diff options
281 files changed, 3251 insertions, 1213 deletions
@@ -187,6 +187,8 @@ Jiri Slaby <jirislaby@kernel.org> <jslaby@novell.com> Jiri Slaby <jirislaby@kernel.org> <jslaby@suse.com> Jiri Slaby <jirislaby@kernel.org> <jslaby@suse.cz> Jiri Slaby <jirislaby@kernel.org> <xslaby@fi.muni.cz> +Jisheng Zhang <jszhang@kernel.org> <jszhang@marvell.com> +Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com> 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> @@ -216,6 +218,7 @@ Koushik <raghavendra.koushik@neterion.com> Krishna Manikandan <quic_mkrishn@quicinc.com> <mkrishn@codeaurora.org> Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski.k@gmail.com> Krzysztof Kozlowski <krzk@kernel.org> <k.kozlowski@samsung.com> +Krzysztof Kozlowski <krzk@kernel.org> <krzysztof.kozlowski@canonical.com> Kuninori Morimoto <kuninori.morimoto.gx@renesas.com> Kuogee Hsieh <quic_khsieh@quicinc.com> <khsieh@codeaurora.org> Leonardo Bras <leobras.c@gmail.com> <leonardo@linux.ibm.com> diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst index a2b22d5640ec..9e9556826450 100644 --- a/Documentation/admin-guide/hw-vuln/spectre.rst +++ b/Documentation/admin-guide/hw-vuln/spectre.rst @@ -60,8 +60,8 @@ privileged data touched during the speculative execution. Spectre variant 1 attacks take advantage of speculative execution of conditional branches, while Spectre variant 2 attacks use speculative execution of indirect branches to leak privileged memory. -See :ref:`[1] <spec_ref1>` :ref:`[5] <spec_ref5>` :ref:`[7] <spec_ref7>` -:ref:`[10] <spec_ref10>` :ref:`[11] <spec_ref11>`. +See :ref:`[1] <spec_ref1>` :ref:`[5] <spec_ref5>` :ref:`[6] <spec_ref6>` +:ref:`[7] <spec_ref7>` :ref:`[10] <spec_ref10>` :ref:`[11] <spec_ref11>`. Spectre variant 1 (Bounds Check Bypass) --------------------------------------- @@ -131,6 +131,19 @@ steer its indirect branch speculations to gadget code, and measure the speculative execution's side effects left in level 1 cache to infer the victim's data. +Yet another variant 2 attack vector is for the attacker to poison the +Branch History Buffer (BHB) to speculatively steer an indirect branch +to a specific Branch Target Buffer (BTB) entry, even if the entry isn't +associated with the source address of the indirect branch. Specifically, +the BHB might be shared across privilege levels even in the presence of +Enhanced IBRS. + +Currently the only known real-world BHB attack vector is via +unprivileged eBPF. Therefore, it's highly recommended to not enable +unprivileged eBPF, especially when eIBRS is used (without retpolines). +For a full mitigation against BHB attacks, it's recommended to use +retpolines (or eIBRS combined with retpolines). + Attack scenarios ---------------- @@ -364,13 +377,15 @@ The possible values in this file are: - Kernel status: - ==================================== ================================= - 'Not affected' The processor is not vulnerable - 'Vulnerable' Vulnerable, no mitigation - 'Mitigation: Full generic retpoline' Software-focused mitigation - 'Mitigation: Full AMD retpoline' AMD-specific software mitigation - 'Mitigation: Enhanced IBRS' Hardware-focused mitigation - ==================================== ================================= + ======================================== ================================= + 'Not affected' The processor is not vulnerable + 'Mitigation: None' Vulnerable, no mitigation + 'Mitigation: Retpolines' Use Retpoline thunks + 'Mitigation: LFENCE' Use LFENCE instructions + 'Mitigation: Enhanced IBRS' Hardware-focused mitigation + 'Mitigation: Enhanced IBRS + Retpolines' Hardware-focused + Retpolines + 'Mitigation: Enhanced IBRS + LFENCE' Hardware-focused + LFENCE + ======================================== ================================= - Firmware status: Show if Indirect Branch Restricted Speculation (IBRS) is used to protect against Spectre variant 2 attacks when calling firmware (x86 only). @@ -583,12 +598,13 @@ kernel command line. Specific mitigations can also be selected manually: - retpoline - replace indirect branches - retpoline,generic - google's original retpoline - retpoline,amd - AMD-specific minimal thunk + retpoline auto pick between generic,lfence + retpoline,generic Retpolines + retpoline,lfence LFENCE; indirect branch + retpoline,amd alias for retpoline,lfence + eibrs enhanced IBRS + eibrs,retpoline enhanced IBRS + Retpolines + eibrs,lfence enhanced IBRS + LFENCE Not specifying this option is equivalent to spectre_v2=auto. @@ -599,7 +615,7 @@ kernel command line. spectre_v2=off. Spectre variant 1 mitigations cannot be disabled. -For spectre_v2_user see :doc:`/admin-guide/kernel-parameters`. +For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt Mitigation selection guide -------------------------- @@ -681,7 +697,7 @@ AMD white papers: .. _spec_ref6: -[6] `Software techniques for managing speculation on AMD processors <https://developer.amd.com/wp-content/resources/90343-B_SoftwareTechniquesforManagingSpeculation_WP_7-18Update_FNL.pdf>`_. +[6] `Software techniques for managing speculation on AMD processors <https://developer.amd.com/wp-content/resources/Managing-Speculation-on-AMD-Processors.pdf>`_. ARM white papers: diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index f5a27f067db9..7123524a86b8 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -5361,8 +5361,12 @@ Specific mitigations can also be selected manually: retpoline - replace indirect branches - retpoline,generic - google's original retpoline - retpoline,amd - AMD-specific minimal thunk + retpoline,generic - Retpolines + retpoline,lfence - LFENCE; indirect branch + retpoline,amd - alias for retpoline,lfence + eibrs - enhanced IBRS + eibrs,retpoline - enhanced IBRS + Retpolines + eibrs,lfence - enhanced IBRS + LFENCE Not specifying this option is equivalent to spectre_v2=auto. diff --git a/Documentation/admin-guide/mm/pagemap.rst b/Documentation/admin-guide/mm/pagemap.rst index bfc28704856c..6e2e416af783 100644 --- a/Documentation/admin-guide/mm/pagemap.rst +++ b/Documentation/admin-guide/mm/pagemap.rst @@ -23,7 +23,7 @@ There are four components to pagemap: * Bit 56 page exclusively mapped (since 4.2) * Bit 57 pte is uffd-wp write-protected (since 5.13) (see :ref:`Documentation/admin-guide/mm/userfaultfd.rst <userfaultfd>`) - * Bits 57-60 zero + * Bits 58-60 zero * Bit 61 page is file-page or shared-anon (since 3.5) * Bit 62 page swapped * Bit 63 page present diff --git a/Documentation/core-api/dma-attributes.rst b/Documentation/core-api/dma-attributes.rst index 17706dc91ec9..1887d92e8e92 100644 --- a/Documentation/core-api/dma-attributes.rst +++ b/Documentation/core-api/dma-attributes.rst @@ -130,11 +130,3 @@ accesses to DMA buffers in both privileged "supervisor" and unprivileged subsystem that the buffer is fully accessible at the elevated privilege level (and ideally inaccessible or at least read-only at the lesser-privileged levels). - -DMA_ATTR_OVERWRITE ------------------- - -This is a hint to the DMA-mapping subsystem that the device is expected to -overwrite the entire mapped size, thus the caller does not require any of the -previous buffer contents to be preserved. This allows bounce-buffering -implementations to optimise DMA_FROM_DEVICE transfers. diff --git a/Documentation/devicetree/bindings/arm/qcom.yaml b/Documentation/devicetree/bindings/arm/qcom.yaml index 370aab274cd1..04ff0b55bb85 100644 --- a/Documentation/devicetree/bindings/arm/qcom.yaml +++ b/Documentation/devicetree/bindings/arm/qcom.yaml @@ -48,7 +48,6 @@ description: | sdx65 sm7225 sm8150 - sdx65 sm8250 sm8350 sm8450 @@ -230,11 +229,6 @@ properties: - items: - enum: - - qcom,sdx65-mtp - - const: qcom,sdx65 - - - items: - - enum: - qcom,ipq6018-cp01 - qcom,ipq6018-cp01-c1 - const: qcom,ipq6018 diff --git a/Documentation/devicetree/bindings/display/bridge/analogix,anx7625.yaml b/Documentation/devicetree/bindings/display/bridge/analogix,anx7625.yaml index 1d3e88daca04..25b5ef3f759c 100644 --- a/Documentation/devicetree/bindings/display/bridge/analogix,anx7625.yaml +++ b/Documentation/devicetree/bindings/display/bridge/analogix,anx7625.yaml @@ -91,22 +91,7 @@ properties: $ref: /schemas/graph.yaml#/$defs/port-base unevaluatedProperties: false description: - MIPI DSI/DPI input. - - properties: - endpoint: - $ref: /schemas/media/video-interfaces.yaml# - type: object - additionalProperties: false - - properties: - remote-endpoint: true - - bus-type: - enum: [1, 5] - default: 1 - - data-lanes: true + Video port for MIPI DSI input. port@1: $ref: /schemas/graph.yaml#/properties/port @@ -155,8 +140,6 @@ examples: reg = <0>; anx7625_in: endpoint { remote-endpoint = <&mipi_dsi>; - bus-type = <5>; - data-lanes = <0 1 2 3>; }; }; diff --git a/Documentation/devicetree/bindings/mfd/brcm,cru.yaml b/Documentation/devicetree/bindings/mfd/brcm,cru.yaml index be4a2df71c25..b85819fbb07c 100644 --- a/Documentation/devicetree/bindings/mfd/brcm,cru.yaml +++ b/Documentation/devicetree/bindings/mfd/brcm,cru.yaml @@ -39,7 +39,7 @@ patternProperties: '^phy@[a-f0-9]+$': $ref: ../phy/bcm-ns-usb2-phy.yaml - '^pin-controller@[a-f0-9]+$': + '^pinctrl@[a-f0-9]+$': $ref: ../pinctrl/brcm,ns-pinmux.yaml '^syscon@[a-f0-9]+$': @@ -94,7 +94,7 @@ examples: reg = <0x180 0x4>; }; - pin-controller@1c0 { + pinctrl@1c0 { compatible = "brcm,bcm4708-pinmux"; reg = <0x1c0 0x24>; reg-names = "cru_gpio_control"; diff --git a/Documentation/devicetree/bindings/mfd/cirrus,lochnagar.yaml b/Documentation/devicetree/bindings/mfd/cirrus,lochnagar.yaml index c00ad3e21c21..ad285cb480c9 100644 --- a/Documentation/devicetree/bindings/mfd/cirrus,lochnagar.yaml +++ b/Documentation/devicetree/bindings/mfd/cirrus,lochnagar.yaml @@ -126,7 +126,7 @@ properties: clock-frequency: const: 12288000 - lochnagar-pinctrl: + pinctrl: type: object $ref: /schemas/pinctrl/cirrus,lochnagar.yaml# @@ -255,7 +255,7 @@ required: - reg - reset-gpios - lochnagar-clk - - lochnagar-pinctrl + - pinctrl additionalProperties: false @@ -293,7 +293,7 @@ examples: clock-frequency = <32768>; }; - lochnagar-pinctrl { + pinctrl { compatible = "cirrus,lochnagar-pinctrl"; gpio-controller; diff --git a/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml b/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml index 6107880e5246..02b76f15e717 100644 --- a/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml +++ b/Documentation/devicetree/bindings/phy/ti,tcan104x-can.yaml @@ -37,6 +37,12 @@ properties: max bit rate supported in bps minimum: 1 + mux-states: + description: + mux controller node to route the signals from controller to + transceiver. + maxItems: 1 + required: - compatible - '#phy-cells' @@ -53,4 +59,5 @@ examples: max-bitrate = <5000000>; standby-gpios = <&wakeup_gpio1 16 GPIO_ACTIVE_LOW>; enable-gpios = <&main_gpio1 67 GPIO_ACTIVE_HIGH>; + mux-states = <&mux0 1>; }; diff --git a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml index c85f759ae5a3..8a90d8273767 100644 --- a/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml +++ b/Documentation/devicetree/bindings/pinctrl/cirrus,madera.yaml @@ -107,9 +107,6 @@ properties: additionalProperties: false -allOf: - - $ref: "pinctrl.yaml#" - required: - pinctrl-0 - pinctrl-names diff --git a/MAINTAINERS b/MAINTAINERS index 9c439a10b02f..76a79c258743 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2572,7 +2572,7 @@ F: sound/soc/rockchip/ N: rockchip ARM/SAMSUNG S3C, S5P AND EXYNOS ARM ARCHITECTURES -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-samsung-soc@vger.kernel.org @@ -2739,7 +2739,7 @@ N: stm32 N: stm ARM/Synaptics SoC support -M: Jisheng Zhang <Jisheng.Zhang@synaptics.com> +M: Jisheng Zhang <jszhang@kernel.org> M: Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained @@ -3907,7 +3907,7 @@ M: Scott Branden <sbranden@broadcom.com> M: bcm-kernel-feedback-list@broadcom.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://github.com/broadcom/cygnus-linux.git +T: git git://github.com/broadcom/stblinux.git F: arch/arm64/boot/dts/broadcom/northstar2/* F: arch/arm64/boot/dts/broadcom/stingray/* F: drivers/clk/bcm/clk-ns* @@ -11683,7 +11683,7 @@ F: drivers/iio/proximity/mb1232.c MAXIM MAX17040 FAMILY FUEL GAUGE DRIVERS R: Iskren Chernev <iskren.chernev@gmail.com> -R: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +R: Krzysztof Kozlowski <krzk@kernel.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Matheus Castello <matheus@castello.eng.br> L: linux-pm@vger.kernel.org @@ -11693,7 +11693,7 @@ F: drivers/power/supply/max17040_battery.c MAXIM MAX17042 FAMILY FUEL GAUGE DRIVERS R: Hans de Goede <hdegoede@redhat.com> -R: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +R: Krzysztof Kozlowski <krzk@kernel.org> R: Marek Szyprowski <m.szyprowski@samsung.com> R: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm> R: Purism Kernel Team <kernel@puri.sm> @@ -11738,7 +11738,7 @@ F: Documentation/devicetree/bindings/power/supply/maxim,max77976.yaml F: drivers/power/supply/max77976_charger.c MAXIM MUIC CHARGER DRIVERS FOR EXYNOS BASED BOARDS -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-pm@vger.kernel.org S: Supported @@ -11747,7 +11747,7 @@ F: drivers/power/supply/max77693_charger.c MAXIM PMIC AND MUIC DRIVERS FOR EXYNOS BASED BOARDS M: Chanwoo Choi <cw00.choi@samsung.com> -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org S: Supported @@ -12436,7 +12436,7 @@ F: include/linux/memblock.h F: mm/memblock.c MEMORY CONTROLLER DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/krzk/linux-mem-ctrl.git @@ -13573,7 +13573,7 @@ F: include/uapi/linux/nexthop.h F: net/ipv4/nexthop.c NFC SUBSYSTEM -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-nfc@lists.01.org (subscribers-only) L: netdev@vger.kernel.org S: Maintained @@ -13887,7 +13887,7 @@ F: Documentation/devicetree/bindings/regulator/nxp,pf8x00-regulator.yaml F: drivers/regulator/pf8x00-regulator.c NXP PTN5150A CC LOGIC AND EXTCON DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-kernel@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/extcon/extcon-ptn5150.yaml @@ -15313,7 +15313,7 @@ F: drivers/pinctrl/renesas/ PIN CONTROLLER - SAMSUNG M: Tomasz Figa <tomasz.figa@gmail.com> -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> R: Alim Akhtar <alim.akhtar@samsung.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -16954,7 +16954,7 @@ W: http://www.ibm.com/developerworks/linux/linux390/ F: drivers/s390/scsi/zfcp_* S3C ADC BATTERY DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-samsung-soc@vger.kernel.org S: Odd Fixes F: drivers/power/supply/s3c_adc_battery.c @@ -16999,7 +16999,7 @@ F: Documentation/admin-guide/LSM/SafeSetID.rst F: security/safesetid/ SAMSUNG AUDIO (ASoC) DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Sylwester Nawrocki <s.nawrocki@samsung.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Supported @@ -17007,7 +17007,7 @@ F: Documentation/devicetree/bindings/sound/samsung* F: sound/soc/samsung/ SAMSUNG EXYNOS PSEUDO RANDOM NUMBER GENERATOR (RNG) DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org S: Maintained @@ -17042,7 +17042,7 @@ S: Maintained F: drivers/platform/x86/samsung-laptop.c SAMSUNG MULTIFUNCTION PMIC DEVICE DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> L: linux-kernel@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -17068,7 +17068,7 @@ F: drivers/media/platform/s3c-camif/ F: include/media/drv-intf/s3c_camif.h SAMSUNG S3FWRN5 NFC DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Krzysztof Opasiak <k.opasiak@samsung.com> L: linux-nfc@lists.01.org (subscribers-only) S: Maintained @@ -17090,7 +17090,7 @@ S: Supported F: drivers/media/i2c/s5k5baf.c SAMSUNG S5P Security SubSystem (SSS) DRIVER -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Vladimir Zapolskiy <vz@mleia.com> L: linux-crypto@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -17125,7 +17125,7 @@ F: include/linux/clk/samsung.h F: include/linux/platform_data/clk-s3c2410.h SAMSUNG SPI DRIVERS -M: Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com> +M: Krzysztof Kozlowski <krzk@kernel.org> M: Andi Shyti <andi@etezian.org> L: linux-spi@vger.kernel.org L: linux-samsung-soc@vger.kernel.org @@ -21475,7 +21475,6 @@ THE REST M: Linus Torvalds <torvalds@linux-foundation.org> L: linux-kernel@vger.kernel.org S: Buried alive in reporters -Q: http://patchwork.kernel.org/project/LKML/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git F: * F: */ @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = -rc7 NAME = Superb Owl # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi index 6dde51c2aed3..e4775bbceecc 100644 --- a/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi +++ b/arch/arm/boot/dts/aspeed-g6-pinctrl.dtsi @@ -118,7 +118,7 @@ }; pinctrl_fwqspid_default: fwqspid_default { - function = "FWQSPID"; + function = "FWSPID"; groups = "FWQSPID"; }; diff --git a/arch/arm/boot/dts/bcm2711.dtsi b/arch/arm/boot/dts/bcm2711.dtsi index dff18fc9a906..21294f775a20 100644 --- a/arch/arm/boot/dts/bcm2711.dtsi +++ b/arch/arm/boot/dts/bcm2711.dtsi @@ -290,6 +290,7 @@ hvs: hvs@7e400000 { compatible = "brcm,bcm2711-hvs"; + reg = <0x7e400000 0x8000>; interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>; }; diff --git a/arch/arm/boot/dts/tegra124-nyan-big-fhd.dts b/arch/arm/boot/dts/tegra124-nyan-big-fhd.dts index d35fb79d2f51..4db43324dafa 100644 --- a/arch/arm/boot/dts/tegra124-nyan-big-fhd.dts +++ b/arch/arm/boot/dts/tegra124-nyan-big-fhd.dts @@ -5,7 +5,13 @@ / { /* Version of Nyan Big with 1080p panel */ - panel { - compatible = "auo,b133htn01"; + host1x@50000000 { + dpaux@545c0000 { + aux-bus { + panel: panel { + compatible = "auo,b133htn01"; + }; + }; + }; }; }; diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h index 6fe67963ba5a..aee73ef5b3dc 100644 --- a/arch/arm/include/asm/assembler.h +++ b/arch/arm/include/asm/assembler.h @@ -107,6 +107,16 @@ .endm #endif +#if __LINUX_ARM_ARCH__ < 7 + .macro dsb, args + mcr p15, 0, r0, c7, c10, 4 + .endm + + .macro isb, args + mcr p15, 0, r0, c7, c5, 4 + .endm +#endif + .macro asm_trace_hardirqs_off, save=1 #if defined(CONFIG_TRACE_IRQFLAGS) .if \save diff --git a/arch/arm/include/asm/spectre.h b/arch/arm/include/asm/spectre.h new file mode 100644 index 000000000000..d1fa5607d3aa --- /dev/null +++ b/arch/arm/include/asm/spectre.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_SPECTRE_H +#define __ASM_SPECTRE_H + +enum { + SPECTRE_UNAFFECTED, + SPECTRE_MITIGATED, + SPECTRE_VULNERABLE, +}; + +enum { + __SPECTRE_V2_METHOD_BPIALL, + __SPECTRE_V2_METHOD_ICIALLU, + __SPECTRE_V2_METHOD_SMC, + __SPECTRE_V2_METHOD_HVC, + __SPECTRE_V2_METHOD_LOOP8, +}; + +enum { + SPECTRE_V2_METHOD_BPIALL = BIT(__SPECTRE_V2_METHOD_BPIALL), + SPECTRE_V2_METHOD_ICIALLU = BIT(__SPECTRE_V2_METHOD_ICIALLU), + SPECTRE_V2_METHOD_SMC = BIT(__SPECTRE_V2_METHOD_SMC), + SPECTRE_V2_METHOD_HVC = BIT(__SPECTRE_V2_METHOD_HVC), + SPECTRE_V2_METHOD_LOOP8 = BIT(__SPECTRE_V2_METHOD_LOOP8), +}; + +void spectre_v2_update_state(unsigned int state, unsigned int methods); + +int spectre_bhb_update_vectors(unsigned int method); + +#endif diff --git a/arch/arm/include/asm/vmlinux.lds.h b/arch/arm/include/asm/vmlinux.lds.h index 4a91428c324d..fad45c884e98 100644 --- a/arch/arm/include/asm/vmlinux.lds.h +++ b/arch/arm/include/asm/vmlinux.lds.h @@ -26,6 +26,19 @@ #define ARM_MMU_DISCARD(x) x #endif +/* + * ld.lld does not support NOCROSSREFS: + * https://github.com/ClangBuiltLinux/linux/issues/1609 + */ +#ifdef CONFIG_LD_IS_LLD +#define NOCROSSREFS +#endif + +/* Set start/end symbol names to the LMA for the section */ +#define ARM_LMA(sym, section) \ + sym##_start = LOADADDR(section); \ + sym##_end = LOADADDR(section) + SIZEOF(section) + #define PROC_INFO \ . = ALIGN(4); \ __proc_info_begin = .; \ @@ -110,19 +123,31 @@ * only thing that matters is their relative offsets */ #define ARM_VECTORS \ - __vectors_start = .; \ - .vectors 0xffff0000 : AT(__vectors_start) { \ - *(.vectors) \ + __vectors_lma = .; \ + OVERLAY 0xffff0000 : NOCROSSREFS AT(__vectors_lma) { \ + .vectors { \ + *(.vectors) \ + } \ + .vectors.bhb.loop8 { \ + *(.vectors.bhb.loop8) \ + } \ + .vectors.bhb.bpiall { \ + *(.vectors.bhb.bpiall) \ + } \ } \ - . = __vectors_start + SIZEOF(.vectors); \ - __vectors_end = .; \ + ARM_LMA(__vectors, .vectors); \ + ARM_LMA(__vectors_bhb_loop8, .vectors.bhb.loop8); \ + ARM_LMA(__vectors_bhb_bpiall, .vectors.bhb.bpiall); \ + . = __vectors_lma + SIZEOF(.vectors) + \ + SIZEOF(.vectors.bhb.loop8) + \ + SIZEOF(.vectors.bhb.bpiall); \ \ - __stubs_start = .; \ - .stubs ADDR(.vectors) + 0x1000 : AT(__stubs_start) { \ + __stubs_lma = .; \ + .stubs ADDR(.vectors) + 0x1000 : AT(__stubs_lma) { \ *(.stubs) \ } \ - . = __stubs_start + SIZEOF(.stubs); \ - __stubs_end = .; \ + ARM_LMA(__stubs, .stubs); \ + . = __stubs_lma + SIZEOF(.stubs); \ \ PROVIDE(vector_fiq_offset = vector_fiq - ADDR(.vectors)); diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index ae295a3bcfef..6ef3b535b7bf 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -106,4 +106,6 @@ endif obj-$(CONFIG_HAVE_ARM_SMCCC) += smccc-call.o +obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += spectre.o + extra-y := $(head-y) vmlinux.lds diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S index 5cd057859fe9..676703cbfe4b 100644 --- a/arch/arm/kernel/entry-armv.S +++ b/arch/arm/kernel/entry-armv.S @@ -1002,12 +1002,11 @@ vector_\name: sub lr, lr, #\correction .endif - @ - @ Save r0, lr_<exception> (parent PC) and spsr_<exception> - @ (parent CPSR) - @ + @ Save r0, lr_<exception> (parent PC) stmia sp, {r0, lr} @ save r0, lr - mrs lr, spsr + + @ Save spsr_<exception> (parent CPSR) +2: mrs lr, spsr str lr, [sp, #8] @ save spsr @ @@ -1028,6 +1027,44 @@ vector_\name: movs pc, lr @ branch to handler in SVC mode ENDPROC(vector_\name) +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .subsection 1 + .align 5 +vector_bhb_loop8_\name: + .if \correction + sub lr, lr, #\correction + .endif + + @ Save r0, lr_<exception> (parent PC) + stmia sp, {r0, lr} + + @ bhb workaround + mov r0, #8 +1: b . + 4 + subs r0, r0, #1 + bne 1b + dsb + isb + b 2b +ENDPROC(vector_bhb_loop8_\name) + +vector_bhb_bpiall_\name: + .if \correction + sub lr, lr, #\correction + .endif + + @ Save r0, lr_<exception> (parent PC) + stmia sp, {r0, lr} + + @ bhb workaround + mcr p15, 0, r0, c7, c5, 6 @ BPIALL + @ isb not needed due to "movs pc, lr" in the vector stub + @ which gives a "context synchronisation". + b 2b +ENDPROC(vector_bhb_bpiall_\name) + .previous +#endif + .align 2 @ handler addresses follow this label 1: @@ -1036,6 +1073,10 @@ ENDPROC(vector_\name) .section .stubs, "ax", %progbits @ This must be the first word .word vector_swi +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .word vector_bhb_loop8_swi + .word vector_bhb_bpiall_swi +#endif vector_rst: ARM( swi SYS_ERROR0 ) @@ -1150,8 +1191,10 @@ vector_addrexcptn: * FIQ "NMI" handler *----------------------------------------------------------------------------- * Handle a FIQ using the SVC stack allowing FIQ act like NMI on x86 - * systems. + * systems. This must be the last vector stub, so lets place it in its own + * subsection. */ + .subsection 2 vector_stub fiq, FIQ_MODE, 4 .long __fiq_usr @ 0 (USR_26 / USR_32) @@ -1184,6 +1227,30 @@ vector_addrexcptn: W(b) vector_irq W(b) vector_fiq +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .section .vectors.bhb.loop8, "ax", %progbits +.L__vectors_bhb_loop8_start: + W(b) vector_rst + W(b) vector_bhb_loop8_und + W(ldr) pc, .L__vectors_bhb_loop8_start + 0x1004 + W(b) vector_bhb_loop8_pabt + W(b) vector_bhb_loop8_dabt + W(b) vector_addrexcptn + W(b) vector_bhb_loop8_irq + W(b) vector_bhb_loop8_fiq + + .section .vectors.bhb.bpiall, "ax", %progbits +.L__vectors_bhb_bpiall_start: + W(b) vector_rst + W(b) vector_bhb_bpiall_und + W(ldr) pc, .L__vectors_bhb_bpiall_start + 0x1008 + W(b) vector_bhb_bpiall_pabt + W(b) vector_bhb_bpiall_dabt + W(b) vector_addrexcptn + W(b) vector_bhb_bpiall_irq + W(b) vector_bhb_bpiall_fiq +#endif + .data .align 2 diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index ac86c34682bb..dbc1913ee30b 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -154,12 +154,36 @@ ENDPROC(ret_from_fork) */ .align 5 +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +ENTRY(vector_bhb_loop8_swi) + sub sp, sp, #PT_REGS_SIZE + stmia sp, {r0 - r12} + mov r8, #8 +1: b 2f +2: subs r8, r8, #1 + bne 1b + dsb + isb + b 3f +ENDPROC(vector_bhb_loop8_swi) + + .align 5 +ENTRY(vector_bhb_bpiall_swi) + sub sp, sp, #PT_REGS_SIZE + stmia sp, {r0 - r12} + mcr p15, 0, r8, c7, c5, 6 @ BPIALL + isb + b 3f +ENDPROC(vector_bhb_bpiall_swi) +#endif + .align 5 ENTRY(vector_swi) #ifdef CONFIG_CPU_V7M v7m_exception_entry #else sub sp, sp, #PT_REGS_SIZE stmia sp, {r0 - r12} @ Calling r0 - r12 +3: ARM( add r8, sp, #S_PC ) ARM( stmdb r8, {sp, lr}^ ) @ Calling sp, lr THUMB( mov r8, sp ) diff --git a/arch/arm/kernel/spectre.c b/arch/arm/kernel/spectre.c new file mode 100644 index 000000000000..0dcefc36fb7a --- /dev/null +++ b/arch/arm/kernel/spectre.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/bpf.h> +#include <linux/cpu.h> +#include <linux/device.h> + +#include <asm/spectre.h> + +static bool _unprivileged_ebpf_enabled(void) +{ +#ifdef CONFIG_BPF_SYSCALL + return !sysctl_unprivileged_bpf_disabled; +#else + return false; +#endif +} + +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); +} + +static unsigned int spectre_v2_state; +static unsigned int spectre_v2_methods; + +void spectre_v2_update_state(unsigned int state, unsigned int method) +{ + if (state > spectre_v2_state) + spectre_v2_state = state; + spectre_v2_methods |= method; +} + +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, + char *buf) +{ + const char *method; + + if (spectre_v2_state == SPECTRE_UNAFFECTED) + return sprintf(buf, "%s\n", "Not affected"); + + if (spectre_v2_state != SPECTRE_MITIGATED) + return sprintf(buf, "%s\n", "Vulnerable"); + + if (_unprivileged_ebpf_enabled()) + return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n"); + + switch (spectre_v2_methods) { + case SPECTRE_V2_METHOD_BPIALL: + method = "Branch predictor hardening"; + break; + + case SPECTRE_V2_METHOD_ICIALLU: + method = "I-cache invalidation"; + break; + + case SPECTRE_V2_METHOD_SMC: + case SPECTRE_V2_METHOD_HVC: + method = "Firmware call"; + break; + + case SPECTRE_V2_METHOD_LOOP8: + method = "History overwrite"; + break; + + default: + method = "Multiple mitigations"; + break; + } + + return sprintf(buf, "Mitigation: %s\n", method); +} diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index da04ed85855a..cae4a748811f 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -30,6 +30,7 @@ #include <linux/atomic.h> #include <asm/cacheflush.h> #include <asm/exception.h> +#include <asm/spectre.h> #include <asm/unistd.h> #include <asm/traps.h> #include <asm/ptrace.h> @@ -789,10 +790,59 @@ static inline void __init kuser_init(void *vectors) } #endif +#ifndef CONFIG_CPU_V7M +static void copy_from_lma(void *vma, void *lma_start, void *lma_end) +{ + memcpy(vma, lma_start, lma_end - lma_start); +} + +static void flush_vectors(void *vma, size_t offset, size_t size) +{ + unsigned long start = (unsigned long)vma + offset; + unsigned long end = start + size; + + flush_icache_range(start, end); +} + +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +int spectre_bhb_update_vectors(unsigned int method) +{ + extern char __vectors_bhb_bpiall_start[], __vectors_bhb_bpiall_end[]; + extern char __vectors_bhb_loop8_start[], __vectors_bhb_loop8_end[]; + void *vec_start, *vec_end; + + if (system_state >= SYSTEM_FREEING_INITMEM) { + pr_err("CPU%u: Spectre BHB workaround too late - system vulnerable\n", + smp_processor_id()); + return SPECTRE_VULNERABLE; + } + + switch (method) { + case SPECTRE_V2_METHOD_LOOP8: + vec_start = __vectors_bhb_loop8_start; + vec_end = __vectors_bhb_loop8_end; + break; + + case SPECTRE_V2_METHOD_BPIALL: + vec_start = __vectors_bhb_bpiall_start; + vec_end = __vectors_bhb_bpiall_end; + break; + + default: + pr_err("CPU%u: unknown Spectre BHB state %d\n", + smp_processor_id(), method); + return SPECTRE_VULNERABLE; + } + + copy_from_lma(vectors_page, vec_start, vec_end); + flush_vectors(vectors_page, 0, vec_end - vec_start); + + return SPECTRE_MITIGATED; +} +#endif + void __init early_trap_init(void *vectors_base) { -#ifndef CONFIG_CPU_V7M - unsigned long vectors = (unsigned long)vectors_base; extern char __stubs_start[], __stubs_end[]; extern char __vectors_start[], __vectors_end[]; unsigned i; @@ -813,17 +863,20 @@ void __init early_trap_init(void *vectors_base) * into the vector page, mapped at 0xffff0000, and ensure these * are visible to the instruction stream. */ - memcpy((void *)vectors, __vectors_start, __vectors_end - __vectors_start); - memcpy((void *)vectors + 0x1000, __stubs_start, __stubs_end - __stubs_start); + copy_from_lma(vectors_base, __vectors_start, __vectors_end); + copy_from_lma(vectors_base + 0x1000, __stubs_start, __stubs_end); kuser_init(vectors_base); - flush_icache_range(vectors, vectors + PAGE_SIZE * 2); + flush_vectors(vectors_base, 0, PAGE_SIZE * 2); +} #else /* ifndef CONFIG_CPU_V7M */ +void __init early_trap_init(void *vectors_base) +{ /* * on V7-M there is no need to copy the vector table to a dedicated * memory area. The address is configurable and so a table in the kernel * image can be used. */ -#endif } +#endif diff --git a/arch/arm/mach-mstar/Kconfig b/arch/arm/mach-mstar/Kconfig index cd300eeedc20..0bf4d312bcfd 100644 --- a/arch/arm/mach-mstar/Kconfig +++ b/arch/arm/mach-mstar/Kconfig @@ -3,6 +3,7 @@ menuconfig ARCH_MSTARV7 depends on ARCH_MULTI_V7 select ARM_GIC select ARM_HEAVY_MB + select HAVE_ARM_ARCH_TIMER select MST_IRQ select MSTAR_MSC313_MPLL help diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index 58afba346729..9724c16e9076 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -830,6 +830,7 @@ config CPU_BPREDICT_DISABLE config CPU_SPECTRE bool + select GENERIC_CPU_VULNERABILITIES config HARDEN_BRANCH_PREDICTOR bool "Harden the branch predictor against aliasing attacks" if EXPERT @@ -850,6 +851,16 @@ config HARDEN_BRANCH_PREDICTOR If unsure, say Y. +config HARDEN_BRANCH_HISTORY + bool "Harden Spectre style attacks against branch history" if EXPERT + depends on CPU_SPECTRE + default y + help + Speculation attacks against some high-performance processors can + make use of branch history to influence future speculation. When + taking an exception, a sequence of branches overwrites the branch + history, or branch history is invalidated. + config TLS_REG_EMUL bool select NEED_KUSER_HELPERS diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c index 114c05ab4dd9..06dbfb968182 100644 --- a/arch/arm/mm/proc-v7-bugs.c +++ b/arch/arm/mm/proc-v7-bugs.c @@ -6,8 +6,35 @@ #include <asm/cp15.h> #include <asm/cputype.h> #include <asm/proc-fns.h> +#include <asm/spectre.h> #include <asm/system_misc.h> +#ifdef CONFIG_ARM_PSCI +static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void) +{ + struct arm_smccc_res res; + + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_1, &res); + + switch ((int)res.a0) { + case SMCCC_RET_SUCCESS: + return SPECTRE_MITIGATED; + + case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED: + return SPECTRE_UNAFFECTED; + + default: + return SPECTRE_VULNERABLE; + } +} +#else +static int __maybe_unused spectre_v2_get_cpu_fw_mitigation_state(void) +{ + return SPECTRE_VULNERABLE; +} +#endif + #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR DEFINE_PER_CPU(harden_branch_predictor_fn_t, harden_branch_predictor_fn); @@ -36,13 +63,61 @@ static void __maybe_unused call_hvc_arch_workaround_1(void) arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_WORKAROUND_1, NULL); } -static void cpu_v7_spectre_init(void) +static unsigned int spectre_v2_install_workaround(unsigned int method) { const char *spectre_v2_method = NULL; int cpu = smp_processor_id(); if (per_cpu(harden_branch_predictor_fn, cpu)) - return; + return SPECTRE_MITIGATED; + + switch (method) { + case SPECTRE_V2_METHOD_BPIALL: + per_cpu(harden_branch_predictor_fn, cpu) = + harden_branch_predictor_bpiall; + spectre_v2_method = "BPIALL"; + break; + + case SPECTRE_V2_METHOD_ICIALLU: + per_cpu(harden_branch_predictor_fn, cpu) = + harden_branch_predictor_iciallu; + spectre_v2_method = "ICIALLU"; + break; + + case SPECTRE_V2_METHOD_HVC: + per_cpu(harden_branch_predictor_fn, cpu) = + call_hvc_arch_workaround_1; + cpu_do_switch_mm = cpu_v7_hvc_switch_mm; + spectre_v2_method = "hypervisor"; + break; + + case SPECTRE_V2_METHOD_SMC: + per_cpu(harden_branch_predictor_fn, cpu) = + call_smc_arch_workaround_1; + cpu_do_switch_mm = cpu_v7_smc_switch_mm; + spectre_v2_method = "firmware"; + break; + } + + if (spectre_v2_method) + pr_info("CPU%u: Spectre v2: using %s workaround\n", + smp_processor_id(), spectre_v2_method); + + return SPECTRE_MITIGATED; +} +#else +static unsigned int spectre_v2_install_workaround(unsigned int method) +{ + pr_info("CPU%u: Spectre V2: workarounds disabled by configuration\n", + smp_processor_id()); + + return SPECTRE_VULNERABLE; +} +#endif + +static void cpu_v7_spectre_v2_init(void) +{ + unsigned int state, method = 0; switch (read_cpuid_part()) { case ARM_CPU_PART_CORTEX_A8: @@ -51,69 +126,133 @@ static void cpu_v7_spectre_init(void) case ARM_CPU_PART_CORTEX_A17: case ARM_CPU_PART_CORTEX_A73: case ARM_CPU_PART_CORTEX_A75: - per_cpu(harden_branch_predictor_fn, cpu) = - harden_branch_predictor_bpiall; - spectre_v2_method = "BPIALL"; + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_BPIALL; break; case ARM_CPU_PART_CORTEX_A15: case ARM_CPU_PART_BRAHMA_B15: - per_cpu(harden_branch_predictor_fn, cpu) = - harden_branch_predictor_iciallu; - spectre_v2_method = "ICIALLU"; + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_ICIALLU; break; -#ifdef CONFIG_ARM_PSCI case ARM_CPU_PART_BRAHMA_B53: /* Requires no workaround */ + state = SPECTRE_UNAFFECTED; break; + default: /* Other ARM CPUs require no workaround */ - if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) + if (read_cpuid_implementor() == ARM_CPU_IMP_ARM) { + state = SPECTRE_UNAFFECTED; break; + } + fallthrough; - /* Cortex A57/A72 require firmware workaround */ - case ARM_CPU_PART_CORTEX_A57: - case ARM_CPU_PART_CORTEX_A72: { - struct arm_smccc_res res; - arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, - ARM_SMCCC_ARCH_WORKAROUND_1, &res); - if ((int)res.a0 != 0) - return; + /* Cortex A57/A72 require firmware workaround */ + case ARM_CPU_PART_CORTEX_A57: + case ARM_CPU_PART_CORTEX_A72: + state = spectre_v2_get_cpu_fw_mitigation_state(); + if (state != SPECTRE_MITIGATED) + break; switch (arm_smccc_1_1_get_conduit()) { case SMCCC_CONDUIT_HVC: - per_cpu(harden_branch_predictor_fn, cpu) = - call_hvc_arch_workaround_1; - cpu_do_switch_mm = cpu_v7_hvc_switch_mm; - spectre_v2_method = "hypervisor"; + method = SPECTRE_V2_METHOD_HVC; break; case SMCCC_CONDUIT_SMC: - per_cpu(harden_branch_predictor_fn, cpu) = - call_smc_arch_workaround_1; - cpu_do_switch_mm = cpu_v7_smc_switch_mm; - spectre_v2_method = "firmware"; + method = SPECTRE_V2_METHOD_SMC; break; default: + state = SPECTRE_VULNERABLE; break; } } -#endif + + if (state == SPECTRE_MITIGATED) + state = spectre_v2_install_workaround(method); + + spectre_v2_update_state(state, method); +} + +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +static int spectre_bhb_method; + +static const char *spectre_bhb_method_name(int method) +{ + switch (method) { + case SPECTRE_V2_METHOD_LOOP8: + return "loop"; + + case SPECTRE_V2_METHOD_BPIALL: + return "BPIALL"; + + default: + return "unknown"; } +} - if (spectre_v2_method) - pr_info("CPU%u: Spectre v2: using %s workaround\n", - smp_processor_id(), spectre_v2_method); +static int spectre_bhb_install_workaround(int method) +{ + if (spectre_bhb_method != method) { + if (spectre_bhb_method) { + pr_err("CPU%u: Spectre BHB: method disagreement, system vulnerable\n", + smp_processor_id()); + + return SPECTRE_VULNERABLE; + } + + if (spectre_bhb_update_vectors(method) == SPECTRE_VULNERABLE) + return SPECTRE_VULNERABLE; + + spectre_bhb_method = method; + } + + pr_info("CPU%u: Spectre BHB: using %s workaround\n", + smp_processor_id(), spectre_bhb_method_name(method)); + + return SPECTRE_MITIGATED; } #else -static void cpu_v7_spectre_init(void) +static int spectre_bhb_install_workaround(int method) { + return SPECTRE_VULNERABLE; } #endif +static void cpu_v7_spectre_bhb_init(void) +{ + unsigned int state, method = 0; + + switch (read_cpuid_part()) { + case ARM_CPU_PART_CORTEX_A15: + case ARM_CPU_PART_BRAHMA_B15: + case ARM_CPU_PART_CORTEX_A57: + case ARM_CPU_PART_CORTEX_A72: + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_LOOP8; + break; + + case ARM_CPU_PART_CORTEX_A73: + case ARM_CPU_PART_CORTEX_A75: + state = SPECTRE_MITIGATED; + method = SPECTRE_V2_METHOD_BPIALL; + break; + + default: + state = SPECTRE_UNAFFECTED; + break; + } + + if (state == SPECTRE_MITIGATED) + state = spectre_bhb_install_workaround(method); + + spectre_v2_update_state(state, method); +} + static __maybe_unused bool cpu_v7_check_auxcr_set(bool *warned, u32 mask, const char *msg) { @@ -142,16 +281,17 @@ static bool check_spectre_auxcr(bool *warned, u32 bit) void cpu_v7_ca8_ibe(void) { if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(6))) - cpu_v7_spectre_init(); + cpu_v7_spectre_v2_init(); } void cpu_v7_ca15_ibe(void) { if (check_spectre_auxcr(this_cpu_ptr(&spectre_warned), BIT(0))) - cpu_v7_spectre_init(); + cpu_v7_spectre_v2_init(); } void cpu_v7_bugs_init(void) { - cpu_v7_spectre_init(); + cpu_v7_spectre_v2_init(); + cpu_v7_spectre_bhb_init(); } diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 09b885cc4db5..c842878f8133 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1252,9 +1252,6 @@ config HW_PERF_EVENTS def_bool y depends on ARM_PMU -config ARCH_HAS_FILTER_PGPROT - def_bool y - # Supported by clang >= 7.0 config CC_HAVE_SHADOW_CALL_STACK def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18) @@ -1383,6 +1380,15 @@ config UNMAP_KERNEL_AT_EL0 If unsure, say Y. +config MITIGATE_SPECTRE_BRANCH_HISTORY + bool "Mitigate Spectre style attacks against branch history" if EXPERT + default y + help + Speculation attacks against some high-performance processors can + make use of branch history to influence future speculation. + When taking an exception from user-space, a sequence of branches + or a firmware call overwrites the branch history. + config RODATA_FULL_DEFAULT_ENABLED bool "Apply r/o permissions of VM areas also to their linear aliases" default y 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 04da07ae4420..1cee26479bfe 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts +++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts @@ -18,6 +18,7 @@ aliases { spi0 = &spi0; + ethernet0 = ð0; ethernet1 = ð1; mmc0 = &sdhci0; mmc1 = &sdhci1; @@ -138,7 +139,9 @@ /* * U-Boot port for Turris Mox has a bug which always expects that "ranges" DT property * contains exactly 2 ranges with 3 (child) address cells, 2 (parent) address cells and - * 2 size cells and also expects that the second range starts at 16 MB offset. If these + * 2 size cells and also expects that the second range starts at 16 MB offset. Also it + * expects that first range uses same address for PCI (child) and CPU (parent) cells (so + * no remapping) and that this address is the lowest from all specified ranges. If these * conditions are not met then U-Boot crashes during loading kernel DTB file. PCIe address * space is 128 MB long, so the best split between MEM and IO is to use fixed 16 MB window * for IO and the rest 112 MB (64+32+16) for MEM, despite that maximal IO size is just 64 kB. @@ -147,6 +150,9 @@ * https://source.denx.de/u-boot/u-boot/-/commit/cb2ddb291ee6fcbddd6d8f4ff49089dfe580f5d7 * https://source.denx.de/u-boot/u-boot/-/commit/c64ac3b3185aeb3846297ad7391fc6df8ecd73bf * https://source.denx.de/u-boot/u-boot/-/commit/4a82fca8e330157081fc132a591ebd99ba02ee33 + * Bug related to requirement of same child and parent addresses for first range is fixed + * in U-Boot version 2022.04 by following commit: + * https://source.denx.de/u-boot/u-boot/-/commit/1fd54253bca7d43d046bba4853fe5fafd034bc17 */ #address-cells = <3>; #size-cells = <2>; diff --git a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi index 673f4906eef9..fb78ef613b29 100644 --- a/arch/arm64/boot/dts/marvell/armada-37xx.