 64 #define PC_MAX_SPEC_CNTRS 16 diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 18df17129695..4c31cae4707e 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -765,7 +765,7 @@ struct perf_sched { }; /* - * Initialize interator that runs through all events and counters. + * Initialize iterator that runs through all events and counters. */ static void perf_sched_init(struct perf_sched *sched, struct event_constraint **constraints, int num, int wmin, int wmax, int gpmax) diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c index 731dd8d0dbb1..6320d2cfd9d3 100644 --- a/arch/x86/events/intel/bts.c +++ b/arch/x86/events/intel/bts.c @@ -594,7 +594,7 @@ static __init int bts_init(void) * we cannot use the user mapping since it will not be available * if we're not running the owning process. * - * With PTI we can't use the kernal map either, because its not + * With PTI we can't use the kernel map either, because its not * there when we run userspace. * * For now, disable this driver when using PTI. diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 37ce38403cb8..3fd69bd5fa6e 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -137,7 +137,7 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */ + INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMPTY */ INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */ INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_LDM_PENDING */ INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */ @@ -2186,7 +2186,7 @@ static void intel_pmu_enable_all(int added) * magic three (non-counting) events 0x4300B5, 0x4300D2, and 0x4300B1 either * in sequence on the same PMC or on different PMCs. * - * In practise it appears some of these events do in fact count, and + * In practice it appears some of these events do in fact count, and * we need to program all 4 events. */ static void intel_pmu_nhm_workaround(void) @@ -2435,7 +2435,7 @@ static inline u64 icl_get_metrics_event_value(u64 metric, u64 slots, int idx) /* * The metric is reported as an 8bit integer fraction - * suming up to 0xff. + * summing up to 0xff. * slots-in-metric = (Metric / 0xff) * slots */ val = (metric >> ((idx - INTEL_PMC_IDX_METRIC_BASE) * 8)) & 0xff; @@ -2776,7 +2776,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) * processing loop coming after that the function, otherwise * phony regular samples may be generated in the sampling buffer * not marked with the EXACT tag. Another possibility is to have - * one PEBS event and at least one non-PEBS event whic hoverflows + * one PEBS event and at least one non-PEBS event which overflows * while PEBS has armed. In this case, bit 62 of GLOBAL_STATUS will * not be set, yet the overflow status bit for the PEBS counter will * be on Skylake. @@ -2824,7 +2824,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) } /* - * Intel Perf mertrics + * Intel Perf metrics */ if (__test_and_clear_bit(GLOBAL_STATUS_PERF_METRICS_OVF_BIT, (unsigned long *)&status)) { handled++; @@ -4516,7 +4516,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = { INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 3, 0x07000009), INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 4, 0x0f000009), INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_D, 5, 0x0e000002), - INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 2, 0x0b000014), + INTEL_CPU_DESC(INTEL_FAM6_BROADWELL_X, 1, 0x0b000014), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 3, 0x00000021), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 4, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000), @@ -4594,7 +4594,7 @@ static bool check_msr(unsigned long msr, u64 mask) /* * Disable the check for real HW, so we don't - * mess with potentionaly enabled registers: + * mess with potentially enabled registers: */ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return true; @@ -4659,7 +4659,7 @@ static __init void intel_arch_events_quirk(void) { int bit; - /* disable event that reported as not presend by cpuid */ + /* disable event that reported as not present by cpuid */ for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(intel_arch_events_map)) { intel_perfmon_event_map[intel_arch_events_map[bit].id] = 0; pr_warn("CPUID marked event: \'%s\' unavailable\n", diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index d32b302719fe..5aabb0e2964a 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1805,7 +1805,7 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) * * [-period, 0] * - * the difference between two consequtive reads is: + * the difference between two consecutive reads is: * * A) value2 - value1; * when no overflows have happened in between, diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 21890dacfcfe..acb04ef3da3f 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1198,7 +1198,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort) /* * The LBR logs any address in the IP, even if the IP just * faulted. This means userspace can control the from address. - * Ensure we don't blindy read any address by validating it is + * Ensure we don't blindly read any address by validating it is * a known text address. */ if (kernel_text_address(from)) { diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c index a4cc66005ce8..971dffe0b77d 100644 --- a/arch/x86/events/intel/p4.c +++ b/arch/x86/events/intel/p4.c @@ -24,7 +24,7 @@ struct p4_event_bind { unsigned int escr_msr[2]; /* ESCR MSR for this event */ unsigned int escr_emask; /* valid ESCR EventMask bits */ unsigned int shared; /* event is shared across threads */ - char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on abscence */ + char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on absence */ }; struct p4_pebs_bind { @@ -45,7 +45,7 @@ struct p4_pebs_bind { * it's needed for mapping P4_PEBS_CONFIG_METRIC_MASK bits of * event configuration to find out which values are to be * written into MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT - * resgisters + * registers */ static struct p4_pebs_bind p4_pebs_bind_map[] = { P4_GEN_PEBS_BIND(1stl_cache_load_miss_retired, 0x0000001, 0x0000001), @@ -1313,7 +1313,7 @@ static __initconst const struct x86_pmu p4_pmu = { .get_event_constraints = x86_get_event_constraints, /* * IF HT disabled we may need to use all - * ARCH_P4_MAX_CCCR counters simulaneously + * ARCH_P4_MAX_CCCR counters simultaneously * though leave it restricted at moment assuming * HT is on */ diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index e94af4a54d0d..915847655c06 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -362,7 +362,7 @@ static bool pt_event_valid(struct perf_event *event) /* * Setting bit 0 (TraceEn in RTIT_CTL MSR) in the attr.config - * clears the assomption that BranchEn must always be enabled, + * clears the assumption that BranchEn must always be enabled, * as was the case with the first implementation of PT. * If this bit is not set, the legacy behavior is preserved * for compatibility with the older userspace. diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index b79951d0707c..4bba0491068c 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -280,17 +280,17 @@ * | [63] | 00h | VALID - When set, indicates the CPU bus * numbers have been initialized. (RO) * |[62:48]| --- | Reserved - * |[47:40]| 00h | BUS_NUM_5 — Return the bus number BIOS assigned + * |[47:40]| 00h | BUS_NUM_5 - Return the bus number BIOS assigned * CPUBUSNO(5). (RO) - * |[39:32]| 00h | BUS_NUM_4 — Return the bus number BIOS assigned + * |[39:32]| 00h | BUS_NUM_4 - Return the bus number BIOS assigned * CPUBUSNO(4). (RO) - * |[31:24]| 00h | BUS_NUM_3 — Return the bus number BIOS assigned + * |[31:24]| 00h | BUS_NUM_3 - Return the bus number BIOS assigned * CPUBUSNO(3). (RO) - * |[23:16]| 00h | BUS_NUM_2 — Return the bus number BIOS assigned + * |[23:16]| 00h | BUS_NUM_2 - Return the bus number BIOS assigned * CPUBUSNO(2). (RO) - * |[15:8] | 00h | BUS_NUM_1 — Return the bus number BIOS assigned + * |[15:8] | 00h | BUS_NUM_1 - Return the bus number BIOS assigned * CPUBUSNO(1). (RO) - * | [7:0] | 00h | BUS_NUM_0 — Return the bus number BIOS assigned + * | [7:0] | 00h | BUS_NUM_0 - Return the bus number BIOS assigned * CPUBUSNO(0). (RO) */ #define SKX_MSR_CPU_BUS_NUMBER 0x300 @@ -1159,7 +1159,6 @@ enum { SNBEP_PCI_QPI_PORT0_FILTER, SNBEP_PCI_QPI_PORT1_FILTER, BDX_PCI_QPI_PORT2_FILTER, - HSWEP_PCI_PCU_3, }; static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) @@ -2857,22 +2856,33 @@ static struct intel_uncore_type *hswep_msr_uncores[] = { NULL, }; -void hswep_uncore_cpu_init(void) +#define HSWEP_PCU_DID 0x2fc0 +#define HSWEP_PCU_CAPID4_OFFET 0x94 +#define hswep_get_chop(_cap) (((_cap) >> 6) & 0x3) + +static bool hswep_has_limit_sbox(unsigned int device) { - int pkg = boot_cpu_data.logical_proc_id; + struct pci_dev *dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, NULL); + u32 capid4; + + if (!dev) + return false; + + pci_read_config_dword(dev, HSWEP_PCU_CAPID4_OFFET, &capid4); + if (!hswep_get_chop(capid4)) + return true; + return false; +} + +void hswep_uncore_cpu_init(void) +{ if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; /* Detect 6-8 core systems with only two SBOXes */ - if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) { - u32 capid4; - - pci_read_config_dword(uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3], - 0x94, &capid4); - if (((capid4 >> 6) & 0x3) == 0) - hswep_uncore_sbox.num_boxes = 2; - } + if (hswep_has_limit_sbox(HSWEP_PCU_DID)) + hswep_uncore_sbox.num_boxes = 2; uncore_msr_uncores = hswep_msr_uncores; } @@ -3135,11 +3145,6 @@ static const struct pci_device_id hswep_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, SNBEP_PCI_QPI_PORT1_FILTER), }, - { /* PCU.3 (for Capability registers) */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - HSWEP_PCI_PCU_3), - }, { /* end: all zeroes */ } }; @@ -3231,27 +3236,18 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = { EVENT_CONSTRAINT_END }; +#define BDX_PCU_DID 0x6fc0 + void bdx_uncore_cpu_init(void) { - int pkg = topology_phys_to_logical_pkg(boot_cpu_data.phys_proc_id); - if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; uncore_msr_uncores = bdx_msr_uncores; - /* BDX-DE doesn't have SBOX */ - if (boot_cpu_data.x86_model == 86) { - uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; /* Detect systems with no SBOXes */ - } else if (uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]) { - struct pci_dev *pdev; - u32 capid4; - - pdev = uncore_extra_pci_dev[pkg].dev[HSWEP_PCI_PCU_3]; - pci_read_config_dword(pdev, 0x94, &capid4); - if (((capid4 >> 6) & 0x3) == 0) - bdx_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; - } + if ((boot_cpu_data.x86_model == 86) || hswep_has_limit_sbox(BDX_PCU_DID)) + uncore_msr_uncores[BDX_MSR_UNCORE_SBOX] = NULL; + hswep_uncore_pcu.constraints = bdx_uncore_pcu_constraints; } @@ -3472,11 +3468,6 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, BDX_PCI_QPI_PORT2_FILTER), }, - { /* PCU.3 (for Capability registers) */ - PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fc0), - .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, - HSWEP_PCI_PCU_3), - }, { /* end: all zeroes */ } }; diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c index e68827e604ad..949d845c922b 100644 --- a/arch/x86/events/zhaoxin/core.c +++ b/arch/x86/events/zhaoxin/core.c @@ -494,7 +494,7 @@ static __init void zhaoxin_arch_events_quirk(void) { int bit; - /* disable event that reported as not presend by cpuid */ + /* disable event that reported as not present by cpuid */ for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(zx_arch_events_map)) { zx_pmon_event_map[zx_arch_events_map[bit].id] = 0; pr_warn("CPUID marked event: \'%s\' unavailable\n", diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index b81047dec1da..e7b94f636cc1 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -162,7 +162,7 @@ EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation); static inline bool hv_reenlightenment_available(void) { /* - * Check for required features and priviliges to make TSC frequency + * Check for required features and privileges to make TSC frequency * change notifications work. */ return ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS && @@ -292,7 +292,7 @@ static int hv_suspend(void) /* * Reset the hypercall page as it is going to be invalidated - * accross hibernation. Setting hv_hypercall_pg to NULL ensures + * across hibernation. Setting hv_hypercall_pg to NULL ensures * that any subsequent hypercall operation fails safely instead of * crashing due to an access of an invalid page. The hypercall page * pointer is restored on resume. diff --git a/arch/x86/include/asm/agp.h b/arch/x86/include/asm/agp.h index 62da760d6d5a..cd7b14322035 100644 --- a/arch/x86/include/asm/agp.h +++ b/arch/x86/include/asm/agp.h @@ -9,7 +9,7 @@ * Functions to keep the agpgart mappings coherent with the MMU. The * GART gives the CPU a physical alias of pages in memory. The alias * region is mapped uncacheable. Make sure there are no conflicting - * mappings with different cachability attributes for the same + * mappings with different cacheability attributes for the same * page. This avoids data corruption on some CPUs. */ diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h deleted file mode 100644 index 464034db299f..000000000000 --- a/arch/x86/include/asm/alternative-asm.h +++ /dev/null @@ -1,114 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_ALTERNATIVE_ASM_H -#define _ASM_X86_ALTERNATIVE_ASM_H - -#ifdef __ASSEMBLY__ - -#include <asm/asm.h> - -#ifdef CONFIG_SMP - .macro LOCK_PREFIX -672: lock - .pushsection .smp_locks,"a" - .balign 4 - .long 672b - . - .popsection - .endm -#else - .macro LOCK_PREFIX - .endm -#endif - -/* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -.macro ANNOTATE_IGNORE_ALTERNATIVE - .Lannotate_\@: - .pushsection .discard.ignore_alts - .long .Lannotate_\@ - . - .popsection -.endm - -/* - * Issue one struct alt_instr descriptor entry (need to put it into - * the section .altinstructions, see below). This entry contains - * enough information for the alternatives patching code to patch an - * instruction. See apply_alternatives(). - */ -.macro altinstruction_entry orig alt feature orig_len alt_len pad_len - .long \orig - . - .long \alt - . - .word \feature - .byte \orig_len - .byte \alt_len - .byte \pad_len -.endm - -/* - * Define an alternative between two instructions. If @feature is - * present, early code in apply_alternatives() replaces @oldinstr with - * @newinstr. ".skip" directive takes care of proper instruction padding - * in case @newinstr is longer than @oldinstr. - */ -.macro ALTERNATIVE oldinstr, newinstr, feature -140: - \oldinstr -141: - .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90 -142: - - .pushsection .altinstructions,"a" - altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b - .popsection - - .pushsection .altinstr_replacement,"ax" -143: - \newinstr -144: - .popsection -.endm - -#define old_len 141b-140b -#define new_len1 144f-143f -#define new_len2 145f-144f - -/* - * gas compatible max based on the idea from: - * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax - * - * The additional "-" is needed because gas uses a "true" value of -1. - */ -#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) - - -/* - * Same as ALTERNATIVE macro above but for two alternatives. If CPU - * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has - * @feature2, it replaces @oldinstr with @feature2. - */ -.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2 -140: - \oldinstr -141: - .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \ - (alt_max_short(new_len1, new_len2) - (old_len)),0x90 -142: - - .pushsection .altinstructions,"a" - altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b - altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b - .popsection - - .pushsection .altinstr_replacement,"ax" -143: - \newinstr1 -144: - \newinstr2 -145: - .popsection -.endm - -#endif /* __ASSEMBLY__ */ - -#endif /* _ASM_X86_ALTERNATIVE_ASM_H */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 13adca37c99a..17b36090d448 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -2,13 +2,17 @@ #ifndef _ASM_X86_ALTERNATIVE_H #define _ASM_X86_ALTERNATIVE_H -#ifndef __ASSEMBLY__ - #include <linux/types.h> -#include <linux/stddef.h> #include <linux/stringify.h> #include <asm/asm.h> +#define ALTINSTR_FLAG_INV (1 << 15) +#define ALT_NOT(feat) ((feat) | ALTINSTR_FLAG_INV) + +#ifndef __ASSEMBLY__ + +#include <linux/stddef.h> + /* * Alternative inline assembly for SMP. * @@ -150,7 +154,7 @@ static inline int alternatives_text_reserved(void *start, void *end) " .byte " alt_rlen(num) "\n" /* replacement len */ \ " .byte " alt_pad_len "\n" /* pad len */ -#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \ +#define ALTINSTR_REPLACEMENT(newinstr, num) /* replacement */ \ "# ALT: replacement " #num "\n" \ b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n" @@ -161,7 +165,7 @@ static inline int alternatives_text_reserved(void *start, void *end) ALTINSTR_ENTRY(feature, 1) \ ".popsection\n" \ ".pushsection .altinstr_replacement, \"ax\"\n" \ - ALTINSTR_REPLACEMENT(newinstr, feature, 1) \ + ALTINSTR_REPLACEMENT(newinstr, 1) \ ".popsection\n" #define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\ @@ -171,10 +175,15 @@ static inline int alternatives_text_reserved(void *start, void *end) ALTINSTR_ENTRY(feature2, 2) \ ".popsection\n" \ ".pushsection .altinstr_replacement, \"ax\"\n" \ - ALTINSTR_REPLACEMENT(newinstr1, feature1, 1) \ - ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ + ALTINSTR_REPLACEMENT(newinstr1, 1) \ + ALTINSTR_REPLACEMENT(newinstr2, 2) \ ".popsection\n" +/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ +#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \ + ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \ + newinstr_yes, feature) + #define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \ OLDINSTR_3(oldinsn, 1, 2, 3) \ ".pushsection .altinstructions,\"a\"\n" \ @@ -183,9 +192,9 @@ static inline int alternatives_text_reserved(void *start, void *end) ALTINSTR_ENTRY(feat3, 3) \ ".popsection\n" \ ".pushsection .altinstr_replacement, \"ax\"\n" \ - ALTINSTR_REPLACEMENT(newinsn1, feat1, 1) \ - ALTINSTR_REPLACEMENT(newinsn2, feat2, 2) \ - ALTINSTR_REPLACEMENT(newinsn3, feat3, 3) \ + ALTINSTR_REPLACEMENT(newinsn1, 1) \ + ALTINSTR_REPLACEMENT(newinsn2, 2) \ + ALTINSTR_REPLACEMENT(newinsn3, 3) \ ".popsection\n" /* @@ -206,6 +215,9 @@ static inline int alternatives_text_reserved(void *start, void *end) #define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \ asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory") +#define alternative_ternary(oldinstr, feature, newinstr_yes, newinstr_no) \ + asm_inline volatile(ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) ::: "memory") + /* * Alternative inline assembly with input. * @@ -271,6 +283,116 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr +#else /* __ASSEMBLY__ */ + +#ifdef CONFIG_SMP + .macro LOCK_PREFIX +672: lock + .pushsection .smp_locks,"a" + .balign 4 + .long 672b - . + .popsection + .endm +#else + .macro LOCK_PREFIX + .endm +#endif + +/* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +.macro ANNOTATE_IGNORE_ALTERNATIVE + .Lannotate_\@: + .pushsection .discard.ignore_alts + .long .Lannotate_\@ - . + .popsection +.endm + +/* + * Issue one struct alt_instr descriptor entry (need to put it into + * the section .altinstructions, see below). This entry contains + * enough information for the alternatives patching code to patch an + * instruction. See apply_alternatives(). + */ +.macro altinstruction_entry orig alt feature orig_len alt_len pad_len + .long \orig - . + .long \alt - . + .word \feature + .byte \orig_len + .byte \alt_len + .byte \pad_len +.endm + +/* + * Define an alternative between two instructions. If @feature is + * present, early code in apply_alternatives() replaces @oldinstr with + * @newinstr. ".skip" directive takes care of proper instruction padding + * in case @newinstr is longer than @oldinstr. + */ +.macro ALTERNATIVE oldinstr, newinstr, feature +140: + \oldinstr +141: + .skip -(((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)),0x90 +142: + + .pushsection .altinstructions,"a" + altinstruction_entry 140b,143f,\feature,142b-140b,144f-143f,142b-141b + .popsection + + .pushsection .altinstr_replacement,"ax" +143: + \newinstr +144: + .popsection +.endm + +#define old_len 141b-140b +#define new_len1 144f-143f +#define new_len2 145f-144f + +/* + * gas compatible max based on the idea from: + * http://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax + * + * The additional "-" is needed because gas uses a "true" value of -1. + */ +#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) + + +/* + * Same as ALTERNATIVE macro above but for two alternatives. If CPU + * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has + * @feature2, it replaces @oldinstr with @feature2. + */ +.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2 +140: + \oldinstr +141: + .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \ + (alt_max_short(new_len1, new_len2) - (old_len)),0x90 +142: + + .pushsection .altinstructions,"a" + altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f,142b-141b + altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f,142b-141b + .popsection + + .pushsection .altinstr_replacement,"ax" +143: + \newinstr1 +144: + \newinstr2 +145: + .popsection +.endm + +/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ +#define ALTERNATIVE_TERNARY(oldinstr, feature, newinstr_yes, newinstr_no) \ + ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \ + newinstr_yes, feature + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index 4d4ec5cbdc51..94fbe6ae7431 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -22,7 +22,7 @@ extern void __add_wrong_size(void) /* * Constants for operation sizes. On 32-bit, the 64-bit size it set to * -1 because sizeof will never return -1, thereby making those switch - * case statements guaranteeed dead code which the compiler will + * case statements guaranteed dead code which the compiler will * eliminate, and allowing the "missing symbol in the default case" to * indicate a usage error. */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 1728d4ce5730..16a51e7288d5 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -8,6 +8,7 @@ #include <asm/asm.h> #include <linux/bitops.h> +#include <asm/alternative.h> enum cpuid_leafs { @@ -175,39 +176,15 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); */ static __always_inline bool _static_cpu_has(u16 bit) { - asm_volatile_goto("1: jmp 6f\n" - "2:\n" - ".skip -(((5f-4f) - (2b-1b)) > 0) * " - "((5f-4f) - (2b-1b)),0x90\n" - "3:\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 4f - .\n" /* repl offset */ - " .word %P[always]\n" /* always replace */ - " .byte 3b - 1b\n" /* src len */ - " .byte 5f - 4f\n" /* repl len */ - " .byte 3b - 2b\n" /* pad len */ - ".previous\n" - ".section .altinstr_replacement,\"ax\"\n" - "4: jmp %l[t_no]\n" - "5:\n" - ".previous\n" - ".section .altinstructions,\"a\"\n" - " .long 1b - .\n" /* src offset */ - " .long 0\n" /* no replacement */ - " .word %P[feature]\n" /* feature bit */ - " .byte 3b - 1b\n" /* src len */ - " .byte 0\n" /* repl len */ - " .byte 0\n" /* pad len */ - ".previous\n" - ".section .altinstr_aux,\"ax\"\n" - "6:\n" - " testb %[bitnum],%[cap_byte]\n" - " jnz %l[t_yes]\n" - " jmp %l[t_no]\n" - ".previous\n" + asm_volatile_goto( + ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") + ".section .altinstr_aux,\"ax\"\n" + "6:\n" + " testb %[bitnum],%[cap_byte]\n" + " jnz %l[t_yes]\n" + " jmp %l[t_no]\n" + ".previous\n" : : [feature] "i" (bit), - [always] "i" (X86_FEATURE_ALWAYS), [bitnum] "i" (1 << (bit & 7)), [cap_byte] "m" (((const char *)boot_cpu_data.x86_capability)[bit >> 3]) : : t_yes, t_no); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index cc96e26d69f7..5e2624a9d890 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -236,6 +236,8 @@ #define X86_FEATURE_EPT_AD ( 8*32+17) /* Intel Extended Page Table access-dirty bit */ #define X86_FEATURE_VMCALL ( 8*32+18) /* "" Hypervisor supports the VMCALL instruction */ #define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* "" VMware prefers VMMCALL hypercall instruction */ +#define X86_FEATURE_PVUNLOCK ( 8*32+20) /* "" PV unlock function */ +#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* "" PV vcpu_is_preempted function */ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ #define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ @@ -290,6 +292,8 @@ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ #define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* #AC for split lock */ #define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */ +#define X86_FEATURE_SGX1 (11*32+ 8) /* "" Basic SGX */ +#define X86_FEATURE_SGX2 (11*32+ 9) /* "" SGX Enclave Dynamic Memory Management (EDMM) */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 9224d40cdefe..7d7500806af8 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -283,12 +283,12 @@ extern u32 elf_hwcap2; * * The decision process for determining the results are: * - * CPU: | lacks NX* | has NX, ia32 | has NX, x86_64 | - * ELF: | | | | + * CPU: | lacks NX* | has NX, ia32 | has NX, x86_64 | + * ELF: | | | | * ---------------------|------------|------------------|----------------| - * missing PT_GNU_STACK | exec-all | exec-all | exec-none | - * PT_GNU_STACK == RWX | exec-stack | exec-stack | exec-stack | - * PT_GNU_STACK == RW | exec-none | exec-none | exec-none | + * missing PT_GNU_STACK | exec-all | exec-all | exec-none | + * PT_GNU_STACK == RWX | exec-stack | exec-stack | exec-stack | + * PT_GNU_STACK == RW | exec-none | exec-none | exec-none | * * exec-all : all PROT_READ user mappings are executable, except when * backed by files on a noexec-filesystem. diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 5eb3bdf36a41..e35e342673c7 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -547,7 +547,7 @@ SYM_CODE_END(spurious_entries_start) /* * Dummy trap number so the low level ASM macro vector number checks do not * match which results in emitting plain IDTENTRY stubs without bells and - * whistels. + * whistles. */ #define X86_TRAP_OTHER 0xFFFF diff --git a/arch/x86/include/asm/intel_pconfig.h b/arch/x86/include/asm/intel_pconfig.h index 3cb002b1d0f9..994638ef171b 100644 --- a/arch/x86/include/asm/intel_pconfig.h +++ b/arch/x86/include/asm/intel_pconfig.h @@ -38,7 +38,7 @@ enum pconfig_leaf { #define MKTME_INVALID_ENC_ALG 4 #define MKTME_DEVICE_BUSY 5 -/* Hardware requires the structure to be 256 byte alinged. Otherwise #GP(0). */ +/* Hardware requires the structure to be 256 byte aligned. Otherwise #GP(0). */ struct mktme_key_program { u16 keyid; u32 keyid_ctrl; diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h index 423b788f495e..ebe8d2ea44fe 100644 --- a/arch/x86/include/asm/intel_pt.h +++ b/arch/x86/include/asm/intel_pt.h @@ -3,7 +3,7 @@ #define _ASM_X86_INTEL_PT_H #define PT_CPUID_LEAVES 2 -#define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */ +#define PT_CPUID_REGS_NUM 4 /* number of registers (eax, ebx, ecx, edx) */ enum pt_capabilities { PT_CAP_max_subleaf = 0, diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index d726459d08e5..841a5d104afa 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -159,7 +159,7 @@ static inline void *phys_to_virt(phys_addr_t address) /* * ISA I/O bus memory addresses are 1:1 with the physical address. * However, we truncate the address to unsigned int to avoid undesirable - * promitions in legacy drivers. + * promotions in legacy drivers. */ static inline unsigned int isa_virt_to_bus(volatile void *address) { diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 9b2a0ff76c73..562854c60808 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -190,7 +190,7 @@ /* * Macro to invoke __do_softirq on the irq stack. This is only called from - * task context when bottom halfs are about to be reenabled and soft + * task context when bottom halves are about to be reenabled and soft * interrupts are pending to be processed. The interrupt stack cannot be in * use here. */ diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index 144d70ea4393..c5ce9845c999 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -109,18 +109,13 @@ static __always_inline unsigned long arch_local_irq_save(void) } #else -#define ENABLE_INTERRUPTS(x) sti -#define DISABLE_INTERRUPTS(x) cli - #ifdef CONFIG_X86_64 #ifdef CONFIG_DEBUG_ENTRY -#define SAVE_FLAGS(x) pushfq; popq %rax +#define SAVE_FLAGS pushfq; popq %rax #endif #define INTERRUPT_RETURN jmp native_iret -#else -#define INTERRUPT_RETURN iret #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h index 97bbb4a9083a..05b48b33baf0 100644 --- a/arch/x86/include/asm/kfence.h +++ b/arch/x86/include/asm/kfence.h @@ -56,8 +56,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) else set_pte(pte, __pte(pte_val(*pte) | _PAGE_PRESENT)); - /* Flush this CPU's TLB. */ + /* + * Flush this CPU's TLB, assuming whoever did the allocation/free is + * likely to continue running on this CPU. + */ + preempt_disable(); flush_tlb_one_kernel(addr); + preempt_enable(); return true; } diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3768819693e5..10eca9e8f7f6 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1488,7 +1488,7 @@ extern u64 kvm_mce_cap_supported; /* * EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing * userspace I/O) to indicate that the emulation context - * should be resued as is, i.e. skip initialization of + * should be reused as is, i.e. skip initialization of * emulation context, instruction fetch and decode. * * EMULTYPE_TRAP_UD - Set when emulating an intercepted #UD from hardware. @@ -1513,7 +1513,7 @@ extern u64 kvm_mce_cap_supported; * * EMULTYPE_VMWARE_GP - Set when emulating an intercepted #GP for VMware * backdoor emulation, which is opt in via module param. - * VMware backoor emulation handles select instructions + * VMware backdoor emulation handles select instructions * and reinjects the #GP for all other cases. * * EMULTYPE_PF - Set when emulating MMIO by way of an intercepted #PF, in which diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ccf60a809a17..e7be720062a8 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -63,7 +63,7 @@ typedef int (*hyperv_fill_flush_list_func)( static __always_inline void hv_setup_sched_clock(void *sched_clock) { #ifdef CONFIG_PARAVIRT - pv_ops.time.sched_clock = sched_clock; + paravirt_set_sched_clock(sched_clock); #endif } diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 546d6ecf0a35..45029354e0a8 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -628,8 +628,6 @@ #define MSR_IA32_APICBASE_ENABLE (1<<11) #define MSR_IA32_APICBASE_BASE (0xfffff<<12) -#define MSR_IA32_TSCDEADLINE 0x000006e0 - #define MSR_IA32_UCODE_WRITE 0x00000079 #define MSR_IA32_UCODE_REV 0x0000008b diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index cb9ad6b73973..c14fb80b9a07 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -7,7 +7,6 @@ #include <linux/objtool.h> #include <asm/alternative.h> -#include <asm/alternative-asm.h> #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> @@ -33,7 +32,7 @@ /* * Google experimented with loop-unrolling and this turned out to be - * the optimal version — two calls, each with their own speculation + * the optimal version - two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ #define __FILL_RETURN_BUFFER(reg, nr, sp) \ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 4abf110e2243..43992e5c52c2 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -15,11 +15,20 @@ #include <linux/bug.h> #include <linux/types.h> #include <linux/cpumask.h> +#include <linux/static_call_types.h> #include <asm/frame.h> -static inline unsigned long long paravirt_sched_clock(void) +u64 dummy_steal_clock(int cpu); +u64 dummy_sched_clock(void); + +DECLARE_STATIC_CALL(pv_steal_clock, dummy_steal_clock); +DECLARE_STATIC_CALL(pv_sched_clock, dummy_sched_clock); + +void paravirt_set_sched_clock(u64 (*func)(void)); + +static inline u64 paravirt_sched_clock(void) { - return PVOP_CALL0(unsigned long long, time.sched_clock); + return static_call(pv_sched_clock)(); } struct static_key; @@ -33,9 +42,13 @@ bool pv_is_native_vcpu_is_preempted(void); static inline u64 paravirt_steal_clock(int cpu) { - return PVOP_CALL1(u64, time.steal_clock, cpu); + return static_call(pv_steal_clock)(cpu); } +#ifdef CONFIG_PARAVIRT_SPINLOCKS +void __init paravirt_set_cap(void); +#endif + /* The paravirtualized I/O functions */ static inline void slow_down_io(void) { @@ -122,7 +135,9 @@ static inline void write_cr0(unsigned long x) static inline unsigned long read_cr2(void) { - return PVOP_CALLEE0(unsigned long, mmu.read_cr2); + return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2, + "mov %%cr2, %%rax;", + ALT_NOT(X86_FEATURE_XENPV)); } static inline void write_cr2(unsigned long x) @@ -132,12 +147,14 @@ static inline void write_cr2(unsigned long x) static inline unsigned long __read_cr3(void) { - return PVOP_CALL0(unsigned long, mmu.read_cr3); + return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3, + "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV)); } static inline void write_cr3(unsigned long x) { - PVOP_VCALL1(mmu.write_cr3, x); + PVOP_ALT_VCALL1(mmu.write_cr3, x, + "mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV)); } static inline void __write_cr4(unsigned long x) @@ -157,7 +174,7 @@ static inline void halt(void) static inline void wbinvd(void) { - PVOP_VCALL0(cpu.wbinvd); + PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV)); } static inline u64 paravirt_read_msr(unsigned msr) @@ -371,22 +388,28 @@ static inline void paravirt_release_p4d(unsigned long pfn) static inline pte_t __pte(pteval_t val) { - return (pte_t) { PVOP_CALLEE1(pteval_t, mmu.make_pte, val) }; + return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val, + "mov %%rdi, %%rax", + ALT_NOT(X86_FEATURE_XENPV)) }; } static inline pteval_t pte_val(pte_t pte) { - return PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte); + return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte, + "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } static inline pgd_t __pgd(pgdval_t val) { - return (pgd_t) { PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val) }; + return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val, + "mov %%rdi, %%rax", + ALT_NOT(X86_FEATURE_XENPV)) }; } static inline pgdval_t pgd_val(pgd_t pgd) { - return PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd); + return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd, + "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION @@ -419,12 +442,15 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) static inline pmd_t __pmd(pmdval_t val) { - return (pmd_t) { PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val) }; + return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val, + "mov %%rdi, %%rax", + ALT_NOT(X86_FEATURE_XENPV)) }; } static inline pmdval_t pmd_val(pmd_t pmd) { - return PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd); + return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd, + "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } static inline void set_pud(pud_t *pudp, pud_t pud) @@ -436,14 +462,16 @@ static inline pud_t __pud(pudval_t val) { pudval_t ret; - ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val); + ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val, + "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); return (pud_t) { ret }; } static inline pudval_t pud_val(pud_t pud) { - return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud); + return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud, + "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } static inline void pud_clear(pud_t *pudp) @@ -462,14 +490,17 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) static inline p4d_t __p4d(p4dval_t val) { - p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val); + p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val, + "mov %%rdi, %%rax", + ALT_NOT(X86_FEATURE_XENPV)); return (p4d_t) { ret }; } static inline p4dval_t p4d_val(p4d_t p4d) { - return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d); + return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d, + "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); } static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd) @@ -556,7 +587,9 @@ static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock, static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock) { - PVOP_VCALLEE1(lock.queued_spin_unlock, lock); + PVOP_ALT_VCALLEE1(lock.queued_spin_unlock, lock, + "movb $0, (%%" _ASM_ARG1 ");", + ALT_NOT(X86_FEATURE_PVUNLOCK)); } static __always_inline void pv_wait(u8 *ptr, u8 val) @@ -571,7 +604,9 @@ static __always_inline void pv_kick(int cpu) static __always_inline bool pv_vcpu_is_preempted(long cpu) { - return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu); + return PVOP_ALT_CALLEE1(bool, lock.vcpu_is_preempted, cpu, + "xor %%" _ASM_AX ", %%" _ASM_AX ";", + ALT_NOT(X86_FEATURE_VCPUPREEMPT)); } void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock); @@ -645,17 +680,18 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); #ifdef CONFIG_PARAVIRT_XXL static inline notrace unsigned long arch_local_save_flags(void) { - return PVOP_CALLEE0(unsigned long, irq.save_fl); + return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;", + ALT_NOT(X86_FEATURE_XENPV)); } static inline notrace void arch_local_irq_disable(void) { - PVOP_VCALLEE0(irq.irq_disable); + PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV)); } static inline notrace void arch_local_irq_enable(void) { - PVOP_VCALLEE0(irq.irq_enable); + PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV)); } static inline notrace unsigned long arch_local_irq_save(void) @@ -700,84 +736,27 @@ extern void default_banner(void); .popsection -#define COND_PUSH(set, mask, reg) \ - .if ((~(set)) & mask); push %reg; .endif -#define COND_POP(set, mask, reg) \ - .if ((~(set)) & mask); pop %reg; .endif - #ifdef CONFIG_X86_64 - -#define PV_SAVE_REGS(set) \ - COND_PUSH(set, CLBR_RAX, rax); \ - COND_PUSH(set, CLBR_RCX, rcx); \ - COND_PUSH(set, CLBR_RDX, rdx); \ - COND_PUSH(set, CLBR_RSI, rsi); \ - COND_PUSH(set, CLBR_RDI, rdi); \ - COND_PUSH(set, CLBR_R8, r8); \ - COND_PUSH(set, CLBR_R9, r9); \ - COND_PUSH(set, CLBR_R10, r10); \ - COND_PUSH(set, CLBR_R11, r11) -#define PV_RESTORE_REGS(set) \ - COND_POP(set, CLBR_R11, r11); \ - COND_POP(set, CLBR_R10, r10); \ - COND_POP(set, CLBR_R9, r9); \ - COND_POP(set, CLBR_R8, r8); \ - COND_POP(set, CLBR_RDI, rdi); \ - COND_POP(set, CLBR_RSI, rsi); \ - COND_POP(set, CLBR_RDX, rdx); \ - COND_POP(set, CLBR_RCX, rcx); \ - COND_POP(set, CLBR_RAX, rax) +#ifdef CONFIG_PARAVIRT_XXL #define PARA_PATCH(off) ((off) / 8) #define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8) #define PARA_INDIRECT(addr) *addr(%rip) -#else -#define PV_SAVE_REGS(set) \ - COND_PUSH(set, CLBR_EAX, eax); \ - COND_PUSH(set, CLBR_EDI, edi); \ - COND_PUSH(set, CLBR_ECX, ecx); \ - COND_PUSH(set, CLBR_EDX, edx) -#define PV_RESTORE_REGS(set) \ - COND_POP(set, CLBR_EDX, edx); \ - COND_POP(set, CLBR_ECX, ecx); \ - COND_POP(set, CLBR_EDI, edi); \ - COND_POP(set, CLBR_EAX, eax) - -#define PARA_PATCH(off) ((off) / 4) -#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .long, 4) -#define PARA_INDIRECT(addr) *%cs:addr -#endif -#ifdef CONFIG_PARAVIRT_XXL #define INTERRUPT_RETURN \ - PARA_SITE(PARA_PATCH(PV_CPU_iret), \ - ANNOTATE_RETPOLINE_SAFE; \ - jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);) - -#define DISABLE_INTERRUPTS(clobbers) \ - PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \ - PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable); \ - PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) - -#define ENABLE_INTERRUPTS(clobbers) \ - PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable), \ - PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \ - PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) -#endif + ANNOTATE_RETPOLINE_SAFE; \ + ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);", \ + X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;") -#ifdef CONFIG_X86_64 -#ifdef CONFIG_PARAVIRT_XXL #ifdef CONFIG_DEBUG_ENTRY -#define SAVE_FLAGS(clobbers) \ - PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \ - PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ - ANNOTATE_RETPOLINE_SAFE; \ - call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); \ - PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) +.macro PARA_IRQ_save_fl + PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), + ANNOTATE_RETPOLINE_SAFE; + call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);) +.endm + +#define SAVE_FLAGS ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \ + ALT_NOT(X86_FEATURE_XENPV) #endif #endif /* CONFIG_PARAVIRT_XXL */ #endif /* CONFIG_X86_64 */ @@ -800,5 +779,11 @@ static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) { } #endif + +#ifndef CONFIG_PARAVIRT_SPINLOCKS +static inline void paravirt_set_cap(void) +{ +} +#endif #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PARAVIRT_H */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index de87087d3bde..ae692c3194e9 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -3,7 +3,6 @@ #define _ASM_X86_PARAVIRT_TYPES_H /* Bitmask of what can be clobbered: usually at least eax. */ -#define CLBR_NONE 0 #define CLBR_EAX (1 << 0) #define CLBR_ECX (1 << 1) #define CLBR_EDX (1 << 2) @@ -15,7 +14,6 @@ #define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX) #define CLBR_RET_REG (CLBR_EAX | CLBR_EDX) -#define CLBR_SCRATCH (0) #else #define CLBR_RAX CLBR_EAX #define CLBR_RCX CLBR_ECX @@ -32,12 +30,9 @@ #define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \ CLBR_RCX | CLBR_R8 | CLBR_R9) #define CLBR_RET_REG (CLBR_RAX) -#define CLBR_SCRATCH (CLBR_R10 | CLBR_R11) #endif /* X86_64 */ -#define CLBR_CALLEE_SAVE ((CLBR_ARG_REGS | CLBR_SCRATCH) & ~CLBR_RET_REG) - #ifndef __ASSEMBLY__ #include <asm/desc_defs.h> @@ -73,19 +68,6 @@ struct pv_info { const char *name; }; -struct pv_init_ops { - /* - * Patch may replace one of the defined code sequences with - * arbitrary code, subject to the same register constraints. - * This generally means the code is not free to clobber any - * registers other than EAX. The patch function should return - * the number of bytes of code generated, as we nop pad the - * rest in generic code. - */ - unsigned (*patch)(u8 type, void *insn_buff, - unsigned long addr, unsigned len); -} __no_randomize_layout; - #ifdef CONFIG_PARAVIRT_XXL struct pv_lazy_ops { /* Set deferred update mode, used for batching operations. */ @@ -95,11 +77,6 @@ struct pv_lazy_ops { } __no_randomize_layout; #endif -struct pv_time_ops { - unsigned long long (*sched_clock)(void); - unsigned long long (*steal_clock)(int cpu); -} __no_randomize_layout; - struct pv_cpu_ops { /* hooks for various privileged instructions */ void (*io_delay)(void); @@ -156,10 +133,6 @@ struct pv_cpu_ops { u64 (*read_pmc)(int counter); - /* Normal iret. Jump to this with the standard iret stack - frame set up. */ - void (*iret)(void); - void (*start_context_switch)(struct task_struct *prev); void (*end_context_switch)(struct task_struct *next); #endif @@ -290,8 +263,6 @@ struct pv_lock_ops { * number for each function using the offset which we use to indicate * what to patch. */ struct paravirt_patch_template { - struct pv_init_ops init; - struct pv_time_ops time; struct pv_cpu_ops cpu; struct pv_irq_ops irq; struct pv_mmu_ops mmu; @@ -300,6 +271,7 @@ struct paravirt_patch_template { extern struct pv_info pv_info; extern struct paravirt_patch_template pv_ops; +extern void (*paravirt_iret)(void); #define PARAVIRT_PATCH(x) \ (offsetof(struct paravirt_patch_template, x) / sizeof(void *)) @@ -331,11 +303,7 @@ extern struct paravirt_patch_template pv_ops; /* Simple instruction patching code. */ #define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t" -unsigned paravirt_patch_ident_64(void *insn_buff, unsigned len); -unsigned paravirt_patch_default(u8 type, void *insn_buff, unsigned long addr, unsigned len); -unsigned paravirt_patch_insns(void *insn_buff, unsigned len, const char *start, const char *end); - -unsigned native_patch(u8 type, void *insn_buff, unsigned long addr, unsigned len); +unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len); int paravirt_disable_iospace(void); @@ -371,7 +339,7 @@ int paravirt_disable_iospace(void); * on the stack. All caller-save registers (eax,edx,ecx) are expected * to be modified (either clobbered or used for return values). * X86_64, on the other hand, already specifies a register-based calling - * conventions, returning at %rax, with parameteres going on %rdi, %rsi, + * conventions, returning at %rax, with parameters going on %rdi, %rsi, * %rdx, and %rcx. Note that for this reason, x86_64 does not need any * special handling for dealing with 4 arguments, unlike i386. * However, x86_64 also have to clobber all caller saved registers, which @@ -414,11 +382,9 @@ int paravirt_disable_iospace(void); * makes sure the incoming and outgoing types are always correct. */ #ifdef CONFIG_X86_32 -#define PVOP_VCALL_ARGS \ +#define PVOP_CALL_ARGS \ unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; -#define PVOP_CALL_ARGS PVOP_VCALL_ARGS - #define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x)) #define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x)) #define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x)) @@ -434,12 +400,10 @@ int paravirt_disable_iospace(void); #define VEXTRA_CLOBBERS #else /* CONFIG_X86_64 */ /* [re]ax isn't an arg, but the return val */ -#define PVOP_VCALL_ARGS \ +#define PVOP_CALL_ARGS \ unsigned long __edi = __edi, __esi = __esi, \ __edx = __edx, __ecx = __ecx, __eax = __eax; -#define PVOP_CALL_ARGS PVOP_VCALL_ARGS - #define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x)) #define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x)) #define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x)) @@ -464,152 +428,138 @@ int paravirt_disable_iospace(void); #define PVOP_TEST_NULL(op) ((void)pv_ops.op) #endif -#define PVOP_RETMASK(rettype) \ +#define PVOP_RETVAL(rettype) \ ({ unsigned long __mask = ~0UL; \ + BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long)); \ switch (sizeof(rettype)) { \ case 1: __mask = 0xffUL; break; \ case 2: __mask = 0xffffUL; break; \ case 4: __mask = 0xffffffffUL; break; \ default: break; \ } \ - __mask; \ + __mask & __eax; \ }) -#define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \ - pre, post, ...) \ +#define ____PVOP_CALL(ret, op, clbr, call_clbr, extra_clbr, ...) \ ({ \ - rettype __ret; \ PVOP_CALL_ARGS; \ PVOP_TEST_NULL(op); \ - /* This is 32-bit specific, but is okay in 64-bit */ \ - /* since this condition will never hold */ \ - if (sizeof(rettype) > sizeof(unsigned long)) { \ - asm volatile(pre \ - paravirt_alt(PARAVIRT_CALL) \ - post \ - : call_clbr, ASM_CALL_CONSTRAINT \ - : paravirt_type(op), \ - paravirt_clobber(clbr), \ - ##__VA_ARGS__ \ - : "memory", "cc" extra_clbr); \ - __ret = (rettype)((((u64)__edx) << 32) | __eax); \ - } else { \ - asm volatile(pre \ - paravirt_alt(PARAVIRT_CALL) \ - post \ - : call_clbr, ASM_CALL_CONSTRAINT \ - : paravirt_type(op), \ - paravirt_clobber(clbr), \ - ##__VA_ARGS__ \ - : "memory", "cc" extra_clbr); \ - __ret = (rettype)(__eax & PVOP_RETMASK(rettype)); \ - } \ - __ret; \ + asm volatile(paravirt_alt(PARAVIRT_CALL) \ + : call_clbr, ASM_CALL_CONSTRAINT \ + : paravirt_type(op), \ + paravirt_clobber(clbr), \ + ##__VA_ARGS__ \ + : "memory", "cc" extra_clbr); \ + ret; \ }) -#define __PVOP_CALL(rettype, op, pre, post, ...) \ - ____PVOP_CALL(rettype, op, CLBR_ANY, PVOP_CALL_CLOBBERS, \ - EXTRA_CLOBBERS, pre, post, ##__VA_ARGS__) - -#define __PVOP_CALLEESAVE(rettype, op, pre, post, ...) \ - ____PVOP_CALL(rettype, op.func, CLBR_RET_REG, \ - PVOP_CALLEE_CLOBBERS, , \ - pre, post, ##__VA_ARGS__) - - -#define ____PVOP_VCALL(op, clbr, call_clbr, extra_clbr, pre, post, ...) \ +#define ____PVOP_ALT_CALL(ret, op, alt, cond, clbr, call_clbr, \ + extra_clbr, ...) \ ({ \ - PVOP_VCALL_ARGS; \ + PVOP_CALL_ARGS; \ PVOP_TEST_NULL(op); \ - asm volatile(pre \ - paravirt_alt(PARAVIRT_CALL) \ - post \ + asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL), \ + alt, cond) \ : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ paravirt_clobber(clbr), \ ##__VA_ARGS__ \ : "memory", "cc" extra_clbr); \ + ret; \ }) -#define __PVOP_VCALL(op, pre, post, ...) \ - ____PVOP_VCALL(op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \ - VEXTRA_CLOBBERS, \ - pre, post, ##__VA_ARGS__) +#define __PVOP_CALL(rettype, op, ...) \ + ____PVOP_CALL(PVOP_RETVAL(rettype), op, CLBR_ANY, \ + PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__) + +#define __PVOP_ALT_CALL(rettype, op, alt, cond, ...) \ + ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op, alt, cond, CLBR_ANY,\ + PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, \ + ##__VA_ARGS__) + +#define __PVOP_CALLEESAVE(rettype, op, ...) \ + ____PVOP_CALL(PVOP_RETVAL(rettype), op.func, CLBR_RET_REG, \ + PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__) + +#define __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, ...) \ + ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op.func, alt, cond, \ + CLBR_RET_REG, PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__) + + +#define __PVOP_VCALL(op, ...) \ + (void)____PVOP_CALL(, op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \ + VEXTRA_CLOBBERS, ##__VA_ARGS__) + +#define __PVOP_ALT_VCALL(op, alt, cond, ...) \ + (void)____PVOP_ALT_CALL(, op, alt, cond, CLBR_ANY, \ + PVOP_VCALL_CLOBBERS, VEXTRA_CLOBBERS, \ + ##__VA_ARGS__) -#define __PVOP_VCALLEESAVE(op, pre, post, ...) \ - ____PVOP_VCALL(op.func, CLBR_RET_REG, \ - PVOP_VCALLEE_CLOBBERS, , \ - pre, post, ##__VA_ARGS__) +#define __PVOP_VCALLEESAVE(op, ...) \ + (void)____PVOP_CALL(, op.func, CLBR_RET_REG, \ + PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__) +#define __PVOP_ALT_VCALLEESAVE(op, alt, cond, ...) \ + (void)____PVOP_ALT_CALL(, op.func, alt, cond, CLBR_RET_REG, \ + PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__) #define PVOP_CALL0(rettype, op) \ - __PVOP_CALL(rettype, op, "", "") + __PVOP_CALL(rettype, op) #define PVOP_VCALL0(op) \ - __PVOP_VCALL(op, "", "") + __PVOP_VCALL(op) +#define PVOP_ALT_CALL0(rettype, op, alt, cond) \ + __PVOP_ALT_CALL(rettype, op, alt, cond) +#define PVOP_ALT_VCALL0(op, alt, cond) \ + __PVOP_ALT_VCALL(op, alt, cond) #define PVOP_CALLEE0(rettype, op) \ - __PVOP_CALLEESAVE(rettype, op, "", "") + __PVOP_CALLEESAVE(rettype, op) #define PVOP_VCALLEE0(op) \ - __PVOP_VCALLEESAVE(op, "", "") + __PVOP_VCALLEESAVE(op) +#define PVOP_ALT_CALLEE0(rettype, op, alt, cond) \ + __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond) +#define PVOP_ALT_VCALLEE0(op, alt, cond) \ + __PVOP_ALT_VCALLEESAVE(op, alt, cond) #define PVOP_CALL1(rettype, op, arg1) \ - __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1)) + __PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1)) #define PVOP_VCALL1(op, arg1) \ - __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1)) + __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1)) +#define PVOP_ALT_VCALL1(op, arg1, alt, cond) \ + __PVOP_ALT_VCALL(op, alt, cond, PVOP_CALL_ARG1(arg1)) #define PVOP_CALLEE1(rettype, op, arg1) \ - __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1)) + __PVOP_CALLEESAVE(rettype, op, PVOP_CALL_ARG1(arg1)) #define PVOP_VCALLEE1(op, arg1) \ - __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1)) + __PVOP_VCALLEESAVE(op, PVOP_CALL_ARG1(arg1)) +#define PVOP_ALT_CALLEE1(rettype, op, arg1, alt, cond) \ + __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, PVOP_CALL_ARG1(arg1)) +#define PVOP_ALT_VCALLEE1(op, arg1, alt, cond) \ + __PVOP_ALT_VCALLEESAVE(op, alt, cond, PVOP_CALL_ARG1(arg1)) #define PVOP_CALL2(rettype, op, arg1, arg2) \ - __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2)) + __PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2)) #define PVOP_VCALL2(op, arg1, arg2) \ - __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2)) - -#define PVOP_CALLEE2(rettype, op, arg1, arg2) \ - __PVOP_CALLEESAVE(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2)) -#define PVOP_VCALLEE2(op, arg1, arg2) \ - __PVOP_VCALLEESAVE(op, "", "", PVOP_CALL_ARG1(arg1), \ - PVOP_CALL_ARG2(arg2)) - + __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2)) #define PVOP_CALL3(rettype, op, arg1, arg2, arg3) \ - __PVOP_CALL(rettype, op, "", "", PVOP_CALL_ARG1(arg1), \ + __PVOP_CALL(rettype, op, PVOP_CALL_ARG1(arg1), \ PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) #define PVOP_VCALL3(op, arg1, arg2, arg3) \ - __PVOP_VCALL(op, "", "", PVOP_CALL_ARG1(arg1), \ + __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), \ PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) -/* This is the only difference in x86_64. We can make it much simpler */ -#ifdef CONFIG_X86_32 #define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \ __PVOP_CALL(rettype, op, \ - "push %[_arg4];", "lea 4(%%esp),%%esp;", \ - PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ - PVOP_CALL_ARG3(arg3), [_arg4] "mr" ((u32)(arg4))) -#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \ - __PVOP_VCALL(op, \ - "push %[_arg4];", "lea 4(%%esp),%%esp;", \ - "0" ((u32)(arg1)), "1" ((u32)(arg2)), \ - "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4))) -#else -#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4) \ - __PVOP_CALL(rettype, op, "", "", \ PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) #define PVOP_VCALL4(op, arg1, arg2, arg3, arg4) \ - __PVOP_VCALL(op, "", "", \ - PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ + __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) -#endif /* Lazy mode for batching updates / context switch */ enum paravirt_lazy_mode { diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index a02c67291cfc..b1099f2d9800 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1244,7 +1244,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); * - * dst - pointer to pgd range anwhere on a pgd page + * dst - pointer to pgd range anywhere on a pgd page * src - "" * count - the number of pgds to copy. * diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index f1b9ed5efaa9..185142b84ebe 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -314,11 +314,6 @@ struct x86_hw_tss { struct x86_hw_tss { u32 reserved1; u64 sp0; - - /* - * We store cpu_current_top_of_stack in sp1 so it's always accessible. - * Linux does not use ring 1, so sp1 is not otherwise needed. - */ u64 sp1; /* @@ -426,12 +421,7 @@ struct irq_stack { char stack[IRQ_STACK_SIZE]; } __aligned(IRQ_STACK_SIZE); -#ifdef CONFIG_X86_32 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); -#else -/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */ -#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1 -#endif #ifdef CONFIG_X86_64 struct fixed_percpu_data { @@ -527,7 +517,7 @@ struct thread_struct { struct io_bitmap *io_bitmap; /* - * IOPL. Priviledge level dependent I/O permission which is + * IOPL. Privilege level dependent I/O permission which is * emulated via the I/O bitmap to prevent user space from disabling * interrupts. */ diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index b6a9d51d1d79..8c5d1910a848 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -4,6 +4,8 @@ #include <asm/ldt.h> +struct task_struct; + /* misc architecture specific prototypes */ void syscall_init(void); diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 4352f08bfbb5..43fa081a1adb 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -8,8 +8,8 @@ /* * The set_memory_* API can be used to change various attributes of a virtual * address range. The attributes include: - * Cachability : UnCached, WriteCombining, WriteThrough, WriteBack - * Executability : eXeutable, NoteXecutable + * Cacheability : UnCached, WriteCombining, WriteThrough, WriteBack + * Executability : eXecutable, NoteXecutable * Read/Write : ReadOnly, ReadWrite * Presence : NotPresent * Encryption : Encrypted, Decrypted diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 389d851a02c4..a12458a7a8d4 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -130,11 +130,6 @@ void *extend_brk(size_t size, size_t align); : : "i" (sz)); \ } -/* Helper for reserving space for arrays of things */ -#define RESERVE_BRK_ARRAY(type, name, entries) \ - type *name; \ - RESERVE_BRK(name, sizeof(type) * entries) - extern void probe_roms(void); #ifdef __i386__ diff --git a/arch/x86/kernel/cpu/sgx/arch.h b/arch/x86/include/asm/sgx.h index dd7602c44c72..9c31e0ebc55b 100644 --- a/arch/x86/kernel/cpu/sgx/arch.h +++ b/arch/x86/include/asm/sgx.h @@ -2,15 +2,20 @@ /** * Copyright(c) 2016-20 Intel Corporation. * - * Contains data structures defined by the SGX architecture. Data structures - * defined by the Linux software stack should not be placed here. + * Intel Software Guard Extensions (SGX) support. */ -#ifndef _ASM_X86_SGX_ARCH_H -#define _ASM_X86_SGX_ARCH_H +#ifndef _ASM_X86_SGX_H +#define _ASM_X86_SGX_H #include <linux/bits.h> #include <linux/types.h> +/* + * This file contains both data structures defined by SGX architecture and Linux + * defined software data structures and functions. The two should not be mixed + * together for better readibility. The architectural definitions come first. + */ + /* The SGX specific CPUID function. */ #define SGX_CPUID 0x12 /* EPC enumeration. */ @@ -22,16 +27,36 @@ /* The bitmask for the EPC section type. */ #define SGX_CPUID_EPC_MASK GENMASK(3, 0) +enum sgx_encls_function { + ECREATE = 0x00, + EADD = 0x01, + EINIT = 0x02, + EREMOVE = 0x03, + EDGBRD = 0x04, + EDGBWR = 0x05, + EEXTEND = 0x06, + ELDU = 0x08, + EBLOCK = 0x09, + EPA = 0x0A, + EWB = 0x0B, + ETRACK = 0x0C, + EAUG = 0x0D, + EMODPR = 0x0E, + EMODT = 0x0F, +}; + /** * enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV * %SGX_NOT_TRACKED: Previous ETRACK's shootdown sequence has not * been completed yet. + * %SGX_CHILD_PRESENT SECS has child pages present in the EPC. * %SGX_INVALID_EINITTOKEN: EINITTOKEN is invalid and enclave signer's * public key does not match IA32_SGXLEPUBKEYHASH. * %SGX_UNMASKED_EVENT: An unmasked event, e.g. INTR, was received */ enum sgx_return_code { SGX_NOT_TRACKED = 11, + SGX_CHILD_PRESENT = 13, SGX_INVALID_EINITTOKEN = 16, SGX_UNMASKED_EVENT = 128, }; @@ -271,7 +296,7 @@ struct sgx_pcmd { * @header1: constant byte string * @vendor: must be either 0x0000 or 0x8086 * @date: YYYYMMDD in BCD - * @header2: costant byte string + * @header2: constant byte string * @swdefined: software defined value */ struct sgx_sigstruct_header { @@ -335,4 +360,19 @@ struct sgx_sigstruct { #define SGX_LAUNCH_TOKEN_SIZE 304 -#endif /* _ASM_X86_SGX_ARCH_H */ +/* + * Do not put any hardware-defined SGX structure representations below this + * comment! + */ + +#ifdef CONFIG_X86_SGX_KVM +int sgx_virt_ecreate(struct sgx_pageinfo *pageinfo, void __user *secs, + int *trapnr); +int sgx_virt_einit(void __user *sigstruct, void __user *token, + void __user *secs, u64 *lepubkeyhash, int *trapnr); +#endif + +int sgx_set_attribute(unsigned long *allowed_attributes, + unsigned int attribute_fd); + +#endif /* _ASM_X86_SGX_H */ diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index 0bc9b0895f33..d17b39893b79 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -11,6 +11,7 @@ #include <asm/nops.h> #include <asm/cpufeatures.h> +#include <asm/alternative.h> /* "Raw" instruction opcodes */ #define __ASM_CLAC ".byte 0x0f,0x01,0xca" @@ -18,8 +19,6 @@ #ifdef __ASSEMBLY__ -#include <asm/alternative-asm.h> - #ifdef CONFIG_X86_SMAP #define ASM_CLAC \ @@ -37,8 +36,6 @@ #else /* __ASSEMBLY__ */ -#include <asm/alternative.h> - #ifdef CONFIG_X86_SMAP static __always_inline void clac(void) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index c0538f82c9a2..630ff08532be 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -132,6 +132,7 @@ void native_play_dead(void); void play_dead_common(void); void wbinvd_on_cpu(int cpu); int wbinvd_on_all_cpus(void); +void cond_wakeup_cpu0(void); void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 9f69cc497f4b..b5f0d2ff47e4 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -71,12 +71,7 @@ static inline void update_task_stack(struct task_struct *task) else this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0); #else - /* - * x86-64 updates x86_tss.sp1 via cpu_current_top_of_stack. That - * doesn't work on x86-32 because sp1 and - * cpu_current_top_of_stack have different values (because of - * the non-zero stack-padding on 32bit). - */ + /* Xen PV enters the kernel on the thread stack. */ if (static_cpu_has(X86_FEATURE_XENPV)) load_sp0(task_top_of_stack(task)); #endif diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index a84333adeef2..80c08c7d5e72 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -80,6 +80,7 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); } #define __COND_SYSCALL(abi, name) \ + __weak long __##abi##_##name(const struct pt_regs *__unused); \ __weak long __##abi##_##name(const struct pt_regs *__unused) \ { \ return sys_ni_syscall(); \ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 06b740bae431..de406d93b515 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -197,13 +197,7 @@ static inline int arch_within_stack_frames(const void * const stack, #endif } -#else /* !__ASSEMBLY__ */ - -#ifdef CONFIG_X86_64 -# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1) -#endif - -#endif +#endif /* !__ASSEMBLY__ */ /* * Thread-synchronous status. diff --git a/arch/x86/include/asm/uv/uv_geo.h b/arch/x86/include/asm/uv/uv_geo.h index f241451035fb..027a9258dbca 100644 --- a/arch/x86/include/asm/uv/uv_geo.h +++ b/arch/x86/include/asm/uv/uv_geo.h @@ -10,7 +10,7 @@ #ifndef _ASM_UV_GEO_H #define _ASM_UV_GEO_H -/* Type declaractions */ +/* Type declarations */ /* Size of a geoid_s structure (must be before decl. of geoid_u) */ #define GEOID_SIZE 8 diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 5002f52be332..d3e3197917be 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -353,7 +353,7 @@ union uvh_apicid { * * Note there are NO leds on a UV system. This register is only * used by the system controller to monitor system-wide operation. - * There are 64 regs per node. With Nahelem cpus (2 cores per node, + * There are 64 regs per node. With Nehalem cpus (2 cores per node, * 8 cpus per core, 2 threads per cpu) there are 32 cpu threads on * a node. * diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 7068e4bb057d..1a162e559753 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -87,18 +87,6 @@ clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, #endif /* - * The maximum amount of extra memory compared to the base size. The - * main scaling factor is the size of struct page. At extreme ratios - * of base:extra, all the base memory can be filled with page - * structures for the extra memory, leaving no space for anything - * else. - * - * 10x seems like a reasonable balance between scaling flexibility and - * leaving a practically usable system. - */ -#define XEN_EXTRA_MEM_RATIO (10) - -/* * Helper functions to write or read unsigned long values to/from * memory, when the access may fault. */ diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 600a141c8805..b25d3f82c2f3 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -234,7 +234,7 @@ struct boot_params { * handling of page tables. * * These enums should only ever be used by x86 code, and the code that uses - * it should be well contained and compartamentalized. + * it should be well contained and compartmentalized. * * KVM and Xen HVM do not have a subarch as these are expected to follow * standard x86 boot entries. If there is a genuine need for "hypervisor" type @@ -252,7 +252,7 @@ struct boot_params { * @X86_SUBARCH_XEN: Used for Xen guest types which follow the PV boot path, * which start at asm startup_xen() entry point and later jump to the C * xen_start_kernel() entry point. Both domU and dom0 type of guests are - * currently supportd through this PV boot path. + * currently supported through this PV boot path. * @X86_SUBARCH_INTEL_MID: Used for Intel MID (Mobile Internet Device) platform * systems which do not have the PCI legacy interfaces. * @X86_SUBARCH_CE4100: Used for Intel CE media processor (CE4100) SoC diff --git a/arch/x86/include/uapi/asm/msgbuf.h b/arch/x86/include/uapi/asm/msgbuf.h index b3d0664fadc9..ac83e25bbf37 100644 --- a/arch/x86/include/uapi/asm/msgbuf.h +++ b/arch/x86/include/uapi/asm/msgbuf.h @@ -12,7 +12,7 @@ * The msqid64_ds structure for x86 architecture with x32 ABI. * * On x86-32 and x86-64 we can just use the generic definition, but - * x32 uses the same binary layout as x86_64, which is differnet + * x32 uses the same binary layout as x86_64, which is different * from other 32-bit architectures. */ diff --git a/arch/x86/include/uapi/asm/sgx.h b/arch/x86/include/uapi/asm/sgx.h index 9034f3007c4e..9690d6899ad9 100644 --- a/arch/x86/include/uapi/asm/sgx.h +++ b/arch/x86/include/uapi/asm/sgx.h @@ -152,7 +152,7 @@ struct sgx_enclave_run { * Most exceptions reported on ENCLU, including those that occur within the * enclave, are fixed up and reported synchronously instead of being delivered * via a standard signal. Debug Exceptions (#DB) and Breakpoints (#BP) are - * never fixed up and are always delivered via standard signals. On synchrously + * never fixed up and are always delivered via standard signals. On synchronously * reported exceptions, -EFAULT is returned and details about the exception are * recorded in @run.exception, the optional sgx_enclave_exception struct. * diff --git a/arch/x86/include/uapi/asm/shmbuf.h b/arch/x86/include/uapi/asm/shmbuf.h index f0305dc660c9..fce18eaa070c 100644 --- a/arch/x86/include/uapi/asm/shmbuf.h +++ b/arch/x86/include/uapi/asm/shmbuf.h @@ -9,7 +9,7 @@ * The shmid64_ds structure for x86 architecture with x32 ABI. * * On x86-32 and x86-64 we can just use the generic definition, but - * x32 uses the same binary layout as x86_64, which is differnet + * x32 uses the same binary layout as x86_64, which is different * from other 32-bit architectures. */ diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h index 844d60eb1882..d0d9b331d3a1 100644 --- a/arch/x86/include/uapi/asm/sigcontext.h +++ b/arch/x86/include/uapi/asm/sigcontext.h @@ -139,7 +139,7 @@ struct _fpstate_32 { * The 64-bit FPU frame. (FXSAVE format and later) * * Note1: If sw_reserved.magic1 == FP_XSTATE_MAGIC1 then the structure is - * larger: 'struct _xstate'. Note that 'struct _xstate' embedds + * larger: 'struct _xstate'. Note that 'struct _xstate' embeds * 'struct _fpstate' so that you can always assume the _fpstate portion * exists so that you can check the magic value. * diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 2ddf08351f0b..0704c2a94272 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -35,7 +35,6 @@ KASAN_SANITIZE_sev-es.o := n KCSAN_SANITIZE := n OBJECT_FILES_NON_STANDARD_test_nx.o := y -OBJECT_FILES_NON_STANDARD_paravirt_patch.o := y ifdef CONFIG_FRAME_POINTER OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o := y @@ -121,7 +120,7 @@ obj-$(CONFIG_AMD_NB) += amd_nb.o obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o -obj-$(CONFIG_PARAVIRT) += paravirt.o paravirt_patch.o +obj-$(CONFIG_PARAVIRT) += paravirt.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o obj-$(CONFIG_PARAVIRT_CLOCK) += pvclock.o obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7bdc0239a943..e90310cbe73a 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -830,7 +830,7 @@ int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base) EXPORT_SYMBOL(acpi_unregister_ioapic); /** - * acpi_ioapic_registered - Check whether IOAPIC assoicatied with @gsi_base + * acpi_ioapic_registered - Check whether IOAPIC associated with @gsi_base * has been registered * @handle: ACPI handle of the IOAPIC device * @gsi_base: GSI base associated with the IOAPIC @@ -1554,10 +1554,18 @@ void __init acpi_boot_table_init(void) /* * Initialize the ACPI boot-time table parser. */ - if (acpi_table_init()) { + if (acpi_locate_initial_tables()) disable_acpi(); - return; - } + else + acpi_reserve_initial_tables(); +} + +int __init early_acpi_boot_init(void) +{ + if (acpi_disabled) + return 1; + + acpi_table_init_complete(); acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf); @@ -1570,18 +1578,9 @@ void __init acpi_boot_table_init(void) } else { printk(KERN_WARNING PREFIX "Disabling ACPI support\n"); disable_acpi(); - return; + return 1; } } -} - -int __init early_acpi_boot_init(void) -{ - /* - * If acpi_disabled, bail out - */ - if (acpi_disabled) - return 1; /* * Process the Multiple APIC Description Table (MADT), if present @@ -1657,7 +1656,7 @@ static int __init parse_acpi(char *arg) else if (strcmp(arg, "noirq") == 0) { acpi_noirq_set(); } - /* "acpi=copy_dsdt" copys DSDT */ + /* "acpi=copy_dsdt" copies DSDT */ else if (strcmp(arg, "copy_dsdt") == 0) { acpi_gbl_copy_dsdt_locally = 1; } diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index cc1fea76aab0..3f85fcae450c 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -41,7 +41,7 @@ unsigned long acpi_get_wakeup_address(void) * x86_acpi_enter_sleep_state - enter sleep state * @state: Sleep state to enter. * - * Wrapper around acpi_enter_sleep_state() to be called by assmebly. + * Wrapper around acpi_enter_sleep_state() to be called by assembly. */ asmlinkage acpi_status __visible x86_acpi_enter_sleep_state(u8 state) { diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index 56b6865afb2a..d5d8a352eafa 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -115,7 +115,7 @@ SYM_FUNC_START(do_suspend_lowlevel) movq pt_regs_r14(%rax), %r14 movq pt_regs_r15(%rax), %r15 -#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) /* * The suspend path may have poisoned some areas deeper in the stack, * which we now need to unpoison. diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 8d778e46725d..f810e6fececd 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -28,6 +28,7 @@ #include <asm/insn.h> #include <asm/io.h> #include <asm/fixmap.h> +#include <asm/paravirt.h> int __read_mostly alternatives_patched; @@ -388,21 +389,31 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, */ for (a = start; a < end; a++) { int insn_buff_sz = 0; + /* Mask away "NOT" flag bit for feature to test. */ + u16 feature = a->cpuid & ~ALTINSTR_FLAG_INV; instr = (u8 *)&a->instr_offset + a->instr_offset; replacement = (u8 *)&a->repl_offset + a->repl_offset; BUG_ON(a->instrlen > sizeof(insn_buff)); - BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32); - if (!boot_cpu_has(a->cpuid)) { + BUG_ON(feature >= (NCAPINTS + NBUGINTS) * 32); + + /* + * Patch if either: + * - feature is present + * - feature not present but ALTINSTR_FLAG_INV is set to mean, + * patch if feature is *NOT* present. + */ + if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV)) { if (a->padlen > 1) optimize_nops(a, instr); continue; } - DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d", - a->cpuid >> 5, - a->cpuid & 0x1f, + DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d", + (a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "", + feature >> 5, + feature & 0x1f, instr, instr, a->instrlen, replacement, a->replacementlen, a->padlen); @@ -605,7 +616,7 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start, BUG_ON(p->len > MAX_PATCH_LEN); /* prep the buffer with the original instructions */ memcpy(insn_buff, p->instr, p->len); - used = pv_ops.init.patch(p->type, insn_buff, (unsigned long)p->instr, p->len); + used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len); BUG_ON(used > p->len); @@ -723,6 +734,33 @@ void __init alternative_instructions(void) * patching. */ + /* + * Paravirt patching and alternative patching can be combined to + * replace a function call with a short direct code sequence (e.g. + * by setting a constant return value instead of doing that in an + * external function). + * In order to make this work the following sequence is required: + * 1. set (artificial) features depending on used paravirt + * functions which can later influence alternative patching + * 2. apply paravirt patching (generally replacing an indirect + * function call with a direct one) + * 3. apply alternative patching (e.g. replacing a direct function + * call with a custom code sequence) + * Doing paravirt patching after alternative patching would clobber + * the optimization of the custom code with a function call again. + */ + paravirt_set_cap(); + + /* + * First patch paravirt functions, such that we overwrite the indirect + * call with the direct call. + */ + apply_paravirt(__parainstructions, __parainstructions_end); + + /* + * Then patch alternatives, such that those paravirt calls that are in + * alternatives can be overwritten by their immediate fragments. + */ apply_alternatives(__alt_instructions, __alt_instructions_end); #ifdef CONFIG_SMP @@ -741,8 +779,6 @@ void __init alternative_instructions(void) } #endif - apply_paravirt(__parainstructions, __parainstructions_end); - restart_nmi(); alternatives_patched = 1; } diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index b4396952c9a6..09083094eb57 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Shared support code for AMD K8 northbridges and derivates. + * Shared support code for AMD K8 northbridges and derivatives. * Copyright 2006 Andi Kleen, SUSE Labs. */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 4f26700f314d..4a39fb429f15 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -619,7 +619,7 @@ static void setup_APIC_timer(void) if (this_cpu_has(X86_FEATURE_ARAT)) { lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP; - /* Make LAPIC timer preferrable over percpu HPET */ + /* Make LAPIC timer preferable over percpu HPET */ lapic_clockevent.rating = 150; } @@ -666,7 +666,7 @@ void lapic_update_tsc_freq(void) * In this functions we calibrate APIC bus clocks to the external timer. * * We want to do the calibration only once since we want to have local timer - * irqs syncron. CPUs connected by the same APIC bus have the very same bus + * irqs synchronous. CPUs connected by the same APIC bus have the very same bus * frequency. * * This was previously done by reading the PIT/HPET and waiting for a wrap @@ -1532,7 +1532,7 @@ static bool apic_check_and_ack(union apic_ir *irr, union apic_ir *isr) * Most probably by now the CPU has serviced that pending interrupt and it * might not have done the ack_APIC_irq() because it thought, interrupt * came from i8259 as ExtInt. LAPIC did not get EOI so it does not clear - * the ISR bit and cpu thinks it has already serivced the interrupt. Hence + * the ISR bit and cpu thinks it has already serviced the interrupt. Hence * a vector might get locked. It was noticed for timer irq (vector * 0x31). Issue an extra EOI to clear ISR. * @@ -1657,7 +1657,7 @@ static void setup_local_APIC(void) */ /* * Actually disabling the focus CPU check just makes the hang less - * frequent as it makes the interrupt distributon model be more + * frequent as it makes the interrupt distribution model be more * like LRU than MRU (the short-term load is more even across CPUs). */ @@ -1875,7 +1875,7 @@ static __init void try_to_enable_x2apic(int remap_mode) /* * Without IR, all CPUs can be addressed by IOAPIC/MSI only - * in physical mode, and CPUs with an APIC ID that cannnot + * in physical mode, and CPUs with an APIC ID that cannot * be addressed must not be brought online. */ x2apic_set_max_apicid(apic_limit); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 73ff4dd426a8..d5c691a3208b 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -928,7 +928,7 @@ static bool mp_check_pin_attr(int irq, struct irq_alloc_info *info) /* * setup_IO_APIC_irqs() programs all legacy IRQs with default trigger - * and polarity attirbutes. So allow the first user to reprogram the + * and polarity attributes. So allow the first user to reprogram the * pin with real trigger and polarity attributes. */ if (irq < nr_legacy_irqs() && data->count == 1) { @@ -994,7 +994,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, /* * Legacy ISA IRQ has already been allocated, just add pin to - * the pin list assoicated with this IRQ and program the IOAPIC + * the pin list associated with this IRQ and program the IOAPIC * entry. The IOAPIC entry */ if (irq_data && irq_data->parent_data) { @@ -1752,7 +1752,7 @@ static inline void ioapic_finish_move(struct irq_data *data, bool moveit) * with masking the ioapic entry and then polling until * Remote IRR was clear before reprogramming the * ioapic I don't trust the Remote IRR bit to be - * completey accurate. + * completely accurate. * * However there appears to be no other way to plug * this race, so if the Remote IRR bit is not @@ -1830,7 +1830,7 @@ static void ioapic_ack_level(struct irq_data *irq_data) /* * Tail end of clearing remote IRR bit (either by delivering the EOI * message via io-apic EOI register write or simulating it using - * mask+edge followed by unnask+level logic) manually when the + * mask+edge followed by unmask+level logic) manually when the * level triggered interrupt is seen as the edge triggered interrupt * at the cpu. */ diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 3c9c7492252f..6aa27e08b3e2 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -1045,7 +1045,7 @@ void irq_force_complete_move(struct irq_desc *desc) * * But in case of cpu hotplug this should be a non issue * because if the affinity update happens right before all - * cpus rendevouz in stop machine, there is no way that the + * cpus rendezvous in stop machine, there is no way that the * interrupt can be blocked on the target cpu because all cpus * loops first with interrupts enabled in stop machine, so the * old vector is not yet cleaned up when the interrupt fires. @@ -1054,7 +1054,7 @@ void irq_force_complete_move(struct irq_desc *desc) * of the interrupt on the apic/system bus would be delayed * beyond the point where the target cpu disables interrupts * in stop machine. I doubt that it can happen, but at least - * there is a theroretical chance. Virtualization might be + * there is a theoretical chance. Virtualization might be * able to expose this, but AFAICT the IOAPIC emulation is not * as stupid as the real hardware. * diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 52bc217ca8c3..f5a48e66e4f5 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -369,6 +369,15 @@ static int __init early_get_arch_type(void) return ret; } +/* UV system found, check which APIC MODE BIOS already selected */ +static void __init early_set_apic_mode(void) +{ + if (x2apic_enabled()) + uv_system_type = UV_X2APIC; + else + uv_system_type = UV_LEGACY_APIC; +} + static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id) { /* Save OEM_ID passed from ACPI MADT */ @@ -404,11 +413,12 @@ static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id) else uv_hubless_system |= 0x8; - /* Copy APIC type */ + /* Copy OEM Table ID */ uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id); pr_info("UV: OEM IDs %s/%s, SystemType %d, HUBLESS ID %x\n", oem_id, oem_table_id, uv_system_type, uv_hubless_system); + return 0; } @@ -453,6 +463,7 @@ static int __init uv_set_system_type(char *_oem_id, char *_oem_table_id) early_set_hub_type(); /* Other UV setup functions */ + early_set_apic_mode(); early_get_pnodeid(); early_get_apic_socketid_shift(); x86_platform.is_untracked_pat_range = uv_is_untracked_pat_range; @@ -472,29 +483,14 @@ static int __init uv_acpi_madt_oem_check(char *_oem_id, char *_oem_table_id) if (uv_set_system_type(_oem_id, _oem_table_id) == 0) return 0; - /* Save and Decode OEM Table ID */ + /* Save for display of the OEM Table ID */ uv_stringify(sizeof(oem_table_id), oem_table_id, _oem_table_id); - /* This is the most common hardware variant, x2apic mode */ - if (!strcmp(oem_table_id, "UVX")) - uv_system_type = UV_X2APIC; - - /* Only used for very small systems, usually 1 chassis, legacy mode */ - else if (!strcmp(oem_table_id, "UVL")) - uv_system_type = UV_LEGACY_APIC; - - else - goto badbios; - pr_info("UV: OEM IDs %s/%s, System/UVType %d/0x%x, HUB RevID %d\n", oem_id, oem_table_id, uv_system_type, is_uv(UV_ANY), uv_min_hub_revision_id); return 0; - -badbios: - pr_err("UV: UVarchtype:%s not supported\n", uv_archtype); - BUG(); } enum uv_system_type get_uv_system_type(void) @@ -1671,6 +1667,9 @@ static __init int uv_system_init_hubless(void) if (rc < 0) return rc; + /* Set section block size for current node memory */ + set_block_size(); + /* Create user access node */ if (rc >= 0) uv_setup_proc_files(1); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 660270359d39..241dda687eb9 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -94,7 +94,7 @@ * Remove APM dependencies in arch/i386/kernel/process.c * Remove APM dependencies in drivers/char/sysrq.c * Reset time across standby. - * Allow more inititialisation on SMP. + * Allow more initialisation on SMP. * Remove CONFIG_APM_POWER_OFF and make it boot time * configurable (default on). * Make debug only a boot time parameter (remove APM_DEBUG). @@ -766,7 +766,7 @@ static int apm_driver_version(u_short *val) * not cleared until it is acknowledged. * * Additional information is returned in the info pointer, providing - * that APM 1.2 is in use. If no messges are pending the value 0x80 + * that APM 1.2 is in use. If no messages are pending the value 0x80 * is returned (No power management events pending). */ static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info) @@ -1025,7 +1025,7 @@ static int apm_enable_power_management(int enable) * status which gives the rough battery status, and current power * source. The bat value returned give an estimate as a percentage * of life and a status value for the battery. The estimated life - * if reported is a lifetime in secodnds/minutes at current powwer + * if reported is a lifetime in seconds/minutes at current power * consumption. */ diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 60b9f42ce3c1..ecd3fd6993d1 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -61,13 +61,6 @@ static void __used common(void) OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext); #endif -#ifdef CONFIG_PARAVIRT_XXL - BLANK(); - OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable); - OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable); - OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret); -#endif - #ifdef CONFIG_XEN BLANK(); OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask); diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 3ca9be482a9e..d66af2950e06 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -877,7 +877,7 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) static int __cache_amd_cpumap_setup(unsigned int cpu, int index, struct _cpuid4_info_regs *base) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cpu_cacheinfo *this_cpu_ci; struct cacheinfo *this_leaf; int i, sibling; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ab640abe26b6..340107800b36 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -482,7 +482,7 @@ static __always_inline void setup_pku(struct cpuinfo_x86 *c) if (pk) pk->pkru = init_pkru_value; /* - * Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE + * Setting X86_CR4_PKE will cause the X86_FEATURE_OSPKE * cpuid bit to be set. We need to ensure that we * update that bit in this CPU's "cpu_info". */ @@ -1404,7 +1404,7 @@ static void detect_null_seg_behavior(struct cpuinfo_x86 *c) * where GS is unused by the prev and next threads. * * Since neither vendor documents this anywhere that I can see, - * detect it directly instead of hardcoding the choice by + * detect it directly instead of hard-coding the choice by * vendor. * * I've designated AMD's behavior as the "bug" because it's @@ -1748,6 +1748,8 @@ DEFINE_PER_CPU(bool, hardirq_stack_inuse); DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; EXPORT_PER_CPU_SYMBOL(__preempt_count); +DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK; + /* May not be marked __init: used by software suspend */ void syscall_init(void) { diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index 42af31b64c2c..defda61f372d 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -72,6 +72,9 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512_FP16, X86_FEATURE_AVX512BW }, { X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES }, { X86_FEATURE_PER_THREAD_MBA, X86_FEATURE_MBA }, + { X86_FEATURE_SGX_LC, X86_FEATURE_SGX }, + { X86_FEATURE_SGX1, X86_FEATURE_SGX }, + { X86_FEATURE_SGX2, X86_FEATURE_SGX1 }, {} }; diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 1d9b8aaea06c..7227c15299d0 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -291,7 +291,7 @@ static void init_cyrix(struct cpuinfo_x86 *c) mark_tsc_unstable("cyrix 5510/5520 detected"); } #endif - c->x86_cache_size = 16; /* Yep 16K integrated cache thats it */ + c->x86_cache_size = 16; /* Yep 16K integrated cache that's it */ /* GXm supports extended cpuid levels 'ala' AMD */ if (c->cpuid_level == 2) { diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c index 3b1b01f2b248..da696eb4821a 100644 --- a/arch/x86/kernel/cpu/feat_ctl.c +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -93,15 +93,9 @@ static void init_vmx_capabilities(struct cpuinfo_x86 *c) } #endif /* CONFIG_X86_VMX_FEATURE_NAMES */ -static void clear_sgx_caps(void) -{ - setup_clear_cpu_cap(X86_FEATURE_SGX); - setup_clear_cpu_cap(X86_FEATURE_SGX_LC); -} - static int __init nosgx(char *str) { - clear_sgx_caps(); + setup_clear_cpu_cap(X86_FEATURE_SGX); return 0; } @@ -110,23 +104,30 @@ early_param("nosgx", nosgx); void init_ia32_feat_ctl(struct cpuinfo_x86 *c) { + bool enable_sgx_kvm = false, enable_sgx_driver = false; bool tboot = tboot_enabled(); - bool enable_sgx; + bool enable_vmx; u64 msr; if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) { clear_cpu_cap(c, X86_FEATURE_VMX); - clear_sgx_caps(); + clear_cpu_cap(c, X86_FEATURE_SGX); return; } - /* - * Enable SGX if and only if the kernel supports SGX and Launch Control - * is supported, i.e. disable SGX if the LE hash MSRs can't be written. - */ - enable_sgx = cpu_has(c, X86_FEATURE_SGX) && - cpu_has(c, X86_FEATURE_SGX_LC) && - IS_ENABLED(CONFIG_X86_SGX); + enable_vmx = cpu_has(c, X86_FEATURE_VMX) && + IS_ENABLED(CONFIG_KVM_INTEL); + + if (cpu_has(c, X86_FEATURE_SGX) && IS_ENABLED(CONFIG_X86_SGX)) { + /* + * Separate out SGX driver enabling from KVM. This allows KVM + * guests to use SGX even if the kernel SGX driver refuses to + * use it. This happens if flexible Launch Control is not + * available. + */ + enable_sgx_driver = cpu_has(c, X86_FEATURE_SGX_LC); + enable_sgx_kvm = enable_vmx && IS_ENABLED(CONFIG_X86_SGX_KVM); + } if (msr & FEAT_CTL_LOCKED) goto update_caps; @@ -142,15 +143,18 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c) * i.e. KVM is enabled, to avoid unnecessarily adding an attack vector * for the kernel, e.g. using VMX to hide malicious code. */ - if (cpu_has(c, X86_FEATURE_VMX) && IS_ENABLED(CONFIG_KVM_INTEL)) { + if (enable_vmx) { msr |= FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; if (tboot) msr |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX; } - if (enable_sgx) - msr |= FEAT_CTL_SGX_ENABLED | FEAT_CTL_SGX_LC_ENABLED; + if (enable_sgx_kvm || enable_sgx_driver) { + msr |= FEAT_CTL_SGX_ENABLED; + if (enable_sgx_driver) + msr |= FEAT_CTL_SGX_LC_ENABLED; + } wrmsrl(MSR_IA32_FEAT_CTL, msr); @@ -173,10 +177,29 @@ update_caps: } update_sgx: - if (!(msr & FEAT_CTL_SGX_ENABLED) || - !(msr & FEAT_CTL_SGX_LC_ENABLED) || !enable_sgx) { - if (enable_sgx) - pr_err_once("SGX disabled by BIOS\n"); - clear_sgx_caps(); + if (!(msr & FEAT_CTL_SGX_ENABLED)) { + if (enable_sgx_kvm || enable_sgx_driver) + pr_err_once("SGX disabled by BIOS.\n"); + clear_cpu_cap(c, X86_FEATURE_SGX); + return; + } + + /* + * VMX feature bit may be cleared due to being disabled in BIOS, + * in which case SGX virtualization cannot be supported either. + */ + if (!cpu_has(c, X86_FEATURE_VMX) && enable_sgx_kvm) { + pr_err_once("SGX virtualization disabled due to lack of VMX.\n"); + enable_sgx_kvm = 0; + } + + if (!(msr & FEAT_CTL_SGX_LC_ENABLED) && enable_sgx_driver) { + if (!enable_sgx_kvm) { + pr_err_once("SGX Launch Control is locked. Disable SGX.\n"); + clear_cpu_cap(c, X86_FEATURE_SGX); + } else { + pr_err_once("SGX Launch Control is locked. Support SGX virtualization only.\n"); + clear_cpu_cap(c, X86_FEATURE_SGX_LC); + } } } diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 0e422a544835..63e381a46153 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -301,7 +301,7 @@ static void early_init_intel(struct cpuinfo_x86 *c) * The operating system must reload CR3 to cause the TLB to be flushed" * * As a result, boot_cpu_has(X86_FEATURE_PGE) in arch/x86/include/asm/tlbflush.h - * should be false so that __flush_tlb_all() causes CR3 insted of CR4.PGE + * should be false so that __flush_tlb_all() causes CR3 instead of CR4.PGE * to be modified. */ if (c->x86 == 5 && c->x86_model == 9) { diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 7962355436da..bf7fe87a7e88 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -529,7 +529,7 @@ static void mce_irq_work_cb(struct irq_work *entry) * Check if the address reported by the CPU is in a format we can parse. * It would be possible to add code for most other cases, but all would * be somewhat complicated (e.g. segment offset would require an instruction - * parser). So only support physical addresses up to page granuality for now. + * parser). So only support physical addresses up to page granularity for now. */ int mce_usable_address(struct mce *m) { diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 7b360731fc2d..4e86d97f9653 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -74,6 +74,7 @@ MCE_INJECT_SET(status); MCE_INJECT_SET(misc); MCE_INJECT_SET(addr); MCE_INJECT_SET(synd); +MCE_INJECT_SET(ipid); #define MCE_INJECT_GET(reg) \ static int inj_##reg##_get(void *data, u64 *val) \ @@ -88,11 +89,13 @@ MCE_INJECT_GET(status); MCE_INJECT_GET(misc); MCE_INJECT_GET(addr); MCE_INJECT_GET(synd); +MCE_INJECT_GET(ipid); DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(ipid_fops, inj_ipid_get, inj_ipid_set, "%llx\n"); static void setup_inj_struct(struct mce *m) { @@ -629,6 +632,8 @@ static const char readme_msg[] = "\t is present in hardware. \n" "\t - \"th\": Trigger APIC interrupt for Threshold errors. Causes threshold \n" "\t APIC interrupt handler to handle the error. \n" +"\n" +"ipid:\t IPID (AMD-specific)\n" "\n"; static ssize_t @@ -652,6 +657,7 @@ static struct dfs_node { { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "synd", .fops = &synd_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "ipid", .fops = &ipid_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 83df991314c5..55ffa84d30d6 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -142,7 +142,7 @@ static struct severity { MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_UC|MCI_STATUS_AR) ), MCESEV( - KEEP, "Non signalled machine check", + KEEP, "Non signaled machine check", SER, BITCLR(MCI_STATUS_S) ), diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b935e1b5f115..6a6318e9590c 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -629,16 +629,16 @@ static ssize_t reload_store(struct device *dev, if (val != 1) return size; - tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); - if (tmp_ret != UCODE_NEW) - return size; - get_online_cpus(); ret = check_online_cpus(); if (ret) goto put; + tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); + if (tmp_ret != UCODE_NEW) + goto put; + mutex_lock(µcode_mutex); ret = microcode_reload_late(); mutex_unlock(µcode_mutex); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e88bc296afca..415bc05d3dc7 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -197,7 +197,7 @@ static unsigned char hv_get_nmi_reason(void) #ifdef CONFIG_X86_LOCAL_APIC /* * Prior to WS2016 Debug-VM sends NMIs to all CPUs which makes - * it dificult to process CHANNELMSG_UNLOAD in case of crash. Handle + * it difficult to process CHANNELMSG_UNLOAD in case of crash. Handle * unknown NMI on the first CPU which gets it. */ static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs) @@ -428,7 +428,7 @@ static void __init ms_hyperv_init_platform(void) /* * Hyper-V doesn't provide irq remapping for IO-APIC. To enable x2apic, - * set x2apic destination mode to physcial mode when x2apic is available + * set x2apic destination mode to physical mode when x2apic is available * and Hyper-V IOMMU driver makes sure cpus assigned with IO-APIC irqs * have 8-bit APIC id. */ diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 9231640782fa..0c3b372318b7 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -434,7 +434,7 @@ set_var_mtrr_range(struct var_mtrr_state *state, unsigned long base_pfn, state->range_sizek = sizek - second_sizek; } -/* Mininum size of mtrr block that can take hole: */ +/* Minimum size of mtrr block that can take hole: */ static u64 mtrr_chunk_size __initdata = (256ULL<<20); static int __init parse_mtrr_chunk_size_opt(char *p) diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 28c8a23aa42e..a76694bffe86 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -799,7 +799,7 @@ void mtrr_ap_init(void) * * This routine is called in two cases: * - * 1. very earily time of software resume, when there absolutely + * 1. very early time of software resume, when there absolutely * isn't mtrr entry changes; * * 2. cpu hotadd time. We let mtrr_add/del_page hold cpuhotplug diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 698bb26aeb6e..23001ae03e82 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -192,7 +192,7 @@ static unsigned int cbm_idx(struct rdt_resource *r, unsigned int closid) * Intel(R) Xeon(R) CPU E5-2608L v3 @ 2.00GHz * Intel(R) Xeon(R) CPU E5-2658A v3 @ 2.20GHz * - * Probe by trying to write the first of the L3 cach mask registers + * Probe by trying to write the first of the L3 cache mask registers * and checking that the bits stick. Max CLOSids is always 4 and max cbm length * is always 20 on hsw server parts. The minimum cache bitmask length * allowed for HSW server is always 2 bits. Hardcode all of them. diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 7ac31210e452..dbeaa8409313 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -387,7 +387,7 @@ void mon_event_count(void *info) * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so * that: * - * current bandwdith(cur_bw) < user specified bandwidth(user_bw) + * current bandwidth(cur_bw) < user specified bandwidth(user_bw) * * This uses the MBM counters to measure the bandwidth and MBA throttle * MSRs to control the bandwidth for a particular rdtgrp. It builds on the @@ -397,7 +397,7 @@ void mon_event_count(void *info) * timer. Having 1s interval makes the calculation of bandwidth simpler. * * Although MBA's goal is to restrict the bandwidth to a maximum, there may - * be a need to increase the bandwidth to avoid uncecessarily restricting + * be a need to increase the bandwidth to avoid unnecessarily restricting * the L2 <-> L3 traffic. * * Since MBA controls the L2 external bandwidth where as MBM measures the @@ -480,7 +480,7 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) /* * Delta values are updated dynamically package wise for each - * rdtgrp everytime the throttle MSR changes value. + * rdtgrp every time the throttle MSR changes value. * * This is because (1)the increase in bandwidth is not perfectly * linear and only "approximately" linear even when the hardware diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index e916646adc69..935af2ac6b1a 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -1307,7 +1307,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) * If the thread does not get on the CPU for whatever * reason and the process which sets up the region is * interrupted then this will leave the thread in runnable - * state and once it gets on the CPU it will derefence + * state and once it gets on the CPU it will dereference * the cleared, but not freed, plr struct resulting in an * empty pseudo-locking loop. */ @@ -1391,7 +1391,7 @@ out: * group is removed from user space via a "rmdir" from userspace or the * unmount of the resctrl filesystem. On removal the resource group does * not go back to pseudo-locksetup mode before it is removed, instead it is - * removed directly. There is thus assymmetry with the creation where the + * removed directly. There is thus asymmetry with the creation where the * &struct pseudo_lock_region is removed here while it was not created in * rdtgroup_pseudo_lock_create(). * diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index f9190adc52cb..01fd30e7829d 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * User interface for Resource Alloction in Resource Director Technology(RDT) + * User interface for Resource Allocation in Resource Director Technology(RDT) * * Copyright (C) 2016 Intel Corporation * @@ -294,7 +294,7 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, /* * This is safe against resctrl_sched_in() called from __switch_to() * because __switch_to() is executed with interrupts disabled. A local call - * from update_closid_rmid() is proteced against __switch_to() because + * from update_closid_rmid() is protected against __switch_to() because * preemption is disabled. */ static void update_cpu_closid_rmid(void *info) @@ -2555,7 +2555,7 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, /* * This creates a directory mon_data which contains the monitored data. * - * mon_data has one directory for each domain whic are named + * mon_data has one directory for each domain which are named * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data * with L3 domain looks as below: * ./mon_data: diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 972ec3bfa9c0..21d1f062895a 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -36,6 +36,8 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_CDP_L2, CPUID_ECX, 2, 0x00000010, 2 }, { X86_FEATURE_MBA, CPUID_EBX, 3, 0x00000010, 0 }, { X86_FEATURE_PER_THREAD_MBA, CPUID_ECX, 0, 0x00000010, 3 }, + { X86_FEATURE_SGX1, CPUID_EAX, 0, 0x00000012, 0 }, + { X86_FEATURE_SGX2, CPUID_EAX, 1, 0x00000012, 0 }, { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, diff --git a/arch/x86/kernel/cpu/sgx/Makefile b/arch/x86/kernel/cpu/sgx/Makefile index 91d3dc784a29..9c1656779b2a 100644 --- a/arch/x86/kernel/cpu/sgx/Makefile +++ b/arch/x86/kernel/cpu/sgx/Makefile @@ -3,3 +3,4 @@ obj-y += \ encl.o \ ioctl.o \ main.o +obj-$(CONFIG_X86_SGX_KVM) += virt.o diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c index 8ce6d8371cfb..aa9b8b868867 100644 --- a/arch/x86/kernel/cpu/sgx/driver.c +++ b/arch/x86/kernel/cpu/sgx/driver.c @@ -136,10 +136,6 @@ static const struct file_operations sgx_encl_fops = { .get_unmapped_area = sgx_get_unmapped_area, }; -const struct file_operations sgx_provision_fops = { - .owner = THIS_MODULE, -}; - static struct miscdevice sgx_dev_enclave = { .minor = MISC_DYNAMIC_MINOR, .name = "sgx_enclave", @@ -147,13 +143,6 @@ static struct miscdevice sgx_dev_enclave = { .fops = &sgx_encl_fops, }; -static struct miscdevice sgx_dev_provision = { - .minor = MISC_DYNAMIC_MINOR, - .name = "sgx_provision", - .nodename = "sgx_provision", - .fops = &sgx_provision_fops, -}; - int __init sgx_drv_init(void) { unsigned int eax, ebx, ecx, edx; @@ -187,11 +176,5 @@ int __init sgx_drv_init(void) if (ret) return ret; - ret = misc_register(&sgx_dev_provision); - if (ret) { - misc_deregister(&sgx_dev_enclave); - return ret; - } - return 0; } diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 7449ef33f081..3be203297988 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -7,7 +7,7 @@ #include <linux/shmem_fs.h> #include <linux/suspend.h> #include <linux/sched/mm.h> -#include "arch.h" +#include <asm/sgx.h> #include "encl.h" #include "encls.h" #include "sgx.h" @@ -78,7 +78,7 @@ static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page, ret = __sgx_encl_eldu(encl_page, epc_page, secs_page); if (ret) { - sgx_free_epc_page(epc_page); + sgx_encl_free_epc_page(epc_page); return ERR_PTR(ret); } @@ -404,7 +404,7 @@ void sgx_encl_release(struct kref *ref) if (sgx_unmark_page_reclaimable(entry->epc_page)) continue; - sgx_free_epc_page(entry->epc_page); + sgx_encl_free_epc_page(entry->epc_page); encl->secs_child_cnt--; entry->epc_page = NULL; } @@ -415,7 +415,7 @@ void sgx_encl_release(struct kref *ref) xa_destroy(&encl->page_array); if (!encl->secs_child_cnt && encl->secs.epc_page) { - sgx_free_epc_page(encl->secs.epc_page); + sgx_encl_free_epc_page(encl->secs.epc_page); encl->secs.epc_page = NULL; } @@ -423,7 +423,7 @@ void sgx_encl_release(struct kref *ref) va_page = list_first_entry(&encl->va_pages, struct sgx_va_page, list); list_del(&va_page->list); - sgx_free_epc_page(va_page->epc_page); + sgx_encl_free_epc_page(va_page->epc_page); kfree(va_page); } @@ -686,7 +686,7 @@ struct sgx_epc_page *sgx_alloc_va_page(void) ret = __epa(sgx_get_epc_virt_addr(epc_page)); if (ret) { WARN_ONCE(1, "EPA returned %d (0x%x)", ret, ret); - sgx_free_epc_page(epc_page); + sgx_encl_free_epc_page(epc_page); return ERR_PTR(-EFAULT); } @@ -735,3 +735,24 @@ bool sgx_va_page_full(struct sgx_va_page *va_page) return slot == SGX_VA_SLOT_COUNT; } + +/** + * sgx_encl_free_epc_page - free an EPC page assigned to an enclave + * @page: EPC page to be freed + * + * Free an EPC page assigned to an enclave. It does EREMOVE for the page, and + * only upon success, it puts the page back to free page list. Otherwise, it + * gives a WARNING to indicate page is leaked. + */ +void sgx_encl_free_epc_page(struct sgx_epc_page *page) +{ + int ret; + + WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED); + + ret = __eremove(sgx_get_epc_virt_addr(page)); + if (WARN_ONCE(ret, EREMOVE_ERROR_MESSAGE, ret, ret)) + return; + + sgx_free_epc_page(page); +} diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h index d8d30ccbef4c..6e74f85b6264 100644 --- a/arch/x86/kernel/cpu/sgx/encl.h +++ b/arch/x86/kernel/cpu/sgx/encl.h @@ -115,5 +115,6 @@ struct sgx_epc_page *sgx_alloc_va_page(void); unsigned int sgx_alloc_va_slot(struct sgx_va_page *va_page); void sgx_free_va_slot(struct sgx_va_page *va_page, unsigned int offset); bool sgx_va_page_full(struct sgx_va_page *va_page); +void sgx_encl_free_epc_page(struct sgx_epc_page *page); #endif /* _X86_ENCL_H */ diff --git a/arch/x86/kernel/cpu/sgx/encls.h b/arch/x86/kernel/cpu/sgx/encls.h index 443188fe7e70..9b204843b78d 100644 --- a/arch/x86/kernel/cpu/sgx/encls.h +++ b/arch/x86/kernel/cpu/sgx/encls.h @@ -11,21 +11,6 @@ #include <asm/traps.h> #include "sgx.h" -enum sgx_encls_function { - ECREATE = 0x00, - EADD = 0x01, - EINIT = 0x02, - EREMOVE = 0x03, - EDGBRD = 0x04, - EDGBWR = 0x05, - EEXTEND = 0x06, - ELDU = 0x08, - EBLOCK = 0x09, - EPA = 0x0A, - EWB = 0x0B, - ETRACK = 0x0C, -}; - /** * ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr * @@ -55,6 +40,19 @@ enum sgx_encls_function { } while (0); \ } +/* + * encls_faulted() - Check if an ENCLS leaf faulted given an error code + * @ret: the return value of an ENCLS leaf function call + * + * Return: + * - true: ENCLS leaf faulted. + * - false: Otherwise. + */ +static inline bool encls_faulted(int ret) +{ + return ret & ENCLS_FAULT_FLAG; +} + /** * encls_failed() - Check if an ENCLS function failed * @ret: the return value of an ENCLS function call @@ -65,7 +63,7 @@ enum sgx_encls_function { */ static inline bool encls_failed(int ret) { - if (ret & ENCLS_FAULT_FLAG) + if (encls_faulted(ret)) return ENCLS_TRAPNR(ret) != X86_TRAP_PF; return !!ret; diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 90a5caf76939..83df20e3e633 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -2,6 +2,7 @@ /* Copyright(c) 2016-20 Intel Corporation. */ #include <asm/mman.h> +#include <asm/sgx.h> #include <linux/mman.h> #include <linux/delay.h> #include <linux/file.h> @@ -47,7 +48,7 @@ static void sgx_encl_shrink(struct sgx_encl *encl, struct sgx_va_page *va_page) encl->page_cnt--; if (va_page) { - sgx_free_epc_page(va_page->epc_page); + sgx_encl_free_epc_page(va_page->epc_page); list_del(&va_page->list); kfree(va_page); } @@ -117,7 +118,7 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs) return 0; err_out: - sgx_free_epc_page(encl->secs.epc_page); + sgx_encl_free_epc_page(encl->secs.epc_page); encl->secs.epc_page = NULL; err_out_backing: @@ -365,7 +366,7 @@ err_out_unlock: mmap_read_unlock(current->mm); err_out_free: - sgx_free_epc_page(epc_page); + sgx_encl_free_epc_page(epc_page); kfree(encl_page); return ret; @@ -495,7 +496,7 @@ static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct, void *token) { u64 mrsigner[4]; - int i, j, k; + int i, j; void *addr; int ret; @@ -544,8 +545,7 @@ static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct, preempt_disable(); - for (k = 0; k < 4; k++) - wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + k, mrsigner[k]); + sgx_update_lepubkeyhash(mrsigner); ret = __einit(sigstruct, token, addr); @@ -568,7 +568,7 @@ static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct, } } - if (ret & ENCLS_FAULT_FLAG) { + if (encls_faulted(ret)) { if (encls_failed(ret)) ENCLS_WARN(ret, "EINIT"); @@ -604,7 +604,6 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg) { struct sgx_sigstruct *sigstruct; struct sgx_enclave_init init_arg; - struct page *initp_page; void *token; int ret; @@ -615,11 +614,15 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg) if (copy_from_user(&init_arg, arg, sizeof(init_arg))) return -EFAULT; - initp_page = alloc_page(GFP_KERNEL); - if (!initp_page) + /* + * 'sigstruct' must be on a page boundary and 'token' on a 512 byte + * boundary. kmalloc() will give this alignment when allocating + * PAGE_SIZE bytes. + */ + sigstruct = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!sigstruct) return -ENOMEM; - sigstruct = kmap(initp_page); token = (void *)((unsigned long)sigstruct + PAGE_SIZE / 2); memset(token, 0, SGX_LAUNCH_TOKEN_SIZE); @@ -645,8 +648,7 @@ static long sgx_ioc_enclave_init(struct sgx_encl *encl, void __user *arg) ret = sgx_encl_init(encl, sigstruct, token); out: - kunmap(initp_page); - __free_page(initp_page); + kfree(sigstruct); return ret; } @@ -665,24 +667,11 @@ out: static long sgx_ioc_enclave_provision(struct sgx_encl *encl, void __user *arg) { struct sgx_enclave_provision params; - struct file *file; if (copy_from_user(¶ms, arg, sizeof(params))) return -EFAULT; - file = fget(params.fd); - if (!file) - return -EINVAL; - - if (file->f_op != &sgx_provision_fops) { - fput(file); - return -EINVAL; - } - - encl->attributes_mask |= SGX_ATTR_PROVISIONKEY; - - fput(file); - return 0; + return sgx_set_attribute(&encl->attributes_mask, params.fd); } long sgx_ioctl(struct file *filep, unsigned int cmd, unsigned long arg) diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 8df81a3ed945..63d3de02bbcc 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -1,14 +1,17 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2016-20 Intel Corporation. */ +#include <linux/file.h> #include <linux/freezer.h> #include <linux/highmem.h> #include <linux/kthread.h> +#include <linux/miscdevice.h> #include <linux/pagemap.h> #include <linux/ratelimit.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> +#include <asm/sgx.h> #include "driver.h" #include "encl.h" #include "encls.h" @@ -23,42 +26,58 @@ static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq); * with sgx_reclaimer_lock acquired. */ static LIST_HEAD(sgx_active_page_list); - static DEFINE_SPINLOCK(sgx_reclaimer_lock); +/* The free page list lock protected variables prepend the lock. */ +static unsigned long sgx_nr_free_pages; + +/* Nodes with one or more EPC sections. */ +static nodemask_t sgx_numa_mask; + +/* + * Array with one list_head for each possible NUMA node. Each + * list contains all the sgx_epc_section's which are on that + * node. + */ +static struct sgx_numa_node *sgx_numa_nodes; + +static LIST_HEAD(sgx_dirty_page_list); + /* - * Reset dirty EPC pages to uninitialized state. Laundry can be left with SECS - * pages whose child pages blocked EREMOVE. + * Reset post-kexec EPC pages to the uninitialized state. The pages are removed + * from the input list, and made available for the page allocator. SECS pages + * prepending their children in the input list are left intact. */ -static void sgx_sanitize_section(struct sgx_epc_section *section) +static void __sgx_sanitize_pages(struct list_head *dirty_page_list) { struct sgx_epc_page *page; LIST_HEAD(dirty); int ret; - /* init_laundry_list is thread-local, no need for a lock: */ - while (!list_empty(§ion->init_laundry_list)) { + /* dirty_page_list is thread-local, no need for a lock: */ + while (!list_empty(dirty_page_list)) { if (kthread_should_stop()) return; - /* needed for access to ->page_list: */ - spin_lock(§ion->lock); - - page = list_first_entry(§ion->init_laundry_list, - struct sgx_epc_page, list); + page = list_first_entry(dirty_page_list, struct sgx_epc_page, list); ret = __eremove(sgx_get_epc_virt_addr(page)); - if (!ret) - list_move(&page->list, §ion->page_list); - else + if (!ret) { + /* + * page is now sanitized. Make it available via the SGX + * page allocator: + */ + list_del(&page->list); + sgx_free_epc_page(page); + } else { + /* The page is not yet clean - move to the dirty list. */ list_move_tail(&page->list, &dirty); - - spin_unlock(§ion->lock); + } cond_resched(); } - list_splice(&dirty, §ion->init_laundry_list); + list_splice(&dirty, dirty_page_list); } static bool sgx_reclaimer_age(struct sgx_epc_page *epc_page) @@ -195,10 +214,10 @@ static const cpumask_t *sgx_encl_ewb_cpumask(struct sgx_encl *encl) /* * Swap page to the regular memory transformed to the blocked state by using - * EBLOCK, which means that it can no loger be referenced (no new TLB entries). + * EBLOCK, which means that it can no longer be referenced (no new TLB entries). * * The first trial just tries to write the page assuming that some other thread - * has reset the count for threads inside the enlave by using ETRACK, and + * has reset the count for threads inside the enclave by using ETRACK, and * previous thread count has been zeroed out. The second trial calls ETRACK * before EWB. If that fails we kick all the HW threads out, and then do EWB, * which should be guaranteed the succeed. @@ -278,7 +297,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page, sgx_encl_ewb(encl->secs.epc_page, &secs_backing); - sgx_free_epc_page(encl->secs.epc_page); + sgx_encl_free_epc_page(encl->secs.epc_page); encl->secs.epc_page = NULL; sgx_encl_put_backing(&secs_backing, true); @@ -308,6 +327,7 @@ static void sgx_reclaim_pages(void) struct sgx_epc_section *section; struct sgx_encl_page *encl_page; struct sgx_epc_page *epc_page; + struct sgx_numa_node *node; pgoff_t page_index; int cnt = 0; int ret; @@ -379,50 +399,33 @@ skip: epc_page->flags &= ~SGX_EPC_PAGE_RECLAIMER_TRACKED; section = &sgx_epc_sections[epc_page->section]; - spin_lock(§ion->lock); - list_add_tail(&epc_page->list, §ion->page_list); - section->free_cnt++; - spin_unlock(§ion->lock); - } -} - -static unsigned long sgx_nr_free_pages(void) -{ - unsigned long cnt = 0; - int i; - - for (i = 0; i < sgx_nr_epc_sections; i++) - cnt += sgx_epc_sections[i].free_cnt; + node = section->node; - return cnt; + spin_lock(&node->lock); + list_add_tail(&epc_page->list, &node->free_page_list); + sgx_nr_free_pages++; + spin_unlock(&node->lock); + } } static bool sgx_should_reclaim(unsigned long watermark) { - return sgx_nr_free_pages() < watermark && - !list_empty(&sgx_active_page_list); + return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list); } static int ksgxd(void *p) { - int i; - set_freezable(); /* * Sanitize pages in order to recover from kexec(). The 2nd pass is * required for SECS pages, whose child pages blocked EREMOVE. */ - for (i = 0; i < sgx_nr_epc_sections; i++) - sgx_sanitize_section(&sgx_epc_sections[i]); - - for (i = 0; i < sgx_nr_epc_sections; i++) { - sgx_sanitize_section(&sgx_epc_sections[i]); + __sgx_sanitize_pages(&sgx_dirty_page_list); + __sgx_sanitize_pages(&sgx_dirty_page_list); - /* Should never happen. */ - if (!list_empty(&sgx_epc_sections[i].init_laundry_list)) - WARN(1, "EPC section %d has unsanitized pages.\n", i); - } + /* sanity check: */ + WARN_ON(!list_empty(&sgx_dirty_page_list)); while (!kthread_should_stop()) { if (try_to_freeze()) @@ -454,45 +457,56 @@ static bool __init sgx_page_reclaimer_init(void) return true; } -static struct sgx_epc_page *__sgx_alloc_epc_page_from_section(struct sgx_epc_section *section) +static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid) { - struct sgx_epc_page *page; + struct sgx_numa_node *node = &sgx_numa_nodes[nid]; + struct sgx_epc_page *page = NULL; - spin_lock(§ion->lock); + spin_lock(&node->lock); - if (list_empty(§ion->page_list)) { - spin_unlock(§ion->lock); + if (list_empty(&node->free_page_list)) { + spin_unlock(&node->lock); return NULL; } - page = list_first_entry(§ion->page_list, struct sgx_epc_page, list); + page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list); list_del_init(&page->list); - section->free_cnt--; + sgx_nr_free_pages--; + + spin_unlock(&node->lock); - spin_unlock(§ion->lock); return page; } /** * __sgx_alloc_epc_page() - Allocate an EPC page * - * Iterate through EPC sections and borrow a free EPC page to the caller. When a - * page is no longer needed it must be released with sgx_free_epc_page(). + * Iterate through NUMA nodes and reserve ia free EPC page to the caller. Start + * from the NUMA node, where the caller is executing. * * Return: - * an EPC page, - * -errno on error + * - an EPC page: A borrowed EPC pages were available. + * - NULL: Out of EPC pages. */ struct sgx_epc_page *__sgx_alloc_epc_page(void) { - struct sgx_epc_section *section; struct sgx_epc_page *page; - int i; + int nid_of_current = numa_node_id(); + int nid = nid_of_current; - for (i = 0; i < sgx_nr_epc_sections; i++) { - section = &sgx_epc_sections[i]; + if (node_isset(nid_of_current, sgx_numa_mask)) { + page = __sgx_alloc_epc_page_from_node(nid_of_current); + if (page) + return page; + } + + /* Fall back to the non-local NUMA nodes: */ + while (true) { + nid = next_node_in(nid, sgx_numa_mask); + if (nid == nid_of_current) + break; - page = __sgx_alloc_epc_page_from_section(section); + page = __sgx_alloc_epc_page_from_node(nid); if (page) return page; } @@ -598,23 +612,22 @@ struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim) * sgx_free_epc_page() - Free an EPC page * @page: an EPC page * - * Call EREMOVE for an EPC page and insert it back to the list of free pages. + * Put the EPC page back to the list of free pages. It's the caller's + * responsibility to make sure that the page is in uninitialized state. In other + * words, do EREMOVE, EWB or whatever operation is necessary before calling + * this function. */ void sgx_free_epc_page(struct sgx_epc_page *page) { struct sgx_epc_section *section = &sgx_epc_sections[page->section]; - int ret; + struct sgx_numa_node *node = section->node; - WARN_ON_ONCE(page->flags & SGX_EPC_PAGE_RECLAIMER_TRACKED); + spin_lock(&node->lock); - ret = __eremove(sgx_get_epc_virt_addr(page)); - if (WARN_ONCE(ret, "EREMOVE returned %d (0x%x)", ret, ret)) - return; + list_add_tail(&page->list, &node->free_page_list); + sgx_nr_free_pages++; - spin_lock(§ion->lock); - list_add_tail(&page->list, §ion->page_list); - section->free_cnt++; - spin_unlock(§ion->lock); + spin_unlock(&node->lock); } static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, @@ -635,18 +648,14 @@ static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, } section->phys_addr = phys_addr; - spin_lock_init(§ion->lock); - INIT_LIST_HEAD(§ion->page_list); - INIT_LIST_HEAD(§ion->init_laundry_list); for (i = 0; i < nr_pages; i++) { section->pages[i].section = index; section->pages[i].flags = 0; section->pages[i].owner = NULL; - list_add_tail(§ion->pages[i].list, §ion->init_laundry_list); + list_add_tail(§ion->pages[i].list, &sgx_dirty_page_list); } - section->free_cnt = nr_pages; return true; } @@ -665,8 +674,13 @@ static bool __init sgx_page_cache_init(void) { u32 eax, ebx, ecx, edx, type; u64 pa, size; + int nid; int i; + sgx_numa_nodes = kmalloc_array(num_possible_nodes(), sizeof(*sgx_numa_nodes), GFP_KERNEL); + if (!sgx_numa_nodes) + return false; + for (i = 0; i < ARRAY_SIZE(sgx_epc_sections); i++) { cpuid_count(SGX_CPUID, i + SGX_CPUID_EPC, &eax, &ebx, &ecx, &edx); @@ -689,6 +703,21 @@ static bool __init sgx_page_cache_init(void) break; } + nid = numa_map_to_online_node(phys_to_target_node(pa)); + if (nid == NUMA_NO_NODE) { + /* The physical address is already printed above. */ + pr_warn(FW_BUG "Unable to map EPC section to online node. Fallback to the NUMA node 0.\n"); + nid = 0; + } + + if (!node_isset(nid, sgx_numa_mask)) { + spin_lock_init(&sgx_numa_nodes[nid].lock); + INIT_LIST_HEAD(&sgx_numa_nodes[nid].free_page_list); + node_set(nid, sgx_numa_mask); + } + + sgx_epc_sections[i].node = &sgx_numa_nodes[nid]; + sgx_nr_epc_sections++; } @@ -700,6 +729,67 @@ static bool __init sgx_page_cache_init(void) return true; } +/* + * Update the SGX_LEPUBKEYHASH MSRs to the values specified by caller. + * Bare-metal driver requires to update them to hash of enclave's signer + * before EINIT. KVM needs to update them to guest's virtual MSR values + * before doing EINIT from guest. + */ +void sgx_update_lepubkeyhash(u64 *lepubkeyhash) +{ + int i; + + WARN_ON_ONCE(preemptible()); + + for (i = 0; i < 4; i++) + wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + i, lepubkeyhash[i]); +} + +const struct file_operations sgx_provision_fops = { + .owner = THIS_MODULE, +}; + +static struct miscdevice sgx_dev_provision = { + .minor = MISC_DYNAMIC_MINOR, + .name = "sgx_provision", + .nodename = "sgx_provision", + .fops = &sgx_provision_fops, +}; + +/** + * sgx_set_attribute() - Update allowed attributes given file descriptor + * @allowed_attributes: Pointer to allowed enclave attributes + * @attribute_fd: File descriptor for specific attribute + * + * Append enclave attribute indicated by file descriptor to allowed + * attributes. Currently only SGX_ATTR_PROVISIONKEY indicated by + * /dev/sgx_provision is supported. + * + * Return: + * -0: SGX_ATTR_PROVISIONKEY is appended to allowed_attributes + * -EINVAL: Invalid, or not supported file descriptor + */ +int sgx_set_attribute(unsigned long *allowed_attributes, + unsigned int attribute_fd) +{ + struct file *file; + + file = fget(attribute_fd); + if (!file) + return -EINVAL; + + if (file->f_op != &sgx_provision_fops) { + fput(file); + return -EINVAL; + } + + *allowed_attributes |= SGX_ATTR_PROVISIONKEY; + + fput(file); + return 0; +} +EXPORT_SYMBOL_GPL(sgx_set_attribute); + static int __init sgx_init(void) { int ret; @@ -716,12 +806,28 @@ static int __init sgx_init(void) goto err_page_cache; } - ret = sgx_drv_init(); + ret = misc_register(&sgx_dev_provision); if (ret) goto err_kthread; + /* + * Always try to initialize the native *and* KVM drivers. + * The KVM driver is less picky than the native one and + * can function if the native one is not supported on the + * current system or fails to initialize. + * + * Error out only if both fail to initialize. + */ + ret = sgx_drv_init(); + + if (sgx_vepc_init() && ret) + goto err_provision; + return 0; +err_provision: + misc_deregister(&sgx_dev_provision); + err_kthread: kthread_stop(ksgxd_tsk); diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h index 5fa42d143feb..4628acec0009 100644 --- a/arch/x86/kernel/cpu/sgx/sgx.h +++ b/arch/x86/kernel/cpu/sgx/sgx.h @@ -8,11 +8,15 @@ #include <linux/rwsem.h> #include <linux/types.h> #include <asm/asm.h> -#include "arch.h" +#include <asm/sgx.h> #undef pr_fmt #define pr_fmt(fmt) "sgx: " fmt +#define EREMOVE_ERROR_MESSAGE \ + "EREMOVE returned %d (0x%x) and an EPC page was leaked. SGX may become unusable. " \ + "Refer to Documentation/x86/sgx.rst for more information." + #define SGX_MAX_EPC_SECTIONS 8 #define SGX_EEXTEND_BLOCK_SIZE 256 #define SGX_NR_TO_SCAN 16 @@ -30,28 +34,25 @@ struct sgx_epc_page { }; /* + * Contains the tracking data for NUMA nodes having EPC pages. Most importantly, + * the free page list local to the node is stored here. + */ +struct sgx_numa_node { + struct list_head free_page_list; + spinlock_t lock; +}; + +/* * The firmware can define multiple chunks of EPC to the different areas of the * physical memory e.g. for memory areas of the each node. This structure is * used to store EPC pages for one EPC section and virtual memory area where * the pages have been mapped. - * - * 'lock' must be held before accessing 'page_list' or 'free_cnt'. */ struct sgx_epc_section { unsigned long phys_addr; void *virt_addr; struct sgx_epc_page *pages; - - spinlock_t lock; - struct list_head page_list; - unsigned long free_cnt; - - /* - * Pages which need EREMOVE run on them before they can be - * used. Only safe to be accessed in ksgxd and init code. - * Not protected by locks. - */ - struct list_head init_laundry_list; + struct sgx_numa_node *node; }; extern struct sgx_epc_section sgx_epc_sections[SGX_MAX_EPC_SECTIONS]; @@ -83,4 +84,15 @@ void sgx_mark_page_reclaimable(struct sgx_epc_page *page); int sgx_unmark_page_reclaimable(struct sgx_epc_page *page); struct sgx_epc_page *sgx_alloc_epc_page(void *owner, bool reclaim); +#ifdef CONFIG_X86_SGX_KVM +int __init sgx_vepc_init(void); +#else +static inline int __init sgx_vepc_init(void) +{ + return -ENODEV; +} +#endif + +void sgx_update_lepubkeyhash(u64 *lepubkeyhash); + #endif /* _X86_SGX_H */ diff --git a/arch/x86/kernel/cpu/sgx/virt.c b/arch/x86/kernel/cpu/sgx/virt.c new file mode 100644 index 000000000000..6ad165a5c0cc --- /dev/null +++ b/arch/x86/kernel/cpu/sgx/virt.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Device driver to expose SGX enclave memory to KVM guests. + * + * Copyright(c) 2021 Intel Corporation. + */ + +#include <linux/miscdevice.h> +#include <linux/mm.h> +#include <linux/mman.h> +#include <linux/sched/mm.h> +#include <linux/sched/signal.h> +#include <linux/slab.h> +#include <linux/xarray.h> +#include <asm/sgx.h> +#include <uapi/asm/sgx.h> + +#include "encls.h" +#include "sgx.h" + +struct sgx_vepc { + struct xarray page_array; + struct mutex lock; +}; + +/* + * Temporary SECS pages that cannot be EREMOVE'd due to having child in other + * virtual EPC instances, and the lock to protect it. + */ +static struct mutex zombie_secs_pages_lock; +static struct list_head zombie_secs_pages; + +static int __sgx_vepc_fault(struct sgx_vepc *vepc, + struct vm_area_struct *vma, unsigned long addr) +{ + struct sgx_epc_page *epc_page; + unsigned long index, pfn; + int ret; + + WARN_ON(!mutex_is_locked(&vepc->lock)); + + /* Calculate index of EPC page in virtual EPC's page_array */ + index = vma->vm_pgoff + PFN_DOWN(addr - vma->vm_start); + + epc_page = xa_load(&vepc->page_array, index); + if (epc_page) + return 0; + + epc_page = sgx_alloc_epc_page(vepc, false); + if (IS_ERR(epc_page)) + return PTR_ERR(epc_page); + + ret = xa_err(xa_store(&vepc->page_array, index, epc_page, GFP_KERNEL)); + if (ret) + goto err_free; + + pfn = PFN_DOWN(sgx_get_epc_phys_addr(epc_page)); + + ret = vmf_insert_pfn(vma, addr, pfn); + if (ret != VM_FAULT_NOPAGE) { + ret = -EFAULT; + goto err_delete; + } + + return 0; + +err_delete: + xa_erase(&vepc->page_array, index); +err_free: + sgx_free_epc_page(epc_page); + return ret; +} + +static vm_fault_t sgx_vepc_fault(struct vm_fault *vmf) +{ + struct vm_area_struct *vma = vmf->vma; + struct sgx_vepc *vepc = vma->vm_private_data; + int ret; + + mutex_lock(&vepc->lock); + ret = __sgx_vepc_fault(vepc, vma, vmf->address); + mutex_unlock(&vepc->lock); + + if (!ret) + return VM_FAULT_NOPAGE; + + if (ret == -EBUSY && (vmf->flags & FAULT_FLAG_ALLOW_RETRY)) { + mmap_read_unlock(vma->vm_mm); + return VM_FAULT_RETRY; + } + + return VM_FAULT_SIGBUS; +} + +static const struct vm_operations_struct sgx_vepc_vm_ops = { + .fault = sgx_vepc_fault, +}; + +static int sgx_vepc_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct sgx_vepc *vepc = file->private_data; + + if (!(vma->vm_flags & VM_SHARED)) + return -EINVAL; + + vma->vm_ops = &sgx_vepc_vm_ops; + /* Don't copy VMA in fork() */ + vma->vm_flags |= VM_PFNMAP | VM_IO | VM_DONTDUMP | VM_DONTCOPY; + vma->vm_private_data = vepc; + + return 0; +} + +static int sgx_vepc_free_page(struct sgx_epc_page *epc_page) +{ + int ret; + + /* + * Take a previously guest-owned EPC page and return it to the + * general EPC page pool. + * + * Guests can not be trusted to have left this page in a good + * state, so run EREMOVE on the page unconditionally. In the + * case that a guest properly EREMOVE'd this page, a superfluous + * EREMOVE is harmless. + */ + ret = __eremove(sgx_get_epc_virt_addr(epc_page)); + if (ret) { + /* + * Only SGX_CHILD_PRESENT is expected, which is because of + * EREMOVE'ing an SECS still with child, in which case it can + * be handled by EREMOVE'ing the SECS again after all pages in + * virtual EPC have been EREMOVE'd. See comments in below in + * sgx_vepc_release(). + * + * The user of virtual EPC (KVM) needs to guarantee there's no + * logical processor is still running in the enclave in guest, + * otherwise EREMOVE will get SGX_ENCLAVE_ACT which cannot be + * handled here. + */ + WARN_ONCE(ret != SGX_CHILD_PRESENT, EREMOVE_ERROR_MESSAGE, + ret, ret); + return ret; + } + + sgx_free_epc_page(epc_page); + + return 0; +} + +static int sgx_vepc_release(struct inode *inode, struct file *file) +{ + struct sgx_vepc *vepc = file->private_data; + struct sgx_epc_page *epc_page, *tmp, *entry; + unsigned long index; + + LIST_HEAD(secs_pages); + + xa_for_each(&vepc->page_array, index, entry) { + /* + * Remove all normal, child pages. sgx_vepc_free_page() + * will fail if EREMOVE fails, but this is OK and expected on + * SECS pages. Those can only be EREMOVE'd *after* all their + * child pages. Retries below will clean them up. + */ + if (sgx_vepc_free_page(entry)) + continue; + + xa_erase(&vepc->page_array, index); + } + + /* + * Retry EREMOVE'ing pages. This will clean up any SECS pages that + * only had children in this 'epc' area. + */ + xa_for_each(&vepc->page_array, index, entry) { + epc_page = entry; + /* + * An EREMOVE failure here means that the SECS page still + * has children. But, since all children in this 'sgx_vepc' + * have been removed, the SECS page must have a child on + * another instance. + */ + if (sgx_vepc_free_page(epc_page)) + list_add_tail(&epc_page->list, &secs_pages); + + xa_erase(&vepc->page_array, index); + } + + /* + * SECS pages are "pinned" by child pages, and "unpinned" once all + * children have been EREMOVE'd. A child page in this instance + * may have pinned an SECS page encountered in an earlier release(), + * creating a zombie. Since some children were EREMOVE'd above, + * try to EREMOVE all zombies in the hopes that one was unpinned. + */ + mutex_lock(&zombie_secs_pages_lock); + list_for_each_entry_safe(epc_page, tmp, &zombie_secs_pages, list) { + /* + * Speculatively remove the page from the list of zombies, + * if the page is successfully EREMOVE'd it will be added to + * the list of free pages. If EREMOVE fails, throw the page + * on the local list, which will be spliced on at the end. + */ + list_del(&epc_page->list); + + if (sgx_vepc_free_page(epc_page)) + list_add_tail(&epc_page->list, &secs_pages); + } + + if (!list_empty(&secs_pages)) + list_splice_tail(&secs_pages, &zombie_secs_pages); + mutex_unlock(&zombie_secs_pages_lock); + + kfree(vepc); + + return 0; +} + +static int sgx_vepc_open(struct inode *inode, struct file *file) +{ + struct sgx_vepc *vepc; + + vepc = kzalloc(sizeof(struct sgx_vepc), GFP_KERNEL); + if (!vepc) + return -ENOMEM; + mutex_init(&vepc->lock); + xa_init(&vepc->page_array); + + file->private_data = vepc; + + return 0; +} + +static const struct file_operations sgx_vepc_fops = { + .owner = THIS_MODULE, + .open = sgx_vepc_open, + .release = sgx_vepc_release, + .mmap = sgx_vepc_mmap, +}; + +static struct miscdevice sgx_vepc_dev = { + .minor = MISC_DYNAMIC_MINOR, + .name = "sgx_vepc", + .nodename = "sgx_vepc", + .fops = &sgx_vepc_fops, +}; + +int __init sgx_vepc_init(void) +{ + /* SGX virtualization requires KVM to work */ + if (!cpu_feature_enabled(X86_FEATURE_VMX)) + return -ENODEV; + + INIT_LIST_HEAD(&zombie_secs_pages); + mutex_init(&zombie_secs_pages_lock); + + return misc_register(&sgx_vepc_dev); +} + +/** + * sgx_virt_ecreate() - Run ECREATE on behalf of guest + * @pageinfo: Pointer to PAGEINFO structure + * @secs: Userspace pointer to SECS page + * @trapnr: trap number injected to guest in case of ECREATE error + * + * Run ECREATE on behalf of guest after KVM traps ECREATE for the purpose + * of enforcing policies of guest's enclaves, and return the trap number + * which should be injected to guest in case of any ECREATE error. + * + * Return: + * - 0: ECREATE was successful. + * - <0: on error. + */ +int sgx_virt_ecreate(struct sgx_pageinfo *pageinfo, void __user *secs, + int *trapnr) +{ + int ret; + + /* + * @secs is an untrusted, userspace-provided address. It comes from + * KVM and is assumed to be a valid pointer which points somewhere in + * userspace. This can fault and call SGX or other fault handlers when + * userspace mapping @secs doesn't exist. + * + * Add a WARN() to make sure @secs is already valid userspace pointer + * from caller (KVM), who should already have handled invalid pointer + * case (for instance, made by malicious guest). All other checks, + * such as alignment of @secs, are deferred to ENCLS itself. + */ + if (WARN_ON_ONCE(!access_ok(secs, PAGE_SIZE))) + return -EINVAL; + + __uaccess_begin(); + ret = __ecreate(pageinfo, (void *)secs); + __uaccess_end(); + + if (encls_faulted(ret)) { + *trapnr = ENCLS_TRAPNR(ret); + return -EFAULT; + } + + /* ECREATE doesn't return an error code, it faults or succeeds. */ + WARN_ON_ONCE(ret); + return 0; +} +EXPORT_SYMBOL_GPL(sgx_virt_ecreate); + +static int __sgx_virt_einit(void __user *sigstruct, void __user *token, + void __user *secs) +{ + int ret; + + /* + * Make sure all userspace pointers from caller (KVM) are valid. + * All other checks deferred to ENCLS itself. Also see comment + * for @secs in sgx_virt_ecreate(). + */ +#define SGX_EINITTOKEN_SIZE 304 + if (WARN_ON_ONCE(!access_ok(sigstruct, sizeof(struct sgx_sigstruct)) || + !access_ok(token, SGX_EINITTOKEN_SIZE) || + !access_ok(secs, PAGE_SIZE))) + return -EINVAL; + + __uaccess_begin(); + ret = __einit((void *)sigstruct, (void *)token, (void *)secs); + __uaccess_end(); + + return ret; +} + +/** + * sgx_virt_einit() - Run EINIT on behalf of guest + * @sigstruct: Userspace pointer to SIGSTRUCT structure + * @token: Userspace pointer to EINITTOKEN structure + * @secs: Userspace pointer to SECS page + * @lepubkeyhash: Pointer to guest's *virtual* SGX_LEPUBKEYHASH MSR values + * @trapnr: trap number injected to guest in case of EINIT error + * + * Run EINIT on behalf of guest after KVM traps EINIT. If SGX_LC is available + * in host, SGX driver may rewrite the hardware values at wish, therefore KVM + * needs to update hardware values to guest's virtual MSR values in order to + * ensure EINIT is executed with expected hardware values. + * + * Return: + * - 0: EINIT was successful. + * - <0: on error. + */ +int sgx_virt_einit(void __user *sigstruct, void __user *token, + void __user *secs, u64 *lepubkeyhash, int *trapnr) +{ + int ret; + + if (!cpu_feature_enabled(X86_FEATURE_SGX_LC)) { + ret = __sgx_virt_einit(sigstruct, token, secs); + } else { + preempt_disable(); + + sgx_update_lepubkeyhash(lepubkeyhash); + + ret = __sgx_virt_einit(sigstruct, token, secs); + preempt_enable(); + } + + /* Propagate up the error from the WARN_ON_ONCE in __sgx_virt_einit() */ + if (ret == -EINVAL) + return ret; + + if (encls_faulted(ret)) { + *trapnr = ENCLS_TRAPNR(ret); + return -EFAULT; + } + + return ret; +} +EXPORT_SYMBOL_GPL(sgx_virt_einit); diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 8678864ce712..132a2de44d2f 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -30,7 +30,7 @@ EXPORT_SYMBOL(__max_die_per_package); #ifdef CONFIG_SMP /* - * Check if given CPUID extended toplogy "leaf" is implemented + * Check if given CPUID extended topology "leaf" is implemented */ static int check_extended_topology_leaf(int leaf) { @@ -44,7 +44,7 @@ static int check_extended_topology_leaf(int leaf) return 0; } /* - * Return best CPUID Extended Toplogy Leaf supported + * Return best CPUID Extended Topology Leaf supported */ static int detect_extended_topology_leaf(struct cpuinfo_x86 *c) { diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index c6ede3b3d302..c04b933f48d3 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -27,6 +27,7 @@ #include <linux/clocksource.h> #include <linux/cpu.h> #include <linux/reboot.h> +#include <linux/static_call.h> #include <asm/div64.h> #include <asm/x86_init.h> #include <asm/hypervisor.h> @@ -336,11 +337,11 @@ static void __init vmware_paravirt_ops_setup(void) vmware_cyc2ns_setup(); if (vmw_sched_clock) - pv_ops.time.sched_clock = vmware_sched_clock; + paravirt_set_sched_clock(vmware_sched_clock); if (vmware_is_stealclock_available()) { has_steal_clock = true; - pv_ops.time.steal_clock = vmware_steal_clock; + static_call_update(pv_steal_clock, vmware_steal_clock); /* We use reboot notifier only to disable steal clock */ register_reboot_notifier(&vmware_pv_reboot_nb); @@ -378,6 +379,8 @@ static void __init vmware_set_capabilities(void) { setup_force_cpu_cap(X86_FEATURE_CONSTANT_TSC); setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); + if (vmware_tsc_khz) + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMCALL) setup_force_cpu_cap(X86_FEATURE_VMCALL); else if (vmware_hypercall_mode == CPUID_VMWARE_FEATURES_ECX_VMMCALL) diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index a8f3af257e26..b1deacbeb266 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -337,7 +337,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) struct crash_memmap_data cmd; struct crash_mem *cmem; - cmem = vzalloc(sizeof(struct crash_mem)); + cmem = vzalloc(struct_size(cmem, ranges, 1)); if (!cmem) return -ENOMEM; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 22aad412f965..f74cb7da9557 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -793,7 +793,7 @@ core_initcall(e820__register_nvs_regions); #endif /* - * Allocate the requested number of bytes with the requsted alignment + * Allocate the requested number of bytes with the requested alignment * and return (the physical address) to the caller. Also register this * range in the 'kexec' E820 table as a reserved range. * diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 683749b80ae2..a85c64000218 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -253,7 +253,7 @@ static bool xfeature_enabled(enum xfeature xfeature) static void __init setup_xstate_features(void) { u32 eax, ebx, ecx, edx, i; - /* start at the beginnning of the "extended state" */ + /* start at the beginning of the "extended state" */ unsigned int last_good_offset = offsetof(struct xregs_state, extended_state_area); /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 5e9beb77cafd..18be44163a50 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -104,7 +104,7 @@ static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr) static bool __head check_la57_support(unsigned long physaddr) { /* - * 5-level paging is detected and enabled at kernel decomression + * 5-level paging is detected and enabled at kernel decompression * stage. Only check if it has been enabled there. */ if (!(native_read_cr4() & X86_CR4_LA57)) diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index ee1a283f8e96..d552f177eca0 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -245,7 +245,7 @@ static const __initconst struct idt_data ist_idts[] = { * after that. * * Note, that X86_64 cannot install the real #PF handler in - * idt_setup_early_traps() because the memory intialization needs the #PF + * idt_setup_early_traps() because the memory initialization needs the #PF * handler from the early_idt_handler_array to initialize the early page * tables. */ diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 58aa712973ac..e28f6a5d14f1 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -338,7 +338,7 @@ void fixup_irqs(void) irq_migrate_all_off_this_cpu(); /* - * We can remove mdelay() and then send spuriuous interrupts to + * We can remove mdelay() and then send spurious interrupts to * new cpu targets for all the irqs that were handled previously by * this cpu. While it works, I have seen spurious interrupt messages * (nothing wrong but still...). diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index ff7878df96b4..3a43a2dee658 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -17,7 +17,7 @@ * Updated by: Tom Rini <trini@kernel.crashing.org> * Updated by: Jason Wessel <jason.wessel@windriver.com> * Modified for 386 by Jim Kingdon, Cygnus Support. - * Origianl kgdb, compatibility with 2.1.xx kernel by + * Original kgdb, compatibility with 2.1.xx kernel by * David Grothe <dave@gcom.com> * Integrated into 2.2.5 kernel by Tigran Aivazian <tigran@sco.com> * X86_64 changes from Andi Kleen's patch merged by Jim Houston @@ -642,7 +642,7 @@ void kgdb_arch_late(void) struct perf_event **pevent; /* - * Pre-allocate the hw breakpoint structions in the non-atomic + * Pre-allocate the hw breakpoint instructions in the non-atomic * portion of kgdb because this operation requires mutexs to * complete. */ diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 51c7f5271aee..596de2f6d3a5 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -12,7 +12,7 @@ #include "common.h" -/* Ftrace callback handler for kprobes -- called under preepmt disabled */ +/* Ftrace callback handler for kprobes -- called under preempt disabled */ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *ops, struct ftrace_regs *fregs) { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 78bb0fae3982..172c947240b9 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -650,7 +650,7 @@ static void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) { has_steal_clock = 1; - pv_ops.time.steal_clock = kvm_steal_clock; + static_call_update(pv_steal_clock, kvm_steal_clock); } if (pv_tlb_flush_supported()) { diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 1fc0962c89c0..d37ed4e1d033 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -106,7 +106,7 @@ static inline void kvm_sched_clock_init(bool stable) if (!stable) clear_sched_clock_stable(); kvm_sched_clock_offset = kvm_clock_read(); - pv_ops.time.sched_clock = kvm_sched_clock_read; + paravirt_set_sched_clock(kvm_sched_clock_read); pr_info("kvm-clock: using sched offset of %llu cycles", kvm_sched_clock_offset); diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index a29a44a98e5b..f01cd9a08155 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -260,7 +260,7 @@ static void set_idt(void *newidt, u16 limit) { struct desc_ptr curidt; - /* x86-64 supports unaliged loads & stores */ + /* x86-64 supports unaligned loads & stores */ curidt.size = limit; curidt.address = (unsigned long)newidt; diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 4f75d0cf6305..9e1ea99ad9df 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -32,3 +32,12 @@ bool pv_is_native_vcpu_is_preempted(void) return pv_ops.lock.vcpu_is_preempted.func == __raw_callee_save___native_vcpu_is_preempted; } + +void __init paravirt_set_cap(void) +{ + if (!pv_is_native_spin_unlock()) + setup_force_cpu_cap(X86_FEATURE_PVUNLOCK); + + if (!pv_is_native_vcpu_is_preempted()) + setup_force_cpu_cap(X86_FEATURE_VCPUPREEMPT); +} diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index c60222ab8ab9..d0730264786b 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -14,6 +14,7 @@ #include <linux/highmem.h> #include <linux/kprobes.h> #include <linux/pgtable.h> +#include <linux/static_call.h> #include <asm/bug.h> #include <asm/paravirt.h> @@ -52,7 +53,10 @@ void __init default_banner(void) } /* Undefined instruction for dealing with missing ops pointers. */ -static const unsigned char ud2a[] = { 0x0f, 0x0b }; +static void paravirt_BUG(void) +{ + BUG(); +} struct branch { unsigned char opcode; @@ -85,25 +89,6 @@ u64 notrace _paravirt_ident_64(u64 x) { return x; } - -static unsigned paravirt_patch_jmp(void *insn_buff, const void *target, - unsigned long addr, unsigned len) -{ - struct branch *b = insn_buff; - unsigned long delta = (unsigned long)target - (addr+5); - - if (len < 5) { -#ifdef CONFIG_RETPOLINE - WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr); -#endif - return len; /* call too long for patch site */ - } - - b->opcode = 0xe9; /* jmp */ - b->delta = delta; - - return 5; -} #endif DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); @@ -114,8 +99,8 @@ void __init native_pv_lock_init(void) static_branch_disable(&virt_spin_lock_key); } -unsigned paravirt_patch_default(u8 type, void *insn_buff, - unsigned long addr, unsigned len) +unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, + unsigned int len) { /* * Neat trick to map patch type back to the call within the @@ -125,20 +110,10 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff, unsigned ret; if (opfunc == NULL) - /* If there's no function, patch it with a ud2a (BUG) */ - ret = paravirt_patch_insns(insn_buff, len, ud2a, ud2a+sizeof(ud2a)); + /* If there's no function, patch it with paravirt_BUG() */ + ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len); else if (opfunc == _paravirt_nop) ret = 0; - -#ifdef CONFIG_PARAVIRT_XXL - /* identity functions just return their single argument */ - else if (opfunc == _paravirt_ident_64) - ret = paravirt_patch_ident_64(insn_buff, len); - - else if (type == PARAVIRT_PATCH(cpu.iret)) - /* If operation requires a jmp, then jmp */ - ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len); -#endif else /* Otherwise call the function. */ ret = paravirt_patch_call(insn_buff, opfunc, addr, len); @@ -146,19 +121,6 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff, return ret; } -unsigned paravirt_patch_insns(void *insn_buff, unsigned len, - const char *start, const char *end) -{ - unsigned insn_len = end - start; - - /* Alternative instruction is too large for the patch site and we cannot continue: */ - BUG_ON(insn_len > len || start == NULL); - - memcpy(insn_buff, start, insn_len); - - return insn_len; -} - struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; @@ -167,6 +129,14 @@ static u64 native_steal_clock(int cpu) return 0; } +DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); +DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock); + +void paravirt_set_sched_clock(u64 (*func)(void)) +{ + static_call_update(pv_sched_clock, func); +} + /* These are in entry.S */ extern void native_iret(void); @@ -269,13 +239,6 @@ struct pv_info pv_info = { #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_64) struct paravirt_patch_template pv_ops = { - /* Init ops. */ - .init.patch = native_patch, - - /* Time ops. */ - .time.sched_clock = native_sched_clock, - .time.steal_clock = native_steal_clock, - /* Cpu ops. */ .cpu.io_delay = native_io_delay, @@ -308,8 +271,6 @@ struct paravirt_patch_template pv_ops = { .cpu.load_sp0 = native_load_sp0, - .cpu.iret = native_iret, - #ifdef CONFIG_X86_IOPL_IOPERM .cpu.invalidate_io_bitmap = native_tss_invalidate_io_bitmap, .cpu.update_io_bitmap = native_tss_update_io_bitmap, @@ -414,6 +375,8 @@ struct paravirt_patch_template pv_ops = { NOKPROBE_SYMBOL(native_get_debugreg); NOKPROBE_SYMBOL(native_set_debugreg); NOKPROBE_SYMBOL(native_load_idt); + +void (*paravirt_iret)(void) = native_iret; #endif EXPORT_SYMBOL(pv_ops); diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c deleted file mode 100644 index abd27ec67397..000000000000 --- a/arch/x86/kernel/paravirt_patch.c +++ /dev/null @@ -1,99 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/stringify.h> - -#include <asm/paravirt.h> -#include <asm/asm-offsets.h> - -#define PSTART(d, m) \ - patch_data_##d.m - -#define PEND(d, m) \ - (PSTART(d, m) + sizeof(patch_data_##d.m)) - -#define PATCH(d, m, insn_buff, len) \ - paravirt_patch_insns(insn_buff, len, PSTART(d, m), PEND(d, m)) - -#define PATCH_CASE(ops, m, data, insn_buff, len) \ - case PARAVIRT_PATCH(ops.m): \ - return PATCH(data, ops##_##m, insn_buff, len) - -#ifdef CONFIG_PARAVIRT_XXL -struct patch_xxl { - const unsigned char irq_irq_disable[1]; - const unsigned char irq_irq_enable[1]; - const unsigned char irq_save_fl[2]; - const unsigned char mmu_read_cr2[3]; - const unsigned char mmu_read_cr3[3]; - const unsigned char mmu_write_cr3[3]; - const unsigned char cpu_wbinvd[2]; - const unsigned char mov64[3]; -}; - -static const struct patch_xxl patch_data_xxl = { - .irq_irq_disable = { 0xfa }, // cli - .irq_irq_enable = { 0xfb }, // sti - .irq_save_fl = { 0x9c, 0x58 }, // pushf; pop %[re]ax - .mmu_read_cr2 = { 0x0f, 0x20, 0xd0 }, // mov %cr2, %[re]ax - .mmu_read_cr3 = { 0x0f, 0x20, 0xd8 }, // mov %cr3, %[re]ax - .mmu_write_cr3 = { 0x0f, 0x22, 0xdf }, // mov %rdi, %cr3 - .cpu_wbinvd = { 0x0f, 0x09 }, // wbinvd - .mov64 = { 0x48, 0x89, 0xf8 }, // mov %rdi, %rax -}; - -unsigned int paravirt_patch_ident_64(void *insn_buff, unsigned int len) -{ - return PATCH(xxl, mov64, insn_buff, len); -} -# endif /* CONFIG_PARAVIRT_XXL */ - -#ifdef CONFIG_PARAVIRT_SPINLOCKS -struct patch_lock { - unsigned char queued_spin_unlock[3]; - unsigned char vcpu_is_preempted[2]; -}; - -static const struct patch_lock patch_data_lock = { - .vcpu_is_preempted = { 0x31, 0xc0 }, // xor %eax, %eax - -# ifdef CONFIG_X86_64 - .queued_spin_unlock = { 0xc6, 0x07, 0x00 }, // movb $0, (%rdi) -# else - .queued_spin_unlock = { 0xc6, 0x00, 0x00 }, // movb $0, (%eax) -# endif -}; -#endif /* CONFIG_PARAVIRT_SPINLOCKS */ - -unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr, - unsigned int len) -{ - switch (type) { - -#ifdef CONFIG_PARAVIRT_XXL - PATCH_CASE(irq, save_fl, xxl, insn_buff, len); - PATCH_CASE(irq, irq_enable, xxl, insn_buff, len); - PATCH_CASE(irq, irq_disable, xxl, insn_buff, len); - - PATCH_CASE(mmu, read_cr2, xxl, insn_buff, len); - PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len); - PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len); - - PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len); -#endif - -#ifdef CONFIG_PARAVIRT_SPINLOCKS - case PARAVIRT_PATCH(lock.queued_spin_unlock): - if (pv_is_native_spin_unlock()) - return PATCH(lock, queued_spin_unlock, insn_buff, len); - break; - - case PARAVIRT_PATCH(lock.vcpu_is_preempted): - if (pv_is_native_vcpu_is_preempted()) - return PATCH(lock, vcpu_is_preempted, insn_buff, len); - break; -#endif - default: - break; - } - - return paravirt_patch_default(type, insn_buff, addr, len); -} diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 9c214d7085a4..43cbfc84153a 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -63,14 +63,9 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = { */ .sp0 = (1UL << (BITS_PER_LONG-1)) + 1, - /* - * .sp1 is cpu_current_top_of_stack. The init task never - * runs user code, but cpu_current_top_of_stack should still - * be well defined before the first context switch. - */ +#ifdef CONFIG_X86_32 .sp1 = TOP_OF_INIT_STACK, -#ifdef CONFIG_X86_32 .ss0 = __KERNEL_DS, .ss1 = __KERNEL_CS, #endif @@ -451,7 +446,7 @@ void speculative_store_bypass_ht_init(void) * First HT sibling to come up on the core. Link shared state of * the first HT sibling to itself. The siblings on the same core * which come up later will see the shared state pointer and link - * themself to the state of this CPU. + * themselves to the state of this CPU. */ st->shared_state = st; } diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 11065dc03f5b..eda37df016f0 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -89,7 +89,7 @@ u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src) /* * Assumption here is that last_value, a global accumulator, always goes * forward. If we are less than that, we should not be much smaller. - * We assume there is an error marging we're inside, and then the correction + * We assume there is an error margin we're inside, and then the correction * does not sacrifice accuracy. * * For reads: global may have changed between test and return, diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index 94b33885f8d2..f469153eca8a 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -107,7 +107,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) * - Write protect disabled * - No task switch * - Don't do FP software emulation. - * - Proctected mode enabled + * - Protected mode enabled */ movl %cr0, %eax andl $~(X86_CR0_PG | X86_CR0_AM | X86_CR0_WP | X86_CR0_TS | X86_CR0_EM), %eax diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index a4d9a261425b..c53271aebb64 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -121,7 +121,7 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped) * - Write protect disabled * - No task switch * - Don't do FP software emulation. - * - Proctected mode enabled + * - Protected mode enabled */ movq %cr0, %rax andq $~(X86_CR0_AM | X86_CR0_WP | X86_CR0_TS | X86_CR0_EM), %rax diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d883176ef2ce..69757fac7462 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -65,7 +65,7 @@ RESERVE_BRK(dmi_alloc, 65536); /* * Range of the BSS area. The size of the BSS area is determined - * at link time, with RESERVE_BRK*() facility reserving additional + * at link time, with RESERVE_BRK() facility reserving additional * chunks. */ unsigned long _brk_start = (unsigned long)__brk_base; @@ -633,11 +633,16 @@ static void __init trim_snb_memory(void) printk(KERN_DEBUG "reserving inaccessible SNB gfx pages\n"); /* - * Reserve all memory below the 1 MB mark that has not - * already been reserved. + * SandyBridge integrated graphics devices have a bug that prevents + * them from accessing certain memory ranges, namely anything below + * 1M and in the pages listed in bad_pages[] above. + * + * To avoid these pages being ever accessed by SNB gfx devices + * reserve all memory below the 1 MB mark and bad_pages that have + * not already been reserved at boot time. */ memblock_reserve(0, 1<<20); - + for (i = 0; i < ARRAY_SIZE(bad_pages); i++) { if (memblock_reserve(bad_pages[i], PAGE_SIZE)) printk(KERN_WARNING "failed to reserve 0x%08lx\n", @@ -645,18 +650,6 @@ static void __init trim_snb_memory(void) } } -/* - * Here we put platform-specific memory range workarounds, i.e. - * memory known to be corrupt or otherwise in need to be reserved on - * specific platforms. - * - * If this gets used more widely it could use a real dispatch mechanism. - */ -static void __init trim_platform_memory_ranges(void) -{ - trim_snb_memory(); -} - static void __init trim_bios_range(void) { /* @@ -725,11 +718,41 @@ static int __init parse_reservelow(char *p) early_param("reservelow", parse_reservelow); -static void __init trim_low_memory_range(void) +static void __init early_reserve_memory(void) { + /* + * Reserve the memory occupied by the kernel between _text and + * __end_of_kernel_reserve symbols. Any kernel sections after the + * __end_of_kernel_reserve symbol must be explicitly reserved with a + * separate memblock_reserve() or they will be discarded. + */ + memblock_reserve(__pa_symbol(_text), + (unsigned long)__end_of_kernel_reserve - (unsigned long)_text); + + /* + * The first 4Kb of memory is a BIOS owned area, but generally it is + * not listed as such in the E820 table. + * + * Reserve the first memory page and typically some additional + * memory (64KiB by default) since some BIOSes are known to corrupt + * low memory. See the Kconfig help text for X86_RESERVE_LOW. + * + * In addition, make sure page 0 is always reserved because on + * systems with L1TF its contents can be leaked to user processes. + */ memblock_reserve(0, ALIGN(reserve_low, PAGE_SIZE)); + + early_reserve_initrd(); + + if (efi_enabled(EFI_BOOT)) + efi_memblock_x86_reserve_range(); + + memblock_x86_reserve_range_setup_data(); + + reserve_ibft_region(); + reserve_bios_regions(); } - + /* * Dump out kernel offset information on panic. */ @@ -764,29 +787,6 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) void __init setup_arch(char **cmdline_p) { - /* - * Reserve the memory occupied by the kernel between _text and - * __end_of_kernel_reserve symbols. Any kernel sections after the - * __end_of_kernel_reserve symbol must be explicitly reserved with a - * separate memblock_reserve() or they will be discarded. - */ - memblock_reserve(__pa_symbol(_text), - (unsigned long)__end_of_kernel_reserve - (unsigned long)_text); - - /* - * Make sure page 0 is always reserved because on systems with - * L1TF its contents can be leaked to user processes. - */ - memblock_reserve(0, PAGE_SIZE); - - early_reserve_initrd(); - - /* - * At this point everything still needed from the boot loader - * or BIOS or kernel text should be early reserved or marked not - * RAM in e820. All other memory is free game. - */ - #ifdef CONFIG_X86_32 memcpy(&boot_cpu_data, &new_cpu_data, sizeof(new_cpu_data)); @@ -910,8 +910,18 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); - if (efi_enabled(EFI_BOOT)) - efi_memblock_x86_reserve_range(); + /* + * Do some memory reservations *before* memory is added to + * memblock, so memblock allocations won't overwrite it. + * Do it after early param, so we could get (unlikely) panic from + * serial. + * + * After this point everything still needed from the boot loader or + * firmware or kernel text should be early reserved or marked not + * RAM in e820. All other memory is free game. + */ + early_reserve_memory(); + #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux @@ -938,9 +948,6 @@ void __init setup_arch(char **cmdline_p) x86_report_nx(); - /* after early param, so could get panic from serial */ - memblock_x86_reserve_range_setup_data(); - if (acpi_mps_check()) { #ifdef CONFIG_X86_LOCAL_APIC disable_apic = 1; @@ -1032,14 +1039,12 @@ void __init setup_arch(char **cmdline_p) */ find_smp_config(); - reserve_ibft_region(); - early_alloc_pgt_buf(); /* * Need to conclude brk, before e820__memblock_setup() - * it could use memblock_find_in_range, could overlap with - * brk area. + * it could use memblock_find_in_range, could overlap with + * brk area. */ reserve_brk(); @@ -1054,8 +1059,6 @@ void __init setup_arch(char **cmdline_p) */ sev_setup_arch(); - reserve_bios_regions(); - efi_fake_memmap(); efi_find_mirror(); efi_esrt_init(); @@ -1081,8 +1084,12 @@ void __init setup_arch(char **cmdline_p) reserve_real_mode(); - trim_platform_memory_ranges(); - trim_low_memory_range(); + /* + * Reserving memory causing GPU hangs on Sandy Bridge integrated + * graphics devices should be done after we allocated memory under + * 1M for the real mode trampoline. + */ + trim_snb_memory(); init_mem_mapping(); @@ -1129,6 +1136,8 @@ void __init setup_arch(char **cmdline_p) reserve_initrd(); acpi_table_upgrade(); + /* Look for ACPI tables and reserve memory occupied by them. */ + acpi_boot_table_init(); vsmp_init(); @@ -1136,11 +1145,6 @@ void __init setup_arch(char **cmdline_p) early_platform_quirks(); - /* - * Parse the ACPI tables for possible boot-time SMP configuration. - */ - acpi_boot_table_init(); - early_acpi_boot_init(); initmem_init(); diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index cdc04d091242..0aa9f13efd57 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -24,7 +24,7 @@ static bool __init sev_es_check_cpu_features(void) return true; } -static void sev_es_terminate(unsigned int reason) +static void __noreturn sev_es_terminate(unsigned int reason) { u64 val = GHCB_SEV_TERMINATE; @@ -186,7 +186,6 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) * make it accessible to the hypervisor. * * In particular, check for: - * - Hypervisor CPUID bit * - Availability of CPUID leaf 0x8000001f * - SEV CPUID bit. * @@ -194,10 +193,7 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) * can't be checked here. */ - if ((fn == 1 && !(regs->cx & BIT(31)))) - /* Hypervisor bit */ - goto fail; - else if (fn == 0x80000000 && (regs->ax < 0x8000001f)) + if (fn == 0x80000000 && (regs->ax < 0x8000001f)) /* SEV leaf check */ goto fail; else if ((fn == 0x8000001f && !(regs->ax & BIT(1)))) @@ -210,12 +206,8 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) return; fail: - sev_es_wr_ghcb_msr(GHCB_SEV_TERMINATE); - VMGEXIT(); - - /* Shouldn't get here - if we do halt the machine */ - while (true) - asm volatile("hlt\n"); + /* Terminate the guest */ + sev_es_terminate(GHCB_SEV_ES_REASON_GENERAL_REQUEST); } static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 04a780abb512..26f5479a97a8 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -137,29 +137,41 @@ static __always_inline bool on_vc_stack(struct pt_regs *regs) } /* - * This function handles the case when an NMI is raised in the #VC exception - * handler entry code. In this case, the IST entry for #VC must be adjusted, so - * that any subsequent #VC exception will not overwrite the stack contents of the - * interrupted #VC handler. + * This function handles the case when an NMI is raised in the #VC + * exception handler entry code, before the #VC handler has switched off + * its IST stack. In this case, the IST entry for #VC must be adjusted, + * so that any nested #VC exception will not overwrite the stack + * contents of the interrupted #VC handler. * * The IST entry is adjusted unconditionally so that it can be also be - * unconditionally adjusted back in sev_es_ist_exit(). Otherwise a nested - * sev_es_ist_exit() call may adjust back the IST entry too early. + * unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a + * nested sev_es_ist_exit() call may adjust back the IST entry too + * early. + * + * The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run + * on the NMI IST stack, as they are only called from NMI handling code + * right now. */ void noinstr __sev_es_ist_enter(struct pt_regs *regs) { unsigned long old_ist, new_ist; /* Read old IST entry */ - old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]); + new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]); - /* Make room on the IST stack */ + /* + * If NMI happened while on the #VC IST stack, set the new IST + * value below regs->sp, so that the interrupted stack frame is + * not overwritten by subsequent #VC exceptions. + */ if (on_vc_stack(regs)) - new_ist = ALIGN_DOWN(regs->sp, 8) - sizeof(old_ist); - else - new_ist = old_ist - sizeof(old_ist); + new_ist = regs->sp; - /* Store old IST entry */ + /* + * Reserve additional 8 bytes and store old IST value so this + * adjustment can be unrolled in __sev_es_ist_exit(). + */ + new_ist -= sizeof(old_ist); *(unsigned long *)new_ist = old_ist; /* Set new IST entry */ @@ -277,7 +289,7 @@ static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt) return ES_EXCEPTION; } - insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE - res, 1); + insn_init(&ctxt->insn, buffer, MAX_INSN_SIZE, 1); insn_get_length(&ctxt->insn); } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index f306e85a08a6..a06cb107c0e8 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -492,7 +492,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, * SS descriptor, but we do need SS to be valid. It's possible * that the old SS is entirely bogus -- this can happen if the * signal we're trying to deliver is #GP or #SS caused by a bad - * SS value. We also have a compatbility issue here: DOSEMU + * SS value. We also have a compatibility issue here: DOSEMU * relies on the contents of the SS register indicating the * SS value at the time of the signal, even though that code in * DOSEMU predates sigreturn's ability to restore SS. (DOSEMU diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index eff4ce3b10da..06db901fabe8 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -67,7 +67,7 @@ * 5AP. symmetric IO mode (normal Linux operation) not affected. * 'noapic' mode has vector 0xf filled out properly. * 6AP. 'noapic' mode might be affected - fixed in later steppings - * 7AP. We do not assume writes to the LVT deassering IRQs + * 7AP. We do not assume writes to the LVT deasserting IRQs * 8AP. We do not enable low power mode (deep sleep) during MP bootup * 9AP. We do not use mixed mode * @@ -204,7 +204,7 @@ static void native_stop_other_cpus(int wait) } /* * Don't wait longer than 10 ms if the caller didn't - * reqeust it. If wait is true, the machine hangs here if + * request it. If wait is true, the machine hangs here if * one or more CPUs do not reach shutdown state. */ timeout = USEC_PER_MSEC * 10; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 02813a7f3a7c..1e2050c4f94a 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1407,7 +1407,7 @@ void __init calculate_max_logical_packages(void) int ncpus; /* - * Today neither Intel nor AMD support heterogenous systems so + * Today neither Intel nor AMD support heterogeneous systems so * extrapolate the boot cpu's data to all packages. */ ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); @@ -1659,13 +1659,17 @@ void play_dead_common(void) local_irq_disable(); } -static bool wakeup_cpu0(void) +/** + * cond_wakeup_cpu0 - Wake up CPU0 if needed. + * + * If NMI wants to wake up CPU0, start CPU0. + */ +void cond_wakeup_cpu0(void) { if (smp_processor_id() == 0 && enable_start_cpu0) - return true; - - return false; + start_cpu0(); } +EXPORT_SYMBOL_GPL(cond_wakeup_cpu0); /* * We need to flush the caches before going to sleep, lest we have @@ -1734,11 +1738,8 @@ static inline void mwait_play_dead(void) __monitor(mwait_ptr, 0, 0); mb(); __mwait(eax, 0); - /* - * If NMI wants to wake up CPU0, start CPU0. - */ - if (wakeup_cpu0()) - start_cpu0(); + + cond_wakeup_cpu0(); } } @@ -1749,11 +1750,8 @@ void hlt_play_dead(void) while (1) { native_halt(); - /* - * If NMI wants to wake up CPU0, start CPU0. - */ - if (wakeup_cpu0()) - start_cpu0(); + + cond_wakeup_cpu0(); } } diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c index 8627fda8d993..15b058eefc4e 100644 --- a/arch/x86/kernel/stacktrace.c +++ b/arch/x86/kernel/stacktrace.c @@ -29,12 +29,6 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, } } -/* - * This function returns an error if it detects any unreliable features of the - * stack. Otherwise it guarantees that the stack trace is reliable. - * - * If the task is not 'current', the caller *must* ensure the task is inactive. - */ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task) { diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c index 653b7f617b61..8a56a6d80098 100644 --- a/arch/x86/kernel/sysfb_efi.c +++ b/arch/x86/kernel/sysfb_efi.c @@ -10,7 +10,7 @@ * EFI Quirks * Several EFI systems do not correctly advertise their boot framebuffers. * Hence, we use this static table of known broken machines and fix up the - * information so framebuffer drivers can load corectly. + * information so framebuffer drivers can load correctly. */ #include <linux/dmi.h> diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 4c09ba110204..f9af561c3cd4 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -49,6 +49,30 @@ bool tboot_enabled(void) return tboot != NULL; } +/* noinline to prevent gcc from warning about dereferencing constant fixaddr */ +static noinline __init bool check_tboot_version(void) +{ + if (memcmp(&tboot_uuid, &tboot->uuid, sizeof(tboot->uuid))) { + pr_warn("tboot at 0x%llx is invalid\n", boot_params.tboot_addr); + return false; + } + + if (tboot->version < 5) { + pr_warn("tboot version is invalid: %u\n", tboot->version); + return false; + } + + pr_info("found shared page at phys addr 0x%llx:\n", + boot_params.tboot_addr); + pr_debug("version: %d\n", tboot->version); + pr_debug("log_addr: 0x%08x\n", tboot->log_addr); + pr_debug("shutdown_entry: 0x%x\n", tboot->shutdown_entry); + pr_debug("tboot_base: 0x%08x\n", tboot->tboot_base); + pr_debug("tboot_size: 0x%x\n", tboot->tboot_size); + + return true; +} + void __init tboot_probe(void) { /* Look for valid page-aligned address for shared page. */ @@ -66,25 +90,9 @@ void __init tboot_probe(void) /* Map and check for tboot UUID. */ set_fixmap(FIX_TBOOT_BASE, boot_params.tboot_addr); - tboot = (struct tboot *)fix_to_virt(FIX_TBOOT_BASE); - if (memcmp(&tboot_uuid, &tboot->uuid, sizeof(tboot->uuid))) { - pr_warn("tboot at 0x%llx is invalid\n", boot_params.tboot_addr); + tboot = (void *)fix_to_virt(FIX_TBOOT_BASE); + if (!check_tboot_version()) tboot = NULL; - return; - } - if (tboot->version < 5) { - pr_warn("tboot version is invalid: %u\n", tboot->version); - tboot = NULL; - return; - } - - pr_info("found shared page at phys addr 0x%llx:\n", - boot_params.tboot_addr); - pr_debug("version: %d\n", tboot->version); - pr_debug("log_addr: 0x%08x\n", tboot->log_addr); - pr_debug("shutdown_entry: 0x%x\n", tboot->shutdown_entry); - pr_debug("tboot_base: 0x%08x\n", tboot->tboot_base); - pr_debug("tboot_size: 0x%x\n", tboot->tboot_size); } static pgd_t *tboot_pg_dir; diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index f5477eab5692..bd83748e2bde 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -113,7 +113,7 @@ int arch_register_cpu(int num) * Two known BSP/CPU0 dependencies: Resume from suspend/hibernate * depends on BSP. PIC interrupts depend on BSP. * - * If the BSP depencies are under control, one can tell kernel to + * If the BSP dependencies are under control, one can tell kernel to * enable BSP hotplug. This basically adds a control file and * one can attempt to offline BSP. */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index ac1874a2a70e..48881db8dca1 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -395,7 +395,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault) /* * Adjust our frame so that we return straight to the #GP * vector with the expected RSP value. This is safe because - * we won't enable interupts or schedule before we invoke + * we won't enable interrupts or schedule before we invoke * general_protection, so nothing will clobber the stack * frame we just set up. * @@ -556,7 +556,7 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) tsk->thread.trap_nr = X86_TRAP_GP; if (fixup_vdso_exception(regs, X86_TRAP_GP, error_code, 0)) - return; + goto exit; show_signal(tsk, SIGSEGV, "", desc, regs, error_code); force_sig(SIGSEGV); @@ -1057,7 +1057,7 @@ static void math_error(struct pt_regs *regs, int trapnr) goto exit; if (fixup_vdso_exception(regs, trapnr, 0, 0)) - return; + goto exit; force_sig_fault(SIGFPE, si_code, (void __user *)uprobe_get_trap_addr(regs)); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index f70dffc2771f..57ec01192180 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -14,6 +14,7 @@ #include <linux/percpu.h> #include <linux/timex.h> #include <linux/static_key.h> +#include <linux/static_call.h> #include <asm/hpet.h> #include <asm/timer.h> @@ -254,7 +255,7 @@ unsigned long long sched_clock(void) bool using_native_sched_clock(void) { - return pv_ops.time.sched_clock == native_sched_clock; + return static_call_query(pv_sched_clock) == native_sched_clock; } #else unsigned long long @@ -739,7 +740,7 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void) * 2) Reference counter. If available we use the HPET or the * PMTIMER as a reference to check the sanity of that value. * We use separate TSC readouts and check inside of the - * reference read for any possible disturbance. We dicard + * reference read for any possible disturbance. We discard * disturbed values here as well. We do that around the PIT * calibration delay loop as we have to wait for a certain * amount of time anyway. @@ -1079,7 +1080,7 @@ static void tsc_resume(struct clocksource *cs) * very small window right after one CPU updated cycle_last under * xtime/vsyscall_gtod lock and the other CPU reads a TSC value which * is smaller than the cycle_last reference value due to a TSC which - * is slighty behind. This delta is nowhere else observable, but in + * is slightly behind. This delta is nowhere else observable, but in * that case it results in a forward time jump in the range of hours * due to the unsigned delta calculation of the time keeping core * code, which is necessary to support wrapping clocksources like pm @@ -1264,7 +1265,7 @@ EXPORT_SYMBOL(convert_art_to_tsc); * corresponding clocksource * @cycles: System counter value * @cs: Clocksource corresponding to system counter value. Used - * by timekeeping code to verify comparibility of two cycle + * by timekeeping code to verify comparability of two cycle * values. */ diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 3d3c761eb74a..50a4515fe0ad 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -472,7 +472,7 @@ retry: /* * Add the result to the previous adjustment value. * - * The adjustement value is slightly off by the overhead of the + * The adjustment value is slightly off by the overhead of the * sync mechanism (observed values are ~200 TSC cycles), but this * really depends on CPU, node distance and frequency. So * compensating for this is hard to get right. Experiments show diff --git a/arch/x86/kernel/umip.c b/arch/x86/kernel/umip.c index f6225bf22c02..fac1daae7994 100644 --- a/arch/x86/kernel/umip.c +++ b/arch/x86/kernel/umip.c @@ -272,7 +272,7 @@ static int emulate_umip_insn(struct insn *insn, int umip_inst, * by whether the operand is a register or a memory location. * If operand is a register, return as many bytes as the operand * size. If operand is memory, return only the two least - * siginificant bytes. + * significant bytes. */ if (X86_MODRM_MOD(insn->modrm.value) == 3) *data_size = insn->opnd_bytes; diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index a788d5120d4d..f6b93a35ce14 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -84,6 +84,18 @@ config KVM_INTEL To compile this as a module, choose M here: the module will be called kvm-intel. +config X86_SGX_KVM + bool "Software Guard eXtensions (SGX) Virtualization" + depends on X86_SGX && KVM_INTEL + help + + Enables KVM guests to create SGX enclaves. + + This includes support to expose "raw" unreclaimable enclave memory to + guests via a device node, e.g. /dev/sgx_vepc. + + If unsure, say N. + config KVM_AMD tristate "KVM for AMD processors support" depends on KVM diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 1b4766fe1de2..eafc4d601f25 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -ccflags-y += -Iarch/x86/kvm +ccflags-y += -I $(srctree)/arch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror ifeq ($(CONFIG_FRAME_POINTER),y) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 6bd2f8b830e4..c02466a1410b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1033,7 +1033,7 @@ EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); * - Centaur: 0xc0000000 - 0xcfffffff * * The Hypervisor class is further subdivided into sub-classes that each act as - * their own indepdent class associated with a 0x100 byte range. E.g. if Qemu + * their own independent class associated with a 0x100 byte range. E.g. if Qemu * is advertising support for both HyperV and KVM, the resulting Hypervisor * CPUID sub-classes are: * diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index f7970ba6219f..cdd2a2b6550e 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -3222,7 +3222,7 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, } /* - * Now load segment descriptors. If fault happenes at this stage + * Now load segment descriptors. If fault happens at this stage * it is handled in a context of new task */ ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR, diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 8a4de3f12820..d5b72a08e566 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -269,7 +269,7 @@ int kvm_set_routing_entry(struct kvm *kvm, const struct kvm_irq_routing_entry *ue) { /* We can't check irqchip_in_kernel() here as some callers are - * currently inititalizing the irqchip. Other callers should therefore + * currently initializing the irqchip. Other callers should therefore * check kvm_arch_can_set_irq_routing() before calling this function. */ switch (ue->type) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index d75524bc8423..62b1729277ef 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4961,7 +4961,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, /* * No need to care whether allocation memory is successful - * or not since pte prefetch is skiped if it does not have + * or not since pte prefetch is skipped if it does not have * enough objects in the cache. */ mmu_topup_memory_caches(vcpu, true); @@ -5884,6 +5884,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) struct kvm_mmu_page *sp; unsigned int ratio; LIST_HEAD(invalid_list); + bool flush = false; ulong to_zap; rcu_idx = srcu_read_lock(&kvm->srcu); @@ -5905,19 +5906,19 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) lpage_disallowed_link); WARN_ON_ONCE(!sp->lpage_disallowed); if (is_tdp_mmu_page(sp)) { - kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, - sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level)); + flush |= kvm_tdp_mmu_zap_sp(kvm, sp); } else { kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); WARN_ON_ONCE(sp->lpage_disallowed); } if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { - kvm_mmu_commit_zap_page(kvm, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); cond_resched_rwlock_write(&kvm->mmu_lock); + flush = false; } } - kvm_mmu_commit_zap_page(kvm, &invalid_list); + kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 1f6f98c76bdf..360983865398 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -59,7 +59,7 @@ struct kvm_mmu_page { #ifdef CONFIG_X86_64 bool tdp_mmu_page; - /* Used for freeing the page asyncronously if it is a TDP MMU page. */ + /* Used for freeing the page asynchronously if it is a TDP MMU page. */ struct rcu_head rcu_head; #endif }; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 462b1f71c77f..34207b874886 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -86,7 +86,7 @@ static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end, bool can_yield); + gfn_t start, gfn_t end, bool can_yield, bool flush); void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) { @@ -99,7 +99,7 @@ void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root) list_del(&root->link); - zap_gfn_range(kvm, root, 0, max_gfn, false); + zap_gfn_range(kvm, root, 0, max_gfn, false, false); free_page((unsigned long)root->spt); kmem_cache_free(mmu_page_header_cache, root); @@ -404,7 +404,7 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, * If this warning were to trigger it would indicate that there was a * missing MMU notifier or a race with some notifier handler. * A present, leaf SPTE should never be directly replaced with another - * present leaf SPTE pointing to a differnt PFN. A notifier handler + * present leaf SPTE pointing to a different PFN. A notifier handler * should be zapping the SPTE before the main MM's page table is * changed, or the SPTE should be zeroed, and the TLBs flushed by the * thread before replacement. @@ -418,7 +418,7 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, /* * Crash the host to prevent error propagation and guest data - * courruption. + * corruption. */ BUG(); } @@ -529,7 +529,7 @@ static inline bool tdp_mmu_zap_spte_atomic(struct kvm *kvm, /* * No other thread can overwrite the removed SPTE as they * must either wait on the MMU lock or use - * tdp_mmu_set_spte_atomic which will not overrite the + * tdp_mmu_set_spte_atomic which will not overwrite the * special removed SPTE value. No bookkeeping is needed * here since the SPTE is going from non-present * to non-present. @@ -668,20 +668,21 @@ static inline bool tdp_mmu_iter_cond_resched(struct kvm *kvm, * scheduler needs the CPU or there is contention on the MMU lock. If this * function cannot yield, it will not release the MMU lock or reschedule and * the caller must ensure it does not supply too large a GFN range, or the - * operation can cause a soft lockup. + * operation can cause a soft lockup. Note, in some use cases a flush may be + * required by prior actions. Ensure the pending flush is performed prior to + * yielding. */ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, - gfn_t start, gfn_t end, bool can_yield) + gfn_t start, gfn_t end, bool can_yield, bool flush) { struct tdp_iter iter; - bool flush_needed = false; rcu_read_lock(); tdp_root_for_each_pte(iter, root, start, end) { if (can_yield && - tdp_mmu_iter_cond_resched(kvm, &iter, flush_needed)) { - flush_needed = false; + tdp_mmu_iter_cond_resched(kvm, &iter, flush)) { + flush = false; continue; } @@ -699,11 +700,11 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, continue; tdp_mmu_set_spte(kvm, &iter, 0); - flush_needed = true; + flush = true; } rcu_read_unlock(); - return flush_needed; + return flush; } /* @@ -712,13 +713,14 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, * SPTEs have been cleared and a TLB flush is needed before releasing the * MMU lock. */ -bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) +bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end, + bool can_yield) { struct kvm_mmu_page *root; bool flush = false; for_each_tdp_mmu_root_yield_safe(kvm, root) - flush |= zap_gfn_range(kvm, root, start, end, true); + flush = zap_gfn_range(kvm, root, start, end, can_yield, flush); return flush; } @@ -930,7 +932,7 @@ static int zap_gfn_range_hva_wrapper(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end, unsigned long unused) { - return zap_gfn_range(kvm, root, start, end, false); + return zap_gfn_range(kvm, root, start, end, false, false); } int kvm_tdp_mmu_zap_hva_range(struct kvm *kvm, unsigned long start, diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 3b761c111bff..31096ece9b14 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -8,7 +8,29 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root); -bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end); +bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end, + bool can_yield); +static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, + gfn_t end) +{ + return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true); +} +static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level); + + /* + * Don't allow yielding, as the caller may have a flush pending. Note, + * if mmu_lock is held for write, zapping will never yield in this case, + * but explicitly disallow it for safety. The TDP MMU does not yield + * until it has made forward progress (steps sideways), and when zapping + * a single shadow page that it's guaranteed to see (thus the mmu_lock + * requirement), its "step sideways" will always step beyond the bounds + * of the shadow page's gfn range and stop iterating before yielding. + */ + lockdep_assert_held_write(&kvm->mmu_lock); + return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false); +} void kvm_tdp_mmu_zap_all(struct kvm *kvm); int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7b30bc967af3..67e753edfa22 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -103,7 +103,7 @@ static inline bool kvm_valid_perf_global_ctrl(struct kvm_pmu *pmu, /* returns general purpose PMC with the specified MSR. Note that it can be * used for both PERFCTRn and EVNTSELn; that is why it accepts base as a - * paramenter to tell them apart. + * parameter to tell them apart. */ static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, u32 base) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 78bdcfac4e40..3e55674098be 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -727,7 +727,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) struct amd_svm_iommu_ir *ir; /** - * In some cases, the existing irte is updaed and re-set, + * In some cases, the existing irte is updated and re-set, * so we need to check here if it's already been * added * to the ir_list. */ @@ -838,7 +838,7 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, * Here, we setup with legacy mode in the following cases: * 1. When cannot target interrupt to a specific vcpu. * 2. Unsetting posted interrupt. - * 3. APIC virtialization is disabled for the vcpu. + * 3. APIC virtualization is disabled for the vcpu. * 4. IRQ has incompatible delivery mode (SMI, INIT, etc) */ if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set && diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 35891d9a1099..fb204eaa8bb3 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -246,11 +246,18 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control) return true; } -static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) +static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12) { struct kvm_vcpu *vcpu = &svm->vcpu; bool vmcb12_lma; + /* + * FIXME: these should be done after copying the fields, + * to avoid TOC/TOU races. For these save area checks + * the possible damage is limited since kvm_set_cr0 and + * kvm_set_cr4 handle failure; EFER_SVME is an exception + * so it is force-set later in nested_prepare_vmcb_save. + */ if ((vmcb12->save.efer & EFER_SVME) == 0) return false; @@ -271,7 +278,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4)) return false; - return nested_vmcb_check_controls(&vmcb12->control); + return true; } static void load_nested_vmcb_control(struct vcpu_svm *svm, @@ -396,7 +403,14 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12) svm->vmcb->save.gdtr = vmcb12->save.gdtr; svm->vmcb->save.idtr = vmcb12->save.idtr; kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED); - svm_set_efer(&svm->vcpu, vmcb12->save.efer); + + /* + * Force-set EFER_SVME even though it is checked earlier on the + * VMCB12, because the guest can flip the bit between the check + * and now. Clearing EFER_SVME would call svm_free_nested. + */ + svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME); + svm_set_cr0(&svm->vcpu, vmcb12->save.cr0); svm_set_cr4(&svm->vcpu, vmcb12->save.cr4); svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2; @@ -468,7 +482,6 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa, svm->nested.vmcb12_gpa = vmcb12_gpa; - load_nested_vmcb_control(svm, &vmcb12->control); nested_prepare_vmcb_control(svm); nested_prepare_vmcb_save(svm, vmcb12); @@ -515,7 +528,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm) if (WARN_ON_ONCE(!svm->nested.initialized)) return -EINVAL; - if (!nested_vmcb_checks(svm, vmcb12)) { + load_nested_vmcb_control(svm, &vmcb12->control); + + if (!nested_vmcb_check_save(svm, vmcb12) || + !nested_vmcb_check_controls(&svm->nested.ctl)) { vmcb12->control.exit_code = SVM_EXIT_ERR; vmcb12->control.exit_code_hi = 0; vmcb12->control.exit_info_1 = 0; @@ -1209,6 +1225,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, */ if (!(save->cr0 & X86_CR0_PG)) goto out_free; + if (!(save->efer & EFER_SVME)) + goto out_free; /* * All checks done, we can enter guest mode. L1 control fields diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 035da07500e8..fdf587f19c5f 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -98,6 +98,8 @@ static enum index msr_to_index(u32 msr) static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, enum pmu_type type) { + struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); + switch (msr) { case MSR_F15H_PERF_CTL0: case MSR_F15H_PERF_CTL1: @@ -105,6 +107,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, case MSR_F15H_PERF_CTL3: case MSR_F15H_PERF_CTL4: case MSR_F15H_PERF_CTL5: + if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) + return NULL; + fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: if (type != PMU_TYPE_EVNTSEL) return NULL; @@ -115,6 +120,9 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, case MSR_F15H_PERF_CTR3: case MSR_F15H_PERF_CTR4: case MSR_F15H_PERF_CTR5: + if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) + return NULL; + fallthrough; case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: if (type != PMU_TYPE_COUNTER) return NULL; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 874ea309279f..2b27a9452403 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2082,7 +2082,7 @@ void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu) hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400); hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - /* PKRU is restored on VMEXIT, save the curent host value */ + /* PKRU is restored on VMEXIT, save the current host value */ hostsa->pkru = read_pkru(); /* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */ diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 58a45bb139f8..6dad89248312 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4400,7 +4400,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, void *insn, int i * * This happens because CPU microcode reading instruction bytes * uses a special opcode which attempts to read data using CPL=0 - * priviledges. The microcode reads CS:RIP and if it hits a SMAP + * privileges. The microcode reads CS:RIP and if it hits a SMAP * fault, it gives up and returns no instruction bytes. * * Detection: diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index bcca0b80e0d0..1e069aac7410 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3537,7 +3537,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) * snapshot restore (migration). * * In this flow, it is assumed that vmcs12 cache was - * trasferred as part of captured nVMX state and should + * transferred as part of captured nVMX state and should * therefore not be read from guest memory (which may not * exist on destination host yet). */ diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 4831bc44ce66..459748680daf 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -10,7 +10,7 @@ #include "vmx.h" /* - * We maintian a per-CPU linked-list of vCPU, so in wakeup_handler() we + * We maintain a per-CPU linked-list of vCPU, so in wakeup_handler() we * can find which vCPU should be waken up. */ static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 32cf8287d4a7..bcbf0d2139e9 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1529,7 +1529,7 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) /* * MTCFreq, CycThresh and PSBFreq encodings check, any MSR write that - * utilize encodings marked reserved will casue a #GP fault. + * utilize encodings marked reserved will cause a #GP fault. */ value = intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc_periods); if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc) && @@ -2761,7 +2761,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); /* - * Update real mode segment cache. It may be not up-to-date if sement + * Update real mode segment cache. It may be not up-to-date if segment * register was written while vcpu was in a guest mode. */ vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES); @@ -6027,19 +6027,19 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && exit_reason.basic != EXIT_REASON_TASK_SWITCH)) { + int ndata = 3; + vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.ndata = 3; vcpu->run->internal.data[0] = vectoring_info; vcpu->run->internal.data[1] = exit_reason.full; vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { - vcpu->run->internal.ndata++; - vcpu->run->internal.data[3] = + vcpu->run->internal.data[ndata++] = vmcs_read64(GUEST_PHYSICAL_ADDRESS); } - vcpu->run->internal.data[vcpu->run->internal.ndata++] = - vcpu->arch.last_vmentry_cpu; + vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; + vcpu->run->internal.ndata = ndata; return 0; } @@ -7252,7 +7252,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_topa_output)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_TOPA; - /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabircEn can be set */ + /* If CPUID.(EAX=14H,ECX=0):ECX[3]=1 FabricEn can be set */ if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_output_subsys)) vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fe806e894212..efc7a82ab140 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -156,9 +156,9 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); /* * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables - * adaptive tuning starting from default advancment of 1000ns. '0' disables + * adaptive tuning starting from default advancement of 1000ns. '0' disables * advancement entirely. Any other value is used as-is and disables adaptive - * tuning, i.e. allows priveleged userspace to set an exact advancement time. + * tuning, i.e. allows privileged userspace to set an exact advancement time. */ static int __read_mostly lapic_timer_advance_ns = -1; module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR); @@ -271,8 +271,7 @@ static struct kmem_cache *x86_emulator_cache; * When called, it means the previous get/set msr reached an invalid msr. * Return true if we want to ignore/silent this failed msr access. */ -static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr, - u64 data, bool write) +static bool kvm_msr_ignored_check(u32 msr, u64 data, bool write) { const char *op = write ? "wrmsr" : "rdmsr"; @@ -1288,7 +1287,7 @@ static const u32 emulated_msrs_all[] = { MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, MSR_IA32_TSC_ADJUST, - MSR_IA32_TSCDEADLINE, + MSR_IA32_TSC_DEADLINE, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, MSR_IA32_MISC_ENABLE, @@ -1373,7 +1372,7 @@ static u64 kvm_get_arch_capabilities(void) /* * If nx_huge_pages is enabled, KVM's shadow paging will ensure that * the nested hypervisor runs with NX huge pages. If it is not, - * L1 is anyway vulnerable to ITLB_MULTIHIT explots from other + * L1 is anyway vulnerable to ITLB_MULTIHIT exploits from other * L1 guests, so it need not worry about its own (L2) guests. */ data |= ARCH_CAP_PSCHANGE_MC_NO; @@ -1445,7 +1444,7 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) if (r == KVM_MSR_RET_INVALID) { /* Unconditionally clear the output for simplicity */ *data = 0; - if (kvm_msr_ignored_check(vcpu, index, 0, false)) + if (kvm_msr_ignored_check(index, 0, false)) r = 0; } @@ -1620,7 +1619,7 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, int ret = __kvm_set_msr(vcpu, index, data, host_initiated); if (ret == KVM_MSR_RET_INVALID) - if (kvm_msr_ignored_check(vcpu, index, data, true)) + if (kvm_msr_ignored_check(index, data, true)) ret = 0; return ret; @@ -1658,7 +1657,7 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu, if (ret == KVM_MSR_RET_INVALID) { /* Unconditionally clear *data for simplicity */ *data = 0; - if (kvm_msr_ignored_check(vcpu, index, 0, false)) + if (kvm_msr_ignored_check(index, 0, false)) ret = 0; } @@ -1850,7 +1849,7 @@ fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu) ret = EXIT_FASTPATH_EXIT_HANDLED; } break; - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: data = kvm_read_edx_eax(vcpu); if (!handle_fastpath_set_tscdeadline(vcpu, data)) { kvm_skip_emulated_instruction(vcpu); @@ -2329,7 +2328,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) kvm_vcpu_write_tsc_offset(vcpu, offset); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); - spin_lock(&kvm->arch.pvclock_gtod_sync_lock); + spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags); if (!matched) { kvm->arch.nr_vcpus_matched_tsc = 0; } else if (!already_matched) { @@ -2337,7 +2336,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) } kvm_track_tsc_matching(vcpu); - spin_unlock(&kvm->arch.pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags); } static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, @@ -2559,13 +2558,16 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) int i; struct kvm_vcpu *vcpu; struct kvm_arch *ka = &kvm->arch; + unsigned long flags; kvm_hv_invalidate_tsc_page(kvm); - spin_lock(&ka->pvclock_gtod_sync_lock); kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -2573,8 +2575,6 @@ static void kvm_gen_update_masterclock(struct kvm *kvm) /* guest entries allowed */ kvm_for_each_vcpu(i, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); - - spin_unlock(&ka->pvclock_gtod_sync_lock); #endif } @@ -2582,17 +2582,18 @@ u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_arch *ka = &kvm->arch; struct pvclock_vcpu_time_info hv_clock; + unsigned long flags; u64 ret; - spin_lock(&ka->pvclock_gtod_sync_lock); + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); if (!ka->use_master_clock) { - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); return get_kvmclock_base_ns() + ka->kvmclock_offset; } hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* both __this_cpu_read() and rdtsc() should be on the same cpu */ get_cpu(); @@ -2686,13 +2687,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) * If the host uses TSC clock, then passthrough TSC as stable * to the guest. */ - spin_lock(&ka->pvclock_gtod_sync_lock); + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); use_master_clock = ka->use_master_clock; if (use_master_clock) { host_tsc = ka->master_cycle_now; kernel_ns = ka->master_kernel_ns; } - spin_unlock(&ka->pvclock_gtod_sync_lock); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); @@ -3086,7 +3087,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_set_apic_base(vcpu, msr_info); case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_write(vcpu, msr, data); - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: kvm_set_lapic_tscdeadline_msr(vcpu, data); break; case MSR_IA32_TSC_ADJUST: @@ -3448,7 +3449,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff: return kvm_x2apic_msr_read(vcpu, msr_info->index, &msr_info->data); - case MSR_IA32_TSCDEADLINE: + case MSR_IA32_TSC_DEADLINE: msr_info->data = kvm_get_lapic_tscdeadline_msr(vcpu); break; case MSR_IA32_TSC_ADJUST: @@ -4024,7 +4025,6 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { struct kvm_host_map map; struct kvm_steal_time *st; - int idx; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4032,15 +4032,9 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; - /* - * Take the srcu lock as memslots will be accessed to check the gfn - * cache generation against the memslots generation. - */ - idx = srcu_read_lock(&vcpu->kvm->srcu); - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, &vcpu->arch.st.cache, true)) - goto out; + return; st = map.hva + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); @@ -4048,20 +4042,25 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); - -out: - srcu_read_unlock(&vcpu->kvm->srcu, idx); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { + int idx; + if (vcpu->preempted && !vcpu->arch.guest_state_protected) vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); if (kvm_xen_msr_enabled(vcpu->kvm)) kvm_xen_runstate_set_preempted(vcpu); else kvm_steal_time_set_preempted(vcpu); + srcu_read_unlock(&vcpu->kvm->srcu, idx); static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); @@ -5726,6 +5725,7 @@ set_pit2_out: } #endif case KVM_SET_CLOCK: { + struct kvm_arch *ka = &kvm->arch; struct kvm_clock_data user_ns; u64 now_ns; @@ -5744,8 +5744,22 @@ set_pit2_out: * pvclock_update_vm_gtod_copy(). */ kvm_gen_update_masterclock(kvm); - now_ns = get_kvmclock_ns(kvm); - kvm->arch.kvmclock_offset += user_ns.clock - now_ns; + + /* + * This pairs with kvm_guest_time_update(): when masterclock is + * in use, we use master_kernel_ns + kvmclock_offset to set + * unsigned 'system_time' so if we use get_kvmclock_ns() (which + * is slightly ahead) here we risk going negative on unsigned + * 'system_time' when 'user_ns.clock' is very small. + */ + spin_lock_irq(&ka->pvclock_gtod_sync_lock); + if (kvm->arch.use_master_clock) + now_ns = ka->master_kernel_ns; + else + now_ns = get_kvmclock_base_ns(); + ka->kvmclock_offset = user_ns.clock - now_ns; + spin_unlock_irq(&ka->pvclock_gtod_sync_lock); + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); break; } @@ -7724,6 +7738,7 @@ static void kvm_hyperv_tsc_notifier(void) struct kvm *kvm; struct kvm_vcpu *vcpu; int cpu; + unsigned long flags; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) @@ -7739,17 +7754,15 @@ static void kvm_hyperv_tsc_notifier(void) list_for_each_entry(kvm, &vm_list, vm_list) { struct kvm_arch *ka = &kvm->arch; - spin_lock(&ka->pvclock_gtod_sync_lock); - + spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); pvclock_update_vm_gtod_copy(kvm); + spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); kvm_for_each_vcpu(cpu, vcpu, kvm) kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu); - - spin_unlock(&ka->pvclock_gtod_sync_lock); } mutex_unlock(&kvm_lock); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 39eb04887141..9035e34aa156 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -250,7 +250,6 @@ static inline bool kvm_vcpu_latch_init(struct kvm_vcpu *vcpu) void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs); void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); -void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr); u64 get_kvmclock_ns(struct kvm *kvm); int kvm_read_guest_virt(struct kvm_vcpu *vcpu, diff --git a/arch/x86/lib/atomic64_386_32.S b/arch/x86/lib/atomic64_386_32.S index 3b6544111ac9..16bc9130e7a5 100644 --- a/arch/x86/lib/atomic64_386_32.S +++ b/arch/x86/lib/atomic64_386_32.S @@ -6,7 +6,7 @@ */ #include <linux/linkage.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> /* if you want SMP support, implement these with real spinlocks */ .macro LOCK reg diff --git a/arch/x86/lib/atomic64_cx8_32.S b/arch/x86/lib/atomic64_cx8_32.S index 1c5c81c16b06..ce6935690766 100644 --- a/arch/x86/lib/atomic64_cx8_32.S +++ b/arch/x86/lib/atomic64_cx8_32.S @@ -6,7 +6,7 @@ */ #include <linux/linkage.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> .macro read64 reg movl %ebx, %eax diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 2402d4c489d2..db4b4f9197c7 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -3,7 +3,7 @@ #include <linux/linkage.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> /* diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 77b9b2a3b5c8..57b79c577496 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -11,7 +11,7 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/asm.h> #include <asm/smap.h> #include <asm/export.h> diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index bb0b3fe1e0a0..2bf07e18e38c 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -232,7 +232,7 @@ static int resolve_default_seg(struct insn *insn, struct pt_regs *regs, int off) * resolve_seg_reg() - obtain segment register index * @insn: Instruction with operands * @regs: Register values as seen when entering kernel mode - * @regoff: Operand offset, in pt_regs, used to deterimine segment register + * @regoff: Operand offset, in pt_regs, used to determine segment register * * Determine the segment register associated with the operands and, if * applicable, prefixes and the instruction pointed by @insn. @@ -517,7 +517,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, * @insn: Instruction containing ModRM byte * @regs: Register values as seen when entering kernel mode * @offs1: Offset of the first operand register - * @offs2: Offset of the second opeand register, if applicable + * @offs2: Offset of the second operand register, if applicable * * Obtain the offset, in pt_regs, of the registers indicated by the ModRM byte * in @insn. This function is to be used with 16-bit address encodings. The @@ -576,7 +576,7 @@ static int get_reg_offset_16(struct insn *insn, struct pt_regs *regs, * If ModRM.mod is 0 and ModRM.rm is 110b, then we use displacement- * only addressing. This means that no registers are involved in * computing the effective address. Thus, ensure that the first - * register offset is invalild. The second register offset is already + * register offset is invalid. The second register offset is already * invalid under the aforementioned conditions. */ if ((X86_MODRM_MOD(insn->modrm.value) == 0) && diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 1e299ac73c86..1cc9da6e29c7 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -4,7 +4,7 @@ #include <linux/linkage.h> #include <asm/errno.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> .pushsection .noinstr.text, "ax" diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index 41902fe8b859..64801010d312 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -8,7 +8,7 @@ */ #include <linux/linkage.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> #undef memmove diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 0bfd26e4ca9e..9827ae267f96 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -3,7 +3,7 @@ #include <linux/linkage.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> /* diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index 419365c48b2a..cc5f4ea943d3 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -14,7 +14,7 @@ * tested so far for any MMX solution figured. * * 22/09/2000 - Arjan van de Ven - * Improved for non-egineering-sample Athlons + * Improved for non-engineering-sample Athlons * */ #include <linux/hardirq.h> diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index 75a0915b0d01..40bbe56bde32 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -252,7 +252,7 @@ static void __wrmsr_safe_regs_on_cpu(void *info) rv->err = wrmsr_safe_regs(rv->regs); } -int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) +int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { int err; struct msr_regs_info rv; @@ -265,7 +265,7 @@ int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) } EXPORT_SYMBOL(rdmsr_safe_regs_on_cpu); -int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 *regs) +int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) { int err; struct msr_regs_info rv; diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 3bd905e10ee2..b09cd2ad426c 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL(msrs_free); * argument @m. * */ -int msr_read(u32 msr, struct msr *m) +static int msr_read(u32 msr, struct msr *m) { int err; u64 val; @@ -54,7 +54,7 @@ int msr_read(u32 msr, struct msr *m) * @msr: MSR to write * @m: value to write */ -int msr_write(u32 msr, struct msr *m) +static int msr_write(u32 msr, struct msr *m) { return wrmsrl_safe(msr, m->q); } diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index f6fb1d218dcc..6bb74b5c238c 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -4,7 +4,7 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> #include <asm/cpufeatures.h> -#include <asm/alternative-asm.h> +#include <asm/alternative.h> #include <asm/export.h> #include <asm/nospec-branch.h> #include <asm/unwind_hints.h> diff --git a/arch/x86/math-emu/fpu_trig.c b/arch/x86/math-emu/fpu_trig.c index 4a9887851ad8..990d847ae902 100644 --- a/arch/x86/math-emu/fpu_trig.c +++ b/arch/x86/math-emu/fpu_trig.c @@ -547,7 +547,7 @@ static void frndint_(FPU_REG *st0_ptr, u_char st0_tag) single_arg_error(st0_ptr, st0_tag); } -static int fsin(FPU_REG *st0_ptr, u_char tag) +static int f_sin(FPU_REG *st0_ptr, u_char tag) { u_char arg_sign = getsign(st0_ptr); @@ -608,6 +608,11 @@ static int fsin(FPU_REG *st0_ptr, u_char tag) } } +static void fsin(FPU_REG *st0_ptr, u_char tag) +{ + f_sin(st0_ptr, tag); +} + static int f_cos(FPU_REG *st0_ptr, u_char tag) { u_char st0_sign; @@ -724,7 +729,7 @@ static void fsincos(FPU_REG *st0_ptr, u_char st0_tag) } reg_copy(st0_ptr, &arg); - if (!fsin(st0_ptr, st0_tag)) { + if (!f_sin(st0_ptr, st0_tag)) { push(); FPU_copy_to_reg0(&arg, st0_tag); f_cos(&st(0), st0_tag); @@ -1635,7 +1640,7 @@ void FPU_triga(void) } static FUNC_ST0 const trig_table_b[] = { - fprem, fyl2xp1, fsqrt_, fsincos, frndint_, fscale, (FUNC_ST0) fsin, fcos + fprem, fyl2xp1, fsqrt_, fsincos, frndint_, fscale, fsin, fcos }; void FPU_trigb(void) diff --git a/arch/x86/math-emu/reg_ld_str.c b/arch/x86/math-emu/reg_ld_str.c index fe6246ff9887..7ca6417c0c8d 100644 --- a/arch/x86/math-emu/reg_ld_str.c +++ b/arch/x86/math-emu/reg_ld_str.c @@ -964,7 +964,7 @@ int FPU_store_bcd(FPU_REG *st0_ptr, u_char st0_tag, u_char __user *d) /* The return value (in eax) is zero if the result is exact, if bits are changed due to rounding, truncation, etc, then a non-zero value is returned */ -/* Overflow is signalled by a non-zero return value (in eax). +/* Overflow is signaled by a non-zero return value (in eax). In the case of overflow, the returned significand always has the largest possible value */ int FPU_round_to_int(FPU_REG *r, u_char tag) diff --git a/arch/x86/math-emu/reg_round.S b/arch/x86/math-emu/reg_round.S index 11a1f798451b..4a9fc3cc5a4d 100644 --- a/arch/x86/math-emu/reg_round.S +++ b/arch/x86/math-emu/reg_round.S @@ -575,7 +575,7 @@ Normalise_result: #ifdef PECULIAR_486 /* * This implements a special feature of 80486 behaviour. - * Underflow will be signalled even if the number is + * Underflow will be signaled even if the number is * not a denormal after rounding. * This difference occurs only for masked underflow, and not * in the unmasked case. diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index a73347e2cdfc..1c548ad00752 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1497,7 +1497,7 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) * userspace task is trying to access some valid (from guest's point of * view) memory which is not currently mapped by the host (e.g. the * memory is swapped out). Note, the corresponding "page ready" event - * which is injected when the memory becomes available, is delived via + * which is injected when the memory becomes available, is delivered via * an interrupt mechanism and not a #PF exception * (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()). * @@ -1523,7 +1523,7 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) * * In case the fault hit a RCU idle region the conditional entry * code reenabled RCU to avoid subsequent wreckage which helps - * debugability. + * debuggability. */ state = irqentry_enter(regs); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index dd694fb93916..fbf41dd142ca 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -29,7 +29,7 @@ /* * We need to define the tracepoints somewhere, and tlb.c - * is only compied when SMP=y. + * is only compiled when SMP=y. */ #define CREATE_TRACE_POINTS #include <trace/events/tlb.h> @@ -756,7 +756,7 @@ void __init init_mem_mapping(void) #ifdef CONFIG_X86_64 if (max_pfn > max_low_pfn) { - /* can we preseve max_low_pfn ?*/ + /* can we preserve max_low_pfn ?*/ max_low_pfn = max_pfn; } #else @@ -939,7 +939,7 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) { /* * end could be not aligned, and We can not align that, - * decompresser could be confused by aligned initrd_end + * decompressor could be confused by aligned initrd_end * We already reserve the end partial page before in * - i386_start_kernel() * - x86_64_start_kernel() diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index b5a3fa4033d3..55247451ba85 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -172,7 +172,7 @@ static void sync_global_pgds_l4(unsigned long start, unsigned long end) /* * With folded p4d, pgd_none() is always false, we need to - * handle synchonization on p4d level. + * handle synchronization on p4d level. */ MAYBE_BUILD_BUG_ON(pgd_none(*pgd_ref)); p4d_ref = p4d_offset(pgd_ref, addr); @@ -986,7 +986,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, if (PAGE_ALIGNED(addr) && PAGE_ALIGNED(next)) { /* * Do not free direct mapping pages since they were - * freed when offlining, or simplely not in use. + * freed when offlining, or simply not in use. */ if (!direct) free_pagetable(pte_page(*pte), 0); @@ -1004,7 +1004,7 @@ remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end, * * If we are not removing the whole page, it means * other page structs in this page are being used and - * we canot remove them. So fill the unused page_structs + * we cannot remove them. So fill the unused page_structs * with 0xFD, and remove the page when it is wholly * filled with 0xFD. */ diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 6e6b39710e5f..557f0fe25dff 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -96,7 +96,7 @@ void __init kernel_randomize_memory(void) memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) + CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING; - /* Adapt phyiscal memory region size based on available memory */ + /* Adapt physical memory region size based on available memory */ if (memory_tb < kaslr_regions[0].size_tb) kaslr_regions[0].size_tb = memory_tb; diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index be020a7bc414..d3efbc5b3449 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Support for MMIO probes. - * Benfit many code from kprobes + * Benefit many code from kprobes * (C) 2002 Louis Zhuang <louis.zhuang@intel.com>. * 2007 Alexander Eichner * 2008 Pekka Paalanen <pq@iki.fi> diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 4b01f7dbaf30..f633f9e23b8f 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -19,6 +19,7 @@ #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/dma-mapping.h> +#include <linux/virtio_config.h> #include <asm/tlbflush.h> #include <asm/fixmap.h> @@ -262,7 +263,7 @@ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc) if (pgprot_val(old_prot) == pgprot_val(new_prot)) return; - pa = pfn << page_level_shift(level); + pa = pfn << PAGE_SHIFT; size = page_level_size(level); /* @@ -484,3 +485,8 @@ void __init mem_encrypt_init(void) print_mem_encrypt_feature_info(); } +int arch_has_restricted_virtio_memory_access(void) +{ + return sev_active(); +} +EXPORT_SYMBOL_GPL(arch_has_restricted_virtio_memory_access); diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 7a84fc8bc5c3..17d292b7072f 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -27,7 +27,7 @@ SYM_FUNC_START(sme_encrypt_execute) * - stack page (PAGE_SIZE) * - encryption routine page (PAGE_SIZE) * - intermediate copy buffer (PMD_PAGE_SIZE) - * R8 - physcial address of the pagetables to use for encryption + * R8 - physical address of the pagetables to use for encryption */ push %rbp diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 6c5eb6f3f14f..a19374d26101 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -503,14 +503,10 @@ void __init sme_enable(struct boot_params *bp) #define AMD_SME_BIT BIT(0) #define AMD_SEV_BIT BIT(1) - /* - * Set the feature mask (SME or SEV) based on whether we are - * running under a hypervisor. - */ - eax = 1; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - feature_mask = (ecx & BIT(31)) ? AMD_SEV_BIT : AMD_SME_BIT; + + /* Check the SEV MSR whether SEV or SME is enabled */ + sev_status = __rdmsr(MSR_AMD64_SEV); + feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; /* * Check for the SME/SEV feature: @@ -530,19 +526,26 @@ void __init sme_enable(struct boot_params *bp) /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { + /* + * No SME if Hypervisor bit is set. This check is here to + * prevent a guest from trying to enable SME. For running as a + * KVM guest the MSR_K8_SYSCFG will be sufficient, but there + * might be other hypervisors which emulate that MSR as non-zero + * or even pass it through to the guest. + * A malicious hypervisor can still trick a guest into this + * path, but there is no way to protect against that. + */ + eax = 1; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (ecx & BIT(31)) + return; + /* For SME, check the SYSCFG MSR */ msr = __rdmsr(MSR_K8_SYSCFG); if (!(msr & MSR_K8_SYSCFG_MEM_ENCRYPT)) return; } else { - /* For SEV, check the SEV MSR */ - msr = __rdmsr(MSR_AMD64_SEV); - if (!