diff options
1338 files changed, 16752 insertions, 10534 deletions
@@ -130,6 +130,7 @@ Domen Puncer <domen@coderock.org> Douglas Gilbert <dougg@torque.net> Ed L. Cashin <ecashin@coraid.com> Erik Kaneda <erik.kaneda@intel.com> <erik.schmauss@intel.com> +Eugen Hristev <eugen.hristev@collabora.com> <eugen.hristev@microchip.com> Evgeniy Polyakov <johnpol@2ka.mipt.ru> Ezequiel Garcia <ezequiel@vanguardiasur.com.ar> <ezequiel@collabora.com> Felipe W Damasio <felipewd@terra.com.br> @@ -214,6 +215,7 @@ 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 Crispin <john@phrozen.org> <blogic@openwrt.org> John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org> @@ -371,6 +373,7 @@ 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> +Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org> 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> @@ -422,6 +425,7 @@ Tony Luck <tony.luck@intel.com> TripleX Chung <xxx.phy@gmail.com> <triplex@zh-kernel.org> TripleX Chung <xxx.phy@gmail.com> <zhongyu@18mail.cn> Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com> +Tudor Ambarus <tudor.ambarus@linaro.org> <tudor.ambarus@microchip.com> Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws> Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com> Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de> @@ -1173,6 +1173,10 @@ D: Future Domain TMC-16x0 SCSI driver (author) D: APM driver (early port) D: DRM drivers (author of several) +N: Veaceslav Falico +E: vfalico@gmail.com +D: Co-maintainer and co-author of the network bonding driver. + N: János Farkas E: chexum@shadow.banki.hu D: romfs, various (mostly networking) fixes @@ -2489,6 +2493,13 @@ D: XF86_Mach8 D: XF86_8514 D: cfdisk (curses based disk partitioning program) +N: Mat Martineau +E: mat@martineau.name +D: MPTCP subsystem co-maintainer 2020-2023 +D: Keyctl restricted keyring and Diffie-Hellman UAPI +D: Bluetooth L2CAP ERTM mode and AMP +S: USA + N: John S. Marvin E: jsm@fc.hp.com D: PA-RISC port @@ -4172,6 +4183,10 @@ S: B-1206 Jingmao Guojigongyu S: 16 Baliqiao Nanjie, Beijing 101100 S: People's Repulic of China +N: Vlad Yasevich +E: vyasevich@gmail.com +D: SCTP protocol maintainer. + N: Aviad Yehezkel E: aviadye@nvidia.com D: Kernel TLS implementation and offload support. diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index c8ae7c897f14..74cec76be9f2 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1245,13 +1245,17 @@ PAGE_SIZE multiple when read back. This is a simple interface to trigger memory reclaim in the target cgroup. - This file accepts a string which contains the number of bytes to - reclaim. + This file accepts a single key, the number of bytes to reclaim. + No nested keys are currently supported. Example:: echo "1G" > memory.reclaim + The interface can be later extended with nested keys to + configure the reclaim behavior. For example, specify the + type of memory to reclaim from (anon, file, ..). + Please note that the kernel can over or under reclaim from the target cgroup. If less bytes are reclaimed than the specified amount, -EAGAIN is returned. @@ -1263,13 +1267,6 @@ PAGE_SIZE multiple when read back. This means that the networking layer will not adapt based on reclaim induced by memory.reclaim. - This file also allows the user to specify the nodes to reclaim from, - via the 'nodes=' key, for example:: - - echo "1G nodes=0,1" > memory.reclaim - - The above instructs the kernel to reclaim memory from nodes 0,1. - memory.peak A read-only single value file which exists on non-root cgroups. diff --git a/Documentation/admin-guide/mm/zswap.rst b/Documentation/admin-guide/mm/zswap.rst index f67de481c7f6..6dd74a18268b 100644 --- a/Documentation/admin-guide/mm/zswap.rst +++ b/Documentation/admin-guide/mm/zswap.rst @@ -70,9 +70,7 @@ e.g. ``zswap.zpool=zbud``. It can also be changed at runtime using the sysfs The zbud type zpool allocates exactly 1 page to store 2 compressed pages, which means the compression ratio will always be 2:1 or worse (because of half-full zbud pages). The zsmalloc type zpool has a more complex compressed page -storage method, and it can achieve greater storage densities. However, -zsmalloc does not implement compressed page eviction, so once zswap fills it -cannot evict the oldest page, it can only reject new pages. +storage method, and it can achieve greater storage densities. When a swap page is passed from frontswap to zswap, zswap maintains a mapping of the swap entry, a combination of the swap type and swap offset, to the zpool diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 808ade4cc008..ec5f889d7681 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -120,6 +120,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A715 | #2645198 | ARM64_ERRATUM_2645198 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X2 | #2119858 | ARM64_ERRATUM_2119858 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X2 | #2224489 | ARM64_ERRATUM_2224489 | diff --git a/Documentation/conf.py b/Documentation/conf.py index a5c45df0bd83..d927737e3c10 100644 --- a/Documentation/conf.py +++ b/Documentation/conf.py @@ -31,6 +31,12 @@ def have_command(cmd): # Get Sphinx version major, minor, patch = sphinx.version_info[:3] +# +# Warn about older versions that we don't want to support for much +# longer. +# +if (major < 2) or (major == 2 and minor < 4): + print('WARNING: support for Sphinx < 2.4 will be removed soon.') # If extensions (or modules to document with autodoc) are in another directory, # add these directories to sys.path here. If the directory is relative to the @@ -339,7 +345,11 @@ html_use_smartypants = False # Custom sidebar templates, maps document names to template names. # Note that the RTD theme ignores this -html_sidebars = { '**': ["about.html", 'searchbox.html', 'localtoc.html', 'sourcelink.html']} +html_sidebars = { '**': ['searchbox.html', 'localtoc.html', 'sourcelink.html']} + +# about.html is available