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-37xx.dtsi @@ -499,7 +499,7 @@ * (totaling 127 MiB) for MEM. */ ranges = <0x82000000 0 0xe8000000 0 0xe8000000 0 0x07f00000 /* Port 0 MEM */ - 0x81000000 0 0xefff0000 0 0xefff0000 0 0x00010000>; /* Port 0 IO */ + 0x81000000 0 0x00000000 0 0xefff0000 0 0x00010000>; /* Port 0 IO */ interrupt-map-mask = <0 0 0 7>; interrupt-map = <0 0 0 1 &pcie_intc 0>, <0 0 0 2 &pcie_intc 1>, diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi index 2d48c3715fc6..aaa00da5351d 100644 --- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi +++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi @@ -1584,7 +1584,7 @@ #iommu-cells = <1>; nvidia,memory-controller = <&mc>; - status = "okay"; + status = "disabled"; }; smmu: iommu@12000000 { diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index 58845a14805f..e2b9ec134cb1 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -807,3 +807,8 @@ qcom,snoc-host-cap-8bit-quirk; }; + +&crypto { + /* FIXME: qce_start triggers an SError */ + status= "disable"; +}; diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index 53b39e718fb6..4b19744bcfb3 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -35,6 +35,24 @@ clock-frequency = <32000>; #clock-cells = <0>; }; + + ufs_phy_rx_symbol_0_clk: ufs-phy-rx-symbol-0 { + compatible = "fixed-clock"; + clock-frequency = <1000>; + #clock-cells = <0>; + }; + + ufs_phy_rx_symbol_1_clk: ufs-phy-rx-symbol-1 { + compatible = "fixed-clock"; + clock-frequency = <1000>; + #clock-cells = <0>; + }; + + ufs_phy_tx_symbol_0_clk: ufs-phy-tx-symbol-0 { + compatible = "fixed-clock"; + clock-frequency = <1000>; + #clock-cells = <0>; + }; }; cpus { @@ -603,9 +621,9 @@ <0>, <0>, <0>, - <0>, - <0>, - <0>, + <&ufs_phy_rx_symbol_0_clk>, + <&ufs_phy_rx_symbol_1_clk>, + <&ufs_phy_tx_symbol_0_clk>, <0>, <0>; }; @@ -1923,8 +1941,8 @@ <75000000 300000000>, <0 0>, <0 0>, - <75000000 300000000>, - <75000000 300000000>; + <0 0>, + <0 0>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi index 10c25ad2d0c7..02b97e838c47 100644 --- a/arch/arm64/boot/dts/qcom/sm8450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi @@ -726,7 +726,7 @@ compatible = "qcom,sm8450-smmu-500", "arm,mmu-500"; reg = <0 0x15000000 0 0x100000>; #iommu-cells = <2>; - #global-interrupts = <2>; + #global-interrupts = <1>; interrupts = <GIC_SPI 65 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>, @@ -813,6 +813,7 @@ <GIC_SPI 412 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 421 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 707 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 423 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 424 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 425 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 690 IRQ_TYPE_LEVEL_HIGH>, @@ -1072,9 +1073,10 @@ <&gcc GCC_USB30_PRIM_MASTER_CLK>, <&gcc GCC_AGGRE_USB3_PRIM_AXI_CLK>, <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>, - <&gcc GCC_USB30_PRIM_SLEEP_CLK>; + <&gcc GCC_USB30_PRIM_SLEEP_CLK>, + <&gcc GCC_USB3_0_CLKREF_EN>; clock-names = "cfg_noc", "core", "iface", "mock_utmi", - "sleep"; + "sleep", "xo"; assigned-clocks = <&gcc GCC_USB30_PRIM_MOCK_UTMI_CLK>, <&gcc GCC_USB30_PRIM_MASTER_CLK>; diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index e8bd0af0141c..6ebdc0f834a7 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -109,6 +109,13 @@ .endm /* + * Clear Branch History instruction + */ + .macro clearbhb + hint #22 + .endm + +/* * Speculation barrier */ .macro sb @@ -850,4 +857,50 @@ alternative_endif #endif /* GNU_PROPERTY_AARCH64_FEATURE_1_DEFAULT */ + .macro __mitigate_spectre_bhb_loop tmp +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb spectre_bhb_patch_loop_iter + mov \tmp, #32 // Patched to correct the immediate +alternative_cb_end +.Lspectre_bhb_loop\@: + b . + 4 + subs \tmp, \tmp, #1 + b.ne .Lspectre_bhb_loop\@ + sb +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + .macro mitigate_spectre_bhb_loop tmp +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb spectre_bhb_patch_loop_mitigation_enable + b .L_spectre_bhb_loop_done\@ // Patched to NOP +alternative_cb_end + __mitigate_spectre_bhb_loop \tmp +.L_spectre_bhb_loop_done\@: +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + /* Save/restores x0-x3 to the stack */ + .macro __mitigate_spectre_bhb_fw +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + stp x0, x1, [sp, #-16]! + stp x2, x3, [sp, #-16]! + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_3 +alternative_cb smccc_patch_fw_mitigation_conduit + nop // Patched to SMC/HVC #0 +alternative_cb_end + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm + + .macro mitigate_spectre_bhb_clear_insn +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +alternative_cb spectre_bhb_patch_clearbhb + /* Patched to NOP when not supported */ + clearbhb + isb +alternative_cb_end +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + .endm #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index ef6be92b1921..a77b5f49b3a6 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -637,6 +637,35 @@ static inline bool cpu_supports_mixed_endian_el0(void) return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1)); } + +static inline bool supports_csv2p3(int scope) +{ + u64 pfr0; + u8 csv2_val; + + if (scope == SCOPE_LOCAL_CPU) + pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1); + else + pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + + csv2_val = cpuid_feature_extract_unsigned_field(pfr0, + ID_AA64PFR0_CSV2_SHIFT); + return csv2_val == 3; +} + +static inline bool supports_clearbhb(int scope) +{ + u64 isar2; + + if (scope == SCOPE_LOCAL_CPU) + isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); + else + isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); + + return cpuid_feature_extract_unsigned_field(isar2, + ID_AA64ISAR2_CLEARBHB_SHIFT); +} + const struct cpumask *system_32bit_el0_cpumask(void); DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 999b9149f856..bfbf0c4c7c5e 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -73,10 +73,14 @@ #define ARM_CPU_PART_CORTEX_A76 0xD0B #define ARM_CPU_PART_NEOVERSE_N1 0xD0C #define ARM_CPU_PART_CORTEX_A77 0xD0D +#define ARM_CPU_PART_NEOVERSE_V1 0xD40 +#define ARM_CPU_PART_CORTEX_A78 0xD41 +#define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 +#define ARM_CPU_PART_CORTEX_A78C 0xD4B #define APM_CPU_PART_POTENZA 0x000 @@ -117,10 +121,14 @@ #define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76) #define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1) #define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77) +#define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1) +#define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78) +#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) +#define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 4335800201c9..daff882883f9 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -62,9 +62,11 @@ enum fixed_addresses { #endif /* CONFIG_ACPI_APEI_GHES */ #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 + FIX_ENTRY_TRAMP_TEXT3, + FIX_ENTRY_TRAMP_TEXT2, + FIX_ENTRY_TRAMP_TEXT1, FIX_ENTRY_TRAMP_DATA, - FIX_ENTRY_TRAMP_TEXT, -#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT)) +#define TRAMP_VALIAS (__fix_to_virt(FIX_ENTRY_TRAMP_TEXT1)) #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ __end_of_permanent_fixed_addresses, diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 0b6b31307e68..1e5760d567ae 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -65,6 +65,7 @@ enum aarch64_insn_hint_cr_op { AARCH64_INSN_HINT_PSB = 0x11 << 5, AARCH64_INSN_HINT_TSB = 0x12 << 5, AARCH64_INSN_HINT_CSDB = 0x14 << 5, + AARCH64_INSN_HINT_CLEARBHB = 0x16 << 5, AARCH64_INSN_HINT_BTI = 0x20 << 5, AARCH64_INSN_HINT_BTIC = 0x22 << 5, diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 5bc01e62c08a..031e3a2537fc 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -714,6 +714,11 @@ static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr(); } +static inline bool kvm_system_needs_idmapped_vectors(void) +{ + return cpus_have_const_cap(ARM64_SPECTRE_V3A); +} + void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu); static inline void kvm_arch_hardware_unsetup(void) {} diff --git a/arch/arm64/include/asm/mte-kasan.h b/arch/arm64/include/asm/mte-kasan.h index e4704a403237..a857bcacf0fe 100644 --- a/arch/arm64/include/asm/mte-kasan.h +++ b/arch/arm64/include/asm/mte-kasan.h @@ -5,6 +5,7 @@ #ifndef __ASM_MTE_KASAN_H #define __ASM_MTE_KASAN_H +#include <asm/compiler.h> #include <asm/mte-def.h> #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 7032f04c8ac6..b1e1b74d993c 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -92,7 +92,7 @@ extern bool arm64_use_ng_mappings; #define __P001 PAGE_READONLY #define __P010 PAGE_READONLY #define __P011 PAGE_READONLY -#define __P100 PAGE_EXECONLY +#define __P100 PAGE_READONLY_EXEC /* PAGE_EXECONLY if Enhanced PAN */ #define __P101 PAGE_READONLY_EXEC #define __P110 PAGE_READONLY_EXEC #define __P111 PAGE_READONLY_EXEC @@ -101,7 +101,7 @@ extern bool arm64_use_ng_mappings; #define __S001 PAGE_READONLY #define __S010 PAGE_SHARED #define __S011 PAGE_SHARED -#define __S100 PAGE_EXECONLY +#define __S100 PAGE_READONLY_EXEC /* PAGE_EXECONLY if Enhanced PAN */ #define __S101 PAGE_READONLY_EXEC #define __S110 PAGE_SHARED_EXEC #define __S111 PAGE_SHARED_EXEC diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index c4ba047a82d2..94e147e5456c 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1017,17 +1017,6 @@ static inline bool arch_wants_old_prefaulted_pte(void) } #define arch_wants_old_prefaulted_pte arch_wants_old_prefaulted_pte -static inline pgprot_t arch_filter_pgprot(pgprot_t prot) -{ - if (cpus_have_const_cap(ARM64_HAS_EPAN)) - return prot; - - if (pgprot_val(prot) != pgprot_val(PAGE_EXECONLY)) - return prot; - - return PAGE_READONLY_EXEC; -} - static inline bool pud_sect_supported(void) { return PAGE_SIZE == SZ_4K; diff --git a/arch/arm64/include/asm/rwonce.h b/arch/arm64/include/asm/rwonce.h index 1bce62fa908a..56f7b1d4d54b 100644 --- a/arch/arm64/include/asm/rwonce.h +++ b/arch/arm64/include/asm/rwonce.h @@ -5,7 +5,7 @@ #ifndef __ASM_RWONCE_H #define __ASM_RWONCE_H -#ifdef CONFIG_LTO +#if defined(CONFIG_LTO) && !defined(__ASSEMBLY__) #include <linux/compiler_types.h> #include <asm/alternative-macros.h> @@ -66,7 +66,7 @@ }) #endif /* !BUILD_VDSO */ -#endif /* CONFIG_LTO */ +#endif /* CONFIG_LTO && !__ASSEMBLY__ */ #include <asm-generic/rwonce.h> diff --git a/arch/arm64/include/asm/sections.h b/arch/arm64/include/asm/sections.h index 152cb35bf9df..40971ac1303f 100644 --- a/arch/arm64/include/asm/sections.h +++ b/arch/arm64/include/asm/sections.h @@ -23,4 +23,9 @@ extern char __mmuoff_data_start[], __mmuoff_data_end[]; extern char __entry_tramp_text_start[], __entry_tramp_text_end[]; extern char __relocate_new_kernel_start[], __relocate_new_kernel_end[]; +static inline size_t entry_tramp_text_size(void) +{ + return __entry_tramp_text_end - __entry_tramp_text_start; +} + #endif /* __ASM_SECTIONS_H */ diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index f62ca39da6c5..86e0cc9b9c68 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -93,5 +93,9 @@ void spectre_v4_enable_task_mitigation(struct task_struct *tsk); enum mitigation_state arm64_get_meltdown_state(void); +enum mitigation_state arm64_get_spectre_bhb_state(void); +bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope); +u8 spectre_bhb_loop_affected(int scope); +void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused); #endif /* __ASSEMBLY__ */ #endif /* __ASM_SPECTRE_H */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 898bee0004ae..932d45b17877 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -773,6 +773,7 @@ #define ID_AA64ISAR1_GPI_IMP_DEF 0x1 /* id_aa64isar2 */ +#define ID_AA64ISAR2_CLEARBHB_SHIFT 28 #define ID_AA64ISAR2_RPRES_SHIFT 4 #define ID_AA64ISAR2_WFXT_SHIFT 0 @@ -904,6 +905,7 @@ #endif /* id_aa64mmfr1 */ +#define ID_AA64MMFR1_ECBHB_SHIFT 60 #define ID_AA64MMFR1_AFP_SHIFT 44 #define ID_AA64MMFR1_ETS_SHIFT 36 #define ID_AA64MMFR1_TWED_SHIFT 32 diff --git a/arch/arm64/include/asm/vectors.h b/arch/arm64/include/asm/vectors.h new file mode 100644 index 000000000000..f64613a96d53 --- /dev/null +++ b/arch/arm64/include/asm/vectors.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 ARM Ltd. + */ +#ifndef __ASM_VECTORS_H +#define __ASM_VECTORS_H + +#include <linux/bug.h> +#include <linux/percpu.h> + +#include <asm/fixmap.h> + +extern char vectors[]; +extern char tramp_vectors[]; +extern char __bp_harden_el1_vectors[]; + +/* + * Note: the order of this enum corresponds to two arrays in entry.S: + * tramp_vecs and __bp_harden_el1_vectors. By default the canonical + * 'full fat' vectors are used directly. + */ +enum arm64_bp_harden_el1_vectors { +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + /* + * Perform the BHB loop mitigation, before branching to the canonical + * vectors. + */ + EL1_VECTOR_BHB_LOOP, + + /* + * Make the SMC call for firmware mitigation, before branching to the + * canonical vectors. + */ + EL1_VECTOR_BHB_FW, + + /* + * Use the ClearBHB instruction, before branching to the canonical + * vectors. + */ + EL1_VECTOR_BHB_CLEAR_INSN, +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + + /* + * Remap the kernel before branching to the canonical vectors. + */ + EL1_VECTOR_KPTI, +}; + +#ifndef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY +#define EL1_VECTOR_BHB_LOOP -1 +#define EL1_VECTOR_BHB_FW -1 +#define EL1_VECTOR_BHB_CLEAR_INSN -1 +#endif /* !CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + +/* The vectors to use on return from EL0. e.g. to remap the kernel */ +DECLARE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector); + +#ifndef CONFIG_UNMAP_KERNEL_AT_EL0 +#define TRAMP_VALIAS 0 +#endif + +static inline const char * +arm64_get_bp_hardening_vector(enum arm64_bp_harden_el1_vectors slot) +{ + if (arm64_kernel_unmapped_at_el0()) + return (char *)TRAMP_VALIAS + SZ_2K * slot; + + WARN_ON_ONCE(slot == EL1_VECTOR_KPTI); + + return __bp_harden_el1_vectors + SZ_2K * slot; +} + +#endif /* __ASM_VECTORS_H */ diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h index b3edde68bc3e..323e251ed37b 100644 --- a/arch/arm64/include/uapi/asm/kvm.h +++ b/arch/arm64/include/uapi/asm/kvm.h @@ -281,6 +281,11 @@ struct kvm_arm_copy_mte_tags { #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED 3 #define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED (1U << 4) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 KVM_REG_ARM_FW_REG(3) +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL 0 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL 1 +#define KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED 2 + /* SVE registers */ #define KVM_REG_ARM64_SVE (0x15 << KVM_REG_ARM_COPROC_SHIFT) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index b217941713a8..a401180e8d66 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -502,6 +502,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .matches = has_spectre_v4, .cpu_enable = spectre_v4_enable_mitigation, }, + { + .desc = "Spectre-BHB", + .capability = ARM64_SPECTRE_BHB, + .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, + .matches = is_spectre_bhb_affected, + .cpu_enable = spectre_bhb_enable_mitigation, + }, #ifdef CONFIG_ARM64_ERRATUM_1418040 { .desc = "ARM erratum 1418040", diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index e5f23dab1c8d..d33687673f6b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -73,6 +73,8 @@ #include <linux/mm.h> #include <linux/cpu.h> #include <linux/kasan.h> +#include <linux/percpu.h> + #include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/cpu_ops.h> @@ -85,6 +87,7 @@ #include <asm/smp.h> #include <asm/sysreg.h> #include <asm/traps.h> +#include <asm/vectors.h> #include <asm/virt.h> /* Kernel representation of AT_HWCAP and AT_HWCAP2 */ @@ -110,6 +113,8 @@ DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE); bool arm64_use_ng_mappings = false; EXPORT_SYMBOL(arm64_use_ng_mappings); +DEFINE_PER_CPU_READ_MOSTLY(const char *, this_cpu_vector) = vectors; + /* * Permit PER_LINUX32 and execve() of 32-bit binaries even if not all CPUs * support it? @@ -226,6 +231,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_CLEARBHB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_RPRES_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -1590,6 +1596,12 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) int cpu = smp_processor_id(); + if (__this_cpu_read(this_cpu_vector) == vectors) { + const char *v = arm64_get_bp_hardening_vector(EL1_VECTOR_KPTI); + + __this_cpu_write(this_cpu_vector, v); + } + /* * We don't need to rewrite the page-tables if either we've done * it already or we have KASLR enabled and therefore have not diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 772ec2ecf488..4a3a653df07e 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -37,18 +37,21 @@ .macro kernel_ventry, el:req, ht:req, regsize:req, label:req .align 7 -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +.Lventry_start\@: .if \el == 0 -alternative_if ARM64_UNMAP_KERNEL_AT_EL0 + /* + * This must be the first instruction of the EL0 vector entries. It is + * skipped by the trampoline vectors, to trigger the cleanup. + */ + b .Lskip_tramp_vectors_cleanup\@ .if \regsize == 64 mrs x30, tpidrro_el0 msr tpidrro_el0, xzr .else mov x30, xzr .endif -alternative_else_nop_endif +.Lskip_tramp_vectors_cleanup\@: .endif -#endif sub sp, sp, #PT_REGS_SIZE #ifdef CONFIG_VMAP_STACK @@ -95,11 +98,15 @@ alternative_else_nop_endif mrs x0, tpidrro_el0 #endif b el\el\ht\()_\regsize\()_\label +.org .Lventry_start\@ + 128 // Did we overflow the ventry slot? .endm - .macro tramp_alias, dst, sym + .macro tramp_alias, dst, sym, tmp mov_q \dst, TRAMP_VALIAS - add \dst, \dst, #(\sym - .entry.tramp.text) + adr_l \tmp, \sym + add \dst, \dst, \tmp + adr_l \tmp, .entry.tramp.text + sub \dst, \dst, \tmp .endm /* @@ -116,7 +123,7 @@ alternative_cb_end tbnz \tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@ mov w0, #ARM_SMCCC_ARCH_WORKAROUND_2 mov w1, #\state -alternative_cb spectre_v4_patch_fw_mitigation_conduit +alternative_cb smccc_patch_fw_mitigation_conduit nop // Patched to SMC/HVC #0 alternative_cb_end .L__asm_ssbd_skip\@: @@ -413,21 +420,26 @@ alternative_else_nop_endif ldp x24, x25, [sp, #16 * 12] ldp x26, x27, [sp, #16 * 13] ldp x28, x29, [sp, #16 * 14] - ldr lr, [sp, #S_LR] - add sp, sp, #PT_REGS_SIZE // restore sp .if \el == 0 -alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 +alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 + ldr lr, [sp, #S_LR] + add sp, sp, #PT_REGS_SIZE // restore sp + eret +alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 bne 4f - msr far_el1, x30 - tramp_alias x30, tramp_exit_native + msr far_el1, x29 + tramp_alias x30, tramp_exit_native, x29 br x30 4: - tramp_alias x30, tramp_exit_compat + tramp_alias x30, tramp_exit_compat, x29 br x30 #endif .else + ldr lr, [sp, #S_LR] + add sp, sp, #PT_REGS_SIZE // restore sp + /* Ensure any device/NC reads complete */ alternative_insn nop, "dmb sy", ARM64_WORKAROUND_1508412 @@ -594,12 +606,6 @@ SYM_CODE_END(ret_to_user) .popsection // .entry.text -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -/* - * Exception vectors trampoline. - */ - .pushsection ".entry.tramp.text", "ax" - // Move from tramp_pg_dir to swapper_pg_dir .macro tramp_map_kernel, tmp mrs \tmp, ttbr1_el1 @@ -633,12 +639,47 @@ alternative_else_nop_endif */ .endm - .macro tramp_ventry, regsize = 64 + .macro tramp_data_page dst + adr_l \dst, .entry.tramp.text + sub \dst, \dst, PAGE_SIZE + .endm + + .macro tramp_data_read_var dst, var +#ifdef CONFIG_RANDOMIZE_BASE + tramp_data_page \dst + add \dst, \dst, #:lo12:__entry_tramp_data_\var + ldr \dst, [\dst] +#else + ldr \dst, =\var +#endif + .endm + +#define BHB_MITIGATION_NONE 0 +#define BHB_MITIGATION_LOOP 1 +#define BHB_MITIGATION_FW 2 +#define BHB_MITIGATION_INSN 3 + + .macro tramp_ventry, vector_start, regsize, kpti, bhb .align 7 1: .if \regsize == 64 msr tpidrro_el0, x30 // Restored in kernel_ventry .endif + + .if \bhb == BHB_MITIGATION_LOOP + /* + * This sequence must appear before the first indirect branch. i.e. the + * ret out of tramp_ventry. It appears here because x30 is free. + */ + __mitigate_spectre_bhb_loop x30 + .endif // \bhb == BHB_MITIGATION_LOOP + + .if \bhb == BHB_MITIGATION_INSN + clearbhb + isb + .endif // \bhb == BHB_MITIGATION_INSN + + .if \kpti == 1 /* * Defend against branch aliasing attacks by pushing a dummy * entry onto the return stack and using a RET instruction to @@ -648,46 +689,75 @@ alternative_else_nop_endif b . 2: tramp_map_kernel x30 -#ifdef CONFIG_RANDOMIZE_BASE - adr x30, tramp_vectors + PAGE_SIZE alternative_insn isb, nop, ARM64_WORKAROUND_QCOM_FALKOR_E1003 - ldr x30, [x30] -#else - ldr x30, =vectors -#endif + tramp_data_read_var x30, vectors alternative_if_not ARM64_WORKAROUND_CAVIUM_TX2_219_PRFM - prfm plil1strm, [x30, #(1b - tramp_vectors)] + prfm plil1strm, [x30, #(1b - \vector_start)] alternative_else_nop_endif + msr vbar_el1, x30 - add x30, x30, #(1b - tramp_vectors) isb + .else + ldr x30, =vectors + .endif // \kpti == 1 + + .if \bhb == BHB_MITIGATION_FW + /* + * The firmware sequence must appear before the first indirect branch. + * i.e. the ret out of tramp_ventry. But it also needs the stack to be + * mapped to save/restore the registers the SMC clobbers. + */ + __mitigate_spectre_bhb_fw + .endif // \bhb == BHB_MITIGATION_FW + + add x30, x30, #(1b - \vector_start + 4) ret +.org 1b + 128 // Did we overflow the ventry slot? .endm .macro tramp_exit, regsize = 64 - adr x30, tramp_vectors + tramp_data_read_var x30, this_cpu_vector + get_this_cpu_offset x29 + ldr x30, [x30, x29] + msr vbar_el1, x30 - tramp_unmap_kernel x30 + ldr lr, [sp, #S_LR] + tramp_unmap_kernel x29 .if \regsize == 64 - mrs x30, far_el1 + mrs x29, far_el1 .endif + add sp, sp, #PT_REGS_SIZE // restore sp eret sb .endm - .align 11 -SYM_CODE_START_NOALIGN(tramp_vectors) + .macro generate_tramp_vector, kpti, bhb +.Lvector_start\@: .space 0x400 - tramp_ventry - tramp_ventry - tramp_ventry - tramp_ventry + .rept 4 + tramp_ventry .Lvector_start\@, 64, \kpti, \bhb + .endr + .rept 4 + tramp_ventry .Lvector_start\@, 32, \kpti, \bhb + .endr + .endm - tramp_ventry 32 - tramp_ventry 32 - tramp_ventry 32 - tramp_ventry 32 +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 +/* + * Exception vectors trampoline. + * The order must match __bp_harden_el1_vectors and the + * arm64_bp_harden_el1_vectors enum. + */ + .pushsection ".entry.tramp.text", "ax" + .align 11 +SYM_CODE_START_NOALIGN(tramp_vectors) +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_LOOP + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_FW + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_INSN +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ + generate_tramp_vector kpti=1, bhb=BHB_MITIGATION_NONE SYM_CODE_END(tramp_vectors) SYM_CODE_START(tramp_exit_native) @@ -704,13 +774,57 @@ SYM_CODE_END(tramp_exit_compat) .pushsection ".rodata", "a" .align PAGE_SHIFT SYM_DATA_START(__entry_tramp_data_start) +__entry_tramp_data_vectors: .quad vectors +#ifdef CONFIG_ARM_SDE_INTERFACE +__entry_tramp_data___sdei_asm_handler: + .quad __sdei_asm_handler +#endif /* CONFIG_ARM_SDE_INTERFACE */ +__entry_tramp_data_this_cpu_vector: + .quad this_cpu_vector SYM_DATA_END(__entry_tramp_data_start) .popsection // .rodata #endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ /* + * Exception vectors for spectre mitigations on entry from EL1 when + * kpti is not in use. + */ + .macro generate_el1_vector, bhb +.Lvector_start\@: + kernel_ventry 1, t, 64, sync // Synchronous EL1t + kernel_ventry 1, t, 64, irq // IRQ EL1t + kernel_ventry 1, t, 64, fiq // FIQ EL1h + kernel_ventry 1, t, 64, error // Error EL1t + + kernel_ventry 1, h, 64, sync // Synchronous EL1h + kernel_ventry 1, h, 64, irq // IRQ EL1h + kernel_ventry 1, h, 64, fiq // FIQ EL1h + kernel_ventry 1, h, 64, error // Error EL1h + + .rept 4 + tramp_ventry .Lvector_start\@, 64, 0, \bhb + .endr + .rept 4 + tramp_ventry .Lvector_start\@, 32, 0, \bhb + .endr + .endm + +/* The order must match tramp_vecs and the arm64_bp_harden_el1_vectors enum. */ + .pushsection ".entry.text", "ax" + .align 11 +SYM_CODE_START(__bp_harden_el1_vectors) +#ifdef CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY + generate_el1_vector bhb=BHB_MITIGATION_LOOP + generate_el1_vector bhb=BHB_MITIGATION_FW + generate_el1_vector bhb=BHB_MITIGATION_INSN +#endif /* CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY */ +SYM_CODE_END(__bp_harden_el1_vectors) + .popsection + + +/* * Register switch for AArch64. The callee-saved registers need to be saved * and restored. On entry: * x0 = previous task_struct (must be preserved across the switch) @@ -835,14 +949,7 @@ SYM_CODE_START(__sdei_asm_entry_trampoline) * Remember whether to unmap the kernel on exit. */ 1: str x4, [x1, #(SDEI_EVENT_INTREGS + S_SDEI_TTBR1)] - -#ifdef CONFIG_RANDOMIZE_BASE - adr x4, tramp_vectors + PAGE_SIZE - add x4, x4, #:lo12:__sdei_asm_trampoline_next_handler - ldr x4, [x4] -#else - ldr x4, =__sdei_asm_handler -#endif + tramp_data_read_var x4, __sdei_asm_handler br x4 SYM_CODE_END(__sdei_asm_entry_trampoline) NOKPROBE(__sdei_asm_entry_trampoline) @@ -865,13 +972,6 @@ SYM_CODE_END(__sdei_asm_exit_trampoline) NOKPROBE(__sdei_asm_exit_trampoline) .ltorg .popsection // .entry.tramp.text -#ifdef CONFIG_RANDOMIZE_BASE -.pushsection ".rodata", "a" -SYM_DATA_START(__sdei_asm_trampoline_next_handler) - .quad __sdei_asm_handler -SYM_DATA_END(__sdei_asm_trampoline_next_handler) -.popsection // .rodata -#endif /* CONFIG_RANDOMIZE_BASE */ #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */ /* @@ -981,7 +1081,7 @@ alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0 alternative_else_nop_endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 - tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline + tramp_alias dst=x5, sym=__sdei_asm_exit_trampoline, tmp=x3 br x5 #endif SYM_CODE_END(__sdei_asm_handler) diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 7eaf1f7c4168..55a1ced8eb77 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -66,6 +66,10 @@ KVM_NVHE_ALIAS(kvm_patch_vector_branch); KVM_NVHE_ALIAS(kvm_update_va_mask); KVM_NVHE_ALIAS(kvm_get_kimage_voffset); KVM_NVHE_ALIAS(kvm_compute_final_ctr_el0); +KVM_NVHE_ALIAS(spectre_bhb_patch_loop_iter); +KVM_NVHE_ALIAS(spectre_bhb_patch_loop_mitigation_enable); +KVM_NVHE_ALIAS(spectre_bhb_patch_wa3); +KVM_NVHE_ALIAS(spectre_bhb_patch_clearbhb); /* Global kernel state accessed by nVHE hyp code. */ KVM_NVHE_ALIAS(kvm_vgic_global_state); diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index 902e4084c477..6d45c63c6454 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -18,15 +18,18 @@ */ #include <linux/arm-smccc.h> +#include <linux/bpf.h> #include <linux/cpu.h> #include <linux/device.h> #include <linux/nospec.h> #include <linux/prctl.h> #include <linux/sched/task_stack.h> +#include <asm/debug-monitors.h> #include <asm/insn.h> #include <asm/spectre.h> #include <asm/traps.h> +#include <asm/vectors.h> #include <asm/virt.h> /* @@ -96,14 +99,51 @@ static bool spectre_v2_mitigations_off(void) return ret; } +static const char *get_bhb_affected_string(enum mitigation_state bhb_state) +{ + switch (bhb_state) { + case SPECTRE_UNAFFECTED: + return ""; + default: + case SPECTRE_VULNERABLE: + return ", but not BHB"; + case SPECTRE_MITIGATED: + return ", BHB"; + } +} + +static bool _unprivileged_ebpf_enabled(void) +{ +#ifdef CONFIG_BPF_SYSCALL + return !sysctl_unprivileged_bpf_disabled; +#else + return false; +#endif +} + ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, char *buf) { + enum mitigation_state bhb_state = arm64_get_spectre_bhb_state(); + const char *bhb_str = get_bhb_affected_string(bhb_state); + const char *v2_str = "Branch predictor hardening"; + switch (spectre_v2_state) { case SPECTRE_UNAFFECTED: - return sprintf(buf, "Not affected\n"); + if (bhb_state == SPECTRE_UNAFFECTED) + return sprintf(buf, "Not affected\n"); + + /* + * Platforms affected by Spectre-BHB can't report + * "Not affected" for Spectre-v2. + */ + v2_str = "CSV2"; + fallthrough; case SPECTRE_MITIGATED: - return sprintf(buf, "Mitigation: Branch predictor hardening\n"); + if (bhb_state == SPECTRE_MITIGATED && _unprivileged_ebpf_enabled()) + return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n"); + + return sprintf(buf, "Mitigation: %s%s\n", v2_str, bhb_str); case SPECTRE_VULNERABLE: fallthrough; default: @@ -554,9 +594,9 @@ void __init spectre_v4_patch_fw_mitigation_enable(struct alt_instr *alt, * Patch a NOP in the Spectre-v4 mitigation code with an SMC/HVC instruction * to call into firmware to adjust the mitigation state. */ -void __init spectre_v4_patch_fw_mitigation_conduit(struct alt_instr *alt, - __le32 *origptr, - __le32 *updptr, int nr_inst) +void __init smccc_patch_fw_mitigation_conduit(struct alt_instr *alt, + __le32 *origptr, + __le32 *updptr, int nr_inst) { u32 insn; @@ -770,3 +810,344 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) return -ENODEV; } } + +/* + * Spectre BHB. + * + * A CPU is either: + * - Mitigated by a branchy loop a CPU specific number of times, and listed + * in our "loop mitigated list". + * - Mitigated in software by the firmware Spectre v2 call. + * - Has the ClearBHB instruction to perform the mitigation. + * - Has the 'Exception Clears Branch History Buffer' (ECBHB) feature, so no + * software mitigation in the vectors is needed. + * - Has CSV2.3, so is unaffected. + */ +static enum mitigation_state spectre_bhb_state; + +enum mitigation_state arm64_get_spectre_bhb_state(void) +{ + return spectre_bhb_state; +} + +enum bhb_mitigation_bits { + BHB_LOOP, + BHB_FW, + BHB_HW, + BHB_INSN, +}; +static unsigned long system_bhb_mitigations; + +/* + * This must be called with SCOPE_LOCAL_CPU for each type of CPU, before any + * SCOPE_SYSTEM call will give the right answer. + */ +u8 spectre_bhb_loop_affected(int scope) +{ + u8 k = 0; + static u8 max_bhb_k; + + if (scope == SCOPE_LOCAL_CPU) { + static const struct midr_range spectre_bhb_k32_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), + {}, + }; + static const struct midr_range spectre_bhb_k24_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A76), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A77), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), + {}, + }; + static const struct midr_range spectre_bhb_k8_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A72), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A57), + {}, + }; + + if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k32_list)) + k = 32; + else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k24_list)) + k = 24; + else if (is_midr_in_range_list(read_cpuid_id(), spectre_bhb_k8_list)) + k = 8; + + max_bhb_k = max(max_bhb_k, k); + } else { + k = max_bhb_k; + } + + return k; +} + +static enum mitigation_state spectre_bhb_get_cpu_fw_mitigation_state(void) +{ + int ret; + struct arm_smccc_res res; + + arm_smccc_1_1_invoke(ARM_SMCCC_ARCH_FEATURES_FUNC_ID, + ARM_SMCCC_ARCH_WORKAROUND_3, &res); + + ret = res.a0; + switch (ret) { + case SMCCC_RET_SUCCESS: + return SPECTRE_MITIGATED; + case SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED: + return SPECTRE_UNAFFECTED; + default: + fallthrough; + case SMCCC_RET_NOT_SUPPORTED: + return SPECTRE_VULNERABLE; + } +} + +static bool is_spectre_bhb_fw_affected(int scope) +{ + static bool system_affected; + enum mitigation_state fw_state; + bool has_smccc = arm_smccc_1_1_get_conduit() != SMCCC_CONDUIT_NONE; + static const struct midr_range spectre_bhb_firmware_mitigated_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A73), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A75), + {}, + }; + bool cpu_in_list = is_midr_in_range_list(read_cpuid_id(), + spectre_bhb_firmware_mitigated_list); + + if (scope != SCOPE_LOCAL_CPU) + return system_affected; + + fw_state = spectre_bhb_get_cpu_fw_mitigation_state(); + if (cpu_in_list || (has_smccc && fw_state == SPECTRE_MITIGATED)) { + system_affected = true; + return true; + } + + return false; +} + +static bool supports_ecbhb(int scope) +{ + u64 mmfr1; + + if (scope == SCOPE_LOCAL_CPU) + mmfr1 = read_sysreg_s(SYS_ID_AA64MMFR1_EL1); + else + mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); + + return cpuid_feature_extract_unsigned_field(mmfr1, + ID_AA64MMFR1_ECBHB_SHIFT); +} + +bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, + int scope) +{ + WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible()); + + if (supports_csv2p3(scope)) + return false; + + if (supports_clearbhb(scope)) + return true; + + if (spectre_bhb_loop_affected(scope)) + return true; + + if (is_spectre_bhb_fw_affected(scope)) + return true; + + return false; +} + +static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) +{ + const char *v = arm64_get_bp_hardening_vector(slot); + + if (slot < 0) + return; + + __this_cpu_write(this_cpu_vector, v); + + /* + * When KPTI is in use, the vectors are switched when exiting to + * user-space. + */ + if (arm64_kernel_unmapped_at_el0()) + return; + + write_sysreg(v, vbar_el1); + isb(); +} + +void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) +{ + bp_hardening_cb_t cpu_cb; + enum mitigation_state fw_state, state = SPECTRE_VULNERABLE; + struct bp_hardening_data *data = this_cpu_ptr(&bp_hardening_data); + + if (!is_spectre_bhb_affected(entry, SCOPE_LOCAL_CPU)) + return; + + if (arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) { + /* No point mitigating Spectre-BHB alone. */ + } else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) { + pr_info_once("spectre-bhb mitigation disabled by compile time option\n"); + } else if (cpu_mitigations_off()) { + pr_info_once("spectre-bhb mitigation disabled by command line option\n"); + } else if (supports_ecbhb(SCOPE_LOCAL_CPU)) { + state = SPECTRE_MITIGATED; + set_bit(BHB_HW, &system_bhb_mitigations); + } else if (supports_clearbhb(SCOPE_LOCAL_CPU)) { + /* + * Ensure KVM uses the indirect vector which will have ClearBHB + * added. + */ + if (!data->slot) + data->slot = HYP_VECTOR_INDIRECT; + + this_cpu_set_vectors(EL1_VECTOR_BHB_CLEAR_INSN); + state = SPECTRE_MITIGATED; + set_bit(BHB_INSN, &system_bhb_mitigations); + } else if (spectre_bhb_loop_affected(SCOPE_LOCAL_CPU)) { + /* + * Ensure KVM uses the indirect vector which will have the + * branchy-loop added. A57/A72-r0 will already have selected + * the spectre-indirect vector, which is sufficient for BHB + * too. + */ + if (!data->slot) + data->slot = HYP_VECTOR_INDIRECT; + + this_cpu_set_vectors(EL1_VECTOR_BHB_LOOP); + state = SPECTRE_MITIGATED; + set_bit(BHB_LOOP, &system_bhb_mitigations); + } else if (is_spectre_bhb_fw_affected(SCOPE_LOCAL_CPU)) { + fw_state = spectre_bhb_get_cpu_fw_mitigation_state(); + if (fw_state == SPECTRE_MITIGATED) { + /* + * Ensure KVM uses one of the spectre bp_hardening + * vectors. The indirect vector doesn't include the EL3 + * call, so needs upgrading to + * HYP_VECTOR_SPECTRE_INDIRECT. + */ + if (!data->slot || data->slot == HYP_VECTOR_INDIRECT) + data->slot += 1; + + this_cpu_set_vectors(EL1_VECTOR_BHB_FW); + + /* + * The WA3 call in the vectors supersedes the WA1 call + * made during context-switch. Uninstall any firmware + * bp_hardening callback. + */ + cpu_cb = spectre_v2_get_sw_mitigation_cb(); + if (__this_cpu_read(bp_hardening_data.fn) != cpu_cb) + __this_cpu_write(bp_hardening_data.fn, NULL); + + state = SPECTRE_MITIGATED; + set_bit(BHB_FW, &system_bhb_mitigations); + } + } + + update_mitigation_state(&spectre_bhb_state, state); +} + +/* Patched to NOP when enabled */ +void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt, + __le32 *origptr, + __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 1); + + if (test_bit(BHB_LOOP, &system_bhb_mitigations)) + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); +} + +/* Patched to NOP when enabled */ +void noinstr spectre_bhb_patch_fw_mitigation_enabled(struct alt_instr *alt, + __le32 *origptr, + __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 1); + + if (test_bit(BHB_FW, &system_bhb_mitigations)) + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); +} + +/* Patched to correct the immediate */ +void noinstr spectre_bhb_patch_loop_iter(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + u8 rd; + u32 insn; + u16 loop_count = spectre_bhb_loop_affected(SCOPE_SYSTEM); + + BUG_ON(nr_inst != 1); /* MOV -> MOV */ + + if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) + return; + + insn = le32_to_cpu(*origptr); + rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn); + insn = aarch64_insn_gen_movewide(rd, loop_count, 0, + AARCH64_INSN_VARIANT_64BIT, + AARCH64_INSN_MOVEWIDE_ZERO); + *updptr++ = cpu_to_le32(insn); +} + +/* Patched to mov WA3 when supported */ +void noinstr spectre_bhb_patch_wa3(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + u8 rd; + u32 insn; + + BUG_ON(nr_inst != 1); /* MOV -> MOV */ + + if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) || + !test_bit(BHB_FW, &system_bhb_mitigations)) + return; + + insn = le32_to_cpu(*origptr); + rd = aarch64_insn_decode_register(AARCH64_INSN_REGTYPE_RD, insn); + + insn = aarch64_insn_gen_logical_immediate(AARCH64_INSN_LOGIC_ORR, + AARCH64_INSN_VARIANT_32BIT, + AARCH64_INSN_REG_ZR, rd, + ARM_SMCCC_ARCH_WORKAROUND_3); + if (WARN_ON_ONCE(insn == AARCH64_BREAK_FAULT)) + return; + + *updptr++ = cpu_to_le32(insn); +} + +/* Patched to NOP when not supported */ +void __init spectre_bhb_patch_clearbhb(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst) +{ + BUG_ON(nr_inst != 2); + + if (test_bit(BHB_INSN, &system_bhb_mitigations)) + return; + + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); + *updptr++ = cpu_to_le32(aarch64_insn_gen_nop()); +} + +#ifdef CONFIG_BPF_SYSCALL +#define EBPF_WARN "Unprivileged eBPF is enabled, data leaks possible via Spectre v2 BHB attacks!