(msr & MSR_AMD64_SEV_ENABLED)) - return; - - /* Save SEV_STATUS to avoid reading MSR again */ - sev_status = msr; - /* SEV state cannot be controlled by a command line option */ sme_me_mask = me_mask; sev_enabled = true; diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index ca311aaa67b8..3112ca7786ed 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -695,7 +695,7 @@ int memtype_free(u64 start, u64 end) /** - * lookup_memtype - Looksup the memory type for a physical address + * lookup_memtype - Looks up the memory type for a physical address * @paddr: physical address of which memory type needs to be looked up * * Only to be called when PAT is enabled @@ -800,6 +800,7 @@ void memtype_free_io(resource_size_t start, resource_size_t end) memtype_free(start, end); } +#ifdef CONFIG_X86_PAT int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size) { enum page_cache_mode type = _PAGE_CACHE_MODE_WC; @@ -813,6 +814,7 @@ void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size) memtype_free_io(start, start + size); } EXPORT_SYMBOL(arch_io_free_memtype_wc); +#endif pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 16f878c26667..427980617557 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -680,7 +680,7 @@ pmd_t *lookup_pmd_address(unsigned long address) * end up in this kind of memory, for instance. * * This could be optimized, but it is only intended to be - * used at inititalization time, and keeping it + * used at initialization time, and keeping it * unoptimized should increase the testing coverage for * the more obscure platforms. */ diff --git a/arch/x86/mm/pkeys.c b/arch/x86/mm/pkeys.c index 8873ed1438a9..a2332eef66e9 100644 --- a/arch/x86/mm/pkeys.c +++ b/arch/x86/mm/pkeys.c @@ -128,7 +128,7 @@ u32 init_pkru_value = PKRU_AD_KEY( 1) | PKRU_AD_KEY( 2) | PKRU_AD_KEY( 3) | /* * Called from the FPU code when creating a fresh set of FPU * registers. This is called from a very specific context where - * we know the FPU regstiers are safe for use and we can use PKRU + * we know the FPU registers are safe for use and we can use PKRU * directly. */ void copy_init_pkru_to_fpregs(void) diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 1aab92930569..5d5c7bb50ce9 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -361,7 +361,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end, * global, so set it as global in both copies. Note: * the X86_FEATURE_PGE check is not _required_ because * the CPU ignores _PAGE_GLOBAL when PGE is not - * supported. The check keeps consistentency with + * supported. The check keeps consistency with * code that only set this bit when supported. */ if (boot_cpu_has(X86_FEATURE_PGE)) @@ -440,10 +440,9 @@ static void __init pti_clone_user_shared(void) for_each_possible_cpu(cpu) { /* - * The SYSCALL64 entry code needs to be able to find the - * thread stack and needs one word of scratch space in which - * to spill a register. All of this lives in the TSS, in - * the sp1 and sp2 slots. + * The SYSCALL64 entry code needs one word of scratch space + * in which to spill a register. It lives in the sp2 slot + * of the CPU's TSS. * * This is done for all possible CPUs during boot to ensure * that it's propagated to all mms. @@ -512,7 +511,7 @@ static void pti_clone_entry_text(void) static inline bool pti_kernel_image_global_ok(void) { /* - * Systems with PCIDs get litlle benefit from global + * Systems with PCIDs get little benefit from global * kernel text and are not worth the downsides. */ if (cpu_feature_enabled(X86_FEATURE_PCID)) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 569ac1d57f55..98f269560d40 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -106,7 +106,7 @@ static inline u16 kern_pcid(u16 asid) #ifdef CONFIG_PAGE_TABLE_ISOLATION /* - * Make sure that the dynamic ASID space does not confict with the + * Make sure that the dynamic ASID space does not conflict with the * bit we are using to switch between user and kernel ASIDs. */ BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_PCID_USER_BIT)); @@ -736,7 +736,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, * 3, we'd be break the invariant: we'd update local_tlb_gen above * 1 without the full flush that's needed for tlb_gen 2. * - * 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimiation. + * 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimization. * Partial TLB flushes are not all that much cheaper than full TLB * flushes, so it seems unlikely that it would be a performance win * to do a partial flush if that won't bring our TLB fully up to @@ -876,7 +876,7 @@ static inline struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm, static inline void put_flush_tlb_info(void) { #ifdef CONFIG_DEBUG_VM - /* Complete reentrency prevention checks */ + /* Complete reentrancy prevention checks */ barrier(); this_cpu_dec(flush_tlb_info_idx); #endif diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 6926d0ca6c71..220e72434f3c 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1556,7 +1556,7 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ if (is_imm8(jmp_offset)) { if (jmp_padding) { /* To keep the jmp_offset valid, the extra bytes are - * padded before the jump insn, so we substract the + * padded before the jump insn, so we subtract the * 2 bytes of jmp_cond insn from INSN_SZ_DIFF. * * If the previous pass already emits an imm8 @@ -1631,7 +1631,7 @@ emit_jmp: if (jmp_padding) { /* To avoid breaking jmp_offset, the extra bytes * are padded before the actual jmp insn, so - * 2 bytes is substracted from INSN_SZ_DIFF. + * 2 bytes is subtracted from INSN_SZ_DIFF. * * If the previous pass already emits an imm8 * jmp, there is nothing to pad (0 byte). @@ -1689,7 +1689,16 @@ emit_jmp: } if (image) { - if (unlikely(proglen + ilen > oldproglen)) { + /* + * When populating the image, assert that: + * + * i) We do not write beyond the allocated space, and + * ii) addrs[i] did not change from the prior run, in order + * to validate assumptions made for computing branch + * displacements. + */ + if (unlikely(proglen + ilen > oldproglen || + proglen + ilen != addrs[i])) { pr_err("bpf_jit: fatal error\n"); return -EFAULT; } @@ -1936,7 +1945,7 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, * add rsp, 8 // skip eth_type_trans's frame * ret // return to its caller */ -int arch_prepare_bpf_trampoline(void *image, void *image_end, +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_progs *tprogs, void *orig_call) @@ -1975,6 +1984,15 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, save_regs(m, &prog, nr_args, stack_size); + if (flags & BPF_TRAMP_F_CALL_ORIG) { + /* arg1: mov rdi, im */ + emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); + if (emit_call(&prog, __bpf_tramp_enter, prog)) { + ret = -EINVAL; + goto cleanup; + } + } + if (fentry->nr_progs) if (invoke_bpf(m, &prog, fentry, stack_size)) return -EINVAL; @@ -1993,8 +2011,7 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, } if (flags & BPF_TRAMP_F_CALL_ORIG) { - if (fentry->nr_progs || fmod_ret->nr_progs) - restore_regs(m, &prog, nr_args, stack_size); + restore_regs(m, &prog, nr_args, stack_size); /* call original function */ if (emit_call(&prog, orig_call, prog)) { @@ -2003,6 +2020,9 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, } /* remember return value in a stack for bpf prog to access */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); + im->ip_after_call = prog; + memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE); + prog += X86_PATCH_SIZE; } if (fmod_ret->nr_progs) { @@ -2033,9 +2053,17 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end, * the return value is only updated on the stack and still needs to be * restored to R0. */ - if (flags & BPF_TRAMP_F_CALL_ORIG) + if (flags & BPF_TRAMP_F_CALL_ORIG) { + im->ip_epilogue = prog; + /* arg1: mov rdi, im */ + emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); + if (emit_call(&prog, __bpf_tramp_exit, prog)) { + ret = -EINVAL; + goto cleanup; + } /* restore original return value back into RAX */ emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); + } EMIT1(0x5B); /* pop rbx */ EMIT1(0xC9); /* leave */ @@ -2225,7 +2253,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) padding = true; goto skip_init_addrs; } - addrs = kmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL); + addrs = kvmalloc_array(prog->len + 1, sizeof(*addrs), GFP_KERNEL); if (!addrs) { prog = orig_prog; goto out_addrs; @@ -2317,7 +2345,7 @@ out_image: if (image) bpf_prog_fill_jited_linfo(prog, addrs + 1); out_addrs: - kfree(addrs); + kvfree(addrs); kfree(jit_data); prog->aux->jit_data = NULL; } diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index d17b67c69f89..6a99def7d315 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -2276,7 +2276,16 @@ notyet: } if (image) { - if (unlikely(proglen + ilen > oldproglen)) { + /* + * When populating the image, assert that: + * + * i) We do not write beyond the allocated space, and + * ii) addrs[i] did not change from the prior run, in order + * to validate assumptions made for computing branch + * displacements. + */ + if (unlikely(proglen + ilen > oldproglen || + proglen + ilen != addrs[i])) { pr_err("bpf_jit: fatal error\n"); return -EFAULT; } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 0a0e168be1cb..02dc64625e64 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -375,7 +375,7 @@ static const struct dmi_system_id msi_k8t_dmi_table[] = { * The BIOS only gives options "DISABLED" and "AUTO". This code sets * the corresponding register-value to enable the soundcard. * - * The soundcard is only enabled, if the mainborad is identified + * The soundcard is only enabled, if the mainboard is identified * via DMI-tables and the soundcard is detected to be off. */ static void pci_fixup_msi_k8t_onboard_sound(struct pci_dev *dev) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 1b82d77019b1..df7b5477fc4f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -195,7 +195,7 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) } /* - * Certain firmware versions are way too sentimential and still believe + * Certain firmware versions are way too sentimental and still believe * they are exclusive and unquestionable owners of the first physical page, * even though they explicitly mark it as EFI_CONVENTIONAL_MEMORY * (but then write-access it later during SetVirtualAddressMap()). @@ -457,7 +457,7 @@ void __init efi_dump_pagetable(void) * in a kernel thread and user context. Preemption needs to remain disabled * while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm * can not change under us. - * It should be ensured that there are no concurent calls to this function. + * It should be ensured that there are no concurrent calls to this function. */ void efi_enter_mm(void) { diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 67d93a243c35..7850111008a8 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -441,7 +441,7 @@ void __init efi_free_boot_services(void) * 1.4.4 with SGX enabled booting Linux via Fedora 24's * grub2-efi on a hard disk. (And no, I don't know why * this happened, but Linux should still try to boot rather - * panicing early.) + * panicking early.) */ rm_size = real_mode_size_needed(); if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) { @@ -726,7 +726,7 @@ void efi_crash_gracefully_on_page_fault(unsigned long phys_addr) * Buggy efi_reset_system() is handled differently from other EFI * Runtime Services as it doesn't use efi_rts_wq. Although, * native_machine_emergency_restart() says that machine_real_restart() - * could fail, it's better not to compilcate this fault handler + * could fail, it's better not to complicate this fault handler * because this case occurs *very* rarely and hence could be improved * on a need by basis. */ diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index 0286fe1b14b5..d3d456925b2a 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * imr.c -- Intel Isolated Memory Region driver * * Copyright(c) 2013 Intel Corporation. @@ -551,7 +551,7 @@ static void __init imr_fixup_memmap(struct imr_device *idev) /* * Setup an unlocked IMR around the physical extent of the kernel - * from the beginning of the .text secton to the end of the + * from the beginning of the .text section to the end of the * .rodata section as one physically contiguous block. * * We don't round up @size since it is already PAGE_SIZE aligned. diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c index 570e3062faac..761f3689f60a 100644 --- a/arch/x86/platform/intel-quark/imr_selftest.c +++ b/arch/x86/platform/intel-quark/imr_selftest.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * imr_selftest.c -- Intel Isolated Memory Region self-test driver * * Copyright(c) 2013 Intel Corporation. diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index 526f70f27c1c..fdd49d70b437 100644 --- a/arch/x86/platform/intel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -187,7 +187,7 @@ bool iosf_mbi_available(void) EXPORT_SYMBOL(iosf_mbi_available); /* - **************** P-Unit/kernel shared I2C bus arbritration **************** + **************** P-Unit/kernel shared I2C bus arbitration **************** * * Some Bay Trail and Cherry Trail devices have the P-Unit and us (the kernel) * share a single I2C bus to the PMIC. Below are helpers to arbitrate the @@ -493,7 +493,7 @@ static void iosf_sideband_debug_init(void) /* mcrx */ debugfs_create_x32("mcrx", 0660, iosf_dbg, &dbg_mcrx); - /* mcr - initiates mailbox tranaction */ + /* mcr - initiates mailbox transaction */ debugfs_create_file("mcr", 0660, iosf_dbg, &dbg_mcr, &iosf_mcr_fops); } diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index 85f4638764d6..994a229cb79f 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -27,7 +27,7 @@ static bool lid_wake_on_close; * wake-on-close. This is implemented as standard by the XO-1.5 DSDT. * * We provide here a sysfs attribute that will additionally enable - * wake-on-close behavior. This is useful (e.g.) when we oportunistically + * wake-on-close behavior. This is useful (e.g.) when we opportunistically * suspend with the display running; if the lid is then closed, we want to * wake up to turn the display off. * diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index 26d1f6693789..75e3319e8bee 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -131,7 +131,7 @@ void * __init prom_early_alloc(unsigned long size) const size_t chunk_size = max(PAGE_SIZE, size); /* - * To mimimize the number of allocations, grab at least + * To minimize the number of allocations, grab at least * PAGE_SIZE of memory (that's an arbitrary choice that's * fast enough on the platforms we care about while minimizing * wasted bootmem) and hand off chunks of it to callers. diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index d2ccadc247e6..66b317398b8a 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -30,10 +30,10 @@ * the boot start info structure. * - `cr0`: bit 0 (PE) must be set. All the other writeable bits are cleared. * - `cr4`: all bits are cleared. - * - `cs `: must be a 32-bit read/execute code segment with a base of ‘0’ - * and a limit of ‘0xFFFFFFFF’. The selector value is unspecified. + * - `cs `: must be a 32-bit read/execute code segment with a base of `0` + * and a limit of `0xFFFFFFFF`. The selector value is unspecified. * - `ds`, `es`: must be a 32-bit read/write data segment with a base of - * ‘0’ and a limit of ‘0xFFFFFFFF’. The selector values are all + * `0` and a limit of `0xFFFFFFFF`. The selector values are all * unspecified. * - `tr`: must be a 32-bit TSS (active) with a base of '0' and a limit * of '0x67'. diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index eafc530c8767..1e9ff28bc2e0 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -24,6 +24,7 @@ #include <asm/kdebug.h> #include <asm/local64.h> #include <asm/nmi.h> +#include <asm/reboot.h> #include <asm/traps.h> #include <asm/uv/uv.h> #include <asm/uv/uv_hub.h> @@ -91,6 +92,8 @@ static atomic_t uv_nmi_cpus_in_nmi = ATOMIC_INIT(-1); static atomic_t uv_nmi_slave_continue; static cpumask_var_t uv_nmi_cpu_mask; +static atomic_t uv_nmi_kexec_failed; + /* Values for uv_nmi_slave_continue */ #define SLAVE_CLEAR 0 #define SLAVE_CONTINUE 1 @@ -834,38 +837,35 @@ static void uv_nmi_touch_watchdogs(void) touch_nmi_watchdog(); } -static atomic_t uv_nmi_kexec_failed; - -#if defined(CONFIG_KEXEC_CORE) -static void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) +static void uv_nmi_kdump(int cpu, int main, struct pt_regs *regs) { + /* Check if kdump kernel loaded for both main and secondary CPUs */ + if (!kexec_crash_image) { + if (main) + pr_err("UV: NMI error: kdump kernel not loaded\n"); + return; + } + /* Call crash to dump system state */ - if (master) { + if (main) { pr_emerg("UV: NMI executing crash_kexec on CPU%d\n", cpu); crash_kexec(regs); - pr_emerg("UV: crash_kexec unexpectedly returned, "); + pr_emerg("UV: crash_kexec unexpectedly returned\n"); atomic_set(&uv_nmi_kexec_failed, 1); - if (!kexec_crash_image) { - pr_cont("crash kernel not loaded\n"); - return; - } - pr_cont("kexec busy, stalling cpus while waiting\n"); - } - /* If crash exec fails the slaves should return, otherwise stall */ - while (atomic_read(&uv_nmi_kexec_failed) == 0) - mdelay(10); -} + } else { /* secondary */ -#else /* !CONFIG_KEXEC_CORE */ -static inline void uv_nmi_kdump(int cpu, int master, struct pt_regs *regs) -{ - if (master) - pr_err("UV: NMI kdump: KEXEC not supported in this kernel\n"); - atomic_set(&uv_nmi_kexec_failed, 1); + /* If kdump kernel fails, secondaries will exit this loop */ + while (atomic_read(&uv_nmi_kexec_failed) == 0) { + + /* Once shootdown cpus starts, they do not return */ + run_crash_ipi_callback(regs); + + mdelay(10); + } + } } -#endif /* !CONFIG_KEXEC_CORE */ #ifdef CONFIG_KGDB #ifdef CONFIG_KGDB_KDB @@ -889,7 +889,7 @@ static inline int uv_nmi_kdb_reason(void) * Call KGDB/KDB from NMI handler * * Note that if both KGDB and KDB are configured, then the action of 'kgdb' or - * 'kdb' has no affect on which is used. See the KGDB documention for further + * 'kdb' has no affect on which is used. See the KGDB documentation for further * information. */ static void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master) diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index db1378c6ff26..c9908bcdb249 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -321,7 +321,7 @@ int hibernate_resume_nonboot_cpu_disable(void) /* * When bsp_check() is called in hibernate and suspend, cpu hotplug - * is disabled already. So it's unnessary to handle race condition between + * is disabled already. So it's unnecessary to handle race condition between * cpumask query and cpu hotplug. */ static int bsp_check(void) diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 22fda7d99159..1be71ef5e4c4 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -103,7 +103,7 @@ static void __init setup_real_mode(void) *ptr += phys_base; } - /* Must be perfomed *after* relocation. */ + /* Must be performed *after* relocation. */ trampoline_header = (struct trampoline_header *) __va(real_mode_header->trampoline_header); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index dc0a337f985b..4f18cd9eacd8 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -1070,8 +1070,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .read_pmc = xen_read_pmc, - .iret = xen_iret, - .load_tr_desc = paravirt_nop, .set_ldt = xen_set_ldt, .load_gdt = xen_load_gdt, @@ -1233,8 +1231,8 @@ asmlinkage __visible void __init xen_start_kernel(void) /* Install Xen paravirt ops */ pv_info = xen_info; - pv_ops.init.patch = paravirt_patch_default; pv_ops.cpu = xen_cpu_ops; + paravirt_iret = xen_iret; xen_init_irq_ops(); /* diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index cf2ade864c30..1e28c880f642 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -2410,7 +2410,7 @@ int xen_remap_pfn(struct vm_area_struct *vma, unsigned long addr, rmd.prot = prot; /* * We use the err_ptr to indicate if there we are doing a contiguous - * mapping or a discontigious mapping. + * mapping or a discontiguous mapping. */ rmd.contiguous = !err_ptr; rmd.no_translate = no_translate; diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 17d80f751fcb..ac06ca32e9ef 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -98,8 +98,8 @@ EXPORT_SYMBOL_GPL(xen_p2m_size); unsigned long xen_max_p2m_pfn __read_mostly; EXPORT_SYMBOL_GPL(xen_max_p2m_pfn); -#ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT -#define P2M_LIMIT CONFIG_XEN_BALLOON_MEMORY_HOTPLUG_LIMIT +#ifdef CONFIG_XEN_MEMORY_HOTPLUG_LIMIT +#define P2M_LIMIT CONFIG_XEN_MEMORY_HOTPLUG_LIMIT #else #define P2M_LIMIT 0 #endif @@ -416,9 +416,6 @@ void __init xen_vmalloc_p2m_tree(void) xen_p2m_last_pfn = xen_max_p2m_pfn; p2m_limit = (phys_addr_t)P2M_LIMIT * 1024 * 1024 * 1024 / PAGE_SIZE; - if (!p2m_limit && IS_ENABLED(CONFIG_XEN_UNPOPULATED_ALLOC)) - p2m_limit = xen_start_info->nr_pages * XEN_EXTRA_MEM_RATIO; - vm.flags = VM_ALLOC; vm.size = ALIGN(sizeof(unsigned long) * max(xen_max_p2m_pfn, p2m_limit), PMD_SIZE * PMDS_PER_MID_PAGE); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 1a3b75652fa4..8bfc10330107 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -59,6 +59,18 @@ static struct { } xen_remap_buf __initdata __aligned(PAGE_SIZE); static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; +/* + * The maximum amount of extra memory compared to the base size. The + * main scaling factor is the size of struct page. At extreme ratios + * of base:extra, all the base memory can be filled with page + * structures for the extra memory, leaving no space for anything + * else. + * + * 10x seems like a reasonable balance between scaling flexibility and + * leaving a practically usable system. + */ +#define EXTRA_MEM_RATIO (10) + static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB); static void __init xen_parse_512gb(void) @@ -778,13 +790,13 @@ char * __init xen_memory_setup(void) extra_pages += max_pages - max_pfn; /* - * Clamp the amount of extra memory to a XEN_EXTRA_MEM_RATIO + * Clamp the amount of extra memory to a EXTRA_MEM_RATIO * factor the base size. * * Make sure we have no memory above max_pages, as this area * isn't handled by the p2m management. */ - extra_pages = min3(XEN_EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), + extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), extra_pages, max_pages - max_pfn); i = 0; addr = xen_e820_table.entries[0].addr; diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index 91f5b330dcc6..d9c945ee1100 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -379,11 +379,6 @@ void xen_timer_resume(void) } } -static const struct pv_time_ops xen_time_ops __initconst = { - .sched_clock = xen_sched_clock, - .steal_clock = xen_steal_clock, -}; - static struct pvclock_vsyscall_time_info *xen_clock __read_mostly; static u64 xen_clock_value_saved; @@ -525,17 +520,24 @@ static void __init xen_time_init(void) pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); } -void __init xen_init_time_ops(void) +static void __init xen_init_time_common(void) { xen_sched_clock_offset = xen_clocksource_read(); - pv_ops.time = xen_time_ops; + static_call_update(pv_steal_clock, xen_steal_clock); + paravirt_set_sched_clock(xen_sched_clock); + + x86_platform.calibrate_tsc = xen_tsc_khz; + x86_platform.get_wallclock = xen_get_wallclock; +} + +void __init xen_init_time_ops(void) +{ + xen_init_time_common(); x86_init.timers.timer_init = xen_time_init; x86_init.timers.setup_percpu_clockev = x86_init_noop; x86_cpuinit.setup_percpu_clockev = x86_init_noop; - x86_platform.calibrate_tsc = xen_tsc_khz; - x86_platform.get_wallclock = xen_get_wallclock; /* Dom0 uses the native method to set the hardware RTC. */ if (!xen_initial_domain()) x86_platform.set_wallclock = xen_set_wallclock; @@ -569,13 +571,11 @@ void __init xen_hvm_init_time_ops(void) return; } - xen_sched_clock_offset = xen_clocksource_read(); - pv_ops.time = xen_time_ops; + xen_init_time_common(); + x86_init.timers.setup_percpu_clockev = xen_time_init; x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents; - x86_platform.calibrate_tsc = xen_tsc_khz; - x86_platform.get_wallclock = xen_get_wallclock; x86_platform.set_wallclock = xen_set_wallclock; } #endif diff --git a/arch/xtensa/kernel/coprocessor.S b/arch/xtensa/kernel/coprocessor.S index c426b846beef..45cc0ae0af6f 100644 --- a/arch/xtensa/kernel/coprocessor.S +++ b/arch/xtensa/kernel/coprocessor.S @@ -100,37 +100,6 @@ LOAD_CP_REGS_TAB(7) /* - * coprocessor_flush(struct thread_info*, index) - * a2 a3 - * - * Save coprocessor registers for coprocessor 'index'. - * The register values are saved to or loaded from the coprocessor area - * inside the task_info structure. - * - * Note that this function doesn't update the coprocessor_owner information! - * - */ - -ENTRY(coprocessor_flush) - - /* reserve 4 bytes on stack to save a0 */ - abi_entry(4) - - s32i a0, a1, 0 - movi a0, .Lsave_cp_regs_jump_table - addx8 a3, a3, a0 - l32i a4, a3, 4 - l32i a3, a3, 0 - add a2, a2, a4 - beqz a3, 1f - callx0 a3 -1: l32i a0, a1, 0 - - abi_ret(4) - -ENDPROC(coprocessor_flush) - -/* * Entry condition: * * a0: trashed, original value saved on stack (PT_AREG0) @@ -245,6 +214,39 @@ ENTRY(fast_coprocessor) ENDPROC(fast_coprocessor) + .text + +/* + * coprocessor_flush(struct thread_info*, index) + * a2 a3 + * + * Save coprocessor registers for coprocessor 'index'. + * The register values are saved to or loaded from the coprocessor area + * inside the task_info structure. + * + * Note that this function doesn't update the coprocessor_owner information! + * + */ + +ENTRY(coprocessor_flush) + + /* reserve 4 bytes on stack to save a0 */ + abi_entry(4) + + s32i a0, a1, 0 + movi a0, .Lsave_cp_regs_jump_table + addx8 a3, a3, a0 + l32i a4, a3, 4 + l32i a3, a3, 0 + add a2, a2, a4 + beqz a3, 1f + callx0 a3 +1: l32i a0, a1, 0 + + abi_ret(4) + +ENDPROC(coprocessor_flush) + .data ENTRY(coprocessor_owner) diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 7666408ce12a..95a74890c7e9 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -112,8 +112,11 @@ good_area: */ fault = handle_mm_fault(vma, address, flags, regs); - if (fault_signal_pending(fault, regs)) + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + goto bad_page_fault; return; + } if (unlikely(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_OOM) diff --git a/block/bio.c b/block/bio.c index 26b7f721cda8..50e579088aca 100644 --- a/block/bio.c +++ b/block/bio.c @@ -277,7 +277,7 @@ static struct bio *__bio_chain_endio(struct bio *bio) { struct bio *parent = bio->bi_private; - if (!parent->bi_status) + if (bio->bi_status && !parent->bi_status) parent->bi_status = bio->bi_status; bio_put(bio); return parent; @@ -949,7 +949,7 @@ void bio_release_pages(struct bio *bio, bool mark_dirty) } EXPORT_SYMBOL_GPL(bio_release_pages); -static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) +static void __bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) { WARN_ON_ONCE(bio->bi_max_vecs); @@ -959,11 +959,26 @@ static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) bio->bi_iter.bi_size = iter->count; bio_set_flag(bio, BIO_NO_PAGE_REF); bio_set_flag(bio, BIO_CLONED); +} +static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) +{ + __bio_iov_bvec_set(bio, iter); iov_iter_advance(iter, iter->count); return 0; } +static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter) +{ + struct request_queue *q = bio->bi_bdev->bd_disk->queue; + struct iov_iter i = *iter; + + iov_iter_truncate(&i, queue_max_zone_append_sectors(q) << 9); + __bio_iov_bvec_set(bio, &i); + iov_iter_advance(iter, i.count); + return 0; +} + #define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) /** @@ -1094,8 +1109,8 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) int ret = 0; if (iov_iter_is_bvec(iter)) { - if (WARN_ON_ONCE(bio_op(bio) == REQ_OP_ZONE_APPEND)) - return -EINVAL; + if (bio_op(bio) == REQ_OP_ZONE_APPEND) + return bio_iov_bvec_set_append(bio, iter); return bio_iov_bvec_set(bio, iter); } diff --git a/block/blk-merge.c b/block/blk-merge.c index ffb4aa0ea68b..4d97fb6dd226 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -382,6 +382,14 @@ unsigned int blk_recalc_rq_segments(struct request *rq) switch (bio_op(rq->bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: + if (queue_max_discard_segments(rq->q) > 1) { + struct bio *bio = rq->bio; + + for_each_bio(bio) + nr_phys_segs++; + return nr_phys_segs; + } + return 1; case REQ_OP_WRITE_ZEROES: return 0; case REQ_OP_WRITE_SAME: diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 9ebb344e2585..271f6596435b 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -302,7 +302,6 @@ static const char *const rqf_name[] = { RQF_NAME(QUIET), RQF_NAME(ELVPRIV), RQF_NAME(IO_STAT), - RQF_NAME(ALLOCED), RQF_NAME(PM), RQF_NAME(HASHED), RQF_NAME(STATS), diff --git a/block/ioctl.c b/block/ioctl.c index ff241e663c01..8ba1ed8defd0 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -89,6 +89,8 @@ static int blkdev_reread_part(struct block_device *bdev, fmode_t mode) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EACCES; + if (bdev->bd_part_count) + return -EBUSY; /* * Reopen the device to revalidate the driver state and force a diff --git a/block/partitions/core.c b/block/partitions/core.c index 1a7558917c47..46f055bc7ecb 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -323,6 +323,13 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, int err; /* + * disk_max_parts() won't be zero, either GENHD_FL_EXT_DEVT is set + * or 'minors' is passed to alloc_disk(). + */ + if (partno >= disk_max_parts(disk)) + return ERR_PTR(-EINVAL); + + /* * Partitions are not supported on zoned block devices that are used as * such. */ diff --git a/certs/Kconfig b/certs/Kconfig index c94e93d8bccf..ab88d2a7f3c7 100644 --- a/certs/Kconfig +++ b/certs/Kconfig @@ -83,4 +83,21 @@ config SYSTEM_BLACKLIST_HASH_LIST wrapper to incorporate the list into the kernel. Each <hash> should be a string of hex digits. +config SYSTEM_REVOCATION_LIST + bool "Provide system-wide ring of revocation certificates" + depends on SYSTEM_BLACKLIST_KEYRING + depends on PKCS7_MESSAGE_PARSER=y + help + If set, this allows revocation certificates to be stored in the + blacklist keyring and implements a hook whereby a PKCS#7 message can + be checked to see if it matches such a certificate. + +config SYSTEM_REVOCATION_KEYS + string "X.509 certificates to be preloaded into the system blacklist keyring" + depends on SYSTEM_REVOCATION_LIST + help + If set, this option should be the filename of a PEM-formatted file + containing X.509 certificates to be included in the default blacklist + keyring. + endmenu diff --git a/certs/Makefile b/certs/Makefile index f4c25b67aad9..b6db52ebf0be 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -3,8 +3,9 @@ # Makefile for the linux kernel signature checking certificates. # -obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o -obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o +obj-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += system_keyring.o system_certificates.o common.o +obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist.o common.o +obj-$(CONFIG_SYSTEM_REVOCATION_LIST) += revocation_certificates.o ifneq ($(CONFIG_SYSTEM_BLACKLIST_HASH_LIST),"") obj-$(CONFIG_SYSTEM_BLACKLIST_KEYRING) += blacklist_hashes.o else @@ -29,7 +30,7 @@ $(obj)/x509_certificate_list: scripts/extract-cert $(SYSTEM_TRUSTED_KEYS_SRCPREF $(call if_changed,extract_certs,$(SYSTEM_TRUSTED_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_TRUSTED_KEYS)) endif # CONFIG_SYSTEM_TRUSTED_KEYRING -clean-files := x509_certificate_list .x509.list +clean-files := x509_certificate_list .x509.list x509_revocation_list ifeq ($(CONFIG_MODULE_SIG),y) ############################################################################### @@ -104,3 +105,17 @@ targets += signing_key.x509 $(obj)/signing_key.x509: scripts/extract-cert $(X509_DEP) FORCE $(call if_changed,extract_certs,$(MODULE_SIG_KEY_SRCPREFIX)$(CONFIG_MODULE_SIG_KEY)) endif # CONFIG_MODULE_SIG + +ifeq ($(CONFIG_SYSTEM_REVOCATION_LIST),y) + +$(eval $(call config_filename,SYSTEM_REVOCATION_KEYS)) + +$(obj)/revocation_certificates.o: $(obj)/x509_revocation_list + +quiet_cmd_extract_certs = EXTRACT_CERTS $(patsubst "%",%,$(2)) + cmd_extract_certs = scripts/extract-cert $(2) $@ + +targets += x509_revocation_list +$(obj)/x509_revocation_list: scripts/extract-cert $(SYSTEM_REVOCATION_KEYS_SRCPREFIX)$(SYSTEM_REVOCATION_KEYS_FILENAME) FORCE + $(call if_changed,extract_certs,$(SYSTEM_REVOCATION_KEYS_SRCPREFIX)$(CONFIG_SYSTEM_REVOCATION_KEYS)) +endif diff --git a/certs/blacklist.c b/certs/blacklist.c index bffe4c6f4a9e..c9a435b15af4 100644 --- a/certs/blacklist.c +++ b/certs/blacklist.c @@ -17,9 +17,15 @@ #include <linux/uidgid.h> #include <keys/system_keyring.h> #include "blacklist.h" +#include "common.h" static struct key *blacklist_keyring; +#ifdef CONFIG_SYSTEM_REVOCATION_LIST +extern __initconst const u8 revocation_certificate_list[]; +extern __initconst const unsigned long revocation_certificate_list_size; +#endif + /* * The description must be a type prefix, a colon and then an even number of * hex digits. The hash is kept in the description. @@ -145,6 +151,49 @@ int is_binary_blacklisted(const u8 *hash, size_t hash_len) } EXPORT_SYMBOL_GPL(is_binary_blacklisted); +#ifdef CONFIG_SYSTEM_REVOCATION_LIST +/** + * add_key_to_revocation_list - Add a revocation certificate to the blacklist + * @data: The data blob containing the certificate + * @size: The size of data blob + */ +int add_key_to_revocation_list(const char *data, size_t size) +{ + key_ref_t key; + + key = key_create_or_update(make_key_ref(blacklist_keyring, true), + "asymmetric", + NULL, + data, + size, + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_VIEW), + KEY_ALLOC_NOT_IN_QUOTA | KEY_ALLOC_BUILT_IN); + + if (IS_ERR(key)) { + pr_err("Problem with revocation key (%ld)\n", PTR_ERR(key)); + return PTR_ERR(key); + } + + return 0; +} + +/** + * is_key_on_revocation_list - Determine if the key for a PKCS#7 message is revoked + * @pkcs7: The PKCS#7 message to check + */ +int is_key_on_revocation_list(struct pkcs7_message *pkcs7) +{ + int ret; + + ret = pkcs7_validate_trust(pkcs7, blacklist_keyring); + + if (ret == 0) + return -EKEYREJECTED; + + return -ENOKEY; +} +#endif + /* * Initialise the blacklist */ @@ -177,3 +226,18 @@ static int __init blacklist_init(void) * Must be initialised before we try and load the keys into the keyring. */ device_initcall(blacklist_init); + +#ifdef CONFIG_SYSTEM_REVOCATION_LIST +/* + * Load the compiled-in list of revocation X.509 certificates. + */ +static __init int load_revocation_certificate_list(void) +{ + if (revocation_certificate_list_size) + pr_notice("Loading compiled-in revocation X.509 certificates\n"); + + return load_certificate_list(revocation_certificate_list, revocation_certificate_list_size, + blacklist_keyring); +} +late_initcall(load_revocation_certificate_list); +#endif diff --git a/certs/blacklist.h b/certs/blacklist.h index 1efd6fa0dc60..51b320cf8574 100644 --- a/certs/blacklist.h +++ b/certs/blacklist.h @@ -1,3 +1,5 @@ #include <linux/kernel.h> +#include <linux/errno.h> +#include <crypto/pkcs7.h> extern const char __initconst *const blacklist_hashes[]; diff --git a/certs/common.c b/certs/common.c new file mode 100644 index 000000000000..16a220887a53 --- /dev/null +++ b/certs/common.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/kernel.h> +#include <linux/key.h> +#include "common.h" + +int load_certificate_list(const u8 cert_list[], + const unsigned long list_size, + const struct key *keyring) +{ + key_ref_t key; + const u8 *p, *end; + size_t plen; + + p = cert_list; + end = p + list_size; + while (p < end) { + /* Each cert begins with an ASN.1 SEQUENCE tag and must be more + * than 256 bytes in size. + */ + if (end - p < 4) + goto dodgy_cert; + if (p[0] != 0x30 && + p[1] != 0x82) + goto dodgy_cert; + plen = (p[2] << 8) | p[3]; + plen += 4; + if (plen > end - p) + goto dodgy_cert; + + key = key_create_or_update(make_key_ref(keyring, 1), + "asymmetric", + NULL, + p, + plen, + ((KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ), + KEY_ALLOC_NOT_IN_QUOTA | + KEY_ALLOC_BUILT_IN | + KEY_ALLOC_BYPASS_RESTRICTION); + if (IS_ERR(key)) { + pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", + PTR_ERR(key)); + } else { + pr_notice("Loaded X.509 cert '%s'\n", + key_ref_to_ptr(key)->description); + key_ref_put(key); + } + p += plen; + } + + return 0; + +dodgy_cert: + pr_err("Problem parsing in-kernel X.509 certificate list\n"); + return 0; +} diff --git a/certs/common.h b/certs/common.h new file mode 100644 index 000000000000..abdb5795936b --- /dev/null +++ b/certs/common.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _CERT_COMMON_H +#define _CERT_COMMON_H + +int load_certificate_list(const u8 cert_list[], const unsigned long list_size, + const struct key *keyring); + +#endif diff --git a/certs/revocation_certificates.S b/certs/revocation_certificates.S new file mode 100644 index 000000000000..f21aae8a8f0e --- /dev/null +++ b/certs/revocation_certificates.S @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/export.h> +#include <linux/init.h> + + __INITRODATA + + .align 8 + .globl revocation_certificate_list +revocation_certificate_list: +__revocation_list_start: + .incbin "certs/x509_revocation_list" +__revocation_list_end: + + .align 8 + .globl revocation_certificate_list_size +revocation_certificate_list_size: +#ifdef CONFIG_64BIT + .quad __revocation_list_end - __revocation_list_start +#else + .long __revocation_list_end - __revocation_list_start +#endif diff --git a/certs/system_keyring.c b/certs/system_keyring.c index 4b693da488f1..0c9a4795e847 100644 --- a/certs/system_keyring.c +++ b/certs/system_keyring.c @@ -16,6 +16,7 @@ #include <keys/asymmetric-type.h> #include <keys/system_keyring.h> #include <crypto/pkcs7.h> +#include "common.h" static struct key *builtin_trusted_keys; #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING @@ -137,54 +138,10 @@ device_initcall(system_trusted_keyring_init); */ static __init int load_system_certificate_list(void) { - key_ref_t key; - const u8 *p, *end; - size_t plen; - pr_notice("Loading compiled-in X.509 certificates\n"); - p = system_certificate_list; - end = p + system_certificate_list_size; - while (p < end) { - /* Each cert begins with an ASN.1 SEQUENCE tag and must be more - * than 256 bytes in size. - */ - if (end - p < 4) - goto dodgy_cert; - if (p[0] != 0x30 && - p[1] != 0x82) - goto dodgy_cert; - plen = (p[2] << 8) | p[3]; - plen += 4; - if (plen > end - p) - goto dodgy_cert; - - key = key_create_or_update(make_key_ref(builtin_trusted_keys, 1), - "asymmetric", - NULL, - p, - plen, - ((KEY_POS_ALL & ~KEY_POS_SETATTR) | - KEY_USR_VIEW | KEY_USR_READ), - KEY_ALLOC_NOT_IN_QUOTA | - KEY_ALLOC_BUILT_IN | - KEY_ALLOC_BYPASS_RESTRICTION); - if (IS_ERR(key)) { - pr_err("Problem loading in-kernel X.509 certificate (%ld)\n", - PTR_ERR(key)); - } else { - pr_notice("Loaded X.509 cert '%s'\n", - key_ref_to_ptr(key)->description); - key_ref_put(key); - } - p += plen; - } - - return 0; - -dodgy_cert: - pr_err("Problem parsing in-kernel X.509 certificate list\n"); - return 0; + return load_certificate_list(system_certificate_list, system_certificate_list_size, + builtin_trusted_keys); } late_initcall(load_system_certificate_list); @@ -242,6 +199,12 @@ int verify_pkcs7_message_sig(const void *data, size_t len, pr_devel("PKCS#7 platform keyring is not available\n"); goto error; } + + ret = is_key_on_revocation_list(pkcs7); + if (ret != -ENOKEY) { + pr_devel("PKCS#7 platform key is on revocation list\n"); + goto error; + } } ret = pkcs7_validate_trust(pkcs7, trusted_keys); if (ret < 0) { diff --git a/crypto/Kconfig b/crypto/Kconfig index 5809cc198fa7..ca3b02dcbbfa 100644 --- a/crypto/Kconfig +++ b/crypto/Kconfig @@ -242,6 +242,16 @@ config CRYPTO_ECDH help Generic implementation of the ECDH algorithm +config CRYPTO_ECDSA + tristate "ECDSA (NIST P192, P256 etc.) algorithm" + select CRYPTO_ECC + select CRYPTO_AKCIPHER + select ASN1 + help + Elliptic Curve Digital Signature Algorithm (NIST P192, P256 etc.) + is A NIST cryptographic standard algorithm. Only signature verification + is implemented. + config CRYPTO_ECRDSA tristate "EC-RDSA (GOST 34.10) algorithm" select CRYPTO_ECC @@ -1213,7 +1223,6 @@ config CRYPTO_BLOWFISH_X86_64 config CRYPTO_CAMELLIA tristate "Camellia cipher algorithms" - depends on CRYPTO select CRYPTO_ALGAPI help Camellia cipher algorithms module. @@ -1229,7 +1238,6 @@ config CRYPTO_CAMELLIA config CRYPTO_CAMELLIA_X86_64 tristate "Camellia cipher algorithm (x86_64)" depends on X86 && 64BIT - depends on CRYPTO select CRYPTO_SKCIPHER imply CRYPTO_CTR help @@ -1246,7 +1254,6 @@ config CRYPTO_CAMELLIA_X86_64 config CRYPTO_CAMELLIA_AESNI_AVX_X86_64 tristate "Camellia cipher algorithm (x86_64/AES-NI/AVX)" depends on X86 && 64BIT - depends on CRYPTO select CRYPTO_SKCIPHER select CRYPTO_CAMELLIA_X86_64 select CRYPTO_SIMD @@ -1265,7 +1272,6 @@ config CRYPTO_CAMELLIA_AESNI_AVX_X86_64 config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64 tristate "Camellia cipher algorithm (x86_64/AES-NI/AVX2)" depends on X86 && 64BIT - depends on CRYPTO select CRYPTO_CAMELLIA_AESNI_AVX_X86_64 help Camellia cipher algorithm module (x86_64/AES-NI/AVX2). @@ -1281,7 +1287,6 @@ config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64 config CRYPTO_CAMELLIA_SPARC64 tristate "Camellia cipher algorithm (SPARC64)" depends on SPARC64 - depends on CRYPTO select CRYPTO_ALGAPI select CRYPTO_SKCIPHER help diff --git a/crypto/Makefile b/crypto/Makefile index cf23affb1678..10526d4559b8 100644 --- a/crypto/Makefile +++ b/crypto/Makefile @@ -50,6 +50,12 @@ sm2_generic-y += sm2.o obj-$(CONFIG_CRYPTO_SM2) += sm2_generic.o +$(obj)/ecdsasignature.asn1.o: $(obj)/ecdsasignature.asn1.c $(obj)/ecdsasignature.asn1.h +$(obj)/ecdsa.o: $(obj)/ecdsasignature.asn1.h +ecdsa_generic-y += ecdsa.o +ecdsa_generic-y += ecdsasignature.asn1.o +obj-$(CONFIG_CRYPTO_ECDSA) += ecdsa_generic.o + crypto_acompress-y := acompress.o crypto_acompress-y += scompress.o obj-$(CONFIG_CRYPTO_ACOMP2) += crypto_acompress.o diff --git a/crypto/aegis.h b/crypto/aegis.h index 6920ebe77679..6ef9c174c973 100644 --- a/crypto/aegis.h +++ b/crypto/aegis.h @@ -21,9 +21,28 @@ union aegis_block { u8 bytes[AEGIS_BLOCK_SIZE]; }; +struct aegis_state; + +extern int aegis128_have_aes_insn; + #define AEGIS_BLOCK_ALIGN (__alignof__(union aegis_block)) #define AEGIS_ALIGNED(p) IS_ALIGNED((uintptr_t)p, AEGIS_BLOCK_ALIGN) +bool crypto_aegis128_have_simd(void); +void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg); +void crypto_aegis128_init_simd(struct aegis_state *state, + const union aegis_block *key, + const u8 *iv); +void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst, + const u8 *src, unsigned int size); +void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst, + const u8 *src, unsigned int size); +int crypto_aegis128_final_simd(struct aegis_state *state, + union aegis_block *tag_xor, + unsigned int assoclen, + unsigned int cryptlen, + unsigned int authsize); + static __always_inline void crypto_aegis_block_xor(union aegis_block *dst, const union aegis_block *src) { diff --git a/crypto/aegis128-core.c b/crypto/aegis128-core.c index 89dc1c559689..c4f1bfa1d04f 100644 --- a/crypto/aegis128-core.c +++ b/crypto/aegis128-core.c @@ -58,21 +58,6 @@ static bool aegis128_do_simd(void) return false; } -bool crypto_aegis128_have_simd(void); -void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg); -void crypto_aegis128_init_simd(struct aegis_state *state, - const union aegis_block *key, - const u8 *iv); -void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst, - const u8 *src, unsigned int size); -void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst, - const u8 *src, unsigned int size); -int crypto_aegis128_final_simd(struct aegis_state *state, - union aegis_block *tag_xor, - unsigned int assoclen, - unsigned int cryptlen, - unsigned int authsize); - static void crypto_aegis128_update(struct aegis_state *state) { union aegis_block tmp; diff --git a/crypto/aegis128-neon.c b/crypto/aegis128-neon.c index 94d591a002a4..a7856915ec85 100644 --- a/crypto/aegis128-neon.c +++ b/crypto/aegis128-neon.c @@ -30,7 +30,7 @@ bool crypto_aegis128_have_simd(void) return IS_ENABLED(CONFIG_ARM64); } -void crypto_aegis128_init_simd(union aegis_block *state, +void crypto_aegis128_init_simd(struct aegis_state *state, const union aegis_block *key, const u8 *iv) { @@ -39,14 +39,14 @@ void crypto_aegis128_init_simd(union aegis_block *state, kernel_neon_end(); } -void crypto_aegis128_update_simd(union aegis_block *state, const void *msg) +void crypto_aegis128_update_simd(struct aegis_state *state, const void *msg) { kernel_neon_begin(); crypto_aegis128_update_neon(state, msg); kernel_neon_end(); } -void crypto_aegis128_encrypt_chunk_simd(union aegis_block *state, u8 *dst, +void crypto_aegis128_encrypt_chunk_simd(struct aegis_state *state, u8 *dst, const u8 *src, unsigned int size) { kernel_neon_begin(); @@ -54,7 +54,7 @@ void crypto_aegis128_encrypt_chunk_simd(union aegis_block *state, u8 *dst, kernel_neon_end(); } -void crypto_aegis128_decrypt_chunk_simd(union aegis_block *state, u8 *dst, +void crypto_aegis128_decrypt_chunk_simd(struct aegis_state *state, u8 *dst, const u8 *src, unsigned int size) { kernel_neon_begin(); @@ -62,7 +62,7 @@ void crypto_aegis128_decrypt_chunk_simd(union aegis_block *state, u8 *dst, kernel_neon_end(); } -int crypto_aegis128_final_simd(union aegis_block *state, +int crypto_aegis128_final_simd(struct aegis_state *state, union aegis_block *tag_xor, unsigned int assoclen, unsigned int cryptlen, diff --git a/crypto/af_alg.c b/crypto/af_alg.c index 9acb9d2c4bcf..18cc82dc4a42 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -491,8 +491,8 @@ static int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con) /** * af_alg_alloc_tsgl - allocate the TX SGL * - * @sk socket of connection to user space - * @return: 0 upon success, < 0 upon error + * @sk: socket of connection to user space + * Return: 0 upon success, < 0 upon error */ static int af_alg_alloc_tsgl(struct sock *sk) { @@ -525,15 +525,15 @@ static int af_alg_alloc_tsgl(struct sock *sk) } /** - * aead_count_tsgl - Count number of TX SG entries + * af_alg_count_tsgl - Count number of TX SG entries * * The counting starts from the beginning of the SGL to @bytes. If - * an offset is provided, the counting of the SG entries starts at the offset. + * an @offset is provided, the counting of the SG entries starts at the @offset. * - * @sk socket of connection to user space - * @bytes Count the number of SG entries holding given number of bytes. - * @offset Start the counting of SG entries from the given offset. - * @return Number of TX SG entries found given the constraints + * @sk: socket of connection to user space + * @bytes: Count the number of SG entries holding given number of bytes. + * @offset: Start the counting of SG entries from the given offset. + * Return: Number of TX SG entries found given the constraints */ unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset) { @@ -577,19 +577,19 @@ unsigned int af_alg_count_tsgl(struct sock *sk, size_t bytes, size_t offset) EXPORT_SYMBOL_GPL(af_alg_count_tsgl); /** - * aead_pull_tsgl - Release the specified buffers from TX SGL + * af_alg_pull_tsgl - Release the specified buffers from TX SGL * - * If @dst is non-null, reassign the pages to dst. The caller must release + * If @dst is non-null, reassign the pages to @dst. The caller must release * the pages. If @dst_offset is given only reassign the pages to @dst starting * at the @dst_offset (byte). The caller must ensure that @dst is large * enough (e.g. by using af_alg_count_tsgl with the same offset). * - * @sk socket of connection to user space - * @used Number of bytes to pull from TX SGL - * @dst If non-NULL, buffer is reassigned to dst SGL instead of releasing. The - * caller must release the buffers in dst. - * @dst_offset Reassign the TX SGL from given offset. All buffers before - * reaching the offset is released. + * @sk: socket of connection to user space + * @used: Number of bytes to pull from TX SGL + * @dst: If non-NULL, buffer is reassigned to dst SGL instead of releasing. The + * caller must release the buffers in dst. + * @dst_offset: Reassign the TX SGL from given offset. All buffers before + * reaching the offset is released. */ void af_alg_pull_tsgl(struct sock *sk, size_t used, struct scatterlist *dst, size_t dst_offset) @@ -657,7 +657,7 @@ EXPORT_SYMBOL_GPL(af_alg_pull_tsgl); /** * af_alg_free_areq_sgls - Release TX and RX SGLs of the request * - * @areq Request holding the TX and RX SGL + * @areq: Request holding the TX and RX SGL */ static void af_alg_free_areq_sgls(struct af_alg_async_req *areq) { @@ -692,9 +692,9 @@ static void af_alg_free_areq_sgls(struct af_alg_async_req *areq) /** * af_alg_wait_for_wmem - wait for availability of writable memory * - * @sk socket of connection to user space - * @flags If MSG_DONTWAIT is set, then only report if function would sleep - * @return 0 when writable memory is available, < 0 upon error + * @sk: socket of connection to user space + * @flags: If MSG_DONTWAIT is set, then only report if function would sleep + * Return: 0 when writable memory is available, < 0 upon error */ static int af_alg_wait_for_wmem(struct sock *sk, unsigned int flags) { @@ -725,7 +725,7 @@ static int af_alg_wait_for_wmem(struct sock *sk, unsigned int flags) /** * af_alg_wmem_wakeup - wakeup caller when writable memory is available * - * @sk socket of connection to user space + * @sk: socket of connection to user space */ void af_alg_wmem_wakeup(struct sock *sk) { @@ -748,10 +748,10 @@ EXPORT_SYMBOL_GPL(af_alg_wmem_wakeup); /** * af_alg_wait_for_data - wait for availability of TX data * - * @sk socket of connection to user space - * @flags If MSG_DONTWAIT is set, then only report if function would sleep - * @min Set to minimum request size if partial requests are allowed. - * @return 0 when writable memory is available, < 0 upon error + * @sk: socket of connection to user space + * @flags: If MSG_DONTWAIT is set, then only report if function would sleep + * @min: Set to minimum request size if partial requests are allowed. + * Return: 0 when writable memory is available, < 0 upon error */ int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min) { @@ -790,7 +790,7 @@ EXPORT_SYMBOL_GPL(af_alg_wait_for_data); /** * af_alg_data_wakeup - wakeup caller when new data can be sent to kernel * - * @sk socket of connection to user space + * @sk: socket of connection to user space */ static void af_alg_data_wakeup(struct sock *sk) { @@ -820,12 +820,12 @@ static void af_alg_data_wakeup(struct sock *sk) * * In addition, the ctx is filled with the information sent via CMSG. * - * @sock socket of connection to user space - * @msg message from user space - * @size size of message from user space - * @ivsize the size of the IV for the cipher operation to verify that the + * @sock: socket of connection to user space + * @msg: message from user space + * @size: size of message from user space + * @ivsize: the size of the IV for the cipher operation to verify that the * user-space-provided IV has the right size - * @return the number of copied data upon success, < 0 upon error + * Return: the number of copied data upon success, < 0 upon error */ int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, unsigned int ivsize) @@ -977,6 +977,11 @@ EXPORT_SYMBOL_GPL(af_alg_sendmsg); /** * af_alg_sendpage - sendpage system call handler + * @sock: socket of connection to user space to write to + * @page: data to send + * @offset: offset into page to begin sending + * @size: length of data + * @flags: message send/receive flags * * This is a generic implementation of sendpage to fill ctx->tsgl_list. */ @@ -1035,6 +1040,7 @@ EXPORT_SYMBOL_GPL(af_alg_sendpage); /** * af_alg_free_resources - release resources required for crypto request + * @areq: Request holding the TX and RX SGL */ void af_alg_free_resources(struct af_alg_async_req *areq) { @@ -1047,6 +1053,9 @@ EXPORT_SYMBOL_GPL(af_alg_free_resources); /** * af_alg_async_cb - AIO callback handler + * @_req: async request info + * @err: if non-zero, error result to be returned via ki_complete(); + * otherwise return the AIO output length via ki_complete(). * * This handler cleans up the struct af_alg_async_req upon completion of the * AIO operation. @@ -1073,6 +1082,9 @@ EXPORT_SYMBOL_GPL(af_alg_async_cb); /** * af_alg_poll - poll system call handler + * @file: file pointer + * @sock: socket to poll + * @wait: poll_table */ __poll_t af_alg_poll(struct file *file, struct socket *sock, poll_table *wait) @@ -1098,9 +1110,9 @@ EXPORT_SYMBOL_GPL(af_alg_poll); /** * af_alg_alloc_areq - allocate struct af_alg_async_req * - * @sk socket of connection to user space - * @areqlen size of struct af_alg_async_req + crypto_*_reqsize - * @return allocated data structure or ERR_PTR upon error + * @sk: socket of connection to user space + * @areqlen: size of struct af_alg_async_req + crypto_*_reqsize + * Return: allocated data structure or ERR_PTR upon error */ struct af_alg_async_req *af_alg_alloc_areq(struct sock *sk, unsigned int areqlen) @@ -1125,13 +1137,13 @@ EXPORT_SYMBOL_GPL(af_alg_alloc_areq); * af_alg_get_rsgl - create the RX SGL for the output data from the crypto * operation * - * @sk socket of connection to user space - * @msg user space message - * @flags flags used to invoke recvmsg with - * @areq instance of the cryptographic request that will hold the RX SGL - * @maxsize maximum number of bytes to be pulled from user space - * @outlen number of bytes in the RX SGL - * @return 0 on success, < 0 upon error + * @sk: socket of connection to user space + * @msg: user space message + * @flags: flags used to invoke recvmsg with + * @areq: instance of the cryptographic request that will hold the RX SGL + * @maxsize: maximum number of bytes to be pulled from user space + * @outlen: number of bytes in the RX SGL + * Return: 0 on success, < 0 upon error */ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags, struct af_alg_async_req *areq, size_t maxsize, diff --git a/crypto/api.c b/crypto/api.c index ed08cbd5b9d3..c4eda56cff89 100644 --- a/crypto/api.c +++ b/crypto/api.c @@ -562,7 +562,7 @@ void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm) { struct crypto_alg *alg; - if (unlikely(!mem)) + if (IS_ERR_OR_NULL(mem)) return; alg = tfm->__crt_alg; diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index 788a4ba1e2e7..4fefb219bfdc 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/seq_file.h> #include <linux/scatterlist.h> +#include <linux/asn1.h> #include <keys/asymmetric-subtype.h> #include <crypto/public_key.h> #include <crypto/akcipher.h> @@ -85,7 +86,8 @@ int software_key_determine_akcipher(const char *encoding, return n >= CRYPTO_MAX_ALG_NAME ? -EINVAL : 0; } - if (strcmp(encoding, "raw") == 0) { + if (strcmp(encoding, "raw") == 0 || + strcmp(encoding, "x962") == 0) { strcpy(alg_name, pkey->pkey_algo); return 0; } diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c index 52c9b455fc7d..6d003096b5bc 100644 --- a/crypto/asymmetric_keys/x509_cert_parser.c +++ b/crypto/asymmetric_keys/x509_cert_parser.c @@ -227,6 +227,26 @@ int x509_note_pkey_algo(void *context, size_t hdrlen, ctx->cert->sig->hash_algo = "sha224"; goto rsa_pkcs1; + case OID_id_ecdsa_with_sha1: + ctx->cert->sig->hash_algo = "sha1"; + goto ecdsa; + + case OID_id_ecdsa_with_sha224: + ctx->cert->sig->hash_algo = "sha224"; + goto ecdsa; + + case OID_id_ecdsa_with_sha256: + ctx->cert->sig->hash_algo = "sha256"; + goto ecdsa; + + case OID_id_ecdsa_with_sha384: + ctx->cert->sig->hash_algo = "sha384"; + goto ecdsa; + + case OID_id_ecdsa_with_sha512: + ctx->cert->sig->hash_algo = "sha512"; + goto ecdsa; + case OID_gost2012Signature256: ctx->cert->sig->hash_algo = "streebog256"; goto ecrdsa; @@ -255,6 +275,11 @@ sm2: ctx->cert->sig->encoding = "raw"; ctx->algo_oid = ctx->last_oid; return 0; +ecdsa: + ctx->cert->sig->pkey_algo = "ecdsa"; + ctx->cert->sig->encoding = "x962"; + ctx->algo_oid = ctx->last_oid; + return 0; } /* @@ -276,7 +301,8 @@ int x509_note_signature(void *context, size_t hdrlen, if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0 || strcmp(ctx->cert->sig->pkey_algo, "ecrdsa") == 0 || - strcmp(ctx->cert->sig->pkey_algo, "sm2") == 0) { + strcmp(ctx->cert->sig->pkey_algo, "sm2") == 0 || + strcmp(ctx->cert->sig->pkey_algo, "ecdsa") == 0) { /* Discard the BIT STRING metadata */ if (vlen < 1 || *(const u8 *)value != 0) return -EBADMSG; @@ -459,6 +485,7 @@ int x509_extract_key_data(void *context, size_t hdrlen, const void *value, size_t vlen) { struct x509_parse_context *ctx = context; + enum OID oid; ctx->key_algo = ctx->last_oid; switch (ctx->last_oid) { @@ -470,7 +497,25 @@ int x509_extract_key_data(void *context, size_t hdrlen, ctx->cert->pub->pkey_algo = "ecrdsa"; break; case OID_id_ecPublicKey: - ctx->cert->pub->pkey_algo = "sm2"; + if (parse_OID(ctx->params, ctx->params_size, &oid) != 0) + return -EBADMSG; + + switch (oid) { + case OID_sm2: + ctx->cert->pub->pkey_algo = "sm2"; + break; + case OID_id_prime192v1: + ctx->cert->pub->pkey_algo = "ecdsa-nist-p192"; + break; + case OID_id_prime256v1: + ctx->cert->pub->pkey_algo = "ecdsa-nist-p256"; + break; + case OID_id_ansip384r1: + ctx->cert->pub->pkey_algo = "ecdsa-nist-p384"; + break; + default: + return -ENOPKG; + } break; default: return -ENOPKG; diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c index ae450eb8be14..3d45161b271a 100644 --- a/crypto/asymmetric_keys/x509_public_key.c +++ b/crypto/asymmetric_keys/x509_public_key.c @@ -129,7 +129,9 @@ int x509_check_for_self_signed(struct x509_certificate *cert) } ret = -EKEYREJECTED; - if (strcmp(cert->pub->pkey_algo, cert->sig->pkey_algo) != 0) + if (strcmp(cert->pub->pkey_algo, cert->sig->pkey_algo) != 0 && + (strncmp(cert->pub->pkey_algo, "ecdsa-", 6) != 0 || + strcmp(cert->sig->pkey_algo, "ecdsa") != 0)) goto out; ret = public_key_verify_signature(cert->pub, cert->sig); diff --git a/crypto/crc32_generic.c b/crypto/crc32_generic.c index 0e103fb5dd77..a989cb44fd16 100644 --- a/crypto/crc32_generic.c +++ b/crypto/crc32_generic.c @@ -1,26 +1,4 @@ -/* GPL HEADER START - * - * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 only, - * as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License version 2 for more details (a copy is included - * in the LICENSE file that accompanied this code). - * - * You should have received a copy of the GNU General Public License - * version 2 along with this program; If not, see http://www.gnu.org/licenses - * - * Please visit http://www.xyratex.com/contact if you need additional - * information or have any questions. - * - * GPL HEADER END - */ - +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2012 Xyratex Technology Limited */ diff --git a/crypto/ecc.c b/crypto/ecc.c index c80aa25994a0..afc6cefdc1d9 100644 --- a/crypto/ecc.c +++ b/crypto/ecc.c @@ -24,6 +24,7 @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +#include <crypto/ecc_curve.h> #include <linux/module.h> #include <linux/random.h> #include <linux/slab.h> @@ -42,7 +43,14 @@ typedef struct { u64 m_high; } uint128_t; -static inline const struct ecc_curve *ecc_get_curve(unsigned int curve_id) +/* Returns curv25519 curve param */ +const struct ecc_curve *ecc_get_curve25519(void) +{ + return &ecc_25519; +} +EXPORT_SYMBOL(ecc_get_curve25519); + +const struct ecc_curve *ecc_get_curve(unsigned int curve_id) { switch (curve_id) { /* In FIPS mode only allow P256 and higher */ @@ -50,10 +58,13 @@ static inline const struct ecc_curve *ecc_get_curve(unsigned int curve_id) return fips_enabled ? NULL : &nist_p192; case ECC_CURVE_NIST_P256: return &nist_p256; + case ECC_CURVE_NIST_P384: + return &nist_p384; default: return NULL; } } +EXPORT_SYMBOL(ecc_get_curve); static u64 *ecc_alloc_digits_space(unsigned int ndigits) { @@ -128,7 +139,7 @@ bool vli_is_zero(const u64 *vli, unsigned int ndigits) } EXPORT_SYMBOL(vli_is_zero); -/* Returns nonzero if bit bit of vli is set. */ +/* Returns nonzero if bit of vli is set. */ static u64 vli_test_bit(const u64 *vli, unsigned int bit) { return (vli[bit / 64] & ((u64)1 << (bit % 64))); @@ -775,18 +786,133 @@ static void vli_mmod_fast_256(u64 *result, const u64 *product, } } +#define SL32OR32(x32, y32) (((u64)x32 << 32) | y32) +#define AND64H(x64) (x64 & 0xffFFffFF00000000ull) +#define AND64L(x64) (x64 & 0x00000000ffFFffFFull) + +/* Computes result = product % curve_prime + * from "Mathematical routines for the NIST prime elliptic curves" + */ +static void vli_mmod_fast_384(u64 *result, const u64 *product, + const u64 *curve_prime, u64 *tmp) +{ + int carry; + const unsigned int ndigits = 6; + + /* t */ + vli_set(result, product, ndigits); + + /* s1 */ + tmp[0] = 0; // 0 || 0 + tmp[1] = 0; // 0 || 0 + tmp[2] = SL32OR32(product[11], (product[10]>>32)); //a22||a21 + tmp[3] = product[11]>>32; // 0 ||a23 + tmp[4] = 0; // 0 || 0 + tmp[5] = 0; // 0 || 0 + carry = vli_lshift(tmp, tmp, 1, ndigits); + carry += vli_add(result, result, tmp, ndigits); + + /* s2 */ + tmp[0] = product[6]; //a13||a12 + tmp[1] = product[7]; //a15||a14 + tmp[2] = product[8]; //a17||a16 + tmp[3] = product[9]; //a19||a18 + tmp[4] = product[10]; //a21||a20 + tmp[5] = product[11]; //a23||a22 + carry += vli_add(result, result, tmp, ndigits); + + /* s3 */ + tmp[0] = SL32OR32(product[11], (product[10]>>32)); //a22||a21 + tmp[1] = SL32OR32(product[6], (product[11]>>32)); //a12||a23 + tmp[2] = SL32OR32(product[7], (product[6])>>32); //a14||a13 + tmp[3] = SL32OR32(product[8], (product[7]>>32)); //a16||a15 + tmp[4] = SL32OR32(product[9], (product[8]>>32)); //a18||a17 + tmp[5] = SL32OR32(product[10], (product[9]>>32)); //a20||a19 + carry += vli_add(result, result, tmp, ndigits); + + /* s4 */ + tmp[0] = AND64H(product[11]); //a23|| 0 + tmp[1] = (product[10]<<32); //a20|| 0 + tmp[2] = product[6]; //a13||a12 + tmp[3] = product[7]; //a15||a14 + tmp[4] = product[8]; //a17||a16 + tmp[5] = product[9]; //a19||a18 + carry += vli_add(result, result, tmp, ndigits); + + /* s5 */ + tmp[0] = 0; // 0|| 0 + tmp[1] = 0; // 0|| 0 + tmp[2] = product[10]; //a21||a20 + tmp[3] = product[11]; //a23||a22 + tmp[4] = 0; // 0|| 0 + tmp[5] = 0; // 0|| 0 + carry += vli_add(result, result, tmp, ndigits); + + /* s6 */ + tmp[0] = AND64L(product[10]); // 0 ||a20 + tmp[1] = AND64H(product[10]); //a21|| 0 + tmp[2] = product[11]; //a23||a22 + tmp[3] = 0; // 0 || 0 + tmp[4] = 0; // 0 || 0 + tmp[5] = 0; // 0 || 0 + carry += vli_add(result, result, tmp, ndigits); + + /* d1 */ + tmp[0] = SL32OR32(product[6], (product[11]>>32)); //a12||a23 + tmp[1] = SL32OR32(product[7], (product[6]>>32)); //a14||a13 + tmp[2] = SL32OR32(product[8], (product[7]>>32)); //a16||a15 + tmp[3] = SL32OR32(product[9], (product[8]>>32)); //a18||a17 + tmp[4] = SL32OR32(product[10], (product[9]>>32)); //a20||a19 + tmp[5] = SL32OR32(product[11], (product[10]>>32)); //a22||a21 + carry -= vli_sub(result, result, tmp, ndigits); + + /* d2 */ + tmp[0] = (product[10]<<32); //a20|| 0 + tmp[1] = SL32OR32(product[11], (product[10]>>32)); //a22||a21 + tmp[2] = (product[11]>>32); // 0 ||a23 + tmp[3] = 0; // 0 || 0 + tmp[4] = 0; // 0 || 0 + tmp[5] = 0; // 0 || 0 + carry -= vli_sub(result, result, tmp, ndigits); + + /* d3 */ + tmp[0] = 0; // 0 || 0 + tmp[1] = AND64H(product[11]); //a23|| 0 + tmp[2] = product[11]>>32; // 0 ||a23 + tmp[3] = 0; // 0 || 0 + tmp[4] = 0; // 0 || 0 + tmp[5] = 0; // 0 || 0 + carry -= vli_sub(result, result, tmp, ndigits); + + if (carry < 0) { + do { + carry += vli_add(result, result, curve_prime, ndigits); + } while (carry < 0); + } else { + while (carry || vli_cmp(curve_prime, result, ndigits) != 1) + carry -= vli_sub(result, result, curve_prime, ndigits); + } + +} + +#undef SL32OR32 +#undef AND64H +#undef AND64L + /* Computes result = product % curve_prime for different curve_primes. * * Note that curve_primes are distinguished just by heuristic check and * not by complete conformance check. */ static bool vli_mmod_fast(u64 *result, u64 *product, - const u64 *curve_prime, unsigned int ndigits) + const struct ecc_curve *curve) { u64 tmp[2 * ECC_MAX_DIGITS]; + const u64 *curve_prime = curve->p; + const unsigned int ndigits = curve->g.ndigits; - /* Currently, both NIST primes have -1 in lowest qword. */ - if (curve_prime[0] != -1ull) { + /* All NIST curves have name prefix 'nist_' */ + if (strncmp(curve->name, "nist_", 5) != 0) { /* Try to handle Pseudo-Marsenne primes. */ if (curve_prime[ndigits - 1] == -1ull) { vli_mmod_special(result, product, curve_prime, @@ -809,6 +935,9 @@ static bool vli_mmod_fast(u64 *result, u64 *product, case 4: vli_mmod_fast_256(result, product, curve_prime, tmp); break; + case 6: + vli_mmod_fast_384(result, product, curve_prime, tmp); + break; default: pr_err_ratelimited("ecc: unsupported digits size!\n"); return false; @@ -832,22 +961,22 @@ EXPORT_SYMBOL(vli_mod_mult_slow); /* Computes result = (left * right) % curve_prime. */ static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right, - const u64 *curve_prime, unsigned int ndigits) + const struct ecc_curve *curve) { u64 product[2 * ECC_MAX_DIGITS]; - vli_mult(product, left, right, ndigits); - vli_mmod_fast(result, product, curve_prime, ndigits); + vli_mult(product, left, right, curve->g.ndigits); + vli_mmod_fast(result, product, curve); } /* Computes result = left^2 % curve_prime. */ static void vli_mod_square_fast(u64 *result, const u64 *left, - const u64 *curve_prime, unsigned int ndigits) + const struct ecc_curve *curve) { u64 product[2 * ECC_MAX_DIGITS]; - vli_square(product, left, ndigits); - vli_mmod_fast(result, product, curve_prime, ndigits); + vli_square(product, left, curve->g.ndigits); + vli_mmod_fast(result, product, curve); } #define EVEN(vli) (!(vli[0] & 1)) @@ -945,25 +1074,27 @@ static bool ecc_point_is_zero(const struct ecc_point *point) /* Double in place */ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1, - u64 *curve_prime, unsigned int ndigits) + const struct ecc_curve *curve) { /* t1 = x, t2 = y, t3 = z */ u64 t4[ECC_MAX_DIGITS]; u64 t5[ECC_MAX_DIGITS]; + const u64 *curve_prime = curve->p; + const unsigned int ndigits = curve->g.ndigits; if (vli_is_zero(z1, ndigits)) return; /* t4 = y1^2 */ - vli_mod_square_fast(t4, y1, curve_prime, ndigits); + vli_mod_square_fast(t4, y1, curve); /* t5 = x1*y1^2 = A */ - vli_mod_mult_fast(t5, x1, t4, curve_prime, ndigits); + vli_mod_mult_fast(t5, x1, t4, curve); /* t4 = y1^4 */ - vli_mod_square_fast(t4, t4, curve_prime, ndigits); + vli_mod_square_fast(t4, t4, curve); /* t2 = y1*z1 = z3 */ - vli_mod_mult_fast(y1, y1, z1, curve_prime, ndigits); + vli_mod_mult_fast(y1, y1, z1, curve); /* t3 = z1^2 */ - vli_mod_square_fast(z1, z1, curve_prime, ndigits); + vli_mod_square_fast(z1, z1, curve); /* t1 = x1 + z1^2 */ vli_mod_add(x1, x1, z1, curve_prime, ndigits); @@ -972,7 +1103,7 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1, /* t3 = x1 - z1^2 */ vli_mod_sub(z1, x1, z1, curve_prime, ndigits); /* t1 = x1^2 - z1^4 */ - vli_mod_mult_fast(x1, x1, z1, curve_prime, ndigits); + vli_mod_mult_fast(x1, x1, z1, curve); /* t3 = 2*(x1^2 - z1^4) */ vli_mod_add(z1, x1, x1, curve_prime, ndigits); @@ -989,7 +1120,7 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1, /* t1 = 3/2*(x1^2 - z1^4) = B */ /* t3 = B^2 */ - vli_mod_square_fast(z1, x1, curve_prime, ndigits); + vli_mod_square_fast(z1, x1, curve); /* t3 = B^2 - A */ vli_mod_sub(z1, z1, t5, curve_prime, ndigits); /* t3 = B^2 - 2A = x3 */ @@ -997,7 +1128,7 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1, /* t5 = A - x3 */ vli_mod_sub(t5, t5, z1, curve_prime, ndigits); /* t1 = B * (A - x3) */ - vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits); + vli_mod_mult_fast(x1, x1, t5, curve); /* t4 = B * (A - x3) - y1^4 = y3 */ vli_mod_sub(t4, x1, t4, curve_prime, ndigits); @@ -1007,23 +1138,22 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1, } /* Modify (x1, y1) => (x1 * z^2, y1 * z^3) */ -static void apply_z(u64 *x1, u64 *y1, u64 *z, u64 *curve_prime, - unsigned int ndigits) +static void apply_z(u64 *x1, u64 *y1, u64 *z, const struct ecc_curve *curve) { u64 t1[ECC_MAX_DIGITS]; - vli_mod_square_fast(t1, z, curve_prime, ndigits); /* z^2 */ - vli_mod_mult_fast(x1, x1, t1, curve_prime, ndigits); /* x1 * z^2 */ - vli_mod_mult_fast(t1, t1, z, curve_prime, ndigits); /* z^3 */ - vli_mod_mult_fast(y1, y1, t1, curve_prime, ndigits); /* y1 * z^3 */ + vli_mod_square_fast(t1, z, curve); /* z^2 */ + vli_mod_mult_fast(x1, x1, t1, curve); /* x1 * z^2 */ + vli_mod_mult_fast(t1, t1, z, curve); /* z^3 */ + vli_mod_mult_fast(y1, y1, t1, curve); /* y1 * z^3 */ } /* P = (x1, y1) => 2P, (x2, y2) => P' */ static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2, - u64 *p_initial_z, u64 *curve_prime, - unsigned int ndigits) + u64 *p_initial_z, const struct ecc_curve *curve) { u64 z[ECC_MAX_DIGITS]; + const unsigned int ndigits = curve->g.ndigits; vli_set(x2, x1, ndigits); vli_set(y2, y1, ndigits); @@ -1034,35 +1164,37 @@ static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2, if (p_initial_z) vli_set(z, p_initial_z, ndigits); - apply_z(x1, y1, z, curve_prime, ndigits); + apply_z(x1, y1, z, curve); - ecc_point_double_jacobian(x1, y1, z, curve_prime, ndigits); + ecc_point_double_jacobian(x1, y1, z, curve); - apply_z(x2, y2, z, curve_prime, ndigits); + apply_z(x2, y2, z, curve); } /* Input P = (x1, y1, Z), Q = (x2, y2, Z) * Output P' = (x1', y1', Z3), P + Q = (x3, y3, Z3) * or P => P', Q => P + Q */ -static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime, - unsigned int ndigits) +static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, + const struct ecc_curve *curve) { /* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */ u64 t5[ECC_MAX_DIGITS]; + const u64 *curve_prime = curve->p; + const unsigned int ndigits = curve->g.ndigits; /* t5 = x2 - x1 */ vli_mod_sub(t5, x2, x1, curve_prime, ndigits); /* t5 = (x2 - x1)^2 = A */ - vli_mod_square_fast(t5, t5, curve_prime, ndigits); + vli_mod_square_fast(t5, t5, curve); /* t1 = x1*A = B */ - vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits); + vli_mod_mult_fast(x1, x1, t5, curve); /* t3 = x2*A = C */ - vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits); + vli_mod_mult_fast(x2, x2, t5, curve); /* t4 = y2 - y1 */ vli_mod_sub(y2, y2, y1, curve_prime, ndigits); /* t5 = (y2 - y1)^2 = D */ - vli_mod_square_fast(t5, y2, curve_prime, ndigits); + vli_mod_square_fast(t5, y2, curve); /* t5 = D - B */ vli_mod_sub(t5, t5, x1, curve_prime, ndigits); @@ -1071,11 +1203,11 @@ static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime, /* t3 = C - B */ vli_mod_sub(x2, x2, x1, curve_prime, ndigits); /* t2 = y1*(C - B) */ - vli_mod_mult_fast(y1, y1, x2, curve_prime, ndigits); + vli_mod_mult_fast(y1, y1, x2, curve); /* t3 = B - x3 */ vli_mod_sub(x2, x1, t5, curve_prime, ndigits); /* t4 = (y2 - y1)*(B - x3) */ - vli_mod_mult_fast(y2, y2, x2, curve_prime, ndigits); + vli_mod_mult_fast(y2, y2, x2, curve); /* t4 = y3 */ vli_mod_sub(y2, y2, y1, curve_prime, ndigits); @@ -1086,22 +1218,24 @@ static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime, * Output P + Q = (x3, y3, Z3), P - Q = (x3', y3', Z3) * or P => P - Q, Q => P + Q */ -static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime, - unsigned int ndigits) +static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2, + const struct ecc_curve *curve) { /* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */ u64 t5[ECC_MAX_DIGITS]; u64 t6[ECC_MAX_DIGITS]; u64 t7[ECC_MAX_DIGITS]; + const u64 *curve_prime = curve->p; + const unsigned int ndigits = curve->g.ndigits; /* t5 = x2 - x1 */ vli_mod_sub(t5, x2, x1, curve_prime, ndigits); /* t5 = (x2 - x1)^2 = A */ - vli_mod_square_fast(t5, t5, curve_prime, ndigits); + vli_mod_square_fast(t5, t5, curve); /* t1 = x1*A = B */ - vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits); + vli_mod_mult_fast(x1, x1, t5, curve); /* t3 = x2*A = C */ - vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits); + vli_mod_mult_fast(x2, x2, t5, curve); /* t4 = y2 + y1 */ vli_mod_add(t5, y2, y1, curve_prime, ndigits); /* t4 = y2 - y1 */ @@ -1110,29 +1244,29 @@ static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime, /* t6 = C - B */ vli_mod_sub(t6, x2, x1, curve_prime, ndigits); /* t2 = y1 * (C - B) */ - vli_mod_mult_fast(y1, y1, t6, curve_prime, ndigits); + vli_mod_mult_fast(y1, y1, t6, curve); /* t6 = B + C */ vli_mod_add(t6, x1, x2, curve_prime, ndigits); /* t3 = (y2 - y1)^2 */ - vli_mod_square_fast(x2, y2, curve_prime, ndigits); + vli_mod_square_fast(x2, y2, curve); /* t3 = x3 */ vli_mod_sub(x2, x2, t6, curve_prime, ndigits); /* t7 = B - x3 */ vli_mod_sub(t7, x1, x2, curve_prime, ndigits); /* t4 = (y2 - y1)*(B - x3) */ - vli_mod_mult_fast(y2, y2, t7, curve_prime, ndigits); + vli_mod_mult_fast(y2, y2, t7, curve); /* t4 = y3 */ vli_mod_sub(y2, y2, y1, curve_prime, ndigits); /* t7 = (y2 + y1)^2 = F */ - vli_mod_square_fast(t7, t5, curve_prime, ndigits); + vli_mod_square_fast(t7, t5, curve); /* t7 = x3' */ vli_mod_sub(t7, t7, t6, curve_prime, ndigits); /* t6 = x3' - B */ vli_mod_sub(t6, t7, x1, curve_prime, ndigits); /* t6 = (y2 + y1)*(x3' - B) */ - vli_mod_mult_fast(t6, t6, t5, curve_prime, ndigits); + vli_mod_mult_fast(t6, t6, t5, curve); /* t2 = y3' */ vli_mod_sub(y1, t6, y1, curve_prime, ndigits); @@ -1162,41 +1296,37 @@ static void ecc_point_mult(struct ecc_point *result, vli_set(rx[1], point->x, ndigits); vli_set(ry[1], point->y, ndigits); - xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z, curve_prime, - ndigits); + xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z, curve); for (i = num_bits - 2; i > 0; i--) { nb = !vli_test_bit(scalar, i); - xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime, - ndigits); - xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime, - ndigits); + xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve); + xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve); } nb = !vli_test_bit(scalar, 0); - xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime, - ndigits); + xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve); /* Find final 1/Z value. */ /* X1 - X0 */ vli_mod_sub(z, rx[1], rx[0], curve_prime, ndigits); /* Yb * (X1 - X0) */ - vli_mod_mult_fast(z, z, ry[1 - nb], curve_prime, ndigits); + vli_mod_mult_fast(z, z, ry[1 - nb], curve); /* xP * Yb * (X1 - X0) */ - vli_mod_mult_fast(z, z, point->x, curve_prime, ndigits); + vli_mod_mult_fast(z, z, point->x, curve); /* 1 / (xP * Yb * (X1 - X0)) */ vli_mod_inv(z, z, curve_prime, point->ndigits); /* yP / (xP * Yb * (X1 - X0)) */ - vli_mod_mult_fast(z, z, point->y, curve_prime, ndigits); + vli_mod_mult_fast(z, z, point->y, curve); /* Xb * yP / (xP * Yb * (X1 - X0)) */ - vli_mod_mult_fast(z, z, rx[1 - nb], curve_prime, ndigits); + vli_mod_mult_fast(z, z, rx[1 - nb], curve); /* End 1/Z calculation */ - xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime, ndigits); + xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve); - apply_z(rx[0], ry[0], z, curve_prime, ndigits); + apply_z(rx[0], ry[0], z, curve); vli_set(result->x, rx[0], ndigits); vli_set(result->y, ry[0], ndigits); @@ -1217,9 +1347,9 @@ static void ecc_point_add(const struct ecc_point *result, vli_mod_sub(z, result->x, p->x, curve->p, ndigits); vli_set(px, p->x, ndigits); vli_set(py, p->y, ndigits); - xycz_add(px, py, result->x, result->y, curve->p, ndigits); + xycz_add(px, py, result->x, result->y, curve); vli_mod_inv(z, z, curve->p, ndigits); - apply_z(result->x, result->y, z, curve->p, ndigits); + apply_z(result->x, result->y, z, curve); } /* Computes R = u1P + u2Q mod p using Shamir's trick. @@ -1248,8 +1378,7 @@ void ecc_point_mult_shamir(const struct ecc_point *result, points[2] = q; points[3] = ∑ - num_bits = max(vli_num_bits(u1, ndigits), - vli_num_bits(u2, ndigits)); + num_bits = max(vli_num_bits(u1, ndigits), vli_num_bits(u2, ndigits)); i = num_bits - 1; idx = (!!vli_test_bit(u1, i)) | ((!!vli_test_bit(u2, i)) << 1); point = points[idx]; @@ -1260,7 +1389,7 @@ void ecc_point_mult_shamir(const struct ecc_point *result, z[0] = 1; for (--i; i >= 0; i--) { - ecc_point_double_jacobian(rx, ry, z, curve->p, ndigits); + ecc_point_double_jacobian(rx, ry, z, curve); idx = (!!vli_test_bit(u1, i)) | ((!!vli_test_bit(u2, i)) << 1); point = points[idx]; if (point) { @@ -1270,27 +1399,17 @@ void ecc_point_mult_shamir(const struct ecc_point *result, vli_set(tx, point->x, ndigits); vli_set(ty, point->y, ndigits); - apply_z(tx, ty, z, curve->p, ndigits); + apply_z(tx, ty, z, curve); vli_mod_sub(tz, rx, tx, curve->p, ndigits); - xycz_add(tx, ty, rx, ry, curve->p, ndigits); - vli_mod_mult_fast(z, z, tz, curve->p, ndigits); + xycz_add(tx, ty, rx, ry, curve); + vli_mod_mult_fast(z, z, tz, curve); } } vli_mod_inv(z, z, curve->p, ndigits); - apply_z(rx, ry, z, curve->p, ndigits); + apply_z(rx, ry, z, curve); } EXPORT_SYMBOL(ecc_point_mult_shamir); -static inline void ecc_swap_digits(const u64 *in, u64 *out, - unsigned int ndigits) -{ - const __be64 *src = (__force __be64 *)in; - int i; - - for (i = 0; i < ndigits; i++) - out[i] = be64_to_cpu(src[ndigits - 1 - i]); -} - static int __ecc_is_key_valid(const struct ecc_curve *curve, const u64 *private_key, unsigned int ndigits) { @@ -1441,10 +1560,10 @@ int ecc_is_pubkey_valid_partial(const struct ecc_curve *curve, return -EINVAL; /* Check 3: Verify that y^2 == (x^3 + a·x + b) mod p */ - vli_mod_square_fast(yy, pk->y, curve->p, pk->ndigits); /* y^2 */ - vli_mod_square_fast(xxx, pk->x, curve->p, pk->ndigits); /* x^2 */ - vli_mod_mult_fast(xxx, xxx, pk->x, curve->p, pk->ndigits); /* x^3 */ - vli_mod_mult_fast(w, curve->a, pk->x, curve->p, pk->ndigits); /* a·x */ + vli_mod_square_fast(yy, pk->y, curve); /* y^2 */ + vli_mod_square_fast(xxx, pk->x, curve); /* x^2 */ + vli_mod_mult_fast(xxx, xxx, pk->x, curve); /* x^3 */ + vli_mod_mult_fast(w, curve->a, pk->x, curve); /* a·x */ vli_mod_add(w, w, curve->b, curve->p, pk->ndigits); /* a·x + b */ vli_mod_add(w, w, xxx, curve->p, pk->ndigits); /* x^3 + a·x + b */ if (vli_cmp(yy, w, pk->ndigits) != 0) /* Equation */ diff --git a/crypto/ecc.h b/crypto/ecc.h index d4e546b9ad79..a006132646a4 100644 --- a/crypto/ecc.h +++ b/crypto/ecc.h @@ -26,49 +26,34 @@ #ifndef _CRYPTO_ECC_H #define _CRYPTO_ECC_H +#include <crypto/ecc_curve.h> + /* One digit is u64 qword. */ #define ECC_CURVE_NIST_P192_DIGITS 3 #define ECC_CURVE_NIST_P256_DIGITS 4 -#define ECC_MAX_DIGITS (512 / 64) +#define ECC_CURVE_NIST_P384_DIGITS 6 +#define ECC_MAX_DIGITS (512 / 64) /* due to ecrdsa */ #define ECC_DIGITS_TO_BYTES_SHIFT 3 -/** - * struct ecc_point - elliptic curve point in affine coordinates - * - * @x: X coordinate in vli form. - * @y: Y coordinate in vli form. - * @ndigits: Length of vlis in u64 qwords. - */ -struct ecc_point { - u64 *x; - u64 *y; - u8 ndigits; -}; +#define ECC_MAX_BYTES (ECC_MAX_DIGITS << ECC_DIGITS_TO_BYTES_SHIFT) #define ECC_POINT_INIT(x, y, ndigits) (struct ecc_point) { x, y, ndigits } /** - * struct ecc_curve - definition of elliptic curve - * - * @name: Short name of the curve. - * @g: Generator point of the curve. - * @p: Prime number, if Barrett's reduction is used for this curve - * pre-calculated value 'mu' is appended to the @p after ndigits. - * Use of Barrett's reduction is heuristically determined in - * vli_mmod_fast(). - * @n: Order of the curve group. - * @a: Curve parameter a. - * @b: Curve parameter b. + * ecc_swap_digits() - Copy ndigits from big endian array to native array + * @in: Input array + * @out: Output array + * @ndigits: Number of digits to copy */ -struct ecc_curve { - char *name; - struct ecc_point g; - u64 *p; - u64 *n; - u64 *a; - u64 *b; -}; +static inline void ecc_swap_digits(const u64 *in, u64 *out, unsigned int ndigits) +{ + const __be64 *src = (__force __be64 *)in; + int i; + + for (i = 0; i < ndigits; i++) + out[i] = be64_to_cpu(src[ndigits - 1 - i]); +} /** * ecc_is_key_valid() - Validate a given ECDH private key diff --git a/crypto/ecc_curve_defs.h b/crypto/ecc_curve_defs.h index 69be6c7d228f..9719934c9428 100644 --- a/crypto/ecc_curve_defs.h +++ b/crypto/ecc_curve_defs.h @@ -54,4 +54,53 @@ static struct ecc_curve nist_p256 = { .b = nist_p256_b }; +/* NIST P-384 */ +static u64 nist_p384_g_x[] = { 0x3A545E3872760AB7ull, 0x5502F25DBF55296Cull, + 0x59F741E082542A38ull, 0x6E1D3B628BA79B98ull, + 0x8Eb1C71EF320AD74ull, 0xAA87CA22BE8B0537ull }; +static u64 nist_p384_g_y[] = { 0x7A431D7C90EA0E5Full, 0x0A60B1CE1D7E819Dull, + 0xE9DA3113B5F0B8C0ull, 0xF8F41DBD289A147Cull, + 0x5D9E98BF9292DC29ull, 0x3617DE4A96262C6Full }; +static u64 nist_p384_p[] = { 0x00000000FFFFFFFFull, 0xFFFFFFFF00000000ull, + 0xFFFFFFFFFFFFFFFEull, 0xFFFFFFFFFFFFFFFFull, + 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull }; +static u64 nist_p384_n[] = { 0xECEC196ACCC52973ull, 0x581A0DB248B0A77Aull, + 0xC7634D81F4372DDFull, 0xFFFFFFFFFFFFFFFFull, + 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull }; +static u64 nist_p384_a[] = { 0x00000000FFFFFFFCull, 0xFFFFFFFF00000000ull, + 0xFFFFFFFFFFFFFFFEull, 0xFFFFFFFFFFFFFFFFull, + 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull }; +static u64 nist_p384_b[] = { 0x2a85c8edd3ec2aefull, 0xc656398d8a2ed19dull, + 0x0314088f5013875aull, 0x181d9c6efe814112ull, + 0x988e056be3f82d19ull, 0xb3312fa7e23ee7e4ull }; +static struct ecc_curve nist_p384 = { + .name = "nist_384", + .g = { + .x = nist_p384_g_x, + .y = nist_p384_g_y, + .ndigits = 6, + }, + .p = nist_p384_p, + .n = nist_p384_n, + .a = nist_p384_a, + .b = nist_p384_b +}; + +/* curve25519 */ +static u64 curve25519_g_x[] = { 0x0000000000000009, 0x0000000000000000, + 0x0000000000000000, 0x0000000000000000 }; +static u64 curve25519_p[] = { 0xffffffffffffffed, 0xffffffffffffffff, + 0xffffffffffffffff, 0x7fffffffffffffff }; +static u64 curve25519_a[] = { 0x000000000001DB41, 0x0000000000000000, + 0x0000000000000000, 0x0000000000000000 }; +static const struct ecc_curve ecc_25519 = { + .name = "curve25519", + .g = { + .x = curve25519_g_x, + .ndigits = 4, + }, + .p = curve25519_p, + .a = curve25519_a, +}; + #endif diff --git a/crypto/ecdh.c b/crypto/ecdh.c index 96f80c8f8e30..04a427b8c956 100644 --- a/crypto/ecdh.c +++ b/crypto/ecdh.c @@ -23,33 +23,16 @@ static inline struct ecdh_ctx *ecdh_get_ctx(struct crypto_kpp *tfm) return kpp_tfm_ctx(tfm); } -static unsigned int ecdh_supported_curve(unsigned int curve_id) -{ - switch (curve_id) { - case ECC_CURVE_NIST_P192: return ECC_CURVE_NIST_P192_DIGITS; - case ECC_CURVE_NIST_P256: return ECC_CURVE_NIST_P256_DIGITS; - default: return 0; - } -} - static int ecdh_set_secret(struct crypto_kpp *tfm, const void *buf, unsigned int len) { struct ecdh_ctx *ctx = ecdh_get_ctx(tfm); struct ecdh params; - unsigned int ndigits; if (crypto_ecdh_decode_key(buf, len, ¶ms) < 0 || - params.key_size > sizeof(ctx->private_key)) + params.key_size > sizeof(u64) * ctx->ndigits) return -EINVAL; - ndigits = ecdh_supported_curve(params.curve_id); - if (!ndigits) - return -EINVAL; - - ctx->curve_id = params.curve_id; - ctx->ndigits = ndigits; - if (!params.key || !params.key_size) return ecc_gen_privkey(ctx->curve_id, ctx->ndigits, ctx->private_key); @@ -140,13 +123,24 @@ static unsigned int ecdh_max_size(struct crypto_kpp *tfm) return ctx->ndigits << (ECC_DIGITS_TO_BYTES_SHIFT + 1); } -static struct kpp_alg ecdh = { +static int ecdh_nist_p192_init_tfm(struct crypto_kpp *tfm) +{ + struct ecdh_ctx *ctx = ecdh_get_ctx(tfm); + + ctx->curve_id = ECC_CURVE_NIST_P192; + ctx->ndigits = ECC_CURVE_NIST_P192_DIGITS; + + return 0; +} + +static struct kpp_alg ecdh_nist_p192 = { .set_secret = ecdh_set_secret, .generate_public_key = ecdh_compute_value, .compute_shared_secret = ecdh_compute_value, .max_size = ecdh_max_size, + .init = ecdh_nist_p192_init_tfm, .base = { - .cra_name = "ecdh", + .cra_name = "ecdh-nist-p192", .cra_driver_name = "ecdh-generic", .cra_priority = 100, .cra_module = THIS_MODULE, @@ -154,14 +148,48 @@ static struct kpp_alg ecdh = { }, }; +static int ecdh_nist_p256_init_tfm(struct crypto_kpp *tfm) +{ + struct ecdh_ctx *ctx = ecdh_get_ctx(tfm); + + ctx->curve_id = ECC_CURVE_NIST_P256; + ctx->ndigits = ECC_CURVE_NIST_P256_DIGITS; + + return 0; +} + +static struct kpp_alg ecdh_nist_p256 = { + .set_secret = ecdh_set_secret, + .generate_public_key = ecdh_compute_value, + .compute_shared_secret = ecdh_compute_value, + .max_size = ecdh_max_size, + .init = ecdh_nist_p256_init_tfm, + .base = { + .cra_name = "ecdh-nist-p256", + .cra_driver_name = "ecdh-generic", + .cra_priority = 100, + .cra_module = THIS_MODULE, + .cra_ctxsize = sizeof(struct ecdh_ctx), + }, +}; + +static bool ecdh_nist_p192_registered; + static int ecdh_init(void) { - return crypto_register_kpp(&ecdh); + int ret; + + ret = crypto_register_kpp(&ecdh_nist_p192); + ecdh_nist_p192_registered = ret == 0; + + return crypto_register_kpp(&ecdh_nist_p256); } static void ecdh_exit(void) { - crypto_unregister_kpp(&ecdh); + if (ecdh_nist_p192_registered) + crypto_unregister_kpp(&ecdh_nist_p192); + crypto_unregister_kpp(&ecdh_nist_p256); } subsys_initcall(ecdh_init); diff --git a/crypto/ecdh_helper.c b/crypto/ecdh_helper.c index fca63b559f65..f18f9028f912 100644 --- a/crypto/ecdh_helper.c +++ b/crypto/ecdh_helper.c @@ -10,7 +10,7 @@ #include <crypto/ecdh.h> #include <crypto/kpp.h> -#define ECDH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + 2 * sizeof(short)) +#define ECDH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + sizeof(short)) static inline u8 *ecdh_pack_data(void *dst, const void *src, size_t sz) { @@ -46,7 +46,6 @@ int crypto_ecdh_encode_key(char *buf, unsigned int len, return -EINVAL; ptr = ecdh_pack_data(ptr, &secret, sizeof(secret)); - ptr = ecdh_pack_data(ptr, ¶ms->curve_id, sizeof(params->curve_id)); ptr = ecdh_pack_data(ptr, ¶ms->key_size, sizeof(params->key_size)); ecdh_pack_data(ptr, params->key, params->key_size); @@ -70,7 +69,6 @@ int crypto_ecdh_decode_key(const char *buf, unsigned int len, if (unlikely(len < secret.len)) return -EINVAL; - ptr = ecdh_unpack_data(¶ms->curve_id, ptr, sizeof(params->curve_id)); ptr = ecdh_unpack_data(¶ms->key_size, ptr, sizeof(params->key_size)); if (secret.len != crypto_ecdh_key_len(params)) return -EINVAL; diff --git a/crypto/ecdsa.c b/crypto/ecdsa.c new file mode 100644 index 000000000000..1e7b15009bf6 --- /dev/null +++ b/crypto/ecdsa.c @@ -0,0 +1,376 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (c) 2021 IBM Corporation + */ + +#include <linux/module.h> +#include <crypto/internal/akcipher.h> +#include <crypto/akcipher.h> +#include <crypto/ecdh.h> +#include <linux/asn1_decoder.h> +#include <linux/scatterlist.h> + +#include "ecc.h" +#include "ecdsasignature.asn1.h" + +struct ecc_ctx { + unsigned int curve_id; + const struct ecc_curve *curve; + + bool pub_key_set; + u64 x[ECC_MAX_DIGITS]; /* pub key x and y coordinates */ + u64 y[ECC_MAX_DIGITS]; + struct ecc_point pub_key; +}; + +struct ecdsa_signature_ctx { + const struct ecc_curve *curve; + u64 r[ECC_MAX_DIGITS]; + u64 s[ECC_MAX_DIGITS]; +}; + +/* + * Get the r and s components of a signature from the X509 certificate. + */ +static int ecdsa_get_signature_rs(u64 *dest, size_t hdrlen, unsigned char tag, + const void *value, size_t vlen, unsigned int ndigits) +{ + size_t keylen = ndigits * sizeof(u64); + ssize_t diff = vlen - keylen; + const char *d = value; + u8 rs[ECC_MAX_BYTES]; + + if (!value || !vlen) + return -EINVAL; + + /* diff = 0: 'value' has exacly the right size + * diff > 0: 'value' has too many bytes; one leading zero is allowed that + * makes the value a positive integer; error on more + * diff < 0: 'value' is missing leading zeros, which we add + */ + if (diff > 0) { + /* skip over leading zeros that make 'value' a positive int */ + if (*d == 0) { + vlen -= 1; + diff--; + d++; + } + if (diff) + return -EINVAL; + } + if (-diff >= keylen) + return -EINVAL; + + if (diff) { + /* leading zeros not given in 'value' */ + memset(rs, 0, -diff); + } + + memcpy(&rs[-diff], d, vlen); + + ecc_swap_digits((u64 *)rs, dest, ndigits); + + return 0; +} + +int ecdsa_get_signature_r(void *context, size_t hdrlen, unsigned char tag, + const void *value, size_t vlen) +{ + struct ecdsa_signature_ctx *sig = context; + + return ecdsa_get_signature_rs(sig->r, hdrlen, tag, value, vlen, + sig->curve->g.ndigits); +} + +int ecdsa_get_signature_s(void *context, size_t hdrlen, unsigned char tag, + const void *value, size_t vlen) +{ + struct ecdsa_signature_ctx *sig = context; + + return ecdsa_get_signature_rs(sig->s, hdrlen, tag, value, vlen, + sig->curve->g.ndigits); +} + +static int _ecdsa_verify(struct ecc_ctx *ctx, const u64 *hash, const u64 *r, const u64 *s) +{ + const struct ecc_curve *curve = ctx->curve; + unsigned int ndigits = curve->g.ndigits; + u64 s1[ECC_MAX_DIGITS]; + u64 u1[ECC_MAX_DIGITS]; + u64 u2[ECC_MAX_DIGITS]; + u64 x1[ECC_MAX_DIGITS]; + u64 y1[ECC_MAX_DIGITS]; + struct ecc_point res = ECC_POINT_INIT(x1, y1, ndigits); + + /* 0 < r < n and 0 < s < n */ + if (vli_is_zero(r, ndigits) || vli_cmp(r, curve->n, ndigits) >= 0 || + vli_is_zero(s, ndigits) || vli_cmp(s, curve->n, ndigits) >= 0) + return -EBADMSG; + + /* hash is given */ + pr_devel("hash : %016llx %016llx ... %016llx\n", + hash[ndigits - 1], hash[ndigits - 2], hash[0]); + + /* s1 = (s^-1) mod n */ + vli_mod_inv(s1, s, curve->n, ndigits); + /* u1 = (hash * s1) mod n */ + vli_mod_mult_slow(u1, hash, s1, curve->n, ndigits); + /* u2 = (r * s1) mod n */ + vli_mod_mult_slow(u2, r, s1, curve->n, ndigits); + /* res = u1*G + u2 * pub_key */ + ecc_point_mult_shamir(&res, u1, &curve->g, u2, &ctx->pub_key, curve); + + /* res.x = res.x mod n (if res.x > order) */ + if (unlikely(vli_cmp(res.x, curve->n, ndigits) == 1)) + /* faster alternative for NIST p384, p256 & p192 */ + vli_sub(res.x, res.x, curve->n, ndigits); + + if (!vli_cmp(res.x, r, ndigits)) + return 0; + + return -EKEYREJECTED; +} + +/* + * Verify an ECDSA signature. + */ +static int ecdsa_verify(struct akcipher_request *req) +{ + struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req); + struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm); + size_t keylen = ctx->curve->g.ndigits * sizeof(u64); + struct ecdsa_signature_ctx sig_ctx = { + .curve = ctx->curve, + }; + u8 rawhash[ECC_MAX_BYTES]; + u64 hash[ECC_MAX_DIGITS]; + unsigned char *buffer; + ssize_t diff; + int ret; + + if (unlikely(!ctx->pub_key_set)) + return -EINVAL; + + buffer = kmalloc(req->src_len + req->dst_len, GFP_KERNEL); + if (!buffer) + return -ENOMEM; + + sg_pcopy_to_buffer(req->src, + sg_nents_for_len(req->src, req->src_len + req->dst_len), + buffer, req->src_len + req->dst_len, 0); + + ret = asn1_ber_decoder(&ecdsasignature_decoder, &sig_ctx, + buffer, req->src_len); + if (ret < 0) + goto error; + + /* if the hash is shorter then we will add leading zeros to fit to ndigits */ + diff = keylen - req->dst_len; + if (diff >= 0) { + if (diff) + memset(rawhash, 0, diff); + memcpy(&rawhash[diff], buffer + req->src_len, req->dst_len); + } else if (diff < 0) { + /* given hash is longer, we take the left-most bytes */ + memcpy(&rawhash, buffer + req->src_len, keylen); + } + + ecc_swap_digits((u64 *)rawhash, hash, ctx->curve->g.ndigits); + + ret = _ecdsa_verify(ctx, hash, sig_ctx.r, sig_ctx.s); + +error: + kfree(buffer); + + return ret; +} + +static int ecdsa_ecc_ctx_init(struct ecc_ctx *ctx, unsigned int curve_id) +{ + ctx->curve_id = curve_id; + ctx->curve = ecc_get_curve(curve_id); + if (!ctx->curve) + return -EINVAL; + + return 0; +} + + +static void ecdsa_ecc_ctx_deinit(struct ecc_ctx *ctx) +{ + ctx->pub_key_set = false; +} + +static int ecdsa_ecc_ctx_reset(struct ecc_ctx *ctx) +{ + unsigned int curve_id = ctx->curve_id; + int ret; + + ecdsa_ecc_ctx_deinit(ctx); + ret = ecdsa_ecc_ctx_init(ctx, curve_id); + if (ret == 0) + ctx->pub_key = ECC_POINT_INIT(ctx->x, ctx->y, + ctx->curve->g.ndigits); + return ret; +} + +/* + * Set the public key given the raw uncompressed key data from an X509 + * certificate. The key data contain the concatenated X and Y coordinates of + * the public key. + */ +static int ecdsa_set_pub_key(struct crypto_akcipher *tfm, const void *key, unsigned int keylen) +{ + struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm); + const unsigned char *d = key; + const u64 *digits = (const u64 *)&d[1]; + unsigned int ndigits; + int ret; + + ret = ecdsa_ecc_ctx_reset(ctx); + if (ret < 0) + return ret; + + if (keylen < 1 || (((keylen - 1) >> 1) % sizeof(u64)) != 0) + return -EINVAL; + /* we only accept uncompressed format indicated by '4' */ + if (d[0] != 4) + return -EINVAL; + + keylen--; + ndigits = (keylen >> 1) / sizeof(u64); + if (ndigits != ctx->curve->g.ndigits) + return -EINVAL; + + ecc_swap_digits(digits, ctx->pub_key.x, ndigits); + ecc_swap_digits(&digits[ndigits], ctx->pub_key.y, ndigits); + ret = ecc_is_pubkey_valid_full(ctx->curve, &ctx->pub_key); + + ctx->pub_key_set = ret == 0; + + return ret; +} + +static void ecdsa_exit_tfm(struct crypto_akcipher *tfm) +{ + struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm); + + ecdsa_ecc_ctx_deinit(ctx); +} + +static unsigned int ecdsa_max_size(struct crypto_akcipher *tfm) +{ + struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm); + + return ctx->pub_key.ndigits << ECC_DIGITS_TO_BYTES_SHIFT; +} + +static int ecdsa_nist_p384_init_tfm(struct crypto_akcipher *tfm) +{ + struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm); + + return ecdsa_ecc_ctx_init(ctx, ECC_CURVE_NIST_P384); +} + +static struct akcipher_alg ecdsa_nist_p384 = { + .verify = ecdsa_verify, + .set_pub_key = ecdsa_set_pub_key, + .max_size = ecdsa_max_size, + .init = ecdsa_nist_p384_init_tfm, + .exit = ecdsa_exit_tfm, + .base = { + .cra_name = "ecdsa-nist-p384", + .cra_driver_name = "ecdsa-nist-p384-generic", + .cra_priority = 100, + .cra_module = THIS_MODULE, + .cra_ctxsize = sizeof(struct ecc_ctx), + }, +}; + +static int ecdsa_nist_p256_init_tfm(struct crypto_akcipher *tfm) +{ + struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm); + + return ecdsa_ecc_ctx_init(ctx, ECC_CURVE_NIST_P256); +} + +static struct akcipher_alg ecdsa_nist_p256 = { + .verify = ecdsa_verify, + .set_pub_key = ecdsa_set_pub_key, + .max_size = ecdsa_max_size, + .init = ecdsa_nist_p256_init_tfm, + .exit = ecdsa_exit_tfm, + .base = { + .cra_name = "ecdsa-nist-p256", + .cra_driver_name = "ecdsa-nist-p256-generic", + .cra_priority = 100, + .cra_module = THIS_MODULE, + .cra_ctxsize = sizeof(struct ecc_ctx), + }, +}; + +static int ecdsa_nist_p192_init_tfm(struct crypto_akcipher *tfm) +{ + struct ecc_ctx *ctx = akcipher_tfm_ctx(tfm); + + return ecdsa_ecc_ctx_init(ctx, ECC_CURVE_NIST_P192); +} + +static struct akcipher_alg ecdsa_nist_p192 = { + .verify = ecdsa_verify, + .set_pub_key = ecdsa_set_pub_key, + .max_size = ecdsa_max_size, + .init = ecdsa_nist_p192_init_tfm, + .exit = ecdsa_exit_tfm, + .base = { + .cra_name = "ecdsa-nist-p192", + .cra_driver_name = "ecdsa-nist-p192-generic", + .cra_priority = 100, + .cra_module = THIS_MODULE, + .cra_ctxsize = sizeof(struct ecc_ctx), + }, +}; +static bool ecdsa_nist_p192_registered; + +static int ecdsa_init(void) +{ + int ret; + + /* NIST p192 may not be available in FIPS mode */ + ret = crypto_register_akcipher(&ecdsa_nist_p192); + ecdsa_nist_p192_registered = ret == 0; + + ret = crypto_register_akcipher(&ecdsa_nist_p256); + if (ret) + goto nist_p256_error; + + ret = crypto_register_akcipher(&ecdsa_nist_p384); + if (ret) + goto nist_p384_error; + + return 0; + +nist_p384_error: + crypto_unregister_akcipher(&ecdsa_nist_p256); + +nist_p256_error: + if (ecdsa_nist_p192_registered) + crypto_unregister_akcipher(&ecdsa_nist_p192); + return ret; +} + +static void ecdsa_exit(void) +{ + if (ecdsa_nist_p192_registered) + crypto_unregister_akcipher(&ecdsa_nist_p192); + crypto_unregister_akcipher(&ecdsa_nist_p256); + crypto_unregister_akcipher(&ecdsa_nist_p384); +} + +subsys_initcall(ecdsa_init); +module_exit(ecdsa_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Stefan Berger <stefanb@linux.ibm.com>"); +MODULE_DESCRIPTION("ECDSA generic algorithm"); +MODULE_ALIAS_CRYPTO("ecdsa-generic"); diff --git a/crypto/ecdsasignature.asn1 b/crypto/ecdsasignature.asn1 new file mode 100644 index 000000000000..621ab754fb9f --- /dev/null +++ b/crypto/ecdsasignature.asn1 @@ -0,0 +1,4 @@ +ECDSASignature ::= SEQUENCE { + r INTEGER ({ ecdsa_get_signature_r }), + s INTEGER ({ ecdsa_get_signature_s }) +} diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c index c36ea0c8be98..76a04d000c0d 100644 --- a/crypto/fcrypt.c +++ b/crypto/fcrypt.c @@ -63,10 +63,7 @@ do { \ } while (0) /* Rotate right one 64 bit number as a 56 bit number */ -#define ror56_64(k, n) \ -do { \ - k = (k >> n) | ((k & ((1 << n) - 1)) << (56 - n)); \ -} while (0) +#define ror56_64(k, n) (k = (k >> n) | ((k & ((1 << n) - 1)) << (56 - n))) /* * Sboxes for Feistel network derived from diff --git a/crypto/jitterentropy.c b/crypto/jitterentropy.c index 6e147c43fc18..a11b3208760f 100644 --- a/crypto/jitterentropy.c +++ b/crypto/jitterentropy.c @@ -597,7 +597,7 @@ int jent_read_entropy(struct rand_data *ec, unsigned char *data, if (!ec) return -1; - while (0 < len) { + while (len > 0) { unsigned int tocopy; jent_gen_entropy(ec); @@ -678,7 +678,7 @@ struct rand_data *jent_entropy_collector_alloc(unsigned int osr, } /* verify and set the oversampling rate */ - if (0 == osr) + if (osr == 0) osr = 1; /* minimum sampling rate is 1 */ entropy_collector->osr = osr; @@ -769,7 +769,7 @@ int jent_entropy_init(void) * etc. with the goal to clear it to get the worst case * measurements. */ - if (CLEARCACHE > i) + if (i < CLEARCACHE) continue; if (stuck) @@ -826,7 +826,7 @@ int jent_entropy_init(void) * should not fail. The value of 3 should cover the NTP case being * performed during our test run. */ - if (3 < time_backwards) + if (time_backwards > 3) return JENT_ENOMONOTONIC; /* diff --git a/crypto/keywrap.c b/crypto/keywrap.c index 3517773bc7f7..054d9a216fc9 100644 --- a/crypto/keywrap.c +++ b/crypto/keywrap.c @@ -114,9 +114,9 @@ static void crypto_kw_scatterlist_ff(struct scatter_walk *walk, scatterwalk_start(walk, sg); scatterwalk_advance(walk, skip); break; - } else - skip -= sg->length; + } + skip -= sg->length; sg = sg_next(sg); } } diff --git a/crypto/rng.c b/crypto/rng.c index a888d84b524a..fea082b25fe4 100644 --- a/crypto/rng.c +++ b/crypto/rng.c @@ -34,22 +34,18 @@ int crypto_rng_reset(struct crypto_rng *tfm, const u8 *seed, unsigned int slen) u8 *buf = NULL; int err; - crypto_stats_get(alg); if (!seed && slen) { buf = kmalloc(slen, GFP_KERNEL); - if (!buf) { - crypto_alg_put(alg); + if (!buf) return -ENOMEM; - } err = get_random_bytes_wait(buf, slen); - if (err) { - crypto_alg_put(alg); + if (err) goto out; - } seed = buf; } + crypto_stats_get(alg); err = crypto_rng_alg(tfm)->seed(tfm, seed, slen); crypto_stats_rng_seed(alg, err); out: diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c index 236c87547a17..45f98b750053 100644 --- a/crypto/serpent_generic.c +++ b/crypto/serpent_generic.c @@ -272,6 +272,7 @@ int __serpent_setkey(struct serpent_ctx *ctx, const u8 *key, u32 *k = ctx->expkey; u8 *k8 = (u8 *)k; u32 r0, r1, r2, r3, r4; + __le32 *lk; int i; /* Copy key, add padding */ @@ -283,22 +284,32 @@ int __serpent_setkey(struct serpent_ctx *ctx, const u8 *key, while (i < SERPENT_MAX_KEY_SIZE) k8[i++] = 0; + lk = (__le32 *)k; + k[0] = le32_to_cpu(lk[0]); + k[1] = le32_to_cpu(lk[1]); + k[2] = le32_to_cpu(lk[2]); + k[3] = le32_to_cpu(lk[3]); + k[4] = le32_to_cpu(lk[4]); + k[5] = le32_to_cpu(lk[5]); + k[6] = le32_to_cpu(lk[6]); + k[7] = le32_to_cpu(lk[7]); + /* Expand key using polynomial */ - r0 = le32_to_cpu(k[3]); - r1 = le32_to_cpu(k[4]); - r2 = le32_to_cpu(k[5]); - r3 = le32_to_cpu(k[6]); - r4 = le32_to_cpu(k[7]); - - keyiter(le32_to_cpu(k[0]), r0, r4, r2, 0, 0); - keyiter(le32_to_cpu(k[1]), r1, r0, r3, 1, 1); - keyiter(le32_to_cpu(k[2]), r2, r1, r4, 2, 2); - keyiter(le32_to_cpu(k[3]), r3, r2, r0, 3, 3); - keyiter(le32_to_cpu(k[4]), r4, r3, r1, 4, 4); - keyiter(le32_to_cpu(k[5]), r0, r4, r2, 5, 5); - keyiter(le32_to_cpu(k[6]), r1, r0, r3, 6, 6); - keyiter(le32_to_cpu(k[7]), r2, r1, r4, 7, 7); + r0 = k[3]; + r1 = k[4]; + r2 = k[5]; + r3 = k[6]; + r4 = k[7]; + + keyiter(k[0], r0, r4, r2, 0, 0); + keyiter(k[1], r1, r0, r3, 1, 1); + keyiter(k[2], r2, r1, r4, 2, 2); + keyiter(k[3], r3, r2, r0, 3, 3); + keyiter(k[4], r4, r3, r1, 4, 4); + keyiter(k[5], r0, r4, r2, 5, 5); + keyiter(k[6], r1, r0, r3, 6, 6); + keyiter(k[7], r2, r1, r4, 7, 7); keyiter(k[0], r3, r2, r0, 8, 8); keyiter(k[1], r4, r3, r1, 9, 9); diff --git a/crypto/testmgr.c b/crypto/testmgr.c index 93359999c94b..10c5b3b01ec4 100644 --- a/crypto/testmgr.c +++ b/crypto/testmgr.c @@ -1168,11 +1168,6 @@ static inline int check_shash_op(const char *op, int err, return err; } -static inline const void *sg_data(struct scatterlist *sg) -{ - return page_address(sg_page(sg)) + sg->offset; -} - /* Test one hash test vector in one configuration, using the shash API */ static int test_shash_vec_cfg(const struct hash_testvec *vec, const char *vec_name, @@ -1230,7 +1225,7 @@ static int test_shash_vec_cfg(const struct hash_testvec *vec, return 0; if (cfg->nosimd) crypto_disable_simd_for_test(); - err = crypto_shash_digest(desc, sg_data(&tsgl->sgl[0]), + err = crypto_shash_digest(desc, sg_virt(&tsgl->sgl[0]), tsgl->sgl[0].length, result); if (cfg->nosimd) crypto_reenable_simd_for_test(); @@ -1266,7 +1261,7 @@ static int test_shash_vec_cfg(const struct hash_testvec *vec, cfg->finalization_type == FINALIZATION_TYPE_FINUP) { if (divs[i]->nosimd) crypto_disable_simd_for_test(); - err = crypto_shash_finup(desc, sg_data(&tsgl->sgl[i]), + err = crypto_shash_finup(desc, sg_virt(&tsgl->sgl[i]), tsgl->sgl[i].length, result); if (divs[i]->nosimd) crypto_reenable_simd_for_test(); @@ -1278,7 +1273,7 @@ static int test_shash_vec_cfg(const struct hash_testvec *vec, } if (divs[i]->nosimd) crypto_disable_simd_for_test(); - err = crypto_shash_update(desc, sg_data(&tsgl->sgl[i]), + err = crypto_shash_update(desc, sg_virt(&tsgl->sgl[i]), tsgl->sgl[i].length); if (divs[i]->nosimd) crypto_reenable_simd_for_test(); @@ -4904,11 +4899,38 @@ static const struct alg_test_desc alg_test_descs[] = { } }, { #endif - .alg = "ecdh", +#ifndef CONFIG_CRYPTO_FIPS + .alg = "ecdh-nist-p192", .test = alg_test_kpp, .fips_allowed = 1, .suite = { - .kpp = __VECS(ecdh_tv_template) + .kpp = __VECS(ecdh_p192_tv_template) + } + }, { +#endif + .alg = "ecdh-nist-p256", + .test = alg_test_kpp, + .fips_allowed = 1, + .suite = { + .kpp = __VECS(ecdh_p256_tv_template) + } + }, { + .alg = "ecdsa-nist-p192", + .test = alg_test_akcipher, + .suite = { + .akcipher = __VECS(ecdsa_nist_p192_tv_template) + } + }, { + .alg = "ecdsa-nist-p256", + .test = alg_test_akcipher, + .suite = { + .akcipher = __VECS(ecdsa_nist_p256_tv_template) + } + }, { + .alg = "ecdsa-nist-p384", + .test = alg_test_akcipher, + .suite = { + .akcipher = __VECS(ecdsa_nist_p384_tv_template) } }, { .alg = "ecrdsa", diff --git a/crypto/testmgr.h b/crypto/testmgr.h index ced56ea0c9b4..34e4a3db3991 100644 --- a/crypto/testmgr.h +++ b/crypto/testmgr.h @@ -567,6 +567,430 @@ static const struct akcipher_testvec rsa_tv_template[] = { }; /* + * ECDSA test vectors. + */ +static const struct akcipher_testvec ecdsa_nist_p192_tv_template[] = { + { + .key = + "\x04\xf7\x46\xf8\x2f\x15\xf6\x22\x8e\xd7\x57\x4f\xcc\xe7\xbb\xc1" + "\xd4\x09\x73\xcf\xea\xd0\x15\x07\x3d\xa5\x8a\x8a\x95\x43\xe4\x68" + "\xea\xc6\x25\xc1\xc1\x01\x25\x4c\x7e\xc3\x3c\xa6\x04\x0a\xe7\x08" + "\x98", + .key_len = 49, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x01", + .param_len = 21, + .m = + "\xcd\xb9\xd2\x1c\xb7\x6f\xcd\x44\xb3\xfd\x63\xea\xa3\x66\x7f\xae" + "\x63\x85\xe7\x82", + .m_size = 20, + .algo = OID_id_ecdsa_with_sha1, + .c = + "\x30\x35\x02\x19\x00\xba\xe5\x93\x83\x6e\xb6\x3b\x63\xa0\x27\x91" + "\xc6\xf6\x7f\xc3\x09\xad\x59\xad\x88\x27\xd6\x92\x6b\x02\x18\x10" + "\x68\x01\x9d\xba\xce\x83\x08\xef\x95\x52\x7b\xa0\x0f\xe4\x18\x86" + "\x80\x6f\xa5\x79\x77\xda\xd0", + .c_size = 55, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = + "\x04\xb6\x4b\xb1\xd1\xac\xba\x24\x8f\x65\xb2\x60\x00\x90\xbf\xbd" + "\x78\x05\x73\xe9\x79\x1d\x6f\x7c\x0b\xd2\xc3\x93\xa7\x28\xe1\x75" + "\xf7\xd5\x95\x1d\x28\x10\xc0\x75\x50\x5c\x1a\x4f\x3f\x8f\xa5\xee" + "\xa3", + .key_len = 49, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x01", + .param_len = 21, + .m = + "\x8d\xd6\xb8\x3e\xe5\xff\x23\xf6\x25\xa2\x43\x42\x74\x45\xa7\x40" + "\x3a\xff\x2f\xe1\xd3\xf6\x9f\xe8\x33\xcb\x12\x11", + .m_size = 28, + .algo = OID_id_ecdsa_with_sha224, + .c = + "\x30\x34\x02\x18\x5a\x8b\x82\x69\x7e\x8a\x0a\x09\x14\xf8\x11\x2b" + "\x55\xdc\xae\x37\x83\x7b\x12\xe6\xb6\x5b\xcb\xd4\x02\x18\x6a\x14" + "\x4f\x53\x75\xc8\x02\x48\xeb\xc3\x92\x0f\x1e\x72\xee\xc4\xa3\xe3" + "\x5c\x99\xdb\x92\x5b\x36", + .c_size = 54, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = + "\x04\xe2\x51\x24\x9b\xf7\xb6\x32\x82\x39\x66\x3d\x5b\xec\x3b\xae" + "\x0c\xd5\xf2\x67\xd1\xc7\xe1\x02\xe4\xbf\x90\x62\xb8\x55\x75\x56" + "\x69\x20\x5e\xcb\x4e\xca\x33\xd6\xcb\x62\x6b\x94\xa9\xa2\xe9\x58" + "\x91", + .key_len = 49, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x01", + .param_len = 21, + .m = + "\x35\xec\xa1\xa0\x9e\x14\xde\x33\x03\xb6\xf6\xbd\x0c\x2f\xb2\xfd" + "\x1f\x27\x82\xa5\xd7\x70\x3f\xef\xa0\x82\x69\x8e\x73\x31\x8e\xd7", + .m_size = 32, + .algo = OID_id_ecdsa_with_sha256, + .c = + "\x30\x35\x02\x18\x3f\x72\x3f\x1f\x42\xd2\x3f\x1d\x6b\x1a\x58\x56" + "\xf1\x8f\xf7\xfd\x01\x48\xfb\x5f\x72\x2a\xd4\x8f\x02\x19\x00\xb3" + "\x69\x43\xfd\x48\x19\x86\xcf\x32\xdd\x41\x74\x6a\x51\xc7\xd9\x7d" + "\x3a\x97\xd9\xcd\x1a\x6a\x49", + .c_size = 55, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = + "\x04\x5a\x13\xfe\x68\x86\x4d\xf4\x17\xc7\xa4\xe5\x8c\x65\x57\xb7" + "\x03\x73\x26\x57\xfb\xe5\x58\x40\xd8\xfd\x49\x05\xab\xf1\x66\x1f" + "\xe2\x9d\x93\x9e\xc2\x22\x5a\x8b\x4f\xf3\x77\x22\x59\x7e\xa6\x4e" + "\x8b", + .key_len = 49, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x01", + .param_len = 21, + .m = + "\x9d\x2e\x1a\x8f\xed\x6c\x4b\x61\xae\xac\xd5\x19\x79\xce\x67\xf9" + "\xa0\x34\xeb\xb0\x81\xf9\xd9\xdc\x6e\xb3\x5c\xa8\x69\xfc\x8a\x61" + "\x39\x81\xfb\xfd\x5c\x30\x6b\xa8\xee\xed\x89\xaf\xa3\x05\xe4\x78", + .m_size = 48, + .algo = OID_id_ecdsa_with_sha384, + .c = + "\x30\x35\x02\x19\x00\xf0\xa3\x38\xce\x2b\xf8\x9d\x1a\xcf\x7f\x34" + "\xb4\xb4\xe5\xc5\x00\xdd\x15\xbb\xd6\x8c\xa7\x03\x78\x02\x18\x64" + "\xbc\x5a\x1f\x82\x96\x61\xd7\xd1\x01\x77\x44\x5d\x53\xa4\x7c\x93" + "\x12\x3b\x3b\x28\xfb\x6d\xe1", + .c_size = 55, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = + "\x04\xd5\xf2\x6e\xc3\x94\x5c\x52\xbc\xdf\x86\x6c\x14\xd1\xca\xea" + "\xcc\x72\x3a\x8a\xf6\x7a\x3a\x56\x36\x3b\xca\xc6\x94\x0e\x17\x1d" + "\x9e\xa0\x58\x28\xf9\x4b\xe6\xd1\xa5\x44\x91\x35\x0d\xe7\xf5\x11" + "\x57", + .key_len = 49, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x01", + .param_len = 21, + .m = + "\xd5\x4b\xe9\x36\xda\xd8\x6e\xc0\x50\x03\xbe\x00\x43\xff\xf0\x23" + "\xac\xa2\x42\xe7\x37\x77\x79\x52\x8f\x3e\xc0\x16\xc1\xfc\x8c\x67" + "\x16\xbc\x8a\x5d\x3b\xd3\x13\xbb\xb6\xc0\x26\x1b\xeb\x33\xcc\x70" + "\x4a\xf2\x11\x37\xe8\x1b\xba\x55\xac\x69\xe1\x74\x62\x7c\x6e\xb5", + .m_size = 64, + .algo = OID_id_ecdsa_with_sha512, + .c = + "\x30\x35\x02\x19\x00\x88\x5b\x8f\x59\x43\xbf\xcf\xc6\xdd\x3f\x07" + "\x87\x12\xa0\xd4\xac\x2b\x11\x2d\x1c\xb6\x06\xc9\x6c\x02\x18\x73" + "\xb4\x22\x9a\x98\x73\x3c\x83\xa9\x14\x2a\x5e\xf5\xe5\xfb\x72\x28" + "\x6a\xdf\x97\xfd\x82\x76\x24", + .c_size = 55, + .public_key_vec = true, + .siggen_sigver_test = true, + }, +}; + +static const struct akcipher_testvec ecdsa_nist_p256_tv_template[] = { + { + .key = + "\x04\xb9\x7b\xbb\xd7\x17\x64\xd2\x7e\xfc\x81\x5d\x87\x06\x83\x41" + "\x22\xd6\x9a\xaa\x87\x17\xec\x4f\x63\x55\x2f\x94\xba\xdd\x83\xe9" + "\x34\x4b\xf3\xe9\x91\x13\x50\xb6\xcb\xca\x62\x08\xe7\x3b\x09\xdc" + "\xc3\x63\x4b\x2d\xb9\x73\x53\xe4\x45\xe6\x7c\xad\xe7\x6b\xb0\xe8" + "\xaf", + .key_len = 65, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x07", + .param_len = 21, + .m = + "\xc2\x2b\x5f\x91\x78\x34\x26\x09\x42\x8d\x6f\x51\xb2\xc5\xaf\x4c" + "\x0b\xde\x6a\x42", + .m_size = 20, + .algo = OID_id_ecdsa_with_sha1, + .c = + "\x30\x46\x02\x21\x00\xf9\x25\xce\x9f\x3a\xa6\x35\x81\xcf\xd4\xe7" + "\xb7\xf0\x82\x56\x41\xf7\xd4\xad\x8d\x94\x5a\x69\x89\xee\xca\x6a" + "\x52\x0e\x48\x4d\xcc\x02\x21\x00\xd7\xe4\xef\x52\x66\xd3\x5b\x9d" + "\x8a\xfa\x54\x93\x29\xa7\x70\x86\xf1\x03\x03\xf3\x3b\xe2\x73\xf7" + "\xfb\x9d\x8b\xde\xd4\x8d\x6f\xad", + .c_size = 72, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = + "\x04\x8b\x6d\xc0\x33\x8e\x2d\x8b\x67\xf5\xeb\xc4\x7f\xa0\xf5\xd9" + "\x7b\x03\xa5\x78\x9a\xb5\xea\x14\xe4\x23\xd0\xaf\xd7\x0e\x2e\xa0" + "\xc9\x8b\xdb\x95\xf8\xb3\xaf\xac\x00\x2c\x2c\x1f\x7a\xfd\x95\x88" + "\x43\x13\xbf\xf3\x1c\x05\x1a\x14\x18\x09\x3f\xd6\x28\x3e\xc5\xa0" + "\xd4", + .key_len = 65, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x07", + .param_len = 21, + .m = + "\x1a\x15\xbc\xa3\xe4\xed\x3a\xb8\x23\x67\xc6\xc4\x34\xf8\x6c\x41" + "\x04\x0b\xda\xc5\x77\xfa\x1c\x2d\xe6\x2c\x3b\xe0", + .m_size = 28, + .algo = OID_id_ecdsa_with_sha224, + .c = + "\x30\x44\x02\x20\x20\x43\xfa\xc0\x9f\x9d\x7b\xe7\xae\xce\x77\x59" + "\x1a\xdb\x59\xd5\x34\x62\x79\xcb\x6a\x91\x67\x2e\x7d\x25\xd8\x25" + "\xf5\x81\xd2\x1e\x02\x20\x5f\xf8\x74\xf8\x57\xd0\x5e\x54\x76\x20" + "\x4a\x77\x22\xec\xc8\x66\xbf\x50\x05\x58\x39\x0e\x26\x92\xce\xd5" + "\x2e\x8b\xde\x5a\x04\x0e", + .c_size = 70, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = + "\x04\xf1\xea\xc4\x53\xf3\xb9\x0e\x9f\x7e\xad\xe3\xea\xd7\x0e\x0f" + "\xd6\x98\x9a\xca\x92\x4d\x0a\x80\xdb\x2d\x45\xc7\xec\x4b\x97\x00" + "\x2f\xe9\x42\x6c\x29\xdc\x55\x0e\x0b\x53\x12\x9b\x2b\xad\x2c\xe9" + "\x80\xe6\xc5\x43\xc2\x1d\x5e\xbb\x65\x21\x50\xb6\x37\xb0\x03\x8e" + "\xb8", + .key_len = 65, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x07", + .param_len = 21, + .m = + "\x8f\x43\x43\x46\x64\x8f\x6b\x96\xdf\x89\xdd\xa9\x01\xc5\x17\x6b" + "\x10\xa6\xd8\x39\x61\xdd\x3c\x1a\xc8\x8b\x59\xb2\xdc\x32\x7a\xa4", + .m_size = 32, + .algo = OID_id_ecdsa_with_sha256, + .c = + "\x30\x45\x02\x20\x08\x31\xfa\x74\x0d\x1d\x21\x5d\x09\xdc\x29\x63" + "\xa8\x1a\xad\xfc\xac\x44\xc3\xe8\x24\x11\x2d\xa4\x91\xdc\x02\x67" + "\xdc\x0c\xd0\x82\x02\x21\x00\xbd\xff\xce\xee\x42\xc3\x97\xff\xf9" + "\xa9\x81\xac\x4a\x50\xd0\x91\x0a\x6e\x1b\xc4\xaf\xe1\x83\xc3\x4f" + "\x2a\x65\x35\x23\xe3\x1d\xfa", + .c_size = 71, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = + "\x04\xc5\xc6\xea\x60\xc9\xce\xad\x02\x8d\xf5\x3e\x24\xe3\x52\x1d" + "\x28\x47\x3b\xc3\x6b\xa4\x99\x35\x99\x11\x88\x88\xc8\xf4\xee\x7e" + "\x8c\x33\x8f\x41\x03\x24\x46\x2b\x1a\x82\xf9\x9f\xe1\x97\x1b\x00" + "\xda\x3b\x24\x41\xf7\x66\x33\x58\x3d\x3a\x81\xad\xcf\x16\xe9\xe2" + "\x7c", + .key_len = 65, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x07", + .param_len = 21, + .m = + "\x3e\x78\x70\xfb\xcd\x66\xba\x91\xa1\x79\xff\x1e\x1c\x6b\x78\xe6" + "\xc0\x81\x3a\x65\x97\x14\x84\x36\x14\x1a\x9a\xb7\xc5\xab\x84\x94" + "\x5e\xbb\x1b\x34\x71\xcb\x41\xe1\xf6\xfc\x92\x7b\x34\xbb\x86\xbb", + .m_size = 48, + .algo = OID_id_ecdsa_with_sha384, + .c = + "\x30\x46\x02\x21\x00\x8e\xf3\x6f\xdc\xf8\x69\xa6\x2e\xd0\x2e\x95" + "\x54\xd1\x95\x64\x93\x08\xb2\x6b\x24\x94\x48\x46\x5e\xf2\xe4\x6c" + "\xc7\x94\xb1\xd5\xfe\x02\x21\x00\xeb\xa7\x80\x26\xdc\xf9\x3a\x44" + "\x19\xfb\x5f\x92\xf4\xc9\x23\x37\x69\xf4\x3b\x4f\x47\xcf\x9b\x16" + "\xc0\x60\x11\x92\xdc\x17\x89\x12", + .c_size = 72, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = + "\x04\xd7\x27\x46\x49\xf6\x26\x85\x12\x40\x76\x8e\xe2\xe6\x2a\x7a" + "\x83\xb1\x4e\x7a\xeb\x3b\x5c\x67\x4a\xb5\xa4\x92\x8c\x69\xff\x38" + "\xee\xd9\x4e\x13\x29\x59\xad\xde\x6b\xbb\x45\x31\xee\xfd\xd1\x1b" + "\x64\xd3\xb5\xfc\xaf\x9b\x4b\x88\x3b\x0e\xb7\xd6\xdf\xf1\xd5\x92" + "\xbf", + .key_len = 65, + .params = + "\x30\x13\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x08\x2a\x86\x48" + "\xce\x3d\x03\x01\x07", + .param_len = 21, + .m = + "\x57\xb7\x9e\xe9\x05\x0a\x8c\x1b\xc9\x13\xe5\x4a\x24\xc7\xe2\xe9" + "\x43\xc3\xd1\x76\x62\xf4\x98\x1a\x9c\x13\xb0\x20\x1b\xe5\x39\xca" + "\x4f\xd9\x85\x34\x95\xa2\x31\xbc\xbb\xde\xdd\x76\xbb\x61\xe3\xcf" + "\x9d\xc0\x49\x7a\xf3\x7a\xc4\x7d\xa8\x04\x4b\x8d\xb4\x4d\x5b\xd6", + .m_size = 64, + .algo = OID_id_ecdsa_with_sha512, + .c = + "\x30\x45\x02\x21\x00\xb8\x6d\x87\x81\x43\xdf\xfb\x9f\x40\xea\x44" + "\x81\x00\x4e\x29\x08\xed\x8c\x73\x30\x6c\x22\xb3\x97\x76\xf6\x04" + "\x99\x09\x37\x4d\xfa\x02\x20\x1e\xb9\x75\x31\xf6\x04\xa5\x4d\xf8" + "\x00\xdd\xab\xd4\xc0\x2b\xe6\x5c\xad\xc3\x78\x1c\xc2\xc1\x19\x76" + "\x31\x79\x4a\xe9\x81\x6a\xee", + .c_size = 71, + .public_key_vec = true, + .siggen_sigver_test = true, + }, +}; + +static const struct akcipher_testvec ecdsa_nist_p384_tv_template[] = { + { + .key = /* secp384r1(sha1) */ + "\x04\x89\x25\xf3\x97\x88\xcb\xb0\x78\xc5\x72\x9a\x14\x6e\x7a\xb1" + "\x5a\xa5\x24\xf1\x95\x06\x9e\x28\xfb\xc4\xb9\xbe\x5a\x0d\xd9\x9f" + "\xf3\xd1\x4d\x2d\x07\x99\xbd\xda\xa7\x66\xec\xbb\xea\xba\x79\x42" + "\xc9\x34\x89\x6a\xe7\x0b\xc3\xf2\xfe\x32\x30\xbe\xba\xf9\xdf\x7e" + "\x4b\x6a\x07\x8e\x26\x66\x3f\x1d\xec\xa2\x57\x91\x51\xdd\x17\x0e" + "\x0b\x25\xd6\x80\x5c\x3b\xe6\x1a\x98\x48\x91\x45\x7a\x73\xb0\xc3" + "\xf1", + .key_len = 97, + .params = + "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04" + "\x00\x22", + .param_len = 18, + .m = + "\x12\x55\x28\xf0\x77\xd5\xb6\x21\x71\x32\x48\xcd\x28\xa8\x25\x22" + "\x3a\x69\xc1\x93", + .m_size = 20, + .algo = OID_id_ecdsa_with_sha1, + .c = + "\x30\x66\x02\x31\x00\xf5\x0f\x24\x4c\x07\x93\x6f\x21\x57\x55\x07" + "\x20\x43\x30\xde\xa0\x8d\x26\x8e\xae\x63\x3f\xbc\x20\x3a\xc6\xf1" + "\x32\x3c\xce\x70\x2b\x78\xf1\x4c\x26\xe6\x5b\x86\xcf\xec\x7c\x7e" + "\xd0\x87\xd7\xd7\x6e\x02\x31\x00\xcd\xbb\x7e\x81\x5d\x8f\x63\xc0" + "\x5f\x63\xb1\xbe\x5e\x4c\x0e\xa1\xdf\x28\x8c\x1b\xfa\xf9\x95\x88" + "\x74\xa0\x0f\xbf\xaf\xc3\x36\x76\x4a\xa1\x59\xf1\x1c\xa4\x58\x26" + "\x79\x12\x2a\xb7\xc5\x15\x92\xc5", + .c_size = 104, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = /* secp384r1(sha224) */ + "\x04\x69\x6c\xcf\x62\xee\xd0\x0d\xe5\xb5\x2f\x70\x54\xcf\x26\xa0" + "\xd9\x98\x8d\x92\x2a\xab\x9b\x11\xcb\x48\x18\xa1\xa9\x0d\xd5\x18" + "\x3e\xe8\x29\x6e\xf6\xe4\xb5\x8e\xc7\x4a\xc2\x5f\x37\x13\x99\x05" + "\xb6\xa4\x9d\xf9\xfb\x79\x41\xe7\xd7\x96\x9f\x73\x3b\x39\x43\xdc" + "\xda\xf4\x06\xb9\xa5\x29\x01\x9d\x3b\xe1\xd8\x68\x77\x2a\xf4\x50" + "\x6b\x93\x99\x6c\x66\x4c\x42\x3f\x65\x60\x6c\x1c\x0b\x93\x9b\x9d" + "\xe0", + .key_len = 97, + .params = + "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04" + "\x00\x22", + .param_len = 18, + .m = + "\x12\x80\xb6\xeb\x25\xe2\x3d\xf0\x21\x32\x96\x17\x3a\x38\x39\xfd" + "\x1f\x05\x34\x7b\xb8\xf9\x71\x66\x03\x4f\xd5\xe5", + .m_size = 28, + .algo = OID_id_ecdsa_with_sha224, + .c = + "\x30\x66\x02\x31\x00\x8a\x51\x84\xce\x13\x1e\xd2\xdc\xec\xcb\xe4" + "\x89\x47\xb2\xf7\xbc\x97\xf1\xc8\x72\x26\xcf\x5a\x5e\xc5\xda\xb4" + "\xe3\x93\x07\xe0\x99\xc9\x9c\x11\xb8\x10\x01\xc5\x41\x3f\xdd\x15" + "\x1b\x68\x2b\x9d\x8b\x02\x31\x00\x8b\x03\x2c\xfc\x1f\xd1\xa9\xa4" + "\x4b\x00\x08\x31\x6c\xf5\xd5\xf6\xdf\xd8\x68\xa2\x64\x42\x65\xf3" + "\x4d\xd0\xc6\x6e\xb0\xe9\xfc\x14\x9f\x19\xd0\x42\x8b\x93\xc2\x11" + "\x88\x2b\x82\x26\x5e\x1c\xda\xfb", + .c_size = 104, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = /* secp384r1(sha256) */ + "\x04\xee\xd6\xda\x3e\x94\x90\x00\x27\xed\xf8\x64\x55\xd6\x51\x9a" + "\x1f\x52\x00\x63\x78\xf1\xa9\xfd\x75\x4c\x9e\xb2\x20\x1a\x91\x5a" + "\xba\x7a\xa3\xe5\x6c\xb6\x25\x68\x4b\xe8\x13\xa6\x54\x87\x2c\x0e" + "\xd0\x83\x95\xbc\xbf\xc5\x28\x4f\x77\x1c\x46\xa6\xf0\xbc\xd4\xa4" + "\x8d\xc2\x8f\xb3\x32\x37\x40\xd6\xca\xf8\xae\x07\x34\x52\x39\x52" + "\x17\xc3\x34\x29\xd6\x40\xea\x5c\xb9\x3f\xfb\x32\x2e\x12\x33\xbc" + "\xab", + .key_len = 97, + .params = + "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04" + "\x00\x22", + .param_len = 18, + .m = + "\xaa\xe7\xfd\x03\x26\xcb\x94\x71\xe4\xce\x0f\xc5\xff\xa6\x29\xa3" + "\xe1\xcc\x4c\x35\x4e\xde\xca\x80\xab\x26\x0c\x25\xe6\x68\x11\xc2", + .m_size = 32, + .algo = OID_id_ecdsa_with_sha256, + .c = + "\x30\x64\x02\x30\x08\x09\x12\x9d\x6e\x96\x64\xa6\x8e\x3f\x7e\xce" + "\x0a\x9b\xaa\x59\xcc\x47\x53\x87\xbc\xbd\x83\x3f\xaf\x06\x3f\x84" + "\x04\xe2\xf9\x67\xb6\xc6\xfc\x70\x2e\x66\x3c\x77\xc8\x8d\x2c\x79" + "\x3a\x8e\x32\xc4\x02\x30\x40\x34\xb8\x90\xa9\x80\xab\x47\x26\xa2" + "\xb0\x89\x42\x0a\xda\xd9\xdd\xce\xbc\xb2\x97\xf4\x9c\xf3\x15\x68" + "\xc0\x75\x3e\x23\x5e\x36\x4f\x8d\xde\x1e\x93\x8d\x95\xbb\x10\x0e" + "\xf4\x1f\x39\xca\x4d\x43", + .c_size = 102, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = /* secp384r1(sha384) */ + "\x04\x3a\x2f\x62\xe7\x1a\xcf\x24\xd0\x0b\x7c\xe0\xed\x46\x0a\x4f" + "\x74\x16\x43\xe9\x1a\x25\x7c\x55\xff\xf0\x29\x68\x66\x20\x91\xf9" + "\xdb\x2b\xf6\xb3\x6c\x54\x01\xca\xc7\x6a\x5c\x0d\xeb\x68\xd9\x3c" + "\xf1\x01\x74\x1f\xf9\x6c\xe5\x5b\x60\xe9\x7f\x5d\xb3\x12\x80\x2a" + "\xd8\x67\x92\xc9\x0e\x4c\x4c\x6b\xa1\xb2\xa8\x1e\xac\x1c\x97\xd9" + "\x21\x67\xe5\x1b\x5a\x52\x31\x68\xd6\xee\xf0\x19\xb0\x55\xed\x89" + "\x9e", + .key_len = 97, + .params = + "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04" + "\x00\x22", + .param_len = 18, + .m = + "\x8d\xf2\xc0\xe9\xa8\xf3\x8e\x44\xc4\x8c\x1a\xa0\xb8\xd7\x17\xdf" + "\xf2\x37\x1b\xc6\xe3\xf5\x62\xcc\x68\xf5\xd5\x0b\xbf\x73\x2b\xb1" + "\xb0\x4c\x04\x00\x31\xab\xfe\xc8\xd6\x09\xc8\xf2\xea\xd3\x28\xff", + .m_size = 48, + .algo = OID_id_ecdsa_with_sha384, + .c = + "\x30\x66\x02\x31\x00\x9b\x28\x68\xc0\xa1\xea\x8c\x50\xee\x2e\x62" + "\x35\x46\xfa\x00\xd8\x2d\x7a\x91\x5f\x49\x2d\x22\x08\x29\xe6\xfb" + "\xca\x8c\xd6\xb6\xb4\x3b\x1f\x07\x8f\x15\x02\xfe\x1d\xa2\xa4\xc8" + "\xf2\xea\x9d\x11\x1f\x02\x31\x00\xfc\x50\xf6\x43\xbd\x50\x82\x0e" + "\xbf\xe3\x75\x24\x49\xac\xfb\xc8\x71\xcd\x8f\x18\x99\xf0\x0f\x13" + "\x44\x92\x8c\x86\x99\x65\xb3\x97\x96\x17\x04\xc9\x05\x77\xf1\x8e" + "\xab\x8d\x4e\xde\xe6\x6d\x9b\x66", + .c_size = 104, + .public_key_vec = true, + .siggen_sigver_test = true, + }, { + .key = /* secp384r1(sha512) */ + "\x04\xb4\xe7\xc1\xeb\x64\x25\x22\x46\xc3\x86\x61\x80\xbe\x1e\x46" + "\xcb\xf6\x05\xc2\xee\x73\x83\xbc\xea\x30\x61\x4d\x40\x05\x41\xf4" + "\x8c\xe3\x0e\x5c\xf0\x50\xf2\x07\x19\xe8\x4f\x25\xbe\xee\x0c\x95" + "\x54\x36\x86\xec\xc2\x20\x75\xf3\x89\xb5\x11\xa1\xb7\xf5\xaf\xbe" + "\x81\xe4\xc3\x39\x06\xbd\xe4\xfe\x68\x1c\x6d\x99\x2b\x1b\x63\xfa" + "\xdf\x42\x5c\xc2\x5a\xc7\x0c\xf4\x15\xf7\x1b\xa3\x2e\xd7\x00\xac" + "\xa3", + .key_len = 97, + .params = + "\x30\x10\x06\x07\x2a\x86\x48\xce\x3d\x02\x01\x06\x05\x2b\x81\x04" + "\x00\x22", + .param_len = 18, + .m = + "\xe8\xb7\x52\x7d\x1a\x44\x20\x05\x53\x6b\x3a\x68\xf2\xe7\x6c\xa1" + "\xae\x9d\x84\xbb\xba\x52\x43\x3e\x2c\x42\x78\x49\xbf\x78\xb2\x71" + "\xeb\xe1\xe0\xe8\x42\x7b\x11\xad\x2b\x99\x05\x1d\x36\xe6\xac\xfc" + "\x55\x73\xf0\x15\x63\x39\xb8\x6a\x6a\xc5\x91\x5b\xca\x6a\xa8\x0e", + .m_size = 64, + .algo = OID_id_ecdsa_with_sha512, + .c = + "\x30\x63\x02\x2f\x1d\x20\x94\x77\xfe\x31\xfa\x4d\xc6\xef\xda\x02" + "\xe7\x0f\x52\x9a\x02\xde\x93\xe8\x83\xe4\x84\x4c\xfc\x6f\x80\xe3" + "\xaf\xb3\xd9\xdc\x2b\x43\x0e\x6a\xb3\x53\x6f\x3e\xb3\xc7\xa8\xb3" + "\x17\x77\xd1\x02\x30\x63\xf6\xf0\x3d\x5f\x5f\x99\x3f\xde\x3a\x3d" + "\x16\xaf\xb4\x52\x6a\xec\x63\xe3\x0c\xec\x50\xdc\xcc\xc4\x6a\x03" + "\x5f\x8d\x7a\xf9\xfb\x34\xe4\x8b\x80\xa5\xb6\xda\x2c\x4e\x45\xcf" + "\x3c\x93\xff\x50\x5d", + .c_size = 101, + .public_key_vec = true, + .siggen_sigver_test = true, + }, +}; + +/* * EC-RDSA test vectors are generated by gost-engine. */ static const struct akcipher_testvec ecrdsa_tv_template[] = { @@ -2261,19 +2685,17 @@ static const struct kpp_testvec curve25519_tv_template[] = { } }; -static const struct kpp_testvec ecdh_tv_template[] = { - { #ifndef CONFIG_CRYPTO_FIPS +static const struct kpp_testvec ecdh_p192_tv_template[] = { + { .secret = #ifdef __LITTLE_ENDIAN "\x02\x00" /* type */ - "\x20\x00" /* len */ - "\x01\x00" /* curve_id */ + "\x1e\x00" /* len */ "\x18\x00" /* key_size */ #else "\x00\x02" /* type */ - "\x00\x20" /* len */ - "\x00\x01" /* curve_id */ + "\x00\x1e" /* len */ "\x00\x18" /* key_size */ #endif "\xb5\x05\xb1\x71\x1e\xbf\x8c\xda" @@ -2301,18 +2723,20 @@ static const struct kpp_testvec ecdh_tv_template[] = { .b_public_size = 48, .expected_a_public_size = 48, .expected_ss_size = 24 - }, { + } +}; #endif + +static const struct kpp_testvec ecdh_p256_tv_template[] = { + { .secret = #ifdef __LITTLE_ENDIAN "\x02\x00" /* type */ - "\x28\x00" /* len */ - "\x02\x00" /* curve_id */ + "\x26\x00" /* len */ "\x20\x00" /* key_size */ #else "\x00\x02" /* type */ - "\x00\x28" /* len */ - "\x00\x02" /* curve_id */ + "\x00\x26" /* len */ "\x00\x20" /* key_size */ #endif "\x24\xd1\x21\xeb\xe5\xcf\x2d\x83" @@ -2350,25 +2774,21 @@ static const struct kpp_testvec ecdh_tv_template[] = { .secret = #ifdef __LITTLE_ENDIAN "\x02\x00" /* type */ - "\x08\x00" /* len */ - "\x02\x00" /* curve_id */ + "\x06\x00" /* len */ "\x00\x00", /* key_size */ #else "\x00\x02" /* type */ - "\x00\x08" /* len */ - "\x00\x02" /* curve_id */ + "\x00\x06" /* len */ "\x00\x00", /* key_size */ #endif .b_secret = #ifdef __LITTLE_ENDIAN "\x02\x00" /* type */ - "\x28\x00" /* len */ - "\x02\x00" /* curve_id */ + "\x26\x00" /* len */ "\x20\x00" /* key_size */ #else "\x00\x02" /* type */ - "\x00\x28" /* len */ - "\x00\x02" /* curve_id */ + "\x00\x26" /* len */ "\x00\x20" /* key_size */ #endif "\x24\xd1\x21\xeb\xe5\xcf\x2d\x83" diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c index 3f045b5953b2..a0c1a665dfc1 100644 --- a/drivers/acpi/acpica/nsaccess.c +++ b/drivers/acpi/acpica/nsaccess.c @@ -99,13 +99,12 @@ acpi_status acpi_ns_root_initialize(void) * just create and link the new node(s) here. */ new_node = - ACPI_ALLOCATE_ZEROED(sizeof(struct acpi_namespace_node)); + acpi_ns_create_node(*ACPI_CAST_PTR(u32, init_val->name)); if (!new_node) { status = AE_NO_MEMORY; goto unlock_and_exit; } - ACPI_COPY_NAMESEG(new_node->name.ascii, init_val->name); new_node->descriptor_type = ACPI_DESC_TYPE_NAMED; new_node->type = init_val->type; diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index e6a5d997241c..cb8f70842249 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -9,6 +9,8 @@ #ifndef _ACPI_INTERNAL_H_ #define _ACPI_INTERNAL_H_ +#include <linux/idr.h> + #define PREFIX "ACPI: " int early_acpi_osi_init(void); @@ -96,9 +98,11 @@ void acpi_scan_table_handler(u32 event, void *table, void *context); extern struct list_head acpi_bus_id_list; +#define ACPI_MAX_DEVICE_INSTANCES 4096 + struct acpi_device_bus_id { const char *bus_id; - unsigned int instance_no; + struct ida instance_ida; struct list_head node; }; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index d93e400940a3..4e2d76b8b697 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -29,6 +29,7 @@ */ #ifdef CONFIG_X86 #include <asm/apic.h> +#include <asm/cpu.h> #endif #define _COMPONENT ACPI_PROCESSOR_COMPONENT @@ -541,6 +542,10 @@ static int acpi_idle_play_dead(struct cpuidle_device *dev, int index) wait_for_freeze(); } else return -ENODEV; + +#if defined(CONFIG_X86) && defined(CONFIG_HOTPLUG_CPU) + cond_wakeup_cpu0(); +#endif } /* Never reached */ diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index a184529d8fa4..6efe7edd7b1e 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -479,9 +479,8 @@ static void acpi_device_del(struct acpi_device *device) list_for_each_entry(acpi_device_bus_id, &acpi_bus_id_list, node) if (!strcmp(acpi_device_bus_id->bus_id, acpi_device_hid(device))) { - if (acpi_device_bus_id->instance_no > 0) - acpi_device_bus_id->instance_no--; - else { + ida_simple_remove(&acpi_device_bus_id->instance_ida, device->pnp.instance_no); + if (ida_is_empty(&acpi_device_bus_id->instance_ida)) { list_del(&acpi_device_bus_id->node); kfree_const(acpi_device_bus_id->bus_id); kfree(acpi_device_bus_id); @@ -631,6 +630,21 @@ static struct acpi_device_bus_id *acpi_device_bus_id_match(const char *dev_id) return NULL; } +static int acpi_device_set_name(struct acpi_device *device, + struct acpi_device_bus_id *acpi_device_bus_id) +{ + struct ida *instance_ida = &acpi_device_bus_id->instance_ida; + int result; + + result = ida_simple_get(instance_ida, 0, ACPI_MAX_DEVICE_INSTANCES, GFP_KERNEL); + if (result < 0) + return result; + + device->pnp.instance_no = result; + dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, result); + return 0; +} + int acpi_device_add(struct acpi_device *device, void (*release)(struct device *)) { @@ -665,7 +679,9 @@ int acpi_device_add(struct acpi_device *device, acpi_device_bus_id = acpi_device_bus_id_match(acpi_device_hid(device)); if (acpi_device_bus_id) { - acpi_device_bus_id->instance_no++; + result = acpi_device_set_name(device, acpi_device_bus_id); + if (result) + goto err_unlock; } else { acpi_device_bus_id = kzalloc(sizeof(*acpi_device_bus_id), GFP_KERNEL); @@ -681,9 +697,16 @@ int acpi_device_add(struct acpi_device *device, goto err_unlock; } + ida_init(&acpi_device_bus_id->instance_ida); + + result = acpi_device_set_name(device, acpi_device_bus_id); + if (result) { + kfree(acpi_device_bus_id); + goto err_unlock; + } + list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list); } - dev_set_name(&device->dev, "%s:%02x", acpi_device_bus_id->bus_id, acpi_device_bus_id->instance_no); if (device->parent) list_add_tail(&device->node, &device->parent->children); @@ -1647,6 +1670,8 @@ void acpi_init_device_object(struct acpi_device *device, acpi_handle handle, device_initialize(&device->dev); dev_set_uevent_suppress(&device->dev, true); acpi_init_coherency(device); + /* Assume there are unmet deps to start with. */ + device->dep_unmet = 1; } void acpi_device_add_finalize(struct acpi_device *device) @@ -1910,6 +1935,8 @@ static void acpi_scan_dep_init(struct acpi_device *adev) { struct acpi_dep_data *dep; + adev->dep_unmet = 0; + mutex_lock(&acpi_dep_list_lock); list_for_each_entry(dep, &acpi_dep_list, node) { @@ -1957,7 +1984,13 @@ static acpi_status acpi_bus_check_add(acpi_handle handle, bool check_dep, return AE_CTRL_DEPTH; acpi_scan_init_hotplug(device); - if (!check_dep) + /* + * If check_dep is true at this point, the device has no dependencies, + * or the creation of the device object would have been postponed above. + */ + if (check_dep) + device->dep_unmet = 0; + else acpi_scan_dep_init(device); out: diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index e48690a006a4..9d581045acff 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -780,7 +780,7 @@ acpi_status acpi_os_table_override(struct acpi_table_header *existing_table, } /* - * acpi_table_init() + * acpi_locate_initial_tables() * * find RSDP, find and checksum SDT/XSDT. * checksum all tables, print SDT/XSDT @@ -788,7 +788,7 @@ acpi_status acpi_os_table_override(struct acpi_table_header *existing_table, * result: sdt_entry[] is initialized */ -int __init acpi_table_init(void) +int __init acpi_locate_initial_tables(void) { acpi_status status; @@ -803,9 +803,45 @@ int __init acpi_table_init(void) status = acpi_initialize_tables(initial_tables, ACPI_MAX_TABLES, 0); if (ACPI_FAILURE(status)) return -EINVAL; - acpi_table_initrd_scan(); + return 0; +} + +void __init acpi_reserve_initial_tables(void) +{ + int i; + + for (i = 0; i < ACPI_MAX_TABLES; i++) { + struct acpi_table_desc *table_desc = &initial_tables[i]; + u64 start = table_desc->address; + u64 size = table_desc->length; + + if (!start || !size) + break; + + pr_info("Reserving %4s table memory at [mem 0x%llx-0x%llx]\n", + table_desc->signature.ascii, start, start + size - 1); + + memblock_reserve(start, size); + } +} + +void __init acpi_table_init_complete(void) +{ + acpi_table_initrd_scan(); check_multiple_madt(); +} + +int __init acpi_table_init(void) +{ + int ret; + + ret = acpi_locate_initial_tables(); + if (ret) + return ret; + + acpi_table_init_complete(); + return 0; } diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 811d298637cb..83cd4c95faf0 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -147,6 +147,7 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, }, { + .callback = video_detect_force_vendor, .ident = "Sony VPCEH3U1E", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"), diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c index f43430e9dcee..24fd6f369ebe 100644 --- a/drivers/auxdisplay/charlcd.c +++ b/drivers/auxdisplay/charlcd.c @@ -470,12 +470,14 @@ static ssize_t charlcd_write(struct file *file, const char __user *buf, char c; for (; count-- > 0; (*ppos)++, tmp++) { - if (!in_interrupt() && (((count + 1) & 0x1f) == 0)) + if (((count + 1) & 0x1f) == 0) { /* - * let's be a little nice with other processes - * that need some CPU + * charlcd_write() is invoked as a VFS->write() callback + * and as such it is always invoked from preemptible + * context and may sleep. */ - schedule(); + cond_resched(); + } if (get_user(c, tmp)) return -EFAULT; @@ -537,12 +539,8 @@ static void charlcd_puts(struct charlcd *lcd, const char *s) int count = strlen(s); for (; count-- > 0; tmp++) { - if (!in_interrupt() && (((count + 1) & 0x1f) == 0)) - /* - * let's be a little nice with other processes - * that need some CPU - */ - schedule(); + if (((count + 1) & 0x1f) == 0) + cond_resched(); charlcd_write_char(lcd, *tmp); } diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 9179825ff646..37a5e5f8b221 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -97,6 +97,9 @@ static void deferred_probe_work_func(struct work_struct *work) get_device(dev); + kfree(dev->p->deferred_probe_reason); + dev->p->deferred_probe_reason = NULL; + /* * Drop the mutex while probing each device; the probe path may * manipulate the deferred list @@ -289,14 +292,16 @@ int driver_deferred_probe_check_state(struct device *dev) static void deferred_probe_timeout_work_func(struct work_struct *work) { - struct device_private *private, *p; + struct device_private *p; driver_deferred_probe_timeout = 0; driver_deferred_probe_trigger(); flush_work(&deferred_probe_work); - list_for_each_entry_safe(private, p, &deferred_probe_pending_list, deferred_probe) - dev_info(private->device, "deferred probe pending\n"); + mutex_lock(&deferred_probe_mutex); + list_for_each_entry(p, &deferred_probe_pending_list, deferred_probe) + dev_info(p->device, "deferred probe pending\n"); + mutex_unlock(&deferred_probe_mutex); wake_up_all(&probe_timeout_waitqueue); } static DECLARE_DELAYED_WORK(deferred_probe_timeout_work, deferred_probe_timeout_work_func); diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index a46a7e30881b..fe1dad68aee4 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -305,7 +305,7 @@ static int rpm_get_suppliers(struct device *dev) return 0; } -static void rpm_put_suppliers(struct device *dev) +static void __rpm_put_suppliers(struct device *dev, bool try_to_suspend) { struct device_link *link; @@ -313,10 +313,30 @@ static void rpm_put_suppliers(struct device *dev) device_links_read_lock_held()) { while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put(link->supplier); + pm_runtime_put_noidle(link->supplier); + + if (try_to_suspend) + pm_request_idle(link->supplier); } } +static void rpm_put_suppliers(struct device *dev) +{ + __rpm_put_suppliers(dev, true); +} + +static void rpm_suspend_suppliers(struct device *dev) +{ + struct device_link *link; + int idx = device_links_read_lock(); + + list_for_each_entry_rcu(link, &dev->links.suppliers, c_node, + device_links_read_lock_held()) + pm_request_idle(link->supplier); + + device_links_read_unlock(idx); +} + /** * __rpm_callback - Run a given runtime PM callback for a given device. * @cb: Runtime PM callback to run. @@ -344,8 +364,10 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) idx = device_links_read_lock(); retval = rpm_get_suppliers(dev); - if (retval) + if (retval) { + rpm_put_suppliers(dev); goto fail; + } device_links_read_unlock(idx); } @@ -368,9 +390,9 @@ static int __rpm_callback(int (*cb)(struct device *), struct device *dev) || (dev->power.runtime_status == RPM_RESUMING && retval))) { idx = device_links_read_lock(); - fail: - rpm_put_suppliers(dev); + __rpm_put_suppliers(dev, false); +fail: device_links_read_unlock(idx); } @@ -642,8 +664,11 @@ static int rpm_suspend(struct device *dev, int rpmflags) goto out; } + if (dev->power.irq_safe) + goto out; + /* Maybe the parent is now able to suspend. */ - if (parent && !parent->power.ignore_children && !dev->power.irq_safe) { + if (parent && !parent->power.ignore_children) { spin_unlock(&dev->power.lock); spin_lock(&parent->power.lock); @@ -652,6 +677,14 @@ static int rpm_suspend(struct device *dev, int rpmflags) spin_lock(&dev->power.lock); } + /* Maybe the suppliers are now able to suspend. */ + if (dev->power.links_count > 0) { + spin_unlock_irq(&dev->power.lock); + + rpm_suspend_suppliers(dev); + + spin_lock_irq(&dev->power.lock); + } out: trace_rpm_return_int_rcuidle(dev, _THIS_IP_, retval); @@ -1657,8 +1690,8 @@ void pm_runtime_get_suppliers(struct device *dev) device_links_read_lock_held()) if (link->flags & DL_FLAG_PM_RUNTIME) { link->supplier_preactivated = true; - refcount_inc(&link->rpm_active); pm_runtime_get_sync(link->supplier); + refcount_inc(&link->rpm_active); } device_links_read_unlock(idx); @@ -1671,6 +1704,8 @@ void pm_runtime_get_suppliers(struct device *dev) void pm_runtime_put_suppliers(struct device *dev) { struct device_link *link; + unsigned long flags; + bool put; int idx; idx = device_links_read_lock(); @@ -1679,7 +1714,11 @@ void pm_runtime_put_suppliers(struct device *dev) device_links_read_lock_held()) if (link->supplier_preactivated) { link->supplier_preactivated = false; - if (refcount_dec_not_one(&link->rpm_active)) + spin_lock_irqsave(&dev->power.lock, flags); + put = pm_runtime_status_suspended(dev) && + refcount_dec_not_one(&link->rpm_active); + spin_unlock_irqrestore(&dev->power.lock, flags); + if (put) pm_runtime_put(link->supplier); } diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index d6c821d48090..51bfd7737552 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1369,10 +1369,13 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd, sector_t sector, } if (dev->zoned) - cmd->error = null_process_zoned_cmd(cmd, op, - sector, nr_sectors); + sts = null_process_zoned_cmd(cmd, op, sector, nr_sectors); else - cmd->error = null_process_cmd(cmd, op, sector, nr_sectors); + sts = null_process_cmd(cmd, op, sector, nr_sectors); + + /* Do not overwrite errors (e.g. timeout errors) */ + if (cmd->error == BLK_STS_OK) + cmd->error = sts; out: nullb_complete_cmd(cmd); @@ -1451,8 +1454,20 @@ static bool should_requeue_request(struct request *rq) static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res) { + struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); + pr_info("rq %p timed out\n", rq); - blk_mq_complete_request(rq); + + /* + * If the device is marked as blocking (i.e. memory backed or zoned + * device), the submission path may be blocked waiting for resources + * and cause real timeouts. For these real timeouts, the submission + * path will complete the request using blk_mq_complete_request(). + * Only fake timeouts need to execute blk_mq_complete_request() here. + */ + cmd->error = BLK_STS_TIMEOUT; + if (cmd->fake_timeout) + blk_mq_complete_request(rq); return BLK_EH_DONE; } @@ -1473,6 +1488,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, cmd->rq = bd->rq; cmd->error = BLK_STS_OK; cmd->nq = nq; + cmd->fake_timeout = should_timeout_request(bd->rq); blk_mq_start_request(bd->rq); @@ -1489,7 +1505,7 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } } - if (should_timeout_request(bd->rq)) + if (cmd->fake_timeout) return BLK_STS_OK; return null_handle_cmd(cmd, sector, nr_sectors, req_op(bd->rq)); diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index 83504f3cc9d6..4876d5adb12d 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -22,6 +22,7 @@ struct nullb_cmd { blk_status_t error; struct nullb_queue *nq; struct hrtimer timer; + bool fake_timeout; }; struct nullb_queue { diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 1cdf09ff67b6..14e452896d04 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -891,7 +891,7 @@ next: out: for (i = last_map; i < num; i++) { /* Don't zap current batch's valid persistent grants. */ - if(i >= last_map + segs_to_map) + if(i >= map_until) pages[i]->persistent_gnt = NULL; pages[i]->handle = BLKBACK_INVALID_HANDLE; } diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 52683fd22e05..5cbfbd948f67 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4849,8 +4849,8 @@ static int btusb_probe(struct usb_interface *intf, data->diag = NULL; } - if (!enable_autosuspend) - usb_disable_autosuspend(data->udev); + if (enable_autosuspend) + usb_enable_autosuspend(data->udev); err = hci_register_dev(hdev); if (err < 0) @@ -4910,9 +4910,6 @@ static void btusb_disconnect(struct usb_interface *intf) gpiod_put(data->reset_gpio); hci_free_dev(hdev); - - if (!enable_autosuspend) - usb_enable_autosuspend(data->udev); } #ifdef CONFIG_PM diff --git a/drivers/bus/moxtet.c b/drivers/bus/moxtet.c index b20fdcbd035b..fd87a59837fa 100644 --- a/drivers/bus/moxtet.c +++ b/drivers/bus/moxtet.c @@ -2,7 +2,7 @@ /* * Turris Mox module configuration bus driver * - * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz> + * Copyright (C) 2019 Marek Behún <kabel@kernel.org> */ #include <dt-bindings/bus/moxtet.h> @@ -879,6 +879,6 @@ static void __exit moxtet_exit(void) } module_exit(moxtet_exit); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); MODULE_DESCRIPTION("CZ.NIC's Turris Mox module configuration bus"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c index dd9e7343a5e3..ea0424922de7 100644 --- a/drivers/bus/mvebu-mbus.c +++ b/drivers/bus/mvebu-mbus.c @@ -618,7 +618,7 @@ mvebu_mbus_find_bridge_hole(uint64_t *start, uint64_t *end) * This part of the memory is above 4 GB, so we don't * care for the MBus bridge hole. */ - if (reg_start >= 0x100000000ULL) + if ((u64)reg_start >= 0x100000000ULL) continue; /* diff --git a/drivers/bus/omap_l3_noc.c b/drivers/bus/omap_l3_noc.c index b040447575ad..dcfb32ee5cb6 100644 --- a/drivers/bus/omap_l3_noc.c +++ b/drivers/bus/omap_l3_noc.c @@ -285,7 +285,7 @@ static int omap_l3_probe(struct platform_device *pdev) */ l3->debug_irq = platform_get_irq(pdev, 0); ret = devm_request_irq(l3->dev, l3->debug_irq, l3_interrupt_handler, - 0x0, "l3-dbg-irq", l3); + IRQF_NO_THREAD, "l3-dbg-irq", l3); if (ret) { dev_err(l3->dev, "request_irq failed for %d\n", l3->debug_irq); @@ -294,7 +294,7 @@ static int omap_l3_probe(struct platform_device *pdev) l3->app_irq = platform_get_irq(pdev, 1); ret = devm_request_irq(l3->dev, l3->app_irq, l3_interrupt_handler, - 0x0, "l3-app-irq", l3); + IRQF_NO_THREAD, "l3-app-irq", l3); if (ret) dev_err(l3->dev, "request_irq failed for %d\n", l3->app_irq); diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index a27d751cf219..3d74f237f005 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -3053,7 +3053,9 @@ static int sysc_remove(struct platform_device *pdev) pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); - reset_control_assert(ddata->rsts); + + if (!reset_control_status(ddata->rsts)) + reset_control_assert(ddata->rsts); unprepare: sysc_unprepare(ddata); diff --git a/drivers/char/agp/Kconfig b/drivers/char/agp/Kconfig index a086dd34f932..4f501e4842ab 100644 --- a/drivers/char/agp/Kconfig +++ b/drivers/char/agp/Kconfig @@ -125,7 +125,7 @@ config AGP_HP_ZX1 config AGP_PARISC tristate "HP Quicksilver AGP support" - depends on AGP && PARISC && 64BIT + depends on AGP && PARISC && 64BIT && IOMMU_SBA help This option gives you AGP GART support for the HP Quicksilver AGP bus adapter on HP PA-RISC machines (Ok, just on the C8000 diff --git a/drivers/char/hw_random/ba431-rng.c b/drivers/char/hw_random/ba431-rng.c index 410b50b05e21..5b7ca0416490 100644 --- a/drivers/char/hw_random/ba431-rng.c +++ b/drivers/char/hw_random/ba431-rng.c @@ -170,7 +170,6 @@ static int ba431_trng_init(struct hwrng *rng) static int ba431_trng_probe(struct platform_device *pdev) { struct ba431_trng *ba431; - struct resource *res; int ret; ba431 = devm_kzalloc(&pdev->dev, sizeof(*ba431), GFP_KERNEL); @@ -179,8 +178,7 @@ static int ba431_trng_probe(struct platform_device *pdev) ba431->dev = &pdev->dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ba431->base = devm_ioremap_resource(&pdev->dev, res); + ba431->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ba431->base)) return PTR_ERR(ba431->base); @@ -193,7 +191,7 @@ static int ba431_trng_probe(struct platform_device *pdev) platform_set_drvdata(pdev, ba431); - ret = hwrng_register(&ba431->rng); + ret = devm_hwrng_register(&pdev->dev, &ba431->rng); if (ret) { dev_err(&pdev->dev, "BA431 registration failed (%d)\n", ret); return ret; @@ -204,15 +202,6 @@ static int ba431_trng_probe(struct platform_device *pdev) return 0; } -static int ba431_trng_remove(struct platform_device *pdev) -{ - struct ba431_trng *ba431 = platform_get_drvdata(pdev); - - hwrng_unregister(&ba431->rng); - - return 0; -} - static const struct of_device_id ba431_trng_dt_ids[] = { { .compatible = "silex-insight,ba431-rng", .data = NULL }, { /* sentinel */ } @@ -225,7 +214,6 @@ static struct platform_driver ba431_trng_driver = { .of_match_table = ba431_trng_dt_ids, }, .probe = ba431_trng_probe, - .remove = ba431_trng_remove, }; module_platform_driver(ba431_trng_driver); diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c index 1a7c43b43c6b..e7dd457e9b22 100644 --- a/drivers/char/hw_random/bcm2835-rng.c +++ b/drivers/char/hw_random/bcm2835-rng.c @@ -13,6 +13,7 @@ #include <linux/platform_device.h> #include <linux/printk.h> #include <linux/clk.h> +#include <linux/reset.h> #define RNG_CTRL 0x0 #define RNG_STATUS 0x4 @@ -32,6 +33,7 @@ struct bcm2835_rng_priv { void __iomem *base; bool mask_interrupts; struct clk *clk; + struct reset_control *reset; }; static inline struct bcm2835_rng_priv *to_rng_priv(struct hwrng *rng) @@ -88,11 +90,13 @@ static int bcm2835_rng_init(struct hwrng *rng) int ret = 0; u32 val; - if (!IS_ERR(priv->clk)) { - ret = clk_prepare_enable(priv->clk); - if (ret) - return ret; - } + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; + + ret = reset_control_reset(priv->reset); + if (ret) + return ret; if (priv->mask_interrupts) { /* mask the interrupt */ @@ -115,8 +119,7 @@ static void bcm2835_rng_cleanup(struct hwrng *rng) /* disable rng hardware */ rng_writel(priv, 0, RNG_CTRL); - if (!IS_ERR(priv->clk)) - clk_disable_unprepare(priv->clk); + clk_disable_unprepare(priv->clk); } struct bcm2835_rng_of_data { @@ -155,9 +158,13 @@ static int bcm2835_rng_probe(struct platform_device *pdev) return PTR_ERR(priv->base); /* Clock is optional on most platforms */ - priv->clk = devm_clk_get(dev, NULL); - if (PTR_ERR(priv->clk) == -EPROBE_DEFER) - return -EPROBE_DEFER; + priv->clk = devm_clk_get_optional(dev, NULL); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); + + priv->reset = devm_reset_control_get_optional_exclusive(dev, NULL); + if (IS_ERR(priv->reset)) + return PTR_ERR(priv->reset); priv->rng.name = pdev->name; priv->rng.init = bcm2835_rng_init; diff --git a/drivers/char/hw_random/cctrng.c b/drivers/char/hw_random/cctrng.c index 7a293f2147a0..302ffa354c2f 100644 --- a/drivers/char/hw_random/cctrng.c +++ b/drivers/char/hw_random/cctrng.c @@ -486,7 +486,6 @@ static void cc_trng_clk_fini(struct cctrng_drvdata *drvdata) static int cctrng_probe(struct platform_device *pdev) { - struct resource *req_mem_cc_regs = NULL; struct cctrng_drvdata *drvdata; struct device *dev = &pdev->dev; int rc = 0; @@ -510,27 +509,16 @@ static int cctrng_probe(struct platform_device *pdev) drvdata->circ.buf = (char *)drvdata->data_buf; - /* Get device resources */ - /* First CC registers space */ - req_mem_cc_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - /* Map registers space */ - drvdata->cc_base = devm_ioremap_resource(dev, req_mem_cc_regs); + drvdata->cc_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(drvdata->cc_base)) { dev_err(dev, "Failed to ioremap registers"); return PTR_ERR(drvdata->cc_base); } - dev_dbg(dev, "Got MEM resource (%s): %pR\n", req_mem_cc_regs->name, - req_mem_cc_regs); - dev_dbg(dev, "CC registers mapped from %pa to 0x%p\n", - &req_mem_cc_regs->start, drvdata->cc_base); - /* Then IRQ */ irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "Failed getting IRQ resource\n"); + if (irq < 0) return irq; - } /* parse sampling rate from device tree */ rc = cc_trng_parse_sampling_ratio(drvdata); @@ -585,7 +573,7 @@ static int cctrng_probe(struct platform_device *pdev) atomic_set(&drvdata->pending_hw, 1); /* registration of the hwrng device */ - rc = hwrng_register(&drvdata->rng); + rc = devm_hwrng_register(dev, &drvdata->rng); if (rc) { dev_err(dev, "Could not register hwrng device.\n"); goto post_pm_err; @@ -618,8 +606,6 @@ static int cctrng_remove(struct platform_device *pdev) dev_dbg(dev, "Releasing cctrng resources...\n"); - hwrng_unregister(&drvdata->rng); - cc_trng_pm_fini(drvdata); cc_trng_clk_fini(drvdata); diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c index 8c1c47dd9f46..adb3c2bd7783 100644 --- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -396,7 +396,7 @@ static ssize_t hwrng_attr_selected_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE, "%d\n", cur_rng_set_by_user); + return sysfs_emit(buf, "%d\n", cur_rng_set_by_user); } static DEVICE_ATTR(rng_current, S_IRUGO | S_IWUSR, diff --git a/drivers/char/hw_random/intel-rng.c b/drivers/char/hw_random/intel-rng.c index eb7db27f9f19..d740b8814bf3 100644 --- a/drivers/char/hw_random/intel-rng.c +++ b/drivers/char/hw_random/intel-rng.c @@ -25,13 +25,13 @@ */ #include <linux/hw_random.h> +#include <linux/io.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/stop_machine.h> #include <linux/delay.h> #include <linux/slab.h> -#include <asm/io.h> #define PFX KBUILD_MODNAME ": " diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c index 5cc5fc504968..cede9f159102 100644 --- a/drivers/char/hw_random/omap-rng.c +++ b/drivers/char/hw_random/omap-rng.c @@ -30,8 +30,7 @@ #include <linux/of_address.h> #include <linux/interrupt.h> #include <linux/clk.h> - -#include <asm/io.h> +#include <linux/io.h> #define RNG_REG_STATUS_RDY (1 << 0) @@ -378,16 +377,13 @@ MODULE_DEVICE_TABLE(of, omap_rng_of_match); static int of_get_omap_rng_device_details(struct omap_rng_dev *priv, struct platform_device *pdev) { - const struct of_device_id *match; struct device *dev = &pdev->dev; int irq, err; - match = of_match_device(of_match_ptr(omap_rng_of_match), dev); - if (!match) { - dev_err(dev, "no compatible OF match\n"); - return -EINVAL; - } - priv->pdata = match->data; + priv->pdata = of_device_get_match_data(dev); + if (!priv->pdata) + return -ENODEV; + if (of_device_is_compatible(dev->of_node, "ti,omap4-rng") || of_device_is_compatible(dev->of_node, "inside-secure,safexcel-eip76")) { diff --git a/drivers/char/hw_random/pic32-rng.c b/drivers/char/hw_random/pic32-rng.c index e8210c1715cf..99c8bd0859a1 100644 --- a/drivers/char/hw_random/pic32-rng.c +++ b/drivers/char/hw_random/pic32-rng.c @@ -96,7 +96,7 @@ static int pic32_rng_probe(struct platform_device *pdev) priv->rng.name = pdev->name; priv->rng.read = pic32_rng_read; - ret = hwrng_register(&priv->rng); + ret = devm_hwrng_register(&pdev->dev, &priv->rng); if (ret) goto err_register; @@ -113,7 +113,6 @@ static int pic32_rng_remove(struct platform_device *pdev) { struct pic32_rng *rng = platform_get_drvdata(pdev); - hwrng_unregister(&rng->rng); writel(0, rng->base + RNGCON); clk_disable_unprepare(rng->clk); return 0; diff --git a/drivers/char/hw_random/xiphera-trng.c b/drivers/char/hw_random/xiphera-trng.c index 7bdab8c8a6a8..2a9fea72b2e0 100644 --- a/drivers/char/hw_random/xiphera-trng.c +++ b/drivers/char/hw_random/xiphera-trng.c @@ -63,14 +63,12 @@ static int xiphera_trng_probe(struct platform_device *pdev) int ret; struct xiphera_trng *trng; struct device *dev = &pdev->dev; - struct resource *res; trng = devm_kzalloc(dev, sizeof(*trng), GFP_KERNEL); if (!trng) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - trng->mem = devm_ioremap_resource(dev, res); + trng->mem = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(trng->mem)) return PTR_ERR(trng->mem); diff --git a/drivers/char/random.c b/drivers/char/random.c index 0fe9e200e4c8..605969ed0f96 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -500,7 +500,6 @@ struct entropy_store { unsigned short add_ptr; unsigned short input_rotate; int entropy_count; - unsigned int initialized:1; unsigned int last_data_init:1; __u8 last_data[EXTRACT_SIZE]; }; @@ -660,7 +659,7 @@ static void process_random_ready_list(void) */ static void credit_entropy_bits(struct entropy_store *r, int nbits) { - int entropy_count, orig, has_initialized = 0; + int entropy_count, orig; const int pool_size = r->poolinfo->poolfracbits; int nfrac = nbits << ENTROPY_SHIFT; @@ -717,23 +716,14 @@ retry: if (cmpxchg(&r->entropy_count, orig, entropy_count) != orig) goto retry; - if (has_initialized) { - r->initialized = 1; - kill_fasync(&fasync, SIGIO, POLL_IN); - } - trace_credit_entropy_bits(r->name, nbits, entropy_count >> ENTROPY_SHIFT, _RET_IP_); if (r == &input_pool) { int entropy_bits = entropy_count >> ENTROPY_SHIFT; - if (crng_init < 2) { - if (entropy_bits < 128) - return; + if (crng_init < 2 && entropy_bits >= 128) crng_reseed(&primary_crng, r); - entropy_bits = ENTROPY_BITS(r); - } } } @@ -819,7 +809,7 @@ static bool __init crng_init_try_arch_early(struct crng_state *crng) static void __maybe_unused crng_initialize_secondary(struct crng_state *crng) { - memcpy(&crng->state[0], "expand 32-byte k", 16); + chacha_init_consts(crng->state); _get_random_bytes(&crng->state[4], sizeof(__u32) * 12); crng_init_try_arch(crng); crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1; @@ -827,7 +817,7 @@ static void __maybe_unused crng_initialize_secondary(struct crng_state *crng) static void __init crng_initialize_primary(struct crng_state *crng) { - memcpy(&crng->state[0], "expand 32-byte k", 16); + chacha_init_consts(crng->state); _extract_entropy(&input_pool, &crng->state[4], sizeof(__u32) * 12, 0); if (crng_init_try_arch_early(crng) && trust_cpu) { invalidate_batched_entropy(); @@ -1372,8 +1362,7 @@ retry: } /* - * This function does the actual extraction for extract_entropy and - * extract_entropy_user. + * This function does the actual extraction for extract_entropy. * * Note: we assume that .poolwords is a multiple of 16 words. */ diff --git a/drivers/char/tpm/eventlog/acpi.c b/drivers/char/tpm/eventlog/acpi.c index 3633ed70f48f..1b18ce5ebab1 100644 --- a/drivers/char/tpm/eventlog/acpi.c +++ b/drivers/char/tpm/eventlog/acpi.c @@ -41,6 +41,27 @@ struct acpi_tcpa { }; }; +/* Check that the given log is indeed a TPM2 log. */ +static bool tpm_is_tpm2_log(void *bios_event_log, u64 len) +{ + struct tcg_efi_specid_event_head *efispecid; + struct tcg_pcr_event *event_header; + int n; + + if (len < sizeof(*event_header)) + return false; + len -= sizeof(*event_header); + event_header = bios_event_log; + + if (len < sizeof(*efispecid)) + return false; + efispecid = (struct tcg_efi_specid_event_head *)event_header->event; + + n = memcmp(efispecid->signature, TCG_SPECID_SIG, + sizeof(TCG_SPECID_SIG)); + return n == 0; +} + /* read binary bios log */ int tpm_read_log_acpi(struct tpm_chip *chip) { @@ -52,6 +73,7 @@ int tpm_read_log_acpi(struct tpm_chip *chip) struct acpi_table_tpm2 *tbl; struct acpi_tpm2_phy *tpm2_phy; int format; + int ret; log = &chip->log; @@ -112,6 +134,7 @@ int tpm_read_log_acpi(struct tpm_chip *chip) log->bios_event_log_end = log->bios_event_log + len; + ret = -EIO; virt = acpi_os_map_iomem(start, len); if (!virt) goto err; @@ -119,11 +142,19 @@ int tpm_read_log_acpi(struct tpm_chip *chip) memcpy_fromio(log->bios_event_log, virt, len); acpi_os_unmap_iomem(virt, len); + + if (chip->flags & TPM_CHIP_FLAG_TPM2 && + !tpm_is_tpm2_log(log->bios_event_log, len)) { + /* try EFI log next */ + ret = -ENODEV; + goto err; + } + return format; err: kfree(log->bios_event_log); log->bios_event_log = NULL; - return -EIO; + return ret; } diff --git a/drivers/char/tpm/eventlog/common.c b/drivers/char/tpm/eventlog/common.c index 7460f230bae4..8512ec76d526 100644 --- a/drivers/char/tpm/eventlog/common.c +++ b/drivers/char/tpm/eventlog/common.c @@ -107,6 +107,9 @@ void tpm_bios_log_setup(struct tpm_chip *chip) int log_version; int rc = 0; + if (chip->flags & TPM_CHIP_FLAG_VIRTUAL) + return; + rc = tpm_read_log(chip); if (rc < 0) return; diff --git a/drivers/char/tpm/eventlog/efi.c b/drivers/char/tpm/eventlog/efi.c index 35229e5143ca..e6cb9d525e30 100644 --- a/drivers/char/tpm/eventlog/efi.c +++ b/drivers/char/tpm/eventlog/efi.c @@ -17,6 +17,7 @@ int tpm_read_log_efi(struct tpm_chip *chip) { struct efi_tcg2_final_events_table *final_tbl = NULL; + int final_events_log_size = efi_tpm_final_log_size; struct linux_efi_tpm_eventlog *log_tbl; struct tpm_bios_log *log; u32 log_size; @@ -66,12 +67,12 @@ int tpm_read_log_efi(struct tpm_chip *chip) ret = tpm_log_version; if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR || - efi_tpm_final_log_size == 0 || + final_events_log_size == 0 || tpm_log_version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) goto out; final_tbl = memremap(efi.tpm_final_log, - sizeof(*final_tbl) + efi_tpm_final_log_size, + sizeof(*final_tbl) + final_events_log_size, MEMREMAP_WB); if (!final_tbl) { pr_err("Could not map UEFI TPM final log\n"); @@ -80,10 +81,18 @@ int tpm_read_log_efi(struct tpm_chip *chip) goto out; } - efi_tpm_final_log_size -= log_tbl->final_events_preboot_size; + /* + * The 'final events log' size excludes the 'final events preboot log' + * at its beginning. + */ + final_events_log_size -= log_tbl->final_events_preboot_size; + /* + * Allocate memory for the 'combined log' where we will append the + * 'final events log' to. + */ tmp = krealloc(log->bios_event_log, - log_size + efi_tpm_final_log_size, + log_size + final_events_log_size, GFP_KERNEL); if (!tmp) { kfree(log->bios_event_log); @@ -94,15 +103,19 @@ int tpm_read_log_efi(struct tpm_chip *chip) log->bios_event_log = tmp; /* - * Copy any of the final events log that didn't also end up in the - * main log. Events can be logged in both if events are generated + * Append any of the 'final events log' that didn't also end up in the + * 'main log'. Events can be logged in both if events are generated * between GetEventLog() and ExitBootServices(). */ memcpy((void *)log->bios_event_log + log_size, final_tbl->events + log_tbl->final_events_preboot_size, - efi_tpm_final_log_size); + final_events_log_size); + /* + * The size of the 'combined log' is the size of the 'main log' plus + * the size of the 'final events log'. + */ log->bios_event_log_end = log->bios_event_log + - log_size + efi_tpm_final_log_size; + log_size + final_events_log_size; out: memunmap(final_tbl); diff --git a/drivers/char/tpm/tpm_tis_i2c_cr50.c b/drivers/char/tpm/tpm_tis_i2c_cr50.c index ec9a65e7887d..f19c227d20f4 100644 --- a/drivers/char/tpm/tpm_tis_i2c_cr50.c +++ b/drivers/char/tpm/tpm_tis_i2c_cr50.c @@ -483,6 +483,7 @@ static int tpm_cr50_i2c_tis_recv(struct tpm_chip *chip, u8 *buf, size_t buf_len) expected = be32_to_cpup((__be32 *)(buf + 2)); if (expected > buf_len) { dev_err(&chip->dev, "Buffer too small to receive i2c data\n"); + rc = -E2BIG; goto out_err; } diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c index 4f7bf3929d6d..4e4b6d367612 100644 --- a/drivers/clk/clk-fixed-factor.c +++ b/drivers/clk/clk-fixed-factor.c @@ -66,7 +66,14 @@ EXPORT_SYMBOL_GPL(clk_fixed_factor_ops); static void devm_clk_hw_register_fixed_factor_release(struct device *dev, void *res) { - clk_hw_unregister_fixed_factor(&((struct clk_fixed_factor *)res)->hw); + struct clk_fixed_factor *fix = res; + + /* + * We can not use clk_hw_unregister_fixed_factor, since it will kfree() + * the hw, resulting in double free. Just unregister the hw and let + * devres code kfree() it. + */ + clk_hw_unregister(&fix->hw); } static struct clk_hw * diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 5052541a0986..39cfc6c6a8d2 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -4357,20 +4357,19 @@ int clk_notifier_register(struct clk *clk, struct notifier_block *nb) /* search the list of notifiers for this clk */ list_for_each_entry(cn, &clk_notifier_list, node) if (cn->clk == clk) - break; + goto found; /* if clk wasn't in the notifier list, allocate new clk_notifier */ - if (cn->clk != clk) { - cn = kzalloc(sizeof(*cn), GFP_KERNEL); - if (!cn) - goto out; + cn = kzalloc(sizeof(*cn), GFP_KERNEL); + if (!cn) + goto out; - cn->clk = clk; - srcu_init_notifier_head(&cn->notifier_head); + cn->clk = clk; + srcu_init_notifier_head(&cn->notifier_head); - list_add(&cn->node, &clk_notifier_list); - } + list_add(&cn->node, &clk_notifier_list); +found: ret = srcu_notifier_chain_register(&cn->notifier_head, nb); clk->core->notifier_count++; @@ -4395,32 +4394,28 @@ EXPORT_SYMBOL_GPL(clk_notifier_register); */ int clk_notifier_unregister(struct clk *clk, struct notifier_block *nb) { - struct clk_notifier *cn = NULL; - int ret = -EINVAL; + struct clk_notifier *cn; + int ret = -ENOENT; if (!clk || !nb) return -EINVAL; clk_prepare_lock(); - list_for_each_entry(cn, &clk_notifier_list, node) - if (cn->clk == clk) - break; - - if (cn->clk == clk) { - ret = srcu_notifier_chain_unregister(&cn->notifier_head, nb); + list_for_each_entry(cn, &clk_notifier_list, node) { + if (cn->clk == clk) { + ret = srcu_notifier_chain_unregister(&cn->notifier_head, nb); - clk->core->notifier_count--; + clk->core->notifier_count--; - /* XXX the notifier code should handle this better */ - if (!cn->notifier_head.head) { - srcu_cleanup_notifier_head(&cn->notifier_head); - list_del(&cn->node); - kfree(cn); + /* XXX the notifier code should handle this better */ + if (!cn->notifier_head.head) { + srcu_cleanup_notifier_head(&cn->notifier_head); + list_del(&cn->node); + kfree(cn); + } + break; } - - } else { - ret = -ENOENT; } clk_prepare_unlock(); diff --git a/drivers/clk/qcom/camcc-sc7180.c b/drivers/clk/qcom/camcc-sc7180.c index dbac5651ab85..9bcf2f8ed4de 100644 --- a/drivers/clk/qcom/camcc-sc7180.c +++ b/drivers/clk/qcom/camcc-sc7180.c @@ -304,7 +304,7 @@ static struct clk_rcg2 cam_cc_bps_clk_src = { .name = "cam_cc_bps_clk_src", .parent_data = cam_cc_parent_data_2, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -325,7 +325,7 @@ static struct clk_rcg2 cam_cc_cci_0_clk_src = { .name = "cam_cc_cci_0_clk_src", .parent_data = cam_cc_parent_data_5, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -339,7 +339,7 @@ static struct clk_rcg2 cam_cc_cci_1_clk_src = { .name = "cam_cc_cci_1_clk_src", .parent_data = cam_cc_parent_data_5, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -360,7 +360,7 @@ static struct clk_rcg2 cam_cc_cphy_rx_clk_src = { .name = "cam_cc_cphy_rx_clk_src", .parent_data = cam_cc_parent_data_3, .num_parents = 6, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -379,7 +379,7 @@ static struct clk_rcg2 cam_cc_csi0phytimer_clk_src = { .name = "cam_cc_csi0phytimer_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -393,7 +393,7 @@ static struct clk_rcg2 cam_cc_csi1phytimer_clk_src = { .name = "cam_cc_csi1phytimer_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -407,7 +407,7 @@ static struct clk_rcg2 cam_cc_csi2phytimer_clk_src = { .name = "cam_cc_csi2phytimer_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -421,7 +421,7 @@ static struct clk_rcg2 cam_cc_csi3phytimer_clk_src = { .name = "cam_cc_csi3phytimer_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -443,7 +443,7 @@ static struct clk_rcg2 cam_cc_fast_ahb_clk_src = { .name = "cam_cc_fast_ahb_clk_src", .parent_data = cam_cc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -466,7 +466,7 @@ static struct clk_rcg2 cam_cc_icp_clk_src = { .name = "cam_cc_icp_clk_src", .parent_data = cam_cc_parent_data_2, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -488,7 +488,7 @@ static struct clk_rcg2 cam_cc_ife_0_clk_src = { .name = "cam_cc_ife_0_clk_src", .parent_data = cam_cc_parent_data_4, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -510,7 +510,7 @@ static struct clk_rcg2 cam_cc_ife_0_csid_clk_src = { .name = "cam_cc_ife_0_csid_clk_src", .parent_data = cam_cc_parent_data_3, .num_parents = 6, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -524,7 +524,7 @@ static struct clk_rcg2 cam_cc_ife_1_clk_src = { .name = "cam_cc_ife_1_clk_src", .parent_data = cam_cc_parent_data_4, .num_parents = 4, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -538,7 +538,7 @@ static struct clk_rcg2 cam_cc_ife_1_csid_clk_src = { .name = "cam_cc_ife_1_csid_clk_src", .parent_data = cam_cc_parent_data_3, .num_parents = 6, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -553,7 +553,7 @@ static struct clk_rcg2 cam_cc_ife_lite_clk_src = { .parent_data = cam_cc_parent_data_4, .num_parents = 4, .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -567,7 +567,7 @@ static struct clk_rcg2 cam_cc_ife_lite_csid_clk_src = { .name = "cam_cc_ife_lite_csid_clk_src", .parent_data = cam_cc_parent_data_3, .num_parents = 6, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -590,7 +590,7 @@ static struct clk_rcg2 cam_cc_ipe_0_clk_src = { .name = "cam_cc_ipe_0_clk_src", .parent_data = cam_cc_parent_data_2, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -613,7 +613,7 @@ static struct clk_rcg2 cam_cc_jpeg_clk_src = { .name = "cam_cc_jpeg_clk_src", .parent_data = cam_cc_parent_data_2, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -635,7 +635,7 @@ static struct clk_rcg2 cam_cc_lrme_clk_src = { .name = "cam_cc_lrme_clk_src", .parent_data = cam_cc_parent_data_6, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -656,7 +656,7 @@ static struct clk_rcg2 cam_cc_mclk0_clk_src = { .name = "cam_cc_mclk0_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -670,7 +670,7 @@ static struct clk_rcg2 cam_cc_mclk1_clk_src = { .name = "cam_cc_mclk1_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -684,7 +684,7 @@ static struct clk_rcg2 cam_cc_mclk2_clk_src = { .name = "cam_cc_mclk2_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -698,7 +698,7 @@ static struct clk_rcg2 cam_cc_mclk3_clk_src = { .name = "cam_cc_mclk3_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -712,7 +712,7 @@ static struct clk_rcg2 cam_cc_mclk4_clk_src = { .name = "cam_cc_mclk4_clk_src", .parent_data = cam_cc_parent_data_1, .num_parents = 3, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -732,7 +732,7 @@ static struct clk_rcg2 cam_cc_slow_ahb_clk_src = { .parent_data = cam_cc_parent_data_0, .num_parents = 4, .flags = CLK_SET_RATE_PARENT | CLK_OPS_PARENT_ENABLE, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index 42f13a2d1cc1..05ff3b0d233e 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -730,7 +730,8 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, struct clk_rate_request parent_req = { }; struct clk_rcg2_gfx3d *cgfx = to_clk_rcg2_gfx3d(hw); struct clk_hw *xo, *p0, *p1, *p2; - unsigned long request, p0_rate; + unsigned long p0_rate; + u8 mux_div = cgfx->div; int ret; p0 = cgfx->hws[0]; @@ -750,14 +751,15 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, return 0; } - request = req->rate; - if (cgfx->div > 1) - parent_req.rate = request = request * cgfx->div; + if (mux_div == 0) + mux_div = 1; + + parent_req.rate = req->rate * mux_div; /* This has to be a fixed rate PLL */ p0_rate = clk_hw_get_rate(p0); - if (request == p0_rate) { + if (parent_req.rate == p0_rate) { req->rate = req->best_parent_rate = p0_rate; req->best_parent_hw = p0; return 0; @@ -765,7 +767,7 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, if (req->best_parent_hw == p0) { /* Are we going back to a previously used rate? */ - if (clk_hw_get_rate(p2) == request) + if (clk_hw_get_rate(p2) == parent_req.rate) req->best_parent_hw = p2; else req->best_parent_hw = p1; @@ -780,8 +782,7 @@ static int clk_gfx3d_determine_rate(struct clk_hw *hw, return ret; req->rate = req->best_parent_rate = parent_req.rate; - if (cgfx->div > 1) - req->rate /= cgfx->div; + req->rate /= mux_div; return 0; } diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c index 91dc390a583b..c623ce900406 100644 --- a/drivers/clk/qcom/clk-rpmh.c +++ b/drivers/clk/qcom/clk-rpmh.c @@ -510,9 +510,12 @@ static const struct clk_rpmh_desc clk_rpmh_sm8350 = { .num_clks = ARRAY_SIZE(sm8350_rpmh_clocks), }; +/* Resource name must match resource id present in cmd-db */ +DEFINE_CLK_RPMH_ARC(sc7280, bi_tcxo, bi_tcxo_ao, "xo.lvl", 0x3, 4); + static struct clk_hw *sc7280_rpmh_clocks[] = { - [RPMH_CXO_CLK] = &sdm845_bi_tcxo.hw, - [RPMH_CXO_CLK_A] = &sdm845_bi_tcxo_ao.hw, + [RPMH_CXO_CLK] = &sc7280_bi_tcxo.hw, + [RPMH_CXO_CLK_A] = &sc7280_bi_tcxo_ao.hw, [RPMH_LN_BB_CLK2] = &sdm845_ln_bb_clk2.hw, [RPMH_LN_BB_CLK2_A] = &sdm845_ln_bb_clk2_ao.hw, [RPMH_RF_CLK1] = &sdm845_rf_clk1.hw, diff --git a/drivers/clk/qcom/gcc-sc7180.c b/drivers/clk/qcom/gcc-sc7180.c index 88e896abb663..da8b627ca156 100644 --- a/drivers/clk/qcom/gcc-sc7180.c +++ b/drivers/clk/qcom/gcc-sc7180.c @@ -620,7 +620,7 @@ static struct clk_rcg2 gcc_sdcc1_apps_clk_src = { .name = "gcc_sdcc1_apps_clk_src", .parent_data = gcc_parent_data_1, .num_parents = 5, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_floor_ops, }, }; @@ -642,7 +642,7 @@ static struct clk_rcg2 gcc_sdcc1_ice_core_clk_src = { .name = "gcc_sdcc1_ice_core_clk_src", .parent_data = gcc_parent_data_0, .num_parents = 4, - .ops = &clk_rcg2_floor_ops, + .ops = &clk_rcg2_ops, }, }; diff --git a/drivers/clk/socfpga/clk-gate.c b/drivers/clk/socfpga/clk-gate.c index 43ecd507bf83..cf94a12459ea 100644 --- a/drivers/clk/socfpga/clk-gate.c +++ b/drivers/clk/socfpga/clk-gate.c @@ -99,7 +99,7 @@ static unsigned long socfpga_clk_recalc_rate(struct clk_hw *hwclk, val = readl(socfpgaclk->div_reg) >> socfpgaclk->shift; val &= GENMASK(socfpgaclk->width - 1, 0); /* Check for GPIO_DB_CLK by its offset */ - if ((int) socfpgaclk->div_reg & SOCFPGA_GPIO_DB_CLK_OFFSET) + if ((uintptr_t) socfpgaclk->div_reg & SOCFPGA_GPIO_DB_CLK_OFFSET) div = val + 1; else div = (1 << val); diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c index d3f756f7b5a0..67e56cf638ef 100644 --- a/drivers/cpufreq/freq_table.c +++ b/drivers/cpufreq/freq_table.c @@ -267,7 +267,7 @@ struct freq_attr cpufreq_freq_attr_##_name##_freqs = \ __ATTR_RO(_name##_frequencies) /* - * show_scaling_available_frequencies - show available normal frequencies for + * scaling_available_frequencies_show - show available normal frequencies for * the specified CPU */ static ssize_t scaling_available_frequencies_show(struct cpufreq_policy *policy, @@ -279,7 +279,7 @@ cpufreq_attr_available_freq(scaling_available); EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs); /* - * show_available_boost_freqs - show available boost frequencies for + * scaling_boost_frequencies_show - show available boost frequencies for * the specified CPU */ static ssize_t scaling_boost_frequencies_show(struct cpufreq_policy *policy, diff --git a/drivers/crypto/allwinner/Kconfig b/drivers/crypto/allwinner/Kconfig index 856fb2045656..b8e75210a0e3 100644 --- a/drivers/crypto/allwinner/Kconfig +++ b/drivers/crypto/allwinner/Kconfig @@ -71,10 +71,10 @@ config CRYPTO_DEV_SUN8I_CE_DEBUG config CRYPTO_DEV_SUN8I_CE_HASH bool "Enable support for hash on sun8i-ce" depends on CRYPTO_DEV_SUN8I_CE - select MD5 - select SHA1 - select SHA256 - select SHA512 + select CRYPTO_MD5 + select CRYPTO_SHA1 + select CRYPTO_SHA256 + select CRYPTO_SHA512 help Say y to enable support for hash algorithms. @@ -132,8 +132,8 @@ config CRYPTO_DEV_SUN8I_SS_PRNG config CRYPTO_DEV_SUN8I_SS_HASH bool "Enable support for hash on sun8i-ss" depends on CRYPTO_DEV_SUN8I_SS - select MD5 - select SHA1 - select SHA256 + select CRYPTO_MD5 + select CRYPTO_SHA1 + select CRYPTO_SHA256 help Say y to enable support for hash algorithms. diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c index c2e6f5ed1d79..dec79fa3ebaf 100644 --- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c +++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-cipher.c @@ -561,7 +561,7 @@ int sun4i_ss_cipher_init(struct crypto_tfm *tfm) sizeof(struct sun4i_cipher_req_ctx) + crypto_skcipher_reqsize(op->fallback_tfm)); - err = pm_runtime_get_sync(op->ss->dev); + err = pm_runtime_resume_and_get(op->ss->dev); if (err < 0) goto error_pm; diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c index 709905ec4680..44b8fc4b786d 100644 --- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c +++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-core.c @@ -288,8 +288,7 @@ static int sun4i_ss_pm_suspend(struct device *dev) { struct sun4i_ss_ctx *ss = dev_get_drvdata(dev); - if (ss->reset) - reset_control_assert(ss->reset); + reset_control_assert(ss->reset); clk_disable_unprepare(ss->ssclk); clk_disable_unprepare(ss->busclk); @@ -314,12 +313,10 @@ static int sun4i_ss_pm_resume(struct device *dev) goto err_enable; } - if (ss->reset) { - err = reset_control_deassert(ss->reset); - if (err) { - dev_err(ss->dev, "Cannot deassert reset control\n"); - goto err_enable; - } + err = reset_control_deassert(ss->reset); + if (err) { + dev_err(ss->dev, "Cannot deassert reset control\n"); + goto err_enable; } return err; @@ -401,12 +398,10 @@ static int sun4i_ss_probe(struct platform_device *pdev) dev_dbg(&pdev->dev, "clock ahb_ss acquired\n"); ss->reset = devm_reset_control_get_optional(&pdev->dev, "ahb"); - if (IS_ERR(ss->reset)) { - if (PTR_ERR(ss->reset) == -EPROBE_DEFER) - return PTR_ERR(ss->reset); + if (IS_ERR(ss->reset)) + return PTR_ERR(ss->reset); + if (!ss->reset) dev_info(&pdev->dev, "no reset control found\n"); - ss->reset = NULL; - } /* * Check that clock have the correct rates given in the datasheet @@ -459,7 +454,7 @@ static int sun4i_ss_probe(struct platform_device *pdev) * this info could be useful */ - err = pm_runtime_get_sync(ss->dev); + err = pm_runtime_resume_and_get(ss->dev); if (err < 0) goto error_pm; diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c index c1b4585e9bbc..d28292762b32 100644 --- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c +++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-hash.c @@ -27,7 +27,7 @@ int sun4i_hash_crainit(struct crypto_tfm *tfm) algt = container_of(alg, struct sun4i_ss_alg_template, alg.hash); op->ss = algt->ss; - err = pm_runtime_get_sync(op->ss->dev); + err = pm_runtime_resume_and_get(op->ss->dev); if (err < 0) return err; diff --git a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c index 443160a114bb..491fcb7b81b4 100644 --- a/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c +++ b/drivers/crypto/allwinner/sun4i-ss/sun4i-ss-prng.c @@ -29,7 +29,7 @@ int sun4i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, algt = container_of(alg, struct sun4i_ss_alg_template, alg.rng); ss = algt->ss; - err = pm_runtime_get_sync(ss->dev); + err = pm_runtime_resume_and_get(ss->dev); if (err < 0) return err; diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c index 33707a2e55ff..54ae8d16e493 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-cipher.c @@ -240,11 +240,14 @@ static int sun8i_ce_cipher_prepare(struct crypto_engine *engine, void *async_req theend_sgs: if (areq->src == areq->dst) { - dma_unmap_sg(ce->dev, areq->src, nr_sgs, DMA_BIDIRECTIONAL); + dma_unmap_sg(ce->dev, areq->src, sg_nents(areq->src), + DMA_BIDIRECTIONAL); } else { if (nr_sgs > 0) - dma_unmap_sg(ce->dev, areq->src, nr_sgs, DMA_TO_DEVICE); - dma_unmap_sg(ce->dev, areq->dst, nr_sgd, DMA_FROM_DEVICE); + dma_unmap_sg(ce->dev, areq->src, sg_nents(areq->src), + DMA_TO_DEVICE); + dma_unmap_sg(ce->dev, areq->dst, sg_nents(areq->dst), + DMA_FROM_DEVICE); } theend_iv: diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c index 158422ff5695..00194d1d9ae6 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-core.c @@ -932,7 +932,7 @@ static int sun8i_ce_probe(struct platform_device *pdev) if (err) goto error_alg; - err = pm_runtime_get_sync(ce->dev); + err = pm_runtime_resume_and_get(ce->dev); if (err < 0) goto error_alg; diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c index 2f09a37306e2..88194718a806 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-hash.c @@ -405,7 +405,8 @@ int sun8i_ce_hash_run(struct crypto_engine *engine, void *breq) err = sun8i_ce_run_task(ce, flow, crypto_tfm_alg_name(areq->base.tfm)); dma_unmap_single(ce->dev, addr_pad, j * 4, DMA_TO_DEVICE); - dma_unmap_sg(ce->dev, areq->src, nr_sgs, DMA_TO_DEVICE); + dma_unmap_sg(ce->dev, areq->src, sg_nents(areq->src), + DMA_TO_DEVICE); dma_unmap_single(ce->dev, addr_res, digestsize, DMA_FROM_DEVICE); diff --git a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c index cfde9ee4356b..cd1baee424a1 100644 --- a/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c +++ b/drivers/crypto/allwinner/sun8i-ce/sun8i-ce-prng.c @@ -99,6 +99,7 @@ int sun8i_ce_prng_generate(struct crypto_rng *tfm, const u8 *src, dma_iv = dma_map_single(ce->dev, ctx->seed, ctx->slen, DMA_TO_DEVICE); if (dma_mapping_error(ce->dev, dma_iv)) { dev_err(ce->dev, "Cannot DMA MAP IV\n"); + err = -EFAULT; goto err_iv; } diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c index ed2a69f82e1c..9ef1c85c4aaa 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-cipher.c @@ -232,10 +232,13 @@ sgd_next: theend_sgs: if (areq->src == areq->dst) { - dma_unmap_sg(ss->dev, areq->src, nr_sgs, DMA_BIDIRECTIONAL); + dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src), + DMA_BIDIRECTIONAL); } else { - dma_unmap_sg(ss->dev, areq->src, nr_sgs, DMA_TO_DEVICE); - dma_unmap_sg(ss->dev, areq->dst, nr_sgd, DMA_FROM_DEVICE); + dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src), + DMA_TO_DEVICE); + dma_unmap_sg(ss->dev, areq->dst, sg_nents(areq->dst), + DMA_FROM_DEVICE); } theend_iv: @@ -351,7 +354,7 @@ int sun8i_ss_cipher_init(struct crypto_tfm *tfm) op->enginectx.op.prepare_request = NULL; op->enginectx.op.unprepare_request = NULL; - err = pm_runtime_get_sync(op->ss->dev); + err = pm_runtime_resume_and_get(op->ss->dev); if (err < 0) { dev_err(op->ss->dev, "pm error %d\n", err); goto error_pm; diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c index e0ddc684798d..80e89066dbd1 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-core.c @@ -753,7 +753,7 @@ static int sun8i_ss_probe(struct platform_device *pdev) if (err) goto error_alg; - err = pm_runtime_get_sync(ss->dev); + err = pm_runtime_resume_and_get(ss->dev); if (err < 0) goto error_alg; diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c index 11cbcbc83a7b..3c073eb3db03 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-hash.c @@ -348,8 +348,10 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq) bf = (__le32 *)pad; result = kzalloc(digestsize, GFP_KERNEL | GFP_DMA); - if (!result) + if (!result) { + kfree(pad); return -ENOMEM; + } for (i = 0; i < MAX_SG; i++) { rctx->t_dst[i].addr = 0; @@ -432,14 +434,14 @@ int sun8i_ss_hash_run(struct crypto_engine *engine, void *breq) err = sun8i_ss_run_hash_task(ss, rctx, crypto_tfm_alg_name(areq->base.tfm)); dma_unmap_single(ss->dev, addr_pad, j * 4, DMA_TO_DEVICE); - dma_unmap_sg(ss->dev, areq->src, nr_sgs, DMA_TO_DEVICE); + dma_unmap_sg(ss->dev, areq->src, sg_nents(areq->src), + DMA_TO_DEVICE); dma_unmap_single(ss->dev, addr_res, digestsize, DMA_FROM_DEVICE); - kfree(pad); - memcpy(areq->result, result, algt->alg.hash.halg.digestsize); - kfree(result); theend: + kfree(pad); + kfree(result); crypto_finalize_hash_request(engine, breq, err); return 0; } diff --git a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c index 08a1473b2145..3191527928e4 100644 --- a/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c +++ b/drivers/crypto/allwinner/sun8i-ss/sun8i-ss-prng.c @@ -103,7 +103,8 @@ int sun8i_ss_prng_generate(struct crypto_rng *tfm, const u8 *src, dma_iv = dma_map_single(ss->dev, ctx->seed, ctx->slen, DMA_TO_DEVICE); if (dma_mapping_error(ss->dev, dma_iv)) { dev_err(ss->dev, "Cannot DMA MAP IV\n"); - return -EFAULT; + err = -EFAULT; + goto err_free; } dma_dst = dma_map_single(ss->dev, d, todo, DMA_FROM_DEVICE); @@ -167,6 +168,7 @@ err_iv: memcpy(ctx->seed, d + dlen, ctx->slen); } memzero_explicit(d, todo); +err_free: kfree(d); return err; diff --git a/drivers/crypto/amcc/crypto4xx_alg.c b/drivers/crypto/amcc/crypto4xx_alg.c index a3fa849b139a..ded732242732 100644 --- a/drivers/crypto/amcc/crypto4xx_alg.c +++ b/drivers/crypto/amcc/crypto4xx_alg.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/** +/* * AMCC SoC PPC4xx Crypto Driver * * Copyright (c) 2008 Applied Micro Circuits Corporation. @@ -115,7 +115,7 @@ int crypto4xx_decrypt_iv_block(struct skcipher_request *req) return crypto4xx_crypt(req, AES_IV_SIZE, true, true); } -/** +/* * AES Functions */ static int crypto4xx_setkey_aes(struct crypto_skcipher *cipher, @@ -374,7 +374,7 @@ static int crypto4xx_aead_setup_fallback(struct crypto4xx_ctx *ctx, return crypto_aead_setkey(ctx->sw_cipher.aead, key, keylen); } -/** +/* * AES-CCM Functions */ @@ -489,7 +489,7 @@ int crypto4xx_setauthsize_aead(struct crypto_aead *cipher, return crypto_aead_setauthsize(ctx->sw_cipher.aead, authsize); } -/** +/* * AES-GCM Functions */ @@ -617,7 +617,7 @@ int crypto4xx_decrypt_aes_gcm(struct aead_request *req) return crypto4xx_crypt_aes_gcm(req, true); } -/** +/* * HASH SHA1 Functions */ static int crypto4xx_hash_alg_init(struct crypto_tfm *tfm, @@ -711,7 +711,7 @@ int crypto4xx_hash_digest(struct ahash_request *req) ctx->sa_len, 0, NULL); } -/** +/* * SHA1 Algorithm */ int crypto4xx_sha1_alg_init(struct crypto_tfm *tfm) diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c index 8d1b918a0533..8278d98074e9 100644 --- a/drivers/crypto/amcc/crypto4xx_core.c +++ b/drivers/crypto/amcc/crypto4xx_core.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/** +/* * AMCC SoC PPC4xx Crypto Driver * * Copyright (c) 2008 Applied Micro Circuits Corporation. @@ -44,7 +44,7 @@ #define PPC4XX_SEC_VERSION_STR "0.5" -/** +/* * PPC4xx Crypto Engine Initialization Routine */ static void crypto4xx_hw_init(struct crypto4xx_device *dev) @@ -159,7 +159,7 @@ void crypto4xx_free_sa(struct crypto4xx_ctx *ctx) ctx->sa_len = 0; } -/** +/* * alloc memory for the gather ring * no need to alloc buf for the ring * gdr_tail, gdr_head and gdr_count are initialized by this function @@ -268,7 +268,7 @@ static u32 crypto4xx_put_pd_to_pdr(struct crypto4xx_device *dev, u32 idx) return tail; } -/** +/* * alloc memory for the gather ring * no need to alloc buf for the ring * gdr_tail, gdr_head and gdr_count are initialized by this function @@ -346,7 +346,7 @@ static inline struct ce_gd *crypto4xx_get_gdp(struct crypto4xx_device *dev, return &dev->gdr[idx]; } -/** +/* * alloc memory for the scatter ring * need to alloc buf for the ring * sdr_tail, sdr_head and sdr_count are initialized by this function @@ -930,7 +930,7 @@ int crypto4xx_build_pd(struct crypto_async_request *req, return is_busy ? -EBUSY : -EINPROGRESS; } -/** +/* * Algorithm Registration Functions */ static void crypto4xx_ctx_init(struct crypto4xx_alg *amcc_alg, @@ -1097,7 +1097,7 @@ static void crypto4xx_bh_tasklet_cb(unsigned long data) } while (head != tail); } -/** +/* * Top Half of isr. */ static inline irqreturn_t crypto4xx_interrupt_handler(int irq, void *data, @@ -1186,7 +1186,7 @@ static int crypto4xx_prng_seed(struct crypto_rng *tfm, const u8 *seed, return 0; } -/** +/* * Supported Crypto Algorithms */ static struct crypto4xx_alg_common crypto4xx_alg[] = { @@ -1369,7 +1369,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = { } }, }; -/** +/* * Module Initialization Routine */ static int crypto4xx_probe(struct platform_device *ofdev) diff --git a/drivers/crypto/amcc/crypto4xx_core.h b/drivers/crypto/amcc/crypto4xx_core.h index a4e25b46cd0a..56c10668c0ab 100644 --- a/drivers/crypto/amcc/crypto4xx_core.h +++ b/drivers/crypto/amcc/crypto4xx_core.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -/** +/* * AMCC SoC PPC4xx Crypto Driver * * Copyright (c) 2008 Applied Micro Circuits Corporation. @@ -188,7 +188,7 @@ int crypto4xx_hash_final(struct ahash_request *req); int crypto4xx_hash_update(struct ahash_request *req); int crypto4xx_hash_init(struct ahash_request *req); -/** +/* * Note: Only use this function to copy items that is word aligned. */ static inline void crypto4xx_memcpy_swab32(u32 *dst, const void *buf, diff --git a/drivers/crypto/amcc/crypto4xx_reg_def.h b/drivers/crypto/amcc/crypto4xx_reg_def.h index c4c0a1a75941..1038061224da 100644 --- a/drivers/crypto/amcc/crypto4xx_reg_def.h +++ b/drivers/crypto/amcc/crypto4xx_reg_def.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -/** +/* * AMCC SoC PPC4xx Crypto Driver * * Copyright (c) 2008 Applied Micro Circuits Corporation. @@ -104,7 +104,7 @@ #define CRYPTO4XX_PRNG_LFSR_L 0x00070030 #define CRYPTO4XX_PRNG_LFSR_H 0x00070034 -/** +/* * Initialize CRYPTO ENGINE registers, and memory bases. */ #define PPC4XX_PDR_POLL 0x3ff @@ -123,7 +123,7 @@ #define PPC4XX_INT_TIMEOUT_CNT 0 #define PPC4XX_INT_TIMEOUT_CNT_REVB 0x3FF #define PPC4XX_INT_CFG 1 -/** +/* * all follow define are ad hoc */ #define PPC4XX_RING_RETRY 100 @@ -131,7 +131,7 @@ #define PPC4XX_SDR_SIZE PPC4XX_NUM_SD #define PPC4XX_GDR_SIZE PPC4XX_NUM_GD -/** +/* * Generic Security Association (SA) with all possible fields. These will * never likely used except for reference purpose. These structure format * can be not changed as the hardware expects them to be layout as defined. diff --git a/drivers/crypto/amcc/crypto4xx_sa.h b/drivers/crypto/amcc/crypto4xx_sa.h index fe756abfc19f..e98e4e7abbad 100644 --- a/drivers/crypto/amcc/crypto4xx_sa.h +++ b/drivers/crypto/amcc/crypto4xx_sa.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -/** +/* * AMCC SoC PPC4xx Crypto Driver * * Copyright (c) 2008 Applied Micro Circuits Corporation. @@ -14,7 +14,7 @@ #define AES_IV_SIZE 16 -/** +/* * Contents of Dynamic Security Association (SA) with all possible fields */ union dynamic_sa_contents { @@ -122,7 +122,7 @@ union sa_command_0 { #define SA_AES_KEY_LEN_256 4 #define SA_REV2 1 -/** +/* * The follow defines bits sa_command_1 * In Basic hash mode this bit define simple hash or hmac. * In IPsec mode, this bit define muting control. @@ -172,7 +172,7 @@ struct dynamic_sa_ctl { union sa_command_1 sa_command_1; } __attribute__((packed)); -/** +/* * State Record for Security Association (SA) */ struct sa_state_record { @@ -184,7 +184,7 @@ struct sa_state_record { }; } __attribute__((packed)); -/** +/* * Security Association (SA) for AES128 * */ @@ -213,7 +213,7 @@ struct dynamic_sa_aes192 { #define SA_AES192_LEN (sizeof(struct dynamic_sa_aes192)/4) #define SA_AES192_CONTENTS 0x3e000062 -/** +/* * Security Association (SA) for AES256 */ struct dynamic_sa_aes256 { @@ -228,7 +228,7 @@ struct dynamic_sa_aes256 { #define SA_AES256_CONTENTS 0x3e000082 #define SA_AES_CONTENTS 0x3e000002 -/** +/* * Security Association (SA) for AES128 CCM */ struct dynamic_sa_aes128_ccm { @@ -242,7 +242,7 @@ struct dynamic_sa_aes128_ccm { #define SA_AES128_CCM_CONTENTS 0x3e000042 #define SA_AES_CCM_CONTENTS 0x3e000002 -/** +/* * Security Association (SA) for AES128_GCM */ struct dynamic_sa_aes128_gcm { @@ -258,7 +258,7 @@ struct dynamic_sa_aes128_gcm { #define SA_AES128_GCM_CONTENTS 0x3e000442 #define SA_AES_GCM_CONTENTS 0x3e000402 -/** +/* * Security Association (SA) for HASH160: HMAC-SHA1 */ struct dynamic_sa_hash160 { diff --git a/drivers/crypto/amcc/crypto4xx_trng.h b/drivers/crypto/amcc/crypto4xx_trng.h index 3af732f25c1c..7356716274cb 100644 --- a/drivers/crypto/amcc/crypto4xx_trng.h +++ b/drivers/crypto/amcc/crypto4xx_trng.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-or-later */ -/** +/* * AMCC SoC PPC4xx Crypto Driver * * Copyright (c) 2008 Applied Micro Circuits Corporation. diff --git a/drivers/crypto/amlogic/amlogic-gxl-cipher.c b/drivers/crypto/amlogic/amlogic-gxl-cipher.c index 8b5e07316352..c6865cbd334b 100644 --- a/drivers/crypto/amlogic/amlogic-gxl-cipher.c +++ b/drivers/crypto/amlogic/amlogic-gxl-cipher.c @@ -236,10 +236,10 @@ static int meson_cipher(struct skcipher_request *areq) dma_unmap_single(mc->dev, phykeyiv, keyivlen, DMA_TO_DEVICE); if (areq->src == areq->dst) { - dma_unmap_sg(mc->dev, areq->src, nr_sgs, DMA_BIDIRECTIONAL); + dma_unmap_sg(mc->dev, areq->src, sg_nents(areq->src), DMA_BIDIRECTIONAL); } else { - dma_unmap_sg(mc->dev, areq->src, nr_sgs, DMA_TO_DEVICE); - dma_unmap_sg(mc->dev, areq->dst, nr_sgd, DMA_FROM_DEVICE); + dma_unmap_sg(mc->dev, areq->src, sg_nents(areq->src), DMA_TO_DEVICE); + dma_unmap_sg(mc->dev, areq->dst, sg_nents(areq->dst), DMA_FROM_DEVICE); } if (areq->iv && ivsize > 0) { diff --git a/drivers/crypto/amlogic/amlogic-gxl-core.c b/drivers/crypto/amlogic/amlogic-gxl-core.c index 5bbeff433c8c..6e7ae896717c 100644 --- a/drivers/crypto/amlogic/amlogic-gxl-core.c +++ b/drivers/crypto/amlogic/amlogic-gxl-core.c @@ -217,9 +217,6 @@ static int meson_crypto_probe(struct platform_device *pdev) struct meson_dev *mc; int err, i; - if (!pdev->dev.of_node) - return -ENODEV; - mc = devm_kzalloc(&pdev->dev, sizeof(*mc), GFP_KERNEL); if (!mc) return -ENOMEM; diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c index 9bd8e5167be3..333fbefbbccb 100644 --- a/drivers/crypto/atmel-ecc.c +++ b/drivers/crypto/atmel-ecc.c @@ -26,7 +26,7 @@ static struct atmel_ecc_driver_data driver_data; /** - * atmel_ecdh_ctx - transformation context + * struct atmel_ecdh_ctx - transformation context * @client : pointer to i2c client device * @fallback : used for unsupported curves or when user wants to use its own * private key. @@ -34,7 +34,6 @@ static struct atmel_ecc_driver_data driver_data; * of the user to not call set_secret() while * generate_public_key() or compute_shared_secret() are in flight. * @curve_id : elliptic curve id - * @n_sz : size in bytes of the n prime * @do_fallback: true when the device doesn't support the curve or when the user * wants to use its own private key. */ @@ -43,7 +42,6 @@ struct atmel_ecdh_ctx { struct crypto_kpp *fallback; const u8 *public_key; unsigned int curve_id; - size_t n_sz; bool do_fallback; }; @@ -51,7 +49,6 @@ static void atmel_ecdh_done(struct atmel_i2c_work_data *work_data, void *areq, int status) { struct kpp_request *req = areq; - struct atmel_ecdh_ctx *ctx = work_data->ctx; struct atmel_i2c_cmd *cmd = &work_data->cmd; size_t copied, n_sz; @@ -59,7 +56,7 @@ static void atmel_ecdh_done(struct atmel_i2c_work_data *work_data, void *areq, goto free_work_data; /* might want less than we've got */ - n_sz = min_t(size_t, ctx->n_sz, req->dst_len); + n_sz = min_t(size_t, ATMEL_ECC_NIST_P256_N_SIZE, req->dst_len); /* copy the shared secret */ copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst, n_sz), @@ -73,14 +70,6 @@ free_work_data: kpp_request_complete(req, status); } -static unsigned int atmel_ecdh_supported_curve(unsigned int curve_id) -{ - if (curve_id == ECC_CURVE_NIST_P256) - return ATMEL_ECC_NIST_P256_N_SIZE; - - return 0; -} - /* * A random private key is generated and stored in the device. The device * returns the pair public key. @@ -104,8 +93,7 @@ static int atmel_ecdh_set_secret(struct crypto_kpp *tfm, const void *buf, return -EINVAL; } - ctx->n_sz = atmel_ecdh_supported_curve(params.curve_id); - if (!ctx->n_sz || params.key_size) { + if (params.key_size) { /* fallback to ecdh software implementation */ ctx->do_fallback = true; return crypto_kpp_set_secret(ctx->fallback, buf, len); @@ -125,7 +113,6 @@ static int atmel_ecdh_set_secret(struct crypto_kpp *tfm, const void *buf, goto free_cmd; ctx->do_fallback = false; - ctx->curve_id = params.curve_id; atmel_i2c_init_genkey_cmd(cmd, DATA_SLOT_2); @@ -263,6 +250,7 @@ static int atmel_ecdh_init_tfm(struct crypto_kpp *tfm) struct crypto_kpp *fallback; struct atmel_ecdh_ctx *ctx = kpp_tfm_ctx(tfm); + ctx->curve_id = ECC_CURVE_NIST_P256; ctx->client = atmel_ecc_i2c_client_alloc(); if (IS_ERR(ctx->client)) { pr_err("tfm - i2c_client binding failed\n"); @@ -306,7 +294,7 @@ static unsigned int atmel_ecdh_max_size(struct crypto_kpp *tfm) return ATMEL_ECC_PUBKEY_SIZE; } -static struct kpp_alg atmel_ecdh = { +static struct kpp_alg atmel_ecdh_nist_p256 = { .set_secret = atmel_ecdh_set_secret, .generate_public_key = atmel_ecdh_generate_public_key, .compute_shared_secret = atmel_ecdh_compute_shared_secret, @@ -315,7 +303,7 @@ static struct kpp_alg atmel_ecdh = { .max_size = atmel_ecdh_max_size, .base = { .cra_flags = CRYPTO_ALG_NEED_FALLBACK, - .cra_name = "ecdh", + .cra_name = "ecdh-nist-p256", .cra_driver_name = "atmel-ecdh", .cra_priority = ATMEL_ECC_PRIORITY, .cra_module = THIS_MODULE, @@ -340,14 +328,14 @@ static int atmel_ecc_probe(struct i2c_client *client, &driver_data.i2c_client_list); spin_unlock(&driver_data.i2c_list_lock); - ret = crypto_register_kpp(&atmel_ecdh); + ret = crypto_register_kpp(&atmel_ecdh_nist_p256); if (ret) { spin_lock(&driver_data.i2c_list_lock); list_del(&i2c_priv->i2c_client_list_node); spin_unlock(&driver_data.i2c_list_lock); dev_err(&client->dev, "%s alg registration failed\n", - atmel_ecdh.base.cra_driver_name); + atmel_ecdh_nist_p256.base.cra_driver_name); } else { dev_info(&client->dev, "atmel ecc algorithms registered in /proc/crypto\n"); } @@ -365,7 +353,7 @@ static int atmel_ecc_remove(struct i2c_client *client) return -EBUSY; } - crypto_unregister_kpp(&atmel_ecdh); + crypto_unregister_kpp(&atmel_ecdh_nist_p256); spin_lock(&driver_data.i2c_list_lock); list_del(&i2c_priv->i2c_client_list_node); diff --git a/drivers/crypto/atmel-i2c.c b/drivers/crypto/atmel-i2c.c index e8e8281e027d..6fd3e969211d 100644 --- a/drivers/crypto/atmel-i2c.c +++ b/drivers/crypto/atmel-i2c.c @@ -339,7 +339,7 @@ int atmel_i2c_probe(struct i2c_client *client, const struct i2c_device_id *id) } if (bus_clk_rate > 1000000L) { - dev_err(dev, "%d exceeds maximum supported clock frequency (1MHz)\n", + dev_err(dev, "%u exceeds maximum supported clock frequency (1MHz)\n", bus_clk_rate); return -EINVAL; } diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c index 352d80cb5ae9..1b13f601fd95 100644 --- a/drivers/crypto/atmel-sha.c +++ b/drivers/crypto/atmel-sha.c @@ -434,7 +434,7 @@ static int atmel_sha_init(struct ahash_request *req) ctx->flags = 0; - dev_dbg(dd->dev, "init: digest size: %d\n", + dev_dbg(dd->dev, "init: digest size: %u\n", crypto_ahash_digestsize(tfm)); switch (crypto_ahash_digestsize(tfm)) { @@ -1102,7 +1102,7 @@ static int atmel_sha_start(struct atmel_sha_dev *dd) struct atmel_sha_reqctx *ctx = ahash_request_ctx(req); int err; - dev_dbg(dd->dev, "handling new req, op: %lu, nbytes: %d\n", + dev_dbg(dd->dev, "handling new req, op: %lu, nbytes: %u\n", ctx->op, req->nbytes); err = atmel_sha_hw_init(dd); diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c index 4d63cb13a54f..6f01c51e3c37 100644 --- a/drivers/crypto/atmel-tdes.c +++ b/drivers/crypto/atmel-tdes.c @@ -1217,7 +1217,6 @@ static int atmel_tdes_probe(struct platform_device *pdev) tdes_dd->io_base = devm_ioremap_resource(&pdev->dev, tdes_res); if (IS_ERR(tdes_dd->io_base)) { - dev_err(dev, "can't ioremap\n"); err = PTR_ERR(tdes_dd->io_base); goto err_tasklet_kill; } diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c index 851b149f7170..053315e260c2 100644 --- a/drivers/crypto/bcm/cipher.c +++ b/drivers/crypto/bcm/cipher.c @@ -1019,6 +1019,7 @@ static void handle_ahash_resp(struct iproc_reqctx_s *rctx) * a SPU response message for an AEAD request. Includes buffers to catch SPU * message headers and the response data. * @mssg: mailbox message containing the receive sg + * @req: Crypto API request * @rctx: crypto request context * @rx_frag_num: number of scatterlist elements required to hold the * SPU response message @@ -2952,9 +2953,9 @@ static int aead_gcm_esp_setkey(struct crypto_aead *cipher, /** * rfc4543_gcm_esp_setkey() - setkey operation for RFC4543 variant of GCM/GMAC. - * cipher: AEAD structure - * key: Key followed by 4 bytes of salt - * keylen: Length of key plus salt, in bytes + * @cipher: AEAD structure + * @key: Key followed by 4 bytes of salt + * @keylen: Length of key plus salt, in bytes * * Extracts salt from key and stores it to be prepended to IV on each request. * Digest is always 16 bytes diff --git a/drivers/crypto/bcm/spu.c b/drivers/crypto/bcm/spu.c index 007abf92cc05..6283e8c6d51d 100644 --- a/drivers/crypto/bcm/spu.c +++ b/drivers/crypto/bcm/spu.c @@ -457,7 +457,7 @@ u16 spum_hash_pad_len(enum hash_alg hash_alg, enum hash_mode hash_mode, * @cipher_mode: Algo type * @data_size: Length of plaintext (bytes) * - * @Return: Length of padding, in bytes + * Return: Length of padding, in bytes */ u32 spum_gcm_ccm_pad_len(enum spu_cipher_mode cipher_mode, unsigned int data_size) @@ -510,10 +510,10 @@ u32 spum_assoc_resp_len(enum spu_cipher_mode cipher_mode, } /** - * spu_aead_ivlen() - Calculate the length of the AEAD IV to be included + * spum_aead_ivlen() - Calculate the length of the AEAD IV to be included * in a SPU request after the AAD and before the payload. * @cipher_mode: cipher mode - * @iv_ctr_len: initialization vector length in bytes + * @iv_len: initialization vector length in bytes * * In Linux ~4.2 and later, the assoc_data sg includes the IV. So no need * to include the IV as a separate field in the SPU request msg. @@ -543,9 +543,9 @@ enum hash_type spum_hash_type(u32 src_sent) /** * spum_digest_size() - Determine the size of a hash digest to expect the SPU to * return. - * alg_digest_size: Number of bytes in the final digest for the given algo - * alg: The hash algorithm - * htype: Type of hash operation (init, update, full, etc) + * @alg_digest_size: Number of bytes in the final digest for the given algo + * @alg: The hash algorithm + * @htype: Type of hash operation (init, update, full, etc) * * When doing incremental hashing for an algorithm with a truncated hash * (e.g., SHA224), the SPU returns the full digest so that it can be fed back as @@ -580,7 +580,7 @@ u32 spum_digest_size(u32 alg_digest_size, enum hash_alg alg, * @aead_parms: Parameters related to AEAD operation * @data_size: Length of data to be encrypted or authenticated. If AEAD, does * not include length of AAD. - + * * Return: the length of the SPU header in bytes. 0 if an error occurs. */ u32 spum_create_request(u8 *spu_hdr, @@ -911,7 +911,7 @@ u16 spum_cipher_req_init(u8 *spu_hdr, struct spu_cipher_parms *cipher_parms) * setkey() time in spu_cipher_req_init(). * @spu_hdr: Start of the request message header (MH field) * @spu_req_hdr_len: Length in bytes of the SPU request header - * @isInbound: 0 encrypt, 1 decrypt + * @is_inbound: 0 encrypt, 1 decrypt * @cipher_parms: Parameters describing cipher operation to be performed * @data_size: Length of the data in the BD field * diff --git a/drivers/crypto/bcm/spu2.c b/drivers/crypto/bcm/spu2.c index 2db35b5ccaa2..07989bb8c220 100644 --- a/drivers/crypto/bcm/spu2.c +++ b/drivers/crypto/bcm/spu2.c @@ -543,7 +543,8 @@ void spu2_dump_msg_hdr(u8 *buf, unsigned int buf_len) /** * spu2_fmd_init() - At setkey time, initialize the fixed meta data for * subsequent skcipher requests for this context. - * @spu2_cipher_type: Cipher algorithm + * @fmd: Start of FMD field to be written + * @spu2_type: Cipher algorithm * @spu2_mode: Cipher mode * @cipher_key_len: Length of cipher key, in bytes * @cipher_iv_len: Length of cipher initialization vector, in bytes @@ -598,7 +599,7 @@ static int spu2_fmd_init(struct SPU2_FMD *fmd, * SPU request packet. * @fmd: Start of FMD field to be written * @is_inbound: true if decrypting. false if encrypting. - * @authFirst: true if alg authenticates before encrypting + * @auth_first: true if alg authenticates before encrypting * @protocol: protocol selector * @cipher_type: cipher algorithm * @cipher_mode: cipher mode @@ -640,6 +641,7 @@ static void spu2_fmd_ctrl0_write(struct SPU2_FMD *fmd, * spu2_fmd_ctrl1_write() - Write ctrl1 field in fixed metadata (FMD) field of * SPU request packet. * @fmd: Start of FMD field to be written + * @is_inbound: true if decrypting. false if encrypting. * @assoc_size: Length of additional associated data, in bytes * @auth_key_len: Length of authentication key, in bytes * @cipher_key_len: Length of cipher key, in bytes @@ -793,7 +795,7 @@ u32 spu2_ctx_max_payload(enum spu_cipher_alg cipher_alg, } /** - * spu_payload_length() - Given a SPU2 message header, extract the payload + * spu2_payload_length() - Given a SPU2 message header, extract the payload * length. * @spu_hdr: Start of SPU message header (FMD) * @@ -812,10 +814,11 @@ u32 spu2_payload_length(u8 *spu_hdr) } /** - * spu_response_hdr_len() - Determine the expected length of a SPU response + * spu2_response_hdr_len() - Determine the expected length of a SPU response * header. * @auth_key_len: Length of authentication key, in bytes * @enc_key_len: Length of encryption key, in bytes + * @is_hash: Unused * * For SPU2, includes just FMD. OMD is never requested. * @@ -827,7 +830,7 @@ u16 spu2_response_hdr_len(u16 auth_key_len, u16 enc_key_len, bool is_hash) } /** - * spu_hash_pad_len() - Calculate the length of hash padding required to extend + * spu2_hash_pad_len() - Calculate the length of hash padding required to extend * data to a full block size. * @hash_alg: hash algorithm * @hash_mode: hash mode @@ -845,8 +848,10 @@ u16 spu2_hash_pad_len(enum hash_alg hash_alg, enum hash_mode hash_mode, } /** - * spu2_gcm_ccm_padlen() - Determine the length of GCM/CCM padding for either + * spu2_gcm_ccm_pad_len() - Determine the length of GCM/CCM padding for either * the AAD field or the data. + * @cipher_mode: Unused + * @data_size: Unused * * Return: 0. Unlike SPU-M, SPU2 hardware does any GCM/CCM padding required. */ @@ -857,7 +862,7 @@ u32 spu2_gcm_ccm_pad_len(enum spu_cipher_mode cipher_mode, } /** - * spu_assoc_resp_len() - Determine the size of the AAD2 buffer needed to catch + * spu2_assoc_resp_len() - Determine the size of the AAD2 buffer needed to catch * associated data in a SPU2 output packet. * @cipher_mode: cipher mode * @assoc_len: length of additional associated data, in bytes @@ -878,11 +883,11 @@ u32 spu2_assoc_resp_len(enum spu_cipher_mode cipher_mode, return resp_len; } -/* - * spu_aead_ivlen() - Calculate the length of the AEAD IV to be included +/** + * spu2_aead_ivlen() - Calculate the length of the AEAD IV to be included * in a SPU request after the AAD and before the payload. * @cipher_mode: cipher mode - * @iv_ctr_len: initialization vector length in bytes + * @iv_len: initialization vector length in bytes * * For SPU2, AEAD IV is included in OMD and does not need to be repeated * prior to the payload. @@ -909,9 +914,9 @@ enum hash_type spu2_hash_type(u32 src_sent) /** * spu2_digest_size() - Determine the size of a hash digest to expect the SPU to * return. - * alg_digest_size: Number of bytes in the final digest for the given algo - * alg: The hash algorithm - * htype: Type of hash operation (init, update, full, etc) + * @alg_digest_size: Number of bytes in the final digest for the given algo + * @alg: The hash algorithm + * @htype: Type of hash operation (init, update, full, etc) * */ u32 spu2_digest_size(u32 alg_digest_size, enum hash_alg alg, @@ -921,7 +926,7 @@ u32 spu2_digest_size(u32 alg_digest_size, enum hash_alg alg, } /** - * spu_create_request() - Build a SPU2 request message header, includint FMD and + * spu2_create_request() - Build a SPU2 request message header, includint FMD and * OMD. * @spu_hdr: Start of buffer where SPU request header is to be written * @req_opts: SPU request message options @@ -1105,7 +1110,7 @@ u32 spu2_create_request(u8 *spu_hdr, } /** - * spu_cipher_req_init() - Build an skcipher SPU2 request message header, + * spu2_cipher_req_init() - Build an skcipher SPU2 request message header, * including FMD and OMD. * @spu_hdr: Location of start of SPU request (FMD field) * @cipher_parms: Parameters describing cipher request @@ -1162,11 +1167,11 @@ u16 spu2_cipher_req_init(u8 *spu_hdr, struct spu_cipher_parms *cipher_parms) } /** - * spu_cipher_req_finish() - Finish building a SPU request message header for a + * spu2_cipher_req_finish() - Finish building a SPU request message header for a * block cipher request. * @spu_hdr: Start of the request message header (MH field) * @spu_req_hdr_len: Length in bytes of the SPU request header - * @isInbound: 0 encrypt, 1 decrypt + * @is_inbound: 0 encrypt, 1 decrypt * @cipher_parms: Parameters describing cipher operation to be performed * @data_size: Length of the data in the BD field * @@ -1222,7 +1227,7 @@ void spu2_cipher_req_finish(u8 *spu_hdr, } /** - * spu_request_pad() - Create pad bytes at the end of the data. + * spu2_request_pad() - Create pad bytes at the end of the data. * @pad_start: Start of buffer where pad bytes are to be written * @gcm_padding: Length of GCM padding, in bytes * @hash_pad_len: Number of bytes of padding extend data to full block @@ -1311,7 +1316,7 @@ u8 spu2_rx_status_len(void) } /** - * spu_status_process() - Process the status from a SPU response message. + * spu2_status_process() - Process the status from a SPU response message. * @statp: start of STATUS word * * Return: 0 - if status is good and response should be processed diff --git a/drivers/crypto/bcm/util.c b/drivers/crypto/bcm/util.c index c4669a96eaec..d5d9cabea55a 100644 --- a/drivers/crypto/bcm/util.c +++ b/drivers/crypto/bcm/util.c @@ -119,8 +119,8 @@ int spu_sg_count(struct scatterlist *sg_list, unsigned int skip, int nbytes) * @from_skip: number of bytes to skip in from_sg. Non-zero when previous * request included part of the buffer in entry in from_sg. * Assumes from_skip < from_sg->length. - * @from_nents number of entries in from_sg - * @length number of bytes to copy. may reach this limit before exhausting + * @from_nents: number of entries in from_sg + * @length: number of bytes to copy. may reach this limit before exhausting * from_sg. * * Copies the entries themselves, not the data in the entries. Assumes to_sg has diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c index a780e627838a..8b8ed77d8715 100644 --- a/drivers/crypto/caam/caamalg_qi2.c +++ b/drivers/crypto/caam/caamalg_qi2.c @@ -71,6 +71,9 @@ struct caam_skcipher_alg { * @adata: authentication algorithm details * @cdata: encryption algorithm details * @authsize: authentication tag (a.k.a. ICV / MAC) size + * @xts_key_fallback: true if fallback tfm needs to be used due + * to unsupported xts key lengths + * @fallback: xts fallback tfm */ struct caam_ctx { struct caam_flc flc[NUM_OP]; diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c index dd5f101e43f8..e313233ec6de 100644 --- a/drivers/crypto/caam/caampkc.c +++ b/drivers/crypto/caam/caampkc.c @@ -187,7 +187,8 @@ static void rsa_priv_f_done(struct device *dev, u32 *desc, u32 err, } /** - * Count leading zeros, need it to strip, from a given scatterlist + * caam_rsa_count_leading_zeros - Count leading zeros, need it to strip, + * from a given scatterlist * * @sgl : scatterlist to count zeros from * @nbytes: number of zeros, in bytes, to strip diff --git a/drivers/crypto/cavium/cpt/cptpf_main.c b/drivers/crypto/cavium/cpt/cptpf_main.c index 711b1acdd4e0..06ee42e8a245 100644 --- a/drivers/crypto/cavium/cpt/cptpf_main.c +++ b/drivers/crypto/cavium/cpt/cptpf_main.c @@ -10,7 +10,6 @@ #include <linux/moduleparam.h> #include <linux/pci.h> #include <linux/printk.h> -#include <linux/version.h> #include "cptpf.h" diff --git a/drivers/crypto/cavium/nitrox/nitrox_isr.c b/drivers/crypto/cavium/nitrox/nitrox_isr.c index 99b053094f5a..c288c4b51783 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_isr.c +++ b/drivers/crypto/cavium/nitrox/nitrox_isr.c @@ -10,7 +10,7 @@ #include "nitrox_isr.h" #include "nitrox_mbx.h" -/** +/* * One vector for each type of ring * - NPS packet ring, AQMQ ring and ZQMQ ring */ @@ -216,7 +216,7 @@ static void nps_core_int_tasklet(unsigned long data) } } -/** +/* * nps_core_int_isr - interrupt handler for NITROX errors and * mailbox communication */ diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c index 53ef06792133..df95ba26b414 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c +++ b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c @@ -58,14 +58,15 @@ static void softreq_unmap_sgbufs(struct nitrox_softreq *sr) struct device *dev = DEV(ndev); - dma_unmap_sg(dev, sr->in.sg, sr->in.sgmap_cnt, DMA_BIDIRECTIONAL); + dma_unmap_sg(dev, sr->in.sg, sg_nents(sr->in.sg), + DMA_BIDIRECTIONAL); dma_unmap_single(dev, sr->in.sgcomp_dma, sr->in.sgcomp_len, DMA_TO_DEVICE); kfree(sr->in.sgcomp); sr->in.sg = NULL; sr->in.sgmap_cnt = 0; - dma_unmap_sg(dev, sr->out.sg, sr->out.sgmap_cnt, + dma_unmap_sg(dev, sr->out.sg, sg_nents(sr->out.sg), DMA_BIDIRECTIONAL); dma_unmap_single(dev, sr->out.sgcomp_dma, sr->out.sgcomp_len, DMA_TO_DEVICE); @@ -178,7 +179,7 @@ static int dma_map_inbufs(struct nitrox_softreq *sr, return 0; incomp_err: - dma_unmap_sg(dev, req->src, nents, DMA_BIDIRECTIONAL); + dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_BIDIRECTIONAL); sr->in.sgmap_cnt = 0; return ret; } @@ -203,7 +204,7 @@ static int dma_map_outbufs(struct nitrox_softreq *sr, return 0; outcomp_map_err: - dma_unmap_sg(dev, req->dst, nents, DMA_BIDIRECTIONAL); + dma_unmap_sg(dev, req->dst, sg_nents(req->dst), DMA_BIDIRECTIONAL); sr->out.sgmap_cnt = 0; sr->out.sg = NULL; return ret; diff --git a/drivers/crypto/cavium/zip/common.h b/drivers/crypto/cavium/zip/common.h index 58fb3ed6e644..54f6fb054119 100644 --- a/drivers/crypto/cavium/zip/common.h +++ b/drivers/crypto/cavium/zip/common.h @@ -56,7 +56,6 @@ #include <linux/seq_file.h> #include <linux/string.h> #include <linux/types.h> -#include <linux/version.h> /* Device specific zlib function definitions */ #include "zip_device.h" diff --git a/drivers/crypto/ccp/ccp-crypto-main.c b/drivers/crypto/ccp/ccp-crypto-main.c index 88275b4867ea..5976530c00a8 100644 --- a/drivers/crypto/ccp/ccp-crypto-main.c +++ b/drivers/crypto/ccp/ccp-crypto-main.c @@ -59,7 +59,7 @@ struct ccp_crypto_queue { #define CCP_CRYPTO_MAX_QLEN 100 static struct ccp_crypto_queue req_queue; -static spinlock_t req_queue_lock; +static DEFINE_SPINLOCK(req_queue_lock); struct ccp_crypto_cmd { struct list_head entry; @@ -410,7 +410,6 @@ static int ccp_crypto_init(void) return ret; } - spin_lock_init(&req_queue_lock); INIT_LIST_HEAD(&req_queue.cmds); req_queue.backlog = &req_queue.cmds; req_queue.cmd_count = 0; diff --git a/drivers/crypto/ccp/ccp-dev.c b/drivers/crypto/ccp/ccp-dev.c index 0971ee60f840..6777582aa1ce 100644 --- a/drivers/crypto/ccp/ccp-dev.c +++ b/drivers/crypto/ccp/ccp-dev.c @@ -548,7 +548,7 @@ bool ccp_queues_suspended(struct ccp_device *ccp) return ccp->cmd_q_count == suspended; } -int ccp_dev_suspend(struct sp_device *sp) +void ccp_dev_suspend(struct sp_device *sp) { struct ccp_device *ccp = sp->ccp_data; unsigned long flags; @@ -556,7 +556,7 @@ int ccp_dev_suspend(struct sp_device *sp) /* If there's no device there's nothing to do */ if (!ccp) - return 0; + return; spin_lock_irqsave(&ccp->cmd_lock, flags); @@ -572,11 +572,9 @@ int ccp_dev_suspend(struct sp_device *sp) while (!ccp_queues_suspended(ccp)) wait_event_interruptible(ccp->suspend_queue, ccp_queues_suspended(ccp)); - - return 0; } -int ccp_dev_resume(struct sp_device *sp) +void ccp_dev_resume(struct sp_device *sp) { struct ccp_device *ccp = sp->ccp_data; unsigned long flags; @@ -584,7 +582,7 @@ int ccp_dev_resume(struct sp_device *sp) /* If there's no device there's nothing to do */ if (!ccp) - return 0; + return; spin_lock_irqsave(&ccp->cmd_lock, flags); @@ -597,8 +595,6 @@ int ccp_dev_resume(struct sp_device *sp) } spin_unlock_irqrestore(&ccp->cmd_lock, flags); - - return 0; } int ccp_dev_init(struct sp_device *sp) diff --git a/drivers/crypto/ccp/ccp-ops.c b/drivers/crypto/ccp/ccp-ops.c index d6a8f4e4b14a..bb88198c874e 100644 --- a/drivers/crypto/ccp/ccp-ops.c +++ b/drivers/crypto/ccp/ccp-ops.c @@ -2418,7 +2418,6 @@ static int ccp_run_ecc_pm_cmd(struct ccp_cmd_queue *cmd_q, struct ccp_cmd *cmd) dst.address += CCP_ECC_OUTPUT_SIZE; ccp_reverse_get_dm_area(&dst, 0, ecc->u.pm.result.y, 0, CCP_ECC_MODULUS_BYTES); - dst.address += CCP_ECC_OUTPUT_SIZE; /* Restore the workarea address */ dst.address = save; diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index cb9b4c4e371e..da3872c48308 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -21,6 +21,7 @@ #include <linux/ccp.h> #include <linux/firmware.h> #include <linux/gfp.h> +#include <linux/cpufeature.h> #include <asm/smp.h> @@ -972,6 +973,11 @@ int sev_dev_init(struct psp_device *psp) struct sev_device *sev; int ret = -ENOMEM; + if (!boot_cpu_has(X86_FEATURE_SEV)) { + dev_info_once(dev, "SEV: memory encryption not enabled by BIOS\n"); + return 0; + } + sev = devm_kzalloc(dev, sizeof(*sev), GFP_KERNEL); if (!sev) goto e_err; diff --git a/drivers/crypto/ccp/sp-dev.c b/drivers/crypto/ccp/sp-dev.c index 6284a15e5047..7eb3e4668286 100644 --- a/drivers/crypto/ccp/sp-dev.c +++ b/drivers/crypto/ccp/sp-dev.c @@ -213,12 +213,8 @@ void sp_destroy(struct sp_device *sp) int sp_suspend(struct sp_device *sp) { - int ret; - if (sp->dev_vdata->ccp_vdata) { - ret = ccp_dev_suspend(sp); - if (ret) - return ret; + ccp_dev_suspend(sp); } return 0; @@ -226,12 +222,8 @@ int sp_suspend(struct sp_device *sp) int sp_resume(struct sp_device *sp) { - int ret; - if (sp->dev_vdata->ccp_vdata) { - ret = ccp_dev_resume(sp); - if (ret) - return ret; + ccp_dev_resume(sp); } return 0; diff --git a/drivers/crypto/ccp/sp-dev.h b/drivers/crypto/ccp/sp-dev.h index 0218d0670eee..20377e67f65d 100644 --- a/drivers/crypto/ccp/sp-dev.h +++ b/drivers/crypto/ccp/sp-dev.h @@ -134,8 +134,8 @@ struct sp_device *sp_get_psp_master_device(void); int ccp_dev_init(struct sp_device *sp); void ccp_dev_destroy(struct sp_device *sp); -int ccp_dev_suspend(struct sp_device *sp); -int ccp_dev_resume(struct sp_device *sp); +void ccp_dev_suspend(struct sp_device *sp); +void ccp_dev_resume(struct sp_device *sp); #else /* !CONFIG_CRYPTO_DEV_SP_CCP */ @@ -144,15 +144,8 @@ static inline int ccp_dev_init(struct sp_device *sp) return 0; } static inline void ccp_dev_destroy(struct sp_device *sp) { } - -static inline int ccp_dev_suspend(struct sp_device *sp) -{ - return 0; -} -static inline int ccp_dev_resume(struct sp_device *sp) -{ - return 0; -} +static inline void ccp_dev_suspend(struct sp_device *sp) { } +static inline void ccp_dev_resume(struct sp_device *sp) { } #endif /* CONFIG_CRYPTO_DEV_SP_CCP */ #ifdef CONFIG_CRYPTO_DEV_SP_PSP diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c index f471dbaef1fb..f468594ef8af 100644 --- a/drivers/crypto/ccp/sp-pci.c +++ b/drivers/crypto/ccp/sp-pci.c @@ -356,6 +356,7 @@ static const struct pci_device_id sp_pci_table[] = { { PCI_VDEVICE(AMD, 0x1468), (kernel_ulong_t)&dev_vdata[2] }, { PCI_VDEVICE(AMD, 0x1486), (kernel_ulong_t)&dev_vdata[3] }, { PCI_VDEVICE(AMD, 0x15DF), (kernel_ulong_t)&dev_vdata[4] }, + { PCI_VDEVICE(AMD, 0x1649), (kernel_ulong_t)&dev_vdata[4] }, /* Last entry must be zero */ { 0, } }; diff --git a/drivers/crypto/ccp/tee-dev.c b/drivers/crypto/ccp/tee-dev.c index 5e697a90ea7f..5c9d47f3be37 100644 --- a/drivers/crypto/ccp/tee-dev.c +++ b/drivers/crypto/ccp/tee-dev.c @@ -5,7 +5,7 @@ * Author: Rijo Thomas <Rijo-john.Thomas@amd.com> * Author: Devaraj Rangasamy <Devaraj.Rangasamy@amd.com> * - * Copyright 2019 Advanced Micro Devices, Inc. + * Copyright (C) 2019,2021 Advanced Micro Devices, Inc. */ #include <linux/types.h> @@ -36,6 +36,7 @@ static int tee_alloc_ring(struct psp_tee_device *tee, int ring_size) if (!start_addr) return -ENOMEM; + memset(start_addr, 0x0, ring_size); rb_mgr->ring_start = start_addr; rb_mgr->ring_size = ring_size; rb_mgr->ring_pa = __psp_pa(start_addr); @@ -244,41 +245,54 @@ static int tee_submit_cmd(struct psp_tee_device *tee, enum tee_cmd_id cmd_id, void *buf, size_t len, struct tee_ring_cmd **resp) { struct tee_ring_cmd *cmd; - u32 rptr, wptr; int nloop = 1000, ret = 0; + u32 rptr; *resp = NULL; mutex_lock(&tee->rb_mgr.mutex); - wptr = tee->rb_mgr.wptr; - - /* Check if ring buffer is full */ + /* Loop until empty entry found in ring buffer */ do { + /* Get pointer to ring buffer command entry */ + cmd = (struct tee_ring_cmd *) + (tee->rb_mgr.ring_start + tee->rb_mgr.wptr); + rptr = ioread32(tee->io_regs + tee->vdata->ring_rptr_reg); - if (!(wptr + sizeof(struct tee_ring_cmd) == rptr)) + /* Check if ring buffer is full or command entry is waiting + * for response from TEE + */ + if (!