for alabaster theme. Add it at the front. +if html_theme == 'alabaster': + html_sidebars['**'].insert(0, 'about.html') # Output file base name for HTML help builder. htmlhelp_basename = 'TheLinuxKerneldoc' diff --git a/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml b/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml index 903b31129f01..99e159bc5fb1 100644 --- a/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml +++ b/Documentation/devicetree/bindings/cpufreq/cpufreq-qcom-hw.yaml @@ -54,6 +54,17 @@ properties: - const: xo - const: alternate + interrupts: + minItems: 1 + maxItems: 3 + + interrupt-names: + minItems: 1 + items: + - const: dcvsh-irq-0 + - const: dcvsh-irq-1 + - const: dcvsh-irq-2 + '#freq-domain-cells': const: 1 diff --git a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml index 0ccaab16dc61..0b7383b3106b 100644 --- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml +++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-aes.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel Advanced Encryption Standard (AES) HW cryptographic accelerator maintainers: - - Tudor Ambarus <tudor.ambarus@microchip.com> + - Tudor Ambarus <tudor.ambarus@linaro.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml index 5163c51b4547..ee2ffb034325 100644 --- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml +++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-sha.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel Secure Hash Algorithm (SHA) HW cryptographic accelerator maintainers: - - Tudor Ambarus <tudor.ambarus@microchip.com> + - Tudor Ambarus <tudor.ambarus@linaro.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml index fcc5adf03cad..3d6ed24b1b00 100644 --- a/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml +++ b/Documentation/devicetree/bindings/crypto/atmel,at91sam9g46-tdes.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel Triple Data Encryption Standard (TDES) HW cryptographic accelerator maintainers: - - Tudor Ambarus <tudor.ambarus@microchip.com> + - Tudor Ambarus <tudor.ambarus@linaro.org> properties: compatible: diff --git a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml index f2c143730a55..6e2fd6e9fa7f 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-controller-main.yaml @@ -32,7 +32,7 @@ properties: - description: Display byte clock - description: Display byte interface clock - description: Display pixel clock - - description: Display escape clock + - description: Display core clock - description: Display AHB clock - description: Display AXI clock @@ -137,8 +137,6 @@ required: - phys - assigned-clocks - assigned-clock-parents - - power-domains - - operating-points-v2 - ports additionalProperties: false diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml index d9ad8b659f58..3ec466c3ab38 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-10nm.yaml @@ -69,7 +69,6 @@ required: - compatible - reg - reg-names - - vdds-supply unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml index 819de5ce0bc9..a43e11d3b00d 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-14nm.yaml @@ -39,7 +39,6 @@ required: - compatible - reg - reg-names - - vcca-supply unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml index 3d8540a06fe2..2f1fd140c87d 100644 --- a/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml +++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-28nm.yaml @@ -34,6 +34,10 @@ properties: vddio-supply: description: Phandle to vdd-io regulator device node. + qcom,dsi-phy-regulator-ldo-mode: + type: boolean + description: Indicates if the LDO mode PHY regulator is wanted. + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml index d6f043a4b08d..4795e13c7b59 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,qcm2290-mdss.yaml @@ -72,7 +72,7 @@ examples: #include <dt-bindings/interconnect/qcom,qcm2290.h> #include <dt-bindings/power/qcom-rpmpd.h> - mdss@5e00000 { + display-subsystem@5e00000 { #address-cells = <1>; #size-cells = <1>; compatible = "qcom,qcm2290-mdss"; diff --git a/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml b/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml index a86d7f53fa84..886858ef6700 100644 --- a/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml +++ b/Documentation/devicetree/bindings/display/msm/qcom,sm6115-mdss.yaml @@ -62,7 +62,7 @@ examples: #include <dt-bindings/interrupt-controller/arm-gic.h> #include <dt-bindings/power/qcom-rpmpd.h> - mdss@5e00000 { + display-subsystem@5e00000 { #address-cells = <1>; #size-cells = <1>; compatible = "qcom,sm6115-mdss"; diff --git a/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml b/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml index c46378efc123..92e899905ef8 100644 --- a/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml +++ b/Documentation/devicetree/bindings/i2c/renesas,rzv2m.yaml @@ -16,7 +16,7 @@ properties: compatible: items: - enum: - - renesas,i2c-r9a09g011 # RZ/V2M + - renesas,r9a09g011-i2c # RZ/V2M - const: renesas,rzv2m-i2c reg: @@ -66,7 +66,7 @@ examples: #include <dt-bindings/interrupt-controller/arm-gic.h> i2c0: i2c@a4030000 { - compatible = "renesas,i2c-r9a09g011", "renesas,rzv2m-i2c"; + compatible = "renesas,r9a09g011-i2c", "renesas,rzv2m-i2c"; reg = <0xa4030000 0x80>; interrupts = <GIC_SPI 232 IRQ_TYPE_EDGE_RISING>, <GIC_SPI 236 IRQ_TYPE_EDGE_RISING>; diff --git a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml index 4b37aa88a375..5e6be4e79201 100644 --- a/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml +++ b/Documentation/devicetree/bindings/interconnect/qcom,rpm.yaml @@ -84,7 +84,6 @@ allOf: - qcom,msm8939-pcnoc - qcom,msm8939-snoc - qcom,msm8996-a1noc - - qcom,msm8996-a2noc - qcom,msm8996-bimc - qcom,msm8996-cnoc - qcom,msm8996-pnoc @@ -191,6 +190,29 @@ allOf: compatible: contains: enum: + - qcom,msm8996-a2noc + + then: + properties: + clock-names: + items: + - const: bus + - const: bus_a + - const: aggre2_ufs_axi + - const: ufs_axi + + clocks: + items: + - description: Bus Clock + - description: Bus A Clock + - description: Aggregate2 NoC UFS AXI Clock + - description: UFS AXI Clock + + - if: + properties: + compatible: + contains: + enum: - qcom,sdm660-a2noc then: diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml index f3a5fbabbbb5..bb01c6b34dab 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb2-phy.