diff options
689 files changed, 7397 insertions, 2987 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> @@ -333,6 +336,9 @@ Rémi Denis-Courmont <rdenis@simphalempin.com> Ricardo Ribalda <ribalda@kernel.org> <ricardo@ribalda.com> Ricardo Ribalda <ribalda@kernel.org> Ricardo Ribalda Delgado <ribalda@kernel.org> Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com> +Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com> +Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com> +Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru> Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com> Rudolf Marek <R.Marek@sh.cvut.cz> Rui Saraiva <rmps@joel.ist.utl.pt> @@ -895,6 +895,12 @@ S: 3000 FORE Drive S: Warrendale, Pennsylvania 15086 S: USA +N: Ludovic Desroches +E: ludovic.desroches@microchip.com +D: Maintainer for ARM/Microchip (AT91) SoC support +D: Author of ADC, pinctrl, XDMA and SDHCI drivers for this platform +S: France + N: Martin Devera E: devik@cdi.cz W: http://luxik.cdi.cz/~devik/qos/ 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/cpu-freq/cpu-drivers.rst b/Documentation/cpu-freq/cpu-drivers.rst index 3b32336a7803..d84ededb66f9 100644 --- a/Documentation/cpu-freq/cpu-drivers.rst +++ b/Documentation/cpu-freq/cpu-drivers.rst @@ -75,6 +75,9 @@ And optionally .resume - A pointer to a per-policy resume function which is called with interrupts disabled and _before_ the governor is started again. + .ready - A pointer to a per-policy ready function which is called after + the policy is fully initialized. + .attr - A pointer to a NULL-terminated list of "struct freq_attr" which allow to export values to sysfs. diff --git a/Documentation/devicetree/bindings/arm/atmel-at91.yaml b/Documentation/devicetree/bindings/arm/atmel-at91.yaml index c612e1f48dba..ff91df04f9f4 100644 --- a/Documentation/devicetree/bindings/arm/atmel-at91.yaml +++ b/Documentation/devicetree/bindings/arm/atmel-at91.yaml @@ -8,7 +8,8 @@ title: Atmel AT91 device tree bindings. maintainers: - Alexandre Belloni <alexandre.belloni@bootlin.com> - - Ludovic Desroches <ludovic.desroches@microchip.com> + - Claudiu Beznea <claudiu.beznea@microchip.com> + - Nicolas Ferre <nicolas.ferre@microchip.com> description: | Boards with a SoC of the Atmel AT91 or SMART family shall have the following diff --git a/Documentation/devicetree/bindings/arm/freescale/fsl,layerscape-dcfg.txt b/Documentation/devicetree/bindings/arm/freescale/fsl,layerscape-dcfg.txt index b5cb374dc47d..10a91cc8b997 100644 --- a/Documentation/devicetree/bindings/arm/freescale/fsl,layerscape-dcfg.txt +++ b/Documentation/devicetree/bindings/arm/freescale/fsl,layerscape-dcfg.txt @@ -8,7 +8,7 @@ Required properties: - compatible: Should contain a chip-specific compatible string, Chip-specific strings are of the form "fsl,<chip>-dcfg", The following <chip>s are known to be supported: - ls1012a, ls1021a, ls1043a, ls1046a, ls2080a. + ls1012a, ls1021a, ls1043a, ls1046a, ls2080a, lx2160a - reg : should contain base address and length of DCFG memory-mapped registers 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/clock/qoriq-clock.txt b/Documentation/devicetree/bindings/clock/qoriq-clock.txt index f7d48f23da44..10119d9ef4b1 100644 --- a/Documentation/devicetree/bindings/clock/qoriq-clock.txt +++ b/Documentation/devicetree/bindings/clock/qoriq-clock.txt @@ -44,6 +44,7 @@ Required properties: * "fsl,ls1046a-clockgen" * "fsl,ls1088a-clockgen" * "fsl,ls2080a-clockgen" + * "fsl,lx2160a-clockgen" Chassis-version clock strings include: * "fsl,qoriq-clockgen-1.0": for chassis 1.0 clocks * "fsl,qoriq-clockgen-2.0": for chassis 2.0 clocks 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/gpio/sifive,gpio.yaml b/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml index e04349567eeb..427c5873f96a 100644 --- a/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml +++ b/Documentation/devicetree/bindings/gpio/sifive,gpio.yaml @@ -7,7 +7,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: SiFive GPIO controller maintainers: - - Yash Shah <yash.shah@sifive.com> - Paul Walmsley <paul.walmsley@sifive.com> properties: diff --git a/Documentation/devicetree/bindings/mfd/brcm,cru.yaml b/Documentation/devicetree/bindings/mfd/brcm,cru.yaml index be4a2df71c25..b85819fbb07c 100644 --- a/Documentation/devicetree/bindings/mfd/brcm,cru.yaml +++ b/Documentation/devicetree/bindings/mfd/brcm,cru.yaml @@ -39,7 +39,7 @@ patternProperties: '^phy@[a-f0-9]+$': $ref: ../phy/bcm-ns-usb2-phy.yaml - '^pin-controller@[a-f0-9]+$': + '^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/mfd/ti,j721e-system-controller.yaml b/Documentation/devicetree/bindings/mfd/ti,j721e-system-controller.yaml index 272832e9f8f2..fa86691ebf16 100644 --- a/Documentation/devicetree/bindings/mfd/ti,j721e-system-controller.yaml +++ b/Documentation/devicetree/bindings/mfd/ti,j721e-system-controller.yaml @@ -20,7 +20,7 @@ description: | maintainers: - Kishon Vijay Abraham I <kishon@ti.com> - - Roger Quadros <rogerq@ti.com + - Roger Quadros <rogerq@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml b/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml index cbbf5e8b1197..f78d3246fbdc 100644 --- a/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml +++ b/Documentation/devicetree/bindings/phy/ti,omap-usb2.yaml @@ -8,7 +8,7 @@ title: OMAP USB2 PHY maintainers: - Kishon Vijay Abraham I <kishon@ti.com> - - Roger Quadros <rogerq@ti.com> + - Roger Quadros <rogerq@kernel.org> properties: compatible: 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/devicetree/bindings/pwm/pwm-sifive.yaml b/Documentation/devicetree/bindings/pwm/pwm-sifive.yaml index 84e66913d042..db41cd7bf150 100644 --- a/Documentation/devicetree/bindings/pwm/pwm-sifive.yaml +++ b/Documentation/devicetree/bindings/pwm/pwm-sifive.yaml @@ -8,7 +8,6 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: SiFive PWM controller maintainers: - - Yash Shah <yash.shah@sifive.com> - Sagar Kadam <sagar.kadam@sifive.com> - Paul Walmsley <paul.walmsley@sifive.com> diff --git a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml index 2b1f91603897..e2d330bd4608 100644 --- a/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml +++ b/Documentation/devicetree/bindings/riscv/sifive-l2-cache.yaml @@ -9,7 +9,6 @@ title: SiFive L2 Cache Controller maintainers: - Sagar Kadam <sagar.kadam@sifive.com> - - Yash Shah <yash.shah@sifive.com> - Paul Walmsley <paul.walmsley@sifive.com> description: diff --git a/Documentation/devicetree/bindings/usb/dwc2.yaml b/Documentation/devicetree/bindings/usb/dwc2.yaml index f00867ebc147..481aaa09f3f2 100644 --- a/Documentation/devicetree/bindings/usb/dwc2.yaml +++ b/Documentation/devicetree/bindings/usb/dwc2.yaml @@ -53,6 +53,7 @@ properties: - const: st,stm32mp15-hsotg - const: snps,dwc2 - const: samsung,s3c6400-hsotg + - const: intel,socfpga-agilex-hsotg reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml index a634774c537c..eedde385d299 100644 --- a/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml +++ b/Documentation/devicetree/bindings/usb/ti,j721e-usb.yaml @@ -7,7 +7,7 @@ $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Bindings for the TI wrapper module for the Cadence USBSS-DRD controller maintainers: - - Roger Quadros <rogerq@ti.com> + - Roger Quadros <rogerq@kernel.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/usb/ti,keystone-dwc3.yaml b/Documentation/devicetree/bindings/usb/ti,keystone-dwc3.yaml index f6e91a5fd8fe..4f7a212fddd3 100644 --- a/Documentation/devicetree/bindings/usb/ti,keystone-dwc3.yaml +++ b/Documentation/devicetree/bindings/usb/ti,keystone-dwc3.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: TI Keystone Soc USB Controller maintainers: - - Roger Quadros <rogerq@ti.com> + - Roger Quadros <rogerq@kernel.org> properties: compatible: diff --git a/Documentation/tools/rtla/common_hist_options.rst b/Documentation/tools/rtla/common_hist_options.rst index 0266cd08a6c9..df53ff835bfb 100644 --- a/Documentation/tools/rtla/common_hist_options.rst +++ b/Documentation/tools/rtla/common_hist_options.rst @@ -2,7 +2,7 @@ Set the histogram bucket size (default *1*). -**-e**, **--entries** *N* +**-E**, **--entries** *N* Set the number of entries of the histogram (default 256). diff --git a/Documentation/tools/rtla/common_osnoise_description.rst b/Documentation/tools/rtla/common_osnoise_description.rst index 8973c5df888f..d5d61615b967 100644 --- a/Documentation/tools/rtla/common_osnoise_description.rst +++ b/Documentation/tools/rtla/common_osnoise_description.rst @@ -1,7 +1,7 @@ The **rtla osnoise** tool is an interface for the *osnoise* tracer. The *osnoise* tracer dispatches a kernel thread per-cpu. These threads read the time in a loop while with preemption, softirq and IRQs enabled, thus -allowing all the sources of operating systme noise during its execution. +allowing all the sources of operating system noise during its execution. The *osnoise*'s tracer threads take note of the delta between each time read, along with an interference counter of all sources of interference. At the end of each period, the *osnoise* tracer displays a summary of diff --git a/Documentation/tools/rtla/rtla-osnoise-hist.rst b/Documentation/tools/rtla/rtla-osnoise-hist.rst index 52298ddd8701..f2e79d22c4c4 100644 --- a/Documentation/tools/rtla/rtla-osnoise-hist.rst +++ b/Documentation/tools/rtla/rtla-osnoise-hist.rst @@ -36,7 +36,7 @@ default). The reason for reducing the runtime is to avoid starving the **rtla** tool. The tool is also set to run for *one minute*. The output histogram is set to group outputs in buckets of *10us* and *25* entries:: - [root@f34 ~/]# rtla osnoise hist -P F:1 -c 0-11 -r 900000 -d 1M -b 10 -e 25 + [root@f34 ~/]# rtla osnoise hist -P F:1 -c 0-11 -r 900000 -d 1M -b 10 -E 25 # RTLA osnoise histogram # Time unit is microseconds (us) # Duration: 0 00:01:00 diff --git a/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst b/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst index 87a36044f828..2ca92042767b 100644 --- a/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst +++ b/Documentation/translations/zh_CN/cpu-freq/cpu-drivers.rst @@ -84,6 +84,8 @@ CPUfreq核心层注册一个cpufreq_driver结构体。 .resume - 一个指向per-policy恢复函数的指针，该函数在关中断且在调节器再一次启动前被 调用。 + .ready - 一个指向per-policy准备函数的指针，该函数在策略完全初始化之后被调用。 + .attr - 一个指向NULL结尾的"struct freq_attr"列表的指针，该列表允许导出值到 sysfs。 diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index a4267104db50..9f3172376ec3 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1394,7 +1394,7 @@ documentation when it pops into existence). ------------------- :Capability: KVM_CAP_ENABLE_CAP -:Architectures: mips, ppc, s390 +:Architectures: mips, ppc, s390, x86 :Type: vcpu ioctl :Parameters: struct kvm_enable_cap (in) :Returns: 0 on success; -1 on error @@ -6997,6 +6997,20 @@ indicated by the fd to the VM this is called on. This is intended to support intra-host migration of VMs between userspace VMMs, upgrading the VMM process without interrupting the guest. +7.30 KVM_CAP_PPC_AIL_MODE_3 +------------------------------- + +:Capability: KVM_CAP_PPC_AIL_MODE_3 +:Architectures: ppc +:Type: vm + +This capability indicates that the kernel supports the mode 3 setting for the +"Address Translation Mode on Interrupt" aka "Alternate Interrupt Location" +resource that is controlled with the H_SET_MODE hypercall. + +This capability allows a guest kernel to use a better-performance mode for +handling interrupts and system calls. + 8. Other capabilities. ====================== diff --git a/MAINTAINERS b/MAINTAINERS index 4195699859e7..621d6440165a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2254,7 +2254,7 @@ F: drivers/phy/mediatek/ ARM/Microchip (AT91) SoC support M: Nicolas Ferre <nicolas.ferre@microchip.com> M: Alexandre Belloni <alexandre.belloni@bootlin.com> -M: Ludovic Desroches <ludovic.desroches@microchip.com> +M: Claudiu Beznea <claudiu.beznea@microchip.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported W: http://www.linux4sam.org @@ -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 @@ -3905,7 +3905,7 @@ 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* @@ -4913,7 +4913,8 @@ F: kernel/cgroup/cpuset.c CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG) M: Johannes Weiner <hannes@cmpxchg.org> M: Michal Hocko <mhocko@kernel.org> -M: Vladimir Davydov <vdavydov.dev@gmail.com> +M: Roman Gushchin <roman.gushchin@linux.dev> +M: Shakeel Butt <shakeelb@google.com> L: cgroups@vger.kernel.org L: linux-mm@kvack.org S: Maintained @@ -7011,12 +7012,6 @@ L: linux-edac@vger.kernel.org S: Maintained F: drivers/edac/sb_edac.c -EDAC-SIFIVE -M: Yash Shah <yash.shah@sifive.com> -L: linux-edac@vger.kernel.org -S: Supported -F: drivers/edac/sifive_edac.c - EDAC-SKYLAKE M: Tony Luck <tony.luck@intel.com> L: linux-edac@vger.kernel.org @@ -7749,8 +7744,7 @@ M: Qiang Zhao <qiang.zhao@nxp.com> L: linuxppc-dev@lists.ozlabs.org S: Maintained F: drivers/soc/fsl/qe/ -F: include/soc/fsl/*qe*.h -F: include/soc/fsl/*ucc*.h +F: include/soc/fsl/qe/ FREESCALE QUICC ENGINE UCC ETHERNET DRIVER M: Li Yang <leoyang.li@nxp.com> @@ -7781,6 +7775,7 @@ F: Documentation/devicetree/bindings/misc/fsl,dpaa2-console.yaml F: Documentation/devicetree/bindings/soc/fsl/ F: drivers/soc/fsl/ F: include/linux/fsl/ +F: include/soc/fsl/ FREESCALE SOC FS_ENET DRIVER M: Pantelis Antoniou <pantelis.antoniou@gmail.com> @@ -11680,7 +11675,7 @@ 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 @@ -11690,7 +11685,7 @@ 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> @@ -11735,7 +11730,7 @@ 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 @@ -11744,7 +11739,7 @@ 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 @@ -12433,7 +12428,7 @@ 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 @@ -13570,7 +13565,7 @@ 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 @@ -13704,7 +13699,7 @@ F: scripts/nsdeps NTB AMD DRIVER M: Sanjay R Mehta <sanju.mehta@amd.com> M: Shyam Sundar S K <Shyam-sundar.S-k@amd.com> -L: linux-ntb@googlegroups.com +L: ntb@lists.linux.dev S: Supported F: drivers/ntb/hw/amd/ @@ -13712,7 +13707,7 @@ NTB DRIVER CORE M: Jon Mason <jdmason@kudzu.us> M: Dave Jiang <dave.jiang@intel.com> M: Allen Hubbe <allenbh@gmail.com> -L: linux-ntb@googlegroups.com +L: ntb@lists.linux.dev S: Supported W: https://github.com/jonmason/ntb/wiki T: git git://github.com/jonmason/ntb.git @@ -13724,13 +13719,13 @@ F: tools/testing/selftests/ntb/ NTB IDT DRIVER M: Serge Semin <fancer.lancer@gmail.com> -L: linux-ntb@googlegroups.com +L: ntb@lists.linux.dev S: Supported F: drivers/ntb/hw/idt/ NTB INTEL DRIVER M: Dave Jiang <dave.jiang@intel.com> -L: linux-ntb@googlegroups.com +L: ntb@lists.linux.dev S: Supported W: https://github.com/davejiang/linux/wiki T: git https://github.com/davejiang/linux.git @@ -13884,7 +13879,7 @@ 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 @@ -15310,7 +15305,7 @@ 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) @@ -15574,6 +15569,7 @@ M: Iurii Zaikin <yzaikin@google.com> L: linux-kernel@vger.kernel.org L: linux-fsdevel@vger.kernel.org S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux.git sysctl-next F: fs/proc/proc_sysctl.c F: include/linux/sysctl.h F: kernel/sysctl-test.c @@ -16080,8 +16076,8 @@ F: Documentation/devicetree/bindings/mtd/qcom,nandc.yaml F: drivers/mtd/nand/raw/qcom_nandc.c QUALCOMM RMNET DRIVER -M: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> -M: Sean Tranchetti <stranche@codeaurora.org> +M: Subash Abhinov Kasiviswanathan <quic_subashab@quicinc.com> +M: Sean Tranchetti <quic_stranche@quicinc.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst @@ -16373,6 +16369,7 @@ F: drivers/watchdog/realtek_otto_wdt.c REALTEK RTL83xx SMI DSA ROUTER CHIPS M: Linus Walleij <linus.walleij@linaro.org> +M: Alvin Šipraga <alsi@bang-olufsen.dk> S: Maintained F: Documentation/devicetree/bindings/net/dsa/realtek-smi.txt F: drivers/net/dsa/realtek-smi* @@ -16951,7 +16948,7 @@ 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 @@ -16996,7 +16993,7 @@ 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 @@ -17004,7 +17001,7 @@ 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 @@ -17039,7 +17036,7 @@ 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 @@ -17065,7 +17062,7 @@ 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 @@ -17087,7 +17084,7 @@ 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 @@ -17122,7 +17119,7 @@ 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 @@ -17766,8 +17763,10 @@ M: David Rientjes <rientjes@google.com> M: Joonsoo Kim <iamjoonsoo.kim@lge.com> M: Andrew Morton <akpm@linux-foundation.org> M: Vlastimil Babka <vbabka@suse.cz> +R: Roman Gushchin <roman.gushchin@linux.dev> L: linux-mm@kvack.org S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab.git F: include/linux/sl?b*.h F: mm/sl?b* @@ -21470,7 +21469,6 @@ 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 = -rc5 +EXTRAVERSION = -rc8 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/omap3-devkit8000-common.dtsi b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi index 5e55198e4576..54cd37336be7 100644 --- a/arch/arm/boot/dts/omap3-devkit8000-common.dtsi +++ b/arch/arm/boot/dts/omap3-devkit8000-common.dtsi @@ -158,6 +158,24 @@ status = "disabled"; }; +/* Unusable as clockevent because if unreliable oscillator, allow to idle */ +&timer1_target { + /delete-property/ti,no-reset-on-init; + /delete-property/ti,no-idle; + timer@0 { + /delete-property/ti,timer-alwon; + }; +}; + +/* Preferred timer for clockevent */ +&timer12_target { + ti,no-reset-on-init; + ti,no-idle; + timer@0 { + /* Always clocked by secure_32k_fck */ + }; +}; + &twl_gpio { ti,use-leds; /* diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts index c2995a280729..162d0726b008 100644 --- a/arch/arm/boot/dts/omap3-devkit8000.dts +++ b/arch/arm/boot/dts/omap3-devkit8000.dts @@ -14,36 +14,3 @@ display2 = &tv0; }; }; - -/* Unusable as clocksource because of unreliable oscillator */ -&counter32k { - status = "disabled"; -}; - -/* Unusable as clockevent because if unreliable oscillator, allow to idle */ -&timer1_target { - /delete-property/ti,no-reset-on-init; - /delete-property/ti,no-idle; - timer@0 { - /delete-property/ti,timer-alwon; - }; -}; - -/* Preferred always-on timer for clocksource */ -&timer12_target { - ti,no-reset-on-init; - ti,no-idle; - timer@0 { - /* Always clocked by secure_32k_fck */ - }; -}; - -/* Preferred timer for clockevent */ -&timer2_target { - ti,no-reset-on-init; - ti,no-idle; - timer@0 { - assigned-clocks = <&gpt2_fck>; - assigned-clock-parents = <&sys_ck>; - }; -}; diff --git a/arch/arm/boot/dts/rk322x.dtsi b/arch/arm/boot/dts/rk322x.dtsi index 8eed9e3a92e9..5868eb512f69 100644 --- a/arch/arm/boot/dts/rk322x.dtsi +++ b/arch/arm/boot/dts/rk322x.dtsi @@ -718,8 +718,8 @@ interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>; assigned-clocks = <&cru SCLK_HDMI_PHY>; assigned-clock-parents = <&hdmi_phy>; - clocks = <&cru SCLK_HDMI_HDCP>, <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_CEC>; - clock-names = "isfr", "iahb", "cec"; + clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_HDCP>, <&cru SCLK_HDMI_CEC>; + clock-names = "iahb", "isfr", "cec"; pinctrl-names = "default"; pinctrl-0 = <&hdmii2c_xfer &hdmi_hpd &hdmi_cec>; resets = <&cru SRST_HDMI_P>; diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi index aaaa61875701..45a9d9b908d2 100644 --- a/arch/arm/boot/dts/rk3288.dtsi +++ b/arch/arm/boot/dts/rk3288.dtsi @@ -971,7 +971,7 @@ status = "disabled"; }; - crypto: cypto-controller@ff8a0000 { + crypto: crypto@ff8a0000 { compatible = "rockchip,rk3288-crypto"; reg = <0x0 0xff8a0000 0x0 0x4000>; interrupts = <GIC_SPI 48 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/boot/dts/tegra124-nyan-big.dts b/arch/arm/boot/dts/tegra124-nyan-big.dts index 1d2aac2cb6d0..fdc1d64dfff9 100644 --- a/arch/arm/boot/dts/tegra124-nyan-big.dts +++ b/arch/arm/boot/dts/tegra124-nyan-big.dts @@ -13,12 +13,15 @@ "google,nyan-big-rev1", "google,nyan-big-rev0", "google,nyan-big", "google,nyan", "nvidia,tegra124"; - panel: panel { - compatible = "auo,b133xtn01"; - - power-supply = <&vdd_3v3_panel>; - backlight = <&backlight>; - ddc-i2c-bus = <&dpaux>; + host1x@50000000 { + dpaux@545c0000 { + aux-bus { + panel: panel { + compatible = "auo,b133xtn01"; + backlight = <&backlight>; + }; + }; + }; }; mmc@700b0400 { /* SD Card on this bus */ diff --git a/arch/arm/boot/dts/tegra124-nyan-blaze.dts b/arch/arm/boot/dts/tegra124-nyan-blaze.dts index 677babde6460..abdf4456826f 100644 --- a/arch/arm/boot/dts/tegra124-nyan-blaze.dts +++ b/arch/arm/boot/dts/tegra124-nyan-blaze.dts @@ -15,12 +15,15 @@ "google,nyan-blaze-rev0", "google,nyan-blaze", "google,nyan", "nvidia,tegra124"; - panel: panel { - compatible = "samsung,ltn140at29-301"; - - power-supply = <&vdd_3v3_panel>; - backlight = <&backlight>; - ddc-i2c-bus = <&dpaux>; + host1x@50000000 { + dpaux@545c0000 { + aux-bus { + panel: panel { + compatible = "samsung,ltn140at29-301"; + backlight = <&backlight>; + }; + }; + }; }; sound { diff --git a/arch/arm/boot/dts/tegra124-venice2.dts b/arch/arm/boot/dts/tegra124-venice2.dts index 232c90604df9..6a9592ceb5f2 100644 --- a/arch/arm/boot/dts/tegra124-venice2.dts +++ b/arch/arm/boot/dts/tegra124-venice2.dts @@ -48,6 +48,13 @@ dpaux@545c0000 { vdd-supply = <&vdd_3v3_panel>; status = "okay"; + + aux-bus { + panel: panel { + compatible = "lg,lp129qe"; + backlight = <&backlight>; + }; + }; }; }; @@ -1080,13 +1087,6 @@ }; }; - panel: panel { - compatible = "lg,lp129qe"; - power-supply = <&vdd_3v3_panel>; - backlight = <&backlight>; - ddc-i2c-bus = <&dpaux>; - }; - vdd_mux: regulator-mux { compatible = "regulator-fixed"; regulator-name = "+VDD_MUX"; 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..85f9e538fb32 --- /dev/null +++ b/arch/arm/include/asm/spectre.h @@ -0,0 +1,38 @@ +/* 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), +}; + +#ifdef CONFIG_GENERIC_CPU_VULNERABILITIES +void spectre_v2_update_state(unsigned int state, unsigned int methods); +#else +static inline void spectre_v2_update_state(unsigned int state, + unsigned int methods) +{} +#endif + +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..ee3f7a599181 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 +3: b . + 4 + subs r0, r0, #1 + bne 3b + 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/kgdb.c b/arch/arm/kernel/kgdb.c index 7bd30c0a4280..22f937e6f3ff 100644 --- a/arch/arm/kernel/kgdb.c +++ b/arch/arm/kernel/kgdb.c @@ -154,22 +154,38 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr) return 0; } -static struct undef_hook kgdb_brkpt_hook = { +static struct undef_hook kgdb_brkpt_arm_hook = { .instr_mask = 0xffffffff, .instr_val = KGDB_BREAKINST, - .cpsr_mask = MODE_MASK, + .cpsr_mask = PSR_T_BIT | MODE_MASK, .cpsr_val = SVC_MODE, .fn = kgdb_brk_fn }; -static struct undef_hook kgdb_compiled_brkpt_hook = { +static struct undef_hook kgdb_brkpt_thumb_hook = { + .instr_mask = 0xffff, + .instr_val = KGDB_BREAKINST & 0xffff, + .cpsr_mask = PSR_T_BIT | MODE_MASK, + .cpsr_val = PSR_T_BIT | SVC_MODE, + .fn = kgdb_brk_fn +}; + +static struct undef_hook kgdb_compiled_brkpt_arm_hook = { .instr_mask = 0xffffffff, .instr_val = KGDB_COMPILED_BREAK, - .cpsr_mask = MODE_MASK, + .cpsr_mask = PSR_T_BIT | MODE_MASK, .cpsr_val = SVC_MODE, .fn = kgdb_compiled_brk_fn }; +static struct undef_hook kgdb_compiled_brkpt_thumb_hook = { + .instr_mask = 0xffff, + .instr_val = KGDB_COMPILED_BREAK & 0xffff, + .cpsr_mask = PSR_T_BIT | MODE_MASK, + .cpsr_val = PSR_T_BIT | SVC_MODE, + .fn = kgdb_compiled_brk_fn +}; + static int __kgdb_notify(struct die_args *args, unsigned long cmd) { struct pt_regs *regs = args->regs; @@ -210,8 +226,10 @@ int kgdb_arch_init(void) if (ret != 0) return ret; - register_undef_hook(&kgdb_brkpt_hook); - register_undef_hook(&kgdb_compiled_brkpt_hook); + register_undef_hook(&kgdb_brkpt_arm_hook); + register_undef_hook(&kgdb_brkpt_thumb_hook); + register_undef_hook(&kgdb_compiled_brkpt_arm_hook); + register_undef_hook(&kgdb_compiled_brkpt_thumb_hook); return 0; } @@ -224,8 +242,10 @@ int kgdb_arch_init(void) */ void kgdb_arch_exit(void) { - unregister_undef_hook(&kgdb_brkpt_hook); - unregister_undef_hook(&kgdb_compiled_brkpt_hook); + unregister_undef_hook(&kgdb_brkpt_arm_hook); + unregister_undef_hook(&kgdb_brkpt_thumb_hook); + unregister_undef_hook(&kgdb_compiled_brkpt_arm_hook); + unregister_undef_hook(&kgdb_compiled_brkpt_thumb_hook); unregister_die_notifier(&kgdb_notifier); } 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/mmu.c b/arch/arm/mm/mmu.c index 274e4f73fd33..5e2be37a198e 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -212,12 +212,14 @@ early_param("ecc", early_ecc); static int __init early_cachepolicy(char *p) { pr_warn("cachepolicy kernel parameter not supported without cp15\n"); + return 0; } early_param("cachepolicy", early_cachepolicy); static int __init noalign_setup(char *__unused) { pr_warn("noalign kernel parameter not supported without cp15\n"); + return 1; } __setup("noalign", noalign_setup); 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 f5e98fe48180..f1a8af8c7d9e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1253,9 +1253,6 @@ 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) @@ -1384,6 +1381,15 @@ 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/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 6288e104a089..a2635b14da30 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -543,8 +543,7 @@ <0x02000000 0x00 0x50000000 0x00 0x50000000 0x0 0x08000000>, <0x42000000 0x40 0x00000000 0x40 0x00000000 0x1 0x00000000>; /* Standard AXI Translation entries as programmed by EDK2 */ - dma-ranges = <0x02000000 0x0 0x2c1c0000 0x0 0x2c1c0000 0x0 0x00040000>, - <0x02000000 0x0 0x80000000 0x0 0x80000000 0x0 0x80000000>, + dma-ranges = <0x02000000 0x0 0x80000000 0x0 0x80000000 0x0 0x80000000>, <0x43000000 0x8 0x00000000 0x8 0x00000000 0x2 0x00000000>; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 7>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index f77f90ed416f..0c7a72c51a31 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -707,7 +707,6 @@ clocks = <&clk IMX8MM_CLK_VPU_DEC_ROOT>; assigned-clocks = <&clk IMX8MM_CLK_VPU_BUS>; assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_800M>; - resets = <&src IMX8MQ_RESET_VPU_RESET>; }; pgc_vpu_g1: power-domain@7 { diff --git a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi index a987ff7156bd..09f7364dd1d0 100644 --- a/arch/arm64/boot/dts/freescale/imx8ulp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8ulp.dtsi @@ -132,7 +132,7 @@ scmi_sensor: protocol@15 { reg = <0x15>; - #thermal-sensor-cells = <0>; + #thermal-sensor-cells = <1>; }; }; }; diff --git a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi index 0dd2d2ee765a..f4270cf18996 100644 --- a/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi +++ b/arch/arm64/boot/dts/intel/socfpga_agilex.dtsi @@ -502,7 +502,7 @@ }; usb0: usb@ffb00000 { - compatible = "snps,dwc2"; + compatible = "intel,socfpga-agilex-hsotg", "snps,dwc2"; reg = <0xffb00000 0x40000>; interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0>; @@ -515,7 +515,7 @@ }; usb1: usb@ffb40000 { - compatible = "snps,dwc2"; + compatible = "intel,socfpga-agilex-hsotg", "snps,dwc2"; reg = <0xffb40000 0x40000>; interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>; phys = <&usbphy0>; 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/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi index f972704dfe7a..56dfbb2e2fa6 100644 --- a/arch/arm64/boot/dts/rockchip/px30.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30.dtsi @@ -711,7 +711,7 @@ clock-names = "pclk", "timer"; }; - dmac: dmac@ff240000 { + dmac: dma-controller@ff240000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x0 0xff240000 0x0 0x4000>; interrupts = <GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 39db0b85b4da..b822533dc7f1 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -489,7 +489,7 @@ status = "disabled"; }; - dmac: dmac@ff1f0000 { + dmac: dma-controller@ff1f0000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x0 0xff1f0000 0x0 0x4000>; interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi index 45a5ae5d2027..162f08bca0d4 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi @@ -286,7 +286,7 @@ sound: sound { compatible = "rockchip,rk3399-gru-sound"; - rockchip,cpu = <&i2s0 &i2s2>; + rockchip,cpu = <&i2s0 &spdif>; }; }; @@ -437,10 +437,6 @@ ap_i2c_audio: &i2c8 { status = "okay"; }; -&i2s2 { - status = "okay"; -}; - &io_domains { status = "okay"; @@ -537,6 +533,17 @@ ap_i2c_audio: &i2c8 { vqmmc-supply = <&ppvar_sd_card_io>; }; +&spdif { + status = "okay"; + + /* + * SPDIF is routed internally to DP; we either don't use these pins, or + * mux them to something else. + */ + /delete-property/ pinctrl-0; + /delete-property/ pinctrl-names; +}; + &spi1 { status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts index 292bb7e80cf3..3ae5d727e367 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou.dts @@ -232,6 +232,7 @@ &usbdrd_dwc3_0 { dr_mode = "otg"; + extcon = <&extcon_usb3>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index fb67db4619ea..08fa00364b42 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -25,6 +25,13 @@ }; }; + extcon_usb3: extcon-usb3 { + compatible = "linux,extcon-usb-gpio"; + id-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&usb3_id>; + }; + clkin_gmac: external-gmac-clock { compatible = "fixed-clock"; clock-frequency = <125000000>; @@ -422,9 +429,22 @@ <4 RK_PA3 RK_FUNC_GPIO &pcfg_pull_none>; }; }; + + usb3 { + usb3_id: usb3-id { + rockchip,pins = + <1 RK_PC2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; }; &sdhci { + /* + * Signal integrity isn't great at 200MHz but 100MHz has proven stable + * enough. + */ + max-frequency = <100000000>; + bus-width = <8>; mmc-hs400-1_8v; mmc-hs400-enhanced-strobe; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index d3cdf6f42a30..080457a68e3c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1881,10 +1881,10 @@ interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH 0>; clocks = <&cru PCLK_HDMI_CTRL>, <&cru SCLK_HDMI_SFR>, - <&cru PLL_VPLL>, + <&cru SCLK_HDMI_CEC>, <&cru PCLK_VIO_GRF>, - <&cru SCLK_HDMI_CEC>; - clock-names = "iahb", "isfr", "vpll", "grf", "cec"; + <&cru PLL_VPLL>; + clock-names = "iahb", "isfr", "cec", "grf", "vpll"; power-domains = <&power RK3399_PD_HDCP>; reg-io-width = <4>; rockchip,grf = <&grf>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts index 166399b7f13f..d9eb92d59099 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3566-quartz64-a.dts @@ -285,8 +285,6 @@ vcc_ddr: DCDC_REG3 { regulator-always-on; regulator-boot-on; - regulator-min-microvolt = <1100000>; - regulator-max-microvolt = <1100000>; regulator-initial-mode = <0x2>; regulator-name = "vcc_ddr"; regulator-state-mem { diff --git a/arch/arm64/boot/dts/rockchip/rk3568.dtsi b/arch/arm64/boot/dts/rockchip/rk3568.dtsi index 2fd313a295f8..d91df1cde736 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3568.dtsi @@ -32,13 +32,11 @@ clocks = <&cru SCLK_GMAC0>, <&cru SCLK_GMAC0_RX_TX>, <&cru SCLK_GMAC0_RX_TX>, <&cru CLK_MAC0_REFOUT>, <&cru ACLK_GMAC0>, <&cru PCLK_GMAC0>, - <&cru SCLK_GMAC0_RX_TX>, <&cru CLK_GMAC0_PTP_REF>, - <&cru PCLK_XPCS>; + <&cru SCLK_GMAC0_RX_TX>, <&cru CLK_GMAC0_PTP_REF>; clock-names = "stmmaceth", "mac_clk_rx", "mac_clk_tx", "clk_mac_refout", "aclk_mac", "pclk_mac", - "clk_mac_speed", "ptp_ref", - "pclk_xpcs"; + "clk_mac_speed", "ptp_ref"; resets = <&cru SRST_A_GMAC0>; reset-names = "stmmaceth"; rockchip,grf = <&grf>; diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi index a68033a23975..8ccce54ee8e7 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi @@ -651,7 +651,7 @@ status = "disabled"; }; - dmac0: dmac@fe530000 { + dmac0: dma-controller@fe530000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x0 0xfe530000 0x0 0x4000>; interrupts = <GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>, @@ -662,7 +662,7 @@ #dma-cells = <1>; }; - dmac1: dmac@fe550000 { + dmac1: dma-controller@fe550000 { compatible = "arm,pl330", "arm,primecell"; reg = <0x0 0xfe550000 0x0 0x4000>; interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>, 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 6b776c8667b2..b02f0c328c8e 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 3eae32876897..5918095c90a5 100644 --- a/arch/arm64/kvm/psci.c +++ b/arch/arm64/kvm/psci.c @@ -46,8 +46,7 @@ static unsigned long kvm_psci_vcpu_suspend(struct kvm_vcpu *vcpu) * specification (ARM DEN 0022A). This means all suspend states * for KVM will preserve the register state. */ - kvm_vcpu_halt(vcpu); - kvm_clear_request(KVM_REQ_UNHALT, vcpu); + kvm_vcpu_wfi(vcpu); return PSCI_RET_SUCCESS; } @@ -406,7 +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) @@ -420,6 +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; } @@ -459,6 +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; @@ -475,6 +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: @@ -520,6 +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/mips/kernel/setup.c b/arch/mips/kernel/setup.c index f979adfd4fc2..ef73ba1e0ec1 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -803,7 +803,7 @@ early_param("coherentio", setcoherentio); static int __init setnocoherentio(char *str) { - dma_default_coherent = true; + dma_default_coherent = false; pr_info("Software DMA cache coherency (command line)\n"); return 0; } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index d542fb7af3ba..1986d1309410 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -351,6 +351,9 @@ asmlinkage void start_secondary(void) cpu = smp_processor_id(); cpu_data[cpu].udelay_val = loops_per_jiffy; + set_cpu_sibling_map(cpu); + set_cpu_core_map(cpu); + cpumask_set_cpu(cpu, &cpu_coherent_mask); notify_cpu_starting(cpu); @@ -362,9 +365,6 @@ asmlinkage void start_secondary(void) /* The CPU is running and counters synchronised, now mark it online */ set_cpu_online(cpu, true); - set_cpu_sibling_map(cpu); - set_cpu_core_map(cpu); - calculate_cpu_foreign_map(); /* diff --git a/arch/mips/ralink/mt7621.c b/arch/mips/ralink/mt7621.c index d6efffd4dd20..fb0565bc34fd 100644 --- a/arch/mips/ralink/mt7621.c +++ b/arch/mips/ralink/mt7621.c @@ -22,7 +22,9 @@ #include "common.h" -static void *detect_magic __initdata = detect_memory_region; +#define MT7621_MEM_TEST_PATTERN 0xaa5555aa + +static u32 detect_magic __initdata; int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) { @@ -58,24 +60,32 @@ phys_addr_t mips_cpc_default_phys_base(void) panic("Cannot detect cpc address"); } +static bool __init mt7621_addr_wraparound_test(phys_addr_t size) +{ + void *dm = (void *)KSEG1ADDR(&detect_magic); + + if (CPHYSADDR(dm + size) >= MT7621_LOWMEM_MAX_SIZE) + return true; + __raw_writel(MT7621_MEM_TEST_PATTERN, dm); + if (__raw_readl(dm) != __raw_readl(dm + size)) + return false; + __raw_writel(~MT7621_MEM_TEST_PATTERN, dm); + return __raw_readl(dm) == __raw_readl(dm + size); +} + static void __init mt7621_memory_detect(void) { - void *dm = &detect_magic; phys_addr_t size; - for (size = 32 * SZ_1M; size < 256 * SZ_1M; size <<= 1) { - if (!__builtin_memcmp(dm, dm + size, sizeof(detect_magic))) - break; + for (size = 32 * SZ_1M; size <= 256 * SZ_1M; size <<= 1) { + if (mt7621_addr_wraparound_test(size)) { + memblock_add(MT7621_LOWMEM_BASE, size); + return; + } } - if ((size == 256 * SZ_1M) && - (CPHYSADDR(dm + size) < MT7621_LOWMEM_MAX_SIZE) && - __builtin_memcmp(dm, dm + size, sizeof(detect_magic))) { - memblock_add(MT7621_LOWMEM_BASE, MT7621_LOWMEM_MAX_SIZE); - memblock_add(MT7621_HIGHMEM_BASE, MT7621_HIGHMEM_SIZE); - } else { - memblock_add(MT7621_LOWMEM_BASE, size); - } + memblock_add(MT7621_LOWMEM_BASE, MT7621_LOWMEM_MAX_SIZE); + memblock_add(MT7621_HIGHMEM_BASE, MT7621_HIGHMEM_SIZE); } void __init ralink_of_remap(void) diff --git a/arch/parisc/kernel/unaligned.c b/arch/parisc/kernel/unaligned.c index 237d20dd5622..286cec4d86d7 100644 --- a/arch/parisc/kernel/unaligned.c +++ b/arch/parisc/kernel/unaligned.c @@ -340,7 +340,7 @@ static int emulate_stw(struct pt_regs *regs, int frreg, int flop) : "r" (val), "r" (regs->ior), "r" (regs->isr) : "r19", "r20", "r21", "r22", "r1", FIXUP_BRANCH_CLOBBER ); - return 0; + return ret; } static int emulate_std(struct pt_regs *regs, int frreg, int flop) { @@ -397,7 +397,7 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) __asm__ __volatile__ ( " mtsp %4, %%sr1\n" " zdep %2, 29, 2, %%r19\n" -" dep %%r0, 31, 2, %2\n" +" dep %%r0, 31, 2, %3\n" " mtsar %%r19\n" " zvdepi -2, 32, %%r19\n" "1: ldw 0(%%sr1,%3),%%r20\n" @@ -409,7 +409,7 @@ static int emulate_std(struct pt_regs *regs, int frreg, int flop) " andcm %%r21, %%r19, %%r21\n" " or %1, %%r20, %1\n" " or %2, %%r21, %2\n" -"3: stw %1,0(%%sr1,%1)\n" +"3: stw %1,0(%%sr1,%3)\n" "4: stw %%r1,4(%%sr1,%3)\n" "5: stw %2,8(%%sr1,%3)\n" " copy %%r0, %0\n" @@ -596,7 +596,6 @@ void handle_unaligned(struct pt_regs *regs) ret = ERR_NOTHANDLED; /* "undefined", but lets kill them. */ break; } -#ifdef CONFIG_PA20 switch (regs->iir & OPCODE2_MASK) { case OPCODE_FLDD_L: @@ -607,22 +606,23 @@ void handle_unaligned(struct pt_regs *regs) flop=1; ret = emulate_std(regs, R2(regs->iir),1); break; +#ifdef CONFIG_PA20 case OPCODE_LDD_L: ret = emulate_ldd(regs, R2(regs->iir),0); break; case OPCODE_STD_L: ret = emulate_std(regs, R2(regs->iir),0); break; - } #endif + } switch (regs->iir & OPCODE3_MASK) { case OPCODE_FLDW_L: flop=1; - ret = emulate_ldw(regs, R2(regs->iir),0); + ret = emulate_ldw(regs, R2(regs->iir), 1); break; case OPCODE_LDW_M: - ret = emulate_ldw(regs, R2(regs->iir),1); + ret = emulate_ldw(regs, R2(regs->iir), 0); break; case OPCODE_FSTW_L: 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/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h index 160abcb8e9fa..ea0e487f87b1 100644 --- a/arch/powerpc/include/asm/nmi.h +++ b/arch/powerpc/include/asm/nmi.h @@ -9,7 +9,7 @@ long soft_nmi_interrupt(struct pt_regs *regs); static inline void arch_touch_nmi_watchdog(void) {} #endif -#if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE) +#ifdef CONFIG_NMI_IPI extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace diff --git a/arch/riscv/Kconfig.erratas b/arch/riscv/Kconfig.erratas index b44d6ecdb46e..0aacd7052585 100644 --- a/arch/riscv/Kconfig.erratas +++ b/arch/riscv/Kconfig.erratas @@ -2,6 +2,7 @@ menu "CPU errata selection" config RISCV_ERRATA_ALTERNATIVE bool "RISC-V alternative scheme" + depends on !XIP_KERNEL default y help This Kconfig allows the kernel to automatically patch the diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs index 6ec44a22278a..c112ab2a9052 100644 --- a/arch/riscv/Kconfig.socs +++ b/arch/riscv/Kconfig.socs @@ -14,8 +14,8 @@ config SOC_SIFIVE select CLK_SIFIVE select CLK_SIFIVE_PRCI select SIFIVE_PLIC - select RISCV_ERRATA_ALTERNATIVE - select ERRATA_SIFIVE + select RISCV_ERRATA_ALTERNATIVE if !XIP_KERNEL + select ERRATA_SIFIVE if !XIP_KERNEL help This enables support for SiFive SoC platform hardware. 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/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig index 2a82a3b2992b..af64b95e88cc 100644 --- a/arch/riscv/configs/nommu_k210_sdcard_defconfig +++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig @@ -23,7 +23,7 @@ CONFIG_SLOB=y CONFIG_SOC_CANAAN=y CONFIG_SMP=y CONFIG_NR_CPUS=2 -CONFIG_CMDLINE="earlycon console=ttySIF0 rootdelay=2 root=/dev/mmcblk0p1 ro" +CONFIG_CMDLINE="earlycon console=ttySIF0 root=/dev/mmcblk0p1 rootwait ro" CONFIG_CMDLINE_FORCE=y # CONFIG_SECCOMP is not set # CONFIG_STACKPROTECTOR is not set 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/kernel/Makefile b/arch/riscv/kernel/Makefile index 612556faa527..ffc87e76b1dd 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -51,6 +51,8 @@ obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o +obj-$(CONFIG_TRACE_IRQFLAGS) += trace_irq.o + obj-$(CONFIG_RISCV_BASE_PMU) += perf_event.o obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index ed29e9c8f660..d6a46ed0bf05 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -108,7 +108,7 @@ _save_context: .option pop #ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_off + call __trace_hardirqs_off #endif #ifdef CONFIG_CONTEXT_TRACKING @@ -143,7 +143,7 @@ skip_context_tracking: li t0, EXC_BREAKPOINT beq s4, t0, 1f #ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on + call __trace_hardirqs_on #endif csrs CSR_STATUS, SR_IE @@ -234,7 +234,7 @@ ret_from_exception: REG_L s0, PT_STATUS(sp) csrc CSR_STATUS, SR_IE #ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_off + call __trace_hardirqs_off #endif #ifdef CONFIG_RISCV_M_MODE /* the MPP value is too large to be used as an immediate arg for addi */ @@ -270,10 +270,10 @@ restore_all: REG_L s1, PT_STATUS(sp) andi t0, s1, SR_PIE beqz t0, 1f - call trace_hardirqs_on + call __trace_hardirqs_on j 2f 1: - call trace_hardirqs_off + call __trace_hardirqs_off 2: #endif REG_L a0, PT_STATUS(sp) diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 68a9e3d1fe16..4a48287513c3 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -13,6 +13,19 @@ #include <linux/pgtable.h> #include <asm/sections.h> +/* + * The auipc+jalr instruction pair can reach any PC-relative offset + * in the range [-2^31 - 2^11, 2^31 - 2^11) + */ +static bool riscv_insn_valid_32bit_offset(ptrdiff_t val) +{ +#ifdef CONFIG_32BIT + return true; +#else + return (-(1L << 31) - (1L << 11)) <= val && val < ((1L << 31) - (1L << 11)); +#endif +} + static int apply_r_riscv_32_rela(struct module *me, u32 *location, Elf_Addr v) { if (v != (u32)v) { @@ -95,7 +108,7 @@ static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location, ptrdiff_t offset = (void *)v - (void *)location; s32 hi20; - if (offset != (s32)offset) { + if (!riscv_insn_valid_32bit_offset(offset)) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", me->name, (long long)v, location); @@ -197,10 +210,9 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location, Elf_Addr v) { ptrdiff_t offset = (void *)v - (void *)location; - s32 fill_v = offset; u32 hi20, lo12; - if (offset != fill_v) { + if (!riscv_insn_valid_32bit_offset(offset)) { /* Only emit the plt entry if offset over 32-bit range */ if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) { offset = module_emit_plt_entry(me, v); @@ -224,10 +236,9 @@ static int apply_r_riscv_call_rela(struct module *me, u32 *location, Elf_Addr v) { ptrdiff_t offset = (void *)v - (void *)location; - s32 fill_v = offset; u32 hi20, lo12; - if (offset != fill_v) { + if (!riscv_insn_valid_32bit_offset(offset)) { pr_err( "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", me->name, (long long)v, location); diff --git a/arch/riscv/kernel/trace_irq.c b/arch/riscv/kernel/trace_irq.c new file mode 100644 index 000000000000..095ac976d7da --- /dev/null +++ b/arch/riscv/kernel/trace_irq.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com> + */ + +#include <linux/irqflags.h> +#include <linux/kprobes.h> +#include "trace_irq.h" + +/* + * trace_hardirqs_on/off require the caller to setup frame pointer properly. + * Otherwise, CALLER_ADDR1 might trigger an pagging exception in kernel. + * Here we add one extra level so they can be safely called by low + * level entry code which $fp is used for other purpose. + */ + +void __trace_hardirqs_on(void) +{ + trace_hardirqs_on(); +} +NOKPROBE_SYMBOL(__trace_hardirqs_on); + +void __trace_hardirqs_off(void) +{ + trace_hardirqs_off(); +} +NOKPROBE_SYMBOL(__trace_hardirqs_off); diff --git a/arch/riscv/kernel/trace_irq.h b/arch/riscv/kernel/trace_irq.h new file mode 100644 index 000000000000..99fe67377e5e --- /dev/null +++ b/arch/riscv/kernel/trace_irq.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 Changbin Du <changbin.du@gmail.com> + */ +#ifndef __TRACE_IRQ_H +#define __TRACE_IRQ_H + +void __trace_hardirqs_on(void); +void __trace_hardirqs_off(void); + +#endif /* __TRACE_IRQ_H */ diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile index 7ebaef10ea1b..ac7a25298a04 100644 --- a/arch/riscv/mm/Makefile +++ b/arch/riscv/mm/Makefile @@ -24,6 +24,9 @@ obj-$(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/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 6dcccb304775..ec9830d2aabf 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -703,7 +703,6 @@ struct kvm_vcpu_arch { struct fpu_guest guest_fpu; u64 xcr0; - u64 guest_supported_xcr0; struct kvm_pio_request pio; void *pio_data; 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 5007c3ffe96f..b4470eabf151 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/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 48afe96ae0f0..7c63a1911fae 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -13,6 +13,30 @@ #include "sgx.h" /* + * Calculate byte offset of a PCMD struct associated with an enclave page. PCMD's + * follow right after the EPC data in the backing storage. In addition to the + * visible enclave pages, there's one extra page slot for SECS, before PCMD + * structs. + */ +static inline pgoff_t sgx_encl_get_backing_page_pcmd_offset(struct sgx_encl *encl, + unsigned long page_index) +{ + pgoff_t epc_end_off = encl->size + sizeof(struct sgx_secs); + + return epc_end_off + page_index * sizeof(struct sgx_pcmd); +} + +/* + * Free a page from the backing storage in the given page index. + */ +static inline void sgx_encl_truncate_backing_page(struct sgx_encl *encl, unsigned long page_index) +{ + struct inode *inode = file_inode(encl->backing); + + shmem_truncate_range(inode, PFN_PHYS(page_index), PFN_PHYS(page_index) + PAGE_SIZE - 1); +} + +/* * ELDU: Load an EPC page as unblocked. For more info, see "OS Management of EPC * Pages" in the SDM. */ @@ -22,9 +46,11 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, { unsigned long va_offset = encl_page->desc & SGX_ENCL_PAGE_VA_OFFSET_MASK; struct sgx_encl *encl = encl_page->encl; + pgoff_t page_index, page_pcmd_off; struct sgx_pageinfo pginfo; struct sgx_backing b; - pgoff_t page_index; + bool pcmd_page_empty; + u8 *pcmd_page; int ret; if (secs_page) @@ -32,14 +58,16 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, else page_index = PFN_DOWN(encl->size); + page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); + ret = sgx_encl_get_backing(encl, page_index, &b); if (ret) return ret; pginfo.addr = encl_page->desc & PAGE_MASK; pginfo.contents = (unsigned long)kmap_atomic(b.contents); - pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) + - b.pcmd_offset; + pcmd_page = kmap_atomic(b.pcmd); + pginfo.metadata = (unsigned long)pcmd_page + b.pcmd_offset; if (secs_page) pginfo.secs = (u64)sgx_get_epc_virt_addr(secs_page); @@ -55,11 +83,24 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, ret = -EFAULT; } - kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset)); + memset(pcmd_page + b.pcmd_offset, 0, sizeof(struct sgx_pcmd)); + + /* + * The area for the PCMD in the page was zeroed above. Check if the + * whole page is now empty meaning that all PCMD's have been zeroed: + */ + pcmd_page_empty = !memchr_inv(pcmd_page, 0, PAGE_SIZE); + + kunmap_atomic(pcmd_page); kunmap_atomic((void *)(unsigned long)pginfo.contents); sgx_encl_put_backing(&b, false); + sgx_encl_truncate_backing_page(encl, page_index); + + if (pcmd_page_empty) + sgx_encl_truncate_backing_page(encl, PFN_DOWN(page_pcmd_off)); + return ret; } @@ -579,7 +620,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl, int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, struct sgx_backing *backing) { - pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5); + pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index); struct page *contents; struct page *pcmd; @@ -587,7 +628,7 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, if (IS_ERR(contents)) return PTR_ERR(contents); - pcmd = sgx_encl_get_backing_page(encl, pcmd_index); + pcmd = sgx_encl_get_backing_page(encl, PFN_DOWN(page_pcmd_off)); if (IS_ERR(pcmd)) { put_page(contents); return PTR_ERR(pcmd); @@ -596,9 +637,7 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index, backing->page_index = page_index; backing->contents = contents; backing->pcmd = pcmd; - backing->pcmd_offset = - (page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) * - sizeof(struct sgx_pcmd); + backing->pcmd_offset = page_pcmd_off & (PAGE_SIZE - 1); return 0; } diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index bc0657f0deed..f267205f2d5a 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -995,8 +995,10 @@ early_param("memmap", parse_memmap_opt); */ void __init e820__reserve_setup_data(void) { + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; + u32 len; pa_data = boot_params.hdr.setup_data; if (!pa_data) @@ -1004,6 +1006,14 @@ void __init e820__reserve_setup_data(void) while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); + if (!data) { + pr_warn("e820: failed to memremap setup_data entry\n"); + return; + } + + len = sizeof(*data); + pa_next = data->next; + e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); /* @@ -1015,18 +1025,27 @@ void __init e820__reserve_setup_data(void) sizeof(*data) + data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - e820__range_update(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - e820__range_update_kexec(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + if (data->type == SETUP_INDIRECT) { + len += data->len; + early_memunmap(data, sizeof(*data)); + data = early_memremap(pa_data, len); + if (!data) { + pr_warn("e820: failed to memremap indirect setup_data\n"); + return; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + e820__range_update(indirect->addr, indirect->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + e820__range_update_kexec(indirect->addr, indirect->len, + E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + } } - pa_data = data->next; - early_memunmap(data, sizeof(*data)); + pa_data = pa_next; + early_memunmap(data, len); } e820__update_table(e820_table); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 02b3ddaf4f75..7c7824ae7862 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1558,7 +1558,10 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; - newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; + + if (!guest_fpu) + newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; + newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c index 64b6da95af98..e2e89bebcbc3 100644 --- a/arch/x86/kernel/kdebugfs.c +++ b/arch/x86/kernel/kdebugfs.c @@ -88,11 +88,13 @@ create_setup_data_node(struct dentry *parent, int no, static int __init create_setup_data_nodes(struct dentry *parent) { + struct setup_indirect *indirect; struct setup_data_node *node; struct setup_data *data; - int error; + u64 pa_data, pa_next; struct dentry *d; - u64 pa_data; + int error; + u32 len; int no = 0; d = debugfs_create_dir("setup_data", parent); @@ -112,12 +114,29 @@ static int __init create_setup_data_nodes(struct dentry *parent) error = -ENOMEM; goto err_dir; } - - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - node->paddr = ((struct setup_indirect *)data->data)->addr; - node->type = ((struct setup_indirect *)data->data)->type; - node->len = ((struct setup_indirect *)data->data)->len; + pa_next = data->next; + + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(pa_data, len, MEMREMAP_WB); + if (!data) { + kfree(node); + error = -ENOMEM; + goto err_dir; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + node->paddr = indirect->addr; + node->type = indirect->type; + node->len = indirect->len; + } else { + node->paddr = pa_data; + node->type = data->type; + node->len = data->len; + } } else { node->paddr = pa_data; node->type = data->type; @@ -125,7 +144,7 @@ static int __init create_setup_data_nodes(struct dentry *parent) } create_setup_data_node(d, no, node); - pa_data = data->next; + pa_data = pa_next; memunmap(data); no++; diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c index d0a19121c6a4..257892fcefa7 100644 --- a/arch/x86/kernel/ksysfs.c +++ b/arch/x86/kernel/ksysfs.c @@ -91,26 +91,41 @@ static int get_setup_data_paddr(int nr, u64 *paddr) static int __init get_setup_data_size(int nr, size_t *size) { - int i = 0; + u64 pa_data = boot_params.hdr.setup_data, pa_next; + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data = boot_params.hdr.setup_data; + int i = 0; + u32 len; while (pa_data) { data = memremap(pa_data, sizeof(*data), MEMREMAP_WB); if (!data) return -ENOMEM; + pa_next = data->next; + if (nr == i) { - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) - *size = ((struct setup_indirect *)data->data)->len; - else + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(pa_data, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) + *size = indirect->len; + else + *size = data->len; + } else { *size = data->len; + } memunmap(data); return 0; } - pa_data = data->next; + pa_data = pa_next; memunmap(data); i++; } @@ -120,9 +135,11 @@ static int __init get_setup_data_size(int nr, size_t *size) static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { + struct setup_indirect *indirect; + struct setup_data *data; int nr, ret; u64 paddr; - struct setup_data *data; + u32 len; ret = kobj_to_setup_data_nr(kobj, &nr); if (ret) @@ -135,10 +152,20 @@ static ssize_t type_show(struct kobject *kobj, if (!data) return -ENOMEM; - if (data->type == SETUP_INDIRECT) - ret = sprintf(buf, "0x%x\n", ((struct setup_indirect *)data->data)->type); - else + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(paddr, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + ret = sprintf(buf, "0x%x\n", indirect->type); + } else { ret = sprintf(buf, "0x%x\n", data->type); + } + memunmap(data); return ret; } @@ -149,9 +176,10 @@ static ssize_t setup_data_data_read(struct file *fp, char *buf, loff_t off, size_t count) { + struct setup_indirect *indirect; + struct setup_data *data; int nr, ret = 0; u64 paddr, len; - struct setup_data *data; void *p; ret = kobj_to_setup_data_nr(kobj, &nr); @@ -165,10 +193,27 @@ static ssize_t setup_data_data_read(struct file *fp, if (!data) return -ENOMEM; - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - paddr = ((struct setup_indirect *)data->data)->addr; - len = ((struct setup_indirect *)data->data)->len; + if (data->type == SETUP_INDIRECT) { + len = sizeof(*data) + data->len; + memunmap(data); + data = memremap(paddr, len, MEMREMAP_WB); + if (!data) + return -ENOMEM; + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } else { + /* + * Even though this is technically undefined, return + * the data as though it is a normal setup_data struct. + * This will at least allow it to be inspected. + */ + paddr += sizeof(*data); + len = data->len; + } } else { paddr += sizeof(*data); len = data->len; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a438217cbfac..d77481ecb0d5 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -462,19 +462,24 @@ 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)); + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && + !boot_cpu_has(X86_FEATURE_MWAIT) && + (num_possible_cpus() != 1)); } static bool pv_ipi_supported(void) { - return kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI); + return (kvm_para_has_feature(KVM_FEATURE_PV_SEND_IPI) && + (num_possible_cpus() != 1)); } 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)); + kvm_para_has_feature(KVM_FEATURE_STEAL_TIME) && + !boot_cpu_has(X86_FEATURE_MWAIT) && + (num_possible_cpus() != 1)); } #define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG) @@ -619,7 +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/kernel/module.c b/arch/x86/kernel/module.c index 95fa745e310a..96d7c27b7093 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -273,6 +273,14 @@ int module_finalize(const Elf_Ehdr *hdr, retpolines = s; } + /* + * See alternative_instructions() for the ordering rules between the + * various patching types. + */ + if (para) { + void *pseg = (void *)para->sh_addr; + apply_paravirt(pseg, pseg + para->sh_size); + } if (retpolines) { void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); @@ -290,11 +298,6 @@ int module_finalize(const Elf_Ehdr *hdr, tseg, tseg + text->sh_size); } - if (para) { - void *pseg = (void *)para->sh_addr; - apply_paravirt(pseg, pseg + para->sh_size); - } - /* make jump label nops */ jump_label_apply_nops(me); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f7a132eb794d..90d7e1788c91 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -369,21 +369,41 @@ static void __init parse_setup_data(void) static void __init memblock_x86_reserve_range_setup_data(void) { + struct setup_indirect *indirect; struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; + u32 len; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); + if (!data) { + pr_warn("setup: failed to memremap setup_data entry\n"); + return; + } + + len = sizeof(*data); + pa_next = data->next; + memblock_reserve(pa_data, sizeof(*data) + data->len); - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) - memblock_reserve(((struct setup_indirect *)data->data)->addr, - ((struct setup_indirect *)data->data)->len); + if (data->type == SETUP_INDIRECT) { + len += data->len; + early_memunmap(data, sizeof(*data)); + data = early_memremap(pa_data, len); + if (!data) { + pr_warn("setup: failed to memremap indirect setup_data\n"); + return; + } - pa_data = data->next; - early_memunmap(data, sizeof(*data)); + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) + memblock_reserve(indirect->addr, indirect->len); + } + + pa_data = pa_next; + early_memunmap(data, len); } } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c9d566dcf89a..8143693a7ea6 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -659,6 +659,7 @@ static bool do_int3(struct pt_regs *regs) return res == NOTIFY_STOP; } +NOKPROBE_SYMBOL(do_int3); static void do_int3_user(struct pt_regs *regs) { diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 494d4d351859..b8f8d268d058 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -282,6 +282,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; + u64 guest_supported_xcr0; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (best && apic) { @@ -293,9 +294,11 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - vcpu->arch.guest_supported_xcr0 = + guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); + vcpu->arch.guest_fpu.fpstate->user_xfeatures = guest_supported_xcr0; + kvm_update_pv_runtime(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 593093b52395..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) @@ -3889,12 +3889,23 @@ static void shadow_page_table_clear_flood(struct kvm_vcpu *vcpu, gva_t addr) walk_shadow_page_lockless_end(vcpu); } +static u32 alloc_apf_token(struct kvm_vcpu *vcpu) +{ + /* make sure the token value is not 0 */ + u32 id = vcpu->arch.apf.id; + + if (id << 12 == 0) + vcpu->arch.apf.id = 1; + + return (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; +} + static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, gfn_t gfn) { struct kvm_arch_async_pf arch; - arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id; + arch.token = alloc_apf_token(vcpu); arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->direct_map; arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 821edf664e7a..fd3a00c892c7 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2693,8 +2693,23 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) u64 data = msr->data; switch (ecx) { case MSR_AMD64_TSC_RATIO: - if (!msr->host_initiated && !svm->tsc_scaling_enabled) - return 1; + + if (!svm->tsc_scaling_enabled) { + + if (!msr->host_initiated) + return 1; + /* + * In case TSC scaling is not enabled, always + * leave this MSR at the default value. + * + * Due to bug in qemu 6.2.0, it would try to set + * this msr to 0 if tsc scaling is not enabled. + * Ignore this value as well. + */ + if (data != 0 && data != svm->tsc_ratio_msr) + return 1; + break; + } if (data & TSC_RATIO_RSVD) return 1; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index ba34e94049c7..dc822a1d403d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -246,8 +246,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, src = &prev->host_state; dest = &vmx->loaded_vmcs->host_state; - vmx_set_vmcs_host_state(dest, src->cr3, src->fs_sel, src->gs_sel, - src->fs_base, src->gs_base); + vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base); dest->ldt_sel = src->ldt_sel; #ifdef CONFIG_X86_64 dest->ds_sel = src->ds_sel; @@ -3056,7 +3055,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr4; + unsigned long cr3, cr4; bool vm_fail; if (!nested_early_check) @@ -3079,6 +3078,12 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) */ vmcs_writel(GUEST_RFLAGS, 0); + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->loaded_vmcs->host_state.cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index efda5e4d6247..b730d799c26e 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1080,14 +1080,9 @@ static void pt_guest_exit(struct vcpu_vmx *vmx) wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl); } -void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, - u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base) +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base) { - if (unlikely(cr3 != host->cr3)) { - vmcs_writel(HOST_CR3, cr3); - host->cr3 = cr3; - } if (unlikely(fs_sel != host->fs_sel)) { if (!