(tee->rb_mgr.wptr + sizeof(struct tee_ring_cmd) == rptr || + cmd->flag == CMD_WAITING_FOR_RESPONSE)) break; - dev_info(tee->dev, "tee: ring buffer full. rptr = %u wptr = %u\n", - rptr, wptr); + dev_dbg(tee->dev, "tee: ring buffer full. rptr = %u wptr = %u\n", + rptr, tee->rb_mgr.wptr); - /* Wait if ring buffer is full */ + /* Wait if ring buffer is full or TEE is processing data */ mutex_unlock(&tee->rb_mgr.mutex); schedule_timeout_interruptible(msecs_to_jiffies(10)); mutex_lock(&tee->rb_mgr.mutex); } while (--nloop); - if (!nloop && (wptr + sizeof(struct tee_ring_cmd) == rptr)) { - dev_err(tee->dev, "tee: ring buffer full. rptr = %u wptr = %u\n", - rptr, wptr); + if (!nloop && + (tee->rb_mgr.wptr + sizeof(struct tee_ring_cmd) == rptr || + cmd->flag == CMD_WAITING_FOR_RESPONSE)) { + dev_err(tee->dev, "tee: ring buffer full. rptr = %u wptr = %u response flag %u\n", + rptr, tee->rb_mgr.wptr, cmd->flag); ret = -EBUSY; goto unlock; } - /* Pointer to empty data entry in ring buffer */ - cmd = (struct tee_ring_cmd *)(tee->rb_mgr.ring_start + wptr); + /* Do not submit command if PSP got disabled while processing any + * command in another thread + */ + if (psp_dead) { + ret = -EBUSY; + goto unlock; + } /* Write command data into ring buffer */ cmd->cmd_id = cmd_id; @@ -286,6 +300,9 @@ static int tee_submit_cmd(struct psp_tee_device *tee, enum tee_cmd_id cmd_id, memset(&cmd->buf[0], 0, sizeof(cmd->buf)); memcpy(&cmd->buf[0], buf, len); + /* Indicate driver is waiting for response */ + cmd->flag = CMD_WAITING_FOR_RESPONSE; + /* Update local copy of write pointer */ tee->rb_mgr.wptr += sizeof(struct tee_ring_cmd); if (tee->rb_mgr.wptr >= tee->rb_mgr.ring_size) @@ -309,14 +326,14 @@ static int tee_wait_cmd_completion(struct psp_tee_device *tee, struct tee_ring_cmd *resp, unsigned int timeout) { - /* ~5ms sleep per loop => nloop = timeout * 200 */ - int nloop = timeout * 200; + /* ~1ms sleep per loop => nloop = timeout * 1000 */ + int nloop = timeout * 1000; while (--nloop) { if (resp->cmd_state == TEE_CMD_STATE_COMPLETED) return 0; - usleep_range(5000, 5100); + usleep_range(1000, 1100); } dev_err(tee->dev, "tee: command 0x%x timed out, disabling PSP\n", @@ -353,12 +370,16 @@ int psp_tee_process_cmd(enum tee_cmd_id cmd_id, void *buf, size_t len, return ret; ret = tee_wait_cmd_completion(tee, resp, TEE_DEFAULT_TIMEOUT); - if (ret) + if (ret) { + resp->flag = CMD_RESPONSE_TIMEDOUT; return ret; + } memcpy(buf, &resp->buf[0], len); *status = resp->status; + resp->flag = CMD_RESPONSE_COPIED; + return 0; } EXPORT_SYMBOL(psp_tee_process_cmd); diff --git a/drivers/crypto/ccp/tee-dev.h b/drivers/crypto/ccp/tee-dev.h index f09960112115..49d26158b71e 100644 --- a/drivers/crypto/ccp/tee-dev.h +++ b/drivers/crypto/ccp/tee-dev.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: MIT */ /* - * Copyright 2019 Advanced Micro Devices, Inc. + * Copyright (C) 2019,2021 Advanced Micro Devices, Inc. * * Author: Rijo Thomas <Rijo-john.Thomas@amd.com> * Author: Devaraj Rangasamy <Devaraj.Rangasamy@amd.com> @@ -18,7 +18,7 @@ #include <linux/mutex.h> #define TEE_DEFAULT_TIMEOUT 10 -#define MAX_BUFFER_SIZE 992 +#define MAX_BUFFER_SIZE 988 /** * enum tee_ring_cmd_id - TEE interface commands for ring buffer configuration @@ -82,6 +82,20 @@ enum tee_cmd_state { }; /** + * enum cmd_resp_state - TEE command's response status maintained by driver + * @CMD_RESPONSE_INVALID: initial state when no command is written to ring + * @CMD_WAITING_FOR_RESPONSE: driver waiting for response from TEE + * @CMD_RESPONSE_TIMEDOUT: failed to get response from TEE + * @CMD_RESPONSE_COPIED: driver has copied response from TEE + */ +enum cmd_resp_state { + CMD_RESPONSE_INVALID, + CMD_WAITING_FOR_RESPONSE, + CMD_RESPONSE_TIMEDOUT, + CMD_RESPONSE_COPIED, +}; + +/** * struct tee_ring_cmd - Structure of the command buffer in TEE ring * @cmd_id: refers to &enum tee_cmd_id. Command id for the ring buffer * interface @@ -91,6 +105,7 @@ enum tee_cmd_state { * @pdata: private data (currently unused) * @res1: reserved region * @buf: TEE command specific buffer + * @flag: refers to &enum cmd_resp_state */ struct tee_ring_cmd { u32 cmd_id; @@ -100,6 +115,7 @@ struct tee_ring_cmd { u64 pdata; u32 res1[2]; u8 buf[MAX_BUFFER_SIZE]; + u32 flag; /* Total size: 1024 bytes */ } __packed; diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c index d0e59e942568..e599ac6dc162 100644 --- a/drivers/crypto/ccree/cc_driver.c +++ b/drivers/crypto/ccree/cc_driver.c @@ -352,10 +352,8 @@ static int init_cc_resources(struct platform_device *plat_dev) req_mem_cc_regs = platform_get_resource(plat_dev, IORESOURCE_MEM, 0); /* Map registers space */ new_drvdata->cc_base = devm_ioremap_resource(dev, req_mem_cc_regs); - if (IS_ERR(new_drvdata->cc_base)) { - dev_err(dev, "Failed to ioremap registers"); + if (IS_ERR(new_drvdata->cc_base)) return PTR_ERR(new_drvdata->cc_base); - } dev_dbg(dev, "Got MEM resource (%s): %pR\n", req_mem_cc_regs->name, req_mem_cc_regs); diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index f5a336634daa..6933546f87b1 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -126,11 +126,6 @@ static inline struct uld_ctx *ULD_CTX(struct chcr_context *ctx) return container_of(ctx->dev, struct uld_ctx, dev); } -static inline int is_ofld_imm(const struct sk_buff *skb) -{ - return (skb->len <= SGE_MAX_WR_LEN); -} - static inline void chcr_init_hctx_per_wr(struct chcr_ahash_req_ctx *reqctx) { memset(&reqctx->hctx_wr, 0, sizeof(struct chcr_hctx_per_wr)); @@ -769,13 +764,14 @@ static inline void create_wreq(struct chcr_context *ctx, struct uld_ctx *u_ctx = ULD_CTX(ctx); unsigned int tx_channel_id, rx_channel_id; unsigned int txqidx = 0, rxqidx = 0; - unsigned int qid, fid; + unsigned int qid, fid, portno; get_qidxs(req, &txqidx, &rxqidx); qid = u_ctx->lldi.rxq_ids[rxqidx]; fid = u_ctx->lldi.rxq_ids[0]; + portno = rxqidx / ctx->rxq_perchan; tx_channel_id = txqidx / ctx->txq_perchan; - rx_channel_id = rxqidx / ctx->rxq_perchan; + rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[portno]); chcr_req->wreq.op_to_cctx_size = FILL_WR_OP_CCTX_SIZE; @@ -797,15 +793,13 @@ static inline void create_wreq(struct chcr_context *ctx, /** * create_cipher_wr - form the WR for cipher operations - * @req: cipher req. - * @ctx: crypto driver context of the request. - * @qid: ingress qid where response of this WR should be received. - * @op_type: encryption or decryption + * @wrparam: Container for create_cipher_wr()'s parameters */ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(wrparam->req); struct chcr_context *ctx = c_ctx(tfm); + struct uld_ctx *u_ctx = ULD_CTX(ctx); struct ablk_ctx *ablkctx = ABLK_CTX(ctx); struct sk_buff *skb = NULL; struct chcr_wr *chcr_req; @@ -822,6 +816,7 @@ static struct sk_buff *create_cipher_wr(struct cipher_wr_param *wrparam) struct adapter *adap = padap(ctx->dev); unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan; + rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]); nents = sg_nents_xlen(reqctx->dstsg, wrparam->bytes, CHCR_DST_SG_SIZE, reqctx->dst_ofst); dst_size = get_space_for_phys_dsgl(nents); @@ -1559,7 +1554,8 @@ static inline void chcr_free_shash(struct crypto_shash *base_hash) /** * create_hash_wr - Create hash work request - * @req - Cipher req base + * @req: Cipher req base + * @param: Container for create_hash_wr()'s parameters */ static struct sk_buff *create_hash_wr(struct ahash_request *req, struct hash_wr_param *param) @@ -1580,6 +1576,7 @@ static struct sk_buff *create_hash_wr(struct ahash_request *req, int error = 0; unsigned int rx_channel_id = req_ctx->rxqidx / ctx->rxq_perchan; + rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]); transhdr_len = HASH_TRANSHDR_SIZE(param->kctx_len); req_ctx->hctx_wr.imm = (transhdr_len + param->bfr_len + param->sg_len) <= SGE_MAX_WR_LEN; @@ -2438,6 +2435,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req, { struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct chcr_context *ctx = a_ctx(tfm); + struct uld_ctx *u_ctx = ULD_CTX(ctx); struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx); struct chcr_authenc_ctx *actx = AUTHENC_CTX(aeadctx); struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); @@ -2457,6 +2455,7 @@ static struct sk_buff *create_authenc_wr(struct aead_request *req, struct adapter *adap = padap(ctx->dev); unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan; + rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]); if (req->cryptlen == 0) return NULL; @@ -2710,9 +2709,11 @@ void chcr_add_aead_dst_ent(struct aead_request *req, struct dsgl_walk dsgl_walk; unsigned int authsize = crypto_aead_authsize(tfm); struct chcr_context *ctx = a_ctx(tfm); + struct uld_ctx *u_ctx = ULD_CTX(ctx); u32 temp; unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan; + rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]); dsgl_walk_init(&dsgl_walk, phys_cpl); dsgl_walk_add_page(&dsgl_walk, IV + reqctx->b0_len, reqctx->iv_dma); temp = req->assoclen + req->cryptlen + @@ -2752,9 +2753,11 @@ void chcr_add_cipher_dst_ent(struct skcipher_request *req, struct chcr_skcipher_req_ctx *reqctx = skcipher_request_ctx(req); struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(wrparam->req); struct chcr_context *ctx = c_ctx(tfm); + struct uld_ctx *u_ctx = ULD_CTX(ctx); struct dsgl_walk dsgl_walk; unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan; + rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]); dsgl_walk_init(&dsgl_walk, phys_cpl); dsgl_walk_add_sg(&dsgl_walk, reqctx->dstsg, wrparam->bytes, reqctx->dst_ofst); @@ -2958,6 +2961,7 @@ static void fill_sec_cpl_for_aead(struct cpl_tx_sec_pdu *sec_cpl, { struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct chcr_context *ctx = a_ctx(tfm); + struct uld_ctx *u_ctx = ULD_CTX(ctx); struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx); struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); unsigned int cipher_mode = CHCR_SCMD_CIPHER_MODE_AES_CCM; @@ -2967,6 +2971,8 @@ static void fill_sec_cpl_for_aead(struct cpl_tx_sec_pdu *sec_cpl, unsigned int tag_offset = 0, auth_offset = 0; unsigned int assoclen; + rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]); + if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4309) assoclen = req->assoclen - 8; else @@ -3127,6 +3133,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, { struct crypto_aead *tfm = crypto_aead_reqtfm(req); struct chcr_context *ctx = a_ctx(tfm); + struct uld_ctx *u_ctx = ULD_CTX(ctx); struct chcr_aead_ctx *aeadctx = AEAD_CTX(ctx); struct chcr_aead_reqctx *reqctx = aead_request_ctx(req); struct sk_buff *skb = NULL; @@ -3143,6 +3150,7 @@ static struct sk_buff *create_gcm_wr(struct aead_request *req, struct adapter *adap = padap(ctx->dev); unsigned int rx_channel_id = reqctx->rxqidx / ctx->rxq_perchan; + rx_channel_id = cxgb4_port_e2cchan(u_ctx->lldi.ports[rx_channel_id]); if (get_aead_subtype(tfm) == CRYPTO_ALG_SUB_TYPE_AEAD_RFC4106) assoclen = req->assoclen - 8; diff --git a/drivers/crypto/chelsio/chcr_core.c b/drivers/crypto/chelsio/chcr_core.c index f91f9d762a45..39c70e6255f9 100644 --- a/drivers/crypto/chelsio/chcr_core.c +++ b/drivers/crypto/chelsio/chcr_core.c @@ -1,4 +1,4 @@ -/** +/* * This file is part of the Chelsio T4/T5/T6 Ethernet driver for Linux. * * Copyright (C) 2011-2016 Chelsio Communications. All rights reserved. @@ -184,7 +184,7 @@ static void *chcr_uld_add(const struct cxgb4_lld_info *lld) struct uld_ctx *u_ctx; /* Create the device and add it in the device list */ - pr_info_once("%s - version %s\n", DRV_DESC, DRV_VERSION); + pr_info_once("%s\n", DRV_DESC); if (!(lld->ulp_crypto & ULP_CRYPTO_LOOKASIDE)) return ERR_PTR(-EOPNOTSUPP); @@ -309,4 +309,3 @@ module_exit(chcr_crypto_exit); MODULE_DESCRIPTION("Crypto Co-processor for Chelsio Terminator cards."); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Chelsio Communications"); -MODULE_VERSION(DRV_VERSION); diff --git a/drivers/crypto/chelsio/chcr_core.h b/drivers/crypto/chelsio/chcr_core.h index b02f981e7c32..f7c8bb95a71b 100644 --- a/drivers/crypto/chelsio/chcr_core.h +++ b/drivers/crypto/chelsio/chcr_core.h @@ -44,7 +44,6 @@ #include "cxgb4_uld.h" #define DRV_MODULE_NAME "chcr" -#define DRV_VERSION "1.0.0.0-ko" #define DRV_DESC "Chelsio T6 Crypto Co-processor Driver" #define MAX_PENDING_REQ_TO_HW 20 diff --git a/drivers/crypto/geode-aes.c b/drivers/crypto/geode-aes.c index 4ee010f39912..fa5a9f207bc9 100644 --- a/drivers/crypto/geode-aes.c +++ b/drivers/crypto/geode-aes.c @@ -21,7 +21,7 @@ /* Static structures */ static void __iomem *_iobase; -static spinlock_t lock; +static DEFINE_SPINLOCK(lock); /* Write a 128 bit field (either a writable key or IV) */ static inline void @@ -383,8 +383,6 @@ static int geode_aes_probe(struct pci_dev *dev, const struct pci_device_id *id) goto erequest; } - spin_lock_init(&lock); - /* Clear any pending activity */ iowrite32(AES_INTR_PENDING | AES_INTR_MASK, _iobase + AES_INTR_REG); diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig index 843192666dc3..e572f9982d4e 100644 --- a/drivers/crypto/hisilicon/Kconfig +++ b/drivers/crypto/hisilicon/Kconfig @@ -68,6 +68,8 @@ config CRYPTO_DEV_HISI_HPRE select CRYPTO_DEV_HISI_QM select CRYPTO_DH select CRYPTO_RSA + select CRYPTO_CURVE25519 + select CRYPTO_ECDH help Support for HiSilicon HPRE(High Performance RSA Engine) accelerator, which can accelerate RSA and DH algorithms. diff --git a/drivers/crypto/hisilicon/hpre/hpre.h b/drivers/crypto/hisilicon/hpre/hpre.h index 181c109b19f7..e0b4a1982ee9 100644 --- a/drivers/crypto/hisilicon/hpre/hpre.h +++ b/drivers/crypto/hisilicon/hpre/hpre.h @@ -10,6 +10,14 @@ #define HPRE_PF_DEF_Q_NUM 64 #define HPRE_PF_DEF_Q_BASE 0 +/* + * type used in qm sqc DW6. + * 0 - Algorithm which has been supported in V2, like RSA, DH and so on; + * 1 - ECC algorithm in V3. + */ +#define HPRE_V2_ALG_TYPE 0 +#define HPRE_V3_ECC_ALG_TYPE 1 + enum { HPRE_CLUSTER0, HPRE_CLUSTER1, @@ -18,7 +26,6 @@ enum { }; enum hpre_ctrl_dbgfs_file { - HPRE_CURRENT_QM, HPRE_CLEAR_ENABLE, HPRE_CLUSTER_CTRL, HPRE_DEBUG_FILE_NUM, @@ -75,6 +82,9 @@ enum hpre_alg_type { HPRE_ALG_KG_CRT = 0x3, HPRE_ALG_DH_G2 = 0x4, HPRE_ALG_DH = 0x5, + HPRE_ALG_ECC_MUL = 0xD, + /* shared by x25519 and x448, but x448 is not supported now */ + HPRE_ALG_CURVE25519_MUL = 0x10, }; struct hpre_sqe { @@ -92,8 +102,8 @@ struct hpre_sqe { __le32 rsvd1[_HPRE_SQE_ALIGN_EXT]; }; -struct hisi_qp *hpre_create_qp(void); -int hpre_algs_register(void); -void hpre_algs_unregister(void); +struct hisi_qp *hpre_create_qp(u8 type); +int hpre_algs_register(struct hisi_qm *qm); +void hpre_algs_unregister(struct hisi_qm *qm); #endif diff --git a/drivers/crypto/hisilicon/hpre/hpre_crypto.c b/drivers/crypto/hisilicon/hpre/hpre_crypto.c index a87f9904087a..a380087c83f7 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_crypto.c +++ b/drivers/crypto/hisilicon/hpre/hpre_crypto.c @@ -1,7 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 HiSilicon Limited. */ #include <crypto/akcipher.h> +#include <crypto/curve25519.h> #include <crypto/dh.h> +#include <crypto/ecc_curve.h> +#include <crypto/ecdh.h> #include <crypto/internal/akcipher.h> #include <crypto/internal/kpp.h> #include <crypto/internal/rsa.h> @@ -36,6 +39,13 @@ struct hpre_ctx; #define HPRE_DFX_SEC_TO_US 1000000 #define HPRE_DFX_US_TO_NS 1000 +/* size in bytes of the n prime */ +#define HPRE_ECC_NIST_P192_N_SIZE 24 +#define HPRE_ECC_NIST_P256_N_SIZE 32 + +/* size in bytes */ +#define HPRE_ECC_HW256_KSZ_B 32 + typedef void (*hpre_cb)(struct hpre_ctx *ctx, void *sqe); struct hpre_rsa_ctx { @@ -61,14 +71,35 @@ struct hpre_dh_ctx { * else if base if the counterpart public key we * compute the shared secret * ZZ = yb^xa mod p; [RFC2631 sec 2.1.1] + * low address: d--->n, please refer to Hisilicon HPRE UM */ - char *xa_p; /* low address: d--->n, please refer to Hisilicon HPRE UM */ + char *xa_p; dma_addr_t dma_xa_p; char *g; /* m */ dma_addr_t dma_g; }; +struct hpre_ecdh_ctx { + /* low address: p->a->k->b */ + unsigned char *p; + dma_addr_t dma_p; + + /* low address: x->y */ + unsigned char *g; + dma_addr_t dma_g; +}; + +struct hpre_curve25519_ctx { + /* low address: p->a->k */ + unsigned char *p; + dma_addr_t dma_p; + + /* gx coordinate */ + unsigned char *g; + dma_addr_t dma_g; +}; + struct hpre_ctx { struct hisi_qp *qp; struct hpre_asym_request **req_list; @@ -80,7 +111,11 @@ struct hpre_ctx { union { struct hpre_rsa_ctx rsa; struct hpre_dh_ctx dh; + struct hpre_ecdh_ctx ecdh; + struct hpre_curve25519_ctx curve25519; }; + /* for ecc algorithms */ + unsigned int curve_id; }; struct hpre_asym_request { @@ -91,6 +126,8 @@ struct hpre_asym_request { union { struct akcipher_request *rsa; struct kpp_request *dh; + struct kpp_request *ecdh; + struct kpp_request *curve25519; } areq; int err; int req_id; @@ -152,12 +189,12 @@ static void hpre_rm_req_from_ctx(struct hpre_asym_request *hpre_req) } } -static struct hisi_qp *hpre_get_qp_and_start(void) +static struct hisi_qp *hpre_get_qp_and_start(u8 type) { struct hisi_qp *qp; int ret; - qp = hpre_create_qp(); + qp = hpre_create_qp(type); if (!qp) { pr_err("Can not create hpre qp!\n"); return ERR_PTR(-ENODEV); @@ -261,8 +298,6 @@ static void hpre_hw_data_clr_all(struct hpre_ctx *ctx, dma_addr_t tmp; tmp = le64_to_cpu(sqe->in); - if (unlikely(!tmp)) - return; if (src) { if (req->src) @@ -272,8 +307,6 @@ static void hpre_hw_data_clr_all(struct hpre_ctx *ctx, } tmp = le64_to_cpu(sqe->out); - if (unlikely(!tmp)) - return; if (req->dst) { if (dst) @@ -288,13 +321,16 @@ static void hpre_hw_data_clr_all(struct hpre_ctx *ctx, static int hpre_alg_res_post_hf(struct hpre_ctx *ctx, struct hpre_sqe *sqe, void **kreq) { + struct device *dev = HPRE_DEV(ctx); struct hpre_asym_request *req; - int err, id, done; + unsigned int err, done, alg; + int id; #define HPRE_NO_HW_ERR 0 #define HPRE_HW_TASK_DONE 3 #define HREE_HW_ERR_MASK 0x7ff #define HREE_SQE_DONE_MASK 0x3 +#define HREE_ALG_TYPE_MASK 0x1f id = (int)le16_to_cpu(sqe->tag); req = ctx->req_list[id]; hpre_rm_req_from_ctx(req); @@ -307,7 +343,11 @@ static int hpre_alg_res_post_hf(struct hpre_ctx *ctx, struct hpre_sqe *sqe, HREE_SQE_DONE_MASK; if (likely(err == HPRE_NO_HW_ERR && done == HPRE_HW_TASK_DONE)) - return 0; + return 0; + + alg = le32_to_cpu(sqe->dw0) & HREE_ALG_TYPE_MASK; + dev_err_ratelimited(dev, "alg[0x%x] error: done[0x%x], etype[0x%x]\n", + alg, done, err); return -EINVAL; } @@ -413,7 +453,6 @@ static void hpre_alg_cb(struct hisi_qp *qp, void *resp) struct hpre_sqe *sqe = resp; struct hpre_asym_request *req = ctx->req_list[le16_to_cpu(sqe->tag)]; - if (unlikely(!req)) { atomic64_inc(&dfx[HPRE_INVALID_REQ_CNT].value); return; @@ -422,18 +461,29 @@ static void hpre_alg_cb(struct hisi_qp *qp, void *resp) req->cb(ctx, resp); } -static int hpre_ctx_init(struct hpre_ctx *ctx) +static void hpre_stop_qp_and_put(struct hisi_qp *qp) +{ + hisi_qm_stop_qp(qp); + hisi_qm_free_qps(&qp, 1); +} + +static int hpre_ctx_init(struct hpre_ctx *ctx, u8 type) { struct hisi_qp *qp; + int ret; - qp = hpre_get_qp_and_start(); + qp = hpre_get_qp_and_start(type); if (IS_ERR(qp)) return PTR_ERR(qp); qp->qp_ctx = ctx; qp->req_cb = hpre_alg_cb; - return hpre_ctx_set(ctx, qp, QM_Q_DEPTH); + ret = hpre_ctx_set(ctx, qp, QM_Q_DEPTH); + if (ret) + hpre_stop_qp_and_put(qp); + + return ret; } static int hpre_msg_request_set(struct hpre_ctx *ctx, void *req, bool is_rsa) @@ -510,7 +560,6 @@ static int hpre_send(struct hpre_ctx *ctx, struct hpre_sqe *msg) return ret; } -#ifdef CONFIG_CRYPTO_DH static int hpre_dh_compute_value(struct kpp_request *req) { struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); @@ -674,7 +723,7 @@ static int hpre_dh_init_tfm(struct crypto_kpp *tfm) { struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); - return hpre_ctx_init(ctx); + return hpre_ctx_init(ctx, HPRE_V2_ALG_TYPE); } static void hpre_dh_exit_tfm(struct crypto_kpp *tfm) @@ -683,7 +732,6 @@ static void hpre_dh_exit_tfm(struct crypto_kpp *tfm) hpre_dh_clear_ctx(ctx, true); } -#endif static void hpre_rsa_drop_leading_zeros(const char **ptr, size_t *len) { @@ -1100,7 +1148,7 @@ static int hpre_rsa_init_tfm(struct crypto_akcipher *tfm) return PTR_ERR(ctx->rsa.soft_tfm); } - ret = hpre_ctx_init(ctx); + ret = hpre_ctx_init(ctx, HPRE_V2_ALG_TYPE); if (ret) crypto_free_akcipher(ctx->rsa.soft_tfm); @@ -1115,6 +1163,734 @@ static void hpre_rsa_exit_tfm(struct crypto_akcipher *tfm) crypto_free_akcipher(ctx->rsa.soft_tfm); } +static void hpre_key_to_big_end(u8 *data, int len) +{ + int i, j; + u8 tmp; + + for (i = 0; i < len / 2; i++) { + j = len - i - 1; + tmp = data[j]; + data[j] = data[i]; + data[i] = tmp; + } +} + +static void hpre_ecc_clear_ctx(struct hpre_ctx *ctx, bool is_clear_all, + bool is_ecdh) +{ + struct device *dev = HPRE_DEV(ctx); + unsigned int sz = ctx->key_sz; + unsigned int shift = sz << 1; + + if (is_clear_all) + hisi_qm_stop_qp(ctx->qp); + + if (is_ecdh && ctx->ecdh.p) { + /* ecdh: p->a->k->b */ + memzero_explicit(ctx->ecdh.p + shift, sz); + dma_free_coherent(dev, sz << 3, ctx->ecdh.p, ctx->ecdh.dma_p); + ctx->ecdh.p = NULL; + } else if (!is_ecdh && ctx->curve25519.p) { + /* curve25519: p->a->k */ + memzero_explicit(ctx->curve25519.p + shift, sz); + dma_free_coherent(dev, sz << 2, ctx->curve25519.p, + ctx->curve25519.dma_p); + ctx->curve25519.p = NULL; + } + + hpre_ctx_clear(ctx, is_clear_all); +} + +static unsigned int hpre_ecdh_supported_curve(unsigned short id) +{ + switch (id) { + case ECC_CURVE_NIST_P192: + case ECC_CURVE_NIST_P256: + return HPRE_ECC_HW256_KSZ_B; + default: + break; + } + + return 0; +} + +static void fill_curve_param(void *addr, u64 *param, unsigned int cur_sz, u8 ndigits) +{ + unsigned int sz = cur_sz - (ndigits - 1) * sizeof(u64); + u8 i = 0; + + while (i < ndigits - 1) { + memcpy(addr + sizeof(u64) * i, ¶m[i], sizeof(u64)); + i++; + } + + memcpy(addr + sizeof(u64) * i, ¶m[ndigits - 1], sz); + hpre_key_to_big_end((u8 *)addr, cur_sz); +} + +static int hpre_ecdh_fill_curve(struct hpre_ctx *ctx, struct ecdh *params, + unsigned int cur_sz) +{ + unsigned int shifta = ctx->key_sz << 1; + unsigned int shiftb = ctx->key_sz << 2; + void *p = ctx->ecdh.p + ctx->key_sz - cur_sz; + void *a = ctx->ecdh.p + shifta - cur_sz; + void *b = ctx->ecdh.p + shiftb - cur_sz; + void *x = ctx->ecdh.g + ctx->key_sz - cur_sz; + void *y = ctx->ecdh.g + shifta - cur_sz; + const struct ecc_curve *curve = ecc_get_curve(ctx->curve_id); + char *n; + + if (unlikely(!curve)) + return -EINVAL; + + n = kzalloc(ctx->key_sz, GFP_KERNEL); + if (!n) + return -ENOMEM; + + fill_curve_param(p, curve->p, cur_sz, curve->g.ndigits); + fill_curve_param(a, curve->a, cur_sz, curve->g.ndigits); + fill_curve_param(b, curve->b, cur_sz, curve->g.ndigits); + fill_curve_param(x, curve->g.x, cur_sz, curve->g.ndigits); + fill_curve_param(y, curve->g.y, cur_sz, curve->g.ndigits); + fill_curve_param(n, curve->n, cur_sz, curve->g.ndigits); + + if (params->key_size == cur_sz && memcmp(params->key, n, cur_sz) >= 0) { + kfree(n); + return -EINVAL; + } + + kfree(n); + return 0; +} + +static unsigned int hpre_ecdh_get_curvesz(unsigned short id) +{ + switch (id) { + case ECC_CURVE_NIST_P192: + return HPRE_ECC_NIST_P192_N_SIZE; + case ECC_CURVE_NIST_P256: + return HPRE_ECC_NIST_P256_N_SIZE; + default: + break; + } + + return 0; +} + +static int hpre_ecdh_set_param(struct hpre_ctx *ctx, struct ecdh *params) +{ + struct device *dev = HPRE_DEV(ctx); + unsigned int sz, shift, curve_sz; + int ret; + + ctx->key_sz = hpre_ecdh_supported_curve(ctx->curve_id); + if (!ctx->key_sz) + return -EINVAL; + + curve_sz = hpre_ecdh_get_curvesz(ctx->curve_id); + if (!curve_sz || params->key_size > curve_sz) + return -EINVAL; + + sz = ctx->key_sz; + + if (!ctx->ecdh.p) { + ctx->ecdh.p = dma_alloc_coherent(dev, sz << 3, &ctx->ecdh.dma_p, + GFP_KERNEL); + if (!ctx->ecdh.p) + return -ENOMEM; + } + + shift = sz << 2; + ctx->ecdh.g = ctx->ecdh.p + shift; + ctx->ecdh.dma_g = ctx->ecdh.dma_p + shift; + + ret = hpre_ecdh_fill_curve(ctx, params, curve_sz); + if (ret) { + dev_err(dev, "failed to fill curve_param, ret = %d!\n", ret); + dma_free_coherent(dev, sz << 3, ctx->ecdh.p, ctx->ecdh.dma_p); + ctx->ecdh.p = NULL; + return ret; + } + + return 0; +} + +static bool hpre_key_is_zero(char *key, unsigned short key_sz) +{ + int i; + + for (i = 0; i < key_sz; i++) + if (key[i]) + return false; + + return true; +} + +static int hpre_ecdh_set_secret(struct crypto_kpp *tfm, const void *buf, + unsigned int len) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + struct device *dev = HPRE_DEV(ctx); + unsigned int sz, sz_shift; + struct ecdh params; + int ret; + + if (crypto_ecdh_decode_key(buf, len, ¶ms) < 0) { + dev_err(dev, "failed to decode ecdh key!\n"); + return -EINVAL; + } + + if (hpre_key_is_zero(params.key, params.key_size)) { + dev_err(dev, "Invalid hpre key!\n"); + return -EINVAL; + } + + hpre_ecc_clear_ctx(ctx, false, true); + + ret = hpre_ecdh_set_param(ctx, ¶ms); + if (ret < 0) { + dev_err(dev, "failed to set hpre param, ret = %d!\n", ret); + return ret; + } + + sz = ctx->key_sz; + sz_shift = (sz << 1) + sz - params.key_size; + memcpy(ctx->ecdh.p + sz_shift, params.key, params.key_size); + + return 0; +} + +static void hpre_ecdh_hw_data_clr_all(struct hpre_ctx *ctx, + struct hpre_asym_request *req, + struct scatterlist *dst, + struct scatterlist *src) +{ + struct device *dev = HPRE_DEV(ctx); + struct hpre_sqe *sqe = &req->req; + dma_addr_t dma; + + dma = le64_to_cpu(sqe->in); + + if (src && req->src) + dma_free_coherent(dev, ctx->key_sz << 2, req->src, dma); + + dma = le64_to_cpu(sqe->out); + + if (req->dst) + dma_free_coherent(dev, ctx->key_sz << 1, req->dst, dma); + if (dst) + dma_unmap_single(dev, dma, ctx->key_sz << 1, DMA_FROM_DEVICE); +} + +static void hpre_ecdh_cb(struct hpre_ctx *ctx, void *resp) +{ + unsigned int curve_sz = hpre_ecdh_get_curvesz(ctx->curve_id); + struct hpre_dfx *dfx = ctx->hpre->debug.dfx; + struct hpre_asym_request *req = NULL; + struct kpp_request *areq; + u64 overtime_thrhld; + char *p; + int ret; + + ret = hpre_alg_res_post_hf(ctx, resp, (void **)&req); + areq = req->areq.ecdh; + areq->dst_len = ctx->key_sz << 1; + + overtime_thrhld = atomic64_read(&dfx[HPRE_OVERTIME_THRHLD].value); + if (overtime_thrhld && hpre_is_bd_timeout(req, overtime_thrhld)) + atomic64_inc(&dfx[HPRE_OVER_THRHLD_CNT].value); + + p = sg_virt(areq->dst); + memmove(p, p + ctx->key_sz - curve_sz, curve_sz); + memmove(p + curve_sz, p + areq->dst_len - curve_sz, curve_sz); + + hpre_ecdh_hw_data_clr_all(ctx, req, areq->dst, areq->src); + kpp_request_complete(areq, ret); + + atomic64_inc(&dfx[HPRE_RECV_CNT].value); +} + +static int hpre_ecdh_msg_request_set(struct hpre_ctx *ctx, + struct kpp_request *req) +{ + struct hpre_asym_request *h_req; + struct hpre_sqe *msg; + int req_id; + void *tmp; + + if (req->dst_len < ctx->key_sz << 1) { + req->dst_len = ctx->key_sz << 1; + return -EINVAL; + } + + tmp = kpp_request_ctx(req); + h_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ); + h_req->cb = hpre_ecdh_cb; + h_req->areq.ecdh = req; + msg = &h_req->req; + memset(msg, 0, sizeof(*msg)); + msg->key = cpu_to_le64(ctx->ecdh.dma_p); + + msg->dw0 |= cpu_to_le32(0x1U << HPRE_SQE_DONE_SHIFT); + msg->task_len1 = (ctx->key_sz >> HPRE_BITS_2_BYTES_SHIFT) - 1; + h_req->ctx = ctx; + + req_id = hpre_add_req_to_ctx(h_req); + if (req_id < 0) + return -EBUSY; + + msg->tag = cpu_to_le16((u16)req_id); + return 0; +} + +static int hpre_ecdh_src_data_init(struct hpre_asym_request *hpre_req, + struct scatterlist *data, unsigned int len) +{ + struct hpre_sqe *msg = &hpre_req->req; + struct hpre_ctx *ctx = hpre_req->ctx; + struct device *dev = HPRE_DEV(ctx); + unsigned int tmpshift; + dma_addr_t dma = 0; + void *ptr; + int shift; + + /* Src_data include gx and gy. */ + shift = ctx->key_sz - (len >> 1); + if (unlikely(shift < 0)) + return -EINVAL; + + ptr = dma_alloc_coherent(dev, ctx->key_sz << 2, &dma, GFP_KERNEL); + if (unlikely(!ptr)) + return -ENOMEM; + + tmpshift = ctx->key_sz << 1; + scatterwalk_map_and_copy(ptr + tmpshift, data, 0, len, 0); + memcpy(ptr + shift, ptr + tmpshift, len >> 1); + memcpy(ptr + ctx->key_sz + shift, ptr + tmpshift + (len >> 1), len >> 1); + + hpre_req->src = ptr; + msg->in = cpu_to_le64(dma); + return 0; +} + +static int hpre_ecdh_dst_data_init(struct hpre_asym_request *hpre_req, + struct scatterlist *data, unsigned int len) +{ + struct hpre_sqe *msg = &hpre_req->req; + struct hpre_ctx *ctx = hpre_req->ctx; + struct device *dev = HPRE_DEV(ctx); + dma_addr_t dma = 0; + + if (unlikely(!data || !sg_is_last(data) || len != ctx->key_sz << 1)) { + dev_err(dev, "data or data length is illegal!\n"); + return -EINVAL; + } + + hpre_req->dst = NULL; + dma = dma_map_single(dev, sg_virt(data), len, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(dev, dma))) { + dev_err(dev, "dma map data err!\n"); + return -ENOMEM; + } + + msg->out = cpu_to_le64(dma); + return 0; +} + +static int hpre_ecdh_compute_value(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + struct device *dev = HPRE_DEV(ctx); + void *tmp = kpp_request_ctx(req); + struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ); + struct hpre_sqe *msg = &hpre_req->req; + int ret; + + ret = hpre_ecdh_msg_request_set(ctx, req); + if (unlikely(ret)) { + dev_err(dev, "failed to set ecdh request, ret = %d!\n", ret); + return ret; + } + + if (req->src) { + ret = hpre_ecdh_src_data_init(hpre_req, req->src, req->src_len); + if (unlikely(ret)) { + dev_err(dev, "failed to init src data, ret = %d!\n", ret); + goto clear_all; + } + } else { + msg->in = cpu_to_le64(ctx->ecdh.dma_g); + } + + ret = hpre_ecdh_dst_data_init(hpre_req, req->dst, req->dst_len); + if (unlikely(ret)) { + dev_err(dev, "failed to init dst data, ret = %d!\n", ret); + goto clear_all; + } + + msg->dw0 = cpu_to_le32(le32_to_cpu(msg->dw0) | HPRE_ALG_ECC_MUL); + ret = hpre_send(ctx, msg); + if (likely(!ret)) + return -EINPROGRESS; + +clear_all: + hpre_rm_req_from_ctx(hpre_req); + hpre_ecdh_hw_data_clr_all(ctx, hpre_req, req->dst, req->src); + return ret; +} + +static unsigned int hpre_ecdh_max_size(struct crypto_kpp *tfm) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + + /* max size is the pub_key_size, include x and y */ + return ctx->key_sz << 1; +} + +static int hpre_ecdh_nist_p192_init_tfm(struct crypto_kpp *tfm) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + + ctx->curve_id = ECC_CURVE_NIST_P192; + + return hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE); +} + +static int hpre_ecdh_nist_p256_init_tfm(struct crypto_kpp *tfm) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + + ctx->curve_id = ECC_CURVE_NIST_P256; + + return hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE); +} + +static void hpre_ecdh_exit_tfm(struct crypto_kpp *tfm) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + + hpre_ecc_clear_ctx(ctx, true, true); +} + +static void hpre_curve25519_fill_curve(struct hpre_ctx *ctx, const void *buf, + unsigned int len) +{ + u8 secret[CURVE25519_KEY_SIZE] = { 0 }; + unsigned int sz = ctx->key_sz; + const struct ecc_curve *curve; + unsigned int shift = sz << 1; + void *p; + + /* + * The key from 'buf' is in little-endian, we should preprocess it as + * the description in rfc7748: "k[0] &= 248, k[31] &= 127, k[31] |= 64", + * then convert it to big endian. Only in this way, the result can be + * the same as the software curve-25519 that exists in crypto. + */ + memcpy(secret, buf, len); + curve25519_clamp_secret(secret); + hpre_key_to_big_end(secret, CURVE25519_KEY_SIZE); + + p = ctx->curve25519.p + sz - len; + + curve = ecc_get_curve25519(); + + /* fill curve parameters */ + fill_curve_param(p, curve->p, len, curve->g.ndigits); + fill_curve_param(p + sz, curve->a, len, curve->g.ndigits); + memcpy(p + shift, secret, len); + fill_curve_param(p + shift + sz, curve->g.x, len, curve->g.ndigits); + memzero_explicit(secret, CURVE25519_KEY_SIZE); +} + +static int hpre_curve25519_set_param(struct hpre_ctx *ctx, const void *buf, + unsigned int len) +{ + struct device *dev = HPRE_DEV(ctx); + unsigned int sz = ctx->key_sz; + unsigned int shift = sz << 1; + + /* p->a->k->gx */ + if (!ctx->curve25519.p) { + ctx->curve25519.p = dma_alloc_coherent(dev, sz << 2, + &ctx->curve25519.dma_p, + GFP_KERNEL); + if (!ctx->curve25519.p) + return -ENOMEM; + } + + ctx->curve25519.g = ctx->curve25519.p + shift + sz; + ctx->curve25519.dma_g = ctx->curve25519.dma_p + shift + sz; + + hpre_curve25519_fill_curve(ctx, buf, len); + + return 0; +} + +static int hpre_curve25519_set_secret(struct crypto_kpp *tfm, const void *buf, + unsigned int len) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + struct device *dev = HPRE_DEV(ctx); + int ret = -EINVAL; + + if (len != CURVE25519_KEY_SIZE || + !crypto_memneq(buf, curve25519_null_point, CURVE25519_KEY_SIZE)) { + dev_err(dev, "key is null or key len is not 32bytes!\n"); + return ret; + } + + /* Free old secret if any */ + hpre_ecc_clear_ctx(ctx, false, false); + + ctx->key_sz = CURVE25519_KEY_SIZE; + ret = hpre_curve25519_set_param(ctx, buf, CURVE25519_KEY_SIZE); + if (ret) { + dev_err(dev, "failed to set curve25519 param, ret = %d!\n", ret); + hpre_ecc_clear_ctx(ctx, false, false); + return ret; + } + + return 0; +} + +static void hpre_curve25519_hw_data_clr_all(struct hpre_ctx *ctx, + struct hpre_asym_request *req, + struct scatterlist *dst, + struct scatterlist *src) +{ + struct device *dev = HPRE_DEV(ctx); + struct hpre_sqe *sqe = &req->req; + dma_addr_t dma; + + dma = le64_to_cpu(sqe->in); + + if (src && req->src) + dma_free_coherent(dev, ctx->key_sz, req->src, dma); + + dma = le64_to_cpu(sqe->out); + + if (req->dst) + dma_free_coherent(dev, ctx->key_sz, req->dst, dma); + if (dst) + dma_unmap_single(dev, dma, ctx->key_sz, DMA_FROM_DEVICE); +} + +static void hpre_curve25519_cb(struct hpre_ctx *ctx, void *resp) +{ + struct hpre_dfx *dfx = ctx->hpre->debug.dfx; + struct hpre_asym_request *req = NULL; + struct kpp_request *areq; + u64 overtime_thrhld; + int ret; + + ret = hpre_alg_res_post_hf(ctx, resp, (void **)&req); + areq = req->areq.curve25519; + areq->dst_len = ctx->key_sz; + + overtime_thrhld = atomic64_read(&dfx[HPRE_OVERTIME_THRHLD].value); + if (overtime_thrhld && hpre_is_bd_timeout(req, overtime_thrhld)) + atomic64_inc(&dfx[HPRE_OVER_THRHLD_CNT].value); + + hpre_key_to_big_end(sg_virt(areq->dst), CURVE25519_KEY_SIZE); + + hpre_curve25519_hw_data_clr_all(ctx, req, areq->dst, areq->src); + kpp_request_complete(areq, ret); + + atomic64_inc(&dfx[HPRE_RECV_CNT].value); +} + +static int hpre_curve25519_msg_request_set(struct hpre_ctx *ctx, + struct kpp_request *req) +{ + struct hpre_asym_request *h_req; + struct hpre_sqe *msg; + int req_id; + void *tmp; + + if (unlikely(req->dst_len < ctx->key_sz)) { + req->dst_len = ctx->key_sz; + return -EINVAL; + } + + tmp = kpp_request_ctx(req); + h_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ); + h_req->cb = hpre_curve25519_cb; + h_req->areq.curve25519 = req; + msg = &h_req->req; + memset(msg, 0, sizeof(*msg)); + msg->key = cpu_to_le64(ctx->curve25519.dma_p); + + msg->dw0 |= cpu_to_le32(0x1U << HPRE_SQE_DONE_SHIFT); + msg->task_len1 = (ctx->key_sz >> HPRE_BITS_2_BYTES_SHIFT) - 1; + h_req->ctx = ctx; + + req_id = hpre_add_req_to_ctx(h_req); + if (req_id < 0) + return -EBUSY; + + msg->tag = cpu_to_le16((u16)req_id); + return 0; +} + +static void hpre_curve25519_src_modulo_p(u8 *ptr) +{ + int i; + + for (i = 0; i < CURVE25519_KEY_SIZE - 1; i++) + ptr[i] = 0; + + /* The modulus is ptr's last byte minus '0xed'(last byte of p) */ + ptr[i] -= 0xed; +} + +static int hpre_curve25519_src_init(struct hpre_asym_request *hpre_req, + struct scatterlist *data, unsigned int len) +{ + struct hpre_sqe *msg = &hpre_req->req; + struct hpre_ctx *ctx = hpre_req->ctx; + struct device *dev = HPRE_DEV(ctx); + u8 p[CURVE25519_KEY_SIZE] = { 0 }; + const struct ecc_curve *curve; + dma_addr_t dma = 0; + u8 *ptr; + + if (len != CURVE25519_KEY_SIZE) { + dev_err(dev, "sourc_data len is not 32bytes, len = %u!\n", len); + return -EINVAL; + } + + ptr = dma_alloc_coherent(dev, ctx->key_sz, &dma, GFP_KERNEL); + if (unlikely(!ptr)) + return -ENOMEM; + + scatterwalk_map_and_copy(ptr, data, 0, len, 0); + + if (!crypto_memneq(ptr, curve25519_null_point, CURVE25519_KEY_SIZE)) { + dev_err(dev, "gx is null!\n"); + goto err; + } + + /* + * Src_data(gx) is in little-endian order, MSB in the final byte should + * be masked as described in RFC7748, then transform it to big-endian + * form, then hisi_hpre can use the data. + */ + ptr[31] &= 0x7f; + hpre_key_to_big_end(ptr, CURVE25519_KEY_SIZE); + + curve = ecc_get_curve25519(); + + fill_curve_param(p, curve->p, CURVE25519_KEY_SIZE, curve->g.ndigits); + + /* + * When src_data equals (2^255 - 19) ~ (2^255 - 1), it is out of p, + * we get its modulus to p, and then use it. + */ + if (memcmp(ptr, p, ctx->key_sz) >= 0) + hpre_curve25519_src_modulo_p(ptr); + + hpre_req->src = ptr; + msg->in = cpu_to_le64(dma); + return 0; + +err: + dma_free_coherent(dev, ctx->key_sz, ptr, dma); + return -EINVAL; +} + +static int hpre_curve25519_dst_init(struct hpre_asym_request *hpre_req, + struct scatterlist *data, unsigned int len) +{ + struct hpre_sqe *msg = &hpre_req->req; + struct hpre_ctx *ctx = hpre_req->ctx; + struct device *dev = HPRE_DEV(ctx); + dma_addr_t dma = 0; + + if (!data || !sg_is_last(data) || len != ctx->key_sz) { + dev_err(dev, "data or data length is illegal!\n"); + return -EINVAL; + } + + hpre_req->dst = NULL; + dma = dma_map_single(dev, sg_virt(data), len, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(dev, dma))) { + dev_err(dev, "dma map data err!\n"); + return -ENOMEM; + } + + msg->out = cpu_to_le64(dma); + return 0; +} + +static int hpre_curve25519_compute_value(struct kpp_request *req) +{ + struct crypto_kpp *tfm = crypto_kpp_reqtfm(req); + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + struct device *dev = HPRE_DEV(ctx); + void *tmp = kpp_request_ctx(req); + struct hpre_asym_request *hpre_req = PTR_ALIGN(tmp, HPRE_ALIGN_SZ); + struct hpre_sqe *msg = &hpre_req->req; + int ret; + + ret = hpre_curve25519_msg_request_set(ctx, req); + if (unlikely(ret)) { + dev_err(dev, "failed to set curve25519 request, ret = %d!\n", ret); + return ret; + } + + if (req->src) { + ret = hpre_curve25519_src_init(hpre_req, req->src, req->src_len); + if (unlikely(ret)) { + dev_err(dev, "failed to init src data, ret = %d!\n", + ret); + goto clear_all; + } + } else { + msg->in = cpu_to_le64(ctx->curve25519.dma_g); + } + + ret = hpre_curve25519_dst_init(hpre_req, req->dst, req->dst_len); + if (unlikely(ret)) { + dev_err(dev, "failed to init dst data, ret = %d!\n", ret); + goto clear_all; + } + + msg->dw0 = cpu_to_le32(le32_to_cpu(msg->dw0) | HPRE_ALG_CURVE25519_MUL); + ret = hpre_send(ctx, msg); + if (likely(!ret)) + return -EINPROGRESS; + +clear_all: + hpre_rm_req_from_ctx(hpre_req); + hpre_curve25519_hw_data_clr_all(ctx, hpre_req, req->dst, req->src); + return ret; +} + +static unsigned int hpre_curve25519_max_size(struct crypto_kpp *tfm) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + + return ctx->key_sz; +} + +static int hpre_curve25519_init_tfm(struct crypto_kpp *tfm) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + + return hpre_ctx_init(ctx, HPRE_V3_ECC_ALG_TYPE); +} + +static void hpre_curve25519_exit_tfm(struct crypto_kpp *tfm) +{ + struct hpre_ctx *ctx = kpp_tfm_ctx(tfm); + + hpre_ecc_clear_ctx(ctx, true, false); +} + static struct akcipher_alg rsa = { .sign = hpre_rsa_dec, .verify = hpre_rsa_enc, @@ -1135,7 +1911,6 @@ static struct akcipher_alg rsa = { }, }; -#ifdef CONFIG_CRYPTO_DH static struct kpp_alg dh = { .set_secret = hpre_dh_set_secret, .generate_public_key = hpre_dh_compute_value, @@ -1152,9 +1927,83 @@ static struct kpp_alg dh = { .cra_module = THIS_MODULE, }, }; -#endif -int hpre_algs_register(void) +static struct kpp_alg ecdh_nist_p192 = { + .set_secret = hpre_ecdh_set_secret, + .generate_public_key = hpre_ecdh_compute_value, + .compute_shared_secret = hpre_ecdh_compute_value, + .max_size = hpre_ecdh_max_size, + .init = hpre_ecdh_nist_p192_init_tfm, + .exit = hpre_ecdh_exit_tfm, + .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ, + .base = { + .cra_ctxsize = sizeof(struct hpre_ctx), + .cra_priority = HPRE_CRYPTO_ALG_PRI, + .cra_name = "ecdh-nist-p192", + .cra_driver_name = "hpre-ecdh", + .cra_module = THIS_MODULE, + }, +}; + +static struct kpp_alg ecdh_nist_p256 = { + .set_secret = hpre_ecdh_set_secret, + .generate_public_key = hpre_ecdh_compute_value, + .compute_shared_secret = hpre_ecdh_compute_value, + .max_size = hpre_ecdh_max_size, + .init = hpre_ecdh_nist_p256_init_tfm, + .exit = hpre_ecdh_exit_tfm, + .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ, + .base = { + .cra_ctxsize = sizeof(struct hpre_ctx), + .cra_priority = HPRE_CRYPTO_ALG_PRI, + .cra_name = "ecdh-nist-p256", + .cra_driver_name = "hpre-ecdh", + .cra_module = THIS_MODULE, + }, +}; + +static struct kpp_alg curve25519_alg = { + .set_secret = hpre_curve25519_set_secret, + .generate_public_key = hpre_curve25519_compute_value, + .compute_shared_secret = hpre_curve25519_compute_value, + .max_size = hpre_curve25519_max_size, + .init = hpre_curve25519_init_tfm, + .exit = hpre_curve25519_exit_tfm, + .reqsize = sizeof(struct hpre_asym_request) + HPRE_ALIGN_SZ, + .base = { + .cra_ctxsize = sizeof(struct hpre_ctx), + .cra_priority = HPRE_CRYPTO_ALG_PRI, + .cra_name = "curve25519", + .cra_driver_name = "hpre-curve25519", + .cra_module = THIS_MODULE, + }, +}; + + +static int hpre_register_ecdh(void) +{ + int ret; + + ret = crypto_register_kpp(&ecdh_nist_p192); + if (ret) + return ret; + + ret = crypto_register_kpp(&ecdh_nist_p256); + if (ret) { + crypto_unregister_kpp(&ecdh_nist_p192); + return ret; + } + + return 0; +} + +static void hpre_unregister_ecdh(void) +{ + crypto_unregister_kpp(&ecdh_nist_p256); + crypto_unregister_kpp(&ecdh_nist_p192); +} + +int hpre_algs_register(struct hisi_qm *qm) { int ret; @@ -1162,19 +2011,37 @@ int hpre_algs_register(void) ret = crypto_register_akcipher(&rsa); if (ret) return ret; -#ifdef CONFIG_CRYPTO_DH + ret = crypto_register_kpp(&dh); if (ret) - crypto_unregister_akcipher(&rsa); -#endif + goto unreg_rsa; + + if (qm->ver >= QM_HW_V3) { + ret = hpre_register_ecdh(); + if (ret) + goto unreg_dh; + ret = crypto_register_kpp(&curve25519_alg); + if (ret) + goto unreg_ecdh; + } + return 0; +unreg_ecdh: + hpre_unregister_ecdh(); +unreg_dh: + crypto_unregister_kpp(&dh); +unreg_rsa: + crypto_unregister_akcipher(&rsa); return ret; } -void hpre_algs_unregister(void) +void hpre_algs_unregister(struct hisi_qm *qm) { - crypto_unregister_akcipher(&rsa); -#ifdef CONFIG_CRYPTO_DH + if (qm->ver >= QM_HW_V3) { + crypto_unregister_kpp(&curve25519_alg); + hpre_unregister_ecdh(); + } + crypto_unregister_kpp(&dh); -#endif + crypto_unregister_akcipher(&rsa); } diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index e7a2c70eb9cf..046bc962c8b2 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -13,7 +13,6 @@ #include <linux/uacce.h> #include "hpre.h" -#define HPRE_QUEUE_NUM_V2 1024 #define HPRE_QM_ABNML_INT_MASK 0x100004 #define HPRE_CTRL_CNT_CLR_CE_BIT BIT(0) #define HPRE_COMM_CNT_CLR_CE 0x0 @@ -119,7 +118,6 @@ static struct hisi_qm_list hpre_devices = { }; static const char * const hpre_debug_file_name[] = { - [HPRE_CURRENT_QM] = "current_qm", [HPRE_CLEAR_ENABLE] = "rdclr_en", [HPRE_CLUSTER_CTRL] = "cluster_ctrl", }; @@ -226,41 +224,44 @@ static u32 vfs_num; module_param_cb(vfs_num, &vfs_num_ops, &vfs_num, 0444); MODULE_PARM_DESC(vfs_num, "Number of VFs to enable(1-63), 0(default)"); -struct hisi_qp *hpre_create_qp(void) +struct hisi_qp *hpre_create_qp(u8 type) { int node = cpu_to_node(smp_processor_id()); struct hisi_qp *qp = NULL; int ret; - ret = hisi_qm_alloc_qps_node(&hpre_devices, 1, 0, node, &qp); + if (type != HPRE_V2_ALG_TYPE && type != HPRE_V3_ECC_ALG_TYPE) + return NULL; + + /* + * type: 0 - RSA/DH. algorithm supported in V2, + * 1 - ECC algorithm in V3. + */ + ret = hisi_qm_alloc_qps_node(&hpre_devices, 1, type, node, &qp); if (!ret) return qp; return NULL; } -static void hpre_pasid_enable(struct hisi_qm *qm) +static void hpre_config_pasid(struct hisi_qm *qm) { - u32 val; - - val = readl_relaxed(qm->io_base + HPRE_DATA_RUSER_CFG); - val |= BIT(HPRE_PASID_EN_BIT); - writel_relaxed(val, qm->io_base + HPRE_DATA_RUSER_CFG); - val = readl_relaxed(qm->io_base + HPRE_DATA_WUSER_CFG); - val |= BIT(HPRE_PASID_EN_BIT); - writel_relaxed(val, qm->io_base + HPRE_DATA_WUSER_CFG); -} + u32 val1, val2; -static void hpre_pasid_disable(struct hisi_qm *qm) -{ - u32 val; + if (qm->ver >= QM_HW_V3) + return; - val = readl_relaxed(qm->io_base + HPRE_DATA_RUSER_CFG); - val &= ~BIT(HPRE_PASID_EN_BIT); - writel_relaxed(val, qm->io_base + HPRE_DATA_RUSER_CFG); - val = readl_relaxed(qm->io_base + HPRE_DATA_WUSER_CFG); - val &= ~BIT(HPRE_PASID_EN_BIT); - writel_relaxed(val, qm->io_base + HPRE_DATA_WUSER_CFG); + val1 = readl_relaxed(qm->io_base + HPRE_DATA_RUSER_CFG); + val2 = readl_relaxed(qm->io_base + HPRE_DATA_WUSER_CFG); + if (qm->use_sva) { + val1 |= BIT(HPRE_PASID_EN_BIT); + val2 |= BIT(HPRE_PASID_EN_BIT); + } else { + val1 &= ~BIT(HPRE_PASID_EN_BIT); + val2 &= ~BIT(HPRE_PASID_EN_BIT); + } + writel_relaxed(val1, qm->io_base + HPRE_DATA_RUSER_CFG); + writel_relaxed(val2, qm->io_base + HPRE_DATA_WUSER_CFG); } static int hpre_cfg_by_dsm(struct hisi_qm *qm) @@ -320,7 +321,7 @@ static int hpre_set_cluster(struct hisi_qm *qm) } /* - * For Kunpeng 920, we shoul disable FLR triggered by hardware (BME/PM/SRIOV). + * For Kunpeng 920, we should disable FLR triggered by hardware (BME/PM/SRIOV). * Or it may stay in D3 state when we bind and unbind hpre quickly, * as it does FLR triggered by hardware. */ @@ -383,15 +384,14 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm) if (qm->ver == QM_HW_V2) { ret = hpre_cfg_by_dsm(qm); if (ret) - dev_err(dev, "acpi_evaluate_dsm err.\n"); + return ret; disable_flr_of_bme(qm); - - /* Enable data buffer pasid */ - if (qm->use_sva) - hpre_pasid_enable(qm); } + /* Config data buffer pasid needed by Kunpeng 920 */ + hpre_config_pasid(qm); + return ret; } @@ -401,10 +401,6 @@ static void hpre_cnt_regs_clear(struct hisi_qm *qm) unsigned long offset; int i; - /* clear current_qm */ - writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF); - writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF); - /* clear clusterX/cluster_ctrl */ for (i = 0; i < clusters_num; i++) { offset = HPRE_CLSTR_BASE + i * HPRE_CLSTR_ADDR_INTRVL; @@ -456,49 +452,6 @@ static inline struct hisi_qm *hpre_file_to_qm(struct hpre_debugfs_file *file) return &hpre->qm; } -static u32 hpre_current_qm_read(struct hpre_debugfs_file *file) -{ - struct hisi_qm *qm = hpre_file_to_qm(file); - - return readl(qm->io_base + QM_DFX_MB_CNT_VF); -} - -static int hpre_current_qm_write(struct hpre_debugfs_file *file, u32 val) -{ - struct hisi_qm *qm = hpre_file_to_qm(file); - u32 num_vfs = qm->vfs_num; - u32 vfq_num, tmp; - - if (val > num_vfs) - return -EINVAL; - - /* According PF or VF Dev ID to calculation curr_qm_qp_num and store */ - if (val == 0) { - qm->debug.curr_qm_qp_num = qm->qp_num; - } else { - vfq_num = (qm->ctrl_qp_num - qm->qp_num) / num_vfs; - if (val == num_vfs) { - qm->debug.curr_qm_qp_num = - qm->ctrl_qp_num - qm->qp_num - (num_vfs - 1) * vfq_num; - } else { - qm->debug.curr_qm_qp_num = vfq_num; - } - } - - writel(val, qm->io_base + QM_DFX_MB_CNT_VF); - writel(val, qm->io_base + QM_DFX_DB_CNT_VF); - - tmp = val | - (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK); - writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN); - - tmp = val | - (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK); - writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN); - - return 0; -} - static u32 hpre_clear_enable_read(struct hpre_debugfs_file *file) { struct hisi_qm *qm = hpre_file_to_qm(file); @@ -519,7 +472,7 @@ static int hpre_clear_enable_write(struct hpre_debugfs_file *file, u32 val) ~HPRE_CTRL_CNT_CLR_CE_BIT) | val; writel(tmp, qm->io_base + HPRE_CTRL_CNT_CLR_CE); - return 0; + return 0; } static u32 hpre_cluster_inqry_read(struct hpre_debugfs_file *file) @@ -541,7 +494,7 @@ static int hpre_cluster_inqry_write(struct hpre_debugfs_file *file, u32 val) writel(val, qm->io_base + offset + HPRE_CLUSTER_INQURY); - return 0; + return 0; } static ssize_t hpre_ctrl_debug_read(struct file *filp, char __user *buf, @@ -554,9 +507,6 @@ static ssize_t hpre_ctrl_debug_read(struct file *filp, char __user *buf, spin_lock_irq(&file->lock); switch (file->type) { - case HPRE_CURRENT_QM: - val = hpre_current_qm_read(file); - break; case HPRE_CLEAR_ENABLE: val = hpre_clear_enable_read(file); break; @@ -597,11 +547,6 @@ static ssize_t hpre_ctrl_debug_write(struct file *filp, const char __user *buf, spin_lock_irq(&file->lock); switch (file->type) { - case HPRE_CURRENT_QM: - ret = hpre_current_qm_write(file, val); - if (ret) - goto err_input; - break; case HPRE_CLEAR_ENABLE: ret = hpre_clear_enable_write(file, val); if (ret) @@ -740,11 +685,6 @@ static int hpre_ctrl_debug_init(struct hisi_qm *qm) { int ret; - ret = hpre_create_debugfs_file(qm, NULL, HPRE_CURRENT_QM, - HPRE_CURRENT_QM); - if (ret) - return ret; - ret = hpre_create_debugfs_file(qm, NULL, HPRE_CLEAR_ENABLE, HPRE_CLEAR_ENABLE); if (ret) @@ -812,9 +752,9 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) } if (pdev->revision >= QM_HW_V3) - qm->algs = "rsa\ndh\necdh\nx25519\nx448\necdsa\nsm2\n"; + qm->algs = "rsa\ndh\necdh\nx25519\nx448\necdsa\nsm2"; else - qm->algs = "rsa\ndh\n"; + qm->algs = "rsa\ndh"; qm->mode = uacce_mode; qm->pdev = pdev; qm->ver = pdev->revision; @@ -867,6 +807,20 @@ static void hpre_open_axi_master_ooo(struct hisi_qm *qm) HPRE_ADDR(qm, HPRE_AM_OOO_SHUTDOWN_ENB)); } +static void hpre_err_info_init(struct hisi_qm *qm) +{ + struct hisi_qm_err_info *err_info = &qm->err_info; + + err_info->ce = QM_BASE_CE; + err_info->fe = 0; + err_info->ecc_2bits_mask = HPRE_CORE_ECC_2BIT_ERR | + HPRE_OOO_ECC_2BIT_ERR; + err_info->dev_ce_mask = HPRE_HAC_RAS_CE_ENABLE; + err_info->msi_wr_port = HPRE_WR_MSI_PORT; + err_info->acpi_rst = "HRST"; + err_info->nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT; +} + static const struct hisi_qm_err_ini hpre_err_ini = { .hw_init = hpre_set_user_domain_and_cache, .hw_err_enable = hpre_hw_error_enable, @@ -875,16 +829,7 @@ static const struct hisi_qm_err_ini hpre_err_ini = { .clear_dev_hw_err_status = hpre_clear_hw_err_status, .log_dev_hw_err = hpre_log_hw_error, .open_axi_master_ooo = hpre_open_axi_master_ooo, - .err_info = { - .ce = QM_BASE_CE, - .nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT, - .fe = 0, - .ecc_2bits_mask = HPRE_CORE_ECC_2BIT_ERR | - HPRE_OOO_ECC_2BIT_ERR, - .dev_ce_mask = HPRE_HAC_RAS_CE_ENABLE, - .msi_wr_port = HPRE_WR_MSI_PORT, - .acpi_rst = "HRST", - } + .err_info_init = hpre_err_info_init, }; static int hpre_pf_probe_init(struct hpre *hpre) @@ -892,13 +837,12 @@ static int hpre_pf_probe_init(struct hpre *hpre) struct hisi_qm *qm = &hpre->qm; int ret; - qm->ctrl_qp_num = HPRE_QUEUE_NUM_V2; - ret = hpre_set_user_domain_and_cache(qm); if (ret) return ret; qm->err_ini = &hpre_err_ini; + qm->err_ini->err_info_init(qm); hisi_qm_dev_err_init(qm); return 0; @@ -1006,8 +950,6 @@ static void hpre_remove(struct pci_dev *pdev) hisi_qm_stop(qm, QM_NORMAL); if (qm->fun_type == QM_HW_PF) { - if (qm->use_sva && qm->ver == QM_HW_V2) - hpre_pasid_disable(qm); hpre_cnt_regs_clear(qm); qm->debug.curr_qm_qp_num = 0; hisi_qm_dev_err_uninit(qm); @@ -1016,7 +958,6 @@ static void hpre_remove(struct pci_dev *pdev) hisi_qm_uninit(qm); } - static const struct pci_error_handlers hpre_err_handler = { .error_detected = hisi_qm_dev_err_detected, .slot_reset = hisi_qm_dev_slot_reset, @@ -1075,4 +1016,5 @@ module_exit(hpre_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com>"); +MODULE_AUTHOR("Meng Yu <yumeng18@huawei.com>"); MODULE_DESCRIPTION("Driver for HiSilicon HPRE accelerator"); diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 13cb4216561a..ce439a0c66c9 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -38,6 +38,7 @@ #define QM_MB_CMD_SQC_BT 0x4 #define QM_MB_CMD_CQC_BT 0x5 #define QM_MB_CMD_SQC_VFT_V2 0x6 +#define QM_MB_CMD_STOP_QP 0x8 #define QM_MB_CMD_SEND_BASE 0x300 #define QM_MB_EVENT_SHIFT 8 @@ -93,6 +94,12 @@ #define QM_DB_PRIORITY_SHIFT_V1 48 #define QM_DOORBELL_SQ_CQ_BASE_V2 0x1000 #define QM_DOORBELL_EQ_AEQ_BASE_V2 0x2000 +#define QM_QUE_ISO_CFG_V 0x0030 +#define QM_QUE_ISO_EN 0x100154 +#define QM_CAPBILITY 0x100158 +#define QM_QP_NUN_MASK GENMASK(10, 0) +#define QM_QP_DB_INTERVAL 0x10000 +#define QM_QP_MAX_NUM_SHIFT 11 #define QM_DB_CMD_SHIFT_V2 12 #define QM_DB_RAND_SHIFT_V2 16 #define QM_DB_INDEX_SHIFT_V2 32 @@ -129,9 +136,9 @@ #define QM_DFX_CNT_CLR_CE 0x100118 #define QM_ABNORMAL_INT_SOURCE 0x100000 -#define QM_ABNORMAL_INT_SOURCE_CLR GENMASK(12, 0) +#define QM_ABNORMAL_INT_SOURCE_CLR GENMASK(14, 0) #define QM_ABNORMAL_INT_MASK 0x100004 -#define QM_ABNORMAL_INT_MASK_VALUE 0x1fff +#define QM_ABNORMAL_INT_MASK_VALUE 0x7fff #define QM_ABNORMAL_INT_STATUS 0x100008 #define QM_ABNORMAL_INT_SET 0x10000c #define QM_ABNORMAL_INF00 0x100010 @@ -164,6 +171,14 @@ #define ACC_AM_ROB_ECC_INT_STS 0x300104 #define ACC_ROB_ECC_ERR_MULTPL BIT(1) +#define QM_DFX_MB_CNT_VF 0x104010 +#define QM_DFX_DB_CNT_VF 0x104020 +#define QM_DFX_SQE_CNT_VF_SQN 0x104030 +#define QM_DFX_CQE_CNT_VF_CQN 0x104040 +#define QM_DFX_QN_SHIFT 16 +#define CURRENT_FUN_MASK GENMASK(5, 0) +#define CURRENT_Q_MASK GENMASK(31, 16) + #define POLL_PERIOD 10 #define POLL_TIMEOUT 1000 #define WAIT_PERIOD_US_MAX 200 @@ -173,6 +188,7 @@ #define QM_CACHE_WB_DONE 0x208 #define PCI_BAR_2 2 +#define PCI_BAR_4 4 #define QM_SQE_DATA_ALIGN_MASK GENMASK(6, 0) #define QMC_ALIGN(sz) ALIGN(sz, 32) @@ -334,6 +350,7 @@ struct hisi_qm_hw_ops { void (*hw_error_init)(struct hisi_qm *qm, u32 ce, u32 nfe, u32 fe); void (*hw_error_uninit)(struct hisi_qm *qm); enum acc_err_result (*hw_error_handle)(struct hisi_qm *qm); + int (*stop_qp)(struct hisi_qp *qp); }; struct qm_dfx_item { @@ -350,6 +367,7 @@ static struct qm_dfx_item qm_dfx_files[] = { }; static const char * const qm_debug_file_name[] = { + [CURRENT_QM] = "current_qm", [CURRENT_Q] = "current_q", [CLEAR_ENABLE] = "clear_enable", }; @@ -373,6 +391,8 @@ static const struct hisi_qm_hw_error qm_hw_error[] = { { .int_msk = BIT(10), .msg = "qm_db_timeout" }, { .int_msk = BIT(11), .msg = "qm_of_fifo_of" }, { .int_msk = BIT(12), .msg = "qm_db_random_invalid" }, + { .int_msk = BIT(13), .msg = "qm_mailbox_timeout" }, + { .int_msk = BIT(14), .msg = "qm_flr_timeout" }, { /* sentinel */ } }; @@ -557,21 +577,22 @@ static void qm_db_v1(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) static void qm_db_v2(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) { - u64 doorbell; - u64 dbase; + void __iomem *io_base = qm->io_base; u16 randata = 0; + u64 doorbell; if (cmd == QM_DOORBELL_CMD_SQ || cmd == QM_DOORBELL_CMD_CQ) - dbase = QM_DOORBELL_SQ_CQ_BASE_V2; + io_base = qm->db_io_base + (u64)qn * qm->db_interval + + QM_DOORBELL_SQ_CQ_BASE_V2; else - dbase = QM_DOORBELL_EQ_AEQ_BASE_V2; + io_base += QM_DOORBELL_EQ_AEQ_BASE_V2; doorbell = qn | ((u64)cmd << QM_DB_CMD_SHIFT_V2) | ((u64)randata << QM_DB_RAND_SHIFT_V2) | ((u64)index << QM_DB_INDEX_SHIFT_V2) | ((u64)priority << QM_DB_PRIORITY_SHIFT_V2); - writeq(doorbell, qm->io_base + dbase); + writeq(doorbell, io_base); } static void qm_db(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) @@ -865,6 +886,26 @@ static int qm_get_vft_v2(struct hisi_qm *qm, u32 *base, u32 *number) return 0; } +static int qm_get_vf_qp_num(struct hisi_qm *qm, u32 fun_num) +{ + u32 remain_q_num, vfq_num; + u32 num_vfs = qm->vfs_num; + + vfq_num = (qm->ctrl_qp_num - qm->qp_num) / num_vfs; + if (vfq_num >= qm->max_qp_num) + return qm->max_qp_num; + + remain_q_num = (qm->ctrl_qp_num - qm->qp_num) % num_vfs; + if (vfq_num + remain_q_num <= qm->max_qp_num) + return fun_num == num_vfs ? vfq_num + remain_q_num : vfq_num; + + /* + * if vfq_num + remain_q_num > max_qp_num, the last VFs, + * each with one more queue. + */ + return fun_num + remain_q_num > num_vfs ? vfq_num + 1 : vfq_num; +} + static struct hisi_qm *file_to_qm(struct debugfs_file *file) { struct qm_debug *debug = file->debug; @@ -918,6 +959,41 @@ static int clear_enable_write(struct debugfs_file *file, u32 rd_clr_ctrl) return 0; } +static u32 current_qm_read(struct debugfs_file *file) +{ + struct hisi_qm *qm = file_to_qm(file); + + return readl(qm->io_base + QM_DFX_MB_CNT_VF); +} + +static int current_qm_write(struct debugfs_file *file, u32 val) +{ + struct hisi_qm *qm = file_to_qm(file); + u32 tmp; + + if (val > qm->vfs_num) + return -EINVAL; + + /* According PF or VF Dev ID to calculation curr_qm_qp_num and store */ + if (!val) + qm->debug.curr_qm_qp_num = qm->qp_num; + else + qm->debug.curr_qm_qp_num = qm_get_vf_qp_num(qm, val); + + writel(val, qm->io_base + QM_DFX_MB_CNT_VF); + writel(val, qm->io_base + QM_DFX_DB_CNT_VF); + + tmp = val | + (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK); + writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN); + + tmp = val | + (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK); + writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN); + + return 0; +} + static ssize_t qm_debug_read(struct file *filp, char __user *buf, size_t count, loff_t *pos) { @@ -929,6 +1005,9 @@ static ssize_t qm_debug_read(struct file *filp, char __user *buf, mutex_lock(&file->lock); switch (index) { + case CURRENT_QM: + val = current_qm_read(file); + break; case CURRENT_Q: val = current_q_read(file); break; @@ -971,27 +1050,24 @@ static ssize_t qm_debug_write(struct file *filp, const char __user *buf, mutex_lock(&file->lock); switch (index) { + case CURRENT_QM: + ret = current_qm_write(file, val); + break; case CURRENT_Q: ret = current_q_write(file, val); - if (ret) - goto err_input; break; case CLEAR_ENABLE: ret = clear_enable_write(file, val); - if (ret) - goto err_input; break; default: ret = -EINVAL; - goto err_input; } mutex_unlock(&file->lock); - return count; + if (ret) + return ret; -err_input: - mutex_unlock(&file->lock); - return ret; + return count; } static const struct file_operations qm_debug_fops = { @@ -1529,12 +1605,12 @@ static const struct file_operations qm_cmd_fops = { .write = qm_cmd_write, }; -static void qm_create_debugfs_file(struct hisi_qm *qm, enum qm_debug_file index) +static void qm_create_debugfs_file(struct hisi_qm *qm, struct dentry *dir, + enum qm_debug_file index) { - struct dentry *qm_d = qm->debug.qm_d; struct debugfs_file *file = qm->debug.files + index; - debugfs_create_file(qm_debug_file_name[index], 0600, qm_d, file, + debugfs_create_file(qm_debug_file_name[index], 0600, dir, file, &qm_debug_fops); file->index = index; @@ -1628,7 +1704,7 @@ static enum acc_err_result qm_hw_error_handle_v2(struct hisi_qm *qm) if (val == (QM_DB_RANDOM_INVALID | QM_BASE_CE)) { writel(error_status, qm->io_base + QM_ABNORMAL_INT_SOURCE); - writel(qm->err_ini->err_info.nfe, + writel(qm->err_info.nfe, qm->io_base + QM_RAS_NFE_ENABLE); return ACC_ERR_RECOVERED; } @@ -1639,6 +1715,11 @@ static enum acc_err_result qm_hw_error_handle_v2(struct hisi_qm *qm) return ACC_ERR_RECOVERED; } +static int qm_stop_qp(struct hisi_qp *qp) +{ + return qm_mb(qp->qm, QM_MB_CMD_STOP_QP, 0, qp->qp_id, 0); +} + static const struct hisi_qm_hw_ops qm_hw_ops_v1 = { .qm_db = qm_db_v1, .get_irq_num = qm_get_irq_num_v1, @@ -1654,6 +1735,16 @@ static const struct hisi_qm_hw_ops qm_hw_ops_v2 = { .hw_error_handle = qm_hw_error_handle_v2, }; +static const struct hisi_qm_hw_ops qm_hw_ops_v3 = { + .get_vft = qm_get_vft_v2, + .qm_db = qm_db_v2, + .get_irq_num = qm_get_irq_num_v2, + .hw_error_init = qm_hw_error_init_v2, + .hw_error_uninit = qm_hw_error_uninit_v2, + .hw_error_handle = qm_hw_error_handle_v2, + .stop_qp = qm_stop_qp, +}; + static void *qm_get_avail_sqe(struct hisi_qp *qp) { struct hisi_qp_status *qp_status = &qp->qp_status; @@ -1933,6 +2024,14 @@ static int qm_drain_qp(struct hisi_qp *qp) if (qm->err_status.is_qm_ecc_mbit || qm->err_status.is_dev_ecc_mbit) return 0; + /* Kunpeng930 supports drain qp by device */ + if (qm->ops->stop_qp) { + ret = qm->ops->stop_qp(qp); + if (ret) + dev_err(dev, "Failed to stop qp(%u)!\n", qp->qp_id); + return ret; + } + addr = qm_ctx_alloc(qm, size, &dma_addr); if (IS_ERR(addr)) { dev_err(dev, "Failed to alloc ctx for sqc and cqc!\n"); @@ -2132,6 +2231,8 @@ static int hisi_qm_uacce_mmap(struct uacce_queue *q, { struct hisi_qp *qp = q->priv; struct hisi_qm *qm = qp->qm; + resource_size_t phys_base = qm->db_phys_base + + qp->qp_id * qm->db_interval; size_t sz = vma->vm_end - vma->vm_start; struct pci_dev *pdev = qm->pdev; struct device *dev = &pdev->dev; @@ -2143,16 +2244,19 @@ static int hisi_qm_uacce_mmap(struct uacce_queue *q, if (qm->ver == QM_HW_V1) { if (sz > PAGE_SIZE * QM_DOORBELL_PAGE_NR) return -EINVAL; - } else { + } else if (qm->ver == QM_HW_V2 || !qm->use_db_isolation) { if (sz > PAGE_SIZE * (QM_DOORBELL_PAGE_NR + QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE)) return -EINVAL; + } else { + if (sz > qm->db_interval) + return -EINVAL; } vma->vm_flags |= VM_IO; return remap_pfn_range(vma, vma->vm_start, - qm->phys_base >> PAGE_SHIFT, + phys_base >> PAGE_SHIFT, sz, pgprot_noncached(vma->vm_page_prot)); case UACCE_QFRT_DUS: if (sz != qp->qdma.size) @@ -2267,14 +2371,20 @@ static int qm_alloc_uacce(struct hisi_qm *qm) uacce->priv = qm; uacce->algs = qm->algs; - if (qm->ver == QM_HW_V1) { - mmio_page_nr = QM_DOORBELL_PAGE_NR; + if (qm->ver == QM_HW_V1) uacce->api_ver = HISI_QM_API_VER_BASE; - } else { + else if (qm->ver == QM_HW_V2) + uacce->api_ver = HISI_QM_API_VER2_BASE; + else + uacce->api_ver = HISI_QM_API_VER3_BASE; + + if (qm->ver == QM_HW_V1) + mmio_page_nr = QM_DOORBELL_PAGE_NR; + else if (qm->ver == QM_HW_V2 || !qm->use_db_isolation) mmio_page_nr = QM_DOORBELL_PAGE_NR + QM_DOORBELL_SQ_CQ_BASE_V2 / PAGE_SIZE; - uacce->api_ver = HISI_QM_API_VER2_BASE; - } + else + mmio_page_nr = qm->db_interval / PAGE_SIZE; dus_page_nr = (PAGE_SIZE - 1 + qm->sqe_size * QM_Q_DEPTH + sizeof(struct qm_cqe) * QM_Q_DEPTH) >> PAGE_SHIFT; @@ -2482,8 +2592,10 @@ static void hisi_qm_pre_init(struct hisi_qm *qm) if (qm->ver == QM_HW_V1) qm->ops = &qm_hw_ops_v1; - else + else if (qm->ver == QM_HW_V2) qm->ops = &qm_hw_ops_v2; + else + qm->ops = &qm_hw_ops_v3; pci_set_drvdata(pdev, qm); mutex_init(&qm->mailbox_lock); @@ -2492,13 +2604,23 @@ static void hisi_qm_pre_init(struct hisi_qm *qm) qm->misc_ctl = false; } -static void hisi_qm_pci_uninit(struct hisi_qm *qm) +static void qm_put_pci_res(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; - pci_free_irq_vectors(pdev); + if (qm->use_db_isolation) + iounmap(qm->db_io_base); + iounmap(qm->io_base); pci_release_mem_regions(pdev); +} + +static void hisi_qm_pci_uninit(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + + pci_free_irq_vectors(pdev); + qm_put_pci_res(qm); pci_disable_device(pdev); } @@ -2527,7 +2649,6 @@ void hisi_qm_uninit(struct hisi_qm *qm) hisi_qm_cache_wb(qm); dma_free_coherent(dev, qm->qdma.size, qm->qdma.va, qm->qdma.dma); - memset(&qm->qdma, 0, sizeof(qm->qdma)); } qm_irq_unregister(qm); @@ -2681,7 +2802,7 @@ static int __hisi_qm_start(struct hisi_qm *qm) { int ret; - WARN_ON(!qm->qdma.dma); + WARN_ON(!qm->qdma.va); if (qm->fun_type == QM_HW_PF) { ret = qm_dev_mem_reset(qm); @@ -2930,9 +3051,11 @@ void hisi_qm_debug_init(struct hisi_qm *qm) qm->debug.qm_d = qm_d; /* only show this in PF */ - if (qm->fun_type == QM_HW_PF) + if (qm->fun_type == QM_HW_PF) { + qm_create_debugfs_file(qm, qm->debug.debug_root, CURRENT_QM); for (i = CURRENT_Q; i < DEBUG_FILE_NUM; i++) - qm_create_debugfs_file(qm, i); + qm_create_debugfs_file(qm, qm_d, i); + } debugfs_create_file("regs", 0444, qm->debug.qm_d, qm, &qm_regs_fops); @@ -2960,6 +3083,10 @@ void hisi_qm_debug_regs_clear(struct hisi_qm *qm) struct qm_dfx_registers *regs; int i; + /* clear current_qm */ + writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF); + writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF); + /* clear current_q */ writel(0x0, qm->io_base + QM_DFX_SQE_CNT_VF_SQN); writel(0x0, qm->io_base + QM_DFX_CQE_CNT_VF_CQN); @@ -2982,7 +3109,7 @@ EXPORT_SYMBOL_GPL(hisi_qm_debug_regs_clear); static void qm_hw_error_init(struct hisi_qm *qm) { - const struct hisi_qm_err_info *err_info = &qm->err_ini->err_info; + struct hisi_qm_err_info *err_info = &qm->err_info; if (!qm->ops->hw_error_init) { dev_err(&qm->pdev->dev, "QM doesn't support hw error handling!\n"); @@ -3175,30 +3302,46 @@ EXPORT_SYMBOL_GPL(hisi_qm_alloc_qps_node); static int qm_vf_q_assign(struct hisi_qm *qm, u32 num_vfs) { - u32 remain_q_num, q_num, i, j; + u32 remain_q_num, vfs_q_num, act_q_num, q_num, i, j; + u32 max_qp_num = qm->max_qp_num; u32 q_base = qm->qp_num; int ret; if (!num_vfs) return -EINVAL; - remain_q_num = qm->ctrl_qp_num - qm->qp_num; + vfs_q_num = qm->ctrl_qp_num - qm->qp_num; - /* If remain queues not enough, return error. */ - if (qm->ctrl_qp_num < qm->qp_num || remain_q_num < num_vfs) + /* If vfs_q_num is less than num_vfs, return error. */ + if (vfs_q_num < num_vfs) return -EINVAL; - q_num = remain_q_num / num_vfs; - for (i = 1; i <= num_vfs; i++) { - if (i == num_vfs) - q_num += remain_q_num % num_vfs; - ret = hisi_qm_set_vft(qm, i, q_base, q_num); + q_num = vfs_q_num / num_vfs; + remain_q_num = vfs_q_num % num_vfs; + + for (i = num_vfs; i > 0; i--) { + /* + * if q_num + remain_q_num > max_qp_num in last vf, divide the + * remaining queues equally. + */ + if (i == num_vfs && q_num + remain_q_num <= max_qp_num) { + act_q_num = q_num + remain_q_num; + remain_q_num = 0; + } else if (remain_q_num > 0) { + act_q_num = q_num + 1; + remain_q_num--; + } else { + act_q_num = q_num; + } + + act_q_num = min_t(int, act_q_num, max_qp_num); + ret = hisi_qm_set_vft(qm, i, q_base, act_q_num); if (ret) { - for (j = i; j > 0; j--) + for (j = num_vfs; j > i; j--) hisi_qm_set_vft(qm, j, 0, 0); return ret; } - q_base += q_num; + q_base += act_q_num; } return 0; @@ -3318,15 +3461,15 @@ static enum acc_err_result qm_dev_err_handle(struct hisi_qm *qm) /* get device hardware error status */ err_sts = qm->err_ini->get_dev_hw_err_status(qm); if (err_sts) { - if (err_sts & qm->err_ini->err_info.ecc_2bits_mask) + if (err_sts & qm->err_info.ecc_2bits_mask) qm->err_status.is_dev_ecc_mbit = true; if (qm->err_ini->log_dev_hw_err) qm->err_ini->log_dev_hw_err(qm, err_sts); /* ce error does not need to be reset */ - if ((err_sts | qm->err_ini->err_info.dev_ce_mask) == - qm->err_ini->err_info.dev_ce_mask) { + if ((err_sts | qm->err_info.dev_ce_mask) == + qm->err_info.dev_ce_mask) { if (qm->err_ini->clear_dev_hw_err_status) qm->err_ini->clear_dev_hw_err_status(qm, err_sts); @@ -3639,7 +3782,7 @@ static int qm_soft_reset(struct hisi_qm *qm) acpi_status s; s = acpi_evaluate_integer(ACPI_HANDLE(&pdev->dev), - qm->err_ini->err_info.acpi_rst, + qm->err_info.acpi_rst, NULL, &value); if (ACPI_FAILURE(s)) { pci_err(pdev, "NO controller reset method!\n"); @@ -3707,12 +3850,11 @@ static void qm_restart_prepare(struct hisi_qm *qm) /* temporarily close the OOO port used for PEH to write out MSI */ value = readl(qm->io_base + ACC_AM_CFG_PORT_WR_EN); - writel(value & ~qm->err_ini->err_info.msi_wr_port, + writel(value & ~qm->err_info.msi_wr_port, qm->io_base + ACC_AM_CFG_PORT_WR_EN); /* clear dev ecc 2bit error source if having */ - value = qm_get_dev_err_status(qm) & - qm->err_ini->err_info.ecc_2bits_mask; + value = qm_get_dev_err_status(qm) & qm->err_info.ecc_2bits_mask; if (value && qm->err_ini->clear_dev_hw_err_status) qm->err_ini->clear_dev_hw_err_status(qm, value); @@ -3736,7 +3878,7 @@ static void qm_restart_done(struct hisi_qm *qm) /* open the OOO port for PEH to write out MSI */ value = readl(qm->io_base + ACC_AM_CFG_PORT_WR_EN); - value |= qm->err_ini->err_info.msi_wr_port; + value |= qm->err_info.msi_wr_port; writel(value, qm->io_base + ACC_AM_CFG_PORT_WR_EN); qm->err_status.is_qm_ecc_mbit = false; @@ -3875,8 +4017,7 @@ static int qm_check_dev_error(struct hisi_qm *qm) if (ret) return ret; - return (qm_get_dev_err_status(qm) & - qm->err_ini->err_info.ecc_2bits_mask); + return (qm_get_dev_err_status(qm) & qm->err_info.ecc_2bits_mask); } void hisi_qm_reset_prepare(struct pci_dev *pdev) @@ -4084,7 +4225,7 @@ int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list) mutex_unlock(&qm_list->lock); if (flag) { - ret = qm_list->register_to_crypto(); + ret = qm_list->register_to_crypto(qm); if (ret) { mutex_lock(&qm_list->lock); list_del(&qm->list); @@ -4115,59 +4256,134 @@ void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list) mutex_unlock(&qm_list->lock); if (list_empty(&qm_list->list)) - qm_list->unregister_from_crypto(); + qm_list->unregister_from_crypto(qm); } EXPORT_SYMBOL_GPL(hisi_qm_alg_unregister); -static int hisi_qm_pci_init(struct hisi_qm *qm) +static int qm_get_qp_num(struct hisi_qm *qm) +{ + if (qm->ver == QM_HW_V1) + qm->ctrl_qp_num = QM_QNUM_V1; + else if (qm->ver == QM_HW_V2) + qm->ctrl_qp_num = QM_QNUM_V2; + else + qm->ctrl_qp_num = readl(qm->io_base + QM_CAPBILITY) & + QM_QP_NUN_MASK; + + if (qm->use_db_isolation) + qm->max_qp_num = (readl(qm->io_base + QM_CAPBILITY) >> + QM_QP_MAX_NUM_SHIFT) & QM_QP_NUN_MASK; + else + qm->max_qp_num = qm->ctrl_qp_num; + + /* check if qp number is valid */ + if (qm->qp_num > qm->max_qp_num) { + dev_err(&qm->pdev->dev, "qp num(%u) is more than max qp num(%u)!\n", + qm->qp_num, qm->max_qp_num); + return -EINVAL; + } + + return 0; +} + +static int qm_get_pci_res(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; struct device *dev = &pdev->dev; - unsigned int num_vec; int ret; - ret = pci_enable_device_mem(pdev); - if (ret < 0) { - dev_err(dev, "Failed to enable device mem!\n"); - return ret; - } - ret = pci_request_mem_regions(pdev, qm->dev_name); if (ret < 0) { dev_err(dev, "Failed to request mem regions!\n"); - goto err_disable_pcidev; + return ret; } qm->phys_base = pci_resource_start(pdev, PCI_BAR_2); - qm->phys_size = pci_resource_len(qm->pdev, PCI_BAR_2); - qm->io_base = ioremap(qm->phys_base, qm->phys_size); + qm->io_base = ioremap(qm->phys_base, pci_resource_len(pdev, PCI_BAR_2)); if (!qm->io_base) { ret = -EIO; - goto err_release_mem_regions; + goto err_request_mem_regions; + } + + if (qm->ver > QM_HW_V2) { + if (qm->fun_type == QM_HW_PF) + qm->use_db_isolation = readl(qm->io_base + + QM_QUE_ISO_EN) & BIT(0); + else + qm->use_db_isolation = readl(qm->io_base + + QM_QUE_ISO_CFG_V) & BIT(0); + } + + if (qm->use_db_isolation) { + qm->db_interval = QM_QP_DB_INTERVAL; + qm->db_phys_base = pci_resource_start(pdev, PCI_BAR_4); + qm->db_io_base = ioremap(qm->db_phys_base, + pci_resource_len(pdev, PCI_BAR_4)); + if (!qm->db_io_base) { + ret = -EIO; + goto err_ioremap; + } + } else { + qm->db_phys_base = qm->phys_base; + qm->db_io_base = qm->io_base; + qm->db_interval = 0; } + if (qm->fun_type == QM_HW_PF) { + ret = qm_get_qp_num(qm); + if (ret) + goto err_db_ioremap; + } + + return 0; + +err_db_ioremap: + if (qm->use_db_isolation) + iounmap(qm->db_io_base); +err_ioremap: + iounmap(qm->io_base); +err_request_mem_regions: + pci_release_mem_regions(pdev); + return ret; +} + +static int hisi_qm_pci_init(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; + struct device *dev = &pdev->dev; + unsigned int num_vec; + int ret; + + ret = pci_enable_device_mem(pdev); + if (ret < 0) { + dev_err(dev, "Failed to enable device mem!\n"); + return ret; + } + + ret = qm_get_pci_res(qm); + if (ret) + goto err_disable_pcidev; + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); if (ret < 0) - goto err_iounmap; + goto err_get_pci_res; pci_set_master(pdev); if (!qm->ops->get_irq_num) { ret = -EOPNOTSUPP; - goto err_iounmap; + goto err_get_pci_res; } num_vec = qm->ops->get_irq_num(qm); ret = pci_alloc_irq_vectors(pdev, num_vec, num_vec, PCI_IRQ_MSI); if (ret < 0) { dev_err(dev, "Failed to enable MSI vectors!\n"); - goto err_iounmap; + goto err_get_pci_res; } return 0; -err_iounmap: - iounmap(qm->io_base); -err_release_mem_regions: - pci_release_mem_regions(pdev); +err_get_pci_res: + qm_put_pci_res(qm); err_disable_pcidev: pci_disable_device(pdev); return ret; @@ -4187,28 +4403,28 @@ int hisi_qm_init(struct hisi_qm *qm) hisi_qm_pre_init(qm); - ret = qm_alloc_uacce(qm); - if (ret < 0) - dev_warn(dev, "fail to alloc uacce (%d)\n", ret); - ret = hisi_qm_pci_init(qm); if (ret) - goto err_remove_uacce; + return ret; ret = qm_irq_register(qm); if (ret) - goto err_pci_uninit; + goto err_pci_init; if (qm->fun_type == QM_HW_VF && qm->ver != QM_HW_V1) { /* v2 starts to support get vft by mailbox */ ret = hisi_qm_get_vft(qm, &qm->qp_base, &qm->qp_num); if (ret) - goto err_irq_unregister; + goto err_irq_register; } + ret = qm_alloc_uacce(qm); + if (ret < 0) + dev_warn(dev, "fail to alloc uacce (%d)\n", ret); + ret = hisi_qm_memory_init(qm); if (ret) - goto err_irq_unregister; + goto err_alloc_uacce; INIT_WORK(&qm->work, qm_work_process); if (qm->fun_type == QM_HW_PF) @@ -4218,13 +4434,13 @@ int hisi_qm_init(struct hisi_qm *qm) return 0; -err_irq_unregister: - qm_irq_unregister(qm); -err_pci_uninit: - hisi_qm_pci_uninit(qm); -err_remove_uacce: +err_alloc_uacce: uacce_remove(qm->uacce); qm->uacce = NULL; +err_irq_register: + qm_irq_unregister(qm); +err_pci_init: + hisi_qm_pci_uninit(qm); return ret; } EXPORT_SYMBOL_GPL(hisi_qm_init); diff --git a/drivers/crypto/hisilicon/qm.h b/drivers/crypto/hisilicon/qm.h index 54967c6b9c78..acefdf8b3a50 100644 --- a/drivers/crypto/hisilicon/qm.h +++ b/drivers/crypto/hisilicon/qm.h @@ -51,14 +51,6 @@ #define PEH_AXUSER_CFG 0x401001 #define PEH_AXUSER_CFG_ENABLE 0xffffffff -#define QM_DFX_MB_CNT_VF 0x104010 -#define QM_DFX_DB_CNT_VF 0x104020 -#define QM_DFX_SQE_CNT_VF_SQN 0x104030 -#define QM_DFX_CQE_CNT_VF_CQN 0x104040 -#define QM_DFX_QN_SHIFT 16 -#define CURRENT_FUN_MASK GENMASK(5, 0) -#define CURRENT_Q_MASK GENMASK(31, 16) - #define QM_AXI_RRESP BIT(0) #define QM_AXI_BRESP BIT(1) #define QM_ECC_MBIT BIT(2) @@ -72,10 +64,13 @@ #define QM_DB_TIMEOUT BIT(10) #define QM_OF_FIFO_OF BIT(11) #define QM_DB_RANDOM_INVALID BIT(12) +#define QM_MAILBOX_TIMEOUT BIT(13) +#define QM_FLR_TIMEOUT BIT(14) #define QM_BASE_NFE (QM_AXI_RRESP | QM_AXI_BRESP | QM_ECC_MBIT | \ QM_ACC_GET_TASK_TIMEOUT | QM_DB_TIMEOUT | \ - QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID) + QM_OF_FIFO_OF | QM_DB_RANDOM_INVALID | \ + QM_MAILBOX_TIMEOUT | QM_FLR_TIMEOUT) #define QM_BASE_CE QM_ECC_1BIT #define QM_Q_DEPTH 1024 @@ -123,6 +118,7 @@ enum qm_fun_type { }; enum qm_debug_file { + CURRENT_QM, CURRENT_Q, CLEAR_ENABLE, DEBUG_FILE_NUM, @@ -193,14 +189,14 @@ struct hisi_qm_err_ini { void (*open_axi_master_ooo)(struct hisi_qm *qm); void (*close_axi_master_ooo)(struct hisi_qm *qm); void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts); - struct hisi_qm_err_info err_info; + void (*err_info_init)(struct hisi_qm *qm); }; struct hisi_qm_list { struct mutex lock; struct list_head list; - int (*register_to_crypto)(void); - void (*unregister_from_crypto)(void); + int (*register_to_crypto)(struct hisi_qm *qm); + void (*unregister_from_crypto)(struct hisi_qm *qm); }; struct hisi_qm { @@ -209,12 +205,15 @@ struct hisi_qm { const char *dev_name; struct pci_dev *pdev; void __iomem *io_base; + void __iomem *db_io_base; u32 sqe_size; u32 qp_base; u32 qp_num; u32 qp_in_used; u32 ctrl_qp_num; + u32 max_qp_num; u32 vfs_num; + u32 db_interval; struct list_head list; struct hisi_qm_list *qm_list; @@ -230,6 +229,7 @@ struct hisi_qm { struct hisi_qm_status status; const struct hisi_qm_err_ini *err_ini; + struct hisi_qm_err_info err_info; struct hisi_qm_err_status err_status; unsigned long misc_ctl; /* driver removing and reset sched */ @@ -252,8 +252,11 @@ struct hisi_qm { const char *algs; bool use_sva; bool is_frozen; + + /* doorbell isolation enable */ + bool use_db_isolation; resource_size_t phys_base; - resource_size_t phys_size; + resource_size_t db_phys_base; struct uacce_device *uacce; int mode; }; diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c index 8ca945ac297e..0a3c8f019b02 100644 --- a/drivers/crypto/hisilicon/sec/sec_algs.c +++ b/drivers/crypto/hisilicon/sec/sec_algs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (c) 2016-2017 Hisilicon Limited. */ +/* Copyright (c) 2016-2017 HiSilicon Limited. */ #include <linux/crypto.h> #include <linux/dma-mapping.h> #include <linux/dmapool.h> diff --git a/drivers/crypto/hisilicon/sec/sec_drv.c b/drivers/crypto/hisilicon/sec/sec_drv.c index 91ee2bb575df..c8de1b51c843 100644 --- a/drivers/crypto/hisilicon/sec/sec_drv.c +++ b/drivers/crypto/hisilicon/sec/sec_drv.c @@ -1,8 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Driver for the Hisilicon SEC units found on Hip06 Hip07 + * Driver for the HiSilicon SEC units found on Hip06 Hip07 * - * Copyright (c) 2016-2017 Hisilicon Limited. + * Copyright (c) 2016-2017 HiSilicon Limited. */ #include <linux/acpi.h> #include <linux/atomic.h> @@ -233,7 +233,7 @@ static int sec_queue_map_io(struct sec_queue *queue) IORESOURCE_MEM, 2 + queue->queue_id); if (!res) { - dev_err(dev, "Failed to get queue %d memory resource\n", + dev_err(dev, "Failed to get queue %u memory resource\n", queue->queue_id); return -ENOMEM; } @@ -653,12 +653,12 @@ static int sec_queue_free(struct sec_queue *queue) struct sec_dev_info *info = queue->dev_info; if (queue->queue_id >= SEC_Q_NUM) { - dev_err(info->dev, "No queue %d\n", queue->queue_id); + dev_err(info->dev, "No queue %u\n", queue->queue_id); return -ENODEV; } if (!queue->in_use) { - dev_err(info->dev, "Queue %d is idle\n", queue->queue_id); + dev_err(info->dev, "Queue %u is idle\n", queue->queue_id); return -ENODEV; } @@ -834,6 +834,7 @@ int sec_queue_stop_release(struct sec_queue *queue) /** * sec_queue_empty() - Is this hardware queue currently empty. + * @queue: The queue to test * * We need to know if we have an empty queue for some of the chaining modes * as if it is not empty we may need to hold the message in a software queue @@ -1315,6 +1316,6 @@ static struct platform_driver sec_driver = { module_platform_driver(sec_driver); MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Hisilicon Security Accelerators"); +MODULE_DESCRIPTION("HiSilicon Security Accelerators"); MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com"); MODULE_AUTHOR("Jonathan Cameron <jonathan.cameron@huawei.com>"); diff --git a/drivers/crypto/hisilicon/sec/sec_drv.h b/drivers/crypto/hisilicon/sec/sec_drv.h index 4d9063a8b10b..179a8250d691 100644 --- a/drivers/crypto/hisilicon/sec/sec_drv.h +++ b/drivers/crypto/hisilicon/sec/sec_drv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2016-2017 Hisilicon Limited. */ +/* Copyright (c) 2016-2017 HiSilicon Limited. */ #ifndef _SEC_DRV_H_ #define _SEC_DRV_H_ diff --git a/drivers/crypto/hisilicon/sec2/sec.h b/drivers/crypto/hisilicon/sec2/sec.h index 08491912afd5..dfdce2f21e65 100644 --- a/drivers/crypto/hisilicon/sec2/sec.h +++ b/drivers/crypto/hisilicon/sec2/sec.h @@ -4,8 +4,6 @@ #ifndef __HISI_SEC_V2_H #define __HISI_SEC_V2_H -#include <linux/list.h> - #include "../qm.h" #include "sec_crypto.h" @@ -50,7 +48,7 @@ struct sec_req { int err_type; int req_id; - int flag; + u32 flag; /* Status of the SEC request */ bool fake_busy; @@ -139,6 +137,7 @@ struct sec_ctx { bool pbuf_supported; struct sec_cipher_ctx c_ctx; struct sec_auth_ctx a_ctx; + struct device *dev; }; enum sec_endian { @@ -148,7 +147,6 @@ enum sec_endian { }; enum sec_debug_file_index { - SEC_CURRENT_QM, SEC_CLEAR_ENABLE, SEC_DEBUG_FILE_NUM, }; @@ -183,6 +181,6 @@ struct sec_dev { void sec_destroy_qps(struct hisi_qp **qps, int qp_num); struct hisi_qp **sec_create_qps(void); -int sec_register_to_crypto(void); -void sec_unregister_from_crypto(void); +int sec_register_to_crypto(struct hisi_qm *qm); +void sec_unregister_from_crypto(struct hisi_qm *qm); #endif diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c index 2eaa516b3231..133aede8bf07 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.c +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c @@ -7,6 +7,7 @@ #include <crypto/des.h> #include <crypto/hash.h> #include <crypto/internal/aead.h> +#include <crypto/internal/des.h> #include <crypto/sha1.h> #include <crypto/sha2.h> #include <crypto/skcipher.h> @@ -43,7 +44,6 @@ #define SEC_TOTAL_IV_SZ (SEC_IV_SIZE * QM_Q_DEPTH) #define SEC_SGL_SGE_NR 128 -#define SEC_CTX_DEV(ctx) (&(ctx)->sec->qm.pdev->dev) #define SEC_CIPHER_AUTH 0xfe #define SEC_AUTH_CIPHER 0x1 #define SEC_MAX_MAC_LEN 64 @@ -96,7 +96,7 @@ static int sec_alloc_req_id(struct sec_req *req, struct sec_qp_ctx *qp_ctx) 0, QM_Q_DEPTH, GFP_ATOMIC); mutex_unlock(&qp_ctx->req_lock); if (unlikely(req_id < 0)) { - dev_err(SEC_CTX_DEV(req->ctx), "alloc req id fail!\n"); + dev_err(req->ctx->dev, "alloc req id fail!\n"); return req_id; } @@ -112,7 +112,7 @@ static void sec_free_req_id(struct sec_req *req) int req_id = req->req_id; if (unlikely(req_id < 0 || req_id >= QM_Q_DEPTH)) { - dev_err(SEC_CTX_DEV(req->ctx), "free request id invalid!\n"); + dev_err(req->ctx->dev, "free request id invalid!\n"); return; } @@ -138,7 +138,7 @@ static int sec_aead_verify(struct sec_req *req) aead_req->cryptlen + aead_req->assoclen - authsize); if (unlikely(sz != authsize || memcmp(mac_out, mac, sz))) { - dev_err(SEC_CTX_DEV(req->ctx), "aead verify failure!\n"); + dev_err(req->ctx->dev, "aead verify failure!\n"); return -EBADMSG; } @@ -177,7 +177,7 @@ static void sec_req_cb(struct hisi_qp *qp, void *resp) if (unlikely(req->err_type || done != SEC_SQE_DONE || (ctx->alg_type == SEC_SKCIPHER && flag != SEC_SQE_CFLAG) || (ctx->alg_type == SEC_AEAD && flag != SEC_SQE_AEAD_FLAG))) { - dev_err(SEC_CTX_DEV(ctx), + dev_err_ratelimited(ctx->dev, "err_type[%d],done[%d],flag[%d]\n", req->err_type, done, flag); err = -EIO; @@ -326,8 +326,8 @@ static int sec_alloc_pbuf_resource(struct device *dev, struct sec_alg_res *res) static int sec_alg_resource_alloc(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx) { - struct device *dev = SEC_CTX_DEV(ctx); struct sec_alg_res *res = qp_ctx->res; + struct device *dev = ctx->dev; int ret; ret = sec_alloc_civ_resource(dev, res); @@ -360,7 +360,7 @@ alloc_fail: static void sec_alg_resource_free(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx) { - struct device *dev = SEC_CTX_DEV(ctx); + struct device *dev = ctx->dev; sec_free_civ_resource(dev, qp_ctx->res); @@ -373,7 +373,7 @@ static void sec_alg_resource_free(struct sec_ctx *ctx, static int sec_create_qp_ctx(struct hisi_qm *qm, struct sec_ctx *ctx, int qp_ctx_id, int alg_type) { - struct device *dev = SEC_CTX_DEV(ctx); + struct device *dev = ctx->dev; struct sec_qp_ctx *qp_ctx; struct hisi_qp *qp; int ret = -ENOMEM; @@ -428,7 +428,7 @@ err_destroy_idr: static void sec_release_qp_ctx(struct sec_ctx *ctx, struct sec_qp_ctx *qp_ctx) { - struct device *dev = SEC_CTX_DEV(ctx); + struct device *dev = ctx->dev; hisi_qm_stop_qp(qp_ctx->qp); sec_alg_resource_free(ctx, qp_ctx); @@ -452,6 +452,7 @@ static int sec_ctx_base_init(struct sec_ctx *ctx) sec = container_of(ctx->qps[0]->qm, struct sec_dev, qm); ctx->sec = sec; + ctx->dev = &sec->qm.pdev->dev; ctx->hlf_q_num = sec->ctx_q_num >> 1; ctx->pbuf_supported = ctx->sec->iommu_used; @@ -476,11 +477,9 @@ static int sec_ctx_base_init(struct sec_ctx *ctx) err_sec_release_qp_ctx: for (i = i - 1; i >= 0; i--) sec_release_qp_ctx(ctx, &ctx->qp_ctx[i]); - kfree(ctx->qp_ctx); err_destroy_qps: sec_destroy_qps(ctx->qps, sec->ctx_q_num); - return ret; } @@ -499,7 +498,7 @@ static int sec_cipher_init(struct sec_ctx *ctx) { struct sec_cipher_ctx *c_ctx = &ctx->c_ctx; - c_ctx->c_key = dma_alloc_coherent(SEC_CTX_DEV(ctx), SEC_MAX_KEY_SIZE, + c_ctx->c_key = dma_alloc_coherent(ctx->dev, SEC_MAX_KEY_SIZE, &c_ctx->c_key_dma, GFP_KERNEL); if (!c_ctx->c_key) return -ENOMEM; @@ -512,7 +511,7 @@ static void sec_cipher_uninit(struct sec_ctx *ctx) struct sec_cipher_ctx *c_ctx = &ctx->c_ctx; memzero_explicit(c_ctx->c_key, SEC_MAX_KEY_SIZE); - dma_free_coherent(SEC_CTX_DEV(ctx), SEC_MAX_KEY_SIZE, + dma_free_coherent(ctx->dev, SEC_MAX_KEY_SIZE, c_ctx->c_key, c_ctx->c_key_dma); } @@ -520,7 +519,7 @@ static int sec_auth_init(struct sec_ctx *ctx) { struct sec_auth_ctx *a_ctx = &ctx->a_ctx; - a_ctx->a_key = dma_alloc_coherent(SEC_CTX_DEV(ctx), SEC_MAX_KEY_SIZE, + a_ctx->a_key = dma_alloc_coherent(ctx->dev, SEC_MAX_KEY_SIZE, &a_ctx->a_key_dma, GFP_KERNEL); if (!a_ctx->a_key) return -ENOMEM; @@ -533,7 +532,7 @@ static void sec_auth_uninit(struct sec_ctx *ctx) struct sec_auth_ctx *a_ctx = &ctx->a_ctx; memzero_explicit(a_ctx->a_key, SEC_MAX_KEY_SIZE); - dma_free_coherent(SEC_CTX_DEV(ctx), SEC_MAX_KEY_SIZE, + dma_free_coherent(ctx->dev, SEC_MAX_KEY_SIZE, a_ctx->a_key, a_ctx->a_key_dma); } @@ -546,7 +545,7 @@ static int sec_skcipher_init(struct crypto_skcipher *tfm) crypto_skcipher_set_reqsize(tfm, sizeof(struct sec_req)); ctx->c_ctx.ivsize = crypto_skcipher_ivsize(tfm); if (ctx->c_ctx.ivsize > SEC_IV_SIZE) { - dev_err(SEC_CTX_DEV(ctx), "get error skcipher iv size!\n"); + pr_err("get error skcipher iv size!\n"); return -EINVAL; } @@ -573,10 +572,18 @@ static void sec_skcipher_uninit(struct crypto_skcipher *tfm) sec_ctx_base_uninit(ctx); } -static int sec_skcipher_3des_setkey(struct sec_cipher_ctx *c_ctx, +static int sec_skcipher_3des_setkey(struct crypto_skcipher *tfm, const u8 *key, const u32 keylen, const enum sec_cmode c_mode) { + struct sec_ctx *ctx = crypto_skcipher_ctx(tfm); + struct sec_cipher_ctx *c_ctx = &ctx->c_ctx; + int ret; + + ret = verify_skcipher_des3_key(tfm, key); + if (ret) + return ret; + switch (keylen) { case SEC_DES3_2KEY_SIZE: c_ctx->c_key_len = SEC_CKEY_3DES_2KEY; @@ -633,12 +640,13 @@ static int sec_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, { struct sec_ctx *ctx = crypto_skcipher_ctx(tfm); struct sec_cipher_ctx *c_ctx = &ctx->c_ctx; + struct device *dev = ctx->dev; int ret; if (c_mode == SEC_CMODE_XTS) { ret = xts_verify_key(tfm, key, keylen); if (ret) { - dev_err(SEC_CTX_DEV(ctx), "xts mode key err!\n"); + dev_err(dev, "xts mode key err!\n"); return ret; } } @@ -648,7 +656,7 @@ static int sec_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, switch (c_alg) { case SEC_CALG_3DES: - ret = sec_skcipher_3des_setkey(c_ctx, keylen, c_mode); + ret = sec_skcipher_3des_setkey(tfm, key, keylen, c_mode); break; case SEC_CALG_AES: case SEC_CALG_SM4: @@ -659,7 +667,7 @@ static int sec_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, } if (ret) { - dev_err(SEC_CTX_DEV(ctx), "set sec key err!\n"); + dev_err(dev, "set sec key err!\n"); return ret; } @@ -691,7 +699,7 @@ static int sec_cipher_pbuf_map(struct sec_ctx *ctx, struct sec_req *req, struct aead_request *aead_req = req->aead_req.aead_req; struct sec_cipher_req *c_req = &req->c_req; struct sec_qp_ctx *qp_ctx = req->qp_ctx; - struct device *dev = SEC_CTX_DEV(ctx); + struct device *dev = ctx->dev; int copy_size, pbuf_length; int req_id = req->req_id; @@ -701,21 +709,14 @@ static int sec_cipher_pbuf_map(struct sec_ctx *ctx, struct sec_req *req, copy_size = c_req->c_len; pbuf_length = sg_copy_to_buffer(src, sg_nents(src), - qp_ctx->res[req_id].pbuf, - copy_size); - + qp_ctx->res[req_id].pbuf, + copy_size); if (unlikely(pbuf_length != copy_size)) { dev_err(dev, "copy src data to pbuf error!\n"); return -EINVAL; } c_req->c_in_dma = qp_ctx->res[req_id].pbuf_dma; - - if (!c_req->c_in_dma) { - dev_err(dev, "fail to set pbuffer address!\n"); - return -ENOMEM; - } - c_req->c_out_dma = c_req->c_in_dma; return 0; @@ -727,7 +728,7 @@ static void sec_cipher_pbuf_unmap(struct sec_ctx *ctx, struct sec_req *req, struct aead_request *aead_req = req->aead_req.aead_req; struct sec_cipher_req *c_req = &req->c_req; struct sec_qp_ctx *qp_ctx = req->qp_ctx; - struct device *dev = SEC_CTX_DEV(ctx); + struct device *dev = ctx->dev; int copy_size, pbuf_length; int req_id = req->req_id; @@ -739,7 +740,6 @@ static void sec_cipher_pbuf_unmap(struct sec_ctx *ctx, struct sec_req *req, pbuf_length = sg_copy_from_buffer(dst, sg_nents(dst), qp_ctx->res[req_id].pbuf, copy_size); - if (unlikely(pbuf_length != copy_size)) dev_err(dev, "copy pbuf data to dst error!\n"); } @@ -751,7 +751,7 @@ static int sec_cipher_map(struct sec_ctx *ctx, struct sec_req *req, struct sec_aead_req *a_req = &req->aead_req; struct sec_qp_ctx *qp_ctx = req->qp_ctx; struct sec_alg_res *res = &qp_ctx->res[req->req_id]; - struct device *dev = SEC_CTX_DEV(ctx); + struct device *dev = ctx->dev; int ret; if (req->use_pbuf) { @@ -806,7 +806,7 @@ static void sec_cipher_unmap(struct sec_ctx *ctx, struct sec_req *req, struct scatterlist *src, struct scatterlist *dst) { struct sec_cipher_req *c_req = &req->c_req; - struct device *dev = SEC_CTX_DEV(ctx); + struct device *dev = ctx->dev; if (req->use_pbuf) { sec_cipher_pbuf_unmap(ctx, req, dst); @@ -891,6 +891,7 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key, { struct sec_ctx *ctx = crypto_aead_ctx(tfm); struct sec_cipher_ctx *c_ctx = &ctx->c_ctx; + struct device *dev = ctx->dev; struct crypto_authenc_keys keys; int ret; @@ -904,13 +905,13 @@ static int sec_aead_setkey(struct crypto_aead *tfm, const u8 *key, ret = sec_aead_aes_set_key(c_ctx, &keys); if (ret) { - dev_err(SEC_CTX_DEV(ctx), "set sec cipher key err!\n"); + dev_err(dev, "set sec cipher key err!\n"); goto bad_key; } ret = sec_aead_auth_set_key(&ctx->a_ctx, &keys); if (ret) { - dev_err(SEC_CTX_DEV(ctx), "set sec auth key err!\n"); + dev_err(dev, "set sec auth key err!\n"); goto bad_key; } @@ -1062,7 +1063,7 @@ static void sec_update_iv(struct sec_req *req, enum sec_alg_type alg_type) sz = sg_pcopy_to_buffer(sgl, sg_nents(sgl), iv, iv_size, cryptlen - iv_size); if (unlikely(sz != iv_size)) - dev_err(SEC_CTX_DEV(req->ctx), "copy output iv error!\n"); + dev_err(req->ctx->dev, "copy output iv error!\n"); } static struct sec_req *sec_back_req_clear(struct sec_ctx *ctx, @@ -1160,7 +1161,7 @@ static int sec_aead_bd_fill(struct sec_ctx *ctx, struct sec_req *req) ret = sec_skcipher_bd_fill(ctx, req); if (unlikely(ret)) { - dev_err(SEC_CTX_DEV(ctx), "skcipher bd fill is error!\n"); + dev_err(ctx->dev, "skcipher bd fill is error!\n"); return ret; } @@ -1194,7 +1195,7 @@ static void sec_aead_callback(struct sec_ctx *c, struct sec_req *req, int err) a_req->assoclen); if (unlikely(sz != authsize)) { - dev_err(SEC_CTX_DEV(req->ctx), "copy out mac err!\n"); + dev_err(c->dev, "copy out mac err!\n"); err = -EINVAL; } } @@ -1259,7 +1260,7 @@ static int sec_process(struct sec_ctx *ctx, struct sec_req *req) ret = ctx->req_op->bd_send(ctx, req); if (unlikely((ret != -EBUSY && ret != -EINPROGRESS) || (ret == -EBUSY && !(req->flag & CRYPTO_TFM_REQ_MAY_BACKLOG)))) { - dev_err_ratelimited(SEC_CTX_DEV(ctx), "send sec request failed!\n"); + dev_err_ratelimited(ctx->dev, "send sec request failed!\n"); goto err_send_req; } @@ -1325,7 +1326,7 @@ static int sec_aead_init(struct crypto_aead *tfm) ctx->alg_type = SEC_AEAD; ctx->c_ctx.ivsize = crypto_aead_ivsize(tfm); if (ctx->c_ctx.ivsize > SEC_IV_SIZE) { - dev_err(SEC_CTX_DEV(ctx), "get error aead iv size!\n"); + dev_err(ctx->dev, "get error aead iv size!\n"); return -EINVAL; } @@ -1374,7 +1375,7 @@ static int sec_aead_ctx_init(struct crypto_aead *tfm, const char *hash_name) auth_ctx->hash_tfm = crypto_alloc_shash(hash_name, 0, 0); if (IS_ERR(auth_ctx->hash_tfm)) { - dev_err(SEC_CTX_DEV(ctx), "aead alloc shash error!\n"); + dev_err(ctx->dev, "aead alloc shash error!\n"); sec_aead_exit(tfm); return PTR_ERR(auth_ctx->hash_tfm); } @@ -1405,10 +1406,40 @@ static int sec_aead_sha512_ctx_init(struct crypto_aead *tfm) return sec_aead_ctx_init(tfm, "sha512"); } + +static int sec_skcipher_cryptlen_ckeck(struct sec_ctx *ctx, + struct sec_req *sreq) +{ + u32 cryptlen = sreq->c_req.sk_req->cryptlen; + struct device *dev = ctx->dev; + u8 c_mode = ctx->c_ctx.c_mode; + int ret = 0; + + switch (c_mode) { + case SEC_CMODE_XTS: + if (unlikely(cryptlen < AES_BLOCK_SIZE)) { + dev_err(dev, "skcipher XTS mode input length error!\n"); + ret = -EINVAL; + } + break; + case SEC_CMODE_ECB: + case SEC_CMODE_CBC: + if (unlikely(cryptlen & (AES_BLOCK_SIZE - 1))) { + dev_err(dev, "skcipher AES input length error!\n"); + ret = -EINVAL; + } + break; + default: + ret = -EINVAL; + } + + return ret; +} + static int sec_skcipher_param_check(struct sec_ctx *ctx, struct sec_req *sreq) { struct skcipher_request *sk_req = sreq->c_req.sk_req; - struct device *dev = SEC_CTX_DEV(ctx); + struct device *dev = ctx->dev; u8 c_alg = ctx->c_ctx.c_alg; if (unlikely(!sk_req->src || !sk_req->dst)) { @@ -1429,12 +1460,9 @@ static int sec_skcipher_param_check(struct sec_ctx *ctx, struct sec_req *sreq) } return 0; } else if (c_alg == SEC_CALG_AES || c_alg == SEC_CALG_SM4) { - if (unlikely(sk_req->cryptlen & (AES_BLOCK_SIZE - 1))) { - dev_err(dev, "skcipher aes input length error!\n"); - return -EINVAL; - } - return 0; + return sec_skcipher_cryptlen_ckeck(ctx, sreq); } + dev_err(dev, "skcipher algorithm error!\n"); return -EINVAL; @@ -1531,14 +1559,15 @@ static struct skcipher_alg sec_skciphers[] = { static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq) { - u8 c_alg = ctx->c_ctx.c_alg; struct aead_request *req = sreq->aead_req.aead_req; struct crypto_aead *tfm = crypto_aead_reqtfm(req); size_t authsize = crypto_aead_authsize(tfm); + struct device *dev = ctx->dev; + u8 c_alg = ctx->c_ctx.c_alg; if (unlikely(!req->src || !req->dst || !req->cryptlen || req->assoclen > SEC_MAX_AAD_LEN)) { - dev_err(SEC_CTX_DEV(ctx), "aead input param error!\n"); + dev_err(dev, "aead input param error!\n"); return -EINVAL; } @@ -1550,7 +1579,7 @@ static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq) /* Support AES only */ if (unlikely(c_alg != SEC_CALG_AES)) { - dev_err(SEC_CTX_DEV(ctx), "aead crypto alg error!\n"); + dev_err(dev, "aead crypto alg error!\n"); return -EINVAL; } if (sreq->c_req.encrypt) @@ -1559,7 +1588,7 @@ static int sec_aead_param_check(struct sec_ctx *ctx, struct sec_req *sreq) sreq->c_req.c_len = req->cryptlen - authsize; if (unlikely(sreq->c_req.c_len & (AES_BLOCK_SIZE - 1))) { - dev_err(SEC_CTX_DEV(ctx), "aead crypto length error!\n"); + dev_err(dev, "aead crypto length error!\n"); return -EINVAL; } @@ -1634,7 +1663,7 @@ static struct aead_alg sec_aeads[] = { AES_BLOCK_SIZE, AES_BLOCK_SIZE, SHA512_DIGEST_SIZE), }; -int sec_register_to_crypto(void) +int sec_register_to_crypto(struct hisi_qm *qm) { int ret; @@ -1651,7 +1680,7 @@ int sec_register_to_crypto(void) return ret; } -void sec_unregister_from_crypto(void) +void sec_unregister_from_crypto(struct hisi_qm *qm) { crypto_unregister_skciphers(sec_skciphers, ARRAY_SIZE(sec_skciphers)); diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.h b/drivers/crypto/hisilicon/sec2/sec_crypto.h index b2786e17d8fe..9c78edac56a4 100644 --- a/drivers/crypto/hisilicon/sec2/sec_crypto.h +++ b/drivers/crypto/hisilicon/sec2/sec_crypto.h @@ -64,7 +64,6 @@ enum sec_addr_type { }; struct sec_sqe_type2 { - /* * mac_len: 0~4 bits * a_key_len: 5~10 bits @@ -120,7 +119,6 @@ struct sec_sqe_type2 { /* c_pad_len_field: 0~1 bits */ __le16 c_pad_len_field; - __le64 long_a_data_len; __le64 a_ivin_addr; __le64 a_key_addr; @@ -211,6 +209,6 @@ struct sec_sqe { struct sec_sqe_type2 type2; }; -int sec_register_to_crypto(void); -void sec_unregister_from_crypto(void); +int sec_register_to_crypto(struct hisi_qm *qm); +void sec_unregister_from_crypto(struct hisi_qm *qm); #endif diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index dc68ba76f65e..6f0062d4408c 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -19,7 +19,6 @@ #define SEC_VF_NUM 63 #define SEC_QUEUE_NUM_V1 4096 -#define SEC_QUEUE_NUM_V2 1024 #define SEC_PF_PCI_DEVICE_ID 0xa255 #define SEC_VF_PCI_DEVICE_ID 0xa256 @@ -35,18 +34,16 @@ #define SEC_CTX_Q_NUM_MAX 32 #define SEC_CTRL_CNT_CLR_CE 0x301120 -#define SEC_CTRL_CNT_CLR_CE_BIT BIT(0) -#define SEC_ENGINE_PF_CFG_OFF 0x300000 -#define SEC_ACC_COMMON_REG_OFF 0x1000 +#define SEC_CTRL_CNT_CLR_CE_BIT BIT(0) #define SEC_CORE_INT_SOURCE 0x301010 #define SEC_CORE_INT_MASK 0x301000 #define SEC_CORE_INT_STATUS 0x301008 #define SEC_CORE_SRAM_ECC_ERR_INFO 0x301C14 -#define SEC_ECC_NUM(err) (((err) >> 16) & 0xFF) -#define SEC_ECC_ADDR(err) ((err) >> 0) +#define SEC_ECC_NUM 16 +#define SEC_ECC_MASH 0xFF #define SEC_CORE_INT_DISABLE 0x0 -#define SEC_CORE_INT_ENABLE 0x1ff -#define SEC_CORE_INT_CLEAR 0x1ff +#define SEC_CORE_INT_ENABLE 0x7c1ff +#define SEC_CORE_INT_CLEAR 0x7c1ff #define SEC_SAA_ENABLE 0x17f #define SEC_RAS_CE_REG 0x301050 @@ -54,24 +51,24 @@ #define SEC_RAS_NFE_REG 0x301058 #define SEC_RAS_CE_ENB_MSK 0x88 #define SEC_RAS_FE_ENB_MSK 0x0 -#define SEC_RAS_NFE_ENB_MSK 0x177 -#define SEC_RAS_DISABLE 0x0 -#define SEC_MEM_START_INIT_REG 0x0100 -#define SEC_MEM_INIT_DONE_REG 0x0104 +#define SEC_RAS_NFE_ENB_MSK 0x7c177 +#define SEC_RAS_DISABLE 0x0 +#define SEC_MEM_START_INIT_REG 0x301100 +#define SEC_MEM_INIT_DONE_REG 0x301104 -#define SEC_CONTROL_REG 0x0200 +#define SEC_CONTROL_REG 0x301200 #define SEC_TRNG_EN_SHIFT 8 #define SEC_CLK_GATE_ENABLE BIT(3) #define SEC_CLK_GATE_DISABLE (~BIT(3)) #define SEC_AXI_SHUTDOWN_ENABLE BIT(12) #define SEC_AXI_SHUTDOWN_DISABLE 0xFFFFEFFF -#define SEC_INTERFACE_USER_CTRL0_REG 0x0220 -#define SEC_INTERFACE_USER_CTRL1_REG 0x0224 -#define SEC_SAA_EN_REG 0x0270 -#define SEC_BD_ERR_CHK_EN_REG0 0x0380 -#define SEC_BD_ERR_CHK_EN_REG1 0x0384 -#define SEC_BD_ERR_CHK_EN_REG3 0x038c +#define SEC_INTERFACE_USER_CTRL0_REG 0x301220 +#define SEC_INTERFACE_USER_CTRL1_REG 0x301224 +#define SEC_SAA_EN_REG 0x301270 +#define SEC_BD_ERR_CHK_EN_REG0 0x301380 +#define SEC_BD_ERR_CHK_EN_REG1 0x301384 +#define SEC_BD_ERR_CHK_EN_REG3 0x30138c #define SEC_USER0_SMMU_NORMAL (BIT(23) | BIT(15)) #define SEC_USER1_SMMU_NORMAL (BIT(31) | BIT(23) | BIT(15) | BIT(7)) @@ -95,9 +92,6 @@ #define SEC_SQE_MASK_OFFSET 64 #define SEC_SQE_MASK_LEN 48 -#define SEC_ADDR(qm, offset) ((qm)->io_base + (offset) + \ - SEC_ENGINE_PF_CFG_OFF + SEC_ACC_COMMON_REG_OFF) - struct sec_hw_error { u32 int_msk; const char *msg; @@ -117,20 +111,66 @@ static struct hisi_qm_list sec_devices = { }; static const struct sec_hw_error sec_hw_errors[] = { - {.int_msk = BIT(0), .msg = "sec_axi_rresp_err_rint"}, - {.int_msk = BIT(1), .msg = "sec_axi_bresp_err_rint"}, - {.int_msk = BIT(2), .msg = "sec_ecc_2bit_err_rint"}, - {.int_msk = BIT(3), .msg = "sec_ecc_1bit_err_rint"}, - {.int_msk = BIT(4), .msg = "sec_req_trng_timeout_rint"}, - {.int_msk = BIT(5), .msg = "sec_fsm_hbeat_rint"}, - {.int_msk = BIT(6), .msg = "sec_channel_req_rng_timeout_rint"}, - {.int_msk = BIT(7), .msg = "sec_bd_err_rint"}, - {.int_msk = BIT(8), .msg = "sec_chain_buff_err_rint"}, - { /* sentinel */ } + { + .int_msk = BIT(0), + .msg = "sec_axi_rresp_err_rint" + }, + { + .int_msk = BIT(1), + .msg = "sec_axi_bresp_err_rint" + }, + { + .int_msk = BIT(2), + .msg = "sec_ecc_2bit_err_rint" + }, + { + .int_msk = BIT(3), + .msg = "sec_ecc_1bit_err_rint" + }, + { + .int_msk = BIT(4), + .msg = "sec_req_trng_timeout_rint" + }, + { + .int_msk = BIT(5), + .msg = "sec_fsm_hbeat_rint" + }, + { + .int_msk = BIT(6), + .msg = "sec_channel_req_rng_timeout_rint" + }, + { + .int_msk = BIT(7), + .msg = "sec_bd_err_rint" + }, + { + .int_msk = BIT(8), + .msg = "sec_chain_buff_err_rint" + }, + { + .int_msk = BIT(14), + .msg = "sec_no_secure_access" + }, + { + .int_msk = BIT(15), + .msg = "sec_wrapping_key_auth_err" + }, + { + .int_msk = BIT(16), + .msg = "sec_km_key_crc_fail" + }, + { + .int_msk = BIT(17), + .msg = "sec_axi_poison_err" + }, + { + .int_msk = BIT(18), + .msg = "sec_sva_err" + }, + {} }; static const char * const sec_dbg_file_name[] = { - [SEC_CURRENT_QM] = "current_qm", [SEC_CLEAR_ENABLE] = "clear_enable", }; @@ -277,9 +317,7 @@ static u8 sec_get_endian(struct hisi_qm *qm) "cannot access a register in VF!\n"); return SEC_LE; } - reg = readl_relaxed(qm->io_base + SEC_ENGINE_PF_CFG_OFF + - SEC_ACC_COMMON_REG_OFF + SEC_CONTROL_REG); - + reg = readl_relaxed(qm->io_base + SEC_CONTROL_REG); /* BD little endian mode */ if (!(reg & BIT(0))) return SEC_LE; @@ -299,13 +337,13 @@ static int sec_engine_init(struct hisi_qm *qm) u32 reg; /* disable clock gate control */ - reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG)); + reg = readl_relaxed(qm->io_base + SEC_CONTROL_REG); reg &= SEC_CLK_GATE_DISABLE; - writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG)); + writel_relaxed(reg, qm->io_base + SEC_CONTROL_REG); - writel_relaxed(0x1, SEC_ADDR(qm, SEC_MEM_START_INIT_REG)); + writel_relaxed(0x1, qm->io_base + SEC_MEM_START_INIT_REG); - ret = readl_relaxed_poll_timeout(SEC_ADDR(qm, SEC_MEM_INIT_DONE_REG), + ret = readl_relaxed_poll_timeout(qm->io_base + SEC_MEM_INIT_DONE_REG, reg, reg & 0x1, SEC_DELAY_10_US, SEC_POLL_TIMEOUT_US); if (ret) { @@ -313,40 +351,40 @@ static int sec_engine_init(struct hisi_qm *qm) return ret; } - reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG)); + reg = readl_relaxed(qm->io_base + SEC_CONTROL_REG); reg |= (0x1 << SEC_TRNG_EN_SHIFT); - writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG)); + writel_relaxed(reg, qm->io_base + SEC_CONTROL_REG); - reg = readl_relaxed(SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL0_REG)); + reg = readl_relaxed(qm->io_base + SEC_INTERFACE_USER_CTRL0_REG); reg |= SEC_USER0_SMMU_NORMAL; - writel_relaxed(reg, SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL0_REG)); + writel_relaxed(reg, qm->io_base + SEC_INTERFACE_USER_CTRL0_REG); - reg = readl_relaxed(SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL1_REG)); + reg = readl_relaxed(qm->io_base + SEC_INTERFACE_USER_CTRL1_REG); reg &= SEC_USER1_SMMU_MASK; if (qm->use_sva && qm->ver == QM_HW_V2) reg |= SEC_USER1_SMMU_SVA; else reg |= SEC_USER1_SMMU_NORMAL; - writel_relaxed(reg, SEC_ADDR(qm, SEC_INTERFACE_USER_CTRL1_REG)); + writel_relaxed(reg, qm->io_base + SEC_INTERFACE_USER_CTRL1_REG); writel(SEC_SINGLE_PORT_MAX_TRANS, qm->io_base + AM_CFG_SINGLE_PORT_MAX_TRANS); - writel(SEC_SAA_ENABLE, SEC_ADDR(qm, SEC_SAA_EN_REG)); + writel(SEC_SAA_ENABLE, qm->io_base + SEC_SAA_EN_REG); /* Enable sm4 extra mode, as ctr/ecb */ writel_relaxed(SEC_BD_ERR_CHK_EN0, - SEC_ADDR(qm, SEC_BD_ERR_CHK_EN_REG0)); + qm->io_base + SEC_BD_ERR_CHK_EN_REG0); /* Enable sm4 xts mode multiple iv */ writel_relaxed(SEC_BD_ERR_CHK_EN1, - SEC_ADDR(qm, SEC_BD_ERR_CHK_EN_REG1)); + qm->io_base + SEC_BD_ERR_CHK_EN_REG1); writel_relaxed(SEC_BD_ERR_CHK_EN3, - SEC_ADDR(qm, SEC_BD_ERR_CHK_EN_REG3)); + qm->io_base + SEC_BD_ERR_CHK_EN_REG3); /* config endian */ - reg = readl_relaxed(SEC_ADDR(qm, SEC_CONTROL_REG)); + reg = readl_relaxed(qm->io_base + SEC_CONTROL_REG); reg |= sec_get_endian(qm); - writel_relaxed(reg, SEC_ADDR(qm, SEC_CONTROL_REG)); + writel_relaxed(reg, qm->io_base + SEC_CONTROL_REG); return 0; } @@ -381,10 +419,6 @@ static void sec_debug_regs_clear(struct hisi_qm *qm) { int i; - /* clear current_qm */ - writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF); - writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF); - /* clear sec dfx regs */ writel(0x1, qm->io_base + SEC_CTRL_CNT_CLR_CE); for (i = 0; i < ARRAY_SIZE(sec_dfx_regs); i++) @@ -406,7 +440,7 @@ static void sec_hw_error_enable(struct hisi_qm *qm) return; } - val = readl(SEC_ADDR(qm, SEC_CONTROL_REG)); + val = readl(qm->io_base + SEC_CONTROL_REG); /* clear SEC hw error source if having */ writel(SEC_CORE_INT_CLEAR, qm->io_base + SEC_CORE_INT_SOURCE); @@ -422,14 +456,14 @@ static void sec_hw_error_enable(struct hisi_qm *qm) /* enable SEC block master OOO when m-bit error occur */ val = val | SEC_AXI_SHUTDOWN_ENABLE; - writel(val, SEC_ADDR(qm, SEC_CONTROL_REG)); + writel(val, qm->io_base + SEC_CONTROL_REG); } static void sec_hw_error_disable(struct hisi_qm *qm) { u32 val; - val = readl(SEC_ADDR(qm, SEC_CONTROL_REG)); + val = readl(qm->io_base + SEC_CONTROL_REG); /* disable RAS int */ writel(SEC_RAS_DISABLE, qm->io_base + SEC_RAS_CE_REG); @@ -442,51 +476,7 @@ static void sec_hw_error_disable(struct hisi_qm *qm) /* disable SEC block master OOO when m-bit error occur */ val = val & SEC_AXI_SHUTDOWN_DISABLE; - writel(val, SEC_ADDR(qm, SEC_CONTROL_REG)); -} - -static u32 sec_current_qm_read(struct sec_debug_file *file) -{ - struct hisi_qm *qm = file->qm; - - return readl(qm->io_base + QM_DFX_MB_CNT_VF); -} - -static int sec_current_qm_write(struct sec_debug_file *file, u32 val) -{ - struct hisi_qm *qm = file->qm; - u32 vfq_num; - u32 tmp; - - if (val > qm->vfs_num) - return -EINVAL; - - /* According PF or VF Dev ID to calculation curr_qm_qp_num and store */ - if (!val) { - qm->debug.curr_qm_qp_num = qm->qp_num; - } else { - vfq_num = (qm->ctrl_qp_num - qm->qp_num) / qm->vfs_num; - - if (val == qm->vfs_num) - qm->debug.curr_qm_qp_num = - qm->ctrl_qp_num - qm->qp_num - - (qm->vfs_num - 1) * vfq_num; - else - qm->debug.curr_qm_qp_num = vfq_num; - } - - writel(val, qm->io_base + QM_DFX_MB_CNT_VF); - writel(val, qm->io_base + QM_DFX_DB_CNT_VF); - - tmp = val | - (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK); - writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN); - - tmp = val | - (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK); - writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN); - - return 0; + writel(val, qm->io_base + SEC_CONTROL_REG); } static u32 sec_clear_enable_read(struct sec_debug_file *file) @@ -523,9 +513,6 @@ static ssize_t sec_debug_read(struct file *filp, char __user *buf, spin_lock_irq(&file->lock); switch (file->index) { - case SEC_CURRENT_QM: - val = sec_current_qm_read(file); - break; case SEC_CLEAR_ENABLE: val = sec_clear_enable_read(file); break; @@ -566,11 +553,6 @@ static ssize_t sec_debug_write(struct file *filp, const char __user *buf, spin_lock_irq(&file->lock); switch (file->index) { - case SEC_CURRENT_QM: - ret = sec_current_qm_write(file, val); - if (ret) - goto err_input; - break; case SEC_CLEAR_ENABLE: ret = sec_clear_enable_write(file, val); if (ret) @@ -655,7 +637,7 @@ static int sec_debug_init(struct hisi_qm *qm) int i; if (qm->pdev->device == SEC_PF_PCI_DEVICE_ID) { - for (i = SEC_CURRENT_QM; i < SEC_DEBUG_FILE_NUM; i++) { + for (i = SEC_CLEAR_ENABLE; i < SEC_DEBUG_FILE_NUM; i++) { spin_lock_init(&sec->debug.files[i].lock); sec->debug.files[i].index = i; sec->debug.files[i].qm = qm; @@ -712,7 +694,8 @@ static void sec_log_hw_error(struct hisi_qm *qm, u32 err_sts) err_val = readl(qm->io_base + SEC_CORE_SRAM_ECC_ERR_INFO); dev_err(dev, "multi ecc sram num=0x%x\n", - SEC_ECC_NUM(err_val)); + ((err_val) >> SEC_ECC_NUM) & + SEC_ECC_MASH); } } errs++; @@ -733,9 +716,23 @@ static void sec_open_axi_master_ooo(struct hisi_qm *qm) { u32 val; - val = readl(SEC_ADDR(qm, SEC_CONTROL_REG)); - writel(val & SEC_AXI_SHUTDOWN_DISABLE, SEC_ADDR(qm, SEC_CONTROL_REG)); - writel(val | SEC_AXI_SHUTDOWN_ENABLE, SEC_ADDR(qm, SEC_CONTROL_REG)); + val = readl(qm->io_base + SEC_CONTROL_REG); + writel(val & SEC_AXI_SHUTDOWN_DISABLE, qm->io_base + SEC_CONTROL_REG); + writel(val | SEC_AXI_SHUTDOWN_ENABLE, qm->io_base + SEC_CONTROL_REG); +} + +static void sec_err_info_init(struct hisi_qm *qm) +{ + struct hisi_qm_err_info *err_info = &qm->err_info; + + err_info->ce = QM_BASE_CE; + err_info->fe = 0; + err_info->ecc_2bits_mask = SEC_CORE_INT_STATUS_M_ECC; + err_info->dev_ce_mask = SEC_RAS_CE_ENB_MSK; + err_info->msi_wr_port = BIT(0); + err_info->acpi_rst = "SRST"; + err_info->nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT | + QM_ACC_WB_NOT_READY_TIMEOUT; } static const struct hisi_qm_err_ini sec_err_ini = { @@ -746,16 +743,7 @@ static const struct hisi_qm_err_ini sec_err_ini = { .clear_dev_hw_err_status = sec_clear_hw_err_status, .log_dev_hw_err = sec_log_hw_error, .open_axi_master_ooo = sec_open_axi_master_ooo, - .err_info = { - .ce = QM_BASE_CE, - .nfe = QM_BASE_NFE | QM_ACC_DO_TASK_TIMEOUT | - QM_ACC_WB_NOT_READY_TIMEOUT, - .fe = 0, - .ecc_2bits_mask = SEC_CORE_INT_STATUS_M_ECC, - .dev_ce_mask = SEC_RAS_CE_ENB_MSK, - .msi_wr_port = BIT(0), - .acpi_rst = "SRST", - } + .err_info_init = sec_err_info_init, }; static int sec_pf_probe_init(struct sec_dev *sec) @@ -763,12 +751,8 @@ static int sec_pf_probe_init(struct sec_dev *sec) struct hisi_qm *qm = &sec->qm; int ret; - if (qm->ver == QM_HW_V1) - qm->ctrl_qp_num = SEC_QUEUE_NUM_V1; - else - qm->ctrl_qp_num = SEC_QUEUE_NUM_V2; - qm->err_ini = &sec_err_ini; + qm->err_ini->err_info_init(qm); ret = sec_set_user_domain_and_cache(qm); if (ret) @@ -786,7 +770,7 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->pdev = pdev; qm->ver = pdev->revision; - qm->algs = "cipher\ndigest\naead\n"; + qm->algs = "cipher\ndigest\naead"; qm->mode = uacce_mode; qm->sqe_size = SEC_SQE_SIZE; qm->dev_name = sec_name; @@ -909,10 +893,15 @@ static int sec_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) pci_warn(pdev, "Failed to init debugfs!\n"); - ret = hisi_qm_alg_register(qm, &sec_devices); - if (ret < 0) { - pr_err("Failed to register driver to crypto.\n"); - goto err_qm_stop; + if (qm->qp_num >= ctx_q_num) { + ret = hisi_qm_alg_register(qm, &sec_devices); + if (ret < 0) { + pr_err("Failed to register driver to crypto.\n"); + goto err_qm_stop; + } + } else { + pci_warn(qm->pdev, + "Failed to use kernel mode, qp not enough!\n"); } if (qm->uacce) { @@ -948,7 +937,9 @@ static void sec_remove(struct pci_dev *pdev) struct hisi_qm *qm = pci_get_drvdata(pdev); hisi_qm_wait_task_finish(qm, &sec_devices); - hisi_qm_alg_unregister(qm, &sec_devices); + if (qm->qp_num >= ctx_q_num) + hisi_qm_alg_unregister(qm, &sec_devices); + if (qm->fun_type == QM_HW_PF && qm->vfs_num) hisi_qm_sriov_disable(pdev, true); diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c index 3bff6394acaf..057273769f26 100644 --- a/drivers/crypto/hisilicon/sgl.c +++ b/drivers/crypto/hisilicon/sgl.c @@ -56,7 +56,7 @@ struct hisi_acc_sgl_pool { struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, u32 count, u32 sge_nr) { - u32 sgl_size, block_size, sgl_num_per_block, block_num, remain_sgl = 0; + u32 sgl_size, block_size, sgl_num_per_block, block_num, remain_sgl; struct hisi_acc_sgl_pool *pool; struct mem_block *block; u32 i, j; @@ -66,6 +66,11 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, sgl_size = sizeof(struct acc_hw_sge) * sge_nr + sizeof(struct hisi_acc_hw_sgl); + + /* + * the pool may allocate a block of memory of size PAGE_SIZE * 2^(MAX_ORDER - 1), + * block size may exceed 2^31 on ia64, so the max of block size is 2^31 + */ block_size = 1 << (PAGE_SHIFT + MAX_ORDER <= 32 ? PAGE_SHIFT + MAX_ORDER - 1 : 31); sgl_num_per_block = block_size / sgl_size; @@ -85,8 +90,10 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, block[i].sgl = dma_alloc_coherent(dev, block_size, &block[i].sgl_dma, GFP_KERNEL); - if (!block[i].sgl) + if (!block[i].sgl) { + dev_err(dev, "Fail to allocate hw SG buffer!\n"); goto err_free_mem; + } block[i].size = block_size; } @@ -95,8 +102,10 @@ struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev, block[i].sgl = dma_alloc_coherent(dev, remain_sgl * sgl_size, &block[i].sgl_dma, GFP_KERNEL); - if (!block[i].sgl) + if (!block[i].sgl) { + dev_err(dev, "Fail to allocate remained hw SG buffer!\n"); goto err_free_mem; + } block[i].size = remain_sgl * sgl_size; } @@ -167,6 +176,7 @@ static void sg_map_to_hw_sg(struct scatterlist *sgl, { hw_sge->buf = sg_dma_address(sgl); hw_sge->len = cpu_to_le32(sg_dma_len(sgl)); + hw_sge->page_ctrl = sg_virt(sgl); } static void inc_hw_sgl_sge(struct hisi_acc_hw_sgl *hw_sgl) @@ -182,6 +192,18 @@ static void update_hw_sgl_sum_sge(struct hisi_acc_hw_sgl *hw_sgl, u16 sum) hw_sgl->entry_sum_in_chain = cpu_to_le16(sum); } +static void clear_hw_sgl_sge(struct hisi_acc_hw_sgl *hw_sgl) +{ + struct acc_hw_sge *hw_sge = hw_sgl->sge_entries; + int i; + + for (i = 0; i < le16_to_cpu(hw_sgl->entry_sum_in_sgl); i++) { + hw_sge[i].page_ctrl = NULL; + hw_sge[i].buf = 0; + hw_sge[i].len = 0; + } +} + /** * hisi_acc_sg_buf_map_to_hw_sgl - Map a scatterlist to a hw sgl. * @dev: The device which hw sgl belongs to. @@ -211,16 +233,19 @@ hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, sg_n = sg_nents(sgl); sg_n_mapped = dma_map_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL); - if (!sg_n_mapped) + if (!sg_n_mapped) { + dev_err(dev, "DMA mapping for SG error!\n"); return ERR_PTR(-EINVAL); + } if (sg_n_mapped > pool->sge_nr) { - dma_unmap_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL); + dev_err(dev, "the number of entries in input scatterlist is bigger than SGL pool setting.\n"); return ERR_PTR(-EINVAL); } curr_hw_sgl = acc_get_sgl(pool, index, &curr_sgl_dma); if (IS_ERR(curr_hw_sgl)) { + dev_err(dev, "Get SGL error!\n"); dma_unmap_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL); return ERR_PTR(-ENOMEM); @@ -256,7 +281,7 @@ void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl, return; dma_unmap_sg(dev, sgl, sg_nents(sgl), DMA_BIDIRECTIONAL); - + clear_hw_sgl_sge(hw_sgl); hw_sgl->entry_sum_in_chain = 0; hw_sgl->entry_sum_in_sgl = 0; hw_sgl->entry_length_in_sgl = 0; diff --git a/drivers/crypto/hisilicon/trng/trng.c b/drivers/crypto/hisilicon/trng/trng.c index 29712685498a..829f2caf0f67 100644 --- a/drivers/crypto/hisilicon/trng/trng.c +++ b/drivers/crypto/hisilicon/trng/trng.c @@ -18,6 +18,8 @@ #define HISI_TRNG_REG 0x00F0 #define HISI_TRNG_BYTES 4 #define HISI_TRNG_QUALITY 512 +#define HISI_TRNG_VERSION 0x01B8 +#define HISI_TRNG_VER_V1 GENMASK(31, 0) #define SLEEP_US 10 #define TIMEOUT_US 10000 #define SW_DRBG_NUM_SHIFT 2 @@ -50,6 +52,7 @@ struct hisi_trng { struct hisi_trng_list *trng_list; struct list_head list; struct hwrng rng; + u32 ver; bool is_used; struct mutex mutex; }; @@ -260,6 +263,7 @@ static int hisi_trng_probe(struct platform_device *pdev) return PTR_ERR(trng->base); trng->is_used = false; + trng->ver = readl(trng->base + HISI_TRNG_VERSION); if (!trng_devices.is_init) { INIT_LIST_HEAD(&trng_devices.list); mutex_init(&trng_devices.lock); @@ -267,7 +271,8 @@ static int hisi_trng_probe(struct platform_device *pdev) } hisi_trng_add_to_list(trng); - if (atomic_inc_return(&trng_active_devs) == 1) { + if (trng->ver != HISI_TRNG_VER_V1 && + atomic_inc_return(&trng_active_devs) == 1) { ret = crypto_register_rng(&hisi_trng_alg); if (ret) { dev_err(&pdev->dev, @@ -289,7 +294,8 @@ static int hisi_trng_probe(struct platform_device *pdev) return ret; err_crypto_unregister: - if (atomic_dec_return(&trng_active_devs) == 0) + if (trng->ver != HISI_TRNG_VER_V1 && + atomic_dec_return(&trng_active_devs) == 0) crypto_unregister_rng(&hisi_trng_alg); err_remove_from_list: @@ -305,7 +311,8 @@ static int hisi_trng_remove(struct platform_device *pdev) while (hisi_trng_del_from_list(trng)) ; - if (atomic_dec_return(&trng_active_devs) == 0) + if (trng->ver != HISI_TRNG_VER_V1 && + atomic_dec_return(&trng_active_devs) == 0) crypto_unregister_rng(&hisi_trng_alg); return 0; diff --git a/drivers/crypto/hisilicon/zip/zip.h b/drivers/crypto/hisilicon/zip/zip.h index 92397f993e23..517fdbdff3ea 100644 --- a/drivers/crypto/hisilicon/zip/zip.h +++ b/drivers/crypto/hisilicon/zip/zip.h @@ -33,35 +33,55 @@ struct hisi_zip_sqe { u32 consumed; u32 produced; u32 comp_data_length; + /* + * status: 0~7 bits + * rsvd: 8~31 bits + */ u32 dw3; u32 input_data_length; - u32 lba_l; - u32 lba_h; + u32 dw5; + u32 dw6; + /* + * in_sge_data_offset: 0~23 bits + * rsvd: 24~27 bits + * sqe_type: 29~31 bits + */ u32 dw7; + /* + * out_sge_data_offset: 0~23 bits + * rsvd: 24~31 bits + */ u32 dw8; + /* + * request_type: 0~7 bits + * buffer_type: 8~11 bits + * rsvd: 13~31 bits + */ u32 dw9; u32 dw10; - u32 priv_info; + u32 dw11; u32 dw12; - u32 tag; + /* tag: in sqe type 0 */ + u32 dw13; u32 dest_avail_out; - u32 rsvd0; - u32 comp_head_addr_l; - u32 comp_head_addr_h; + u32 dw15; + u32 dw16; + u32 dw17; u32 source_addr_l; u32 source_addr_h; u32 dest_addr_l; u32 dest_addr_h; - u32 stream_ctx_addr_l; - u32 stream_ctx_addr_h; - u32 cipher_key1_addr_l; - u32 cipher_key1_addr_h; - u32 cipher_key2_addr_l; - u32 cipher_key2_addr_h; + u32 dw22; + u32 dw23; + u32 dw24; + u32 dw25; + /* tag: in sqe type 3 */ + u32 dw26; + u32 dw27; u32 rsvd1[4]; }; int zip_create_qps(struct hisi_qp **qps, int ctx_num, int node); -int hisi_zip_register_to_crypto(void); -void hisi_zip_unregister_from_crypto(void); +int hisi_zip_register_to_crypto(struct hisi_qm *qm); +void hisi_zip_unregister_from_crypto(struct hisi_qm *qm); #endif diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c index 08b4660b014c..9520a4113c81 100644 --- a/drivers/crypto/hisilicon/zip/zip_crypto.c +++ b/drivers/crypto/hisilicon/zip/zip_crypto.c @@ -10,6 +10,7 @@ #define HZIP_BD_STATUS_M GENMASK(7, 0) /* hisi_zip_sqe dw7 */ #define HZIP_IN_SGE_DATA_OFFSET_M GENMASK(23, 0) +#define HZIP_SQE_TYPE_M GENMASK(31, 28) /* hisi_zip_sqe dw8 */ #define HZIP_OUT_SGE_DATA_OFFSET_M GENMASK(23, 0) /* hisi_zip_sqe dw9 */ @@ -91,8 +92,22 @@ struct hisi_zip_qp_ctx { struct hisi_zip_ctx *ctx; }; +struct hisi_zip_sqe_ops { + u8 sqe_type; + void (*fill_addr)(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req); + void (*fill_buf_size)(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req); + void (*fill_buf_type)(struct hisi_zip_sqe *sqe, u8 buf_type); + void (*fill_req_type)(struct hisi_zip_sqe *sqe, u8 req_type); + void (*fill_tag)(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req); + void (*fill_sqe_type)(struct hisi_zip_sqe *sqe, u8 sqe_type); + u32 (*get_tag)(struct hisi_zip_sqe *sqe); + u32 (*get_status)(struct hisi_zip_sqe *sqe); + u32 (*get_dstlen)(struct hisi_zip_sqe *sqe); +}; + struct hisi_zip_ctx { struct hisi_zip_qp_ctx qp_ctx[HZIP_CTX_Q_NUM]; + const struct hisi_zip_sqe_ops *ops; }; static int sgl_sge_nr_set(const char *val, const struct kernel_param *kp) @@ -119,35 +134,367 @@ static u16 sgl_sge_nr = HZIP_SGL_SGE_NR; module_param_cb(sgl_sge_nr, &sgl_sge_nr_ops, &sgl_sge_nr, 0444); MODULE_PARM_DESC(sgl_sge_nr, "Number of sge in sgl(1-255)"); -static void hisi_zip_config_buf_type(struct hisi_zip_sqe *sqe, u8 buf_type) +static u16 get_extra_field_size(const u8 *start) +{ + return *((u16 *)start) + GZIP_HEAD_FEXTRA_XLEN; +} + +static u32 get_name_field_size(const u8 *start) +{ + return strlen(start) + 1; +} + +static u32 get_comment_field_size(const u8 *start) +{ + return strlen(start) + 1; +} + +static u32 __get_gzip_head_size(const u8 *src) +{ + u8 head_flg = *(src + GZIP_HEAD_FLG_SHIFT); + u32 size = GZIP_HEAD_FEXTRA_SHIFT; + + if (head_flg & GZIP_HEAD_FEXTRA_BIT) + size += get_extra_field_size(src + size); + if (head_flg & GZIP_HEAD_FNAME_BIT) + size += get_name_field_size(src + size); + if (head_flg & GZIP_HEAD_FCOMMENT_BIT) + size += get_comment_field_size(src + size); + if (head_flg & GZIP_HEAD_FHCRC_BIT) + size += GZIP_HEAD_FHCRC_SIZE; + + return size; +} + +static size_t __maybe_unused get_gzip_head_size(struct scatterlist *sgl) +{ + char buf[HZIP_GZIP_HEAD_BUF]; + + sg_copy_to_buffer(sgl, sg_nents(sgl), buf, sizeof(buf)); + + return __get_gzip_head_size(buf); +} + +static int add_comp_head(struct scatterlist *dst, u8 req_type) +{ + int head_size = TO_HEAD_SIZE(req_type); + const u8 *head = TO_HEAD(req_type); + int ret; + + ret = sg_copy_from_buffer(dst, sg_nents(dst), head, head_size); + if (ret != head_size) { + pr_err("the head size of buffer is wrong (%d)!\n", ret); + return -ENOMEM; + } + + return head_size; +} + +static int get_comp_head_size(struct acomp_req *acomp_req, u8 req_type) +{ + if (!acomp_req->src || !acomp_req->slen) + return -EINVAL; + + if (req_type == HZIP_ALG_TYPE_GZIP && + acomp_req->slen < GZIP_HEAD_FEXTRA_SHIFT) + return -EINVAL; + + switch (req_type) { + case HZIP_ALG_TYPE_ZLIB: + return TO_HEAD_SIZE(HZIP_ALG_TYPE_ZLIB); + case HZIP_ALG_TYPE_GZIP: + return TO_HEAD_SIZE(HZIP_ALG_TYPE_GZIP); + default: + pr_err("request type does not support!\n"); + return -EINVAL; + } +} + +static struct hisi_zip_req *hisi_zip_create_req(struct acomp_req *req, + struct hisi_zip_qp_ctx *qp_ctx, + size_t head_size, bool is_comp) +{ + struct hisi_zip_req_q *req_q = &qp_ctx->req_q; + struct hisi_zip_req *q = req_q->q; + struct hisi_zip_req *req_cache; + int req_id; + + write_lock(&req_q->req_lock); + + req_id = find_first_zero_bit(req_q->req_bitmap, req_q->size); + if (req_id >= req_q->size) { + write_unlock(&req_q->req_lock); + dev_dbg(&qp_ctx->qp->qm->pdev->dev, "req cache is full!\n"); + return ERR_PTR(-EAGAIN); + } + set_bit(req_id, req_q->req_bitmap); + + req_cache = q + req_id; + req_cache->req_id = req_id; + req_cache->req = req; + + if (is_comp) { + req_cache->sskip = 0; + req_cache->dskip = head_size; + } else { + req_cache->sskip = head_size; + req_cache->dskip = 0; + } + + write_unlock(&req_q->req_lock); + + return req_cache; +} + +static void hisi_zip_remove_req(struct hisi_zip_qp_ctx *qp_ctx, + struct hisi_zip_req *req) +{ + struct hisi_zip_req_q *req_q = &qp_ctx->req_q; + + write_lock(&req_q->req_lock); + clear_bit(req->req_id, req_q->req_bitmap); + memset(req, 0, sizeof(struct hisi_zip_req)); + write_unlock(&req_q->req_lock); +} + +static void hisi_zip_fill_addr(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req) +{ + sqe->source_addr_l = lower_32_bits(req->dma_src); + sqe->source_addr_h = upper_32_bits(req->dma_src); + sqe->dest_addr_l = lower_32_bits(req->dma_dst); + sqe->dest_addr_h = upper_32_bits(req->dma_dst); +} + +static void hisi_zip_fill_buf_size(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req) +{ + struct acomp_req *a_req = req->req; + + sqe->input_data_length = a_req->slen - req->sskip; + sqe->dest_avail_out = a_req->dlen - req->dskip; + sqe->dw7 = FIELD_PREP(HZIP_IN_SGE_DATA_OFFSET_M, req->sskip); + sqe->dw8 = FIELD_PREP(HZIP_OUT_SGE_DATA_OFFSET_M, req->dskip); +} + +static void hisi_zip_fill_buf_type(struct hisi_zip_sqe *sqe, u8 buf_type) { u32 val; - val = (sqe->dw9) & ~HZIP_BUF_TYPE_M; + val = sqe->dw9 & ~HZIP_BUF_TYPE_M; val |= FIELD_PREP(HZIP_BUF_TYPE_M, buf_type); sqe->dw9 = val; } -static void hisi_zip_config_tag(struct hisi_zip_sqe *sqe, u32 tag) +static void hisi_zip_fill_req_type(struct hisi_zip_sqe *sqe, u8 req_type) { - sqe->tag = tag; + u32 val; + + val = sqe->dw9 & ~HZIP_REQ_TYPE_M; + val |= FIELD_PREP(HZIP_REQ_TYPE_M, req_type); + sqe->dw9 = val; } -static void hisi_zip_fill_sqe(struct hisi_zip_sqe *sqe, u8 req_type, - dma_addr_t s_addr, dma_addr_t d_addr, u32 slen, - u32 dlen, u32 sskip, u32 dskip) +static void hisi_zip_fill_tag_v1(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req) { + sqe->dw13 = req->req_id; +} + +static void hisi_zip_fill_tag_v2(struct hisi_zip_sqe *sqe, struct hisi_zip_req *req) +{ + sqe->dw26 = req->req_id; +} + +static void hisi_zip_fill_sqe_type(struct hisi_zip_sqe *sqe, u8 sqe_type) +{ + u32 val; + + val = sqe->dw7 & ~HZIP_SQE_TYPE_M; + val |= FIELD_PREP(HZIP_SQE_TYPE_M, sqe_type); + sqe->dw7 = val; +} + +static void hisi_zip_fill_sqe(struct hisi_zip_ctx *ctx, struct hisi_zip_sqe *sqe, + u8 req_type, struct hisi_zip_req *req) +{ + const struct hisi_zip_sqe_ops *ops = ctx->ops; + memset(sqe, 0, sizeof(struct hisi_zip_sqe)); - sqe->input_data_length = slen - sskip; - sqe->dw7 = FIELD_PREP(HZIP_IN_SGE_DATA_OFFSET_M, sskip); - sqe->dw8 = FIELD_PREP(HZIP_OUT_SGE_DATA_OFFSET_M, dskip); - sqe->dw9 = FIELD_PREP(HZIP_REQ_TYPE_M, req_type); - sqe->dest_avail_out = dlen - dskip; - sqe->source_addr_l = lower_32_bits(s_addr); - sqe->source_addr_h = upper_32_bits(s_addr); - sqe->dest_addr_l = lower_32_bits(d_addr); - sqe->dest_addr_h = upper_32_bits(d_addr); + ops->fill_addr(sqe, req); + ops->fill_buf_size(sqe, req); + ops->fill_buf_type(sqe, HZIP_SGL); + ops->fill_req_type(sqe, req_type); + ops->fill_tag(sqe, req); + ops->fill_sqe_type(sqe, ops->sqe_type); +} + +static int hisi_zip_do_work(struct hisi_zip_req *req, + struct hisi_zip_qp_ctx *qp_ctx) +{ + struct hisi_acc_sgl_pool *pool = qp_ctx->sgl_pool; + struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx; + struct acomp_req *a_req = req->req; + struct hisi_qp *qp = qp_ctx->qp; + struct device *dev = &qp->qm->pdev->dev; + struct hisi_zip_sqe zip_sqe; + int ret; + + if (!a_req->src || !a_req->slen || !a_req->dst || !a_req->dlen) + return -EINVAL; + + req->hw_src = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->src, pool, + req->req_id << 1, &req->dma_src); + if (IS_ERR(req->hw_src)) { + dev_err(dev, "failed to map the src buffer to hw sgl (%ld)!\n", + PTR_ERR(req->hw_src)); + return PTR_ERR(req->hw_src); + } + + req->hw_dst = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->dst, pool, + (req->req_id << 1) + 1, + &req->dma_dst); + if (IS_ERR(req->hw_dst)) { + ret = PTR_ERR(req->hw_dst); + dev_err(dev, "failed to map the dst buffer to hw slg (%d)!\n", + ret); + goto err_unmap_input; + } + + hisi_zip_fill_sqe(qp_ctx->ctx, &zip_sqe, qp->req_type, req); + + /* send command to start a task */ + atomic64_inc(&dfx->send_cnt); + ret = hisi_qp_send(qp, &zip_sqe); + if (ret < 0) { + atomic64_inc(&dfx->send_busy_cnt); + ret = -EAGAIN; + dev_dbg_ratelimited(dev, "failed to send request!\n"); + goto err_unmap_output; + } + + return -EINPROGRESS; + +err_unmap_output: + hisi_acc_sg_buf_unmap(dev, a_req->dst, req->hw_dst); +err_unmap_input: + hisi_acc_sg_buf_unmap(dev, a_req->src, req->hw_src); + return ret; +} + +static u32 hisi_zip_get_tag_v1(struct hisi_zip_sqe *sqe) +{ + return sqe->dw13; +} + +static u32 hisi_zip_get_tag_v2(struct hisi_zip_sqe *sqe) +{ + return sqe->dw26; +} + +static u32 hisi_zip_get_status(struct hisi_zip_sqe *sqe) +{ + return sqe->dw3 & HZIP_BD_STATUS_M; +} + +static u32 hisi_zip_get_dstlen(struct hisi_zip_sqe *sqe) +{ + return sqe->produced; +} + +static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data) +{ + struct hisi_zip_qp_ctx *qp_ctx = qp->qp_ctx; + const struct hisi_zip_sqe_ops *ops = qp_ctx->ctx->ops; + struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx; + struct hisi_zip_req_q *req_q = &qp_ctx->req_q; + struct device *dev = &qp->qm->pdev->dev; + struct hisi_zip_sqe *sqe = data; + u32 tag = ops->get_tag(sqe); + struct hisi_zip_req *req = req_q->q + tag; + struct acomp_req *acomp_req = req->req; + u32 status, dlen, head_size; + int err = 0; + + atomic64_inc(&dfx->recv_cnt); + status = ops->get_status(sqe); + if (status != 0 && status != HZIP_NC_ERR) { + dev_err(dev, "%scompress fail in qp%u: %u, output: %u\n", + (qp->alg_type == 0) ? "" : "de", qp->qp_id, status, + sqe->produced); + atomic64_inc(&dfx->err_bd_cnt); + err = -EIO; + } + + dlen = ops->get_dstlen(sqe); + + hisi_acc_sg_buf_unmap(dev, acomp_req->src, req->hw_src); + hisi_acc_sg_buf_unmap(dev, acomp_req->dst, req->hw_dst); + + head_size = (qp->alg_type == 0) ? TO_HEAD_SIZE(qp->req_type) : 0; + acomp_req->dlen = dlen + head_size; + + if (acomp_req->base.complete) + acomp_request_complete(acomp_req, err); + + hisi_zip_remove_req(qp_ctx, req); +} + +static int hisi_zip_acompress(struct acomp_req *acomp_req) +{ + struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm); + struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_COMP]; + struct device *dev = &qp_ctx->qp->qm->pdev->dev; + struct hisi_zip_req *req; + int head_size; + int ret; + + /* let's output compression head now */ + head_size = add_comp_head(acomp_req->dst, qp_ctx->qp->req_type); + if (head_size < 0) { + dev_err_ratelimited(dev, "failed to add comp head (%d)!\n", + head_size); + return head_size; + } + + req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, true); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = hisi_zip_do_work(req, qp_ctx); + if (ret != -EINPROGRESS) { + dev_info_ratelimited(dev, "failed to do compress (%d)!\n", ret); + hisi_zip_remove_req(qp_ctx, req); + } + + return ret; +} + +static int hisi_zip_adecompress(struct acomp_req *acomp_req) +{ + struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm); + struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_DECOMP]; + struct device *dev = &qp_ctx->qp->qm->pdev->dev; + struct hisi_zip_req *req; + int head_size, ret; + + head_size = get_comp_head_size(acomp_req, qp_ctx->qp->req_type); + if (head_size < 0) { + dev_err_ratelimited(dev, "failed to get comp head size (%d)!\n", + head_size); + return head_size; + } + + req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, false); + if (IS_ERR(req)) + return PTR_ERR(req); + + ret = hisi_zip_do_work(req, qp_ctx); + if (ret != -EINPROGRESS) { + dev_info_ratelimited(dev, "failed to do decompress (%d)!\n", + ret); + hisi_zip_remove_req(qp_ctx, req); + } + + return ret; } static int hisi_zip_start_qp(struct hisi_qp *qp, struct hisi_zip_qp_ctx *ctx, @@ -177,9 +524,36 @@ static void hisi_zip_release_qp(struct hisi_zip_qp_ctx *ctx) hisi_qm_release_qp(ctx->qp); } +static const struct hisi_zip_sqe_ops hisi_zip_ops_v1 = { + .sqe_type = 0, + .fill_addr = hisi_zip_fill_addr, + .fill_buf_size = hisi_zip_fill_buf_size, + .fill_buf_type = hisi_zip_fill_buf_type, + .fill_req_type = hisi_zip_fill_req_type, + .fill_tag = hisi_zip_fill_tag_v1, + .fill_sqe_type = hisi_zip_fill_sqe_type, + .get_tag = hisi_zip_get_tag_v1, + .get_status = hisi_zip_get_status, + .get_dstlen = hisi_zip_get_dstlen, +}; + +static const struct hisi_zip_sqe_ops hisi_zip_ops_v2 = { + .sqe_type = 0x3, + .fill_addr = hisi_zip_fill_addr, + .fill_buf_size = hisi_zip_fill_buf_size, + .fill_buf_type = hisi_zip_fill_buf_type, + .fill_req_type = hisi_zip_fill_req_type, + .fill_tag = hisi_zip_fill_tag_v2, + .fill_sqe_type = hisi_zip_fill_sqe_type, + .get_tag = hisi_zip_get_tag_v2, + .get_status = hisi_zip_get_status, + .get_dstlen = hisi_zip_get_dstlen, +}; + static int hisi_zip_ctx_init(struct hisi_zip_ctx *hisi_zip_ctx, u8 req_type, int node) { struct hisi_qp *qps[HZIP_CTX_Q_NUM] = { NULL }; + struct hisi_zip_qp_ctx *qp_ctx; struct hisi_zip *hisi_zip; int ret, i, j; @@ -193,8 +567,9 @@ static int hisi_zip_ctx_init(struct hisi_zip_ctx *hisi_zip_ctx, u8 req_type, int for (i = 0; i < HZIP_CTX_Q_NUM; i++) { /* alg_type = 0 for compress, 1 for decompress in hw sqe */ - ret = hisi_zip_start_qp(qps[i], &hisi_zip_ctx->qp_ctx[i], i, - req_type); + qp_ctx = &hisi_zip_ctx->qp_ctx[i]; + qp_ctx->ctx = hisi_zip_ctx; + ret = hisi_zip_start_qp(qps[i], qp_ctx, i, req_type); if (ret) { for (j = i - 1; j >= 0; j--) hisi_qm_stop_qp(hisi_zip_ctx->qp_ctx[j].qp); @@ -203,9 +578,14 @@ static int hisi_zip_ctx_init(struct hisi_zip_ctx *hisi_zip_ctx, u8 req_type, int return ret; } - hisi_zip_ctx->qp_ctx[i].zip_dev = hisi_zip; + qp_ctx->zip_dev = hisi_zip; } + if (hisi_zip->qm.ver < QM_HW_V3) + hisi_zip_ctx->ops = &hisi_zip_ops_v1; + else + hisi_zip_ctx->ops = &hisi_zip_ops_v2; + return 0; } @@ -217,38 +597,6 @@ static void hisi_zip_ctx_exit(struct hisi_zip_ctx *hisi_zip_ctx) hisi_zip_release_qp(&hisi_zip_ctx->qp_ctx[i]); } -static u16 get_extra_field_size(const u8 *start) -{ - return *((u16 *)start) + GZIP_HEAD_FEXTRA_XLEN; -} - -static u32 get_name_field_size(const u8 *start) -{ - return strlen(start) + 1; -} - -static u32 get_comment_field_size(const u8 *start) -{ - return strlen(start) + 1; -} - -static u32 __get_gzip_head_size(const u8 *src) -{ - u8 head_flg = *(src + GZIP_HEAD_FLG_SHIFT); - u32 size = GZIP_HEAD_FEXTRA_SHIFT; - - if (head_flg & GZIP_HEAD_FEXTRA_BIT) - size += get_extra_field_size(src + size); - if (head_flg & GZIP_HEAD_FNAME_BIT) - size += get_name_field_size(src + size); - if (head_flg & GZIP_HEAD_FCOMMENT_BIT) - size += get_comment_field_size(src + size); - if (head_flg & GZIP_HEAD_FHCRC_BIT) - size += GZIP_HEAD_FHCRC_SIZE; - - return size; -} - static int hisi_zip_create_req_q(struct hisi_zip_ctx *ctx) { struct hisi_zip_req_q *req_q; @@ -336,52 +684,6 @@ static void hisi_zip_release_sgl_pool(struct hisi_zip_ctx *ctx) ctx->qp_ctx[i].sgl_pool); } -static void hisi_zip_remove_req(struct hisi_zip_qp_ctx *qp_ctx, - struct hisi_zip_req *req) -{ - struct hisi_zip_req_q *req_q = &qp_ctx->req_q; - - write_lock(&req_q->req_lock); - clear_bit(req->req_id, req_q->req_bitmap); - memset(req, 0, sizeof(struct hisi_zip_req)); - write_unlock(&req_q->req_lock); -} - -static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data) -{ - struct hisi_zip_sqe *sqe = data; - struct hisi_zip_qp_ctx *qp_ctx = qp->qp_ctx; - struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx; - struct hisi_zip_req_q *req_q = &qp_ctx->req_q; - struct hisi_zip_req *req = req_q->q + sqe->tag; - struct acomp_req *acomp_req = req->req; - struct device *dev = &qp->qm->pdev->dev; - u32 status, dlen, head_size; - int err = 0; - - atomic64_inc(&dfx->recv_cnt); - status = sqe->dw3 & HZIP_BD_STATUS_M; - if (status != 0 && status != HZIP_NC_ERR) { - dev_err(dev, "%scompress fail in qp%u: %u, output: %u\n", - (qp->alg_type == 0) ? "" : "de", qp->qp_id, status, - sqe->produced); - atomic64_inc(&dfx->err_bd_cnt); - err = -EIO; - } - dlen = sqe->produced; - - hisi_acc_sg_buf_unmap(dev, acomp_req->src, req->hw_src); - hisi_acc_sg_buf_unmap(dev, acomp_req->dst, req->hw_dst); - - head_size = (qp->alg_type == 0) ? TO_HEAD_SIZE(qp->req_type) : 0; - acomp_req->dlen = dlen + head_size; - - if (acomp_req->base.complete) - acomp_request_complete(acomp_req, err); - - hisi_zip_remove_req(qp_ctx, req); -} - static void hisi_zip_set_acomp_cb(struct hisi_zip_ctx *ctx, void (*fn)(struct hisi_qp *, void *)) { @@ -439,204 +741,6 @@ static void hisi_zip_acomp_exit(struct crypto_acomp *tfm) hisi_zip_ctx_exit(ctx); } -static int add_comp_head(struct scatterlist *dst, u8 req_type) -{ - int head_size = TO_HEAD_SIZE(req_type); - const u8 *head = TO_HEAD(req_type); - int ret; - - ret = sg_copy_from_buffer(dst, sg_nents(dst), head, head_size); - if (ret != head_size) { - pr_err("the head size of buffer is wrong (%d)!\n", ret); - return -ENOMEM; - } - - return head_size; -} - -static size_t __maybe_unused get_gzip_head_size(struct scatterlist *sgl) -{ - char buf[HZIP_GZIP_HEAD_BUF]; - - sg_copy_to_buffer(sgl, sg_nents(sgl), buf, sizeof(buf)); - - return __get_gzip_head_size(buf); -} - -static int get_comp_head_size(struct acomp_req *acomp_req, u8 req_type) -{ - if (!acomp_req->src || !acomp_req->slen) - return -EINVAL; - - if ((req_type == HZIP_ALG_TYPE_GZIP) && - (acomp_req->slen < GZIP_HEAD_FEXTRA_SHIFT)) - return -EINVAL; - - switch (req_type) { - case HZIP_ALG_TYPE_ZLIB: - return TO_HEAD_SIZE(HZIP_ALG_TYPE_ZLIB); - case HZIP_ALG_TYPE_GZIP: - return TO_HEAD_SIZE(HZIP_ALG_TYPE_GZIP); - default: - pr_err("request type does not support!\n"); - return -EINVAL; - } -} - -static struct hisi_zip_req *hisi_zip_create_req(struct acomp_req *req, - struct hisi_zip_qp_ctx *qp_ctx, - size_t head_size, bool is_comp) -{ - struct hisi_zip_req_q *req_q = &qp_ctx->req_q; - struct hisi_zip_req *q = req_q->q; - struct hisi_zip_req *req_cache; - int req_id; - - write_lock(&req_q->req_lock); - - req_id = find_first_zero_bit(req_q->req_bitmap, req_q->size); - if (req_id >= req_q->size) { - write_unlock(&req_q->req_lock); - dev_dbg(&qp_ctx->qp->qm->pdev->dev, "req cache is full!\n"); - return ERR_PTR(-EAGAIN); - } - set_bit(req_id, req_q->req_bitmap); - - req_cache = q + req_id; - req_cache->req_id = req_id; - req_cache->req = req; - - if (is_comp) { - req_cache->sskip = 0; - req_cache->dskip = head_size; - } else { - req_cache->sskip = head_size; - req_cache->dskip = 0; - } - - write_unlock(&req_q->req_lock); - - return req_cache; -} - -static int hisi_zip_do_work(struct hisi_zip_req *req, - struct hisi_zip_qp_ctx *qp_ctx) -{ - struct acomp_req *a_req = req->req; - struct hisi_qp *qp = qp_ctx->qp; - struct device *dev = &qp->qm->pdev->dev; - struct hisi_acc_sgl_pool *pool = qp_ctx->sgl_pool; - struct hisi_zip_dfx *dfx = &qp_ctx->zip_dev->dfx; - struct hisi_zip_sqe zip_sqe; - dma_addr_t input, output; - int ret; - - if (!a_req->src || !a_req->slen || !a_req->dst || !a_req->dlen) - return -EINVAL; - - req->hw_src = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->src, pool, - req->req_id << 1, &input); - if (IS_ERR(req->hw_src)) { - dev_err(dev, "failed to map the src buffer to hw sgl (%ld)!\n", - PTR_ERR(req->hw_src)); - return PTR_ERR(req->hw_src); - } - req->dma_src = input; - - req->hw_dst = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->dst, pool, - (req->req_id << 1) + 1, - &output); - if (IS_ERR(req->hw_dst)) { - ret = PTR_ERR(req->hw_dst); - dev_err(dev, "failed to map the dst buffer to hw slg (%d)!\n", - ret); - goto err_unmap_input; - } - req->dma_dst = output; - - hisi_zip_fill_sqe(&zip_sqe, qp->req_type, input, output, a_req->slen, - a_req->dlen, req->sskip, req->dskip); - hisi_zip_config_buf_type(&zip_sqe, HZIP_SGL); - hisi_zip_config_tag(&zip_sqe, req->req_id); - - /* send command to start a task */ - atomic64_inc(&dfx->send_cnt); - ret = hisi_qp_send(qp, &zip_sqe); - if (ret < 0) { - atomic64_inc(&dfx->send_busy_cnt); - ret = -EAGAIN; - dev_dbg_ratelimited(dev, "failed to send request!\n"); - goto err_unmap_output; - } - - return -EINPROGRESS; - -err_unmap_output: - hisi_acc_sg_buf_unmap(dev, a_req->dst, req->hw_dst); -err_unmap_input: - hisi_acc_sg_buf_unmap(dev, a_req->src, req->hw_src); - return ret; -} - -static int hisi_zip_acompress(struct acomp_req *acomp_req) -{ - struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm); - struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_COMP]; - struct device *dev = &qp_ctx->qp->qm->pdev->dev; - struct hisi_zip_req *req; - int head_size; - int ret; - - /* let's output compression head now */ - head_size = add_comp_head(acomp_req->dst, qp_ctx->qp->req_type); - if (head_size < 0) { - dev_err_ratelimited(dev, "failed to add comp head (%d)!\n", - head_size); - return head_size; - } - - req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, true); - if (IS_ERR(req)) - return PTR_ERR(req); - - ret = hisi_zip_do_work(req, qp_ctx); - if (ret != -EINPROGRESS) { - dev_info_ratelimited(dev, "failed to do compress (%d)!\n", ret); - hisi_zip_remove_req(qp_ctx, req); - } - - return ret; -} - -static int hisi_zip_adecompress(struct acomp_req *acomp_req) -{ - struct hisi_zip_ctx *ctx = crypto_tfm_ctx(acomp_req->base.tfm); - struct hisi_zip_qp_ctx *qp_ctx = &ctx->qp_ctx[HZIP_QPC_DECOMP]; - struct device *dev = &qp_ctx->qp->qm->pdev->dev; - struct hisi_zip_req *req; - int head_size, ret; - - head_size = get_comp_head_size(acomp_req, qp_ctx->qp->req_type); - if (head_size < 0) { - dev_err_ratelimited(dev, "failed to get comp head size (%d)!\n", - head_size); - return head_size; - } - - req = hisi_zip_create_req(acomp_req, qp_ctx, head_size, false); - if (IS_ERR(req)) - return PTR_ERR(req); - - ret = hisi_zip_do_work(req, qp_ctx); - if (ret != -EINPROGRESS) { - dev_info_ratelimited(dev, "failed to do decompress (%d)!\n", - ret); - hisi_zip_remove_req(qp_ctx, req); - } - - return ret; -} - static struct acomp_alg hisi_zip_acomp_zlib = { .init = hisi_zip_acomp_init, .exit = hisi_zip_acomp_exit, @@ -665,7 +769,7 @@ static struct acomp_alg hisi_zip_acomp_gzip = { } }; -int hisi_zip_register_to_crypto(void) +int hisi_zip_register_to_crypto(struct hisi_qm *qm) { int ret; @@ -684,7 +788,7 @@ int hisi_zip_register_to_crypto(void) return ret; } -void hisi_zip_unregister_from_crypto(void) +void hisi_zip_unregister_from_crypto(struct hisi_qm *qm) { crypto_unregister_acomp(&hisi_zip_acomp_gzip); crypto_unregister_acomp(&hisi_zip_acomp_zlib); diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 02c445722445..2178b40e9f82 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -18,7 +18,6 @@ #define PCI_DEVICE_ID_ZIP_VF 0xa251 #define HZIP_QUEUE_NUM_V1 4096 -#define HZIP_QUEUE_NUM_V2 1024 #define HZIP_CLOCK_GATE_CTRL 0x301004 #define COMP0_ENABLE BIT(0) @@ -69,10 +68,10 @@ #define HZIP_CORE_INT_RAS_CE_ENABLE 0x1 #define HZIP_CORE_INT_RAS_NFE_ENB 0x301164 #define HZIP_CORE_INT_RAS_FE_ENB 0x301168 -#define HZIP_CORE_INT_RAS_NFE_ENABLE 0x7FE +#define HZIP_CORE_INT_RAS_NFE_ENABLE 0x1FFE #define HZIP_SRAM_ECC_ERR_NUM_SHIFT 16 #define HZIP_SRAM_ECC_ERR_ADDR_SHIFT 24 -#define HZIP_CORE_INT_MASK_ALL GENMASK(10, 0) +#define HZIP_CORE_INT_MASK_ALL GENMASK(12, 0) #define HZIP_COMP_CORE_NUM 2 #define HZIP_DECOMP_CORE_NUM 6 #define HZIP_CORE_NUM (HZIP_COMP_CORE_NUM + \ @@ -134,17 +133,17 @@ static const struct hisi_zip_hw_error zip_hw_error[] = { { .int_msk = BIT(8), .msg = "zip_com_inf_err" }, { .int_msk = BIT(9), .msg = "zip_enc_inf_err" }, { .int_msk = BIT(10), .msg = "zip_pre_out_err" }, + { .int_msk = BIT(11), .msg = "zip_axi_poison_err" }, + { .int_msk = BIT(12), .msg = "zip_sva_err" }, { /* sentinel */ } }; enum ctrl_debug_file_index { - HZIP_CURRENT_QM, HZIP_CLEAR_ENABLE, HZIP_DEBUG_FILE_NUM, }; static const char * const ctrl_debug_file_name[] = { - [HZIP_CURRENT_QM] = "current_qm", [HZIP_CLEAR_ENABLE] = "clear_enable", }; @@ -363,48 +362,6 @@ static inline struct hisi_qm *file_to_qm(struct ctrl_debug_file *file) return &hisi_zip->qm; } -static u32 current_qm_read(struct ctrl_debug_file *file) -{ - struct hisi_qm *qm = file_to_qm(file); - - return readl(qm->io_base + QM_DFX_MB_CNT_VF); -} - -static int current_qm_write(struct ctrl_debug_file *file, u32 val) -{ - struct hisi_qm *qm = file_to_qm(file); - u32 vfq_num; - u32 tmp; - - if (val > qm->vfs_num) - return -EINVAL; - - /* According PF or VF Dev ID to calculation curr_qm_qp_num and store */ - if (val == 0) { - qm->debug.curr_qm_qp_num = qm->qp_num; - } else { - vfq_num = (qm->ctrl_qp_num - qm->qp_num) / qm->vfs_num; - if (val == qm->vfs_num) - qm->debug.curr_qm_qp_num = qm->ctrl_qp_num - - qm->qp_num - (qm->vfs_num - 1) * vfq_num; - else - qm->debug.curr_qm_qp_num = vfq_num; - } - - writel(val, qm->io_base + QM_DFX_MB_CNT_VF); - writel(val, qm->io_base + QM_DFX_DB_CNT_VF); - - tmp = val | - (readl(qm->io_base + QM_DFX_SQE_CNT_VF_SQN) & CURRENT_Q_MASK); - writel(tmp, qm->io_base + QM_DFX_SQE_CNT_VF_SQN); - - tmp = val | - (readl(qm->io_base + QM_DFX_CQE_CNT_VF_CQN) & CURRENT_Q_MASK); - writel(tmp, qm->io_base + QM_DFX_CQE_CNT_VF_CQN); - - return 0; -} - static u32 clear_enable_read(struct ctrl_debug_file *file) { struct hisi_qm *qm = file_to_qm(file); @@ -438,9 +395,6 @@ static ssize_t hisi_zip_ctrl_debug_read(struct file *filp, char __user *buf, spin_lock_irq(&file->lock); switch (file->index) { - case HZIP_CURRENT_QM: - val = current_qm_read(file); - break; case HZIP_CLEAR_ENABLE: val = clear_enable_read(file); break; @@ -478,11 +432,6 @@ static ssize_t hisi_zip_ctrl_debug_write(struct file *filp, spin_lock_irq(&file->lock); switch (file->index) { - case HZIP_CURRENT_QM: - ret = current_qm_write(file, val); - if (ret) - goto err_input; - break; case HZIP_CLEAR_ENABLE: ret = clear_enable_write(file, val); if (ret) @@ -580,7 +529,7 @@ static int hisi_zip_ctrl_debug_init(struct hisi_qm *qm) struct hisi_zip *zip = container_of(qm, struct hisi_zip, qm); int i; - for (i = HZIP_CURRENT_QM; i < HZIP_DEBUG_FILE_NUM; i++) { + for (i = HZIP_CLEAR_ENABLE; i < HZIP_DEBUG_FILE_NUM; i++) { spin_lock_init(&zip->ctrl->files[i].lock); zip->ctrl->files[i].ctrl = zip->ctrl; zip->ctrl->files[i].index = i; @@ -627,10 +576,6 @@ static void hisi_zip_debug_regs_clear(struct hisi_qm *qm) { int i, j; - /* clear current_qm */ - writel(0x0, qm->io_base + QM_DFX_MB_CNT_VF); - writel(0x0, qm->io_base + QM_DFX_DB_CNT_VF); - /* enable register read_clear bit */ writel(HZIP_RD_CNT_CLR_CE_EN, qm->io_base + HZIP_SOFT_CTRL_CNT_CLR_CE); for (i = 0; i < ARRAY_SIZE(core_offsets); i++) @@ -714,6 +659,22 @@ static void hisi_zip_close_axi_master_ooo(struct hisi_qm *qm) qm->io_base + HZIP_CORE_INT_SET); } +static void hisi_zip_err_info_init(struct hisi_qm *qm) +{ + struct hisi_qm_err_info *err_info = &qm->err_info; + + err_info->ce = QM_BASE_CE; + err_info->fe = 0; + err_info->ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC; + err_info->dev_ce_mask = HZIP_CORE_INT_RAS_CE_ENABLE; + err_info->msi_wr_port = HZIP_WR_PORT; + err_info->acpi_rst = "ZRST"; + err_info->nfe = QM_BASE_NFE | QM_ACC_WB_NOT_READY_TIMEOUT; + + if (qm->ver >= QM_HW_V3) + err_info->nfe |= QM_ACC_DO_TASK_TIMEOUT; +} + static const struct hisi_qm_err_ini hisi_zip_err_ini = { .hw_init = hisi_zip_set_user_domain_and_cache, .hw_err_enable = hisi_zip_hw_error_enable, @@ -723,16 +684,7 @@ static const struct hisi_qm_err_ini hisi_zip_err_ini = { .log_dev_hw_err = hisi_zip_log_hw_error, .open_axi_master_ooo = hisi_zip_open_axi_master_ooo, .close_axi_master_ooo = hisi_zip_close_axi_master_ooo, - .err_info = { - .ce = QM_BASE_CE, - .nfe = QM_BASE_NFE | - QM_ACC_WB_NOT_READY_TIMEOUT, - .fe = 0, - .ecc_2bits_mask = HZIP_CORE_INT_STATUS_M_ECC, - .dev_ce_mask = HZIP_CORE_INT_RAS_CE_ENABLE, - .msi_wr_port = HZIP_WR_PORT, - .acpi_rst = "ZRST", - } + .err_info_init = hisi_zip_err_info_init, }; static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) @@ -746,13 +698,8 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) hisi_zip->ctrl = ctrl; ctrl->hisi_zip = hisi_zip; - - if (qm->ver == QM_HW_V1) - qm->ctrl_qp_num = HZIP_QUEUE_NUM_V1; - else - qm->ctrl_qp_num = HZIP_QUEUE_NUM_V2; - qm->err_ini = &hisi_zip_err_ini; + qm->err_ini->err_info_init(qm); hisi_zip_set_user_domain_and_cache(qm); hisi_qm_dev_err_init(qm); diff --git a/drivers/crypto/img-hash.c b/drivers/crypto/img-hash.c index e813115d5432..aa4c7b2af3e2 100644 --- a/drivers/crypto/img-hash.c +++ b/drivers/crypto/img-hash.c @@ -963,8 +963,6 @@ static int img_hash_probe(struct platform_device *pdev) hdev->io_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(hdev->io_base)) { err = PTR_ERR(hdev->io_base); - dev_err(dev, "can't ioremap, returned %d\n", err); - goto res_err; } @@ -972,7 +970,6 @@ static int img_hash_probe(struct platform_device *pdev) hash_res = platform_get_resource(pdev, IORESOURCE_MEM, 1); hdev->cpu_addr = devm_ioremap_resource(dev, hash_res); if (IS_ERR(hdev->cpu_addr)) { - dev_err(dev, "can't ioremap write port\n"); err = PTR_ERR(hdev->cpu_addr); goto res_err; } diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c index 6364583b88b2..9ff885d50edf 100644 --- a/drivers/crypto/inside-secure/safexcel.c +++ b/drivers/crypto/inside-secure/safexcel.c @@ -688,7 +688,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv) /* Leave the DSE threads reset state */ writel(0, EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL(pe)); - /* Configure the procesing engine thresholds */ + /* Configure the processing engine thresholds */ writel(EIP197_PE_OUT_DBUF_THRES_MIN(opbuflo) | EIP197_PE_OUT_DBUF_THRES_MAX(opbufhi), EIP197_PE(priv) + EIP197_PE_OUT_DBUF_THRES(pe)); diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c index 8b0f17fc09fb..0616e369522e 100644 --- a/drivers/crypto/ixp4xx_crypto.c +++ b/drivers/crypto/ixp4xx_crypto.c @@ -265,7 +265,7 @@ static int setup_crypt_desc(void) return 0; } -static spinlock_t desc_lock; +static DEFINE_SPINLOCK(desc_lock); static struct crypt_ctl *get_crypt_desc(void) { int i; @@ -293,7 +293,7 @@ static struct crypt_ctl *get_crypt_desc(void) } } -static spinlock_t emerg_lock; +static DEFINE_SPINLOCK(emerg_lock); static struct crypt_ctl *get_crypt_desc_emerg(void) { int i; @@ -1379,9 +1379,6 @@ static int __init ixp_module_init(void) if (IS_ERR(pdev)) return PTR_ERR(pdev); - spin_lock_init(&desc_lock); - spin_lock_init(&emerg_lock); - err = init_ixp_crypto(&pdev->dev); if (err) { platform_device_unregister(pdev); diff --git a/drivers/crypto/keembay/keembay-ocs-aes-core.c b/drivers/crypto/keembay/keembay-ocs-aes-core.c index b6b25d994af3..e2a39fdaf623 100644 --- a/drivers/crypto/keembay/keembay-ocs-aes-core.c +++ b/drivers/crypto/keembay/keembay-ocs-aes-core.c @@ -1623,10 +1623,8 @@ static int kmb_ocs_aes_probe(struct platform_device *pdev) } aes_dev->base_reg = devm_ioremap_resource(&pdev->dev, aes_mem); - if (IS_ERR(aes_dev->base_reg)) { - dev_err(dev, "Failed to get base address\n"); + if (IS_ERR(aes_dev->base_reg)) return PTR_ERR(aes_dev->base_reg); - } /* Get and request IRQ */ aes_dev->irq = platform_get_irq(pdev, 0); @@ -1649,8 +1647,10 @@ static int kmb_ocs_aes_probe(struct platform_device *pdev) /* Initialize crypto engine */ aes_dev->engine = crypto_engine_alloc_init(dev, true); - if (!aes_dev->engine) + if (!aes_dev->engine) { + rc = -ENOMEM; goto list_del; + } rc = crypto_engine_start(aes_dev->engine); if (rc) { diff --git a/drivers/crypto/keembay/keembay-ocs-hcu-core.c b/drivers/crypto/keembay/keembay-ocs-hcu-core.c index c4b97b4160e9..0379dbf32a4c 100644 --- a/drivers/crypto/keembay/keembay-ocs-hcu-core.c +++ b/drivers/crypto/keembay/keembay-ocs-hcu-core.c @@ -1192,10 +1192,8 @@ static int kmb_ocs_hcu_probe(struct platform_device *pdev) } hcu_dev->io_base = devm_ioremap_resource(dev, hcu_mem); - if (IS_ERR(hcu_dev->io_base)) { - dev_err(dev, "Could not io-remap mem resource.\n"); + if (IS_ERR(hcu_dev->io_base)) return PTR_ERR(hcu_dev->io_base); - } init_completion(&hcu_dev->irq_done); @@ -1220,8 +1218,10 @@ static int kmb_ocs_hcu_probe(struct platform_device *pdev) /* Initialize crypto engine */ hcu_dev->engine = crypto_engine_alloc_init(dev, 1); - if (!hcu_dev->engine) + if (!hcu_dev->engine) { + rc = -ENOMEM; goto list_del; + } rc = crypto_engine_start(hcu_dev->engine); if (rc) { diff --git a/drivers/crypto/keembay/ocs-hcu.c b/drivers/crypto/keembay/ocs-hcu.c index 81eecacf603a..deb9bd460ee6 100644 --- a/drivers/crypto/keembay/ocs-hcu.c +++ b/drivers/crypto/keembay/ocs-hcu.c @@ -93,7 +93,7 @@ #define OCS_HCU_WAIT_BUSY_TIMEOUT_US 1000000 /** - * struct ocs_hcu_dma_list - An entry in an OCS DMA linked list. + * struct ocs_hcu_dma_entry - An entry in an OCS DMA linked list. * @src_addr: Source address of the data. * @src_len: Length of data to be fetched. * @nxt_desc: Next descriptor to fetch. @@ -107,7 +107,7 @@ struct ocs_hcu_dma_entry { }; /** - * struct ocs_dma_list - OCS-specific DMA linked list. + * struct ocs_hcu_dma_list - OCS-specific DMA linked list. * @head: The head of the list (points to the array backing the list). * @tail: The current tail of the list; NULL if the list is empty. * @dma_addr: The DMA address of @head (i.e., the DMA address of the backing @@ -597,7 +597,7 @@ int ocs_hcu_hash_init(struct ocs_hcu_hash_ctx *ctx, enum ocs_hcu_algo algo) } /** - * ocs_hcu_digest() - Perform a hashing iteration. + * ocs_hcu_hash_update() - Perform a hashing iteration. * @hcu_dev: The OCS HCU device to use. * @ctx: The OCS HCU hashing context. * @dma_list: The OCS DMA list mapping the input data to process. @@ -632,7 +632,7 @@ int ocs_hcu_hash_update(struct ocs_hcu_dev *hcu_dev, } /** - * ocs_hcu_hash_final() - Update and finalize hash computation. + * ocs_hcu_hash_finup() - Update and finalize hash computation. * @hcu_dev: The OCS HCU device to use. * @ctx: The OCS HCU hashing context. * @dma_list: The OCS DMA list mapping the input data to process. diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h index 3518fac29834..ecedd91a8d85 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h @@ -121,14 +121,14 @@ int otx2_cpt_send_mbox_msg(struct otx2_mbox *mbox, struct pci_dev *pdev); int otx2_cpt_send_af_reg_requests(struct otx2_mbox *mbox, struct pci_dev *pdev); -int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox, - struct pci_dev *pdev, u64 reg, u64 *val); +int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, + u64 reg, u64 *val, int blkaddr); int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, - u64 reg, u64 val); + u64 reg, u64 val, int blkaddr); int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, - u64 reg, u64 *val); + u64 reg, u64 *val, int blkaddr); int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, - u64 reg, u64 val); + u64 reg, u64 val, int blkaddr); struct otx2_cptlfs_info; int otx2_cpt_attach_rscrs_msg(struct otx2_cptlfs_info *lfs); int otx2_cpt_detach_rsrcs_msg(struct otx2_cptlfs_info *lfs); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c index 51cb6404ded7..9074876d38e5 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_mbox_common.c @@ -43,7 +43,7 @@ int otx2_cpt_send_af_reg_requests(struct otx2_mbox *mbox, struct pci_dev *pdev) } int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, - u64 reg, u64 *val) + u64 reg, u64 *val, int blkaddr) { struct cpt_rd_wr_reg_msg *reg_msg; @@ -62,12 +62,13 @@ int otx2_cpt_add_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, reg_msg->is_write = 0; reg_msg->reg_offset = reg; reg_msg->ret_val = val; + reg_msg->blkaddr = blkaddr; return 0; } int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, - u64 reg, u64 val) + u64 reg, u64 val, int blkaddr) { struct cpt_rd_wr_reg_msg *reg_msg; @@ -86,16 +87,17 @@ int otx2_cpt_add_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, reg_msg->is_write = 1; reg_msg->reg_offset = reg; reg_msg->val = val; + reg_msg->blkaddr = blkaddr; return 0; } int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, - u64 reg, u64 *val) + u64 reg, u64 *val, int blkaddr) { int ret; - ret = otx2_cpt_add_read_af_reg(mbox, pdev, reg, val); + ret = otx2_cpt_add_read_af_reg(mbox, pdev, reg, val, blkaddr); if (ret) return ret; @@ -103,11 +105,11 @@ int otx2_cpt_read_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, } int otx2_cpt_write_af_reg(struct otx2_mbox *mbox, struct pci_dev *pdev, - u64 reg, u64 val) + u64 reg, u64 val, int blkaddr) { int ret; - ret = otx2_cpt_add_write_af_reg(mbox, pdev, reg, val); + ret = otx2_cpt_add_write_af_reg(mbox, pdev, reg, val, blkaddr); if (ret) return ret; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c index 823a4571fd67..34aba1532761 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptlf.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.c @@ -56,7 +56,7 @@ static int cptlf_set_pri(struct otx2_cptlf_info *lf, int pri) ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev, CPT_AF_LFX_CTL(lf->slot), - &lf_ctrl.u); + &lf_ctrl.u, lfs->blkaddr); if (ret) return ret; @@ -64,7 +64,7 @@ static int cptlf_set_pri(struct otx2_cptlf_info *lf, int pri) ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev, CPT_AF_LFX_CTL(lf->slot), - lf_ctrl.u); + lf_ctrl.u, lfs->blkaddr); return ret; } @@ -77,7 +77,7 @@ static int cptlf_set_eng_grps_mask(struct otx2_cptlf_info *lf, ret = otx2_cpt_read_af_reg(lfs->mbox, lfs->pdev, CPT_AF_LFX_CTL(lf->slot), - &lf_ctrl.u); + &lf_ctrl.u, lfs->blkaddr); if (ret) return ret; @@ -85,7 +85,7 @@ static int cptlf_set_eng_grps_mask(struct otx2_cptlf_info *lf, ret = otx2_cpt_write_af_reg(lfs->mbox, lfs->pdev, CPT_AF_LFX_CTL(lf->slot), - lf_ctrl.u); + lf_ctrl.u, lfs->blkaddr); return ret; } diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h index 314e97354100..ab1678fc564d 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptlf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptlf.h @@ -95,6 +95,7 @@ struct otx2_cptlfs_info { u8 kcrypto_eng_grp_num; /* Kernel crypto engine group number */ u8 kvf_limits; /* Kernel crypto limits */ atomic_t state; /* LF's state. started/reset */ + int blkaddr; /* CPT blkaddr: BLKADDR_CPT0/BLKADDR_CPT1 */ }; static inline void otx2_cpt_free_instruction_queues( diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h index 8c899ad531a5..e19af1356f12 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf.h +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf.h @@ -51,6 +51,7 @@ struct otx2_cptpf_dev { u8 max_vfs; /* Maximum number of VFs supported by CPT */ u8 enabled_vfs; /* Number of enabled VFs */ u8 kvf_limits; /* Kernel crypto limits */ + bool has_cpt1; }; irqreturn_t otx2_cptpf_afpf_mbox_intr(int irq, void *arg); diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c index 5277e04badd9..58f47e3ab62e 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_main.c @@ -451,19 +451,19 @@ static int cpt_is_pf_usable(struct otx2_cptpf_dev *cptpf) return 0; } -static int cptpf_device_reset(struct otx2_cptpf_dev *cptpf) +static int cptx_device_reset(struct otx2_cptpf_dev *cptpf, int blkaddr) { int timeout = 10, ret; u64 reg = 0; ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_BLK_RST, 0x1); + CPT_AF_BLK_RST, 0x1, blkaddr); if (ret) return ret; do { ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_BLK_RST, ®); + CPT_AF_BLK_RST, ®, blkaddr); if (ret) return ret; @@ -478,11 +478,35 @@ static int cptpf_device_reset(struct otx2_cptpf_dev *cptpf) return ret; } +static int cptpf_device_reset(struct otx2_cptpf_dev *cptpf) +{ + int ret = 0; + + if (cptpf->has_cpt1) { + ret = cptx_device_reset(cptpf, BLKADDR_CPT1); + if (ret) + return ret; + } + return cptx_device_reset(cptpf, BLKADDR_CPT0); +} + +static void cptpf_check_block_implemented(struct otx2_cptpf_dev *cptpf) +{ + u64 cfg; + + cfg = otx2_cpt_read64(cptpf->reg_base, BLKADDR_RVUM, 0, + RVU_PF_BLOCK_ADDRX_DISC(BLKADDR_CPT1)); + if (cfg & BIT_ULL(11)) + cptpf->has_cpt1 = true; +} + static int cptpf_device_init(struct otx2_cptpf_dev *cptpf) { union otx2_cptx_af_constants1 af_cnsts1 = {0}; int ret = 0; + /* check if 'implemented' bit is set for block BLKADDR_CPT1 */ + cptpf_check_block_implemented(cptpf); /* Reset the CPT PF device */ ret = cptpf_device_reset(cptpf); if (ret) @@ -490,7 +514,8 @@ static int cptpf_device_init(struct otx2_cptpf_dev *cptpf) /* Get number of SE, IE and AE engines */ ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_CONSTANTS1, &af_cnsts1.u); + CPT_AF_CONSTANTS1, &af_cnsts1.u, + BLKADDR_CPT0); if (ret) return ret; diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c index 1dc3ba298139..a531f4c8b441 100644 --- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c +++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c @@ -153,16 +153,16 @@ static int get_ucode_type(struct device *dev, } static int __write_ucode_base(struct otx2_cptpf_dev *cptpf, int eng, - dma_addr_t dma_addr) + dma_addr_t dma_addr, int blkaddr) { return otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, CPT_AF_EXEX_UCODE_BASE(eng), - (u64)dma_addr); + (u64)dma_addr, blkaddr); } -static int cpt_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, void *obj) +static int cptx_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, + struct otx2_cptpf_dev *cptpf, int blkaddr) { - struct otx2_cptpf_dev *cptpf = obj; struct otx2_cpt_engs_rsvd *engs; dma_addr_t dma_addr; int i, bit, ret; @@ -170,7 +170,7 @@ static int cpt_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, void *obj) /* Set PF number for microcode fetches */ ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, CPT_AF_PF_FUNC, - cptpf->pf_id << RVU_PFVF_PF_SHIFT); + cptpf->pf_id << RVU_PFVF_PF_SHIFT, blkaddr); if (ret) return ret; @@ -187,7 +187,8 @@ static int cpt_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, void *obj) */ for_each_set_bit(bit, engs->bmap, eng_grp->g->engs_num) if (!eng_grp->g->eng_ref_cnt[bit]) { - ret = __write_ucode_base(cptpf, bit, dma_addr); + ret = __write_ucode_base(cptpf, bit, dma_addr, + blkaddr); if (ret) return ret; } @@ -195,23 +196,32 @@ static int cpt_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, void *obj) return 0; } -static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp, - void *obj) +static int cpt_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp, void *obj) { struct otx2_cptpf_dev *cptpf = obj; - struct otx2_cpt_bitmap bmap; + int ret; + + if (cptpf->has_cpt1) { + ret = cptx_set_ucode_base(eng_grp, cptpf, BLKADDR_CPT1); + if (ret) + return ret; + } + return cptx_set_ucode_base(eng_grp, cptpf, BLKADDR_CPT0); +} + +static int cptx_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp, + struct otx2_cptpf_dev *cptpf, + struct otx2_cpt_bitmap bmap, + int blkaddr) +{ int i, timeout = 10; int busy, ret; u64 reg = 0; - bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp); - if (!bmap.size) - return -EINVAL; - /* Detach the cores from group */ for_each_set_bit(i, bmap.bits, bmap.size) { ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_EXEX_CTL2(i), ®); + CPT_AF_EXEX_CTL2(i), ®, blkaddr); if (ret) return ret; @@ -221,7 +231,8 @@ static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp, ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_EXEX_CTL2(i), reg); + CPT_AF_EXEX_CTL2(i), reg, + blkaddr); if (ret) return ret; } @@ -237,7 +248,8 @@ static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp, for_each_set_bit(i, bmap.bits, bmap.size) { ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_EXEX_STS(i), ®); + CPT_AF_EXEX_STS(i), ®, + blkaddr); if (ret) return ret; @@ -253,7 +265,8 @@ static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp, if (!eng_grp->g->eng_ref_cnt[i]) { ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_EXEX_CTL(i), 0x0); + CPT_AF_EXEX_CTL(i), 0x0, + blkaddr); if (ret) return ret; } @@ -262,22 +275,39 @@ static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp, return 0; } -static int cpt_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp, - void *obj) +static int cpt_detach_and_disable_cores(struct otx2_cpt_eng_grp_info *eng_grp, + void *obj) { struct otx2_cptpf_dev *cptpf = obj; struct otx2_cpt_bitmap bmap; - u64 reg = 0; - int i, ret; + int ret; bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp); if (!bmap.size) return -EINVAL; + if (cptpf->has_cpt1) { + ret = cptx_detach_and_disable_cores(eng_grp, cptpf, bmap, + BLKADDR_CPT1); + if (ret) + return ret; + } + return cptx_detach_and_disable_cores(eng_grp, cptpf, bmap, + BLKADDR_CPT0); +} + +static int cptx_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp, + struct otx2_cptpf_dev *cptpf, + struct otx2_cpt_bitmap bmap, + int blkaddr) +{ + u64 reg = 0; + int i, ret; + /* Attach the cores to the group */ for_each_set_bit(i, bmap.bits, bmap.size) { ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_EXEX_CTL2(i), ®); + CPT_AF_EXEX_CTL2(i), ®, blkaddr); if (ret) return ret; @@ -287,7 +317,8 @@ static int cpt_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp, ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_EXEX_CTL2(i), reg); + CPT_AF_EXEX_CTL2(i), reg, + blkaddr); if (ret) return ret; } @@ -295,15 +326,33 @@ static int cpt_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp, /* Enable the cores */ for_each_set_bit(i, bmap.bits, bmap.size) { - ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, - cptpf->pdev, - CPT_AF_EXEX_CTL(i), 0x1); + ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, + CPT_AF_EXEX_CTL(i), 0x1, + blkaddr); if (ret) return ret; } - ret = otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev); + return otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev); +} - return ret; +static int cpt_attach_and_enable_cores(struct otx2_cpt_eng_grp_info *eng_grp, + void *obj) +{ + struct otx2_cptpf_dev *cptpf = obj; + struct otx2_cpt_bitmap bmap; + int ret; + + bmap = get_cores_bmap(&cptpf->pdev->dev, eng_grp); + if (!bmap.size) + return -EINVAL; + + if (cptpf->has_cpt1) { + ret = cptx_attach_and_enable_cores(eng_grp, cptpf, bmap, + BLKADDR_CPT1); + if (ret) + return ret; + } + return cptx_attach_and_enable_cores(eng_grp, cptpf, bmap, BLKADDR_CPT0); } static int load_fw(struct device *dev, struct fw_info_t *fw_info, @@ -1140,20 +1189,18 @@ release_fw: return ret; } -int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf) +static int cptx_disable_all_cores(struct otx2_cptpf_dev *cptpf, int total_cores, + int blkaddr) { - int i, ret, busy, total_cores; - int timeout = 10; - u64 reg = 0; - - total_cores = cptpf->eng_grps.avail.max_se_cnt + - cptpf->eng_grps.avail.max_ie_cnt + - cptpf->eng_grps.avail.max_ae_cnt; + int timeout = 10, ret; + int i, busy; + u64 reg; /* Disengage the cores from groups */ for (i = 0; i < total_cores; i++) { ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_EXEX_CTL2(i), 0x0); + CPT_AF_EXEX_CTL2(i), 0x0, + blkaddr); if (ret) return ret; @@ -1173,7 +1220,8 @@ int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf) for (i = 0; i < total_cores; i++) { ret = otx2_cpt_read_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_EXEX_STS(i), ®); + CPT_AF_EXEX_STS(i), ®, + blkaddr); if (ret) return ret; @@ -1187,13 +1235,30 @@ int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf) /* Disable the cores */ for (i = 0; i < total_cores; i++) { ret = otx2_cpt_add_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev, - CPT_AF_EXEX_CTL(i), 0x0); + CPT_AF_EXEX_CTL(i), 0x0, + blkaddr); if (ret) return ret; } return otx2_cpt_send_af_reg_requests(&cptpf->afpf_mbox, cptpf->pdev); } +int otx2_cpt_disable_all_cores(struct otx2_cptpf_dev *cptpf) +{ + int total_cores, ret; + + total_cores = cptpf->eng_grps.avail.max_se_cnt + + cptpf->eng_grps.avail.max_ie_cnt + + cptpf->eng_grps.avail.max_ae_cnt; + + if (cptpf->has_cpt1) { + ret = cptx_disable_all_cores(cptpf, total_cores, BLKADDR_CPT1); + if (ret) + return ret; + } + return cptx_disable_all_cores(cptpf, total_cores, BLKADDR_CPT0); +} + void otx2_cpt_cleanup_eng_grps(struct pci_dev *pdev, struct otx2_cpt_eng_grps *eng_grps) { @@ -1354,6 +1419,7 @@ int otx2_cpt_discover_eng_capabilities(struct otx2_cptpf_dev *cptpf) lfs->pdev = pdev; lfs->reg_base = cptpf->reg_base; lfs->mbox = &cptpf->afpf_mbox; + lfs->blkaddr = BLKADDR_CPT0; ret = otx2_cptlf_init(&cptpf->lfs, OTX2_CPT_ALL_ENG_GRPS_MASK, OTX2_CPT_QUEUE_HI_PRIO, 1); if (ret) diff --git a/drivers/crypto/nx/nx-aes-cbc.c b/drivers/crypto/nx/nx-aes-cbc.c index 92e921eceed7..d6314ea9ae89 100644 --- a/drivers/crypto/nx/nx-aes-cbc.c +++ b/drivers/crypto/nx/nx-aes-cbc.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES CBC routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2011-2012 International Business Machines Inc. diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c index 4c9362eebefd..e7384d107573 100644 --- a/drivers/crypto/nx/nx-aes-ccm.c +++ b/drivers/crypto/nx/nx-aes-ccm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES CCM routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2012 International Business Machines Inc. diff --git a/drivers/crypto/nx/nx-aes-ctr.c b/drivers/crypto/nx/nx-aes-ctr.c index 6d5ce1a66f1e..13f518802343 100644 --- a/drivers/crypto/nx/nx-aes-ctr.c +++ b/drivers/crypto/nx/nx-aes-ctr.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES CTR routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2011-2012 International Business Machines Inc. diff --git a/drivers/crypto/nx/nx-aes-ecb.c b/drivers/crypto/nx/nx-aes-ecb.c index 77e338dc33f1..7a729dc2bc17 100644 --- a/drivers/crypto/nx/nx-aes-ecb.c +++ b/drivers/crypto/nx/nx-aes-ecb.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES ECB routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2011-2012 International Business Machines Inc. diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c index 19c6ed5baea4..fc9baca13920 100644 --- a/drivers/crypto/nx/nx-aes-gcm.c +++ b/drivers/crypto/nx/nx-aes-gcm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES GCM routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2012 International Business Machines Inc. diff --git a/drivers/crypto/nx/nx-aes-xcbc.c b/drivers/crypto/nx/nx-aes-xcbc.c index 48dc1c98ca52..eb5c8f689360 100644 --- a/drivers/crypto/nx/nx-aes-xcbc.c +++ b/drivers/crypto/nx/nx-aes-xcbc.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES XCBC routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2011-2012 International Business Machines Inc. diff --git a/drivers/crypto/nx/nx-common-powernv.c b/drivers/crypto/nx/nx-common-powernv.c index 13c65deda8e9..446f611726df 100644 --- a/drivers/crypto/nx/nx-common-powernv.c +++ b/drivers/crypto/nx/nx-common-powernv.c @@ -932,8 +932,10 @@ static int __init nx_powernv_probe_vas(struct device_node *pn) ret = find_nx_device_tree(dn, chip_id, vasid, NX_CT_GZIP, "ibm,p9-nx-gzip", &ct_gzip); - if (ret) + if (ret) { + of_node_put(dn); return ret; + } } if (!ct_842 || !ct_gzip) { diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c index 90d9a37a57f6..b0ad665e4bda 100644 --- a/drivers/crypto/nx/nx-sha256.c +++ b/drivers/crypto/nx/nx-sha256.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * SHA-256 routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2011-2012 International Business Machines Inc. diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c index eb8627a0f317..c29103a1a0b6 100644 --- a/drivers/crypto/nx/nx-sha512.c +++ b/drivers/crypto/nx/nx-sha512.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * SHA-512 routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2011-2012 International Business Machines Inc. diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c index 1d0e8a1ba160..010e87d9da36 100644 --- a/drivers/crypto/nx/nx.c +++ b/drivers/crypto/nx/nx.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * Routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2011-2012 International Business Machines Inc. @@ -200,7 +200,8 @@ struct nx_sg *nx_walk_and_build(struct nx_sg *nx_dst, * @sg: sg list head * @end: sg lisg end * @delta: is the amount we need to crop in order to bound the list. - * + * @nbytes: length of data in the scatterlists or data length - whichever + * is greater. */ static long int trim_sg_list(struct nx_sg *sg, struct nx_sg *end, diff --git a/drivers/crypto/nx/nx_debugfs.c b/drivers/crypto/nx/nx_debugfs.c index 1975bcbee997..ee7cd88bb10a 100644 --- a/drivers/crypto/nx/nx_debugfs.c +++ b/drivers/crypto/nx/nx_debugfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * debugfs routines supporting the Power 7+ Nest Accelerators driver * * Copyright (C) 2011-2012 International Business Machines Inc. diff --git a/drivers/crypto/omap-aes.c b/drivers/crypto/omap-aes.c index a45bdcf3026d..0dd4c6b157de 100644 --- a/drivers/crypto/omap-aes.c +++ b/drivers/crypto/omap-aes.c @@ -103,9 +103,8 @@ static int omap_aes_hw_init(struct omap_aes_dev *dd) dd->err = 0; } - err = pm_runtime_get_sync(dd->dev); + err = pm_runtime_resume_and_get(dd->dev); if (err < 0) { - pm_runtime_put_noidle(dd->dev); dev_err(dd->dev, "failed to get sync: %d\n", err); return err; } @@ -1134,7 +1133,7 @@ static int omap_aes_probe(struct platform_device *pdev) pm_runtime_set_autosuspend_delay(dev, DEFAULT_AUTOSUSPEND_DELAY); pm_runtime_enable(dev); - err = pm_runtime_get_sync(dev); + err = pm_runtime_resume_and_get(dev); if (err < 0) { dev_err(dev, "%s: failed to get_sync(%d)\n", __func__, err); @@ -1303,7 +1302,7 @@ static int omap_aes_suspend(struct device *dev) static int omap_aes_resume(struct device *dev) { - pm_runtime_get_sync(dev); + pm_runtime_resume_and_get(dev); return 0; } #endif diff --git a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c index 6a9be01fdf33..3524ddd48930 100644 --- a/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c +++ b/drivers/crypto/qat/qat_4xxx/adf_4xxx_hw_data.c @@ -224,6 +224,7 @@ void adf_init_hw_data_4xxx(struct adf_hw_device_data *hw_data) hw_data->uof_get_name = uof_get_name; hw_data->uof_get_ae_mask = uof_get_ae_mask; hw_data->set_msix_rttable = set_msix_default_rttable; + hw_data->set_ssm_wdtimer = adf_gen4_set_ssm_wdtimer; adf_gen4_init_hw_csr_ops(&hw_data->csr_ops); } diff --git a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c index f5990d042c9a..1dd64af22bea 100644 --- a/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c +++ b/drivers/crypto/qat/qat_c3xxx/adf_c3xxx_hw_data.c @@ -212,6 +212,7 @@ void adf_init_hw_data_c3xxx(struct adf_hw_device_data *hw_data) hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms; hw_data->reset_device = adf_reset_flr; hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION; + hw_data->set_ssm_wdtimer = adf_gen2_set_ssm_wdtimer; adf_gen2_init_hw_csr_ops(&hw_data->csr_ops); } diff --git a/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c b/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c index 1d1532e8fb6d..067ca5e17d38 100644 --- a/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c +++ b/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c @@ -184,12 +184,12 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) goto out_err_free_reg; - set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status); - ret = adf_dev_init(accel_dev); if (ret) goto out_err_dev_shutdown; + set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status); + ret = adf_dev_start(accel_dev); if (ret) goto out_err_dev_stop; diff --git a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c index cadcf12884c8..30337390513c 100644 --- a/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c +++ b/drivers/crypto/qat/qat_c62x/adf_c62x_hw_data.c @@ -214,6 +214,7 @@ void adf_init_hw_data_c62x(struct adf_hw_device_data *hw_data) hw_data->enable_vf2pf_comms = adf_pf_enable_vf2pf_comms; hw_data->reset_device = adf_reset_flr; hw_data->min_iov_compat_ver = ADF_PFVF_COMPATIBILITY_VERSION; + hw_data->set_ssm_wdtimer = adf_gen2_set_ssm_wdtimer; adf_gen2_init_hw_csr_ops(&hw_data->csr_ops); } diff --git a/drivers/crypto/qat/qat_c62xvf/adf_drv.c b/drivers/crypto/qat/qat_c62xvf/adf_drv.c index 04742a6d91ca..51ea88c0b17d 100644 --- a/drivers/crypto/qat/qat_c62xvf/adf_drv.c +++ b/drivers/crypto/qat/qat_c62xvf/adf_drv.c @@ -184,12 +184,12 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) goto out_err_free_reg; - set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status); - ret = adf_dev_init(accel_dev); if (ret) goto out_err_dev_shutdown; + set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status); + ret = adf_dev_start(accel_dev); if (ret) goto out_err_dev_stop; diff --git a/drivers/crypto/qat/qat_common/adf_accel_devices.h b/drivers/crypto/qat/qat_common/adf_accel_devices.h index 5527344546e5..ac435b44f1d2 100644 --- a/drivers/crypto/qat/qat_common/adf_accel_devices.h +++ b/drivers/crypto/qat/qat_common/adf_accel_devices.h @@ -173,6 +173,7 @@ struct adf_hw_device_data { void (*configure_iov_threads)(struct adf_accel_dev *accel_dev, bool enable); void (*enable_ints)(struct adf_accel_dev *accel_dev); + void (*set_ssm_wdtimer)(struct adf_accel_dev *accel_dev); int (*enable_vf2pf_comms)(struct adf_accel_dev *accel_dev); void (*reset_device)(struct adf_accel_dev *accel_dev); void (*set_msix_rttable)(struct adf_accel_dev *accel_dev); diff --git a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c b/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c index 1aa17303838d..9e560c7d4163 100644 --- a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c +++ b/drivers/crypto/qat/qat_common/adf_gen2_hw_data.c @@ -179,3 +179,28 @@ u32 adf_gen2_get_accel_cap(struct adf_accel_dev *accel_dev) return capabilities; } EXPORT_SYMBOL_GPL(adf_gen2_get_accel_cap); + +void adf_gen2_set_ssm_wdtimer(struct adf_accel_dev *accel_dev) +{ + struct adf_hw_device_data *hw_data = accel_dev->hw_device; + u32 timer_val_pke = ADF_SSM_WDT_PKE_DEFAULT_VALUE; + u32 timer_val = ADF_SSM_WDT_DEFAULT_VALUE; + unsigned long accel_mask = hw_data->accel_mask; + void __iomem *pmisc_addr; + struct adf_bar *pmisc; + int pmisc_id; + u32 i = 0; + + pmisc_id = hw_data->get_misc_bar_id(hw_data); + pmisc = &GET_BARS(accel_dev)[pmisc_id]; + pmisc_addr = pmisc->virt_addr; + + /* Configures WDT timers */ + for_each_set_bit(i, &accel_mask, hw_data->num_accel) { + /* Enable WDT for sym and dc */ + ADF_CSR_WR(pmisc_addr, ADF_SSMWDT(i), timer_val); + /* Enable WDT for pke */ + ADF_CSR_WR(pmisc_addr, ADF_SSMWDTPKE(i), timer_val_pke); + } +} +EXPORT_SYMBOL_GPL(adf_gen2_set_ssm_wdtimer); diff --git a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h b/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h index 3816e6500352..756b0ddfac5e 100644 --- a/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h +++ b/drivers/crypto/qat/qat_common/adf_gen2_hw_data.h @@ -113,11 +113,24 @@ do { \ /* Power gating */ #define ADF_POWERGATE_PKE BIT(24) +/* WDT timers + * + * Timeout is in cycles. Clock speed may vary across products but this + * value should be a few milli-seconds. + */ +#define ADF_SSM_WDT_DEFAULT_VALUE 0x200000 +#define ADF_SSM_WDT_PKE_DEFAULT_VALUE 0x2000000 +#define ADF_SSMWDT_OFFSET 0x54 +#define ADF_SSMWDTPKE_OFFSET 0x58 +#define ADF_SSMWDT(i) (ADF_SSMWDT_OFFSET + ((i) * 0x4000)) +#define ADF_SSMWDTPKE(i) (ADF_SSMWDTPKE_OFFSET + ((i) * 0x4000)) + void adf_gen2_cfg_iov_thds(struct adf_accel_dev *accel_dev, bool enable, int num_a_regs, int num_b_regs); void adf_gen2_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops); void adf_gen2_get_admin_info(struct admin_info *admin_csrs_info); void adf_gen2_get_arb_info(struct arb_info *arb_info); u32 adf_gen2_get_accel_cap(struct adf_accel_dev *accel_dev); +void adf_gen2_set_ssm_wdtimer(struct adf_accel_dev *accel_dev); #endif diff --git a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.c b/drivers/crypto/qat/qat_common/adf_gen4_hw_data.c index b72ff58e0bc7..000528327b29 100644 --- a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.c +++ b/drivers/crypto/qat/qat_common/adf_gen4_hw_data.c @@ -99,3 +99,43 @@ void adf_gen4_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops) csr_ops->write_csr_ring_srv_arb_en = write_csr_ring_srv_arb_en; } EXPORT_SYMBOL_GPL(adf_gen4_init_hw_csr_ops); + +static inline void adf_gen4_unpack_ssm_wdtimer(u64 value, u32 *upper, + u32 *lower) +{ + *lower = lower_32_bits(value); + *upper = upper_32_bits(value); +} + +void adf_gen4_set_ssm_wdtimer(struct adf_accel_dev *accel_dev) +{ + struct adf_hw_device_data *hw_data = accel_dev->hw_device; + u64 timer_val_pke = ADF_SSM_WDT_PKE_DEFAULT_VALUE; + u64 timer_val = ADF_SSM_WDT_DEFAULT_VALUE; + u32 ssm_wdt_pke_high = 0; + u32 ssm_wdt_pke_low = 0; + u32 ssm_wdt_high = 0; + u32 ssm_wdt_low = 0; + void __iomem *pmisc_addr; + struct adf_bar *pmisc; + int pmisc_id; + + pmisc_id = hw_data->get_misc_bar_id(hw_data); + pmisc = &GET_BARS(accel_dev)[pmisc_id]; + pmisc_addr = pmisc->virt_addr; + + /* Convert 64bit WDT timer value into 32bit values for + * mmio write to 32bit CSRs. + */ + adf_gen4_unpack_ssm_wdtimer(timer_val, &ssm_wdt_high, &ssm_wdt_low); + adf_gen4_unpack_ssm_wdtimer(timer_val_pke, &ssm_wdt_pke_high, + &ssm_wdt_pke_low); + + /* Enable WDT for sym and dc */ + ADF_CSR_WR(pmisc_addr, ADF_SSMWDTL_OFFSET, ssm_wdt_low); + ADF_CSR_WR(pmisc_addr, ADF_SSMWDTH_OFFSET, ssm_wdt_high); + /* Enable WDT for pke */ + ADF_CSR_WR(pmisc_addr, ADF_SSMWDTPKEL_OFFSET, ssm_wdt_pke_low); + ADF_CSR_WR(pmisc_addr, ADF_SSMWDTPKEH_OFFSET, ssm_wdt_pke_high); +} +EXPORT_SYMBOL_GPL(adf_gen4_set_ssm_wdtimer); diff --git a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h b/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h index 8ab62b2ac311..b8fca1ff7aab 100644 --- a/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h +++ b/drivers/crypto/qat/qat_common/adf_gen4_hw_data.h @@ -94,6 +94,18 @@ do { \ ADF_RING_BUNDLE_SIZE * (bank) + \ ADF_RING_CSR_RING_SRV_ARB_EN, (value)) -void adf_gen4_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops); +/* WDT timers + * + * Timeout is in cycles. Clock speed may vary across products but this + * value should be a few milli-seconds. + */ +#define ADF_SSM_WDT_DEFAULT_VALUE 0x200000 +#define ADF_SSM_WDT_PKE_DEFAULT_VALUE 0x8000000 +#define ADF_SSMWDTL_OFFSET 0x54 +#define ADF_SSMWDTH_OFFSET 0x5C +#define ADF_SSMWDTPKEL_OFFSET 0x58 +#define ADF_SSMWDTPKEH_OFFSET 0x60 +void adf_gen4_set_ssm_wdtimer(struct adf_accel_dev *accel_dev); +void adf_gen4_init_hw_csr_ops(struct adf_hw_csr_ops *csr_ops); #endif diff --git a/drivers/crypto/qat/qat_common/adf_init.c b/drivers/crypto/qat/qat_common/adf_init.c index 42029153408e..744c40351428 100644 --- a/drivers/crypto/qat/qat_common/adf_init.c +++ b/drivers/crypto/qat/qat_common/adf_init.c @@ -162,6 +162,10 @@ int adf_dev_start(struct adf_accel_dev *accel_dev) return -EFAULT; } + /* Set ssm watch dog timer */ + if (hw_data->set_ssm_wdtimer) + hw_data->set_ssm_wdtimer(accel_dev); + list_for_each(list_itr, &service_table) { service = list_entry(list_itr, struct service_hndl, list); if (service->event_hld(accel_dev, ADF_EVENT_START)) { diff --git a/drivers/crypto/qat/qat_common/adf_isr.c b/drivers/crypto/qat/qat_common/adf_isr.c index c45853463530..e3ad5587be49 100644 --- a/drivers/crypto/qat/qat_common/adf_isr.c +++ b/drivers/crypto/qat/qat_common/adf_isr.c @@ -291,19 +291,32 @@ int adf_isr_resource_alloc(struct adf_accel_dev *accel_dev) ret = adf_isr_alloc_msix_entry_table(accel_dev); if (ret) - return ret; - if (adf_enable_msix(accel_dev)) goto err_out; - if (adf_setup_bh(accel_dev)) - goto err_out; + ret = adf_enable_msix(accel_dev); + if (ret) + goto err_free_msix_table; - if (adf_request_irqs(accel_dev)) - goto err_out; + ret = adf_setup_bh(accel_dev); + if (ret) + goto err_disable_msix; + + ret = adf_request_irqs(accel_dev); + if (ret) + goto err_cleanup_bh; return 0; + +err_cleanup_bh: + adf_cleanup_bh(accel_dev); + +err_disable_msix: + adf_disable_msix(&accel_dev->accel_pci_dev); + +err_free_msix_table: + adf_isr_free_msix_entry_table(accel_dev); + err_out: - adf_isr_resource_free(accel_dev); - return -EFAULT; + return ret; } EXPORT_SYMBOL_GPL(adf_isr_resource_alloc); diff --git a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c index 8b090b7ae8c6..a1b77bd7a894 100644 --- a/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c +++ b/drivers/crypto/qat/qat_common/adf_pf2vf_msg.c @@ -169,7 +169,7 @@ out: * @msg: Message to send * @vf_nr: VF number to which the message will be sent * - * Function sends a messge from the PF to a VF + * Function sends a message from the PF to a VF * * Return: 0 on success, error code otherwise. */ diff --git a/drivers/crypto/qat/qat_common/adf_transport.c b/drivers/crypto/qat/qat_common/adf_transport.c index 888c1e047295..8ba28409fb74 100644 --- a/drivers/crypto/qat/qat_common/adf_transport.c +++ b/drivers/crypto/qat/qat_common/adf_transport.c @@ -172,6 +172,7 @@ static int adf_init_ring(struct adf_etr_ring_data *ring) dev_err(&GET_DEV(accel_dev), "Ring address not aligned\n"); dma_free_coherent(&GET_DEV(accel_dev), ring_size_bytes, ring->base_addr, ring->dma_addr); + ring->base_addr = NULL; return -EFAULT; } diff --git a/drivers/crypto/qat/qat_common/adf_vf2pf_msg.c b/drivers/crypto/qat/qat_common/adf_vf2pf_msg.c index 2c98fb63f7b7..e85bd62d134a 100644 --- a/drivers/crypto/qat/qat_common/adf_vf2pf_msg.c +++ b/drivers/crypto/qat/qat_common/adf_vf2pf_msg.c @@ -8,7 +8,7 @@ * adf_vf2pf_init() - send init msg to PF * @accel_dev: Pointer to acceleration VF device. * - * Function sends an init messge from the VF to a PF + * Function sends an init message from the VF to a PF * * Return: 0 on success, error code otherwise. */ @@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(adf_vf2pf_init); * adf_vf2pf_shutdown() - send shutdown msg to PF * @accel_dev: Pointer to acceleration VF device. * - * Function sends a shutdown messge from the VF to a PF + * Function sends a shutdown message from the VF to a PF * * Return: void */ diff --git a/drivers/crypto/qat/qat_common/adf_vf_isr.c b/drivers/crypto/qat/qat_common/adf_vf_isr.c index 38d316a42ba6..888388acb6bd 100644 --- a/drivers/crypto/qat/qat_common/adf_vf_isr.c +++ b/drivers/crypto/qat/qat_common/adf_vf_isr.c @@ -261,17 +261,26 @@ int adf_vf_isr_resource_alloc(struct adf_accel_dev *accel_dev) goto err_out; if (adf_setup_pf2vf_bh(accel_dev)) - goto err_out; + goto err_disable_msi; if (adf_setup_bh(accel_dev)) - goto err_out; + goto err_cleanup_pf2vf_bh; if (adf_request_msi_irq(accel_dev)) - goto err_out; + goto err_cleanup_bh; return 0; + +err_cleanup_bh: + adf_cleanup_bh(accel_dev); + +err_cleanup_pf2vf_bh: + adf_cleanup_pf2vf_bh(accel_dev); + +err_disable_msi: + adf_disable_msi(accel_dev); + err_out: - adf_vf_isr_resource_free(accel_dev); return -EFAULT; } EXPORT_SYMBOL_GPL(adf_vf_isr_resource_alloc); diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c index ff78c73c47e3..f998ed58457c 100644 --- a/drivers/crypto/qat/qat_common/qat_algs.c +++ b/drivers/crypto/qat/qat_common/qat_algs.c @@ -718,8 +718,8 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, int n = sg_nents(sgl); struct qat_alg_buf_list *bufl; struct qat_alg_buf_list *buflout = NULL; - dma_addr_t blp; - dma_addr_t bloutp = 0; + dma_addr_t blp = DMA_MAPPING_ERROR; + dma_addr_t bloutp = DMA_MAPPING_ERROR; struct scatterlist *sg; size_t sz_out, sz = struct_size(bufl, bufers, n + 1); @@ -731,9 +731,8 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, if (unlikely(!bufl)) return -ENOMEM; - blp = dma_map_single(dev, bufl, sz, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev, blp))) - goto err_in; + for_each_sg(sgl, sg, n, i) + bufl->bufers[i].addr = DMA_MAPPING_ERROR; for_each_sg(sgl, sg, n, i) { int y = sg_nctr; @@ -750,6 +749,9 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, sg_nctr++; } bufl->num_bufs = sg_nctr; + blp = dma_map_single(dev, bufl, sz, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev, blp))) + goto err_in; qat_req->buf.bl = bufl; qat_req->buf.blp = blp; qat_req->buf.sz = sz; @@ -764,10 +766,11 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, dev_to_node(&GET_DEV(inst->accel_dev))); if (unlikely(!buflout)) goto err_in; - bloutp = dma_map_single(dev, buflout, sz_out, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(dev, bloutp))) - goto err_out; + bufers = buflout->bufers; + for_each_sg(sglout, sg, n, i) + bufers[i].addr = DMA_MAPPING_ERROR; + for_each_sg(sglout, sg, n, i) { int y = sg_nctr; @@ -784,6 +787,9 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, } buflout->num_bufs = sg_nctr; buflout->num_mapped_bufs = sg_nctr; + bloutp = dma_map_single(dev, buflout, sz_out, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dev, bloutp))) + goto err_out; qat_req->buf.blout = buflout; qat_req->buf.bloutp = bloutp; qat_req->buf.sz_out = sz_out; @@ -795,17 +801,21 @@ static int qat_alg_sgl_to_bufl(struct qat_crypto_instance *inst, return 0; err_out: + if (!dma_mapping_error(dev, bloutp)) + dma_unmap_single(dev, bloutp, sz_out, DMA_TO_DEVICE); + n = sg_nents(sglout); for (i = 0; i < n; i++) if (!dma_mapping_error(dev, buflout->bufers[i].addr)) dma_unmap_single(dev, buflout->bufers[i].addr, buflout->bufers[i].len, DMA_BIDIRECTIONAL); - if (!dma_mapping_error(dev, bloutp)) - dma_unmap_single(dev, bloutp, sz_out, DMA_TO_DEVICE); kfree(buflout); err_in: + if (!dma_mapping_error(dev, blp)) + dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE); + n = sg_nents(sgl); for (i = 0; i < n; i++) if (!dma_mapping_error(dev, bufl->bufers[i].addr)) @@ -813,8 +823,6 @@ err_in: bufl->bufers[i].len, DMA_BIDIRECTIONAL); - if (!dma_mapping_error(dev, blp)) - dma_unmap_single(dev, blp, sz, DMA_TO_DEVICE); kfree(bufl); dev_err(dev, "Failed to map buf for dma\n"); diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c index c972554a755e..29999da716cc 100644 --- a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c +++ b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c @@ -184,12 +184,12 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) goto out_err_free_reg; - set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status); - ret = adf_dev_init(accel_dev); if (ret) goto out_err_dev_shutdown; + set_bit(ADF_STATUS_PF_RUNNING, &accel_dev->status); + ret = adf_dev_start(accel_dev); if (ret) goto out_err_dev_stop; diff --git a/drivers/crypto/qce/cipher.h b/drivers/crypto/qce/cipher.h index cffa9fc628ff..850f257d00f3 100644 --- a/drivers/crypto/qce/cipher.h +++ b/drivers/crypto/qce/cipher.h @@ -40,7 +40,6 @@ struct qce_cipher_reqctx { struct scatterlist result_sg; struct sg_table dst_tbl; struct scatterlist *dst_sg; - struct sg_table src_tbl; struct scatterlist *src_sg; unsigned int cryptlen; struct skcipher_request fallback_req; // keep at the end diff --git a/drivers/crypto/qce/common.c b/drivers/crypto/qce/common.c index a73db2a5637f..dceb9579d87a 100644 --- a/drivers/crypto/qce/common.c +++ b/drivers/crypto/qce/common.c @@ -140,8 +140,7 @@ static u32 qce_auth_cfg(unsigned long flags, u32 key_size) return cfg; } -static int qce_setup_regs_ahash(struct crypto_async_request *async_req, - u32 totallen, u32 offset) +static int qce_setup_regs_ahash(struct crypto_async_request *async_req) { struct ahash_request *req = ahash_request_cast(async_req); struct crypto_ahash *ahash = __crypto_ahash_cast(async_req->tfm); @@ -295,19 +294,18 @@ static void qce_xtskey(struct qce_device *qce, const u8 *enckey, { u32 xtskey[QCE_MAX_CIPHER_KEY_SIZE / sizeof(u32)] = {0}; unsigned int xtsklen = enckeylen / (2 * sizeof(u32)); - unsigned int xtsdusize; qce_cpu_to_be32p_array((__be32 *)xtskey, enckey + enckeylen / 2, enckeylen / 2); qce_write_array(qce, REG_ENCR_XTS_KEY0, xtskey, xtsklen); - /* xts du size 512B */ - xtsdusize = min_t(u32, QCE_SECTOR_SIZE, cryptlen); - qce_write(qce, REG_ENCR_XTS_DU_SIZE, xtsdusize); + /* Set data unit size to cryptlen. Anything else causes + * crypto engine to return back incorrect results. + */ + qce_write(qce, REG_ENCR_XTS_DU_SIZE, cryptlen); } -static int qce_setup_regs_skcipher(struct crypto_async_request *async_req, - u32 totallen, u32 offset) +static int qce_setup_regs_skcipher(struct crypto_async_request *async_req) { struct skcipher_request *req = skcipher_request_cast(async_req); struct qce_cipher_reqctx *rctx = skcipher_request_ctx(req); @@ -367,7 +365,7 @@ static int qce_setup_regs_skcipher(struct crypto_async_request *async_req, qce_write(qce, REG_ENCR_SEG_CFG, encr_cfg); qce_write(qce, REG_ENCR_SEG_SIZE, rctx->cryptlen); - qce_write(qce, REG_ENCR_SEG_START, offset & 0xffff); + qce_write(qce, REG_ENCR_SEG_START, 0); if (IS_CTR(flags)) { qce_write(qce, REG_CNTR_MASK, ~0); @@ -376,7 +374,7 @@ static int qce_setup_regs_skcipher(struct crypto_async_request *async_req, qce_write(qce, REG_CNTR_MASK2, ~0); } - qce_write(qce, REG_SEG_SIZE, totallen); + qce_write(qce, REG_SEG_SIZE, rctx->cryptlen); /* get little endianness */ config = qce_config_reg(qce, 1); @@ -388,17 +386,16 @@ static int qce_setup_regs_skcipher(struct crypto_async_request *async_req, } #endif -int qce_start(struct crypto_async_request *async_req, u32 type, u32 totallen, - u32 offset) +int qce_start(struct crypto_async_request *async_req, u32 type) { switch (type) { #ifdef CONFIG_CRYPTO_DEV_QCE_SKCIPHER case CRYPTO_ALG_TYPE_SKCIPHER: - return qce_setup_regs_skcipher(async_req, totallen, offset); + return qce_setup_regs_skcipher(async_req); #endif #ifdef CONFIG_CRYPTO_DEV_QCE_SHA case CRYPTO_ALG_TYPE_AHASH: - return qce_setup_regs_ahash(async_req, totallen, offset); + return qce_setup_regs_ahash(async_req); #endif default: return -EINVAL; diff --git a/drivers/crypto/qce/common.h b/drivers/crypto/qce/common.h index 85ba16418a04..3bc244bcca2d 100644 --- a/drivers/crypto/qce/common.h +++ b/drivers/crypto/qce/common.h @@ -94,7 +94,6 @@ struct qce_alg_template { void qce_cpu_to_be32p_array(__be32 *dst, const u8 *src, unsigned int len); int qce_check_status(struct qce_device *qce, u32 *status); void qce_get_version(struct qce_device *qce, u32 *major, u32 *minor, u32 *step); -int qce_start(struct crypto_async_request *async_req, u32 type, u32 totallen, - u32 offset); +int qce_start(struct crypto_async_request *async_req, u32 type); #endif /* _COMMON_H_ */ diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c index 61c418c12345..8e6fcf2c21cc 100644 --- a/drivers/crypto/qce/sha.c +++ b/drivers/crypto/qce/sha.c @@ -12,9 +12,15 @@ #include "core.h" #include "sha.h" -/* crypto hw padding constant for first operation */ -#define SHA_PADDING 64 -#define SHA_PADDING_MASK (SHA_PADDING - 1) +struct qce_sha_saved_state { + u8 pending_buf[QCE_SHA_MAX_BLOCKSIZE]; + u8 partial_digest[QCE_SHA_MAX_DIGESTSIZE]; + __be32 byte_count[2]; + unsigned int pending_buflen; + unsigned int flags; + u64 count; + bool first_blk; +}; static LIST_HEAD(ahash_algs); @@ -107,7 +113,7 @@ static int qce_ahash_async_req_handle(struct crypto_async_request *async_req) qce_dma_issue_pending(&qce->dma); - ret = qce_start(async_req, tmpl->crypto_alg_type, 0, 0); + ret = qce_start(async_req, tmpl->crypto_alg_type); if (ret) goto error_terminate; @@ -139,97 +145,37 @@ static int qce_ahash_init(struct ahash_request *req) static int qce_ahash_export(struct ahash_request *req, void *out) { - struct crypto_ahash *ahash = crypto_ahash_reqtfm(req); struct qce_sha_reqctx *rctx = ahash_request_ctx(req); - unsigned long flags = rctx->flags; - unsigned int digestsize = crypto_ahash_digestsize(ahash); - unsigned int blocksize = - crypto_tfm_alg_blocksize(crypto_ahash_tfm(ahash)); - - if (IS_SHA1(flags) || IS_SHA1_HMAC(flags)) { - struct sha1_state *out_state = out; - - out_state->count = rctx->count; - qce_cpu_to_be32p_array((__be32 *)out_state->state, - rctx->digest, digestsize); - memcpy(out_state->buffer, rctx->buf, blocksize); - } else if (IS_SHA256(flags) || IS_SHA256_HMAC(flags)) { - struct sha256_state *out_state = out; - - out_state->count = rctx->count; - qce_cpu_to_be32p_array((__be32 *)out_state->state, - rctx->digest, digestsize); - memcpy(out_state->buf, rctx->buf, blocksize); - } else { - return -EINVAL; - } + struct qce_sha_saved_state *export_state = out; - return 0; -} - -static int qce_import_common(struct ahash_request *req, u64 in_count, - const u32 *state, const u8 *buffer, bool hmac) -{ - struct crypto_ahash *ahash = crypto_ahash_reqtfm(req); - struct qce_sha_reqctx *rctx = ahash_request_ctx(req); - unsigned int digestsize = crypto_ahash_digestsize(ahash); - unsigned int blocksize; - u64 count = in_count; - - blocksize = crypto_tfm_alg_blocksize(crypto_ahash_tfm(ahash)); - rctx->count = in_count; - memcpy(rctx->buf, buffer, blocksize); - - if (in_count <= blocksize) { - rctx->first_blk = 1; - } else { - rctx->first_blk = 0; - /* - * For HMAC, there is a hardware padding done when first block - * is set. Therefore the byte_count must be incremened by 64 - * after the first block operation. - */ - if (hmac) - count += SHA_PADDING; - } - - rctx->byte_count[0] = (__force __be32)(count & ~SHA_PADDING_MASK); - rctx->byte_count[1] = (__force __be32)(count >> 32); - qce_cpu_to_be32p_array((__be32 *)rctx->digest, (const u8 *)state, - digestsize); - rctx->buflen = (unsigned int)(in_count & (blocksize - 1)); + memcpy(export_state->pending_buf, rctx->buf, rctx->buflen); + memcpy(export_state->partial_digest, rctx->digest, sizeof(rctx->digest)); + export_state->byte_count[0] = rctx->byte_count[0]; + export_state->byte_count[1] = rctx->byte_count[1]; + export_state->pending_buflen = rctx->buflen; + export_state->count = rctx->count; + export_state->first_blk = rctx->first_blk; + export_state->flags = rctx->flags; return 0; } static int qce_ahash_import(struct ahash_request *req, const void *in) { - struct qce_sha_reqctx *rctx; - unsigned long flags; - bool hmac; - int ret; - - ret = qce_ahash_init(req); - if (ret) - return ret; - - rctx = ahash_request_ctx(req); - flags = rctx->flags; - hmac = IS_SHA_HMAC(flags); - - if (IS_SHA1(flags) || IS_SHA1_HMAC(flags)) { - const struct sha1_state *state = in; - - ret = qce_import_common(req, state->count, state->state, - state->buffer, hmac); - } else if (IS_SHA256(flags) || IS_SHA256_HMAC(flags)) { - const struct sha256_state *state = in; + struct qce_sha_reqctx *rctx = ahash_request_ctx(req); + const struct qce_sha_saved_state *import_state = in; - ret = qce_import_common(req, state->count, state->state, - state->buf, hmac); - } + memset(rctx, 0, sizeof(*rctx)); + rctx->count = import_state->count; + rctx->buflen = import_state->pending_buflen; + rctx->first_blk = import_state->first_blk; + rctx->flags = import_state->flags; + rctx->byte_count[0] = import_state->byte_count[0]; + rctx->byte_count[1] = import_state->byte_count[1]; + memcpy(rctx->buf, import_state->pending_buf, rctx->buflen); + memcpy(rctx->digest, import_state->partial_digest, sizeof(rctx->digest)); - return ret; + return 0; } static int qce_ahash_update(struct ahash_request *req) @@ -270,6 +216,25 @@ static int qce_ahash_update(struct ahash_request *req) /* calculate how many bytes will be hashed later */ hash_later = total % blocksize; + + /* + * At this point, there is more than one block size of data. If + * the available data to transfer is exactly a multiple of block + * size, save the last block to be transferred in qce_ahash_final + * (with the last block bit set) if this is indeed the end of data + * stream. If not this saved block will be transferred as part of + * next update. If this block is not held back and if this is + * indeed the end of data stream, the digest obtained will be wrong + * since qce_ahash_final will see that rctx->buflen is 0 and return + * doing nothing which in turn means that a digest will not be + * copied to the destination result buffer. qce_ahash_final cannot + * be made to alter this behavior and allowed to proceed if + * rctx->buflen is 0 because the crypto engine BAM does not allow + * for zero length transfers. + */ + if (!hash_later) + hash_later = blocksize; + if (hash_later) { unsigned int src_offset = req->nbytes - hash_later; scatterwalk_map_and_copy(rctx->buf, req->src, src_offset, @@ -450,7 +415,7 @@ static const struct qce_ahash_def ahash_def[] = { .drv_name = "sha1-qce", .digestsize = SHA1_DIGEST_SIZE, .blocksize = SHA1_BLOCK_SIZE, - .statesize = sizeof(struct sha1_state), + .statesize = sizeof(struct qce_sha_saved_state), .std_iv = std_iv_sha1, }, { @@ -459,7 +424,7 @@ static const struct qce_ahash_def ahash_def[] = { .drv_name = "sha256-qce", .digestsize = SHA256_DIGEST_SIZE, .blocksize = SHA256_BLOCK_SIZE, - .statesize = sizeof(struct sha256_state), + .statesize = sizeof(struct qce_sha_saved_state), .std_iv = std_iv_sha256, }, { @@ -468,7 +433,7 @@ static const struct qce_ahash_def ahash_def[] = { .drv_name = "hmac-sha1-qce", .digestsize = SHA1_DIGEST_SIZE, .blocksize = SHA1_BLOCK_SIZE, - .statesize = sizeof(struct sha1_state), + .statesize = sizeof(struct qce_sha_saved_state), .std_iv = std_iv_sha1, }, { @@ -477,7 +442,7 @@ static const struct qce_ahash_def ahash_def[] = { .drv_name = "hmac-sha256-qce", .digestsize = SHA256_DIGEST_SIZE, .blocksize = SHA256_BLOCK_SIZE, - .statesize = sizeof(struct sha256_state), + .statesize = sizeof(struct qce_sha_saved_state), .std_iv = std_iv_sha256, }, }; diff --git a/drivers/crypto/qce/skcipher.c b/drivers/crypto/qce/skcipher.c index a2d3da0ad95f..c0a0d8c4fce1 100644 --- a/drivers/crypto/qce/skcipher.c +++ b/drivers/crypto/qce/skcipher.c @@ -8,6 +8,7 @@ #include <linux/interrupt.h> #include <linux/moduleparam.h> #include <linux/types.h> +#include <linux/errno.h> #include <crypto/aes.h> #include <crypto/internal/des.h> #include <crypto/internal/skcipher.h> @@ -143,7 +144,7 @@ qce_skcipher_async_req_handle(struct crypto_async_request *async_req) qce_dma_issue_pending(&qce->dma); - ret = qce_start(async_req, tmpl->crypto_alg_type, req->cryptlen, 0); + ret = qce_start(async_req, tmpl->crypto_alg_type); if (ret) goto error_terminate; @@ -167,16 +168,33 @@ static int qce_skcipher_setkey(struct crypto_skcipher *ablk, const u8 *key, struct crypto_tfm *tfm = crypto_skcipher_tfm(ablk); struct qce_cipher_ctx *ctx = crypto_tfm_ctx(tfm); unsigned long flags = to_cipher_tmpl(ablk)->alg_flags; + unsigned int __keylen; int ret; if (!key || !keylen) return -EINVAL; - switch (IS_XTS(flags) ? keylen >> 1 : keylen) { + /* + * AES XTS key1 = key2 not supported by crypto engine. + * Revisit to request a fallback cipher in this case. + */ + if (IS_XTS(flags)) { + __keylen = keylen >> 1; + if (!memcmp(key, key + __keylen, __keylen)) + return -ENOKEY; + } else { + __keylen = keylen; + } + + switch (__keylen) { case AES_KEYSIZE_128: case AES_KEYSIZE_256: memcpy(ctx->enc_key, key, keylen); break; + case AES_KEYSIZE_192: + break; + default: + return -EINVAL; } ret = crypto_skcipher_setkey(ctx->fallback, key, keylen); @@ -204,12 +222,27 @@ static int qce_des3_setkey(struct crypto_skcipher *ablk, const u8 *key, unsigned int keylen) { struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(ablk); + u32 _key[6]; int err; err = verify_skcipher_des3_key(ablk, key); if (err) return err; + /* + * The crypto engine does not support any two keys + * being the same for triple des algorithms. The + * verify_skcipher_des3_key does not check for all the + * below conditions. Return -ENOKEY in case any two keys + * are the same. Revisit to see if a fallback cipher + * is needed to handle this condition. + */ + memcpy(_key, key, DES3_EDE_KEY_SIZE); + if (!((_key[0] ^ _key[2]) | (_key[1] ^ _key[3])) || + !((_key[2] ^ _key[4]) | (_key[3] ^ _key[5])) || + !((_key[0] ^ _key[4]) | (_key[1] ^ _key[5]))) + return -ENOKEY; + ctx->enc_keylen = keylen; memcpy(ctx->enc_key, key, keylen); return 0; @@ -221,6 +254,7 @@ static int qce_skcipher_crypt(struct skcipher_request *req, int encrypt) struct qce_cipher_ctx *ctx = crypto_skcipher_ctx(tfm); struct qce_cipher_reqctx *rctx = skcipher_request_ctx(req); struct qce_alg_template *tmpl = to_cipher_tmpl(tfm); + unsigned int blocksize = crypto_skcipher_blocksize(tfm); int keylen; int ret; @@ -228,14 +262,31 @@ static int qce_skcipher_crypt(struct skcipher_request *req, int encrypt) rctx->flags |= encrypt ? QCE_ENCRYPT : QCE_DECRYPT; keylen = IS_XTS(rctx->flags) ? ctx->enc_keylen >> 1 : ctx->enc_keylen; - /* qce is hanging when AES-XTS request len > QCE_SECTOR_SIZE and - * is not a multiple of it; pass such requests to the fallback + /* CE does not handle 0 length messages */ + if (!req->cryptlen) + return 0; + + /* + * ECB and CBC algorithms require message lengths to be + * multiples of block size. + */ + if (IS_ECB(rctx->flags) || IS_CBC(rctx->flags)) + if (!IS_ALIGNED(req->cryptlen, blocksize)) + return -EINVAL; + + /* + * Conditions for requesting a fallback cipher + * AES-192 (not supported by crypto engine (CE)) + * AES-XTS request with len <= 512 byte (not recommended to use CE) + * AES-XTS request with len > QCE_SECTOR_SIZE and + * is not a multiple of it.(Revisit this condition to check if it is + * needed in all versions of CE) */ if (IS_AES(rctx->flags) && - (((keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_256) || - req->cryptlen <= aes_sw_max_len) || - (IS_XTS(rctx->flags) && req->cryptlen > QCE_SECTOR_SIZE && - req->cryptlen % QCE_SECTOR_SIZE))) { + ((keylen != AES_KEYSIZE_128 && keylen != AES_KEYSIZE_256) || + (IS_XTS(rctx->flags) && ((req->cryptlen <= aes_sw_max_len) || + (req->cryptlen > QCE_SECTOR_SIZE && + req->cryptlen % QCE_SECTOR_SIZE))))) { skcipher_request_set_tfm(&rctx->fallback_req, ctx->fallback); skcipher_request_set_callback(&rctx->fallback_req, req->base.flags, @@ -307,7 +358,7 @@ static const struct qce_skcipher_def skcipher_def[] = { .name = "ecb(aes)", .drv_name = "ecb-aes-qce", .blocksize = AES_BLOCK_SIZE, - .ivsize = AES_BLOCK_SIZE, + .ivsize = 0, .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, }, diff --git a/drivers/crypto/rockchip/rk3288_crypto_ahash.c b/drivers/crypto/rockchip/rk3288_crypto_ahash.c index 81befe7febaa..ed03058497bc 100644 --- a/drivers/crypto/rockchip/rk3288_crypto_ahash.c +++ b/drivers/crypto/rockchip/rk3288_crypto_ahash.c @@ -48,7 +48,7 @@ static void rk_ahash_reg_init(struct rk_crypto_info *dev) { struct ahash_request *req = ahash_request_cast(dev->async_req); struct rk_ahash_rctx *rctx = ahash_request_ctx(req); - int reg_status = 0; + int reg_status; reg_status = CRYPTO_READ(dev, RK_CRYPTO_CTRL) | RK_CRYPTO_HASH_FLUSH | _SBF(0xffff, 16); diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c index 682c8a450a57..55aa3a71169b 100644 --- a/drivers/crypto/s5p-sss.c +++ b/drivers/crypto/s5p-sss.c @@ -20,6 +20,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> +#include <linux/of_device.h> #include <linux/platform_device.h> #include <linux/scatterlist.h> @@ -401,7 +402,7 @@ static const struct samsung_aes_variant exynos_aes_data = { static const struct samsung_aes_variant exynos5433_slim_aes_data = { .aes_offset = 0x400, .hash_offset = 0x800, - .clk_names = { "pclk", "aclk", }, + .clk_names = { "aclk", "pclk", }, }; static const struct of_device_id s5p_sss_dt_match[] = { @@ -424,13 +425,9 @@ MODULE_DEVICE_TABLE(of, s5p_sss_dt_match); static inline const struct samsung_aes_variant *find_s5p_sss_version (const struct platform_device *pdev) { - if (IS_ENABLED(CONFIG_OF) && (pdev->dev.of_node)) { - const struct of_device_id *match; + if (IS_ENABLED(CONFIG_OF) && (pdev->dev.of_node)) + return of_device_get_match_data(&pdev->dev); - match = of_match_node(s5p_sss_dt_match, - pdev->dev.of_node); - return (const struct samsung_aes_variant *)match->data; - } return (const struct samsung_aes_variant *) platform_get_device_id(pdev)->driver_data; } @@ -2159,7 +2156,7 @@ static struct skcipher_alg algs[] = { static int s5p_aes_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - int i, j, err = -ENODEV; + int i, j, err; const struct samsung_aes_variant *variant; struct s5p_aes_dev *pdata; struct resource *res; @@ -2189,14 +2186,14 @@ static int s5p_aes_probe(struct platform_device *pdev) } pdata->res = res; - pdata->ioaddr = devm_ioremap_resource(&pdev->dev, res); + pdata->ioaddr = devm_ioremap_resource(dev, res); if (IS_ERR(pdata->ioaddr)) { if (!pdata->use_hash) return PTR_ERR(pdata->ioaddr); /* try AES without HASH */ res->end -= 0x300; pdata->use_hash = false; - pdata->ioaddr = devm_ioremap_resource(&pdev->dev, res); + pdata->ioaddr = devm_ioremap_resource(dev, res); if (IS_ERR(pdata->ioaddr)) return PTR_ERR(pdata->ioaddr); } diff --git a/drivers/crypto/sa2ul.c b/drivers/crypto/sa2ul.c index f300b0a5958a..1c6929fb3a13 100644 --- a/drivers/crypto/sa2ul.c +++ b/drivers/crypto/sa2ul.c @@ -69,8 +69,24 @@ /* Max Authentication tag size */ #define SA_MAX_AUTH_TAG_SZ 64 -#define PRIV_ID 0x1 -#define PRIV 0x1 +enum sa_algo_id { + SA_ALG_CBC_AES = 0, + SA_ALG_EBC_AES, + SA_ALG_CBC_DES3, + SA_ALG_ECB_DES3, + SA_ALG_SHA1, + SA_ALG_SHA256, + SA_ALG_SHA512, + SA_ALG_AUTHENC_SHA1_AES, + SA_ALG_AUTHENC_SHA256_AES, +}; + +struct sa_match_data { + u8 priv; + u8 priv_id; + u32 supported_algos; + bool skip_engine_control; +}; static struct device *sa_k3_dev; @@ -696,8 +712,9 @@ static void sa_dump_sc(u8 *buf, dma_addr_t dma_addr) } static -int sa_init_sc(struct sa_ctx_info *ctx, const u8 *enc_key, - u16 enc_key_sz, const u8 *auth_key, u16 auth_key_sz, +int sa_init_sc(struct sa_ctx_info *ctx, const struct sa_match_data *match_data, + const u8 *enc_key, u16 enc_key_sz, + const u8 *auth_key, u16 auth_key_sz, struct algo_data *ad, u8 enc, u32 *swinfo) { int enc_sc_offset = 0; @@ -732,8 +749,8 @@ int sa_init_sc(struct sa_ctx_info *ctx, const u8 *enc_key, sc_buf[SA_CTX_SCCTL_OWNER_OFFSET] = 0; memcpy(&sc_buf[2], &sc_id, 2); sc_buf[4] = 0x0; - sc_buf[5] = PRIV_ID; - sc_buf[6] = PRIV; + sc_buf[5] = match_data->priv_id; + sc_buf[6] = match_data->priv; sc_buf[7] = 0x0; /* Prepare context for encryption engine */ @@ -892,8 +909,8 @@ static int sa_cipher_setkey(struct crypto_skcipher *tfm, const u8 *key, return ret; /* Setup Encryption Security Context & Command label template */ - if (sa_init_sc(&ctx->enc, key, keylen, NULL, 0, ad, 1, - &ctx->enc.epib[1])) + if (sa_init_sc(&ctx->enc, ctx->dev_data->match_data, key, keylen, NULL, 0, + ad, 1, &ctx->enc.epib[1])) goto badkey; cmdl_len = sa_format_cmdl_gen(&cfg, @@ -905,8 +922,8 @@ static int sa_cipher_setkey(struct crypto_skcipher *tfm, const u8 *key, ctx->enc.cmdl_size = cmdl_len; /* Setup Decryption Security Context & Command label template */ - if (sa_init_sc(&ctx->dec, key, keylen, NULL, 0, ad, 0, - &ctx->dec.epib[1])) + if (sa_init_sc(&ctx->dec, ctx->dev_data->match_data, key, keylen, NULL, 0, + ad, 0, &ctx->dec.epib[1])) goto badkey; cfg.enc_eng_id = ad->enc_eng.eng_id; @@ -1106,7 +1123,7 @@ static int sa_run(struct sa_req *req) else dma_rx = pdata->dma_rx1; - ddev = dma_rx->device->dev; + ddev = dmaengine_get_dma_device(pdata->dma_tx); rxd->ddev = ddev; memcpy(cmdl, sa_ctx->cmdl, sa_ctx->cmdl_size); @@ -1146,8 +1163,10 @@ static int sa_run(struct sa_req *req) mapped_sg->sgt.sgl = src; mapped_sg->sgt.orig_nents = src_nents; ret = dma_map_sgtable(ddev, &mapped_sg->sgt, dir_src, 0); - if (ret) + if (ret) { + kfree(rxd); return ret; + } mapped_sg->dir = dir_src; mapped_sg->mapped = true; @@ -1155,8 +1174,10 @@ static int sa_run(struct sa_req *req) mapped_sg->sgt.sgl = req->src; mapped_sg->sgt.orig_nents = sg_nents; ret = dma_map_sgtable(ddev, &mapped_sg->sgt, dir_src, 0); - if (ret) + if (ret) { + kfree(rxd); return ret; + } mapped_sg->dir = dir_src; mapped_sg->mapped = true; @@ -1446,9 +1467,10 @@ static int sa_sha_setup(struct sa_tfm_ctx *ctx, struct algo_data *ad) cfg.akey = NULL; cfg.akey_len = 0; + ctx->dev_data = dev_get_drvdata(sa_k3_dev); /* Setup Encryption Security Context & Command label template */ - if (sa_init_sc(&ctx->enc, NULL, 0, NULL, 0, ad, 0, - &ctx->enc.epib[1])) + if (sa_init_sc(&ctx->enc, ctx->dev_data->match_data, NULL, 0, NULL, 0, + ad, 0, &ctx->enc.epib[1])) goto badkey; cmdl_len = sa_format_cmdl_gen(&cfg, @@ -1716,6 +1738,7 @@ static int sa_cra_init_aead(struct crypto_aead *tfm, const char *hash, int ret; memzero_explicit(ctx, sizeof(*ctx)); + ctx->dev_data = data; ctx->shash = crypto_alloc_shash(hash, 0, CRYPTO_ALG_NEED_FALLBACK); if (IS_ERR(ctx->shash)) { @@ -1817,8 +1840,8 @@ static int sa_aead_setkey(struct crypto_aead *authenc, cfg.akey_len = keys.authkeylen; /* Setup Encryption Security Context & Command label template */ - if (sa_init_sc(&ctx->enc, keys.enckey, keys.enckeylen, - keys.authkey, keys.authkeylen, + if (sa_init_sc(&ctx->enc, ctx->dev_data->match_data, keys.enckey, + keys.enckeylen, keys.authkey, keys.authkeylen, ad, 1, &ctx->enc.epib[1])) return -EINVAL; @@ -1831,8 +1854,8 @@ static int sa_aead_setkey(struct crypto_aead *authenc, ctx->enc.cmdl_size = cmdl_len; /* Setup Decryption Security Context & Command label template */ - if (sa_init_sc(&ctx->dec, keys.enckey, keys.enckeylen, - keys.authkey, keys.authkeylen, + if (sa_init_sc(&ctx->dec, ctx->dev_data->match_data, keys.enckey, + keys.enckeylen, keys.authkey, keys.authkeylen, ad, 0, &ctx->dec.epib[1])) return -EINVAL; @@ -1950,7 +1973,7 @@ static int sa_aead_decrypt(struct aead_request *req) } static struct sa_alg_tmpl sa_algs[] = { - { + [SA_ALG_CBC_AES] = { .type = CRYPTO_ALG_TYPE_SKCIPHER, .alg.skcipher = { .base.cra_name = "cbc(aes)", @@ -1973,7 +1996,7 @@ static struct sa_alg_tmpl sa_algs[] = { .decrypt = sa_decrypt, } }, - { + [SA_ALG_EBC_AES] = { .type = CRYPTO_ALG_TYPE_SKCIPHER, .alg.skcipher = { .base.cra_name = "ecb(aes)", @@ -1995,7 +2018,7 @@ static struct sa_alg_tmpl sa_algs[] = { .decrypt = sa_decrypt, } }, - { + [SA_ALG_CBC_DES3] = { .type = CRYPTO_ALG_TYPE_SKCIPHER, .alg.skcipher = { .base.cra_name = "cbc(des3_ede)", @@ -2018,7 +2041,7 @@ static struct sa_alg_tmpl sa_algs[] = { .decrypt = sa_decrypt, } }, - { + [SA_ALG_ECB_DES3] = { .type = CRYPTO_ALG_TYPE_SKCIPHER, .alg.skcipher = { .base.cra_name = "ecb(des3_ede)", @@ -2040,7 +2063,7 @@ static struct sa_alg_tmpl sa_algs[] = { .decrypt = sa_decrypt, } }, - { + [SA_ALG_SHA1] = { .type = CRYPTO_ALG_TYPE_AHASH, .alg.ahash = { .halg.base = { @@ -2069,7 +2092,7 @@ static struct sa_alg_tmpl sa_algs[] = { .import = sa_sha_import, }, }, - { + [SA_ALG_SHA256] = { .type = CRYPTO_ALG_TYPE_AHASH, .alg.ahash = { .halg.base = { @@ -2098,7 +2121,7 @@ static struct sa_alg_tmpl sa_algs[] = { .import = sa_sha_import, }, }, - { + [SA_ALG_SHA512] = { .type = CRYPTO_ALG_TYPE_AHASH, .alg.ahash = { .halg.base = { @@ -2127,7 +2150,7 @@ static struct sa_alg_tmpl sa_algs[] = { .import = sa_sha_import, }, }, - { + [SA_ALG_AUTHENC_SHA1_AES] = { .type = CRYPTO_ALG_TYPE_AEAD, .alg.aead = { .base = { @@ -2154,7 +2177,7 @@ static struct sa_alg_tmpl sa_algs[] = { .decrypt = sa_aead_decrypt, }, }, - { + [SA_ALG_AUTHENC_SHA256_AES] = { .type = CRYPTO_ALG_TYPE_AEAD, .alg.aead = { .base = { @@ -2185,13 +2208,19 @@ static struct sa_alg_tmpl sa_algs[] = { }; /* Register the algorithms in crypto framework */ -static void sa_register_algos(const struct device *dev) +static void sa_register_algos(struct sa_crypto_data *dev_data) { + const struct sa_match_data *match_data = dev_data->match_data; + struct device *dev = dev_data->dev; char *alg_name; u32 type; int i, err; for (i = 0; i < ARRAY_SIZE(sa_algs); i++) { + /* Skip unsupported algos */ + if (!