\n" +void unpriv_ebpf_notify(int new_state) +{ + if (spectre_v2_state == SPECTRE_VULNERABLE || + spectre_bhb_state != SPECTRE_MITIGATED) + return; + + if (!new_state) + pr_err("WARNING: %s", EBPF_WARN); +} +#endif diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 50bab186c49b..edaf0faf766f 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -341,7 +341,7 @@ ASSERT(__hibernate_exit_text_end - (__hibernate_exit_text_start & ~(SZ_4K - 1)) <= SZ_4K, "Hibernate exit text too big or misaligned") #endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) == PAGE_SIZE, +ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE, "Entry trampoline text too big") #endif #ifdef CONFIG_KVM diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index ecc5958e27fe..4dca6ffd03d4 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1491,10 +1491,7 @@ static int kvm_init_vector_slots(void) base = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs)); kvm_init_vector_slot(base, HYP_VECTOR_SPECTRE_DIRECT); - if (!cpus_have_const_cap(ARM64_SPECTRE_V3A)) - return 0; - - if (!has_vhe()) { + if (kvm_system_needs_idmapped_vectors() && !has_vhe()) { err = create_hyp_exec_mappings(__pa_symbol(__bp_harden_hyp_vecs), __BP_HARDEN_HYP_VECS_SZ, &base); if (err) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S index b6b6801d96d5..7839d075729b 100644 --- a/arch/arm64/kvm/hyp/hyp-entry.S +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -62,6 +62,10 @@ el1_sync: // Guest trapped into EL2 /* ARM_SMCCC_ARCH_WORKAROUND_2 handling */ eor w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_1 ^ \ ARM_SMCCC_ARCH_WORKAROUND_2) + cbz w1, wa_epilogue + + eor w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_2 ^ \ + ARM_SMCCC_ARCH_WORKAROUND_3) cbnz w1, el1_trap wa_epilogue: @@ -192,7 +196,10 @@ SYM_CODE_END(__kvm_hyp_vector) sub sp, sp, #(8 * 4) stp x2, x3, [sp, #(8 * 0)] stp x0, x1, [sp, #(8 * 2)] + alternative_cb spectre_bhb_patch_wa3 + /* Patched to mov WA3 when supported */ mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 + alternative_cb_end smc #0 ldp x2, x3, [sp, #(8 * 0)] add sp, sp, #(8 * 2) @@ -205,6 +212,8 @@ SYM_CODE_END(__kvm_hyp_vector) spectrev2_smccc_wa1_smc .else stp x0, x1, [sp, #-16]! + mitigate_spectre_bhb_loop x0 + mitigate_spectre_bhb_clear_insn .endif .if \indirect != 0 alternative_cb kvm_patch_vector_branch diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c index 526a7d6fa86f..cdbe8e246418 100644 --- a/arch/arm64/kvm/hyp/nvhe/mm.c +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -148,8 +148,10 @@ int hyp_map_vectors(void) phys_addr_t phys; void *bp_base; - if (!cpus_have_const_cap(ARM64_SPECTRE_V3A)) + if (!kvm_system_needs_idmapped_vectors()) { + __hyp_bp_vect_base = __bp_harden_hyp_vecs; return 0; + } phys = __hyp_pa(__bp_harden_hyp_vecs); bp_base = (void *)__pkvm_create_private_mapping(phys, diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 11d053fdd604..54af47005e45 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -10,6 +10,7 @@ #include <linux/kvm_host.h> #include <linux/types.h> #include <linux/jump_label.h> +#include <linux/percpu.h> #include <uapi/linux/psci.h> #include <kvm/arm_psci.h> @@ -24,6 +25,8 @@ #include <asm/fpsimd.h> #include <asm/debug-monitors.h> #include <asm/processor.h> +#include <asm/thread_info.h> +#include <asm/vectors.h> /* VHE specific context */ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); @@ -67,7 +70,7 @@ NOKPROBE_SYMBOL(__activate_traps); static void __deactivate_traps(struct kvm_vcpu *vcpu) { - extern char vectors[]; /* kernel exception vectors */ + const char *host_vectors = vectors; ___deactivate_traps(vcpu); @@ -81,7 +84,10 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); - write_sysreg(vectors, vbar_el1); + + if (!arm64_kernel_unmapped_at_el0()) + host_vectors = __this_cpu_read(this_cpu_vector); + write_sysreg(host_vectors, vbar_el1); } NOKPROBE_SYMBOL(__deactivate_traps); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 30da78f72b3b..202b8c455724 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -107,6 +107,18 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu) break; } break; + case ARM_SMCCC_ARCH_WORKAROUND_3: + switch (arm64_get_spectre_bhb_state()) { + case SPECTRE_VULNERABLE: + break; + case SPECTRE_MITIGATED: + val[0] = SMCCC_RET_SUCCESS; + break; + case SPECTRE_UNAFFECTED: + val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED; + break; + } + break; case ARM_SMCCC_HV_PV_TIME_FEATURES: val[0] = SMCCC_RET_SUCCESS; break; diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c index 2ce60fecd861..5918095c90a5 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -405,7 +405,7 @@ int kvm_psci_call(struct kvm_vcpu *vcpu) int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) { - return 3; /* PSCI version and two workaround registers */ + return 4; /* PSCI version and three workaround registers */ } int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) @@ -419,6 +419,9 @@ int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, uindices++)) return -EFAULT; + if (put_user(KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, uindices++)) + return -EFAULT; + return 0; } @@ -458,6 +461,17 @@ static int get_kernel_wa_level(u64 regid) case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; } + break; + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: + switch (arm64_get_spectre_bhb_state()) { + case SPECTRE_VULNERABLE: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; + case SPECTRE_MITIGATED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL; + case SPECTRE_UNAFFECTED: + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED; + } + return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; } return -EINVAL; @@ -474,6 +488,7 @@ int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK; break; default: @@ -519,6 +534,7 @@ int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) } case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: + case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: if (val & ~KVM_REG_FEATURE_LEVEL_MASK) return -EINVAL; diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index a38f54cd638c..77ada00280d9 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -7,8 +7,10 @@ #include <linux/io.h> #include <linux/memblock.h> +#include <linux/mm.h> #include <linux/types.h> +#include <asm/cpufeature.h> #include <asm/page.h> /* @@ -38,3 +40,18 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) { return !(((pfn << PAGE_SHIFT) + size) & ~PHYS_MASK); } + +static int __init adjust_protection_map(void) +{ + /* + * With Enhanced PAN we can honour the execute-only permissions as + * there is no PAN override with such mappings. + */ + if (cpus_have_const_cap(ARM64_HAS_EPAN)) { + protection_map[VM_EXEC] = PAGE_EXECONLY; + protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY; + } + + return 0; +} +arch_initcall(adjust_protection_map); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index acfae9b41cc8..49abbf43bf35 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -617,6 +617,8 @@ early_param("rodata", parse_rodata); #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 static int __init map_entry_trampoline(void) { + int i; + pgprot_t prot = rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC; phys_addr_t pa_start = __pa_symbol(__entry_tramp_text_start); @@ -625,11 +627,15 @@ static int __init map_entry_trampoline(void) /* Map only the text into the trampoline page table */ memset(tramp_pg_dir, 0, PGD_SIZE); - __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE, - prot, __pgd_pgtable_alloc, 0); + __create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, + entry_tramp_text_size(), prot, + __pgd_pgtable_alloc, NO_BLOCK_MAPPINGS); /* Map both the text and data into the kernel page table */ - __set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot); + for (i = 0; i < DIV_ROUND_UP(entry_tramp_text_size(), PAGE_SIZE); i++) + __set_fixmap(FIX_ENTRY_TRAMP_TEXT1 - i, + pa_start + i * PAGE_SIZE, prot); + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern char __entry_tramp_data_start[]; diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 9c65b1e25a96..cea7533cb304 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -44,6 +44,7 @@ MTE_ASYMM SPECTRE_V2 SPECTRE_V3A SPECTRE_V4 +SPECTRE_BHB SSBS SVE UNMAP_KERNEL_AT_EL0 diff --git a/arch/powerpc/include/asm/book3s/64/mmu.h b/arch/powerpc/include/asm/book3s/64/mmu.h index ba5b1becf518..006cbec70ffe 100644 --- a/arch/powerpc/include/asm/book3s/64/mmu.h +++ b/arch/powerpc/include/asm/book3s/64/mmu.h @@ -202,7 +202,6 @@ static inline struct subpage_prot_table *mm_ctx_subpage_prot(mm_context_t *ctx) /* * The current system page and segment sizes */ -extern int mmu_linear_psize; extern int mmu_virtual_psize; extern int mmu_vmalloc_psize; extern int mmu_io_psize; @@ -213,6 +212,7 @@ extern int mmu_io_psize; #define mmu_virtual_psize MMU_PAGE_4K #endif #endif +extern int mmu_linear_psize; extern int mmu_vmemmap_psize; /* MMU initialization */ diff --git a/arch/powerpc/include/asm/kexec_ranges.h b/arch/powerpc/include/asm/kexec_ranges.h index 7a90000f8d15..f83866a19e87 100644 --- a/arch/powerpc/include/asm/kexec_ranges.h +++ b/arch/powerpc/include/asm/kexec_ranges.h @@ -9,7 +9,7 @@ struct crash_mem *realloc_mem_ranges(struct crash_mem **mem_ranges); int add_mem_range(struct crash_mem **mem_ranges, u64 base, u64 size); int add_tce_mem_ranges(struct crash_mem **mem_ranges); int add_initrd_mem_range(struct crash_mem **mem_ranges); -#ifdef CONFIG_PPC_BOOK3S_64 +#ifdef CONFIG_PPC_64S_HASH_MMU int add_htab_mem_range(struct crash_mem **mem_ranges); #else static inline int add_htab_mem_range(struct crash_mem **mem_ranges) diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi index 56f57118c633..44d338514761 100644 --- a/arch/riscv/boot/dts/canaan/k210.dtsi +++ b/arch/riscv/boot/dts/canaan/k210.dtsi @@ -113,7 +113,8 @@ compatible = "canaan,k210-plic", "sifive,plic-1.0.0"; reg = <0xC000000 0x4000000>; interrupt-controller; - interrupts-extended = <&cpu0_intc 11>, <&cpu1_intc 11>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>; riscv,ndev = <65>; }; diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 160e3a1e8f8b..004372f8da54 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -119,7 +119,7 @@ extern phys_addr_t phys_ram_base; ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) #define is_linear_mapping(x) \ - ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < kernel_map.virt_addr)) + ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < PAGE_OFFSET + KERN_VIRT_SIZE)) #define linear_mapping_pa_to_va(x) ((void *)((unsigned long)(x) + kernel_map.va_pa_offset)) #define kernel_mapping_pa_to_va(y) ({ \ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 7e949f25c933..e3549e50de95 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -13,6 +13,7 @@ #ifndef CONFIG_MMU #define KERNEL_LINK_ADDR PAGE_OFFSET +#define KERN_VIRT_SIZE (UL(-1)) #else #define ADDRESS_SPACE_END (UL(-1)) diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index 7ebaef10ea1b..ac7a25298a04 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -24,6 +24,9 @@ obj-$(CONFIG_KASAN) += kasan_init.o ifdef CONFIG_KASAN KASAN_SANITIZE_kasan_init.o := n KASAN_SANITIZE_init.o := n +ifdef CONFIG_DEBUG_VIRTUAL +KASAN_SANITIZE_physaddr.o := n +endif endif obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index c27294128e18..0d588032d6e6 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -125,7 +125,6 @@ void __init mem_init(void) else swiotlb_force = SWIOTLB_NO_FORCE; #endif - high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); memblock_free_all(); print_vm_layout(); @@ -195,6 +194,7 @@ static void __init setup_bootmem(void) min_low_pfn = PFN_UP(phys_ram_base); max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end); + high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index f61f7ca6fe0f..cd1a145257b7 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -113,8 +113,11 @@ static void __init kasan_populate_pud(pgd_t *pgd, base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd))); } else { base_pud = (pud_t *)pgd_page_vaddr(*pgd); - if (base_pud == lm_alias(kasan_early_shadow_pud)) + if (base_pud == lm_alias(kasan_early_shadow_pud)) { base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); + memcpy(base_pud, (void *)kasan_early_shadow_pud, + sizeof(pud_t) * PTRS_PER_PUD); + } } pudp = base_pud + pud_index(vaddr); @@ -202,8 +205,7 @@ asmlinkage void __init kasan_early_init(void) for (i = 0; i < PTRS_PER_PTE; ++i) set_pte(kasan_early_shadow_pte + i, - mk_pte(virt_to_page(kasan_early_shadow_page), - PAGE_KERNEL)); + pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL)); for (i = 0; i < PTRS_PER_PMD; ++i) set_pmd(kasan_early_shadow_pmd + i, diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c index e7fd0c253c7b..19cf25a74ee2 100644 --- a/arch/riscv/mm/physaddr.c +++ b/arch/riscv/mm/physaddr.c @@ -8,12 +8,10 @@ phys_addr_t __virt_to_phys(unsigned long x) { - phys_addr_t y = x - PAGE_OFFSET; - /* * Boundary checking aginst the kernel linear mapping space. */ - WARN(y >= KERN_VIRT_SIZE, + WARN(!is_linear_mapping(x) && !is_kernel_mapping(x), "virt_to_phys used for non-linear address: %pK (%pS)\n", (void *)x, (void *)x); diff --git a/arch/s390/include/asm/extable.h b/arch/s390/include/asm/extable.h index 16dc57dd90b3..8511f0e59290 100644 --- a/arch/s390/include/asm/extable.h +++ b/arch/s390/include/asm/extable.h @@ -69,8 +69,13 @@ static inline void swap_ex_entry_fixup(struct exception_table_entry *a, { a->fixup = b->fixup + delta; b->fixup = tmp.fixup - delta; - a->handler = b->handler + delta; - b->handler = tmp.handler - delta; + a->handler = b->handler; + if (a->handler) + a->handler += delta; + b->handler = tmp.handler; + if (b->handler) + b->handler -= delta; } +#define swap_ex_entry_fixup swap_ex_entry_fixup #endif diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index 267f70f4393f..6f80ec9c04be 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -47,15 +47,17 @@ struct ftrace_regs { static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs) { - return &fregs->regs; + struct pt_regs *regs = &fregs->regs; + + if (test_pt_regs_flag(regs, PIF_FTRACE_FULL_REGS)) + return regs; + return NULL; } static __always_inline void ftrace_instruction_pointer_set(struct ftrace_regs *fregs, unsigned long ip) { - struct pt_regs *regs = arch_ftrace_get_regs(fregs); - - regs->psw.addr = ip; + fregs->regs.psw.addr = ip; } /* diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h index 4ffa8e7f0ed3..ddb70fb13fbc 100644 --- a/arch/s390/include/asm/ptrace.h +++ b/arch/s390/include/asm/ptrace.h @@ -15,11 +15,13 @@ #define PIF_EXECVE_PGSTE_RESTART 1 /* restart execve for PGSTE binaries */ #define PIF_SYSCALL_RET_SET 2 /* return value was set via ptrace */ #define PIF_GUEST_FAULT 3 /* indicates program check in sie64a */ +#define PIF_FTRACE_FULL_REGS 4 /* all register contents valid (ftrace) */ #define _PIF_SYSCALL BIT(PIF_SYSCALL) #define _PIF_EXECVE_PGSTE_RESTART BIT(PIF_EXECVE_PGSTE_RESTART) #define _PIF_SYSCALL_RET_SET BIT(PIF_SYSCALL_RET_SET) #define _PIF_GUEST_FAULT BIT(PIF_GUEST_FAULT) +#define _PIF_FTRACE_FULL_REGS BIT(PIF_FTRACE_FULL_REGS) #ifndef __ASSEMBLY__ diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 21d62d8b6b9a..89c0870d5679 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -159,9 +159,38 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) return 0; } +static struct ftrace_hotpatch_trampoline *ftrace_get_trampoline(struct dyn_ftrace *rec) +{ + struct ftrace_hotpatch_trampoline *trampoline; + struct ftrace_insn insn; + s64 disp; + u16 opc; + + if (copy_from_kernel_nofault(&insn, (void *)rec->ip, sizeof(insn))) + return ERR_PTR(-EFAULT); + disp = (s64)insn.disp * 2; + trampoline = (void *)(rec->ip + disp); + if (get_kernel_nofault(opc, &trampoline->brasl_opc)) + return ERR_PTR(-EFAULT); + if (opc != 0xc015) + return ERR_PTR(-EINVAL); + return trampoline; +} + int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { + struct ftrace_hotpatch_trampoline *trampoline; + u64 old; + + trampoline = ftrace_get_trampoline(rec); + if (IS_ERR(trampoline)) + return PTR_ERR(trampoline); + if (get_kernel_nofault(old, &trampoline->interceptor)) + return -EFAULT; + if (old != old_addr) + return -EINVAL; + s390_kernel_write(&trampoline->interceptor, &addr, sizeof(addr)); return 0; } @@ -188,6 +217,12 @@ static void brcl_enable(void *brcl) int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { + struct ftrace_hotpatch_trampoline *trampoline; + + trampoline = ftrace_get_trampoline(rec); + if (IS_ERR(trampoline)) + return PTR_ERR(trampoline); + s390_kernel_write(&trampoline->interceptor, &addr, sizeof(addr)); brcl_enable((void *)rec->ip); return 0; } @@ -291,7 +326,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, regs = ftrace_get_regs(fregs); p = get_kprobe((kprobe_opcode_t *)ip); - if (unlikely(!p) || kprobe_disabled(p)) + if (!regs || unlikely(!p) || kprobe_disabled(p)) goto out; if (kprobe_running()) { diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 39bcc0e39a10..a24177dcd12a 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -27,6 +27,7 @@ ENDPROC(ftrace_stub) #define STACK_PTREGS_GPRS (STACK_PTREGS + __PT_GPRS) #define STACK_PTREGS_PSW (STACK_PTREGS + __PT_PSW) #define STACK_PTREGS_ORIG_GPR2 (STACK_PTREGS + __PT_ORIG_GPR2) +#define STACK_PTREGS_FLAGS (STACK_PTREGS + __PT_FLAGS) #ifdef __PACK_STACK /* allocate just enough for r14, r15 and backchain */ #define TRACED_FUNC_FRAME_SIZE 24 @@ -57,6 +58,14 @@ ENDPROC(ftrace_stub) .if \allregs == 1 stg %r14,(STACK_PTREGS_PSW)(%r15) stosm (STACK_PTREGS_PSW)(%r15),0 +#ifdef CONFIG_HAVE_MARCH_Z10_FEATURES + mvghi STACK_PTREGS_FLAGS(%r15),_PIF_FTRACE_FULL_REGS +#else + lghi %r14,_PIF_FTRACE_FULL_REGS + stg %r14,STACK_PTREGS_FLAGS(%r15) +#endif + .else + xc STACK_PTREGS_FLAGS(8,%r15),STACK_PTREGS_FLAGS(%r15) .endif lg %r14,(__SF_GPRS+8*8)(%r1) # restore original return address diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index f2c25d113e7b..05327be3a982 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -800,6 +800,8 @@ static void __init check_initrd(void) static void __init reserve_kernel(void) { memblock_reserve(0, STARTUP_NORMAL_OFFSET); + memblock_reserve(OLDMEM_BASE, sizeof(unsigned long)); + memblock_reserve(OLDMEM_SIZE, sizeof(unsigned long)); memblock_reserve(__amode31_base, __eamode31 - __samode31); memblock_reserve(__pa(sclp_early_sccb), EXT_SCCB_READ_SCP); memblock_reserve(__pa(_stext), _end - _stext); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6db4e2932b3d..65d147974f8d 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -204,7 +204,7 @@ /* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCE for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index cc74dc584836..acbaeaf83b61 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -84,7 +84,7 @@ #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else jmp *%\reg #endif @@ -94,7 +94,7 @@ #ifdef CONFIG_RETPOLINE ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \ __stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_LFENCE #else call *%\reg #endif @@ -146,7 +146,7 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ - X86_FEATURE_RETPOLINE_AMD) + X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "r" (addr) @@ -176,7 +176,7 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ - X86_FEATURE_RETPOLINE_AMD) + X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif @@ -188,9 +188,11 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[]; /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, - SPECTRE_V2_RETPOLINE_GENERIC, - SPECTRE_V2_RETPOLINE_AMD, - SPECTRE_V2_IBRS_ENHANCED, + SPECTRE_V2_RETPOLINE, + SPECTRE_V2_LFENCE, + SPECTRE_V2_EIBRS, + SPECTRE_V2_EIBRS_RETPOLINE, + SPECTRE_V2_EIBRS_LFENCE, }; /* The indirect branch speculation control variants */ diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 018b61febf0e..b4e576600969 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -389,7 +389,7 @@ static int emit_indirect(int op, int reg, u8 *bytes) * * CALL *%\reg * - * It also tries to inline spectre_v2=retpoline,amd when size permits. + * It also tries to inline spectre_v2=retpoline,lfence when size permits. */ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) { @@ -407,7 +407,7 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) BUG_ON(reg == 4); if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) && - !cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) + !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) return -1; op = insn->opcode.bytes[0]; @@ -438,9 +438,9 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) } /* - * For RETPOLINE_AMD: prepend the indirect CALL/JMP with an LFENCE. + * For RETPOLINE_LFENCE: prepend the indirect CALL/JMP with an LFENCE. */ - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) { + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { bytes[i++] = 0x0f; bytes[i++] = 0xae; bytes[i++] = 0xe8; /* LFENCE */ diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1c1f218a701d..6296e1ebed1d 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -16,6 +16,7 @@ #include <linux/prctl.h> #include <linux/sched/smt.h> #include <linux/pgtable.h> +#include <linux/bpf.h> #include <asm/spec-ctrl.h> #include <asm/cmdline.h> @@ -650,6 +651,32 @@ static inline const char *spectre_v2_module_string(void) static inline const char *spectre_v2_module_string(void) { return ""; } #endif +#define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n" +#define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n" +#define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n" + +#ifdef CONFIG_BPF_SYSCALL +void unpriv_ebpf_notify(int new_state) +{ + if (new_state) + return; + + /* Unprivileged eBPF is enabled */ + + switch (spectre_v2_enabled) { + case SPECTRE_V2_EIBRS: + pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); + break; + case SPECTRE_V2_EIBRS_LFENCE: + if (sched_smt_active()) + pr_err(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); + break; + default: + break; + } +} +#endif + static inline bool match_option(const char *arg, int arglen, const char *opt) { int len = strlen(opt); @@ -664,7 +691,10 @@ enum spectre_v2_mitigation_cmd { SPECTRE_V2_CMD_FORCE, SPECTRE_V2_CMD_RETPOLINE, SPECTRE_V2_CMD_RETPOLINE_GENERIC, - SPECTRE_V2_CMD_RETPOLINE_AMD, + SPECTRE_V2_CMD_RETPOLINE_LFENCE, + SPECTRE_V2_CMD_EIBRS, + SPECTRE_V2_CMD_EIBRS_RETPOLINE, + SPECTRE_V2_CMD_EIBRS_LFENCE, }; enum spectre_v2_user_cmd { @@ -737,6 +767,13 @@ spectre_v2_parse_user_cmdline(enum spectre_v2_mitigation_cmd v2_cmd) return SPECTRE_V2_USER_CMD_AUTO; } +static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) +{ + return (mode == SPECTRE_V2_EIBRS || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_EIBRS_LFENCE); +} + static void __init spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) { @@ -804,7 +841,7 @@ spectre_v2_user_select_mitigation(enum spectre_v2_mitigation_cmd v2_cmd) */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return; /* @@ -824,9 +861,11 @@ set_mode: static const char * const spectre_v2_strings[] = { [SPECTRE_V2_NONE] = "Vulnerable", - [SPECTRE_V2_RETPOLINE_GENERIC] = "Mitigation: Full generic retpoline", - [SPECTRE_V2_RETPOLINE_AMD] = "Mitigation: Full AMD retpoline", - [SPECTRE_V2_IBRS_ENHANCED] = "Mitigation: Enhanced IBRS", + [SPECTRE_V2_RETPOLINE] = "Mitigation: Retpolines", + [SPECTRE_V2_LFENCE] = "Mitigation: LFENCE", + [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", + [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", + [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", }; static const struct { @@ -837,8 +876,12 @@ static const struct { { "off", SPECTRE_V2_CMD_NONE, false }, { "on", SPECTRE_V2_CMD_FORCE, true }, { "retpoline", SPECTRE_V2_CMD_RETPOLINE, false }, - { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_AMD, false }, + { "retpoline,amd", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false }, + { "retpoline,lfence", SPECTRE_V2_CMD_RETPOLINE_LFENCE, false }, { "retpoline,generic", SPECTRE_V2_CMD_RETPOLINE_GENERIC, false }, + { "eibrs", SPECTRE_V2_CMD_EIBRS, false }, + { "eibrs,lfence", SPECTRE_V2_CMD_EIBRS_LFENCE, false }, + { "eibrs,retpoline", SPECTRE_V2_CMD_EIBRS_RETPOLINE, false }, { "auto", SPECTRE_V2_CMD_AUTO, false }, }; @@ -875,10 +918,30 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) } if ((cmd == SPECTRE_V2_CMD_RETPOLINE || - cmd == SPECTRE_V2_CMD_RETPOLINE_AMD || - cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC) && + cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE || + cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC || + cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || + cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && !IS_ENABLED(CONFIG_RETPOLINE)) { - pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); + pr_err("%s selected but not compiled in. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if ((cmd == SPECTRE_V2_CMD_EIBRS || + cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || + cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { + pr_err("%s selected but CPU doesn't have eIBRS. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if ((cmd == SPECTRE_V2_CMD_RETPOLINE_LFENCE || + cmd == SPECTRE_V2_CMD_EIBRS_LFENCE) && + !boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { + pr_err("%s selected, but CPU doesn't have a serializing LFENCE. Switching to AUTO select\n", + mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; } @@ -887,6 +950,16 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return cmd; } +static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) +{ + if (!IS_ENABLED(CONFIG_RETPOLINE)) { + pr_err("Kernel not compiled with retpoline; no mitigation available!"); + return SPECTRE_V2_NONE; + } + + return SPECTRE_V2_RETPOLINE; +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -907,49 +980,64 @@ static void __init spectre_v2_select_mitigation(void) case SPECTRE_V2_CMD_FORCE: case SPECTRE_V2_CMD_AUTO: if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) { - mode = SPECTRE_V2_IBRS_ENHANCED; - /* Force it so VMEXIT will restore correctly */ - x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); - goto specv2_set_mode; + mode = SPECTRE_V2_EIBRS; + break; } - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_auto; + + mode = spectre_v2_select_retpoline(); break; - case SPECTRE_V2_CMD_RETPOLINE_AMD: - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_amd; + + case SPECTRE_V2_CMD_RETPOLINE_LFENCE: + pr_err(SPECTRE_V2_LFENCE_MSG); + mode = SPECTRE_V2_LFENCE; break; + case SPECTRE_V2_CMD_RETPOLINE_GENERIC: - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_generic; + mode = SPECTRE_V2_RETPOLINE; break; + case SPECTRE_V2_CMD_RETPOLINE: - if (IS_ENABLED(CONFIG_RETPOLINE)) - goto retpoline_auto; + mode = spectre_v2_select_retpoline(); + break; + + case SPECTRE_V2_CMD_EIBRS: + mode = SPECTRE_V2_EIBRS; + break; + + case SPECTRE_V2_CMD_EIBRS_LFENCE: + mode = SPECTRE_V2_EIBRS_LFENCE; + break; + + case SPECTRE_V2_CMD_EIBRS_RETPOLINE: + mode = SPECTRE_V2_EIBRS_RETPOLINE; break; } - pr_err("Spectre mitigation: kernel not compiled with retpoline; no mitigation available!"); - return; -retpoline_auto: - if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { - retpoline_amd: - if (!boot_cpu_has(X86_FEATURE_LFENCE_RDTSC)) { - pr_err("Spectre mitigation: LFENCE not serializing, switching to generic retpoline\n"); - goto retpoline_generic; - } - mode = SPECTRE_V2_RETPOLINE_AMD; - setup_force_cpu_cap(X86_FEATURE_RETPOLINE_AMD); - setup_force_cpu_cap(X86_FEATURE_RETPOLINE); - } else { - retpoline_generic: - mode = SPECTRE_V2_RETPOLINE_GENERIC; + if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) + pr_err(SPECTRE_V2_EIBRS_EBPF_MSG); + + if (spectre_v2_in_eibrs_mode(mode)) { + /* Force it so VMEXIT will restore correctly */ + x86_spec_ctrl_base |= SPEC_CTRL_IBRS; + wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + } + + switch (mode) { + case SPECTRE_V2_NONE: + case SPECTRE_V2_EIBRS: + break; + + case SPECTRE_V2_LFENCE: + case SPECTRE_V2_EIBRS_LFENCE: + setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE); + fallthrough; + + case SPECTRE_V2_RETPOLINE: + case SPECTRE_V2_EIBRS_RETPOLINE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE); + break; } -specv2_set_mode: spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -975,7 +1063,7 @@ specv2_set_mode: * the CPU supports Enhanced IBRS, kernel might un-intentionally not * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) { + if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_eibrs_mode(mode)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } @@ -1045,6 +1133,10 @@ void cpu_bugs_smt_update(void) { mutex_lock(&spec_ctrl_mutex); + if (sched_smt_active() && unprivileged_ebpf_enabled() && + spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) + pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); + switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: break; @@ -1684,7 +1776,7 @@ static ssize_t tsx_async_abort_show_state(char *buf) static char *stibp_state(void) { - if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return ""; switch (spectre_v2_user_stibp) { @@ -1714,6 +1806,27 @@ static char *ibpb_state(void) return ""; } +static ssize_t spectre_v2_show_state(char *buf) +{ + if (spectre_v2_enabled == SPECTRE_V2_LFENCE) + return sprintf(buf, "Vulnerable: LFENCE\n"); + + if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) + return sprintf(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); + + if (sched_smt_active() && unprivileged_ebpf_enabled() && + spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) + return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); + + return sprintf(buf, "%s%s%s%s%s%s\n", + spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + stibp_state(), + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + spectre_v2_module_string()); +} + static ssize_t srbds_show_state(char *buf) { return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); @@ -1739,12 +1852,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: - return sprintf(buf, "%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], - ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", - spectre_v2_module_string()); + return spectre_v2_show_state(buf); case X86_BUG_SPEC_STORE_BYPASS: return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index f734e3b0cfec..d77481ecb0d5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -463,6 +463,7 @@ static bool pv_tlb_flush_supported(void) return (kvm_para_has_feature(KVM_FEATURE_PV_TLB_FLUSH) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && + !boot_cpu_has(X86_FEATURE_MWAIT) && (num_possible_cpus() != 1)); } @@ -477,6 +478,7 @@ static bool pv_sched_yield_supported(void) return (kvm_para_has_feature(KVM_FEATURE_PV_SCHED_YIELD) && !kvm_para_has_hint(KVM_HINTS_REALTIME) && kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && + !boot_cpu_has(X86_FEATURE_MWAIT) && (num_possible_cpus() != 1)); } @@ -622,7 +624,7 @@ static void kvm_smp_send_call_func_ipi(const struct cpumask *mask) /* Make sure other vCPUs get a chance to run if they need to. */ for_each_cpu(cpu, mask) { - if (vcpu_is_preempted(cpu)) { + if (!idle_cpu(cpu) && vcpu_is_preempted(cpu)) { kvm_hypercall1(KVM_HC_SCHED_YIELD, per_cpu(x86_cpu_to_apicid, cpu)); break; } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index a35cbf9107af..c5caa7311bd8 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -239,6 +239,9 @@ static void __init kvmclock_init_mem(void) static int __init kvm_setup_vsyscall_timeinfo(void) { + if (!kvm_para_available() || !kvmclock) + return 0; + kvmclock_init_mem(); #ifdef CONFIG_X86_64 diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 8e24f73bf60b..5628d0ba637e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3565,7 +3565,7 @@ set_root_pgd: out_unlock: write_unlock(&vcpu->kvm->mmu_lock); - return 0; + return r; } static int mmu_alloc_special_roots(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 82a9dcd8c67f..eb4029660bd9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9180,6 +9180,7 @@ static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) likely(!pic_in_kernel(vcpu->kvm)); } +/* Called within kvm->srcu read side. */ static void post_kvm_run_save(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; @@ -9188,16 +9189,9 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); - /* - * The call to kvm_ready_for_interrupt_injection() may end up in - * kvm_xen_has_interrupt() which may require the srcu lock to be - * held, to protect against changes in the vcpu_info address. - */ - vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (is_smm(vcpu)) kvm_run->flags |= KVM_RUN_X86_SMM; @@ -9815,6 +9809,7 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); /* + * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without * exiting to the userspace. Otherwise, the value will be returned to the * userspace. @@ -10193,6 +10188,7 @@ out: return r; } +/* Called within kvm->srcu read side. */ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { bool hv_timer; @@ -10252,12 +10248,12 @@ static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted); } +/* Called within kvm->srcu read side. */ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; struct kvm *kvm = vcpu->kvm; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); vcpu->arch.l1tf_flush_l1d = true; for (;;) { @@ -10285,14 +10281,12 @@ static int vcpu_run(struct kvm_vcpu *vcpu) if (__xfer_to_guest_mode_work_pending()) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); r = xfer_to_guest_mode_handle_work(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (r) return r; - vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } - srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); - return r; } @@ -10398,6 +10392,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_run *kvm_run = vcpu->run; + struct kvm *kvm = vcpu->kvm; int r; vcpu_load(vcpu); @@ -10405,6 +10400,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { if (kvm_run->immediate_exit) { r = -EINTR; @@ -10415,7 +10411,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) * use before KVM has ever run the vCPU. */ WARN_ON_ONCE(kvm_lapic_hv_timer_in_use(vcpu)); + + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); + if (kvm_apic_accept_events(vcpu) < 0) { r = 0; goto out; @@ -10475,8 +10475,9 @@ out: if (kvm_run->kvm_valid_regs) store_regs(vcpu); post_kvm_run_save(vcpu); - kvm_sigset_deactivate(vcpu); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + kvm_sigset_deactivate(vcpu); vcpu_put(vcpu); return r; } diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 89b3fb244e15..afbdda539b80 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -34,7 +34,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \ __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \ - __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_AMD + __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE .endm diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index e6ff8f4f9ea4..6b8de13faf83 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -390,7 +390,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) u8 *prog = *pprog; #ifdef CONFIG_RETPOLINE - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) { + if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { diff --git a/block/blk-mq.c b/block/blk-mq.c index d69ca91fbc8b..9a9185a0a2d1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2718,7 +2718,8 @@ static bool blk_mq_attempt_bio_merge(struct request_queue *q, static struct request *blk_mq_get_new_requests(struct request_queue *q, struct blk_plug *plug, - struct bio *bio) + struct bio *bio, + unsigned int nsegs) { struct blk_mq_alloc_data data = { .q = q, @@ -2730,6 +2731,11 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, if (unlikely(bio_queue_enter(bio))) return NULL; + if (blk_mq_attempt_bio_merge(q, bio, nsegs)) + goto queue_exit; + + rq_qos_throttle(q, bio); + if (plug) { data.nr_tags = plug->nr_ios; plug->nr_ios = 1; @@ -2742,12 +2748,13 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); +queue_exit: blk_queue_exit(q); return NULL; } static inline struct request *blk_mq_get_cached_request(struct request_queue *q, - struct blk_plug *plug, struct bio *bio) + struct blk_plug *plug, struct bio **bio, unsigned int nsegs) { struct request *rq; @@ -2757,12 +2764,19 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, if (!rq || rq->q != q) return NULL; - if (blk_mq_get_hctx_type(bio->bi_opf) != rq->mq_hctx->type) + if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) { + *bio = NULL; + return NULL; + } + + rq_qos_throttle(q, *bio); + + if (blk_mq_get_hctx_type((*bio)->bi_opf) != rq->mq_hctx->type) return NULL; - if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf)) + if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf)) return NULL; - rq->cmd_flags = bio->bi_opf; + rq->cmd_flags = (*bio)->bi_opf; plug->cached_rq = rq_list_next(rq); INIT_LIST_HEAD(&rq->queuelist); return rq; @@ -2800,14 +2814,11 @@ void blk_mq_submit_bio(struct bio *bio) if (!bio_integrity_prep(bio)) return; - if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) - return; - - rq_qos_throttle(q, bio); - - rq = blk_mq_get_cached_request(q, plug, bio); + rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs); if (!rq) { - rq = blk_mq_get_new_requests(q, plug, bio); + if (!bio) + return; + rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); if (unlikely(!rq)) return; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index c443cd64fc9b..8c415be86732 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -76,9 +76,6 @@ struct virtio_blk { */ refcount_t refs; - /* What host tells us, plus 2 for header & tailer. */ - unsigned int sg_elems; - /* Ida index - used to track minor number allocations. */ int index; @@ -322,8 +319,6 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, blk_status_t status; int err; - BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); - status = virtblk_setup_cmd(vblk->vdev, req, vbr); if (unlikely(status)) return status; @@ -783,8 +778,6 @@ static int virtblk_probe(struct virtio_device *vdev) /* Prevent integer overflows and honor max vq size */ sg_elems = min_t(u32, sg_elems, VIRTIO_BLK_MAX_SG_ELEMS - 2); - /* We need extra sg elements at head and tail. */ - sg_elems += 2; vdev->priv = vblk = kmalloc(sizeof(*vblk), GFP_KERNEL); if (!vblk) { err = -ENOMEM; @@ -796,7 +789,6 @@ static int virtblk_probe(struct virtio_device *vdev) mutex_init(&vblk->vdev_mutex); vblk->vdev = vdev; - vblk->sg_elems = sg_elems; INIT_WORK(&vblk->config_work, virtblk_config_changed_work); @@ -853,7 +845,7 @@ static int virtblk_probe(struct virtio_device *vdev) set_disk_ro(vblk->disk, 1); /* We can handle whatever the host told us to handle. */ - blk_queue_max_segments(q, vblk->sg_elems-2); + blk_queue_max_segments(q, sg_elems); /* No real sector limit. */ blk_queue_max_hw_sectors(q, -1U); @@ -925,9 +917,15 @@ static int virtblk_probe(struct virtio_device *vdev) virtio_cread(vdev, struct virtio_blk_config, max_discard_seg, &v); + + /* + * max_discard_seg == 0 is out of spec but we always + * handled it. + */ + if (!v) + v = sg_elems; blk_queue_max_discard_segments(q, - min_not_zero(v, - MAX_DISCARD_SEGMENTS)); + min(v, MAX_DISCARD_SEGMENTS)); blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index ca71a0585333..03b5fb341e58 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1288,7 +1288,8 @@ free_shadow: rinfo->ring_ref[i] = GRANT_INVALID_REF; } } - free_pages((unsigned long)rinfo->ring.sring, get_order(info->nr_ring_pages * XEN_PAGE_SIZE)); + free_pages_exact(rinfo->ring.sring, + info->nr_ring_pages * XEN_PAGE_SIZE); rinfo->ring.sring = NULL; if (rinfo->irq) @@ -1372,9 +1373,15 @@ static int blkif_get_final_status(enum blk_req_status s1, return BLKIF_RSP_OKAY; } -static bool blkif_completion(unsigned long *id, - struct blkfront_ring_info *rinfo, - struct blkif_response *bret) +/* + * Return values: + * 1 response processed. + * 0 missing further responses. + * -1 error while processing. + */ +static int blkif_completion(unsigned long *id, + struct blkfront_ring_info *rinfo, + struct blkif_response *bret) { int i = 0; struct scatterlist *sg; @@ -1397,7 +1404,7 @@ static bool blkif_completion(unsigned long *id, /* Wait the second response if not yet here. */ if (s2->status < REQ_DONE) - return false; + return 0; bret->status = blkif_get_final_status(s->status, s2->status); @@ -1448,42 +1455,43 @@ static bool blkif_completion(unsigned long *id, } /* Add the persistent grant into the list of free grants */ for (i = 0; i < num_grant; i++) { - if (gnttab_query_foreign_access(s->grants_used[i]->gref)) { + if (!gnttab_try_end_foreign_access(s->grants_used[i]->gref)) { /* * If the grant is still mapped by the backend (the * backend has chosen to make this grant persistent) * we add it at the head of the list, so it will be * reused first. */ - if (!info->feature_persistent) - pr_alert_ratelimited("backed has not unmapped grant: %u\n", - s->grants_used[i]->gref); + if (!info->feature_persistent) { + pr_alert("backed has not unmapped grant: %u\n", + s->grants_used[i]->gref); + return -1; + } list_add(&s->grants_used[i]->node, &rinfo->grants); rinfo->persistent_gnts_c++; } else { /* - * If the grant is not mapped by the backend we end the - * foreign access and add it to the tail of the list, - * so it will not be picked again unless we run out of - * persistent grants. + * If the grant is not mapped by the backend we add it + * to the tail of the list, so it will not be picked + * again unless we run out of persistent grants. */ - gnttab_end_foreign_access(s->grants_used[i]->gref, 0, 0UL); s->grants_used[i]->gref = GRANT_INVALID_REF; list_add_tail(&s->grants_used[i]->node, &rinfo->grants); } } if (s->req.operation == BLKIF_OP_INDIRECT) { for (i = 0; i < INDIRECT_GREFS(num_grant); i++) { - if (gnttab_query_foreign_access(s->indirect_grants[i]->gref)) { - if (!info->feature_persistent) - pr_alert_ratelimited("backed has not unmapped grant: %u\n", - s->indirect_grants[i]->gref); + if (!gnttab_try_end_foreign_access(s->indirect_grants[i]->gref)) { + if (!info->feature_persistent) { + pr_alert("backed has not unmapped grant: %u\n", + s->indirect_grants[i]->gref); + return -1; + } list_add(&s->indirect_grants[i]->node, &rinfo->grants); rinfo->persistent_gnts_c++; } else { struct page *indirect_page; - gnttab_end_foreign_access(s->indirect_grants[i]->gref, 0, 0UL); /* * Add the used indirect page back to the list of * available pages for indirect grefs. @@ -1498,7 +1506,7 @@ static bool blkif_completion(unsigned long *id, } } - return true; + return 1; } static irqreturn_t blkif_interrupt(int irq, void *dev_id) @@ -1564,12 +1572,17 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) } if (bret.operation != BLKIF_OP_DISCARD) { + int ret; + /* * We may need to wait for an extra response if the * I/O request is split in 2 */ - if (!blkif_completion(&id, rinfo, &bret)) + ret = blkif_completion(&id, rinfo, &bret); + if (!ret) continue; + if (unlikely(ret < 0)) + goto err; } if (add_id_to_freelist(rinfo, id)) { @@ -1676,8 +1689,7 @@ static int setup_blkring(struct xenbus_device *dev, for (i = 0; i < info->nr_ring_pages; i++) rinfo->ring_ref[i] = GRANT_INVALID_REF; - sring = (struct blkif_sring *)__get_free_pages(GFP_NOIO | __GFP_HIGH, - get_order(ring_size)); + sring = alloc_pages_exact(ring_size, GFP_NOIO); if (!sring) { xenbus_dev_fatal(dev, -ENOMEM, "allocating shared ring"); return -ENOMEM; @@ -1687,7 +1699,7 @@ static int setup_blkring(struct xenbus_device *dev, err = xenbus_grant_ring(dev, rinfo->ring.sring, info->nr_ring_pages, gref); if (err < 0) { - free_pages((unsigned long)sring, get_order(ring_size)); + free_pages_exact(sring, ring_size); rinfo->ring.sring = NULL; goto fail; } @@ -2532,11 +2544,10 @@ static void purge_persistent_grants(struct blkfront_info *info) list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants, node) { if (gnt_list_entry->gref == GRANT_INVALID_REF || - gnttab_query_foreign_access(gnt_list_entry->gref)) + !gnttab_try_end_foreign_access(gnt_list_entry->gref)) continue; list_del(&gnt_list_entry->node); - gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL); rinfo->persistent_gnts_c--; gnt_list_entry->gref = GRANT_INVALID_REF; list_add_tail(&gnt_list_entry->node, &rinfo->grants); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 2359889a35a0..e3c430539a17 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -1957,6 +1957,13 @@ static void virtcons_remove(struct virtio_device *vdev) list_del(&portdev->list); spin_unlock_irq(&pdrvdata_lock); + /* Device is going away, exit any polling for buffers */ + virtio_break_device(vdev); + if (use_multiport(portdev)) + flush_work(&portdev->control_work); + else + flush_work(&portdev->config_work); + /* Disable interrupts for vqs */ virtio_reset_device(vdev); /* Finish up work that's lined up */ diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index ad4256d54361..d4d67fbae869 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -231,6 +231,8 @@ config COMMON_CLK_GEMINI config COMMON_CLK_LAN966X bool "Generic Clock Controller driver for LAN966X SoC" + depends on HAS_IOMEM + depends on OF help This driver provides support for Generic Clock Controller(GCK) on LAN966X SoC. GCK generates and supplies clock to various peripherals diff --git a/drivers/clk/qcom/dispcc-sc7180.c b/drivers/clk/qcom/dispcc-sc7180.c index 538e4963c915..5d2ae297e741 100644 --- a/drivers/clk/qcom/dispcc-sc7180.c +++ b/drivers/clk/qcom/dispcc-sc7180.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2019, The Linux Foundation. All rights reserved. + * Copyright (c) 2019, 2022, The Linux Foundation. All rights reserved. */ #include <linux/clk-provider.h> @@ -625,6 +625,9 @@ static struct clk_branch disp_cc_mdss_vsync_clk = { static struct gdsc mdss_gdsc = { .gdscr = 0x3000, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "mdss_gdsc", }, diff --git a/drivers/clk/qcom/dispcc-sc7280.c b/drivers/clk/qcom/dispcc-sc7280.c index 4ef4ae231794..ad596d567f6a 100644 --- a/drivers/clk/qcom/dispcc-sc7280.c +++ b/drivers/clk/qcom/dispcc-sc7280.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2021, The Linux Foundation. All rights reserved. + * Copyright (c) 2021-2022, The Linux Foundation. All rights reserved. */ #include <linux/clk-provider.h> @@ -787,6 +787,9 @@ static struct clk_branch disp_cc_sleep_clk = { static struct gdsc disp_cc_mdss_core_gdsc = { .gdscr = 0x1004, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "disp_cc_mdss_core_gdsc", }, diff --git a/drivers/clk/qcom/dispcc-sm8250.c b/drivers/clk/qcom/dispcc-sm8250.c index 566fdfa0a15b..db9379634fb2 100644 --- a/drivers/clk/qcom/dispcc-sm8250.c +++ b/drivers/clk/qcom/dispcc-sm8250.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2018-2020, The Linux Foundation. All rights reserved. + * Copyright (c) 2018-2020, 2022, The Linux Foundation. All rights reserved. */ #include <linux/clk-provider.h> @@ -1126,6 +1126,9 @@ static struct clk_branch disp_cc_mdss_vsync_clk = { static struct gdsc mdss_gdsc = { .gdscr = 0x3000, + .en_rest_wait_val = 0x2, + .en_few_wait_val = 0x2, + .clk_dis_wait_val = 0xf, .pd = { .name = "mdss_gdsc", }, diff --git a/drivers/clk/qcom/gdsc.c b/drivers/clk/qcom/gdsc.c index 7e1dd8ccfa38..44520efc6c72 100644 --- a/drivers/clk/qcom/gdsc.c +++ b/drivers/clk/qcom/gdsc.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2015, 2017-2018, The Linux Foundation. All rights reserved. + * Copyright (c) 2015, 2017-2018, 2022, The Linux Foundation. All rights reserved. */ #include <linux/bitops.h> @@ -35,9 +35,14 @@ #define CFG_GDSCR_OFFSET 0x4 /* Wait 2^n CXO cycles between all states. Here, n=2 (4 cycles). */ -#define EN_REST_WAIT_VAL (0x2 << 20) -#define EN_FEW_WAIT_VAL (0x8 << 16) -#define CLK_DIS_WAIT_VAL (0x2 << 12) +#define EN_REST_WAIT_VAL 0x2 +#define EN_FEW_WAIT_VAL 0x8 +#define CLK_DIS_WAIT_VAL 0x2 + +/* Transition delay shifts */ +#define EN_REST_WAIT_SHIFT 20 +#define EN_FEW_WAIT_SHIFT 16 +#define CLK_DIS_WAIT_SHIFT 12 #define RETAIN_MEM BIT(14) #define RETAIN_PERIPH BIT(13) @@ -380,7 +385,18 @@ static int gdsc_init(struct gdsc *sc) */ mask = HW_CONTROL_MASK | SW_OVERRIDE_MASK | EN_REST_WAIT_MASK | EN_FEW_WAIT_MASK | CLK_DIS_WAIT_MASK; - val = EN_REST_WAIT_VAL | EN_FEW_WAIT_VAL | CLK_DIS_WAIT_VAL; + + if (!sc->en_rest_wait_val) + sc->en_rest_wait_val = EN_REST_WAIT_VAL; + if (!sc->en_few_wait_val) + sc->en_few_wait_val = EN_FEW_WAIT_VAL; + if (!sc->clk_dis_wait_val) + sc->clk_dis_wait_val = CLK_DIS_WAIT_VAL; + + val = sc->en_rest_wait_val << EN_REST_WAIT_SHIFT | + sc->en_few_wait_val << EN_FEW_WAIT_SHIFT | + sc->clk_dis_wait_val << CLK_DIS_WAIT_SHIFT; + ret = regmap_update_bits(sc->regmap, sc->gdscr, mask, val); if (ret) return ret; diff --git a/drivers/clk/qcom/gdsc.h b/drivers/clk/qcom/gdsc.h index d7cc4c21a9d4..ad313d7210bd 100644 --- a/drivers/clk/qcom/gdsc.h +++ b/drivers/clk/qcom/gdsc.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2015, 2017-2018, The Linux Foundation. All rights reserved. + * Copyright (c) 2015, 2017-2018, 2022, The Linux Foundation. All rights reserved. */ #ifndef __QCOM_GDSC_H__ @@ -22,6 +22,9 @@ struct reset_controller_dev; * @cxcs: offsets of branch registers to toggle mem/periph bits in * @cxc_count: number of @cxcs * @pwrsts: Possible powerdomain power states + * @en_rest_wait_val: transition delay value for receiving enr ack signal + * @en_few_wait_val: transition delay value for receiving enf ack signal + * @clk_dis_wait_val: transition delay value for halting clock * @resets: ids of resets associated with this gdsc * @reset_count: number of @resets * @rcdev: reset controller @@ -36,6 +39,9 @@ struct gdsc { unsigned int clamp_io_ctrl; unsigned int *cxcs; unsigned int cxc_count; + unsigned int en_rest_wait_val; + unsigned int en_few_wait_val; + unsigned int clk_dis_wait_val; const u8 pwrsts; /* Powerdomain allowable state bitfields */ #define PWRSTS_OFF BIT(0) diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c index 153fe79e1bf3..8e5d87984a48 100644 --- a/drivers/gpio/gpio-sim.c +++ b/drivers/gpio/gpio-sim.c @@ -547,7 +547,7 @@ struct gpio_sim_bank { * * So we need to store the pointer to the parent struct here. We can * dereference it anywhere we need with no checks and no locking as - * it's guaranteed to survive the childred and protected by configfs + * it's guaranteed to survive the children and protected by configfs * locks. * * Same for other structures. @@ -1322,7 +1322,7 @@ static void gpio_sim_hog_config_item_release(struct config_item *item) kfree(hog); } -struct configfs_item_operations gpio_sim_hog_config_item_ops = { +static struct configfs_item_operations gpio_sim_hog_config_item_ops = { .release = gpio_sim_hog_config_item_release, }; diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c index 8d298beffd86..031fe105b58e 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -1075,6 +1075,7 @@ static const struct tegra_gpio_soc tegra241_main_soc = { .ports = tegra241_main_ports, .name = "tegra241-gpio", .instance = 0, + .num_irqs_per_bank = 8, }; #define TEGRA241_AON_GPIO_PORT(_name, _bank, _port, _pins) \ @@ -1095,6 +1096,7 @@ static const struct tegra_gpio_soc tegra241_aon_soc = { .ports = tegra241_aon_ports, .name = "tegra241-gpio-aon", .instance = 1, + .num_irqs_per_bank = 8, }; static const struct of_device_id tegra186_gpio_of_match[] = { diff --git a/drivers/gpio/gpio-ts4900.c b/drivers/gpio/gpio-ts4900.c index d885032cf814..d918d2df4de2 100644 --- a/drivers/gpio/gpio-ts4900.c +++ b/drivers/gpio/gpio-ts4900.c @@ -1,7 +1,7 @@ /* * Digital I/O driver for Technologic Systems I2C FPGA Core * - * Copyright (C) 2015 Technologic Systems + * Copyright (C) 2015, 2018 Technologic Systems * Copyright (C) 2016 Savoir-Faire Linux * * This program is free software; you can redistribute it and/or @@ -55,19 +55,33 @@ static int ts4900_gpio_direction_input(struct gpio_chip *chip, { struct ts4900_gpio_priv *priv = gpiochip_get_data(chip); - /* - * This will clear the output enable bit, the other bits are - * dontcare when this is cleared + /* Only clear the OE bit here, requires a RMW. Prevents potential issue + * with OE and data getting to the physical pin at different times. */ - return regmap_write(priv->regmap, offset, 0); + return regmap_update_bits(priv->regmap, offset, TS4900_GPIO_OE, 0); } static int ts4900_gpio_direction_output(struct gpio_chip *chip, unsigned int offset, int value) { struct ts4900_gpio_priv *priv = gpiochip_get_data(chip); + unsigned int reg; int ret; + /* If changing from an input to an output, we need to first set the + * proper data bit to what is requested and then set OE bit. This + * prevents a glitch that can occur on the IO line + */ + regmap_read(priv->regmap, offset, ®); + if (!(reg & TS4900_GPIO_OE)) { + if (value) + reg = TS4900_GPIO_OUT; + else + reg &= ~TS4900_GPIO_OUT; + + regmap_write(priv->regmap, offset, reg); + } + if (value) ret = regmap_write(priv->regmap, offset, TS4900_GPIO_OE | TS4900_GPIO_OUT); diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index c0f6a25c3279..a5495ad31c9c 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -307,7 +307,8 @@ static struct gpio_desc *acpi_request_own_gpiod(struct gpio_chip *chip, if (IS_ERR(desc)) return desc; - ret = gpio_set_debounce_timeout(desc, agpio->debounce_timeout); + /* ACPI uses hundredths of milliseconds units */ + ret = gpio_set_debounce_timeout(desc, agpio->debounce_timeout * 10); if (ret) dev_warn(chip->parent, "Failed to set debounce-timeout for pin 0x%04X, err %d\n", @@ -1035,7 +1036,8 @@ int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name, int ind if (ret < 0) return ret; - ret = gpio_set_debounce_timeout(desc, info.debounce); + /* ACPI uses hundredths of milliseconds units */ + ret = gpio_set_debounce_timeout(desc, info.debounce * 10); if (ret) return ret; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index a3d14277f17c..defb7c464b87 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1701,11 +1701,6 @@ static inline void gpiochip_irqchip_free_valid_mask(struct gpio_chip *gc) */ int gpiochip_generic_request(struct gpio_chip *gc, unsigned int offset) { -#ifdef CONFIG_PINCTRL - if (list_empty(&gc->gpiodev->pin_ranges)) - return 0; -#endif - return pinctrl_gpio_request(gc->gpiodev->base + offset); } EXPORT_SYMBOL_GPL(gpiochip_generic_request); @@ -1717,11 +1712,6 @@ EXPORT_SYMBOL_GPL(gpiochip_generic_request); */ void gpiochip_generic_free(struct gpio_chip *gc, unsigned int offset) { -#ifdef CONFIG_PINCTRL - if (list_empty(&gc->gpiodev->pin_ranges)) - return; -#endif - pinctrl_gpio_free(gc->gpiodev->base + offset); } EXPORT_SYMBOL_GPL(gpiochip_generic_free); @@ -2227,6 +2217,16 @@ static int gpio_set_bias(struct gpio_desc *desc) return gpio_set_config_with_argument_optional(desc, bias, arg); } +/** + * gpio_set_debounce_timeout() - Set debounce timeout + * @desc: GPIO descriptor to set the debounce timeout + * @debounce: Debounce timeout in microseconds + * + * The function calls the certain GPIO driver to set debounce timeout + * in the hardware. + * + * Returns 0 on success, or negative error code otherwise. + */ int gpio_set_debounce_timeout(struct gpio_desc *desc, unsigned int debounce) { return gpio_set_config_with_argument_optional(desc, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index d62190b3dd9b..418341a67517 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -777,7 +777,8 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm) amdgpu_vm_eviction_lock(vm); ret = !vm->evicting; amdgpu_vm_eviction_unlock(vm); - return ret; + + return ret && list_empty(&vm->evicted); } /** diff --git a/drivers/gpu/drm/arm/Kconfig b/drivers/gpu/drm/arm/Kconfig index 58a242871b28..6e3f1d600541 100644 --- a/drivers/gpu/drm/arm/Kconfig +++ b/drivers/gpu/drm/arm/Kconfig @@ -6,6 +6,7 @@ config DRM_HDLCD depends on DRM && OF && (ARM || ARM64 || COMPILE_TEST) depends on COMMON_CLK select DRM_KMS_HELPER + select DRM_GEM_CMA_HELPER help Choose this option if you have an ARM High Definition Colour LCD controller. diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index dab8f76618f3..68d8415e6c28 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -1802,6 +1802,7 @@ static inline void ti_sn_gpio_unregister(void) {} static void ti_sn65dsi86_runtime_disable(void *data) { + pm_runtime_dont_use_autosuspend(data); pm_runtime_disable(data); } @@ -1861,11 +1862,11 @@ static int ti_sn65dsi86_probe(struct i2c_client *client, "failed to get reference clock\n"); pm_runtime_enable(dev); + pm_runtime_set_autosuspend_delay(pdata->dev, 500); + pm_runtime_use_autosuspend(pdata->dev); ret = devm_add_action_or_reset(dev, ti_sn65dsi86_runtime_disable, dev); if (ret) return ret; - pm_runtime_set_autosuspend_delay(pdata->dev, 500); - pm_runtime_use_autosuspend(pdata->dev); ti_sn65dsi86_debugfs_init(pdata); diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c index a50c82bc2b2f..76a8c707c34b 100644 --- a/drivers/gpu/drm/drm_connector.c +++ b/drivers/gpu/drm/drm_connector.c @@ -2330,6 +2330,9 @@ EXPORT_SYMBOL(drm_connector_atomic_hdr_metadata_equal); void drm_connector_set_vrr_capable_property( struct drm_connector *connector, bool capable) { + if (!connector->vrr_capable_property) + return; + drm_object_property_set_value(&connector->base, connector->vrr_capable_property, capable); diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c index 12571ac45540..c04264f70ad1 100644 --- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c @@ -678,7 +678,6 @@ static int decon_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct decon_context *ctx; struct device_node *i80_if_timings; - struct resource *res; int ret; if (!dev->of_node) @@ -728,16 +727,11 @@ static int decon_probe(struct platform_device *pdev) goto err_iounmap; } - res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, - ctx->i80_if ? "lcd_sys" : "vsync"); - if (!res) { - dev_err(dev, "irq request failed.\n"); - ret = -ENXIO; + ret = platform_get_irq_byname(pdev, ctx->i80_if ? "lcd_sys" : "vsync"); + if (ret < 0) goto err_iounmap; - } - ret = devm_request_irq(dev, res->start, decon_irq_handler, - 0, "drm_decon", ctx); + ret = devm_request_irq(dev, ret, decon_irq_handler, 0, "drm_decon", ctx); if (ret) { dev_err(dev, "irq request failed.\n"); goto err_iounmap; diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index 32a36572b894..d13f5e3a030d 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1334,8 +1334,10 @@ static int exynos_dsi_register_te_irq(struct exynos_dsi *dsi, int ret; int te_gpio_irq; - dsi->te_gpio = devm_gpiod_get_optional(dsi->dev, "te", GPIOD_IN); - if (IS_ERR(dsi->te_gpio)) { + dsi->te_gpio = gpiod_get_optional(panel, "te", GPIOD_IN); + if (!dsi->te_gpio) { + return 0; + } else if (IS_ERR(dsi->te_gpio)) { dev_err(dsi->dev, "gpio request failed with %ld\n", PTR_ERR(dsi->te_gpio)); return PTR_ERR(dsi->te_gpio); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index 023f54ee61a8..0ee32e4b1e43 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -1267,7 +1267,6 @@ static int fimc_probe(struct platform_device *pdev) struct exynos_drm_ipp_formats *formats; struct device *dev = &pdev->dev; struct fimc_context *ctx; - struct resource *res; int ret; int i, j, num_limits, num_formats; @@ -1330,14 +1329,12 @@ static int fimc_probe(struct platform_device *pdev) return PTR_ERR(ctx->regs); /* resource irq */ - res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!res) { - dev_err(dev, "failed to request irq resource.\n"); - return -ENOENT; - } + ret = platform_get_irq(pdev, 0); + if (ret < 0) + return ret; - ret = devm_request_irq(dev, res->start, fimc_irq_handler, - 0, dev_name(dev), ctx); + ret = devm_request_irq(dev, ret, fimc_irq_handler, + 0, dev_name(dev), ctx); if (ret < 0) { dev_err(dev, "failed to request irq.\n"); return ret; diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index c735e53939d8..7d5a483a54de 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -1133,7 +1133,6 @@ static int fimd_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct fimd_context *ctx; struct device_node *i80_if_timings; - struct resource *res; int ret; if (!dev->of_node) @@ -1206,15 +1205,11 @@ static int fimd_probe(struct platform_device *pdev) if (IS_ERR(ctx->regs)) return PTR_ERR(ctx->regs); - res = platform_get_resource_byname(pdev, IORESOURCE_IRQ, - ctx->i80_if ? "lcd_sys" : "vsync"); - if (!res) { - dev_err(dev, "irq request failed.\n"); - return -ENXIO; - } + ret = platform_get_irq_byname(pdev, ctx->i80_if ? "lcd_sys" : "vsync"); + if (ret < 0) + return ret; - ret = devm_request_irq(dev, res->start, fimd_irq_handler, - 0, "drm_fimd", ctx); + ret = devm_request_irq(dev, ret, fimd_irq_handler, 0, "drm_fimd", ctx); if (ret) { dev_err(dev, "irq request failed.\n"); return ret; diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 166a80262896..964dceb28c1e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -1220,7 +1220,6 @@ static int gsc_probe(struct platform_device *pdev) struct gsc_driverdata *driver_data; struct exynos_drm_ipp_formats *formats; struct gsc_context *ctx; - struct resource *res; int num_formats, ret, i, j; ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL); @@ -1275,13 +1274,10 @@ static int gsc_probe(struct platform_device *pdev) return PTR_ERR(ctx->regs); /* resource irq */ - res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (!res) { - dev_err(dev, "failed to request irq resource.\n"); - return -ENOENT; - } + ctx->irq = platform_get_irq(pdev, 0); + if (ctx->irq < 0) + return ctx->irq; - ctx->irq = res->start; ret = devm_request_irq(dev, ctx->irq, gsc_irq_handler, 0, dev_name(dev), ctx); if (ret < 0) { diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c index 41c54f1f60bc..e5204be86093 100644 --- a/drivers/gpu/drm/exynos/exynos_mixer.c +++ b/drivers/gpu/drm/exynos/exynos_mixer.c @@ -809,19 +809,17 @@ static int mixer_resources_init(struct mixer_context *mixer_ctx) return -ENXIO; } - res = platform_get_resource(mixer_ctx->pdev, IORESOURCE_IRQ, 0); - if (res == NULL) { - dev_err(dev, "get interrupt resource failed.\n"); - return -ENXIO; - } + ret = platform_get_irq(mixer_ctx->pdev, 0); + if (ret < 0) + return ret; + mixer_ctx->irq = ret; - ret = devm_request_irq(dev, res->start, mixer_irq_handler, - 0, "drm_mixer", mixer_ctx); + ret = devm_request_irq(dev, mixer_ctx->irq, mixer_irq_handler, + 0, "drm_mixer", mixer_ctx); if (ret) { dev_err(dev, "request interrupt failed.\n"); return ret; } - mixer_ctx->irq = res->start; return 0; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c index 13b27b8ff74e..ba21ace973da 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_slpc.c @@ -110,7 +110,7 @@ static int guc_action_slpc_unset_param(struct intel_guc *guc, u8 id) { u32 request[] = { GUC_ACTION_HOST2GUC_PC_SLPC_REQUEST, - SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 2), + SLPC_EVENT(SLPC_EVENT_PARAMETER_UNSET, 1), id, }; diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c index da8f82c2342f..fc8a68f3a2ed 100644 --- a/drivers/gpu/drm/i915/intel_pch.c +++ b/drivers/gpu/drm/i915/intel_pch.c @@ -108,6 +108,7 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id) /* Comet Lake V PCH is based on KBP, which is SPT compatible */ return PCH_SPT; case INTEL_PCH_ICP_DEVICE_ID_TYPE: + case INTEL_PCH_ICP2_DEVICE_ID_TYPE: drm_dbg_kms(&dev_priv->drm, "Found Ice Lake PCH\n"); drm_WARN_ON(&dev_priv->drm, !IS_ICELAKE(dev_priv)); return PCH_ICP; @@ -123,7 +124,6 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id) !IS_GEN9_BC(dev_priv)); return PCH_TGP; case INTEL_PCH_JSP_DEVICE_ID_TYPE: - case INTEL_PCH_JSP2_DEVICE_ID_TYPE: drm_dbg_kms(&dev_priv->drm, "Found Jasper Lake PCH\n"); drm_WARN_ON(&dev_priv->drm, !IS_JSL_EHL(dev_priv)); return PCH_JSP; diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h index 6bff77521094..4ba0f1967cca 100644 --- a/drivers/gpu/drm/i915/intel_pch.h +++ b/drivers/gpu/drm/i915/intel_pch.h @@ -50,11 +50,11 @@ enum intel_pch { #define INTEL_PCH_CMP2_DEVICE_ID_TYPE 0x0680 #define INTEL_PCH_CMP_V_DEVICE_ID_TYPE 0xA380 #define INTEL_PCH_ICP_DEVICE_ID_TYPE 0x3480 +#define INTEL_PCH_ICP2_DEVICE_ID_TYPE 0x3880 #define INTEL_PCH_MCC_DEVICE_ID_TYPE 0x4B00 #define INTEL_PCH_TGP_DEVICE_ID_TYPE 0xA080 #define INTEL_PCH_TGP2_DEVICE_ID_TYPE 0x4380 #define INTEL_PCH_JSP_DEVICE_ID_TYPE 0x4D80 -#define INTEL_PCH_JSP2_DEVICE_ID_TYPE 0x3880 #define INTEL_PCH_ADP_DEVICE_ID_TYPE 0x7A80 #define INTEL_PCH_ADP2_DEVICE_ID_TYPE 0x5180 #define INTEL_PCH_ADP3_DEVICE_ID_TYPE 0x7A00 diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 26c31d759914..81e7e404a5fc 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -860,7 +860,9 @@ static const char *keys[KEY_MAX + 1] = { [KEY_F22] = "F22", [KEY_F23] = "F23", [KEY_F24] = "F24", [KEY_PLAYCD] = "PlayCD", [KEY_PAUSECD] = "PauseCD", [KEY_PROG3] = "Prog3", - [KEY_PROG4] = "Prog4", [KEY_SUSPEND] = "Suspend", + [KEY_PROG4] = "Prog4", + [KEY_ALL_APPLICATIONS] = "AllApplications", + [KEY_SUSPEND] = "Suspend", [KEY_CLOSE] = "Close", [KEY_PLAY] = "Play", [KEY_FASTFORWARD] = "FastForward", [KEY_BASSBOOST] = "BassBoost", [KEY_PRINT] = "Print", [KEY_HP] = "HP", @@ -969,6 +971,7 @@ static const char *keys[KEY_MAX + 1] = { [KEY_ASSISTANT] = "Assistant", [KEY_KBD_LAYOUT_NEXT] = "KbdLayoutNext", [KEY_EMOJI_PICKER] = "EmojiPicker", + [KEY_DICTATE] = "Dictate", [KEY_BRIGHTNESS_MIN] = "BrightnessMin", [KEY_BRIGHTNESS_MAX] = "BrightnessMax", [KEY_BRIGHTNESS_AUTO] = "BrightnessAuto", diff --git a/drivers/hid/hid-elo.c b/drivers/hid/hid-elo.c index 9b42b0cdeef0..2876cb6a7dca 100644 --- a/drivers/hid/hid-elo.c +++ b/drivers/hid/hid-elo.c @@ -228,7 +228,6 @@ static int elo_probe(struct hid_device *hdev, const struct hid_device_id *id) { struct elo_priv *priv; int ret; - struct usb_device *udev; if (!hid_is_usb(hdev)) return -EINVAL; @@ -238,8 +237,7 @@ static int elo_probe(struct hid_device *hdev, const struct hid_device_id *id) return -ENOMEM; INIT_DELAYED_WORK(&priv->work, elo_work); - udev = interface_to_usbdev(to_usb_interface(hdev->dev.parent)); - priv->usbdev = usb_get_dev(udev); + priv->usbdev = interface_to_usbdev(to_usb_interface(hdev->dev.parent)); hid_set_drvdata(hdev, priv); @@ -262,7 +260,6 @@ static int elo_probe(struct hid_device *hdev, const struct hid_device_id *id) return 0; err_free: - usb_put_dev(udev); kfree(priv); return ret; } @@ -271,8 +268,6 @@ static void elo_remove(struct hid_device *hdev) { struct elo_priv *priv = hid_get_drvdata(hdev); - usb_put_dev(priv->usbdev); - hid_hw_stop(hdev); cancel_delayed_work_sync(&priv->work); kfree(priv); diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 112901d2d8d2..56ec27398a00 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -992,6 +992,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x0cd: map_key_clear(KEY_PLAYPAUSE); break; case 0x0cf: map_key_clear(KEY_VOICECOMMAND); break; + case 0x0d8: map_key_clear(KEY_DICTATE); break; case 0x0d9: map_key_clear(KEY_EMOJI_PICKER); break; case 0x0e0: map_abs_clear(ABS_VOLUME); break; @@ -1083,6 +1084,8 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x29d: map_key_clear(KEY_KBD_LAYOUT_NEXT); break; + case 0x2a2: map_key_clear(KEY_ALL_APPLICATIONS); break; + case 0x2c7: map_key_clear(KEY_KBDINPUTASSIST_PREV); break; case 0x2c8: map_key_clear(KEY_KBDINPUTASSIST_NEXT); break; case 0x2c9: map_key_clear(KEY_KBDINPUTASSIST_PREVGROUP); break; diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index 7106b921b53c..c358778e070b 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -1068,6 +1068,7 @@ static void logi_hidpp_recv_queue_notif(struct hid_device *hdev, workitem.reports_supported |= STD_KEYBOARD; break; case 0x0f: + case 0x11: device_type = "eQUAD Lightspeed 1.2"; logi_hidpp_dev_conn_notif_equad(hdev, hidpp_report, &workitem); workitem.reports_supported |= STD_KEYBOARD; diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c index b6a9a0f3966e..2204de889739 100644 --- a/drivers/hid/hid-nintendo.c +++ b/drivers/hid/hid-nintendo.c @@ -2128,6 +2128,10 @@ static int nintendo_hid_probe(struct hid_device *hdev, spin_lock_init(&ctlr->lock); ctlr->rumble_queue = alloc_workqueue("hid-nintendo-rumble_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM, 0); + if (!ctlr->rumble_queue) { + ret = -ENOMEM; + goto err; + } INIT_WORK(&ctlr->rumble_worker, joycon_rumble_worker); ret = hid_parse(hdev); diff --git a/drivers/hid/hid-thrustmaster.c b/drivers/hid/hid-thrustmaster.c index 03b935ff02d5..c3e6d69fdfbd 100644 --- a/drivers/hid/hid-thrustmaster.c +++ b/drivers/hid/hid-thrustmaster.c @@ -64,7 +64,9 @@ struct tm_wheel_info { */ static const struct tm_wheel_info tm_wheels_infos[] = { {0x0306, 0x0006, "Thrustmaster T150RS"}, + {0x0200, 0x0005, "Thrustmaster T300RS (Missing Attachment)"}, {0x0206, 0x0005, "Thrustmaster T300RS"}, + {0x0209, 0x0005, "Thrustmaster T300RS (Open Wheel Attachment)"}, {0x0204, 0x0005, "Thrustmaster T300 Ferrari Alcantara Edition"}, {0x0002, 0x0002, "Thrustmaster T500RS"} //{0x0407, 0x0001, "Thrustmaster TMX"} @@ -158,6 +160,12 @@ static void thrustmaster_interrupts(struct hid_device *hdev) return; } + if (usbif->cur_altsetting->desc.bNumEndpoints < 2) { + kfree(send_buf); + hid_err(hdev, "Wrong number of endpoints?\n"); + return; + } + ep = &usbif->cur_altsetting->endpoint[1]; b_ep = ep->desc.bEndpointAddress; diff --git a/drivers/hid/hid-vivaldi.c b/drivers/hid/hid-vivaldi.c index efa6140915f4..42ceb2058a09 100644 --- a/drivers/hid/hid-vivaldi.c +++ b/drivers/hid/hid-vivaldi.c @@ -144,7 +144,7 @@ out: static int vivaldi_input_configured(struct hid_device *hdev, struct hid_input *hidinput) { - return sysfs_create_group(&hdev->dev.kobj, &input_attribute_group); + return devm_device_add_group(&hdev->dev, &input_attribute_group); } static const struct hid_device_id vivaldi_table[] = { diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig index 0c607da9ee10..9417ee0b1eff 100644 --- a/drivers/input/keyboard/Kconfig +++ b/drivers/input/keyboard/Kconfig @@ -556,7 +556,7 @@ config KEYBOARD_PMIC8XXX config KEYBOARD_SAMSUNG tristate "Samsung keypad support" - depends on HAVE_CLK + depends on HAS_IOMEM && HAVE_CLK select INPUT_MATRIXKMAP help Say Y here if you want to use the keypad on your Samsung mobile diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c index 47af62c12267..e1758d5ffe42 100644 --- a/drivers/input/mouse/elan_i2c_core.c +++ b/drivers/input/mouse/elan_i2c_core.c @@ -186,55 +186,21 @@ static int elan_get_fwinfo(u16 ic_type, u8 iap_version, u16 *validpage_count, return 0; } -static int elan_enable_power(struct elan_tp_data *data) +static int elan_set_power(struct elan_tp_data *data, bool on) { int repeat = ETP_RETRY_COUNT; int error; - error = regulator_enable(data->vcc); - if (error) { - dev_err(&data->client->dev, - "failed to enable regulator: %d\n", error); - return error; - } - do { - error = data->ops->power_control(data->client, true); + error = data->ops->power_control(data->client, on); if (error >= 0) return 0; msleep(30); } while (--repeat > 0); - dev_err(&data->client->dev, "failed to enable power: %d\n", error); - return error; -} - -static int elan_disable_power(struct elan_tp_data *data) -{ - int repeat = ETP_RETRY_COUNT; - int error; - - do { - error = data->ops->power_control(data->client, false); - if (!error) { - error = regulator_disable(data->vcc); - if (error) { - dev_err(&data->client->dev, - "failed to disable regulator: %d\n", - error); - /* Attempt to power the chip back up */ - data->ops->power_control(data->client, true); - break; - } - - return 0; - } - - msleep(30); - } while (--repeat > 0); - - dev_err(&data->client->dev, "failed to disable power: %d\n", error); + dev_err(&data->client->dev, "failed to set power %s: %d\n", + on ? "on" : "off", error); return error; } @@ -1399,9 +1365,19 @@ static int __maybe_unused elan_suspend(struct device *dev) /* Enable wake from IRQ */ data->irq_wake = (enable_irq_wake(client->irq) == 0); } else { - ret = elan_disable_power(data); + ret = elan_set_power(data, false); + if (ret) + goto err; + + ret = regulator_disable(data->vcc); + if (ret) { + dev_err(dev, "error %d disabling regulator\n", ret); + /* Attempt to power the chip back up */ + elan_set_power(data, true); + } } +err: mutex_unlock(&data->sysfs_mutex); return ret; } @@ -1412,12 +1388,18 @@ static int __maybe_unused elan_resume(struct device *dev) struct elan_tp_data *data = i2c_get_clientdata(client); int error; - if (device_may_wakeup(dev) && data->irq_wake) { + if (!device_may_wakeup(dev)) { + error = regulator_enable(data->vcc); + if (error) { + dev_err(dev, "error %d enabling regulator\n", error); + goto err; + } + } else if (data->irq_wake) { disable_irq_wake(client->irq); data->irq_wake = false; } - error = elan_enable_power(data); + error = elan_set_power(data, true); if (error) { dev_err(dev, "power up when resuming failed: %d\n", error); goto err; diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index a3bfc7a41679..752e8ba4fecb 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -18,6 +18,7 @@ #include <linux/delay.h> #include <linux/irq.h> #include <linux/interrupt.h> +#include <linux/platform_data/x86/soc.h> #include <linux/slab.h> #include <linux/acpi.h> #include <linux/of.h> @@ -805,21 +806,6 @@ static int goodix_reset(struct goodix_ts_data *ts) } #ifdef ACPI_GPIO_SUPPORT -#include <asm/cpu_device_id.h> -#include <asm/intel-family.h> - -static const struct x86_cpu_id baytrail_cpu_ids[] = { - { X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT, X86_FEATURE_ANY, }, - {} -}; - -static inline bool is_byt(void) -{ - const struct x86_cpu_id *id = x86_match_cpu(baytrail_cpu_ids); - - return !!id; -} - static const struct acpi_gpio_params first_gpio = { 0, 0, false }; static const struct acpi_gpio_params second_gpio = { 1, 0, false }; @@ -878,7 +864,7 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts) const struct acpi_gpio_mapping *gpio_mapping = NULL; struct device *dev = &ts->client->dev; LIST_HEAD(resources); - int ret; + int irq, ret; ts->gpio_count = 0; ts->gpio_int_idx = -1; @@ -891,6 +877,20 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts) acpi_dev_free_resource_list(&resources); + /* + * CHT devices should have a GpioInt + a regular GPIO ACPI resource. + * Some CHT devices have a bug (where the also is bogus Interrupt + * resource copied from a previous BYT based generation). i2c-core-acpi + * will use the non-working Interrupt resource, fix this up. + */ + if (soc_intel_is_cht() && ts->gpio_count == 2 && ts->gpio_int_idx != -1) { + irq = acpi_dev_gpio_irq_get(ACPI_COMPANION(dev), 0); + if (irq > 0 && irq != ts->client->irq) { + dev_warn(dev, "Overriding IRQ %d -> %d\n", ts->client->irq, irq); + ts->client->irq = irq; + } + } + if (ts->gpio_count == 2 && ts->gpio_int_idx == 0) { ts->irq_pin_access_method = IRQ_PIN_ACCESS_ACPI_GPIO; gpio_mapping = acpi_goodix_int_first_gpios; @@ -903,7 +903,7 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts) dev_info(dev, "Using ACPI INTI and INTO methods for IRQ pin access\n"); ts->irq_pin_access_method = IRQ_PIN_ACCESS_ACPI_METHOD; gpio_mapping = acpi_goodix_reset_only_gpios; - } else if (is_byt() && ts->gpio_count == 2 && ts->gpio_int_idx == -1) { + } else if (soc_intel_is_byt() && ts->gpio_count == 2 && ts->gpio_int_idx == -1) { dev_info(dev, "No ACPI GpioInt resource, assuming that the GPIO order is reset, int\n"); ts->irq_pin_access_method = IRQ_PIN_ACCESS_ACPI_GPIO; gpio_mapping = acpi_goodix_int_last_gpios; diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h index 416815a525d6..bb95edf74415 100644 --- a/drivers/iommu/amd/amd_iommu.h +++ b/drivers/iommu/amd/amd_iommu.h @@ -14,6 +14,7 @@ extern irqreturn_t amd_iommu_int_thread(int irq, void *data); extern irqreturn_t amd_iommu_int_handler(int irq, void *data); extern void amd_iommu_apply_erratum_63(u16 devid); +extern void amd_iommu_restart_event_logging(struct amd_iommu *iommu); extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu); extern int amd_iommu_init_devices(void); extern void amd_iommu_uninit_devices(void); diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h index ffc89c4fb120..47108ed44fbb 100644 --- a/drivers/iommu/amd/amd_iommu_types.h +++ b/drivers/iommu/amd/amd_iommu_types.h @@ -110,6 +110,7 @@ #define PASID_MASK 0x0000ffff /* MMIO status bits */ +#define MMIO_STATUS_EVT_OVERFLOW_INT_MASK (1 << 0) #define MMIO_STATUS_EVT_INT_MASK (1 << 1) #define MMIO_STATUS_COM_WAIT_INT_MASK (1 << 2) #define MMIO_STATUS_PPR_INT_MASK (1 << 6) diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c index b10fb52ea442..7bfe37e52e21 100644 --- a/drivers/iommu/amd/init.c +++ b/drivers/iommu/amd/init.c @@ -658,6 +658,16 @@ static int __init alloc_command_buffer(struct amd_iommu *iommu) } /* + * This function restarts event logging in case the IOMMU experienced + * an event log buffer overflow. + */ +void amd_iommu_restart_event_logging(struct amd_iommu *iommu) +{ + iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN); + iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN); +} + +/* * This function resets the command buffer if the IOMMU stopped fetching * commands from it. */ diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c index b1bf4125b0f7..6608d1717574 100644 --- a/drivers/iommu/amd/io_pgtable.c +++ b/drivers/iommu/amd/io_pgtable.c @@ -492,18 +492,18 @@ static void v1_free_pgtable(struct io_pgtable *iop) dom = container_of(pgtable, struct protection_domain, iop); - /* Update data structure */ - amd_iommu_domain_clr_pt_root(dom); - - /* Make changes visible to IOMMUs */ - amd_iommu_domain_update(dom); - /* Page-table is not visible to IOMMU anymore, so free it */ BUG_ON(pgtable->mode < PAGE_MODE_NONE || pgtable->mode > PAGE_MODE_6_LEVEL); free_sub_pt(pgtable->root, pgtable->mode, &freelist); + /* Update data structure */ + amd_iommu_domain_clr_pt_root(dom); + + /* Make changes visible to IOMMUs */ + amd_iommu_domain_update(dom); + put_pages_list(&freelist); } diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c index 461f1844ed1f..a18b549951bb 100644 --- a/drivers/iommu/amd/iommu.c +++ b/drivers/iommu/amd/iommu.c @@ -764,7 +764,8 @@ amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { } #endif /* !CONFIG_IRQ_REMAP */ #define AMD_IOMMU_INT_MASK \ - (MMIO_STATUS_EVT_INT_MASK | \ + (MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \ + MMIO_STATUS_EVT_INT_MASK | \ MMIO_STATUS_PPR_INT_MASK | \ MMIO_STATUS_GALOG_INT_MASK) @@ -774,7 +775,7 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data) u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); while (status & AMD_IOMMU_INT_MASK) { - /* Enable EVT and PPR and GA interrupts again */ + /* Enable interrupt sources again */ writel(AMD_IOMMU_INT_MASK, iommu->mmio_base + MMIO_STATUS_OFFSET); @@ -795,6 +796,11 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data) } #endif + if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) { + pr_info_ratelimited("IOMMU event log overflow\n"); + amd_iommu_restart_event_logging(iommu); + } + /* * Hardware bug: ERBT1312 * When re-enabling interrupt (by writing 1 diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 92fea3fbbb11..5b196cfe9ed2 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -2738,7 +2738,7 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu, spin_unlock_irqrestore(&device_domain_lock, flags); /* PASID table is mandatory for a PCI device in scalable mode. */ - if (dev && dev_is_pci(dev) && sm_supported(iommu)) { + if (sm_supported(iommu) && !dev_is_real_dma_subdevice(dev)) { ret = intel_pasid_alloc_table(dev); if (ret) { dev_err(dev, "PASID table allocation failed\n"); diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c index e900e3c46903..2561ce8a2ce8 100644 --- a/drivers/iommu/tegra-smmu.c +++ b/drivers/iommu/tegra-smmu.c @@ -808,8 +808,10 @@ static struct tegra_smmu *tegra_smmu_find(struct device_node *np) return NULL; mc = platform_get_drvdata(pdev); - if (!mc) + if (!mc) { + put_device(&pdev->dev); return NULL; + } return mc->smmu; } diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index bd087cca1c1d..af17459c1a5c 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -2005,7 +2005,11 @@ setup_hw(struct hfc_pci *hc) } /* Allocate memory for FIFOS */ /* the memory needs to be on a 32k boundary within the first 4G */ - dma_set_mask(&hc->pdev->dev, 0xFFFF8000); + if (dma_set_mask(&hc->pdev->dev, 0xFFFF8000)) { + printk(KERN_WARNING + "HFC-PCI: No usable DMA configuration!