(fs_sel & 7)) vmcs_write16(HOST_FS_SELECTOR, fs_sel); @@ -1182,9 +1177,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) gs_base = segment_base(gs_sel); #endif - vmx_set_vmcs_host_state(host_state, __get_current_cr3_fast(), - fs_sel, gs_sel, fs_base, gs_base); - + vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base); vmx->guest_state_loaded = true; } @@ -6791,7 +6784,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - unsigned long cr4; + unsigned long cr3, cr4; /* Record the guest's net vcpu time for enforced NMI injections. */ if (unlikely(!enable_vnmi && @@ -6834,6 +6827,19 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]); vcpu->arch.regs_dirty = 0; + /* + * Refresh vmcs.HOST_CR3 if necessary. This must be done immediately + * prior to VM-Enter, as the kernel may load a new ASID (PCID) any time + * it switches back to the current->mm, which can occur in KVM context + * when switching to a temporary mm to patch kernel code, e.g. if KVM + * toggles a static key while handling a VM-Exit. + */ + cr3 = __get_current_cr3_fast(); + if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) { + vmcs_writel(HOST_CR3, cr3); + vmx->loaded_vmcs->host_state.cr3 = cr3; + } + cr4 = cr4_read_shadow(); if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) { vmcs_writel(HOST_CR4, cr4); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f2c82e7f38f..9c6bfcd84008 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -374,9 +374,8 @@ int allocate_vpid(void); void free_vpid(int vpid); void vmx_set_constant_host_state(struct vcpu_vmx *vmx); void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu); -void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3, - u16 fs_sel, u16 gs_sel, - unsigned long fs_base, unsigned long gs_base); +void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel, + unsigned long fs_base, unsigned long gs_base); int vmx_get_cpl(struct kvm_vcpu *vcpu); bool vmx_emulation_required(struct kvm_vcpu *vcpu); unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6661207dd637..7bfcafc6e7ce 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -984,6 +984,18 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_load_host_xsave_state); +static inline u64 kvm_guest_supported_xcr0(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_fpu.fpstate->user_xfeatures; +} + +#ifdef CONFIG_X86_64 +static inline u64 kvm_guest_supported_xfd(struct kvm_vcpu *vcpu) +{ + return kvm_guest_supported_xcr0(vcpu) & XFEATURE_MASK_USER_DYNAMIC; +} +#endif + static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { u64 xcr0 = xcr; @@ -1003,7 +1015,7 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) * saving. However, xcr0 bit 0 is always set, even if the * emulated CPU does not support XSAVE (see kvm_vcpu_reset()). */ - valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP; + valid_bits = kvm_guest_supported_xcr0(vcpu) | XFEATURE_MASK_FP; if (xcr0 & ~valid_bits) return 1; @@ -2351,10 +2363,12 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) return tsc; } +#ifdef CONFIG_X86_64 static inline int gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } +#endif static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) { @@ -3706,8 +3720,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; fpu_update_guest_xfd(&vcpu->arch.guest_fpu, data); @@ -3717,8 +3730,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) return 1; - if (data & ~(XFEATURE_MASK_USER_DYNAMIC & - vcpu->arch.guest_supported_xcr0)) + if (data & ~kvm_guest_supported_xfd(vcpu)) return 1; vcpu->arch.guest_fpu.xfd_err = data; @@ -4233,6 +4245,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_EXIT_ON_EMULATION_FAILURE: case KVM_CAP_VCPU_ATTRIBUTES: case KVM_CAP_SYS_ATTRIBUTES: + case KVM_CAP_ENABLE_CAP: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -8942,6 +8955,13 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; + /* + * When tsc is in permanent catchup mode guests won't be able to use + * pvclock_read_retry loop to get consistent view of pvclock + */ + if (vcpu->arch.tsc_always_catchup) + return -KVM_EOPNOTSUPP; + if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; @@ -9160,6 +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; @@ -9168,16 +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; @@ -9795,6 +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. @@ -10173,6 +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; @@ -10232,12 +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 (;;) { @@ -10265,14 +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; } @@ -10378,6 +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); @@ -10385,6 +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; @@ -10395,7 +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; @@ -10455,8 +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/mm/ioremap.c b/arch/x86/mm/ioremap.c index 026031b3b782..17a492c27306 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -615,6 +615,7 @@ static bool memremap_is_efi_data(resource_size_t phys_addr, static bool memremap_is_setup_data(resource_size_t phys_addr, unsigned long size) { + struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; @@ -627,6 +628,10 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, data = memremap(paddr, sizeof(*data), MEMREMAP_WB | MEMREMAP_DEC); + if (!data) { + pr_warn("failed to memremap setup_data entry\n"); + return false; + } paddr_next = data->next; len = data->len; @@ -636,10 +641,21 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, return true; } - if (data->type == SETUP_INDIRECT && - ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) { - paddr = ((struct setup_indirect *)data->data)->addr; - len = ((struct setup_indirect *)data->data)->len; + if (data->type == SETUP_INDIRECT) { + memunmap(data); + data = memremap(paddr, sizeof(*data) + len, + MEMREMAP_WB | MEMREMAP_DEC); + if (!data) { + pr_warn("failed to memremap indirect setup_data\n"); + return false; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } } memunmap(data); @@ -660,22 +676,51 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, unsigned long size) { + struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; paddr = boot_params.hdr.setup_data; while (paddr) { - unsigned int len; + unsigned int len, size; if (phys_addr == paddr) return true; data = early_memremap_decrypted(paddr, sizeof(*data)); + if (!data) { + pr_warn("failed to early memremap setup_data entry\n"); + return false; + } + + size = sizeof(*data); paddr_next = data->next; len = data->len; - early_memunmap(data, sizeof(*data)); + if ((phys_addr > paddr) && (phys_addr < (paddr + len))) { + early_memunmap(data, sizeof(*data)); + return true; + } + + if (data->type == SETUP_INDIRECT) { + size += len; + early_memunmap(data, sizeof(*data)); + data = early_memremap_decrypted(paddr, size); + if (!data) { + pr_warn("failed to early memremap indirect setup_data\n"); + return false; + } + + indirect = (struct setup_indirect *)data->data; + + if (indirect->type != SETUP_INDIRECT) { + paddr = indirect->addr; + len = indirect->len; + } + } + + early_memunmap(data, size); if ((phys_addr > paddr) && (phys_addr < (paddr + len))) return true; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 2b1e266ff95c..0ecb140864b2 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -394,7 +394,7 @@ 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/block/fops.c b/block/fops.c index 4f59e0f5bf30..a18e7fbd97b8 100644 --- a/block/fops.c +++ b/block/fops.c @@ -289,6 +289,8 @@ static void blkdev_bio_end_io_async(struct bio *bio) struct kiocb *iocb = dio->iocb; ssize_t ret; + WRITE_ONCE(iocb->private, NULL); + if (likely(!bio->bi_status)) { ret = dio->size; iocb->ki_pos += ret; diff --git a/drivers/ata/pata_hpt37x.c b/drivers/ata/pata_hpt37x.c index 7abc7e04f656..6fa4a2faf49c 100644 --- a/drivers/ata/pata_hpt37x.c +++ b/drivers/ata/pata_hpt37x.c @@ -920,6 +920,20 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id) pci_write_config_byte(dev, 0x5a, irqmask); /* + * HPT371 chips physically have only one channel, the secondary one, + * but the primary channel registers do exist! Go figure... + * So, we manually disable the non-existing channel here + * (if the BIOS hasn't done this already). + */ + if (dev->device == PCI_DEVICE_ID_TTI_HPT371) { + u8 mcr1; + + pci_read_config_byte(dev, 0x50, &mcr1); + mcr1 &= ~0x04; + pci_write_config_byte(dev, 0x50, mcr1); + } + + /* * default to pci clock. make sure MA15/16 are set to output * to prevent drives having problems with 40-pin cables. Needed * for some drives such as IBM-DTLA which will not enter ready @@ -950,14 +964,14 @@ static int hpt37x_init_one(struct pci_dev *dev, const struct pci_device_id *id) if ((freq >> 12) != 0xABCDE) { int i; - u8 sr; + u16 sr; u32 total = 0; dev_warn(&dev->dev, "BIOS has not set timing clocks\n"); /* This is the process the HPT371 BIOS is reported to use */ for (i = 0; i < 128; i++) { - pci_read_config_byte(dev, 0x78, &sr); + pci_read_config_word(dev, 0x78, &sr); total += sr & 0x1FF; udelay(15); } diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c index 3bc3c314a467..4f67404fe64c 100644 --- a/drivers/atm/firestream.c +++ b/drivers/atm/firestream.c @@ -1676,6 +1676,8 @@ static int fs_init(struct fs_dev *dev) dev->hw_base = pci_resource_start(pci_dev, 0); dev->base = ioremap(dev->hw_base, 0x1000); + if (!dev->base) + return 1; reset_chip (dev); diff --git a/drivers/auxdisplay/lcd2s.c b/drivers/auxdisplay/lcd2s.c index 38ba08628ccb..2578b2d45439 100644 --- a/drivers/auxdisplay/lcd2s.c +++ b/drivers/auxdisplay/lcd2s.c @@ -238,7 +238,7 @@ static int lcd2s_redefine_char(struct charlcd *lcd, char *esc) if (buf[1] > 7) return 1; - i = 0; + i = 2; shift = 0; value = 0; while (*esc && i < LCD2S_CHARACTER_SIZE + 2) { @@ -298,6 +298,10 @@ static int lcd2s_i2c_probe(struct i2c_client *i2c, I2C_FUNC_SMBUS_WRITE_BLOCK_DATA)) return -EIO; + lcd2s = devm_kzalloc(&i2c->dev, sizeof(*lcd2s), GFP_KERNEL); + if (!lcd2s) + return -ENOMEM; + /* Test, if the display is responding */ err = lcd2s_i2c_smbus_write_byte(i2c, LCD2S_CMD_DISPLAY_OFF); if (err < 0) @@ -307,12 +311,6 @@ static int lcd2s_i2c_probe(struct i2c_client *i2c, if (!lcd) return -ENOMEM; - lcd2s = kzalloc(sizeof(struct lcd2s_data), GFP_KERNEL); - if (!lcd2s) { - err = -ENOMEM; - goto fail1; - } - lcd->drvdata = lcd2s; lcd2s->i2c = i2c; lcd2s->charlcd = lcd; @@ -321,26 +319,24 @@ static int lcd2s_i2c_probe(struct i2c_client *i2c, err = device_property_read_u32(&i2c->dev, "display-height-chars", &lcd->height); if (err) - goto fail2; + goto fail1; err = device_property_read_u32(&i2c->dev, "display-width-chars", &lcd->width); if (err) - goto fail2; + goto fail1; lcd->ops = &lcd2s_ops; err = charlcd_register(lcd2s->charlcd); if (err) - goto fail2; + goto fail1; i2c_set_clientdata(i2c, lcd2s); return 0; -fail2: - kfree(lcd2s); fail1: - kfree(lcd); + charlcd_free(lcd2s->charlcd); return err; } @@ -349,7 +345,7 @@ static int lcd2s_i2c_remove(struct i2c_client *i2c) struct lcd2s_data *lcd2s = i2c_get_clientdata(i2c); charlcd_unregister(lcd2s->charlcd); - kfree(lcd2s->charlcd); + charlcd_free(lcd2s->charlcd); return 0; } diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 9eaaff2f556c..f47cab21430f 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -629,6 +629,9 @@ re_probe: drv->remove(dev); devres_release_all(dev); + arch_teardown_dma_ops(dev); + kfree(dev->dma_range_map); + dev->dma_range_map = NULL; driver_sysfs_remove(dev); dev->driver = NULL; dev_set_drvdata(dev, NULL); @@ -1209,6 +1212,8 @@ static void __device_release_driver(struct device *dev, struct device *parent) devres_release_all(dev); arch_teardown_dma_ops(dev); + kfree(dev->dma_range_map); + dev->dma_range_map = NULL; dev->driver = NULL; dev_set_drvdata(dev, NULL); if (dev->pm_domain && dev->pm_domain->dismiss) diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index d2656581a608..4a446259a184 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -189,11 +189,9 @@ static void regmap_irq_sync_unlock(struct irq_data *data) ret = regmap_write(map, reg, d->mask_buf[i]); if (d->chip->clear_ack) { if (d->chip->ack_invert && !ret) - ret = regmap_write(map, reg, - d->mask_buf[i]); + ret = regmap_write(map, reg, UINT_MAX); else if (!ret) - ret = regmap_write(map, reg, - ~d->mask_buf[i]); + ret = regmap_write(map, reg, 0); } if (ret != 0) dev_err(d->map->dev, "Failed to ack 0x%x: %d\n", @@ -556,11 +554,9 @@ static irqreturn_t regmap_irq_thread(int irq, void *d) data->status_buf[i]); if (chip->clear_ack) { if (chip->ack_invert && !ret) - ret = regmap_write(map, reg, - data->status_buf[i]); + ret = regmap_write(map, reg, UINT_MAX); else if (!ret) - ret = regmap_write(map, reg, - ~data->status_buf[i]); + ret = regmap_write(map, reg, 0); } if (ret != 0) dev_err(map->dev, "Failed to ack 0x%x: %d\n", @@ -817,13 +813,9 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, d->status_buf[i] & d->mask_buf[i]); if (chip->clear_ack) { if (chip->ack_invert && !ret) - ret = regmap_write(map, reg, - (d->status_buf[i] & - d->mask_buf[i])); + ret = regmap_write(map, reg, UINT_MAX); else if (!ret) - ret = regmap_write(map, reg, - ~(d->status_buf[i] & - d->mask_buf[i])); + ret = regmap_write(map, reg, 0); } if (ret != 0) { dev_err(map->dev, "Failed to ack 0x%x: %d\n", 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/ingenic/jz4725b-cgu.c b/drivers/clk/ingenic/jz4725b-cgu.c index 744d136b721b..15d61793f53b 100644 --- a/drivers/clk/ingenic/jz4725b-cgu.c +++ b/drivers/clk/ingenic/jz4725b-cgu.c @@ -139,11 +139,10 @@ static const struct ingenic_cgu_clk_info jz4725b_cgu_clocks[] = { }, [JZ4725B_CLK_I2S] = { - "i2s", CGU_CLK_MUX | CGU_CLK_DIV | CGU_CLK_GATE, + "i2s", CGU_CLK_MUX | CGU_CLK_DIV, .parents = { JZ4725B_CLK_EXT, JZ4725B_CLK_PLL_HALF, -1, -1 }, .mux = { CGU_REG_CPCCR, 31, 1 }, .div = { CGU_REG_I2SCDR, 0, 1, 9, -1, -1, -1 }, - .gate = { CGU_REG_CLKGR, 6 }, }, [JZ4725B_CLK_SPI] = { 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/gcc-msm8994.c b/drivers/clk/qcom/gcc-msm8994.c index 71aa630fa4bd..f09499999eb3 100644 --- a/drivers/clk/qcom/gcc-msm8994.c +++ b/drivers/clk/qcom/gcc-msm8994.c @@ -108,42 +108,6 @@ static const struct clk_parent_data gcc_xo_gpll0_gpll4[] = { { .hw = &gpll4.clkr.hw }, }; -static struct clk_rcg2 system_noc_clk_src = { - .cmd_rcgr = 0x0120, - .hid_width = 5, - .parent_map = gcc_xo_gpll0_map, - .clkr.hw.init = &(struct clk_init_data){ - .name = "system_noc_clk_src", - .parent_data = gcc_xo_gpll0, - .num_parents = ARRAY_SIZE(gcc_xo_gpll0), - .ops = &clk_rcg2_ops, - }, -}; - -static struct clk_rcg2 config_noc_clk_src = { - .cmd_rcgr = 0x0150, - .hid_width = 5, - .parent_map = gcc_xo_gpll0_map, - .clkr.hw.init = &(struct clk_init_data){ - .name = "config_noc_clk_src", - .parent_data = gcc_xo_gpll0, - .num_parents = ARRAY_SIZE(gcc_xo_gpll0), - .ops = &clk_rcg2_ops, - }, -}; - -static struct clk_rcg2 periph_noc_clk_src = { - .cmd_rcgr = 0x0190, - .hid_width = 5, - .parent_map = gcc_xo_gpll0_map, - .clkr.hw.init = &(struct clk_init_data){ - .name = "periph_noc_clk_src", - .parent_data = gcc_xo_gpll0, - .num_parents = ARRAY_SIZE(gcc_xo_gpll0), - .ops = &clk_rcg2_ops, - }, -}; - static struct freq_tbl ftbl_ufs_axi_clk_src[] = { F(50000000, P_GPLL0, 12, 0, 0), F(100000000, P_GPLL0, 6, 0, 0), @@ -1150,8 +1114,6 @@ static struct clk_branch gcc_blsp1_ahb_clk = { .enable_mask = BIT(17), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp1_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -1435,8 +1397,6 @@ static struct clk_branch gcc_blsp2_ahb_clk = { .enable_mask = BIT(15), .hw.init = &(struct clk_init_data){ .name = "gcc_blsp2_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -1764,8 +1724,6 @@ static struct clk_branch gcc_lpass_q6_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_lpass_q6_axi_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -1778,8 +1736,6 @@ static struct clk_branch gcc_mss_q6_bimc_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_mss_q6_bimc_axi_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -1807,9 +1763,6 @@ static struct clk_branch gcc_pcie_0_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_0_cfg_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &config_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1822,9 +1775,6 @@ static struct clk_branch gcc_pcie_0_mstr_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_0_mstr_axi_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1854,9 +1804,6 @@ static struct clk_branch gcc_pcie_0_slv_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_0_slv_axi_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1884,9 +1831,6 @@ static struct clk_branch gcc_pcie_1_cfg_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_1_cfg_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &config_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1899,9 +1843,6 @@ static struct clk_branch gcc_pcie_1_mstr_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_1_mstr_axi_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1930,9 +1871,6 @@ static struct clk_branch gcc_pcie_1_slv_axi_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pcie_1_slv_axi_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1960,8 +1898,6 @@ static struct clk_branch gcc_pdm_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_pdm_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -1989,9 +1925,6 @@ static struct clk_branch gcc_sdcc1_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc1_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2004,9 +1937,6 @@ static struct clk_branch gcc_sdcc2_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc2_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2034,9 +1964,6 @@ static struct clk_branch gcc_sdcc3_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc3_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2064,9 +1991,6 @@ static struct clk_branch gcc_sdcc4_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_sdcc4_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, - .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -2124,8 +2048,6 @@ static struct clk_branch gcc_tsif_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_tsif_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -2153,8 +2075,6 @@ static struct clk_branch gcc_ufs_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_ufs_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &config_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -2198,8 +2118,6 @@ static struct clk_branch gcc_ufs_rx_symbol_0_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_ufs_rx_symbol_0_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -2213,8 +2131,6 @@ static struct clk_branch gcc_ufs_rx_symbol_1_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_ufs_rx_symbol_1_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -2243,8 +2159,6 @@ static struct clk_branch gcc_ufs_tx_symbol_0_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_ufs_tx_symbol_0_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -2258,8 +2172,6 @@ static struct clk_branch gcc_ufs_tx_symbol_1_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_ufs_tx_symbol_1_clk", - .parent_hws = (const struct clk_hw *[]){ &system_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -2364,8 +2276,6 @@ static struct clk_branch gcc_usb_hs_ahb_clk = { .enable_mask = BIT(0), .hw.init = &(struct clk_init_data){ .name = "gcc_usb_hs_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -2488,8 +2398,6 @@ static struct clk_branch gcc_boot_rom_ahb_clk = { .enable_mask = BIT(10), .hw.init = &(struct clk_init_data){ .name = "gcc_boot_rom_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &config_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -2503,8 +2411,6 @@ static struct clk_branch gcc_prng_ahb_clk = { .enable_mask = BIT(13), .hw.init = &(struct clk_init_data){ .name = "gcc_prng_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ &periph_noc_clk_src.clkr.hw }, - .num_parents = 1, .ops = &clk_branch2_ops, }, }, @@ -2547,9 +2453,6 @@ static struct clk_regmap *gcc_msm8994_clocks[] = { [GPLL0] = &gpll0.clkr, [GPLL4_EARLY] = &gpll4_early.clkr, [GPLL4] = &gpll4.clkr, - [CONFIG_NOC_CLK_SRC] = &config_noc_clk_src.clkr, - [PERIPH_NOC_CLK_SRC] = &periph_noc_clk_src.clkr, - [SYSTEM_NOC_CLK_SRC] = &system_noc_clk_src.clkr, [UFS_AXI_CLK_SRC] = &ufs_axi_clk_src.clkr, [USB30_MASTER_CLK_SRC] = &usb30_master_clk_src.clkr, [BLSP1_QUP1_I2C_APPS_CLK_SRC] = &blsp1_qup1_i2c_apps_clk_src.clkr, @@ -2696,6 +2599,15 @@ static struct clk_regmap *gcc_msm8994_clocks[] = { [USB_SS_PHY_LDO] = &usb_ss_phy_ldo.clkr, [GCC_BOOT_ROM_AHB_CLK] = &gcc_boot_rom_ahb_clk.clkr, [GCC_PRNG_AHB_CLK] = &gcc_prng_ahb_clk.clkr, + + /* + * The following clocks should NOT be managed by this driver, but they once were + * mistakengly added. Now they are only here to indicate that they are not defined + * on purpose, even though the names will stay in the header file (for ABI sanity). + */ + [CONFIG_NOC_CLK_SRC] = NULL, + [PERIPH_NOC_CLK_SRC] = NULL, + [SYSTEM_NOC_CLK_SRC] = NULL, }; static struct gdsc *gcc_msm8994_gdscs[] = { 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/clocksource/timer-ti-dm-systimer.c b/drivers/clocksource/timer-ti-dm-systimer.c index 5c40ca1d4740..1fccb457fcc5 100644 --- a/drivers/clocksource/timer-ti-dm-systimer.c +++ b/drivers/clocksource/timer-ti-dm-systimer.c @@ -241,8 +241,7 @@ static void __init dmtimer_systimer_assign_alwon(void) bool quirk_unreliable_oscillator = false; /* Quirk unreliable 32 KiHz oscillator with incomplete dts */ - if (of_machine_is_compatible("ti,omap3-beagle-ab4") || - of_machine_is_compatible("timll,omap3-devkit8000")) { + if (of_machine_is_compatible("ti,omap3-beagle-ab4")) { quirk_unreliable_oscillator = true; counter_32k = -ENODEV; } diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index b8d95536ee22..80f535cc8a75 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -1518,6 +1518,10 @@ static int cpufreq_online(unsigned int cpu) kobject_uevent(&policy->kobj, KOBJ_ADD); + /* Callback for handling stuff after policy is ready */ + if (cpufreq_driver->ready) + cpufreq_driver->ready(policy); + if (cpufreq_thermal_control_enabled(cpufreq_driver)) policy->cdev = of_cpufreq_cooling_register(policy); diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 05f3d7876e44..effbb680b453 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -388,7 +388,7 @@ static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index) snprintf(data->irq_name, sizeof(data->irq_name), "dcvsh-irq-%u", policy->cpu); ret = request_threaded_irq(data->throttle_irq, NULL, qcom_lmh_dcvs_handle_irq, - IRQF_ONESHOT, data->irq_name, data); + IRQF_ONESHOT | IRQF_NO_AUTOEN, data->irq_name, data); if (ret) { dev_err(&pdev->dev, "Error registering %s: %d\n", data->irq_name, ret); return 0; @@ -542,6 +542,14 @@ static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) return 0; } +static void qcom_cpufreq_ready(struct cpufreq_policy *policy) +{ + struct qcom_cpufreq_data *data = policy->driver_data; + + if (data->throttle_irq >= 0) + enable_irq(data->throttle_irq); +} + static struct freq_attr *qcom_cpufreq_hw_attr[] = { &cpufreq_freq_attr_scaling_available_freqs, &cpufreq_freq_attr_scaling_boost_freqs, @@ -561,6 +569,7 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = { .fast_switch = qcom_cpufreq_hw_fast_switch, .name = "qcom-cpufreq-hw", .attr = qcom_cpufreq_hw_attr, + .ready = qcom_cpufreq_ready, }; static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index b406b3f78f46..d76bab3aaac4 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2112,7 +2112,7 @@ static void __exit scmi_driver_exit(void) } module_exit(scmi_driver_exit); -MODULE_ALIAS("platform: arm-scmi"); +MODULE_ALIAS("platform:arm-scmi"); MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>"); MODULE_DESCRIPTION("ARM SCMI protocol driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/firmware/efi/libstub/riscv-stub.c b/drivers/firmware/efi/libstub/riscv-stub.c index 380e4e251399..9c460843442f 100644 --- a/drivers/firmware/efi/libstub/riscv-stub.c +++ b/drivers/firmware/efi/libstub/riscv-stub.c @@ -25,7 +25,7 @@ typedef void __noreturn (*jump_kernel_func)(unsigned int, unsigned long); static u32 hartid; -static u32 get_boot_hartid_from_fdt(void) +static int get_boot_hartid_from_fdt(void) { const void *fdt; int chosen_node, len; @@ -33,23 +33,26 @@ static u32 get_boot_hartid_from_fdt(void) fdt = get_efi_config_table(DEVICE_TREE_GUID); if (!fdt) - return U32_MAX; + return -EINVAL; chosen_node = fdt_path_offset(fdt, "/chosen"); if (chosen_node < 0) - return U32_MAX; + return -EINVAL; prop = fdt_getprop((void *)fdt, chosen_node, "boot-hartid", &len); if (!prop || len != sizeof(u32)) - return U32_MAX; + return -EINVAL; - return fdt32_to_cpu(*prop); + hartid = fdt32_to_cpu(*prop); + return 0; } efi_status_t check_platform_features(void) { - hartid = get_boot_hartid_from_fdt(); - if (hartid == U32_MAX) { + int ret; + + ret = get_boot_hartid_from_fdt(); + if (ret) { efi_err("/chosen/boot-hartid missing or invalid!\n"); return EFI_UNSUPPORTED; } diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index abdc8a6a3963..cae590bd08f2 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -742,6 +742,7 @@ int efivar_entry_set_safe(efi_char16_t *name, efi_guid_t vendor, u32 attributes, { const struct efivar_operations *ops; efi_status_t status; + unsigned long varsize; if (!__efivars) return -EINVAL; @@ -764,15 +765,17 @@ int efivar_entry_set_safe(efi_char16_t *name, efi_guid_t vendor, u32 attributes, return efivar_entry_set_nonblocking(name, vendor, attributes, size, data); + varsize = size + ucs2_strsize(name, 1024); if (!block) { if (down_trylock(&efivars_lock)) return -EBUSY; + status = check_var_size_nonblocking(attributes, varsize); } else { if (down_interruptible(&efivars_lock)) return -EINTR; + status = check_var_size(attributes, varsize); } - status = check_var_size(attributes, size + ucs2_strsize(name, 1024)); if (status != EFI_SUCCESS) { up(&efivars_lock); return -ENOSPC; diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index a4c4e4584f5b..099e358d2491 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -410,10 +410,8 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type) level = rockchip_gpio_readl(bank, bank->gpio_regs->int_type); polarity = rockchip_gpio_readl(bank, bank->gpio_regs->int_polarity); - switch (type) { - case IRQ_TYPE_EDGE_BOTH: + if (type == IRQ_TYPE_EDGE_BOTH) { if (bank->gpio_type == GPIO_TYPE_V2) { - bank->toggle_edge_mode &= ~mask; rockchip_gpio_writel_bit(bank, d->hwirq, 1, bank->gpio_regs->int_bothedge); goto out; @@ -431,30 +429,34 @@ static int rockchip_irq_set_type(struct irq_data *d, unsigned int type) else polarity |= mask; } - break; - case IRQ_TYPE_EDGE_RISING: - bank->toggle_edge_mode &= ~mask; - level |= mask; - polarity |= mask; - break; - case IRQ_TYPE_EDGE_FALLING: - bank->toggle_edge_mode &= ~mask; - level |= mask; - polarity &= ~mask; - break; - case IRQ_TYPE_LEVEL_HIGH: - bank->toggle_edge_mode &= ~mask; - level &= ~mask; - polarity |= mask; - break; - case IRQ_TYPE_LEVEL_LOW: - bank->toggle_edge_mode &= ~mask; - level &= ~mask; - polarity &= ~mask; - break; - default: - ret = -EINVAL; - goto out; + } else { + if (bank->gpio_type == GPIO_TYPE_V2) { + rockchip_gpio_writel_bit(bank, d->hwirq, 0, + bank->gpio_regs->int_bothedge); + } else { + bank->toggle_edge_mode &= ~mask; + } + switch (type) { + case IRQ_TYPE_EDGE_RISING: + level |= mask; + polarity |= mask; + break; + case IRQ_TYPE_EDGE_FALLING: + level |= mask; + polarity &= ~mask; + break; + case IRQ_TYPE_LEVEL_HIGH: + level &= ~mask; + polarity |= mask; + break; + case IRQ_TYPE_LEVEL_LOW: + level &= ~mask; + polarity &= ~mask; + break; + default: + ret = -EINVAL; + goto out; + } } rockchip_gpio_writel(bank, level, bank->gpio_regs->int_type); 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 34b36a8c035f..031fe105b58e 100644 --- a/drivers/gpio/gpio-tegra186.c +++ b/drivers/gpio/gpio-tegra186.c @@ -343,9 +343,12 @@ static int tegra186_gpio_of_xlate(struct gpio_chip *chip, return offset + pin; } +#define to_tegra_gpio(x) container_of((x), struct tegra_gpio, gpio) + static void tegra186_irq_ack(struct irq_data *data) { - struct tegra_gpio *gpio = irq_data_get_irq_chip_data(data); + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct tegra_gpio *gpio = to_tegra_gpio(gc); void __iomem *base; base = tegra186_gpio_get_base(gpio, data->hwirq); @@ -357,7 +360,8 @@ static void tegra186_irq_ack(struct irq_data *data) static void tegra186_irq_mask(struct irq_data *data) { - struct tegra_gpio *gpio = irq_data_get_irq_chip_data(data); + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct tegra_gpio *gpio = to_tegra_gpio(gc); void __iomem *base; u32 value; @@ -372,7 +376,8 @@ static void tegra186_irq_mask(struct irq_data *data) static void tegra186_irq_unmask(struct irq_data *data) { - struct tegra_gpio *gpio = irq_data_get_irq_chip_data(data); + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct tegra_gpio *gpio = to_tegra_gpio(gc); void __iomem *base; u32 value; @@ -387,7 +392,8 @@ static void tegra186_irq_unmask(struct irq_data *data) static int tegra186_irq_set_type(struct irq_data *data, unsigned int type) { - struct tegra_gpio *gpio = irq_data_get_irq_chip_data(data); + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + struct tegra_gpio *gpio = to_tegra_gpio(gc); void __iomem *base; u32 value; @@ -1069,6 +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) \ @@ -1089,6 +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 3859911b61e9..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, @@ -3147,6 +3147,16 @@ int gpiod_to_irq(const struct gpio_desc *desc) return retirq; } +#ifdef CONFIG_GPIOLIB_IRQCHIP + if (gc->irq.chip) { + /* + * Avoid race condition with other code, which tries to lookup + * an IRQ before the irqchip has been properly registered, + * i.e. while gpiochip is still being brought up. + */ + return -EPROBE_DEFER; + } +#endif return -ENXIO; } EXPORT_SYMBOL_GPL(gpiod_to_irq); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 82011e75ed85..c4387b38229c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1141,7 +1141,7 @@ int amdgpu_display_framebuffer_init(struct drm_device *dev, if (ret) return ret; - if (!dev->mode_config.allow_fb_modifiers) { + if (!dev->mode_config.allow_fb_modifiers && !adev->enable_virtual_display) { drm_WARN_ONCE(dev, adev->family >= AMDGPU_FAMILY_AI, "GFX9+ requires FB check based on format modifier\n"); ret = check_tiling_flags_gfx6(rfb); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 63a089992645..0ead08ba58c2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2011,6 +2011,9 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, return -ENODEV; } + if (amdgpu_aspm == -1 && !pcie_aspm_enabled(pdev)) + amdgpu_aspm = 0; + if (amdgpu_virtual_display || amdgpu_device_asic_has_dc_support(flags & AMD_ASIC_MASK)) supports_atomic = true; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c index d99c8779b51e..5224d9a39737 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c @@ -391,7 +391,6 @@ static struct drm_plane *amdgpu_vkms_plane_init(struct drm_device *dev, int index) { struct drm_plane *plane; - uint64_t modifiers[] = {DRM_FORMAT_MOD_LINEAR, DRM_FORMAT_MOD_INVALID}; int ret; plane = kzalloc(sizeof(*plane), GFP_KERNEL); @@ -402,7 +401,7 @@ static struct drm_plane *amdgpu_vkms_plane_init(struct drm_device *dev, &amdgpu_vkms_plane_funcs, amdgpu_vkms_formats, ARRAY_SIZE(amdgpu_vkms_formats), - modifiers, type, NULL); + NULL, type, NULL); if (ret) { kfree(plane); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index b37fc7d7d2c7..418341a67517 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -768,11 +768,17 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm, * Check if all VM PDs/PTs are ready for updates * * Returns: - * True if eviction list is empty. + * True if VM is not evicting. */ bool amdgpu_vm_ready(struct amdgpu_vm *vm) { - return list_empty(&vm->evicted); + bool ret; + + amdgpu_vm_eviction_lock(vm); + ret = !vm->evicting; + amdgpu_vm_eviction_unlock(vm); + + return ret && list_empty(&vm->evicted); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 0fc1747e4a70..12f80fdc1fbc 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -619,8 +619,8 @@ soc15_asic_reset_method(struct amdgpu_device *adev) static int soc15_asic_reset(struct amdgpu_device *adev) { /* original raven doesn't have full asic reset */ - if ((adev->apu_flags & AMD_APU_IS_RAVEN) && - !(adev->apu_flags & AMD_APU_IS_RAVEN2)) + if ((adev->apu_flags & AMD_APU_IS_RAVEN) || + (adev->apu_flags & AMD_APU_IS_RAVEN2)) return 0; switch (soc15_asic_reset_method(adev)) { @@ -1114,8 +1114,11 @@ static int soc15_common_early_init(void *handle) AMD_CG_SUPPORT_SDMA_LS | AMD_CG_SUPPORT_VCN_MGCG; + /* + * MMHUB PG needs to be disabled for Picasso for + * stability reasons. + */ adev->pg_flags = AMD_PG_SUPPORT_SDMA | - AMD_PG_SUPPORT_MMHUB | AMD_PG_SUPPORT_VCN; } else { adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 7c1c623ba799..075429bea427 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4256,6 +4256,9 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) } #endif + /* Disable vblank IRQs aggressively for power-saving. */ + adev_to_drm(adev)->vblank_disable_immediate = true; + /* loops over all connectors on the board */ for (i = 0; i < link_cnt; i++) { struct dc_link *link = NULL; @@ -4301,19 +4304,17 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) update_connector_ext_caps(aconnector); if (psr_feature_enabled) amdgpu_dm_set_psr_caps(link); + + /* TODO: Fix vblank control helpers to delay PSR entry to allow this when + * PSR is also supported. + */ + if (link->psr_settings.psr_feature_enabled) + adev_to_drm(adev)->vblank_disable_immediate = false; } } - /* - * Disable vblank IRQs aggressively for power-saving. - * - * TODO: Fix vblank control helpers to delay PSR entry to allow this when PSR - * is also supported. - */ - adev_to_drm(adev)->vblank_disable_immediate = !psr_feature_enabled; - /* Software is initialized. Now we can register interrupt handlers. */ switch (adev->asic_type) { #if defined(CONFIG_DRM_AMD_DC_SI) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c index f977f29907df..10c7be40dfb0 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c @@ -473,8 +473,10 @@ static void dcn3_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base) clk_mgr_base->bw_params->dc_mode_softmax_memclk = dcn30_smu_get_dc_mode_max_dpm_freq(clk_mgr, PPCLK_UCLK); /* Refresh bounding box */ + DC_FP_START(); clk_mgr_base->ctx->dc->res_pool->funcs->update_bw_bounding_box( clk_mgr->base.ctx->dc, clk_mgr_base->bw_params); + DC_FP_END(); } static bool dcn3_is_smu_present(struct clk_mgr *clk_mgr_base) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index d18e9f3ea998..ba1aa994db4b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -985,10 +985,13 @@ static bool dc_construct(struct dc *dc, goto fail; #ifdef CONFIG_DRM_AMD_DC_DCN dc->clk_mgr->force_smu_not_present = init_params->force_smu_not_present; -#endif - if (dc->res_pool->funcs->update_bw_bounding_box) + if (dc->res_pool->funcs->update_bw_bounding_box) { + DC_FP_START(); dc->res_pool->funcs->update_bw_bounding_box(dc, dc->clk_mgr->bw_params); + DC_FP_END(); + } +#endif /* Creation of current_state must occur after dc->dml * is initialized in dc_create_resource_pool because diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index b3912ff9dc91..18757c158523 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1964,10 +1964,6 @@ enum dc_status dc_remove_stream_from_ctx( dc->res_pool, del_pipe->stream_res.stream_enc, false); - /* Release link encoder from stream in new dc_state. */ - if (dc->res_pool->funcs->link_enc_unassign) - dc->res_pool->funcs->link_enc_unassign(new_ctx, del_pipe->stream); - #if defined(CONFIG_DRM_AMD_DC_DCN) if (is_dp_128b_132b_signal(del_pipe)) { update_hpo_dp_stream_engine_usage( diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 2320bd750876..5488a0edb942 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -421,6 +421,36 @@ static int sienna_cichlid_store_powerplay_table(struct smu_context *smu) return 0; } +static int sienna_cichlid_patch_pptable_quirk(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + uint32_t *board_reserved; + uint16_t *freq_table_gfx; + uint32_t i; + + /* Fix some OEM SKU specific stability issues */ + GET_PPTABLE_MEMBER(BoardReserved, &board_reserved); + if ((adev->pdev->device == 0x73DF) && + (adev->pdev->revision == 0XC3) && + (adev->pdev->subsystem_device == 0x16C2) && + (adev->pdev->subsystem_vendor == 0x1043)) + board_reserved[0] = 1387; + + GET_PPTABLE_MEMBER(FreqTableGfx, &freq_table_gfx); + if ((adev->pdev->device == 0x73DF) && + (adev->pdev->revision == 0XC3) && + ((adev->pdev->subsystem_device == 0x16C2) || + (adev->pdev->subsystem_device == 0x133C)) && + (adev->pdev->subsystem_vendor == 0x1043)) { + for (i = 0; i < NUM_GFXCLK_DPM_LEVELS; i++) { + if (freq_table_gfx[i] > 2500) + freq_table_gfx[i] = 2500; + } + } + + return 0; +} + static int sienna_cichlid_setup_pptable(struct smu_context *smu) { int ret = 0; @@ -441,7 +471,7 @@ static int sienna_cichlid_setup_pptable(struct smu_context *smu) if (ret) return ret; - return ret; + return sienna_cichlid_patch_pptable_quirk(smu); } static int sienna_cichlid_tables_init(struct smu_context *smu) 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/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 12893e7be89b..f5f5de362ff2 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -5345,6 +5345,7 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi if (!(edid->input & DRM_EDID_INPUT_DIGITAL)) return quirks; + info->color_formats |= DRM_COLOR_FORMAT_RGB444; drm_parse_cea_ext(connector, edid); /* @@ -5393,7 +5394,6 @@ u32 drm_add_display_info(struct drm_connector *connector, const struct edid *edi DRM_DEBUG("%s: Assigning EDID-1.4 digital sink color depth as %d bpc.\n", connector->name, info->bpc); - info->color_formats |= DRM_COLOR_FORMAT_RGB444; if (edid->features & DRM_EDID_FEATURE_RGB_YCRCB444) info->color_formats |= DRM_COLOR_FORMAT_YCRCB444; if (edid->features & DRM_EDID_FEATURE_RGB_YCRCB422) 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/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 2da4aacc956b..8ac196e814d5 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -825,6 +825,7 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) unsigned int max_bw_point = 0, max_bw = 0; unsigned int num_qgv_points = dev_priv->max_bw[0].num_qgv_points; unsigned int num_psf_gv_points = dev_priv->max_bw[0].num_psf_gv_points; + bool changed = false; u32 mask = 0; /* FIXME earlier gens need some checks too */ @@ -868,6 +869,8 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) new_bw_state->data_rate[crtc->pipe] = new_data_rate; new_bw_state->num_active_planes[crtc->pipe] = new_active_planes; + changed = true; + drm_dbg_kms(&dev_priv->drm, "pipe %c data rate %u num active planes %u\n", pipe_name(crtc->pipe), @@ -875,7 +878,19 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) new_bw_state->num_active_planes[crtc->pipe]); } - if (!new_bw_state) + old_bw_state = intel_atomic_get_old_bw_state(state); + new_bw_state = intel_atomic_get_new_bw_state(state); + + if (new_bw_state && + intel_can_enable_sagv(dev_priv, old_bw_state) != + intel_can_enable_sagv(dev_priv, new_bw_state)) + changed = true; + + /* + * If none of our inputs (data rates, number of active + * planes, SAGV yes/no) changed then nothing to do here. + */ + if (!changed) return 0; ret = intel_atomic_lock_global_state(&new_bw_state->base); @@ -961,7 +976,6 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) */ new_bw_state->qgv_points_mask = ~allowed_points & mask; - old_bw_state = intel_atomic_get_old_bw_state(state); /* * If the actual mask had changed we need to make sure that * the commits are serialized(in case this is a nomodeset, nonblocking) diff --git a/drivers/gpu/drm/i915/display/intel_bw.h b/drivers/gpu/drm/i915/display/intel_bw.h index 46c6eecbd917..0ceaed1c9656 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.h +++ b/drivers/gpu/drm/i915/display/intel_bw.h @@ -30,19 +30,19 @@ struct intel_bw_state { */ u8 pipe_sagv_reject; + /* bitmask of active pipes */ + u8 active_pipes; + /* * Current QGV points mask, which restricts * some particular SAGV states, not to confuse * with pipe_sagv_mask. */ - u8 qgv_points_mask; + u16 qgv_points_mask; unsigned int data_rate[I915_MAX_PIPES]; u8 num_active_planes[I915_MAX_PIPES]; - /* bitmask of active pipes */ - u8 active_pipes; - int min_cdclk; }; diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index a1a663f362e7..00279e8c2775 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -1406,6 +1406,13 @@ static inline u32 man_trk_ctl_single_full_frame_bit_get(struct drm_i915_private PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME; } +static inline u32 man_trk_ctl_partial_frame_bit_get(struct drm_i915_private *dev_priv) +{ + return IS_ALDERLAKE_P(dev_priv) ? + ADLP_PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE : + PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE; +} + static void psr_force_hw_tracking_exit(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); @@ -1510,7 +1517,13 @@ static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - u32 val = PSR2_MAN_TRK_CTL_ENABLE; + u32 val = 0; + + if (!IS_ALDERLAKE_P(dev_priv)) + val = PSR2_MAN_TRK_CTL_ENABLE; + + /* SF partial frame enable has to be set even on full update */ + val |= man_trk_ctl_partial_frame_bit_get(dev_priv); if (full_update) { /* @@ -1530,7 +1543,6 @@ static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state, } else { drm_WARN_ON(crtc_state->uapi.crtc->dev, clip->y1 % 4 || clip->y2 % 4); - val |= PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE; val |= PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(clip->y1 / 4 + 1); val |= PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(clip->y2 / 4 + 1); } diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.c b/drivers/gpu/drm/i915/display/intel_snps_phy.c index 09f405e4d363..92ff654f54f5 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy.c +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c @@ -34,7 +34,7 @@ void intel_snps_phy_wait_for_calibration(struct drm_i915_private *dev_priv) if (intel_de_wait_for_clear(dev_priv, ICL_PHY_MISC(phy), DG2_PHY_DP_TX_ACK_MASK, 25)) DRM_ERROR("SNPS PHY %c failed to calibrate after 25ms.\n", - phy); + phy_name(phy)); } } diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index dbd7d0d83a14..7784c30fe893 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -691,6 +691,8 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); struct intel_encoder *encoder = &dig_port->base; + intel_wakeref_t tc_cold_wref; + enum intel_display_power_domain domain; int active_links = 0; mutex_lock(&dig_port->tc_lock); @@ -702,12 +704,11 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port) drm_WARN_ON(&i915->drm, dig_port->tc_mode != TC_PORT_DISCONNECTED); drm_WARN_ON(&i915->drm, dig_port->tc_lock_wakeref); - if (active_links) { - enum intel_display_power_domain domain; - intel_wakeref_t tc_cold_wref = tc_cold_block(dig_port, &domain); - dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port); + tc_cold_wref = tc_cold_block(dig_port, &domain); + dig_port->tc_mode = intel_tc_port_get_current_mode(dig_port); + if (active_links) { if (!icl_tc_phy_is_connected(dig_port)) drm_dbg_kms(&i915->drm, "Port %s: PHY disconnected with %d active link(s)\n", @@ -716,10 +717,23 @@ void intel_tc_port_sanitize(struct intel_digital_port *dig_port) dig_port->tc_lock_wakeref = tc_cold_block(dig_port, &dig_port->tc_lock_power_domain); - - tc_cold_unblock(dig_port, domain, tc_cold_wref); + } else { + /* + * TBT-alt is the default mode in any case the PHY ownership is not + * held (regardless of the sink's connected live state), so + * we'll just switch to disconnected mode from it here without + * a note. + */ + if (dig_port->tc_mode != TC_PORT_TBT_ALT) + drm_dbg_kms(&i915->drm, + "Port %s: PHY left in %s mode on disabled port, disconnecting it\n", + dig_port->tc_port_name, + tc_port_mode_name(dig_port->tc_mode)); + icl_tc_phy_disconnect(dig_port); } + tc_cold_unblock(dig_port, domain, tc_cold_wref); + drm_dbg_kms(&i915->drm, "Port %s: sanitize mode (%s)\n", dig_port->tc_port_name, tc_port_mode_name(dig_port->tc_mode)); 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/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index c2bb33febb68..902e4c802a12 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -4829,6 +4829,7 @@ enum { #define ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR(val) REG_FIELD_PREP(ADLP_PSR2_MAN_TRK_CTL_SU_REGION_START_ADDR_MASK, val) #define ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR_MASK REG_GENMASK(12, 0) #define ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR(val) REG_FIELD_PREP(ADLP_PSR2_MAN_TRK_CTL_SU_REGION_END_ADDR_MASK, val) +#define ADLP_PSR2_MAN_TRK_CTL_SF_PARTIAL_FRAME_UPDATE REG_BIT(31) #define ADLP_PSR2_MAN_TRK_CTL_SF_SINGLE_FULL_FRAME REG_BIT(14) #define ADLP_PSR2_MAN_TRK_CTL_SF_CONTINUOS_FULL_FRAME REG_BIT(13) 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/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 32bc155f5dc0..fae4f7818d28 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -4029,6 +4029,17 @@ static int intel_compute_sagv_mask(struct intel_atomic_state *state) return ret; } + if (intel_can_enable_sagv(dev_priv, new_bw_state) != + intel_can_enable_sagv(dev_priv, old_bw_state)) { + ret = intel_atomic_serialize_global_state(&new_bw_state->base); + if (ret) + return ret; + } else if (new_bw_state->pipe_sagv_reject != old_bw_state->pipe_sagv_reject) { + ret = intel_atomic_lock_global_state(&new_bw_state->base); + if (ret) + return ret; + } + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { struct skl_pipe_wm *pipe_wm = &new_crtc_state->wm.skl.optimal; @@ -4044,17 +4055,6 @@ static int intel_compute_sagv_mask(struct intel_atomic_state *state) intel_can_enable_sagv(dev_priv, new_bw_state); } - if (intel_can_enable_sagv(dev_priv, new_bw_state) != - intel_can_enable_sagv(dev_priv, old_bw_state)) { - ret = intel_atomic_serialize_global_state(&new_bw_state->base); - if (ret) - return ret; - } else if (new_bw_state->pipe_sagv_reject != old_bw_state->pipe_sagv_reject) { - ret = intel_atomic_lock_global_state(&new_bw_state->base); - if (ret) - return ret; - } - return 0; } diff --git a/drivers/gpu/drm/imx/dcss/Kconfig b/drivers/gpu/drm/imx/dcss/Kconfig index 7374f1952762..5c2b2277afbf 100644 --- a/drivers/gpu/drm/imx/dcss/Kconfig +++ b/drivers/gpu/drm/imx/dcss/Kconfig @@ -2,6 +2,7 @@ config DRM_IMX_DCSS tristate "i.MX8MQ DCSS" select IMX_IRQSTEER select DRM_KMS_HELPER + select DRM_GEM_CMA_HELPER select VIDEOMODE_HELPERS depends on DRM && ARCH_MXC && ARM64 help diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig index 434c2861bb40..0aec5a10b064 100644 --- a/drivers/gpu/drm/panel/Kconfig +++ b/drivers/gpu/drm/panel/Kconfig @@ -106,6 +106,7 @@ config DRM_PANEL_EDP depends on PM select VIDEOMODE_HELPERS select DRM_DP_AUX_BUS + select DRM_DP_HELPER help DRM panel driver for dumb eDP panels that need at most a regulator and a GPIO to be powered up. Optionally a backlight can be attached so diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c index 377f9cdb5b53..84013faa4756 100644 --- a/drivers/gpu/drm/radeon/radeon_uvd.c +++ b/drivers/gpu/drm/radeon/radeon_uvd.c @@ -470,8 +470,8 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, int32_t *msg, msg_type, handle; unsigned img_size = 0; void *ptr; - - int i, r; + long r; + int i; if (offset & 0x3F) { DRM_ERROR("UVD messages must be 64 byte aligned!\n"); @@ -481,13 +481,13 @@ static int radeon_uvd_cs_msg(struct radeon_cs_parser *p, struct radeon_bo *bo, r = dma_resv_wait_timeout(bo->tbo.base.resv, false, false, MAX_SCHEDULE_TIMEOUT); if (r <= 0) { - DRM_ERROR("Failed waiting for UVD message (%d)!\n", r); + DRM_ERROR("Failed waiting for UVD message (%ld)!\n", r); return r ? r : -ETIME; } r = radeon_bo_kmap(bo, &ptr); if (r) { - DRM_ERROR("Failed mapping the UVD message (%d)!\n", r); + DRM_ERROR("Failed mapping the UVD message (%ld)!\n", r); return r; } diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h index 145833a9d82d..5b3fbee18671 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.h +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h @@ -111,10 +111,10 @@ /* format 13 is semi-planar YUV411 VUVU */ #define SUN8I_MIXER_FBFMT_YUV411 14 /* format 15 doesn't exist */ -/* format 16 is P010 YVU */ -#define SUN8I_MIXER_FBFMT_P010_YUV 17 -/* format 18 is P210 YVU */ -#define SUN8I_MIXER_FBFMT_P210_YUV 19 +#define SUN8I_MIXER_FBFMT_P010_YUV 16 +/* format 17 is P010 YVU */ +#define SUN8I_MIXER_FBFMT_P210_YUV 18 +/* format 19 is P210 YVU */ /* format 20 is packed YVU444 10-bit */ /* format 21 is packed YUV444 10-bit */ diff --git a/drivers/gpu/drm/tegra/Kconfig b/drivers/gpu/drm/tegra/Kconfig index 8cf5aeb9db6c..201f5175ecfe 100644 --- a/drivers/gpu/drm/tegra/Kconfig +++ b/drivers/gpu/drm/tegra/Kconfig @@ -5,6 +5,7 @@ config DRM_TEGRA depends on COMMON_CLK depends on DRM depends on OF + select DRM_DP_AUX_BUS select DRM_KMS_HELPER select DRM_MIPI_DSI select DRM_PANEL diff --git a/drivers/gpu/drm/tegra/dpaux.c b/drivers/gpu/drm/tegra/dpaux.c index 1f96e416fa08..d7a731d287d2 100644 --- a/drivers/gpu/drm/tegra/dpaux.c +++ b/drivers/gpu/drm/tegra/dpaux.c @@ -19,6 +19,7 @@ #include <linux/workqueue.h> #include <drm/drm_dp_helper.h> +#include <drm/drm_dp_aux_bus.h> #include <drm/drm_panel.h> #include "dp.h" @@ -570,6 +571,12 @@ static int tegra_dpaux_probe(struct platform_device *pdev) list_add_tail(&dpaux->list, &dpaux_list); mutex_unlock(&dpaux_lock); + err = devm_of_dp_aux_populate_ep_devices(&dpaux->aux); + if (err < 0) { + dev_err(dpaux->dev, "failed to populate AUX bus: %d\n", err); + return err; + } + return 0; } diff --git a/drivers/gpu/drm/tegra/falcon.c b/drivers/gpu/drm/tegra/falcon.c index 223ab2ceb7e6..3762d87759d9 100644 --- a/drivers/gpu/drm/tegra/falcon.c +++ b/drivers/gpu/drm/tegra/falcon.c @@ -63,7 +63,7 @@ static void falcon_copy_firmware_image(struct falcon *falcon, /* copy the whole thing taking into account endianness */ for (i = 0; i < firmware->size / sizeof(u32); i++) - virt[i] = le32_to_cpu(((u32 *)firmware->data)[i]); + virt[i] = le32_to_cpu(((__le32 *)firmware->data)[i]); } static int falcon_parse_firmware_image(struct falcon *falcon) diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c index e6cc47470e03..783890e8d43a 100644 --- a/drivers/gpu/drm/vc4/vc4_crtc.c +++ b/drivers/gpu/drm/vc4/vc4_crtc.c @@ -525,9 +525,11 @@ int vc4_crtc_disable_at_boot(struct drm_crtc *crtc) if (ret) return ret; - ret = pm_runtime_put(&vc4_hdmi->pdev->dev); - if (ret) - return ret; + /* + * post_crtc_powerdown will have called pm_runtime_put, so we + * don't need it here otherwise we'll get the reference counting + * wrong. + */ return 0; } diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index b30500405fa7..3a1626f261e5 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1749,6 +1749,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) dev_err(dev, "Couldn't register the HDMI codec: %ld\n", PTR_ERR(codec_pdev)); return PTR_ERR(codec_pdev); } + vc4_hdmi->audio.codec_pdev = codec_pdev; dai_link->cpus = &vc4_hdmi->audio.cpu; dai_link->codecs = &vc4_hdmi->audio.codec; @@ -1788,6 +1789,12 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi) } +static void vc4_hdmi_audio_exit(struct vc4_hdmi *vc4_hdmi) +{ + platform_device_unregister(vc4_hdmi->audio.codec_pdev); + vc4_hdmi->audio.codec_pdev = NULL; +} + static irqreturn_t vc4_hdmi_hpd_irq_thread(int irq, void *priv) { struct vc4_hdmi *vc4_hdmi = priv; @@ -2660,6 +2667,7 @@ static void vc4_hdmi_unbind(struct device *dev, struct device *master, kfree(vc4_hdmi->hdmi_regset.regs); kfree(vc4_hdmi->hd_regset.regs); + vc4_hdmi_audio_exit(vc4_hdmi); vc4_hdmi_cec_exit(vc4_hdmi); vc4_hdmi_hotplug_exit(vc4_hdmi); vc4_hdmi_connector_destroy(&vc4_hdmi->connector); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index 31b77a94c526..6ffdd4ec5fb6 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -116,6 +116,7 @@ struct vc4_hdmi_audio { struct snd_soc_dai_link_component platform; struct snd_dmaengine_dai_dma_data dma_data; struct hdmi_audio_infoframe infoframe; + struct platform_device *codec_pdev; bool streaming; }; diff --git a/drivers/gpu/host1x/syncpt.c b/drivers/gpu/host1x/syncpt.c index e08e331e46ae..f87a8705f518 100644 --- a/drivers/gpu/host1x/syncpt.c +++ b/drivers/gpu/host1x/syncpt.c @@ -137,8 +137,15 @@ void host1x_syncpt_restore(struct host1x *host) struct host1x_syncpt *sp_base = host->syncpt; unsigned int i; - for (i = 0; i < host1x_syncpt_nb_pts(host); i++) + for (i = 0; i < host1x_syncpt_nb_pts(host); i++) { + /* + * Unassign syncpt from channels for purposes of Tegra186 + * syncpoint protection. This prevents any channel from + * accessing it until it is reassigned. + */ + host1x_hw_syncpt_assign_to_channel(host, sp_base + i, NULL); host1x_hw_syncpt_restore(host, sp_base + i); + } for (i = 0; i < host1x_syncpt_nb_bases(host); i++) host1x_hw_syncpt_restore_wait_base(host, sp_base + i); @@ -227,27 +234,12 @@ int host1x_syncpt_wait(struct host1x_syncpt *sp, u32 thresh, long timeout, void *ref; struct host1x_waitlist *waiter; int err = 0, check_count = 0; - u32 val; if (value) - *value = 0; - - /* first check cache */ - if (host1x_syncpt_is_expired(sp, thresh)) { - if (value) - *value = host1x_syncpt_load(sp); + *value = host1x_syncpt_load(sp); + if (host1x_syncpt_is_expired(sp, thresh)) return 0; - } - - /* try to read from register */ - val = host1x_hw_syncpt_load(sp->host, sp); - if (host1x_syncpt_is_expired(sp, thresh)) { - if (value) - *value = val; - - goto done; - } if (!timeout) { err = -EAGAIN; @@ -352,13 +344,6 @@ int host1x_syncpt_init(struct host1x *host) for (i = 0; i < host->info->nb_pts; i++) { syncpt[i].id = i; syncpt[i].host = host; - - /* - * Unassign syncpt from channels for purposes of Tegra186 - * syncpoint protection. This prevents any channel from - * accessing it until it is reassigned. - */ - host1x_hw_syncpt_assign_to_channel(host, &syncpt[i], NULL); } for (i = 0; i < host->info->nb_bases; i++) 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/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 3501a3ead4ba..3ae961986fc3 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -214,12 +214,14 @@ static int hwmon_thermal_add_sensor(struct device *dev, int index) tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata, &hwmon_thermal_ops); - /* - * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV, - * so ignore that error but forward any other error. - */ - if (IS_ERR(tzd) && (PTR_ERR(tzd) != -ENODEV)) - return PTR_ERR(tzd); + if (IS_ERR(tzd)) { + if (PTR_ERR(tzd) != -ENODEV) + return PTR_ERR(tzd); + dev_info(dev, "temp%d_input not attached to any thermal zone\n", + index + 1); + devm_kfree(dev, tdata); + return 0; + } err = devm_add_action(dev, hwmon_thermal_remove_sensor, &tdata->node); if (err) diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c index 414204f5704c..9c9e9f4ccb9e 100644 --- a/drivers/hwmon/ntc_thermistor.c +++ b/drivers/hwmon/ntc_thermistor.c @@ -59,7 +59,7 @@ static const struct platform_device_id ntc_thermistor_id[] = { [NTC_NCP15XH103] = { "ncp15xh103", TYPE_NCPXXXH103 }, [NTC_NCP18WB473] = { "ncp18wb473", TYPE_NCPXXWB473 }, [NTC_NCP21WB473] = { "ncp21wb473", TYPE_NCPXXWB473 }, - [NTC_SSG1404001221] = { "ssg1404-001221", TYPE_NCPXXWB473 }, + [NTC_SSG1404001221] = { "ssg1404_001221", TYPE_NCPXXWB473 }, [NTC_LAST] = { }, }; diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c index 776ee2237be2..ac2fbee1ba9c 100644 --- a/drivers/hwmon/pmbus/pmbus_core.c +++ b/drivers/hwmon/pmbus/pmbus_core.c @@ -911,6 +911,11 @@ static int pmbus_get_boolean(struct i2c_client *client, struct pmbus_boolean *b, pmbus_update_sensor_data(client, s2); regval = status & mask; + if (regval) { + ret = pmbus_write_byte_data(client, page, reg, regval); + if (ret) + goto unlock; + } if (s1 && s2) { s64 v1, v2; diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c index e6081dd0a880..d11f668016a6 100644 --- a/drivers/iio/accel/bmc150-accel-core.c +++ b/drivers/iio/accel/bmc150-accel-core.c @@ -1783,11 +1783,14 @@ int bmc150_accel_core_probe(struct device *dev, struct regmap *regmap, int irq, ret = iio_device_register(indio_dev); if (ret < 0) { dev_err(dev, "Unable to register iio device\n"); - goto err_trigger_unregister; + goto err_pm_cleanup; } return 0; +err_pm_cleanup: + pm_runtime_dont_use_autosuspend(dev); + pm_runtime_disable(dev); err_trigger_unregister: bmc150_accel_unregister_triggers(data, BMC150_ACCEL_TRIGGERS - 1); err_buffer_cleanup: diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c index 32989d91b982..f7fd9e046588 100644 --- a/drivers/iio/accel/fxls8962af-core.c +++ b/drivers/iio/accel/fxls8962af-core.c @@ -173,12 +173,20 @@ struct fxls8962af_data { u16 upper_thres; }; -const struct regmap_config fxls8962af_regmap_conf = { +const struct regmap_config fxls8962af_i2c_regmap_conf = { .reg_bits = 8, .val_bits = 8, .max_register = FXLS8962AF_MAX_REG, }; -EXPORT_SYMBOL_GPL(fxls8962af_regmap_conf); +EXPORT_SYMBOL_GPL(fxls8962af_i2c_regmap_conf); + +const struct regmap_config fxls8962af_spi_regmap_conf = { + .reg_bits = 8, + .pad_bits = 8, + .val_bits = 8, + .max_register = FXLS8962AF_MAX_REG, +}; +EXPORT_SYMBOL_GPL(fxls8962af_spi_regmap_conf); enum { fxls8962af_idx_x, diff --git a/drivers/iio/accel/fxls8962af-i2c.c b/drivers/iio/accel/fxls8962af-i2c.c index cfb004b20455..6bde9891effb 100644 --- a/drivers/iio/accel/fxls8962af-i2c.c +++ b/drivers/iio/accel/fxls8962af-i2c.c @@ -18,7 +18,7 @@ static int fxls8962af_probe(struct i2c_client *client) { struct regmap *regmap; - regmap = devm_regmap_init_i2c(client, &fxls8962af_regmap_conf); + regmap = devm_regmap_init_i2c(client, &fxls8962af_i2c_regmap_conf); if (IS_ERR(regmap)) { dev_err(&client->dev, "Failed to initialize i2c regmap\n"); return PTR_ERR(regmap); diff --git a/drivers/iio/accel/fxls8962af-spi.c b/drivers/iio/accel/fxls8962af-spi.c index 57108d3d480b..6f4dff3238d3 100644 --- a/drivers/iio/accel/fxls8962af-spi.c +++ b/drivers/iio/accel/fxls8962af-spi.c @@ -18,7 +18,7 @@ static int fxls8962af_probe(struct spi_device *spi) { struct regmap *regmap; - regmap = devm_regmap_init_spi(spi, &fxls8962af_regmap_conf); + regmap = devm_regmap_init_spi(spi, &fxls8962af_spi_regmap_conf); if (IS_ERR(regmap)) { dev_err(&spi->dev, "Failed to initialize spi regmap\n"); return PTR_ERR(regmap); diff --git a/drivers/iio/accel/fxls8962af.h b/drivers/iio/accel/fxls8962af.h index b67572c3ef06..9cbe98c3ba9a 100644 --- a/drivers/iio/accel/fxls8962af.h +++ b/drivers/iio/accel/fxls8962af.h @@ -17,6 +17,7 @@ int fxls8962af_core_probe(struct device *dev, struct regmap *regmap, int irq); int fxls8962af_core_remove(struct device *dev); extern const struct dev_pm_ops fxls8962af_pm_ops; -extern const struct regmap_config fxls8962af_regmap_conf; +extern const struct regmap_config fxls8962af_i2c_regmap_conf; +extern const struct regmap_config fxls8962af_spi_regmap_conf; #endif /* _FXLS8962AF_H_ */ diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c index 0fe570316848..ac74cdcd2bc8 100644 --- a/drivers/iio/accel/kxcjk-1013.c +++ b/drivers/iio/accel/kxcjk-1013.c @@ -1590,11 +1590,14 @@ static int kxcjk1013_probe(struct i2c_client *client, ret = iio_device_register(indio_dev); if (ret < 0) { dev_err(&client->dev, "unable to register iio device\n"); - goto err_buffer_cleanup; + goto err_pm_cleanup; } return 0; +err_pm_cleanup: + pm_runtime_dont_use_autosuspend(&client->dev); + pm_runtime_disable(&client->dev); err_buffer_cleanup: iio_triggered_buffer_cleanup(indio_dev); err_trigger_unregister: diff --git a/drivers/iio/accel/mma9551.c b/drivers/iio/accel/mma9551.c index 4c359fb05480..c53a3398b14c 100644 --- a/drivers/iio/accel/mma9551.c +++ b/drivers/iio/accel/mma9551.c @@ -495,11 +495,14 @@ static int mma9551_probe(struct i2c_client *client, ret = iio_device_register(indio_dev); if (ret < 0) { dev_err(&client->dev, "unable to register iio device\n"); - goto out_poweroff; + goto err_pm_cleanup; } return 0; +err_pm_cleanup: + pm_runtime_dont_use_autosuspend(&client->dev); + pm_runtime_disable(&client->dev); out_poweroff: mma9551_set_device_state(client, false); diff --git a/drivers/iio/accel/mma9553.c b/drivers/iio/accel/mma9553.c index 0570ab1cc064..5ff6bc70708b 100644 --- a/drivers/iio/accel/mma9553.c +++ b/drivers/iio/accel/mma9553.c @@ -1134,12 +1134,15 @@ static int mma9553_probe(struct i2c_client *client, ret = iio_device_register(indio_dev); if (ret < 0) { dev_err(&client->dev, "unable to register iio device\n"); - goto out_poweroff; + goto err_pm_cleanup; } dev_dbg(&indio_dev->dev, "Registered device %s\n", name); return 0; +err_pm_cleanup: + pm_runtime_dont_use_autosuspend(&client->dev); + pm_runtime_disable(&client->dev); out_poweroff: mma9551_set_device_state(client, false); return ret; diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c index bc2cfa5f9592..b400bbe291aa 100644 --- a/drivers/iio/adc/ad7124.c +++ b/drivers/iio/adc/ad7124.c @@ -76,7 +76,7 @@ #define AD7124_CONFIG_REF_SEL(x) FIELD_PREP(AD7124_CONFIG_REF_SEL_MSK, x) #define AD7124_CONFIG_PGA_MSK GENMASK(2, 0) #define AD7124_CONFIG_PGA(x) FIELD_PREP(AD7124_CONFIG_PGA_MSK, x) -#define AD7124_CONFIG_IN_BUFF_MSK GENMASK(7, 6) +#define AD7124_CONFIG_IN_BUFF_MSK GENMASK(6, 5) #define AD7124_CONFIG_IN_BUFF(x) FIELD_PREP(AD7124_CONFIG_IN_BUFF_MSK, x) /* AD7124_FILTER_X */ diff --git a/drivers/iio/adc/men_z188_adc.c b/drivers/iio/adc/men_z188_adc.c index 42ea8bc7e780..adc5ceaef8c9 100644 --- a/drivers/iio/adc/men_z188_adc.c +++ b/drivers/iio/adc/men_z188_adc.c @@ -103,6 +103,7 @@ static int men_z188_probe(struct mcb_device *dev, struct z188_adc *adc; struct iio_dev *indio_dev; struct resource *mem; + int ret; indio_dev = devm_iio_device_alloc(&dev->dev, sizeof(struct z188_adc)); if (!indio_dev) @@ -128,8 +129,14 @@ static int men_z188_probe(struct mcb_device *dev, adc->mem = mem; mcb_set_drvdata(dev, indio_dev); - return iio_device_register(indio_dev); + ret = iio_device_register(indio_dev); + if (ret) + goto err_unmap; + + return 0; +err_unmap: + iounmap(adc->base); err: mcb_release_mem(mem); return -ENXIO; diff --git a/drivers/iio/adc/ti-tsc2046.c b/drivers/iio/adc/ti-tsc2046.c index d84ae6b008c1..e8fc4d01f30b 100644 --- a/drivers/iio/adc/ti-tsc2046.c +++ b/drivers/iio/adc/ti-tsc2046.c @@ -388,7 +388,7 @@ static int tsc2046_adc_update_scan_mode(struct iio_dev *indio_dev, mutex_lock(&priv->slock); size = 0; - for_each_set_bit(ch_idx, active_scan_mask, indio_dev->num_channels) { + for_each_set_bit(ch_idx, active_scan_mask, ARRAY_SIZE(priv->l)) { size += tsc2046_adc_group_set_layout(priv, group, ch_idx); tsc2046_adc_group_set_cmd(priv, group, ch_idx); group++; @@ -548,7 +548,7 @@ static int tsc2046_adc_setup_spi_msg(struct tsc2046_adc_priv *priv) * enabled. */ size = 0; - for (ch_idx = 0; ch_idx < priv->dcfg->num_channels; ch_idx++) + for (ch_idx = 0; ch_idx < ARRAY_SIZE(priv->l); ch_idx++) size += tsc2046_adc_group_set_layout(priv, ch_idx, ch_idx); priv->tx = devm_kzalloc(&priv->spi->dev, size, GFP_KERNEL); diff --git a/drivers/iio/addac/ad74413r.c b/drivers/iio/addac/ad74413r.c index 5271073bb74e..acd230a6af35 100644 --- a/drivers/iio/addac/ad74413r.c +++ b/drivers/iio/addac/ad74413r.c @@ -134,7 +134,6 @@ struct ad74413r_state { #define AD74413R_CH_EN_MASK(x) BIT(x) #define AD74413R_REG_DIN_COMP_OUT 0x25 -#define AD74413R_DIN_COMP_OUT_SHIFT_X(x) x #define AD74413R_REG_ADC_RESULT_X(x) (0x26 + (x)) #define AD74413R_ADC_RESULT_MAX GENMASK(15, 0) @@ -288,7 +287,7 @@ static void ad74413r_gpio_set_multiple(struct gpio_chip *chip, unsigned int offset = 0; int ret; - for_each_set_bit_from(offset, mask, AD74413R_CHANNEL_MAX) { + for_each_set_bit_from(offset, mask, chip->ngpio) { unsigned int real_offset = st->gpo_gpio_offsets[offset]; ret = ad74413r_set_gpo_config(st, real_offset, @@ -316,7 +315,7 @@ static int ad74413r_gpio_get(struct gpio_chip *chip, unsigned int offset) if (ret) return ret; - status &= AD74413R_DIN_COMP_OUT_SHIFT_X(real_offset); + status &= BIT(real_offset); return status ? 