(match_data->supported_algos & BIT(i))) + continue; + type = sa_algs[i].type; if (type == CRYPTO_ALG_TYPE_SKCIPHER) { alg_name = sa_algs[i].alg.skcipher.base.cra_name; @@ -2329,14 +2358,39 @@ static int sa_link_child(struct device *dev, void *data) return 0; } +static struct sa_match_data am654_match_data = { + .priv = 1, + .priv_id = 1, + .supported_algos = GENMASK(SA_ALG_AUTHENC_SHA256_AES, 0), +}; + +static struct sa_match_data am64_match_data = { + .priv = 0, + .priv_id = 0, + .supported_algos = BIT(SA_ALG_CBC_AES) | + BIT(SA_ALG_EBC_AES) | + BIT(SA_ALG_SHA256) | + BIT(SA_ALG_SHA512) | + BIT(SA_ALG_AUTHENC_SHA256_AES), + .skip_engine_control = true, +}; + +static const struct of_device_id of_match[] = { + { .compatible = "ti,j721e-sa2ul", .data = &am654_match_data, }, + { .compatible = "ti,am654-sa2ul", .data = &am654_match_data, }, + { .compatible = "ti,am64-sa2ul", .data = &am64_match_data, }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_match); + static int sa_ul_probe(struct platform_device *pdev) { + const struct of_device_id *match; struct device *dev = &pdev->dev; struct device_node *node = dev->of_node; struct resource *res; static void __iomem *saul_base; struct sa_crypto_data *dev_data; - u32 val; int ret; dev_data = devm_kzalloc(dev, sizeof(*dev_data), GFP_KERNEL); @@ -2350,7 +2404,7 @@ static int sa_ul_probe(struct platform_device *pdev) dev_set_drvdata(sa_k3_dev, dev_data); pm_runtime_enable(dev); - ret = pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); if (ret < 0) { dev_err(&pdev->dev, "%s: failed to get sync: %d\n", __func__, ret); @@ -2362,18 +2416,28 @@ static int sa_ul_probe(struct platform_device *pdev) if (ret) goto disable_pm_runtime; + match = of_match_node(of_match, dev->of_node); + if (!match) { + dev_err(dev, "No compatible match found\n"); + return -ENODEV; + } + dev_data->match_data = match->data; + spin_lock_init(&dev_data->scid_lock); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); saul_base = devm_ioremap_resource(dev, res); dev_data->base = saul_base; - val = SA_EEC_ENCSS_EN | SA_EEC_AUTHSS_EN | SA_EEC_CTXCACH_EN | - SA_EEC_CPPI_PORT_IN_EN | SA_EEC_CPPI_PORT_OUT_EN | - SA_EEC_TRNG_EN; - writel_relaxed(val, saul_base + SA_ENGINE_ENABLE_CONTROL); + if (!dev_data->match_data->skip_engine_control) { + u32 val = SA_EEC_ENCSS_EN | SA_EEC_AUTHSS_EN | SA_EEC_CTXCACH_EN | + SA_EEC_CPPI_PORT_IN_EN | SA_EEC_CPPI_PORT_OUT_EN | + SA_EEC_TRNG_EN; - sa_register_algos(dev); + writel_relaxed(val, saul_base + SA_ENGINE_ENABLE_CONTROL); + } + + sa_register_algos(dev_data); ret = of_platform_populate(node, NULL, NULL, &pdev->dev); if (ret) @@ -2419,13 +2483,6 @@ static int sa_ul_remove(struct platform_device *pdev) return 0; } -static const struct of_device_id of_match[] = { - {.compatible = "ti,j721e-sa2ul",}, - {.compatible = "ti,am654-sa2ul",}, - {}, -}; -MODULE_DEVICE_TABLE(of, of_match); - static struct platform_driver sa_ul_driver = { .probe = sa_ul_probe, .remove = sa_ul_remove, diff --git a/drivers/crypto/sa2ul.h b/drivers/crypto/sa2ul.h index f597ddecde34..ed66d1f111db 100644 --- a/drivers/crypto/sa2ul.h +++ b/drivers/crypto/sa2ul.h @@ -171,9 +171,12 @@ struct sa_tfm_ctx; #define SA_UNSAFE_DATA_SZ_MIN 240 #define SA_UNSAFE_DATA_SZ_MAX 256 +struct sa_match_data; + /** * struct sa_crypto_data - Crypto driver instance data * @base: Base address of the register space + * @soc_data: Pointer to SoC specific data * @pdev: Platform device pointer * @sc_pool: security context pool * @dev: Device pointer @@ -189,6 +192,7 @@ struct sa_tfm_ctx; */ struct sa_crypto_data { void __iomem *base; + const struct sa_match_data *match_data; struct platform_device *pdev; struct dma_pool *sc_pool; struct device *dev; diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c index 2a4793176c71..7389a0536ff0 100644 --- a/drivers/crypto/stm32/stm32-cryp.c +++ b/drivers/crypto/stm32/stm32-cryp.c @@ -542,7 +542,7 @@ static int stm32_cryp_hw_init(struct stm32_cryp *cryp) int ret; u32 cfg, hw_mode; - pm_runtime_get_sync(cryp->dev); + pm_runtime_resume_and_get(cryp->dev); /* Disable interrupt */ stm32_cryp_write(cryp, CRYP_IMSCR, 0); @@ -2043,7 +2043,7 @@ static int stm32_cryp_remove(struct platform_device *pdev) if (!cryp) return -ENODEV; - ret = pm_runtime_get_sync(cryp->dev); + ret = pm_runtime_resume_and_get(cryp->dev); if (ret < 0) return ret; diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c index 7ac0573ef663..389de9e3302d 100644 --- a/drivers/crypto/stm32/stm32-hash.c +++ b/drivers/crypto/stm32/stm32-hash.c @@ -813,7 +813,7 @@ static void stm32_hash_finish_req(struct ahash_request *req, int err) static int stm32_hash_hw_init(struct stm32_hash_dev *hdev, struct stm32_hash_request_ctx *rctx) { - pm_runtime_get_sync(hdev->dev); + pm_runtime_resume_and_get(hdev->dev); if (!(HASH_FLAGS_INIT & hdev->flags)) { stm32_hash_write(hdev, HASH_CR, HASH_CR_INIT); @@ -962,7 +962,7 @@ static int stm32_hash_export(struct ahash_request *req, void *out) u32 *preg; unsigned int i; - pm_runtime_get_sync(hdev->dev); + pm_runtime_resume_and_get(hdev->dev); while ((stm32_hash_read(hdev, HASH_SR) & HASH_SR_BUSY)) cpu_relax(); @@ -1000,7 +1000,7 @@ static int stm32_hash_import(struct ahash_request *req, const void *in) preg = rctx->hw_context; - pm_runtime_get_sync(hdev->dev); + pm_runtime_resume_and_get(hdev->dev); stm32_hash_write(hdev, HASH_IMR, *preg++); stm32_hash_write(hdev, HASH_STR, *preg++); @@ -1566,7 +1566,7 @@ static int stm32_hash_remove(struct platform_device *pdev) if (!hdev) return -ENODEV; - ret = pm_runtime_get_sync(hdev->dev); + ret = pm_runtime_resume_and_get(hdev->dev); if (ret < 0) return ret; diff --git a/drivers/crypto/ux500/cryp/cryp.c b/drivers/crypto/ux500/cryp/cryp.c index 9866c2a5e9a7..759d0d9786fd 100644 --- a/drivers/crypto/ux500/cryp/cryp.c +++ b/drivers/crypto/ux500/cryp/cryp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * Copyright (C) ST-Ericsson SA 2010 * Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson. * Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson. @@ -15,7 +15,7 @@ #include "cryp_p.h" #include "cryp.h" -/** +/* * cryp_wait_until_done - wait until the device logic is not busy */ void cryp_wait_until_done(struct cryp_device_data *device_data) @@ -285,6 +285,7 @@ int cryp_configure_init_vector(struct cryp_device_data *device_data, * other device context parameter * @device_data: Pointer to the device data struct for base address. * @ctx: Crypto device context + * @cryp_mode: Mode: Polling, Interrupt or DMA */ void cryp_save_device_context(struct cryp_device_data *device_data, struct cryp_device_context *ctx, diff --git a/drivers/crypto/ux500/cryp/cryp.h b/drivers/crypto/ux500/cryp/cryp.h index 8da7f87b339b..db5713d7c940 100644 --- a/drivers/crypto/ux500/cryp/cryp.h +++ b/drivers/crypto/ux500/cryp/cryp.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/** +/* * Copyright (C) ST-Ericsson SA 2010 * Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson. * Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson. diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c index c3adeb2e5823..30cdd5253929 100644 --- a/drivers/crypto/ux500/cryp/cryp_core.c +++ b/drivers/crypto/ux500/cryp/cryp_core.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * Copyright (C) ST-Ericsson SA 2010 * Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson. * Author: Joakim Bech <joakim.xx.bech@stericsson.com> for ST-Ericsson. @@ -62,7 +62,7 @@ struct cryp_driver_data { /** * struct cryp_ctx - Crypto context * @config: Crypto mode. - * @key[CRYP_MAX_KEY_SIZE]: Key. + * @key: Key array. * @keylen: Length of key. * @iv: Pointer to initialization vector. * @indata: Pointer to indata. @@ -73,6 +73,7 @@ struct cryp_driver_data { * @updated: Updated flag. * @dev_ctx: Device dependent context. * @device: Pointer to the device. + * @session_id: Atomic session ID. */ struct cryp_ctx { struct cryp_config config; @@ -608,12 +609,12 @@ static void cryp_dma_done(struct cryp_ctx *ctx) chan = ctx->device->dma.chan_mem2cryp; dmaengine_terminate_all(chan); dma_unmap_sg(chan->device->dev, ctx->device->dma.sg_src, - ctx->device->dma.sg_src_len, DMA_TO_DEVICE); + ctx->device->dma.nents_src, DMA_TO_DEVICE); chan = ctx->device->dma.chan_cryp2mem; dmaengine_terminate_all(chan); dma_unmap_sg(chan->device->dev, ctx->device->dma.sg_dst, - ctx->device->dma.sg_dst_len, DMA_FROM_DEVICE); + ctx->device->dma.nents_dst, DMA_FROM_DEVICE); } static int cryp_dma_write(struct cryp_ctx *ctx, struct scatterlist *sg, @@ -1290,7 +1291,6 @@ static int ux500_cryp_probe(struct platform_device *pdev) device_data->phybase = res->start; device_data->base = devm_ioremap_resource(dev, res); if (IS_ERR(device_data->base)) { - dev_err(dev, "[%s]: ioremap failed!", __func__); ret = PTR_ERR(device_data->base); goto out; } diff --git a/drivers/crypto/ux500/cryp/cryp_irq.c b/drivers/crypto/ux500/cryp/cryp_irq.c index 7ebde69e8c76..6d2f07bec98a 100644 --- a/drivers/crypto/ux500/cryp/cryp_irq.c +++ b/drivers/crypto/ux500/cryp/cryp_irq.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * Copyright (C) ST-Ericsson SA 2010 * Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson. * Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson. diff --git a/drivers/crypto/ux500/cryp/cryp_irq.h b/drivers/crypto/ux500/cryp/cryp_irq.h index 1984f30100ff..da90029ea141 100644 --- a/drivers/crypto/ux500/cryp/cryp_irq.h +++ b/drivers/crypto/ux500/cryp/cryp_irq.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/** +/* * Copyright (C) ST-Ericsson SA 2010 * Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson. * Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson. @@ -19,7 +19,7 @@ enum cryp_irq_src_id { CRYP_IRQ_SRC_ALL = 0x3 }; -/** +/* * M0 Funtions */ void cryp_enable_irq_src(struct cryp_device_data *device_data, u32 irq_src); diff --git a/drivers/crypto/ux500/cryp/cryp_irqp.h b/drivers/crypto/ux500/cryp/cryp_irqp.h index 879ed68a12d7..4981a3f461e5 100644 --- a/drivers/crypto/ux500/cryp/cryp_irqp.h +++ b/drivers/crypto/ux500/cryp/cryp_irqp.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/** +/* * Copyright (C) ST-Ericsson SA 2010 * Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson. * Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson. @@ -13,7 +13,7 @@ #include "cryp_irq.h" -/** +/* * * CRYP Registers - Offset mapping * +-----------------+ diff --git a/drivers/crypto/ux500/cryp/cryp_p.h b/drivers/crypto/ux500/cryp/cryp_p.h index 0df84eaa8531..60b47fe4de35 100644 --- a/drivers/crypto/ux500/cryp/cryp_p.h +++ b/drivers/crypto/ux500/cryp/cryp_p.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/** +/* * Copyright (C) ST-Ericsson SA 2010 * Author: Shujuan Chen <shujuan.chen@stericsson.com> for ST-Ericsson. * Author: Jonas Linde <jonas.linde@stericsson.com> for ST-Ericsson. @@ -17,7 +17,7 @@ #include "cryp.h" #include "cryp_irqp.h" -/** +/* * Generic Macros */ #define CRYP_SET_BITS(reg_name, mask) \ @@ -34,7 +34,7 @@ writel_relaxed(((readl_relaxed(reg) & ~(mask)) | \ (((u32)val << shift) & (mask))), reg) -/** +/* * CRYP specific Macros */ #define CRYP_PERIPHERAL_ID0 0xE3 @@ -48,7 +48,7 @@ #define CRYP_PCELL_ID2 0x05 #define CRYP_PCELL_ID3 0xB1 -/** +/* * CRYP register default values */ #define MAX_DEVICE_SUPPORT 2 @@ -62,7 +62,7 @@ #define CRYP_KEY_DEFAULT 0x0 #define CRYP_INIT_VECT_DEFAULT 0x0 -/** +/* * CRYP Control register specific mask */ #define CRYP_CR_SECURE_MASK BIT(0) @@ -81,7 +81,6 @@ CRYP_CR_PRLG_MASK |\ CRYP_CR_ALGODIR_MASK |\ CRYP_CR_ALGOMODE_MASK |\ - CRYP_CR_DATATYPE_MASK |\ CRYP_CR_KEYSIZE_MASK |\ CRYP_CR_KEYRDEN_MASK |\ CRYP_CR_DATATYPE_MASK) @@ -91,7 +90,7 @@ #define CRYP_SR_IFEM_MASK BIT(0) #define CRYP_SR_BUSY_MASK BIT(4) -/** +/* * Bit position used while setting bits in register */ #define CRYP_CR_PRLG_POS 1 @@ -107,7 +106,7 @@ #define CRYP_SR_BUSY_POS 4 -/** +/* * CRYP PCRs------PC_NAND control register * BIT_MASK */ diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c index da284b0ea1b2..ecb7412e84e3 100644 --- a/drivers/crypto/ux500/hash/hash_core.c +++ b/drivers/crypto/ux500/hash/hash_core.c @@ -190,7 +190,7 @@ static void hash_dma_done(struct hash_ctx *ctx) chan = ctx->device->dma.chan_mem2hash; dmaengine_terminate_all(chan); dma_unmap_sg(chan->device->dev, ctx->device->dma.sg, - ctx->device->dma.sg_len, DMA_TO_DEVICE); + ctx->device->dma.nents, DMA_TO_DEVICE); } static int hash_dma_write(struct hash_ctx *ctx, @@ -356,7 +356,7 @@ out: /** * hash_get_device_data - Checks for an available hash device and return it. - * @hash_ctx: Structure for the hash context. + * @ctx: Structure for the hash context. * @device_data: Structure for the hash device. * * This function check for an available hash device and return it to @@ -542,7 +542,7 @@ static bool hash_dma_valid_data(struct scatterlist *sg, int datasize) } /** - * hash_init - Common hash init function for SHA1/SHA2 (SHA256). + * ux500_hash_init - Common hash init function for SHA1/SHA2 (SHA256). * @req: The hash request for the job. * * Initialize structures. @@ -585,6 +585,7 @@ static int ux500_hash_init(struct ahash_request *req) * @device_data: Structure for the hash device. * @message: Block (512 bits) of message to be written to * the HASH hardware. + * @length: Message length * */ static void hash_processblock(struct hash_device_data *device_data, @@ -1295,7 +1296,7 @@ void hash_get_digest(struct hash_device_data *device_data, } /** - * hash_update - The hash update function for SHA1/SHA2 (SHA256). + * ahash_update - The hash update function for SHA1/SHA2 (SHA256). * @req: The hash request for the job. */ static int ahash_update(struct ahash_request *req) @@ -1315,7 +1316,7 @@ static int ahash_update(struct ahash_request *req) } /** - * hash_final - The hash final function for SHA1/SHA2 (SHA256). + * ahash_final - The hash final function for SHA1/SHA2 (SHA256). * @req: The hash request for the job. */ static int ahash_final(struct ahash_request *req) @@ -1615,9 +1616,6 @@ static struct hash_algo_template hash_algs[] = { } }; -/** - * hash_algs_register_all - - */ static int ahash_algs_register_all(struct hash_device_data *device_data) { int ret; @@ -1640,9 +1638,6 @@ unreg: return ret; } -/** - * hash_algs_unregister_all - - */ static void ahash_algs_unregister_all(struct hash_device_data *device_data) { int i; @@ -1681,7 +1676,6 @@ static int ux500_hash_probe(struct platform_device *pdev) device_data->phybase = res->start; device_data->base = devm_ioremap_resource(dev, res); if (IS_ERR(device_data->base)) { - dev_err(dev, "%s: ioremap() failed!\n", __func__); ret = PTR_ERR(device_data->base); goto out; } diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c index d05c02baebcf..ec06189fbf99 100644 --- a/drivers/crypto/vmx/aes.c +++ b/drivers/crypto/vmx/aes.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES routines supporting VMX instructions on the Power 8 * * Copyright (C) 2015 International Business Machines Inc. diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c index d88084447f1c..ed0debc7acb5 100644 --- a/drivers/crypto/vmx/aes_cbc.c +++ b/drivers/crypto/vmx/aes_cbc.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES CBC routines supporting VMX instructions on the Power 8 * * Copyright (C) 2015 International Business Machines Inc. diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c index 79ba062ee1c1..9a3da8cd62f3 100644 --- a/drivers/crypto/vmx/aes_ctr.c +++ b/drivers/crypto/vmx/aes_ctr.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES CTR routines supporting VMX instructions on the Power 8 * * Copyright (C) 2015 International Business Machines Inc. diff --git a/drivers/crypto/vmx/aes_xts.c b/drivers/crypto/vmx/aes_xts.c index 9fee1b1532a4..dabbccb41550 100644 --- a/drivers/crypto/vmx/aes_xts.c +++ b/drivers/crypto/vmx/aes_xts.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * AES XTS routines supporting VMX In-core instructions on Power 8 * * Copyright (C) 2015 International Business Machines Inc. diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c index 14807ac2e3b9..5bc5710a6de0 100644 --- a/drivers/crypto/vmx/ghash.c +++ b/drivers/crypto/vmx/ghash.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * GHASH routines supporting VMX instructions on the Power 8 * * Copyright (C) 2015, 2019 International Business Machines Inc. diff --git a/drivers/crypto/vmx/vmx.c b/drivers/crypto/vmx/vmx.c index a40d08e75fc0..7eb713cc87c8 100644 --- a/drivers/crypto/vmx/vmx.c +++ b/drivers/crypto/vmx/vmx.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * Routines supporting VMX instructions on the Power 8 * * Copyright (C) 2015 International Business Machines Inc. diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c index 244cb7d89678..2acc6173da36 100644 --- a/drivers/cxl/mem.c +++ b/drivers/cxl/mem.c @@ -4,6 +4,7 @@ #include <linux/security.h> #include <linux/debugfs.h> #include <linux/module.h> +#include <linux/sizes.h> #include <linux/mutex.h> #include <linux/cdev.h> #include <linux/idr.h> @@ -96,21 +97,18 @@ struct mbox_cmd { * @dev: driver core device object * @cdev: char dev core object for ioctl operations * @cxlm: pointer to the parent device driver data - * @ops_active: active user of @cxlm in ops handlers - * @ops_dead: completion when all @cxlm ops users have exited * @id: id number of this memdev instance. */ struct cxl_memdev { struct device dev; struct cdev cdev; struct cxl_mem *cxlm; - struct percpu_ref ops_active; - struct completion ops_dead; int id; }; static int cxl_mem_major; static DEFINE_IDA(cxl_memdev_ida); +static DECLARE_RWSEM(cxl_memdev_rwsem); static struct dentry *cxl_debugfs; static bool cxl_raw_allow_all; @@ -169,7 +167,7 @@ struct cxl_mem_command { * table will be validated against the user's input. For example, if size_in is * 0, and the user passed in 1, it is an error. */ -static struct cxl_mem_command mem_commands[] = { +static struct cxl_mem_command mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(IDENTIFY, 0, 0x43, CXL_CMD_FLAG_FORCE_ENABLE), #ifdef CONFIG_CXL_MEM_RAW_COMMANDS CXL_CMD(RAW, ~0, ~0, 0), @@ -776,26 +774,43 @@ static long __cxl_memdev_ioctl(struct cxl_memdev *cxlmd, unsigned int cmd, static long cxl_memdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { - struct cxl_memdev *cxlmd; - struct inode *inode; - int rc = -ENOTTY; + struct cxl_memdev *cxlmd = file->private_data; + int rc = -ENXIO; - inode = file_inode(file); - cxlmd = container_of(inode->i_cdev, typeof(*cxlmd), cdev); + down_read(&cxl_memdev_rwsem); + if (cxlmd->cxlm) + rc = __cxl_memdev_ioctl(cxlmd, cmd, arg); + up_read(&cxl_memdev_rwsem); - if (!percpu_ref_tryget_live(&cxlmd->ops_active)) - return -ENXIO; + return rc; +} - rc = __cxl_memdev_ioctl(cxlmd, cmd, arg); +static int cxl_memdev_open(struct inode *inode, struct file *file) +{ + struct cxl_memdev *cxlmd = + container_of(inode->i_cdev, typeof(*cxlmd), cdev); - percpu_ref_put(&cxlmd->ops_active); + get_device(&cxlmd->dev); + file->private_data = cxlmd; - return rc; + return 0; +} + +static int cxl_memdev_release_file(struct inode *inode, struct file *file) +{ + struct cxl_memdev *cxlmd = + container_of(inode->i_cdev, typeof(*cxlmd), cdev); + + put_device(&cxlmd->dev); + + return 0; } static const struct file_operations cxl_memdev_fops = { .owner = THIS_MODULE, .unlocked_ioctl = cxl_memdev_ioctl, + .open = cxl_memdev_open, + .release = cxl_memdev_release_file, .compat_ioctl = compat_ptr_ioctl, .llseek = noop_llseek, }; @@ -984,7 +999,7 @@ static struct cxl_mem *cxl_mem_create(struct pci_dev *pdev, u32 reg_lo, return NULL; } - offset = ((u64)reg_hi << 32) | FIELD_GET(CXL_REGLOC_ADDR_MASK, reg_lo); + offset = ((u64)reg_hi << 32) | (reg_lo & CXL_REGLOC_ADDR_MASK); bar = FIELD_GET(CXL_REGLOC_BIR_MASK, reg_lo); /* Basic sanity check that BAR is big enough */ @@ -1049,7 +1064,6 @@ static void cxl_memdev_release(struct device *dev) { struct cxl_memdev *cxlmd = to_cxl_memdev(dev); - percpu_ref_exit(&cxlmd->ops_active); ida_free(&cxl_memdev_ida, cxlmd->id); kfree(cxlmd); } @@ -1066,7 +1080,7 @@ static ssize_t firmware_version_show(struct device *dev, struct cxl_memdev *cxlmd = to_cxl_memdev(dev); struct cxl_mem *cxlm = cxlmd->cxlm; - return sprintf(buf, "%.16s\n", cxlm->firmware_version); + return sysfs_emit(buf, "%.16s\n", cxlm->firmware_version); } static DEVICE_ATTR_RO(firmware_version); @@ -1076,7 +1090,7 @@ static ssize_t payload_max_show(struct device *dev, struct cxl_memdev *cxlmd = to_cxl_memdev(dev); struct cxl_mem *cxlm = cxlmd->cxlm; - return sprintf(buf, "%zu\n", cxlm->payload_size); + return sysfs_emit(buf, "%zu\n", cxlm->payload_size); } static DEVICE_ATTR_RO(payload_max); @@ -1087,7 +1101,7 @@ static ssize_t ram_size_show(struct device *dev, struct device_attribute *attr, struct cxl_mem *cxlm = cxlmd->cxlm; unsigned long long len = range_len(&cxlm->ram_range); - return sprintf(buf, "%#llx\n", len); + return sysfs_emit(buf, "%#llx\n", len); } static struct device_attribute dev_attr_ram_size = @@ -1100,7 +1114,7 @@ static ssize_t pmem_size_show(struct device *dev, struct device_attribute *attr, struct cxl_mem *cxlm = cxlmd->cxlm; unsigned long long len = range_len(&cxlm->pmem_range); - return sprintf(buf, "%#llx\n", len); + return sysfs_emit(buf, "%#llx\n", len); } static struct device_attribute dev_attr_pmem_size = @@ -1150,27 +1164,24 @@ static const struct device_type cxl_memdev_type = { .groups = cxl_memdev_attribute_groups, }; -static void cxlmdev_unregister(void *_cxlmd) +static void cxl_memdev_shutdown(struct cxl_memdev *cxlmd) { - struct cxl_memdev *cxlmd = _cxlmd; - struct device *dev = &cxlmd->dev; - - percpu_ref_kill(&cxlmd->ops_active); - cdev_device_del(&cxlmd->cdev, dev); - wait_for_completion(&cxlmd->ops_dead); + down_write(&cxl_memdev_rwsem); cxlmd->cxlm = NULL; - put_device(dev); + up_write(&cxl_memdev_rwsem); } -static void cxlmdev_ops_active_release(struct percpu_ref *ref) +static void cxl_memdev_unregister(void *_cxlmd) { - struct cxl_memdev *cxlmd = - container_of(ref, typeof(*cxlmd), ops_active); + struct cxl_memdev *cxlmd = _cxlmd; + struct device *dev = &cxlmd->dev; - complete(&cxlmd->ops_dead); + cdev_device_del(&cxlmd->cdev, dev); + cxl_memdev_shutdown(cxlmd); + put_device(dev); } -static int cxl_mem_add_memdev(struct cxl_mem *cxlm) +static struct cxl_memdev *cxl_memdev_alloc(struct cxl_mem *cxlm) { struct pci_dev *pdev = cxlm->pdev; struct cxl_memdev *cxlmd; @@ -1180,22 +1191,11 @@ static int cxl_mem_add_memdev(struct cxl_mem *cxlm) cxlmd = kzalloc(sizeof(*cxlmd), GFP_KERNEL); if (!cxlmd) - return -ENOMEM; - init_completion(&cxlmd->ops_dead); - - /* - * @cxlm is deallocated when the driver unbinds so operations - * that are using it need to hold a live reference. - */ - cxlmd->cxlm = cxlm; - rc = percpu_ref_init(&cxlmd->ops_active, cxlmdev_ops_active_release, 0, - GFP_KERNEL); - if (rc) - goto err_ref; + return ERR_PTR(-ENOMEM); rc = ida_alloc_range(&cxl_memdev_ida, 0, CXL_MEM_MAX_DEVS, GFP_KERNEL); if (rc < 0) - goto err_id; + goto err; cxlmd->id = rc; dev = &cxlmd->dev; @@ -1204,30 +1204,54 @@ static int cxl_mem_add_memdev(struct cxl_mem *cxlm) dev->bus = &cxl_bus_type; dev->devt = MKDEV(cxl_mem_major, cxlmd->id); dev->type = &cxl_memdev_type; - dev_set_name(dev, "mem%d", cxlmd->id); + device_set_pm_not_required(dev); cdev = &cxlmd->cdev; cdev_init(cdev, &cxl_memdev_fops); + return cxlmd; + +err: + kfree(cxlmd); + return ERR_PTR(rc); +} + +static int cxl_mem_add_memdev(struct cxl_mem *cxlm) +{ + struct cxl_memdev *cxlmd; + struct device *dev; + struct cdev *cdev; + int rc; + + cxlmd = cxl_memdev_alloc(cxlm); + if (IS_ERR(cxlmd)) + return PTR_ERR(cxlmd); + + dev = &cxlmd->dev; + rc = dev_set_name(dev, "mem%d", cxlmd->id); + if (rc) + goto err; + + /* + * Activate ioctl operations, no cxl_memdev_rwsem manipulation + * needed as this is ordered with cdev_add() publishing the device. + */ + cxlmd->cxlm = cxlm; + cdev = &cxlmd->cdev; rc = cdev_device_add(cdev, dev); if (rc) - goto err_add; + goto err; - return devm_add_action_or_reset(dev->parent, cxlmdev_unregister, cxlmd); + return devm_add_action_or_reset(dev->parent, cxl_memdev_unregister, + cxlmd); -err_add: - ida_free(&cxl_memdev_ida, cxlmd->id); -err_id: +err: /* - * Theoretically userspace could have already entered the fops, - * so flush ops_active. + * The cdev was briefly live, shutdown any ioctl operations that + * saw that state. */ - percpu_ref_kill(&cxlmd->ops_active); - wait_for_completion(&cxlmd->ops_dead); - percpu_ref_exit(&cxlmd->ops_active); -err_ref: - kfree(cxlmd); - + cxl_memdev_shutdown(cxlmd); + put_device(dev); return rc; } @@ -1396,6 +1420,7 @@ out: */ static int cxl_mem_identify(struct cxl_mem *cxlm) { + /* See CXL 2.0 Table 175 Identify Memory Device Output Payload */ struct cxl_mbox_identify { char fw_revision[0x10]; __le64 total_capacity; @@ -1424,10 +1449,11 @@ static int cxl_mem_identify(struct cxl_mem *cxlm) * For now, only the capacity is exported in sysfs */ cxlm->ram_range.start = 0; - cxlm->ram_range.end = le64_to_cpu(id.volatile_capacity) - 1; + cxlm->ram_range.end = le64_to_cpu(id.volatile_capacity) * SZ_256M - 1; cxlm->pmem_range.start = 0; - cxlm->pmem_range.end = le64_to_cpu(id.persistent_capacity) - 1; + cxlm->pmem_range.end = + le64_to_cpu(id.persistent_capacity) * SZ_256M - 1; memcpy(cxlm->firmware_version, id.fw_revision, sizeof(id.fw_revision)); diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c index 452e85ae87a8..5aee26e1bbd6 100644 --- a/drivers/dax/bus.c +++ b/drivers/dax/bus.c @@ -90,13 +90,11 @@ static ssize_t do_id_store(struct device_driver *drv, const char *buf, list_add(&dax_id->list, &dax_drv->ids); } else rc = -ENOMEM; - } else - /* nothing to remove */; + } } else if (action == ID_REMOVE) { list_del(&dax_id->list); kfree(dax_id); - } else - /* dax_id already added */; + } mutex_unlock(&dax_bus_lock); if (rc < 0) diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index fe6a460c4373..af3ee288bc11 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -1086,6 +1086,7 @@ static int __dma_async_device_channel_register(struct dma_device *device, kfree(chan->dev); err_free_local: free_percpu(chan->local); + chan->local = NULL; return rc; } diff --git a/drivers/dma/dw/Kconfig b/drivers/dma/dw/Kconfig index e5162690de8f..db25f9b7778c 100644 --- a/drivers/dma/dw/Kconfig +++ b/drivers/dma/dw/Kconfig @@ -10,6 +10,7 @@ config DW_DMAC_CORE config DW_DMAC tristate "Synopsys DesignWare AHB DMA platform driver" + depends on HAS_IOMEM select DW_DMAC_CORE help Support the Synopsys DesignWare AHB DMA controller. This @@ -18,6 +19,7 @@ config DW_DMAC config DW_DMAC_PCI tristate "Synopsys DesignWare AHB DMA PCI driver" depends on PCI + depends on HAS_IOMEM select DW_DMAC_CORE help Support the Synopsys DesignWare AHB DMA controller on the diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 84a6ea60ecf0..31c819544a22 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -282,6 +282,22 @@ void idxd_wq_drain(struct idxd_wq *wq) idxd_cmd_exec(idxd, IDXD_CMD_DRAIN_WQ, operand, NULL); } +void idxd_wq_reset(struct idxd_wq *wq) +{ + struct idxd_device *idxd = wq->idxd; + struct device *dev = &idxd->pdev->dev; + u32 operand; + + if (wq->state != IDXD_WQ_ENABLED) { + dev_dbg(dev, "WQ %d in wrong state: %d\n", wq->id, wq->state); + return; + } + + operand = BIT(wq->id % 16) | ((wq->id / 16) << 16); + idxd_cmd_exec(idxd, IDXD_CMD_RESET_WQ, operand, NULL); + wq->state = IDXD_WQ_DISABLED; +} + int idxd_wq_map_portal(struct idxd_wq *wq) { struct idxd_device *idxd = wq->idxd; @@ -363,8 +379,6 @@ int idxd_wq_disable_pasid(struct idxd_wq *wq) void idxd_wq_disable_cleanup(struct idxd_wq *wq) { struct idxd_device *idxd = wq->idxd; - struct device *dev = &idxd->pdev->dev; - int i, wq_offset; lockdep_assert_held(&idxd->dev_lock); memset(wq->wqcfg, 0, idxd->wqcfg_size); @@ -376,14 +390,6 @@ void idxd_wq_disable_cleanup(struct idxd_wq *wq) wq->ats_dis = 0; clear_bit(WQ_FLAG_DEDICATED, &wq->flags); memset(wq->name, 0, WQ_NAME_SIZE); - - for (i = 0; i < WQCFG_STRIDES(idxd); i++) { - wq_offset = WQCFG_OFFSET(idxd, wq->id, i); - iowrite32(0, idxd->reg_base + wq_offset); - dev_dbg(dev, "WQ[%d][%d][%#x]: %#x\n", - wq->id, i, wq_offset, - ioread32(idxd->reg_base + wq_offset)); - } } /* Device control bits */ @@ -574,6 +580,36 @@ void idxd_device_drain_pasid(struct idxd_device *idxd, int pasid) } /* Device configuration bits */ +void idxd_msix_perm_setup(struct idxd_device *idxd) +{ + union msix_perm mperm; + int i, msixcnt; + + msixcnt = pci_msix_vec_count(idxd->pdev); + if (msixcnt < 0) + return; + + mperm.bits = 0; + mperm.pasid = idxd->pasid; + mperm.pasid_en = device_pasid_enabled(idxd); + for (i = 1; i < msixcnt; i++) + iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8); +} + +void idxd_msix_perm_clear(struct idxd_device *idxd) +{ + union msix_perm mperm; + int i, msixcnt; + + msixcnt = pci_msix_vec_count(idxd->pdev); + if (msixcnt < 0) + return; + + mperm.bits = 0; + for (i = 1; i < msixcnt; i++) + iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8); +} + static void idxd_group_config_write(struct idxd_group *group) { struct idxd_device *idxd = group->idxd; @@ -642,7 +678,14 @@ static int idxd_wq_config_write(struct idxd_wq *wq) if (!wq->group) return 0; - memset(wq->wqcfg, 0, idxd->wqcfg_size); + /* + * Instead of memset the entire shadow copy of WQCFG, copy from the hardware after + * wq reset. This will copy back the sticky values that are present on some devices. + */ + for (i = 0; i < WQCFG_STRIDES(idxd); i++) { + wq_offset = WQCFG_OFFSET(idxd, wq->id, i); + wq->wqcfg->bits[i] = ioread32(idxd->reg_base + wq_offset); + } /* byte 0-3 */ wq->wqcfg->wq_size = wq->size; diff --git a/drivers/dma/idxd/idxd.h b/drivers/dma/idxd/idxd.h index 81a0e65fd316..76014c14f473 100644 --- a/drivers/dma/idxd/idxd.h +++ b/drivers/dma/idxd/idxd.h @@ -316,6 +316,8 @@ void idxd_unregister_driver(void); struct bus_type *idxd_get_bus_type(struct idxd_device *idxd); /* device interrupt control */ +void idxd_msix_perm_setup(struct idxd_device *idxd); +void idxd_msix_perm_clear(struct idxd_device *idxd); irqreturn_t idxd_irq_handler(int vec, void *data); irqreturn_t idxd_misc_thread(int vec, void *data); irqreturn_t idxd_wq_thread(int irq, void *data); @@ -341,6 +343,7 @@ void idxd_wq_free_resources(struct idxd_wq *wq); int idxd_wq_enable(struct idxd_wq *wq); int idxd_wq_disable(struct idxd_wq *wq); void idxd_wq_drain(struct idxd_wq *wq); +void idxd_wq_reset(struct idxd_wq *wq); int idxd_wq_map_portal(struct idxd_wq *wq); void idxd_wq_unmap_portal(struct idxd_wq *wq); void idxd_wq_disable_cleanup(struct idxd_wq *wq); diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 085a0c3b62c6..6584b0ec07d5 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -65,7 +65,6 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) struct idxd_irq_entry *irq_entry; int i, msixcnt; int rc = 0; - union msix_perm mperm; msixcnt = pci_msix_vec_count(pdev); if (msixcnt < 0) { @@ -144,14 +143,7 @@ static int idxd_setup_interrupts(struct idxd_device *idxd) } idxd_unmask_error_interrupts(idxd); - - /* Setup MSIX permission table */ - mperm.bits = 0; - mperm.pasid = idxd->pasid; - mperm.pasid_en = device_pasid_enabled(idxd); - for (i = 1; i < msixcnt; i++) - iowrite32(mperm.bits, idxd->reg_base + idxd->msix_perm_offset + i * 8); - + idxd_msix_perm_setup(idxd); return 0; err_no_irq: @@ -510,6 +502,7 @@ static void idxd_shutdown(struct pci_dev *pdev) idxd_flush_work_list(irq_entry); } + idxd_msix_perm_clear(idxd); destroy_workqueue(idxd->wq); } diff --git a/drivers/dma/idxd/irq.c b/drivers/dma/idxd/irq.c index a60ca11a5784..f1463fc58112 100644 --- a/drivers/dma/idxd/irq.c +++ b/drivers/dma/idxd/irq.c @@ -124,7 +124,9 @@ static int process_misc_interrupts(struct idxd_device *idxd, u32 cause) for (i = 0; i < 4; i++) idxd->sw_err.bits[i] = ioread64(idxd->reg_base + IDXD_SWERR_OFFSET + i * sizeof(u64)); - iowrite64(IDXD_SWERR_ACK, idxd->reg_base + IDXD_SWERR_OFFSET); + + iowrite64(idxd->sw_err.bits[0] & IDXD_SWERR_ACK, + idxd->reg_base + IDXD_SWERR_OFFSET); if (idxd->sw_err.valid && idxd->sw_err.wq_idx_valid) { int id = idxd->sw_err.wq_idx; diff --git a/drivers/dma/idxd/sysfs.c b/drivers/dma/idxd/sysfs.c index 4dbb03c545e4..18bf4d148989 100644 --- a/drivers/dma/idxd/sysfs.c +++ b/drivers/dma/idxd/sysfs.c @@ -275,7 +275,6 @@ static void disable_wq(struct idxd_wq *wq) { struct idxd_device *idxd = wq->idxd; struct device *dev = &idxd->pdev->dev; - int rc; mutex_lock(&wq->wq_lock); dev_dbg(dev, "%s removing WQ %s\n", __func__, dev_name(&wq->conf_dev)); @@ -296,17 +295,13 @@ static void disable_wq(struct idxd_wq *wq) idxd_wq_unmap_portal(wq); idxd_wq_drain(wq); - rc = idxd_wq_disable(wq); + idxd_wq_reset(wq); idxd_wq_free_resources(wq); wq->client_count = 0; mutex_unlock(&wq->wq_lock); - if (rc < 0) - dev_warn(dev, "Failed to disable %s: %d\n", - dev_name(&wq->conf_dev), rc); - else - dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev)); + dev_info(dev, "wq %s disabled\n", dev_name(&wq->conf_dev)); } static int idxd_config_bus_remove(struct device *dev) @@ -989,7 +984,7 @@ static ssize_t wq_size_store(struct device *dev, if (!test_bit(IDXD_FLAG_CONFIGURABLE, &idxd->flags)) return -EPERM; - if (wq->state != IDXD_WQ_DISABLED) + if (idxd->state == IDXD_DEV_ENABLED) return -EPERM; if (size + total_claimed_wq_size(idxd) - wq->size > idxd->max_wq_size) @@ -1449,8 +1444,14 @@ static ssize_t op_cap_show(struct device *dev, { struct idxd_device *idxd = container_of(dev, struct idxd_device, conf_dev); + int i, rc = 0; + + for (i = 0; i < 4; i++) + rc += sysfs_emit_at(buf, rc, "%#llx ", idxd->hw.opcap.bits[i]); - return sprintf(buf, "%#llx\n", idxd->hw.opcap.bits[0]); + rc--; + rc += sysfs_emit_at(buf, rc, "\n"); + return rc; } static DEVICE_ATTR_RO(op_cap); diff --git a/drivers/dma/plx_dma.c b/drivers/dma/plx_dma.c index f387c5bbc170..166934544161 100644 --- a/drivers/dma/plx_dma.c +++ b/drivers/dma/plx_dma.c @@ -507,10 +507,8 @@ static int plx_dma_create(struct pci_dev *pdev) rc = request_irq(pci_irq_vector(pdev, 0), plx_dma_isr, 0, KBUILD_MODNAME, plxdev); - if (rc) { - kfree(plxdev); - return rc; - } + if (rc) + goto free_plx; spin_lock_init(&plxdev->ring_lock); tasklet_setup(&plxdev->desc_task, plx_dma_desc_task); @@ -540,14 +538,20 @@ static int plx_dma_create(struct pci_dev *pdev) rc = dma_async_device_register(dma); if (rc) { pci_err(pdev, "Failed to register dma device: %d\n", rc); - free_irq(pci_irq_vector(pdev, 0), plxdev); - kfree(plxdev); - return rc; + goto put_device; } pci_set_drvdata(pdev, plxdev); return 0; + +put_device: + put_device(&pdev->dev); + free_irq(pci_irq_vector(pdev, 0), plxdev); +free_plx: + kfree(plxdev); + + return rc; } static int plx_dma_probe(struct pci_dev *pdev, diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index 71827d9b0aa1..b7260749e8ee 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -723,7 +723,7 @@ static void tegra_dma_issue_pending(struct dma_chan *dc) goto end; } if (!tdc->busy) { - err = pm_runtime_get_sync(tdc->tdma->dev); + err = pm_runtime_resume_and_get(tdc->tdma->dev); if (err < 0) { dev_err(tdc2dev(tdc), "Failed to enable DMA\n"); goto end; @@ -818,7 +818,7 @@ static void tegra_dma_synchronize(struct dma_chan *dc) struct tegra_dma_channel *tdc = to_tegra_dma_chan(dc); int err; - err = pm_runtime_get_sync(tdc->tdma->dev); + err = pm_runtime_resume_and_get(tdc->tdma->dev); if (err < 0) { dev_err(tdc2dev(tdc), "Failed to synchronize DMA: %d\n", err); return; diff --git a/drivers/dma/xilinx/xilinx_dpdma.c b/drivers/dma/xilinx/xilinx_dpdma.c index 55df63dead8d..70b29bd079c9 100644 --- a/drivers/dma/xilinx/xilinx_dpdma.c +++ b/drivers/dma/xilinx/xilinx_dpdma.c @@ -839,6 +839,7 @@ static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan) struct xilinx_dpdma_tx_desc *desc; struct virt_dma_desc *vdesc; u32 reg, channels; + bool first_frame; lockdep_assert_held(&chan->lock); @@ -852,14 +853,6 @@ static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan) chan->running = true; } - if (chan->video_group) - channels = xilinx_dpdma_chan_video_group_ready(chan); - else - channels = BIT(chan->id); - - if (!channels) - return; - vdesc = vchan_next_desc(&chan->vchan); if (!vdesc) return; @@ -884,13 +877,26 @@ static void xilinx_dpdma_chan_queue_transfer(struct xilinx_dpdma_chan *chan) FIELD_PREP(XILINX_DPDMA_CH_DESC_START_ADDRE_MASK, upper_32_bits(sw_desc->dma_addr))); - if (chan->first_frame) + first_frame = chan->first_frame; + chan->first_frame = false; + + if (chan->video_group) { + channels = xilinx_dpdma_chan_video_group_ready(chan); + /* + * Trigger the transfer only when all channels in the group are + * ready. + */ + if (!channels) + return; + } else { + channels = BIT(chan->id); + } + + if (first_frame) reg = XILINX_DPDMA_GBL_TRIG_MASK(channels); else reg = XILINX_DPDMA_GBL_RETRIG_MASK(channels); - chan->first_frame = false; - dpdma_write(xdev->reg, XILINX_DPDMA_GBL, reg); } @@ -1042,13 +1048,14 @@ static int xilinx_dpdma_chan_stop(struct xilinx_dpdma_chan *chan) */ static void xilinx_dpdma_chan_done_irq(struct xilinx_dpdma_chan *chan) { - struct xilinx_dpdma_tx_desc *active = chan->desc.active; + struct xilinx_dpdma_tx_desc *active; unsigned long flags; spin_lock_irqsave(&chan->lock, flags); xilinx_dpdma_debugfs_desc_done_irq(chan); + active = chan->desc.active; if (active) vchan_cyclic_callback(&active->vdesc); else diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c index 0a6438cbb3f3..e7a9561a826d 100644 --- a/drivers/extcon/extcon.c +++ b/drivers/extcon/extcon.c @@ -1241,6 +1241,7 @@ int extcon_dev_register(struct extcon_dev *edev) sizeof(*edev->nh), GFP_KERNEL); if (!edev->nh) { ret = -ENOMEM; + device_unregister(&edev->dev); goto err_dev; } diff --git a/drivers/firewire/nosy.c b/drivers/firewire/nosy.c index 5fd6a60b6741..88ed971e32c0 100644 --- a/drivers/firewire/nosy.c +++ b/drivers/firewire/nosy.c @@ -346,6 +346,7 @@ nosy_ioctl(struct file *file, unsigned int cmd, unsigned long arg) struct client *client = file->private_data; spinlock_t *client_list_lock = &client->lynx->client_list_lock; struct nosy_stats stats; + int ret; switch (cmd) { case NOSY_IOC_GET_STATS: @@ -360,11 +361,15 @@ nosy_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return 0; case NOSY_IOC_START: + ret = -EBUSY; spin_lock_irq(client_list_lock); - list_add_tail(&client->link, &client->lynx->client_list); + if (list_empty(&client->link)) { + list_add_tail(&client->link, &client->lynx->client_list); + ret = 0; + } spin_unlock_irq(client_list_lock); - return 0; + return ret; case NOSY_IOC_STOP: spin_lock_irq(client_list_lock); diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index c23466e05e60..d0537573501e 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -13,7 +13,8 @@ cflags-$(CONFIG_X86) += -m$(BITS) -D__KERNEL__ \ -Wno-pointer-sign \ $(call cc-disable-warning, address-of-packed-member) \ $(call cc-disable-warning, gnu) \ - -fno-asynchronous-unwind-tables + -fno-asynchronous-unwind-tables \ + $(CLANG_FLAGS) # arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly # disable the stackleak plugin diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c index 50bb2a6d6ccf..62f0d1a5dd32 100644 --- a/drivers/firmware/turris-mox-rwtm.c +++ b/drivers/firmware/turris-mox-rwtm.c @@ -2,7 +2,7 @@ /* * Turris Mox rWTM firmware driver * - * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz> + * Copyright (C) 2019 Marek Behún <kabel@kernel.org> */ #include <linux/armada-37xx-rwtm-mailbox.h> @@ -547,4 +547,4 @@ module_platform_driver(turris_mox_rwtm_driver); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("Turris Mox rWTM firmware driver"); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); diff --git a/drivers/gpio/gpio-moxtet.c b/drivers/gpio/gpio-moxtet.c index 8299909318f4..61f9efd6c64f 100644 --- a/drivers/gpio/gpio-moxtet.c +++ b/drivers/gpio/gpio-moxtet.c @@ -2,7 +2,7 @@ /* * Turris Mox Moxtet GPIO expander * - * Copyright (C) 2018 Marek Behun <marek.behun@nic.cz> + * Copyright (C) 2018 Marek Behún <kabel@kernel.org> */ #include <linux/bitops.h> @@ -174,6 +174,6 @@ static struct moxtet_driver moxtet_gpio_driver = { }; module_moxtet_driver(moxtet_gpio_driver); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); MODULE_DESCRIPTION("Turris Mox Moxtet GPIO expander"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c index 41952bb818ad..56152263ab38 100644 --- a/drivers/gpio/gpio-omap.c +++ b/drivers/gpio/gpio-omap.c @@ -29,6 +29,7 @@ #define OMAP4_GPIO_DEBOUNCINGTIME_MASK 0xFF struct gpio_regs { + u32 sysconfig; u32 irqenable1; u32 irqenable2; u32 wake_en; @@ -1069,6 +1070,7 @@ static void omap_gpio_init_context(struct gpio_bank *p) const struct omap_gpio_reg_offs *regs = p->regs; void __iomem *base = p->base; + p->context.sysconfig = readl_relaxed(base + regs->sysconfig); p->context.ctrl = readl_relaxed(base + regs->ctrl); p->context.oe = readl_relaxed(base + regs->direction); p->context.wake_en = readl_relaxed(base + regs->wkup_en); @@ -1088,6 +1090,7 @@ static void omap_gpio_restore_context(struct gpio_bank *bank) const struct omap_gpio_reg_offs *regs = bank->regs; void __iomem *base = bank->base; + writel_relaxed(bank->context.sysconfig, base + regs->sysconfig); writel_relaxed(bank->context.wake_en, base + regs->wkup_en); writel_relaxed(bank->context.ctrl, base + regs->ctrl); writel_relaxed(bank->context.leveldetect0, base + regs->leveldetect0); @@ -1115,6 +1118,10 @@ static void omap_gpio_idle(struct gpio_bank *bank, bool may_lose_context) bank->saved_datain = readl_relaxed(base + bank->regs->datain); + /* Save syconfig, it's runtime value can be different from init value */ + if (bank->loses_context) + bank->context.sysconfig = readl_relaxed(base + bank->regs->sysconfig); + if (!bank->enabled_non_wakeup_gpios) goto update_gpio_context_count; @@ -1279,6 +1286,7 @@ out_unlock: static const struct omap_gpio_reg_offs omap2_gpio_regs = { .revision = OMAP24XX_GPIO_REVISION, + .sysconfig = OMAP24XX_GPIO_SYSCONFIG, .direction = OMAP24XX_GPIO_OE, .datain = OMAP24XX_GPIO_DATAIN, .dataout = OMAP24XX_GPIO_DATAOUT, @@ -1302,6 +1310,7 @@ static const struct omap_gpio_reg_offs omap2_gpio_regs = { static const struct omap_gpio_reg_offs omap4_gpio_regs = { .revision = OMAP4_GPIO_REVISION, + .sysconfig = OMAP4_GPIO_SYSCONFIG, .direction = OMAP4_GPIO_OE, .datain = OMAP4_GPIO_DATAIN, .dataout = OMAP4_GPIO_DATAOUT, diff --git a/drivers/gpio/gpiolib-sysfs.c b/drivers/gpio/gpiolib-sysfs.c index 26c5466b8179..ae49bb23c6ed 100644 --- a/drivers/gpio/gpiolib-sysfs.c +++ b/drivers/gpio/gpiolib-sysfs.c @@ -458,6 +458,8 @@ static ssize_t export_store(struct class *class, long gpio; struct gpio_desc *desc; int status; + struct gpio_chip *gc; + int offset; status = kstrtol(buf, 0, &gpio); if (status < 0) @@ -469,6 +471,12 @@ static ssize_t export_store(struct class *class, pr_warn("%s: invalid GPIO %ld\n", __func__, gpio); return -EINVAL; } + gc = desc->gdev->chip; + offset = gpio_chip_hwgpio(desc); + if (!gpiochip_line_is_valid(gc, offset)) { + pr_warn("%s: GPIO %ld masked\n", __func__, gpio); + return -EINVAL; + } /* No extra locking here; FLAG_SYSFS just signifies that the * request and export were done by on behalf of userspace, so diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 49267eb64302..29885febc0b0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1007,13 +1007,9 @@ struct amdgpu_device { /* s3/s4 mask */ bool in_suspend; - bool in_hibernate; - - /* - * The combination flag in_poweroff_reboot_com used to identify the poweroff - * and reboot opt in the s0i3 system-wide suspend. - */ - bool in_poweroff_reboot_com; + bool in_s3; + bool in_s4; + bool in_s0ix; atomic_t in_gpu_reset; enum pp_mp1_state mp1_state; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 6447cd6ca5a8..8a5a8ff5d362 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2371,6 +2371,10 @@ static int amdgpu_device_set_cg_state(struct amdgpu_device *adev, i = state == AMD_CG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + /* skip CG for GFX on S0ix */ + if (adev->in_s0ix && + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX) + continue; /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && @@ -2402,6 +2406,10 @@ static int amdgpu_device_set_pg_state(struct amdgpu_device *adev, enum amd_power i = state == AMD_PG_STATE_GATE ? j : adev->num_ip_blocks - j - 1; if (!adev->ip_blocks[i].status.late_initialized) continue; + /* skip PG for GFX on S0ix */ + if (adev->in_s0ix && + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX) + continue; /* skip CG for VCE/UVD, it's handled specially */ if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD && adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE && @@ -2678,11 +2686,8 @@ static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev) { int i, r; - if (adev->in_poweroff_reboot_com || - !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) { - amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); - amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); - } + amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE); + amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE); for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.valid) @@ -2722,6 +2727,9 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev) { int i, r; + if (adev->in_s0ix) + amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry); + for (i = adev->num_ip_blocks - 1; i >= 0; i--) { if (!adev->ip_blocks[i].status.valid) continue; @@ -2734,6 +2742,17 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev) adev->ip_blocks[i].status.hw = false; continue; } + + /* skip suspend of gfx and psp for S0ix + * gfx is in gfxoff state, so on resume it will exit gfxoff just + * like at runtime. PSP is also part of the always on hardware + * so no need to suspend it. + */ + if (adev->in_s0ix && + (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP || + adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_GFX)) + continue; + /* XXX handle errors */ r = adev->ip_blocks[i].version->funcs->suspend(adev); /* XXX handle errors */ @@ -3673,14 +3692,9 @@ void amdgpu_device_fini(struct amdgpu_device *adev) */ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) { - struct amdgpu_device *adev; - struct drm_crtc *crtc; - struct drm_connector *connector; - struct drm_connector_list_iter iter; + struct amdgpu_device *adev = drm_to_adev(dev); int r; - adev = drm_to_adev(dev); - if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; @@ -3692,61 +3706,19 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) cancel_delayed_work_sync(&adev->delayed_init_work); - if (!amdgpu_device_has_dc_support(adev)) { - /* turn off display hw */ - drm_modeset_lock_all(dev); - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) - drm_helper_connector_dpms(connector, - DRM_MODE_DPMS_OFF); - drm_connector_list_iter_end(&iter); - drm_modeset_unlock_all(dev); - /* unpin the front buffers and cursors */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - struct drm_framebuffer *fb = crtc->primary->fb; - struct amdgpu_bo *robj; - - if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { - struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - r = amdgpu_bo_reserve(aobj, true); - if (r == 0) { - amdgpu_bo_unpin(aobj); - amdgpu_bo_unreserve(aobj); - } - } - - if (fb == NULL || fb->obj[0] == NULL) { - continue; - } - robj = gem_to_amdgpu_bo(fb->obj[0]); - /* don't unpin kernel fb objects */ - if (!amdgpu_fbdev_robj_is_fb(adev, robj)) { - r = amdgpu_bo_reserve(robj, true); - if (r == 0) { - amdgpu_bo_unpin(robj); - amdgpu_bo_unreserve(robj); - } - } - } - } - amdgpu_ras_suspend(adev); r = amdgpu_device_ip_suspend_phase1(adev); - amdgpu_amdkfd_suspend(adev, adev->in_runpm); + if (!adev->in_s0ix) + amdgpu_amdkfd_suspend(adev, adev->in_runpm); /* evict vram memory */ amdgpu_bo_evict_vram(adev); amdgpu_fence_driver_suspend(adev); - if (adev->in_poweroff_reboot_com || - !amdgpu_acpi_is_s0ix_supported(adev) || amdgpu_in_reset(adev)) - r = amdgpu_device_ip_suspend_phase2(adev); - else - amdgpu_gfx_state_change_set(adev, sGpuChangeState_D3Entry); + r = amdgpu_device_ip_suspend_phase2(adev); /* evict remaining vram memory * This second call to evict vram is to evict the gart page table * using the CPU. @@ -3768,16 +3740,13 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon) */ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) { - struct drm_connector *connector; - struct drm_connector_list_iter iter; struct amdgpu_device *adev = drm_to_adev(dev); - struct drm_crtc *crtc; int r = 0; if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) return 0; - if (amdgpu_acpi_is_s0ix_supported(adev)) + if (adev->in_s0ix) amdgpu_gfx_state_change_set(adev, sGpuChangeState_D0Entry); /* post card */ @@ -3802,50 +3771,17 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon) queue_delayed_work(system_wq, &adev->delayed_init_work, msecs_to_jiffies(AMDGPU_RESUME_MS)); - if (!amdgpu_device_has_dc_support(adev)) { - /* pin cursors */ - list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { - struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); - - if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { - struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); - r = amdgpu_bo_reserve(aobj, true); - if (r == 0) { - r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); - if (r != 0) - dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r); - amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj); - amdgpu_bo_unreserve(aobj); - } - } - } + if (!adev->in_s0ix) { + r = amdgpu_amdkfd_resume(adev, adev->in_runpm); + if (r) + return r; } - r = amdgpu_amdkfd_resume(adev, adev->in_runpm); - if (r) - return r; /* Make sure IB tests flushed */ flush_delayed_work(&adev->delayed_init_work); - /* blat the mode back in */ - if (fbcon) { - if (!amdgpu_device_has_dc_support(adev)) { - /* pre DCE11 */ - drm_helper_resume_force_mode(dev); - - /* turn on display hw */ - drm_modeset_lock_all(dev); - - drm_connector_list_iter_begin(dev, &iter); - drm_for_each_connector_iter(connector, &iter) - drm_helper_connector_dpms(connector, - DRM_MODE_DPMS_ON); - drm_connector_list_iter_end(&iter); - - drm_modeset_unlock_all(dev); - } + if (fbcon) amdgpu_fbdev_set_suspend(adev, 0); - } drm_kms_helper_poll_enable(dev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 48cb33e5b382..f753e04fee99 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1310,3 +1310,92 @@ bool amdgpu_crtc_get_scanout_position(struct drm_crtc *crtc, return amdgpu_display_get_crtc_scanoutpos(dev, pipe, 0, vpos, hpos, stime, etime, mode); } + +int amdgpu_display_suspend_helper(struct amdgpu_device *adev) +{ + struct drm_device *dev = adev_to_drm(adev); + struct drm_crtc *crtc; + struct drm_connector *connector; + struct drm_connector_list_iter iter; + int r; + + /* turn off display hw */ + drm_modeset_lock_all(dev); + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) + drm_helper_connector_dpms(connector, + DRM_MODE_DPMS_OFF); + drm_connector_list_iter_end(&iter); + drm_modeset_unlock_all(dev); + /* unpin the front buffers and cursors */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + struct drm_framebuffer *fb = crtc->primary->fb; + struct amdgpu_bo *robj; + + if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + r = amdgpu_bo_reserve(aobj, true); + if (r == 0) { + amdgpu_bo_unpin(aobj); + amdgpu_bo_unreserve(aobj); + } + } + + if (fb == NULL || fb->obj[0] == NULL) { + continue; + } + robj = gem_to_amdgpu_bo(fb->obj[0]); + /* don't unpin kernel fb objects */ + if (!amdgpu_fbdev_robj_is_fb(adev, robj)) { + r = amdgpu_bo_reserve(robj, true); + if (r == 0) { + amdgpu_bo_unpin(robj); + amdgpu_bo_unreserve(robj); + } + } + } + return r; +} + +int amdgpu_display_resume_helper(struct amdgpu_device *adev) +{ + struct drm_device *dev = adev_to_drm(adev); + struct drm_connector *connector; + struct drm_connector_list_iter iter; + struct drm_crtc *crtc; + int r; + + /* pin cursors */ + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { + struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc); + + if (amdgpu_crtc->cursor_bo && !adev->enable_virtual_display) { + struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo); + r = amdgpu_bo_reserve(aobj, true); + if (r == 0) { + r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM); + if (r != 0) + dev_err(adev->dev, "Failed to pin cursor BO (%d)\n", r); + amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj); + amdgpu_bo_unreserve(aobj); + } + } + } + + drm_helper_resume_force_mode(dev); + + /* turn on display hw */ + drm_modeset_lock_all(dev); + + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) + drm_helper_connector_dpms(connector, + DRM_MODE_DPMS_ON); + drm_connector_list_iter_end(&iter); + + drm_modeset_unlock_all(dev); + + return 0; +} + diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h index dc7b7d116549..7b6d83e2b13c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.h @@ -47,4 +47,7 @@ amdgpu_display_user_framebuffer_create(struct drm_device *dev, const struct drm_format_info * amdgpu_lookup_format_info(u32 format, uint64_t modifier); +int amdgpu_display_suspend_helper(struct amdgpu_device *adev); +int amdgpu_display_resume_helper(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index b26e2fd1c538..e92e7dea71da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1107,6 +1107,7 @@ static const struct pci_device_id pciidlist[] = { {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, 0x73AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, /* Van Gogh */ @@ -1274,24 +1275,35 @@ amdgpu_pci_shutdown(struct pci_dev *pdev) */ if (!amdgpu_passthrough(adev)) adev->mp1_state = PP_MP1_STATE_UNLOAD; - adev->in_poweroff_reboot_com = true; amdgpu_device_ip_suspend(adev); - adev->in_poweroff_reboot_com = false; adev->mp1_state = PP_MP1_STATE_NONE; } static int amdgpu_pmops_suspend(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - return amdgpu_device_suspend(drm_dev, true); + if (amdgpu_acpi_is_s0ix_supported(adev)) + adev->in_s0ix = true; + adev->in_s3 = true; + r = amdgpu_device_suspend(drm_dev, true); + adev->in_s3 = false; + + return r; } static int amdgpu_pmops_resume(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); + struct amdgpu_device *adev = drm_to_adev(drm_dev); + int r; - return amdgpu_device_resume(drm_dev, true); + r = amdgpu_device_resume(drm_dev, true); + if (amdgpu_acpi_is_s0ix_supported(adev)) + adev->in_s0ix = false; + return r; } static int amdgpu_pmops_freeze(struct device *dev) @@ -1300,9 +1312,9 @@ static int amdgpu_pmops_freeze(struct device *dev) struct amdgpu_device *adev = drm_to_adev(drm_dev); int r; - adev->in_hibernate = true; + adev->in_s4 = true; r = amdgpu_device_suspend(drm_dev, true); - adev->in_hibernate = false; + adev->in_s4 = false; if (r) return r; return amdgpu_asic_reset(adev); @@ -1318,13 +1330,8 @@ static int amdgpu_pmops_thaw(struct device *dev) static int amdgpu_pmops_poweroff(struct device *dev) { struct drm_device *drm_dev = dev_get_drvdata(dev); - struct amdgpu_device *adev = drm_to_adev(drm_dev); - int r; - adev->in_poweroff_reboot_com = true; - r = amdgpu_device_suspend(drm_dev, true); - adev->in_poweroff_reboot_com = false; - return r; + return amdgpu_device_suspend(drm_dev, true); } static int amdgpu_pmops_restore(struct device *dev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 64beb3399604..a4e2cf7cada1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -778,9 +778,9 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) dev_info->high_va_offset = AMDGPU_GMC_HOLE_END; dev_info->high_va_max = AMDGPU_GMC_HOLE_END | vm_size; } - dev_info->virtual_address_alignment = max((int)PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE); + dev_info->virtual_address_alignment = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE); dev_info->pte_fragment_size = (1 << adev->vm_manager.fragment_size) * AMDGPU_GPU_PAGE_SIZE; - dev_info->gart_page_size = AMDGPU_GPU_PAGE_SIZE; + dev_info->gart_page_size = max_t(u32, PAGE_SIZE, AMDGPU_GPU_PAGE_SIZE); dev_info->cu_active_number = adev->gfx.cu_info.number; dev_info->cu_ao_mask = adev->gfx.cu_info.ao_cu_mask; dev_info->ce_ram_size = adev->gfx.ce_ram_size; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 4b29b8205442..072050429a2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -1028,13 +1028,10 @@ int amdgpu_bo_evict_vram(struct amdgpu_device *adev) { struct ttm_resource_manager *man; - /* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */ -#ifndef CONFIG_HIBERNATION - if (adev->flags & AMD_IS_APU) { - /* Useless to evict on IGP chips */ + if (adev->in_s3 && (adev->flags & AMD_IS_APU)) { + /* No need to evict vram on APUs for suspend to ram */ return 0; } -#endif man = ttm_manager_type(&adev->mman.bdev, TTM_PL_VRAM); return ttm_resource_manager_evict_all(&adev->mman.bdev, man); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 9fd2157b133a..5efa331e3ee8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -906,7 +906,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, /* Allocate an SG array and squash pages into it */ r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0, - ttm->num_pages << PAGE_SHIFT, + (u64)ttm->num_pages << PAGE_SHIFT, GFP_KERNEL); if (r) goto release_sg; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index ad91c0c3c423..326dae31b675 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2197,8 +2197,8 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev, uint64_t eaddr; /* validate the parameters */ - if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK || - size == 0 || size & AMDGPU_GPU_PAGE_MASK) + if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || + size == 0 || size & ~PAGE_MASK) return -EINVAL; /* make sure object fit at this offset */ @@ -2263,8 +2263,8 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev, int r; /* validate the parameters */ - if (saddr & AMDGPU_GPU_PAGE_MASK || offset & AMDGPU_GPU_PAGE_MASK || - size == 0 || size & AMDGPU_GPU_PAGE_MASK) + if (saddr & ~PAGE_MASK || offset & ~PAGE_MASK || + size == 0 || size & ~PAGE_MASK) return -EINVAL; /* make sure object fit at this offset */ @@ -2409,7 +2409,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev, after->start = eaddr + 1; after->last = tmp->last; after->offset = tmp->offset; - after->offset += after->start - tmp->start; + after->offset += (after->start - tmp->start) << PAGE_SHIFT; after->flags = tmp->flags; after->bo_va = tmp->bo_va; list_add(&after->list, &tmp->bo_va->invalids); @@ -3300,7 +3300,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, struct amdgpu_bo *root; uint64_t value, flags; struct amdgpu_vm *vm; - long r; + int r; spin_lock(&adev->vm_manager.pasid_lock); vm = idr_find(&adev->vm_manager.pasid_idr, pasid); @@ -3349,6 +3349,12 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, value = 0; } + r = dma_resv_reserve_shared(root->tbo.base.resv, 1); + if (r) { + pr_debug("failed %d to reserve fence slot\n", r); + goto error_unlock; + } + r = amdgpu_vm_bo_update_mapping(adev, adev, vm, true, false, NULL, addr, addr, flags, value, NULL, NULL, NULL); @@ -3360,7 +3366,7 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, error_unlock: amdgpu_bo_unreserve(root); if (r < 0) - DRM_ERROR("Can't handle page fault (%ld)\n", r); + DRM_ERROR("Can't handle page fault (%d)\n", r); error_unref: amdgpu_bo_unref(&root); diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index 7944781e1086..19abb740a169 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -2897,6 +2897,11 @@ static int dce_v10_0_hw_fini(void *handle) static int dce_v10_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -2921,8 +2926,10 @@ static int dce_v10_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v10_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 1b6ff0470011..320ec35bfd37 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -3027,6 +3027,11 @@ static int dce_v11_0_hw_fini(void *handle) static int dce_v11_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -3051,8 +3056,10 @@ static int dce_v11_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v11_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 83a88385b762..13322000ebd6 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -2770,7 +2770,11 @@ static int dce_v6_0_hw_fini(void *handle) static int dce_v6_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -2794,8 +2798,10 @@ static int dce_v6_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v6_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index 224b30214427..04ebf02e5b8c 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -2796,6 +2796,11 @@ static int dce_v8_0_hw_fini(void *handle) static int dce_v8_0_suspend(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; adev->mode_info.bl_level = amdgpu_atombios_encoder_get_backlight_level_from_reg(adev); @@ -2820,8 +2825,10 @@ static int dce_v8_0_resume(void *handle) amdgpu_display_backlight_set_level(adev, adev->mode_info.bl_encoder, bl_level); } + if (ret) + return ret; - return ret; + return amdgpu_display_resume_helper(adev); } static bool dce_v8_0_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index 9810af712cc0..5c11144da051 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -39,6 +39,7 @@ #include "dce_v11_0.h" #include "dce_virtual.h" #include "ivsrcid/ivsrcid_vislands30.h" +#include "amdgpu_display.h" #define DCE_VIRTUAL_VBLANK_PERIOD 16666666 @@ -491,12 +492,24 @@ static int dce_virtual_hw_fini(void *handle) static int dce_virtual_suspend(void *handle) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = amdgpu_display_suspend_helper(adev); + if (r) + return r; return dce_virtual_hw_fini(handle); } static int dce_virtual_resume(void *handle) { - return dce_virtual_hw_init(handle); + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int r; + + r = dce_virtual_hw_init(handle); + if (r) + return r; + return amdgpu_display_resume_helper(adev); } static bool dce_virtual_is_idle(void *handle) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 45d1172b7bff..63691deb7df3 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3280,7 +3280,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_4[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_GCR_CNTL, 0x0007ffff, 0x0000c000), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG3, 0x00000280, 0x00000280), SOC15_REG_GOLDEN_VALUE(GC, 0, mmDB_DEBUG4, 0x07800000, 0x00800000), - SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL, 0x00001d00, 0x00000500), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmGCR_GENERAL_CNTL_Sienna_Cichlid, 0x00001d00, 0x00000500), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGE_PC_CNTL, 0x003c0000, 0x00280400), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2A_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf), diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c index b258a3dae767..159add0f5aaa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c @@ -155,7 +155,7 @@ static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev, /* Wait till CP writes sync code: */ status = amdkfd_fence_wait_timeout( - (unsigned int *) rm_state, + rm_state, QUEUESTATE__ACTIVE, 1500); kfd_gtt_sa_free(dbgdev->dev, mem_obj); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index e686ce2bf3b3..4598a9a58125 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1167,7 +1167,7 @@ static int start_cpsch(struct device_queue_manager *dqm) if (retval) goto fail_allocate_vidmem; - dqm->fence_addr = dqm->fence_mem->cpu_ptr; + dqm->fence_addr = (uint64_t *)dqm->fence_mem->cpu_ptr; dqm->fence_gpu_addr = dqm->fence_mem->gpu_addr; init_interrupts(dqm); @@ -1340,8 +1340,8 @@ out: return retval; } -int amdkfd_fence_wait_timeout(unsigned int *fence_addr, - unsigned int fence_value, +int amdkfd_fence_wait_timeout(uint64_t *fence_addr, + uint64_t fence_value, unsigned int timeout_ms) { unsigned long end_jiffies = msecs_to_jiffies(timeout_ms) + jiffies; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h index 7351dd195274..45f815946554 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h @@ -192,7 +192,7 @@ struct device_queue_manager { uint16_t vmid_pasid[VMID_NUM]; uint64_t pipelines_addr; uint64_t fence_gpu_addr; - unsigned int *fence_addr; + uint64_t *fence_addr; struct kfd_mem_obj *fence_mem; bool active_runlist; int sched_policy; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c index 5d541e0cc8ca..f71a7fa6680c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c @@ -347,7 +347,7 @@ fail_create_runlist_ib: } int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address, - uint32_t fence_value) + uint64_t fence_value) { uint32_t *buffer, size; int retval = 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c index dfaf771a42e6..e3ba0cd3b6fa 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c @@ -283,7 +283,7 @@ static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer, } static int pm_query_status_v9(struct packet_manager *pm, uint32_t *buffer, - uint64_t fence_address, uint32_t fence_value) + uint64_t fence_address, uint64_t fence_value) { struct pm4_mes_query_status *packet; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c index a852e0d7d804..08442e7d9944 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_vi.c @@ -263,7 +263,7 @@ static int pm_unmap_queues_vi(struct packet_manager *pm, uint32_t *buffer, } static int pm_query_status_vi(struct packet_manager *pm, uint32_t *buffer, - uint64_t fence_address, uint32_t fence_value) + uint64_t fence_address, uint64_t fence_value) { struct pm4_mes_query_status *packet; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 09599efa41fc..f304d1f8df5f 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -1003,8 +1003,8 @@ int pqm_get_wave_state(struct process_queue_manager *pqm, u32 *ctl_stack_used_size, u32 *save_area_used_size); -int amdkfd_fence_wait_timeout(unsigned int *fence_addr, - unsigned int fence_value, +int amdkfd_fence_wait_timeout(uint64_t *fence_addr, + uint64_t fence_value, unsigned int timeout_ms); /* Packet Manager */ @@ -1040,7 +1040,7 @@ struct packet_manager_funcs { uint32_t filter_param, bool reset, unsigned int sdma_engine); int (*query_status)(struct packet_manager *pm, uint32_t *buffer, - uint64_t fence_address, uint32_t fence_value); + uint64_t fence_address, uint64_t fence_value); int (*release_mem)(uint64_t gpu_addr, uint32_t *buffer); /* Packet sizes */ @@ -1062,7 +1062,7 @@ int pm_send_set_resources(struct packet_manager *pm, struct scheduling_resources *res); int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues); int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address, - uint32_t fence_value); + uint64_t fence_value); int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type, enum kfd_unmap_queues_filter mode, 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 573cf17262da..d699a5cf6c11 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4072,13 +4072,6 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane, return true; /* - * The arbitrary tiling support for multiplane formats has not been hooked - * up. - */ - if (info->num_planes > 1) - return false; - - /* * For D swizzle the canonical modifier depends on the bpp, so check * it here. */ @@ -4096,6 +4089,10 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane, /* Per radeonsi comments 16/64 bpp are more complicated. */ if (info->cpp[0] != 4) return false; + /* We support multi-planar formats, but not when combined with + * additional DCC metadata planes. */ + if (info->num_planes > 1) + return false; } return true; @@ -4296,7 +4293,7 @@ add_gfx10_3_modifiers(const struct amdgpu_device *adev, AMD_FMT_MOD_SET(DCC_CONSTANT_ENCODE, 1) | AMD_FMT_MOD_SET(DCC_INDEPENDENT_64B, 1) | AMD_FMT_MOD_SET(DCC_INDEPENDENT_128B, 1) | - AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_128B)); + AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_64B)); add_modifier(mods, size, capacity, AMD_FMT_MOD | AMD_FMT_MOD_SET(TILE, AMD_FMT_MOD_TILE_GFX9_64K_R_X) | @@ -4308,7 +4305,7 @@ add_gfx10_3_modifiers(const struct amdgpu_device *adev, AMD_FMT_MOD_SET(DCC_CONSTANT_ENCODE, 1) | AMD_FMT_MOD_SET(DCC_INDEPENDENT_64B, 1) | AMD_FMT_MOD_SET(DCC_INDEPENDENT_128B, 1) | - AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_128B)); + AMD_FMT_MOD_SET(DCC_MAX_COMPRESSED_BLOCK, AMD_FMT_MOD_DCC_BLOCK_64B)); add_modifier(mods, size, capacity, AMD_FMT_MOD | AMD_FMT_MOD_SET(TILE, AMD_FMT_MOD_TILE_GFX9_64K_R_X) | diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c index fa013496e26b..2f9bfaeaba8d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.c @@ -341,8 +341,7 @@ void enc2_hw_init(struct link_encoder *enc) } else { AUX_REG_WRITE(AUX_DPHY_RX_CONTROL0, 0x103d1110); - AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c4d); - + AUX_REG_WRITE(AUX_DPHY_TX_CONTROL, 0x21c7a); } //AUX_DPHY_TX_REF_CONTROL'AUX_TX_REF_DIV HW default is 0x32; diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h index 705fbfc37502..8a32772d4e91 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h @@ -134,6 +134,7 @@ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_EN, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK, mask_sh),\ HUBP_SF(HUBPREQ0_DCSURF_SURFACE_CONTROL, SECONDARY_SURFACE_DCC_IND_BLK_C, mask_sh),\ + HUBP_SF(HUBPREQ0_DCSURF_SURFACE_FLIP_INTERRUPT, SURFACE_FLIP_INT_MASK, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, DET_BUF_PLANE1_BASE_ADDRESS, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CB_B, mask_sh),\ HUBP_SF(HUBPRET0_HUBPRET_CONTROL, CROSSBAR_SRC_CR_R, mask_sh),\ diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index a2681fe875ed..c0565a932a12 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -587,6 +587,48 @@ static int smu7_force_switch_to_arbf0(struct pp_hwmgr *hwmgr) tmp, MC_CG_ARB_FREQ_F0); } +static uint16_t smu7_override_pcie_speed(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + uint16_t pcie_gen = 0; + + if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4 && + adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4) + pcie_gen = 3; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3 && + adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3) + pcie_gen = 2; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 && + adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2) + pcie_gen = 1; + else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 && + adev->pm.pcie_gen_mask & CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1) + pcie_gen = 0; + + return pcie_gen; +} + +static uint16_t smu7_override_pcie_width(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev); + uint16_t pcie_width = 0; + + if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16) + pcie_width = 16; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12) + pcie_width = 12; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8) + pcie_width = 8; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4) + pcie_width = 4; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2) + pcie_width = 2; + else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1) + pcie_width = 1; + + return pcie_width; +} + static int smu7_setup_default_pcie_table(struct pp_hwmgr *hwmgr) { struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend); @@ -683,6 +725,11 @@ static int smu7_setup_default_pcie_table(struct pp_hwmgr *hwmgr) PP_Min_PCIEGen), get_pcie_lane_support(data->pcie_lane_cap, PP_Max_PCIELane)); + + if (data->pcie_dpm_key_disabled) + phm_setup_pcie_table_entry(&data->dpm_table.pcie_speed_table, + data->dpm_table.pcie_speed_table.count, + smu7_override_pcie_speed(hwmgr), smu7_override_pcie_width(hwmgr)); } return 0; } @@ -1177,7 +1224,8 @@ static int smu7_enable_sclk_mclk_dpm(struct pp_hwmgr *hwmgr) (hwmgr->chip_id == CHIP_POLARIS10) || (hwmgr->chip_id == CHIP_POLARIS11) || (hwmgr->chip_id == CHIP_POLARIS12) || - (hwmgr->chip_id == CHIP_TONGA)) + (hwmgr->chip_id == CHIP_TONGA) || + (hwmgr->chip_id == CHIP_TOPAZ)) PHM_WRITE_FIELD(hwmgr->device, MC_SEQ_CNTL_3, CAC_EN, 0x1); @@ -1248,6 +1296,13 @@ static int smu7_start_dpm(struct pp_hwmgr *hwmgr) NULL)), "Failed to enable pcie DPM during DPM Start Function!", return -EINVAL); + } else { + PP_ASSERT_WITH_CODE( + (0 == smum_send_msg_to_smc(hwmgr, + PPSMC_MSG_PCIeDPM_Disable, + NULL)), + "Failed to disble pcie DPM during DPM Start Function!", + return -EINVAL); } if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, @@ -3276,7 +3331,8 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, disable_mclk_switching_for_display = ((1 < hwmgr->display_config->num_display) && !hwmgr->display_config->multi_monitor_in_sync) || - smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time); + (hwmgr->display_config->num_display && + smu7_vblank_too_short(hwmgr, hwmgr->display_config->min_vblank_time)); disable_mclk_switching = disable_mclk_switching_for_frame_lock || disable_mclk_switching_for_display; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index 22b636e2b89b..599ec9726601 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -54,6 +54,9 @@ #include "smuio/smuio_9_0_offset.h" #include "smuio/smuio_9_0_sh_mask.h" +#define smnPCIE_LC_SPEED_CNTL 0x11140290 +#define smnPCIE_LC_LINK_WIDTH_CNTL 0x11140288 + #define HBM_MEMORY_CHANNEL_WIDTH 128 static const uint32_t channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2}; @@ -443,8 +446,7 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) if (PP_CAP(PHM_PlatformCaps_VCEDPM)) data->smu_features[GNLD_DPM_VCE].supported = true; - if (!data->registry_data.pcie_dpm_key_disabled) - data->smu_features[GNLD_DPM_LINK].supported = true; + data->smu_features[GNLD_DPM_LINK].supported = true; if (!data->registry_data.dcefclk_dpm_key_disabled) data->smu_features[GNLD_DPM_DCEFCLK].supported = true; @@ -1544,6 +1546,13 @@ static int vega10_override_pcie_parameters(struct pp_hwmgr *hwmgr) pp_table->PcieLaneCount[i] = pcie_width; } + if (data->registry_data.pcie_dpm_key_disabled) { + for (i = 0; i < NUM_LINK_LEVELS; i++) { + pp_table->PcieGenSpeed[i] = pcie_gen; + pp_table->PcieLaneCount[i] = pcie_width; + } + } + return 0; } @@ -2966,6 +2975,14 @@ static int vega10_start_dpm(struct pp_hwmgr *hwmgr, uint32_t bitmap) } } + if (data->registry_data.pcie_dpm_key_disabled) { + PP_ASSERT_WITH_CODE(!vega10_enable_smc_features(hwmgr, + false, data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap), + "Attempt to Disable Link DPM feature Failed!", return -EINVAL); + data->smu_features[GNLD_DPM_LINK].enabled = false; + data->smu_features[GNLD_DPM_LINK].supported = false; + } + return 0; } @@ -4584,6 +4601,24 @@ static int vega10_set_ppfeature_status(struct pp_hwmgr *hwmgr, uint64_t new_ppfe return 0; } +static int vega10_get_current_pcie_link_width_level(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = hwmgr->adev; + + return (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) & + PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK) + >> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT; +} + +static int vega10_get_current_pcie_link_speed_level(struct pp_hwmgr *hwmgr) +{ + struct amdgpu_device *adev = hwmgr->adev; + + return (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) & + PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK) + >> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT; +} + static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, enum pp_clock_type type, char *buf) { @@ -4592,8 +4627,9 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table); struct vega10_single_dpm_table *soc_table = &(data->dpm_table.soc_table); struct vega10_single_dpm_table *dcef_table = &(data->dpm_table.dcef_table); - struct vega10_pcie_table *pcie_table = &(data->dpm_table.pcie_table); struct vega10_odn_clock_voltage_dependency_table *podn_vdd_dep = NULL; + uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width; + PPTable_t *pptable = &(data->smc_state_table.pp_table); int i, now, size = 0, count = 0; @@ -4650,15 +4686,31 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, "*" : ""); break; case PP_PCIE: - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentLinkIndex, &now); - - for (i = 0; i < pcie_table->count; i++) - size += sprintf(buf + size, "%d: %s %s\n", i, - (pcie_table->pcie_gen[i] == 0) ? "2.5GT/s, x1" : - (pcie_table->pcie_gen[i] == 1) ? "5.0GT/s, x16" : - (pcie_table->pcie_gen[i] == 2) ? "8.0GT/s, x16" : "", - (i == now) ? "*" : ""); + current_gen_speed = + vega10_get_current_pcie_link_speed_level(hwmgr); + current_lane_width = + vega10_get_current_pcie_link_width_level(hwmgr); + for (i = 0; i < NUM_LINK_LEVELS; i++) { + gen_speed = pptable->PcieGenSpeed[i]; + lane_width = pptable->PcieLaneCount[i]; + + size += sprintf(buf + size, "%d: %s %s %s\n", i, + (gen_speed == 0) ? "2.5GT/s," : + (gen_speed == 1) ? "5.0GT/s," : + (gen_speed == 2) ? "8.0GT/s," : + (gen_speed == 3) ? "16.0GT/s," : "", + (lane_width == 1) ? "x1" : + (lane_width == 2) ? "x2" : + (lane_width == 3) ? "x4" : + (lane_width == 4) ? "x8" : + (lane_width == 5) ? "x12" : + (lane_width == 6) ? "x16" : "", + (current_gen_speed == gen_speed) && + (current_lane_width == lane_width) ? + "*" : ""); + } break; + case OD_SCLK: if (hwmgr->od_enabled) { size = sprintf(buf, "%s:\n", "OD_SCLK"); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index 43e01d880f7c..4f6da11e8f10 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -133,6 +133,7 @@ static void vega12_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.auto_wattman_debug = 0; data->registry_data.auto_wattman_sample_period = 100; data->registry_data.auto_wattman_threshold = 50; + data->registry_data.pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK); } static int vega12_set_features_platform_caps(struct pp_hwmgr *hwmgr) @@ -539,6 +540,29 @@ static int vega12_override_pcie_parameters(struct pp_hwmgr *hwmgr) pp_table->PcieLaneCount[i] = pcie_width_arg; } + /* override to the highest if it's disabled from ppfeaturmask */ + if (data->registry_data.pcie_dpm_key_disabled) { + for (i = 0; i < NUM_LINK_LEVELS; i++) { + smu_pcie_arg = (i << 16) | (pcie_gen << 8) | pcie_width; + ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, + NULL); + PP_ASSERT_WITH_CODE(!ret, + "[OverridePcieParameters] Attempt to override pcie params failed!", + return ret); + + pp_table->PcieGenSpeed[i] = pcie_gen; + pp_table->PcieLaneCount[i] = pcie_width; + } + ret = vega12_enable_smc_features(hwmgr, + false, + data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap); + PP_ASSERT_WITH_CODE(!ret, + "Attempt to Disable DPM LINK Failed!", + return ret); + data->smu_features[GNLD_DPM_LINK].enabled = false; + data->smu_features[GNLD_DPM_LINK].supported = false; + } return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index f19964c69a00..b6ee3a285c9d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -171,6 +171,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.gfxoff_controlled_by_driver = 1; data->gfxoff_allowed = false; data->counter_gfxoff = 0; + data->registry_data.pcie_dpm_key_disabled = !(hwmgr->feature_mask & PP_PCIE_DPM_MASK); } static int vega20_set_features_platform_caps(struct pp_hwmgr *hwmgr) @@ -884,6 +885,30 @@ static int vega20_override_pcie_parameters(struct pp_hwmgr *hwmgr) pp_table->PcieLaneCount[i] = pcie_width_arg; } + /* override to the highest if it's disabled from ppfeaturmask */ + if (data->registry_data.pcie_dpm_key_disabled) { + for (i = 0; i < NUM_LINK_LEVELS; i++) { + smu_pcie_arg = (i << 16) | (pcie_gen << 8) | pcie_width; + ret = smum_send_msg_to_smc_with_parameter(hwmgr, + PPSMC_MSG_OverridePcieParameters, smu_pcie_arg, + NULL); + PP_ASSERT_WITH_CODE(!ret, + "[OverridePcieParameters] Attempt to override pcie params failed!", + return ret); + + pp_table->PcieGenSpeed[i] = pcie_gen; + pp_table->PcieLaneCount[i] = pcie_width; + } + ret = vega20_enable_smc_features(hwmgr, + false, + data->smu_features[GNLD_DPM_LINK].smu_feature_bitmap); + PP_ASSERT_WITH_CODE(!ret, + "Attempt to Disable DPM LINK Failed!", + return ret); + data->smu_features[GNLD_DPM_LINK].enabled = false; + data->smu_features[GNLD_DPM_LINK].supported = false; + } + return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index d143ef1b460b..cd905e41080e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1294,7 +1294,7 @@ static int smu_disable_dpms(struct smu_context *smu) bool use_baco = !smu->is_apu && ((amdgpu_in_reset(adev) && (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) || - ((adev->in_runpm || adev->in_hibernate) && amdgpu_asic_supports_baco(adev))); + ((adev->in_runpm || adev->in_s4) && amdgpu_asic_supports_baco(adev))); /* * For custom pptable uploading, skip the DPM features @@ -1431,7 +1431,8 @@ static int smu_suspend(void *handle) smu->watermarks_bitmap &= ~(WATERMARKS_LOADED); - if (smu->is_apu) + /* skip CGPG when in S0ix */ + if (smu->is_apu && !adev->in_s0ix) smu_set_gfx_cgpg(&adev->smu, false); return 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 7ddbaecb11c2..101eaa20db9b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -384,10 +384,15 @@ static int vangogh_dpm_set_jpeg_enable(struct smu_context *smu, bool enable) static bool vangogh_is_dpm_running(struct smu_context *smu) { + struct amdgpu_device *adev = smu->adev; int ret = 0; uint32_t feature_mask[2]; uint64_t feature_enabled; + /* we need to re-init after suspend so return false */ + if (adev->in_suspend) + return false; + ret = smu_cmn_get_enabled_32_bits_mask(smu, feature_mask, 2); if (ret) diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 6d38c5c17f23..db69f19ab5bc 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -689,7 +689,8 @@ static int etnaviv_gem_userptr_get_pages(struct etnaviv_gem_object *etnaviv_obj) struct page **pages = pvec + pinned; ret = pin_user_pages_fast(ptr, num_pages, - !userptr->ro ? FOLL_WRITE : 0, pages); + FOLL_WRITE | FOLL_FORCE | FOLL_LONGTERM, + pages); if (ret < 0) { unpin_user_pages(pvec, pinned); kvfree(pvec); diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 1f79bc2a881e..1510e4e2973c 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -13,7 +13,6 @@ #include <linux/irq.h> #include <linux/mfd/syscon.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/regmap.h> diff --git a/drivers/gpu/drm/i915/display/intel_acpi.c b/drivers/gpu/drm/i915/display/intel_acpi.c index e21fb14d5e07..833d0c1be4f1 100644 --- a/drivers/gpu/drm/i915/display/intel_acpi.c +++ b/drivers/gpu/drm/i915/display/intel_acpi.c @@ -84,13 +84,31 @@ static void intel_dsm_platform_mux_info(acpi_handle dhandle) return; } + if (!pkg->package.count) { + DRM_DEBUG_DRIVER("no connection in _DSM\n"); + return; + } + connector_count = &pkg->package.elements[0]; DRM_DEBUG_DRIVER("MUX info connectors: %lld\n", (unsigned long long)connector_count->integer.value); for (i = 1; i < pkg->package.count; i++) { union acpi_object *obj = &pkg->package.elements[i]; - union acpi_object *connector_id = &obj->package.elements[0]; - union acpi_object *info = &obj->package.elements[1]; + union acpi_object *connector_id; + union acpi_object *info; + + if (obj->type != ACPI_TYPE_PACKAGE || obj->package.count < 2) { + DRM_DEBUG_DRIVER("Invalid object for MUX #%d\n", i); + continue; + } + + connector_id = &obj->package.elements[0]; + info = &obj->package.elements[1]; + if (info->type != ACPI_TYPE_BUFFER || info->buffer.length < 4) { + DRM_DEBUG_DRIVER("Invalid info for MUX obj #%d\n", i); + continue; + } + DRM_DEBUG_DRIVER("Connector id: 0x%016llx\n", (unsigned long long)connector_id->integer.value); DRM_DEBUG_DRIVER(" port id: %s\n", diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index 4683f98f7e54..c3f2962aa1eb 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -317,12 +317,13 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_ if (!new_plane_state->hw.crtc && !old_plane_state->hw.crtc) return 0; - new_crtc_state->enabled_planes |= BIT(plane->id); - ret = plane->check_plane(new_crtc_state, new_plane_state); if (ret) return ret; + if (fb) + new_crtc_state->enabled_planes |= BIT(plane->id); + /* FIXME pre-g4x don't work like this */ if (new_plane_state->uapi.visible) new_crtc_state->active_planes |= BIT(plane->id); diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 8c12d5375607..775d89b6c3fc 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -3619,9 +3619,7 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp) { int ret; - intel_dp_lttpr_init(intel_dp); - - if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) + if (intel_dp_init_lttpr_and_dprx_caps(intel_dp) < 0) return false; /* diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c index eaebf123310a..10fe17b7280d 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c @@ -133,6 +133,7 @@ static u32 g4x_get_aux_send_ctl(struct intel_dp *intel_dp, else precharge = 5; + /* Max timeout value on G4x-BDW: 1.6ms */ if (IS_BROADWELL(dev_priv)) timeout = DP_AUX_CH_CTL_TIME_OUT_600us; else @@ -159,6 +160,12 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, enum phy phy = intel_port_to_phy(i915, dig_port->base.port); u32 ret; + /* + * Max timeout values: + * SKL-GLK: 1.6ms + * CNL: 3.2ms + * ICL+: 4ms + */ ret = DP_AUX_CH_CTL_SEND_BUSY | DP_AUX_CH_CTL_DONE | DP_AUX_CH_CTL_INTERRUPT | diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index 651884390137..4f8337c7fd2e 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -646,7 +646,6 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *connector) break; case INTEL_BACKLIGHT_DISPLAY_DDI: try_intel_interface = true; - try_vesa_interface = true; break; default: return -ENODEV; diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 892d7db7d94f..2ed309534e97 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -34,6 +34,11 @@ intel_dp_dump_link_status(const u8 link_status[DP_LINK_STATUS_SIZE]) link_status[3], link_status[4], link_status[5]); } +static void intel_dp_reset_lttpr_common_caps(struct intel_dp *intel_dp) +{ + memset(&intel_dp->lttpr_common_caps, 0, sizeof(intel_dp->lttpr_common_caps)); +} + static void intel_dp_reset_lttpr_count(struct intel_dp *intel_dp) { intel_dp->lttpr_common_caps[DP_PHY_REPEATER_CNT - @@ -81,19 +86,36 @@ static void intel_dp_read_lttpr_phy_caps(struct intel_dp *intel_dp, static bool intel_dp_read_lttpr_common_caps(struct intel_dp *intel_dp) { - if (drm_dp_read_lttpr_common_caps(&intel_dp->aux, - intel_dp->lttpr_common_caps) < 0) { - memset(intel_dp->lttpr_common_caps, 0, - sizeof(intel_dp->lttpr_common_caps)); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + + if (intel_dp_is_edp(intel_dp)) return false; - } + + /* + * Detecting LTTPRs must be avoided on platforms with an AUX timeout + * period < 3.2ms. (see DP Standard v2.0, 2.11.2, 3.6.6.1). + */ + if (INTEL_GEN(i915) < 10) + return false; + + if (drm_dp_read_lttpr_common_caps(&intel_dp->aux, + intel_dp->lttpr_common_caps) < 0) + goto reset_caps; drm_dbg_kms(&dp_to_i915(intel_dp)->drm, "LTTPR common capabilities: %*ph\n", (int)sizeof(intel_dp->lttpr_common_caps), intel_dp->lttpr_common_caps); + /* The minimum value of LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV is 1.4 */ + if (intel_dp->lttpr_common_caps[0] < 0x14) + goto reset_caps; + return true; + +reset_caps: + intel_dp_reset_lttpr_common_caps(intel_dp); + return false; } static bool @@ -106,33 +128,49 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable) } /** - * intel_dp_lttpr_init - detect LTTPRs and init the LTTPR link training mode + * intel_dp_init_lttpr_and_dprx_caps - detect LTTPR and DPRX caps, init the LTTPR link training mode * @intel_dp: Intel DP struct * - * Read the LTTPR common capabilities, switch to non-transparent link training - * mode if any is detected and read the PHY capabilities for all detected - * LTTPRs. In case of an LTTPR detection error or if the number of + * Read the LTTPR common and DPRX capabilities and switch to non-transparent + * link training mode if any is detected and read the PHY capabilities for all + * detected LTTPRs. In case of an LTTPR detection error or if the number of * LTTPRs is more than is supported (8), fall back to the no-LTTPR, * transparent mode link training mode. * * Returns: - * >0 if LTTPRs were detected and the non-transparent LT mode was set + * >0 if LTTPRs were detected and the non-transparent LT mode was set. The + * DPRX capabilities are read out. * 0 if no LTTPRs or more than 8 LTTPRs were detected or in case of a - * detection failure and the transparent LT mode was set + * detection failure and the transparent LT mode was set. The DPRX + * capabilities are read out. + * <0 Reading out the DPRX capabilities failed. */ -int intel_dp_lttpr_init(struct intel_dp *intel_dp) +int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp) { int lttpr_count; bool ret; int i; - if (intel_dp_is_edp(intel_dp)) - return 0; - ret = intel_dp_read_lttpr_common_caps(intel_dp); + + /* The DPTX shall read the DPRX caps after LTTPR detection. */ + if (drm_dp_read_dpcd_caps(&intel_dp->aux, intel_dp->dpcd)) { + intel_dp_reset_lttpr_common_caps(intel_dp); + return -EIO; + } + if (!ret) return 0; + /* + * The 0xF0000-0xF02FF range is only valid if the DPCD revision is + * at least 1.4. + */ + if (intel_dp->dpcd[DP_DPCD_REV] < 0x14) { + intel_dp_reset_lttpr_common_caps(intel_dp); + return 0; + } + lttpr_count = drm_dp_lttpr_count(intel_dp->lttpr_common_caps); /* * Prevent setting LTTPR transparent mode explicitly if no LTTPRs are @@ -172,7 +210,7 @@ int intel_dp_lttpr_init(struct intel_dp *intel_dp) return lttpr_count; } -EXPORT_SYMBOL(intel_dp_lttpr_init); +EXPORT_SYMBOL(intel_dp_init_lttpr_and_dprx_caps); static u8 dp_voltage_max(u8 preemph) { @@ -807,7 +845,11 @@ void intel_dp_start_link_train(struct intel_dp *intel_dp, * TODO: Reiniting LTTPRs here won't be needed once proper connector * HW state readout is added. */ - int lttpr_count = intel_dp_lttpr_init(intel_dp); + int lttpr_count = intel_dp_init_lttpr_and_dprx_caps(intel_dp); + + if (lttpr_count < 0) + /* Still continue with enabling the port and link training. */ + lttpr_count = 0; if (!intel_dp_link_train_all_phys(intel_dp, crtc_state, lttpr_count)) intel_dp_schedule_fallback_link_training(intel_dp, crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.h b/drivers/gpu/drm/i915/display/intel_dp_link_training.h index 6a1f76bd8c75..9cb7c28027f0 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.h +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.h @@ -11,7 +11,7 @@ struct intel_crtc_state; struct intel_dp; -int intel_dp_lttpr_init(struct intel_dp *intel_dp); +int intel_dp_init_lttpr_and_dprx_caps(struct intel_dp *intel_dp); void intel_dp_get_adjust_train(struct intel_dp *intel_dp, const struct intel_crtc_state *crtc_state, diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index f58cc5700784..a86c57d117f2 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -1014,20 +1014,14 @@ static i915_reg_t dss_ctl1_reg(const struct intel_crtc_state *crtc_state) { enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe; - if (crtc_state->cpu_transcoder == TRANSCODER_EDP) - return DSS_CTL1; - - return ICL_PIPE_DSS_CTL1(pipe); + return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL1(pipe) : DSS_CTL1; } static i915_reg_t dss_ctl2_reg(const struct intel_crtc_state *crtc_state) { enum pipe pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe; - if (crtc_state->cpu_transcoder == TRANSCODER_EDP) - return DSS_CTL2; - - return ICL_PIPE_DSS_CTL2(pipe); + return is_pipe_dsc(crtc_state) ? ICL_PIPE_DSS_CTL2(pipe) : DSS_CTL2; } void intel_dsc_enable(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index f94025ec603a..a9a8ba1d3aba 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -992,14 +992,14 @@ static void intel_dsi_post_disable(struct intel_atomic_state *state, * FIXME As we do with eDP, just make a note of the time here * and perform the wait before the next panel power on. */ - intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay); + msleep(intel_dsi->panel_pwr_cycle_delay); } static void intel_dsi_shutdown(struct intel_encoder *encoder) { struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); - intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay); + msleep(intel_dsi->panel_pwr_cycle_delay); } static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index a357bb431815..67de2b189598 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -316,7 +316,18 @@ void i915_vma_revoke_fence(struct i915_vma *vma) WRITE_ONCE(fence->vma, NULL); vma->fence = NULL; - with_intel_runtime_pm_if_in_use(fence_to_uncore(fence)->rpm, wakeref) + /* + * Skip the write to HW if and only if the device is currently + * suspended. + * + * If the driver does not currently hold a wakeref (if_in_use == 0), + * the device may currently be runtime suspended, or it may be woken + * up before the suspend takes place. If the device is not suspended + * (powered down) and we skip clearing the fence register, the HW is + * left in an undefined state where we may end up with multiple + * registers overlapping. + */ + with_intel_runtime_pm_if_active(fence_to_uncore(fence)->rpm, wakeref) fence_write(fence); } diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index fef1e857cefc..01c1d1b36acd 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -916,19 +916,26 @@ static int cmd_reg_handler(struct parser_exec_state *s, if (!strncmp(cmd, "srm", 3) || !strncmp(cmd, "lrm", 3)) { - if (offset != i915_mmio_reg_offset(GEN8_L3SQCREG4) && - offset != 0x21f0) { + if (offset == i915_mmio_reg_offset(GEN8_L3SQCREG4) || + offset == 0x21f0 || + (IS_BROADWELL(gvt->gt->i915) && + offset == i915_mmio_reg_offset(INSTPM))) + return 0; + else { gvt_vgpu_err("%s access to register (%x)\n", cmd, offset); return -EPERM; - } else - return 0; + } } if (!strncmp(cmd, "lrr-src", 7) || !strncmp(cmd, "lrr-dst", 7)) { - gvt_vgpu_err("not allowed cmd %s\n", cmd); - return -EPERM; + if (IS_BROADWELL(gvt->gt->i915) && offset == 0x215c) + return 0; + else { + gvt_vgpu_err("not allowed cmd %s reg (%x)\n", cmd, offset); + return -EPERM; + } } if (!strncmp(cmd, "pipe_ctrl", 9)) { diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 97b57acc02e2..4b4d8d034782 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -5471,12 +5471,12 @@ static int icl_build_plane_wm(struct intel_crtc_state *crtc_state, struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id]; int ret; - memset(wm, 0, sizeof(*wm)); - /* Watermarks calculated in master */ if (plane_state->planar_slave) return 0; + memset(wm, 0, sizeof(*wm)); + if (plane_state->planar_linked_plane) { const struct drm_framebuffer *fb = plane_state->hw.fb; enum plane_id y_plane_id = plane_state->planar_linked_plane->id; diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 153ca9e65382..8b725efb2254 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -412,12 +412,20 @@ intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm) } /** - * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use + * __intel_runtime_pm_get_if_active - grab a runtime pm reference if device is active * @rpm: the intel_runtime_pm structure + * @ignore_usecount: get a ref even if dev->power.usage_count is 0 * * This function grabs a device-level runtime pm reference if the device is - * already in use and ensures that it is powered up. It is illegal to try - * and access the HW should intel_runtime_pm_get_if_in_use() report failure. + * already active and ensures that it is powered up. It is illegal to try + * and access the HW should intel_runtime_pm_get_if_active() report failure. + * + * If @ignore_usecount=true, a reference will be acquired even if there is no + * user requiring the device to be powered up (dev->power.usage_count == 0). + * If the function returns false in this case then it's guaranteed that the + * device's runtime suspend hook has been called already or that it will be + * called (and hence it's also guaranteed that the device's runtime resume + * hook will be called eventually). * * Any runtime pm reference obtained by this function must have a symmetric * call to intel_runtime_pm_put() to release the reference again. @@ -425,7 +433,8 @@ intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm) * Returns: the wakeref cookie to pass to intel_runtime_pm_put(), evaluates * as True if the wakeref was acquired, or False otherwise. */ -intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) +static intel_wakeref_t __intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm, + bool ignore_usecount) { if (IS_ENABLED(CONFIG_PM)) { /* @@ -434,7 +443,7 @@ intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) * function, since the power state is undefined. This applies * atm to the late/early system suspend/resume handlers. */ - if (pm_runtime_get_if_in_use(rpm->kdev) <= 0) + if (pm_runtime_get_if_active(rpm->kdev, ignore_usecount) <= 0) return 0; } @@ -443,6 +452,16 @@ intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) return track_intel_runtime_pm_wakeref(rpm); } +intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm) +{ + return __intel_runtime_pm_get_if_active(rpm, false); +} + +intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm) +{ + return __intel_runtime_pm_get_if_active(rpm, true); +} + /** * intel_runtime_pm_get_noresume - grab a runtime pm reference * @rpm: the intel_runtime_pm structure diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.h b/drivers/gpu/drm/i915/intel_runtime_pm.h index ae64ff14c642..1e4ddd11c12b 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.h +++ b/drivers/gpu/drm/i915/intel_runtime_pm.h @@ -177,6 +177,7 @@ void intel_runtime_pm_driver_release(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get_if_in_use(struct intel_runtime_pm *rpm); +intel_wakeref_t intel_runtime_pm_get_if_active(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get_noresume(struct intel_runtime_pm *rpm); intel_wakeref_t intel_runtime_pm_get_raw(struct intel_runtime_pm *rpm); @@ -188,6 +189,10 @@ intel_wakeref_t intel_runtime_pm_get_raw(struct intel_runtime_pm *rpm); for ((wf) = intel_runtime_pm_get_if_in_use(rpm); (wf); \ intel_runtime_pm_put((rpm), (wf)), (wf) = 0) +#define with_intel_runtime_pm_if_active(rpm, wf) \ + for ((wf) = intel_runtime_pm_get_if_active(rpm); (wf); \ + intel_runtime_pm_put((rpm), (wf)), (wf) = 0) + void intel_runtime_pm_put_unchecked(struct intel_runtime_pm *rpm); #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM) void intel_runtime_pm_put(struct intel_runtime_pm *rpm, intel_wakeref_t wref); diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index d1a9841adeed..e6a88c8cbd69 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -215,7 +215,7 @@ static int imx_drm_bind(struct device *dev) ret = drmm_mode_config_init(drm); if (ret) - return ret; + goto err_kms; ret = drm_vblank_init(drm, MAX_CRTC); if (ret) diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index dbfe39e2f7f6..ffdc492c5bc5 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -197,6 +197,11 @@ static void imx_ldb_encoder_enable(struct drm_encoder *encoder) int dual = ldb->ldb_ctrl & LDB_SPLIT_MODE_EN; int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder); + if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) { + dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux); + return; + } + drm_panel_prepare(imx_ldb_ch->panel); if (dual) { @@ -255,6 +260,11 @@ imx_ldb_encoder_atomic_mode_set(struct drm_encoder *encoder, int mux = drm_of_encoder_active_port_id(imx_ldb_ch->child, encoder); u32 bus_format = imx_ldb_ch->bus_format; + if (mux < 0 || mux >= ARRAY_SIZE(ldb->clk_sel)) { + dev_warn(ldb->dev, "%s: invalid mux %d\n", __func__, mux); + return; + } + if (mode->clock > 170000) { dev_warn(ldb->dev, "%s: mode exceeds 170 MHz pixel clock\n", __func__); @@ -583,7 +593,7 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) struct imx_ldb_channel *channel = &imx_ldb->channel[i]; if (!channel->ldb) - break; + continue; ret = imx_ldb_register(drm, channel); if (ret) diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 7e553d3efeb2..ce13d49e615b 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1386,8 +1386,8 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu) static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { - *value = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_CP_0_LO, - REG_A5XX_RBBM_PERFCTR_CP_0_HI); + *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO, + REG_A5XX_RBBM_ALWAYSON_COUNTER_HI); return 0; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c index 5ccc9da455a1..c35b06b46fcc 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_power.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c @@ -304,7 +304,7 @@ int a5xx_power_init(struct msm_gpu *gpu) /* Set up the limits management */ if (adreno_is_a530(adreno_gpu)) a530_lm_setup(gpu); - else + else if (adreno_is_a540(adreno_gpu)) a540_lm_setup(gpu); /* Set up SP/TP power collpase */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 71c917f909af..91cf46f84025 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -339,7 +339,7 @@ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) else bit = a6xx_gmu_oob_bits[state].ack_new; - gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, bit); + gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << bit); } /* Enable CPU control of SPTP power power collapse */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index ba8e9d3cf0fe..d553f62f4eeb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -522,28 +522,73 @@ static int a6xx_cp_init(struct msm_gpu *gpu) return a6xx_idle(gpu, ring) ? 0 : -EINVAL; } -static void a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu, +/* + * Check that the microcode version is new enough to include several key + * security fixes. Return true if the ucode is safe. + */ +static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu, struct drm_gem_object *obj) { + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; u32 *buf = msm_gem_get_vaddr(obj); + bool ret = false; if (IS_ERR(buf)) - return; + return false; /* - * If the lowest nibble is 0xa that is an indication that this microcode - * has been patched. The actual version is in dword [3] but we only care - * about the patchlevel which is the lowest nibble of dword [3] - * - * Otherwise check that the firmware is greater than or equal to 1.90 - * which was the first version that had this fix built in + * Targets up to a640 (a618, a630 and a640) need to check for a + * microcode version that is patched to support the whereami opcode or + * one that is new enough to include it by default. */ - if (((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) - a6xx_gpu->has_whereami = true; - else if ((buf[0] & 0xfff) > 0x190) - a6xx_gpu->has_whereami = true; + if (adreno_is_a618(adreno_gpu) || adreno_is_a630(adreno_gpu) || + adreno_is_a640(adreno_gpu)) { + /* + * If the lowest nibble is 0xa that is an indication that this + * microcode has been patched. The actual version is in dword + * [3] but we only care about the patchlevel which is the lowest + * nibble of dword [3] + * + * Otherwise check that the firmware is greater than or equal + * to 1.90 which was the first version that had this fix built + * in + */ + if ((((buf[0] & 0xf) == 0xa) && (buf[2] & 0xf) >= 1) || + (buf[0] & 0xfff) >= 0x190) { + a6xx_gpu->has_whereami = true; + ret = true; + goto out; + } + DRM_DEV_ERROR(&gpu->pdev->dev, + "a630 SQE ucode is too old. Have version %x need at least %x\n", + buf[0] & 0xfff, 0x190); + } else { + /* + * a650 tier targets don't need whereami but still need to be + * equal to or newer than 0.95 for other security fixes + */ + if (adreno_is_a650(adreno_gpu)) { + if ((buf[0] & 0xfff) >= 0x095) { + ret = true; + goto out; + } + + DRM_DEV_ERROR(&gpu->pdev->dev, + "a650 SQE ucode is too old. Have version %x need at least %x\n", + buf[0] & 0xfff, 0x095); + } + + /* + * When a660 is added those targets should return true here + * since those have all the critical security fixes built in + * from the start + */ + } +out: msm_gem_put_vaddr(obj); + return ret; } static int a6xx_ucode_init(struct msm_gpu *gpu) @@ -566,7 +611,13 @@ static int a6xx_ucode_init(struct msm_gpu *gpu) } msm_gem_object_set_name(a6xx_gpu->sqe_bo, "sqefw"); - a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo); + if (!a6xx_ucode_check_version(a6xx_gpu, a6xx_gpu->sqe_bo)) { + msm_gem_unpin_iova(a6xx_gpu->sqe_bo, gpu->aspace); + drm_gem_object_put(a6xx_gpu->sqe_bo); + + a6xx_gpu->sqe_bo = NULL; + return -EPERM; + } } gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE_LO, @@ -1177,8 +1228,8 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) /* Force the GPU power on so we can read this register */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); - *value = gpu_read64(gpu, REG_A6XX_RBBM_PERFCTR_CP_0_LO, - REG_A6XX_RBBM_PERFCTR_CP_0_HI); + *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, + REG_A6XX_CP_ALWAYS_ON_COUNTER_HI); a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); mutex_unlock(&perfcounter_oob); @@ -1350,35 +1401,26 @@ static int a6xx_set_supported_hw(struct device *dev, struct a6xx_gpu *a6xx_gpu, u32 revn) { struct opp_table *opp_table; - struct nvmem_cell *cell; u32 supp_hw = UINT_MAX; - void *buf; + u16 speedbin; + int ret; - cell = nvmem_cell_get(dev, "speed_bin"); + ret = nvmem_cell_read_u16(dev, "speed_bin", &speedbin); /* * -ENOENT means that the platform doesn't support speedbin which is * fine */ - if (PTR_ERR(cell) == -ENOENT) + if (ret == -ENOENT) { return 0; - else if (IS_ERR(cell)) { - DRM_DEV_ERROR(dev, - "failed to read speed-bin. Some OPPs may not be supported by hardware"); - goto done; - } - - buf = nvmem_cell_read(cell, NULL); - if (IS_ERR(buf)) { - nvmem_cell_put(cell); + } else if (ret) { DRM_DEV_ERROR(dev, - "failed to read speed-bin. Some OPPs may not be supported by hardware"); + "failed to read speed-bin (%d). Some OPPs may not be supported by hardware", + ret); goto done; } + speedbin = le16_to_cpu(speedbin); - supp_hw = fuse_to_supp_hw(dev, revn, *((u32 *) buf)); - - kfree(buf); - nvmem_cell_put(cell); + supp_hw = fuse_to_supp_hw(dev, revn, speedbin); done: opp_table = dev_pm_opp_set_supported_hw(dev, &supp_hw, 1); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c index 8981cfa9dbc3..92e6f1b94738 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -496,7 +496,9 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, DPU_REG_WRITE(c, CTL_TOP, mode_sel); DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); - DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, BIT(cfg->merge_3d - MERGE_3D_0)); + if (cfg->merge_3d) + DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, + BIT(cfg->merge_3d - MERGE_3D_0)); } static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 5a8e3e1fc48c..85f2c3564c96 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -43,6 +43,8 @@ #define DPU_DEBUGFS_DIR "msm_dpu" #define DPU_DEBUGFS_HWMASKNAME "hw_log_mask" +#define MIN_IB_BW 400000000ULL /* Min ib vote 400MB */ + static int dpu_kms_hw_init(struct msm_kms *kms); static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms); @@ -931,6 +933,9 @@ static int dpu_kms_hw_init(struct msm_kms *kms) DPU_DEBUG("REG_DMA is not defined"); } + if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss")) + dpu_kms_parse_data_bus_icc_path(dpu_kms); + pm_runtime_get_sync(&dpu_kms->pdev->dev); dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0); @@ -1032,9 +1037,6 @@ static int dpu_kms_hw_init(struct msm_kms *kms) dpu_vbif_init_memtypes(dpu_kms); - if (of_device_is_compatible(dev->dev->of_node, "qcom,sc7180-mdss")) - dpu_kms_parse_data_bus_icc_path(dpu_kms); - pm_runtime_put_sync(&dpu_kms->pdev->dev); return 0; @@ -1191,10 +1193,10 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev) ddev = dpu_kms->dev; + WARN_ON(!(dpu_kms->num_paths)); /* Min vote of BW is required before turning on AXI clk */ for (i = 0; i < dpu_kms->num_paths; i++) - icc_set_bw(dpu_kms->path[i], 0, - dpu_kms->catalog->perf.min_dram_ib); + icc_set_bw(dpu_kms->path[i], 0, Bps_to_icc(MIN_IB_BW)); rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true); if (rc) { diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index 1c6e1d2b947c..7c22bfe0fc7d 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -32,6 +32,8 @@ struct dp_aux_private { struct drm_dp_aux dp_aux; }; +#define MAX_AUX_RETRIES 5 + static const char *dp_aux_get_error(u32 aux_error) { switch (aux_error) { @@ -377,6 +379,11 @@ static ssize_t dp_aux_transfer(struct drm_dp_aux *dp_aux, ret = dp_aux_cmd_fifo_tx(aux, msg); if (ret < 0) { + if (aux->native) { + aux->retry_cnt++; + if (!(aux->retry_cnt % MAX_AUX_RETRIES)) + dp_catalog_aux_update_cfg(aux->catalog); + } usleep_range(400, 500); /* at least 400us to next try */ goto unlock_exit; } diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c index a45fe95aff49..3dc65877fa10 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.c @@ -163,7 +163,7 @@ struct msm_dsi_pll *msm_dsi_pll_init(struct platform_device *pdev, break; case MSM_DSI_PHY_7NM: case MSM_DSI_PHY_7NM_V4_1: - pll = msm_dsi_pll_7nm_init(pdev, id); + pll = msm_dsi_pll_7nm_init(pdev, type, id); break; default: pll = ERR_PTR(-ENXIO); diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h index 3405982a092c..bbecb1de5678 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll.h @@ -117,10 +117,12 @@ msm_dsi_pll_10nm_init(struct platform_device *pdev, int id) } #endif #ifdef CONFIG_DRM_MSM_DSI_7NM_PHY -struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id); +struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, + enum msm_dsi_phy_type type, int id); #else static inline struct msm_dsi_pll * -msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) +msm_dsi_pll_7nm_init(struct platform_device *pdev, + enum msm_dsi_phy_type type, int id) { return ERR_PTR(-ENODEV); } diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c index 93bf142e4a4e..e29b3bfd63d1 100644 --- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c +++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c @@ -325,7 +325,7 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll) pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1, reg->frac_div_start_low); pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1, reg->frac_div_start_mid); pll_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1, reg->frac_div_start_high); - pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40); + pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, reg->pll_lockdet_rate); pll_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); pll_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, 0x10); /* TODO: 0x00 for CPHY */ pll_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, reg->pll_clock_inverters); @@ -509,6 +509,7 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, { struct msm_dsi_pll *pll = hw_clk_to_pll(hw); struct dsi_pll_7nm *pll_7nm = to_pll_7nm(pll); + struct dsi_pll_config *config = &pll_7nm->pll_configuration; void __iomem *base = pll_7nm->mmio; u64 ref_clk = pll_7nm->vco_ref_clk_rate; u64 vco_rate = 0x0; @@ -529,9 +530,8 @@ static unsigned long dsi_pll_7nm_vco_recalc_rate(struct clk_hw *hw, /* * TODO: * 1. Assumes prescaler is disabled - * 2. Multiplier is 2^18. it should be 2^(num_of_frac_bits) */ - multiplier = 1 << 18; + multiplier = 1 << config->frac_bits; pll_freq = dec * (ref_clk * 2); tmp64 = (ref_clk * 2 * frac); pll_freq += div_u64(tmp64, multiplier); @@ -852,7 +852,8 @@ err_base_clk_hw: return ret; } -struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) +struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, + enum msm_dsi_phy_type type, int id) { struct dsi_pll_7nm *pll_7nm; struct msm_dsi_pll *pll; @@ -885,7 +886,7 @@ struct msm_dsi_pll *msm_dsi_pll_7nm_init(struct platform_device *pdev, int id) pll = &pll_7nm->base; pll->min_rate = 1000000000UL; pll->max_rate = 3500000000UL; - if (pll->type == MSM_DSI_PHY_7NM_V4_1) { + if (type == MSM_DSI_PHY_7NM_V4_1) { pll->min_rate = 600000000UL; pll->max_rate = (unsigned long)5000000000ULL; /* workaround for max rate overflowing on 32-bit builds: */ diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 6a326761dc4a..edcaccaa27e6 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -57,10 +57,13 @@ static void vblank_put(struct msm_kms *kms, unsigned crtc_mask) static void lock_crtcs(struct msm_kms *kms, unsigned int crtc_mask) { + int crtc_index; struct drm_crtc *crtc; - for_each_crtc_mask(kms->dev, crtc, crtc_mask) - mutex_lock(&kms->commit_lock[drm_crtc_index(crtc)]); + for_each_crtc_mask(kms->dev, crtc, crtc_mask) { + crtc_index = drm_crtc_index(crtc); + mutex_lock_nested(&kms->commit_lock[crtc_index], crtc_index); + } } static void unlock_crtcs(struct msm_kms *kms, unsigned int crtc_mask) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 94525ac76d4e..196907689c82 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -570,6 +570,7 @@ err_free_priv: kfree(priv); err_put_drm_dev: drm_dev_put(ddev); + platform_set_drvdata(pdev, NULL); return ret; } @@ -1072,6 +1073,10 @@ static int __maybe_unused msm_pm_resume(struct device *dev) static int __maybe_unused msm_pm_prepare(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); + struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL; + + if (!priv || !priv->kms) + return 0; return drm_mode_config_helper_suspend(ddev); } @@ -1079,6 +1084,10 @@ static int __maybe_unused msm_pm_prepare(struct device *dev) static void __maybe_unused msm_pm_complete(struct device *dev) { struct drm_device *ddev = dev_get_drvdata(dev); + struct msm_drm_private *priv = ddev ? ddev->dev_private : NULL; + + if (!priv || !priv->kms) + return; drm_mode_config_helper_resume(ddev); } @@ -1311,6 +1320,10 @@ static int msm_pdev_remove(struct platform_device *pdev) static void msm_pdev_shutdown(struct platform_device *pdev) { struct drm_device *drm = platform_get_drvdata(pdev); + struct msm_drm_private *priv = drm ? drm->dev_private : NULL; + + if (!priv || !priv->kms) + return; drm_atomic_helper_shutdown(drm); } diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c index ad2703698b05..cd59a5918038 100644 --- a/drivers/gpu/drm/msm/msm_fence.c +++ b/drivers/gpu/drm/msm/msm_fence.c @@ -45,7 +45,7 @@ int msm_wait_fence(struct msm_fence_context *fctx, uint32_t fence, int ret; if (fence > fctx->last_fence) { - DRM_ERROR("%s: waiting on invalid fence: %u (of %u)\n", + DRM_ERROR_RATELIMITED("%s: waiting on invalid fence: %u (of %u)\n", fctx->name, fence, fctx->last_fence); return -EINVAL; } diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index 4735251a394d..d8151a89e163 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -157,7 +157,6 @@ struct msm_kms { * from the crtc's pending_timer close to end of the frame: */ struct mutex commit_lock[MAX_CRTCS]; - struct lock_class_key commit_lock_keys[MAX_CRTCS]; unsigned pending_crtc_mask; struct msm_pending_timer pending_timers[MAX_CRTCS]; }; @@ -167,11 +166,8 @@ static inline int msm_kms_init(struct msm_kms *kms, { unsigned i, ret; - for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) { - lockdep_register_key(&kms->commit_lock_keys[i]); - __mutex_init(&kms->commit_lock[i], "&kms->commit_lock[i]", - &kms->commit_lock_keys[i]); - } + for (i = 0; i < ARRAY_SIZE(kms->commit_lock); i++) + mutex_init(&kms->commit_lock[i]); kms->funcs = funcs; diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 196612addfd6..1c9c0cdf85db 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2693,9 +2693,20 @@ nv50_display_create(struct drm_device *dev) else nouveau_display(dev)->format_modifiers = disp50xx_modifiers; - if (disp->disp->object.oclass >= GK104_DISP) { + /* FIXME: 256x256 cursors are supported on Kepler, however unlike Maxwell and later + * generations Kepler requires that we use small pages (4K) for cursor scanout surfaces. The + * proper fix for this is to teach nouveau to migrate fbs being used for the cursor plane to + * small page allocations in prepare_fb(). When this is implemented, we should also force + * large pages (128K) for ovly fbs in order to fix Kepler ovlys. + * But until then, just limit cursors to 128x128 - which is small enough to avoid ever using + * large pages. + */ + if (disp->disp->object.oclass >= GM107_DISP) { dev->mode_config.cursor_width = 256; dev->mode_config.cursor_height = 256; + } else if (disp->disp->object.oclass >= GK104_DISP) { + dev->mode_config.cursor_width = 128; + dev->mode_config.cursor_height = 128; } else { dev->mode_config.cursor_width = 64; dev->mode_config.cursor_height = 64; diff --git a/drivers/gpu/drm/panel/panel-dsi-cm.c b/drivers/gpu/drm/panel/panel-dsi-cm.c index af381d756ac1..5fbfb71ca3d9 100644 --- a/drivers/gpu/drm/panel/panel-dsi-cm.c +++ b/drivers/gpu/drm/panel/panel-dsi-cm.c @@ -37,6 +37,7 @@ struct dsic_panel_data { u32 height_mm; u32 max_hs_rate; u32 max_lp_rate; + bool te_support; }; struct panel_drv_data { @@ -334,9 +335,11 @@ static int dsicm_power_on(struct panel_drv_data *ddata) if (r) goto err; - r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK); - if (r) - goto err; + if (ddata->panel_data->te_support) { + r = mipi_dsi_dcs_set_tear_on(ddata->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK); + if (r) + goto err; + } /* possible panel bug */ msleep(100); @@ -619,6 +622,7 @@ static const struct dsic_panel_data taal_data = { .height_mm = 0, .max_hs_rate = 300000000, .max_lp_rate = 10000000, + .te_support = true, }; static const struct dsic_panel_data himalaya_data = { @@ -629,6 +633,7 @@ static const struct dsic_panel_data himalaya_data = { .height_mm = 88, .max_hs_rate = 300000000, .max_lp_rate = 10000000, + .te_support = false, }; static const struct dsic_panel_data droid4_data = { @@ -639,6 +644,7 @@ static const struct dsic_panel_data droid4_data = { .height_mm = 89, .max_hs_rate = 300000000, .max_lp_rate = 10000000, + .te_support = false, }; static const struct of_device_id dsicm_of_match[] = { diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index e8c66d10478f..78893bea85ae 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -364,7 +364,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, struct ttm_tt * if (gtt->userflags & RADEON_GEM_USERPTR_ANONONLY) { /* check that we only pin down anonymous memory to prevent problems with writeback */ - unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE; + unsigned long end = gtt->userptr + (u64)ttm->num_pages * PAGE_SIZE; struct vm_area_struct *vma; vma = find_vma(gtt->usermm, gtt->userptr); if (!vma || vma->vm_file || vma->vm_end < end) @@ -386,7 +386,7 @@ static int radeon_ttm_tt_pin_userptr(struct ttm_bo_device *bdev, struct ttm_tt * } while (pinned < ttm->num_pages); r = sg_alloc_table_from_pages(ttm->sg, ttm->pages, ttm->num_pages, 0, - ttm->num_pages << PAGE_SHIFT, + (u64)ttm->num_pages << PAGE_SHIFT, GFP_KERNEL); if (r) goto release_sg; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c index ba8c6038cd63..ca3761772211 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c @@ -48,21 +48,12 @@ static unsigned int rcar_du_encoder_count_ports(struct device_node *node) static const struct drm_encoder_funcs rcar_du_encoder_funcs = { }; -static void rcar_du_encoder_release(struct drm_device *dev, void *res) -{ - struct rcar_du_encoder *renc = res; - - drm_encoder_cleanup(&renc->base); - kfree(renc); -} - int rcar_du_encoder_init(struct rcar_du_device *rcdu, enum rcar_du_output output, struct device_node *enc_node) { struct rcar_du_encoder *renc; struct drm_bridge *bridge; - int ret; /* * Locate the DRM bridge from the DT node. For the DPAD outputs, if the @@ -101,26 +92,16 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu, return -ENOLINK; } - renc = kzalloc(sizeof(*renc), GFP_KERNEL); - if (renc == NULL) - return -ENOMEM; - - renc->output = output; - dev_dbg(rcdu->dev, "initializing encoder %pOF for output %u\n", enc_node, output); - ret = drm_encoder_init(&rcdu->ddev, &renc->base, &rcar_du_encoder_funcs, - DRM_MODE_ENCODER_NONE, NULL); - if (ret < 0) { - kfree(renc); - return ret; - } + renc = drmm_encoder_alloc(&rcdu->ddev, struct rcar_du_encoder, base, + &rcar_du_encoder_funcs, DRM_MODE_ENCODER_NONE, + NULL); + if (!renc) + return -ENOMEM; - ret = drmm_add_action_or_reset(&rcdu->ddev, rcar_du_encoder_release, - renc); - if (ret) - return ret; + renc->output = output; /* * Attach the bridge to the encoder. The bridge will create the diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c index 0ae3a025efe9..134986dc2783 100644 --- a/drivers/gpu/drm/tegra/dc.c +++ b/drivers/gpu/drm/tegra/dc.c @@ -1688,6 +1688,11 @@ static void tegra_dc_commit_state(struct tegra_dc *dc, dev_err(dc->dev, "failed to set clock rate to %lu Hz\n", state->pclk); + + err = clk_set_rate(dc->clk, state->pclk); + if (err < 0) + dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n", + dc->clk, state->pclk, err); } DRM_DEBUG_KMS("rate: %lu, div: %u\n", clk_get_rate(dc->clk), @@ -1698,11 +1703,6 @@ static void tegra_dc_commit_state(struct tegra_dc *dc, value = SHIFT_CLK_DIVIDER(state->div) | PIXEL_CLK_DIVIDER_PCD1; tegra_dc_writel(dc, value, DC_DISP_DISP_CLOCK_CONTROL); } - - err = clk_set_rate(dc->clk, state->pclk); - if (err < 0) - dev_err(dc->dev, "failed to set clock %pC to %lu Hz: %d\n", - dc->clk, state->pclk, err); } static void tegra_dc_stop(struct tegra_dc *dc) @@ -2501,22 +2501,18 @@ static int tegra_dc_couple(struct tegra_dc *dc) * POWER_CONTROL registers during CRTC enabling. */ if (dc->soc->coupled_pm && dc->pipe == 1) { - u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER; - struct device_link *link; - struct device *partner; + struct device *companion; + struct tegra_dc *parent; - partner = driver_find_device(dc->dev->driver, NULL, NULL, - tegra_dc_match_by_pipe); - if (!partner) + companion = driver_find_device(dc->dev->driver, NULL, (const void *)0, + tegra_dc_match_by_pipe); + if (!companion) return -EPROBE_DEFER; - link = device_link_add(dc->dev, partner, flags); - if (!link) { - dev_err(dc->dev, "failed to link controllers\n"); - return -EINVAL; - } + parent = dev_get_drvdata(companion); + dc->client.parent = &parent->client; - dev_dbg(dc->dev, "coupled to %s\n", dev_name(partner)); + dev_dbg(dc->dev, "coupled to %s\n", dev_name(companion)); } return 0; diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c index f02a035dda45..7b88261f57bb 100644 --- a/drivers/gpu/drm/tegra/sor.c +++ b/drivers/gpu/drm/tegra/sor.c @@ -3115,6 +3115,12 @@ static int tegra_sor_init(struct host1x_client *client) * kernel is possible. */ if (sor->rst) { + err = pm_runtime_resume_and_get(sor->dev); + if (err < 0) { + dev_err(sor->dev, "failed to get runtime PM: %d\n", err); + return err; + } + err = reset_control_acquire(sor->rst); if (err < 0) { dev_err(sor->dev, "failed to acquire SOR reset: %d\n", @@ -3148,6 +3154,7 @@ static int tegra_sor_init(struct host1x_client *client) } reset_control_release(sor->rst); + pm_runtime_put(sor->dev); } err = clk_prepare_enable(sor->clk_safe); diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index 269390bc586e..76657dcdf9b0 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -210,6 +210,7 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format) { const struct vc4_crtc_data *crtc_data = vc4_crtc_to_vc4_crtc_data(vc4_crtc); const struct vc4_pv_data *pv_data = vc4_crtc_to_vc4_pv_data(vc4_crtc); + struct vc4_dev *vc4 = to_vc4_dev(vc4_crtc->base.dev); u32 fifo_len_bytes = pv_data->fifo_depth; /* @@ -238,6 +239,22 @@ static u32 vc4_get_fifo_full_level(struct vc4_crtc *vc4_crtc, u32 format) if (crtc_data->hvs_output == 5) return 32; + /* + * It looks like in some situations, we will overflow + * the PixelValve FIFO (with the bit 10 of PV stat being + * set) and stall the HVS / PV, eventually resulting in + * a page flip timeout. + * + * Displaying the video overlay during a playback with + * Kodi on an RPi3 seems to be a great solution with a + * failure rate around 50%. + * + * Removing 1 from the FIFO full level however + * seems to completely remove that issue. + */ + if (!vc4->hvs->hvs5) + return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX - 1; + return fifo_len_bytes - 3 * HVS_FIFO_LATENCY_PIX; } } diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c index 7322169c0682..1e9c84cf614a 100644 --- a/drivers/gpu/drm/vc4/vc4_plane.c +++ b/drivers/gpu/drm/vc4/vc4_plane.c @@ -1146,7 +1146,6 @@ static void vc4_plane_atomic_async_update(struct drm_plane *plane, plane->state->src_y = state->src_y; plane->state->src_w = state->src_w; plane->state->src_h = state->src_h; - plane->state->src_h = state->src_h; plane->state->alpha = state->alpha; plane->state->pixel_blend_mode = state->pixel_blend_mode; plane->state->rotation = state->rotation; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index ba658fa9cf6c..183571c387b7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -481,11 +481,15 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) vmw_bo_unreference(&old_buf); res->id = vcotbl->type; + /* Release the pin acquired in vmw_bo_init */ + ttm_bo_unpin(bo); + return 0; out_map_new: ttm_bo_kunmap(&old_map); out_wait: + ttm_bo_unpin(bo); ttm_bo_unreserve(bo); vmw_bo_unreference(&buf); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index dd69b51c40e4..6fa24645fbbf 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -712,17 +712,8 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) dev_priv->last_read_seqno = (uint32_t) -100; dev_priv->drm.dev_private = dev_priv; - ret = vmw_setup_pci_resources(dev_priv, pci_id); - if (ret) - return ret; - ret = vmw_detect_version(dev_priv); - if (ret) - goto out_no_pci_or_version; - mutex_init(&dev_priv->cmdbuf_mutex); - mutex_init(&dev_priv->release_mutex); mutex_init(&dev_priv->binding_mutex); - mutex_init(&dev_priv->global_kms_state_mutex); ttm_lock_init(&dev_priv->reservation_sem); spin_lock_init(&dev_priv->resource_lock); spin_lock_init(&dev_priv->hw_lock); @@ -730,6 +721,14 @@ static int vmw_driver_load(struct vmw_private *dev_priv, u32 pci_id) spin_lock_init(&dev_priv->cap_lock); spin_lock_init(&dev_priv->cursor_lock); + ret = vmw_setup_pci_resources(dev_priv, pci_id); + if (ret) + return ret; + ret = vmw_detect_version(dev_priv); + if (ret) + goto out_no_pci_or_version; + + for (i = vmw_res_context; i < vmw_res_max; ++i) { idr_init(&dev_priv->res_idr[i]); INIT_LIST_HEAD(&dev_priv->res_lru[i]); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 5fa5bcd20cc5..eb76a6b9ebca 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -529,7 +529,6 @@ struct vmw_private { struct vmw_overlay *overlay_priv; struct drm_property *hotplug_mode_update_property; struct drm_property *implicit_placement_property; - struct mutex global_kms_state_mutex; spinlock_t cursor_lock; struct drm_atomic_state *suspend_state; @@ -592,7 +591,6 @@ struct vmw_private { bool refuse_hibernation; bool suspend_locked; - struct mutex release_mutex; atomic_t num_fifo_resources; /* @@ -1524,9 +1522,8 @@ static inline void vmw_bo_unreference(struct vmw_buffer_object **buf) struct vmw_buffer_object *tmp_buf = *buf; *buf = NULL; - if (tmp_buf != NULL) { + if (tmp_buf != NULL) ttm_bo_put(&tmp_buf->base); - } } static inline struct vmw_buffer_object * diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c index a372980fe6a5..f2d625415458 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c @@ -94,6 +94,16 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob, struct vmw_piter data_iter, unsigned long num_data_pages); + +static inline void vmw_bo_unpin_unlocked(struct ttm_buffer_object *bo) +{ + int ret = ttm_bo_reserve(bo, false, true, NULL); + BUG_ON(ret != 0); + ttm_bo_unpin(bo); + ttm_bo_unreserve(bo); +} + + /* * vmw_setup_otable_base - Issue an object table base setup command to * the device @@ -277,6 +287,7 @@ out_no_setup: &batch->otables[i]); } + vmw_bo_unpin_unlocked(batch->otable_bo); ttm_bo_put(batch->otable_bo); batch->otable_bo = NULL; return ret; @@ -340,6 +351,7 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv, BUG_ON(ret != 0); vmw_bo_fence_single(bo, NULL); + ttm_bo_unpin(bo); ttm_bo_unreserve(bo); ttm_bo_put(batch->otable_bo); @@ -528,6 +540,7 @@ static void vmw_mob_pt_setup(struct vmw_mob *mob, void vmw_mob_destroy(struct vmw_mob *mob) { if (mob->pt_bo) { + vmw_bo_unpin_unlocked(mob->pt_bo); ttm_bo_put(mob->pt_bo); mob->pt_bo = NULL; } @@ -643,6 +656,7 @@ int vmw_mob_bind(struct vmw_private *dev_priv, out_no_cmd_space: vmw_fifo_resource_dec(dev_priv); if (pt_set_up) { + vmw_bo_unpin_unlocked(mob->pt_bo); ttm_bo_put(mob->pt_bo); mob->pt_bo = NULL; } diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index 30d9adf31c84..9f14d99c763c 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -521,7 +521,7 @@ static int xen_drm_drv_init(struct xen_drm_front_info *front_info) drm_dev = drm_dev_alloc(&xen_drm_driver, dev); if (IS_ERR(drm_dev)) { ret = PTR_ERR(drm_dev); - goto fail; + goto fail_dev; } drm_info->drm_dev = drm_dev; @@ -551,8 +551,10 @@ fail_modeset: drm_kms_helper_poll_fini(drm_dev); drm_mode_config_cleanup(drm_dev); drm_dev_put(drm_dev); -fail: +fail_dev: kfree(drm_info); + front_info->drm_info = NULL; +fail: return ret; } diff --git a/drivers/gpu/drm/xen/xen_drm_front_conn.h b/drivers/gpu/drm/xen/xen_drm_front_conn.h index 3adacba9a23b..e5f4314899ee 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_conn.h +++ b/drivers/gpu/drm/xen/xen_drm_front_conn.h @@ -16,7 +16,6 @@ struct drm_connector; struct xen_drm_front_drm_info; -struct xen_drm_front_drm_info; int xen_drm_front_conn_init(struct xen_drm_front_drm_info *drm_info, struct drm_connector *connector); diff --git a/drivers/gpu/host1x/bus.c b/drivers/gpu/host1x/bus.c index 347fb962b6c9..68a766ff0e9d 100644 --- a/drivers/gpu/host1x/bus.c +++ b/drivers/gpu/host1x/bus.c @@ -705,8 +705,9 @@ void host1x_driver_unregister(struct host1x_driver *driver) EXPORT_SYMBOL(host1x_driver_unregister); /** - * host1x_client_register() - register a host1x client + * __host1x_client_register() - register a host1x client * @client: host1x client + * @key: lock class key for the client-specific mutex * * Registers a host1x client with each host1x controller instance. Note that * each client will only match their parent host1x controller and will only be @@ -715,13 +716,14 @@ EXPORT_SYMBOL(host1x_driver_unregister); * device and call host1x_device_init(), which will in turn call each client's * &host1x_client_ops.init implementation. */ -int host1x_client_register(struct host1x_client *client) +int __host1x_client_register(struct host1x_client *client, + struct lock_class_key *key) { struct host1x *host1x; int err; INIT_LIST_HEAD(&client->list); - mutex_init(&client->lock); + __mutex_init(&client->lock, "host1x client lock", key); client->usecount = 0; mutex_lock(&devices_lock); @@ -742,7 +744,7 @@ int host1x_client_register(struct host1x_client *client) return 0; } -EXPORT_SYMBOL(host1x_client_register); +EXPORT_SYMBOL(__host1x_client_register); /** * host1x_client_unregister() - unregister a host1x client diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c index dbac16641662..ddecc84fd6f0 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c @@ -10,6 +10,7 @@ #include <linux/bitops.h> #include <linux/delay.h> #include <linux/dma-mapping.h> +#include <linux/dmi.h> #include <linux/interrupt.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/module.h> @@ -22,9 +23,13 @@ #define ACEL_EN BIT(0) #define GYRO_EN BIT(1) -#define MAGNO_EN BIT(2) +#define MAGNO_EN BIT(2) #define ALS_EN BIT(19) +static int sensor_mask_override = -1; +module_param_named(sensor_mask, sensor_mask_override, int, 0444); +MODULE_PARM_DESC(sensor_mask, "override the detected sensors mask"); + void amd_start_sensor(struct amd_mp2_dev *privdata, struct amd_mp2_sensor_info info) { union sfh_cmd_param cmd_param; @@ -73,12 +78,41 @@ void amd_stop_all_sensors(struct amd_mp2_dev *privdata) writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0); } +static const struct dmi_system_id dmi_sensor_mask_overrides[] = { + { + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY x360 Convertible 13-ag0xxx"), + }, + .driver_data = (void *)(ACEL_EN | MAGNO_EN), + }, + { + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "HP ENVY x360 Convertible 15-cp0xxx"), + }, + .driver_data = (void *)(ACEL_EN | MAGNO_EN), + }, + { } +}; + int amd_mp2_get_sensor_num(struct amd_mp2_dev *privdata, u8 *sensor_id) { int activestatus, num_of_sensors = 0; + const struct dmi_system_id *dmi_id; + u32 activecontrolstatus; + + if (sensor_mask_override == -1) { + dmi_id = dmi_first_match(dmi_sensor_mask_overrides); + if (dmi_id) + sensor_mask_override = (long)dmi_id->driver_data; + } + + if (sensor_mask_override >= 0) { + activestatus = sensor_mask_override; + } else { + activecontrolstatus = readl(privdata->mmio + AMD_P2C_MSG3); + activestatus = activecontrolstatus >> 4; + } - privdata->activecontrolstatus = readl(privdata->mmio + AMD_P2C_MSG3); - activestatus = privdata->activecontrolstatus >> 4; if (ACEL_EN & activestatus) sensor_id[num_of_sensors++] = accel_idx; diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h index 8f8d19b2cfe5..489415f7c22c 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h +++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.h @@ -61,7 +61,6 @@ struct amd_mp2_dev { struct pci_dev *pdev; struct amdtp_cl_data *cl_data; void __iomem *mmio; - u32 activecontrolstatus; }; struct amd_mp2_sensor_info { diff --git a/drivers/hid/hid-alps.c b/drivers/hid/hid-alps.c index 3feaece13ade..6b665931147d 100644 --- a/drivers/hid/hid-alps.c +++ b/drivers/hid/hid-alps.c @@ -761,6 +761,7 @@ static int alps_input_configured(struct hid_device *hdev, struct hid_input *hi) if (input_register_device(data->input2)) { input_free_device(input2); + ret = -ENOENT; goto exit; } } diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 1dfe184ebf5a..2ab22b925941 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -1222,6 +1222,9 @@ static const struct hid_device_id asus_devices[] = { USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD), QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD }, { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, + USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD2), + QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD }, + { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, USB_DEVICE_ID_ASUSTEK_T100TA_KEYBOARD), QUIRK_T100_KEYBOARD | QUIRK_NO_CONSUMER_USAGES }, { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK, diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c index 21e15627a461..477baa30889c 100644 --- a/drivers/hid/hid-cp2112.c +++ b/drivers/hid/hid-cp2112.c @@ -161,6 +161,7 @@ struct cp2112_device { atomic_t read_avail; atomic_t xfer_avail; struct gpio_chip gc; + struct irq_chip irq; u8 *in_out_buffer; struct mutex lock; @@ -1175,16 +1176,6 @@ static int cp2112_gpio_irq_type(struct irq_data *d, unsigned int type) return 0; } -static struct irq_chip cp2112_gpio_irqchip = { - .name = "cp2112-gpio", - .irq_startup = cp2112_gpio_irq_startup, - .irq_shutdown = cp2112_gpio_irq_shutdown, - .irq_ack = cp2112_gpio_irq_ack, - .irq_mask = cp2112_gpio_irq_mask, - .irq_unmask = cp2112_gpio_irq_unmask, - .irq_set_type = cp2112_gpio_irq_type, -}; - static int __maybe_unused cp2112_allocate_irq(struct cp2112_device *dev, int pin) { @@ -1339,8 +1330,17 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id) dev->gc.can_sleep = 1; dev->gc.parent = &hdev->dev; + dev->irq.name = "cp2112-gpio"; + dev->irq.irq_startup = cp2112_gpio_irq_startup; + dev->irq.irq_shutdown = cp2112_gpio_irq_shutdown; + dev->irq.irq_ack = cp2112_gpio_irq_ack; + dev->irq.irq_mask = cp2112_gpio_irq_mask; + dev->irq.irq_unmask = cp2112_gpio_irq_unmask; + dev->irq.irq_set_type = cp2112_gpio_irq_type; + dev->irq.flags = IRQCHIP_MASK_ON_SUSPEND; + girq = &dev->gc.irq; - girq->chip = &cp2112_gpio_irqchip; + girq->chip = &dev->irq; /* The event comes from the outside so no parent handler */ girq->parent_handler = NULL; girq->num_parents = 0; diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c index d9319622da44..e60c31dd05ff 100644 --- a/drivers/hid/hid-google-hammer.c +++ b/drivers/hid/hid-google-hammer.c @@ -574,6 +574,8 @@ static void hammer_remove(struct hid_device *hdev) static const struct hid_device_id hammer_devices[] = { { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, + USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_DON) }, + { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) }, { HID_DEVICE(BUS_USB, HID_GROUP_GENERIC, USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index e42aaae3138f..67fd8a2f5aba 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -194,6 +194,7 @@ #define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD2 0x1837 #define USB_DEVICE_ID_ASUSTEK_ROG_KEYBOARD3 0x1822 #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD 0x1866 +#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD2 0x19b6 #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD 0x1869 #define USB_VENDOR_ID_ATEN 0x0557 @@ -493,6 +494,7 @@ #define USB_DEVICE_ID_GOOGLE_MASTERBALL 0x503c #define USB_DEVICE_ID_GOOGLE_MAGNEMITE 0x503d #define USB_DEVICE_ID_GOOGLE_MOONBALL 0x5044 +#define USB_DEVICE_ID_GOOGLE_DON 0x5050 #define USB_VENDOR_ID_GOTOP 0x08f2 #define USB_DEVICE_ID_SUPER_Q2 0x007f diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c index 44d715c12f6a..2d70dc4bea65 100644 --- a/drivers/hid/wacom_wac.c +++ b/drivers/hid/wacom_wac.c @@ -2533,7 +2533,7 @@ static void wacom_wac_finger_slot(struct wacom_wac *wacom_wac, !wacom_wac->shared->is_touch_on) { if (!wacom_wac->shared->touch_down) return; - prox = 0; + prox = false; } wacom_wac->hid_data.num_received++; @@ -3574,8 +3574,6 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev, { struct wacom_features *features = &wacom_wac->features; - input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS); - if (!(features->device_type & WACOM_DEVICETYPE_PEN)) return -ENODEV; @@ -3590,6 +3588,7 @@ int wacom_setup_pen_input_capabilities(struct input_dev *input_dev, return 0; } + input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS); __set_bit(BTN_TOUCH, input_dev->keybit); __set_bit(ABS_MISC, input_dev->absbit); @@ -3742,8 +3741,6 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev, { struct wacom_features *features = &wacom_wac->features; - input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS); - if (!(features->device_type & WACOM_DEVICETYPE_TOUCH)) return -ENODEV; @@ -3756,6 +3753,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev, /* setup has already been done */ return 0; + input_dev->evbit[0] |= BIT_MASK(EV_KEY) | BIT_MASK(EV_ABS); __set_bit(BTN_TOUCH, input_dev->keybit); if (features->touch_max == 1) { diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index dd27b9dbe931..873ef38eb1c8 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -129,6 +129,7 @@ static int i2c_dw_set_timings_master(struct dw_i2c_dev *dev) if ((comp_param1 & DW_IC_COMP_PARAM_1_SPEED_MODE_MASK) != DW_IC_COMP_PARAM_1_SPEED_MODE_HIGH) { dev_err(dev->dev, "High Speed not supported!\n"); + t->bus_freq_hz = I2C_MAX_FAST_MODE_FREQ; dev->master_cfg &= ~DW_IC_CON_SPEED_MASK; dev->master_cfg |= DW_IC_CON_SPEED_FAST; dev->hs_hcnt = 0; diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c index 5ac30d95650c..97d4f3ac0abd 100644 --- a/drivers/i2c/busses/i2c-exynos5.c +++ b/drivers/i2c/busses/i2c-exynos5.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * i2c-exynos5.c - Samsung Exynos5 I2C Controller Driver * * Copyright (C) 2013 Samsung Electronics Co., Ltd. diff --git a/drivers/i2c/busses/i2c-hix5hd2.c b/drivers/i2c/busses/i2c-hix5hd2.c index c45f226c2b85..aa00ba8bcb70 100644 --- a/drivers/i2c/busses/i2c-hix5hd2.c +++ b/drivers/i2c/busses/i2c-hix5hd2.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2014 Linaro Ltd. - * Copyright (c) 2014 Hisilicon Limited. + * Copyright (c) 2014 HiSilicon Limited. * * Now only support 7 bit address. */ diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c index 8509c5f11356..55177eb21d7b 100644 --- a/drivers/i2c/busses/i2c-jz4780.c +++ b/drivers/i2c/busses/i2c-jz4780.c @@ -525,8 +525,8 @@ static irqreturn_t jz4780_i2c_irq(int irqno, void *dev_id) i2c_sta = jz4780_i2c_readw(i2c, JZ4780_I2C_STA); data = *i2c->wbuf; data &= ~JZ4780_I2C_DC_READ; - if ((!i2c->stop_hold) && (i2c->cdata->version >= - ID_X1000)) + if ((i2c->wt_len == 1) && (!i2c->stop_hold) && + (i2c->cdata->version >= ID_X1000)) data |= X1000_I2C_DC_STOP; jz4780_i2c_writew(i2c, JZ4780_I2C_DC, data); i2c->wbuf++; diff --git a/drivers/i2c/busses/i2c-mv64xxx.c b/drivers/i2c/busses/i2c-mv64xxx.c index c590d36b5fd1..5c8e94b6cdb5 100644 --- a/drivers/i2c/busses/i2c-mv64xxx.c +++ b/drivers/i2c/busses/i2c-mv64xxx.c @@ -221,6 +221,10 @@ mv64xxx_i2c_hw_init(struct mv64xxx_i2c_data *drv_data) writel(0, drv_data->reg_base + drv_data->reg_offsets.ext_addr); writel(MV64XXX_I2C_REG_CONTROL_TWSIEN | MV64XXX_I2C_REG_CONTROL_STOP, drv_data->reg_base + drv_data->reg_offsets.control); + + if (drv_data->errata_delay) + udelay(5); + drv_data->state = MV64XXX_I2C_STATE_IDLE; } diff --git a/drivers/i2c/busses/i2c-stm32f4.c b/drivers/i2c/busses/i2c-stm32f4.c index 937c2c8fd349..4933fc8ce3fd 100644 --- a/drivers/i2c/busses/i2c-stm32f4.c +++ b/drivers/i2c/busses/i2c-stm32f4.c @@ -534,7 +534,7 @@ static void stm32f4_i2c_handle_rx_addr(struct stm32f4_i2c_dev *i2c_dev) default: /* * N-byte reception: - * Enable ACK, reset POS (ACK postion) and clear ADDR flag. + * Enable ACK, reset POS (ACK position) and clear ADDR flag. * In that way, ACK will be sent as soon as the current byte * will be received in the shift register */ diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index 63ebf722a424..f21362355973 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -378,7 +378,7 @@ static int i2c_gpio_init_recovery(struct i2c_adapter *adap) static int i2c_init_recovery(struct i2c_adapter *adap) { struct i2c_bus_recovery_info *bri = adap->bus_recovery_info; - char *err_str; + char *err_str, *err_level = KERN_ERR; if (!bri) return 0; @@ -387,7 +387,8 @@ static int i2c_init_recovery(struct i2c_adapter *adap) return -EPROBE_DEFER; if (!bri->recover_bus) { - err_str = "no recover_bus() found"; + err_str = "no suitable method provided"; + err_level = KERN_DEBUG; goto err; } @@ -414,7 +415,7 @@ static int i2c_init_recovery(struct i2c_adapter *adap) return 0; err: - dev_err(&adap->dev, "Not using recovery: %s\n", err_str); + dev_printk(err_level, &adap->dev, "Not using recovery: %s\n", err_str); adap->bus_recovery_info = NULL; return -EINVAL; diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 0abce004a959..65e3e7df8a4b 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -76,7 +76,9 @@ static struct workqueue_struct *addr_wq; static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = { [LS_NLA_TYPE_DGID] = {.type = NLA_BINARY, - .len = sizeof(struct rdma_nla_ls_gid)}, + .len = sizeof(struct rdma_nla_ls_gid), + .validation_type = NLA_VALIDATE_MIN, + .min = sizeof(struct rdma_nla_ls_gid)}, }; static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 8769e7aa097f..e42c812e74c3 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3610,13 +3610,14 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id) ep->com.local_addr.ss_family == AF_INET) { err = cxgb4_remove_server_filter( ep->com.dev->rdev.lldi.ports[0], ep->stid, - ep->com.dev->rdev.lldi.rxq_ids[0], 0); + ep->com.dev->rdev.lldi.rxq_ids[0], false); } else { struct sockaddr_in6 *sin6; c4iw_init_wr_wait(ep->com.wr_waitp); err = cxgb4_remove_server( ep->com.dev->rdev.lldi.ports[0], ep->stid, - ep->com.dev->rdev.lldi.rxq_ids[0], 0); + ep->com.dev->rdev.lldi.rxq_ids[0], + ep->com.local_addr.ss_family == AF_INET6); if (err) goto done; err = c4iw_wait_for_reply(&ep->com.dev->rdev, ep->com.wr_waitp, diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 2a91b8d95e12..04b1e8f021f6 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -632,22 +632,11 @@ static void _dev_comp_vect_cpu_mask_clean_up(struct hfi1_devdata *dd, */ int hfi1_dev_affinity_init(struct hfi1_devdata *dd) { - int node = pcibus_to_node(dd->pcidev->bus); struct hfi1_affinity_node *entry; const struct cpumask *local_mask; int curr_cpu, possible, i, ret; bool new_entry = false; - /* - * If the BIOS does not have the NUMA node information set, select - * NUMA 0 so we get consistent performance. - */ - if (node < 0) { - dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n"); - node = 0; - } - dd->node = node; - local_mask = cpumask_of_node(dd->node); if (cpumask_first(local_mask) >= nr_cpu_ids) local_mask = topology_core_cpumask(0); @@ -660,7 +649,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd) * create an entry in the global affinity structure and initialize it. */ if (!entry) { - entry = node_affinity_allocate(node); + entry = node_affinity_allocate(dd->node); if (!entry) { dd_dev_err(dd, "Unable to allocate global affinity node\n"); @@ -751,6 +740,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd) if (new_entry) node_affinity_add_tail(entry); + dd->affinity_entry = entry; mutex_unlock(&node_affinity.lock); return 0; @@ -766,10 +756,9 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd) { struct hfi1_affinity_node *entry; - if (dd->node < 0) - return; - mutex_lock(&node_affinity.lock); + if (!dd->affinity_entry) + goto unlock; entry = node_affinity_lookup(dd->node); if (!entry) goto unlock; @@ -780,8 +769,8 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd) */ _dev_comp_vect_cpu_mask_clean_up(dd, entry); unlock: + dd->affinity_entry = NULL; mutex_unlock(&node_affinity.lock); - dd->node = NUMA_NO_NODE; } /* diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index e09e8244a94c..2a9a040569eb 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1409,6 +1409,7 @@ struct hfi1_devdata { spinlock_t irq_src_lock; int vnic_num_vports; struct net_device *dummy_netdev; + struct hfi1_affinity_node *affinity_entry; /* Keeps track of IPoIB RSM rule users */ atomic_t ipoib_rsm_usr_num; diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index cb7ad1288821..786c6316273f 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1277,7 +1277,6 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, dd->pport = (struct hfi1_pportdata *)(dd + 1); dd->pcidev = pdev; pci_set_drvdata(pdev, dd); - dd->node = NUMA_NO_NODE; ret = xa_alloc_irq(&hfi1_dev_table, &dd->unit, dd, xa_limit_32b, GFP_KERNEL); @@ -1287,6 +1286,15 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, goto bail; } rvt_set_ibdev_name(&dd->verbs_dev.rdi, "%s_%d", class_name(), dd->unit); + /* + * If the BIOS does not have the NUMA node information set, select + * NUMA 0 so we get consistent performance. + */ + dd->node = pcibus_to_node(pdev->bus); + if (dd->node == NUMA_NO_NODE) { + dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n"); + dd->node = 0; + } /* * Initialize all locks for the device. This needs to be as early as diff --git a/drivers/infiniband/hw/hfi1/netdev_rx.c b/drivers/infiniband/hw/hfi1/netdev_rx.c index 1fb6e1a0e4e1..1bcab992ac26 100644 --- a/drivers/infiniband/hw/hfi1/netdev_rx.c +++ b/drivers/infiniband/hw/hfi1/netdev_rx.c @@ -173,8 +173,7 @@ u32 hfi1_num_netdev_contexts(struct hfi1_devdata *dd, u32 available_contexts, return 0; } - cpumask_and(node_cpu_mask, cpu_mask, - cpumask_of_node(pcibus_to_node(dd->pcidev->bus))); + cpumask_and(node_cpu_mask, cpu_mask, cpumask_of_node(dd->node)); available_cpus = cpumask_weight(node_cpu_mask); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index c3934abeb260..ce26f97b2ca2 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -1194,8 +1194,10 @@ static void hns_roce_cmq_init_regs(struct hns_roce_dev *hr_dev, bool ring_type) upper_32_bits(dma)); roce_write(hr_dev, ROCEE_TX_CMQ_DEPTH_REG, (u32)ring->desc_num >> HNS_ROCE_CMQ_DESC_NUM_S); - roce_write(hr_dev, ROCEE_TX_CMQ_HEAD_REG, 0); + + /* Make sure to write tail first and then head */ roce_write(hr_dev, ROCEE_TX_CMQ_TAIL_REG, 0); + roce_write(hr_dev, ROCEE_TX_CMQ_HEAD_REG, 0); } else { roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_L_REG, (u32)dma); roce_write(hr_dev, ROCEE_RX_CMQ_BASEADDR_H_REG, diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index de3c2fc6f361..07b8350929cd 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1116,7 +1116,7 @@ static void devx_obj_build_destroy_cmd(void *in, void *out, void *din, case MLX5_CMD_OP_CREATE_MKEY: MLX5_SET(destroy_mkey_in, din, opcode, MLX5_CMD_OP_DESTROY_MKEY); - MLX5_SET(destroy_mkey_in, in, mkey_index, *obj_id); + MLX5_SET(destroy_mkey_in, din, mkey_index, *obj_id); break; case MLX5_CMD_OP_CREATE_CQ: MLX5_SET(destroy_cq_in, din, opcode, MLX5_CMD_OP_DESTROY_CQ); diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index ec4b3f6a8222..f5a52a6fae43 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1078,7 +1078,7 @@ static int _create_kernel_qp(struct mlx5_ib_dev *dev, qpc = MLX5_ADDR_OF(create_qp_in, *in, qpc); MLX5_SET(qpc, qpc, uar_page, uar_index); - MLX5_SET(qpc, qpc, ts_format, MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(dev->mdev)); MLX5_SET(qpc, qpc, log_page_size, qp->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); /* Set "fast registration enabled" for all kernel QPs */ @@ -1188,7 +1188,8 @@ static int get_rq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq) } return MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING; } - return MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT; + return fr_supported ? MLX5_RQC_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_RQC_TIMESTAMP_FORMAT_DEFAULT; } static int get_sq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq) @@ -1206,7 +1207,8 @@ static int get_sq_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq) } return MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING; } - return MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT; + return fr_supported ? MLX5_SQC_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_SQC_TIMESTAMP_FORMAT_DEFAULT; } static int get_qp_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq, @@ -1217,7 +1219,8 @@ static int get_qp_ts_format(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *send_cq, MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING || MLX5_CAP_ROCE(dev->mdev, qp_ts_format) == MLX5_QP_TIMESTAMP_FORMAT_CAP_FREE_RUNNING_AND_REAL_TIME; - int ts_format = MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT; + int ts_format = fr_supported ? MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT; if (recv_cq && recv_cq->create_flags & IB_UVERBS_CQ_FLAGS_TIMESTAMP_COMPLETION) @@ -1930,6 +1933,7 @@ static int create_xrc_tgt_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp, if (qp->flags & IB_QP_CREATE_MANAGED_RECV) MLX5_SET(qpc, qpc, cd_slave_receive, 1); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(dev->mdev)); MLX5_SET(qpc, qpc, rq_type, MLX5_SRQ_RQ); MLX5_SET(qpc, qpc, no_sq, 1); MLX5_SET(qpc, qpc, cqn_rcv, to_mcq(devr->c0)->mcq.cqn); @@ -4873,6 +4877,7 @@ static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd, struct mlx5_ib_dev *dev; int has_net_offloads; __be64 *rq_pas0; + int ts_format; void *in; void *rqc; void *wq; @@ -4881,6 +4886,10 @@ static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd, dev = to_mdev(pd->device); + ts_format = get_rq_ts_format(dev, to_mcq(init_attr->cq)); + if (ts_format < 0) + return ts_format; + inlen = MLX5_ST_SZ_BYTES(create_rq_in) + sizeof(u64) * rwq->rq_num_pas; in = kvzalloc(inlen, GFP_KERNEL); if (!in) @@ -4890,6 +4899,7 @@ static int create_rq(struct mlx5_ib_rwq *rwq, struct ib_pd *pd, rqc = MLX5_ADDR_OF(create_rq_in, in, ctx); MLX5_SET(rqc, rqc, mem_rq_type, MLX5_RQC_MEM_RQ_TYPE_MEMORY_RQ_INLINE); + MLX5_SET(rqc, rqc, ts_format, ts_format); MLX5_SET(rqc, rqc, user_index, rwq->user_index); MLX5_SET(rqc, rqc, cqn, to_mcq(init_attr->cq)->mcq.cqn); MLX5_SET(rqc, rqc, state, MLX5_RQC_STATE_RST); diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 0eb6a7a618e0..9ea542270ed4 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1244,7 +1244,8 @@ static int qedr_check_qp_attrs(struct ib_pd *ibpd, struct qedr_dev *dev, * TGT QP isn't associated with RQ/SQ */ if ((attrs->qp_type != IB_QPT_GSI) && (dev->gsi_qp_created) && - (attrs->qp_type != IB_QPT_XRC_TGT)) { + (attrs->qp_type != IB_QPT_XRC_TGT) && + (attrs->qp_type != IB_QPT_XRC_INI)) { struct qedr_cq *send_cq = get_qedr_cq(attrs->send_cq); struct qedr_cq *recv_cq = get_qedr_cq(attrs->recv_cq); diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 0a08b4b742a3..6734329cca33 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -2720,8 +2720,8 @@ void rtrs_clt_close(struct rtrs_clt *clt) /* Now it is safe to iterate over all paths without locks */ list_for_each_entry_safe(sess, tmp, &clt->paths_list, s.entry) { - rtrs_clt_destroy_sess_files(sess, NULL); rtrs_clt_close_conns(sess, true); + rtrs_clt_destroy_sess_files(sess, NULL); kobject_put(&sess->kobj); } free_clt(clt); diff --git a/drivers/input/joystick/n64joy.c b/drivers/input/joystick/n64joy.c index 8bcc529942bc..9dbca366613e 100644 --- a/drivers/input/joystick/n64joy.c +++ b/drivers/input/joystick/n64joy.c @@ -252,8 +252,8 @@ static int __init n64joy_probe(struct platform_device *pdev) mutex_init(&priv->n64joy_mutex); priv->reg_base = devm_platform_ioremap_resource(pdev, 0); - if (!priv->reg_base) { - err = -EINVAL; + if (IS_ERR(priv->reg_base)) { + err = PTR_ERR(priv->reg_base); goto fail; } diff --git a/drivers/input/keyboard/nspire-keypad.c b/drivers/input/keyboard/nspire-keypad.c index 63d5e488137d..e9fa1423f136 100644 --- a/drivers/input/keyboard/nspire-keypad.c +++ b/drivers/input/keyboard/nspire-keypad.c @@ -93,9 +93,15 @@ static irqreturn_t nspire_keypad_irq(int irq, void *dev_id) return IRQ_HANDLED; } -static int nspire_keypad_chip_init(struct nspire_keypad *keypad) +static int nspire_keypad_open(struct input_dev *input) { + struct nspire_keypad *keypad = input_get_drvdata(input); unsigned long val = 0, cycles_per_us, delay_cycles, row_delay_cycles; + int error; + + error = clk_prepare_enable(keypad->clk); + if (error) + return error; cycles_per_us = (clk_get_rate(keypad->clk) / 1000000); if (cycles_per_us == 0) @@ -121,30 +127,6 @@ static int nspire_keypad_chip_init(struct nspire_keypad *keypad) keypad->int_mask = 1 << 1; writel(keypad->int_mask, keypad->reg_base + KEYPAD_INTMSK); - /* Disable GPIO interrupts to prevent hanging on touchpad */ - /* Possibly used to detect touchpad events */ - writel(0, keypad->reg_base + KEYPAD_UNKNOWN_INT); - /* Acknowledge existing interrupts */ - writel(~0, keypad->reg_base + KEYPAD_UNKNOWN_INT_STS); - - return 0; -} - -static int nspire_keypad_open(struct input_dev *input) -{ - struct nspire_keypad *keypad = input_get_drvdata(input); - int error; - - error = clk_prepare_enable(keypad->clk); - if (error) - return error; - - error = nspire_keypad_chip_init(keypad); - if (error) { - clk_disable_unprepare(keypad->clk); - return error; - } - return 0; } @@ -152,6 +134,11 @@ static void nspire_keypad_close(struct input_dev *input) { struct nspire_keypad *keypad = input_get_drvdata(input); + /* Disable interrupts */ + writel(0, keypad->reg_base + KEYPAD_INTMSK); + /* Acknowledge existing interrupts */ + writel(~0, keypad->reg_base + KEYPAD_INT); + clk_disable_unprepare(keypad->clk); } @@ -210,6 +197,25 @@ static int nspire_keypad_probe(struct platform_device *pdev) return -ENOMEM; } + error = clk_prepare_enable(keypad->clk); + if (error) { + dev_err(&pdev->dev, "failed to enable clock\n"); + return error; + } + + /* Disable interrupts */ + writel(0, keypad->reg_base + KEYPAD_INTMSK); + /* Acknowledge existing interrupts */ + writel(~0, keypad->reg_base + KEYPAD_INT); + + /* Disable GPIO interrupts to prevent hanging on touchpad */ + /* Possibly used to detect touchpad events */ + writel(0, keypad->reg_base + KEYPAD_UNKNOWN_INT); + /* Acknowledge existing GPIO interrupts */ + writel(~0, keypad->reg_base + KEYPAD_UNKNOWN_INT_STS); + + clk_disable_unprepare(keypad->clk); + input_set_drvdata(input, keypad); input->id.bustype = BUS_HOST; diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h index 9119e12a5778..a5a003553646 100644 --- a/drivers/input/serio/i8042-x86ia64io.h +++ b/drivers/input/serio/i8042-x86ia64io.h @@ -588,6 +588,7 @@ static const struct dmi_system_id i8042_dmi_noselftest_table[] = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_CHASSIS_TYPE, "10"), /* Notebook */ }, + }, { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), DMI_MATCH(DMI_CHASSIS_TYPE, "31"), /* Convertible Notebook */ diff --git a/drivers/input/touchscreen/elants_i2c.c b/drivers/input/touchscreen/elants_i2c.c index 4c2b579f6c8b..5f7706febcb0 100644 --- a/drivers/input/touchscreen/elants_i2c.c +++ b/drivers/input/touchscreen/elants_i2c.c @@ -1441,7 +1441,7 @@ static int elants_i2c_probe(struct i2c_client *client, touchscreen_parse_properties(ts->input, true, &ts->prop); - if (ts->chip_id == EKTF3624) { + if (ts->chip_id == EKTF3624 && ts->phy_x && ts->phy_y) { /* calculate resolution from size */ ts->x_res = DIV_ROUND_CLOSEST(ts->prop.max_x, ts->phy_x); ts->y_res = DIV_ROUND_CLOSEST(ts->prop.max_y, ts->phy_y); @@ -1449,8 +1449,7 @@ static int elants_i2c_probe(struct i2c_client *client, input_abs_set_res(ts->input, ABS_MT_POSITION_X, ts->x_res); input_abs_set_res(ts->input, ABS_MT_POSITION_Y, ts->y_res); - if (ts->major_res > 0) - input_abs_set_res(ts->input, ABS_MT_TOUCH_MAJOR, ts->major_res); + input_abs_set_res(ts->input, ABS_MT_TOUCH_MAJOR, ts->major_res); error = input_mt_init_slots(ts->input, MAX_CONTACT_NUM, INPUT_MT_DIRECT | INPUT_MT_DROP_UNUSED); diff --git a/drivers/input/touchscreen/s6sy761.c b/drivers/input/touchscreen/s6sy761.c index b63d7fdf0cd2..85a1f465c097 100644 --- a/drivers/input/touchscreen/s6sy761.c +++ b/drivers/input/touchscreen/s6sy761.c @@ -145,8 +145,8 @@ static void s6sy761_report_coordinates(struct s6sy761_data *sdata, u8 major = event[4]; u8 minor = event[5]; u8 z = event[6] & S6SY761_MASK_Z; - u16 x = (event[1] << 3) | ((event[3] & S6SY761_MASK_X) >> 4); - u16 y = (event[2] << 3) | (event[3] & S6SY761_MASK_Y); + u16 x = (event[1] << 4) | ((event[3] & S6SY761_MASK_X) >> 4); + u16 y = (event[2] << 4) | (event[3] & S6SY761_MASK_Y); input_mt_slot(sdata->input, tid); diff --git a/drivers/interconnect/bulk.c b/drivers/interconnect/bulk.c index 73e2c8d0a412..448cc536aa79 100644 --- a/drivers/interconnect/bulk.c +++ b/drivers/interconnect/bulk.c @@ -53,7 +53,7 @@ void icc_bulk_put(int num_paths, struct icc_bulk_data *paths) EXPORT_SYMBOL_GPL(icc_bulk_put); /** - * icc_bulk_set() - set bandwidth to a set of paths + * icc_bulk_set_bw() - set bandwidth to a set of paths * @num_paths: the number of icc_bulk_data * @paths: the icc_bulk_data table containing the paths and bandwidth * diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 5ad519c9f239..8a1e70e00876 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -942,6 +942,8 @@ int icc_link_destroy(struct icc_node *src, struct icc_node *dst) GFP_KERNEL); if (new) src->links = new; + else + ret = -ENOMEM; out: mutex_unlock(&icc_lock); diff --git a/drivers/interconnect/qcom/msm8939.c b/drivers/interconnect/qcom/msm8939.c index dfbec30ed149..20f31a1b4192 100644 --- a/drivers/interconnect/qcom/msm8939.c +++ b/drivers/interconnect/qcom/msm8939.c @@ -131,7 +131,7 @@ DEFINE_QNODE(mas_pcnoc_sdcc_1, MSM8939_MASTER_SDCC_1, 8, -1, -1, MSM8939_PNOC_IN DEFINE_QNODE(mas_pcnoc_sdcc_2, MSM8939_MASTER_SDCC_2, 8, -1, -1, MSM8939_PNOC_INT_1); DEFINE_QNODE(mas_qdss_bam, MSM8939_MASTER_QDSS_BAM, 8, -1, -1, MSM8939_SNOC_QDSS_INT); DEFINE_QNODE(mas_qdss_etr, MSM8939_MASTER_QDSS_ETR, 8, -1, -1, MSM8939_SNOC_QDSS_INT); -DEFINE_QNODE(mas_snoc_cfg, MSM8939_MASTER_SNOC_CFG, 4, 20, -1, MSM8939_SLAVE_SRVC_SNOC); +DEFINE_QNODE(mas_snoc_cfg, MSM8939_MASTER_SNOC_CFG, 4, -1, -1, MSM8939_SLAVE_SRVC_SNOC); DEFINE_QNODE(mas_spdm, MSM8939_MASTER_SPDM, 4, -1, -1, MSM8939_PNOC_MAS_0); DEFINE_QNODE(mas_tcu0, MSM8939_MASTER_TCU0, 16, -1, -1, MSM8939_SLAVE_EBI_CH0, MSM8939_BIMC_SNOC_MAS, MSM8939_SLAVE_AMPSS_L2); DEFINE_QNODE(mas_usb_hs1, MSM8939_MASTER_USB_HS1, 4, -1, -1, MSM8939_PNOC_MAS_1); @@ -156,14 +156,14 @@ DEFINE_QNODE(pcnoc_snoc_mas, MSM8939_PNOC_SNOC_MAS, 8, 29, -1, MSM8939_PNOC_SNOC DEFINE_QNODE(pcnoc_snoc_slv, MSM8939_PNOC_SNOC_SLV, 8, -1, 45, MSM8939_SNOC_INT_0, MSM8939_SNOC_INT_BIMC, MSM8939_SNOC_INT_1); DEFINE_QNODE(qdss_int, MSM8939_SNOC_QDSS_INT, 8, -1, -1, MSM8939_SNOC_INT_0, MSM8939_SNOC_INT_BIMC); DEFINE_QNODE(slv_apps_l2, MSM8939_SLAVE_AMPSS_L2, 16, -1, -1, 0); -DEFINE_QNODE(slv_apss, MSM8939_SLAVE_APSS, 4, -1, 20, 0); +DEFINE_QNODE(slv_apss, MSM8939_SLAVE_APSS, 4, -1, -1, 0); DEFINE_QNODE(slv_audio, MSM8939_SLAVE_LPASS, 4, -1, -1, 0); DEFINE_QNODE(slv_bimc_cfg, MSM8939_SLAVE_BIMC_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_blsp_1, MSM8939_SLAVE_BLSP_1, 4, -1, -1, 0); DEFINE_QNODE(slv_boot_rom, MSM8939_SLAVE_BOOT_ROM, 4, -1, -1, 0); DEFINE_QNODE(slv_camera_cfg, MSM8939_SLAVE_CAMERA_CFG, 4, -1, -1, 0); -DEFINE_QNODE(slv_cats_0, MSM8939_SLAVE_CATS_128, 16, -1, 106, 0); -DEFINE_QNODE(slv_cats_1, MSM8939_SLAVE_OCMEM_64, 8, -1, 107, 0); +DEFINE_QNODE(slv_cats_0, MSM8939_SLAVE_CATS_128, 16, -1, -1, 0); +DEFINE_QNODE(slv_cats_1, MSM8939_SLAVE_OCMEM_64, 8, -1, -1, 0); DEFINE_QNODE(slv_clk_ctl, MSM8939_SLAVE_CLK_CTL, 4, -1, -1, 0); DEFINE_QNODE(slv_crypto_0_cfg, MSM8939_SLAVE_CRYPTO_0_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_dehr_cfg, MSM8939_SLAVE_DEHR_CFG, 4, -1, -1, 0); @@ -187,20 +187,20 @@ DEFINE_QNODE(slv_sdcc_2, MSM8939_SLAVE_SDCC_2, 4, -1, -1, 0); DEFINE_QNODE(slv_security, MSM8939_SLAVE_SECURITY, 4, -1, -1, 0); DEFINE_QNODE(slv_snoc_cfg, MSM8939_SLAVE_SNOC_CFG, 4, -1, -1, 0); DEFINE_QNODE(slv_spdm, MSM8939_SLAVE_SPDM, 4, -1, -1, 0); -DEFINE_QNODE(slv_srvc_snoc, MSM8939_SLAVE_SRVC_SNOC, 8, -1, 29, 0); +DEFINE_QNODE(slv_srvc_snoc, MSM8939_SLAVE_SRVC_SNOC, 8, -1, -1, 0); DEFINE_QNODE(slv_tcsr, MSM8939_SLAVE_TCSR, 4, -1, -1, 0); DEFINE_QNODE(slv_tlmm, MSM8939_SLAVE_TLMM, 4, -1, -1, 0); DEFINE_QNODE(slv_usb_hs1, MSM8939_SLAVE_USB_HS1, 4, -1, -1, 0); DEFINE_QNODE(slv_usb_hs2, MSM8939_SLAVE_USB_HS2, 4, -1, -1, 0); DEFINE_QNODE(slv_venus_cfg, MSM8939_SLAVE_VENUS_CFG, 4, -1, -1, 0); -DEFINE_QNODE(snoc_bimc_0_mas, MSM8939_SNOC_BIMC_0_MAS, 16, 3, -1, MSM8939_SNOC_BIMC_0_SLV); -DEFINE_QNODE(snoc_bimc_0_slv, MSM8939_SNOC_BIMC_0_SLV, 16, -1, 24, MSM8939_SLAVE_EBI_CH0); +DEFINE_QNODE(snoc_bimc_0_mas, MSM8939_SNOC_BIMC_0_MAS, 16, -1, -1, MSM8939_SNOC_BIMC_0_SLV); +DEFINE_QNODE(snoc_bimc_0_slv, MSM8939_SNOC_BIMC_0_SLV, 16, -1, -1, MSM8939_SLAVE_EBI_CH0); DEFINE_QNODE(snoc_bimc_1_mas, MSM8939_SNOC_BIMC_1_MAS, 16, 76, -1, MSM8939_SNOC_BIMC_1_SLV); DEFINE_QNODE(snoc_bimc_1_slv, MSM8939_SNOC_BIMC_1_SLV, 16, -1, 104, MSM8939_SLAVE_EBI_CH0); DEFINE_QNODE(snoc_bimc_2_mas, MSM8939_SNOC_BIMC_2_MAS, 16, -1, -1, MSM8939_SNOC_BIMC_2_SLV); DEFINE_QNODE(snoc_bimc_2_slv, MSM8939_SNOC_BIMC_2_SLV, 16, -1, -1, MSM8939_SLAVE_EBI_CH0); DEFINE_QNODE(snoc_int_0, MSM8939_SNOC_INT_0, 8, 99, 130, MSM8939_SLAVE_QDSS_STM, MSM8939_SLAVE_IMEM, MSM8939_SNOC_PNOC_MAS); -DEFINE_QNODE(snoc_int_1, MSM8939_SNOC_INT_1, 8, 100, 131, MSM8939_SLAVE_APSS, MSM8939_SLAVE_CATS_128, MSM8939_SLAVE_OCMEM_64); +DEFINE_QNODE(snoc_int_1, MSM8939_SNOC_INT_1, 8, -1, -1, MSM8939_SLAVE_APSS, MSM8939_SLAVE_CATS_128, MSM8939_SLAVE_OCMEM_64); DEFINE_QNODE(snoc_int_bimc, MSM8939_SNOC_INT_BIMC, 8, 101, 132, MSM8939_SNOC_BIMC_1_MAS); DEFINE_QNODE(snoc_pcnoc_mas, MSM8939_SNOC_PNOC_MAS, 8, -1, -1, MSM8939_SNOC_PNOC_SLV); DEFINE_QNODE(snoc_pcnoc_slv, MSM8939_SNOC_PNOC_SLV, 8, -1, -1, MSM8939_PNOC_INT_0); diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c index 7168778fbbe1..cb0afe897162 100644 --- a/drivers/isdn/capi/kcapi.c +++ b/drivers/isdn/capi/kcapi.c @@ -721,7 +721,7 @@ u16 capi20_put_message(struct capi20_appl *ap, struct sk_buff *skb) * Return value: CAPI result code */ -u16 capi20_get_manufacturer(u32 contr, u8 *buf) +u16 capi20_get_manufacturer(u32 contr, u8 buf[CAPI_MANUFACTURER_LEN]) { struct capi_ctr *ctr; u16 ret; @@ -787,7 +787,7 @@ u16 capi20_get_version(u32 contr, struct capi_version *verp) * Return value: CAPI result code */ -u16 capi20_get_serial(u32 contr, u8 *serial) +u16 capi20_get_serial(u32 contr, u8 serial[CAPI_SERIAL_LEN]) { struct capi_ctr *ctr; u16 ret; diff --git a/drivers/isdn/hardware/mISDN/mISDNipac.c b/drivers/isdn/hardware/mISDN/mISDNipac.c index ec475087fbf9..39f841b42488 100644 --- a/drivers/isdn/hardware/mISDN/mISDNipac.c +++ b/drivers/isdn/hardware/mISDN/mISDNipac.c @@ -694,7 +694,7 @@ isac_release(struct isac_hw *isac) { if (isac->type & IPAC_TYPE_ISACX) WriteISAC(isac, ISACX_MASK, 0xff); - else + else if (isac->type != 0) WriteISAC(isac, ISAC_MASK, 0xff); if (isac->dch.timer.function != NULL) { del_timer(&isac->dch.timer); diff --git a/drivers/leds/leds-turris-omnia.c b/drivers/leds/leds-turris-omnia.c index 7b2f4d0ae3fe..2f9a289ab245 100644 --- a/drivers/leds/leds-turris-omnia.c +++ b/drivers/leds/leds-turris-omnia.c @@ -2,7 +2,7 @@ /* * CZ.NIC's Turris Omnia LEDs driver * - * 2020 by Marek Behun <marek.behun@nic.cz> + * 2020 by Marek Behún <kabel@kernel.org> */ #include <linux/i2c.h> @@ -287,6 +287,6 @@ static struct i2c_driver omnia_leds_driver = { module_i2c_driver(omnia_leds_driver); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); MODULE_DESCRIPTION("CZ.NIC's Turris Omnia LEDs"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/mailbox/armada-37xx-rwtm-mailbox.c b/drivers/mailbox/armada-37xx-rwtm-mailbox.c index 9f2ce7f03c67..456a117a65fd 100644 --- a/drivers/mailbox/armada-37xx-rwtm-mailbox.c +++ b/drivers/mailbox/armada-37xx-rwtm-mailbox.c @@ -2,7 +2,7 @@ /* * rWTM BIU Mailbox driver for Armada 37xx * - * Author: Marek Behun <marek.behun@nic.cz> + * Author: Marek Behún <kabel@kernel.org> */ #include <linux/device.h> @@ -203,4 +203,4 @@ module_platform_driver(armada_37xx_mbox_driver); MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("rWTM BIU Mailbox driver for Armada 37xx"); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index 5e306bba4375..1ca65b434f1f 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -529,7 +529,7 @@ static int list_devices(struct file *filp, struct dm_ioctl *param, size_t param_ * Grab our output buffer. */ nl = orig_nl = get_result_buffer(param, param_size, &len); - if (len < needed) { + if (len < needed || len < sizeof(nl->dev)) { param->flags |= DM_BUFFER_FULL_FLAG; goto out; } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 95391f78b8d5..e5f0f1703c5d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1594,6 +1594,13 @@ static int device_not_zoned_model(struct dm_target *ti, struct dm_dev *dev, return blk_queue_zoned_model(q) != *zoned_model; } +/* + * Check the device zoned model based on the target feature flag. If the target + * has the DM_TARGET_ZONED_HM feature flag set, host-managed zoned devices are + * also accepted but all devices must have the same zoned model. If the target + * has the DM_TARGET_MIXED_ZONED_MODEL feature set, the devices can have any + * zoned model with all zoned devices having the same zone size. + */ static bool dm_table_supports_zoned_model(struct dm_table *t, enum blk_zoned_model zoned_model) { @@ -1603,13 +1610,15 @@ static bool dm_table_supports_zoned_model(struct dm_table *t, for (i = 0; i < dm_table_get_num_targets(t); i++) { ti = dm_table_get_target(t, i); - if (zoned_model == BLK_ZONED_HM && - !dm_target_supports_zoned_hm(ti->type)) - return false; - - if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, device_not_zoned_model, &zoned_model)) - return false; + if (dm_target_supports_zoned_hm(ti->type)) { + if (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_not_zoned_model, + &zoned_model)) + return false; + } else if (!dm_target_supports_mixed_zoned_model(ti->type)) { + if (zoned_model == BLK_ZONED_HM) + return false; + } } return true; @@ -1621,9 +1630,17 @@ static int device_not_matches_zone_sectors(struct dm_target *ti, struct dm_dev * struct request_queue *q = bdev_get_queue(dev->bdev); unsigned int *zone_sectors = data; + if (!blk_queue_is_zoned(q)) + return 0; + return blk_queue_zone_sectors(q) != *zone_sectors; } +/* + * Check consistency of zoned model and zone sectors across all targets. For + * zone sectors, if the destination device is a zoned block device, it shall + * have the specified zone_sectors. + */ static int validate_hardware_zoned_model(struct dm_table *table, enum blk_zoned_model zoned_model, unsigned int zone_sectors) @@ -1642,7 +1659,7 @@ static int validate_hardware_zoned_model(struct dm_table *table, return -EINVAL; if (dm_table_any_dev_attr(table, device_not_matches_zone_sectors, &zone_sectors)) { - DMERR("%s: zone sectors is not consistent across all devices", + DMERR("%s: zone sectors is not consistent across all zoned devices", dm_device_name(table->md)); return -EINVAL; } diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 66f4c6398f67..cea2b3789736 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -65,7 +65,7 @@ static u8 *fec_read_parity(struct dm_verity *v, u64 rsb, int index, u8 *res; position = (index + rsb) * v->fec->roots; - block = div64_u64_rem(position, v->fec->roots << SECTOR_SHIFT, &rem); + block = div64_u64_rem(position, v->fec->io_size, &rem); *offset = (unsigned)rem; res = dm_bufio_read(v->fec->bufio, block, buf); @@ -154,7 +154,7 @@ static int fec_decode_bufs(struct dm_verity *v, struct dm_verity_fec_io *fio, /* read the next block when we run out of parity bytes */ offset += v->fec->roots; - if (offset >= v->fec->roots << SECTOR_SHIFT) { + if (offset >= v->fec->io_size) { dm_bufio_release(buf); par = fec_read_parity(v, rsb, block_offset, &offset, &buf); @@ -742,8 +742,13 @@ int verity_fec_ctr(struct dm_verity *v) return -E2BIG; } + if ((f->roots << SECTOR_SHIFT) & ((1 << v->data_dev_block_bits) - 1)) + f->io_size = 1 << v->data_dev_block_bits; + else + f->io_size = v->fec->roots << SECTOR_SHIFT; + f->bufio = dm_bufio_client_create(f->dev->bdev, - f->roots << SECTOR_SHIFT, + f->io_size, 1, 0, NULL, NULL); if (IS_ERR(f->bufio)) { ti->error = "Cannot initialize FEC bufio client"; diff --git a/drivers/md/dm-verity-fec.h b/drivers/md/dm-verity-fec.h index 42fbd3a7fc9f..3c46c8d61883 100644 --- a/drivers/md/dm-verity-fec.h +++ b/drivers/md/dm-verity-fec.h @@ -36,6 +36,7 @@ struct dm_verity_fec { struct dm_dev *dev; /* parity data device */ struct dm_bufio_client *data_bufio; /* for data dev access */ struct dm_bufio_client *bufio; /* for parity data access */ + size_t io_size; /* IO size for roots */ sector_t start; /* parity data start in blocks */ sector_t blocks; /* number of blocks covered */ sector_t rounds; /* number of interleaving rounds */ diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 6b8e5bdd8526..808a98ef624c 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -34,7 +34,7 @@ #define DM_VERITY_OPT_IGN_ZEROES "ignore_zero_blocks" #define DM_VERITY_OPT_AT_MOST_ONCE "check_at_most_once" -#define DM_VERITY_OPTS_MAX (2 + DM_VERITY_OPTS_FEC + \ +#define DM_VERITY_OPTS_MAX (3 + DM_VERITY_OPTS_FEC + \ DM_VERITY_ROOT_HASH_VERIFICATION_OPTS) static unsigned dm_verity_prefetch_cluster = DM_VERITY_DEFAULT_PREFETCH_SIZE; diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 697f9de37355..7e88df64d197 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -1143,7 +1143,7 @@ static int dmz_message(struct dm_target *ti, unsigned int argc, char **argv, static struct target_type dmz_type = { .name = "zoned", .version = {2, 0, 0}, - .features = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM, + .features = DM_TARGET_SINGLETON | DM_TARGET_MIXED_ZONED_MODEL, .module = THIS_MODULE, .ctr = dmz_ctr, .dtr = dmz_dtr, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 50b693d776d6..3f3be9408afa 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2036,7 +2036,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t, if (size != dm_get_size(md)) memset(&md->geometry, 0, sizeof(md->geometry)); - set_capacity_and_notify(md->disk, size); + if (!get_capacity(md->disk)) + set_capacity(md->disk, size); + else + set_capacity_and_notify(md->disk, size); dm_table_event_callback(t, event_callback, md); diff --git a/drivers/mfd/intel_quark_i2c_gpio.c b/drivers/mfd/intel_quark_i2c_gpio.c index fe8ca945f367..b67cb0a3ab05 100644 --- a/drivers/mfd/intel_quark_i2c_gpio.c +++ b/drivers/mfd/intel_quark_i2c_gpio.c @@ -72,7 +72,8 @@ static const struct dmi_system_id dmi_platform_info[] = { {} }; -static const struct resource intel_quark_i2c_res[] = { +/* This is used as a place holder and will be modified at run-time */ +static struct resource intel_quark_i2c_res[] = { [INTEL_QUARK_IORES_MEM] = { .flags = IORESOURCE_MEM, }, @@ -85,7 +86,8 @@ static struct mfd_cell_acpi_match intel_quark_acpi_match_i2c = { .adr = MFD_ACPI_MATCH_I2C, }; -static const struct resource intel_quark_gpio_res[] = { +/* This is used as a place holder and will be modified at run-time */ +static struct resource intel_quark_gpio_res[] = { [INTEL_QUARK_IORES_MEM] = { .flags = IORESOURCE_MEM, }, diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 4378a9b25848..2cc370adb238 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -2286,8 +2286,8 @@ int mei_cl_dma_alloc_and_map(struct mei_cl *cl, const struct file *fp, if (buffer_id == 0) return -EINVAL; - if (!mei_cl_is_connected(cl)) - return -ENODEV; + if (mei_cl_is_connected(cl)) + return -EPROTO; if (cl->dma_mapped) return -EPROTO; @@ -2327,9 +2327,7 @@ int mei_cl_dma_alloc_and_map(struct mei_cl *cl, const struct file *fp, mutex_unlock(&dev->device_lock); wait_event_timeout(cl->wait, - cl->dma_mapped || - cl->status || - !mei_cl_is_connected(cl), + cl->dma_mapped || cl->status, mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT)); mutex_lock(&dev->device_lock); @@ -2376,8 +2374,9 @@ int mei_cl_dma_unmap(struct mei_cl *cl, const struct file *fp) return -EOPNOTSUPP; } - if (!mei_cl_is_connected(cl)) - return -ENODEV; + /* do not allow unmap for connected client */ + if (mei_cl_is_connected(cl)) + return -EPROTO; if (!cl->dma_mapped) return -EPROTO; @@ -2405,9 +2404,7 @@ int mei_cl_dma_unmap(struct mei_cl *cl, const struct file *fp) mutex_unlock(&dev->device_lock); wait_event_timeout(cl->wait, - !cl->dma_mapped || - cl->status || - !mei_cl_is_connected(cl), + !cl->dma_mapped || cl->status, mei_secs_to_jiffies(MEI_CL_CONNECT_TIMEOUT)); mutex_lock(&dev->device_lock); diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index eb6c02bc4a02..b8b771b643cc 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -247,8 +247,9 @@ static void meson_mmc_get_transfer_mode(struct mmc_host *mmc, */ for_each_sg(data->sg, sg, data->sg_len, i) { if (sg->length % data->blksz) { - WARN_ONCE(1, "unaligned sg len %u blksize %u\n", - sg->length, data->blksz); + dev_warn_once(mmc_dev(mmc), + "unaligned sg len %u blksize %u, disabling descriptor DMA for transfer\n", + sg->length, data->blksz); return; } } diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c index 57f1f1708994..5c5c92132287 100644 --- a/drivers/mtd/nand/raw/mtk_nand.c +++ b/drivers/mtd/nand/raw/mtk_nand.c @@ -488,8 +488,8 @@ static int mtk_nfc_exec_instr(struct nand_chip *chip, return 0; case NAND_OP_WAITRDY_INSTR: return readl_poll_timeout(nfc->regs + NFI_STA, status, - status & STA_BUSY, 20, - instr->ctx.waitrdy.timeout_ms); + !(status & STA_BUSY), 20, + instr->ctx.waitrdy.timeout_ms * 1000); default: break; } diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 8bdc44b7e09a..3c8f665c1558 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -127,6 +127,8 @@ static int com20020pci_probe(struct pci_dev *pdev, int i, ioaddr, ret; struct resource *r; + ret = 0; + if (pci_enable_device(pdev)) return -EIO; @@ -139,6 +141,8 @@ static int com20020pci_probe(struct pci_dev *pdev, priv->ci = ci; mm = &ci->misc_map; + pci_set_drvdata(pdev, priv); + INIT_LIST_HEAD(&priv->list_dev); if (mm->size) { @@ -161,7 +165,7 @@ static int com20020pci_probe(struct pci_dev *pdev, dev = alloc_arcdev(device); if (!dev) { ret = -ENOMEM; - goto out_port; + break; } dev->dev_port = i; @@ -178,7 +182,7 @@ static int com20020pci_probe(struct pci_dev *pdev, pr_err("IO region %xh-%xh already allocated\n", ioaddr, ioaddr + cm->size - 1); ret = -EBUSY; - goto out_port; + goto err_free_arcdev; } /* Dummy access after Reset @@ -216,18 +220,18 @@ static int com20020pci_probe(struct pci_dev *pdev, if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) { pr_err("IO address %Xh is empty!\n", ioaddr); ret = -EIO; - goto out_port; + goto err_free_arcdev; } if (com20020_check(dev)) { ret = -EIO; - goto out_port; + goto err_free_arcdev; } card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev), GFP_KERNEL); if (!card) { ret = -ENOMEM; - goto out_port; + goto err_free_arcdev; } card->index = i; @@ -253,29 +257,29 @@ static int com20020pci_probe(struct pci_dev *pdev, ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); if (ret) - goto out_port; + goto err_free_arcdev; ret = devm_led_classdev_register(&pdev->dev, &card->recon_led); if (ret) - goto out_port; + goto err_free_arcdev; dev_set_drvdata(&dev->dev, card); ret = com20020_found(dev, IRQF_SHARED); if (ret) - goto out_port; + goto err_free_arcdev; devm_arcnet_led_init(dev, dev->dev_id, i); list_add(&card->list, &priv->list_dev); - } + continue; - pci_set_drvdata(pdev, priv); - - return 0; - -out_port: - com20020pci_remove(pdev); +err_free_arcdev: + free_arcdev(dev); + break; + } + if (ret) + com20020pci_remove(pdev); return ret; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 456315bef3a8..74cbbb22470b 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3978,15 +3978,11 @@ static int bond_neigh_init(struct neighbour *n) rcu_read_lock(); slave = bond_first_slave_rcu(bond); - if (!slave) { - ret = -EINVAL; + if (!slave) goto out; - } slave_ops = slave->dev->netdev_ops; - if (!slave_ops->ndo_neigh_setup) { - ret = -EINVAL; + if (!slave_ops->ndo_neigh_setup) goto out; - } /* TODO: find another way [1] to implement this. * Passing a zeroed structure is fragile, diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index ef474bae47a1..6958830cb983 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -212,18 +212,6 @@ static const struct can_bittiming_const c_can_bittiming_const = { .brp_inc = 1, }; -static inline void c_can_pm_runtime_enable(const struct c_can_priv *priv) -{ - if (priv->device) - pm_runtime_enable(priv->device); -} - -static inline void c_can_pm_runtime_disable(const struct c_can_priv *priv) -{ - if (priv->device) - pm_runtime_disable(priv->device); -} - static inline void c_can_pm_runtime_get_sync(const struct c_can_priv *priv) { if (priv->device) @@ -1335,7 +1323,6 @@ static const struct net_device_ops c_can_netdev_ops = { int register_c_can_dev(struct net_device *dev) { - struct c_can_priv *priv = netdev_priv(dev); int err; /* Deactivate pins to prevent DRA7 DCAN IP from being @@ -1345,28 +1332,19 @@ int register_c_can_dev(struct net_device *dev) */ pinctrl_pm_select_sleep_state(dev->dev.parent); - c_can_pm_runtime_enable(priv); - dev->flags |= IFF_ECHO; /* we support local echo */ dev->netdev_ops = &c_can_netdev_ops; err = register_candev(dev); - if (err) - c_can_pm_runtime_disable(priv); - else + if (!err) devm_can_led_init(dev); - return err; } EXPORT_SYMBOL_GPL(register_c_can_dev); void unregister_c_can_dev(struct net_device *dev) { - struct c_can_priv *priv = netdev_priv(dev); - unregister_candev(dev); - - c_can_pm_runtime_disable(priv); } EXPORT_SYMBOL_GPL(unregister_c_can_dev); diff --git a/drivers/net/can/c_can/c_can_pci.c b/drivers/net/can/c_can/c_can_pci.c index 406b4847e5dc..7efb60b50876 100644 --- a/drivers/net/can/c_can/c_can_pci.c +++ b/drivers/net/can/c_can/c_can_pci.c @@ -239,12 +239,13 @@ static void c_can_pci_remove(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); struct c_can_priv *priv = netdev_priv(dev); + void __iomem *addr = priv->base; unregister_c_can_dev(dev); free_c_can_dev(dev); - pci_iounmap(pdev, priv->base); + pci_iounmap(pdev, addr); pci_disable_msi(pdev); pci_clear_master(pdev); pci_release_regions(pdev); diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c index 05f425ceb53a..47b251b1607c 100644 --- a/drivers/net/can/c_can/c_can_platform.c +++ b/drivers/net/can/c_can/c_can_platform.c @@ -29,6 +29,7 @@ #include <linux/list.h> #include <linux/io.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/clk.h> #include <linux/of.h> #include <linux/of_device.h> @@ -386,6 +387,7 @@ static int c_can_plat_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dev); SET_NETDEV_DEV(dev, &pdev->dev); + pm_runtime_enable(priv->device); ret = register_c_can_dev(dev); if (ret) { dev_err(&pdev->dev, "registering %s failed (err=%d)\n", @@ -398,6 +400,7 @@ static int c_can_plat_probe(struct platform_device *pdev) return 0; exit_free_device: + pm_runtime_disable(priv->device); free_c_can_dev(dev); exit: dev_err(&pdev->dev, "probe failed\n"); @@ -408,9 +411,10 @@ exit: static int c_can_plat_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); + struct c_can_priv *priv = netdev_priv(dev); unregister_c_can_dev(dev); - + pm_runtime_disable(priv->device); free_c_can_dev(dev); return 0; diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index 867f6be31230..f5d79e6e5483 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -355,6 +355,7 @@ static void can_dellink(struct net_device *dev, struct list_head *head) struct rtnl_link_ops can_link_ops __read_mostly = { .kind = "can", + .netns_refund = true, .maxtype = IFLA_CAN_MAX, .policy = can_policy, .setup = can_setup, diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 134c05757a3b..57f3635ad8d7 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -697,9 +697,15 @@ static int flexcan_chip_disable(struct flexcan_priv *priv) static int flexcan_chip_freeze(struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; - unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate; + unsigned int timeout; + u32 bitrate = priv->can.bittiming.bitrate; u32 reg; + if (bitrate) + timeout = 1000 * 1000 * 10 / bitrate; + else + timeout = FLEXCAN_TIMEOUT_US / 10; + reg = priv->read(®s->mcr); reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT; priv->write(reg, ®s->mcr); diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c index 37e05010ca91..74d9899fc904 100644 --- a/drivers/net/can/kvaser_pciefd.c +++ b/drivers/net/can/kvaser_pciefd.c @@ -57,6 +57,7 @@ MODULE_DESCRIPTION("CAN driver for Kvaser CAN/PCIe devices"); #define KVASER_PCIEFD_KCAN_STAT_REG 0x418 #define KVASER_PCIEFD_KCAN_MODE_REG 0x41c #define KVASER_PCIEFD_KCAN_BTRN_REG 0x420 +#define KVASER_PCIEFD_KCAN_BUS_LOAD_REG 0x424 #define KVASER_PCIEFD_KCAN_BTRD_REG 0x428 #define KVASER_PCIEFD_KCAN_PWM_REG 0x430 /* Loopback control register */ @@ -949,6 +950,9 @@ static int kvaser_pciefd_setup_can_ctrls(struct kvaser_pciefd *pcie) timer_setup(&can->bec_poll_timer, kvaser_pciefd_bec_poll_timer, 0); + /* Disable Bus load reporting */ + iowrite32(0, can->reg_base + KVASER_PCIEFD_KCAN_BUS_LOAD_REG); + tx_npackets = ioread32(can->reg_base + KVASER_PCIEFD_KCAN_TX_NPACKETS_REG); if (((tx_npackets >> KVASER_PCIEFD_KCAN_TX_NPACKETS_MAX_SHIFT) & diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index 3752520a7d4b..0c8d36bc668c 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -501,9 +501,6 @@ static int m_can_do_rx_poll(struct net_device *dev, int quota) } while ((rxfs & RXFS_FFL_MASK) && (quota > 0)) { - if (rxfs & RXFS_RFL) - netdev_warn(dev, "Rx FIFO 0 Message Lost\n"); - m_can_read_fifo(dev, rxfs); quota--; @@ -876,7 +873,7 @@ static int m_can_rx_peripheral(struct net_device *dev) { struct m_can_classdev *cdev = netdev_priv(dev); - m_can_rx_handler(dev, 1); + m_can_rx_handler(dev, M_CAN_NAPI_WEIGHT); m_can_enable_all_interrupts(cdev); diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index f69fb4238a65..a57da43680d8 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -314,6 +314,18 @@ static int mcp251x_spi_trans(struct spi_device *spi, int len) return ret; } +static int mcp251x_spi_write(struct spi_device *spi, int len) +{ + struct mcp251x_priv *priv = spi_get_drvdata(spi); + int ret; + + ret = spi_write(spi, priv->spi_tx_buf, len); + if (ret) + dev_err(&spi->dev, "spi write failed: ret = %d\n", ret); + + return ret; +} + static u8 mcp251x_read_reg(struct spi_device *spi, u8 reg) { struct mcp251x_priv *priv = spi_get_drvdata(spi); @@ -361,7 +373,7 @@ static void mcp251x_write_reg(struct spi_device *spi, u8 reg, u8 val) priv->spi_tx_buf[1] = reg; priv->spi_tx_buf[2] = val; - mcp251x_spi_trans(spi, 3); + mcp251x_spi_write(spi, 3); } static void mcp251x_write_2regs(struct spi_device *spi, u8 reg, u8 v1, u8 v2) @@ -373,7 +385,7 @@ static void mcp251x_write_2regs(struct spi_device *spi, u8 reg, u8 v1, u8 v2) priv->spi_tx_buf[2] = v1; priv->spi_tx_buf[3] = v2; - mcp251x_spi_trans(spi, 4); + mcp251x_spi_write(spi, 4); } static void mcp251x_write_bits(struct spi_device *spi, u8 reg, @@ -386,7 +398,7 @@ static void mcp251x_write_bits(struct spi_device *spi, u8 reg, priv->spi_tx_buf[2] = mask; priv->spi_tx_buf[3] = val; - mcp251x_spi_trans(spi, 4); + mcp251x_spi_write(spi, 4); } static u8 mcp251x_read_stat(struct spi_device *spi) @@ -618,7 +630,7 @@ static void mcp251x_hw_tx_frame(struct spi_device *spi, u8 *buf, buf[i]); } else { memcpy(priv->spi_tx_buf, buf, TXBDAT_OFF + len); - mcp251x_spi_trans(spi, TXBDAT_OFF + len); + mcp251x_spi_write(spi, TXBDAT_OFF + len); } } @@ -650,7 +662,7 @@ static void mcp251x_hw_tx(struct spi_device *spi, struct can_frame *frame, /* use INSTRUCTION_RTS, to avoid "repeated frame problem" */ priv->spi_tx_buf[0] = INSTRUCTION_RTS(1 << tx_buf_idx); - mcp251x_spi_trans(priv->spi, 1); + mcp251x_spi_write(priv->spi, 1); } static void mcp251x_hw_rx_frame(struct spi_device *spi, u8 *buf, @@ -888,7 +900,7 @@ static int mcp251x_hw_reset(struct spi_device *spi) mdelay(MCP251X_OST_DELAY_MS); priv->spi_tx_buf[0] = INSTRUCTION_RESET; - ret = mcp251x_spi_trans(spi, 1); + ret = mcp251x_spi_write(spi, 1); if (ret) return ret; diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig index c1e5d5b570b6..538f4d9adb91 100644 --- a/drivers/net/can/usb/Kconfig +++ b/drivers/net/can/usb/Kconfig @@ -73,6 +73,7 @@ config CAN_KVASER_USB - Kvaser Memorator Pro 5xHS - Kvaser USBcan Light 4xHS - Kvaser USBcan Pro 2xHS v2 + - Kvaser USBcan Pro 4xHS - Kvaser USBcan Pro 5xHS - Kvaser U100 - Kvaser U100P diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 2b7efd296758..4e97da8434ab 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -86,8 +86,9 @@ #define USB_U100_PRODUCT_ID 273 #define USB_U100P_PRODUCT_ID 274 #define USB_U100S_PRODUCT_ID 275 +#define USB_USBCAN_PRO_4HS_PRODUCT_ID 276 #define USB_HYDRA_PRODUCT_ID_END \ - USB_U100S_PRODUCT_ID + USB_USBCAN_PRO_4HS_PRODUCT_ID static inline bool kvaser_is_leaf(const struct usb_device_id *id) { @@ -193,6 +194,7 @@ static const struct usb_device_id kvaser_usb_table[] = { { USB_DEVICE(KVASER_VENDOR_ID, USB_U100_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_U100P_PRODUCT_ID) }, { USB_DEVICE(KVASER_VENDOR_ID, USB_U100S_PRODUCT_ID) }, + { USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_4HS_PRODUCT_ID) }, { } }; MODULE_DEVICE_TABLE(usb, kvaser_usb_table); diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index 573b11559d73..28e916a04047 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -857,7 +857,7 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, if (dev->adapter->dev_set_bus) { err = dev->adapter->dev_set_bus(dev, 0); if (err) - goto lbl_unregister_candev; + goto adap_dev_free; } /* get device number early */ @@ -869,6 +869,10 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter, return 0; +adap_dev_free: + if (dev->adapter->dev_free) + dev->adapter->dev_free(dev); + lbl_unregister_candev: unregister_candev(netdev); diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index a162499bcafc..eb443721c58e 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1105,13 +1105,6 @@ static int b53_setup(struct dsa_switch *ds) b53_disable_port(ds, port); } - /* Let DSA handle the case were multiple bridges span the same switch - * device and different VLAN awareness settings are requested, which - * would be breaking filtering semantics for any of the other bridge - * devices. (not hardware supported) - */ - ds->vlan_filtering_is_global = true; - return b53_setup_devlink_resources(ds); } @@ -2664,6 +2657,13 @@ struct b53_device *b53_switch_alloc(struct device *base, ds->ops = &b53_switch_ops; ds->untag_bridge_pvid = true; dev->vlan_enabled = true; + /* Let DSA handle the case were multiple bridges span the same switch + * device and different VLAN awareness settings are requested, which + * would be breaking filtering semantics for any of the other bridge + * devices. (not hardware supported) + */ + ds->vlan_filtering_is_global = true; + mutex_init(&dev->reg_mutex); mutex_init(&dev->stats_mutex); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index f277df922fcd..ba5d546d06aa 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -114,7 +114,10 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port) /* Force link status for IMP port */ reg = core_readl(priv, offset); reg |= (MII_SW_OR | LINK_STS); - reg &= ~GMII_SPEED_UP_2G; + if (priv->type == BCM4908_DEVICE_ID) + reg |= GMII_SPEED_UP_2G; + else + reg &= ~GMII_SPEED_UP_2G; core_writel(priv, reg, offset); /* Enable Broadcast, Multicast, Unicast forwarding to IMP port */ @@ -585,8 +588,10 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) * in bits 15:8 and the patch level in bits 7:0 which is exactly what * the REG_PHY_REVISION register layout is. */ - - return priv->hw_params.gphy_rev; + if (priv->int_phy_mask & BIT(port)) + return priv->hw_params.gphy_rev; + else + return 0; } static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port, diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 52e865a3912c..bf5c62e5c0b0 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -93,8 +93,12 @@ /* GSWIP MII Registers */ #define GSWIP_MII_CFGp(p) (0x2 * (p)) +#define GSWIP_MII_CFG_RESET BIT(15) #define GSWIP_MII_CFG_EN BIT(14) +#define GSWIP_MII_CFG_ISOLATE BIT(13) #define GSWIP_MII_CFG_LDCLKDIS BIT(12) +#define GSWIP_MII_CFG_RGMII_IBS BIT(8) +#define GSWIP_MII_CFG_RMII_CLK BIT(7) #define GSWIP_MII_CFG_MODE_MIIP 0x0 #define GSWIP_MII_CFG_MODE_MIIM 0x1 #define GSWIP_MII_CFG_MODE_RMIIP 0x2 @@ -190,6 +194,23 @@ #define GSWIP_PCE_DEFPVID(p) (0x486 + ((p) * 0xA)) #define GSWIP_MAC_FLEN 0x8C5 +#define GSWIP_MAC_CTRL_0p(p) (0x903 + ((p) * 0xC)) +#define GSWIP_MAC_CTRL_0_PADEN BIT(8) +#define GSWIP_MAC_CTRL_0_FCS_EN BIT(7) +#define GSWIP_MAC_CTRL_0_FCON_MASK 0x0070 +#define GSWIP_MAC_CTRL_0_FCON_AUTO 0x0000 +#define GSWIP_MAC_CTRL_0_FCON_RX 0x0010 +#define GSWIP_MAC_CTRL_0_FCON_TX 0x0020 +#define GSWIP_MAC_CTRL_0_FCON_RXTX 0x0030 +#define GSWIP_MAC_CTRL_0_FCON_NONE 0x0040 +#define GSWIP_MAC_CTRL_0_FDUP_MASK 0x000C +#define GSWIP_MAC_CTRL_0_FDUP_AUTO 0x0000 +#define GSWIP_MAC_CTRL_0_FDUP_EN 0x0004 +#define GSWIP_MAC_CTRL_0_FDUP_DIS 0x000C +#define GSWIP_MAC_CTRL_0_GMII_MASK 0x0003 +#define GSWIP_MAC_CTRL_0_GMII_AUTO 0x0000 +#define GSWIP_MAC_CTRL_0_GMII_MII 0x0001 +#define GSWIP_MAC_CTRL_0_GMII_RGMII 0x0002 #define GSWIP_MAC_CTRL_2p(p) (0x905 + ((p) * 0xC)) #define GSWIP_MAC_CTRL_2_MLEN BIT(3) /* Maximum Untagged Frame Lnegth */ @@ -653,16 +674,13 @@ static int gswip_port_enable(struct dsa_switch *ds, int port, GSWIP_SDMA_PCTRLp(port)); if (!dsa_is_cpu_port(ds, port)) { - u32 macconf = GSWIP_MDIO_PHY_LINK_AUTO | - GSWIP_MDIO_PHY_SPEED_AUTO | - GSWIP_MDIO_PHY_FDUP_AUTO | - GSWIP_MDIO_PHY_FCONTX_AUTO | - GSWIP_MDIO_PHY_FCONRX_AUTO | - (phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK); - - gswip_mdio_w(priv, macconf, GSWIP_MDIO_PHYp(port)); - /* Activate MDIO auto polling */ - gswip_mdio_mask(priv, 0, BIT(port), GSWIP_MDIO_MDC_CFG0); + u32 mdio_phy = 0; + + if (phydev) + mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK; + + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_ADDR_MASK, mdio_phy, + GSWIP_MDIO_PHYp(port)); } return 0; @@ -675,14 +693,6 @@ static void gswip_port_disable(struct dsa_switch *ds, int port) if (!dsa_is_user_port(ds, port)) return; - if (!dsa_is_cpu_port(ds, port)) { - gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_DOWN, - GSWIP_MDIO_PHY_LINK_MASK, - GSWIP_MDIO_PHYp(port)); - /* Deactivate MDIO auto polling */ - gswip_mdio_mask(priv, BIT(port), 0, GSWIP_MDIO_MDC_CFG0); - } - gswip_switch_mask(priv, GSWIP_FDMA_PCTRL_EN, 0, GSWIP_FDMA_PCTRLp(port)); gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0, @@ -794,14 +804,32 @@ static int gswip_setup(struct dsa_switch *ds) gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP2); gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP3); - /* disable PHY auto polling */ + /* Deactivate MDIO PHY auto polling. Some PHYs as the AR8030 have an + * interoperability problem with this auto polling mechanism because + * their status registers think that the link is in a different state + * than it actually is. For the AR8030 it has the BMSR_ESTATEN bit set + * as well as ESTATUS_1000_TFULL and ESTATUS_1000_XFULL. This makes the + * auto polling state machine consider the link being negotiated with + * 1Gbit/s. Since the PHY itself is a Fast Ethernet RMII PHY this leads + * to the switch port being completely dead (RX and TX are both not + * working). + * Also with various other PHY / port combinations (PHY11G GPHY, PHY22F + * GPHY, external RGMII PEF7071/7072) any traffic would stop. Sometimes + * it would work fine for a few minutes to hours and then stop, on + * other device it would no traffic could be sent or received at all. + * Testing shows that when PHY auto polling is disabled these problems + * go away. + */ gswip_mdio_w(priv, 0x0, GSWIP_MDIO_MDC_CFG0); + /* Configure the MDIO Clock 2.5 MHz */ gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1); - /* Disable the xMII link */ + /* Disable the xMII interface and clear it's isolation bit */ for (i = 0; i < priv->hw_info->max_ports; i++) - gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, i); + gswip_mii_mask_cfg(priv, + GSWIP_MII_CFG_EN | GSWIP_MII_CFG_ISOLATE, + 0, i); /* enable special tag insertion on cpu port */ gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN, @@ -1450,6 +1478,112 @@ unsupported: return; } +static void gswip_port_set_link(struct gswip_priv *priv, int port, bool link) +{ + u32 mdio_phy; + + if (link) + mdio_phy = GSWIP_MDIO_PHY_LINK_UP; + else + mdio_phy = GSWIP_MDIO_PHY_LINK_DOWN; + + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_MASK, mdio_phy, + GSWIP_MDIO_PHYp(port)); +} + +static void gswip_port_set_speed(struct gswip_priv *priv, int port, int speed, + phy_interface_t interface) +{ + u32 mdio_phy = 0, mii_cfg = 0, mac_ctrl_0 = 0; + + switch (speed) { + case SPEED_10: + mdio_phy = GSWIP_MDIO_PHY_SPEED_M10; + + if (interface == PHY_INTERFACE_MODE_RMII) + mii_cfg = GSWIP_MII_CFG_RATE_M50; + else + mii_cfg = GSWIP_MII_CFG_RATE_M2P5; + + mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII; + break; + + case SPEED_100: + mdio_phy = GSWIP_MDIO_PHY_SPEED_M100; + + if (interface == PHY_INTERFACE_MODE_RMII) + mii_cfg = GSWIP_MII_CFG_RATE_M50; + else + mii_cfg = GSWIP_MII_CFG_RATE_M25; + + mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII; + break; + + case SPEED_1000: + mdio_phy = GSWIP_MDIO_PHY_SPEED_G1; + + mii_cfg = GSWIP_MII_CFG_RATE_M125; + + mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_RGMII; + break; + } + + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_SPEED_MASK, mdio_phy, + GSWIP_MDIO_PHYp(port)); + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK, mii_cfg, port); + gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_GMII_MASK, mac_ctrl_0, + GSWIP_MAC_CTRL_0p(port)); +} + +static void gswip_port_set_duplex(struct gswip_priv *priv, int port, int duplex) +{ + u32 mac_ctrl_0, mdio_phy; + + if (duplex == DUPLEX_FULL) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_EN; + mdio_phy = GSWIP_MDIO_PHY_FDUP_EN; + } else { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_DIS; + mdio_phy = GSWIP_MDIO_PHY_FDUP_DIS; + } + + gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FDUP_MASK, mac_ctrl_0, + GSWIP_MAC_CTRL_0p(port)); + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_FDUP_MASK, mdio_phy, + GSWIP_MDIO_PHYp(port)); +} + +static void gswip_port_set_pause(struct gswip_priv *priv, int port, + bool tx_pause, bool rx_pause) +{ + u32 mac_ctrl_0, mdio_phy; + + if (tx_pause && rx_pause) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RXTX; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN | + GSWIP_MDIO_PHY_FCONRX_EN; + } else if (tx_pause) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_TX; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN | + GSWIP_MDIO_PHY_FCONRX_DIS; + } else if (rx_pause) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RX; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS | + GSWIP_MDIO_PHY_FCONRX_EN; + } else { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_NONE; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS | + GSWIP_MDIO_PHY_FCONRX_DIS; + } + + gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FCON_MASK, + mac_ctrl_0, GSWIP_MAC_CTRL_0p(port)); + gswip_mdio_mask(priv, + GSWIP_MDIO_PHY_FCONTX_MASK | + GSWIP_MDIO_PHY_FCONRX_MASK, + mdio_phy, GSWIP_MDIO_PHYp(port)); +} + static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, unsigned int mode, const struct phylink_link_state *state) @@ -1469,6 +1603,9 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, break; case PHY_INTERFACE_MODE_RMII: miicfg |= GSWIP_MII_CFG_MODE_RMIIM; + + /* Configure the RMII clock as output: */ + miicfg |= GSWIP_MII_CFG_RMII_CLK; break; case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: @@ -1481,7 +1618,11 @@ static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, "Unsupported interface: %d\n", state->interface); return; } - gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_MODE_MASK, miicfg, port); + + gswip_mii_mask_cfg(priv, + GSWIP_MII_CFG_MODE_MASK | GSWIP_MII_CFG_RMII_CLK | + GSWIP_MII_CFG_RGMII_IBS | GSWIP_MII_CFG_LDCLKDIS, + miicfg, port); switch (state->interface) { case PHY_INTERFACE_MODE_RGMII_ID: @@ -1506,6 +1647,9 @@ static void gswip_phylink_mac_link_down(struct dsa_switch *ds, int port, struct gswip_priv *priv = ds->priv; gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port); + + if (!dsa_is_cpu_port(ds, port)) + gswip_port_set_link(priv, port, false); } static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port, @@ -1517,6 +1661,13 @@ static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port, { struct gswip_priv *priv = ds->priv; + if (!dsa_is_cpu_port(ds, port)) { + gswip_port_set_link(priv, port, true); + gswip_port_set_speed(priv, port, speed, interface); + gswip_port_set_duplex(priv, port, duplex); + gswip_port_set_pause(priv, port, tx_pause, rx_pause); + } + gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port); } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index f06f5fa2f898..9871d7cff93a 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -436,34 +436,32 @@ mt7530_pad_clk_setup(struct dsa_switch *ds, phy_interface_t interface) TD_DM_DRVP(8) | TD_DM_DRVN(8)); /* Setup core clock for MT7530 */ - if (!trgint) { - /* Disable MT7530 core clock */ - core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); - - /* Disable PLL, since phy_device has not yet been created - * provided for phy_[read,write]_mmd_indirect is called, we - * provide our own core_write_mmd_indirect to complete this - * function. - */ - core_write_mmd_indirect(priv, - CORE_GSWPLL_GRP1, - MDIO_MMD_VEND2, - 0); - - /* Set core clock into 500Mhz */ - core_write(priv, CORE_GSWPLL_GRP2, - RG_GSWPLL_POSDIV_500M(1) | - RG_GSWPLL_FBKDIV_500M(25)); + /* Disable MT7530 core clock */ + core_clear(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); - /* Enable PLL */ - core_write(priv, CORE_GSWPLL_GRP1, - RG_GSWPLL_EN_PRE | - RG_GSWPLL_POSDIV_200M(2) | - RG_GSWPLL_FBKDIV_200M(32)); - - /* Enable MT7530 core clock */ - core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); - } + /* Disable PLL, since phy_device has not yet been created + * provided for phy_[read,write]_mmd_indirect is called, we + * provide our own core_write_mmd_indirect to complete this + * function. + */ + core_write_mmd_indirect(priv, + CORE_GSWPLL_GRP1, + MDIO_MMD_VEND2, + 0); + + /* Set core clock into 500Mhz */ + core_write(priv, CORE_GSWPLL_GRP2, + RG_GSWPLL_POSDIV_500M(1) | + RG_GSWPLL_FBKDIV_500M(25)); + + /* Enable PLL */ + core_write(priv, CORE_GSWPLL_GRP1, + RG_GSWPLL_EN_PRE | + RG_GSWPLL_POSDIV_200M(2) | + RG_GSWPLL_FBKDIV_200M(32)); + + /* Enable MT7530 core clock */ + core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); /* Setup the MT7530 TRGMII Tx Clock */ core_set(priv, CORE_TRGMII_GSW_CLK_CG, REG_GSWCK_EN); diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 903d619e08ed..e08bf9377140 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3026,10 +3026,17 @@ out_resources: return err; } +/* prod_id for switch families which do not have a PHY model number */ +static const u16 family_prod_id_table[] = { + [MV88E6XXX_FAMILY_6341] = MV88E6XXX_PORT_SWITCH_ID_PROD_6341, + [MV88E6XXX_FAMILY_6390] = MV88E6XXX_PORT_SWITCH_ID_PROD_6390, +}; + static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg) { struct mv88e6xxx_mdio_bus *mdio_bus = bus->priv; struct mv88e6xxx_chip *chip = mdio_bus->chip; + u16 prod_id; u16 val; int err; @@ -3040,23 +3047,12 @@ static int mv88e6xxx_mdio_read(struct mii_bus *bus, int phy, int reg) err = chip->info->ops->phy_read(chip, bus, phy, reg, &val); mv88e6xxx_reg_unlock(chip); - if (reg == MII_PHYSID2) { - /* Some internal PHYs don't have a model number. */ - if (chip->info->family != MV88E6XXX_FAMILY_6165) - /* Then there is the 6165 family. It gets is - * PHYs correct. But it can also have two - * SERDES interfaces in the PHY address - * space. And these don't have a model - * number. But they are not PHYs, so we don't - * want to give them something a PHY driver - * will recognise. - * - * Use the mv88e6390 family model number - * instead, for anything which really could be - * a PHY, - */ - if (!(val & 0x3f0)) - val |= MV88E6XXX_PORT_SWITCH_ID_PROD_6390 >> 4; + /* Some internal PHYs don't have a model number. */ + if (reg == MII_PHYSID2 && !(val & 0x3f0) && + chip->info->family < ARRAY_SIZE(family_prod_id_table)) { + prod_id = family_prod_id_table[chip->info->family]; + if (prod_id) + val |= prod_id >> 4; } return err ? err : val; diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index 187b0b9a6e1d..f78daba60b35 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1534,8 +1534,7 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent) } pci_set_master(pdev); - ioaddr = pci_resource_start(pdev, 0); - if (!ioaddr) { + if (!pci_resource_len(pdev, 0)) { if (pcnet32_debug & NETIF_MSG_PROBE) pr_err("card has no PCI IO resources, aborting\n"); err = -ENODEV; @@ -1548,6 +1547,8 @@ pcnet32_probe_pci(struct pci_dev *pdev, const struct pci_device_id *ent) pr_err("architecture does not support 32bit PCI busmaster DMA\n"); goto err_disable_dev; } + + ioaddr = pci_resource_start(pdev, 0); if (!request_region(ioaddr, PCNET32_TOTAL_SIZE, "pcnet32_probe_pci")) { if (pcnet32_debug & NETIF_MSG_PROBE) pr_err("io address range already allocated\n"); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index ba8321ec1ee7..3305979a9f7c 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -180,9 +180,9 @@ #define XGBE_DMA_SYS_AWCR 0x30303030 /* DMA cache settings - PCI device */ -#define XGBE_DMA_PCI_ARCR 0x00000003 -#define XGBE_DMA_PCI_AWCR 0x13131313 -#define XGBE_DMA_PCI_AWARCR 0x00000313 +#define XGBE_DMA_PCI_ARCR 0x000f0f0f +#define XGBE_DMA_PCI_AWCR 0x0f0f0f0f +#define XGBE_DMA_PCI_AWARCR 0x00000f0f /* DMA channel interrupt modes */ #define XGBE_IRQ_MODE_EDGE 0 diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index f8a168b73307..cb88ffb8f12f 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -54,7 +54,7 @@ config B44_PCI config BCM4908_ENET tristate "Broadcom BCM4908 internal mac support" depends on ARCH_BCM4908 || COMPILE_TEST - default y + default y if ARCH_BCM4908 help This driver supports Ethernet controller integrated into Broadcom BCM4908 family SoCs. diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c index 98cf82dea3e4..65981931a798 100644 --- a/drivers/net/ethernet/broadcom/bcm4908_enet.c +++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c @@ -172,6 +172,7 @@ static int bcm4908_dma_alloc_buf_descs(struct bcm4908_enet *enet, err_free_buf_descs: dma_free_coherent(dev, size, ring->cpu_addr, ring->dma_addr); + ring->cpu_addr = NULL; return -ENOMEM; } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 15362d016a87..0f6a6cb7e98d 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -3239,6 +3239,9 @@ static void gem_prog_cmp_regs(struct macb *bp, struct ethtool_rx_flow_spec *fs) bool cmp_b = false; bool cmp_c = false; + if (!macb_is_gem(bp)) + return; + tp4sp_v = &(fs->h_u.tcp_ip4_spec); tp4sp_m = &(fs->m_u.tcp_ip4_spec); @@ -3607,6 +3610,7 @@ static void macb_restore_features(struct macb *bp) { struct net_device *netdev = bp->dev; netdev_features_t features = netdev->features; + struct ethtool_rx_fs_item *item; /* TX checksum offload */ macb_set_txcsum_feature(bp, features); @@ -3615,6 +3619,9 @@ static void macb_restore_features(struct macb *bp) macb_set_rxcsum_feature(bp, features); /* RX Flow Filters */ + list_for_each_entry(item, &bp->rx_fs_list.list, list) + gem_prog_cmp_regs(bp, &item->fs); + macb_set_rxflow_feature(bp, features); } @@ -3911,6 +3918,7 @@ static int macb_init(struct platform_device *pdev) reg = gem_readl(bp, DCFG8); bp->max_tuples = min((GEM_BFEXT(SCR2CMP, reg) / 3), GEM_BFEXT(T2SCR, reg)); + INIT_LIST_HEAD(&bp->rx_fs_list.list); if (bp->max_tuples > 0) { /* also needs one ethtype match to check IPv4 */ if (GEM_BFEXT(SCR2ETH, reg) > 0) { @@ -3921,7 +3929,6 @@ static int macb_init(struct platform_device *pdev) /* Filtering is supported in hw but don't enable it in kernel now */ dev->hw_features |= NETIF_F_NTUPLE; /* init Rx flow definitions */ - INIT_LIST_HEAD(&bp->rx_fs_list.list); bp->rx_fs_list.count = 0; spin_lock_init(&bp->rx_fs_lock); } else diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h b/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h index b248966837b4..7aad40b2aa73 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h +++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_regs.h @@ -412,7 +412,7 @@ | CN6XXX_INTR_M0UNWI_ERR \ | CN6XXX_INTR_M1UPB0_ERR \ | CN6XXX_INTR_M1UPWI_ERR \ - | CN6XXX_INTR_M1UPB0_ERR \ + | CN6XXX_INTR_M1UNB0_ERR \ | CN6XXX_INTR_M1UNWI_ERR \ | CN6XXX_INTR_INSTR_DB_OF_ERR \ | CN6XXX_INTR_SLIST_DB_OF_ERR \ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index 6c85a10f465c..23a2ebdfd503 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -1794,11 +1794,25 @@ int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init, struct cudbg_buffer temp_buff = { 0 }; struct sge_qbase_reg_field *sge_qbase; struct ireg_buf *ch_sge_dbg; + u8 padap_running = 0; int i, rc; + u32 size; - rc = cudbg_get_buff(pdbg_init, dbg_buff, - sizeof(*ch_sge_dbg) * 2 + sizeof(*sge_qbase), - &temp_buff); + /* Accessing SGE_QBASE_MAP[0-3] and SGE_QBASE_INDEX regs can + * lead to SGE missing doorbells under heavy traffic. So, only + * collect them when adapter is idle. + */ + for_each_port(padap, i) { + padap_running = netif_running(padap->port[i]); + if (padap_running) + break; + } + + size = sizeof(*ch_sge_dbg) * 2; + if (!padap_running) + size += sizeof(*sge_qbase); + + rc = cudbg_get_buff(pdbg_init, dbg_buff, size, &temp_buff); if (rc) return rc; @@ -1820,7 +1834,8 @@ int cudbg_collect_sge_indirect(struct cudbg_init *pdbg_init, ch_sge_dbg++; } - if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5) { + if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5 && + !padap_running) { sge_qbase = (struct sge_qbase_reg_field *)ch_sge_dbg; /* 1 addr reg SGE_QBASE_INDEX and 4 data reg * SGE_QBASE_MAP[0-3] diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 98829e482bfa..80882cfc370f 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -2090,7 +2090,8 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) 0x1190, 0x1194, 0x11a0, 0x11a4, 0x11b0, 0x11b4, - 0x11fc, 0x1274, + 0x11fc, 0x123c, + 0x1254, 0x1274, 0x1280, 0x133c, 0x1800, 0x18fc, 0x3000, 0x302c, diff --git a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c index 169e10c91378..a3f5b80888e5 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/ch_ktls/chcr_ktls.c @@ -350,18 +350,6 @@ static int chcr_set_tcb_field(struct chcr_ktls_info *tx_info, u16 word, } /* - * chcr_ktls_mark_tcb_close: mark tcb state to CLOSE - * @tx_info - driver specific tls info. - * return: NET_TX_OK/NET_XMIT_DROP. - */ -static int chcr_ktls_mark_tcb_close(struct chcr_ktls_info *tx_info) -{ - return chcr_set_tcb_field(tx_info, TCB_T_STATE_W, - TCB_T_STATE_V(TCB_T_STATE_M), - CHCR_TCB_STATE_CLOSED, 1); -} - -/* * chcr_ktls_dev_del: call back for tls_dev_del. * Remove the tid and l2t entry and close the connection. * it per connection basis. @@ -395,8 +383,6 @@ static void chcr_ktls_dev_del(struct net_device *netdev, /* clear tid */ if (tx_info->tid != -1) { - /* clear tcb state and then release tid */ - chcr_ktls_mark_tcb_close(tx_info); cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, tx_info->tid, tx_info->ip_family); } @@ -574,7 +560,6 @@ static int chcr_ktls_dev_add(struct net_device *netdev, struct sock *sk, return 0; free_tid: - chcr_ktls_mark_tcb_close(tx_info); #if IS_ENABLED(CONFIG_IPV6) /* clear clip entry */ if (tx_info->ip_family == AF_INET6) @@ -672,10 +657,6 @@ static int chcr_ktls_cpl_act_open_rpl(struct adapter *adap, if (tx_info->pending_close) { spin_unlock(&tx_info->lock); if (!status) { - /* it's a late success, tcb status is established, - * mark it close. - */ - chcr_ktls_mark_tcb_close(tx_info); cxgb4_remove_tid(&tx_info->adap->tids, tx_info->tx_chan, tid, tx_info->ip_family); } @@ -722,7 +703,7 @@ static int chcr_ktls_cpl_set_tcb_rpl(struct adapter *adap, unsigned char *input) kvfree(tx_info); return 0; } - tx_info->open_state = false; + tx_info->open_state = CH_KTLS_OPEN_SUCCESS; spin_unlock(&tx_info->lock); complete(&tx_info->completion); @@ -1664,54 +1645,6 @@ static void chcr_ktls_copy_record_in_skb(struct sk_buff *nskb, } /* - * chcr_ktls_update_snd_una: Reset the SEND_UNA. It will be done to avoid - * sending the same segment again. It will discard the segment which is before - * the current tx max. - * @tx_info - driver specific tls info. - * @q - TX queue. - * return: NET_TX_OK/NET_XMIT_DROP. - */ -static int chcr_ktls_update_snd_una(struct chcr_ktls_info *tx_info, - struct sge_eth_txq *q) -{ - struct fw_ulptx_wr *wr; - unsigned int ndesc; - int credits; - void *pos; - u32 len; - - len = sizeof(*wr) + roundup(CHCR_SET_TCB_FIELD_LEN, 16); - ndesc = DIV_ROUND_UP(len, 64); - - credits = chcr_txq_avail(&q->q) - ndesc; - if (unlikely(credits < 0)) { - chcr_eth_txq_stop(q); - return NETDEV_TX_BUSY; - } - - pos = &q->q.desc[q->q.pidx]; - - wr = pos; - /* ULPTX wr */ - wr->op_to_compl = htonl(FW_WR_OP_V(FW_ULPTX_WR)); - wr->cookie = 0; - /* fill len in wr field */ - wr->flowid_len16 = htonl(FW_WR_LEN16_V(DIV_ROUND_UP(len, 16))); - - pos += sizeof(*wr); - - pos = chcr_write_cpl_set_tcb_ulp(tx_info, q, tx_info->tid, pos, - TCB_SND_UNA_RAW_W, - TCB_SND_UNA_RAW_V(TCB_SND_UNA_RAW_M), - TCB_SND_UNA_RAW_V(0), 0); - - chcr_txq_advance(&q->q, ndesc); - cxgb4_ring_tx_db(tx_info->adap, &q->q, ndesc); - - return 0; -} - -/* * chcr_end_part_handler: This handler will handle the record which * is complete or if record's end part is received. T6 adapter has a issue that * it can't send out TAG with partial record so if its an end part then we have @@ -1735,7 +1668,9 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info, struct sge_eth_txq *q, u32 skb_offset, u32 tls_end_offset, bool last_wr) { + bool free_skb_if_tx_fails = false; struct sk_buff *nskb = NULL; + /* check if it is a complete record */ if (tls_end_offset == record->len) { nskb = skb; @@ -1758,6 +1693,8 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info, if (last_wr) dev_kfree_skb_any(skb); + else + free_skb_if_tx_fails = true; last_wr = true; @@ -1769,6 +1706,8 @@ static int chcr_end_part_handler(struct chcr_ktls_info *tx_info, record->num_frags, (last_wr && tcp_push_no_fin), mss)) { + if (free_skb_if_tx_fails) + dev_kfree_skb_any(skb); goto out; } tx_info->prev_seq = record->end_seq; @@ -1905,11 +1844,6 @@ static int chcr_short_record_handler(struct chcr_ktls_info *tx_info, /* reset tcp_seq as per the prior_data_required len */ tcp_seq -= prior_data_len; } - /* reset snd una, so the middle record won't send the already - * sent part. - */ - if (chcr_ktls_update_snd_una(tx_info, q)) - goto out; atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_middle_pkts); } else { atomic64_inc(&tx_info->adap->ch_ktls_stats.ktls_tx_start_pkts); @@ -2010,12 +1944,11 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) * we will send the complete record again. */ + spin_lock_irqsave(&tx_ctx->base.lock, flags); + do { - int i; cxgb4_reclaim_completed_tx(adap, &q->q, true); - /* lock taken */ - spin_lock_irqsave(&tx_ctx->base.lock, flags); /* fetch the tls record */ record = tls_get_record(&tx_ctx->base, tcp_seq, &tx_info->record_no); @@ -2074,11 +2007,11 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) tls_end_offset, skb_offset, 0); - spin_unlock_irqrestore(&tx_ctx->base.lock, flags); if (ret) { /* free the refcount taken earlier */ if (tls_end_offset < data_len) dev_kfree_skb_any(skb); + spin_unlock_irqrestore(&tx_ctx->base.lock, flags); goto out; } @@ -2088,16 +2021,6 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) continue; } - /* increase page reference count of the record, so that there - * won't be any chance of page free in middle if in case stack - * receives ACK and try to delete the record. - */ - for (i = 0; i < record->num_frags; i++) - __skb_frag_ref(&record->frags[i]); - /* lock cleared */ - spin_unlock_irqrestore(&tx_ctx->base.lock, flags); - - /* if a tls record is finishing in this SKB */ if (tls_end_offset <= data_len) { ret = chcr_end_part_handler(tx_info, skb, record, @@ -2122,13 +2045,9 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) data_len = 0; } - /* clear the frag ref count which increased locally before */ - for (i = 0; i < record->num_frags; i++) { - /* clear the frag ref count */ - __skb_frag_unref(&record->frags[i]); - } /* if any failure, come out from the loop. */ if (ret) { + spin_unlock_irqrestore(&tx_ctx->base.lock, flags); if (th->fin) dev_kfree_skb_any(skb); @@ -2143,6 +2062,7 @@ static int chcr_ktls_xmit(struct sk_buff *skb, struct net_device *dev) } while (data_len > 0); + spin_unlock_irqrestore(&tx_ctx->base.lock, flags); atomic64_inc(&port_stats->ktls_tx_encrypted_packets); atomic64_add(skb_data_len, &port_stats->ktls_tx_encrypted_bytes); diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 252adfa5d837..8a9096aa85cd 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1471,8 +1471,10 @@ dm9000_probe(struct platform_device *pdev) /* Init network device */ ndev = alloc_etherdev(sizeof(struct board_info)); - if (!ndev) - return -ENOMEM; + if (!ndev) { + ret = -ENOMEM; + goto out_regulator_disable; + } SET_NETDEV_DEV(ndev, &pdev->dev); diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 88bfe2107938..04421aec2dfd 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1337,6 +1337,7 @@ static int ftgmac100_poll(struct napi_struct *napi, int budget) */ if (unlikely(priv->need_mac_restart)) { ftgmac100_start_hw(priv); + priv->need_mac_restart = false; /* Re-enable "bad" interrupts */ iowrite32(FTGMAC100_INT_BAD, diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 1cf8ef717453..3ec4d9fddd52 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -363,7 +363,11 @@ static void gfar_set_mac_for_addr(struct net_device *dev, int num, static int gfar_set_mac_addr(struct net_device *dev, void *p) { - eth_mac_addr(dev, p); + int ret; + + ret = eth_mac_addr(dev, p); + if (ret) + return ret; gfar_set_mac_for_addr(dev, 0, dev->dev_addr); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index e3f81c7e0ce7..b0dbe6dcaa7b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3966,7 +3966,6 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle) * normalcy is to reset. * 2. A new reset request from the stack due to timeout * - * For the first case,error event might not have ae handle available. * check if this is a new reset request and we are not here just because * last reset attempt did not succeed and watchdog hit us again. We will * know this if last reset request did not occur very recently (watchdog @@ -3976,14 +3975,14 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle) * want to make sure we throttle the reset request. Therefore, we will * not allow it again before 3*HZ times. */ - if (!handle) - handle = &hdev->vport[0].nic; if (time_before(jiffies, (hdev->last_reset_time + HCLGE_RESET_INTERVAL))) { mod_timer(&hdev->reset_timer, jiffies + HCLGE_RESET_INTERVAL); return; - } else if (hdev->default_reset_request) { + } + + if (hdev->default_reset_request) { hdev->reset_level = hclge_get_reset_level(ae_dev, &hdev->default_reset_request); @@ -11211,7 +11210,7 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num, if (ret) return ret; - /* RSS indirection table has been configuared by user */ + /* RSS indirection table has been configured by user */ if (rxfh_configured) goto out; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 700e068764c8..e295d359e912 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2193,7 +2193,7 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev) if (test_and_clear_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state)) { - /* PF has initmated that it is about to reset the hardware. + /* PF has intimated that it is about to reset the hardware. * We now have to poll & check if hardware has actually * completed the reset sequence. On hardware reset completion, * VF needs to reset the client and ae device. @@ -2624,14 +2624,14 @@ static int hclgevf_ae_start(struct hnae3_handle *handle) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + clear_bit(HCLGEVF_STATE_DOWN, &hdev->state); + hclgevf_reset_tqp_stats(handle); hclgevf_request_link_info(hdev); hclgevf_update_link_mode(hdev); - clear_bit(HCLGEVF_STATE_DOWN, &hdev->state); - return 0; } @@ -3497,7 +3497,7 @@ static int hclgevf_set_channels(struct hnae3_handle *handle, u32 new_tqps_num, if (ret) return ret; - /* RSS indirection table has been configuared by user */ + /* RSS indirection table has been configured by user */ if (rxfh_configured) goto out; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 9c6438d3b3a5..ffb2a91750c7 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1149,19 +1149,13 @@ static int __ibmvnic_open(struct net_device *netdev) rc = set_link_state(adapter, IBMVNIC_LOGICAL_LNK_UP); if (rc) { - for (i = 0; i < adapter->req_rx_queues; i++) - napi_disable(&adapter->napi[i]); + ibmvnic_napi_disable(adapter); release_resources(adapter); return rc; } netif_tx_start_all_queues(netdev); - if (prev_state == VNIC_CLOSED) { - for (i = 0; i < adapter->req_rx_queues; i++) - napi_schedule(&adapter->napi[i]); - } - adapter->state = VNIC_OPEN; return rc; } @@ -1922,7 +1916,7 @@ static int do_reset(struct ibmvnic_adapter *adapter, u64 old_num_rx_queues, old_num_tx_queues; u64 old_num_rx_slots, old_num_tx_slots; struct net_device *netdev = adapter->netdev; - int i, rc; + int rc; netdev_dbg(adapter->netdev, "[S:%d FOP:%d] Reset reason %d, reset_state %d\n", @@ -2111,10 +2105,6 @@ static int do_reset(struct ibmvnic_adapter *adapter, /* refresh device's multicast list */ ibmvnic_set_multi(netdev); - /* kick napi */ - for (i = 0; i < adapter->req_rx_queues; i++) - napi_schedule(&adapter->napi[i]); - if (adapter->reset_reason == VNIC_RESET_FAILOVER || adapter->reset_reason == VNIC_RESET_MOBILITY) __netdev_notify_peers(netdev); @@ -3204,9 +3194,6 @@ restart_loop: next = ibmvnic_next_scrq(adapter, scrq); for (i = 0; i < next->tx_comp.num_comps; i++) { - if (next->tx_comp.rcs[i]) - dev_err(dev, "tx error %x\n", - next->tx_comp.rcs[i]); index = be32_to_cpu(next->tx_comp.correlators[i]); if (index & IBMVNIC_TSO_POOL_MASK) { tx_pool = &adapter->tso_pool[pool]; @@ -3220,7 +3207,13 @@ restart_loop: num_entries += txbuff->num_entries; if (txbuff->skb) { total_bytes += txbuff->skb->len; - dev_consume_skb_irq(txbuff->skb); + if (next->tx_comp.rcs[i]) { + dev_err(dev, "tx error %x\n", + next->tx_comp.rcs[i]); + dev_kfree_skb_irq(txbuff->skb); + } else { + dev_consume_skb_irq(txbuff->skb); + } txbuff->skb = NULL; } else { netdev_warn(adapter->netdev, diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 88faf05e23ba..0b1e890dd583 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -899,6 +899,8 @@ static s32 e1000_set_d0_lplu_state_82571(struct e1000_hw *hw, bool active) } else { data &= ~IGP02E1000_PM_D0_LPLU; ret_val = e1e_wphy(hw, IGP02E1000_PHY_POWER_MGMT, data); + if (ret_val) + return ret_val; /* LPLU and SmartSpeed are mutually exclusive. LPLU is used * during Dx states where the power conservation is most * important. During driver activity we should enable diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 69a2329ea463..db79c4e6413e 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 1999 - 2018 Intel Corporation. */ -#ifndef _E1000_HW_H_ -#define _E1000_HW_H_ +#ifndef _E1000E_HW_H_ +#define _E1000E_HW_H_ #include "regs.h" #include "defines.h" @@ -714,4 +714,4 @@ struct e1000_hw { #include "80003es2lan.h" #include "ich8lan.h" -#endif +#endif /* _E1000E_HW_H_ */ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e9b82c209c2d..a0948002ddf8 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5974,15 +5974,19 @@ static void e1000_reset_task(struct work_struct *work) struct e1000_adapter *adapter; adapter = container_of(work, struct e1000_adapter, reset_task); + rtnl_lock(); /* don't run the task if already down */ - if (test_bit(__E1000_DOWN, &adapter->state)) + if (test_bit(__E1000_DOWN, &adapter->state)) { + rtnl_unlock(); return; + } if (!