\n"); + return -EIO; + } buffer = dma_alloc_coherent(&hc->pdev->dev, 0x8000, &hc->hw.dmahandle, GFP_KERNEL); /* We silently assume the address is okay if nonzero */ diff --git a/drivers/isdn/mISDN/dsp_pipeline.c b/drivers/isdn/mISDN/dsp_pipeline.c index e11ca6bbc7f4..c3b2c99b5cd5 100644 --- a/drivers/isdn/mISDN/dsp_pipeline.c +++ b/drivers/isdn/mISDN/dsp_pipeline.c @@ -192,7 +192,7 @@ void dsp_pipeline_destroy(struct dsp_pipeline *pipeline) int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg) { int found = 0; - char *dup, *tok, *name, *args; + char *dup, *next, *tok, *name, *args; struct dsp_element_entry *entry, *n; struct dsp_pipeline_entry *pipeline_entry; struct mISDN_dsp_element *elem; @@ -203,10 +203,10 @@ int dsp_pipeline_build(struct dsp_pipeline *pipeline, const char *cfg) if (!list_empty(&pipeline->list)) _dsp_pipeline_destroy(pipeline); - dup = kstrdup(cfg, GFP_ATOMIC); + dup = next = kstrdup(cfg, GFP_ATOMIC); if (!dup) return 0; - while ((tok = strsep(&dup, "|"))) { + while ((tok = strsep(&next, "|"))) { if (!strlen(tok)) continue; name = strsep(&tok, "("); diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig index d986ab4e4c35..820e5dc3bc9b 100644 --- a/drivers/mtd/nand/raw/Kconfig +++ b/drivers/mtd/nand/raw/Kconfig @@ -42,8 +42,7 @@ config MTD_NAND_OMAP2 tristate "OMAP2, OMAP3, OMAP4 and Keystone NAND controller" depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST depends on HAS_IOMEM - select MEMORY - select OMAP_GPMC + depends on OMAP_GPMC help Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4 and Keystone platforms. diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 66b00c19ebe0..669f008528ec 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2941,7 +2941,7 @@ mt753x_phylink_validate(struct dsa_switch *ds, int port, phylink_set_port_modes(mask); - if (state->interface != PHY_INTERFACE_MODE_TRGMII || + if (state->interface != PHY_INTERFACE_MODE_TRGMII && !phy_interface_mode_is_8023z(state->interface)) { phylink_set(mask, 10baseT_Half); phylink_set(mask, 10baseT_Full); diff --git a/drivers/net/ethernet/8390/mcf8390.c b/drivers/net/ethernet/8390/mcf8390.c index e320cccba61a..90cd7bdf06f5 100644 --- a/drivers/net/ethernet/8390/mcf8390.c +++ b/drivers/net/ethernet/8390/mcf8390.c @@ -405,12 +405,12 @@ static int mcf8390_init(struct net_device *dev) static int mcf8390_probe(struct platform_device *pdev) { struct net_device *dev; - struct resource *mem, *irq; + struct resource *mem; resource_size_t msize; - int ret; + int ret, irq; - irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (irq == NULL) { + irq = platform_get_irq(pdev, 0); + if (irq < 0) { dev_err(&pdev->dev, "no IRQ specified?\n"); return -ENXIO; } @@ -433,7 +433,7 @@ static int mcf8390_probe(struct platform_device *pdev) SET_NETDEV_DEV(dev, &pdev->dev); platform_set_drvdata(pdev, dev); - dev->irq = irq->start; + dev->irq = irq; dev->base_addr = mem->start; ret = mcf8390_init(dev); diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c index 9acf589b1178..87f40c2ba904 100644 --- a/drivers/net/ethernet/arc/emac_mdio.c +++ b/drivers/net/ethernet/arc/emac_mdio.c @@ -132,6 +132,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv) { struct arc_emac_mdio_bus_data *data = &priv->bus_data; struct device_node *np = priv->dev->of_node; + const char *name = "Synopsys MII Bus"; struct mii_bus *bus; int error; @@ -142,7 +143,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv) priv->bus = bus; bus->priv = priv; bus->parent = priv->dev; - bus->name = "Synopsys MII Bus"; + bus->name = name; bus->read = &arc_mdio_read; bus->write = &arc_mdio_write; bus->reset = &arc_mdio_reset; @@ -167,7 +168,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv) if (error) { mdiobus_free(bus); return dev_err_probe(priv->dev, error, - "cannot register MDIO bus %s\n", bus->name); + "cannot register MDIO bus %s\n", name); } return 0; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c index e31a5a397f11..f55d9d9c01a8 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c @@ -40,6 +40,13 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct bcmgenet_priv *priv = netdev_priv(dev); + struct device *kdev = &priv->pdev->dev; + + if (!device_can_wakeup(kdev)) { + wol->supported = 0; + wol->wolopts = 0; + return; + } wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; wol->wolopts = priv->wolopts; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 4c231159b562..800d5ced5800 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1575,7 +1575,14 @@ static int macb_poll(struct napi_struct *napi, int budget) if (work_done < budget) { napi_complete_done(napi, work_done); - /* Packets received while interrupts were disabled */ + /* RSR bits only seem to propagate to raise interrupts when + * interrupts are enabled at the time, so if bits are already + * set due to packets received while interrupts were disabled, + * they will not cause another interrupt to be generated when + * interrupts are re-enabled. + * Check for this case here. This has been seen to happen + * around 30% of the time under heavy network load. + */ status = macb_readl(bp, RSR); if (status) { if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) @@ -1583,6 +1590,22 @@ static int macb_poll(struct napi_struct *napi, int budget) napi_reschedule(napi); } else { queue_writel(queue, IER, bp->rx_intr_mask); + + /* In rare cases, packets could have been received in + * the window between the check above and re-enabling + * interrupts. Therefore, a double-check is required + * to avoid losing a wakeup. This can potentially race + * with the interrupt handler doing the same actions + * if an interrupt is raised just after enabling them, + * but this should be harmless. + */ + status = macb_readl(bp, RSR); + if (unlikely(status)) { + queue_writel(queue, IDR, bp->rx_intr_mask); + if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) + queue_writel(queue, ISR, MACB_BIT(RCOMP)); + napi_schedule(napi); + } } } diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index ff756265d58f..9a2c16d69e2c 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -1464,6 +1464,7 @@ static int gfar_get_ts_info(struct net_device *dev, ptp_node = of_find_compatible_node(NULL, NULL, "fsl,etsec-ptp"); if (ptp_node) { ptp_dev = of_find_device_by_node(ptp_node); + of_node_put(ptp_node); if (ptp_dev) ptp = platform_get_drvdata(ptp_dev); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 90fff05fbd2b..be7c6f34d45c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -741,10 +741,8 @@ static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id) vsi = pf->vsi[vf->lan_vsi_idx]; dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n", vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs); - dev_info(&pf->pdev->dev, " num MDD=%lld, invalid msg=%lld, valid msg=%lld\n", - vf->num_mdd_events, - vf->num_invalid_msgs, - vf->num_valid_msgs); + dev_info(&pf->pdev->dev, " num MDD=%lld\n", + vf->num_mdd_events); } else { dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index dfdb6e786461..2606e8f0f19b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1917,19 +1917,17 @@ sriov_configure_out: /***********************virtual channel routines******************/ /** - * i40e_vc_send_msg_to_vf_ex + * i40e_vc_send_msg_to_vf * @vf: pointer to the VF info * @v_opcode: virtual channel opcode * @v_retval: virtual channel return value * @msg: pointer to the msg buffer * @msglen: msg length - * @is_quiet: true for not printing unsuccessful return values, false otherwise * * send msg to VF **/ -static int i40e_vc_send_msg_to_vf_ex(struct i40e_vf *vf, u32 v_opcode, - u32 v_retval, u8 *msg, u16 msglen, - bool is_quiet) +static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, + u32 v_retval, u8 *msg, u16 msglen) { struct i40e_pf *pf; struct i40e_hw *hw; @@ -1944,25 +1942,6 @@ static int i40e_vc_send_msg_to_vf_ex(struct i40e_vf *vf, u32 v_opcode, hw = &pf->hw; abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; - /* single place to detect unsuccessful return values */ - if (v_retval && !is_quiet) { - vf->num_invalid_msgs++; - dev_info(&pf->pdev->dev, "VF %d failed opcode %d, retval: %d\n", - vf->vf_id, v_opcode, v_retval); - if (vf->num_invalid_msgs > - I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED) { - dev_err(&pf->pdev->dev, - "Number of invalid messages exceeded for VF %d\n", - vf->vf_id); - dev_err(&pf->pdev->dev, "Use PF Control I/F to enable the VF\n"); - set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); - } - } else { - vf->num_valid_msgs++; - /* reset the invalid counter, if a valid message is received. */ - vf->num_invalid_msgs = 0; - } - aq_ret = i40e_aq_send_msg_to_vf(hw, abs_vf_id, v_opcode, v_retval, msg, msglen, NULL); if (aq_ret) { @@ -1976,23 +1955,6 @@ static int i40e_vc_send_msg_to_vf_ex(struct i40e_vf *vf, u32 v_opcode, } /** - * i40e_vc_send_msg_to_vf - * @vf: pointer to the VF info - * @v_opcode: virtual channel opcode - * @v_retval: virtual channel return value - * @msg: pointer to the msg buffer - * @msglen: msg length - * - * send msg to VF - **/ -static int i40e_vc_send_msg_to_vf(struct i40e_vf *vf, u32 v_opcode, - u32 v_retval, u8 *msg, u16 msglen) -{ - return i40e_vc_send_msg_to_vf_ex(vf, v_opcode, v_retval, - msg, msglen, false); -} - -/** * i40e_vc_send_resp_to_vf * @vf: pointer to the VF info * @opcode: operation code @@ -2822,7 +2784,6 @@ error_param: * i40e_check_vf_permission * @vf: pointer to the VF info * @al: MAC address list from virtchnl - * @is_quiet: set true for printing msg without opcode info, false otherwise * * Check that the given list of MAC addresses is allowed. Will return -EPERM * if any address in the list is not valid. Checks the following conditions: @@ -2837,8 +2798,7 @@ error_param: * addresses might not be accurate. **/ static inline int i40e_check_vf_permission(struct i40e_vf *vf, - struct virtchnl_ether_addr_list *al, - bool *is_quiet) + struct virtchnl_ether_addr_list *al) { struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = pf->vsi[vf->lan_vsi_idx]; @@ -2846,7 +2806,6 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, int mac2add_cnt = 0; int i; - *is_quiet = false; for (i = 0; i < al->num_elements; i++) { struct i40e_mac_filter *f; u8 *addr = al->list[i].addr; @@ -2870,7 +2829,6 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, !ether_addr_equal(addr, vf->default_lan_addr.addr)) { dev_err(&pf->pdev->dev, "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); - *is_quiet = true; return -EPERM; } @@ -2921,7 +2879,6 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) (struct virtchnl_ether_addr_list *)msg; struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; - bool is_quiet = false; i40e_status ret = 0; int i; @@ -2938,7 +2895,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) */ spin_lock_bh(&vsi->mac_filter_hash_lock); - ret = i40e_check_vf_permission(vf, al, &is_quiet); + ret = i40e_check_vf_permission(vf, al); if (ret) { spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; @@ -2976,8 +2933,8 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) error_param: /* send the response to the VF */ - return i40e_vc_send_msg_to_vf_ex(vf, VIRTCHNL_OP_ADD_ETH_ADDR, - ret, NULL, 0, is_quiet); + return i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_ADD_ETH_ADDR, + ret, NULL, 0); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 03c42fd0fea1..a554d0a0b09b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -10,8 +10,6 @@ #define I40E_VIRTCHNL_SUPPORTED_QTYPES 2 -#define I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED 10 - #define I40E_VLAN_PRIORITY_SHIFT 13 #define I40E_VLAN_MASK 0xFFF #define I40E_PRIORITY_MASK 0xE000 @@ -92,9 +90,6 @@ struct i40e_vf { u8 num_queue_pairs; /* num of qps assigned to VF vsis */ u8 num_req_queues; /* num of requested qps */ u64 num_mdd_events; /* num of mdd events detected */ - /* num of continuous malformed or invalid msgs detected */ - u64 num_invalid_msgs; - u64 num_valid_msgs; /* num of valid msgs detected */ unsigned long vf_caps; /* vf's adv. capabilities */ unsigned long vf_states; /* vf's runtime states */ diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index bed2ebf15627..49aed3e506a6 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -291,6 +291,7 @@ struct iavf_adapter { #define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16) #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) +#define IAVF_FLAG_REINIT_MSIX_NEEDED BIT(20) /* duplicates for common code */ #define IAVF_FLAG_DCB_ENABLED 0 /* flags for admin queue service task */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 45a1e88c9276..7c4b75a5e1b5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2234,7 +2234,7 @@ int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter) "Requested %d queues, but PF only gave us %d.\n", num_req_queues, adapter->vsi_res->num_queue_pairs); - adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->flags |= IAVF_FLAG_REINIT_MSIX_NEEDED; adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; iavf_schedule_reset(adapter); @@ -2894,7 +2894,8 @@ continue_reset: } adapter->aq_required = 0; - if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { + if ((adapter->flags & IAVF_FLAG_REINIT_MSIX_NEEDED) || + (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED)) { err = iavf_reinit_interrupt_scheme(adapter); if (err) goto reset_err; @@ -2966,12 +2967,13 @@ continue_reset: if (err) goto reset_err; - if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { + if ((adapter->flags & IAVF_FLAG_REINIT_MSIX_NEEDED) || + (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED)) { err = iavf_request_traffic_irqs(adapter, netdev->name); if (err) goto reset_err; - adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->flags &= ~IAVF_FLAG_REINIT_MSIX_NEEDED; } iavf_configure(adapter); @@ -2986,6 +2988,9 @@ continue_reset: iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); } + + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index c6f52f8ef678..782450d5c12f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1829,6 +1829,22 @@ int iavf_request_reset(struct iavf_adapter *adapter) } /** + * iavf_netdev_features_vlan_strip_set - update vlan strip status + * @netdev: ptr to netdev being adjusted + * @enable: enable or disable vlan strip + * + * Helper function to change vlan strip status in netdev->features. + */ +static void iavf_netdev_features_vlan_strip_set(struct net_device *netdev, + const bool enable) +{ + if (enable) + netdev->features |= NETIF_F_HW_VLAN_CTAG_RX; + else + netdev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; +} + +/** * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF @@ -2051,8 +2067,18 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } break; case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + dev_warn(&adapter->pdev->dev, "Changing VLAN Stripping is not allowed when Port VLAN is configured\n"); + /* Vlan stripping could not be enabled by ethtool. + * Disable it in netdev->features. + */ + iavf_netdev_features_vlan_strip_set(netdev, false); + break; case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: dev_warn(&adapter->pdev->dev, "Changing VLAN Stripping is not allowed when Port VLAN is configured\n"); + /* Vlan stripping could not be disabled by ethtool. + * Enable it in netdev->features. + */ + iavf_netdev_features_vlan_strip_set(netdev, true); break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", @@ -2306,6 +2332,20 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->adv_rss_lock); } break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING: + /* PF enabled vlan strip on this VF. + * Update netdev->features if needed to be in sync with ethtool. + */ + if (!v_retval) + iavf_netdev_features_vlan_strip_set(netdev, true); + break; + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING: + /* PF disabled vlan strip on this VF. + * Update netdev->features if needed to be in sync with ethtool. + */ + if (!v_retval) + iavf_netdev_features_vlan_strip_set(netdev, false); + break; default: if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index dc42ff92dbad..c7a987c89423 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -487,6 +487,7 @@ enum ice_pf_flags { ICE_FLAG_VF_VLAN_PRUNING, ICE_FLAG_LINK_LENIENT_MODE_ENA, ICE_FLAG_PLUG_AUX_DEV, + ICE_FLAG_MTU_CHANGED, ICE_FLAG_GNSS, /* GNSS successfully initialized */ ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -896,7 +897,16 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) */ static inline void ice_clear_rdma_cap(struct ice_pf *pf) { - ice_unplug_aux_dev(pf); + /* We can directly unplug aux device here only if the flag bit + * ICE_FLAG_PLUG_AUX_DEV is not set because ice_unplug_aux_dev() + * could race with ice_plug_aux_dev() called from + * ice_service_task(). In this case we only clear that bit now and + * aux device will be unplugged later once ice_plug_aux_device() + * called from ice_service_task() finishes (see ice_service_task()). + */ + if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); + clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); } #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 399625892f9e..24cda7e1f916 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2311,7 +2311,7 @@ ice_set_link_ksettings(struct net_device *netdev, if (err) goto done; - curr_link_speed = pi->phy.link_info.link_speed; + curr_link_speed = pi->phy.curr_user_speed_req; adv_link_speed = ice_ksettings_find_adv_link_speed(ks); /* If speed didn't get set, set it to what it currently is. diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 289e5c99e313..85b18548c5ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2265,9 +2265,30 @@ static void ice_service_task(struct work_struct *work) return; } - if (test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + if (test_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) { + /* Plug aux device per request */ ice_plug_aux_dev(pf); + /* Mark plugging as done but check whether unplug was + * requested during ice_plug_aux_dev() call + * (e.g. from ice_clear_rdma_cap()) and if so then + * plug aux device. + */ + if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); + } + + if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) { + struct iidc_event *event; + + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (event) { + set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + } + } + ice_clean_adminq_subtask(pf); ice_check_media_subtask(pf); ice_check_for_hang_subtask(pf); @@ -3033,7 +3054,7 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) struct iidc_event *event; ena_mask &= ~ICE_AUX_CRIT_ERR; - event = kzalloc(sizeof(*event), GFP_KERNEL); + event = kzalloc(sizeof(*event), GFP_ATOMIC); if (event) { set_bit(IIDC_EVENT_CRIT_ERR, event->type); /* report the entire OICR value to AUX driver */ @@ -7037,7 +7058,6 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; - struct iidc_event *event; u8 count = 0; int err = 0; @@ -7072,14 +7092,6 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) return -EBUSY; } - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (!event) - return -ENOMEM; - - set_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - clear_bit(IIDC_EVENT_BEFORE_MTU_CHANGE, event->type); - netdev->mtu = (unsigned int)new_mtu; /* if VSI is up, bring it down and then back up */ @@ -7087,21 +7099,18 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) err = ice_down(vsi); if (err) { netdev_err(netdev, "change MTU if_down err %d\n", err); - goto event_after; + return err; } err = ice_up(vsi); if (err) { netdev_err(netdev, "change MTU if_up err %d\n", err); - goto event_after; + return err; } } netdev_dbg(netdev, "changed MTU to %d\n", new_mtu); -event_after: - set_bit(IIDC_EVENT_AFTER_MTU_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - kfree(event); + set_bit(ICE_FLAG_MTU_CHANGED, pf->flags); return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 4840570c494d..45fe36db076a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -2365,24 +2365,6 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, pf = vf->pf; dev = ice_pf_to_dev(pf); - /* single place to detect unsuccessful return values */ - if (v_retval) { - vf->num_inval_msgs++; - dev_info(dev, "VF %d failed opcode %d, retval: %d\n", vf->vf_id, - v_opcode, v_retval); - if (vf->num_inval_msgs > ICE_DFLT_NUM_INVAL_MSGS_ALLOWED) { - dev_err(dev, "Number of invalid messages exceeded for VF %d\n", - vf->vf_id); - dev_err(dev, "Use PF Control I/F to enable the VF\n"); - set_bit(ICE_VF_STATE_DIS, vf->vf_states); - return -EIO; - } - } else { - vf->num_valid_msgs++; - /* reset the invalid counter, if a valid message is received. */ - vf->num_inval_msgs = 0; - } - aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, msg, msglen, NULL); if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) { diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 02e3d306f6dd..7f16ed9c70d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -15,7 +15,6 @@ #define ICE_MAX_MACADDR_PER_VF 18 /* Malicious Driver Detection */ -#define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED 10 #define ICE_MDD_EVENTS_THRESHOLD 30 /* Static VF transaction/status register def */ @@ -199,8 +198,6 @@ struct ice_vf { unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ - u64 num_inval_msgs; /* number of continuous invalid msgs */ - u64 num_valid_msgs; /* number of valid msgs detected */ unsigned long vf_caps; /* VF's adv. capabilities */ u8 num_req_qs; /* num of queue pairs requested by VF */ u16 num_mac; diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index 41d11137cde0..5712c3e94be8 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -260,9 +260,9 @@ static int xrx200_hw_receive(struct xrx200_chan *ch) if (ctl & LTQ_DMA_EOP) { ch->skb_head->protocol = eth_type_trans(ch->skb_head, net_dev); - netif_receive_skb(ch->skb_head); net_dev->stats.rx_packets++; net_dev->stats.rx_bytes += ch->skb_head->len; + netif_receive_skb(ch->skb_head); ch->skb_head = NULL; ch->skb_tail = NULL; ret = XRX200_DMA_PACKET_COMPLETE; diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index a180b6812e54..1402c7889e78 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -560,6 +560,7 @@ static int prestera_switch_set_base_mac_addr(struct prestera_switch *sw) dev_info(prestera_dev(sw), "using random base mac address\n"); } of_node_put(base_mac_np); + of_node_put(np); return prestera_hw_switch_mac_set(sw, sw->base_mac); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 3b61224e9a3a..989e7cb48a95 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -131,11 +131,8 @@ static int cmd_alloc_index(struct mlx5_cmd *cmd) static void cmd_free_index(struct mlx5_cmd *cmd, int idx) { - unsigned long flags; - - spin_lock_irqsave(&cmd->alloc_lock, flags); + lockdep_assert_held(&cmd->alloc_lock); set_bit(idx, &cmd->bitmask); - spin_unlock_irqrestore(&cmd->alloc_lock, flags); } static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) @@ -145,17 +142,21 @@ static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) static void cmd_ent_put(struct mlx5_cmd_work_ent *ent) { + struct mlx5_cmd *cmd = ent->cmd; + unsigned long flags; + + spin_lock_irqsave(&cmd->alloc_lock, flags); if (!refcount_dec_and_test(&ent->refcnt)) - return; + goto out; if (ent->idx >= 0) { - struct mlx5_cmd *cmd = ent->cmd; - cmd_free_index(cmd, ent->idx); up(ent->page_queue ? &cmd->pages_sem : &cmd->sem); } cmd_free_ent(ent); +out: + spin_unlock_irqrestore(&cmd->alloc_lock, flags); } static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c index da169b816665..d4239e3b3c88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c @@ -88,9 +88,6 @@ void mlx5e_tir_builder_build_packet_merge(struct mlx5e_tir_builder *builder, (MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ - rough_max_l2_l3_hdr_sz) >> 8); MLX5_SET(tirc, tirc, lro_timeout_period_usecs, pkt_merge_param->timeout); break; - case MLX5E_PACKET_MERGE_SHAMPO: - MLX5_SET(tirc, tirc, packet_merge_mask, MLX5_TIRC_PACKET_MERGE_MASK_SHAMPO); - break; default: break; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b2ed2f6d4a92..91b90bbb2b28 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3643,8 +3643,7 @@ static int set_feature_hw_gro(struct net_device *netdev, bool enable) goto out; } - err = mlx5e_safe_switch_params(priv, &new_params, - mlx5e_modify_tirs_packet_merge_ctx, NULL, reset); + err = mlx5e_safe_switch_params(priv, &new_params, NULL, NULL, reset); out: mutex_unlock(&priv->state_lock); return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index 4213208d9ef7..4a6ec15ef046 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c @@ -126,6 +126,10 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, return; } + /* Handle multipath entry with lower priority value */ + if (mp->mfi && mp->mfi != fi && fi->fib_priority >= mp->mfi->fib_priority) + return; + /* Handle add/replace event */ nhs = fib_info_num_path(fi); if (nhs == 1) { @@ -135,12 +139,13 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev, int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev); if (i < 0) - i = MLX5_LAG_NORMAL_AFFINITY; - else - ++i; + return; + i++; mlx5_lag_set_port_affinity(ldev, i); } + + mp->mfi = fi; return; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c index 1e8ec4f236b2..df58cba37930 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c @@ -121,9 +121,6 @@ u32 mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains) u32 mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains) { - if (!mlx5_chains_prios_supported(chains)) - return 1; - if (mlx5_chains_ignore_flow_level_supported(chains)) return UINT_MAX; diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index bc39558fe82b..756f97dce85b 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1471,6 +1471,7 @@ static int lpc_eth_drv_resume(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct netdata_local *pldat; + int ret; if (device_may_wakeup(&pdev->dev)) disable_irq_wake(ndev->irq); @@ -1480,7 +1481,9 @@ static int lpc_eth_drv_resume(struct platform_device *pdev) pldat = netdev_priv(ndev); /* Enable interface clock */ - clk_enable(pldat->clk); + ret = clk_enable(pldat->clk); + if (ret) + return ret; /* Reset and initialize */ __lpc_eth_reset(pldat); diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index bf4a95186e55..0848b5529d48 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -3817,11 +3817,11 @@ bool qed_iov_mark_vf_flr(struct qed_hwfn *p_hwfn, u32 *p_disabled_vfs) return found; } -static void qed_iov_get_link(struct qed_hwfn *p_hwfn, - u16 vfid, - struct qed_mcp_link_params *p_params, - struct qed_mcp_link_state *p_link, - struct qed_mcp_link_capabilities *p_caps) +static int qed_iov_get_link(struct qed_hwfn *p_hwfn, + u16 vfid, + struct qed_mcp_link_params *p_params, + struct qed_mcp_link_state *p_link, + struct qed_mcp_link_capabilities *p_caps) { struct qed_vf_info *p_vf = qed_iov_get_vf_info(p_hwfn, vfid, @@ -3829,7 +3829,7 @@ static void qed_iov_get_link(struct qed_hwfn *p_hwfn, struct qed_bulletin_content *p_bulletin; if (!p_vf) - return; + return -EINVAL; p_bulletin = p_vf->bulletin.p_virt; @@ -3839,6 +3839,7 @@ static void qed_iov_get_link(struct qed_hwfn *p_hwfn, __qed_vf_get_link_state(p_hwfn, p_link, p_bulletin); if (p_caps) __qed_vf_get_link_caps(p_hwfn, p_caps, p_bulletin); + return 0; } static int @@ -4697,6 +4698,7 @@ static int qed_get_vf_config(struct qed_dev *cdev, struct qed_public_vf_info *vf_info; struct qed_mcp_link_state link; u32 tx_rate; + int ret; /* Sanitize request */ if (IS_VF(cdev)) @@ -4710,7 +4712,9 @@ static int qed_get_vf_config(struct qed_dev *cdev, vf_info = qed_iov_get_public_vf_info(hwfn, vf_id, true); - qed_iov_get_link(hwfn, vf_id, NULL, &link, NULL); + ret = qed_iov_get_link(hwfn, vf_id, NULL, &link, NULL); + if (ret) + return ret; /* Fill information about VF */ ivi->vf = vf_id; diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 597cd9cd57b5..7b0e390c0b07 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -513,6 +513,9 @@ int qed_vf_hw_prepare(struct qed_hwfn *p_hwfn) p_iov->bulletin.size, &p_iov->bulletin.phys, GFP_KERNEL); + if (!p_iov->bulletin.p_virt) + goto free_pf2vf_reply; + DP_VERBOSE(p_hwfn, QED_MSG_IOV, "VF's bulletin Board [%p virt 0x%llx phys 0x%08x bytes]\n", p_iov->bulletin.p_virt, @@ -552,6 +555,10 @@ int qed_vf_hw_prepare(struct qed_hwfn *p_hwfn) return rc; +free_pf2vf_reply: + dma_free_coherent(&p_hwfn->cdev->pdev->dev, + sizeof(union pfvf_tlvs), + p_iov->pf2vf_reply, p_iov->pf2vf_reply_phys); free_vf2pf_request: dma_free_coherent(&p_hwfn->cdev->pdev->dev, sizeof(union vfpf_tlvs), diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index ad9029ae6848..77e5dffb558f 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -3146,7 +3146,7 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, if (err) { printk(KERN_ERR "happymeal(PCI): Cannot register net device, " "aborting.\n"); - goto err_out_iounmap; + goto err_out_free_coherent; } pci_set_drvdata(pdev, hp); @@ -3179,6 +3179,10 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, return 0; +err_out_free_coherent: + dma_free_coherent(hp->dma_dev, PAGE_SIZE, + hp->happy_block, hp->hblock_dvma); + err_out_iounmap: iounmap(hp->gregs); diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c index dc70a6bfaa6a..92ca739fac01 100644 --- a/drivers/net/ethernet/ti/cpts.c +++ b/drivers/net/ethernet/ti/cpts.c @@ -568,7 +568,9 @@ int cpts_register(struct cpts *cpts) for (i = 0; i < CPTS_MAX_EVENTS; i++) list_add(&cpts->pool_data[i].list, &cpts->pool); - clk_enable(cpts->refclk); + err = clk_enable(cpts->refclk); + if (err) + return err; cpts_write32(cpts, CPTS_EN, control); cpts_write32(cpts, TS_PEND_EN, int_enable); diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index f65a638b7239..57a24f62e353 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -1183,7 +1183,7 @@ static int xemaclite_of_probe(struct platform_device *ofdev) if (rc) { dev_err(dev, "Cannot register network device, aborting\n"); - goto error; + goto put_node; } dev_info(dev, @@ -1191,6 +1191,8 @@ static int xemaclite_of_probe(struct platform_device *ofdev) (unsigned long __force)ndev->mem_start, lp->base_addr, ndev->irq); return 0; +put_node: + of_node_put(lp->phy_node); error: free_netdev(ndev); return rc; diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 211b5476a6f5..ce17b2af3218 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -274,7 +274,7 @@ static int dp83822_config_intr(struct phy_device *phydev) if (err < 0) return err; - err = phy_write(phydev, MII_DP83822_MISR1, 0); + err = phy_write(phydev, MII_DP83822_MISR2, 0); if (err < 0) return err; diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index 7e7904fee1d9..73f7962a37d3 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -30,8 +30,12 @@ #define INTSRC_LINK_DOWN BIT(4) #define INTSRC_REMOTE_FAULT BIT(5) #define INTSRC_ANEG_COMPLETE BIT(6) +#define INTSRC_ENERGY_DETECT BIT(7) #define INTSRC_MASK 30 +#define INT_SOURCES (INTSRC_LINK_DOWN | INTSRC_ANEG_COMPLETE | \ + INTSRC_ENERGY_DETECT) + #define BANK_ANALOG_DSP 0 #define BANK_WOL 1 #define BANK_BIST 3 @@ -200,7 +204,6 @@ static int meson_gxl_ack_interrupt(struct phy_device *phydev) static int meson_gxl_config_intr(struct phy_device *phydev) { - u16 val; int ret; if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { @@ -209,16 +212,9 @@ static int meson_gxl_config_intr(struct phy_device *phydev) if (ret) return ret; - val = INTSRC_ANEG_PR - | INTSRC_PARALLEL_FAULT - | INTSRC_ANEG_LP_ACK - | INTSRC_LINK_DOWN - | INTSRC_REMOTE_FAULT - | INTSRC_ANEG_COMPLETE; - ret = phy_write(phydev, INTSRC_MASK, val); + ret = phy_write(phydev, INTSRC_MASK, INT_SOURCES); } else { - val = 0; - ret = phy_write(phydev, INTSRC_MASK, val); + ret = phy_write(phydev, INTSRC_MASK, 0); /* Ack any pending IRQ */ ret = meson_gxl_ack_interrupt(phydev); @@ -237,10 +233,23 @@ static irqreturn_t meson_gxl_handle_interrupt(struct phy_device *phydev) return IRQ_NONE; } + irq_status &= INT_SOURCES; + if (irq_status == 0) return IRQ_NONE; - phy_trigger_machine(phydev); + /* Aneg-complete interrupt is used for link-up detection */ + if (phydev->autoneg == AUTONEG_ENABLE && + irq_status == INTSRC_ENERGY_DETECT) + return IRQ_HANDLED; + + /* Give PHY some time before MAC starts sending data. This works + * around an issue where network doesn't come up properly. + */ + if (!