1 : 0; } @@ -334,11 +333,10 @@ static int ad74413r_gpio_get_multiple(struct gpio_chip *chip, if (ret) return ret; - for_each_set_bit_from(offset, mask, AD74413R_CHANNEL_MAX) { + for_each_set_bit_from(offset, mask, chip->ngpio) { unsigned int real_offset = st->comp_gpio_offsets[offset]; - if (val & BIT(real_offset)) - *bits |= offset; + __assign_bit(offset, bits, val & BIT(real_offset)); } return ret; @@ -840,7 +838,7 @@ static int ad74413r_update_scan_mode(struct iio_dev *indio_dev, { struct ad74413r_state *st = iio_priv(indio_dev); struct spi_transfer *xfer = st->adc_samples_xfer; - u8 *rx_buf = &st->adc_samples_buf.rx_buf[-1 * AD74413R_FRAME_SIZE]; + u8 *rx_buf = st->adc_samples_buf.rx_buf; u8 *tx_buf = st->adc_samples_tx_buf; unsigned int channel; int ret = -EINVAL; @@ -894,9 +892,10 @@ static int ad74413r_update_scan_mode(struct iio_dev *indio_dev, spi_message_add_tail(xfer, &st->adc_samples_msg); - xfer++; tx_buf += AD74413R_FRAME_SIZE; - rx_buf += AD74413R_FRAME_SIZE; + if (xfer != st->adc_samples_xfer) + rx_buf += AD74413R_FRAME_SIZE; + xfer++; } xfer->rx_buf = rx_buf; diff --git a/drivers/iio/frequency/admv1013.c b/drivers/iio/frequency/admv1013.c index 6cdeb50143af..3f3c478e9baa 100644 --- a/drivers/iio/frequency/admv1013.c +++ b/drivers/iio/frequency/admv1013.c @@ -348,7 +348,7 @@ static int admv1013_update_mixer_vgate(struct admv1013_state *st) vcm = regulator_get_voltage(st->reg); - if (vcm >= 0 && vcm < 1800000) + if (vcm < 1800000) mixer_vgate = (2389 * vcm / 1000000 + 8100) / 100; else if (vcm > 1800000 && vcm < 2600000) mixer_vgate = (2375 * vcm / 1000000 + 125) / 100; diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c index 17b939a367ad..81a6d09788bd 100644 --- a/drivers/iio/gyro/bmg160_core.c +++ b/drivers/iio/gyro/bmg160_core.c @@ -1188,11 +1188,14 @@ int bmg160_core_probe(struct device *dev, struct regmap *regmap, int irq, ret = iio_device_register(indio_dev); if (ret < 0) { dev_err(dev, "unable to register iio device\n"); - goto err_buffer_cleanup; + goto err_pm_cleanup; } return 0; +err_pm_cleanup: + pm_runtime_dont_use_autosuspend(dev); + pm_runtime_disable(dev); err_buffer_cleanup: iio_triggered_buffer_cleanup(indio_dev); err_trigger_unregister: diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c index ed129321a14d..f9b4540db1f4 100644 --- a/drivers/iio/imu/adis16480.c +++ b/drivers/iio/imu/adis16480.c @@ -1403,6 +1403,7 @@ static int adis16480_probe(struct spi_device *spi) { const struct spi_device_id *id = spi_get_device_id(spi); const struct adis_data *adis16480_data; + irq_handler_t trigger_handler = NULL; struct iio_dev *indio_dev; struct adis16480 *st; int ret; @@ -1474,8 +1475,12 @@ static int adis16480_probe(struct spi_device *spi) st->clk_freq = st->chip_info->int_clk; } + /* Only use our trigger handler if burst mode is supported */ + if (adis16480_data->burst_len) + trigger_handler = adis16480_trigger_handler; + ret = devm_adis_setup_buffer_and_trigger(&st->adis, indio_dev, - adis16480_trigger_handler); + trigger_handler); if (ret) return ret; diff --git a/drivers/iio/imu/kmx61.c b/drivers/iio/imu/kmx61.c index 1dabfd615dab..f89724481df9 100644 --- a/drivers/iio/imu/kmx61.c +++ b/drivers/iio/imu/kmx61.c @@ -1385,7 +1385,7 @@ static int kmx61_probe(struct i2c_client *client, ret = iio_device_register(data->acc_indio_dev); if (ret < 0) { dev_err(&client->dev, "Failed to register acc iio device\n"); - goto err_buffer_cleanup_mag; + goto err_pm_cleanup; } ret = iio_device_register(data->mag_indio_dev); @@ -1398,6 +1398,9 @@ static int kmx61_probe(struct i2c_client *client, err_iio_unregister_acc: iio_device_unregister(data->acc_indio_dev); +err_pm_cleanup: + pm_runtime_dont_use_autosuspend(&client->dev); + pm_runtime_disable(&client->dev); err_buffer_cleanup_mag: if (client->irq > 0) iio_triggered_buffer_cleanup(data->mag_indio_dev); diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index 727b4b6ac696..93f0c6bce502 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -1374,8 +1374,12 @@ static int st_lsm6dsx_read_oneshot(struct st_lsm6dsx_sensor *sensor, if (err < 0) return err; + /* + * we need to wait for sensor settling time before + * reading data in order to avoid corrupted samples + */ delay = 1000000000 / sensor->odr; - usleep_range(delay, 2 * delay); + usleep_range(3 * delay, 4 * delay); err = st_lsm6dsx_read_locked(hw, addr, &data, sizeof(data)); if (err < 0) diff --git a/drivers/iio/magnetometer/bmc150_magn.c b/drivers/iio/magnetometer/bmc150_magn.c index f96f53175349..3d4d21f979fa 100644 --- a/drivers/iio/magnetometer/bmc150_magn.c +++ b/drivers/iio/magnetometer/bmc150_magn.c @@ -962,13 +962,14 @@ int bmc150_magn_probe(struct device *dev, struct regmap *regmap, ret = iio_device_register(indio_dev); if (ret < 0) { dev_err(dev, "unable to register iio device\n"); - goto err_disable_runtime_pm; + goto err_pm_cleanup; } dev_dbg(dev, "Registered device %s\n", name); return 0; -err_disable_runtime_pm: +err_pm_cleanup: + pm_runtime_dont_use_autosuspend(dev); pm_runtime_disable(dev); err_buffer_cleanup: iio_triggered_buffer_cleanup(indio_dev); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index c447526288f4..50c53409ceb6 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -3370,22 +3370,30 @@ err: static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { - if (!src_addr || !src_addr->sa_family) { - src_addr = (struct sockaddr *) &id->route.addr.src_addr; - src_addr->sa_family = dst_addr->sa_family; - if (IS_ENABLED(CONFIG_IPV6) && - dst_addr->sa_family == AF_INET6) { - struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *) src_addr; - struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *) dst_addr; - src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; - if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) - id->route.addr.dev_addr.bound_dev_if = dst_addr6->sin6_scope_id; - } else if (dst_addr->sa_family == AF_IB) { - ((struct sockaddr_ib *) src_addr)->sib_pkey = - ((struct sockaddr_ib *) dst_addr)->sib_pkey; - } - } - return rdma_bind_addr(id, src_addr); + struct sockaddr_storage zero_sock = {}; + + if (src_addr && src_addr->sa_family) + return rdma_bind_addr(id, src_addr); + + /* + * When the src_addr is not specified, automatically supply an any addr + */ + zero_sock.ss_family = dst_addr->sa_family; + if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { + struct sockaddr_in6 *src_addr6 = + (struct sockaddr_in6 *)&zero_sock; + struct sockaddr_in6 *dst_addr6 = + (struct sockaddr_in6 *)dst_addr; + + src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; + if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) + id->route.addr.dev_addr.bound_dev_if = + dst_addr6->sin6_scope_id; + } else if (dst_addr->sa_family == AF_IB) { + ((struct sockaddr_ib *)&zero_sock)->sib_pkey = + ((struct sockaddr_ib *)dst_addr)->sib_pkey; + } + return rdma_bind_addr(id, (struct sockaddr *)&zero_sock); } /* diff --git a/drivers/infiniband/hw/qib/qib_sysfs.c b/drivers/infiniband/hw/qib/qib_sysfs.c index 0a3b28142c05..41c272980f91 100644 --- a/drivers/infiniband/hw/qib/qib_sysfs.c +++ b/drivers/infiniband/hw/qib/qib_sysfs.c @@ -541,7 +541,7 @@ static struct attribute *port_diagc_attributes[] = { }; static const struct attribute_group port_diagc_group = { - .name = "linkcontrol", + .name = "diag_counters", .attrs = port_diagc_attributes, }; diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 7c3f98e57889..759b85f03331 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -2682,6 +2682,8 @@ static void rtrs_clt_dev_release(struct device *dev) struct rtrs_clt_sess *clt = container_of(dev, struct rtrs_clt_sess, dev); + mutex_destroy(&clt->paths_ev_mutex); + mutex_destroy(&clt->paths_mutex); kfree(clt); } @@ -2711,6 +2713,8 @@ static struct rtrs_clt_sess *alloc_clt(const char *sessname, size_t paths_num, return ERR_PTR(-ENOMEM); } + clt->dev.class = rtrs_clt_dev_class; + clt->dev.release = rtrs_clt_dev_release; uuid_gen(&clt->paths_uuid); INIT_LIST_HEAD_RCU(&clt->paths_list); clt->paths_num = paths_num; @@ -2727,53 +2731,51 @@ static struct rtrs_clt_sess *alloc_clt(const char *sessname, size_t paths_num, init_waitqueue_head(&clt->permits_wait); mutex_init(&clt->paths_ev_mutex); mutex_init(&clt->paths_mutex); + device_initialize(&clt->dev); - clt->dev.class = rtrs_clt_dev_class; - clt->dev.release = rtrs_clt_dev_release; err = dev_set_name(&clt->dev, "%s", sessname); if (err) - goto err; + goto err_put; + /* * Suppress user space notification until * sysfs files are created */ dev_set_uevent_suppress(&clt->dev, true); - err = device_register(&clt->dev); - if (err) { - put_device(&clt->dev); - goto err; - } + err = device_add(&clt->dev); + if (err) + goto err_put; clt->kobj_paths = kobject_create_and_add("paths", &clt->dev.kobj); if (!clt->kobj_paths) { err = -ENOMEM; - goto err_dev; + goto err_del; } err = rtrs_clt_create_sysfs_root_files(clt); if (err) { kobject_del(clt->kobj_paths); kobject_put(clt->kobj_paths); - goto err_dev; + goto err_del; } dev_set_uevent_suppress(&clt->dev, false); kobject_uevent(&clt->dev.kobj, KOBJ_ADD); return clt; -err_dev: - device_unregister(&clt->dev); -err: +err_del: + device_del(&clt->dev); +err_put: free_percpu(clt->pcpu_path); - kfree(clt); + put_device(&clt->dev); return ERR_PTR(err); } static void free_clt(struct rtrs_clt_sess *clt) { - free_permits(clt); free_percpu(clt->pcpu_path); - mutex_destroy(&clt->paths_ev_mutex); - mutex_destroy(&clt->paths_mutex); - /* release callback will free clt in last put */ + + /* + * release callback will free clt and destroy mutexes in last put + */ device_unregister(&clt->dev); } @@ -2890,6 +2892,7 @@ void rtrs_clt_close(struct rtrs_clt_sess *clt) rtrs_clt_destroy_path_files(clt_path, NULL); kobject_put(&clt_path->kobj); } + free_permits(clt); free_clt(clt); } EXPORT_SYMBOL(rtrs_clt_close); diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c index e174e853f8a4..285b766e4e70 100644 --- a/drivers/infiniband/ulp/srp/ib_srp.c +++ b/drivers/infiniband/ulp/srp/ib_srp.c @@ -4047,9 +4047,11 @@ static void srp_remove_one(struct ib_device *device, void *client_data) spin_unlock(&host->target_lock); /* - * Wait for tl_err and target port removal tasks. + * srp_queue_remove_work() queues a call to + * srp_remove_target(). The latter function cancels + * target->tl_err_work so waiting for the remove works to + * finish is sufficient. */ - flush_workqueue(system_long_wq); flush_workqueue(srp_remove_wq); kfree(host); 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/mmc/core/block.c b/drivers/mmc/core/block.c index 8d718aa56d33..4e67c1403cc9 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -1908,7 +1908,7 @@ static int mmc_blk_card_busy(struct mmc_card *card, struct request *req) cb_data.card = card; cb_data.status = 0; - err = __mmc_poll_for_busy(card->host, MMC_BLK_TIMEOUT_MS, + err = __mmc_poll_for_busy(card->host, 0, MMC_BLK_TIMEOUT_MS, &mmc_blk_busy_cb, &cb_data); /* diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index bbbbcaf70a59..8421519c2a98 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -1962,7 +1962,7 @@ static int mmc_sleep(struct mmc_host *host) goto out_release; } - err = __mmc_poll_for_busy(host, timeout_ms, &mmc_sleep_busy_cb, host); + err = __mmc_poll_for_busy(host, 0, timeout_ms, &mmc_sleep_busy_cb, host); out_release: mmc_retune_release(host); diff --git a/drivers/mmc/core/mmc_ops.c b/drivers/mmc/core/mmc_ops.c index d63d1c735335..180d7e9d3400 100644 --- a/drivers/mmc/core/mmc_ops.c +++ b/drivers/mmc/core/mmc_ops.c @@ -21,6 +21,8 @@ #define MMC_BKOPS_TIMEOUT_MS (120 * 1000) /* 120s */ #define MMC_SANITIZE_TIMEOUT_MS (240 * 1000) /* 240s */ +#define MMC_OP_COND_PERIOD_US (1 * 1000) /* 1ms */ +#define MMC_OP_COND_TIMEOUT_MS 1000 /* 1s */ static const u8 tuning_blk_pattern_4bit[] = { 0xff, 0x0f, 0xff, 0x00, 0xff, 0xcc, 0xc3, 0xcc, @@ -232,7 +234,9 @@ int mmc_send_op_cond(struct mmc_host *host, u32 ocr, u32 *rocr) cmd.arg = mmc_host_is_spi(host) ? 0 : ocr; cmd.flags = MMC_RSP_SPI_R1 | MMC_RSP_R3 | MMC_CMD_BCR; - err = __mmc_poll_for_busy(host, 1000, &__mmc_send_op_cond_cb, &cb_data); + err = __mmc_poll_for_busy(host, MMC_OP_COND_PERIOD_US, + MMC_OP_COND_TIMEOUT_MS, + &__mmc_send_op_cond_cb, &cb_data); if (err) return err; @@ -495,13 +499,14 @@ static int mmc_busy_cb(void *cb_data, bool *busy) return 0; } -int __mmc_poll_for_busy(struct mmc_host *host, unsigned int timeout_ms, +int __mmc_poll_for_busy(struct mmc_host *host, unsigned int period_us, + unsigned int timeout_ms, int (*busy_cb)(void *cb_data, bool *busy), void *cb_data) { int err; unsigned long timeout; - unsigned int udelay = 32, udelay_max = 32768; + unsigned int udelay = period_us ? period_us : 32, udelay_max = 32768; bool expired = false; bool busy = false; @@ -546,7 +551,7 @@ int mmc_poll_for_busy(struct mmc_card *card, unsigned int timeout_ms, cb_data.retry_crc_err = retry_crc_err; cb_data.busy_cmd = busy_cmd; - return __mmc_poll_for_busy(host, timeout_ms, &mmc_busy_cb, &cb_data); + return __mmc_poll_for_busy(host, 0, timeout_ms, &mmc_busy_cb, &cb_data); } EXPORT_SYMBOL_GPL(mmc_poll_for_busy); diff --git a/drivers/mmc/core/mmc_ops.h b/drivers/mmc/core/mmc_ops.h index 9c813b851d0b..09ffbc00908b 100644 --- a/drivers/mmc/core/mmc_ops.h +++ b/drivers/mmc/core/mmc_ops.h @@ -41,7 +41,8 @@ int mmc_can_ext_csd(struct mmc_card *card); int mmc_switch_status(struct mmc_card *card, bool crc_err_fatal); bool mmc_prepare_busy_cmd(struct mmc_host *host, struct mmc_command *cmd, unsigned int timeout_ms); -int __mmc_poll_for_busy(struct mmc_host *host, unsigned int timeout_ms, +int __mmc_poll_for_busy(struct mmc_host *host, unsigned int period_us, + unsigned int timeout_ms, int (*busy_cb)(void *cb_data, bool *busy), void *cb_data); int mmc_poll_for_busy(struct mmc_card *card, unsigned int timeout_ms, diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c index bd87012c220c..bfbfed30dc4d 100644 --- a/drivers/mmc/core/sd.c +++ b/drivers/mmc/core/sd.c @@ -1672,7 +1672,7 @@ static int sd_poweroff_notify(struct mmc_card *card) cb_data.card = card; cb_data.reg_buf = reg_buf; - err = __mmc_poll_for_busy(card->host, SD_POWEROFF_NOTIFY_TIMEOUT_MS, + err = __mmc_poll_for_busy(card->host, 0, SD_POWEROFF_NOTIFY_TIMEOUT_MS, &sd_busy_poweroff_notify_cb, &cb_data); out: diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index 8f36536cb1b6..58ab9d90bc8b 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -173,6 +173,8 @@ struct meson_host { int irq; bool vqmmc_enabled; + bool needs_pre_post_req; + }; #define CMD_CFG_LENGTH_MASK GENMASK(8, 0) @@ -663,6 +665,8 @@ static void meson_mmc_request_done(struct mmc_host *mmc, struct meson_host *host = mmc_priv(mmc); host->cmd = NULL; + if (host->needs_pre_post_req) + meson_mmc_post_req(mmc, mrq, 0); mmc_request_done(host->mmc, mrq); } @@ -880,7 +884,7 @@ static int meson_mmc_validate_dram_access(struct mmc_host *mmc, struct mmc_data static void meson_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq) { struct meson_host *host = mmc_priv(mmc); - bool needs_pre_post_req = mrq->data && + host->needs_pre_post_req = mrq->data && !(mrq->data->host_cookie & SD_EMMC_PRE_REQ_DONE); /* @@ -896,22 +900,19 @@ static void meson_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq) } } - if (needs_pre_post_req) { + if (host->needs_pre_post_req) { meson_mmc_get_transfer_mode(mmc, mrq); if (!meson_mmc_desc_chain_mode(mrq->data)) - needs_pre_post_req = false; + host->needs_pre_post_req = false; } - if (needs_pre_post_req) + if (host->needs_pre_post_req) meson_mmc_pre_req(mmc, mrq); /* Stop execution */ writel(0, host->regs + SD_EMMC_START); meson_mmc_start_cmd(mmc, mrq->sbc ?: mrq->cmd); - - if (needs_pre_post_req) - meson_mmc_post_req(mmc, mrq, 0); } static void meson_mmc_read_resp(struct mmc_host *mmc, struct mmc_command *cmd) diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c index 70f492dce158..eef87b28d6c8 100644 --- a/drivers/mtd/mtdcore.c +++ b/drivers/mtd/mtdcore.c @@ -546,6 +546,7 @@ static int mtd_nvmem_add(struct mtd_info *mtd) config.stride = 1; config.read_only = true; config.root_only = true; + config.ignore_wp = true; config.no_of_node = !of_device_is_compatible(node, "nvmem-cells"); config.priv = mtd; @@ -833,6 +834,7 @@ static struct nvmem_device *mtd_otp_nvmem_register(struct mtd_info *mtd, config.owner = THIS_MODULE; config.type = NVMEM_TYPE_OTP; config.root_only = true; + config.ignore_wp = true; config.reg_read = reg_read; config.size = size; config.of_node = np; 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/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 6382e1937cca..c580acb8b1d3 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -138,6 +138,9 @@ static int com20020pci_probe(struct pci_dev *pdev, return -ENOMEM; ci = (struct com20020_pci_card_info *)id->driver_data; + if (!ci) + return -EINVAL; + priv->ci = ci; mm = &ci->misc_map; diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index b7dc1c32875f..acd74725831f 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1715,15 +1715,15 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch, netif_napi_add(ndev, &priv->napi, rcar_canfd_rx_poll, RCANFD_NAPI_WEIGHT); + spin_lock_init(&priv->tx_lock); + devm_can_led_init(ndev); + gpriv->ch[priv->channel] = priv; err = register_candev(ndev); if (err) { dev_err(&pdev->dev, "register_candev() failed, error %d\n", err); goto fail_candev; } - spin_lock_init(&priv->tx_lock); - devm_can_led_init(ndev); - gpriv->ch[priv->channel] = priv; dev_info(&pdev->dev, "device registered (channel %u)\n", priv->channel); return 0; diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index 2ed2370a3166..2d73ebbf3836 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1787,7 +1787,7 @@ static int es58x_open(struct net_device *netdev) struct es58x_device *es58x_dev = es58x_priv(netdev)->es58x_dev; int ret; - if (atomic_inc_return(&es58x_dev->opened_channel_cnt) == 1) { + if (!es58x_dev->opened_channel_cnt) { ret = es58x_alloc_rx_urbs(es58x_dev); if (ret) return ret; @@ -1805,12 +1805,13 @@ static int es58x_open(struct net_device *netdev) if (ret) goto free_urbs; + es58x_dev->opened_channel_cnt++; netif_start_queue(netdev); return ret; free_urbs: - if (atomic_dec_and_test(&es58x_dev->opened_channel_cnt)) + if (!es58x_dev->opened_channel_cnt) es58x_free_urbs(es58x_dev); netdev_err(netdev, "%s: Could not open the network device: %pe\n", __func__, ERR_PTR(ret)); @@ -1845,7 +1846,8 @@ static int es58x_stop(struct net_device *netdev) es58x_flush_pending_tx_msg(netdev); - if (atomic_dec_and_test(&es58x_dev->opened_channel_cnt)) + es58x_dev->opened_channel_cnt--; + if (!es58x_dev->opened_channel_cnt) es58x_free_urbs(es58x_dev); return 0; @@ -2215,7 +2217,6 @@ static struct es58x_device *es58x_init_es58x_dev(struct usb_interface *intf, init_usb_anchor(&es58x_dev->tx_urbs_idle); init_usb_anchor(&es58x_dev->tx_urbs_busy); atomic_set(&es58x_dev->tx_urbs_idle_cnt, 0); - atomic_set(&es58x_dev->opened_channel_cnt, 0); usb_set_intfdata(intf, es58x_dev); es58x_dev->rx_pipe = usb_rcvbulkpipe(es58x_dev->udev, diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.h b/drivers/net/can/usb/etas_es58x/es58x_core.h index 826a15871573..e5033cb5e695 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.h +++ b/drivers/net/can/usb/etas_es58x/es58x_core.h @@ -373,8 +373,6 @@ struct es58x_operators { * queue wake/stop logic should prevent this URB from getting * empty. Please refer to es58x_get_tx_urb() for more details. * @tx_urbs_idle_cnt: number of urbs in @tx_urbs_idle. - * @opened_channel_cnt: number of channels opened (c.f. es58x_open() - * and es58x_stop()). * @ktime_req_ns: kernel timestamp when es58x_set_realtime_diff_ns() * was called. * @realtime_diff_ns: difference in nanoseconds between the clocks of @@ -384,6 +382,10 @@ struct es58x_operators { * in RX branches. * @rx_max_packet_size: Maximum length of bulk-in URB. * @num_can_ch: Number of CAN channel (i.e. number of elements of @netdev). + * @opened_channel_cnt: number of channels opened. Free of race + * conditions because its two users (net_device_ops:ndo_open() + * and net_device_ops:ndo_close()) guarantee that the network + * stack big kernel lock (a.k.a. rtnl_mutex) is being hold. * @rx_cmd_buf_len: Length of @rx_cmd_buf. * @rx_cmd_buf: The device might split the URB commands in an * arbitrary amount of pieces. This buffer is used to concatenate @@ -406,7 +408,6 @@ struct es58x_device { struct usb_anchor tx_urbs_busy; struct usb_anchor tx_urbs_idle; atomic_t tx_urbs_idle_cnt; - atomic_t opened_channel_cnt; u64 ktime_req_ns; s64 realtime_diff_ns; @@ -415,6 +416,7 @@ struct es58x_device { u16 rx_max_packet_size; u8 num_can_ch; + u8 opened_channel_cnt; u16 rx_cmd_buf_len; union es58x_urb_cmd rx_cmd_buf; diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index b487e3fe770a..d35749fad1ef 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -191,8 +191,8 @@ struct gs_can { struct gs_usb { struct gs_can *canch[GS_MAX_INTF]; struct usb_anchor rx_submitted; - atomic_t active_channels; struct usb_device *udev; + u8 active_channels; }; /* 'allocate' a tx context. @@ -589,7 +589,7 @@ static int gs_can_open(struct net_device *netdev) if (rc) return rc; - if (atomic_add_return(1, &parent->active_channels) == 1) { + if (!parent->active_channels) { for (i = 0; i < GS_MAX_RX_URBS; i++) { struct urb *urb; u8 *buf; @@ -690,6 +690,7 @@ static int gs_can_open(struct net_device *netdev) dev->can.state = CAN_STATE_ERROR_ACTIVE; + parent->active_channels++; if (!(dev->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)) netif_start_queue(netdev); @@ -705,7 +706,8 @@ static int gs_can_close(struct net_device *netdev) netif_stop_queue(netdev); /* Stop polling */ - if (atomic_dec_and_test(&parent->active_channels)) + parent->active_channels--; + if (!parent->active_channels) usb_kill_anchored_urbs(&parent->rx_submitted); /* Stop sending URBs */ @@ -984,8 +986,6 @@ static int gs_usb_probe(struct usb_interface *intf, init_usb_anchor(&dev->rx_submitted); - atomic_set(&dev->active_channels, 0); - usb_set_intfdata(intf, dev); dev->udev = interface_to_usbdev(intf); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 55dbda04ea62..243f8ad6d06e 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -26,7 +26,7 @@ void ksz_update_port_member(struct ksz_device *dev, int port) struct dsa_switch *ds = dev->ds; u8 port_member = 0, cpu_port; const struct dsa_port *dp; - int i; + int i, j; if (!dsa_is_user_port(ds, port)) return; @@ -45,13 +45,33 @@ void ksz_update_port_member(struct ksz_device *dev, int port) continue; if (!dsa_port_bridge_same(dp, other_dp)) continue; + if (other_p->stp_state != BR_STATE_FORWARDING) + continue; - if (other_p->stp_state == BR_STATE_FORWARDING && - p->stp_state == BR_STATE_FORWARDING) { + if (p->stp_state == BR_STATE_FORWARDING) { val |= BIT(port); port_member |= BIT(i); } + /* Retain port [i]'s relationship to other ports than [port] */ + for (j = 0; j < ds->num_ports; j++) { + const struct dsa_port *third_dp; + struct ksz_port *third_p; + + if (j == i) + continue; + if (j == port) + continue; + if (!dsa_is_user_port(ds, j)) + continue; + third_p = &dev->ports[j]; + if (third_p->stp_state != BR_STATE_FORWARDING) + continue; + third_dp = dsa_to_port(ds, j); + if (dsa_port_bridge_same(other_dp, third_dp)) + val |= BIT(j); + } + dev->dev_ops->cfg_port_member(dev, i, val | cpu_port); } diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index ff3c267d0f26..a251bc55727f 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2936,7 +2936,7 @@ 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/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index e20aafeb4ca9..b97ed9b5f685 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -8216,7 +8216,7 @@ bnx2_init_board(struct pci_dev *pdev, struct net_device *dev) rc = dma_set_coherent_mask(&pdev->dev, persist_dma_mask); if (rc) { dev_err(&pdev->dev, - "pci_set_consistent_dma_mask failed, aborting\n"); + "dma_set_coherent_mask failed, aborting\n"); goto err_out_unmap; } } else if ((rc = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32))) != 0) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 774c1f1a57c3..eedb48d945ed 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -100,6 +100,9 @@ MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FW_FILE_NAME_E1); MODULE_FIRMWARE(FW_FILE_NAME_E1H); MODULE_FIRMWARE(FW_FILE_NAME_E2); +MODULE_FIRMWARE(FW_FILE_NAME_E1_V15); +MODULE_FIRMWARE(FW_FILE_NAME_E1H_V15); +MODULE_FIRMWARE(FW_FILE_NAME_E2_V15); int bnx2x_num_queues; module_param_named(num_queues, bnx2x_num_queues, int, 0444); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 4f94136a011a..b1c98d1408b8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4747,8 +4747,10 @@ static int bnxt_hwrm_cfa_l2_set_rx_mask(struct bnxt *bp, u16 vnic_id) return rc; req->vnic_id = cpu_to_le32(vnic->fw_vnic_id); - req->num_mc_entries = cpu_to_le32(vnic->mc_list_count); - req->mc_tbl_addr = cpu_to_le64(vnic->mc_list_mapping); + if (vnic->rx_mask & CFA_L2_SET_RX_MASK_REQ_MASK_MCAST) { + req->num_mc_entries = cpu_to_le32(vnic->mc_list_count); + req->mc_tbl_addr = cpu_to_le64(vnic->mc_list_mapping); + } req->mask = cpu_to_le32(vnic->rx_mask); return hwrm_req_send_silent(bp, req); } @@ -7787,6 +7789,19 @@ static int bnxt_map_fw_health_regs(struct bnxt *bp) return 0; } +static void bnxt_remap_fw_health_regs(struct bnxt *bp) +{ + if (!bp->fw_health) + return; + + if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) { + bp->fw_health->status_reliable = true; + bp->fw_health->resets_reliable = true; + } else { + bnxt_try_map_fw_health_reg(bp); + } +} + static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp) { struct bnxt_fw_health *fw_health = bp->fw_health; @@ -8639,6 +8654,9 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) vnic->uc_filter_count = 1; vnic->rx_mask = 0; + if (test_bit(BNXT_STATE_HALF_OPEN, &bp->state)) + goto skip_rx_mask; + if (bp->dev->flags & IFF_BROADCAST) vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST; @@ -8648,7 +8666,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) if (bp->dev->flags & IFF_ALLMULTI) { vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST; vnic->mc_list_count = 0; - } else { + } else if (bp->dev->flags & IFF_MULTICAST) { u32 mask = 0; bnxt_mc_list_updated(bp, &mask); @@ -8659,6 +8677,7 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init) if (rc) goto err_out; +skip_rx_mask: rc = bnxt_hwrm_set_coal(bp); if (rc) netdev_warn(bp->dev, "HWRM set coalescing failure rc: %x\n", @@ -9850,8 +9869,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) resc_reinit = true; if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE) fw_reset = true; - else if (bp->fw_health && !bp->fw_health->status_reliable) - bnxt_try_map_fw_health_reg(bp); + else + bnxt_remap_fw_health_regs(bp); if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) && !fw_reset) { netdev_err(bp->dev, "RESET_DONE not set during FW reset.\n"); @@ -10330,13 +10349,15 @@ int bnxt_half_open_nic(struct bnxt *bp) goto half_open_err; } - rc = bnxt_alloc_mem(bp, false); + rc = bnxt_alloc_mem(bp, true); if (rc) { netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc); goto half_open_err; } - rc = bnxt_init_nic(bp, false); + set_bit(BNXT_STATE_HALF_OPEN, &bp->state); + rc = bnxt_init_nic(bp, true); if (rc) { + clear_bit(BNXT_STATE_HALF_OPEN, &bp->state); netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); goto half_open_err; } @@ -10344,7 +10365,7 @@ int bnxt_half_open_nic(struct bnxt *bp) half_open_err: bnxt_free_skbs(bp); - bnxt_free_mem(bp, false); + bnxt_free_mem(bp, true); dev_close(bp->dev); return rc; } @@ -10354,9 +10375,10 @@ half_open_err: */ void bnxt_half_close_nic(struct bnxt *bp) { - bnxt_hwrm_resource_free(bp, false, false); + bnxt_hwrm_resource_free(bp, false, true); bnxt_free_skbs(bp); - bnxt_free_mem(bp, false); + bnxt_free_mem(bp, true); + clear_bit(BNXT_STATE_HALF_OPEN, &bp->state); } void bnxt_reenable_sriov(struct bnxt *bp) @@ -10772,7 +10794,7 @@ static void bnxt_set_rx_mode(struct net_device *dev) if (dev->flags & IFF_ALLMULTI) { mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST; vnic->mc_list_count = 0; - } else { + } else if (dev->flags & IFF_MULTICAST) { mc_update = bnxt_mc_list_updated(bp, &mask); } @@ -10849,9 +10871,10 @@ skip_uc: !bnxt_promisc_ok(bp)) vnic->rx_mask &= ~CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS; rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0); - if (rc && vnic->mc_list_count) { + if (rc && (vnic->rx_mask & CFA_L2_SET_RX_MASK_REQ_MASK_MCAST)) { netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n", rc); + vnic->rx_mask &= ~CFA_L2_SET_RX_MASK_REQ_MASK_MCAST; vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST; vnic->mc_list_count = 0; rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 440dfeb4948b..666fc1e7a7d2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1921,6 +1921,7 @@ struct bnxt { #define BNXT_STATE_RECOVER 12 #define BNXT_STATE_FW_NON_FATAL_COND 13 #define BNXT_STATE_FW_ACTIVATE_RESET 14 +#define BNXT_STATE_HALF_OPEN 15 /* For offline ethtool tests */ #define BNXT_NO_FW_ACCESS(bp) \ (test_bit(BNXT_STATE_FW_FATAL_COND, &(bp)->state) || \ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 4da31b1b84f9..f6e21fac0e69 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -367,6 +367,16 @@ bnxt_dl_livepatch_report_err(struct bnxt *bp, struct netlink_ext_ack *extack, } } +/* Live patch status in NVM */ +#define BNXT_LIVEPATCH_NOT_INSTALLED 0 +#define BNXT_LIVEPATCH_INSTALLED FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL +#define BNXT_LIVEPATCH_REMOVED FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE +#define BNXT_LIVEPATCH_MASK (FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL | \ + FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE) +#define BNXT_LIVEPATCH_ACTIVATED BNXT_LIVEPATCH_MASK + +#define BNXT_LIVEPATCH_STATE(flags) ((flags) & BNXT_LIVEPATCH_MASK) + static int bnxt_dl_livepatch_activate(struct bnxt *bp, struct netlink_ext_ack *extack) { @@ -374,8 +384,9 @@ bnxt_dl_livepatch_activate(struct bnxt *bp, struct netlink_ext_ack *extack) struct hwrm_fw_livepatch_query_input *query_req; struct hwrm_fw_livepatch_output *patch_resp; struct hwrm_fw_livepatch_input *patch_req; + u16 flags, live_patch_state; + bool activated = false; u32 installed = 0; - u16 flags; u8 target; int rc; @@ -394,7 +405,6 @@ bnxt_dl_livepatch_activate(struct bnxt *bp, struct netlink_ext_ack *extack) hwrm_req_drop(bp, query_req); return rc; } - patch_req->opcode = FW_LIVEPATCH_REQ_OPCODE_ACTIVATE; patch_req->loadtype = FW_LIVEPATCH_REQ_LOADTYPE_NVM_INSTALL; patch_resp = hwrm_req_hold(bp, patch_req); @@ -407,12 +417,20 @@ bnxt_dl_livepatch_activate(struct bnxt *bp, struct netlink_ext_ack *extack) } flags = le16_to_cpu(query_resp->status_flags); - if (~flags & FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL) + live_patch_state = BNXT_LIVEPATCH_STATE(flags); + + if (live_patch_state == BNXT_LIVEPATCH_NOT_INSTALLED) continue; - if ((flags & FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE) && - !strncmp(query_resp->active_ver, query_resp->install_ver, - sizeof(query_resp->active_ver))) + + if (live_patch_state == BNXT_LIVEPATCH_ACTIVATED) { + activated = true; continue; + } + + if (live_patch_state == BNXT_LIVEPATCH_INSTALLED) + patch_req->opcode = FW_LIVEPATCH_REQ_OPCODE_ACTIVATE; + else if (live_patch_state == BNXT_LIVEPATCH_REMOVED) + patch_req->opcode = FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE; patch_req->fw_target = target; rc = hwrm_req_send(bp, patch_req); @@ -424,8 +442,13 @@ bnxt_dl_livepatch_activate(struct bnxt *bp, struct netlink_ext_ack *extack) } if (!rc && !installed) { - NL_SET_ERR_MSG_MOD(extack, "No live patches found"); - rc = -ENOENT; + if (activated) { + NL_SET_ERR_MSG_MOD(extack, "Live patch already activated"); + rc = -EEXIST; + } else { + NL_SET_ERR_MSG_MOD(extack, "No live patches found"); + rc = -ENOENT; + } } hwrm_req_drop(bp, query_req); hwrm_req_drop(bp, patch_req); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 003330e8cd58..8aaa2335f848 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -25,6 +25,7 @@ #include "bnxt_hsi.h" #include "bnxt.h" #include "bnxt_hwrm.h" +#include "bnxt_ulp.h" #include "bnxt_xdp.h" #include "bnxt_ptp.h" #include "bnxt_ethtool.h" @@ -1969,6 +1970,9 @@ static int bnxt_get_fecparam(struct net_device *dev, case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE: fec->active_fec |= ETHTOOL_FEC_LLRS; break; + case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE: + fec->active_fec |= ETHTOOL_FEC_OFF; + break; } return 0; } @@ -3454,7 +3458,7 @@ static int bnxt_run_loopback(struct bnxt *bp) if (!skb) return -ENOMEM; data = skb_put(skb, pkt_size); - eth_broadcast_addr(data); + ether_addr_copy(&data[i], bp->dev->dev_addr); i += ETH_ALEN; ether_addr_copy(&data[i], bp->dev->dev_addr); i += ETH_ALEN; @@ -3548,9 +3552,12 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, if (!offline) { bnxt_run_fw_tests(bp, test_mask, &test_results); } else { - rc = bnxt_close_nic(bp, false, false); - if (rc) + bnxt_ulp_stop(bp); + rc = bnxt_close_nic(bp, true, false); + if (rc) { + bnxt_ulp_start(bp, rc); return; + } bnxt_run_fw_tests(bp, test_mask, &test_results); buf[BNXT_MACLPBK_TEST_IDX] = 1; @@ -3560,6 +3567,7 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, if (rc) { bnxt_hwrm_mac_loopback(bp, false); etest->flags |= ETH_TEST_FL_FAILED; + bnxt_ulp_start(bp, rc); return; } if (bnxt_run_loopback(bp)) @@ -3585,7 +3593,8 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest, } bnxt_hwrm_phy_loopback(bp, false, false); bnxt_half_close_nic(bp); - rc = bnxt_open_nic(bp, false, true); + rc = bnxt_open_nic(bp, true, true); + bnxt_ulp_start(bp, rc); } if (rc || bnxt_test_irq(bp)) { buf[BNXT_IRQ_TEST_IDX] = 1; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c index 566c9487ef55..b01d42928a53 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c @@ -644,17 +644,23 @@ static int __hwrm_send(struct bnxt *bp, struct bnxt_hwrm_ctx *ctx) /* Last byte of resp contains valid bit */ valid = ((u8 *)ctx->resp) + len - 1; - for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) { + for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; ) { /* make sure we read from updated DMA memory */ dma_rmb(); if (*valid) break; - usleep_range(1, 5); + if (j < 10) { + udelay(1); + j++; + } else { + usleep_range(20, 30); + j += 20; + } } if (j >= HWRM_VALID_BIT_DELAY_USEC) { hwrm_err(bp, ctx, "Error (timeout: %u) msg {0x%x 0x%x} len:%d v:%d\n", - hwrm_total_timeout(i), req_type, + hwrm_total_timeout(i) + j, req_type, le16_to_cpu(ctx->req->seq_id), len, *valid); goto exit; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h index d52bd2d63aec..c98032e38188 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h @@ -90,7 +90,7 @@ static inline unsigned int hwrm_total_timeout(unsigned int n) } -#define HWRM_VALID_BIT_DELAY_USEC 150 +#define HWRM_VALID_BIT_DELAY_USEC 50000 static inline bool bnxt_cfa_hwrm_message(u16 req_type) { 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 98498a76ae16..d13f06cf0308 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1573,7 +1573,14 @@ 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) @@ -1581,6 +1588,22 @@ 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/chelsio/cxgb3/t3_hw.c b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c index da41eee2f25c..a06003bfa04b 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c @@ -3613,6 +3613,8 @@ int t3_prep_adapter(struct adapter *adapter, const struct adapter_info *ai, MAC_STATS_ACCUM_SECS : (MAC_STATS_ACCUM_SECS * 10); adapter->params.pci.vpd_cap_addr = pci_find_capability(adapter->pdev, PCI_CAP_ID_VPD); + if (!adapter->params.pci.vpd_cap_addr) + return -ENODEV; ret = get_vpd_params(adapter, &adapter->params.vpd); if (ret < 0) return ret; diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 691605c15265..d5356db7539a 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -989,117 +989,6 @@ static int ftgmac100_alloc_rx_buffers(struct ftgmac100 *priv) return 0; } -static void ftgmac100_adjust_link(struct net_device *netdev) -{ - struct ftgmac100 *priv = netdev_priv(netdev); - struct phy_device *phydev = netdev->phydev; - bool tx_pause, rx_pause; - int new_speed; - - /* We store "no link" as speed 0 */ - if (!phydev->link) - new_speed = 0; - else - new_speed = phydev->speed; - - /* Grab pause settings from PHY if configured to do so */ - if (priv->aneg_pause) { - rx_pause = tx_pause = phydev->pause; - if (phydev->asym_pause) - tx_pause = !rx_pause; - } else { - rx_pause = priv->rx_pause; - tx_pause = priv->tx_pause; - } - - /* Link hasn't changed, do nothing */ - if (phydev->speed == priv->cur_speed && - phydev->duplex == priv->cur_duplex && - rx_pause == priv->rx_pause && - tx_pause == priv->tx_pause) - return; - - /* Print status if we have a link or we had one and just lost it, - * don't print otherwise. - */ - if (new_speed || priv->cur_speed) - phy_print_status(phydev); - - priv->cur_speed = new_speed; - priv->cur_duplex = phydev->duplex; - priv->rx_pause = rx_pause; - priv->tx_pause = tx_pause; - - /* Link is down, do nothing else */ - if (!new_speed) - return; - - /* Disable all interrupts */ - iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); - - /* Reset the adapter asynchronously */ - schedule_work(&priv->reset_task); -} - -static int ftgmac100_mii_probe(struct net_device *netdev) -{ - struct ftgmac100 *priv = netdev_priv(netdev); - struct platform_device *pdev = to_platform_device(priv->dev); - struct device_node *np = pdev->dev.of_node; - struct phy_device *phydev; - phy_interface_t phy_intf; - int err; - - /* Default to RGMII. It's a gigabit part after all */ - err = of_get_phy_mode(np, &phy_intf); - if (err) - phy_intf = PHY_INTERFACE_MODE_RGMII; - - /* Aspeed only supports these. I don't know about other IP - * block vendors so I'm going to just let them through for - * now. Note that this is only a warning if for some obscure - * reason the DT really means to lie about it or it's a newer - * part we don't know about. - * - * On the Aspeed SoC there are additionally straps and SCU - * control bits that could tell us what the interface is - * (or allow us to configure it while the IP block is held - * in reset). For now I chose to keep this driver away from - * those SoC specific bits and assume the device-tree is - * right and the SCU has been configured properly by pinmux - * or the firmware. - */ - if (priv->is_aspeed && !(phy_interface_mode_is_rgmii(phy_intf))) { - netdev_warn(netdev, - "Unsupported PHY mode %s !\n", - phy_modes(phy_intf)); - } - - phydev = phy_find_first(priv->mii_bus); - if (!phydev) { - netdev_info(netdev, "%s: no PHY found\n", netdev->name); - return -ENODEV; - } - - phydev = phy_connect(netdev, phydev_name(phydev), - &ftgmac100_adjust_link, phy_intf); - - if (IS_ERR(phydev)) { - netdev_err(netdev, "%s: Could not attach to PHY\n", netdev->name); - return PTR_ERR(phydev); - } - - /* Indicate that we support PAUSE frames (see comment in - * Documentation/networking/phy.rst) - */ - phy_support_asym_pause(phydev); - - /* Display what we found */ - phy_attached_info(phydev); - - return 0; -} - static int ftgmac100_mdiobus_read(struct mii_bus *bus, int phy_addr, int regnum) { struct net_device *netdev = bus->priv; @@ -1410,10 +1299,8 @@ static int ftgmac100_init_all(struct ftgmac100 *priv, bool ignore_alloc_err) return err; } -static void ftgmac100_reset_task(struct work_struct *work) +static void ftgmac100_reset(struct ftgmac100 *priv) { - struct ftgmac100 *priv = container_of(work, struct ftgmac100, - reset_task); struct net_device *netdev = priv->netdev; int err; @@ -1459,6 +1346,134 @@ static void ftgmac100_reset_task(struct work_struct *work) rtnl_unlock(); } +static void ftgmac100_reset_task(struct work_struct *work) +{ + struct ftgmac100 *priv = container_of(work, struct ftgmac100, + reset_task); + + ftgmac100_reset(priv); +} + +static void ftgmac100_adjust_link(struct net_device *netdev) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + struct phy_device *phydev = netdev->phydev; + bool tx_pause, rx_pause; + int new_speed; + + /* We store "no link" as speed 0 */ + if (!phydev->link) + new_speed = 0; + else + new_speed = phydev->speed; + + /* Grab pause settings from PHY if configured to do so */ + if (priv->aneg_pause) { + rx_pause = tx_pause = phydev->pause; + if (phydev->asym_pause) + tx_pause = !rx_pause; + } else { + rx_pause = priv->rx_pause; + tx_pause = priv->tx_pause; + } + + /* Link hasn't changed, do nothing */ + if (phydev->speed == priv->cur_speed && + phydev->duplex == priv->cur_duplex && + rx_pause == priv->rx_pause && + tx_pause == priv->tx_pause) + return; + + /* Print status if we have a link or we had one and just lost it, + * don't print otherwise. + */ + if (new_speed || priv->cur_speed) + phy_print_status(phydev); + + priv->cur_speed = new_speed; + priv->cur_duplex = phydev->duplex; + priv->rx_pause = rx_pause; + priv->tx_pause = tx_pause; + + /* Link is down, do nothing else */ + if (!new_speed) + return; + + /* Disable all interrupts */ + iowrite32(0, priv->base + FTGMAC100_OFFSET_IER); + + /* Release phy lock to allow ftgmac100_reset to aquire it, keeping lock + * order consistent to prevent dead lock. + */ + if (netdev->phydev) + mutex_unlock(&netdev->phydev->lock); + + ftgmac100_reset(priv); + + if (netdev->phydev) + mutex_lock(&netdev->phydev->lock); + +} + +static int ftgmac100_mii_probe(struct net_device *netdev) +{ + struct ftgmac100 *priv = netdev_priv(netdev); + struct platform_device *pdev = to_platform_device(priv->dev); + struct device_node *np = pdev->dev.of_node; + struct phy_device *phydev; + phy_interface_t phy_intf; + int err; + + /* Default to RGMII. It's a gigabit part after all */ + err = of_get_phy_mode(np, &phy_intf); + if (err) + phy_intf = PHY_INTERFACE_MODE_RGMII; + + /* Aspeed only supports these. I don't know about other IP + * block vendors so I'm going to just let them through for + * now. Note that this is only a warning if for some obscure + * reason the DT really means to lie about it or it's a newer + * part we don't know about. + * + * On the Aspeed SoC there are additionally straps and SCU + * control bits that could tell us what the interface is + * (or allow us to configure it while the IP block is held + * in reset). For now I chose to keep this driver away from + * those SoC specific bits and assume the device-tree is + * right and the SCU has been configured properly by pinmux + * or the firmware. + */ + if (priv->is_aspeed && !(phy_interface_mode_is_rgmii(phy_intf))) { + netdev_warn(netdev, + "Unsupported PHY mode %s !\n", + phy_modes(phy_intf)); + } + + phydev = phy_find_first(priv->mii_bus); + if (!phydev) { + netdev_info(netdev, "%s: no PHY found\n", netdev->name); + return -ENODEV; + } + + phydev = phy_connect(netdev, phydev_name(phydev), + &ftgmac100_adjust_link, phy_intf); + + if (IS_ERR(phydev)) { + netdev_err(netdev, "%s: Could not attach to PHY\n", netdev->name); + return PTR_ERR(phydev); + } + + /* Indicate that we support PAUSE frames (see comment in + * Documentation/networking/phy.rst) + */ + phy_support_asym_pause(phydev); + + /* Display what we found */ + phy_attached_info(phydev); + + return 0; +} + static int ftgmac100_open(struct net_device *netdev) { struct ftgmac100 *priv = netdev_priv(netdev); 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/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 29617a86b299..b423e94956f1 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2213,6 +2213,19 @@ static const char *reset_reason_to_string(enum ibmvnic_reset_reason reason) } /* + * Initialize the init_done completion and return code values. We + * can get a transport event just after registering the CRQ and the + * tasklet will use this to communicate the transport event. To ensure + * we don't miss the notification/error, initialize these _before_ + * regisering the CRQ. + */ +static inline void reinit_init_done(struct ibmvnic_adapter *adapter) +{ + reinit_completion(&adapter->init_done); + adapter->init_done_rc = 0; +} + +/* * do_reset returns zero if we are able to keep processing reset events, or * non-zero if we hit a fatal error and must halt. */ @@ -2318,6 +2331,8 @@ static int do_reset(struct ibmvnic_adapter *adapter, */ adapter->state = VNIC_PROBED; + reinit_init_done(adapter); + if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM) { rc = init_crq_queue(adapter); } else if (adapter->reset_reason == VNIC_RESET_MOBILITY) { @@ -2461,7 +2476,8 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter, */ adapter->state = VNIC_PROBED; - reinit_completion(&adapter->init_done); + reinit_init_done(adapter); + rc = init_crq_queue(adapter); if (rc) { netdev_err(adapter->netdev, @@ -2602,23 +2618,82 @@ out: static void __ibmvnic_reset(struct work_struct *work) { struct ibmvnic_adapter *adapter; - bool saved_state = false; + unsigned int timeout = 5000; struct ibmvnic_rwi *tmprwi; + bool saved_state = false; struct ibmvnic_rwi *rwi; unsigned long flags; - u32 reset_state; + struct device *dev; + bool need_reset; int num_fails = 0; + u32 reset_state; int rc = 0; adapter = container_of(work, struct ibmvnic_adapter, ibmvnic_reset); + dev = &adapter->vdev->dev; - if (test_and_set_bit_lock(0, &adapter->resetting)) { + /* Wait for ibmvnic_probe() to complete. If probe is taking too long + * or if another reset is in progress, defer work for now. If probe + * eventually fails it will flush and terminate our work. + * + * Three possibilities here: + * 1. Adpater being removed - just return + * 2. Timed out on probe or another reset in progress - delay the work + * 3. Completed probe - perform any resets in queue + */ + if (adapter->state == VNIC_PROBING && + !wait_for_completion_timeout(&adapter->probe_done, timeout)) { + dev_err(dev, "Reset thread timed out on probe"); queue_delayed_work(system_long_wq, &adapter->ibmvnic_delayed_reset, IBMVNIC_RESET_DELAY); return; } + /* adapter is done with probe (i.e state is never VNIC_PROBING now) */ + if (adapter->state == VNIC_REMOVING) + return; + + /* ->rwi_list is stable now (no one else is removing entries) */ + + /* ibmvnic_probe() may have purged the reset queue after we were + * scheduled to process a reset so there maybe no resets to process. + * Before setting the ->resetting bit though, we have to make sure + * that there is infact a reset to process. Otherwise we may race + * with ibmvnic_open() and end up leaving the vnic down: + * + * __ibmvnic_reset() ibmvnic_open() + * ----------------- -------------- + * + * set ->resetting bit + * find ->resetting bit is set + * set ->state to IBMVNIC_OPEN (i.e + * assume reset will open device) + * return + * find reset queue empty + * return + * + * Neither performed vnic login/open and vnic stays down + * + * If we hold the lock and conditionally set the bit, either we + * or ibmvnic_open() will complete the open. + */ + need_reset = false; + spin_lock(&adapter->rwi_lock); + if (!list_empty(&adapter->rwi_list)) { + if (test_and_set_bit_lock(0, &adapter->resetting)) { + queue_delayed_work(system_long_wq, + &adapter->ibmvnic_delayed_reset, + IBMVNIC_RESET_DELAY); + } else { + need_reset = true; + } + } + spin_unlock(&adapter->rwi_lock); + + if (!need_reset) + return; + rwi = get_next_rwi(adapter); while (rwi) { spin_lock_irqsave(&adapter->state_lock, flags); @@ -2735,12 +2810,23 @@ static void __ibmvnic_delayed_reset(struct work_struct *work) __ibmvnic_reset(&adapter->ibmvnic_reset); } +static void flush_reset_queue(struct ibmvnic_adapter *adapter) +{ + struct list_head *entry, *tmp_entry; + + if (!list_empty(&adapter->rwi_list)) { + list_for_each_safe(entry, tmp_entry, &adapter->rwi_list) { + list_del(entry); + kfree(list_entry(entry, struct ibmvnic_rwi, list)); + } + } +} + static int ibmvnic_reset(struct ibmvnic_adapter *adapter, enum ibmvnic_reset_reason reason) { - struct list_head *entry, *tmp_entry; - struct ibmvnic_rwi *rwi, *tmp; struct net_device *netdev = adapter->netdev; + struct ibmvnic_rwi *rwi, *tmp; unsigned long flags; int ret; @@ -2759,13 +2845,6 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, goto err; } - if (adapter->state == VNIC_PROBING) { - netdev_warn(netdev, "Adapter reset during probe\n"); - adapter->init_done_rc = -EAGAIN; - ret = EAGAIN; - goto err; - } - list_for_each_entry(tmp, &adapter->rwi_list, list) { if (tmp->reset_reason == reason) { netdev_dbg(netdev, "Skipping matching reset, reason=%s\n", @@ -2783,10 +2862,9 @@ static int ibmvnic_reset(struct ibmvnic_adapter *adapter, /* if we just received a transport event, * flush reset queue and process this reset */ - if (adapter->force_reset_recovery && !list_empty(&adapter->rwi_list)) { - list_for_each_safe(entry, tmp_entry, &adapter->rwi_list) - list_del(entry); - } + if (adapter->force_reset_recovery) + flush_reset_queue(adapter); + rwi->reset_reason = reason; list_add_tail(&rwi->list, &adapter->rwi_list); netdev_dbg(adapter->netdev, "Scheduling reset (reason %s)\n", @@ -5321,9 +5399,9 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, } if (!completion_done(&adapter->init_done)) { - complete(&adapter->init_done); if (!adapter->init_done_rc) adapter->init_done_rc = -EAGAIN; + complete(&adapter->init_done); } break; @@ -5346,6 +5424,13 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq, adapter->fw_done_rc = -EIO; complete(&adapter->fw_done); } + + /* if we got here during crq-init, retry crq-init */ + if (!completion_done(&adapter->init_done)) { + adapter->init_done_rc = -EAGAIN; + complete(&adapter->init_done); + } + if (!completion_done(&adapter->stats_done)) complete(&adapter->stats_done); if (test_bit(0, &adapter->resetting)) @@ -5662,10 +5747,6 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset) adapter->from_passive_init = false; - if (reset) - reinit_completion(&adapter->init_done); - - adapter->init_done_rc = 0; rc = ibmvnic_send_crq_init(adapter); if (rc) { dev_err(dev, "Send crq init failed with error %d\n", rc); @@ -5679,12 +5760,14 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset) if (adapter->init_done_rc) { release_crq_queue(adapter); + dev_err(dev, "CRQ-init failed, %d\n", adapter->init_done_rc); return adapter->init_done_rc; } if (adapter->from_passive_init) { adapter->state = VNIC_OPEN; adapter->from_passive_init = false; + dev_err(dev, "CRQ-init failed, passive-init\n"); return -EINVAL; } @@ -5724,6 +5807,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) struct ibmvnic_adapter *adapter; struct net_device *netdev; unsigned char *mac_addr_p; + unsigned long flags; bool init_success; int rc; @@ -5768,6 +5852,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) spin_lock_init(&adapter->rwi_lock); spin_lock_init(&adapter->state_lock); mutex_init(&adapter->fw_lock); + init_completion(&adapter->probe_done); init_completion(&adapter->init_done); init_completion(&adapter->fw_done); init_completion(&adapter->reset_done); @@ -5778,6 +5863,33 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) init_success = false; do { + reinit_init_done(adapter); + + /* clear any failovers we got in the previous pass + * since we are reinitializing the CRQ + */ + adapter->failover_pending = false; + + /* If we had already initialized CRQ, we may have one or + * more resets queued already. Discard those and release + * the CRQ before initializing the CRQ again. + */ + release_crq_queue(adapter); + + /* Since we are still in PROBING state, __ibmvnic_reset() + * will not access the ->rwi_list and since we released CRQ, + * we won't get _new_ transport events. But there maybe an + * ongoing ibmvnic_reset() call. So serialize access to + * rwi_list. If we win the race, ibvmnic_reset() could add + * a reset after we purged but thats ok - we just may end + * up with an extra reset (i.e similar to having two or more + * resets in the queue at once). + * CHECK. + */ + spin_lock_irqsave(&adapter->rwi_lock, flags); + flush_reset_queue(adapter); + spin_unlock_irqrestore(&adapter->rwi_lock, flags); + rc = init_crq_queue(adapter); if (rc) { dev_err(&dev->dev, "Couldn't initialize crq. rc=%d\n", @@ -5809,12 +5921,6 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) goto ibmvnic_dev_file_err; netif_carrier_off(netdev); - rc = register_netdev(netdev); - if (rc) { - dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); - goto ibmvnic_register_fail; - } - dev_info(&dev->dev, "ibmvnic registered\n"); if (init_success) { adapter->state = VNIC_PROBED; @@ -5827,6 +5933,16 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id) adapter->wait_for_reset = false; adapter->last_reset_time = jiffies; + + rc = register_netdev(netdev); + if (rc) { + dev_err(&dev->dev, "failed to register netdev rc=%d\n", rc); + goto ibmvnic_register_fail; + } + dev_info(&dev->dev, "ibmvnic registered\n"); + + complete(&adapter->probe_done); + return 0; ibmvnic_register_fail: @@ -5841,6 +5957,17 @@ ibmvnic_stats_fail: ibmvnic_init_fail: release_sub_crqs(adapter, 1); release_crq_queue(adapter); + + /* cleanup worker thread after releasing CRQ so we don't get + * transport events (i.e new work items for the worker thread). + */ + adapter->state = VNIC_REMOVING; + complete(&adapter->probe_done); + flush_work(&adapter->ibmvnic_reset); + flush_delayed_work(&adapter->ibmvnic_delayed_reset); + + flush_reset_queue(adapter); + mutex_destroy(&adapter->fw_lock); free_netdev(netdev); @@ -5917,10 +6044,14 @@ static ssize_t failover_store(struct device *dev, struct device_attribute *attr, be64_to_cpu(session_token)); rc = plpar_hcall_norets(H_VIOCTL, adapter->vdev->unit_address, H_SESSION_ERR_DETECTED, session_token, 0, 0); - if (rc) + if (rc) { netdev_err(netdev, "H_VIOCTL initiated failover failed, rc %ld\n", rc); + goto last_resort; + } + + return count; last_resort: netdev_dbg(netdev, "Trying to send CRQ_CMD, the last resort\n"); diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h index 4a7a56ff74ce..fa2d607a7b1b 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.h +++ b/drivers/net/ethernet/ibm/ibmvnic.h @@ -930,6 +930,7 @@ struct ibmvnic_adapter { struct ibmvnic_tx_pool *tx_pool; struct ibmvnic_tx_pool *tso_pool; + struct completion probe_done; struct completion init_done; int init_done_rc; diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index bcf680e83811..13382df2f2ef 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -630,6 +630,7 @@ struct e1000_phy_info { bool disable_polarity_correction; bool is_mdix; bool polarity_correction; + bool reset_disable; bool speed_downgraded; bool autoneg_wait_to_complete; }; diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index c908c84b86d2..d60e2016d03c 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -2050,6 +2050,10 @@ static s32 e1000_check_reset_block_ich8lan(struct e1000_hw *hw) bool blocked = false; int i = 0; + /* Check the PHY (LCD) reset flag */ + if (hw->phy.reset_disable) + return true; + while ((blocked = !(er32(FWSM) & E1000_ICH_FWSM_RSPCIPHY)) && (i++ < 30)) usleep_range(10000, 11000); @@ -4136,9 +4140,9 @@ static s32 e1000_validate_nvm_checksum_ich8lan(struct e1000_hw *hw) return ret_val; if (!