(adapter->flags & FLAG_RESTART_NOW)) { e1000e_dump(adapter); e_err("Reset adapter unexpectedly\n"); } e1000e_reinit_locked(adapter); + rtnl_unlock(); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index cd53981fa5e0..15f93b355099 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -142,6 +142,7 @@ enum i40e_state_t { __I40E_VIRTCHNL_OP_PENDING, __I40E_RECOVERY_MODE, __I40E_VF_RESETS_DISABLED, /* disable resets during i40e_remove */ + __I40E_VFS_RELEASING, /* This must be last as it determines the size of the BITMAP */ __I40E_STATE_SIZE__, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index d7c13ca9be7d..d627b59ad446 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -578,6 +578,9 @@ static void i40e_dbg_dump_desc(int cnt, int vsi_seid, int ring_id, int desc_n, case RING_TYPE_XDP: ring = kmemdup(vsi->xdp_rings[ring_id], sizeof(*ring), GFP_KERNEL); break; + default: + ring = NULL; + break; } if (!ring) return; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index c70dec65a572..0e92668012e3 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -232,6 +232,8 @@ static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[], I40E_STAT(struct i40e_vsi, _name, _stat) #define I40E_VEB_STAT(_name, _stat) \ I40E_STAT(struct i40e_veb, _name, _stat) +#define I40E_VEB_TC_STAT(_name, _stat) \ + I40E_STAT(struct i40e_cp_veb_tc_stats, _name, _stat) #define I40E_PFC_STAT(_name, _stat) \ I40E_STAT(struct i40e_pfc_stats, _name, _stat) #define I40E_QUEUE_STAT(_name, _stat) \ @@ -266,11 +268,18 @@ static const struct i40e_stats i40e_gstrings_veb_stats[] = { I40E_VEB_STAT("veb.rx_unknown_protocol", stats.rx_unknown_protocol), }; +struct i40e_cp_veb_tc_stats { + u64 tc_rx_packets; + u64 tc_rx_bytes; + u64 tc_tx_packets; + u64 tc_tx_bytes; +}; + static const struct i40e_stats i40e_gstrings_veb_tc_stats[] = { - I40E_VEB_STAT("veb.tc_%u_tx_packets", tc_stats.tc_tx_packets), - I40E_VEB_STAT("veb.tc_%u_tx_bytes", tc_stats.tc_tx_bytes), - I40E_VEB_STAT("veb.tc_%u_rx_packets", tc_stats.tc_rx_packets), - I40E_VEB_STAT("veb.tc_%u_rx_bytes", tc_stats.tc_rx_bytes), + I40E_VEB_TC_STAT("veb.tc_%u_tx_packets", tc_tx_packets), + I40E_VEB_TC_STAT("veb.tc_%u_tx_bytes", tc_tx_bytes), + I40E_VEB_TC_STAT("veb.tc_%u_rx_packets", tc_rx_packets), + I40E_VEB_TC_STAT("veb.tc_%u_rx_bytes", tc_rx_bytes), }; static const struct i40e_stats i40e_gstrings_misc_stats[] = { @@ -1101,6 +1110,7 @@ static int i40e_get_link_ksettings(struct net_device *netdev, /* Set flow control settings */ ethtool_link_ksettings_add_link_mode(ks, supported, Pause); + ethtool_link_ksettings_add_link_mode(ks, supported, Asym_Pause); switch (hw->fc.requested_mode) { case I40E_FC_FULL: @@ -2217,6 +2227,29 @@ static int i40e_get_sset_count(struct net_device *netdev, int sset) } /** + * i40e_get_veb_tc_stats - copy VEB TC statistics to formatted structure + * @tc: the TC statistics in VEB structure (veb->tc_stats) + * @i: the index of traffic class in (veb->tc_stats) structure to copy + * + * Copy VEB TC statistics from structure of arrays (veb->tc_stats) to + * one dimensional structure i40e_cp_veb_tc_stats. + * Produce formatted i40e_cp_veb_tc_stats structure of the VEB TC + * statistics for the given TC. + **/ +static struct i40e_cp_veb_tc_stats +i40e_get_veb_tc_stats(struct i40e_veb_tc_stats *tc, unsigned int i) +{ + struct i40e_cp_veb_tc_stats veb_tc = { + .tc_rx_packets = tc->tc_rx_packets[i], + .tc_rx_bytes = tc->tc_rx_bytes[i], + .tc_tx_packets = tc->tc_tx_packets[i], + .tc_tx_bytes = tc->tc_tx_bytes[i], + }; + + return veb_tc; +} + +/** * i40e_get_pfc_stats - copy HW PFC statistics to formatted structure * @pf: the PF device structure * @i: the priority value to copy @@ -2300,8 +2333,16 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, i40e_gstrings_veb_stats); for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) - i40e_add_ethtool_stats(&data, veb_stats ? veb : NULL, - i40e_gstrings_veb_tc_stats); + if (veb_stats) { + struct i40e_cp_veb_tc_stats veb_tc = + i40e_get_veb_tc_stats(&veb->tc_stats, i); + + i40e_add_ethtool_stats(&data, &veb_tc, + i40e_gstrings_veb_tc_stats); + } else { + i40e_add_ethtool_stats(&data, NULL, + i40e_gstrings_veb_tc_stats); + } i40e_add_ethtool_stats(&data, pf, i40e_gstrings_stats); @@ -5439,7 +5480,7 @@ static int i40e_get_module_eeprom(struct net_device *netdev, status = i40e_aq_get_phy_register(hw, I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, - true, addr, offset, &value, NULL); + addr, true, offset, &value, NULL); if (status) return -EIO; data[i] = value; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 353deae139f9..527023ee4c07 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2560,8 +2560,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) i40e_stat_str(hw, aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); } else { - dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n", - vsi->netdev->name, + dev_info(&pf->pdev->dev, "%s allmulti mode.\n", cur_multipromisc ? "entering" : "leaving"); } } @@ -3259,6 +3258,17 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) } /** + * i40e_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; +} + +/** * i40e_configure_rx_ring - Configure a receive ring context * @ring: The Rx ring to configure * @@ -3369,6 +3379,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) else set_ring_build_skb_enabled(ring); + ring->rx_offset = i40e_rx_offset(ring); + /* cache tail for quicker writes, and clear the reg before use */ ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); @@ -6725,9 +6737,9 @@ out: set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state); set_bit(__I40E_CLIENT_L2_CHANGE, pf->state); } - /* registers are set, lets apply */ - if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB) - ret = i40e_hw_set_dcb_config(pf, new_cfg); + /* registers are set, lets apply */ + if (pf->hw_features & I40E_HW_USE_SET_LLDP_MIB) + ret = i40e_hw_set_dcb_config(pf, new_cfg); } err: @@ -10560,12 +10572,6 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) goto end_core_reset; } - if (!lock_acquired) - rtnl_lock(); - ret = i40e_setup_pf_switch(pf, reinit); - if (ret) - goto end_unlock; - #ifdef CONFIG_I40E_DCB /* Enable FW to write a default DCB config on link-up * unless I40E_FLAG_TC_MQPRIO was enabled or DCB @@ -10580,7 +10586,7 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) i40e_aq_set_dcb_parameters(hw, false, NULL); dev_warn(&pf->pdev->dev, "DCB is not supported for X710-T*L 2.5/5G speeds\n"); - pf->flags &= ~I40E_FLAG_DCB_CAPABLE; + pf->flags &= ~I40E_FLAG_DCB_CAPABLE; } else { i40e_aq_set_dcb_parameters(hw, true, NULL); ret = i40e_init_pf_dcb(pf); @@ -10594,6 +10600,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) } #endif /* CONFIG_I40E_DCB */ + if (!lock_acquired) + rtnl_lock(); + ret = i40e_setup_pf_switch(pf, reinit); + if (ret) + goto end_unlock; /* The driver only wants link up/down and module qualification * reports from firmware. Note the negative logic. @@ -12346,6 +12357,7 @@ static int i40e_sw_init(struct i40e_pf *pf) { int err = 0; int size; + u16 pow; /* Set default capability flags */ pf->flags = I40E_FLAG_RX_CSUM_ENABLED | @@ -12364,6 +12376,11 @@ static int i40e_sw_init(struct i40e_pf *pf) pf->rss_table_size = pf->hw.func_caps.rss_table_size; pf->rss_size_max = min_t(int, pf->rss_size_max, pf->hw.func_caps.num_tx_qp); + + /* find the next higher power-of-2 of num cpus */ + pow = roundup_pow_of_two(num_online_cpus()); + pf->rss_size_max = min_t(int, pf->rss_size_max, pow); + if (pf->hw.func_caps.rss) { pf->flags |= I40E_FLAG_RSS_ENABLED; pf->alloc_rss_size = min_t(int, pf->rss_size_max, @@ -15127,12 +15144,16 @@ static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw) * in order to register the netdev */ v_idx = i40e_vsi_mem_alloc(pf, I40E_VSI_MAIN); - if (v_idx < 0) + if (v_idx < 0) { + err = v_idx; goto err_switch_setup; + } pf->lan_vsi = v_idx; vsi = pf->vsi[v_idx]; - if (!vsi) + if (!vsi) { + err = -EFAULT; goto err_switch_setup; + } vsi->alloc_queue_pairs = 1; err = i40e_config_netdev(vsi); if (err) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 627794b31e33..06b4271219b1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1570,17 +1570,6 @@ void i40e_free_rx_resources(struct i40e_ring *rx_ring) } /** - * i40e_rx_offset - Return expected offset into page to access data - * @rx_ring: Ring we are requesting offset of - * - * Returns the offset value for ring into the data buffer. - */ -static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) -{ - return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; -} - -/** * i40e_setup_rx_descriptors - Allocate Rx descriptors * @rx_ring: Rx descriptor ring (for a specific queue) to setup * @@ -1608,7 +1597,6 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; - rx_ring->rx_offset = i40e_rx_offset(rx_ring); /* XDP RX-queue info only needed for RX rings exposed to XDP */ if (rx_ring->vsi->type == I40E_VSI_MAIN) { @@ -2307,8 +2295,7 @@ int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring) * @rx_ring: Rx ring being processed * @xdp: XDP buffer containing the frame **/ -static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring, - struct xdp_buff *xdp) +static int i40e_run_xdp(struct i40e_ring *rx_ring, struct xdp_buff *xdp) { int err, result = I40E_XDP_PASS; struct i40e_ring *xdp_ring; @@ -2347,7 +2334,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring, } xdp_out: rcu_read_unlock(); - return ERR_PTR(-result); + return result; } /** @@ -2460,6 +2447,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) unsigned int xdp_xmit = 0; bool failure = false; struct xdp_buff xdp; + int xdp_res = 0; #if (PAGE_SIZE < 8192) frame_sz = i40e_rx_frame_truesize(rx_ring, 0); @@ -2525,12 +2513,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, size); #endif - skb = i40e_run_xdp(rx_ring, &xdp); + xdp_res = i40e_run_xdp(rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { xdp_xmit |= xdp_res; i40e_rx_buffer_flip(rx_ring, rx_buffer, size); diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 1b6ec9be155a..5d301a466f5c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -137,6 +137,7 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) **/ static inline void i40e_vc_disable_vf(struct i40e_vf *vf) { + struct i40e_pf *pf = vf->pf; int i; i40e_vc_notify_vf_reset(vf); @@ -147,6 +148,11 @@ static inline void i40e_vc_disable_vf(struct i40e_vf *vf) * ensure a reset. */ for (i = 0; i < 20; i++) { + /* If PF is in VFs releasing state reset VF is impossible, + * so leave it. + */ + if (test_bit(__I40E_VFS_RELEASING, pf->state)) + return; if (i40e_reset_vf(vf, false)) return; usleep_range(10000, 20000); @@ -1574,6 +1580,8 @@ void i40e_free_vfs(struct i40e_pf *pf) if (!pf->vf) return; + + set_bit(__I40E_VFS_RELEASING, pf->state); while (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) usleep_range(1000, 2000); @@ -1631,6 +1639,7 @@ void i40e_free_vfs(struct i40e_pf *pf) } } clear_bit(__I40E_VF_DISABLE, pf->state); + clear_bit(__I40E_VFS_RELEASING, pf->state); } #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index fc32c5019b0f..12ca84113587 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -471,7 +471,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, descs, budget); if (!nb_pkts) - return false; + return true; if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) { nb_processed = xdp_ring->count - xdp_ring->next_to_use; @@ -488,7 +488,7 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) i40e_update_tx_stats(xdp_ring, nb_pkts, total_bytes); - return true; + return nb_pkts < budget; } /** diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 357706444dd5..17101c45cbcd 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -196,7 +196,6 @@ enum ice_state { __ICE_NEEDS_RESTART, __ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ __ICE_RESET_OICR_RECV, /* set by driver after rcv reset OICR */ - __ICE_DCBNL_DEVRESET, /* set by dcbnl devreset */ __ICE_PFR_REQ, /* set by driver and peers */ __ICE_CORER_REQ, /* set by driver and peers */ __ICE_GLOBR_REQ, /* set by driver and peers */ @@ -624,7 +623,7 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset); void ice_print_link_msg(struct ice_vsi *vsi, bool isup); const char *ice_stat_str(enum ice_status stat_err); const char *ice_aq_str(enum ice_aq_err aq_err); -bool ice_is_wol_supported(struct ice_pf *pf); +bool ice_is_wol_supported(struct ice_hw *hw); int ice_fdir_write_fltr(struct ice_pf *pf, struct ice_fdir_fltr *input, bool add, bool is_tun); @@ -642,6 +641,7 @@ int ice_fdir_create_dflt_rules(struct ice_pf *pf); int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout, struct ice_rq_event_info *event); int ice_open(struct net_device *netdev); +int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 3124a3bf519a..1148d768f8ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -275,6 +275,22 @@ ice_setup_tx_ctx(struct ice_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf_q) } /** + * ice_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static unsigned int ice_rx_offset(struct ice_ring *rx_ring) +{ + if (ice_ring_uses_build_skb(rx_ring)) + return ICE_SKB_PAD; + else if (ice_is_xdp_ena_vsi(rx_ring->vsi)) + return XDP_PACKET_HEADROOM; + + return 0; +} + +/** * ice_setup_rx_ctx - Configure a receive ring context * @ring: The Rx ring to configure * @@ -413,11 +429,15 @@ int ice_setup_rx_ctx(struct ice_ring *ring) else ice_set_ring_build_skb_ena(ring); + ring->rx_offset = ice_rx_offset(ring); + /* init queue specific tail register */ ring->tail = hw->hw_addr + QRX_TAIL(pf_q); writel(0, ring->tail); if (ring->xsk_pool) { + bool ok; + if (!xsk_buff_can_alloc(ring->xsk_pool, num_bufs)) { dev_warn(dev, "XSK buffer pool does not provide enough addresses to fill %d buffers on Rx ring %d\n", num_bufs, ring->q_index); @@ -426,8 +446,8 @@ int ice_setup_rx_ctx(struct ice_ring *ring) return 0; } - err = ice_alloc_rx_bufs_zc(ring, num_bufs); - if (err) + ok = ice_alloc_rx_bufs_zc(ring, num_bufs); + if (!ok) dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n", ring->q_index, pf_q); return 0; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 3d9475e222cd..a20edf1538a0 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -717,8 +717,8 @@ static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable) if (!data) { data = devm_kcalloc(ice_hw_to_dev(hw), - sizeof(*data), ICE_AQC_FW_LOG_ID_MAX, + sizeof(*data), GFP_KERNEL); if (!data) return ICE_ERR_NO_MEMORY; diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index faaa08e8171b..68866f4f0eb0 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -31,8 +31,8 @@ enum ice_ctl_q { ICE_CTL_Q_MAILBOX, }; -/* Control Queue timeout settings - max delay 250ms */ -#define ICE_CTL_Q_SQ_CMD_TIMEOUT 2500 /* Count 2500 times */ +/* Control Queue timeout settings - max delay 1s */ +#define ICE_CTL_Q_SQ_CMD_TIMEOUT 10000 /* Count 10000 times */ #define ICE_CTL_Q_SQ_CMD_USEC 100 /* Check every 100usec */ #define ICE_CTL_Q_ADMIN_INIT_TIMEOUT 10 /* Count 10 times */ #define ICE_CTL_Q_ADMIN_INIT_MSEC 100 /* Check every 100msec */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index e42727941ef5..28e834a128c0 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -738,22 +738,27 @@ ice_aq_get_cee_dcb_cfg(struct ice_hw *hw, /** * ice_cee_to_dcb_cfg * @cee_cfg: pointer to CEE configuration struct - * @dcbcfg: DCB configuration struct + * @pi: port information structure * * Convert CEE configuration from firmware to DCB configuration */ static void ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, - struct ice_dcbx_cfg *dcbcfg) + struct ice_port_info *pi) { u32 status, tlv_status = le32_to_cpu(cee_cfg->tlv_status); - u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift; - u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio); + u32 ice_aqc_cee_status_mask, ice_aqc_cee_status_shift, j; u8 i, err, sync, oper, app_index, ice_app_sel_type; + u16 app_prio = le16_to_cpu(cee_cfg->oper_app_prio); u16 ice_aqc_cee_app_mask, ice_aqc_cee_app_shift; + struct ice_dcbx_cfg *cmp_dcbcfg, *dcbcfg; u16 ice_app_prot_id_type; - /* CEE PG data to ETS config */ + dcbcfg = &pi->qos_cfg.local_dcbx_cfg; + dcbcfg->dcbx_mode = ICE_DCBX_MODE_CEE; + dcbcfg->tlv_status = tlv_status; + + /* CEE PG data */ dcbcfg->etscfg.maxtcs = cee_cfg->oper_num_tc; /* Note that the FW creates the oper_prio_tc nibbles reversed @@ -780,10 +785,16 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, } } - /* CEE PFC data to ETS config */ + /* CEE PFC data */ dcbcfg->pfc.pfcena = cee_cfg->oper_pfc_en; dcbcfg->pfc.pfccap = ICE_MAX_TRAFFIC_CLASS; + /* CEE APP TLV data */ + if (dcbcfg->app_mode == ICE_DCBX_APPS_NON_WILLING) + cmp_dcbcfg = &pi->qos_cfg.desired_dcbx_cfg; + else + cmp_dcbcfg = &pi->qos_cfg.remote_dcbx_cfg; + app_index = 0; for (i = 0; i < 3; i++) { if (i == 0) { @@ -802,6 +813,18 @@ ice_cee_to_dcb_cfg(struct ice_aqc_get_cee_dcb_cfg_resp *cee_cfg, ice_aqc_cee_app_shift = ICE_AQC_CEE_APP_ISCSI_S; ice_app_sel_type = ICE_APP_SEL_TCPIP; ice_app_prot_id_type = ICE_APP_PROT_ID_ISCSI; + + for (j = 0; j < cmp_dcbcfg->numapps; j++) { + u16 prot_id = cmp_dcbcfg->app[j].prot_id; + u8 sel = cmp_dcbcfg->app[j].selector; + + if (sel == ICE_APP_SEL_TCPIP && + (prot_id == ICE_APP_PROT_ID_ISCSI || + prot_id == ICE_APP_PROT_ID_ISCSI_860)) { + ice_app_prot_id_type = prot_id; + break; + } + } } else { /* FIP APP */ ice_aqc_cee_status_mask = ICE_AQC_CEE_FIP_STATUS_M; @@ -892,11 +915,8 @@ enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi) ret = ice_aq_get_cee_dcb_cfg(pi->hw, &cee_cfg, NULL); if (!ret) { /* CEE mode */ - dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg; - dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_CEE; - dcbx_cfg->tlv_status = le32_to_cpu(cee_cfg.tlv_status); - ice_cee_to_dcb_cfg(&cee_cfg, dcbx_cfg); ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_CEE); + ice_cee_to_dcb_cfg(&cee_cfg, pi); } else if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) { /* CEE mode not enabled try querying IEEE data */ dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg; diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c index 468a63f7eff9..4180f1f35fb8 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_nl.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_nl.c @@ -18,12 +18,10 @@ static void ice_dcbnl_devreset(struct net_device *netdev) while (ice_is_reset_in_progress(pf->state)) usleep_range(1000, 2000); - set_bit(__ICE_DCBNL_DEVRESET, pf->state); dev_close(netdev); netdev_state_change(netdev); dev_open(netdev, NULL); netdev_state_change(netdev); - clear_bit(__ICE_DCBNL_DEVRESET, pf->state); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 2dcfa685b763..32ba71a16165 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3472,7 +3472,7 @@ static void ice_get_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) netdev_warn(netdev, "Wake on LAN is not supported on this interface!\n"); /* Get WoL settings based on the HW capability */ - if (ice_is_wol_supported(pf)) { + if (ice_is_wol_supported(&pf->hw)) { wol->supported = WAKE_MAGIC; wol->wolopts = pf->wol_ena ? WAKE_MAGIC : 0; } else { @@ -3492,7 +3492,7 @@ static int ice_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; - if (vsi->type != ICE_VSI_PF || !ice_is_wol_supported(pf)) + if (vsi->type != ICE_VSI_PF || !ice_is_wol_supported(&pf->hw)) return -EOPNOTSUPP; /* only magic packet is supported */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 8d4e2ad4328d..d13c7fc8fb0a 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2620,7 +2620,7 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked) if (!locked) rtnl_lock(); - err = ice_open(vsi->netdev); + err = ice_open_internal(vsi->netdev); if (!locked) rtnl_unlock(); @@ -2649,7 +2649,7 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) if (!locked) rtnl_lock(); - ice_stop(vsi->netdev); + ice_vsi_close(vsi); if (!locked) rtnl_unlock(); @@ -3078,7 +3078,6 @@ err_vsi: bool ice_is_reset_in_progress(unsigned long *state) { return test_bit(__ICE_RESET_OICR_RECV, state) || - test_bit(__ICE_DCBNL_DEVRESET, state) || test_bit(__ICE_PFR_REQ, state) || test_bit(__ICE_CORER_REQ, state) || test_bit(__ICE_GLOBR_REQ, state); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 2c23c8f468a5..d821c687f239 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3537,15 +3537,14 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) } /** - * ice_is_wol_supported - get NVM state of WoL - * @pf: board private structure + * ice_is_wol_supported - check if WoL is supported + * @hw: pointer to hardware info * * Check if WoL is supported based on the HW configuration. * Returns true if NVM supports and enables WoL for this port, false otherwise */ -bool ice_is_wol_supported(struct ice_pf *pf) +bool ice_is_wol_supported(struct ice_hw *hw) { - struct ice_hw *hw = &pf->hw; u16 wol_ctrl; /* A bit set to 1 in the NVM Software Reserved Word 2 (WoL control @@ -3554,7 +3553,7 @@ bool ice_is_wol_supported(struct ice_pf *pf) if (ice_read_sr_word(hw, ICE_SR_NVM_WOL_CFG, &wol_ctrl)) return false; - return !(BIT(hw->pf_id) & wol_ctrl); + return !(BIT(hw->port_info->lport) & wol_ctrl); } /** @@ -4192,28 +4191,25 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) goto err_send_version_unroll; } + /* not a fatal error if this fails */ err = ice_init_nvm_phy_type(pf->hw.port_info); - if (err) { + if (err) dev_err(dev, "ice_init_nvm_phy_type failed: %d\n", err); - goto err_send_version_unroll; - } + /* not a fatal error if this fails */ err = ice_update_link_info(pf->hw.port_info); - if (err) { + if (err) dev_err(dev, "ice_update_link_info failed: %d\n", err); - goto err_send_version_unroll; - } ice_init_link_dflt_override(pf->hw.port_info); /* if media available, initialize PHY settings */ if (pf->hw.port_info->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { + /* not a fatal error if this fails */ err = ice_init_phy_user_cfg(pf->hw.port_info); - if (err) { + if (err) dev_err(dev, "ice_init_phy_user_cfg failed: %d\n", err); - goto err_send_version_unroll; - } if (!test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, pf->flags)) { struct ice_vsi *vsi = ice_get_main_vsi(pf); @@ -4568,6 +4564,7 @@ static int __maybe_unused ice_suspend(struct device *dev) continue; ice_vsi_free_q_vectors(pf->vsi[v]); } + ice_free_cpu_rx_rmap(ice_get_main_vsi(pf)); ice_clear_interrupt_scheme(pf); pci_save_state(pdev); @@ -6637,6 +6634,28 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue) int ice_open(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = np->vsi->back; + + if (ice_is_reset_in_progress(pf->state)) { + netdev_err(netdev, "can't open net device while reset is in progress"); + return -EBUSY; + } + + return ice_open_internal(netdev); +} + +/** + * ice_open_internal - Called when a network interface becomes active + * @netdev: network interface device structure + * + * Internal ice_open implementation. Should not be used directly except for ice_open and reset + * handling routine + * + * Returns 0 on success, negative value on failure + */ +int ice_open_internal(struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_port_info *pi; @@ -6715,6 +6734,12 @@ int ice_stop(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + + if (ice_is_reset_in_progress(pf->state)) { + netdev_err(netdev, "can't stop net device while reset is in progress"); + return -EBUSY; + } ice_vsi_close(vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 67c965a3f5d2..834cbd3f7b31 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1238,6 +1238,9 @@ ice_add_update_vsi_list(struct ice_hw *hw, ice_create_vsi_list_map(hw, &vsi_handle_arr[0], 2, vsi_list_id); + if (!m_entry->vsi_list_info) + return ICE_ERR_NO_MEMORY; + /* If this entry was large action then the large action needs * to be updated to point to FWD to VSI list */ @@ -2220,6 +2223,7 @@ ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_handle) return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI && fm_entry->fltr_info.vsi_handle == vsi_handle) || (fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST && + fm_entry->vsi_list_info && (test_bit(vsi_handle, fm_entry->vsi_list_info->vsi_map)))); } @@ -2292,14 +2296,12 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_handle, return ICE_ERR_PARAM; list_for_each_entry(fm_entry, lkup_list_head, list_entry) { - struct ice_fltr_info *fi; - - fi = &fm_entry->fltr_info; - if (!fi || !ice_vsi_uses_fltr(fm_entry, vsi_handle)) + if (!ice_vsi_uses_fltr(fm_entry, vsi_handle)) continue; status = ice_add_entry_to_vsi_fltr_list(hw, vsi_handle, - vsi_list_head, fi); + vsi_list_head, + &fm_entry->fltr_info); if (status) return status; } @@ -2622,7 +2624,7 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle, &remove_list_head); mutex_unlock(rule_lock); if (status) - return; + goto free_fltr_list; switch (lkup) { case ICE_SW_LKUP_MAC: @@ -2645,6 +2647,7 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_handle, break; } +free_fltr_list: list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) { list_del(&fm_entry->list_entry); devm_kfree(ice_hw_to_dev(hw), fm_entry); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index b7dc25da1202..b91dcfd12727 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -444,22 +444,6 @@ void ice_free_rx_ring(struct ice_ring *rx_ring) } /** - * ice_rx_offset - Return expected offset into page to access data - * @rx_ring: Ring we are requesting offset of - * - * Returns the offset value for ring into the data buffer. - */ -static unsigned int ice_rx_offset(struct ice_ring *rx_ring) -{ - if (ice_ring_uses_build_skb(rx_ring)) - return ICE_SKB_PAD; - else if (ice_is_xdp_ena_vsi(rx_ring->vsi)) - return XDP_PACKET_HEADROOM; - - return 0; -} - -/** * ice_setup_rx_ring - Allocate the Rx descriptors * @rx_ring: the Rx ring to set up * @@ -493,7 +477,6 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring) rx_ring->next_to_use = 0; rx_ring->next_to_clean = 0; - rx_ring->rx_offset = ice_rx_offset(rx_ring); if (ice_is_xdp_ena_vsi(rx_ring->vsi)) WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog); diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index a6cb0c35748c..266036b7a49a 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -535,6 +535,7 @@ struct ice_dcb_app_priority_table { #define ICE_TLV_STATUS_ERR 0x4 #define ICE_APP_PROT_ID_FCOE 0x8906 #define ICE_APP_PROT_ID_ISCSI 0x0cbc +#define ICE_APP_PROT_ID_ISCSI_860 0x035c #define ICE_APP_PROT_ID_FIP 0x8914 #define ICE_APP_SEL_ETHTYPE 0x1 #define ICE_APP_SEL_TCPIP 0x2 diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 83f3c9574ed1..9f94d9159acd 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -358,18 +358,18 @@ xsk_pool_if_up: * This function allocates a number of Rx buffers from the fill ring * or the internal recycle mechanism and places them on the Rx ring. * - * Returns false if all allocations were successful, true if any fail. + * Returns true if all allocations were successful, false if any fail. */ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) { union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; struct ice_rx_buf *rx_buf; - bool ret = false; + bool ok = true; dma_addr_t dma; if (!count) - return false; + return true; rx_desc = ICE_RX_DESC(rx_ring, ntu); rx_buf = &rx_ring->rx_buf[ntu]; @@ -377,7 +377,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) do { rx_buf->xdp = xsk_buff_alloc(rx_ring->xsk_pool); if (!rx_buf->xdp) { - ret = true; + ok = false; break; } @@ -402,7 +402,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_ring *rx_ring, u16 count) ice_release_rx_desc(rx_ring, ntu); } - return ret; + return ok; } /** diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h index 5d87957b2627..44111f65afc7 100644 --- a/drivers/net/ethernet/intel/igb/e1000_hw.h +++ b/drivers/net/ethernet/intel/igb/e1000_hw.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2007 - 2018 Intel Corporation. */ -#ifndef _E1000_HW_H_ -#define _E1000_HW_H_ +#ifndef _E1000_IGB_HW_H_ +#define _E1000_IGB_HW_H_ #include <linux/types.h> #include <linux/delay.h> @@ -551,4 +551,4 @@ s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value); void igb_read_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value); void igb_write_pci_cfg(struct e1000_hw *hw, u32 reg, u16 *value); -#endif /* _E1000_HW_H_ */ +#endif /* _E1000_IGB_HW_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index aaa954aae574..7bda8c5edea5 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -748,8 +748,8 @@ void igb_ptp_suspend(struct igb_adapter *adapter); void igb_ptp_rx_hang(struct igb_adapter *adapter); void igb_ptp_tx_hang(struct igb_adapter *adapter); void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, - struct sk_buff *skb); +int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, + struct sk_buff *skb); int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); void igb_set_flag_queue_pairs(struct igb_adapter *, const u32); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 878b31d534ec..a45cd2b416c8 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8214,7 +8214,8 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, new_buff->pagecnt_bias = old_buff->pagecnt_bias; } -static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) +static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, + int rx_buf_pgcnt) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -8225,7 +8226,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1)) return false; #else #define IGB_LAST_OFFSET \ @@ -8301,9 +8302,10 @@ static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, return NULL; if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { - igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb); - xdp->data += IGB_TS_HDR_LEN; - size -= IGB_TS_HDR_LEN; + if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) { + xdp->data += IGB_TS_HDR_LEN; + size -= IGB_TS_HDR_LEN; + } } /* Determine available headroom for copy */ @@ -8364,8 +8366,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, /* pull timestamp out of packet data */ if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); - __skb_pull(skb, IGB_TS_HDR_LEN); + if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb)) + __skb_pull(skb, IGB_TS_HDR_LEN); } /* update buffer offset */ @@ -8614,11 +8616,17 @@ static unsigned int igb_rx_offset(struct igb_ring *rx_ring) } static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, - const unsigned int size) + const unsigned int size, int *rx_buf_pgcnt) { struct igb_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buf_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif prefetchw(rx_buffer->page); /* we are reusing so sync this buffer for CPU use */ @@ -8634,9 +8642,9 @@ static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, } static void igb_put_rx_buffer(struct igb_ring *rx_ring, - struct igb_rx_buffer *rx_buffer) + struct igb_rx_buffer *rx_buffer, int rx_buf_pgcnt) { - if (igb_can_reuse_rx_page(rx_buffer)) { + if (igb_can_reuse_rx_page(rx_buffer, rx_buf_pgcnt)) { /* hand second half of page back to the ring */ igb_reuse_rx_page(rx_ring, rx_buffer); } else { @@ -8664,6 +8672,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) unsigned int xdp_xmit = 0; struct xdp_buff xdp; u32 frame_sz = 0; + int rx_buf_pgcnt; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -8693,7 +8702,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) */ dma_rmb(); - rx_buffer = igb_get_rx_buffer(rx_ring, size); + rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt); /* retrieve a buffer from the ring */ if (!skb) { @@ -8736,7 +8745,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) break; } - igb_put_rx_buffer(rx_ring, rx_buffer); + igb_put_rx_buffer(rx_ring, rx_buffer, rx_buf_pgcnt); cleaned_count++; /* fetch next buffer in frame if non-eop */ diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 7cc5428c3b3d..86a576201f5f 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -856,6 +856,9 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) dev_kfree_skb_any(skb); } +#define IGB_RET_PTP_DISABLED 1 +#define IGB_RET_PTP_INVALID 2 + /** * igb_ptp_rx_pktstamp - retrieve Rx per packet timestamp * @q_vector: Pointer to interrupt specific structure @@ -864,19 +867,29 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) * * This function is meant to retrieve a timestamp from the first buffer of an * incoming frame. The value is stored in little endian format starting on - * byte 8. + * byte 8 + * + * Returns: 0 if success, nonzero if failure **/ -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, - struct sk_buff *skb) +int igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, + struct sk_buff *skb) { - __le64 *regval = (__le64 *)va; struct igb_adapter *adapter = q_vector->adapter; + __le64 *regval = (__le64 *)va; int adjust = 0; + if (!(adapter->ptp_flags & IGB_PTP_ENABLED)) + return IGB_RET_PTP_DISABLED; + /* The timestamp is recorded in little endian format. * DWORD: 0 1 2 3 * Field: Reserved Reserved SYSTIML SYSTIMH */ + + /* check reserved dwords are zero, be/le doesn't matter for zero */ + if (regval[0]) + return IGB_RET_PTP_INVALID; + igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), le64_to_cpu(regval[1])); @@ -896,6 +909,8 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, } skb_hwtstamps(skb)->hwtstamp = ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); + + return 0; } /** @@ -906,13 +921,15 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, * This function is meant to retrieve a timestamp from the internal registers * of the adapter and store it in the skb. **/ -void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, - struct sk_buff *skb) +void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb) { struct igb_adapter *adapter = q_vector->adapter; struct e1000_hw *hw = &adapter->hw; - u64 regval; int adjust = 0; + u64 regval; + + if (!(adapter->ptp_flags & IGB_PTP_ENABLED)) + return; /* If this bit is set, then the RX registers contain the time stamp. No * other packet will be time stamped until we read these registers, so diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 5d2809dfd06a..1b08a7dc7bc4 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -547,7 +547,7 @@ void igc_ptp_init(struct igc_adapter *adapter); void igc_ptp_reset(struct igc_adapter *adapter); void igc_ptp_suspend(struct igc_adapter *adapter); void igc_ptp_stop(struct igc_adapter *adapter); -void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va, +void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, struct sk_buff *skb); int igc_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igc_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 824a6c454bca..8722294ab90c 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -1711,6 +1711,9 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, Autoneg); } + /* Set pause flow control settings */ + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + switch (hw->fc.requested_mode) { case igc_fc_full: ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); @@ -1725,9 +1728,7 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, Asym_Pause); break; default: - ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Asym_Pause); + break; } status = pm_runtime_suspended(&adapter->pdev->dev) ? diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 7ac9597ddb84..4d989ebc9713 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -3831,10 +3831,19 @@ static void igc_reset_task(struct work_struct *work) adapter = container_of(work, struct igc_adapter, reset_task); + rtnl_lock(); + /* If we're already down or resetting, just bail */ + if (test_bit(__IGC_DOWN, &adapter->state) || + test_bit(__IGC_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + igc_rings_dump(adapter); igc_regs_dump(adapter); netdev_err(adapter->netdev, "Reset adapter\n"); igc_reinit_locked(adapter); + rtnl_unlock(); } /** diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index ac0b9c85da7c..545f4d0e67cf 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -152,46 +152,54 @@ static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, } /** - * igc_ptp_rx_pktstamp - retrieve Rx per packet timestamp + * igc_ptp_rx_pktstamp - Retrieve timestamp from Rx packet buffer * @q_vector: Pointer to interrupt specific structure * @va: Pointer to address containing Rx buffer * @skb: Buffer containing timestamp and packet * - * This function is meant to retrieve the first timestamp from the - * first buffer of an incoming frame. The value is stored in little - * endian format starting on byte 0. There's a second timestamp - * starting on byte 8. - **/ -void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, void *va, + * This function retrieves the timestamp saved in the beginning of packet + * buffer. While two timestamps are available, one in timer0 reference and the + * other in timer1 reference, this function considers only the timestamp in + * timer0 reference. + */ +void igc_ptp_rx_pktstamp(struct igc_q_vector *q_vector, __le32 *va, struct sk_buff *skb) { struct igc_adapter *adapter = q_vector->adapter; - __le64 *regval = (__le64 *)va; - int adjust = 0; - - /* The timestamp is recorded in little endian format. - * DWORD: | 0 | 1 | 2 | 3 - * Field: | Timer0 Low | Timer0 High | Timer1 Low | Timer1 High + u64 regval; + int adjust; + + /* Timestamps are saved in little endian at the beginning of the packet + * buffer following the layout: + * + * DWORD: | 0 | 1 | 2 | 3 | + * Field: | Timer1 SYSTIML | Timer1 SYSTIMH | Timer0 SYSTIML | Timer0 SYSTIMH | + * + * SYSTIML holds the nanoseconds part while SYSTIMH holds the seconds + * part of the timestamp. */ - igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), - le64_to_cpu(regval[0])); - - /* adjust timestamp for the RX latency based on link speed */ - if (adapter->hw.mac.type == igc_i225) { - switch (adapter->link_speed) { - case SPEED_10: - adjust = IGC_I225_RX_LATENCY_10; - break; - case SPEED_100: - adjust = IGC_I225_RX_LATENCY_100; - break; - case SPEED_1000: - adjust = IGC_I225_RX_LATENCY_1000; - break; - case SPEED_2500: - adjust = IGC_I225_RX_LATENCY_2500; - break; - } + regval = le32_to_cpu(va[2]); + regval |= (u64)le32_to_cpu(va[3]) << 32; + igc_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); + + /* Adjust timestamp for the RX latency based on link speed */ + switch (adapter->link_speed) { + case SPEED_10: + adjust = IGC_I225_RX_LATENCY_10; + break; + case SPEED_100: + adjust = IGC_I225_RX_LATENCY_100; + break; + case SPEED_1000: + adjust = IGC_I225_RX_LATENCY_1000; + break; + case SPEED_2500: + adjust = IGC_I225_RX_LATENCY_2500; + break; + default: + adjust = 0; + netdev_warn_once(adapter->netdev, "Imprecise timestamp\n"); + break; } skb_hwtstamps(skb)->hwtstamp = ktime_sub_ns(skb_hwtstamps(skb)->hwtstamp, adjust); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 9f3f12e2ccf2..cffb95f8f632 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4118,6 +4118,8 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, #endif } + ring->rx_offset = ixgbe_rx_offset(ring); + if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) { u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); @@ -6534,6 +6536,13 @@ err_setup_tx: return err; } +static int ixgbe_rx_napi_id(struct ixgbe_ring *rx_ring) +{ + struct ixgbe_q_vector *q_vector = rx_ring->q_vector; + + return q_vector ? q_vector->napi.napi_id : 0; +} + /** * ixgbe_setup_rx_resources - allocate Rx resources (Descriptors) * @adapter: pointer to ixgbe_adapter @@ -6578,11 +6587,10 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; - rx_ring->rx_offset = ixgbe_rx_offset(rx_ring); /* XDP RX-queue info */ if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev, - rx_ring->queue_index, rx_ring->q_vector->napi.napi_id) < 0) + rx_ring->queue_index, ixgbe_rx_napi_id(rx_ring)) < 0) goto err; rx_ring->xdp_prog = adapter->xdp_prog; @@ -6891,6 +6899,11 @@ static int __maybe_unused ixgbe_resume(struct device *dev_d) adapter->hw.hw_addr = adapter->io_addr; + err = pci_enable_device_mem(pdev); + if (err) { + e_dev_err("Cannot enable PCI device from suspend\n"); + return err; + } smp_mb__before_atomic(); clear_bit(__IXGBE_DISABLED, &adapter->state); pci_set_master(pdev); diff --git a/drivers/net/ethernet/marvell/Kconfig b/drivers/net/ethernet/marvell/Kconfig index 7fe15a3286f4..fe0989c0fc25 100644 --- a/drivers/net/ethernet/marvell/Kconfig +++ b/drivers/net/ethernet/marvell/Kconfig @@ -6,7 +6,7 @@ config NET_VENDOR_MARVELL bool "Marvell devices" default y - depends on PCI || CPU_PXA168 || MV64X60 || PPC32 || PLAT_ORION || INET || COMPILE_TEST + depends on PCI || CPU_PXA168 || PPC32 || PLAT_ORION || INET || COMPILE_TEST help If you have a network (Ethernet) card belonging to this class, say Y. @@ -19,7 +19,7 @@ if NET_VENDOR_MARVELL config MV643XX_ETH tristate "Marvell Discovery (643XX) and Orion ethernet support" - depends on MV64X60 || PPC32 || PLAT_ORION || COMPILE_TEST + depends on PPC32 || PLAT_ORION || COMPILE_TEST depends on INET select PHYLIB select MVMDIO diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 90e6111ce534..3bfb659b5c99 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2684,7 +2684,7 @@ static const struct of_device_id mv643xx_eth_shared_ids[] = { MODULE_DEVICE_TABLE(of, mv643xx_eth_shared_ids); #endif -#if defined(CONFIG_OF_IRQ) && !defined(CONFIG_MV64X60) +#ifdef CONFIG_OF_IRQ #define mv643xx_eth_property(_np, _name, _v) \ do { \ u32 tmp; \ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h index b192692b4fc4..5c372d2c24a1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h @@ -13499,8 +13499,6 @@ static struct npc_mcam_kex npc_mkex_default = { [NPC_LT_LC_IP] = { /* SIP+DIP: 8 bytes, KW2[63:0] */ KEX_LD_CFG(0x07, 0xc, 0x1, 0x0, 0x10), - /* TOS: 1 byte, KW1[63:56] */ - KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0xf), }, /* Layer C: IPv6 */ [NPC_LT_LC_IP6] = { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index d9a1a71c7ccc..ab24a5e8ee8a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -2462,8 +2462,10 @@ static void rvu_unregister_interrupts(struct rvu *rvu) INTR_MASK(rvu->hw->total_pfs) & ~1ULL); for (irq = 0; irq < rvu->num_vec; irq++) { - if (rvu->irq_allocated[irq]) + if (rvu->irq_allocated[irq]) { free_irq(pci_irq_vector(rvu->pdev, irq), rvu); + rvu->irq_allocated[irq] = false; + } } pci_free_irq_vectors(rvu->pdev); @@ -2975,8 +2977,8 @@ static void rvu_remove(struct pci_dev *pdev) struct rvu *rvu = pci_get_drvdata(pdev); rvu_dbg_exit(rvu); - rvu_unregister_interrupts(rvu); rvu_unregister_dl(rvu); + rvu_unregister_interrupts(rvu); rvu_flr_wq_destroy(rvu); rvu_cgx_exit(rvu); rvu_fwdata_exit(rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index fa6e46e36ae4..76f399229ddb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -678,6 +678,7 @@ void npc_read_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, u8 *intf, u8 *ena); bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature); u32 rvu_cgx_get_fifolen(struct rvu *rvu); +void *rvu_first_cgx_pdata(struct rvu *rvu); /* CPT APIs */ int rvu_cpt_lf_teardown(struct rvu *rvu, u16 pcifunc, int lf, int slot); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index e668e482383a..6e2bf4fcd29c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -89,6 +89,21 @@ void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu) return rvu->cgx_idmap[cgx_id]; } +/* Return first enabled CGX instance if none are enabled then return NULL */ +void *rvu_first_cgx_pdata(struct rvu *rvu) +{ + int first_enabled_cgx = 0; + void *cgxd = NULL; + + for (; first_enabled_cgx < rvu->cgx_cnt_max; first_enabled_cgx++) { + cgxd = rvu_cgx_pdata(first_enabled_cgx, rvu); + if (cgxd) + break; + } + + return cgxd; +} + /* Based on P2X connectivity find mapped NIX block for a PF */ static void rvu_map_cgx_nix_block(struct rvu *rvu, int pf, int cgx_id, int lmac_id) @@ -711,10 +726,9 @@ int rvu_mbox_handler_cgx_features_get(struct rvu *rvu, u32 rvu_cgx_get_fifolen(struct rvu *rvu) { struct mac_ops *mac_ops; - int rvu_def_cgx_id = 0; u32 fifo_len; - mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu)); + mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu)); fifo_len = mac_ops ? mac_ops->fifo_len : 0; return fifo_len; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index aa2ca8780b9c..de3968d2e5ce 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -234,12 +234,14 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, char __user *buffer, size_t count, loff_t *ppos) { - int index, off = 0, flag = 0, go_back = 0, off_prev; + int index, off = 0, flag = 0, go_back = 0, len = 0; struct rvu *rvu = filp->private_data; int lf, pf, vf, pcifunc; struct rvu_block block; int bytes_not_copied; + int lf_str_size = 12; int buf_size = 2048; + char *lfs; char *buf; /* don't allow partial reads */ @@ -249,12 +251,20 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, buf = kzalloc(buf_size, GFP_KERNEL); if (!buf) return -ENOSPC; - off += scnprintf(&buf[off], buf_size - 1 - off, "\npcifunc\t\t"); + + lfs = kzalloc(lf_str_size, GFP_KERNEL); + if (!lfs) { + kfree(buf); + return -ENOMEM; + } + off += scnprintf(&buf[off], buf_size - 1 - off, "%-*s", lf_str_size, + "pcifunc"); for (index = 0; index < BLK_COUNT; index++) - if (strlen(rvu->hw->block[index].name)) - off += scnprintf(&buf[off], buf_size - 1 - off, - "%*s\t", (index - 1) * 2, - rvu->hw->block[index].name); + if (strlen(rvu->hw->block[index].name)) { + off += scnprintf(&buf[off], buf_size - 1 - off, + "%-*s", lf_str_size, + rvu->hw->block[index].name); + } off += scnprintf(&buf[off], buf_size - 1 - off, "\n"); for (pf = 0; pf < rvu->hw->total_pfs; pf++) { for (vf = 0; vf <= rvu->hw->total_vfs; vf++) { @@ -263,14 +273,15 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, continue; if (vf) { + sprintf(lfs, "PF%d:VF%d", pf, vf - 1); go_back = scnprintf(&buf[off], buf_size - 1 - off, - "PF%d:VF%d\t\t", pf, - vf - 1); + "%-*s", lf_str_size, lfs); } else { + sprintf(lfs, "PF%d", pf); go_back = scnprintf(&buf[off], buf_size - 1 - off, - "PF%d\t\t", pf); + "%-*s", lf_str_size, lfs); } off += go_back; @@ -278,20 +289,22 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, block = rvu->hw->block[index]; if (!strlen(block.name)) continue; - off_prev = off; + len = 0; + lfs[len] = '\0'; for (lf = 0; lf < block.lf.max; lf++) { if (block.fn_map[lf] != pcifunc) continue; flag = 1; - off += scnprintf(&buf[off], buf_size - 1 - - off, "%3d,", lf); + len += sprintf(&lfs[len], "%d,", lf); } - if (flag && off_prev != off) - off--; - else - go_back++; + + if (flag) + len--; + lfs[len] = '\0'; off += scnprintf(&buf[off], buf_size - 1 - off, - "\t"); + "%-*s", lf_str_size, lfs); + if (!strlen(lfs)) + go_back += lf_str_size; } if (!flag) off -= go_back; @@ -303,6 +316,7 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, } bytes_not_copied = copy_to_user(buffer, buf, off); + kfree(lfs); kfree(buf); if (bytes_not_copied) @@ -319,7 +333,6 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) struct rvu *rvu = filp->private; struct pci_dev *pdev = NULL; struct mac_ops *mac_ops; - int rvu_def_cgx_id = 0; char cgx[10], lmac[10]; struct rvu_pfvf *pfvf; int pf, domain, blkid; @@ -327,7 +340,10 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) u16 pcifunc; domain = 2; - mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu)); + mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu)); + /* There can be no CGX devices at all */ + if (!mac_ops) + return 0; seq_printf(filp, "PCI dev\t\tRVU PF Func\tNIX block\t%s\tLMAC\n", mac_ops->name); for (pf = 0; pf < rvu->hw->total_pfs; pf++) { @@ -1818,7 +1834,6 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) { struct mac_ops *mac_ops; unsigned long lmac_bmap; - int rvu_def_cgx_id = 0; int i, lmac_id; char dname[20]; void *cgx; @@ -1826,7 +1841,7 @@ static void rvu_dbg_cgx_init(struct rvu *rvu) if (!cgx_get_cgxcnt_max()) return; - mac_ops = get_mac_ops(rvu_cgx_pdata(rvu_def_cgx_id, rvu)); + mac_ops = get_mac_ops(rvu_first_cgx_pdata(rvu)); if (!mac_ops) return; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index d3000194e2d3..3d068b7d46bd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -2629,7 +2629,7 @@ static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg) struct nix_rx_flowkey_alg *field; struct nix_rx_flowkey_alg tmp; u32 key_type, valid_key; - int l4_key_offset; + int l4_key_offset = 0; if (!alg) return -EINVAL; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 04bb0803a5c5..0bd49c7080a6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -2490,10 +2490,10 @@ int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu, index = find_next_bit(mcam->bmap, mcam->bmap_entries, entry); if (index >= mcam->bmap_entries) break; + entry = index + 1; if (mcam->entry2cntr_map[index] != req->cntr) continue; - entry = index + 1; npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr, index, req->cntr); } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 0dbbf38e0597..dc1778420978 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -257,17 +257,19 @@ int otx2_get_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc, int otx2_get_all_flows(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc, u32 *rule_locs) { + u32 rule_cnt = nfc->rule_cnt; u32 location = 0; int idx = 0; int err = 0; nfc->data = pfvf->flow_cfg->ntuple_max_flows; - while ((!err || err == -ENOENT) && idx < nfc->rule_cnt) { + while ((!err || err == -ENOENT) && idx < rule_cnt) { err = otx2_get_flow(pfvf, nfc, location); if (!err) rule_locs[idx++] = location; location++; } + nfc->rule_cnt = rule_cnt; return err; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 53ab1814d74b..2fd3d235d292 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1672,6 +1672,7 @@ int otx2_stop(struct net_device *netdev) struct otx2_nic *pf = netdev_priv(netdev); struct otx2_cq_poll *cq_poll = NULL; struct otx2_qset *qset = &pf->qset; + struct otx2_rss_info *rss; int qidx, vec, wrk; netif_carrier_off(netdev); @@ -1684,6 +1685,10 @@ int otx2_stop(struct net_device *netdev) /* First stop packet Rx/Tx */ otx2_rxtx_enable(pf, false); + /* Clear RSS enable flag */ + rss = &pf->hw.rss_info; + rss->enable = false; + /* Cleanup Queue IRQ */ vec = pci_irq_vector(pf->pdev, pf->hw.nix_msixoff + NIX_LF_QINT_VEC_START); diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index d1e4d42e497d..3712e1786091 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1544,8 +1544,8 @@ static int pxa168_eth_remove(struct platform_device *pdev) clk_disable_unprepare(pep->clk); mdiobus_unregister(pep->smi_bus); mdiobus_free(pep->smi_bus); - unregister_netdev(dev); cancel_work_sync(&pep->tx_timeout_task); + unregister_netdev(dev); free_netdev(dev); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index b051417ede67..9153c9bda96f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -191,12 +191,12 @@ static bool is_ib_supported(struct mlx5_core_dev *dev) } enum { - MLX5_INTERFACE_PROTOCOL_ETH_REP, MLX5_INTERFACE_PROTOCOL_ETH, + MLX5_INTERFACE_PROTOCOL_ETH_REP, + MLX5_INTERFACE_PROTOCOL_IB, MLX5_INTERFACE_PROTOCOL_IB_REP, MLX5_INTERFACE_PROTOCOL_MPIB, - MLX5_INTERFACE_PROTOCOL_IB, MLX5_INTERFACE_PROTOCOL_VNET, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index d7d8a68ef23d..d0f9d3cee97d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -246,6 +246,11 @@ static int mlx5_devlink_trap_action_set(struct devlink *devlink, struct mlx5_devlink_trap *dl_trap; int err = 0; + if (is_mdev_switchdev_mode(dev)) { + NL_SET_ERR_MSG_MOD(extack, "Devlink traps can't be set in switchdev mode"); + return -EOPNOTSUPP; + } + dl_trap = mlx5_find_trap_by_id(dev, trap->id); if (!dl_trap) { mlx5_core_err(dev, "Devlink trap: Set action on invalid trap id 0x%x", trap->id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 7435fe6829b6..bc6f77ea0a31 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -92,14 +92,15 @@ struct page_pool; MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT : 0) #define MLX5_MPWRQ_PAGES_PER_WQE BIT(MLX5_MPWRQ_WQE_PAGE_ORDER) -#define MLX5_MTT_OCTW(npages) (ALIGN(npages, 8) / 2) +#define MLX5_ALIGN_MTTS(mtts) (ALIGN(mtts, 8)) +#define MLX5_ALIGNED_MTTS_OCTW(mtts) ((mtts) / 2) +#define MLX5_MTT_OCTW(mtts) (MLX5_ALIGNED_MTTS_OCTW(MLX5_ALIGN_MTTS(mtts))) /* 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_WQE_MTTS (MLX5_ALIGN_MTTS(MLX5_MPWRQ_PAGES_PER_WQE + 1)) #define MLX5E_REQUIRED_MTTS(wqes) (wqes * MLX5E_REQUIRED_WQE_MTTS) #define MLX5E_MAX_RQ_NUM_MTTS \ ((1 << 16) * 2) /* So that MLX5_MTT_OCTW(num_mtts) fits into u16 */ @@ -515,6 +516,7 @@ struct mlx5e_icosq { struct mlx5_wq_cyc wq; void __iomem *uar_map; u32 sqn; + u16 reserved_room; unsigned long state; /* control path */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 308fd279669e..89510cac46c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -387,21 +387,6 @@ enum mlx5e_fec_supported_link_mode { *_policy = MLX5_GET(pplm_reg, _buf, fec_override_admin_##link); \ } while (0) -#define MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(buf, policy, write, link) \ - do { \ - unsigned long policy_long; \ - u16 *__policy = &(policy); \ - bool _write = (write); \ - \ - policy_long = *__policy; \ - if (_write && *__policy) \ - *__policy = find_first_bit(&policy_long, \ - sizeof(policy_long) * BITS_PER_BYTE);\ - MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, *__policy, _write, link); \ - if (!_write && *__policy) \ - *__policy = 1 << *__policy; \ - } while (0) - /* get/set FEC admin field for a given speed */ static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write, enum mlx5e_fec_supported_link_mode link_mode) @@ -423,16 +408,16 @@ static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write, MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 100g); break; case MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X: - MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 50g_1x); + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 50g_1x); break; case MLX5E_FEC_SUPPORTED_LINK_MODE_100G_2X: - MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 100g_2x); + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 100g_2x); break; case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_4X: - MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 200g_4x); + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 200g_4x); break; case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_8X: - MLX5E_FEC_OVERRIDE_ADMIN_50G_POLICY(pplm, *fec_policy, write, 400g_8x); + MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 400g_8x); break; default: return -EINVAL; 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 f3f6eb081948..68e54cc1cd16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -186,6 +186,28 @@ mlx5_tc_ct_entry_has_nat(struct mlx5_ct_entry *entry) } static int +mlx5_get_label_mapping(struct mlx5_tc_ct_priv *ct_priv, + u32 *labels, u32 *id) +{ + if (!memchr_inv(labels, 0, sizeof(u32) * 4)) { + *id = 0; + return 0; + } + + if (mapping_add(ct_priv->labels_mapping, labels, id)) + return -EOPNOTSUPP; + + return 0; +} + +static void +mlx5_put_label_mapping(struct mlx5_tc_ct_priv *ct_priv, u32 id) +{ + if (id) + mapping_remove(ct_priv->labels_mapping, id); +} + +static int mlx5_tc_ct_rule_to_tuple(struct mlx5_ct_tuple *tuple, struct flow_rule *rule) { struct flow_match_control control; @@ -436,7 +458,7 @@ mlx5_tc_ct_entry_del_rule(struct mlx5_tc_ct_priv *ct_priv, mlx5_tc_rule_delete(netdev_priv(ct_priv->netdev), zone_rule->rule, attr); mlx5e_mod_hdr_detach(ct_priv->dev, ct_priv->mod_hdr_tbl, zone_rule->mh); - mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id); + mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); kfree(attr); } @@ -639,8 +661,8 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, if (!meta) return -EOPNOTSUPP; - err = mapping_add(ct_priv->labels_mapping, meta->ct_metadata.labels, - &attr->ct_attr.ct_labels_id); + err = mlx5_get_label_mapping(ct_priv, meta->ct_metadata.labels, + &attr->ct_attr.ct_labels_id); if (err) return -EOPNOTSUPP; if (nat) { @@ -677,7 +699,7 @@ mlx5_tc_ct_entry_create_mod_hdr(struct mlx5_tc_ct_priv *ct_priv, err_mapping: dealloc_mod_hdr_actions(&mod_acts); - mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id); + mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); return err; } @@ -745,7 +767,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, err_rule: mlx5e_mod_hdr_detach(ct_priv->dev, ct_priv->mod_hdr_tbl, zone_rule->mh); - mapping_remove(ct_priv->labels_mapping, attr->ct_attr.ct_labels_id); + mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); err_mod_hdr: kfree(attr); err_attr: @@ -1181,7 +1203,8 @@ int mlx5_tc_ct_add_no_trk_match(struct mlx5_flow_spec *spec) mlx5e_tc_match_to_reg_get_match(spec, CTSTATE_TO_REG, &ctstate, &ctstate_mask); - if (ctstate_mask) + + if ((ctstate & ctstate_mask) == MLX5_CT_STATE_TRK_BIT) return -EOPNOTSUPP; ctstate_mask |= MLX5_CT_STATE_TRK_BIT; @@ -1196,7 +1219,7 @@ void mlx5_tc_ct_match_del(struct mlx5_tc_ct_priv *priv, struct mlx5_ct_attr *ct_ if (!priv || !ct_attr->ct_labels_id) return; - mapping_remove(priv->labels_mapping, ct_attr->ct_labels_id); + mlx5_put_label_mapping(priv, ct_attr->ct_labels_id); } int @@ -1279,7 +1302,7 @@ mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv, ct_labels[1] = key->ct_labels[1] & mask->ct_labels[1]; ct_labels[2] = key->ct_labels[2] & mask->ct_labels[2]; ct_labels[3] = key->ct_labels[3] & mask->ct_labels[3]; - if (mapping_add(priv->labels_mapping, ct_labels, &ct_attr->ct_labels_id)) + if (mlx5_get_label_mapping(priv, ct_labels, &ct_attr->ct_labels_id)) return -EOPNOTSUPP; mlx5e_tc_match_to_reg_match(spec, LABELS_TO_REG, ct_attr->ct_labels_id, MLX5_CT_LABELS_MASK); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index f8075a604605..172e0474f2e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -685,14 +685,14 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, u16 vport_num; int err = 0; - if (flow_attr->ip_version == 4) { + if (flow_attr->tun_ip_version == 4) { /* Addresses are swapped for decap */ attr.fl.fl4.saddr = esw_attr->rx_tun_attr->dst_ip.v4; attr.fl.fl4.daddr = esw_attr->rx_tun_attr->src_ip.v4; err = mlx5e_route_lookup_ipv4_get(priv, priv->netdev, &attr); } #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) - else if (flow_attr->ip_version == 6) { + else if (flow_attr->tun_ip_version == 6) { /* Addresses are swapped for decap */ attr.fl.fl6.saddr = esw_attr->rx_tun_attr->dst_ip.v6; attr.fl.fl6.daddr = esw_attr->rx_tun_attr->src_ip.v6; @@ -718,10 +718,10 @@ int mlx5e_tc_tun_route_lookup(struct mlx5e_priv *priv, esw_attr->rx_tun_attr->decap_vport = vport_num; out: - if (flow_attr->ip_version == 4) + if (flow_attr->tun_ip_version == 4) mlx5e_route_lookup_ipv4_put(&attr); #if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6) - else if (flow_attr->ip_version == 6) + else if (flow_attr->tun_ip_version == 6) mlx5e_route_lookup_ipv6_put(&attr); #endif return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index 67de2bf36861..e1271998b937 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -21,6 +21,11 @@ enum { MLX5E_TC_TUNNEL_TYPE_MPLSOUDP, }; +struct mlx5e_encap_key { + const struct ip_tunnel_key *ip_tun_key; + struct mlx5e_tc_tunnel *tc_tunnel; +}; + struct mlx5e_tc_tunnel { int tunnel_type; enum mlx5_flow_match_level match_level; @@ -44,6 +49,8 @@ struct mlx5e_tc_tunnel { struct flow_cls_offload *f, void *headers_c, void *headers_v); + bool (*encap_info_equal)(struct mlx5e_encap_key *a, + struct mlx5e_encap_key *b); }; extern struct mlx5e_tc_tunnel vxlan_tunnel; @@ -101,6 +108,9 @@ int mlx5e_tc_tun_parse_udp_ports(struct mlx5e_priv *priv, void *headers_c, void *headers_v); +bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a, + struct mlx5e_encap_key *b); + #endif /* CONFIG_MLX5_ESWITCH */ #endif //__MLX5_EN_TC_TUNNEL_H__ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 6a116335bb21..9f16ad2c0710 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -89,6 +89,7 @@ int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow, * required to establish routing. */ flow_flag_set(flow, TUN_RX); + flow->attr->tun_ip_version = ip_version; return 0; } @@ -475,16 +476,11 @@ void mlx5e_detach_decap(struct mlx5e_priv *priv, mlx5e_decap_dealloc(priv, d); } -struct encap_key { - const struct ip_tunnel_key *ip_tun_key; - struct mlx5e_tc_tunnel *tc_tunnel; -}; - -static int cmp_encap_info(struct encap_key *a, - struct encap_key *b) +bool mlx5e_tc_tun_encap_info_equal_generic(struct mlx5e_encap_key *a, + struct mlx5e_encap_key *b) { - return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) || - a->tc_tunnel->tunnel_type != b->tc_tunnel->tunnel_type; + return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) == 0 && + a->tc_tunnel->tunnel_type == b->tc_tunnel->tunnel_type; } static int cmp_decap_info(struct mlx5e_decap_key *a, @@ -493,7 +489,7 @@ static int cmp_decap_info(struct mlx5e_decap_key *a, return memcmp(&a->key, &b->key, sizeof(b->key)); } -static int hash_encap_info(struct encap_key *key) +static int hash_encap_info(struct mlx5e_encap_key *key) { return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key), key->tc_tunnel->tunnel_type); @@ -515,18 +511,18 @@ static bool mlx5e_decap_take(struct mlx5e_decap_entry *e) } static struct mlx5e_encap_entry * -mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key, +mlx5e_encap_get(struct mlx5e_priv *priv, struct mlx5e_encap_key *key, uintptr_t hash_key) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_encap_key e_key; struct mlx5e_encap_entry *e; - struct encap_key e_key; hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, encap_hlist, hash_key) { e_key.ip_tun_key = &e->tun_info->key; e_key.tc_tunnel = e->tunnel; - if (!cmp_encap_info(&e_key, key) && + if (e->tunnel->encap_info_equal(&e_key, key) && mlx5e_encap_take(e)) return e; } @@ -693,8 +689,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5_flow_attr *attr = flow->attr; const struct ip_tunnel_info *tun_info; unsigned long tbl_time_before = 0; - struct encap_key key; struct mlx5e_encap_entry *e; + struct mlx5e_encap_key key; bool entry_created = false; unsigned short family; uintptr_t hash_key; @@ -1091,7 +1087,7 @@ int mlx5e_attach_decap_route(struct mlx5e_priv *priv, if (err || !esw_attr->rx_tun_attr->decap_vport) goto out; - key.ip_version = attr->ip_version; + key.ip_version = attr->tun_ip_version; if (key.ip_version == 4) key.endpoint_ip.v4 = esw_attr->rx_tun_attr->dst_ip.v4; else diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c index e472ed0eacfb..f5b26f5a7de4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c @@ -227,6 +227,10 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv, option_key = (struct geneve_opt *)&enc_opts.key->data[0]; option_mask = (struct geneve_opt *)&enc_opts.mask->data[0]; + if (option_mask->opt_class == 0 && option_mask->type == 0 && + !memchr_inv(option_mask->opt_data, 0, option_mask->length * 4)) + return 0; + if (option_key->length > max_tlv_option_data_len) { NL_SET_ERR_MSG_MOD(extack, "Matching on GENEVE options: unsupported option len"); @@ -325,6 +329,34 @@ static int mlx5e_tc_tun_parse_geneve(struct mlx5e_priv *priv, return mlx5e_tc_tun_parse_geneve_options(priv, spec, f); } +static bool mlx5e_tc_tun_encap_info_equal_geneve(struct mlx5e_encap_key *a, + struct mlx5e_encap_key *b) +{ + struct ip_tunnel_info *a_info; + struct ip_tunnel_info *b_info; + bool a_has_opts, b_has_opts; + + if (!mlx5e_tc_tun_encap_info_equal_generic(a, b)) + return false; + + a_has_opts = !!(a->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT); + b_has_opts = !!(b->ip_tun_key->tun_flags & TUNNEL_GENEVE_OPT); + + /* keys are equal when both don't have any options attached */ + if (!a_has_opts && !b_has_opts) + return true; + + if (a_has_opts != b_has_opts) + return false; + + /* geneve options stored in memory next to ip_tunnel_info struct */ + a_info = container_of(a->ip_tun_key, struct ip_tunnel_info, key); + b_info = container_of(b->ip_tun_key, struct ip_tunnel_info, key); + + return a_info->options_len == b_info->options_len && + memcmp(a_info + 1, b_info + 1, a_info->options_len) == 0; +} + struct mlx5e_tc_tunnel geneve_tunnel = { .tunnel_type = MLX5E_TC_TUNNEL_TYPE_GENEVE, .match_level = MLX5_MATCH_L4, @@ -334,4 +366,5 @@ struct mlx5e_tc_tunnel geneve_tunnel = { .generate_ip_tun_hdr = mlx5e_gen_ip_tunnel_header_geneve, .parse_udp_ports = mlx5e_tc_tun_parse_udp_ports_geneve, .parse_tunnel = mlx5e_tc_tun_parse_geneve, + .encap_info_equal = mlx5e_tc_tun_encap_info_equal_geneve, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c index 2805416c32a3..ada14f0574dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c @@ -94,4 +94,5 @@ struct mlx5e_tc_tunnel gre_tunnel = { .generate_ip_tun_hdr = mlx5e_gen_ip_tunnel_header_gretap, .parse_udp_ports = NULL, .parse_tunnel = mlx5e_tc_tun_parse_gretap, + .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c index 3479672e84cf..60952b33b568 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c @@ -131,4 +131,5 @@ struct mlx5e_tc_tunnel mplsoudp_tunnel = { .generate_ip_tun_hdr = generate_ip_tun_hdr, .parse_udp_ports = parse_udp_ports, .parse_tunnel = parse_tunnel, + .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index 038a0f1cecec..4267f3a1059e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -150,4 +150,5 @@ struct mlx5e_tc_tunnel vxlan_tunnel = { .generate_ip_tun_hdr = mlx5e_gen_ip_tunnel_header_vxlan, .parse_udp_ports = mlx5e_tc_tun_parse_udp_ports_vxlan, .parse_tunnel = mlx5e_tc_tun_parse_vxlan, + .encap_info_equal = mlx5e_tc_tun_encap_info_equal_generic, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 2371b83dad9c..055c3bc23733 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -441,4 +441,10 @@ static inline u16 mlx5e_stop_room_for_wqe(u16 wqe_size) return wqe_size * 2 - 1; } +static inline bool mlx5e_icosq_can_post_wqe(struct mlx5e_icosq *sq, u16 wqe_size) +{ + u16 room = sq->reserved_room + mlx5e_stop_room_for_wqe(wqe_size); + + return mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room); +} #endif 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 d06532d0baa4..19d22a63313f 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 @@ -46,7 +46,8 @@ struct mlx5e_ktls_offload_context_rx { struct tls12_crypto_info_aes_gcm_128 crypto_info; struct accel_rule rule; struct sock *sk; - struct mlx5e_rq_stats *stats; + struct mlx5e_rq_stats *rq_stats; + struct mlx5e_tls_sw_stats *sw_stats; struct completion add_ctx; u32 tirn; u32 key_id; @@ -137,11 +138,10 @@ post_static_params(struct mlx5e_icosq *sq, { struct mlx5e_set_tls_static_params_wqe *wqe; struct mlx5e_icosq_wqe_info wi; - u16 pi, num_wqebbs, room; + u16 pi, num_wqebbs; num_wqebbs = MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS; - room = mlx5e_stop_room_for_wqe(num_wqebbs); - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room))) + if (unlikely(!mlx5e_icosq_can_post_wqe(sq, num_wqebbs))) return ERR_PTR(-ENOSPC); pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs); @@ -168,11 +168,10 @@ post_progress_params(struct mlx5e_icosq *sq, { struct mlx5e_set_tls_progress_params_wqe *wqe; struct mlx5e_icosq_wqe_info wi; - u16 pi, num_wqebbs, room; + u16 pi, num_wqebbs; num_wqebbs = MLX5E_TLS_SET_PROGRESS_PARAMS_WQEBBS; - room = mlx5e_stop_room_for_wqe(num_wqebbs); - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, room))) + if (unlikely(!mlx5e_icosq_can_post_wqe(sq, num_wqebbs))) return ERR_PTR(-ENOSPC); pi = mlx5e_icosq_get_next_pi(sq, num_wqebbs); @@ -218,7 +217,7 @@ unlock: return err; err_out: - priv_rx->stats->tls_resync_req_skip++; + priv_rx->rq_stats->tls_resync_req_skip++; err = PTR_ERR(cseg); complete(&priv_rx->add_ctx); goto unlock; @@ -277,17 +276,15 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, buf->priv_rx = priv_rx; - BUILD_BUG_ON(MLX5E_KTLS_GET_PROGRESS_WQEBBS != 1); - spin_lock_bh(&sq->channel->async_icosq_lock); - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { + if (unlikely(!mlx5e_icosq_can_post_wqe(sq, MLX5E_KTLS_GET_PROGRESS_WQEBBS))) { spin_unlock_bh(&sq->channel->async_icosq_lock); err = -ENOSPC; goto err_dma_unmap; } - pi = mlx5e_icosq_get_next_pi(sq, 1); + pi = mlx5e_icosq_get_next_pi(sq, MLX5E_KTLS_GET_PROGRESS_WQEBBS); wqe = MLX5E_TLS_FETCH_GET_PROGRESS_PARAMS_WQE(sq, pi); #define GET_PSV_DS_CNT (DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS)) @@ -307,7 +304,7 @@ resync_post_get_progress_params(struct mlx5e_icosq *sq, wi = (struct mlx5e_icosq_wqe_info) { .wqe_type = MLX5E_ICOSQ_WQE_GET_PSV_TLS, - .num_wqebbs = 1, + .num_wqebbs = MLX5E_KTLS_GET_PROGRESS_WQEBBS, .tls_get_params.buf = buf, }; icosq_fill_wi(sq, pi, &wi); @@ -322,7 +319,7 @@ err_dma_unmap: err_free: kfree(buf); err_out: - priv_rx->stats->tls_resync_req_skip++; + priv_rx->rq_stats->tls_resync_req_skip++; return err; } @@ -378,13 +375,13 @@ static int resync_handle_seq_match(struct mlx5e_ktls_offload_context_rx *priv_rx cseg = post_static_params(sq, priv_rx); if (IS_ERR(cseg)) { - priv_rx->stats->tls_resync_res_skip++; + priv_rx->rq_stats->tls_resync_res_skip++; err = PTR_ERR(cseg); goto unlock; } /* Do not increment priv_rx refcnt, CQE handling is empty */ mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, cseg); - priv_rx->stats->tls_resync_res_ok++; + priv_rx->rq_stats->tls_resync_res_ok++; unlock: spin_unlock_bh(&c->async_icosq_lock); @@ -420,13 +417,13 @@ void mlx5e_ktls_handle_get_psv_completion(struct mlx5e_icosq_wqe_info *wi, auth_state = MLX5_GET(tls_progress_params, ctx, auth_state); if (tracker_state != MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_TRACKING || auth_state != MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD) { - priv_rx->stats->tls_resync_req_skip++; + priv_rx->rq_stats->tls_resync_req_skip++; goto out; } hw_seq = MLX5_GET(tls_progress_params, ctx, hw_resync_tcp_sn); tls_offload_rx_resync_async_request_end(priv_rx->sk, cpu_to_be32(hw_seq)); - priv_rx->stats->tls_resync_req_end++; + priv_rx->rq_stats->tls_resync_req_end++; out: mlx5e_ktls_priv_rx_put(priv_rx); dma_unmap_single(dev, buf->dma_addr, PROGRESS_PARAMS_PADDED_SIZE, DMA_FROM_DEVICE); @@ -609,7 +606,8 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, priv_rx->rxq = rxq; priv_rx->sk = sk; - priv_rx->stats = &priv->channel_stats[rxq].rq; + priv_rx->rq_stats = &priv->channel_stats[rxq].rq; + priv_rx->sw_stats = &priv->tls->sw_stats; mlx5e_set_ktls_rx_priv_ctx(tls_ctx, priv_rx); rqtn = priv->direct_tir[rxq].rqt.rqtn; @@ -630,7 +628,7 @@ int mlx5e_ktls_add_rx(struct net_device *netdev, struct sock *sk, if (err) goto err_post_wqes; - priv_rx->stats->tls_ctx++; + atomic64_inc(&priv_rx->sw_stats->rx_tls_ctx); return 0; @@ -666,7 +664,7 @@ void mlx5e_ktls_del_rx(struct net_device *netdev, struct tls_context *tls_ctx) if (cancel_work_sync(&resync->work)) mlx5e_ktls_priv_rx_put(priv_rx); - priv_rx->stats->tls_del++; + atomic64_inc(&priv_rx->sw_stats->rx_tls_del); if (priv_rx->rule.rule) mlx5e_accel_fs_del_sk(priv_rx->rule.rule); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index d16def68ecff..51bdf71073f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB // Copyright (c) 2019 Mellanox Technologies. +#include "en_accel/tls.h" #include "en_accel/ktls_txrx.h" #include "en_accel/ktls_utils.h" @@ -50,6 +51,7 @@ static int mlx5e_ktls_create_tis(struct mlx5_core_dev *mdev, u32 *tisn) struct mlx5e_ktls_offload_context_tx { struct tls_offload_context_tx *tx_ctx; struct tls12_crypto_info_aes_gcm_128 crypto_info; + struct mlx5e_tls_sw_stats *sw_stats; u32 expected_seq; u32 tisn; u32 key_id; @@ -99,6 +101,7 @@ int mlx5e_ktls_add_tx(struct net_device *netdev, struct sock *sk, if (err) goto err_create_key; + priv_tx->sw_stats = &priv->tls->sw_stats; priv_tx->expected_seq = start_offload_tcp_sn; priv_tx->crypto_info = *(struct tls12_crypto_info_aes_gcm_128 *)crypto_info; @@ -111,6 +114,7 @@ int mlx5e_ktls_add_tx(struct net_device *netdev, struct sock *sk, goto err_create_tis; priv_tx->ctx_post_pending = true; + atomic64_inc(&priv_tx->sw_stats->tx_tls_ctx); return 0; @@ -452,7 +456,6 @@ bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *s if (unlikely(mlx5e_ktls_tx_offload_test_and_clear_pending(priv_tx))) { mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, false, false); - stats->tls_ctx++; } seq = ntohl(tcp_hdr(skb)->seq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h index bd270a85c804..4c9274d390da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h @@ -41,10 +41,13 @@ #include "en.h" struct mlx5e_tls_sw_stats { + atomic64_t tx_tls_ctx; atomic64_t tx_tls_drop_metadata; atomic64_t tx_tls_drop_resync_alloc; atomic64_t tx_tls_drop_no_sync_data; atomic64_t tx_tls_drop_bypass_required; + atomic64_t rx_tls_ctx; + atomic64_t rx_tls_del; atomic64_t rx_tls_drop_resync_request; atomic64_t rx_tls_resync_request; atomic64_t rx_tls_resync_reply; 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 b949b9a7538b..29463bdb7715 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 @@ -45,49 +45,60 @@ static const struct counter_desc mlx5e_tls_sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_bypass_required) }, }; +static const struct counter_desc mlx5e_ktls_sw_stats_desc[] = { + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_ctx) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_ctx) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, rx_tls_del) }, +}; + #define MLX5E_READ_CTR_ATOMIC64(ptr, dsc, i) \ atomic64_read((atomic64_t *)((char *)(ptr) + (dsc)[i].offset)) -#define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc) - -static bool is_tls_atomic_stats(struct mlx5e_priv *priv) +static const struct counter_desc *get_tls_atomic_stats(struct mlx5e_priv *priv) { - return priv->tls && !mlx5_accel_is_ktls_device(priv->mdev); + if (!priv->tls) + return NULL; + if (mlx5_accel_is_ktls_device(priv->mdev)) + return mlx5e_ktls_sw_stats_desc; + return mlx5e_tls_sw_stats_desc; } int mlx5e_tls_get_count(struct mlx5e_priv *priv) { - if (!is_tls_atomic_stats(priv)) + if (!priv->tls) return 0; - - return NUM_TLS_SW_COUNTERS; + if (mlx5_accel_is_ktls_device(priv->mdev)) + return ARRAY_SIZE(mlx5e_ktls_sw_stats_desc); + return ARRAY_SIZE(mlx5e_tls_sw_stats_desc); } int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { - unsigned int i, idx = 0; + const struct counter_desc *stats_desc; + unsigned int i, n, idx = 0; - if (!is_tls_atomic_stats(priv)) - return 0; + stats_desc = get_tls_atomic_stats(priv); + n = mlx5e_tls_get_count(priv); - for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) + for (i = 0; i < n; i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, - mlx5e_tls_sw_stats_desc[i].format); + stats_desc[i].format); - return NUM_TLS_SW_COUNTERS; + return n; } int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { - int i, idx = 0; + const struct counter_desc *stats_desc; + unsigned int i, n, idx = 0; - if (!is_tls_atomic_stats(priv)) - return 0; + stats_desc = get_tls_atomic_stats(priv); + n = mlx5e_tls_get_count(priv); - for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) + for (i = 0; i < n; i++) data[idx++] = MLX5E_READ_CTR_ATOMIC64(&priv->tls->sw_stats, - mlx5e_tls_sw_stats_desc, i); + stats_desc, i); - return NUM_TLS_SW_COUNTERS; + return n; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index abdf721bb264..53802e18af90 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -758,11 +758,11 @@ static int get_fec_supported_advertised(struct mlx5_core_dev *dev, return 0; } -static void ptys2ethtool_supported_advertised_port(struct ethtool_link_ksettings *link_ksettings, - u32 eth_proto_cap, - u8 connector_type, bool ext) +static void ptys2ethtool_supported_advertised_port(struct mlx5_core_dev *mdev, + struct ethtool_link_ksettings *link_ksettings, + u32 eth_proto_cap, u8 connector_type) { - if ((!connector_type && !ext) || connector_type >= MLX5E_CONNECTOR_TYPE_NUMBER) { + if (!MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type)) { if (eth_proto_cap & (MLX5E_PROT_MASK(MLX5E_10GBASE_CR) | MLX5E_PROT_MASK(MLX5E_10GBASE_SR) | MLX5E_PROT_MASK(MLX5E_40GBASE_CR4) @@ -898,9 +898,9 @@ static int ptys2connector_type[MLX5E_CONNECTOR_TYPE_NUMBER] = { [MLX5E_PORT_OTHER] = PORT_OTHER, }; -static u8 get_connector_port(u32 eth_proto, u8 connector_type, bool ext) +static u8 get_connector_port(struct mlx5_core_dev *mdev, u32 eth_proto, u8 connector_type) { - if ((connector_type || ext) && connector_type < MLX5E_CONNECTOR_TYPE_NUMBER) + if (MLX5_CAP_PCAM_FEATURE(mdev, ptys_connector_type)) return ptys2connector_type[connector_type]; if (eth_proto & @@ -1001,11 +1001,11 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv, data_rate_oper, link_ksettings); eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap; - - link_ksettings->base.port = get_connector_port(eth_proto_oper, - connector_type, ext); - ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin, - connector_type, ext); + connector_type = connector_type < MLX5E_CONNECTOR_TYPE_NUMBER ? + connector_type : MLX5E_PORT_UNKNOWN; + link_ksettings->base.port = get_connector_port(mdev, eth_proto_oper, connector_type); + ptys2ethtool_supported_advertised_port(mdev, link_ksettings, eth_proto_admin, + connector_type); get_lp_advertising(mdev, eth_proto_lp, link_ksettings); if (an_status == MLX5_AN_COMPLETE) @@ -1887,6 +1887,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, { struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = priv->mdev; + int err; if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; @@ -1896,7 +1897,10 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, return -EINVAL; } - mlx5e_modify_rx_cqe_compression_locked(priv, enable); + err = mlx5e_modify_rx_cqe_compression_locked(priv, enable); + if (err) + return err; + priv->channels.params.rx_cqe_compress_def = enable; return 0; @@ -2014,8 +2018,13 @@ static int set_pflag_tx_port_ts(struct net_device *netdev, bool enable) */ if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + struct mlx5e_params old_params; + + old_params = priv->channels.params; priv->channels.params = new_channels.params; err = mlx5e_num_channels_changed(priv); + if (err) + priv->channels.params = old_params; goto out; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index ec2fcb2a2977..5db63b9f3b70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -334,9 +334,9 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq rq->wqe_overflow.addr); } -static inline u64 mlx5e_get_mpwqe_offset(struct mlx5e_rq *rq, u16 wqe_ix) +static u64 mlx5e_get_mpwqe_offset(u16 wqe_ix) { - return (wqe_ix << MLX5E_LOG_ALIGNED_MPWQE_PPW) << PAGE_SHIFT; + return MLX5E_REQUIRED_MTTS(wqe_ix) << PAGE_SHIFT; } static void mlx5e_init_frags_partition(struct mlx5e_rq *rq) @@ -577,7 +577,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, mlx5_wq_ll_get_wqe(&rq->mpwqe.wq, i); u32 byte_count = rq->mpwqe.num_strides << rq->mpwqe.log_stride_sz; - u64 dma_offset = mlx5e_get_mpwqe_offset(rq, i); + u64 dma_offset = mlx5e_get_mpwqe_offset(i); wqe->data[0].addr = cpu_to_be64(dma_offset + rq->buff.headroom); wqe->data[0].byte_count = cpu_to_be32(byte_count); @@ -1091,6 +1091,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, sq->channel = c; sq->uar_map = mdev->mlx5e_res.bfreg.map; + sq->reserved_room = param->stop_room; param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); @@ -2350,6 +2351,24 @@ void mlx5e_build_icosq_param(struct mlx5e_priv *priv, mlx5e_build_ico_cq_param(priv, log_wq_size, ¶m->cqp); } +static void mlx5e_build_async_icosq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + u8 log_wq_size, + struct mlx5e_sq_param *param) +{ + void *sqc = param->sqc; + void *wq = MLX5_ADDR_OF(sqc, sqc, wq); + + mlx5e_build_sq_param_common(priv, param); + + /* async_icosq is used by XSK only if xdp_prog is active */ + if (params->xdp_prog) + param->stop_room = mlx5e_stop_room_for_wqe(1); /* for XSK NOP */ + MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq)); + MLX5_SET(wq, wq, log_wq_sz, log_wq_size); + mlx5e_build_ico_cq_param(priv, log_wq_size, ¶m->cqp); +} + void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv, struct mlx5e_params *params, struct mlx5e_sq_param *param) @@ -2368,8 +2387,9 @@ static u8 mlx5e_build_icosq_log_wq_sz(struct mlx5e_params *params, { switch (params->rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - return order_base_2(MLX5E_UMR_WQEBBS) + - mlx5e_get_rq_log_wq_sz(rqp->rqc); + return max_t(u8, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE, + order_base_2(MLX5E_UMR_WQEBBS) + + mlx5e_get_rq_log_wq_sz(rqp->rqc)); default: /* MLX5_WQ_TYPE_CYCLIC */ return MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE; } @@ -2397,7 +2417,7 @@ static void mlx5e_build_channel_param(struct mlx5e_priv *priv, mlx5e_build_sq_param(priv, params, &cparam->txq_sq); mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq); mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq); - mlx5e_build_icosq_param(priv, async_icosq_log_wq_sz, &cparam->async_icosq); + mlx5e_build_async_icosq_param(priv, params, async_icosq_log_wq_sz, &cparam->async_icosq); } int mlx5e_open_channels(struct mlx5e_priv *priv, @@ -2502,8 +2522,10 @@ void mlx5e_close_channels(struct mlx5e_channels *chs) { int i; - if (chs->port_ptp) + if (chs->port_ptp) { mlx5e_port_ptp_close(chs->port_ptp); + chs->port_ptp = NULL; + } for (i = 0; i < chs->num; i++) mlx5e_close_channel(chs->c[i]); @@ -3815,6 +3837,15 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) s->tx_dropped += sq_stats->dropped; } } + if (priv->port_ptp_opened) { + for (i = 0; i < priv->max_opened_tc; i++) { + struct mlx5e_sq_stats *sq_stats = &priv->port_ptp_stats.sq[i]; + + s->tx_packets += sq_stats->packets; + s->tx_bytes += sq_stats->bytes; + s->tx_dropped += sq_stats->dropped; + } + } } void @@ -3834,10 +3865,17 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) } if (mlx5e_is_uplink_rep(priv)) { + struct mlx5e_vport_stats *vstats = &priv->stats.vport; + stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok); stats->rx_bytes = PPORT_802_3_GET(pstats, a_octets_received_ok); stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok); stats->tx_bytes = PPORT_802_3_GET(pstats, a_octets_transmitted_ok); + + /* 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); } else { mlx5e_fold_sw_stats64(priv, stats); } @@ -4683,8 +4721,10 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) struct mlx5e_channel *c = priv->channels.c[i]; mlx5e_rq_replace_xdp_prog(&c->rq, prog); - if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) { + bpf_prog_inc(prog); mlx5e_rq_replace_xdp_prog(&c->xskrq, prog); + } } unlock: @@ -4958,6 +4998,11 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16 priv->max_nch); params->num_tc = 1; + /* Set an initial non-zero value, so that mlx5e_select_queue won't + * divide by zero if called before first activating channels. + */ + priv->num_tc_x_num_ch = params->num_channels * params->num_tc; + /* SQ */ params->log_sq_size = is_kdump_kernel() ? MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE : @@ -5474,8 +5519,6 @@ int mlx5e_priv_init(struct mlx5e_priv *priv, struct net_device *netdev, struct mlx5_core_dev *mdev) { - memset(priv, 0, sizeof(*priv)); - /* priv init */ priv->mdev = mdev; priv->netdev = netdev; @@ -5508,12 +5551,18 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv) { int i; + /* bail if change profile failed and also rollback failed */ + if (!priv->mdev) + return; + destroy_workqueue(priv->wq); free_cpumask_var(priv->scratchpad.cpumask); for (i = 0; i < priv->htb.max_qos_sqs; i++) kfree(priv->htb.qos_sq_stats[i]); kvfree(priv->htb.qos_sq_stats); + + memset(priv, 0, sizeof(*priv)); } struct net_device * @@ -5630,11 +5679,10 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) } static int -mlx5e_netdev_attach_profile(struct mlx5e_priv *priv, +mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, const struct mlx5e_profile *new_profile, void *new_ppriv) { - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_priv *priv = netdev_priv(netdev); int err; err = mlx5e_priv_init(priv, netdev, mdev); @@ -5647,10 +5695,16 @@ mlx5e_netdev_attach_profile(struct mlx5e_priv *priv, priv->ppriv = new_ppriv; err = new_profile->init(priv->mdev, priv->netdev); if (err) - return err; + goto priv_cleanup; err = mlx5e_attach_netdev(priv); if (err) - new_profile->cleanup(priv); + goto profile_cleanup; + return err; + +profile_cleanup: + new_profile->cleanup(priv); +priv_cleanup: + mlx5e_priv_cleanup(priv); return err; } @@ -5659,13 +5713,14 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, { unsigned int new_max_nch = mlx5e_calc_max_nch(priv, new_profile); const struct mlx5e_profile *orig_profile = priv->profile; + struct net_device *netdev = priv->netdev; + struct mlx5_core_dev *mdev = priv->mdev; void *orig_ppriv = priv->ppriv; int err, rollback_err; /* sanity */ if (new_max_nch != priv->max_nch) { - netdev_warn(priv->netdev, - "%s: Replacing profile with different max channels\n", + netdev_warn(netdev, "%s: Replacing profile with different max channels\n", __func__); return -EINVAL; } @@ -5675,22 +5730,19 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv, priv->profile->cleanup(priv); mlx5e_priv_cleanup(priv); - err = mlx5e_netdev_attach_profile(priv, new_profile, new_ppriv); + err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv); if (err) { /* roll back to original profile */ - netdev_warn(priv->netdev, "%s: new profile init failed, %d\n", - __func__, err); + netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err); goto rollback; } return 0; rollback: - rollback_err = mlx5e_netdev_attach_profile(priv, orig_profile, orig_ppriv); - if (rollback_err) { - netdev_err(priv->netdev, - "%s: failed to rollback to orig profile, %d\n", + rollback_err = mlx5e_netdev_attach_profile(netdev, mdev, orig_profile, orig_ppriv); + if (rollback_err) + netdev_err(netdev, "%s: failed to rollback to orig profile, %d\n", __func__, rollback_err); - } return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index a132fff7a980..8d39bfee84a9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1107,8 +1107,9 @@ static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv) mlx5e_rep_tc_enable(priv); - mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK, - 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO); + if (MLX5_CAP_GEN(mdev, uplink_follow)) + mlx5_modify_vport_admin_state(mdev, MLX5_VPORT_STATE_OP_MOD_UPLINK, + 0, 0, MLX5_VPORT_ADMIN_STATE_AUTO); mlx5_lag_add(mdev, netdev); priv->events_nb.notifier_call = uplink_rep_async_event; mlx5_notifier_register(mdev, &priv->events_nb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 1b6ad94ebb10..249d8905e644 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -500,7 +500,6 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) struct mlx5e_icosq *sq = rq->icosq; struct mlx5_wq_cyc *wq = &sq->wq; struct mlx5e_umr_wqe *umr_wqe; - u16 xlt_offset = ix << (MLX5E_LOG_ALIGNED_MPWQE_PPW - 1); u16 pi; int err; int i; @@ -531,7 +530,8 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) umr_wqe->ctrl.opmod_idx_opcode = cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | MLX5_OPCODE_UMR); - umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset); + umr_wqe->uctrl.xlt_offset = + cpu_to_be16(MLX5_ALIGNED_MTTS_OCTW(MLX5E_REQUIRED_MTTS(ix))); sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) { .wqe_type = MLX5E_ICOSQ_WQE_UMR_RX, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 92c5b81427b9..88a01c59ce61 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -116,7 +116,6 @@ static const struct counter_desc sw_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ctx) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) }, @@ -180,8 +179,6 @@ static const struct counter_desc sw_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_bytes) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_ctx) }, - { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_del) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_pkt) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_start) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_resync_req_end) }, @@ -342,8 +339,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s, #ifdef CONFIG_MLX5_EN_TLS s->rx_tls_decrypted_packets += rq_stats->tls_decrypted_packets; s->rx_tls_decrypted_bytes += rq_stats->tls_decrypted_bytes; - s->rx_tls_ctx += rq_stats->tls_ctx; - s->rx_tls_del += rq_stats->tls_del; s->rx_tls_resync_req_pkt += rq_stats->tls_resync_req_pkt; s->rx_tls_resync_req_start += rq_stats->tls_resync_req_start; s->rx_tls_resync_req_end += rq_stats->tls_resync_req_end; @@ -390,7 +385,6 @@ static void mlx5e_stats_grp_sw_update_stats_sq(struct mlx5e_sw_stats *s, #ifdef CONFIG_MLX5_EN_TLS s->tx_tls_encrypted_packets += sq_stats->tls_encrypted_packets; s->tx_tls_encrypted_bytes += sq_stats->tls_encrypted_bytes; - s->tx_tls_ctx += sq_stats->tls_ctx; s->tx_tls_ooo += sq_stats->tls_ooo; s->tx_tls_dump_bytes += sq_stats->tls_dump_bytes; s->tx_tls_dump_packets += sq_stats->tls_dump_packets; @@ -1622,8 +1616,6 @@ static const struct counter_desc rq_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_bytes) }, - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_ctx) }, - { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_del) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_pkt) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_start) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_resync_req_end) }, @@ -1650,7 +1642,6 @@ static const struct counter_desc sq_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) }, - { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ctx) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ooo) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) }, { MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) }, @@ -1776,7 +1767,6 @@ static const struct counter_desc qos_sq_stats_desc[] = { #ifdef CONFIG_MLX5_EN_TLS { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_packets) }, { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) }, - { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_ctx) }, { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_ooo) }, { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) }, { MLX5E_DECLARE_QOS_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 93c41312fb03..adf9b7b8b712 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -191,7 +191,6 @@ struct mlx5e_sw_stats { #ifdef CONFIG_MLX5_EN_TLS u64 tx_tls_encrypted_packets; u64 tx_tls_encrypted_bytes; - u64 tx_tls_ctx; u64 tx_tls_ooo; u64 tx_tls_dump_packets; u64 tx_tls_dump_bytes; @@ -202,8 +201,6 @@ struct mlx5e_sw_stats { u64 rx_tls_decrypted_packets; u64 rx_tls_decrypted_bytes; - u64 rx_tls_ctx; - u64 rx_tls_del; u64 rx_tls_resync_req_pkt; u64 rx_tls_resync_req_start; u64 rx_tls_resync_req_end; @@ -334,8 +331,6 @@ struct mlx5e_rq_stats { #ifdef CONFIG_MLX5_EN_TLS u64 tls_decrypted_packets; u64 tls_decrypted_bytes; - u64 tls_ctx; - u64 tls_del; u64 tls_resync_req_pkt; u64 tls_resync_req_start; u64 tls_resync_req_end; @@ -364,7 +359,6 @@ struct mlx5e_sq_stats { #ifdef CONFIG_MLX5_EN_TLS u64 tls_encrypted_packets; u64 tls_encrypted_bytes; - u64 tls_ctx; u64 tls_ooo; u64 tls_dump_packets; u64 tls_dump_bytes; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 0da69b98f38f..d675107d9eca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1895,6 +1895,9 @@ static int mlx5e_flower_parse_meta(struct net_device *filter_dev, return 0; flow_rule_match_meta(rule, &match); + if (!match.mask->ingress_ifindex) + return 0; + if (match.mask->ingress_ifindex != 0xFFFFFFFF) { NL_SET_ERR_MSG_MOD(extack, "Unsupported ingress ifindex mask"); return -EOPNOTSUPP; @@ -2296,6 +2299,16 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, *match_level = MLX5_MATCH_L4; } + /* Currenlty supported only for MPLS over UDP */ + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS) && + !netif_is_bareudp(filter_dev)) { + NL_SET_ERR_MSG_MOD(extack, + "Matching on MPLS is supported only for MPLS over UDP"); + netdev_err(priv->netdev, + "Matching on MPLS is supported only for MPLS over UDP\n"); + return -EOPNOTSUPP; + } + return 0; } @@ -2899,6 +2912,37 @@ static int is_action_keys_supported(const struct flow_action_entry *act, return 0; } +static bool modify_tuple_supported(bool modify_tuple, bool ct_clear, + bool ct_flow, struct netlink_ext_ack *extack, + struct mlx5e_priv *priv, + struct mlx5_flow_spec *spec) +{ + if (!modify_tuple || ct_clear) + return true; + + if (ct_flow) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload tuple modification with non-clear ct()"); + netdev_info(priv->netdev, + "can't offload tuple modification with non-clear ct()"); + return false; + } + + /* Add ct_state=-trk match so it will be offloaded for non ct flows + * (or after clear action), as otherwise, since the tuple is changed, + * we can't restore ct state + */ + if (mlx5_tc_ct_add_no_trk_match(spec)) { + NL_SET_ERR_MSG_MOD(extack, + "can't offload tuple modification with ct matches and no ct(clear) action"); + netdev_info(priv->netdev, + "can't offload tuple modification with ct matches and no ct(clear) action"); + return false; + } + + return true; +} + static bool modify_header_match_supported(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct flow_action *flow_action, @@ -2937,18 +2981,9 @@ static bool modify_header_match_supported(struct mlx5e_priv *priv, return err; } - /* Add ct_state=-trk match so it will be offloaded for non ct flows - * (or after clear action), as otherwise, since the tuple is changed, - * we can't restore ct state - */ - if (!ct_clear && modify_tuple && - mlx5_tc_ct_add_no_trk_match(spec)) { - NL_SET_ERR_MSG_MOD(extack, - "can't offload tuple modify header with ct matches"); - netdev_info(priv->netdev, - "can't offload tuple modify header with ct matches"); + if (!modify_tuple_supported(modify_tuple, ct_clear, ct_flow, extack, + priv, spec)) return false; - } ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol); if (modify_ip_header && ip_proto != IPPROTO_TCP && @@ -4445,7 +4480,8 @@ static int apply_police_params(struct mlx5e_priv *priv, u64 rate, */ if (rate) { rate = (rate * BITS_PER_BYTE) + 500000; - rate_mbps = max_t(u64, do_div(rate, 1000000), 1); + do_div(rate, 1000000); + rate_mbps = max_t(u32, rate, 1); } err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 89003ae7775a..25c091795bcd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -79,6 +79,7 @@ struct mlx5_flow_attr { u8 inner_match_level; u8 outer_match_level; u8 ip_version; + u8 tun_ip_version; u32 flags; union { struct mlx5_esw_flow_attr esw_attr[0]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 174dfbc996c6..1fa9c18563da 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -931,13 +931,24 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev) mutex_unlock(&table->lock); } +#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING +#define MLX5_MAX_ASYNC_EQS 4 +#else +#define MLX5_MAX_ASYNC_EQS 3 +#endif + int mlx5_eq_table_create(struct mlx5_core_dev *dev) { struct mlx5_eq_table *eq_table = dev->priv.eq_table; + int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ? + MLX5_CAP_GEN(dev, max_num_eqs) : + 1 << MLX5_CAP_GEN(dev, log_max_eq); int err; eq_table->num_comp_eqs = - mlx5_irq_get_num_comp(eq_table->irq_table); + min_t(int, + mlx5_irq_get_num_comp(eq_table->irq_table), + num_eqs - MLX5_MAX_ASYNC_EQS); err = create_async_eqs(dev); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c index 6f6772bf61a2..3da7becc1069 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c @@ -248,7 +248,7 @@ err_mod_hdr_regc0: err_ethertype: kfree(rule); out: - kfree(rule_spec); + kvfree(rule_spec); return err; } @@ -328,7 +328,7 @@ static int mlx5_create_indir_recirc_group(struct mlx5_eswitch *esw, e->recirc_cnt = 0; out: - kfree(in); + kvfree(in); return err; } @@ -347,7 +347,7 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw, spec = kvzalloc(sizeof(*spec), GFP_KERNEL); if (!spec) { - kfree(in); + kvfree(in); return -ENOMEM; } @@ -371,8 +371,8 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw, } err_out: - kfree(spec); - kfree(in); + kvfree(spec); + kvfree(in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 94cb0217b4f3..d4a2f8d1ee9f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -537,6 +537,14 @@ esw_setup_vport_dests(struct mlx5_flow_destination *dest, struct mlx5_flow_act * return i; } +static bool +esw_src_port_rewrite_supported(struct mlx5_eswitch *esw) +{ + return MLX5_CAP_GEN(esw->dev, reg_c_preserve) && + mlx5_eswitch_vport_match_metadata_enabled(esw) && + MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ignore_flow_level); +} + static int esw_setup_dests(struct mlx5_flow_destination *dest, struct mlx5_flow_act *flow_act, @@ -550,8 +558,7 @@ esw_setup_dests(struct mlx5_flow_destination *dest, int err = 0; if (!mlx5_eswitch_termtbl_required(esw, attr, flow_act, spec) && - MLX5_CAP_GEN(esw_attr->in_mdev, reg_c_preserve) && - mlx5_eswitch_vport_match_metadata_enabled(esw)) + esw_src_port_rewrite_supported(esw)) attr->flags |= MLX5_ESW_ATTR_FLAG_SRC_REWRITE; if (attr->dest_ft) { @@ -1715,36 +1722,40 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw) } esw->fdb_table.offloads.send_to_vport_grp = g; - /* meta send to vport */ - memset(flow_group_in, 0, inlen); - MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, - MLX5_MATCH_MISC_PARAMETERS_2); - - match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); + if (esw_src_port_rewrite_supported(esw)) { + /* meta send to vport */ + memset(flow_group_in, 0, inlen); + MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, + MLX5_MATCH_MISC_PARAMETERS_2); - MLX5_SET(fte_match_param, match_criteria, - misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask()); - MLX5_SET(fte_match_param, match_criteria, - misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK); + match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria); - num_vfs = esw->esw_funcs.num_vfs; - if (num_vfs) { - 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 + num_vfs - 1); - ix += num_vfs; + MLX5_SET(fte_match_param, match_criteria, + misc_parameters_2.metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_mask()); + MLX5_SET(fte_match_param, match_criteria, + misc_parameters_2.metadata_reg_c_1, ESW_TUN_MASK); - g = mlx5_create_flow_group(fdb, flow_group_in); - if (IS_ERR(g)) { - err = PTR_ERR(g); - esw_warn(dev, "Failed to create send-to-vport meta flow group err(%d)\n", - err); - goto send_vport_meta_err; + num_vfs = esw->esw_funcs.num_vfs; + if (num_vfs) { + 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 + num_vfs - 1); + ix += num_vfs; + + g = mlx5_create_flow_group(fdb, flow_group_in); + if (IS_ERR(g)) { + err = PTR_ERR(g); + esw_warn(dev, "Failed to create send-to-vport meta flow group err(%d)\n", + err); + goto send_vport_meta_err; + } + esw->fdb_table.offloads.send_to_vport_meta_grp = g; + + err = mlx5_eswitch_add_send_to_vport_meta_rules(esw); + if (err) + goto meta_rule_err; } - esw->fdb_table.offloads.send_to_vport_meta_grp = g; - - err = mlx5_eswitch_add_send_to_vport_meta_rules(esw); - if (err) - goto meta_rule_err; } if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c index 80da50e12915..bd66ab2af5b5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c @@ -575,6 +575,7 @@ static int mlx5_fpga_conn_create_qp(struct mlx5_fpga_conn *conn, MLX5_SET(qpc, qpc, log_sq_size, ilog2(conn->qp.sq.size)); MLX5_SET(qpc, qpc, cqn_snd, conn->cq.mcq.cqn); MLX5_SET(qpc, qpc, cqn_rcv, conn->cq.mcq.cqn); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(mdev)); MLX5_SET64(qpc, qpc, dbr_addr, conn->qp.wq_ctrl.db.dma); if (MLX5_CAP_GEN(mdev, cqe_version) == 1) MLX5_SET(qpc, qpc, user_index, 0xFFFFFF); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 1eeca45cfcdf..6f7cef47e04c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -233,6 +233,7 @@ int mlx5i_create_underlay_qp(struct mlx5e_priv *priv) } qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(priv->mdev)); MLX5_SET(qpc, qpc, st, MLX5_QP_ST_UD); MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); MLX5_SET(qpc, qpc, ulp_stateless_offload_mode, @@ -694,6 +695,7 @@ static int mlx5i_check_required_hca_cap(struct mlx5_core_dev *mdev) static void mlx5_rdma_netdev_free(struct net_device *netdev) { struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5_core_dev *mdev = priv->mdev; struct mlx5i_priv *ipriv = priv->ppriv; const struct mlx5e_profile *profile = priv->profile; @@ -702,7 +704,7 @@ static void mlx5_rdma_netdev_free(struct net_device *netdev) if (!ipriv->sub_interface) { mlx5i_pkey_qpn_ht_cleanup(netdev); - mlx5e_destroy_mdev_resources(priv->mdev); + mlx5e_destroy_mdev_resources(mdev); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index b0e129d0f6d8..1e7f26b240de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -495,15 +495,15 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, return -EINVAL; field_select = MLX5_MTPPS_FS_ENABLE; + pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, rq->perout.index); + if (pin < 0) + return -EBUSY; + if (on) { bool rt_mode = mlx5_real_time_mode(mdev); u32 nsec; s64 sec; - pin = ptp_find_pin(clock->ptp, PTP_PF_PEROUT, rq->perout.index); - if (pin < 0) - return -EBUSY; - pin_mode = MLX5_PIN_MODE_OUT; pattern = MLX5_OUT_PATTERN_PERIODIC; ts.tv_sec = rq->perout.period.sec; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c index b265f27b2166..90b524c59f3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c @@ -181,15 +181,13 @@ static int mlx5_sf_dev_vhca_arm_all(struct mlx5_sf_dev_table *table) u16 max_functions; u16 function_id; int err = 0; - bool ecpu; int i; max_functions = mlx5_sf_max_functions(dev); function_id = MLX5_CAP_GEN(dev, sf_base_id); - ecpu = mlx5_read_embedded_cpu(dev); /* Arm the vhca context as the vhca event notifier */ for (i = 0; i < max_functions; i++) { - err = mlx5_vhca_event_arm(dev, function_id, ecpu); + err = mlx5_vhca_event_arm(dev, function_id); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c index 58b6be0b03d7..a5a0f60bef66 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c @@ -6,7 +6,7 @@ #include "sf.h" #include "mlx5_ifc_vhca_event.h" #include "vhca_event.h" -#include "ecpf.h" +#include "mlx5_core.h" struct mlx5_sf_hw { u32 usr_sfnum; @@ -18,7 +18,6 @@ struct mlx5_sf_hw_table { struct mlx5_core_dev *dev; struct mlx5_sf_hw *sfs; int max_local_functions; - u8 ecpu: 1; struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */ struct notifier_block vhca_nb; }; @@ -64,7 +63,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum) } if (sw_id == -ENOSPC) { err = -ENOSPC; - goto err; + goto exist_err; } hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, sw_id); @@ -72,7 +71,7 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum) if (err) goto err; - err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, table->ecpu, usr_sfnum); + err = mlx5_modify_vhca_sw_id(dev, hw_fn_id, usr_sfnum); if (err) goto vhca_err; @@ -118,7 +117,7 @@ void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u16 id) hw_fn_id = mlx5_sf_sw_to_hw_id(dev, id); mutex_lock(&table->table_lock); - err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, table->ecpu, out, sizeof(out)); + err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, out, sizeof(out)); if (err) goto err; state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state); @@ -164,7 +163,6 @@ int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev) table->dev = dev; table->sfs = sfs; table->max_local_functions = max_functions; - table->ecpu = mlx5_read_embedded_cpu(dev); dev->priv.sf_hw_table = table; mlx5_core_dbg(dev, "SF HW table: max sfs = %d\n", max_functions); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h index 1daf5a122ba3..4fc870140d71 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/mlx5_ifc_vhca_event.h @@ -20,7 +20,7 @@ struct mlx5_ifc_vhca_state_context_bits { u8 sw_function_id[0x20]; - u8 reserved_at_40[0x80]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_vhca_state_out_bits { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c index af2f2dd9db25..28b14b05086f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.c @@ -19,52 +19,51 @@ struct mlx5_vhca_event_work { struct mlx5_vhca_state_event event; }; -int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, - bool ecpu, u32 *out, u32 outlen) +int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, u32 *out, u32 outlen) { u32 in[MLX5_ST_SZ_DW(query_vhca_state_in)] = {}; MLX5_SET(query_vhca_state_in, in, opcode, MLX5_CMD_OP_QUERY_VHCA_STATE); MLX5_SET(query_vhca_state_in, in, function_id, function_id); - MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, ecpu); + MLX5_SET(query_vhca_state_in, in, embedded_cpu_function, 0); return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } static int mlx5_cmd_modify_vhca_state(struct mlx5_core_dev *dev, u16 function_id, - bool ecpu, u32 *in, u32 inlen) + u32 *in, u32 inlen) { u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {}; MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE); MLX5_SET(modify_vhca_state_in, in, function_id, function_id); - MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu); + MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0); return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); } -int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id) +int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id) { u32 out[MLX5_ST_SZ_DW(modify_vhca_state_out)] = {}; u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {}; MLX5_SET(modify_vhca_state_in, in, opcode, MLX5_CMD_OP_MODIFY_VHCA_STATE); MLX5_SET(modify_vhca_state_in, in, function_id, function_id); - MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, ecpu); + MLX5_SET(modify_vhca_state_in, in, embedded_cpu_function, 0); MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.sw_function_id, 1); MLX5_SET(modify_vhca_state_in, in, vhca_state_context.sw_function_id, sw_fn_id); return mlx5_cmd_exec_inout(dev, modify_vhca_state, in, out); } -int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu) +int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id) { u32 in[MLX5_ST_SZ_DW(modify_vhca_state_in)] = {}; MLX5_SET(modify_vhca_state_in, in, vhca_state_context.arm_change_event, 1); MLX5_SET(modify_vhca_state_in, in, vhca_state_field_select.arm_change_event, 1); - return mlx5_cmd_modify_vhca_state(dev, function_id, ecpu, in, sizeof(in)); + return mlx5_cmd_modify_vhca_state(dev, function_id, in, sizeof(in)); } static void @@ -73,7 +72,7 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event * u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {}; int err; - err = mlx5_cmd_query_vhca_state(dev, event->function_id, event->ecpu, out, sizeof(out)); + err = mlx5_cmd_query_vhca_state(dev, event->function_id, out, sizeof(out)); if (err) return; @@ -82,7 +81,7 @@ mlx5_vhca_event_notify(struct mlx5_core_dev *dev, struct mlx5_vhca_state_event * event->new_vhca_state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state); - mlx5_vhca_event_arm(dev, event->function_id, event->ecpu); + mlx5_vhca_event_arm(dev, event->function_id); blocking_notifier_call_chain(&dev->priv.vhca_state_notifier->n_head, 0, event); } @@ -94,6 +93,7 @@ static void mlx5_vhca_state_work_handler(struct work_struct *_work) struct mlx5_core_dev *dev = notifier->dev; mlx5_vhca_event_notify(dev, &work->event); + kfree(work); } static int @@ -110,7 +110,6 @@ mlx5_vhca_state_change_notifier(struct notifier_block *nb, unsigned long type, v INIT_WORK(&work->work, &mlx5_vhca_state_work_handler); work->notifier = notifier; work->event.function_id = be16_to_cpu(eqe->data.vhca_state.function_id); - work->event.ecpu = be16_to_cpu(eqe->data.vhca_state.ec_function); mlx5_events_work_enqueue(notifier->dev, &work->work); return NOTIFY_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h index 1fe1ec6f4d4b..013cdfe90616 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/vhca_event.h @@ -10,7 +10,6 @@ struct mlx5_vhca_state_event { u16 function_id; u16 sw_function_id; u8 new_vhca_state; - bool ecpu; }; static inline bool mlx5_vhca_event_supported(const struct mlx5_core_dev *dev) @@ -25,10 +24,10 @@ void mlx5_vhca_event_start(struct mlx5_core_dev *dev); void mlx5_vhca_event_stop(struct mlx5_core_dev *dev); int mlx5_vhca_event_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb); void mlx5_vhca_event_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb); -int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, bool ecpu, u32 sw_fn_id); -int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id, bool ecpu); +int mlx5_modify_vhca_sw_id(struct mlx5_core_dev *dev, u16 function_id, u32 sw_fn_id); +int mlx5_vhca_event_arm(struct mlx5_core_dev *dev, u16 function_id); int mlx5_cmd_query_vhca_state(struct mlx5_core_dev *dev, u16 function_id, - bool ecpu, u32 *out, u32 outlen); + u32 *out, u32 outlen); #else static inline void mlx5_vhca_state_cap_handle(struct mlx5_core_dev *dev, void *set_hca_cap) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c index 83c4c877d558..8a6a56f9dc4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -169,6 +169,7 @@ static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, MLX5_SET(qpc, qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt)); MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ); MLX5_SET(qpc, qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt)); + MLX5_SET(qpc, qpc, ts_format, mlx5_get_qp_default_ts(mdev)); MLX5_SET64(qpc, qpc, dbr_addr, dr_qp->wq_ctrl.db.dma); if (MLX5_CAP_GEN(mdev, cqe_version) == 1) MLX5_SET(qpc, qpc, user_index, 0xFFFFFF); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 4088d6e51508..9143ec326ebf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -264,8 +264,8 @@ static void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) static u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p) { u64 index = - (MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) | - MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32) << 26); + ((u64)MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) | + ((u64)MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_39_32)) << 26); return index << 6; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index d9d9e1f488f9..ba28ac7e79bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -21,6 +21,7 @@ #include <net/red.h> #include <net/vxlan.h> #include <net/flow_offload.h> +#include <net/inet_ecn.h> #include "port.h" #include "core.h" @@ -347,6 +348,20 @@ struct mlxsw_sp_port_type_speed_ops { u32 (*ptys_proto_cap_masked_get)(u32 eth_proto_cap); }; +static inline u8 mlxsw_sp_tunnel_ecn_decap(u8 outer_ecn, u8 inner_ecn, + bool *trap_en) +{ + bool set_ce = false; + + *trap_en = !!__INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce); + if (set_ce) + return INET_ECN_CE; + else if (outer_ecn == INET_ECN_ECT_1 && inner_ecn == INET_ECN_ECT_0) + return INET_ECN_ECT_1; + else + return inner_ecn; +} + static inline struct net_device * mlxsw_sp_bridge_vxlan_dev_find(struct net_device *br_dev) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c index 0bd64169bf81..078601d31cde 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ethtool.c @@ -1230,16 +1230,22 @@ mlxsw_sp1_from_ptys_link_mode(struct mlxsw_sp *mlxsw_sp, bool carrier_ok, u32 ptys_eth_proto, struct ethtool_link_ksettings *cmd) { + struct mlxsw_sp1_port_link_mode link; int i; - cmd->link_mode = -1; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->lanes = 0; if (!carrier_ok) return; for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) { - if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask) - cmd->link_mode = mlxsw_sp1_port_link_mode[i].mask_ethtool; + if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask) { + link = mlxsw_sp1_port_link_mode[i]; + ethtool_params_from_link_mode(cmd, + link.mask_ethtool); + } } } @@ -1672,7 +1678,9 @@ mlxsw_sp2_from_ptys_link_mode(struct mlxsw_sp *mlxsw_sp, bool carrier_ok, struct mlxsw_sp2_port_link_mode link; int i; - cmd->link_mode = -1; + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + cmd->lanes = 0; if (!carrier_ok) return; @@ -1680,7 +1688,8 @@ mlxsw_sp2_from_ptys_link_mode(struct mlxsw_sp *mlxsw_sp, bool carrier_ok, for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) { if (ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask) { link = mlxsw_sp2_port_link_mode[i]; - cmd->link_mode = link.mask_ethtool[1]; + ethtool_params_from_link_mode(cmd, + link.mask_ethtool[1]); } } } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index 6ccca39bae84..64a8f838eb53 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -335,12 +335,11 @@ static int mlxsw_sp_ipip_ecn_decap_init_one(struct mlxsw_sp *mlxsw_sp, u8 inner_ecn, u8 outer_ecn) { char tidem_pl[MLXSW_REG_TIDEM_LEN]; - bool trap_en, set_ce = false; u8 new_inner_ecn; + bool trap_en; - trap_en = __INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce); - new_inner_ecn = set_ce ? INET_ECN_CE : inner_ecn; - + new_inner_ecn = mlxsw_sp_tunnel_ecn_decap(outer_ecn, inner_ecn, + &trap_en); mlxsw_reg_tidem_pack(tidem_pl, outer_ecn, inner_ecn, new_inner_ecn, trap_en, trap_en ? MLXSW_TRAP_ID_DECAP_ECN0 : 0); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tidem), tidem_pl); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index e5ec595593f4..9eba8fa684ae 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -909,12 +909,11 @@ static int __mlxsw_sp_nve_ecn_decap_init(struct mlxsw_sp *mlxsw_sp, u8 inner_ecn, u8 outer_ecn) { char tndem_pl[MLXSW_REG_TNDEM_LEN]; - bool trap_en, set_ce = false; u8 new_inner_ecn; + bool trap_en; - trap_en = !!__INET_ECN_decapsulate(outer_ecn, inner_ecn, &set_ce); - new_inner_ecn = set_ce ? INET_ECN_CE : inner_ecn; - + new_inner_ecn = mlxsw_sp_tunnel_ecn_decap(outer_ecn, inner_ecn, + &trap_en); mlxsw_reg_tndem_pack(tndem_pl, outer_ecn, inner_ecn, new_inner_ecn, trap_en, trap_en ? MLXSW_TRAP_ID_DECAP_ECN0 : 0); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tndem), tndem_pl); diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 1c3e204d727c..7b6794aa8ea9 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -885,8 +885,8 @@ static int lan743x_mac_set_mtu(struct lan743x_adapter *adapter, int new_mtu) } mac_rx &= ~(MAC_RX_MAX_SIZE_MASK_); - mac_rx |= (((new_mtu + ETH_HLEN + 4) << MAC_RX_MAX_SIZE_SHIFT_) & - MAC_RX_MAX_SIZE_MASK_); + mac_rx |= (((new_mtu + ETH_HLEN + ETH_FCS_LEN) + << MAC_RX_MAX_SIZE_SHIFT_) & MAC_RX_MAX_SIZE_MASK_); lan743x_csr_write(adapter, MAC_RX, mac_rx); if (enabled) { @@ -1944,7 +1944,7 @@ static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index) struct sk_buff *skb; dma_addr_t dma_ptr; - buffer_length = netdev->mtu + ETH_HLEN + 4 + RX_HEAD_PADDING; + buffer_length = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + RX_HEAD_PADDING; descriptor = &rx->ring_cpu_ptr[index]; buffer_info = &rx->buffer_info[index]; @@ -2040,7 +2040,7 @@ lan743x_rx_trim_skb(struct sk_buff *skb, int frame_length) dev_kfree_skb_irq(skb); return NULL; } - frame_length = max_t(int, 0, frame_length - RX_HEAD_PADDING - 4); + frame_length = max_t(int, 0, frame_length - ETH_FCS_LEN); if (skb->len > frame_length) { skb->tail -= skb->len - frame_length; skb->len = frame_length; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 1634ca6d4a8f..c84c8bf2bc20 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -2897,7 +2897,7 @@ static netdev_tx_t myri10ge_sw_tso(struct sk_buff *skb, dev_kfree_skb_any(curr); if (segs != NULL) { curr = segs; - segs = segs->next; + segs = next; curr->next = NULL; dev_kfree_skb_any(segs); } diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c index 0e2db6ea79e9..2ec62c8d86e1 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c @@ -454,6 +454,7 @@ void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb) dev_consume_skb_any(skb); else dev_kfree_skb_any(skb); + return; } nfp_ccm_rx(&bpf->ccm, skb); diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index caf12eec9945..56833a41f3d2 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -190,6 +190,7 @@ struct nfp_fl_internal_ports { * @qos_rate_limiters: Current active qos rate limiters * @qos_stats_lock: Lock on qos stats updates * @pre_tun_rule_cnt: Number of pre-tunnel rules offloaded + * @merge_table: Hash table to store merged flows */ struct nfp_flower_priv { struct nfp_app *app; @@ -223,6 +224,7 @@ struct nfp_flower_priv { unsigned int qos_rate_limiters; spinlock_t qos_stats_lock; /* Protect the qos stats */ int pre_tun_rule_cnt; + struct rhashtable merge_table; }; /** @@ -350,6 +352,12 @@ struct nfp_fl_payload_link { }; extern const struct rhashtable_params nfp_flower_table_params; +extern const struct rhashtable_params merge_table_params; + +struct nfp_merge_info { + u64 parent_ctx; + struct rhash_head ht_node; +}; struct nfp_fl_stats_frame { __be32 stats_con_id; diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index 5defd31d481c..327bb56b3ef5 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -327,8 +327,14 @@ int nfp_compile_flow_metadata(struct nfp_app *app, goto err_free_ctx_entry; } + /* Do net allocate a mask-id for pre_tun_rules. These flows are used to + * configure the pre_tun table and are never actually send to the + * firmware as an add-flow message. This causes the mask-id allocation + * on the firmware to get out of sync if allocated here. + */ new_mask_id = 0; - if (!nfp_check_mask_add(app, nfp_flow->mask_data, + if (!nfp_flow->pre_tun_rule.dev && + !nfp_check_mask_add(app, nfp_flow->mask_data, nfp_flow->meta.mask_len, &nfp_flow->meta.flags, &new_mask_id)) { NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot allocate a new mask id"); @@ -359,7 +365,8 @@ int nfp_compile_flow_metadata(struct nfp_app *app, goto err_remove_mask; } - if (!nfp_check_mask_remove(app, nfp_flow->mask_data, + if (!nfp_flow->pre_tun_rule.dev && + !nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len, NULL, &new_mask_id)) { NL_SET_ERR_MSG_MOD(extack, "invalid entry: cannot release mask id"); @@ -374,8 +381,10 @@ int nfp_compile_flow_metadata(struct nfp_app *app, return 0; err_remove_mask: - nfp_check_mask_remove(app, nfp_flow->mask_data, nfp_flow->meta.mask_len, - NULL, &new_mask_id); + if (!nfp_flow->pre_tun_rule.dev) + nfp_check_mask_remove(app, nfp_flow->mask_data, + nfp_flow->meta.mask_len, + NULL, &new_mask_id); err_remove_rhash: WARN_ON_ONCE(rhashtable_remove_fast(&priv->stats_ctx_table, &ctx_entry->ht_node, @@ -406,9 +415,10 @@ int nfp_modify_flow_metadata(struct nfp_app *app, __nfp_modify_flow_metadata(priv, nfp_flow); - nfp_check_mask_remove(app, nfp_flow->mask_data, - nfp_flow->meta.mask_len, &nfp_flow->meta.flags, - &new_mask_id); + if (!nfp_flow->pre_tun_rule.dev) + nfp_check_mask_remove(app, nfp_flow->mask_data, + nfp_flow->meta.mask_len, &nfp_flow->meta.flags, + &new_mask_id); /* Update flow payload with mask ids. */ nfp_flow->unmasked_data[NFP_FL_MASK_ID_LOCATION] = new_mask_id; @@ -480,6 +490,12 @@ const struct rhashtable_params nfp_flower_table_params = { .automatic_shrinking = true, }; +const struct rhashtable_params merge_table_params = { + .key_offset = offsetof(struct nfp_merge_info, parent_ctx), + .head_offset = offsetof(struct nfp_merge_info, ht_node), + .key_len = sizeof(u64), +}; + int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, unsigned int host_num_mems) { @@ -496,6 +512,10 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, if (err) goto err_free_flow_table; + err = rhashtable_init(&priv->merge_table, &merge_table_params); + if (err) + goto err_free_stats_ctx_table; + get_random_bytes(&priv->mask_id_seed, sizeof(priv->mask_id_seed)); /* Init ring buffer and unallocated mask_ids. */ @@ -503,7 +523,7 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, kmalloc_array(NFP_FLOWER_MASK_ENTRY_RS, NFP_FLOWER_MASK_ELEMENT_RS, GFP_KERNEL); if (!priv->mask_ids.mask_id_free_list.buf) - goto err_free_stats_ctx_table; + goto err_free_merge_table; priv->mask_ids.init_unallocated = NFP_FLOWER_MASK_ENTRY_RS - 1; @@ -540,6 +560,8 @@ err_free_last_used: kfree(priv->mask_ids.last_used); err_free_mask_id: kfree(priv->mask_ids.mask_id_free_list.buf); +err_free_merge_table: + rhashtable_destroy(&priv->merge_table); err_free_stats_ctx_table: rhashtable_destroy(&priv->stats_ctx_table); err_free_flow_table: @@ -558,6 +580,8 @@ void nfp_flower_metadata_cleanup(struct nfp_app *app) nfp_check_rhashtable_empty, NULL); rhashtable_free_and_destroy(&priv->stats_ctx_table, nfp_check_rhashtable_empty, NULL); + rhashtable_free_and_destroy(&priv->merge_table, + nfp_check_rhashtable_empty, NULL); kvfree(priv->stats); kfree(priv->mask_ids.mask_id_free_list.buf); kfree(priv->mask_ids.last_used); diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 1c59aff2163c..e95969c462e4 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -1009,6 +1009,8 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app, struct netlink_ext_ack *extack = NULL; struct nfp_fl_payload *merge_flow; struct nfp_fl_key_ls merge_key_ls; + struct nfp_merge_info *merge_info; + u64 parent_ctx = 0; int err; ASSERT_RTNL(); @@ -1019,6 +1021,15 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app, nfp_flower_is_merge_flow(sub_flow2)) return -EINVAL; + /* check if the two flows are already merged */ + parent_ctx = (u64)(be32_to_cpu(sub_flow1->meta.host_ctx_id)) << 32; + parent_ctx |= (u64)(be32_to_cpu(sub_flow2->meta.host_ctx_id)); + if (rhashtable_lookup_fast(&priv->merge_table, + &parent_ctx, merge_table_params)) { + nfp_flower_cmsg_warn(app, "The two flows are already merged.\n"); + return 0; + } + err = nfp_flower_can_merge(sub_flow1, sub_flow2); if (err) return err; @@ -1060,16 +1071,33 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app, if (err) goto err_release_metadata; + merge_info = kmalloc(sizeof(*merge_info), GFP_KERNEL); + if (!merge_info) { + err = -ENOMEM; + goto err_remove_rhash; + } + merge_info->parent_ctx = parent_ctx; + err = rhashtable_insert_fast(&priv->merge_table, &merge_info->ht_node, + merge_table_params); + if (err) + goto err_destroy_merge_info; + err = nfp_flower_xmit_flow(app, merge_flow, NFP_FLOWER_CMSG_TYPE_FLOW_MOD); if (err) - goto err_remove_rhash; + goto err_remove_merge_info; merge_flow->in_hw = true; sub_flow1->in_hw = false; return 0; +err_remove_merge_info: + WARN_ON_ONCE(rhashtable_remove_fast(&priv->merge_table, + &merge_info->ht_node, + merge_table_params)); +err_destroy_merge_info: + kfree(merge_info); err_remove_rhash: WARN_ON_ONCE(rhashtable_remove_fast(&priv->flow_table, &merge_flow->fl_node, @@ -1142,6 +1170,12 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, return -EOPNOTSUPP; } + if (!(key_layer & NFP_FLOWER_LAYER_IPV4) && + !(key_layer & NFP_FLOWER_LAYER_IPV6)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: match on ipv4/ipv6 eth_type must be present"); + return -EOPNOTSUPP; + } + /* Skip fields known to exist. */ mask += sizeof(struct nfp_flower_meta_tci); ext += sizeof(struct nfp_flower_meta_tci); @@ -1152,6 +1186,13 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, mask += sizeof(struct nfp_flower_in_port); ext += sizeof(struct nfp_flower_in_port); + /* Ensure destination MAC address matches pre_tun_dev. */ + mac = (struct nfp_flower_mac_mpls *)ext; + if (memcmp(&mac->mac_dst[0], flow->pre_tun_rule.dev->dev_addr, 6)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: dest MAC must match output dev MAC"); + return -EOPNOTSUPP; + } + /* Ensure destination MAC address is fully matched. */ mac = (struct nfp_flower_mac_mpls *)mask; if (!is_broadcast_ether_addr(&mac->mac_dst[0])) { @@ -1159,6 +1200,11 @@ nfp_flower_validate_pre_tun_rule(struct nfp_app *app, return -EOPNOTSUPP; } + if (mac->mpls_lse) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: MPLS not supported"); + return -EOPNOTSUPP; + } + mask += sizeof(struct nfp_flower_mac_mpls); ext += sizeof(struct nfp_flower_mac_mpls); if (key_layer & NFP_FLOWER_LAYER_IPV4 || @@ -1341,7 +1387,9 @@ nfp_flower_remove_merge_flow(struct nfp_app *app, { struct nfp_flower_priv *priv = app->priv; struct nfp_fl_payload_link *link, *temp; + struct nfp_merge_info *merge_info; struct nfp_fl_payload *origin; + u64 parent_ctx = 0; bool mod = false; int err; @@ -1378,8 +1426,22 @@ nfp_flower_remove_merge_flow(struct nfp_app *app, err_free_links: /* Clean any links connected with the merged flow. */ list_for_each_entry_safe(link, temp, &merge_flow->linked_flows, - merge_flow.list) + merge_flow.list) { + u32 ctx_id = be32_to_cpu(link->sub_flow.flow->meta.host_ctx_id); + + parent_ctx = (parent_ctx << 32) | (u64)(ctx_id); nfp_flower_unlink_flow(link); + } + + merge_info = rhashtable_lookup_fast(&priv->merge_table, + &parent_ctx, + merge_table_params); + if (merge_info) { + WARN_ON_ONCE(rhashtable_remove_fast(&priv->merge_table, + &merge_info->ht_node, + merge_table_params)); + kfree(merge_info); + } kfree(merge_flow->action_data); kfree(merge_flow->mask_data); diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 7248d248f604..d19c02e99114 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -16,8 +16,9 @@ #define NFP_FL_MAX_ROUTES 32 #define NFP_TUN_PRE_TUN_RULE_LIMIT 32 -#define NFP_TUN_PRE_TUN_RULE_DEL 0x1 -#define NFP_TUN_PRE_TUN_IDX_BIT 0x8 +#define NFP_TUN_PRE_TUN_RULE_DEL BIT(0) +#define NFP_TUN_PRE_TUN_IDX_BIT BIT(3) +#define NFP_TUN_PRE_TUN_IPV6_BIT BIT(7) /** * struct nfp_tun_pre_run_rule - rule matched before decap @@ -1268,6 +1269,7 @@ int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, { struct nfp_flower_priv *app_priv = app->priv; struct nfp_tun_offloaded_mac *mac_entry; + struct nfp_flower_meta_tci *key_meta; struct nfp_tun_pre_tun_rule payload; struct net_device *internal_dev; int err; @@ -1290,6 +1292,15 @@ int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, if (!mac_entry) return -ENOENT; + /* Set/clear IPV6 bit. cpu_to_be16() swap will lead to MSB being + * set/clear for port_idx. + */ + key_meta = (struct nfp_flower_meta_tci *)flow->unmasked_data; + if (key_meta->nfp_flow_key_layer & NFP_FLOWER_LAYER_IPV6) + mac_entry->index |= NFP_TUN_PRE_TUN_IPV6_BIT; + else + mac_entry->index &= ~NFP_TUN_PRE_TUN_IPV6_BIT; + payload.port_idx = cpu_to_be16(mac_entry->index); /* Copy mac id and vlan to flow - dev may not exist at delete time. */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c index 162a1ff1e9d2..4087311f7082 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -1079,15 +1079,17 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) { int sg_elems = q->lif->qtype_info[IONIC_QTYPE_TXQ].max_sg_elems; struct ionic_tx_stats *stats = q_to_tx_stats(q); + int ndescs; int err; - /* If TSO, need roundup(skb->len/mss) descs */ + /* Each desc is mss long max, so a descriptor for each gso_seg */ if (skb_is_gso(skb)) - return (skb->len / skb_shinfo(skb)->gso_size) + 1; + ndescs = skb_shinfo(skb)->gso_segs; + else + ndescs = 1; - /* If non-TSO, just need 1 desc and nr_frags sg elems */ if (skb_shinfo(skb)->nr_frags <= sg_elems) - return 1; + return ndescs; /* Too many frags, so linearize */ err = skb_linearize(skb); @@ -1096,8 +1098,7 @@ static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) stats->linearize++; - /* Need 1 desc and zero sg elems */ - return 1; + return ndescs; } static int ionic_maybe_stop_tx(struct ionic_queue *q, int ndescs) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c index 7760a3394e93..7ecb3dfe30bd 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_minidump.c @@ -1425,6 +1425,7 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter) if (fw_dump->tmpl_hdr == NULL || current_version > prev_version) { vfree(fw_dump->tmpl_hdr); + fw_dump->tmpl_hdr = NULL; if (qlcnic_83xx_md_check_extended_dump_capability(adapter)) extended = !qlcnic_83xx_extend_md_capab(adapter); @@ -1443,6 +1444,8 @@ void qlcnic_83xx_get_minidump_template(struct qlcnic_adapter *adapter) struct qlcnic_83xx_dump_template_hdr *hdr; hdr = fw_dump->tmpl_hdr; + if (!hdr) + return; hdr->drv_cap_mask = 0x1f; fw_dump->cap_mask = 0x1f; dev_info(&pdev->dev, diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 7aad0ba53372..1df2c002c9f6 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2350,6 +2350,13 @@ static void rtl_jumbo_config(struct rtl8169_private *tp) if (pci_is_pcie(tp->pci_dev) && tp->supports_gmii) pcie_set_readrq(tp->pci_dev, readrq); + + /* Chip doesn't support pause in jumbo mode */ + linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT, + tp->phydev->advertising, !jumbo); + linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + tp->phydev->advertising, !jumbo); + phy_start_aneg(tp->phydev); } DECLARE_RTL_COND(rtl_chipcmd_cond) @@ -4630,8 +4637,6 @@ static int r8169_phy_connect(struct rtl8169_private *tp) if (!tp->supports_gmii) phy_set_max_speed(phydev, SPEED_100); - phy_support_asym_pause(phydev); - phy_attached_info(phydev); return 0; @@ -4646,6 +4651,9 @@ static void rtl8169_down(struct rtl8169_private *tp) rtl8169_update_counters(tp); + pci_clear_master(tp->pci_dev); + rtl_pci_commit(tp); + rtl8169_cleanup(tp, true); rtl_prepare_power_down(tp); @@ -4653,6 +4661,7 @@ static void rtl8169_down(struct rtl8169_private *tp) static void rtl8169_up(struct rtl8169_private *tp) { + pci_set_master(tp->pci_dev); phy_resume(tp->phydev); rtl8169_init_phy(tp); napi_enable(&tp->napi); @@ -5307,8 +5316,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) rtl_hw_reset(tp); - pci_set_master(pdev); - rc = rtl_alloc_irq(tp); if (rc < 0) { dev_err(&pdev->dev, "Can't allocate interrupt\n"); diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 3c53051bdacf..200785e703c8 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1715,14 +1715,17 @@ static int netsec_netdev_init(struct net_device *ndev) goto err1; /* set phy power down */ - data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR) | - BMCR_PDOWN; - netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data); + data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR); + netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, + data | BMCR_PDOWN); ret = netsec_reset_hardware(priv, true); if (ret) goto err2; + /* Restore phy power state */ + netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data); + spin_lock_init(&priv->desc_ring[NETSEC_RING_TX].lock); spin_lock_init(&priv->desc_ring[NETSEC_RING_RX].lock); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 6b75cf2603ff..e62efd166ec8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1214,6 +1214,8 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) plat_dat->init = sun8i_dwmac_init; plat_dat->exit = sun8i_dwmac_exit; plat_dat->setup = sun8i_dwmac_setup; + plat_dat->tx_fifo_size = 4096; + plat_dat->rx_fifo_size = 16384; ret = sun8i_dwmac_set_syscon(&pdev->dev, plat_dat); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 208cae344ffa..4749bd0af160 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1380,88 +1380,6 @@ static void stmmac_free_tx_buffer(struct stmmac_priv *priv, u32 queue, int i) } /** - * stmmac_reinit_rx_buffers - reinit the RX descriptor buffer. - * @priv: driver private structure - * Description: this function is called to re-allocate a receive buffer, perform - * the DMA mapping and init the descriptor. - */ -static void stmmac_reinit_rx_buffers(struct stmmac_priv *priv) -{ - u32 rx_count = priv->plat->rx_queues_to_use; - u32 queue; - int i; - - for (queue = 0; queue < rx_count; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; - - for (i = 0; i < priv->dma_rx_size; i++) { - struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i]; - - if (buf->page) { - page_pool_recycle_direct(rx_q->page_pool, buf->page); - buf->page = NULL; - } - - if (priv->sph && buf->sec_page) { - page_pool_recycle_direct(rx_q->page_pool, buf->sec_page); - buf->sec_page = NULL; - } - } - } - - for (queue = 0; queue < rx_count; queue++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; - - for (i = 0; i < priv->dma_rx_size; i++) { - struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i]; - struct dma_desc *p; - - if (priv->extend_desc) - p = &((rx_q->dma_erx + i)->basic); - else - p = rx_q->dma_rx + i; - - if (!buf->page) { - buf->page = page_pool_dev_alloc_pages(rx_q->page_pool); - if (!buf->page) - goto err_reinit_rx_buffers; - - buf->addr = page_pool_get_dma_addr(buf->page); - } - - if (priv->sph && !buf->sec_page) { - buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool); - if (!buf->sec_page) - goto err_reinit_rx_buffers; - - buf->sec_addr = page_pool_get_dma_addr(buf->sec_page); - } - - stmmac_set_desc_addr(priv, p, buf->addr); - if (priv->sph) - stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, true); - else - stmmac_set_desc_sec_addr(priv, p, buf->sec_addr, false); - if (priv->dma_buf_sz == BUF_SIZE_16KiB) - stmmac_init_desc3(priv, p); - } - } - - return; - -err_reinit_rx_buffers: - do { - while (--i >= 0) - stmmac_free_rx_buffer(priv, queue, i); - - if (queue == 0) - break; - - i = priv->dma_rx_size; - } while (queue-- > 0); -} - -/** * init_dma_rx_desc_rings - init the RX descriptor rings * @dev: net device structure * @flags: gfp flag. @@ -5428,7 +5346,7 @@ int stmmac_resume(struct device *dev) mutex_lock(&priv->lock); stmmac_reset_queues_param(priv); - stmmac_reinit_rx_buffers(priv); + stmmac_free_tx_skbufs(priv); stmmac_clear_descriptors(priv); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 1e966a39967e..aca7f82f6791 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -504,6 +504,18 @@ static inline u32 axinet_ior_read_mcr(struct axienet_local *lp) return axienet_ior(lp, XAE_MDIO_MCR_OFFSET); } +static inline void axienet_lock_mii(struct axienet_local *lp) +{ + if (lp->mii_bus) + mutex_lock(&lp->mii_bus->mdio_lock); +} + +static inline void axienet_unlock_mii(struct axienet_local *lp) +{ + if (lp->mii_bus) + mutex_unlock(&lp->mii_bus->mdio_lock); +} + /** * axienet_iow - Memory mapped Axi Ethernet register write * @lp: Pointer to axienet local structure diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 3a8775e0ca55..f8f8654ea728 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1053,9 +1053,9 @@ static int axienet_open(struct net_device *ndev) * including the MDIO. MDIO must be disabled before resetting. * Hold MDIO bus lock to avoid MDIO accesses during the reset. */ - mutex_lock(&lp->mii_bus->mdio_lock); + axienet_lock_mii(lp); ret = axienet_device_reset(ndev); - mutex_unlock(&lp->mii_bus->mdio_lock); + axienet_unlock_mii(lp); ret = phylink_of_phy_connect(lp->phylink, lp->dev->of_node, 0); if (ret) { @@ -1148,9 +1148,9 @@ static int axienet_stop(struct net_device *ndev) } /* Do a reset to ensure DMA is really stopped */ - mutex_lock(&lp->mii_bus->mdio_lock); + axienet_lock_mii(lp); __axienet_device_reset(lp); - mutex_unlock(&lp->mii_bus->mdio_lock); + axienet_unlock_mii(lp); cancel_work_sync(&lp->dma_err_task); @@ -1709,9 +1709,9 @@ static void axienet_dma_err_handler(struct work_struct *work) * including the MDIO. MDIO must be disabled before resetting. * Hold MDIO bus lock to avoid MDIO accesses during the reset. */ - mutex_lock(&lp->mii_bus->mdio_lock); + axienet_lock_mii(lp); __axienet_device_reset(lp); - mutex_unlock(&lp->mii_bus->mdio_lock); + axienet_unlock_mii(lp); for (i = 0; i < lp->tx_bd_num; i++) { cur_p = &lp->tx_bd_v[i]; @@ -1880,7 +1880,7 @@ static int axienet_probe(struct platform_device *pdev) if (IS_ERR(lp->regs)) { dev_err(&pdev->dev, "could not map Axi Ethernet regs.\n"); ret = PTR_ERR(lp->regs); - goto free_netdev; + goto cleanup_clk; } lp->regs_start = ethres->start; @@ -1958,18 +1958,18 @@ static int axienet_probe(struct platform_device *pdev) break; default: ret = -EINVAL; - goto free_netdev; + goto cleanup_clk; } } else { ret = of_get_phy_mode(pdev->dev.of_node, &lp->phy_mode); if (ret) - goto free_netdev; + goto cleanup_clk; } if (lp->switch_x_sgmii && lp->phy_mode != PHY_INTERFACE_MODE_SGMII && lp->phy_mode != PHY_INTERFACE_MODE_1000BASEX) { dev_err(&pdev->dev, "xlnx,switch-x-sgmii only supported with SGMII or 1000BaseX\n"); ret = -EINVAL; - goto free_netdev; + goto cleanup_clk; } /* Find the DMA node, map the DMA registers, and decode the DMA IRQs */ @@ -1982,7 +1982,7 @@ static int axienet_probe(struct platform_device *pdev) dev_err(&pdev->dev, "unable to get DMA resource\n"); of_node_put(np); - goto free_netdev; + goto cleanup_clk; } lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares); @@ -2002,12 +2002,12 @@ static int axienet_probe(struct platform_device *pdev) if (IS_ERR(lp->dma_regs)) { dev_err(&pdev->dev, "could not map DMA regs\n"); ret = PTR_ERR(lp->dma_regs); - goto free_netdev; + goto cleanup_clk; } if ((lp->rx_irq <= 0) || (lp->tx_irq <= 0)) { dev_err(&pdev->dev, "could not determine irqs\n"); ret = -ENOMEM; - goto free_netdev; + goto cleanup_clk; } /* Autodetect the need for 64-bit DMA pointers. @@ -2037,7 +2037,7 @@ static int axienet_probe(struct platform_device *pdev) ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(addr_width)); if (ret) { dev_err(&pdev->dev, "No suitable DMA available\n"); - goto free_netdev; + goto cleanup_clk; } /* Check for Ethernet core IRQ (optional) */ @@ -2068,12 +2068,12 @@ static int axienet_probe(struct platform_device *pdev) if (!lp->phy_node) { dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n"); ret = -EINVAL; - goto free_netdev; + goto cleanup_mdio; } lp->pcs_phy = of_mdio_find_device(lp->phy_node); if (!lp->pcs_phy) { ret = -EPROBE_DEFER; - goto free_netdev; + goto cleanup_mdio; } lp->phylink_config.pcs_poll = true; } @@ -2087,17 +2087,30 @@ static int axienet_probe(struct platform_device *pdev) if (IS_ERR(lp->phylink)) { ret = PTR_ERR(lp->phylink); dev_err(&pdev->dev, "phylink_create error (%i)\n", ret); - goto free_netdev; + goto cleanup_mdio; } ret = register_netdev(lp->ndev); if (ret) { dev_err(lp->dev, "register_netdev() error (%i)\n", ret); - goto free_netdev; + goto cleanup_phylink; } return 0; +cleanup_phylink: + phylink_destroy(lp->phylink); + +cleanup_mdio: + if (lp->pcs_phy) + put_device(&lp->pcs_phy->dev); + if (lp->mii_bus) + axienet_mdio_teardown(lp); + of_node_put(lp->phy_node); + +cleanup_clk: + clk_disable_unprepare(lp->clk); + free_netdev: free_netdev(ndev); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 4ac0373326ef..42f31c681846 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -891,6 +891,9 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; + if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) + return -EINVAL; + 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); @@ -908,8 +911,16 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, info = skb_tunnel_info(skb); if (info) { - info->key.u.ipv4.dst = fl4.saddr; - info->key.u.ipv4.src = fl4.daddr; + struct ip_tunnel_info *unclone; + + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) { + dst_release(&rt->dst); + return -ENOMEM; + } + + unclone->key.u.ipv4.dst = fl4.saddr; + unclone->key.u.ipv4.src = fl4.daddr; } if (!pskb_may_pull(skb, ETH_HLEN)) { @@ -977,6 +988,9 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, __be16 sport; int err; + if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) + return -EINVAL; + 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); @@ -993,8 +1007,16 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_info *info = skb_tunnel_info(skb); if (info) { - info->key.u.ipv6.dst = fl6.saddr; - info->key.u.ipv6.src = fl6.daddr; + struct ip_tunnel_info *unclone; + + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) { + dst_release(dst); + return -ENOMEM; + } + + unclone->key.u.ipv6.dst = fl6.saddr; + unclone->key.u.ipv6.src = fl6.daddr; } if (!pskb_may_pull(skb, ETH_HLEN)) { diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 0dd0ba915ab9..23ee0b14cbfa 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -365,6 +365,7 @@ static int atusb_alloc_urbs(struct atusb *atusb, int n) return -ENOMEM; } usb_anchor_urb(urb, &atusb->idle_urbs); + usb_free_urb(urb); n--; } return 0; diff --git a/drivers/net/ipa/ipa_cmd.c b/drivers/net/ipa/ipa_cmd.c index 35e35852c25c..d73b03a80ef8 100644 --- a/drivers/net/ipa/ipa_cmd.c +++ b/drivers/net/ipa/ipa_cmd.c @@ -175,21 +175,23 @@ bool ipa_cmd_table_valid(struct ipa *ipa, const struct ipa_mem *mem, : field_max(IP_FLTRT_FLAGS_NHASH_ADDR_FMASK); if (mem->offset > offset_max || ipa->mem_offset > offset_max - mem->offset) { - dev_err(dev, "IPv%c %s%s table region offset too large " - "(0x%04x + 0x%04x > 0x%04x)\n", - ipv6 ? '6' : '4', hashed ? "hashed " : "", - route ? "route" : "filter", - ipa->mem_offset, mem->offset, offset_max); + dev_err(dev, "IPv%c %s%s table region offset too large\n", + ipv6 ? '6' : '4', hashed ? "hashed " : "", + route ? "route" : "filter"); + dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", + ipa->mem_offset, mem->offset, offset_max); + return false; } if (mem->offset > ipa->mem_size || mem->size > ipa->mem_size - mem->offset) { - dev_err(dev, "IPv%c %s%s table region out of range " - "(0x%04x + 0x%04x > 0x%04x)\n", - ipv6 ? '6' : '4', hashed ? "hashed " : "", - route ? "route" : "filter", - mem->offset, mem->size, ipa->mem_size); + dev_err(dev, "IPv%c %s%s table region out of range\n", + ipv6 ? '6' : '4', hashed ? "hashed " : "", + route ? "route" : "filter"); + dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", + mem->offset, mem->size, ipa->mem_size); + return false; } @@ -205,22 +207,36 @@ static bool ipa_cmd_header_valid(struct ipa *ipa) u32 size_max; u32 size; + /* In ipa_cmd_hdr_init_local_add() we record the offset and size + * of the header table memory area. Make sure the offset and size + * fit in the fields that need to hold them, and that the entire + * range is within the overall IPA memory range. + */ offset_max = field_max(HDR_INIT_LOCAL_FLAGS_HDR_ADDR_FMASK); if (mem->offset > offset_max || ipa->mem_offset > offset_max - mem->offset) { - dev_err(dev, "header table region offset too large " - "(0x%04x + 0x%04x > 0x%04x)\n", - ipa->mem_offset + mem->offset, offset_max); + dev_err(dev, "header table region offset too large\n"); + dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", + ipa->mem_offset, mem->offset, offset_max); + return false; } size_max = field_max(HDR_INIT_LOCAL_FLAGS_TABLE_SIZE_FMASK); size = ipa->mem[IPA_MEM_MODEM_HEADER].size; size += ipa->mem[IPA_MEM_AP_HEADER].size; - if (mem->offset > ipa->mem_size || size > ipa->mem_size - mem->offset) { - dev_err(dev, "header table region out of range " - "(0x%04x + 0x%04x > 0x%04x)\n", - mem->offset, size, ipa->mem_size); + + if (size > size_max) { + dev_err(dev, "header table region size too large\n"); + dev_err(dev, " (0x%04x > 0x%08x)\n", size, size_max); + + return false; + } + if (size > ipa->mem_size || mem->offset > ipa->mem_size - size) { + dev_err(dev, "header table region out of range\n"); + dev_err(dev, " (0x%04x + 0x%04x > 0x%04x)\n", + mem->offset, size, ipa->mem_size); + return false; } diff --git a/drivers/net/ipa/ipa_qmi.c b/drivers/net/ipa/ipa_qmi.c index 2fc64483f275..e594bf3b600f 100644 --- a/drivers/net/ipa/ipa_qmi.c +++ b/drivers/net/ipa/ipa_qmi.c @@ -249,6 +249,7 @@ static const struct qmi_msg_handler ipa_server_msg_handlers[] = { .decoded_size = IPA_QMI_DRIVER_INIT_COMPLETE_REQ_SZ, .fn = ipa_server_driver_init_complete, }, + { }, }; /* Handle an INIT_DRIVER response message from the modem. */ @@ -269,6 +270,7 @@ static const struct qmi_msg_handler ipa_client_msg_handlers[] = { .decoded_size = IPA_QMI_INIT_DRIVER_RSP_SZ, .fn = ipa_client_init_driver, }, + { }, }; /* Return a pointer to an init modem driver request structure, which contains diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index 53282a6d5928..287cccf8f7f4 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -369,7 +369,7 @@ EXPORT_SYMBOL_GPL(bcm_phy_enable_apd); int bcm_phy_set_eee(struct phy_device *phydev, bool enable) { - int val; + int val, mask = 0; /* Enable EEE at PHY level */ val = phy_read_mmd(phydev, MDIO_MMD_AN, BRCM_CL45VEN_EEE_CONTROL); @@ -388,10 +388,17 @@ int bcm_phy_set_eee(struct phy_device *phydev, bool enable) if (val < 0) return val; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + phydev->supported)) + mask |= MDIO_EEE_1000T; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + phydev->supported)) + mask |= MDIO_EEE_100TX; + if (enable) - val |= (MDIO_EEE_100TX | MDIO_EEE_1000T); + val |= mask; else - val &= ~(MDIO_EEE_100TX | MDIO_EEE_1000T); + val &= ~mask; phy_write_mmd(phydev, MDIO_MMD_AN, BCM_CL45VEN_EEE_ADV, (u32)val); diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index fa0be591ae79..82fe5f43f0e9 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -342,6 +342,10 @@ static int bcm54xx_config_init(struct phy_device *phydev) bcm54xx_adjust_rxrefclk(phydev); switch (BRCM_PHY_MODEL(phydev)) { + case PHY_ID_BCM50610: + case PHY_ID_BCM50610M: + err = bcm54xx_config_clock_delay(phydev); + break; case PHY_ID_BCM54210E: err = bcm54210e_config_init(phydev); break; @@ -399,6 +403,11 @@ static int bcm54xx_resume(struct phy_device *phydev) if (ret < 0) return ret; + /* Upon exiting power down, the PHY remains in an internal reset state + * for 40us + */ + fsleep(40); + return bcm54xx_config_init(phydev); } diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index e26a5d663f8a..8018ddf7f316 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -3021,9 +3021,34 @@ static struct phy_driver marvell_drivers[] = { .get_stats = marvell_get_stats, }, { - .phy_id = MARVELL_PHY_ID_88E6390, + .phy_id = MARVELL_PHY_ID_88E6341_FAMILY, .phy_id_mask = MARVELL_PHY_ID_MASK, - .name = "Marvell 88E6390", + .name = "Marvell 88E6341 Family", + /* PHY_GBIT_FEATURES */ + .flags = PHY_POLL_CABLE_TEST, + .probe = m88e1510_probe, + .config_init = marvell_config_init, + .config_aneg = m88e6390_config_aneg, + .read_status = marvell_read_status, + .config_intr = marvell_config_intr, + .handle_interrupt = marvell_handle_interrupt, + .resume = genphy_resume, + .suspend = genphy_suspend, + .read_page = marvell_read_page, + .write_page = marvell_write_page, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, + .get_tunable = m88e1540_get_tunable, + .set_tunable = m88e1540_set_tunable, + .cable_test_start = marvell_vct7_cable_test_start, + .cable_test_tdr_start = marvell_vct5_cable_test_tdr_start, + .cable_test_get_status = marvell_vct7_cable_test_get_status, + }, + { + .phy_id = MARVELL_PHY_ID_88E6390_FAMILY, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .name = "Marvell 88E6390 Family", /* PHY_GBIT_FEATURES */ .flags = PHY_POLL_CABLE_TEST, .probe = m88e6390_probe, @@ -3107,7 +3132,8 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = { { MARVELL_PHY_ID_88E1540, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1545, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E3016, MARVELL_PHY_ID_MASK }, - { MARVELL_PHY_ID_88E6390, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E6341_FAMILY, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E6390_FAMILY, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1340S, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1548P, MARVELL_PHY_ID_MASK }, { } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 053c92e02cd8..dc2800beacc3 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -476,7 +476,7 @@ static void phylink_major_config(struct phylink *pl, bool restart, err = pl->mac_ops->mac_finish(pl->config, pl->cur_link_an_mode, state->interface); if (err < 0) - phylink_err(pl, "mac_prepare failed: %pe\n", + phylink_err(pl, "mac_finish failed: %pe\n", ERR_PTR(err)); } } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index fc86da7f1628..4cf38be26dc9 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -69,6 +69,14 @@ #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <linux/mutex.h> +#include <linux/ieee802154.h> +#include <linux/if_ltalk.h> +#include <uapi/linux/if_fddi.h> +#include <uapi/linux/if_hippi.h> +#include <uapi/linux/if_fc.h> +#include <net/ax25.h> +#include <net/rose.h> +#include <net/6lowpan.h> #include <linux/uaccess.h> #include <linux/proc_fs.h> @@ -2919,6 +2927,45 @@ static int tun_set_ebpf(struct tun_struct *tun, struct tun_prog __rcu **prog_p, return __tun_set_ebpf(tun, prog_p, prog); } +/* Return correct value for tun->dev->addr_len based on tun->dev->type. */ +static unsigned char tun_get_addr_len(unsigned short type) +{ + switch (type) { + case ARPHRD_IP6GRE: + case ARPHRD_TUNNEL6: + return sizeof(struct in6_addr); + case ARPHRD_IPGRE: + case ARPHRD_TUNNEL: + case ARPHRD_SIT: + return 4; + case ARPHRD_ETHER: + return ETH_ALEN; + case ARPHRD_IEEE802154: + case ARPHRD_IEEE802154_MONITOR: + return IEEE802154_EXTENDED_ADDR_LEN; + case ARPHRD_PHONET_PIPE: + case ARPHRD_PPP: + case ARPHRD_NONE: + return 0; + case ARPHRD_6LOWPAN: + return EUI64_ADDR_LEN; + case ARPHRD_FDDI: + return FDDI_K_ALEN; + case ARPHRD_HIPPI: + return HIPPI_ALEN; + case ARPHRD_IEEE802: + return FC_ALEN; + case ARPHRD_ROSE: + return ROSE_ADDR_LEN; + case ARPHRD_NETROM: + return AX25_ADDR_LEN; + case ARPHRD_LOCALTLK: + return LTALK_ALEN; + default: + return 0; + } +} + static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { @@ -3082,6 +3129,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, break; } tun->dev->type = (int) arg; + tun->dev->addr_len = tun_get_addr_len(tun->dev->type); netif_info(tun, drv, tun->dev, "linktype set to %d\n", tun->dev->type); call_netdevice_notifiers(NETDEV_POST_TYPE_CHANGE, diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 02e6bbb17b15..8d1f69dad603 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -387,6 +387,8 @@ static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *i err = register_netdev(dev); if (err) { + /* Set disconnected flag so that disconnect() returns early. */ + pnd->disconnected = 1; usb_driver_release_interface(&usbpn_driver, data_intf); goto out; } diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c index 31d51346786a..9bc58e64b5b7 100644 --- a/drivers/net/usb/hso.c +++ b/drivers/net/usb/hso.c @@ -611,7 +611,7 @@ static struct hso_serial *get_serial_by_index(unsigned index) return serial; } -static int get_free_serial_index(void) +static int obtain_minor(struct hso_serial *serial) { int index; unsigned long flags; @@ -619,8 +619,10 @@ static int get_free_serial_index(void) spin_lock_irqsave(&serial_table_lock, flags); for (index = 0; index < HSO_SERIAL_TTY_MINORS; index++) { if (serial_table[index] == NULL) { + serial_table[index] = serial->parent; + serial->minor = index; spin_unlock_irqrestore(&serial_table_lock, flags); - return index; + return 0; } } spin_unlock_irqrestore(&serial_table_lock, flags); @@ -629,15 +631,12 @@ static int get_free_serial_index(void) return -1; } -static void set_serial_by_index(unsigned index, struct hso_serial *serial) +static void release_minor(struct hso_serial *serial) { unsigned long flags; spin_lock_irqsave(&serial_table_lock, flags); - if (serial) - serial_table[index] = serial->parent; - else - serial_table[index] = NULL; + serial_table[serial->minor] = NULL; spin_unlock_irqrestore(&serial_table_lock, flags); } @@ -2230,6 +2229,7 @@ static int hso_stop_serial_device(struct hso_device *hso_dev) static void hso_serial_tty_unregister(struct hso_serial *serial) { tty_unregister_device(tty_drv, serial->minor); + release_minor(serial); } static void hso_serial_common_free(struct hso_serial *serial) @@ -2253,24 +2253,22 @@ static void hso_serial_common_free(struct hso_serial *serial) static int hso_serial_common_create(struct hso_serial *serial, int num_urbs, int rx_size, int tx_size) { - int minor; int i; tty_port_init(&serial->port); - minor = get_free_serial_index(); - if (minor < 0) + if (obtain_minor(serial)) goto exit2; /* register our minor number */ serial->parent->dev = tty_port_register_device_attr(&serial->port, - tty_drv, minor, &serial->parent->interface->dev, + tty_drv, serial->minor, &serial->parent->interface->dev, serial->parent, hso_serial_dev_groups); - if (IS_ERR(serial->parent->dev)) + if (IS_ERR(serial->parent->dev)) { + release_minor(serial); goto exit2; + } - /* fill in specific data for later use */ - serial->minor = minor; serial->magic = HSO_SERIAL_MAGIC; spin_lock_init(&serial->serial_lock); serial->num_rx_urbs = num_urbs; @@ -2667,9 +2665,6 @@ static struct hso_device *hso_create_bulk_serial_device( serial->write_data = hso_std_serial_write_data; - /* and record this serial */ - set_serial_by_index(serial->minor, serial); - /* setup the proc dirs and files if needed */ hso_log_port(hso_dev); @@ -2726,9 +2721,6 @@ struct hso_device *hso_create_mux_serial_device(struct usb_interface *interface, serial->shared_int->ref_count++; mutex_unlock(&serial->shared_int->shared_int_lock); - /* and record this serial */ - set_serial_by_index(serial->minor, serial); - /* setup the proc dirs and files if needed */ hso_log_port(hso_dev); @@ -3113,7 +3105,6 @@ static void hso_free_interface(struct usb_interface *interface) cancel_work_sync(&serial_table[i]->async_get_intf); hso_serial_tty_unregister(serial); kref_put(&serial_table[i]->ref, hso_serial_ref_free); - set_serial_by_index(i, NULL); } } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 90f1c0200042..20fb5638ac65 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -6553,7 +6553,10 @@ static int rtl_ops_init(struct r8152 *tp) ops->in_nway = rtl8153_in_nway; ops->hw_phy_cfg = r8153_hw_phy_cfg; ops->autosuspend_en = rtl8153_runtime_enable; - tp->rx_buf_sz = 32 * 1024; + if (tp->udev->speed < USB_SPEED_SUPER) + tp->rx_buf_sz = 16 * 1024; + else + tp->rx_buf_sz = 32 * 1024; tp->eee_en = true; tp->eee_adv = MDIO_EEE_1000T | MDIO_EEE_100TX; break; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index aa1a66ad2ce5..34e49c75db42 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -302,8 +302,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) if (rxq < rcv->real_num_rx_queues) { rq = &rcv_priv->rq[rxq]; rcv_xdp = rcu_access_pointer(rq->xdp_prog); - if (rcv_xdp) - skb_record_rx_queue(skb, rxq); + skb_record_rx_queue(skb, rxq); } skb_tx_timestamp(skb); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 82e520d2cb12..0824e6999e49 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -406,9 +406,13 @@ static struct sk_buff *page_to_skb(struct virtnet_info *vi, offset += hdr_padded_len; p += hdr_padded_len; - copy = len; - if (copy > skb_tailroom(skb)) - copy = skb_tailroom(skb); + /* Copy all frame if it fits skb->head, otherwise + * we let virtio_net_hdr_to_skb() and GRO pull headers as needed. + */ + if (len <= skb_tailroom(skb)) + copy = len; + else + copy = ETH_HLEN + metasize; skb_put_data(skb, p, copy); if (metasize) { diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 6d9130859c55..503e2fd7ce51 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -471,9 +471,8 @@ static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb, skb_dst_drop(skb); - /* if dst.dev is loopback or the VRF device again this is locally - * originated traffic destined to a local address. Short circuit - * to Rx path + /* if dst.dev is the VRF device again this is locally originated traffic + * destined to a local address. Short circuit to Rx path. */ if (dst->dev == dev) return vrf_local_xmit(skb, dev, dst); @@ -547,9 +546,8 @@ static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb, skb_dst_drop(skb); - /* if dst.dev is loopback or the VRF device again this is locally - * originated traffic destined to a local address. Short circuit - * to Rx path + /* if dst.dev is the VRF device again this is locally originated traffic + * destined to a local address. Short circuit to Rx path. */ if (rt->dst.dev == vrf_dev) return vrf_local_xmit(skb, vrf_dev, &rt->dst); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 666dd201c3d5..53dbc67e8a34 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2725,12 +2725,17 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto tx_error; } else if (err) { if (info) { + struct ip_tunnel_info *unclone; struct in_addr src, dst; + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) + goto tx_error; + src = remote_ip.sin.sin_addr; dst = local_ip.sin.sin_addr; - info->key.u.ipv4.src = src.s_addr; - info->key.u.ipv4.dst = dst.s_addr; + unclone->key.u.ipv4.src = src.s_addr; + unclone->key.u.ipv4.dst = dst.s_addr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); dst_release(ndst); @@ -2781,12 +2786,17 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto tx_error; } else if (err) { if (info) { + struct ip_tunnel_info *unclone; struct in6_addr src, dst; + unclone = skb_tunnel_info_unclone(skb); + if (unlikely(!unclone)) + goto tx_error; + src = remote_ip.sin6.sin6_addr; dst = local_ip.sin6.sin6_addr; - info->key.u.ipv6.src = src; - info->key.u.ipv6.dst = dst; + unclone->key.u.ipv6.src = src; + unclone->key.u.ipv6.dst = dst; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 0720f5f92caa..4d9dc7d15908 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -415,7 +415,7 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev) if (pad > 0) { /* Pad the frame with zeros */ if (__skb_pad(skb, pad, false)) - goto drop; + goto out; skb_put(skb, pad); } } @@ -448,8 +448,9 @@ static netdev_tx_t pvc_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; drop: - dev->stats.tx_dropped++; kfree_skb(skb); +out: + dev->stats.tx_dropped++; return NETDEV_TX_OK; } diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index 4aaa6388b9ee..5a6a945f6c81 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -23,6 +23,8 @@ struct x25_state { x25_hdlc_proto settings; + bool up; + spinlock_t up_lock; /* Protects "up" */ }; static int x25_ioctl(struct net_device *dev, struct ifreq *ifr); @@ -104,6 +106,8 @@ static void x25_data_transmit(struct net_device *dev, struct sk_buff *skb) static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) { + hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); int result; /* There should be a pseudo header of 1 byte added by upper layers. @@ -114,11 +118,19 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } + spin_lock_bh(&x25st->up_lock); + if (!x25st->up) { + spin_unlock_bh(&x25st->up_lock); + kfree_skb(skb); + return NETDEV_TX_OK; + } + switch (skb->data[0]) { case X25_IFACE_DATA: /* Data to be transmitted */ skb_pull(skb, 1); if ((result = lapb_data_request(dev, skb)) != LAPB_OK) dev_kfree_skb(skb); + spin_unlock_bh(&x25st->up_lock); return NETDEV_TX_OK; case X25_IFACE_CONNECT: @@ -147,6 +159,7 @@ static netdev_tx_t x25_xmit(struct sk_buff *skb, struct net_device *dev) break; } + spin_unlock_bh(&x25st->up_lock); dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -164,6 +177,7 @@ static int x25_open(struct net_device *dev) .data_transmit = x25_data_transmit, }; hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); struct lapb_parms_struct params; int result; @@ -190,6 +204,10 @@ static int x25_open(struct net_device *dev) if (result != LAPB_OK) return -EINVAL; + spin_lock_bh(&x25st->up_lock); + x25st->up = true; + spin_unlock_bh(&x25st->up_lock); + return 0; } @@ -197,6 +215,13 @@ static int x25_open(struct net_device *dev) static void x25_close(struct net_device *dev) { + hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); + + spin_lock_bh(&x25st->up_lock); + x25st->up = false; + spin_unlock_bh(&x25st->up_lock); + lapb_unregister(dev); } @@ -205,15 +230,28 @@ static void x25_close(struct net_device *dev) static int x25_rx(struct sk_buff *skb) { struct net_device *dev = skb->dev; + hdlc_device *hdlc = dev_to_hdlc(dev); + struct x25_state *x25st = state(hdlc); if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { dev->stats.rx_dropped++; return NET_RX_DROP; } - if (lapb_data_received(dev, skb) == LAPB_OK) + spin_lock_bh(&x25st->up_lock); + if (!x25st->up) { + spin_unlock_bh(&x25st->up_lock); + kfree_skb(skb); + dev->stats.rx_dropped++; + return NET_RX_DROP; + } + + if (lapb_data_received(dev, skb) == LAPB_OK) { + spin_unlock_bh(&x25st->up_lock); return NET_RX_SUCCESS; + } + spin_unlock_bh(&x25st->up_lock); dev->stats.rx_errors++; dev_kfree_skb_any(skb); return NET_RX_DROP; @@ -298,6 +336,8 @@ static int x25_ioctl(struct net_device *dev, struct ifreq *ifr) return result; memcpy(&state(hdlc)->settings, &new_settings, size); + state(hdlc)->up = false; + spin_lock_init(&state(hdlc)->up_lock); /* There's no header_ops so hard_header_len should be 0. */ dev->hard_header_len = 0; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c index 6d30a0fcecea..34cd8a7401fe 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/p2p.c @@ -2439,7 +2439,7 @@ void brcmf_p2p_ifp_removed(struct brcmf_if *ifp, bool locked) vif = ifp->vif; cfg = wdev_to_cfg(&vif->wdev); cfg->p2p.bss_idx[P2PAPI_BSSCFG_DEVICE].vif = NULL; - if (locked) { + if (!locked) { rtnl_lock(); wiphy_lock(cfg->wiphy); cfg80211_unregister_wdev(&vif->wdev); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c b/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c index 3dbc6f3f92cc..231d2517f398 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/notif-wait.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2005-2014 Intel Corporation + * Copyright (C) 2005-2014, 2021 Intel Corporation * Copyright (C) 2015-2017 Intel Deutschland GmbH */ #include <linux/sched.h> @@ -26,7 +26,7 @@ bool iwl_notification_wait(struct iwl_notif_wait_data *notif_wait, if (!list_empty(¬if_wait->notif_waits)) { struct iwl_notification_wait *w; - spin_lock(¬if_wait->notif_wait_lock); + spin_lock_bh(¬if_wait->notif_wait_lock); list_for_each_entry(w, ¬if_wait->notif_waits, list) { int i; bool found = false; @@ -59,7 +59,7 @@ bool iwl_notification_wait(struct iwl_notif_wait_data *notif_wait, triggered = true; } } - spin_unlock(¬if_wait->notif_wait_lock); + spin_unlock_bh(¬if_wait->notif_wait_lock); } return triggered; @@ -70,10 +70,10 @@ void iwl_abort_notification_waits(struct iwl_notif_wait_data *notif_wait) { struct iwl_notification_wait *wait_entry; - spin_lock(¬if_wait->notif_wait_lock); + spin_lock_bh(¬if_wait->notif_wait_lock); list_for_each_entry(wait_entry, ¬if_wait->notif_waits, list) wait_entry->aborted = true; - spin_unlock(¬if_wait->notif_wait_lock); + spin_unlock_bh(¬if_wait->notif_wait_lock); wake_up_all(¬if_wait->notif_waitq); } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 75f99ff7f908..c4f5da76f1c0 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -414,6 +414,7 @@ struct iwl_cfg { #define IWL_CFG_MAC_TYPE_QNJ 0x36 #define IWL_CFG_MAC_TYPE_SO 0x37 #define IWL_CFG_MAC_TYPE_SNJ 0x42 +#define IWL_CFG_MAC_TYPE_SOF 0x43 #define IWL_CFG_MAC_TYPE_MA 0x44 #define IWL_CFG_RF_TYPE_TH 0x105 diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index af684f80b0cc..c5a1e84dc1ab 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -232,7 +232,7 @@ enum iwl_reg_capa_flags_v2 { REG_CAPA_V2_MCS_9_ALLOWED = BIT(6), REG_CAPA_V2_WEATHER_DISABLED = BIT(7), REG_CAPA_V2_40MHZ_ALLOWED = BIT(8), - REG_CAPA_V2_11AX_DISABLED = BIT(13), + REG_CAPA_V2_11AX_DISABLED = BIT(10), }; /* diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index 130760572262..34ddef97b099 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -1786,10 +1786,13 @@ static ssize_t iwl_dbgfs_rfi_freq_table_write(struct iwl_mvm *mvm, char *buf, return -EINVAL; /* value zero triggers re-sending the default table to the device */ - if (!op_id) + if (!op_id) { + mutex_lock(&mvm->mutex); ret = iwl_rfi_send_config_cmd(mvm, NULL); - else + mutex_unlock(&mvm->mutex); + } else { ret = -EOPNOTSUPP; /* in the future a new table will be added */ + } return ret ?: count; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c index 873919048143..0b818067067c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rfi.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2020 Intel Corporation + * Copyright (C) 2020 - 2021 Intel Corporation */ #include "mvm.h" @@ -66,6 +66,8 @@ int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_t if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_RFIM_SUPPORT)) return -EOPNOTSUPP; + lockdep_assert_held(&mvm->mutex); + /* in case no table is passed, use the default one */ if (!rfi_table) { memcpy(cmd.table, iwl_rfi_table, sizeof(cmd.table)); @@ -75,9 +77,7 @@ int iwl_rfi_send_config_cmd(struct iwl_mvm *mvm, struct iwl_rfi_lut_entry *rfi_t cmd.oem = 1; } - mutex_lock(&mvm->mutex); ret = iwl_mvm_send_cmd(mvm, &hcmd); - mutex_unlock(&mvm->mutex); if (ret) IWL_ERR(mvm, "Failed to send RFI config cmd %d\n", ret); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index c21736f80c29..af5a6dd81c41 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -272,10 +272,10 @@ static void iwl_mvm_get_signal_strength(struct iwl_mvm *mvm, rx_status->chain_signal[2] = S8_MIN; } -static int iwl_mvm_rx_mgmt_crypto(struct ieee80211_sta *sta, - struct ieee80211_hdr *hdr, - struct iwl_rx_mpdu_desc *desc, - u32 status) +static int iwl_mvm_rx_mgmt_prot(struct ieee80211_sta *sta, + struct ieee80211_hdr *hdr, + struct iwl_rx_mpdu_desc *desc, + u32 status) { struct iwl_mvm_sta *mvmsta; struct iwl_mvm_vif *mvmvif; @@ -285,6 +285,9 @@ static int iwl_mvm_rx_mgmt_crypto(struct ieee80211_sta *sta, u32 len = le16_to_cpu(desc->mpdu_len); const u8 *frame = (void *)hdr; + if ((status & IWL_RX_MPDU_STATUS_SEC_MASK) == IWL_RX_MPDU_STATUS_SEC_NONE) + return 0; + /* * For non-beacon, we don't really care. But beacons may * be filtered out, and we thus need the firmware's replay @@ -356,6 +359,10 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_sta *sta, IWL_RX_MPDU_STATUS_SEC_UNKNOWN && !mvm->monitor_on) return -1; + if (unlikely(ieee80211_is_mgmt(hdr->frame_control) && + !ieee80211_has_protected(hdr->frame_control))) + return iwl_mvm_rx_mgmt_prot(sta, hdr, desc, status); + if (!ieee80211_has_protected(hdr->frame_control) || (status & IWL_RX_MPDU_STATUS_SEC_MASK) == IWL_RX_MPDU_STATUS_SEC_NONE) @@ -411,7 +418,7 @@ static int iwl_mvm_rx_crypto(struct iwl_mvm *mvm, struct ieee80211_sta *sta, stats->flag |= RX_FLAG_DECRYPTED; return 0; case RX_MPDU_RES_STATUS_SEC_CMAC_GMAC_ENC: - return iwl_mvm_rx_mgmt_crypto(sta, hdr, desc, status); + break; default: /* * Sometimes we can get frames that were not decrypted diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c index 8fba190e84cf..cecc32e7dbe8 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include "iwl-trans.h" #include "iwl-fh.h" @@ -75,15 +75,6 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, const struct fw_img *fw) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); - u32 ltr_val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ | - u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, - CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) | - u32_encode_bits(250, - CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) | - CSR_LTR_LONG_VAL_AD_SNOOP_REQ | - u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, - CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) | - u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL); struct iwl_context_info_gen3 *ctxt_info_gen3; struct iwl_prph_scratch *prph_scratch; struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl; @@ -217,26 +208,6 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans, iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL, CSR_AUTO_FUNC_BOOT_ENA); - /* - * To workaround hardware latency issues during the boot process, - * initialize the LTR to ~250 usec (see ltr_val above). - * The firmware initializes this again later (to a smaller value). - */ - if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 || - trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) && - !trans->trans_cfg->integrated) { - iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val); - } else if (trans->trans_cfg->integrated && - trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) { - iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL); - iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val); - } - - if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) - iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1); - else - iwl_set_bit(trans, CSR_GP_CNTRL, CSR_AUTO_FUNC_INIT); - return 0; err_free_ctxt_info: diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c index d1bb273d6b6d..74ce31fdf45e 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* * Copyright (C) 2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include "iwl-trans.h" #include "iwl-fh.h" @@ -240,7 +240,6 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans, /* kick FW self load */ iwl_write64(trans, CSR_CTXT_INFO_BA, trans_pcie->ctxt_info_dma_addr); - iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1); /* Context info will be released upon alive or failure to get one */ diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index ffaf973dae94..558a0b2ef0fc 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -592,6 +592,7 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_DEV_INFO(0x4DF0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0, NULL), IWL_DEV_INFO(0x4DF0, 0x2074, iwl_ax201_cfg_qu_hr, NULL), IWL_DEV_INFO(0x4DF0, 0x4070, iwl_ax201_cfg_qu_hr, NULL), + IWL_DEV_INFO(0x4DF0, 0x6074, iwl_ax201_cfg_qu_hr, NULL), /* So with HR */ IWL_DEV_INFO(0x2725, 0x0090, iwlax211_2ax_cfg_so_gf_a0, NULL), @@ -1040,7 +1041,31 @@ static const struct iwl_dev_info iwl_dev_info_table[] = { IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY, IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, - iwl_cfg_so_a0_hr_a0, iwl_ax201_name) + iwl_cfg_so_a0_hr_a0, iwl_ax201_name), + +/* So-F with Hr */ + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, + IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, + iwl_cfg_so_a0_hr_a0, iwl_ax203_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, + IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, + iwl_cfg_so_a0_hr_a0, iwl_ax101_name), + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, + IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, + iwl_cfg_so_a0_hr_a0, iwl_ax201_name), + +/* So-F with Gf */ + _IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY, + IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY, + IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, + IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB, + iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name), #endif /* CONFIG_IWLMVM */ }; diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c index 497ef3405da3..94ffc1ae484d 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c @@ -266,6 +266,34 @@ void iwl_trans_pcie_gen2_fw_alive(struct iwl_trans *trans, u32 scd_addr) mutex_unlock(&trans_pcie->mutex); } +static void iwl_pcie_set_ltr(struct iwl_trans *trans) +{ + u32 ltr_val = CSR_LTR_LONG_VAL_AD_NO_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_SCALE) | + u32_encode_bits(250, + CSR_LTR_LONG_VAL_AD_NO_SNOOP_VAL) | + CSR_LTR_LONG_VAL_AD_SNOOP_REQ | + u32_encode_bits(CSR_LTR_LONG_VAL_AD_SCALE_USEC, + CSR_LTR_LONG_VAL_AD_SNOOP_SCALE) | + u32_encode_bits(250, CSR_LTR_LONG_VAL_AD_SNOOP_VAL); + + /* + * To workaround hardware latency issues during the boot process, + * initialize the LTR to ~250 usec (see ltr_val above). + * The firmware initializes this again later (to a smaller value). + */ + if ((trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_AX210 || + trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) && + !trans->trans_cfg->integrated) { + iwl_write32(trans, CSR_LTR_LONG_VAL_AD, ltr_val); + } else if (trans->trans_cfg->integrated && + trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000) { + iwl_write_prph(trans, HPM_MAC_LTR_CSR, HPM_MAC_LRT_ENABLE_ALL); + iwl_write_prph(trans, HPM_UMAC_LTR, ltr_val); + } +} + int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans, const struct fw_img *fw, bool run_in_rfkill) { @@ -332,6 +360,13 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans, if (ret) goto out; + iwl_pcie_set_ltr(trans); + + if (trans->trans_cfg->device_family >= IWL_DEVICE_FAMILY_AX210) + iwl_write_umac_prph(trans, UREG_CPU_INIT_RUN, 1); + else + iwl_write_prph(trans, UREG_CPU_INIT_RUN, 1); + /* re-check RF-Kill state since we may have missed the interrupt */ hw_rfkill = iwl_pcie_check_hw_rf_kill(trans); if (hw_rfkill && !run_in_rfkill) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index 381e8f90b6f2..7ae32491b5da 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -928,6 +928,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans, u32 cmd_pos; const u8 *cmddata[IWL_MAX_CMD_TBS_PER_TFD]; u16 cmdlen[IWL_MAX_CMD_TBS_PER_TFD]; + unsigned long flags; if (WARN(!trans->wide_cmd_header && group_id > IWL_ALWAYS_LONG_GROUP, @@ -1011,10 +1012,10 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans, goto free_dup_buf; } - spin_lock_bh(&txq->lock); + spin_lock_irqsave(&txq->lock, flags); if (iwl_txq_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) { - spin_unlock_bh(&txq->lock); + spin_unlock_irqrestore(&txq->lock, flags); IWL_ERR(trans, "No space in command queue\n"); iwl_op_mode_cmd_queue_full(trans->op_mode); @@ -1174,7 +1175,7 @@ int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans, unlock_reg: spin_unlock(&trans_pcie->reg_lock); out: - spin_unlock_bh(&txq->lock); + spin_unlock_irqrestore(&txq->lock, flags); free_dup_buf: if (idx < 0) kfree(dup_buf); diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h index 18980bb32dee..6dad7f6ab09d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt7921/regs.h @@ -135,10 +135,10 @@ #define MT_WTBLON_TOP_BASE 0x34000 #define MT_WTBLON_TOP(ofs) (MT_WTBLON_TOP_BASE + (ofs)) -#define MT_WTBLON_TOP_WDUCR MT_WTBLON_TOP(0x0) +#define MT_WTBLON_TOP_WDUCR MT_WTBLON_TOP(0x200) #define MT_WTBLON_TOP_WDUCR_GROUP GENMASK(2, 0) -#define MT_WTBL_UPDATE MT_WTBLON_TOP(0x030) +#define MT_WTBL_UPDATE MT_WTBLON_TOP(0x230) #define MT_WTBL_UPDATE_WLAN_IDX GENMASK(9, 0) #define MT_WTBL_UPDATE_ADM_COUNT_CLEAR BIT(12) #define MT_WTBL_UPDATE_BUSY BIT(31) diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index c878097f0dda..1df959532c7d 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -12,6 +12,7 @@ #include <net/cfg80211.h> #include <net/rtnetlink.h> #include <linux/etherdevice.h> +#include <linux/math64.h> #include <linux/module.h> static struct wiphy *common_wiphy; @@ -168,11 +169,11 @@ static void virt_wifi_scan_result(struct work_struct *work) scan_result.work); struct wiphy *wiphy = priv_to_wiphy(priv); struct cfg80211_scan_info scan_info = { .aborted = false }; + u64 tsf = div_u64(ktime_get_boottime_ns(), 1000); informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz, CFG80211_BSS_FTYPE_PRESP, - fake_router_bssid, - ktime_get_boottime_ns(), + fake_router_bssid, tsf, WLAN_CAPABILITY_ESS, 0, (void *)&ssid, sizeof(ssid), DBM_TO_MBM(-50), GFP_KERNEL); diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index a5439c130130..d24b7a7993aa 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -824,11 +824,15 @@ static void connect(struct backend_info *be) xenvif_carrier_on(be->vif); unregister_hotplug_status_watch(be); - err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, NULL, - hotplug_status_changed, - "%s/%s", dev->nodename, "hotplug-status"); - if (!err) + if (xenbus_exists(XBT_NIL, dev->nodename, "hotplug-status")) { + err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, + NULL, hotplug_status_changed, + "%s/%s", dev->nodename, + "hotplug-status"); + if (err) + goto err; be->have_hotplug_status_watch = 1; + } netif_tx_wake_all_queues(be->vif->dev); diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 48f0985ca8a0..3a777d0073b7 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -631,16 +631,14 @@ void nvdimm_check_and_set_ro(struct gendisk *disk) struct nd_region *nd_region = to_nd_region(dev->parent); int disk_ro = get_disk_ro(disk); - /* - * Upgrade to read-only if the region is read-only preserve as - * read-only if the disk is already read-only. - */ - if (disk_ro || nd_region->ro == disk_ro) + /* catch the disk up with the region ro state */ + if (disk_ro == nd_region->ro) return; - dev_info(dev, "%s read-only, marking %s read-only\n", - dev_name(&nd_region->dev), disk->disk_name); - set_disk_ro(disk, 1); + dev_info(dev, "%s read-%s, marking %s read-%s\n", + dev_name(&nd_region->dev), nd_region->ro ? "only" : "write", + disk->disk_name, nd_region->ro ? "only" : "write"); + set_disk_ro(disk, nd_region->ro); } EXPORT_SYMBOL(nvdimm_check_and_set_ro); diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index b8a85bfb2e95..7daac795db39 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -26,6 +26,7 @@ #include <linux/mm.h> #include <asm/cacheflush.h> #include "pmem.h" +#include "btt.h" #include "pfn.h" #include "nd.h" @@ -585,7 +586,7 @@ static void nd_pmem_shutdown(struct device *dev) nvdimm_flush(to_nd_region(dev->parent), NULL); } -static void nd_pmem_notify(struct device *dev, enum nvdimm_event event) +static void pmem_revalidate_poison(struct device *dev) { struct nd_region *nd_region; resource_size_t offset = 0, end_trunc = 0; @@ -595,9 +596,6 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event) struct range range; struct kernfs_node *bb_state; - if (event != NVDIMM_REVALIDATE_POISON) - return; - if (is_nd_btt(dev)) { struct nd_btt *nd_btt = to_nd_btt(dev); @@ -635,6 +633,37 @@ static void nd_pmem_notify(struct device *dev, enum nvdimm_event event) sysfs_notify_dirent(bb_state); } +static void pmem_revalidate_region(struct device *dev) +{ + struct pmem_device *pmem; + + if (is_nd_btt(dev)) { + struct nd_btt *nd_btt = to_nd_btt(dev); + struct btt *btt = nd_btt->btt; + + nvdimm_check_and_set_ro(btt->btt_disk); + return; + } + + pmem = dev_get_drvdata(dev); + nvdimm_check_and_set_ro(pmem->disk); +} + +static void nd_pmem_notify(struct device *dev, enum nvdimm_event event) +{ + switch (event) { + case NVDIMM_REVALIDATE_POISON: + pmem_revalidate_poison(dev); + break; + case NVDIMM_REVALIDATE_REGION: + pmem_revalidate_region(dev); + break; + default: + dev_WARN_ONCE(dev, 1, "notify: unknown event: %d\n", event); + break; + } +} + MODULE_ALIAS("pmem"); MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO); MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM); diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index ef23119db574..9ccf3d608799 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -518,6 +518,12 @@ static ssize_t read_only_show(struct device *dev, return sprintf(buf, "%d\n", nd_region->ro); } +static int revalidate_read_only(struct device *dev, void *data) +{ + nd_device_notify(dev, NVDIMM_REVALIDATE_REGION); + return 0; +} + static ssize_t read_only_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -529,6 +535,7 @@ static ssize_t read_only_store(struct device *dev, return rc; nd_region->ro = ro; + device_for_each_child(dev, NULL, revalidate_read_only); return len; } static DEVICE_ATTR_RW(read_only); @@ -1239,6 +1246,11 @@ int nvdimm_has_flush(struct nd_region *nd_region) || !IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API)) return -ENXIO; + /* Test if an explicit flush function is defined */ + if (test_bit(ND_REGION_ASYNC, &nd_region->flags) && nd_region->flush) + return 1; + + /* Test if any flush hints for the region are available */ for (i = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; struct nvdimm *nvdimm = nd_mapping->nvdimm; @@ -1249,8 +1261,8 @@ int nvdimm_has_flush(struct nd_region *nd_region) } /* - * The platform defines dimm devices without hints, assume - * platform persistence mechanism like ADR + * The platform defines dimm devices without hints nor explicit flush, + * assume platform persistence mechanism like ADR */ return 0; } diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index dcc1dd96911a..adb26aff481d 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -205,7 +205,7 @@ static void populate_properties(const void *blob, *pprev = NULL; } -static bool populate_node(const void *blob, +static int populate_node(const void *blob, int offset, void **mem, struct device_node *dad, @@ -214,24 +214,24 @@ static bool populate_node(const void *blob, { struct device_node *np; const char *pathp; - unsigned int l, allocl; + int len; - pathp = fdt_get_name(blob, offset, &l); + pathp = fdt_get_name(blob, offset, &len); if (!pathp) { *pnp = NULL; - return false; + return len; } - allocl = ++l; + len++; - np = unflatten_dt_alloc(mem, sizeof(struct device_node) + allocl, + np = unflatten_dt_alloc(mem, sizeof(struct device_node) + len, __alignof__(struct device_node)); if (!dryrun) { char *fn; of_node_init(np); np->full_name = fn = ((char *)np) + sizeof(*np); - memcpy(fn, pathp, l); + memcpy(fn, pathp, len); if (dad != NULL) { np->parent = dad; @@ -295,6 +295,7 @@ static int unflatten_dt_nodes(const void *blob, struct device_node *nps[FDT_MAX_DEPTH]; void *base = mem; bool dryrun = !base; + int ret; if (nodepp) *nodepp = NULL; @@ -322,9 +323,10 @@ static int unflatten_dt_nodes(const void *blob, !of_fdt_device_is_available(blob, offset)) continue; - if (!populate_node(blob, offset, &mem, nps[depth], - &nps[depth+1], dryrun)) - return mem - base; + ret = populate_node(blob, offset, &mem, nps[depth], + &nps[depth+1], dryrun); + if (ret < 0) + return ret; if (!dryrun && nodepp && !*nodepp) *nodepp = nps[depth+1]; @@ -372,6 +374,10 @@ void *__unflatten_device_tree(const void *blob, { int size; void *mem; + int ret; + + if (mynodes) + *mynodes = NULL; pr_debug(" -> unflatten_device_tree()\n"); @@ -392,7 +398,7 @@ void *__unflatten_device_tree(const void *blob, /* First pass, scan for size */ size = unflatten_dt_nodes(blob, NULL, dad, NULL); - if (size < 0) + if (size <= 0) return NULL; size = ALIGN(size, 4); @@ -410,12 +416,16 @@ void *__unflatten_device_tree(const void *blob, pr_debug(" unflattening %p...\n", mem); /* Second pass, do actual unflattening */ - unflatten_dt_nodes(blob, mem, dad, mynodes); + ret = unflatten_dt_nodes(blob, mem, dad, mynodes); + if (be32_to_cpup(mem + size) != 0xdeadbeef) pr_warn("End of tree marker overwritten: %08x\n", be32_to_cpup(mem + size)); - if (detached && mynodes) { + if (ret <= 0) + return NULL; + + if (detached && mynodes && *mynodes) { of_node_set_flag(*mynodes, OF_DETACHED); pr_debug("unflattened tree is detached\n"); } diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h index d9e6a324de0a..d717efbd637d 100644 --- a/drivers/of/of_private.h +++ b/drivers/of/of_private.h @@ -8,6 +8,8 @@ * Copyright (C) 1996-2005 Paul Mackerras. */ +#define FDT_ALIGN_SIZE 8 + /** * struct alias_prop - Alias property in 'aliases' node * @link: List node to link the structure in aliases_lookup list diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c index 50bbe0edf538..23effe5e50ec 100644 --- a/drivers/of/overlay.c +++ b/drivers/of/overlay.c @@ -57,7 +57,7 @@ struct fragment { * struct overlay_changeset * @id: changeset identifier * @ovcs_list: list on which we are located - * @fdt: FDT that was unflattened to create @overlay_tree + * @fdt: base of memory allocated to hold aligned FDT that was unflattened to create @overlay_tree * @overlay_tree: expanded device tree that contains the fragment nodes * @count: count of fragment structures * @fragments: fragment nodes in the overlay expanded device tree @@ -719,8 +719,8 @@ static struct device_node *find_target(struct device_node *info_node) /** * init_overlay_changeset() - initialize overlay changeset from overlay tree * @ovcs: Overlay changeset to build - * @fdt: the FDT that was unflattened to create @tree - * @tree: Contains all the overlay fragments and overlay fixup nodes + * @fdt: base of memory allocated to hold aligned FDT that was unflattened to create @tree + * @tree: Contains the overlay fragments and overlay fixup nodes * * Initialize @ovcs. Populate @ovcs->fragments with node information from * the top level of @tree. The relevant top level nodes are the fragment @@ -873,7 +873,7 @@ static void free_overlay_changeset(struct overlay_changeset *ovcs) * internal documentation * * of_overlay_apply() - Create and apply an overlay changeset - * @fdt: the FDT that was unflattened to create @tree + * @fdt: base of memory allocated to hold the aligned FDT * @tree: Expanded overlay device tree * @ovcs_id: Pointer to overlay changeset id * @@ -953,7 +953,9 @@ static int of_overlay_apply(const void *fdt, struct device_node *tree, /* * after overlay_notify(), ovcs->overlay_tree related pointers may have * leaked to drivers, so can not kfree() tree, aka ovcs->overlay_tree; - * and can not free fdt, aka ovcs->fdt + * and can not free memory containing aligned fdt. The aligned fdt + * is contained within the memory at ovcs->fdt, possibly at an offset + * from ovcs->fdt. */ ret = overlay_notify(ovcs, OF_OVERLAY_PRE_APPLY); if (ret) { @@ -1014,10 +1016,11 @@ out: int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size, int *ovcs_id) { - const void *new_fdt; + void *new_fdt; + void *new_fdt_align; int ret; u32 size; - struct device_node *overlay_root; + struct device_node *overlay_root = NULL; *ovcs_id = 0; ret = 0; @@ -1036,11 +1039,14 @@ int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size, * Must create permanent copy of FDT because of_fdt_unflatten_tree() * will create pointers to the passed in FDT in the unflattened tree. */ - new_fdt = kmemdup(overlay_fdt, size, GFP_KERNEL); + new_fdt = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL); if (!new_fdt) return -ENOMEM; - of_fdt_unflatten_tree(new_fdt, NULL, &overlay_root); + new_fdt_align = PTR_ALIGN(new_fdt, FDT_ALIGN_SIZE); + memcpy(new_fdt_align, overlay_fdt, size); + + of_fdt_unflatten_tree(new_fdt_align, NULL, &overlay_root); if (!overlay_root) { pr_err("unable to unflatten overlay_fdt\n"); ret = -EINVAL; diff --git a/drivers/of/property.c b/drivers/of/property.c index 5036a362f52e..78427c85bef3 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1262,7 +1262,16 @@ DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL) DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL) DEFINE_SUFFIX_PROP(regulators, "-supply", NULL) DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells") -DEFINE_SUFFIX_PROP(gpios, "-gpios", "#gpio-cells") + +static struct device_node *parse_gpios(struct device_node *np, + const char *prop_name, int index) +{ + if (!strcmp_suffix(prop_name, ",nr-gpios")) + return NULL; + + return parse_suffix_prop_cells(np, prop_name, index, "-gpios", + "#gpio-cells"); +} static struct device_node *parse_iommu_maps(struct device_node *np, const char *prop_name, int index) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index eb100627c186..819a20acaa93 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -22,6 +22,7 @@ #include <linux/slab.h> #include <linux/device.h> #include <linux/platform_device.h> +#include <linux/kernel.h> #include <linux/i2c.h> #include <linux/i2c-mux.h> @@ -1408,7 +1409,8 @@ static void attach_node_and_children(struct device_node *np) static int __init unittest_data_add(void) { void *unittest_data; - struct device_node *unittest_data_node, *np; + void *unittest_data_align; + struct device_node *unittest_data_node = NULL, *np; /* * __dtb_testcases_begin[] and __dtb_testcases_end[] are magically * created by cmd_dt_S_dtb in scripts/Makefile.lib @@ -1417,21 +1419,29 @@ static int __init unittest_data_add(void) extern uint8_t __dtb_testcases_end[]; const int size = __dtb_testcases_end - __dtb_testcases_begin; int rc; + void *ret; if (!size) { - pr_warn("%s: No testcase data to attach; not running tests\n", - __func__); + pr_warn("%s: testcases is empty\n", __func__); return -ENODATA; } /* creating copy */ - unittest_data = kmemdup(__dtb_testcases_begin, size, GFP_KERNEL); + unittest_data = kmalloc(size + FDT_ALIGN_SIZE, GFP_KERNEL); if (!unittest_data) return -ENOMEM; - of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node); + unittest_data_align = PTR_ALIGN(unittest_data, FDT_ALIGN_SIZE); + memcpy(unittest_data_align, __dtb_testcases_begin, size); + + ret = of_fdt_unflatten_tree(unittest_data_align, NULL, &unittest_data_node); + if (!ret) { + pr_warn("%s: unflatten testcases tree failed\n", __func__); + kfree(unittest_data); + return -ENODATA; + } if (!unittest_data_node) { - pr_warn("%s: No tree to attach; not running tests\n", __func__); + pr_warn("%s: testcases tree is empty\n", __func__); kfree(unittest_data); return -ENODATA; } diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index 7d3370289938..6e6825d17a1d 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -1604,8 +1604,8 @@ static int pinctrl_pins_show(struct seq_file *s, void *what) unsigned i, pin; #ifdef CONFIG_GPIOLIB struct pinctrl_gpio_range *range; - unsigned int gpio_num; struct gpio_chip *chip; + int gpio_num; #endif seq_printf(s, "registered pins: %d\n", pctldev->desc->npins); @@ -1625,7 +1625,7 @@ static int pinctrl_pins_show(struct seq_file *s, void *what) seq_printf(s, "pin %d (%s) ", pin, desc->name); #ifdef CONFIG_GPIOLIB - gpio_num = 0; + gpio_num = -1; list_for_each_entry(range, &pctldev->gpio_ranges, node) { if ((pin >= range->pin_base) && (pin < (range->pin_base + range->npins))) { @@ -1633,10 +1633,12 @@ static int pinctrl_pins_show(struct seq_file *s, void *what) break; } } - chip = gpio_to_chip(gpio_num); - if (chip && chip->gpiodev && chip->gpiodev->base) - seq_printf(s, "%u:%s ", gpio_num - - chip->gpiodev->base, chip->label); + if (gpio_num >= 0) + chip = gpio_to_chip(gpio_num); + else + chip = NULL; + if (chip) + seq_printf(s, "%u:%s ", gpio_num - chip->gpiodev->base, chip->label); else seq_puts(s, "0:? "); #endif diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c index 8085782cd8f9..9f3361c13ded 100644 --- a/drivers/pinctrl/intel/pinctrl-intel.c +++ b/drivers/pinctrl/intel/pinctrl-intel.c @@ -1357,6 +1357,7 @@ static int intel_pinctrl_add_padgroups_by_gpps(struct intel_pinctrl *pctrl, gpps[i].gpio_base = 0; break; case INTEL_GPIO_BASE_NOMAP: + break; default: break; } @@ -1393,6 +1394,7 @@ static int intel_pinctrl_add_padgroups_by_size(struct intel_pinctrl *pctrl, gpps[i].size = min(gpp_size, npins); npins -= gpps[i].size; + gpps[i].gpio_base = gpps[i].base; gpps[i].padown_num = padown_num; /* @@ -1491,8 +1493,13 @@ static int intel_pinctrl_probe(struct platform_device *pdev, if (IS_ERR(regs)) return PTR_ERR(regs); - /* Determine community features based on the revision */ + /* + * Determine community features based on the revision. + * A value of all ones means the device is not present. + */ value = readl(regs + REVID); + if (value == ~0u) + return -ENODEV; if (((value & REVID_MASK) >> REVID_SHIFT) >= 0x94) { community->features |= PINCTRL_FEATURE_DEBOUNCE; community->features |= PINCTRL_FEATURE_1K_PD; diff --git a/drivers/pinctrl/intel/pinctrl-lewisburg.c b/drivers/pinctrl/intel/pinctrl-lewisburg.c index 7fdf4257df1e..ad4b446d588e 100644 --- a/drivers/pinctrl/intel/pinctrl-lewisburg.c +++ b/drivers/pinctrl/intel/pinctrl-lewisburg.c @@ -299,9 +299,9 @@ static const struct pinctrl_pin_desc lbg_pins[] = { static const struct intel_community lbg_communities[] = { LBG_COMMUNITY(0, 0, 71), LBG_COMMUNITY(1, 72, 132), - LBG_COMMUNITY(3, 133, 144), - LBG_COMMUNITY(4, 145, 180), - LBG_COMMUNITY(5, 181, 246), + LBG_COMMUNITY(3, 133, 143), + LBG_COMMUNITY(4, 144, 178), + LBG_COMMUNITY(5, 179, 246), }; static const struct intel_pinctrl_soc_data lbg_soc_data = { diff --git a/drivers/pinctrl/pinctrl-microchip-sgpio.c b/drivers/pinctrl/pinctrl-microchip-sgpio.c index f35edb0eac40..c12fa57ebd12 100644 --- a/drivers/pinctrl/pinctrl-microchip-sgpio.c +++ b/drivers/pinctrl/pinctrl-microchip-sgpio.c @@ -572,7 +572,7 @@ static void microchip_sgpio_irq_settype(struct irq_data *data, /* Type value spread over 2 registers sets: low, high bit */ sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER, addr.bit, BIT(addr.port), (!!(type & 0x1)) << addr.port); - sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER + SGPIO_MAX_BITS, addr.bit, + sgpio_clrsetbits(bank->priv, REG_INT_TRIGGER, SGPIO_MAX_BITS + addr.bit, BIT(addr.port), (!!(type & 0x2)) << addr.port); if (type == SGPIO_INT_TRG_LEVEL) diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index aa1a1c850d05..53a0badc6b03 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -3727,12 +3727,15 @@ static int __maybe_unused rockchip_pinctrl_suspend(struct device *dev) static int __maybe_unused rockchip_pinctrl_resume(struct device *dev) { struct rockchip_pinctrl *info = dev_get_drvdata(dev); - int ret = regmap_write(info->regmap_base, RK3288_GRF_GPIO6C_IOMUX, - rk3288_grf_gpio6c_iomux | - GPIO6C6_SEL_WRITE_ENABLE); + int ret; - if (ret) - return ret; + if (info->ctrl->type == RK3288) { + ret = regmap_write(info->regmap_base, RK3288_GRF_GPIO6C_IOMUX, + rk3288_grf_gpio6c_iomux | + GPIO6C6_SEL_WRITE_ENABLE); + if (ret) + return ret; + } return pinctrl_force_default(info->pctl_dev); } diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c index 369ee20a7ea9..2f19ab4db720 100644 --- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c @@ -392,7 +392,7 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group, unsigned long *configs, unsigned int nconfs) { struct lpi_pinctrl *pctrl = dev_get_drvdata(pctldev->dev); - unsigned int param, arg, pullup, strength; + unsigned int param, arg, pullup = LPI_GPIO_BIAS_DISABLE, strength = 2; bool value, output_enabled = false; const struct lpi_pingroup *g; unsigned long sval; diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280.c b/drivers/pinctrl/qcom/pinctrl-sc7280.c index 8daccd530285..9d41abfca37e 100644 --- a/drivers/pinctrl/qcom/pinctrl-sc7280.c +++ b/drivers/pinctrl/qcom/pinctrl-sc7280.c @@ -1439,14 +1439,14 @@ static const struct msm_pingroup sc7280_groups[] = { [172] = PINGROUP(172, qdss, _, _, _, _, _, _, _, _), [173] = PINGROUP(173, qdss, _, _, _, _, _, _, _, _), [174] = PINGROUP(174, qdss, _, _, _, _, _, _, _, _), - [175] = UFS_RESET(ufs_reset, 0x1be000), - [176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0x1b3000, 15, 0), - [177] = SDC_QDSD_PINGROUP(sdc1_clk, 0x1b3000, 13, 6), - [178] = SDC_QDSD_PINGROUP(sdc1_cmd, 0x1b3000, 11, 3), - [179] = SDC_QDSD_PINGROUP(sdc1_data, 0x1b3000, 9, 0), - [180] = SDC_QDSD_PINGROUP(sdc2_clk, 0x1b4000, 14, 6), - [181] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x1b4000, 11, 3), - [182] = SDC_QDSD_PINGROUP(sdc2_data, 0x1b4000, 9, 0), + [175] = UFS_RESET(ufs_reset, 0xbe000), + [176] = SDC_QDSD_PINGROUP(sdc1_rclk, 0xb3004, 0, 6), + [177] = SDC_QDSD_PINGROUP(sdc1_clk, 0xb3000, 13, 6), + [178] = SDC_QDSD_PINGROUP(sdc1_cmd, 0xb3000, 11, 3), + [179] = SDC_QDSD_PINGROUP(sdc1_data, 0xb3000, 9, 0), + [180] = SDC_QDSD_PINGROUP(sdc2_clk, 0xb4000, 14, 6), + [181] = SDC_QDSD_PINGROUP(sdc2_cmd, 0xb4000, 11, 3), + [182] = SDC_QDSD_PINGROUP(sdc2_data, 0xb4000, 9, 0), }; static const struct msm_pinctrl_soc_data sc7280_pinctrl = { diff --git a/drivers/pinctrl/qcom/pinctrl-sdx55.c b/drivers/pinctrl/qcom/pinctrl-sdx55.c index 2b5b0e2b03ad..5aaf57b40407 100644 --- a/drivers/pinctrl/qcom/pinctrl-sdx55.c +++ b/drivers/pinctrl/qcom/pinctrl-sdx55.c @@ -423,7 +423,7 @@ static const char * const gpio_groups[] = { static const char * const qdss_stm_groups[] = { "gpio0", "gpio1", "gpio2", "gpio3", "gpio4", "gpio5", "gpio6", "gpio7", "gpio12", "gpio13", - "gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19" "gpio20", "gpio21", "gpio22", + "gpio14", "gpio15", "gpio16", "gpio17", "gpio18", "gpio19", "gpio20", "gpio21", "gpio22", "gpio23", "gpio44", "gpio45", "gpio52", "gpio53", "gpio56", "gpio57", "gpio61", "gpio62", "gpio63", "gpio64", "gpio65", "gpio66", }; diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index ad4e630e73e2..461ec61530eb 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -1173,15 +1173,20 @@ config INTEL_PMC_CORE depends on PCI help The Intel Platform Controller Hub for Intel Core SoCs provides access - to Power Management Controller registers via a PCI interface. This + to Power Management Controller registers via various interfaces. This driver can utilize debugging capabilities and supported features as - exposed by the Power Management Controller. + exposed by the Power Management Controller. It also may perform some + tasks in the PMC in order to enable transition into the SLPS0 state. + It should be selected on all Intel platforms supported by the driver. Supported features: - SLP_S0_RESIDENCY counter - PCH IP Power Gating status - - LTR Ignore + - LTR Ignore / LTR Show - MPHY/PLL gating status (Sunrisepoint PCH only) + - SLPS0 Debug registers (Cannonlake/Icelake PCH) + - Low Power Mode registers (Tigerlake and beyond) + - PMC quirks as needed to enable SLPS0/S0ix config INTEL_PMT_CLASS tristate diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c index 80f4b7785c6c..091e48c217ed 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/enum-attributes.c @@ -185,5 +185,8 @@ void exit_enum_attributes(void) sysfs_remove_group(wmi_priv.enumeration_data[instance_id].attr_name_kobj, &enumeration_attr_group); } + wmi_priv.enumeration_instances_count = 0; + kfree(wmi_priv.enumeration_data); + wmi_priv.enumeration_data = NULL; } diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c index 75aedbb733be..8a49ba6e44f9 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/int-attributes.c @@ -175,5 +175,8 @@ void exit_int_attributes(void) sysfs_remove_group(wmi_priv.integer_data[instance_id].attr_name_kobj, &integer_attr_group); } + wmi_priv.integer_instances_count = 0; + kfree(wmi_priv.integer_data); + wmi_priv.integer_data = NULL; } diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c index 3abcd95477c0..834b3e82ad9f 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/passobj-attributes.c @@ -183,5 +183,8 @@ void exit_po_attributes(void) sysfs_remove_group(wmi_priv.po_data[instance_id].attr_name_kobj, &po_attr_group); } + wmi_priv.po_instances_count = 0; + kfree(wmi_priv.po_data); + wmi_priv.po_data = NULL; } diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c index ac75dce88a4c..552537852459 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/string-attributes.c @@ -155,5 +155,8 @@ void exit_str_attributes(void) sysfs_remove_group(wmi_priv.str_data[instance_id].attr_name_kobj, &str_attr_group); } + wmi_priv.str_instances_count = 0; + kfree(wmi_priv.str_data); + wmi_priv.str_data = NULL; } diff --git a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c index cb81010ba1a2..7410ccae650c 100644 --- a/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c +++ b/drivers/platform/x86/dell/dell-wmi-sysman/sysman.c @@ -210,25 +210,17 @@ static struct kobj_attribute pending_reboot = __ATTR_RO(pending_reboot); */ static int create_attributes_level_sysfs_files(void) { - int ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); + int ret; - if (ret) { - pr_debug("could not create reset_bios file\n"); + ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); + if (ret) return ret; - } ret = sysfs_create_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr); - if (ret) { - pr_debug("could not create changing_pending_reboot file\n"); - sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); - } - return ret; -} + if (ret) + return ret; -static void release_reset_bios_data(void) -{ - sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); - sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr); + return 0; } static ssize_t wmi_sysman_attr_show(struct kobject *kobj, struct attribute *attr, @@ -373,8 +365,6 @@ static void destroy_attribute_objs(struct kset *kset) */ static void release_attributes_data(void) { - release_reset_bios_data(); - mutex_lock(&wmi_priv.mutex); exit_enum_attributes(); exit_int_attributes(); @@ -386,11 +376,13 @@ static void release_attributes_data(void) wmi_priv.authentication_dir_kset = NULL; } if (wmi_priv.main_dir_kset) { + sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &reset_bios.attr); + sysfs_remove_file(&wmi_priv.main_dir_kset->kobj, &pending_reboot.attr); destroy_attribute_objs(wmi_priv.main_dir_kset); kset_unregister(wmi_priv.main_dir_kset); + wmi_priv.main_dir_kset = NULL; } mutex_unlock(&wmi_priv.mutex); - } /** @@ -497,7 +489,6 @@ nextobj: err_attr_init: mutex_unlock(&wmi_priv.mutex); - release_attributes_data(); kfree(obj); return retval; } @@ -513,102 +504,91 @@ static int __init sysman_init(void) } ret = init_bios_attr_set_interface(); - if (ret || !wmi_priv.bios_attr_wdev) { - pr_debug("failed to initialize set interface\n"); - goto fail_set_interface; - } + if (ret) + return ret; ret = init_bios_attr_pass_interface(); - if (ret || !wmi_priv.password_attr_wdev) { - pr_debug("failed to initialize pass interface\n"); - goto fail_pass_interface; + if (ret) + goto err_exit_bios_attr_set_interface; + + if (!wmi_priv.bios_attr_wdev || !wmi_priv.password_attr_wdev) { + pr_debug("failed to find set or pass interface\n"); + ret = -ENODEV; + goto err_exit_bios_attr_pass_interface; } ret = class_register(&firmware_attributes_class); if (ret) - goto fail_class; + goto err_exit_bios_attr_pass_interface; wmi_priv.class_dev = device_create(&firmware_attributes_class, NULL, MKDEV(0, 0), NULL, "%s", DRIVER_NAME); if (IS_ERR(wmi_priv.class_dev)) { ret = PTR_ERR(wmi_priv.class_dev); - goto fail_classdev; + goto err_unregister_class; } wmi_priv.main_dir_kset = kset_create_and_add("attributes", NULL, &wmi_priv.class_dev->kobj); if (!wmi_priv.main_dir_kset) { ret = -ENOMEM; - goto fail_main_kset; + goto err_destroy_classdev; } wmi_priv.authentication_dir_kset = kset_create_and_add("authentication", NULL, &wmi_priv.class_dev->kobj); if (!wmi_priv.authentication_dir_kset) { ret = -ENOMEM; - goto fail_authentication_kset; + goto err_release_attributes_data; } ret = create_attributes_level_sysfs_files(); if (ret) { pr_debug("could not create reset BIOS attribute\n"); - goto fail_reset_bios; + goto err_release_attributes_data; } ret = init_bios_attributes(ENUM, DELL_WMI_BIOS_ENUMERATION_ATTRIBUTE_GUID); if (ret) { pr_debug("failed to populate enumeration type attributes\n"); - goto fail_create_group; + goto err_release_attributes_data; } ret = init_bios_attributes(INT, DELL_WMI_BIOS_INTEGER_ATTRIBUTE_GUID); if (ret) { pr_debug("failed to populate integer type attributes\n"); - goto fail_create_group; + goto err_release_attributes_data; } ret = init_bios_attributes(STR, DELL_WMI_BIOS_STRING_ATTRIBUTE_GUID); if (ret) { pr_debug("failed to populate string type attributes\n"); - goto fail_create_group; + goto err_release_attributes_data; } ret = init_bios_attributes(PO, DELL_WMI_BIOS_PASSOBJ_ATTRIBUTE_GUID); if (ret) { pr_debug("failed to populate pass object type attributes\n"); - goto fail_create_group; + goto err_release_attributes_data; } return 0; -fail_create_group: +err_release_attributes_data: release_attributes_data(); -fail_reset_bios: - if (wmi_priv.authentication_dir_kset) { - kset_unregister(wmi_priv.authentication_dir_kset); - wmi_priv.authentication_dir_kset = NULL; - } - -fail_authentication_kset: - if (wmi_priv.main_dir_kset) { - kset_unregister(wmi_priv.main_dir_kset); - wmi_priv.main_dir_kset = NULL; - } - -fail_main_kset: +err_destroy_classdev: device_destroy(&firmware_attributes_class, MKDEV(0, 0)); -fail_classdev: +err_unregister_class: class_unregister(&firmware_attributes_class); -fail_class: +err_exit_bios_attr_pass_interface: exit_bios_attr_pass_interface(); -fail_pass_interface: +err_exit_bios_attr_set_interface: exit_bios_attr_set_interface(); -fail_set_interface: return ret; } diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c index 2f5b8d09143e..078648a9201b 100644 --- a/drivers/platform/x86/intel-hid.c +++ b/drivers/platform/x86/intel-hid.c @@ -90,6 +90,13 @@ static const struct dmi_system_id button_array_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "HP Spectre x2 Detachable"), }, }, + { + .ident = "Lenovo ThinkPad X1 Tablet Gen 2", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Tablet Gen 2"), + }, + }, { } }; @@ -476,11 +483,16 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) goto wakeup; /* - * Switch events will wake the device and report the new switch - * position to the input subsystem. + * Some devices send (duplicate) tablet-mode events when moved + * around even though the mode has not changed; and they do this + * even when suspended. + * Update the switch state in case it changed and then return + * without waking up to avoid spurious wakeups. */ - if (priv->switches && (event == 0xcc || event == 0xcd)) - goto wakeup; + if (event == 0xcc || event == 0xcd) { + report_tablet_mode_event(priv->switches, event); + return; + } /* Wake up on 5-button array events only. */ if (event == 0xc0 || !priv->array) @@ -494,9 +506,6 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) wakeup: pm_wakeup_hard_event(&device->dev); - if (report_tablet_mode_event(priv->switches, event)) - return; - return; } diff --git a/drivers/platform/x86/intel-vbtn.c b/drivers/platform/x86/intel-vbtn.c index 8a8017f9ca91..3fdf4cbec9ad 100644 --- a/drivers/platform/x86/intel-vbtn.c +++ b/drivers/platform/x86/intel-vbtn.c @@ -48,8 +48,16 @@ static const struct key_entry intel_vbtn_keymap[] = { }; static const struct key_entry intel_vbtn_switchmap[] = { - { KE_SW, 0xCA, { .sw = { SW_DOCK, 1 } } }, /* Docked */ - { KE_SW, 0xCB, { .sw = { SW_DOCK, 0 } } }, /* Undocked */ + /* + * SW_DOCK should only be reported for docking stations, but DSDTs using the + * intel-vbtn code, always seem to use this for 2-in-1s / convertibles and set + * SW_DOCK=1 when in laptop-mode (in tandem with setting SW_TABLET_MODE=0). + * This causes userspace to think the laptop is docked to a port-replicator + * and to disable suspend-on-lid-close, which is undesirable. + * Map the dock events to KEY_IGNORE to avoid this broken SW_DOCK reporting. + */ + { KE_IGNORE, 0xCA, { .sw = { SW_DOCK, 1 } } }, /* Docked */ + { KE_IGNORE, 0xCB, { .sw = { SW_DOCK, 0 } } }, /* Undocked */ { KE_SW, 0xCC, { .sw = { SW_TABLET_MODE, 1 } } }, /* Tablet */ { KE_SW, 0xCD, { .sw = { SW_TABLET_MODE, 0 } } }, /* Laptop */ { KE_END } diff --git a/drivers/platform/x86/intel_pmc_core.c b/drivers/platform/x86/intel_pmc_core.c index ee2f757515b0..b5888aeb4bcf 100644 --- a/drivers/platform/x86/intel_pmc_core.c +++ b/drivers/platform/x86/intel_pmc_core.c @@ -863,34 +863,45 @@ out_unlock: } DEFINE_SHOW_ATTRIBUTE(pmc_core_pll); -static ssize_t pmc_core_ltr_ignore_write(struct file *file, - const char __user *userbuf, - size_t count, loff_t *ppos) +static int pmc_core_send_ltr_ignore(u32 value) { struct pmc_dev *pmcdev = &pmc; const struct pmc_reg_map *map = pmcdev->map; - u32 val, buf_size, fd; - int err; - - buf_size = count < 64 ? count : 64; - - err = kstrtou32_from_user(userbuf, buf_size, 10, &val); - if (err) - return err; + u32 reg; + int err = 0; mutex_lock(&pmcdev->lock); - if (val > map->ltr_ignore_max) { + if (value > map->ltr_ignore_max) { err = -EINVAL; goto out_unlock; } - fd = pmc_core_reg_read(pmcdev, map->ltr_ignore_offset); - fd |= (1U << val); - pmc_core_reg_write(pmcdev, map->ltr_ignore_offset, fd); + reg = pmc_core_reg_read(pmcdev, map->ltr_ignore_offset); + reg |= BIT(value); + pmc_core_reg_write(pmcdev, map->ltr_ignore_offset, reg); out_unlock: mutex_unlock(&pmcdev->lock); + + return err; +} + +static ssize_t pmc_core_ltr_ignore_write(struct file *file, + const char __user *userbuf, + size_t count, loff_t *ppos) +{ + u32 buf_size, value; + int err; + + buf_size = min_t(u32, count, 64); + + err = kstrtou32_from_user(userbuf, buf_size, 10, &value); + if (err) + return err; + + err = pmc_core_send_ltr_ignore(value); + return err == 0 ? count : err; } @@ -1244,6 +1255,15 @@ static int pmc_core_probe(struct platform_device *pdev) pmcdev->pmc_xram_read_bit = pmc_core_check_read_lock_bit(); dmi_check_system(pmc_core_dmi_table); + /* + * On TGL, due to a hardware limitation, the GBE LTR blocks PC10 when + * a cable is attached. Tell the PMC to ignore it. + */ + if (pmcdev->map == &tgl_reg_map) { + dev_dbg(&pdev->dev, "ignoring GBE LTR\n"); + pmc_core_send_ltr_ignore(3); + } + pmc_core_dbgfs_register(pmcdev); device_initialized = true; diff --git a/drivers/platform/x86/intel_pmt_class.c b/drivers/platform/x86/intel_pmt_class.c index c8939fba4509..ee2b3bbeb83d 100644 --- a/drivers/platform/x86/intel_pmt_class.c +++ b/drivers/platform/x86/intel_pmt_class.c @@ -173,7 +173,7 @@ static int intel_pmt_dev_register(struct intel_pmt_entry *entry, struct intel_pmt_namespace *ns, struct device *parent) { - struct resource res; + struct resource res = {0}; struct device *dev; int ret; diff --git a/drivers/platform/x86/intel_pmt_crashlog.c b/drivers/platform/x86/intel_pmt_crashlog.c index 97dd749c8290..92d315a16cfd 100644 --- a/drivers/platform/x86/intel_pmt_crashlog.c +++ b/drivers/platform/x86/intel_pmt_crashlog.c @@ -23,18 +23,17 @@ #define CRASH_TYPE_OOBMSM 1 /* Control Flags */ -#define CRASHLOG_FLAG_DISABLE BIT(27) +#define CRASHLOG_FLAG_DISABLE BIT(28) /* - * Bits 28 and 29 control the state of bit 31. + * Bits 29 and 30 control the state of bit 31. * - * Bit 28 will clear bit 31, if set, allowing a new crashlog to be captured. - * Bit 29 will immediately trigger a crashlog to be generated, setting bit 31. - * Bit 30 is read-only and reserved as 0. + * Bit 29 will clear bit 31, if set, allowing a new crashlog to be captured. + * Bit 30 will immediately trigger a crashlog to be generated, setting bit 31. * Bit 31 is the read-only status with a 1 indicating log is complete. */ -#define CRASHLOG_FLAG_TRIGGER_CLEAR BIT(28) -#define CRASHLOG_FLAG_TRIGGER_EXECUTE BIT(29) +#define CRASHLOG_FLAG_TRIGGER_CLEAR BIT(29) +#define CRASHLOG_FLAG_TRIGGER_EXECUTE BIT(30) #define CRASHLOG_FLAG_TRIGGER_COMPLETE BIT(31) #define CRASHLOG_FLAG_TRIGGER_MASK GENMASK(31, 28) diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index b881044b31b0..0d9e2ddbf904 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -4081,13 +4081,19 @@ static bool hotkey_notify_6xxx(const u32 hkey, case TP_HKEY_EV_KEY_NUMLOCK: case TP_HKEY_EV_KEY_FN: - case TP_HKEY_EV_KEY_FN_ESC: /* key press events, we just ignore them as long as the EC * is still reporting them in the normal keyboard stream */ *send_acpi_ev = false; *ignore_acpi_ev = true; return true; + case TP_HKEY_EV_KEY_FN_ESC: + /* Get the media key status to foce the status LED to update */ + acpi_evalf(hkey_handle, NULL, "GMKS", "v"); + *send_acpi_ev = false; + *ignore_acpi_ev = true; + return true; + case TP_HKEY_EV_TABLET_CHANGED: tpacpi_input_send_tabletsw(); hotkey_tablet_mode_notify_change(); @@ -9845,6 +9851,11 @@ static struct ibm_struct lcdshadow_driver_data = { * Thinkpad sensor interfaces */ +#define DYTC_CMD_QUERY 0 /* To get DYTC status - enable/revision */ +#define DYTC_QUERY_ENABLE_BIT 8 /* Bit 8 - 0 = disabled, 1 = enabled */ +#define DYTC_QUERY_SUBREV_BIT 16 /* Bits 16 - 27 - sub revision */ +#define DYTC_QUERY_REV_BIT 28 /* Bits 28 - 31 - revision */ + #define DYTC_CMD_GET 2 /* To get current IC function and mode */ #define DYTC_GET_LAPMODE_BIT 17 /* Set when in lapmode */ @@ -9855,6 +9866,7 @@ static bool has_palmsensor; static bool has_lapsensor; static bool palm_state; static bool lap_state; +static int dytc_version; static int dytc_command(int command, int *output) { @@ -9869,6 +9881,33 @@ static int dytc_command(int command, int *output) return 0; } +static int dytc_get_version(void) +{ + int err, output; + + /* Check if we've been called before - and just return cached value */ + if (dytc_version) + return dytc_version; + + /* Otherwise query DYTC and extract version information */ + err = dytc_command(DYTC_CMD_QUERY, &output); + /* + * If support isn't available (ENODEV) then don't return an error + * and don't create the sysfs group + */ + if (err == -ENODEV) + return 0; + /* For all other errors we can flag the failure */ + if (err) + return err; + + /* Check DYTC is enabled and supports mode setting */ + if (output & BIT(DYTC_QUERY_ENABLE_BIT)) + dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF; + + return 0; +} + static int lapsensor_get(bool *present, bool *state) { int output, err; @@ -9974,7 +10013,18 @@ static int tpacpi_proxsensor_init(struct ibm_init_struct *iibm) if (err) return err; } - if (has_lapsensor) { + + /* Check if we know the DYTC version, if we don't then get it */ + if (!dytc_version) { + err = dytc_get_version(); + if (err) + return err; + } + /* + * Platforms before DYTC version 5 claim to have a lap sensor, but it doesn't work, so we + * ignore them + */ + if (has_lapsensor && (dytc_version >= 5)) { err = sysfs_create_file(&tpacpi_pdev->dev.kobj, &dev_attr_dytc_lapmode.attr); if (err) return err; @@ -9999,14 +10049,9 @@ static struct ibm_struct proxsensor_driver_data = { * DYTC Platform Profile interface */ -#define DYTC_CMD_QUERY 0 /* To get DYTC status - enable/revision */ #define DYTC_CMD_SET 1 /* To enable/disable IC function mode */ #define DYTC_CMD_RESET 0x1ff /* To reset back to default */ -#define DYTC_QUERY_ENABLE_BIT 8 /* Bit 8 - 0 = disabled, 1 = enabled */ -#define DYTC_QUERY_SUBREV_BIT 16 /* Bits 16 - 27 - sub revision */ -#define DYTC_QUERY_REV_BIT 28 /* Bits 28 - 31 - revision */ - #define DYTC_GET_FUNCTION_BIT 8 /* Bits 8-11 - function setting */ #define DYTC_GET_MODE_BIT 12 /* Bits 12-15 - mode setting */ @@ -10142,8 +10187,13 @@ static int dytc_profile_set(struct platform_profile_handler *pprof, return err; if (profile == PLATFORM_PROFILE_BALANCED) { - /* To get back to balanced mode we just issue a reset command */ - err = dytc_command(DYTC_CMD_RESET, &output); + /* + * To get back to balanced mode we need to issue a reset command. + * Note we still need to disable CQL mode before hand and re-enable + * it afterwards, otherwise dytc_lapmode gets reset to 0 and stays + * stuck at 0 for aprox. 