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb2-phy.yaml @@ -2,7 +2,7 @@ # Copyright 2019 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,meson-g12a-usb2-phy.yaml#" +$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb2-phy.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Amlogic G12A USB2 PHY @@ -13,8 +13,8 @@ maintainers: properties: compatible: enum: - - amlogic,meson-g12a-usb2-phy - - amlogic,meson-a1-usb2-phy + - amlogic,g12a-usb2-phy + - amlogic,a1-usb2-phy reg: maxItems: 1 @@ -68,7 +68,7 @@ additionalProperties: false examples: - | phy@36000 { - compatible = "amlogic,meson-g12a-usb2-phy"; + compatible = "amlogic,g12a-usb2-phy"; reg = <0x36000 0x2000>; clocks = <&xtal>; clock-names = "xtal"; diff --git a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml index 868b4e6fde71..129d26e99776 100644 --- a/Documentation/devicetree/bindings/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/amlogic,g12a-usb3-pcie-phy.yaml @@ -2,7 +2,7 @@ # Copyright 2019 BayLibre, SAS %YAML 1.2 --- -$id: "http://devicetree.org/schemas/phy/amlogic,meson-g12a-usb3-pcie-phy.yaml#" +$id: "http://devicetree.org/schemas/phy/amlogic,g12a-usb3-pcie-phy.yaml#" $schema: "http://devicetree.org/meta-schemas/core.yaml#" title: Amlogic G12A USB3 + PCIE Combo PHY @@ -13,7 +13,7 @@ maintainers: properties: compatible: enum: - - amlogic,meson-g12a-usb3-pcie-phy + - amlogic,g12a-usb3-pcie-phy reg: maxItems: 1 @@ -49,7 +49,7 @@ additionalProperties: false examples: - | phy@46000 { - compatible = "amlogic,meson-g12a-usb3-pcie-phy"; + compatible = "amlogic,g12a-usb3-pcie-phy"; reg = <0x46000 0x2000>; clocks = <&ref_clk>; clock-names = "ref_clk"; diff --git a/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml b/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml index abcc4373f39e..ca6a0836b53c 100644 --- a/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,usb-hs-28nm.yaml @@ -16,7 +16,6 @@ properties: compatible: enum: - qcom,usb-hs-28nm-femtophy - - qcom,usb-hs-28nm-mdm9607 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml index 01f9d4e236e9..a7feb497eb89 100644 --- a/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml +++ b/Documentation/devicetree/bindings/regulator/samsung,s2mps14.yaml @@ -19,8 +19,8 @@ description: | additional information and example. patternProperties: - # 25 LDOs - "^LDO([1-9]|[1][0-9]|2[0-5])$": + # 25 LDOs, without LDO10-12 + "^LDO([1-9]|1[3-9]|2[0-5])$": type: object $ref: regulator.yaml# unevaluatedProperties: false @@ -30,6 +30,23 @@ patternProperties: required: - regulator-name + "^LDO(1[0-2])$": + type: object + $ref: regulator.yaml# + unevaluatedProperties: false + description: + Properties for single LDO regulator. + + properties: + samsung,ext-control-gpios: + maxItems: 1 + description: + LDO10, LDO11 and LDO12 can be configured to external control over + GPIO. + + required: + - regulator-name + # 5 bucks "^BUCK[1-5]$": type: object diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index c6720764e765..a2884e3113da 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -83,7 +83,7 @@ properties: insensitive, letters in the riscv,isa string must be all lowercase to simplify parsing. $ref: "/schemas/types.yaml#/definitions/string" - pattern: ^rv(?:64|32)imaf?d?q?c?b?v?k?h?(?:_[hsxz](?:[a-z])+)*$ + pattern: ^rv(?:64|32)imaf?d?q?c?b?k?j?p?v?h?(?:[hsxz](?:[a-z])+)?(?:_[hsxz](?:[a-z])+)*$ # RISC-V requires 'timebase-frequency' in /cpus, so disallow it here timebase-frequency: false diff --git a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml index 0a7aa29563c1..21c8ea08ff0a 100644 --- a/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml +++ b/Documentation/devicetree/bindings/rtc/qcom-pm8xxx-rtc.yaml @@ -40,6 +40,8 @@ properties: description: Indicates that the setting of RTC time is allowed by the host CPU. + wakeup-source: true + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,apr-services.yaml b/Documentation/devicetree/bindings/soc/qcom/qcom,apr-services.yaml index 290555426c39..bdf482db32aa 100644 --- a/Documentation/devicetree/bindings/soc/qcom/qcom,apr-services.yaml +++ b/Documentation/devicetree/bindings/soc/qcom/qcom,apr-services.yaml @@ -39,8 +39,8 @@ properties: qcom,protection-domain: $ref: /schemas/types.yaml#/definitions/string-array description: | - Protection domain service name and path for APR service - possible values are:: + Protection domain service name and path for APR service (if supported). + Possible values are:: "avs/audio", "msm/adsp/audio_pd". "kernel/elf_loader", "msm/modem/wlan_pd". "tms/servreg", "msm/adsp/audio_pd". @@ -49,6 +49,5 @@ properties: required: - reg - - qcom,protection-domain additionalProperties: true diff --git a/Documentation/devicetree/bindings/sound/everest,es8326.yaml b/Documentation/devicetree/bindings/sound/everest,es8326.yaml index 07781408e788..07781408e788 100755..100644 --- a/Documentation/devicetree/bindings/sound/everest,es8326.yaml +++ b/Documentation/devicetree/bindings/sound/everest,es8326.yaml diff --git a/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml b/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml index 9d3139990237..aa23b0024c46 100644 --- a/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml +++ b/Documentation/devicetree/bindings/sound/mt8186-mt6366-rt1019-rt5682s.yaml @@ -16,6 +16,7 @@ properties: compatible: enum: - mediatek,mt8186-mt6366-rt1019-rt5682s-sound + - mediatek,mt8186-mt6366-rt5682s-max98360-sound