(data & valid_csum_mask)) { - e_dbg("NVM Checksum Invalid\n"); + e_dbg("NVM Checksum valid bit not set\n"); - if (hw->mac.type < e1000_pch_cnp) { + if (hw->mac.type < e1000_pch_tgp) { data |= valid_csum_mask; ret_val = e1000_write_nvm(hw, word, 1, &data); if (ret_val) diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 2504b11c3169..638a3ddd7ada 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -271,6 +271,7 @@ #define I217_CGFREG_ENABLE_MTA_RESET 0x0002 #define I217_MEMPWR PHY_REG(772, 26) #define I217_MEMPWR_DISABLE_SMB_RELEASE 0x0010 +#define I217_MEMPWR_MOEM 0x1000 /* Receive Address Initial CRC Calculation */ #define E1000_PCH_RAICC(_n) (0x05F50 + ((_n) * 4)) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index a42aeb555f34..c5bdef3ffe26 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6987,8 +6987,21 @@ static __maybe_unused int e1000e_pm_suspend(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); + struct e1000_hw *hw = &adapter->hw; + u16 phy_data; int rc; + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { + /* Mask OEM Bits / Gig Disable / Restart AN (772_26[12] = 1) */ + e1e_rphy(hw, I217_MEMPWR, &phy_data); + phy_data |= I217_MEMPWR_MOEM; + e1e_wphy(hw, I217_MEMPWR, phy_data); + + /* Disable LCD reset */ + hw->phy.reset_disable = true; + } + e1000e_flush_lpic(pdev); e1000e_pm_freeze(dev); @@ -7010,6 +7023,8 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev) struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); struct e1000_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = to_pci_dev(dev); + struct e1000_hw *hw = &adapter->hw; + u16 phy_data; int rc; /* Introduce S0ix implementation */ @@ -7020,6 +7035,17 @@ static __maybe_unused int e1000e_pm_resume(struct device *dev) if (rc) return rc; + if (er32(FWSM) & E1000_ICH_FWSM_FW_VALID && + hw->mac.type >= e1000_pch_adp) { + /* Unmask OEM Bits / Gig Disable / Restart AN 772_26[12] = 0 */ + e1e_rphy(hw, I217_MEMPWR, &phy_data); + phy_data &= ~I217_MEMPWR_MOEM; + e1e_wphy(hw, I217_MEMPWR, phy_data); + + /* Enable LCD reset */ + hw->phy.reset_disable = false; + } + return e1000e_pm_thaw(dev); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 1e57cc8c47d7..9db5001297c7 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -742,10 +742,8 @@ 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_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 0c4b7dfb3b35..31b03fe78d3b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -5372,15 +5372,7 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, /* There is no need to reset BW when mqprio mode is on. */ if (pf->flags & I40E_FLAG_TC_MQPRIO) return 0; - - if (!vsi->mqprio_qopt.qopt.hw) { - if (pf->flags & I40E_FLAG_DCB_ENABLED) - goto skip_reset; - - if (IS_ENABLED(CONFIG_I40E_DCB) && - i40e_dcb_hw_get_num_tc(&pf->hw) == 1) - goto skip_reset; - + if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) { ret = i40e_set_bw_limit(vsi, vsi->seid, 0); if (ret) dev_info(&pf->pdev->dev, @@ -5388,8 +5380,6 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, vsi->seid); return ret; } - -skip_reset: memset(&bw_data, 0, sizeof(bw_data)); bw_data.tc_valid_bits = enabled_tc; for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) 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 59806d1f7e79..4babe4705a55 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -201,6 +201,10 @@ enum iavf_state_t { __IAVF_RUNNING, /* opened, working */ }; +enum iavf_critical_section_t { + __IAVF_IN_REMOVE_TASK, /* device being removed */ +}; + #define IAVF_CLOUD_FIELD_OMAC 0x01 #define IAVF_CLOUD_FIELD_IMAC 0x02 #define IAVF_CLOUD_FIELD_IVLAN 0x04 @@ -246,7 +250,6 @@ struct iavf_adapter { struct list_head mac_filter_list; struct mutex crit_lock; struct mutex client_lock; - struct mutex remove_lock; /* Lock to protect accesses to MAC and VLAN lists */ spinlock_t mac_vlan_list_lock; char misc_vector_name[IFNAMSIZ + 9]; @@ -284,6 +287,8 @@ struct iavf_adapter { #define IAVF_FLAG_LEGACY_RX BIT(15) #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 8125b9120615..8e644e9ed8da 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -302,8 +302,9 @@ static irqreturn_t iavf_msix_aq(int irq, void *data) rd32(hw, IAVF_VFINT_ICR01); rd32(hw, IAVF_VFINT_ICR0_ENA1); - /* schedule work on the private workqueue */ - queue_work(iavf_wq, &adapter->adminq_task); + if (adapter->state != __IAVF_REMOVE) + /* schedule work on the private workqueue */ + queue_work(iavf_wq, &adapter->adminq_task); return IRQ_HANDLED; } @@ -1136,8 +1137,7 @@ void iavf_down(struct iavf_adapter *adapter) rss->state = IAVF_ADV_RSS_DEL_REQUEST; spin_unlock_bh(&adapter->adv_rss_lock); - if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && - adapter->state != __IAVF_RESETTING) { + if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)) { /* cancel any current operation */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; /* Schedule operations to close down the HW. Don't wait @@ -2120,7 +2120,7 @@ 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); @@ -2374,17 +2374,22 @@ static void iavf_watchdog_task(struct work_struct *work) struct iavf_hw *hw = &adapter->hw; u32 reg_val; - if (!mutex_trylock(&adapter->crit_lock)) + if (!mutex_trylock(&adapter->crit_lock)) { + if (adapter->state == __IAVF_REMOVE) + return; + goto restart_watchdog; + } if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) iavf_change_state(adapter, __IAVF_COMM_FAILED); - if (adapter->flags & IAVF_FLAG_RESET_NEEDED && - adapter->state != __IAVF_RESETTING) { - iavf_change_state(adapter, __IAVF_RESETTING); + if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; + mutex_unlock(&adapter->crit_lock); + queue_work(iavf_wq, &adapter->reset_task); + return; } switch (adapter->state) { @@ -2419,6 +2424,15 @@ static void iavf_watchdog_task(struct work_struct *work) msecs_to_jiffies(1)); return; case __IAVF_INIT_FAILED: + if (test_bit(__IAVF_IN_REMOVE_TASK, + &adapter->crit_section)) { + /* Do not update the state and do not reschedule + * watchdog task, iavf_remove should handle this state + * as it can loop forever + */ + mutex_unlock(&adapter->crit_lock); + return; + } if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { dev_err(&adapter->pdev->dev, "Failed to communicate with PF; waiting before retry\n"); @@ -2435,6 +2449,17 @@ static void iavf_watchdog_task(struct work_struct *work) queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ); return; case __IAVF_COMM_FAILED: + if (test_bit(__IAVF_IN_REMOVE_TASK, + &adapter->crit_section)) { + /* Set state to __IAVF_INIT_FAILED and perform remove + * steps. Remove IAVF_FLAG_PF_COMMS_FAILED so the task + * doesn't bring the state back to __IAVF_COMM_FAILED. + */ + iavf_change_state(adapter, __IAVF_INIT_FAILED); + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + mutex_unlock(&adapter->crit_lock); + return; + } reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if (reg_val == VIRTCHNL_VFR_VFACTIVE || @@ -2507,7 +2532,8 @@ static void iavf_watchdog_task(struct work_struct *work) schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); mutex_unlock(&adapter->crit_lock); restart_watchdog: - queue_work(iavf_wq, &adapter->adminq_task); + if (adapter->state >= __IAVF_DOWN) + queue_work(iavf_wq, &adapter->adminq_task); if (adapter->aq_required) queue_delayed_work(iavf_wq, &adapter->watchdog_task, msecs_to_jiffies(20)); @@ -2601,13 +2627,13 @@ static void iavf_reset_task(struct work_struct *work) /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ - if (mutex_is_locked(&adapter->remove_lock)) - return; + if (!mutex_trylock(&adapter->crit_lock)) { + if (adapter->state != __IAVF_REMOVE) + queue_work(iavf_wq, &adapter->reset_task); - if (iavf_lock_timeout(&adapter->crit_lock, 200)) { - schedule_work(&adapter->reset_task); return; } + while (!mutex_trylock(&adapter->client_lock)) usleep_range(500, 1000); if (CLIENT_ENABLED(adapter)) { @@ -2662,6 +2688,7 @@ static void iavf_reset_task(struct work_struct *work) reg_val); iavf_disable_vf(adapter); mutex_unlock(&adapter->client_lock); + mutex_unlock(&adapter->crit_lock); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -2670,8 +2697,7 @@ continue_reset: * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. */ - running = ((adapter->state == __IAVF_RUNNING) || - (adapter->state == __IAVF_RESETTING)); + running = adapter->state == __IAVF_RUNNING; if (running) { netdev->flags &= ~IFF_UP; @@ -2701,7 +2727,8 @@ continue_reset: err); 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; @@ -2773,12 +2800,13 @@ 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); @@ -2793,6 +2821,9 @@ 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); @@ -2826,13 +2857,19 @@ static void iavf_adminq_task(struct work_struct *work) if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) goto out; + if (!mutex_trylock(&adapter->crit_lock)) { + if (adapter->state == __IAVF_REMOVE) + return; + + queue_work(iavf_wq, &adapter->adminq_task); + goto out; + } + event.buf_len = IAVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) goto out; - if (iavf_lock_timeout(&adapter->crit_lock, 200)) - goto freedom; do { ret = iavf_clean_arq_element(hw, &event, &pending); v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); @@ -2848,6 +2885,24 @@ static void iavf_adminq_task(struct work_struct *work) } while (pending); mutex_unlock(&adapter->crit_lock); + if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES)) { + if (adapter->netdev_registered || + !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) { + struct net_device *netdev = adapter->netdev; + + rtnl_lock(); + netdev_update_features(netdev); + rtnl_unlock(); + /* Request VLAN offload settings */ + if (VLAN_V2_ALLOWED(adapter)) + iavf_set_vlan_offload_features + (adapter, 0, netdev->features); + + iavf_set_queue_vlan_tag_loc(adapter); + } + + adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; + } if ((adapter->flags & (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || adapter->state == __IAVF_RESETTING) @@ -3800,11 +3855,12 @@ static int iavf_close(struct net_device *netdev) struct iavf_adapter *adapter = netdev_priv(netdev); int status; - if (adapter->state <= __IAVF_DOWN_PENDING) - return 0; + mutex_lock(&adapter->crit_lock); - while (!mutex_trylock(&adapter->crit_lock)) - usleep_range(500, 1000); + if (adapter->state <= __IAVF_DOWN_PENDING) { + mutex_unlock(&adapter->crit_lock); + return 0; + } set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); if (CLIENT_ENABLED(adapter)) @@ -3853,8 +3909,11 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) iavf_notify_client_l2_params(&adapter->vsi); adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; } - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(iavf_wq, &adapter->reset_task); + + if (netif_running(netdev)) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + queue_work(iavf_wq, &adapter->reset_task); + } return 0; } @@ -4431,7 +4490,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) */ mutex_init(&adapter->crit_lock); mutex_init(&adapter->client_lock); - mutex_init(&adapter->remove_lock); mutex_init(&hw->aq.asq_mutex); mutex_init(&hw->aq.arq_mutex); @@ -4547,7 +4605,6 @@ static int __maybe_unused iavf_resume(struct device *dev_d) static void iavf_remove(struct pci_dev *pdev) { struct iavf_adapter *adapter = iavf_pdev_to_adapter(pdev); - enum iavf_state_t prev_state = adapter->last_state; struct net_device *netdev = adapter->netdev; struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; @@ -4556,14 +4613,30 @@ static void iavf_remove(struct pci_dev *pdev) struct iavf_cloud_filter *cf, *cftmp; struct iavf_hw *hw = &adapter->hw; int err; - /* Indicate we are in remove and not to run reset_task */ - mutex_lock(&adapter->remove_lock); - cancel_work_sync(&adapter->reset_task); + + set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); + /* Wait until port initialization is complete. + * There are flows where register/unregister netdev may race. + */ + while (1) { + mutex_lock(&adapter->crit_lock); + if (adapter->state == __IAVF_RUNNING || + adapter->state == __IAVF_DOWN || + adapter->state == __IAVF_INIT_FAILED) { + mutex_unlock(&adapter->crit_lock); + break; + } + + mutex_unlock(&adapter->crit_lock); + usleep_range(500, 1000); + } cancel_delayed_work_sync(&adapter->watchdog_task); - cancel_delayed_work_sync(&adapter->client_task); + if (adapter->netdev_registered) { - unregister_netdev(netdev); + rtnl_lock(); + unregister_netdevice(netdev); adapter->netdev_registered = false; + rtnl_unlock(); } if (CLIENT_ALLOWED(adapter)) { err = iavf_lan_del_device(adapter); @@ -4572,6 +4645,10 @@ static void iavf_remove(struct pci_dev *pdev) err); } + mutex_lock(&adapter->crit_lock); + dev_info(&adapter->pdev->dev, "Remove device\n"); + iavf_change_state(adapter, __IAVF_REMOVE); + iavf_request_reset(adapter); msleep(50); /* If the FW isn't responding, kick it once, but only once. */ @@ -4579,37 +4656,24 @@ static void iavf_remove(struct pci_dev *pdev) iavf_request_reset(adapter); msleep(50); } - if (iavf_lock_timeout(&adapter->crit_lock, 5000)) - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", __FUNCTION__); - dev_info(&adapter->pdev->dev, "Removing device\n"); + iavf_misc_irq_disable(adapter); /* Shut down all the garbage mashers on the detention level */ - iavf_change_state(adapter, __IAVF_REMOVE); + cancel_work_sync(&adapter->reset_task); + cancel_delayed_work_sync(&adapter->watchdog_task); + cancel_work_sync(&adapter->adminq_task); + cancel_delayed_work_sync(&adapter->client_task); + adapter->aq_required = 0; adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; iavf_free_all_tx_resources(adapter); iavf_free_all_rx_resources(adapter); - iavf_misc_irq_disable(adapter); iavf_free_misc_irq(adapter); - /* In case we enter iavf_remove from erroneous state, free traffic irqs - * here, so as to not cause a kernel crash, when calling - * iavf_reset_interrupt_capability. - */ - if ((adapter->last_state == __IAVF_RESETTING && - prev_state != __IAVF_DOWN) || - (adapter->last_state == __IAVF_RUNNING && - !(netdev->flags & IFF_UP))) - iavf_free_traffic_irqs(adapter); - iavf_reset_interrupt_capability(adapter); iavf_free_q_vectors(adapter); - cancel_delayed_work_sync(&adapter->watchdog_task); - - cancel_work_sync(&adapter->adminq_task); - iavf_free_rss(adapter); if (hw->aq.asq.count) @@ -4621,8 +4685,6 @@ static void iavf_remove(struct pci_dev *pdev) mutex_destroy(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); mutex_destroy(&adapter->crit_lock); - mutex_unlock(&adapter->remove_lock); - mutex_destroy(&adapter->remove_lock); iounmap(hw->hw_addr); pci_release_regions(pdev); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 5ee1d118fd30..5263cefe46f5 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1835,6 +1835,22 @@ void 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 @@ -2057,8 +2073,18 @@ 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", @@ -2146,29 +2172,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, sizeof(adapter->vlan_v2_caps))); iavf_process_config(adapter); - - /* unlock crit_lock before acquiring rtnl_lock as other - * processes holding rtnl_lock could be waiting for the same - * crit_lock - */ - mutex_unlock(&adapter->crit_lock); - /* VLAN capabilities can change during VFR, so make sure to - * update the netdev features with the new capabilities - */ - rtnl_lock(); - netdev_update_features(netdev); - rtnl_unlock(); - if (iavf_lock_timeout(&adapter->crit_lock, 10000)) - dev_warn(&adapter->pdev->dev, "failed to acquire crit_lock in %s\n", - __FUNCTION__); - - /* Request VLAN offload settings */ - if (VLAN_V2_ALLOWED(adapter)) - iavf_set_vlan_offload_features(adapter, 0, - netdev->features); - - iavf_set_queue_vlan_tag_loc(adapter); - + adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; } break; case VIRTCHNL_OP_ENABLE_QUEUES: @@ -2334,6 +2338,20 @@ 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 a9fa701aaa95..bea1d1e39fa2 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -280,7 +280,6 @@ enum ice_pf_state { ICE_VFLR_EVENT_PENDING, ICE_FLTR_OVERFLOW_PROMISC, ICE_VF_DIS, - ICE_VF_DEINIT_IN_PROGRESS, ICE_CFG_BUSY, ICE_SERVICE_SCHED, ICE_SERVICE_DIS, @@ -484,6 +483,7 @@ enum ice_pf_flags { ICE_FLAG_MDD_AUTO_RESET_VF, ICE_FLAG_LINK_LENIENT_MODE_ENA, ICE_FLAG_PLUG_AUX_DEV, + ICE_FLAG_MTU_CHANGED, ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -898,7 +898,16 @@ 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); clear_bit(ICE_FLAG_AUX_ENA, pf->flags); } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index a6d7d3eff186..e2af99a763ed 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -3340,7 +3340,7 @@ ice_cfg_phy_fec(struct ice_port_info *pi, struct ice_aqc_set_phy_cfg_data *cfg, if (fec == ICE_FEC_AUTO && ice_fw_supports_link_override(hw) && !ice_fw_supports_report_dflt_cfg(hw)) { - struct ice_link_default_override_tlv tlv; + struct ice_link_default_override_tlv tlv = { 0 }; status = ice_get_link_default_override(&tlv, pi); if (status) diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c index 864692b157b6..73edc24d81d5 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c @@ -44,6 +44,7 @@ ice_eswitch_add_vf_mac_rule(struct ice_pf *pf, struct ice_vf *vf, const u8 *mac) ctrl_vsi->rxq_map[vf->vf_id]; rule_info.flags_info.act |= ICE_SINGLE_ACT_LB_ENABLE; rule_info.flags_info.act_valid = true; + rule_info.tun_type = ICE_SW_TUN_AND_NON_TUN; err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, vf->repr->mac_rule); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index e2e3ef7fba7f..a5dc9824e255 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2298,7 +2298,7 @@ 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 17a9bb461dc3..493942e910be 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1799,7 +1799,9 @@ static void ice_handle_mdd_event(struct ice_pf *pf) * reset, so print the event prior to reset. */ ice_print_vf_rx_mdd_event(vf); + mutex_lock(&pf->vf[i].cfg_lock); ice_reset_vf(&pf->vf[i], false); + mutex_unlock(&pf->vf[i].cfg_lock); } } } @@ -2253,9 +2255,30 @@ 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); @@ -3021,7 +3044,7 @@ 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 */ @@ -6820,7 +6843,6 @@ 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; @@ -6855,14 +6877,6 @@ 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 */ @@ -6870,21 +6884,18 @@ 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_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index dc1b0e9e6df5..695b6dd61dc2 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -47,6 +47,7 @@ enum ice_protocol_type { enum ice_sw_tunnel_type { ICE_NON_TUN = 0, + ICE_SW_TUN_AND_NON_TUN, ICE_SW_TUN_VXLAN, ICE_SW_TUN_GENEVE, ICE_SW_TUN_NVGRE, diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index ae291d442539..000c39d163a2 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -1533,9 +1533,12 @@ exit: static int ice_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta) { struct timespec64 now, then; + int ret; then = ns_to_timespec64(delta); - ice_ptp_gettimex64(info, &now, NULL); + ret = ice_ptp_gettimex64(info, &now, NULL); + if (ret) + return ret; now = timespec64_add(now, then); return ice_ptp_settime64(info, (const struct timespec64 *)&now); diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 11ae0bee3590..475ec2afa210 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -4537,6 +4537,7 @@ ice_get_compat_fv_bitmap(struct ice_hw *hw, struct ice_adv_rule_info *rinfo, case ICE_SW_TUN_NVGRE: prof_type = ICE_PROF_TUN_GRE; break; + case ICE_SW_TUN_AND_NON_TUN: default: prof_type = ICE_PROF_ALL; break; @@ -5305,7 +5306,8 @@ ice_add_adv_rule(struct ice_hw *hw, struct ice_adv_lkup_elem *lkups, if (status) goto err_ice_add_adv_rule; - if (rinfo->tun_type != ICE_NON_TUN) { + if (rinfo->tun_type != ICE_NON_TUN && + rinfo->tun_type != ICE_SW_TUN_AND_NON_TUN) { status = ice_fill_adv_packet_tun(hw, rinfo->tun_type, s_rule->pdata.lkup_tx_rx.hdr, pkt_offsets); diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index e8aab664270a..65cf32eb4046 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -709,7 +709,7 @@ ice_tc_set_port(struct flow_match_ports match, fltr->flags |= ICE_TC_FLWR_FIELD_ENC_DEST_L4_PORT; else fltr->flags |= ICE_TC_FLWR_FIELD_DEST_L4_PORT; - fltr->flags |= ICE_TC_FLWR_FIELD_DEST_L4_PORT; + headers->l4_key.dst_port = match.key->dst; headers->l4_mask.dst_port = match.mask->dst; } @@ -718,7 +718,7 @@ ice_tc_set_port(struct flow_match_ports match, fltr->flags |= ICE_TC_FLWR_FIELD_ENC_SRC_L4_PORT; else fltr->flags |= ICE_TC_FLWR_FIELD_SRC_L4_PORT; - fltr->flags |= ICE_TC_FLWR_FIELD_SRC_L4_PORT; + headers->l4_key.src_port = match.key->src; headers->l4_mask.src_port = match.mask->src; } diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 39b80124d282..1be3cd4b2bef 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -500,8 +500,6 @@ void ice_free_vfs(struct ice_pf *pf) struct ice_hw *hw = &pf->hw; unsigned int tmp, i; - set_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); - if (!pf->vf) return; @@ -519,22 +517,26 @@ void ice_free_vfs(struct ice_pf *pf) else dev_warn(dev, "VFs are assigned - not disabling SR-IOV\n"); - /* Avoid wait time by stopping all VFs at the same time */ - ice_for_each_vf(pf, i) - ice_dis_vf_qs(&pf->vf[i]); - tmp = pf->num_alloc_vfs; pf->num_qps_per_vf = 0; pf->num_alloc_vfs = 0; for (i = 0; i < tmp; i++) { - if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { + struct ice_vf *vf = &pf->vf[i]; + + mutex_lock(&vf->cfg_lock); + + ice_dis_vf_qs(vf); + + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { /* disable VF qp mappings and set VF disable state */ - ice_dis_vf_mappings(&pf->vf[i]); - set_bit(ICE_VF_STATE_DIS, pf->vf[i].vf_states); - ice_free_vf_res(&pf->vf[i]); + ice_dis_vf_mappings(vf); + set_bit(ICE_VF_STATE_DIS, vf->vf_states); + ice_free_vf_res(vf); } - mutex_destroy(&pf->vf[i].cfg_lock); + mutex_unlock(&vf->cfg_lock); + + mutex_destroy(&vf->cfg_lock); } if (ice_sriov_free_msix_res(pf)) @@ -570,7 +572,6 @@ void ice_free_vfs(struct ice_pf *pf) i); clear_bit(ICE_VF_DIS, pf->state); - clear_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state); clear_bit(ICE_FLAG_SRIOV_ENA, pf->flags); } @@ -1498,6 +1499,8 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_for_each_vf(pf, v) { vf = &pf->vf[v]; + mutex_lock(&vf->cfg_lock); + vf->driver_caps = 0; ice_vc_set_default_allowlist(vf); @@ -1512,6 +1515,8 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) ice_vf_pre_vsi_rebuild(vf); ice_vf_rebuild_vsi(vf); ice_vf_post_vsi_rebuild(vf); + + mutex_unlock(&vf->cfg_lock); } if (ice_is_eswitch_mode_switchdev(pf)) @@ -1562,6 +1567,8 @@ bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) u32 reg; int i; + lockdep_assert_held(&vf->cfg_lock); + dev = ice_pf_to_dev(pf); if (test_bit(ICE_VF_RESETS_DISABLED, pf->state)) { @@ -2061,9 +2068,12 @@ void ice_process_vflr_event(struct ice_pf *pf) bit_idx = (hw->func_caps.vf_base_id + vf_id) % 32; /* read GLGEN_VFLRSTAT register to find out the flr VFs */ reg = rd32(hw, GLGEN_VFLRSTAT(reg_idx)); - if (reg & BIT(bit_idx)) + if (reg & BIT(bit_idx)) { /* GLGEN_VFLRSTAT bit will be cleared in ice_reset_vf */ + mutex_lock(&vf->cfg_lock); ice_reset_vf(vf, true); + mutex_unlock(&vf->cfg_lock); + } } } @@ -2140,7 +2150,9 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) if (!vf) return; + mutex_lock(&vf->cfg_lock); ice_vc_reset_vf(vf); + mutex_unlock(&vf->cfg_lock); } /** @@ -2170,24 +2182,6 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, 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) { @@ -4625,10 +4619,6 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) struct device *dev; int err = 0; - /* if de-init is underway, don't process messages from VF */ - if (test_bit(ICE_VF_DEINIT_IN_PROGRESS, pf->state)) - return; - dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) { err = -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 752487a1bdd6..8f27255cc0cc 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -14,7 +14,6 @@ #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 */ @@ -134,8 +133,6 @@ 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/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 5cad31c3c7b0..40dbf4b43234 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -746,8 +746,6 @@ s32 igc_write_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 data) if (ret_val) return ret_val; ret_val = igc_write_phy_reg_mdic(hw, offset, data); - if (ret_val) - return ret_val; hw->phy.ops.release(hw); } else { ret_val = igc_write_xmdio_reg(hw, (u16)offset, dev_addr, @@ -779,8 +777,6 @@ s32 igc_read_phy_reg_gpy(struct igc_hw *hw, u32 offset, u16 *data) if (ret_val) return ret_val; ret_val = igc_read_phy_reg_mdic(hw, offset, data); - if (ret_val) - return ret_val; hw->phy.ops.release(hw); } else { ret_val = igc_read_xmdio_reg(hw, (u16)offset, dev_addr, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index b3fd8e5cd85b..6a5e9cf6b5da 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -390,12 +390,14 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) u32 cmd_type; while (budget-- > 0) { - if (unlikely(!ixgbe_desc_unused(xdp_ring)) || - !netif_carrier_ok(xdp_ring->netdev)) { + if (unlikely(!ixgbe_desc_unused(xdp_ring))) { work_done = false; break; } + if (!netif_carrier_ok(xdp_ring->netdev)) + break; + if (!xsk_tx_peek_desc(pool, &desc)) break; 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/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 105247582684..143ca8be5eb5 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2704,6 +2704,16 @@ MODULE_DEVICE_TABLE(of, mv643xx_eth_shared_ids); static struct platform_device *port_platdev[3]; +static void mv643xx_eth_shared_of_remove(void) +{ + int n; + + for (n = 0; n < 3; n++) { + platform_device_del(port_platdev[n]); + port_platdev[n] = NULL; + } +} + static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, struct device_node *pnp) { @@ -2740,7 +2750,9 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, return -EINVAL; } - of_get_mac_address(pnp, ppd.mac_addr); + ret = of_get_mac_address(pnp, ppd.mac_addr); + if (ret) + return ret; mv643xx_eth_property(pnp, "tx-queue-size", ppd.tx_queue_size); mv643xx_eth_property(pnp, "tx-sram-addr", ppd.tx_sram_addr); @@ -2804,21 +2816,13 @@ static int mv643xx_eth_shared_of_probe(struct platform_device *pdev) ret = mv643xx_eth_shared_of_add_port(pdev, pnp); if (ret) { of_node_put(pnp); + mv643xx_eth_shared_of_remove(); return ret; } } return 0; } -static void mv643xx_eth_shared_of_remove(void) -{ - int n; - - for (n = 0; n < 3; n++) { - platform_device_del(port_platdev[n]); - port_platdev[n] = NULL; - } -} #else static inline int mv643xx_eth_shared_of_probe(struct platform_device *pdev) { diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 7cdbf8b8bbf6..1a835b48791b 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -6870,6 +6870,9 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->max_mtu = MVPP2_BM_JUMBO_PKT_SIZE; dev->dev.of_node = port_node; + port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops; + port->pcs_xlg.ops = &mvpp2_phylink_xlg_pcs_ops; + if (!mvpp2_use_acpi_compat_mode(port_fwnode)) { port->phylink_config.dev = &dev->dev; port->phylink_config.type = PHYLINK_NETDEV; @@ -6940,9 +6943,6 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->phylink_config.supported_interfaces); } - port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops; - port->pcs_xlg.ops = &mvpp2_phylink_xlg_pcs_ops; - phylink = phylink_create(&port->phylink_config, port_fwnode, phy_mode, &mvpp2_phylink_ops); if (IS_ERR(phylink)) { diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c index cad93f747d0c..73cd0a4b7291 100644 --- a/drivers/net/ethernet/marvell/prestera/prestera_main.c +++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c @@ -554,6 +554,7 @@ static int prestera_switch_set_base_mac_addr(struct prestera_switch *sw) dev_info(prestera_dev(sw), "using random base mac address\n"); } of_node_put(base_mac_np); + of_node_put(np); return prestera_hw_switch_mac_set(sw, sw->base_mac); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 17fe05809653..3eacd8739929 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -131,11 +131,8 @@ static int cmd_alloc_index(struct mlx5_cmd *cmd) static void cmd_free_index(struct mlx5_cmd *cmd, int idx) { - unsigned long flags; - - spin_lock_irqsave(&cmd->alloc_lock, flags); + lockdep_assert_held(&cmd->alloc_lock); set_bit(idx, &cmd->bitmask); - spin_unlock_irqrestore(&cmd->alloc_lock, flags); } static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) @@ -145,17 +142,21 @@ static void cmd_ent_get(struct mlx5_cmd_work_ent *ent) static void cmd_ent_put(struct mlx5_cmd_work_ent *ent) { + struct mlx5_cmd *cmd = ent->cmd; + unsigned long flags; + + spin_lock_irqsave(&cmd->alloc_lock, flags); if (!refcount_dec_and_test(&ent->refcnt)) - return; + goto out; if (ent->idx >= 0) { - struct mlx5_cmd *cmd = ent->cmd; - cmd_free_index(cmd, ent->idx); up(ent->page_queue ? &cmd->pages_sem : &cmd->sem); } cmd_free_ent(ent); +out: + spin_unlock_irqrestore(&cmd->alloc_lock, flags); } static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h index 26efa33de56f..9cc844bd00f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h @@ -16,11 +16,13 @@ struct mlx5e_tc_act_parse_state { unsigned int num_actions; struct mlx5e_tc_flow *flow; struct netlink_ext_ack *extack; + bool ct_clear; bool encap; bool decap; bool mpls_push; bool ptype_host; const struct ip_tunnel_info *tun_info; + struct mlx5e_mpls_info mpls_info; struct pedit_headers_action hdrs[__PEDIT_CMD_MAX]; int ifindexes[MLX5_MAX_FLOW_FWD_VPORTS]; int if_count; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c index 06ec30cdb269..58cc33f1363d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c @@ -27,8 +27,13 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5e_priv *priv, struct mlx5_flow_attr *attr) { + bool clear_action = act->ct.action & TCA_CT_ACT_CLEAR; int err; + /* It's redundant to do ct clear more than once. */ + if (clear_action && parse_state->ct_clear) + return 0; + err = mlx5_tc_ct_parse_action(parse_state->ct_priv, attr, &attr->parse_attr->mod_hdr_acts, act, parse_state->extack); @@ -40,6 +45,8 @@ tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state, if (mlx5e_is_eswitch_flow(parse_state->flow)) attr->esw_attr->split_count = attr->esw_attr->out_count; + parse_state->ct_clear = clear_action; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c index c614fc7fdc9c..2e615e0ba972 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mirred.c @@ -177,6 +177,12 @@ parse_mirred_encap(struct mlx5e_tc_act_parse_state *parse_state, return -ENOMEM; parse_state->encap = false; + + if (parse_state->mpls_push) { + memcpy(&parse_attr->mpls_info[esw_attr->out_count], + &parse_state->mpls_info, sizeof(parse_state->mpls_info)); + parse_state->mpls_push = false; + } esw_attr->dests[esw_attr->out_count].flags |= MLX5_ESW_DEST_ENCAP; esw_attr->out_count++; /* attr->dests[].rep is resolved when we handle encap */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c index 784fc4f68b1e..89ca88c78840 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/mpls.c @@ -22,6 +22,16 @@ tc_act_can_offload_mpls_push(struct mlx5e_tc_act_parse_state *parse_state, return true; } +static void +copy_mpls_info(struct mlx5e_mpls_info *mpls_info, + const struct flow_action_entry *act) +{ + mpls_info->label = act->mpls_push.label; + mpls_info->tc = act->mpls_push.tc; + mpls_info->bos = act->mpls_push.bos; + mpls_info->ttl = act->mpls_push.ttl; +} + static int tc_act_parse_mpls_push(struct mlx5e_tc_act_parse_state *parse_state, const struct flow_action_entry *act, @@ -29,6 +39,7 @@ tc_act_parse_mpls_push(struct mlx5e_tc_act_parse_state *parse_state, struct mlx5_flow_attr *attr) { parse_state->mpls_push = true; + copy_mpls_info(&parse_state->mpls_info, act); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h index f832c26ff2c3..70b40ae384e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h @@ -35,6 +35,7 @@ enum { struct mlx5e_tc_flow_parse_attr { const struct ip_tunnel_info *tun_info[MLX5_MAX_FLOW_FWD_VPORTS]; + struct mlx5e_mpls_info mpls_info[MLX5_MAX_FLOW_FWD_VPORTS]; struct net_device *filter_dev; struct mlx5_flow_spec spec; struct mlx5e_tc_mod_hdr_acts mod_hdr_acts; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 9918ed8c059b..d39d0dae22fc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -750,6 +750,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5_flow_attr *attr = flow->attr; const struct ip_tunnel_info *tun_info; + const struct mlx5e_mpls_info *mpls_info; unsigned long tbl_time_before = 0; struct mlx5e_encap_entry *e; struct mlx5e_encap_key key; @@ -760,6 +761,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, parse_attr = attr->parse_attr; tun_info = parse_attr->tun_info[out_index]; + mpls_info = &parse_attr->mpls_info[out_index]; family = ip_tunnel_info_af(tun_info); key.ip_tun_key = &tun_info->key; key.tc_tunnel = mlx5e_get_tc_tun(mirred_dev); @@ -810,6 +812,7 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv, goto out_err_init; } e->tun_info = tun_info; + memcpy(&e->mpls_info, mpls_info, sizeof(*mpls_info)); err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack); if (err) goto out_err_init; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c index 60952b33b568..c5b1617d556f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_mplsoudp.c @@ -30,16 +30,15 @@ static int generate_ip_tun_hdr(char buf[], struct mlx5e_encap_entry *r) { const struct ip_tunnel_key *tun_key = &r->tun_info->key; + const struct mlx5e_mpls_info *mpls_info = &r->mpls_info; struct udphdr *udp = (struct udphdr *)(buf); struct mpls_shim_hdr *mpls; - u32 tun_id; - tun_id = be32_to_cpu(tunnel_id_to_key32(tun_key->tun_id)); mpls = (struct mpls_shim_hdr *)(udp + 1); *ip_proto = IPPROTO_UDP; udp->dest = tun_key->tp_dst; - *mpls = mpls_entry_encode(tun_id, tun_key->ttl, tun_key->tos, true); + *mpls = mpls_entry_encode(mpls_info->label, mpls_info->ttl, mpls_info->tc, mpls_info->bos); return 0; } @@ -60,37 +59,31 @@ static int parse_tunnel(struct mlx5e_priv *priv, void *headers_v) { struct flow_rule *rule = flow_cls_offload_flow_rule(f); - struct flow_match_enc_keyid enc_keyid; struct flow_match_mpls match; void *misc2_c; void *misc2_v; - misc2_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, - misc_parameters_2); - misc2_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, - misc_parameters_2); - - if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) - return 0; - - if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) - return 0; - - flow_rule_match_enc_keyid(rule, &enc_keyid); - - if (!enc_keyid.mask->keyid) - return 0; - if (!MLX5_CAP_ETH(priv->mdev, tunnel_stateless_mpls_over_udp) && !(MLX5_CAP_GEN(priv->mdev, flex_parser_protocols) & MLX5_FLEX_PROTO_CW_MPLS_UDP)) return -EOPNOTSUPP; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) + return -EOPNOTSUPP; + + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) + return 0; + flow_rule_match_mpls(rule, &match); /* Only support matching the first LSE */ if (match.mask->used_lses != 1) return -EOPNOTSUPP; + misc2_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + misc_parameters_2); + misc2_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, + misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc2_c, outer_first_mpls_over_udp.mpls_label, match.mask->ls[0].mpls_label); 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_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 57d755db1cf5..6e80585d731f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1792,7 +1792,7 @@ static int mlx5e_get_module_eeprom(struct net_device *netdev, if (size_read < 0) { netdev_err(priv->netdev, "%s: mlx5_query_eeprom failed:0x%x\n", __func__, size_read); - return 0; + return size_read; } i += size_read; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bf80fb612449..3667f5ef5990 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3616,8 +3616,7 @@ 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_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index b01dacb6f527..b3f7520dfd08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -183,6 +183,13 @@ struct mlx5e_decap_entry { struct rcu_head rcu; }; +struct mlx5e_mpls_info { + u32 label; + u8 tc; + u8 bos; + u8 ttl; +}; + struct mlx5e_encap_entry { /* attached neigh hash entry */ struct mlx5e_neigh_hash_entry *nhe; @@ -196,6 +203,7 @@ struct mlx5e_encap_entry { struct list_head route_list; struct mlx5_pkt_reformat *pkt_reformat; const struct ip_tunnel_info *tun_info; + struct mlx5e_mpls_info mpls_info; unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ struct net_device *out_dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index ee0a8f5206e3..6530d7bd5045 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1349,7 +1349,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, } /* True when explicitly set via priv flag, or XDP prog is loaded */ - if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)) + if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state) || + get_cqe_tls_offload(cqe)) goto csum_unnecessary; /* CQE csum doesn't cover padding octets in short ethernet diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 8c9163d2c646..08a75654f5f1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -334,6 +334,7 @@ void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, netdev_info(ndev, "\t[%d] %s start..\n", i, st.name); buf[count] = st.st_func(priv); netdev_info(ndev, "\t[%d] %s end: result(%lld)\n", i, st.name, buf[count]); + count++; } mutex_unlock(&priv->state_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 26e326fe503c..00f1d16db456 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -1254,9 +1254,6 @@ static void fec_set_corrected_bits_total(struct mlx5e_priv *priv, u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {}; int sz = MLX5_ST_SZ_BYTES(ppcnt_reg); - if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group)) - return; - MLX5_SET(ppcnt_reg, in, local_port, 1); MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP); if (mlx5_core_access_reg(mdev, in, sz, ppcnt_phy_statistical, @@ -1272,6 +1269,9 @@ static void fec_set_corrected_bits_total(struct mlx5e_priv *priv, void mlx5e_stats_fec_get(struct mlx5e_priv *priv, struct ethtool_fec_stats *fec_stats) { + if (!MLX5_CAP_PCAM_FEATURE(priv->mdev, ppcnt_statistical_group)) + return; + fec_set_corrected_bits_total(priv, fec_stats); fec_set_block_stats(priv, fec_stats); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 2022fa4a9598..b27532a9301e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3204,6 +3204,18 @@ actions_match_supported(struct mlx5e_priv *priv, return false; } + if (!(~actions & + (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) { + NL_SET_ERR_MSG_MOD(extack, "Rule cannot support forward+drop action"); + return false; + } + + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && + actions & MLX5_FLOW_CONTEXT_ACTION_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Drop with modify header action is not supported"); + return false; + } + if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR && !modify_header_match_supported(priv, &parse_attr->spec, flow_action, actions, ct_flow, ct_clear, extack)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 11bbcd5f5b8b..694c54066955 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -697,7 +697,7 @@ void mlx5_esw_qos_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vpo } int mlx5_esw_qos_set_vport_rate(struct mlx5_eswitch *esw, struct mlx5_vport *vport, - u32 min_rate, u32 max_rate) + u32 max_rate, u32 min_rate) { int err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 9a7b25692505..cfcd72bad9af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -2838,10 +2838,6 @@ bool mlx5_esw_vport_match_metadata_supported(const struct mlx5_eswitch *esw) if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source)) return false; - if (mlx5_core_is_ecpf_esw_manager(esw->dev) || - mlx5_ecpf_vport_exists(esw->dev)) - return false; - return true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index b628917e38e4..537c82b9aa53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -2074,6 +2074,8 @@ void mlx5_del_flow_rules(struct mlx5_flow_handle *handle) fte->node.del_hw_func = NULL; up_write_ref_node(&fte->node, false); tree_put_node(&fte->node, false); + } else { + up_write_ref_node(&fte->node, false); } kfree(handle); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mp.c index 1ca01a5b6cdd..626aa60b6099 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/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 2c774f367199..bba72b220cc3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -526,7 +526,7 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) /* Check log_max_qp from HCA caps to set in current profile */ if (prof->log_max_qp == LOG_MAX_SUPPORTED_QPS) { - prof->log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); + prof->log_max_qp = min_t(u8, 17, MLX5_CAP_GEN_MAX(dev, log_max_qp)); } else if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) { mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n", prof->log_max_qp, @@ -1840,10 +1840,12 @@ static const struct pci_device_id mlx5_core_pci_table[] = { { PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF}, /* ConnectX Family mlx5Gen Virtual Function */ { PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */ { PCI_VDEVICE(MELLANOX, 0x1021) }, /* ConnectX-7 */ + { PCI_VDEVICE(MELLANOX, 0x1023) }, /* ConnectX-8 */ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */ { PCI_VDEVICE(MELLANOX, 0xa2dc) }, /* BlueField-3 integrated ConnectX-7 network controller */ + { PCI_VDEVICE(MELLANOX, 0xa2df) }, /* BlueField-4 integrated ConnectX-8 network controller */ { 0, } }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c index 7f6fd9c5e371..e289cfdbce07 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -4,7 +4,6 @@ #include "dr_types.h" #define DR_ICM_MODIFY_HDR_ALIGN_BASE 64 -#define DR_ICM_SYNC_THRESHOLD_POOL (64 * 1024 * 1024) struct mlx5dr_icm_pool { enum mlx5dr_icm_type icm_type; @@ -136,37 +135,35 @@ static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr) kvfree(icm_mr); } -static int dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk) +static int dr_icm_buddy_get_ste_size(struct mlx5dr_icm_buddy_mem *buddy) { - chunk->ste_arr = kvzalloc(chunk->num_of_entries * - sizeof(chunk->ste_arr[0]), GFP_KERNEL); - if (!chunk->ste_arr) - return -ENOMEM; - - chunk->hw_ste_arr = kvzalloc(chunk->num_of_entries * - DR_STE_SIZE_REDUCED, GFP_KERNEL); - if (!chunk->hw_ste_arr) - goto out_free_ste_arr; - - chunk->miss_list = kvmalloc(chunk->num_of_entries * - sizeof(chunk->miss_list[0]), GFP_KERNEL); - if (!chunk->miss_list) - goto out_free_hw_ste_arr; + /* We support only one type of STE size, both for ConnectX-5 and later + * devices. Once the support for match STE which has a larger tag is + * added (32B instead of 16B), the STE size for devices later than + * ConnectX-5 needs to account for that. + */ + return DR_STE_SIZE_REDUCED; +} - return 0; +static void dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk, int offset) +{ + struct mlx5dr_icm_buddy_mem *buddy = chunk->buddy_mem; + int index = offset / DR_STE_SIZE; -out_free_hw_ste_arr: - kvfree(chunk->hw_ste_arr); -out_free_ste_arr: - kvfree(chunk->ste_arr); - return -ENOMEM; + chunk->ste_arr = &buddy->ste_arr[index]; + chunk->miss_list = &buddy->miss_list[index]; + chunk->hw_ste_arr = buddy->hw_ste_arr + + index * dr_icm_buddy_get_ste_size(buddy); } static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk) { - kvfree(chunk->miss_list); - kvfree(chunk->hw_ste_arr); - kvfree(chunk->ste_arr); + struct mlx5dr_icm_buddy_mem *buddy = chunk->buddy_mem; + + memset(chunk->hw_ste_arr, 0, + chunk->num_of_entries * dr_icm_buddy_get_ste_size(buddy)); + memset(chunk->ste_arr, 0, + chunk->num_of_entries * sizeof(chunk->ste_arr[0])); } static enum mlx5dr_icm_type @@ -189,6 +186,44 @@ static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk, kvfree(chunk); } +static int dr_icm_buddy_init_ste_cache(struct mlx5dr_icm_buddy_mem *buddy) +{ + int num_of_entries = + mlx5dr_icm_pool_chunk_size_to_entries(buddy->pool->max_log_chunk_sz); + + buddy->ste_arr = kvcalloc(num_of_entries, + sizeof(struct mlx5dr_ste), GFP_KERNEL); + if (!buddy->ste_arr) + return -ENOMEM; + + /* Preallocate full STE size on non-ConnectX-5 devices since + * we need to support both full and reduced with the same cache. + */ + buddy->hw_ste_arr = kvcalloc(num_of_entries, + dr_icm_buddy_get_ste_size(buddy), GFP_KERNEL); + if (!buddy->hw_ste_arr) + goto free_ste_arr; + + buddy->miss_list = kvmalloc(num_of_entries * sizeof(struct list_head), GFP_KERNEL); + if (!buddy->miss_list) + goto free_hw_ste_arr; + + return 0; + +free_hw_ste_arr: + kvfree(buddy->hw_ste_arr); +free_ste_arr: + kvfree(buddy->ste_arr); + return -ENOMEM; +} + +static void dr_icm_buddy_cleanup_ste_cache(struct mlx5dr_icm_buddy_mem *buddy) +{ + kvfree(buddy->ste_arr); + kvfree(buddy->hw_ste_arr); + kvfree(buddy->miss_list); +} + static int dr_icm_buddy_create(struct mlx5dr_icm_pool *pool) { struct mlx5dr_icm_buddy_mem *buddy; @@ -208,11 +243,19 @@ static int dr_icm_buddy_create(struct mlx5dr_icm_pool *pool) buddy->icm_mr = icm_mr; buddy->pool = pool; + if (pool->icm_type == DR_ICM_TYPE_STE) { + /* Reduce allocations by preallocating and reusing the STE structures */ + if (dr_icm_buddy_init_ste_cache(buddy)) + goto err_cleanup_buddy; + } + /* add it to the -start- of the list in order to search in it first */ list_add(&buddy->list_node, &pool->buddy_mem_list); return 0; +err_cleanup_buddy: + mlx5dr_buddy_cleanup(buddy); err_free_buddy: kvfree(buddy); free_mr: @@ -234,6 +277,9 @@ static void dr_icm_buddy_destroy(struct mlx5dr_icm_buddy_mem *buddy) mlx5dr_buddy_cleanup(buddy); + if (buddy->pool->icm_type == DR_ICM_TYPE_STE) + dr_icm_buddy_cleanup_ste_cache(buddy); + kvfree(buddy); } @@ -261,34 +307,30 @@ dr_icm_chunk_create(struct mlx5dr_icm_pool *pool, chunk->byte_size = mlx5dr_icm_pool_chunk_size_to_byte(chunk_size, pool->icm_type); chunk->seg = seg; + chunk->buddy_mem = buddy_mem_pool; - if (pool->icm_type == DR_ICM_TYPE_STE && dr_icm_chunk_ste_init(chunk)) { - mlx5dr_err(pool->dmn, - "Failed to init ste arrays (order: %d)\n", - chunk_size); - goto out_free_chunk; - } + if (pool->icm_type == DR_ICM_TYPE_STE) + dr_icm_chunk_ste_init(chunk, offset); buddy_mem_pool->used_memory += chunk->byte_size; - chunk->buddy_mem = buddy_mem_pool; INIT_LIST_HEAD(&chunk->chunk_list); /* chunk now is part of the used_list */ list_add_tail(&chunk->chunk_list, &buddy_mem_pool->used_list); return chunk; - -out_free_chunk: - kvfree(chunk); - return NULL; } static bool dr_icm_pool_is_sync_required(struct mlx5dr_icm_pool *pool) { - if (pool->hot_memory_size > DR_ICM_SYNC_THRESHOLD_POOL) - return true; + int allow_hot_size; + + /* sync when hot memory reaches half of the pool size */ + allow_hot_size = + mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, + pool->icm_type) / 2; - return false; + return pool->hot_memory_size > allow_hot_size; } static int dr_icm_pool_sync_all_buddy_pools(struct mlx5dr_icm_pool *pool) 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 e87cf498c77b..38971fe1dfe1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -13,18 +13,6 @@ static bool dr_mask_is_dmac_set(struct mlx5dr_match_spec *spec) return (spec->dmac_47_16 || spec->dmac_15_0); } -static bool dr_mask_is_src_addr_set(struct mlx5dr_match_spec *spec) -{ - return (spec->src_ip_127_96 || spec->src_ip_95_64 || - spec->src_ip_63_32 || spec->src_ip_31_0); -} - -static bool dr_mask_is_dst_addr_set(struct mlx5dr_match_spec *spec) -{ - return (spec->dst_ip_127_96 || spec->dst_ip_95_64 || - spec->dst_ip_63_32 || spec->dst_ip_31_0); -} - static bool dr_mask_is_l3_base_set(struct mlx5dr_match_spec *spec) { return (spec->ip_protocol || spec->frag || spec->tcp_flags || @@ -503,11 +491,11 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, &mask, inner, rx); if (outer_ipv == DR_RULE_IPV6) { - if (dr_mask_is_dst_addr_set(&mask.outer)) + if (DR_MASK_IS_DST_IP_SET(&mask.outer)) mlx5dr_ste_build_eth_l3_ipv6_dst(ste_ctx, &sb[idx++], &mask, inner, rx); - if (dr_mask_is_src_addr_set(&mask.outer)) + if (DR_MASK_IS_SRC_IP_SET(&mask.outer)) mlx5dr_ste_build_eth_l3_ipv6_src(ste_ctx, &sb[idx++], &mask, inner, rx); @@ -610,11 +598,11 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, &mask, inner, rx); if (inner_ipv == DR_RULE_IPV6) { - if (dr_mask_is_dst_addr_set(&mask.inner)) + if (DR_MASK_IS_DST_IP_SET(&mask.inner)) mlx5dr_ste_build_eth_l3_ipv6_dst(ste_ctx, &sb[idx++], &mask, inner, rx); - if (dr_mask_is_src_addr_set(&mask.inner)) + if (DR_MASK_IS_SRC_IP_SET(&mask.inner)) mlx5dr_ste_build_eth_l3_ipv6_src(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 7e61742e58a0..187e29b409b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -602,12 +602,34 @@ int mlx5dr_ste_set_action_decap_l3_list(struct mlx5dr_ste_ctx *ste_ctx, used_hw_action_num); } +static int dr_ste_build_pre_check_spec(struct mlx5dr_domain *dmn, + struct mlx5dr_match_spec *spec) +{ + if (spec->ip_version) { + if (spec->ip_version != 0xf) { + mlx5dr_err(dmn, + "Partial ip_version mask with src/dst IP is not supported\n"); + return -EINVAL; + } + } else if (spec->ethertype != 0xffff && + (DR_MASK_IS_SRC_IP_SET(spec) || DR_MASK_IS_DST_IP_SET(spec))) { + mlx5dr_err(dmn, + "Partial/no ethertype mask with src/dst IP is not supported\n"); + return -EINVAL; + } + + return 0; +} + int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn, u8 match_criteria, struct mlx5dr_match_param *mask, struct mlx5dr_match_param *value) { - if (!value && (match_criteria & DR_MATCHER_CRITERIA_MISC)) { + if (value) + return 0; + + if (match_criteria & DR_MATCHER_CRITERIA_MISC) { if (mask->misc.source_port && mask->misc.source_port != 0xffff) { mlx5dr_err(dmn, "Partial mask source_port is not supported\n"); @@ -621,6 +643,14 @@ int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn, } } + if ((match_criteria & DR_MATCHER_CRITERIA_OUTER) && + dr_ste_build_pre_check_spec(dmn, &mask->outer)) + return -EINVAL; + + if ((match_criteria & DR_MATCHER_CRITERIA_INNER) && + dr_ste_build_pre_check_spec(dmn, &mask->inner)) + return -EINVAL; + return 0; } 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 1b3d484b99be..55fcb751e24a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -798,6 +798,16 @@ struct mlx5dr_match_param { (_misc3)->icmpv4_code || \ (_misc3)->icmpv4_header_data) +#define DR_MASK_IS_SRC_IP_SET(_spec) ((_spec)->src_ip_127_96 || \ + (_spec)->src_ip_95_64 || \ + (_spec)->src_ip_63_32 || \ + (_spec)->src_ip_31_0) + +#define DR_MASK_IS_DST_IP_SET(_spec) ((_spec)->dst_ip_127_96 || \ + (_spec)->dst_ip_95_64 || \ + (_spec)->dst_ip_63_32 || \ + (_spec)->dst_ip_31_0) + struct mlx5dr_esw_caps { u64 drop_icm_address_rx; u64 drop_icm_address_tx; 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 a476da2424f8..3f311462bedf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -233,7 +233,11 @@ static bool contain_vport_reformat_action(struct mlx5_flow_rule *dst) dst->dest_attr.vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID; } -#define MLX5_FLOW_CONTEXT_ACTION_MAX 32 +/* We want to support a rule with 32 destinations, which means we need to + * account for 32 destinations plus usually a counter plus one more action + * for a multi-destination flow table. + */ +#define MLX5_FLOW_CONTEXT_ACTION_MAX 34 static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, struct mlx5_flow_group *group, @@ -403,9 +407,9 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, enum mlx5_flow_destination_type type = dst->dest_attr.type; u32 id; - if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || - num_term_actions >= MLX5_FLOW_CONTEXT_ACTION_MAX) { - err = -ENOSPC; + if (fs_dr_num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || + num_term_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; goto free_actions; } @@ -478,8 +482,9 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, MLX5_FLOW_DESTINATION_TYPE_COUNTER) continue; - if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { - err = -ENOSPC; + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || + fs_dr_num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; goto free_actions; } @@ -499,14 +504,28 @@ static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, params.match_sz = match_sz; params.match_buf = (u64 *)fte->val; if (num_term_actions == 1) { - if (term_actions->reformat) + if (term_actions->reformat) { + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } actions[num_actions++] = term_actions->reformat; + } + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } actions[num_actions++] = term_actions->dest; } else if (num_term_actions > 1) { bool ignore_flow_level = !!(fte->action.flags & FLOW_ACT_IGNORE_FLOW_LEVEL); + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX || + fs_dr_num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -EOPNOTSUPP; + goto free_actions; + } tmp_action = mlx5dr_action_create_mult_dest_tbl(domain, term_actions, num_term_actions, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index c7c93131b762..dfa223415fe2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -160,6 +160,11 @@ struct mlx5dr_icm_buddy_mem { * sync_ste command sets them free. */ struct list_head hot_list; + + /* Memory optimisation */ + struct mlx5dr_ste *ste_arr; + struct list_head *miss_list; + u8 *hw_ste_arr; }; int mlx5dr_buddy_init(struct mlx5dr_icm_buddy_mem *buddy, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index a1acc9b461f2..d40e18ce3293 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -16,6 +16,8 @@ #include <linux/phylink.h> #include <linux/hrtimer.h> +#include "sparx5_main_regs.h" + /* Target chip type */ enum spx5_target_chiptype { SPX5_TARGET_CT_7546 = 0x7546, /* SparX-5-64 Enterprise */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_vlan.c b/drivers/net/ethernet/microchip/sparx5/sparx5_vlan.c index 4ce490a25f33..8e56ffa1c4f7 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_vlan.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_vlan.c @@ -58,16 +58,6 @@ int sparx5_vlan_vid_add(struct sparx5_port *port, u16 vid, bool pvid, struct sparx5 *sparx5 = port->sparx5; int ret; - /* Make the port a member of the VLAN */ - set_bit(port->portno, sparx5->vlan_mask[vid]); - ret = sparx5_vlant_set_mask(sparx5, vid); - if (ret) - return ret; - - /* Default ingress vlan classification */ - if (pvid) - port->pvid = vid; - /* Untagged egress vlan classification */ if (untagged && port->vid != vid) { if (port->vid) { @@ -79,6 +69,16 @@ int sparx5_vlan_vid_add(struct sparx5_port *port, u16 vid, bool pvid, port->vid = vid; } + /* Make the port a member of the VLAN */ + set_bit(port->portno, sparx5->vlan_mask[vid]); + ret = sparx5_vlant_set_mask(sparx5, vid); + if (ret) + return ret; + + /* Default ingress vlan classification */ + if (pvid) + port->pvid = vid; + sparx5_vlan_port_apply(sparx5, port); return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index 0a326e04e692..cb43651ea9ba 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -922,8 +922,8 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev, int port, bool mod) { struct nfp_flower_priv *priv = app->priv; - int ida_idx = NFP_MAX_MAC_INDEX, err; struct nfp_tun_offloaded_mac *entry; + int ida_idx = -1, err; u16 nfp_mac_idx = 0; entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); @@ -997,7 +997,7 @@ err_remove_hash: err_free_entry: kfree(entry); err_free_ida: - if (ida_idx != NFP_MAX_MAC_INDEX) + if (ida_idx != -1) ida_simple_remove(&priv->tun.mac_off_ids, ida_idx); return err; 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 8ac38828ba45..48cf4355bc47 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -3806,11 +3806,11 @@ 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, @@ -3818,7 +3818,7 @@ 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; @@ -3828,6 +3828,7 @@ 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 @@ -4686,6 +4687,7 @@ 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)) @@ -4699,7 +4701,9 @@ 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/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 32161a56726c..2881f5b2b5f4 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -2285,18 +2285,18 @@ static int __init sxgbe_cmdline_opt(char *str) char *opt; if (!str || !*str) - return -EINVAL; + return 1; while ((opt = strsep(&str, ",")) != NULL) { if (!strncmp(opt, "eee_timer:", 10)) { if (kstrtoint(opt + 10, 0, &eee_timer)) goto err; } } - return 0; + return 1; err: pr_err("%s: ERROR broken module parameter conversion\n", __func__); - return -EINVAL; + return 1; } __setup("sxgbeeth=", sxgbe_cmdline_opt); diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index be6bfd6b7ec7..50baf62b2cbc 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -163,9 +163,9 @@ static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd, /* Serialise with efx_mcdi_ev_cpl() and efx_mcdi_ev_death() */ spin_lock_bh(&mcdi->iface_lock); ++mcdi->seqno; + seqno = mcdi->seqno & SEQ_MASK; spin_unlock_bh(&mcdi->iface_lock); - seqno = mcdi->seqno & SEQ_MASK; xflags = 0; if (mcdi->mode == MCDI_MODE_EVENTS) xflags |= MCDI_HEADER_XFLAGS_EVREQ; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index bde76ea2deec..422e3225f476 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2262,6 +2262,23 @@ static void stmmac_stop_tx_dma(struct stmmac_priv *priv, u32 chan) stmmac_stop_tx(priv, priv->ioaddr, chan); } +static void stmmac_enable_all_dma_irq(struct stmmac_priv *priv) +{ + u32 rx_channels_count = priv->plat->rx_queues_to_use; + u32 tx_channels_count = priv->plat->tx_queues_to_use; + u32 dma_csr_ch = max(rx_channels_count, tx_channels_count); + u32 chan; + + for (chan = 0; chan < dma_csr_ch; chan++) { + struct stmmac_channel *ch = &priv->channel[chan]; + unsigned long flags; + + spin_lock_irqsave(&ch->lock, flags); + stmmac_enable_dma_irq(priv, priv->ioaddr, chan, 1, 1); + spin_unlock_irqrestore(&ch->lock, flags); + } +} + /** * stmmac_start_all_dma - start all RX and TX DMA channels * @priv: driver private structure @@ -2904,8 +2921,10 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) stmmac_axi(priv, priv->ioaddr, priv->plat->axi); /* DMA CSR Channel configuration */ - for (chan = 0; chan < dma_csr_ch; chan++) + for (chan = 0; chan < dma_csr_ch; chan++) { stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan); + stmmac_disable_dma_irq(priv, priv->ioaddr, chan, 1, 1); + } /* DMA RX Channel Configuration */ for (chan = 0; chan < rx_channels_count; chan++) { @@ -3761,6 +3780,7 @@ static int stmmac_open(struct net_device *dev) stmmac_enable_all_queues(priv); netif_tx_start_all_queues(priv->dev); + stmmac_enable_all_dma_irq(priv); return 0; @@ -6510,8 +6530,10 @@ int stmmac_xdp_open(struct net_device *dev) } /* DMA CSR Channel configuration */ - for (chan = 0; chan < dma_csr_ch; chan++) + for (chan = 0; chan < dma_csr_ch; chan++) { stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan); + stmmac_disable_dma_irq(priv, priv->ioaddr, chan, 1, 1); + } /* Adjust Split header */ sph_en = (priv->hw->rx_csum > 0) && priv->sph; @@ -6572,6 +6594,7 @@ int stmmac_xdp_open(struct net_device *dev) stmmac_enable_all_queues(priv); netif_carrier_on(dev); netif_tx_start_all_queues(dev); + stmmac_enable_all_dma_irq(priv); return 0; @@ -7451,6 +7474,7 @@ int stmmac_resume(struct device *dev) stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw); stmmac_enable_all_queues(priv); + stmmac_enable_all_dma_irq(priv); mutex_unlock(&priv->lock); rtnl_unlock(); @@ -7467,7 +7491,7 @@ static int __init stmmac_cmdline_opt(char *str) char *opt; if (!str || !*str) - return -EINVAL; + return 1; while ((opt = strsep(&str, ",")) != NULL) { if (!strncmp(opt, "debug:", 6)) { if (kstrtoint(opt + 6, 0, &debug)) @@ -7498,11 +7522,11 @@ static int __init stmmac_cmdline_opt(char *str) goto err; } } - return 0; + return 1; err: pr_err("%s: ERROR broken module parameter conversion", __func__); - return -EINVAL; + return 1; } __setup("stmmaceth=", stmmac_cmdline_opt); 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/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index b900ab5aef2a..64c7e26c3b75 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -1433,6 +1433,8 @@ static int temac_probe(struct platform_device *pdev) lp->indirect_lock = devm_kmalloc(&pdev->dev, sizeof(*lp->indirect_lock), GFP_KERNEL); + if (!lp->indirect_lock) + return -ENOMEM; spin_lock_init(lp->indirect_lock); } diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 519599480b15..77fa2cb03aca 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/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index b1fc153125d9..45c3c4a1101b 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -668,11 +668,11 @@ static void sixpack_close(struct tty_struct *tty) */ netif_stop_queue(sp->dev); + unregister_netdev(sp->dev); + del_timer_sync(&sp->tx_t); del_timer_sync(&sp->resync_t); - unregister_netdev(sp->dev); - /* Free all 6pack frame buffers after unreg. */ kfree(sp->rbuff); kfree(sp->xbuff); diff --git a/drivers/net/ipa/Kconfig b/drivers/net/ipa/Kconfig index d037682fb7ad..6782c2cbf542 100644 --- a/drivers/net/ipa/Kconfig +++ b/drivers/net/ipa/Kconfig @@ -2,7 +2,9 @@ config QCOM_IPA tristate "Qualcomm IPA support" depends on NET && QCOM_SMEM depends on ARCH_QCOM || COMPILE_TEST + depends on INTERCONNECT depends on QCOM_RPROC_COMMON || (QCOM_RPROC_COMMON=n && COMPILE_TEST) + depends on QCOM_AOSS_QMP || QCOM_AOSS_QMP=n select QCOM_MDT_LOADER if ARCH_QCOM select QCOM_SCM select QCOM_QMI_HELPERS diff --git a/drivers/net/mdio/mdio-ipq4019.c b/drivers/net/mdio/mdio-ipq4019.c index 5f4cd24a0241..4eba5a91075c 100644 --- a/drivers/net/mdio/mdio-ipq4019.c +++ b/drivers/net/mdio/mdio-ipq4019.c @@ -200,7 +200,11 @@ static int ipq_mdio_reset(struct mii_bus *bus) if (ret) return ret; - return clk_prepare_enable(priv->mdio_clk); + ret = clk_prepare_enable(priv->mdio_clk); + if (ret == 0) + mdelay(10); + + return ret; } static int ipq4019_mdio_probe(struct platform_device *pdev) 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 bc1e3dd67c04..a0f29482294d 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -84,9 +84,10 @@ 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; } @@ -116,7 +117,7 @@ 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); @@ -159,6 +160,9 @@ 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; } @@ -194,7 +198,8 @@ 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; } @@ -206,7 +211,8 @@ 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; } @@ -214,6 +220,10 @@ 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; } @@ -235,7 +245,8 @@ 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; } @@ -243,7 +254,8 @@ 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/usb/sr9700.c b/drivers/net/usb/sr9700.c index b658510cc9a4..5a53e63d33a6 100644 --- a/drivers/net/usb/sr9700.c +++ b/drivers/net/usb/sr9700.c @@ -413,7 +413,7 @@ static int sr9700_rx_fixup(struct usbnet *dev, struct sk_buff *skb) /* ignore the CRC length */ len = (skb->data[1] | (skb->data[2] << 8)) - 4; - if (len > ETH_FRAME_LEN) + if (len > ETH_FRAME_LEN || len > skb->len) return 0; /* the last packet of current skb */ diff --git a/drivers/net/wireless/intel/Makefile b/drivers/net/wireless/intel/Makefile index 1364b0014488..208e73a16051 100644 --- a/drivers/net/wireless/intel/Makefile +++ b/drivers/net/wireless/intel/Makefile @@ -5,3 +5,4 @@ obj-$(CONFIG_IPW2200) += ipw2x00/ obj-$(CONFIG_IWLEGACY) += iwlegacy/ obj-$(CONFIG_IWLWIFI) += iwlwifi/ +obj-$(CONFIG_IWLMEI) += iwlwifi/ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index dd58c8f9aa11..04addf964d83 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -553,8 +553,7 @@ static const struct ieee80211_sband_iftype_data iwl_he_capa[] = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = - IEEE80211_HE_MAC_CAP0_HTC_HE | - IEEE80211_HE_MAC_CAP0_TWT_REQ, + IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index 63432c24eb59..445c94adb076 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -5,6 +5,7 @@ * Copyright (C) 2016-2017 Intel Deutschland GmbH */ #include <linux/vmalloc.h> +#include <linux/err.h> #include <linux/ieee80211.h> #include <linux/netdevice.h> @@ -1857,7 +1858,6 @@ void iwl_mvm_sta_add_debugfs(struct ieee80211_hw *hw, void iwl_mvm_dbgfs_register(struct iwl_mvm *mvm) { struct dentry *bcast_dir __maybe_unused; - char buf[100]; spin_lock_init(&mvm->drv_stats_lock); @@ -1939,6 +1939,11 @@ void iwl_mvm_dbgfs_register(struct iwl_mvm *mvm) * Create a symlink with mac80211. It will be removed when mac80211 * exists (before the opmode exists which removes the target.) */ - snprintf(buf, 100, "../../%pd2", mvm->debugfs_dir->d_parent); - debugfs_create_symlink("iwlwifi", mvm->hw->wiphy->debugfsdir, buf); + if (!IS_ERR(mvm->debugfs_dir)) { + char buf[100]; + + snprintf(buf, 100, "../../%pd2", mvm->debugfs_dir->d_parent); + debugfs_create_symlink("iwlwifi", mvm->hw->wiphy->debugfsdir, + buf); + } } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 4ac599f6ad22..709a3df57b10 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -226,7 +226,6 @@ static const u8 he_if_types_ext_capa_sta[] = { [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING, [2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT, [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF, - [9] = WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT, }; static const struct wiphy_iftype_ext_capab he_iftypes_ext_capa[] = { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/vendor-cmd.c b/drivers/net/wireless/intel/iwlwifi/mvm/vendor-cmd.c index 78450366312b..080a1587caa5 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/vendor-cmd.