30 minutes. + */ + err = dytc_cql_command(DYTC_CMD_RESET, &output); if (err) goto unlock; } else { @@ -10211,28 +10261,28 @@ static int tpacpi_dytc_profile_init(struct ibm_init_struct *iibm) if (err) return err; + /* Check if we know the DYTC version, if we don't then get it */ + if (!dytc_version) { + err = dytc_get_version(); + if (err) + return err; + } /* Check DYTC is enabled and supports mode setting */ - if (output & BIT(DYTC_QUERY_ENABLE_BIT)) { - /* Only DYTC v5.0 and later has this feature. */ - int dytc_version; - - dytc_version = (output >> DYTC_QUERY_REV_BIT) & 0xF; - if (dytc_version >= 5) { - dbg_printk(TPACPI_DBG_INIT, - "DYTC version %d: thermal mode available\n", dytc_version); - /* Create platform_profile structure and register */ - err = platform_profile_register(&dytc_profile); - /* - * If for some reason platform_profiles aren't enabled - * don't quit terminally. - */ - if (err) - return 0; + if (dytc_version >= 5) { + dbg_printk(TPACPI_DBG_INIT, + "DYTC version %d: thermal mode available\n", dytc_version); + /* Create platform_profile structure and register */ + err = platform_profile_register(&dytc_profile); + /* + * If for some reason platform_profiles aren't enabled + * don't quit terminally. + */ + if (err) + return 0; - dytc_profile_available = true; - /* Ensure initial values are correct */ - dytc_profile_refresh(); - } + dytc_profile_available = true; + /* Ensure initial values are correct */ + dytc_profile_refresh(); } return 0; } diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index beb5f74944cd..08f4cf0ad9e3 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -189,15 +189,16 @@ int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) tmr_add = ptp_qoriq->tmr_add; adj = tmr_add; - /* calculate diff as adj*(scaled_ppm/65536)/1000000 - * and round() to the nearest integer + /* + * Calculate diff and round() to the nearest integer + * + * diff = adj * (ppb / 1000000000) + * = adj * scaled_ppm / 65536000000 */ - adj *= scaled_ppm; - diff = div_u64(adj, 8000000); - diff = (diff >> 13) + ((diff >> 12) & 1); + diff = mul_u64_u64_div_u64(adj, scaled_ppm, 32768000000); + diff = DIV64_U64_ROUND_UP(diff, 2); tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff; - ptp_qoriq->write(®s->ctrl_regs->tmr_add, tmr_add); return 0; diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c index ddecf25b5dd4..d7894f178bd4 100644 --- a/drivers/ras/cec.c +++ b/drivers/ras/cec.c @@ -309,11 +309,20 @@ static bool sanity_check(struct ce_array *ca) return ret; } +/** + * cec_add_elem - Add an element to the CEC array. + * @pfn: page frame number to insert + * + * Return values: + * - <0: on error + * - 0: on success + * - >0: when the inserted pfn was offlined + */ static int cec_add_elem(u64 pfn) { struct ce_array *ca = &ce_arr; + int count, err, ret = 0; unsigned int to = 0; - int count, ret = 0; /* * We can be called very early on the identify_cpu() path where we are @@ -330,8 +339,8 @@ static int cec_add_elem(u64 pfn) if (ca->n == MAX_ELEMS) WARN_ON(!del_lru_elem_unlocked(ca)); - ret = find_elem(ca, pfn, &to); - if (ret < 0) { + err = find_elem(ca, pfn, &to); + if (err < 0) { /* * Shift range [to-end] to make room for one more element. */ diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c index 7b0cd08db446..ba020a45f238 100644 --- a/drivers/regulator/bd9571mwv-regulator.c +++ b/drivers/regulator/bd9571mwv-regulator.c @@ -125,7 +125,7 @@ static const struct regulator_ops vid_ops = { static const struct regulator_desc regulators[] = { BD9571MWV_REG("VD09", "vd09", VD09, avs_ops, 0, 0x7f, - 0x80, 600000, 10000, 0x3c), + 0x6f, 600000, 10000, 0x3c), BD9571MWV_REG("VD18", "vd18", VD18, vid_ops, BD9571MWV_VD18_VID, 0xf, 16, 1625000, 25000, 0), BD9571MWV_REG("VD25", "vd25", VD25, vid_ops, BD9571MWV_VD25_VID, 0xf, @@ -134,7 +134,7 @@ static const struct regulator_desc regulators[] = { 11, 2800000, 100000, 0), BD9571MWV_REG("DVFS", "dvfs", DVFS, reg_ops, BD9571MWV_DVFS_MONIVDAC, 0x7f, - 0x80, 600000, 10000, 0x3c), + 0x6f, 600000, 10000, 0x3c), }; #ifdef CONFIG_PM_SLEEP @@ -174,7 +174,7 @@ static ssize_t backup_mode_show(struct device *dev, { struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev); - return sprintf(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off"); + return sysfs_emit(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off"); } static ssize_t backup_mode_store(struct device *dev, @@ -301,7 +301,7 @@ static int bd9571mwv_regulator_probe(struct platform_device *pdev) &config); if (IS_ERR(rdev)) { dev_err(&pdev->dev, "failed to register %s regulator\n", - pdev->name); + regulators[i].name); return PTR_ERR(rdev); } } diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c index 2667919d76b3..dcb380e868df 100644 --- a/drivers/remoteproc/pru_rproc.c +++ b/drivers/remoteproc/pru_rproc.c @@ -450,6 +450,24 @@ static void *pru_i_da_to_va(struct pru_rproc *pru, u32 da, size_t len) if (len == 0) return NULL; + /* + * GNU binutils do not support multiple address spaces. The GNU + * linker's default linker script places IRAM at an arbitrary high + * offset, in order to differentiate it from DRAM. Hence we need to + * strip the artificial offset in the IRAM addresses coming from the + * ELF file. + * + * The TI proprietary linker would never set those higher IRAM address + * bits anyway. PRU architecture limits the program counter to 16-bit + * word-address range. This in turn corresponds to 18-bit IRAM + * byte-address range for ELF. + * + * Two more bits are added just in case to make the final 20-bit mask. + * Idea is to have a safeguard in case TI decides to add banking + * in future SoCs. + */ + da &= 0xfffff; + if (da >= PRU_IRAM_DA && da + len <= PRU_IRAM_DA + pru->mem_regions[PRU_IOMEM_IRAM].size) { offset = da - PRU_IRAM_DA; @@ -585,7 +603,7 @@ pru_rproc_load_elf_segments(struct rproc *rproc, const struct firmware *fw) break; } - if (pru->data->is_k3 && is_iram) { + if (pru->data->is_k3) { ret = pru_rproc_memcpy(ptr, elf_data + phdr->p_offset, filesz); if (ret) { diff --git a/drivers/remoteproc/qcom_pil_info.c b/drivers/remoteproc/qcom_pil_info.c index 5521c4437ffa..7c007dd7b200 100644 --- a/drivers/remoteproc/qcom_pil_info.c +++ b/drivers/remoteproc/qcom_pil_info.c @@ -56,7 +56,7 @@ static int qcom_pil_info_init(void) memset_io(base, 0, resource_size(&imem)); _reloc.base = base; - _reloc.num_entries = resource_size(&imem) / PIL_RELOC_ENTRY_SIZE; + _reloc.num_entries = (u32)resource_size(&imem) / PIL_RELOC_ENTRY_SIZE; return 0; } diff --git a/drivers/scsi/hpsa_cmd.h b/drivers/scsi/hpsa_cmd.h index d126bb877250..ba6a3aa8d954 100644 --- a/drivers/scsi/hpsa_cmd.h +++ b/drivers/scsi/hpsa_cmd.h @@ -20,6 +20,11 @@ #ifndef HPSA_CMD_H #define HPSA_CMD_H +#include <linux/compiler.h> + +#include <linux/build_bug.h> /* static_assert */ +#include <linux/stddef.h> /* offsetof */ + /* general boundary defintions */ #define SENSEINFOBYTES 32 /* may vary between hbas */ #define SG_ENTRIES_IN_CMD 32 /* Max SG entries excluding chain blocks */ @@ -200,12 +205,10 @@ union u64bit { MAX_EXT_TARGETS + 1) /* + 1 is for the controller itself */ /* SCSI-3 Commands */ -#pragma pack(1) - #define HPSA_INQUIRY 0x12 struct InquiryData { u8 data_byte[36]; -}; +} __packed; #define HPSA_REPORT_LOG 0xc2 /* Report Logical LUNs */ #define HPSA_REPORT_PHYS 0xc3 /* Report Physical LUNs */ @@ -221,7 +224,7 @@ struct raid_map_disk_data { u8 xor_mult[2]; /**< XOR multipliers for this position, * valid for data disks only */ u8 reserved[2]; -}; +} __packed; struct raid_map_data { __le32 structure_size; /* Size of entire structure in bytes */ @@ -247,14 +250,14 @@ struct raid_map_data { __le16 dekindex; /* Data encryption key index. */ u8 reserved[16]; struct raid_map_disk_data data[RAID_MAP_MAX_ENTRIES]; -}; +} __packed; struct ReportLUNdata { u8 LUNListLength[4]; u8 extended_response_flag; u8 reserved[3]; u8 LUN[HPSA_MAX_LUN][8]; -}; +} __packed; struct ext_report_lun_entry { u8 lunid[8]; @@ -269,20 +272,20 @@ struct ext_report_lun_entry { u8 lun_count; /* multi-lun device, how many luns */ u8 redundant_paths; u32 ioaccel_handle; /* ioaccel1 only uses lower 16 bits */ -}; +} __packed; struct ReportExtendedLUNdata { u8 LUNListLength[4]; u8 extended_response_flag; u8 reserved[3]; struct ext_report_lun_entry LUN[HPSA_MAX_PHYS_LUN]; -}; +} __packed; struct SenseSubsystem_info { u8 reserved[36]; u8 portname[8]; u8 reserved1[1108]; -}; +} __packed; /* BMIC commands */ #define BMIC_READ 0x26 @@ -317,7 +320,7 @@ union SCSI3Addr { u8 Targ:6; u8 Mode:2; /* b10 */ } LogUnit; -}; +} __packed; struct PhysDevAddr { u32 TargetId:24; @@ -325,20 +328,20 @@ struct PhysDevAddr { u32 Mode:2; /* 2 level target device addr */ union SCSI3Addr Target[2]; -}; +} __packed; struct LogDevAddr { u32 VolId:30; u32 Mode:2; u8 reserved[4]; -}; +} __packed; union LUNAddr { u8 LunAddrBytes[8]; union SCSI3Addr SCSI3Lun[4]; struct PhysDevAddr PhysDev; struct LogDevAddr LogDev; -}; +} __packed; struct CommandListHeader { u8 ReplyQueue; @@ -346,7 +349,7 @@ struct CommandListHeader { __le16 SGTotal; __le64 tag; union LUNAddr LUN; -}; +} __packed; struct RequestBlock { u8 CDBLen; @@ -365,18 +368,18 @@ struct RequestBlock { #define GET_DIR(tad) (((tad) >> 6) & 0x03) u16 Timeout; u8 CDB[16]; -}; +} __packed; struct ErrDescriptor { __le64 Addr; __le32 Len; -}; +} __packed; struct SGDescriptor { __le64 Addr; __le32 Len; __le32 Ext; -}; +} __packed; union MoreErrInfo { struct { @@ -390,7 +393,8 @@ union MoreErrInfo { u8 offense_num; /* byte # of offense 0-base */ u32 offense_value; } Invalid_Cmd; -}; +} __packed; + struct ErrorInfo { u8 ScsiStatus; u8 SenseLen; @@ -398,7 +402,7 @@ struct ErrorInfo { u32 ResidualCnt; union MoreErrInfo MoreErrInfo; u8 SenseInfo[SENSEINFOBYTES]; -}; +} __packed; /* Command types */ #define CMD_IOCTL_PEND 0x01 #define CMD_SCSI 0x03 @@ -453,6 +457,15 @@ struct CommandList { atomic_t refcount; /* Must be last to avoid memset in hpsa_cmd_init() */ } __aligned(COMMANDLIST_ALIGNMENT); +/* + * Make sure our embedded atomic variable is aligned. Otherwise we break atomic + * operations on architectures that don't support unaligned atomics like IA64. + * + * The assert guards against reintroductin against unwanted __packed to + * the struct CommandList. + */ +static_assert(offsetof(struct CommandList, refcount) % __alignof__(atomic_t) == 0); + /* Max S/G elements in I/O accelerator command */ #define IOACCEL1_MAXSGENTRIES 24 #define IOACCEL2_MAXSGENTRIES 28 @@ -489,7 +502,7 @@ struct io_accel1_cmd { __le64 host_addr; /* 0x70 - 0x77 */ u8 CISS_LUN[8]; /* 0x78 - 0x7F */ struct SGDescriptor SG[IOACCEL1_MAXSGENTRIES]; -} __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT); +} __packed __aligned(IOACCEL1_COMMANDLIST_ALIGNMENT); #define IOACCEL1_FUNCTION_SCSIIO 0x00 #define IOACCEL1_SGLOFFSET 32 @@ -519,7 +532,7 @@ struct ioaccel2_sg_element { u8 chain_indicator; #define IOACCEL2_CHAIN 0x80 #define IOACCEL2_LAST_SG 0x40 -}; +} __packed; /* * SCSI Response Format structure for IO Accelerator Mode 2 @@ -559,7 +572,7 @@ struct io_accel2_scsi_response { u8 sense_data_len; /* sense/response data length */ u8 resid_cnt[4]; /* residual count */ u8 sense_data_buff[32]; /* sense/response data buffer */ -}; +} __packed; /* * Structure for I/O accelerator (mode 2 or m2) commands. @@ -592,7 +605,7 @@ struct io_accel2_cmd { __le32 tweak_upper; /* Encryption tweak, upper 4 bytes */ struct ioaccel2_sg_element sg[IOACCEL2_MAXSGENTRIES]; struct io_accel2_scsi_response error_data; -} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT); +} __packed __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT); /* * defines for Mode 2 command struct @@ -618,7 +631,7 @@ struct hpsa_tmf_struct { __le64 abort_tag; /* cciss tag of SCSI cmd or TMF to abort */ __le64 error_ptr; /* Error Pointer */ __le32 error_len; /* Error Length */ -} __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT); +} __packed __aligned(IOACCEL2_COMMANDLIST_ALIGNMENT); /* Configuration Table Structure */ struct HostWrite { @@ -626,7 +639,7 @@ struct HostWrite { __le32 command_pool_addr_hi; __le32 CoalIntDelay; __le32 CoalIntCount; -}; +} __packed; #define SIMPLE_MODE 0x02 #define PERFORMANT_MODE 0x04 @@ -675,7 +688,7 @@ struct CfgTable { #define HPSA_EVENT_NOTIFY_ACCEL_IO_PATH_STATE_CHANGE (1 << 30) #define HPSA_EVENT_NOTIFY_ACCEL_IO_PATH_CONFIG_CHANGE (1 << 31) __le32 clear_event_notify; -}; +} __packed; #define NUM_BLOCKFETCH_ENTRIES 8 struct TransTable_struct { @@ -686,14 +699,14 @@ struct TransTable_struct { __le32 RepQCtrAddrHigh32; #define MAX_REPLY_QUEUES 64 struct vals32 RepQAddr[MAX_REPLY_QUEUES]; -}; +} __packed; struct hpsa_pci_info { unsigned char bus; unsigned char dev_fn; unsigned short domain; u32 board_id; -}; +} __packed; struct bmic_identify_controller { u8 configured_logical_drive_count; /* offset 0 */ @@ -702,7 +715,7 @@ struct bmic_identify_controller { u8 pad2[136]; u8 controller_mode; /* offset 292 */ u8 pad3[32]; -}; +} __packed; struct bmic_identify_physical_device { @@ -845,7 +858,7 @@ struct bmic_identify_physical_device { u8 max_link_rate[256]; u8 neg_phys_link_rate[256]; u8 box_conn_name[8]; -} __attribute((aligned(512))); +} __packed __attribute((aligned(512))); struct bmic_sense_subsystem_info { u8 primary_slot_number; @@ -858,7 +871,7 @@ struct bmic_sense_subsystem_info { u8 secondary_array_serial_number[32]; u8 secondary_cache_serial_number[32]; u8 pad[332]; -}; +} __packed; struct bmic_sense_storage_box_params { u8 reserved[36]; @@ -870,7 +883,6 @@ struct bmic_sense_storage_box_params { u8 reserver_3[84]; u8 phys_connector[2]; u8 reserved_4[296]; -}; +} __packed; -#pragma pack() #endif /* HPSA_CMD_H */ diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c index f140eafc0d6a..61831f2fdb30 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.c +++ b/drivers/scsi/ibmvscsi/ibmvfc.c @@ -2372,6 +2372,24 @@ static int ibmvfc_match_lun(struct ibmvfc_event *evt, void *device) } /** + * ibmvfc_event_is_free - Check if event is free or not + * @evt: ibmvfc event struct + * + * Returns: + * true / false + **/ +static bool ibmvfc_event_is_free(struct ibmvfc_event *evt) +{ + struct ibmvfc_event *loop_evt; + + list_for_each_entry(loop_evt, &evt->queue->free, queue_list) + if (loop_evt == evt) + return true; + + return false; +} + +/** * ibmvfc_wait_for_ops - Wait for ops to complete * @vhost: ibmvfc host struct * @device: device to match (starget or sdev) @@ -2385,35 +2403,58 @@ static int ibmvfc_wait_for_ops(struct ibmvfc_host *vhost, void *device, { struct ibmvfc_event *evt; DECLARE_COMPLETION_ONSTACK(comp); - int wait; + int wait, i, q_index, q_size; unsigned long flags; signed long timeout = IBMVFC_ABORT_WAIT_TIMEOUT * HZ; + struct ibmvfc_queue *queues; ENTER; + if (vhost->mq_enabled && vhost->using_channels) { + queues = vhost->scsi_scrqs.scrqs; + q_size = vhost->scsi_scrqs.active_queues; + } else { + queues = &vhost->crq; + q_size = 1; + } + do { wait = 0; - spin_lock_irqsave(&vhost->crq.l_lock, flags); - list_for_each_entry(evt, &vhost->crq.sent, queue_list) { - if (match(evt, device)) { - evt->eh_comp = ∁ - wait++; + spin_lock_irqsave(vhost->host->host_lock, flags); + for (q_index = 0; q_index < q_size; q_index++) { + spin_lock(&queues[q_index].l_lock); + for (i = 0; i < queues[q_index].evt_pool.size; i++) { + evt = &queues[q_index].evt_pool.events[i]; + if (!ibmvfc_event_is_free(evt)) { + if (match(evt, device)) { + evt->eh_comp = ∁ + wait++; + } + } } + spin_unlock(&queues[q_index].l_lock); } - spin_unlock_irqrestore(&vhost->crq.l_lock, flags); + spin_unlock_irqrestore(vhost->host->host_lock, flags); if (wait) { timeout = wait_for_completion_timeout(&comp, timeout); if (!timeout) { wait = 0; - spin_lock_irqsave(&vhost->crq.l_lock, flags); - list_for_each_entry(evt, &vhost->crq.sent, queue_list) { - if (match(evt, device)) { - evt->eh_comp = NULL; - wait++; + spin_lock_irqsave(vhost->host->host_lock, flags); + for (q_index = 0; q_index < q_size; q_index++) { + spin_lock(&queues[q_index].l_lock); + for (i = 0; i < queues[q_index].evt_pool.size; i++) { + evt = &queues[q_index].evt_pool.events[i]; + if (!ibmvfc_event_is_free(evt)) { + if (match(evt, device)) { + evt->eh_comp = NULL; + wait++; + } + } } + spin_unlock(&queues[q_index].l_lock); } - spin_unlock_irqrestore(&vhost->crq.l_lock, flags); + spin_unlock_irqrestore(vhost->host->host_lock, flags); if (wait) dev_err(vhost->dev, "Timed out waiting for aborted commands\n"); LEAVE; diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 04633e5157e9..4834219497ee 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -3179,9 +3179,10 @@ fail_mgmt_tasks(struct iscsi_session *session, struct iscsi_conn *conn) } } -static void iscsi_start_session_recovery(struct iscsi_session *session, - struct iscsi_conn *conn, int flag) +void iscsi_conn_stop(struct iscsi_cls_conn *cls_conn, int flag) { + struct iscsi_conn *conn = cls_conn->dd_data; + struct iscsi_session *session = conn->session; int old_stop_stage; mutex_lock(&session->eh_mutex); @@ -3239,27 +3240,6 @@ static void iscsi_start_session_recovery(struct iscsi_session *session, spin_unlock_bh(&session->frwd_lock); mutex_unlock(&session->eh_mutex); } - -void iscsi_conn_stop(struct iscsi_cls_conn *cls_conn, int flag) -{ - struct iscsi_conn *conn = cls_conn->dd_data; - struct iscsi_session *session = conn->session; - - switch (flag) { - case STOP_CONN_RECOVER: - cls_conn->state = ISCSI_CONN_FAILED; - break; - case STOP_CONN_TERM: - cls_conn->state = ISCSI_CONN_DOWN; - break; - default: - iscsi_conn_printk(KERN_ERR, conn, - "invalid stop flag %d\n", flag); - return; - } - - iscsi_start_session_recovery(session, conn, flag); -} EXPORT_SYMBOL_GPL(iscsi_conn_stop); int iscsi_conn_bind(struct iscsi_cls_session *cls_session, diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 024e5a550759..8b9a39077dba 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -201,18 +201,17 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc) memcpy(task->ata_task.atapi_packet, qc->cdb, qc->dev->cdb_len); task->total_xfer_len = qc->nbytes; task->num_scatter = qc->n_elem; + task->data_dir = qc->dma_dir; + } else if (qc->tf.protocol == ATA_PROT_NODATA) { + task->data_dir = DMA_NONE; } else { for_each_sg(qc->sg, sg, qc->n_elem, si) xfer += sg_dma_len(sg); task->total_xfer_len = xfer; task->num_scatter = si; - } - - if (qc->tf.protocol == ATA_PROT_NODATA) - task->data_dir = DMA_NONE; - else task->data_dir = qc->dma_dir; + } task->scatter = qc->sg; task->ata_task.retry_count = 1; task->task_state_flags = SAS_TASK_STATE_PENDING; diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index ac066f86bb14..ac0eef975f17 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7806,14 +7806,18 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pend_os_device_add_sz++; ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz, GFP_KERNEL); - if (!ioc->pend_os_device_add) + if (!ioc->pend_os_device_add) { + r = -ENOMEM; goto out_free_resources; + } ioc->device_remove_in_progress_sz = ioc->pend_os_device_add_sz; ioc->device_remove_in_progress = kzalloc(ioc->device_remove_in_progress_sz, GFP_KERNEL); - if (!ioc->device_remove_in_progress) + if (!ioc->device_remove_in_progress) { + r = -ENOMEM; goto out_free_resources; + } ioc->fwfault_debug = mpt3sas_fwfault_debug; diff --git a/drivers/scsi/pm8001/pm8001_hwi.c b/drivers/scsi/pm8001/pm8001_hwi.c index 49bf2f70a470..31e5455d280c 100644 --- a/drivers/scsi/pm8001/pm8001_hwi.c +++ b/drivers/scsi/pm8001/pm8001_hwi.c @@ -223,7 +223,7 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha) PM8001_EVENT_LOG_SIZE; pm8001_ha->main_cfg_tbl.pm8001_tbl.iop_event_log_option = 0x01; pm8001_ha->main_cfg_tbl.pm8001_tbl.fatal_err_interrupt = 0x01; - for (i = 0; i < PM8001_MAX_INB_NUM; i++) { + for (i = 0; i < pm8001_ha->max_q_num; i++) { pm8001_ha->inbnd_q_tbl[i].element_pri_size_cnt = PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x00<<30); pm8001_ha->inbnd_q_tbl[i].upper_base_addr = @@ -249,7 +249,7 @@ static void init_default_table_values(struct pm8001_hba_info *pm8001_ha) pm8001_ha->inbnd_q_tbl[i].producer_idx = 0; pm8001_ha->inbnd_q_tbl[i].consumer_index = 0; } - for (i = 0; i < PM8001_MAX_OUTB_NUM; i++) { + for (i = 0; i < pm8001_ha->max_q_num; i++) { pm8001_ha->outbnd_q_tbl[i].element_size_cnt = PM8001_MPI_QUEUE | (pm8001_ha->iomb_size << 16) | (0x01<<30); pm8001_ha->outbnd_q_tbl[i].upper_base_addr = @@ -671,9 +671,9 @@ static int pm8001_chip_init(struct pm8001_hba_info *pm8001_ha) read_outbnd_queue_table(pm8001_ha); /* update main config table ,inbound table and outbound table */ update_main_config_table(pm8001_ha); - for (i = 0; i < PM8001_MAX_INB_NUM; i++) + for (i = 0; i < pm8001_ha->max_q_num; i++) update_inbnd_queue_table(pm8001_ha, i); - for (i = 0; i < PM8001_MAX_OUTB_NUM; i++) + for (i = 0; i < pm8001_ha->max_q_num; i++) update_outbnd_queue_table(pm8001_ha, i); /* 8081 controller donot require these operations */ if (deviceid != 0x8081 && deviceid != 0x0042) { diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 47ad64b06623..69c5b5ee2169 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1675,6 +1675,7 @@ static int qedi_alloc_global_queues(struct qedi_ctx *qedi) if (!qedi->global_queues[i]) { QEDI_ERR(&qedi->dbg_ctx, "Unable to allocation global queue %d.\n", i); + status = -ENOMEM; goto mem_alloc_failure; } diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c index c48daf52725d..480e7d2dcf3e 100644 --- a/drivers/scsi/qla2xxx/qla_target.c +++ b/drivers/scsi/qla2xxx/qla_target.c @@ -3222,8 +3222,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, if (!qpair->fw_started || (cmd->reset_count != qpair->chip_reset) || (cmd->sess && cmd->sess->deleted)) { cmd->state = QLA_TGT_STATE_PROCESSED; - res = 0; - goto free; + return 0; } ql_dbg_qp(ql_dbg_tgt, qpair, 0xe018, @@ -3234,8 +3233,9 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status, &full_req_cnt); - if (unlikely(res != 0)) - goto free; + if (unlikely(res != 0)) { + return res; + } spin_lock_irqsave(qpair->qp_lock_ptr, flags); @@ -3255,8 +3255,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type, vha->flags.online, qla2x00_reset_active(vha), cmd->reset_count, qpair->chip_reset); spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); - res = 0; - goto free; + return 0; } /* Does F/W have an IOCBs for this request */ @@ -3359,8 +3358,6 @@ out_unmap_unlock: qlt_unmap_sg(vha, cmd); spin_unlock_irqrestore(qpair->qp_lock_ptr, flags); -free: - vha->hw->tgt.tgt_ops->free_cmd(cmd); return res; } EXPORT_SYMBOL(qlt_xmit_response); diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c index b55fc768a2a7..8b4890cdd4ca 100644 --- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c +++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c @@ -644,7 +644,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - struct scsi_qla_host *vha = cmd->vha; if (cmd->aborted) { /* Cmd can loop during Q-full. tcm_qla2xxx_aborted_task @@ -657,7 +656,6 @@ static int tcm_qla2xxx_queue_data_in(struct se_cmd *se_cmd) cmd->se_cmd.transport_state, cmd->se_cmd.t_state, cmd->se_cmd.se_cmd_flags); - vha->hw->tgt.tgt_ops->free_cmd(cmd); return 0; } @@ -685,7 +683,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd) { struct qla_tgt_cmd *cmd = container_of(se_cmd, struct qla_tgt_cmd, se_cmd); - struct scsi_qla_host *vha = cmd->vha; int xmit_type = QLA_TGT_XMIT_STATUS; if (cmd->aborted) { @@ -699,7 +696,6 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd) cmd, kref_read(&cmd->se_cmd.cmd_kref), cmd->se_cmd.transport_state, cmd->se_cmd.t_state, cmd->se_cmd.se_cmd_flags); - vha->hw->tgt.tgt_ops->free_cmd(cmd); return 0; } cmd->bufflen = se_cmd->data_length; diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 91074fd97f64..441f0152193f 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2474,9 +2474,22 @@ static void iscsi_if_stop_conn(struct iscsi_cls_conn *conn, int flag) * it works. */ mutex_lock(&conn_mutex); + switch (flag) { + case STOP_CONN_RECOVER: + conn->state = ISCSI_CONN_FAILED; + break; + case STOP_CONN_TERM: + conn->state = ISCSI_CONN_DOWN; + break; + default: + iscsi_cls_conn_printk(KERN_ERR, conn, + "invalid stop flag %d\n", flag); + goto unlock; + } + conn->transport->stop_conn(conn, flag); +unlock: mutex_unlock(&conn_mutex); - } static void stop_conn_work_fn(struct work_struct *work) @@ -2901,6 +2914,13 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev) default: err = transport->set_param(conn, ev->u.set_param.param, data, ev->u.set_param.len); + if ((conn->state == ISCSI_CONN_BOUND) || + (conn->state == ISCSI_CONN_UP)) { + err = transport->set_param(conn, ev->u.set_param.param, + data, ev->u.set_param.len); + } else { + return -ENOTCONN; + } } return err; @@ -2960,6 +2980,7 @@ static int iscsi_if_ep_disconnect(struct iscsi_transport *transport, mutex_lock(&conn->ep_mutex); conn->ep = NULL; mutex_unlock(&conn->ep_mutex); + conn->state = ISCSI_CONN_FAILED; } transport->ep_disconnect(ep); @@ -3727,6 +3748,8 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) ev->r.retcode = transport->bind_conn(session, conn, ev->u.b_conn.transport_eph, ev->u.b_conn.is_leading); + if (!ev->r.retcode) + conn->state = ISCSI_CONN_BOUND; mutex_unlock(&conn_mutex); if (ev->r.retcode || !transport->ep_connect) @@ -3966,7 +3989,8 @@ iscsi_conn_attr(local_ipaddr, ISCSI_PARAM_LOCAL_IPADDR); static const char *const connection_state_names[] = { [ISCSI_CONN_UP] = "up", [ISCSI_CONN_DOWN] = "down", - [ISCSI_CONN_FAILED] = "failed" + [ISCSI_CONN_FAILED] = "failed", + [ISCSI_CONN_BOUND] = "bound" }; static ssize_t show_conn_state(struct device *dev, diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c index 1e939a2a387f..98a34ed10f1a 100644 --- a/drivers/scsi/scsi_transport_srp.c +++ b/drivers/scsi/scsi_transport_srp.c @@ -541,7 +541,7 @@ int srp_reconnect_rport(struct srp_rport *rport) res = mutex_lock_interruptible(&rport->mutex); if (res) goto out; - if (rport->state != SRP_RPORT_FAIL_FAST) + if (rport->state != SRP_RPORT_FAIL_FAST && rport->state != SRP_RPORT_LOST) /* * sdev state must be SDEV_TRANSPORT_OFFLINE, transition * to SDEV_BLOCK is illegal. Calling scsi_target_unblock() diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index c86760788c72..d3d05e997c13 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -6386,37 +6386,34 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, DECLARE_COMPLETION_ONSTACK(wait); struct request *req; unsigned long flags; - int free_slot, task_tag, err; + int task_tag, err; /* - * Get free slot, sleep if slots are unavailable. - * Even though we use wait_event() which sleeps indefinitely, - * the maximum wait time is bounded by %TM_CMD_TIMEOUT. + * blk_get_request() is used here only to get a free tag. */ req = blk_get_request(q, REQ_OP_DRV_OUT, 0); if (IS_ERR(req)) return PTR_ERR(req); req->end_io_data = &wait; - free_slot = req->tag; - WARN_ON_ONCE(free_slot < 0 || free_slot >= hba->nutmrs); ufshcd_hold(hba, false); spin_lock_irqsave(host->host_lock, flags); - task_tag = hba->nutrs + free_slot; + blk_mq_start_request(req); + task_tag = req->tag; treq->req_header.dword_0 |= cpu_to_be32(task_tag); - memcpy(hba->utmrdl_base_addr + free_slot, treq, sizeof(*treq)); - ufshcd_vops_setup_task_mgmt(hba, free_slot, tm_function); + memcpy(hba->utmrdl_base_addr + task_tag, treq, sizeof(*treq)); + ufshcd_vops_setup_task_mgmt(hba, task_tag, tm_function); /* send command to the controller */ - __set_bit(free_slot, &hba->outstanding_tasks); + __set_bit(task_tag, &hba->outstanding_tasks); /* Make sure descriptors are ready before ringing the task doorbell */ wmb(); - ufshcd_writel(hba, 1 << free_slot, REG_UTP_TASK_REQ_DOOR_BELL); + ufshcd_writel(hba, 1 << task_tag, REG_UTP_TASK_REQ_DOOR_BELL); /* Make sure that doorbell is committed immediately */ wmb(); @@ -6436,24 +6433,24 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_ERR); dev_err(hba->dev, "%s: task management cmd 0x%.2x timed-out\n", __func__, tm_function); - if (ufshcd_clear_tm_cmd(hba, free_slot)) - dev_WARN(hba->dev, "%s: unable clear tm cmd (slot %d) after timeout\n", - __func__, free_slot); + if (ufshcd_clear_tm_cmd(hba, task_tag)) + dev_WARN(hba->dev, "%s: unable to clear tm cmd (slot %d) after timeout\n", + __func__, task_tag); err = -ETIMEDOUT; } else { err = 0; - memcpy(treq, hba->utmrdl_base_addr + free_slot, sizeof(*treq)); + memcpy(treq, hba->utmrdl_base_addr + task_tag, sizeof(*treq)); ufshcd_add_tm_upiu_trace(hba, task_tag, UFS_TM_COMP); } spin_lock_irqsave(hba->host->host_lock, flags); - __clear_bit(free_slot, &hba->outstanding_tasks); + __clear_bit(task_tag, &hba->outstanding_tasks); spin_unlock_irqrestore(hba->host->host_lock, flags); + ufshcd_release(hba); blk_put_request(req); - ufshcd_release(hba); return err; } diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index a1b9be1d105a..fde4edd83c14 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -186,7 +186,7 @@ struct qm_eqcr_entry { __be32 tag; struct qm_fd fd; u8 __reserved3[32]; -} __packed; +} __packed __aligned(8); #define QM_EQCR_VERB_VBIT 0x80 #define QM_EQCR_VERB_CMD_MASK 0x61 /* but only one value; */ #define QM_EQCR_VERB_CMD_ENQUEUE 0x01 diff --git a/drivers/soc/litex/litex_soc_ctrl.c b/drivers/soc/litex/litex_soc_ctrl.c index 6268bfa7f0d6..c3e379a990f2 100644 --- a/drivers/soc/litex/litex_soc_ctrl.c +++ b/drivers/soc/litex/litex_soc_ctrl.c @@ -13,7 +13,6 @@ #include <linux/platform_device.h> #include <linux/printk.h> #include <linux/module.h> -#include <linux/errno.h> #include <linux/io.h> #include <linux/reboot.h> diff --git a/drivers/soc/qcom/qcom-geni-se.c b/drivers/soc/qcom/qcom-geni-se.c index f42954e2c98e..5bdfb1565c14 100644 --- a/drivers/soc/qcom/qcom-geni-se.c +++ b/drivers/soc/qcom/qcom-geni-se.c @@ -3,7 +3,6 @@ #include <linux/acpi.h> #include <linux/clk.h> -#include <linux/console.h> #include <linux/slab.h> #include <linux/dma-mapping.h> #include <linux/io.h> @@ -92,14 +91,11 @@ struct geni_wrapper { struct device *dev; void __iomem *base; struct clk_bulk_data ahb_clks[NUM_AHB_CLKS]; - struct geni_icc_path to_core; }; static const char * const icc_path_names[] = {"qup-core", "qup-config", "qup-memory"}; -static struct geni_wrapper *earlycon_wrapper; - #define QUP_HW_VER_REG 0x4 /* Common SE registers */ @@ -760,6 +756,9 @@ int geni_icc_get(struct geni_se *se, const char *icc_ddr) int i, err; const char *icc_names[] = {"qup-core", "qup-config", icc_ddr}; + if (has_acpi_companion(se->dev)) + return 0; + for (i = 0; i < ARRAY_SIZE(se->icc_paths); i++) { if (!icc_names[i]) continue; @@ -843,44 +842,11 @@ int geni_icc_disable(struct geni_se *se) } EXPORT_SYMBOL(geni_icc_disable); -void geni_remove_earlycon_icc_vote(void) -{ - struct platform_device *pdev; - struct geni_wrapper *wrapper; - struct device_node *parent; - struct device_node *child; - - if (!earlycon_wrapper) - return; - - wrapper = earlycon_wrapper; - parent = of_get_next_parent(wrapper->dev->of_node); - for_each_child_of_node(parent, child) { - if (!of_device_is_compatible(child, "qcom,geni-se-qup")) - continue; - - pdev = of_find_device_by_node(child); - if (!pdev) - continue; - - wrapper = platform_get_drvdata(pdev); - icc_put(wrapper->to_core.path); - wrapper->to_core.path = NULL; - - } - of_node_put(parent); - - earlycon_wrapper = NULL; -} -EXPORT_SYMBOL(geni_remove_earlycon_icc_vote); - static int geni_se_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct resource *res; struct geni_wrapper *wrapper; - struct console __maybe_unused *bcon; - bool __maybe_unused has_earlycon = false; int ret; wrapper = devm_kzalloc(dev, sizeof(*wrapper), GFP_KERNEL); @@ -903,43 +869,6 @@ static int geni_se_probe(struct platform_device *pdev) } } -#ifdef CONFIG_SERIAL_EARLYCON - for_each_console(bcon) { - if (!strcmp(bcon->name, "qcom_geni")) { - has_earlycon = true; - break; - } - } - if (!has_earlycon) - goto exit; - - wrapper->to_core.path = devm_of_icc_get(dev, "qup-core"); - if (IS_ERR(wrapper->to_core.path)) - return PTR_ERR(wrapper->to_core.path); - /* - * Put minmal BW request on core clocks on behalf of early console. - * The vote will be removed earlycon exit function. - * - * Note: We are putting vote on each QUP wrapper instead only to which - * earlycon is connected because QUP core clock of different wrapper - * share same voltage domain. If core1 is put to 0, then core2 will - * also run at 0, if not voted. Default ICC vote will be removed ASA - * we touch any of the core clock. - * core1 = core2 = max(core1, core2) - */ - ret = icc_set_bw(wrapper->to_core.path, GENI_DEFAULT_BW, - GENI_DEFAULT_BW); - if (ret) { - dev_err(&pdev->dev, "%s: ICC BW voting failed for core: %d\n", - __func__, ret); - return ret; - } - - if (of_get_compatible_child(pdev->dev.of_node, "qcom,geni-debug-uart")) - earlycon_wrapper = wrapper; - of_node_put(pdev->dev.of_node); -exit: -#endif dev_set_drvdata(dev, wrapper); dev_dbg(dev, "GENI SE Driver probed\n"); return devm_of_platform_populate(dev); diff --git a/drivers/soc/ti/omap_prm.c b/drivers/soc/ti/omap_prm.c index bf1468e5bccb..51143a68a889 100644 --- a/drivers/soc/ti/omap_prm.c +++ b/drivers/soc/ti/omap_prm.c @@ -332,7 +332,7 @@ static const struct omap_prm_data dra7_prm_data[] = { { .name = "l3init", .base = 0x4ae07300, .pwrstctrl = 0x0, .pwrstst = 0x4, .dmap = &omap_prm_alwon, - .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_012, + .rstctrl = 0x10, .rstst = 0x14, .rstmap = rst_map_01, .clkdm_name = "pcie" }, { @@ -830,8 +830,12 @@ static int omap_reset_deassert(struct reset_controller_dev *rcdev, reset->prm->data->name, id); exit: - if (reset->clkdm) + if (reset->clkdm) { + /* At least dra7 iva needs a delay before clkdm idle */ + if (has_rstst) + udelay(1); pdata->clkdm_allow_idle(reset->clkdm); + } return ret; } diff --git a/drivers/staging/rtl8192e/rtllib.h b/drivers/staging/rtl8192e/rtllib.h index b84f00b8d18b..4cabaf21c1ca 100644 --- a/drivers/staging/rtl8192e/rtllib.h +++ b/drivers/staging/rtl8192e/rtllib.h @@ -1105,7 +1105,7 @@ struct rtllib_network { bool bWithAironetIE; bool bCkipSupported; bool bCcxRmEnable; - u16 CcxRmState[2]; + u8 CcxRmState[2]; bool bMBssidValid; u8 MBssidMask; u8 MBssid[ETH_ALEN]; diff --git a/drivers/staging/rtl8192e/rtllib_rx.c b/drivers/staging/rtl8192e/rtllib_rx.c index 66c135321da4..15bbb63ca130 100644 --- a/drivers/staging/rtl8192e/rtllib_rx.c +++ b/drivers/staging/rtl8192e/rtllib_rx.c @@ -1967,7 +1967,7 @@ static void rtllib_parse_mife_generic(struct rtllib_device *ieee, info_element->data[2] == 0x96 && info_element->data[3] == 0x01) { if (info_element->len == 6) { - memcpy(network->CcxRmState, &info_element[4], 2); + memcpy(network->CcxRmState, &info_element->data[4], 2); if (network->CcxRmState[0] != 0) network->bCcxRmEnable = true; else diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index d0e7ed8f28cc..e5c443bfbdf9 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -1166,6 +1166,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, target_get_sess_cmd(&cmd->se_cmd, true); + cmd->se_cmd.tag = (__force u32)cmd->init_task_tag; cmd->sense_reason = target_cmd_init_cdb(&cmd->se_cmd, hdr->cdb); if (cmd->sense_reason) { if (cmd->sense_reason == TCM_OUT_OF_RESOURCES) { @@ -1180,8 +1181,6 @@ int iscsit_setup_scsi_cmd(struct iscsi_conn *conn, struct iscsi_cmd *cmd, if (cmd->sense_reason) goto attach_cmd; - /* only used for printks or comparing with ->ref_task_tag */ - cmd->se_cmd.tag = (__force u32)cmd->init_task_tag; cmd->sense_reason = target_cmd_parse_cdb(&cmd->se_cmd); if (cmd->sense_reason) goto attach_cmd; diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 3cbc074992bc..9ee797b8cb7e 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -882,7 +882,6 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, if (!bio) { new_bio: nr_vecs = bio_max_segs(nr_pages); - nr_pages -= nr_vecs; /* * Calls bio_kmalloc() and sets bio->bi_end_io() */ @@ -939,6 +938,14 @@ new_bio: return 0; fail: + if (bio) + bio_put(bio); + while (req->bio) { + bio = req->bio; + req->bio = bio->bi_next; + bio_put(bio); + } + req->biotail = NULL; return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE; } diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 620bcf586ee2..c44fad2b9fbb 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -347,7 +347,7 @@ static int tb_retimer_add(struct tb_port *port, u8 index, u32 auth_status) ret = tb_retimer_nvm_add(rt); if (ret) { dev_err(&rt->dev, "failed to add NVM devices: %d\n", ret); - device_del(&rt->dev); + device_unregister(&rt->dev); return ret; } @@ -406,7 +406,7 @@ static struct tb_retimer *tb_port_find_retimer(struct tb_port *port, u8 index) */ int tb_retimer_scan(struct tb_port *port) { - u32 status[TB_MAX_RETIMER_INDEX] = {}; + u32 status[TB_MAX_RETIMER_INDEX + 1] = {}; int ret, i, last_idx = 0; if (!port->cap_usb4) diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index 291649f02821..0d85b55ea823 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -1177,12 +1177,6 @@ static inline void qcom_geni_serial_enable_early_read(struct geni_se *se, struct console *con) { } #endif -static int qcom_geni_serial_earlycon_exit(struct console *con) -{ - geni_remove_earlycon_icc_vote(); - return 0; -} - static struct qcom_geni_private_data earlycon_private_data; static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev, @@ -1233,7 +1227,6 @@ static int __init qcom_geni_serial_earlycon_setup(struct earlycon_device *dev, writel(stop_bit_len, uport->membase + SE_UART_TX_STOP_BIT_LEN); dev->con->write = qcom_geni_serial_earlycon_write; - dev->con->exit = qcom_geni_serial_earlycon_exit; dev->con->setup = NULL; qcom_geni_serial_enable_early_read(&se, dev->con); diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index f2ebbacd932e..d7d4bdd57f46 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -1128,6 +1128,10 @@ static int cdnsp_gadget_ep_dequeue(struct usb_ep *ep, return -ESHUTDOWN; } + /* Requests has been dequeued during disabling endpoint. */ + if (!(pep->ep_state & EP_ENABLED)) + return 0; + spin_lock_irqsave(&pdev->lock, flags); ret = cdnsp_ep_dequeue(pep, to_cdnsp_request(request)); spin_unlock_irqrestore(&pdev->lock, flags); diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 39ddb5585ded..3fda1ec961d7 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -147,17 +147,29 @@ static inline int acm_set_control(struct acm *acm, int control) #define acm_send_break(acm, ms) \ acm_ctrl_msg(acm, USB_CDC_REQ_SEND_BREAK, ms, NULL, 0) -static void acm_kill_urbs(struct acm *acm) +static void acm_poison_urbs(struct acm *acm) { int i; - usb_kill_urb(acm->ctrlurb); + usb_poison_urb(acm->ctrlurb); for (i = 0; i < ACM_NW; i++) - usb_kill_urb(acm->wb[i].urb); + usb_poison_urb(acm->wb[i].urb); for (i = 0; i < acm->rx_buflimit; i++) - usb_kill_urb(acm->read_urbs[i]); + usb_poison_urb(acm->read_urbs[i]); +} + +static void acm_unpoison_urbs(struct acm *acm) +{ + int i; + + for (i = 0; i < acm->rx_buflimit; i++) + usb_unpoison_urb(acm->read_urbs[i]); + for (i = 0; i < ACM_NW; i++) + usb_unpoison_urb(acm->wb[i].urb); + usb_unpoison_urb(acm->ctrlurb); } + /* * Write buffer management. * All of these assume proper locks taken by the caller. @@ -226,9 +238,10 @@ static int acm_start_wb(struct acm *acm, struct acm_wb *wb) rc = usb_submit_urb(wb->urb, GFP_ATOMIC); if (rc < 0) { - dev_err(&acm->data->dev, - "%s - usb_submit_urb(write bulk) failed: %d\n", - __func__, rc); + if (rc != -EPERM) + dev_err(&acm->data->dev, + "%s - usb_submit_urb(write bulk) failed: %d\n", + __func__, rc); acm_write_done(acm, wb); } return rc; @@ -313,8 +326,10 @@ static void acm_process_notification(struct acm *acm, unsigned char *buf) acm->iocount.dsr++; if (difference & ACM_CTRL_DCD) acm->iocount.dcd++; - if (newctrl & ACM_CTRL_BRK) + if (newctrl & ACM_CTRL_BRK) { acm->iocount.brk++; + tty_insert_flip_char(&acm->port, 0, TTY_BREAK); + } if (newctrl & ACM_CTRL_RI) acm->iocount.rng++; if (newctrl & ACM_CTRL_FRAMING) @@ -480,11 +495,6 @@ static void acm_read_bulk_callback(struct urb *urb) dev_vdbg(&acm->data->dev, "got urb %d, len %d, status %d\n", rb->index, urb->actual_length, status); - if (!acm->dev) { - dev_dbg(&acm->data->dev, "%s - disconnected\n", __func__); - return; - } - switch (status) { case 0: usb_mark_last_busy(acm->dev); @@ -649,7 +659,8 @@ static void acm_port_dtr_rts(struct tty_port *port, int raise) res = acm_set_control(acm, val); if (res && (acm->ctrl_caps & USB_CDC_CAP_LINE)) - dev_err(&acm->control->dev, "failed to set dtr/rts\n"); + /* This is broken in too many devices to spam the logs */ + dev_dbg(&acm->control->dev, "failed to set dtr/rts\n"); } static int acm_port_activate(struct tty_port *port, struct tty_struct *tty) @@ -731,6 +742,7 @@ static void acm_port_shutdown(struct tty_port *port) * Need to grab write_lock to prevent race with resume, but no need to * hold it due to the tty-port initialised flag. */ + acm_poison_urbs(acm); spin_lock_irq(&acm->write_lock); spin_unlock_irq(&acm->write_lock); @@ -747,7 +759,8 @@ static void acm_port_shutdown(struct tty_port *port) usb_autopm_put_interface_async(acm->control); } - acm_kill_urbs(acm); + acm_unpoison_urbs(acm); + } static void acm_tty_cleanup(struct tty_struct *tty) @@ -1296,13 +1309,6 @@ skip_normal_probe: if (!combined_interfaces && intf != control_interface) return -ENODEV; - if (!combined_interfaces && usb_interface_claimed(data_interface)) { - /* valid in this context */ - dev_dbg(&intf->dev, "The data interface isn't available\n"); - return -EBUSY; - } - - if (data_interface->cur_altsetting->desc.bNumEndpoints < 2 || control_interface->cur_altsetting->desc.bNumEndpoints == 0) return -EINVAL; @@ -1323,8 +1329,8 @@ made_compressed_probe: dev_dbg(&intf->dev, "interfaces are valid\n"); acm = kzalloc(sizeof(struct acm), GFP_KERNEL); - if (acm == NULL) - goto alloc_fail; + if (!acm) + return -ENOMEM; tty_port_init(&acm->port); acm->port.ops = &acm_port_ops; @@ -1341,7 +1347,7 @@ made_compressed_probe: minor = acm_alloc_minor(acm); if (minor < 0) - goto alloc_fail1; + goto err_put_port; acm->minor = minor; acm->dev = usb_dev; @@ -1372,15 +1378,15 @@ made_compressed_probe: buf = usb_alloc_coherent(usb_dev, ctrlsize, GFP_KERNEL, &acm->ctrl_dma); if (!buf) - goto alloc_fail1; + goto err_put_port; acm->ctrl_buffer = buf; if (acm_write_buffers_alloc(acm) < 0) - goto alloc_fail2; + goto err_free_ctrl_buffer; acm->ctrlurb = usb_alloc_urb(0, GFP_KERNEL); if (!acm->ctrlurb) - goto alloc_fail3; + goto err_free_write_buffers; for (i = 0; i < num_rx_buf; i++) { struct acm_rb *rb = &(acm->read_buffers[i]); @@ -1389,13 +1395,13 @@ made_compressed_probe: rb->base = usb_alloc_coherent(acm->dev, readsize, GFP_KERNEL, &rb->dma); if (!rb->base) - goto alloc_fail4; + goto err_free_read_urbs; rb->index = i; rb->instance = acm; urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) - goto alloc_fail4; + goto err_free_read_urbs; urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; urb->transfer_dma = rb->dma; @@ -1416,8 +1422,8 @@ made_compressed_probe: struct acm_wb *snd = &(acm->wb[i]); snd->urb = usb_alloc_urb(0, GFP_KERNEL); - if (snd->urb == NULL) - goto alloc_fail5; + if (!snd->urb) + goto err_free_write_urbs; if (usb_endpoint_xfer_int(epwrite)) usb_fill_int_urb(snd->urb, usb_dev, acm->out, @@ -1435,7 +1441,7 @@ made_compressed_probe: i = device_create_file(&intf->dev, &dev_attr_bmCapabilities); if (i < 0) - goto alloc_fail5; + goto err_free_write_urbs; if (h.usb_cdc_country_functional_desc) { /* export the country data */ struct usb_cdc_country_functional_desc * cfd = @@ -1480,20 +1486,21 @@ skip_countries: acm->nb_index = 0; acm->nb_size = 0; - dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor); - acm->line.dwDTERate = cpu_to_le32(9600); acm->line.bDataBits = 8; acm_set_line(acm, &acm->line); - usb_driver_claim_interface(&acm_driver, data_interface, acm); - usb_set_intfdata(data_interface, acm); + if (!acm->combined_interfaces) { + rv = usb_driver_claim_interface(&acm_driver, data_interface, acm); + if (rv) + goto err_remove_files; + } tty_dev = tty_port_register_device(&acm->port, acm_tty_driver, minor, &control_interface->dev); if (IS_ERR(tty_dev)) { rv = PTR_ERR(tty_dev); - goto alloc_fail6; + goto err_release_data_interface; } if (quirks & CLEAR_HALT_CONDITIONS) { @@ -1501,32 +1508,39 @@ skip_countries: usb_clear_halt(usb_dev, acm->out); } + dev_info(&intf->dev, "ttyACM%d: USB ACM device\n", minor); + return 0; -alloc_fail6: + +err_release_data_interface: + if (!acm->combined_interfaces) { + /* Clear driver data so that disconnect() returns early. */ + usb_set_intfdata(data_interface, NULL); + usb_driver_release_interface(&acm_driver, data_interface); + } +err_remove_files: if (acm->country_codes) { device_remove_file(&acm->control->dev, &dev_attr_wCountryCodes); device_remove_file(&acm->control->dev, &dev_attr_iCountryCodeRelDate); - kfree(acm->country_codes); } device_remove_file(&acm->control->dev, &dev_attr_bmCapabilities); -alloc_fail5: - usb_set_intfdata(intf, NULL); +err_free_write_urbs: for (i = 0; i < ACM_NW; i++) usb_free_urb(acm->wb[i].urb); -alloc_fail4: +err_free_read_urbs: for (i = 0; i < num_rx_buf; i++) usb_free_urb(acm->read_urbs[i]); acm_read_buffers_free(acm); usb_free_urb(acm->ctrlurb); -alloc_fail3: +err_free_write_buffers: acm_write_buffers_free(acm); -alloc_fail2: +err_free_ctrl_buffer: usb_free_coherent(usb_dev, ctrlsize, acm->ctrl_buffer, acm->ctrl_dma); -alloc_fail1: +err_put_port: tty_port_put(&acm->port); -alloc_fail: + return rv; } @@ -1540,8 +1554,14 @@ static void acm_disconnect(struct usb_interface *intf) if (!acm) return; - mutex_lock(&acm->mutex); acm->disconnected = true; + /* + * there is a circular dependency. acm_softint() can resubmit + * the URBs in error handling so we need to block any + * submission right away + */ + acm_poison_urbs(acm); + mutex_lock(&acm->mutex); if (acm->country_codes) { device_remove_file(&acm->control->dev, &dev_attr_wCountryCodes); @@ -1560,7 +1580,6 @@ static void acm_disconnect(struct usb_interface *intf) tty_kref_put(tty); } - acm_kill_urbs(acm); cancel_delayed_work_sync(&acm->dwork); tty_unregister_device(acm_tty_driver, acm->minor); @@ -1602,7 +1621,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message) if (cnt) return 0; - acm_kill_urbs(acm); + acm_poison_urbs(acm); cancel_delayed_work_sync(&acm->dwork); acm->urbs_in_error_delay = 0; @@ -1615,6 +1634,7 @@ static int acm_resume(struct usb_interface *intf) struct urb *urb; int rv = 0; + acm_unpoison_urbs(acm); spin_lock_irq(&acm->write_lock); if (--acm->susp_count) diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 6ade3daf7858..76ac5d6555ae 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -498,6 +498,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* DJI CineSSD */ { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* Fibocom L850-GL LTE Modem */ + { USB_DEVICE(0x2cb7, 0x0007), .driver_info = + USB_QUIRK_IGNORE_REMOTE_WAKEUP }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c index fc3269f5faf1..1a9789ec5847 100644 --- a/drivers/usb/dwc2/hcd.c +++ b/drivers/usb/dwc2/hcd.c @@ -4322,7 +4322,8 @@ static int _dwc2_hcd_suspend(struct usb_hcd *hcd) if (hsotg->op_state == OTG_STATE_B_PERIPHERAL) goto unlock; - if (hsotg->params.power_down > DWC2_POWER_DOWN_PARAM_PARTIAL) + if (hsotg->params.power_down != DWC2_POWER_DOWN_PARAM_PARTIAL || + hsotg->flags.b.port_connect_status == 0) goto skip_power_saving; /* @@ -5398,7 +5399,7 @@ int dwc2_host_enter_hibernation(struct dwc2_hsotg *hsotg) dwc2_writel(hsotg, hprt0, HPRT0); /* Wait for the HPRT0.PrtSusp register field to be set */ - if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 3000)) + if (dwc2_hsotg_wait_bit_set(hsotg, HPRT0, HPRT0_SUSP, 5000)) dev_warn(hsotg->dev, "Suspend wasn't generated\n"); /* diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 3d3918a8d5fb..4c5c6972124a 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -120,6 +120,8 @@ static const struct property_entry dwc3_pci_intel_properties[] = { static const struct property_entry dwc3_pci_mrfld_properties[] = { PROPERTY_ENTRY_STRING("dr_mode", "otg"), PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"), + PROPERTY_ENTRY_BOOL("snps,dis_u3_susphy_quirk"), + PROPERTY_ENTRY_BOOL("snps,dis_u2_susphy_quirk"), PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"), {} }; diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index fcaf04483ad0..3de291ab951a 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -244,6 +244,9 @@ static int dwc3_qcom_interconnect_init(struct dwc3_qcom *qcom) struct device *dev = qcom->dev; int ret; + if (has_acpi_companion(dev)) + return 0; + qcom->icc_path_ddr = of_icc_get(dev, "usb-ddr"); if (IS_ERR(qcom->icc_path_ddr)) { dev_err(dev, "failed to get usb-ddr path: %ld\n", diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 4a337f348651..c7ef218e7a8c 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -791,10 +791,6 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) reg &= ~DWC3_DALEPENA_EP(dep->number); dwc3_writel(dwc->regs, DWC3_DALEPENA, reg); - dep->stream_capable = false; - dep->type = 0; - dep->flags = 0; - /* Clear out the ep descriptors for non-ep0 */ if (dep->number > 1) { dep->endpoint.comp_desc = NULL; @@ -803,6 +799,10 @@ static int __dwc3_gadget_ep_disable(struct dwc3_ep *dep) dwc3_remove_requests(dwc, dep); + dep->stream_capable = false; + dep->type = 0; + dep->flags = 0; + return 0; } @@ -2083,7 +2083,7 @@ static void __dwc3_gadget_set_speed(struct dwc3 *dwc) u32 reg; speed = dwc->gadget_max_speed; - if (speed > dwc->maximum_speed) + if (speed == USB_SPEED_UNKNOWN || speed > dwc->maximum_speed) speed = dwc->maximum_speed; if (speed == USB_SPEED_SUPER_PLUS && @@ -2523,6 +2523,7 @@ static void dwc3_gadget_set_ssp_rate(struct usb_gadget *g, unsigned long flags; spin_lock_irqsave(&dwc->lock, flags); + dwc->gadget_max_speed = USB_SPEED_SUPER_PLUS; dwc->gadget_ssp_rate = rate; spin_unlock_irqrestore(&dwc->lock, flags); } diff --git a/drivers/usb/gadget/udc/amd5536udc_pci.c b/drivers/usb/gadget/udc/amd5536udc_pci.c index 8d387e0e4d91..c80f9bd51b75 100644 --- a/drivers/usb/gadget/udc/amd5536udc_pci.c +++ b/drivers/usb/gadget/udc/amd5536udc_pci.c @@ -153,6 +153,11 @@ static int udc_pci_probe( pci_set_master(pdev); pci_try_set_mwi(pdev); + dev->phys_addr = resource; + dev->irq = pdev->irq; + dev->pdev = pdev; + dev->dev = &pdev->dev; + /* init dma pools */ if (use_dma) { retval = init_dma_pools(dev); @@ -160,11 +165,6 @@ static int udc_pci_probe( goto err_dma; } - dev->phys_addr = resource; - dev->irq = pdev->irq; - dev->pdev = pdev; - dev->dev = &pdev->dev; - /* general probing */ if (udc_probe(dev)) { retval = -ENODEV; diff --git a/drivers/usb/host/xhci-mtk.c b/drivers/usb/host/xhci-mtk.c index fe010cc61f19..2f27dc0d9c6b 100644 --- a/drivers/usb/host/xhci-mtk.c +++ b/drivers/usb/host/xhci-mtk.c @@ -397,6 +397,13 @@ static void xhci_mtk_quirks(struct device *dev, struct xhci_hcd *xhci) xhci->quirks |= XHCI_SPURIOUS_SUCCESS; if (mtk->lpm_support) xhci->quirks |= XHCI_LPM_SUPPORT; + + /* + * MTK xHCI 0.96: PSA is 1 by default even if doesn't support stream, + * and it's 3 when support it. + */ + if (xhci->hci_version < 0x100 && HCC_MAX_PSA(xhci->hcc_params) == 4) + xhci->quirks |= XHCI_BROKEN_STREAMS; } /* called during probe() after chip reset completes */ @@ -548,7 +555,8 @@ static int xhci_mtk_probe(struct platform_device *pdev) if (ret) goto put_usb3_hcd; - if (HCC_MAX_PSA(xhci->hcc_params) >= 4) + if (HCC_MAX_PSA(xhci->hcc_params) >= 4 && + !(xhci->quirks & XHCI_BROKEN_STREAMS)) xhci->shared_hcd->can_do_streams = 1; ret = usb_add_hcd(xhci->shared_hcd, irq, IRQF_SHARED); diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c index 1cd87729ba60..fc0457db62e1 100644 --- a/drivers/usb/musb/musb_core.c +++ b/drivers/usb/musb/musb_core.c @@ -2004,10 +2004,14 @@ static void musb_pm_runtime_check_session(struct musb *musb) MUSB_DEVCTL_HR; switch (devctl & ~s) { case MUSB_QUIRK_B_DISCONNECT_99: - musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n"); - schedule_delayed_work(&musb->irq_work, - msecs_to_jiffies(1000)); - break; + if (musb->quirk_retries && !musb->flush_irq_work) { + musb_dbg(musb, "Poll devctl in case of suspend after disconnect\n"); + schedule_delayed_work(&musb->irq_work, + msecs_to_jiffies(1000)); + musb->quirk_retries--; + break; + } + fallthrough; case MUSB_QUIRK_B_INVALID_VBUS_91: if (musb->quirk_retries && !musb->flush_irq_work) { musb_dbg(musb, diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c index 8f1de1fbbeed..d8d3892e5a69 100644 --- a/drivers/usb/usbip/stub_dev.c +++ b/drivers/usb/usbip/stub_dev.c @@ -63,6 +63,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a dev_info(dev, "stub up\n"); + mutex_lock(&sdev->ud.sysfs_lock); spin_lock_irq(&sdev->ud.lock); if (sdev->ud.status != SDEV_ST_AVAILABLE) { @@ -87,13 +88,13 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a tcp_rx = kthread_create(stub_rx_loop, &sdev->ud, "stub_rx"); if (IS_ERR(tcp_rx)) { sockfd_put(socket); - return -EINVAL; + goto unlock_mutex; } tcp_tx = kthread_create(stub_tx_loop, &sdev->ud, "stub_tx"); if (IS_ERR(tcp_tx)) { kthread_stop(tcp_rx); sockfd_put(socket); - return -EINVAL; + goto unlock_mutex; } /* get task structs now */ @@ -112,6 +113,8 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a wake_up_process(sdev->ud.tcp_rx); wake_up_process(sdev->ud.tcp_tx); + mutex_unlock(&sdev->ud.sysfs_lock); + } else { dev_info(dev, "stub down\n"); @@ -122,6 +125,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, struct device_attribute *a spin_unlock_irq(&sdev->ud.lock); usbip_event_add(&sdev->ud, SDEV_EVENT_DOWN); + mutex_unlock(&sdev->ud.sysfs_lock); } return count; @@ -130,6 +134,8 @@ sock_err: sockfd_put(socket); err: spin_unlock_irq(&sdev->ud.lock); +unlock_mutex: + mutex_unlock(&sdev->ud.sysfs_lock); return -EINVAL; } static DEVICE_ATTR_WO(usbip_sockfd); @@ -270,6 +276,7 @@ static struct stub_device *stub_device_alloc(struct usb_device *udev) sdev->ud.side = USBIP_STUB; sdev->ud.status = SDEV_ST_AVAILABLE; spin_lock_init(&sdev->ud.lock); + mutex_init(&sdev->ud.sysfs_lock); sdev->ud.tcp_socket = NULL; sdev->ud.sockfd = -1; diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h index d60ce17d3dd2..ea2a20e6d27d 100644 --- a/drivers/usb/usbip/usbip_common.h +++ b/drivers/usb/usbip/usbip_common.h @@ -263,6 +263,9 @@ struct usbip_device { /* lock for status */ spinlock_t lock; + /* mutex for synchronizing sysfs store paths */ + struct mutex sysfs_lock; + int sockfd; struct socket *tcp_socket; diff --git a/drivers/usb/usbip/usbip_event.c b/drivers/usb/usbip/usbip_event.c index 5d88917c9631..086ca76dd053 100644 --- a/drivers/usb/usbip/usbip_event.c +++ b/drivers/usb/usbip/usbip_event.c @@ -70,6 +70,7 @@ static void event_handler(struct work_struct *work) while ((ud = get_event()) != NULL) { usbip_dbg_eh("pending event %lx\n", ud->event); + mutex_lock(&ud->sysfs_lock); /* * NOTE: shutdown must come first. * Shutdown the device. @@ -90,6 +91,7 @@ static void event_handler(struct work_struct *work) ud->eh_ops.unusable(ud); unset_event(ud, USBIP_EH_UNUSABLE); } + mutex_unlock(&ud->sysfs_lock); wake_up(&ud->eh_waitq); } diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c index 3209b5ddd30c..4ba6bcdaa8e9 100644 --- a/drivers/usb/usbip/vhci_hcd.c +++ b/drivers/usb/usbip/vhci_hcd.c @@ -594,6 +594,8 @@ static int vhci_hub_control(struct usb_hcd *hcd, u16 typeReq, u16 wValue, pr_err("invalid port number %d\n", wIndex); goto error; } + if (wValue >= 32) + goto error; if (hcd->speed == HCD_USB3) { if ((vhci_hcd->port_status[rhport] & USB_SS_PORT_STAT_POWER) != 0) { @@ -1099,6 +1101,7 @@ static void vhci_device_init(struct vhci_device *vdev) vdev->ud.side = USBIP_VHCI; vdev->ud.status = VDEV_ST_NULL; spin_lock_init(&vdev->ud.lock); + mutex_init(&vdev->ud.sysfs_lock); INIT_LIST_HEAD(&vdev->priv_rx); INIT_LIST_HEAD(&vdev->priv_tx); diff --git a/drivers/usb/usbip/vhci_sysfs.c b/drivers/usb/usbip/vhci_sysfs.c index c4b4256e5dad..e2847cd3e6e3 100644 --- a/drivers/usb/usbip/vhci_sysfs.c +++ b/drivers/usb/usbip/vhci_sysfs.c @@ -185,6 +185,8 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport) usbip_dbg_vhci_sysfs("enter\n"); + mutex_lock(&vdev->ud.sysfs_lock); + /* lock */ spin_lock_irqsave(&vhci->lock, flags); spin_lock(&vdev->ud.lock); @@ -195,6 +197,7 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport) /* unlock */ spin_unlock(&vdev->ud.lock); spin_unlock_irqrestore(&vhci->lock, flags); + mutex_unlock(&vdev->ud.sysfs_lock); return -EINVAL; } @@ -205,6 +208,8 @@ static int vhci_port_disconnect(struct vhci_hcd *vhci_hcd, __u32 rhport) usbip_event_add(&vdev->ud, VDEV_EVENT_DOWN); + mutex_unlock(&vdev->ud.sysfs_lock); + return 0; } @@ -349,30 +354,36 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr, else vdev = &vhci->vhci_hcd_hs->vdev[rhport]; + mutex_lock(&vdev->ud.sysfs_lock); + /* Extract socket from fd. */ socket = sockfd_lookup(sockfd, &err); if (!socket) { dev_err(dev, "failed to lookup sock"); - return -EINVAL; + err = -EINVAL; + goto unlock_mutex; } if (socket->type != SOCK_STREAM) { dev_err(dev, "Expecting SOCK_STREAM - found %d", socket->type); sockfd_put(socket); - return -EINVAL; + err = -EINVAL; + goto unlock_mutex; } /* create threads before locking */ tcp_rx = kthread_create(vhci_rx_loop, &vdev->ud, "vhci_rx"); if (IS_ERR(tcp_rx)) { sockfd_put(socket); - return -EINVAL; + err = -EINVAL; + goto unlock_mutex; } tcp_tx = kthread_create(vhci_tx_loop, &vdev->ud, "vhci_tx"); if (IS_ERR(tcp_tx)) { kthread_stop(tcp_rx); sockfd_put(socket); - return -EINVAL; + err = -EINVAL; + goto unlock_mutex; } /* get task structs now */ @@ -397,7 +408,8 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr, * Will be retried from userspace * if there's another free port. */ - return -EBUSY; + err = -EBUSY; + goto unlock_mutex; } dev_info(dev, "pdev(%u) rhport(%u) sockfd(%d)\n", @@ -423,7 +435,15 @@ static ssize_t attach_store(struct device *dev, struct device_attribute *attr, rh_port_connect(vdev, speed); + dev_info(dev, "Device attached\n"); + + mutex_unlock(&vdev->ud.sysfs_lock); + return count; + +unlock_mutex: + mutex_unlock(&vdev->ud.sysfs_lock); + return err; } static DEVICE_ATTR_WO(attach); diff --git a/drivers/usb/usbip/vudc_dev.c b/drivers/usb/usbip/vudc_dev.c index c8eeabdd9b56..2bc428f2e261 100644 --- a/drivers/usb/usbip/vudc_dev.c +++ b/drivers/usb/usbip/vudc_dev.c @@ -572,6 +572,7 @@ static int init_vudc_hw(struct vudc *udc) init_waitqueue_head(&udc->tx_waitq); spin_lock_init(&ud->lock); + mutex_init(&ud->sysfs_lock); ud->status = SDEV_ST_AVAILABLE; ud->side = USBIP_VUDC; diff --git a/drivers/usb/usbip/vudc_sysfs.c b/drivers/usb/usbip/vudc_sysfs.c index 7383a543c6d1..f7633ee655a1 100644 --- a/drivers/usb/usbip/vudc_sysfs.c +++ b/drivers/usb/usbip/vudc_sysfs.c @@ -112,6 +112,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, dev_err(dev, "no device"); return -ENODEV; } + mutex_lock(&udc->ud.sysfs_lock); spin_lock_irqsave(&udc->lock, flags); /* Don't export what we don't have */ if (!udc->driver || !udc->pullup) { @@ -187,6 +188,8 @@ static ssize_t usbip_sockfd_store(struct device *dev, wake_up_process(udc->ud.tcp_rx); wake_up_process(udc->ud.tcp_tx); + + mutex_unlock(&udc->ud.sysfs_lock); return count; } else { @@ -207,6 +210,7 @@ static ssize_t usbip_sockfd_store(struct device *dev, } spin_unlock_irqrestore(&udc->lock, flags); + mutex_unlock(&udc->ud.sysfs_lock); return count; @@ -216,6 +220,7 @@ unlock_ud: spin_unlock_irq(&udc->ud.lock); unlock: spin_unlock_irqrestore(&udc->lock, flags); + mutex_unlock(&udc->ud.sysfs_lock); return ret; } diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 08f742fd2409..b6cc53ba980c 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -4,9 +4,13 @@ #ifndef __MLX5_VDPA_H__ #define __MLX5_VDPA_H__ +#include <linux/etherdevice.h> +#include <linux/if_vlan.h> #include <linux/vdpa.h> #include <linux/mlx5/driver.h> +#define MLX5V_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) + struct mlx5_vdpa_direct_mr { u64 start; u64 end; diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index d300f799efcd..800cfd1967ad 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -219,6 +219,11 @@ static void destroy_indirect_key(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_m mlx5_vdpa_destroy_mkey(mvdev, &mkey->mkey); } +static struct device *get_dma_device(struct mlx5_vdpa_dev *mvdev) +{ + return &mvdev->mdev->pdev->dev; +} + static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr, struct vhost_iotlb *iotlb) { @@ -234,7 +239,7 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr u64 pa; u64 paend; struct scatterlist *sg; - struct device *dma = mvdev->mdev->device; + struct device *dma = get_dma_device(mvdev); for (map = vhost_iotlb_itree_first(iotlb, mr->start, mr->end - 1); map; map = vhost_iotlb_itree_next(map, start, mr->end - 1)) { @@ -273,8 +278,10 @@ done: mr->log_size = log_entity_size; mr->nsg = nsg; mr->nent = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); - if (!mr->nent) + if (!mr->nent) { + err = -ENOMEM; goto err_map; + } err = create_direct_mr(mvdev, mr); if (err) @@ -291,7 +298,7 @@ err_map: static void unmap_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) { - struct device *dma = mvdev->mdev->device; + struct device *dma = get_dma_device(mvdev); destroy_direct_mr(mvdev, mr); dma_unmap_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c index 96e6421c5d1c..6521cbd0f5c2 100644 --- a/drivers/vdpa/mlx5/core/resources.c +++ b/drivers/vdpa/mlx5/core/resources.c @@ -246,7 +246,8 @@ int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev) if (err) goto err_key; - kick_addr = pci_resource_start(mdev->pdev, 0) + offset; + kick_addr = mdev->bar_addr + offset; + res->kick_addr = ioremap(kick_addr, PAGE_SIZE); if (!res->kick_addr) { err = -ENOMEM; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 71397fdafa6a..4d2809c7d4e3 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -820,7 +820,7 @@ static int create_virtqueue(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtque MLX5_SET(virtio_q, vq_ctx, event_qpn_or_msix, mvq->fwqp.mqp.qpn); MLX5_SET(virtio_q, vq_ctx, queue_size, mvq->num_ent); MLX5_SET(virtio_q, vq_ctx, virtio_version_1_0, - !!(ndev->mvdev.actual_features & VIRTIO_F_VERSION_1)); + !!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_F_VERSION_1))); MLX5_SET64(virtio_q, vq_ctx, desc_addr, mvq->desc_addr); MLX5_SET64(virtio_q, vq_ctx, used_addr, mvq->device_addr); MLX5_SET64(virtio_q, vq_ctx, available_addr, mvq->driver_addr); @@ -1169,6 +1169,7 @@ static void suspend_vq(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *m return; } mvq->avail_idx = attr.available_index; + mvq->used_idx = attr.used_index; } static void suspend_vqs(struct mlx5_vdpa_net *ndev) @@ -1426,6 +1427,7 @@ static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx, return -EINVAL; } + mvq->used_idx = state->avail_index; mvq->avail_idx = state->avail_index; return 0; } @@ -1443,7 +1445,11 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa * that cares about emulating the index after vq is stopped. */ if (!mvq->initialized) { - state->avail_index = mvq->avail_idx; + /* Firmware returns a wrong value for the available index. + * Since both values should be identical, we take the value of + * used_idx which is reported correctly. + */ + state->avail_index = mvq->used_idx; return 0; } @@ -1452,7 +1458,7 @@ static int mlx5_vdpa_get_vq_state(struct vdpa_device *vdev, u16 idx, struct vdpa mlx5_vdpa_warn(mvdev, "failed to query virtqueue\n"); return err; } - state->avail_index = attr.available_index; + state->avail_index = attr.used_index; return 0; } @@ -1540,21 +1546,11 @@ static void teardown_virtqueues(struct mlx5_vdpa_net *ndev) } } -static void clear_virtqueues(struct mlx5_vdpa_net *ndev) -{ - int i; - - for (i = ndev->mvdev.max_vqs - 1; i >= 0; i--) { - ndev->vqs[i].avail_idx = 0; - ndev->vqs[i].used_idx = 0; - } -} - /* TODO: cross-endian support */ static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev) { return virtio_legacy_is_little_endian() || - (mvdev->actual_features & (1ULL << VIRTIO_F_VERSION_1)); + (mvdev->actual_features & BIT_ULL(VIRTIO_F_VERSION_1)); } static __virtio16 cpu_to_mlx5vdpa16(struct mlx5_vdpa_dev *mvdev, u16 val) @@ -1785,7 +1781,6 @@ static void mlx5_vdpa_set_status(struct vdpa_device *vdev, u8 status) if (!status) { mlx5_vdpa_info(mvdev, "performing device reset\n"); teardown_driver(ndev); - clear_virtqueues(ndev); mlx5_vdpa_destroy_mr(&ndev->mvdev); ndev->mvdev.status = 0; ndev->mvdev.mlx_features = 0; @@ -1907,6 +1902,19 @@ static const struct vdpa_config_ops mlx5_vdpa_ops = { .free = mlx5_vdpa_free, }; +static int query_mtu(struct mlx5_core_dev *mdev, u16 *mtu) +{ + u16 hw_mtu; + int err; + + err = mlx5_query_nic_vport_mtu(mdev, &hw_mtu); + if (err) + return err; + + *mtu = hw_mtu - MLX5V_ETH_HARD_MTU; + return 0; +} + static int alloc_resources(struct mlx5_vdpa_net *ndev) { struct mlx5_vdpa_net_resources *res = &ndev->res; @@ -1992,7 +2000,7 @@ static int mlx5v_probe(struct auxiliary_device *adev, init_mvqs(ndev); mutex_init(&ndev->reslock); config = &ndev->config; - err = mlx5_query_nic_vport_mtu(mdev, &ndev->mtu); + err = query_mtu(mdev, &ndev->mtu); if (err) goto err_mtu; diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig index ac3c1dd3edef..4abddbebd4b2 100644 --- a/drivers/vfio/pci/Kconfig +++ b/drivers/vfio/pci/Kconfig @@ -42,6 +42,6 @@ config VFIO_PCI_IGD config VFIO_PCI_NVLINK2 def_bool y - depends on VFIO_PCI && PPC_POWERNV + depends on VFIO_PCI && PPC_POWERNV && SPAPR_TCE_IOMMU help VFIO PCI support for P9 Witherspoon machine with NVIDIA V100 GPUs diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 65e7e6b44578..5023e23db3bc 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -1656,6 +1656,8 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) index = vma->vm_pgoff >> (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT); + if (index >= VFIO_PCI_NUM_REGIONS + vdev->num_regions) + return -EINVAL; if (vma->vm_end < vma->vm_start) return -EINVAL; if ((vma->vm_flags & VM_SHARED) == 0) @@ -1664,7 +1666,7 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) int regnum = index - VFIO_PCI_NUM_REGIONS; struct vfio_pci_region *region = vdev->region + regnum; - if (region && region->ops && region->ops->mmap && + if (region->ops && region->ops->mmap && (region->flags & VFIO_REGION_INFO_FLAG_MMAP)) return region->ops->mmap(vdev, region, vma); return -EINVAL; diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index be444407664a..45cbfd4879a5 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -739,6 +739,12 @@ out: ret = vfio_lock_acct(dma, lock_acct, false); unpin_out: + if (batch->size == 1 && !batch->offset) { + /* May be a VM_PFNMAP pfn, which the batch can't remember. */ + put_pfn(pfn, dma->prot); + batch->size = 0; + } + if (ret < 0) { if (pinned && !rsvd) { for (pfn = *pfn_base ; pinned ; pfn++, pinned--) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index e0a27e336293..bfa4c6ef554e 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -745,9 +745,11 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, const struct vdpa_config_ops *ops = vdpa->config; int r = 0; + mutex_lock(&dev->mutex); + r = vhost_dev_check_owner(dev); if (r) - return r; + goto unlock; switch (msg->type) { case VHOST_IOTLB_UPDATE: @@ -768,6 +770,8 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, r = -EINVAL; break; } +unlock: + mutex_unlock(&dev->mutex); return r; } diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 44a5cd2f54cc..3406067985b1 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -1333,6 +1333,9 @@ static void fbcon_cursor(struct vc_data *vc, int mode) ops->cursor_flash = (mode == CM_ERASE) ? 0 : 1; + if (!ops->cursor) + return; + ops->cursor(vc, info, mode, get_color(vc, info, c, 1), get_color(vc, info, c, 0)); } diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c index c8b0ae676809..4dc9077dd2ac 100644 --- a/drivers/video/fbdev/hyperv_fb.c +++ b/drivers/video/fbdev/hyperv_fb.c @@ -1031,7 +1031,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info) PCI_DEVICE_ID_HYPERV_VIDEO, NULL); if (!pdev) { pr_err("Unable to find PCI Hyper-V video\n"); - kfree(info->apertures); return -ENODEV; } @@ -1129,7 +1128,6 @@ getmem_done: } else { pci_dev_put(pdev); } - kfree(info->apertures); return 0; @@ -1141,7 +1139,6 @@ err2: err1: if (!gen2vm) pci_dev_put(pdev); - kfree(info->apertures); return -ENOMEM; } diff --git a/drivers/watchdog/armada_37xx_wdt.c b/drivers/watchdog/armada_37xx_wdt.c index e5dcb26d85f0..1635f421ef2c 100644 --- a/drivers/watchdog/armada_37xx_wdt.c +++ b/drivers/watchdog/armada_37xx_wdt.c @@ -2,7 +2,7 @@ /* * Watchdog driver for Marvell Armada 37xx SoCs * - * Author: Marek Behun <marek.behun@nic.cz> + * Author: Marek Behún <kabel@kernel.org> */ #include <linux/clk.h> @@ -366,7 +366,7 @@ static struct platform_driver armada_37xx_wdt_driver = { module_platform_driver(armada_37xx_wdt_driver); -MODULE_AUTHOR("Marek Behun <marek.behun@nic.cz>"); +MODULE_AUTHOR("Marek Behun <kabel@kernel.org>"); MODULE_DESCRIPTION("Armada 37xx CPU Watchdog"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index 41645fe6ad48..ea0efd290c37 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -50,11 +50,11 @@ config XEN_BALLOON_MEMORY_HOTPLUG SUBSYSTEM=="memory", ACTION=="add", RUN+="/bin/sh -c '[ -f /sys$devpath/state ] && echo online > /sys$devpath/state'" -config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT +config XEN_MEMORY_HOTPLUG_LIMIT int "Hotplugged memory limit (in GiB) for a PV guest" default 512 depends on XEN_HAVE_PVMMU - depends on XEN_BALLOON_MEMORY_HOTPLUG + depends on MEMORY_HOTPLUG help Maxmium amount of memory (in GiB) that a PV guest can be expanded to when using memory hotplug. diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 8236e2364eeb..7bbfd58958bc 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -110,7 +110,7 @@ struct irq_info { unsigned short eoi_cpu; /* EOI must happen on this cpu-1 */ unsigned int irq_epoch; /* If eoi_cpu valid: irq_epoch of event */ u64 eoi_time; /* Time in jiffies when to EOI. */ - spinlock_t lock; + raw_spinlock_t lock; union { unsigned short virq; @@ -312,7 +312,7 @@ static int xen_irq_info_common_setup(struct irq_info *info, info->evtchn = evtchn; info->cpu = cpu; info->mask_reason = EVT_MASK_REASON_EXPLICIT; - spin_lock_init(&info->lock); + raw_spin_lock_init(&info->lock); ret = set_evtchn_to_irq(evtchn, irq); if (ret < 0) @@ -472,28 +472,28 @@ static void do_mask(struct irq_info *info, u8 reason) { unsigned long flags; - spin_lock_irqsave(&info->lock, flags); + raw_spin_lock_irqsave(&info->lock, flags); if (!info->mask_reason) mask_evtchn(info->evtchn); info->mask_reason |= reason; - spin_unlock_irqrestore(&info->lock, flags); + raw_spin_unlock_irqrestore(&info->lock, flags); } static void do_unmask(struct irq_info *info, u8 reason) { unsigned long flags; - spin_lock_irqsave(&info->lock, flags); + raw_spin_lock_irqsave(&info->lock, flags); info->mask_reason &= ~reason; if (!info->mask_reason) unmask_evtchn(info->evtchn); - spin_unlock_irqrestore(&info->lock, flags); + raw_spin_unlock_irqrestore(&info->lock, flags); } #ifdef CONFIG_X86 diff --git a/drivers/xen/time.c b/drivers/xen/time.c index 108edbcbc040..152dd33bb223 100644 --- a/drivers/xen/time.c +++ b/drivers/xen/time.c @@ -7,6 +7,7 @@ #include <linux/math64.h> #include <linux/gfp.h> #include <linux/slab.h> +#include <linux/static_call.h> #include <asm/paravirt.h> #include <asm/xen/hypervisor.h> @@ -175,7 +176,7 @@ void __init xen_time_setup_guest(void) xen_runstate_remote = !HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_runstate_update_flag); - pv_ops.time.steal_clock = xen_steal_clock; + static_call_update(pv_steal_clock, xen_steal_clock); static_key_slow_inc(¶virt_steal_enabled); if (xen_runstate_remote) diff --git a/fs/afs/write.c b/fs/afs/write.c index c9195fc67fd8..eb737ed63afb 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -851,8 +851,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf) fscache_wait_on_page_write(vnode->cache, vmf->page); #endif - if (PageWriteback(vmf->page) && - wait_on_page_bit_killable(vmf->page, PG_writeback) < 0) + if (wait_on_page_writeback_killable(vmf->page)) return VM_FAULT_RETRY; if (lock_page_killable(vmf->page) < 0) diff --git a/fs/block_dev.c b/fs/block_dev.c index 92ed7d5df677..09d6f7229db9 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -275,6 +275,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, bio.bi_opf = dio_bio_write_op(iocb); task_io_account_write(ret); } + if (iocb->ki_flags & IOCB_NOWAIT) + bio.bi_opf |= REQ_NOWAIT; if (iocb->ki_flags & IOCB_HIPRI) bio_set_polled(&bio, iocb); @@ -428,6 +430,8 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, bio->bi_opf = dio_bio_write_op(iocb); task_io_account_write(bio->bi_iter.bi_size); } + if (iocb->ki_flags & IOCB_NOWAIT) + bio->bi_opf |= REQ_NOWAIT; dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; @@ -1240,13 +1244,13 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate) lockdep_assert_held(&bdev->bd_mutex); - clear_bit(GD_NEED_PART_SCAN, &bdev->bd_disk->state); - rescan: ret = blk_drop_partitions(bdev); if (ret) return ret; + clear_bit(GD_NEED_PART_SCAN, &disk->state); + /* * Historically we only set the capacity to zero for devices that * support partitions (independ of actually having partitions created). diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile index b634c42115ea..b4fb997eda16 100644 --- a/fs/btrfs/Makefile +++ b/fs/btrfs/Makefile @@ -7,10 +7,12 @@ subdir-ccflags-y += -Wmissing-format-attribute subdir-ccflags-y += -Wmissing-prototypes subdir-ccflags-y += -Wold-style-definition subdir-ccflags-y += -Wmissing-include-dirs -subdir-ccflags-y += $(call cc-option, -Wunused-but-set-variable) -subdir-ccflags-y += $(call cc-option, -Wunused-const-variable) -subdir-ccflags-y += $(call cc-option, -Wpacked-not-aligned) -subdir-ccflags-y += $(call cc-option, -Wstringop-truncation) +condflags := \ + $(call cc-option, -Wunused-but-set-variable) \ + $(call cc-option, -Wunused-const-variable) \ + $(call cc-option, -Wpacked-not-aligned) \ + $(call cc-option, -Wstringop-truncation) +subdir-ccflags-y += $(condflags) # The following turn off the warnings enabled by -Wextra subdir-ccflags-y += -Wno-missing-field-initializers subdir-ccflags-y += -Wno-sign-compare diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 3a9c1e046ebe..d05f73530af7 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -81,6 +81,9 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info) struct btrfs_dev_replace_item *ptr; u64 src_devid; + if (!dev_root) + return 0; + path = btrfs_alloc_path(); if (!path) { ret = -ENOMEM; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 41b718cfea40..289f1f09481d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2387,8 +2387,9 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) } else { set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state); fs_info->dev_root = root; - btrfs_init_devices_late(fs_info); } + /* Initialize fs_info for all devices in any case */ + btrfs_init_devices_late(fs_info); /* If IGNOREDATACSUMS is set don't bother reading the csum root. */ if (!btrfs_test_opt(fs_info, IGNOREDATACSUMS)) { @@ -3009,6 +3010,21 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) } } + /* + * btrfs_find_orphan_roots() is responsible for finding all the dead + * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load + * them into the fs_info->fs_roots_radix tree. This must be done before + * calling btrfs_orphan_cleanup() on the tree root. If we don't do it + * first, then btrfs_orphan_cleanup() will delete a dead root's orphan + * item before the root's tree is deleted - this means that if we unmount + * or crash before the deletion completes, on the next mount we will not + * delete what remains of the tree because the orphan item does not + * exists anymore, which is what tells us we have a pending deletion. + */ + ret = btrfs_find_orphan_roots(fs_info); + if (ret) + goto out; + ret = btrfs_cleanup_fs_roots(fs_info); if (ret) goto out; @@ -3068,7 +3084,6 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info) } } - ret = btrfs_find_orphan_roots(fs_info); out: return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7cdf65be3707..a520775949a0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3099,11 +3099,13 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start, * @bio_offset: offset to the beginning of the bio (in bytes) * @page: page where is the data to be verified * @pgoff: offset inside the page + * @start: logical offset in the file * * The length of such check is always one sector size. */ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio, - u32 bio_offset, struct page *page, u32 pgoff) + u32 bio_offset, struct page *page, u32 pgoff, + u64 start) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); @@ -3130,8 +3132,8 @@ static int check_data_csum(struct inode *inode, struct btrfs_io_bio *io_bio, kunmap_atomic(kaddr); return 0; zeroit: - btrfs_print_data_csum_error(BTRFS_I(inode), page_offset(page) + pgoff, - csum, csum_expected, io_bio->mirror_num); + btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected, + io_bio->mirror_num); if (io_bio->device) btrfs_dev_stat_inc_and_print(io_bio->device, BTRFS_DEV_STAT_CORRUPTION_ERRS); @@ -3184,7 +3186,8 @@ int btrfs_verify_data_csum(struct btrfs_io_bio *io_bio, u32 bio_offset, pg_off += sectorsize, bio_offset += sectorsize) { int ret; - ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off); + ret = check_data_csum(inode, io_bio, bio_offset, page, pg_off, + page_offset(page) + pg_off); if (ret < 0) return -EIO; } @@ -7910,7 +7913,8 @@ static blk_status_t btrfs_check_read_dio_bio(struct inode *inode, ASSERT(pgoff < PAGE_SIZE); if (uptodate && (!csum || !check_data_csum(inode, io_bio, - bio_offset, bvec.bv_page, pgoff))) { + bio_offset, bvec.bv_page, + pgoff, start))) { clean_io_failure(fs_info, failure_tree, io_tree, start, bvec.bv_page, btrfs_ino(BTRFS_I(inode)), @@ -8169,10 +8173,6 @@ static blk_qc_t btrfs_submit_direct(struct inode *inode, struct iomap *iomap, bio->bi_end_io = btrfs_end_dio_bio; btrfs_io_bio(bio)->logical = file_offset; - WARN_ON_ONCE(write && btrfs_is_zoned(fs_info) && - fs_info->max_zone_append_size && - bio_op(bio) != REQ_OP_ZONE_APPEND); - if (bio_op(bio) == REQ_OP_ZONE_APPEND) { status = extract_ordered_extent(BTRFS_I(inode), bio, file_offset); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 14ff388fd3bd..f0b9ef13153a 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -226,7 +226,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info, { struct btrfs_qgroup_list *list; - btrfs_sysfs_del_one_qgroup(fs_info, qgroup); list_del(&qgroup->dirty); while (!list_empty(&qgroup->groups)) { list = list_first_entry(&qgroup->groups, @@ -243,7 +242,6 @@ static void __del_qgroup_rb(struct btrfs_fs_info *fs_info, list_del(&list->next_member); kfree(list); } - kfree(qgroup); } /* must be called with qgroup_lock held */ @@ -569,6 +567,8 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info) qgroup = rb_entry(n, struct btrfs_qgroup, node); rb_erase(n, &fs_info->qgroup_tree); __del_qgroup_rb(fs_info, qgroup); + btrfs_sysfs_del_one_qgroup(fs_info, qgroup); + kfree(qgroup); } /* * We call btrfs_free_qgroup_config() when unmounting @@ -1578,6 +1578,14 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid) spin_lock(&fs_info->qgroup_lock); del_qgroup_rb(fs_info, qgroupid); spin_unlock(&fs_info->qgroup_lock); + + /* + * Remove the qgroup from sysfs now without holding the qgroup_lock + * spinlock, since the sysfs_remove_group() function needs to take + * the mutex kernfs_mutex through kernfs_remove_by_name_ns(). + */ + btrfs_sysfs_del_one_qgroup(fs_info, qgroup); + kfree(qgroup); out: mutex_unlock(&fs_info->qgroup_ioctl_lock); return ret; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bc3b33efddc5..1c6810bbaf8b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7448,6 +7448,9 @@ static int btrfs_device_init_dev_stats(struct btrfs_device *device, int item_size; int i, ret, slot; + if (!device->fs_info->dev_root) + return 0; + key.objectid = BTRFS_DEV_STATS_OBJECTID; key.type = BTRFS_PERSISTENT_ITEM_KEY; key.offset = device->devid; diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 1f972b75a9ab..eeb3ebe11d7a 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -21,9 +21,30 @@ /* Pseudo write pointer value for conventional zone */ #define WP_CONVENTIONAL ((u64)-2) +/* + * Location of the first zone of superblock logging zone pairs. + * + * - primary superblock: 0B (zone 0) + * - first copy: 512G (zone starting at that offset) + * - second copy: 4T (zone starting at that offset) + */ +#define BTRFS_SB_LOG_PRIMARY_OFFSET (0ULL) +#define BTRFS_SB_LOG_FIRST_OFFSET (512ULL * SZ_1G) +#define BTRFS_SB_LOG_SECOND_OFFSET (4096ULL * SZ_1G) + +#define BTRFS_SB_LOG_FIRST_SHIFT const_ilog2(BTRFS_SB_LOG_FIRST_OFFSET) +#define BTRFS_SB_LOG_SECOND_SHIFT const_ilog2(BTRFS_SB_LOG_SECOND_OFFSET) + /* Number of superblock log zones */ #define BTRFS_NR_SB_LOG_ZONES 2 +/* + * Maximum supported zone size. Currently, SMR disks have a zone size of + * 256MiB, and we are expecting ZNS drives to be in the 1-4GiB range. We do not + * expect the zone size to become larger than 8GiB in the near future. + */ +#define BTRFS_MAX_ZONE_SIZE SZ_8G + static int copy_zone_info_cb(struct blk_zone *zone, unsigned int idx, void *data) { struct blk_zone *zones = data; @@ -111,23 +132,22 @@ static int sb_write_pointer(struct block_device *bdev, struct blk_zone *zones, } /* - * The following zones are reserved as the circular buffer on ZONED btrfs. - * - The primary superblock: zones 0 and 1 - * - The first copy: zones 16 and 17 - * - The second copy: zones 1024 or zone at 256GB which is minimum, and - * the following one + * Get the first zone number of the superblock mirror */ static inline u32 sb_zone_number(int shift, int mirror) { - ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX); + u64 zone; + ASSERT(mirror < BTRFS_SUPER_MIRROR_MAX); switch (mirror) { - case 0: return 0; - case 1: return 16; - case 2: return min_t(u64, btrfs_sb_offset(mirror) >> shift, 1024); + case 0: zone = 0; break; + case 1: zone = 1ULL << (BTRFS_SB_LOG_FIRST_SHIFT - shift); break; + case 2: zone = 1ULL << (BTRFS_SB_LOG_SECOND_SHIFT - shift); break; } - return 0; + ASSERT(zone <= U32_MAX); + + return (u32)zone; } /* @@ -300,10 +320,21 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device) zone_sectors = bdev_zone_sectors(bdev); } - nr_sectors = bdev_nr_sectors(bdev); /* Check if it's power of 2 (see is_power_of_2) */ ASSERT(zone_sectors != 0 && (zone_sectors & (zone_sectors - 1)) == 0); zone_info->zone_size = zone_sectors << SECTOR_SHIFT; + + /* We reject devices with a zone size larger than 8GB */ + if (zone_info->zone_size > BTRFS_MAX_ZONE_SIZE) { + btrfs_err_in_rcu(fs_info, + "zoned: %s: zone size %llu larger than supported maximum %llu", + rcu_str_deref(device->name), + zone_info->zone_size, BTRFS_MAX_ZONE_SIZE); + ret = -EINVAL; + goto out; + } + + nr_sectors = bdev_nr_sectors(bdev); zone_info->zone_size_shift = ilog2(zone_info->zone_size); zone_info->max_zone_append_size = (u64)queue_max_zone_append_sectors(queue) << SECTOR_SHIFT; diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c index dfb14dbddf51..38bb7764b454 100644 --- a/fs/cachefiles/bind.c +++ b/fs/cachefiles/bind.c @@ -118,6 +118,12 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache) cache->mnt = path.mnt; root = path.dentry; + ret = -EINVAL; + if (mnt_user_ns(path.mnt) != &init_user_ns) { + pr_warn("File cache on idmapped mounts not supported"); + goto error_unsupported; + } + /* check parameters */ ret = -EOPNOTSUPP; if (d_is_negative(root) || diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c index e027c718ca01..8ffc40e84a59 100644 --- a/fs/cachefiles/rdwr.c +++ b/fs/cachefiles/rdwr.c @@ -24,17 +24,16 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode, container_of(wait, struct cachefiles_one_read, monitor); struct cachefiles_object *object; struct fscache_retrieval *op = monitor->op; - struct wait_bit_key *key = _key; + struct wait_page_key *key = _key; struct page *page = wait->private; ASSERT(key); _enter("{%lu},%u,%d,{%p,%u}", monitor->netfs_page->index, mode, sync, - key->flags, key->bit_nr); + key->page, key->bit_nr); - if (key->flags != &page->flags || - key->bit_nr != PG_locked) + if (key->page != page || key->bit_nr != PG_locked) return 0; _debug("--- monitor %p %lx ---", page, page->flags); diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index fe03cbdae959..bf52e9326ebe 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -18,6 +18,7 @@ config CIFS select CRYPTO_AES select CRYPTO_LIB_DES select KEYS + select DNS_RESOLVER help This is the client VFS module for the SMB3 family of NAS protocols, (including support for the most recent, most secure dialect SMB3.1.1) @@ -112,7 +113,6 @@ config CIFS_WEAK_PW_HASH config CIFS_UPCALL bool "Kerberos/SPNEGO advanced session setup" depends on CIFS - select DNS_RESOLVER help Enables an upcall mechanism for CIFS which accesses userspace helper utilities to provide SPNEGO packaged (RFC 4178) Kerberos tickets @@ -179,7 +179,6 @@ config CIFS_DEBUG_DUMP_KEYS config CIFS_DFS_UPCALL bool "DFS feature support" depends on CIFS - select DNS_RESOLVER help Distributed File System (DFS) support is used to access shares transparently in an enterprise name space, even if the share diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile index 5213b20843b5..3ee3b7de4ded 100644 --- a/fs/cifs/Makefile +++ b/fs/cifs/Makefile @@ -10,13 +10,14 @@ cifs-y := trace.o cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o \ cifs_unicode.o nterr.o cifsencrypt.o \ readdir.o ioctl.o sess.o export.o smb1ops.o unc.o winucase.o \ smb2ops.o smb2maperror.o smb2transport.o \ - smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o + smb2misc.o smb2pdu.o smb2inode.o smb2file.o cifsacl.o fs_context.o \ + dns_resolve.o cifs-$(CONFIG_CIFS_XATTR) += xattr.o cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o -cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o dfs_cache.o +cifs-$(CONFIG_CIFS_DFS_UPCALL) += cifs_dfs_ref.o dfs_cache.o cifs-$(CONFIG_CIFS_SWN_UPCALL) += netlink.o cifs_swn.o diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 2be22a5c690f..d178cf85e926 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1130,8 +1130,7 @@ static int set_chmod_dacl(struct cifs_acl *pdacl, struct cifs_acl *pndacl, } /* If it's any one of the ACE we're replacing, skip! */ - if (!mode_from_sid && - ((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) || + if (((compare_sids(&pntace->sid, &sid_unix_NFS_mode) == 0) || (compare_sids(&pntace->sid, pownersid) == 0) || (compare_sids(&pntace->sid, pgrpsid) == 0) || (compare_sids(&pntace->sid, &sid_everyone) == 0) || diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 099ad9f3660b..5ddd20b62484 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -476,7 +476,8 @@ static int cifs_show_devname(struct seq_file *m, struct dentry *root) seq_puts(m, "none"); else { convert_delimiter(devname, '/'); - seq_puts(m, devname); + /* escape all spaces in share names */ + seq_escape(m, devname, " \t"); kfree(devname); } return 0; diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 31fc8695abd6..ec824ab8c5ca 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -919,8 +919,8 @@ struct cifs_ses { bool binding:1; /* are we binding the session? */ __u16 session_flags; __u8 smb3signingkey[SMB3_SIGN_KEY_SIZE]; - __u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE]; - __u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE]; + __u8 smb3encryptionkey[SMB3_ENC_DEC_KEY_SIZE]; + __u8 smb3decryptionkey[SMB3_ENC_DEC_KEY_SIZE]; __u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE]; __u8 binding_preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE]; @@ -1283,8 +1283,6 @@ struct cifs_aio_ctx { bool direct_io; }; -struct cifs_readdata; - /* asynchronous read support */ struct cifs_readdata { struct kref refcount; diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 64fe5a47b5e8..9adc74bd9f8f 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -147,6 +147,11 @@ */ #define SMB3_SIGN_KEY_SIZE (16) +/* + * Size of the smb3 encryption/decryption keys + */ +#define SMB3_ENC_DEC_KEY_SIZE (32) + #define CIFS_CLIENT_CHALLENGE_SIZE (8) #define CIFS_SERVER_CHALLENGE_SIZE (8) #define CIFS_HMAC_MD5_HASH_SIZE (16) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index eec8a2052da2..24668eb006c6 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -87,7 +87,6 @@ static void cifs_prune_tlinks(struct work_struct *work); * * This should be called with server->srv_mutex held. */ -#ifdef CONFIG_CIFS_DFS_UPCALL static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) { int rc; @@ -124,6 +123,7 @@ static int reconn_set_ipaddr_from_hostname(struct TCP_Server_Info *server) return !rc ? -1 : 0; } +#ifdef CONFIG_CIFS_DFS_UPCALL /* These functions must be called with server->srv_mutex held */ static void reconn_set_next_dfs_target(struct TCP_Server_Info *server, struct cifs_sb_info *cifs_sb, @@ -321,14 +321,29 @@ cifs_reconnect(struct TCP_Server_Info *server) #endif #ifdef CONFIG_CIFS_DFS_UPCALL + if (cifs_sb && cifs_sb->origin_fullpath) /* * Set up next DFS target server (if any) for reconnect. If DFS * feature is disabled, then we will retry last server we * connected to before. */ reconn_set_next_dfs_target(server, cifs_sb, &tgt_list, &tgt_it); + else { +#endif + /* + * Resolve the hostname again to make sure that IP address is up-to-date. + */ + rc = reconn_set_ipaddr_from_hostname(server); + if (rc) { + cifs_dbg(FYI, "%s: failed to resolve hostname: %d\n", + __func__, rc); + } + +#ifdef CONFIG_CIFS_DFS_UPCALL + } #endif + #ifdef CONFIG_CIFS_SWN_UPCALL } #endif diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 26de4329d161..042e24aad410 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -165,6 +165,7 @@ int cifs_posix_open(char *full_path, struct inode **pinode, goto posix_open_ret; } } else { + cifs_revalidate_mapping(*pinode); cifs_fattr_to_inode(*pinode, &fattr); } diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index 99a1951a01ec..d9a990c99121 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -58,6 +58,7 @@ #define SMB2_HMACSHA256_SIZE (32) #define SMB2_CMACAES_SIZE (16) #define SMB3_SIGNKEY_SIZE (16) +#define SMB3_GCM128_CRYPTKEY_SIZE (16) #define SMB3_GCM256_CRYPTKEY_SIZE (32) /* Maximum buffer size value we can send with 1 credit */ diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index b50164e2c88d..aac384f69f74 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -754,8 +754,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) } } spin_unlock(&cifs_tcp_ses_lock); - cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n"); - return false; + cifs_dbg(FYI, "No file id matched, oplock break ignored\n"); + return true; } void diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 9bae7e8deb09..f703204fb185 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2038,6 +2038,7 @@ smb2_duplicate_extents(const unsigned int xid, { int rc; unsigned int ret_data_len; + struct inode *inode; struct duplicate_extents_to_file dup_ext_buf; struct cifs_tcon *tcon = tlink_tcon(trgtfile->tlink); @@ -2054,10 +2055,21 @@ smb2_duplicate_extents(const unsigned int xid, cifs_dbg(FYI, "Duplicate extents: src off %lld dst off %lld len %lld\n", src_off, dest_off, len); - rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); - if (rc) - goto duplicate_extents_out; + inode = d_inode(trgtfile->dentry); + if (inode->i_size < dest_off + len) { + rc = smb2_set_file_size(xid, tcon, trgtfile, dest_off + len, false); + if (rc) + goto duplicate_extents_out; + /* + * Although also could set plausible allocation size (i_blocks) + * here in addition to setting the file size, in reflink + * it is likely that the target file is sparse. Its allocation + * size will be queried on next revalidate, but it is important + * to make sure that file's cached size is updated immediately + */ + cifs_setsize(inode, dest_off + len); + } rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid, trgtfile->fid.volatile_fid, FSCTL_DUPLICATE_EXTENTS_TO_FILE, @@ -4158,7 +4170,7 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key) if (ses->Suid == ses_id) { ses_enc_key = enc ? ses->smb3encryptionkey : ses->smb3decryptionkey; - memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE); + memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); spin_unlock(&cifs_tcp_ses_lock); return 0; } @@ -4185,7 +4197,7 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, int rc = 0; struct scatterlist *sg; u8 sign[SMB2_SIGNATURE_SIZE] = {}; - u8 key[SMB3_SIGN_KEY_SIZE]; + u8 key[SMB3_ENC_DEC_KEY_SIZE]; struct aead_request *req; char *iv; unsigned int iv_len; @@ -4209,10 +4221,11 @@ crypt_message(struct TCP_Server_Info *server, int num_rqst, tfm = enc ? server->secmech.ccmaesencrypt : server->secmech.ccmaesdecrypt; - if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM) + if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || + (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) rc = crypto_aead_setkey(tfm, key, SMB3_GCM256_CRYPTKEY_SIZE); else - rc = crypto_aead_setkey(tfm, key, SMB3_SIGN_KEY_SIZE); + rc = crypto_aead_setkey(tfm, key, SMB3_GCM128_CRYPTKEY_SIZE); if (rc) { cifs_server_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index ebccd71cc60a..e6fa76ab70be 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -298,7 +298,8 @@ static int generate_key(struct cifs_ses *ses, struct kvec label, { unsigned char zero = 0x0; __u8 i[4] = {0, 0, 0, 1}; - __u8 L[4] = {0, 0, 0, 128}; + __u8 L128[4] = {0, 0, 0, 128}; + __u8 L256[4] = {0, 0, 1, 0}; int rc = 0; unsigned char prfhash[SMB2_HMACSHA256_SIZE]; unsigned char *hashptr = prfhash; @@ -354,8 +355,14 @@ static int generate_key(struct cifs_ses *ses, struct kvec label, goto smb3signkey_ret; } - rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, - L, 4); + if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || + (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) { + rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, + L256, 4); + } else { + rc = crypto_shash_update(&server->secmech.sdeschmacsha256->shash, + L128, 4); + } if (rc) { cifs_server_dbg(VFS, "%s: Could not update with L\n", __func__); goto smb3signkey_ret; @@ -390,6 +397,9 @@ generate_smb3signingkey(struct cifs_ses *ses, const struct derivation_triplet *ptriplet) { int rc; +#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS + struct TCP_Server_Info *server = ses->server; +#endif /* * All channels use the same encryption/decryption keys but @@ -422,11 +432,11 @@ generate_smb3signingkey(struct cifs_ses *ses, rc = generate_key(ses, ptriplet->encryption.label, ptriplet->encryption.context, ses->smb3encryptionkey, - SMB3_SIGN_KEY_SIZE); + SMB3_ENC_DEC_KEY_SIZE); rc = generate_key(ses, ptriplet->decryption.label, ptriplet->decryption.context, ses->smb3decryptionkey, - SMB3_SIGN_KEY_SIZE); + SMB3_ENC_DEC_KEY_SIZE); if (rc) return rc; } @@ -442,14 +452,23 @@ generate_smb3signingkey(struct cifs_ses *ses, */ cifs_dbg(VFS, "Session Id %*ph\n", (int)sizeof(ses->Suid), &ses->Suid); + cifs_dbg(VFS, "Cipher type %d\n", server->cipher_type); cifs_dbg(VFS, "Session Key %*ph\n", SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response); cifs_dbg(VFS, "Signing Key %*ph\n", SMB3_SIGN_KEY_SIZE, ses->smb3signingkey); - cifs_dbg(VFS, "ServerIn Key %*ph\n", - SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey); - cifs_dbg(VFS, "ServerOut Key %*ph\n", - SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey); + if ((server->cipher_type == SMB2_ENCRYPTION_AES256_CCM) || + (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM)) { + cifs_dbg(VFS, "ServerIn Key %*ph\n", + SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3encryptionkey); + cifs_dbg(VFS, "ServerOut Key %*ph\n", + SMB3_GCM256_CRYPTKEY_SIZE, ses->smb3decryptionkey); + } else { + cifs_dbg(VFS, "ServerIn Key %*ph\n", + SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3encryptionkey); + cifs_dbg(VFS, "ServerOut Key %*ph\n", + SMB3_GCM128_CRYPTKEY_SIZE, ses->smb3decryptionkey); + } #endif return rc; } diff --git a/fs/coda/file.c b/fs/coda/file.c index 128d63df5bfb..ef5ca22bfb3e 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -175,10 +175,10 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma) ret = call_mmap(vma->vm_file, vma); if (ret) { - /* if call_mmap fails, our caller will put coda_file so we - * should drop the reference to the host_file that we got. + /* if call_mmap fails, our caller will put host_file so we + * should drop the reference to the coda_file that we got. */ - fput(host_file); + fput(coda_file); kfree(cvm_ops); } else { /* here we add redirects for the open/close vm_operations */ diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig index a5f5c30368a2..2d0c8922f635 100644 --- a/fs/crypto/Kconfig +++ b/fs/crypto/Kconfig @@ -14,16 +14,30 @@ config FS_ENCRYPTION F2FS and UBIFS make use of this feature. # Filesystems supporting encryption must select this if FS_ENCRYPTION. This -# allows the algorithms to be built as modules when all the filesystems are. +# allows the algorithms to be built as modules when all the filesystems are, +# whereas selecting them from FS_ENCRYPTION would force them to be built-in. +# +# Note: this option only pulls in the algorithms that filesystem encryption +# needs "by default". If userspace will use "non-default" encryption modes such +# as Adiantum encryption, then those other modes need to be explicitly enabled +# in the crypto API; see Documentation/filesystems/fscrypt.rst for details. +# +# Also note that this option only pulls in the generic implementations of the +# algorithms, not any per-architecture optimized implementations. It is +# strongly recommended to enable optimized implementations too. It is safe to +# disable these generic implementations if corresponding optimized +# implementations will always be available too; for this reason, these are soft +# dependencies ('imply' rather than 'select'). Only disable these generic +# implementations if you're sure they will never be needed, though. config FS_ENCRYPTION_ALGS tristate - select CRYPTO_AES - select CRYPTO_CBC - select CRYPTO_CTS - select CRYPTO_ECB - select CRYPTO_HMAC - select CRYPTO_SHA512 - select CRYPTO_XTS + imply CRYPTO_AES + imply CRYPTO_CBC + imply CRYPTO_CTS + imply CRYPTO_ECB + imply CRYPTO_HMAC + imply CRYPTO_SHA512 + imply CRYPTO_XTS config FS_ENCRYPTION_INLINE_CRYPT bool "Enable fscrypt to use inline crypto" diff --git a/fs/direct-io.c b/fs/direct-io.c index b61491bf3166..b2e86e739d7a 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -812,6 +812,7 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, struct buffer_head *map_bh) { int ret = 0; + int boundary = sdio->boundary; /* dio_send_cur_page may clear it */ if (dio->op == REQ_OP_WRITE) { /* @@ -850,10 +851,10 @@ submit_page_section(struct dio *dio, struct dio_submit *sdio, struct page *page, sdio->cur_page_fs_offset = sdio->block_in_file << sdio->blkbits; out: /* - * If sdio->boundary then we want to schedule the IO now to + * If boundary then we want to schedule the IO now to * avoid metadata seeks. */ - if (sdio->boundary) { + if (boundary) { ret = dio_send_cur_page(dio, sdio, map_bh); if (sdio->bio) dio_bio_submit(dio, sdio); diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index f45f9feebe59..74a5172c2d83 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -626,27 +626,41 @@ int ext4_claim_free_clusters(struct ext4_sb_info *sbi, /** * ext4_should_retry_alloc() - check if a block allocation should be retried - * @sb: super block - * @retries: number of attemps has been made + * @sb: superblock + * @retries: number of retry attempts made so far * - * ext4_should_retry_alloc() is called when ENOSPC is returned, and if - * it is profitable to retry the operation, this function will wait - * for the current or committing transaction to complete, and then - * return TRUE. We will only retry once. + * ext4_should_retry_alloc() is called when ENOSPC is returned while + * attempting to allocate blocks. If there's an indication that a pending + * journal transaction might free some space and allow another attempt to + * succeed, this function will wait for the current or committing transaction + * to complete and then return TRUE. */ int ext4_should_retry_alloc(struct super_block *sb, int *retries) { - if (!ext4_has_free_clusters(EXT4_SB(sb), 1, 0) || - (*retries)++ > 1 || - !EXT4_SB(sb)->s_journal) + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (!sbi->s_journal) return 0; - smp_mb(); - if (EXT4_SB(sb)->s_mb_free_pending == 0) + if (++(*retries) > 3) { + percpu_counter_inc(&sbi->s_sra_exceeded_retry_limit); return 0; + } + /* + * if there's no indication that blocks are about to be freed it's + * possible we just missed a transaction commit that did so + */ + smp_mb(); + if (sbi->s_mb_free_pending == 0) + return ext4_has_free_clusters(sbi, 1, 0); + + /* + * it's possible we've just missed a transaction commit here, + * so ignore the returned status + */ jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id); - jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal); + (void) jbd2_journal_force_commit_nested(sbi->s_journal); return 1; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 644fd69185d3..826a56e3bbd2 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1484,6 +1484,7 @@ struct ext4_sb_info { struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; struct percpu_counter s_dirtyclusters_counter; + struct percpu_counter s_sra_exceeded_retry_limit; struct blockgroup_lock *s_blockgroup_lock; struct proc_dir_entry *s_proc; struct kobject s_kobj; @@ -2793,6 +2794,8 @@ void __ext4_fc_track_link(handle_t *handle, struct inode *inode, struct dentry *dentry); void ext4_fc_track_unlink(handle_t *handle, struct dentry *dentry); void ext4_fc_track_link(handle_t *handle, struct dentry *dentry); +void __ext4_fc_track_create(handle_t *handle, struct inode *inode, + struct dentry *dentry); void ext4_fc_track_create(handle_t *handle, struct dentry *dentry); void ext4_fc_track_inode(handle_t *handle, struct inode *inode); void ext4_fc_mark_ineligible(struct super_block *sb, int reason); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 77c7c8a54da7..77c84d6f1af6 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4382,7 +4382,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset, { struct inode *inode = file_inode(file); handle_t *handle; - int ret, ret2 = 0, ret3 = 0; + int ret = 0, ret2 = 0, ret3 = 0; int retries = 0; int depth = 0; struct ext4_map_blocks map; diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 6c4f19b0a556..7541d0b5d706 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -513,10 +513,10 @@ void ext4_fc_track_link(handle_t *handle, struct dentry *dentry) __ext4_fc_track_link(handle, d_inode(dentry), dentry); } -void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) +void __ext4_fc_track_create(handle_t *handle, struct inode *inode, + struct dentry *dentry) { struct __track_dentry_update_args args; - struct inode *inode = d_inode(dentry); int ret; args.dentry = dentry; @@ -527,6 +527,11 @@ void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) trace_ext4_fc_track_create(inode, dentry, ret); } +void ext4_fc_track_create(handle_t *handle, struct dentry *dentry) +{ + __ext4_fc_track_create(handle, d_inode(dentry), dentry); +} + /* __track_fn for inode tracking */ static int __track_inode(struct inode *inode, void *arg, bool update) { diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 650c5acd2f2d..0948a43f1b3d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1938,13 +1938,13 @@ static int __ext4_journalled_writepage(struct page *page, if (!ret) ret = err; - if (!ext4_has_inline_data(inode)) - ext4_walk_page_buffers(NULL, page_bufs, 0, len, - NULL, bput_one); ext4_set_inode_state(inode, EXT4_STATE_JDATA); out: unlock_page(page); out_no_pagelock: + if (!inline_data && page_bufs) + ext4_walk_page_buffers(NULL, page_bufs, 0, len, + NULL, bput_one); brelse(inode_bh); return ret; } @@ -5026,7 +5026,7 @@ static int ext4_do_update_inode(handle_t *handle, struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; struct super_block *sb = inode->i_sb; - int err = 0, rc, block; + int err = 0, block; int need_datasync = 0, set_large_file = 0; uid_t i_uid; gid_t i_gid; @@ -5138,9 +5138,9 @@ static int ext4_do_update_inode(handle_t *handle, bh->b_data); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); - rc = ext4_handle_dirty_metadata(handle, NULL, bh); - if (!err) - err = rc; + err = ext4_handle_dirty_metadata(handle, NULL, bh); + if (err) + goto out_brelse; ext4_clear_inode_state(inode, EXT4_STATE_NEW); if (set_large_file) { BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access"); @@ -5387,8 +5387,10 @@ int ext4_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, inode->i_gid = attr->ia_gid; error = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); - if (unlikely(error)) + if (unlikely(error)) { + ext4_fc_stop_update(inode); return error; + } } if (attr->ia_valid & ATTR_SIZE) { diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 99bf091fee10..a02fadf4fc84 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2709,8 +2709,15 @@ static int ext4_mb_init_backend(struct super_block *sb) } if (ext4_has_feature_flex_bg(sb)) { - /* a single flex group is supposed to be read by a single IO */ - sbi->s_mb_prefetch = min(1 << sbi->s_es->s_log_groups_per_flex, + /* a single flex group is supposed to be read by a single IO. + * 2 ^ s_log_groups_per_flex != UINT_MAX as s_mb_prefetch is + * unsigned integer, so the maximum shift is 32. + */ + if (sbi->s_es->s_log_groups_per_flex >= 32) { + ext4_msg(sb, KERN_ERR, "too many log groups per flexible block group"); + goto err_freesgi; + } + sbi->s_mb_prefetch = min_t(uint, 1 << sbi->s_es->s_log_groups_per_flex, BLK_MAX_SEGMENT_SIZE >> (sb->s_blocksize_bits - 9)); sbi->s_mb_prefetch *= 8; /* 8 prefetch IOs in flight at most */ } else { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 686bf982c84e..883e2a7cd4ab 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3613,6 +3613,31 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent, return retval; } +static void ext4_resetent(handle_t *handle, struct ext4_renament *ent, + unsigned ino, unsigned file_type) +{ + struct ext4_renament old = *ent; + int retval = 0; + + /* + * old->de could have moved from under us during make indexed dir, + * so the old->de may no longer valid and need to find it again + * before reset old inode info. + */ + old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL); + if (IS_ERR(old.bh)) + retval = PTR_ERR(old.bh); + if (!old.bh) + retval = -ENOENT; + if (retval) { + ext4_std_error(old.dir->i_sb, retval); + return; + } + + ext4_setent(handle, &old, ino, file_type); + brelse(old.bh); +} + static int ext4_find_delete_entry(handle_t *handle, struct inode *dir, const struct qstr *d_name) { @@ -3774,14 +3799,14 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, */ retval = -ENOENT; if (!old.bh || le32_to_cpu(old.de->inode) != old.inode->i_ino) - goto end_rename; + goto release_bh; new.bh = ext4_find_entry(new.dir, &new.dentry->d_name, &new.de, &new.inlined); if (IS_ERR(new.bh)) { retval = PTR_ERR(new.bh); new.bh = NULL; - goto end_rename; + goto release_bh; } if (new.bh) { if (!new.inode) { @@ -3798,15 +3823,13 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, handle = ext4_journal_start(old.dir, EXT4_HT_DIR, credits); if (IS_ERR(handle)) { retval = PTR_ERR(handle); - handle = NULL; - goto end_rename; + goto release_bh; } } else { whiteout = ext4_whiteout_for_rename(mnt_userns, &old, credits, &handle); if (IS_ERR(whiteout)) { retval = PTR_ERR(whiteout); - whiteout = NULL; - goto end_rename; + goto release_bh; } } @@ -3850,6 +3873,7 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, retval = ext4_mark_inode_dirty(handle, whiteout); if (unlikely(retval)) goto end_rename; + } if (!new.bh) { retval = ext4_add_entry(handle, new.dentry, old.inode); @@ -3923,6 +3947,8 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, ext4_fc_track_unlink(handle, new.dentry); __ext4_fc_track_link(handle, old.inode, new.dentry); __ext4_fc_track_unlink(handle, old.inode, old.dentry); + if (whiteout) + __ext4_fc_track_create(handle, whiteout, old.dentry); } if (new.inode) { @@ -3937,19 +3963,21 @@ static int ext4_rename(struct user_namespace *mnt_userns, struct inode *old_dir, end_rename: if (whiteout) { if (retval) { - ext4_setent(handle, &old, - old.inode->i_ino, old_file_type); + ext4_resetent(handle, &old, + old.inode->i_ino, old_file_type); drop_nlink(whiteout); + ext4_orphan_add(handle, whiteout); } unlock_new_inode(whiteout); + ext4_journal_stop(handle); iput(whiteout); - + } else { + ext4_journal_stop(handle); } +release_bh: brelse(old.dir_bh); brelse(old.bh); brelse(new.bh); - if (handle) - ext4_journal_stop(handle); return retval; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ad34a37278cd..b9693680463a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1210,6 +1210,7 @@ static void ext4_put_super(struct super_block *sb) percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit); percpu_free_rwsem(&sbi->s_writepages_rwsem); #ifdef CONFIG_QUOTA for (i = 0; i < EXT4_MAXQUOTAS; i++) @@ -5012,6 +5013,9 @@ no_journal: err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0, GFP_KERNEL); if (!err) + err = percpu_counter_init(&sbi->s_sra_exceeded_retry_limit, 0, + GFP_KERNEL); + if (!err) err = percpu_init_rwsem(&sbi->s_writepages_rwsem); if (err) { @@ -5124,6 +5128,7 @@ failed_mount6: percpu_counter_destroy(&sbi->s_freeinodes_counter); percpu_counter_destroy(&sbi->s_dirs_counter); percpu_counter_destroy(&sbi->s_dirtyclusters_counter); + percpu_counter_destroy(&sbi->s_sra_exceeded_retry_limit); percpu_free_rwsem(&sbi->s_writepages_rwsem); failed_mount5: ext4_ext_release(sb); @@ -5149,8 +5154,8 @@ failed_mount_wq: failed_mount3a: ext4_es_unregister_shrinker(sbi); failed_mount3: - del_timer_sync(&sbi->s_err_report); flush_work(&sbi->s_error_work); + del_timer_sync(&sbi->s_err_report); if (sbi->s_mmp_tsk) kthread_stop(sbi->s_mmp_tsk); failed_mount2: diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 075aa3a19ff5..a3d08276d441 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -24,6 +24,7 @@ typedef enum { attr_session_write_kbytes, attr_lifetime_write_kbytes, attr_reserved_clusters, + attr_sra_exceeded_retry_limit, attr_inode_readahead, attr_trigger_test_error, attr_first_error_time, @@ -202,6 +203,7 @@ EXT4_ATTR_FUNC(delayed_allocation_blocks, 0444); EXT4_ATTR_FUNC(session_write_kbytes, 0444); EXT4_ATTR_FUNC(lifetime_write_kbytes, 0444); EXT4_ATTR_FUNC(reserved_clusters, 0644); +EXT4_ATTR_FUNC(sra_exceeded_retry_limit, 0444); EXT4_ATTR_OFFSET(inode_readahead_blks, 0644, inode_readahead, ext4_sb_info, s_inode_readahead_blks); @@ -251,6 +253,7 @@ static struct attribute *ext4_attrs[] = { ATTR_LIST(session_write_kbytes), ATTR_LIST(lifetime_write_kbytes), ATTR_LIST(reserved_clusters), + ATTR_LIST(sra_exceeded_retry_limit), ATTR_LIST(inode_readahead_blks), ATTR_LIST(inode_goal), ATTR_LIST(mb_stats), @@ -374,6 +377,10 @@ static ssize_t ext4_attr_show(struct kobject *kobj, return snprintf(buf, PAGE_SIZE, "%llu\n", (unsigned long long) atomic64_read(&sbi->s_resv_clusters)); + case attr_sra_exceeded_retry_limit: + return snprintf(buf, PAGE_SIZE, "%llu\n", + (unsigned long long) + percpu_counter_sum(&sbi->s_sra_exceeded_retry_limit)); case attr_inode_readahead: case attr_pointer_ui: if (!ptr) diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c index 5b7ba8f71153..00e3cbde472e 100644 --- a/fs/ext4/verity.c +++ b/fs/ext4/verity.c @@ -201,55 +201,76 @@ static int ext4_end_enable_verity(struct file *filp, const void *desc, struct inode *inode = file_inode(filp); const int credits = 2; /* superblock and inode for ext4_orphan_del() */ handle_t *handle; + struct ext4_iloc iloc; int err = 0; - int err2; - if (desc != NULL) { - /* Succeeded; write the verity descriptor. */ - err = ext4_write_verity_descriptor(inode, desc, desc_size, - merkle_tree_size); - - /* Write all pages before clearing VERITY_IN_PROGRESS. */ - if (!err) - err = filemap_write_and_wait(inode->i_mapping); - } + /* + * If an error already occurred (which fs/verity/ signals by passing + * desc == NULL), then only clean-up is needed. + */ + if (desc == NULL) + goto cleanup; - /* If we failed, truncate anything we wrote past i_size. */ - if (desc == NULL || err) - ext4_truncate(inode); + /* Append the verity descriptor. */ + err = ext4_write_verity_descriptor(inode, desc, desc_size, + merkle_tree_size); + if (err) + goto cleanup; /* - * We must always clean up by clearing EXT4_STATE_VERITY_IN_PROGRESS and - * deleting the inode from the orphan list, even if something failed. - * If everything succeeded, we'll also set the verity bit in the same - * transaction. + * Write all pages (both data and verity metadata). Note that this must + * happen before clearing EXT4_STATE_VERITY_IN_PROGRESS; otherwise pages + * beyond i_size won't be written properly. For crash consistency, this + * also must happen before the verity inode flag gets persisted. */ + err = filemap_write_and_wait(inode->i_mapping); + if (err) + goto cleanup; - ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + /* + * Finally, set the verity inode flag and remove the inode from the + * orphan list (in a single transaction). + */ handle = ext4_journal_start(inode, EXT4_HT_INODE, credits); if (IS_ERR(handle)) { - ext4_orphan_del(NULL, inode); - return PTR_ERR(handle); + err = PTR_ERR(handle); + goto cleanup; } - err2 = ext4_orphan_del(handle, inode); - if (err2) - goto out_stop; + err = ext4_orphan_del(handle, inode); + if (err) + goto stop_and_cleanup; - if (desc != NULL && !err) { - struct ext4_iloc iloc; + err = ext4_reserve_inode_write(handle, inode, &iloc); + if (err) + goto stop_and_cleanup; - err = ext4_reserve_inode_write(handle, inode, &iloc); - if (err) - goto out_stop; - ext4_set_inode_flag(inode, EXT4_INODE_VERITY); - ext4_set_inode_flags(inode, false); - err = ext4_mark_iloc_dirty(handle, inode, &iloc); - } -out_stop: + ext4_set_inode_flag(inode, EXT4_INODE_VERITY); + ext4_set_inode_flags(inode, false); + err = ext4_mark_iloc_dirty(handle, inode, &iloc); + if (err) + goto stop_and_cleanup; + + ext4_journal_stop(handle); + + ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + return 0; + +stop_and_cleanup: ext4_journal_stop(handle); - return err ?: err2; +cleanup: + /* + * Verity failed to be enabled, so clean up by truncating any verity + * metadata that was written beyond i_size (both from cache and from + * disk), removing the inode from the orphan list (if it wasn't done + * already), and clearing EXT4_STATE_VERITY_IN_PROGRESS. + */ + truncate_inode_pages(inode->i_mapping, inode->i_size); + ext4_truncate(inode); + ext4_orphan_del(NULL, inode); + ext4_clear_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS); + return err; } static int ext4_get_verity_descriptor_location(struct inode *inode, diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 372208500f4e..6c1018223c54 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1462,6 +1462,9 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value, if (!ce) return NULL; + WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) && + !(current->flags & PF_MEMALLOC_NOFS)); + ea_data = kvmalloc(value_len, GFP_KERNEL); if (!ea_data) { mb_cache_entry_put(ea_inode_cache, ce); @@ -2327,6 +2330,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, error = -ENOSPC; goto cleanup; } + WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } error = ext4_reserve_inode_write(handle, inode, &is.iloc); @@ -2400,7 +2404,7 @@ retry_inode: * external inode if possible. */ if (ext4_has_feature_ea_inode(inode->i_sb) && - !i.in_inode) { + i.value_len && !i.in_inode) { i.in_inode = 1; goto retry_inode; } diff --git a/fs/file.c b/fs/file.c index f3a4bac2cbe9..f633348029a5 100644 --- a/fs/file.c +++ b/fs/file.c @@ -629,17 +629,30 @@ int close_fd(unsigned fd) } EXPORT_SYMBOL(close_fd); /* for ksys_close() */ +/** + * last_fd - return last valid index into fd table + * @cur_fds: files struct + * + * Context: Either rcu read lock or files_lock must be held. + * + * Returns: Last valid index into fdtable. + */ +static inline unsigned last_fd(struct fdtable *fdt) +{ + return fdt->max_fds - 1; +} + static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; - if (fd > max_fd) - return; - + /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); - bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); + max_fd = min(last_fd(fdt), max_fd); + if (fd <= max_fd) + bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index 97076d3f562f..8fb9602d79b4 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -162,8 +162,10 @@ int gfs2_make_fs_rw(struct gfs2_sbd *sdp) int error; error = init_threads(sdp); - if (error) + if (error) { + gfs2_withdraw_delayed(sdp); return error; + } j_gl->gl_ops->go_inval(j_gl, DIO_METADATA); if (gfs2_withdrawn(sdp)) { @@ -750,11 +752,13 @@ void gfs2_freeze_func(struct work_struct *work) static int gfs2_freeze(struct super_block *sb) { struct gfs2_sbd *sdp = sb->s_fs_info; - int error = 0; + int error; mutex_lock(&sdp->sd_freeze_mutex); - if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) + if (atomic_read(&sdp->sd_freeze_state) != SFS_UNFROZEN) { + error = -EBUSY; goto out; + } for (;;) { if (gfs2_withdrawn(sdp)) { @@ -795,10 +799,10 @@ static int gfs2_unfreeze(struct super_block *sb) struct gfs2_sbd *sdp = sb->s_fs_info; mutex_lock(&sdp->sd_freeze_mutex); - if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN || + if (atomic_read(&sdp->sd_freeze_state) != SFS_FROZEN || !gfs2_holder_initialized(&sdp->sd_freeze_gh)) { mutex_unlock(&sdp->sd_freeze_mutex); - return 0; + return -EINVAL; } gfs2_freeze_unlock(&sdp->sd_freeze_gh); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 29e407762626..743a005a5c64 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -144,7 +144,7 @@ static char *follow_link(char *link) char *name, *resolved, *end; int n; - name = __getname(); + name = kmalloc(PATH_MAX, GFP_KERNEL); if (!name) { n = -ENOMEM; goto out_free; @@ -173,12 +173,11 @@ static char *follow_link(char *link) goto out_free; } - __putname(name); - kfree(link); + kfree(name); return resolved; out_free: - __putname(name); + kfree(name); return ERR_PTR(n); } diff --git a/fs/io-wq.c b/fs/io-wq.c index 3dc10bfd8c3b..4eba531bea5a 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -16,7 +16,6 @@ #include <linux/rculist_nulls.h> #include <linux/cpu.h> #include <linux/tracehook.h> -#include <linux/freezer.h> #include "../kernel/sched/sched.h" #include "io-wq.h" @@ -388,11 +387,9 @@ static struct io_wq_work *io_get_next_work(struct io_wqe *wqe) static bool io_flush_signals(void) { - if (unlikely(test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL))) { + if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL))) { __set_current_state(TASK_RUNNING); - if (current->task_works) - task_work_run(); - clear_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL); + tracehook_notify_signal(); return true; } return false; @@ -418,6 +415,7 @@ static void io_worker_handle_work(struct io_worker *worker) { struct io_wqe *wqe = worker->wqe; struct io_wq *wq = wqe->wq; + bool do_kill = test_bit(IO_WQ_BIT_EXIT, &wq->state); do { struct io_wq_work *work; @@ -447,6 +445,9 @@ get_next: unsigned int hash = io_get_work_hash(work); next_hashed = wq_next_work(work); + + if (unlikely(do_kill) && (work->flags & IO_WQ_WORK_UNBOUND)) + work->flags |= IO_WQ_WORK_CANCEL; wq->do_work(work); io_assign_current_work(worker, NULL); @@ -487,7 +488,7 @@ static int io_wqe_worker(void *data) worker->flags |= (IO_WORKER_F_UP | IO_WORKER_F_RUNNING); io_wqe_inc_running(worker); - sprintf(buf, "iou-wrk-%d", wq->task_pid); + snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task_pid); set_task_comm(current, buf); while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { @@ -505,10 +506,15 @@ loop: if (io_flush_signals()) continue; ret = schedule_timeout(WORKER_IDLE_TIMEOUT); - if (try_to_freeze() || ret) - continue; - if (fatal_signal_pending(current)) + if (signal_pending(current)) { + struct ksignal ksig; + + if (!get_signal(&ksig)) + continue; break; + } + if (ret) + continue; /* timed out, exit unless we're the fixed worker */ if (test_bit(IO_WQ_BIT_EXIT, &wq->state) || !(worker->flags & IO_WORKER_F_FIXED)) @@ -709,16 +715,20 @@ static int io_wq_manager(void *data) char buf[TASK_COMM_LEN]; int node; - sprintf(buf, "iou-mgr-%d", wq->task_pid); + snprintf(buf, sizeof(buf), "iou-mgr-%d", wq->task_pid); set_task_comm(current, buf); do { set_current_state(TASK_INTERRUPTIBLE); io_wq_check_workers(wq); schedule_timeout(HZ); - try_to_freeze(); - if (fatal_signal_pending(current)) + if (signal_pending(current)) { + struct ksignal ksig; + + if (!get_signal(&ksig)) + continue; set_bit(IO_WQ_BIT_EXIT, &wq->state); + } } while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)); io_wq_check_workers(wq); @@ -1065,7 +1075,11 @@ static void io_wq_destroy(struct io_wq *wq) for_each_node(node) { struct io_wqe *wqe = wq->wqes[node]; - WARN_ON_ONCE(!wq_list_empty(&wqe->work_list)); + struct io_cb_cancel_data match = { + .fn = io_wq_work_match_all, + .cancel_all = true, + }; + io_wqe_cancel_pending_work(wqe, &match); kfree(wqe); } io_wq_put_hash(wq->hash); diff --git a/fs/io_uring.c b/fs/io_uring.c index 543551d70327..dff34975d86b 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -78,7 +78,6 @@ #include <linux/task_work.h> #include <linux/pagemap.h> #include <linux/io_uring.h> -#include <linux/freezer.h> #define CREATE_TRACE_POINTS #include <trace/events/io_uring.h> @@ -698,6 +697,7 @@ enum { REQ_F_NO_FILE_TABLE_BIT, REQ_F_LTIMEOUT_ACTIVE_BIT, REQ_F_COMPLETE_INLINE_BIT, + REQ_F_REISSUE_BIT, /* not a real bit, just to check we're not overflowing the space */ __REQ_F_LAST_BIT, @@ -741,6 +741,8 @@ enum { REQ_F_LTIMEOUT_ACTIVE = BIT(REQ_F_LTIMEOUT_ACTIVE_BIT), /* completion is deferred through io_comp_state */ REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), + /* caller should reissue async */ + REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), }; struct async_poll { @@ -1095,8 +1097,6 @@ static bool io_match_task(struct io_kiocb *head, io_for_each_link(req, head) { if (req->flags & REQ_F_INFLIGHT) return true; - if (req->task->files == files) - return true; } return false; } @@ -1216,7 +1216,7 @@ static void io_prep_async_work(struct io_kiocb *req) if (req->flags & REQ_F_ISREG) { if (def->hash_reg_file || (ctx->flags & IORING_SETUP_IOPOLL)) io_wq_hash_work(&req->work, file_inode(req->file)); - } else { + } else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) { if (def->unbound_nonreg_file) req->work.flags |= IO_WQ_WORK_UNBOUND; } @@ -1239,16 +1239,16 @@ static void io_queue_async_work(struct io_kiocb *req) BUG_ON(!tctx); BUG_ON(!tctx->io_wq); - trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, - &req->work, req->flags); /* init ->work of the whole link before punting */ io_prep_async_link(req); + trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req, + &req->work, req->flags); io_wq_enqueue(tctx->io_wq, &req->work); if (link) io_queue_linked_timeout(link); } -static void io_kill_timeout(struct io_kiocb *req) +static void io_kill_timeout(struct io_kiocb *req, int status) { struct io_timeout_data *io = req->async_data; int ret; @@ -1258,31 +1258,11 @@ static void io_kill_timeout(struct io_kiocb *req) atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); list_del_init(&req->timeout.list); - io_cqring_fill_event(req, 0); + io_cqring_fill_event(req, status); io_put_req_deferred(req, 1); } } -/* - * Returns true if we found and killed one or more timeouts - */ -static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, - struct files_struct *files) -{ - struct io_kiocb *req, *tmp; - int canceled = 0; - - spin_lock_irq(&ctx->completion_lock); - list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { - if (io_match_task(req, tsk, files)) { - io_kill_timeout(req); - canceled++; - } - } - spin_unlock_irq(&ctx->completion_lock); - return canceled != 0; -} - static void __io_queue_deferred(struct io_ring_ctx *ctx) { do { @@ -1327,7 +1307,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx) break; list_del_init(&req->timeout.list); - io_kill_timeout(req); + io_kill_timeout(req, 0); } while (!list_empty(&ctx->timeout_list)); ctx->cq_last_tm_flush = seq; @@ -2499,6 +2479,11 @@ static bool io_rw_should_reissue(struct io_kiocb *req) return false; return true; } +#else +static bool io_rw_should_reissue(struct io_kiocb *req) +{ + return false; +} #endif static bool io_rw_reissue(struct io_kiocb *req) @@ -2524,13 +2509,14 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2, { int cflags = 0; - if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_reissue(req)) + if (req->rw.kiocb.ki_flags & IOCB_WRITE) + kiocb_end_write(req); + if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { + req->flags |= REQ_F_REISSUE; return; + } if (res != req->result) req_set_fail_links(req); - - if (req->rw.kiocb.ki_flags & IOCB_WRITE) - kiocb_end_write(req); if (req->flags & REQ_F_BUFFER_SELECTED) cflags = io_put_rw_kbuf(req); __io_req_complete(req, issue_flags, res, cflags); @@ -2776,6 +2762,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, { struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw.kiocb); struct io_async_rw *io = req->async_data; + bool check_reissue = kiocb->ki_complete == io_complete_rw; /* add previously done IO, if any */ if (io && io->bytes_done > 0) { @@ -2791,6 +2778,18 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, __io_complete_rw(req, ret, 0, issue_flags); else io_rw_done(kiocb, ret); + + if (check_reissue && req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + if (!io_rw_reissue(req)) { + int cflags = 0; + + req_set_fail_links(req); + if (req->flags & REQ_F_BUFFER_SELECTED) + cflags = io_put_rw_kbuf(req); + __io_req_complete(req, issue_flags, ret, cflags); + } + } } static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) @@ -3307,11 +3306,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) ret = io_iter_do_read(req, iter); - if (ret == -EIOCBQUEUED) { - if (req->async_data) - iov_iter_revert(iter, io_size - iov_iter_count(iter)); - goto out_free; - } else if (ret == -EAGAIN) { + if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { + req->flags &= ~REQ_F_REISSUE; /* IOPOLL retry should happen for io-wq threads */ if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL)) goto done; @@ -3321,6 +3317,8 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) /* some cases will consume bytes even on error returns */ iov_iter_revert(iter, io_size - iov_iter_count(iter)); ret = 0; + } else if (ret == -EIOCBQUEUED) { + goto out_free; } else if (ret <= 0 || ret == io_size || !force_nonblock || (req->flags & REQ_F_NOWAIT) || !(req->flags & REQ_F_ISREG)) { /* read all, failed, already did sync or don't want to retry */ @@ -3433,6 +3431,11 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) else ret2 = -EINVAL; + if (req->flags & REQ_F_REISSUE) { + req->flags &= ~REQ_F_REISSUE; + ret2 = -EAGAIN; + } + /* * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just * retry them without IOCB_NOWAIT. @@ -3442,8 +3445,6 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) /* no retry on NONBLOCK nor RWF_NOWAIT */ if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT)) goto done; - if (ret2 == -EIOCBQUEUED && req->async_data) - iov_iter_revert(iter, io_size - iov_iter_count(iter)); if (!force_nonblock || ret2 != -EAGAIN) { /* IOPOLL retry should happen for io-wq threads */ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) @@ -3978,6 +3979,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) static int io_provide_buffers_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { + unsigned long size; struct io_provide_buf *p = &req->pbuf; u64 tmp; @@ -3991,7 +3993,8 @@ static int io_provide_buffers_prep(struct io_kiocb *req, p->addr = READ_ONCE(sqe->addr); p->len = READ_ONCE(sqe->len); - if (!access_ok(u64_to_user_ptr(p->addr), (p->len * p->nbufs))) + size = (unsigned long)p->len * p->nbufs; + if (!access_ok(u64_to_user_ptr(p->addr), size)) return -EFAULT; p->bgid = READ_ONCE(sqe->buf_group); @@ -4820,7 +4823,6 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags) ret = -ENOMEM; goto out; } - io = req->async_data; memcpy(req->async_data, &__io, sizeof(__io)); return -EAGAIN; } @@ -5583,7 +5585,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, data->mode = io_translate_timeout_mode(flags); hrtimer_init(&data->timer, CLOCK_MONOTONIC, data->mode); - io_req_track_inflight(req); + if (is_timeout_link) + io_req_track_inflight(req); return 0; } @@ -6479,8 +6482,6 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, ret = io_init_req(ctx, req, sqe); if (unlikely(ret)) { fail_req: - io_put_req(req); - io_req_complete(req, ret); if (link->head) { /* fail even hard links since we don't submit */ link->head->flags |= REQ_F_FAIL_LINK; @@ -6488,6 +6489,8 @@ fail_req: io_req_complete(link->head, -ECANCELED); link->head = NULL; } + io_put_req(req); + io_req_complete(req, ret); return ret; } ret = io_req_prep(req, sqe); @@ -6740,7 +6743,7 @@ static int io_sq_thread(void *data) char buf[TASK_COMM_LEN]; DEFINE_WAIT(wait); - sprintf(buf, "iou-sqp-%d", sqd->task_pid); + snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); set_task_comm(current, buf); current->pf_io_worker = NULL; @@ -6751,21 +6754,32 @@ static int io_sq_thread(void *data) current->flags |= PF_NO_SETAFFINITY; mutex_lock(&sqd->lock); + /* a user may had exited before the thread started */ + io_run_task_work_head(&sqd->park_task_work); + while (!test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state)) { int ret; bool cap_entries, sqt_spin, needs_sched; - if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state)) { + if (test_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state) || + signal_pending(current)) { + bool did_sig = false; + mutex_unlock(&sqd->lock); + if (signal_pending(current)) { + struct ksignal ksig; + + did_sig = get_signal(&ksig); + } cond_resched(); mutex_lock(&sqd->lock); io_run_task_work(); io_run_task_work_head(&sqd->park_task_work); + if (did_sig) + break; timeout = jiffies + sqd->sq_thread_idle; continue; } - if (fatal_signal_pending(current)) - break; sqt_spin = false; cap_entries = !list_is_singular(&sqd->ctx_list); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { @@ -6808,7 +6822,6 @@ static int io_sq_thread(void *data) mutex_unlock(&sqd->lock); schedule(); - try_to_freeze(); mutex_lock(&sqd->lock); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_clear_wakeup_flag(ctx); @@ -6873,7 +6886,7 @@ static int io_run_task_work_sig(void) return 1; if (!signal_pending(current)) return 0; - if (test_tsk_thread_flag(current, TIF_NOTIFY_SIGNAL)) + if (test_thread_flag(TIF_NOTIFY_SIGNAL)) return -ERESTARTSYS; return -EINTR; } @@ -8563,6 +8576,14 @@ static void io_ring_exit_work(struct work_struct *work) struct io_tctx_node *node; int ret; + /* prevent SQPOLL from submitting new requests */ + if (ctx->sq_data) { + io_sq_thread_park(ctx->sq_data); + list_del_init(&ctx->sqd_list); + io_sqd_update_thread_idle(ctx->sq_data); + io_sq_thread_unpark(ctx->sq_data); + } + /* * If we're doing polled IO and end up having requests being * submitted async (out-of-line), then completions can come in while @@ -8599,6 +8620,28 @@ static void io_ring_exit_work(struct work_struct *work) io_ring_ctx_free(ctx); } +/* Returns true if we found and killed one or more timeouts */ +static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, + struct files_struct *files) +{ + struct io_kiocb *req, *tmp; + int canceled = 0; + + spin_lock_irq(&ctx->completion_lock); + list_for_each_entry_safe(req, tmp, &ctx->timeout_list, timeout.list) { + if (io_match_task(req, tsk, files)) { + io_kill_timeout(req, -ECANCELED); + canceled++; + } + } + if (canceled != 0) + io_commit_cqring(ctx); + spin_unlock_irq(&ctx->completion_lock); + if (canceled != 0) + io_cqring_ev_posted(ctx); + return canceled != 0; +} + static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { unsigned long index; @@ -8614,14 +8657,6 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) io_unregister_personality(ctx, index); mutex_unlock(&ctx->uring_lock); - /* prevent SQPOLL from submitting new requests */ - if (ctx->sq_data) { - io_sq_thread_park(ctx->sq_data); - list_del_init(&ctx->sqd_list); - io_sqd_update_thread_idle(ctx->sq_data); - io_sq_thread_unpark(ctx->sq_data); - } - io_kill_timeouts(ctx, NULL, NULL); io_poll_remove_all(ctx, NULL, NULL); @@ -8998,6 +9033,8 @@ void __io_uring_task_cancel(void) /* make sure overflow events are dropped */ atomic_inc(&tctx->in_idle); + __io_uring_files_cancel(NULL); + do { /* read completions before cancelations */ inflight = tctx_inflight(tctx); diff --git a/fs/namei.c b/fs/namei.c index 216f16e74351..48a2f288e802 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -579,6 +579,8 @@ static void set_nameidata(struct nameidata *p, int dfd, struct filename *name) p->stack = p->internal; p->dfd = dfd; p->name = name; + p->path.mnt = NULL; + p->path.dentry = NULL; p->total_link_count = old ? old->total_link_count : 0; p->saved = old; current->nameidata = p; @@ -652,6 +654,8 @@ static void terminate_walk(struct nameidata *nd) rcu_read_unlock(); } nd->depth = 0; + nd->path.mnt = NULL; + nd->path.dentry = NULL; } /* path_put is needed afterwards regardless of success or failure */ @@ -2322,8 +2326,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags) } nd->root.mnt = NULL; - nd->path.mnt = NULL; - nd->path.dentry = NULL; /* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */ if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) { @@ -2419,16 +2421,16 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path while (!(err = link_path_walk(s, nd)) && (s = lookup_last(nd)) != NULL) ; + if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { + err = handle_lookup_down(nd); + nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please... + } if (!err) err = complete_walk(nd); if (!err && nd->flags & LOOKUP_DIRECTORY) if (!d_can_lookup(nd->path.dentry)) err = -ENOTDIR; - if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) { - err = handle_lookup_down(nd); - nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please... - } if (!err) { *path = nd->path; nd->path.mnt = NULL; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 3bfb4147895a..ad20403b383f 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2295,7 +2295,7 @@ static int ocfs2_dio_end_io_write(struct inode *inode, struct ocfs2_alloc_context *meta_ac = NULL; handle_t *handle = NULL; loff_t end = offset + bytes; - int ret = 0, credits = 0, locked = 0; + int ret = 0, credits = 0; ocfs2_init_dealloc_ctxt(&dealloc); @@ -2306,13 +2306,6 @@ static int ocfs2_dio_end_io_write(struct inode *inode, !dwc->dw_orphaned) goto out; - /* ocfs2_file_write_iter will get i_mutex, so we need not lock if we - * are in that context. */ - if (dwc->dw_writer_pid != task_pid_nr(current)) { - inode_lock(inode); - locked = 1; - } - ret = ocfs2_inode_lock(inode, &di_bh, 1); if (ret < 0) { mlog_errno(ret); @@ -2393,8 +2386,6 @@ out: if (meta_ac) ocfs2_free_alloc_context(meta_ac); ocfs2_run_deallocs(osb, &dealloc); - if (locked) - inode_unlock(inode); ocfs2_dio_free_write_ctx(inode, dwc); return ret; diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 6611c64ca0be..5edc1d0cf115 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1245,22 +1245,24 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, goto bail_unlock; } } + down_write(&OCFS2_I(inode)->ip_alloc_sem); handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS + 2 * ocfs2_quota_trans_credits(sb)); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); - goto bail_unlock; + goto bail_unlock_alloc; } status = __dquot_transfer(inode, transfer_to); if (status < 0) goto bail_commit; } else { + down_write(&OCFS2_I(inode)->ip_alloc_sem); handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS); if (IS_ERR(handle)) { status = PTR_ERR(handle); mlog_errno(status); - goto bail_unlock; + goto bail_unlock_alloc; } } @@ -1273,6 +1275,8 @@ int ocfs2_setattr(struct user_namespace *mnt_userns, struct dentry *dentry, bail_commit: ocfs2_commit_trans(osb, handle); +bail_unlock_alloc: + up_write(&OCFS2_I(inode)->ip_alloc_sem); bail_unlock: if (status && inode_locked) { ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock); diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index dbfb35fb0ff7..3847cdc069b5 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -430,20 +430,11 @@ static int ovl_mmap(struct file *file, struct vm_area_struct *vma) if (WARN_ON(file != vma->vm_file)) return -EIO; - vma->vm_file = get_file(realfile); + vma_set_file(vma, realfile); old_cred = ovl_override_creds(file_inode(file)->i_sb); ret = call_mmap(vma->vm_file, vma); revert_creds(old_cred); - - if (ret) { - /* Drop reference count from new vm_file value */ - fput(realfile); - } else { - /* Drop reference count from previous vm_file value */ - fput(file); - } - ovl_file_accessed(file); return ret; diff --git a/fs/readdir.c b/fs/readdir.c index 19434b3c982c..09e8ed7d4161 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -150,6 +150,9 @@ static int fillonedir(struct dir_context *ctx, const char *name, int namlen, if (buf->result) return -EINVAL; + buf->result = verify_dirent_name(name, namlen); + if (buf->result < 0) + return buf->result; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->result = -EOVERFLOW; @@ -405,6 +408,9 @@ static int compat_fillonedir(struct dir_context *ctx, const char *name, if (buf->result) return -EINVAL; + buf->result = verify_dirent_name(name, namlen); + if (buf->result < 0) + return buf->result; d_ino = ino; if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { buf->result = -EOVERFLOW; diff --git a/fs/reiserfs/xattr.h b/fs/reiserfs/xattr.h index 9b3b06da568c..e47fde1182de 100644 --- a/fs/reiserfs/xattr.h +++ b/fs/reiserfs/xattr.h @@ -44,7 +44,7 @@ void reiserfs_security_free(struct reiserfs_security_handle *sec); static inline int reiserfs_xattrs_initialized(struct super_block *sb) { - return REISERFS_SB(sb)->priv_root != NULL; + return REISERFS_SB(sb)->priv_root && REISERFS_SB(sb)->xattr_root; } #define xattr_size(size) ((size) + sizeof(struct reiserfs_xattr_header)) diff --git a/fs/squashfs/export.c b/fs/squashfs/export.c index eb02072d28dd..723763746238 100644 --- a/fs/squashfs/export.c +++ b/fs/squashfs/export.c @@ -152,14 +152,18 @@ __le64 *squashfs_read_inode_lookup_table(struct super_block *sb, start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); - if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end + || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); - if (start >= lookup_table_start || (lookup_table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= lookup_table_start || + (lookup_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/id.c b/fs/squashfs/id.c index 11581bf31af4..ea5387679723 100644 --- a/fs/squashfs/id.c +++ b/fs/squashfs/id.c @@ -97,14 +97,16 @@ __le64 *squashfs_read_id_index_table(struct super_block *sb, start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); - if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); - if (start >= id_table_start || (id_table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= id_table_start || (id_table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index 8d64edb80ebf..b3fdc8212c5f 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -17,6 +17,7 @@ /* size of metadata (inode and directory) blocks */ #define SQUASHFS_METADATA_SIZE 8192 +#define SQUASHFS_BLOCK_OFFSET 2 /* default size of block device I/O */ #ifdef CONFIG_SQUASHFS_4K_DEVBLK_SIZE diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index ead66670b41a..087cab8c78f4 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -109,14 +109,16 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, start = le64_to_cpu(table[n]); end = le64_to_cpu(table[n + 1]); - if (start >= end || (end - start) > SQUASHFS_METADATA_SIZE) { + if (start >= end || (end - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } } start = le64_to_cpu(table[indexes - 1]); - if (start >= table_start || (table_start - start) > SQUASHFS_METADATA_SIZE) { + if (start >= table_start || (table_start - start) > + (SQUASHFS_METADATA_SIZE + SQUASHFS_BLOCK_OFFSET)) { kfree(table); return ERR_PTR(-EINVAL); } diff --git a/fs/verity/Kconfig b/fs/verity/Kconfig index 88fb25119899..24d1b54de807 100644 --- a/fs/verity/Kconfig +++ b/fs/verity/Kconfig @@ -3,9 +3,13 @@ config FS_VERITY bool "FS Verity (read-only file-based authenticity protection)" select CRYPTO - # SHA-256 is selected as it's intended to be the default hash algorithm. + # SHA-256 is implied as it's intended to be the default hash algorithm. # To avoid bloat, other wanted algorithms must be selected explicitly. - select CRYPTO_SHA256 + # Note that CRYPTO_SHA256 denotes the generic C implementation, but + # some architectures provided optimized implementations of the same + # algorithm that may be used instead. In this case, CRYPTO_SHA256 may + # be omitted even if SHA-256 is being used. + imply CRYPTO_SHA256 help This option enables fs-verity. fs-verity is the dm-verity mechanism implemented at the file level. On supported diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 02a716a0af5d..f28b097c658f 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -233,6 +233,7 @@ struct acpi_pnp_type { struct acpi_device_pnp { acpi_bus_id bus_id; /* Object name */ + int instance_no; /* Instance number of this object */ struct acpi_pnp_type type; /* ID type */ acpi_bus_address bus_address; /* _ADR */ char *unique_id; /* _UID */ diff --git a/include/crypto/acompress.h b/include/crypto/acompress.h index fcde59c65a81..cb3d6b1c655d 100644 --- a/include/crypto/acompress.h +++ b/include/crypto/acompress.h @@ -165,6 +165,8 @@ static inline struct crypto_acomp *crypto_acomp_reqtfm(struct acomp_req *req) * crypto_free_acomp() -- free ACOMPRESS tfm handle * * @tfm: ACOMPRESS tfm handle allocated with crypto_alloc_acomp() + * + * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_acomp(struct crypto_acomp *tfm) { diff --git a/include/crypto/aead.h b/include/crypto/aead.h index fcc12c593ef8..e728469c4ccc 100644 --- a/include/crypto/aead.h +++ b/include/crypto/aead.h @@ -185,6 +185,8 @@ static inline struct crypto_tfm *crypto_aead_tfm(struct crypto_aead *tfm) /** * crypto_free_aead() - zeroize and free aead handle * @tfm: cipher handle to be freed + * + * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_aead(struct crypto_aead *tfm) { diff --git a/include/crypto/akcipher.h b/include/crypto/akcipher.h index 1d3aa252caba..5764b46bd1ec 100644 --- a/include/crypto/akcipher.h +++ b/include/crypto/akcipher.h @@ -174,6 +174,8 @@ static inline struct crypto_akcipher *crypto_akcipher_reqtfm( * crypto_free_akcipher() - free AKCIPHER tfm handle * * @tfm: AKCIPHER tfm handle allocated with crypto_alloc_akcipher() + * + * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_akcipher(struct crypto_akcipher *tfm) { diff --git a/include/crypto/chacha.h b/include/crypto/chacha.h index 3a1c72fdb7cf..dabaee698718 100644 --- a/include/crypto/chacha.h +++ b/include/crypto/chacha.h @@ -47,13 +47,18 @@ static inline void hchacha_block(const u32 *state, u32 *out, int nrounds) hchacha_block_generic(state, out, nrounds); } -void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv); -static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv) +static inline void chacha_init_consts(u32 *state) { state[0] = 0x61707865; /* "expa" */ state[1] = 0x3320646e; /* "nd 3" */ state[2] = 0x79622d32; /* "2-by" */ state[3] = 0x6b206574; /* "te k" */ +} + +void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv); +static inline void chacha_init_generic(u32 *state, const u32 *key, const u8 *iv) +{ + chacha_init_consts(state); state[4] = key[0]; state[5] = key[1]; state[6] = key[2]; diff --git a/include/crypto/ecc_curve.h b/include/crypto/ecc_curve.h new file mode 100644 index 000000000000..70964781eb68 --- /dev/null +++ b/include/crypto/ecc_curve.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021 HiSilicon */ + +#ifndef _CRYTO_ECC_CURVE_H +#define _CRYTO_ECC_CURVE_H + +#include <linux/types.h> + +/** + * struct ecc_point - elliptic curve point in affine coordinates + * + * @x: X coordinate in vli form. + * @y: Y coordinate in vli form. + * @ndigits: Length of vlis in u64 qwords. + */ +struct ecc_point { + u64 *x; + u64 *y; + u8 ndigits; +}; + +/** + * struct ecc_curve - definition of elliptic curve + * + * @name: Short name of the curve. + * @g: Generator point of the curve. + * @p: Prime number, if Barrett's reduction is used for this curve + * pre-calculated value 'mu' is appended to the @p after ndigits. + * Use of Barrett's reduction is heuristically determined in + * vli_mmod_fast(). + * @n: Order of the curve group. + * @a: Curve parameter a. + * @b: Curve parameter b. + */ +struct ecc_curve { + char *name; + struct ecc_point g; + u64 *p; + u64 *n; + u64 *a; + u64 *b; +}; + +/** + * ecc_get_curve() - get elliptic curve; + * @curve_id: Curves IDs: + * defined in 'include/crypto/ecdh.h'; + * + * Returns curve if get curve succssful, NULL otherwise + */ +const struct ecc_curve *ecc_get_curve(unsigned int curve_id); + +/** + * ecc_get_curve25519() - get curve25519 curve; + * + * Returns curve25519 + */ +const struct ecc_curve *ecc_get_curve25519(void); + +#endif diff --git a/include/crypto/ecdh.h b/include/crypto/ecdh.h index a5b805b5526d..a9f98078d29c 100644 --- a/include/crypto/ecdh.h +++ b/include/crypto/ecdh.h @@ -25,16 +25,15 @@ /* Curves IDs */ #define ECC_CURVE_NIST_P192 0x0001 #define ECC_CURVE_NIST_P256 0x0002 +#define ECC_CURVE_NIST_P384 0x0003 /** * struct ecdh - define an ECDH private key * - * @curve_id: ECC curve the key is based on. * @key: Private ECDH key * @key_size: Size of the private ECDH key */ struct ecdh { - unsigned short curve_id; char *key; unsigned short key_size; }; diff --git a/include/crypto/hash.h b/include/crypto/hash.h index 13f8a6a54ca8..b2bc1e46e86a 100644 --- a/include/crypto/hash.h +++ b/include/crypto/hash.h @@ -281,6 +281,8 @@ static inline struct crypto_tfm *crypto_ahash_tfm(struct crypto_ahash *tfm) /** * crypto_free_ahash() - zeroize and free the ahash handle * @tfm: cipher handle to be freed + * + * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_ahash(struct crypto_ahash *tfm) { @@ -724,6 +726,8 @@ static inline struct crypto_tfm *crypto_shash_tfm(struct crypto_shash *tfm) /** * crypto_free_shash() - zeroize and free the message digest handle * @tfm: cipher handle to be freed + * + * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_shash(struct crypto_shash *tfm) { diff --git a/include/crypto/internal/poly1305.h b/include/crypto/internal/poly1305.h index 064e52ca5248..196aa769f296 100644 --- a/include/crypto/internal/poly1305.h +++ b/include/crypto/internal/poly1305.h @@ -18,7 +18,8 @@ * only the ε-almost-∆-universal hash function (not the full MAC) is computed. */ -void poly1305_core_setkey(struct poly1305_core_key *key, const u8 *raw_key); +void poly1305_core_setkey(struct poly1305_core_key *key, + const u8 raw_key[POLY1305_BLOCK_SIZE]); static inline void poly1305_core_init(struct poly1305_state *state) { *state = (struct poly1305_state){}; diff --git a/include/crypto/kpp.h b/include/crypto/kpp.h index 88b591215d5c..cccceadc164b 100644 --- a/include/crypto/kpp.h +++ b/include/crypto/kpp.h @@ -154,6 +154,8 @@ static inline void crypto_kpp_set_flags(struct crypto_kpp *tfm, u32 flags) * crypto_free_kpp() - free KPP tfm handle * * @tfm: KPP tfm handle allocated with crypto_alloc_kpp() + * + * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_kpp(struct crypto_kpp *tfm) { diff --git a/include/crypto/poly1305.h b/include/crypto/poly1305.h index f1f67fc749cf..090692ec3bc7 100644 --- a/include/crypto/poly1305.h +++ b/include/crypto/poly1305.h @@ -58,8 +58,10 @@ struct poly1305_desc_ctx { }; }; -void poly1305_init_arch(struct poly1305_desc_ctx *desc, const u8 *key); -void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key); +void poly1305_init_arch(struct poly1305_desc_ctx *desc, + const u8 key[POLY1305_KEY_SIZE]); +void poly1305_init_generic(struct poly1305_desc_ctx *desc, + const u8 key[POLY1305_KEY_SIZE]); static inline void poly1305_init(struct poly1305_desc_ctx *desc, const u8 *key) { diff --git a/include/crypto/rng.h b/include/crypto/rng.h index 8b4b844b4eef..17bb3673d3c1 100644 --- a/include/crypto/rng.h +++ b/include/crypto/rng.h @@ -111,6 +111,8 @@ static inline struct rng_alg *crypto_rng_alg(struct crypto_rng *tfm) /** * crypto_free_rng() - zeroize and free RNG handle * @tfm: cipher handle to be freed + * + * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_rng(struct crypto_rng *tfm) { diff --git a/include/crypto/skcipher.h b/include/crypto/skcipher.h index 6a733b171a5d..ef0fc9ed4342 100644 --- a/include/crypto/skcipher.h +++ b/include/crypto/skcipher.h @@ -196,6 +196,8 @@ static inline struct crypto_tfm *crypto_skcipher_tfm( /** * crypto_free_skcipher() - zeroize and free cipher handle * @tfm: cipher handle to be freed + * + * If @tfm is a NULL or error pointer, this function does nothing. */ static inline void crypto_free_skcipher(struct crypto_skcipher *tfm) { diff --git a/include/dt-bindings/bus/moxtet.h b/include/dt-bindings/bus/moxtet.h index dc9345440ebe..10528de7b3ef 100644 --- a/include/dt-bindings/bus/moxtet.h +++ b/include/dt-bindings/bus/moxtet.h @@ -2,7 +2,7 @@ /* * Constant for device tree bindings for Turris Mox module configuration bus * - * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz> + * Copyright (C) 2019 Marek Behún <kabel@kernel.org> */ #ifndef _DT_BINDINGS_BUS_MOXTET_H diff --git a/include/keys/asymmetric-type.h b/include/keys/asymmetric-type.h index a29d3ff2e7e8..c432fdb8547f 100644 --- a/include/keys/asymmetric-type.h +++ b/include/keys/asymmetric-type.h @@ -72,6 +72,12 @@ const struct asymmetric_key_ids *asymmetric_key_ids(const struct key *key) return key->payload.data[asym_key_ids]; } +static inline +const struct public_key *asymmetric_key_public_key(const struct key *key) +{ + return key->payload.data[asym_crypto]; +} + extern struct key *find_asymmetric_key(struct key *keyring, const struct asymmetric_key_id *id_0, const struct asymmetric_key_id *id_1, diff --git a/include/keys/system_keyring.h b/include/keys/system_keyring.h index fb8b07daa9d1..875e002a4180 100644 --- a/include/keys/system_keyring.h +++ b/include/keys/system_keyring.h @@ -31,6 +31,7 @@ extern int restrict_link_by_builtin_and_secondary_trusted( #define restrict_link_by_builtin_and_secondary_trusted restrict_link_by_builtin_trusted #endif +extern struct pkcs7_message *pkcs7; #ifdef CONFIG_SYSTEM_BLACKLIST_KEYRING extern int mark_hash_blacklisted(const char *hash); extern int is_hash_blacklisted(const u8 *hash, size_t hash_len, @@ -49,6 +50,20 @@ static inline int is_binary_blacklisted(const u8 *hash, size_t hash_len) } #endif +#ifdef CONFIG_SYSTEM_REVOCATION_LIST +extern int add_key_to_revocation_list(const char *data, size_t size); +extern int is_key_on_revocation_list(struct pkcs7_message *pkcs7); +#else +static inline int add_key_to_revocation_list(const char *data, size_t size) +{ + return 0; +} +static inline int is_key_on_revocation_list(struct pkcs7_message *pkcs7) +{ + return -ENOKEY; +} +#endif + #ifdef CONFIG_IMA_BLACKLIST_KEYRING extern struct key *ima_blacklist_keyring; diff --git a/include/keys/trusted-type.h b/include/keys/trusted-type.h index a94c03a61d8f..d89fa2579ac0 100644 --- a/include/keys/trusted-type.h +++ b/include/keys/trusted-type.h @@ -11,6 +11,12 @@ #include <linux/rcupdate.h> #include <linux/tpm.h> +#ifdef pr_fmt +#undef pr_fmt +#endif + +#define pr_fmt(fmt) "trusted_key: " fmt + #define MIN_KEY_SIZE 32 #define MAX_KEY_SIZE 128 #define MAX_BLOB_SIZE 512 @@ -22,6 +28,7 @@ struct trusted_key_payload { unsigned int key_len; unsigned int blob_len; unsigned char migratable; + unsigned char old_format; unsigned char key[MAX_KEY_SIZE + 1]; unsigned char blob[MAX_BLOB_SIZE]; }; @@ -30,6 +37,7 @@ struct trusted_key_options { uint16_t keytype; uint32_t keyhandle; unsigned char keyauth[TPM_DIGEST_SIZE]; + uint32_t blobauth_len; unsigned char blobauth[TPM_DIGEST_SIZE]; uint32_t pcrinfo_len; unsigned char pcrinfo[MAX_PCRINFO_SIZE]; @@ -40,6 +48,53 @@ struct trusted_key_options { uint32_t policyhandle; }; +struct trusted_key_ops { + /* + * flag to indicate if trusted key implementation supports migration + * or not. + */ + unsigned char migratable; + + /* Initialize key interface. */ + int (*init)(void); + + /* Seal a key. */ + int (*seal)(struct trusted_key_payload *p, char *datablob); + + /* Unseal a key. */ + int (*unseal)(struct trusted_key_payload *p, char *datablob); + + /* Get a randomized key. */ + int (*get_random)(unsigned char *key, size_t key_len); + + /* Exit key interface. */ + void (*exit)(void); +}; + +struct trusted_key_source { + char *name; + struct trusted_key_ops *ops; +}; + extern struct key_type key_type_trusted; +#define TRUSTED_DEBUG 0 + +#if TRUSTED_DEBUG +static inline void dump_payload(struct trusted_key_payload *p) +{ + pr_info("key_len %d\n", p->key_len); + print_hex_dump(KERN_INFO, "key ", DUMP_PREFIX_NONE, + 16, 1, p->key, p->key_len, 0); + pr_info("bloblen %d\n", p->blob_len); + print_hex_dump(KERN_INFO, "blob ", DUMP_PREFIX_NONE, + 16, 1, p->blob, p->blob_len, 0); + pr_info("migratable %d\n", p->migratable); +} +#else +static inline void dump_payload(struct trusted_key_payload *p) +{ +} +#endif + #endif /* _KEYS_TRUSTED_TYPE_H */ diff --git a/include/keys/trusted_tee.h b/include/keys/trusted_tee.h new file mode 100644 index 000000000000..151be25a979e --- /dev/null +++ b/include/keys/trusted_tee.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019-2021 Linaro Ltd. + * + * Author: + * Sumit Garg <sumit.garg@linaro.org> + */ + +#ifndef __TEE_TRUSTED_KEY_H +#define __TEE_TRUSTED_KEY_H + +#include <keys/trusted-type.h> + +extern struct trusted_key_ops trusted_key_tee_ops; + +#endif diff --git a/include/keys/trusted_tpm.h b/include/keys/trusted_tpm.h index a56d8e1298f2..7769b726863a 100644 --- a/include/keys/trusted_tpm.h +++ b/include/keys/trusted_tpm.h @@ -16,6 +16,8 @@ #define LOAD32N(buffer, offset) (*(uint32_t *)&buffer[offset]) #define LOAD16(buffer, offset) (ntohs(*(uint16_t *)&buffer[offset])) +extern struct trusted_key_ops trusted_key_tpm_ops; + struct osapsess { uint32_t handle; unsigned char secret[SHA1_DIGEST_SIZE]; @@ -52,30 +54,19 @@ int tpm2_unseal_trusted(struct tpm_chip *chip, #if TPM_DEBUG static inline void dump_options(struct trusted_key_options *o) { - pr_info("trusted_key: sealing key type %d\n", o->keytype); - pr_info("trusted_key: sealing key handle %0X\n", o->keyhandle); - pr_info("trusted_key: pcrlock %d\n", o->pcrlock); - pr_info("trusted_key: pcrinfo %d\n", o->pcrinfo_len); + pr_info("sealing key type %d\n", o->keytype); + pr_info("sealing key handle %0X\n", o->keyhandle); + pr_info("pcrlock %d\n", o->pcrlock); + pr_info("pcrinfo %d\n", o->pcrinfo_len); print_hex_dump(KERN_INFO, "pcrinfo ", DUMP_PREFIX_NONE, 16, 1, o->pcrinfo, o->pcrinfo_len, 0); } -static inline void dump_payload(struct trusted_key_payload *p) -{ - pr_info("trusted_key: key_len %d\n", p->key_len); - print_hex_dump(KERN_INFO, "key ", DUMP_PREFIX_NONE, - 16, 1, p->key, p->key_len, 0); - pr_info("trusted_key: bloblen %d\n", p->blob_len); - print_hex_dump(KERN_INFO, "blob ", DUMP_PREFIX_NONE, - 16, 1, p->blob, p->blob_len, 0); - pr_info("trusted_key: migratable %d\n", p->migratable); -} - static inline void dump_sess(struct osapsess *s) { print_hex_dump(KERN_INFO, "trusted-key: handle ", DUMP_PREFIX_NONE, 16, 1, &s->handle, 4, 0); - pr_info("trusted-key: secret:\n"); + pr_info("secret:\n"); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE, 16, 1, &s->secret, SHA1_DIGEST_SIZE, 0); pr_info("trusted-key: enonce:\n"); @@ -87,7 +78,7 @@ static inline void dump_tpm_buf(unsigned char *buf) { int len; - pr_info("\ntrusted-key: tpm buffer\n"); + pr_info("\ntpm buffer\n"); len = LOAD32(buf, TPM_SIZE_OFFSET); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE, 16, 1, buf, len, 0); } @@ -96,10 +87,6 @@ static inline void dump_options(struct trusted_key_options *o) { } -static inline void dump_payload(struct trusted_key_payload *p) -{ -} - static inline void dump_sess(struct osapsess *s) { } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index fcdaab723916..3bdcfc4401b7 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -222,10 +222,14 @@ void __iomem *__acpi_map_table(unsigned long phys, unsigned long size); void __acpi_unmap_table(void __iomem *map, unsigned long size); int early_acpi_boot_init(void); int acpi_boot_init (void); +void acpi_boot_table_prepare (void); void acpi_boot_table_init (void); int acpi_mps_check (void); int acpi_numa_init (void); +int acpi_locate_initial_tables (void); +void acpi_reserve_initial_tables (void); +void acpi_table_init_complete (void); int acpi_table_init (void); int acpi_table_parse(char *id, acpi_tbl_table_handler handler); int __init acpi_table_parse_entries(char *id, unsigned long table_size, @@ -814,9 +818,12 @@ static inline int acpi_boot_init(void) return 0; } +static inline void acpi_boot_table_prepare(void) +{ +} + static inline void acpi_boot_table_init(void) { - return; } static inline int acpi_mps_check(void) diff --git a/include/linux/armada-37xx-rwtm-mailbox.h b/include/linux/armada-37xx-rwtm-mailbox.h index 57bb54f6767a..ef4bd705eb65 100644 --- a/include/linux/armada-37xx-rwtm-mailbox.h +++ b/include/linux/armada-37xx-rwtm-mailbox.h @@ -2,7 +2,7 @@ /* * rWTM BIU Mailbox driver for Armada 37xx * - * Author: Marek Behun <marek.behun@nic.cz> + * Author: Marek Behún <kabel@kernel.org> */ #ifndef _LINUX_ARMADA_37XX_RWTM_MAILBOX_H_ diff --git a/include/linux/asn1_encoder.h b/include/linux/asn1_encoder.h new file mode 100644 index 000000000000..08cd0c2ad34f --- /dev/null +++ b/include/linux/asn1_encoder.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _LINUX_ASN1_ENCODER_H +#define _LINUX_ASN1_ENCODER_H + +#include <linux/types.h> +#include <linux/asn1.h> +#include <linux/asn1_ber_bytecode.h> +#include <linux/bug.h> + +#define asn1_oid_len(oid) (sizeof(oid)/sizeof(u32)) +unsigned char * +asn1_encode_integer(unsigned char *data, const unsigned char *end_data, + s64 integer); +unsigned char * +asn1_encode_oid(unsigned char *data, const unsigned char *end_data, + u32 oid[], int oid_len); +unsigned char * +asn1_encode_tag(unsigned char *data, const unsigned char *end_data, + u32 tag, const unsigned char *string, int len); +unsigned char * +asn1_encode_octet_string(unsigned char *data, + const unsigned char *end_data, + const unsigned char *string, u32 len); +unsigned char * +asn1_encode_sequence(unsigned char *data, const unsigned char *end_data, + const unsigned char *seq, int len); +unsigned char * +asn1_encode_boolean(unsigned char *data, const unsigned char *end_data, + bool val); + +#endif diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 40bad71865ea..532bcbfc4716 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -476,7 +476,6 @@ struct virtchnl_rss_key { u16 vsi_id; u16 key_len; u8 key[1]; /* RSS hash key, packed bytes */ - u8 pad[1]; }; VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key); @@ -485,7 +484,6 @@ struct virtchnl_rss_lut { u16 vsi_id; u16 lut_entries; u8 lut[1]; /* RSS lookup table */ - u8 pad[1]; }; VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bc6bc8383b43..158aefae1030 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -85,8 +85,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) /* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) -/* request came from our alloc pool */ -#define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) /* runtime pm request */ #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index cccaef1088ea..fdac0534ce79 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -21,6 +21,7 @@ #include <linux/capability.h> #include <linux/sched/mm.h> #include <linux/slab.h> +#include <linux/percpu-refcount.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -39,6 +40,7 @@ struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; struct mem_cgroup; +struct module; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -556,7 +558,8 @@ struct bpf_tramp_progs { * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function */ -int arch_prepare_bpf_trampoline(void *image, void *image_end, +struct bpf_tramp_image; +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_progs *tprogs, void *orig_call); @@ -565,6 +568,8 @@ u64 notrace __bpf_prog_enter(struct bpf_prog *prog); void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start); u64 notrace __bpf_prog_enter_sleepable(struct bpf_prog *prog); void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start); +void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); +void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); struct bpf_ksym { unsigned long start; @@ -583,6 +588,18 @@ enum bpf_tramp_prog_type { BPF_TRAMP_REPLACE, /* more than MAX */ }; +struct bpf_tramp_image { + void *image; + struct bpf_ksym ksym; + struct percpu_ref pcref; + void *ip_after_call; + void *ip_epilogue; + union { + struct rcu_head rcu; + struct work_struct work; + }; +}; + struct bpf_trampoline { /* hlist for trampoline_table */ struct hlist_node hlist; @@ -605,9 +622,9 @@ struct bpf_trampoline { /* Number of attached programs. A counter per kind. */ int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ - void *image; + struct bpf_tramp_image *cur_image; u64 selector; - struct bpf_ksym ksym; + struct module *mod; }; struct bpf_attach_target_info { @@ -691,6 +708,8 @@ void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); +int bpf_jit_charge_modmem(u32 pages); +void bpf_jit_uncharge_modmem(u32 pages); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) @@ -787,7 +806,6 @@ struct bpf_prog_aux { bool func_proto_unreliable; bool sleepable; bool tail_call_reachable; - enum bpf_tramp_prog_type trampoline_prog_type; struct hlist_node tramp_hlist; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; @@ -1093,7 +1111,7 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, _ret; \ }) -#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \ +#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null, set_cg_storage) \ ({ \ struct bpf_prog_array_item *_item; \ struct bpf_prog *_prog; \ @@ -1106,7 +1124,8 @@ int bpf_prog_array_copy(struct bpf_prog_array *old_array, goto _out; \ _item = &_array->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ - bpf_cgroup_storage_set(_item->cgroup_storage); \ + if (set_cg_storage) \ + bpf_cgroup_storage_set(_item->cgroup_storage); \ _ret &= func(_prog, ctx); \ _item++; \ } \ @@ -1153,10 +1172,10 @@ _out: \ }) #define BPF_PROG_RUN_ARRAY(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, false) + __BPF_PROG_RUN_ARRAY(array, ctx, func, false, true) #define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \ - __BPF_PROG_RUN_ARRAY(array, ctx, func, true) + __BPF_PROG_RUN_ARRAY(array, ctx, func, true, false) #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 7f4ac87c0b32..5c641f930caf 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -253,7 +253,11 @@ struct target_type { #define dm_target_passes_integrity(type) ((type)->features & DM_TARGET_PASSES_INTEGRITY) /* - * Indicates that a target supports host-managed zoned block devices. + * Indicates support for zoned block devices: + * - DM_TARGET_ZONED_HM: the target also supports host-managed zoned + * block devices but does not support combining different zoned models. + * - DM_TARGET_MIXED_ZONED_MODEL: the target supports combining multiple + * devices with different zoned models. */ #ifdef CONFIG_BLK_DEV_ZONED #define DM_TARGET_ZONED_HM 0x00000040 @@ -275,6 +279,15 @@ struct target_type { #define DM_TARGET_PASSES_CRYPTO 0x00000100 #define dm_target_passes_crypto(type) ((type)->features & DM_TARGET_PASSES_CRYPTO) +#ifdef CONFIG_BLK_DEV_ZONED +#define DM_TARGET_MIXED_ZONED_MODEL 0x00000200 +#define dm_target_supports_mixed_zoned_model(type) \ + ((type)->features & DM_TARGET_MIXED_ZONED_MODEL) +#else +#define DM_TARGET_MIXED_ZONED_MODEL 0x00000000 +#define dm_target_supports_mixed_zoned_model(type) (false) +#endif + struct dm_target { struct dm_table *table; struct target_type *type; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index ec4cd3921c67..cdca84e6dd6b 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -87,9 +87,7 @@ u32 ethtool_op_get_link(struct net_device *dev); int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti); -/** - * struct ethtool_link_ext_state_info - link extended state and substate. - */ +/* Link extended state and substate. */ struct ethtool_link_ext_state_info { enum ethtool_link_ext_state link_ext_state; union { @@ -129,7 +127,6 @@ struct ethtool_link_ksettings { __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); } link_modes; u32 lanes; - enum ethtool_link_mode_bit_indices link_mode; }; /** @@ -292,6 +289,9 @@ struct ethtool_pause_stats { * do not attach ext_substate attribute to netlink message). If link_ext_state * and link_ext_substate are unknown, return -ENODATA. If not implemented, * link_ext_state and link_ext_substate will not be sent to userspace. + * @get_eeprom_len: Read range of EEPROM addresses for validation of + * @get_eeprom and @set_eeprom requests. + * Returns 0 if device does not support EEPROM access. * @get_eeprom: Read data from the device EEPROM. * Should fill in the magic field. Don't need to check len for zero * or wraparound. Fill in the data argument with the eeprom values @@ -384,6 +384,8 @@ struct ethtool_pause_stats { * @get_module_eeprom: Get the eeprom information from the plug-in module * @get_eee: Get Energy-Efficient (EEE) supported and status. * @set_eee: Set EEE status (enable/disable) as well as LPI timers. + * @get_tunable: Read the value of a driver / device tunable. + * @set_tunable: Set the value of a driver / device tunable. * @get_per_queue_coalesce: Get interrupt coalescing parameters per queue. * It must check that the given queue number is valid. If neither a RX nor * a TX queue has this number, return -EINVAL. If only a RX queue or a TX @@ -547,8 +549,8 @@ struct phy_tdr_config; * @get_sset_count: Get number of strings that @get_strings will write. * @get_strings: Return a set of strings that describe the requested objects * @get_stats: Return extended statistics about the PHY device. - * @start_cable_test - Start a cable test - * @start_cable_test_tdr - Start a Time Domain Reflectometry cable test + * @start_cable_test: Start a cable test + * @start_cable_test_tdr: Start a Time Domain Reflectometry cable test * * All operations are optional (i.e. the function pointer may be set to %NULL) * and callers must take this into account. Callers must hold the RTNL lock. @@ -571,4 +573,12 @@ struct ethtool_phy_ops { */ void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops); +/* + * ethtool_params_from_link_mode - Derive link parameters from a given link mode + * @link_ksettings: Link parameters to be derived from the link mode + * @link_mode: Link mode + */ +void +ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, + enum ethtool_link_mode_bit_indices link_mode); #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/extcon.h b/include/linux/extcon.h index fd183fb9c20f..0c19010da77f 100644 --- a/include/linux/extcon.h +++ b/include/linux/extcon.h @@ -271,6 +271,29 @@ static inline void devm_extcon_unregister_notifier(struct device *dev, struct extcon_dev *edev, unsigned int id, struct notifier_block *nb) { } +static inline int extcon_register_notifier_all(struct extcon_dev *edev, + struct notifier_block *nb) +{ + return 0; +} + +static inline int extcon_unregister_notifier_all(struct extcon_dev *edev, + struct notifier_block *nb) +{ + return 0; +} + +static inline int devm_extcon_register_notifier_all(struct device *dev, + struct extcon_dev *edev, + struct notifier_block *nb) +{ + return 0; +} + +static inline void devm_extcon_unregister_notifier_all(struct device *dev, + struct extcon_dev *edev, + struct notifier_block *nb) { } + static inline struct extcon_dev *extcon_get_extcon_dev(const char *extcon_name) { return ERR_PTR(-ENODEV); diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h index ebc295647581..19781b0f6429 100644 --- a/include/linux/firmware/intel/stratix10-svc-client.h +++ b/include/linux/firmware/intel/stratix10-svc-client.h @@ -56,7 +56,7 @@ * COMMAND_RECONFIG_FLAG_PARTIAL: * Set to FPGA configuration type (full or partial). */ -#define COMMAND_RECONFIG_FLAG_PARTIAL 1 +#define COMMAND_RECONFIG_FLAG_PARTIAL 0 /* * Timeout settings for service clients: diff --git a/include/linux/host1x.h b/include/linux/host1x.h index ce59a6a6a008..9eb77c87a83b 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -320,7 +320,14 @@ static inline struct host1x_device *to_host1x_device(struct device *dev) int host1x_device_init(struct host1x_device *device); int host1x_device_exit(struct host1x_device *device); -int host1x_client_register(struct host1x_client *client); +int __host1x_client_register(struct host1x_client *client, + struct lock_class_key *key); +#define host1x_client_register(class) \ + ({ \ + static struct lock_class_key __key; \ + __host1x_client_register(class, &__key); \ + }) + int host1x_client_unregister(struct host1x_client *client); int host1x_client_suspend(struct host1x_client *client); diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h index 2ad6e92f124a..0bff345c4bc6 100644 --- a/include/linux/hugetlb_cgroup.h +++ b/include/linux/hugetlb_cgroup.h @@ -113,6 +113,11 @@ static inline bool hugetlb_cgroup_disabled(void) return !cgroup_subsys_enabled(hugetlb_cgrp_subsys); } +static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) +{ + css_put(&h_cg->css); +} + extern int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr); extern int hugetlb_cgroup_charge_cgroup_rsvd(int idx, unsigned long nr_pages, @@ -138,7 +143,8 @@ extern void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, extern void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages); + unsigned long nr_pages, + bool region_del); extern void hugetlb_cgroup_file_init(void) __init; extern void hugetlb_cgroup_migrate(struct page *oldhpage, @@ -147,7 +153,8 @@ extern void hugetlb_cgroup_migrate(struct page *oldhpage, #else static inline void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages) + unsigned long nr_pages, + bool region_del) { } @@ -185,6 +192,10 @@ static inline bool hugetlb_cgroup_disabled(void) return true; } +static inline void hugetlb_cgroup_put_rsvd_cgroup(struct hugetlb_cgroup *h_cg) +{ +} + static inline int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 96556c64c95d..10c94a3936ca 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -43,13 +43,14 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan, if (likely(success)) { struct vlan_pcpu_stats *pcpu_stats; - pcpu_stats = this_cpu_ptr(vlan->pcpu_stats); + pcpu_stats = get_cpu_ptr(vlan->pcpu_stats); u64_stats_update_begin(&pcpu_stats->syncp); pcpu_stats->rx_packets++; pcpu_stats->rx_bytes += len; if (multicast) pcpu_stats->rx_multicast++; u64_stats_update_end(&pcpu_stats->syncp); + put_cpu_ptr(vlan->pcpu_stats); } else { this_cpu_inc(vlan->pcpu_stats->rx_errors); } diff --git a/include/linux/kasan.h b/include/linux/kasan.h index b91732bd05d7..14f72ec96492 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -330,7 +330,7 @@ static inline bool kasan_check_byte(const void *address) #endif /* CONFIG_KASAN */ -#if defined(CONFIG_KASAN) && CONFIG_KASAN_STACK +#if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) void kasan_unpoison_task_stack(struct task_struct *task); #else static inline void kasan_unpoison_task_stack(struct task_struct *task) {} diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index 52b1610eae68..c544b70dfbd2 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -28,11 +28,12 @@ /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ #define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 -/* The MV88e6390 Ethernet switch contains embedded PHYs. These PHYs do +/* These Ethernet switch families contain embedded PHYs, but they do * not have a model ID. So the switch driver traps reads to the ID2 * register and returns the switch family ID */ -#define MARVELL_PHY_ID_88E6390 0x01410f90 +#define MARVELL_PHY_ID_88E6341_FAMILY 0x01410f41 +#define MARVELL_PHY_ID_88E6390_FAMILY 0x01410f90 #define MARVELL_PHY_FAMILY_ID(id) ((id) >> 4) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index d13e3cd938b4..5984fff3f175 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -460,7 +460,7 @@ static inline void memblock_free_late(phys_addr_t base, phys_addr_t size) /* * Set the allocation direction to bottom-up or top-down. */ -static inline __init void memblock_set_bottom_up(bool enable) +static inline __init_memblock void memblock_set_bottom_up(bool enable) { memblock.bottom_up = enable; } @@ -470,7 +470,7 @@ static inline __init void memblock_set_bottom_up(bool enable) * if this is true, that said, memblock will allocate memory * in bottom-up direction. */ -static inline __init bool memblock_bottom_up(void) +static inline __init_memblock bool memblock_bottom_up(void) { return memblock.bottom_up; } diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index df5d91c8b2d4..9c68b2da14c6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -437,11 +437,11 @@ struct mlx5_ifc_flow_table_prop_layout_bits { u8 reserved_at_60[0x18]; u8 log_max_ft_num[0x8]; - u8 reserved_at_80[0x18]; + u8 reserved_at_80[0x10]; + u8 log_max_flow_counter[0x8]; u8 log_max_destination[0x8]; - u8 log_max_flow_counter[0x8]; - u8 reserved_at_a8[0x10]; + u8 reserved_at_a0[0x18]; u8 log_max_flow[0x8]; u8 reserved_at_c0[0x40]; @@ -8835,6 +8835,8 @@ struct mlx5_ifc_pplm_reg_bits { u8 fec_override_admin_100g_2x[0x10]; u8 fec_override_admin_50g_1x[0x10]; + + u8 reserved_at_140[0x140]; }; struct mlx5_ifc_ppcnt_reg_bits { @@ -10198,7 +10200,7 @@ struct mlx5_ifc_pbmc_reg_bits { struct mlx5_ifc_bufferx_reg_bits buffer[10]; - u8 reserved_at_2e0[0x40]; + u8 reserved_at_2e0[0x80]; }; struct mlx5_ifc_qtct_reg_bits { diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index d75ef8aa8fac..b7deb790f257 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -547,4 +547,11 @@ static inline const char *mlx5_qp_state_str(int state) } } +static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev) +{ + return !MLX5_CAP_ROCE(dev, qp_ts_format) ? + MLX5_QPC_TIMESTAMP_FORMAT_FREE_RUNNING : + MLX5_QPC_TIMESTAMP_FORMAT_DEFAULT; +} + #endif /* MLX5_QP_H */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 64a71bf20536..8ba434287387 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1461,16 +1461,28 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid) #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) +/* + * KASAN per-page tags are stored xor'ed with 0xff. This allows to avoid + * setting tags for all pages to native kernel tag value 0xff, as the default + * value 0x00 maps to 0xff. + */ + static inline u8 page_kasan_tag(const struct page *page) { - if (kasan_enabled()) - return (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; - return 0xff; + u8 tag = 0xff; + + if (kasan_enabled()) { + tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK; + tag ^= 0xff; + } + + return tag; } static inline void page_kasan_tag_set(struct page *page, u8 tag) { if (kasan_enabled()) { + tag ^= 0xff; page->flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT); page->flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT; } diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index b8200782dede..1a6a9eb6d3fa 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -169,11 +169,11 @@ struct mmu_notifier_ops { * the last refcount is dropped. * * If blockable argument is set to false then the callback cannot - * sleep and has to return with -EAGAIN. 0 should be returned - * otherwise. Please note that if invalidate_range_start approves - * a non-blocking behavior then the same applies to - * invalidate_range_end. - * + * sleep and has to return with -EAGAIN if sleeping would be required. + * 0 should be returned otherwise. Please note that notifiers that can + * fail invalidate_range_start are not allowed to implement + * invalidate_range_end, as there is no mechanism for informing the + * notifier that its start failed. */ int (*invalidate_range_start)(struct mmu_notifier *subscription, const struct mmu_notifier_range *range); diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h index 490db6886dcc..79184948fab4 100644 --- a/include/linux/moxtet.h +++ b/include/linux/moxtet.h @@ -2,7 +2,7 @@ /* * Turris Mox module configuration bus driver * - * Copyright (C) 2019 Marek Behun <marek.behun@nic.cz> + * Copyright (C) 2019 Marek Behún <kabel@kernel.org> */ #ifndef __LINUX_MOXTET_H diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 0cd631a19727..515cff77a4f4 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -185,7 +185,7 @@ extern void mutex_lock_io(struct mutex *lock); # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock) # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock) # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) -# define mutex_lock_io_nested(lock, subclass) mutex_lock(lock) +# define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock) #endif /* diff --git a/include/linux/nd.h b/include/linux/nd.h index cec526c8043d..ee9ad76afbba 100644 --- a/include/linux/nd.h +++ b/include/linux/nd.h @@ -11,6 +11,7 @@ enum nvdimm_event { NVDIMM_REVALIDATE_POISON, + NVDIMM_REVALIDATE_REGION, }; enum nvdimm_claim_class { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5b67ea89d5f2..87a5d186faff 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -360,6 +360,7 @@ enum { NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ + NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */ }; enum { @@ -372,6 +373,7 @@ enum { NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), + NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED), }; enum gro_result { diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 8ebb64193757..8ec48466410a 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -227,7 +227,7 @@ struct xt_table { unsigned int valid_hooks; /* Man behind the curtain... */ - struct xt_table_info __rcu *private; + struct xt_table_info *private; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; @@ -376,7 +376,7 @@ static inline unsigned int xt_write_recseq_begin(void) * since addend is most likely 1 */ __this_cpu_add(xt_recseq.sequence, addend); - smp_wmb(); + smp_mb(); return addend; } @@ -448,9 +448,6 @@ xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); -struct xt_table_info -*xt_table_get_private_protected(const struct xt_table *table); - #ifdef CONFIG_COMPAT #include <net/compat.h> diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index 7d3537c40ec9..26a13294318c 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -52,8 +52,9 @@ extern void *arpt_alloc_initial_table(const struct xt_table *); int arpt_register_table(struct net *net, const struct xt_table *table, const struct arpt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); -void arpt_unregister_table(struct net *net, struct xt_table *table, - const struct nf_hook_ops *ops); +void arpt_unregister_table(struct net *net, struct xt_table *table); +void arpt_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); extern unsigned int arpt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 2f5c4e6ecd8a..3a956145a25c 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -110,8 +110,9 @@ extern int ebt_register_table(struct net *net, const struct ebt_table *table, const struct nf_hook_ops *ops, struct ebt_table **res); -extern void ebt_unregister_table(struct net *net, struct ebt_table *table, - const struct nf_hook_ops *); +extern void ebt_unregister_table(struct net *net, struct ebt_table *table); +void ebt_unregister_table_pre_exit(struct net *net, const char *tablename, + const struct nf_hook_ops *ops); extern unsigned int ebt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct ebt_table *table); diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h index 4462ed2c18cd..461b7aa587ba 100644 --- a/include/linux/oid_registry.h +++ b/include/linux/oid_registry.h @@ -19,8 +19,14 @@ enum OID { OID_id_dsa_with_sha1, /* 1.2.840.10030.4.3 */ OID_id_dsa, /* 1.2.840.10040.4.1 */ - OID_id_ecdsa_with_sha1, /* 1.2.840.10045.4.1 */ OID_id_ecPublicKey, /* 1.2.840.10045.2.1 */ + OID_id_prime192v1, /* 1.2.840.10045.3.1.1 */ + OID_id_prime256v1, /* 1.2.840.10045.3.1.7 */ + OID_id_ecdsa_with_sha1, /* 1.2.840.10045.4.1 */ + OID_id_ecdsa_with_sha224, /* 1.2.840.10045.4.3.1 */ + OID_id_ecdsa_with_sha256, /* 1.2.840.10045.4.3.2 */ + OID_id_ecdsa_with_sha384, /* 1.2.840.10045.4.3.3 */ + OID_id_ecdsa_with_sha512, /* 1.2.840.10045.4.3.4 */ /* PKCS#1 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-1(1)} */ OID_rsaEncryption, /* 1.2.840.113549.1.1.1 */ @@ -58,6 +64,7 @@ enum OID { OID_certAuthInfoAccess, /* 1.3.6.1.5.5.7.1.1 */ OID_sha1, /* 1.3.14.3.2.26 */ + OID_id_ansip384r1, /* 1.3.132.0.34 */ OID_sha256, /* 2.16.840.1.101.3.4.2.1 */ OID_sha384, /* 2.16.840.1.101.3.4.2.2 */ OID_sha512, /* 2.16.840.1.101.3.4.2.3 */ @@ -113,10 +120,16 @@ enum OID { OID_SM2_with_SM3, /* 1.2.156.10197.1.501 */ OID_sm3WithRSAEncryption, /* 1.2.156.10197.1.504 */ + /* TCG defined OIDS for TPM based keys */ + OID_TPMLoadableKey, /* 2.23.133.10.1.3 */ + OID_TPMImportableKey, /* 2.23.133.10.1.4 */ + OID_TPMSealedData, /* 2.23.133.10.1.5 */ + OID__NR }; extern enum OID look_up_OID(const void *data, size_t datasize); +extern int parse_OID(const void *data, size_t datasize, enum OID *oid); extern int sprint_oid(const void *, size_t, char *, size_t); extern int sprint_OID(enum OID, char *, size_t); diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 20225b067583..8c9947fd62f3 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -559,7 +559,6 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, return pgoff; } -/* This has the same layout as wait_bit_key - see fs/cachefiles/rdwr.c */ struct wait_page_key { struct page *page; int bit_nr; @@ -683,6 +682,7 @@ static inline int wait_on_page_locked_killable(struct page *page) int put_and_wait_on_page_locked(struct page *page, int state); void wait_on_page_writeback(struct page *page); +int wait_on_page_writeback_killable(struct page *page); extern void end_page_writeback(struct page *page); void wait_for_stable_page(struct page *page); diff --git a/include/linux/platform_data/gpio-omap.h b/include/linux/platform_data/gpio-omap.h index 8b30b14b47d3..f377817ce75c 100644 --- a/include/linux/platform_data/gpio-omap.h +++ b/include/linux/platform_data/gpio-omap.h @@ -85,6 +85,7 @@ * omap2+ specific GPIO registers */ #define OMAP24XX_GPIO_REVISION 0x0000 +#define OMAP24XX_GPIO_SYSCONFIG 0x0010 #define OMAP24XX_GPIO_IRQSTATUS1 0x0018 #define OMAP24XX_GPIO_IRQSTATUS2 0x0028 #define OMAP24XX_GPIO_IRQENABLE2 0x002c @@ -108,6 +109,7 @@ #define OMAP24XX_GPIO_SETDATAOUT 0x0094 #define OMAP4_GPIO_REVISION 0x0000 +#define OMAP4_GPIO_SYSCONFIG 0x0010 #define OMAP4_GPIO_EOI 0x0020 #define OMAP4_GPIO_IRQSTATUSRAW0 0x0024 #define OMAP4_GPIO_IRQSTATUSRAW1 0x0028 @@ -148,6 +150,7 @@ #ifndef __ASSEMBLER__ struct omap_gpio_reg_offs { u16 revision; + u16 sysconfig; u16 direction; u16 datain; u16 dataout; diff --git a/include/linux/qcom-geni-se.h b/include/linux/qcom-geni-se.h index ec2ad4b0fe14..c4fdb4463f7d 100644 --- a/include/linux/qcom-geni-se.h +++ b/include/linux/qcom-geni-se.h @@ -460,7 +460,5 @@ void geni_icc_set_tag(struct geni_se *se, u32 tag); int geni_icc_enable(struct geni_se *se); int geni_icc_disable(struct geni_se *se); - -void geni_remove_earlycon_icc_vote(void); #endif #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6d0a33d1c0db..f2c9ee71cb2c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -285,6 +285,7 @@ struct nf_bridge_info { struct tc_skb_ext { __u32 chain; __u16 mru; + bool post_ct; }; #endif diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 8edbbf5f2f93..822c048934e3 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -349,8 +349,13 @@ static inline void sk_psock_update_proto(struct sock *sk, static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { - sk->sk_prot->unhash = psock->saved_unhash; if (inet_csk_has_ulp(sk)) { + /* TLS does not have an unhash proto in SW cases, but we need + * to ensure we stop using the sock_map unhash routine because + * the associated psock is being removed. So use the original + * unhash handler. + */ + WRITE_ONCE(sk->sk_prot->unhash, psock->saved_unhash); tcp_update_ulp(sk, psock->sk_proto, psock->saved_write_space); } else { sk->sk_write_space = psock->saved_write_space; diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 50e2df30b0aa..9edecb494e9e 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -52,8 +52,27 @@ typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr); */ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs); + +/** + * arch_stack_walk_reliable - Architecture specific function to walk the + * stack reliably + * + * @consume_entry: Callback which is invoked by the architecture code for + * each entry. + * @cookie: Caller supplied pointer which is handed back to + * @consume_entry + * @task: Pointer to a task struct, can be NULL + * + * This function returns an error if it detects any unreliable + * features of the stack. Otherwise it guarantees that the stack + * trace is reliable. + * + * If the task is not 'current', the caller *must* ensure the task is + * inactive and its stack is pinned. + */ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task); + void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, const struct pt_regs *regs); diff --git a/include/linux/static_call.h b/include/linux/static_call.h index 85ecc789f4ff..e01b61ab86b1 100644 --- a/include/linux/static_call.h +++ b/include/linux/static_call.h @@ -20,6 +20,7 @@ * static_call(name)(args...); * static_call_cond(name)(args...); * static_call_update(name, func); + * static_call_query(name); * * Usage example: * @@ -91,6 +92,10 @@ * * which will include the required value tests to avoid NULL-pointer * dereferences. + * + * To query which function is currently set to be called, use: + * + * func = static_call_query(name); */ #include <linux/types.h> @@ -118,6 +123,8 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool STATIC_CALL_TRAMP_ADDR(name), func); \ }) +#define static_call_query(name) (READ_ONCE(STATIC_CALL_KEY(name).func)) + #ifdef CONFIG_HAVE_STATIC_CALL_INLINE extern int __init static_call_init(void); @@ -128,16 +135,6 @@ struct static_call_mod { struct static_call_site *sites; }; -struct static_call_key { - void *func; - union { - /* bit 0: 0 = mods, 1 = sites */ - unsigned long type; - struct static_call_mod *mods; - struct static_call_site *sites; - }; -}; - /* For finding the key associated with a trampoline */ struct static_call_tramp_key { s32 tramp; @@ -187,10 +184,6 @@ extern long __static_call_return0(void); static inline int static_call_init(void) { return 0; } -struct static_call_key { - void *func; -}; - #define __DEFINE_STATIC_CALL(name, _func, _func_init) \ DECLARE_STATIC_CALL(name, _func); \ struct static_call_key STATIC_CALL_KEY(name) = { \ @@ -205,6 +198,7 @@ struct static_call_key { }; \ ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) + #define static_call_cond(name) (void)__static_call(name) static inline @@ -243,10 +237,6 @@ static inline long __static_call_return0(void) static inline int static_call_init(void) { return 0; } -struct static_call_key { - void *func; -}; - static inline long __static_call_return0(void) { return 0; diff --git a/include/linux/static_call_types.h b/include/linux/static_call_types.h index ae5662d368b9..5a00b8b2cf9f 100644 --- a/include/linux/static_call_types.h +++ b/include/linux/static_call_types.h @@ -58,11 +58,25 @@ struct static_call_site { __raw_static_call(name); \ }) +struct static_call_key { + void *func; + union { + /* bit 0: 0 = mods, 1 = sites */ + unsigned long type; + struct static_call_mod *mods; + struct static_call_site *sites; + }; +}; + #else /* !CONFIG_HAVE_STATIC_CALL_INLINE */ #define __STATIC_CALL_ADDRESSABLE(name) #define __static_call(name) __raw_static_call(name) +struct static_call_key { + void *func; +}; + #endif /* CONFIG_HAVE_STATIC_CALL_INLINE */ #ifdef MODULE @@ -77,6 +91,10 @@ struct static_call_site { #else +struct static_call_key { + void *func; +}; + #define static_call(name) \ ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) diff --git a/include/linux/tpm.h b/include/linux/tpm.h index 543aa3b1dedc..aa11fe323c56 100644 --- a/include/linux/tpm.h +++ b/include/linux/tpm.h @@ -305,6 +305,8 @@ struct tpm_buf { }; enum tpm2_object_attributes { + TPM2_OA_FIXED_TPM = BIT(1), + TPM2_OA_FIXED_PARENT = BIT(4), TPM2_OA_USER_WITH_AUTH = BIT(6), }; diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 64cf8ebdc4ec..f6c5f784be5a 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -63,6 +63,9 @@ struct user_namespace { kgid_t group; struct ns_common ns; unsigned long flags; + /* parent_could_setfcap: true if the creator if this ns had CAP_SETFCAP + * in its effective capability set at the child ns creation time. */ + bool parent_could_setfcap; #ifdef CONFIG_KEYS /* List of joinable keyrings in this namespace. Modification access of diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h index 073a9e0ec07d..ad970416260d 100644 --- a/include/linux/usermode_driver.h +++ b/include/linux/usermode_driver.h @@ -14,5 +14,6 @@ struct umd_info { int umd_load_blob(struct umd_info *info, const void *data, size_t len); int umd_unload_blob(struct umd_info *info); int fork_usermode_driver(struct umd_info *info); +void umd_cleanup_helper(struct umd_info *info); #endif /* __LINUX_USERMODE_DRIVER_H__ */ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 6b5fcfa1e555..b465f8f3e554 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -62,15 +62,21 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb, return -EINVAL; } + skb_reset_mac_header(skb); + if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { - u16 start = __virtio16_to_cpu(little_endian, hdr->csum_start); - u16 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); + u32 start = __virtio16_to_cpu(little_endian, hdr->csum_start); + u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset); + u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16)); + + if (!pskb_may_pull(skb, needed)) + return -EINVAL; if (!skb_partial_csum_set(skb, start, off)) return -EINVAL; p_off = skb_transport_offset(skb) + thlen; - if (p_off > skb_headlen(skb)) + if (!pskb_may_pull(skb, p_off)) return -EINVAL; } else { /* gso packets without NEEDS_CSUM do not set transport_offset. @@ -100,14 +106,14 @@ retry: } p_off = keys.control.thoff + thlen; - if (p_off > skb_headlen(skb) || + if (!pskb_may_pull(skb, p_off) || keys.basic.ip_proto != ip_proto) return -EINVAL; skb_set_transport_header(skb, keys.control.thoff); } else if (gso_type) { p_off = thlen; - if (p_off > skb_headlen(skb)) + if (!pskb_may_pull(skb, p_off)) return -EINVAL; } } diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 92c0160b3352..a91e3d90df8a 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -229,9 +229,10 @@ static inline int xa_err(void *entry) * * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. - * Two common ranges are predefined for you: + * Three common ranges are predefined for you: * * xa_limit_32b - [0 - UINT_MAX] * * xa_limit_31b - [0 - INT_MAX] + * * xa_limit_16b - [0 - USHRT_MAX] */ struct xa_limit { u32 max; @@ -242,6 +243,7 @@ struct xa_limit { #define xa_limit_32b XA_LIMIT(0, UINT_MAX) #define xa_limit_31b XA_LIMIT(0, INT_MAX) +#define xa_limit_16b XA_LIMIT(0, USHRT_MAX) typedef unsigned __bitwise xa_mark_t; #define XA_MARK_0 ((__force xa_mark_t)0U) diff --git a/include/net/act_api.h b/include/net/act_api.h index 2bf3092ae7ec..086b291e9530 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -170,12 +170,7 @@ void tcf_idr_insert_many(struct tc_action *actions[]); 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); -int __tcf_idr_release(struct tc_action *a, bool bind, bool strict); - -static inline int tcf_idr_release(struct tc_action *a, bool bind) -{ - return __tcf_idr_release(a, bind, false); -} +int tcf_idr_release(struct tc_action *a, bool bind); int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops); int tcf_unregister_action(struct tc_action_ops *a, @@ -185,7 +180,7 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int nr_actions, struct tcf_result *res); int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, - struct tc_action *actions[], size_t *attr_size, + struct tc_action *actions[], int init_res[], size_t *attr_size, bool rtnl_held, struct netlink_ext_ack *extack); struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, bool rtnl_held, @@ -193,7 +188,8 @@ struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, 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, - struct tc_action_ops *ops, bool rtnl_held, + struct tc_action_ops *a_o, int *init_res, + bool rtnl_held, struct netlink_ext_ack *extack); int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind, int ref, bool terse); diff --git a/include/net/dst.h b/include/net/dst.h index 26f134ad3a25..75b1e734e9c2 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -550,4 +550,15 @@ static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu) dst->ops->update_pmtu(dst, NULL, skb, mtu, false); } +struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie); +void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu, bool confirm_neigh); +void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb); +u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old); +struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr); +unsigned int dst_blackhole_mtu(const struct dst_entry *dst); + #endif /* _NET_DST_H */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 10a625760de9..3c8c59471bc1 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog; } -void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); +bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); static inline void inet_csk_prepare_for_destroy_sock(struct sock *sk) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index fdec57d862b7..5aaced6bf13e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1536,6 +1536,7 @@ struct nft_trans_flowtable { struct nft_flowtable *flowtable; bool update; struct list_head hook_list; + u32 flags; }; #define nft_trans_flowtable(trans) \ @@ -1544,6 +1545,8 @@ struct nft_trans_flowtable { (((struct nft_trans_flowtable *)trans->data)->update) #define nft_trans_flowtable_hooks(trans) \ (((struct nft_trans_flowtable *)trans->data)->hook_list) +#define nft_trans_flowtable_flags(trans) \ + (((struct nft_trans_flowtable *)trans->data)->flags) int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 59f45b1e9dac..e816b6a3ef2b 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -72,7 +72,9 @@ struct netns_xfrm { #if IS_ENABLED(CONFIG_IPV6) struct dst_ops xfrm6_dst_ops; #endif - spinlock_t xfrm_state_lock; + spinlock_t xfrm_state_lock; + seqcount_spinlock_t xfrm_state_hash_generation; + spinlock_t xfrm_policy_lock; struct mutex xfrm_cfg_mutex; }; diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 7bc057aee40b..a10a319d7eb2 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -410,6 +410,7 @@ static inline struct fib_nh *fib_info_nh(struct fib_info *fi, int nhsel) int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg, struct netlink_ext_ack *extack); +/* Caller should either hold rcu_read_lock(), or RTNL. */ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) { struct nh_info *nhi; @@ -430,6 +431,29 @@ static inline struct fib6_nh *nexthop_fib6_nh(struct nexthop *nh) return NULL; } +/* Variant of nexthop_fib6_nh(). + * Caller should either hold rcu_read_lock_bh(), or RTNL. + */ +static inline struct fib6_nh *nexthop_fib6_nh_bh(struct nexthop *nh) +{ + struct nh_info *nhi; + + if (nh->is_group) { + struct nh_group *nh_grp; + + nh_grp = rcu_dereference_bh_rtnl(nh->nh_grp); + nh = nexthop_mpath_select(nh_grp, 0); + if (!nh) + return NULL; + } + + nhi = rcu_dereference_bh_rtnl(nh->nh_info); + if (nhi->family == AF_INET6) + return &nhi->fib6_nh; + + return NULL; +} + static inline struct net_device *fib6_info_nh_dev(struct fib6_info *f6i) { struct fib6_nh *fib6_nh; diff --git a/include/net/red.h b/include/net/red.h index 932f0d79d60c..be11dbd26492 100644 --- a/include/net/red.h +++ b/include/net/red.h @@ -168,16 +168,24 @@ static inline void red_set_vars(struct red_vars *v) v->qcount = -1; } -static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, u8 Scell_log) +static inline bool red_check_params(u32 qth_min, u32 qth_max, u8 Wlog, + u8 Scell_log, u8 *stab) { - if (fls(qth_min) + Wlog > 32) + if (fls(qth_min) + Wlog >= 32) return false; - if (fls(qth_max) + Wlog > 32) + if (fls(qth_max) + Wlog >= 32) return false; if (Scell_log >= 32) return false; if (qth_max < qth_min) return false; + if (stab) { + int i; + + for (i = 0; i < RED_STAB_SIZE; i++) + if (stab[i] >= 32) + return false; + } return true; } @@ -287,7 +295,7 @@ static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms int shift; /* - * The problem: ideally, average length queue recalcultion should + * The problem: ideally, average length queue recalculation should * be done over constant clock intervals. This is too expensive, so * that the calculation is driven by outgoing packets. * When the queue is idle we have to model this clock by hand. diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index e2091bb2b3a8..479f60ef54c0 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -33,6 +33,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh) * * @list: Used internally * @kind: Identifier + * @netns_refund: Physical device, move to init_net on netns exit * @maxtype: Highest device specific netlink attribute number * @policy: Netlink policy for device specific attribute validation * @validate: Optional validation function for netlink/changelink parameters @@ -64,6 +65,7 @@ struct rtnl_link_ops { size_t priv_size; void (*setup)(struct net_device *dev); + bool netns_refund; unsigned int maxtype; const struct nla_policy *policy; int (*validate)(struct nlattr *tb[], @@ -145,8 +147,8 @@ struct rtnl_af_ops { int (*validate_link_af)(const struct net_device *dev, const struct nlattr *attr); int (*set_link_af)(struct net_device *dev, - const struct nlattr *attr); - + const struct nlattr *attr, + struct netlink_ext_ack *extack); int (*fill_stats_af)(struct sk_buff *skb, const struct net_device *dev); size_t (*get_stats_af_size)(const struct net_device *dev); diff --git a/include/net/sock.h b/include/net/sock.h index 636810ddcd9b..8487f58da36d 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -934,6 +934,10 @@ static inline void sk_acceptq_added(struct sock *sk) WRITE_ONCE(sk->sk_ack_backlog, sk->sk_ack_backlog + 1); } +/* Note: If you think the test should be: + * return READ_ONCE(sk->sk_ack_backlog) >= READ_ONCE(sk->sk_max_ack_backlog); + * Then please take a look at commit 64a146513f8f ("[NET]: Revert incorrect accept queue backlog changes.") + */ static inline bool sk_acceptq_is_full(const struct sock *sk) { return READ_ONCE(sk->sk_ack_backlog) > READ_ONCE(sk->sk_max_ack_backlog); @@ -2221,6 +2225,15 @@ static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk) sk_mem_charge(sk, skb->truesize); } +static inline void skb_set_owner_sk_safe(struct sk_buff *skb, struct sock *sk) +{ + if (sk && refcount_inc_not_zero(&sk->sk_refcnt)) { + skb_orphan(skb); + skb->destructor = sock_efree; + skb->sk = sk; + } +} + void sk_reset_timer(struct sock *sk, struct timer_list *timer, unsigned long expires); diff --git a/include/net/xfrm.h b/include/net/xfrm.h index b2a06f10b62c..c58a6d4eb610 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1097,7 +1097,7 @@ static inline int __xfrm_policy_check2(struct sock *sk, int dir, return __xfrm_policy_check(sk, ndir, skb, family); return (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) || - (skb_dst(skb)->flags & DST_NOPOLICY) || + (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || __xfrm_policy_check(sk, ndir, skb, family); } @@ -1557,7 +1557,7 @@ int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, int xfrm_trans_queue(struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)); -int xfrm_output_resume(struct sk_buff *skb, int err); +int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err); int xfrm_output(struct sock *sk, struct sk_buff *skb); #if IS_ENABLED(CONFIG_NET_PKTGEN) diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index 8a26a2ffa952..fc5a39839b4b 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -193,6 +193,7 @@ enum iscsi_connection_state { ISCSI_CONN_UP = 0, ISCSI_CONN_DOWN, ISCSI_CONN_FAILED, + ISCSI_CONN_BOUND, }; struct iscsi_cls_conn { diff --git a/include/trace/events/random.h b/include/trace/events/random.h index 9570a10cb949..3d7b432ca5f3 100644 --- a/include/trace/events/random.h +++ b/include/trace/events/random.h @@ -85,28 +85,6 @@ TRACE_EVENT(credit_entropy_bits, __entry->entropy_count, (void *)__entry->IP) ); -TRACE_EVENT(push_to_pool, - TP_PROTO(const char *pool_name, int pool_bits, int input_bits), - - TP_ARGS(pool_name, pool_bits, input_bits), - - TP_STRUCT__entry( - __field( const char *, pool_name ) - __field( int, pool_bits ) - __field( int, input_bits ) - ), - - TP_fast_assign( - __entry->pool_name = pool_name; - __entry->pool_bits = pool_bits; - __entry->input_bits = input_bits; - ), - - TP_printk("%s: pool_bits %d input_pool_bits %d", - __entry->pool_name, __entry->pool_bits, - __entry->input_bits) -); - TRACE_EVENT(debit_entropy, TP_PROTO(const char *pool_name, int debit_bits), @@ -161,35 +139,6 @@ TRACE_EVENT(add_disk_randomness, MINOR(__entry->dev), __entry->input_bits) ); -TRACE_EVENT(xfer_secondary_pool, - TP_PROTO(const char *pool_name, int xfer_bits, int request_bits, - int pool_entropy, int input_entropy), - - TP_ARGS(pool_name, xfer_bits, request_bits, pool_entropy, - input_entropy), - - TP_STRUCT__entry( - __field( const char *, pool_name ) - __field( int, xfer_bits ) - __field( int, request_bits ) - __field( int, pool_entropy ) - __field( int, input_entropy ) - ), - - TP_fast_assign( - __entry->pool_name = pool_name; - __entry->xfer_bits = xfer_bits; - __entry->request_bits = request_bits; - __entry->pool_entropy = pool_entropy; - __entry->input_entropy = input_entropy; - ), - - TP_printk("pool %s xfer_bits %d request_bits %d pool_entropy %d " - "input_entropy %d", __entry->pool_name, __entry->xfer_bits, - __entry->request_bits, __entry->pool_entropy, - __entry->input_entropy) -); - DECLARE_EVENT_CLASS(random__get_random_bytes, TP_PROTO(int nbytes, unsigned long IP), @@ -253,38 +202,6 @@ DEFINE_EVENT(random__extract_entropy, extract_entropy, TP_ARGS(pool_name, nbytes, entropy_count, IP) ); -DEFINE_EVENT(random__extract_entropy, extract_entropy_user, - TP_PROTO(const char *pool_name, int nbytes, int entropy_count, - unsigned long IP), - - TP_ARGS(pool_name, nbytes, entropy_count, IP) -); - -TRACE_EVENT(random_read, - TP_PROTO(int got_bits, int need_bits, int pool_left, int input_left), - - TP_ARGS(got_bits, need_bits, pool_left, input_left), - - TP_STRUCT__entry( - __field( int, got_bits ) - __field( int, need_bits ) - __field( int, pool_left ) - __field( int, input_left ) - ), - - TP_fast_assign( - __entry->got_bits = got_bits; - __entry->need_bits = need_bits; - __entry->pool_left = pool_left; - __entry->input_left = input_left; - ), - - TP_printk("got_bits %d still_needed_bits %d " - "blocking_pool_entropy_left %d input_entropy_left %d", - __entry->got_bits, __entry->got_bits, __entry->pool_left, - __entry->input_left) -); - TRACE_EVENT(urandom_read, TP_PROTO(int got_bits, int pool_left, int input_left), diff --git a/include/uapi/linux/blkpg.h b/include/uapi/linux/blkpg.h index ac6474e4f29d..d0a64ee97c6d 100644 --- a/include/uapi/linux/blkpg.h +++ b/include/uapi/linux/blkpg.h @@ -2,29 +2,6 @@ #ifndef _UAPI__LINUX_BLKPG_H #define _UAPI__LINUX_BLKPG_H -/* - * Partition table and disk geometry handling - * - * A single ioctl with lots of subfunctions: - * - * Device number stuff: - * get_whole_disk() (given the device number of a partition, - * find the device number of the encompassing disk) - * get_all_partitions() (given the device number of a disk, return the - * device numbers of all its known partitions) - * - * Partition stuff: - * add_partition() - * delete_partition() - * test_partition_in_use() (also for test_disk_in_use) - * - * Geometry stuff: - * get_geometry() - * set_geometry() - * get_bios_drivedata() - * - * For today, only the partition stuff - aeb, 990515 - */ #include <linux/compiler.h> #include <linux/ioctl.h> @@ -52,9 +29,8 @@ struct blkpg_partition { long long start; /* starting offset in bytes */ long long length; /* length in bytes */ int pno; /* partition number */ - char devname[BLKPG_DEVNAMELTH]; /* partition name, like sda5 or c0d1p2, - to be used in kernel messages */ - char volname[BLKPG_VOLNAMELTH]; /* volume label */ + char devname[BLKPG_DEVNAMELTH]; /* unused / ignored */ + char volname[BLKPG_VOLNAMELTH]; /* unused / ignore */ }; #endif /* _UAPI__LINUX_BLKPG_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 79c893310492..4ba4ef0ff63a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -3850,7 +3850,7 @@ union bpf_attr { * * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags) * Description - * Check ctx packet size against exceeding MTU of net device (based + * Check packet size against exceeding MTU of net device (based * on *ifindex*). This helper will likely be used in combination * with helpers that adjust/change the packet size. * @@ -3867,6 +3867,14 @@ union bpf_attr { * against the current net device. This is practical if this isn't * used prior to redirect. * + * On input *mtu_len* must be a valid pointer, else verifier will + * reject BPF program. If the value *mtu_len* is initialized to + * zero then the ctx packet size is use. When value *mtu_len* is + * provided as input this specify the L3 length that the MTU check + * is done against. Remember XDP and TC length operate at L2, but + * this value is L3 as this correlate to MTU and IP-header tot_len + * values which are L3 (similar behavior as bpf_fib_lookup). + * * The Linux kernel route table can configure MTUs on a more * specific per route level, which is not provided by this helper. * For route level MTU checks use the **bpf_fib_lookup**\ () @@ -3891,11 +3899,9 @@ union bpf_attr { * * On return *mtu_len* pointer contains the MTU value of the net * device. Remember the net device configured MTU is the L3 size, - * which is returned here and XDP and TX length operate at L2. + * which is returned here and XDP and TC length operate at L2. * Helper take this into account for you, but remember when using - * MTU value in your BPF-code. On input *mtu_len* must be a valid - * pointer and be initialized (to zero), else verifier will reject - * BPF program. + * MTU value in your BPF-code. * * Return * * 0 on success, and populate MTU value in *mtu_len* pointer. diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h index f75238ac6dce..c7535352fef6 100644 --- a/include/uapi/linux/can.h +++ b/include/uapi/linux/can.h @@ -113,7 +113,7 @@ struct can_frame { */ __u8 len; __u8 can_dlc; /* deprecated */ - }; + } __attribute__((packed)); /* disable padding added in some ABIs */ __u8 __pad; /* padding */ __u8 __res0; /* reserved / padding */ __u8 len8_dlc; /* optional DLC for 8 byte payload length (9 .. 