diff options
344 files changed, 6201 insertions, 3509 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/net/can/renesas,rcar-canfd.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml index 546c6e6d2fb0..91a3554ca950 100644 --- a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml +++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml @@ -35,6 +35,8 @@ properties: - renesas,r9a07g044-canfd # RZ/G2{L,LC} - const: renesas,rzg2l-canfd # RZ/G2L family + - const: renesas,r8a779a0-canfd # R-Car V3U + reg: maxItems: 1 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/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 2572eecc3e86..b0024aa7b051 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -878,6 +878,29 @@ tcp_min_tso_segs - INTEGER Default: 2 +tcp_tso_rtt_log - INTEGER + Adjustment of TSO packet sizes based on min_rtt + + Starting from linux-5.18, TCP autosizing can be tweaked + for flows having small RTT. + + Old autosizing was splitting the pacing budget to send 1024 TSO + per second. + + tso_packet_size = sk->sk_pacing_rate / 1024; + + With the new mechanism, we increase this TSO sizing using: + + distance = min_rtt_usec / (2^tcp_tso_rtt_log) + tso_packet_size += gso_max_size >> distance; + + This means that flows between very close hosts can use bigger + TSO packets, reducing their cpu costs. + + If you want to use the old autosizing, set this sysctl to 0. + + Default: 9 (2^9 = 512 usec) + tcp_pacing_ss_ratio - INTEGER sk->sk_pacing_rate is set by TCP stack using a ratio applied to current rate. (current_rate = cwnd * mss / srtt) 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/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c index 0b61df52332a..290ea8ac3838 100644 --- a/drivers/infiniband/hw/mlx5/cong.c +++ b/drivers/infiniband/hw/mlx5/cong.c @@ -433,8 +433,7 @@ void mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev, u32 port_num) dev->port[port_num].dbg_cc_params = dbg_cc_params; - dbg_cc_params->root = debugfs_create_dir("cc_params", - mdev->priv.dbg_root); + dbg_cc_params->root = debugfs_create_dir("cc_params", mlx5_debugfs_get_dev_root(mdev)); for (i = 0; i < MLX5_IB_DBG_CC_MAX; i++) { dbg_cc_params->params[i].offset = i; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 85f526c861e9..32a0ea820573 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4178,7 +4178,7 @@ static int mlx5_ib_stage_delay_drop_init(struct mlx5_ib_dev *dev) if (!mlx5_debugfs_root) return 0; - root = debugfs_create_dir("delay_drop", dev->mdev->priv.dbg_root); + root = debugfs_create_dir("delay_drop", mlx5_debugfs_get_dev_root(dev->mdev)); dev->delay_drop.dir_debugfs = root; debugfs_create_atomic_t("num_timeout_events", 0400, root, diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index 06e4b8cea6bd..32cb7068f0ca 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -696,7 +696,7 @@ static void mlx5_mr_cache_debugfs_init(struct mlx5_ib_dev *dev) if (!mlx5_debugfs_root || dev->is_rep) return; - cache->root = debugfs_create_dir("mr_cache", dev->mdev->priv.dbg_root); + cache->root = debugfs_create_dir("mr_cache", mlx5_debugfs_get_dev_root(dev->mdev)); for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) { ent = &cache->ent[i]; 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/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index acd74725831f..1e121e04208c 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -44,6 +44,7 @@ enum rcanfd_chip_id { RENESAS_RCAR_GEN3 = 0, RENESAS_RZG2L, + RENESAS_R8A779A0, }; /* Global register bits */ @@ -79,6 +80,7 @@ enum rcanfd_chip_id { #define RCANFD_GSTS_GNOPM (BIT(0) | BIT(1) | BIT(2) | BIT(3)) /* RSCFDnCFDGERFL / RSCFDnGERFL */ +#define RCANFD_GERFL_EEF0_7 GENMASK(23, 16) #define RCANFD_GERFL_EEF1 BIT(17) #define RCANFD_GERFL_EEF0 BIT(16) #define RCANFD_GERFL_CMPOF BIT(3) /* CAN FD only */ @@ -86,20 +88,26 @@ enum rcanfd_chip_id { #define RCANFD_GERFL_MES BIT(1) #define RCANFD_GERFL_DEF BIT(0) -#define RCANFD_GERFL_ERR(gpriv, x) ((x) & (RCANFD_GERFL_EEF1 |\ - RCANFD_GERFL_EEF0 | RCANFD_GERFL_MES |\ - (gpriv->fdmode ?\ - RCANFD_GERFL_CMPOF : 0))) +#define RCANFD_GERFL_ERR(gpriv, x) \ + ((x) & (reg_v3u(gpriv, RCANFD_GERFL_EEF0_7, \ + RCANFD_GERFL_EEF0 | RCANFD_GERFL_EEF1) | \ + RCANFD_GERFL_MES | \ + ((gpriv)->fdmode ? RCANFD_GERFL_CMPOF : 0))) /* AFL Rx rules registers */ /* RSCFDnCFDGAFLCFG0 / RSCFDnGAFLCFG0 */ -#define RCANFD_GAFLCFG_SETRNC(n, x) (((x) & 0xff) << (24 - n * 8)) -#define RCANFD_GAFLCFG_GETRNC(n, x) (((x) >> (24 - n * 8)) & 0xff) +#define RCANFD_GAFLCFG_SETRNC(gpriv, n, x) \ + (((x) & reg_v3u(gpriv, 0x1ff, 0xff)) << \ + (reg_v3u(gpriv, 16, 24) - (n) * reg_v3u(gpriv, 16, 8))) + +#define RCANFD_GAFLCFG_GETRNC(gpriv, n, x) \ + (((x) >> (reg_v3u(gpriv, 16, 24) - (n) * reg_v3u(gpriv, 16, 8))) & \ + reg_v3u(gpriv, 0x1ff, 0xff)) /* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */ #define RCANFD_GAFLECTR_AFLDAE BIT(8) -#define RCANFD_GAFLECTR_AFLPN(x) ((x) & 0x1f) +#define RCANFD_GAFLECTR_AFLPN(gpriv, x) ((x) & reg_v3u(gpriv, 0x7f, 0x1f)) /* RSCFDnCFDGAFLIDj / RSCFDnGAFLIDj */ #define RCANFD_GAFLID_GAFLLB BIT(29) @@ -116,9 +124,15 @@ enum rcanfd_chip_id { #define RCANFD_CFG_BRP(x) (((x) & 0x3ff) << 0) /* RSCFDnCFDCmNCFG - CAN FD only */ -#define RCANFD_NCFG_NTSEG2(x) (((x) & 0x1f) << 24) -#define RCANFD_NCFG_NTSEG1(x) (((x) & 0x7f) << 16) -#define RCANFD_NCFG_NSJW(x) (((x) & 0x1f) << 11) +#define RCANFD_NCFG_NTSEG2(gpriv, x) \ + (((x) & reg_v3u(gpriv, 0x7f, 0x1f)) << reg_v3u(gpriv, 25, 24)) + +#define RCANFD_NCFG_NTSEG1(gpriv, x) \ + (((x) & reg_v3u(gpriv, 0xff, 0x7f)) << reg_v3u(gpriv, 17, 16)) + +#define RCANFD_NCFG_NSJW(gpriv, x) \ + (((x) & reg_v3u(gpriv, 0x7f, 0x1f)) << reg_v3u(gpriv, 10, 11)) + #define RCANFD_NCFG_NBRP(x) (((x) & 0x3ff) << 0) /* RSCFDnCFDCmCTR / RSCFDnCmCTR */ @@ -180,11 +194,18 @@ enum rcanfd_chip_id { /* RSCFDnCFDCmDCFG */ #define RCANFD_DCFG_DSJW(x) (((x) & 0x7) << 24) -#define RCANFD_DCFG_DTSEG2(x) (((x) & 0x7) << 20) -#define RCANFD_DCFG_DTSEG1(x) (((x) & 0xf) << 16) + +#define RCANFD_DCFG_DTSEG2(gpriv, x) \ + (((x) & reg_v3u(gpriv, 0x0f, 0x7)) << reg_v3u(gpriv, 16, 20)) + +#define RCANFD_DCFG_DTSEG1(gpriv, x) \ + (((x) & reg_v3u(gpriv, 0x1f, 0xf)) << reg_v3u(gpriv, 8, 16)) + #define RCANFD_DCFG_DBRP(x) (((x) & 0xff) << 0) /* RSCFDnCFDCmFDCFG */ +#define RCANFD_FDCFG_CLOE BIT(30) +#define RCANFD_FDCFG_FDOE BIT(28) #define RCANFD_FDCFG_TDCE BIT(9) #define RCANFD_FDCFG_TDCOC BIT(8) #define RCANFD_FDCFG_TDCO(x) (((x) & 0x7f) >> 16) @@ -219,10 +240,10 @@ enum rcanfd_chip_id { /* Common FIFO bits */ /* RSCFDnCFDCFCCk */ -#define RCANFD_CFCC_CFTML(x) (((x) & 0xf) << 20) -#define RCANFD_CFCC_CFM(x) (((x) & 0x3) << 16) +#define RCANFD_CFCC_CFTML(gpriv, x) (((x) & 0xf) << reg_v3u(gpriv, 16, 20)) +#define RCANFD_CFCC_CFM(gpriv, x) (((x) & 0x3) << reg_v3u(gpriv, 8, 16)) #define RCANFD_CFCC_CFIM BIT(12) -#define RCANFD_CFCC_CFDC(x) (((x) & 0x7) << 8) +#define RCANFD_CFCC_CFDC(gpriv, x) (((x) & 0x7) << reg_v3u(gpriv, 21, 8)) #define RCANFD_CFCC_CFPLS(x) (((x) & 0x7) << 4) #define RCANFD_CFCC_CFTXIE BIT(2) #define RCANFD_CFCC_CFE BIT(0) @@ -282,33 +303,31 @@ enum rcanfd_chip_id { #define RCANFD_GTSC (0x0094) /* RSCFDnCFDGAFLECTR / RSCFDnGAFLECTR */ #define RCANFD_GAFLECTR (0x0098) -/* RSCFDnCFDGAFLCFG0 / RSCFDnGAFLCFG0 */ -#define RCANFD_GAFLCFG0 (0x009c) -/* RSCFDnCFDGAFLCFG1 / RSCFDnGAFLCFG1 */ -#define RCANFD_GAFLCFG1 (0x00a0) +/* RSCFDnCFDGAFLCFG / RSCFDnGAFLCFG */ +#define RCANFD_GAFLCFG(ch) (0x009c + (0x04 * ((ch) / 2))) /* RSCFDnCFDRMNB / RSCFDnRMNB */ #define RCANFD_RMNB (0x00a4) /* RSCFDnCFDRMND / RSCFDnRMND */ #define RCANFD_RMND(y) (0x00a8 + (0x04 * (y))) /* RSCFDnCFDRFCCx / RSCFDnRFCCx */ -#define RCANFD_RFCC(x) (0x00b8 + (0x04 * (x))) +#define RCANFD_RFCC(gpriv, x) (reg_v3u(gpriv, 0x00c0, 0x00b8) + (0x04 * (x))) /* RSCFDnCFDRFSTSx / RSCFDnRFSTSx */ -#define RCANFD_RFSTS(x) (0x00d8 + (0x04 * (x))) +#define RCANFD_RFSTS(gpriv, x) (RCANFD_RFCC(gpriv, x) + 0x20) /* RSCFDnCFDRFPCTRx / RSCFDnRFPCTRx */ -#define RCANFD_RFPCTR(x) (0x00f8 + (0x04 * (x))) +#define RCANFD_RFPCTR(gpriv, x) (RCANFD_RFCC(gpriv, x) + 0x40) /* Common FIFO Control registers */ /* RSCFDnCFDCFCCx / RSCFDnCFCCx */ -#define RCANFD_CFCC(ch, idx) (0x0118 + (0x0c * (ch)) + \ - (0x04 * (idx))) +#define RCANFD_CFCC(gpriv, ch, idx) \ + (reg_v3u(gpriv, 0x0120, 0x0118) + (0x0c * (ch)) + (0x04 * (idx))) /* RSCFDnCFDCFSTSx / RSCFDnCFSTSx */ -#define RCANFD_CFSTS(ch, idx) (0x0178 + (0x0c * (ch)) + \ - (0x04 * (idx))) +#define RCANFD_CFSTS(gpriv, ch, idx) \ + (reg_v3u(gpriv, 0x01e0, 0x0178) + (0x0c * (ch)) + (0x04 * (idx))) /* RSCFDnCFDCFPCTRx / RSCFDnCFPCTRx */ -#define RCANFD_CFPCTR(ch, idx) (0x01d8 + (0x0c * (ch)) + \ - (0x04 * (idx))) +#define RCANFD_CFPCTR(gpriv, ch, idx) \ + (reg_v3u(gpriv, 0x0240, 0x01d8) + (0x0c * (ch)) + (0x04 * (idx))) /* RSCFDnCFDFESTS / RSCFDnFESTS */ #define RCANFD_FESTS (0x0238) @@ -387,22 +406,23 @@ enum rcanfd_chip_id { #define RCANFD_C_RMDF1(q) (0x060c + (0x10 * (q))) /* RSCFDnRFXXx -> RCANFD_C_RFXX(x) */ -#define RCANFD_C_RFOFFSET (0x0e00) -#define RCANFD_C_RFID(x) (RCANFD_C_RFOFFSET + (0x10 * (x))) -#define RCANFD_C_RFPTR(x) (RCANFD_C_RFOFFSET + 0x04 + \ - (0x10 * (x))) -#define RCANFD_C_RFDF(x, df) (RCANFD_C_RFOFFSET + 0x08 + \ - (0x10 * (x)) + (0x04 * (df))) +#define RCANFD_C_RFOFFSET (0x0e00) +#define RCANFD_C_RFID(x) (RCANFD_C_RFOFFSET + (0x10 * (x))) +#define RCANFD_C_RFPTR(x) (RCANFD_C_RFOFFSET + 0x04 + (0x10 * (x))) +#define RCANFD_C_RFDF(x, df) \ + (RCANFD_C_RFOFFSET + 0x08 + (0x10 * (x)) + (0x04 * (df))) /* RSCFDnCFXXk -> RCANFD_C_CFXX(ch, k) */ #define RCANFD_C_CFOFFSET (0x0e80) -#define RCANFD_C_CFID(ch, idx) (RCANFD_C_CFOFFSET + (0x30 * (ch)) + \ - (0x10 * (idx))) -#define RCANFD_C_CFPTR(ch, idx) (RCANFD_C_CFOFFSET + 0x04 + \ - (0x30 * (ch)) + (0x10 * (idx))) -#define RCANFD_C_CFDF(ch, idx, df) (RCANFD_C_CFOFFSET + 0x08 + \ - (0x30 * (ch)) + (0x10 * (idx)) + \ - (0x04 * (df))) + +#define RCANFD_C_CFID(ch, idx) \ + (RCANFD_C_CFOFFSET + (0x30 * (ch)) + (0x10 * (idx))) + +#define RCANFD_C_CFPTR(ch, idx) \ + (RCANFD_C_CFOFFSET + 0x04 + (0x30 * (ch)) + (0x10 * (idx))) + +#define RCANFD_C_CFDF(ch, idx, df) \ + (RCANFD_C_CFOFFSET + 0x08 + (0x30 * (ch)) + (0x10 * (idx)) + (0x04 * (df))) /* RSCFDnTMXXp -> RCANFD_C_TMXX(p) */ #define RCANFD_C_TMID(p) (0x1000 + (0x10 * (p))) @@ -415,6 +435,12 @@ enum rcanfd_chip_id { /* RSCFDnRPGACCr */ #define RCANFD_C_RPGACC(r) (0x1900 + (0x04 * (r))) +/* R-Car V3U Classical and CAN FD mode specific register map */ +#define RCANFD_V3U_CFDCFG (0x1314) +#define RCANFD_V3U_DCFG(m) (0x1400 + (0x20 * (m))) + +#define RCANFD_V3U_GAFL_OFFSET (0x1800) + /* CAN FD mode specific register map */ /* RSCFDnCFDCmXXX -> RCANFD_F_XXX(m) */ @@ -434,26 +460,28 @@ enum rcanfd_chip_id { #define RCANFD_F_RMDF(q, b) (0x200c + (0x04 * (b)) + (0x20 * (q))) /* RSCFDnCFDRFXXx -> RCANFD_F_RFXX(x) */ -#define RCANFD_F_RFOFFSET (0x3000) -#define RCANFD_F_RFID(x) (RCANFD_F_RFOFFSET + (0x80 * (x))) -#define RCANFD_F_RFPTR(x) (RCANFD_F_RFOFFSET + 0x04 + \ - (0x80 * (x))) -#define RCANFD_F_RFFDSTS(x) (RCANFD_F_RFOFFSET + 0x08 + \ - (0x80 * (x))) -#define RCANFD_F_RFDF(x, df) (RCANFD_F_RFOFFSET + 0x0c + \ - (0x80 * (x)) + (0x04 * (df))) +#define RCANFD_F_RFOFFSET(gpriv) reg_v3u(gpriv, 0x6000, 0x3000) +#define RCANFD_F_RFID(gpriv, x) (RCANFD_F_RFOFFSET(gpriv) + (0x80 * (x))) +#define RCANFD_F_RFPTR(gpriv, x) (RCANFD_F_RFOFFSET(gpriv) + 0x04 + (0x80 * (x))) +#define RCANFD_F_RFFDSTS(gpriv, x) (RCANFD_F_RFOFFSET(gpriv) + 0x08 + (0x80 * (x))) +#define RCANFD_F_RFDF(gpriv, x, df) \ + (RCANFD_F_RFOFFSET(gpriv) + 0x0c + (0x80 * (x)) + (0x04 * (df))) /* RSCFDnCFDCFXXk -> RCANFD_F_CFXX(ch, k) */ -#define RCANFD_F_CFOFFSET (0x3400) -#define RCANFD_F_CFID(ch, idx) (RCANFD_F_CFOFFSET + (0x180 * (ch)) + \ - (0x80 * (idx))) -#define RCANFD_F_CFPTR(ch, idx) (RCANFD_F_CFOFFSET + 0x04 + \ - (0x180 * (ch)) + (0x80 * (idx))) -#define RCANFD_F_CFFDCSTS(ch, idx) (RCANFD_F_CFOFFSET + 0x08 + \ - (0x180 * (ch)) + (0x80 * (idx))) -#define RCANFD_F_CFDF(ch, idx, df) (RCANFD_F_CFOFFSET + 0x0c + \ - (0x180 * (ch)) + (0x80 * (idx)) + \ - (0x04 * (df))) +#define RCANFD_F_CFOFFSET(gpriv) reg_v3u(gpriv, 0x6400, 0x3400) + +#define RCANFD_F_CFID(gpriv, ch, idx) \ + (RCANFD_F_CFOFFSET(gpriv) + (0x180 * (ch)) + (0x80 * (idx))) + +#define RCANFD_F_CFPTR(gpriv, ch, idx) \ + (RCANFD_F_CFOFFSET(gpriv) + 0x04 + (0x180 * (ch)) + (0x80 * (idx))) + +#define RCANFD_F_CFFDCSTS(gpriv, ch, idx) \ + (RCANFD_F_CFOFFSET(gpriv) + 0x08 + (0x180 * (ch)) + (0x80 * (idx))) + +#define RCANFD_F_CFDF(gpriv, ch, idx, df) \ + (RCANFD_F_CFOFFSET(gpriv) + 0x0c + (0x180 * (ch)) + (0x80 * (idx)) + \ + (0x04 * (df))) /* RSCFDnCFDTMXXp -> RCANFD_F_TMXX(p) */ #define RCANFD_F_TMID(p) (0x4000 + (0x20 * (p))) @@ -470,7 +498,7 @@ enum rcanfd_chip_id { #define RCANFD_FIFO_DEPTH 8 /* Tx FIFO depth */ #define RCANFD_NAPI_WEIGHT 8 /* Rx poll quota */ -#define RCANFD_NUM_CHANNELS 2 /* Two channels max */ +#define RCANFD_NUM_CHANNELS 8 /* Eight channels max */ #define RCANFD_CHANNELS_MASK BIT((RCANFD_NUM_CHANNELS) - 1) #define RCANFD_GAFL_PAGENUM(entry) ((entry) / 16) @@ -521,6 +549,7 @@ struct rcar_canfd_global { struct reset_control *rstc1; struct reset_control *rstc2; enum rcanfd_chip_id chip_id; + u32 max_channels; }; /* CAN FD mode nominal rate constants */ @@ -563,6 +592,17 @@ static const struct can_bittiming_const rcar_canfd_bittiming_const = { }; /* Helper functions */ +static inline bool is_v3u(struct rcar_canfd_global *gpriv) +{ + return gpriv->chip_id == RENESAS_R8A779A0; +} + +static inline u32 reg_v3u(struct rcar_canfd_global *gpriv, + u32 v3u, u32 not_v3u) +{ + return is_v3u(gpriv) ? v3u : not_v3u; +} + static inline void rcar_canfd_update(u32 mask, u32 val, u32 __iomem *reg) { u32 data = readl(reg); @@ -628,6 +668,25 @@ static void rcar_canfd_tx_failure_cleanup(struct net_device *ndev) can_free_echo_skb(ndev, i, NULL); } +static void rcar_canfd_set_mode(struct rcar_canfd_global *gpriv) +{ + if (is_v3u(gpriv)) { + if (gpriv->fdmode) + rcar_canfd_set_bit(gpriv->base, RCANFD_V3U_CFDCFG, + RCANFD_FDCFG_FDOE); + else + rcar_canfd_set_bit(gpriv->base, RCANFD_V3U_CFDCFG, + RCANFD_FDCFG_CLOE); + } else { + if (gpriv->fdmode) + rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG, + RCANFD_GRMCFG_RCMC); + else + rcar_canfd_clear_bit(gpriv->base, RCANFD_GRMCFG, + RCANFD_GRMCFG_RCMC); + } +} + static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv) { u32 sts, ch; @@ -660,15 +719,10 @@ static int rcar_canfd_reset_controller(struct rcar_canfd_global *gpriv) rcar_canfd_write(gpriv->base, RCANFD_GERFL, 0x0); /* Set the controller into appropriate mode */ - if (gpriv->fdmode) - rcar_canfd_set_bit(gpriv->base, RCANFD_GRMCFG, - RCANFD_GRMCFG_RCMC); - else - rcar_canfd_clear_bit(gpriv->base, RCANFD_GRMCFG, - RCANFD_GRMCFG_RCMC); + rcar_canfd_set_mode(gpriv); /* Transition all Channels to reset mode */ - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) { + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) { rcar_canfd_clear_bit(gpriv->base, RCANFD_CCTR(ch), RCANFD_CCTR_CSLPR); @@ -709,7 +763,7 @@ static void rcar_canfd_configure_controller(struct rcar_canfd_global *gpriv) rcar_canfd_set_bit(gpriv->base, RCANFD_GCFG, cfg); /* Channel configuration settings */ - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) { + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) { rcar_canfd_set_bit(gpriv->base, RCANFD_CCTR(ch), RCANFD_CCTR_ERRD); rcar_canfd_update_bit(gpriv->base, RCANFD_CCTR(ch), @@ -729,20 +783,22 @@ static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv, start = 0; /* Channel 0 always starts from 0th rule */ } else { /* Get number of Channel 0 rules and adjust */ - cfg = rcar_canfd_read(gpriv->base, RCANFD_GAFLCFG0); - start = RCANFD_GAFLCFG_GETRNC(0, cfg); + cfg = rcar_canfd_read(gpriv->base, RCANFD_GAFLCFG(ch)); + start = RCANFD_GAFLCFG_GETRNC(gpriv, 0, cfg); } /* Enable write access to entry */ page = RCANFD_GAFL_PAGENUM(start); rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLECTR, - (RCANFD_GAFLECTR_AFLPN(page) | + (RCANFD_GAFLECTR_AFLPN(gpriv, page) | RCANFD_GAFLECTR_AFLDAE)); /* Write number of rules for channel */ - rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG0, - RCANFD_GAFLCFG_SETRNC(ch, num_rules)); - if (gpriv->fdmode) + rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLCFG(ch), + RCANFD_GAFLCFG_SETRNC(gpriv, ch, num_rules)); + if (is_v3u(gpriv)) + offset = RCANFD_V3U_GAFL_OFFSET; + else if (gpriv->fdmode) offset = RCANFD_F_GAFL_OFFSET; else offset = RCANFD_C_GAFL_OFFSET; @@ -754,8 +810,8 @@ static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv, /* Any data length accepted */ rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, start), 0); /* Place the msg in corresponding Rx FIFO entry */ - rcar_canfd_write(gpriv->base, RCANFD_GAFLP1(offset, start), - RCANFD_GAFLP1_GAFLFDP(ridx)); + rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLP1(offset, start), + RCANFD_GAFLP1_GAFLFDP(ridx)); /* Disable write access to page */ rcar_canfd_clear_bit(gpriv->base, @@ -779,7 +835,7 @@ static void rcar_canfd_configure_rx(struct rcar_canfd_global *gpriv, u32 ch) cfg = (RCANFD_RFCC_RFIM | RCANFD_RFCC_RFDC(rfdc) | RCANFD_RFCC_RFPLS(rfpls) | RCANFD_RFCC_RFIE); - rcar_canfd_write(gpriv->base, RCANFD_RFCC(ridx), cfg); + rcar_canfd_write(gpriv->base, RCANFD_RFCC(gpriv, ridx), cfg); } static void rcar_canfd_configure_tx(struct rcar_canfd_global *gpriv, u32 ch) @@ -801,15 +857,15 @@ static void rcar_canfd_configure_tx(struct rcar_canfd_global *gpriv, u32 ch) else cfpls = 0; /* b000 - Max 8 bytes payload */ - cfg = (RCANFD_CFCC_CFTML(cftml) | RCANFD_CFCC_CFM(cfm) | - RCANFD_CFCC_CFIM | RCANFD_CFCC_CFDC(cfdc) | + cfg = (RCANFD_CFCC_CFTML(gpriv, cftml) | RCANFD_CFCC_CFM(gpriv, cfm) | + RCANFD_CFCC_CFIM | RCANFD_CFCC_CFDC(gpriv, cfdc) | RCANFD_CFCC_CFPLS(cfpls) | RCANFD_CFCC_CFTXIE); - rcar_canfd_write(gpriv->base, RCANFD_CFCC(ch, RCANFD_CFFIFO_IDX), cfg); + rcar_canfd_write(gpriv->base, RCANFD_CFCC(gpriv, ch, RCANFD_CFFIFO_IDX), cfg); if (gpriv->fdmode) /* Clear FD mode specific control/status register */ rcar_canfd_write(gpriv->base, - RCANFD_F_CFFDCSTS(ch, RCANFD_CFFIFO_IDX), 0); + RCANFD_F_CFFDCSTS(gpriv, ch, RCANFD_CFFIFO_IDX), 0); } static void rcar_canfd_enable_global_interrupts(struct rcar_canfd_global *gpriv) @@ -890,20 +946,20 @@ static void rcar_canfd_global_error(struct net_device *ndev) } if (gerfl & RCANFD_GERFL_MES) { sts = rcar_canfd_read(priv->base, - RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX)); + RCANFD_CFSTS(gpriv, ch, RCANFD_CFFIFO_IDX)); if (sts & RCANFD_CFSTS_CFMLT) { netdev_dbg(ndev, "Tx Message Lost flag\n"); stats->tx_dropped++; rcar_canfd_write(priv->base, - RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX), + RCANFD_CFSTS(gpriv, ch, RCANFD_CFFIFO_IDX), sts & ~RCANFD_CFSTS_CFMLT); } - sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx)); + sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(gpriv, ridx)); if (sts & RCANFD_RFSTS_RFMLT) { netdev_dbg(ndev, "Rx Message Lost flag\n"); stats->rx_dropped++; - rcar_canfd_write(priv->base, RCANFD_RFSTS(ridx), + rcar_canfd_write(priv->base, RCANFD_RFSTS(gpriv, ridx), sts & ~RCANFD_RFSTS_RFMLT); } } @@ -1038,6 +1094,7 @@ static void rcar_canfd_error(struct net_device *ndev, u32 cerfl, static void rcar_canfd_tx_done(struct net_device *ndev) { struct rcar_canfd_channel *priv = netdev_priv(ndev); + struct rcar_canfd_global *gpriv = priv->gpriv; struct net_device_stats *stats = &ndev->stats; u32 sts; unsigned long flags; @@ -1053,7 +1110,7 @@ static void rcar_canfd_tx_done(struct net_device *ndev) spin_lock_irqsave(&priv->tx_lock, flags); priv->tx_tail++; sts = rcar_canfd_read(priv->base, - RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX)); + RCANFD_CFSTS(gpriv, ch, RCANFD_CFFIFO_IDX)); unsent = RCANFD_CFSTS_CFMC(sts); /* Wake producer only when there is room */ @@ -1069,7 +1126,7 @@ static void rcar_canfd_tx_done(struct net_device *ndev) } while (1); /* Clear interrupt */ - rcar_canfd_write(priv->base, RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX), + rcar_canfd_write(priv->base, RCANFD_CFSTS(gpriv, ch, RCANFD_CFFIFO_IDX), sts & ~RCANFD_CFSTS_CFTXIF); can_led_event(ndev, CAN_LED_EVENT_TX); } @@ -1091,7 +1148,7 @@ static irqreturn_t rcar_canfd_global_err_interrupt(int irq, void *dev_id) struct rcar_canfd_global *gpriv = dev_id; u32 ch; - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) rcar_canfd_handle_global_err(gpriv, ch); return IRQ_HANDLED; @@ -1104,12 +1161,12 @@ static void rcar_canfd_handle_global_receive(struct rcar_canfd_global *gpriv, u3 u32 sts; /* Handle Rx interrupts */ - sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx)); + sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(gpriv, ridx)); if (likely(sts & RCANFD_RFSTS_RFIF)) { if (napi_schedule_prep(&priv->napi)) { /* Disable Rx FIFO interrupts */ rcar_canfd_clear_bit(priv->base, - RCANFD_RFCC(ridx), + RCANFD_RFCC(gpriv, ridx), RCANFD_RFCC_RFIE); __napi_schedule(&priv->napi); } @@ -1121,7 +1178,7 @@ static irqreturn_t rcar_canfd_global_receive_fifo_interrupt(int irq, void *dev_i struct rcar_canfd_global *gpriv = dev_id; u32 ch; - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) rcar_canfd_handle_global_receive(gpriv, ch); return IRQ_HANDLED; @@ -1135,7 +1192,7 @@ static irqreturn_t rcar_canfd_global_interrupt(int irq, void *dev_id) /* Global error interrupts still indicate a condition specific * to a channel. RxFIFO interrupt is a global interrupt. */ - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) { + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) { rcar_canfd_handle_global_err(gpriv, ch); rcar_canfd_handle_global_receive(gpriv, ch); } @@ -1181,7 +1238,7 @@ static void rcar_canfd_handle_channel_tx(struct rcar_canfd_global *gpriv, u32 ch /* Handle Tx interrupts */ sts = rcar_canfd_read(priv->base, - RCANFD_CFSTS(ch, RCANFD_CFFIFO_IDX)); + RCANFD_CFSTS(gpriv, ch, RCANFD_CFFIFO_IDX)); if (likely(sts & RCANFD_CFSTS_CFTXIF)) rcar_canfd_tx_done(ndev); } @@ -1191,7 +1248,7 @@ static irqreturn_t rcar_canfd_channel_tx_interrupt(int irq, void *dev_id) struct rcar_canfd_global *gpriv = dev_id; u32 ch; - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) rcar_canfd_handle_channel_tx(gpriv, ch); return IRQ_HANDLED; @@ -1223,7 +1280,7 @@ static irqreturn_t rcar_canfd_channel_err_interrupt(int irq, void *dev_id) struct rcar_canfd_global *gpriv = dev_id; u32 ch; - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) rcar_canfd_handle_channel_err(gpriv, ch); return IRQ_HANDLED; @@ -1235,7 +1292,7 @@ static irqreturn_t rcar_canfd_channel_interrupt(int irq, void *dev_id) u32 ch; /* Common FIFO is a per channel resource */ - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) { + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) { rcar_canfd_handle_channel_err(gpriv, ch); rcar_canfd_handle_channel_tx(gpriv, ch); } @@ -1246,6 +1303,7 @@ static irqreturn_t rcar_canfd_channel_interrupt(int irq, void *dev_id) static void rcar_canfd_set_bittiming(struct net_device *dev) { struct rcar_canfd_channel *priv = netdev_priv(dev); + struct rcar_canfd_global *gpriv = priv->gpriv; const struct can_bittiming *bt = &priv->can.bittiming; const struct can_bittiming *dbt = &priv->can.data_bittiming; u16 brp, sjw, tseg1, tseg2; @@ -1260,8 +1318,8 @@ static void rcar_canfd_set_bittiming(struct net_device *dev) if (priv->can.ctrlmode & CAN_CTRLMODE_FD) { /* CAN FD only mode */ - cfg = (RCANFD_NCFG_NTSEG1(tseg1) | RCANFD_NCFG_NBRP(brp) | - RCANFD_NCFG_NSJW(sjw) | RCANFD_NCFG_NTSEG2(tseg2)); + cfg = (RCANFD_NCFG_NTSEG1(gpriv, tseg1) | RCANFD_NCFG_NBRP(brp) | + RCANFD_NCFG_NSJW(gpriv, sjw) | RCANFD_NCFG_NTSEG2(gpriv, tseg2)); rcar_canfd_write(priv->base, RCANFD_CCFG(ch), cfg); netdev_dbg(priv->ndev, "nrate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n", @@ -1273,16 +1331,25 @@ static void rcar_canfd_set_bittiming(struct net_device *dev) tseg1 = dbt->prop_seg + dbt->phase_seg1 - 1; tseg2 = dbt->phase_seg2 - 1; - cfg = (RCANFD_DCFG_DTSEG1(tseg1) | RCANFD_DCFG_DBRP(brp) | - RCANFD_DCFG_DSJW(sjw) | RCANFD_DCFG_DTSEG2(tseg2)); + cfg = (RCANFD_DCFG_DTSEG1(gpriv, tseg1) | RCANFD_DCFG_DBRP(brp) | + RCANFD_DCFG_DSJW(sjw) | RCANFD_DCFG_DTSEG2(gpriv, tseg2)); rcar_canfd_write(priv->base, RCANFD_F_DCFG(ch), cfg); netdev_dbg(priv->ndev, "drate: brp %u, sjw %u, tseg1 %u, tseg2 %u\n", brp, sjw, tseg1, tseg2); } else { /* Classical CAN only mode */ - cfg = (RCANFD_CFG_TSEG1(tseg1) | RCANFD_CFG_BRP(brp) | - RCANFD_CFG_SJW(sjw) | RCANFD_CFG_TSEG2(tseg2)); + if (is_v3u(gpriv)) { + cfg = (RCANFD_NCFG_NTSEG1(gpriv, tseg1) | + RCANFD_NCFG_NBRP(brp) | + RCANFD_NCFG_NSJW(gpriv, sjw) | + RCANFD_NCFG_NTSEG2(gpriv, tseg2)); + } else { + cfg = (RCANFD_CFG_TSEG1(tseg1) | + RCANFD_CFG_BRP(brp) | + RCANFD_CFG_SJW(sjw) | + RCANFD_CFG_TSEG2(tseg2)); + } rcar_canfd_write(priv->base, RCANFD_CCFG(ch), cfg); netdev_dbg(priv->ndev, @@ -1294,6 +1361,7 @@ static void rcar_canfd_set_bittiming(struct net_device *dev) static int rcar_canfd_start(struct net_device *ndev) { struct rcar_canfd_channel *priv = netdev_priv(ndev); + struct rcar_canfd_global *gpriv = priv->gpriv; int err = -EOPNOTSUPP; u32 sts, ch = priv->channel; u32 ridx = ch + RCANFD_RFFIFO_IDX; @@ -1315,9 +1383,9 @@ static int rcar_canfd_start(struct net_device *ndev) } /* Enable Common & Rx FIFO */ - rcar_canfd_set_bit(priv->base, RCANFD_CFCC(ch, RCANFD_CFFIFO_IDX), + rcar_canfd_set_bit(priv->base, RCANFD_CFCC(gpriv, ch, RCANFD_CFFIFO_IDX), RCANFD_CFCC_CFE); - rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx), RCANFD_RFCC_RFE); + rcar_canfd_set_bit(priv->base, RCANFD_RFCC(gpriv, ridx), RCANFD_RFCC_RFE); priv->can.state = CAN_STATE_ERROR_ACTIVE; return 0; @@ -1365,6 +1433,7 @@ out_clock: static void rcar_canfd_stop(struct net_device *ndev) { struct rcar_canfd_channel *priv = netdev_priv(ndev); + struct rcar_canfd_global *gpriv = priv->gpriv; int err; u32 sts, ch = priv->channel; u32 ridx = ch + RCANFD_RFFIFO_IDX; @@ -1382,9 +1451,9 @@ static void rcar_canfd_stop(struct net_device *ndev) rcar_canfd_disable_channel_interrupts(priv); /* Disable Common & Rx FIFO */ - rcar_canfd_clear_bit(priv->base, RCANFD_CFCC(ch, RCANFD_CFFIFO_IDX), + rcar_canfd_clear_bit(priv->base, RCANFD_CFCC(gpriv, ch, RCANFD_CFFIFO_IDX), RCANFD_CFCC_CFE); - rcar_canfd_clear_bit(priv->base, RCANFD_RFCC(ridx), RCANFD_RFCC_RFE); + rcar_canfd_clear_bit(priv->base, RCANFD_RFCC(gpriv, ridx), RCANFD_RFCC_RFE); /* Set the state as STOPPED */ priv->can.state = CAN_STATE_STOPPED; @@ -1408,6 +1477,7 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct rcar_canfd_channel *priv = netdev_priv(ndev); + struct rcar_canfd_global *gpriv = priv->gpriv; struct canfd_frame *cf = (struct canfd_frame *)skb->data; u32 sts = 0, id, dlc; unsigned long flags; @@ -1428,11 +1498,11 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb, dlc = RCANFD_CFPTR_CFDLC(can_fd_len2dlc(cf->len)); - if (priv->can.ctrlmode & CAN_CTRLMODE_FD) { + if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_v3u(gpriv)) { rcar_canfd_write(priv->base, - RCANFD_F_CFID(ch, RCANFD_CFFIFO_IDX), id); + RCANFD_F_CFID(gpriv, ch, RCANFD_CFFIFO_IDX), id); rcar_canfd_write(priv->base, - RCANFD_F_CFPTR(ch, RCANFD_CFFIFO_IDX), dlc); + RCANFD_F_CFPTR(gpriv, ch, RCANFD_CFFIFO_IDX), dlc); if (can_is_canfd_skb(skb)) { /* CAN FD frame format */ @@ -1445,10 +1515,10 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb, } rcar_canfd_write(priv->base, - RCANFD_F_CFFDCSTS(ch, RCANFD_CFFIFO_IDX), sts); + RCANFD_F_CFFDCSTS(gpriv, ch, RCANFD_CFFIFO_IDX), sts); rcar_canfd_put_data(priv, cf, - RCANFD_F_CFDF(ch, RCANFD_CFFIFO_IDX, 0)); + RCANFD_F_CFDF(gpriv, ch, RCANFD_CFFIFO_IDX, 0)); } else { rcar_canfd_write(priv->base, RCANFD_C_CFID(ch, RCANFD_CFFIFO_IDX), id); @@ -1471,7 +1541,7 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb, * pointer for the Common FIFO */ rcar_canfd_write(priv->base, - RCANFD_CFPCTR(ch, RCANFD_CFFIFO_IDX), 0xff); + RCANFD_CFPCTR(gpriv, ch, RCANFD_CFFIFO_IDX), 0xff); spin_unlock_irqrestore(&priv->tx_lock, flags); return NETDEV_TX_OK; @@ -1480,18 +1550,21 @@ static netdev_tx_t rcar_canfd_start_xmit(struct sk_buff *skb, static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv) { struct net_device_stats *stats = &priv->ndev->stats; + struct rcar_canfd_global *gpriv = priv->gpriv; struct canfd_frame *cf; struct sk_buff *skb; u32 sts = 0, id, dlc; u32 ch = priv->channel; u32 ridx = ch + RCANFD_RFFIFO_IDX; - if (priv->can.ctrlmode & CAN_CTRLMODE_FD) { - id = rcar_canfd_read(priv->base, RCANFD_F_RFID(ridx)); - dlc = rcar_canfd_read(priv->base, RCANFD_F_RFPTR(ridx)); + if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) || is_v3u(gpriv)) { + id = rcar_canfd_read(priv->base, RCANFD_F_RFID(gpriv, ridx)); + dlc = rcar_canfd_read(priv->base, RCANFD_F_RFPTR(gpriv, ridx)); - sts = rcar_canfd_read(priv->base, RCANFD_F_RFFDSTS(ridx)); - if (sts & RCANFD_RFFDSTS_RFFDF) + sts = rcar_canfd_read(priv->base, RCANFD_F_RFFDSTS(gpriv, ridx)); + + if ((priv->can.ctrlmode & CAN_CTRLMODE_FD) && + sts & RCANFD_RFFDSTS_RFFDF) skb = alloc_canfd_skb(priv->ndev, &cf); else skb = alloc_can_skb(priv->ndev, @@ -1529,12 +1602,14 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv) if (sts & RCANFD_RFFDSTS_RFBRS) cf->flags |= CANFD_BRS; - rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(ridx, 0)); + rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(gpriv, ridx, 0)); } } else { cf->len = can_cc_dlc2len(RCANFD_RFPTR_RFDLC(dlc)); if (id & RCANFD_RFID_RFRTR) cf->can_id |= CAN_RTR_FLAG; + else if (is_v3u(gpriv)) + rcar_canfd_get_data(priv, cf, RCANFD_F_RFDF(gpriv, ridx, 0)); else rcar_canfd_get_data(priv, cf, RCANFD_C_RFDF(ridx, 0)); } @@ -1542,7 +1617,7 @@ static void rcar_canfd_rx_pkt(struct rcar_canfd_channel *priv) /* Write 0xff to RFPC to increment the CPU-side * pointer of the Rx FIFO */ - rcar_canfd_write(priv->base, RCANFD_RFPCTR(ridx), 0xff); + rcar_canfd_write(priv->base, RCANFD_RFPCTR(gpriv, ridx), 0xff); can_led_event(priv->ndev, CAN_LED_EVENT_RX); @@ -1556,13 +1631,14 @@ static int rcar_canfd_rx_poll(struct napi_struct *napi, int quota) { struct rcar_canfd_channel *priv = container_of(napi, struct rcar_canfd_channel, napi); + struct rcar_canfd_global *gpriv = priv->gpriv; int num_pkts; u32 sts; u32 ch = priv->channel; u32 ridx = ch + RCANFD_RFFIFO_IDX; for (num_pkts = 0; num_pkts < quota; num_pkts++) { - sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(ridx)); + sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(gpriv, ridx)); /* Check FIFO empty condition */ if (sts & RCANFD_RFSTS_RFEMP) break; @@ -1571,7 +1647,7 @@ static int rcar_canfd_rx_poll(struct napi_struct *napi, int quota) /* Clear interrupt bit */ if (sts & RCANFD_RFSTS_RFIF) - rcar_canfd_write(priv->base, RCANFD_RFSTS(ridx), + rcar_canfd_write(priv->base, RCANFD_RFSTS(gpriv, ridx), sts & ~RCANFD_RFSTS_RFIF); } @@ -1579,7 +1655,7 @@ static int rcar_canfd_rx_poll(struct napi_struct *napi, int quota) if (num_pkts < quota) { if (napi_complete_done(napi, num_pkts)) { /* Enable Rx FIFO interrupts */ - rcar_canfd_set_bit(priv->base, RCANFD_RFCC(ridx), + rcar_canfd_set_bit(priv->base, RCANFD_RFCC(gpriv, ridx), RCANFD_RFCC_RFIE); } } @@ -1756,21 +1832,24 @@ static int rcar_canfd_probe(struct platform_device *pdev) int g_err_irq, g_recc_irq; bool fdmode = true; /* CAN FD only mode - default */ enum rcanfd_chip_id chip_id; + int max_channels; + char name[9] = "channelX"; + int i; chip_id = (uintptr_t)of_device_get_match_data(&pdev->dev); + max_channels = chip_id == RENESAS_R8A779A0 ? 