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/vendor-cmd.c @@ -71,12 +71,13 @@ static int iwl_mvm_vendor_host_get_ownership(struct wiphy *wiphy, { struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy); struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); + int ret; mutex_lock(&mvm->mutex); - iwl_mvm_mei_get_ownership(mvm); + ret = iwl_mvm_mei_get_ownership(mvm); mutex_unlock(&mvm->mutex); - return 0; + return ret; } static const struct wiphy_vendor_command iwl_mvm_vendor_commands[] = { diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index d24b7a7993aa..990360d75cb6 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -256,6 +256,7 @@ static void backend_disconnect(struct backend_info *be) unsigned int queue_index; xen_unregister_watchers(vif); + xenbus_rm(XBT_NIL, be->dev->nodename, "hotplug-status"); #ifdef CONFIG_DEBUG_FS xenvif_debugfs_delif(vif); #endif /* CONFIG_DEBUG_FS */ @@ -675,7 +676,6 @@ static void hotplug_status_changed(struct xenbus_watch *watch, /* Not interested in this watch anymore. */ unregister_hotplug_status_watch(be); - xenbus_rm(XBT_NIL, be->dev->nodename, "hotplug-status"); } kfree(str); } @@ -824,15 +824,11 @@ static void connect(struct backend_info *be) xenvif_carrier_on(be->vif); unregister_hotplug_status_watch(be); - if (xenbus_exists(XBT_NIL, dev->nodename, "hotplug-status")) { - err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, - NULL, hotplug_status_changed, - "%s/%s", dev->nodename, - "hotplug-status"); - if (err) - goto err; + err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, NULL, + hotplug_status_changed, + "%s/%s", dev->nodename, "hotplug-status"); + if (!err) be->have_hotplug_status_watch = 1; - } netif_tx_wake_all_queues(be->vif->dev); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 8b18246ad999..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; @@ -842,6 +840,28 @@ static int xennet_close(struct net_device *dev) return 0; } +static void xennet_destroy_queues(struct netfront_info *info) +{ + unsigned int i; + + for (i = 0; i < info->netdev->real_num_tx_queues; i++) { + struct netfront_queue *queue = &info->queues[i]; + + if (netif_running(info->netdev)) + napi_disable(&queue->napi); + netif_napi_del(&queue->napi); + } + + kfree(info->queues); + info->queues = NULL; +} + +static void xennet_uninit(struct net_device *dev) +{ + struct netfront_info *np = netdev_priv(dev); + xennet_destroy_queues(np); +} + static void xennet_set_rx_rsp_cons(struct netfront_queue *queue, RING_IDX val) { unsigned long flags; @@ -968,7 +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; @@ -1010,8 +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); @@ -1232,6 +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); @@ -1611,6 +1639,7 @@ static int xennet_xdp(struct net_device *dev, struct netdev_bpf *xdp) } static const struct net_device_ops xennet_netdev_ops = { + .ndo_uninit = xennet_uninit, .ndo_open = xennet_open, .ndo_stop = xennet_close, .ndo_start_xmit = xennet_start_xmit, @@ -1895,7 +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; @@ -1915,21 +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) @@ -1942,22 +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; } @@ -2103,22 +2138,6 @@ error: return err; } -static void xennet_destroy_queues(struct netfront_info *info) -{ - unsigned int i; - - for (i = 0; i < info->netdev->real_num_tx_queues; i++) { - struct netfront_queue *queue = &info->queues[i]; - - if (netif_running(info->netdev)) - napi_disable(&queue->napi); - netif_napi_del(&queue->napi); - } - - kfree(info->queues); - info->queues = NULL; -} - static int xennet_create_page_pool(struct netfront_queue *queue) 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/ntb/hw/intel/ntb_hw_gen4.c b/drivers/ntb/hw/intel/ntb_hw_gen4.c index fede05151f69..4081fc538ff4 100644 --- a/drivers/ntb/hw/intel/ntb_hw_gen4.c +++ b/drivers/ntb/hw/intel/ntb_hw_gen4.c @@ -168,6 +168,18 @@ static enum ntb_topo gen4_ppd_topo(struct intel_ntb_dev *ndev, u32 ppd) return NTB_TOPO_NONE; } +static enum ntb_topo spr_ppd_topo(struct intel_ntb_dev *ndev, u32 ppd) +{ + switch (ppd & SPR_PPD_TOPO_MASK) { + case SPR_PPD_TOPO_B2B_USD: + return NTB_TOPO_B2B_USD; + case SPR_PPD_TOPO_B2B_DSD: + return NTB_TOPO_B2B_DSD; + } + + return NTB_TOPO_NONE; +} + int gen4_init_dev(struct intel_ntb_dev *ndev) { struct pci_dev *pdev = ndev->ntb.pdev; @@ -183,7 +195,10 @@ int gen4_init_dev(struct intel_ntb_dev *ndev) } ppd1 = ioread32(ndev->self_mmio + GEN4_PPD1_OFFSET); - ndev->ntb.topo = gen4_ppd_topo(ndev, ppd1); + if (pdev_is_ICX(pdev)) + ndev->ntb.topo = gen4_ppd_topo(ndev, ppd1); + else if (pdev_is_SPR(pdev)) + ndev->ntb.topo = spr_ppd_topo(ndev, ppd1); dev_dbg(&pdev->dev, "ppd %#x topo %s\n", ppd1, ntb_topo_string(ndev->ntb.topo)); if (ndev->ntb.topo == NTB_TOPO_NONE) diff --git a/drivers/ntb/hw/intel/ntb_hw_gen4.h b/drivers/ntb/hw/intel/ntb_hw_gen4.h index 3fcd3fdce9ed..f91323eaf5ce 100644 --- a/drivers/ntb/hw/intel/ntb_hw_gen4.h +++ b/drivers/ntb/hw/intel/ntb_hw_gen4.h @@ -49,10 +49,14 @@ #define GEN4_PPD_CLEAR_TRN 0x0001 #define GEN4_PPD_LINKTRN 0x0008 #define GEN4_PPD_CONN_MASK 0x0300 +#define SPR_PPD_CONN_MASK 0x0700 #define GEN4_PPD_CONN_B2B 0x0200 #define GEN4_PPD_DEV_MASK 0x1000 #define GEN4_PPD_DEV_DSD 0x1000 #define GEN4_PPD_DEV_USD 0x0000 +#define SPR_PPD_DEV_MASK 0x4000 +#define SPR_PPD_DEV_DSD 0x4000 +#define SPR_PPD_DEV_USD 0x0000 #define GEN4_LINK_CTRL_LINK_DISABLE 0x0010 #define GEN4_SLOTSTS 0xb05a @@ -62,6 +66,10 @@ #define GEN4_PPD_TOPO_B2B_USD (GEN4_PPD_CONN_B2B | GEN4_PPD_DEV_USD) #define GEN4_PPD_TOPO_B2B_DSD (GEN4_PPD_CONN_B2B | GEN4_PPD_DEV_DSD) +#define SPR_PPD_TOPO_MASK (SPR_PPD_CONN_MASK | SPR_PPD_DEV_MASK) +#define SPR_PPD_TOPO_B2B_USD (GEN4_PPD_CONN_B2B | SPR_PPD_DEV_USD) +#define SPR_PPD_TOPO_B2B_DSD (GEN4_PPD_CONN_B2B | SPR_PPD_DEV_DSD) + #define GEN4_DB_COUNT 32 #define GEN4_DB_LINK 32 #define GEN4_DB_LINK_BIT BIT_ULL(GEN4_DB_LINK) @@ -112,4 +120,12 @@ static inline int pdev_is_ICX(struct pci_dev *pdev) return 0; } +static inline int pdev_is_SPR(struct pci_dev *pdev) +{ + if (pdev_is_gen4(pdev) && + pdev->revision > PCI_DEVICE_REVISION_ICX_MAX) + return 1; + return 0; +} + #endif diff --git a/drivers/ntb/msi.c b/drivers/ntb/msi.c index dd683cb58d09..6295e55ef85e 100644 --- a/drivers/ntb/msi.c +++ b/drivers/ntb/msi.c @@ -33,7 +33,6 @@ int ntb_msi_init(struct ntb_dev *ntb, { phys_addr_t mw_phys_addr; resource_size_t mw_size; - size_t struct_size; int peer_widx; int peers; int ret; @@ -43,9 +42,8 @@ int ntb_msi_init(struct ntb_dev *ntb, if (peers <= 0) return -EINVAL; - struct_size = sizeof(*ntb->msi) + sizeof(*ntb->msi->peer_mws) * peers; - - ntb->msi = devm_kzalloc(&ntb->dev, struct_size, GFP_KERNEL); + ntb->msi = devm_kzalloc(&ntb->dev, struct_size(ntb->msi, peer_mws, peers), + GFP_KERNEL); if (!ntb->msi) return -ENOMEM; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 469f23186159..fd4720d37cc0 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1723,7 +1723,7 @@ static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns, return 0; } -static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) +static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) { struct nvme_ctrl *ctrl = ns->ctrl; @@ -1739,7 +1739,8 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS); if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)) - return 0; + return; + if (ctrl->ops->flags & NVME_F_FABRICS) { /* * The NVMe over Fabrics specification only supports metadata as @@ -1747,7 +1748,7 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) * remap the separate metadata buffer from the block layer. */ if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT))) - return -EINVAL; + return; ns->features |= NVME_NS_EXT_LBAS; @@ -1774,8 +1775,6 @@ static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id) else ns->features |= NVME_NS_METADATA_SUPPORTED; } - - return 0; } static void nvme_set_queue_limits(struct nvme_ctrl *ctrl, @@ -1916,9 +1915,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) ns->lba_shift = id->lbaf[lbaf].ds; nvme_set_queue_limits(ns->ctrl, ns->queue); - ret = nvme_configure_metadata(ns, id); - if (ret) - goto out_unfreeze; + nvme_configure_metadata(ns, id); nvme_set_chunk_sectors(ns, id); nvme_update_disk_info(ns->disk, ns, id); @@ -1934,7 +1931,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) if (blk_queue_is_zoned(ns->queue)) { ret = nvme_revalidate_zones(ns); if (ret && !nvme_first_scan(ns->disk)) - goto out; + return ret; } if (nvme_ns_head_multipath(ns->head)) { @@ -1949,16 +1946,16 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_id_ns *id) return 0; out_unfreeze: - blk_mq_unfreeze_queue(ns->disk->queue); -out: /* * If probing fails due an unsupported feature, hide the block device, * but still allow other access. */ if (ret == -ENODEV) { ns->disk->flags |= GENHD_FL_HIDDEN; + set_bit(NVME_NS_READY, &ns->flags); ret = 0; } + blk_mq_unfreeze_queue(ns->disk->queue); return ret; } diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 891a36d02e7c..65e00c64a588 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -44,6 +44,8 @@ struct nvme_tcp_request { u32 data_len; u32 pdu_len; u32 pdu_sent; + u32 h2cdata_left; + u32 h2cdata_offset; u16 ttag; __le16 status; struct list_head entry; @@ -95,6 +97,7 @@ struct nvme_tcp_queue { struct nvme_tcp_request *request; int queue_size; + u32 maxh2cdata; size_t cmnd_capsule_len; struct nvme_tcp_ctrl *ctrl; unsigned long flags; @@ -572,23 +575,26 @@ static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue, return ret; } -static void nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, - struct nvme_tcp_r2t_pdu *pdu) +static void nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req) { struct nvme_tcp_data_pdu *data = req->pdu; struct nvme_tcp_queue *queue = req->queue; struct request *rq = blk_mq_rq_from_pdu(req); + u32 h2cdata_sent = req->pdu_len; u8 hdgst = nvme_tcp_hdgst_len(queue); u8 ddgst = nvme_tcp_ddgst_len(queue); req->state = NVME_TCP_SEND_H2C_PDU; req->offset = 0; - req->pdu_len = le32_to_cpu(pdu->r2t_length); + req->pdu_len = min(req->h2cdata_left, queue->maxh2cdata); req->pdu_sent = 0; + req->h2cdata_left -= req->pdu_len; + req->h2cdata_offset += h2cdata_sent; memset(data, 0, sizeof(*data)); data->hdr.type = nvme_tcp_h2c_data; - data->hdr.flags = NVME_TCP_F_DATA_LAST; + if (!req->h2cdata_left) + data->hdr.flags = NVME_TCP_F_DATA_LAST; if (queue->hdr_digest) data->hdr.flags |= NVME_TCP_F_HDGST; if (queue->data_digest) @@ -597,9 +603,9 @@ static void nvme_tcp_setup_h2c_data_pdu(struct nvme_tcp_request *req, data->hdr.pdo = data->hdr.hlen + hdgst; data->hdr.plen = cpu_to_le32(data->hdr.hlen + hdgst + req->pdu_len + ddgst); - data->ttag = pdu->ttag; + data->ttag = req->ttag; data->command_id = nvme_cid(rq); - data->data_offset = pdu->r2t_offset; + data->data_offset = cpu_to_le32(req->h2cdata_offset); data->data_length = cpu_to_le32(req->pdu_len); } @@ -609,6 +615,7 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, struct nvme_tcp_request *req; struct request *rq; u32 r2t_length = le32_to_cpu(pdu->r2t_length); + u32 r2t_offset = le32_to_cpu(pdu->r2t_offset); rq = nvme_find_rq(nvme_tcp_tagset(queue), pdu->command_id); if (!rq) { @@ -633,14 +640,19 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, return -EPROTO; } - if (unlikely(le32_to_cpu(pdu->r2t_offset) < req->data_sent)) { + if (unlikely(r2t_offset < req->data_sent)) { dev_err(queue->ctrl->ctrl.device, "req %d unexpected r2t offset %u (expected %zu)\n", - rq->tag, le32_to_cpu(pdu->r2t_offset), req->data_sent); + rq->tag, r2t_offset, req->data_sent); return -EPROTO; } - nvme_tcp_setup_h2c_data_pdu(req, pdu); + req->pdu_len = 0; + req->h2cdata_left = r2t_length; + req->h2cdata_offset = r2t_offset; + req->ttag = pdu->ttag; + + nvme_tcp_setup_h2c_data_pdu(req); nvme_tcp_queue_request(req, false, true); return 0; @@ -928,6 +940,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) { struct nvme_tcp_queue *queue = req->queue; int req_data_len = req->data_len; + u32 h2cdata_left = req->h2cdata_left; while (true) { struct page *page = nvme_tcp_req_cur_page(req); @@ -972,7 +985,10 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req) req->state = NVME_TCP_SEND_DDGST; req->offset = 0; } else { - nvme_tcp_done_send_req(queue); + if (h2cdata_left) + nvme_tcp_setup_h2c_data_pdu(req); + else + nvme_tcp_done_send_req(queue); } return 1; } @@ -1030,9 +1046,14 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req) if (queue->hdr_digest && !req->offset) nvme_tcp_hdgst(queue->snd_hash, pdu, sizeof(*pdu)); - ret = kernel_sendpage(queue->sock, virt_to_page(pdu), - offset_in_page(pdu) + req->offset, len, - MSG_DONTWAIT | MSG_MORE | MSG_SENDPAGE_NOTLAST); + if (!req->h2cdata_left) + ret = kernel_sendpage(queue->sock, virt_to_page(pdu), + offset_in_page(pdu) + req->offset, len, + MSG_DONTWAIT | MSG_MORE | MSG_SENDPAGE_NOTLAST); + else + ret = sock_no_sendpage(queue->sock, virt_to_page(pdu), + offset_in_page(pdu) + req->offset, len, + MSG_DONTWAIT | MSG_MORE); if (unlikely(ret <= 0)) return ret; @@ -1052,6 +1073,7 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req) { struct nvme_tcp_queue *queue = req->queue; size_t offset = req->offset; + u32 h2cdata_left = req->h2cdata_left; int ret; struct msghdr msg = { .msg_flags = MSG_DONTWAIT }; struct kvec iov = { @@ -1069,7 +1091,10 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req) return ret; if (offset + ret == NVME_TCP_DIGEST_LENGTH) { - nvme_tcp_done_send_req(queue); + if (h2cdata_left) + nvme_tcp_setup_h2c_data_pdu(req); + else + nvme_tcp_done_send_req(queue); return 1; } @@ -1261,6 +1286,7 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) struct msghdr msg = {}; struct kvec iov; bool ctrl_hdgst, ctrl_ddgst; + u32 maxh2cdata; int ret; icreq = kzalloc(sizeof(*icreq), GFP_KERNEL); @@ -1344,6 +1370,14 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) goto free_icresp; } + maxh2cdata = le32_to_cpu(icresp->maxdata); + if ((maxh2cdata % 4) || (maxh2cdata < NVME_TCP_MIN_MAXH2CDATA)) { + pr_err("queue %d: invalid maxh2cdata returned %u\n", + nvme_tcp_queue_id(queue), maxh2cdata); + goto free_icresp; + } + queue->maxh2cdata = maxh2cdata; + ret = 0; free_icresp: kfree(icresp); @@ -2329,6 +2363,7 @@ static blk_status_t nvme_tcp_setup_cmd_pdu(struct nvme_ns *ns, req->data_sent = 0; req->pdu_len = 0; req->pdu_sent = 0; + req->h2cdata_left = 0; req->data_len = blk_rq_nr_phys_segments(rq) ? blk_rq_payload_bytes(rq) : 0; req->curr_bio = rq->bio; diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 23a38dcf0fc4..9fd1602b539d 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -771,7 +771,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (config->wp_gpio) nvmem->wp_gpio = config->wp_gpio; - else + else if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index ad85ff6474ff..ec315b060cd5 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -648,8 +648,8 @@ void __init early_init_fdt_scan_reserved_mem(void) } fdt_scan_reserved_mem(); - fdt_init_reserved_mem(); fdt_reserve_elfcorehdr(); + fdt_init_reserved_mem(); } /** diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 70992103c07d..2c2fb161b572 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -513,24 +513,24 @@ static void __init of_unittest_parse_phandle_with_args(void) memset(&args, 0, sizeof(args)); EXPECT_BEGIN(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-a: #phandle-cells = 3 found -1"); + "OF: /testcase-data/phandle-tests/consumer-a: #phandle-cells = 3 found 1"); rc = of_parse_phandle_with_args(np, "phandle-list-bad-args", "#phandle-cells", 1, &args); EXPECT_END(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-a: #phandle-cells = 3 found -1"); + "OF: /testcase-data/phandle-tests/consumer-a: #phandle-cells = 3 found 1"); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); EXPECT_BEGIN(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-a: #phandle-cells = 3 found -1"); + "OF: /testcase-data/phandle-tests/consumer-a: #phandle-cells = 3 found 1"); rc = of_count_phandle_with_args(np, "phandle-list-bad-args", "#phandle-cells"); EXPECT_END(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-a: #phandle-cells = 3 found -1"); + "OF: /testcase-data/phandle-tests/consumer-a: #phandle-cells = 3 found 1"); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); } @@ -670,12 +670,12 @@ static void __init of_unittest_parse_phandle_with_args_map(void) memset(&args, 0, sizeof(args)); EXPECT_BEGIN(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-b: #phandle-cells = 2 found -1"); + "OF: /testcase-data/phandle-tests/consumer-b: #phandle-cells = 2 found 1"); rc = of_parse_phandle_with_args_map(np, "phandle-list-bad-args", "phandle", 1, &args); EXPECT_END(KERN_INFO, - "OF: /testcase-data/phandle-tests/consumer-b: #phandle-cells = 2 found -1"); + "OF: /testcase-data/phandle-tests/consumer-b: #phandle-cells = 2 found 1"); unittest(rc == -EINVAL, "expected:%i got:%i\n", -EINVAL, rc); } @@ -1257,12 +1257,12 @@ static void __init of_unittest_platform_populate(void) unittest(pdev, "device 2 creation failed\n"); EXPECT_BEGIN(KERN_INFO, - "platform testcase-data:testcase-device2: IRQ index 0 not found"); + "platform testcase-data:testcase-device2: error -ENXIO: IRQ index 0 not found"); irq = platform_get_irq(pdev, 0); EXPECT_END(KERN_INFO, - "platform testcase-data:testcase-device2: IRQ index 0 not found"); + "platform testcase-data:testcase-device2: error -ENXIO: IRQ index 0 not found"); unittest(irq < 0 && irq != -EPROBE_DEFER, "device parsing error failed - %d\n", irq); diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index 71258ea3d35f..f8e82c5e2d87 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -1329,7 +1329,8 @@ static int mvebu_pcie_probe(struct platform_device *pdev) * indirectly via kernel emulated PCI bridge driver. */ mvebu_pcie_setup_hw(port); - mvebu_pcie_set_local_dev_nr(port, 0); + mvebu_pcie_set_local_dev_nr(port, 1); + mvebu_pcie_set_local_bus_nr(port, 0); } pcie->nports = i; diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index cc166c683638..eb05cceab964 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -99,11 +99,13 @@ struct vmd_irq { * @srcu: SRCU struct for local synchronization. * @count: number of child IRQs assigned to this vector; used to track * sharing. + * @virq: The underlying VMD Linux interrupt number */ struct vmd_irq_list { struct list_head irq_list; struct srcu_struct srcu; unsigned int count; + unsigned int virq; }; struct vmd_dev { @@ -253,7 +255,6 @@ static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info, struct msi_desc *desc = arg->desc; struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(desc)->bus); struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); - unsigned int index, vector; if (!vmdirq) return -ENOMEM; @@ -261,10 +262,8 @@ static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info, INIT_LIST_HEAD(&vmdirq->node); vmdirq->irq = vmd_next_irq(vmd, desc); vmdirq->virq = virq; - index = index_from_irqs(vmd, vmdirq->irq); - vector = pci_irq_vector(vmd->dev, index); - irq_domain_set_info(domain, virq, vector, info->chip, vmdirq, + irq_domain_set_info(domain, virq, vmdirq->irq->virq, info->chip, vmdirq, handle_untracked_irq, vmd, NULL); return 0; } @@ -685,7 +684,8 @@ static int vmd_alloc_irqs(struct vmd_dev *vmd) return err; INIT_LIST_HEAD(&vmd->irqs[i].irq_list); - err = devm_request_irq(&dev->dev, pci_irq_vector(dev, i), + vmd->irqs[i].virq = pci_irq_vector(dev, i); + err = devm_request_irq(&dev->dev, vmd->irqs[i].virq, vmd_irq, IRQF_NO_THREAD, vmd->name, &vmd->irqs[i]); if (err) @@ -969,7 +969,7 @@ static int vmd_suspend(struct device *dev) int i; for (i = 0; i < vmd->msix_count; i++) - devm_free_irq(dev, pci_irq_vector(pdev, i), &vmd->irqs[i]); + devm_free_irq(dev, vmd->irqs[i].virq, &vmd->irqs[i]); return 0; } @@ -981,7 +981,7 @@ static int vmd_resume(struct device *dev) int err, i; for (i = 0; i < vmd->msix_count; i++) { - err = devm_request_irq(dev, pci_irq_vector(pdev, i), + err = devm_request_irq(dev, vmd->irqs[i].virq, vmd_irq, IRQF_NO_THREAD, vmd->name, &vmd->irqs[i]); if (err) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index d2dd6a6cda60..65f7f6b0576c 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5344,11 +5344,6 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags); */ static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) { - if ((pdev->device == 0x7312 && pdev->revision != 0x00) || - (pdev->device == 0x7340 && pdev->revision != 0xc5) || - (pdev->device == 0x7341 && pdev->revision != 0x00)) - return; - if (pdev->device == 0x15d8) { if (pdev->revision == 0xcf && pdev->subsystem_vendor == 0xea50 && @@ -5370,10 +5365,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats); /* AMD Iceland dGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats); /* AMD Navi10 dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7310, quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7312, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7318, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7319, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731a, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731b, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731e, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x731f, quirk_amd_harvest_no_ats); /* AMD Navi14 dGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7341, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7347, quirk_amd_harvest_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x734f, quirk_amd_harvest_no_ats); /* AMD Raven platform iGPU */ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x15d8, quirk_amd_harvest_no_ats); #endif /* CONFIG_PCI_ATS */ diff --git a/drivers/pinctrl/intel/pinctrl-tigerlake.c b/drivers/pinctrl/intel/pinctrl-tigerlake.c index 0bcd19597e4a..3ddaeffc0415 100644 --- a/drivers/pinctrl/intel/pinctrl-tigerlake.c +++ b/drivers/pinctrl/intel/pinctrl-tigerlake.c @@ -749,7 +749,6 @@ static const struct acpi_device_id tgl_pinctrl_acpi_match[] = { { "INT34C5", (kernel_ulong_t)&tgllp_soc_data }, { "INT34C6", (kernel_ulong_t)&tglh_soc_data }, { "INTC1055", (kernel_ulong_t)&tgllp_soc_data }, - { "INTC1057", (kernel_ulong_t)&tgllp_soc_data }, { } }; MODULE_DEVICE_TABLE(acpi, tgl_pinctrl_acpi_match); diff --git a/drivers/pinctrl/pinctrl-k210.c b/drivers/pinctrl/pinctrl-k210.c index 49e32684dbb2..ecab6bf63dc6 100644 --- a/drivers/pinctrl/pinctrl-k210.c +++ b/drivers/pinctrl/pinctrl-k210.c @@ -482,7 +482,7 @@ static int k210_pinconf_get_drive(unsigned int max_strength_ua) { int i; - for (i = K210_PC_DRIVE_MAX; i; i--) { + for (i = K210_PC_DRIVE_MAX; i >= 0; i--) { if (k210_pinconf_drive_strength[i] <= max_strength_ua) return i; } @@ -527,7 +527,7 @@ static int k210_pinconf_set_param(struct pinctrl_dev *pctldev, case PIN_CONFIG_BIAS_PULL_UP: if (!arg) return -EINVAL; - val |= K210_PC_PD; + val |= K210_PC_PU; break; case PIN_CONFIG_DRIVE_STRENGTH: arg *= 1000; diff --git a/drivers/pinctrl/pinctrl-starfive.c b/drivers/pinctrl/pinctrl-starfive.c index 0b912152a405..266da41a6162 100644 --- a/drivers/pinctrl/pinctrl-starfive.c +++ b/drivers/pinctrl/pinctrl-starfive.c @@ -1164,6 +1164,7 @@ static int starfive_irq_set_type(struct irq_data *d, unsigned int trigger) } static struct irq_chip starfive_irq_chip = { + .name = "StarFive GPIO", .irq_ack = starfive_irq_ack, .irq_mask = starfive_irq_mask, .irq_mask_ack = starfive_irq_mask_ack, @@ -1308,7 +1309,6 @@ static int starfive_probe(struct platform_device *pdev) sfp->gc.ngpio = NR_GPIOS; starfive_irq_chip.parent_device = dev; - starfive_irq_chip.name = sfp->gc.label; sfp->gc.irq.chip = &starfive_irq_chip; sfp->gc.irq.parent_handler = starfive_gpio_irq_handler; 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/platform/surface/surface3_power.c b/drivers/platform/surface/surface3_power.c index abac3eec565e..444ec81ba02d 100644 --- a/drivers/platform/surface/surface3_power.c +++ b/drivers/platform/surface/surface3_power.c @@ -232,14 +232,21 @@ static int mshw0011_bix(struct mshw0011_data *cdata, struct bix *bix) } bix->last_full_charg_capacity = ret; - /* get serial number */ + /* + * Get serial number, on some devices (with unofficial replacement + * battery?) reading any of the serial number range addresses gets + * nacked in this case just leave the serial number empty. + */ ret = i2c_smbus_read_i2c_block_data(client, MSHW0011_BAT0_REG_SERIAL_NO, sizeof(buf), buf); - if (ret != sizeof(buf)) { + if (ret == -EREMOTEIO) { + /* no serial number available */ + } else if (ret != sizeof(buf)) { dev_err(&client->dev, "Error reading serial no: %d\n", ret); return ret; + } else { + snprintf(bix->serial, ARRAY_SIZE(bix->serial), "%3pE%6pE", buf + 7, buf); } - snprintf(bix->serial, ARRAY_SIZE(bix->serial), "%3pE%6pE", buf + 7, buf); /* get cycle count */ ret = i2c_smbus_read_word_data(client, MSHW0011_BAT0_REG_CYCLE_CNT); diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c index 4c72ba68b315..b1103f85a85a 100644 --- a/drivers/platform/x86/amd-pmc.c +++ b/drivers/platform/x86/amd-pmc.c @@ -21,6 +21,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/platform_device.h> +#include <linux/pm_qos.h> #include <linux/rtc.h> #include <linux/suspend.h> #include <linux/seq_file.h> @@ -85,6 +86,9 @@ #define PMC_MSG_DELAY_MIN_US 50 #define RESPONSE_REGISTER_LOOP_MAX 20000 +/* QoS request for letting CPUs in idle states, but not the deepest */ +#define AMD_PMC_MAX_IDLE_STATE_LATENCY 3 + #define SOC_SUBSYSTEM_IP_MAX 12 #define DELAY_MIN_US 2000 #define DELAY_MAX_US 3000 @@ -131,6 +135,7 @@ struct amd_pmc_dev { struct device *dev; struct pci_dev *rdev; struct mutex lock; /* generic mutex lock */ + struct pm_qos_request amd_pmc_pm_qos_req; #if IS_ENABLED(CONFIG_DEBUG_FS) struct dentry *dbgfs_dir; #endif /* CONFIG_DEBUG_FS */ @@ -521,6 +526,14 @@ static int amd_pmc_verify_czn_rtc(struct amd_pmc_dev *pdev, u32 *arg) rc = rtc_alarm_irq_enable(rtc_device, 0); dev_dbg(pdev->dev, "wakeup timer programmed for %lld seconds\n", duration); + /* + * Prevent CPUs from getting into deep idle states while sending OS_HINT + * which is otherwise generally safe to send when at least one of the CPUs + * is not in deep idle states. + */ + cpu_latency_qos_update_request(&pdev->amd_pmc_pm_qos_req, AMD_PMC_MAX_IDLE_STATE_LATENCY); + wake_up_all_idle_cpus(); + return rc; } @@ -538,24 +551,31 @@ static int __maybe_unused amd_pmc_suspend(struct device *dev) /* Activate CZN specific RTC functionality */ if (pdev->cpu_id == AMD_CPU_ID_CZN) { rc = amd_pmc_verify_czn_rtc(pdev, &arg); - if (rc < 0) - return rc; + if (rc) + goto fail; } /* Dump the IdleMask before we send hint to SMU */ amd_pmc_idlemask_read(pdev, dev, NULL); msg = amd_pmc_get_os_hint(pdev); rc = amd_pmc_send_cmd(pdev, arg, NULL, msg, 0); - if (rc) + if (rc) { dev_err(pdev->dev, "suspend failed\n"); + goto fail; + } if (enable_stb) rc = amd_pmc_write_stb(pdev, AMD_PMC_STB_PREDEF); - if (rc) { + if (rc) { dev_err(pdev->dev, "error writing to STB\n"); - return rc; + goto fail; } + return 0; +fail: + if (pdev->cpu_id == AMD_CPU_ID_CZN) + cpu_latency_qos_update_request(&pdev->amd_pmc_pm_qos_req, + PM_QOS_DEFAULT_VALUE); return rc; } @@ -579,12 +599,15 @@ static int __maybe_unused amd_pmc_resume(struct device *dev) /* Write data incremented by 1 to distinguish in stb_read */ if (enable_stb) rc = amd_pmc_write_stb(pdev, AMD_PMC_STB_PREDEF + 1); - if (rc) { + if (rc) dev_err(pdev->dev, "error writing to STB\n"); - return rc; - } - return 0; + /* Restore the QoS request back to defaults if it was set */ + if (pdev->cpu_id == AMD_CPU_ID_CZN) + cpu_latency_qos_update_request(&pdev->amd_pmc_pm_qos_req, + PM_QOS_DEFAULT_VALUE); + + return rc; } static const struct dev_pm_ops amd_pmc_pm_ops = { @@ -722,6 +745,7 @@ static int amd_pmc_probe(struct platform_device *pdev) amd_pmc_get_smu_version(dev); platform_set_drvdata(pdev, dev); amd_pmc_dbgfs_register(dev); + cpu_latency_qos_add_request(&dev->amd_pmc_pm_qos_req, PM_QOS_DEFAULT_VALUE); return 0; err_pci_dev_put: diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index a3b83b22a3b1..2104a2621e50 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -2223,7 +2223,7 @@ static int fan_curve_check_present(struct asus_wmi *asus, bool *available, err = fan_curve_get_factory_default(asus, fan_dev); if (err) { - if (err == -ENODEV) + if (err == -ENODEV || err == -ENODATA) return 0; return err; } diff --git a/drivers/platform/x86/intel/int3472/tps68470_board_data.c b/drivers/platform/x86/intel/int3472/tps68470_board_data.c index f93d437fd192..525f09a3b5ff 100644 --- a/drivers/platform/x86/intel/int3472/tps68470_board_data.c +++ b/drivers/platform/x86/intel/int3472/tps68470_board_data.c @@ -100,7 +100,8 @@ static struct gpiod_lookup_table surface_go_tps68470_gpios = { .dev_id = "i2c-INT347A:00", .table = { GPIO_LOOKUP("tps68470-gpio", 9, "reset", GPIO_ACTIVE_LOW), - GPIO_LOOKUP("tps68470-gpio", 7, "powerdown", GPIO_ACTIVE_LOW) + GPIO_LOOKUP("tps68470-gpio", 7, "powerdown", GPIO_ACTIVE_LOW), + { } } }; diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index bd045486b933..3424b080db77 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -8703,6 +8703,7 @@ static const struct tpacpi_quirk fan_quirk_table[] __initconst = { TPACPI_Q_LNV3('N', '4', '0', TPACPI_FAN_2CTL), /* P1 / X1 Extreme (4nd gen) */ TPACPI_Q_LNV3('N', '3', '0', TPACPI_FAN_2CTL), /* P15 (1st gen) / P15v (1st gen) */ TPACPI_Q_LNV3('N', '3', '2', TPACPI_FAN_2CTL), /* X1 Carbon (9th gen) */ + TPACPI_Q_LNV3('N', '3', '7', TPACPI_FAN_2CTL), /* T15g (2nd gen) */ TPACPI_Q_LNV3('N', '1', 'O', TPACPI_FAN_NOFAN), /* X1 Tablet (2nd gen) */ }; diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index 0f1b5a7d2a89..17ad5f0d13b2 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -607,7 +607,7 @@ ptp_ocp_settime(struct ptp_clock_info *ptp_info, const struct timespec64 *ts) } static void -__ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u64 adj_val) +__ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u32 adj_val) { u32 select, ctrl; @@ -615,7 +615,7 @@ __ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u64 adj_val) iowrite32(OCP_SELECT_CLK_REG, &bp->reg->select); iowrite32(adj_val, &bp->reg->offset_ns); - iowrite32(adj_val & 0x7f, &bp->reg->offset_window_ns); + iowrite32(NSEC_PER_SEC, &bp->reg->offset_window_ns); ctrl = OCP_CTRL_ADJUST_OFFSET | OCP_CTRL_ENABLE; iowrite32(ctrl, &bp->reg->ctrl); @@ -624,6 +624,22 @@ __ptp_ocp_adjtime_locked(struct ptp_ocp *bp, u64 adj_val) iowrite32(select >> 16, &bp->reg->select); } +static void +ptp_ocp_adjtime_coarse(struct ptp_ocp *bp, u64 delta_ns) +{ + struct timespec64 ts; + unsigned long flags; + int err; + + spin_lock_irqsave(&bp->lock, flags); + err = __ptp_ocp_gettime_locked(bp, &ts, NULL); + if (likely(!err)) { + timespec64_add_ns(&ts, delta_ns); + __ptp_ocp_settime_locked(bp, &ts); + } + spin_unlock_irqrestore(&bp->lock, flags); +} + static int ptp_ocp_adjtime(struct ptp_clock_info *ptp_info, s64 delta_ns) { @@ -631,6 +647,11 @@ ptp_ocp_adjtime(struct ptp_clock_info *ptp_info, s64 delta_ns) unsigned long flags; u32 adj_ns, sign; + if (delta_ns > NSEC_PER_SEC || -delta_ns > NSEC_PER_SEC) { + ptp_ocp_adjtime_coarse(bp, delta_ns); + return 0; + } + sign = delta_ns < 0 ? BIT(31) : 0; adj_ns = sign ? -delta_ns : delta_ns; diff --git a/drivers/regulator/da9121-regulator.c b/drivers/regulator/da9121-regulator.c index 6f21223a488e..eb9df485bd8a 100644 --- a/drivers/regulator/da9121-regulator.c +++ b/drivers/regulator/da9121-regulator.c @@ -87,16 +87,16 @@ static struct da9121_range da9121_3A_1phase_current = { }; static struct da9121_range da914x_40A_4phase_current = { - .val_min = 14000000, - .val_max = 80000000, - .val_stp = 2000000, + .val_min = 26000000, + .val_max = 78000000, + .val_stp = 4000000, .reg_min = 1, .reg_max = 14, }; static struct da9121_range da914x_20A_2phase_current = { - .val_min = 7000000, - .val_max = 40000000, + .val_min = 13000000, + .val_max = 39000000, .val_stp = 2000000, .reg_min = 1, .reg_max = 14, @@ -561,7 +561,7 @@ static const struct regulator_desc da9217_reg = { }; #define DA914X_MIN_MV 500 -#define DA914X_MAX_MV 1000 +#define DA914X_MAX_MV 1300 #define DA914X_STEP_MV 10 #define DA914X_MIN_SEL (DA914X_MIN_MV / DA914X_STEP_MV) #define DA914X_N_VOLTAGES (((DA914X_MAX_MV - DA914X_MIN_MV) / DA914X_STEP_MV) \ @@ -585,10 +585,6 @@ static const struct regulator_desc da9141_reg = { .vsel_mask = DA9121_MASK_BUCK_BUCKx_5_CHx_A_VOUT, .enable_reg = DA9121_REG_BUCK_BUCK1_0, .enable_mask = DA9121_MASK_BUCK_BUCKx_0_CHx_EN, - /* Default value of BUCK_BUCK1_0.CH1_SRC_DVC_UP */ - .ramp_delay = 20000, - /* tBUCK_EN */ - .enable_time = 20, }; static const struct regulator_desc da9142_reg = { 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/fsl/guts.c b/drivers/soc/fsl/guts.c index 072473a16f4d..5ed2fc1c53a0 100644 --- a/drivers/soc/fsl/guts.c +++ b/drivers/soc/fsl/guts.c @@ -28,7 +28,6 @@ struct fsl_soc_die_attr { static struct guts *guts; static struct soc_device_attribute soc_dev_attr; static struct soc_device *soc_dev; -static struct device_node *root; /* SoC die attribute definition for QorIQ platform */ @@ -138,7 +137,7 @@ static u32 fsl_guts_get_svr(void) static int fsl_guts_probe(struct platform_device *pdev) { - struct device_node *np = pdev->dev.of_node; + struct device_node *root, *np = pdev->dev.of_node; struct device *dev = &pdev->dev; const struct fsl_soc_die_attr *soc_die; const char *machine; @@ -159,8 +158,14 @@ static int fsl_guts_probe(struct platform_device *pdev) root = of_find_node_by_path("/"); if (of_property_read_string(root, "model", &machine)) of_property_read_string_index(root, "compatible", 0, &machine); - if (machine) - soc_dev_attr.machine = machine; + if (machine) { + soc_dev_attr.machine = devm_kstrdup(dev, machine, GFP_KERNEL); + if (!soc_dev_attr.machine) { + of_node_put(root); + return -ENOMEM; + } + } + of_node_put(root); svr = fsl_guts_get_svr(); soc_die = fsl_soc_die_match(svr, fsl_soc_die); @@ -195,7 +200,6 @@ static int fsl_guts_probe(struct platform_device *pdev) static int fsl_guts_remove(struct platform_device *dev) { soc_device_unregister(soc_dev); - of_node_put(root); return 0; } diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c index 4d38c80f8be8..b3c226eb5292 100644 --- a/drivers/soc/fsl/qe/qe.c +++ b/drivers/soc/fsl/qe/qe.c @@ -147,7 +147,7 @@ EXPORT_SYMBOL(qe_issue_cmd); * memory mapped space. * The BRG clock is the QE clock divided by 2. * It was set up long ago during the initial boot phase and is - * is given to us. + * given to us. * Baud rate clocks are zero-based in the driver code (as that maps * to port numbers). Documentation uses 1-based numbering. */ @@ -421,7 +421,7 @@ static void qe_upload_microcode(const void *base, for (i = 0; i < be32_to_cpu(ucode->count); i++) iowrite32be(be32_to_cpu(code[i]), &qe_immr->iram.idata); - + /* Set I-RAM Ready Register */ iowrite32be(QE_IRAM_READY, &qe_immr->iram.iready); } diff --git a/drivers/soc/fsl/qe/qe_io.c b/drivers/soc/fsl/qe/qe_io.c index e277c827bdf3..a5e2d0e5ab51 100644 --- a/drivers/soc/fsl/qe/qe_io.c +++ b/drivers/soc/fsl/qe/qe_io.c @@ -35,6 +35,8 @@ int par_io_init(struct device_node *np) if (ret) return ret; par_io = ioremap(res.start, resource_size(&res)); + if (!par_io) + return -ENOMEM; if (!of_property_read_u32(np, "num-ports", &num_ports)) num_par_io_ports = num_ports; diff --git a/drivers/soc/imx/gpcv2.c b/drivers/soc/imx/gpcv2.c index 3e59d479d001..3cb123016b3e 100644 --- a/drivers/soc/imx/gpcv2.c +++ b/drivers/soc/imx/gpcv2.c @@ -382,7 +382,8 @@ static int imx_pgc_power_down(struct generic_pm_domain *genpd) return 0; out_clk_disable: - clk_bulk_disable_unprepare(domain->num_clks, domain->clks); + if (!domain->keep_clocks) + clk_bulk_disable_unprepare(domain->num_clks, domain->clks); return ret; } 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-rockchip.c b/drivers/spi/spi-rockchip.c index 553b6b9d0222..c6a1bb09be05 100644 --- a/drivers/spi/spi-rockchip.c +++ b/drivers/spi/spi-rockchip.c @@ -585,6 +585,12 @@ static int rockchip_spi_slave_abort(struct spi_controller *ctlr) { struct rockchip_spi *rs = spi_controller_get_devdata(ctlr); + if (atomic_read(&rs->state) & RXDMA) + dmaengine_terminate_sync(ctlr->dma_rx); + if (atomic_read(&rs->state) & TXDMA) + dmaengine_terminate_sync(ctlr->dma_tx); + atomic_set(&rs->state, 0); + spi_enable_chip(rs, false); rs->slave_abort = true; spi_finalize_current_transfer(ctlr); @@ -654,7 +660,7 @@ static int rockchip_spi_probe(struct platform_device *pdev) struct spi_controller *ctlr; struct resource *mem; struct device_node *np = pdev->dev.of_node; - u32 rsd_nsecs; + u32 rsd_nsecs, num_cs; bool slave_mode; slave_mode = of_property_read_bool(np, "spi-slave"); @@ -764,8 +770,9 @@ static int rockchip_spi_probe(struct platform_device *pdev) * rk spi0 has two native cs, spi1..5 one cs only * if num-cs is missing in the dts, default to 1 */ - if (of_property_read_u16(np, "num-cs", &ctlr->num_chipselect)) - ctlr->num_chipselect = 1; + if (of_property_read_u32(np, "num-cs", &num_cs)) + num_cs = 1; + ctlr->num_chipselect = num_cs; ctlr->use_gpio_descriptors = true; } ctlr->dev.of_node = pdev->dev.of_node; diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c index cfa222c9bd5e..78f31b61a2aa 100644 --- a/drivers/spi/spi-zynq-qspi.c +++ b/drivers/spi/spi-zynq-qspi.c @@ -570,6 +570,9 @@ static int zynq_qspi_exec_mem_op(struct spi_mem *mem, if (op->dummy.nbytes) { tmpbuf = kzalloc(op->dummy.nbytes, GFP_KERNEL); + if (!tmpbuf) + return -ENOMEM; + memset(tmpbuf, 0xff, op->dummy.nbytes); reinit_completion(&xqspi->data_completion); xqspi->txbuf = tmpbuf; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 4599b121d744..d96082dc3340 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -1019,10 +1019,10 @@ 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/fbtft/fb_st7789v.c b/drivers/staging/fbtft/fb_st7789v.c index abe9395a0aef..861a154144e6 100644 --- a/drivers/staging/fbtft/fb_st7789v.c +++ b/drivers/staging/fbtft/fb_st7789v.c @@ -144,6 +144,8 @@ static int init_display(struct fbtft_par *par) { int rc; + par->fbtftops.reset(par); + rc = init_tearing_effect_line(par); if (rc) return rc; diff --git a/drivers/staging/gdm724x/gdm_lte.c b/drivers/staging/gdm724x/gdm_lte.c index 493ed4821515..0d8d8fed283d 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_ni(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/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c index f2bf6c61197f..f744ab15bf2c 100644 --- a/drivers/tee/optee/ffa_abi.c +++ b/drivers/tee/optee/ffa_abi.c @@ -869,8 +869,10 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev) optee_supp_init(&optee->supp); ffa_dev_set_drvdata(ffa_dev, optee); ctx = teedev_open(optee->teedev); - if (IS_ERR(ctx)) + if (IS_ERR(ctx)) { + rc = PTR_ERR(ctx); goto err_rhashtable_free; + } optee->ctx = ctx; rc = optee_notif_init(optee, OPTEE_DEFAULT_MAX_NOTIF_VALUE); if (rc) diff --git a/drivers/tee/optee/smc_abi.c b/drivers/tee/optee/smc_abi.c index 1a55339c7072..c517d310249f 100644 --- a/drivers/tee/optee/smc_abi.c +++ b/drivers/tee/optee/smc_abi.c @@ -1417,8 +1417,10 @@ static int optee_probe(struct platform_device *pdev) platform_set_drvdata(pdev, optee); ctx = teedev_open(optee->teedev); - if (IS_ERR(ctx)) + if (IS_ERR(ctx)) { + rc = PTR_ERR(ctx); goto err_supp_uninit; + } optee->ctx = ctx; rc = optee_notif_init(optee, max_notif_value); if (rc) diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c index 72acb1f61849..4f478812cb51 100644 --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c @@ -404,6 +404,10 @@ static void int3400_notify(acpi_handle handle, thermal_prop[3] = kasprintf(GFP_KERNEL, "EVENT=%d", therm_event); thermal_prop[4] = NULL; kobject_uevent_env(&priv->thermal->device.kobj, KOBJ_CHANGE, thermal_prop); + kfree(thermal_prop[0]); + kfree(thermal_prop[1]); + kfree(thermal_prop[2]); + kfree(thermal_prop[3]); } static int int3400_thermal_get_temp(struct thermal_zone_device *thermal, 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/tty/n_gsm.c b/drivers/tty/n_gsm.c index 0b1808e3a912..fa92f727fdf8 100644 --- a/drivers/tty/n_gsm.c +++ b/drivers/tty/n_gsm.c @@ -439,7 +439,7 @@ static u8 gsm_encode_modem(const struct gsm_dlci *dlci) modembits |= MDM_RTR; if (dlci->modem_tx & TIOCM_RI) modembits |= MDM_IC; - if (dlci->modem_tx & TIOCM_CD) + if (dlci->modem_tx & TIOCM_CD || dlci->gsm->initiator) modembits |= MDM_DV; return modembits; } @@ -448,7 +448,7 @@ static u8 gsm_encode_modem(const struct gsm_dlci *dlci) * gsm_print_packet - display a frame for debug * @hdr: header to print before decode * @addr: address EA from the frame - * @cr: C/R bit from the frame + * @cr: C/R bit seen as initiator * @control: control including PF bit * @data: following data bytes * @dlen: length of data @@ -548,7 +548,7 @@ static int gsm_stuff_frame(const u8 *input, u8 *output, int len) * gsm_send - send a control frame * @gsm: our GSM mux * @addr: address for control frame - * @cr: command/response bit + * @cr: command/response bit seen as initiator * @control: control byte including PF bit * * Format up and transmit a control frame. These do not go via the @@ -563,11 +563,15 @@ static void gsm_send(struct gsm_mux *gsm, int addr, int cr, int control) int len; u8 cbuf[10]; u8 ibuf[3]; + int ocr; + + /* toggle C/R coding if not initiator */ + ocr = cr ^ (gsm->initiator ? 0 : 1); switch (gsm->encoding) { case 0: cbuf[0] = GSM0_SOF; - cbuf[1] = (addr << 2) | (cr << 1) | EA; + cbuf[1] = (addr << 2) | (ocr << 1) | EA; cbuf[2] = control; cbuf[3] = EA; /* Length of data = 0 */ cbuf[4] = 0xFF - gsm_fcs_add_block(INIT_FCS, cbuf + 1, 3); @@ -577,7 +581,7 @@ static void gsm_send(struct gsm_mux *gsm, int addr, int cr, int control) case 1: case 2: /* Control frame + packing (but not frame stuffing) in mode 1 */ - ibuf[0] = (addr << 2) | (cr << 1) | EA; + ibuf[0] = (addr << 2) | (ocr << 1) | EA; ibuf[1] = control; ibuf[2] = 0xFF - gsm_fcs_add_block(INIT_FCS, ibuf, 2); /* Stuffing may double the size worst case */ @@ -611,7 +615,7 @@ static void gsm_send(struct gsm_mux *gsm, int addr, int cr, int control) static inline void gsm_response(struct gsm_mux *gsm, int addr, int control) { - gsm_send(gsm, addr, 1, control); + gsm_send(gsm, addr, 0, control); } /** @@ -1017,25 +1021,25 @@ static void gsm_control_reply(struct gsm_mux *gsm, int cmd, const u8 *data, * @tty: virtual tty bound to the DLCI * @dlci: DLCI to affect * @modem: modem bits (full EA) - * @clen: command length + * @slen: number of signal octets * * Used when a modem control message or line state inline in adaption * layer 2 is processed. Sort out the local modem state and throttles */ static void gsm_process_modem(struct tty_struct *tty, struct gsm_dlci *dlci, - u32 modem, int clen) + u32 modem, int slen) { int mlines = 0; u8 brk = 0; int fc; - /* The modem status command can either contain one octet (v.24 signals) - or two octets (v.24 signals + break signals). The length field will - either be 2 or 3 respectively. This is specified in section - 5.4.6.3.7 of the 27.010 mux spec. */ + /* The modem status command can either contain one octet (V.24 signals) + * or two octets (V.24 signals + break signals). This is specified in + * section 5.4.6.3.7 of the 07.10 mux spec. + */ - if (clen == 2) + if (slen == 1) modem = modem & 0x7f; else { brk = modem & 0x7f; @@ -1092,6 +1096,7 @@ static void gsm_control_modem(struct gsm_mux *gsm, const u8 *data, int clen) unsigned int brk = 0; struct gsm_dlci *dlci; int len = clen; + int slen; const u8 *dp = data; struct tty_struct *tty; @@ -1111,6 +1116,7 @@ static void gsm_control_modem(struct gsm_mux *gsm, const u8 *data, int clen) return; dlci = gsm->dlci[addr]; + slen = len; while (gsm_read_ea(&modem, *dp++) == 0) { len--; if (len == 0) @@ -1127,7 +1133,7 @@ static void gsm_control_modem(struct gsm_mux *gsm, const u8 *data, int clen) modem |= (brk & 0x7f); } tty = tty_port_tty_get(&dlci->port); - gsm_process_modem(tty, dlci, modem, clen); + gsm_process_modem(tty, dlci, modem, slen); if (tty) { tty_wakeup(tty); tty_kref_put(tty); @@ -1451,6 +1457,9 @@ static void gsm_dlci_close(struct gsm_dlci *dlci) if (dlci->addr != 0) { tty_port_tty_hangup(&dlci->port, false); kfifo_reset(&dlci->fifo); + /* Ensure that gsmtty_open() can return. */ + tty_port_set_initialized(&dlci->port, 0); + wake_up_interruptible(&dlci->port.open_wait); } else dlci->gsm->dead = true; /* Unregister gsmtty driver,report gsmtty dev remove uevent for user */ @@ -1514,7 +1523,7 @@ static void gsm_dlci_t1(struct timer_list *t) dlci->mode = DLCI_MODE_ADM; gsm_dlci_open(dlci); } else { - gsm_dlci_close(dlci); + gsm_dlci_begin_close(dlci); /* prevent half open link */ } break; @@ -1593,6 +1602,7 @@ static void gsm_dlci_data(struct gsm_dlci *dlci, const u8 *data, int clen) struct tty_struct *tty; unsigned int modem = 0; int len = clen; + int slen = 0; if (debug & 16) pr_debug("%d bytes for tty\n", len); @@ -1605,12 +1615,14 @@ static void gsm_dlci_data(struct gsm_dlci *dlci, const u8 *data, int clen) case 2: /* Asynchronous serial with line state in each frame */ while (gsm_read_ea(&modem, *data++) == 0) { len--; + slen++; if (len == 0) return; } + slen++; tty = tty_port_tty_get(port); if (tty) { - gsm_process_modem(tty, dlci, modem, clen); + gsm_process_modem(tty, dlci, modem, slen); tty_kref_put(tty); } fallthrough; @@ -1748,7 +1760,12 @@ static void gsm_dlci_release(struct gsm_dlci *dlci) gsm_destroy_network(dlci); mutex_unlock(&dlci->mutex); - tty_hangup(tty); + /* We cannot use tty_hangup() because in tty_kref_put() the tty + * driver assumes that the hangup queue is free and reuses it to + * queue release_one_tty() -> NULL pointer panic in + * process_one_work(). + */ + tty_vhangup(tty); tty_port_tty_set(&dlci->port, NULL); tty_kref_put(tty); @@ -1800,10 +1817,10 @@ static void gsm_queue(struct gsm_mux *gsm) goto invalid; cr = gsm->address & 1; /* C/R bit */ + cr ^= gsm->initiator ? 0 : 1; /* Flip so 1 always means command */ gsm_print_packet("<--", address, cr, gsm->control, gsm->buf, gsm->len); - cr ^= 1 - gsm->initiator; /* Flip so 1 always means command */ dlci = gsm->dlci[address]; switch (gsm->control) { @@ -3234,9 +3251,9 @@ static void gsmtty_throttle(struct tty_struct *tty) if (dlci->state == DLCI_CLOSED) return; if (C_CRTSCTS(tty)) - dlci->modem_tx &= ~TIOCM_DTR; + dlci->modem_tx &= ~TIOCM_RTS; dlci->throttled = true; - /* Send an MSC with DTR cleared */ + /* Send an MSC with RTS cleared */ gsmtty_modem_update(dlci, 0); } @@ -3246,9 +3263,9 @@ static void gsmtty_unthrottle(struct tty_struct *tty) if (dlci->state == DLCI_CLOSED) return; if (C_CRTSCTS(tty)) - dlci->modem_tx |= TIOCM_DTR; + dlci->modem_tx |= TIOCM_RTS; dlci->throttled = false; - /* Send an MSC with DTR set */ + /* Send an MSC with RTS set */ gsmtty_modem_update(dlci, 0); } diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 64e7e6c8145f..38d1c0748533 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -734,12 +734,15 @@ static irqreturn_t sc16is7xx_irq(int irq, void *dev_id) static void sc16is7xx_tx_proc(struct kthread_work *ws) { struct uart_port *port = &(to_sc16is7xx_one(ws, tx_work)->port); + struct sc16is7xx_port *s = dev_get_drvdata(port->dev); if ((port->rs485.flags & SER_RS485_ENABLED) && (port->rs485.delay_rts_before_send > 0)) msleep(port->rs485.delay_rts_before_send); + mutex_lock(&s->efr_lock); sc16is7xx_handle_tx(port); + mutex_unlock(&s->efr_lock); } static void sc16is7xx_reconf_rs485(struct uart_port *port) diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h index 8a63da3ab39d..88c337bf564f 100644 --- a/drivers/usb/dwc2/core.h +++ b/drivers/usb/dwc2/core.h @@ -1418,6 +1418,7 @@ void dwc2_hsotg_core_connect(struct dwc2_hsotg *hsotg); void dwc2_hsotg_disconnect(struct dwc2_hsotg *dwc2); int dwc2_hsotg_set_test_mode(struct dwc2_hsotg *hsotg, int testmode); #define dwc2_is_device_connected(hsotg) (hsotg->connected) +#define dwc2_is_device_enabled(hsotg) (hsotg->enabled) int dwc2_backup_device_registers(struct dwc2_hsotg *hsotg); int dwc2_restore_device_registers(struct dwc2_hsotg *hsotg, int remote_wakeup); int dwc2_gadget_enter_hibernation(struct dwc2_hsotg *hsotg); @@ -1454,6 +1455,7 @@ static inline int dwc2_hsotg_set_test_mode(struct dwc2_hsotg *hsotg, int testmode) { return 0; } #define dwc2_is_device_connected(hsotg) (0) +#define dwc2_is_device_enabled(hsotg) (0) static inline int dwc2_backup_device_registers(struct dwc2_hsotg *hsotg) { return 0; } static inline int dwc2_restore_device_registers(struct dwc2_hsotg *hsotg, diff --git a/drivers/usb/dwc2/drd.c b/drivers/usb/dwc2/drd.c index 1b39c4776369..d8d6493bc457 100644 --- a/drivers/usb/dwc2/drd.c +++ b/drivers/usb/dwc2/drd.c @@ -130,8 +130,10 @@ static int dwc2_drd_role_sw_set(struct usb_role_switch *sw, enum usb_role role) already = dwc2_ovr_avalid(hsotg, true); } else if (role == USB_ROLE_DEVICE) { already = dwc2_ovr_bvalid(hsotg, true); - /* This clear DCTL.SFTDISCON bit */ - dwc2_hsotg_core_connect(hsotg); + if (dwc2_is_device_enabled(hsotg)) { + /* This clear DCTL.SFTDISCON bit */ + dwc2_hsotg_core_connect(hsotg); + } } else { if (dwc2_is_device_mode(hsotg)) { if (!dwc2_ovr_bvalid(hsotg, false)) diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 7ff8fc8f79a9..06d0e88ec8af 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -43,6 +43,7 @@ #define PCI_DEVICE_ID_INTEL_ADLP 0x51ee #define PCI_DEVICE_ID_INTEL_ADLM 0x54ee #define PCI_DEVICE_ID_INTEL_ADLS 0x7ae1 +#define PCI_DEVICE_ID_INTEL_RPLS 0x7a61 #define PCI_DEVICE_ID_INTEL_TGL 0x9a15 #define PCI_DEVICE_ID_AMD_MR 0x163a @@ -85,8 +86,8 @@ static const struct acpi_gpio_mapping acpi_dwc3_byt_gpios[] = { static struct gpiod_lookup_table platform_bytcr_gpios = { .dev_id = "0000:00:16.0", .table = { - GPIO_LOOKUP("INT33FC:00", 54, "reset", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("INT33FC:02", 14, "cs", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("INT33FC:00", 54, "cs", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("INT33FC:02", 14, "reset", GPIO_ACTIVE_HIGH), {} }, }; @@ -119,6 +120,13 @@ static const struct property_entry dwc3_pci_intel_properties[] = { {} }; +static const struct property_entry dwc3_pci_intel_byt_properties[] = { + PROPERTY_ENTRY_STRING("dr_mode", "peripheral"), + PROPERTY_ENTRY_BOOL("snps,dis_u2_susphy_quirk"), + PROPERTY_ENTRY_BOOL("linux,sysdev_is_parent"), + {} +}; + static const struct property_entry dwc3_pci_mrfld_properties[] = { PROPERTY_ENTRY_STRING("dr_mode", "otg"), PROPERTY_ENTRY_STRING("linux,extcon-name", "mrfld_bcove_pwrsrc"), @@ -161,6 +169,10 @@ static const struct software_node dwc3_pci_intel_swnode = { .properties = dwc3_pci_intel_properties, }; +static const struct software_node dwc3_pci_intel_byt_swnode = { + .properties = dwc3_pci_intel_byt_properties, +}; + static const struct software_node dwc3_pci_intel_mrfld_swnode = { .properties = dwc3_pci_mrfld_properties, }; @@ -344,7 +356,7 @@ static const struct pci_device_id dwc3_pci_id_table[] = { (kernel_ulong_t) &dwc3_pci_intel_swnode, }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_BYT), - (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + (kernel_ulong_t) &dwc3_pci_intel_byt_swnode, }, { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MRFLD), (kernel_ulong_t) &dwc3_pci_intel_mrfld_swnode, }, @@ -409,6 +421,9 @@ static const struct pci_device_id dwc3_pci_id_table[] = { { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ADLS), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_RPLS), + (kernel_ulong_t) &dwc3_pci_intel_swnode, }, + { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_TGL), (kernel_ulong_t) &dwc3_pci_intel_swnode, }, diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 183b90923f51..a0c883f19a41 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -4160,9 +4160,11 @@ static irqreturn_t dwc3_thread_interrupt(int irq, void *_evt) unsigned long flags; irqreturn_t ret = IRQ_NONE; + local_bh_disable(); spin_lock_irqsave(&dwc->lock, flags); ret = dwc3_process_event_buf(evt); spin_unlock_irqrestore(&dwc->lock, flags); + local_bh_enable(); return ret; } diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index b7ccf1803656..00b3f6b3bb31 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -922,6 +922,7 @@ struct rndis_params *rndis_register(void (*resp_avail)(void *v), void *v) params->resp_avail = resp_avail; params->v = v; INIT_LIST_HEAD(¶ms->resp_queue); + spin_lock_init(¶ms->resp_lock); pr_debug("%s: configNr = %d\n", __func__, i); return params; @@ -1015,12 +1016,14 @@ void rndis_free_response(struct rndis_params *params, u8 *buf) { rndis_resp_t *r, *n; + spin_lock(¶ms->resp_lock); list_for_each_entry_safe(r, n, ¶ms->resp_queue, list) { if (r->buf == buf) { list_del(&r->list); kfree(r); } } + spin_unlock(¶ms->resp_lock); } EXPORT_SYMBOL_GPL(rndis_free_response); @@ -1030,14 +1033,17 @@ u8 *rndis_get_next_response(struct rndis_params *params, u32 *length) if (!length) return NULL; + spin_lock(¶ms->resp_lock); list_for_each_entry_safe(r, n, ¶ms->resp_queue, list) { if (!r->send) { r->send = 1; *length = r->length; + spin_unlock(¶ms->resp_lock); return r->buf; } } + spin_unlock(¶ms->resp_lock); return NULL; } EXPORT_SYMBOL_GPL(rndis_get_next_response); @@ -1054,7 +1060,9 @@ static rndis_resp_t *rndis_add_response(struct rndis_params *params, u32 length) r->length = length; r->send = 0; + spin_lock(¶ms->resp_lock); list_add_tail(&r->list, ¶ms->resp_queue); + spin_unlock(¶ms->resp_lock); return r; } diff --git a/drivers/usb/gadget/function/rndis.h b/drivers/usb/gadget/function/rndis.h index f6167f7fea82..6206b8b7490f 100644 --- a/drivers/usb/gadget/function/rndis.h +++ b/drivers/usb/gadget/function/rndis.h @@ -174,6 +174,7 @@ typedef struct rndis_params { void (*resp_avail)(void *v); void *v; struct list_head resp_queue; + spinlock_t resp_lock; } rndis_params; /* RNDIS Message parser and other useless functions */ diff --git a/drivers/usb/gadget/udc/udc-xilinx.c b/drivers/usb/gadget/udc/udc-xilinx.c index 6ce886fb7bfe..2907fad04e2c 100644 --- a/drivers/usb/gadget/udc/udc-xilinx.c +++ b/drivers/usb/gadget/udc/udc-xilinx.c @@ -1615,6 +1615,8 @@ static void xudc_getstatus(struct xusb_udc *udc) break; case USB_RECIP_ENDPOINT: epnum = udc->setup.wIndex & USB_ENDPOINT_NUMBER_MASK; + if (epnum >= XUSB_MAX_ENDPOINTS) + goto stall; target_ep = &udc->ep[epnum]; epcfgreg = udc->read_fn(udc->addr + target_ep->offset); halt = epcfgreg & XUSB_EP_CFG_STALL_MASK; @@ -1682,6 +1684,10 @@ static void xudc_set_clear_feature(struct xusb_udc *udc) case USB_RECIP_ENDPOINT: if (!udc->setup.wValue) { endpoint = udc->setup.wIndex & USB_ENDPOINT_NUMBER_MASK; + if (endpoint >= XUSB_MAX_ENDPOINTS) { + xudc_ep0_stall(udc); + return; + } target_ep = &udc->ep[endpoint]; outinbit = udc->setup.wIndex & USB_ENDPOINT_DIR_MASK; outinbit = outinbit >> 7; 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/usb/host/xhci.c b/drivers/usb/host/xhci.c index dc357cabb265..2d378543bc3a 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -1091,6 +1091,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) int retval = 0; bool comp_timer_running = false; bool pending_portevent = false; + bool reinit_xhc = false; if (!hcd->state) return 0; @@ -1107,10 +1108,11 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) set_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags); spin_lock_irq(&xhci->lock); - if ((xhci->quirks & XHCI_RESET_ON_RESUME) || xhci->broken_suspend) - hibernated = true; - if (!hibernated) { + if (hibernated || xhci->quirks & XHCI_RESET_ON_RESUME || xhci->broken_suspend) + reinit_xhc = true; + + if (!reinit_xhc) { /* * Some controllers might lose power during suspend, so wait * for controller not ready bit to clear, just as in xHC init. @@ -1143,12 +1145,17 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated) spin_unlock_irq(&xhci->lock); return -ETIMEDOUT; } - temp = readl(&xhci->op_regs->status); } - /* If restore operation fails, re-initialize the HC during resume */ - if ((temp & STS_SRE) || hibernated) { + temp = readl(&xhci->op_regs->status); + /* re-initialize the HC on Restore Error, or Host Controller Error */ + if (temp & (STS_SRE | STS_HCE)) { + reinit_xhc = true; + xhci_warn(xhci, "xHC error in resume, USBSTS 0x%x, Reinit\n", temp); + } + + if (reinit_xhc) { if ((xhci->quirks & XHCI_COMP_MODE_QUIRK) && !