15) */ diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index c6ca33034147..2ddb4226cd23 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -335,7 +335,8 @@ struct vfs_ns_cap_data { #define CAP_AUDIT_CONTROL 30 -/* Set or remove capabilities on files */ +/* Set or remove capabilities on files. + Map uid=0 into a child user namespace. */ #define CAP_SETFCAP 31 diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index cde753bb2093..5afea692a3f7 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -26,6 +26,14 @@ * have the same layout for 32-bit and 64-bit userland. */ +/* Note on reserved space. + * Reserved fields must not be accessed directly by user space because + * they may be replaced by a different field in the future. They must + * be initialized to zero before making the request, e.g. via memset + * of the entire structure or implicitly by not being set in a structure + * initializer. + */ + /** * struct ethtool_cmd - DEPRECATED, link control and status * This structure is DEPRECATED, please use struct ethtool_link_settings. @@ -67,6 +75,7 @@ * and other link features that the link partner advertised * through autonegotiation; 0 if unknown or not applicable. * Read-only. + * @reserved: Reserved for future use; see the note on reserved space. * * The link speed in Mbps is split between @speed and @speed_hi. Use * the ethtool_cmd_speed() and ethtool_cmd_speed_set() functions to @@ -155,6 +164,7 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep) * @bus_info: Device bus address. This should match the dev_name() * string for the underlying bus device, if there is one. May be * an empty string. + * @reserved2: Reserved for future use; see the note on reserved space. * @n_priv_flags: Number of flags valid for %ETHTOOL_GPFLAGS and * %ETHTOOL_SPFLAGS commands; also the number of strings in the * %ETH_SS_PRIV_FLAGS set @@ -356,6 +366,7 @@ struct ethtool_eeprom { * @tx_lpi_timer: Time in microseconds the interface delays prior to asserting * its tx lpi (after reaching 'idle' state). Effective only when eee * was negotiated and tx_lpi_enabled was set. + * @reserved: Reserved for future use; see the note on reserved space. */ struct ethtool_eee { __u32 cmd; @@ -374,6 +385,7 @@ struct ethtool_eee { * @cmd: %ETHTOOL_GMODULEINFO * @type: Standard the module information conforms to %ETH_MODULE_SFF_xxxx * @eeprom_len: Length of the eeprom + * @reserved: Reserved for future use; see the note on reserved space. * * This structure is used to return the information to * properly size memory for a subsequent call to %ETHTOOL_GMODULEEEPROM. @@ -579,9 +591,7 @@ struct ethtool_pauseparam { __u32 tx_pause; }; -/** - * enum ethtool_link_ext_state - link extended state - */ +/* Link extended state */ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_AUTONEG, ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE, @@ -595,10 +605,7 @@ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_OVERHEAT, }; -/** - * enum ethtool_link_ext_substate_autoneg - more information in addition to - * ETHTOOL_LINK_EXT_STATE_AUTONEG. - */ +/* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */ enum ethtool_link_ext_substate_autoneg { ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_PARTNER_DETECTED = 1, ETHTOOL_LINK_EXT_SUBSTATE_AN_ACK_NOT_RECEIVED, @@ -608,9 +615,7 @@ enum ethtool_link_ext_substate_autoneg { ETHTOOL_LINK_EXT_SUBSTATE_AN_NO_HCD, }; -/** - * enum ethtool_link_ext_substate_link_training - more information in addition to - * ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE. +/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_TRAINING_FAILURE. */ enum ethtool_link_ext_substate_link_training { ETHTOOL_LINK_EXT_SUBSTATE_LT_KR_FRAME_LOCK_NOT_ACQUIRED = 1, @@ -619,9 +624,7 @@ enum ethtool_link_ext_substate_link_training { ETHTOOL_LINK_EXT_SUBSTATE_LT_REMOTE_FAULT, }; -/** - * enum ethtool_link_ext_substate_logical_mismatch - more information in addition - * to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH. +/* More information in addition to ETHTOOL_LINK_EXT_STATE_LINK_LOGICAL_MISMATCH. */ enum ethtool_link_ext_substate_link_logical_mismatch { ETHTOOL_LINK_EXT_SUBSTATE_LLM_PCS_DID_NOT_ACQUIRE_BLOCK_LOCK = 1, @@ -631,19 +634,14 @@ enum ethtool_link_ext_substate_link_logical_mismatch { ETHTOOL_LINK_EXT_SUBSTATE_LLM_RS_FEC_IS_NOT_LOCKED, }; -/** - * enum ethtool_link_ext_substate_bad_signal_integrity - more information in - * addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY. +/* More information in addition to ETHTOOL_LINK_EXT_STATE_BAD_SIGNAL_INTEGRITY. */ enum ethtool_link_ext_substate_bad_signal_integrity { ETHTOOL_LINK_EXT_SUBSTATE_BSI_LARGE_NUMBER_OF_PHYSICAL_ERRORS = 1, ETHTOOL_LINK_EXT_SUBSTATE_BSI_UNSUPPORTED_RATE, }; -/** - * enum ethtool_link_ext_substate_cable_issue - more information in - * addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. - */ +/* More information in addition to ETHTOOL_LINK_EXT_STATE_CABLE_ISSUE. */ enum ethtool_link_ext_substate_cable_issue { ETHTOOL_LINK_EXT_SUBSTATE_CI_UNSUPPORTED_CABLE = 1, ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE, @@ -661,6 +659,7 @@ enum ethtool_link_ext_substate_cable_issue { * now deprecated * @ETH_SS_FEATURES: Device feature names * @ETH_SS_RSS_HASH_FUNCS: RSS hush function names + * @ETH_SS_TUNABLES: tunable names * @ETH_SS_PHY_STATS: Statistic names, for use with %ETHTOOL_GPHYSTATS * @ETH_SS_PHY_TUNABLES: PHY tunable names * @ETH_SS_LINK_MODES: link mode names @@ -670,6 +669,8 @@ enum ethtool_link_ext_substate_cable_issue { * @ETH_SS_TS_TX_TYPES: timestamping Tx types * @ETH_SS_TS_RX_FILTERS: timestamping Rx filters * @ETH_SS_UDP_TUNNEL_TYPES: UDP tunnel types + * + * @ETH_SS_COUNT: number of defined string sets */ enum ethtool_stringset { ETH_SS_TEST = 0, @@ -715,6 +716,7 @@ struct ethtool_gstrings { /** * struct ethtool_sset_info - string set information * @cmd: Command number = %ETHTOOL_GSSET_INFO + * @reserved: Reserved for future use; see the note on reserved space. * @sset_mask: On entry, a bitmask of string sets to query, with bits * numbered according to &enum ethtool_stringset. On return, a * bitmask of those string sets queried that are supported. @@ -759,6 +761,7 @@ enum ethtool_test_flags { * @flags: A bitmask of flags from &enum ethtool_test_flags. Some * flags may be set by the user on entry; others may be set by * the driver on return. + * @reserved: Reserved for future use; see the note on reserved space. * @len: On return, the number of test results * @data: Array of test results * @@ -959,6 +962,7 @@ union ethtool_flow_union { * @vlan_etype: VLAN EtherType * @vlan_tci: VLAN tag control information * @data: user defined data + * @padding: Reserved for future use; see the note on reserved space. * * Note, @vlan_etype, @vlan_tci, and @data are only valid if %FLOW_EXT * is set in &struct ethtool_rx_flow_spec @flow_type. @@ -1134,7 +1138,8 @@ struct ethtool_rxfh_indir { * hardware hash key. * @hfunc: Defines the current RSS hash function used by HW (or to be set to). * Valid values are one of the %ETH_RSS_HASH_*. - * @rsvd: Reserved for future extensions. + * @rsvd8: Reserved for future use; see the note on reserved space. + * @rsvd32: Reserved for future use; see the note on reserved space. * @rss_config: RX ring/queue index for each hash value i.e., indirection table * of @indir_size __u32 elements, followed by hash key of @key_size * bytes. @@ -1302,7 +1307,9 @@ struct ethtool_sfeatures { * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags * @phc_index: device index of the associated PHC, or -1 if there is none * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values + * @tx_reserved: Reserved for future use; see the note on reserved space. * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values + * @rx_reserved: Reserved for future use; see the note on reserved space. * * The bits in the 'tx_types' and 'rx_filters' fields correspond to * the 'hwtstamp_tx_types' and 'hwtstamp_rx_filters' enumeration values, @@ -1958,6 +1965,11 @@ enum ethtool_reset_flags { * autonegotiation; 0 if unknown or not applicable. Read-only. * @transceiver: Used to distinguish different possible PHY types, * reported consistently by PHYLIB. Read-only. + * @master_slave_cfg: Master/slave port mode. + * @master_slave_state: Master/slave port state. + * @reserved: Reserved for future use; see the note on reserved space. + * @reserved1: Reserved for future use; see the note on reserved space. + * @link_mode_masks: Variable length bitmaps. * * If autonegotiation is disabled, the speed and @duplex represent the * fixed link mode and are writable if the driver supports multiple diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 236d437947bc..e33997b4d750 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -247,8 +247,8 @@ struct dsa_completion_record { uint32_t rsvd2:8; }; - uint16_t delta_rec_size; - uint16_t crc_val; + uint32_t delta_rec_size; + uint32_t crc_val; /* DIF check & strip */ struct { diff --git a/include/uapi/linux/psample.h b/include/uapi/linux/psample.h index aea26ab1431c..bff5032c98df 100644 --- a/include/uapi/linux/psample.h +++ b/include/uapi/linux/psample.h @@ -3,7 +3,6 @@ #define __UAPI_PSAMPLE_H enum { - /* sampled packet metadata */ PSAMPLE_ATTR_IIFINDEX, PSAMPLE_ATTR_OIFINDEX, PSAMPLE_ATTR_ORIGSIZE, @@ -11,10 +10,8 @@ enum { PSAMPLE_ATTR_GROUP_SEQ, PSAMPLE_ATTR_SAMPLE_RATE, PSAMPLE_ATTR_DATA, - PSAMPLE_ATTR_TUNNEL, - - /* commands attributes */ PSAMPLE_ATTR_GROUP_REFCOUNT, + PSAMPLE_ATTR_TUNNEL, __PSAMPLE_ATTR_MAX }; diff --git a/include/uapi/linux/rfkill.h b/include/uapi/linux/rfkill.h index 03e8af87b364..9b77cfc42efa 100644 --- a/include/uapi/linux/rfkill.h +++ b/include/uapi/linux/rfkill.h @@ -86,34 +86,90 @@ enum rfkill_hard_block_reasons { * @op: operation code * @hard: hard state (0/1) * @soft: soft state (0/1) + * + * Structure used for userspace communication on /dev/rfkill, + * used for events from the kernel and control to the kernel. + */ +struct rfkill_event { + __u32 idx; + __u8 type; + __u8 op; + __u8 soft; + __u8 hard; +} __attribute__((packed)); + +/** + * struct rfkill_event_ext - events for userspace on /dev/rfkill + * @idx: index of dev rfkill + * @type: type of the rfkill struct + * @op: operation code + * @hard: hard state (0/1) + * @soft: soft state (0/1) * @hard_block_reasons: valid if hard is set. One or several reasons from * &enum rfkill_hard_block_reasons. * * Structure used for userspace communication on /dev/rfkill, * used for events from the kernel and control to the kernel. + * + * See the extensibility docs below. */ -struct rfkill_event { +struct rfkill_event_ext { __u32 idx; __u8 type; __u8 op; __u8 soft; __u8 hard; + + /* + * older kernels will accept/send only up to this point, + * and if extended further up to any chunk marked below + */ + __u8 hard_block_reasons; } __attribute__((packed)); -/* - * We are planning to be backward and forward compatible with changes - * to the event struct, by adding new, optional, members at the end. - * When reading an event (whether the kernel from userspace or vice - * versa) we need to accept anything that's at least as large as the - * version 1 event size, but might be able to accept other sizes in - * the future. +/** + * DOC: Extensibility + * + * Originally, we had planned to allow backward and forward compatible + * changes by just adding fields at the end of the structure that are + * then not reported on older kernels on read(), and not written to by + * older kernels on write(), with the kernel reporting the size it did + * accept as the result. + * + * This would have allowed userspace to detect on read() and write() + * which kernel structure version it was dealing with, and if was just + * recompiled it would have gotten the new fields, but obviously not + * accessed them, but things should've continued to work. + * + * Unfortunately, while actually exercising this mechanism to add the + * hard block reasons field, we found that userspace (notably systemd) + * did all kinds of fun things not in line with this scheme: + * + * 1. treat the (expected) short writes as an error; + * 2. ask to read sizeof(struct rfkill_event) but then compare the + * actual return value to RFKILL_EVENT_SIZE_V1 and treat any + * mismatch as an error. + * + * As a consequence, just recompiling with a new struct version caused + * things to no longer work correctly on old and new kernels. + * + * Hence, we've rolled back &struct rfkill_event to the original version + * and added &struct rfkill_event_ext. This effectively reverts to the + * old behaviour for all userspace, unless it explicitly opts in to the + * rules outlined here by using the new &struct rfkill_event_ext. + * + * Userspace using &struct rfkill_event_ext must adhere to the following + * rules * - * One exception is the kernel -- we already have two event sizes in - * that we've made the 'hard' member optional since our only option - * is to ignore it anyway. + * 1. accept short writes, optionally using them to detect that it's + * running on an older kernel; + * 2. accept short reads, knowing that this means it's running on an + * older kernel; + * 3. treat reads that are as long as requested as acceptable, not + * checking against RFKILL_EVENT_SIZE_V1 or such. */ -#define RFKILL_EVENT_SIZE_V1 8 +#define RFKILL_EVENT_SIZE_V1 sizeof(struct rfkill_event) /* ioctl for turning off rfkill-input (if present) */ #define RFKILL_IOC_MAGIC 'R' diff --git a/include/uapi/misc/uacce/hisi_qm.h b/include/uapi/misc/uacce/hisi_qm.h index 6435f0bcb556..1faef5ff87ef 100644 --- a/include/uapi/misc/uacce/hisi_qm.h +++ b/include/uapi/misc/uacce/hisi_qm.h @@ -16,6 +16,7 @@ struct hisi_qp_ctx { #define HISI_QM_API_VER_BASE "hisi_qm_v1" #define HISI_QM_API_VER2_BASE "hisi_qm_v2" +#define HISI_QM_API_VER3_BASE "hisi_qm_v3" /* UACCE_CMD_QM_SET_QP_CTX: Set qp algorithm type */ #define UACCE_CMD_QM_SET_QP_CTX _IOWR('H', 10, struct hisi_qp_ctx) diff --git a/kernel/bpf/bpf_inode_storage.c b/kernel/bpf/bpf_inode_storage.c index 6639640523c0..b58b2efb9b43 100644 --- a/kernel/bpf/bpf_inode_storage.c +++ b/kernel/bpf/bpf_inode_storage.c @@ -109,7 +109,7 @@ static void *bpf_fd_inode_storage_lookup_elem(struct bpf_map *map, void *key) fd = *(int *)key; f = fget_raw(fd); if (!f) - return NULL; + return ERR_PTR(-EBADF); sdata = inode_storage_lookup(f->f_inode, map, true); fput(f); diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 1a666a975416..70f6fd4fa305 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -430,7 +430,7 @@ static int bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, tprogs[BPF_TRAMP_FENTRY].progs[0] = prog; tprogs[BPF_TRAMP_FENTRY].nr_progs = 1; - err = arch_prepare_bpf_trampoline(image, + err = arch_prepare_bpf_trampoline(NULL, image, st_map->image + PAGE_SIZE, &st_ops->func_models[i], 0, tprogs, NULL); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 3a283bf97f2f..75244ecb2389 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -827,7 +827,7 @@ static int __init bpf_jit_charge_init(void) } pure_initcall(bpf_jit_charge_init); -static int bpf_jit_charge_modmem(u32 pages) +int bpf_jit_charge_modmem(u32 pages) { if (atomic_long_add_return(pages, &bpf_jit_current) > (bpf_jit_limit >> PAGE_SHIFT)) { @@ -840,7 +840,7 @@ static int bpf_jit_charge_modmem(u32 pages) return 0; } -static void bpf_jit_uncharge_modmem(u32 pages) +void bpf_jit_uncharge_modmem(u32 pages) { atomic_long_sub(pages, &bpf_jit_current); } diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 3acc7e0b6916..faa54d58972c 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -84,7 +84,7 @@ static const char *const bpf_atomic_alu_string[16] = { [BPF_ADD >> 4] = "add", [BPF_AND >> 4] = "and", [BPF_OR >> 4] = "or", - [BPF_XOR >> 4] = "or", + [BPF_XOR >> 4] = "xor", }; static const char *const bpf_ldst_string[] = { diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 1576ff331ee4..d2de2abec35b 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -543,11 +543,11 @@ int bpf_obj_get_user(const char __user *pathname, int flags) return PTR_ERR(raw); if (type == BPF_TYPE_PROG) - ret = bpf_prog_new_fd(raw); + ret = (f_flags != O_RDWR) ? -EINVAL : bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) ret = bpf_map_new_fd(raw, f_flags); else if (type == BPF_TYPE_LINK) - ret = bpf_link_new_fd(raw); + ret = (f_flags != O_RDWR) ? -EINVAL : bpf_link_new_fd(raw); else return -ENOENT; diff --git a/kernel/bpf/preload/bpf_preload_kern.c b/kernel/bpf/preload/bpf_preload_kern.c index 79c5772465f1..53736e52c1df 100644 --- a/kernel/bpf/preload/bpf_preload_kern.c +++ b/kernel/bpf/preload/bpf_preload_kern.c @@ -60,9 +60,12 @@ static int finish(void) &magic, sizeof(magic), &pos); if (n != sizeof(magic)) return -EPIPE; + tgid = umd_ops.info.tgid; - wait_event(tgid->wait_pidfd, thread_group_exited(tgid)); - umd_ops.info.tgid = NULL; + if (tgid) { + wait_event(tgid->wait_pidfd, thread_group_exited(tgid)); + umd_cleanup_helper(&umd_ops.info); + } return 0; } @@ -80,10 +83,18 @@ static int __init load_umd(void) static void __exit fini_umd(void) { + struct pid *tgid; + bpf_preload_ops = NULL; + /* kill UMD in case it's still there due to earlier error */ - kill_pid(umd_ops.info.tgid, SIGKILL, 1); - umd_ops.info.tgid = NULL; + tgid = umd_ops.info.tgid; + if (tgid) { + kill_pid(tgid, SIGKILL, 1); + + wait_event(tgid->wait_pidfd, thread_group_exited(tgid)); + umd_cleanup_helper(&umd_ops.info); + } umd_unload_blob(&umd_ops.info); } late_initcall(load_umd); diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index be35bfb7fb13..6fbc2abe9c91 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -517,9 +517,17 @@ const struct bpf_func_proto bpf_get_stack_proto = { BPF_CALL_4(bpf_get_task_stack, struct task_struct *, task, void *, buf, u32, size, u64, flags) { - struct pt_regs *regs = task_pt_regs(task); + struct pt_regs *regs; + long res; - return __bpf_get_stack(regs, task, NULL, buf, size, flags); + if (!try_get_task_stack(task)) + return -EFAULT; + + regs = task_pt_regs(task); + res = __bpf_get_stack(regs, task, NULL, buf, size, flags); + put_task_stack(task); + + return res; } BTF_ID_LIST_SINGLE(bpf_get_task_stack_btf_ids, struct, task_struct) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c859bc46d06c..250503482cda 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -854,6 +854,11 @@ static int map_create(union bpf_attr *attr) err = PTR_ERR(btf); goto free_map; } + if (btf_is_kernel(btf)) { + btf_put(btf); + err = -EACCES; + goto free_map; + } map->btf = btf; if (attr->btf_value_type_id) { diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index 7bc3b3209224..4aa8b52adf25 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -9,6 +9,7 @@ #include <linux/btf.h> #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> +#include <linux/module.h> /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -57,19 +58,10 @@ void bpf_image_ksym_del(struct bpf_ksym *ksym) PAGE_SIZE, true, ksym->name); } -static void bpf_trampoline_ksym_add(struct bpf_trampoline *tr) -{ - struct bpf_ksym *ksym = &tr->ksym; - - snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu", tr->key); - bpf_image_ksym_add(tr->image, ksym); -} - static struct bpf_trampoline *bpf_trampoline_lookup(u64 key) { struct bpf_trampoline *tr; struct hlist_head *head; - void *image; int i; mutex_lock(&trampoline_mutex); @@ -84,14 +76,6 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key) if (!tr) goto out; - /* is_root was checked earlier. No need for bpf_jit_charge_modmem() */ - image = bpf_jit_alloc_exec_page(); - if (!image) { - kfree(tr); - tr = NULL; - goto out; - } - tr->key = key; INIT_HLIST_NODE(&tr->hlist); hlist_add_head(&tr->hlist, head); @@ -99,14 +83,31 @@ static struct bpf_trampoline *bpf_trampoline_lookup(u64 key) mutex_init(&tr->mutex); for (i = 0; i < BPF_TRAMP_MAX; i++) INIT_HLIST_HEAD(&tr->progs_hlist[i]); - tr->image = image; - INIT_LIST_HEAD_RCU(&tr->ksym.lnode); - bpf_trampoline_ksym_add(tr); out: mutex_unlock(&trampoline_mutex); return tr; } +static int bpf_trampoline_module_get(struct bpf_trampoline *tr) +{ + struct module *mod; + int err = 0; + + preempt_disable(); + mod = __module_text_address((unsigned long) tr->func.addr); + if (mod && !try_module_get(mod)) + err = -ENOENT; + preempt_enable(); + tr->mod = mod; + return err; +} + +static void bpf_trampoline_module_put(struct bpf_trampoline *tr) +{ + module_put(tr->mod); + tr->mod = NULL; +} + static int is_ftrace_location(void *ip) { long addr; @@ -128,6 +129,9 @@ static int unregister_fentry(struct bpf_trampoline *tr, void *old_addr) ret = unregister_ftrace_direct((long)ip, (long)old_addr); else ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, old_addr, NULL); + + if (!ret) + bpf_trampoline_module_put(tr); return ret; } @@ -154,10 +158,16 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr) return ret; tr->func.ftrace_managed = ret; + if (bpf_trampoline_module_get(tr)) + return -ENOENT; + if (tr->func.ftrace_managed) ret = register_ftrace_direct((long)ip, (long)new_addr); else ret = bpf_arch_text_poke(ip, BPF_MOD_CALL, NULL, new_addr); + + if (ret) + bpf_trampoline_module_put(tr); return ret; } @@ -185,10 +195,142 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total) return tprogs; } +static void __bpf_tramp_image_put_deferred(struct work_struct *work) +{ + struct bpf_tramp_image *im; + + im = container_of(work, struct bpf_tramp_image, work); + bpf_image_ksym_del(&im->ksym); + bpf_jit_free_exec(im->image); + bpf_jit_uncharge_modmem(1); + percpu_ref_exit(&im->pcref); + kfree_rcu(im, rcu); +} + +/* callback, fexit step 3 or fentry step 2 */ +static void __bpf_tramp_image_put_rcu(struct rcu_head *rcu) +{ + struct bpf_tramp_image *im; + + im = container_of(rcu, struct bpf_tramp_image, rcu); + INIT_WORK(&im->work, __bpf_tramp_image_put_deferred); + schedule_work(&im->work); +} + +/* callback, fexit step 2. Called after percpu_ref_kill confirms. */ +static void __bpf_tramp_image_release(struct percpu_ref *pcref) +{ + struct bpf_tramp_image *im; + + im = container_of(pcref, struct bpf_tramp_image, pcref); + call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu); +} + +/* callback, fexit or fentry step 1 */ +static void __bpf_tramp_image_put_rcu_tasks(struct rcu_head *rcu) +{ + struct bpf_tramp_image *im; + + im = container_of(rcu, struct bpf_tramp_image, rcu); + if (im->ip_after_call) + /* the case of fmod_ret/fexit trampoline and CONFIG_PREEMPTION=y */ + percpu_ref_kill(&im->pcref); + else + /* the case of fentry trampoline */ + call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu); +} + +static void bpf_tramp_image_put(struct bpf_tramp_image *im) +{ + /* The trampoline image that calls original function is using: + * rcu_read_lock_trace to protect sleepable bpf progs + * rcu_read_lock to protect normal bpf progs + * percpu_ref to protect trampoline itself + * rcu tasks to protect trampoline asm not covered by percpu_ref + * (which are few asm insns before __bpf_tramp_enter and + * after __bpf_tramp_exit) + * + * The trampoline is unreachable before bpf_tramp_image_put(). + * + * First, patch the trampoline to avoid calling into fexit progs. + * The progs will be freed even if the original function is still + * executing or sleeping. + * In case of CONFIG_PREEMPT=y use call_rcu_tasks() to wait on + * first few asm instructions to execute and call into + * __bpf_tramp_enter->percpu_ref_get. + * Then use percpu_ref_kill to wait for the trampoline and the original + * function to finish. + * Then use call_rcu_tasks() to make sure few asm insns in + * the trampoline epilogue are done as well. + * + * In !PREEMPT case the task that got interrupted in the first asm + * insns won't go through an RCU quiescent state which the + * percpu_ref_kill will be waiting for. Hence the first + * call_rcu_tasks() is not necessary. + */ + if (im->ip_after_call) { + int err = bpf_arch_text_poke(im->ip_after_call, BPF_MOD_JUMP, + NULL, im->ip_epilogue); + WARN_ON(err); + if (IS_ENABLED(CONFIG_PREEMPTION)) + call_rcu_tasks(&im->rcu, __bpf_tramp_image_put_rcu_tasks); + else + percpu_ref_kill(&im->pcref); + return; + } + + /* The trampoline without fexit and fmod_ret progs doesn't call original + * function and doesn't use percpu_ref. + * Use call_rcu_tasks_trace() to wait for sleepable progs to finish. + * Then use call_rcu_tasks() to wait for the rest of trampoline asm + * and normal progs. + */ + call_rcu_tasks_trace(&im->rcu, __bpf_tramp_image_put_rcu_tasks); +} + +static struct bpf_tramp_image *bpf_tramp_image_alloc(u64 key, u32 idx) +{ + struct bpf_tramp_image *im; + struct bpf_ksym *ksym; + void *image; + int err = -ENOMEM; + + im = kzalloc(sizeof(*im), GFP_KERNEL); + if (!im) + goto out; + + err = bpf_jit_charge_modmem(1); + if (err) + goto out_free_im; + + err = -ENOMEM; + im->image = image = bpf_jit_alloc_exec_page(); + if (!image) + goto out_uncharge; + + err = percpu_ref_init(&im->pcref, __bpf_tramp_image_release, 0, GFP_KERNEL); + if (err) + goto out_free_image; + + ksym = &im->ksym; + INIT_LIST_HEAD_RCU(&ksym->lnode); + snprintf(ksym->name, KSYM_NAME_LEN, "bpf_trampoline_%llu_%u", key, idx); + bpf_image_ksym_add(image, ksym); + return im; + +out_free_image: + bpf_jit_free_exec(im->image); +out_uncharge: + bpf_jit_uncharge_modmem(1); +out_free_im: + kfree(im); +out: + return ERR_PTR(err); +} + static int bpf_trampoline_update(struct bpf_trampoline *tr) { - void *old_image = tr->image + ((tr->selector + 1) & 1) * PAGE_SIZE/2; - void *new_image = tr->image + (tr->selector & 1) * PAGE_SIZE/2; + struct bpf_tramp_image *im; struct bpf_tramp_progs *tprogs; u32 flags = BPF_TRAMP_F_RESTORE_REGS; int err, total; @@ -198,41 +340,42 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr) return PTR_ERR(tprogs); if (total == 0) { - err = unregister_fentry(tr, old_image); + err = unregister_fentry(tr, tr->cur_image->image); + bpf_tramp_image_put(tr->cur_image); + tr->cur_image = NULL; tr->selector = 0; goto out; } + im = bpf_tramp_image_alloc(tr->key, tr->selector); + if (IS_ERR(im)) { + err = PTR_ERR(im); + goto out; + } + if (tprogs[BPF_TRAMP_FEXIT].nr_progs || tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs) flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME; - /* Though the second half of trampoline page is unused a task could be - * preempted in the middle of the first half of trampoline and two - * updates to trampoline would change the code from underneath the - * preempted task. Hence wait for tasks to voluntarily schedule or go - * to userspace. - * The same trampoline can hold both sleepable and non-sleepable progs. - * synchronize_rcu_tasks_trace() is needed to make sure all sleepable - * programs finish executing. - * Wait for these two grace periods together. - */ - synchronize_rcu_mult(call_rcu_tasks, call_rcu_tasks_trace); - - err = arch_prepare_bpf_trampoline(new_image, new_image + PAGE_SIZE / 2, + err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE, &tr->func.model, flags, tprogs, tr->func.addr); if (err < 0) goto out; - if (tr->selector) + WARN_ON(tr->cur_image && tr->selector == 0); + WARN_ON(!tr->cur_image && tr->selector); + if (tr->cur_image) /* progs already running at this address */ - err = modify_fentry(tr, old_image, new_image); + err = modify_fentry(tr, tr->cur_image->image, im->image); else /* first time registering */ - err = register_fentry(tr, new_image); + err = register_fentry(tr, im->image); if (err) goto out; + if (tr->cur_image) + bpf_tramp_image_put(tr->cur_image); + tr->cur_image = im; tr->selector++; out: kfree(tprogs); @@ -364,17 +507,12 @@ void bpf_trampoline_put(struct bpf_trampoline *tr) goto out; if (WARN_ON_ONCE(!hlist_empty(&tr->progs_hlist[BPF_TRAMP_FEXIT]))) goto out; - bpf_image_ksym_del(&tr->ksym); - /* This code will be executed when all bpf progs (both sleepable and - * non-sleepable) went through - * bpf_prog_put()->call_rcu[_tasks_trace]()->bpf_prog_free_deferred(). - * Hence no need for another synchronize_rcu_tasks_trace() here, - * but synchronize_rcu_tasks() is still needed, since trampoline - * may not have had any sleepable programs and we need to wait - * for tasks to get out of trampoline code before freeing it. + /* This code will be executed even when the last bpf_tramp_image + * is alive. All progs are detached from the trampoline and the + * trampoline image is patched with jmp into epilogue to skip + * fexit progs. The fentry-only trampoline will be freed via + * multiple rcu callbacks. */ - synchronize_rcu_tasks(); - bpf_jit_free_exec(tr->image); hlist_del(&tr->hlist); kfree(tr); out: @@ -478,8 +616,18 @@ void notrace __bpf_prog_exit_sleepable(struct bpf_prog *prog, u64 start) rcu_read_unlock_trace(); } +void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr) +{ + percpu_ref_get(&tr->pcref); +} + +void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr) +{ + percpu_ref_put(&tr->pcref); +} + int __weak -arch_prepare_bpf_trampoline(void *image, void *image_end, +arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_progs *tprogs, void *orig_call) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c56e3fcb5f1a..0399ac092b36 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5856,35 +5856,51 @@ static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env) return &env->insn_aux_data[env->insn_idx]; } +enum { + REASON_BOUNDS = -1, + REASON_TYPE = -2, + REASON_PATHS = -3, + REASON_LIMIT = -4, + REASON_STACK = -5, +}; + static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg, - u32 *ptr_limit, u8 opcode, bool off_is_neg) + const struct bpf_reg_state *off_reg, + u32 *alu_limit, u8 opcode) { + bool off_is_neg = off_reg->smin_value < 0; bool mask_to_left = (opcode == BPF_ADD && off_is_neg) || (opcode == BPF_SUB && !off_is_neg); - u32 off; + u32 max = 0, ptr_limit = 0; + + if (!tnum_is_const(off_reg->var_off) && + (off_reg->smin_value < 0) != (off_reg->smax_value < 0)) + return REASON_BOUNDS; switch (ptr_reg->type) { case PTR_TO_STACK: - /* Indirect variable offset stack access is prohibited in - * unprivileged mode so it's not handled here. + /* Offset 0 is out-of-bounds, but acceptable start for the + * left direction, see BPF_REG_FP. Also, unknown scalar + * offset where we would need to deal with min/max bounds is + * currently prohibited for unprivileged. */ - off = ptr_reg->off + ptr_reg->var_off.value; - if (mask_to_left) - *ptr_limit = MAX_BPF_STACK + off; - else - *ptr_limit = -off; - return 0; + max = MAX_BPF_STACK + mask_to_left; + ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off); + break; case PTR_TO_MAP_VALUE: - if (mask_to_left) { - *ptr_limit = ptr_reg->umax_value + ptr_reg->off; - } else { - off = ptr_reg->smin_value + ptr_reg->off; - *ptr_limit = ptr_reg->map_ptr->value_size - off; - } - return 0; + max = ptr_reg->map_ptr->value_size; + ptr_limit = (mask_to_left ? + ptr_reg->smin_value : + ptr_reg->umax_value) + ptr_reg->off; + break; default: - return -EINVAL; + return REASON_TYPE; } + + if (ptr_limit >= max) + return REASON_LIMIT; + *alu_limit = ptr_limit; + return 0; } static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env, @@ -5902,7 +5918,7 @@ static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux, if (aux->alu_state && (aux->alu_state != alu_state || aux->alu_limit != alu_limit)) - return -EACCES; + return REASON_PATHS; /* Corresponding fixup done in fixup_bpf_calls(). */ aux->alu_state = alu_state; @@ -5921,19 +5937,28 @@ static int sanitize_val_alu(struct bpf_verifier_env *env, return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0); } +static bool sanitize_needed(u8 opcode) +{ + return opcode == BPF_ADD || opcode == BPF_SUB; +} + static int sanitize_ptr_alu(struct bpf_verifier_env *env, struct bpf_insn *insn, const struct bpf_reg_state *ptr_reg, + const struct bpf_reg_state *off_reg, struct bpf_reg_state *dst_reg, - bool off_is_neg) + struct bpf_insn_aux_data *tmp_aux, + const bool commit_window) { + struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux; struct bpf_verifier_state *vstate = env->cur_state; - struct bpf_insn_aux_data *aux = cur_aux(env); + bool off_is_neg = off_reg->smin_value < 0; bool ptr_is_dst_reg = ptr_reg == dst_reg; u8 opcode = BPF_OP(insn->code); u32 alu_state, alu_limit; struct bpf_reg_state tmp; bool ret; + int err; if (can_skip_alu_sanitation(env, insn)) return 0; @@ -5945,15 +5970,33 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env, if (vstate->speculative) goto do_sim; - alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; - alu_state |= ptr_is_dst_reg ? - BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode); + if (err < 0) + return err; + + if (commit_window) { + /* In commit phase we narrow the masking window based on + * the observed pointer move after the simulated operation. + */ + alu_state = tmp_aux->alu_state; + alu_limit = abs(tmp_aux->alu_limit - alu_limit); + } else { + alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0; + alu_state |= ptr_is_dst_reg ? + BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST; + } - if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg)) - return 0; - if (update_alu_sanitation_state(aux, alu_state, alu_limit)) - return -EACCES; + err = update_alu_sanitation_state(aux, alu_state, alu_limit); + if (err < 0) + return err; do_sim: + /* If we're in commit phase, we're done here given we already + * pushed the truncated dst_reg into the speculative verification + * stack. + */ + if (commit_window) + return 0; + /* Simulate and find potential out-of-bounds access under * speculative execution from truncation as a result of * masking when off was not within expected range. If off @@ -5970,7 +6013,46 @@ do_sim: ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true); if (!ptr_is_dst_reg && ret) *dst_reg = tmp; - return !ret ? -EFAULT : 0; + return !ret ? REASON_STACK : 0; +} + +static int sanitize_err(struct bpf_verifier_env *env, + const struct bpf_insn *insn, int reason, + const struct bpf_reg_state *off_reg, + const struct bpf_reg_state *dst_reg) +{ + static const char *err = "pointer arithmetic with it prohibited for !root"; + const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub"; + u32 dst = insn->dst_reg, src = insn->src_reg; + + switch (reason) { + case REASON_BOUNDS: + verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n", + off_reg == dst_reg ? dst : src, err); + break; + case REASON_TYPE: + verbose(env, "R%d has pointer with unsupported alu operation, %s\n", + off_reg == dst_reg ? src : dst, err); + break; + case REASON_PATHS: + verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n", + dst, op, err); + break; + case REASON_LIMIT: + verbose(env, "R%d tried to %s beyond pointer bounds, %s\n", + dst, op, err); + break; + case REASON_STACK: + verbose(env, "R%d could not be pushed for speculative verification, %s\n", + dst, err); + break; + default: + verbose(env, "verifier internal error: unknown reason (%d)\n", + reason); + break; + } + + return -EACCES; } /* check that stack access falls within stack limits and that 'reg' doesn't @@ -6007,6 +6089,37 @@ static int check_stack_access_for_ptr_arithmetic( return 0; } +static int sanitize_check_bounds(struct bpf_verifier_env *env, + const struct bpf_insn *insn, + const struct bpf_reg_state *dst_reg) +{ + u32 dst = insn->dst_reg; + + /* For unprivileged we require that resulting offset must be in bounds + * in order to be able to sanitize access later on. + */ + if (env->bypass_spec_v1) + return 0; + + switch (dst_reg->type) { + case PTR_TO_STACK: + if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg, + dst_reg->off + dst_reg->var_off.value)) + return -EACCES; + break; + case PTR_TO_MAP_VALUE: + if (check_map_access(env, dst, dst_reg->off, 1, false)) { + verbose(env, "R%d pointer arithmetic of map value goes out of range, " + "prohibited for !root\n", dst); + return -EACCES; + } + break; + default: + break; + } + + return 0; +} /* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off. * Caller should also handle BPF_MOV case separately. @@ -6026,8 +6139,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value; u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value, umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value; - u32 dst = insn->dst_reg, src = insn->src_reg; + struct bpf_insn_aux_data tmp_aux = {}; u8 opcode = BPF_OP(insn->code); + u32 dst = insn->dst_reg; int ret; dst_reg = ®s[dst]; @@ -6075,13 +6189,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str[ptr_reg->type]); return -EACCES; - case PTR_TO_MAP_VALUE: - if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) { - verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n", - off_reg == dst_reg ? dst : src); - return -EACCES; - } - fallthrough; default: break; } @@ -6099,13 +6206,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, /* pointer types do not carry 32-bit bounds at the moment. */ __mark_reg32_unbounded(dst_reg); + if (sanitize_needed(opcode)) { + ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg, + &tmp_aux, false); + if (ret < 0) + return sanitize_err(env, insn, ret, off_reg, dst_reg); + } + switch (opcode) { case BPF_ADD: - ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); - if (ret < 0) { - verbose(env, "R%d tried to add from different maps or paths\n", dst); - return ret; - } /* We can take a fixed offset as long as it doesn't overflow * the s32 'off' field */ @@ -6156,11 +6265,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } break; case BPF_SUB: - ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0); - if (ret < 0) { - verbose(env, "R%d tried to sub from different maps or paths\n", dst); - return ret; - } if (dst_reg == off_reg) { /* scalar -= pointer. Creates an unknown scalar */ verbose(env, "R%d tried to subtract pointer from scalar\n", @@ -6241,21 +6345,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, __reg_deduce_bounds(dst_reg); __reg_bound_offset(dst_reg); - /* For unprivileged we require that resulting offset must be in bounds - * in order to be able to sanitize access later on. - */ - if (!env->bypass_spec_v1) { - if (dst_reg->type == PTR_TO_MAP_VALUE && - check_map_access(env, dst, dst_reg->off, 1, false)) { - verbose(env, "R%d pointer arithmetic of map value goes out of range, " - "prohibited for !root\n", dst); - return -EACCES; - } else if (dst_reg->type == PTR_TO_STACK && - check_stack_access_for_ptr_arithmetic( - env, dst, dst_reg, dst_reg->off + - dst_reg->var_off.value)) { - return -EACCES; - } + if (sanitize_check_bounds(env, insn, dst_reg) < 0) + return -EACCES; + if (sanitize_needed(opcode)) { + ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg, + &tmp_aux, true); + if (ret < 0) + return sanitize_err(env, insn, ret, off_reg, dst_reg); } return 0; @@ -6849,9 +6945,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, s32 s32_min_val, s32_max_val; u32 u32_min_val, u32_max_val; u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32; - u32 dst = insn->dst_reg; - int ret; bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64); + int ret; smin_val = src_reg.smin_value; smax_val = src_reg.smax_value; @@ -6893,6 +6988,12 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, return 0; } + if (sanitize_needed(opcode)) { + ret = sanitize_val_alu(env, insn); + if (ret < 0) + return sanitize_err(env, insn, ret, NULL, NULL); + } + /* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops. * There are two classes of instructions: The first class we track both * alu32 and alu64 sign/unsigned bounds independently this provides the @@ -6909,21 +7010,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, */ switch (opcode) { case BPF_ADD: - ret = sanitize_val_alu(env, insn); - if (ret < 0) { - verbose(env, "R%d tried to add from different pointers or scalars\n", dst); - return ret; - } scalar32_min_max_add(dst_reg, &src_reg); scalar_min_max_add(dst_reg, &src_reg); dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off); break; case BPF_SUB: - ret = sanitize_val_alu(env, insn); - if (ret < 0) { - verbose(env, "R%d tried to sub from different pointers or scalars\n", dst); - return ret; - } scalar32_min_max_sub(dst_reg, &src_reg); scalar_min_max_sub(dst_reg, &src_reg); dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off); @@ -9056,6 +9147,10 @@ static int check_btf_info(struct bpf_verifier_env *env, btf = btf_get_by_fd(attr->prog_btf_fd); if (IS_ERR(btf)) return PTR_ERR(btf); + if (btf_is_kernel(btf)) { + btf_put(btf); + return -EACCES; + } env->prog->aux->btf = btf; err = check_btf_func(env, attr, uattr); @@ -11660,7 +11755,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) off_reg = issrc ? insn->src_reg : insn->dst_reg; if (isneg) *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1); - *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1); + *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit); *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg); *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0); @@ -12145,6 +12240,11 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) u32 btf_id, member_idx; const char *mname; + if (!prog->gpl_compatible) { + verbose(env, "struct ops programs must have a GPL compatible license\n"); + return -EINVAL; + } + btf_id = prog->aux->attach_btf_id; st_ops = bpf_struct_ops_find(btf_id); if (!st_ops) { diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 8d996dddf8b9..a0b3b04fb596 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -422,7 +422,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state) instrumentation_begin(); if (IS_ENABLED(CONFIG_PREEMPTION)) { -#ifdef CONFIG_PREEMT_DYNAMIC +#ifdef CONFIG_PREEMPT_DYNAMIC static_call(irqentry_exit_cond_resched)(); #else irqentry_exit_cond_resched(); diff --git a/kernel/fork.c b/kernel/fork.c index 54cc905e5fe0..426cd0c51f9e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1948,8 +1948,14 @@ static __latent_entropy struct task_struct *copy_process( p = dup_task_struct(current, node); if (!p) goto fork_out; - if (args->io_thread) + if (args->io_thread) { + /* + * Mark us an IO worker, and block any signal that isn't + * fatal or STOP + */ p->flags |= PF_IO_WORKER; + siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); + } /* * This _must_ happen before we call free_task(), i.e. before we jump @@ -2438,14 +2444,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) .stack_size = (unsigned long)arg, .io_thread = 1, }; - struct task_struct *tsk; - tsk = copy_process(NULL, 0, node, &args); - if (!IS_ERR(tsk)) { - sigfillset(&tsk->blocked); - sigdelsetmask(&tsk->blocked, sigmask(SIGKILL)); - } - return tsk; + return copy_process(NULL, 0, node, &args); } /* diff --git a/kernel/freezer.c b/kernel/freezer.c index 1a2d57d1327c..dc520f01f99d 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -134,7 +134,7 @@ bool freeze_task(struct task_struct *p) return false; } - if (!(p->flags & (PF_KTHREAD | PF_IO_WORKER))) + if (!(p->flags & PF_KTHREAD)) fake_signal_wake_up(p); else wake_up_state(p, TASK_INTERRUPTIBLE); diff --git a/kernel/gcov/clang.c b/kernel/gcov/clang.c index c94b820a1b62..c466c7fbdece 100644 --- a/kernel/gcov/clang.c +++ b/kernel/gcov/clang.c @@ -70,12 +70,16 @@ struct gcov_fn_info { u32 ident; u32 checksum; +#if CONFIG_CLANG_VERSION < 110000 u8 use_extra_checksum; +#endif u32 cfg_checksum; u32 num_counters; u64 *counters; +#if CONFIG_CLANG_VERSION < 110000 const char *function_name; +#endif }; static struct gcov_info *current_info; @@ -105,6 +109,7 @@ void llvm_gcov_init(llvm_gcov_callback writeout, llvm_gcov_callback flush) } EXPORT_SYMBOL(llvm_gcov_init); +#if CONFIG_CLANG_VERSION < 110000 void llvm_gcda_start_file(const char *orig_filename, const char version[4], u32 checksum) { @@ -113,7 +118,17 @@ void llvm_gcda_start_file(const char *orig_filename, const char version[4], current_info->checksum = checksum; } EXPORT_SYMBOL(llvm_gcda_start_file); +#else +void llvm_gcda_start_file(const char *orig_filename, u32 version, u32 checksum) +{ + current_info->filename = orig_filename; + current_info->version = version; + current_info->checksum = checksum; +} +EXPORT_SYMBOL(llvm_gcda_start_file); +#endif +#if CONFIG_CLANG_VERSION < 110000 void llvm_gcda_emit_function(u32 ident, const char *function_name, u32 func_checksum, u8 use_extra_checksum, u32 cfg_checksum) { @@ -132,6 +147,21 @@ void llvm_gcda_emit_function(u32 ident, const char *function_name, list_add_tail(&info->head, ¤t_info->functions); } +#else +void llvm_gcda_emit_function(u32 ident, u32 func_checksum, u32 cfg_checksum) +{ + struct gcov_fn_info *info = kzalloc(sizeof(*info), GFP_KERNEL); + + if (!info) + return; + + INIT_LIST_HEAD(&info->head); + info->ident = ident; + info->checksum = func_checksum; + info->cfg_checksum = cfg_checksum; + list_add_tail(&info->head, ¤t_info->functions); +} +#endif EXPORT_SYMBOL(llvm_gcda_emit_function); void llvm_gcda_emit_arcs(u32 num_counters, u64 *counters) @@ -262,11 +292,16 @@ int gcov_info_is_compatible(struct gcov_info *info1, struct gcov_info *info2) !list_is_last(&fn_ptr2->head, &info2->functions)) { if (fn_ptr1->checksum != fn_ptr2->checksum) return false; +#if CONFIG_CLANG_VERSION < 110000 if (fn_ptr1->use_extra_checksum != fn_ptr2->use_extra_checksum) return false; if (fn_ptr1->use_extra_checksum && fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum) return false; +#else + if (fn_ptr1->cfg_checksum != fn_ptr2->cfg_checksum) + return false; +#endif fn_ptr1 = list_next_entry(fn_ptr1, head); fn_ptr2 = list_next_entry(fn_ptr2, head); } @@ -295,6 +330,7 @@ void gcov_info_add(struct gcov_info *dst, struct gcov_info *src) } } +#if CONFIG_CLANG_VERSION < 110000 static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) { size_t cv_size; /* counter values size */ @@ -322,6 +358,28 @@ err_name: kfree(fn_dup); return NULL; } +#else +static struct gcov_fn_info *gcov_fn_info_dup(struct gcov_fn_info *fn) +{ + size_t cv_size; /* counter values size */ + struct gcov_fn_info *fn_dup = kmemdup(fn, sizeof(*fn), + GFP_KERNEL); + if (!fn_dup) + return NULL; + INIT_LIST_HEAD(&fn_dup->head); + + cv_size = fn->num_counters * sizeof(fn->counters[0]); + fn_dup->counters = vmalloc(cv_size); + if (!fn_dup->counters) { + kfree(fn_dup); + return NULL; + } + + memcpy(fn_dup->counters, fn->counters, cv_size); + + return fn_dup; +} +#endif /** * gcov_info_dup - duplicate profiling data set @@ -362,6 +420,7 @@ err: * gcov_info_free - release memory for profiling data set duplicate * @info: profiling data set duplicate to free */ +#if CONFIG_CLANG_VERSION < 110000 void gcov_info_free(struct gcov_info *info) { struct gcov_fn_info *fn, *tmp; @@ -375,6 +434,20 @@ void gcov_info_free(struct gcov_info *info) kfree(info->filename); kfree(info); } +#else +void gcov_info_free(struct gcov_info *info) +{ + struct gcov_fn_info *fn, *tmp; + + list_for_each_entry_safe(fn, tmp, &info->functions, head) { + vfree(fn->counters); + list_del(&fn->head); + kfree(fn); + } + kfree(info->filename); + kfree(info); +} +#endif #define ITER_STRIDE PAGE_SIZE @@ -460,17 +533,22 @@ static size_t convert_to_gcda(char *buffer, struct gcov_info *info) list_for_each_entry(fi_ptr, &info->functions, head) { u32 i; - u32 len = 2; - - if (fi_ptr->use_extra_checksum) - len++; pos += store_gcov_u32(buffer, pos, GCOV_TAG_FUNCTION); - pos += store_gcov_u32(buffer, pos, len); +#if CONFIG_CLANG_VERSION < 110000 + pos += store_gcov_u32(buffer, pos, + fi_ptr->use_extra_checksum ? 3 : 2); +#else + pos += store_gcov_u32(buffer, pos, 3); +#endif pos += store_gcov_u32(buffer, pos, fi_ptr->ident); pos += store_gcov_u32(buffer, pos, fi_ptr->checksum); +#if CONFIG_CLANG_VERSION < 110000 if (fi_ptr->use_extra_checksum) pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum); +#else + pos += store_gcov_u32(buffer, pos, fi_ptr->cfg_checksum); +#endif pos += store_gcov_u32(buffer, pos, GCOV_TAG_COUNTER_BASE); pos += store_gcov_u32(buffer, pos, fi_ptr->num_counters * 2); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index c6d0c1dc6253..ef28a0b9cf1e 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -705,7 +705,7 @@ static void print_lock_name(struct lock_class *class) printk(KERN_CONT " ("); __print_lock_name(class); - printk(KERN_CONT "){%s}-{%hd:%hd}", usage, + printk(KERN_CONT "){%s}-{%d:%d}", usage, class->wait_type_outer ?: class->wait_type_inner, class->wait_type_inner); } @@ -930,7 +930,8 @@ static bool assign_lock_key(struct lockdep_map *lock) /* Debug-check: all keys must be persistent! */ debug_locks_off(); pr_err("INFO: trying to register non-static key.\n"); - pr_err("the code is fine but needs lockdep annotation.\n"); + pr_err("The code is fine but needs lockdep annotation, or maybe\n"); + pr_err("you didn't initialize this object before use?\n"); pr_err("turning off the locking correctness validator.\n"); dump_stack(); return false; @@ -1392,7 +1393,7 @@ static int add_lock_to_list(struct lock_class *this, /* * For good efficiency of modular, we use power of 2 */ -#define MAX_CIRCULAR_QUEUE_SIZE 4096UL +#define MAX_CIRCULAR_QUEUE_SIZE (1UL << CONFIG_LOCKDEP_CIRCULAR_QUEUE_BITS) #define CQ_MASK (MAX_CIRCULAR_QUEUE_SIZE-1) /* diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index de49f9e1c11b..ecb8662e7a4e 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -99,16 +99,16 @@ static const unsigned long LOCKF_USED_IN_IRQ_READ = #define MAX_STACK_TRACE_ENTRIES 262144UL #define STACK_TRACE_HASH_SIZE 8192 #else -#define MAX_LOCKDEP_ENTRIES 32768UL +#define MAX_LOCKDEP_ENTRIES (1UL << CONFIG_LOCKDEP_BITS) -#define MAX_LOCKDEP_CHAINS_BITS 16 +#define MAX_LOCKDEP_CHAINS_BITS CONFIG_LOCKDEP_CHAINS_BITS /* * Stack-trace: tightly packed array of stack backtrace * addresses. Protected by the hash_lock. */ -#define MAX_STACK_TRACE_ENTRIES 524288UL -#define STACK_TRACE_HASH_SIZE 16384 +#define MAX_STACK_TRACE_ENTRIES (1UL << CONFIG_LOCKDEP_STACK_TRACE_BITS) +#define STACK_TRACE_HASH_SIZE (1 << CONFIG_LOCKDEP_STACK_TRACE_HASH_BITS) #endif /* diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index 4786dd271b45..b94f3831e963 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -60,6 +60,8 @@ EXPORT_SYMBOL(queued_read_lock_slowpath); */ void queued_write_lock_slowpath(struct qrwlock *lock) { + int cnts; + /* Put the writer into the wait queue */ arch_spin_lock(&lock->wait_lock); @@ -73,9 +75,8 @@ void queued_write_lock_slowpath(struct qrwlock *lock) /* When no more readers or writers, set the locked flag */ do { - atomic_cond_read_acquire(&lock->cnts, VAL == _QW_WAITING); - } while (atomic_cmpxchg_relaxed(&lock->cnts, _QW_WAITING, - _QW_LOCKED) != _QW_WAITING); + cnts = atomic_cond_read_relaxed(&lock->cnts, VAL == _QW_WAITING); + } while (!atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED)); unlock: arch_spin_unlock(&lock->wait_lock); } diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 1358fa4abfa8..0f4530b3a8cd 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -98,7 +98,7 @@ static int __init em_debug_init(void) return 0; } -core_initcall(em_debug_init); +fs_initcall(em_debug_init); #else /* CONFIG_DEBUG_FS */ static void em_debug_create_pd(struct device *dev) {} static void em_debug_remove_pd(struct device *dev) {} diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 821cf1723814..61db50f7ca86 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -375,7 +375,7 @@ static int ptrace_attach(struct task_struct *task, long request, audit_ptrace(task); retval = -EPERM; - if (unlikely(task->flags & (PF_KTHREAD | PF_IO_WORKER))) + if (unlikely(task->flags & PF_KTHREAD)) goto out; if (same_thread_group(task, current)) goto out; diff --git a/kernel/signal.c b/kernel/signal.c index f2a1b898da29..f2718350bf4b 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -91,7 +91,7 @@ static bool sig_task_ignored(struct task_struct *t, int sig, bool force) return true; /* Only allow kernel generated signals to this kthread */ - if (unlikely((t->flags & (PF_KTHREAD | PF_IO_WORKER)) && + if (unlikely((t->flags & PF_KTHREAD) && (handler == SIG_KTHREAD_KERNEL) && !force)) return true; @@ -288,8 +288,7 @@ bool task_set_jobctl_pending(struct task_struct *task, unsigned long mask) JOBCTL_STOP_SIGMASK | JOBCTL_TRAPPING)); BUG_ON((mask & JOBCTL_TRAPPING) && !(mask & JOBCTL_PENDING_MASK)); - if (unlikely(fatal_signal_pending(task) || - (task->flags & (PF_EXITING | PF_IO_WORKER)))) + if (unlikely(fatal_signal_pending(task) || (task->flags & PF_EXITING))) return false; if (mask & JOBCTL_STOP_SIGMASK) @@ -834,9 +833,6 @@ static int check_kill_permission(int sig, struct kernel_siginfo *info, if (!valid_signal(sig)) return -EINVAL; - /* PF_IO_WORKER threads don't take any signals */ - if (t->flags & PF_IO_WORKER) - return -ESRCH; if (!si_fromuser(info)) return 0; @@ -1100,7 +1096,7 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc /* * Skip useless siginfo allocation for SIGKILL and kernel threads. */ - if ((sig == SIGKILL) || (t->flags & (PF_KTHREAD | PF_IO_WORKER))) + if ((sig == SIGKILL) || (t->flags & PF_KTHREAD)) goto out_set; /* @@ -2772,13 +2768,21 @@ relock: } /* + * PF_IO_WORKER threads will catch and exit on fatal signals + * themselves. They have cleanup that must be performed, so + * we cannot call do_exit() on their behalf. + */ + if (current->flags & PF_IO_WORKER) + goto out; + + /* * Death signals, no core dump. */ do_group_exit(ksig->info.si_signo); /* NOTREACHED */ } spin_unlock_irq(&sighand->siglock); - +out: ksig->sig = signr; if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS)) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 4d8e35575549..3ba52d4e1314 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3231,7 +3231,8 @@ ftrace_allocate_pages(unsigned long num_to_init) pg = start_pg; while (pg) { order = get_count_order(pg->size / ENTRIES_PER_PAGE); - free_pages((unsigned long)pg->records, order); + if (order >= 0) + free_pages((unsigned long)pg->records, order); start_pg = pg->next; kfree(pg); pg = start_pg; @@ -5045,6 +5046,20 @@ struct ftrace_direct_func *ftrace_find_direct_func(unsigned long addr) return NULL; } +static struct ftrace_direct_func *ftrace_alloc_direct_func(unsigned long addr) +{ + struct ftrace_direct_func *direct; + + direct = kmalloc(sizeof(*direct), GFP_KERNEL); + if (!direct) + return NULL; + direct->addr = addr; + direct->count = 0; + list_add_rcu(&direct->next, &ftrace_direct_funcs); + ftrace_direct_func_count++; + return direct; +} + /** * register_ftrace_direct - Call a custom trampoline directly * @ip: The address of the nop at the beginning of a function @@ -5120,15 +5135,11 @@ int register_ftrace_direct(unsigned long ip, unsigned long addr) direct = ftrace_find_direct_func(addr); if (!direct) { - direct = kmalloc(sizeof(*direct), GFP_KERNEL); + direct = ftrace_alloc_direct_func(addr); if (!direct) { kfree(entry); goto out_unlock; } - direct->addr = addr; - direct->count = 0; - list_add_rcu(&direct->next, &ftrace_direct_funcs); - ftrace_direct_func_count++; } entry->ip = ip; @@ -5329,6 +5340,7 @@ int __weak ftrace_modify_direct_caller(struct ftrace_func_entry *entry, int modify_ftrace_direct(unsigned long ip, unsigned long old_addr, unsigned long new_addr) { + struct ftrace_direct_func *direct, *new_direct = NULL; struct ftrace_func_entry *entry; struct dyn_ftrace *rec; int ret = -ENODEV; @@ -5344,6 +5356,20 @@ int modify_ftrace_direct(unsigned long ip, if (entry->direct != old_addr) goto out_unlock; + direct = ftrace_find_direct_func(old_addr); + if (WARN_ON(!direct)) + goto out_unlock; + if (direct->count > 1) { + ret = -ENOMEM; + new_direct = ftrace_alloc_direct_func(new_addr); + if (!new_direct) + goto out_unlock; + direct->count--; + new_direct->count++; + } else { + direct->addr = new_addr; + } + /* * If there's no other ftrace callback on the rec->ip location, * then it can be changed directly by the architecture. @@ -5357,6 +5383,14 @@ int modify_ftrace_direct(unsigned long ip, ret = 0; } + if (unlikely(ret && new_direct)) { + direct->count++; + list_del_rcu(&new_direct->next); + synchronize_rcu_tasks(); + kfree(new_direct); + ftrace_direct_func_count--; + } + out_unlock: mutex_unlock(&ftrace_lock); mutex_unlock(&direct_mutex); @@ -6418,7 +6452,8 @@ void ftrace_release_mod(struct module *mod) clear_mod_from_hashes(pg); order = get_count_order(pg->size / ENTRIES_PER_PAGE); - free_pages((unsigned long)pg->records, order); + if (order >= 0) + free_pages((unsigned long)pg->records, order); tmp_page = pg->next; kfree(pg); ftrace_number_of_pages -= 1 << order; @@ -6778,7 +6813,8 @@ void ftrace_free_mem(struct module *mod, void *start_ptr, void *end_ptr) if (!pg->index) { *last_pg = pg->next; order = get_count_order(pg->size / ENTRIES_PER_PAGE); - free_pages((unsigned long)pg->records, order); + if (order >= 0) + free_pages((unsigned long)pg->records, order); ftrace_number_of_pages -= 1 << order; ftrace_number_of_groups--; kfree(pg); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index eccb4e1187cc..c0c9aa5cd8e2 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2984,7 +2984,8 @@ static void __ftrace_trace_stack(struct trace_buffer *buffer, size = nr_entries * sizeof(unsigned long); event = __trace_buffer_lock_reserve(buffer, TRACE_STACK, - sizeof(*entry) + size, trace_ctx); + (sizeof(*entry) - sizeof(entry->caller)) + size, + trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); @@ -3544,7 +3545,11 @@ static char *trace_iter_expand_format(struct trace_iterator *iter) { char *tmp; - if (iter->fmt == static_fmt_buf) + /* + * iter->tr is NULL when used with tp_printk, which makes + * this get called where it is not safe to call krealloc(). + */ + if (!iter->tr || iter->fmt == static_fmt_buf) return NULL; tmp = krealloc(iter->fmt, iter->fmt_size + STATIC_FMT_BUF_SIZE, @@ -3565,7 +3570,7 @@ const char *trace_event_format(struct trace_iterator *iter, const char *fmt) if (WARN_ON_ONCE(!fmt)) return fmt; - if (iter->tr->trace_flags & TRACE_ITER_HASH_PTR) + if (!iter->tr || iter->tr->trace_flags & TRACE_ITER_HASH_PTR) return fmt; p = fmt; @@ -9691,7 +9696,7 @@ void __init early_trace_init(void) { if (tracepoint_printk) { tracepoint_print_iter = - kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL); + kzalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL); if (MEM_FAIL(!tracepoint_print_iter, "Failed to allocate trace iterator\n")) tracepoint_printk = 0; diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c index dc971a68dda4..e57cc0870892 100644 --- a/kernel/trace/trace_dynevent.c +++ b/kernel/trace/trace_dynevent.c @@ -63,8 +63,10 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type event = p + 1; *p = '\0'; } - if (event[0] == '\0') - return -EINVAL; + if (event[0] == '\0') { + ret = -EINVAL; + goto out; + } mutex_lock(&event_mutex); for_each_dyn_event_safe(pos, n) { diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index af612945a4d0..9a4b980d695b 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -106,6 +106,7 @@ int create_user_ns(struct cred *new) if (!ns) goto fail_dec; + ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP); ret = ns_alloc_inum(&ns->ns); if (ret) goto fail_free; @@ -841,6 +842,60 @@ static int sort_idmaps(struct uid_gid_map *map) return 0; } +/** + * verify_root_map() - check the uid 0 mapping + * @file: idmapping file + * @map_ns: user namespace of the target process + * @new_map: requested idmap + * + * If a process requests mapping parent uid 0 into the new ns, verify that the + * process writing the map had the CAP_SETFCAP capability as the target process + * will be able to write fscaps that are valid in ancestor user namespaces. + * + * Return: true if the mapping is allowed, false if not. + */ +static bool verify_root_map(const struct file *file, + struct user_namespace *map_ns, + struct uid_gid_map *new_map) +{ + int idx; + const struct user_namespace *file_ns = file->f_cred->user_ns; + struct uid_gid_extent *extent0 = NULL; + + for (idx = 0; idx < new_map->nr_extents; idx++) { + if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) + extent0 = &new_map->extent[idx]; + else + extent0 = &new_map->forward[idx]; + if (extent0->lower_first == 0) + break; + + extent0 = NULL; + } + + if (!extent0) + return true; + + if (map_ns == file_ns) { + /* The process unshared its ns and is writing to its own + * /proc/self/uid_map. User already has full capabilites in + * the new namespace. Verify that the parent had CAP_SETFCAP + * when it unshared. + * */ + if (!file_ns->parent_could_setfcap) + return false; + } else { + /* Process p1 is writing to uid_map of p2, who is in a child + * user namespace to p1's. Verify that the opener of the map + * file has CAP_SETFCAP against the parent of the new map + * namespace */ + if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP)) + return false; + } + + return true; +} + static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, @@ -848,7 +903,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, struct uid_gid_map *parent_map) { struct seq_file *seq = file->private_data; - struct user_namespace *ns = seq->private; + struct user_namespace *map_ns = seq->private; struct uid_gid_map new_map; unsigned idx; struct uid_gid_extent extent; @@ -895,7 +950,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, /* * Adjusting namespace settings requires capabilities on the target. */ - if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN)) + if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN)) goto out; /* Parse the user data */ @@ -965,7 +1020,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, ret = -EPERM; /* Validate the user is allowed to use user id's mapped to. */ - if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) + if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map)) goto out; ret = -EPERM; @@ -1086,6 +1141,10 @@ static bool new_idmap_permitted(const struct file *file, struct uid_gid_map *new_map) { const struct cred *cred = file->f_cred; + + if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map)) + return false; + /* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c index 0b35212ffc3d..bb7bb3b478ab 100644 --- a/kernel/usermode_driver.c +++ b/kernel/usermode_driver.c @@ -139,13 +139,22 @@ static void umd_cleanup(struct subprocess_info *info) struct umd_info *umd_info = info->data; /* cleanup if umh_setup() was successful but exec failed */ - if (info->retval) { - fput(umd_info->pipe_to_umh); - fput(umd_info->pipe_from_umh); - put_pid(umd_info->tgid); - umd_info->tgid = NULL; - } + if (info->retval) + umd_cleanup_helper(umd_info); +} + +/** + * umd_cleanup_helper - release the resources which were allocated in umd_setup + * @info: information about usermode driver + */ +void umd_cleanup_helper(struct umd_info *info) +{ + fput(info->pipe_to_umh); + fput(info->pipe_from_umh); + put_pid(info->tgid); + info->tgid = NULL; } +EXPORT_SYMBOL_GPL(umd_cleanup_helper); /** * fork_usermode_driver - fork a usermode driver diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 71109065bd8e..107bc38b1945 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -278,9 +278,10 @@ void touch_all_softlockup_watchdogs(void) * update as well, the only side effect might be a cycle delay for * the softlockup check. */ - for_each_cpu(cpu, &watchdog_allowed_mask) + for_each_cpu(cpu, &watchdog_allowed_mask) { per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET; - wq_watchdog_touch(-1); + wq_watchdog_touch(cpu); + } } void touch_softlockup_watchdog_sync(void) diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0d150da252e8..79f2319543ce 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -1412,7 +1412,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, */ lockdep_assert_irqs_disabled(); - debug_work_activate(work); /* if draining, only works from the same workqueue are allowed */ if (unlikely(wq->flags & __WQ_DRAINING) && @@ -1494,6 +1493,7 @@ retry: worklist = &pwq->delayed_works; } + debug_work_activate(work); insert_work(pwq, work, worklist, work_flags); out: @@ -5787,22 +5787,17 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) continue; /* get the latest of pool and touched timestamps */ + if (pool->cpu >= 0) + touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); + else + touched = READ_ONCE(wq_watchdog_touched); pool_ts = READ_ONCE(pool->watchdog_ts); - touched = READ_ONCE(wq_watchdog_touched); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; - if (pool->cpu >= 0) { - unsigned long cpu_touched = - READ_ONCE(per_cpu(wq_watchdog_touched_cpu, - pool->cpu)); - if (time_after(cpu_touched, ts)) - ts = cpu_touched; - } - /* did we stall? */ if (time_after(jiffies, ts + thresh)) { lockup_detected = true; @@ -5826,8 +5821,8 @@ notrace void wq_watchdog_touch(int cpu) { if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; - else - wq_watchdog_touched = jiffies; + + wq_watchdog_touched = jiffies; } static void wq_watchdog_set_thresh(unsigned long thresh) diff --git a/lib/Kconfig b/lib/Kconfig index a38cc61256f1..ac3b30697b2b 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -701,3 +701,6 @@ config GENERIC_LIB_DEVMEM_IS_ALLOWED config PLDMFW bool default n + +config ASN1_ENCODER + tristate diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2779c29d9981..2c7f46b366f1 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1363,13 +1363,53 @@ config LOCKDEP bool depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT select STACKTRACE - select FRAME_POINTER if !MIPS && !PPC && !ARM && !S390 && !MICROBLAZE && !ARC && !X86 + depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86 select KALLSYMS select KALLSYMS_ALL config LOCKDEP_SMALL bool +config LOCKDEP_BITS + int "Bitsize for MAX_LOCKDEP_ENTRIES" + depends on LOCKDEP && !LOCKDEP_SMALL + range 10 30 + default 15 + help + Try increasing this value if you hit "BUG: MAX_LOCKDEP_ENTRIES too low!" message. + +config LOCKDEP_CHAINS_BITS + int "Bitsize for MAX_LOCKDEP_CHAINS" + depends on LOCKDEP && !LOCKDEP_SMALL + range 10 30 + default 16 + help + Try increasing this value if you hit "BUG: MAX_LOCKDEP_CHAINS too low!" message. + +config LOCKDEP_STACK_TRACE_BITS + int "Bitsize for MAX_STACK_TRACE_ENTRIES" + depends on LOCKDEP && !LOCKDEP_SMALL + range 10 30 + default 19 + help + Try increasing this value if you hit "BUG: MAX_STACK_TRACE_ENTRIES too low!" message. + +config LOCKDEP_STACK_TRACE_HASH_BITS + int "Bitsize for STACK_TRACE_HASH_SIZE" + depends on LOCKDEP && !LOCKDEP_SMALL + range 10 30 + default 14 + help + Try increasing this value if you need large MAX_STACK_TRACE_ENTRIES. + +config LOCKDEP_CIRCULAR_QUEUE_BITS + int "Bitsize for elements in circular_queue struct" + depends on LOCKDEP + range 10 30 + default 12 + help + Try increasing this value if you hit "lockdep bfs error:-1" warning due to __cq_enqueue() failure. + config DEBUG_LOCKDEP bool "Lock dependency engine debugging" depends on DEBUG_KERNEL && LOCKDEP @@ -1665,7 +1705,7 @@ config LATENCYTOP depends on DEBUG_KERNEL depends on STACKTRACE_SUPPORT depends on PROC_FS - select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM && !ARC && !X86 + depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86 select KALLSYMS select KALLSYMS_ALL select STACKTRACE @@ -1918,7 +1958,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT depends on !X86_64 select STACKTRACE - select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM && !ARC && !X86 + depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86 help Provide stacktrace filter for fault-injection capabilities diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan index fba9909e31b7..cffc2ebbf185 100644 --- a/lib/Kconfig.kasan +++ b/lib/Kconfig.kasan @@ -138,9 +138,10 @@ config KASAN_INLINE endchoice -config KASAN_STACK_ENABLE +config KASAN_STACK bool "Enable stack instrumentation (unsafe)" if CC_IS_CLANG && !COMPILE_TEST depends on KASAN_GENERIC || KASAN_SW_TAGS + default y if CC_IS_GCC help The LLVM stack address sanitizer has a know problem that causes excessive stack usage in a lot of functions, see @@ -154,12 +155,6 @@ config KASAN_STACK_ENABLE CONFIG_COMPILE_TEST. On gcc it is assumed to always be safe to use and enabled by default. -config KASAN_STACK - int - depends on KASAN_GENERIC || KASAN_SW_TAGS - default 1 if KASAN_STACK_ENABLE || CC_IS_GCC - default 0 - config KASAN_SW_TAGS_IDENTIFY bool "Enable memory corruption identification" depends on KASAN_SW_TAGS diff --git a/lib/Makefile b/lib/Makefile index b5307d3eec1a..e11cfc18b6c0 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -280,6 +280,7 @@ obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o obj-$(CONFIG_PERCPU_TEST) += percpu_test.o obj-$(CONFIG_ASN1) += asn1_decoder.o +obj-$(CONFIG_ASN1_ENCODER) += asn1_encoder.o obj-$(CONFIG_FONT_SUPPORT) += fonts/ diff --git a/lib/asn1_encoder.c b/lib/asn1_encoder.c new file mode 100644 index 000000000000..41e71aae3ef6 --- /dev/null +++ b/lib/asn1_encoder.c @@ -0,0 +1,454 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Simple encoder primitives for ASN.1 BER/DER/CER + * + * Copyright (C) 2019 James.Bottomley@HansenPartnership.com + */ + +#include <linux/asn1_encoder.h> +#include <linux/bug.h> +#include <linux/string.h> +#include <linux/module.h> + +/** + * asn1_encode_integer() - encode positive integer to ASN.1 + * @data: pointer to the pointer to the data + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @integer: integer to be encoded + * + * This is a simplified encoder: it only currently does + * positive integers, but it should be simple enough to add the + * negative case if a use comes along. + */ +unsigned char * +asn1_encode_integer(unsigned char *data, const unsigned char *end_data, + s64 integer) +{ + int data_len = end_data - data; + unsigned char *d = &data[2]; + bool found = false; + int i; + + if (WARN(integer < 0, + "BUG: integer encode only supports positive integers")) + return ERR_PTR(-EINVAL); + + if (IS_ERR(data)) + return data; + + /* need at least 3 bytes for tag, length and integer encoding */ + if (data_len < 3) + return ERR_PTR(-EINVAL); + + /* remaining length where at d (the start of the integer encoding) */ + data_len -= 2; + + data[0] = _tag(UNIV, PRIM, INT); + if (integer == 0) { + *d++ = 0; + goto out; + } + + for (i = sizeof(integer); i > 0 ; i--) { + int byte = integer >> (8 * (i - 1)); + + if (!found && byte == 0) + continue; + + /* + * for a positive number the first byte must have bit + * 7 clear in two's complement (otherwise it's a + * negative number) so prepend a leading zero if + * that's not the case + */ + if (!found && (byte & 0x80)) { + /* + * no check needed here, we already know we + * have len >= 1 + */ + *d++ = 0; + data_len--; + } + + found = true; + if (data_len == 0) + return ERR_PTR(-EINVAL); + + *d++ = byte; + data_len--; + } + + out: + data[1] = d - data - 2; + + return d; +} +EXPORT_SYMBOL_GPL(asn1_encode_integer); + +/* calculate the base 128 digit values setting the top bit of the first octet */ +static int asn1_encode_oid_digit(unsigned char **_data, int *data_len, u32 oid) +{ + unsigned char *data = *_data; + int start = 7 + 7 + 7 + 7; + int ret = 0; + + if (*data_len < 1) + return -EINVAL; + + /* quick case */ + if (oid == 0) { + *data++ = 0x80; + (*data_len)--; + goto out; + } + + while (oid >> start == 0) + start -= 7; + + while (start > 0 && *data_len > 0) { + u8 byte; + + byte = oid >> start; + oid = oid - (byte << start); + start -= 7; + byte |= 0x80; + *data++ = byte; + (*data_len)--; + } + + if (*data_len > 0) { + *data++ = oid; + (*data_len)--; + } else { + ret = -EINVAL; + } + + out: + *_data = data; + return ret; +} + +/** + * asn1_encode_oid() - encode an oid to ASN.1 + * @data: position to begin encoding at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @oid: array of oids + * @oid_len: length of oid array + * + * this encodes an OID up to ASN.1 when presented as an array of OID values + */ +unsigned char * +asn1_encode_oid(unsigned char *data, const unsigned char *end_data, + u32 oid[], int oid_len) +{ + int data_len = end_data - data; + unsigned char *d = data + 2; + int i, ret; + + if (WARN(oid_len < 2, "OID must have at least two elements")) + return ERR_PTR(-EINVAL); + + if (WARN(oid_len > 32, "OID is too large")) + return ERR_PTR(-EINVAL); + + if (IS_ERR(data)) + return data; + + + /* need at least 3 bytes for tag, length and OID encoding */ + if (data_len < 3) + return ERR_PTR(-EINVAL); + + data[0] = _tag(UNIV, PRIM, OID); + *d++ = oid[0] * 40 + oid[1]; + + data_len -= 3; + + ret = 0; + + for (i = 2; i < oid_len; i++) { + ret = asn1_encode_oid_digit(&d, &data_len, oid[i]); + if (ret < 0) + return ERR_PTR(ret); + } + + data[1] = d - data - 2; + + return d; +} +EXPORT_SYMBOL_GPL(asn1_encode_oid); + +/** + * asn1_encode_length() - encode a length to follow an ASN.1 tag + * @data: pointer to encode at + * @data_len: pointer to remaning length (adjusted by routine) + * @len: length to encode + * + * This routine can encode lengths up to 65535 using the ASN.1 rules. + * It will accept a negative length and place a zero length tag + * instead (to keep the ASN.1 valid). This convention allows other + * encoder primitives to accept negative lengths as singalling the + * sequence will be re-encoded when the length is known. + */ +static int asn1_encode_length(unsigned char **data, int *data_len, int len) +{ + if (*data_len < 1) + return -EINVAL; + + if (len < 0) { + *((*data)++) = 0; + (*data_len)--; + return 0; + } + + if (len <= 0x7f) { + *((*data)++) = len; + (*data_len)--; + return 0; + } + + if (*data_len < 2) + return -EINVAL; + + if (len <= 0xff) { + *((*data)++) = 0x81; + *((*data)++) = len & 0xff; + *data_len -= 2; + return 0; + } + + if (*data_len < 3) + return -EINVAL; + + if (len <= 0xffff) { + *((*data)++) = 0x82; + *((*data)++) = (len >> 8) & 0xff; + *((*data)++) = len & 0xff; + *data_len -= 3; + return 0; + } + + if (WARN(len > 0xffffff, "ASN.1 length can't be > 0xffffff")) + return -EINVAL; + + if (*data_len < 4) + return -EINVAL; + *((*data)++) = 0x83; + *((*data)++) = (len >> 16) & 0xff; + *((*data)++) = (len >> 8) & 0xff; + *((*data)++) = len & 0xff; + *data_len -= 4; + + return 0; +} + +/** + * asn1_encode_tag() - add a tag for optional or explicit value + * @data: pointer to place tag at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @tag: tag to be placed + * @string: the data to be tagged + * @len: the length of the data to be tagged + * + * Note this currently only handles short form tags < 31. + * + * Standard usage is to pass in a @tag, @string and @length and the + * @string will be ASN.1 encoded with @tag and placed into @data. If + * the encoding would put data past @end_data then an error is + * returned, otherwise a pointer to a position one beyond the encoding + * is returned. + * + * To encode in place pass a NULL @string and -1 for @len and the + * maximum allowable beginning and end of the data; all this will do + * is add the current maximum length and update the data pointer to + * the place where the tag contents should be placed is returned. The + * data should be copied in by the calling routine which should then + * repeat the prior statement but now with the known length. In order + * to avoid having to keep both before and after pointers, the repeat + * expects to be called with @data pointing to where the first encode + * returned it and still NULL for @string but the real length in @len. + */ +unsigned char * +asn1_encode_tag(unsigned char *data, const unsigned char *end_data, + u32 tag, const unsigned char *string, int len) +{ + int data_len = end_data - data; + int ret; + + if (WARN(tag > 30, "ASN.1 tag can't be > 30")) + return ERR_PTR(-EINVAL); + + if (!string && WARN(len > 127, + "BUG: recode tag is too big (>127)")) + return ERR_PTR(-EINVAL); + + if (IS_ERR(data)) + return data; + + if (!string && len > 0) { + /* + * we're recoding, so move back to the start of the + * tag and install a dummy length because the real + * data_len should be NULL + */ + data -= 2; + data_len = 2; + } + + if (data_len < 2) + return ERR_PTR(-EINVAL); + + *(data++) = _tagn(CONT, CONS, tag); + data_len--; + ret = asn1_encode_length(&data, &data_len, len); + if (ret < 0) + return ERR_PTR(ret); + + if (!string) + return data; + + if (data_len < len) + return ERR_PTR(-EINVAL); + + memcpy(data, string, len); + data += len; + + return data; +} +EXPORT_SYMBOL_GPL(asn1_encode_tag); + +/** + * asn1_encode_octet_string() - encode an ASN.1 OCTET STRING + * @data: pointer to encode at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @string: string to be encoded + * @len: length of string + * + * Note ASN.1 octet strings may contain zeros, so the length is obligatory. + */ +unsigned char * +asn1_encode_octet_string(unsigned char *data, + const unsigned char *end_data, + const unsigned char *string, u32 len) +{ + int data_len = end_data - data; + int ret; + + if (IS_ERR(data)) + return data; + + /* need minimum of 2 bytes for tag and length of zero length string */ + if (data_len < 2) + return ERR_PTR(-EINVAL); + + *(data++) = _tag(UNIV, PRIM, OTS); + data_len--; + + ret = asn1_encode_length(&data, &data_len, len); + if (ret) + return ERR_PTR(ret); + + if (data_len < len) + return ERR_PTR(-EINVAL); + + memcpy(data, string, len); + data += len; + + return data; +} +EXPORT_SYMBOL_GPL(asn1_encode_octet_string); + +/** + * asn1_encode_sequence() - wrap a byte stream in an ASN.1 SEQUENCE + * @data: pointer to encode at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @seq: data to be encoded as a sequence + * @len: length of the data to be encoded as a sequence + * + * Fill in a sequence. To encode in place, pass NULL for @seq and -1 + * for @len; then call again once the length is known (still with NULL + * for @seq). In order to avoid having to keep both before and after + * pointers, the repeat expects to be called with @data pointing to + * where the first encode placed it. + */ +unsigned char * +asn1_encode_sequence(unsigned char *data, const unsigned char *end_data, + const unsigned char *seq, int len) +{ + int data_len = end_data - data; + int ret; + + if (!seq && WARN(len > 127, + "BUG: recode sequence is too big (>127)")) + return ERR_PTR(-EINVAL); + + if (IS_ERR(data)) + return data; + + if (!seq && len >= 0) { + /* + * we're recoding, so move back to the start of the + * sequence and install a dummy length because the + * real length should be NULL + */ + data -= 2; + data_len = 2; + } + + if (data_len < 2) + return ERR_PTR(-EINVAL); + + *(data++) = _tag(UNIV, CONS, SEQ); + data_len--; + + ret = asn1_encode_length(&data, &data_len, len); + if (ret) + return ERR_PTR(ret); + + if (!seq) + return data; + + if (data_len < len) + return ERR_PTR(-EINVAL); + + memcpy(data, seq, len); + data += len; + + return data; +} +EXPORT_SYMBOL_GPL(asn1_encode_sequence); + +/** + * asn1_encode_boolean() - encode a boolean value to ASN.1 + * @data: pointer to encode at + * @end_data: end of data pointer, points one beyond last usable byte in @data + * @val: the boolean true/false value + */ +unsigned char * +asn1_encode_boolean(unsigned char *data, const unsigned char *end_data, + bool val) +{ + int data_len = end_data - data; + + if (IS_ERR(data)) + return data; + + /* booleans are 3 bytes: tag, length == 1 and value == 0 or 1 */ + if (data_len < 3) + return ERR_PTR(-EINVAL); + + *(data++) = _tag(UNIV, PRIM, BOOL); + data_len--; + + asn1_encode_length(&data, &data_len, 1); + + if (val) + *(data++) = 1; + else + *(data++) = 0; + + return data; +} +EXPORT_SYMBOL_GPL(asn1_encode_boolean); + +MODULE_LICENSE("GPL"); diff --git a/lib/crypto/chacha.c b/lib/crypto/chacha.c index 4ccbec442469..b748fd3d256e 100644 --- a/lib/crypto/chacha.c +++ b/lib/crypto/chacha.c @@ -64,7 +64,7 @@ static void chacha_permute(u32 *x, int nrounds) } /** - * chacha_block - generate one keystream block and increment block counter + * chacha_block_generic - generate one keystream block and increment block counter * @state: input state matrix (16 32-bit words) * @stream: output keystream block (64 bytes) * @nrounds: number of rounds (20 or 12; 20 is recommended) @@ -92,7 +92,7 @@ EXPORT_SYMBOL(chacha_block_generic); /** * hchacha_block_generic - abbreviated ChaCha core, for XChaCha * @state: input state matrix (16 32-bit words) - * @out: output (8 32-bit words) + * @stream: output (8 32-bit words) * @nrounds: number of rounds (20 or 12; 20 is recommended) * * HChaCha is the ChaCha equivalent of HSalsa and is an intermediate step diff --git a/lib/crypto/poly1305-donna32.c b/lib/crypto/poly1305-donna32.c index 3cc77d94390b..7fb71845cc84 100644 --- a/lib/crypto/poly1305-donna32.c +++ b/lib/crypto/poly1305-donna32.c @@ -10,7 +10,8 @@ #include <asm/unaligned.h> #include <crypto/internal/poly1305.h> -void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16]) +void poly1305_core_setkey(struct poly1305_core_key *key, + const u8 raw_key[POLY1305_BLOCK_SIZE]) { /* r &= 0xffffffc0ffffffc0ffffffc0fffffff */ key->key.r[0] = (get_unaligned_le32(&raw_key[0])) & 0x3ffffff; diff --git a/lib/crypto/poly1305-donna64.c b/lib/crypto/poly1305-donna64.c index 6ae181bb4345..d34cf4053668 100644 --- a/lib/crypto/poly1305-donna64.c +++ b/lib/crypto/poly1305-donna64.c @@ -12,7 +12,8 @@ typedef __uint128_t u128; -void poly1305_core_setkey(struct poly1305_core_key *key, const u8 raw_key[16]) +void poly1305_core_setkey(struct poly1305_core_key *key, + const u8 raw_key[POLY1305_BLOCK_SIZE]) { u64 t0, t1; diff --git a/lib/crypto/poly1305.c b/lib/crypto/poly1305.c index 9d2d14df0fee..26d87fc3823e 100644 --- a/lib/crypto/poly1305.c +++ b/lib/crypto/poly1305.c @@ -12,7 +12,8 @@ #include <linux/module.h> #include <asm/unaligned.h> -void poly1305_init_generic(struct poly1305_desc_ctx *desc, const u8 *key) +void poly1305_init_generic(struct poly1305_desc_ctx *desc, + const u8 key[POLY1305_KEY_SIZE]) { poly1305_core_setkey(&desc->core_r, key); desc->s[0] = get_unaligned_le32(key + 16); diff --git a/lib/earlycpio.c b/lib/earlycpio.c index e83628882001..7921193f0424 100644 --- a/lib/earlycpio.c +++ b/lib/earlycpio.c @@ -40,7 +40,7 @@ enum cpio_fields { }; /** - * cpio_data find_cpio_data - Search for files in an uncompressed cpio + * find_cpio_data - Search for files in an uncompressed cpio * @path: The directory to search for, including a slash at the end * @data: Pointer to the cpio archive or a header inside * @len: Remaining length of the cpio based on data pointer @@ -49,7 +49,7 @@ enum cpio_fields { * matching file itself. It can be used to iterate through the cpio * to find all files inside of a directory path. * - * @return: struct cpio_data containing the address, length and + * Return: &struct cpio_data containing the address, length and * filename (with the directory path cut off) of the found file. * If you search for a filename and not for files in a directory, * pass the absolute path of the filename in the cpio and make sure diff --git a/lib/lru_cache.c b/lib/lru_cache.c index c69ee53d8dde..52313acbfa62 100644 --- a/lib/lru_cache.c +++ b/lib/lru_cache.c @@ -76,6 +76,7 @@ int lc_try_lock(struct lru_cache *lc) /** * lc_create - prepares to track objects in an active set * @name: descriptive name only used in lc_seq_printf_stats and lc_seq_dump_details + * @cache: cache root pointer * @max_pending_changes: maximum changes to accumulate until a transaction is required * @e_count: number of elements allowed to be active simultaneously * @e_size: size of the tracked objects @@ -627,7 +628,7 @@ void lc_set(struct lru_cache *lc, unsigned int enr, int index) } /** - * lc_dump - Dump a complete LRU cache to seq in textual form. + * lc_seq_dump_details - Dump a complete LRU cache to seq in textual form. * @lc: the lru cache to operate on * @seq: the &struct seq_file pointer to seq_printf into * @utext: user supplied additional "heading" or other info diff --git a/lib/math/div64.c b/lib/math/div64.c index 064d68a5391a..46866394fc84 100644 --- a/lib/math/div64.c +++ b/lib/math/div64.c @@ -232,4 +232,5 @@ u64 mul_u64_u64_div_u64(u64 a, u64 b, u64 c) return res + div64_u64(a * b, c); } +EXPORT_SYMBOL(mul_u64_u64_div_u64); #endif diff --git a/lib/oid_registry.c b/lib/oid_registry.c index f7ad43f28579..3dfaa836e7c5 100644 --- a/lib/oid_registry.c +++ b/lib/oid_registry.c @@ -11,6 +11,7 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/bug.h> +#include <linux/asn1.h> #include "oid_registry_data.c" MODULE_DESCRIPTION("OID Registry"); @@ -92,6 +93,29 @@ enum OID look_up_OID(const void *data, size_t datasize) } EXPORT_SYMBOL_GPL(look_up_OID); +/** + * parse_OID - Parse an OID from a bytestream + * @data: Binary representation of the header + OID + * @datasize: Size of the binary representation + * @oid: Pointer to oid to return result + * + * Parse an OID from a bytestream that holds the OID in the format + * ASN1_OID | length | oid. The length indicator must equal to datasize - 2. + * -EBADMSG is returned if the bytestream is too short. + */ +int parse_OID(const void *data, size_t datasize, enum OID *oid) +{ + const unsigned char *v = data; + + /* we need 2 bytes of header and at least 1 byte for oid */ + if (datasize < 3 || v[0] != ASN1_OID || v[1] != datasize - 2) + return -EBADMSG; + + *oid = look_up_OID(data + 2, datasize - 2); + return 0; +} +EXPORT_SYMBOL_GPL(parse_OID); + /* * sprint_OID - Print an Object Identifier into a buffer * @data: The encoded OID to print diff --git a/lib/parman.c b/lib/parman.c index a11f2f667639..3f8f8d422e62 100644 --- a/lib/parman.c +++ b/lib/parman.c @@ -297,7 +297,7 @@ EXPORT_SYMBOL(parman_destroy); * parman_prio_init - initializes a parman priority chunk * @parman: parman instance * @prio: parman prio structure to be initialized - * @prority: desired priority of the chunk + * @priority: desired priority of the chunk * * Note: all locking must be provided by the caller. * @@ -356,7 +356,7 @@ int parman_item_add(struct parman *parman, struct parman_prio *prio, EXPORT_SYMBOL(parman_item_add); /** - * parman_item_del - deletes parman item + * parman_item_remove - deletes parman item * @parman: parman instance * @prio: parman prio instance to delete the item from * @item: parman item instance diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 3a4da11b804d..b3afafe46fff 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -166,9 +166,9 @@ static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) /** * radix_tree_find_next_bit - find the next set bit in a memory region * - * @addr: The address to base the search on - * @size: The bitmap size in bits - * @offset: The bitnumber to start searching at + * @node: where to begin the search + * @tag: the tag index + * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. @@ -461,7 +461,7 @@ out: /** * radix_tree_shrink - shrink radix tree to minimum height - * @root radix tree root + * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { @@ -691,7 +691,7 @@ static inline int insert_entries(struct radix_tree_node *node, } /** - * __radix_tree_insert - insert into a radix tree + * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert @@ -919,6 +919,7 @@ EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root + * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * diff --git a/lib/test_kasan_module.c b/lib/test_kasan_module.c index eee017ff8980..f1017f345d6c 100644 --- a/lib/test_kasan_module.c +++ b/lib/test_kasan_module.c @@ -22,7 +22,7 @@ static noinline void __init copy_user_test(void) char *kmem; char __user *usermem; size_t size = 10; - int unused; + int __maybe_unused unused; kmem = kmalloc(size, GFP_KERNEL); if (!kmem) diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 8294f43f4981..8b1c318189ce 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -1530,24 +1530,24 @@ static noinline void check_store_range(struct xarray *xa) #ifdef CONFIG_XARRAY_MULTI static void check_split_1(struct xarray *xa, unsigned long index, - unsigned int order) + unsigned int order, unsigned int new_order) { - XA_STATE(xas, xa, index); - void *entry; - unsigned int i = 0; + XA_STATE_ORDER(xas, xa, index, new_order); + unsigned int i; xa_store_order(xa, index, order, xa, GFP_KERNEL); xas_split_alloc(&xas, xa, order, GFP_KERNEL); xas_lock(&xas); xas_split(&xas, xa, order); + for (i = 0; i < (1 << order); i += (1 << new_order)) + __xa_store(xa, index + i, xa_mk_index(index + i), 0); xas_unlock(&xas); - xa_for_each(xa, index, entry) { - XA_BUG_ON(xa, entry != xa); - i++; + for (i = 0; i < (1 << order); i++) { + unsigned int val = index + (i & ~((1 << new_order) - 1)); + XA_BUG_ON(xa, xa_load(xa, index + i) != xa_mk_index(val)); } - XA_BUG_ON(xa, i != 1 << order); xa_set_mark(xa, index, XA_MARK_0); XA_BUG_ON(xa, !xa_get_mark(xa, index, XA_MARK_0)); @@ -1557,14 +1557,16 @@ static void check_split_1(struct xarray *xa, unsigned long index, static noinline void check_split(struct xarray *xa) { - unsigned int order; + unsigned int order, new_order; XA_BUG_ON(xa, !xa_empty(xa)); for (order = 1; order < 2 * XA_CHUNK_SHIFT; order++) { - check_split_1(xa, 0, order); - check_split_1(xa, 1UL << order, order); - check_split_1(xa, 3UL << order, order); + for (new_order = 0; new_order < order; new_order++) { + check_split_1(xa, 0, order, new_order); + check_split_1(xa, 1UL << order, order, new_order); + check_split_1(xa, 3UL << order, order, new_order); + } } } #else diff --git a/lib/xarray.c b/lib/xarray.c index 5fa51614802a..f5d8f54907b4 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -987,7 +987,7 @@ static void node_set_marks(struct xa_node *node, unsigned int offset, * xas_split_alloc() - Allocate memory for splitting an entry. * @xas: XArray operation state. * @entry: New entry which will be stored in the array. - * @order: New entry order. + * @order: Current entry order. * @gfp: Memory allocation flags. * * This function should be called before calling xas_split(). @@ -1011,7 +1011,7 @@ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, do { unsigned int i; - void *sibling; + void *sibling = NULL; struct xa_node *node; node = kmem_cache_alloc(radix_tree_node_cachep, gfp); @@ -1021,7 +1021,7 @@ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, for (i = 0; i < XA_CHUNK_SIZE; i++) { if ((i & mask) == 0) { RCU_INIT_POINTER(node->slots[i], entry); - sibling = xa_mk_sibling(0); + sibling = xa_mk_sibling(i); } else { RCU_INIT_POINTER(node->slots[i], sibling); } @@ -1041,9 +1041,10 @@ EXPORT_SYMBOL_GPL(xas_split_alloc); * xas_split() - Split a multi-index entry into smaller entries. * @xas: XArray operation state. * @entry: New entry to store in the array. - * @order: New entry order. + * @order: Current entry order. * - * The value in the entry is copied to all the replacement entries. + * The size of the new entries is set in @xas. The value in @entry is + * copied to all the replacement entries. * * Context: Any context. The caller should hold the xa_lock. */ diff --git a/mm/filemap.c b/mm/filemap.c index 43700480d897..6ce832dc59e7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1969,8 +1969,14 @@ unlock: put: put_page(page); next: - if (!xa_is_value(page) && PageTransHuge(page)) - xas_set(&xas, page->index + thp_nr_pages(page)); + if (!xa_is_value(page) && PageTransHuge(page)) { + unsigned int nr_pages = thp_nr_pages(page); + + /* Final THP may cross MAX_LFS_FILESIZE on 32-bit */ + xas_set(&xas, page->index + nr_pages); + if (xas.xa_index < nr_pages) + break; + } } rcu_read_unlock(); @@ -2672,7 +2678,7 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, loff_t end, int whence) { XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); - pgoff_t max = (end - 1) / PAGE_SIZE; + pgoff_t max = (end - 1) >> PAGE_SHIFT; bool seek_data = (whence == SEEK_DATA); struct page *page; @@ -2681,7 +2687,8 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, rcu_read_lock(); while ((page = find_get_entry(&xas, max, XA_PRESENT))) { - loff_t pos = xas.xa_index * PAGE_SIZE; + loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; + unsigned int seek_size; if (start < pos) { if (!seek_data) @@ -2689,25 +2696,25 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, start = pos; } - pos += seek_page_size(&xas, page); + seek_size = seek_page_size(&xas, page); + pos = round_up(pos + 1, seek_size); start = page_seek_hole_data(&xas, mapping, page, start, pos, seek_data); if (start < pos) goto unlock; + if (start >= end) + break; + if (seek_size > PAGE_SIZE) + xas_set(&xas, pos >> PAGE_SHIFT); if (!xa_is_value(page)) put_page(page); } - rcu_read_unlock(); - if (seek_data) - return -ENXIO; - goto out; - + start = -ENXIO; unlock: rcu_read_unlock(); - if (!xa_is_value(page)) + if (page && !xa_is_value(page)) put_page(page); -out: if (start > end) return end; return start; @@ -1535,6 +1535,10 @@ struct page *get_dump_page(unsigned long addr) FOLL_FORCE | FOLL_DUMP | FOLL_GET); if (locked) mmap_read_unlock(mm); + + if (ret == 1 && is_page_poisoned(page)) + return NULL; + return (ret == 1) ? page : NULL; } #endif /* CONFIG_ELF_CORE */ diff --git a/mm/highmem.c b/mm/highmem.c index 86f2b9495f9c..6ef8f5e05e7e 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -618,7 +618,7 @@ void __kmap_local_sched_out(void) int idx; /* With debug all even slots are unmapped and act as guard */ - if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) { + if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { WARN_ON_ONCE(!pte_none(pteval)); continue; } @@ -654,7 +654,7 @@ void __kmap_local_sched_in(void) int idx; /* With debug all even slots are unmapped and act as guard */ - if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) { + if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) { WARN_ON_ONCE(!pte_none(pteval)); continue; } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5b1ab1f427c5..a86a58ef132d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -280,6 +280,17 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; + /* + * The caller will hold exactly one h_cg->css reference for the + * whole contiguous reservation region. But this area might be + * scattered when there are already some file_regions reside in + * it. As a result, many file_regions may share only one css + * reference. In order to ensure that one file_region must hold + * exactly one h_cg->css reference, we should do css_get for + * each file_region and leave the reference held by caller + * untouched. + */ + css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in @@ -293,6 +304,14 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, #endif } +static void put_uncharge_info(struct file_region *rg) +{ +#ifdef CONFIG_CGROUP_HUGETLB + if (rg->css) + css_put(rg->css); +#endif +} + static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { @@ -316,6 +335,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) prg->to = rg->to; list_del(&rg->link); + put_uncharge_info(rg); kfree(rg); rg = prg; @@ -327,6 +347,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) nrg->from = rg->from; list_del(&rg->link); + put_uncharge_info(rg); kfree(rg); } } @@ -662,7 +683,7 @@ retry: del += t - f; hugetlb_cgroup_uncharge_file_region( - resv, rg, t - f); + resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; @@ -683,7 +704,7 @@ retry: if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, - rg->to - rg->from); + rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; @@ -691,13 +712,13 @@ retry: if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, - t - rg->from); + t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, - rg->to - f); + rg->to - f, false); del += rg->to - f; rg->to = f; @@ -5187,6 +5208,10 @@ bool hugetlb_reserve_pages(struct inode *inode, */ long rsv_adjust; + /* + * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the + * reference to h_cg->css. See comment below for detail. + */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); @@ -5194,6 +5219,14 @@ bool hugetlb_reserve_pages(struct inode *inode, rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); + } else if (h_cg) { + /* + * The file_regions will hold their own reference to + * h_cg->css. So we should release the reference held + * via hugetlb_cgroup_charge_cgroup_rsvd() when we are + * done. + */ + hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return true; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index f68b51fcda3d..603a131e262d 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -391,7 +391,8 @@ void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start, void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, struct file_region *rg, - unsigned long nr_pages) + unsigned long nr_pages, + bool region_del) { if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages) return; @@ -400,7 +401,12 @@ void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv, !resv->reservation_counter) { page_counter_uncharge(rg->reservation_counter, nr_pages * resv->pages_per_hpage); - css_put(rg->css); + /* + * Only do css_put(rg->css) when we delete the entire region + * because one file_region must hold exactly one css reference. + */ + if (region_del) + css_put(rg->css); } } diff --git a/mm/internal.h b/mm/internal.h index 1432feec62df..cb3c5e0a7799 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -97,6 +97,26 @@ static inline void set_page_refcounted(struct page *page) set_page_count(page, 1); } +/* + * When kernel touch the user page, the user page may be have been marked + * poison but still mapped in user space, if without this page, the kernel + * can guarantee the data integrity and operation success, the kernel is + * better to check the posion status and avoid touching it, be good not to + * panic, coredump for process fatal signal is a sample case matching this + * scenario. Or if kernel can't guarantee the data integrity, it's better + * not to call this function, let kernel touch the poison page and get to + * panic. + */ +static inline bool is_page_poisoned(struct page *page) +{ + if (PageHWPoison(page)) + return true; + else if (PageHuge(page) && PageHWPoison(compound_head(page))) + return true; + + return false; +} + extern unsigned long highest_memmap_pfn; /* diff --git a/mm/kasan/common.c b/mm/kasan/common.c index b5e08d4cefec..7b53291dafa1 100644 --- a/mm/kasan/common.c +++ b/mm/kasan/common.c @@ -63,7 +63,7 @@ void __kasan_unpoison_range(const void *address, size_t size) kasan_unpoison(address, size); } -#if CONFIG_KASAN_STACK +#ifdef CONFIG_KASAN_STACK /* Unpoison the entire stack for a task. */ void kasan_unpoison_task_stack(struct task_struct *task) { diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 8c55634d6edd..3436c6bf7c0c 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -231,7 +231,7 @@ void *kasan_find_first_bad_addr(void *addr, size_t size); const char *kasan_get_bug_type(struct kasan_access_info *info); void kasan_metadata_fetch_row(char *buffer, void *row); -#if defined(CONFIG_KASAN_GENERIC) && CONFIG_KASAN_STACK +#if defined(CONFIG_KASAN_GENERIC) && defined(CONFIG_KASAN_STACK) void kasan_print_address_stack_frame(const void *addr); #else static inline void kasan_print_address_stack_frame(const void *addr) { } diff --git a/mm/kasan/report_generic.c b/mm/kasan/report_generic.c index 41f374585144..de732bc341c5 100644 --- a/mm/kasan/report_generic.c +++ b/mm/kasan/report_generic.c @@ -128,7 +128,7 @@ void kasan_metadata_fetch_row(char *buffer, void *row) memcpy(buffer, kasan_mem_to_shadow(row), META_BYTES_PER_ROW); } -#if CONFIG_KASAN_STACK +#ifdef CONFIG_KASAN_STACK static bool __must_check tokenize_frame_descr(const char **frame_descr, char *token, size_t max_tok_len, unsigned long *value) diff --git a/mm/kfence/core.c b/mm/kfence/core.c index 3b8ec938470a..d53c91f881a4 100644 --- a/mm/kfence/core.c +++ b/mm/kfence/core.c @@ -12,6 +12,7 @@ #include <linux/debugfs.h> #include <linux/kcsan-checks.h> #include <linux/kfence.h> +#include <linux/kmemleak.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/memblock.h> @@ -480,6 +481,14 @@ static bool __init kfence_init_pool(void) addr += 2 * PAGE_SIZE; } + /* + * The pool is live and will never be deallocated from this point on. + * Remove the pool object from the kmemleak object tree, as it would + * otherwise overlap with allocations returned by kfence_alloc(), which + * are registered with kmemleak through the slab post-alloc hook. + */ + kmemleak_free(__kfence_pool); + return true; err: diff --git a/mm/kmemleak.c b/mm/kmemleak.c index c0014d3b91c1..fe6e3ae8e8c6 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -97,6 +97,7 @@ #include <linux/atomic.h> #include <linux/kasan.h> +#include <linux/kfence.h> #include <linux/kmemleak.h> #include <linux/memory_hotplug.h> @@ -589,7 +590,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size, atomic_set(&object->use_count, 1); object->flags = OBJECT_ALLOCATED; object->pointer = ptr; - object->size = size; + object->size = kfence_ksize((void *)ptr) ?: size; object->excess_ref = 0; object->min_count = min_count; object->count = 0; /* white color initially */ diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c index b59054ef2e10..b890854ec761 100644 --- a/mm/mapping_dirty_helpers.c +++ b/mm/mapping_dirty_helpers.c @@ -165,10 +165,12 @@ static int wp_clean_pud_entry(pud_t *pud, unsigned long addr, unsigned long end, return 0; } +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD /* Huge pud */ walk->action = ACTION_CONTINUE; if (pud_trans_huge(pudval) || pud_devmap(pudval)) WARN_ON(pud_write(pudval) || pud_dirty(pudval)); +#endif return 0; } diff --git a/mm/memory.c b/mm/memory.c index 5efa07fb6cdc..550405fc3b5e 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -166,7 +166,7 @@ static int __init init_zero_pfn(void) zero_pfn = page_to_pfn(ZERO_PAGE(0)); return 0; } -core_initcall(init_zero_pfn); +early_initcall(init_zero_pfn); void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) { diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 0dc7149b0c61..1b9837419bf9 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -249,16 +249,6 @@ void tlb_flush_mmu(struct mmu_gather *tlb) tlb_flush_mmu_free(tlb); } -/** - * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down - * @tlb: the mmu_gather structure to initialize - * @mm: the mm_struct of the target address space - * @fullmm: @mm is without users and we're going to destroy the full address - * space (exit/execve) - * - * Called to initialize an (on-stack) mmu_gather structure for page-table - * tear-down from @mm. - */ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) { @@ -283,11 +273,30 @@ static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, inc_tlb_flush_pending(tlb->mm); } +/** + * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down + * @tlb: the mmu_gather structure to initialize + * @mm: the mm_struct of the target address space + * + * Called to initialize an (on-stack) mmu_gather structure for page-table + * tear-down from @mm. + */ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm) { __tlb_gather_mmu(tlb, mm, false); } +/** + * tlb_gather_mmu_fullmm - initialize an mmu_gather structure for page-table tear-down + * @tlb: the mmu_gather structure to initialize + * @mm: the mm_struct of the target address space + * + * In this case, @mm is without users and we're going to destroy the + * full address space (exit/execve). + * + * Called to initialize an (on-stack) mmu_gather structure for page-table + * tear-down from @mm. + */ void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm) { __tlb_gather_mmu(tlb, mm, true); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 61ee40ed804e..459d195d2ff6 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -501,10 +501,33 @@ static int mn_hlist_invalidate_range_start( ""); WARN_ON(mmu_notifier_range_blockable(range) || _ret != -EAGAIN); + /* + * We call all the notifiers on any EAGAIN, + * there is no way for a notifier to know if + * its start method failed, thus a start that + * does EAGAIN can't also do end. + */ + WARN_ON(ops->invalidate_range_end); ret = _ret; } } } + + if (ret) { + /* + * Must be non-blocking to get here. If there are multiple + * notifiers and one or more failed start, any that succeeded + * start are expecting their end to be called. Do so now. + */ + hlist_for_each_entry_rcu(subscription, &subscriptions->list, + hlist, srcu_read_lock_held(&srcu)) { + if (!subscription->ops->invalidate_range_end) + continue; + + subscription->ops->invalidate_range_end(subscription, + range); + } + } srcu_read_unlock(&srcu, id); return ret; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 9efaf430cfd3..fa1cf18bac97 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -170,7 +170,7 @@ static bool oom_unkillable_task(struct task_struct *p) return false; } -/** +/* * Check whether unreclaimable slab amount is greater than * all user memory(LRU pages). * dump_unreclaimable_slab() could help in the case that diff --git a/mm/page-writeback.c b/mm/page-writeback.c index eb34d204d4ee..9e35b636a393 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2833,6 +2833,22 @@ void wait_on_page_writeback(struct page *page) } EXPORT_SYMBOL_GPL(wait_on_page_writeback); +/* + * Wait for a page to complete writeback. Returns -EINTR if we get a + * fatal signal while waiting. + */ +int wait_on_page_writeback_killable(struct page *page) +{ + while (PageWriteback(page)) { + trace_wait_on_page_writeback(page, page_mapping(page)); + if (wait_on_page_bit_killable(page, PG_writeback)) + return -EINTR; + } + + return 0; +} +EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable); + /** * wait_for_stable_page() - wait for writeback to finish, if necessary. * @page: The page to wait on. diff --git a/mm/page_poison.c b/mm/page_poison.c index 65cdf844c8ad..655dc5895604 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -77,12 +77,14 @@ static void unpoison_page(struct page *page) void *addr; addr = kmap_atomic(page); + kasan_disable_current(); /* * Page poisoning when enabled poisons each and every page * that is freed to buddy. Thus no extra check is done to * see if a page was poisoned. */ - check_poison_mem(addr, PAGE_SIZE); + check_poison_mem(kasan_reset_tag(addr), PAGE_SIZE); + kasan_enable_current(); kunmap_atomic(addr); } diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h index 18b768ac7dca..095d7eaa0db4 100644 --- a/mm/percpu-internal.h +++ b/mm/percpu-internal.h @@ -87,7 +87,7 @@ extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; -extern int pcpu_nr_empty_pop_pages; +extern int pcpu_nr_empty_pop_pages[]; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c index c8400a2adbc2..f6026dbcdf6b 100644 --- a/mm/percpu-stats.c +++ b/mm/percpu-stats.c @@ -145,6 +145,7 @@ static int percpu_stats_show(struct seq_file *m, void *v) int slot, max_nr_alloc; int *buffer; enum pcpu_chunk_type type; + int nr_empty_pop_pages; alloc_buffer: spin_lock_irq(&pcpu_lock); @@ -165,7 +166,11 @@ alloc_buffer: goto alloc_buffer; } -#define PL(X) \ + nr_empty_pop_pages = 0; + for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) + nr_empty_pop_pages += pcpu_nr_empty_pop_pages[type]; + +#define PL(X) \ seq_printf(m, " %-20s: %12lld\n", #X, (long long int)pcpu_stats_ai.X) seq_printf(m, @@ -196,7 +201,7 @@ alloc_buffer: PU(nr_max_chunks); PU(min_alloc_size); PU(max_alloc_size); - P("empty_pop_pages", pcpu_nr_empty_pop_pages); + P("empty_pop_pages", nr_empty_pop_pages); seq_putc(m, '\n'); #undef PU diff --git a/mm/percpu.c b/mm/percpu.c index 6596a0a4286e..23308113a5ff 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -173,10 +173,10 @@ struct list_head *pcpu_chunk_lists __ro_after_init; /* chunk list slots */ static LIST_HEAD(pcpu_map_extend_chunks); /* - * The number of empty populated pages, protected by pcpu_lock. The - * reserved chunk doesn't contribute to the count. + * The number of empty populated pages by chunk type, protected by pcpu_lock. + * The reserved chunk doesn't contribute to the count. */ -int pcpu_nr_empty_pop_pages; +int pcpu_nr_empty_pop_pages[PCPU_NR_CHUNK_TYPES]; /* * The number of populated pages in use by the allocator, protected by @@ -556,7 +556,7 @@ static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; if (chunk != pcpu_reserved_chunk) - pcpu_nr_empty_pop_pages += nr; + pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr; } /* @@ -1832,7 +1832,7 @@ area_found: mutex_unlock(&pcpu_alloc_mutex); } - if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW) + if (pcpu_nr_empty_pop_pages[type] < PCPU_EMPTY_POP_PAGES_LOW) pcpu_schedule_balance_work(); /* clear the areas and return address relative to base address */ @@ -2000,7 +2000,7 @@ retry_pop: pcpu_atomic_alloc_failed = false; } else { nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH - - pcpu_nr_empty_pop_pages, + pcpu_nr_empty_pop_pages[type], 0, PCPU_EMPTY_POP_PAGES_HIGH); } @@ -2580,7 +2580,7 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, /* link the first chunk in */ pcpu_first_chunk = chunk; - pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages; + pcpu_nr_empty_pop_pages[PCPU_CHUNK_ROOT] = pcpu_first_chunk->nr_empty_pop_pages; pcpu_chunk_relocate(pcpu_first_chunk, -1); /* include all regions of the first chunk */ diff --git a/mm/ptdump.c b/mm/ptdump.c index 4354c1422d57..da751448d0e4 100644 --- a/mm/ptdump.c +++ b/mm/ptdump.c @@ -111,7 +111,7 @@ static int ptdump_pte_entry(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { struct ptdump_state *st = walk->private; - pte_t val = READ_ONCE(*pte); + pte_t val = ptep_get(pte); if (st->effective_prot) st->effective_prot(st, 4, pte_val(val)); diff --git a/mm/shuffle.c b/mm/shuffle.c index 9c2e145a747a..c13c33b247e8 100644 --- a/mm/shuffle.c +++ b/mm/shuffle.c @@ -147,8 +147,8 @@ void __meminit __shuffle_zone(struct zone *z) spin_unlock_irqrestore(&z->lock, flags); } -/** - * shuffle_free_memory - reduce the predictability of the page allocator +/* + * __shuffle_free_memory - reduce the predictability of the page allocator * @pgdat: node page data */ void __meminit __shuffle_free_memory(pg_data_t *pgdat) diff --git a/mm/z3fold.c b/mm/z3fold.c index b5dafa7e44e4..9d889ad2bb86 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -1346,8 +1346,22 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) page = list_entry(pos, struct page, lru); zhdr = page_address(page); - if (test_bit(PAGE_HEADLESS, &page->private)) + if (test_bit(PAGE_HEADLESS, &page->private)) { + /* + * For non-headless pages, we wait to do this + * until we have the page lock to avoid racing + * with __z3fold_alloc(). Headless pages don't + * have a lock (and __z3fold_alloc() will never + * see them), but we still need to test and set + * PAGE_CLAIMED to avoid racing with + * z3fold_free(), so just do it now before + * leaving the loop. + */ + if (test_and_set_bit(PAGE_CLAIMED, &page->private)) + continue; + break; + } if (kref_get_unless_zero(&zhdr->refcount) == 0) { zhdr = NULL; diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index f8761281aab0..434b4f042909 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -890,6 +890,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node, hlist_for_each_entry(vlan, &orig_node->vlan_list, list) { tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); + tt_vlan->reserved = 0; tt_vlan++; } @@ -973,6 +974,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv, tt_vlan->vid = htons(vlan->vid); tt_vlan->crc = htonl(vlan->tt.crc); + tt_vlan->reserved = 0; tt_vlan++; } diff --git a/net/bluetooth/ecdh_helper.c b/net/bluetooth/ecdh_helper.c index 3226fe02e875..989401f116e9 100644 --- a/net/bluetooth/ecdh_helper.c +++ b/net/bluetooth/ecdh_helper.c @@ -126,8 +126,6 @@ int set_ecdh_privkey(struct crypto_kpp *tfm, const u8 private_key[32]) int err; struct ecdh p = {0}; - p.curve_id = ECC_CURVE_NIST_P256; - if (private_key) { tmp = kmalloc(32, GFP_KERNEL); if (!tmp) diff --git a/net/bluetooth/selftest.c b/net/bluetooth/selftest.c index f71c6fa65fb3..f49604d44b87 100644 --- a/net/bluetooth/selftest.c +++ b/net/bluetooth/selftest.c @@ -205,7 +205,7 @@ static int __init test_ecdh(void) calltime = ktime_get(); - tfm = crypto_alloc_kpp("ecdh", 0, 0); + tfm = crypto_alloc_kpp("ecdh-nist-p256", 0, 0); if (IS_ERR(tfm)) { BT_ERR("Unable to create ECDH crypto context"); err = PTR_ERR(tfm); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index b0c1ee110eff..21e445993f39 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -1386,7 +1386,7 @@ static struct smp_chan *smp_chan_create(struct l2cap_conn *conn) goto zfree_smp; } - smp->tfm_ecdh = crypto_alloc_kpp("ecdh", 0, 0); + smp->tfm_ecdh = crypto_alloc_kpp("ecdh-nist-p256", 0, 0); if (IS_ERR(smp->tfm_ecdh)) { BT_ERR("Unable to create ECDH crypto context"); goto free_shash; @@ -3281,7 +3281,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) return ERR_CAST(tfm_cmac); } - tfm_ecdh = crypto_alloc_kpp("ecdh", 0, 0); + tfm_ecdh = crypto_alloc_kpp("ecdh-nist-p256", 0, 0); if (IS_ERR(tfm_ecdh)) { BT_ERR("Unable to create ECDH crypto context"); crypto_free_shash(tfm_cmac); @@ -3806,7 +3806,7 @@ int __init bt_selftest_smp(void) return PTR_ERR(tfm_cmac); } - tfm_ecdh = crypto_alloc_kpp("ecdh", 0, 0); + tfm_ecdh = crypto_alloc_kpp("ecdh-nist-p256", 0, 0); if (IS_ERR(tfm_ecdh)) { BT_ERR("Unable to create ECDH crypto context"); crypto_free_shash(tfm_cmac); diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index b89503832fcc..1e24d9a2c9a7 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -128,6 +128,8 @@ br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) { if (!fdb->dst) return; + if (test_bit(BR_FDB_LOCAL, &fdb->flags)) + return; switch (type) { case RTM_DELNEIGH: diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index 66e7af165494..32bc2821027f 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -105,14 +105,20 @@ static int __net_init broute_net_init(struct net *net) &net->xt.broute_table); } +static void __net_exit broute_net_pre_exit(struct net *net) +{ + ebt_unregister_table_pre_exit(net, "broute", &ebt_ops_broute); +} + static void __net_exit broute_net_exit(struct net *net) { - ebt_unregister_table(net, net->xt.broute_table, &ebt_ops_broute); + ebt_unregister_table(net, net->xt.broute_table); } static struct pernet_operations broute_net_ops = { .init = broute_net_init, .exit = broute_net_exit, + .pre_exit = broute_net_pre_exit, }; static int __init ebtable_broute_init(void) diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 78cb9b21022d..bcf982e12f16 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -99,14 +99,20 @@ static int __net_init frame_filter_net_init(struct net *net) &net->xt.frame_filter); } +static void __net_exit frame_filter_net_pre_exit(struct net *net) +{ + ebt_unregister_table_pre_exit(net, "filter", ebt_ops_filter); +} + static void __net_exit frame_filter_net_exit(struct net *net) { - ebt_unregister_table(net, net->xt.frame_filter, ebt_ops_filter); + ebt_unregister_table(net, net->xt.frame_filter); } static struct pernet_operations frame_filter_net_ops = { .init = frame_filter_net_init, .exit = frame_filter_net_exit, + .pre_exit = frame_filter_net_pre_exit, }; static int __init ebtable_filter_init(void) diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 0888936ef853..0d092773f816 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -99,14 +99,20 @@ static int __net_init frame_nat_net_init(struct net *net) &net->xt.frame_nat); } +static void __net_exit frame_nat_net_pre_exit(struct net *net) +{ + ebt_unregister_table_pre_exit(net, "nat", ebt_ops_nat); +} + static void __net_exit frame_nat_net_exit(struct net *net) { - ebt_unregister_table(net, net->xt.frame_nat, ebt_ops_nat); + ebt_unregister_table(net, net->xt.frame_nat); } static struct pernet_operations frame_nat_net_ops = { .init = frame_nat_net_init, .exit = frame_nat_net_exit, + .pre_exit = frame_nat_net_pre_exit, }; static int __init ebtable_nat_init(void) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index ebe33b60efd6..d481ff24a150 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1232,10 +1232,34 @@ out: return ret; } -void ebt_unregister_table(struct net *net, struct ebt_table *table, - const struct nf_hook_ops *ops) +static struct ebt_table *__ebt_find_table(struct net *net, const char *name) +{ + struct ebt_table *t; + + mutex_lock(&ebt_mutex); + + list_for_each_entry(t, &net->xt.tables[NFPROTO_BRIDGE], list) { + if (strcmp(t->name, name) == 0) { + mutex_unlock(&ebt_mutex); + return t; + } + } + + mutex_unlock(&ebt_mutex); + return NULL; +} + +void ebt_unregister_table_pre_exit(struct net *net, const char *name, const struct nf_hook_ops *ops) +{ + struct ebt_table *table = __ebt_find_table(net, name); + + if (table) + nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); +} +EXPORT_SYMBOL(ebt_unregister_table_pre_exit); + +void ebt_unregister_table(struct net *net, struct ebt_table *table) { - nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); __ebt_unregister_table(net, table); } diff --git a/net/can/bcm.c b/net/can/bcm.c index 0e5c37be4a2b..909b9e684e04 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -86,6 +86,8 @@ MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>"); MODULE_ALIAS("can-proto-2"); +#define BCM_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) + /* * easy access to the first 64 bit of can(fd)_frame payload. cp->data is * 64 bit aligned so the offset has to be multiples of 8 which is ensured @@ -1292,7 +1294,7 @@ static int bcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) /* no bound device as default => check msg_name */ DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); - if (msg->msg_namelen < CAN_REQUIRED_SIZE(*addr, can_ifindex)) + if (msg->msg_namelen < BCM_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) @@ -1534,7 +1536,7 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, struct net *net = sock_net(sk); int ret = 0; - if (len < CAN_REQUIRED_SIZE(*addr, can_ifindex)) + if (len < BCM_MIN_NAMELEN) return -EINVAL; lock_sock(sk); @@ -1616,8 +1618,8 @@ static int bcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { - __sockaddr_check_size(sizeof(struct sockaddr_can)); - msg->msg_namelen = sizeof(struct sockaddr_can); + __sockaddr_check_size(BCM_MIN_NAMELEN); + msg->msg_namelen = BCM_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } diff --git a/net/can/isotp.c b/net/can/isotp.c index 3ef7f78e553b..9f94ad3caee9 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -77,6 +77,8 @@ MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>"); MODULE_ALIAS("can-proto-6"); +#define ISOTP_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp) + #define SINGLE_MASK(id) (((id) & CAN_EFF_FLAG) ? \ (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \ (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG)) @@ -196,7 +198,7 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) nskb->dev = dev; can_skb_set_owner(nskb, sk); ncf = (struct canfd_frame *)nskb->data; - skb_put(nskb, so->ll.mtu); + skb_put_zero(nskb, so->ll.mtu); /* create & send flow control reply */ ncf->can_id = so->txid; @@ -215,8 +217,7 @@ static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus) if (ae) ncf->data[0] = so->opt.ext_address; - if (so->ll.mtu == CANFD_MTU) - ncf->flags = so->ll.tx_flags; + ncf->flags = so->ll.tx_flags; can_send_ret = can_send(nskb, 1); if (can_send_ret) @@ -780,7 +781,7 @@ isotp_tx_burst: can_skb_prv(skb)->skbcnt = 0; cf = (struct canfd_frame *)skb->data; - skb_put(skb, so->ll.mtu); + skb_put_zero(skb, so->ll.mtu); /* create consecutive frame */ isotp_fill_dataframe(cf, so, ae, 0); @@ -790,8 +791,7 @@ isotp_tx_burst: so->tx.sn %= 16; so->tx.bs++; - if (so->ll.mtu == CANFD_MTU) - cf->flags = so->ll.tx_flags; + cf->flags = so->ll.tx_flags; skb->dev = dev; can_skb_set_owner(skb, sk); @@ -897,7 +897,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) so->tx.idx = 0; cf = (struct canfd_frame *)skb->data; - skb_put(skb, so->ll.mtu); + skb_put_zero(skb, so->ll.mtu); /* check for single frame transmission depending on TX_DL */ if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) { @@ -939,8 +939,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) } /* send the first or only CAN frame */ - if (so->ll.mtu == CANFD_MTU) - cf->flags = so->ll.tx_flags; + cf->flags = so->ll.tx_flags; skb->dev = dev; skb->sk = sk; @@ -989,7 +988,8 @@ static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, sock_recv_timestamp(msg, sk, skb); if (msg->msg_name) { - msg->msg_namelen = sizeof(struct sockaddr_can); + __sockaddr_check_size(ISOTP_MIN_NAMELEN); + msg->msg_namelen = ISOTP_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } @@ -1059,7 +1059,7 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) int notify_enetdown = 0; int do_rx_reg = 1; - if (len < CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp)) + if (len < ISOTP_MIN_NAMELEN) return -EINVAL; /* do not register frame reception for functional addressing */ @@ -1155,13 +1155,13 @@ static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer) if (peer) return -EOPNOTSUPP; - memset(addr, 0, sizeof(*addr)); + memset(addr, 0, ISOTP_MIN_NAMELEN); addr->can_family = AF_CAN; addr->can_ifindex = so->ifindex; addr->can_addr.tp.rx_id = so->rxid; addr->can_addr.tp.tx_id = so->txid; - return sizeof(*addr); + return ISOTP_MIN_NAMELEN; } static int isotp_setsockopt(struct socket *sock, int level, int optname, @@ -1228,7 +1228,8 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname, if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU) return -EINVAL; - if (ll.mtu == CAN_MTU && ll.tx_dl > CAN_MAX_DLEN) + if (ll.mtu == CAN_MTU && + (ll.tx_dl > CAN_MAX_DLEN || ll.tx_flags != 0)) return -EINVAL; memcpy(&so->ll, &ll, sizeof(ll)); diff --git a/net/can/raw.c b/net/can/raw.c index 37b47a39a3ed..139d9471ddcf 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -60,6 +60,8 @@ MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>"); MODULE_ALIAS("can-proto-1"); +#define RAW_MIN_NAMELEN CAN_REQUIRED_SIZE(struct sockaddr_can, can_ifindex) + #define MASK_ALL 0 /* A raw socket has a list of can_filters attached to it, each receiving @@ -394,7 +396,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) int err = 0; int notify_enetdown = 0; - if (len < CAN_REQUIRED_SIZE(*addr, can_ifindex)) + if (len < RAW_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) return -EINVAL; @@ -475,11 +477,11 @@ static int raw_getname(struct socket *sock, struct sockaddr *uaddr, if (peer) return -EOPNOTSUPP; - memset(addr, 0, sizeof(*addr)); + memset(addr, 0, RAW_MIN_NAMELEN); addr->can_family = AF_CAN; addr->can_ifindex = ro->ifindex; - return sizeof(*addr); + return RAW_MIN_NAMELEN; } static int raw_setsockopt(struct socket *sock, int level, int optname, @@ -739,7 +741,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (msg->msg_name) { DECLARE_SOCKADDR(struct sockaddr_can *, addr, msg->msg_name); - if (msg->msg_namelen < CAN_REQUIRED_SIZE(*addr, can_ifindex)) + if (msg->msg_namelen < RAW_MIN_NAMELEN) return -EINVAL; if (addr->can_family != AF_CAN) @@ -832,8 +834,8 @@ static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name) { - __sockaddr_check_size(sizeof(struct sockaddr_can)); - msg->msg_namelen = sizeof(struct sockaddr_can); + __sockaddr_check_size(RAW_MIN_NAMELEN); + msg->msg_namelen = RAW_MIN_NAMELEN; memcpy(msg->msg_name, skb->cb, msg->msg_namelen); } diff --git a/net/core/dev.c b/net/core/dev.c index 6c5967e80132..1f79b9aa9a3f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1184,6 +1184,18 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) return -ENOMEM; for_each_netdev(net, d) { + struct netdev_name_node *name_node; + list_for_each_entry(name_node, &d->name_node->list, list) { + if (!sscanf(name_node->name, name, &i)) + continue; + if (i < 0 || i >= max_netdevices) + continue; + + /* avoid cases where sscanf is not exact inverse of printf */ + snprintf(buf, IFNAMSIZ, name, i); + if (!strncmp(buf, name_node->name, IFNAMSIZ)) + set_bit(i, inuse); + } if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) @@ -4294,6 +4306,13 @@ static inline void ____napi_schedule(struct softnet_data *sd, */ thread = READ_ONCE(napi->thread); if (thread) { + /* Avoid doing set_bit() if the thread is in + * INTERRUPTIBLE state, cause napi_thread_wait() + * makes sure to proceed with napi polling + * if the thread is explicitly woken from here. + */ + if (READ_ONCE(thread->state) != TASK_INTERRUPTIBLE) + set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); wake_up_process(thread); return; } @@ -5905,7 +5924,8 @@ static void skb_gro_reset_offset(struct sk_buff *skb) NAPI_GRO_CB(skb)->frag0_len = 0; if (!skb_headlen(skb) && pinfo->nr_frags && - !PageHighMem(skb_frag_page(frag0))) { + !PageHighMem(skb_frag_page(frag0)) && + (!NET_IP_ALIGN || !(skb_frag_off(frag0) & 3))) { NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0); NAPI_GRO_CB(skb)->frag0_len = min_t(unsigned int, skb_frag_size(frag0), @@ -6486,6 +6506,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done) WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | + NAPIF_STATE_SCHED_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, @@ -6968,19 +6989,29 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) static int napi_thread_wait(struct napi_struct *napi) { + bool woken = false; + set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop() && !napi_disable_pending(napi)) { - if (test_bit(NAPI_STATE_SCHED, &napi->state)) { + while (!kthread_should_stop()) { + /* Testing SCHED_THREADED bit here to make sure the current + * kthread owns this napi and could poll on this napi. + * Testing SCHED bit is not enough because SCHED bit might be + * set by some other busy poll thread or by napi_disable(). + */ + if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state) || woken) { WARN_ON(!list_empty(&napi->poll_list)); __set_current_state(TASK_RUNNING); return 0; } schedule(); + /* woken being true indicates this thread owns this napi. */ + woken = true; set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); + return -1; } @@ -11346,7 +11377,7 @@ static void __net_exit default_device_exit(struct net *net) continue; /* Leave virtual devices for the generic cleanup */ - if (dev->rtnl_link_ops) + if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 571f191c06d9..db65ce62b625 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1053,6 +1053,20 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) return 0; err_module_put: + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); + struct sk_buff *skb; + + del_timer_sync(&hw_data->send_timer); + cancel_work_sync(&hw_data->dm_alert_work); + while ((skb = __skb_dequeue(&hw_data->drop_queue))) { + struct devlink_trap_metadata *hw_metadata; + + hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; + net_dm_hw_metadata_free(hw_metadata); + consume_skb(skb); + } + } module_put(THIS_MODULE); return rc; } @@ -1134,6 +1148,15 @@ static int net_dm_trace_on_set(struct netlink_ext_ack *extack) err_unregister_trace: unregister_trace_kfree_skb(ops->kfree_skb_probe, NULL); err_module_put: + for_each_possible_cpu(cpu) { + struct per_cpu_dm_data *data = &per_cpu(dm_cpu_data, cpu); + struct sk_buff *skb; + + del_timer_sync(&data->send_timer); + cancel_work_sync(&data->dm_alert_work); + while ((skb = __skb_dequeue(&data->drop_queue))) + consume_skb(skb); + } module_put(THIS_MODULE); return rc; } diff --git a/net/core/dst.c b/net/core/dst.c index 0c01bd8d9d81..fb3bcba87744 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -237,37 +237,62 @@ void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) } EXPORT_SYMBOL(__dst_destroy_metrics_generic); -static struct dst_ops md_dst_ops = { - .family = AF_UNSPEC, -}; +struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie) +{ + return NULL; +} -static int dst_md_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) +u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old) { - WARN_ONCE(1, "Attempting to call output on metadata dst\n"); - kfree_skb(skb); - return 0; + return NULL; } -static int dst_md_discard(struct sk_buff *skb) +struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) { - WARN_ONCE(1, "Attempting to call input on metadata dst\n"); - kfree_skb(skb); - return 0; + return NULL; +} + +void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) +{ +} +EXPORT_SYMBOL_GPL(dst_blackhole_update_pmtu); + +void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk, + struct sk_buff *skb) +{ +} +EXPORT_SYMBOL_GPL(dst_blackhole_redirect); + +unsigned int dst_blackhole_mtu(const struct dst_entry *dst) +{ + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } +EXPORT_SYMBOL_GPL(dst_blackhole_mtu); + +static struct dst_ops dst_blackhole_ops = { + .family = AF_UNSPEC, + .neigh_lookup = dst_blackhole_neigh_lookup, + .check = dst_blackhole_check, + .cow_metrics = dst_blackhole_cow_metrics, + .update_pmtu = dst_blackhole_update_pmtu, + .redirect = dst_blackhole_redirect, + .mtu = dst_blackhole_mtu, +}; static void __metadata_dst_init(struct metadata_dst *md_dst, enum metadata_type type, u8 optslen) - { struct dst_entry *dst; dst = &md_dst->dst; - dst_init(dst, &md_dst_ops, NULL, 1, DST_OBSOLETE_NONE, + dst_init(dst, &dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, DST_METADATA | DST_NOCOUNT); - - dst->input = dst_md_discard; - dst->output = dst_md_discard_out; - memset(dst + 1, 0, sizeof(*md_dst) + optslen - sizeof(*dst)); md_dst->type = type; } diff --git a/net/core/filter.c b/net/core/filter.c index adfdad234674..9323d34d34cc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5658,7 +5658,7 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) return -EINVAL; - if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff)) + if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) return -EINVAL; dev = __dev_via_ifindex(dev, ifindex); @@ -5668,7 +5668,11 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb, mtu = READ_ONCE(dev->mtu); dev_len = mtu + dev->hard_header_len; - skb_len = skb->len + len_diff; /* minus result pass check */ + + /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ + skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len; + + skb_len += len_diff; /* minus result pass check */ if (skb_len <= dev_len) { ret = BPF_MTU_CHK_RET_SUCCESS; goto out; @@ -5713,6 +5717,10 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp, /* Add L2-header as dev MTU is L3 size */ dev_len = mtu + dev->hard_header_len; + /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */ + if (*mtu_len) + xdp_len = *mtu_len + dev->hard_header_len; + xdp_len += len_diff; /* minus result pass check */ if (xdp_len > dev_len) ret = BPF_MTU_CHK_RET_FRAG_NEEDED; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2ef2224b3bff..a96a4f5de0ce 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -176,7 +176,7 @@ void skb_flow_get_icmp_tci(const struct sk_buff *skb, * avoid confusion with packets without such field */ if (icmp_has_id(ih->type)) - key_icmp->id = ih->un.echo.id ? : 1; + key_icmp->id = ih->un.echo.id ? ntohs(ih->un.echo.id) : 1; else key_icmp->id = 0; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e2982b3970b8..8379719d1dce 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1379,7 +1379,7 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, * we can reinject the packet there. */ n2 = NULL; - if (dst) { + if (dst && dst->obsolete != DST_OBSOLETE_DEAD) { n2 = dst_neigh_lookup_skb(dst, skb); if (n2) n1 = n2; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1bdcb33fb561..3485b16a7ff3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2863,7 +2863,7 @@ static int do_setlink(const struct sk_buff *skb, BUG_ON(!(af_ops = rtnl_af_lookup(nla_type(af)))); - err = af_ops->set_link_af(dev, af); + err = af_ops->set_link_af(dev, af, extack); if (err < 0) { rcu_read_unlock(); goto errout; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 1261512d6807..5def3a2e85be 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -488,6 +488,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb if (unlikely(!msg)) return -EAGAIN; sk_msg_init(msg); + skb_set_owner_r(skb, sk); return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg); } @@ -790,7 +791,6 @@ static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int { switch (verdict) { case __SK_REDIRECT: - skb_set_owner_r(skb, sk); sk_psock_skb_redirect(skb); break; case __SK_PASS: @@ -808,10 +808,6 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) rcu_read_lock(); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { - /* We skip full set_owner_r here because if we do a SK_PASS - * or SK_DROP we can skip skb memory accounting and use the - * TLS context. - */ skb->sk = psock->sk; tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); @@ -880,12 +876,13 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) kfree_skb(skb); goto out; } - skb_set_owner_r(skb, sk); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { + skb->sk = sk; tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + skb->sk = NULL; } sk_psock_verdict_apply(psock, skb, ret); out: @@ -956,12 +953,13 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, kfree_skb(skb); goto out; } - skb_set_owner_r(skb, sk); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { + skb->sk = sk; tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + skb->sk = NULL; } sk_psock_verdict_apply(psock, skb, ret); out: diff --git a/net/core/sock.c b/net/core/sock.c index 0ed98f20448a..5ec90f99e102 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2132,16 +2132,10 @@ void skb_orphan_partial(struct sk_buff *skb) if (skb_is_tcp_pure_ack(skb)) return; - if (can_skb_orphan_partial(skb)) { - struct sock *sk = skb->sk; - - if (refcount_inc_not_zero(&sk->sk_refcnt)) { - WARN_ON(refcount_sub_and_test(skb->truesize, &sk->sk_wmem_alloc)); - skb->destructor = sock_efree; - } - } else { + if (can_skb_orphan_partial(skb)) + skb_set_owner_sk_safe(skb, skb->sk); + else skb_orphan(skb); - } } EXPORT_SYMBOL(skb_orphan_partial); @@ -3440,6 +3434,32 @@ static void tw_prot_cleanup(struct timewait_sock_ops *twsk_prot) twsk_prot->twsk_slab = NULL; } +static int tw_prot_init(const struct proto *prot) +{ + struct timewait_sock_ops *twsk_prot = prot->twsk_prot; + + if (!twsk_prot) + return 0; + + twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", + prot->name); + if (!twsk_prot->twsk_slab_name) + return -ENOMEM; + + twsk_prot->twsk_slab = + kmem_cache_create(twsk_prot->twsk_slab_name, + twsk_prot->twsk_obj_size, 0, + SLAB_ACCOUNT | prot->slab_flags, + NULL); + if (!twsk_prot->twsk_slab) { + pr_crit("%s: Can't create timewait sock SLAB cache!\n", + prot->name); + return -ENOMEM; + } + + return 0; +} + static void req_prot_cleanup(struct request_sock_ops *rsk_prot) { if (!rsk_prot) @@ -3496,22 +3516,8 @@ int proto_register(struct proto *prot, int alloc_slab) if (req_prot_init(prot)) goto out_free_request_sock_slab; - if (prot->twsk_prot != NULL) { - prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name); - - if (prot->twsk_prot->twsk_slab_name == NULL) - goto out_free_request_sock_slab; - - prot->twsk_prot->twsk_slab = - kmem_cache_create(prot->twsk_prot->twsk_slab_name, - prot->twsk_prot->twsk_obj_size, - 0, - SLAB_ACCOUNT | - prot->slab_flags, - NULL); - if (prot->twsk_prot->twsk_slab == NULL) - goto out_free_timewait_sock_slab; - } + if (tw_prot_init(prot)) + goto out_free_timewait_sock_slab; } mutex_lock(&proto_list_mutex); diff --git a/net/core/xdp.c b/net/core/xdp.c index 05354976c1fc..858276e72c68 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -350,7 +350,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); - napi_direct &= !xdp_return_frame_no_direct(); + if (napi_direct && xdp_return_frame_no_direct()) + napi_direct = false; page_pool_put_full_page(xa->page_pool, page, napi_direct); rcu_read_unlock(); break; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 1f73603913f5..2be5c69824f9 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -319,6 +319,11 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) return 0; /* discard, don't send a reset here */ + if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { + __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); + return 0; + } + if (dccp_bad_service_code(sk, service)) { dcb->dccpd_reset_code = DCCP_RESET_CODE_BAD_SERVICE_CODE; goto drop; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 4d4956ed303b..3c3e56a1f34d 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -795,8 +795,14 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) list_for_each_entry(dp, &dst->ports, list) { err = dsa_port_setup(dp); - if (err) + if (err) { + dsa_port_devlink_teardown(dp); + dp->type = DSA_PORT_TYPE_UNUSED; + err = dsa_port_devlink_setup(dp); + if (err) + goto teardown; continue; + } } return 0; @@ -1066,6 +1072,7 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) { struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst = ds->dst; + const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol tag_protocol; tag_protocol = dsa_get_tag_protocol(dp, master); @@ -1080,14 +1087,16 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) * nothing to do here. */ } else { - dst->tag_ops = dsa_tag_driver_get(tag_protocol); - if (IS_ERR(dst->tag_ops)) { - if (PTR_ERR(dst->tag_ops) == -ENOPROTOOPT) + tag_ops = dsa_tag_driver_get(tag_protocol); + if (IS_ERR(tag_ops)) { + if (PTR_ERR(tag_ops) == -ENOPROTOOPT) return -EPROBE_DEFER; dev_warn(ds->dev, "No tagger for this switch\n"); dp->master = NULL; - return PTR_ERR(dst->tag_ops); + return PTR_ERR(tag_ops); } + + dst->tag_ops = tag_ops; } dp->master = master; diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 4b5da89dc27a..32963276452f 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -107,7 +107,7 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, bool unset_vlan_filtering = br_vlan_enabled(info->br); struct dsa_switch_tree *dst = ds->dst; struct netlink_ext_ack extack = {0}; - int err, i; + int err, port; if (dst->index == info->tree_index && ds->index == info->sw_index && ds->ops->port_bridge_join) @@ -124,13 +124,16 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds, * it. That is a good thing, because that lets us handle it and also * handle the case where the switch's vlan_filtering setting is global * (not per port). When that happens, the correct moment to trigger the - * vlan_filtering callback is only when the last port left this bridge. + * vlan_filtering callback is only when the last port leaves the last + * VLAN-aware bridge. */ if (unset_vlan_filtering && ds->vlan_filtering_is_global) { - for (i = 0; i < ds->num_ports; i++) { - if (i == info->port) - continue; - if (dsa_to_port(ds, i)->bridge_dev == info->br) { + for (port = 0; port < ds->num_ports; port++) { + struct net_device *bridge_dev; + + bridge_dev = dsa_to_port(ds, port)->bridge_dev; + + if (bridge_dev && br_vlan_enabled(bridge_dev)) { unset_vlan_filtering = false; break; } diff --git a/net/ethtool/common.c b/net/ethtool/common.c index c6a383dfd6c2..f9dcbad84788 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -273,6 +273,7 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(10000, KR, Full), [ETHTOOL_LINK_MODE_10000baseR_FEC_BIT] = { .speed = SPEED_10000, + .lanes = 1, .duplex = DUPLEX_FULL, }, __DEFINE_LINK_MODE_PARAMS(20000, MLD2, Full), @@ -562,3 +563,19 @@ void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops) rtnl_unlock(); } EXPORT_SYMBOL_GPL(ethtool_set_ethtool_phy_ops); + +void +ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, + enum ethtool_link_mode_bit_indices link_mode) +{ + const struct link_mode_info *link_info; + + if (WARN_ON_ONCE(link_mode >= __ETHTOOL_LINK_MODE_MASK_NBITS)) + return; + + link_info = &link_mode_params[link_mode]; + link_ksettings->base.speed = link_info->speed; + link_ksettings->lanes = link_info->lanes; + link_ksettings->base.duplex = link_info->duplex; +} +EXPORT_SYMBOL_GPL(ethtool_params_from_link_mode); diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c index 901b7de941ab..e10bfcc07853 100644 --- a/net/ethtool/eee.c +++ b/net/ethtool/eee.c @@ -169,8 +169,8 @@ int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info) ethnl_update_bool32(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod); ethnl_update_bool32(&eee.tx_lpi_enabled, tb[ETHTOOL_A_EEE_TX_LPI_ENABLED], &mod); - ethnl_update_bool32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER], - &mod); + ethnl_update_u32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER], + &mod); ret = 0; if (!mod) goto out_ops; diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index 24783b71c584..771688e1b0da 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -426,29 +426,13 @@ struct ethtool_link_usettings { int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { - const struct link_mode_info *link_info; - int err; - ASSERT_RTNL(); if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; memset(link_ksettings, 0, sizeof(*link_ksettings)); - - link_ksettings->link_mode = -1; - err = dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); - if (err) - return err; - - if (link_ksettings->link_mode != -1) { - link_info = &link_mode_params[link_ksettings->link_mode]; - link_ksettings->base.speed = link_info->speed; - link_ksettings->lanes = link_info->lanes; - link_ksettings->base.duplex = link_info->duplex; - } - - return 0; + return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } EXPORT_SYMBOL(__ethtool_get_link_ksettings); diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 6eabd58d81bf..cde9f3169ae5 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -36,9 +36,9 @@ static inline int ethnl_strz_size(const char *s) /** * ethnl_put_strz() - put string attribute with fixed size string - * @skb: skb with the message - * @attrype: attribute type - * @s: ETH_GSTRING_LEN sized string (may not be null terminated) + * @skb: skb with the message + * @attrtype: attribute type + * @s: ETH_GSTRING_LEN sized string (may not be null terminated) * * Puts an attribute with null terminated string from @s into the message. * diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index 09998dc5c185..d4ac02718b72 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -38,16 +38,16 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base, if (!dev->ethtool_ops->get_pauseparam) return -EOPNOTSUPP; + ethtool_stats_init((u64 *)&data->pausestat, + sizeof(data->pausestat) / 8); + ret = ethnl_ops_begin(dev); if (ret < 0) return ret; dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam); if (req_base->flags & ETHTOOL_FLAG_STATS && - dev->ethtool_ops->get_pause_stats) { - ethtool_stats_init((u64 *)&data->pausestat, - sizeof(data->pausestat) / 8); + dev->ethtool_ops->get_pause_stats) dev->ethtool_ops->get_pause_stats(dev, &data->pausestat); - } ethnl_ops_complete(dev); return 0; diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 7444ec6e298e..bfcdc75fc01e 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -217,6 +217,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; + skb_reset_mac_header(skb); hsr_forward_skb(skb, master); } else { atomic_long_inc(&dev->tx_dropped); diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c index ed82a470b6e1..b218e4594009 100644 --- a/net/hsr/hsr_forward.c +++ b/net/hsr/hsr_forward.c @@ -555,12 +555,6 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port) { struct hsr_frame_info frame; - if (skb_mac_header(skb) != skb->data) { - WARN_ONCE(1, "%s:%d: Malformed frame (port_src %s)\n", - __FILE__, __LINE__, port->dev->name); - goto out_drop; - } - if (fill_frame_info(&frame, skb, port) < 0) goto out_drop; diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 9c640d670ffe..0c1b0770c59e 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -551,9 +551,7 @@ ieee802154_llsec_parse_key_id(struct genl_info *info, desc->mode = nla_get_u8(info->attrs[IEEE802154_ATTR_LLSEC_KEY_MODE]); if (desc->mode == IEEE802154_SCF_KEY_IMPLICIT) { - if (!info->attrs[IEEE802154_ATTR_PAN_ID] && - !(info->attrs[IEEE802154_ATTR_SHORT_ADDR] || - info->attrs[IEEE802154_ATTR_HW_ADDR])) + if (!info->attrs[IEEE802154_ATTR_PAN_ID]) return -EINVAL; desc->device_addr.pan_id = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_PAN_ID]); @@ -562,6 +560,9 @@ ieee802154_llsec_parse_key_id(struct genl_info *info, desc->device_addr.mode = IEEE802154_ADDR_SHORT; desc->device_addr.short_addr = nla_get_shortaddr(info->attrs[IEEE802154_ATTR_SHORT_ADDR]); } else { + if (!info->attrs[IEEE802154_ATTR_HW_ADDR]) + return -EINVAL; + desc->device_addr.mode = IEEE802154_ADDR_LONG; desc->device_addr.extended_addr = nla_get_hwaddr(info->attrs[IEEE802154_ATTR_HW_ADDR]); } diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index 7c5a1aa5adb4..05f6bd89a7dd 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -820,8 +820,13 @@ nl802154_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, goto nla_put_failure; #ifdef CONFIG_IEEE802154_NL802154_EXPERIMENTAL + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + goto out; + if (nl802154_get_llsec_params(msg, rdev, wpan_dev) < 0) goto nla_put_failure; + +out: #endif /* CONFIG_IEEE802154_NL802154_EXPERIMENTAL */ genlmsg_end(msg, hdr); @@ -1384,6 +1389,9 @@ static int nl802154_set_llsec_params(struct sk_buff *skb, u32 changed = 0; int ret; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (info->attrs[NL802154_ATTR_SEC_ENABLED]) { u8 enabled; @@ -1490,6 +1498,11 @@ nl802154_dump_llsec_key(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { + err = skb->len; + goto out_err; + } + if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; @@ -1544,7 +1557,11 @@ static int nl802154_add_llsec_key(struct sk_buff *skb, struct genl_info *info) struct ieee802154_llsec_key_id id = { }; u32 commands[NL802154_CMD_FRAME_NR_IDS / 32] = { }; - if (nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + + if (!info->attrs[NL802154_ATTR_SEC_KEY] || + nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) return -EINVAL; if (!attrs[NL802154_KEY_ATTR_USAGE_FRAMES] || @@ -1592,7 +1609,11 @@ static int nl802154_del_llsec_key(struct sk_buff *skb, struct genl_info *info) struct nlattr *attrs[NL802154_KEY_ATTR_MAX + 1]; struct ieee802154_llsec_key_id id; - if (nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + + if (!info->attrs[NL802154_ATTR_SEC_KEY] || + nla_parse_nested_deprecated(attrs, NL802154_KEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_KEY], nl802154_key_policy, info->extack)) return -EINVAL; if (ieee802154_llsec_parse_key_id(attrs[NL802154_KEY_ATTR_ID], &id) < 0) @@ -1656,6 +1677,11 @@ nl802154_dump_llsec_dev(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { + err = skb->len; + goto out_err; + } + if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; @@ -1742,6 +1768,9 @@ static int nl802154_add_llsec_dev(struct sk_buff *skb, struct genl_info *info) struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_device dev_desc; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (ieee802154_llsec_parse_device(info->attrs[NL802154_ATTR_SEC_DEVICE], &dev_desc) < 0) return -EINVAL; @@ -1757,7 +1786,11 @@ static int nl802154_del_llsec_dev(struct sk_buff *skb, struct genl_info *info) struct nlattr *attrs[NL802154_DEV_ATTR_MAX + 1]; __le64 extended_addr; - if (nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack)) + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + + if (!info->attrs[NL802154_ATTR_SEC_DEVICE] || + nla_parse_nested_deprecated(attrs, NL802154_DEV_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVICE], nl802154_dev_policy, info->extack)) return -EINVAL; if (!attrs[NL802154_DEV_ATTR_EXTENDED_ADDR]) @@ -1825,6 +1858,11 @@ nl802154_dump_llsec_devkey(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { + err = skb->len; + goto out_err; + } + if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; @@ -1882,6 +1920,9 @@ static int nl802154_add_llsec_devkey(struct sk_buff *skb, struct genl_info *info struct ieee802154_llsec_device_key key; __le64 extended_addr; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] || nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack) < 0) return -EINVAL; @@ -1913,7 +1954,11 @@ static int nl802154_del_llsec_devkey(struct sk_buff *skb, struct genl_info *info struct ieee802154_llsec_device_key key; __le64 extended_addr; - if (nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack)) + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + + if (!info->attrs[NL802154_ATTR_SEC_DEVKEY] || + nla_parse_nested_deprecated(attrs, NL802154_DEVKEY_ATTR_MAX, info->attrs[NL802154_ATTR_SEC_DEVKEY], nl802154_devkey_policy, info->extack)) return -EINVAL; if (!attrs[NL802154_DEVKEY_ATTR_EXTENDED_ADDR]) @@ -1986,6 +2031,11 @@ nl802154_dump_llsec_seclevel(struct sk_buff *skb, struct netlink_callback *cb) if (err) return err; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) { + err = skb->len; + goto out_err; + } + if (!wpan_dev->netdev) { err = -EINVAL; goto out_err; @@ -2070,6 +2120,9 @@ static int nl802154_add_llsec_seclevel(struct sk_buff *skb, struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_seclevel sl; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) return -EINVAL; @@ -2085,6 +2138,9 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb, struct wpan_dev *wpan_dev = dev->ieee802154_ptr; struct ieee802154_llsec_seclevel sl; + if (wpan_dev->iftype == NL802154_IFTYPE_MONITOR) + return -EOPNOTSUPP; + if (!info->attrs[NL802154_ATTR_SEC_LEVEL] || llsec_parse_seclevel(info->attrs[NL802154_ATTR_SEC_LEVEL], &sl) < 0) @@ -2098,11 +2154,7 @@ static int nl802154_del_llsec_seclevel(struct sk_buff *skb, #define NL802154_FLAG_NEED_NETDEV 0x02 #define NL802154_FLAG_NEED_RTNL 0x04 #define NL802154_FLAG_CHECK_NETDEV_UP 0x08 -#define NL802154_FLAG_NEED_NETDEV_UP (NL802154_FLAG_NEED_NETDEV |\ - NL802154_FLAG_CHECK_NETDEV_UP) #define NL802154_FLAG_NEED_WPAN_DEV 0x10 -#define NL802154_FLAG_NEED_WPAN_DEV_UP (NL802154_FLAG_NEED_WPAN_DEV |\ - NL802154_FLAG_CHECK_NETDEV_UP) static int nl802154_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index d99e1be94019..36ed85bf2ad5 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -141,7 +141,7 @@ static void ah_output_done(struct crypto_async_request *base, int err) } kfree(AH_SKB_CB(skb)->tmp); - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } static int ah_output(struct xfrm_state *x, struct sk_buff *skb) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 75f67994fc85..2e35f68da40a 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1978,7 +1978,8 @@ static int inet_validate_link_af(const struct net_device *dev, return 0; } -static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) +static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla, + struct netlink_ext_ack *extack) { struct in_device *in_dev = __in_dev_get_rcu(dev); struct nlattr *a, *tb[IFLA_INET_MAX+1]; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index a3271ec3e162..4b834bbf95e0 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -279,7 +279,7 @@ static void esp_output_done(struct crypto_async_request *base, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } } diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 601f5fbfc63f..33687cf58286 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -217,10 +217,12 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb, if ((!(skb->dev->gso_partial_features & NETIF_F_HW_ESP) && !(features & NETIF_F_HW_ESP)) || x->xso.dev != skb->dev) - esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); + esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK | + NETIF_F_SCTP_CRC); else if (!(features & NETIF_F_HW_ESP_TX_CSUM) && !(skb->dev->gso_partial_features & NETIF_F_HW_ESP_TX_CSUM)) - esp_features = features & ~NETIF_F_CSUM_MASK; + esp_features = features & ~(NETIF_F_CSUM_MASK | + NETIF_F_SCTP_CRC); xo->flags |= XFRM_GSO_SEGMENT; @@ -312,8 +314,17 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features_ ip_hdr(skb)->tot_len = htons(skb->len); ip_send_check(ip_hdr(skb)); - if (hw_offload) + if (hw_offload) { + if (!skb_ext_add(skb, SKB_EXT_SEC_PATH)) + return -ENOMEM; + + xo = xfrm_offload(skb); + if (!xo) + return -EINVAL; + + xo->flags |= XFRM_XMIT; return 0; + } err = esp_output_tail(x, skb, &esp); if (err) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 6bd7ca09af03..fd472eae4f5c 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -705,12 +705,15 @@ static bool reqsk_queue_unlink(struct request_sock *req) return found; } -void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) +bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req) { - if (reqsk_queue_unlink(req)) { + bool unlinked = reqsk_queue_unlink(req); + + if (unlinked) { reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); reqsk_put(req); } + return unlinked; } EXPORT_SYMBOL(inet_csk_reqsk_queue_drop); diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index eb207089ece0..31c6c6d99d5e 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -218,7 +218,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, } if (dst->flags & DST_XFRM_QUEUE) - goto queued; + goto xmit; if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { dev->stats.tx_carrier_errors++; @@ -238,6 +238,8 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { + if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) + goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } else { @@ -251,7 +253,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } -queued: +xmit: skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 47db1bfdaaa0..bc2f6ca97152 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -309,7 +309,7 @@ have_carrier: */ static void __init ic_close_devs(void) { - struct net_device *selected_dev = ic_dev->dev; + struct net_device *selected_dev = ic_dev ? ic_dev->dev : NULL; struct ic_device *d, *next; struct net_device *dev; @@ -317,16 +317,18 @@ static void __init ic_close_devs(void) next = ic_first_dev; while ((d = next)) { bool bring_down = (d != ic_dev); - struct net_device *lower_dev; + struct net_device *lower; struct list_head *iter; next = d->next; dev = d->dev; - netdev_for_each_lower_dev(selected_dev, lower_dev, iter) { - if (dev == lower_dev) { - bring_down = false; - break; + if (selected_dev) { + netdev_for_each_lower_dev(selected_dev, lower, iter) { + if (dev == lower) { + bring_down = false; + break; + } } } if (bring_down) { diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index c576a63d09db..d6d45d820d79 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -203,7 +203,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); - private = rcu_access_pointer(table->private); + private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; @@ -649,7 +649,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care @@ -673,7 +673,7 @@ static int copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct arpt_entry *e; struct xt_counters *counters; - struct xt_table_info *private = xt_table_get_private_protected(table); + struct xt_table_info *private = table->private; int ret = 0; void *loc_cpu_entry; @@ -807,7 +807,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (!IS_ERR(t)) { struct arpt_getinfo info; - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -860,7 +860,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, @@ -1017,7 +1017,7 @@ static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = xt_table_get_private_protected(t); + private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1193,6 +1193,8 @@ static int translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; @@ -1330,7 +1332,7 @@ static int compat_copy_entries_to_user(unsigned int total_size, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; @@ -1379,7 +1381,7 @@ static int compat_get_entries(struct net *net, xt_compat_lock(NFPROTO_ARP); t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); @@ -1539,10 +1541,15 @@ out_free: return ret; } -void arpt_unregister_table(struct net *net, struct xt_table *table, - const struct nf_hook_ops *ops) +void arpt_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops) { nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); +} +EXPORT_SYMBOL(arpt_unregister_table_pre_exit); + +void arpt_unregister_table(struct net *net, struct xt_table *table) +{ __arpt_unregister_table(net, table); } diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index c216b9ad3bb2..6c300ba5634e 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -56,16 +56,24 @@ static int __net_init arptable_filter_table_init(struct net *net) return err; } +static void __net_exit arptable_filter_net_pre_exit(struct net *net) +{ + if (net->ipv4.arptable_filter) + arpt_unregister_table_pre_exit(net, net->ipv4.arptable_filter, + arpfilter_ops); +} + static void __net_exit arptable_filter_net_exit(struct net *net) { if (!net->ipv4.arptable_filter) return; - arpt_unregister_table(net, net->ipv4.arptable_filter, arpfilter_ops); + arpt_unregister_table(net, net->ipv4.arptable_filter); net->ipv4.arptable_filter = NULL; } static struct pernet_operations arptable_filter_net_ops = { .exit = arptable_filter_net_exit, + .pre_exit = arptable_filter_net_pre_exit, }; static int __init arptable_filter_init(void) diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index e8f6f9d86237..f77ea0dbe656 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -258,7 +258,7 @@ ipt_do_table(struct sk_buff *skb, WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); - private = rcu_access_pointer(table->private); + private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; @@ -791,7 +791,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -815,7 +815,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ipt_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; @@ -964,7 +964,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, AF_INET, name); if (!IS_ERR(t)) { struct ipt_getinfo info; - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -1018,7 +1018,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr, t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1173,7 +1173,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = xt_table_get_private_protected(t); + private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1428,6 +1428,8 @@ translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; @@ -1543,7 +1545,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; @@ -1589,7 +1591,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr, xt_compat_lock(AF_INET); t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 02d81d79deeb..bba150fdd265 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2687,44 +2687,15 @@ out: return rth; } -static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) -{ - return NULL; -} - -static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) -{ - unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); - - return mtu ? : dst->dev->mtu; -} - -static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu, - bool confirm_neigh) -{ -} - -static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb) -{ -} - -static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst, - unsigned long old) -{ - return NULL; -} - static struct dst_ops ipv4_dst_blackhole_ops = { - .family = AF_INET, - .check = ipv4_blackhole_dst_check, - .mtu = ipv4_blackhole_mtu, - .default_advmss = ipv4_default_advmss, - .update_pmtu = ipv4_rt_blackhole_update_pmtu, - .redirect = ipv4_rt_blackhole_redirect, - .cow_metrics = ipv4_rt_blackhole_cow_metrics, - .neigh_lookup = ipv4_neigh_lookup, + .family = AF_INET, + .default_advmss = ipv4_default_advmss, + .neigh_lookup = ipv4_neigh_lookup, + .check = dst_blackhole_check, + .cow_metrics = dst_blackhole_cow_metrics, + .update_pmtu = dst_blackhole_update_pmtu, + .redirect = dst_blackhole_redirect, + .mtu = dst_blackhole_mtu, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index f55095d3ed16..60465f077497 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1378,9 +1378,19 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) if (!table) goto err_alloc; - /* Update the variables to point into the current struct net */ - for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) - table[i].data += (void *)net - (void *)&init_net; + for (i = 0; i < ARRAY_SIZE(ipv4_net_table) - 1; i++) { + if (table[i].data) { + /* Update the variables to point into + * the current struct net + */ + table[i].data += (void *)net - (void *)&init_net; + } else { + /* Entries without data pointer are global; + * Make them read-only in non-init_net ns + */ + table[i].mode &= ~0222; + } + } } net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 0055ae0a3bf8..7513ba45553d 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -804,8 +804,11 @@ embryonic_reset: tcp_reset(sk, skb); } if (!fastopen) { - inet_csk_reqsk_queue_drop(sk, req); - __NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); + bool unlinked = inet_csk_reqsk_queue_drop(sk, req); + + if (unlinked) + __NET_INC_STATS(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); + *req_stolen = !unlinked; } return NULL; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 4a0478b17243..99d743eb9dc4 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2754,6 +2754,10 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, val = up->gso_size; break; + case UDP_GRO: + val = up->gro_enabled; + break; + /* The following two cannot be changed on UDP sockets, the return is * always 0 (which corresponds to the full checksum coverage of UDP). */ case UDPLITE_SEND_CSCOV: diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f2337fb756ac..a9e53f5942fa 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5669,7 +5669,8 @@ static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev, return 0; } -static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) +static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token, + struct netlink_ext_ack *extack) { struct inet6_ifaddr *ifp; struct net_device *dev = idev->dev; @@ -5680,12 +5681,29 @@ static int inet6_set_iftoken(struct inet6_dev *idev, struct in6_addr *token) if (!token) return -EINVAL; - if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) + + if (dev->flags & IFF_LOOPBACK) { + NL_SET_ERR_MSG_MOD(extack, "Device is loopback"); return -EINVAL; - if (!ipv6_accept_ra(idev)) + } + + if (dev->flags & IFF_NOARP) { + NL_SET_ERR_MSG_MOD(extack, + "Device does not do neighbour discovery"); + return -EINVAL; + } + + if (!ipv6_accept_ra(idev)) { + NL_SET_ERR_MSG_MOD(extack, + "Router advertisement is disabled on device"); return -EINVAL; - if (idev->cnf.rtr_solicits == 0) + } + + if (idev->cnf.rtr_solicits == 0) { + NL_SET_ERR_MSG(extack, + "Router solicitation is disabled on device"); return -EINVAL; + } write_lock_bh(&idev->lock); @@ -5793,7 +5811,8 @@ static int inet6_validate_link_af(const struct net_device *dev, return 0; } -static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) +static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla, + struct netlink_ext_ack *extack) { struct inet6_dev *idev = __in6_dev_get(dev); struct nlattr *tb[IFLA_INET6_MAX + 1]; @@ -5806,7 +5825,8 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) BUG(); if (tb[IFLA_INET6_TOKEN]) { - err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN])); + err = inet6_set_iftoken(idev, nla_data(tb[IFLA_INET6_TOKEN]), + extack); if (err) return err; } diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 440080da805b..080ee7f44c64 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -316,7 +316,7 @@ static void ah6_output_done(struct crypto_async_request *base, int err) } kfree(AH_SKB_CB(skb)->tmp); - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 153ad103ba74..727d791ed5e6 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -314,7 +314,7 @@ static void esp_output_done(struct crypto_async_request *base, int err) x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) esp_output_tail_tcp(x, skb); else - xfrm_output_resume(skb, err); + xfrm_output_resume(skb->sk, skb, err); } } diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index 1ca516fb30e1..4af56affaafd 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -254,9 +254,11 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb, skb->encap_hdr_csum = 1; if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) - esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK); + esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK | + NETIF_F_SCTP_CRC); else if (!(features & NETIF_F_HW_ESP_TX_CSUM)) - esp_features = features & ~NETIF_F_CSUM_MASK; + esp_features = features & ~(NETIF_F_CSUM_MASK | + NETIF_F_SCTP_CRC); xo->flags |= XFRM_GSO_SEGMENT; @@ -346,8 +348,17 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb, netdev_features ipv6_hdr(skb)->payload_len = htons(len); - if (hw_offload) + if (hw_offload) { + if (!skb_ext_add(skb, SKB_EXT_SEC_PATH)) + return -ENOMEM; + + xo = xfrm_offload(skb); + if (!xo) + return -EINVAL; + + xo->flags |= XFRM_XMIT; return 0; + } err = esp6_output_tail(x, skb, &esp); if (err) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index ef9d022e693f..679699e953f1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2486,7 +2486,7 @@ static int ipv6_route_native_seq_show(struct seq_file *seq, void *v) const struct net_device *dev; if (rt->nh) - fib6_nh = nexthop_fib6_nh(rt->nh); + fib6_nh = nexthop_fib6_nh_bh(rt->nh); seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index e9d2a4a409aa..80256717868e 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -245,16 +245,6 @@ static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev, if (ipv6_addr_is_multicast(&hdr->saddr)) goto err; - /* While RFC4291 is not explicit about v4mapped addresses - * in IPv6 headers, it seems clear linux dual-stack - * model can not deal properly with these. - * Security models could be fooled by ::ffff:127.0.0.1 for example. - * - * https://tools.ietf.org/html/draft-itojun-v6ops-v4mapped-harmful-02 - */ - if (ipv6_addr_v4mapped(&hdr->saddr)) - goto err; - skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 3fa0eca5a06f..42fe7db6bbb3 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -2244,6 +2244,16 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head t = rtnl_dereference(t->next); } } + + t = rtnl_dereference(ip6n->tnls_wc[0]); + while (t) { + /* If dev is in the same netns, it has already + * been added to the list by the previous loop. + */ + if (!net_eq(dev_net(t->dev), net)) + unregister_netdevice_queue(t->dev, list); + t = rtnl_dereference(t->next); + } } static int __net_init ip6_tnl_init_net(struct net *net) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index f10e7a72ea62..e0cc32e45880 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -494,7 +494,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } if (dst->flags & DST_XFRM_QUEUE) - goto queued; + goto xmit; x = dst->xfrm; if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr)) @@ -523,6 +523,8 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { + if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) + goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } @@ -531,7 +533,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) goto tx_err_dst_release; } -queued: +xmit: skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 0d453fa9e327..eb2b5404806c 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); - private = rcu_access_pointer(table->private); + private = READ_ONCE(table->private); /* Address dependency. */ cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; @@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; int ret = 0; const void *loc_cpu_entry; @@ -980,7 +980,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -1035,7 +1035,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr, t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { - struct xt_table_info *private = xt_table_get_private_protected(t); + struct xt_table_info *private = t->private; if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1189,7 +1189,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = xt_table_get_private_protected(t); + private = t->private; if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1443,6 +1443,8 @@ translate_compat_table(struct net *net, if (!newinfo) goto out_unlock; + memset(newinfo->entries, 0, size); + newinfo->number = compatr->num_entries; for (i = 0; i < NF_INET_NUMHOOKS; i++) { newinfo->hook_entry[i] = compatr->hook_entry[i]; @@ -1552,7 +1554,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = xt_table_get_private_protected(table); + const struct xt_table_info *private = table->private; void __user *pos; unsigned int size; int ret = 0; @@ -1598,7 +1600,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr, xt_compat_lock(AF_INET6); t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = xt_table_get_private_protected(t); + const struct xt_table_info *private = t->private; struct xt_table_info info; ret = compat_table_info(private, &info); if (!ret && get.size == info.size) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 1f56d9aae589..bf3646b57c68 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -298,7 +298,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && - !sock_net(sk)->ipv6.sysctl.ip_nonlocal_bind) { + !ipv6_can_nonlocal_bind(sock_net(sk), inet)) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1536f4948e86..373d48073106 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -260,34 +260,16 @@ static struct dst_ops ip6_dst_ops_template = { .confirm_neigh = ip6_confirm_neigh, }; -static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) -{ - unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); - - return mtu ? : dst->dev->mtu; -} - -static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu, - bool confirm_neigh) -{ -} - -static void ip6_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb) -{ -} - static struct dst_ops ip6_dst_blackhole_ops = { - .family = AF_INET6, - .destroy = ip6_dst_destroy, - .check = ip6_dst_check, - .mtu = ip6_blackhole_mtu, - .default_advmss = ip6_default_advmss, - .update_pmtu = ip6_rt_blackhole_update_pmtu, - .redirect = ip6_rt_blackhole_redirect, - .cow_metrics = dst_cow_metrics_generic, - .neigh_lookup = ip6_dst_neigh_lookup, + .family = AF_INET6, + .default_advmss = ip6_default_advmss, + .neigh_lookup = ip6_dst_neigh_lookup, + .check = ip6_dst_check, + .destroy = ip6_dst_destroy, + .cow_metrics = dst_cow_metrics_generic, + .update_pmtu = dst_blackhole_update_pmtu, + .redirect = dst_blackhole_redirect, + .mtu = dst_blackhole_mtu, }; static const u32 ip6_template_metrics[RTAX_MAX] = { @@ -5227,9 +5209,11 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, * nexthops have been replaced by first new, the rest should * be added to it. */ - cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | - NLM_F_REPLACE); - cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; + if (cfg->fc_nlinfo.nlh) { + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | + NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; + } nhn++; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 63ccd9f2dccc..9fdccf0718b5 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1867,9 +1867,9 @@ static void __net_exit sit_destroy_tunnels(struct net *net, if (dev->rtnl_link_ops == &sit_link_ops) unregister_netdevice_queue(dev, head); - for (prio = 1; prio < 4; prio++) { + for (prio = 0; prio < 4; prio++) { int h; - for (h = 0; h < IP6_SIT_HASH_SIZE; h++) { + for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) { struct ip_tunnel *t; t = rtnl_dereference(sitn->tunnels[prio][h]); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index bd44ded7e50c..d0f007741e8e 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1175,6 +1175,11 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; + if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { + __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); + return 0; + } + return tcp_conn_request(&tcp6_request_sock_ops, &tcp_request_sock_ipv6_ops, sk, skb); diff --git a/net/mac80211/aead_api.c b/net/mac80211/aead_api.c index d7b3d905d535..b00d6f5b33f4 100644 --- a/net/mac80211/aead_api.c +++ b/net/mac80211/aead_api.c @@ -23,6 +23,7 @@ int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); u8 *__aad; + int ret; aead_req = kzalloc(reqsize + aad_len, GFP_ATOMIC); if (!aead_req) @@ -40,10 +41,10 @@ int aead_encrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, aead_request_set_crypt(aead_req, sg, sg, data_len, b_0); aead_request_set_ad(aead_req, sg[0].length); - crypto_aead_encrypt(aead_req); + ret = crypto_aead_encrypt(aead_req); kfree_sensitive(aead_req); - return 0; + return ret; } int aead_decrypt(struct crypto_aead *tfm, u8 *b_0, u8 *aad, size_t aad_len, diff --git a/net/mac80211/aes_gmac.c b/net/mac80211/aes_gmac.c index 6f3b3a0cc10a..512cab073f2e 100644 --- a/net/mac80211/aes_gmac.c +++ b/net/mac80211/aes_gmac.c @@ -22,6 +22,7 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, struct aead_request *aead_req; int reqsize = sizeof(*aead_req) + crypto_aead_reqsize(tfm); const __le16 *fc; + int ret; if (data_len < GMAC_MIC_LEN) return -EINVAL; @@ -59,10 +60,10 @@ int ieee80211_aes_gmac(struct crypto_aead *tfm, const u8 *aad, u8 *nonce, aead_request_set_crypt(aead_req, sg, sg, 0, iv); aead_request_set_ad(aead_req, GMAC_AAD_LEN + data_len); - crypto_aead_encrypt(aead_req); + ret = crypto_aead_encrypt(aead_req); kfree_sensitive(aead_req); - return 0; + return ret; } struct crypto_aead *ieee80211_aes_gmac_key_setup(const u8 key[], diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c4c70e30ad7f..860bc35383d5 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1788,8 +1788,10 @@ static int ieee80211_change_station(struct wiphy *wiphy, } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && - sta->sdata->u.vlan.sta) + sta->sdata->u.vlan.sta) { + ieee80211_clear_fast_rx(sta); RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); + } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); @@ -2950,14 +2952,14 @@ static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, continue; for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) { - if (~sdata->rc_rateidx_mcs_mask[i][j]) { + if (sdata->rc_rateidx_mcs_mask[i][j] != 0xff) { sdata->rc_has_mcs_mask[i] = true; break; } } for (j = 0; j < NL80211_VHT_NSS_MAX; j++) { - if (~sdata->rc_rateidx_vht_mcs_mask[i][j]) { + if (sdata->rc_rateidx_vht_mcs_mask[i][j] != 0xffff) { sdata->rc_has_vht_mcs_mask[i] = true; break; } diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 1f552f374e97..a7ac53a2f00d 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -1874,6 +1874,8 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) /* remove beacon */ kfree(sdata->u.ibss.ie); + sdata->u.ibss.ie = NULL; + sdata->u.ibss.ie_len = 0; /* on the next join, re-program HT parameters */ memset(&ifibss->ht_capa, 0, sizeof(ifibss->ht_capa)); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4f3f8bb58e76..1b9c82616606 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -973,8 +973,19 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) continue; if (!dflt_chandef.chan) { + /* + * Assign the first enabled channel to dflt_chandef + * from the list of channels + */ + for (i = 0; i < sband->n_channels; i++) + if (!(sband->channels[i].flags & + IEEE80211_CHAN_DISABLED)) + break; + /* if none found then use the first anyway */ + if (i == sband->n_channels) + i = 0; cfg80211_chandef_create(&dflt_chandef, - &sband->channels[0], + &sband->channels[i], NL80211_CHAN_NO_HT); /* init channel we're on */ if (!local->use_chanctx && !local->_oper_chandef.chan) { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 2e33a1263518..96f487fc0071 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -4707,7 +4707,10 @@ static void ieee80211_sta_conn_mon_timer(struct timer_list *t) timeout = sta->rx_stats.last_rx; timeout += IEEE80211_CONNECTION_IDLE_TIME; - if (time_is_before_jiffies(timeout)) { + /* If timeout is after now, then update timer to fire at + * the later date, but do not actually probe at this time. + */ + if (time_is_after_jiffies(timeout)) { mod_timer(&ifmgd->conn_mon_timer, round_jiffies_up(timeout)); return; } @@ -5071,7 +5074,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, he_oper_ie = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ies->data, ies->len); if (he_oper_ie && - he_oper_ie[1] == ieee80211_he_oper_size(&he_oper_ie[3])) + he_oper_ie[1] >= ieee80211_he_oper_size(&he_oper_ie[3])) he_oper = (void *)(he_oper_ie + 3); else he_oper = NULL; diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 2f44f4919789..ecad9b10984f 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -805,7 +805,6 @@ minstrel_ht_group_min_rate_offset(struct minstrel_ht_sta *mi, int group, static u16 minstrel_ht_next_inc_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur) { - struct minstrel_mcs_group_data *mg; u8 type = MINSTREL_SAMPLE_TYPE_INC; int i, index = 0; u8 group; @@ -813,7 +812,6 @@ minstrel_ht_next_inc_rate(struct minstrel_ht_sta *mi, u32 fast_rate_dur) group = mi->sample[type].sample_group; for (i = 0; i < ARRAY_SIZE(minstrel_mcs_groups); i++) { group = (group + 1) % ARRAY_SIZE(minstrel_mcs_groups); - mg = &mi->groups[group]; index = minstrel_ht_group_min_rate_offset(mi, group, fast_rate_dur); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 5d06de61047a..3b3bcefbf657 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3573,7 +3573,7 @@ begin: test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags)) goto out; - if (vif->txqs_stopped[ieee80211_ac_from_tid(txq->tid)]) { + if (vif->txqs_stopped[txq->ac]) { set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags); goto out; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index f080fcf60e45..c0fa526a45b4 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -968,7 +968,7 @@ static void ieee80211_parse_extension_element(u32 *crc, break; case WLAN_EID_EXT_HE_OPERATION: if (len >= sizeof(*elems->he_operation) && - len == ieee80211_he_oper_size(data) - 1) { + len >= ieee80211_he_oper_size(data) - 1) { if (crc) *crc = crc32_be(*crc, (void *)elem, elem->datalen + 2); diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 585d33144c33..55550ead2ced 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -152,7 +152,7 @@ err_tfm0: crypto_free_sync_skcipher(key->tfm0); err_tfm: for (i = 0; i < ARRAY_SIZE(key->tfm); i++) - if (key->tfm[i]) + if (!IS_ERR_OR_NULL(key->tfm[i])) crypto_free_aead(key->tfm[i]); kfree_sensitive(key); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 444a38681e93..89a4225ed321 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -567,15 +567,15 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, } static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id, - struct in_addr *addr) + struct in_addr *addr, u16 port) { u8 hmac[SHA256_DIGEST_SIZE]; u8 msg[7]; msg[0] = addr_id; memcpy(&msg[1], &addr->s_addr, 4); - msg[5] = 0; - msg[6] = 0; + msg[5] = port >> 8; + msg[6] = port & 0xFF; mptcp_crypto_hmac_sha(key1, key2, msg, 7, hmac); @@ -584,15 +584,15 @@ static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id, #if IS_ENABLED(CONFIG_MPTCP_IPV6) static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id, - struct in6_addr *addr) + struct in6_addr *addr, u16 port) { u8 hmac[SHA256_DIGEST_SIZE]; u8 msg[19]; msg[0] = addr_id; memcpy(&msg[1], &addr->s6_addr, 16); - msg[17] = 0; - msg[18] = 0; + msg[17] = port >> 8; + msg[18] = port & 0xFF; mptcp_crypto_hmac_sha(key1, key2, msg, 19, hmac); @@ -646,7 +646,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * opts->ahmac = add_addr_generate_hmac(msk->local_key, msk->remote_key, opts->addr_id, - &opts->addr); + &opts->addr, + opts->port); } } #if IS_ENABLED(CONFIG_MPTCP_IPV6) @@ -657,7 +658,8 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * opts->ahmac = add_addr6_generate_hmac(msk->local_key, msk->remote_key, opts->addr_id, - &opts->addr6); + &opts->addr6, + opts->port); } } #endif @@ -962,12 +964,14 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk, if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) hmac = add_addr_generate_hmac(msk->remote_key, msk->local_key, - mp_opt->addr_id, &mp_opt->addr); + mp_opt->addr_id, &mp_opt->addr, + mp_opt->port); #if IS_ENABLED(CONFIG_MPTCP_IPV6) else hmac = add_addr6_generate_hmac(msk->remote_key, msk->local_key, - mp_opt->addr_id, &mp_opt->addr6); + mp_opt->addr_id, &mp_opt->addr6, + mp_opt->port); #endif pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n", diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 76958570ae7f..4bde960e19dc 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -11,7 +11,6 @@ #include <linux/netdevice.h> #include <linux/sched/signal.h> #include <linux/atomic.h> -#include <linux/igmp.h> #include <net/sock.h> #include <net/inet_common.h> #include <net/inet_hashtables.h> @@ -20,7 +19,6 @@ #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_MPTCP_IPV6) #include <net/transp_v6.h> -#include <net/addrconf.h> #endif #include <net/mptcp.h> #include <net/xfrm.h> @@ -2878,6 +2876,48 @@ static int mptcp_setsockopt_v6(struct mptcp_sock *msk, int optname, return ret; } +static bool mptcp_unsupported(int level, int optname) +{ + if (level == SOL_IP) { + switch (optname) { + case IP_ADD_MEMBERSHIP: + case IP_ADD_SOURCE_MEMBERSHIP: + case IP_DROP_MEMBERSHIP: + case IP_DROP_SOURCE_MEMBERSHIP: + case IP_BLOCK_SOURCE: + case IP_UNBLOCK_SOURCE: + case MCAST_JOIN_GROUP: + case MCAST_LEAVE_GROUP: + case MCAST_JOIN_SOURCE_GROUP: + case MCAST_LEAVE_SOURCE_GROUP: + case MCAST_BLOCK_SOURCE: + case MCAST_UNBLOCK_SOURCE: + case MCAST_MSFILTER: + return true; + } + return false; + } + if (level == SOL_IPV6) { + switch (optname) { + case IPV6_ADDRFORM: + case IPV6_ADD_MEMBERSHIP: + case IPV6_DROP_MEMBERSHIP: + case IPV6_JOIN_ANYCAST: + case IPV6_LEAVE_ANYCAST: + case MCAST_JOIN_GROUP: + case MCAST_LEAVE_GROUP: + case MCAST_JOIN_SOURCE_GROUP: + case MCAST_LEAVE_SOURCE_GROUP: + case MCAST_BLOCK_SOURCE: + case MCAST_UNBLOCK_SOURCE: + case MCAST_MSFILTER: + return true; + } + return false; + } + return false; +} + static int mptcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen) { @@ -2886,6 +2926,9 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname, pr_debug("msk=%p", msk); + if (mptcp_unsupported(level, optname)) + return -ENOPROTOOPT; + if (level == SOL_SOCKET) return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen); @@ -2968,7 +3011,7 @@ static void mptcp_release_cb(struct sock *sk) for (;;) { flags = 0; if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) - flags |= MPTCP_PUSH_PENDING; + flags |= BIT(MPTCP_PUSH_PENDING); if (!flags) break; @@ -2981,7 +3024,7 @@ static void mptcp_release_cb(struct sock *sk) */ spin_unlock_bh(&sk->sk_lock.slock); - if (flags & MPTCP_PUSH_PENDING) + if (flags & BIT(MPTCP_PUSH_PENDING)) __mptcp_push_pending(sk, 0); cond_resched(); @@ -3419,34 +3462,10 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, return mask; } -static int mptcp_release(struct socket *sock) -{ - struct mptcp_subflow_context *subflow; - struct sock *sk = sock->sk; - struct mptcp_sock *msk; - - if (!sk) - return 0; - - lock_sock(sk); - - msk = mptcp_sk(sk); - - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - - ip_mc_drop_socket(ssk); - } - - release_sock(sk); - - return inet_release(sock); -} - static const struct proto_ops mptcp_stream_ops = { .family = PF_INET, .owner = THIS_MODULE, - .release = mptcp_release, + .release = inet_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, @@ -3538,35 +3557,10 @@ void __init mptcp_proto_init(void) } #if IS_ENABLED(CONFIG_MPTCP_IPV6) -static int mptcp6_release(struct socket *sock) -{ - struct mptcp_subflow_context *subflow; - struct mptcp_sock *msk; - struct sock *sk = sock->sk; - - if (!sk) - return 0; - - lock_sock(sk); - - msk = mptcp_sk(sk); - - mptcp_for_each_subflow(msk, subflow) { - struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - - ip_mc_drop_socket(ssk); - ipv6_sock_mc_close(ssk); - ipv6_sock_ac_close(ssk); - } - - release_sock(sk); - return inet6_release(sock); -} - static const struct proto_ops mptcp_v6_stream_ops = { .family = PF_INET6, .owner = THIS_MODULE, - .release = mptcp6_release, + .release = inet6_release, .bind = mptcp_bind, .connect = mptcp_stream_connect, .socketpair = sock_no_socketpair, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3d47d670e665..d17d39ccdf34 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -477,6 +477,11 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; + if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) { + __IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS); + return 0; + } + return tcp_conn_request(&mptcp_subflow_request_sock_ops, &subflow_request_sock_ipv6_ops, sk, skb); diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index a9cb355324d1..ffff8da707b8 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -105,13 +105,20 @@ static void ncsi_channel_monitor(struct timer_list *t) monitor_state = nc->monitor.state; spin_unlock_irqrestore(&nc->lock, flags); - if (!enabled || chained) { - ncsi_stop_channel_monitor(nc); - return; - } + if (!enabled) + return; /* expected race disabling timer */ + if (WARN_ON_ONCE(chained)) + goto bad_state; + if (state != NCSI_CHANNEL_INACTIVE && state != NCSI_CHANNEL_ACTIVE) { - ncsi_stop_channel_monitor(nc); +bad_state: + netdev_warn(ndp->ndev.dev, + "Bad NCSI monitor state channel %d 0x%x %s queue\n", + nc->id, state, chained ? "on" : "off"); + spin_lock_irqsave(&nc->lock, flags); + nc->monitor.enabled = false; + spin_unlock_irqrestore(&nc->lock, flags); return; } @@ -136,10 +143,9 @@ static void ncsi_channel_monitor(struct timer_list *t) ncsi_report_link(ndp, true); ndp->flags |= NCSI_DEV_RESHUFFLE; - ncsi_stop_channel_monitor(nc); - ncm = &nc->modes[NCSI_MODE_LINK]; spin_lock_irqsave(&nc->lock, flags); + nc->monitor.enabled = false; nc->state = NCSI_CHANNEL_INVISIBLE; ncm->data[2] &= ~0x1; spin_unlock_irqrestore(&nc->lock, flags); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1469365bac7e..1d519b0e51a5 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2962,6 +2962,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, memset(&m, 0xFF, sizeof(m)); memcpy(&m.src.u3, &mask->src.u3, sizeof(m.src.u3)); m.src.u.all = mask->src.u.all; + m.src.l3num = tuple->src.l3num; m.dst.protonum = tuple->dst.protonum; nest_parms = nla_nest_start(skb, CTA_EXPECT_MASK); diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 5b05487a60d2..db11e403d818 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -218,9 +218,6 @@ int nf_conntrack_gre_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, const struct nf_hook_state *state) { - if (state->pf != NFPROTO_IPV4) - return -NF_ACCEPT; - if (!nf_ct_is_confirmed(ct)) { unsigned int *timeouts = nf_ct_timeout_lookup(ct); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 0ee702d374b0..c6c0cb465664 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -266,6 +266,7 @@ static const char* l4proto_name(u16 proto) case IPPROTO_GRE: return "gre"; case IPPROTO_SCTP: return "sctp"; case IPPROTO_UDPLITE: return "udplite"; + case IPPROTO_ICMPV6: return "icmpv6"; } return "unknown"; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 5fa657b8e03d..c77ba8690ed8 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -506,7 +506,7 @@ int nf_flow_table_init(struct nf_flowtable *flowtable) { int err; - INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc); + INIT_DELAYED_WORK(&flowtable->gc_work, nf_flow_offload_work_gc); flow_block_init(&flowtable->flow_block); init_rwsem(&flowtable->flow_block_lock); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 2a6993fa40d7..1c5460e7bce8 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -305,12 +305,12 @@ static void flow_offload_ipv6_mangle(struct nf_flow_rule *flow_rule, const __be32 *addr, const __be32 *mask) { struct flow_action_entry *entry; - int i; + int i, j; - for (i = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32)) { + for (i = 0, j = 0; i < sizeof(struct in6_addr) / sizeof(u32); i += sizeof(u32), j++) { entry = flow_action_entry_next(flow_rule); flow_offload_mangle(entry, FLOW_ACT_MANGLE_HDR_TYPE_IP6, - offset + i, &addr[i], mask); + offset + i, &addr[j], mask); } } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 224c8e537cb3..589d2f6978d3 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5295,16 +5295,35 @@ err_expr: return -ENOMEM; } -static void nft_set_elem_expr_setup(const struct nft_set_ext *ext, int i, - struct nft_expr *expr_array[]) +static int nft_set_elem_expr_setup(struct nft_ctx *ctx, + const struct nft_set_ext *ext, + struct nft_expr *expr_array[], + u32 num_exprs) { struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext); - struct nft_expr *expr = nft_setelem_expr_at(elem_expr, elem_expr->size); + struct nft_expr *expr; + int i, err; + + for (i = 0; i < num_exprs; i++) { + expr = nft_setelem_expr_at(elem_expr, elem_expr->size); + err = nft_expr_clone(expr, expr_array[i]); + if (err < 0) + goto err_elem_expr_setup; + + elem_expr->size += expr_array[i]->ops->size; + nft_expr_destroy(ctx, expr_array[i]); + expr_array[i] = NULL; + } + + return 0; - memcpy(expr, expr_array[i], expr_array[i]->ops->size); - elem_expr->size += expr_array[i]->ops->size; - kfree(expr_array[i]); - expr_array[i] = NULL; +err_elem_expr_setup: + for (; i < num_exprs; i++) { + nft_expr_destroy(ctx, expr_array[i]); + expr_array[i] = NULL; + } + + return -ENOMEM; } static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, @@ -5556,12 +5575,15 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, *nft_set_ext_obj(ext) = obj; obj->use++; } - for (i = 0; i < num_exprs; i++) - nft_set_elem_expr_setup(ext, i, expr_array); + err = nft_set_elem_expr_setup(ctx, ext, expr_array, num_exprs); + if (err < 0) + goto err_elem_expr; trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set); - if (trans == NULL) - goto err_trans; + if (trans == NULL) { + err = -ENOMEM; + goto err_elem_expr; + } ext->genmask = nft_genmask_cur(ctx->net) | NFT_SET_ELEM_BUSY_MASK; err = set->ops->insert(ctx->net, set, &elem, &ext2); @@ -5605,7 +5627,7 @@ err_set_full: set->ops->remove(ctx->net, set, &elem); err_element_clash: kfree(trans); -err_trans: +err_elem_expr: if (obj) obj->use--; @@ -6783,6 +6805,9 @@ static int nft_register_flowtable_net_hooks(struct net *net, list_for_each_entry(hook, hook_list, list) { list_for_each_entry(ft, &table->flowtables, list) { + if (!nft_is_active_next(net, ft)) + continue; + list_for_each_entry(hook2, &ft->hook_list, list) { if (hook->ops.dev == hook2->ops.dev && hook->ops.pf == hook2->ops.pf) { @@ -6842,6 +6867,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, struct nft_hook *hook, *next; struct nft_trans *trans; bool unregister = false; + u32 flags; int err; err = nft_flowtable_parse_hook(ctx, nla[NFTA_FLOWTABLE_HOOK], @@ -6856,6 +6882,17 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, } } + if (nla[NFTA_FLOWTABLE_FLAGS]) { + flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); + if (flags & ~NFT_FLOWTABLE_MASK) + return -EOPNOTSUPP; + if ((flowtable->data.flags & NFT_FLOWTABLE_HW_OFFLOAD) ^ + (flags & NFT_FLOWTABLE_HW_OFFLOAD)) + return -EOPNOTSUPP; + } else { + flags = flowtable->data.flags; + } + err = nft_register_flowtable_net_hooks(ctx->net, ctx->table, &flowtable_hook.list, flowtable); if (err < 0) @@ -6869,6 +6906,7 @@ static int nft_flowtable_update(struct nft_ctx *ctx, const struct nlmsghdr *nlh, goto err_flowtable_update_hook; } + nft_trans_flowtable_flags(trans) = flags; nft_trans_flowtable(trans) = flowtable; nft_trans_flowtable_update(trans) = true; INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans)); @@ -6963,8 +7001,10 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, if (nla[NFTA_FLOWTABLE_FLAGS]) { flowtable->data.flags = ntohl(nla_get_be32(nla[NFTA_FLOWTABLE_FLAGS])); - if (flowtable->data.flags & ~NFT_FLOWTABLE_MASK) + if (flowtable->data.flags & ~NFT_FLOWTABLE_MASK) { + err = -EOPNOTSUPP; goto err3; + } } write_pnet(&flowtable->data.net, net); @@ -8176,6 +8216,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) break; case NFT_MSG_NEWFLOWTABLE: if (nft_trans_flowtable_update(trans)) { + nft_trans_flowtable(trans)->data.flags = + nft_trans_flowtable_flags(trans); nf_tables_flowtable_notify(&trans->ctx, nft_trans_flowtable(trans), &nft_trans_flowtable_hooks(trans), diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index 0e2c315c3b5e..82ec27bdf941 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -76,13 +76,13 @@ static int nft_limit_init(struct nft_limit *limit, return -EOVERFLOW; if (pkts) { - tokens = div_u64(limit->nsecs, limit->rate) * limit->burst; + tokens = div64_u64(limit->nsecs, limit->rate) * limit->burst; } else { /* The token bucket size limits the number of tokens can be * accumulated. tokens_max specifies the bucket size. * tokens_max = unit * (rate + burst) / rate. */ - tokens = div_u64(limit->nsecs * (limit->rate + limit->burst), + tokens = div64_u64(limit->nsecs * (limit->rate + limit->burst), limit->rate); } diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index bce6ca203d46..92e9d4ebc5e8 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -733,7 +733,7 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, { const struct xt_match *match = m->u.kernel.match; struct compat_xt_entry_match *cm = (struct compat_xt_entry_match *)m; - int pad, off = xt_compat_match_offset(match); + int off = xt_compat_match_offset(match); u_int16_t msize = cm->u.user.match_size; char name[sizeof(m->u.user.name)]; @@ -743,9 +743,6 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, match->compat_from_user(m->data, cm->data); else memcpy(m->data, cm->data, msize - sizeof(*cm)); - pad = XT_ALIGN(match->matchsize) - match->matchsize; - if (pad > 0) - memset(m->data + match->matchsize, 0, pad); msize += off; m->u.user.match_size = msize; @@ -1116,7 +1113,7 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, { const struct xt_target *target = t->u.kernel.target; struct compat_xt_entry_target *ct = (struct compat_xt_entry_target *)t; - int pad, off = xt_compat_target_offset(target); + int off = xt_compat_target_offset(target); u_int16_t tsize = ct->u.user.target_size; char name[sizeof(t->u.user.name)]; @@ -1126,9 +1123,6 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, target->compat_from_user(t->data, ct->data); else memcpy(t->data, ct->data, tsize - sizeof(*ct)); - pad = XT_ALIGN(target->targetsize) - target->targetsize; - if (pad > 0) - memset(t->data + target->targetsize, 0, pad); tsize += off; t->u.user.target_size = tsize; @@ -1351,14 +1345,6 @@ struct xt_counters *xt_counters_alloc(unsigned int counters) } EXPORT_SYMBOL(xt_counters_alloc); -struct xt_table_info -*xt_table_get_private_protected(const struct xt_table *table) -{ - return rcu_dereference_protected(table->private, - mutex_is_locked(&xt[table->af].mutex)); -} -EXPORT_SYMBOL(xt_table_get_private_protected); - struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, @@ -1366,6 +1352,7 @@ xt_replace_table(struct xt_table *table, int *error) { struct xt_table_info *private; + unsigned int cpu; int ret; ret = xt_jumpstack_alloc(newinfo); @@ -1375,20 +1362,47 @@ xt_replace_table(struct xt_table *table, } /* Do the substitution. */ - private = xt_table_get_private_protected(table); + local_bh_disable(); + private = table->private; /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); + local_bh_enable(); *error = -EAGAIN; return NULL; } newinfo->initial_entries = private->initial_entries; + /* + * Ensure contents of newinfo are visible before assigning to + * private. + */ + smp_wmb(); + table->private = newinfo; - rcu_assign_pointer(table->private, newinfo); - synchronize_rcu(); + /* make sure all cpus see new ->private value */ + smp_mb(); + + /* + * Even though table entries have now been swapped, other CPU's + * may still be using the old entries... + */ + local_bh_enable(); + + /* ... so wait for even xt_recseq on all cpus */ + for_each_possible_cpu(cpu) { + seqcount_t *s = &per_cpu(xt_recseq, cpu); + u32 seq = raw_read_seqcount(s); + + if (seq & 1) { + do { + cond_resched(); + cpu_relax(); + } while (seq == raw_read_seqcount(s)); + } + } audit_log_nfcfg(table->name, table->af, private->number, !private->number ? AUDIT_XT_OP_REGISTER : @@ -1424,12 +1438,12 @@ struct xt_table *xt_register_table(struct net *net, } /* Simplifies replace_table code. */ - rcu_assign_pointer(table->private, bootstrap); + table->private = bootstrap; if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; - private = xt_table_get_private_protected(table); + private = table->private; pr_debug("table->private->number = %u\n", private->number); /* save number of initial entries */ @@ -1452,8 +1466,7 @@ void *xt_unregister_table(struct xt_table *table) struct xt_table_info *private; mutex_lock(&xt[table->af].mutex); - private = xt_table_get_private_protected(table); - RCU_INIT_POINTER(table->private, NULL); + private = table->private; list_del(&table->list); mutex_unlock(&xt[table->af].mutex); audit_log_nfcfg(table->name, table->af, private->number, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index dd488938447f..3a62f97acf39 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1019,7 +1019,6 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return -EINVAL; } - netlink_lock_table(); if (nlk->netlink_bind && groups) { int group; @@ -1031,13 +1030,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (!err) continue; netlink_undo_bind(group, groups, sk); - goto unlock; + return err; } } /* No need for barriers here as we return to user-space without * using any of the bound attributes. */ + netlink_lock_table(); if (!bound) { err = nladdr->nl_pid ? netlink_insert(sk, nladdr->nl_pid) : diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index d257ed3b732a..a3b46f888803 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -108,11 +108,13 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) llcp_sock->service_name_len, GFP_KERNEL); if (!llcp_sock->service_name) { + nfc_llcp_local_put(llcp_sock->local); ret = -ENOMEM; goto put_dev; } llcp_sock->ssap = nfc_llcp_get_sdp_ssap(local, llcp_sock); if (llcp_sock->ssap == LLCP_SAP_MAX) { + nfc_llcp_local_put(llcp_sock->local); kfree(llcp_sock->service_name); llcp_sock->service_name = NULL; ret = -EADDRINUSE; @@ -671,6 +673,10 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, ret = -EISCONN; goto error; } + if (sk->sk_state == LLCP_CONNECTING) { + ret = -EINPROGRESS; + goto error; + } dev = nfc_get_device(addr->dev_idx); if (dev == NULL) { @@ -702,6 +708,7 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, llcp_sock->local = nfc_llcp_local_get(local); llcp_sock->ssap = nfc_llcp_get_local_ssap(local); if (llcp_sock->ssap == LLCP_SAP_MAX) { + nfc_llcp_local_put(llcp_sock->local); ret = -ENOMEM; goto put_dev; } @@ -743,9 +750,12 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, sock_unlink: nfc_llcp_sock_unlink(&local->connecting_sockets, sk); + kfree(llcp_sock->service_name); + llcp_sock->service_name = NULL; sock_llcp_release: nfc_llcp_put_ssap(local, llcp_sock->ssap); + nfc_llcp_local_put(llcp_sock->local); put_dev: nfc_put_device(dev); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 5eddfe7bd391..d217bd91176b 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -271,9 +271,11 @@ static void ovs_ct_update_key(const struct sk_buff *skb, /* This is called to initialize CT key fields possibly coming in from the local * stack. */ -void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) +void ovs_ct_fill_key(const struct sk_buff *skb, + struct sw_flow_key *key, + bool post_ct) { - ovs_ct_update_key(skb, NULL, key, false, false); + ovs_ct_update_key(skb, NULL, key, post_ct, false); } int ovs_ct_put_key(const struct sw_flow_key *swkey, @@ -1332,7 +1334,7 @@ int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key) if (skb_nfct(skb)) { nf_conntrack_put(skb_nfct(skb)); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); - ovs_ct_fill_key(skb, key); + ovs_ct_fill_key(skb, key, false); } return 0; @@ -2032,10 +2034,10 @@ static int ovs_ct_limit_del_zone_limit(struct nlattr *nla_zone_limit, static int ovs_ct_limit_get_default_limit(struct ovs_ct_limit_info *info, struct sk_buff *reply) { - struct ovs_zone_limit zone_limit; - - zone_limit.zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE; - zone_limit.limit = info->default_limit; + struct ovs_zone_limit zone_limit = { + .zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE, + .limit = info->default_limit, + }; return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit); } diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 59dc32761b91..317e525c8a11 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -25,7 +25,8 @@ int ovs_ct_execute(struct net *, struct sk_buff *, struct sw_flow_key *, const struct ovs_conntrack_info *); int ovs_ct_clear(struct sk_buff *skb, struct sw_flow_key *key); -void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); +void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key, + bool post_ct); int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb); void ovs_ct_free_action(const struct nlattr *a); @@ -74,7 +75,8 @@ static inline int ovs_ct_clear(struct sk_buff *skb, } static inline void ovs_ct_fill_key(const struct sk_buff *skb, - struct sw_flow_key *key) + struct sw_flow_key *key, + bool post_ct) { key->ct_state = 0; key->ct_zone = 0; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index c7f34d6a9934..e586424d8b04 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -857,6 +857,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) struct tc_skb_ext *tc_ext; #endif + bool post_ct = false; int res, err; /* Extract metadata from packet. */ @@ -895,6 +896,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, tc_ext = skb_ext_find(skb, TC_SKB_EXT); key->recirc_id = tc_ext ? tc_ext->chain : 0; OVS_CB(skb)->mru = tc_ext ? tc_ext->mru : 0; + post_ct = tc_ext ? tc_ext->post_ct : false; } else { key->recirc_id = 0; } @@ -904,7 +906,7 @@ int ovs_flow_key_extract(const struct ip_tunnel_info *tun_info, err = key_extract(skb, key); if (!err) - ovs_ct_fill_key(skb, key); /* Must be after key_extract(). */ + ovs_ct_fill_key(skb, key, post_ct); /* Must be after key_extract(). */ return err; } diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index edb6ac17ceca..1e4fb568fa84 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -271,7 +271,10 @@ static int qrtr_tx_wait(struct qrtr_node *node, int dest_node, int dest_port, flow = kzalloc(sizeof(*flow), GFP_KERNEL); if (flow) { init_waitqueue_head(&flow->resume_tx); - radix_tree_insert(&node->qrtr_tx_flow, key, flow); + if (radix_tree_insert(&node->qrtr_tx_flow, key, flow)) { + kfree(flow); + flow = NULL; + } } } mutex_unlock(&node->qrtr_tx_lock); @@ -1058,6 +1061,11 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, rc = copied; if (addr) { + /* There is an anonymous 2-byte hole after sq_family, + * make sure to clear it. + */ + memset(addr, 0, sizeof(*addr)); + addr->sq_family = AF_QIPCRTR; addr->sq_node = cb->src_node; addr->sq_port = cb->src_port; diff --git a/net/rds/message.c b/net/rds/message.c index 071a261fdaab..799034e0f513 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -347,8 +347,9 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE); rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); if (IS_ERR(rm->data.op_sg)) { + void *err = ERR_CAST(rm->data.op_sg); rds_message_put(rm); - return ERR_CAST(rm->data.op_sg); + return err; } for (i = 0; i < rm->data.op_nents; ++i) { diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 68d6ef9e59fc..ac15a944573f 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -69,7 +69,7 @@ struct rfkill { struct rfkill_int_event { struct list_head list; - struct rfkill_event ev; + struct rfkill_event_ext ev; }; struct rfkill_data { @@ -253,7 +253,8 @@ static void rfkill_global_led_trigger_unregister(void) } #endif /* CONFIG_RFKILL_LEDS */ -static void rfkill_fill_event(struct rfkill_event *ev, struct rfkill *rfkill, +static void rfkill_fill_event(struct rfkill_event_ext *ev, + struct rfkill *rfkill, enum rfkill_operation op) { unsigned long flags; @@ -1237,7 +1238,7 @@ static ssize_t rfkill_fop_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { struct rfkill *rfkill; - struct rfkill_event ev; + struct rfkill_event_ext ev; int ret; /* we don't need the 'hard' variable but accept it */ diff --git a/net/sched/act_api.c b/net/sched/act_api.c index b919826939e0..f6d5755d669e 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -158,7 +158,7 @@ static int __tcf_action_put(struct tc_action *p, bool bind) return 0; } -int __tcf_idr_release(struct tc_action *p, bool bind, bool strict) +static int __tcf_idr_release(struct tc_action *p, bool bind, bool strict) { int ret = 0; @@ -184,7 +184,18 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict) return ret; } -EXPORT_SYMBOL(__tcf_idr_release); + +int tcf_idr_release(struct tc_action *a, bool bind) +{ + const struct tc_action_ops *ops = a->ops; + int ret; + + ret = __tcf_idr_release(a, bind, false); + if (ret == ACT_P_DELETED) + module_put(ops->owner); + return ret; +} +EXPORT_SYMBOL(tcf_idr_release); static size_t tcf_action_shared_attrs_size(const struct tc_action *act) { @@ -493,6 +504,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, } p->idrinfo = idrinfo; + __module_get(ops->owner); p->ops = ops; *a = p; return 0; @@ -992,7 +1004,8 @@ struct tc_action_ops *tc_action_load_ops(char *name, struct nlattr *nla, 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, - struct tc_action_ops *a_o, bool rtnl_held, + struct tc_action_ops *a_o, int *init_res, + bool rtnl_held, struct netlink_ext_ack *extack) { struct nla_bitfield32 flags = { 0, 0 }; @@ -1028,6 +1041,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, } if (err < 0) goto err_out; + *init_res = err; if (!name && tb[TCA_ACT_COOKIE]) tcf_set_action_cookie(&a->act_cookie, cookie); @@ -1035,13 +1049,6 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (!name) a->hw_stats = hw_stats; - /* module count goes up only when brand new policy is created - * if it exists and is only bound to in a_o->init() then - * ACT_P_CREATED is not returned (a zero is). - */ - if (err != ACT_P_CREATED) - module_put(a_o->owner); - return a; err_out: @@ -1056,7 +1063,7 @@ err_out: int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind, - struct tc_action *actions[], size_t *attr_size, + struct tc_action *actions[], int init_res[], size_t *attr_size, bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_action_ops *ops[TCA_ACT_MAX_PRIO] = {}; @@ -1084,7 +1091,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind, - ops[i - 1], rtnl_held, extack); + ops[i - 1], &init_res[i - 1], rtnl_held, + extack); if (IS_ERR(act)) { err = PTR_ERR(act); goto err; @@ -1100,7 +1108,8 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, tcf_idr_insert_many(actions); *attr_size = tcf_action_full_attrs_size(sz); - return i - 1; + err = i - 1; + goto err_mod; err: tcf_action_destroy(actions, bind); @@ -1497,12 +1506,13 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { size_t attr_size = 0; - int loop, ret; + int loop, ret, i; struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; + int init_res[TCA_ACT_MAX_PRIO] = {}; for (loop = 0; loop < 10; loop++) { ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, - actions, &attr_size, true, extack); + actions, init_res, &attr_size, true, extack); if (ret != -EAGAIN) break; } @@ -1510,8 +1520,12 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, if (ret < 0) return ret; ret = tcf_add_notify(net, n, actions, portid, attr_size, extack); - if (ovr) - tcf_action_put_many(actions); + + /* only put existing actions */ + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) + if (init_res[i] == ACT_P_CREATED) + actions[i] = NULL; + tcf_action_put_many(actions); return ret; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index f0a0aa125b00..16e888a9601d 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -945,13 +945,14 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&c->tcf_tm); if (clear) { + qdisc_skb_cb(skb)->post_ct = false; ct = nf_ct_get(skb, &ctinfo); if (ct) { nf_conntrack_put(&ct->ct_general); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); } - goto out; + goto out_clear; } family = tcf_ct_skb_nf_family(skb); @@ -1030,8 +1031,9 @@ out_push: skb_push_rcsum(skb, nh_ofs); out: - tcf_action_update_bstats(&c->common, skb); qdisc_skb_cb(skb)->post_ct = true; +out_clear: + tcf_action_update_bstats(&c->common, skb); if (defrag) qdisc_skb_cb(skb)->pkt_len = skb->len; return retval; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e37556cc37ab..340d5af86e87 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -646,7 +646,7 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb) struct net_device *dev = block_cb->indr.dev; struct Qdisc *sch = block_cb->indr.sch; struct netlink_ext_ack extack = {}; - struct flow_block_offload bo; + struct flow_block_offload bo = {}; tcf_block_offload_init(&bo, dev, sch, FLOW_BLOCK_UNBIND, block_cb->indr.binder_type, @@ -1629,6 +1629,7 @@ int tcf_classify_ingress(struct sk_buff *skb, return TC_ACT_SHOT; ext->chain = last_executed_chain; ext->mru = qdisc_skb_cb(skb)->mru; + ext->post_ct = qdisc_skb_cb(skb)->post_ct; } return ret; @@ -3039,6 +3040,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, { #ifdef CONFIG_NET_CLS_ACT { + int init_res[TCA_ACT_MAX_PRIO] = {}; struct tc_action *act; size_t attr_size = 0; @@ -3050,12 +3052,11 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, return PTR_ERR(a_o); act = tcf_action_init_1(net, tp, tb[exts->police], rate_tlv, "police", ovr, - TCA_ACT_BIND, a_o, rtnl_held, - extack); - if (IS_ERR(act)) { - module_put(a_o->owner); + TCA_ACT_BIND, a_o, init_res, + rtnl_held, extack); + module_put(a_o->owner); + if (IS_ERR(act)) return PTR_ERR(act); - } act->type = exts->type = TCA_OLD_COMPAT; exts->actions[0] = act; @@ -3066,8 +3067,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, err = tcf_action_init(net, tp, tb[exts->action], rate_tlv, NULL, ovr, TCA_ACT_BIND, - exts->actions, &attr_size, - rtnl_held, extack); + exts->actions, init_res, + &attr_size, rtnl_held, extack); if (err < 0) return err; exts->nr_actions = err; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d097b5c15faa..c69a4ba9c33f 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -1451,7 +1451,7 @@ static int fl_set_key_ct(struct nlattr **tb, &mask->ct_state, TCA_FLOWER_KEY_CT_STATE_MASK, sizeof(key->ct_state)); - err = fl_validate_ct_state(mask->ct_state, + err = fl_validate_ct_state(key->ct_state & mask->ct_state, tb[TCA_FLOWER_KEY_CT_STATE_MASK], extack); if (err) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 50f680f03a54..2adbd945bf15 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -345,6 +345,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, struct sk_buff **old = NULL; unsigned int mask; u32 max_P; + u8 *stab; if (opt == NULL) return -EINVAL; @@ -361,8 +362,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0; ctl = nla_data(tb[TCA_CHOKE_PARMS]); - - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) + stab = nla_data(tb[TCA_CHOKE_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) return -EINVAL; if (ctl->limit > CHOKE_MAX_QUEUE) @@ -412,7 +413,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt, red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_CHOKE_STAB]), + stab, max_P); red_set_vars(&q->vars); diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index e0bc77533acc..f4132dc25ac0 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -480,7 +480,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp, struct gred_sched *table = qdisc_priv(sch); struct gred_sched_data *q = table->tab[dp]; - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) { + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log, stab)) { NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters"); return -EINVAL; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index dff3adf5a915..081c11d5717c 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -1020,6 +1020,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_glob *gopt; unsigned int ntx; + bool offload; int err; qdisc_watchdog_init(&q->watchdog, sch); @@ -1044,9 +1045,9 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, if (gopt->version != HTB_VER >> 16) return -EINVAL; - q->offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]); + offload = nla_get_flag(tb[TCA_HTB_OFFLOAD]); - if (q->offload) { + if (offload) { if (sch->parent != TC_H_ROOT) return -EOPNOTSUPP; @@ -1076,7 +1077,7 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, q->rate2quantum = 1; q->defcls = gopt->defcls; - if (!q->offload) + if (!offload) return 0; for (ntx = 0; ntx < q->num_direct_qdiscs; ntx++) { @@ -1107,12 +1108,14 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt, if (err) goto err_free_qdiscs; + /* Defer this assignment, so that htb_destroy skips offload-related + * parts (especially calling ndo_setup_tc) on errors. + */ + q->offload = true; + return 0; err_free_qdiscs: - /* TC_HTB_CREATE call failed, avoid any further calls to the driver. */ - q->offload = false; - for (ntx = 0; ntx < q->num_direct_qdiscs && q->direct_qdiscs[ntx]; ntx++) qdisc_put(q->direct_qdiscs[ntx]); @@ -1340,8 +1343,12 @@ htb_select_queue(struct Qdisc *sch, struct tcmsg *tcm) { struct net_device *dev = qdisc_dev(sch); struct tc_htb_qopt_offload offload_opt; + struct htb_sched *q = qdisc_priv(sch); int err; + if (!q->offload) + return sch->dev_queue; + offload_opt = (struct tc_htb_qopt_offload) { .command = TC_HTB_LEAF_QUERY_QUEUE, .classid = TC_H_MIN(tcm->tcm_parent), @@ -1668,9 +1675,10 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg, cl->parent->common.classid, NULL); if (q->offload) { - if (new_q) + if (new_q) { htb_set_lockdep_class_child(new_q); - htb_parent_to_leaf_offload(sch, dev_queue, new_q); + htb_parent_to_leaf_offload(sch, dev_queue, new_q); + } } } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index b4ae34d7aa96..40adf1f07a82 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -242,6 +242,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, unsigned char flags; int err; u32 max_P; + u8 *stab; if (tb[TCA_RED_PARMS] == NULL || tb[TCA_RED_STAB] == NULL) @@ -250,7 +251,9 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0; ctl = nla_data(tb[TCA_RED_PARMS]); - if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) + stab = nla_data(tb[TCA_RED_STAB]); + if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, + ctl->Scell_log, stab)) return -EINVAL; err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS, @@ -288,7 +291,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb, red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog, ctl->Scell_log, - nla_data(tb[TCA_RED_STAB]), + stab, max_P); red_set_vars(&q->vars); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index b25e51440623..066754a18569 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -647,7 +647,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) } if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, - ctl_v1->Wlog, ctl_v1->Scell_log)) + ctl_v1->Wlog, ctl_v1->Scell_log, NULL)) return -EINVAL; if (ctl_v1 && ctl_v1->qth_min) { p = kmalloc(sizeof(*p), GFP_KERNEL); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 2f1f0a378408..6af6b95bdb67 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -134,6 +134,9 @@ teql_destroy(struct Qdisc *sch) struct teql_sched_data *dat = qdisc_priv(sch); struct teql_master *master = dat->m; + if (!master) + return; + prev = master->slaves; if (prev) { do { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index c3e89c776e66..bd08807c9e44 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -664,8 +664,8 @@ static int sctp_v6_available(union sctp_addr *addr, struct sctp_sock *sp) if (!