8 : 2; if (of_property_read_bool(pdev->dev.of_node, "renesas,no-can-fd")) fdmode = false; /* Classical CAN only mode */ - of_child = of_get_child_by_name(pdev->dev.of_node, "channel0"); - if (of_child && of_device_is_available(of_child)) - channels_mask |= BIT(0); /* Channel 0 */ - - of_child = of_get_child_by_name(pdev->dev.of_node, "channel1"); - if (of_child && of_device_is_available(of_child)) - channels_mask |= BIT(1); /* Channel 1 */ + for (i = 0; i < max_channels; ++i) { + name[7] = '0' + i; + of_child = of_get_child_by_name(pdev->dev.of_node, name); + if (of_child && of_device_is_available(of_child)) + channels_mask |= BIT(i); + } - if (chip_id == RENESAS_RCAR_GEN3) { + if (chip_id != RENESAS_RZG2L) { ch_irq = platform_get_irq_byname_optional(pdev, "ch_int"); if (ch_irq < 0) { /* For backward compatibility get irq by index */ @@ -1806,6 +1885,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) gpriv->channels_mask = channels_mask; gpriv->fdmode = fdmode; gpriv->chip_id = chip_id; + gpriv->max_channels = max_channels; if (gpriv->chip_id == RENESAS_RZG2L) { gpriv->rstc1 = devm_reset_control_get_exclusive(&pdev->dev, "rstp_n"); @@ -1847,7 +1927,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) } fcan_freq = clk_get_rate(gpriv->can_clk); - if (gpriv->fcan == RCANFD_CANFDCLK && gpriv->chip_id == RENESAS_RCAR_GEN3) + if (gpriv->fcan == RCANFD_CANFDCLK && gpriv->chip_id != RENESAS_RZG2L) /* CANFD clock is further divided by (1/2) within the IP */ fcan_freq /= 2; @@ -1859,7 +1939,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) gpriv->base = addr; /* Request IRQ that's common for both channels */ - if (gpriv->chip_id == RENESAS_RCAR_GEN3) { + if (gpriv->chip_id != RENESAS_RZG2L) { err = devm_request_irq(&pdev->dev, ch_irq, rcar_canfd_channel_interrupt, 0, "canfd.ch_int", gpriv); @@ -1925,7 +2005,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) rcar_canfd_configure_controller(gpriv); /* Configure per channel attributes */ - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) { + for_each_set_bit(ch, &gpriv->channels_mask, max_channels) { /* Configure Channel's Rx fifo */ rcar_canfd_configure_rx(gpriv, ch); @@ -1951,7 +2031,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) goto fail_mode; } - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) { + for_each_set_bit(ch, &gpriv->channels_mask, max_channels) { err = rcar_canfd_channel_probe(gpriv, ch, fcan_freq); if (err) goto fail_channel; @@ -1963,7 +2043,7 @@ static int rcar_canfd_probe(struct platform_device *pdev) return 0; fail_channel: - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) + for_each_set_bit(ch, &gpriv->channels_mask, max_channels) rcar_canfd_channel_remove(gpriv, ch); fail_mode: rcar_canfd_disable_global_interrupts(gpriv); @@ -1984,7 +2064,7 @@ static int rcar_canfd_remove(struct platform_device *pdev) rcar_canfd_reset_controller(gpriv); rcar_canfd_disable_global_interrupts(gpriv); - for_each_set_bit(ch, &gpriv->channels_mask, RCANFD_NUM_CHANNELS) { + for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels) { rcar_canfd_disable_channel_interrupts(gpriv->ch[ch]); rcar_canfd_channel_remove(gpriv, ch); } @@ -2014,6 +2094,7 @@ static SIMPLE_DEV_PM_OPS(rcar_canfd_pm_ops, rcar_canfd_suspend, static const __maybe_unused struct of_device_id rcar_canfd_of_table[] = { { .compatible = "renesas,rcar-gen3-canfd", .data = (void *)RENESAS_RCAR_GEN3 }, { .compatible = "renesas,rzg2l-canfd", .data = (void *)RENESAS_RZG2L }, + { .compatible = "renesas,r8a779a0-canfd", .data = (void *)RENESAS_R8A779A0 }, { } }; diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c index 88d2540abbbe..c97ffa71fd75 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_fd.c +++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c @@ -173,12 +173,11 @@ static int es58x_fd_rx_event_msg(struct net_device *netdev, const struct es58x_fd_rx_event_msg *rx_event_msg; int ret; + rx_event_msg = &es58x_fd_urb_cmd->rx_event_msg; ret = es58x_check_msg_len(es58x_dev->dev, *rx_event_msg, msg_len); if (ret) return ret; - rx_event_msg = &es58x_fd_urb_cmd->rx_event_msg; - return es58x_rx_err_msg(netdev, rx_event_msg->error_code, rx_event_msg->event_code, get_unaligned_le64(&rx_event_msg->timestamp)); diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index d35749fad1ef..67408e316062 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -9,11 +9,12 @@ * Many thanks to all socketcan devs! */ +#include <linux/bitfield.h> #include <linux/ethtool.h> #include <linux/init.h> -#include <linux/signal.h> #include <linux/module.h> #include <linux/netdevice.h> +#include <linux/signal.h> #include <linux/usb.h> #include <linux/can.h> @@ -21,14 +22,20 @@ #include <linux/can/error.h> /* Device specific constants */ -#define USB_GSUSB_1_VENDOR_ID 0x1d50 -#define USB_GSUSB_1_PRODUCT_ID 0x606f +#define USB_GSUSB_1_VENDOR_ID 0x1d50 +#define USB_GSUSB_1_PRODUCT_ID 0x606f -#define USB_CANDLELIGHT_VENDOR_ID 0x1209 +#define USB_CANDLELIGHT_VENDOR_ID 0x1209 #define USB_CANDLELIGHT_PRODUCT_ID 0x2323 -#define GSUSB_ENDPOINT_IN 1 -#define GSUSB_ENDPOINT_OUT 2 +#define USB_CES_CANEXT_FD_VENDOR_ID 0x1cd2 +#define USB_CES_CANEXT_FD_PRODUCT_ID 0x606f + +#define USB_ABE_CANDEBUGGER_FD_VENDOR_ID 0x16d0 +#define USB_ABE_CANDEBUGGER_FD_PRODUCT_ID 0x10b8 + +#define GSUSB_ENDPOINT_IN 1 +#define GSUSB_ENDPOINT_OUT 2 /* Device specific constants */ enum gs_usb_breq { @@ -40,6 +47,11 @@ enum gs_usb_breq { GS_USB_BREQ_DEVICE_CONFIG, GS_USB_BREQ_TIMESTAMP, GS_USB_BREQ_IDENTIFY, + GS_USB_BREQ_GET_USER_ID, + GS_USB_BREQ_QUIRK_CANTACT_PRO_DATA_BITTIMING = GS_USB_BREQ_GET_USER_ID, + GS_USB_BREQ_SET_USER_ID, + GS_USB_BREQ_DATA_BITTIMING, + GS_USB_BREQ_BT_CONST_EXT, }; enum gs_can_mode { @@ -87,11 +99,18 @@ struct gs_device_config { __le32 hw_version; } __packed; -#define GS_CAN_MODE_NORMAL 0 -#define GS_CAN_MODE_LISTEN_ONLY BIT(0) -#define GS_CAN_MODE_LOOP_BACK BIT(1) -#define GS_CAN_MODE_TRIPLE_SAMPLE BIT(2) -#define GS_CAN_MODE_ONE_SHOT BIT(3) +#define GS_CAN_MODE_NORMAL 0 +#define GS_CAN_MODE_LISTEN_ONLY BIT(0) +#define GS_CAN_MODE_LOOP_BACK BIT(1) +#define GS_CAN_MODE_TRIPLE_SAMPLE BIT(2) +#define GS_CAN_MODE_ONE_SHOT BIT(3) +#define GS_CAN_MODE_HW_TIMESTAMP BIT(4) +/* GS_CAN_FEATURE_IDENTIFY BIT(5) */ +/* GS_CAN_FEATURE_USER_ID BIT(6) */ +#define GS_CAN_MODE_PAD_PKTS_TO_MAX_PKT_SIZE BIT(7) +#define GS_CAN_MODE_FD BIT(8) +/* GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX BIT(9) */ +/* GS_CAN_FEATURE_BT_CONST_EXT BIT(10) */ struct gs_device_mode { __le32 mode; @@ -116,12 +135,25 @@ struct gs_identify_mode { __le32 mode; } __packed; -#define GS_CAN_FEATURE_LISTEN_ONLY BIT(0) -#define GS_CAN_FEATURE_LOOP_BACK BIT(1) -#define GS_CAN_FEATURE_TRIPLE_SAMPLE BIT(2) -#define GS_CAN_FEATURE_ONE_SHOT BIT(3) -#define GS_CAN_FEATURE_HW_TIMESTAMP BIT(4) -#define GS_CAN_FEATURE_IDENTIFY BIT(5) +#define GS_CAN_FEATURE_LISTEN_ONLY BIT(0) +#define GS_CAN_FEATURE_LOOP_BACK BIT(1) +#define GS_CAN_FEATURE_TRIPLE_SAMPLE BIT(2) +#define GS_CAN_FEATURE_ONE_SHOT BIT(3) +#define GS_CAN_FEATURE_HW_TIMESTAMP BIT(4) +#define GS_CAN_FEATURE_IDENTIFY BIT(5) +#define GS_CAN_FEATURE_USER_ID BIT(6) +#define GS_CAN_FEATURE_PAD_PKTS_TO_MAX_PKT_SIZE BIT(7) +#define GS_CAN_FEATURE_FD BIT(8) +#define GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX BIT(9) +#define GS_CAN_FEATURE_BT_CONST_EXT BIT(10) +#define GS_CAN_FEATURE_MASK GENMASK(10, 0) + +/* internal quirks - keep in GS_CAN_FEATURE space for now */ + +/* CANtact Pro original firmware: + * BREQ DATA_BITTIMING overlaps with GET_USER_ID + */ +#define GS_CAN_FEATURE_QUIRK_BREQ_CANTACT_PRO BIT(31) struct gs_device_bt_const { __le32 feature; @@ -136,7 +168,50 @@ struct gs_device_bt_const { __le32 brp_inc; } __packed; -#define GS_CAN_FLAG_OVERFLOW 1 +struct gs_device_bt_const_extended { + __le32 feature; + __le32 fclk_can; + __le32 tseg1_min; + __le32 tseg1_max; + __le32 tseg2_min; + __le32 tseg2_max; + __le32 sjw_max; + __le32 brp_min; + __le32 brp_max; + __le32 brp_inc; + + __le32 dtseg1_min; + __le32 dtseg1_max; + __le32 dtseg2_min; + __le32 dtseg2_max; + __le32 dsjw_max; + __le32 dbrp_min; + __le32 dbrp_max; + __le32 dbrp_inc; +} __packed; + +#define GS_CAN_FLAG_OVERFLOW BIT(0) +#define GS_CAN_FLAG_FD BIT(1) +#define GS_CAN_FLAG_BRS BIT(2) +#define GS_CAN_FLAG_ESI BIT(3) + +struct classic_can { + u8 data[8]; +} __packed; + +struct classic_can_quirk { + u8 data[8]; + u8 quirk; +} __packed; + +struct canfd { + u8 data[64]; +} __packed; + +struct canfd_quirk { + u8 data[64]; + u8 quirk; +} __packed; struct gs_host_frame { u32 echo_id; @@ -147,7 +222,12 @@ struct gs_host_frame { u8 flags; u8 reserved; - u8 data[8]; + union { + DECLARE_FLEX_ARRAY(struct classic_can, classic_can); + DECLARE_FLEX_ARRAY(struct classic_can_quirk, classic_can_quirk); + DECLARE_FLEX_ARRAY(struct canfd, canfd); + DECLARE_FLEX_ARRAY(struct canfd_quirk, canfd_quirk); + }; } __packed; /* The GS USB devices make use of the same flags and masks as in * linux/can.h and linux/can/error.h, and no additional mapping is necessary. @@ -158,9 +238,9 @@ struct gs_host_frame { /* Only launch a max of GS_MAX_RX_URBS usb requests at a time. */ #define GS_MAX_RX_URBS 30 /* Maximum number of interfaces the driver supports per device. - * Current hardware only supports 2 interfaces. The future may vary. + * Current hardware only supports 3 interfaces. The future may vary. */ -#define GS_MAX_INTF 2 +#define GS_MAX_INTF 3 struct gs_tx_context { struct gs_can *dev; @@ -176,9 +256,12 @@ struct gs_can { struct usb_device *udev; struct usb_interface *iface; - struct can_bittiming_const bt_const; + struct can_bittiming_const bt_const, data_bt_const; unsigned int channel; /* channel number */ + u32 feature; + unsigned int hf_size_tx; + /* This lock prevents a race condition between xmit and receive. */ spinlock_t tx_ctx_lock; struct gs_tx_context tx_context[GS_MAX_TX_URBS]; @@ -192,6 +275,7 @@ struct gs_usb { struct gs_can *canch[GS_MAX_INTF]; struct usb_anchor rx_submitted; struct usb_device *udev; + unsigned int hf_size_rx; u8 active_channels; }; @@ -258,11 +342,7 @@ static int gs_cmd_reset(struct gs_can *gsdev) usb_sndctrlpipe(interface_to_usbdev(intf), 0), GS_USB_BREQ_MODE, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, - gsdev->channel, - 0, - dm, - sizeof(*dm), - 1000); + gsdev->channel, 0, dm, sizeof(*dm), 1000); kfree(dm); @@ -304,6 +384,7 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) struct gs_host_frame *hf = urb->transfer_buffer; struct gs_tx_context *txc; struct can_frame *cf; + struct canfd_frame *cfd; struct sk_buff *skb; BUG_ON(!usbcan); @@ -332,18 +413,33 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) return; if (hf->echo_id == -1) { /* normal rx */ - skb = alloc_can_skb(dev->netdev, &cf); - if (!skb) - return; + if (hf->flags & GS_CAN_FLAG_FD) { + skb = alloc_canfd_skb(dev->netdev, &cfd); + if (!skb) + return; + + cfd->can_id = le32_to_cpu(hf->can_id); + cfd->len = can_fd_dlc2len(hf->can_dlc); + if (hf->flags & GS_CAN_FLAG_BRS) + cfd->flags |= CANFD_BRS; + if (hf->flags & GS_CAN_FLAG_ESI) + cfd->flags |= CANFD_ESI; + + memcpy(cfd->data, hf->canfd->data, cfd->len); + } else { + skb = alloc_can_skb(dev->netdev, &cf); + if (!skb) + return; - cf->can_id = le32_to_cpu(hf->can_id); + cf->can_id = le32_to_cpu(hf->can_id); + can_frame_set_cc_len(cf, hf->can_dlc, dev->can.ctrlmode); - can_frame_set_cc_len(cf, hf->can_dlc, dev->can.ctrlmode); - memcpy(cf->data, hf->data, 8); + memcpy(cf->data, hf->classic_can->data, 8); - /* ERROR frames tell us information about the controller */ - if (le32_to_cpu(hf->can_id) & CAN_ERR_FLAG) - gs_update_state(dev, cf); + /* ERROR frames tell us information about the controller */ + if (le32_to_cpu(hf->can_id) & CAN_ERR_FLAG) + gs_update_state(dev, cf); + } netdev->stats.rx_packets++; netdev->stats.rx_bytes += hf->can_dlc; @@ -392,14 +488,10 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) } resubmit_urb: - usb_fill_bulk_urb(urb, - usbcan->udev, + usb_fill_bulk_urb(urb, usbcan->udev, usb_rcvbulkpipe(usbcan->udev, GSUSB_ENDPOINT_IN), - hf, - sizeof(struct gs_host_frame), - gs_usb_receive_bulk_callback, - usbcan - ); + hf, dev->parent->hf_size_rx, + gs_usb_receive_bulk_callback, usbcan); rc = usb_submit_urb(urb, GFP_ATOMIC); @@ -436,11 +528,7 @@ static int gs_usb_set_bittiming(struct net_device *netdev) usb_sndctrlpipe(interface_to_usbdev(intf), 0), GS_USB_BREQ_BITTIMING, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, - dev->channel, - 0, - dbt, - sizeof(*dbt), - 1000); + dev->channel, 0, dbt, sizeof(*dbt), 1000); kfree(dbt); @@ -451,6 +539,44 @@ static int gs_usb_set_bittiming(struct net_device *netdev) return (rc > 0) ? 0 : rc; } +static int gs_usb_set_data_bittiming(struct net_device *netdev) +{ + struct gs_can *dev = netdev_priv(netdev); + struct can_bittiming *bt = &dev->can.data_bittiming; + struct usb_interface *intf = dev->iface; + struct gs_device_bittiming *dbt; + u8 request = GS_USB_BREQ_DATA_BITTIMING; + int rc; + + dbt = kmalloc(sizeof(*dbt), GFP_KERNEL); + if (!dbt) + return -ENOMEM; + + dbt->prop_seg = cpu_to_le32(bt->prop_seg); + dbt->phase_seg1 = cpu_to_le32(bt->phase_seg1); + dbt->phase_seg2 = cpu_to_le32(bt->phase_seg2); + dbt->sjw = cpu_to_le32(bt->sjw); + dbt->brp = cpu_to_le32(bt->brp); + + if (dev->feature & GS_CAN_FEATURE_QUIRK_BREQ_CANTACT_PRO) + request = GS_USB_BREQ_QUIRK_CANTACT_PRO_DATA_BITTIMING; + + /* request bit timings */ + rc = usb_control_msg(interface_to_usbdev(intf), + usb_sndctrlpipe(interface_to_usbdev(intf), 0), + request, + USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, + dev->channel, 0, dbt, sizeof(*dbt), 1000); + + kfree(dbt); + + if (rc < 0) + dev_err(netdev->dev.parent, + "Couldn't set data bittimings (err=%d)", rc); + + return (rc > 0) ? 0 : rc; +} + static void gs_usb_xmit_callback(struct urb *urb) { struct gs_tx_context *txc = urb->context; @@ -460,10 +586,8 @@ static void gs_usb_xmit_callback(struct urb *urb) if (urb->status) netdev_info(netdev, "usb xmit fail %u\n", txc->echo_id); - usb_free_coherent(urb->dev, - urb->transfer_buffer_length, - urb->transfer_buffer, - urb->transfer_dma); + usb_free_coherent(urb->dev, urb->transfer_buffer_length, + urb->transfer_buffer, urb->transfer_dma); } static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, @@ -474,6 +598,7 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, struct urb *urb; struct gs_host_frame *hf; struct can_frame *cf; + struct canfd_frame *cfd; int rc; unsigned int idx; struct gs_tx_context *txc; @@ -491,7 +616,7 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, if (!urb) goto nomem_urb; - hf = usb_alloc_coherent(dev->udev, sizeof(*hf), GFP_ATOMIC, + hf = usb_alloc_coherent(dev->udev, dev->hf_size_tx, GFP_ATOMIC, &urb->transfer_dma); if (!hf) { netdev_err(netdev, "No memory left for USB buffer\n"); @@ -510,19 +635,31 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, hf->flags = 0; hf->reserved = 0; - cf = (struct can_frame *)skb->data; + if (can_is_canfd_skb(skb)) { + cfd = (struct canfd_frame *)skb->data; - hf->can_id = cpu_to_le32(cf->can_id); - hf->can_dlc = can_get_cc_dlc(cf, dev->can.ctrlmode); + hf->can_id = cpu_to_le32(cfd->can_id); + hf->can_dlc = can_fd_len2dlc(cfd->len); + hf->flags |= GS_CAN_FLAG_FD; + if (cfd->flags & CANFD_BRS) + hf->flags |= GS_CAN_FLAG_BRS; + if (cfd->flags & CANFD_ESI) + hf->flags |= GS_CAN_FLAG_ESI; - memcpy(hf->data, cf->data, cf->len); + memcpy(hf->canfd->data, cfd->data, cfd->len); + } else { + cf = (struct can_frame *)skb->data; + + hf->can_id = cpu_to_le32(cf->can_id); + hf->can_dlc = can_get_cc_dlc(cf, dev->can.ctrlmode); + + memcpy(hf->classic_can->data, cf->data, cf->len); + } usb_fill_bulk_urb(urb, dev->udev, usb_sndbulkpipe(dev->udev, GSUSB_ENDPOINT_OUT), - hf, - sizeof(*hf), - gs_usb_xmit_callback, - txc); + hf, dev->hf_size_tx, + gs_usb_xmit_callback, txc); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; usb_anchor_urb(urb, &dev->tx_submitted); @@ -539,10 +676,8 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, gs_free_tx_context(txc); usb_unanchor_urb(urb); - usb_free_coherent(dev->udev, - sizeof(*hf), - hf, - urb->transfer_dma); + usb_free_coherent(dev->udev, urb->transfer_buffer_length, + urb->transfer_buffer, urb->transfer_dma); if (rc == -ENODEV) { netif_device_detach(netdev); @@ -562,10 +697,8 @@ static netdev_tx_t gs_can_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; badidx: - usb_free_coherent(dev->udev, - sizeof(*hf), - hf, - urb->transfer_dma); + usb_free_coherent(dev->udev, urb->transfer_buffer_length, + urb->transfer_buffer, urb->transfer_dma); nomem_hf: usb_free_urb(urb); @@ -582,6 +715,7 @@ static int gs_can_open(struct net_device *netdev) struct gs_usb *parent = dev->parent; int rc, i; struct gs_device_mode *dm; + struct gs_host_frame *hf; u32 ctrlmode; u32 flags = 0; @@ -589,6 +723,21 @@ static int gs_can_open(struct net_device *netdev) if (rc) return rc; + ctrlmode = dev->can.ctrlmode; + if (ctrlmode & CAN_CTRLMODE_FD) { + flags |= GS_CAN_MODE_FD; + + if (dev->feature & GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX) + dev->hf_size_tx = struct_size(hf, canfd_quirk, 1); + else + dev->hf_size_tx = struct_size(hf, canfd, 1); + } else { + if (dev->feature & GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX) + dev->hf_size_tx = struct_size(hf, classic_can_quirk, 1); + else + dev->hf_size_tx = struct_size(hf, classic_can, 1); + } + if (!parent->active_channels) { for (i = 0; i < GS_MAX_RX_URBS; i++) { struct urb *urb; @@ -601,7 +750,7 @@ static int gs_can_open(struct net_device *netdev) /* alloc rx buffer */ buf = usb_alloc_coherent(dev->udev, - sizeof(struct gs_host_frame), + dev->parent->hf_size_rx, GFP_KERNEL, &urb->transfer_dma); if (!buf) { @@ -617,9 +766,8 @@ static int gs_can_open(struct net_device *netdev) usb_rcvbulkpipe(dev->udev, GSUSB_ENDPOINT_IN), buf, - sizeof(struct gs_host_frame), - gs_usb_receive_bulk_callback, - parent); + dev->parent->hf_size_rx, + gs_usb_receive_bulk_callback, parent); urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP; usb_anchor_urb(urb, &parent->rx_submitted); @@ -630,8 +778,7 @@ static int gs_can_open(struct net_device *netdev) netif_device_detach(dev->netdev); netdev_err(netdev, - "usb_submit failed (err=%d)\n", - rc); + "usb_submit failed (err=%d)\n", rc); usb_unanchor_urb(urb); usb_free_urb(urb); @@ -650,8 +797,6 @@ static int gs_can_open(struct net_device *netdev) return -ENOMEM; /* flags */ - ctrlmode = dev->can.ctrlmode; - if (ctrlmode & CAN_CTRLMODE_LOOPBACK) flags |= GS_CAN_MODE_LOOP_BACK; else if (ctrlmode & CAN_CTRLMODE_LISTENONLY) @@ -672,13 +817,8 @@ static int gs_can_open(struct net_device *netdev) rc = usb_control_msg(interface_to_usbdev(dev->iface), usb_sndctrlpipe(interface_to_usbdev(dev->iface), 0), GS_USB_BREQ_MODE, - USB_DIR_OUT | USB_TYPE_VENDOR | - USB_RECIP_INTERFACE, - dev->channel, - 0, - dm, - sizeof(*dm), - 1000); + USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, + dev->channel, 0, dm, sizeof(*dm), 1000); if (rc < 0) { netdev_err(netdev, "Couldn't start device (err=%d)\n", rc); @@ -755,16 +895,10 @@ static int gs_usb_set_identify(struct net_device *netdev, bool do_identify) imode->mode = cpu_to_le32(GS_CAN_IDENTIFY_OFF); rc = usb_control_msg(interface_to_usbdev(dev->iface), - usb_sndctrlpipe(interface_to_usbdev(dev->iface), - 0), + usb_sndctrlpipe(interface_to_usbdev(dev->iface), 0), GS_USB_BREQ_IDENTIFY, - USB_DIR_OUT | USB_TYPE_VENDOR | - USB_RECIP_INTERFACE, - dev->channel, - 0, - imode, - sizeof(*imode), - 100); + USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, + dev->channel, 0, imode, sizeof(*imode), 100); kfree(imode); @@ -803,6 +937,7 @@ static struct gs_can *gs_make_candev(unsigned int channel, struct net_device *netdev; int rc; struct gs_device_bt_const *bt_const; + struct gs_device_bt_const_extended *bt_const_extended; u32 feature; bt_const = kmalloc(sizeof(*bt_const), GFP_KERNEL); @@ -814,11 +949,7 @@ static struct gs_can *gs_make_candev(unsigned int channel, usb_rcvctrlpipe(interface_to_usbdev(intf), 0), GS_USB_BREQ_BT_CONST, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, - channel, - 0, - bt_const, - sizeof(*bt_const), - 1000); + channel, 0, bt_const, sizeof(*bt_const), 1000); if (rc < 0) { dev_err(&intf->dev, @@ -875,6 +1006,7 @@ static struct gs_can *gs_make_candev(unsigned int channel, dev->can.ctrlmode_supported = CAN_CTRLMODE_CC_LEN8_DLC; feature = le32_to_cpu(bt_const->feature); + dev->feature = FIELD_GET(GS_CAN_FEATURE_MASK, feature); if (feature & GS_CAN_FEATURE_LISTEN_ONLY) dev->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY; @@ -887,7 +1019,37 @@ static struct gs_can *gs_make_candev(unsigned int channel, if (feature & GS_CAN_FEATURE_ONE_SHOT) dev->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT; - SET_NETDEV_DEV(netdev, &intf->dev); + if (feature & GS_CAN_FEATURE_FD) { + dev->can.ctrlmode_supported |= CAN_CTRLMODE_FD; + /* The data bit timing will be overwritten, if + * GS_CAN_FEATURE_BT_CONST_EXT is set. + */ + dev->can.data_bittiming_const = &dev->bt_const; + dev->can.do_set_data_bittiming = gs_usb_set_data_bittiming; + } + + /* The CANtact Pro from LinkLayer Labs is based on the + * LPC54616 µC, which is affected by the NXP LPC USB transfer + * erratum. However, the current firmware (version 2) doesn't + * set the GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX bit. Set the + * feature GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX to workaround + * this issue. + * + * For the GS_USB_BREQ_DATA_BITTIMING USB control message the + * CANtact Pro firmware uses a request value, which is already + * used by the candleLight firmware for a different purpose + * (GS_USB_BREQ_GET_USER_ID). Set the feature + * GS_CAN_FEATURE_QUIRK_BREQ_CANTACT_PRO to workaround this + * issue. + */ + if (dev->udev->descriptor.idVendor == cpu_to_le16(USB_GSUSB_1_VENDOR_ID) && + dev->udev->descriptor.idProduct == cpu_to_le16(USB_GSUSB_1_PRODUCT_ID) && + dev->udev->manufacturer && dev->udev->product && + !strcmp(dev->udev->manufacturer, "LinkLayer Labs") && + !strcmp(dev->udev->product, "CANtact Pro") && + (le32_to_cpu(dconf->sw_version) <= 2)) + dev->feature |= GS_CAN_FEATURE_REQ_USB_QUIRK_LPC546XX | + GS_CAN_FEATURE_QUIRK_BREQ_CANTACT_PRO; if (le32_to_cpu(dconf->sw_version) > 1) if (feature & GS_CAN_FEATURE_IDENTIFY) @@ -895,6 +1057,45 @@ static struct gs_can *gs_make_candev(unsigned int channel, kfree(bt_const); + /* fetch extended bit timing constants if device has feature + * GS_CAN_FEATURE_FD and GS_CAN_FEATURE_BT_CONST_EXT + */ + if (feature & GS_CAN_FEATURE_FD && + feature & GS_CAN_FEATURE_BT_CONST_EXT) { + bt_const_extended = kmalloc(sizeof(*bt_const_extended), GFP_KERNEL); + if (!bt_const_extended) + return ERR_PTR(-ENOMEM); + + rc = usb_control_msg(interface_to_usbdev(intf), + usb_rcvctrlpipe(interface_to_usbdev(intf), 0), + GS_USB_BREQ_BT_CONST_EXT, + USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, + channel, 0, bt_const_extended, + sizeof(*bt_const_extended), + 1000); + if (rc < 0) { + dev_err(&intf->dev, + "Couldn't get extended bit timing const for channel (err=%d)\n", + rc); + kfree(bt_const_extended); + return ERR_PTR(rc); + } + + strcpy(dev->data_bt_const.name, "gs_usb"); + dev->data_bt_const.tseg1_min = le32_to_cpu(bt_const_extended->dtseg1_min); + dev->data_bt_const.tseg1_max = le32_to_cpu(bt_const_extended->dtseg1_max); + dev->data_bt_const.tseg2_min = le32_to_cpu(bt_const_extended->dtseg2_min); + dev->data_bt_const.tseg2_max = le32_to_cpu(bt_const_extended->dtseg2_max); + dev->data_bt_const.sjw_max = le32_to_cpu(bt_const_extended->dsjw_max); + dev->data_bt_const.brp_min = le32_to_cpu(bt_const_extended->dbrp_min); + dev->data_bt_const.brp_max = le32_to_cpu(bt_const_extended->dbrp_max); + dev->data_bt_const.brp_inc = le32_to_cpu(bt_const_extended->dbrp_inc); + + dev->can.data_bittiming_const = &dev->data_bt_const; + } + + SET_NETDEV_DEV(netdev, &intf->dev); + rc = register_candev(dev->netdev); if (rc) { free_candev(dev->netdev); @@ -915,6 +1116,8 @@ static void gs_destroy_candev(struct gs_can *dev) static int gs_usb_probe(struct usb_interface *intf, const struct usb_device_id *id) { + struct usb_device *udev = interface_to_usbdev(intf); + struct gs_host_frame *hf; struct gs_usb *dev; int rc = -ENOMEM; unsigned int icount, i; @@ -928,21 +1131,16 @@ static int gs_usb_probe(struct usb_interface *intf, hconf->byte_order = cpu_to_le32(0x0000beef); /* send host config */ - rc = usb_control_msg(interface_to_usbdev(intf), - usb_sndctrlpipe(interface_to_usbdev(intf), 0), + rc = usb_control_msg(udev, usb_sndctrlpipe(udev, 0), GS_USB_BREQ_HOST_FORMAT, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, - 1, - intf->cur_altsetting->desc.bInterfaceNumber, - hconf, - sizeof(*hconf), - 1000); + 1, intf->cur_altsetting->desc.bInterfaceNumber, + hconf, sizeof(*hconf), 1000); kfree(hconf); if (rc < 0) { - dev_err(&intf->dev, "Couldn't send data format (err=%d)\n", - rc); + dev_err(&intf->dev, "Couldn't send data format (err=%d)\n", rc); return rc; } @@ -951,15 +1149,11 @@ static int gs_usb_probe(struct usb_interface *intf, return -ENOMEM; /* read device config */ - rc = usb_control_msg(interface_to_usbdev(intf), - usb_rcvctrlpipe(interface_to_usbdev(intf), 0), + rc = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), GS_USB_BREQ_DEVICE_CONFIG, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, - 1, - intf->cur_altsetting->desc.bInterfaceNumber, - dconf, - sizeof(*dconf), - 1000); + 1, intf->cur_altsetting->desc.bInterfaceNumber, + dconf, sizeof(*dconf), 1000); if (rc < 0) { dev_err(&intf->dev, "Couldn't get device config: (err=%d)\n", rc); @@ -985,9 +1179,13 @@ static int gs_usb_probe(struct usb_interface *intf, } init_usb_anchor(&dev->rx_submitted); + /* default to classic CAN, switch to CAN-FD if at least one of + * our channels support CAN-FD. + */ + dev->hf_size_rx = struct_size(hf, classic_can, 1); usb_set_intfdata(intf, dev); - dev->udev = interface_to_usbdev(intf); + dev->udev = udev; for (i = 0; i < icount; i++) { dev->canch[i] = gs_make_candev(i, intf, dconf); @@ -1006,6 +1204,9 @@ static int gs_usb_probe(struct usb_interface *intf, return rc; } dev->canch[i]->parent = dev; + + if (dev->canch[i]->can.ctrlmode_supported & CAN_CTRLMODE_FD) + dev->hf_size_rx = struct_size(hf, canfd, 1); } kfree(dconf); @@ -1015,8 +1216,9 @@ static int gs_usb_probe(struct usb_interface *intf, static void gs_usb_disconnect(struct usb_interface *intf) { - unsigned i; struct gs_usb *dev = usb_get_intfdata(intf); + unsigned int i; + usb_set_intfdata(intf, NULL); if (!dev) { @@ -1037,16 +1239,20 @@ static const struct usb_device_id gs_usb_table[] = { USB_GSUSB_1_PRODUCT_ID, 0) }, { USB_DEVICE_INTERFACE_NUMBER(USB_CANDLELIGHT_VENDOR_ID, USB_CANDLELIGHT_PRODUCT_ID, 0) }, + { USB_DEVICE_INTERFACE_NUMBER(USB_CES_CANEXT_FD_VENDOR_ID, + USB_CES_CANEXT_FD_PRODUCT_ID, 0) }, + { USB_DEVICE_INTERFACE_NUMBER(USB_ABE_CANDEBUGGER_FD_VENDOR_ID, + USB_ABE_CANDEBUGGER_FD_PRODUCT_ID, 0) }, {} /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, gs_usb_table); static struct usb_driver gs_usb_driver = { - .name = "gs_usb", - .probe = gs_usb_probe, + .name = "gs_usb", + .probe = gs_usb_probe, .disconnect = gs_usb_disconnect, - .id_table = gs_usb_table, + .id_table = gs_usb_table, }; module_usb_driver(gs_usb_driver); diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c index 556f1a12ec9a..94a0c9c6a509 100644 --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@ -33,28 +33,33 @@ struct vxcan_priv { struct net_device __rcu *peer; }; -static netdev_tx_t vxcan_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t vxcan_xmit(struct sk_buff *oskb, struct net_device *dev) { struct vxcan_priv *priv = netdev_priv(dev); struct net_device *peer; - struct canfd_frame *cfd = (struct canfd_frame *)skb->data; + struct canfd_frame *cfd = (struct canfd_frame *)oskb->data; struct net_device_stats *peerstats, *srcstats = &dev->stats; + struct sk_buff *skb; u8 len; - if (can_dropped_invalid_skb(dev, skb)) + if (can_dropped_invalid_skb(dev, oskb)) return NETDEV_TX_OK; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (unlikely(!peer)) { - kfree_skb(skb); + kfree_skb(oskb); dev->stats.tx_dropped++; goto out_unlock; } - skb = can_create_echo_skb(skb); - if (!skb) + skb = skb_clone(oskb, GFP_ATOMIC); + if (skb) { + consume_skb(oskb); + } else { + kfree(oskb); goto out_unlock; + } /* reset CAN GW hop counter */ skb->csum_start = 0; @@ -148,7 +153,7 @@ static void vxcan_setup(struct net_device *dev) dev->hard_header_len = 0; dev->addr_len = 0; dev->tx_queue_len = 0; - dev->flags = (IFF_NOARP|IFF_ECHO); + dev->flags = IFF_NOARP; dev->netdev_ops = &vxcan_netdev_ops; dev->needs_free_netdev = true; diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index a8bd233f3cb9..a416240d001b 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -213,6 +213,7 @@ #define GSWIP_MAC_CTRL_0_GMII_MII 0x0001 #define GSWIP_MAC_CTRL_0_GMII_RGMII 0x0002 #define GSWIP_MAC_CTRL_2p(p) (0x905 + ((p) * 0xC)) +#define GSWIP_MAC_CTRL_2_LCHKL BIT(2) /* Frame Length Check Long Enable */ #define GSWIP_MAC_CTRL_2_MLEN BIT(3) /* Maximum Untagged Frame Lnegth */ /* Ethernet Switch Fetch DMA Port Control Register */ @@ -239,6 +240,15 @@ #define XRX200_GPHY_FW_ALIGN (16 * 1024) +/* Maximum packet size supported by the switch. In theory this should be 10240, + * but long packets currently cause lock-ups with an MTU of over 2526. Medium + * packets are sometimes dropped (e.g. TCP over 2477, UDP over 2516-2519, ICMP + * over 2526), hence an MTU value of 2400 seems safe. This issue only affects + * packet reception. This is probably caused by the PPA engine, which is on the + * RX part of the device. Packet transmission works properly up to 10240. + */ +#define GSWIP_MAX_PACKET_LENGTH 2400 + struct gswip_hw_info { int max_ports; int cpu_port; @@ -863,10 +873,6 @@ static int gswip_setup(struct dsa_switch *ds) gswip_switch_mask(priv, 0, GSWIP_PCE_PCTRL_0_INGRESS, GSWIP_PCE_PCTRL_0p(cpu_port)); - gswip_switch_mask(priv, 0, GSWIP_MAC_CTRL_2_MLEN, - GSWIP_MAC_CTRL_2p(cpu_port)); - gswip_switch_w(priv, VLAN_ETH_FRAME_LEN + 8 + ETH_FCS_LEN, - GSWIP_MAC_FLEN); gswip_switch_mask(priv, 0, GSWIP_BM_QUEUE_GCTRL_GL_MOD, GSWIP_BM_QUEUE_GCTRL); @@ -883,6 +889,8 @@ static int gswip_setup(struct dsa_switch *ds) return err; } + ds->mtu_enforcement_ingress = true; + gswip_port_enable(ds, cpu_port, NULL); ds->configure_vlan_while_not_filtering = false; @@ -1449,6 +1457,39 @@ static int gswip_port_fdb_dump(struct dsa_switch *ds, int port, return 0; } +static int gswip_port_max_mtu(struct dsa_switch *ds, int port) +{ + /* Includes 8 bytes for special header. */ + return GSWIP_MAX_PACKET_LENGTH - VLAN_ETH_HLEN - ETH_FCS_LEN; +} + +static int gswip_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) +{ + struct gswip_priv *priv = ds->priv; + int cpu_port = priv->hw_info->cpu_port; + + /* CPU port always has maximum mtu of user ports, so use it to set + * switch frame size, including 8 byte special header. + */ + if (port == cpu_port) { + new_mtu += 8; + gswip_switch_w(priv, VLAN_ETH_HLEN + new_mtu + ETH_FCS_LEN, + GSWIP_MAC_FLEN); + } + + /* Enable MLEN for ports with non-standard MTUs, including the special + * header on the CPU port added above. + */ + if (new_mtu != ETH_DATA_LEN) + gswip_switch_mask(priv, 0, GSWIP_MAC_CTRL_2_MLEN, + GSWIP_MAC_CTRL_2p(port)); + else + gswip_switch_mask(priv, GSWIP_MAC_CTRL_2_MLEN, 0, + GSWIP_MAC_CTRL_2p(port)); + + return 0; +} + static void gswip_xrx200_phylink_get_caps(struct dsa_switch *ds, int port, struct phylink_config *config) { @@ -1794,6 +1835,8 @@ static const struct dsa_switch_ops gswip_xrx200_switch_ops = { .port_fdb_add = gswip_port_fdb_add, .port_fdb_del = gswip_port_fdb_del, .port_fdb_dump = gswip_port_fdb_dump, + .port_change_mtu = gswip_port_change_mtu, + .port_max_mtu = gswip_port_max_mtu, .phylink_get_caps = gswip_xrx200_phylink_get_caps, .phylink_mac_config = gswip_phylink_mac_config, .phylink_mac_link_down = gswip_phylink_mac_link_down, @@ -1818,6 +1861,8 @@ static const struct dsa_switch_ops gswip_xrx300_switch_ops = { .port_fdb_add = gswip_port_fdb_add, .port_fdb_del = gswip_port_fdb_del, .port_fdb_dump = gswip_port_fdb_dump, + .port_change_mtu = gswip_port_change_mtu, + .port_max_mtu = gswip_port_max_mtu, .phylink_get_caps = gswip_xrx300_phylink_get_caps, .phylink_mac_config = gswip_phylink_mac_config, .phylink_mac_link_down = gswip_phylink_mac_link_down, diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 94ad6d9504f4..a4699481c746 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -11,6 +11,7 @@ #include <linux/platform_data/microchip-ksz.h> #include <linux/phy.h> #include <linux/if_bridge.h> +#include <linux/if_vlan.h> #include <net/dsa.h> #include <net/switchdev.h> @@ -182,6 +183,29 @@ static void ksz9477_port_cfg32(struct ksz_device *dev, int port, int offset, bits, set ? bits : 0); } +static int ksz9477_change_mtu(struct dsa_switch *ds, int port, int mtu) +{ + struct ksz_device *dev = ds->priv; + u16 frame_size, max_frame = 0; + int i; + + frame_size = mtu + VLAN_ETH_HLEN + ETH_FCS_LEN; + + /* Cache the per-port MTU setting */ + dev->ports[port].max_frame = frame_size; + + for (i = 0; i < dev->port_cnt; i++) + max_frame = max(max_frame, dev->ports[i].max_frame); + + return regmap_update_bits(dev->regmap[1], REG_SW_MTU__2, + REG_SW_MTU_MASK, max_frame); +} + +static int ksz9477_max_mtu(struct dsa_switch *ds, int port) +{ + return KSZ9477_MAX_FRAME_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN; +} + static int ksz9477_wait_vlan_ctrl_ready(struct ksz_device *dev) { unsigned int val; @@ -1416,8 +1440,14 @@ static int ksz9477_setup(struct dsa_switch *ds) /* Do not work correctly with tail tagging. */ ksz_cfg(dev, REG_SW_MAC_CTRL_0, SW_CHECK_LENGTH, false); - /* accept packet up to 2000bytes */ - ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_LEGAL_PACKET_DISABLE, true); + /* Enable REG_SW_MTU__2 reg by setting SW_JUMBO_PACKET */ + ksz_cfg(dev, REG_SW_MAC_CTRL_1, SW_JUMBO_PACKET, true); + + /* Now we can configure default MTU value */ + ret = regmap_update_bits(dev->regmap[1], REG_SW_MTU__2, REG_SW_MTU_MASK, + VLAN_ETH_FRAME_LEN + ETH_FCS_LEN); + if (ret) + return ret; ksz9477_config_cpu_port(ds); @@ -1464,6 +1494,8 @@ static const struct dsa_switch_ops ksz9477_switch_ops = { .port_mirror_add = ksz9477_port_mirror_add, .port_mirror_del = ksz9477_port_mirror_del, .get_stats64 = ksz9477_get_stats64, + .port_change_mtu = ksz9477_change_mtu, + .port_max_mtu = ksz9477_max_mtu, }; static u32 ksz9477_get_port_addr(int port, int offset) diff --git a/drivers/net/dsa/microchip/ksz9477_reg.h b/drivers/net/dsa/microchip/ksz9477_reg.h index 16939f29faa5..0bd58467181f 100644 --- a/drivers/net/dsa/microchip/ksz9477_reg.h +++ b/drivers/net/dsa/microchip/ksz9477_reg.h @@ -176,6 +176,7 @@ #define REG_SW_MAC_ADDR_5 0x0307 #define REG_SW_MTU__2 0x0308 +#define REG_SW_MTU_MASK GENMASK(13, 0) #define REG_SW_ISP_TPID__2 0x030A @@ -1662,4 +1663,6 @@ /* 148,800 frames * 67 ms / 100 */ #define BROADCAST_STORM_VALUE 9969 +#define KSZ9477_MAX_FRAME_SIZE 9000 + #endif /* KSZ9477_REGS_H */ diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 4ff0a159ce3c..fa39ee73cbd2 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -41,6 +41,7 @@ struct ksz_port { struct ksz_port_mib mib; phy_interface_t interface; + u16 max_frame; }; struct ksz_device { 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/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 63b8fc4f9d42..2de02950086f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2061,22 +2061,6 @@ static void bnxt_event_error_report(struct bnxt *bp, u32 data1, u32 data2) case ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD: netdev_warn(bp->dev, "One or more MMIO doorbells dropped by the device!