mediatek,platform: $ref: "/schemas/types.yaml#/definitions/phandle" diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml index 66431aade3b7..da5f70910da5 100644 --- a/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,lpass-tx-macro.yaml @@ -30,7 +30,9 @@ properties: const: 0 clocks: - maxItems: 5 + oneOf: + - maxItems: 3 + - maxItems: 5 clock-names: oneOf: diff --git a/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml b/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml index 2bf8d082f8f1..66cbb1f5e31a 100644 --- a/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml +++ b/Documentation/devicetree/bindings/sound/qcom,lpass-wsa-macro.yaml @@ -9,9 +9,6 @@ title: LPASS(Low Power Audio Subsystem) VA Macro audio codec maintainers: - Srinivas Kandagatla <srinivas.kandagatla@linaro.org> -allOf: - - $ref: dai-common.yaml# - properties: compatible: enum: @@ -30,15 +27,12 @@ properties: const: 0 clocks: - maxItems: 5 + minItems: 5 + maxItems: 6 clock-names: - items: - - const: mclk - - const: npl - - const: macro - - const: dcodec - - const: fsgen + minItems: 5 + maxItems: 6 clock-output-names: maxItems: 1 @@ -55,10 +49,51 @@ required: - reg - "#sound-dai-cells" +allOf: + - $ref: dai-common.yaml# + + - if: + properties: + compatible: + enum: + - qcom,sc7280-lpass-wsa-macro + - qcom,sm8450-lpass-wsa-macro + - qcom,sc8280xp-lpass-wsa-macro + then: + properties: + clocks: + maxItems: 5 + clock-names: + items: + - const: mclk + - const: npl + - const: macro + - const: dcodec + - const: fsgen + + - if: + properties: + compatible: + enum: + - qcom,sm8250-lpass-wsa-macro + then: + properties: + clocks: + minItems: 6 + clock-names: + items: + - const: mclk + - const: npl + - const: macro + - const: dcodec + - const: va + - const: fsgen + unevaluatedProperties: false examples: - | + #include <dt-bindings/clock/qcom,sm8250-lpass-aoncc.h> #include <dt-bindings/sound/qcom,q6afe.h> codec@3240000 { compatible = "qcom,sm8250-lpass-wsa-macro"; @@ -69,7 +104,8 @@ examples: <&audiocc 0>, <&q6afecc LPASS_HW_MACRO_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>, <&q6afecc LPASS_HW_DCODEC_VOTE LPASS_CLK_ATTRIBUTE_COUPLE_NO>, + <&aoncc LPASS_CDC_VA_MCLK>, <&vamacro>; - clock-names = "mclk", "npl", "macro", "dcodec", "fsgen"; + clock-names = "mclk", "npl", "macro", "dcodec", "va", "fsgen"; clock-output-names = "mclk"; }; diff --git a/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml b/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml index 4dd973e341e6..6c57dd6c3a36 100644 --- a/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml +++ b/Documentation/devicetree/bindings/spi/atmel,at91rm9200-spi.yaml @@ -8,7 +8,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel SPI device maintainers: - - Tudor Ambarus <tudor.ambarus@microchip.com> + - Tudor Ambarus <tudor.ambarus@linaro.org> allOf: - $ref: spi-controller.yaml# diff --git a/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml b/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml index 1d493add4053..b0d99bc10535 100644 --- a/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml +++ b/Documentation/devicetree/bindings/spi/atmel,quadspi.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Atmel Quad Serial Peripheral Interface (QSPI) maintainers: - - Tudor Ambarus <tudor.ambarus@microchip.com> + - Tudor Ambarus <tudor.ambarus@linaro.org> allOf: - $ref: spi-controller.yaml# diff --git a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml index ead2cccf658f..9a60c0664bbe 100644 --- a/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml +++ b/Documentation/devicetree/bindings/spi/spi-peripheral-props.yaml @@ -44,9 +44,9 @@ properties: description: Maximum SPI clocking speed of the device in Hz. - spi-cs-setup-ns: + spi-cs-setup-delay-ns: description: - Delay in nanosecods to be introduced by the controller after CS is + Delay in nanoseconds to be introduced by the controller after CS is asserted. spi-rx-bus-width: diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst index 067fd1670b1f..a43aacf1494e 100644 --- a/Documentation/filesystems/erofs.rst +++ b/Documentation/filesystems/erofs.rst @@ -120,6 +120,8 @@ dax={always,never} Use direct access (no page cache). See dax A legacy option which is an alias for ``dax=always``. device=%s Specify a path to an extra device to be used together. fsid=%s Specify a filesystem image ID for Fscache back-end. +domain_id=%s Specify a domain ID in fscache mode so that different images + with the same blobs under a given domain ID can share storage. =================== ========================================================= Sysfs Entries diff --git a/Documentation/kbuild/makefiles.rst b/Documentation/kbuild/makefiles.rst index 6b7368d1f516..38bc74eaa547 100644 --- a/Documentation/kbuild/makefiles.rst +++ b/Documentation/kbuild/makefiles.rst @@ -1042,7 +1042,7 @@ $(clean-files). When executing "make clean", the file "crc32table.h" will be deleted. Kbuild will assume files to be in the same relative directory as the -Makefile, except if prefixed with $(objtree). +Makefile. To exclude certain files or directories from make clean, use the $(no-clean-files) variable. diff --git a/Documentation/networking/bridge.rst b/Documentation/networking/bridge.rst index 4aef9cddde2f..c859f3c1636e 100644 --- a/Documentation/networking/bridge.rst +++ b/Documentation/networking/bridge.rst @@ -8,7 +8,7 @@ In order to use the Ethernet bridging functionality, you'll need the userspace tools. Documentation for Linux bridging is on: - http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge + https://wiki.linuxfoundation.org/networking/bridge The bridge-utilities are maintained at: git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/bridge-utils.git diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst index dc2e60ced927..b481b81f3be5 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst @@ -819,7 +819,7 @@ NAPI ---- This driver supports NAPI (Rx polling mode). For more information on NAPI, see -https://www.linuxfoundation.org/collaborate/workgroups/networking/napi +https://wiki.linuxfoundation.org/networking/napi MACVLAN diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst index 49db1d11d7c4..8b1045c3b59e 100644 --- a/Documentation/networking/nf_conntrack-sysctl.rst +++ b/Documentation/networking/nf_conntrack-sysctl.rst @@ -173,7 +173,9 @@ nf_conntrack_sctp_timeout_cookie_echoed - INTEGER (seconds) default 3 nf_conntrack_sctp_timeout_established - INTEGER (seconds) - default 432000 (5 days) + default 210 + + Default is set to (hb_interval * path_max_retrans + rto_max) nf_conntrack_sctp_timeout_shutdown_sent - INTEGER (seconds) default 0.3 @@ -190,12 +192,6 @@ nf_conntrack_sctp_timeout_heartbeat_sent - INTEGER (seconds) This timeout is used to setup conntrack entry on secondary paths. Default is set to hb_interval. -nf_conntrack_sctp_timeout_heartbeat_acked - INTEGER (seconds) - default 210 - - This timeout is used to setup conntrack entry on secondary paths. - Default is set to (hb_interval * path_max_retrans + rto_max) - nf_conntrack_udp_timeout - INTEGER (seconds) default 30 diff --git a/Documentation/networking/rxrpc.rst b/Documentation/networking/rxrpc.rst index 39494a6ea739..e1af54424192 100644 --- a/Documentation/networking/rxrpc.rst +++ b/Documentation/networking/rxrpc.rst @@ -880,8 +880,8 @@ The kernel interface functions are as follows: notify_end_rx can be NULL or it can be used to specify a function to be called when the call changes state to end the Tx phase. This function is - called with the call-state spinlock held to prevent any reply or final ACK - from being delivered first. + called with a spinlock held to prevent the last DATA packet from being + transmitted until the function returns. (#) Receive data from a call:: diff --git a/Documentation/sphinx/load_config.py b/Documentation/sphinx/load_config.py index eeb394b39e2c..8b416bfd75ac 100644 --- a/Documentation/sphinx/load_config.py +++ b/Documentation/sphinx/load_config.py @@ -3,7 +3,7 @@ import os import sys -from sphinx.util.pycompat import execfile_ +from sphinx.util.osutil import fs_encoding # ------------------------------------------------------------------------------ def loadConfig(namespace): @@ -48,7 +48,9 @@ def loadConfig(namespace): sys.stdout.write("load additional sphinx-config: %s\n" % config_file) config = namespace.copy() config['__file__'] = config_file - execfile_(config_file, config) + with open(config_file, 'rb') as f: + code = compile(f.read(), fs_encoding, 'exec') + exec(code, config) del config['__file__'] namespace.update(config) else: diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index a4c9dbccc7c2..62de0768d6aa 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1354,6 +1354,14 @@ the memory region are automatically reflected into the guest. For example, an mmap() that affects the region will be made visible immediately. Another example is madvise(MADV_DROP). +Note: On arm64, a write generated by the page-table walker (to update +the Access and Dirty flags, for example) never results in a +KVM_EXIT_MMIO exit when the slot has the KVM_MEM_READONLY flag. This +is because KVM cannot provide the data that would be written by the +page-table walker, making it impossible to emulate the access. +Instead, an abort (data abort if the cause of the page-table update +was a load or a store, instruction abort if it was an instruction +fetch) is injected in the guest. 4.36 KVM_SET_TSS_ADDR --------------------- @@ -5025,6 +5033,15 @@ using this ioctl. :Parameters: struct kvm_pmu_event_filter (in) :Returns: 0 on success, -1 on error +Errors: + + ====== ============================================================ + EFAULT args[0] cannot be accessed + EINVAL args[0] contains invalid data in the filter or filter events + E2BIG nevents is too large + EBUSY not enough memory to allocate the filter + ====== ============================================================ + :: struct kvm_pmu_event_filter { @@ -5036,14 +5053,69 @@ using this ioctl. __u64 events[0]; }; -This ioctl restricts the set of PMU events that the guest can program. -The argument holds a list of events which will be allowed or denied. -The eventsel+umask of each event the guest attempts to program is compared -against the events field to determine whether the guest should have access. -The events field only controls general purpose counters; fixed purpose -counters are controlled by the fixed_counter_bitmap. +This ioctl restricts the set of PMU events the guest can program by limiting +which event select and unit mask combinations are permitted. + +The argument holds a list of filter events which will be allowed or denied. + +Filter events only control general purpose counters; fixed purpose counters +are controlled by the fixed_counter_bitmap. + +Valid values for 'flags':: + +``0`` + +To use this mode, clear the 'flags' field. + +In this mode each event will contain an event select + unit mask. -No flags are defined yet, the field must be zero. +When the guest attempts to program the PMU the guest's event select + +unit mask is compared against the filter events to determine whether the +guest should have access. + +``KVM_PMU_EVENT_FLAG_MASKED_EVENTS`` +:Capability: KVM_CAP_PMU_EVENT_MASKED_EVENTS + +In this mode each filter event will contain an event select, mask, match, and +exclude value. To encode a masked event use:: + + KVM_PMU_ENCODE_MASKED_ENTRY() + +An encoded event will follow this layout:: + + Bits Description + ---- ----------- + 7:0 event select (low bits) + 15:8 umask match + 31:16 unused + 35:32 event select (high bits) + 36:54 unused + 55 exclude bit + 63:56 umask mask + +When the guest attempts to program the PMU, these steps are followed in +determining if the guest should have access: + + 1. Match the event select from