(xhci_all_ports_seen_u0(xhci))) { del_timer_sync(&xhci->comp_mode_recovery_timer); @@ -1604,9 +1611,12 @@ static int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag struct urb_priv *urb_priv; int num_tds; - if (!urb || xhci_check_args(hcd, urb->dev, urb->ep, - true, true, __func__) <= 0) + if (!urb) return -EINVAL; + ret = xhci_check_args(hcd, urb->dev, urb->ep, + true, true, __func__); + if (ret <= 0) + return ret ? ret : -EINVAL; slot_id = urb->dev->slot_id; ep_index = xhci_get_endpoint_index(&urb->ep->desc); @@ -3323,7 +3333,7 @@ static int xhci_check_streams_endpoint(struct xhci_hcd *xhci, return -EINVAL; ret = xhci_check_args(xhci_to_hcd(xhci), udev, ep, 1, true, __func__); if (ret <= 0) - return -EINVAL; + return ret ? ret : -EINVAL; if (usb_ss_max_streams(&ep->ss_ep_comp) == 0) { xhci_warn(xhci, "WARN: SuperSpeed Endpoint Companion" " descriptor for ep 0x%x does not support streams\n", diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c index 58cba8ee0277..2798fca71261 100644 --- a/drivers/usb/serial/ch341.c +++ b/drivers/usb/serial/ch341.c @@ -81,7 +81,6 @@ #define CH341_QUIRK_SIMULATE_BREAK BIT(1) static const struct usb_device_id id_table[] = { - { USB_DEVICE(0x1a86, 0x5512) }, { USB_DEVICE(0x1a86, 0x5523) }, { USB_DEVICE(0x1a86, 0x7522) }, { USB_DEVICE(0x1a86, 0x7523) }, diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 962e9943fc20..e7755d9cfc61 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -198,6 +198,8 @@ static void option_instat_callback(struct urb *urb); #define DELL_PRODUCT_5821E 0x81d7 #define DELL_PRODUCT_5821E_ESIM 0x81e0 +#define DELL_PRODUCT_5829E_ESIM 0x81e4 +#define DELL_PRODUCT_5829E 0x81e6 #define KYOCERA_VENDOR_ID 0x0c88 #define KYOCERA_PRODUCT_KPC650 0x17da @@ -1063,6 +1065,10 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5821E_ESIM), .driver_info = RSVD(0) | RSVD(1) | RSVD(6) }, + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5829E), + .driver_info = RSVD(0) | RSVD(6) }, + { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5829E_ESIM), + .driver_info = RSVD(0) | RSVD(6) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_E100A) }, /* ADU-E100, ADU-310 */ { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_500A) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_620UW) }, @@ -1273,10 +1279,16 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x7011, 0xff), /* Telit LE910-S1 (ECM) */ .driver_info = NCTRL(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x701a, 0xff), /* Telit LE910R1 (RNDIS) */ + .driver_info = NCTRL(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x701b, 0xff), /* Telit LE910R1 (ECM) */ + .driver_info = NCTRL(2) }, { USB_DEVICE(TELIT_VENDOR_ID, 0x9010), /* Telit SBL FN980 flashing device */ .driver_info = NCTRL(0) | ZLP }, { USB_DEVICE(TELIT_VENDOR_ID, 0x9200), /* Telit LE910S1 flashing device */ .driver_info = NCTRL(0) | ZLP }, + { USB_DEVICE(TELIT_VENDOR_ID, 0x9201), /* Telit LE910R1 flashing device */ + .driver_info = NCTRL(0) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MF622, 0xff, 0xff, 0xff) }, /* ZTE WCDMA products */ { USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0x0002, 0xff, 0xff, 0xff), .driver_info = RSVD(1) }, diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c index 6d27a5b5e3ca..7ffcda94d323 100644 --- a/drivers/usb/typec/tipd/core.c +++ b/drivers/usb/typec/tipd/core.c @@ -761,12 +761,12 @@ static int tps6598x_probe(struct i2c_client *client) ret = tps6598x_read32(tps, TPS_REG_STATUS, &status); if (ret < 0) - return ret; + goto err_clear_mask; trace_tps6598x_status(status); ret = tps6598x_read32(tps, TPS_REG_SYSTEM_CONF, &conf); if (ret < 0) - return ret; + goto err_clear_mask; /* * This fwnode has a "compatible" property, but is never populated as a @@ -855,7 +855,8 @@ err_role_put: usb_role_switch_put(tps->role_sw); err_fwnode_put: fwnode_handle_put(fwnode); - +err_clear_mask: + tps6598x_write64(tps, TPS_REG_INT_MASK1, 0); return ret; } 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/vhost/vsock.c b/drivers/vhost/vsock.c index d6ca1c7ad513..37f0b4274113 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -629,16 +629,18 @@ err: return ret; } -static int vhost_vsock_stop(struct vhost_vsock *vsock) +static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner) { size_t i; - int ret; + int ret = 0; mutex_lock(&vsock->dev.mutex); - ret = vhost_dev_check_owner(&vsock->dev); - if (ret) - goto err; + if (check_owner) { + ret = vhost_dev_check_owner(&vsock->dev); + if (ret) + goto err; + } for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { struct vhost_virtqueue *vq = &vsock->vqs[i]; @@ -753,7 +755,12 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file) * inefficient. Room for improvement here. */ vsock_for_each_connected_socket(vhost_vsock_reset_orphans); - vhost_vsock_stop(vsock); + /* Don't check the owner, because we are in the release path, so we + * need to stop the vsock device in any case. + * vhost_vsock_stop() can not fail in this case, so we don't need to + * check the return code. + */ + vhost_vsock_stop(vsock, false); vhost_vsock_flush(vsock); vhost_dev_stop(&vsock->dev); @@ -868,7 +875,7 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl, if (start) return vhost_vsock_start(vsock); else - return vhost_vsock_stop(vsock); + return vhost_vsock_stop(vsock, true); case VHOST_GET_FEATURES: features = VHOST_VSOCK_FEATURES; if (copy_to_user(argp, &features, sizeof(features))) 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/afs/write.c b/fs/afs/write.c index 5e9157d0da29..f447c902318d 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -703,7 +703,7 @@ static int afs_writepages_region(struct address_space *mapping, struct folio *folio; struct page *head_page; ssize_t ret; - int n; + int n, skips = 0; _enter("%llx,%llx,", start, end); @@ -754,8 +754,15 @@ static int afs_writepages_region(struct address_space *mapping, #ifdef CONFIG_AFS_FSCACHE folio_wait_fscache(folio); #endif + } else { + start += folio_size(folio); } folio_put(folio); + if (wbc->sync_mode == WB_SYNC_NONE) { + if (skips >= 5 || need_resched()) + break; + skips++; + } continue; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 9e11e6f13e83..d61543fbd652 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1135,14 +1135,25 @@ out_free_interp: * is then page aligned. */ load_bias = ELF_PAGESTART(load_bias - vaddr); - } - /* - * Calculate the entire size of the ELF mapping (total_size). - * (Note that load_addr_set is set to true later once the - * initial mapping is performed.) - */ - if (!load_addr_set) { + /* + * Calculate the entire size of the ELF mapping + * (total_size), used for the initial mapping, + * due to load_addr_set which is set to true later + * once the initial mapping is performed. + * + * Note that this is only sensible when the LOAD + * segments are contiguous (or overlapping). If + * used for LOADs that are far apart, this would + * cause the holes between LOADs to be mapped, + * running the risk of having the mapping fail, + * as it would be larger than the ELF file itself. + * + * As a result, only ET_DYN does this, since + * some ET_EXEC (e.g. ia64) may have large virtual + * memory holes between LOADs. + * + */ total_size = total_mapping_size(elf_phdata, elf_ex->e_phnum); if (!total_size) { diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 8992e0096163..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. @@ -3291,7 +3301,7 @@ void btrfs_exclop_balance(struct btrfs_fs_info *fs_info, int __init btrfs_auto_defrag_init(void); void __cold btrfs_auto_defrag_exit(void); int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode); + struct btrfs_inode *inode, u32 extent_thresh); int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info); void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info); int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync); 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/extent_map.c b/fs/btrfs/extent_map.c index 5a36add21305..c28ceddefae4 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -261,6 +261,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) em->mod_len = (em->mod_len + em->mod_start) - merge->mod_start; em->mod_start = merge->mod_start; em->generation = max(em->generation, merge->generation); + set_bit(EXTENT_FLAG_MERGED, &em->flags); rb_erase_cached(&merge->rb_node, &tree->map); RB_CLEAR_NODE(&merge->rb_node); @@ -278,6 +279,7 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em) RB_CLEAR_NODE(&merge->rb_node); em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start; em->generation = max(em->generation, merge->generation); + set_bit(EXTENT_FLAG_MERGED, &em->flags); free_extent_map(merge); } } diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h index 8e217337dff9..d2fa32ffe304 100644 --- a/fs/btrfs/extent_map.h +++ b/fs/btrfs/extent_map.h @@ -25,6 +25,8 @@ enum { EXTENT_FLAG_FILLING, /* filesystem extent mapping type */ EXTENT_FLAG_FS_MAPPING, + /* This em is merged from two or more physically adjacent ems */ + EXTENT_FLAG_MERGED, }; struct extent_map { @@ -40,6 +42,12 @@ struct extent_map { u64 ram_bytes; u64 block_start; u64 block_len; + + /* + * Generation of the extent map, for merged em it's the highest + * generation of all merged ems. + * For non-merged extents, it's from btrfs_file_extent_item::generation. + */ u64 generation; unsigned long flags; /* Used for chunk mappings, flag EXTENT_FLAG_FS_MAPPING must be set */ diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 11204dbbe053..a0179cc62913 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -50,11 +50,14 @@ struct inode_defrag { /* root objectid */ u64 root; - /* last offset we were able to defrag */ - u64 last_offset; - - /* if we've wrapped around back to zero once already */ - int cycled; + /* + * The extent size threshold for autodefrag. + * + * This value is different for compressed/non-compressed extents, + * thus needs to be passed from higher layer. + * (aka, inode_should_defrag()) + */ + u32 extent_thresh; }; static int __compare_inode_defrag(struct inode_defrag *defrag1, @@ -107,8 +110,8 @@ static int __btrfs_add_inode_defrag(struct btrfs_inode *inode, */ if (defrag->transid < entry->transid) entry->transid = defrag->transid; - if (defrag->last_offset > entry->last_offset) - entry->last_offset = defrag->last_offset; + entry->extent_thresh = min(defrag->extent_thresh, + entry->extent_thresh); return -EEXIST; } } @@ -134,7 +137,7 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info) * enabled */ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode) + struct btrfs_inode *inode, u32 extent_thresh) { struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; @@ -160,6 +163,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, defrag->ino = btrfs_ino(inode); defrag->transid = transid; defrag->root = root->root_key.objectid; + defrag->extent_thresh = extent_thresh; spin_lock(&fs_info->defrag_inodes_lock); if (!test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) { @@ -179,34 +183,6 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, } /* - * Requeue the defrag object. If there is a defrag object that points to - * the same inode in the tree, we will merge them together (by - * __btrfs_add_inode_defrag()) and free the one that we want to requeue. - */ -static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode, - struct inode_defrag *defrag) -{ - struct btrfs_fs_info *fs_info = inode->root->fs_info; - int ret; - - if (!__need_auto_defrag(fs_info)) - goto out; - - /* - * Here we don't check the IN_DEFRAG flag, because we need merge - * them together. - */ - spin_lock(&fs_info->defrag_inodes_lock); - ret = __btrfs_add_inode_defrag(inode, defrag); - spin_unlock(&fs_info->defrag_inodes_lock); - if (ret) - goto out; - return; -out: - kmem_cache_free(btrfs_inode_defrag_cachep, defrag); -} - -/* * pick the defragable inode that we want, if it doesn't exist, we will get * the next one. */ @@ -278,8 +254,14 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, struct btrfs_root *inode_root; struct inode *inode; struct btrfs_ioctl_defrag_range_args range; - int num_defrag; - int ret; + int ret = 0; + u64 cur = 0; + +again: + if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state)) + goto cleanup; + if (!__need_auto_defrag(fs_info)) + goto cleanup; /* get the inode */ inode_root = btrfs_get_fs_root(fs_info, defrag->root, true); @@ -295,39 +277,30 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info, goto cleanup; } + if (cur >= i_size_read(inode)) { + iput(inode); + goto cleanup; + } + /* do a chunk of defrag */ clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags); memset(&range, 0, sizeof(range)); range.len = (u64)-1; - range.start = defrag->last_offset; + range.start = cur; + range.extent_thresh = defrag->extent_thresh; sb_start_write(fs_info->sb); - num_defrag = btrfs_defrag_file(inode, NULL, &range, defrag->transid, + ret = btrfs_defrag_file(inode, NULL, &range, defrag->transid, BTRFS_DEFRAG_BATCH); sb_end_write(fs_info->sb); - /* - * if we filled the whole defrag batch, there - * must be more work to do. Queue this defrag - * again - */ - if (num_defrag == BTRFS_DEFRAG_BATCH) { - defrag->last_offset = range.start; - btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag); - } else if (defrag->last_offset && !defrag->cycled) { - /* - * we didn't fill our defrag batch, but - * we didn't start at zero. Make sure we loop - * around to the start of the file. - */ - defrag->last_offset = 0; - defrag->cycled = 1; - btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag); - } else { - kmem_cache_free(btrfs_inode_defrag_cachep, defrag); - } - iput(inode); - return 0; + + if (ret < 0) + goto cleanup; + + cur = max(cur + fs_info->sectorsize, range.start); + goto again; + cleanup: kmem_cache_free(btrfs_inode_defrag_cachep, defrag); return ret; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3b2403b6127f..5bbea5ec31fc 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -560,12 +560,12 @@ static inline int inode_need_compress(struct btrfs_inode *inode, u64 start, } static inline void inode_should_defrag(struct btrfs_inode *inode, - u64 start, u64 end, u64 num_bytes, u64 small_write) + u64 start, u64 end, u64 num_bytes, u32 small_write) { /* If this is a small write inside eof, kick off a defrag */ if (num_bytes < small_write && (start > 0 || end + 1 < inode->disk_i_size)) - btrfs_add_inode_defrag(NULL, inode); + btrfs_add_inode_defrag(NULL, inode, small_write); } /* @@ -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/ioctl.c b/fs/btrfs/ioctl.c index 927771d1853f..8d47ec5fc4f4 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1012,8 +1012,155 @@ out: return ret; } +/* + * Defrag specific helper to get an extent map. + * + * Differences between this and btrfs_get_extent() are: + * + * - No extent_map will be added to inode->extent_tree + * To reduce memory usage in the long run. + * + * - Extra optimization to skip file extents older than @newer_than + * By using btrfs_search_forward() we can skip entire file ranges that + * have extents created in past transactions, because btrfs_search_forward() + * will not visit leaves and nodes with a generation smaller than given + * minimal generation threshold (@newer_than). + * + * Return valid em if we find a file extent matching the requirement. + * Return NULL if we can not find a file extent matching the requirement. + * + * Return ERR_PTR() for error. + */ +static struct extent_map *defrag_get_extent(struct btrfs_inode *inode, + u64 start, u64 newer_than) +{ + struct btrfs_root *root = inode->root; + struct btrfs_file_extent_item *fi; + struct btrfs_path path = { 0 }; + struct extent_map *em; + struct btrfs_key key; + u64 ino = btrfs_ino(inode); + int ret; + + em = alloc_extent_map(); + if (!em) { + ret = -ENOMEM; + goto err; + } + + key.objectid = ino; + key.type = BTRFS_EXTENT_DATA_KEY; + key.offset = start; + + if (newer_than) { + ret = btrfs_search_forward(root, &key, &path, newer_than); + if (ret < 0) + goto err; + /* Can't find anything newer */ + if (ret > 0) + goto not_found; + } else { + ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0); + if (ret < 0) + goto err; + } + if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) { + /* + * If btrfs_search_slot() makes path to point beyond nritems, + * we should not have an empty leaf, as this inode must at + * least have its INODE_ITEM. + */ + ASSERT(btrfs_header_nritems(path.nodes[0])); + path.slots[0] = btrfs_header_nritems(path.nodes[0]) - 1; + } + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + /* Perfect match, no need to go one slot back */ + if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY && + key.offset == start) + goto iterate; + + /* We didn't find a perfect match, needs to go one slot back */ + if (path.slots[0] > 0) { + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY) + path.slots[0]--; + } + +iterate: + /* Iterate through the path to find a file extent covering @start */ + while (true) { + u64 extent_end; + + if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) + goto next; + + btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]); + + /* + * We may go one slot back to INODE_REF/XATTR item, then + * need to go forward until we reach an EXTENT_DATA. + * But we should still has the correct ino as key.objectid. + */ + if (WARN_ON(key.objectid < ino) || key.type < BTRFS_EXTENT_DATA_KEY) + goto next; + + /* It's beyond our target range, definitely not extent found */ + if (key.objectid > ino || key.type > BTRFS_EXTENT_DATA_KEY) + goto not_found; + + /* + * | |<- File extent ->| + * \- start + * + * This means there is a hole between start and key.offset. + */ + if (key.offset > start) { + em->start = start; + em->orig_start = start; + em->block_start = EXTENT_MAP_HOLE; + em->len = key.offset - start; + break; + } + + fi = btrfs_item_ptr(path.nodes[0], path.slots[0], + struct btrfs_file_extent_item); + extent_end = btrfs_file_extent_end(&path); + + /* + * |<- file extent ->| | + * \- start + * + * We haven't reached start, search next slot. + */ + if (extent_end <= start) + goto next; + + /* Now this extent covers @start, convert it to em */ + btrfs_extent_item_to_extent_map(inode, &path, fi, false, em); + break; +next: + ret = btrfs_next_item(root, &path); + if (ret < 0) + goto err; + if (ret > 0) + goto not_found; + } + btrfs_release_path(&path); + return em; + +not_found: + btrfs_release_path(&path); + free_extent_map(em); + return NULL; + +err: + btrfs_release_path(&path); + free_extent_map(em); + return ERR_PTR(ret); +} + static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start, - bool locked) + u64 newer_than, bool locked) { struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree; struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree; @@ -1028,6 +1175,20 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start, em = lookup_extent_mapping(em_tree, start, sectorsize); read_unlock(&em_tree->lock); + /* + * We can get a merged extent, in that case, we need to re-search + * tree to get the original em for defrag. + * + * If @newer_than is 0 or em::generation < newer_than, we can trust + * this em, as either we don't care about the generation, or the + * merged extent map will be rejected anyway. + */ + if (em && test_bit(EXTENT_FLAG_MERGED, &em->flags) && + newer_than && em->generation >= newer_than) { + free_extent_map(em); + em = NULL; + } + if (!em) { struct extent_state *cached = NULL; u64 end = start + sectorsize - 1; @@ -1035,7 +1196,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start, /* get the big lock and read metadata off disk */ if (!locked) lock_extent_bits(io_tree, start, end, &cached); - em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, sectorsize); + em = defrag_get_extent(BTRFS_I(inode), start, newer_than); if (!locked) unlock_extent_cached(io_tree, start, end, &cached); @@ -1046,23 +1207,42 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start, return em; } +static u32 get_extent_max_capacity(const struct extent_map *em) +{ + if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags)) + return BTRFS_MAX_COMPRESSED; + return BTRFS_MAX_EXTENT_SIZE; +} + static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em, bool locked) { struct extent_map *next; - bool ret = true; + bool ret = false; /* this is the last extent */ if (em->start + em->len >= i_size_read(inode)) return false; - next = defrag_lookup_extent(inode, em->start + em->len, locked); + /* + * We want to check if the next extent can be merged with the current + * one, which can be an extent created in a past generation, so we pass + * a minimum generation of 0 to defrag_lookup_extent(). + */ + next = defrag_lookup_extent(inode, em->start + em->len, 0, locked); + /* No more em or hole */ if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE) - ret = false; - else if ((em->block_start + em->block_len == next->block_start) && - (em->block_len > SZ_128K && next->block_len > SZ_128K)) - ret = false; - + goto out; + if (test_bit(EXTENT_FLAG_PREALLOC, &next->flags)) + goto out; + /* + * If the next extent is at its max capacity, defragging current extent + * makes no sense, as the total number of extents won't change. + */ + if (next->len >= get_extent_max_capacity(em)) + goto out; + ret = true; +out: free_extent_map(next); return ret; } @@ -1186,8 +1366,10 @@ struct defrag_target_range { static int defrag_collect_targets(struct btrfs_inode *inode, u64 start, u64 len, u32 extent_thresh, u64 newer_than, bool do_compress, - bool locked, struct list_head *target_list) + bool locked, struct list_head *target_list, + u64 *last_scanned_ret) { + bool last_is_target = false; u64 cur = start; int ret = 0; @@ -1197,7 +1379,9 @@ static int defrag_collect_targets(struct btrfs_inode *inode, bool next_mergeable = true; u64 range_len; - em = defrag_lookup_extent(&inode->vfs_inode, cur, locked); + last_is_target = false; + em = defrag_lookup_extent(&inode->vfs_inode, cur, + newer_than, locked); if (!em) break; @@ -1254,6 +1438,13 @@ static int defrag_collect_targets(struct btrfs_inode *inode, if (range_len >= extent_thresh) goto next; + /* + * Skip extents already at its max capacity, this is mostly for + * compressed extents, which max cap is only 128K. + */ + if (em->len >= get_extent_max_capacity(em)) + goto next; + next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em, locked); if (!next_mergeable) { @@ -1272,6 +1463,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode, } add: + last_is_target = true; range_len = min(extent_map_end(em), start + len) - cur; /* * This one is a good target, check if it can be merged into @@ -1315,6 +1507,17 @@ next: kfree(entry); } } + if (!ret && last_scanned_ret) { + /* + * If the last extent is not a target, the caller can skip to + * the end of that extent. + * Otherwise, we can only go the end of the specified range. + */ + if (!last_is_target) + *last_scanned_ret = max(cur, *last_scanned_ret); + else + *last_scanned_ret = max(start + len, *last_scanned_ret); + } return ret; } @@ -1373,7 +1576,8 @@ static int defrag_one_locked_target(struct btrfs_inode *inode, } static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len, - u32 extent_thresh, u64 newer_than, bool do_compress) + u32 extent_thresh, u64 newer_than, bool do_compress, + u64 *last_scanned_ret) { struct extent_state *cached_state = NULL; struct defrag_target_range *entry; @@ -1419,7 +1623,7 @@ static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len, */ ret = defrag_collect_targets(inode, start, len, extent_thresh, newer_than, do_compress, true, - &target_list); + &target_list, last_scanned_ret); if (ret < 0) goto unlock_extent; @@ -1454,7 +1658,8 @@ static int defrag_one_cluster(struct btrfs_inode *inode, u64 start, u32 len, u32 extent_thresh, u64 newer_than, bool do_compress, unsigned long *sectors_defragged, - unsigned long max_sectors) + unsigned long max_sectors, + u64 *last_scanned_ret) { const u32 sectorsize = inode->root->fs_info->sectorsize; struct defrag_target_range *entry; @@ -1465,7 +1670,7 @@ static int defrag_one_cluster(struct btrfs_inode *inode, BUILD_BUG_ON(!IS_ALIGNED(CLUSTER_SIZE, PAGE_SIZE)); ret = defrag_collect_targets(inode, start, len, extent_thresh, newer_than, do_compress, false, - &target_list); + &target_list, NULL); if (ret < 0) goto out; @@ -1482,6 +1687,15 @@ static int defrag_one_cluster(struct btrfs_inode *inode, range_len = min_t(u32, range_len, (max_sectors - *sectors_defragged) * sectorsize); + /* + * If defrag_one_range() has updated last_scanned_ret, + * our range may already be invalid (e.g. hole punched). + * Skip if our range is before last_scanned_ret, as there is + * no need to defrag the range anymore. + */ + if (entry->start + range_len <= *last_scanned_ret) + continue; + if (ra) page_cache_sync_readahead(inode->vfs_inode.i_mapping, ra, NULL, entry->start >> PAGE_SHIFT, @@ -1494,7 +1708,8 @@ static int defrag_one_cluster(struct btrfs_inode *inode, * accounting. */ ret = defrag_one_range(inode, entry->start, range_len, - extent_thresh, newer_than, do_compress); + extent_thresh, newer_than, do_compress, + last_scanned_ret); if (ret < 0) break; *sectors_defragged += range_len >> @@ -1505,6 +1720,8 @@ out: list_del_init(&entry->list); kfree(entry); } + if (ret >= 0) + *last_scanned_ret = max(*last_scanned_ret, start + len); return ret; } @@ -1590,6 +1807,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, while (cur < last_byte) { const unsigned long prev_sectors_defragged = sectors_defragged; + u64 last_scanned = cur; u64 cluster_end; /* The cluster size 256K should always be page aligned */ @@ -1619,8 +1837,8 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, BTRFS_I(inode)->defrag_compress = compress_type; ret = defrag_one_cluster(BTRFS_I(inode), ra, cur, cluster_end + 1 - cur, extent_thresh, - newer_than, do_compress, - §ors_defragged, max_to_defrag); + newer_than, do_compress, §ors_defragged, + max_to_defrag, &last_scanned); if (sectors_defragged > prev_sectors_defragged) balance_dirty_pages_ratelimited(inode->i_mapping); @@ -1628,7 +1846,7 @@ int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra, btrfs_inode_unlock(inode, 0); if (ret < 0) break; - cur = cluster_end + 1; + cur = max(cluster_end + 1, last_scanned); if (ret > 0) { ret = 0; break; diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c index 0fb90cbe7669..e6e28a9c7987 100644 --- a/fs/btrfs/lzo.c +++ b/fs/btrfs/lzo.c @@ -380,6 +380,17 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb) kunmap(cur_page); cur_in += LZO_LEN; + if (seg_len > lzo1x_worst_compress(PAGE_SIZE)) { + /* + * seg_len shouldn't be larger than we have allocated + * for workspace->cbuf + */ + btrfs_err(fs_info, "unexpectedly large lzo segment len %u", + seg_len); + ret = -EIO; + goto out; + } + /* Copy the compressed segment payload into workspace */ copy_compressed_segment(cb, workspace->cbuf, seg_len, &cur_in); 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/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 83f41bd0c3a9..35465109d9c4 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -28,6 +28,11 @@ struct cachefiles_xattr { static const char cachefiles_xattr_cache[] = XATTR_USER_PREFIX "CacheFiles.cache"; +struct cachefiles_vol_xattr { + __be32 reserved; /* Reserved, should be 0 */ + __u8 data[]; /* netfs volume coherency data */ +} __packed; + /* * set the state xattr on a cache file */ @@ -185,6 +190,7 @@ void cachefiles_prepare_to_write(struct fscache_cookie *cookie) */ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) { + struct cachefiles_vol_xattr *buf; unsigned int len = volume->vcookie->coherency_len; const void *p = volume->vcookie->coherency; struct dentry *dentry = volume->dentry; @@ -192,10 +198,17 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) _enter("%x,#%d", volume->vcookie->debug_id, len); + len += sizeof(*buf); + buf = kmalloc(len, GFP_KERNEL); + if (!buf) + return false; + buf->reserved = cpu_to_be32(0); + memcpy(buf->data, p, len); + ret = cachefiles_inject_write_error(); if (ret == 0) ret = vfs_setxattr(&init_user_ns, dentry, cachefiles_xattr_cache, - p, len, 0); + buf, len, 0); if (ret < 0) { trace_cachefiles_vfs_error(NULL, d_inode(dentry), ret, cachefiles_trace_setxattr_error); @@ -209,6 +222,7 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) cachefiles_coherency_vol_set_ok); } + kfree(buf); _leave(" = %d", ret); return ret == 0; } @@ -218,7 +232,7 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) */ int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) { - struct cachefiles_xattr *buf; + struct cachefiles_vol_xattr *buf; struct dentry *dentry = volume->dentry; unsigned int len = volume->vcookie->coherency_len; const void *p = volume->vcookie->coherency; @@ -228,6 +242,7 @@ int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) _enter(""); + len += sizeof(*buf); buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -245,7 +260,9 @@ int cachefiles_check_volume_xattr(struct cachefiles_volume *volume) "Failed to read xattr with error %zd", xlen); } why = cachefiles_coherency_vol_check_xattr; - } else if (memcmp(buf->data, p, len) != 0) { + } else if (buf->reserved != cpu_to_be32(0)) { + why = cachefiles_coherency_vol_check_resv; + } else if (memcmp(buf->data, p, len - sizeof(*buf)) != 0) { why = cachefiles_coherency_vol_check_cmp; } else { why = cachefiles_coherency_vol_check_ok; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index d3cd2a94d1e8..d1f9d2632202 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -34,6 +34,14 @@ */ DEFINE_SPINLOCK(configfs_dirent_lock); +/* + * All of link_obj/unlink_obj/link_group/unlink_group require that + * subsys->su_mutex is held. + * But parent configfs_subsystem is NULL when config_item is root. + * Use this mutex when config_item is root. + */ +static DEFINE_MUTEX(configfs_subsystem_mutex); + static void configfs_d_iput(struct dentry * dentry, struct inode * inode) { @@ -1859,7 +1867,9 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) group->cg_item.ci_name = group->cg_item.ci_namebuf; sd = root->d_fsdata; + mutex_lock(&configfs_subsystem_mutex); link_group(to_config_group(sd->s_element), group); + mutex_unlock(&configfs_subsystem_mutex); inode_lock_nested(d_inode(root), I_MUTEX_PARENT); @@ -1884,7 +1894,9 @@ int configfs_register_subsystem(struct configfs_subsystem *subsys) inode_unlock(d_inode(root)); if (err) { + mutex_lock(&configfs_subsystem_mutex); unlink_group(group); + mutex_unlock(&configfs_subsystem_mutex); configfs_release_fs(); } put_fragment(frag); @@ -1931,7 +1943,9 @@ void configfs_unregister_subsystem(struct configfs_subsystem *subsys) dput(dentry); + mutex_lock(&configfs_subsystem_mutex); unlink_group(group); + mutex_unlock(&configfs_subsystem_mutex); configfs_release_fs(); } diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index b8272fb95fd6..5aa2cf2c2f80 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -325,7 +325,7 @@ struct erofs_inode { unsigned char z_algorithmtype[2]; unsigned char z_logical_clusterbits; unsigned long z_tailextent_headlcn; - unsigned int z_idataoff; + erofs_off_t z_idataoff; unsigned short z_idata_size; }; #endif /* CONFIG_EROFS_FS_ZIP */ 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/io_uring.c b/fs/io_uring.c index 77b9c7e4793b..4715980e9015 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4567,6 +4567,7 @@ static int io_add_buffers(struct io_provide_buf *pbuf, struct io_buffer **head) } else { list_add_tail(&buf->list, &(*head)->list); } + cond_resched(); } return i ? i : -ENOMEM; @@ -7693,7 +7694,7 @@ static int io_run_task_work_sig(void) /* when returns >0, the caller should retry */ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq, - signed long *timeout) + ktime_t timeout) { int ret; @@ -7705,8 +7706,9 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, if (test_bit(0, &ctx->check_cq_overflow)) return 1; - *timeout = schedule_timeout(*timeout); - return !*timeout ? -ETIME : 1; + if (!schedule_hrtimeout(&timeout, HRTIMER_MODE_ABS)) + return -ETIME; + return 1; } /* @@ -7719,7 +7721,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, { struct io_wait_queue iowq; struct io_rings *rings = ctx->rings; - signed long timeout = MAX_SCHEDULE_TIMEOUT; + ktime_t timeout = KTIME_MAX; int ret; do { @@ -7735,7 +7737,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, if (get_timespec64(&ts, uts)) return -EFAULT; - timeout = timespec64_to_jiffies(&ts); + timeout = ktime_add_ns(timespec64_to_ktime(ts), ktime_get_ns()); } if (sig) { @@ -7767,7 +7769,7 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, } prepare_to_wait_exclusive(&ctx->cq_wait, &iowq.wq, TASK_INTERRUPTIBLE); - ret = io_cqring_wait_schedule(ctx, &iowq, &timeout); + ret = io_cqring_wait_schedule(ctx, &iowq, timeout); finish_wait(&ctx->cq_wait, &iowq.wq); cond_resched(); } while (ret > 0); @@ -7924,7 +7926,15 @@ static __cold int io_rsrc_ref_quiesce(struct io_rsrc_data *data, ret = wait_for_completion_interruptible(&data->done); if (!ret) { mutex_lock(&ctx->uring_lock); - break; + if (atomic_read(&data->refs) > 0) { + /* + * it has been revived by another thread while + * we were unlocked + */ + mutex_unlock(&ctx->uring_lock); + } else { + break; + } } atomic_inc(&data->refs); diff --git a/fs/pipe.c b/fs/pipe.c index cc28623a67b6..2667db9506e2 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -253,7 +253,8 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to) */ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { - unsigned int head = pipe->head; + /* Read ->head with a barrier vs post_one_notification() */ + unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; @@ -831,10 +832,8 @@ void free_pipe_info(struct pipe_inode_info *pipe) int i; #ifdef CONFIG_WATCH_QUEUE - if (pipe->watch_queue) { + if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); - put_watch_queue(pipe->watch_queue); - } #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); @@ -844,6 +843,10 @@ void free_pipe_info(struct pipe_inode_info *pipe) if (buf->ops) pipe_buf_release(pipe, buf); } +#ifdef CONFIG_WATCH_QUEUE + if (pipe->watch_queue) + put_watch_queue(pipe->watch_queue); +#endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); 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/tracefs/inode.c b/fs/tracefs/inode.c index bafc02bf8220..de7252715b12 100644 --- a/fs/tracefs/inode.c +++ b/fs/tracefs/inode.c @@ -264,7 +264,6 @@ static int tracefs_parse_options(char *data, struct tracefs_mount_opts *opts) if (!gid_valid(gid)) return -EINVAL; opts->gid = gid; - set_gid(tracefs_mount->mnt_root, gid); break; case Opt_mode: if (match_octal(&args[0], &option)) @@ -291,7 +290,9 @@ static int tracefs_apply_options(struct super_block *sb) inode->i_mode |= opts->mode; inode->i_uid = opts->uid; - inode->i_gid = opts->gid; + + /* Set all the group ids to the mount option */ + set_gid(sb->s_root, opts->gid); return 0; } 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/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 4c0dee78b2f8..d84714e4e46a 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1753,6 +1753,11 @@ xfs_remount_ro( }; int error; + /* Flush all the dirty data to disk. */ + error = sync_filesystem(mp->m_super); + if (error) + return error; + /* * Cancel background eofb scanning so it cannot race with the final * log force+buftarg wait and deadlock the remount. @@ -1831,8 +1836,6 @@ xfs_fs_reconfigure( if (error) return error; - sync_filesystem(mp->m_super); - /* inode32 -> inode64 */ if (xfs_has_small_inums(mp) && !xfs_has_small_inums(new_mp)) { mp->m_features &= ~XFS_FEAT_SMALL_INUMS; 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 fa517ae604ad..3121d1fc8e75 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -209,11 +209,9 @@ static inline bool map_value_has_timer(const struct bpf_map *map) static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { if (unlikely(map_value_has_spin_lock(map))) - *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = - (struct bpf_spin_lock){}; + memset(dst + map->spin_lock_off, 0, sizeof(struct bpf_spin_lock)); if (unlikely(map_value_has_timer(map))) - *(struct bpf_timer *)(dst + map->timer_off) = - (struct bpf_timer){}; + memset(dst + map->timer_off, 0, sizeof(struct bpf_timer)); } /* copy everything but bpf_spin_lock and bpf_timer. There could be one of each. */ @@ -224,7 +222,8 @@ static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) if (unlikely(map_value_has_spin_lock(map))) { s_off = map->spin_lock_off; s_sz = sizeof(struct bpf_spin_lock); - } else if (unlikely(map_value_has_timer(map))) { + } + if (unlikely(map_value_has_timer(map))) { t_off = map->timer_off; t_sz = sizeof(struct bpf_timer); } @@ -1793,6 +1792,11 @@ 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) { @@ -2012,6 +2016,12 @@ 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/cpufreq.h b/include/linux/cpufreq.h index 1ab29e61b078..3522a272b74d 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -382,6 +382,9 @@ struct cpufreq_driver { int (*suspend)(struct cpufreq_policy *policy); int (*resume)(struct cpufreq_policy *policy); + /* Will be called after the driver is fully initialized */ + void (*ready)(struct cpufreq_policy *policy); + struct freq_attr **attr; /* platform specific boost support code */ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 598ac3bcc901..49a48d7709ac 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -3434,7 +3434,6 @@ 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 { @@ -9900,8 +9899,8 @@ 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 8b5a314db167..f53ea7038441 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4602,6 +4602,8 @@ 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/netfilter_netdev.h b/include/linux/netfilter_netdev.h index b4dd96e4dc8d..e6487a691136 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -101,7 +101,11 @@ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, nf_hook_state_init(&state, NF_NETDEV_EGRESS, NFPROTO_NETDEV, dev, NULL, NULL, dev_net(dev), NULL); + + /* nf assumes rcu_read_lock, not just read_lock_bh */ + rcu_read_lock(); ret = nf_hook_slow(skb, &state, e, 0); + rcu_read_unlock(); if (ret == 1) { return skb; diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index 959e0bd9a913..75470159a194 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -12,6 +12,7 @@ #define NVME_TCP_DISC_PORT 8009 #define NVME_TCP_ADMIN_CCSZ SZ_8K #define NVME_TCP_DIGEST_LENGTH 4 +#define NVME_TCP_MIN_MAXH2CDATA 4096 enum nvme_tcp_pfv { NVME_TCP_PFV_1_0 = 0x0, diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 98efb7b5660d..c9a3ac9efeaa 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -70,7 +70,8 @@ struct nvmem_keepout { * @word_size: Minimum read/write access granularity. * @stride: Minimum read/write access stride. * @priv: User context passed to read/write callbacks. - * @wp-gpio: Write protect pin + * @wp-gpio: Write protect pin + * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem<id>" name will be assigned to the device if * no name is specified in its configuration. In such case "<id>" is @@ -92,6 +93,7 @@ struct nvmem_config { enum nvmem_type type; bool read_only; bool root_only; + bool ignore_wp; struct device_node *of_node; bool no_of_node; nvmem_reg_read_t reg_read; diff --git a/include/linux/phy.h b/include/linux/phy.h index 6de8d7a90d78..8fa70ba063a5 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/rfkill.h b/include/linux/rfkill.h index c35f3962dc4f..373003ace639 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -308,6 +308,11 @@ static inline bool rfkill_blocked(struct rfkill *rfkill) return false; } +static inline bool rfkill_soft_blocked(struct rfkill *rfkill) +{ + return false; +} + static inline enum rfkill_type rfkill_find_type(const char *name) { return RFKILL_TYPE_ALL; diff --git a/include/linux/slab.h b/include/linux/slab.h index 37bde99b74af..5b6193fd8bd9 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -660,8 +660,7 @@ static inline __alloc_size(1, 2) void *kcalloc(size_t n, size_t size, gfp_t flag * allocator where we care about the real place the memory allocation * request comes from. */ -extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller) - __alloc_size(1); +extern void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller); #define kmalloc_track_caller(size, flags) \ __kmalloc_track_caller(size, flags, _RET_IP_) diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 70c069aef02c..dcea51fb60e2 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -699,6 +699,8 @@ event_triggers_post_call(struct trace_event_file *file, bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); +bool __trace_trigger_soft_disabled(struct trace_event_file *file); + /** * trace_trigger_soft_disabled - do triggers and test if soft disabled * @file: The file pointer of the event to test @@ -708,20 +710,20 @@ bool trace_event_ignore_this_pid(struct trace_event_file *trace_file); * triggers that require testing the fields, it will return true, * otherwise false. */ -static inline bool +static __always_inline bool trace_trigger_soft_disabled(struct trace_event_file *file) { unsigned long eflags = file->flags; - if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) { - if (eflags & EVENT_FILE_FL_TRIGGER_MODE) - event_triggers_call(file, NULL, NULL, NULL); - if (eflags & EVENT_FILE_FL_SOFT_DISABLED) - return true; - if (eflags & EVENT_FILE_FL_PID_FILTER) - return trace_event_ignore_this_pid(file); - } - return false; + if (likely(!(eflags & (EVENT_FILE_FL_TRIGGER_MODE | + EVENT_FILE_FL_SOFT_DISABLED | + EVENT_FILE_FL_PID_FILTER)))) + return false; + + if (likely(eflags & EVENT_FILE_FL_TRIGGER_COND)) + return false; + + return __trace_trigger_soft_disabled(file); } #ifdef CONFIG_BPF_EVENTS 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/linux/watch_queue.h b/include/linux/watch_queue.h index c994d1b2cdba..3b9a40ae8bdb 100644 --- a/include/linux/watch_queue.h +++ b/include/linux/watch_queue.h @@ -28,7 +28,8 @@ struct watch_type_filter { struct watch_filter { union { struct rcu_head rcu; - unsigned long type_filter[2]; /* Bitmask of accepted types */ + /* Bitmask of accepted types */ + DECLARE_BITMAP(type_filter, WATCH_TYPE__NR); }; u32 nr_filters; /* Number of filters */ struct watch_type_filter filters[]; diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 4b3d0b16c185..a647e5fabdbd 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -506,8 +506,7 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk, tmp = bt_skb_sendmsg(sk, msg, len, mtu, headroom, tailroom); if (IS_ERR(tmp)) { - kfree_skb(skb); - return tmp; + return skb; } len -= tmp->len; diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 586f69d084a2..e336e9c1dda4 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -1489,6 +1489,14 @@ void hci_conn_del_sysfs(struct hci_conn *conn); /* Extended advertising support */ #define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV)) +/* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 1789: + * + * C24: Mandatory if the LE Controller supports Connection State and either + * LE Feature (LL Privacy) or LE Feature (Extended Advertising) is supported + */ +#define use_enhanced_conn_complete(dev) (ll_privacy_capable(dev) || \ + ext_adv_capable(dev)) + /* ----- HCI protocols ----- */ #define HCI_PROTO_DEFER 0x01 diff --git a/include/net/checksum.h b/include/net/checksum.h index 5218041e5c8f..79c67f14c448 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -22,7 +22,7 @@ #include <asm/checksum.h> #ifndef _HAVE_ARCH_COPY_AND_CSUM_FROM_USER -static inline +static __always_inline __wsum csum_and_copy_from_user (const void __user *src, void *dst, int len) { @@ -33,7 +33,7 @@ __wsum csum_and_copy_from_user (const void __user *src, void *dst, #endif #ifndef HAVE_CSUM_COPY_USER -static __inline__ __wsum csum_and_copy_to_user +static __always_inline __wsum csum_and_copy_to_user (const void *src, void __user *dst, int len) { __wsum sum = csum_partial(src, len, ~0U); @@ -45,7 +45,7 @@ static __inline__ __wsum csum_and_copy_to_user #endif #ifndef _HAVE_ARCH_CSUM_AND_COPY -static inline __wsum +static __always_inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len) { memcpy(dst, src, len); @@ -54,7 +54,7 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len) #endif #ifndef HAVE_ARCH_CSUM_ADD -static inline __wsum csum_add(__wsum csum, __wsum addend) +static __always_inline __wsum csum_add(__wsum csum, __wsum addend) { u32 res = (__force u32)csum; res += (__force u32)addend; @@ -62,12 +62,12 @@ static inline __wsum csum_add(__wsum csum, __wsum addend) } #endif -static inline __wsum csum_sub(__wsum csum, __wsum addend) +static __always_inline __wsum csum_sub(__wsum csum, __wsum addend) { return csum_add(csum, ~addend); } -static inline __sum16 csum16_add(__sum16 csum, __be16 addend) +static __always_inline __sum16 csum16_add(__sum16 csum, __be16 addend) { u16 res = (__force u16)csum; @@ -75,12 +75,12 @@ static inline __sum16 csum16_add(__sum16 csum, __be16 addend) return (__force __sum16)(res + (res < (__force u16)addend)); } -static inline __sum16 csum16_sub(__sum16 csum, __be16 addend) +static __always_inline __sum16 csum16_sub(__sum16 csum, __be16 addend) { return csum16_add(csum, ~addend); } -static inline __wsum csum_shift(__wsum sum, int offset) +static __always_inline __wsum csum_shift(__wsum sum, int offset) { /* rotate sum to align it with a 16b boundary */ if (offset & 1) @@ -88,42 +88,43 @@ static inline __wsum csum_shift(__wsum sum, int offset) return sum; } -static inline __wsum +static __always_inline __wsum csum_block_add(__wsum csum, __wsum csum2, int offset) { return csum_add(csum, csum_shift(csum2, offset)); } -static inline __wsum +static __always_inline __wsum csum_block_add_ext(__wsum csum, __wsum csum2, int offset, int len) { return csum_block_add(csum, csum2, offset); } -static inline __wsum +static __always_inline __wsum csum_block_sub(__wsum csum, __wsum csum2, int offset) { return csum_block_add(csum, ~csum2, offset); } -static inline __wsum csum_unfold(__sum16 n) +static __always_inline __wsum csum_unfold(__sum16 n) { return (__force __wsum)n; } -static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum) +static __always_inline +__wsum csum_partial_ext(const void *buff, int len, __wsum sum) { return csum_partial(buff, len, sum); } #define CSUM_MANGLED_0 ((__force __sum16)0xffff) -static inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) +static __always_inline void csum_replace_by_diff(__sum16 *sum, __wsum diff) { *sum = csum_fold(csum_add(diff, ~csum_unfold(*sum))); } -static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) +static __always_inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) { __wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from); @@ -136,11 +137,16 @@ static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to) * m : old value of a 16bit field * m' : new value of a 16bit field */ -static inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new) +static __always_inline void csum_replace2(__sum16 *sum, __be16 old, __be16 new) { *sum = ~csum16_add(csum16_sub(~(*sum), old), new); } +static inline void csum_replace(__wsum *csum, __wsum old, __wsum new) +{ + *csum = csum_add(csum_sub(*csum, old), new); +} + struct sk_buff; void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, __be32 from, __be32 to, bool pseudohdr); @@ -150,16 +156,16 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, void inet_proto_csum_replace_by_diff(__sum16 *sum, struct sk_buff *skb, __wsum diff, bool pseudohdr); -static inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb, - __be16 from, __be16 to, - bool pseudohdr) +static __always_inline +void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb, + __be16 from, __be16 to, bool pseudohdr) { inet_proto_csum_replace4(sum, skb, (__force __be32)from, (__force __be32)to, pseudohdr); } -static inline __wsum remcsum_adjust(void *ptr, __wsum csum, - int start, int offset) +static __always_inline __wsum remcsum_adjust(void *ptr, __wsum csum, + int start, int offset) { __sum16 *psum = (__sum16 *)(ptr + offset); __wsum delta; @@ -175,12 +181,12 @@ static inline __wsum remcsum_adjust(void *ptr, __wsum csum, return delta; } -static inline void remcsum_unadjust(__sum16 *psum, __wsum delta) +static __always_inline void remcsum_unadjust(__sum16 *psum, __wsum delta) { *psum = csum_fold(csum_sub(delta, (__force __wsum)*psum)); } -static inline __wsum wsum_negate(__wsum val) +static __always_inline __wsum wsum_negate(__wsum val) { return (__force __wsum)-((__force u32)val); } 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/ndisc.h b/include/net/ndisc.h index 53cb8de0e589..47ffb360ddfa 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -475,9 +475,9 @@ int igmp6_late_init(void); void igmp6_cleanup(void); void igmp6_late_cleanup(void); -int igmp6_event_query(struct sk_buff *skb); +void igmp6_event_query(struct sk_buff *skb); -int igmp6_event_report(struct sk_buff *skb); +void igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index a3647fadf1cc..bd59e950f4d6 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -96,6 +96,7 @@ enum flow_offload_xmit_type { FLOW_OFFLOAD_XMIT_NEIGH, FLOW_OFFLOAD_XMIT_XFRM, FLOW_OFFLOAD_XMIT_DIRECT, + FLOW_OFFLOAD_XMIT_TC, }; #define NF_FLOW_TABLE_ENCAP_MAX 2 @@ -127,7 +128,7 @@ struct flow_offload_tuple { struct { } __hash; u8 dir:2, - xmit_type:2, + xmit_type:3, encap_num:2, in_vlan_ingress:2; u16 mtu; @@ -142,6 +143,9 @@ struct flow_offload_tuple { u8 h_source[ETH_ALEN]; u8 h_dest[ETH_ALEN]; } out; + struct { + u32 iifidx; + } tc; }; }; diff --git a/include/net/netfilter/nf_queue.h b/include/net/netfilter/nf_queue.h index 9eed51e920e8..980daa6e1e3a 100644 --- a/include/net/netfilter/nf_queue.h +++ b/include/net/netfilter/nf_queue.h @@ -37,7 +37,7 @@ void nf_register_queue_handler(const struct nf_queue_handler *qh); void nf_unregister_queue_handler(void); void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict); -void nf_queue_entry_get_refs(struct nf_queue_entry *entry); +bool nf_queue_entry_get_refs(struct nf_queue_entry *entry); void nf_queue_entry_free(struct nf_queue_entry *entry); static inline void init_hashrandom(u32 *jhash_initval) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index eaf55da9a205..c4c0861deac1 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -905,9 +905,9 @@ struct nft_expr_ops { int (*offload)(struct nft_offload_ctx *ctx, struct nft_flow_rule *flow, const struct nft_expr *expr); + bool (*offload_action)(const struct nft_expr *expr); void (*offload_stats)(struct nft_expr *expr, const struct flow_stats *stats); - u32 offload_flags; const struct nft_expr_type *type; void *data; }; diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h index f9d95ff82df8..797147843958 100644 --- a/include/net/netfilter/nf_tables_offload.h +++ b/include/net/netfilter/nf_tables_offload.h @@ -67,8 +67,6 @@ struct nft_flow_rule { struct flow_rule *rule; }; -#define NFT_OFFLOAD_F_ACTION (1 << 0) - void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow, enum flow_dissector_key_id addr_type); diff --git a/include/net/sock.h b/include/net/sock.h index ff9b508d9c5f..50aecd28b355 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -507,7 +507,7 @@ struct sock { #endif u16 sk_tsflags; u8 sk_shutdown; - u32 sk_tskey; + atomic_t sk_tskey; atomic_t sk_zckey; u8 sk_clockid; @@ -2667,7 +2667,7 @@ static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, __sock_tx_timestamp(tsflags, tx_flags); if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) - *tskey = sk->sk_tskey++; + *tskey = atomic_inc_return(&sk->sk_tskey) - 1; } if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index fdb41e8bb626..76aa6f11a540 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1568,7 +1568,6 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x); -u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload); int xfrm_init_state(struct xfrm_state *x); @@ -1681,14 +1680,15 @@ int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap); -struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net); +struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, + u32 if_id); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, struct xfrm_encap_tmpl *encap); int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k, struct net *net, - struct xfrm_encap_tmpl *encap); + struct xfrm_encap_tmpl *encap, u32 if_id); #endif int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); diff --git a/include/soc/fsl/dpaa2-fd.h b/include/soc/fsl/dpaa2-fd.h index 90ae8d191f1a..bae490cac0aa 100644 --- a/include/soc/fsl/dpaa2-fd.h +++ b/include/soc/fsl/dpaa2-fd.h @@ -7,7 +7,8 @@ #ifndef __FSL_DPAA2_FD_H #define __FSL_DPAA2_FD_H -#include <linux/kernel.h> +#include <linux/byteorder/generic.h> +#include <linux/types.h> /** * DOC: DPAA2 FD - Frame Descriptor APIs for DPAA2 diff --git a/include/soc/fsl/qe/immap_qe.h b/include/soc/fsl/qe/immap_qe.h index 7614fee532f1..edd601f53f5d 100644 --- a/include/soc/fsl/qe/immap_qe.h +++ b/include/soc/fsl/qe/immap_qe.h @@ -13,7 +13,8 @@ #define _ASM_POWERPC_IMMAP_QE_H #ifdef __KERNEL__ -#include <linux/kernel.h> +#include <linux/types.h> + #include <asm/io.h> #define QE_IMMAP_SIZE (1024 * 1024) /* 1MB from 1MB+IMMR */ diff --git a/include/soc/fsl/qe/qe_tdm.h b/include/soc/fsl/qe/qe_tdm.h index b6febe225071..43ea830cfe1f 100644 --- a/include/soc/fsl/qe/qe_tdm.h +++ b/include/soc/fsl/qe/qe_tdm.h @@ -10,8 +10,8 @@ #ifndef _QE_TDM_H_ #define _QE_TDM_H_ -#include <linux/kernel.h> #include <linux/list.h> +#include <linux/types.h> #include <soc/fsl/qe/immap_qe.h> #include <soc/fsl/qe/qe.h> @@ -19,6 +19,8 @@ #include <soc/fsl/qe/ucc.h> #include <soc/fsl/qe/ucc_fast.h> +struct device_node; + /* SI RAM entries */ #define SIR_LAST 0x0001 #define SIR_BYTE 0x0002 diff --git a/include/soc/fsl/qe/ucc_fast.h b/include/soc/fsl/qe/ucc_fast.h index 9696a5b9b5d1..ad60b87a3c69 100644 --- a/include/soc/fsl/qe/ucc_fast.h +++ b/include/soc/fsl/qe/ucc_fast.h @@ -10,7 +10,7 @@ #ifndef __UCC_FAST_H__ #define __UCC_FAST_H__ -#include <linux/kernel.h> +#include <linux/types.h> #include <soc/fsl/qe/immap_qe.h> #include <soc/fsl/qe/qe.h> diff --git a/include/soc/fsl/qe/ucc_slow.h b/include/soc/fsl/qe/ucc_slow.h index 11a216e4e919..7548ce8a202d 100644 --- a/include/soc/fsl/qe/ucc_slow.h +++ b/include/soc/fsl/qe/ucc_slow.h @@ -11,7 +11,7 @@ #ifndef __UCC_SLOW_H__ #define __UCC_SLOW_H__ -#include <linux/kernel.h> +#include <linux/types.h> #include <soc/fsl/qe/immap_qe.h> #include <soc/fsl/qe/qe.h> diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h index c6f5aa74db89..2c530637e10a 100644 --- a/include/trace/events/cachefiles.h +++ b/include/trace/events/cachefiles.h @@ -56,6 +56,7 @@ enum cachefiles_coherency_trace { cachefiles_coherency_set_ok, cachefiles_coherency_vol_check_cmp, cachefiles_coherency_vol_check_ok, + cachefiles_coherency_vol_check_resv, cachefiles_coherency_vol_check_xattr, cachefiles_coherency_vol_set_fail, cachefiles_coherency_vol_set_ok, @@ -139,6 +140,7 @@ enum cachefiles_error_trace { EM(cachefiles_coherency_set_ok, "SET ok ") \ EM(cachefiles_coherency_vol_check_cmp, "VOL BAD cmp ") \ EM(cachefiles_coherency_vol_check_ok, "VOL OK ") \ + EM(cachefiles_coherency_vol_check_resv, "VOL BAD resv") \ EM(cachefiles_coherency_vol_check_xattr,"VOL BAD xatt") \ EM(cachefiles_coherency_vol_set_fail, "VOL SET fail") \ E_(cachefiles_coherency_vol_set_ok, "VOL SET ok ") 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/kvm.h b/include/uapi/linux/kvm.h index 5191b57e1562..507ee1f2aa96 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_GPA_BITS 207 #define KVM_CAP_XSAVE2 208 #define KVM_CAP_SYS_ATTRIBUTES 209 +#define KVM_CAP_PPC_AIL_MODE_3 210 #ifdef KVM_CAP_IRQ_ROUTING 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/xfrm.h b/include/uapi/linux/xfrm.h index 4e29d7851890..65e13a099b1a 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -511,6 +511,12 @@ struct xfrm_user_offload { int ifindex; __u8 flags; }; +/* This flag was exposed without any kernel code that supporting it. + * Unfortunately, strongswan has the code that uses sets this flag, + * which makes impossible to reuse this bit. + * + * So leave it here to make sure that it won't be reused by mistake. + */ #define XFRM_OFFLOAD_IPV6 1 #define XFRM_OFFLOAD_INBOUND 2 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/bpf/btf.c b/kernel/bpf/btf.c index e16dafeb2450..3e23b3fa79ff 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -5688,7 +5688,8 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, } if (check_ptr_off_reg(env, reg, regno)) return -EINVAL; - } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || reg2btf_ids[reg->type])) { + } else if (is_kfunc && (reg->type == PTR_TO_BTF_ID || + (reg2btf_ids[base_type(reg->type)] && !type_flag(reg->type)))) { const struct btf_type *reg_ref_t; const struct btf *reg_btf; const char *reg_ref_tname; @@ -5706,7 +5707,7 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, reg_ref_id = reg->btf_id; } else { reg_btf = btf_vmlinux; - reg_ref_id = *reg2btf_ids[reg->type]; + reg_ref_id = *reg2btf_ids[base_type(reg->type)]; } reg_ref_t = btf_type_skip_modifiers(reg_btf, reg_ref_id, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 01cfdf40c838..55c084251fab 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2,6 +2,7 @@ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/bpf-cgroup.h> #include <linux/rcupdate.h> #include <linux/random.h> @@ -1075,6 +1076,7 @@ static enum hrtimer_restart bpf_timer_cb(struct hrtimer *hrtimer) void *key; u32 idx; + BTF_TYPE_EMIT(struct bpf_timer); callback_fn = rcu_dereference_check(t->callback_fn, rcu_read_lock_bh_held()); if (!callback_fn) goto out; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index fa4505f9b611..ca70fe6fba38 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1355,6 +1355,7 @@ int generic_map_delete_batch(struct bpf_map *map, maybe_wait_bpf_programs(map); if (err) break; + cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) err = -EFAULT; @@ -1412,6 +1413,7 @@ int generic_map_update_batch(struct bpf_map *map, if (err) break; + cond_resched(); } if (copy_to_user(&uattr->batch.count, &cp, sizeof(cp))) @@ -1509,6 +1511,7 @@ int generic_map_lookup_batch(struct bpf_map *map, swap(prev_key, key); retry = MAP_LOOKUP_RETRIES; cp++; + cond_resched(); } if (err == -EFAULT) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 0e877dbcfeea..afc6c0e9c966 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -546,6 +546,7 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; + struct cgroup_file_ctx *ctx; BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); @@ -553,8 +554,9 @@ static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, * Release agent gets called with all capabilities, * require capabilities to set release agent. */ - if ((of->file->f_cred->user_ns != &init_user_ns) || - !capable(CAP_SYS_ADMIN)) + ctx = of->priv; + if ((ctx->ns->user_ns != &init_user_ns) || + !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN)) return -EPERM; cgrp = cgroup_kn_lock_live(of->kn, false); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 9d05c3ca2d5e..a557eea7166f 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -6166,6 +6166,20 @@ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) if (ret) goto err; + /* + * Spawning a task directly into a cgroup works by passing a file + * descriptor to the target cgroup directory. This can even be an O_PATH + * file descriptor. But it can never be a cgroup.procs file descriptor. + * This was done on purpose so spawning into a cgroup could be + * conceptualized as an atomic + * + * fd = openat(dfd_cgroup, "cgroup.procs", ...); + * write(fd, <child-pid>, ...); + * + * sequence, i.e. it's a shorthand for the caller opening and writing + * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us + * to always use the caller's credentials. + */ ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, !(kargs->flags & CLONE_THREAD), current->nsproxy->cgroup_ns); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 721325e3fa23..ef88cc366bb8 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2289,6 +2289,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); + cpus_read_lock(); percpu_down_write(&cpuset_rwsem); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); @@ -2342,6 +2343,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); + cpus_read_unlock(); } /* The various types of files and directories in a cpuset file system */ @@ -3522,8 +3524,8 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) return cs; } -/** - * cpuset_node_allowed - Can we allocate on a memory node? +/* + * __cpuset_node_allowed - Can we allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * @@ -3694,8 +3696,8 @@ void cpuset_print_current_mems_allowed(void) int cpuset_memory_pressure_enabled __read_mostly; -/** - * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. +/* + * __cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. * * Keep a running average of the rate of synchronous (direct) * page reclaim efforts initiated by tasks in each cpuset. @@ -3710,7 +3712,7 @@ int cpuset_memory_pressure_enabled __read_mostly; * "memory_pressure". Value displayed is an integer * representing the recent rate of entry into the synchronous * (direct) page reclaim by any task attached to the cpuset. - **/ + */ void __cpuset_memory_pressure_bump(void) { 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 f1e7ea160b43..6db1c475ec82 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -627,9 +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) && - (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; } @@ -696,10 +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 1cb7ca68cd4e..5ec3494b829b 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/ftrace.c b/kernel/trace/ftrace.c index 6762ae029fdd..8b568f57cc24 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -7191,7 +7191,6 @@ static int __init ftrace_nodyn_init(void) core_initcall(ftrace_nodyn_init); static inline int ftrace_init_dyn_tracefs(struct dentry *d_tracer) { return 0; } -static inline void ftrace_startup_enable(int command) { } static inline void ftrace_startup_all(int command) { } # define ftrace_startup_sysctl() do { } while (0) @@ -7793,7 +7792,7 @@ int ftrace_is_dead(void) /** * register_ftrace_function - register a function for profiling - * @ops - ops structure that holds the function for profiling. + * @ops: ops structure that holds the function for profiling. * * Register a function to be called by all functions in the * kernel. @@ -7820,7 +7819,7 @@ EXPORT_SYMBOL_GPL(register_ftrace_function); /** * unregister_ftrace_function - unregister a function for profiling. - * @ops - ops structure that holds the function to unregister + * @ops: ops structure that holds the function to unregister * * Unregister a function that was added to be called by ftrace profiling. */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7c2578efde26..