\n"); break; - case ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM: { - struct bnxt_hw_health *hw_health = &bp->hw_health; - - hw_health->nvm_err_address = EVENT_DATA2_NVM_ERR_ADDR(data2); - if (EVENT_DATA1_NVM_ERR_TYPE_WRITE(data1)) { - hw_health->synd = BNXT_HW_STATUS_NVM_WRITE_ERR; - hw_health->nvm_write_errors++; - } else if (EVENT_DATA1_NVM_ERR_TYPE_ERASE(data1)) { - hw_health->synd = BNXT_HW_STATUS_NVM_ERASE_ERR; - hw_health->nvm_erase_errors++; - } else { - hw_health->synd = BNXT_HW_STATUS_NVM_UNKNOWN_ERR; - } - set_bit(BNXT_FW_NVM_ERR_SP_EVENT, &bp->sp_event); - break; - } default: netdev_err(bp->dev, "FW reported unknown error type %u\n", err_type); @@ -11903,9 +11887,6 @@ static void bnxt_sp_task(struct work_struct *work) if (test_and_clear_bit(BNXT_FW_ECHO_REQUEST_SP_EVENT, &bp->sp_event)) bnxt_fw_echo_reply(bp); - if (test_and_clear_bit(BNXT_FW_NVM_ERR_SP_EVENT, &bp->sp_event)) - bnxt_devlink_health_hw_report(bp); - /* These functions below will clear BNXT_STATE_IN_SP_TASK. They * must be the last functions to be called before exiting. */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 9dd878def3c2..447a9406b8a2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -516,21 +516,6 @@ struct rx_tpa_end_cmp_ext { ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_MASK) >>\ ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_SFT) -#define EVENT_DATA2_NVM_ERR_ADDR(data2) \ - (((data2) & \ - ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_MASK) >>\ - ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_SFT) - -#define EVENT_DATA1_NVM_ERR_TYPE_WRITE(data1) \ - (((data1) & \ - ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_MASK) ==\ - ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_WRITE) - -#define EVENT_DATA1_NVM_ERR_TYPE_ERASE(data1) \ - (((data1) & \ - ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_MASK) ==\ - ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE) - struct nqe_cn { __le16 type; #define NQ_CN_TYPE_MASK 0x3fUL @@ -1543,33 +1528,6 @@ struct bnxt_ctx_mem_info { struct bnxt_mem_init mem_init[BNXT_CTX_MEM_INIT_MAX]; }; -enum bnxt_hw_err { - BNXT_HW_STATUS_HEALTHY = 0x0, - BNXT_HW_STATUS_NVM_WRITE_ERR = 0x1, - BNXT_HW_STATUS_NVM_ERASE_ERR = 0x2, - BNXT_HW_STATUS_NVM_UNKNOWN_ERR = 0x3, - BNXT_HW_STATUS_NVM_TEST_VPD_ENT_ERR = 0x4, - BNXT_HW_STATUS_NVM_TEST_VPD_READ_ERR = 0x5, - BNXT_HW_STATUS_NVM_TEST_VPD_WRITE_ERR = 0x6, - BNXT_HW_STATUS_NVM_TEST_INCMPL_ERR = 0x7, -}; - -struct bnxt_hw_health { - u32 nvm_err_address; - u32 nvm_write_errors; - u32 nvm_erase_errors; - u32 nvm_test_vpd_ent_errors; - u32 nvm_test_vpd_read_errors; - u32 nvm_test_vpd_write_errors; - u32 nvm_test_incmpl_errors; - u8 synd; - /* max a test in a day if previous test was successful */ -#define HW_RETEST_MIN_TIME (1000 * 3600 * 24) - u8 nvm_test_result; - unsigned long nvm_test_timestamp; - struct devlink_health_reporter *hw_reporter; -}; - enum bnxt_health_severity { SEVERITY_NORMAL = 0, SEVERITY_WARNING, @@ -2087,7 +2045,6 @@ struct bnxt { #define BNXT_FW_EXCEPTION_SP_EVENT 19 #define BNXT_LINK_CFG_CHANGE_SP_EVENT 21 #define BNXT_FW_ECHO_REQUEST_SP_EVENT 23 -#define BNXT_FW_NVM_ERR_SP_EVENT 25 struct delayed_work fw_reset_task; int fw_reset_state; @@ -2188,8 +2145,6 @@ struct bnxt { struct dentry *debugfs_pdev; struct device *hwmon_dev; enum board_idx board_idx; - - struct bnxt_hw_health hw_health; }; #define BNXT_NUM_RX_RING_STATS 8 diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 77e55105d645..0c17f90d44a2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -20,7 +20,6 @@ #include "bnxt_ulp.h" #include "bnxt_ptp.h" #include "bnxt_coredump.h" -#include "bnxt_nvm_defs.h" /* NVRAM content constant and structure defs */ static void __bnxt_fw_recover(struct bnxt *bp) { @@ -242,148 +241,6 @@ static const struct devlink_health_reporter_ops bnxt_dl_fw_reporter_ops = { .recover = bnxt_fw_recover, }; -static int bnxt_hw_recover(struct devlink_health_reporter *reporter, - void *priv_ctx, - struct netlink_ext_ack *extack) -{ - struct bnxt *bp = devlink_health_reporter_priv(reporter); - struct bnxt_hw_health *hw_health = &bp->hw_health; - - hw_health->synd = BNXT_HW_STATUS_HEALTHY; - return 0; -} - -static const char *hw_err_str(u8 synd) -{ - switch (synd) { - case BNXT_HW_STATUS_HEALTHY: - return "healthy"; - case BNXT_HW_STATUS_NVM_WRITE_ERR: - return "nvm write error"; - case BNXT_HW_STATUS_NVM_ERASE_ERR: - return "nvm erase error"; - case BNXT_HW_STATUS_NVM_UNKNOWN_ERR: - return "unrecognized nvm error"; - case BNXT_HW_STATUS_NVM_TEST_VPD_ENT_ERR: - return "nvm test vpd entry error"; - case BNXT_HW_STATUS_NVM_TEST_VPD_READ_ERR: - return "nvm test vpd read error"; - case BNXT_HW_STATUS_NVM_TEST_VPD_WRITE_ERR: - return "nvm test vpd write error"; - case BNXT_HW_STATUS_NVM_TEST_INCMPL_ERR: - return "nvm test incomplete error"; - default: - return "unknown hw error"; - } -} - -static void bnxt_nvm_test(struct bnxt *bp) -{ - struct bnxt_hw_health *h = &bp->hw_health; - u32 datalen; - u16 index; - u8 *buf; - - if (!h->nvm_test_result) { - if (!h->nvm_test_timestamp || - time_after(jiffies, h->nvm_test_timestamp + - msecs_to_jiffies(HW_RETEST_MIN_TIME))) - h->nvm_test_timestamp = jiffies; - else - return; - } - - if (bnxt_find_nvram_item(bp->dev, BNX_DIR_TYPE_VPD, - BNX_DIR_ORDINAL_FIRST, BNX_DIR_EXT_NONE, - &index, NULL, &datalen) || !datalen) { - h->nvm_test_result = BNXT_HW_STATUS_NVM_TEST_VPD_ENT_ERR; - h->nvm_test_vpd_ent_errors++; - return; - } - - buf = kzalloc(datalen, GFP_KERNEL); - if (!buf) { - h->nvm_test_result = BNXT_HW_STATUS_NVM_TEST_INCMPL_ERR; - h->nvm_test_incmpl_errors++; - return; - } - - if (bnxt_get_nvram_item(bp->dev, index, 0, datalen, buf)) { - h->nvm_test_result = BNXT_HW_STATUS_NVM_TEST_VPD_READ_ERR; - h->nvm_test_vpd_read_errors++; - goto err; - } - - if (bnxt_flash_nvram(bp->dev, BNX_DIR_TYPE_VPD, BNX_DIR_ORDINAL_FIRST, - BNX_DIR_EXT_NONE, 0, 0, buf, datalen)) { - h->nvm_test_result = BNXT_HW_STATUS_NVM_TEST_VPD_WRITE_ERR; - h->nvm_test_vpd_write_errors++; - } - -err: - kfree(buf); -} - -static int bnxt_hw_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, - struct netlink_ext_ack *extack) -{ - struct bnxt *bp = devlink_health_reporter_priv(reporter); - struct bnxt_hw_health *h = &bp->hw_health; - u8 synd = h->synd; - int rc; - - bnxt_nvm_test(bp); - if (h->nvm_test_result) { - synd = h->nvm_test_result; - devlink_health_report(h->hw_reporter, hw_err_str(synd), NULL); - } - - rc = devlink_fmsg_string_pair_put(fmsg, "Status", hw_err_str(synd)); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "nvm_write_errors", h->nvm_write_errors); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "nvm_erase_errors", h->nvm_erase_errors); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "nvm_test_vpd_ent_errors", - h->nvm_test_vpd_ent_errors); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "nvm_test_vpd_read_errors", - h->nvm_test_vpd_read_errors); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "nvm_test_vpd_write_errors", - h->nvm_test_vpd_write_errors); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "nvm_test_incomplete_errors", - h->nvm_test_incmpl_errors); - if (rc) - return rc; - - return 0; -} - -void bnxt_devlink_health_hw_report(struct bnxt *bp) -{ - struct bnxt_hw_health *hw_health = &bp->hw_health; - - netdev_warn(bp->dev, "%s reported at address 0x%x\n", hw_err_str(hw_health->synd), - hw_health->nvm_err_address); - - devlink_health_report(hw_health->hw_reporter, hw_err_str(hw_health->synd), NULL); -} - -static const struct devlink_health_reporter_ops bnxt_dl_hw_reporter_ops = { - .name = "hw", - .diagnose = bnxt_hw_diagnose, - .recover = bnxt_hw_recover, -}; - static struct devlink_health_reporter * __bnxt_dl_reporter_create(struct bnxt *bp, const struct devlink_health_reporter_ops *ops) @@ -403,10 +260,6 @@ __bnxt_dl_reporter_create(struct bnxt *bp, void bnxt_dl_fw_reporters_create(struct bnxt *bp) { struct bnxt_fw_health *fw_health = bp->fw_health; - struct bnxt_hw_health *hw_health = &bp->hw_health; - - if (!hw_health->hw_reporter) - hw_health->hw_reporter = __bnxt_dl_reporter_create(bp, &bnxt_dl_hw_reporter_ops); if (fw_health && !fw_health->fw_reporter) fw_health->fw_reporter = __bnxt_dl_reporter_create(bp, &bnxt_dl_fw_reporter_ops); @@ -415,12 +268,6 @@ void bnxt_dl_fw_reporters_create(struct bnxt *bp) void bnxt_dl_fw_reporters_destroy(struct bnxt *bp) { struct bnxt_fw_health *fw_health = bp->fw_health; - struct bnxt_hw_health *hw_health = &bp->hw_health; - - if (hw_health->hw_reporter) { - devlink_health_reporter_destroy(hw_health->hw_reporter); - hw_health->hw_reporter = NULL; - } if (fw_health && fw_health->fw_reporter) { devlink_health_reporter_destroy(fw_health->fw_reporter); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 056962e4b177..b8105065367b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -74,7 +74,6 @@ enum bnxt_dl_version_type { void bnxt_devlink_health_fw_report(struct bnxt *bp); void bnxt_dl_health_fw_status_update(struct bnxt *bp, bool healthy); void bnxt_dl_health_fw_recovery_done(struct bnxt *bp); -void bnxt_devlink_health_hw_report(struct bnxt *bp); void bnxt_dl_fw_reporters_create(struct bnxt *bp); void bnxt_dl_fw_reporters_destroy(struct bnxt *bp); int bnxt_dl_register(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 178074795b27..22e965e18fbc 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -2168,10 +2168,14 @@ static void bnxt_print_admin_err(struct bnxt *bp) netdev_info(bp->dev, "PF does not have admin privileges to flash or reset the device\n"); } -int bnxt_flash_nvram(struct net_device *dev, u16 dir_type, - u16 dir_ordinal, u16 dir_ext, u16 dir_attr, - u32 dir_item_len, const u8 *data, - size_t data_len) +static int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal, + u16 ext, u16 *index, u32 *item_length, + u32 *data_length); + +static int bnxt_flash_nvram(struct net_device *dev, u16 dir_type, + u16 dir_ordinal, u16 dir_ext, u16 dir_attr, + u32 dir_item_len, const u8 *data, + size_t data_len) { struct bnxt *bp = netdev_priv(dev); struct hwrm_nvm_write_input *req; @@ -2495,48 +2499,6 @@ static int bnxt_flash_firmware_from_file(struct net_device *dev, return rc; } -static int nvm_update_err_to_stderr(struct net_device *dev, u8 result) -{ - switch (result) { - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TYPE_PARAMETER: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_INDEX_PARAMETER: - case NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_DATA_ERROR: - case NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_CHECKSUM_ERROR: - case NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_NOT_FOUND: - case NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED: - netdev_err(dev, "PKG install error : Data integrity on NVM\n"); - return -EINVAL; - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PREREQUISITE: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_FILE_HEADER: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_SIGNATURE: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_STREAM: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_LENGTH: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_MANIFEST: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TRAILER: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_CHECKSUM: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_ITEM_CHECKSUM: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DATA_LENGTH: - case NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DIRECTIVE: - case NVM_INSTALL_UPDATE_RESP_RESULT_DUPLICATE_ITEM: - case NVM_INSTALL_UPDATE_RESP_RESULT_ZERO_LENGTH_ITEM: - netdev_err(dev, "PKG install error : Invalid package\n"); - return -ENOPKG; - case NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_AUTHENTICATION_ERROR: - netdev_err(dev, "PKG install error : Authentication error\n"); - return -EPERM; - case NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_CHIP_REV: - case NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_DEVICE_ID: - case NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_VENDOR: - case NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_ID: - case NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_PLATFORM: - netdev_err(dev, "PKG install error : Invalid device\n"); - return -EOPNOTSUPP; - default: - netdev_err(dev, "PKG install error : Internal error\n"); - return -EIO; - } -} - #define BNXT_PKG_DMA_SIZE 0x40000 #define BNXT_NVM_MORE_FLAG (cpu_to_le16(NVM_MODIFY_REQ_FLAGS_BATCH_MODE)) #define BNXT_NVM_LAST_FLAG (cpu_to_le16(NVM_MODIFY_REQ_FLAGS_BATCH_LAST)) @@ -2691,7 +2653,7 @@ pkg_abort: if (resp->result) { netdev_err(dev, "PKG install error = %d, problem_item = %d\n", (s8)resp->result, (int)resp->problem_item); - rc = nvm_update_err_to_stderr(dev, resp->result); + rc = -ENOPKG; } if (rc == -EACCES) bnxt_print_admin_err(bp); @@ -2815,8 +2777,8 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data) return rc; } -int bnxt_get_nvram_item(struct net_device *dev, u32 index, u32 offset, - u32 length, u8 *data) +static int bnxt_get_nvram_item(struct net_device *dev, u32 index, u32 offset, + u32 length, u8 *data) { struct bnxt *bp = netdev_priv(dev); int rc; @@ -2850,9 +2812,9 @@ int bnxt_get_nvram_item(struct net_device *dev, u32 index, u32 offset, return rc; } -int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal, - u16 ext, u16 *index, u32 *item_length, - u32 *data_length) +static int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal, + u16 ext, u16 *index, u32 *item_length, + u32 *data_length) { struct hwrm_nvm_find_dir_entry_output *output; struct hwrm_nvm_find_dir_entry_input *req; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h index 2593e0049582..6aa44840f13a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h @@ -56,13 +56,6 @@ int bnxt_hwrm_firmware_reset(struct net_device *dev, u8 proc_type, int bnxt_flash_package_from_fw_obj(struct net_device *dev, const struct firmware *fw, u32 install_type); int bnxt_get_pkginfo(struct net_device *dev, char *ver, int size); -int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal, u16 ext, - u16 *index, u32 *item_length, u32 *data_length); -int bnxt_get_nvram_item(struct net_device *dev, u32 index, u32 offset, - u32 length, u8 *data); -int bnxt_flash_nvram(struct net_device *dev, u16 dir_type, u16 dir_ordinal, - u16 dir_ext, u16 dir_attr, u32 dir_item_len, - const u8 *data, size_t data_len); void bnxt_ethtool_init(struct bnxt *bp); void bnxt_ethtool_free(struct bnxt *bp); 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/fungible/funeth/funeth_ktls.h b/drivers/net/ethernet/fungible/funeth/funeth_ktls.h index 1b21cccf1278..9d6f2141a959 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_ktls.h +++ b/drivers/net/ethernet/fungible/funeth/funeth_ktls.h @@ -3,17 +3,16 @@ #ifndef _FUN_KTLS_H #define _FUN_KTLS_H -struct net_device; -struct funeth_priv; - -#ifdef CONFIG_TLS_DEVICE #include <net/tls.h> +struct funeth_priv; + struct fun_ktls_tx_ctx { __be64 tlsid; u32 next_seq; }; +#if IS_ENABLED(CONFIG_TLS_DEVICE) int fun_ktls_init(struct net_device *netdev); void fun_ktls_cleanup(struct funeth_priv *fp); diff --git a/drivers/net/ethernet/fungible/funeth/funeth_tx.c b/drivers/net/ethernet/fungible/funeth/funeth_tx.c index 46684afa97a0..ff6e29237253 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_tx.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_tx.c @@ -7,6 +7,7 @@ #include <linux/tcp.h> #include <uapi/linux/udp.h> #include "funeth.h" +#include "funeth_ktls.h" #include "funeth_txrx.h" #include "funeth_trace.h" #include "fun_queue.h" @@ -75,12 +76,10 @@ static __be16 tcp_hdr_doff_flags(const struct tcphdr *th) return *(__be16 *)&tcp_flag_word(th); } -#if IS_ENABLED(CONFIG_TLS_DEVICE) -#include "funeth_ktls.h" - static struct sk_buff *fun_tls_tx(struct sk_buff *skb, struct funeth_txq *q, unsigned int *tls_len) { +#if IS_ENABLED(CONFIG_TLS_DEVICE) const struct fun_ktls_tx_ctx *tls_ctx; u32 datalen, seq; @@ -108,8 +107,10 @@ static struct sk_buff *fun_tls_tx(struct sk_buff *skb, struct funeth_txq *q, FUN_QSTAT_INC(q, tx_tls_drops); return skb; -} +#else + return NULL; #endif +} /* Write as many descriptors as needed for the supplied skb starting at the * current producer location. The caller has made certain enough descriptors diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 0f0efee5fc8e..fd07c3679bb1 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -146,11 +146,11 @@ s32 e1000e_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) break; } if (!(mdic & E1000_MDIC_READY)) { - e_dbg("MDI Read did not complete\n"); + e_dbg("MDI Read PHY Reg Address %d did not complete\n", offset); return -E1000_ERR_PHY; } if (mdic & E1000_MDIC_ERROR) { - e_dbg("MDI Error\n"); + e_dbg("MDI Read PHY Reg Address %d Error\n", offset); return -E1000_ERR_PHY; } if (((mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT) != offset) { @@ -210,11 +210,11 @@ s32 e1000e_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) break; } if (!(mdic & E1000_MDIC_READY)) { - e_dbg("MDI Write did not complete\n"); + e_dbg("MDI Write PHY Reg Address %d did not complete\n", offset); return -E1000_ERR_PHY; } if (mdic & E1000_MDIC_ERROR) { - e_dbg("MDI Error\n"); + e_dbg("MDI Write PHY Red Address %d Error\n", offset); return -E1000_ERR_PHY; } if (((mdic & E1000_MDIC_REG_MASK) >> E1000_MDIC_REG_SHIFT) != offset) { 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 f9ebd6084474..23c39805a1b0 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 */ }; @@ -899,7 +900,16 @@ 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 ca22c60636b9..2694acb1aa01 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/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index a7170ab3af97..b94cca45eb78 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -103,6 +103,7 @@ mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o steering/dr_icm_pool.o steering/dr_buddy.o \ steering/dr_ste.o steering/dr_send.o \ steering/dr_ste_v0.o steering/dr_ste_v1.o \ + steering/dr_ste_v2.o \ steering/dr_cmd.o steering/dr_fw.o \ steering/dr_action.o steering/fs_dr.o \ steering/dr_dbg.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 823d5808d5a0..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) @@ -1543,7 +1544,7 @@ static void create_debugfs_files(struct mlx5_core_dev *dev) { struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - dbg->dbg_root = debugfs_create_dir("cmd", dev->priv.dbg_root); + dbg->dbg_root = debugfs_create_dir("cmd", mlx5_debugfs_get_dev_root(dev)); debugfs_create_file("in", 0400, dbg->dbg_root, dev, &dfops); debugfs_create_file("out", 0200, dbg->dbg_root, dev, &dfops); @@ -1877,16 +1878,38 @@ out_in: return err; } +static void cmd_status_log(struct mlx5_core_dev *dev, u16 opcode, u8 status, int err) +{ + struct mlx5_cmd_stats *stats; + + if (!err) + return; + + stats = &dev->cmd.stats[opcode]; + spin_lock_irq(&stats->lock); + stats->failed++; + if (err < 0) + stats->last_failed_errno = -err; + if (err == -EREMOTEIO) { + stats->failed_mbox_status++; + stats->last_failed_mbox_status = status; + } + spin_unlock_irq(&stats->lock); +} + /* preserve -EREMOTEIO for outbox.status != OK, otherwise return err as is */ -static int cmd_status_err(int err, void *out) +static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, void *out) { - if (err) /* -EREMOTEIO is preserved */ - return err == -EREMOTEIO ? -EIO : err; + u8 status = MLX5_GET(mbox_out, out, status); - if (MLX5_GET(mbox_out, out, status) != MLX5_CMD_STAT_OK) - return -EREMOTEIO; + if (err == -EREMOTEIO) /* -EREMOTEIO is preserved */ + err = -EIO; - return 0; + if (!err && status != MLX5_CMD_STAT_OK) + err = -EREMOTEIO; + + cmd_status_log(dev, opcode, status, err); + return err; } /** @@ -1910,8 +1933,10 @@ static int cmd_status_err(int err, void *out) int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size) { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false); + u16 opcode = MLX5_GET(mbox_in, in, opcode); - return cmd_status_err(err, out); + err = cmd_status_err(dev, err, opcode, out); + return err; } EXPORT_SYMBOL(mlx5_cmd_do); @@ -1954,8 +1979,9 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size) { int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true); + u16 opcode = MLX5_GET(mbox_in, in, opcode); - err = cmd_status_err(err, out); + err = cmd_status_err(dev, err, opcode, out); return mlx5_cmd_check(dev, err, in, out); } EXPORT_SYMBOL(mlx5_cmd_exec_polling); @@ -1991,7 +2017,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work) struct mlx5_async_ctx *ctx; ctx = work->ctx; - status = cmd_status_err(status, work->out); + status = cmd_status_err(ctx->dev, status, work->opcode, work->out); work->user_callback(status, work); if (atomic_dec_and_test(&ctx->num_inflight)) wake_up(&ctx->wait); @@ -2005,6 +2031,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, work->ctx = ctx; work->user_callback = callback; + work->opcode = MLX5_GET(mbox_in, in, opcode); work->out = out; if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) return -EIO; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index 10d195042ab5..d69bac93a83b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -99,26 +99,32 @@ void mlx5_unregister_debugfs(void) debugfs_remove(mlx5_debugfs_root); } +struct dentry *mlx5_debugfs_get_dev_root(struct mlx5_core_dev *dev) +{ + return dev->priv.dbg.dbg_root; +} +EXPORT_SYMBOL(mlx5_debugfs_get_dev_root); + void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev) { - dev->priv.qp_debugfs = debugfs_create_dir("QPs", dev->priv.dbg_root); + dev->priv.dbg.qp_debugfs = debugfs_create_dir("QPs", dev->priv.dbg.dbg_root); } EXPORT_SYMBOL(mlx5_qp_debugfs_init); void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev) { - debugfs_remove_recursive(dev->priv.qp_debugfs); + debugfs_remove_recursive(dev->priv.dbg.qp_debugfs); } EXPORT_SYMBOL(mlx5_qp_debugfs_cleanup); void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev) { - dev->priv.eq_debugfs = debugfs_create_dir("EQs", dev->priv.dbg_root); + dev->priv.dbg.eq_debugfs = debugfs_create_dir("EQs", dev->priv.dbg.dbg_root); } void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev) { - debugfs_remove_recursive(dev->priv.eq_debugfs); + debugfs_remove_recursive(dev->priv.dbg.eq_debugfs); } static ssize_t average_read(struct file *filp, char __user *buf, size_t count, @@ -168,8 +174,8 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) const char *namep; int i; - cmd = &dev->priv.cmdif_debugfs; - *cmd = debugfs_create_dir("commands", dev->priv.dbg_root); + cmd = &dev->priv.dbg.cmdif_debugfs; + *cmd = debugfs_create_dir("commands", dev->priv.dbg.dbg_root); for (i = 0; i < MLX5_CMD_OP_MAX; i++) { stats = &dev->cmd.stats[i]; @@ -180,23 +186,51 @@ void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) debugfs_create_file("average", 0400, stats->root, stats, &stats_fops); debugfs_create_u64("n", 0400, stats->root, &stats->n); + debugfs_create_u64("failed", 0400, stats->root, &stats->failed); + debugfs_create_u64("failed_mbox_status", 0400, stats->root, + &stats->failed_mbox_status); + debugfs_create_u32("last_failed_errno", 0400, stats->root, + &stats->last_failed_errno); + debugfs_create_u8("last_failed_mbox_status", 0400, stats->root, + &stats->last_failed_mbox_status); } } } void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev) { - debugfs_remove_recursive(dev->priv.cmdif_debugfs); + debugfs_remove_recursive(dev->priv.dbg.cmdif_debugfs); } void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) { - dev->priv.cq_debugfs = debugfs_create_dir("CQs", dev->priv.dbg_root); + dev->priv.dbg.cq_debugfs = debugfs_create_dir("CQs", dev->priv.dbg.dbg_root); } void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev) { - debugfs_remove_recursive(dev->priv.cq_debugfs); + debugfs_remove_recursive(dev->priv.dbg.cq_debugfs); +} + +void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev) +{ + struct dentry *pages; + + dev->priv.dbg.pages_debugfs = debugfs_create_dir("pages", dev->priv.dbg.dbg_root); + pages = dev->priv.dbg.pages_debugfs; + + debugfs_create_u32("fw_pages_total", 0400, pages, &dev->priv.fw_pages); + debugfs_create_u32("fw_pages_vfs", 0400, pages, &dev->priv.vfs_pages); + debugfs_create_u32("fw_pages_host_pf", 0400, pages, &dev->priv.host_pf_pages); + debugfs_create_u32("fw_pages_alloc_failed", 0400, pages, &dev->priv.fw_pages_alloc_failed); + debugfs_create_u32("fw_pages_give_dropped", 0400, pages, &dev->priv.give_pages_dropped); + debugfs_create_u32("fw_pages_reclaim_discard", 0400, pages, + &dev->priv.reclaim_pages_discard); +} + +void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev) +{ + debugfs_remove_recursive(dev->priv.dbg.pages_debugfs); } static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp, @@ -441,7 +475,7 @@ int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp) if (!mlx5_debugfs_root) return 0; - err = add_res_tree(dev, MLX5_DBG_RSC_QP, dev->priv.qp_debugfs, + err = add_res_tree(dev, MLX5_DBG_RSC_QP, dev->priv.dbg.qp_debugfs, &qp->dbg, qp->qpn, qp_fields, ARRAY_SIZE(qp_fields), qp); if (err) @@ -468,7 +502,7 @@ int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq) if (!mlx5_debugfs_root) return 0; - err = add_res_tree(dev, MLX5_DBG_RSC_EQ, dev->priv.eq_debugfs, + err = add_res_tree(dev, MLX5_DBG_RSC_EQ, dev->priv.dbg.eq_debugfs, &eq->dbg, eq->eqn, eq_fields, ARRAY_SIZE(eq_fields), eq); if (err) @@ -493,7 +527,7 @@ int mlx5_debug_cq_add(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq) if (!mlx5_debugfs_root) return 0; - err = add_res_tree(dev, MLX5_DBG_RSC_CQ, dev->priv.cq_debugfs, + err = add_res_tree(dev, MLX5_DBG_RSC_CQ, dev->priv.dbg.cq_debugfs, &cq->dbg, cq->cqn, cq_fields, ARRAY_SIZE(cq_fields), cq); if (err) 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/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 40416e0a8bb1..e3fc15ae7bb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3410,7 +3410,7 @@ mlx5e_clone_flow_attr_for_post_act(struct mlx5_flow_attr *attr, if (!attr2 || !parse_attr) { kvfree(parse_attr); kfree(attr2); - return attr2; + return NULL; } memcpy(attr2, attr, attr_sz); 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/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 98be7050aa8d..d8d36477b97f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1487,8 +1487,8 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) INIT_LIST_HEAD(&priv->pgdir_list); priv->numa_node = dev_to_node(mlx5_core_dma_dev(dev)); - priv->dbg_root = debugfs_create_dir(dev_name(dev->device), - mlx5_debugfs_root); + priv->dbg.dbg_root = debugfs_create_dir(dev_name(dev->device), + mlx5_debugfs_root); INIT_LIST_HEAD(&priv->traps); err = mlx5_tout_init(dev); @@ -1524,7 +1524,7 @@ err_pagealloc_init: err_health_init: mlx5_tout_cleanup(dev); err_timeout_init: - debugfs_remove(dev->priv.dbg_root); + debugfs_remove(dev->priv.dbg.dbg_root); mutex_destroy(&priv->pgdir_mutex); mutex_destroy(&priv->alloc_mutex); mutex_destroy(&priv->bfregs.wc_head.lock); @@ -1542,7 +1542,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) mlx5_pagealloc_cleanup(dev); mlx5_health_cleanup(dev); mlx5_tout_cleanup(dev); - debugfs_remove_recursive(dev->priv.dbg_root); + debugfs_remove_recursive(dev->priv.dbg.dbg_root); mutex_destroy(&priv->pgdir_mutex); mutex_destroy(&priv->alloc_mutex); mutex_destroy(&priv->bfregs.wc_head.lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index f6b5451328fc..e0543b860144 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -327,11 +327,12 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id, } static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, - int notify_fail, bool ec_function) + int event, bool ec_function) { u32 function = get_function(func_id, ec_function); u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; int inlen = MLX5_ST_SZ_BYTES(manage_pages_in); + int notify_fail = event; u64 addr; int err; u32 *in; @@ -351,8 +352,10 @@ retry: if (err) { if (err == -ENOMEM) err = alloc_system_page(dev, function); - if (err) + if (err) { + dev->priv.fw_pages_alloc_failed += (npages - i); goto out_4k; + } goto retry; } @@ -365,11 +368,20 @@ retry: MLX5_SET(manage_pages_in, in, input_num_entries, npages); MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); - err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); + err = mlx5_cmd_do(dev, in, inlen, out, sizeof(out)); + if (err == -EREMOTEIO) { + notify_fail = 0; + /* if triggered by FW and failed by FW ignore */ + if (event) { + err = 0; + goto out_dropped; + } + } if (err) { + err = mlx5_cmd_check(dev, err, in, out); mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n", func_id, npages, err); - goto out_4k; + goto out_dropped; } dev->priv.fw_pages += npages; @@ -384,6 +396,8 @@ retry: kvfree(in); return 0; +out_dropped: + dev->priv.give_pages_dropped += npages; out_4k: for (i--; i >= 0; i--) free_4k(dev, MLX5_GET64(manage_pages_in, in, pas[i]), function); @@ -455,7 +469,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, u32 i = 0; if (!mlx5_cmd_is_down(dev)) - return mlx5_cmd_exec(dev, in, in_size, out, out_size); + return mlx5_cmd_do(dev, in, in_size, out, out_size); /* No hard feelings, we want our pages back! */ npages = MLX5_GET(manage_pages_in, in, input_num_entries); @@ -479,7 +493,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, } static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, - int *nclaimed, bool ec_function) + int *nclaimed, bool event, bool ec_function) { u32 function = get_function(func_id, ec_function); int outlen = MLX5_ST_SZ_BYTES(manage_pages_out); @@ -507,6 +521,14 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, func_id, npages, outlen); err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen); if (err) { + npages = MLX5_GET(manage_pages_in, in, input_num_entries); + dev->priv.reclaim_pages_discard += npages; + } + /* if triggered by FW event and failed by FW then ignore */ + if (event && err == -EREMOTEIO) + err = 0; + if (err) { + err = mlx5_cmd_check(dev, err, in, out); mlx5_core_err(dev, "failed reclaiming pages: err %d\n", err); goto out_free; } @@ -546,7 +568,7 @@ static void pages_work_handler(struct work_struct *work) release_all_pages(dev, req->func_id, req->ec_function); else if (req->npages < 0) err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL, - req->ec_function); + true, req->ec_function); else if (req->npages > 0) err = give_pages(dev, req->func_id, req->npages, 1, req->ec_function); @@ -645,7 +667,7 @@ static int mlx5_reclaim_root_pages(struct mlx5_core_dev *dev, int err; err = reclaim_pages(dev, func_id, optimal_reclaimed_pages(), - &nclaimed, mlx5_core_is_ecpf(dev)); + &nclaimed, false, mlx5_core_is_ecpf(dev)); if (err) { mlx5_core_warn(dev, "failed reclaiming pages (%d) for func id 0x%x\n", err, func_id); @@ -700,12 +722,14 @@ int mlx5_pagealloc_init(struct mlx5_core_dev *dev) return -ENOMEM; xa_init(&dev->priv.page_root_xa); + mlx5_pages_debugfs_init(dev); return 0; } void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev) { + mlx5_pages_debugfs_cleanup(dev); xa_destroy(&dev->priv.page_root_xa); destroy_workqueue(dev->priv.pg_wq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index c61a5e83c78c..743422acc3d8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -669,15 +669,9 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, case DR_ACTION_TYP_VPORT: attr.hit_gvmi = action->vport->caps->vhca_gvmi; dest_action = action; - if (rx_rule) { - if (action->vport->caps->num == MLX5_VPORT_UPLINK) { - mlx5dr_dbg(dmn, "Device doesn't support Loopback on WIRE vport\n"); - return -EOPNOTSUPP; - } - attr.final_icm_addr = action->vport->caps->icm_address_rx; - } else { - attr.final_icm_addr = action->vport->caps->icm_address_tx; - } + attr.final_icm_addr = rx_rule ? + action->vport->caps->icm_address_rx : + action->vport->caps->icm_address_tx; break; case DR_ACTION_TYP_POP_VLAN: if (!rx_rule && !