the guest against the filter events. + 2. If a match is found, match the guest's unit mask to the mask and match + values of the included filter events. + I.e. (unit mask & mask) == match && !exclude. + 3. If a match is found, match the guest's unit mask to the mask and match + values of the excluded filter events. + I.e. (unit mask & mask) == match && exclude. + 4. + a. If an included match is found and an excluded match is not found, filter + the event. + b. For everything else, do not filter the event. + 5. + a. If the event is filtered and it's an allow list, allow the guest to + program the event. + b. If the event is filtered and it's a deny list, do not allow the guest to + program the event. + +When setting a new pmu event filter, -EINVAL will be returned if any of the +unused fields are set or if any of the high bits (35:32) in the event +select are set when called on Intel. Valid values for 'action':: @@ -8090,9 +8162,13 @@ considering the state as complete. VMM needs to ensure that the dirty state is final and avoid missing dirty pages from another ioctl ordered after the bitmap collection. -NOTE: One example of using the backup bitmap is saving arm64 vgic/its -tables through KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} command on -KVM device "kvm-arm-vgic-its" when dirty ring is enabled. +NOTE: Multiple examples of using the backup bitmap: (1) save vgic/its +tables through command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} on +KVM device "kvm-arm-vgic-its". (2) restore vgic/its tables through +command KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_RESTORE_TABLES} on KVM device +"kvm-arm-vgic-its". VGICv3 LPI pending status is restored. (3) save +vgic3 pending table through KVM_DEV_ARM_VGIC_{GRP_CTRL, SAVE_PENDING_TABLES} +command on KVM device "kvm-arm-vgic-v3". 8.30 KVM_CAP_XEN_HVM -------------------- @@ -8338,6 +8414,20 @@ CPU[EAX=1]:ECX[24] (TSC_DEADLINE) is not reported by ``KVM_GET_SUPPORTED_CPUID`` It can be enabled if ``KVM_CAP_TSC_DEADLINE_TIMER`` is present and the kernel has enabled in-kernel emulation of the local APIC. +CPU topology +~~~~~~~~~~~~ + +Several CPUID values include topology information for the host CPU: +0x0b and 0x1f for Intel systems, 0x8000001e for AMD systems. Different +versions of KVM return different values for this information and userspace +should not rely on it. Currently they return all zeroes. + +If userspace wishes to set up a guest topology, it should be careful that +the values of these three leaves differ for each CPU. In particular, +the APIC ID is found in EDX for all subleaves of 0x0b and 0x1f, and in EAX +for 0x8000001e; the latter also encodes the core id and node id in bits +7:0 of EBX and ECX respectively. + Obsolete ioctls and capabilities ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst index a3ca76f9be75..14c4e9fa501d 100644 --- a/Documentation/virt/kvm/locking.rst +++ b/Documentation/virt/kvm/locking.rst @@ -9,6 +9,8 @@ KVM Lock Overview The acquisition orders for mutexes are as follows: +- cpus_read_lock() is taken outside kvm_lock + - kvm->lock is taken outside vcpu->mutex - kvm->lock is taken outside kvm->slots_lock and kvm->irq_lock @@ -24,21 +26,22 @@ The acquisition orders for mutexes are as follows: For SRCU: -- ``synchronize_srcu(&kvm->srcu)`` is called _inside_ - the kvm->slots_lock critical section, therefore kvm->slots_lock - cannot be taken inside a kvm->srcu read-side critical section. - Instead, kvm->slots_arch_lock is released before the call - to ``synchronize_srcu()`` and _can_ be taken inside a - kvm->srcu read-side critical section. +- ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections + for kvm->lock, vcpu->mutex and kvm->slots_lock. These locks _cannot_ + be taken inside a kvm->srcu read-side critical section; that is, the + following is broken:: + + srcu_read_lock(&kvm->srcu); + mutex_lock(&kvm->slots_lock); -- kvm->lock is taken inside kvm->srcu, therefore - ``synchronize_srcu(&kvm->srcu)`` cannot be called inside - a kvm->lock critical section. If you cannot delay the - call until after kvm->lock is released, use ``call_srcu``. +- kvm->slots_arch_lock instead is released before the call to + ``synchronize_srcu()``. It _can_ therefore be taken inside a + kvm->srcu read-side critical section, for example while processing + a vmexit. On x86: -- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock +- vcpu->mutex is taken outside kvm->arch.hyperv.hv_lock and kvm->arch.xen.xen_lock - kvm->arch.mmu_lock is an rwlock. kvm->arch.tdp_mmu_pages_lock and kvm->arch.mmu_unsync_pages_lock are taken inside kvm->arch.mmu_lock, and @@ -225,15 +228,10 @@ time it will be set using the Dirty tracking mechanism described above. :Type: mutex :Arch: any :Protects: - vm_list - -``kvm_count_lock`` -^^^^^^^^^^^^^^^^^^ - -:Type: raw_spinlock_t -:Arch: any -:Protects: - hardware virtualization enable/disable -:Comment: 'raw' because hardware enabling/disabling must be atomic /wrt - migration. + - kvm_usage_count + - hardware virtualization enable/disable +:Comment: KVM also disables CPU hotplug via cpus_read_lock() during + enable/disable. ``kvm->mn_invalidate_lock`` ^^^^^^^^^^^^^^^^^^^^^^^^^^^ @@ -291,3 +289,13 @@ time it will be set using the Dirty tracking mechanism described above. wakeup notification event since external interrupts from the assigned devices happens, we will find the vCPU on the list to wakeup. + +``vendor_module_lock`` +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +:Type: mutex +:Arch: x86 +:Protects: loading a vendor module (kvm_amd or kvm_intel) +:Comment: Exists because using kvm_lock leads to deadlock. cpu_hotplug_lock is + taken outside of kvm_lock, e.g. in KVM's CPU online/offline callbacks, and + many operations need to take cpu_hotplug_lock when loading a vendor module, + e.g. updating static calls. diff --git a/Documentation/virt/kvm/x86/errata.rst