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); @@ -1474,10 +1474,12 @@ static int __init set_buf_size(char *str) if (!str) return 0; buf_size = memparse(str, &str); - /* nr_entries can not be zero */ - if (buf_size == 0) - return 0; - trace_buf_size = buf_size; + /* + * nr_entries can not be zero and the startup + * tests require some buffer space. Therefore + * ensure we have at least 4096 bytes of buffer. + */ + trace_buf_size = max(4096UL, buf_size); return 1; } __setup("trace_buf_size=", set_buf_size); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index d038ddbf1bea..c5b09c31e077 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -136,7 +136,6 @@ struct kprobe_trace_entry_head { struct eprobe_trace_entry_head { struct trace_entry ent; - unsigned int type; }; struct kretprobe_trace_entry_head { diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 191db32dec46..541aa13581b9 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -242,7 +242,6 @@ static int trace_eprobe_tp_arg_update(struct trace_eprobe *ep, int i) static int eprobe_event_define_fields(struct trace_event_call *event_call) { - int ret; struct eprobe_trace_entry_head field; struct trace_probe *tp; @@ -250,8 +249,6 @@ static int eprobe_event_define_fields(struct trace_event_call *event_call) if (WARN_ON_ONCE(!tp)) return -ENOENT; - DEFINE_FIELD(unsigned int, type, FIELD_STRING_TYPE, 0); - return traceprobe_define_arg_fields(event_call, sizeof(field), tp); } @@ -270,7 +267,9 @@ print_eprobe_event(struct trace_iterator *iter, int flags, struct trace_event_call *pevent; struct trace_event *probed_event; struct trace_seq *s = &iter->seq; + struct trace_eprobe *ep; struct trace_probe *tp; + unsigned int type; field = (struct eprobe_trace_entry_head *)iter->ent; tp = trace_probe_primary_from_call( @@ -278,15 +277,18 @@ print_eprobe_event(struct trace_iterator *iter, int flags, if (WARN_ON_ONCE(!tp)) goto out; + ep = container_of(tp, struct trace_eprobe, tp); + type = ep->event->event.type; + trace_seq_printf(s, "%s: (", trace_probe_name(tp)); - probed_event = ftrace_find_event(field->type); + probed_event = ftrace_find_event(type); if (probed_event) { pevent = container_of(probed_event, struct trace_event_call, event); trace_seq_printf(s, "%s.%s", pevent->class->system, trace_event_name(pevent)); } else { - trace_seq_printf(s, "%u", field->type); + trace_seq_printf(s, "%u", type); } trace_seq_putc(s, ')'); @@ -498,10 +500,6 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec) return; entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); - if (edata->ep->event) - entry->type = edata->ep->event->event.type; - else - entry->type = 0; store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); 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_events_trigger.c b/kernel/trace/trace_events_trigger.c index d00fee705f9c..7eb9d04f1c2e 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -84,6 +84,20 @@ event_triggers_call(struct trace_event_file *file, } EXPORT_SYMBOL_GPL(event_triggers_call); +bool __trace_trigger_soft_disabled(struct trace_event_file *file) +{ + unsigned long eflags = file->flags; + + if (eflags & EVENT_FILE_FL_TRIGGER_MODE) + event_triggers_call(file, NULL, NULL, NULL); + if (eflags & EVENT_FILE_FL_SOFT_DISABLED) + return true; + if (eflags & EVENT_FILE_FL_PID_FILTER) + return trace_event_ignore_this_pid(file); + return false; +} +EXPORT_SYMBOL_GPL(__trace_trigger_soft_disabled); + /** * event_triggers_post_call - Call 'post_triggers' for a trace event * @file: The trace_event_file associated with the event @@ -1295,6 +1309,16 @@ traceon_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { + struct trace_event_file *file = data->private_data; + + if (file) { + if (tracer_tracing_is_on(file->tr)) + return; + + tracer_tracing_on(file->tr); + return; + } + if (tracing_is_on()) return; @@ -1306,8 +1330,15 @@ traceon_count_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { - if (tracing_is_on()) - return; + struct trace_event_file *file = data->private_data; + + if (file) { + if (tracer_tracing_is_on(file->tr)) + return; + } else { + if (tracing_is_on()) + return; + } if (!data->count) return; @@ -1315,7 +1346,10 @@ traceon_count_trigger(struct event_trigger_data *data, if (data->count != -1) (data->count)--; - tracing_on(); + if (file) + tracer_tracing_on(file->tr); + else + tracing_on(); } static void @@ -1323,6 +1357,16 @@ traceoff_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { + struct trace_event_file *file = data->private_data; + + if (file) { + if (!tracer_tracing_is_on(file->tr)) + return; + + tracer_tracing_off(file->tr); + return; + } + if (!tracing_is_on()) return; @@ -1334,8 +1378,15 @@ traceoff_count_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { - if (!tracing_is_on()) - return; + struct trace_event_file *file = data->private_data; + + if (file) { + if (!tracer_tracing_is_on(file->tr)) + return; + } else { + if (!tracing_is_on()) + return; + } if (!data->count) return; @@ -1343,7 +1394,10 @@ traceoff_count_trigger(struct event_trigger_data *data, if (data->count != -1) (data->count)--; - tracing_off(); + if (file) + tracer_tracing_off(file->tr); + else + tracing_off(); } static int @@ -1540,7 +1594,12 @@ stacktrace_trigger(struct event_trigger_data *data, struct trace_buffer *buffer, void *rec, struct ring_buffer_event *event) { - trace_dump_stack(STACK_SKIP); + struct trace_event_file *file = data->private_data; + + if (file) + __trace_stack(file->tr, tracing_gen_ctx(), STACK_SKIP); + else + trace_dump_stack(STACK_SKIP); } static void 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); diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 1829b4cb8cc1..e9ae1f33a7f0 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -1389,6 +1389,26 @@ static int run_osnoise(void) } /* + * In some cases, notably when running on a nohz_full CPU with + * a stopped tick PREEMPT_RCU has no way to account for QSs. + * This will eventually cause unwarranted noise as PREEMPT_RCU + * will force preemption as the means of ending the current + * grace period. We avoid this problem by calling + * rcu_momentary_dyntick_idle(), which performs a zero duration + * EQS allowing PREEMPT_RCU to end the current grace period. + * This call shouldn't be wrapped inside an RCU critical + * section. + * + * Note that in non PREEMPT_RCU kernels QSs are handled through + * cond_resched() + */ + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) { + local_irq_disable(); + rcu_momentary_dyntick_idle(); + local_irq_enable(); + } + + /* * For the non-preemptive kernel config: let threads runs, if * they so wish. */ @@ -1439,6 +1459,37 @@ static struct cpumask osnoise_cpumask; static struct cpumask save_cpumask; /* + * osnoise_sleep - sleep until the next period + */ +static void osnoise_sleep(void) +{ + u64 interval; + ktime_t wake_time; + + mutex_lock(&interface_lock); + interval = osnoise_data.sample_period - osnoise_data.sample_runtime; + mutex_unlock(&interface_lock); + + /* + * differently from hwlat_detector, the osnoise tracer can run + * without a pause because preemption is on. + */ + if (!interval) { + /* Let synchronize_rcu_tasks() make progress */ + cond_resched_tasks_rcu_qs(); + return; + } + + wake_time = ktime_add_us(ktime_get(), interval); + __set_current_state(TASK_INTERRUPTIBLE); + + while (schedule_hrtimeout_range(&wake_time, 0, HRTIMER_MODE_ABS)) { + if (kthread_should_stop()) + break; + } +} + +/* * osnoise_main - The osnoise detection kernel thread * * Calls run_osnoise() function to measure the osnoise for the configured runtime, @@ -1446,30 +1497,10 @@ static struct cpumask save_cpumask; */ static int osnoise_main(void *data) { - u64 interval; while (!kthread_should_stop()) { - run_osnoise(); - - mutex_lock(&interface_lock); - interval = osnoise_data.sample_period - osnoise_data.sample_runtime; - mutex_unlock(&interface_lock); - - do_div(interval, USEC_PER_MSEC); - - /* - * differently from hwlat_detector, the osnoise tracer can run - * without a pause because preemption is on. - */ - if (interval < 1) { - /* Let synchronize_rcu_tasks() make progress */ - cond_resched_tasks_rcu_qs(); - continue; - } - - if (msleep_interruptible(interval)) - break; + osnoise_sleep(); } return 0; @@ -2191,6 +2222,17 @@ static void osnoise_workload_stop(void) if (osnoise_has_registered_instances()) return; + /* + * If callbacks were already disabled in a previous stop + * call, there is no need to disable then again. + * + * For instance, this happens when tracing is stopped via: + * echo 0 > tracing_on + * echo nop > current_tracer. + */ + if (!trace_osnoise_callback_enabled) + return; + trace_osnoise_callback_enabled = false; /* * Make sure that ftrace_nmi_enter/exit() see diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 73d90179b51b..80863c6508e5 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -871,15 +871,15 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, switch (ptype) { case PROBE_PRINT_NORMAL: fmt = "(%lx)"; - arg = "REC->" FIELD_STRING_IP; + arg = ", REC->" FIELD_STRING_IP; break; case PROBE_PRINT_RETURN: fmt = "(%lx <- %lx)"; - arg = "REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP; + arg = ", REC->" FIELD_STRING_FUNC ", REC->" FIELD_STRING_RETIP; break; case PROBE_PRINT_EVENT: - fmt = "(%u)"; - arg = "REC->" FIELD_STRING_TYPE; + fmt = ""; + arg = ""; break; default: WARN_ON_ONCE(1); @@ -903,7 +903,7 @@ static int __set_print_fmt(struct trace_probe *tp, char *buf, int len, parg->type->fmt); } - pos += snprintf(buf + pos, LEN_OR_ZERO, "\", %s", arg); + pos += snprintf(buf + pos, LEN_OR_ZERO, "\"%s", arg); for (i = 0; i < tp->nr_args; i++) { parg = tp->args + i; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 99e7a5df025e..92cc149af0fd 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -38,7 +38,6 @@ #define FIELD_STRING_IP "__probe_ip" #define FIELD_STRING_RETIP "__probe_ret_ip" #define FIELD_STRING_FUNC "__probe_func" -#define FIELD_STRING_TYPE "__probe_type" #undef DEFINE_FIELD #define DEFINE_FIELD(type, item, name, is_signed) \ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index afd937a46496..abcadbe933bb 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -784,9 +784,7 @@ static struct fgraph_ops fgraph_ops __initdata = { .retfunc = &trace_graph_return, }; -#if defined(CONFIG_DYNAMIC_FTRACE) && \ - defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) -#define TEST_DIRECT_TRAMP +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS noinline __noclone static void trace_direct_tramp(void) { } #endif @@ -849,7 +847,7 @@ trace_selftest_startup_function_graph(struct tracer *trace, goto out; } -#ifdef TEST_DIRECT_TRAMP +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS tracing_reset_online_cpus(&tr->array_buffer); set_graph_array(tr); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 6b2e3ca7ee99..5481ba44a8d6 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -58,6 +58,18 @@ static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) cred->user_ns = user_ns; } +static unsigned long enforced_nproc_rlimit(void) +{ + unsigned long limit = RLIM_INFINITY; + + /* Is RLIMIT_NPROC currently enforced? */ + if (!uid_eq(current_uid(), GLOBAL_ROOT_UID) || + (current_user_ns() != &init_user_ns)) + limit = rlimit(RLIMIT_NPROC); + + return limit; +} + /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the @@ -122,7 +134,7 @@ int create_user_ns(struct cred *new) for (i = 0; i < MAX_PER_NAMESPACE_UCOUNTS; i++) { ns->ucount_max[i] = INT_MAX; } - set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)); + set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_NPROC, enforced_nproc_rlimit()); set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MSGQUEUE, rlimit(RLIMIT_MSGQUEUE)); set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_SIGPENDING, rlimit(RLIMIT_SIGPENDING)); set_rlimit_ucount_max(ns, UCOUNT_RLIMIT_MEMLOCK, rlimit(RLIMIT_MEMLOCK)); diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c index 9c9eb20dd2c5..00703444a219 100644 --- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -54,6 +54,7 @@ static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, bit += page->index; set_bit(bit, wqueue->notes_bitmap); + generic_pipe_buf_release(pipe, buf); } // No try_steal function => no stealing @@ -112,7 +113,7 @@ static bool post_one_notification(struct watch_queue *wqueue, buf->offset = offset; buf->len = len; buf->flags = PIPE_BUF_FLAG_WHOLE; - pipe->head = head + 1; + smp_store_release(&pipe->head, head + 1); /* vs pipe_read() */ if (!test_and_clear_bit(note, wqueue->notes_bitmap)) { spin_unlock_irq(&pipe->rd_wait.lock); @@ -219,7 +220,6 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) struct page **pages; unsigned long *bitmap; unsigned long user_bufs; - unsigned int bmsize; int ret, i, nr_pages; if (!wqueue) @@ -243,7 +243,8 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) goto error; } - ret = pipe_resize_ring(pipe, nr_notes); + nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE; + ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes)); if (ret < 0) goto error; @@ -258,17 +259,15 @@ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) pages[i]->index = i * WATCH_QUEUE_NOTES_PER_PAGE; } - bmsize = (nr_notes + BITS_PER_LONG - 1) / BITS_PER_LONG; - bmsize *= sizeof(unsigned long); - bitmap = kmalloc(bmsize, GFP_KERNEL); + bitmap = bitmap_alloc(nr_notes, GFP_KERNEL); if (!bitmap) goto error_p; - memset(bitmap, 0xff, bmsize); + bitmap_fill(bitmap, nr_notes); wqueue->notes = pages; wqueue->notes_bitmap = bitmap; wqueue->nr_pages = nr_pages; - wqueue->nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE; + wqueue->nr_notes = nr_notes; return 0; error_p: @@ -320,7 +319,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe, tf[i].info_mask & WATCH_INFO_LENGTH) goto err_filter; /* Ignore any unknown types */ - if (tf[i].type >= sizeof(wfilter->type_filter) * 8) + if (tf[i].type >= WATCH_TYPE__NR) continue; nr_filter++; } @@ -336,7 +335,7 @@ long watch_queue_set_filter(struct pipe_inode_info *pipe, q = wfilter->filters; for (i = 0; i < filter.nr_filters; i++) { - if (tf[i].type >= sizeof(wfilter->type_filter) * BITS_PER_LONG) + if (tf[i].type >= WATCH_TYPE__NR) continue; q->type = tf[i].type; @@ -371,6 +370,7 @@ static void __put_watch_queue(struct kref *kref) for (i = 0; i < wqueue->nr_pages; i++) __free_page(wqueue->notes[i]); + bitmap_free(wqueue->notes_bitmap); wfilter = rcu_access_pointer(wqueue->filter); if (wfilter) @@ -566,7 +566,7 @@ void watch_queue_clear(struct watch_queue *wqueue) rcu_read_lock(); spin_lock_bh(&wqueue->lock); - /* Prevent new additions and prevent notifications from happening */ + /* Prevent new notifications from being stored. */ wqueue->defunct = true; while (!hlist_empty(&wqueue->watches)) { diff --git a/lib/Kconfig b/lib/Kconfig index c80fde816a7e..9b5a692ce00c 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -45,7 +45,6 @@ config BITREVERSE config HAVE_ARCH_BITREVERSE bool default n - depends on BITREVERSE help This option enables the use of hardware bit-reversal instructions on architectures which support such operations. diff --git a/lib/iov_iter.c b/lib/iov_iter.c index b0e0acdf96c1..6dd5330f7a99 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -414,6 +414,7 @@ static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t by return 0; buf->ops = &page_cache_pipe_buf_ops; + buf->flags = 0; get_page(page); buf->page = page; buf->offset = offset; @@ -577,6 +578,7 @@ static size_t push_pipe(struct iov_iter *i, size_t size, break; buf->ops = &default_pipe_buf_ops; + buf->flags = 0; buf->page = page; buf->offset = 0; buf->len = min_t(ssize_t, left, PAGE_SIZE); diff --git a/lib/test_kasan.c b/lib/test_kasan.c index 26a5c9007653..3b413f8c8a71 100644 --- a/lib/test_kasan.c +++ b/lib/test_kasan.c @@ -869,11 +869,14 @@ static void kmem_cache_invalid_free(struct kunit *test) kmem_cache_destroy(cache); } +static void empty_cache_ctor(void *object) { } + static void kmem_cache_double_destroy(struct kunit *test) { struct kmem_cache *cache; - cache = kmem_cache_create("test_cache", 200, 0, 0, NULL); + /* Provide a constructor to prevent cache merging. */ + cache = kmem_cache_create("test_cache", 200, 0, 0, empty_cache_ctor); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, cache); kmem_cache_destroy(cache); KUNIT_EXPECT_KASAN_FAIL(test, kmem_cache_destroy(cache)); @@ -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/hugetlb.c b/mm/hugetlb.c index 61895cc01d09..f294db835f4b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4159,10 +4159,10 @@ static int __init hugepages_setup(char *s) pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); return 0; } + if (tmp >= nr_online_nodes) + goto invalid; node = tmp; p += count + 1; - if (node < 0 || node >= nr_online_nodes) - goto invalid; /* Parse hugepages */ if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; @@ -4851,14 +4851,13 @@ again: } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, - unsigned long new_addr, pte_t *src_pte) + unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte) { struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; - pte_t *dst_pte, pte; spinlock_t *src_ptl, *dst_ptl; + pte_t pte; - dst_pte = huge_pte_offset(mm, new_addr, huge_page_size(h)); dst_ptl = huge_pte_lock(h, mm, dst_pte); src_ptl = huge_pte_lockptr(h, mm, src_pte); @@ -4917,7 +4916,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, if (!dst_pte) break; - move_huge_pte(vma, old_addr, new_addr, src_pte); + move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte); } flush_tlb_range(vma, old_end - len, old_end); mmu_notifier_invalidate_range_end(&range); 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/memblock.c b/mm/memblock.c index 1018e50566f3..b12a364f2766 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -366,14 +366,20 @@ void __init memblock_discard(void) addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); - memblock_free_late(addr, size); + if (memblock_reserved_in_slab) + kfree(memblock.reserved.regions); + else + memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); - memblock_free_late(addr, size); + if (memblock_memory_in_slab) + kfree(memblock.memory.regions); + else + memblock_free_late(addr, size); } memblock_memory = NULL; 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 1e8fdb0b51ed..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; @@ -3186,6 +3186,7 @@ void exit_mmap(struct mm_struct *mm) vma = remove_vma(vma); cond_resched(); } + mm->mmap = NULL; mmap_write_unlock(mm); vm_unacct_memory(nr_accounted); } @@ -3255,7 +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/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 8a2b78f9c4b2..35fadb924849 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -149,22 +149,25 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) struct net *net = dev_net(net_dev); struct net_device *parent_dev; struct net *parent_net; + int iflink; bool ret; /* check if this is a batman-adv mesh interface */ if (batadv_softif_is_valid(net_dev)) return true; - /* no more parents..stop recursion */ - if (dev_get_iflink(net_dev) == 0 || - dev_get_iflink(net_dev) == net_dev->ifindex) + iflink = dev_get_iflink(net_dev); + if (iflink == 0) return false; parent_net = batadv_getlink_net(net_dev, net); + /* iflink to itself, most likely physical device */ + if (net == parent_net && iflink == net_dev->ifindex) + return false; + /* recurse over the parent device */ - parent_dev = __dev_get_by_index((struct net *)parent_net, - dev_get_iflink(net_dev)); + parent_dev = __dev_get_by_index((struct net *)parent_net, iflink); /* if we got a NULL parent_dev there is something broken.. */ if (!parent_dev) { pr_err("Cannot find parent device\n"); @@ -214,14 +217,15 @@ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) struct net_device *real_netdev = NULL; struct net *real_net; struct net *net; - int ifindex; + int iflink; ASSERT_RTNL(); if (!netdev) return NULL; - if (netdev->ifindex == dev_get_iflink(netdev)) { + iflink = dev_get_iflink(netdev); + if (iflink == 0) { dev_hold(netdev); return netdev; } @@ -231,9 +235,16 @@ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev) goto out; net = dev_net(hard_iface->soft_iface); - ifindex = dev_get_iflink(netdev); real_net = batadv_getlink_net(netdev, net); - real_netdev = dev_get_by_index(real_net, ifindex); + + /* iflink to itself, most likely physical device */ + if (net == real_net && netdev->ifindex == iflink) { + real_netdev = netdev; + dev_hold(real_netdev); + goto out; + } + + real_netdev = dev_get_by_index(real_net, iflink); out: batadv_hardif_put(hard_iface); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 2b7bd3655b07..2882bc7d79d7 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2738,6 +2738,7 @@ void hci_release_dev(struct hci_dev *hdev) hci_dev_unlock(hdev); ida_simple_remove(&hci_index_ida, hdev->id); + kfree_skb(hdev->sent_cmd); kfree(hdev); } EXPORT_SYMBOL(hci_release_dev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 0feb68f12545..ab9aa700b6b3 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); - hci_req_sync_lock(hdev); + if (!entry) + break; - err = func(hdev, data); + bt_dev_dbg(hdev, "entry %p", entry); - if (destroy) - destroy(hdev, data, err); + if (entry->func) { + int err; - hci_req_sync_unlock(hdev); + 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); + } + + kfree(entry); } } @@ -1841,6 +1838,7 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) struct bdaddr_list *b, *t; u8 num_entries = 0; bool pend_conn, pend_report; + u8 filter_policy; int err; /* Pause advertising if resolving list can be used as controllers are @@ -1927,6 +1925,8 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) err = -EINVAL; done: + filter_policy = err ? 0x00 : 0x01; + /* Enable address resolution when LL Privacy is enabled. */ err = hci_le_set_addr_resolution_enable_sync(hdev, 0x01); if (err) @@ -1937,7 +1937,7 @@ done: hci_resume_advertising_sync(hdev); /* Select filter policy to use accept list */ - return err ? 0x00 : 0x01; + return filter_policy; } /* Returns true if an le connection is in the scanning state */ @@ -3262,10 +3262,10 @@ static int hci_le_set_event_mask_sync(struct hci_dev *hdev) if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) events[0] |= 0x40; /* LE Data Length Change */ - /* If the controller supports LL Privacy feature, enable - * the corresponding event. + /* If the controller supports LL Privacy feature or LE Extended Adv, + * enable the corresponding event. */ - if (hdev->le_features[0] & HCI_LE_LL_PRIVACY) + if (use_enhanced_conn_complete(hdev)) events[1] |= 0x02; /* LE Enhanced Connection Complete */ /* If the controller supports Extended Scanner Filter @@ -4106,9 +4106,9 @@ int hci_dev_close_sync(struct hci_dev *hdev) hci_inquiry_cache_flush(hdev); hci_pend_le_actions_clear(hdev); hci_conn_hash_flush(hdev); - hci_dev_unlock(hdev); - + /* Prevent data races on hdev->smp_data or hdev->smp_bredr_data */ smp_unregister(hdev); + hci_dev_unlock(hdev); hci_sock_dev_event(hdev, HCI_DEV_DOWN); @@ -5185,7 +5185,7 @@ int hci_le_ext_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, return __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_EXT_CREATE_CONN, plen, data, HCI_EV_LE_ENHANCED_CONN_COMPLETE, - HCI_CMD_TIMEOUT, NULL); + conn->conn_timeout, NULL); } int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -5270,9 +5270,18 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) cp.min_ce_len = cpu_to_le16(0x0000); cp.max_ce_len = cpu_to_le16(0x0000); + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 4, Part E page 2261: + * + * If this event is unmasked and the HCI_LE_Connection_Complete event + * is unmasked, only the HCI_LE_Enhanced_Connection_Complete event is + * sent when a new connection has been created. + */ err = __hci_cmd_sync_status_sk(hdev, HCI_OP_LE_CREATE_CONN, - sizeof(cp), &cp, HCI_EV_LE_CONN_COMPLETE, - HCI_CMD_TIMEOUT, NULL); + sizeof(cp), &cp, + use_enhanced_conn_complete(hdev) ? + HCI_EV_LE_ENHANCED_CONN_COMPLETE : + HCI_EV_LE_CONN_COMPLETE, + conn->conn_timeout, NULL); done: /* Re-enable advertising after the connection attempt is finished. */ diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 37087cf7dc5a..230a7a8196c0 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1218,7 +1218,13 @@ static int new_settings(struct hci_dev *hdev, struct sock *skip) static void mgmt_set_powered_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; - struct mgmt_mode *cp = cmd->param; + struct mgmt_mode *cp; + + /* Make sure cmd still outstanding. */ + if (cmd != pending_find(MGMT_OP_SET_POWERED, hdev)) + return; + + cp = cmd->param; bt_dev_dbg(hdev, "err %d", err); @@ -1242,7 +1248,7 @@ static void mgmt_set_powered_complete(struct hci_dev *hdev, void *data, int err) mgmt_status(err)); } - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); } static int set_powered_sync(struct hci_dev *hdev, void *data) @@ -1281,7 +1287,7 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - cmd = mgmt_pending_new(sk, MGMT_OP_SET_POWERED, hdev, data, len); + cmd = mgmt_pending_add(sk, MGMT_OP_SET_POWERED, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@ -1290,6 +1296,9 @@ static int set_powered(struct sock *sk, struct hci_dev *hdev, void *data, err = hci_cmd_sync_queue(hdev, set_powered_sync, cmd, mgmt_set_powered_complete); + if (err < 0) + mgmt_pending_remove(cmd); + failed: hci_dev_unlock(hdev); return err; @@ -1383,6 +1392,10 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "err %d", err); + /* Make sure cmd still outstanding. */ + if (cmd != pending_find(MGMT_OP_SET_DISCOVERABLE, hdev)) + return; + hci_dev_lock(hdev); if (err) { @@ -1402,7 +1415,7 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data, new_settings(hdev, cmd->sk); done: - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); hci_dev_unlock(hdev); } @@ -1511,7 +1524,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - cmd = mgmt_pending_new(sk, MGMT_OP_SET_DISCOVERABLE, hdev, data, len); + cmd = mgmt_pending_add(sk, MGMT_OP_SET_DISCOVERABLE, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@ -1538,6 +1551,9 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data, err = hci_cmd_sync_queue(hdev, set_discoverable_sync, cmd, mgmt_set_discoverable_complete); + if (err < 0) + mgmt_pending_remove(cmd); + failed: hci_dev_unlock(hdev); return err; @@ -1550,6 +1566,10 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "err %d", err); + /* Make sure cmd still outstanding. */ + if (cmd != pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) + return; + hci_dev_lock(hdev); if (err) { @@ -1562,7 +1582,9 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data, new_settings(hdev, cmd->sk); done: - mgmt_pending_free(cmd); + if (cmd) + mgmt_pending_remove(cmd); + hci_dev_unlock(hdev); } @@ -1634,7 +1656,7 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, goto failed; } - cmd = mgmt_pending_new(sk, MGMT_OP_SET_CONNECTABLE, hdev, data, len); + cmd = mgmt_pending_add(sk, MGMT_OP_SET_CONNECTABLE, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@ -1654,6 +1676,9 @@ static int set_connectable(struct sock *sk, struct hci_dev *hdev, void *data, err = hci_cmd_sync_queue(hdev, set_connectable_sync, cmd, mgmt_set_connectable_complete); + if (err < 0) + mgmt_pending_remove(cmd); + failed: hci_dev_unlock(hdev); return err; @@ -1774,6 +1799,10 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) u8 enable = cp->val; bool changed; + /* Make sure cmd still outstanding. */ + if (cmd != pending_find(MGMT_OP_SET_SSP, hdev)) + return; + if (err) { u8 mgmt_err = mgmt_status(err); @@ -3321,6 +3350,9 @@ static void set_name_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); + if (cmd != pending_find(MGMT_OP_SET_LOCAL_NAME, hdev)) + return; + if (status) { mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_SET_LOCAL_NAME, status); @@ -3493,6 +3525,9 @@ static void set_default_phy_complete(struct hci_dev *hdev, void *data, int err) struct sk_buff *skb = cmd->skb; u8 status = mgmt_status(err); + if (cmd != pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev)) + return; + if (!status) { if (!skb) status = MGMT_STATUS_FAILED; @@ -3759,13 +3794,6 @@ static int set_wideband_speech(struct sock *sk, struct hci_dev *hdev, hci_dev_lock(hdev); - if (pending_find(MGMT_OP_SET_WIDEBAND_SPEECH, hdev)) { - err = mgmt_cmd_status(sk, hdev->id, - MGMT_OP_SET_WIDEBAND_SPEECH, - MGMT_STATUS_BUSY); - goto unlock; - } - if (hdev_is_powered(hdev) && !!cp->val != hci_dev_test_flag(hdev, HCI_WIDEBAND_SPEECH_ENABLED)) { @@ -4513,9 +4541,9 @@ 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); @@ -5036,12 +5064,6 @@ static int read_local_oob_data(struct sock *sk, struct hci_dev *hdev, goto unlock; } - if (pending_find(MGMT_OP_READ_LOCAL_OOB_DATA, hdev)) { - err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_READ_LOCAL_OOB_DATA, - MGMT_STATUS_BUSY); - goto unlock; - } - cmd = mgmt_pending_new(sk, MGMT_OP_READ_LOCAL_OOB_DATA, hdev, NULL, 0); if (!cmd) err = -ENOMEM; @@ -5261,11 +5283,16 @@ static void start_discovery_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; + if (cmd != pending_find(MGMT_OP_START_DISCOVERY, hdev) && + cmd != pending_find(MGMT_OP_START_LIMITED_DISCOVERY, hdev) && + cmd != pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev)) + return; + bt_dev_dbg(hdev, "err %d", err); mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err), cmd->param, 1); - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); hci_discovery_set_state(hdev, err ? DISCOVERY_STOPPED: DISCOVERY_FINDING); @@ -5327,7 +5354,7 @@ static int start_discovery_internal(struct sock *sk, struct hci_dev *hdev, else hdev->discovery.limited = false; - cmd = mgmt_pending_new(sk, op, hdev, data, len); + cmd = mgmt_pending_add(sk, op, hdev, data, len); if (!cmd) { err = -ENOMEM; goto failed; @@ -5336,7 +5363,7 @@ static int start_discovery_internal(struct sock *sk, struct hci_dev *hdev, err = hci_cmd_sync_queue(hdev, start_discovery_sync, cmd, start_discovery_complete); if (err < 0) { - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); goto failed; } @@ -5430,7 +5457,7 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, goto failed; } - cmd = mgmt_pending_new(sk, MGMT_OP_START_SERVICE_DISCOVERY, + cmd = mgmt_pending_add(sk, MGMT_OP_START_SERVICE_DISCOVERY, hdev, data, len); if (!cmd) { err = -ENOMEM; @@ -5463,7 +5490,7 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev, err = hci_cmd_sync_queue(hdev, start_discovery_sync, cmd, start_discovery_complete); if (err < 0) { - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); goto failed; } @@ -5495,11 +5522,14 @@ static void stop_discovery_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; + if (cmd != pending_find(MGMT_OP_STOP_DISCOVERY, hdev)) + return; + bt_dev_dbg(hdev, "err %d", err); mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err), cmd->param, 1); - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); if (!err) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); @@ -5535,7 +5565,7 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - cmd = mgmt_pending_new(sk, MGMT_OP_STOP_DISCOVERY, hdev, data, len); + cmd = mgmt_pending_add(sk, MGMT_OP_STOP_DISCOVERY, hdev, data, len); if (!cmd) { err = -ENOMEM; goto unlock; @@ -5544,7 +5574,7 @@ static int stop_discovery(struct sock *sk, struct hci_dev *hdev, void *data, err = hci_cmd_sync_queue(hdev, stop_discovery_sync, cmd, stop_discovery_complete); if (err < 0) { - mgmt_pending_free(cmd); + mgmt_pending_remove(cmd); goto unlock; } @@ -7474,6 +7504,9 @@ static void read_local_oob_ext_data_complete(struct hci_dev *hdev, void *data, u8 status = mgmt_status(err); u16 eir_len; + if (cmd != pending_find(MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev)) + return; + if (!status) { if (!skb) status = MGMT_STATUS_FAILED; @@ -7969,11 +8002,7 @@ static bool requested_adv_flags_are_valid(struct hci_dev *hdev, u32 adv_flags) static bool adv_busy(struct hci_dev *hdev) { - return (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) || - pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) || - pending_find(MGMT_OP_SET_LE, hdev) || - pending_find(MGMT_OP_ADD_EXT_ADV_PARAMS, hdev) || - pending_find(MGMT_OP_ADD_EXT_ADV_DATA, hdev)); + return pending_find(MGMT_OP_SET_LE, hdev); } static void add_adv_complete(struct hci_dev *hdev, struct sock *sk, u8 instance, @@ -8563,9 +8592,7 @@ static int remove_advertising(struct sock *sk, struct hci_dev *hdev, goto unlock; } - if (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) || - pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) || - pending_find(MGMT_OP_SET_LE, hdev)) { + if (pending_find(MGMT_OP_SET_LE, hdev)) { err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_REMOVE_ADVERTISING, MGMT_STATUS_BUSY); goto unlock; diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c index edee60bbc7b4..37eef2ce55ae 100644 --- a/net/bluetooth/mgmt_util.c +++ b/net/bluetooth/mgmt_util.c @@ -77,11 +77,12 @@ int mgmt_send_event_skb(unsigned short channel, struct sk_buff *skb, int flag, { struct hci_dev *hdev; struct mgmt_hdr *hdr; - int len = skb->len; + int len; if (!skb) return -EINVAL; + len = skb->len; hdev = bt_cb(skb)->mgmt.hdev; /* Time stamp */ diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index a271688780a2..307ee1174a6e 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -2006,7 +2006,7 @@ struct j1939_session *j1939_tp_send(struct j1939_priv *priv, /* set the end-packet for broadcast */ session->pkt.last = session->pkt.total; - skcb->tskey = session->sk->sk_tskey++; + skcb->tskey = atomic_inc_return(&session->sk->sk_tskey) - 1; session->tskey = skcb->tskey; return session; diff --git a/net/core/filter.c b/net/core/filter.c index 4603b7cd3cd1..9eb785842258 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2710,6 +2710,9 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, if (unlikely(flags)) return -EINVAL; + if (unlikely(len == 0)) + return 0; + /* First find the starting scatterlist element */ i = msg->sg.start; do { diff --git a/net/core/gro.c b/net/core/gro.c index a11b286d1495..b7d2b0dc59a2 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/net-sysfs.c b/net/core/net-sysfs.c index 7ceb3460161b..9cbc1c8289bc 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -213,7 +213,7 @@ static ssize_t speed_show(struct device *dev, if (!rtnl_trylock()) return restart_syscall(); - if (netif_running(netdev)) { + if (netif_running(netdev) && netif_device_present(netdev)) { struct ethtool_link_ksettings cmd; if (!__ethtool_get_link_ksettings(netdev, &cmd)) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9d0388bed0c1..ea51e23e9247 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2276,7 +2276,7 @@ void *__pskb_pull_tail(struct sk_buff *skb, int delta) /* Free pulled out fragments. */ while ((list = skb_shinfo(skb)->frag_list) != insp) { skb_shinfo(skb)->frag_list = list->next; - kfree_skb(list); + consume_skb(list); } /* And insert new clone at head. */ if (clone) { @@ -3876,6 +3876,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, list_skb = list_skb->next; err = 0; + delta_truesize += nskb->truesize; if (skb_shared(nskb)) { tmp = skb_clone(nskb, GFP_ATOMIC); if (tmp) { @@ -3900,7 +3901,6 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, tail = nskb; delta_len += nskb->len; - delta_truesize += nskb->truesize; skb_push(nskb, -skb_network_offset(nskb) + offset); @@ -4730,7 +4730,7 @@ static void __skb_complete_tx_timestamp(struct sk_buff *skb, if (sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) { serr->ee.ee_data = skb_shinfo(skb)->tskey; if (sk_is_tcp(sk)) - serr->ee.ee_data -= sk->sk_tskey; + serr->ee.ee_data -= atomic_read(&sk->sk_tskey); } err = sock_queue_err_skb(sk, skb); @@ -6105,7 +6105,7 @@ static int pskb_carve_frag_list(struct sk_buff *skb, /* Free pulled out fragments. */ while ((list = shinfo->frag_list) != insp) { shinfo->frag_list = list->next; - kfree_skb(list); + consume_skb(list); } /* And insert new clone at head. */ if (clone) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 8eb671c827f9..929a2b096b04 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1153,7 +1153,7 @@ static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, struct sk_psock *psock; struct bpf_prog *prog; int ret = __SK_DROP; - int len = skb->len; + int len = orig_len; /* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */ skb = skb_clone(skb, GFP_ATOMIC); diff --git a/net/core/sock.c b/net/core/sock.c index 4ff806d71921..6eb174805bf0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -879,9 +879,9 @@ int sock_set_timestamping(struct sock *sk, int optname, if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return -EINVAL; - sk->sk_tskey = tcp_sk(sk)->snd_una; + atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); } else { - sk->sk_tskey = 0; + atomic_set(&sk->sk_tskey, 0); } } diff --git a/net/core/xdp.c b/net/core/xdp.c index 7aba35504986..73fae16264e1 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -357,7 +357,8 @@ 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/dcb/dcbnl.c b/net/dcb/dcbnl.c index b441ab330fd3..dc4fb699b56c 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -2073,8 +2073,52 @@ u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev) } EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask); +static void dcbnl_flush_dev(struct net_device *dev) +{ + struct dcb_app_type *itr, *tmp; + + spin_lock_bh(&dcb_lock); + + list_for_each_entry_safe(itr, tmp, &dcb_app_list, list) { + if (itr->ifindex == dev->ifindex) { + list_del(&itr->list); + kfree(itr); + } + } + + spin_unlock_bh(&dcb_lock); +} + +static int dcbnl_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + switch (event) { + case NETDEV_UNREGISTER: + if (!dev->dcbnl_ops) + return NOTIFY_DONE; + + dcbnl_flush_dev(dev); + + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block dcbnl_nb __read_mostly = { + .notifier_call = dcbnl_netdevice_event, +}; + static int __init dcbnl_init(void) { + int err; + + err = register_netdevice_notifier(&dcbnl_nb); + if (err) + return err; + rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, 0); rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, 0); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index dcad3100b164..074e4a69a728 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1058,7 +1058,7 @@ 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(); @@ -1066,13 +1066,13 @@ static int dsa_tree_setup_master(struct dsa_switch_tree *dst) if (dsa_port_is_cpu(dp)) { err = dsa_master_setup(dp->master, dp); if (err) - return err; + break; } } rtnl_unlock(); - return 0; + return err; } static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) @@ -1261,7 +1261,7 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, info.tag_ops = tag_ops; err = dsa_tree_notify(dst, DSA_NOTIFIER_TAG_PROTO, &info); if (err) - return err; + goto out_unwind_tagger; err = dsa_tree_bind_tag_proto(dst, tag_ops); if (err) diff --git a/net/dsa/master.c b/net/dsa/master.c index 2199104ca7df..880f910b23a9 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -260,11 +260,16 @@ static void dsa_netdev_ops_set(struct net_device *dev, dev->dsa_ptr->netdev_ops = ops; } +/* Keep the master always promiscuous if the tagging protocol requires that + * (garbles MAC DA) or if it doesn't support unicast filtering, case in which + * it would revert to promiscuous mode as soon as we call dev_uc_add() on it + * anyway. + */ static void dsa_master_set_promiscuity(struct net_device *dev, int inc) { const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops; - if (!ops->promisc_on_master) + if ((dev->priv_flags & IFF_UNICAST_FLT) && !ops->promisc_on_master) return; ASSERT_RTNL(); diff --git a/net/dsa/port.c b/net/dsa/port.c index bd78192e0e47..1a40c52f5a42 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -395,10 +395,17 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br) .tree_index = dp->ds->dst->index, .sw_index = dp->ds->index, .port = dp->index, - .bridge = *dp->bridge, }; int err; + /* If the port could not be offloaded to begin with, then + * there is nothing to do. + */ + if (!dp->bridge) + return; + + info.bridge = *dp->bridge; + /* Here the port is already unbridged. Reflect the current configuration * so that drivers can program their chips accordingly. */ @@ -781,9 +788,15 @@ int dsa_port_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, struct dsa_port *cpu_dp = dp->cpu_dp; int err; - err = dev_uc_add(cpu_dp->master, addr); - if (err) - return err; + /* Avoid a call to __dev_set_promiscuity() on the master, which + * requires rtnl_lock(), since we can't guarantee that is held here, + * and we can't take it either. + */ + if (cpu_dp->master->priv_flags & IFF_UNICAST_FLT) { + err = dev_uc_add(cpu_dp->master, addr); + if (err) + return err; + } return dsa_port_notify(dp, DSA_NOTIFIER_HOST_FDB_ADD, &info); } @@ -800,9 +813,11 @@ int dsa_port_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, struct dsa_port *cpu_dp = dp->cpu_dp; int err; - err = dev_uc_del(cpu_dp->master, addr); - if (err) - return err; + if (cpu_dp->master->priv_flags & IFF_UNICAST_FLT) { + err = dev_uc_del(cpu_dp->master, addr); + if (err) + return err; + } return dsa_port_notify(dp, DSA_NOTIFIER_HOST_FDB_DEL, &info); } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9c465bac1eb0..72fde2888ad2 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1376,8 +1376,11 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, } ops = rcu_dereference(inet_offloads[proto]); - if (likely(ops && ops->callbacks.gso_segment)) + if (likely(ops && ops->callbacks.gso_segment)) { segs = ops->callbacks.gso_segment(skb, features); + if (!segs) + skb->network_header = skb_mac_header(skb) + nhoff - skb->head; + } if (IS_ERR_OR_NULL(segs)) goto out; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 851f542928a3..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; @@ -671,7 +676,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } 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/ip_output.c b/net/ipv4/ip_output.c index 139cec29ed06..7911916a480b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -991,7 +991,7 @@ static int __ip_append_data(struct sock *sk, if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) - tskey = sk->sk_tskey++; + tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 3a5994b50571..3ee947557b88 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -187,7 +187,6 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) (int)ident, &ipv6_hdr(skb)->daddr, dif); #endif } else { - pr_err("ping: protocol(%x) is not supported\n", ntohs(skb->protocol)); return NULL; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 02cb275e5487..28ff2a820f7c 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1684,11 +1684,13 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, if (!copied) copied = used; break; - } else if (used <= len) { - seq += used; - copied += used; - offset += used; } + if (WARN_ON_ONCE(used > len)) + used = len; + seq += used; + copied += used; + offset += used; + /* If recv_actor drops the lock (e.g. TCP splice * receive) the skb pointer might be invalid when * getting here: tcp_collapse might have deleted it diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c index b91003538d87..bc3a043a5d5c 100644 --- a/net/ipv4/udp_tunnel_nic.c +++ b/net/ipv4/udp_tunnel_nic.c @@ -846,7 +846,7 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn) list_for_each_entry(node, &info->shared->devices, list) if (node->dev == dev) break; - if (node->dev != dev) + if (list_entry_is_head(node, &info->shared->devices, list)) return; list_del(&node->list); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3f23da8c0b10..f908e2fd30b2 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3732,6 +3732,7 @@ static int addrconf_ifdown(struct net_device *dev, bool unregister) struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; bool keep_addr = false; + bool was_ready; int state, i; ASSERT_RTNL(); @@ -3797,7 +3798,10 @@ restart: addrconf_del_rs_timer(idev); - /* Step 2: clear flags for stateless addrconf */ + /* Step 2: clear flags for stateless addrconf, repeated down + * detection + */ + was_ready = idev->if_flags & IF_READY; if (!unregister) idev->if_flags &= ~(IF_RS_SENT|IF_RA_RCVD|IF_READY); @@ -3871,7 +3875,7 @@ restart: if (unregister) { ipv6_ac_destroy_dev(idev); ipv6_mc_destroy_dev(idev); - } else { + } else if (was_ready) { ipv6_mc_down(idev); } @@ -4998,6 +5002,7 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) goto error; + spin_lock_bh(&ifa->lock); if (!((ifa->flags&IFA_F_PERMANENT) && (ifa->prefered_lft == INFINITY_LIFE_TIME))) { preferred = ifa->prefered_lft; @@ -5019,6 +5024,7 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, preferred = INFINITY_LIFE_TIME; valid = INFINITY_LIFE_TIME; } + spin_unlock_bh(&ifa->lock); if (!ipv6_addr_any(&ifa->peer_addr)) { if (nla_put_in6_addr(skb, IFA_LOCAL, &ifa->addr) < 0 || diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 8bb2c407b46b..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; @@ -707,7 +712,7 @@ static int esp6_output(struct xfrm_state *x, struct sk_buff *skb) struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); u32 padto; - padto = min(x->tfcpad, __xfrm_state_mtu(x, dst->child_mtu_cached)); + padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached)); if (skb->len < padto) esp.tfclen = padto - skb->len; } 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/ip6_offload.c b/net/ipv6/ip6_offload.c index b29e9ba5e113..5f577e21459b 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -114,6 +114,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (likely(ops && ops->callbacks.gso_segment)) { skb_reset_transport_header(skb); segs = ops->callbacks.gso_segment(skb, features); + if (!segs) + skb->network_header = skb_mac_header(skb) + nhoff - skb->head; } if (IS_ERR_OR_NULL(segs)) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2995f8d89e7e..4788f6b37053 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1408,8 +1408,6 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (np->frag_size) mtu = np->frag_size; } - if (mtu < IPV6_MIN_MTU) - return -EINVAL; cork->base.fragsize = mtu; cork->base.gso_size = ipc6->gso_size; cork->base.tx_flags = 0; @@ -1465,14 +1463,12 @@ static int __ip6_append_data(struct sock *sk, if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) - tskey = sk->sk_tskey++; + tskey = atomic_inc_return(&sk->sk_tskey) - 1; hh_len = LL_RESERVED_SPACE(rt->dst.dev); fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len + (opt ? opt->opt_nflen : 0); - maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - - sizeof(struct frag_hdr); headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + @@ -1480,6 +1476,13 @@ static int __ip6_append_data(struct sock *sk, sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; + if (mtu < fragheaderlen || + ((mtu - fragheaderlen) & ~7) + fragheaderlen < sizeof(struct frag_hdr)) + goto emsgsize; + + maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - + sizeof(struct frag_hdr); + /* as per RFC 7112 section 5, the entire IPv6 Header Chain must fit * the first fragment */ diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index a8861db52c18..909f937befd7 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1371,27 +1371,23 @@ static void mld_process_v2(struct inet6_dev *idev, struct mld2_query *mld, } /* called with rcu_read_lock() */ -int igmp6_event_query(struct sk_buff *skb) +void igmp6_event_query(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); - if (!idev) - return -EINVAL; - - if (idev->dead) { - kfree_skb(skb); - return -ENODEV; - } + if (!idev || idev->dead) + goto out; spin_lock_bh(&idev->mc_query_lock); if (skb_queue_len(&idev->mc_query_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_query_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_query_work, 0)) in6_dev_hold(idev); + skb = NULL; } spin_unlock_bh(&idev->mc_query_lock); - - return 0; +out: + kfree_skb(skb); } static void __mld_query_work(struct sk_buff *skb) @@ -1542,27 +1538,23 @@ static void mld_query_work(struct work_struct *work) } /* called with rcu_read_lock() */ -int igmp6_event_report(struct sk_buff *skb) +void igmp6_event_report(struct sk_buff *skb) { struct inet6_dev *idev = __in6_dev_get(skb->dev); - if (!idev) - return -EINVAL; - - if (idev->dead) { - kfree_skb(skb); - return -ENODEV; - } + if (!idev || idev->dead) + goto out; spin_lock_bh(&idev->mc_report_lock); if (skb_queue_len(&idev->mc_report_queue) < MLD_MAX_SKBS) { __skb_queue_tail(&idev->mc_report_queue, skb); if (!mod_delayed_work(mld_wq, &idev->mc_report_work, 0)) in6_dev_hold(idev); + skb = NULL; } spin_unlock_bh(&idev->mc_report_lock); - - return 0; +out: + kfree_skb(skb); } static void __mld_report_work(struct sk_buff *skb) 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/key/af_key.c b/net/key/af_key.c index de24a7d474df..9bf52a09b5ff 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2623,7 +2623,7 @@ static int pfkey_migrate(struct sock *sk, struct sk_buff *skb, } return xfrm_migrate(&sel, dir, XFRM_POLICY_TYPE_MAIN, m, i, - kma ? &k : NULL, net, NULL); + kma ? &k : NULL, net, NULL, 0); out: return err; diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 74a878f213d3..1deb3d874a4b 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2021 Intel Corporation + * Copyright (C) 2018 - 2022 Intel Corporation */ #include <linux/ieee80211.h> @@ -626,6 +626,14 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, return -EINVAL; } + if (test_sta_flag(sta, WLAN_STA_MFP) && + !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { + ht_dbg(sdata, + "MFP STA not authorized - deny BA session request %pM tid %d\n", + sta->sta.addr, tid); + return -EINVAL; + } + /* * 802.11n-2009 11.5.1.1: If the initiating STA is an HT STA, is a * member of an IBSS, and has no other existing Block Ack agreement diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 330ea62231fa..e87bccaab561 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -376,7 +376,7 @@ struct ieee80211_mgd_auth_data { u8 key[WLAN_KEY_LEN_WEP104]; u8 key_len, key_idx; - bool done; + bool done, waiting; bool peer_confirmed; bool timeout_started; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e5ccf17618ab..744842c4513b 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -37,6 +37,7 @@ #define IEEE80211_AUTH_TIMEOUT_SAE (HZ * 2) #define IEEE80211_AUTH_MAX_TRIES 3 #define IEEE80211_AUTH_WAIT_ASSOC (HZ * 5) +#define IEEE80211_AUTH_WAIT_SAE_RETRY (HZ * 2) #define IEEE80211_ASSOC_TIMEOUT (HZ / 5) #define IEEE80211_ASSOC_TIMEOUT_LONG (HZ / 2) #define IEEE80211_ASSOC_TIMEOUT_SHORT (HZ / 10) @@ -3011,8 +3012,15 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, (status_code == WLAN_STATUS_ANTI_CLOG_REQUIRED || (auth_transaction == 1 && (status_code == WLAN_STATUS_SAE_HASH_TO_ELEMENT || - status_code == WLAN_STATUS_SAE_PK)))) + status_code == WLAN_STATUS_SAE_PK)))) { + /* waiting for userspace now */ + ifmgd->auth_data->waiting = true; + ifmgd->auth_data->timeout = + jiffies + IEEE80211_AUTH_WAIT_SAE_RETRY; + ifmgd->auth_data->timeout_started = true; + run_again(sdata, ifmgd->auth_data->timeout); goto notify_driver; + } sdata_info(sdata, "%pM denied authentication (status %d)\n", mgmt->sa, status_code); @@ -4603,10 +4611,10 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) if (ifmgd->auth_data && ifmgd->auth_data->timeout_started && time_after(jiffies, ifmgd->auth_data->timeout)) { - if (ifmgd->auth_data->done) { + if (ifmgd->auth_data->done || ifmgd->auth_data->waiting) { /* - * ok ... we waited for assoc but userspace didn't, - * so let's just kill the auth data + * ok ... we waited for assoc or continuation but + * userspace didn't do it, so kill the auth data */ ieee80211_destroy_auth_data(sdata, false); } else if (ieee80211_auth(sdata)) { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 93680af62c47..48d9553dafe3 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2607,7 +2607,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, * address, so that the authenticator (e.g. hostapd) will see * the frame, but bridge won't forward it anywhere else. Note * that due to earlier filtering, the only other address can - * be the PAE group address. + * be the PAE group address, unless the hardware allowed them + * through in 802.3 offloaded mode. */ if (unlikely(skb->protocol == sdata->control_port_protocol && !ether_addr_equal(ehdr->h_dest, sdata->vif.addr))) @@ -2922,13 +2923,13 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx) ether_addr_equal(sdata->vif.addr, hdr->addr3)) return RX_CONTINUE; - ac = ieee80211_select_queue_80211(sdata, skb, hdr); + ac = ieee802_1d_to_ac[skb->priority]; q = sdata->vif.hw_queue[ac]; if (ieee80211_queue_stopped(&local->hw, q)) { IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_congestion); return RX_DROP_MONITOR; } - skb_set_queue_mapping(skb, q); + skb_set_queue_mapping(skb, ac); if (!--mesh_hdr->ttl) { if (!is_multicast_ether_addr(hdr->addr1)) @@ -4514,12 +4515,7 @@ static void ieee80211_rx_8023(struct ieee80211_rx_data *rx, /* deliver to local stack */ skb->protocol = eth_type_trans(skb, fast_rx->dev); - memset(skb->cb, 0, sizeof(skb->cb)); - if (rx->list) - list_add_tail(&skb->list, rx->list); - else - netif_receive_skb(skb); - + ieee80211_deliver_skb_to_local_stack(skb, rx); } static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 3240b72271a7..7558802a1435 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -35,12 +35,14 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR), SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD), SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD), + SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP), SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX), SNMP_MIB_ITEM("MPJoinPortSynAckRx", MPTCP_MIB_JOINPORTSYNACKRX), SNMP_MIB_ITEM("MPJoinPortAckRx", MPTCP_MIB_JOINPORTACKRX), SNMP_MIB_ITEM("MismatchPortSynRx", MPTCP_MIB_MISMATCHPORTSYNRX), SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX), SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR), + SNMP_MIB_ITEM("RmAddrDrop", MPTCP_MIB_RMADDRDROP), SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index ecd3d8b117e0..2966fcb6548b 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -28,12 +28,14 @@ enum linux_mptcp_mib_field { MPTCP_MIB_ADDADDR, /* Received ADD_ADDR with echo-flag=0 */ MPTCP_MIB_ECHOADD, /* Received ADD_ADDR with echo-flag=1 */ MPTCP_MIB_PORTADD, /* Received ADD_ADDR with a port-number */ + MPTCP_MIB_ADDADDRDROP, /* Dropped incoming ADD_ADDR */ MPTCP_MIB_JOINPORTSYNRX, /* Received a SYN MP_JOIN with a different port-number */ MPTCP_MIB_JOINPORTSYNACKRX, /* Received a SYNACK MP_JOIN with a different port-number */ MPTCP_MIB_JOINPORTACKRX, /* Received an ACK MP_JOIN with a different port-number */ MPTCP_MIB_MISMATCHPORTSYNRX, /* Received a SYN MP_JOIN with a mismatched port-number */ MPTCP_MIB_MISMATCHPORTACKRX, /* Received an ACK MP_JOIN with a mismatched port-number */ MPTCP_MIB_RMADDR, /* Received RM_ADDR */ + MPTCP_MIB_RMADDRDROP, /* Dropped incoming RM_ADDR */ MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 696b2c4613a7..7bea318ac5f2 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -213,6 +213,8 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk, mptcp_pm_add_addr_send_ack(msk); } else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) { pm->remote = *addr; + } else { + __MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP); } spin_unlock_bh(&pm->lock); @@ -253,8 +255,10 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, mptcp_event_addr_removed(msk, rm_list->ids[i]); spin_lock_bh(&pm->lock); - mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED); - pm->rm_list_rx = *rm_list; + if (mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED)) + pm->rm_list_rx = *rm_list; + else + __MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_RMADDRDROP); spin_unlock_bh(&pm->lock); } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 356f596e2032..4b5d795383cd 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -546,6 +546,16 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) if (msk->pm.add_addr_signaled < add_addr_signal_max) { local = select_signal_address(pernet, msk); + /* due to racing events on both ends we can reach here while + * previous add address is still running: if we invoke now + * mptcp_pm_announce_addr(), that will fail and the + * corresponding id will be marked as used. + * Instead let the PM machinery reschedule us when the + * current address announce will be completed. + */ + if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) + return; + if (local) { if (mptcp_pm_alloc_anno_list(msk, local)) { __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); @@ -650,6 +660,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) unsigned int add_addr_accept_max; struct mptcp_addr_info remote; unsigned int subflows_max; + bool reset_port = false; int i, nr; add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk); @@ -659,15 +670,19 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) msk->pm.add_addr_accepted, add_addr_accept_max, msk->pm.remote.family); - if (lookup_subflow_by_daddr(&msk->conn_list, &msk->pm.remote)) + remote = msk->pm.remote; + if (lookup_subflow_by_daddr(&msk->conn_list, &remote)) goto add_addr_echo; + /* pick id 0 port, if none is provided the remote address */ + if (!remote.port) { + reset_port = true; + remote.port = sk->sk_dport; + } + /* connect to the specified remote address, using whatever * local address the routing configuration will pick. */ - remote = msk->pm.remote; - if (!remote.port) - remote.port = sk->sk_dport; nr = fill_local_addresses_vec(msk, addrs); msk->pm.add_addr_accepted++; @@ -680,8 +695,12 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) __mptcp_subflow_connect(sk, &addrs[i], &remote); spin_lock_bh(&msk->pm.lock); + /* be sure to echo exactly the received address */ + if (reset_port) + remote.port = 0; + add_addr_echo: - mptcp_pm_announce_addr(msk, &msk->pm.remote, true); + mptcp_pm_announce_addr(msk, &remote, true); mptcp_pm_nl_addr_send_ack(msk); } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f60f01b14fac..1c72f25f083e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -466,9 +466,12 @@ static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq) static void mptcp_set_datafin_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + u32 retransmits; - mptcp_sk(sk)->timer_ival = min(TCP_RTO_MAX, - TCP_RTO_MIN << icsk->icsk_retransmits); + retransmits = min_t(u32, icsk->icsk_retransmits, + ilog2(TCP_RTO_MAX / TCP_RTO_MIN)); + + mptcp_sk(sk)->timer_ival = TCP_RTO_MIN << retransmits; } static void __mptcp_set_timeout(struct sock *sk, long tout) @@ -3294,6 +3297,17 @@ static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) return 0; delta = msk->write_seq - v; + if (__mptcp_check_fallback(msk) && msk->first) { + struct tcp_sock *tp = tcp_sk(msk->first); + + /* the first subflow is disconnected after close - see + * __mptcp_close_ssk(). tcp_disconnect() moves the write_seq + * so ignore that status, too. + */ + if (!((1 << msk->first->sk_state) & + (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))) + delta += READ_ONCE(tp->write_seq) - tp->snd_una; + } if (delta > INT_MAX) delta = INT_MAX; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 354cb472f386..8a77a3fd69bc 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -428,14 +428,15 @@ static int __nf_register_net_hook(struct net *net, int pf, p = nf_entry_dereference(*pp); new_hooks = nf_hook_entries_grow(p, reg); - if (!IS_ERR(new_hooks)) + if (!IS_ERR(new_hooks)) { + hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); + } mutex_unlock(&nf_hook_mutex); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); - hooks_validate(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index b561e0a44a45..fc4265acd9c4 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -110,7 +110,11 @@ static int nf_flow_rule_match(struct nf_flow_match *match, nf_flow_rule_lwt_match(match, tun_info); } - key->meta.ingress_ifindex = tuple->iifidx; + if (tuple->xmit_type == FLOW_OFFLOAD_XMIT_TC) + key->meta.ingress_ifindex = tuple->tc.iifidx; + else + key->meta.ingress_ifindex = tuple->iifidx; + mask->meta.ingress_ifindex = 0xffffffff; if (tuple->encap_num > 0 && !