(dmn->ste_ctx->actions_caps & diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c index 2784cd59fefe..2e8b109fb34e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c @@ -630,7 +630,7 @@ void mlx5dr_dbg_init_dump(struct mlx5dr_domain *dmn) } dmn->dump_info.steering_debugfs = - debugfs_create_dir("steering", dev->priv.dbg_root); + debugfs_create_dir("steering", mlx5_debugfs_get_dev_root(dev)); dmn->dump_info.fdb_debugfs = debugfs_create_dir("fdb", dmn->dump_info.steering_debugfs); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c index 5fa7f9d6d8b9..fc6ae49b5ecc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -8,7 +8,7 @@ #define DR_DOMAIN_SW_STEERING_SUPPORTED(dmn, dmn_type) \ ((dmn)->info.caps.dmn_type##_sw_owner || \ ((dmn)->info.caps.dmn_type##_sw_owner_v2 && \ - (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_6DX)) + (dmn)->info.caps.sw_format_ver <= MLX5_STEERING_FORMAT_CONNECTX_7)) static void dr_domain_init_csum_recalc_fts(struct mlx5dr_domain *dmn) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 38971fe1dfe1..a4b5b415df90 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -47,6 +47,11 @@ static bool dr_mask_is_ttl_set(struct mlx5dr_match_spec *spec) return spec->ttl_hoplimit; } +static bool dr_mask_is_ipv4_ihl_set(struct mlx5dr_match_spec *spec) +{ + return spec->ipv4_ihl; +} + #define DR_MASK_IS_L2_DST(_spec, _misc, _inner_outer) (_spec.first_vid || \ (_spec).first_cfi || (_spec).first_prio || (_spec).cvlan_tag || \ (_spec).svlan_tag || (_spec).dmac_47_16 || (_spec).dmac_15_0 || \ @@ -103,7 +108,7 @@ dr_mask_is_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3) static bool dr_matcher_supp_vxlan_gpe(struct mlx5dr_cmd_caps *caps) { - return (caps->sw_format_ver == MLX5_STEERING_FORMAT_CONNECTX_6DX) || + return (caps->sw_format_ver >= MLX5_STEERING_FORMAT_CONNECTX_6DX) || (caps->flex_protocols & MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED); } @@ -144,7 +149,7 @@ static bool dr_mask_is_tnl_geneve_tlv_opt_exist_set(struct mlx5dr_match_misc *mi static bool dr_matcher_supp_tnl_geneve(struct mlx5dr_cmd_caps *caps) { - return (caps->sw_format_ver == MLX5_STEERING_FORMAT_CONNECTX_6DX) || + return (caps->sw_format_ver >= MLX5_STEERING_FORMAT_CONNECTX_6DX) || (caps->flex_protocols & MLX5_FLEX_PARSER_GENEVE_ENABLED); } @@ -261,13 +266,13 @@ static bool dr_mask_is_tnl_gtpu_any(struct mlx5dr_match_param *mask, static int dr_matcher_supp_icmp_v4(struct mlx5dr_cmd_caps *caps) { - return (caps->sw_format_ver == MLX5_STEERING_FORMAT_CONNECTX_6DX) || + return (caps->sw_format_ver >= MLX5_STEERING_FORMAT_CONNECTX_6DX) || (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED); } static int dr_matcher_supp_icmp_v6(struct mlx5dr_cmd_caps *caps) { - return (caps->sw_format_ver == MLX5_STEERING_FORMAT_CONNECTX_6DX) || + return (caps->sw_format_ver >= MLX5_STEERING_FORMAT_CONNECTX_6DX) || (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED); } @@ -507,7 +512,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, mlx5dr_ste_build_eth_l3_ipv4_5_tuple(ste_ctx, &sb[idx++], &mask, inner, rx); - if (dr_mask_is_ttl_set(&mask.outer)) + if (dr_mask_is_ttl_set(&mask.outer) || + dr_mask_is_ipv4_ihl_set(&mask.outer)) mlx5dr_ste_build_eth_l3_ipv4_misc(ste_ctx, &sb[idx++], &mask, inner, rx); } @@ -614,7 +620,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, mlx5dr_ste_build_eth_l3_ipv4_5_tuple(ste_ctx, &sb[idx++], &mask, inner, rx); - if (dr_mask_is_ttl_set(&mask.inner)) + if (dr_mask_is_ttl_set(&mask.inner) || + dr_mask_is_ipv4_ihl_set(&mask.inner)) mlx5dr_ste_build_eth_l3_ipv4_misc(ste_ctx, &sb[idx++], &mask, inner, rx); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index 187e29b409b6..518e949847a3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -523,8 +523,8 @@ void mlx5dr_ste_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes) { - ste_ctx->set_actions_tx(dmn, action_type_set, hw_ste_arr, - attr, added_stes); + ste_ctx->set_actions_tx(dmn, action_type_set, ste_ctx->actions_caps, + hw_ste_arr, attr, added_stes); } void mlx5dr_ste_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx, @@ -534,8 +534,8 @@ void mlx5dr_ste_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes) { - ste_ctx->set_actions_rx(dmn, action_type_set, hw_ste_arr, - attr, added_stes); + ste_ctx->set_actions_rx(dmn, action_type_set, ste_ctx->actions_caps, + hw_ste_arr, attr, added_stes); } const struct mlx5dr_ste_action_modify_field * @@ -793,6 +793,7 @@ static void dr_ste_copy_mask_spec(char *mask, struct mlx5dr_match_spec *spec, bo spec->tcp_sport = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, tcp_sport, clr); spec->tcp_dport = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, tcp_dport, clr); + spec->ipv4_ihl = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, ipv4_ihl, clr); spec->ttl_hoplimit = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, ttl_hoplimit, clr); spec->udp_sport = IFC_GET_CLR(fte_match_set_lyr_2_4, mask, udp_sport, clr); @@ -1360,15 +1361,14 @@ void mlx5dr_ste_build_tnl_header_0_1(struct mlx5dr_ste_ctx *ste_ctx, ste_ctx->build_tnl_header_0_1_init(sb, mask); } -static struct mlx5dr_ste_ctx *mlx5dr_ste_ctx_arr[] = { - [MLX5_STEERING_FORMAT_CONNECTX_5] = &ste_ctx_v0, - [MLX5_STEERING_FORMAT_CONNECTX_6DX] = &ste_ctx_v1, -}; - struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx(u8 version) { - if (version > MLX5_STEERING_FORMAT_CONNECTX_6DX) - return NULL; + if (version == MLX5_STEERING_FORMAT_CONNECTX_5) + return mlx5dr_ste_get_ctx_v0(); + else if (version == MLX5_STEERING_FORMAT_CONNECTX_6DX) + return mlx5dr_ste_get_ctx_v1(); + else if (version == MLX5_STEERING_FORMAT_CONNECTX_7) + return mlx5dr_ste_get_ctx_v2(); - return mlx5dr_ste_ctx_arr[version]; + return NULL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h index ca8fa32b8680..17513baff9b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.h @@ -161,11 +161,13 @@ struct mlx5dr_ste_ctx { u32 actions_caps; void (*set_actions_rx)(struct mlx5dr_domain *dmn, u8 *action_type_set, + u32 actions_caps, u8 *hw_ste_arr, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes); void (*set_actions_tx)(struct mlx5dr_domain *dmn, u8 *action_type_set, + u32 actions_caps, u8 *hw_ste_arr, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes); @@ -197,7 +199,8 @@ struct mlx5dr_ste_ctx { void (*prepare_for_postsend)(u8 *hw_ste_p, u32 ste_size); }; -extern struct mlx5dr_ste_ctx ste_ctx_v0; -extern struct mlx5dr_ste_ctx ste_ctx_v1; +struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v0(void); +struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v1(void); +struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v2(void); #endif /* _DR_STE_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c index 2d62950f7a29..5a322335f204 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v0.c @@ -408,6 +408,7 @@ static void dr_ste_v0_arr_init_next(u8 **last_ste, static void dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, u8 *action_type_set, + u32 actions_caps, u8 *last_ste, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes) @@ -477,6 +478,7 @@ dr_ste_v0_set_actions_tx(struct mlx5dr_domain *dmn, static void dr_ste_v0_set_actions_rx(struct mlx5dr_domain *dmn, u8 *action_type_set, + u32 actions_caps, u8 *last_ste, struct mlx5dr_ste_actions_attr *attr, u32 *added_stes) @@ -1152,6 +1154,7 @@ dr_ste_v0_build_eth_l3_ipv4_misc_tag(struct mlx5dr_match_param *value, struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; DR_STE_SET_TAG(eth_l3_ipv4_misc, tag, time_to_live, spec, ttl_hoplimit); + DR_STE_SET_TAG(eth_l3_ipv4_misc, tag, ihl, spec, ipv4_ihl); return 0; } @@ -1897,7 +1900,7 @@ static void dr_ste_v0_build_tnl_header_0_1_init(struct mlx5dr_ste_build *sb, sb->ste_build_tag_func = &dr_ste_v0_build_tnl_header_0_1_tag; } -struct mlx5dr_ste_ctx ste_ctx_v0 = { +static struct mlx5dr_ste_ctx ste_ctx_v0 = { /* Builders */ .build_eth_l2_src_dst_init = &dr_ste_v0_build_eth_l2_src_dst_init, .build_eth_l3_ipv6_src_init = &dr_ste_v0_build_eth_l3_ipv6_src_init, @@ -1950,3 +1953,8 @@ struct mlx5dr_ste_ctx ste_ctx_v0 = { .set_action_copy = &dr_ste_v0_set_action_copy, .set_action_decap_l3_list = &dr_ste_v0_set_action_decap_l3_list, }; + +struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v0(void) +{ + return &ste_ctx_v0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c index 6ca06800f1d9..fcb962c6db2e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.c @@ -3,7 +3,7 @@ #include <linux/types.h> #include "mlx5_ifc_dr_ste_v1.h" -#include "dr_ste.h" +#include "dr_ste_v1.h" #define DR_STE_CALC_DFNR_TYPE(lookup_type, inner) \ ((inner) ? DR_STE_V1_LU_TYPE_##lookup_type##_I : \ @@ -121,12 +121,12 @@ enum { DR_STE_V1_ACTION_MDFY_FLD_CFG_HDR_0_1 = 0x70, DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE = 0x7b, DR_STE_V1_ACTION_MDFY_FLD_GNRL_PURPOSE = 0x7c, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2 = 0x8c, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_3 = 0x8d, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_4 = 0x8e, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_5 = 0x8f, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_6 = 0x90, - DR_STE_V1_ACTION_MDFY_FLD_REGISTER_7 = 0x91, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_0 = 0x8c, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_1 = 0x8d, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_0 = 0x8e, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_1 = 0x8f, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_0 = 0x90, + DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_1 = 0x91, }; static const struct mlx5dr_ste_action_modify_field dr_ste_v1_action_modify_field_arr[] = { @@ -223,22 +223,22 @@ static const struct mlx5dr_ste_action_modify_field dr_ste_v1_action_modify_field .hw_field = DR_STE_V1_ACTION_MDFY_FLD_METADATA_2_CQE, .start = 0, .end = 31, }, [MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = { - .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_6, .start = 0, .end = 31, + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_0, .start = 0, .end = 31, }, [MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = { - .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_7, .start = 0, .end = 31, + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_0_1, .start = 0, .end = 31, }, [MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = { - .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_4, .start = 0, .end = 31, + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_0, .start = 0, .end = 31, }, [MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = { - .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_5, .start = 0, .end = 31, + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_1_1, .start = 0, .end = 31, }, [MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = { - .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2, .start = 0, .end = 31, + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_0, .start = 0, .end = 31, }, [MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = { - .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_3, .start = 0, .end = 31, + .hw_field = DR_STE_V1_ACTION_MDFY_FLD_REGISTER_2_1, .start = 0, .end = 31, }, [MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = { .hw_field = DR_STE_V1_ACTION_MDFY_FLD_TCP_MISC_0, .start = 0, .end = 31, @@ -262,7 +262,7 @@ static void dr_ste_v1_set_entry_type(u8 *hw_ste_p, u8 entry_type) MLX5_SET(ste_match_bwc_v1, hw_ste_p, entry_format, entry_type); } -static void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) +void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) { u64 index = miss_addr >> 6; @@ -270,7 +270,7 @@ static void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) MLX5_SET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6, index); } -static u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p) +u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p) { u64 index = ((u64)MLX5_GET(ste_match_bwc_v1, hw_ste_p, miss_address_31_6) | @@ -279,12 +279,12 @@ static u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p) return index << 6; } -static void dr_ste_v1_set_byte_mask(u8 *hw_ste_p, u16 byte_mask) +void dr_ste_v1_set_byte_mask(u8 *hw_ste_p, u16 byte_mask) { MLX5_SET(ste_match_bwc_v1, hw_ste_p, byte_mask, byte_mask); } -static u16 dr_ste_v1_get_byte_mask(u8 *hw_ste_p) +u16 dr_ste_v1_get_byte_mask(u8 *hw_ste_p) { return MLX5_GET(ste_match_bwc_v1, hw_ste_p, byte_mask); } @@ -295,13 +295,13 @@ static void dr_ste_v1_set_lu_type(u8 *hw_ste_p, u16 lu_type) MLX5_SET(ste_match_bwc_v1, hw_ste_p, match_definer_ctx_idx, lu_type & 0xFF); } -static void dr_ste_v1_set_next_lu_type(u8 *hw_ste_p, u16 lu_type) +void dr_ste_v1_set_next_lu_type(u8 *hw_ste_p, u16 lu_type) { MLX5_SET(ste_match_bwc_v1, hw_ste_p, next_entry_format, lu_type >> 8); MLX5_SET(ste_match_bwc_v1, hw_ste_p, hash_definer_ctx_idx, lu_type & 0xFF); } -static u16 dr_ste_v1_get_next_lu_type(u8 *hw_ste_p) +u16 dr_ste_v1_get_next_lu_type(u8 *hw_ste_p) { u8 mode = MLX5_GET(ste_match_bwc_v1, hw_ste_p, next_entry_format); u8 index = MLX5_GET(ste_match_bwc_v1, hw_ste_p, hash_definer_ctx_idx); @@ -314,7 +314,7 @@ static void dr_ste_v1_set_hit_gvmi(u8 *hw_ste_p, u16 gvmi) MLX5_SET(ste_match_bwc_v1, hw_ste_p, next_table_base_63_48, gvmi); } -static void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size) +void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size) { u64 index = (icm_addr >> 5) | ht_size; @@ -322,8 +322,7 @@ static void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size) MLX5_SET(ste_match_bwc_v1, hw_ste_p, next_table_base_31_5_size, index); } -static void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type, - bool is_rx, u16 gvmi) +void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type, bool is_rx, u16 gvmi) { dr_ste_v1_set_lu_type(hw_ste_p, lu_type); dr_ste_v1_set_next_lu_type(hw_ste_p, MLX5DR_STE_LU_TYPE_DONT_CARE); @@ -333,8 +332,7 @@ static void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type, MLX5_SET(ste_match_bwc_v1, hw_ste_p, miss_address_63_48, gvmi); } -static void dr_ste_v1_prepare_for_postsend(u8 *hw_ste_p, - u32 ste_size) +void dr_ste_v1_prepare_for_postsend(u8 *hw_ste_p, u32 ste_size) { u8 *tag = hw_ste_p + DR_STE_SIZE_CTRL; u8 *mask = tag + DR_STE_SIZE_TAG; @@ -511,11 +509,12 @@ static void dr_ste_v1_arr_init_next_match(u8 **last_ste, memset(action, 0, MLX5_FLD_SZ_BYTES(ste_mask_and_match_v1, action)); } -static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, - u8 *action_type_set, - u8 *last_ste, - struct mlx5dr_ste_actions_attr *attr, - u32 *added_stes) +void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, + u8 *action_type_set, + u32 actions_caps, + u8 *last_ste, + struct mlx5dr_ste_actions_attr *attr, + u32 *added_stes) { u8 *action = MLX5_ADDR_OF(ste_match_bwc_v1, last_ste, action); u8 action_sz = DR_STE_ACTION_DOUBLE_SZ; @@ -533,7 +532,10 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count); action_sz -= DR_STE_ACTION_SINGLE_SZ; action += DR_STE_ACTION_SINGLE_SZ; - allow_modify_hdr = false; + + /* Check if vlan_pop and modify_hdr on same STE is supported */ + if (!(actions_caps & DR_STE_CTX_ACTION_CAP_POP_MDFY)) + allow_modify_hdr = false; } if (action_type_set[DR_ACTION_TYP_CTR]) @@ -631,11 +633,12 @@ static void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1); } -static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, - u8 *action_type_set, - u8 *last_ste, - struct mlx5dr_ste_actions_attr *attr, - u32 *added_stes) +void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, + u8 *action_type_set, + u32 actions_caps, + u8 *last_ste, + struct mlx5dr_ste_actions_attr *attr, + u32 *added_stes) { u8 *action = MLX5_ADDR_OF(ste_match_bwc_v1, last_ste, action); u8 action_sz = DR_STE_ACTION_DOUBLE_SZ; @@ -677,13 +680,16 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, dr_ste_v1_arr_init_next_match(&last_ste, added_stes, attr->gvmi); action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); action_sz = DR_STE_ACTION_TRIPLE_SZ; - allow_modify_hdr = false; - allow_ctr = false; } dr_ste_v1_set_pop_vlan(last_ste, action, attr->vlans.count); action_sz -= DR_STE_ACTION_SINGLE_SZ; action += DR_STE_ACTION_SINGLE_SZ; + allow_ctr = false; + + /* Check if vlan_pop and modify_hdr on same STE is supported */ + if (!(actions_caps & DR_STE_CTX_ACTION_CAP_POP_MDFY)) + allow_modify_hdr = false; } if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { @@ -731,9 +737,9 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action); action_sz = DR_STE_ACTION_TRIPLE_SZ; allow_modify_hdr = true; - allow_ctr = false; } dr_ste_v1_set_counter_id(last_ste, attr->ctr_id); + allow_ctr = false; } if (action_type_set[DR_ACTION_TYP_L2_TO_TNL_L2]) { @@ -800,11 +806,11 @@ static void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, dr_ste_v1_set_hit_addr(last_ste, attr->final_icm_addr, 1); } -static void dr_ste_v1_set_action_set(u8 *d_action, - u8 hw_field, - u8 shifter, - u8 length, - u32 data) +void dr_ste_v1_set_action_set(u8 *d_action, + u8 hw_field, + u8 shifter, + u8 length, + u32 data) { shifter += MLX5_MODIFY_HEADER_V1_QW_OFFSET; MLX5_SET(ste_double_action_set_v1, d_action, action_id, DR_STE_V1_ACTION_ID_SET); @@ -814,11 +820,11 @@ static void dr_ste_v1_set_action_set(u8 *d_action, MLX5_SET(ste_double_action_set_v1, d_action, inline_data, data); } -static void dr_ste_v1_set_action_add(u8 *d_action, - u8 hw_field, - u8 shifter, - u8 length, - u32 data) +void dr_ste_v1_set_action_add(u8 *d_action, + u8 hw_field, + u8 shifter, + u8 length, + u32 data) { shifter += MLX5_MODIFY_HEADER_V1_QW_OFFSET; MLX5_SET(ste_double_action_add_v1, d_action, action_id, DR_STE_V1_ACTION_ID_ADD); @@ -828,12 +834,12 @@ static void dr_ste_v1_set_action_add(u8 *d_action, MLX5_SET(ste_double_action_add_v1, d_action, add_value, data); } -static void dr_ste_v1_set_action_copy(u8 *d_action, - u8 dst_hw_field, - u8 dst_shifter, - u8 dst_len, - u8 src_hw_field, - u8 src_shifter) +void dr_ste_v1_set_action_copy(u8 *d_action, + u8 dst_hw_field, + u8 dst_shifter, + u8 dst_len, + u8 src_hw_field, + u8 src_shifter) { dst_shifter += MLX5_MODIFY_HEADER_V1_QW_OFFSET; src_shifter += MLX5_MODIFY_HEADER_V1_QW_OFFSET; @@ -848,11 +854,11 @@ static void dr_ste_v1_set_action_copy(u8 *d_action, #define DR_STE_DECAP_L3_ACTION_NUM 8 #define DR_STE_L2_HDR_MAX_SZ 20 -static int dr_ste_v1_set_action_decap_l3_list(void *data, - u32 data_sz, - u8 *hw_action, - u32 hw_action_sz, - u16 *used_hw_action_num) +int dr_ste_v1_set_action_decap_l3_list(void *data, + u32 data_sz, + u8 *hw_action, + u32 hw_action_sz, + u16 *used_hw_action_num) { u8 padded_data[DR_STE_L2_HDR_MAX_SZ] = {}; void *data_ptr = padded_data; @@ -977,8 +983,8 @@ static int dr_ste_v1_build_eth_l2_src_dst_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_eth_l2_src_dst_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_l2_src_dst_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_l2_src_dst_bit_mask(mask, sb->inner, sb->bit_mask); @@ -1001,8 +1007,8 @@ static int dr_ste_v1_build_eth_l3_ipv6_dst_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_eth_l3_ipv6_dst_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_l3_ipv6_dst_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_l3_ipv6_dst_tag(mask, sb, sb->bit_mask); @@ -1025,8 +1031,8 @@ static int dr_ste_v1_build_eth_l3_ipv6_src_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_eth_l3_ipv6_src_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_l3_ipv6_src_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_l3_ipv6_src_tag(mask, sb, sb->bit_mask); @@ -1060,8 +1066,8 @@ static int dr_ste_v1_build_eth_l3_ipv4_5_tuple_tag(struct mlx5dr_match_param *va return 0; } -static void dr_ste_v1_build_eth_l3_ipv4_5_tuple_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_l3_ipv4_5_tuple_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_l3_ipv4_5_tuple_tag(mask, sb, sb->bit_mask); @@ -1079,8 +1085,8 @@ static void dr_ste_v1_build_eth_l2_src_or_dst_bit_mask(struct mlx5dr_match_param DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, first_vlan_id, mask, first_vid); DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, first_cfi, mask, first_cfi); DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, first_priority, mask, first_prio); - DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, ip_fragmented, mask, frag); // ? - DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, l3_ethertype, mask, ethertype); // ? + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, ip_fragmented, mask, frag); + DR_STE_SET_TAG(eth_l2_src_v1, bit_mask, l3_ethertype, mask, ethertype); DR_STE_SET_ONES(eth_l2_src_v1, bit_mask, l3_type, mask, ip_version); if (mask->svlan_tag || mask->cvlan_tag) { @@ -1201,8 +1207,8 @@ static int dr_ste_v1_build_eth_l2_src_tag(struct mlx5dr_match_param *value, return dr_ste_v1_build_eth_l2_src_or_dst_tag(value, sb->inner, tag); } -static void dr_ste_v1_build_eth_l2_src_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_l2_src_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_l2_src_bit_mask(mask, sb->inner, sb->bit_mask); @@ -1234,8 +1240,8 @@ static int dr_ste_v1_build_eth_l2_dst_tag(struct mlx5dr_match_param *value, return dr_ste_v1_build_eth_l2_src_or_dst_tag(value, sb->inner, tag); } -static void dr_ste_v1_build_eth_l2_dst_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_l2_dst_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_l2_dst_bit_mask(mask, sb->inner, sb->bit_mask); @@ -1314,8 +1320,8 @@ static int dr_ste_v1_build_eth_l2_tnl_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_eth_l2_tnl_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_l2_tnl_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_l2_tnl_bit_mask(mask, sb->inner, sb->bit_mask); @@ -1331,12 +1337,13 @@ static int dr_ste_v1_build_eth_l3_ipv4_misc_tag(struct mlx5dr_match_param *value struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; DR_STE_SET_TAG(eth_l3_ipv4_misc_v1, tag, time_to_live, spec, ttl_hoplimit); + DR_STE_SET_TAG(eth_l3_ipv4_misc_v1, tag, ihl, spec, ipv4_ihl); return 0; } -static void dr_ste_v1_build_eth_l3_ipv4_misc_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_l3_ipv4_misc_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_l3_ipv4_misc_tag(mask, sb, sb->bit_mask); @@ -1375,8 +1382,8 @@ static int dr_ste_v1_build_eth_ipv6_l3_l4_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_eth_ipv6_l3_l4_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_ipv6_l3_l4_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_ipv6_l3_l4_tag(mask, sb, sb->bit_mask); @@ -1399,8 +1406,8 @@ static int dr_ste_v1_build_mpls_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_mpls_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_mpls_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_mpls_tag(mask, sb, sb->bit_mask); @@ -1426,8 +1433,8 @@ static int dr_ste_v1_build_tnl_gre_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_tnl_gre_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_tnl_gre_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_tnl_gre_tag(mask, sb, sb->bit_mask); @@ -1471,8 +1478,8 @@ static int dr_ste_v1_build_tnl_mpls_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_tnl_mpls_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_tnl_mpls_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_tnl_mpls_tag(mask, sb, sb->bit_mask); @@ -1506,8 +1513,8 @@ static int dr_ste_v1_build_tnl_mpls_over_udp_tag(struct mlx5dr_match_param *valu return 0; } -static void dr_ste_v1_build_tnl_mpls_over_udp_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_tnl_mpls_over_udp_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_tnl_mpls_over_udp_tag(mask, sb, sb->bit_mask); @@ -1547,8 +1554,8 @@ static int dr_ste_v1_build_tnl_mpls_over_gre_tag(struct mlx5dr_match_param *valu return 0; } -static void dr_ste_v1_build_tnl_mpls_over_gre_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_tnl_mpls_over_gre_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_tnl_mpls_over_gre_tag(mask, sb, sb->bit_mask); @@ -1594,8 +1601,8 @@ static int dr_ste_v1_build_icmp_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_icmp_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_icmp_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_icmp_tag(mask, sb, sb->bit_mask); @@ -1616,8 +1623,8 @@ static int dr_ste_v1_build_general_purpose_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_general_purpose_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_general_purpose_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_general_purpose_tag(mask, sb, sb->bit_mask); @@ -1643,8 +1650,8 @@ static int dr_ste_v1_build_eth_l4_misc_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_eth_l4_misc_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_eth_l4_misc_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_eth_l4_misc_tag(mask, sb, sb->bit_mask); @@ -1673,9 +1680,8 @@ dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_tag(struct mlx5dr_match_param *value, return 0; } -static void -dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_tag(mask, sb, sb->bit_mask); @@ -1703,9 +1709,8 @@ dr_ste_v1_build_flex_parser_tnl_geneve_tag(struct mlx5dr_match_param *value, return 0; } -static void -dr_ste_v1_build_flex_parser_tnl_geneve_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_flex_parser_tnl_geneve_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_flex_parser_tnl_geneve_tag(mask, sb, sb->bit_mask); @@ -1726,8 +1731,8 @@ static int dr_ste_v1_build_tnl_header_0_1_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_tnl_header_0_1_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_tnl_header_0_1_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { sb->lu_type = DR_STE_V1_LU_TYPE_FLEX_PARSER_TNL_HEADER; dr_ste_v1_build_tnl_header_0_1_tag(mask, sb, sb->bit_mask); @@ -1749,8 +1754,8 @@ static int dr_ste_v1_build_register_0_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_register_0_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_register_0_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_register_0_tag(mask, sb, sb->bit_mask); @@ -1773,8 +1778,8 @@ static int dr_ste_v1_build_register_1_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_register_1_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_register_1_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_register_1_tag(mask, sb, sb->bit_mask); @@ -1837,8 +1842,8 @@ static int dr_ste_v1_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_src_gvmi_qpn_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_src_gvmi_qpn_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_src_gvmi_qpn_bit_mask(mask, sb->bit_mask); @@ -1892,8 +1897,8 @@ static int dr_ste_v1_build_felx_parser_tag(struct mlx5dr_match_param *value, return 0; } -static void dr_ste_v1_build_flex_parser_0_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_flex_parser_0_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { sb->lu_type = DR_STE_V1_LU_TYPE_FLEX_PARSER_0; dr_ste_v1_build_felx_parser_tag(mask, sb, sb->bit_mask); @@ -1901,8 +1906,8 @@ static void dr_ste_v1_build_flex_parser_0_init(struct mlx5dr_ste_build *sb, sb->ste_build_tag_func = &dr_ste_v1_build_felx_parser_tag; } -static void dr_ste_v1_build_flex_parser_1_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_flex_parser_1_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { sb->lu_type = DR_STE_V1_LU_TYPE_FLEX_PARSER_1; dr_ste_v1_build_felx_parser_tag(mask, sb, sb->bit_mask); @@ -1926,7 +1931,7 @@ dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_tag(struct mlx5dr_match_param *va return 0; } -static void +void dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask) { @@ -1959,7 +1964,7 @@ dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_tag(struct mlx5dr_match_par return 0; } -static void +void dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_init(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask) { @@ -1982,8 +1987,8 @@ static int dr_ste_v1_build_flex_parser_tnl_gtpu_tag(struct mlx5dr_match_param *v return 0; } -static void dr_ste_v1_build_flex_parser_tnl_gtpu_init(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask) +void dr_ste_v1_build_flex_parser_tnl_gtpu_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask) { dr_ste_v1_build_flex_parser_tnl_gtpu_tag(mask, sb, sb->bit_mask); @@ -2008,7 +2013,7 @@ dr_ste_v1_build_tnl_gtpu_flex_parser_0_tag(struct mlx5dr_match_param *value, return 0; } -static void +void dr_ste_v1_build_tnl_gtpu_flex_parser_0_init(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask) { @@ -2035,7 +2040,7 @@ dr_ste_v1_build_tnl_gtpu_flex_parser_1_tag(struct mlx5dr_match_param *value, return 0; } -static void +void dr_ste_v1_build_tnl_gtpu_flex_parser_1_init(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask) { @@ -2046,7 +2051,7 @@ dr_ste_v1_build_tnl_gtpu_flex_parser_1_init(struct mlx5dr_ste_build *sb, sb->ste_build_tag_func = &dr_ste_v1_build_tnl_gtpu_flex_parser_1_tag; } -struct mlx5dr_ste_ctx ste_ctx_v1 = { +static struct mlx5dr_ste_ctx ste_ctx_v1 = { /* Builders */ .build_eth_l2_src_dst_init = &dr_ste_v1_build_eth_l2_src_dst_init, .build_eth_l3_ipv6_src_init = &dr_ste_v1_build_eth_l3_ipv6_src_init, @@ -2091,7 +2096,8 @@ struct mlx5dr_ste_ctx ste_ctx_v1 = { /* Actions */ .actions_caps = DR_STE_CTX_ACTION_CAP_TX_POP | DR_STE_CTX_ACTION_CAP_RX_PUSH | - DR_STE_CTX_ACTION_CAP_RX_ENCAP, + DR_STE_CTX_ACTION_CAP_RX_ENCAP | + DR_STE_CTX_ACTION_CAP_POP_MDFY, .set_actions_rx = &dr_ste_v1_set_actions_rx, .set_actions_tx = &dr_ste_v1_set_actions_tx, .modify_field_arr_sz = ARRAY_SIZE(dr_ste_v1_action_modify_field_arr), @@ -2103,3 +2109,8 @@ struct mlx5dr_ste_ctx ste_ctx_v1 = { /* Send */ .prepare_for_postsend = &dr_ste_v1_prepare_for_postsend, }; + +struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v1(void) +{ + return &ste_ctx_v1; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.h new file mode 100644 index 000000000000..8a1d49790c6e --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v1.