(type & IPV6_ADDR_UNICAST)) return 0; - return sp->inet.freebind || net->ipv6.sysctl.ip_nonlocal_bind || - ipv6_chk_addr(net, in6, NULL, 0); + return ipv6_can_nonlocal_bind(net, &sp->inet) || + ipv6_chk_addr(net, in6, NULL, 0); } /* This function checks if the address is a valid address to be used for @@ -954,8 +954,7 @@ static int sctp_inet6_bind_verify(struct sctp_sock *opt, union sctp_addr *addr) net = sock_net(&opt->inet.sk); rcu_read_lock(); dev = dev_get_by_index_rcu(net, addr->v6.sin6_scope_id); - if (!dev || !(opt->inet.freebind || - net->ipv6.sysctl.ip_nonlocal_bind || + if (!dev || !(ipv6_can_nonlocal_bind(net, &opt->inet) || ipv6_chk_addr(net, &addr->v6.sin6_addr, dev, 0))) { rcu_read_unlock(); diff --git a/net/sctp/output.c b/net/sctp/output.c index 6614c9fdc51e..a6aa17df09ef 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -584,13 +584,6 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) goto out; } - rcu_read_lock(); - if (__sk_dst_get(sk) != tp->dst) { - dst_hold(tp->dst); - sk_setup_caps(sk, tp->dst); - } - rcu_read_unlock(); - /* pack up chunks */ pkt_count = sctp_packet_pack(packet, head, gso, gfp); if (!pkt_count) { diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 3fd06a27105d..5cb1aa5f067b 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1135,6 +1135,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx, static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx) { + struct sock *sk = ctx->asoc->base.sk; struct list_head *ltransport; struct sctp_packet *packet; struct sctp_transport *t; @@ -1144,6 +1145,12 @@ static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx) t = list_entry(ltransport, struct sctp_transport, send_ready); packet = &t->packet; if (!sctp_packet_empty(packet)) { + rcu_read_lock(); + if (t->dst && __sk_dst_get(sk) != t->dst) { + dst_hold(t->dst); + sk_setup_caps(sk, t->dst); + } + rcu_read_unlock(); error = sctp_packet_transmit(packet, ctx->gfp); if (error < 0) ctx->q->asoc->base.sk->sk_err = -error; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a710917c5ac7..b9b3d899a611 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1520,11 +1520,9 @@ static void sctp_close(struct sock *sk, long timeout) /* Supposedly, no process has access to the socket, but * the net layers still may. - * Also, sctp_destroy_sock() needs to be called with addr_wq_lock - * held and that should be grabbed before socket lock. */ - spin_lock_bh(&net->sctp.addr_wq_lock); - bh_lock_sock_nested(sk); + local_bh_disable(); + bh_lock_sock(sk); /* Hold the sock, since sk_common_release() will put sock_put() * and we have just a little more cleanup. @@ -1533,7 +1531,7 @@ static void sctp_close(struct sock *sk, long timeout) sk_common_release(sk); bh_unlock_sock(sk); - spin_unlock_bh(&net->sctp.addr_wq_lock); + local_bh_enable(); sock_put(sk); @@ -4993,9 +4991,6 @@ static int sctp_init_sock(struct sock *sk) sk_sockets_allocated_inc(sk); sock_prot_inuse_add(net, sk->sk_prot, 1); - /* Nothing can fail after this block, otherwise - * sctp_destroy_sock() will be called without addr_wq_lock held - */ if (net->sctp.default_auto_asconf) { spin_lock(&sock_net(sk)->sctp.addr_wq_lock); list_add_tail(&sp->auto_asconf_list, @@ -5030,7 +5025,9 @@ static void sctp_destroy_sock(struct sock *sk) if (sp->do_auto_asconf) { sp->do_auto_asconf = 0; + spin_lock_bh(&sock_net(sk)->sctp.addr_wq_lock); list_del(&sp->auto_asconf_list); + spin_unlock_bh(&sock_net(sk)->sctp.addr_wq_lock); } sctp_endpoint_free(sp->ep); local_bh_disable(); diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 6bf4550aa1ac..57c6a1a719e2 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -154,9 +154,9 @@ struct tipc_media { * care of initializing all other fields. */ struct tipc_bearer { - void __rcu *media_ptr; /* initalized by media */ - u32 mtu; /* initalized by media */ - struct tipc_media_addr addr; /* initalized by media */ + void __rcu *media_ptr; /* initialized by media */ + u32 mtu; /* initialized by media */ + struct tipc_media_addr addr; /* initialized by media */ char name[TIPC_MAX_BEARER_NAME]; struct tipc_media *media; struct tipc_media_addr bcast_addr; diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c index f4fca8f7f63f..97710ce36047 100644 --- a/net/tipc/crypto.c +++ b/net/tipc/crypto.c @@ -1941,12 +1941,13 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead, goto rcv; if (tipc_aead_clone(&tmp, aead) < 0) goto rcv; + WARN_ON(!refcount_inc_not_zero(&tmp->refcnt)); if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key, false) < 0) { tipc_aead_free(&tmp->rcu); goto rcv; } tipc_aead_put(aead); - aead = tipc_aead_get(tmp); + aead = tmp; } if (unlikely(err)) { diff --git a/net/tipc/net.c b/net/tipc/net.c index a129f661bee3..faf6bf554514 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -89,7 +89,7 @@ * - A spin lock to protect the registry of kernel/driver users (reg.c) * - A global spin_lock (tipc_port_lock), which only task is to ensure * consistency where more than one port is involved in an operation, - * i.e., whe a port is part of a linked list of ports. + * i.e., when a port is part of a linked list of ports. * There are two such lists; 'port_list', which is used for management, * and 'wait_list', which is used to queue ports during congestion. * diff --git a/net/tipc/node.c b/net/tipc/node.c index 008670d1f43e..e0ee83263a39 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1734,7 +1734,7 @@ int tipc_node_xmit(struct net *net, struct sk_buff_head *list, } /* tipc_node_xmit_skb(): send single buffer to destination - * Buffers sent via this functon are generally TIPC_SYSTEM_IMPORTANCE + * Buffers sent via this function are generally TIPC_SYSTEM_IMPORTANCE * messages, which will not be rejected * The only exception is datagram messages rerouted after secondary * lookup, which are rare and safe to dispose of anyway. @@ -2895,17 +2895,22 @@ int tipc_nl_node_dump_monitor_peer(struct sk_buff *skb, #ifdef CONFIG_TIPC_CRYPTO static int tipc_nl_retrieve_key(struct nlattr **attrs, - struct tipc_aead_key **key) + struct tipc_aead_key **pkey) { struct nlattr *attr = attrs[TIPC_NLA_NODE_KEY]; + struct tipc_aead_key *key; if (!attr) return -ENODATA; - *key = (struct tipc_aead_key *)nla_data(attr); - if (nla_len(attr) < tipc_aead_key_size(*key)) + if (nla_len(attr) < sizeof(*key)) + return -EINVAL; + key = (struct tipc_aead_key *)nla_data(attr); + if (key->keylen > TIPC_AEAD_KEYLEN_MAX || + nla_len(attr) < tipc_aead_key_size(key)) return -EINVAL; + *pkey = key; return 0; } diff --git a/net/tipc/socket.c b/net/tipc/socket.c index cebcc104dc70..022999e0202d 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1265,7 +1265,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq, spin_lock_bh(&inputq->lock); if (skb_peek(arrvq) == skb) { skb_queue_splice_tail_init(&tmpq, inputq); - kfree_skb(__skb_dequeue(arrvq)); + __skb_dequeue(arrvq); } spin_unlock_bh(&inputq->lock); __skb_queue_purge(&tmpq); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 5546710d8ac1..bc7fb9bf3351 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -755,6 +755,7 @@ static struct sock *__vsock_create(struct net *net, vsk->buffer_size = psk->buffer_size; vsk->buffer_min_size = psk->buffer_min_size; vsk->buffer_max_size = psk->buffer_max_size; + security_sk_clone(parent, sk); } else { vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN); vsk->owner = get_current_cred(); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 521d36bb0803..b1df42e4f1eb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -5,7 +5,7 @@ * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2020 Intel Corporation + * Copyright (C) 2018-2021 Intel Corporation */ #include <linux/if.h> @@ -70,7 +70,7 @@ __cfg80211_wdev_from_attrs(struct cfg80211_registered_device *rdev, struct wireless_dev *result = NULL; bool have_ifidx = attrs[NL80211_ATTR_IFINDEX]; bool have_wdev_id = attrs[NL80211_ATTR_WDEV]; - u64 wdev_id; + u64 wdev_id = 0; int wiphy_idx = -1; int ifidx = -1; @@ -229,9 +229,13 @@ static int validate_beacon_head(const struct nlattr *attr, unsigned int len = nla_len(attr); const struct element *elem; const struct ieee80211_mgmt *mgmt = (void *)data; - bool s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control); unsigned int fixedlen, hdrlen; + bool s1g_bcn; + if (len < offsetofend(typeof(*mgmt), frame_control)) + goto err; + + s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control); if (s1g_bcn) { fixedlen = offsetof(struct ieee80211_ext, u.s1g_beacon.variable); @@ -5485,7 +5489,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) rdev, info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP], ¶ms); if (err) - return err; + goto out; } nl80211_calculate_ap_params(¶ms); @@ -14789,6 +14793,7 @@ bad_tid_conf: #define NL80211_FLAG_NEED_WDEV_UP (NL80211_FLAG_NEED_WDEV |\ NL80211_FLAG_CHECK_NETDEV_UP) #define NL80211_FLAG_CLEAR_SKB 0x20 +#define NL80211_FLAG_NO_WIPHY_MTX 0x40 static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, struct genl_info *info) @@ -14840,7 +14845,7 @@ static int nl80211_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, info->user_ptr[0] = rdev; } - if (rdev) { + if (rdev && !(ops->internal_flags & NL80211_FLAG_NO_WIPHY_MTX)) { wiphy_lock(&rdev->wiphy); /* we keep the mutex locked until post_doit */ __release(&rdev->wiphy.mtx); @@ -14865,7 +14870,8 @@ static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb, } } - if (info->user_ptr[0]) { + if (info->user_ptr[0] && + !(ops->internal_flags & NL80211_FLAG_NO_WIPHY_MTX)) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; /* we kept the mutex locked since pre_doit */ @@ -15329,7 +15335,9 @@ static const struct genl_small_ops nl80211_small_ops[] = { .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = nl80211_wiphy_netns, .flags = GENL_UNS_ADMIN_PERM, - .internal_flags = NL80211_FLAG_NEED_WIPHY, + .internal_flags = NL80211_FLAG_NEED_WIPHY | + NL80211_FLAG_NEED_RTNL | + NL80211_FLAG_NO_WIPHY_MTX, }, { .cmd = NL80211_CMD_GET_SURVEY, diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 019952d4fc7d..758eb7d2a706 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2352,14 +2352,16 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy, return NULL; if (ext) { - struct ieee80211_s1g_bcn_compat_ie *compat; - u8 *ie; + const struct ieee80211_s1g_bcn_compat_ie *compat; + const struct element *elem; - ie = (void *)cfg80211_find_ie(WLAN_EID_S1G_BCN_COMPAT, - variable, ielen); - if (!ie) + elem = cfg80211_find_elem(WLAN_EID_S1G_BCN_COMPAT, + variable, ielen); + if (!elem) + return NULL; + if (elem->datalen < sizeof(*compat)) return NULL; - compat = (void *)(ie + 2); + compat = (void *)elem->data; bssid = ext->u.s1g_beacon.sa; capability = le16_to_cpu(compat->compat_info); beacon_int = le16_to_cpu(compat->beacon_int); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 07756ca5e3b5..08a70b4f090c 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -529,7 +529,7 @@ static int cfg80211_sme_connect(struct wireless_dev *wdev, cfg80211_sme_free(wdev); } - if (WARN_ON(wdev->conn)) + if (wdev->conn) return -EINPROGRESS; wdev->conn = kzalloc(sizeof(*wdev->conn), GFP_KERNEL); diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index d8e8a11ca845..a20aec9d7393 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -216,7 +216,7 @@ static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb, case XFRM_MSG_GETSADINFO: case XFRM_MSG_GETSPDINFO: default: - WARN_ONCE(1, "unsupported nlmsg_type %d", nlh_src->nlmsg_type); + pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return ERR_PTR(-EOPNOTSUPP); } @@ -277,7 +277,7 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) return xfrm_nla_cpy(dst, src, nla_len(src)); default: BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID); - WARN_ONCE(1, "unsupported nla_type %d", src->nla_type); + pr_warn_once("unsupported nla_type %d\n", src->nla_type); return -EOPNOTSUPP; } } @@ -315,8 +315,10 @@ static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src struct sk_buff *new = NULL; int err; - if (WARN_ON_ONCE(type >= ARRAY_SIZE(xfrm_msg_min))) + if (type >= ARRAY_SIZE(xfrm_msg_min)) { + pr_warn_once("unsupported nlmsg_type %d\n", nlh_src->nlmsg_type); return -EOPNOTSUPP; + } if (skb_shinfo(skb)->frag_list == NULL) { new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC); @@ -378,6 +380,10 @@ static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src, struct nlmsghdr *nlmsg = dst; struct nlattr *nla; + /* xfrm_user_rcv_msg_compat() relies on fact that 32-bit messages + * have the same len or shorted than 64-bit ones. + * 32-bit translation that is bigger than 64-bit original is unexpected. + */ if (WARN_ON_ONCE(copy_len > payload)) copy_len = payload; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index edf11893dbe8..6d6917b68856 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -134,8 +134,6 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - xo->flags |= XFRM_XMIT; - if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) { struct sk_buff *segs; diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 495b1f5c979b..8831f5a9e992 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -306,6 +306,8 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { + if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) + goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } @@ -314,6 +316,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) return -EMSGSIZE; } +xmit: xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = tdev; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index a7ab19353313..e4cb0ff4dcf4 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -503,22 +503,22 @@ out: return err; } -int xfrm_output_resume(struct sk_buff *skb, int err) +int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err) { struct net *net = xs_net(skb_dst(skb)->xfrm); while (likely((err = xfrm_output_one(skb, err)) == 0)) { nf_reset_ct(skb); - err = skb_dst(skb)->ops->local_out(net, skb->sk, skb); + err = skb_dst(skb)->ops->local_out(net, sk, skb); if (unlikely(err != 1)) goto out; if (!skb_dst(skb)->xfrm) - return dst_output(net, skb->sk, skb); + return dst_output(net, sk, skb); err = nf_hook(skb_dst(skb)->ops->family, - NF_INET_POST_ROUTING, net, skb->sk, skb, + NF_INET_POST_ROUTING, net, sk, skb, NULL, skb_dst(skb)->dev, xfrm_output2); if (unlikely(err != 1)) goto out; @@ -534,7 +534,7 @@ EXPORT_SYMBOL_GPL(xfrm_output_resume); static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { - return xfrm_output_resume(skb, 1); + return xfrm_output_resume(sk, skb, 1); } static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -660,6 +660,12 @@ static int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + if (x->outer_mode.encap == XFRM_MODE_BEET && + ip_is_fragment(ip_hdr(skb))) { + net_warn_ratelimited("BEET mode doesn't support inner IPv4 fragments\n"); + return -EAFNOSUPPORT; + } + err = xfrm4_tunnel_check_size(skb); if (err) return err; @@ -705,8 +711,15 @@ out: static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb) { #if IS_ENABLED(CONFIG_IPV6) + unsigned int ptr = 0; int err; + if (x->outer_mode.encap == XFRM_MODE_BEET && + ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL) >= 0) { + net_warn_ratelimited("BEET mode doesn't support inner IPv6 fragments\n"); + return -EAFNOSUPPORT; + } + err = xfrm6_tunnel_check_size(skb); if (err) return err; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d01ca1a18418..4496f7efa220 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -44,7 +44,6 @@ static void xfrm_state_gc_task(struct work_struct *work); */ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; -static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation); static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); @@ -140,7 +139,7 @@ static void xfrm_hash_resize(struct work_struct *work) } spin_lock_bh(&net->xfrm.xfrm_state_lock); - write_seqcount_begin(&xfrm_state_hash_generation); + write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); @@ -156,7 +155,7 @@ static void xfrm_hash_resize(struct work_struct *work) rcu_assign_pointer(net->xfrm.state_byspi, nspi); net->xfrm.state_hmask = nhashmask; - write_seqcount_end(&xfrm_state_hash_generation); + write_seqcount_end(&net->xfrm.xfrm_state_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); @@ -1063,7 +1062,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, to_put = NULL; - sequence = read_seqcount_begin(&xfrm_state_hash_generation); + sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); rcu_read_lock(); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); @@ -1176,7 +1175,7 @@ out: if (to_put) xfrm_state_put(to_put); - if (read_seqcount_retry(&xfrm_state_hash_generation, sequence)) { + if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) { *err = -EAGAIN; if (x) { xfrm_state_put(x); @@ -2666,6 +2665,8 @@ int __net_init xfrm_state_init(struct net *net) net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); spin_lock_init(&net->xfrm.xfrm_state_lock); + seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation, + &net->xfrm.xfrm_state_lock); return 0; out_byspi: diff --git a/scripts/Makefile b/scripts/Makefile index c36106bce80e..9adb6d247818 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -14,6 +14,7 @@ hostprogs-always-$(CONFIG_ASN1) += asn1_compiler hostprogs-always-$(CONFIG_MODULE_SIG_FORMAT) += sign-file hostprogs-always-$(CONFIG_SYSTEM_TRUSTED_KEYRING) += extract-cert hostprogs-always-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert +hostprogs-always-$(CONFIG_SYSTEM_REVOCATION_LIST) += extract-cert HOSTCFLAGS_sorttable.o = -I$(srctree)/tools/include HOSTCFLAGS_asn1_compiler.o = -I$(srctree)/include diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index 1e000cc2e7b4..3d791908ed36 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -2,6 +2,14 @@ CFLAGS_KASAN_NOSANITIZE := -fno-builtin KASAN_SHADOW_OFFSET ?= $(CONFIG_KASAN_SHADOW_OFFSET) +cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1))) + +ifdef CONFIG_KASAN_STACK + stack_enable := 1 +else + stack_enable := 0 +endif + ifdef CONFIG_KASAN_GENERIC ifdef CONFIG_KASAN_INLINE @@ -12,8 +20,6 @@ endif CFLAGS_KASAN_MINIMAL := -fsanitize=kernel-address -cc-param = $(call cc-option, -mllvm -$(1), $(call cc-option, --param $(1))) - # -fasan-shadow-offset fails without -fsanitize CFLAGS_KASAN_SHADOW := $(call cc-option, -fsanitize=kernel-address \ -fasan-shadow-offset=$(KASAN_SHADOW_OFFSET), \ @@ -27,7 +33,7 @@ else CFLAGS_KASAN := $(CFLAGS_KASAN_SHADOW) \ $(call cc-param,asan-globals=1) \ $(call cc-param,asan-instrumentation-with-call-threshold=$(call_threshold)) \ - $(call cc-param,asan-stack=$(CONFIG_KASAN_STACK)) \ + $(call cc-param,asan-stack=$(stack_enable)) \ $(call cc-param,asan-instrument-allocas=1) endif @@ -36,14 +42,14 @@ endif # CONFIG_KASAN_GENERIC ifdef CONFIG_KASAN_SW_TAGS ifdef CONFIG_KASAN_INLINE - instrumentation_flags := -mllvm -hwasan-mapping-offset=$(KASAN_SHADOW_OFFSET) + instrumentation_flags := $(call cc-param,hwasan-mapping-offset=$(KASAN_SHADOW_OFFSET)) else - instrumentation_flags := -mllvm -hwasan-instrument-with-calls=1 + instrumentation_flags := $(call cc-param,hwasan-instrument-with-calls=1) endif CFLAGS_KASAN := -fsanitize=kernel-hwaddress \ - -mllvm -hwasan-instrument-stack=$(CONFIG_KASAN_STACK) \ - -mllvm -hwasan-use-short-granules=0 \ + $(call cc-param,hwasan-instrument-stack=$(stack_enable)) \ + $(call cc-param,hwasan-use-short-granules=0) \ $(instrumentation_flags) endif # CONFIG_KASAN_SW_TAGS diff --git a/scripts/module.lds.S b/scripts/module.lds.S index 168cd27e6122..2c52535f9b56 100644 --- a/scripts/module.lds.S +++ b/scripts/module.lds.S @@ -20,6 +20,7 @@ SECTIONS { __patchable_function_entries : { *(__patchable_function_entries) } +#ifdef CONFIG_LTO_CLANG /* * With CONFIG_LTO_CLANG, LLD always enables -fdata-sections and * -ffunction-sections, which increases the size of the final module. @@ -41,6 +42,7 @@ SECTIONS { } .text : { *(.text .text.[0-9a-zA-Z_]*) } +#endif } /* bring in arch-specific sections */ diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening index 269967c4fc1b..a56c36470cb1 100644 --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -64,7 +64,7 @@ choice config GCC_PLUGIN_STRUCTLEAK_BYREF bool "zero-init structs passed by reference (strong)" depends on GCC_PLUGINS - depends on !(KASAN && KASAN_STACK=1) + depends on !(KASAN && KASAN_STACK) select GCC_PLUGIN_STRUCTLEAK help Zero-initialize any structures on the stack that may @@ -82,7 +82,7 @@ choice config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL bool "zero-init anything passed by reference (very strong)" depends on GCC_PLUGINS - depends on !(KASAN && KASAN_STACK=1) + depends on !(KASAN && KASAN_STACK) select GCC_PLUGIN_STRUCTLEAK help Zero-initialize any stack variables that may be passed diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c index a662024b4c70..23240d793b07 100644 --- a/security/integrity/digsig_asymmetric.c +++ b/security/integrity/digsig_asymmetric.c @@ -84,6 +84,7 @@ int asymmetric_verify(struct key *keyring, const char *sig, { struct public_key_signature pks; struct signature_v2_hdr *hdr = (struct signature_v2_hdr *)sig; + const struct public_key *pk; struct key *key; int ret; @@ -105,23 +106,20 @@ int asymmetric_verify(struct key *keyring, const char *sig, memset(&pks, 0, sizeof(pks)); pks.hash_algo = hash_algo_name[hdr->hash_algo]; - switch (hdr->hash_algo) { - case HASH_ALGO_STREEBOG_256: - case HASH_ALGO_STREEBOG_512: - /* EC-RDSA and Streebog should go together. */ - pks.pkey_algo = "ecrdsa"; - pks.encoding = "raw"; - break; - case HASH_ALGO_SM3_256: - /* SM2 and SM3 should go together. */ - pks.pkey_algo = "sm2"; - pks.encoding = "raw"; - break; - default: - pks.pkey_algo = "rsa"; + + pk = asymmetric_key_public_key(key); + pks.pkey_algo = pk->pkey_algo; + if (!strcmp(pk->pkey_algo, "rsa")) pks.encoding = "pkcs1"; - break; - } + else if (!strncmp(pk->pkey_algo, "ecdsa-", 6)) + /* edcsa-nist-p192 etc. */ + pks.encoding = "x962"; + else if (!strcmp(pk->pkey_algo, "ecrdsa") || + !strcmp(pk->pkey_algo, "sm2")) + pks.encoding = "raw"; + else + return -ENOPKG; + pks.digest = (u8 *)data; pks.digest_size = datalen; pks.s = hdr->sig; diff --git a/security/integrity/iint.c b/security/integrity/iint.c index 1d20003243c3..0ba01847e836 100644 --- a/security/integrity/iint.c +++ b/security/integrity/iint.c @@ -98,6 +98,14 @@ struct integrity_iint_cache *integrity_inode_get(struct inode *inode) struct rb_node *node, *parent = NULL; struct integrity_iint_cache *iint, *test_iint; + /* + * The integrity's "iint_cache" is initialized at security_init(), + * unless it is not included in the ordered list of LSMs enabled + * on the boot command line. + */ + if (!iint_cache) + panic("%s: lsm=integrity required.\n", __func__); + iint = integrity_iint_find(inode); if (iint) return iint; diff --git a/security/integrity/platform_certs/keyring_handler.c b/security/integrity/platform_certs/keyring_handler.c index c5ba695c10e3..5604bd57c990 100644 --- a/security/integrity/platform_certs/keyring_handler.c +++ b/security/integrity/platform_certs/keyring_handler.c @@ -56,6 +56,15 @@ static __init void uefi_blacklist_binary(const char *source, } /* + * Add an X509 cert to the revocation list. + */ +static __init void uefi_revocation_list_x509(const char *source, + const void *data, size_t len) +{ + add_key_to_revocation_list(data, len); +} + +/* * Return the appropriate handler for particular signature list types found in * the UEFI db and MokListRT tables. */ @@ -76,5 +85,7 @@ __init efi_element_handler_t get_handler_for_dbx(const efi_guid_t *sig_type) return uefi_blacklist_x509_tbs; if (efi_guidcmp(*sig_type, efi_cert_sha256_guid) == 0) return uefi_blacklist_binary; + if (efi_guidcmp(*sig_type, efi_cert_x509_guid) == 0) + return uefi_revocation_list_x509; return 0; } diff --git a/security/integrity/platform_certs/load_uefi.c b/security/integrity/platform_certs/load_uefi.c index ee4b4c666854..f290f78c3f30 100644 --- a/security/integrity/platform_certs/load_uefi.c +++ b/security/integrity/platform_certs/load_uefi.c @@ -132,8 +132,9 @@ static int __init load_moklist_certs(void) static int __init load_uefi_certs(void) { efi_guid_t secure_var = EFI_IMAGE_SECURITY_DATABASE_GUID; - void *db = NULL, *dbx = NULL; - unsigned long dbsize = 0, dbxsize = 0; + efi_guid_t mok_var = EFI_SHIM_LOCK_GUID; + void *db = NULL, *dbx = NULL, *mokx = NULL; + unsigned long dbsize = 0, dbxsize = 0, mokxsize = 0; efi_status_t status; int rc = 0; @@ -175,6 +176,21 @@ static int __init load_uefi_certs(void) kfree(dbx); } + mokx = get_cert_list(L"MokListXRT", &mok_var, &mokxsize, &status); + if (!mokx) { + if (status == EFI_NOT_FOUND) + pr_debug("mokx variable wasn't found\n"); + else + pr_info("Couldn't get mokx list\n"); + } else { + rc = parse_efi_signature_list("UEFI:MokListXRT", + mokx, mokxsize, + get_handler_for_dbx); + if (rc) + pr_err("Couldn't parse mokx signatures %d\n", rc); + kfree(mokx); + } + /* Load the MokListRT certs */ rc = load_moklist_certs(); diff --git a/security/keys/Kconfig b/security/keys/Kconfig index c161642a8484..64b81abd087e 100644 --- a/security/keys/Kconfig +++ b/security/keys/Kconfig @@ -75,6 +75,9 @@ config TRUSTED_KEYS select CRYPTO_HMAC select CRYPTO_SHA1 select CRYPTO_HASH_INFO + select ASN1_ENCODER + select OID_REGISTRY + select ASN1 help This option provides support for creating, sealing, and unsealing keys in the kernel. Trusted keys are random number symmetric keys, diff --git a/security/keys/trusted-keys/Makefile b/security/keys/trusted-keys/Makefile index 7b73cebbb378..feb8b6c3cc79 100644 --- a/security/keys/trusted-keys/Makefile +++ b/security/keys/trusted-keys/Makefile @@ -4,5 +4,11 @@ # obj-$(CONFIG_TRUSTED_KEYS) += trusted.o +trusted-y += trusted_core.o trusted-y += trusted_tpm1.o + +$(obj)/trusted_tpm2.o: $(obj)/tpm2key.asn1.h trusted-y += trusted_tpm2.o +trusted-y += tpm2key.asn1.o + +trusted-$(CONFIG_TEE) += trusted_tee.o diff --git a/security/keys/trusted-keys/tpm2key.asn1 b/security/keys/trusted-keys/tpm2key.asn1 new file mode 100644 index 000000000000..f57f869ad600 --- /dev/null +++ b/security/keys/trusted-keys/tpm2key.asn1 @@ -0,0 +1,11 @@ +--- +--- ASN.1 for TPM 2.0 keys +--- + +TPMKey ::= SEQUENCE { + type OBJECT IDENTIFIER ({tpm2_key_type}), + emptyAuth [0] EXPLICIT BOOLEAN OPTIONAL, + parent INTEGER ({tpm2_key_parent}), + pubkey OCTET STRING ({tpm2_key_pub}), + privkey OCTET STRING ({tpm2_key_priv}) + } diff --git a/security/keys/trusted-keys/trusted_core.c b/security/keys/trusted-keys/trusted_core.c new file mode 100644 index 000000000000..d5c891d8d353 --- /dev/null +++ b/security/keys/trusted-keys/trusted_core.c @@ -0,0 +1,360 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2010 IBM Corporation + * Copyright (c) 2019-2021, Linaro Limited + * + * See Documentation/security/keys/trusted-encrypted.rst + */ + +#include <keys/user-type.h> +#include <keys/trusted-type.h> +#include <keys/trusted_tee.h> +#include <keys/trusted_tpm.h> +#include <linux/capability.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/key-type.h> +#include <linux/module.h> +#include <linux/parser.h> +#include <linux/rcupdate.h> +#include <linux/slab.h> +#include <linux/static_call.h> +#include <linux/string.h> +#include <linux/uaccess.h> + +static char *trusted_key_source; +module_param_named(source, trusted_key_source, charp, 0); +MODULE_PARM_DESC(source, "Select trusted keys source (tpm or tee)"); + +static const struct trusted_key_source trusted_key_sources[] = { +#if defined(CONFIG_TCG_TPM) + { "tpm", &trusted_key_tpm_ops }, +#endif +#if defined(CONFIG_TEE) + { "tee", &trusted_key_tee_ops }, +#endif +}; + +DEFINE_STATIC_CALL_NULL(trusted_key_init, *trusted_key_sources[0].ops->init); +DEFINE_STATIC_CALL_NULL(trusted_key_seal, *trusted_key_sources[0].ops->seal); +DEFINE_STATIC_CALL_NULL(trusted_key_unseal, + *trusted_key_sources[0].ops->unseal); +DEFINE_STATIC_CALL_NULL(trusted_key_get_random, + *trusted_key_sources[0].ops->get_random); +DEFINE_STATIC_CALL_NULL(trusted_key_exit, *trusted_key_sources[0].ops->exit); +static unsigned char migratable; + +enum { + Opt_err, + Opt_new, Opt_load, Opt_update, +}; + +static const match_table_t key_tokens = { + {Opt_new, "new"}, + {Opt_load, "load"}, + {Opt_update, "update"}, + {Opt_err, NULL} +}; + +/* + * datablob_parse - parse the keyctl data and fill in the + * payload structure + * + * On success returns 0, otherwise -EINVAL. + */ +static int datablob_parse(char **datablob, struct trusted_key_payload *p) +{ + substring_t args[MAX_OPT_ARGS]; + long keylen; + int ret = -EINVAL; + int key_cmd; + char *c; + + /* main command */ + c = strsep(datablob, " \t"); + if (!c) + return -EINVAL; + key_cmd = match_token(c, key_tokens, args); + switch (key_cmd) { + case Opt_new: + /* first argument is key size */ + c = strsep(datablob, " \t"); + if (!c) + return -EINVAL; + ret = kstrtol(c, 10, &keylen); + if (ret < 0 || keylen < MIN_KEY_SIZE || keylen > MAX_KEY_SIZE) + return -EINVAL; + p->key_len = keylen; + ret = Opt_new; + break; + case Opt_load: + /* first argument is sealed blob */ + c = strsep(datablob, " \t"); + if (!c) + return -EINVAL; + p->blob_len = strlen(c) / 2; + if (p->blob_len > MAX_BLOB_SIZE) + return -EINVAL; + ret = hex2bin(p->blob, c, p->blob_len); + if (ret < 0) + return -EINVAL; + ret = Opt_load; + break; + case Opt_update: + ret = Opt_update; + break; + case Opt_err: + return -EINVAL; + } + return ret; +} + +static struct trusted_key_payload *trusted_payload_alloc(struct key *key) +{ + struct trusted_key_payload *p = NULL; + int ret; + + ret = key_payload_reserve(key, sizeof(*p)); + if (ret < 0) + goto err; + p = kzalloc(sizeof(*p), GFP_KERNEL); + if (!p) + goto err; + + p->migratable = migratable; +err: + return p; +} + +/* + * trusted_instantiate - create a new trusted key + * + * Unseal an existing trusted blob or, for a new key, get a + * random key, then seal and create a trusted key-type key, + * adding it to the specified keyring. + * + * On success, return 0. Otherwise return errno. + */ +static int trusted_instantiate(struct key *key, + struct key_preparsed_payload *prep) +{ + struct trusted_key_payload *payload = NULL; + size_t datalen = prep->datalen; + char *datablob, *orig_datablob; + int ret = 0; + int key_cmd; + size_t key_len; + + if (datalen <= 0 || datalen > 32767 || !prep->data) + return -EINVAL; + + orig_datablob = datablob = kmalloc(datalen + 1, GFP_KERNEL); + if (!datablob) + return -ENOMEM; + memcpy(datablob, prep->data, datalen); + datablob[datalen] = '\0'; + + payload = trusted_payload_alloc(key); + if (!payload) { + ret = -ENOMEM; + goto out; + } + + key_cmd = datablob_parse(&datablob, payload); + if (key_cmd < 0) { + ret = key_cmd; + goto out; + } + + dump_payload(payload); + + switch (key_cmd) { + case Opt_load: + ret = static_call(trusted_key_unseal)(payload, datablob); + dump_payload(payload); + if (ret < 0) + pr_info("key_unseal failed (%d)\n", ret); + break; + case Opt_new: + key_len = payload->key_len; + ret = static_call(trusted_key_get_random)(payload->key, + key_len); + if (ret < 0) + goto out; + + if (ret != key_len) { + pr_info("key_create failed (%d)\n", ret); + ret = -EIO; + goto out; + } + + ret = static_call(trusted_key_seal)(payload, datablob); + if (ret < 0) + pr_info("key_seal failed (%d)\n", ret); + break; + default: + ret = -EINVAL; + } +out: + kfree_sensitive(orig_datablob); + if (!ret) + rcu_assign_keypointer(key, payload); + else + kfree_sensitive(payload); + return ret; +} + +static void trusted_rcu_free(struct rcu_head *rcu) +{ + struct trusted_key_payload *p; + + p = container_of(rcu, struct trusted_key_payload, rcu); + kfree_sensitive(p); +} + +/* + * trusted_update - reseal an existing key with new PCR values + */ +static int trusted_update(struct key *key, struct key_preparsed_payload *prep) +{ + struct trusted_key_payload *p; + struct trusted_key_payload *new_p; + size_t datalen = prep->datalen; + char *datablob, *orig_datablob; + int ret = 0; + + if (key_is_negative(key)) + return -ENOKEY; + p = key->payload.data[0]; + if (!p->migratable) + return -EPERM; + if (datalen <= 0 || datalen > 32767 || !prep->data) + return -EINVAL; + + orig_datablob = datablob = kmalloc(datalen + 1, GFP_KERNEL); + if (!datablob) + return -ENOMEM; + + new_p = trusted_payload_alloc(key); + if (!new_p) { + ret = -ENOMEM; + goto out; + } + + memcpy(datablob, prep->data, datalen); + datablob[datalen] = '\0'; + ret = datablob_parse(&datablob, new_p); + if (ret != Opt_update) { + ret = -EINVAL; + kfree_sensitive(new_p); + goto out; + } + + /* copy old key values, and reseal with new pcrs */ + new_p->migratable = p->migratable; + new_p->key_len = p->key_len; + memcpy(new_p->key, p->key, p->key_len); + dump_payload(p); + dump_payload(new_p); + + ret = static_call(trusted_key_seal)(new_p, datablob); + if (ret < 0) { + pr_info("key_seal failed (%d)\n", ret); + kfree_sensitive(new_p); + goto out; + } + + rcu_assign_keypointer(key, new_p); + call_rcu(&p->rcu, trusted_rcu_free); +out: + kfree_sensitive(orig_datablob); + return ret; +} + +/* + * trusted_read - copy the sealed blob data to userspace in hex. + * On success, return to userspace the trusted key datablob size. + */ +static long trusted_read(const struct key *key, char *buffer, + size_t buflen) +{ + const struct trusted_key_payload *p; + char *bufp; + int i; + + p = dereference_key_locked(key); + if (!p) + return -EINVAL; + + if (buffer && buflen >= 2 * p->blob_len) { + bufp = buffer; + for (i = 0; i < p->blob_len; i++) + bufp = hex_byte_pack(bufp, p->blob[i]); + } + return 2 * p->blob_len; +} + +/* + * trusted_destroy - clear and free the key's payload + */ +static void trusted_destroy(struct key *key) +{ + kfree_sensitive(key->payload.data[0]); +} + +struct key_type key_type_trusted = { + .name = "trusted", + .instantiate = trusted_instantiate, + .update = trusted_update, + .destroy = trusted_destroy, + .describe = user_describe, + .read = trusted_read, +}; +EXPORT_SYMBOL_GPL(key_type_trusted); + +static int __init init_trusted(void) +{ + int i, ret = 0; + + for (i = 0; i < ARRAY_SIZE(trusted_key_sources); i++) { + if (trusted_key_source && + strncmp(trusted_key_source, trusted_key_sources[i].name, + strlen(trusted_key_sources[i].name))) + continue; + + static_call_update(trusted_key_init, + trusted_key_sources[i].ops->init); + static_call_update(trusted_key_seal, + trusted_key_sources[i].ops->seal); + static_call_update(trusted_key_unseal, + trusted_key_sources[i].ops->unseal); + static_call_update(trusted_key_get_random, + trusted_key_sources[i].ops->get_random); + static_call_update(trusted_key_exit, + trusted_key_sources[i].ops->exit); + migratable = trusted_key_sources[i].ops->migratable; + + ret = static_call(trusted_key_init)(); + if (!ret) + break; + } + + /* + * encrypted_keys.ko depends on successful load of this module even if + * trusted key implementation is not found. + */ + if (ret == -ENODEV) + return 0; + + return ret; +} + +static void __exit cleanup_trusted(void) +{ + static_call(trusted_key_exit)(); +} + +late_initcall(init_trusted); +module_exit(cleanup_trusted); + +MODULE_LICENSE("GPL"); diff --git a/security/keys/trusted-keys/trusted_tee.c b/security/keys/trusted-keys/trusted_tee.c new file mode 100644 index 000000000000..2ce66c199e1d --- /dev/null +++ b/security/keys/trusted-keys/trusted_tee.c @@ -0,0 +1,318 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019-2021 Linaro Ltd. + * + * Author: + * Sumit Garg <sumit.garg@linaro.org> + */ + +#include <linux/err.h> +#include <linux/key-type.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/tee_drv.h> +#include <linux/uuid.h> + +#include <keys/trusted_tee.h> + +#define DRIVER_NAME "trusted-key-tee" + +/* + * Get random data for symmetric key + * + * [out] memref[0] Random data + */ +#define TA_CMD_GET_RANDOM 0x0 + +/* + * Seal trusted key using hardware unique key + * + * [in] memref[0] Plain key + * [out] memref[1] Sealed key datablob + */ +#define TA_CMD_SEAL 0x1 + +/* + * Unseal trusted key using hardware unique key + * + * [in] memref[0] Sealed key datablob + * [out] memref[1] Plain key + */ +#define TA_CMD_UNSEAL 0x2 + +/** + * struct trusted_key_tee_private - TEE Trusted key private data + * @dev: TEE based Trusted key device. + * @ctx: TEE context handler. + * @session_id: Trusted key TA session identifier. + * @shm_pool: Memory pool shared with TEE device. + */ +struct trusted_key_tee_private { + struct device *dev; + struct tee_context *ctx; + u32 session_id; + struct tee_shm *shm_pool; +}; + +static struct trusted_key_tee_private pvt_data; + +/* + * Have the TEE seal(encrypt) the symmetric key + */ +static int trusted_tee_seal(struct trusted_key_payload *p, char *datablob) +{ + int ret; + struct tee_ioctl_invoke_arg inv_arg; + struct tee_param param[4]; + struct tee_shm *reg_shm_in = NULL, *reg_shm_out = NULL; + + memset(&inv_arg, 0, sizeof(inv_arg)); + memset(¶m, 0, sizeof(param)); + + reg_shm_in = tee_shm_register(pvt_data.ctx, (unsigned long)p->key, + p->key_len, TEE_SHM_DMA_BUF | + TEE_SHM_KERNEL_MAPPED); + if (IS_ERR(reg_shm_in)) { + dev_err(pvt_data.dev, "key shm register failed\n"); + return PTR_ERR(reg_shm_in); + } + + reg_shm_out = tee_shm_register(pvt_data.ctx, (unsigned long)p->blob, + sizeof(p->blob), TEE_SHM_DMA_BUF | + TEE_SHM_KERNEL_MAPPED); + if (IS_ERR(reg_shm_out)) { + dev_err(pvt_data.dev, "blob shm register failed\n"); + ret = PTR_ERR(reg_shm_out); + goto out; + } + + inv_arg.func = TA_CMD_SEAL; + inv_arg.session = pvt_data.session_id; + inv_arg.num_params = 4; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT; + param[0].u.memref.shm = reg_shm_in; + param[0].u.memref.size = p->key_len; + param[0].u.memref.shm_offs = 0; + param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT; + param[1].u.memref.shm = reg_shm_out; + param[1].u.memref.size = sizeof(p->blob); + param[1].u.memref.shm_offs = 0; + + ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param); + if ((ret < 0) || (inv_arg.ret != 0)) { + dev_err(pvt_data.dev, "TA_CMD_SEAL invoke err: %x\n", + inv_arg.ret); + ret = -EFAULT; + } else { + p->blob_len = param[1].u.memref.size; + } + +out: + if (reg_shm_out) + tee_shm_free(reg_shm_out); + if (reg_shm_in) + tee_shm_free(reg_shm_in); + + return ret; +} + +/* + * Have the TEE unseal(decrypt) the symmetric key + */ +static int trusted_tee_unseal(struct trusted_key_payload *p, char *datablob) +{ + int ret; + struct tee_ioctl_invoke_arg inv_arg; + struct tee_param param[4]; + struct tee_shm *reg_shm_in = NULL, *reg_shm_out = NULL; + + memset(&inv_arg, 0, sizeof(inv_arg)); + memset(¶m, 0, sizeof(param)); + + reg_shm_in = tee_shm_register(pvt_data.ctx, (unsigned long)p->blob, + p->blob_len, TEE_SHM_DMA_BUF | + TEE_SHM_KERNEL_MAPPED); + if (IS_ERR(reg_shm_in)) { + dev_err(pvt_data.dev, "blob shm register failed\n"); + return PTR_ERR(reg_shm_in); + } + + reg_shm_out = tee_shm_register(pvt_data.ctx, (unsigned long)p->key, + sizeof(p->key), TEE_SHM_DMA_BUF | + TEE_SHM_KERNEL_MAPPED); + if (IS_ERR(reg_shm_out)) { + dev_err(pvt_data.dev, "key shm register failed\n"); + ret = PTR_ERR(reg_shm_out); + goto out; + } + + inv_arg.func = TA_CMD_UNSEAL; + inv_arg.session = pvt_data.session_id; + inv_arg.num_params = 4; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_INPUT; + param[0].u.memref.shm = reg_shm_in; + param[0].u.memref.size = p->blob_len; + param[0].u.memref.shm_offs = 0; + param[1].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT; + param[1].u.memref.shm = reg_shm_out; + param[1].u.memref.size = sizeof(p->key); + param[1].u.memref.shm_offs = 0; + + ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param); + if ((ret < 0) || (inv_arg.ret != 0)) { + dev_err(pvt_data.dev, "TA_CMD_UNSEAL invoke err: %x\n", + inv_arg.ret); + ret = -EFAULT; + } else { + p->key_len = param[1].u.memref.size; + } + +out: + if (reg_shm_out) + tee_shm_free(reg_shm_out); + if (reg_shm_in) + tee_shm_free(reg_shm_in); + + return ret; +} + +/* + * Have the TEE generate random symmetric key + */ +static int trusted_tee_get_random(unsigned char *key, size_t key_len) +{ + int ret; + struct tee_ioctl_invoke_arg inv_arg; + struct tee_param param[4]; + struct tee_shm *reg_shm = NULL; + + memset(&inv_arg, 0, sizeof(inv_arg)); + memset(¶m, 0, sizeof(param)); + + reg_shm = tee_shm_register(pvt_data.ctx, (unsigned long)key, key_len, + TEE_SHM_DMA_BUF | TEE_SHM_KERNEL_MAPPED); + if (IS_ERR(reg_shm)) { + dev_err(pvt_data.dev, "key shm register failed\n"); + return PTR_ERR(reg_shm); + } + + inv_arg.func = TA_CMD_GET_RANDOM; + inv_arg.session = pvt_data.session_id; + inv_arg.num_params = 4; + + param[0].attr = TEE_IOCTL_PARAM_ATTR_TYPE_MEMREF_OUTPUT; + param[0].u.memref.shm = reg_shm; + param[0].u.memref.size = key_len; + param[0].u.memref.shm_offs = 0; + + ret = tee_client_invoke_func(pvt_data.ctx, &inv_arg, param); + if ((ret < 0) || (inv_arg.ret != 0)) { + dev_err(pvt_data.dev, "TA_CMD_GET_RANDOM invoke err: %x\n", + inv_arg.ret); + ret = -EFAULT; + } else { + ret = param[0].u.memref.size; + } + + tee_shm_free(reg_shm); + + return ret; +} + +static int optee_ctx_match(struct tee_ioctl_version_data *ver, const void *data) +{ + if (ver->impl_id == TEE_IMPL_ID_OPTEE) + return 1; + else + return 0; +} + +static int trusted_key_probe(struct device *dev) +{ + struct tee_client_device *rng_device = to_tee_client_device(dev); + int ret; + struct tee_ioctl_open_session_arg sess_arg; + + memset(&sess_arg, 0, sizeof(sess_arg)); + + pvt_data.ctx = tee_client_open_context(NULL, optee_ctx_match, NULL, + NULL); + if (IS_ERR(pvt_data.ctx)) + return -ENODEV; + + memcpy(sess_arg.uuid, rng_device->id.uuid.b, TEE_IOCTL_UUID_LEN); + sess_arg.clnt_login = TEE_IOCTL_LOGIN_REE_KERNEL; + sess_arg.num_params = 0; + + ret = tee_client_open_session(pvt_data.ctx, &sess_arg, NULL); + if ((ret < 0) || (sess_arg.ret != 0)) { + dev_err(dev, "tee_client_open_session failed, err: %x\n", + sess_arg.ret); + ret = -EINVAL; + goto out_ctx; + } + pvt_data.session_id = sess_arg.session; + + ret = register_key_type(&key_type_trusted); + if (ret < 0) + goto out_sess; + + pvt_data.dev = dev; + + return 0; + +out_sess: + tee_client_close_session(pvt_data.ctx, pvt_data.session_id); +out_ctx: + tee_client_close_context(pvt_data.ctx); + + return ret; +} + +static int trusted_key_remove(struct device *dev) +{ + unregister_key_type(&key_type_trusted); + tee_client_close_session(pvt_data.ctx, pvt_data.session_id); + tee_client_close_context(pvt_data.ctx); + + return 0; +} + +static const struct tee_client_device_id trusted_key_id_table[] = { + {UUID_INIT(0xf04a0fe7, 0x1f5d, 0x4b9b, + 0xab, 0xf7, 0x61, 0x9b, 0x85, 0xb4, 0xce, 0x8c)}, + {} +}; +MODULE_DEVICE_TABLE(tee, trusted_key_id_table); + +static struct tee_client_driver trusted_key_driver = { + .id_table = trusted_key_id_table, + .driver = { + .name = DRIVER_NAME, + .bus = &tee_bus_type, + .probe = trusted_key_probe, + .remove = trusted_key_remove, + }, +}; + +static int trusted_tee_init(void) +{ + return driver_register(&trusted_key_driver.driver); +} + +static void trusted_tee_exit(void) +{ + driver_unregister(&trusted_key_driver.driver); +} + +struct trusted_key_ops trusted_key_tee_ops = { + .migratable = 0, /* non-migratable */ + .init = trusted_tee_init, + .seal = trusted_tee_seal, + .unseal = trusted_tee_unseal, + .get_random = trusted_tee_get_random, + .exit = trusted_tee_exit, +}; diff --git a/security/keys/trusted-keys/trusted_tpm1.c b/security/keys/trusted-keys/trusted_tpm1.c index 493eb91ed017..469394550801 100644 --- a/security/keys/trusted-keys/trusted_tpm1.c +++ b/security/keys/trusted-keys/trusted_tpm1.c @@ -1,29 +1,22 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 IBM Corporation - * - * Author: - * David Safford <safford@us.ibm.com> + * Copyright (c) 2019-2021, Linaro Limited * * See Documentation/security/keys/trusted-encrypted.rst */ #include <crypto/hash_info.h> -#include <linux/uaccess.h> -#include <linux/module.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/parser.h> #include <linux/string.h> #include <linux/err.h> -#include <keys/user-type.h> #include <keys/trusted-type.h> #include <linux/key-type.h> -#include <linux/rcupdate.h> #include <linux/crypto.h> #include <crypto/hash.h> #include <crypto/sha1.h> -#include <linux/capability.h> #include <linux/tpm.h> #include <linux/tpm_command.h> @@ -63,7 +56,7 @@ static int TSS_sha1(const unsigned char *data, unsigned int datalen, sdesc = init_sdesc(hashalg); if (IS_ERR(sdesc)) { - pr_info("trusted_key: can't alloc %s\n", hash_alg); + pr_info("can't alloc %s\n", hash_alg); return PTR_ERR(sdesc); } @@ -83,7 +76,7 @@ static int TSS_rawhmac(unsigned char *digest, const unsigned char *key, sdesc = init_sdesc(hmacalg); if (IS_ERR(sdesc)) { - pr_info("trusted_key: can't alloc %s\n", hmac_alg); + pr_info("can't alloc %s\n", hmac_alg); return PTR_ERR(sdesc); } @@ -136,7 +129,7 @@ int TSS_authhmac(unsigned char *digest, const unsigned char *key, sdesc = init_sdesc(hashalg); if (IS_ERR(sdesc)) { - pr_info("trusted_key: can't alloc %s\n", hash_alg); + pr_info("can't alloc %s\n", hash_alg); return PTR_ERR(sdesc); } @@ -212,7 +205,7 @@ int TSS_checkhmac1(unsigned char *buffer, sdesc = init_sdesc(hashalg); if (IS_ERR(sdesc)) { - pr_info("trusted_key: can't alloc %s\n", hash_alg); + pr_info("can't alloc %s\n", hash_alg); return PTR_ERR(sdesc); } ret = crypto_shash_init(&sdesc->shash); @@ -305,7 +298,7 @@ static int TSS_checkhmac2(unsigned char *buffer, sdesc = init_sdesc(hashalg); if (IS_ERR(sdesc)) { - pr_info("trusted_key: can't alloc %s\n", hash_alg); + pr_info("can't alloc %s\n", hash_alg); return PTR_ERR(sdesc); } ret = crypto_shash_init(&sdesc->shash); @@ -597,12 +590,12 @@ static int tpm_unseal(struct tpm_buf *tb, /* sessions for unsealing key and data */ ret = oiap(tb, &authhandle1, enonce1); if (ret < 0) { - pr_info("trusted_key: oiap failed (%d)\n", ret); + pr_info("oiap failed (%d)\n", ret); return ret; } ret = oiap(tb, &authhandle2, enonce2); if (ret < 0) { - pr_info("trusted_key: oiap failed (%d)\n", ret); + pr_info("oiap failed (%d)\n", ret); return ret; } @@ -612,7 +605,7 @@ static int tpm_unseal(struct tpm_buf *tb, return ret; if (ret != TPM_NONCE_SIZE) { - pr_info("trusted_key: tpm_get_random failed (%d)\n", ret); + pr_info("tpm_get_random failed (%d)\n", ret); return -EIO; } ret = TSS_authhmac(authdata1, keyauth, TPM_NONCE_SIZE, @@ -641,7 +634,7 @@ static int tpm_unseal(struct tpm_buf *tb, ret = trusted_tpm_send(tb->data, MAX_BUF_SIZE); if (ret < 0) { - pr_info("trusted_key: authhmac failed (%d)\n", ret); + pr_info("authhmac failed (%d)\n", ret); return ret; } @@ -653,7 +646,7 @@ static int tpm_unseal(struct tpm_buf *tb, *datalen, TPM_DATA_OFFSET + sizeof(uint32_t), 0, 0); if (ret < 0) { - pr_info("trusted_key: TSS_checkhmac2 failed (%d)\n", ret); + pr_info("TSS_checkhmac2 failed (%d)\n", ret); return ret; } memcpy(data, tb->data + TPM_DATA_OFFSET + sizeof(uint32_t), *datalen); @@ -680,7 +673,7 @@ static int key_seal(struct trusted_key_payload *p, p->key, p->key_len + 1, p->blob, &p->blob_len, o->blobauth, o->pcrinfo, o->pcrinfo_len); if (ret < 0) - pr_info("trusted_key: srkseal failed (%d)\n", ret); + pr_info("srkseal failed (%d)\n", ret); tpm_buf_destroy(&tb); return ret; @@ -702,7 +695,7 @@ static int key_unseal(struct trusted_key_payload *p, ret = tpm_unseal(&tb, o->keyhandle, o->keyauth, p->blob, p->blob_len, o->blobauth, p->key, &p->key_len); if (ret < 0) - pr_info("trusted_key: srkunseal failed (%d)\n", ret); + pr_info("srkunseal failed (%d)\n", ret); else /* pull migratable flag out of sealed key */ p->migratable = p->key[--p->key_len]; @@ -713,7 +706,6 @@ static int key_unseal(struct trusted_key_payload *p, enum { Opt_err, - Opt_new, Opt_load, Opt_update, Opt_keyhandle, Opt_keyauth, Opt_blobauth, Opt_pcrinfo, Opt_pcrlock, Opt_migratable, Opt_hash, @@ -722,9 +714,6 @@ enum { }; static const match_table_t key_tokens = { - {Opt_new, "new"}, - {Opt_load, "load"}, - {Opt_update, "update"}, {Opt_keyhandle, "keyhandle=%s"}, {Opt_keyauth, "keyauth=%s"}, {Opt_blobauth, "blobauth=%s"}, @@ -758,6 +747,9 @@ static int getoptions(char *c, struct trusted_key_payload *pay, opt->hash = tpm2 ? HASH_ALGO_SHA256 : HASH_ALGO_SHA1; + if (!c) + return 0; + while ((p = strsep(&c, " \t"))) { if (*p == '\0' || *p == ' ' || *p == '\t') continue; @@ -791,13 +783,33 @@ static int getoptions(char *c, struct trusted_key_payload *pay, return -EINVAL; break; case Opt_blobauth: - if (strlen(args[0].from) != 2 * SHA1_DIGEST_SIZE) - return -EINVAL; - res = hex2bin(opt->blobauth, args[0].from, - SHA1_DIGEST_SIZE); - if (res < 0) - return -EINVAL; + /* + * TPM 1.2 authorizations are sha1 hashes passed in as + * hex strings. TPM 2.0 authorizations are simple + * passwords (although it can take a hash as well) + */ + opt->blobauth_len = strlen(args[0].from); + + if (opt->blobauth_len == 2 * TPM_DIGEST_SIZE) { + res = hex2bin(opt->blobauth, args[0].from, + TPM_DIGEST_SIZE); + if (res < 0) + return -EINVAL; + + opt->blobauth_len = TPM_DIGEST_SIZE; + break; + } + + if (tpm2 && opt->blobauth_len <= sizeof(opt->blobauth)) { + memcpy(opt->blobauth, args[0].from, + opt->blobauth_len); + break; + } + + return -EINVAL; + break; + case Opt_migratable: if (*args[0].from == '0') pay->migratable = 0; @@ -822,7 +834,7 @@ static int getoptions(char *c, struct trusted_key_payload *pay, if (i == HASH_ALGO__LAST) return -EINVAL; if (!tpm2 && i != HASH_ALGO_SHA1) { - pr_info("trusted_key: TPM 1.x only supports SHA-1.\n"); + pr_info("TPM 1.x only supports SHA-1.\n"); return -EINVAL; } break; @@ -851,71 +863,6 @@ static int getoptions(char *c, struct trusted_key_payload *pay, return 0; } -/* - * datablob_parse - parse the keyctl data and fill in the - * payload and options structures - * - * On success returns 0, otherwise -EINVAL. - */ -static int datablob_parse(char *datablob, struct trusted_key_payload *p, - struct trusted_key_options *o) -{ - substring_t args[MAX_OPT_ARGS]; - long keylen; - int ret = -EINVAL; - int key_cmd; - char *c; - - /* main command */ - c = strsep(&datablob, " \t"); - if (!c) - return -EINVAL; - key_cmd = match_token(c, key_tokens, args); - switch (key_cmd) { - case Opt_new: - /* first argument is key size */ - c = strsep(&datablob, " \t"); - if (!c) - return -EINVAL; - ret = kstrtol(c, 10, &keylen); - if (ret < 0 || keylen < MIN_KEY_SIZE || keylen > MAX_KEY_SIZE) - return -EINVAL; - p->key_len = keylen; - ret = getoptions(datablob, p, o); - if (ret < 0) - return ret; - ret = Opt_new; - break; - case Opt_load: - /* first argument is sealed blob */ - c = strsep(&datablob, " \t"); - if (!c) - return -EINVAL; - p->blob_len = strlen(c) / 2; - if (p->blob_len > MAX_BLOB_SIZE) - return -EINVAL; - ret = hex2bin(p->blob, c, p->blob_len); - if (ret < 0) - return -EINVAL; - ret = getoptions(datablob, p, o); - if (ret < 0) - return ret; - ret = Opt_load; - break; - case Opt_update: - /* all arguments are options */ - ret = getoptions(datablob, p, o); - if (ret < 0) - return ret; - ret = Opt_update; - break; - case Opt_err: - return -EINVAL; - break; - } - return ret; -} - static struct trusted_key_options *trusted_options_alloc(void) { struct trusted_key_options *options; @@ -936,252 +883,99 @@ static struct trusted_key_options *trusted_options_alloc(void) return options; } -static struct trusted_key_payload *trusted_payload_alloc(struct key *key) +static int trusted_tpm_seal(struct trusted_key_payload *p, char *datablob) { - struct trusted_key_payload *p = NULL; - int ret; - - ret = key_payload_reserve(key, sizeof *p); - if (ret < 0) - return p; - p = kzalloc(sizeof *p, GFP_KERNEL); - if (p) - p->migratable = 1; /* migratable by default */ - return p; -} - -/* - * trusted_instantiate - create a new trusted key - * - * Unseal an existing trusted blob or, for a new key, get a - * random key, then seal and create a trusted key-type key, - * adding it to the specified keyring. - * - * On success, return 0. Otherwise return errno. - */ -static int trusted_instantiate(struct key *key, - struct key_preparsed_payload *prep) -{ - struct trusted_key_payload *payload = NULL; struct trusted_key_options *options = NULL; - size_t datalen = prep->datalen; - char *datablob; int ret = 0; - int key_cmd; - size_t key_len; int tpm2; tpm2 = tpm_is_tpm2(chip); if (tpm2 < 0) return tpm2; - if (datalen <= 0 || datalen > 32767 || !prep->data) - return -EINVAL; - - datablob = kmalloc(datalen + 1, GFP_KERNEL); - if (!datablob) + options = trusted_options_alloc(); + if (!options) return -ENOMEM; - memcpy(datablob, prep->data, datalen); - datablob[datalen] = '\0'; - options = trusted_options_alloc(); - if (!options) { - ret = -ENOMEM; - goto out; - } - payload = trusted_payload_alloc(key); - if (!payload) { - ret = -ENOMEM; + ret = getoptions(datablob, p, options); + if (ret < 0) goto out; - } + dump_options(options); - key_cmd = datablob_parse(datablob, payload, options); - if (key_cmd < 0) { - ret = key_cmd; + if (!options->keyhandle && !tpm2) { + ret = -EINVAL; goto out; } - if (!options->keyhandle) { - ret = -EINVAL; + if (tpm2) + ret = tpm2_seal_trusted(chip, p, options); + else + ret = key_seal(p, options); + if (ret < 0) { + pr_info("key_seal failed (%d)\n", ret); goto out; } - dump_payload(payload); - dump_options(options); - - switch (key_cmd) { - case Opt_load: - if (tpm2) - ret = tpm2_unseal_trusted(chip, payload, options); - else - ret = key_unseal(payload, options); - dump_payload(payload); - dump_options(options); - if (ret < 0) - pr_info("trusted_key: key_unseal failed (%d)\n", ret); - break; - case Opt_new: - key_len = payload->key_len; - ret = tpm_get_random(chip, payload->key, key_len); - if (ret < 0) - goto out; - - if (ret != key_len) { - pr_info("trusted_key: key_create failed (%d)\n", ret); - ret = -EIO; + if (options->pcrlock) { + ret = pcrlock(options->pcrlock); + if (ret < 0) { + pr_info("pcrlock failed (%d)\n", ret); goto out; } - if (tpm2) - ret = tpm2_seal_trusted(chip, payload, options); - else - ret = key_seal(payload, options); - if (ret < 0) - pr_info("trusted_key: key_seal failed (%d)\n", ret); - break; - default: - ret = -EINVAL; - goto out; } - if (!ret && options->pcrlock) - ret = pcrlock(options->pcrlock); out: - kfree_sensitive(datablob); kfree_sensitive(options); - if (!ret) - rcu_assign_keypointer(key, payload); - else - kfree_sensitive(payload); return ret; } -static void trusted_rcu_free(struct rcu_head *rcu) +static int trusted_tpm_unseal(struct trusted_key_payload *p, char *datablob) { - struct trusted_key_payload *p; - - p = container_of(rcu, struct trusted_key_payload, rcu); - kfree_sensitive(p); -} - -/* - * trusted_update - reseal an existing key with new PCR values - */ -static int trusted_update(struct key *key, struct key_preparsed_payload *prep) -{ - struct trusted_key_payload *p; - struct trusted_key_payload *new_p; - struct trusted_key_options *new_o; - size_t datalen = prep->datalen; - char *datablob; + struct trusted_key_options *options = NULL; int ret = 0; + int tpm2; - if (key_is_negative(key)) - return -ENOKEY; - p = key->payload.data[0]; - if (!p->migratable) - return -EPERM; - if (datalen <= 0 || datalen > 32767 || !prep->data) - return -EINVAL; + tpm2 = tpm_is_tpm2(chip); + if (tpm2 < 0) + return tpm2; - datablob = kmalloc(datalen + 1, GFP_KERNEL); - if (!datablob) + options = trusted_options_alloc(); + if (!options) return -ENOMEM; - new_o = trusted_options_alloc(); - if (!new_o) { - ret = -ENOMEM; - goto out; - } - new_p = trusted_payload_alloc(key); - if (!new_p) { - ret = -ENOMEM; - goto out; - } - memcpy(datablob, prep->data, datalen); - datablob[datalen] = '\0'; - ret = datablob_parse(datablob, new_p, new_o); - if (ret != Opt_update) { - ret = -EINVAL; - kfree_sensitive(new_p); + ret = getoptions(datablob, p, options); + if (ret < 0) goto out; - } + dump_options(options); - if (!new_o->keyhandle) { + if (!options->keyhandle && !tpm2) { ret = -EINVAL; - kfree_sensitive(new_p); goto out; } - /* copy old key values, and reseal with new pcrs */ - new_p->migratable = p->migratable; - new_p->key_len = p->key_len; - memcpy(new_p->key, p->key, p->key_len); - dump_payload(p); - dump_payload(new_p); + if (tpm2) + ret = tpm2_unseal_trusted(chip, p, options); + else + ret = key_unseal(p, options); + if (ret < 0) + pr_info("key_unseal failed (%d)\n", ret); - ret = key_seal(new_p, new_o); - if (ret < 0) { - pr_info("trusted_key: key_seal failed (%d)\n", ret); - kfree_sensitive(new_p); - goto out; - } - if (new_o->pcrlock) { - ret = pcrlock(new_o->pcrlock); + if (options->pcrlock) { + ret = pcrlock(options->pcrlock); if (ret < 0) { - pr_info("trusted_key: pcrlock failed (%d)\n", ret); - kfree_sensitive(new_p); + pr_info("pcrlock failed (%d)\n", ret); goto out; } } - rcu_assign_keypointer(key, new_p); - call_rcu(&p->rcu, trusted_rcu_free); out: - kfree_sensitive(datablob); - kfree_sensitive(new_o); + kfree_sensitive(options); return ret; } -/* - * trusted_read - copy the sealed blob data to userspace in hex. - * On success, return to userspace the trusted key datablob size. - */ -static long trusted_read(const struct key *key, char *buffer, - size_t buflen) -{ - const struct trusted_key_payload *p; - char *bufp; - int i; - - p = dereference_key_locked(key); - if (!p) - return -EINVAL; - - if (buffer && buflen >= 2 * p->blob_len) { - bufp = buffer; - for (i = 0; i < p->blob_len; i++) - bufp = hex_byte_pack(bufp, p->blob[i]); - } - return 2 * p->blob_len; -} - -/* - * trusted_destroy - clear and free the key's payload - */ -static void trusted_destroy(struct key *key) +static int trusted_tpm_get_random(unsigned char *key, size_t key_len) { - kfree_sensitive(key->payload.data[0]); + return tpm_get_random(chip, key, key_len); } -struct key_type key_type_trusted = { - .name = "trusted", - .instantiate = trusted_instantiate, - .update = trusted_update, - .destroy = trusted_destroy, - .describe = user_describe, - .read = trusted_read, -}; - -EXPORT_SYMBOL_GPL(key_type_trusted); - static void trusted_shash_release(void) { if (hashalg) @@ -1196,14 +990,14 @@ static int __init trusted_shash_alloc(void) hmacalg = crypto_alloc_shash(hmac_alg, 0, 0); if (IS_ERR(hmacalg)) { - pr_info("trusted_key: could not allocate crypto %s\n", + pr_info("could not allocate crypto %s\n", hmac_alg); return PTR_ERR(hmacalg); } hashalg = crypto_alloc_shash(hash_alg, 0, 0); if (IS_ERR(hashalg)) { - pr_info("trusted_key: could not allocate crypto %s\n", + pr_info("could not allocate crypto %s\n", hash_alg); ret = PTR_ERR(hashalg); goto hashalg_fail; @@ -1231,16 +1025,13 @@ static int __init init_digests(void) return 0; } -static int __init init_trusted(void) +static int __init trusted_tpm_init(void) { int ret; - /* encrypted_keys.ko depends on successful load of this module even if - * TPM is not used. - */ chip = tpm_default_chip(); if (!chip) - return 0; + return -ENODEV; ret = init_digests(); if (ret < 0) @@ -1261,7 +1052,7 @@ err_put: return ret; } -static void __exit cleanup_trusted(void) +static void trusted_tpm_exit(void) { if (chip) { put_device(&chip->dev); @@ -1271,7 +1062,11 @@ static void __exit cleanup_trusted(void) } } -late_initcall(init_trusted); -module_exit(cleanup_trusted); - -MODULE_LICENSE("GPL"); +struct trusted_key_ops trusted_key_tpm_ops = { + .migratable = 1, /* migratable by default */ + .init = trusted_tpm_init, + .seal = trusted_tpm_seal, + .unseal = trusted_tpm_unseal, + .get_random = trusted_tpm_get_random, + .exit = trusted_tpm_exit, +}; diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index e2a0ed5d02f0..617fabd4d913 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -4,6 +4,8 @@ * Copyright (C) 2014 Intel Corporation */ +#include <linux/asn1_encoder.h> +#include <linux/oid_registry.h> #include <linux/string.h> #include <linux/err.h> #include <linux/tpm.h> @@ -12,6 +14,10 @@ #include <keys/trusted-type.h> #include <keys/trusted_tpm.h> +#include <asm/unaligned.h> + +#include "tpm2key.asn1.h" + static struct tpm2_hash tpm2_hash_map[] = { {HASH_ALGO_SHA1, TPM_ALG_SHA1}, {HASH_ALGO_SHA256, TPM_ALG_SHA256}, @@ -20,6 +26,165 @@ static struct tpm2_hash tpm2_hash_map[] = { {HASH_ALGO_SM3_256, TPM_ALG_SM3_256}, }; +static u32 tpm2key_oid[] = { 2, 23, 133, 10, 1, 5 }; + +static int tpm2_key_encode(struct trusted_key_payload *payload, + struct trusted_key_options *options, + u8 *src, u32 len) +{ + const int SCRATCH_SIZE = PAGE_SIZE; + u8 *scratch = kmalloc(SCRATCH_SIZE, GFP_KERNEL); + u8 *work = scratch, *work1; + u8 *end_work = scratch + SCRATCH_SIZE; + u8 *priv, *pub; + u16 priv_len, pub_len; + + priv_len = get_unaligned_be16(src) + 2; + priv = src; + + src += priv_len; + + pub_len = get_unaligned_be16(src) + 2; + pub = src; + + if (!scratch) + return -ENOMEM; + + work = asn1_encode_oid(work, end_work, tpm2key_oid, + asn1_oid_len(tpm2key_oid)); + + if (options->blobauth_len == 0) { + unsigned char bool[3], *w = bool; + /* tag 0 is emptyAuth */ + w = asn1_encode_boolean(w, w + sizeof(bool), true); + if (WARN(IS_ERR(w), "BUG: Boolean failed to encode")) + return PTR_ERR(w); + work = asn1_encode_tag(work, end_work, 0, bool, w - bool); + } + + /* + * Assume both octet strings will encode to a 2 byte definite length + * + * Note: For a well behaved TPM, this warning should never + * trigger, so if it does there's something nefarious going on + */ + if (WARN(work - scratch + pub_len + priv_len + 14 > SCRATCH_SIZE, + "BUG: scratch buffer is too small")) + return -EINVAL; + + work = asn1_encode_integer(work, end_work, options->keyhandle); + work = asn1_encode_octet_string(work, end_work, pub, pub_len); + work = asn1_encode_octet_string(work, end_work, priv, priv_len); + + work1 = payload->blob; + work1 = asn1_encode_sequence(work1, work1 + sizeof(payload->blob), + scratch, work - scratch); + if (WARN(IS_ERR(work1), "BUG: ASN.1 encoder failed")) + return PTR_ERR(work1); + + return work1 - payload->blob; +} + +struct tpm2_key_context { + u32 parent; + const u8 *pub; + u32 pub_len; + const u8 *priv; + u32 priv_len; +}; + +static int tpm2_key_decode(struct trusted_key_payload *payload, + struct trusted_key_options *options, + u8 **buf) +{ + int ret; + struct tpm2_key_context ctx; + u8 *blob; + + memset(&ctx, 0, sizeof(ctx)); + + ret = asn1_ber_decoder(&tpm2key_decoder, &ctx, payload->blob, + payload->blob_len); + if (ret < 0) + return ret; + + if (ctx.priv_len + ctx.pub_len > MAX_BLOB_SIZE) + return -EINVAL; + + blob = kmalloc(ctx.priv_len + ctx.pub_len + 4, GFP_KERNEL); + if (!blob) + return -ENOMEM; + + *buf = blob; + options->keyhandle = ctx.parent; + + memcpy(blob, ctx.priv, ctx.priv_len); + blob += ctx.priv_len; + + memcpy(blob, ctx.pub, ctx.pub_len); + + return 0; +} + +int tpm2_key_parent(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + struct tpm2_key_context *ctx = context; + const u8 *v = value; + int i; + + ctx->parent = 0; + for (i = 0; i < vlen; i++) { + ctx->parent <<= 8; + ctx->parent |= v[i]; + } + + return 0; +} + +int tpm2_key_type(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + enum OID oid = look_up_OID(value, vlen); + + if (oid != OID_TPMSealedData) { + char buffer[50]; + + sprint_oid(value, vlen, buffer, sizeof(buffer)); + pr_debug("OID is \"%s\" which is not TPMSealedData\n", + buffer); + return -EINVAL; + } + + return 0; +} + +int tpm2_key_pub(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + struct tpm2_key_context *ctx = context; + + ctx->pub = value; + ctx->pub_len = vlen; + + return 0; +} + +int tpm2_key_priv(void *context, size_t hdrlen, + unsigned char tag, + const void *value, size_t vlen) +{ + struct tpm2_key_context *ctx = context; + + ctx->priv = value; + ctx->priv_len = vlen; + + return 0; +} + /** * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. * @@ -63,9 +228,10 @@ int tpm2_seal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload, struct trusted_key_options *options) { - unsigned int blob_len; + int blob_len = 0; struct tpm_buf buf; u32 hash; + u32 flags; int i; int rc; @@ -79,7 +245,10 @@ int tpm2_seal_trusted(struct tpm_chip *chip, if (i == ARRAY_SIZE(tpm2_hash_map)) return -EINVAL; - rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_CREATE); + if (!options->keyhandle) + return -EINVAL; + + rc = tpm_try_get_ops(chip); if (rc) return rc; @@ -97,29 +266,32 @@ int tpm2_seal_trusted(struct tpm_chip *chip, TPM_DIGEST_SIZE); /* sensitive */ - tpm_buf_append_u16(&buf, 4 + TPM_DIGEST_SIZE + payload->key_len + 1); + tpm_buf_append_u16(&buf, 4 + options->blobauth_len + payload->key_len); + + tpm_buf_append_u16(&buf, options->blobauth_len); + if (options->blobauth_len) + tpm_buf_append(&buf, options->blobauth, options->blobauth_len); - tpm_buf_append_u16(&buf, TPM_DIGEST_SIZE); - tpm_buf_append(&buf, options->blobauth, TPM_DIGEST_SIZE); - tpm_buf_append_u16(&buf, payload->key_len + 1); + tpm_buf_append_u16(&buf, payload->key_len); tpm_buf_append(&buf, payload->key, payload->key_len); - tpm_buf_append_u8(&buf, payload->migratable); /* public */ tpm_buf_append_u16(&buf, 14 + options->policydigest_len); tpm_buf_append_u16(&buf, TPM_ALG_KEYEDHASH); tpm_buf_append_u16(&buf, hash); + /* key properties */ + flags = 0; + flags |= options->policydigest_len ? 0 : TPM2_OA_USER_WITH_AUTH; + flags |= payload->migratable ? (TPM2_OA_FIXED_TPM | + TPM2_OA_FIXED_PARENT) : 0; + tpm_buf_append_u32(&buf, flags); + /* policy */ - if (options->policydigest_len) { - tpm_buf_append_u32(&buf, 0); - tpm_buf_append_u16(&buf, options->policydigest_len); + tpm_buf_append_u16(&buf, options->policydigest_len); + if (options->policydigest_len) tpm_buf_append(&buf, options->policydigest, options->policydigest_len); - } else { - tpm_buf_append_u32(&buf, TPM2_OA_USER_WITH_AUTH); - tpm_buf_append_u16(&buf, 0); - } /* public parameters */ tpm_buf_append_u16(&buf, TPM_ALG_NULL); @@ -150,8 +322,9 @@ int tpm2_seal_trusted(struct tpm_chip *chip, goto out; } - memcpy(payload->blob, &buf.data[TPM_HEADER_SIZE + 4], blob_len); - payload->blob_len = blob_len; + blob_len = tpm2_key_encode(payload, options, + &buf.data[TPM_HEADER_SIZE + 4], + blob_len); out: tpm_buf_destroy(&buf); @@ -162,6 +335,10 @@ out: else rc = -EPERM; } + if (blob_len < 0) + return blob_len; + + payload->blob_len = blob_len; tpm_put_ops(chip); return rc; @@ -189,13 +366,45 @@ static int tpm2_load_cmd(struct tpm_chip *chip, unsigned int private_len; unsigned int public_len; unsigned int blob_len; + u8 *blob, *pub; int rc; + u32 attrs; + + rc = tpm2_key_decode(payload, options, &blob); + if (rc) { + /* old form */ + blob = payload->blob; + payload->old_format = 1; + } + + /* new format carries keyhandle but old format doesn't */ + if (!options->keyhandle) + return -EINVAL; - private_len = be16_to_cpup((__be16 *) &payload->blob[0]); - if (private_len > (payload->blob_len - 2)) + /* must be big enough for at least the two be16 size counts */ + if (payload->blob_len < 4) + return -EINVAL; + + private_len = get_unaligned_be16(blob); + + /* must be big enough for following public_len */ + if (private_len + 2 + 2 > (payload->blob_len)) + return -E2BIG; + + public_len = get_unaligned_be16(blob + 2 + private_len); + if (private_len + 2 + public_len + 2 > payload->blob_len) return -E2BIG; - public_len = be16_to_cpup((__be16 *) &payload->blob[2 + private_len]); + pub = blob + 2 + private_len + 2; + /* key attributes are always at offset 4 */ + attrs = get_unaligned_be32(pub + 4); + + if ((attrs & (TPM2_OA_FIXED_TPM | TPM2_OA_FIXED_PARENT)) == + (TPM2_OA_FIXED_TPM | TPM2_OA_FIXED_PARENT)) + payload->migratable = 0; + else + payload->migratable = 1; + blob_len = private_len + public_len + 4; if (blob_len > payload->blob_len) return -E2BIG; @@ -211,7 +420,7 @@ static int tpm2_load_cmd(struct tpm_chip *chip, options->keyauth /* hmac */, TPM_DIGEST_SIZE); - tpm_buf_append(&buf, payload->blob, blob_len); + tpm_buf_append(&buf, blob, blob_len); if (buf.flags & TPM_BUF_OVERFLOW) { rc = -E2BIG; @@ -224,6 +433,8 @@ static int tpm2_load_cmd(struct tpm_chip *chip, (__be32 *) &buf.data[TPM_HEADER_SIZE]); out: + if (blob != payload->blob) + kfree(blob); tpm_buf_destroy(&buf); if (rc > 0) @@ -265,7 +476,7 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, NULL /* nonce */, 0, TPM2_SA_CONTINUE_SESSION, options->blobauth /* hmac */, - TPM_DIGEST_SIZE); + options->blobauth_len); rc = tpm_transmit_cmd(chip, &buf, 6, "unsealing"); if (rc > 0) @@ -274,7 +485,7 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, if (!rc) { data_len = be16_to_cpup( (__be16 *) &buf.data[TPM_HEADER_SIZE + 4]); - if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE + 1) { + if (data_len < MIN_KEY_SIZE || data_len > MAX_KEY_SIZE) { rc = -EFAULT; goto out; } @@ -285,9 +496,19 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip, } data = &buf.data[TPM_HEADER_SIZE + 6]; - memcpy(payload->key, data, data_len - 1); - payload->key_len = data_len - 1; - payload->migratable = data[data_len - 1]; + if (payload->old_format) { + /* migratable flag is at the end of the key */ + memcpy(payload->key, data, data_len - 1); + payload->key_len = data_len - 1; + payload->migratable = data[data_len - 1]; + } else { + /* + * migratable flag already collected from key + * attributes + */ + memcpy(payload->key, data, data_len); + payload->key_len = data_len; + } } out: diff --git a/security/selinux/include/security.h b/security/selinux/include/security.h index 6fe25300b89d..7650de048570 100644 --- a/security/selinux/include/security.h +++ b/security/selinux/include/security.h @@ -219,14 +219,21 @@ static inline bool selinux_policycap_genfs_seclabel_symlinks(void) return READ_ONCE(state->policycap[POLICYDB_CAPABILITY_GENFS_SECLABEL_SYMLINKS]); } +struct selinux_policy_convert_data; + +struct selinux_load_state { + struct selinux_policy *policy; + struct selinux_policy_convert_data *convert_data; +}; + int security_mls_enabled(struct selinux_state *state); int security_load_policy(struct selinux_state *state, - void *data, size_t len, - struct selinux_policy **newpolicyp); + void *data, size_t len, + struct selinux_load_state *load_state); void selinux_policy_commit(struct selinux_state *state, - struct selinux_policy *newpolicy); + struct selinux_load_state *load_state); void selinux_policy_cancel(struct selinux_state *state, - struct selinux_policy *policy); + struct selinux_load_state *load_state); int security_read_policy(struct selinux_state *state, void **data, size_t *len); int security_read_state_kernel(struct selinux_state *state, diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 01a7d50ed39b..fff6babeeae6 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -563,17 +563,13 @@ static int sel_make_policy_nodes(struct selinux_fs_info *fsi, ret = sel_make_bools(newpolicy, tmp_bool_dir, &tmp_bool_num, &tmp_bool_names, &tmp_bool_values); - if (ret) { - pr_err("SELinux: failed to load policy booleans\n"); + if (ret) goto out; - } ret = sel_make_classes(newpolicy, tmp_class_dir, &fsi->last_class_ino); - if (ret) { - pr_err("SELinux: failed to load policy classes\n"); + if (ret) goto out; - } /* booleans */ old_dentry = fsi->bool_dir; @@ -616,7 +612,7 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, { struct selinux_fs_info *fsi = file_inode(file)->i_sb->s_fs_info; - struct selinux_policy *newpolicy; + struct selinux_load_state load_state; ssize_t length; void *data = NULL; @@ -642,23 +638,23 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf, if (copy_from_user(data, buf, count) != 0) goto out; - length = security_load_policy(fsi->state, data, count, &newpolicy); + length = security_load_policy(fsi->state, data, count, &load_state); if (length) { pr_warn_ratelimited("SELinux: failed to load policy\n"); goto out; } - length = sel_make_policy_nodes(fsi, newpolicy); + length = sel_make_policy_nodes(fsi, load_state.policy); if (length) { - selinux_policy_cancel(fsi->state, newpolicy); - goto out1; + pr_warn_ratelimited("SELinux: failed to initialize selinuxfs\n"); + selinux_policy_cancel(fsi->state, &load_state); + goto out; } - selinux_policy_commit(fsi->state, newpolicy); + selinux_policy_commit(fsi->state, &load_state); length = count; -out1: audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_POLICY_LOAD, "auid=%u ses=%u lsm=selinux res=1", from_kuid(&init_user_ns, audit_get_loginuid(current)), diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c index 6dcb6aa4db7f..75df32906055 100644 --- a/security/selinux/ss/avtab.c +++ b/security/selinux/ss/avtab.c @@ -109,7 +109,7 @@ static int avtab_insert(struct avtab *h, struct avtab_key *key, struct avtab_dat struct avtab_node *prev, *cur, *newnode; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); - if (!h) + if (!h || !h->nslot) return -EINVAL; hvalue = avtab_hash(key, h->mask); @@ -154,7 +154,7 @@ avtab_insert_nonunique(struct avtab *h, struct avtab_key *key, struct avtab_datu struct avtab_node *prev, *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); - if (!h) + if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; @@ -184,7 +184,7 @@ struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *key) struct avtab_node *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); - if (!h) + if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); @@ -220,7 +220,7 @@ avtab_search_node(struct avtab *h, struct avtab_key *key) struct avtab_node *cur; u16 specified = key->specified & ~(AVTAB_ENABLED|AVTAB_ENABLED_OLD); - if (!h) + if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); @@ -295,6 +295,7 @@ void avtab_destroy(struct avtab *h) } kvfree(h->htable); h->htable = NULL; + h->nel = 0; h->nslot = 0; h->mask = 0; } @@ -303,88 +304,52 @@ void avtab_init(struct avtab *h) { h->htable = NULL; h->nel = 0; + h->nslot = 0; + h->mask = 0; } -int avtab_alloc(struct avtab *h, u32 nrules) +static int avtab_alloc_common(struct avtab *h, u32 nslot) { - u32 mask = 0; - u32 shift = 0; - u32 work = nrules; - u32 nslot = 0; - - if (nrules == 0) - goto avtab_alloc_out; - - while (work) { - work = work >> 1; - shift++; - } - if (shift > 2) - shift = shift - 2; - nslot = 1 << shift; - if (nslot > MAX_AVTAB_HASH_BUCKETS) - nslot = MAX_AVTAB_HASH_BUCKETS; - mask = nslot - 1; + if (!nslot) + return 0; h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL); if (!h->htable) return -ENOMEM; - avtab_alloc_out: - h->nel = 0; h->nslot = nslot; - h->mask = mask; - pr_debug("SELinux: %d avtab hash slots, %d rules.\n", - h->nslot, nrules); + h->mask = nslot - 1; return 0; } -int avtab_duplicate(struct avtab *new, struct avtab *orig) +int avtab_alloc(struct avtab *h, u32 nrules) { - int i; - struct avtab_node *node, *tmp, *tail; - - memset(new, 0, sizeof(*new)); + int rc; + u32 nslot = 0; - new->htable = kvcalloc(orig->nslot, sizeof(void *), GFP_KERNEL); - if (!new->htable) - return -ENOMEM; - new->nslot = orig->nslot; - new->mask = orig->mask; - - for (i = 0; i < orig->nslot; i++) { - tail = NULL; - for (node = orig->htable[i]; node; node = node->next) { - tmp = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL); - if (!tmp) - goto error; - tmp->key = node->key; - if (tmp->key.specified & AVTAB_XPERMS) { - tmp->datum.u.xperms = - kmem_cache_zalloc(avtab_xperms_cachep, - GFP_KERNEL); - if (!tmp->datum.u.xperms) { - kmem_cache_free(avtab_node_cachep, tmp); - goto error; - } - tmp->datum.u.xperms = node->datum.u.xperms; - } else - tmp->datum.u.data = node->datum.u.data; - - if (tail) - tail->next = tmp; - else - new->htable[i] = tmp; - - tail = tmp; - new->nel++; + if (nrules != 0) { + u32 shift = 1; + u32 work = nrules >> 3; + while (work) { + work >>= 1; + shift++; } + nslot = 1 << shift; + if (nslot > MAX_AVTAB_HASH_BUCKETS) + nslot = MAX_AVTAB_HASH_BUCKETS; + + rc = avtab_alloc_common(h, nslot); + if (rc) + return rc; } + pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules); return 0; -error: - avtab_destroy(new); - return -ENOMEM; +} + +int avtab_alloc_dup(struct avtab *new, const struct avtab *orig) +{ + return avtab_alloc_common(new, orig->nslot); } void avtab_hash_eval(struct avtab *h, char *tag) diff --git a/security/selinux/ss/avtab.h b/security/selinux/ss/avtab.h index 4c4445ca9118..f2eeb36265d1 100644 --- a/security/selinux/ss/avtab.h +++ b/security/selinux/ss/avtab.h @@ -89,7 +89,7 @@ struct avtab { void avtab_init(struct avtab *h); int avtab_alloc(struct avtab *, u32); -int avtab_duplicate(struct avtab *new, struct avtab *orig); +int avtab_alloc_dup(struct avtab *new, const struct avtab *orig); struct avtab_datum *avtab_search(struct avtab *h, struct avtab_key *k); void avtab_destroy(struct avtab *h); void avtab_hash_eval(struct avtab *h, char *tag); diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c index 0b32f3ab025e..1ef74c085f2b 100644 --- a/security/selinux/ss/conditional.c +++ b/security/selinux/ss/conditional.c @@ -605,7 +605,6 @@ static int cond_dup_av_list(struct cond_av_list *new, struct cond_av_list *orig, struct avtab *avtab) { - struct avtab_node *avnode; u32 i; memset(new, 0, sizeof(*new)); @@ -615,10 +614,11 @@ static int cond_dup_av_list(struct cond_av_list *new, return -ENOMEM; for (i = 0; i < orig->len; i++) { - avnode = avtab_search_node(avtab, &orig->nodes[i]->key); - if (WARN_ON(!avnode)) - return -EINVAL; - new->nodes[i] = avnode; + new->nodes[i] = avtab_insert_nonunique(avtab, + &orig->nodes[i]->key, + &orig->nodes[i]->datum); + if (!new->nodes[i]) + return -ENOMEM; new->len++; } @@ -630,7 +630,7 @@ static int duplicate_policydb_cond_list(struct policydb *newp, { int rc, i, j; - rc = avtab_duplicate(&newp->te_cond_avtab, &origp->te_cond_avtab); + rc = avtab_alloc_dup(&newp->te_cond_avtab, &origp->te_cond_avtab); if (rc) return rc; diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index 3438d0130378..301633145040 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -67,6 +67,17 @@ #include "policycap_names.h" #include "ima.h" +struct convert_context_args { + struct selinux_state *state; + struct policydb *oldp; + struct policydb *newp; +}; + +struct selinux_policy_convert_data { + struct convert_context_args args; + struct sidtab_convert_params sidtab_params; +}; + /* Forward declaration. */ static int context_struct_to_string(struct policydb *policydb, struct context *context, @@ -1541,6 +1552,7 @@ static int security_context_to_sid_core(struct selinux_state *state, if (!str) goto out; } +retry: rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; @@ -1554,6 +1566,15 @@ static int security_context_to_sid_core(struct selinux_state *state, } else if (rc) goto out_unlock; rc = sidtab_context_to_sid(sidtab, &context, sid); + if (rc == -ESTALE) { + rcu_read_unlock(); + if (context.str) { + str = context.str; + context.str = NULL; + } + context_destroy(&context); + goto retry; + } context_destroy(&context); out_unlock: rcu_read_unlock(); @@ -1703,7 +1724,7 @@ static int security_compute_sid(struct selinux_state *state, struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; - struct class_datum *cladatum = NULL; + struct class_datum *cladatum; struct context *scontext, *tcontext, newcontext; struct sidtab_entry *sentry, *tentry; struct avtab_key avkey; @@ -1725,6 +1746,8 @@ static int security_compute_sid(struct selinux_state *state, goto out; } +retry: + cladatum = NULL; context_init(&newcontext); rcu_read_lock(); @@ -1869,6 +1892,11 @@ static int security_compute_sid(struct selinux_state *state, } /* Obtain the sid for the context. */ rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid); + if (rc == -ESTALE) { + rcu_read_unlock(); + context_destroy(&newcontext); + goto retry; + } out_unlock: rcu_read_unlock(); context_destroy(&newcontext); @@ -1974,12 +2002,6 @@ static inline int convert_context_handle_invalid_context( return 0; } -struct convert_context_args { - struct selinux_state *state; - struct policydb *oldp; - struct policydb *newp; -}; - /* * Convert the values in the security context * structure `oldc' from the values specified @@ -2159,7 +2181,7 @@ static void selinux_policy_cond_free(struct selinux_policy *policy) } void selinux_policy_cancel(struct selinux_state *state, - struct selinux_policy *policy) + struct selinux_load_state *load_state) { struct selinux_policy *oldpolicy; @@ -2167,7 +2189,8 @@ void selinux_policy_cancel(struct selinux_state *state, lockdep_is_held(&state->policy_mutex)); sidtab_cancel_convert(oldpolicy->sidtab); - selinux_policy_free(policy); + selinux_policy_free(load_state->policy); + kfree(load_state->convert_data); } static void selinux_notify_policy_change(struct selinux_state *state, @@ -2183,9 +2206,10 @@ static void selinux_notify_policy_change(struct selinux_state *state, } void selinux_policy_commit(struct selinux_state *state, - struct selinux_policy *newpolicy) + struct selinux_load_state *load_state) { - struct selinux_policy *oldpolicy; + struct selinux_policy *oldpolicy, *newpolicy = load_state->policy; + unsigned long flags; u32 seqno; oldpolicy = rcu_dereference_protected(state->policy, @@ -2207,7 +2231,13 @@ void selinux_policy_commit(struct selinux_state *state, seqno = newpolicy->latest_granting; /* Install the new policy. */ - rcu_assign_pointer(state->policy, newpolicy); + if (oldpolicy) { + sidtab_freeze_begin(oldpolicy->sidtab, &flags); + rcu_assign_pointer(state->policy, newpolicy); + sidtab_freeze_end(oldpolicy->sidtab, &flags); + } else { + rcu_assign_pointer(state->policy, newpolicy); + } /* Load the policycaps from the new policy */ security_load_policycaps(state, newpolicy); @@ -2225,6 +2255,7 @@ void selinux_policy_commit(struct selinux_state *state, /* Free the old policy */ synchronize_rcu(); selinux_policy_free(oldpolicy); + kfree(load_state->convert_data); /* Notify others of the policy change */ selinux_notify_policy_change(state, seqno); @@ -2241,11 +2272,10 @@ void selinux_policy_commit(struct selinux_state *state, * loading the new policy. */ int security_load_policy(struct selinux_state *state, void *data, size_t len, - struct selinux_policy **newpolicyp) + struct selinux_load_state *load_state) { struct selinux_policy *newpolicy, *oldpolicy; - struct sidtab_convert_params convert_params; - struct convert_context_args args; + struct selinux_policy_convert_data *convert_data; int rc = 0; struct policy_file file = { data, len }, *fp = &file; @@ -2275,10 +2305,10 @@ int security_load_policy(struct selinux_state *state, void *data, size_t len, goto err_mapping; } - if (!selinux_initialized(state)) { /* First policy load, so no need to preserve state from old policy */ - *newpolicyp = newpolicy; + load_state->policy = newpolicy; + load_state->convert_data = NULL; return 0; } @@ -2292,29 +2322,38 @@ int security_load_policy(struct selinux_state *state, void *data, size_t len, goto err_free_isids; } + convert_data = kmalloc(sizeof(*convert_data), GFP_KERNEL); + if (!convert_data) { + rc = -ENOMEM; + goto err_free_isids; + } + /* * Convert the internal representations of contexts * in the new SID table. */ - args.state = state; - args.oldp = &oldpolicy->policydb; - args.newp = &newpolicy->policydb; + convert_data->args.state = state; + convert_data->args.oldp = &oldpolicy->policydb; + convert_data->args.newp = &newpolicy->policydb; - convert_params.func = convert_context; - convert_params.args = &args; - convert_params.target = newpolicy->sidtab; + convert_data->sidtab_params.func = convert_context; + convert_data->sidtab_params.args = &convert_data->args; + convert_data->sidtab_params.target = newpolicy->sidtab; - rc = sidtab_convert(oldpolicy->sidtab, &convert_params); + rc = sidtab_convert(oldpolicy->sidtab, &convert_data->sidtab_params); if (rc) { pr_err("SELinux: unable to convert the internal" " representation of contexts in the new SID" " table\n"); - goto err_free_isids; + goto err_free_convert_data; } - *newpolicyp = newpolicy; + load_state->policy = newpolicy; + load_state->convert_data = convert_data; return 0; +err_free_convert_data: + kfree(convert_data); err_free_isids: sidtab_destroy(newpolicy->sidtab); err_mapping: @@ -2342,13 +2381,15 @@ int security_port_sid(struct selinux_state *state, struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; - int rc = 0; + int rc; if (!selinux_initialized(state)) { *out_sid = SECINITSID_PORT; return 0; } +retry: + rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; @@ -2367,6 +2408,10 @@ int security_port_sid(struct selinux_state *state, if (!c->sid[0]) { rc = sidtab_context_to_sid(sidtab, &c->context[0], &c->sid[0]); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) goto out; } @@ -2393,13 +2438,15 @@ int security_ib_pkey_sid(struct selinux_state *state, struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; - int rc = 0; + int rc; if (!selinux_initialized(state)) { *out_sid = SECINITSID_UNLABELED; return 0; } +retry: + rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; @@ -2420,6 +2467,10 @@ int security_ib_pkey_sid(struct selinux_state *state, rc = sidtab_context_to_sid(sidtab, &c->context[0], &c->sid[0]); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) goto out; } @@ -2445,13 +2496,15 @@ int security_ib_endport_sid(struct selinux_state *state, struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; - int rc = 0; + int rc; if (!selinux_initialized(state)) { *out_sid = SECINITSID_UNLABELED; return 0; } +retry: + rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; @@ -2472,6 +2525,10 @@ int security_ib_endport_sid(struct selinux_state *state, if (!c->sid[0]) { rc = sidtab_context_to_sid(sidtab, &c->context[0], &c->sid[0]); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) goto out; } @@ -2495,7 +2552,7 @@ int security_netif_sid(struct selinux_state *state, struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; - int rc = 0; + int rc; struct ocontext *c; if (!selinux_initialized(state)) { @@ -2503,6 +2560,8 @@ int security_netif_sid(struct selinux_state *state, return 0; } +retry: + rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; @@ -2519,10 +2578,18 @@ int security_netif_sid(struct selinux_state *state, if (!c->sid[0] || !c->sid[1]) { rc = sidtab_context_to_sid(sidtab, &c->context[0], &c->sid[0]); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) goto out; rc = sidtab_context_to_sid(sidtab, &c->context[1], &c->sid[1]); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) goto out; } @@ -2572,6 +2639,7 @@ int security_node_sid(struct selinux_state *state, return 0; } +retry: rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; @@ -2620,6 +2688,10 @@ int security_node_sid(struct selinux_state *state, rc = sidtab_context_to_sid(sidtab, &c->context[0], &c->sid[0]); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) goto out; } @@ -2661,18 +2733,24 @@ int security_get_user_sids(struct selinux_state *state, struct sidtab *sidtab; struct context *fromcon, usercon; u32 *mysids = NULL, *mysids2, sid; - u32 mynel = 0, maxnel = SIDS_NEL; + u32 i, j, mynel, maxnel = SIDS_NEL; struct user_datum *user; struct role_datum *role; struct ebitmap_node *rnode, *tnode; - int rc = 0, i, j; + int rc; *sids = NULL; *nel = 0; if (!selinux_initialized(state)) - goto out; + return 0; + + mysids = kcalloc(maxnel, sizeof(*mysids), GFP_KERNEL); + if (!mysids) + return -ENOMEM; +retry: + mynel = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; @@ -2692,11 +2770,6 @@ int security_get_user_sids(struct selinux_state *state, usercon.user = user->value; - rc = -ENOMEM; - mysids = kcalloc(maxnel, sizeof(*mysids), GFP_ATOMIC); - if (!mysids) - goto out_unlock; - ebitmap_for_each_positive_bit(&user->roles, rnode, i) { role = policydb->role_val_to_struct[i]; usercon.role = i + 1; @@ -2708,6 +2781,10 @@ int security_get_user_sids(struct selinux_state *state, continue; rc = sidtab_context_to_sid(sidtab, &usercon, &sid); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) goto out_unlock; if (mynel < maxnel) { @@ -2730,14 +2807,14 @@ out_unlock: rcu_read_unlock(); if (rc || !mynel) { kfree(mysids); - goto out; + return rc; } rc = -ENOMEM; mysids2 = kcalloc(mynel, sizeof(*mysids2), GFP_KERNEL); if (!mysids2) { kfree(mysids); - goto out; + return rc; } for (i = 0, j = 0; i < mynel; i++) { struct av_decision dummy_avd; @@ -2750,12 +2827,10 @@ out_unlock: mysids2[j++] = mysids[i]; cond_resched(); } - rc = 0; kfree(mysids); *sids = mysids2; *nel = j; -out: - return rc; + return 0; } /** @@ -2768,6 +2843,9 @@ out: * Obtain a SID to use for a file in a filesystem that * cannot support xattr or use a fixed labeling behavior like * transition SIDs or task SIDs. + * + * WARNING: This function may return -ESTALE, indicating that the caller + * must retry the operation after re-acquiring the policy pointer! */ static inline int __security_genfs_sid(struct selinux_policy *policy, const char *fstype, @@ -2846,11 +2924,13 @@ int security_genfs_sid(struct selinux_state *state, return 0; } - rcu_read_lock(); - policy = rcu_dereference(state->policy); - retval = __security_genfs_sid(policy, - fstype, path, orig_sclass, sid); - rcu_read_unlock(); + do { + rcu_read_lock(); + policy = rcu_dereference(state->policy); + retval = __security_genfs_sid(policy, fstype, path, + orig_sclass, sid); + rcu_read_unlock(); + } while (retval == -ESTALE); return retval; } @@ -2873,7 +2953,7 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) struct selinux_policy *policy; struct policydb *policydb; struct sidtab *sidtab; - int rc = 0; + int rc; struct ocontext *c; struct superblock_security_struct *sbsec = sb->s_security; const char *fstype = sb->s_type->name; @@ -2884,6 +2964,8 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) return 0; } +retry: + rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; @@ -2901,6 +2983,10 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) if (!c->sid[0]) { rc = sidtab_context_to_sid(sidtab, &c->context[0], &c->sid[0]); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) goto out; } @@ -2908,6 +2994,10 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) } else { rc = __security_genfs_sid(policy, fstype, "/", SECCLASS_DIR, &sbsec->sid); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) { sbsec->behavior = SECURITY_FS_USE_NONE; rc = 0; @@ -3117,12 +3207,13 @@ int security_sid_mls_copy(struct selinux_state *state, u32 len; int rc; - rc = 0; if (!selinux_initialized(state)) { *new_sid = sid; - goto out; + return 0; } +retry: + rc = 0; context_init(&newcon); rcu_read_lock(); @@ -3181,10 +3272,14 @@ int security_sid_mls_copy(struct selinux_state *state, } } rc = sidtab_context_to_sid(sidtab, &newcon, new_sid); + if (rc == -ESTALE) { + rcu_read_unlock(); + context_destroy(&newcon); + goto retry; + } out_unlock: rcu_read_unlock(); context_destroy(&newcon); -out: return rc; } @@ -3777,6 +3872,8 @@ int security_netlbl_secattr_to_sid(struct selinux_state *state, return 0; } +retry: + rc = 0; rcu_read_lock(); policy = rcu_dereference(state->policy); policydb = &policy->policydb; @@ -3803,23 +3900,24 @@ int security_netlbl_secattr_to_sid(struct selinux_state *state, goto out; } rc = -EIDRM; - if (!mls_context_isvalid(policydb, &ctx_new)) - goto out_free; + if (!mls_context_isvalid(policydb, &ctx_new)) { + ebitmap_destroy(&ctx_new.range.level[0].cat); + goto out; + } rc = sidtab_context_to_sid(sidtab, &ctx_new, sid); + ebitmap_destroy(&ctx_new.range.level[0].cat); + if (rc == -ESTALE) { + rcu_read_unlock(); + goto retry; + } if (rc) - goto out_free; + goto out; security_netlbl_cache_add(secattr, *sid); - - ebitmap_destroy(&ctx_new.range.level[0].cat); } else *sid = SECSID_NULL; - rcu_read_unlock(); - return 0; -out_free: - ebitmap_destroy(&ctx_new.range.level[0].cat); out: rcu_read_unlock(); return rc; diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c index 5ee190bd30f5..656d50b09f76 100644 --- a/security/selinux/ss/sidtab.c +++ b/security/selinux/ss/sidtab.c @@ -39,6 +39,7 @@ int sidtab_init(struct sidtab *s) for (i = 0; i < SECINITSID_NUM; i++) s->isids[i].set = 0; + s->frozen = false; s->count = 0; s->convert = NULL; hash_init(s->context_to_sid); @@ -281,6 +282,15 @@ int sidtab_context_to_sid(struct sidtab *s, struct context *context, if (*sid) goto out_unlock; + if (unlikely(s->frozen)) { + /* + * This sidtab is now frozen - tell the caller to abort and + * get the new one. + */ + rc = -ESTALE; + goto out_unlock; + } + count = s->count; convert = s->convert; @@ -474,6 +484,17 @@ void sidtab_cancel_convert(struct sidtab *s) spin_unlock_irqrestore(&s->lock, flags); } +void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock) +{ + spin_lock_irqsave(&s->lock, *flags); + s->frozen = true; + s->convert = NULL; +} +void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock) +{ + spin_unlock_irqrestore(&s->lock, *flags); +} + static void sidtab_destroy_entry(struct sidtab_entry *entry) { context_destroy(&entry->context); diff --git a/security/selinux/ss/sidtab.h b/security/selinux/ss/sidtab.h index 80c744d07ad6..4eff0e49dcb2 100644 --- a/security/selinux/ss/sidtab.h +++ b/security/selinux/ss/sidtab.h @@ -86,6 +86,7 @@ struct sidtab { u32 count; /* access only under spinlock */ struct sidtab_convert_params *convert; + bool frozen; spinlock_t lock; #if CONFIG_SECURITY_SELINUX_SID2STR_CACHE_SIZE > 0 @@ -125,6 +126,9 @@ int sidtab_convert(struct sidtab *s, struct sidtab_convert_params *params); void sidtab_cancel_convert(struct sidtab *s); +void sidtab_freeze_begin(struct sidtab *s, unsigned long *flags) __acquires(&s->lock); +void sidtab_freeze_end(struct sidtab *s, unsigned long *flags) __releases(&s->lock); + int sidtab_context_to_sid(struct sidtab *s, struct context *context, u32 *sid); void sidtab_destroy(struct sidtab *s); diff --git a/security/tomoyo/network.c b/security/tomoyo/network.c index 478f757ff843..8dc61335f65e 100644 --- a/security/tomoyo/network.c +++ b/security/tomoyo/network.c @@ -613,7 +613,7 @@ static int tomoyo_check_unix_address(struct sockaddr *addr, static bool tomoyo_kernel_service(void) { /* Nothing to do if I am a kernel service. */ - return (current->flags & (PF_KTHREAD | PF_IO_WORKER)) == PF_KTHREAD; + return current->flags & PF_KTHREAD; } /** diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c index 52637180af33..80b814b9922a 100644 --- a/sound/drivers/aloop.c +++ b/sound/drivers/aloop.c @@ -1571,6 +1571,14 @@ static int loopback_mixer_new(struct loopback *loopback, int notify) return -ENOMEM; kctl->id.device = dev; kctl->id.subdevice = substr; + + /* Add the control before copying the id so that + * the numid field of the id is set in the copy. + */ + err = snd_ctl_add(card, kctl); + if (err < 0) + return err; + switch (idx) { case ACTIVE_IDX: setup->active_id = kctl->id; @@ -1587,9 +1595,6 @@ static int loopback_mixer_new(struct loopback *loopback, int notify) default: break; } - err = snd_ctl_add(card, kctl); - if (err < 0) - return err; } } } diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index b59b0f323d4e..79ade335c8a0 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -989,8 +989,12 @@ static int azx_prepare(struct device *dev) struct snd_card *card = dev_get_drvdata(dev); struct azx *chip; + if (!azx_is_pm_ready(card)) + return 0; + chip = card->private_data; chip->pm_prepared = 1; + snd_power_change_state(card, SNDRV_CTL_POWER_D3hot); flush_work(&azx_bus(chip)->unsol_work); @@ -1005,7 +1009,11 @@ static void azx_complete(struct device *dev) struct snd_card *card = dev_get_drvdata(dev); struct azx *chip; + if (!azx_is_pm_ready(card)) + return; + chip = card->private_data; + snd_power_change_state(card, SNDRV_CTL_POWER_D0); chip->pm_prepared = 0; } diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index c20dad46a7c9..dfef9c17e140 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -944,6 +944,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8402, "HP ProBook 645 G4", CXT_FIXUP_MUTE_LED_GPIO), SND_PCI_QUIRK(0x103c, 0x8427, "HP ZBook Studio G5", CXT_FIXUP_HP_ZBOOK_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x844f, "HP ZBook Studio G5", CXT_FIXUP_HP_ZBOOK_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8456, "HP Z2 G4 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x8457, "HP Z2 G4 mini", CXT_FIXUP_HP_MIC_NO_PRESENCE), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 316b9b4ccb32..a7544b77d3f7 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3927,6 +3927,15 @@ static void alc271_fixup_dmic(struct hda_codec *codec, snd_hda_sequence_write(codec, verbs); } +/* Fix the speaker amp after resume, etc */ +static void alc269vb_fixup_aspire_e1_coef(struct hda_codec *codec, + const struct hda_fixup *fix, + int action) +{ + if (action == HDA_FIXUP_ACT_INIT) + alc_update_coef_idx(codec, 0x0d, 0x6000, 0x6000); +} + static void alc269_fixup_pcm_44k(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -5256,7 +5265,7 @@ static void alc_determine_headset_type(struct hda_codec *codec) case 0x10ec0274: case 0x10ec0294: alc_process_coef_fw(codec, coef0274); - msleep(80); + msleep(850); val = alc_read_coef_idx(codec, 0x46); is_ctia = (val & 0x00f0) == 0x00f0; break; @@ -5440,6 +5449,7 @@ static void alc_update_headset_jack_cb(struct hda_codec *codec, struct hda_jack_callback *jack) { snd_hda_gen_hp_automute(codec, jack); + alc_update_headset_mode(codec); } static void alc_probe_headset_mode(struct hda_codec *codec) @@ -6300,6 +6310,7 @@ enum { ALC283_FIXUP_HEADSET_MIC, ALC255_FIXUP_MIC_MUTE_LED, ALC282_FIXUP_ASPIRE_V5_PINS, + ALC269VB_FIXUP_ASPIRE_E1_COEF, ALC280_FIXUP_HP_GPIO4, ALC286_FIXUP_HP_GPIO_LED, ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY, @@ -6978,6 +6989,10 @@ static const struct hda_fixup alc269_fixups[] = { { }, }, }, + [ALC269VB_FIXUP_ASPIRE_E1_COEF] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc269vb_fixup_aspire_e1_coef, + }, [ALC280_FIXUP_HP_GPIO4] = { .type = HDA_FIXUP_FUNC, .v.func = alc280_fixup_hp_gpio4, @@ -7900,6 +7915,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x0762, "Acer Aspire E1-472", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x0775, "Acer Aspire E1-572", ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572), SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS), + SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF), SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK), SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC), @@ -8057,6 +8073,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x87c8, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87e5, "HP ProBook 440 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x87f2, "HP ProBook 640 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f4, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP), @@ -8393,6 +8410,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC283_FIXUP_HEADSET_MIC, .name = "alc283-headset"}, {.id = ALC255_FIXUP_MIC_MUTE_LED, .name = "alc255-dell-mute"}, {.id = ALC282_FIXUP_ASPIRE_V5_PINS, .name = "aspire-v5"}, + {.id = ALC269VB_FIXUP_ASPIRE_E1_COEF, .name = "aspire-e1-coef"}, {.id = ALC280_FIXUP_HP_GPIO4, .name = "hp-gpio4"}, {.id = ALC286_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"}, {.id = ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY, .name = "hp-gpio2-hotkey"}, diff --git a/sound/soc/bcm/cygnus-ssp.c b/sound/soc/bcm/cygnus-ssp.c index 6e634b448293..aa16a2375134 100644 --- a/sound/soc/bcm/cygnus-ssp.c +++ b/sound/soc/bcm/cygnus-ssp.c @@ -1348,8 +1348,10 @@ static int cygnus_ssp_probe(struct platform_device *pdev) &cygnus_ssp_dai[active_port_count]); /* negative is err, 0 is active and good, 1 is disabled */ - if (err < 0) + if (err < 0) { + of_node_put(child_node); return err; + } else if (!err) { dev_dbg(dev, "Activating DAI: %s\n", cygnus_ssp_dai[active_port_count].name); diff --git a/sound/soc/codecs/lpass-rx-macro.c b/sound/soc/codecs/lpass-rx-macro.c index 8c04b3b2c907..7878da89d8e0 100644 --- a/sound/soc/codecs/lpass-rx-macro.c +++ b/sound/soc/codecs/lpass-rx-macro.c @@ -3551,7 +3551,7 @@ static int rx_macro_probe(struct platform_device *pdev) /* set MCLK and NPL rates */ clk_set_rate(rx->clks[2].clk, MCLK_FREQ); - clk_set_rate(rx->clks[3].clk, MCLK_FREQ); + clk_set_rate(rx->clks[3].clk, 2 * MCLK_FREQ); ret = clk_bulk_prepare_enable(RX_NUM_CLKS_MAX, rx->clks); if (ret) diff --git a/sound/soc/codecs/lpass-tx-macro.c b/sound/soc/codecs/lpass-tx-macro.c index 36d7a6442cdb..e8c6c738bbaa 100644 --- a/sound/soc/codecs/lpass-tx-macro.c +++ b/sound/soc/codecs/lpass-tx-macro.c @@ -1811,7 +1811,7 @@ static int tx_macro_probe(struct platform_device *pdev) /* set MCLK and NPL rates */ clk_set_rate(tx->clks[2].clk, MCLK_FREQ); - clk_set_rate(tx->clks[3].clk, MCLK_FREQ); + clk_set_rate(tx->clks[3].clk, 2 * MCLK_FREQ); ret = clk_bulk_prepare_enable(TX_NUM_CLKS_MAX, tx->clks); if (ret) diff --git a/sound/soc/codecs/max98373-i2c.c b/sound/soc/codecs/max98373-i2c.c index 85f6865019d4..ddb6436835d7 100644 --- a/sound/soc/codecs/max98373-i2c.c +++ b/sound/soc/codecs/max98373-i2c.c @@ -446,6 +446,7 @@ static bool max98373_volatile_reg(struct device *dev, unsigned int reg) case MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK: case MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK: case MAX98373_R20B6_BDE_CUR_STATE_READBACK: + case MAX98373_R20FF_GLOBAL_SHDN: case MAX98373_R21FF_REV_ID: return true; default: diff --git a/sound/soc/codecs/max98373-sdw.c b/sound/soc/codecs/max98373-sdw.c index d8c47667a9ea..f3a12205cd48 100644 --- a/sound/soc/codecs/max98373-sdw.c +++ b/sound/soc/codecs/max98373-sdw.c @@ -220,6 +220,7 @@ static bool max98373_volatile_reg(struct device *dev, unsigned int reg) case MAX98373_R2054_MEAS_ADC_PVDD_CH_READBACK: case MAX98373_R2055_MEAS_ADC_THERM_CH_READBACK: case MAX98373_R20B6_BDE_CUR_STATE_READBACK: + case MAX98373_R20FF_GLOBAL_SHDN: case MAX98373_R21FF_REV_ID: /* SoundWire Control Port Registers */ case MAX98373_R0040_SCP_INIT_STAT_1 ... MAX98373_R0070_SCP_FRAME_CTLR: diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c index 746c829312b8..1346a98ce8a1 100644 --- a/sound/soc/codecs/max98373.c +++ b/sound/soc/codecs/max98373.c @@ -28,11 +28,13 @@ static int max98373_dac_event(struct snd_soc_dapm_widget *w, regmap_update_bits(max98373->regmap, MAX98373_R20FF_GLOBAL_SHDN, MAX98373_GLOBAL_EN_MASK, 1); + usleep_range(30000, 31000); break; case SND_SOC_DAPM_POST_PMD: regmap_update_bits(max98373->regmap, MAX98373_R20FF_GLOBAL_SHDN, MAX98373_GLOBAL_EN_MASK, 0); + usleep_range(30000, 31000); max98373->tdm_mode = false; break; default: diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c index df351519a3a6..cda9cd935d4f 100644 --- a/sound/soc/codecs/wm8960.c +++ b/sound/soc/codecs/wm8960.c @@ -707,7 +707,13 @@ int wm8960_configure_pll(struct snd_soc_component *component, int freq_in, best_freq_out = -EINVAL; *sysclk_idx = *dac_idx = *bclk_idx = -1; - for (i = 0; i < ARRAY_SIZE(sysclk_divs); ++i) { + /* + * From Datasheet, the PLL performs best when f2 is between + * 90MHz and 100MHz, the desired sysclk output is 11.2896MHz + * or 12.288MHz, then sysclkdiv = 2 is the best choice. + * So search sysclk_divs from 2 to 1 other than from 1 to 2. + */ + for (i = ARRAY_SIZE(sysclk_divs) - 1; i >= 0; --i) { if (sysclk_divs[i] == -1) continue; for (j = 0; j < ARRAY_SIZE(dac_divs); ++j) { diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c index 08056fa0a0fa..a857a624864f 100644 --- a/sound/soc/fsl/fsl_esai.c +++ b/sound/soc/fsl/fsl_esai.c @@ -519,11 +519,13 @@ static int fsl_esai_startup(struct snd_pcm_substream *substream, ESAI_SAICR_SYNC, esai_priv->synchronous ? ESAI_SAICR_SYNC : 0); - /* Set a default slot number -- 2 */ + /* Set slots count */ regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR, - ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(2)); + ESAI_xCCR_xDC_MASK, + ESAI_xCCR_xDC(esai_priv->slots)); regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR, - ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(2)); + ESAI_xCCR_xDC_MASK, + ESAI_xCCR_xDC(esai_priv->slots)); } return 0; diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c index 9e9b05883557..4124aa2fc247 100644 --- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c +++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c @@ -487,15 +487,15 @@ static struct snd_soc_dai_driver sst_platform_dai[] = { .stream_name = "Headset Playback", .channels_min = SST_STEREO, .channels_max = SST_STEREO, - .rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000, - .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .rates = SNDRV_PCM_RATE_48000, + .formats = SNDRV_PCM_FMTBIT_S16_LE, }, .capture = { .stream_name = "Headset Capture", .channels_min = 1, .channels_max = 2, - .rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000, - .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .rates = SNDRV_PCM_RATE_48000, + .formats = SNDRV_PCM_FMTBIT_S16_LE, }, }, { @@ -505,8 +505,8 @@ static struct snd_soc_dai_driver sst_platform_dai[] = { .stream_name = "Deepbuffer Playback", .channels_min = SST_STEREO, .channels_max = SST_STEREO, - .rates = SNDRV_PCM_RATE_44100|SNDRV_PCM_RATE_48000, - .formats = SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S24_LE, + .rates = SNDRV_PCM_RATE_48000, + .formats = SNDRV_PCM_FMTBIT_S16_LE, }, }, { diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c index 6d8f7d9fd192..4a3d522f612b 100644 --- a/sound/soc/sof/core.c +++ b/sound/soc/sof/core.c @@ -399,7 +399,13 @@ int snd_sof_device_shutdown(struct device *dev) { struct snd_sof_dev *sdev = dev_get_drvdata(dev); - return snd_sof_shutdown(sdev); + if (IS_ENABLED(CONFIG_SND_SOC_SOF_PROBE_WORK_QUEUE)) + cancel_work_sync(&sdev->probe_work); + + if (sdev->fw_state == SOF_FW_BOOT_COMPLETE) + return snd_sof_shutdown(sdev); + + return 0; } EXPORT_SYMBOL(snd_sof_device_shutdown); diff --git a/sound/soc/sof/intel/apl.c b/sound/soc/sof/intel/apl.c index fc29b91b8932..c7ed2b3d6abc 100644 --- a/sound/soc/sof/intel/apl.c +++ b/sound/soc/sof/intel/apl.c @@ -27,9 +27,10 @@ static const struct snd_sof_debugfs_map apl_dsp_debugfs[] = { /* apollolake ops */ const struct snd_sof_dsp_ops sof_apl_ops = { - /* probe and remove */ + /* probe/remove/shutdown */ .probe = hda_dsp_probe, .remove = hda_dsp_remove, + .shutdown = hda_dsp_shutdown, /* Register IO */ .write = sof_io_write, diff --git a/sound/soc/sof/intel/cnl.c b/sound/soc/sof/intel/cnl.c index e38db519f38d..821f25fbcf08 100644 --- a/sound/soc/sof/intel/cnl.c +++ b/sound/soc/sof/intel/cnl.c @@ -232,9 +232,10 @@ void cnl_ipc_dump(struct snd_sof_dev *sdev) /* cannonlake ops */ const struct snd_sof_dsp_ops sof_cnl_ops = { - /* probe and remove */ + /* probe/remove/shutdown */ .probe = hda_dsp_probe, .remove = hda_dsp_remove, + .shutdown = hda_dsp_shutdown, /* Register IO */ .write = sof_io_write, @@ -349,22 +350,6 @@ const struct sof_intel_dsp_desc cnl_chip_info = { }; EXPORT_SYMBOL_NS(cnl_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON); -const struct sof_intel_dsp_desc ehl_chip_info = { - /* Elkhartlake */ - .cores_num = 4, - .init_core_mask = 1, - .host_managed_cores_mask = BIT(0), - .ipc_req = CNL_DSP_REG_HIPCIDR, - .ipc_req_mask = CNL_DSP_REG_HIPCIDR_BUSY, - .ipc_ack = CNL_DSP_REG_HIPCIDA, - .ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE, - .ipc_ctl = CNL_DSP_REG_HIPCCTL, - .rom_init_timeout = 300, - .ssp_count = ICL_SSP_COUNT, - .ssp_base_offset = CNL_SSP_BASE_OFFSET, -}; -EXPORT_SYMBOL_NS(ehl_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON); - const struct sof_intel_dsp_desc jsl_chip_info = { /* Jasperlake */ .cores_num = 2, diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c index c3b757cf01a0..736a54beca23 100644 --- a/sound/soc/sof/intel/hda-dsp.c +++ b/sound/soc/sof/intel/hda-dsp.c @@ -226,10 +226,17 @@ bool hda_dsp_core_is_enabled(struct snd_sof_dev *sdev, val = snd_sof_dsp_read(sdev, HDA_DSP_BAR, HDA_DSP_REG_ADSPCS); - is_enable = (val & HDA_DSP_ADSPCS_CPA_MASK(core_mask)) && - (val & HDA_DSP_ADSPCS_SPA_MASK(core_mask)) && - !(val & HDA_DSP_ADSPCS_CRST_MASK(core_mask)) && - !(val & HDA_DSP_ADSPCS_CSTALL_MASK(core_mask)); +#define MASK_IS_EQUAL(v, m, field) ({ \ + u32 _m = field(m); \ + ((v) & _m) == _m; \ +}) + + is_enable = MASK_IS_EQUAL(val, core_mask, HDA_DSP_ADSPCS_CPA_MASK) && + MASK_IS_EQUAL(val, core_mask, HDA_DSP_ADSPCS_SPA_MASK) && + !(val & HDA_DSP_ADSPCS_CRST_MASK(core_mask)) && + !(val & HDA_DSP_ADSPCS_CSTALL_MASK(core_mask)); + +#undef MASK_IS_EQUAL dev_dbg(sdev->dev, "DSP core(s) enabled? %d : core_mask %x\n", is_enable, core_mask); @@ -885,6 +892,12 @@ int hda_dsp_suspend(struct snd_sof_dev *sdev, u32 target_state) return snd_sof_dsp_set_power_state(sdev, &target_dsp_state); } +int hda_dsp_shutdown(struct snd_sof_dev *sdev) +{ + sdev->system_suspend_target = SOF_SUSPEND_S3; + return snd_sof_suspend(sdev->dev); +} + int hda_dsp_set_hw_params_upon_resume(struct snd_sof_dev *sdev) { #if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA) diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h index 7c7579daee7f..ae80725b0e33 100644 --- a/sound/soc/sof/intel/hda.h +++ b/sound/soc/sof/intel/hda.h @@ -517,6 +517,7 @@ int hda_dsp_resume(struct snd_sof_dev *sdev); int hda_dsp_runtime_suspend(struct snd_sof_dev *sdev); int hda_dsp_runtime_resume(struct snd_sof_dev *sdev); int hda_dsp_runtime_idle(struct snd_sof_dev *sdev); +int hda_dsp_shutdown(struct snd_sof_dev *sdev); int hda_dsp_set_hw_params_upon_resume(struct snd_sof_dev *sdev); void hda_dsp_dump(struct snd_sof_dev *sdev, u32 flags); void hda_ipc_dump(struct snd_sof_dev *sdev); diff --git a/sound/soc/sof/intel/icl.c b/sound/soc/sof/intel/icl.c index e9d5a0a58504..88a74be8a0c1 100644 --- a/sound/soc/sof/intel/icl.c +++ b/sound/soc/sof/intel/icl.c @@ -26,9 +26,10 @@ static const struct snd_sof_debugfs_map icl_dsp_debugfs[] = { /* Icelake ops */ const struct snd_sof_dsp_ops sof_icl_ops = { - /* probe and remove */ + /* probe/remove/shutdown */ .probe = hda_dsp_probe, .remove = hda_dsp_remove, + .shutdown = hda_dsp_shutdown, /* Register IO */ .write = sof_io_write, diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c index 485607471181..38bc353f7313 100644 --- a/sound/soc/sof/intel/pci-tgl.c +++ b/sound/soc/sof/intel/pci-tgl.c @@ -65,7 +65,7 @@ static const struct sof_dev_desc ehl_desc = { .default_tplg_path = "intel/sof-tplg", .default_fw_filename = "sof-ehl.ri", .nocodec_tplg_filename = "sof-ehl-nocodec.tplg", - .ops = &sof_cnl_ops, + .ops = &sof_tgl_ops, }; static const struct sof_dev_desc adls_desc = { diff --git a/sound/soc/sof/intel/tgl.c b/sound/soc/sof/intel/tgl.c index 419f05ba1920..54ba1b88ba86 100644 --- a/sound/soc/sof/intel/tgl.c +++ b/sound/soc/sof/intel/tgl.c @@ -25,7 +25,7 @@ const struct snd_sof_dsp_ops sof_tgl_ops = { /* probe/remove/shutdown */ .probe = hda_dsp_probe, .remove = hda_dsp_remove, - .shutdown = hda_dsp_remove, + .shutdown = hda_dsp_shutdown, /* Register IO */ .write = sof_io_write, @@ -156,6 +156,22 @@ const struct sof_intel_dsp_desc tglh_chip_info = { }; EXPORT_SYMBOL_NS(tglh_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON); +const struct sof_intel_dsp_desc ehl_chip_info = { + /* Elkhartlake */ + .cores_num = 4, + .init_core_mask = 1, + .host_managed_cores_mask = BIT(0), + .ipc_req = CNL_DSP_REG_HIPCIDR, + .ipc_req_mask = CNL_DSP_REG_HIPCIDR_BUSY, + .ipc_ack = CNL_DSP_REG_HIPCIDA, + .ipc_ack_mask = CNL_DSP_REG_HIPCIDA_DONE, + .ipc_ctl = CNL_DSP_REG_HIPCCTL, + .rom_init_timeout = 300, + .ssp_count = ICL_SSP_COUNT, + .ssp_base_offset = CNL_SSP_BASE_OFFSET, +}; +EXPORT_SYMBOL_NS(ehl_chip_info, SND_SOC_SOF_INTEL_HDA_COMMON); + const struct sof_intel_dsp_desc adls_chip_info = { /* Alderlake-S */ .cores_num = 2, diff --git a/sound/soc/sunxi/sun4i-codec.c b/sound/soc/sunxi/sun4i-codec.c index 6c13cc84b3fb..2173991c13db 100644 --- a/sound/soc/sunxi/sun4i-codec.c +++ b/sound/soc/sunxi/sun4i-codec.c @@ -1364,6 +1364,7 @@ static struct snd_soc_card *sun4i_codec_create_card(struct device *dev) return ERR_PTR(-ENOMEM); card->dev = dev; + card->owner = THIS_MODULE; card->name = "sun4i-codec"; card->dapm_widgets = sun4i_codec_card_dapm_widgets; card->num_dapm_widgets = ARRAY_SIZE(sun4i_codec_card_dapm_widgets); @@ -1396,6 +1397,7 @@ static struct snd_soc_card *sun6i_codec_create_card(struct device *dev) return ERR_PTR(-ENOMEM); card->dev = dev; + card->owner = THIS_MODULE; card->name = "A31 Audio Codec"; card->dapm_widgets = sun6i_codec_card_dapm_widgets; card->num_dapm_widgets = ARRAY_SIZE(sun6i_codec_card_dapm_widgets); @@ -1449,6 +1451,7 @@ static struct snd_soc_card *sun8i_a23_codec_create_card(struct device *dev) return ERR_PTR(-ENOMEM); card->dev = dev; + card->owner = THIS_MODULE; card->name = "A23 Audio Codec"; card->dapm_widgets = sun6i_codec_card_dapm_widgets; card->num_dapm_widgets = ARRAY_SIZE(sun6i_codec_card_dapm_widgets); @@ -1487,6 +1490,7 @@ static struct snd_soc_card *sun8i_h3_codec_create_card(struct device *dev) return ERR_PTR(-ENOMEM); card->dev = dev; + card->owner = THIS_MODULE; card->name = "H3 Audio Codec"; card->dapm_widgets = sun6i_codec_card_dapm_widgets; card->num_dapm_widgets = ARRAY_SIZE(sun6i_codec_card_dapm_widgets); @@ -1525,6 +1529,7 @@ static struct snd_soc_card *sun8i_v3s_codec_create_card(struct device *dev) return ERR_PTR(-ENOMEM); card->dev = dev; + card->owner = THIS_MODULE; card->name = "V3s Audio Codec"; card->dapm_widgets = sun6i_codec_card_dapm_widgets; card->num_dapm_widgets = ARRAY_SIZE(sun6i_codec_card_dapm_widgets); diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index d3001fb18141..176437a441e6 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1521,6 +1521,7 @@ bool snd_usb_get_sample_rate_quirk(struct snd_usb_audio *chip) case USB_ID(0x21b4, 0x0081): /* AudioQuest DragonFly */ case USB_ID(0x2912, 0x30c8): /* Audioengine D1 */ case USB_ID(0x413c, 0xa506): /* Dell AE515 sound bar */ + case USB_ID(0x046d, 0x084c): /* Logitech ConferenceCam Connect */ return true; } diff --git a/tools/arch/ia64/include/asm/barrier.h b/tools/arch/ia64/include/asm/barrier.h index 4d471d9511a5..6fffe5682713 100644 --- a/tools/arch/ia64/include/asm/barrier.h +++ b/tools/arch/ia64/include/asm/barrier.h @@ -39,9 +39,6 @@ * sequential memory pages only. */ -/* XXX From arch/ia64/include/uapi/asm/gcc_intrin.h */ -#define ia64_mf() asm volatile ("mf" ::: "memory") - #define mb() ia64_mf() #define rmb() mb() #define wmb() mb() diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 546d6ecf0a35..45029354e0a8 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -628,8 +628,6 @@ #define MSR_IA32_APICBASE_ENABLE (1<<11) #define MSR_IA32_APICBASE_BASE (0xfffff<<12) -#define MSR_IA32_TSCDEADLINE 0x000006e0 - #define MSR_IA32_UCODE_WRITE 0x00000079 #define MSR_IA32_UCODE_REV 0x0000008b diff --git a/tools/arch/x86/kcpuid/Makefile b/tools/arch/x86/kcpuid/Makefile new file mode 100644 index 000000000000..87b554fab14b --- /dev/null +++ b/tools/arch/x86/kcpuid/Makefile @@ -0,0 +1,24 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for x86/kcpuid tool + +kcpuid : kcpuid.c + +CFLAGS = -Wextra + +BINDIR ?= /usr/sbin + +HWDATADIR ?= /usr/share/misc/ + +override CFLAGS += -O2 -Wall -I../../../include + +%: %.c + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +.PHONY : clean +clean : + @rm -f kcpuid + +install : kcpuid + install -d $(DESTDIR)$(BINDIR) + install -m 755 -p kcpuid $(DESTDIR)$(BINDIR)/kcpuid + install -m 444 -p cpuid.csv $(HWDATADIR)/cpuid.csv diff --git a/tools/arch/x86/kcpuid/cpuid.csv b/tools/arch/x86/kcpuid/cpuid.csv new file mode 100644 index 000000000000..4f1c4b0c29e9 --- /dev/null +++ b/tools/arch/x86/kcpuid/cpuid.csv @@ -0,0 +1,400 @@ +# The basic row format is: +# LEAF, SUBLEAF, register_name, bits, short_name, long_description + +# Leaf 00H + 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + +# Leaf 01H + 1, 0, EAX, 3:0, stepping, Stepping ID + 1, 0, EAX, 7:4, model, Model + 1, 0, EAX, 11:8, family, Family ID + 1, 0, EAX, 13:12, processor, Processor Type + 1, 0, EAX, 19:16, model_ext, Extended Model ID + 1, 0, EAX, 27:20, family_ext, Extended Family ID + + 1, 0, EBX, 7:0, brand, Brand Index + 1, 0, EBX, 15:8, clflush_size, CLFLUSH line size (value * 8) in bytes + 1, 0, EBX, 23:16, max_cpu_id, Maxim number of addressable logic cpu in this package + 1, 0, EBX, 31:24, apic_id, Initial APIC ID + + 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + 1, 0, ECX, 1, pclmulqdq, PCLMULQDQ instruction supported + 1, 0, ECX, 2, dtes64, DS area uses 64-bit layout + 1, 0, ECX, 3, mwait, MONITOR/MWAIT supported + 1, 0, ECX, 4, ds_cpl, CPL Qualified Debug Store which allows for branch message storage qualified by CPL + 1, 0, ECX, 5, vmx, Virtual Machine Extensions supported + 1, 0, ECX, 6, smx, Safer Mode Extension supported + 1, 0, ECX, 7, eist, Enhanced Intel SpeedStep Technology + 1, 0, ECX, 8, tm2, Thermal Monitor 2 + 1, 0, ECX, 9, ssse3, Supplemental Streaming SIMD Extensions 3 (SSSE3) + 1, 0, ECX, 10, l1_ctx_id, L1 data cache could be set to either adaptive mode or shared mode (check IA32_MISC_ENABLE bit 24 definition) + 1, 0, ECX, 11, sdbg, IA32_DEBUG_INTERFACE MSR for silicon debug supported + 1, 0, ECX, 12, fma, FMA extensions using YMM state supported + 1, 0, ECX, 13, cmpxchg16b, 'CMPXCHG16B - Compare and Exchange Bytes' supported + 1, 0, ECX, 14, xtpr_update, xTPR Update Control supported + 1, 0, ECX, 15, pdcm, Perfmon and Debug Capability present + 1, 0, ECX, 17, pcid, Process-Context Identifiers feature present + 1, 0, ECX, 18, dca, Prefetching data from a memory mapped device supported + 1, 0, ECX, 19, sse4_1, SSE4.1 feature present + 1, 0, ECX, 20, sse4_2, SSE4.2 feature present + 1, 0, ECX, 21, x2apic, x2APIC supported + 1, 0, ECX, 22, movbe, MOVBE instruction supported + 1, 0, ECX, 23, popcnt, POPCNT instruction supported + 1, 0, ECX, 24, tsc_deadline_timer, LAPIC supports one-shot operation using a TSC deadline value + 1, 0, ECX, 25, aesni, AESNI instruction supported + 1, 0, ECX, 26, xsave, XSAVE/XRSTOR processor extended states (XSETBV/XGETBV/XCR0) + 1, 0, ECX, 27, osxsave, OS has set CR4.OSXSAVE bit to enable XSETBV/XGETBV/XCR0 + 1, 0, ECX, 28, avx, AVX instruction supported + 1, 0, ECX, 29, f16c, 16-bit floating-point conversion instruction supported + 1, 0, ECX, 30, rdrand, RDRAND instruction supported + + 1, 0, EDX, 0, fpu, x87 FPU on chip + 1, 0, EDX, 1, vme, Virtual-8086 Mode Enhancement + 1, 0, EDX, 2, de, Debugging Extensions + 1, 0, EDX, 3, pse, Page Size Extensions + 1, 0, EDX, 4, tsc, Time Stamp Counter + 1, 0, EDX, 5, msr, RDMSR and WRMSR Support + 1, 0, EDX, 6, pae, Physical Address Extensions + 1, 0, EDX, 7, mce, Machine Check Exception + 1, 0, EDX, 8, cx8, CMPXCHG8B instr + 1, 0, EDX, 9, apic, APIC on Chip + 1, 0, EDX, 11, sep, SYSENTER and SYSEXIT instrs + 1, 0, EDX, 12, mtrr, Memory Type Range Registers + 1, 0, EDX, 13, pge, Page Global Bit + 1, 0, EDX, 14, mca, Machine Check Architecture + 1, 0, EDX, 15, cmov, Conditional Move Instrs + 1, 0, EDX, 16, pat, Page Attribute Table + 1, 0, EDX, 17, pse36, 36-Bit Page Size Extension + 1, 0, EDX, 18, psn, Processor Serial Number + 1, 0, EDX, 19, clflush, CLFLUSH instr +# 1, 0, EDX, 20, + 1, 0, EDX, 21, ds, Debug Store + 1, 0, EDX, 22, acpi, Thermal Monitor and Software Controlled Clock Facilities + 1, 0, EDX, 23, mmx, Intel MMX Technology + 1, 0, EDX, 24, fxsr, XSAVE and FXRSTOR Instrs + 1, 0, EDX, 25, sse, SSE + 1, 0, EDX, 26, sse2, SSE2 + 1, 0, EDX, 27, ss, Self Snoop + 1, 0, EDX, 28, hit, Max APIC IDs + 1, 0, EDX, 29, tm, Thermal Monitor +# 1, 0, EDX, 30, + 1, 0, EDX, 31, pbe, Pending Break Enable + +# Leaf 02H +# cache and TLB descriptor info + +# Leaf 03H +# Precessor Serial Number, introduced on Pentium III, not valid for +# latest models + +# Leaf 04H +# thread/core and cache topology + 4, 0, EAX, 4:0, cache_type, Cache type like instr/data or unified + 4, 0, EAX, 7:5, cache_level, Cache Level (starts at 1) + 4, 0, EAX, 8, cache_self_init, Cache Self Initialization + 4, 0, EAX, 9, fully_associate, Fully Associative cache +# 4, 0, EAX, 13:10, resvd, resvd + 4, 0, EAX, 25:14, max_logical_id, Max number of addressable IDs for logical processors sharing the cache + 4, 0, EAX, 31:26, max_phy_id, Max number of addressable IDs for processors in phy package + + 4, 0, EBX, 11:0, cache_linesize, Size of a cache line in bytes + 4, 0, EBX, 21:12, cache_partition, Physical Line partitions + 4, 0, EBX, 31:22, cache_ways, Ways of associativity + 4, 0, ECX, 31:0, cache_sets, Number of Sets - 1 + 4, 0, EDX, 0, c_wbinvd, 1 means WBINVD/INVD is not ganranteed to act upon lower level caches of non-originating threads sharing this cache + 4, 0, EDX, 1, c_incl, Whether cache is inclusive of lower cache level + 4, 0, EDX, 2, c_comp_index, Complex Cache Indexing + +# Leaf 05H +# MONITOR/MWAIT + 5, 0, EAX, 15:0, min_mon_size, Smallest monitor line size in bytes + 5, 0, EBX, 15:0, max_mon_size, Largest monitor line size in bytes + 5, 0, ECX, 0, mwait_ext, Enum of Monitor-Mwait extensions supported + 5, 0, ECX, 1, mwait_irq_break, Largest monitor line size in bytes + 5, 0, EDX, 3:0, c0_sub_stats, Number of C0* sub C-states supported using MWAIT + 5, 0, EDX, 7:4, c1_sub_stats, Number of C1* sub C-states supported using MWAIT + 5, 0, EDX, 11:8, c2_sub_stats, Number of C2* sub C-states supported using MWAIT + 5, 0, EDX, 15:12, c3_sub_stats, Number of C3* sub C-states supported using MWAIT + 5, 0, EDX, 19:16, c4_sub_stats, Number of C4* sub C-states supported using MWAIT + 5, 0, EDX, 23:20, c5_sub_stats, Number of C5* sub C-states supported using MWAIT + 5, 0, EDX, 27:24, c6_sub_stats, Number of C6* sub C-states supported using MWAIT + 5, 0, EDX, 31:28, c7_sub_stats, Number of C7* sub C-states supported using MWAIT + +# Leaf 06H +# Thermal & Power Management + + 6, 0, EAX, 0, dig_temp, Digital temperature sensor supported + 6, 0, EAX, 1, turbo, Intel Turbo Boost + 6, 0, EAX, 2, arat, Always running APIC timer +# 6, 0, EAX, 3, resv, Reserved + 6, 0, EAX, 4, pln, Power limit notifications supported + 6, 0, EAX, 5, ecmd, Clock modulation duty cycle extension supported + 6, 0, EAX, 6, ptm, Package thermal management supported + 6, 0, EAX, 7, hwp, HWP base register + 6, 0, EAX, 8, hwp_notify, HWP notification + 6, 0, EAX, 9, hwp_act_window, HWP activity window + 6, 0, EAX, 10, hwp_energy, HWP energy performance preference + 6, 0, EAX, 11, hwp_pkg_req, HWP package level request +# 6, 0, EAX, 12, resv, Reserved + 6, 0, EAX, 13, hdc, HDC base registers supported + 6, 0, EAX, 14, turbo3, Turbo Boost Max 3.0 + 6, 0, EAX, 15, hwp_cap, Highest Performance change supported + 6, 0, EAX, 16, hwp_peci, HWP PECI override is supported + 6, 0, EAX, 17, hwp_flex, Flexible HWP is supported + 6, 0, EAX, 18, hwp_fast, Fast access mode for the IA32_HWP_REQUEST MSR is supported +# 6, 0, EAX, 19, resv, Reserved + 6, 0, EAX, 20, hwp_ignr, Ignoring Idle Logical Processor HWP request is supported + + 6, 0, EBX, 3:0, therm_irq_thresh, Number of Interrupt Thresholds in Digital Thermal Sensor + 6, 0, ECX, 0, aperfmperf, Presence of IA32_MPERF and IA32_APERF + 6, 0, ECX, 3, energ_bias, Performance-energy bias preference supported + +# Leaf 07H +# ECX == 0 +# AVX512 refers to https://en.wikipedia.org/wiki/AVX-512 +# XXX: Do we really need to enumerate each and every AVX512 sub features + + 7, 0, EBX, 0, fsgsbase, RDFSBASE/RDGSBASE/WRFSBASE/WRGSBASE supported + 7, 0, EBX, 1, tsc_adjust, TSC_ADJUST MSR supported + 7, 0, EBX, 2, sgx, Software Guard Extensions + 7, 0, EBX, 3, bmi1, BMI1 + 7, 0, EBX, 4, hle, Hardware Lock Elision + 7, 0, EBX, 5, avx2, AVX2 +# 7, 0, EBX, 6, fdp_excp_only, x87 FPU Data Pointer updated only on x87 exceptions + 7, 0, EBX, 7, smep, Supervisor-Mode Execution Prevention + 7, 0, EBX, 8, bmi2, BMI2 + 7, 0, EBX, 9, rep_movsb, Enhanced REP MOVSB/STOSB + 7, 0, EBX, 10, invpcid, INVPCID instruction + 7, 0, EBX, 11, rtm, Restricted Transactional Memory + 7, 0, EBX, 12, rdt_m, Intel RDT Monitoring capability + 7, 0, EBX, 13, depc_fpu_cs_ds, Deprecates FPU CS and FPU DS + 7, 0, EBX, 14, mpx, Memory Protection Extensions + 7, 0, EBX, 15, rdt_a, Intel RDT Allocation capability + 7, 0, EBX, 16, avx512f, AVX512 Foundation instr + 7, 0, EBX, 17, avx512dq, AVX512 Double and Quadword AVX512 instr + 7, 0, EBX, 18, rdseed, RDSEED instr + 7, 0, EBX, 19, adx, ADX instr + 7, 0, EBX, 20, smap, Supervisor Mode Access Prevention + 7, 0, EBX, 21, avx512ifma, AVX512 Integer Fused Multiply Add +# 7, 0, EBX, 22, resvd, resvd + 7, 0, EBX, 23, clflushopt, CLFLUSHOPT instr + 7, 0, EBX, 24, clwb, CLWB instr + 7, 0, EBX, 25, intel_pt, Intel Processor Trace instr + 7, 0, EBX, 26, avx512pf, Prefetch + 7, 0, EBX, 27, avx512er, AVX512 Exponent Reciproca instr + 7, 0, EBX, 28, avx512cd, AVX512 Conflict Detection instr + 7, 0, EBX, 29, sha, Intel Secure Hash Algorithm Extensions instr + 7, 0, EBX, 26, avx512bw, AVX512 Byte & Word instr + 7, 0, EBX, 28, avx512vl, AVX512 Vector Length Extentions (VL) + 7, 0, ECX, 0, prefetchwt1, X + 7, 0, ECX, 1, avx512vbmi, AVX512 Vector Byte Manipulation Instructions + 7, 0, ECX, 2, umip, User-mode Instruction Prevention + + 7, 0, ECX, 3, pku, Protection Keys for User-mode pages + 7, 0, ECX, 4, ospke, CR4 PKE set to enable protection keys +# 7, 0, ECX, 16:5, resvd, resvd + 7, 0, ECX, 21:17, mawau, The value of MAWAU used by the BNDLDX and BNDSTX instructions in 64-bit mode + 7, 0, ECX, 22, rdpid, RDPID and IA32_TSC_AUX +# 7, 0, ECX, 29:23, resvd, resvd + 7, 0, ECX, 30, sgx_lc, SGX Launch Configuration +# 7, 0, ECX, 31, resvd, resvd + +# Leaf 08H +# + + +# Leaf 09H +# Direct Cache Access (DCA) information + 9, 0, ECX, 31:0, dca_cap, The value of IA32_PLATFORM_DCA_CAP + +# Leaf 0AH +# Architectural Performance Monitoring +# +# Do we really need to print out the PMU related stuff? +# Does normal user really care about it? +# + 0xA, 0, EAX, 7:0, pmu_ver, Performance Monitoring Unit version + 0xA, 0, EAX, 15:8, pmu_gp_cnt_num, Numer of general-purose PMU counters per logical CPU + 0xA, 0, EAX, 23:16, pmu_cnt_bits, Bit wideth of PMU counter + 0xA, 0, EAX, 31:24, pmu_ebx_bits, Length of EBX bit vector to enumerate PMU events + + 0xA, 0, EBX, 0, pmu_no_core_cycle_evt, Core cycle event not available + 0xA, 0, EBX, 1, pmu_no_instr_ret_evt, Instruction retired event not available + 0xA, 0, EBX, 2, pmu_no_ref_cycle_evt, Reference cycles event not available + 0xA, 0, EBX, 3, pmu_no_llc_ref_evt, Last-level cache reference event not available + 0xA, 0, EBX, 4, pmu_no_llc_mis_evt, Last-level cache misses event not available + 0xA, 0, EBX, 5, pmu_no_br_instr_ret_evt, Branch instruction retired event not available + 0xA, 0, EBX, 6, pmu_no_br_mispredict_evt, Branch mispredict retired event not available + + 0xA, 0, ECX, 4:0, pmu_fixed_cnt_num, Performance Monitoring Unit version + 0xA, 0, ECX, 12:5, pmu_fixed_cnt_bits, Numer of PMU counters per logical CPU + +# Leaf 0BH +# Extended Topology Enumeration Leaf +# + + 0xB, 0, EAX, 4:0, id_shift, Number of bits to shift right on x2APIC ID to get a unique topology ID of the next level type + 0xB, 0, EBX, 15:0, cpu_nr, Number of logical processors at this level type + 0xB, 0, ECX, 15:8, lvl_type, 0-Invalid 1-SMT 2-Core + 0xB, 0, EDX, 31:0, x2apic_id, x2APIC ID the current logical processor + + +# Leaf 0DH +# Processor Extended State + + 0xD, 0, EAX, 0, x87, X87 state + 0xD, 0, EAX, 1, sse, SSE state + 0xD, 0, EAX, 2, avx, AVX state + 0xD, 0, EAX, 4:3, mpx, MPX state + 0xD, 0, EAX, 7:5, avx512, AVX-512 state + 0xD, 0, EAX, 9, pkru, PKRU state + + 0xD, 0, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 0, ECX, 31:0, max_sz_xsave, Maximum size (bytes) of the XSAVE/XRSTOR save area + + 0xD, 1, EAX, 0, xsaveopt, XSAVEOPT available + 0xD, 1, EAX, 1, xsavec, XSAVEC and compacted form supported + 0xD, 1, EAX, 2, xgetbv, XGETBV supported + 0xD, 1, EAX, 3, xsaves, XSAVES/XRSTORS and IA32_XSS supported + + 0xD, 1, EBX, 31:0, max_sz_xcr0, Maximum size (bytes) required by enabled features in XCR0 + 0xD, 1, ECX, 8, pt, PT state + 0xD, 1, ECX, 11, cet_usr, CET user state + 0xD, 1, ECX, 12, cet_supv, CET supervisor state + 0xD, 1, ECX, 13, hdc, HDC state + 0xD, 1, ECX, 16, hwp, HWP state + +# Leaf 0FH +# Intel RDT Monitoring + + 0xF, 0, EBX, 31:0, rmid_range, Maximum range (zero-based) of RMID within this physical processor of all types + 0xF, 0, EDX, 1, l3c_rdt_mon, L3 Cache RDT Monitoring supported + + 0xF, 1, ECX, 31:0, rmid_range, Maximum range (zero-based) of RMID of this types + 0xF, 1, EDX, 0, l3c_ocp_mon, L3 Cache occupancy Monitoring supported + 0xF, 1, EDX, 1, l3c_tbw_mon, L3 Cache Total Bandwidth Monitoring supported + 0xF, 1, EDX, 2, l3c_lbw_mon, L3 Cache Local Bandwidth Monitoring supported + +# Leaf 10H +# Intel RDT Allocation + + 0x10, 0, EBX, 1, l3c_rdt_alloc, L3 Cache Allocation supported + 0x10, 0, EBX, 2, l2c_rdt_alloc, L2 Cache Allocation supported + 0x10, 0, EBX, 3, mem_bw_alloc, Memory Bandwidth Allocation supported + + +# Leaf 12H +# SGX Capability +# +# Some detailed SGX features not added yet + + 0x12, 0, EAX, 0, sgx1, L3 Cache Allocation supported + 0x12, 1, EAX, 0, sgx2, L3 Cache Allocation supported + + +# Leaf 14H +# Intel Processor Tracer +# + +# Leaf 15H +# Time Stamp Counter and Nominal Core Crystal Clock Information + + 0x15, 0, EAX, 31:0, tsc_denominator, The denominator of the TSC/”core crystal clock” ratio + 0x15, 0, EBX, 31:0, tsc_numerator, The numerator of the TSC/”core crystal clock” ratio + 0x15, 0, ECX, 31:0, nom_freq, Nominal frequency of the core crystal clock in Hz + +# Leaf 16H +# Processor Frequency Information + + 0x16, 0, EAX, 15:0, cpu_base_freq, Processor Base Frequency in MHz + 0x16, 0, EBX, 15:0, cpu_max_freq, Maximum Frequency in MHz + 0x16, 0, ECX, 15:0, bus_freq, Bus (Reference) Frequency in MHz + +# Leaf 17H +# System-On-Chip Vendor Attribute + + 0x17, 0, EAX, 31:0, max_socid, Maximum input value of supported sub-leaf + 0x17, 0, EBX, 15:0, soc_vid, SOC Vendor ID + 0x17, 0, EBX, 16, std_vid, SOC Vendor ID is assigned via an industry standard scheme + 0x17, 0, ECX, 31:0, soc_pid, SOC Project ID assigned by vendor + 0x17, 0, EDX, 31:0, soc_sid, SOC Stepping ID + +# Leaf 18H +# Deterministic Address Translation Parameters + + +# Leaf 19H +# Key Locker Leaf + + +# Leaf 1AH +# Hybrid Information + + 0x1A, 0, EAX, 31:24, core_type, 20H-Intel_Atom 40H-Intel_Core + + +# Leaf 1FH +# V2 Extended Topology - A preferred superset to leaf 0BH + + +# According to SDM +# 40000000H - 4FFFFFFFH is invalid range + + +# Leaf 80000001H +# Extended Processor Signature and Feature Bits + +0x80000001, 0, ECX, 0, lahf_lm, LAHF/SAHF available in 64-bit mode +0x80000001, 0, ECX, 5, lzcnt, LZCNT +0x80000001, 0, ECX, 8, prefetchw, PREFETCHW + +0x80000001, 0, EDX, 11, sysret, SYSCALL/SYSRET supported +0x80000001, 0, EDX, 20, exec_dis, Execute Disable Bit available +0x80000001, 0, EDX, 26, 1gb_page, 1GB page supported +0x80000001, 0, EDX, 27, rdtscp, RDTSCP and IA32_TSC_AUX are available +#0x80000001, 0, EDX, 29, 64b, 64b Architecture supported + +# Leaf 80000002H/80000003H/80000004H +# Processor Brand String + +# Leaf 80000005H +# Reserved + +# Leaf 80000006H +# Extended L2 Cache Features + +0x80000006, 0, ECX, 7:0, clsize, Cache Line size in bytes +0x80000006, 0, ECX, 15:12, l2c_assoc, L2 Associativity +0x80000006, 0, ECX, 31:16, csize, Cache size in 1K units + + +# Leaf 80000007H + +0x80000007, 0, EDX, 8, nonstop_tsc, Invariant TSC available + + +# Leaf 80000008H + +0x80000008, 0, EAX, 7:0, phy_adr_bits, Physical Address Bits +0x80000008, 0, EAX, 15:8, lnr_adr_bits, Linear Address Bits +0x80000007, 0, EBX, 9, wbnoinvd, WBNOINVD + +# 0x8000001E +# EAX: Extended APIC ID +0x8000001E, 0, EAX, 31:0, extended_apic_id, Extended APIC ID +# EBX: Core Identifiers +0x8000001E, 0, EBX, 7:0, core_id, Identifies the logical core ID +0x8000001E, 0, EBX, 15:8, threads_per_core, The number of threads per core is threads_per_core + 1 +# ECX: Node Identifiers +0x8000001E, 0, ECX, 7:0, node_id, Node ID +0x8000001E, 0, ECX, 10:8, nodes_per_processor, Nodes per processor { 0: 1 node, else reserved } + +# 8000001F: AMD Secure Encryption +0x8000001F, 0, EAX, 0, sme, Secure Memory Encryption +0x8000001F, 0, EAX, 1, sev, Secure Encrypted Virtualization +0x8000001F, 0, EAX, 2, vmpgflush, VM Page Flush MSR +0x8000001F, 0, EAX, 3, seves, SEV Encrypted State +0x8000001F, 0, EBX, 5:0, c-bit, Page table bit number used to enable memory encryption +0x8000001F, 0, EBX, 11:6, mem_encrypt_physaddr_width, Reduction of physical address space in bits with SME enabled +0x8000001F, 0, ECX, 31:0, num_encrypted_guests, Maximum ASID value that may be used for an SEV-enabled guest +0x8000001F, 0, EDX, 31:0, minimum_sev_asid, Minimum ASID value that must be used for an SEV-enabled, SEV-ES-disabled guest diff --git a/tools/arch/x86/kcpuid/kcpuid.c b/tools/arch/x86/kcpuid/kcpuid.c new file mode 100644 index 000000000000..dae75511fef7 --- /dev/null +++ b/tools/arch/x86/kcpuid/kcpuid.c @@ -0,0 +1,657 @@ +// SPDX-License-Identifier: GPL-2.0 +#define _GNU_SOURCE + +#include <stdio.h> +#include <stdbool.h> +#include <stdlib.h> +#include <string.h> +#include <getopt.h> + +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) + +typedef unsigned int u32; +typedef unsigned long long u64; + +char *def_csv = "/usr/share/misc/cpuid.csv"; +char *user_csv; + + +/* Cover both single-bit flag and multiple-bits fields */ +struct bits_desc { + /* start and end bits */ + int start, end; + /* 0 or 1 for 1-bit flag */ + int value; + char simp[32]; + char detail[256]; +}; + +/* descriptor info for eax/ebx/ecx/edx */ +struct reg_desc { + /* number of valid entries */ + int nr; + struct bits_desc descs[32]; +}; + +enum { + R_EAX = 0, + R_EBX, + R_ECX, + R_EDX, + NR_REGS +}; + +struct subleaf { + u32 index; + u32 sub; + u32 eax, ebx, ecx, edx; + struct reg_desc info[NR_REGS]; +}; + +/* Represent one leaf (basic or extended) */ +struct cpuid_func { + /* + * Array of subleafs for this func, if there is no subleafs + * then the leafs[0] is the main leaf + */ + struct subleaf *leafs; + int nr; +}; + +struct cpuid_range { + /* array of main leafs */ + struct cpuid_func *funcs; + /* number of valid leafs */ + int nr; + bool is_ext; +}; + +/* + * basic: basic functions range: [0... ] + * ext: extended functions range: [0x80000000... ] + */ +struct cpuid_range *leafs_basic, *leafs_ext; + +static int num_leafs; +static bool is_amd; +static bool show_details; +static bool show_raw; +static bool show_flags_only = true; +static u32 user_index = 0xFFFFFFFF; +static u32 user_sub = 0xFFFFFFFF; +static int flines; + +static inline void cpuid(u32 *eax, u32 *ebx, u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx)); +} + +static inline bool has_subleafs(u32 f) +{ + if (f == 0x7 || f == 0xd) + return true; + + if (is_amd) { + if (f == 0x8000001d) + return true; + return false; + } + + switch (f) { + case 0x4: + case 0xb: + case 0xf: + case 0x10: + case 0x14: + case 0x18: + case 0x1f: + return true; + default: + return false; + } +} + +static void leaf_print_raw(struct subleaf *leaf) +{ + if (has_subleafs(leaf->index)) { + if (leaf->sub == 0) + printf("0x%08x: subleafs:\n", leaf->index); + + printf(" %2d: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->sub, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } else { + printf("0x%08x: EAX=0x%08x, EBX=0x%08x, ECX=0x%08x, EDX=0x%08x\n", + leaf->index, leaf->eax, leaf->ebx, leaf->ecx, leaf->edx); + } +} + +/* Return true is the input eax/ebx/ecx/edx are all zero */ +static bool cpuid_store(struct cpuid_range *range, u32 f, int subleaf, + u32 a, u32 b, u32 c, u32 d) +{ + struct cpuid_func *func; + struct subleaf *leaf; + int s = 0; + + if (a == 0 && b == 0 && c == 0 && d == 0) + return true; + + /* + * Cut off vendor-prefix from CPUID function as we're using it as an + * index into ->funcs. + */ + func = &range->funcs[f & 0xffff]; + + if (!func->leafs) { + func->leafs = malloc(sizeof(struct subleaf)); + if (!func->leafs) + perror("malloc func leaf"); + + func->nr = 1; + } else { + s = func->nr; + func->leafs = realloc(func->leafs, (s + 1) * sizeof(*leaf)); + if (!func->leafs) + perror("realloc f->leafs"); + + func->nr++; + } + + leaf = &func->leafs[s]; + + leaf->index = f; + leaf->sub = subleaf; + leaf->eax = a; + leaf->ebx = b; + leaf->ecx = c; + leaf->edx = d; + + return false; +} + +static void raw_dump_range(struct cpuid_range *range) +{ + u32 f; + int i; + + printf("%s Leafs :\n", range->is_ext ? "Extended" : "Basic"); + printf("================\n"); + + for (f = 0; (int)f < range->nr; f++) { + struct cpuid_func *func = &range->funcs[f]; + u32 index = f; + + if (range->is_ext) + index += 0x80000000; + + /* Skip leaf without valid items */ + if (!func->nr) + continue; + + /* First item is the main leaf, followed by all subleafs */ + for (i = 0; i < func->nr; i++) + leaf_print_raw(&func->leafs[i]); + } +} + +#define MAX_SUBLEAF_NUM 32 +struct cpuid_range *setup_cpuid_range(u32 input_eax) +{ + u32 max_func, idx_func; + int subleaf; + struct cpuid_range *range; + u32 eax, ebx, ecx, edx; + u32 f = input_eax; + int max_subleaf; + bool allzero; + + eax = input_eax; + ebx = ecx = edx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + max_func = eax; + idx_func = (max_func & 0xffff) + 1; + + range = malloc(sizeof(struct cpuid_range)); + if (!range) + perror("malloc range"); + + if (input_eax & 0x80000000) + range->is_ext = true; + else + range->is_ext = false; + + range->funcs = malloc(sizeof(struct cpuid_func) * idx_func); + if (!range->funcs) + perror("malloc range->funcs"); + + range->nr = idx_func; + memset(range->funcs, 0, sizeof(struct cpuid_func) * idx_func); + + for (; f <= max_func; f++) { + eax = f; + subleaf = ecx = 0; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + + if (!has_subleafs(f)) + continue; + + max_subleaf = MAX_SUBLEAF_NUM; + + /* + * Some can provide the exact number of subleafs, + * others have to be tried (0xf) + */ + if (f == 0x7 || f == 0x14 || f == 0x17 || f == 0x18) + max_subleaf = (eax & 0xff) + 1; + + if (f == 0xb) + max_subleaf = 2; + + for (subleaf = 1; subleaf < max_subleaf; subleaf++) { + eax = f; + ecx = subleaf; + + cpuid(&eax, &ebx, &ecx, &edx); + allzero = cpuid_store(range, f, subleaf, + eax, ebx, ecx, edx); + if (allzero) + continue; + num_leafs++; + } + + } + + return range; +} + +/* + * The basic row format for cpuid.csv is + * LEAF,SUBLEAF,register_name,bits,short name,long description + * + * like: + * 0, 0, EAX, 31:0, max_basic_leafs, Max input value for supported subleafs + * 1, 0, ECX, 0, sse3, Streaming SIMD Extensions 3(SSE3) + */ +static int parse_line(char *line) +{ + char *str; + int i; + struct cpuid_range *range; + struct cpuid_func *func; + struct subleaf *leaf; + u32 index; + u32 sub; + char buffer[512]; + char *buf; + /* + * Tokens: + * 1. leaf + * 2. subleaf + * 3. register + * 4. bits + * 5. short name + * 6. long detail + */ + char *tokens[6]; + struct reg_desc *reg; + struct bits_desc *bdesc; + int reg_index; + char *start, *end; + + /* Skip comments and NULL line */ + if (line[0] == '#' || line[0] == '\n') + return 0; + + strncpy(buffer, line, 511); + buffer[511] = 0; + str = buffer; + for (i = 0; i < 5; i++) { + tokens[i] = strtok(str, ","); + if (!tokens[i]) + goto err_exit; + str = NULL; + } + tokens[5] = strtok(str, "\n"); + if (!tokens[5]) + goto err_exit; + + /* index/main-leaf */ + index = strtoull(tokens[0], NULL, 0); + + if (index & 0x80000000) + range = leafs_ext; + else + range = leafs_basic; + + index &= 0x7FFFFFFF; + /* Skip line parsing for non-existing indexes */ + if ((int)index >= range->nr) + return -1; + + func = &range->funcs[index]; + + /* Return if the index has no valid item on this platform */ + if (!func->nr) + return 0; + + /* subleaf */ + sub = strtoul(tokens[1], NULL, 0); + if ((int)sub > func->nr) + return -1; + + leaf = &func->leafs[sub]; + buf = tokens[2]; + + if (strcasestr(buf, "EAX")) + reg_index = R_EAX; + else if (strcasestr(buf, "EBX")) + reg_index = R_EBX; + else if (strcasestr(buf, "ECX")) + reg_index = R_ECX; + else if (strcasestr(buf, "EDX")) + reg_index = R_EDX; + else + goto err_exit; + + reg = &leaf->info[reg_index]; + bdesc = ®->descs[reg->nr++]; + + /* bit flag or bits field */ + buf = tokens[3]; + + end = strtok(buf, ":"); + bdesc->end = strtoul(end, NULL, 0); + bdesc->start = bdesc->end; + + /* start != NULL means it is bit fields */ + start = strtok(NULL, ":"); + if (start) + bdesc->start = strtoul(start, NULL, 0); + + strcpy(bdesc->simp, tokens[4]); + strcpy(bdesc->detail, tokens[5]); + return 0; + +err_exit: + printf("Warning: wrong line format:\n"); + printf("\tline[%d]: %s\n", flines, line); + return -1; +} + +/* Parse csv file, and construct the array of all leafs and subleafs */ +static void parse_text(void) +{ + FILE *file; + char *filename, *line = NULL; + size_t len = 0; + int ret; + + if (show_raw) + return; + + filename = user_csv ? user_csv : def_csv; + file = fopen(filename, "r"); + if (!file) { + /* Fallback to a csv in the same dir */ + file = fopen("./cpuid.csv", "r"); + } + + if (!file) { + printf("Fail to open '%s'\n", filename); + return; + } + + while (1) { + ret = getline(&line, &len, file); + flines++; + if (ret > 0) + parse_line(line); + + if (feof(file)) + break; + } + + fclose(file); +} + + +/* Decode every eax/ebx/ecx/edx */ +static void decode_bits(u32 value, struct reg_desc *rdesc) +{ + struct bits_desc *bdesc; + int start, end, i; + u32 mask; + + for (i = 0; i < rdesc->nr; i++) { + bdesc = &rdesc->descs[i]; + + start = bdesc->start; + end = bdesc->end; + if (start == end) { + /* single bit flag */ + if (value & (1 << start)) + printf("\t%-20s %s%s\n", + bdesc->simp, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } else { + /* bit fields */ + if (show_flags_only) + continue; + + mask = ((u64)1 << (end - start + 1)) - 1; + printf("\t%-20s\t: 0x%-8x\t%s%s\n", + bdesc->simp, + (value >> start) & mask, + show_details ? "-" : "", + show_details ? bdesc->detail : "" + ); + } + } +} + +static void show_leaf(struct subleaf *leaf) +{ + if (!leaf) + return; + + if (show_raw) + leaf_print_raw(leaf); + + decode_bits(leaf->eax, &leaf->info[R_EAX]); + decode_bits(leaf->ebx, &leaf->info[R_EBX]); + decode_bits(leaf->ecx, &leaf->info[R_ECX]); + decode_bits(leaf->edx, &leaf->info[R_EDX]); +} + +static void show_func(struct cpuid_func *func) +{ + int i; + + if (!func) + return; + + for (i = 0; i < func->nr; i++) + show_leaf(&func->leafs[i]); +} + +static void show_range(struct cpuid_range *range) +{ + int i; + + for (i = 0; i < range->nr; i++) + show_func(&range->funcs[i]); +} + +static inline struct cpuid_func *index_to_func(u32 index) +{ + struct cpuid_range *range; + + range = (index & 0x80000000) ? leafs_ext : leafs_basic; + index &= 0x7FFFFFFF; + + if (((index & 0xFFFF) + 1) > (u32)range->nr) { + printf("ERR: invalid input index (0x%x)\n", index); + return NULL; + } + return &range->funcs[index]; +} + +static void show_info(void) +{ + struct cpuid_func *func; + + if (show_raw) { + /* Show all of the raw output of 'cpuid' instr */ + raw_dump_range(leafs_basic); + raw_dump_range(leafs_ext); + return; + } + + if (user_index != 0xFFFFFFFF) { + /* Only show specific leaf/subleaf info */ + func = index_to_func(user_index); + if (!func) + return; + + /* Dump the raw data also */ + show_raw = true; + + if (user_sub != 0xFFFFFFFF) { + if (user_sub + 1 <= (u32)func->nr) { + show_leaf(&func->leafs[user_sub]); + return; + } + + printf("ERR: invalid input subleaf (0x%x)\n", user_sub); + } + + show_func(func); + return; + } + + printf("CPU features:\n=============\n\n"); + show_range(leafs_basic); + show_range(leafs_ext); +} + +static void setup_platform_cpuid(void) +{ + u32 eax, ebx, ecx, edx; + + /* Check vendor */ + eax = ebx = ecx = edx = 0; + cpuid(&eax, &ebx, &ecx, &edx); + + /* "htuA" */ + if (ebx == 0x68747541) + is_amd = true; + + /* Setup leafs for the basic and extended range */ + leafs_basic = setup_cpuid_range(0x0); + leafs_ext = setup_cpuid_range(0x80000000); +} + +static void usage(void) +{ + printf("kcpuid [-abdfhr] [-l leaf] [-s subleaf]\n" + "\t-a|--all Show both bit flags and complex bit fields info\n" + "\t-b|--bitflags Show boolean flags only\n" + "\t-d|--detail Show details of the flag/fields (default)\n" + "\t-f|--flags Specify the cpuid csv file\n" + "\t-h|--help Show usage info\n" + "\t-l|--leaf=index Specify the leaf you want to check\n" + "\t-r|--raw Show raw cpuid data\n" + "\t-s|--subleaf=sub Specify the subleaf you want to check\n" + ); +} + +static struct option opts[] = { + { "all", no_argument, NULL, 'a' }, /* show both bit flags and fields */ + { "bitflags", no_argument, NULL, 'b' }, /* only show bit flags, default on */ + { "detail", no_argument, NULL, 'd' }, /* show detail descriptions */ + { "file", required_argument, NULL, 'f' }, /* use user's cpuid file */ + { "help", no_argument, NULL, 'h'}, /* show usage */ + { "leaf", required_argument, NULL, 'l'}, /* only check a specific leaf */ + { "raw", no_argument, NULL, 'r'}, /* show raw CPUID leaf data */ + { "subleaf", required_argument, NULL, 's'}, /* check a specific subleaf */ + { NULL, 0, NULL, 0 } +}; + +static int parse_options(int argc, char *argv[]) +{ + int c; + + while ((c = getopt_long(argc, argv, "abdf:hl:rs:", + opts, NULL)) != -1) + switch (c) { + case 'a': + show_flags_only = false; + break; + case 'b': + show_flags_only = true; + break; + case 'd': + show_details = true; + break; + case 'f': + user_csv = optarg; + break; + case 'h': + usage(); + exit(1); + break; + case 'l': + /* main leaf */ + user_index = strtoul(optarg, NULL, 0); + break; + case 'r': + show_raw = true; + break; + case 's': + /* subleaf */ + user_sub = strtoul(optarg, NULL, 0); + break; + default: + printf("%s: Invalid option '%c'\n", argv[0], optopt); + return -1; + } + + return 0; +} + +/* + * Do 4 things in turn: + * 1. Parse user options + * 2. Parse and store all the CPUID leaf data supported on this platform + * 2. Parse the csv file, while skipping leafs which are not available + * on this platform + * 3. Print leafs info based on user options + */ +int main(int argc, char *argv[]) +{ + if (parse_options(argc, argv)) + return -1; + + /* Setup the cpuid leafs of current platform */ + setup_platform_cpuid(); + + /* Read and parse the 'cpuid.csv' */ + parse_text(); + + show_info(); + return 0; +} diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py index c4225ed63565..1600b17dbb8a 100644 --- a/tools/cgroup/memcg_slabinfo.py +++ b/tools/cgroup/memcg_slabinfo.py @@ -128,9 +128,9 @@ def detect_kernel_config(): cfg['nr_nodes'] = prog['nr_online_nodes'].value_() - if prog.type('struct kmem_cache').members[1][1] == 'flags': + if prog.type('struct kmem_cache').members[1].name == 'flags': cfg['allocator'] = 'SLUB' - elif prog.type('struct kmem_cache').members[1][1] == 'batchcount': + elif prog.type('struct kmem_cache').members[1].name == 'batchcount': cfg['allocator'] = 'SLAB' else: err('Can\'t determine the slab allocator') @@ -193,7 +193,7 @@ def main(): # look over all slab pages, belonging to non-root memcgs # and look for objects belonging to the given memory cgroup for page in for_each_slab_page(prog): - objcg_vec_raw = page.obj_cgroups.value_() + objcg_vec_raw = page.memcg_data.value_() if objcg_vec_raw == 0: continue cache = page.slab_cache @@ -202,7 +202,7 @@ def main(): addr = cache.value_() caches[addr] = cache # clear the lowest bit to get the true obj_cgroups - objcg_vec = Object(prog, page.obj_cgroups.type_, + objcg_vec = Object(prog, 'struct obj_cgroup **', value=objcg_vec_raw & ~1) if addr not in stats: diff --git a/tools/include/linux/static_call_types.h b/tools/include/linux/static_call_types.h index ae5662d368b9..5a00b8b2cf9f 100644 --- a/tools/include/linux/static_call_types.h +++ b/tools/include/linux/static_call_types.h @@ -58,11 +58,25 @@ struct static_call_site { __raw_static_call(name); \ }) +struct static_call_key { + void *func; + union { + /* bit 0: 0 = mods, 1 = sites */ + unsigned long type; + struct static_call_mod *mods; + struct static_call_site *sites; + }; +}; + #else /* !CONFIG_HAVE_STATIC_CALL_INLINE */ #define __STATIC_CALL_ADDRESSABLE(name) #define __static_call(name) __raw_static_call(name) +struct static_call_key { + void *func; +}; + #endif /* CONFIG_HAVE_STATIC_CALL_INLINE */ #ifdef MODULE @@ -77,6 +91,10 @@ struct static_call_site { #else +struct static_call_key { + void *func; +}; + #define static_call(name) \ ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) diff --git a/tools/include/uapi/asm/errno.h b/tools/include/uapi/asm/errno.h index 637189ec1ab9..d30439b4b8ab 100644 --- a/tools/include/uapi/asm/errno.h +++ b/tools/include/uapi/asm/errno.h @@ -9,8 +9,6 @@ #include "../../../arch/alpha/include/uapi/asm/errno.h" #elif defined(__mips__) #include "../../../arch/mips/include/uapi/asm/errno.h" -#elif defined(__ia64__) -#include "../../../arch/ia64/include/uapi/asm/errno.h" #elif defined(__xtensa__) #include "../../../arch/xtensa/include/uapi/asm/errno.h" #else diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 8b281f722e5b..f6afee209620 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1154,6 +1154,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) struct kvm_xen_hvm_config { __u32 flags; @@ -1621,12 +1622,24 @@ struct kvm_xen_vcpu_attr { union { __u64 gpa; __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; } u; }; /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 #define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { diff --git a/tools/kvm/kvm_stat/kvm_stat.service b/tools/kvm/kvm_stat/kvm_stat.service index 71aabaffe779..8f13b843d5b4 100644 --- a/tools/kvm/kvm_stat/kvm_stat.service +++ b/tools/kvm/kvm_stat/kvm_stat.service @@ -9,6 +9,7 @@ Type=simple ExecStart=/usr/bin/kvm_stat -dtcz -s 10 -L /var/log/kvm_stat.csv ExecReload=/bin/kill -HUP $MAINPID Restart=always +RestartSec=60s SyslogIdentifier=kvm_stat SyslogLevel=debug diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 887a494ad5fc..e9eb6a6e80d2 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -215,7 +215,7 @@ define do_install if [ ! -d '$(DESTDIR_SQ)$2' ]; then \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \ fi; \ - $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2' + $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2' endef install_lib: all_cmd diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index 2f9d685bd522..0911aea4cdbe 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -462,7 +462,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) return err; case BTF_KIND_ARRAY: - return btf_dump_order_type(d, btf_array(t)->type, through_ptr); + return btf_dump_order_type(d, btf_array(t)->type, false); case BTF_KIND_STRUCT: case BTF_KIND_UNION: { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index d43cc3f29dae..4181d178ee7b 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -1181,7 +1181,8 @@ static int bpf_object__elf_init(struct bpf_object *obj) if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) { pr_warn("elf: failed to get section names strings from %s: %s\n", obj->path, elf_errmsg(-1)); - return -LIBBPF_ERRNO__FORMAT; + err = -LIBBPF_ERRNO__FORMAT; + goto errout; } /* Old LLVM set e_machine to EM_NONE */ diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 4dd73de00b6f..d2cb28e9ef52 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -40,7 +40,7 @@ static int libbpf_netlink_open(__u32 *nl_pid) memset(&sa, 0, sizeof(sa)); sa.nl_family = AF_NETLINK; - sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + sock = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, NETLINK_ROUTE); if (sock < 0) return -errno; diff --git a/tools/lib/bpf/ringbuf.c b/tools/lib/bpf/ringbuf.c index 8caaafe7e312..e7a8d847161f 100644 --- a/tools/lib/bpf/ringbuf.c +++ b/tools/lib/bpf/ringbuf.c @@ -227,7 +227,7 @@ static int ringbuf_process_ring(struct ring* r) if ((len & BPF_RINGBUF_DISCARD_BIT) == 0) { sample = (void *)len_ptr + BPF_RINGBUF_HDR_SZ; err = r->sample_cb(r->ctx, sample, len); - if (err) { + if (err < 0) { /* update consumer pos and bail out */ smp_store_release(r->consumer_pos, cons_pos); diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 526fc35c0b23..007fe5d59438 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -59,6 +59,8 @@ struct xsk_umem { int fd; int refcount; struct list_head ctx_list; + bool rx_ring_setup_done; + bool tx_ring_setup_done; }; struct xsk_ctx { @@ -743,26 +745,30 @@ static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex, return NULL; } -static void xsk_put_ctx(struct xsk_ctx *ctx) +static void xsk_put_ctx(struct xsk_ctx *ctx, bool unmap) { struct xsk_umem *umem = ctx->umem; struct xdp_mmap_offsets off; int err; - if (--ctx->refcount == 0) { - err = xsk_get_mmap_offsets(umem->fd, &off); - if (!err) { - munmap(ctx->fill->ring - off.fr.desc, - off.fr.desc + umem->config.fill_size * - sizeof(__u64)); - munmap(ctx->comp->ring - off.cr.desc, - off.cr.desc + umem->config.comp_size * - sizeof(__u64)); - } + if (--ctx->refcount) + return; - list_del(&ctx->list); - free(ctx); - } + if (!unmap) + goto out_free; + + err = xsk_get_mmap_offsets(umem->fd, &off); + if (err) + goto out_free; + + munmap(ctx->fill->ring - off.fr.desc, off.fr.desc + umem->config.fill_size * + sizeof(__u64)); + munmap(ctx->comp->ring - off.cr.desc, off.cr.desc + umem->config.comp_size * + sizeof(__u64)); + +out_free: + list_del(&ctx->list); + free(ctx); } static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk, @@ -797,8 +803,6 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk, memcpy(ctx->ifname, ifname, IFNAMSIZ - 1); ctx->ifname[IFNAMSIZ - 1] = '\0'; - umem->fill_save = NULL; - umem->comp_save = NULL; ctx->fill = fill; ctx->comp = comp; list_add(&ctx->list, &umem->ctx_list); @@ -848,6 +852,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, struct xsk_ring_cons *comp, const struct xsk_socket_config *usr_config) { + bool unmap, rx_setup_done = false, tx_setup_done = false; void *rx_map = NULL, *tx_map = NULL; struct sockaddr_xdp sxdp = {}; struct xdp_mmap_offsets off; @@ -858,6 +863,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, if (!umem || !xsk_ptr || !(rx || tx)) return -EFAULT; + unmap = umem->fill_save != fill; + xsk = calloc(1, sizeof(*xsk)); if (!xsk) return -ENOMEM; @@ -881,6 +888,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, } } else { xsk->fd = umem->fd; + rx_setup_done = umem->rx_ring_setup_done; + tx_setup_done = umem->tx_ring_setup_done; } ctx = xsk_get_ctx(umem, ifindex, queue_id); @@ -899,7 +908,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, } xsk->ctx = ctx; - if (rx) { + if (rx && !rx_setup_done) { err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING, &xsk->config.rx_size, sizeof(xsk->config.rx_size)); @@ -907,8 +916,10 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, err = -errno; goto out_put_ctx; } + if (xsk->fd == umem->fd) + umem->rx_ring_setup_done = true; } - if (tx) { + if (tx && !tx_setup_done) { err = setsockopt(xsk->fd, SOL_XDP, XDP_TX_RING, &xsk->config.tx_size, sizeof(xsk->config.tx_size)); @@ -916,6 +927,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, err = -errno; goto out_put_ctx; } + if (xsk->fd == umem->fd) + umem->rx_ring_setup_done = true; } err = xsk_get_mmap_offsets(xsk->fd, &off); @@ -994,6 +1007,8 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, } *xsk_ptr = xsk; + umem->fill_save = NULL; + umem->comp_save = NULL; return 0; out_mmap_tx: @@ -1005,7 +1020,7 @@ out_mmap_rx: munmap(rx_map, off.rx.desc + xsk->config.rx_size * sizeof(struct xdp_desc)); out_put_ctx: - xsk_put_ctx(ctx); + xsk_put_ctx(ctx, unmap); out_socket: if (--umem->refcount) close(xsk->fd); @@ -1019,6 +1034,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, struct xsk_ring_cons *rx, struct xsk_ring_prod *tx, const struct xsk_socket_config *usr_config) { + if (!umem) + return -EFAULT; + return xsk_socket__create_shared(xsk_ptr, ifname, queue_id, umem, rx, tx, umem->fill_save, umem->comp_save, usr_config); @@ -1068,7 +1086,7 @@ void xsk_socket__delete(struct xsk_socket *xsk) } } - xsk_put_ctx(ctx); + xsk_put_ctx(ctx, true); umem->refcount--; /* Do not close an fd that also has an associated umem connected diff --git a/tools/perf/builtin-daemon.c b/tools/perf/builtin-daemon.c index ace8772a4f03..7c4a9d424a64 100644 --- a/tools/perf/builtin-daemon.c +++ b/tools/perf/builtin-daemon.c @@ -402,35 +402,42 @@ static pid_t handle_signalfd(struct daemon *daemon) int status; pid_t pid; + /* + * Take signal fd data as pure signal notification and check all + * the sessions state. The reason is that multiple signals can get + * coalesced in kernel and we can receive only single signal even + * if multiple SIGCHLD were generated. + */ err = read(daemon->signal_fd, &si, sizeof(struct signalfd_siginfo)); - if (err != sizeof(struct signalfd_siginfo)) + if (err != sizeof(struct signalfd_siginfo)) { + pr_err("failed to read signal fd\n"); return -1; + } list_for_each_entry(session, &daemon->sessions, list) { + if (session->pid == -1) + continue; - if (session->pid != (int) si.ssi_pid) + pid = waitpid(session->pid, &status, WNOHANG); + if (pid <= 0) continue; - pid = waitpid(session->pid, &status, 0); - if (pid == session->pid) { - if (WIFEXITED(status)) { - pr_info("session '%s' exited, status=%d\n", - session->name, WEXITSTATUS(status)); - } else if (WIFSIGNALED(status)) { - pr_info("session '%s' killed (signal %d)\n", - session->name, WTERMSIG(status)); - } else if (WIFSTOPPED(status)) { - pr_info("session '%s' stopped (signal %d)\n", - session->name, WSTOPSIG(status)); - } else { - pr_info("session '%s' Unexpected status (0x%x)\n", - session->name, status); - } + if (WIFEXITED(status)) { + pr_info("session '%s' exited, status=%d\n", + session->name, WEXITSTATUS(status)); + } else if (WIFSIGNALED(status)) { + pr_info("session '%s' killed (signal %d)\n", + session->name, WTERMSIG(status)); + } else if (WIFSTOPPED(status)) { + pr_info("session '%s' stopped (signal %d)\n", + session->name, WSTOPSIG(status)); + } else { + pr_info("session '%s' Unexpected status (0x%x)\n", + session->name, status); } session->state = KILL; session->pid = -1; - return pid; } return 0; @@ -443,7 +450,6 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d .fd = daemon->signal_fd, .events = POLLIN, }; - pid_t wpid = 0, pid = session->pid; time_t start; start = time(NULL); @@ -452,7 +458,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d int err = poll(&pollfd, 1, 1000); if (err > 0) { - wpid = handle_signalfd(daemon); + handle_signalfd(daemon); } else if (err < 0) { perror("failed: poll\n"); return -1; @@ -460,7 +466,7 @@ static int daemon_session__wait(struct daemon_session *session, struct daemon *d if (start + secs < time(NULL)) return -1; - } while (wpid != pid); + } while (session->pid != -1); return 0; } @@ -902,7 +908,9 @@ static void daemon_session__kill(struct daemon_session *session, daemon_session__signal(session, SIGKILL); break; default: - break; + pr_err("failed to wait for session %s\n", + session->name); + return; } how++; @@ -955,7 +963,8 @@ static void daemon__kill(struct daemon *daemon) daemon__signal(daemon, SIGKILL); break; default: - break; + pr_err("failed to wait for sessions\n"); + return; } how++; @@ -1344,7 +1353,7 @@ out: close(sock_fd); if (conf_fd != -1) close(conf_fd); - if (conf_fd != -1) + if (signal_fd != -1) close(signal_fd); pr_info("daemon exited\n"); diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c index d49448a1060c..87cb11a7a3ee 100644 --- a/tools/perf/builtin-ftrace.c +++ b/tools/perf/builtin-ftrace.c @@ -289,7 +289,7 @@ static int set_tracing_pid(struct perf_ftrace *ftrace) for (i = 0; i < perf_thread_map__nr(ftrace->evlist->core.threads); i++) { scnprintf(buf, sizeof(buf), "%d", - ftrace->evlist->core.threads->map[i]); + perf_thread_map__pid(ftrace->evlist->core.threads, i)); if (append_tracing_file("set_ftrace_pid", buf) < 0) return -1; } diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c index 6fe44d97fde5..ddccc0eb7390 100644 --- a/tools/perf/builtin-inject.c +++ b/tools/perf/builtin-inject.c @@ -906,7 +906,7 @@ int cmd_inject(int argc, const char **argv) } data.path = inject.input_name; - inject.session = perf_session__new(&data, true, &inject.tool); + inject.session = perf_session__new(&data, inject.output.is_pipe, &inject.tool); if (IS_ERR(inject.session)) return PTR_ERR(inject.session); diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c index f57e075b0ed2..c72adbd67386 100644 --- a/tools/perf/tests/bpf.c +++ b/tools/perf/tests/bpf.c @@ -86,7 +86,7 @@ static struct { .msg_load_fail = "check your vmlinux setting?", .target_func = &epoll_pwait_loop, .expect_result = (NR_ITERS + 1) / 2, - .pin = true, + .pin = true, }, #ifdef HAVE_BPF_PROLOGUE { @@ -99,13 +99,6 @@ static struct { .expect_result = (NR_ITERS + 1) / 4, }, #endif - { - .prog_id = LLVM_TESTCASE_BPF_RELOCATION, - .desc = "BPF relocation checker", - .name = "[bpf_relocation_test]", - .msg_compile_fail = "fix 'perf test LLVM' first", - .msg_load_fail = "libbpf error when dealing with relocation", - }, }; static int do_test(struct bpf_object *obj, int (*func)(void), diff --git a/tools/perf/tests/shell/daemon.sh b/tools/perf/tests/shell/daemon.sh index 5ad3ca8d681b..58984380b211 100755 --- a/tools/perf/tests/shell/daemon.sh +++ b/tools/perf/tests/shell/daemon.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # daemon operations # SPDX-License-Identifier: GPL-2.0 diff --git a/tools/perf/trace/beauty/tracepoints/x86_msr.sh b/tools/perf/trace/beauty/tracepoints/x86_msr.sh index 27ee1ea1fe94..9b0614a87831 100755 --- a/tools/perf/trace/beauty/tracepoints/x86_msr.sh +++ b/tools/perf/trace/beauty/tracepoints/x86_msr.sh @@ -15,7 +15,7 @@ x86_msr_index=${arch_x86_header_dir}/msr-index.h printf "static const char *x86_MSRs[] = {\n" regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MSR_([[:alnum:]][[:alnum:]_]+)[[:space:]]+(0x00000[[:xdigit:]]+)[[:space:]]*.*' -egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|IA32_(TSCDEADLINE|UCODE_REV)|IDT_FCR4)' | \ +egrep $regex ${x86_msr_index} | egrep -v 'MSR_(ATOM|P[46]|IA32_(TSC_DEADLINE|UCODE_REV)|IDT_FCR4)' | \ sed -r "s/$regex/\2 \1/g" | sort -n | \ xargs printf "\t[%s] = \"%s\",\n" printf "};\n\n" diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c index f3ac9d40cebf..2e5eff4f8f03 100644 --- a/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c +++ b/tools/perf/util/arm-spe-decoder/arm-spe-pkt-decoder.c @@ -210,8 +210,10 @@ static int arm_spe_do_get_packet(const unsigned char *buf, size_t len, if ((hdr & SPE_HEADER0_MASK2) == SPE_HEADER0_EXTENDED) { /* 16-bit extended format header */ - ext_hdr = 1; + if (len == 1) + return ARM_SPE_BAD_PACKET; + ext_hdr = 1; hdr = buf[1]; if (hdr == SPE_HEADER1_ALIGNMENT) return arm_spe_get_alignment(buf, len, packet); diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 953f4afacd3b..1b4091a3b508 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -298,10 +298,6 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues, queue->set = true; queue->tid = buffer->tid; queue->cpu = buffer->cpu; - } else if (buffer->cpu != queue->cpu || buffer->tid != queue->tid) { - pr_err("auxtrace queue conflict: cpu %d, tid %d vs cpu %d, tid %d\n", - queue->cpu, queue->tid, buffer->cpu, buffer->tid); - return -EINVAL; } buffer->buffer_nr = queues->next_buffer_nr++; @@ -638,7 +634,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr, break; } - if (itr) + if (itr && itr->parse_snapshot_options) return itr->parse_snapshot_options(itr, opts, str); pr_err("No AUX area tracing to snapshot\n"); diff --git a/tools/perf/util/block-info.c b/tools/perf/util/block-info.c index 423ec69bda6c..5ecd4f401f32 100644 --- a/tools/perf/util/block-info.c +++ b/tools/perf/util/block-info.c @@ -201,7 +201,7 @@ static int block_total_cycles_pct_entry(struct perf_hpp_fmt *fmt, double ratio = 0.0; if (block_fmt->total_cycles) - ratio = (double)bi->cycles / (double)block_fmt->total_cycles; + ratio = (double)bi->cycles_aggr / (double)block_fmt->total_cycles; return color_pct(hpp, block_fmt->width, 100.0 * ratio); } @@ -216,9 +216,9 @@ static int64_t block_total_cycles_pct_sort(struct perf_hpp_fmt *fmt, double l, r; if (block_fmt->total_cycles) { - l = ((double)bi_l->cycles / + l = ((double)bi_l->cycles_aggr / (double)block_fmt->total_cycles) * 100000.0; - r = ((double)bi_r->cycles / + r = ((double)bi_r->cycles_aggr / (double)block_fmt->total_cycles) * 100000.0; return (int64_t)l - (int64_t)r; } diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 57d58c81a5f8..cdecda1ddd36 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -196,25 +196,32 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, } if (info_linear->info_len < offsetof(struct bpf_prog_info, prog_tags)) { + free(info_linear); pr_debug("%s: the kernel is too old, aborting\n", __func__); return -2; } info = &info_linear->info; + if (!info->jited_ksyms) { + free(info_linear); + return -1; + } /* number of ksyms, func_lengths, and tags should match */ sub_prog_cnt = info->nr_jited_ksyms; if (sub_prog_cnt != info->nr_prog_tags || - sub_prog_cnt != info->nr_jited_func_lens) + sub_prog_cnt != info->nr_jited_func_lens) { + free(info_linear); return -1; + } /* check BTF func info support */ if (info->btf_id && info->nr_func_info && info->func_info_rec_size) { /* btf func info number should be same as sub_prog_cnt */ if (sub_prog_cnt != info->nr_func_info) { pr_debug("%s: mismatch in BPF sub program count and BTF function info count, aborting\n", __func__); - err = -1; - goto out; + free(info_linear); + return -1; } if (btf__get_from_id(info->btf_id, &btf)) { pr_debug("%s: failed to get BTF of id %u, aborting\n", __func__, info->btf_id); diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index f29af4fc3d09..8fca4779ae6a 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -35,7 +35,7 @@ void perf_data__close_dir(struct perf_data *data) int perf_data__create_dir(struct perf_data *data, int nr) { struct perf_data_file *files = NULL; - int i, ret = -1; + int i, ret; if (WARN_ON(!data->is_dir)) return -EINVAL; @@ -51,7 +51,8 @@ int perf_data__create_dir(struct perf_data *data, int nr) for (i = 0; i < nr; i++) { struct perf_data_file *file = &files[i]; - if (asprintf(&file->path, "%s/data.%d", data->path, i) < 0) + ret = asprintf(&file->path, "%s/data.%d", data->path, i); + if (ret < 0) goto out_err; ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR); diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index fbc40a2c17d4..8af693d9678c 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -840,15 +840,18 @@ out: int maps__clone(struct thread *thread, struct maps *parent) { struct maps *maps = thread->maps; - int err = -ENOMEM; + int err; struct map *map; down_read(&parent->lock); maps__for_each_entry(parent, map) { struct map *new = map__clone(map); - if (new == NULL) + + if (new == NULL) { + err = -ENOMEM; goto out_unlock; + } err = unwind__prepare_access(maps, new, NULL); if (err) diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 42c84adeb2fb..c0c0fab22cb8 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -356,6 +356,9 @@ __add_event(struct list_head *list, int *idx, struct perf_cpu_map *cpus = pmu ? perf_cpu_map__get(pmu->cpus) : cpu_list ? perf_cpu_map__new(cpu_list) : NULL; + if (pmu && attr->type == PERF_TYPE_RAW) + perf_pmu__warn_invalid_config(pmu, attr->config, name); + if (init_attr) event_attr_init(attr); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 44ef28302fc7..46fd0f998484 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -1812,3 +1812,36 @@ int perf_pmu__caps_parse(struct perf_pmu *pmu) return nr_caps; } + +void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, + char *name) +{ + struct perf_pmu_format *format; + __u64 masks = 0, bits; + char buf[100]; + unsigned int i; + + list_for_each_entry(format, &pmu->format, list) { + if (format->value != PERF_PMU_FORMAT_VALUE_CONFIG) + continue; + + for_each_set_bit(i, format->bits, PERF_PMU_FORMAT_BITS) + masks |= 1ULL << i; + } + + /* + * Kernel doesn't export any valid format bits. + */ + if (masks == 0) + return; + + bits = config & ~masks; + if (bits == 0) + return; + + bitmap_scnprintf((unsigned long *)&bits, sizeof(bits) * 8, buf, sizeof(buf)); + + pr_warning("WARNING: event '%s' not valid (bits %s of config " + "'%llx' not supported by kernel)!\n", + name ?: "N/A", buf, config); +} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 8164388478c6..160b0f561771 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -123,4 +123,7 @@ int perf_pmu__convert_scale(const char *scale, char **end, double *sval); int perf_pmu__caps_parse(struct perf_pmu *pmu); +void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config, + char *name); + #endif /* __PMU_H */ diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c index b698046ec2db..dff178103ce5 100644 --- a/tools/perf/util/synthetic-events.c +++ b/tools/perf/util/synthetic-events.c @@ -424,7 +424,7 @@ int perf_event__synthesize_mmap_events(struct perf_tool *tool, while (!io.eof) { static const char anonstr[] = "//anon"; - size_t size; + size_t size, aligned_size; /* ensure null termination since stack will be reused. */ event->mmap2.filename[0] = '\0'; @@ -484,11 +484,12 @@ out: } size = strlen(event->mmap2.filename) + 1; - size = PERF_ALIGN(size, sizeof(u64)); + aligned_size = PERF_ALIGN(size, sizeof(u64)); event->mmap2.len -= event->mmap.start; event->mmap2.header.size = (sizeof(event->mmap2) - - (sizeof(event->mmap2.filename) - size)); - memset(event->mmap2.filename + size, 0, machine->id_hdr_size); + (sizeof(event->mmap2.filename) - aligned_size)); + memset(event->mmap2.filename + size, 0, machine->id_hdr_size + + (aligned_size - size)); event->mmap2.header.size += machine->id_hdr_size; event->mmap2.pid = tgid; event->mmap2.tid = pid; @@ -758,7 +759,7 @@ static int __event__synthesize_thread(union perf_event *comm_event, for (i = 0; i < n; i++) { char *end; pid_t _pid; - bool kernel_thread; + bool kernel_thread = false; _pid = strtol(dirent[i]->d_name, &end, 10); if (*end) diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c index 3cc91ad048ea..43beb169631d 100644 --- a/tools/perf/util/vdso.c +++ b/tools/perf/util/vdso.c @@ -133,6 +133,8 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s if (dso != NULL) { __dsos__add(&machine->dsos, dso); dso__set_long_name(dso, long_name, false); + /* Put dso here because __dsos_add already got it */ + dso__put(dso); } return dso; diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index a7c4f0772e53..5939615265f1 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -2449,7 +2449,7 @@ dump_knl_turbo_ratio_limits(void) fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, msr); - /** + /* * Turbo encoding in KNL is as follows: * [0] -- Reserved * [7:1] -- Base value of number of active cores of bucket 1. diff --git a/tools/testing/kunit/configs/broken_on_uml.config b/tools/testing/kunit/configs/broken_on_uml.config index a7f0603d33f6..690870043ac0 100644 --- a/tools/testing/kunit/configs/broken_on_uml.config +++ b/tools/testing/kunit/configs/broken_on_uml.config @@ -40,3 +40,5 @@ # CONFIG_RESET_BRCMSTB_RESCAL is not set # CONFIG_RESET_INTEL_GW is not set # CONFIG_ADI_AXI_ADC is not set +# CONFIG_DEBUG_PAGEALLOC is not set +# CONFIG_PAGE_POISONING is not set diff --git a/tools/testing/kunit/kunit_config.py b/tools/testing/kunit/kunit_config.py index 0b550cbd667d..1e2683dcc0e7 100644 --- a/tools/testing/kunit/kunit_config.py +++ b/tools/testing/kunit/kunit_config.py @@ -13,7 +13,7 @@ from typing import List, Set CONFIG_IS_NOT_SET_PATTERN = r'^# CONFIG_(\w+) is not set$' CONFIG_PATTERN = r'^CONFIG_(\w+)=(\S+|".*")$' -KconfigEntryBase = collections.namedtuple('KconfigEntry', ['name', 'value']) +KconfigEntryBase = collections.namedtuple('KconfigEntryBase', ['name', 'value']) class KconfigEntry(KconfigEntryBase): diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 3b796dd5e577..ca24f6839d50 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -296,21 +296,34 @@ static void *idr_throbber(void *arg) return NULL; } +/* + * There are always either 1 or 2 objects in the IDR. If we find nothing, + * or we find something at an ID we didn't expect, that's a bug. + */ void idr_find_test_1(int anchor_id, int throbber_id) { pthread_t throbber; time_t start = time(NULL); - pthread_create(&throbber, NULL, idr_throbber, &throbber_id); - BUG_ON(idr_alloc(&find_idr, xa_mk_value(anchor_id), anchor_id, anchor_id + 1, GFP_KERNEL) != anchor_id); + pthread_create(&throbber, NULL, idr_throbber, &throbber_id); + + rcu_read_lock(); do { int id = 0; void *entry = idr_get_next(&find_idr, &id); - BUG_ON(entry != xa_mk_value(id)); + rcu_read_unlock(); + if ((id != anchor_id && id != throbber_id) || + entry != xa_mk_value(id)) { + printf("%s(%d, %d): %p at %d\n", __func__, anchor_id, + throbber_id, entry, id); + abort(); + } + rcu_read_lock(); } while (time(NULL) < start + 11); + rcu_read_unlock(); pthread_join(throbber, NULL); @@ -577,6 +590,7 @@ void ida_tests(void) int __weak main(void) { + rcu_register_thread(); radix_tree_init(); idr_checks(); ida_tests(); @@ -584,5 +598,6 @@ int __weak main(void) rcu_barrier(); if (nr_allocated) printf("nr_allocated = %d\n", nr_allocated); + rcu_unregister_thread(); return 0; } diff --git a/tools/testing/radix-tree/linux/compiler_types.h b/tools/testing/radix-tree/linux/compiler_types.h deleted file mode 100644 index e69de29bb2d1..000000000000 --- a/tools/testing/radix-tree/linux/compiler_types.h +++ /dev/null diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 9eae0fb5a67d..e00520cc6349 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -224,7 +224,9 @@ void multiorder_checks(void) int __weak main(void) { + rcu_register_thread(); radix_tree_init(); multiorder_checks(); + rcu_unregister_thread(); return 0; } diff --git a/tools/testing/radix-tree/xarray.c b/tools/testing/radix-tree/xarray.c index e61e43efe463..f20e12cbbfd4 100644 --- a/tools/testing/radix-tree/xarray.c +++ b/tools/testing/radix-tree/xarray.c @@ -25,11 +25,13 @@ void xarray_tests(void) int __weak main(void) { + rcu_register_thread(); radix_tree_init(); xarray_tests(); radix_tree_cpu_dead(1); rcu_barrier(); if (nr_allocated) printf("nr_allocated = %d\n", nr_allocated); + rcu_unregister_thread(); return 0; } diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index 9210691aa998..e3e08d9c7020 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -284,16 +284,28 @@ endfunction // Set up test pattern in the FFR // x0: pid // x2: generation +// +// We need to generate a canonical FFR value, which consists of a number of +// low "1" bits, followed by a number of zeros. This gives us 17 unique values +// per 16 bits of FFR, so we create a 4 bit signature out of the PID and +// generation, and use that as the initial number of ones in the pattern. +// We fill the upper lanes of FFR with zeros. // Beware: corrupts P0. function setup_ffr mov x4, x30 - bl pattern + and w0, w0, #0x3 + bfi w0, w2, #2, #2 + mov w1, #1 + lsl w1, w1, w0 + sub w1, w1, #1 + ldr x0, =ffrref - ldr x1, =scratch - rdvl x2, #1 - lsr x2, x2, #3 - bl memcpy + strh w1, [x0], 2 + rdvl x1, #1 + lsr x1, x1, #3 + sub x1, x1, #2 + bl memclr mov x0, #0 ldr x1, =ffrref diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c index 37c5494a0381..e25917f04602 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c @@ -6,6 +6,7 @@ #include <test_progs.h> #include "bpf_dctcp.skel.h" #include "bpf_cubic.skel.h" +#include "bpf_tcp_nogpl.skel.h" #define min(a, b) ((a) < (b) ? (a) : (b)) @@ -227,10 +228,53 @@ static void test_dctcp(void) bpf_dctcp__destroy(dctcp_skel); } +static char *err_str; +static bool found; + +static int libbpf_debug_print(enum libbpf_print_level level, + const char *format, va_list args) +{ + char *log_buf; + + if (level != LIBBPF_WARN || + strcmp(format, "libbpf: \n%s\n")) { + vprintf(format, args); + return 0; + } + + log_buf = va_arg(args, char *); + if (!log_buf) + goto out; + if (err_str && strstr(log_buf, err_str) != NULL) + found = true; +out: + printf(format, log_buf); + return 0; +} + +static void test_invalid_license(void) +{ + libbpf_print_fn_t old_print_fn; + struct bpf_tcp_nogpl *skel; + + err_str = "struct ops programs must have a GPL compatible license"; + found = false; + old_print_fn = libbpf_set_print(libbpf_debug_print); + + skel = bpf_tcp_nogpl__open_and_load(); + ASSERT_NULL(skel, "bpf_tcp_nogpl"); + ASSERT_EQ(found, true, "expected_err_msg"); + + bpf_tcp_nogpl__destroy(skel); + libbpf_set_print(old_print_fn); +} + void test_bpf_tcp_ca(void) { if (test__start_subtest("dctcp")) test_dctcp(); if (test__start_subtest("cubic")) test_cubic(); + if (test__start_subtest("invalid_license")) + test_invalid_license(); } diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c index 36af1c138faf..b62a39315336 100644 --- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c +++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c @@ -128,6 +128,8 @@ static void test_check_mtu_xdp(__u32 mtu, __u32 ifindex) test_check_mtu_run_xdp(skel, skel->progs.xdp_use_helper, mtu); test_check_mtu_run_xdp(skel, skel->progs.xdp_exceed_mtu, mtu); test_check_mtu_run_xdp(skel, skel->progs.xdp_minus_delta, mtu); + test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len, mtu); + test_check_mtu_run_xdp(skel, skel->progs.xdp_input_len_exceed, mtu); cleanup: test_check_mtu__destroy(skel); @@ -187,6 +189,8 @@ static void test_check_mtu_tc(__u32 mtu, __u32 ifindex) test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu, mtu); test_check_mtu_run_tc(skel, skel->progs.tc_exceed_mtu_da, mtu); test_check_mtu_run_tc(skel, skel->progs.tc_minus_delta, mtu); + test_check_mtu_run_tc(skel, skel->progs.tc_input_len, mtu); + test_check_mtu_run_tc(skel, skel->progs.tc_input_len_exceed, mtu); cleanup: test_check_mtu__destroy(skel); } diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c new file mode 100644 index 000000000000..6c4d42a2386f --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#define _GNU_SOURCE +#include <sched.h> +#include <test_progs.h> +#include <time.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include "fexit_sleep.skel.h" + +static int do_sleep(void *skel) +{ + struct fexit_sleep *fexit_skel = skel; + struct timespec ts1 = { .tv_nsec = 1 }; + struct timespec ts2 = { .tv_sec = 10 }; + + fexit_skel->bss->pid = getpid(); + (void)syscall(__NR_nanosleep, &ts1, NULL); + (void)syscall(__NR_nanosleep, &ts2, NULL); + return 0; +} + +#define STACK_SIZE (1024 * 1024) +static char child_stack[STACK_SIZE]; + +void test_fexit_sleep(void) +{ + struct fexit_sleep *fexit_skel = NULL; + int wstatus, duration = 0; + pid_t cpid; + int err, fexit_cnt; + + fexit_skel = fexit_sleep__open_and_load(); + if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n")) + goto cleanup; + + err = fexit_sleep__attach(fexit_skel); + if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err)) + goto cleanup; + + cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel); + if (CHECK(cpid == -1, "clone", strerror(errno))) + goto cleanup; + + /* wait until first sys_nanosleep ends and second sys_nanosleep starts */ + while (READ_ONCE(fexit_skel->bss->fentry_cnt) != 2); + fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt); + if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt)) + goto cleanup; + + /* close progs and detach them. That will trigger two nop5->jmp5 rewrites + * in the trampolines to skip nanosleep_fexit prog. + * The nanosleep_fentry prog will get detached first. + * The nanosleep_fexit prog will get detached second. + * Detaching will trigger freeing of both progs JITed images. + * There will be two dying bpf_tramp_image-s, but only the initial + * bpf_tramp_image (with both _fentry and _fexit progs will be stuck + * waiting for percpu_ref_kill to confirm). The other one + * will be freed quickly. + */ + close(bpf_program__fd(fexit_skel->progs.nanosleep_fentry)); + close(bpf_program__fd(fexit_skel->progs.nanosleep_fexit)); + fexit_sleep__detach(fexit_skel); + + /* kill the thread to unwind sys_nanosleep stack through the trampoline */ + kill(cpid, 9); + + if (CHECK(waitpid(cpid, &wstatus, 0) == -1, "waitpid", strerror(errno))) + goto cleanup; + if (CHECK(WEXITSTATUS(wstatus) != 0, "exitstatus", "failed")) + goto cleanup; + + /* The bypassed nanosleep_fexit prog shouldn't have executed. + * Unlike progs the maps were not freed and directly accessible. + */ + fexit_cnt = READ_ONCE(fexit_skel->bss->fexit_cnt); + if (CHECK(fexit_cnt != 1, "fexit_cnt", "%d", fexit_cnt)) + goto cleanup; + +cleanup: + fexit_sleep__destroy(fexit_skel); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c new file mode 100644 index 000000000000..2ecd833dcd41 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_tcp_nogpl.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <linux/types.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_tcp_helpers.h" + +char _license[] SEC("license") = "X"; + +void BPF_STRUCT_OPS(nogpltcp_init, struct sock *sk) +{ +} + +SEC(".struct_ops") +struct tcp_congestion_ops bpf_nogpltcp = { + .init = (void *)nogpltcp_init, + .name = "bpf_nogpltcp", +}; diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c index 31975c96e2c9..3ac0c9afc35a 100644 --- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c +++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c @@ -174,6 +174,12 @@ struct struct_in_struct { }; }; +struct struct_in_array {}; + +struct struct_in_array_typed {}; + +typedef struct struct_in_array_typed struct_in_array_t[2]; + struct struct_with_embedded_stuff { int a; struct { @@ -203,6 +209,8 @@ struct struct_with_embedded_stuff { } r[5]; struct struct_in_struct s[10]; int t[11]; + struct struct_in_array (*u)[2]; + struct_in_array_t *v; }; struct root_struct { diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c new file mode 100644 index 000000000000..03a672d76353 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char LICENSE[] SEC("license") = "GPL"; + +int pid = 0; +int fentry_cnt = 0; +int fexit_cnt = 0; + +SEC("fentry/__x64_sys_nanosleep") +int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs) +{ + if ((int)bpf_get_current_pid_tgid() != pid) + return 0; + + fentry_cnt++; + return 0; +} + +SEC("fexit/__x64_sys_nanosleep") +int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret) +{ + if ((int)bpf_get_current_pid_tgid() != pid) + return 0; + + fexit_cnt++; + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c index b7787b43f9db..c4a9bae96e75 100644 --- a/tools/testing/selftests/bpf/progs/test_check_mtu.c +++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c @@ -105,6 +105,54 @@ int xdp_minus_delta(struct xdp_md *ctx) return retval; } +SEC("xdp") +int xdp_input_len(struct xdp_md *ctx) +{ + int retval = XDP_PASS; /* Expected retval on successful test */ + void *data_end = (void *)(long)ctx->data_end; + void *data = (void *)(long)ctx->data; + __u32 ifindex = GLOBAL_USER_IFINDEX; + __u32 data_len = data_end - data; + + /* API allow user give length to check as input via mtu_len param, + * resulting MTU value is still output in mtu_len param after call. + * + * Input len is L3, like MTU and iph->tot_len. + * Remember XDP data_len is L2. + */ + __u32 mtu_len = data_len - ETH_HLEN; + + if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0)) + retval = XDP_ABORTED; + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("xdp") +int xdp_input_len_exceed(struct xdp_md *ctx) +{ + int retval = XDP_ABORTED; /* Fail */ + __u32 ifindex = GLOBAL_USER_IFINDEX; + int err; + + /* API allow user give length to check as input via mtu_len param, + * resulting MTU value is still output in mtu_len param after call. + * + * Input length value is L3 size like MTU. + */ + __u32 mtu_len = GLOBAL_USER_MTU; + + mtu_len += 1; /* Exceed with 1 */ + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0); + if (err == BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = XDP_PASS ; /* Success in exceeding MTU check */ + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + SEC("classifier") int tc_use_helper(struct __sk_buff *ctx) { @@ -196,3 +244,47 @@ int tc_minus_delta(struct __sk_buff *ctx) global_bpf_mtu_xdp = mtu_len; return retval; } + +SEC("classifier") +int tc_input_len(struct __sk_buff *ctx) +{ + int retval = BPF_OK; /* Expected retval on successful test */ + __u32 ifindex = GLOBAL_USER_IFINDEX; + + /* API allow user give length to check as input via mtu_len param, + * resulting MTU value is still output in mtu_len param after call. + * + * Input length value is L3 size. + */ + __u32 mtu_len = GLOBAL_USER_MTU; + + if (bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0)) + retval = BPF_DROP; + + global_bpf_mtu_xdp = mtu_len; + return retval; +} + +SEC("classifier") +int tc_input_len_exceed(struct __sk_buff *ctx) +{ + int retval = BPF_DROP; /* Fail */ + __u32 ifindex = GLOBAL_USER_IFINDEX; + int err; + + /* API allow user give length to check as input via mtu_len param, + * resulting MTU value is still output in mtu_len param after call. + * + * Input length value is L3 size like MTU. + */ + __u32 mtu_len = GLOBAL_USER_MTU; + + mtu_len += 1; /* Exceed with 1 */ + + err = bpf_check_mtu(ctx, ifindex, &mtu_len, 0, 0); + if (err == BPF_MTU_CHK_RET_FRAG_NEEDED) + retval = BPF_OK; /* Success in exceeding MTU check */ + + global_bpf_mtu_xdp = mtu_len; + return retval; +} diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 9afe947cfae9..ba6eadfec565 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -508,10 +508,8 @@ int _ip6geneve_get_tunnel(struct __sk_buff *skb) } ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); - if (ret < 0) { - ERROR(ret); - return TC_ACT_SHOT; - } + if (ret < 0) + gopt.opt_class = 0; bpf_trace_printk(fmt, sizeof(fmt), key.tunnel_id, key.remote_ipv4, gopt.opt_class); diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c index 57ed67b86074..8a1caf46ffbc 100644 --- a/tools/testing/selftests/bpf/verifier/bounds.c +++ b/tools/testing/selftests/bpf/verifier/bounds.c @@ -261,8 +261,6 @@ }, .fixup_map_hash_8b = { 3 }, /* not actually fully unbounded, but the bound is very high */ - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root", - .result_unpriv = REJECT, .errstr = "value -4294967168 makes map_value pointer be out of bounds", .result = REJECT, }, @@ -298,9 +296,6 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_8b = { 3 }, - /* not actually fully unbounded, but the bound is very high */ - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root", - .result_unpriv = REJECT, .errstr = "value -4294967168 makes map_value pointer be out of bounds", .result = REJECT, }, diff --git a/tools/testing/selftests/bpf/verifier/bounds_deduction.c b/tools/testing/selftests/bpf/verifier/bounds_deduction.c index 1fd07a4f27ac..91869aea6d64 100644 --- a/tools/testing/selftests/bpf/verifier/bounds_deduction.c +++ b/tools/testing/selftests/bpf/verifier/bounds_deduction.c @@ -6,8 +6,9 @@ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }, - .result = REJECT, + .errstr_unpriv = "R1 has pointer with unsupported alu operation", .errstr = "R0 tried to subtract pointer from scalar", + .result = REJECT, }, { "check deducing bounds from const, 2", @@ -20,6 +21,8 @@ BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R1 has pointer with unsupported alu operation", + .result_unpriv = REJECT, .result = ACCEPT, .retval = 1, }, @@ -31,20 +34,24 @@ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }, - .result = REJECT, + .errstr_unpriv = "R1 has pointer with unsupported alu operation", .errstr = "R0 tried to subtract pointer from scalar", + .result = REJECT, }, { "check deducing bounds from const, 4", .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), BPF_MOV64_IMM(BPF_REG_0, 0), BPF_JMP_IMM(BPF_JSLE, BPF_REG_0, 0, 1), BPF_EXIT_INSN(), BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 1), BPF_EXIT_INSN(), - BPF_ALU64_REG(BPF_SUB, BPF_REG_1, BPF_REG_0), + BPF_ALU64_REG(BPF_SUB, BPF_REG_6, BPF_REG_0), BPF_EXIT_INSN(), }, + .errstr_unpriv = "R6 has pointer with unsupported alu operation", + .result_unpriv = REJECT, .result = ACCEPT, }, { @@ -55,8 +62,9 @@ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }, - .result = REJECT, + .errstr_unpriv = "R1 has pointer with unsupported alu operation", .errstr = "R0 tried to subtract pointer from scalar", + .result = REJECT, }, { "check deducing bounds from const, 6", @@ -67,8 +75,9 @@ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }, - .result = REJECT, + .errstr_unpriv = "R1 has pointer with unsupported alu operation", .errstr = "R0 tried to subtract pointer from scalar", + .result = REJECT, }, { "check deducing bounds from const, 7", @@ -80,8 +89,9 @@ offsetof(struct __sk_buff, mark)), BPF_EXIT_INSN(), }, - .result = REJECT, + .errstr_unpriv = "R1 has pointer with unsupported alu operation", .errstr = "dereference of modified ctx ptr", + .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { @@ -94,8 +104,9 @@ offsetof(struct __sk_buff, mark)), BPF_EXIT_INSN(), }, - .result = REJECT, + .errstr_unpriv = "R1 has pointer with unsupported alu operation", .errstr = "dereference of modified ctx ptr", + .result = REJECT, .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { @@ -106,8 +117,9 @@ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }, - .result = REJECT, + .errstr_unpriv = "R1 has pointer with unsupported alu operation", .errstr = "R0 tried to subtract pointer from scalar", + .result = REJECT, }, { "check deducing bounds from const, 10", @@ -119,6 +131,6 @@ BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), }, - .result = REJECT, .errstr = "math between ctx pointer and register with unbounded min value is not allowed", + .result = REJECT, }, diff --git a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c index 9baca7a75c42..c2aa6f26738b 100644 --- a/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c +++ b/tools/testing/selftests/bpf/verifier/bounds_mix_sign_unsign.c @@ -19,7 +19,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -43,7 +42,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -69,7 +67,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -94,7 +91,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R8 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -141,7 +137,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -210,7 +205,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -260,7 +254,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -287,7 +280,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -313,7 +305,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -342,7 +333,6 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R7 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -372,7 +362,6 @@ }, .fixup_map_hash_8b = { 4 }, .errstr = "unbounded min value", - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, }, { @@ -400,7 +389,5 @@ }, .fixup_map_hash_8b = { 3 }, .errstr = "unbounded min value", - .errstr_unpriv = "R1 has unknown scalar with mixed signed bounds", .result = REJECT, - .result_unpriv = REJECT, }, diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c index b117bdd3806d..1f82021429bf 100644 --- a/tools/testing/selftests/bpf/verifier/map_ptr.c +++ b/tools/testing/selftests/bpf/verifier/map_ptr.c @@ -75,6 +75,8 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_16b = { 4 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R1 has pointer with unsupported alu operation", .result = ACCEPT, }, { @@ -91,5 +93,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_16b = { 4 }, + .result_unpriv = REJECT, + .errstr_unpriv = "R0 has pointer with unsupported alu operation", .result = ACCEPT, }, diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c index b018ad71e0a8..bd436df5cc32 100644 --- a/tools/testing/selftests/bpf/verifier/unpriv.c +++ b/tools/testing/selftests/bpf/verifier/unpriv.c @@ -497,7 +497,7 @@ .result = ACCEPT, }, { - "unpriv: adding of fp", + "unpriv: adding of fp, reg", .insns = { BPF_MOV64_IMM(BPF_REG_0, 0), BPF_MOV64_IMM(BPF_REG_1, 0), @@ -510,6 +510,19 @@ .result = ACCEPT, }, { + "unpriv: adding of fp, imm", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8), + BPF_EXIT_INSN(), + }, + .errstr_unpriv = "R1 stack pointer arithmetic goes out of range", + .result_unpriv = REJECT, + .result = ACCEPT, +}, +{ "unpriv: cmp of stack pointer", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index ed4e76b24649..e5913fd3b903 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -21,8 +21,6 @@ .fixup_map_hash_16b = { 5 }, .fixup_map_array_48b = { 8 }, .result = ACCEPT, - .result_unpriv = REJECT, - .errstr_unpriv = "R1 tried to add from different maps", .retval = 1, }, { @@ -122,7 +120,7 @@ .fixup_map_array_48b = { 1 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R2 tried to add from different pointers or scalars", + .errstr_unpriv = "R2 tried to add from different maps, paths or scalars", .retval = 0, }, { @@ -169,7 +167,7 @@ .fixup_map_array_48b = { 1 }, .result = ACCEPT, .result_unpriv = REJECT, - .errstr_unpriv = "R2 tried to add from different maps or paths", + .errstr_unpriv = "R2 tried to add from different maps, paths or scalars", .retval = 0, }, { @@ -517,6 +515,27 @@ .retval = 0xabcdef12, }, { + "map access: value_ptr += N, value_ptr -= N known scalar", + .insns = { + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV32_IMM(BPF_REG_1, 0x12345678), + BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 2), + BPF_MOV64_IMM(BPF_REG_1, 2), + BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_array_48b = { 3 }, + .result = ACCEPT, + .retval = 0x12345678, +}, +{ "map access: unknown scalar += value_ptr, 1", .insns = { BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index 2f2eeb8a1d86..5aadf84c91c0 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -108,7 +108,7 @@ static void run_test(uint32_t run) kvm_vm_elf_load(vm, program_invocation_name, 0, 0); vm_create_irqchip(vm); - fprintf(stderr, "%s: [%d] start vcpus\n", __func__, run); + pr_debug("%s: [%d] start vcpus\n", __func__, run); for (i = 0; i < VCPU_NUM; ++i) { vm_vcpu_add_default(vm, i, guest_code); payloads[i].vm = vm; @@ -124,7 +124,7 @@ static void run_test(uint32_t run) check_set_affinity(throw_away, &cpu_set); } } - fprintf(stderr, "%s: [%d] all threads launched\n", __func__, run); + pr_debug("%s: [%d] all threads launched\n", __func__, run); sem_post(sem); for (i = 0; i < VCPU_NUM; ++i) check_join(threads[i], &b); @@ -147,16 +147,16 @@ int main(int argc, char **argv) if (pid == 0) run_test(i); /* This function always exits */ - fprintf(stderr, "%s: [%d] waiting semaphore\n", __func__, i); + pr_debug("%s: [%d] waiting semaphore\n", __func__, i); sem_wait(sem); r = (rand() % DELAY_US_MAX) + 1; - fprintf(stderr, "%s: [%d] waiting %dus\n", __func__, i, r); + pr_debug("%s: [%d] waiting %dus\n", __func__, i, r); usleep(r); r = waitpid(pid, &s, WNOHANG); TEST_ASSERT(r != pid, "%s: [%d] child exited unexpectedly status: [%d]", __func__, i, s); - fprintf(stderr, "%s: [%d] killing child\n", __func__, i); + pr_debug("%s: [%d] killing child\n", __func__, i); kill(pid, SIGKILL); } diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index ffbc4555c6e2..7f1d2765572c 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -80,19 +80,24 @@ static inline void check_tsc_msr_rdtsc(void) GUEST_ASSERT(delta_ns * 100 < (t2 - t1) * 100); } +static inline u64 get_tscpage_ts(struct ms_hyperv_tsc_page *tsc_page) +{ + return mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset; +} + static inline void check_tsc_msr_tsc_page(struct ms_hyperv_tsc_page *tsc_page) { u64 r1, r2, t1, t2; /* Compare TSC page clocksource with HV_X64_MSR_TIME_REF_COUNT */ - t1 = mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset; + t1 = get_tscpage_ts(tsc_page); r1 = rdmsr(HV_X64_MSR_TIME_REF_COUNT); /* 10 ms tolerance */ GUEST_ASSERT(r1 >= t1 && r1 - t1 < 100000); nop_loop(); - t2 = mul_u64_u64_shr64(rdtsc(), tsc_page->tsc_scale) + tsc_page->tsc_offset; + t2 = get_tscpage_ts(tsc_page); r2 = rdmsr(HV_X64_MSR_TIME_REF_COUNT); GUEST_ASSERT(r2 >= t1 && r2 - t2 < 100000); } @@ -130,7 +135,11 @@ static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_ tsc_offset = tsc_page->tsc_offset; /* Call KVM_SET_CLOCK from userspace, check that TSC page was updated */ + GUEST_SYNC(7); + /* Sanity check TSC page timestamp, it should be close to 0 */ + GUEST_ASSERT(get_tscpage_ts(tsc_page) < 100000); + GUEST_ASSERT(tsc_page->tsc_offset != tsc_offset); nop_loop(); diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index ce6bea9675c0..eb307ca37bfa 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -657,10 +657,21 @@ test_ecn_decap() { # In accordance with INET_ECN_decapsulate() __test_ecn_decap 00 00 0x00 + __test_ecn_decap 00 01 0x00 + __test_ecn_decap 00 02 0x00 + # 00 03 is tested in test_ecn_decap_error() + __test_ecn_decap 01 00 0x01 __test_ecn_decap 01 01 0x01 - __test_ecn_decap 02 01 0x02 + __test_ecn_decap 01 02 0x01 __test_ecn_decap 01 03 0x03 + __test_ecn_decap 02 00 0x02 + __test_ecn_decap 02 01 0x01 + __test_ecn_decap 02 02 0x02 __test_ecn_decap 02 03 0x03 + __test_ecn_decap 03 00 0x03 + __test_ecn_decap 03 01 0x03 + __test_ecn_decap 03 02 0x03 + __test_ecn_decap 03 03 0x03 test_ecn_decap_error } diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 964db9ed544f..ad32240fbfda 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -11,6 +11,7 @@ ksft_skip=4 timeout=30 mptcp_connect="" capture=0 +do_all_tests=1 TEST_COUNT=0 @@ -121,12 +122,6 @@ reset_with_add_addr_timeout() -j DROP } -for arg in "$@"; do - if [ "$arg" = "-c" ]; then - capture=1 - fi -done - ip -Version > /dev/null 2>&1 if [ $? -ne 0 ];then echo "SKIP: Could not run test without ip tool" @@ -1221,7 +1216,8 @@ usage() echo " -4 v4mapped_tests" echo " -b backup_tests" echo " -p add_addr_ports_tests" - echo " -c syncookies_tests" + echo " -k syncookies_tests" + echo " -c capture pcap files" echo " -h help" } @@ -1235,12 +1231,24 @@ make_file "$cin" "client" 1 make_file "$sin" "server" 1 trap cleanup EXIT -if [ -z $1 ]; then +for arg in "$@"; do + # check for "capture" arg before launching tests + if [[ "${arg}" =~ ^"-"[0-9a-zA-Z]*"c"[0-9a-zA-Z]*$ ]]; then + capture=1 + fi + + # exception for the capture option, the rest means: a part of the tests + if [ "${arg}" != "-c" ]; then + do_all_tests=0 + fi +done + +if [ $do_all_tests -eq 1 ]; then all_tests exit $ret fi -while getopts 'fsltra64bpch' opt; do +while getopts 'fsltra64bpkch' opt; do case $opt in f) subflows_tests @@ -1272,9 +1280,11 @@ while getopts 'fsltra64bpch' opt; do p) add_addr_ports_tests ;; - c) + k) syncookies_tests ;; + c) + ;; h | *) usage ;; diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c index 7b01b7c2ec10..066efd30e294 100644 --- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c +++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c @@ -30,25 +30,25 @@ struct reuse_opts { }; struct reuse_opts unreusable_opts[12] = { - {0, 0, 0, 0}, - {0, 0, 0, 1}, - {0, 0, 1, 0}, - {0, 0, 1, 1}, - {0, 1, 0, 0}, - {0, 1, 0, 1}, - {0, 1, 1, 0}, - {0, 1, 1, 1}, - {1, 0, 0, 0}, - {1, 0, 0, 1}, - {1, 0, 1, 0}, - {1, 0, 1, 1}, + {{0, 0}, {0, 0}}, + {{0, 0}, {0, 1}}, + {{0, 0}, {1, 0}}, + {{0, 0}, {1, 1}}, + {{0, 1}, {0, 0}}, + {{0, 1}, {0, 1}}, + {{0, 1}, {1, 0}}, + {{0, 1}, {1, 1}}, + {{1, 0}, {0, 0}}, + {{1, 0}, {0, 1}}, + {{1, 0}, {1, 0}}, + {{1, 0}, {1, 1}}, }; struct reuse_opts reusable_opts[4] = { - {1, 1, 0, 0}, - {1, 1, 0, 1}, - {1, 1, 1, 0}, - {1, 1, 1, 1}, + {{1, 1}, {0, 0}}, + {{1, 1}, {0, 1}}, + {{1, 1}, {1, 0}}, + {{1, 1}, {1, 1}}, }; int bind_port(struct __test_metadata *_metadata, int reuseaddr, int reuseport) diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h index 592c1ccf4576..0bd73428d2f3 100644 --- a/tools/testing/selftests/sgx/defines.h +++ b/tools/testing/selftests/sgx/defines.h @@ -14,7 +14,7 @@ #define __aligned(x) __attribute__((__aligned__(x))) #define __packed __attribute__((packed)) -#include "../../../../arch/x86/kernel/cpu/sgx/arch.h" +#include "../../../../arch/x86/include/asm/sgx.h" #include "../../../../arch/x86/include/asm/enclu.h" #include "../../../../arch/x86/include/uapi/asm/sgx.h" diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c index 9d43b75aaa55..f441ac34b4d4 100644 --- a/tools/testing/selftests/sgx/load.c +++ b/tools/testing/selftests/sgx/load.c @@ -45,19 +45,19 @@ static bool encl_map_bin(const char *path, struct encl *encl) fd = open(path, O_RDONLY); if (fd == -1) { - perror("open()"); + perror("enclave executable open()"); return false; } ret = stat(path, &sb); if (ret) { - perror("stat()"); + perror("enclave executable stat()"); goto err; } bin = mmap(NULL, sb.st_size, PROT_READ, MAP_PRIVATE, fd, 0); if (bin == MAP_FAILED) { - perror("mmap()"); + perror("enclave executable mmap()"); goto err; } @@ -90,8 +90,7 @@ static bool encl_ioc_create(struct encl *encl) ioc.src = (unsigned long)secs; rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_CREATE, &ioc); if (rc) { - fprintf(stderr, "SGX_IOC_ENCLAVE_CREATE failed: errno=%d\n", - errno); + perror("SGX_IOC_ENCLAVE_CREATE failed"); munmap((void *)secs->base, encl->encl_size); return false; } @@ -116,31 +115,72 @@ static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg) rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_ADD_PAGES, &ioc); if (rc < 0) { - fprintf(stderr, "SGX_IOC_ENCLAVE_ADD_PAGES failed: errno=%d.\n", - errno); + perror("SGX_IOC_ENCLAVE_ADD_PAGES failed"); return false; } return true; } + + bool encl_load(const char *path, struct encl *encl) { + const char device_path[] = "/dev/sgx_enclave"; Elf64_Phdr *phdr_tbl; off_t src_offset; Elf64_Ehdr *ehdr; + struct stat sb; + void *ptr; int i, j; int ret; + int fd = -1; memset(encl, 0, sizeof(*encl)); - ret = open("/dev/sgx_enclave", O_RDWR); - if (ret < 0) { - fprintf(stderr, "Unable to open /dev/sgx_enclave\n"); + fd = open(device_path, O_RDWR); + if (fd < 0) { + perror("Unable to open /dev/sgx_enclave"); + goto err; + } + + ret = stat(device_path, &sb); + if (ret) { + perror("device file stat()"); + goto err; + } + + /* + * This just checks if the /dev file has these permission + * bits set. It does not check that the current user is + * the owner or in the owning group. + */ + if (!(sb.st_mode & (S_IXUSR | S_IXGRP | S_IXOTH))) { + fprintf(stderr, "no execute permissions on device file %s\n", device_path); + goto err; + } + + ptr = mmap(NULL, PAGE_SIZE, PROT_READ, MAP_SHARED, fd, 0); + if (ptr == (void *)-1) { + perror("mmap for read"); + goto err; + } + munmap(ptr, PAGE_SIZE); + +#define ERR_MSG \ +"mmap() succeeded for PROT_READ, but failed for PROT_EXEC.\n" \ +" Check that current user has execute permissions on %s and \n" \ +" that /dev does not have noexec set: mount | grep \"/dev .*noexec\"\n" \ +" If so, remount it executable: mount -o remount,exec /dev\n\n" + + ptr = mmap(NULL, PAGE_SIZE, PROT_EXEC, MAP_SHARED, fd, 0); + if (ptr == (void *)-1) { + fprintf(stderr, ERR_MSG, device_path); goto err; } + munmap(ptr, PAGE_SIZE); - encl->fd = ret; + encl->fd = fd; if (!encl_map_bin(path, encl)) goto err; @@ -217,6 +257,8 @@ bool encl_load(const char *path, struct encl *encl) return true; err: + if (fd != -1) + close(fd); encl_delete(encl); return false; } @@ -229,7 +271,7 @@ static bool encl_map_area(struct encl *encl) area = mmap(NULL, encl_size * 2, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (area == MAP_FAILED) { - perror("mmap"); + perror("reservation mmap()"); return false; } @@ -268,8 +310,7 @@ bool encl_build(struct encl *encl) ioc.sigstruct = (uint64_t)&encl->sigstruct; ret = ioctl(encl->fd, SGX_IOC_ENCLAVE_INIT, &ioc); if (ret) { - fprintf(stderr, "SGX_IOC_ENCLAVE_INIT failed: errno=%d\n", - errno); + perror("SGX_IOC_ENCLAVE_INIT failed"); return false; } diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c index 724cec700926..d304a4044eb9 100644 --- a/tools/testing/selftests/sgx/main.c +++ b/tools/testing/selftests/sgx/main.c @@ -15,6 +15,7 @@ #include <sys/stat.h> #include <sys/time.h> #include <sys/types.h> +#include <sys/auxv.h> #include "defines.h" #include "main.h" #include "../kselftest.h" @@ -28,24 +29,6 @@ struct vdso_symtab { Elf64_Word *elf_hashtab; }; -static void *vdso_get_base_addr(char *envp[]) -{ - Elf64_auxv_t *auxv; - int i; - - for (i = 0; envp[i]; i++) - ; - - auxv = (Elf64_auxv_t *)&envp[i + 1]; - - for (i = 0; auxv[i].a_type != AT_NULL; i++) { - if (auxv[i].a_type == AT_SYSINFO_EHDR) - return (void *)auxv[i].a_un.a_val; - } - - return NULL; -} - static Elf64_Dyn *vdso_get_dyntab(void *addr) { Elf64_Ehdr *ehdr = addr; @@ -162,7 +145,7 @@ static int user_handler(long rdi, long rsi, long rdx, long ursp, long r8, long r return 0; } -int main(int argc, char *argv[], char *envp[]) +int main(int argc, char *argv[]) { struct sgx_enclave_run run; struct vdso_symtab symtab; @@ -195,7 +178,7 @@ int main(int argc, char *argv[], char *envp[]) addr = mmap((void *)encl.encl_base + seg->offset, seg->size, seg->prot, MAP_SHARED | MAP_FIXED, encl.fd, 0); if (addr == MAP_FAILED) { - fprintf(stderr, "mmap() failed, errno=%d.\n", errno); + perror("mmap() segment failed"); exit(KSFT_FAIL); } } @@ -203,7 +186,8 @@ int main(int argc, char *argv[], char *envp[]) memset(&run, 0, sizeof(run)); run.tcs = encl.encl_base; - addr = vdso_get_base_addr(envp); + /* Get vDSO base address */ + addr = (void *)getauxval(AT_SYSINFO_EHDR); if (!addr) goto err; diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index d42115e4284d..8b0cd421ebd3 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -101,7 +101,7 @@ endef ifeq ($(CAN_BUILD_I386),1) $(BINARIES_32): CFLAGS += -m32 $(BINARIES_32): LDLIBS += -lrt -ldl -lm -$(BINARIES_32): %_32: %.c +$(BINARIES_32): $(OUTPUT)/%_32: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t)))) endif @@ -109,7 +109,7 @@ endif ifeq ($(CAN_BUILD_X86_64),1) $(BINARIES_64): CFLAGS += -m64 $(BINARIES_64): LDLIBS += -lrt -ldl -$(BINARIES_64): %_64: %.c +$(BINARIES_64): $(OUTPUT)/%_64: %.c $(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@ $(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t)))) endif diff --git a/tools/testing/selftests/x86/thunks_32.S b/tools/testing/selftests/x86/thunks_32.S index a71d92da8f46..f3f56e681e9f 100644 --- a/tools/testing/selftests/x86/thunks_32.S +++ b/tools/testing/selftests/x86/thunks_32.S @@ -45,3 +45,5 @@ call64_from_32: ret .size call64_from_32, .-call64_from_32 + +.section .note.GNU-stack,"",%progbits |