(tuple->in_vlan_ingress & BIT(0)) && diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 6d12afabfe8a..63d1516816b1 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -46,6 +46,15 @@ void nf_unregister_queue_handler(void) } EXPORT_SYMBOL(nf_unregister_queue_handler); +static void nf_queue_sock_put(struct sock *sk) +{ +#ifdef CONFIG_INET + sock_gen_put(sk); +#else + sock_put(sk); +#endif +} + static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; @@ -54,7 +63,7 @@ static void nf_queue_entry_release_refs(struct nf_queue_entry *entry) dev_put(state->in); dev_put(state->out); if (state->sk) - sock_put(state->sk); + nf_queue_sock_put(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) dev_put(entry->physin); @@ -87,19 +96,21 @@ static void __nf_queue_entry_init_physdevs(struct nf_queue_entry *entry) } /* Bump dev refs so they don't vanish while packet is out */ -void nf_queue_entry_get_refs(struct nf_queue_entry *entry) +bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; + if (state->sk && !refcount_inc_not_zero(&state->sk->sk_refcnt)) + return false; + dev_hold(state->in); dev_hold(state->out); - if (state->sk) - sock_hold(state->sk); #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) dev_hold(entry->physin); dev_hold(entry->physout); #endif + return true; } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); @@ -169,6 +180,18 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, break; } + if (skb_sk_is_prefetched(skb)) { + struct sock *sk = skb->sk; + + if (!sk_is_refcounted(sk)) { + if (!refcount_inc_not_zero(&sk->sk_refcnt)) + return -ENOTCONN; + + /* drop refcount on skb_orphan */ + skb->destructor = sock_edemux; + } + } + entry = kmalloc(sizeof(*entry) + route_key_size, GFP_ATOMIC); if (!entry) return -ENOMEM; @@ -187,7 +210,10 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, __nf_queue_entry_init_physdevs(entry); - nf_queue_entry_get_refs(entry); + if (!nf_queue_entry_get_refs(entry)) { + kfree(entry); + return -ENOTCONN; + } switch (entry->state.pf) { case AF_INET: diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5fa16990da95..c86748b3873b 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4502,7 +4502,7 @@ static void nft_set_catchall_destroy(const struct nft_ctx *ctx, list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { list_del_rcu(&catchall->list); nft_set_elem_destroy(set, catchall->elem, true); - kfree_rcu(catchall); + kfree_rcu(catchall, rcu); } } @@ -5669,7 +5669,7 @@ static void nft_setelem_catchall_remove(const struct net *net, list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { if (catchall->elem == elem->priv) { list_del_rcu(&catchall->list); - kfree_rcu(catchall); + kfree_rcu(catchall, rcu); break; } } @@ -6551,12 +6551,15 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, { struct nft_object *newobj; struct nft_trans *trans; - int err; + int err = -ENOMEM; + + if (!try_module_get(type->owner)) + return -ENOENT; trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ, sizeof(struct nft_trans_obj)); if (!trans) - return -ENOMEM; + goto err_trans; newobj = nft_obj_init(ctx, type, attr); if (IS_ERR(newobj)) { @@ -6573,6 +6576,8 @@ static int nf_tables_updobj(const struct nft_ctx *ctx, err_free_trans: kfree(trans); +err_trans: + module_put(type->owner); return err; } @@ -8185,7 +8190,7 @@ static void nft_obj_commit_update(struct nft_trans *trans) if (obj->ops->update) obj->ops->update(obj, newobj); - kfree(newobj); + nft_obj_destroy(&trans->ctx, newobj); } static void nft_commit_release(struct nft_trans *trans) @@ -8976,7 +8981,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; case NFT_MSG_NEWOBJ: if (nft_trans_obj_update(trans)) { - kfree(nft_trans_obj_newobj(trans)); + nft_obj_destroy(&trans->ctx, nft_trans_obj_newobj(trans)); nft_trans_destroy(trans); } else { trans->ctx.table->use--; @@ -9636,10 +9641,13 @@ EXPORT_SYMBOL_GPL(__nft_release_basechain); static void __nft_release_hook(struct net *net, struct nft_table *table) { + struct nft_flowtable *flowtable; struct nft_chain *chain; list_for_each_entry(chain, &table->chains, list) nf_tables_unregister_hook(net, table, chain); + list_for_each_entry(flowtable, &table->flowtables, list) + nft_unregister_flowtable_net_hooks(net, &flowtable->hook_list); } static void __nft_release_hooks(struct net *net) diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c index 9656c1646222..2d36952b1392 100644 --- a/net/netfilter/nf_tables_offload.c +++ b/net/netfilter/nf_tables_offload.c @@ -94,7 +94,8 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net, expr = nft_expr_first(rule); while (nft_expr_more(rule, expr)) { - if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION) + if (expr->ops->offload_action && + expr->ops->offload_action(expr)) num_actions++; expr = nft_expr_next(expr); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea2d9c2a44cf..64a6acb6aeae 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -710,9 +710,15 @@ static struct nf_queue_entry * nf_queue_entry_dup(struct nf_queue_entry *e) { struct nf_queue_entry *entry = kmemdup(e, e->size, GFP_ATOMIC); - if (entry) - nf_queue_entry_get_refs(entry); - return entry; + + if (!entry) + return NULL; + + if (nf_queue_entry_get_refs(entry)) + return entry; + + kfree(entry); + return NULL; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) diff --git a/net/netfilter/nft_dup_netdev.c b/net/netfilter/nft_dup_netdev.c index bbf3fcba3df4..5b5c607fbf83 100644 --- a/net/netfilter/nft_dup_netdev.c +++ b/net/netfilter/nft_dup_netdev.c @@ -67,6 +67,11 @@ static int nft_dup_netdev_offload(struct nft_offload_ctx *ctx, return nft_fwd_dup_netdev_offload(ctx, flow, FLOW_ACTION_MIRRED, oif); } +static bool nft_dup_netdev_offload_action(const struct nft_expr *expr) +{ + return true; +} + static struct nft_expr_type nft_dup_netdev_type; static const struct nft_expr_ops nft_dup_netdev_ops = { .type = &nft_dup_netdev_type, @@ -75,6 +80,7 @@ static const struct nft_expr_ops nft_dup_netdev_ops = { .init = nft_dup_netdev_init, .dump = nft_dup_netdev_dump, .offload = nft_dup_netdev_offload, + .offload_action = nft_dup_netdev_offload_action, }; static struct nft_expr_type nft_dup_netdev_type __read_mostly = { diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index fa9301ca6033..619e394a91de 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -79,6 +79,11 @@ static int nft_fwd_netdev_offload(struct nft_offload_ctx *ctx, return nft_fwd_dup_netdev_offload(ctx, flow, FLOW_ACTION_REDIRECT, oif); } +static bool nft_fwd_netdev_offload_action(const struct nft_expr *expr) +{ + return true; +} + struct nft_fwd_neigh { u8 sreg_dev; u8 sreg_addr; @@ -222,6 +227,7 @@ static const struct nft_expr_ops nft_fwd_netdev_ops = { .dump = nft_fwd_netdev_dump, .validate = nft_fwd_validate, .offload = nft_fwd_netdev_offload, + .offload_action = nft_fwd_netdev_offload_action, }; static const struct nft_expr_ops * diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 90c64d27ae53..d0f67d325bdf 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -213,6 +213,16 @@ static int nft_immediate_offload(struct nft_offload_ctx *ctx, return 0; } +static bool nft_immediate_offload_action(const struct nft_expr *expr) +{ + const struct nft_immediate_expr *priv = nft_expr_priv(expr); + + if (priv->dreg == NFT_REG_VERDICT) + return true; + + return false; +} + static const struct nft_expr_ops nft_imm_ops = { .type = &nft_imm_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)), @@ -224,7 +234,7 @@ static const struct nft_expr_ops nft_imm_ops = { .dump = nft_immediate_dump, .validate = nft_immediate_validate, .offload = nft_immediate_offload, - .offload_flags = NFT_OFFLOAD_F_ACTION, + .offload_action = nft_immediate_offload_action, }; struct nft_expr_type nft_imm_type __read_mostly = { diff --git a/net/netfilter/nft_limit.c b/net/netfilter/nft_limit.c index c4f308460dd1..a726b623963d 100644 --- a/net/netfilter/nft_limit.c +++ b/net/netfilter/nft_limit.c @@ -340,11 +340,20 @@ static int nft_limit_obj_pkts_dump(struct sk_buff *skb, return nft_limit_dump(skb, &priv->limit, NFT_LIMIT_PKTS); } +static void nft_limit_obj_pkts_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) +{ + struct nft_limit_priv_pkts *priv = nft_obj_data(obj); + + nft_limit_destroy(ctx, &priv->limit); +} + static struct nft_object_type nft_limit_obj_type; static const struct nft_object_ops nft_limit_obj_pkts_ops = { .type = &nft_limit_obj_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_limit_priv_pkts)), .init = nft_limit_obj_pkts_init, + .destroy = nft_limit_obj_pkts_destroy, .eval = nft_limit_obj_pkts_eval, .dump = nft_limit_obj_pkts_dump, }; @@ -378,11 +387,20 @@ static int nft_limit_obj_bytes_dump(struct sk_buff *skb, return nft_limit_dump(skb, priv, NFT_LIMIT_PKT_BYTES); } +static void nft_limit_obj_bytes_destroy(const struct nft_ctx *ctx, + struct nft_object *obj) +{ + struct nft_limit_priv *priv = nft_obj_data(obj); + + nft_limit_destroy(ctx, priv); +} + static struct nft_object_type nft_limit_obj_type; static const struct nft_object_ops nft_limit_obj_bytes_ops = { .type = &nft_limit_obj_type, .size = sizeof(struct nft_limit_priv), .init = nft_limit_obj_bytes_init, + .destroy = nft_limit_obj_bytes_destroy, .eval = nft_limit_obj_bytes_eval, .dump = nft_limit_obj_bytes_dump, }; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 662e5eb1cc39..7013f55f05d1 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -220,8 +220,10 @@ static void socket_mt_destroy(const struct xt_mtdtor_param *par) { if (par->family == NFPROTO_IPV4) nf_defrag_ipv4_disable(par->net); +#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) else if (par->family == NFPROTO_IPV6) nf_defrag_ipv6_disable(par->net); +#endif } static struct xt_match socket_mt_reg[] __read_mostly = { diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 076774034bb9..780d9e2246f3 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -423,12 +423,43 @@ static void set_ipv6_addr(struct sk_buff *skb, u8 l4_proto, memcpy(addr, new_addr, sizeof(__be32[4])); } -static void set_ipv6_fl(struct ipv6hdr *nh, u32 fl, u32 mask) +static void set_ipv6_dsfield(struct sk_buff *skb, struct ipv6hdr *nh, u8 ipv6_tclass, u8 mask) { + u8 old_ipv6_tclass = ipv6_get_dsfield(nh); + + ipv6_tclass = OVS_MASKED(old_ipv6_tclass, ipv6_tclass, mask); + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum_replace(&skb->csum, (__force __wsum)(old_ipv6_tclass << 12), + (__force __wsum)(ipv6_tclass << 12)); + + ipv6_change_dsfield(nh, ~mask, ipv6_tclass); +} + +static void set_ipv6_fl(struct sk_buff *skb, struct ipv6hdr *nh, u32 fl, u32 mask) +{ + u32 ofl; + + ofl = nh->flow_lbl[0] << 16 | nh->flow_lbl[1] << 8 | nh->flow_lbl[2]; + fl = OVS_MASKED(ofl, fl, mask); + /* Bits 21-24 are always unmasked, so this retains their values. */ - OVS_SET_MASKED(nh->flow_lbl[0], (u8)(fl >> 16), (u8)(mask >> 16)); - OVS_SET_MASKED(nh->flow_lbl[1], (u8)(fl >> 8), (u8)(mask >> 8)); - OVS_SET_MASKED(nh->flow_lbl[2], (u8)fl, (u8)mask); + nh->flow_lbl[0] = (u8)(fl >> 16); + nh->flow_lbl[1] = (u8)(fl >> 8); + nh->flow_lbl[2] = (u8)fl; + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum_replace(&skb->csum, (__force __wsum)htonl(ofl), (__force __wsum)htonl(fl)); +} + +static void set_ipv6_ttl(struct sk_buff *skb, struct ipv6hdr *nh, u8 new_ttl, u8 mask) +{ + new_ttl = OVS_MASKED(nh->hop_limit, new_ttl, mask); + + if (skb->ip_summed == CHECKSUM_COMPLETE) + csum_replace(&skb->csum, (__force __wsum)(nh->hop_limit << 8), + (__force __wsum)(new_ttl << 8)); + nh->hop_limit = new_ttl; } static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl, @@ -546,18 +577,17 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, } } if (mask->ipv6_tclass) { - ipv6_change_dsfield(nh, ~mask->ipv6_tclass, key->ipv6_tclass); + set_ipv6_dsfield(skb, nh, key->ipv6_tclass, mask->ipv6_tclass); flow_key->ip.tos = ipv6_get_dsfield(nh); } if (mask->ipv6_label) { - set_ipv6_fl(nh, ntohl(key->ipv6_label), + set_ipv6_fl(skb, nh, ntohl(key->ipv6_label), ntohl(mask->ipv6_label)); flow_key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL); } if (mask->ipv6_hlimit) { - OVS_SET_MASKED(nh->hop_limit, key->ipv6_hlimit, - mask->ipv6_hlimit); + set_ipv6_ttl(skb, nh, key->ipv6_hlimit, mask->ipv6_hlimit); flow_key->ip.ttl = nh->hop_limit; } return 0; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 2811348f3acc..ca03e7284254 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -274,7 +274,7 @@ static int tcf_action_offload_add_ex(struct tc_action *action, err = tc_setup_action(&fl_action->action, actions); if (err) { NL_SET_ERR_MSG_MOD(extack, - "Failed to setup tc actions for offload\n"); + "Failed to setup tc actions for offload"); goto fl_err; } diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index f99247fc6468..ec19f625863a 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -361,6 +361,13 @@ static void tcf_ct_flow_table_put(struct tcf_ct_params *params) } } +static void tcf_ct_flow_tc_ifidx(struct flow_offload *entry, + struct nf_conn_act_ct_ext *act_ct_ext, u8 dir) +{ + entry->tuplehash[dir].tuple.xmit_type = FLOW_OFFLOAD_XMIT_TC; + entry->tuplehash[dir].tuple.tc.iifidx = act_ct_ext->ifindex[dir]; +} + static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, struct nf_conn *ct, bool tcp) @@ -385,10 +392,8 @@ static void tcf_ct_flow_table_add(struct tcf_ct_flow_table *ct_ft, act_ct_ext = nf_conn_act_ct_ext_find(ct); if (act_ct_ext) { - entry->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx = - act_ct_ext->ifindex[IP_CT_DIR_ORIGINAL]; - entry->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx = - act_ct_ext->ifindex[IP_CT_DIR_REPLY]; + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_ORIGINAL); + tcf_ct_flow_tc_ifidx(entry, act_ct_ext, FLOW_OFFLOAD_DIR_REPLY); } err = flow_offload_add(&ct_ft->nf_ft, entry); @@ -533,11 +538,6 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p, struct nf_conn *ct; u8 dir; - /* Previously seen or loopback */ - ct = nf_ct_get(skb, &ctinfo); - if ((ct && !nf_ct_is_template(ct)) || ctinfo == IP_CT_UNTRACKED) - return false; - switch (family) { case NFPROTO_IPV4: if (!tcf_ct_flow_table_fill_tuple_ipv4(skb, &tuple, &tcph)) 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/af_smc.c b/net/smc/af_smc.c index 306d9e8cd1dd..284befa90967 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -183,7 +183,7 @@ static int smc_release(struct socket *sock) { struct sock *sk = sock->sk; struct smc_sock *smc; - int rc = 0; + int old_state, rc = 0; if (!sk) goto out; @@ -191,8 +191,10 @@ static int smc_release(struct socket *sock) sock_hold(sk); /* sock_put below */ smc = smc_sk(sk); + old_state = sk->sk_state; + /* cleanup for a dangling non-blocking connect */ - if (smc->connect_nonblock && sk->sk_state == SMC_INIT) + if (smc->connect_nonblock && old_state == SMC_INIT) tcp_abort(smc->clcsock->sk, ECONNABORTED); if (cancel_work_sync(&smc->connect_work)) @@ -206,6 +208,10 @@ static int smc_release(struct socket *sock) else lock_sock(sk); + if (old_state == SMC_INIT && sk->sk_state == SMC_ACTIVE && + !smc->use_fallback) + smc_close_active_abort(smc); + rc = __smc_release(smc); /* detach socket */ @@ -3081,12 +3087,14 @@ static int __init smc_init(void) rc = tcp_register_ulp(&smc_ulp_ops); if (rc) { pr_err("%s: tcp_ulp_register fails with %d\n", __func__, rc); - goto out_sock; + goto out_ib; } static_branch_enable(&tcp_have_smc); return 0; +out_ib: + smc_ib_unregister_client(); out_sock: sock_unregister(PF_SMC); out_proto6: diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 29525d03b253..be7d704976ff 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -1161,8 +1161,8 @@ void smc_conn_free(struct smc_connection *conn) cancel_work_sync(&conn->abort_work); } if (!list_empty(&lgr->list)) { - smc_lgr_unregister_conn(conn); smc_buf_unuse(conn, lgr); /* allow buffer reuse */ + smc_lgr_unregister_conn(conn); } if (!lgr->conns_num) @@ -1864,7 +1864,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini) (ini->smcd_version == SMC_V2 || lgr->vlan_id == ini->vlan_id) && (role == SMC_CLNT || ini->is_smcd || - lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) { + (lgr->conns_num < SMC_RMBS_PER_LGR_MAX && + !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) { /* link group found */ ini->first_contact_local = 0; conn->lgr = lgr; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 0599246c0376..29f0a559d884 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -113,7 +113,7 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) pnettable = &sn->pnettable; /* remove table entry */ - write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (!pnet_name || @@ -131,7 +131,7 @@ static int smc_pnet_remove_by_pnetid(struct net *net, char *pnet_name) rc = 0; } } - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); /* if this is not the initial namespace, stop here */ if (net != &init_net) @@ -192,7 +192,7 @@ static int smc_pnet_add_by_ndev(struct net_device *ndev) sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; - write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && !pnetelem->ndev && !strncmp(pnetelem->eth_name, ndev->name, IFNAMSIZ)) { @@ -206,7 +206,7 @@ static int smc_pnet_add_by_ndev(struct net_device *ndev) break; } } - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return rc; } @@ -224,7 +224,7 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev) sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; - write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry_safe(pnetelem, tmp_pe, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && pnetelem->ndev == ndev) { dev_put_track(pnetelem->ndev, &pnetelem->dev_tracker); @@ -237,7 +237,7 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev) break; } } - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return rc; } @@ -370,7 +370,7 @@ static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, strncpy(new_pe->eth_name, eth_name, IFNAMSIZ); rc = -EEXIST; new_netdev = true; - write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_ETH && !strncmp(tmp_pe->eth_name, eth_name, IFNAMSIZ)) { @@ -385,9 +385,9 @@ static int smc_pnet_add_eth(struct smc_pnettable *pnettable, struct net *net, GFP_ATOMIC); } list_add_tail(&new_pe->list, &pnettable->pnetlist); - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); } else { - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); kfree(new_pe); goto out_put; } @@ -448,7 +448,7 @@ static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name, new_pe->ib_port = ib_port; new_ibdev = true; - write_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { @@ -458,9 +458,9 @@ static int smc_pnet_add_ib(struct smc_pnettable *pnettable, char *ib_name, } if (new_ibdev) { list_add_tail(&new_pe->list, &pnettable->pnetlist); - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); } else { - write_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); kfree(new_pe); } return (new_ibdev) ? 0 : -EEXIST; @@ -605,7 +605,7 @@ static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid, pnettable = &sn->pnettable; /* dump pnettable entries */ - read_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetid && !smc_pnet_match(pnetelem->pnet_name, pnetid)) continue; @@ -620,7 +620,7 @@ static int _smc_pnet_dump(struct net *net, struct sk_buff *skb, u32 portid, break; } } - read_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return idx; } @@ -864,7 +864,7 @@ int smc_pnet_net_init(struct net *net) struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev; INIT_LIST_HEAD(&pnettable->pnetlist); - rwlock_init(&pnettable->lock); + mutex_init(&pnettable->lock); INIT_LIST_HEAD(&pnetids_ndev->list); rwlock_init(&pnetids_ndev->lock); @@ -944,7 +944,7 @@ static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, sn = net_generic(net, smc_net_id); pnettable = &sn->pnettable; - read_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(pnetelem, &pnettable->pnetlist, list) { if (pnetelem->type == SMC_PNET_ETH && ndev == pnetelem->ndev) { /* get pnetid of netdev device */ @@ -953,7 +953,7 @@ static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev, break; } } - read_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return rc; } @@ -1156,7 +1156,7 @@ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port) sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; - read_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX) && @@ -1166,7 +1166,7 @@ int smc_pnetid_by_table_ib(struct smc_ib_device *smcibdev, u8 ib_port) break; } } - read_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return rc; } @@ -1185,7 +1185,7 @@ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev) sn = net_generic(&init_net, smc_net_id); pnettable = &sn->pnettable; - read_lock(&pnettable->lock); + mutex_lock(&pnettable->lock); list_for_each_entry(tmp_pe, &pnettable->pnetlist, list) { if (tmp_pe->type == SMC_PNET_IB && !strncmp(tmp_pe->ib_name, ib_name, IB_DEVICE_NAME_MAX)) { @@ -1194,7 +1194,7 @@ int smc_pnetid_by_table_smcd(struct smcd_dev *smcddev) break; } } - read_unlock(&pnettable->lock); + mutex_unlock(&pnettable->lock); return rc; } diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h index 14039272f7e4..80a88eea4949 100644 --- a/net/smc/smc_pnet.h +++ b/net/smc/smc_pnet.h @@ -29,7 +29,7 @@ struct smc_link_group; * @pnetlist: List of PNETIDs */ struct smc_pnettable { - rwlock_t lock; + struct mutex lock; struct list_head pnetlist; }; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 473a790f5894..a2f9c9640716 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/tipc/name_table.c b/net/tipc/name_table.c index 01396dd1c899..1d8ba233d047 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -967,7 +967,7 @@ static int __tipc_nl_add_nametable_publ(struct tipc_nl_msg *msg, list_for_each_entry(p, &sr->all_publ, all_publ) if (p->key == *last_key) break; - if (p->key != *last_key) + if (list_entry_is_head(p, &sr->all_publ, all_publ)) return -EPIPE; } else { p = list_first_entry(&sr->all_publ, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3e63c83e641c..7545321c3440 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3749,7 +3749,7 @@ static int __tipc_nl_list_sk_publ(struct sk_buff *skb, if (p->key == *last_publ) break; } - if (p->key != *last_publ) { + if (list_entry_is_head(p, &tsk->publications, binding_sock)) { /* We never set seq or call nl_dump_check_consistent() * this means that setting prev_seq here will cause the * consistence check to fail in the netlink callback diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 1e9be50469ce..527ae669f6f7 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -33,7 +33,7 @@ $(obj)/shipped-certs.c: $(wildcard $(srctree)/$(src)/certs/*.hex) echo 'unsigned int shipped_regdb_certs_len = sizeof(shipped_regdb_certs);'; \ ) > $@ -$(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDI) \ +$(obj)/extra-certs.c: $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR) \ $(wildcard $(CONFIG_CFG80211_EXTRA_REGDB_KEYDIR)/*.x509) @$(kecho) " GEN $@" $(Q)(set -e; \ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 578bff9c378b..c01fbcc848e8 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -13411,6 +13411,9 @@ static int handle_nan_filter(struct nlattr *attr_filter, i = 0; nla_for_each_nested(attr, attr_filter, rem) { filter[i].filter = nla_memdup(attr, GFP_KERNEL); + if (!filter[i].filter) + goto err; + filter[i].len = nla_len(attr); i++; } @@ -13423,6 +13426,15 @@ static int handle_nan_filter(struct nlattr *attr_filter, } return 0; + +err: + i = 0; + nla_for_each_nested(attr, attr_filter, rem) { + kfree(filter[i].filter); + i++; + } + kfree(filter); + return -ENOMEM; } static int nl80211_nan_add_func(struct sk_buff *skb, @@ -17816,7 +17828,8 @@ void cfg80211_ch_switch_notify(struct net_device *dev, wdev->chandef = *chandef; wdev->preset_chandef = *chandef; - if (wdev->iftype == NL80211_IFTYPE_STATION && + if ((wdev->iftype == NL80211_IFTYPE_STATION || + wdev->iftype == NL80211_IFTYPE_P2P_CLIENT) && !WARN_ON(!wdev->current_bss)) cfg80211_update_assoc_bss_entry(wdev, chandef->chan); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 3fa066419d37..39bce5d764de 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -223,6 +223,9 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, if (x->encap || x->tfcpad) return -EINVAL; + if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND)) + return -EINVAL; + dev = dev_get_by_index(net, xuo->ifindex); if (!dev) { if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) { @@ -262,7 +265,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC); xso->real_dev = dev; xso->num_exthdrs = 1; - xso->flags = xuo->flags; + /* Don't forward bit that is not implemented */ + xso->flags = xuo->flags & ~XFRM_OFFLOAD_IPV6; err = dev->xfrmdev_ops->xdo_dev_state_add(x); if (err) { diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index 57448fc519fc..1e8b26eecb3f 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; @@ -673,12 +676,12 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], struct net *net = xi->net; struct xfrm_if_parms p = {}; + xfrmi_netlink_parms(data, &p); if (!p.if_id) { NL_SET_ERR_MSG(extack, "if_id must be non zero"); return -EINVAL; } - xfrmi_netlink_parms(data, &p); xi = xfrmi_locate(net, &p); if (!xi) { xi = netdev_priv(dev); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 04d1ce9b510f..882526159d3a 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -4256,7 +4256,7 @@ static bool xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, } static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, - u8 dir, u8 type, struct net *net) + u8 dir, u8 type, struct net *net, u32 if_id) { struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; @@ -4265,7 +4265,8 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector * spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_direct(net, &sel->daddr, &sel->saddr, sel->family, dir); hlist_for_each_entry(pol, chain, bydst) { - if (xfrm_migrate_selector_match(sel, &pol->selector) && + if ((if_id == 0 || pol->if_id == if_id) && + xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { ret = pol; priority = ret->priority; @@ -4277,7 +4278,8 @@ static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector * if ((pol->priority >= priority) && ret) break; - if (xfrm_migrate_selector_match(sel, &pol->selector) && + if ((if_id == 0 || pol->if_id == if_id) && + xfrm_migrate_selector_match(sel, &pol->selector) && pol->type == type) { ret = pol; break; @@ -4393,7 +4395,7 @@ static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, struct xfrm_kmaddress *k, struct net *net, - struct xfrm_encap_tmpl *encap) + struct xfrm_encap_tmpl *encap, u32 if_id) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; @@ -4412,14 +4414,14 @@ int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, } /* Stage 1 - find policy */ - if ((pol = xfrm_migrate_policy_find(sel, dir, type, net)) == NULL) { + if ((pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id)) == NULL) { err = -ENOENT; goto out; } /* Stage 2 - find and update state(s) */ for (i = 0, mp = m; i < num_migrate; i++, mp++) { - if ((x = xfrm_migrate_state_find(mp, net))) { + if ((x = xfrm_migrate_state_find(mp, net, if_id))) { x_cur[nx_cur] = x; nx_cur++; xc = xfrm_state_migrate(x, mp, encap); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index ca6bee18346d..b749935152ba 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1579,9 +1579,6 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, memcpy(&x->mark, &orig->mark, sizeof(x->mark)); memcpy(&x->props.smark, &orig->props.smark, sizeof(x->props.smark)); - if (xfrm_init_state(x) < 0) - goto error; - x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; @@ -1606,7 +1603,8 @@ out: return NULL; } -struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net) +struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, + u32 if_id) { unsigned int h; struct xfrm_state *x = NULL; @@ -1622,6 +1620,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n continue; if (m->reqid && x->props.reqid != m->reqid) continue; + if (if_id != 0 && x->if_id != if_id) + continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, @@ -1637,6 +1637,8 @@ struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *n if (x->props.mode != m->mode || x->id.proto != m->proto) continue; + if (if_id != 0 && x->if_id != if_id) + continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, @@ -1663,6 +1665,11 @@ struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, if (!xc) return NULL; + xc->props.family = m->new_family; + + if (xfrm_init_state(xc) < 0) + goto error; + memcpy(&xc->id.daddr, &m->new_daddr, sizeof(xc->id.daddr)); memcpy(&xc->props.saddr, &m->new_saddr, sizeof(xc->props.saddr)); @@ -2572,7 +2579,7 @@ void xfrm_state_delete_tunnel(struct xfrm_state *x) } EXPORT_SYMBOL(xfrm_state_delete_tunnel); -u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu) +u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; @@ -2603,17 +2610,7 @@ u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu) return ((mtu - x->props.header_len - crypto_aead_authsize(aead) - net_adj) & ~(blksize - 1)) + net_adj - 2; } -EXPORT_SYMBOL_GPL(__xfrm_state_mtu); - -u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) -{ - mtu = __xfrm_state_mtu(x, mtu); - - if (x->props.family == AF_INET6 && mtu < IPV6_MIN_MTU) - return IPV6_MIN_MTU; - - return mtu; -} +EXPORT_SYMBOL_GPL(xfrm_state_mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8cd6c8129004..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: @@ -2608,6 +2593,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, int n = 0; struct net *net = sock_net(skb->sk); struct xfrm_encap_tmpl *encap = NULL; + u32 if_id = 0; if (attrs[XFRMA_MIGRATE] == NULL) return -EINVAL; @@ -2632,7 +2618,10 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, return -ENOMEM; } - err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap); + if (attrs[XFRMA_IF_ID]) + if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + + err = xfrm_migrate(&pi->sel, pi->dir, type, m, n, kmp, net, encap, if_id); kfree(encap); diff --git a/security/selinux/ima.c b/security/selinux/ima.c index 727c4e43219d..ff7aea6b3774 100644 --- a/security/selinux/ima.c +++ b/security/selinux/ima.c @@ -77,7 +77,7 @@ void selinux_ima_measure_state_locked(struct selinux_state *state) size_t policy_len; int rc = 0; - WARN_ON(!mutex_is_locked(&state->policy_mutex)); + lockdep_assert_held(&state->policy_mutex); state_str = selinux_ima_collect_state(state); if (!state_str) { @@ -117,7 +117,7 @@ void selinux_ima_measure_state_locked(struct selinux_state *state) */ void selinux_ima_measure_state(struct selinux_state *state) { - WARN_ON(mutex_is_locked(&state->policy_mutex)); + lockdep_assert_not_held(&state->policy_mutex); mutex_lock(&state->policy_mutex); selinux_ima_measure_state_locked(state); 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/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index b3edde68bc3e..323e251ed37b 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/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/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h index 6db4e2932b3d..65d147974f8d 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 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/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index 3faf0f97edb1..a4a39c3e0f19 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -476,6 +476,7 @@ #define MSR_AMD64_ICIBSEXTDCTL 0xc001103c #define MSR_AMD64_IBSOPDATA4 0xc001103d #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ +#define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 diff --git a/tools/cgroup/memcg_slabinfo.py b/tools/cgroup/memcg_slabinfo.py index 1600b17dbb8a..1d3a90d93fe2 100644 --- a/tools/cgroup/memcg_slabinfo.py +++ b/tools/cgroup/memcg_slabinfo.py @@ -11,7 +11,7 @@ from drgn.helpers.linux import list_for_each_entry, list_empty from drgn.helpers.linux import for_each_page from drgn.helpers.linux.cpumask import for_each_online_cpu from drgn.helpers.linux.percpu import per_cpu_ptr -from drgn import container_of, FaultError, Object +from drgn import container_of, FaultError, Object, cast DESC = """ @@ -69,15 +69,15 @@ def oo_objects(s): def count_partial(n, fn): - nr_pages = 0 - for page in list_for_each_entry('struct page', n.partial.address_of_(), - 'lru'): - nr_pages += fn(page) - return nr_pages + nr_objs = 0 + for slab in list_for_each_entry('struct slab', n.partial.address_of_(), + 'slab_list'): + nr_objs += fn(slab) + return nr_objs -def count_free(page): - return page.objects - page.inuse +def count_free(slab): + return slab.objects - slab.inuse def slub_get_slabinfo(s, cfg): @@ -145,14 +145,14 @@ def detect_kernel_config(): return cfg -def for_each_slab_page(prog): +def for_each_slab(prog): PGSlab = 1 << prog.constant('PG_slab') PGHead = 1 << prog.constant('PG_head') for page in for_each_page(prog): try: if page.flags.value_() & PGSlab: - yield page + yield cast('struct slab *', page) except FaultError: pass @@ -190,13 +190,13 @@ def main(): 'list'): obj_cgroups.add(ptr.value_()) - # look over all slab pages, belonging to non-root memcgs - # and look for objects belonging to the given memory cgroup - for page in for_each_slab_page(prog): - objcg_vec_raw = page.memcg_data.value_() + # look over all slab folios and look for objects belonging + # to the given memory cgroup + for slab in for_each_slab(prog): + objcg_vec_raw = slab.memcg_data.value_() if objcg_vec_raw == 0: continue - cache = page.slab_cache + cache = slab.slab_cache if not cache: continue addr = cache.value_() diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 5191b57e1562..507ee1f2aa96 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1134,6 +1134,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_VM_GPA_BITS 207 #define KVM_CAP_XSAVE2 208 #define KVM_CAP_SYS_ATTRIBUTES 209 +#define KVM_CAP_PPC_AIL_MODE_3 210 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 740ae764537e..134612bde0cb 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -106,7 +106,7 @@ static void nest_epollfd(void) printinfo("Nesting level(s): %d\n", nested); epollfdp = calloc(nested, sizeof(int)); - if (!epollfd) + if (!epollfdp) err(EXIT_FAILURE, "calloc"); for (i = 0; i < nested; i++) { diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index abae8184e171..fa478ddcd18a 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -463,7 +463,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(WEIGHT) && - evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT)) + evsel__do_check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT, allow_user_set)) return -EINVAL; if (PRINT_FIELD(SYM) && diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c index 1f147fe6595f..e32ece90e164 100644 --- a/tools/perf/tests/sigtrap.c +++ b/tools/perf/tests/sigtrap.c @@ -22,19 +22,6 @@ #include "tests.h" #include "../perf-sys.h" -/* - * PowerPC and S390 do not support creation of instruction breakpoints using the - * perf_event interface. - * - * Just disable the test for these architectures until these issues are - * resolved. - */ -#if defined(__powerpc__) || defined(__s390x__) -#define BP_ACCOUNT_IS_SUPPORTED 0 -#else -#define BP_ACCOUNT_IS_SUPPORTED 1 -#endif - #define NUM_THREADS 5 static struct { @@ -135,7 +122,7 @@ static int test__sigtrap(struct test_suite *test __maybe_unused, int subtest __m char sbuf[STRERR_BUFSIZE]; int i, fd, ret = TEST_FAIL; - if (!BP_ACCOUNT_IS_SUPPORTED) { + if (!BP_SIGNAL_IS_SUPPORTED) { pr_debug("Test not supported on this architecture"); return TEST_SKIP; } diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index f5d260b1df4d..15a4547d608e 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -44,10 +44,6 @@ int perf_data__create_dir(struct perf_data *data, int nr) if (!files) return -ENOMEM; - data->dir.version = PERF_DIR_VERSION; - data->dir.files = files; - data->dir.nr = nr; - for (i = 0; i < nr; i++) { struct perf_data_file *file = &files[i]; @@ -62,6 +58,9 @@ int perf_data__create_dir(struct perf_data *data, int nr) file->fd = ret; } + data->dir.version = PERF_DIR_VERSION; + data->dir.files = files; + data->dir.nr = nr; return 0; out_err: diff --git a/tools/perf/util/evlist-hybrid.c b/tools/perf/util/evlist-hybrid.c index 7f234215147d..57f02beef023 100644 --- a/tools/perf/util/evlist-hybrid.c +++ b/tools/perf/util/evlist-hybrid.c @@ -154,8 +154,8 @@ int evlist__fix_hybrid_cpus(struct evlist *evlist, const char *cpu_list) perf_cpu_map__put(matched_cpus); perf_cpu_map__put(unmatched_cpus); } - - ret = (unmatched_count == events_nr) ? -1 : 0; + if (events_nr) + ret = (unmatched_count == events_nr) ? -1 : 0; out: perf_cpu_map__put(cpus); return ret; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 9739b05b999e..24997925ae00 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1648,6 +1648,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, { struct parse_events_term *term; struct list_head *list = NULL; + struct list_head *orig_head = NULL; struct perf_pmu *pmu = NULL; int ok = 0; char *config; @@ -1674,7 +1675,6 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, } list_add_tail(&term->list, head); - /* Add it for all PMUs that support the alias */ list = malloc(sizeof(struct list_head)); if (!list) @@ -1687,13 +1687,15 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, list_for_each_entry(alias, &pmu->aliases, list) { if (!strcasecmp(alias->name, str)) { + parse_events_copy_term_list(head, &orig_head); if (!parse_events_add_pmu(parse_state, list, - pmu->name, head, + pmu->name, orig_head, true, true)) { pr_debug("%s -> %s/%s/\n", str, pmu->name, alias->str); ok++; } + parse_events_terms__delete(orig_head); } } } @@ -2193,7 +2195,7 @@ int perf_pmu__test_parse_init(void) for (i = 0; i < ARRAY_SIZE(symbols); i++, tmp++) { tmp->type = symbols[i].type; tmp->symbol = strdup(symbols[i].symbol); - if (!list->symbol) + if (!tmp->symbol) goto err_free; } diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c new file mode 100644 index 000000000000..f74b82305da8 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <test_progs.h> +#include "timer_crash.skel.h" + +enum { + MODE_ARRAY, + MODE_HASH, +}; + +static void test_timer_crash_mode(int mode) +{ + struct timer_crash *skel; + + skel = timer_crash__open_and_load(); + if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load")) + return; + skel->bss->pid = getpid(); + skel->bss->crash_map = mode; + if (!ASSERT_OK(timer_crash__attach(skel), "timer_crash__attach")) + goto end; + usleep(1); +end: + timer_crash__destroy(skel); +} + +void test_timer_crash(void) +{ + if (test__start_subtest("array")) + test_timer_crash_mode(MODE_ARRAY); + if (test__start_subtest("hash")) + test_timer_crash_mode(MODE_HASH); +} diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h index 2966564b8497..6c85b00f27b2 100644 --- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h @@ -235,7 +235,7 @@ SEC("sk_msg1") int bpf_prog4(struct sk_msg_md *msg) { int *bytes, zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5; - int *start, *end, *start_push, *end_push, *start_pop, *pop; + int *start, *end, *start_push, *end_push, *start_pop, *pop, err = 0; bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); if (bytes) @@ -249,8 +249,11 @@ int bpf_prog4(struct sk_msg_md *msg) bpf_msg_pull_data(msg, *start, *end, 0); start_push = bpf_map_lookup_elem(&sock_bytes, &two); end_push = bpf_map_lookup_elem(&sock_bytes, &three); - if (start_push && end_push) - bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_DROP; + } start_pop = bpf_map_lookup_elem(&sock_bytes, &four); pop = bpf_map_lookup_elem(&sock_bytes, &five); if (start_pop && pop) @@ -263,6 +266,7 @@ int bpf_prog6(struct sk_msg_md *msg) { int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, key = 0; int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop, *f; + int err = 0; __u64 flags = 0; bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); @@ -279,8 +283,11 @@ int bpf_prog6(struct sk_msg_md *msg) start_push = bpf_map_lookup_elem(&sock_bytes, &two); end_push = bpf_map_lookup_elem(&sock_bytes, &three); - if (start_push && end_push) - bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_DROP; + } start_pop = bpf_map_lookup_elem(&sock_bytes, &four); pop = bpf_map_lookup_elem(&sock_bytes, &five); @@ -338,7 +345,7 @@ SEC("sk_msg5") int bpf_prog10(struct sk_msg_md *msg) { int *bytes, *start, *end, *start_push, *end_push, *start_pop, *pop; - int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5; + int zero = 0, one = 1, two = 2, three = 3, four = 4, five = 5, err = 0; bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero); if (bytes) @@ -352,8 +359,11 @@ int bpf_prog10(struct sk_msg_md *msg) bpf_msg_pull_data(msg, *start, *end, 0); start_push = bpf_map_lookup_elem(&sock_bytes, &two); end_push = bpf_map_lookup_elem(&sock_bytes, &three); - if (start_push && end_push) - bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (start_push && end_push) { + err = bpf_msg_push_data(msg, *start_push, *end_push, 0); + if (err) + return SK_PASS; + } start_pop = bpf_map_lookup_elem(&sock_bytes, &four); pop = bpf_map_lookup_elem(&sock_bytes, &five); if (start_pop && pop) diff --git a/tools/testing/selftests/bpf/progs/timer_crash.c b/tools/testing/selftests/bpf/progs/timer_crash.c new file mode 100644 index 000000000000..f8f7944e70da --- /dev/null +++ b/tools/testing/selftests/bpf/progs/timer_crash.c @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <vmlinux.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +struct map_elem { + struct bpf_timer timer; + struct bpf_spin_lock lock; +}; + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_elem); +} amap SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 1); + __type(key, int); + __type(value, struct map_elem); +} hmap SEC(".maps"); + +int pid = 0; +int crash_map = 0; /* 0 for amap, 1 for hmap */ + +SEC("fentry/do_nanosleep") +int sys_enter(void *ctx) +{ + struct map_elem *e, value = {}; + void *map = crash_map ? (void *)&hmap : (void *)&amap; + + if (bpf_get_current_task_btf()->tgid != pid) + return 0; + + *(void **)&value = (void *)0xdeadcaf3; + + bpf_map_update_elem(map, &(int){0}, &value, 0); + /* For array map, doing bpf_map_update_elem will do a + * check_and_free_timer_in_array, which will trigger the crash if timer + * pointer was overwritten, for hmap we need to use bpf_timer_cancel. + */ + if (crash_map == 1) { + e = bpf_map_lookup_elem(map, &(int){0}); + if (!e) + return 0; + bpf_timer_cancel(&e->timer); + } + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index bcb110e830ce..dea33dc93790 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -50,8 +50,8 @@ for current_test in ${TESTS:-$ALL_TESTS}; do else log_test "'$current_test' [$profile] overflow $target" fi + RET_FIN=$(( RET_FIN || RET )) done - RET_FIN=$(( RET_FIN || RET )) done done current_test="" diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh index 3e3e06ea5703..86e787895f78 100644 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_police_scale.sh @@ -60,7 +60,8 @@ __tc_police_test() tc_police_rules_create $count $should_fail - offload_count=$(tc filter show dev $swp1 ingress | grep in_hw | wc -l) + offload_count=$(tc -j filter show dev $swp1 ingress | + jq "[.[] | select(.options.in_hw == true)] | length") ((offload_count == count)) check_err_fail $should_fail $? "tc police offload count" } diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c index 9ad38bd360a4..b08d30bf71c5 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c @@ -366,6 +366,7 @@ static struct kvm_vm *test_vm_create(void) { struct kvm_vm *vm; unsigned int i; + int ret; int nr_vcpus = test_args.nr_vcpus; vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL); @@ -382,7 +383,11 @@ static struct kvm_vm *test_vm_create(void) ucall_init(vm, NULL); test_init_timer_irq(vm); - vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); + ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA); + if (ret < 0) { + print_skip("Failed to create vgic-v3"); + exit(KSFT_SKIP); + } /* Make all the test's cmdline args visible to the guest */ sync_global_to_guest(vm, test_args); diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c index e6c7d7f8fbd1..7eca97799917 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c +++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c @@ -761,6 +761,10 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split) gic_fd = vgic_v3_setup(vm, 1, nr_irqs, GICD_BASE_GPA, GICR_BASE_GPA); + if (gic_fd < 0) { + print_skip("Failed to create vgic-v3, skipping"); + exit(KSFT_SKIP); + } vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handlers[args.eoi_split][args.level_sensitive]); diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c index b3a0fca0d780..f5cd0c536d85 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c +++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c @@ -52,7 +52,9 @@ int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs, nr_vcpus, nr_vcpus_created); /* Distributor setup */ - gic_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, false); + if (_kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, + false, &gic_fd) != 0) + return -1; kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS, 0, &nr_irqs, true); diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index 192a2899bae8..94df2692e6e4 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -455,6 +455,7 @@ static void mfd_fail_write(int fd) printf("mmap()+mprotect() didn't fail as expected\n"); abort(); } + munmap(p, mfd_def_size); } /* verify PUNCH_HOLE fails */ diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 2674ba20d524..ff821025d309 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -71,6 +71,36 @@ chk_msk_remote_key_nr() __chk_nr "grep -c remote_key" $* } +# $1: ns, $2: port +wait_local_port_listen() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec "${listener_ns}" cat /proc/net/tcp | \ + awk "BEGIN {rc=1} {if (\$2 ~ /:${port_hex}\$/ && \$4 ~ /0A/) {rc=0; exit}} END {exit rc}" && + break + sleep 0.1 + done +} + +wait_connected() +{ + local listener_ns="${1}" + local port="${2}" + + local port_hex i + + port_hex="$(printf "%04X" "${port}")" + for i in $(seq 10); do + ip netns exec ${listener_ns} grep -q " 0100007F:${port_hex} " /proc/net/tcp && break + sleep 0.1 + done +} trap cleanup EXIT ip netns add $ns @@ -81,15 +111,15 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10000 -l -t ${timeout_poll} \ 0.0.0.0 >/dev/null & -sleep 0.1 +wait_local_port_listen $ns 10000 chk_msk_nr 0 "no msk on netns creation" echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10000 -j -t ${timeout_poll} \ + ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \ 127.0.0.1 >/dev/null & -sleep 0.1 +wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" @@ -101,13 +131,13 @@ echo "a" | \ ip netns exec $ns \ ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \ 0.0.0.0 >/dev/null & -sleep 0.1 +wait_local_port_listen $ns 10001 echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10001 -j -t ${timeout_poll} \ + ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \ 127.0.0.1 >/dev/null & -sleep 0.1 +wait_connected $ns 10001 chk_msk_fallback_nr 1 "check fallback" flush_pids @@ -119,7 +149,7 @@ for I in `seq 1 $NR_CLIENTS`; do ./mptcp_connect -p $((I+10001)) -l -w 10 \ -t ${timeout_poll} 0.0.0.0 >/dev/null & done -sleep 0.1 +wait_local_port_listen $ns $((NR_CLIENTS + 10001)) for I in `seq 1 $NR_CLIENTS`; do echo "b" | \ diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index cb5809b89081..f0f4ab96b8f3 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -763,8 +763,8 @@ run_tests_disconnect() run_tests_lo "$ns1" "$ns1" dead:beef:1::1 1 "-I 3 -i $old_cin" # restore previous status - cout=$old_cout - cout_disconnect="$cout".disconnect + sin=$old_sin + sin_disconnect="$cout".disconnect cin=$old_cin cin_disconnect="$cin".disconnect connect_per_transfer=1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index c0801df15f54..0c8a2a20b96c 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -660,6 +660,7 @@ chk_join_nr() local ack_nr=$4 local count local dump_stats + local with_cookie printf "%02u %-36s %s" "$TEST_COUNT" "$msg" "syn" count=`ip netns exec $ns1 nstat -as | grep MPTcpExtMPJoinSynRx | awk '{print $2}'` @@ -673,12 +674,20 @@ chk_join_nr() 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 $2}'` [ -z "$count" ] && count=0 if [ "$count" != "$syn_ack_nr" ]; then - echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" - ret=1 - dump_stats=1 + # simult connections exceeding the limit with cookie enabled could go up to + # synack validation as the conn limit can be enforced reliably only after + # the subflow creation + if [ "$with_cookie" = 2 ] && [ "$count" -gt "$syn_ack_nr" ] && [ "$count" -le "$syn_nr" ]; then + echo -n "[ ok ]" + else + echo "[fail] got $count JOIN[s] synack expected $syn_ack_nr" + ret=1 + dump_stats=1 + fi else echo -n "[ ok ]" fi @@ -752,11 +761,17 @@ chk_add_nr() local mis_ack_nr=${8:-0} local count local dump_stats + local timeout + + timeout=`ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout` printf "%-39s %s" " " "add" - count=`ip netns exec $ns2 nstat -as | grep MPTcpExtAddAddr | awk '{print $2}'` + count=`ip netns exec $ns2 nstat -as MPTcpExtAddAddr | grep MPTcpExtAddAddr | awk '{print $2}'` [ -z "$count" ] && count=0 - if [ "$count" != "$add_nr" ]; then + + # 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 echo "[fail] got $count ADD_ADDR[s] expected $add_nr" ret=1 dump_stats=1 @@ -961,7 +976,7 @@ wait_for_tw() local ns=$1 while [ $time -lt $timeout_ms ]; do - local cnt=$(ip netns exec $ns ss -t state time-wait |wc -l) + local cnt=$(ip netns exec $ns nstat -as TcpAttemptFails | grep TcpAttemptFails | awk '{print $2}') [ "$cnt" = 1 ] && return 1 time=$((time + 100)) @@ -1158,7 +1173,10 @@ signal_address_tests() ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags signal ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags signal ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags signal - run_tests $ns1 $ns2 10.0.1.1 + + # 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 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/netfilter/.gitignore b/tools/testing/selftests/netfilter/.gitignore index 8448f74adfec..4cb887b57413 100644 --- a/tools/testing/selftests/netfilter/.gitignore +++ b/tools/testing/selftests/netfilter/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only nf-queue +connect_close diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index e4f845dd942b..7e81c9a7fff9 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -9,6 +9,6 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ conntrack_vrf.sh nft_synproxy.sh LDLIBS = -lmnl -TEST_GEN_FILES = nf-queue +TEST_GEN_FILES = nf-queue connect_close include ../lib.mk diff --git a/tools/testing/selftests/netfilter/connect_close.c b/tools/testing/selftests/netfilter/connect_close.c new file mode 100644 index 000000000000..1c3b0add54c4 --- /dev/null +++ b/tools/testing/selftests/netfilter/connect_close.c @@ -0,0 +1,136 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <stdlib.h> +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <signal.h> + +#include <arpa/inet.h> +#include <sys/socket.h> + +#define PORT 12345 +#define RUNTIME 10 + +static struct { + unsigned int timeout; + unsigned int port; +} opts = { + .timeout = RUNTIME, + .port = PORT, +}; + +static void handler(int sig) +{ + _exit(sig == SIGALRM ? 0 : 1); +} + +static void set_timeout(void) +{ + struct sigaction action = { + .sa_handler = handler, + }; + + sigaction(SIGALRM, &action, NULL); + + alarm(opts.timeout); +} + +static void do_connect(const struct sockaddr_in *dst) +{ + int s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + + if (s >= 0) + fcntl(s, F_SETFL, O_NONBLOCK); + + connect(s, (struct sockaddr *)dst, sizeof(*dst)); + close(s); +} + +static void do_accept(const struct sockaddr_in *src) +{ + int c, one = 1, s = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP); + + if (s < 0) + return; + + setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &one, sizeof(one)); + setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &one, sizeof(one)); + + bind(s, (struct sockaddr *)src, sizeof(*src)); + + listen(s, 16); + + c = accept(s, NULL, NULL); + if (c >= 0) + close(c); + + close(s); +} + +static int accept_loop(void) +{ + struct sockaddr_in src = { + .sin_family = AF_INET, + .sin_port = htons(opts.port), + }; + + inet_pton(AF_INET, "127.0.0.1", &src.sin_addr); + + set_timeout(); + + for (;;) + do_accept(&src); + + return 1; +} + +static int connect_loop(void) +{ + struct sockaddr_in dst = { + .sin_family = AF_INET, + .sin_port = htons(opts.port), + }; + + inet_pton(AF_INET, "127.0.0.1", &dst.sin_addr); + + set_timeout(); + + for (;;) + do_connect(&dst); + + return 1; +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "t:p:")) != -1) { + switch (c) { + case 't': + opts.timeout = atoi(optarg); + break; + case 'p': + opts.port = atoi(optarg); + break; + } + } +} + +int main(int argc, char *argv[]) +{ + pid_t p; + + parse_opts(argc, argv); + + p = fork(); + if (p < 0) + return 111; + + if (p > 0) + return accept_loop(); + + return connect_loop(); +} diff --git a/tools/testing/selftests/netfilter/nft_queue.sh b/tools/testing/selftests/netfilter/nft_queue.sh index 7d27f1f3bc01..e12729753351 100755 --- a/tools/testing/selftests/netfilter/nft_queue.sh +++ b/tools/testing/selftests/netfilter/nft_queue.sh @@ -113,6 +113,7 @@ table inet $name { chain output { type filter hook output priority $prio; policy accept; tcp dport 12345 queue num 3 + tcp sport 23456 queue num 3 jump nfq } chain post { @@ -296,6 +297,23 @@ test_tcp_localhost() wait 2>/dev/null } +test_tcp_localhost_connectclose() +{ + tmpfile=$(mktemp) || exit 1 + + ip netns exec ${nsrouter} ./connect_close -p 23456 -t $timeout & + + ip netns exec ${nsrouter} ./nf-queue -q 3 -t $timeout & + local nfqpid=$! + + sleep 1 + rm -f "$tmpfile" + + wait $rpid + [ $? -eq 0 ] && echo "PASS: tcp via loopback with connect/close" + wait 2>/dev/null +} + test_tcp_localhost_requeue() { ip netns exec ${nsrouter} nft -f /dev/stdin <<EOF @@ -424,6 +442,7 @@ test_queue 20 test_tcp_forward test_tcp_localhost +test_tcp_localhost_connectclose test_tcp_localhost_requeue test_icmp_vrf 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/map_fixed_noreplace.c b/tools/testing/selftests/vm/map_fixed_noreplace.c index d91bde511268..eed44322d1a6 100644 --- a/tools/testing/selftests/vm/map_fixed_noreplace.c +++ b/tools/testing/selftests/vm/map_fixed_noreplace.c @@ -17,9 +17,6 @@ #define MAP_FIXED_NOREPLACE 0x100000 #endif -#define BASE_ADDRESS (256ul * 1024 * 1024) - - static void dump_maps(void) { char cmd[32]; @@ -28,18 +25,46 @@ static void dump_maps(void) system(cmd); } +static unsigned long find_base_addr(unsigned long size) +{ + void *addr; + unsigned long flags; + + flags = MAP_PRIVATE | MAP_ANONYMOUS; + addr = mmap(NULL, size, PROT_NONE, flags, -1, 0); + if (addr == MAP_FAILED) { + printf("Error: couldn't map the space we need for the test\n"); + return 0; + } + + if (munmap(addr, size) != 0) { + printf("Error: couldn't map the space we need for the test\n"); + return 0; + } + return (unsigned long)addr; +} + int main(void) { + unsigned long base_addr; unsigned long flags, addr, size, page_size; char *p; page_size = sysconf(_SC_PAGE_SIZE); + //let's find a base addr that is free before we start the tests + size = 5 * page_size; + base_addr = find_base_addr(size); + if (!base_addr) { + printf("Error: couldn't map the space we need for the test\n"); + return 1; + } + flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE; // Check we can map all the areas we need below errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); @@ -60,7 +85,7 @@ int main(void) printf("unmap() successful\n"); errno = 0; - addr = BASE_ADDRESS + page_size; + addr = base_addr + page_size; size = 3 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -80,7 +105,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -101,7 +126,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS + (2 * page_size); + addr = base_addr + (2 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -121,7 +146,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS + (3 * page_size); + addr = base_addr + (3 * page_size); size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -141,7 +166,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = 2 * page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -161,7 +186,7 @@ int main(void) * +4 | free | */ errno = 0; - addr = BASE_ADDRESS; + addr = base_addr; size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -181,7 +206,7 @@ int main(void) * +4 | free | new */ errno = 0; - addr = BASE_ADDRESS + (4 * page_size); + addr = base_addr + (4 * page_size); size = page_size; p = mmap((void *)addr, size, PROT_NONE, flags, -1, 0); printf("mmap() @ 0x%lx-0x%lx p=%p result=%m\n", addr, addr + size, p); @@ -192,7 +217,7 @@ int main(void) return 1; } - addr = BASE_ADDRESS; + addr = base_addr; size = 5 * page_size; if (munmap((void *)addr, size) != 0) { dump_maps(); 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/tracing/rtla/src/osnoise.c b/tools/tracing/rtla/src/osnoise.c index 5648f9252e58..e60f1862bad0 100644 --- a/tools/tracing/rtla/src/osnoise.c +++ b/tools/tracing/rtla/src/osnoise.c @@ -810,7 +810,7 @@ struct osnoise_tool *osnoise_init_trace_tool(char *tracer) retval = enable_tracer_by_name(trace->trace.inst, tracer); if (retval) { - err_msg("Could not enable osnoiser tracer for tracing\n"); + err_msg("Could not enable %s tracer for tracing\n", tracer); goto out_err; } diff --git a/tools/tracing/rtla/src/osnoise_hist.c b/tools/tracing/rtla/src/osnoise_hist.c index 1f0b7fce55cf..52c053cc1789 100644 --- a/tools/tracing/rtla/src/osnoise_hist.c +++ b/tools/tracing/rtla/src/osnoise_hist.c @@ -426,7 +426,7 @@ static void osnoise_hist_usage(char *usage) static const char * const msg[] = { "", " usage: rtla osnoise hist [-h] [-D] [-d s] [-p us] [-r us] [-s us] [-S us] [-t[=file]] \\", - " [-c cpu-list] [-P priority] [-b N] [-e N] [--no-header] [--no-summary] \\", + " [-c cpu-list] [-P priority] [-b N] [-E N] [--no-header] [--no-summary] \\", " [--no-index] [--with-zeros]", "", " -h/--help: print this menu", @@ -439,7 +439,7 @@ static void osnoise_hist_usage(char *usage) " -D/--debug: print debug info", " -t/--trace[=file]: save the stopped trace to [file|osnoise_trace.txt]", " -b/--bucket-size N: set the histogram bucket size (default 1)", - " -e/--entries N: set the number of entries of the histogram (default 256)", + " -E/--entries N: set the number of entries of the histogram (default 256)", " --no-header: do not print header", " --no-summary: do not print summary", " --no-index: do not print index", @@ -486,7 +486,7 @@ static struct osnoise_hist_params while (1) { static struct option long_options[] = { {"bucket-size", required_argument, 0, 'b'}, - {"entries", required_argument, 0, 'e'}, + {"entries", required_argument, 0, 'E'}, {"cpus", required_argument, 0, 'c'}, {"debug", no_argument, 0, 'D'}, {"duration", required_argument, 0, 'd'}, @@ -507,7 +507,7 @@ static struct osnoise_hist_params /* getopt_long stores the option index here. */ int option_index = 0; - c = getopt_long(argc, argv, "c:b:d:e:Dhp:P:r:s:S:t::0123", + c = getopt_long(argc, argv, "c:b:d:E:Dhp:P:r:s:S:t::0123", long_options, &option_index); /* detect the end of the options. */ @@ -534,7 +534,7 @@ static struct osnoise_hist_params if (!params->duration) osnoise_hist_usage("Invalid -D duration\n"); break; - case 'e': + case 'E': params->entries = get_llong_from_str(optarg); if ((params->entries < 10) || (params->entries > 9999999)) osnoise_hist_usage("Entries must be > 10 and < 9999999\n"); diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c index c67dc28ef716..7af769b9c0de 100644 --- a/tools/tracing/rtla/src/osnoise_top.c +++ b/tools/tracing/rtla/src/osnoise_top.c @@ -573,6 +573,7 @@ out_top: osnoise_free_top(tool->data); osnoise_destroy_tool(record); osnoise_destroy_tool(tool); + free(params); out_exit: exit(return_value); } diff --git a/tools/tracing/rtla/src/timerlat_hist.c b/tools/tracing/rtla/src/timerlat_hist.c index 436a799f9adf..237e1735afa7 100644 --- a/tools/tracing/rtla/src/timerlat_hist.c +++ b/tools/tracing/rtla/src/timerlat_hist.c @@ -429,7 +429,7 @@ static void timerlat_hist_usage(char *usage) char *msg[] = { "", " usage: [rtla] timerlat hist [-h] [-q] [-d s] [-D] [-n] [-p us] [-i us] [-T us] [-s us] [-t[=file]] \\", - " [-c cpu-list] [-P priority] [-e N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\", + " [-c cpu-list] [-P priority] [-E N] [-b N] [--no-irq] [--no-thread] [--no-header] [--no-summary] \\", " [--no-index] [--with-zeros]", "", " -h/--help: print this menu", @@ -443,7 +443,7 @@ static void timerlat_hist_usage(char *usage) " -T/--trace[=file]: save the stopped trace to [file|timerlat_trace.txt]", " -n/--nano: display data in nanoseconds", " -b/--bucket-size N: set the histogram bucket size (default 1)", - " -e/--entries N: set the number of entries of the histogram (default 256)", + " -E/--entries N: set the number of entries of the histogram (default 256)", " --no-irq: ignore IRQ latencies", " --no-thread: ignore thread latencies", " --no-header: do not print header", @@ -494,7 +494,7 @@ static struct timerlat_hist_params {"cpus", required_argument, 0, 'c'}, {"bucket-size", required_argument, 0, 'b'}, {"debug", no_argument, 0, 'D'}, - {"entries", required_argument, 0, 'e'}, + {"entries", required_argument, 0, 'E'}, {"duration", required_argument, 0, 'd'}, {"help", no_argument, 0, 'h'}, {"irq", required_argument, 0, 'i'}, @@ -516,7 +516,7 @@ static struct timerlat_hist_params /* getopt_long stores the option index here. */ int option_index = 0; - c = getopt_long(argc, argv, "c:b:d:e:Dhi:np:P:s:t::T:012345", + c = getopt_long(argc, argv, "c:b:d:E:Dhi:np:P:s:t::T:012345", long_options, &option_index); /* detect the end of the options. */ @@ -543,7 +543,7 @@ static struct timerlat_hist_params if (!params->duration) timerlat_hist_usage("Invalid -D duration\n"); break; - case 'e': + case 'E': params->entries = get_llong_from_str(optarg); if ((params->entries < 10) || (params->entries > 9999999)) timerlat_hist_usage("Entries must be > 10 and < 9999999\n"); 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); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 58d31da8a2f7..0afc016cc54d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5528,9 +5528,7 @@ static int kvm_suspend(void) static void kvm_resume(void) { if (kvm_usage_count) { -#ifdef CONFIG_LOCKDEP - WARN_ON(lockdep_is_held(&kvm_count_lock)); -#endif + lockdep_assert_not_held(&kvm_count_lock); hardware_enable_nolock(NULL); } } |