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#ifndef _DR_STE_V1_ +#define _DR_STE_V1_ + +#include "dr_types.h" +#include "dr_ste.h" + +void dr_ste_v1_set_miss_addr(u8 *hw_ste_p, u64 miss_addr); +u64 dr_ste_v1_get_miss_addr(u8 *hw_ste_p); +void dr_ste_v1_set_byte_mask(u8 *hw_ste_p, u16 byte_mask); +u16 dr_ste_v1_get_byte_mask(u8 *hw_ste_p); +void dr_ste_v1_set_next_lu_type(u8 *hw_ste_p, u16 lu_type); +u16 dr_ste_v1_get_next_lu_type(u8 *hw_ste_p); +void dr_ste_v1_set_hit_addr(u8 *hw_ste_p, u64 icm_addr, u32 ht_size); +void dr_ste_v1_init(u8 *hw_ste_p, u16 lu_type, bool is_rx, u16 gvmi); +void dr_ste_v1_prepare_for_postsend(u8 *hw_ste_p, u32 ste_size); +void dr_ste_v1_set_actions_tx(struct mlx5dr_domain *dmn, u8 *action_type_set, + u32 actions_caps, u8 *last_ste, + struct mlx5dr_ste_actions_attr *attr, u32 *added_stes); +void dr_ste_v1_set_actions_rx(struct mlx5dr_domain *dmn, u8 *action_type_set, + u32 actions_caps, u8 *last_ste, + struct mlx5dr_ste_actions_attr *attr, u32 *added_stes); +void dr_ste_v1_set_action_set(u8 *d_action, u8 hw_field, u8 shifter, + u8 length, u32 data); +void dr_ste_v1_set_action_add(u8 *d_action, u8 hw_field, u8 shifter, + u8 length, u32 data); +void dr_ste_v1_set_action_copy(u8 *d_action, u8 dst_hw_field, u8 dst_shifter, + u8 dst_len, u8 src_hw_field, u8 src_shifter); +int dr_ste_v1_set_action_decap_l3_list(void *data, u32 data_sz, u8 *hw_action, + u32 hw_action_sz, u16 *used_hw_action_num); +void dr_ste_v1_build_eth_l2_src_dst_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_eth_l3_ipv6_dst_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_eth_l3_ipv6_src_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_eth_l3_ipv4_5_tuple_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_eth_l2_src_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_eth_l2_dst_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_eth_l2_tnl_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_eth_l3_ipv4_misc_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_eth_ipv6_l3_l4_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_mpls_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_tnl_gre_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_tnl_mpls_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_tnl_mpls_over_udp_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_tnl_mpls_over_gre_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_icmp_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_general_purpose_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_eth_l4_misc_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_flex_parser_tnl_geneve_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_tnl_header_0_1_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_register_0_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_register_1_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_src_gvmi_qpn_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_flex_parser_0_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_flex_parser_1_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_flex_parser_tnl_gtpu_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_tnl_gtpu_flex_parser_0_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); +void dr_ste_v1_build_tnl_gtpu_flex_parser_1_init(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask); + +#endif /* _DR_STE_V1_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v2.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v2.c new file mode 100644 index 000000000000..c60fddd125d2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste_v2.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */ + +#include "dr_ste_v1.h" + +enum { + DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0 = 0x00, + DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1 = 0x01, + DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2 = 0x02, + DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0 = 0x08, + DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1 = 0x09, + DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0 = 0x0e, + DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0 = 0x18, + DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1 = 0x19, + DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0 = 0x40, + DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1 = 0x41, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0 = 0x44, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1 = 0x45, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2 = 0x46, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3 = 0x47, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0 = 0x4c, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1 = 0x4d, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2 = 0x4e, + DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3 = 0x4f, + DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0 = 0x5e, + DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1 = 0x5f, + DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0 = 0x6f, + DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1 = 0x70, + DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE = 0x7b, + DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE = 0x7c, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0 = 0x90, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1 = 0x91, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0 = 0x92, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1 = 0x93, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0 = 0x94, + DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1 = 0x95, +}; + +static const struct mlx5dr_ste_action_modify_field dr_ste_v2_action_modify_field_arr[] = { + [MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_SRC_L2_OUT_1, .start = 16, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 0, .end = 15, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_1, .start = 16, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 18, .end = 23, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_1, .start = 16, .end = 24, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L3_OUT_0, .start = 8, .end = 15, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 16, .end = 31, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L4_OUT_0, .start = 0, .end = 15, + .l4_type = DR_STE_ACTION_MDFY_TYPE_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_0, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_1, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_2, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_SRC_OUT_3, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_0, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_1, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_2, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV6_DST_OUT_3, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV4] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_0, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV4] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_IPV4_OUT_1, .start = 0, .end = 31, + .l3_type = DR_STE_ACTION_MDFY_TYPE_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_A] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_GNRL_PURPOSE, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_B] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_METADATA_2_CQE, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_0_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_1_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_REGISTER_2_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_TCP_MISC_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_L2_OUT_2, .start = 0, .end = 15, + }, + [MLX5_ACTION_IN_FIELD_OUT_EMD_31_0] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_EMD_47_32] = { + .hw_field = DR_STE_V2_ACTION_MDFY_FLD_CFG_HDR_0_0, .start = 0, .end = 15, + }, +}; + +static struct mlx5dr_ste_ctx ste_ctx_v2 = { + /* Builders */ + .build_eth_l2_src_dst_init = &dr_ste_v1_build_eth_l2_src_dst_init, + .build_eth_l3_ipv6_src_init = &dr_ste_v1_build_eth_l3_ipv6_src_init, + .build_eth_l3_ipv6_dst_init = &dr_ste_v1_build_eth_l3_ipv6_dst_init, + .build_eth_l3_ipv4_5_tuple_init = &dr_ste_v1_build_eth_l3_ipv4_5_tuple_init, + .build_eth_l2_src_init = &dr_ste_v1_build_eth_l2_src_init, + .build_eth_l2_dst_init = &dr_ste_v1_build_eth_l2_dst_init, + .build_eth_l2_tnl_init = &dr_ste_v1_build_eth_l2_tnl_init, + .build_eth_l3_ipv4_misc_init = &dr_ste_v1_build_eth_l3_ipv4_misc_init, + .build_eth_ipv6_l3_l4_init = &dr_ste_v1_build_eth_ipv6_l3_l4_init, + .build_mpls_init = &dr_ste_v1_build_mpls_init, + .build_tnl_gre_init = &dr_ste_v1_build_tnl_gre_init, + .build_tnl_mpls_init = &dr_ste_v1_build_tnl_mpls_init, + .build_tnl_mpls_over_udp_init = &dr_ste_v1_build_tnl_mpls_over_udp_init, + .build_tnl_mpls_over_gre_init = &dr_ste_v1_build_tnl_mpls_over_gre_init, + .build_icmp_init = &dr_ste_v1_build_icmp_init, + .build_general_purpose_init = &dr_ste_v1_build_general_purpose_init, + .build_eth_l4_misc_init = &dr_ste_v1_build_eth_l4_misc_init, + .build_tnl_vxlan_gpe_init = &dr_ste_v1_build_flex_parser_tnl_vxlan_gpe_init, + .build_tnl_geneve_init = &dr_ste_v1_build_flex_parser_tnl_geneve_init, + .build_tnl_geneve_tlv_opt_init = &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_init, + .build_tnl_geneve_tlv_opt_exist_init = + &dr_ste_v1_build_flex_parser_tnl_geneve_tlv_opt_exist_init, + .build_register_0_init = &dr_ste_v1_build_register_0_init, + .build_register_1_init = &dr_ste_v1_build_register_1_init, + .build_src_gvmi_qpn_init = &dr_ste_v1_build_src_gvmi_qpn_init, + .build_flex_parser_0_init = &dr_ste_v1_build_flex_parser_0_init, + .build_flex_parser_1_init = &dr_ste_v1_build_flex_parser_1_init, + .build_tnl_gtpu_init = &dr_ste_v1_build_flex_parser_tnl_gtpu_init, + .build_tnl_header_0_1_init = &dr_ste_v1_build_tnl_header_0_1_init, + .build_tnl_gtpu_flex_parser_0_init = &dr_ste_v1_build_tnl_gtpu_flex_parser_0_init, + .build_tnl_gtpu_flex_parser_1_init = &dr_ste_v1_build_tnl_gtpu_flex_parser_1_init, + + /* Getters and Setters */ + .ste_init = &dr_ste_v1_init, + .set_next_lu_type = &dr_ste_v1_set_next_lu_type, + .get_next_lu_type = &dr_ste_v1_get_next_lu_type, + .set_miss_addr = &dr_ste_v1_set_miss_addr, + .get_miss_addr = &dr_ste_v1_get_miss_addr, + .set_hit_addr = &dr_ste_v1_set_hit_addr, + .set_byte_mask = &dr_ste_v1_set_byte_mask, + .get_byte_mask = &dr_ste_v1_get_byte_mask, + + /* Actions */ + .actions_caps = DR_STE_CTX_ACTION_CAP_TX_POP | + DR_STE_CTX_ACTION_CAP_RX_PUSH | + DR_STE_CTX_ACTION_CAP_RX_ENCAP, + .set_actions_rx = &dr_ste_v1_set_actions_rx, + .set_actions_tx = &dr_ste_v1_set_actions_tx, + .modify_field_arr_sz = ARRAY_SIZE(dr_ste_v2_action_modify_field_arr), + .modify_field_arr = dr_ste_v2_action_modify_field_arr, + .set_action_set = &dr_ste_v1_set_action_set, + .set_action_add = &dr_ste_v1_set_action_add, + .set_action_copy = &dr_ste_v1_set_action_copy, + .set_action_decap_l3_list = &dr_ste_v1_set_action_decap_l3_list, + + /* Send */ + .prepare_for_postsend = &dr_ste_v1_prepare_for_postsend, +}; + +struct mlx5dr_ste_ctx *mlx5dr_ste_get_ctx_v2(void) +{ + return &ste_ctx_v2; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index 55fcb751e24a..88092fabf55b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -91,6 +91,7 @@ enum mlx5dr_ste_ctx_action_cap { DR_STE_CTX_ACTION_CAP_TX_POP = 1 << 0, DR_STE_CTX_ACTION_CAP_RX_PUSH = 1 << 1, DR_STE_CTX_ACTION_CAP_RX_ENCAP = 1 << 2, + DR_STE_CTX_ACTION_CAP_POP_MDFY = 1 << 3, }; enum { @@ -555,7 +556,9 @@ struct mlx5dr_match_spec { */ u32 tcp_dport:16; - u32 reserved_auto1:24; + u32 reserved_auto1:16; + u32 ipv4_ihl:4; + u32 reserved_auto2:4; u32 ttl_hoplimit:8; /* UDP source port.;tcp and udp sport/dport are mutually exclusive */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 57ffcab7294c..045b0cf90063 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -758,7 +758,7 @@ static u32 mlx5_cmd_dr_get_capabilities(struct mlx5_flow_root_namespace *ns, enum fs_flow_table_type ft_type) { if (ft_type != FS_FT_FDB || - MLX5_CAP_GEN(ns->dev, steering_format_version) != MLX5_STEERING_FORMAT_CONNECTX_6DX) + MLX5_CAP_GEN(ns->dev, steering_format_version) == MLX5_STEERING_FORMAT_CONNECTX_5) return 0; return MLX5_FLOW_STEERING_CAP_VLAN_PUSH_ON_RX | MLX5_FLOW_STEERING_CAP_VLAN_POP_ON_TX; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index dfa223415fe2..03efbdf3fec3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -136,7 +136,7 @@ mlx5dr_is_supported(struct mlx5_core_dev *dev) (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner) || (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner_v2) && (MLX5_CAP_GEN(dev, steering_format_version) <= - MLX5_STEERING_FORMAT_CONNECTX_6DX))); + MLX5_STEERING_FORMAT_CONNECTX_7))); } /* buddy functions & structure */ 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/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 32ef3df4e266..63754a9c4ba7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -1159,6 +1159,7 @@ static SIMPLE_DEV_PM_OPS(intel_eth_pm_ops, intel_eth_pci_suspend, #define PCI_DEVICE_ID_INTEL_TGL_SGMII1G 0xa0ac #define PCI_DEVICE_ID_INTEL_ADLS_SGMII1G_0 0x7aac #define PCI_DEVICE_ID_INTEL_ADLS_SGMII1G_1 0x7aad +#define PCI_DEVICE_ID_INTEL_ADLN_SGMII1G 0x54ac static const struct pci_device_id intel_eth_pci_id_table[] = { { PCI_DEVICE_DATA(INTEL, QUARK, &quark_info) }, @@ -1176,6 +1177,7 @@ static const struct pci_device_id intel_eth_pci_id_table[] = { { PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1, &tgl_sgmii1g_phy1_info) }, { PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_0, &adls_sgmii1g_phy0_info) }, { PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_1, &adls_sgmii1g_phy1_info) }, + { PCI_DEVICE_DATA(INTEL, ADLN_SGMII1G, &tgl_sgmii1g_phy0_info) }, {} }; MODULE_DEVICE_TABLE(pci, intel_eth_pci_id_table); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index cf4e077d21ff..c1bfd89a5a1f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3275,7 +3275,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) ret = stmmac_init_ptp(priv); if (ret == -EOPNOTSUPP) - netdev_warn(priv->dev, "PTP not supported by HW\n"); + netdev_info(priv->dev, "PTP not supported by HW\n"); else if (ret) netdev_warn(priv->dev, "PTP init failed\n"); else if (ptp_register) 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_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 1d8c6e910279..c7eb05e4a6bf 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -965,7 +965,7 @@ static int axienet_poll(struct napi_struct *napi, int budget) packets++; } - new_skb = netdev_alloc_skb_ip_align(lp->ndev, lp->max_frm_size); + new_skb = napi_alloc_skb(napi, lp->max_frm_size); if (!new_skb) break; 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/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index e440cdd4f710..3872f76ea1d3 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2990,7 +2990,6 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all) static int vxlan_stop(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); - int ret = 0; vxlan_multicast_leave(vxlan); @@ -2999,7 +2998,7 @@ static int vxlan_stop(struct net_device *dev) vxlan_flush(vxlan, false); vxlan_sock_release(vxlan); - return ret; + return 0; } /* Stub, nothing needs to be 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/ptp/ptp_idt82p33.c b/drivers/ptp/ptp_idt82p33.c index c1c959f7e52b..97c1be44e323 100644 --- a/drivers/ptp/ptp_idt82p33.c +++ b/drivers/ptp/ptp_idt82p33.c @@ -6,13 +6,17 @@ #define pr_fmt(fmt) "IDT_82p33xxx: " fmt #include <linux/firmware.h> -#include <linux/i2c.h> +#include <linux/platform_device.h> #include <linux/module.h> #include <linux/ptp_clock_kernel.h> #include <linux/delay.h> +#include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/timekeeping.h> #include <linux/bitops.h> +#include <linux/of.h> +#include <linux/mfd/rsmu.h> +#include <linux/mfd/idt82p33_reg.h> #include "ptp_private.h" #include "ptp_idt82p33.h" @@ -24,15 +28,25 @@ MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FW_FILENAME); /* Module Parameters */ -static u32 sync_tod_timeout = SYNC_TOD_TIMEOUT_SEC; -module_param(sync_tod_timeout, uint, 0); -MODULE_PARM_DESC(sync_tod_timeout, -"duration in second to keep SYNC_TOD on (set to 0 to keep it always on)"); - static u32 phase_snap_threshold = SNAP_THRESHOLD_NS; module_param(phase_snap_threshold, uint, 0); MODULE_PARM_DESC(phase_snap_threshold, -"threshold (150000ns by default) below which adjtime would ignore"); +"threshold (10000ns by default) below which adjtime would use double dco"); + +static char *firmware; +module_param(firmware, charp, 0); + +static inline int idt82p33_read(struct idt82p33 *idt82p33, u16 regaddr, + u8 *buf, u16 count) +{ + return regmap_bulk_read(idt82p33->regmap, regaddr, buf, count); +} + +static inline int idt82p33_write(struct idt82p33 *idt82p33, u16 regaddr, + u8 *buf, u16 count) +{ + return regmap_bulk_write(idt82p33->regmap, regaddr, buf, count); +} static void idt82p33_byte_array_to_timespec(struct timespec64 *ts, u8 buf[TOD_BYTE_COUNT]) @@ -78,110 +92,6 @@ static void idt82p33_timespec_to_byte_array(struct timespec64 const *ts, } } -static int idt82p33_xfer_read(struct idt82p33 *idt82p33, - unsigned char regaddr, - unsigned char *buf, - unsigned int count) -{ - struct i2c_client *client = idt82p33->client; - struct i2c_msg msg[2]; - int cnt; - - msg[0].addr = client->addr; - msg[0].flags = 0; - msg[0].len = 1; - msg[0].buf = ®addr; - - msg[1].addr = client->addr; - msg[1].flags = I2C_M_RD; - msg[1].len = count; - msg[1].buf = buf; - - cnt = i2c_transfer(client->adapter, msg, 2); - if (cnt < 0) { - dev_err(&client->dev, "i2c_transfer returned %d\n", cnt); - return cnt; - } else if (cnt != 2) { - dev_err(&client->dev, - "i2c_transfer sent only %d of %d messages\n", cnt, 2); - return -EIO; - } - return 0; -} - -static int idt82p33_xfer_write(struct idt82p33 *idt82p33, - u8 regaddr, - u8 *buf, - u16 count) -{ - struct i2c_client *client = idt82p33->client; - /* we add 1 byte for device register */ - u8 msg[IDT82P33_MAX_WRITE_COUNT + 1]; - int err; - - if (count > IDT82P33_MAX_WRITE_COUNT) - return -EINVAL; - - msg[0] = regaddr; - memcpy(&msg[1], buf, count); - - err = i2c_master_send(client, msg, count + 1); - if (err < 0) { - dev_err(&client->dev, "i2c_master_send returned %d\n", err); - return err; - } - - return 0; -} - -static int idt82p33_page_offset(struct idt82p33 *idt82p33, unsigned char val) -{ - int err; - - if (idt82p33->page_offset == val) - return 0; - - err = idt82p33_xfer_write(idt82p33, PAGE_ADDR, &val, sizeof(val)); - if (err) - dev_err(&idt82p33->client->dev, - "failed to set page offset %d\n", val); - else - idt82p33->page_offset = val; - - return err; -} - -static int idt82p33_rdwr(struct idt82p33 *idt82p33, unsigned int regaddr, - unsigned char *buf, unsigned int count, bool write) -{ - u8 offset, page; - int err; - - page = _PAGE(regaddr); - offset = _OFFSET(regaddr); - - err = idt82p33_page_offset(idt82p33, page); - if (err) - return err; - - if (write) - return idt82p33_xfer_write(idt82p33, offset, buf, count); - - return idt82p33_xfer_read(idt82p33, offset, buf, count); -} - -static int idt82p33_read(struct idt82p33 *idt82p33, unsigned int regaddr, - unsigned char *buf, unsigned int count) -{ - return idt82p33_rdwr(idt82p33, regaddr, buf, count, false); -} - -static int idt82p33_write(struct idt82p33 *idt82p33, unsigned int regaddr, - unsigned char *buf, unsigned int count) -{ - return idt82p33_rdwr(idt82p33, regaddr, buf, count, true); -} - static int idt82p33_dpll_set_mode(struct idt82p33_channel *channel, enum pll_mode mode) { @@ -206,7 +116,7 @@ static int idt82p33_dpll_set_mode(struct idt82p33_channel *channel, if (err) return err; - channel->pll_mode = dpll_mode; + channel->pll_mode = mode; return 0; } @@ -467,7 +377,7 @@ static int idt82p33_measure_tod_write_overhead(struct idt82p33_channel *channel) err = idt82p33_measure_settime_gettime_gap_overhead(channel, &gap_ns); if (err) { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Failed in %s with err %d!\n", __func__, err); return err; } @@ -499,8 +409,8 @@ static int idt82p33_check_and_set_masks(struct idt82p33 *idt82p33, if (page == PLLMASK_ADDR_HI && offset == PLLMASK_ADDR_LO) { if ((val & 0xfc) || !(val & 0x3)) { - dev_err(&idt82p33->client->dev, - "Invalid PLL mask 0x%hhx\n", val); + dev_err(idt82p33->dev, + "Invalid PLL mask 0x%x\n", val); err = -EINVAL; } else { idt82p33->pll_mask = val; @@ -520,14 +430,14 @@ static void idt82p33_display_masks(struct idt82p33 *idt82p33) { u8 mask, i; - dev_info(&idt82p33->client->dev, + dev_info(idt82p33->dev, "pllmask = 0x%02x\n", idt82p33->pll_mask); for (i = 0; i < MAX_PHC_PLL; i++) { mask = 1 << i; if (mask & idt82p33->pll_mask) - dev_info(&idt82p33->client->dev, + dev_info(idt82p33->dev, "PLL%d output_mask = 0x%04x\n", i, idt82p33->channel[i].output_mask); } @@ -539,11 +449,6 @@ static int idt82p33_sync_tod(struct idt82p33_channel *channel, bool enable) u8 sync_cnfg; int err; - /* Turn it off after sync_tod_timeout seconds */ - if (enable && sync_tod_timeout) - ptp_schedule_worker(channel->ptp_clock, - sync_tod_timeout * HZ); - err = idt82p33_read(idt82p33, channel->dpll_sync_cnfg, &sync_cnfg, sizeof(sync_cnfg)); if (err) @@ -557,22 +462,6 @@ static int idt82p33_sync_tod(struct idt82p33_channel *channel, bool enable) &sync_cnfg, sizeof(sync_cnfg)); } -static long idt82p33_sync_tod_work_handler(struct ptp_clock_info *ptp) -{ - struct idt82p33_channel *channel = - container_of(ptp, struct idt82p33_channel, caps); - struct idt82p33 *idt82p33 = channel->idt82p33; - - mutex_lock(&idt82p33->reg_lock); - - (void)idt82p33_sync_tod(channel, false); - - mutex_unlock(&idt82p33->reg_lock); - - /* Return a negative value here to not reschedule */ - return -1; -} - static int idt82p33_output_enable(struct idt82p33_channel *channel, bool enable, unsigned int outn) { @@ -634,18 +523,11 @@ static int idt82p33_enable_tod(struct idt82p33_channel *channel) struct idt82p33 *idt82p33 = channel->idt82p33; struct timespec64 ts = {0, 0}; int err; - u8 val; - - val = 0; - err = idt82p33_write(idt82p33, channel->dpll_input_mode_cnfg, - &val, sizeof(val)); - if (err) - return err; err = idt82p33_measure_tod_write_overhead(channel); if (err) { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Failed in %s with err %d!\n", __func__, err); return err; } @@ -673,16 +555,14 @@ static void idt82p33_ptp_clock_unregister_all(struct idt82p33 *idt82p33) } static int idt82p33_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, int on) + struct ptp_clock_request *rq, int on) { struct idt82p33_channel *channel = container_of(ptp, struct idt82p33_channel, caps); struct idt82p33 *idt82p33 = channel->idt82p33; - int err; - - err = -EOPNOTSUPP; + int err = -EOPNOTSUPP; - mutex_lock(&idt82p33->reg_lock); + mutex_lock(idt82p33->lock); if (rq->type == PTP_CLK_REQ_PEROUT) { if (!on) @@ -690,15 +570,18 @@ static int idt82p33_enable(struct ptp_clock_info *ptp, &rq->perout); /* Only accept a 1-PPS aligned to the second. */ else if (rq->perout.start.nsec || rq->perout.period.sec != 1 || - rq->perout.period.nsec) { + rq->perout.period.nsec) err = -ERANGE; - } else + else err = idt82p33_perout_enable(channel, true, &rq->perout); } - mutex_unlock(&idt82p33->reg_lock); + mutex_unlock(idt82p33->lock); + if (err) + dev_err(idt82p33->dev, + "Failed in %s with err %d!\n", __func__, err); return err; } @@ -727,11 +610,11 @@ static int idt82p33_adjwritephase(struct ptp_clock_info *ptp, s32 offset_ns) val[3] = (offset_regval >> 24) & 0x1F; val[3] |= PH_OFFSET_EN; - mutex_lock(&idt82p33->reg_lock); + mutex_lock(idt82p33->lock); err = idt82p33_dpll_set_mode(channel, PLL_MODE_WPH); if (err) { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Failed in %s with err %d!\n", __func__, err); goto out; } @@ -740,7 +623,7 @@ static int idt82p33_adjwritephase(struct ptp_clock_info *ptp, s32 offset_ns) sizeof(val)); out: - mutex_unlock(&idt82p33->reg_lock); + mutex_unlock(idt82p33->lock); return err; } @@ -751,12 +634,12 @@ static int idt82p33_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) struct idt82p33 *idt82p33 = channel->idt82p33; int err; - mutex_lock(&idt82p33->reg_lock); + mutex_lock(idt82p33->lock); err = _idt82p33_adjfine(channel, scaled_ppm); + mutex_unlock(idt82p33->lock); if (err) - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Failed in %s with err %d!\n", __func__, err); - mutex_unlock(&idt82p33->reg_lock); return err; } @@ -768,29 +651,20 @@ static int idt82p33_adjtime(struct ptp_clock_info *ptp, s64 delta_ns) struct idt82p33 *idt82p33 = channel->idt82p33; int err; - mutex_lock(&idt82p33->reg_lock); + mutex_lock(idt82p33->lock); if (abs(delta_ns) < phase_snap_threshold) { - mutex_unlock(&idt82p33->reg_lock); + mutex_unlock(idt82p33->lock); return 0; } err = _idt82p33_adjtime(channel, delta_ns); - if (err) { - mutex_unlock(&idt82p33->reg_lock); - dev_err(&idt82p33->client->dev, - "Adjtime failed in %s with err %d!\n", __func__, err); - return err; - } + mutex_unlock(idt82p33->lock); - err = idt82p33_sync_tod(channel, true); if (err) - dev_err(&idt82p33->client->dev, - "Sync_tod failed in %s with err %d!\n", __func__, err); - - mutex_unlock(&idt82p33->reg_lock); - + dev_err(idt82p33->dev, + "Failed in %s with err %d!\n", __func__, err); return err; } @@ -801,31 +675,31 @@ static int idt82p33_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) struct idt82p33 *idt82p33 = channel->idt82p33; int err; - mutex_lock(&idt82p33->reg_lock); + mutex_lock(idt82p33->lock); err = _idt82p33_gettime(channel, ts); + mutex_unlock(idt82p33->lock); + if (err) - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Failed in %s with err %d!\n", __func__, err); - mutex_unlock(&idt82p33->reg_lock); - return err; } static int idt82p33_settime(struct ptp_clock_info *ptp, - const struct timespec64 *ts) + const struct timespec64 *ts) { struct idt82p33_channel *channel = container_of(ptp, struct idt82p33_channel, caps); struct idt82p33 *idt82p33 = channel->idt82p33; int err; - mutex_lock(&idt82p33->reg_lock); + mutex_lock(idt82p33->lock); err = _idt82p33_settime(channel, ts); + mutex_unlock(idt82p33->lock); + if (err) - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Failed in %s with err %d!\n", __func__, err); - mutex_unlock(&idt82p33->reg_lock); - return err; } @@ -864,7 +738,7 @@ static int idt82p33_channel_init(struct idt82p33_channel *channel, int index) static void idt82p33_caps_init(struct ptp_clock_info *caps) { caps->owner = THIS_MODULE; - caps->max_adj = 92000; + caps->max_adj = DCO_MAX_PPB; caps->n_per_out = 11; caps->adjphase = idt82p33_adjwritephase; caps->adjfine = idt82p33_adjfine; @@ -872,7 +746,6 @@ static void idt82p33_caps_init(struct ptp_clock_info *caps) caps->gettime64 = idt82p33_gettime; caps->settime64 = idt82p33_settime; caps->enable = idt82p33_enable; - caps->do_aux_work = idt82p33_sync_tod_work_handler; } static int idt82p33_enable_channel(struct idt82p33 *idt82p33, u32 index) @@ -887,7 +760,7 @@ static int idt82p33_enable_channel(struct idt82p33 *idt82p33, u32 index) err = idt82p33_channel_init(channel, index); if (err) { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Channel_init failed in %s with err %d!\n", __func__, err); return err; @@ -912,7 +785,7 @@ static int idt82p33_enable_channel(struct idt82p33 *idt82p33, u32 index) err = idt82p33_dpll_set_mode(channel, PLL_MODE_DCO); if (err) { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Dpll_set_mode failed in %s with err %d!\n", __func__, err); return err; @@ -920,13 +793,13 @@ static int idt82p33_enable_channel(struct idt82p33 *idt82p33, u32 index) err = idt82p33_enable_tod(channel); if (err) { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Enable_tod failed in %s with err %d!\n", __func__, err); return err; } - dev_info(&idt82p33->client->dev, "PLL%d registered as ptp%d\n", + dev_info(idt82p33->dev, "PLL%d registered as ptp%d\n", index, channel->ptp_clock->index); return 0; @@ -940,25 +813,24 @@ static int idt82p33_load_firmware(struct idt82p33 *idt82p33) int err; s32 len; - dev_dbg(&idt82p33->client->dev, - "requesting firmware '%s'\n", FW_FILENAME); + dev_dbg(idt82p33->dev, "requesting firmware '%s'\n", FW_FILENAME); - err = request_firmware(&fw, FW_FILENAME, &idt82p33->client->dev); + err = request_firmware(&fw, FW_FILENAME, idt82p33->dev); if (err) { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Failed in %s with err %d!\n", __func__, err); return err; } - dev_dbg(&idt82p33->client->dev, "firmware size %zu bytes\n", fw->size); + dev_dbg(idt82p33->dev, "firmware size %zu bytes\n", fw->size); rec = (struct idt82p33_fwrc *) fw->data; for (len = fw->size; len > 0; len -= sizeof(*rec)) { if (rec->reserved) { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "bad firmware, reserved field non-zero\n"); err = -EINVAL; } else { @@ -973,16 +845,11 @@ static int idt82p33_load_firmware(struct idt82p33 *idt82p33) } if (err == 0) { - /* maximum 8 pages */ - if (page >= PAGE_NUM) - continue; - /* Page size 128, last 4 bytes of page skipped */ - if (((loaddr > 0x7b) && (loaddr <= 0x7f)) - || loaddr > 0xfb) + if (loaddr > 0x7b) continue; - err = idt82p33_write(idt82p33, _ADDR(page, loaddr), + err = idt82p33_write(idt82p33, REG_ADDR(page, loaddr), &val, sizeof(val)); } @@ -997,36 +864,34 @@ out: } -static int idt82p33_probe(struct i2c_client *client, - const struct i2c_device_id *id) +static int idt82p33_probe(struct platform_device *pdev) { + struct rsmu_ddata *ddata = dev_get_drvdata(pdev->dev.parent); struct idt82p33 *idt82p33; int err; u8 i; - (void)id; - - idt82p33 = devm_kzalloc(&client->dev, + idt82p33 = devm_kzalloc(&pdev->dev, sizeof(struct idt82p33), GFP_KERNEL); if (!idt82p33) return -ENOMEM; - mutex_init(&idt82p33->reg_lock); - - idt82p33->client = client; - idt82p33->page_offset = 0xff; + idt82p33->dev = &pdev->dev; + idt82p33->mfd = pdev->dev.parent; + idt82p33->lock = &ddata->lock; + idt82p33->regmap = ddata->regmap; idt82p33->tod_write_overhead_ns = 0; idt82p33->calculate_overhead_flag = 0; idt82p33->pll_mask = DEFAULT_PLL_MASK; idt82p33->channel[0].output_mask = DEFAULT_OUTPUT_MASK_PLL0; idt82p33->channel[1].output_mask = DEFAULT_OUTPUT_MASK_PLL1; - mutex_lock(&idt82p33->reg_lock); + mutex_lock(idt82p33->lock); err = idt82p33_load_firmware(idt82p33); if (err) - dev_warn(&idt82p33->client->dev, + dev_warn(idt82p33->dev, "loading firmware failed with %d\n", err); if (idt82p33->pll_mask) { @@ -1034,7 +899,7 @@ static int idt82p33_probe(struct i2c_client *client, if (idt82p33->pll_mask & (1 << i)) { err = idt82p33_enable_channel(idt82p33, i); if (err) { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "Failed in %s with err %d!