(irq_status & INTSRC_LINK_DOWN)) + phy_queue_state_machine(phydev, msecs_to_jiffies(100)); + else + phy_trigger_machine(phydev); return IRQ_HANDLED; } diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 5567220e9d16..4ef61f6b85df 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -86,9 +86,10 @@ static int __must_check __smsc95xx_read_reg(struct usbnet *dev, u32 index, ret = fn(dev, USB_VENDOR_REQUEST_READ_REGISTER, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, index, &buf, 4); - if (unlikely(ret < 0)) { - netdev_warn(dev->net, "Failed to read reg index 0x%08x: %d\n", - index, ret); + if (ret < 0) { + if (ret != -ENODEV) + netdev_warn(dev->net, "Failed to read reg index 0x%08x: %d\n", + index, ret); return ret; } @@ -118,7 +119,7 @@ static int __must_check __smsc95xx_write_reg(struct usbnet *dev, u32 index, ret = fn(dev, USB_VENDOR_REQUEST_WRITE_REGISTER, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, index, &buf, 4); - if (unlikely(ret < 0)) + if (ret < 0 && ret != -ENODEV) netdev_warn(dev->net, "Failed to write reg index 0x%08x: %d\n", index, ret); @@ -161,6 +162,9 @@ static int __must_check __smsc95xx_phy_wait_not_busy(struct usbnet *dev, do { ret = __smsc95xx_read_reg(dev, MII_ADDR, &val, in_pm); if (ret < 0) { + /* Ignore -ENODEV error during disconnect() */ + if (ret == -ENODEV) + return 0; netdev_warn(dev->net, "Error reading MII_ACCESS\n"); return ret; } @@ -196,7 +200,8 @@ static int __smsc95xx_mdio_read(struct usbnet *dev, int phy_id, int idx, addr = mii_address_cmd(phy_id, idx, MII_READ_ | MII_BUSY_); ret = __smsc95xx_write_reg(dev, MII_ADDR, addr, in_pm); if (ret < 0) { - netdev_warn(dev->net, "Error writing MII_ADDR\n"); + if (ret != -ENODEV) + netdev_warn(dev->net, "Error writing MII_ADDR\n"); goto done; } @@ -208,7 +213,8 @@ static int __smsc95xx_mdio_read(struct usbnet *dev, int phy_id, int idx, ret = __smsc95xx_read_reg(dev, MII_DATA, &val, in_pm); if (ret < 0) { - netdev_warn(dev->net, "Error reading MII_DATA\n"); + if (ret != -ENODEV) + netdev_warn(dev->net, "Error reading MII_DATA\n"); goto done; } @@ -216,6 +222,10 @@ static int __smsc95xx_mdio_read(struct usbnet *dev, int phy_id, int idx, done: mutex_unlock(&dev->phy_mutex); + + /* Ignore -ENODEV error during disconnect() */ + if (ret == -ENODEV) + return 0; return ret; } @@ -237,7 +247,8 @@ static void __smsc95xx_mdio_write(struct usbnet *dev, int phy_id, val = regval; ret = __smsc95xx_write_reg(dev, MII_DATA, val, in_pm); if (ret < 0) { - netdev_warn(dev->net, "Error writing MII_DATA\n"); + if (ret != -ENODEV) + netdev_warn(dev->net, "Error writing MII_DATA\n"); goto done; } @@ -245,7 +256,8 @@ static void __smsc95xx_mdio_write(struct usbnet *dev, int phy_id, addr = mii_address_cmd(phy_id, idx, MII_WRITE_ | MII_BUSY_); ret = __smsc95xx_write_reg(dev, MII_ADDR, addr, in_pm); if (ret < 0) { - netdev_warn(dev->net, "Error writing MII_ADDR\n"); + if (ret != -ENODEV) + netdev_warn(dev->net, "Error writing MII_ADDR\n"); goto done; } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 7748f07e2cf1..daa4e6106aac 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -424,14 +424,12 @@ static bool xennet_tx_buf_gc(struct netfront_queue *queue) queue->tx_link[id] = TX_LINK_NONE; skb = queue->tx_skbs[id]; queue->tx_skbs[id] = NULL; - if (unlikely(gnttab_query_foreign_access( - queue->grant_tx_ref[id]) != 0)) { + if (unlikely(!gnttab_end_foreign_access_ref( + queue->grant_tx_ref[id], GNTMAP_readonly))) { dev_alert(dev, "Grant still in use by backend domain\n"); goto err; } - gnttab_end_foreign_access_ref( - queue->grant_tx_ref[id], GNTMAP_readonly); gnttab_release_grant_reference( &queue->gref_tx_head, queue->grant_tx_ref[id]); queue->grant_tx_ref[id] = GRANT_INVALID_REF; @@ -990,7 +988,6 @@ static int xennet_get_responses(struct netfront_queue *queue, struct device *dev = &queue->info->netdev->dev; struct bpf_prog *xdp_prog; struct xdp_buff xdp; - unsigned long ret; int slots = 1; int err = 0; u32 verdict; @@ -1032,8 +1029,13 @@ static int xennet_get_responses(struct netfront_queue *queue, goto next; } - ret = gnttab_end_foreign_access_ref(ref, 0); - BUG_ON(!ret); + if (!gnttab_end_foreign_access_ref(ref, 0)) { + dev_alert(dev, + "Grant still in use by backend domain\n"); + queue->info->broken = true; + dev_alert(dev, "Disabled for further use\n"); + return -EINVAL; + } gnttab_release_grant_reference(&queue->gref_rx_head, ref); @@ -1254,6 +1256,10 @@ static int xennet_poll(struct napi_struct *napi, int budget) &need_xdp_flush); if (unlikely(err)) { + if (queue->info->broken) { + spin_unlock(&queue->rx_lock); + return 0; + } err: while ((skb = __skb_dequeue(&tmpq))) __skb_queue_tail(&errq, skb); @@ -1918,7 +1924,7 @@ static int setup_netfront(struct xenbus_device *dev, struct netfront_queue *queue, unsigned int feature_split_evtchn) { struct xen_netif_tx_sring *txs; - struct xen_netif_rx_sring *rxs; + struct xen_netif_rx_sring *rxs = NULL; grant_ref_t gref; int err; @@ -1938,21 +1944,21 @@ static int setup_netfront(struct xenbus_device *dev, err = xenbus_grant_ring(dev, txs, 1, &gref); if (err < 0) - goto grant_tx_ring_fail; + goto fail; queue->tx_ring_ref = gref; rxs = (struct xen_netif_rx_sring *)get_zeroed_page(GFP_NOIO | __GFP_HIGH); if (!rxs) { err = -ENOMEM; xenbus_dev_fatal(dev, err, "allocating rx ring page"); - goto alloc_rx_ring_fail; + goto fail; } SHARED_RING_INIT(rxs); FRONT_RING_INIT(&queue->rx, rxs, XEN_PAGE_SIZE); err = xenbus_grant_ring(dev, rxs, 1, &gref); if (err < 0) - goto grant_rx_ring_fail; + goto fail; queue->rx_ring_ref = gref; if (feature_split_evtchn) @@ -1965,22 +1971,28 @@ static int setup_netfront(struct xenbus_device *dev, err = setup_netfront_single(queue); if (err) - goto alloc_evtchn_fail; + goto fail; return 0; /* If we fail to setup netfront, it is safe to just revoke access to * granted pages because backend is not accessing it at this point. */ -alloc_evtchn_fail: - gnttab_end_foreign_access_ref(queue->rx_ring_ref, 0); -grant_rx_ring_fail: - free_page((unsigned long)rxs); -alloc_rx_ring_fail: - gnttab_end_foreign_access_ref(queue->tx_ring_ref, 0); -grant_tx_ring_fail: - free_page((unsigned long)txs); -fail: + fail: + if (queue->rx_ring_ref != GRANT_INVALID_REF) { + gnttab_end_foreign_access(queue->rx_ring_ref, 0, + (unsigned long)rxs); + queue->rx_ring_ref = GRANT_INVALID_REF; + } else { + free_page((unsigned long)rxs); + } + if (queue->tx_ring_ref != GRANT_INVALID_REF) { + gnttab_end_foreign_access(queue->tx_ring_ref, 0, + (unsigned long)txs); + queue->tx_ring_ref = GRANT_INVALID_REF; + } else { + free_page((unsigned long)txs); + } return err; } diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c index d7db1a0e6be1..00d8ea6dcb5d 100644 --- a/drivers/nfc/port100.c +++ b/drivers/nfc/port100.c @@ -1612,7 +1612,9 @@ free_nfc_dev: nfc_digital_free_device(dev->nfc_digital_dev); error: + usb_kill_urb(dev->in_urb); usb_free_urb(dev->in_urb); + usb_kill_urb(dev->out_urb); usb_free_urb(dev->out_urb); usb_put_dev(dev->udev); diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 80d6750c74a6..1f401377ff60 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -36,6 +36,13 @@ #include "../core.h" #include "pinctrl-sunxi.h" +/* + * These lock classes tell lockdep that GPIO IRQs are in a different + * category than their parents, so it won't report false recursion. + */ +static struct lock_class_key sunxi_pinctrl_irq_lock_class; +static struct lock_class_key sunxi_pinctrl_irq_request_class; + static struct irq_chip sunxi_pinctrl_edge_irq_chip; static struct irq_chip sunxi_pinctrl_level_irq_chip; @@ -837,7 +844,8 @@ static int sunxi_pinctrl_gpio_direction_input(struct gpio_chip *chip, { struct sunxi_pinctrl *pctl = gpiochip_get_data(chip); - return sunxi_pmx_gpio_set_direction(pctl->pctl_dev, NULL, offset, true); + return sunxi_pmx_gpio_set_direction(pctl->pctl_dev, NULL, + chip->base + offset, true); } static int sunxi_pinctrl_gpio_get(struct gpio_chip *chip, unsigned offset) @@ -890,7 +898,8 @@ static int sunxi_pinctrl_gpio_direction_output(struct gpio_chip *chip, struct sunxi_pinctrl *pctl = gpiochip_get_data(chip); sunxi_pinctrl_gpio_set(chip, offset, value); - return sunxi_pmx_gpio_set_direction(pctl->pctl_dev, NULL, offset, false); + return sunxi_pmx_gpio_set_direction(pctl->pctl_dev, NULL, + chip->base + offset, false); } static int sunxi_pinctrl_gpio_of_xlate(struct gpio_chip *gc, @@ -1555,6 +1564,8 @@ int sunxi_pinctrl_init_with_variant(struct platform_device *pdev, for (i = 0; i < (pctl->desc->irq_banks * IRQ_PER_BANK); i++) { int irqno = irq_create_mapping(pctl->domain, i); + irq_set_lockdep_class(irqno, &sunxi_pinctrl_irq_lock_class, + &sunxi_pinctrl_irq_request_class); irq_set_chip_and_handler(irqno, &sunxi_pinctrl_edge_irq_chip, handle_edge_irq); irq_set_chip_data(irqno, pctl); diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 12c10a5e3d93..7f421600cb66 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -233,12 +233,11 @@ static void scsifront_gnttab_done(struct vscsifrnt_info *info, return; for (i = 0; i < shadow->nr_grants; i++) { - if (unlikely(gnttab_query_foreign_access(shadow->gref[i]))) { + if (unlikely(!gnttab_try_end_foreign_access(shadow->gref[i]))) { shost_printk(KERN_ALERT, info->host, KBUILD_MODNAME "grant still in use by backend\n"); BUG(); } - gnttab_end_foreign_access(shadow->gref[i], 0, 0UL); } kfree(shadow->sg); diff --git a/drivers/soc/mediatek/mt8192-mmsys.h b/drivers/soc/mediatek/mt8192-mmsys.h index 6f0a57044a7b..6aae0b12b6ff 100644 --- a/drivers/soc/mediatek/mt8192-mmsys.h +++ b/drivers/soc/mediatek/mt8192-mmsys.h @@ -53,7 +53,8 @@ static const struct mtk_mmsys_routes mmsys_mt8192_routing_table[] = { MT8192_AAL0_SEL_IN_CCORR0 }, { DDP_COMPONENT_DITHER, DDP_COMPONENT_DSI0, - MT8192_DISP_DSI0_SEL_IN, MT8192_DSI0_SEL_IN_DITHER0 + MT8192_DISP_DSI0_SEL_IN, MT8192_DSI0_SEL_IN_DITHER0, + MT8192_DSI0_SEL_IN_DITHER0 }, { DDP_COMPONENT_RDMA0, DDP_COMPONENT_COLOR0, MT8192_DISP_RDMA0_SOUT_SEL, MT8192_RDMA0_SOUT_COLOR0, diff --git a/drivers/soc/samsung/exynos-chipid.c b/drivers/soc/samsung/exynos-chipid.c index 2746d05936d3..0fb3631e7346 100644 --- a/drivers/soc/samsung/exynos-chipid.c +++ b/drivers/soc/samsung/exynos-chipid.c @@ -204,7 +204,7 @@ module_platform_driver(exynos_chipid_driver); MODULE_DESCRIPTION("Samsung Exynos ChipID controller and ASV driver"); MODULE_AUTHOR("Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>"); -MODULE_AUTHOR("Krzysztof Kozlowski <krzysztof.kozlowski@canonical.com>"); +MODULE_AUTHOR("Krzysztof Kozlowski <krzk@kernel.org>"); MODULE_AUTHOR("Pankaj Dubey <pankaj.dubey@samsung.com>"); MODULE_AUTHOR("Sylwester Nawrocki <s.nawrocki@samsung.com>"); MODULE_LICENSE("GPL"); diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ead9a132dcb9..646cff67e06d 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1012,10 +1012,10 @@ int spi_map_buf(struct spi_controller *ctlr, struct device *dev, int i, ret; if (vmalloced_buf || kmap_buf) { - desc_len = min_t(int, max_seg_size, PAGE_SIZE); + desc_len = min_t(unsigned int, max_seg_size, PAGE_SIZE); sgs = DIV_ROUND_UP(len + offset_in_page(buf), desc_len); } else if (virt_addr_valid(buf)) { - desc_len = min_t(int, max_seg_size, ctlr->max_dma_len); + desc_len = min_t(unsigned int, max_seg_size, ctlr->max_dma_len); sgs = DIV_ROUND_UP(len, desc_len); } else { return -EINVAL; diff --git a/drivers/staging/gdm724x/gdm_lte.c b/drivers/staging/gdm724x/gdm_lte.c index 2587309da766..8ebb21d4b24b 100644 --- a/drivers/staging/gdm724x/gdm_lte.c +++ b/drivers/staging/gdm724x/gdm_lte.c @@ -76,14 +76,15 @@ static void tx_complete(void *arg) static int gdm_lte_rx(struct sk_buff *skb, struct nic *nic, int nic_type) { - int ret; + int ret, len; + len = skb->len + ETH_HLEN; ret = netif_rx(skb); if (ret == NET_RX_DROP) { nic->stats.rx_dropped++; } else { nic->stats.rx_packets++; - nic->stats.rx_bytes += skb->len + ETH_HLEN; + nic->stats.rx_bytes += len; } return 0; diff --git a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c index 0f82f5031c43..49a3f45cb771 100644 --- a/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c +++ b/drivers/staging/rtl8723bs/core/rtw_mlme_ext.c @@ -5907,6 +5907,7 @@ u8 chk_bmc_sleepq_hdl(struct adapter *padapter, unsigned char *pbuf) struct sta_info *psta_bmc; struct list_head *xmitframe_plist, *xmitframe_phead, *tmp; struct xmit_frame *pxmitframe = NULL; + struct xmit_priv *pxmitpriv = &padapter->xmitpriv; struct sta_priv *pstapriv = &padapter->stapriv; /* for BC/MC Frames */ @@ -5917,7 +5918,8 @@ u8 chk_bmc_sleepq_hdl(struct adapter *padapter, unsigned char *pbuf) if ((pstapriv->tim_bitmap&BIT(0)) && (psta_bmc->sleepq_len > 0)) { msleep(10);/* 10ms, ATIM(HIQ) Windows */ - spin_lock_bh(&psta_bmc->sleep_q.lock); + /* spin_lock_bh(&psta_bmc->sleep_q.lock); */ + spin_lock_bh(&pxmitpriv->lock); xmitframe_phead = get_list_head(&psta_bmc->sleep_q); list_for_each_safe(xmitframe_plist, tmp, xmitframe_phead) { @@ -5940,7 +5942,8 @@ u8 chk_bmc_sleepq_hdl(struct adapter *padapter, unsigned char *pbuf) rtw_hal_xmitframe_enqueue(padapter, pxmitframe); } - spin_unlock_bh(&psta_bmc->sleep_q.lock); + /* spin_unlock_bh(&psta_bmc->sleep_q.lock); */ + spin_unlock_bh(&pxmitpriv->lock); /* check hi queue and bmc_sleepq */ rtw_chk_hi_queue_cmd(padapter); diff --git a/drivers/staging/rtl8723bs/core/rtw_recv.c b/drivers/staging/rtl8723bs/core/rtw_recv.c index 41bfca549c64..105fe0e3482a 100644 --- a/drivers/staging/rtl8723bs/core/rtw_recv.c +++ b/drivers/staging/rtl8723bs/core/rtw_recv.c @@ -957,8 +957,10 @@ static signed int validate_recv_ctrl_frame(struct adapter *padapter, union recv_ if ((psta->state&WIFI_SLEEP_STATE) && (pstapriv->sta_dz_bitmap&BIT(psta->aid))) { struct list_head *xmitframe_plist, *xmitframe_phead; struct xmit_frame *pxmitframe = NULL; + struct xmit_priv *pxmitpriv = &padapter->xmitpriv; - spin_lock_bh(&psta->sleep_q.lock); + /* spin_lock_bh(&psta->sleep_q.lock); */ + spin_lock_bh(&pxmitpriv->lock); xmitframe_phead = get_list_head(&psta->sleep_q); xmitframe_plist = get_next(xmitframe_phead); @@ -989,10 +991,12 @@ static signed int validate_recv_ctrl_frame(struct adapter *padapter, union recv_ update_beacon(padapter, WLAN_EID_TIM, NULL, true); } - spin_unlock_bh(&psta->sleep_q.lock); + /* spin_unlock_bh(&psta->sleep_q.lock); */ + spin_unlock_bh(&pxmitpriv->lock); } else { - spin_unlock_bh(&psta->sleep_q.lock); + /* spin_unlock_bh(&psta->sleep_q.lock); */ + spin_unlock_bh(&pxmitpriv->lock); if (pstapriv->tim_bitmap&BIT(psta->aid)) { if (psta->sleepq_len == 0) { diff --git a/drivers/staging/rtl8723bs/core/rtw_sta_mgt.c b/drivers/staging/rtl8723bs/core/rtw_sta_mgt.c index 0c9ea1520fd0..beb11d89db18 100644 --- a/drivers/staging/rtl8723bs/core/rtw_sta_mgt.c +++ b/drivers/staging/rtl8723bs/core/rtw_sta_mgt.c @@ -293,48 +293,46 @@ u32 rtw_free_stainfo(struct adapter *padapter, struct sta_info *psta) /* list_del_init(&psta->wakeup_list); */ - spin_lock_bh(&psta->sleep_q.lock); + spin_lock_bh(&pxmitpriv->lock); + rtw_free_xmitframe_queue(pxmitpriv, &psta->sleep_q); psta->sleepq_len = 0; - spin_unlock_bh(&psta->sleep_q.lock); - - spin_lock_bh(&pxmitpriv->lock); /* vo */ - spin_lock_bh(&pstaxmitpriv->vo_q.sta_pending.lock); + /* spin_lock_bh(&(pxmitpriv->vo_pending.lock)); */ rtw_free_xmitframe_queue(pxmitpriv, &pstaxmitpriv->vo_q.sta_pending); list_del_init(&(pstaxmitpriv->vo_q.tx_pending)); phwxmit = pxmitpriv->hwxmits; phwxmit->accnt -= pstaxmitpriv->vo_q.qcnt; pstaxmitpriv->vo_q.qcnt = 0; - spin_unlock_bh(&pstaxmitpriv->vo_q.sta_pending.lock); + /* spin_unlock_bh(&(pxmitpriv->vo_pending.lock)); */ /* vi */ - spin_lock_bh(&pstaxmitpriv->vi_q.sta_pending.lock); + /* spin_lock_bh(&(pxmitpriv->vi_pending.lock)); */ rtw_free_xmitframe_queue(pxmitpriv, &pstaxmitpriv->vi_q.sta_pending); list_del_init(&(pstaxmitpriv->vi_q.tx_pending)); phwxmit = pxmitpriv->hwxmits+1; phwxmit->accnt -= pstaxmitpriv->vi_q.qcnt; pstaxmitpriv->vi_q.qcnt = 0; - spin_unlock_bh(&pstaxmitpriv->vi_q.sta_pending.lock); + /* spin_unlock_bh(&(pxmitpriv->vi_pending.lock)); */ /* be */ - spin_lock_bh(&pstaxmitpriv->be_q.sta_pending.lock); + /* spin_lock_bh(&(pxmitpriv->be_pending.lock)); */ rtw_free_xmitframe_queue(pxmitpriv, &pstaxmitpriv->be_q.sta_pending); list_del_init(&(pstaxmitpriv->be_q.tx_pending)); phwxmit = pxmitpriv->hwxmits+2; phwxmit->accnt -= pstaxmitpriv->be_q.qcnt; pstaxmitpriv->be_q.qcnt = 0; - spin_unlock_bh(&pstaxmitpriv->be_q.sta_pending.lock); + /* spin_unlock_bh(&(pxmitpriv->be_pending.lock)); */ /* bk */ - spin_lock_bh(&pstaxmitpriv->bk_q.sta_pending.lock); + /* spin_lock_bh(&(pxmitpriv->bk_pending.lock)); */ rtw_free_xmitframe_queue(pxmitpriv, &pstaxmitpriv->bk_q.sta_pending); list_del_init(&(pstaxmitpriv->bk_q.tx_pending)); phwxmit = pxmitpriv->hwxmits+3; phwxmit->accnt -= pstaxmitpriv->bk_q.qcnt; pstaxmitpriv->bk_q.qcnt = 0; - spin_unlock_bh(&pstaxmitpriv->bk_q.sta_pending.lock); + /* spin_unlock_bh(&(pxmitpriv->bk_pending.lock)); */ spin_unlock_bh(&pxmitpriv->lock); diff --git a/drivers/staging/rtl8723bs/core/rtw_xmit.c b/drivers/staging/rtl8723bs/core/rtw_xmit.c index 13b8bd5ffabc..f466bfd248fb 100644 --- a/drivers/staging/rtl8723bs/core/rtw_xmit.c +++ b/drivers/staging/rtl8723bs/core/rtw_xmit.c @@ -1734,12 +1734,15 @@ void rtw_free_xmitframe_queue(struct xmit_priv *pxmitpriv, struct __queue *pfram struct list_head *plist, *phead, *tmp; struct xmit_frame *pxmitframe; + spin_lock_bh(&pframequeue->lock); + phead = get_list_head(pframequeue); list_for_each_safe(plist, tmp, phead) { pxmitframe = list_entry(plist, struct xmit_frame, list); rtw_free_xmitframe(pxmitpriv, pxmitframe); } + spin_unlock_bh(&pframequeue->lock); } s32 rtw_xmitframe_enqueue(struct adapter *padapter, struct xmit_frame *pxmitframe) @@ -1794,7 +1797,6 @@ s32 rtw_xmit_classifier(struct adapter *padapter, struct xmit_frame *pxmitframe) struct sta_info *psta; struct tx_servq *ptxservq; struct pkt_attrib *pattrib = &pxmitframe->attrib; - struct xmit_priv *xmit_priv = &padapter->xmitpriv; struct hw_xmit *phwxmits = padapter->xmitpriv.hwxmits; signed int res = _SUCCESS; @@ -1812,14 +1814,12 @@ s32 rtw_xmit_classifier(struct adapter *padapter, struct xmit_frame *pxmitframe) ptxservq = rtw_get_sta_pending(padapter, psta, pattrib->priority, (u8 *)(&ac_index)); - spin_lock_bh(&xmit_priv->lock); if (list_empty(&ptxservq->tx_pending)) list_add_tail(&ptxservq->tx_pending, get_list_head(phwxmits[ac_index].sta_queue)); list_add_tail(&pxmitframe->list, get_list_head(&ptxservq->sta_pending)); ptxservq->qcnt++; phwxmits[ac_index].accnt++; - spin_unlock_bh(&xmit_priv->lock); exit: @@ -2202,10 +2202,11 @@ void wakeup_sta_to_xmit(struct adapter *padapter, struct sta_info *psta) struct list_head *xmitframe_plist, *xmitframe_phead, *tmp; struct xmit_frame *pxmitframe = NULL; struct sta_priv *pstapriv = &padapter->stapriv; + struct xmit_priv *pxmitpriv = &padapter->xmitpriv; psta_bmc = rtw_get_bcmc_stainfo(padapter); - spin_lock_bh(&psta->sleep_q.lock); + spin_lock_bh(&pxmitpriv->lock); xmitframe_phead = get_list_head(&psta->sleep_q); list_for_each_safe(xmitframe_plist, tmp, xmitframe_phead) { @@ -2306,7 +2307,7 @@ void wakeup_sta_to_xmit(struct adapter *padapter, struct sta_info *psta) _exit: - spin_unlock_bh(&psta->sleep_q.lock); + spin_unlock_bh(&pxmitpriv->lock); if (update_mask) update_beacon(padapter, WLAN_EID_TIM, NULL, true); @@ -2318,8 +2319,9 @@ void xmit_delivery_enabled_frames(struct adapter *padapter, struct sta_info *pst struct list_head *xmitframe_plist, *xmitframe_phead, *tmp; struct xmit_frame *pxmitframe = NULL; struct sta_priv *pstapriv = &padapter->stapriv; + struct xmit_priv *pxmitpriv = &padapter->xmitpriv; - spin_lock_bh(&psta->sleep_q.lock); + spin_lock_bh(&pxmitpriv->lock); xmitframe_phead = get_list_head(&psta->sleep_q); list_for_each_safe(xmitframe_plist, tmp, xmitframe_phead) { @@ -2372,7 +2374,7 @@ void xmit_delivery_enabled_frames(struct adapter *padapter, struct sta_info *pst } } - spin_unlock_bh(&psta->sleep_q.lock); + spin_unlock_bh(&pxmitpriv->lock); } void enqueue_pending_xmitbuf(struct xmit_priv *pxmitpriv, struct xmit_buf *pxmitbuf) diff --git a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c index b5d5e922231c..15810438a472 100644 --- a/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c +++ b/drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c @@ -502,7 +502,9 @@ s32 rtl8723bs_hal_xmit( rtw_issue_addbareq_cmd(padapter, pxmitframe); } + spin_lock_bh(&pxmitpriv->lock); err = rtw_xmitframe_enqueue(padapter, pxmitframe); + spin_unlock_bh(&pxmitpriv->lock); if (err != _SUCCESS) { rtw_free_xmitframe(pxmitpriv, pxmitframe); diff --git a/drivers/staging/rtl8723bs/include/rtw_mlme.h b/drivers/staging/rtl8723bs/include/rtw_mlme.h index c94fa7d8d5a9..1b343b434f4d 100644 --- a/drivers/staging/rtl8723bs/include/rtw_mlme.h +++ b/drivers/staging/rtl8723bs/include/rtw_mlme.h @@ -102,13 +102,17 @@ there are several "locks" in mlme_priv, since mlme_priv is a shared resource between many threads, like ISR/Call-Back functions, the OID handlers, and even timer functions. - Each struct __queue has its own locks, already. -Other items are protected by mlme_priv.lock. +Other items in mlme_priv are protected by mlme_priv.lock, while items in +xmit_priv are protected by xmit_priv.lock. To avoid possible dead lock, any thread trying to modifiying mlme_priv SHALL not lock up more than one locks at a time! +The only exception is that queue functions which take the __queue.lock +may be called with the xmit_priv.lock held. In this case the order +MUST always be first lock xmit_priv.lock and then call any queue functions +which take __queue.lock. */ diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c index a16dd4d5d710..73e68cce292e 100644 --- a/drivers/thermal/thermal_netlink.c +++ b/drivers/thermal/thermal_netlink.c @@ -419,11 +419,12 @@ static int thermal_genl_cmd_tz_get_trip(struct param *p) for (i = 0; i < tz->trips; i++) { enum thermal_trip_type type; - int temp, hyst; + int temp, hyst = 0; tz->ops->get_trip_type(tz, i, &type); tz->ops->get_trip_temp(tz, i, &temp); - tz->ops->get_trip_hyst(tz, i, &hyst); + if (tz->ops->get_trip_hyst) + tz->ops->get_trip_hyst(tz, i, &hyst); if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, i) || nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, type) || diff --git a/drivers/usb/host/xen-hcd.c b/drivers/usb/host/xen-hcd.c index be09fd9bac58..19b8c7ed74cb 100644 --- a/drivers/usb/host/xen-hcd.c +++ b/drivers/usb/host/xen-hcd.c @@ -716,8 +716,9 @@ static int xenhcd_map_urb_for_request(struct xenhcd_info *info, struct urb *urb, return 0; } -static void xenhcd_gnttab_done(struct usb_shadow *shadow) +static void xenhcd_gnttab_done(struct xenhcd_info *info, unsigned int id) { + struct usb_shadow *shadow = info->shadow + id; int nr_segs = 0; int i; @@ -726,8 +727,10 @@ static void xenhcd_gnttab_done(struct usb_shadow *shadow) if (xenusb_pipeisoc(shadow->req.pipe)) nr_segs += shadow->req.u.isoc.nr_frame_desc_segs; - for (i = 0; i < nr_segs; i++) - gnttab_end_foreign_access(shadow->req.seg[i].gref, 0, 0UL); + for (i = 0; i < nr_segs; i++) { + if (!gnttab_try_end_foreign_access(shadow->req.seg[i].gref)) + xenhcd_set_error(info, "backend didn't release grant"); + } shadow->req.nr_buffer_segs = 0; shadow->req.u.isoc.nr_frame_desc_segs = 0; @@ -841,7 +844,9 @@ static void xenhcd_cancel_all_enqueued_urbs(struct xenhcd_info *info) list_for_each_entry_safe(urbp, tmp, &info->in_progress_list, list) { req_id = urbp->req_id; if (!urbp->unlinked) { - xenhcd_gnttab_done(&info->shadow[req_id]); + xenhcd_gnttab_done(info, req_id); + if (info->error) + return; if (urbp->urb->status == -EINPROGRESS) /* not dequeued */ xenhcd_giveback_urb(info, urbp->urb, @@ -942,8 +947,7 @@ static int xenhcd_urb_request_done(struct xenhcd_info *info) rp = info->urb_ring.sring->rsp_prod; if (RING_RESPONSE_PROD_OVERFLOW(&info->urb_ring, rp)) { xenhcd_set_error(info, "Illegal index on urb-ring"); - spin_unlock_irqrestore(&info->lock, flags); - return 0; + goto err; } rmb(); /* ensure we see queued responses up to "rp" */ @@ -952,11 +956,13 @@ static int xenhcd_urb_request_done(struct xenhcd_info *info) id = res.id; if (id >= XENUSB_URB_RING_SIZE) { xenhcd_set_error(info, "Illegal data on urb-ring"); - continue; + goto err; } if (likely(xenusb_pipesubmit(info->shadow[id].req.pipe))) { - xenhcd_gnttab_done(&info->shadow[id]); + xenhcd_gnttab_done(info, id); + if (info->error) + goto err; urb = info->shadow[id].urb; if (likely(urb)) { urb->actual_length = res.actual_length; @@ -978,6 +984,10 @@ static int xenhcd_urb_request_done(struct xenhcd_info *info) spin_unlock_irqrestore(&info->lock, flags); return more_to_do; + + err: + spin_unlock_irqrestore(&info->lock, flags); + return 0; } static int xenhcd_conn_notify(struct xenhcd_info *info) diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index f648f1c54a0f..d0f91078600e 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -1563,11 +1563,27 @@ static virtio_net_ctrl_ack handle_ctrl_mq(struct mlx5_vdpa_dev *mvdev, u8 cmd) switch (cmd) { case VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET: + /* This mq feature check aligns with pre-existing userspace + * implementation. + * + * Without it, an untrusted driver could fake a multiqueue config + * request down to a non-mq device that may cause kernel to + * panic due to uninitialized resources for extra vqs. Even with + * a well behaving guest driver, it is not expected to allow + * changing the number of vqs on a non-mq device. + */ + if (!MLX5_FEATURE(mvdev, VIRTIO_NET_F_MQ)) + break; + read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->riov, (void *)&mq, sizeof(mq)); if (read != sizeof(mq)) break; newqps = mlx5vdpa16_to_cpu(mvdev, mq.virtqueue_pairs); + if (newqps < VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN || + newqps > mlx5_vdpa_max_qps(mvdev->max_vqs)) + break; + if (ndev->cur_num_vqs == 2 * newqps) { status = VIRTIO_NET_OK; break; @@ -1897,11 +1913,25 @@ static u64 mlx5_vdpa_get_device_features(struct vdpa_device *vdev) return ndev->mvdev.mlx_features; } -static int verify_min_features(struct mlx5_vdpa_dev *mvdev, u64 features) +static int verify_driver_features(struct mlx5_vdpa_dev *mvdev, u64 features) { + /* Minimum features to expect */ if (!(features & BIT_ULL(VIRTIO_F_ACCESS_PLATFORM))) return -EOPNOTSUPP; + /* Double check features combination sent down by the driver. + * Fail invalid features due to absence of the depended feature. + * + * Per VIRTIO v1.1 specification, section 5.1.3.1 Feature bit + * requirements: "VIRTIO_NET_F_MQ Requires VIRTIO_NET_F_CTRL_VQ". + * By failing the invalid features sent down by untrusted drivers, + * we're assured the assumption made upon is_index_valid() and + * is_ctrl_vq_idx() will not be compromised. + */ + if ((features & (BIT_ULL(VIRTIO_NET_F_MQ) | BIT_ULL(VIRTIO_NET_F_CTRL_VQ))) == + BIT_ULL(VIRTIO_NET_F_MQ)) + return -EINVAL; + return 0; } @@ -1977,7 +2007,7 @@ static int mlx5_vdpa_set_driver_features(struct vdpa_device *vdev, u64 features) print_features(mvdev, features, true); - err = verify_min_features(mvdev, features); + err = verify_driver_features(mvdev, features); if (err) return err; diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index 9846c9de4bfa..1ea525433a5c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -393,7 +393,7 @@ static void vdpa_get_config_unlocked(struct vdpa_device *vdev, * If it does happen we assume a legacy guest. */ if (!vdev->features_valid) - vdpa_set_features(vdev, 0, true); + vdpa_set_features_unlocked(vdev, 0); ops->get_config(vdev, offset, buf, len); } diff --git a/drivers/vdpa/vdpa_user/iova_domain.c b/drivers/vdpa/vdpa_user/iova_domain.c index 2b1143f11d8f..0a4d93edc4c0 100644 --- a/drivers/vdpa/vdpa_user/iova_domain.c +++ b/drivers/vdpa/vdpa_user/iova_domain.c @@ -294,7 +294,7 @@ vduse_domain_alloc_iova(struct iova_domain *iovad, iova_pfn = alloc_iova_fast(iovad, iova_len, limit >> shift, true); - return iova_pfn << shift; + return (dma_addr_t)iova_pfn << shift; } static void vduse_domain_free_iova(struct iova_domain *iovad, diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c index a57e381e830b..cce101e6a940 100644 --- a/drivers/vdpa/virtio_pci/vp_vdpa.c +++ b/drivers/vdpa/virtio_pci/vp_vdpa.c @@ -533,8 +533,8 @@ static void vp_vdpa_remove(struct pci_dev *pdev) { struct vp_vdpa *vp_vdpa = pci_get_drvdata(pdev); - vdpa_unregister_device(&vp_vdpa->vdpa); vp_modern_remove(&vp_vdpa->mdev); + vdpa_unregister_device(&vp_vdpa->vdpa); } static struct pci_driver vp_vdpa_driver = { diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c index 670d56c879e5..40b098320b2a 100644 --- a/drivers/vhost/iotlb.c +++ b/drivers/vhost/iotlb.c @@ -57,6 +57,17 @@ int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, if (last < start) return -EFAULT; + /* If the range being mapped is [0, ULONG_MAX], split it into two entries + * otherwise its size would overflow u64. + */ + if (start == 0 && last == ULONG_MAX) { + u64 mid = last / 2; + + vhost_iotlb_add_range_ctx(iotlb, start, mid, addr, perm, opaque); + addr += mid + 1; + start = mid + 1; + } + if (iotlb->limit && iotlb->nmaps == iotlb->limit && iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) { diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 851539807bc9..ec5249e8c32d 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -286,7 +286,7 @@ static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep) if (copy_from_user(&features, featurep, sizeof(features))) return -EFAULT; - if (vdpa_set_features(vdpa, features, false)) + if (vdpa_set_features(vdpa, features)) return -EINVAL; return 0; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 59edb5a1ffe2..082380c03a3e 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1170,6 +1170,11 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, goto done; } + if (msg.size == 0) { + ret = -EINVAL; + goto done; + } + if (dev->msg_handler) ret = dev->msg_handler(dev, &msg); else @@ -1981,7 +1986,7 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq) return 0; } -static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event) +static int vhost_update_avail_event(struct vhost_virtqueue *vq) { if (vhost_put_avail_event(vq)) return -EFAULT; @@ -2527,7 +2532,7 @@ bool vhost_enable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq) return false; } } else { - r = vhost_update_avail_event(vq, vq->avail_idx); + r = vhost_update_avail_event(vq); if (r) { vq_err(vq, "Failed to update avail event index at %p: %d\n", vhost_avail_event(vq), r); diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index 34f80b7a8a64..492fc26f0b65 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -105,7 +105,6 @@ config VIRTIO_BALLOON config VIRTIO_MEM tristate "Virtio mem driver" - default m depends on X86_64 depends on VIRTIO depends on MEMORY_HOTPLUG diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 00ac9db792a4..22f15f444f75 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -166,14 +166,13 @@ void virtio_add_status(struct virtio_device *dev, unsigned int status) } EXPORT_SYMBOL_GPL(virtio_add_status); -int virtio_finalize_features(struct virtio_device *dev) +/* Do some validation, then set FEATURES_OK */ +static int virtio_features_ok(struct virtio_device *dev) { - int ret = dev->config->finalize_features(dev); unsigned status; + int ret; might_sleep(); - if (ret) - return ret; ret = arch_has_restricted_virtio_memory_access(); if (ret) { @@ -202,8 +201,23 @@ int virtio_finalize_features(struct virtio_device *dev) } return 0; } -EXPORT_SYMBOL_GPL(virtio_finalize_features); +/** + * virtio_reset_device - quiesce device for removal + * @dev: the device to reset + * + * Prevents device from sending interrupts and accessing memory. + * + * Generally used for cleanup during driver / device removal. + * + * Once this has been invoked, caller must ensure that + * virtqueue_notify / virtqueue_kick are not in progress. + * + * Note: this guarantees that vq callbacks are not in progress, however caller + * is responsible for preventing access from other contexts, such as a system + * call/workqueue/bh. Invoking virtio_break_device then flushing any such + * contexts is one way to handle that. + * */ void virtio_reset_device(struct virtio_device *dev) { dev->config->reset(dev); @@ -245,17 +259,6 @@ static int virtio_dev_probe(struct device *_d) driver_features_legacy = driver_features; } - /* - * Some devices detect legacy solely via F_VERSION_1. Write - * F_VERSION_1 to force LE config space accesses before FEATURES_OK for - * these when needed. - */ - if (drv->validate && !virtio_legacy_is_little_endian() - && device_features & BIT_ULL(VIRTIO_F_VERSION_1)) { - dev->features = BIT_ULL(VIRTIO_F_VERSION_1); - dev->config->finalize_features(dev); - } - if (device_features & (1ULL << VIRTIO_F_VERSION_1)) dev->features = driver_features & device_features; else @@ -266,13 +269,26 @@ static int virtio_dev_probe(struct device *_d) if (device_features & (1ULL << i)) __virtio_set_bit(dev, i); + err = dev->config->finalize_features(dev); + if (err) + goto err; + if (drv->validate) { + u64 features = dev->features; + err = drv->validate(dev); if (err) goto err; + + /* Did validation change any features? Then write them again. */ + if (features != dev->features) { + err = dev->config->finalize_features(dev); + if (err) + goto err; + } } - err = virtio_finalize_features(dev); + err = virtio_features_ok(dev); if (err) goto err; @@ -496,7 +512,11 @@ int virtio_device_restore(struct virtio_device *dev) /* We have a driver! */ virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER); - ret = virtio_finalize_features(dev); + ret = dev->config->finalize_features(dev); + if (ret) + goto err; + + ret = virtio_features_ok(dev); if (ret) goto err; diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c index 7767a7f0119b..76504559bc25 100644 --- a/drivers/virtio/virtio_vdpa.c +++ b/drivers/virtio/virtio_vdpa.c @@ -317,7 +317,7 @@ static int virtio_vdpa_finalize_features(struct virtio_device *vdev) /* Give virtio_ring a chance to accept features. */ vring_transport_features(vdev); - return vdpa_set_features(vdpa, vdev->features, false); + return vdpa_set_features(vdpa, vdev->features); } static const char *virtio_vdpa_bus_name(struct virtio_device *vdev) diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index 3fa40c723e8e..edb0acd0b832 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -169,20 +169,14 @@ undo: __del_gref(gref); } - /* It's possible for the target domain to map the just-allocated grant - * references by blindly guessing their IDs; if this is done, then - * __del_gref will leave them in the queue_gref list. They need to be - * added to the global list so that we can free them when they are no - * longer referenced. - */ - if (unlikely(!list_empty(&queue_gref))) - list_splice_tail(&queue_gref, &gref_list); mutex_unlock(&gref_mutex); return rc; } static void __del_gref(struct gntalloc_gref *gref) { + unsigned long addr; + if (gref->notify.flags & UNMAP_NOTIFY_CLEAR_BYTE) { uint8_t *tmp = kmap(gref->page); tmp[gref->notify.pgoff] = 0; @@ -196,21 +190,16 @@ static void __del_gref(struct gntalloc_gref *gref) gref->notify.flags = 0; if (gref->gref_id) { - if (gnttab_query_foreign_access(gref->gref_id)) - return; - - if (!gnttab_end_foreign_access_ref(gref->gref_id, 0)) - return; - - gnttab_free_grant_reference(gref->gref_id); + if (gref->page) { + addr = (unsigned long)page_to_virt(gref->page); + gnttab_end_foreign_access(gref->gref_id, 0, addr); + } else + gnttab_free_grant_reference(gref->gref_id); } gref_size--; list_del(&gref->next_gref); - if (gref->page) - __free_page(gref->page); - kfree(gref); } diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 3729bea0c989..5c83d41766c8 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -134,12 +134,9 @@ struct gnttab_ops { */ unsigned long (*end_foreign_transfer_ref)(grant_ref_t ref); /* - * Query the status of a grant entry. Ref parameter is reference of - * queried grant entry, return value is the status of queried entry. - * Detailed status(writing/reading) can be gotten from the return value - * by bit operations. + * Read the frame number related to a given grant reference. */ - int (*query_foreign_access)(grant_ref_t ref); + unsigned long (*read_frame)(grant_ref_t ref); }; struct unmap_refs_callback_data { @@ -284,22 +281,6 @@ int gnttab_grant_foreign_access(domid_t domid, unsigned long frame, } EXPORT_SYMBOL_GPL(gnttab_grant_foreign_access); -static int gnttab_query_foreign_access_v1(grant_ref_t ref) -{ - return gnttab_shared.v1[ref].flags & (GTF_reading|GTF_writing); -} - -static int gnttab_query_foreign_access_v2(grant_ref_t ref) -{ - return grstatus[ref] & (GTF_reading|GTF_writing); -} - -int gnttab_query_foreign_access(grant_ref_t ref) -{ - return gnttab_interface->query_foreign_access(ref); -} -EXPORT_SYMBOL_GPL(gnttab_query_foreign_access); - static int gnttab_end_foreign_access_ref_v1(grant_ref_t ref, int readonly) { u16 flags, nflags; @@ -353,6 +334,16 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly) } EXPORT_SYMBOL_GPL(gnttab_end_foreign_access_ref); +static unsigned long gnttab_read_frame_v1(grant_ref_t ref) +{ + return gnttab_shared.v1[ref].frame; +} + +static unsigned long gnttab_read_frame_v2(grant_ref_t ref) +{ + return gnttab_shared.v2[ref].full_page.frame; +} + struct deferred_entry { struct list_head list; grant_ref_t ref; @@ -382,12 +373,9 @@ static void gnttab_handle_deferred(struct timer_list *unused) spin_unlock_irqrestore(&gnttab_list_lock, flags); if (_gnttab_end_foreign_access_ref(entry->ref, entry->ro)) { put_free_entry(entry->ref); - if (entry->page) { - pr_debug("freeing g.e. %#x (pfn %#lx)\n", - entry->ref, page_to_pfn(entry->page)); - put_page(entry->page); - } else - pr_info("freeing g.e. %#x\n", entry->ref); + pr_debug("freeing g.e. %#x (pfn %#lx)\n", + entry->ref, page_to_pfn(entry->page)); + put_page(entry->page); kfree(entry); entry = NULL; } else { @@ -412,9 +400,18 @@ static void gnttab_handle_deferred(struct timer_list *unused) static void gnttab_add_deferred(grant_ref_t ref, bool readonly, struct page *page) { - struct deferred_entry *entry = kmalloc(sizeof(*entry), GFP_ATOMIC); + struct deferred_entry *entry; + gfp_t gfp = (in_atomic() || irqs_disabled()) ? GFP_ATOMIC : GFP_KERNEL; const char *what = KERN_WARNING "leaking"; + entry = kmalloc(sizeof(*entry), gfp); + if (!page) { + unsigned long gfn = gnttab_interface->read_frame(ref); + + page = pfn_to_page(gfn_to_pfn(gfn)); + get_page(page); + } + if (entry) { unsigned long flags; @@ -435,11 +432,21 @@ static void gnttab_add_deferred(grant_ref_t ref, bool readonly, what, ref, page ? page_to_pfn(page) : -1); } +int gnttab_try_end_foreign_access(grant_ref_t ref) +{ + int ret = _gnttab_end_foreign_access_ref(ref, 0); + + if (ret) + put_free_entry(ref); + + return ret; +} +EXPORT_SYMBOL_GPL(gnttab_try_end_foreign_access); + void gnttab_end_foreign_access(grant_ref_t ref, int readonly, unsigned long page) { - if (gnttab_end_foreign_access_ref(ref, readonly)) { - put_free_entry(ref); + if (gnttab_try_end_foreign_access(ref)) { if (page != 0) put_page(virt_to_page(page)); } else @@ -1417,7 +1424,7 @@ static const struct gnttab_ops gnttab_v1_ops = { .update_entry = gnttab_update_entry_v1, .end_foreign_access_ref = gnttab_end_foreign_access_ref_v1, .end_foreign_transfer_ref = gnttab_end_foreign_transfer_ref_v1, - .query_foreign_access = gnttab_query_foreign_access_v1, + .read_frame = gnttab_read_frame_v1, }; static const struct gnttab_ops gnttab_v2_ops = { @@ -1429,7 +1436,7 @@ static const struct gnttab_ops gnttab_v2_ops = { .update_entry = gnttab_update_entry_v2, .end_foreign_access_ref = gnttab_end_foreign_access_ref_v2, .end_foreign_transfer_ref = gnttab_end_foreign_transfer_ref_v2, - .query_foreign_access = gnttab_query_foreign_access_v2, + .read_frame = gnttab_read_frame_v2, }; static bool gnttab_need_v2(void) diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 3c9ae156b597..0ca351f30a6d 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -337,8 +337,8 @@ static void free_active_ring(struct sock_mapping *map) if (!map->active.ring) return; - free_pages((unsigned long)map->active.data.in, - map->active.ring->ring_order); + free_pages_exact(map->active.data.in, + PAGE_SIZE << map->active.ring->ring_order); free_page((unsigned long)map->active.ring); } @@ -352,8 +352,8 @@ static int alloc_active_ring(struct sock_mapping *map) goto out; map->active.ring->ring_order = PVCALLS_RING_ORDER; - bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - PVCALLS_RING_ORDER); + bytes = alloc_pages_exact(PAGE_SIZE << PVCALLS_RING_ORDER, + GFP_KERNEL | __GFP_ZERO); if (!bytes) goto out; diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c index e8bed1cb76ba..df6890681231 100644 --- a/drivers/xen/xenbus/xenbus_client.c +++ b/drivers/xen/xenbus/xenbus_client.c @@ -379,7 +379,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, unsigned int nr_pages, grant_ref_t *grefs) { int err; - int i, j; + unsigned int i; + grant_ref_t gref_head; + + err = gnttab_alloc_grant_references(nr_pages, &gref_head); + if (err) { + xenbus_dev_fatal(dev, err, "granting access to ring page"); + return err; + } for (i = 0; i < nr_pages; i++) { unsigned long gfn; @@ -389,23 +396,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, else gfn = virt_to_gfn(vaddr); - err = gnttab_grant_foreign_access(dev->otherend_id, gfn, 0); - if (err < 0) { - xenbus_dev_fatal(dev, err, - "granting access to ring page"); - goto fail; - } - grefs[i] = err; + grefs[i] = gnttab_claim_grant_reference(&gref_head); + gnttab_grant_foreign_access_ref(grefs[i], dev->otherend_id, + gfn, 0); vaddr = vaddr + XEN_PAGE_SIZE; } return 0; - -fail: - for (j = 0; j < i; j++) - gnttab_end_foreign_access_ref(grefs[j], 0); - return err; } EXPORT_SYMBOL_GPL(xenbus_grant_ring); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 947f04789389..ebb2d109e8bb 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -602,6 +602,9 @@ enum { /* Indicate that we want the transaction kthread to commit right now. */ BTRFS_FS_COMMIT_TRANS, + /* Indicate we have half completed snapshot deletions pending. */ + BTRFS_FS_UNFINISHED_DROPS, + #if BITS_PER_LONG == 32 /* Indicate if we have error/warn message printed on 32bit systems */ BTRFS_FS_32BIT_ERROR, @@ -1106,8 +1109,15 @@ enum { BTRFS_ROOT_QGROUP_FLUSHING, /* We started the orphan cleanup for this root. */ BTRFS_ROOT_ORPHAN_CLEANUP, + /* This root has a drop operation that was started previously. */ + BTRFS_ROOT_UNFINISHED_DROP, }; +static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info) +{ + clear_and_wake_up_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags); +} + /* * Record swapped tree blocks of a subvolume tree for delayed subtree trace * code. For detail check comment in fs/btrfs/qgroup.c. diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 87a5addbedf6..48590a380762 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3813,6 +3813,10 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device set_bit(BTRFS_FS_OPEN, &fs_info->flags); + /* Kick