\n", __func__, err); break; @@ -1042,69 +907,38 @@ static int idt82p33_probe(struct i2c_client *client, } } } else { - dev_err(&idt82p33->client->dev, + dev_err(idt82p33->dev, "no PLLs flagged as PHCs, nothing to do\n"); err = -ENODEV; } - mutex_unlock(&idt82p33->reg_lock); + mutex_unlock(idt82p33->lock); if (err) { idt82p33_ptp_clock_unregister_all(idt82p33); return err; } - i2c_set_clientdata(client, idt82p33); + platform_set_drvdata(pdev, idt82p33); return 0; } -static int idt82p33_remove(struct i2c_client *client) +static int idt82p33_remove(struct platform_device *pdev) { - struct idt82p33 *idt82p33 = i2c_get_clientdata(client); + struct idt82p33 *idt82p33 = platform_get_drvdata(pdev); idt82p33_ptp_clock_unregister_all(idt82p33); - mutex_destroy(&idt82p33->reg_lock); return 0; } -#ifdef CONFIG_OF -static const struct of_device_id idt82p33_dt_id[] = { - { .compatible = "idt,82p33810" }, - { .compatible = "idt,82p33813" }, - { .compatible = "idt,82p33814" }, - { .compatible = "idt,82p33831" }, - { .compatible = "idt,82p33910" }, - { .compatible = "idt,82p33913" }, - { .compatible = "idt,82p33914" }, - { .compatible = "idt,82p33931" }, - {}, -}; -MODULE_DEVICE_TABLE(of, idt82p33_dt_id); -#endif - -static const struct i2c_device_id idt82p33_i2c_id[] = { - { "idt82p33810", }, - { "idt82p33813", }, - { "idt82p33814", }, - { "idt82p33831", }, - { "idt82p33910", }, - { "idt82p33913", }, - { "idt82p33914", }, - { "idt82p33931", }, - {}, -}; -MODULE_DEVICE_TABLE(i2c, idt82p33_i2c_id); - -static struct i2c_driver idt82p33_driver = { +static struct platform_driver idt82p33_driver = { .driver = { - .of_match_table = of_match_ptr(idt82p33_dt_id), - .name = "idt82p33", + .name = "82p33x1x-phc", }, - .probe = idt82p33_probe, - .remove = idt82p33_remove, - .id_table = idt82p33_i2c_id, + .probe = idt82p33_probe, + .remove = idt82p33_remove, }; -module_i2c_driver(idt82p33_driver); +module_platform_driver(idt82p33_driver); diff --git a/drivers/ptp/ptp_idt82p33.h b/drivers/ptp/ptp_idt82p33.h index 1c7a0f0872e8..0ea1c35c0f9f 100644 --- a/drivers/ptp/ptp_idt82p33.h +++ b/drivers/ptp/ptp_idt82p33.h @@ -8,94 +8,19 @@ #define PTP_IDT82P33_H #include <linux/ktime.h> -#include <linux/workqueue.h> +#include <linux/mfd/idt82p33_reg.h> +#include <linux/regmap.h> - -/* Register Map - AN888_SMUforIEEE_SynchEther_82P33xxx_RevH.pdf */ -#define PAGE_NUM (8) -#define _ADDR(page, offset) (((page) << 0x7) | ((offset) & 0x7f)) -#define _PAGE(addr) (((addr) >> 0x7) & 0x7) -#define _OFFSET(addr) ((addr) & 0x7f) - -#define DPLL1_TOD_CNFG 0x134 -#define DPLL2_TOD_CNFG 0x1B4 - -#define DPLL1_TOD_STS 0x10B -#define DPLL2_TOD_STS 0x18B - -#define DPLL1_TOD_TRIGGER 0x115 -#define DPLL2_TOD_TRIGGER 0x195 - -#define DPLL1_OPERATING_MODE_CNFG 0x120 -#define DPLL2_OPERATING_MODE_CNFG 0x1A0 - -#define DPLL1_HOLDOVER_FREQ_CNFG 0x12C -#define DPLL2_HOLDOVER_FREQ_CNFG 0x1AC - -#define DPLL1_PHASE_OFFSET_CNFG 0x143 -#define DPLL2_PHASE_OFFSET_CNFG 0x1C3 - -#define DPLL1_SYNC_EDGE_CNFG 0X140 -#define DPLL2_SYNC_EDGE_CNFG 0X1C0 - -#define DPLL1_INPUT_MODE_CNFG 0X116 -#define DPLL2_INPUT_MODE_CNFG 0X196 - -#define OUT_MUX_CNFG(outn) _ADDR(0x6, (0xC * (outn))) - -#define PAGE_ADDR 0x7F -/* Register Map end */ - -/* Register definitions - AN888_SMUforIEEE_SynchEther_82P33xxx_RevH.pdf*/ -#define TOD_TRIGGER(wr_trig, rd_trig) ((wr_trig & 0xf) << 4 | (rd_trig & 0xf)) -#define SYNC_TOD BIT(1) -#define PH_OFFSET_EN BIT(7) -#define SQUELCH_ENABLE BIT(5) - -/* Bit definitions for the DPLL_MODE register */ -#define PLL_MODE_SHIFT (0) -#define PLL_MODE_MASK (0x1F) - -#define PEROUT_ENABLE_OUTPUT_MASK (0xdeadbeef) - -enum pll_mode { - PLL_MODE_MIN = 0, - PLL_MODE_AUTOMATIC = PLL_MODE_MIN, - PLL_MODE_FORCE_FREERUN = 1, - PLL_MODE_FORCE_HOLDOVER = 2, - PLL_MODE_FORCE_LOCKED = 4, - PLL_MODE_FORCE_PRE_LOCKED2 = 5, - PLL_MODE_FORCE_PRE_LOCKED = 6, - PLL_MODE_FORCE_LOST_PHASE = 7, - PLL_MODE_DCO = 10, - PLL_MODE_WPH = 18, - PLL_MODE_MAX = PLL_MODE_WPH, -}; - -enum hw_tod_trig_sel { - HW_TOD_TRIG_SEL_MIN = 0, - HW_TOD_TRIG_SEL_NO_WRITE = HW_TOD_TRIG_SEL_MIN, - HW_TOD_TRIG_SEL_SYNC_SEL = 1, - HW_TOD_TRIG_SEL_IN12 = 2, - HW_TOD_TRIG_SEL_IN13 = 3, - HW_TOD_TRIG_SEL_IN14 = 4, - HW_TOD_TRIG_SEL_TOD_PPS = 5, - HW_TOD_TRIG_SEL_TIMER_INTERVAL = 6, - HW_TOD_TRIG_SEL_MSB_PHASE_OFFSET_CNFG = 7, - HW_TOD_TRIG_SEL_MSB_HOLDOVER_FREQ_CNFG = 8, - HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG = 9, - HW_TOD_RD_TRIG_SEL_LSB_TOD_STS = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, - WR_TRIG_SEL_MAX = HW_TOD_WR_TRIG_SEL_MSB_TOD_CNFG, -}; - -/* Register bit definitions end */ #define FW_FILENAME "idt82p33xxx.bin" -#define MAX_PHC_PLL (2) -#define TOD_BYTE_COUNT (10) -#define MAX_MEASURMENT_COUNT (5) -#define SNAP_THRESHOLD_NS (150000) -#define SYNC_TOD_TIMEOUT_SEC (5) -#define IDT82P33_MAX_WRITE_COUNT (512) +#define MAX_PHC_PLL (2) +#define TOD_BYTE_COUNT (10) +#define DCO_MAX_PPB (92000) +#define MAX_MEASURMENT_COUNT (5) +#define SNAP_THRESHOLD_NS (10000) +#define IMMEDIATE_SNAP_THRESHOLD_NS (50000) +#define DDCO_THRESHOLD_NS (5) +#define IDT82P33_MAX_WRITE_COUNT (512) +#define PEROUT_ENABLE_OUTPUT_MASK (0xdeadbeef) #define PLLMASK_ADDR_HI 0xFF #define PLLMASK_ADDR_LO 0xA5 @@ -116,15 +41,25 @@ enum hw_tod_trig_sel { #define DEFAULT_OUTPUT_MASK_PLL0 (0xc0) #define DEFAULT_OUTPUT_MASK_PLL1 DEFAULT_OUTPUT_MASK_PLL0 +/** + * @brief Maximum absolute value for write phase offset in femtoseconds + */ +#define WRITE_PHASE_OFFSET_LIMIT (20000052084ll) + +/** @brief Phase offset resolution + * + * DPLL phase offset = 10^15 fs / ( System Clock * 2^13) + * = 10^15 fs / ( 1638400000 * 2^23) + * = 74.5058059692382 fs + */ +#define IDT_T0DPLL_PHASE_RESOL 74506 + /* PTP Hardware Clock interface */ struct idt82p33_channel { struct ptp_clock_info caps; struct ptp_clock *ptp_clock; - struct idt82p33 *idt82p33; - enum pll_mode pll_mode; - /* task to turn off SYNC_TOD bit after pps sync */ - struct delayed_work sync_tod_work; - bool sync_tod_on; + struct idt82p33 *idt82p33; + enum pll_mode pll_mode; s32 current_freq_ppb; u8 output_mask; u16 dpll_tod_cnfg; @@ -138,15 +73,17 @@ struct idt82p33_channel { }; struct idt82p33 { - struct idt82p33_channel channel[MAX_PHC_PLL]; - struct i2c_client *client; - u8 page_offset; - u8 pll_mask; - ktime_t start_time; - int calculate_overhead_flag; - s64 tod_write_overhead_ns; - /* Protects I2C read/modify/write registers from concurrent access */ - struct mutex reg_lock; + struct idt82p33_channel channel[MAX_PHC_PLL]; + struct device *dev; + u8 pll_mask; + /* Mutex to protect operations from being interrupted */ + struct mutex *lock; + struct regmap *regmap; + struct device *mfd; + /* Overhead calculation for adjtime */ + ktime_t start_time; + int calculate_overhead_flag; + s64 tod_write_overhead_ns; }; /* firmware interface */ @@ -157,18 +94,4 @@ struct idt82p33_fwrc { u8 reserved; } __packed; -/** - * @brief Maximum absolute value for write phase offset in femtoseconds - */ -#define WRITE_PHASE_OFFSET_LIMIT (20000052084ll) - -/** @brief Phase offset resolution - * - * DPLL phase offset = 10^15 fs / ( System Clock * 2^13) - * = 10^15 fs / ( 1638400000 * 2^23) - * = 74.5058059692382 fs - */ -#define IDT_T0DPLL_PHASE_RESOL 74506 - - #endif /* PTP_IDT82P33_H */ 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/mfd/idt82p33_reg.h b/include/linux/mfd/idt82p33_reg.h index 129a6c078221..1db532feeb91 100644 --- a/include/linux/mfd/idt82p33_reg.h +++ b/include/linux/mfd/idt82p33_reg.h @@ -7,6 +7,8 @@ #ifndef HAVE_IDT82P33_REG #define HAVE_IDT82P33_REG +#define REG_ADDR(page, offset) (((page) << 0x7) | ((offset) & 0x7f)) + /* Register address */ #define DPLL1_TOD_CNFG 0x134 #define DPLL2_TOD_CNFG 0x1B4 @@ -41,6 +43,7 @@ #define REG_SOFT_RESET 0X381 #define OUT_MUX_CNFG(outn) REG_ADDR(0x6, (0xC * (outn))) +#define TOD_TRIGGER(wr_trig, rd_trig) ((wr_trig & 0xf) << 4 | (rd_trig & 0xf)) /* Register bit definitions */ #define SYNC_TOD BIT(1) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d3b1a6a1f8d2..00a914b0716e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -264,6 +264,14 @@ enum { struct mlx5_cmd_stats { u64 sum; u64 n; + /* number of times command failed */ + u64 failed; + /* number of times command failed on bad status returned by FW */ + u64 failed_mbox_status; + /* last command failed returned errno */ + u32 last_failed_errno; + /* last bad status returned by FW */ + u8 last_failed_mbox_status; struct dentry *root; /* protect command average calculations */ spinlock_t lock; @@ -543,6 +551,15 @@ struct mlx5_adev { int idx; }; +struct mlx5_debugfs_entries { + struct dentry *dbg_root; + struct dentry *qp_debugfs; + struct dentry *eq_debugfs; + struct dentry *cq_debugfs; + struct dentry *cmdif_debugfs; + struct dentry *pages_debugfs; +}; + struct mlx5_ft_pool; struct mlx5_priv { /* IRQ table valid only for real pci devices PF or VF */ @@ -553,21 +570,19 @@ struct mlx5_priv { struct mlx5_nb pg_nb; struct workqueue_struct *pg_wq; struct xarray page_root_xa; - int fw_pages; + u32 fw_pages; atomic_t reg_pages; struct list_head free_list; - int vfs_pages; - int host_pf_pages; + u32 vfs_pages; + u32 host_pf_pages; + u32 fw_pages_alloc_failed; + u32 give_pages_dropped; + u32 reclaim_pages_discard; struct mlx5_core_health health; struct list_head traps; - /* start: qp staff */ - struct dentry *qp_debugfs; - struct dentry *eq_debugfs; - struct dentry *cq_debugfs; - struct dentry *cmdif_debugfs; - /* end: qp staff */ + struct mlx5_debugfs_entries dbg; /* start: alloc staff */ /* protect buffer allocation according to numa node */ @@ -577,7 +592,6 @@ struct mlx5_priv { struct mutex pgdir_mutex; struct list_head pgdir_list; /* end: alloc staff */ - struct dentry *dbg_root; struct list_head ctx_list; spinlock_t ctx_lock; @@ -955,6 +969,7 @@ typedef void (*mlx5_async_cbk_t)(int status, struct mlx5_async_work *context); struct mlx5_async_work { struct mlx5_async_ctx *ctx; mlx5_async_cbk_t user_callback; + u16 opcode; /* cmd opcode */ void *out; /* pointer to the cmd output buffer */ }; @@ -1015,6 +1030,8 @@ int mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); void mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); +void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, s32 npages, bool ec_function); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); @@ -1029,6 +1046,7 @@ int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn); int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn); +struct dentry *mlx5_debugfs_get_dev_root(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev); void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_access_reg(struct mlx5_core_dev *dev, void *data_in, int size_in, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ea65131835ab..318fae4b3560 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -493,7 +493,10 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_at_c0[0x18]; + u8 reserved_at_c0[0x10]; + u8 ipv4_ihl[0x4]; + u8 reserved_at_c4[0x4]; + u8 ttl_hoplimit[0x8]; u8 udp_sport[0x10]; @@ -1343,6 +1346,7 @@ enum mlx5_fc_bulk_alloc_bitmask { enum { MLX5_STEERING_FORMAT_CONNECTX_5 = 0, MLX5_STEERING_FORMAT_CONNECTX_6DX = 1, + MLX5_STEERING_FORMAT_CONNECTX_7 = 2, }; struct mlx5_ifc_cmd_hca_cap_bits { @@ -1419,8 +1423,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 reserved_at_130[0xa]; u8 log_max_ra_res_dc[0x6]; - u8 reserved_at_140[0x6]; + u8 reserved_at_140[0x5]; u8 release_all_pages[0x1]; + u8 must_not_use[0x1]; u8 reserved_at_147[0x2]; u8 roce_accl[0x1]; u8 log_max_ra_req_qp[0x6]; @@ -3427,7 +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 { @@ -9894,8 +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/net/netns/ipv4.h b/include/net/netns/ipv4.h index f0687867b5cd..ce0cc4e8d8c7 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -127,6 +127,7 @@ struct netns_ipv4 { u8 sysctl_tcp_synack_retries; u8 sysctl_tcp_syncookies; u8 sysctl_tcp_migrate_req; + u8 sysctl_tcp_comp_sack_nr; int sysctl_tcp_reordering; u8 sysctl_tcp_retries1; u8 sysctl_tcp_retries2; @@ -160,9 +161,9 @@ struct netns_ipv4 { int sysctl_tcp_challenge_ack_limit; int sysctl_tcp_min_rtt_wlen; u8 sysctl_tcp_min_tso_segs; + u8 sysctl_tcp_tso_rtt_log; u8 sysctl_tcp_autocorking; u8 sysctl_tcp_reflect_tos; - u8 sysctl_tcp_comp_sack_nr; int sysctl_tcp_invalid_ratelimit; int sysctl_tcp_pacing_ss_ratio; int sysctl_tcp_pacing_ca_ratio; diff --git a/include/net/tcp.h b/include/net/tcp.h index ee8237b58e1d..70ca4a5e330a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1693,7 +1693,7 @@ tcp_md5_do_lookup(const struct sock *sk, int l3index, static inline enum skb_drop_reason tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, const void *saddr, const void *daddr, - int family, int dif, int sdif); + int family, int dif, int sdif) { return SKB_NOT_DROPPED_YET; } diff --git a/include/net/tls.h b/include/net/tls.h index 526cb2c3b724..b6968a5b5538 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -626,7 +626,6 @@ tls_offload_ctx_rx(const struct tls_context *tls_ctx) return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx; } -#if IS_ENABLED(CONFIG_TLS_DEVICE) static inline void *__tls_driver_ctx(struct tls_context *tls_ctx, enum tls_offload_ctx_dir direction) { @@ -641,7 +640,6 @@ tls_driver_ctx(const struct sock *sk, enum tls_offload_ctx_dir direction) { return __tls_driver_ctx(tls_get_ctx(sk), direction); } -#endif #define RESYNC_REQ BIT(0) #define RESYNC_REQ_ASYNC BIT(1) diff --git a/include/uapi/linux/can/isotp.h b/include/uapi/linux/can/isotp.h index c55935b64ccc..590f8aea2b6d 100644 --- a/include/uapi/linux/can/isotp.h +++ b/include/uapi/linux/can/isotp.h @@ -137,20 +137,16 @@ struct can_isotp_ll_options { #define CAN_ISOTP_WAIT_TX_DONE 0x400 /* wait for tx completion */ #define CAN_ISOTP_SF_BROADCAST 0x800 /* 1-to-N functional addressing */ -/* default values */ +/* protocol machine default values */ #define CAN_ISOTP_DEFAULT_FLAGS 0 #define CAN_ISOTP_DEFAULT_EXT_ADDRESS 0x00 #define CAN_ISOTP_DEFAULT_PAD_CONTENT 0xCC /* prevent bit-stuffing */ -#define CAN_ISOTP_DEFAULT_FRAME_TXTIME 0 +#define CAN_ISOTP_DEFAULT_FRAME_TXTIME 50000 /* 50 micro seconds */ #define CAN_ISOTP_DEFAULT_RECV_BS 0 #define CAN_ISOTP_DEFAULT_RECV_STMIN 0x00 #define CAN_ISOTP_DEFAULT_RECV_WFTMAX 0 -#define CAN_ISOTP_DEFAULT_LL_MTU CAN_MTU -#define CAN_ISOTP_DEFAULT_LL_TX_DL CAN_MAX_DLEN -#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS 0 - /* * Remark on CAN_ISOTP_DEFAULT_RECV_* values: * @@ -162,4 +158,24 @@ struct can_isotp_ll_options { * consistency and copied directly into the flow control (FC) frame. */ +/* link layer default values => make use of Classical CAN frames */ + +#define CAN_ISOTP_DEFAULT_LL_MTU CAN_MTU +#define CAN_ISOTP_DEFAULT_LL_TX_DL CAN_MAX_DLEN +#define CAN_ISOTP_DEFAULT_LL_TX_FLAGS 0 + +/* + * The CAN_ISOTP_DEFAULT_FRAME_TXTIME has become a non-zero value as + * it only makes sense for isotp implementation tests to run without + * a N_As value. As user space applications usually do not set the + * frame_txtime element of struct can_isotp_options the new in-kernel + * default is very likely overwritten with zero when the sockopt() + * CAN_ISOTP_OPTS is invoked. + * To make sure that a N_As value of zero is only set intentional the + * value '0' is now interpreted as 'do not change the current value'. + * When a frame_txtime of zero is required for testing purposes this + * CAN_ISOTP_FRAME_TXTIME_ZERO u32 value has to be set in frame_txtime. + */ +#define CAN_ISOTP_FRAME_TXTIME_ZERO 0xFFFFFFFF + #endif /* !_UAPI_CAN_ISOTP_H */ 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/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 9d1710f20505..ce3e1738d427 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -351,11 +351,21 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, /* struct ovs_key_ct_tuple_ipv4 */ OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, /* struct ovs_key_ct_tuple_ipv6 */ OVS_KEY_ATTR_NSH, /* Nested set of ovs_nsh_key_* */ - OVS_KEY_ATTR_IPV6_EXTHDRS, /* struct ovs_key_ipv6_exthdr */ -#ifdef __KERNEL__ - OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ -#endif + /* User space decided to squat on types 29 and 30. They are defined + * below, but should not be sent to the kernel. + * + * WARNING: No new types should be added unless they are defined + * for both kernel and user space (no 'ifdef's). It's hard + * to keep compatibility otherwise. + */ + OVS_KEY_ATTR_PACKET_TYPE, /* be32 packet type */ + OVS_KEY_ATTR_ND_EXTENSIONS, /* IPv6 Neighbor Discovery extensions */ + + OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info. + * For in-kernel use only. + */ + OVS_KEY_ATTR_IPV6_EXTHDRS, /* struct ovs_key_ipv6_exthdr */ __OVS_KEY_ATTR_MAX }; 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/can/isotp.c b/net/can/isotp.c index d2a430b6a13b..d4c0b4704987 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -14,7 +14,6 @@ * - use CAN_ISOTP_WAIT_TX_DONE flag to block the caller until the PDU is sent * - as we have static buffers the check whether the PDU fits into the buffer * is done at FF reception time (no support for sending 'wait frames') - * - take care of the tx-queue-len as traffic shaping is still on the TODO list * * Copyright (c) 2020 Volkswagen Group Electronic Research * All rights reserved. @@ -87,9 +86,9 @@ MODULE_ALIAS("can-proto-6"); /* ISO 15765-2:2016 supports more than 4095 byte per ISO PDU as the FF_DL can * take full 32 bit values (4 Gbyte). We would need some good concept to handle * this between user space and kernel space. For now increase the static buffer - * to something about 8 kbyte to be able to test this new functionality. + * to something about 64 kbyte to be able to test this new functionality. */ -#define MAX_MSG_LENGTH 8200 +#define MAX_MSG_LENGTH 66000 /* N_PCI type values in bits 7-4 of N_PCI bytes */ #define N_PCI_SF 0x00 /* single frame */ @@ -141,8 +140,10 @@ struct isotp_sock { struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; + u32 frame_txtime; u32 force_tx_stmin; u32 force_rx_stmin; + u32 cfecho; /* consecutive frame echo tag */ struct tpcon rx, tx; struct list_head notifier; wait_queue_head_t wait; @@ -360,7 +361,7 @@ static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae) so->tx_gap = ktime_set(0, 0); /* add transmission time for CAN frame N_As */ - so->tx_gap = ktime_add_ns(so->tx_gap, so->opt.frame_txtime); + so->tx_gap = ktime_add_ns(so->tx_gap, so->frame_txtime); /* add waiting time for consecutive frames N_Cs */ if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN) so->tx_gap = ktime_add_ns(so->tx_gap, @@ -712,6 +713,63 @@ static void isotp_fill_dataframe(struct canfd_frame *cf, struct isotp_sock *so, cf->data[0] = so->opt.ext_address; } +static void isotp_send_cframe(struct isotp_sock *so) +{ + struct sock *sk = &so->sk; + struct sk_buff *skb; + struct net_device *dev; + struct canfd_frame *cf; + int can_send_ret; + int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; + + dev = dev_get_by_index(sock_net(sk), so->ifindex); + if (!dev) + return; + + skb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), GFP_ATOMIC); + if (!skb) { + dev_put(dev); + return; + } + + can_skb_reserve(skb); + can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + + cf = (struct canfd_frame *)skb->data; + skb_put_zero(skb, so->ll.mtu); + + /* create consecutive frame */ + isotp_fill_dataframe(cf, so, ae, 0); + + /* place consecutive frame N_PCI in appropriate index */ + cf->data[ae] = N_PCI_CF | so->tx.sn++; + so->tx.sn %= 16; + so->tx.bs++; + + cf->flags = so->ll.tx_flags; + + skb->dev = dev; + can_skb_set_owner(skb, sk); + + /* cfecho should have been zero'ed by init/isotp_rcv_echo() */ + if (so->cfecho) + pr_notice_once("can-isotp: cfecho is %08X != 0\n", so->cfecho); + + /* set consecutive frame echo tag */ + so->cfecho = *(u32 *)cf->data; + + /* send frame with local echo enabled */ + can_send_ret = can_send(skb, 1); + if (can_send_ret) { + pr_notice_once("can-isotp: %s: can_send_ret %pe\n", + __func__, ERR_PTR(can_send_ret)); + if (can_send_ret == -ENOBUFS) + pr_notice_once("can-isotp: tx queue is full\n"); + } + dev_put(dev); +} + static void isotp_create_fframe(struct canfd_frame *cf, struct isotp_sock *so, int ae) { @@ -748,19 +806,74 @@ static void isotp_create_fframe(struct canfd_frame *cf, struct isotp_sock *so, so->tx.state = ISOTP_WAIT_FIRST_FC; } +static void isotp_rcv_echo(struct sk_buff *skb, void *data) +{ + struct sock *sk = (struct sock *)data; + struct isotp_sock *so = isotp_sk(sk); + struct canfd_frame *cf = (struct canfd_frame *)skb->data; + + /* only handle my own local echo skb's */ + if (skb->sk != sk || so->cfecho != *(u32 *)cf->data) + return; + + /* cancel local echo timeout */ + hrtimer_cancel(&so->txtimer); + + /* local echo skb with consecutive frame has been consumed */ + so->cfecho = 0; + + if (so->tx.idx >= so->tx.len) { + /* we are done */ + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); + return; + } + + if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { + /* stop and wait for FC with timeout */ + so->tx.state = ISOTP_WAIT_FC; + hrtimer_start(&so->txtimer, ktime_set(1, 0), + HRTIMER_MODE_REL_SOFT); + return; + } + + /* no gap between data frames needed => use burst mode */ + if (!so->tx_gap) { + isotp_send_cframe(so); + return; + } + + /* start timer to send next consecutive frame with correct delay */ + hrtimer_start(&so->txtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); +} + static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) { struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txtimer); struct sock *sk = &so->sk; - struct sk_buff *skb; - struct net_device *dev; - struct canfd_frame *cf; enum hrtimer_restart restart = HRTIMER_NORESTART; - int can_send_ret; - int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0; switch (so->tx.state) { + case ISOTP_SENDING: + + /* cfecho should be consumed by isotp_rcv_echo() here */ + if (!so->cfecho) { + /* start timeout for unlikely lost echo skb */ + hrtimer_set_expires(&so->txtimer, + ktime_add(ktime_get(), + ktime_set(2, 0))); + restart = HRTIMER_RESTART; + + /* push out the next consecutive frame */ + isotp_send_cframe(so); + break; + } + + /* cfecho has not been cleared in isotp_rcv_echo() */ + pr_notice_once("can-isotp: cfecho %08X timeout\n", so->cfecho); + fallthrough; + case ISOTP_WAIT_FC: case ISOTP_WAIT_FIRST_FC: @@ -776,78 +889,6 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) wake_up_interruptible(&so->wait); break; - case ISOTP_SENDING: - - /* push out the next segmented pdu */ - dev = dev_get_by_index(sock_net(sk), so->ifindex); - if (!dev) - break; - -isotp_tx_burst: - skb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), - GFP_ATOMIC); - if (!skb) { - dev_put(dev); - break; - } - - can_skb_reserve(skb); - can_skb_prv(skb)->ifindex = dev->ifindex; - can_skb_prv(skb)->skbcnt = 0; - - cf = (struct canfd_frame *)skb->data; - skb_put_zero(skb, so->ll.mtu); - - /* create consecutive frame */ - isotp_fill_dataframe(cf, so, ae, 0); - - /* place consecutive frame N_PCI in appropriate index */ - cf->data[ae] = N_PCI_CF | so->tx.sn++; - so->tx.sn %= 16; - so->tx.bs++; - - cf->flags = so->ll.tx_flags; - - skb->dev = dev; - can_skb_set_owner(skb, sk); - - can_send_ret = can_send(skb, 1); - if (can_send_ret) { - pr_notice_once("can-isotp: %s: can_send_ret %pe\n", - __func__, ERR_PTR(can_send_ret)); - if (can_send_ret == -ENOBUFS) - pr_notice_once("can-isotp: tx queue is full, increasing txqueuelen may prevent this error\n"); - } - if (so->tx.idx >= so->tx.len) { - /* we are done */ - so->tx.state = ISOTP_IDLE; - dev_put(dev); - wake_up_interruptible(&so->wait); - break; - } - - if (so->txfc.bs && so->tx.bs >= so->txfc.bs) { - /* stop and wait for FC */ - so->tx.state = ISOTP_WAIT_FC; - dev_put(dev); - hrtimer_set_expires(&so->txtimer, - ktime_add(ktime_get(), - ktime_set(1, 0))); - restart = HRTIMER_RESTART; - break; - } - - /* no gap between data frames needed => use burst mode */ - if (!so->tx_gap) - goto isotp_tx_burst; - - /* start timer to send next data frame with correct delay */ - dev_put(dev); - hrtimer_set_expires(&so->txtimer, - ktime_add(ktime_get(), so->tx_gap)); - restart = HRTIMER_RESTART; - break; - default: WARN_ON_ONCE(1); } @@ -1075,6 +1116,9 @@ static int isotp_release(struct socket *sock) can_rx_unregister(net, dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); + can_rx_unregister(net, dev, so->txid, + SINGLE_MASK(so->txid), + isotp_rcv_echo, sk); dev_put(dev); synchronize_rcu(); } @@ -1161,11 +1205,20 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) ifindex = dev->ifindex; - if (do_rx_reg) + if (do_rx_reg) { can_rx_register(net, dev, addr->can_addr.tp.rx_id, SINGLE_MASK(addr->can_addr.tp.rx_id), isotp_rcv, sk, "isotp", sk); + /* no consecutive frame echo skb in flight */ + so->cfecho = 0; + + /* register for echo skb's */ + can_rx_register(net, dev, addr->can_addr.tp.tx_id, + SINGLE_MASK(addr->can_addr.tp.tx_id), + isotp_rcv_echo, sk, "isotpe", sk); + } + dev_put(dev); if (so->bound && do_rx_reg) { @@ -1176,6 +1229,9 @@ static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) can_rx_unregister(net, dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); + can_rx_unregister(net, dev, so->txid, + SINGLE_MASK(so->txid), + isotp_rcv_echo, sk); dev_put(dev); } } @@ -1238,6 +1294,14 @@ static int isotp_setsockopt_locked(struct socket *sock, int level, int optname, /* no separate rx_ext_address is given => use ext_address */ if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR)) so->opt.rx_ext_address = so->opt.ext_address; + + /* check for frame_txtime changes (0 => no changes) */ + if (so->opt.frame_txtime) { + if (so->opt.frame_txtime == CAN_ISOTP_FRAME_TXTIME_ZERO) + so->frame_txtime = 0; + else + so->frame_txtime = so->opt.frame_txtime; + } break; case CAN_ISOTP_RECV_FC: @@ -1381,10 +1445,14 @@ static void isotp_notify(struct isotp_sock *so, unsigned long msg, case NETDEV_UNREGISTER: lock_sock(sk); /* remove current filters & unregister */ - if (so->bound && (!(so->opt.flags & CAN_ISOTP_SF_BROADCAST))) + if (so->bound && (!(so->opt.flags & CAN_ISOTP_SF_BROADCAST))) { can_rx_unregister(dev_net(dev), dev, so->rxid, SINGLE_MASK(so->rxid), isotp_rcv, sk); + can_rx_unregister(dev_net(dev), dev, so->txid, + SINGLE_MASK(so->txid), + isotp_rcv_echo, sk); + } so->ifindex = 0; so->bound = 0; @@ -1439,6 +1507,7 @@ static int isotp_init(struct sock *sk) so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT; so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; + so->frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME; so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS; so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN; so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX; 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/rtnetlink.c b/net/core/rtnetlink.c index a759f9e0a847..159c9c61e6af 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3652,13 +3652,24 @@ static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr, bool *changed, struct netlink_ext_ack *extack) { char *alt_ifname; + size_t size; int err; err = nla_validate(attr, attr->nla_len, IFLA_MAX, ifla_policy, extack); if (err) return err; - alt_ifname = nla_strdup(attr, GFP_KERNEL); + if (cmd == RTM_NEWLINKPROP) { + size = rtnl_prop_list_size(dev); + size += nla_total_size(ALTIFNAMSIZ); + if (size >= U16_MAX) { + NL_SET_ERR_MSG(extack, + "effective property list too long"); + return -EINVAL; + } + } + + alt_ifname = nla_strdup(attr, GFP_KERNEL_ACCOUNT); if (!alt_ifname) return -ENOMEM; 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/dsa/tag_rtl8_4.c b/net/dsa/tag_rtl8_4.c index 71fec45fd0ea..a593ead7ff26 100644 --- a/net/dsa/tag_rtl8_4.c +++ b/net/dsa/tag_rtl8_4.c @@ -247,7 +247,7 @@ static const struct dsa_device_ops rtl8_4t_netdev_ops = { DSA_TAG_DRIVER(rtl8_4t_netdev_ops); -MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4L); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_RTL8_4T); static struct dsa_tag_driver *dsa_tag_drivers[] = { &DSA_TAG_DRIVER_NAME(rtl8_4_netdev_ops), 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/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1cae27b5dcd8..ad80d180b60b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -1272,6 +1272,13 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ONE, }, { + .procname = "tcp_tso_rtt_log", + .data = &init_net.ipv4.sysctl_tcp_tso_rtt_log, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + }, + { .procname = "tcp_min_rtt_wlen", .data = &init_net.ipv4.sysctl_tcp_min_rtt_wlen, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b5f032958b2c..cf18fbcbf123 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -688,7 +688,8 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, return skb->len < size_goal && sock_net(sk)->ipv4.sysctl_tcp_autocorking && !tcp_rtx_queue_empty(sk) && - refcount_read(&sk->sk_wmem_alloc) > skb->truesize; + refcount_read(&sk->sk_wmem_alloc) > skb->truesize && + tcp_skb_can_collapse_to(skb); } void tcp_push(struct sock *sk, int flags, int mss_now, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 81694a354110..f9cec624068d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3137,6 +3137,7 @@ static int __net_init tcp_sk_init(struct net *net) /* rfc5961 challenge ack rate limiting */ net->ipv4.sysctl_tcp_challenge_ack_limit = 1000; net->ipv4.sysctl_tcp_min_tso_segs = 2; + net->ipv4.sysctl_tcp_tso_rtt_log = 9; /* 2^9 = 512 usec */ net->ipv4.sysctl_tcp_min_rtt_wlen = 300; net->ipv4.sysctl_tcp_autocorking = 1; net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2319531267c6..81aaa7da3e8c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1951,25 +1951,34 @@ static bool tcp_nagle_check(bool partial, const struct tcp_sock *tp, } /* Return how many segs we'd like on a TSO packet, - * to send one TSO packet per ms + * depending on current pacing rate, and how close the peer is. + * + * Rationale is: + * - For close peers, we rather send bigger packets to reduce + * cpu costs, because occasional losses will be repaired fast. + * - For long distance/rtt flows, we would like to get ACK clocking + * with 1 ACK per ms. + * + * Use min_rtt to help adapt TSO burst size, with smaller min_rtt resulting + * in bigger TSO bursts. We we cut the RTT-based allowance in half + * for every 2^9 usec (aka 512 us) of RTT, so that the RTT-based allowance + * is below 1500 bytes after 6 * ~500 usec = 3ms. */ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, int min_tso_segs) { - u32 bytes, segs; + unsigned long bytes; + u32 r; - bytes = min_t(unsigned long, - sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), - sk->sk_gso_max_size); + bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift); - /* Goal is to send at least one packet per ms, - * not one big TSO packet every 100 ms. - * This preserves ACK clocking and is consistent - * with tcp_tso_should_defer() heuristic. - */ - segs = max_t(u32, bytes / mss_now, min_tso_segs); + r = tcp_min_rtt(tcp_sk(sk)) >> sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log; + if (r < BITS_PER_TYPE(sk->sk_gso_max_size)) + bytes += sk->sk_gso_max_size >> r; + + bytes = min_t(unsigned long, bytes, sk->sk_gso_max_size); - return segs; + return max_t(u32, bytes / mss_now, min_tso_segs); } /* Return the number of segments we want in the skb we are transmitting. 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/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 8b4124820f7d..5176f6ccac8e 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -346,7 +346,7 @@ size_t ovs_key_attr_size(void) /* Whenever adding new OVS_KEY_ FIELDS, we should consider * updating this function. */ - BUILD_BUG_ON(OVS_KEY_ATTR_TUNNEL_INFO != 30); + BUILD_BUG_ON(OVS_KEY_ATTR_MAX != 32); return nla_total_size(4) /* OVS_KEY_ATTR_PRIORITY */ + nla_total_size(0) /* OVS_KEY_ATTR_TUNNEL */ @@ -482,7 +482,14 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, return -EINVAL; } - if (attrs & (1 << type)) { + if (type == OVS_KEY_ATTR_PACKET_TYPE || + type == OVS_KEY_ATTR_ND_EXTENSIONS || + type == OVS_KEY_ATTR_TUNNEL_INFO) { + OVS_NLERR(log, "Key type %d is not supported", type); + return -EINVAL; + } + + if (attrs & (1ULL << type)) { OVS_NLERR(log, "Duplicate key (type %d).", type); return -EINVAL; } @@ -495,7 +502,7 @@ static int __parse_flow_nlattrs(const struct nlattr *attr, } if (!nz || !is_all_zero(nla_data(nla), nla_len(nla))) { - attrs |= 1 << type; + attrs |= 1ULL << type; a[type] = nla; } } 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/smc/smc_sysctl.h b/net/smc/smc_sysctl.h index 1d554300604d..0becc11bd2f4 100644 --- a/net/smc/smc_sysctl.h +++ b/net/smc/smc_sysctl.h @@ -20,13 +20,13 @@ void __net_exit smc_sysctl_net_exit(struct net *net); #else -int __net_init smc_sysctl_net_init(struct net *net) +static inline int smc_sysctl_net_init(struct net *net) { net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; return 0; } -void __net_exit smc_sysctl_net_exit(struct net *net) { } +static inline void smc_sysctl_net_exit(struct net *net) { } #endif /* CONFIG_SYSCTL */ 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/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index ee435948d130..7314257d248a 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1,6 +1,11 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +# Double quotes to prevent globbing and word splitting is recommended in new +# code but we accept it, especially because there were too many before having +# address all other issues detected by shellcheck. +#shellcheck disable=SC2086 + ret=0 sin="" sinfail="" @@ -9,6 +14,9 @@ cin="" cinfail="" cinsent="" cout="" +capout="" +ns1="" +ns2="" ksft_skip=4 timeout_poll=30 timeout_test=$((timeout_poll * 2 + 1)) @@ -16,11 +24,19 @@ capture=0 checksum=0 ip_mptcp=0 check_invert=0 +validate_checksum=0 init=0 +declare -A all_tests +declare -a only_tests_ids +declare -a only_tests_names +declare -A failed_tests TEST_COUNT=0 +TEST_NAME="" nr_blank=40 +export FAILING_LINKS="" + # generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || # (ip6 && (ip6[74] & 0xf0) == 0x30)'" CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, @@ -43,12 +59,14 @@ init_partial() { capout=$(mktemp) + local rndh rndh=$(mktemp -u XXXXXX) ns1="ns1-$rndh" ns2="ns2-$rndh" - for netns in "$ns1" "$ns2";do + local netns + for netns in "$ns1" "$ns2"; do ip netns add $netns || exit $ksft_skip ip -net $netns link set lo up ip netns exec $netns sysctl -q net.mptcp.enabled=1 @@ -60,14 +78,17 @@ init_partial() done check_invert=0 + validate_checksum=$checksum + FAILING_LINKS="" - # ns1 ns2 + # ns1 ns2 # ns1eth1 ns2eth1 # ns1eth2 ns2eth2 # ns1eth3 ns2eth3 # ns1eth4 ns2eth4 - for i in `seq 1 4`; do + local i + for i in $(seq 1 4); do ip link add ns1eth$i netns "$ns1" type veth peer name ns2eth$i netns "$ns2" ip -net "$ns1" addr add 10.0.$i.1/24 dev ns1eth$i ip -net "$ns1" addr add dead:beef:$i::1/64 dev ns1eth$i nodad @@ -85,7 +106,8 @@ init_partial() init_shapers() { - for i in `seq 1 4`; do + local i + for i in $(seq 1 4); do tc -n $ns1 qdisc add dev ns1eth$i root netem rate 20mbit delay 1 tc -n $ns2 qdisc add dev ns2eth$i root netem rate 20mbit delay 1 done @@ -95,6 +117,7 @@ cleanup_partial() { rm -f "$capout" + local netns for netns in "$ns1" "$ns2"; do ip netns del $netns rm -f /tmp/$netns.{nstat,out} @@ -143,8 +166,38 @@ cleanup() cleanup_partial } +skip_test() +{ + if [ "${#only_tests_ids[@]}" -eq 0 ] && [ "${#only_tests_names[@]}" -eq 0 ]; then + return 1 + fi + + local i + for i in "${only_tests_ids[@]}"; do + if [ "${TEST_COUNT}" -eq "${i}" ]; then + return 1 + fi + done + for i in "${only_tests_names[@]}"; do + if [ "${TEST_NAME}" = "${i}" ]; then + return 1 + fi + done + + return 0 +} + +# $1: test name reset() { + TEST_NAME="${1}" + + TEST_COUNT=$((TEST_COUNT+1)) + + if skip_test; then + return 1 + fi + if [ "${init}" != "1" ]; then init else @@ -152,29 +205,34 @@ reset() fi init_partial + + return 0 } +# $1: test name reset_with_cookies() { - reset + reset "${1}" || return 1 - for netns in "$ns1" "$ns2";do + local netns + for netns in "$ns1" "$ns2"; do ip netns exec $netns sysctl -q net.ipv4.tcp_syncookies=2 done } +# $1: test name reset_with_add_addr_timeout() { - local ip="${1:-4}" + local ip="${2:-4}" local tables + reset "${1}" || return 1 + tables="iptables" if [ $ip -eq 6 ]; then tables="ip6tables" fi - reset - ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 ip netns exec $ns2 $tables -A OUTPUT -p tcp \ -m tcp --tcp-option 30 \ @@ -183,28 +241,46 @@ reset_with_add_addr_timeout() -j DROP } +# $1: test name reset_with_checksum() { local ns1_enable=$1 local ns2_enable=$2 - reset + reset "checksum test ${1} ${2}" || return 1 ip netns exec $ns1 sysctl -q net.mptcp.checksum_enabled=$ns1_enable ip netns exec $ns2 sysctl -q net.mptcp.checksum_enabled=$ns2_enable + + validate_checksum=1 } reset_with_allow_join_id0() { - local ns1_enable=$1 - local ns2_enable=$2 + local ns1_enable=$2 + local ns2_enable=$3 - reset + reset "${1}" || return 1 ip netns exec $ns1 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns1_enable ip netns exec $ns2 sysctl -q net.mptcp.allow_join_initial_addr_port=$ns2_enable } +fail_test() +{ + ret=1 + failed_tests[${TEST_COUNT}]="${TEST_NAME}" +} + +get_failed_tests_ids() +{ + # sorted + local i + for i in "${!failed_tests[@]}"; do + echo "${i}" + done | sort -n +} + print_file_err() { ls -l "$1" 1>&2 @@ -214,23 +290,23 @@ print_file_err() check_transfer() { - in=$1 - out=$2 - what=$3 - - cmp -l "$in" "$out" | while read line; do - local arr=($line) - - let sum=0${arr[1]}+0${arr[2]} + local in=$1 + local out=$2 + local what=$3 + local i a b + + local line + cmp -l "$in" "$out" | while read -r i a b; do + local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then echo "[ FAIL ] $what does not match (in, out):" print_file_err "$in" print_file_err "$out" - ret=1 + fail_test return 1 else - echo "$what has inverted byte at ${arr[0]}" + echo "$what has inverted byte at ${i}" fi done @@ -239,28 +315,28 @@ check_transfer() do_ping() { - listener_ns="$1" - connector_ns="$2" - connect_addr="$3" + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" - ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null - if [ $? -ne 0 ] ; then + if ! ip netns exec ${connector_ns} ping -q -c 1 $connect_addr >/dev/null; then echo "$listener_ns -> $connect_addr connectivity [ FAIL ]" 1>&2 - ret=1 + fail_test fi } link_failure() { - ns="$1" + local ns="$1" if [ -z "$FAILING_LINKS" ]; then l=$((RANDOM%4)) FAILING_LINKS=$((l+1)) fi + local l for l in $FAILING_LINKS; do - veth="ns1eth$l" + local veth="ns1eth$l" ip -net "$ns" link set "$veth" down done } @@ -277,9 +353,10 @@ wait_local_port_listen() local listener_ns="${1}" local port="${2}" - local port_hex i - + local port_hex port_hex="$(printf "%04X" "${port}")" + + local i for i in $(seq 10); do ip netns exec "${listener_ns}" cat /proc/net/tcp* | \ awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && @@ -290,7 +367,7 @@ wait_local_port_listen() rm_addr_count() { - ns=${1} + local ns=${1} ip netns exec ${ns} nstat -as | grep MPTcpExtRmAddr | awk '{print $2}' } @@ -301,8 +378,8 @@ wait_rm_addr() local ns="${1}" local old_cnt="${2}" local cnt - local i + local i for i in $(seq 10); do cnt=$(rm_addr_count ${ns}) [ "$cnt" = "${old_cnt}" ] || break @@ -342,32 +419,33 @@ pm_nl_add_endpoint() { local ns=$1 local addr=$2 - local flags - local port - local dev - local id + local flags _flags + local port _port + local dev _dev + local id _id local nr=2 - for p in $@ + local p + for p in "${@}" do if [ $p = "flags" ]; then eval _flags=\$"$nr" - [ ! -z $_flags ]; flags="flags $_flags" + [ -n "$_flags" ]; flags="flags $_flags" fi if [ $p = "dev" ]; then eval _dev=\$"$nr" - [ ! -z $_dev ]; dev="dev $_dev" + [ -n "$_dev" ]; dev="dev $_dev" fi if [ $p = "id" ]; then eval _id=\$"$nr" - [ ! -z $_id ]; id="id $_id" + [ -n "$_id" ]; id="id $_id" fi if [ $p = "port" ]; then eval _port=\$"$nr" - [ ! -z $_port ]; port="port $_port" + [ -n "$_port" ]; port="port $_port" fi - let nr+=1 + nr=$((nr + 1)) done if [ $ip_mptcp -eq 1 ]; then @@ -428,7 +506,7 @@ pm_nl_change_endpoint() pm_nl_check_endpoint() { local line expected_line - local title="$1" + local need_title=$1 local msg="$2" local ns=$3 local addr=$4 @@ -440,8 +518,8 @@ pm_nl_check_endpoint() local _id local id - if [ -n "${title}" ]; then - printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "${msg}" + if [ "${need_title}" = 1 ]; then + printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}" else printf "%-${nr_blank}s %s" " " "${msg}" fi @@ -450,18 +528,18 @@ pm_nl_check_endpoint() while [ -n "$1" ]; do if [ $1 = "flags" ]; then _flags=$2 - [ ! -z $_flags ]; flags="flags $_flags" + [ -n "$_flags" ]; flags="flags $_flags" shift elif [ $1 = "dev" ]; then - [ ! -z $2 ]; dev="dev $1" + [ -n "$2" ]; dev="dev $1" shift elif [ $1 = "id" ]; then _id=$2 - [ ! -z $_id ]; id="id $_id" + [ -n "$_id" ]; id="id $_id" shift elif [ $1 = "port" ]; then _port=$2 - [ ! -z $_port ]; port=" port $_port" + [ -n "$_port" ]; port=" port $_port" shift fi @@ -495,31 +573,41 @@ pm_nl_check_endpoint() echo "[ ok ]" else echo "[fail] expected '$expected_line' found '$line'" - ret=1 + fail_test fi } +filter_tcp_from() +{ + local ns="${1}" + local src="${2}" + local target="${3}" + + ip netns exec "${ns}" iptables -A INPUT -s "${src}" -p tcp -j "${target}" +} + do_transfer() { - listener_ns="$1" - connector_ns="$2" - cl_proto="$3" - srv_proto="$4" - connect_addr="$5" - test_link_fail="$6" - addr_nr_ns1="$7" - addr_nr_ns2="$8" - speed="$9" - sflags="${10}" - - port=$((10000+$TEST_COUNT)) - TEST_COUNT=$((TEST_COUNT+1)) + local listener_ns="$1" + local connector_ns="$2" + local cl_proto="$3" + local srv_proto="$4" + local connect_addr="$5" + local test_link_fail="$6" + local addr_nr_ns1="$7" + local addr_nr_ns2="$8" + local speed="$9" + local sflags="${10}" + + local port=$((10000 + TEST_COUNT - 1)) + local cappid :> "$cout" :> "$sout" :> "$capout" if [ $capture -eq 1 ]; then + local capuser if [ -z $SUDO_USER ] ; then capuser="" else @@ -573,7 +661,7 @@ do_transfer() ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ $extra_args ${local_addr} < "$sin" > "$sout" & fi - spid=$! + local spid=$! wait_local_port_listen "${listener_ns}" "${port}" @@ -590,21 +678,23 @@ do_transfer() ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ $extra_args $connect_addr > "$cout" & else - cat "$cinfail" | tee "$cinsent" | \ + tee "$cinsent" < "$cinfail" | \ timeout ${timeout_test} \ ip netns exec ${connector_ns} \ ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ $extra_args $connect_addr > "$cout" & fi - cpid=$! + local cpid=$! # let the mptcp subflow be established in background before # do endpoint manipulation - [ $addr_nr_ns1 = "0" -a $addr_nr_ns2 = "0" ] || sleep 1 + if [ $addr_nr_ns1 != "0" ] || [ $addr_nr_ns2 != "0" ]; then + sleep 1 + fi if [ $addr_nr_ns1 -gt 0 ]; then - let add_nr_ns1=addr_nr_ns1 - counter=2 + local counter=2 + local add_nr_ns1=${addr_nr_ns1} while [ $add_nr_ns1 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -613,18 +703,21 @@ do_transfer() addr="10.0.$counter.1" fi pm_nl_add_endpoint $ns1 $addr flags signal - let counter+=1 - let add_nr_ns1-=1 + counter=$((counter + 1)) + add_nr_ns1=$((add_nr_ns1 - 1)) done elif [ $addr_nr_ns1 -lt 0 ]; then - let rm_nr_ns1=-addr_nr_ns1 + local rm_nr_ns1=$((-addr_nr_ns1)) if [ $rm_nr_ns1 -lt 8 ]; then - counter=0 - pm_nl_show_endpoints ${listener_ns} | while read line; do + local counter=0 + local line + pm_nl_show_endpoints ${listener_ns} | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word local arr=($line) local nr=0 - for i in ${arr[@]}; do + local i + for i in "${arr[@]}"; do if [ $i = "id" ]; then if [ $counter -eq $rm_nr_ns1 ]; then break @@ -633,9 +726,9 @@ do_transfer() rm_addr=$(rm_addr_count ${connector_ns}) pm_nl_del_endpoint ${listener_ns} $id wait_rm_addr ${connector_ns} ${rm_addr} - let counter+=1 + counter=$((counter + 1)) fi - let nr+=1 + nr=$((nr + 1)) done done elif [ $rm_nr_ns1 -eq 8 ]; then @@ -645,7 +738,7 @@ do_transfer() fi fi - flags="subflow" + local flags="subflow" if [[ "${addr_nr_ns2}" = "fullmesh_"* ]]; then flags="${flags},fullmesh" addr_nr_ns2=${addr_nr_ns2:9} @@ -653,11 +746,11 @@ do_transfer() # if newly added endpoints must be deleted, give the background msk # some time to created them - [ $addr_nr_ns1 -gt 0 -a $addr_nr_ns2 -lt 0 ] && sleep 1 + [ $addr_nr_ns1 -gt 0 ] && [ $addr_nr_ns2 -lt 0 ] && sleep 1 if [ $addr_nr_ns2 -gt 0 ]; then - let add_nr_ns2=addr_nr_ns2 - counter=3 + local add_nr_ns2=${addr_nr_ns2} + local counter=3 while [ $add_nr_ns2 -gt 0 ]; do local addr if is_v6 "${connect_addr}"; then @@ -666,31 +759,35 @@ do_transfer() addr="10.0.$counter.2" fi pm_nl_add_endpoint $ns2 $addr flags $flags - let counter+=1 - let add_nr_ns2-=1 + counter=$((counter + 1)) + add_nr_ns2=$((add_nr_ns2 - 1)) done elif [ $addr_nr_ns2 -lt 0 ]; then - let rm_nr_ns2=-addr_nr_ns2 + local rm_nr_ns2=$((-addr_nr_ns2)) if [ $rm_nr_ns2 -lt 8 ]; then - counter=0 - pm_nl_show_endpoints ${connector_ns} | while read line; do + local counter=0 + local line + pm_nl_show_endpoints ${connector_ns} | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word local arr=($line) local nr=0 - for i in ${arr[@]}; do + local i + for i in "${arr[@]}"; do if [ $i = "id" ]; then if [ $counter -eq $rm_nr_ns2 ]; then break fi + local id rm_addr # rm_addr are serialized, allow the previous one to # complete id=${arr[$nr+1]} rm_addr=$(rm_addr_count ${listener_ns}) pm_nl_del_endpoint ${connector_ns} $id wait_rm_addr ${listener_ns} ${rm_addr} - let counter+=1 + counter=$((counter + 1)) fi - let nr+=1 + nr=$((nr + 1)) done done elif [ $rm_nr_ns2 -eq 8 ]; then @@ -706,19 +803,24 @@ do_transfer() fi fi - if [ ! -z $sflags ]; then + if [ -n "${sflags}" ]; then sleep 1 + + local netns for netns in "$ns1" "$ns2"; do - pm_nl_show_endpoints $netns | while read line; do + local line + pm_nl_show_endpoints $netns | while read -r line; do + # shellcheck disable=SC2206 # we do want to split per word local arr=($line) local nr=0 local id - for i in ${arr[@]}; do + local i + for i in "${arr[@]}"; do if [ $i = "id" ]; then id=${arr[$nr+1]} fi - let nr+=1 + nr=$((nr + 1)) done pm_nl_change_endpoint $netns $id $sflags done @@ -726,9 +828,9 @@ do_transfer() fi wait $cpid - retc=$? + local retc=$? wait $spid - rets=$? + local rets=$? if [ $capture -eq 1 ]; then sleep 1 @@ -750,7 +852,7 @@ do_transfer() cat /tmp/${connector_ns}.out cat "$capout" - ret=1 + fail_test return 1 fi @@ -778,9 +880,9 @@ do_transfer() make_file() { - name=$1 - who=$2 - size=$3 + local name=$1 + local who=$2 + local size=$3 dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name" @@ -790,14 +892,16 @@ make_file() run_tests() { - listener_ns="$1" - connector_ns="$2" - connect_addr="$3" - test_linkfail="${4:-0}" - addr_nr_ns1="${5:-0}" - addr_nr_ns2="${6:-0}" - speed="${7:-fast}" - sflags="${8:-""}" + local listener_ns="$1" + local connector_ns="$2" + local connect_addr="$3" + local test_linkfail="${4:-0}" + local addr_nr_ns1="${5:-0}" + local addr_nr_ns2="${6:-0}" + local speed="${7:-fast}" + local sflags="${8:-""}" + + local size # The values above 2 are reused to make test files # with the given sizes (KB) @@ -810,14 +914,14 @@ run_tests() make_file "$cinfail" "client" $size # create the input file for the failure test when # the first failure test run - elif [ "$test_linkfail" -ne 0 -a -z "$cinfail" ]; then + elif [ "$test_linkfail" -ne 0 ] && [ -z "$cinfail" ]; then # the client file must be considerably larger # of the maximum expected cwin value, or the # link utilization will be not predicable size=$((RANDOM%2)) size=$((size+1)) size=$((size*8192)) - size=$((size + ( $RANDOM % 8192) )) + size=$((size + ( RANDOM % 8192) )) cinfail=$(mktemp) make_file "$cinfail" "client" $size @@ -830,7 +934,7 @@ run_tests() sinfail=$(mktemp) fi make_file "$sinfail" "server" $size - elif [ "$test_linkfail" -eq 2 -a -z "$sinfail" ]; then + elif [ "$test_linkfail" -eq 2 ] && [ -z "$sinfail" ]; then size=$((RANDOM%16)) size=$((size+1)) size=$((size*2048)) @@ -853,9 +957,8 @@ dump_stats() chk_csum_nr() { - local msg=${1:-""} - local csum_ns1=${2:-0} - local csum_ns2=${3:-0} + local csum_ns1=${1:-0} + local csum_ns2=${2:-0} local count local dump_stats local allow_multi_errors_ns1=0 @@ -870,29 +973,24 @@ chk_csum_nr() csum_ns2=${csum_ns2:1} fi - if [ ! -z "$msg" ]; then - printf "%03u" "$TEST_COUNT" - else - echo -n " " - fi - printf " %-36s %s" "$msg" "sum" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'` + printf "%-${nr_blank}s %s" " " "sum" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != $csum_ns1 -a $allow_multi_errors_ns1 -eq 0 ] || - [ "$count" -lt $csum_ns1 -a $allow_multi_errors_ns1 -eq 1 ]; then + if { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } || + { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns1" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - csum " - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtDataCsumErr | awk '{print $2}') [ -z "$count" ] && count=0 - if [ "$count" != $csum_ns2 -a $allow_multi_errors_ns2 -eq 0 ] || - [ "$count" -lt $csum_ns2 -a $allow_multi_errors_ns2 -eq 1 ]; then + if { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } || + { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then echo "[fail] got $count data checksum error[s] expected $csum_ns2" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -908,22 +1006,22 @@ chk_fail_nr() local dump_stats printf "%-${nr_blank}s %s" " " "ftx" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPFailTx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$fail_tx" ]; then echo "[fail] got $count MP_FAIL[s] TX expected $fail_tx" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - failrx" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPFailRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$fail_rx" ]; then echo "[fail] got $count MP_FAIL[s] RX expected $fail_rx" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -944,7 +1042,7 @@ chk_fclose_nr() [ -z "$count" ] && count=0 if [ "$count" != "$fclose_tx" ]; then echo "[fail] got $count MP_FASTCLOSE[s] TX expected $fclose_tx" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" @@ -955,7 +1053,7 @@ chk_fclose_nr() [ -z "$count" ] && count=0 if [ "$count" != "$fclose_rx" ]; then echo "[fail] got $count MP_FASTCLOSE[s] RX expected $fclose_rx" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -986,7 +1084,7 @@ chk_rst_nr() [ -z "$count" ] && count=0 if [ "$count" != "$rst_tx" ]; then echo "[fail] got $count MP_RST[s] TX expected $rst_tx" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" @@ -997,7 +1095,7 @@ chk_rst_nr() [ -z "$count" ] && count=0 if [ "$count" != "$rst_rx" ]; then echo "[fail] got $count MP_RST[s] RX expected $rst_rx" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" @@ -1010,32 +1108,37 @@ chk_rst_nr() chk_join_nr() { - local msg="$1" - local syn_nr=$2 - local syn_ack_nr=$3 - local ack_nr=$4 - local csum_ns1=${5:-0} - local csum_ns2=${6:-0} - local fail_nr=${7:-0} - local rst_nr=${8:-0} + local syn_nr=$1 + local syn_ack_nr=$2 + local ack_nr=$3 + local csum_ns1=${4:-0} + local csum_ns2=${5:-0} + local fail_nr=${6:-0} + local rst_nr=${7:-0} + local corrupted_pkts=${8:-0} local count local dump_stats local with_cookie + local title="${TEST_NAME}" - printf "%03u %-36s %s" "$TEST_COUNT" "$msg" "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'` + if [ "${corrupted_pkts}" -gt 0 ]; then + title+=": ${corrupted_pkts} corrupted pkts" + fi + + printf "%03u %-36s %s" "${TEST_COUNT}" "${title}" "syn" + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn expected $syn_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" - with_cookie=`ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies` - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}'` + with_cookie=$(ip netns exec $ns2 sysctl -n net.ipv4.tcp_syncookies) + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinSynAckRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_ack_nr" ]; then # simult connections exceeding the limit with cookie enabled could go up to @@ -1045,7 +1148,7 @@ chk_join_nr() echo -n "[ ok ]" else echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" - ret=1 + fail_test dump_stats=1 fi else @@ -1053,18 +1156,18 @@ chk_join_nr() fi echo -n " - ack" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinAckRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack expected $ack_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" fi [ "${dump_stats}" = 1 ] && dump_stats if [ $checksum -eq 1 ]; then - chk_csum_nr "" $csum_ns1 $csum_ns2 + chk_csum_nr $csum_ns1 $csum_ns2 chk_fail_nr $fail_nr $fail_nr chk_rst_nr $rst_nr $rst_nr fi @@ -1086,18 +1189,18 @@ chk_stale_nr() local recover_nr printf "%-${nr_blank}s %-18s" " " "stale" - stale_nr=`ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}'` + stale_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowStale | awk '{print $2}') [ -z "$stale_nr" ] && stale_nr=0 - recover_nr=`ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}'` + recover_nr=$(ip netns exec $ns nstat -as | grep MPTcpExtSubflowRecover | awk '{print $2}') [ -z "$recover_nr" ] && recover_nr=0 if [ $stale_nr -lt $stale_min ] || - [ $stale_max -gt 0 -a $stale_nr -gt $stale_max ] || - [ $((stale_nr - $recover_nr)) -ne $stale_delta ]; then + { [ $stale_max -gt 0 ] && [ $stale_nr -gt $stale_max ]; } || + [ $((stale_nr - recover_nr)) -ne $stale_delta ]; then echo "[fail] got $stale_nr stale[s] $recover_nr recover[s], " \ " expected stale in range [$stale_min..$stale_max]," \ " stale-recover delta $stale_delta " - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -1124,28 +1227,28 @@ chk_add_nr() local dump_stats local timeout - timeout=`ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout` + timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout) printf "%-${nr_blank}s %s" " " "add" - count=`ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}') [ -z "$count" ] && count=0 # if the test configured a short timeout tolerate greater then expected # add addrs options, due to retransmissions - if [ "$count" != "$add_nr" ] && [ "$timeout" -gt 1 -o "$count" -lt "$add_nr" ]; then + if [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then echo "[fail] got $count ADD_ADDR[s] expected $add_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - echo " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" @@ -1153,76 +1256,76 @@ chk_add_nr() if [ $port_nr -gt 0 ]; then echo -n " - pt " - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtPortAdd | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$port_nr" ]; then echo "[fail] got $count ADD_ADDR[s] with a port-number expected $port_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" fi printf "%-${nr_blank}s %s" " " "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | - awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortSynRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a different \ port-number expected $syn_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - synack" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | - awk '{print $2}'` + count=$(ip netns exec $ns2 nstat -as | grep MPTcpExtMPJoinPortSynAckRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$syn_ack_nr" ]; then echo "[fail] got $count JOIN[s] synack with a different \ port-number expected $syn_ack_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | - awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinPortAckRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a different \ port-number expected $ack_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" fi printf "%-${nr_blank}s %s" " " "syn" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | - awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortSynRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mis_syn_nr" ]; then echo "[fail] got $count JOIN[s] syn with a mismatched \ port-number expected $mis_syn_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - ack " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | - awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMismatchPortAckRx | + awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mis_ack_nr" ]; then echo "[fail] got $count JOIN[s] ack with a mismatched \ port-number expected $mis_ack_nr" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -1263,22 +1366,23 @@ chk_rm_nr() fi printf "%-${nr_blank}s %s" " " "rm " - count=`ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}'` + count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - rmsf " - count=`ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}'` + count=$(ip netns exec $subflow_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') [ -z "$count" ] && count=0 if [ -n "$simult" ]; then - local cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') - local suffix + local cnt suffix + + cnt=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmSubflow | awk '{print $2}') # in case of simult flush, the subflow removal count on each side is # unreliable @@ -1290,14 +1394,14 @@ chk_rm_nr() echo "[ ok ] $suffix" else echo "[fail] got $count RM_SUBFLOW[s] expected in range [$rm_subflow_nr:$((rm_subflow_nr*2))]" - ret=1 + fail_test dump_stats=1 fi return fi if [ "$count" != "$rm_subflow_nr" ]; then echo "[fail] got $count RM_SUBFLOW[s] expected $rm_subflow_nr" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" @@ -1316,22 +1420,22 @@ chk_prio_nr() local dump_stats printf "%-${nr_blank}s %s" " " "ptx" - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mp_prio_nr_tx" ]; then echo "[fail] got $count MP_PRIO[s] TX expected $mp_prio_nr_tx" - ret=1 + fail_test dump_stats=1 else echo -n "[ ok ]" fi echo -n " - prx " - count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}'` + count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$mp_prio_nr_rx" ]; then echo "[fail] got $count MP_PRIO[s] RX expected $mp_prio_nr_rx" - ret=1 + fail_test dump_stats=1 else echo "[ ok ]" @@ -1346,16 +1450,18 @@ chk_link_usage() local link=$2 local out=$3 local expected_rate=$4 - local tx_link=`ip netns exec $ns cat /sys/class/net/$link/statistics/tx_bytes` - local tx_total=`ls -l $out | awk '{print $5}'` - local tx_rate=$((tx_link * 100 / $tx_total)) + + local tx_link tx_total + tx_link=$(ip netns exec $ns cat /sys/class/net/$link/statistics/tx_bytes) + tx_total=$(stat --format=%s $out) + local tx_rate=$((tx_link * 100 / tx_total)) local tolerance=5 printf "%-${nr_blank}s %-18s" " " "link usage" - if [ $tx_rate -lt $((expected_rate - $tolerance)) -o \ - $tx_rate -gt $((expected_rate + $tolerance)) ]; then + if [ $tx_rate -lt $((expected_rate - tolerance)) ] || \ + [ $tx_rate -gt $((expected_rate + tolerance)) ]; then echo "[fail] got $tx_rate% usage, expected $expected_rate%" - ret=1 + fail_test else echo "[ ok ]" fi @@ -1368,7 +1474,9 @@ wait_attempt_fail() local ns=$1 while [ $time -lt $timeout_ms ]; do - local cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') + local cnt + + cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -1379,887 +1487,968 @@ wait_attempt_fail() subflows_tests() { - reset - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "no JOIN" "0" "0" "0" + if reset "no JOIN"; then + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # subflow limited by client - reset - pm_nl_set_limits $ns1 0 0 - pm_nl_set_limits $ns2 0 0 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow, limited by client" 0 0 0 + if reset "single subflow, limited by client"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 0 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # subflow limited by server - reset - pm_nl_set_limits $ns1 0 0 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow, limited by server" 1 1 0 + if reset "single subflow, limited by server"; then + pm_nl_set_limits $ns1 0 0 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 0 + fi # subflow - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow" 1 1 1 + if reset "single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # multiple subflows - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 0 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows" 2 2 2 + if reset "multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi # multiple subflows limited by server - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows, limited by server" 2 2 1 + if reset "multiple subflows, limited by server"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 1 + fi # single subflow, dev - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow dev ns2eth3 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow, dev" 1 1 1 + if reset "single subflow, dev"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow dev ns2eth3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi } subflows_error_tests() { # If a single subflow is configured, and matches the MPC src # address, no additional subflow should be created - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "no MPC reuse with single endpoint" 0 0 0 + if reset "no MPC reuse with single endpoint"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 0 0 0 + fi # multiple subflows, with subflow creation error - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 0 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "multi subflows, with failing subflow" 1 1 1 + if reset "multi subflows, with failing subflow"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + filter_tcp_from $ns1 10.0.3.2 REJECT + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + fi # multiple subflows, with subflow timeout on MPJ - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 0 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j DROP - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "multi subflows, with subflow timeout" 1 1 1 + if reset "multi subflows, with subflow timeout"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + filter_tcp_from $ns1 10.0.3.2 DROP + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + fi # multiple subflows, check that the endpoint corresponding to # closed subflow (due to reset) is not reused if additional # subflows are added later - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - ip netns exec $ns1 iptables -A INPUT -s 10.0.3.2 -p tcp -j REJECT - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & - - # updates in the child shell do not have any effect here, we - # need to bump the test counter for the above case - TEST_COUNT=$((TEST_COUNT+1)) - - # mpj subflow will be in TW after the reset - wait_attempt_fail $ns2 - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - wait - - # additional subflow could be created only if the PM select - # the later endpoint, skipping the already used one - chk_join_nr "multi subflows, fair usage on close" 1 1 1 + if reset "multi subflows, fair usage on close"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + filter_tcp_from $ns1 10.0.3.2 REJECT + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + + # mpj subflow will be in TW after the reset + wait_attempt_fail $ns2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + wait + + # additional subflow could be created only if the PM select + # the later endpoint, skipping the already used one + chk_join_nr 1 1 1 + fi } signal_address_tests() { # add_address, unused - reset - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "unused signal address" 0 0 0 - chk_add_nr 1 1 + if reset "unused signal address"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi # accept and use add_addr - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address" 1 1 1 - chk_add_nr 1 1 + if reset "signal address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # accept and use add_addr with an additional subflow # note: signal address in server ns and local addresses in client ns must # belong to different subnets or one of the listed local address could be # used for 'add_addr' subflow - reset - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 1 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and signal" 2 2 2 - chk_add_nr 1 1 + if reset "subflow and signal"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + fi # accept and use add_addr with additional subflows - reset - pm_nl_set_limits $ns1 0 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows and signal" 3 3 3 - chk_add_nr 1 1 + if reset "multiple subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi # signal addresses - reset - pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.4.1 flags signal - pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal addresses" 3 3 3 - chk_add_nr 3 3 + if reset "signal addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 3 3 + fi # signal invalid addresses - reset - pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.12.