the cleaner thread so it'll start deleting snapshots. */ + if (test_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags)) + wake_up_process(fs_info->cleaner_kthread); + clear_oneshot: btrfs_clear_oneshot_options(fs_info); return 0; @@ -4538,6 +4542,12 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info) */ kthread_park(fs_info->cleaner_kthread); + /* + * If we had UNFINISHED_DROPS we could still be processing them, so + * clear that bit and wake up relocation so it can stop. + */ + btrfs_wake_unfinished_drop(fs_info); + /* wait for the qgroup rescan worker to stop */ btrfs_qgroup_wait_for_completion(fs_info, false); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d89273c4b6b8..96427b1ecac3 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5622,6 +5622,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) int ret; int level; bool root_dropped = false; + bool unfinished_drop = false; btrfs_debug(fs_info, "Drop subvolume %llu", root->root_key.objectid); @@ -5664,6 +5665,8 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int update_ref, int for_reloc) * already dropped. */ set_bit(BTRFS_ROOT_DELETING, &root->state); + unfinished_drop = test_bit(BTRFS_ROOT_UNFINISHED_DROP, &root->state); + if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) { level = btrfs_header_level(root->node); path->nodes[level] = btrfs_lock_root_node(root); @@ -5839,6 +5842,13 @@ out_free: btrfs_free_path(path); out: /* + * We were an unfinished drop root, check to see if there are any + * pending, and if not clear and wake up any waiters. + */ + if (!err && unfinished_drop) + btrfs_maybe_wake_unfinished_drop(fs_info); + + /* * So if we need to stop dropping the snapshot for whatever reason we * need to make sure to add it back to the dead root list so that we * keep trying to do the work later. This also cleans up roots if we diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 409bad3928db..4c91060d103a 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -6841,14 +6841,24 @@ static void assert_eb_page_uptodate(const struct extent_buffer *eb, { struct btrfs_fs_info *fs_info = eb->fs_info; + /* + * If we are using the commit root we could potentially clear a page + * Uptodate while we're using the extent buffer that we've previously + * looked up. We don't want to complain in this case, as the page was + * valid before, we just didn't write it out. Instead we want to catch + * the case where we didn't actually read the block properly, which + * would have !PageUptodate && !PageError, as we clear PageError before + * reading. + */ if (fs_info->sectorsize < PAGE_SIZE) { - bool uptodate; + bool uptodate, error; uptodate = btrfs_subpage_test_uptodate(fs_info, page, eb->start, eb->len); - WARN_ON(!uptodate); + error = btrfs_subpage_test_error(fs_info, page, eb->start, eb->len); + WARN_ON(!uptodate && !error); } else { - WARN_ON(!PageUptodate(page)); + WARN_ON(!PageUptodate(page) && !PageError(page)); } } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 76e530f76e3c..5bbea5ec31fc 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7600,6 +7600,34 @@ static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start, } len = min(len, em->len - (start - em->start)); + + /* + * If we have a NOWAIT request and the range contains multiple extents + * (or a mix of extents and holes), then we return -EAGAIN to make the + * caller fallback to a context where it can do a blocking (without + * NOWAIT) request. This way we avoid doing partial IO and returning + * success to the caller, which is not optimal for writes and for reads + * it can result in unexpected behaviour for an application. + * + * When doing a read, because we use IOMAP_DIO_PARTIAL when calling + * iomap_dio_rw(), we can end up returning less data then what the caller + * asked for, resulting in an unexpected, and incorrect, short read. + * That is, the caller asked to read N bytes and we return less than that, + * which is wrong unless we are crossing EOF. This happens if we get a + * page fault error when trying to fault in pages for the buffer that is + * associated to the struct iov_iter passed to iomap_dio_rw(), and we + * have previously submitted bios for other extents in the range, in + * which case iomap_dio_rw() may return us EIOCBQUEUED if not all of + * those bios have completed by the time we get the page fault error, + * which we return back to our caller - we should only return EIOCBQUEUED + * after we have submitted bios for all the extents in the range. + */ + if ((flags & IOMAP_NOWAIT) && len < length) { + free_extent_map(em); + ret = -EAGAIN; + goto unlock_err; + } + if (write) { ret = btrfs_get_blocks_direct_write(&em, inode, dio_data, start, len); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index f12dc687350c..30d42ea655ce 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1197,13 +1197,20 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info) goto out; /* + * Unlock the qgroup_ioctl_lock mutex before waiting for the rescan worker to + * complete. Otherwise we can deadlock because btrfs_remove_qgroup() needs + * to lock that mutex while holding a transaction handle and the rescan + * worker needs to commit a transaction. + */ + mutex_unlock(&fs_info->qgroup_ioctl_lock); + + /* * Request qgroup rescan worker to complete and wait for it. This wait * must be done before transaction start for quota disable since it may * deadlock with transaction by the qgroup rescan worker. */ clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags); btrfs_qgroup_wait_for_completion(fs_info, false); - mutex_unlock(&fs_info->qgroup_ioctl_lock); /* * 1 For the root item diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index f5465197996d..9d8054839782 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -3960,6 +3960,19 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start) int rw = 0; int err = 0; + /* + * This only gets set if we had a half-deleted snapshot on mount. We + * cannot allow relocation to start while we're still trying to clean up + * these pending deletions. + */ + ret = wait_on_bit(&fs_info->flags, BTRFS_FS_UNFINISHED_DROPS, TASK_INTERRUPTIBLE); + if (ret) + return ret; + + /* We may have been woken up by close_ctree, so bail if we're closing. */ + if (btrfs_fs_closing(fs_info)) + return -EINTR; + bg = btrfs_lookup_block_group(fs_info, group_start); if (!bg) return -ENOENT; diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 3d68d2dcd83e..ca7426ef61c8 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -278,6 +278,21 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info) WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)); if (btrfs_root_refs(&root->root_item) == 0) { + struct btrfs_key drop_key; + + btrfs_disk_key_to_cpu(&drop_key, &root->root_item.drop_progress); + /* + * If we have a non-zero drop_progress then we know we + * made it partly through deleting this snapshot, and + * thus we need to make sure we block any balance from + * happening until this snapshot is completely dropped. + */ + if (drop_key.objectid != 0 || drop_key.type != 0 || + drop_key.offset != 0) { + set_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags); + set_bit(BTRFS_ROOT_UNFINISHED_DROP, &root->state); + } + set_bit(BTRFS_ROOT_DEAD_TREE, &root->state); btrfs_add_dead_root(root); } diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c index 29bd8c7a7706..ef7ae20d2b77 100644 --- a/fs/btrfs/subpage.c +++ b/fs/btrfs/subpage.c @@ -736,7 +736,7 @@ void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page, * Since we own the page lock, no one else could touch subpage::writers * and we are safe to do several atomic operations without spinlock. */ - if (atomic_read(&subpage->writers)) + if (atomic_read(&subpage->writers) == 0) /* No writers, locked by plain lock_page() */ return unlock_page(page); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index c3cfdfd8de9b..1f1c25db6f6b 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -854,7 +854,37 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root) static noinline void wait_for_commit(struct btrfs_transaction *commit, const enum btrfs_trans_state min_state) { - wait_event(commit->commit_wait, commit->state >= min_state); + struct btrfs_fs_info *fs_info = commit->fs_info; + u64 transid = commit->transid; + bool put = false; + + while (1) { + wait_event(commit->commit_wait, commit->state >= min_state); + if (put) + btrfs_put_transaction(commit); + + if (min_state < TRANS_STATE_COMPLETED) + break; + + /* + * A transaction isn't really completed until all of the + * previous transactions are completed, but with fsync we can + * end up with SUPER_COMMITTED transactions before a COMPLETED + * transaction. Wait for those. + */ + + spin_lock(&fs_info->trans_lock); + commit = list_first_entry_or_null(&fs_info->trans_list, + struct btrfs_transaction, + list); + if (!commit || commit->transid > transid) { + spin_unlock(&fs_info->trans_lock); + break; + } + refcount_inc(&commit->use_count); + put = true; + spin_unlock(&fs_info->trans_lock); + } } int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid) @@ -1320,6 +1350,32 @@ again: } /* + * If we had a pending drop we need to see if there are any others left in our + * dead roots list, and if not clear our bit and wake any waiters. + */ +void btrfs_maybe_wake_unfinished_drop(struct btrfs_fs_info *fs_info) +{ + /* + * We put the drop in progress roots at the front of the list, so if the + * first entry doesn't have UNFINISHED_DROP set we can wake everybody + * up. + */ + spin_lock(&fs_info->trans_lock); + if (!list_empty(&fs_info->dead_roots)) { + struct btrfs_root *root = list_first_entry(&fs_info->dead_roots, + struct btrfs_root, + root_list); + if (test_bit(BTRFS_ROOT_UNFINISHED_DROP, &root->state)) { + spin_unlock(&fs_info->trans_lock); + return; + } + } + spin_unlock(&fs_info->trans_lock); + + btrfs_wake_unfinished_drop(fs_info); +} + +/* * dead roots are old snapshots that need to be deleted. This allocates * a dirty root struct and adds it into the list of dead roots that need to * be deleted @@ -1331,7 +1387,12 @@ void btrfs_add_dead_root(struct btrfs_root *root) spin_lock(&fs_info->trans_lock); if (list_empty(&root->root_list)) { btrfs_grab_root(root); - list_add_tail(&root->root_list, &fs_info->dead_roots); + + /* We want to process the partially complete drops first. */ + if (test_bit(BTRFS_ROOT_UNFINISHED_DROP, &root->state)) + list_add(&root->root_list, &fs_info->dead_roots); + else + list_add_tail(&root->root_list, &fs_info->dead_roots); } spin_unlock(&fs_info->trans_lock); } diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 9402d8d94484..ba8a9826eb37 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -216,6 +216,7 @@ int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid); void btrfs_add_dead_root(struct btrfs_root *root); int btrfs_defrag_root(struct btrfs_root *root); +void btrfs_maybe_wake_unfinished_drop(struct btrfs_fs_info *fs_info); int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root); int btrfs_commit_transaction(struct btrfs_trans_handle *trans); void btrfs_commit_transaction_async(struct btrfs_trans_handle *trans); diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 9fd145f1c4bc..aae5697dde32 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -1682,6 +1682,7 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) */ for (slot = 0; slot < nritems; slot++) { u32 item_end_expected; + u64 item_data_end; int ret; btrfs_item_key_to_cpu(leaf, &key, slot); @@ -1696,6 +1697,8 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) return -EUCLEAN; } + item_data_end = (u64)btrfs_item_offset(leaf, slot) + + btrfs_item_size(leaf, slot); /* * Make sure the offset and ends are right, remember that the * item data starts at the end of the leaf and grows towards the @@ -1706,11 +1709,10 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) else item_end_expected = btrfs_item_offset(leaf, slot - 1); - if (unlikely(btrfs_item_data_end(leaf, slot) != item_end_expected)) { + if (unlikely(item_data_end != item_end_expected)) { generic_err(leaf, slot, - "unexpected item end, have %u expect %u", - btrfs_item_data_end(leaf, slot), - item_end_expected); + "unexpected item end, have %llu expect %u", + item_data_end, item_end_expected); return -EUCLEAN; } @@ -1719,12 +1721,10 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data) * just in case all the items are consistent to each other, but * all point outside of the leaf. */ - if (unlikely(btrfs_item_data_end(leaf, slot) > - BTRFS_LEAF_DATA_SIZE(fs_info))) { + if (unlikely(item_data_end > BTRFS_LEAF_DATA_SIZE(fs_info))) { generic_err(leaf, slot, - "slot end outside of leaf, have %u expect range [0, %u]", - btrfs_item_data_end(leaf, slot), - BTRFS_LEAF_DATA_SIZE(fs_info)); + "slot end outside of leaf, have %llu expect range [0, %u]", + item_data_end, BTRFS_LEAF_DATA_SIZE(fs_info)); return -EUCLEAN; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 3ee014c06b82..6bc8834ac8f7 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1362,6 +1362,15 @@ again: inode, name, namelen); kfree(name); iput(dir); + /* + * Whenever we need to check if a name exists or not, we + * check the subvolume tree. So after an unlink we must + * run delayed items, so that future checks for a name + * during log replay see that the name does not exists + * anymore. + */ + if (!ret) + ret = btrfs_run_delayed_items(trans); if (ret) goto out; goto again; @@ -1614,6 +1623,15 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, */ if (!ret && inode->i_nlink == 0) inc_nlink(inode); + /* + * Whenever we need to check if a name exists or + * not, we check the subvolume tree. So after an + * unlink we must run delayed items, so that future + * checks for a name during log replay see that the + * name does not exists anymore. + */ + if (!ret) + ret = btrfs_run_delayed_items(trans); } if (ret < 0) goto out; @@ -4635,7 +4653,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans, /* * Log all prealloc extents beyond the inode's i_size to make sure we do not - * lose them after doing a fast fsync and replaying the log. We scan the + * lose them after doing a full/fast fsync and replaying the log. We scan the * subvolume's root instead of iterating the inode's extent map tree because * otherwise we can log incorrect extent items based on extent map conversion. * That can happen due to the fact that extent maps are merged when they @@ -5414,6 +5432,7 @@ static int copy_inode_items_to_log(struct btrfs_trans_handle *trans, struct btrfs_log_ctx *ctx, bool *need_log_inode_item) { + const u64 i_size = i_size_read(&inode->vfs_inode); struct btrfs_root *root = inode->root; int ins_start_slot = 0; int ins_nr = 0; @@ -5434,13 +5453,21 @@ again: if (min_key->type > max_key->type) break; - if (min_key->type == BTRFS_INODE_ITEM_KEY) + if (min_key->type == BTRFS_INODE_ITEM_KEY) { *need_log_inode_item = false; - - if ((min_key->type == BTRFS_INODE_REF_KEY || - min_key->type == BTRFS_INODE_EXTREF_KEY) && - inode->generation == trans->transid && - !recursive_logging) { + } else if (min_key->type == BTRFS_EXTENT_DATA_KEY && + min_key->offset >= i_size) { + /* + * Extents at and beyond eof are logged with + * btrfs_log_prealloc_extents(). + * Only regular files have BTRFS_EXTENT_DATA_KEY keys, + * and no keys greater than that, so bail out. + */ + break; + } else if ((min_key->type == BTRFS_INODE_REF_KEY || + min_key->type == BTRFS_INODE_EXTREF_KEY) && + inode->generation == trans->transid && + !recursive_logging) { u64 other_ino = 0; u64 other_parent = 0; @@ -5471,10 +5498,8 @@ again: btrfs_release_path(path); goto next_key; } - } - - /* Skip xattrs, we log them later with btrfs_log_all_xattrs() */ - if (min_key->type == BTRFS_XATTR_ITEM_KEY) { + } else if (min_key->type == BTRFS_XATTR_ITEM_KEY) { + /* Skip xattrs, logged later with btrfs_log_all_xattrs() */ if (ins_nr == 0) goto next_slot; ret = copy_items(trans, inode, dst_path, path, @@ -5527,9 +5552,21 @@ next_key: break; } } - if (ins_nr) + if (ins_nr) { ret = copy_items(trans, inode, dst_path, path, ins_start_slot, ins_nr, inode_only, logged_isize); + if (ret) + return ret; + } + + if (inode_only == LOG_INODE_ALL && S_ISREG(inode->vfs_inode.i_mode)) { + /* + * Release the path because otherwise we might attempt to double + * lock the same leaf with btrfs_log_prealloc_extents() below. + */ + btrfs_release_path(path); + ret = btrfs_log_prealloc_extents(trans, inode, dst_path); + } return ret; } diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index 51c968cd00a6..ae93cee9d25d 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -254,7 +254,7 @@ static bool cachefiles_shorten_object(struct cachefiles_object *object, ret = cachefiles_inject_write_error(); if (ret == 0) ret = vfs_fallocate(file, FALLOC_FL_ZERO_RANGE, - new_size, dio_size); + new_size, dio_size - new_size); if (ret < 0) { trace_cachefiles_io_error(object, file_inode(file), ret, cachefiles_trace_fallocate_error); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index cd54a529460d..592730fd6e42 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -941,7 +941,17 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep, while (count) { if (cs->write && cs->pipebufs && page) { - return fuse_ref_page(cs, page, offset, count); + /* + * Can't control lifetime of pipe buffers, so always + * copy user pages. + */ + if (cs->req->args->user_pages) { + err = fuse_copy_fill(cs); + if (err) + return err; + } else { + return fuse_ref_page(cs, page, offset, count); + } } else if (!cs->len) { if (cs->move_pages && page && offset == 0 && count == PAGE_SIZE) { diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 829094451774..0fc150c1c50b 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1413,6 +1413,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii, (PAGE_SIZE - ret) & (PAGE_SIZE - 1); } + ap->args.user_pages = true; if (write) ap->args.in_pages = true; else diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index e8e59fbdefeb..eac4984cc753 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -256,6 +256,7 @@ struct fuse_args { bool nocreds:1; bool in_pages:1; bool out_pages:1; + bool user_pages:1; bool out_argvar:1; bool page_zeroing:1; bool page_replace:1; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index ee846ce371d8..9ee36aa73251 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -23,6 +23,7 @@ #include <linux/exportfs.h> #include <linux/posix_acl.h> #include <linux/pid_namespace.h> +#include <uapi/linux/magic.h> MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>"); MODULE_DESCRIPTION("Filesystem in Userspace"); @@ -50,8 +51,6 @@ MODULE_PARM_DESC(max_user_congthresh, "Global limit for the maximum congestion threshold an " "unprivileged user can set"); -#define FUSE_SUPER_MAGIC 0x65735546 - #define FUSE_DEFAULT_BLKSIZE 512 /** Maximum number of outstanding background requests */ diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c index fbc09dab1f85..df58966bc874 100644 --- a/fs/fuse/ioctl.c +++ b/fs/fuse/ioctl.c @@ -394,9 +394,12 @@ static int fuse_priv_ioctl(struct inode *inode, struct fuse_file *ff, args.out_args[1].value = ptr; err = fuse_simple_request(fm, &args); - if (!err && outarg.flags & FUSE_IOCTL_RETRY) - err = -EIO; - + if (!err) { + if (outarg.result < 0) + err = outarg.result; + else if (outarg.flags & FUSE_IOCTL_RETRY) + err = -EIO; + } return err; } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 6e97ed775074..f46060eb91b5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -309,7 +309,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) name = arch_vma_name(vma); if (!name) { - const char *anon_name; + struct anon_vma_name *anon_name; if (!mm) { name = "[vdso]"; @@ -327,10 +327,10 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) goto done; } - anon_name = vma_anon_name(vma); + anon_name = anon_vma_name(vma); if (anon_name) { seq_pad(m, ' '); - seq_printf(m, "[anon:%s]", anon_name); + seq_printf(m, "[anon:%s]", anon_name->name); } } @@ -1597,7 +1597,8 @@ static const struct mm_walk_ops pagemap_ops = { * Bits 5-54 swap offset if swapped * Bit 55 pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst) * Bit 56 page exclusively mapped - * Bits 57-60 zero + * Bit 57 pte is uffd-wp write-protected + * Bits 58-60 zero * Bit 61 page is file-page or shared-anon * Bit 62 page swapped * Bit 63 page present diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index e26b10132d47..8e03b3d3f5fa 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -878,7 +878,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX, vma_anon_name(vma)); + NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) vma = prev; else @@ -1438,7 +1438,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), ((struct vm_userfaultfd_ctx){ ctx }), - vma_anon_name(vma)); + anon_vma_name(vma)); if (prev) { vma = prev; goto next; @@ -1615,7 +1615,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX, vma_anon_name(vma)); + NULL_VM_UFFD_CTX, anon_vma_name(vma)); if (prev) { vma = prev; goto next; diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 63ccb5252190..220c8c60e021 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -92,6 +92,11 @@ ARM_SMCCC_SMC_32, \ 0, 0x7fff) +#define ARM_SMCCC_ARCH_WORKAROUND_3 \ + ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ + ARM_SMCCC_SMC_32, \ + 0, 0x3fff) + #define ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID \ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f19abc59b6cd..57cb6af3177a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1822,6 +1822,11 @@ struct bpf_core_ctx { int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, int relo_idx, void *insn); +static inline bool unprivileged_ebpf_enabled(void) +{ + return !sysctl_unprivileged_bpf_disabled; +} + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -2025,6 +2030,12 @@ bpf_jit_find_kfunc_model(const struct bpf_prog *prog, { return NULL; } + +static inline bool unprivileged_ebpf_enabled(void) +{ + return false; +} + #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 6150d11a607e..dca2b1355bb1 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -62,14 +62,6 @@ #define DMA_ATTR_PRIVILEGED (1UL << 9) /* - * This is a hint to the DMA-mapping subsystem that the device is expected - * to overwrite the entire mapped size, thus the caller does not require any - * of the previous buffer contents to be preserved. This allows - * bounce-buffering implementations to optimise DMA_FROM_DEVICE transfers. - */ -#define DMA_ATTR_OVERWRITE (1UL << 10) - -/* * A dma_addr_t can hold any valid DMA or bus address for the platform. It can * be given to a device to use as a DMA source or target. It is specific to a * given device and there may be a translation between the CPU physical address diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index bcf60ede6fcc..318fae4b3560 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3432,7 +3432,6 @@ enum { enum { MLX5_TIRC_PACKET_MERGE_MASK_IPV4_LRO = BIT(0), MLX5_TIRC_PACKET_MERGE_MASK_IPV6_LRO = BIT(1), - MLX5_TIRC_PACKET_MERGE_MASK_SHAMPO = BIT(2), }; enum { @@ -9899,8 +9898,8 @@ struct mlx5_ifc_bufferx_reg_bits { u8 reserved_at_0[0x6]; u8 lossy[0x1]; u8 epsb[0x1]; - u8 reserved_at_8[0xc]; - u8 size[0xc]; + u8 reserved_at_8[0x8]; + u8 size[0x10]; u8 xoff_threshold[0x10]; u8 xon_threshold[0x10]; diff --git a/include/linux/mm.h b/include/linux/mm.h index 213cc569b192..5744a3fc4716 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2626,7 +2626,7 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx, const char *); + struct mempolicy *, struct vm_userfaultfd_ctx, struct anon_vma_name *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); @@ -3372,11 +3372,12 @@ static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) #ifdef CONFIG_ANON_VMA_NAME int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, - unsigned long len_in, const char *name); + unsigned long len_in, + struct anon_vma_name *anon_name); #else static inline int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, - unsigned long len_in, const char *name) { + unsigned long len_in, struct anon_vma_name *anon_name) { return 0; } #endif diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index b725839dfe71..cf90b1fa2c60 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -140,50 +140,91 @@ static __always_inline void del_page_from_lru_list(struct page *page, #ifdef CONFIG_ANON_VMA_NAME /* - * mmap_lock should be read-locked when calling vma_anon_name() and while using - * the returned pointer. + * mmap_lock should be read-locked when calling anon_vma_name(). Caller should + * either keep holding the lock while using the returned pointer or it should + * raise anon_vma_name refcount before releasing the lock. */ -extern const char *vma_anon_name(struct vm_area_struct *vma); +extern struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma); +extern struct anon_vma_name *anon_vma_name_alloc(const char *name); +extern void anon_vma_name_free(struct kref *kref); -/* - * mmap_lock should be read-locked for orig_vma->vm_mm. - * mmap_lock should be write-locked for new_vma->vm_mm or new_vma should be - * isolated. - */ -extern void dup_vma_anon_name(struct vm_area_struct *orig_vma, - struct vm_area_struct *new_vma); +/* mmap_lock should be read-locked */ +static inline void anon_vma_name_get(struct anon_vma_name *anon_name) +{ + if (anon_name) + kref_get(&anon_name->kref); +} -/* - * mmap_lock should be write-locked or vma should have been isolated under - * write-locked mmap_lock protection. - */ -extern void free_vma_anon_name(struct vm_area_struct *vma); +static inline void anon_vma_name_put(struct anon_vma_name *anon_name) +{ + if (anon_name) + kref_put(&anon_name->kref, anon_vma_name_free); +} -/* mmap_lock should be read-locked */ -static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, - const char *name) +static inline +struct anon_vma_name *anon_vma_name_reuse(struct anon_vma_name *anon_name) +{ + /* Prevent anon_name refcount saturation early on */ + if (kref_read(&anon_name->kref) < REFCOUNT_MAX) { + anon_vma_name_get(anon_name); + return anon_name; + + } + return anon_vma_name_alloc(anon_name->name); +} + +static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) +{ + struct anon_vma_name *anon_name = anon_vma_name(orig_vma); + + if (anon_name) + new_vma->anon_name = anon_vma_name_reuse(anon_name); +} + +static inline void free_anon_vma_name(struct vm_area_struct *vma) { - const char *vma_name = vma_anon_name(vma); + /* + * Not using anon_vma_name because it generates a warning if mmap_lock + * is not held, which might be the case here. + */ + if (!vma->vm_file) + anon_vma_name_put(vma->anon_name); +} - /* either both NULL, or pointers to same string */ - if (vma_name == name) +static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, + struct anon_vma_name *anon_name2) +{ + if (anon_name1 == anon_name2) return true; - return name && vma_name && !strcmp(name, vma_name); + return anon_name1 && anon_name2 && + !strcmp(anon_name1->name, anon_name2->name); } + #else /* CONFIG_ANON_VMA_NAME */ -static inline const char *vma_anon_name(struct vm_area_struct *vma) +static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { return NULL; } -static inline void dup_vma_anon_name(struct vm_area_struct *orig_vma, - struct vm_area_struct *new_vma) {} -static inline void free_vma_anon_name(struct vm_area_struct *vma) {} -static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, - const char *name) + +static inline struct anon_vma_name *anon_vma_name_alloc(const char *name) +{ + return NULL; +} + +static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {} +static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {} +static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma, + struct vm_area_struct *new_vma) {} +static inline void free_anon_vma_name(struct vm_area_struct *vma) {} + +static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, + struct anon_vma_name *anon_name2) { return true; } + #endif /* CONFIG_ANON_VMA_NAME */ static inline void init_tlb_flush_pending(struct mm_struct *mm) diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5140e5feb486..0f549870da6a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -416,7 +416,10 @@ struct vm_area_struct { struct rb_node rb; unsigned long rb_subtree_last; } shared; - /* Serialized by mmap_sem. */ + /* + * Serialized by mmap_sem. Never use directly because it is + * valid only when vm_file is NULL. Use anon_vma_name instead. + */ struct anon_vma_name *anon_name; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 29a850a8d460..acd3cf69b61f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4672,6 +4672,8 @@ int skb_csum_hwoffload_help(struct sk_buff *skb, struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); +struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, + netdev_features_t features, __be16 type); struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, netdev_features_t features); diff --git a/include/linux/phy.h b/include/linux/phy.h index 20beeaa7443b..36ca2b5c2253 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -87,8 +87,8 @@ extern const int phy_10gbit_features_array[1]; * * @PHY_INTERFACE_MODE_NA: Not Applicable - don't touch * @PHY_INTERFACE_MODE_INTERNAL: No interface, MAC and PHY combined - * @PHY_INTERFACE_MODE_MII: Median-independent interface - * @PHY_INTERFACE_MODE_GMII: Gigabit median-independent interface + * @PHY_INTERFACE_MODE_MII: Media-independent interface + * @PHY_INTERFACE_MODE_GMII: Gigabit media-independent interface * @PHY_INTERFACE_MODE_SGMII: Serial gigabit media-independent interface * @PHY_INTERFACE_MODE_TBI: Ten Bit Interface * @PHY_INTERFACE_MODE_REVMII: Reverse Media Independent Interface diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 2de442ececae..721089bb4c84 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -401,18 +401,24 @@ static inline int vdpa_reset(struct vdpa_device *vdev) return ret; } -static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features, bool locked) +static inline int vdpa_set_features_unlocked(struct vdpa_device *vdev, u64 features) { const struct vdpa_config_ops *ops = vdev->config; int ret; - if (!locked) - mutex_lock(&vdev->cf_mutex); - vdev->features_valid = true; ret = ops->set_driver_features(vdev, features); - if (!locked) - mutex_unlock(&vdev->cf_mutex); + + return ret; +} + +static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features) +{ + int ret; + + mutex_lock(&vdev->cf_mutex); + ret = vdpa_set_features_unlocked(vdev, features); + mutex_unlock(&vdev->cf_mutex); return ret; } diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 72292a62cd90..5464f398912a 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -133,7 +133,6 @@ bool is_virtio_device(struct device *dev); void virtio_break_device(struct virtio_device *dev); void virtio_config_changed(struct virtio_device *dev); -int virtio_finalize_features(struct virtio_device *dev); #ifdef CONFIG_PM_SLEEP int virtio_device_freeze(struct virtio_device *dev); int virtio_device_restore(struct virtio_device *dev); diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 4d107ad31149..dafdc7f48c01 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -64,8 +64,9 @@ struct virtio_shm_region { * Returns the first 64 feature bits (all we currently need). * @finalize_features: confirm what device features we'll be using. * vdev: the virtio_device - * This gives the final feature bits for the device: it can change + * This sends the driver feature bits to the device: it can change * the dev->feature bits if it wants. + * Note: despite the name this can be called any number of times. * Returns 0 on success or error status * @bus_name: return the bus name associated with the device (optional) * vdev: the virtio_device diff --git a/include/net/esp.h b/include/net/esp.h index 9c5637d41d95..90cd02ff77ef 100644 --- a/include/net/esp.h +++ b/include/net/esp.h @@ -4,6 +4,8 @@ #include <linux/skbuff.h> +#define ESP_SKB_FRAG_MAXSIZE (PAGE_SIZE << SKB_FRAG_PAGE_ORDER) + struct ip_esp_hdr; static inline struct ip_esp_hdr *ip_esp_hdr(const struct sk_buff *skb) diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 225ec87d4f22..7989d9483ea7 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -278,7 +278,8 @@ #define KEY_PAUSECD 201 #define KEY_PROG3 202 #define KEY_PROG4 203 -#define KEY_DASHBOARD 204 /* AL Dashboard */ +#define KEY_ALL_APPLICATIONS 204 /* AC Desktop Show All Applications */ +#define KEY_DASHBOARD KEY_ALL_APPLICATIONS #define KEY_SUSPEND 205 #define KEY_CLOSE 206 /* AC Close */ #define KEY_PLAY 207 @@ -612,6 +613,7 @@ #define KEY_ASSISTANT 0x247 /* AL Context-aware desktop assistant */ #define KEY_KBD_LAYOUT_NEXT 0x248 /* AC Next Keyboard Layout Select */ #define KEY_EMOJI_PICKER 0x249 /* Show/hide emoji picker (HUTRR101) */ +#define KEY_DICTATE 0x24a /* Start or Stop Voice Dictation Session (HUTRR99) */ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 0425cd79af9a..f724129c0425 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -36,6 +36,7 @@ #define EFIVARFS_MAGIC 0xde5e81e4 #define HOSTFS_SUPER_MAGIC 0x00c0ffee #define OVERLAYFS_SUPER_MAGIC 0x794c7630 +#define FUSE_SUPER_MAGIC 0x65735546 #define MINIX_SUPER_MAGIC 0x137F /* minix v1 fs, 14 char names */ #define MINIX_SUPER_MAGIC2 0x138F /* minix v1 fs, 30 char names */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h index cb854df031ce..c9fea9389ebe 100644 --- a/include/xen/grant_table.h +++ b/include/xen/grant_table.h @@ -104,17 +104,32 @@ int gnttab_end_foreign_access_ref(grant_ref_t ref, int readonly); * access has been ended, free the given page too. Access will be ended * immediately iff the grant entry is not in use, otherwise it will happen * some time later. page may be 0, in which case no freeing will occur. + * Note that the granted page might still be accessed (read or write) by the + * other side after gnttab_end_foreign_access() returns, so even if page was + * specified as 0 it is not allowed to just reuse the page for other + * purposes immediately. gnttab_end_foreign_access() will take an additional + * reference to the granted page in this case, which is dropped only after + * the grant is no longer in use. + * This requires that multi page allocations for areas subject to + * gnttab_end_foreign_access() are done via alloc_pages_exact() (and freeing + * via free_pages_exact()) in order to avoid high order pages. */ void gnttab_end_foreign_access(grant_ref_t ref, int readonly, unsigned long page); +/* + * End access through the given grant reference, iff the grant entry is + * no longer in use. In case of success ending foreign access, the + * grant reference is deallocated. + * Return 1 if the grant entry was freed, 0 if it is still in use. + */ +int gnttab_try_end_foreign_access(grant_ref_t ref); + int gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn); unsigned long gnttab_end_foreign_transfer_ref(grant_ref_t ref); unsigned long gnttab_end_foreign_transfer(grant_ref_t ref); -int gnttab_query_foreign_access(grant_ref_t ref); - /* * operations on reserved batches of grant references */ diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config index e9ffb0cc1eec..07df6d93c4df 100644 --- a/kernel/configs/debug.config +++ b/kernel/configs/debug.config @@ -16,7 +16,7 @@ CONFIG_SYMBOLIC_ERRNAME=y # # Compile-time checks and compiler options # -CONFIG_DEBUG_INFO=y +CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y CONFIG_DEBUG_SECTION_MISMATCH=y CONFIG_FRAME_WARN=2048 CONFIG_SECTION_MISMATCH_WARN_ONLY=y diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index bfc56cb21705..6db1c475ec82 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -627,10 +627,14 @@ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, for (i = 0; i < nr_slots(alloc_size + offset); i++) mem->slots[index + i].orig_addr = slot_addr(orig_addr, i); tlb_addr = slot_addr(mem->start, index) + offset; - if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && - (!(attrs & DMA_ATTR_OVERWRITE) || dir == DMA_TO_DEVICE || - dir == DMA_BIDIRECTIONAL)) - swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE); + /* + * When dir == DMA_FROM_DEVICE we could omit the copy from the orig + * to the tlb buffer, if we knew for sure the device will + * overwirte the entire current content. But we don't. Thus + * unconditional bounce may prevent leaking swiotlb content (i.e. + * kernel memory) to user-space. + */ + swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE); return tlb_addr; } @@ -697,10 +701,13 @@ void swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr, void swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir) { - if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) - swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE); - else - BUG_ON(dir != DMA_FROM_DEVICE); + /* + * Unconditional bounce is necessary to avoid corruption on + * sync_*_for_cpu or dma_ummap_* when the device didn't overwrite + * the whole lengt of the bounce buffer. + */ + swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE); + BUG_ON(!valid_dma_direction(dir)); } void swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, diff --git a/kernel/fork.c b/kernel/fork.c index a024bf6254df..f1e89007f228 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -366,14 +366,14 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig) *new = data_race(*orig); INIT_LIST_HEAD(&new->anon_vma_chain); new->vm_next = new->vm_prev = NULL; - dup_vma_anon_name(orig, new); + dup_anon_vma_name(orig, new); } return new; } void vm_area_free(struct vm_area_struct *vma) { - free_vma_anon_name(vma); + free_anon_vma_name(vma); kmem_cache_free(vm_area_cachep, vma); } diff --git a/kernel/sys.c b/kernel/sys.c index 97dc9e5d6bf9..5b0e172c4d47 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -7,6 +7,7 @@ #include <linux/export.h> #include <linux/mm.h> +#include <linux/mm_inline.h> #include <linux/utsname.h> #include <linux/mman.h> #include <linux/reboot.h> @@ -2286,15 +2287,16 @@ static int prctl_set_vma(unsigned long opt, unsigned long addr, { struct mm_struct *mm = current->mm; const char __user *uname; - char *name, *pch; + struct anon_vma_name *anon_name = NULL; int error; switch (opt) { case PR_SET_VMA_ANON_NAME: uname = (const char __user *)arg; if (uname) { - name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); + char *name, *pch; + name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN); if (IS_ERR(name)) return PTR_ERR(name); @@ -2304,15 +2306,18 @@ static int prctl_set_vma(unsigned long opt, unsigned long addr, return -EINVAL; } } - } else { - /* Reset the name */ - name = NULL; + /* anon_vma has its own copy */ + anon_name = anon_vma_name_alloc(name); + kfree(name); + if (!anon_name) + return -ENOMEM; + } mmap_write_lock(mm); - error = madvise_set_anon_name(mm, addr, size, name); + error = madvise_set_anon_name(mm, addr, size, anon_name); mmap_write_unlock(mm); - kfree(name); + anon_vma_name_put(anon_name); break; default: error = -EINVAL; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5ae443b2882e..730ab56d9e92 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -180,6 +180,10 @@ static int bpf_stats_handler(struct ctl_table *table, int write, return ret; } +void __weak unpriv_ebpf_notify(int new_state) +{ +} + static int bpf_unpriv_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { @@ -197,6 +201,9 @@ static int bpf_unpriv_handler(struct ctl_table *table, int write, return -EPERM; *(int *)table->data = unpriv_enable; } + + unpriv_ebpf_notify(unpriv_enable); + return ret; } #endif /* CONFIG_BPF_SYSCALL && CONFIG_SYSCTL */ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index af68a67179b4..21dea90eaa93 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -310,10 +310,20 @@ record_it: local_irq_restore(flags); } -static void blk_trace_free(struct blk_trace *bt) +static void blk_trace_free(struct request_queue *q, struct blk_trace *bt) { relay_close(bt->rchan); - debugfs_remove(bt->dir); + + /* + * If 'bt->dir' is not set, then both 'dropped' and 'msg' are created + * under 'q->debugfs_dir', thus lookup and remove them. + */ + if (!bt->dir) { + debugfs_remove(debugfs_lookup("dropped", q->debugfs_dir)); + debugfs_remove(debugfs_lookup("msg", q->debugfs_dir)); + } else { + debugfs_remove(bt->dir); + } free_percpu(bt->sequence); free_percpu(bt->msg_data); kfree(bt); @@ -335,10 +345,10 @@ static void put_probe_ref(void) mutex_unlock(&blk_probe_mutex); } -static void blk_trace_cleanup(struct blk_trace *bt) +static void blk_trace_cleanup(struct request_queue *q, struct blk_trace *bt) { synchronize_rcu(); - blk_trace_free(bt); + blk_trace_free(q, bt); put_probe_ref(); } @@ -352,7 +362,7 @@ static int __blk_trace_remove(struct request_queue *q) return -EINVAL; if (bt->trace_state != Blktrace_running) - blk_trace_cleanup(bt); + blk_trace_cleanup(q, bt); return 0; } @@ -572,7 +582,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev, ret = 0; err: if (ret) - blk_trace_free(bt); + blk_trace_free(q, bt); return ret; } @@ -1616,7 +1626,7 @@ static int blk_trace_remove_queue(struct request_queue *q) put_probe_ref(); synchronize_rcu(); - blk_trace_free(bt); + blk_trace_free(q, bt); return 0; } @@ -1647,7 +1657,7 @@ static int blk_trace_setup_queue(struct request_queue *q, return 0; free_bt: - blk_trace_free(bt); + blk_trace_free(q, bt); return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 3050892d1812..eb44418574f9 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -235,7 +235,7 @@ static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static int __init set_trace_boot_options(char *str) { strlcpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); - return 0; + return 1; } __setup("trace_options=", set_trace_boot_options); @@ -246,7 +246,7 @@ static int __init set_trace_boot_clock(char *str) { strlcpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE); trace_boot_clock = trace_boot_clock_buf; - return 0; + return 1; } __setup("trace_clock=", set_trace_boot_clock); diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index ada87bfb5bb8..dc7f733b4cb3 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -2289,9 +2289,9 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file, /* * For backward compatibility, if field_name * was "cpu", then we treat this the same as - * common_cpu. + * common_cpu. This also works for "CPU". */ - if (strcmp(field_name, "cpu") == 0) { + if (field && field->filter_type == FILTER_CPU) { *flags |= HIST_FIELD_FL_CPU; } else { hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, @@ -4832,7 +4832,7 @@ static int create_tracing_map_fields(struct hist_trigger_data *hist_data) if (hist_field->flags & HIST_FIELD_FL_STACKTRACE) cmp_fn = tracing_map_cmp_none; - else if (!field) + else if (!field || hist_field->flags & HIST_FIELD_FL_CPU) cmp_fn = tracing_map_cmp_num(hist_field->size, hist_field->is_signed); else if (is_string_field(field)) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 508f14af4f2c..b62fd785b599 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -32,7 +32,7 @@ static int __init set_kprobe_boot_events(char *str) strlcpy(kprobe_boot_events_buf, str, COMMAND_LINE_SIZE); disable_tracing_selftest("running kprobe events"); - return 0; + return 1; } __setup("kprobe_event=", set_kprobe_boot_events); @@ -1729,11 +1729,11 @@ EXPORT_SYMBOL(fault_in_writeable); * @uaddr: start of address range * @size: length of address range * - * Faults in an address range using get_user_pages, i.e., without triggering - * hardware page faults. This is primarily useful when we already know that - * some or all of the pages in the address range aren't in memory. + * Faults in an address range for writing. This is primarily useful when we + * already know that some or all of the pages in the address range aren't in + * memory. * - * Other than fault_in_writeable(), this function is non-destructive. + * Unlike fault_in_writeable(), this function is non-destructive. * * Note that we don't pin or otherwise hold the pages referenced that we fault * in. There's no guarantee that they'll stay in memory for any duration of @@ -1744,46 +1744,27 @@ EXPORT_SYMBOL(fault_in_writeable); */ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) { - unsigned long start = (unsigned long)untagged_addr(uaddr); - unsigned long end, nstart, nend; + unsigned long start = (unsigned long)uaddr, end; struct mm_struct *mm = current->mm; - struct vm_area_struct *vma = NULL; - int locked = 0; + bool unlocked = false; - nstart = start & PAGE_MASK; + if (unlikely(size == 0)) + return 0; end = PAGE_ALIGN(start + size); - if (end < nstart) + if (end < start) end = 0; - for (; nstart != end; nstart = nend) { - unsigned long nr_pages; - long ret; - if (!locked) { - locked = 1; - mmap_read_lock(mm); - vma = find_vma(mm, nstart); - } else if (nstart >= vma->vm_end) - vma = vma->vm_next; - if (!vma || vma->vm_start >= end) - break; - nend = end ? min(end, vma->vm_end) : vma->vm_end; - if (vma->vm_flags & (VM_IO | VM_PFNMAP)) - continue; - if (nstart < vma->vm_start) - nstart = vma->vm_start; - nr_pages = (nend - nstart) / PAGE_SIZE; - ret = __get_user_pages_locked(mm, nstart, nr_pages, - NULL, NULL, &locked, - FOLL_TOUCH | FOLL_WRITE); - if (ret <= 0) + mmap_read_lock(mm); + do { + if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked)) break; - nend = nstart + ret * PAGE_SIZE; - } - if (locked) - mmap_read_unlock(mm); - if (nstart == end) - return 0; - return size - min_t(size_t, nstart - start, size); + start = (start + PAGE_SIZE) & PAGE_MASK; + } while (start != end); + mmap_read_unlock(mm); + + if (size > (unsigned long)uaddr - start) + return size - ((unsigned long)uaddr - start); + return 0; } EXPORT_SYMBOL(fault_in_safe_writeable); diff --git a/mm/madvise.c b/mm/madvise.c index 5604064df464..38d0f515d548 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -65,7 +65,7 @@ static int madvise_need_mmap_write(int behavior) } #ifdef CONFIG_ANON_VMA_NAME -static struct anon_vma_name *anon_vma_name_alloc(const char *name) +struct anon_vma_name *anon_vma_name_alloc(const char *name) { struct anon_vma_name *anon_name; size_t count; @@ -81,78 +81,48 @@ static struct anon_vma_name *anon_vma_name_alloc(const char *name) return anon_name; } -static void vma_anon_name_free(struct kref *kref) +void anon_vma_name_free(struct kref *kref) { struct anon_vma_name *anon_name = container_of(kref, struct anon_vma_name, kref); kfree(anon_name); } -static inline bool has_vma_anon_name(struct vm_area_struct *vma) +struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { - return !vma->vm_file && vma->anon_name; -} - -const char *vma_anon_name(struct vm_area_struct *vma) -{ - if (!has_vma_anon_name(vma)) - return NULL; - mmap_assert_locked(vma->vm_mm); - return vma->anon_name->name; -} - -void dup_vma_anon_name(struct vm_area_struct *orig_vma, - struct vm_area_struct *new_vma) -{ - if (!has_vma_anon_name(orig_vma)) - return; - - kref_get(&orig_vma->anon_name->kref); - new_vma->anon_name = orig_vma->anon_name; -} - -void free_vma_anon_name(struct vm_area_struct *vma) -{ - struct anon_vma_name *anon_name; - - if (!has_vma_anon_name(vma)) - return; + if (vma->vm_file) + return NULL; - anon_name = vma->anon_name; - vma->anon_name = NULL; - kref_put(&anon_name->kref, vma_anon_name_free); + return vma->anon_name; } /* mmap_lock should be write-locked */ -static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +static int replace_anon_vma_name(struct vm_area_struct *vma, + struct anon_vma_name *anon_name) { - const char *anon_name; + struct anon_vma_name *orig_name = anon_vma_name(vma); - if (!name) { - free_vma_anon_name(vma); + if (!anon_name) { + vma->anon_name = NULL; + anon_vma_name_put(orig_name); return 0; } - anon_name = vma_anon_name(vma); - if (anon_name) { - /* Same name, nothing to do here */ - if (!strcmp(name, anon_name)) - return 0; + if (anon_vma_name_eq(orig_name, anon_name)) + return 0; - free_vma_anon_name(vma); - } - vma->anon_name = anon_vma_name_alloc(name); - if (!vma->anon_name) - return -ENOMEM; + vma->anon_name = anon_vma_name_reuse(anon_name); + anon_vma_name_put(orig_name); return 0; } #else /* CONFIG_ANON_VMA_NAME */ -static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) +static int replace_anon_vma_name(struct vm_area_struct *vma, + struct anon_vma_name *anon_name) { - if (name) + if (anon_name) return -EINVAL; return 0; @@ -161,17 +131,19 @@ static int replace_vma_anon_name(struct vm_area_struct *vma, const char *name) /* * Update the vm_flags on region of a vma, splitting it or merging it as * necessary. Must be called with mmap_sem held for writing; + * Caller should ensure anon_name stability by raising its refcount even when + * anon_name belongs to a valid vma because this function might free that vma. */ static int madvise_update_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long new_flags, - const char *name) + struct anon_vma_name *anon_name) { struct mm_struct *mm = vma->vm_mm; int error; pgoff_t pgoff; - if (new_flags == vma->vm_flags && is_same_vma_anon_name(vma, name)) { + if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) { *prev = vma; return 0; } @@ -179,7 +151,7 @@ static int madvise_update_vma(struct vm_area_struct *vma, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, name); + vma->vm_userfaultfd_ctx, anon_name); if (*prev) { vma = *prev; goto success; @@ -209,7 +181,7 @@ success: */ vma->vm_flags = new_flags; if (!vma->vm_file) { - error = replace_vma_anon_name(vma, name); + error = replace_anon_vma_name(vma, anon_name); if (error) return error; } @@ -975,6 +947,7 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, unsigned long behavior) { int error; + struct anon_vma_name *anon_name; unsigned long new_flags = vma->vm_flags; switch (behavior) { @@ -1040,8 +1013,11 @@ static int madvise_vma_behavior(struct vm_area_struct *vma, break; } + anon_name = anon_vma_name(vma); + anon_vma_name_get(anon_name); error = madvise_update_vma(vma, prev, start, end, new_flags, - vma_anon_name(vma)); + anon_name); + anon_vma_name_put(anon_name); out: /* @@ -1225,7 +1201,7 @@ int madvise_walk_vmas(struct mm_struct *mm, unsigned long start, static int madvise_vma_anon_name(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, - unsigned long name) + unsigned long anon_name) { int error; @@ -1234,7 +1210,7 @@ static int madvise_vma_anon_name(struct vm_area_struct *vma, return -EBADF; error = madvise_update_vma(vma, prev, start, end, vma->vm_flags, - (const char *)name); + (struct anon_vma_name *)anon_name); /* * madvise() returns EAGAIN if kernel resources, such as @@ -1246,7 +1222,7 @@ static int madvise_vma_anon_name(struct vm_area_struct *vma, } int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, - unsigned long len_in, const char *name) + unsigned long len_in, struct anon_vma_name *anon_name) { unsigned long end; unsigned long len; @@ -1266,7 +1242,7 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, if (end == start) return 0; - return madvise_walk_vmas(mm, start, end, (unsigned long)name, + return madvise_walk_vmas(mm, start, end, (unsigned long)anon_name, madvise_vma_anon_name); } #endif /* CONFIG_ANON_VMA_NAME */ diff --git a/mm/memfd.c b/mm/memfd.c index 9f80f162791a..08f5f8304746 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -31,20 +31,28 @@ static void memfd_tag_pins(struct xa_state *xas) { struct page *page; - unsigned int tagged = 0; + int latency = 0; + int cache_count; lru_add_drain(); xas_lock_irq(xas); xas_for_each(xas, page, ULONG_MAX) { - if (xa_is_value(page)) - continue; - page = find_subpage(page, xas->xa_index); - if (page_count(page) - page_mapcount(page) > 1) + cache_count = 1; + if (!xa_is_value(page) && + PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + + if (!xa_is_value(page) && + page_count(page) - total_mapcount(page) != cache_count) xas_set_mark(xas, MEMFD_TAG_PINNED); + if (cache_count != 1) + xas_set(xas, page->index + cache_count); - if (++tagged % XA_CHECK_SCHED) + latency += cache_count; + if (latency < XA_CHECK_SCHED) continue; + latency = 0; xas_pause(xas); xas_unlock_irq(xas); @@ -73,7 +81,8 @@ static int memfd_wait_for_pins(struct address_space *mapping) error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { - unsigned int tagged = 0; + int latency = 0; + int cache_count; if (!xas_marked(&xas, MEMFD_TAG_PINNED)) break; @@ -87,10 +96,14 @@ static int memfd_wait_for_pins(struct address_space *mapping) xas_lock_irq(&xas); xas_for_each_marked(&xas, page, ULONG_MAX, MEMFD_TAG_PINNED) { bool clear = true; - if (xa_is_value(page)) - continue; - page = find_subpage(page, xas.xa_index); - if (page_count(page) - page_mapcount(page) != 1) { + + cache_count = 1; + if (!xa_is_value(page) && + PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + + if (!xa_is_value(page) && cache_count != + page_count(page) - total_mapcount(page)) { /* * On the last scan, we clean up all those tags * we inserted; but make a note that we still @@ -103,8 +116,11 @@ static int memfd_wait_for_pins(struct address_space *mapping) } if (clear) xas_clear_mark(&xas, MEMFD_TAG_PINNED); - if (++tagged % XA_CHECK_SCHED) + + latency += cache_count; + if (latency < XA_CHECK_SCHED) continue; + latency = 0; xas_pause(&xas); xas_unlock_irq(&xas); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 028e8dd82b44..69284d3b5e53 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -814,7 +814,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, new_pol, vma->vm_userfaultfd_ctx, - vma_anon_name(vma)); + anon_vma_name(vma)); if (prev) { vma = prev; next = vma->vm_next; diff --git a/mm/mlock.c b/mm/mlock.c index 8f584eddd305..25934e7db3e1 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -512,7 +512,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, vma_anon_name(vma)); + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (*prev) { vma = *prev; goto success; diff --git a/mm/mmap.c b/mm/mmap.c index d445c1b9d606..f61a15474dd6 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1031,7 +1031,7 @@ again: static inline int is_mergeable_vma(struct vm_area_struct *vma, struct file *file, unsigned long vm_flags, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - const char *anon_name) + struct anon_vma_name *anon_name) { /* * VM_SOFTDIRTY should not prevent from VMA merging, if we @@ -1049,7 +1049,7 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, return 0; if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx)) return 0; - if (!is_same_vma_anon_name(vma, anon_name)) + if (!anon_vma_name_eq(anon_vma_name(vma), anon_name)) return 0; return 1; } @@ -1084,7 +1084,7 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - const char *anon_name) + struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { @@ -1106,7 +1106,7 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - const char *anon_name) + struct anon_vma_name *anon_name) { if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) && is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) { @@ -1167,7 +1167,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, struct vm_userfaultfd_ctx vm_userfaultfd_ctx, - const char *anon_name) + struct anon_vma_name *anon_name) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; @@ -3256,7 +3256,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, return NULL; /* should never get here */ new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, vma_anon_name(vma)); + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (new_vma) { /* * Source vma may have been merged into new_vma diff --git a/mm/mprotect.c b/mm/mprotect.c index 5ca3fbcb1495..2887644fd150 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -464,7 +464,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *pprev = vma_merge(mm, *pprev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx, vma_anon_name(vma)); + vma->vm_userfaultfd_ctx, anon_vma_name(vma)); if (*pprev) { vma = *pprev; VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); diff --git a/mm/util.c b/mm/util.c index 7e43369064c8..d3102081add0 100644 --- a/mm/util.c +++ b/mm/util.c @@ -587,8 +587,10 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) return ret; /* Don't even allow crazy sizes */ - if (WARN_ON_ONCE(size > INT_MAX)) + if (unlikely(size > INT_MAX)) { + WARN_ON_ONCE(!(flags & __GFP_NOWARN)); return NULL; + } return __vmalloc_node(size, 1, flags, node, __builtin_return_address(0)); diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index eb9fb55280ef..01f8067994d6 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -281,9 +281,9 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) ref = priv->rings[i].intf->ref[j]; gnttab_end_foreign_access(ref, 0, 0); } - free_pages((unsigned long)priv->rings[i].data.in, - priv->rings[i].intf->ring_order - - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + free_pages_exact(priv->rings[i].data.in, + 1UL << (priv->rings[i].intf->ring_order + + XEN_PAGE_SHIFT)); } gnttab_end_foreign_access(priv->rings[i].ref, 0, 0); free_page((unsigned long)priv->rings[i].intf); @@ -322,8 +322,8 @@ static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev, if (ret < 0) goto out; ring->ref = ret; - bytes = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - order - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + bytes = alloc_pages_exact(1UL << (order + XEN_PAGE_SHIFT), + GFP_KERNEL | __GFP_ZERO); if (!bytes) { ret = -ENOMEM; goto out; @@ -354,9 +354,7 @@ out: if (bytes) { for (i--; i >= 0; i--) gnttab_end_foreign_access(ring->intf->ref[i], 0, 0); - free_pages((unsigned long)bytes, - ring->intf->ring_order - - (PAGE_SHIFT - XEN_PAGE_SHIFT)); + free_pages_exact(bytes, 1UL << (order + XEN_PAGE_SHIFT)); } gnttab_end_foreign_access(ring->ref, 0, 0); free_page((unsigned long)ring->intf); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index d53cbb4e2503..6bd097180772 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -87,6 +87,13 @@ again: ax25_for_each(s, &ax25_list) { if (s->ax25_dev == ax25_dev) { sk = s->sk; + if (!sk) { + spin_unlock_bh(&ax25_list_lock); + s->ax25_dev = NULL; + ax25_disconnect(s, ENETUNREACH); + spin_lock_bh(&ax25_list_lock); + goto again; + } sock_hold(sk); spin_unlock_bh(&ax25_list_lock); lock_sock(sk); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index e31d1150dc71..af7ea8a3317d 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -276,40 +276,37 @@ EXPORT_SYMBOL(__hci_cmd_sync_status); static void hci_cmd_sync_work(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, cmd_sync_work); - struct hci_cmd_sync_work_entry *entry; - hci_cmd_sync_work_func_t func; - hci_cmd_sync_work_destroy_t destroy; - void *data; bt_dev_dbg(hdev, ""); - mutex_lock(&hdev->cmd_sync_work_lock); - entry = list_first_entry(&hdev->cmd_sync_work_list, - struct hci_cmd_sync_work_entry, list); - if (entry) { - list_del(&entry->list); - func = entry->func; - data = entry->data; - destroy = entry->destroy; - kfree(entry); - } else { - func = NULL; - data = NULL; - destroy = NULL; - } - mutex_unlock(&hdev->cmd_sync_work_lock); + /* Dequeue all entries and run them */ + while (1) { + struct hci_cmd_sync_work_entry *entry; - if (func) { - int err; + mutex_lock(&hdev->cmd_sync_work_lock); + entry = list_first_entry_or_null(&hdev->cmd_sync_work_list, + struct hci_cmd_sync_work_entry, + list); + if (entry) + list_del(&entry->list); + mutex_unlock(&hdev->cmd_sync_work_lock); + + if (!entry) + break; - hci_req_sync_lock(hdev); + bt_dev_dbg(hdev, "entry %p", entry); - err = func(hdev, data); + if (entry->func) { + int err; - if (destroy) - destroy(hdev, data, err); + hci_req_sync_lock(hdev); + err = entry->func(hdev, entry->data); + if (entry->destroy) + entry->destroy(hdev, entry->data, err); + hci_req_sync_unlock(hdev); + } - hci_req_sync_unlock(hdev); + kfree(entry); } } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 68ce7dcff0e3..8101a6a31841 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -4545,9 +4545,9 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, } } -done: hci_dev_unlock(hdev); +done: if (status == MGMT_STATUS_SUCCESS) device_flags_changed(sk, hdev, &cp->addr.bdaddr, cp->addr.type, supported_flags, current_flags); diff --git a/net/core/gro.c b/net/core/gro.c index ee5e7e889d8b..78110edf5d4b 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -93,6 +93,31 @@ void dev_remove_offload(struct packet_offload *po) EXPORT_SYMBOL(dev_remove_offload); /** + * skb_eth_gso_segment - segmentation handler for ethernet protocols. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + * @type: Ethernet Protocol ID + */ +struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb, + netdev_features_t features, __be16 type) +{ + struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); + struct packet_offload *ptype; + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, &offload_base, list) { + if (ptype->type == type && ptype->callbacks.gso_segment) { + segs = ptype->callbacks.gso_segment(skb, features); + break; + } + } + rcu_read_unlock(); + + return segs; +} +EXPORT_SYMBOL(skb_eth_gso_segment); + +/** * skb_mac_gso_segment - mac layer segmentation handler. * @skb: buffer to segment * @features: features for the output path (see dev->features) diff --git a/net/core/xdp.c b/net/core/xdp.c index 361df312ee7f..7577adf19ef4 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -359,7 +359,8 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, if (IS_ERR(xdp_alloc)) return PTR_ERR(xdp_alloc); - trace_mem_connect(xdp_alloc, xdp_rxq); + if (trace_mem_connect_enabled() && xdp_alloc) + trace_mem_connect(xdp_alloc, xdp_rxq); return 0; } diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 39e696185720..bef1aaa7ec1c 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1049,7 +1049,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) static int dsa_tree_setup_master(struct dsa_switch_tree *dst) { struct dsa_port *dp; - int err; + int err = 0; rtnl_lock(); @@ -1061,7 +1061,7 @@ static int dsa_tree_setup_master(struct dsa_switch_tree *dst) err = dsa_master_setup(master, dp); if (err) - return err; + break; /* Replay master state event */ dsa_tree_master_admin_state_change(dst, master, admin_up); @@ -1072,7 +1072,7 @@ static int dsa_tree_setup_master(struct dsa_switch_tree *dst) rtnl_unlock(); - return 0; + return err; } static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index e1b1d080e908..70e6c87fbe3d 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -446,6 +446,7 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; + unsigned int allocsz; /* this is non-NULL only with TCP/UDP Encapsulation */ if (x->encap) { @@ -455,6 +456,10 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * return err; } + allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); + if (allocsz > ESP_SKB_FRAG_MAXSIZE) + goto cow; + if (!skb_cloned(skb)) { if (tailen <= skb_tailroom(skb)) { nfrags = 1; diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index d87f02a6e934..935026f4c807 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -110,8 +110,7 @@ static struct sk_buff *xfrm4_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - __skb_push(skb, skb->mac_len); - return skb_mac_gso_segment(skb, features); + return skb_eth_gso_segment(skb, features, htons(ETH_P_IP)); } static struct sk_buff *xfrm4_transport_gso_segment(struct xfrm_state *x, @@ -160,6 +159,9 @@ static struct sk_buff *xfrm4_beet_gso_segment(struct xfrm_state *x, skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4; } + if (proto == IPPROTO_IPV6) + skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4; + __skb_pull(skb, skb_transport_offset(skb)); ops = rcu_dereference(inet_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 7591160edce1..b0ffbcd5432d 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -482,6 +482,7 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info struct page *page; struct sk_buff *trailer; int tailen = esp->tailen; + unsigned int allocsz; if (x->encap) { int err = esp6_output_encap(x, skb, esp); @@ -490,6 +491,10 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info return err; } + allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES); + if (allocsz > ESP_SKB_FRAG_MAXSIZE) + goto cow; + if (!skb_cloned(skb)) { if (tailen <= skb_tailroom(skb)) { nfrags = 1; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index ba5e81cd569c..3a293838a91d 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -145,8 +145,7 @@ static struct sk_buff *xfrm6_tunnel_gso_segment(struct xfrm_state *x, struct sk_buff *skb, netdev_features_t features) { - __skb_push(skb, skb->mac_len); - return skb_mac_gso_segment(skb, features); + return skb_eth_gso_segment(skb, features, htons(ETH_P_IPV6)); } static struct sk_buff *xfrm6_transport_gso_segment(struct xfrm_state *x, @@ -199,6 +198,9 @@ static struct sk_buff *xfrm6_beet_gso_segment(struct xfrm_state *x, ipv6_skip_exthdr(skb, 0, &proto, &frag); } + if (proto == IPPROTO_IPIP) + skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6; + __skb_pull(skb, skb_transport_offset(skb)); ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index d0d280077721..ad07904642ca 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -45,6 +45,19 @@ static int __xfrm6_output_finish(struct net *net, struct sock *sk, struct sk_buf return xfrm_output(sk, skb); } +static int xfrm6_noneed_fragment(struct sk_buff *skb) +{ + struct frag_hdr *fh; + u8 prevhdr = ipv6_hdr(skb)->nexthdr; + + if (prevhdr != NEXTHDR_FRAGMENT) + return 0; + fh = (struct frag_hdr *)(skb->data + sizeof(struct ipv6hdr)); + if (fh->nexthdr == NEXTHDR_ESP || fh->nexthdr == NEXTHDR_AUTH) + return 1; + return 0; +} + static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -73,6 +86,9 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) xfrm6_local_rxpmtu(skb, mtu); kfree_skb(skb); return -EMSGSIZE; + } else if (toobig && xfrm6_noneed_fragment(skb)) { + skb->ignore_df = 1; + goto skip_frag; } else if (!skb->ignore_df && toobig && skb->sk) { xfrm_local_error(skb, mtu); kfree_skb(skb); diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 034e2c74497d..d9c6d8f30f09 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -61,10 +61,6 @@ static void inet_diag_msg_sctpasoc_fill(struct inet_diag_msg *r, r->idiag_timer = SCTP_EVENT_TIMEOUT_T3_RTX; r->idiag_retrans = asoc->rtx_data_chunks; r->idiag_expires = jiffies_to_msecs(t3_rtx->expires - jiffies); - } else { - r->idiag_timer = 0; - r->idiag_retrans = 0; - r->idiag_expires = 0; } } @@ -144,13 +140,14 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, r = nlmsg_data(nlh); BUG_ON(!sk_fullsock(sk)); + r->idiag_timer = 0; + r->idiag_retrans = 0; + r->idiag_expires = 0; if (asoc) { inet_diag_msg_sctpasoc_fill(r, sk, asoc); } else { inet_diag_msg_common_fill(r, sk); r->idiag_state = sk->sk_state; - r->idiag_timer = 0; - r->idiag_retrans = 0; } if (inet_diag_msg_attrs_fill(sk, skb, r, ext, user_ns, net_admin)) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 9dfe2bdf1482..6d39ca05f249 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -352,16 +352,18 @@ static int tipc_enable_bearer(struct net *net, const char *name, goto rejected; } - test_and_set_bit_lock(0, &b->up); - rcu_assign_pointer(tn->bearer_list[bearer_id], b); - if (skb) - tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr); - + /* Create monitoring data before accepting activate messages */ if (tipc_mon_create(net, bearer_id)) { bearer_disable(net, b); + kfree_skb(skb); return -ENOMEM; } + test_and_set_bit_lock(0, &b->up); + rcu_assign_pointer(tn->bearer_list[bearer_id], b); + if (skb) + tipc_bearer_xmit_skb(net, bearer_id, skb, &b->bcast_addr); + pr_info("Enabled bearer <%s>, priority %u\n", name, prio); return res; diff --git a/net/tipc/link.c b/net/tipc/link.c index 1e14d7f8f28f..e260c0d557f5 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2286,6 +2286,11 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, break; case STATE_MSG: + /* Validate Gap ACK blocks, drop if invalid */ + glen = tipc_get_gap_ack_blks(&ga, l, hdr, true); + if (glen > dlen) + break; + l->rcv_nxt_state = msg_seqno(hdr) + 1; /* Update own tolerance if peer indicates a non-zero value */ @@ -2311,10 +2316,6 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, break; } - /* Receive Gap ACK blocks from peer if any */ - glen = tipc_get_gap_ack_blks(&ga, l, hdr, true); - if(glen > dlen) - break; tipc_mon_rcv(l->net, data + glen, dlen - glen, l->addr, &l->mon_state, l->bearer_id); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index daec1fb08bf5..5113fa0fbcee 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -304,7 +304,10 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + if (skb->len > 1280) + icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); + else + goto xmit; } else { if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) goto xmit; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index a4fb596e87af..72b2f173aac8 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -630,13 +630,8 @@ static struct xfrm_state *xfrm_state_construct(struct net *net, xfrm_smark_init(attrs, &x->props.smark); - if (attrs[XFRMA_IF_ID]) { + if (attrs[XFRMA_IF_ID]) x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); - if (!x->if_id) { - err = -EINVAL; - goto error; - } - } err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]); if (err) @@ -1432,13 +1427,8 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, mark = xfrm_mark_get(attrs, &m); - if (attrs[XFRMA_IF_ID]) { + if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); - if (!if_id) { - err = -EINVAL; - goto out_noput; - } - } if (p->info.seq) { x = xfrm_find_acq_byseq(net, mark, p->info.seq); @@ -1751,13 +1741,8 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_us xfrm_mark_get(attrs, &xp->mark); - if (attrs[XFRMA_IF_ID]) { + if (attrs[XFRMA_IF_ID]) xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]); - if (!xp->if_id) { - err = -EINVAL; - goto error; - } - } return xp; error: diff --git a/sound/soc/codecs/cs4265.c b/sound/soc/codecs/cs4265.c index 4aaee1873a11..4415fb364d4d 100644 --- a/sound/soc/codecs/cs4265.c +++ b/sound/soc/codecs/cs4265.c @@ -150,7 +150,6 @@ static const struct snd_kcontrol_new cs4265_snd_controls[] = { SOC_SINGLE("E to F Buffer Disable Switch", CS4265_SPDIF_CTL1, 6, 1, 0), SOC_ENUM("C Data Access", cam_mode_enum), - SOC_SINGLE("SPDIF Switch", CS4265_SPDIF_CTL2, 5, 1, 1), SOC_SINGLE("Validity Bit Control Switch", CS4265_SPDIF_CTL2, 3, 1, 0), SOC_ENUM("SPDIF Mono/Stereo", spdif_mono_stereo_enum), @@ -186,7 +185,7 @@ static const struct snd_soc_dapm_widget cs4265_dapm_widgets[] = { SND_SOC_DAPM_SWITCH("Loopback", SND_SOC_NOPM, 0, 0, &loopback_ctl), - SND_SOC_DAPM_SWITCH("SPDIF", SND_SOC_NOPM, 0, 0, + SND_SOC_DAPM_SWITCH("SPDIF", CS4265_SPDIF_CTL2, 5, 1, &spdif_switch), SND_SOC_DAPM_SWITCH("DAC", CS4265_PWRCTL, 1, 1, &dac_switch), diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c index 03ea9591fb16..a0ca58ba1627 100644 --- a/sound/soc/soc-ops.c +++ b/sound/soc/soc-ops.c @@ -319,7 +319,7 @@ int snd_soc_put_volsw(struct snd_kcontrol *kcontrol, if (ucontrol->value.integer.value[0] < 0) return -EINVAL; val = ucontrol->value.integer.value[0]; - if (mc->platform_max && val > mc->platform_max) + if (mc->platform_max && ((int)val + min) > mc->platform_max) return -EINVAL; if (val > max - min) return -EINVAL; @@ -332,7 +332,7 @@ int snd_soc_put_volsw(struct snd_kcontrol *kcontrol, if (ucontrol->value.integer.value[1] < 0) return -EINVAL; val2 = ucontrol->value.integer.value[1]; - if (mc->platform_max && val2 > mc->platform_max) + if (mc->platform_max && ((int)val2 + min) > mc->platform_max) return -EINVAL; if (val2 > max - min) return -EINVAL; diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c index 1c94eaff1931..4a3ff6468aa7 100644 --- a/sound/x86/intel_hdmi_audio.c +++ b/sound/x86/intel_hdmi_audio.c @@ -1261,7 +1261,7 @@ static int had_pcm_mmap(struct snd_pcm_substream *substream, { vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); return remap_pfn_range(vma, vma->vm_start, - substream->dma_buffer.addr >> PAGE_SHIFT, + substream->runtime->dma_addr >> PAGE_SHIFT, vma->vm_end - vma->vm_start, vma->vm_page_prot); } diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 6db4e2932b3d..ab4e53715d8a 100644 --- a/tools/arch/x86/include/asm/cpufeatures.h +++ b/tools/arch/x86/include/asm/cpufeatures.h @@ -204,7 +204,7 @@ /* FREE! ( 7*32+10) */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_RETPOLINE ( 7*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ -#define X86_FEATURE_RETPOLINE_AMD ( 7*32+13) /* "" AMD Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE ( 7*32+13) /* "" Use LFENCEs for Spectre variant 2 */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 543ad7513a8e..694732e4b344 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -374,6 +374,16 @@ run_cmd() { return $rc } +run_cmd_bg() { + cmd="$*" + + if [ "$VERBOSE" = "1" ]; then + printf " COMMAND: %s &\n" "${cmd}" + fi + + $cmd 2>&1 & +} + # Find the auto-generated name for this namespace nsname() { eval echo \$NS_$1 @@ -670,10 +680,10 @@ setup_nettest_xfrm() { [ ${1} -eq 6 ] && proto="-6" || proto="" port=${2} - run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + run_cmd_bg "${ns_a}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5 nettest_pids="${nettest_pids} $!" - run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 & + run_cmd_bg "${ns_b}" nettest "${proto}" -q -D -s -x -p "${port}" -t 5 nettest_pids="${nettest_pids} $!" } @@ -865,7 +875,6 @@ setup_ovs_bridge() { setup() { [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip - cleanup for arg do eval setup_${arg} || { echo " ${arg} not supported"; return 1; } done @@ -876,7 +885,7 @@ trace() { for arg do [ "${ns_cmd}" = "" ] && ns_cmd="${arg}" && continue - ${ns_cmd} tcpdump -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null & + ${ns_cmd} tcpdump --immediate-mode -s 0 -i "${arg}" -w "${name}_${arg}.pcap" 2> /dev/null & tcpdump_pids="${tcpdump_pids} $!" ns_cmd= done @@ -1836,6 +1845,10 @@ run_test() { unset IFS + # Since cleanup() relies on variables modified by this subshell, it + # has to run in this context. + trap cleanup EXIT + if [ "$VERBOSE" = "1" ]; then printf "\n##########################################################################\n\n" fi diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c index 2a7c33631a29..1d689084a54b 100644 --- a/tools/testing/selftests/vm/hugepage-mremap.c +++ b/tools/testing/selftests/vm/hugepage-mremap.c @@ -3,9 +3,10 @@ * hugepage-mremap: * * Example of remapping huge page memory in a user application using the - * mremap system call. Code assumes a hugetlbfs filesystem is mounted - * at './huge'. The amount of memory used by this test is decided by a command - * line argument in MBs. If missing, the default amount is 10MB. + * mremap system call. The path to a file in a hugetlbfs filesystem must + * be passed as the last argument to this test. The amount of memory used + * by this test in MBs can optionally be passed as an argument. If no memory + * amount is passed, the default amount is 10MB. * * To make sure the test triggers pmd sharing and goes through the 'unshare' * path in the mremap code use 1GB (1024) or more. @@ -25,7 +26,6 @@ #define DEFAULT_LENGTH_MB 10UL #define MB_TO_BYTES(x) (x * 1024 * 1024) -#define FILE_NAME "huge/hugepagefile" #define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC) #define FLAGS (MAP_SHARED | MAP_ANONYMOUS) @@ -107,17 +107,26 @@ static void register_region_with_uffd(char *addr, size_t len) int main(int argc, char *argv[]) { + size_t length; + + if (argc != 2 && argc != 3) { + printf("Usage: %s [length_in_MB] <hugetlb_file>\n", argv[0]); + exit(1); + } + /* Read memory length as the first arg if valid, otherwise fallback to - * the default length. Any additional args are ignored. + * the default length. */ - size_t length = argc > 1 ? (size_t)atoi(argv[1]) : 0UL; + if (argc == 3) + length = argc > 2 ? (size_t)atoi(argv[1]) : 0UL; length = length > 0 ? length : DEFAULT_LENGTH_MB; length = MB_TO_BYTES(length); int ret = 0; - int fd = open(FILE_NAME, O_CREAT | O_RDWR, 0755); + /* last arg is the hugetlb file name */ + int fd = open(argv[argc-1], O_CREAT | O_RDWR, 0755); if (fd < 0) { perror("Open failed"); @@ -169,5 +178,8 @@ int main(int argc, char *argv[]) munmap(addr, length); + close(fd); + unlink(argv[argc-1]); + return ret; } diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh index 75d401741394..71d2dc198fc1 100755 --- a/tools/testing/selftests/vm/run_vmtests.sh +++ b/tools/testing/selftests/vm/run_vmtests.sh @@ -111,13 +111,14 @@ fi echo "-----------------------" echo "running hugepage-mremap" echo "-----------------------" -./hugepage-mremap 256 +./hugepage-mremap $mnt/huge_mremap if [ $? -ne 0 ]; then echo "[FAIL]" exitcode=1 else echo "[PASS]" fi +rm -f $mnt/huge_mremap echo "NOTE: The above hugetlb tests provide minimal coverage. Use" echo " https://github.com/libhugetlbfs/libhugetlbfs.git for" diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c index 2f49c9af1b58..3fc1d2ee2948 100644 --- a/tools/testing/selftests/vm/userfaultfd.c +++ b/tools/testing/selftests/vm/userfaultfd.c @@ -46,6 +46,7 @@ #include <signal.h> #include <poll.h> #include <string.h> +#include <linux/mman.h> #include <sys/mman.h> #include <sys/syscall.h> #include <sys/ioctl.h> diff --git a/tools/virtio/linux/mm_types.h b/tools/virtio/linux/mm_types.h new file mode 100644 index 000000000000..356ba4d496f6 --- /dev/null +++ b/tools/virtio/linux/mm_types.h @@ -0,0 +1,3 @@ +struct folio { + struct page page; +}; diff --git a/tools/virtio/virtio_test.c b/tools/virtio/virtio_test.c index cb3f29c09aff..23f142af544a 100644 --- a/tools/virtio/virtio_test.c +++ b/tools/virtio/virtio_test.c @@ -130,6 +130,7 @@ static void vdev_info_init(struct vdev_info* dev, unsigned long long features) memset(dev, 0, sizeof *dev); dev->vdev.features = features; INIT_LIST_HEAD(&dev->vdev.vqs); + spin_lock_init(&dev->vdev.vqs_list_lock); dev->buf_size = 1024; dev->buf = malloc(dev->buf_size); assert(dev->buf); |