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.14.1 flags signal - pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal invalid addresses" 1 1 1 - chk_add_nr 3 3 + if reset "signal invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 3 3 + fi # signal addresses race test - reset - pm_nl_set_limits $ns1 4 4 - pm_nl_set_limits $ns2 4 4 - pm_nl_add_endpoint $ns1 10.0.1.1 flags signal - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.4.1 flags signal - pm_nl_add_endpoint $ns2 10.0.1.2 flags signal - pm_nl_add_endpoint $ns2 10.0.2.2 flags signal - pm_nl_add_endpoint $ns2 10.0.3.2 flags signal - pm_nl_add_endpoint $ns2 10.0.4.2 flags signal - - # the peer could possibly miss some addr notification, allow retransmission - ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "signal addresses race test" 3 3 3 - - # the server will not signal the address terminating - # the MPC subflow - chk_add_nr 3 3 + if reset "signal addresses race test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns1 10.0.1.1 flags signal + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_add_endpoint $ns2 10.0.1.2 flags signal + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags signal + pm_nl_add_endpoint $ns2 10.0.4.2 flags signal + + # the peer could possibly miss some addr notification, allow retransmission + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 3 3 3 + + # the server will not signal the address terminating + # the MPC subflow + chk_add_nr 3 3 + fi } link_failure_tests() { # accept and use add_addr with additional subflows and link loss - reset - - # without any b/w limit each veth could spool the packets and get - # them acked at xmit time, so that the corresponding subflow will - # have almost always no outstanding pkts, the scheduler will pick - # always the first subflow and we will have hard time testing - # active backup and link switch-over. - # Let's set some arbitrary (low) virtual link limits. - init_shapers - pm_nl_set_limits $ns1 0 3 - pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal - pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 1 - chk_join_nr "multiple flows, signal, link failure" 3 3 3 - chk_add_nr 1 1 - chk_stale_nr $ns2 1 5 1 + if reset "multiple flows, signal, link failure"; then + # without any b/w limit each veth could spool the packets and get + # them acked at xmit time, so that the corresponding subflow will + # have almost always no outstanding pkts, the scheduler will pick + # always the first subflow and we will have hard time testing + # active backup and link switch-over. + # Let's set some arbitrary (low) virtual link limits. + init_shapers + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 5 1 + fi # accept and use add_addr with additional subflows and link loss # for bidirectional transfer - reset - init_shapers - pm_nl_set_limits $ns1 0 3 - pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal - pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow - run_tests $ns1 $ns2 10.0.1.1 2 - chk_join_nr "multi flows, signal, bidi, link fail" 3 3 3 - chk_add_nr 1 1 - chk_stale_nr $ns2 1 -1 1 + if reset "multi flows, signal, bidi, link fail"; then + init_shapers + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 dev ns2eth4 flags subflow + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 1 + fi # 2 subflows plus 1 backup subflow with a lossy link, backup # will never be used - reset - init_shapers - pm_nl_set_limits $ns1 0 2 - pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal - pm_nl_set_limits $ns2 1 2 - export FAILING_LINKS="1" - pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 1 - chk_join_nr "backup subflow unused, link failure" 2 2 2 - chk_add_nr 1 1 - chk_link_usage $ns2 ns2eth3 $cinsent 0 + if reset "backup subflow unused, link failure"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + FAILING_LINKS="1" + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_link_usage $ns2 ns2eth3 $cinsent 0 + fi # 2 lossy links after half transfer, backup will get half of # the traffic - reset - init_shapers - pm_nl_set_limits $ns1 0 2 - pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal - pm_nl_set_limits $ns2 1 2 - pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - export FAILING_LINKS="1 2" - run_tests $ns1 $ns2 10.0.1.1 1 - chk_join_nr "backup flow used, multi links fail" 2 2 2 - chk_add_nr 1 1 - chk_stale_nr $ns2 2 4 2 - chk_link_usage $ns2 ns2eth3 $cinsent 50 + if reset "backup flow used, multi links fail"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + FAILING_LINKS="1 2" + run_tests $ns1 $ns2 10.0.1.1 1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 2 4 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 + fi # use a backup subflow with the first subflow on a lossy link # for bidirectional transfer - reset - init_shapers - pm_nl_set_limits $ns1 0 2 - pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal - pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 2 - chk_join_nr "backup flow used, bidi, link failure" 2 2 2 - chk_add_nr 1 1 - chk_stale_nr $ns2 1 -1 2 - chk_link_usage $ns2 ns2eth3 $cinsent 50 + if reset "backup flow used, bidi, link failure"; then + init_shapers + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 dev ns1eth2 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 dev ns2eth3 flags subflow,backup + FAILING_LINKS="1 2" + run_tests $ns1 $ns2 10.0.1.1 2 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_stale_nr $ns2 1 -1 2 + chk_link_usage $ns2 ns2eth3 $cinsent 50 + fi } add_addr_timeout_tests() { # add_addr timeout - reset_with_add_addr_timeout - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow - chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1 - chk_add_nr 4 0 + if reset_with_add_addr_timeout "signal address, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 4 0 + fi # add_addr timeout IPv6 - reset_with_add_addr_timeout 6 - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1 - chk_add_nr 4 0 + if reset_with_add_addr_timeout "signal address, ADD_ADDR6 timeout" 6; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 4 0 + fi # signal addresses timeout - reset_with_add_addr_timeout - pm_nl_set_limits $ns1 2 2 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 - chk_join_nr "signal addresses, ADD_ADDR timeout" 2 2 2 - chk_add_nr 8 0 + if reset_with_add_addr_timeout "signal addresses, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + chk_join_nr 2 2 2 + chk_add_nr 8 0 + fi # signal invalid addresses timeout - reset_with_add_addr_timeout - pm_nl_set_limits $ns1 2 2 - pm_nl_add_endpoint $ns1 10.0.12.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 - chk_join_nr "invalid address, ADD_ADDR timeout" 1 1 1 - chk_add_nr 8 0 + if reset_with_add_addr_timeout "invalid address, ADD_ADDR timeout"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 speed_10 + chk_join_nr 1 1 1 + chk_add_nr 8 0 + fi } remove_tests() { # single subflow, remove - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow - chk_join_nr "remove single subflow" 1 1 1 - chk_rm_nr 1 1 + if reset "remove single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + chk_join_nr 1 1 1 + chk_rm_nr 1 1 + fi # multiple subflows, remove - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 0 2 - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow - chk_join_nr "remove multiple subflows" 2 2 2 - chk_rm_nr 2 2 + if reset "remove multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -2 slow + chk_join_nr 2 2 2 + chk_rm_nr 2 2 + fi # single address, remove - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow - chk_join_nr "remove single address" 1 1 1 - chk_add_nr 1 1 - chk_rm_nr 1 1 invert + if reset "remove single address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi # subflow and signal, remove - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns2 1 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow - chk_join_nr "remove subflow and signal" 2 2 2 - chk_add_nr 1 1 - chk_rm_nr 1 1 + if reset "remove subflow and signal"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_rm_nr 1 1 + fi # subflows and signal, remove - reset - pm_nl_set_limits $ns1 0 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow - chk_join_nr "remove subflows and signal" 3 3 3 - chk_add_nr 1 1 - chk_rm_nr 2 2 + if reset "remove subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -2 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 2 2 + fi # addresses remove - reset - pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.4.1 flags signal - pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow - chk_join_nr "remove addresses" 3 3 3 - chk_add_nr 3 3 - chk_rm_nr 3 3 invert + if reset "remove addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + chk_join_nr 3 3 3 + chk_add_nr 3 3 + chk_rm_nr 3 3 invert + fi # invalid addresses remove - reset - pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.12.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.14.1 flags signal - pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow - chk_join_nr "remove invalid addresses" 1 1 1 - chk_add_nr 3 3 - chk_rm_nr 3 1 invert + if reset "remove invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -3 0 slow + chk_join_nr 1 1 1 + chk_add_nr 3 3 + chk_rm_nr 3 1 invert + fi # subflows and signal, flush - reset - pm_nl_set_limits $ns1 0 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow - chk_join_nr "flush subflows and signal" 3 3 3 - chk_add_nr 1 1 - chk_rm_nr 1 3 invert simult + if reset "flush subflows and signal"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 1 3 invert simult + fi # subflows flush - reset - pm_nl_set_limits $ns1 3 3 - pm_nl_set_limits $ns2 3 3 - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow - chk_join_nr "flush subflows" 3 3 3 - chk_rm_nr 0 3 simult + if reset "flush subflows"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_set_limits $ns2 3 3 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow id 150 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_rm_nr 0 3 simult + fi # addresses flush - reset - pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.4.1 flags signal - pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow - chk_join_nr "flush addresses" 3 3 3 - chk_add_nr 3 3 - chk_rm_nr 3 3 invert simult + if reset "flush addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal id 250 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.4.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -8 -8 slow + chk_join_nr 3 3 3 + chk_add_nr 3 3 + chk_rm_nr 3 3 invert simult + fi # invalid addresses flush - reset - pm_nl_set_limits $ns1 3 3 - pm_nl_add_endpoint $ns1 10.0.12.1 flags signal - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal - pm_nl_add_endpoint $ns1 10.0.14.1 flags signal - pm_nl_set_limits $ns2 3 3 - run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow - chk_join_nr "flush invalid addresses" 1 1 1 - chk_add_nr 3 3 - chk_rm_nr 3 1 invert + if reset "flush invalid addresses"; then + pm_nl_set_limits $ns1 3 3 + pm_nl_add_endpoint $ns1 10.0.12.1 flags signal + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal + pm_nl_add_endpoint $ns1 10.0.14.1 flags signal + pm_nl_set_limits $ns2 3 3 + run_tests $ns1 $ns2 10.0.1.1 0 -8 0 slow + chk_join_nr 1 1 1 + chk_add_nr 3 3 + chk_rm_nr 3 1 invert + fi # remove id 0 subflow - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow - chk_join_nr "remove id 0 subflow" 1 1 1 - chk_rm_nr 1 1 + if reset "remove id 0 subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -9 slow + chk_join_nr 1 1 1 + chk_rm_nr 1 1 + fi # remove id 0 address - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow - chk_join_nr "remove id 0 address" 1 1 1 - chk_add_nr 1 1 - chk_rm_nr 1 1 invert + if reset "remove id 0 address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -9 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi } add_tests() { # add single subflow - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow - chk_join_nr "add single subflow" 1 1 1 + if reset "add single subflow"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow + chk_join_nr 1 1 1 + fi # add signal address - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow - chk_join_nr "add signal address" 1 1 1 - chk_add_nr 1 1 + if reset "add signal address"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # add multiple subflows - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 0 2 - run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow - chk_join_nr "add multiple subflows" 2 2 2 + if reset "add multiple subflows"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow + chk_join_nr 2 2 2 + fi # add multiple subflows IPv6 - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 0 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow - chk_join_nr "add multiple subflows IPv6" 2 2 2 + if reset "add multiple subflows IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + run_tests $ns1 $ns2 dead:beef:1::1 0 0 2 slow + chk_join_nr 2 2 2 + fi # add multiple addresses IPv6 - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow - chk_join_nr "add multiple addresses IPv6" 2 2 2 - chk_add_nr 2 2 + if reset "add multiple addresses IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 dead:beef:1::1 0 2 0 slow + chk_join_nr 2 2 2 + chk_add_nr 2 2 + fi } ipv6_tests() { # subflow IPv6 - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "single subflow IPv6" 1 1 1 + if reset "single subflow IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + fi # add_address, unused IPv6 - reset - pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "unused signal address IPv6" 0 0 0 - chk_add_nr 1 1 + if reset "unused signal address IPv6"; then + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi # signal address IPv6 - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow - chk_join_nr "single address IPv6" 1 1 1 - chk_add_nr 1 1 + if reset "single address IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # single address IPv6, remove - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow - chk_join_nr "remove single address IPv6" 1 1 1 - chk_add_nr 1 1 - chk_rm_nr 1 1 invert + if reset "remove single address IPv6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 dead:beef:1::1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_rm_nr 1 1 invert + fi # subflow and signal IPv6, remove - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal - pm_nl_set_limits $ns2 1 2 - pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow - chk_join_nr "remove subflow and signal IPv6" 2 2 2 - chk_add_nr 1 1 - chk_rm_nr 1 1 + if reset "remove subflow and signal IPv6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 dead:beef:3::2 dev ns2eth3 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 + chk_rm_nr 1 1 + fi } v4mapped_tests() { # subflow IPv4-mapped to IPv4-mapped - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "single subflow IPv4-mapped" 1 1 1 + if reset "single subflow IPv4-mapped"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + fi # signal address IPv4-mapped with IPv4-mapped sk - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "signal address IPv4-mapped" 1 1 1 - chk_add_nr 1 1 + if reset "signal address IPv4-mapped"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # subflow v4-map-v6 - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "single subflow v4-map-v6" 1 1 1 + if reset "single subflow v4-map-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + fi # signal address v4-map-v6 - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 "::ffff:10.0.1.1" - chk_join_nr "signal address v4-map-v6" 1 1 1 - chk_add_nr 1 1 + if reset "signal address v4-map-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 "::ffff:10.0.1.1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # subflow v6-map-v4 - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow v6-map-v4" 1 1 1 + if reset "single subflow v6-map-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 "::ffff:10.0.3.2" flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # signal address v6-map-v4 - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address v6-map-v4" 1 1 1 - chk_add_nr 1 1 + if reset "signal address v6-map-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 "::ffff:10.0.2.1" flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # no subflow IPv6 to v4 address - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "no JOIN with diff families v4-v6" 0 0 0 + if reset "no JOIN with diff families v4-v6"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # no subflow IPv6 to v4 address even if v6 has a valid v4 at the end - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 dead:beef:2::10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "no JOIN with diff families v4-v6-2" 0 0 0 + if reset "no JOIN with diff families v4-v6-2"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 dead:beef:2::10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # no subflow IPv4 to v6 address, no need to slow down too then - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 dead:beef:1::1 - chk_join_nr "no JOIN with diff families v6-v4" 0 0 0 + if reset "no JOIN with diff families v6-v4"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 dead:beef:1::1 + chk_join_nr 0 0 0 + fi } backup_tests() { # single subflow, backup - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup - chk_join_nr "single subflow, backup" 1 1 1 - chk_prio_nr 0 1 + if reset "single subflow, backup"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,backup + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup + chk_join_nr 1 1 1 + chk_prio_nr 0 1 + fi # single address, backup - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup - chk_join_nr "single address, backup" 1 1 1 - chk_add_nr 1 1 - chk_prio_nr 1 1 + if reset "single address, backup"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 1 + fi # single address with port, backup - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 - pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup - chk_join_nr "single address with port, backup" 1 1 1 - chk_add_nr 1 1 - chk_prio_nr 1 1 + if reset "single address with port, backup"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 1 + chk_add_nr 1 1 + chk_prio_nr 1 1 + fi } add_addr_ports_tests() { # signal address with port - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address with port" 1 1 1 - chk_add_nr 1 1 1 + if reset "signal address with port"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 1 + fi # subflow and signal with port - reset - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 1 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and signal with port" 2 2 2 - chk_add_nr 1 1 1 + if reset "subflow and signal with port"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 1 + fi # single address with port, remove - reset - pm_nl_set_limits $ns1 0 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 - pm_nl_set_limits $ns2 1 1 - run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow - chk_join_nr "remove single address with port" 1 1 1 - chk_add_nr 1 1 1 - chk_rm_nr 1 1 invert + if reset "remove single address with port"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 1 + run_tests $ns1 $ns2 10.0.1.1 0 -1 0 slow + chk_join_nr 1 1 1 + chk_add_nr 1 1 1 + chk_rm_nr 1 1 invert + fi # subflow and signal with port, remove - reset - pm_nl_set_limits $ns1 0 2 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 - pm_nl_set_limits $ns2 1 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow - chk_join_nr "remove subflow and signal with port" 2 2 2 - chk_add_nr 1 1 1 - chk_rm_nr 1 1 + if reset "remove subflow and signal with port"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -1 -1 slow + chk_join_nr 2 2 2 + chk_add_nr 1 1 1 + chk_rm_nr 1 1 + fi # subflows and signal with port, flush - reset - pm_nl_set_limits $ns1 0 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 - pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow - chk_join_nr "flush subflows and signal with port" 3 3 3 - chk_add_nr 1 1 - chk_rm_nr 1 3 invert simult + if reset "flush subflows and signal with port"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 -8 -2 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + chk_rm_nr 1 3 invert simult + fi # multiple addresses with port - reset - pm_nl_set_limits $ns1 2 2 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10100 - pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple addresses with port" 2 2 2 - chk_add_nr 2 2 2 + if reset "multiple addresses with port"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10100 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 2 2 2 + fi # multiple addresses with ports - reset - pm_nl_set_limits $ns1 2 2 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 - pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10101 - pm_nl_set_limits $ns2 2 2 - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple addresses with ports" 2 2 2 - chk_add_nr 2 2 2 + if reset "multiple addresses with ports"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100 + pm_nl_add_endpoint $ns1 10.0.3.1 flags signal port 10101 + pm_nl_set_limits $ns2 2 2 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 2 2 2 + fi } syncookies_tests() { # single subflow, syncookies - reset_with_cookies - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow with syn cookies" 1 1 1 + if reset_with_cookies "single subflow with syn cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # multiple subflows with syn cookies - reset_with_cookies - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 0 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "multiple subflows with syn cookies" 2 2 2 + if reset_with_cookies "multiple subflows with syn cookies"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi # multiple subflows limited by server - reset_with_cookies - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflows limited by server w cookies" 2 1 1 + if reset_with_cookies "subflows limited by server w cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 1 1 + fi # test signal address with cookies - reset_with_cookies - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address with syn cookies" 1 1 1 - chk_add_nr 1 1 + if reset_with_cookies "signal address with syn cookies"; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # test cookie with subflow and signal - reset_with_cookies - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns1 0 2 - pm_nl_set_limits $ns2 1 2 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and signal w cookies" 2 2 2 - chk_add_nr 1 1 + if reset_with_cookies "subflow and signal w cookies"; then + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 1 2 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + chk_add_nr 1 1 + fi # accept and use add_addr with additional subflows - reset_with_cookies - pm_nl_set_limits $ns1 0 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflows and signal w. cookies" 3 3 3 - chk_add_nr 1 1 + if reset_with_cookies "subflows and signal w. cookies"; then + pm_nl_set_limits $ns1 0 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + pm_nl_add_endpoint $ns2 10.0.4.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi } checksum_tests() { # checksum test 0 0 - reset_with_checksum 0 0 - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 0 0" + if reset_with_checksum 0 0; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # checksum test 1 1 - reset_with_checksum 1 1 - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 1 1" + if reset_with_checksum 1 1; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # checksum test 0 1 - reset_with_checksum 0 1 - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 0 1" + if reset_with_checksum 0 1; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # checksum test 1 0 - reset_with_checksum 1 0 - pm_nl_set_limits $ns1 0 1 - pm_nl_set_limits $ns2 0 1 - run_tests $ns1 $ns2 10.0.1.1 - chk_csum_nr "checksum test 1 0" + if reset_with_checksum 1 0; then + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi } deny_join_id0_tests() { # subflow allow join id0 ns1 - reset_with_allow_join_id0 1 0 - pm_nl_set_limits $ns1 1 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow allow join id0 ns1" 1 1 1 + if reset_with_allow_join_id0 "single subflow allow join id0 ns1" 1 0; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi # subflow allow join id0 ns2 - reset_with_allow_join_id0 0 1 - pm_nl_set_limits $ns1 1 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "single subflow allow join id0 ns2" 0 0 0 + if reset_with_allow_join_id0 "single subflow allow join id0 ns2" 0 1; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi # signal address allow join id0 ns1 # ADD_ADDRs are not affected by allow_join_id0 value. - reset_with_allow_join_id0 1 0 - pm_nl_set_limits $ns1 1 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address allow join id0 ns1" 1 1 1 - chk_add_nr 1 1 + if reset_with_allow_join_id0 "signal address allow join id0 ns1" 1 0; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # signal address allow join id0 ns2 # ADD_ADDRs are not affected by allow_join_id0 value. - reset_with_allow_join_id0 0 1 - pm_nl_set_limits $ns1 1 1 - pm_nl_set_limits $ns2 1 1 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "signal address allow join id0 ns2" 1 1 1 - chk_add_nr 1 1 + if reset_with_allow_join_id0 "signal address allow join id0 ns2" 0 1; then + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + fi # subflow and address allow join id0 ns1 - reset_with_allow_join_id0 1 0 - pm_nl_set_limits $ns1 2 2 - pm_nl_set_limits $ns2 2 2 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and address allow join id0 1" 2 2 2 + if reset_with_allow_join_id0 "subflow and address allow join id0 1" 1 0; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 2 2 2 + fi # subflow and address allow join id0 ns2 - reset_with_allow_join_id0 0 1 - pm_nl_set_limits $ns1 2 2 - pm_nl_set_limits $ns2 2 2 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow - run_tests $ns1 $ns2 10.0.1.1 - chk_join_nr "subflow and address allow join id0 2" 1 1 1 + if reset_with_allow_join_id0 "subflow and address allow join id0 2" 0 1; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + fi } fullmesh_tests() @@ -2267,140 +2456,128 @@ fullmesh_tests() # fullmesh 1 # 2 fullmesh addrs in ns2, added before the connection, # 1 non-fullmesh addr in ns1, added during the connection. - reset - pm_nl_set_limits $ns1 0 4 - pm_nl_set_limits $ns2 1 4 - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh - pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh - run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow - chk_join_nr "fullmesh test 2x1" 4 4 4 - chk_add_nr 1 1 + if reset "fullmesh test 2x1"; then + pm_nl_set_limits $ns1 0 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,fullmesh + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow + chk_join_nr 4 4 4 + chk_add_nr 1 1 + fi # fullmesh 2 # 1 non-fullmesh addr in ns1, added before the connection, # 1 fullmesh addr in ns2, added during the connection. - reset - pm_nl_set_limits $ns1 1 3 - pm_nl_set_limits $ns2 1 3 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow - chk_join_nr "fullmesh test 1x1" 3 3 3 - chk_add_nr 1 1 + if reset "fullmesh test 1x1"; then + pm_nl_set_limits $ns1 1 3 + pm_nl_set_limits $ns2 1 3 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow + chk_join_nr 3 3 3 + chk_add_nr 1 1 + fi # fullmesh 3 # 1 non-fullmesh addr in ns1, added before the connection, # 2 fullmesh addrs in ns2, added during the connection. - reset - pm_nl_set_limits $ns1 2 5 - pm_nl_set_limits $ns2 1 5 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow - chk_join_nr "fullmesh test 1x2" 5 5 5 - chk_add_nr 1 1 + if reset "fullmesh test 1x2"; then + pm_nl_set_limits $ns1 2 5 + pm_nl_set_limits $ns2 1 5 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr 5 5 5 + chk_add_nr 1 1 + fi # fullmesh 4 # 1 non-fullmesh addr in ns1, added before the connection, # 2 fullmesh addrs in ns2, added during the connection, # limit max_subflows to 4. - reset - pm_nl_set_limits $ns1 2 4 - pm_nl_set_limits $ns2 1 4 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow - chk_join_nr "fullmesh test 1x2, limited" 4 4 4 - chk_add_nr 1 1 + if reset "fullmesh test 1x2, limited"; then + pm_nl_set_limits $ns1 2 4 + pm_nl_set_limits $ns2 1 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_2 slow + chk_join_nr 4 4 4 + chk_add_nr 1 1 + fi # set fullmesh flag - reset - pm_nl_set_limits $ns1 4 4 - pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow - pm_nl_set_limits $ns2 4 4 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh - chk_join_nr "set fullmesh flag test" 2 2 2 - chk_rm_nr 0 1 + if reset "set fullmesh flag test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow fullmesh + chk_join_nr 2 2 2 + chk_rm_nr 0 1 + fi # set nofullmesh flag - reset - pm_nl_set_limits $ns1 4 4 - pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh - pm_nl_set_limits $ns2 4 4 - run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh - chk_join_nr "set nofullmesh flag test" 2 2 2 - chk_rm_nr 0 1 + if reset "set nofullmesh flag test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow,fullmesh + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 fullmesh_1 slow nofullmesh + chk_join_nr 2 2 2 + chk_rm_nr 0 1 + fi # set backup,fullmesh flags - reset - pm_nl_set_limits $ns1 4 4 - pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow - pm_nl_set_limits $ns2 4 4 - run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh - chk_join_nr "set backup,fullmesh flags test" 2 2 2 - chk_prio_nr 0 1 - chk_rm_nr 0 1 + if reset "set backup,fullmesh flags test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_add_endpoint $ns1 10.0.2.1 flags subflow + pm_nl_set_limits $ns2 4 4 + run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow backup,fullmesh + chk_join_nr 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + fi # set nobackup,nofullmesh flags - reset - pm_nl_set_limits $ns1 4 4 - pm_nl_set_limits $ns2 4 4 - pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh - chk_join_nr "set nobackup,nofullmesh flags test" 2 2 2 - chk_prio_nr 0 1 - chk_rm_nr 0 1 + if reset "set nobackup,nofullmesh flags test"; then + pm_nl_set_limits $ns1 4 4 + pm_nl_set_limits $ns2 4 4 + pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow,backup,fullmesh + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow nobackup,nofullmesh + chk_join_nr 2 2 2 + chk_prio_nr 0 1 + chk_rm_nr 0 1 + fi } fastclose_tests() { - reset - run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_2 - chk_join_nr "fastclose test" 0 0 0 - chk_fclose_nr 1 1 - chk_rst_nr 1 1 invert + if reset "fastclose test"; then + run_tests $ns1 $ns2 10.0.1.1 1024 0 fastclose_2 + chk_join_nr 0 0 0 + chk_fclose_nr 1 1 + chk_rst_nr 1 1 invert + fi } implicit_tests() { # userspace pm type prevents add_addr - reset - pm_nl_set_limits $ns1 2 2 - pm_nl_set_limits $ns2 2 2 - pm_nl_add_endpoint $ns1 10.0.2.1 flags signal - run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & - - wait_mpj $ns1 - TEST_COUNT=$((TEST_COUNT + 1)) - pm_nl_check_endpoint "implicit EP" "creation" \ - $ns2 10.0.2.2 id 1 flags implicit - - pm_nl_add_endpoint $ns2 10.0.2.2 id 33 - pm_nl_check_endpoint "" "ID change is prevented" \ - $ns2 10.0.2.2 id 1 flags implicit - - pm_nl_add_endpoint $ns2 10.0.2.2 flags signal - pm_nl_check_endpoint "" "modif is allowed" \ - $ns2 10.0.2.2 id 1 flags signal - wait -} - -all_tests() -{ - subflows_tests - subflows_error_tests - signal_address_tests - link_failure_tests - add_addr_timeout_tests - remove_tests - add_tests - ipv6_tests - v4mapped_tests - backup_tests - add_addr_ports_tests - syncookies_tests - checksum_tests - deny_join_id0_tests - fullmesh_tests - fastclose_tests - implicit_tests + if reset "implicit EP"; then + pm_nl_set_limits $ns1 2 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow & + + wait_mpj $ns1 + pm_nl_check_endpoint 1 "creation" \ + $ns2 10.0.2.2 id 1 flags implicit + + pm_nl_add_endpoint $ns2 10.0.2.2 id 33 + pm_nl_check_endpoint 0 "ID change is prevented" \ + $ns2 10.0.2.2 id 1 flags implicit + + pm_nl_add_endpoint $ns2 10.0.2.2 flags signal + pm_nl_check_endpoint 0 "modif is allowed" \ + $ns2 10.0.2.2 id 1 flags signal + wait + fi } # [$1: error message] @@ -2412,85 +2589,60 @@ usage() fi echo "mptcp_join usage:" - echo " -f subflows_tests" - echo " -e subflows_error_tests" - echo " -s signal_address_tests" - echo " -l link_failure_tests" - echo " -t add_addr_timeout_tests" - echo " -r remove_tests" - echo " -a add_tests" - echo " -6 ipv6_tests" - echo " -4 v4mapped_tests" - echo " -b backup_tests" - echo " -p add_addr_ports_tests" - echo " -k syncookies_tests" - echo " -S checksum_tests" - echo " -d deny_join_id0_tests" - echo " -m fullmesh_tests" - echo " -z fastclose_tests" - echo " -I implicit_tests" + + local key + for key in "${!all_tests[@]}"; do + echo " -${key} ${all_tests[${key}]}" + done + echo " -c capture pcap files" echo " -C enable data checksum" echo " -i use ip mptcp" echo " -h help" + echo "[test ids|names]" + exit ${ret} } +# Use a "simple" array to force an specific order we cannot have with an associative one +all_tests_sorted=( + f@subflows_tests + e@subflows_error_tests + s@signal_address_tests + l@link_failure_tests + t@add_addr_timeout_tests + r@remove_tests + a@add_tests + 6@ipv6_tests + 4@v4mapped_tests + b@backup_tests + p@add_addr_ports_tests + k@syncookies_tests + S@checksum_tests + d@deny_join_id0_tests + m@fullmesh_tests + z@fastclose_tests + I@implicit_tests +) + +all_tests_args="" +all_tests_names=() +for subtests in "${all_tests_sorted[@]}"; do + key="${subtests%@*}" + value="${subtests#*@}" + + all_tests_args+="${key}" + all_tests_names+=("${value}") + all_tests[${key}]="${value}" +done + tests=() -while getopts 'fesltra64bpkdmchzICSi' opt; do +while getopts "${all_tests_args}cCih" opt; do case $opt in - f) - tests+=(subflows_tests) - ;; - e) - tests+=(subflows_error_tests) - ;; - s) - tests+=(signal_address_tests) - ;; - l) - tests+=(link_failure_tests) - ;; - t) - tests+=(add_addr_timeout_tests) - ;; - r) - tests+=(remove_tests) - ;; - a) - tests+=(add_tests) - ;; - 6) - tests+=(ipv6_tests) - ;; - 4) - tests+=(v4mapped_tests) - ;; - b) - tests+=(backup_tests) - ;; - p) - tests+=(add_addr_ports_tests) - ;; - k) - tests+=(syncookies_tests) - ;; - S) - tests+=(checksum_tests) - ;; - d) - tests+=(deny_join_id0_tests) - ;; - m) - tests+=(fullmesh_tests) - ;; - z) - tests+=(fastclose_tests) - ;; - I) - tests+=(implicit_tests) + ["${all_tests_args}"]) + tests+=("${all_tests[${opt}]}") ;; c) capture=1 @@ -2510,12 +2662,31 @@ while getopts 'fesltra64bpkdmchzICSi' opt; do esac done +shift $((OPTIND - 1)) + +for arg in "${@}"; do + if [[ "${arg}" =~ ^[0-9]+$ ]]; then + only_tests_ids+=("${arg}") + else + only_tests_names+=("${arg}") + fi +done + if [ ${#tests[@]} -eq 0 ]; then - all_tests -else - for subtests in "${tests[@]}"; do - "${subtests}" + tests=("${all_tests_names[@]}") +fi + +for subtests in "${tests[@]}"; do + "${subtests}" +done + +if [ ${ret} -ne 0 ]; then + echo + echo "${#failed_tests[@]} failure(s) has(ve) been detected:" + for i in $(get_failed_tests_ids); do + echo -e "\t- ${i}: ${failed_tests[${i}]}" done + echo fi exit $ret 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); |