b/Documentation/virt/kvm/x86/errata.rst index 410e0aa63493..49a05f24747b 100644 --- a/Documentation/virt/kvm/x86/errata.rst +++ b/Documentation/virt/kvm/x86/errata.rst @@ -37,3 +37,14 @@ Nested virtualization features ------------------------------ TBD + +x2APIC +------ +When KVM_X2APIC_API_USE_32BIT_IDS is enabled, KVM activates a hack/quirk that +allows sending events to a single vCPU using its x2APIC ID even if the target +vCPU has legacy xAPIC enabled, e.g. to bring up hotplugged vCPUs via INIT-SIPI +on VMs with > 255 vCPUs. A side effect of the quirk is that, if multiple vCPUs +have the same physical APIC ID, KVM will deliver events targeting that APIC ID +only to the vCPU with the lowest vCPU ID. If KVM_X2APIC_API_USE_32BIT_IDS is +not enabled, KVM follows x86 architecture when processing interrupts (all vCPUs +matching the target APIC ID receive the interrupt). diff --git a/Documentation/x86/amd-memory-encryption.rst b/Documentation/x86/amd-memory-encryption.rst index a1940ebe7be5..934310ce7258 100644 --- a/Documentation/x86/amd-memory-encryption.rst +++ b/Documentation/x86/amd-memory-encryption.rst @@ -95,3 +95,39 @@ by supplying mem_encrypt=on on the kernel command line. However, if BIOS does not enable SME, then Linux will not be able to activate memory encryption, even if configured to do so by default or the mem_encrypt=on command line parameter is specified. + +Secure Nested Paging (SNP) +========================== + +SEV-SNP introduces new features (SEV_FEATURES[1:63]) which can be enabled +by the hypervisor for security enhancements. Some of these features need +guest side implementation to function correctly. The below table lists the +expected guest behavior with various possible scenarios of guest/hypervisor +SNP feature support. + ++-----------------+---------------+---------------+------------------+ +| Feature Enabled | Guest needs | Guest has | Guest boot | +| by the HV | implementation| implementation| behaviour | ++=================+===============+===============+==================+ +| No | No | No | Boot | +| | | | | ++-----------------+---------------+---------------+------------------+ +| No | Yes | No | Boot | +| | | | | ++-----------------+---------------+---------------+------------------+ +| No | Yes | Yes | Boot | +| | | | | ++-----------------+---------------+---------------+------------------+ +| Yes | No | No | Boot with | +| | | | feature enabled | ++-----------------+---------------+---------------+------------------+ +| Yes | Yes | No | Graceful boot | +| | | | failure | ++-----------------+---------------+---------------+------------------+ +| Yes | Yes | Yes | Boot with | +| | | | feature enabled | ++-----------------+---------------+---------------+------------------+ + +More details in AMD64 APM[1] Vol 2: 15.34.10 SEV_STATUS MSR + +[1] https://www.amd.com/system/files/TechDocs/40332.pdf diff --git a/MAINTAINERS b/MAINTAINERS index a36df9ed283d..fb1471cb5ed3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -383,7 +383,7 @@ ACPI COMPONENT ARCHITECTURE (ACPICA) M: Robert Moore <robert.moore@intel.com> M: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com> L: linux-acpi@vger.kernel.org -L: devel@acpica.org +L: acpica-devel@lists.linuxfoundation.org S: Supported W: https://acpica.org/ W: https://github.com/acpica/acpica/ @@ -1097,14 +1097,12 @@ S: Maintained F: drivers/dma/ptdma/ AMD SEATTLE DEVICE TREE SUPPORT -M: Brijesh Singh <brijeshkumar.singh@amd.com> M: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com> M: Tom Lendacky <thomas.lendacky@amd.com> S: Supported F: arch/arm64/boot/dts/amd/ AMD XGBE DRIVER -M: Tom Lendacky <thomas.lendacky@amd.com> M: "Shyam Sundar S K" <Shyam-sundar.S-k@amd.com> L: netdev@vger.kernel.org S: Supported @@ -2213,6 +2211,9 @@ L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git X: drivers/media/i2c/ +F: arch/arm64/boot/dts/freescale/ +X: arch/arm64/boot/dts/freescale/fsl-* +X: arch/arm64/boot/dts/freescale/qoriq-* N: imx N: mxs @@ -2451,11 +2452,14 @@ F: drivers/rtc/rtc-mt7622.c ARM/Mediatek SoC support M: Matthias Brugger <matthias.bgg@gmail.com> +R: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com> +L: linux-kernel@vger.kernel.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-mediatek@lists.infradead.org (moderated for non-subscribers) S: Maintained W: https://mtk.wiki.kernel.org/ -C: irc://chat.freenode.net/linux-mediatek +C: irc://irc.libera.chat/linux-mediatek +F: arch/arm/boot/dts/mt2* F: arch/arm/boot/dts/mt6* F: arch/arm/boot/dts/mt7* F: arch/arm/boot/dts/mt8* @@ -2463,7 +2467,7 @@ F: arch/arm/mach-mediatek/ F: arch/arm64/boot/dts/mediatek/ F: drivers/soc/mediatek/ N: mtk -N: mt[678] +N: mt[2678] K: mediatek ARM/Mediatek USB3 PHY DRIVER @@ -3767,7 +3771,6 @@ F: net/bluetooth/ BONDING DRIVER M: Jay Vosburgh <j.vosburgh@gmail.com> -M: Veaceslav Falico <vfalico@gmail.com> M: Andy Gospodarek <andy@greyhouse.net> L: netdev@vger.kernel.org S: Supported @@ -6948,7 +6951,7 @@ F: drivers/gpu/drm/atmel-hlcdc/ DRM DRIVERS FOR BRIDGE CHIPS M: Andrzej Hajda <andrzej.hajda@intel.com> M: Neil Armstrong <neil.armstrong@linaro.org> -M: Robert Foss <robert.foss@linaro.org> +M: Robert Foss <rfoss@kernel.org> R: Laurent Pinchart <Laurent.pinchart@ideasonboard.com> R: Jonas Karlman <jonas@kwiboo.se> R: Jernej Skrabec <jernej.skrabec@gmail.com> @@ -7616,7 +7619,6 @@ S: Maintained F: drivers/firmware/efi/test/ EFI VARIABLE FILESYSTEM -M: Matthew Garrett <matthew.garrett@nebula.com> M: Jeremy Kerr <jk@ozlabs.org> M: Ard Biesheuvel <ardb@kernel.org> L: linux-efi@vger.kernel.org @@ -7895,7 +7897,11 @@ F: include/linux/extcon/ EXTRA BOOT CONFIG M: Masami Hiramatsu <mhiramat@kernel.org> +L: linux-kernel@vger.kernel.org +L: linux-trace-kernel@vger.kernel.org +Q: https://patchwork.kernel.org/project/linux-trace-kernel/list/ S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git F: Documentation/admin-guide/bootconfig.rst F: fs/proc/bootconfig.c F: include/linux/bootconfig.h @@ -8468,16 +8474,16 @@ F: fs/fscache/ F: include/linux/fscache*.h FSCRYPT: FILE SYSTEM LEVEL ENCRYPTION SUPPORT +M: Eric Biggers <ebiggers@kernel.org> M: Theodore Y. Ts'o <tytso@mit.edu> M: Jaegeuk Kim <jaegeuk@kernel.org> -M: Eric Biggers <ebiggers@kernel.org> L: linux-fscrypt@vger.kernel.org S: Supported Q: https://patchwork.kernel.org/project/linux-fscrypt/list/ -T: git git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt.git +T: git https://git.kernel.org/pub/scm/fs/fscrypt/linux.git F: Documentation/filesystems/fscrypt.rst F: fs/crypto/ -F: include/linux/fscrypt*.h +F: include/linux/fscrypt.h F: include/uapi/linux/fscrypt.h FSI SUBSYSTEM @@ -8520,10 +8526,10 @@ F: include/linux/fsnotify*.h FSVERITY: READ-ONLY FILE-BASED AUTHENTICITY PROTECTION M: Eric Biggers <ebiggers@kernel.org> M: Theodore Y. Ts'o <tytso@mit.edu> -L: linux-fscrypt@vger.kernel.org +L: fsverity@lists.linux.dev S: Supported -Q: https://patchwork.kernel.org/project/linux-fscrypt/list/ -T: git git://git.kernel.org/pub/scm/fs/fscrypt/fscrypt.git fsverity +Q: https://patchwork.kernel.org/project/fsverity/list/ +T: git https://git.kernel.org/pub/scm/fs/fsverity/linux.git F: Documentation/filesystems/fsverity.rst F: fs/verity/ F: include/linux/fsverity.h @@ -8571,6 +8577,7 @@ F: kernel/trace/fgraph.c F: arch/*/*/*/*ftrace* F: arch/*/*/*ftrace* F: include/*/ftrace.h +F: samples/ftrace FUNGIBLE ETHERNET DRIVERS M: Dimitris Michailidis <dmichail@fungible.com> @@ -9299,7 +9306,7 @@ F: net/dsa/tag_hellcreek.c HISILICON DMA DRIVER M: Zhou Wang <wangzhou1@hisilicon.com> -M: Jie Hai <haijie1@hisilicon.com> +M: Jie Hai <haijie1@huawei.com> L: dmaengine@vger.kernel.org S: Maintained F: drivers/dma/hisi_dma.c @@ -11356,9 +11363,9 @@ F: virt/kvm/* KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64) M: Marc Zyngier <maz@kernel.org> R: James Morse <james.morse@arm.com> -R: Alexandru Elisei <alexandru.elisei@arm.com> R: Suzuki K Poulose <suzuki.poulose@arm.com> R: Oliver Upton <oliver.upton@linux.dev> +R: Zenghui Yu <yuzenghui@huawei.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: kvmarm@lists.linux.dev L: kvmarm@lists.cs.columbia.edu (deprecated, moderated for non-subscribers) @@ -13620,7 +13627,7 @@ F: arch/microblaze/ MICROCHIP AT91 DMA DRIVERS M: Ludovic Desroches <ludovic.desroches@microchip.com> -M: Tudor Ambarus <tudor.ambarus@microchip.com> +M: Tudor Ambarus <tudor.ambarus@linaro.org> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: dmaengine@vger.kernel.org S: Supported @@ -13665,7 +13672,7 @@ F: Documentation/devicetree/bindings/media/microchip,csi2dc.yaml F: drivers/media/platform/microchip/microchip-csi2dc.c MICROCHIP ECC DRIVER -M: Tudor Ambarus <tudor.ambarus@microchip.com> +M: Tudor Ambarus <tudor.ambarus@linaro.org> L: linux-crypto@vger.kernel.org S: Maintained F: drivers/crypto/atmel-ecc.* @@ -13762,7 +13769,7 @@ S: Maintained F: drivers/mmc/host/atmel-mci.c MICROCHIP NAND DRIVER -M: Tudor Ambarus <tudor.ambarus@microchip.com> +M: Tudor Ambarus <tudor.ambarus@linaro.org> L: linux-mtd@lists.infradead.org S: Supported F: Documentation/devicetree/bindings/mtd/atmel-nand.txt @@ -13814,7 +13821,7 @@ S: Supported F: drivers/power/reset/at91-sama5d2_shdwc.c MICROCHIP SPI DRIVER -M: Tudor Ambarus <tudor.ambarus@microchip.com> +M: Tudor Ambarus <tudor.ambarus@linaro.org> S: Supported F: drivers/spi/spi-atmel.* @@ -14601,7 +14608,6 @@ F: tools/testing/selftests/net/ipsec.c NETWORKING [IPv4/IPv6] M: "David S. Miller" <davem@davemloft.net> -M: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org> M: David Ahern <dsahern@kernel.org> L: netdev@vger.kernel.org S: Maintained @@ -14634,7 +14640,6 @@ F: net/netfilter/xt_SECMARK.c F: net/netlabel/ NETWORKING [MPTCP] -M: Mat Martineau <mathew.j.martineau@linux.intel.com> M: Matthieu Baerts <matthieu.baerts@tessares.net> L: netdev@vger.kernel.org L: mptcp@lists.linux.dev @@ -14919,7 +14924,8 @@ T: git://git.infradead.org/nvme.git F: Documentation/nvme/ F: drivers/nvme/host/ F: drivers/nvme/common/ -F: include/linux/nvme* +F: include/linux/nvme.h +F: include/linux/nvme-*.h F: include/uapi/linux/nvme_ioctl.h NVM EXPRESS FABRICS AUTHENTICATION @@ -15658,7 +15664,7 @@ OPENRISC ARCHITECTURE M: Jonas Bonn <jonas@southpole.se> M: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi> M: Stafford Horne <shorne@gmail.com> -L: openrisc@lists.librecores.org +L: linux-openrisc@vger.kernel.org S: Maintained W: http://openrisc.io T: git https://github.com/openrisc/linux.git @@ -15749,6 +15755,12 @@ S: Maintained W: https://wireless.wiki.kernel.org/en/users/Drivers/p54 F: drivers/net/wireless/intersil/p54/ +PACKET SOCKETS +M: Willem de Bruijn <willemdebruijn.kernel@gmail.com> +S: Maintained +F: include/uapi/linux/if_packet.h +F: net/packet/af_packet.c + PACKING M: Vladimir Oltean <olteanv@gmail.com> L: netdev@vger.kernel.org @@ -17237,7 +17249,7 @@ F: Documentation/devicetree/bindings/net/qcom,bam-dmux.yaml F: drivers/net/wwan/qcom_bam_dmux.c QUALCOMM CAMERA SUBSYSTEM DRIVER -M: Robert Foss <robert.foss@linaro.org> +M: Robert Foss <rfoss@kernel.org> M: Todor Tomov <todor.too@gmail.com> L: linux-media@vger.kernel.org S: Maintained @@ -17317,7 +17329,7 @@ F: drivers/dma/qcom/hidma* QUALCOMM I2C CCI DRIVER M: Loic Poulain <loic.poulain@linaro.org> -M: Robert Foss <robert.foss@linaro.org> +M: Robert Foss <rfoss@kernel.org> L: linux-i2c@vger.kernel.org L: linux-arm-msm@vger.kernel.org S: Maintained @@ -17956,6 +17968,7 @@ M: Albert Ou <aou@eecs.berkeley.edu> L: linux-riscv@lists.infradead.org S: Supported Q: https://patchwork.kernel.org/project/linux-riscv/list/ +C: irc://irc.libera.chat/riscv P: Documentation/riscv/patch-acceptance.rst T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git F: arch/riscv/ @@ -18677,9 +18690,9 @@ F: drivers/target/ F: include/target/ SCTP PROTOCOL -M: Vlad Yasevich <vyasevich@gmail.com> M: Neil Horman <nhorman@tuxdriver.com> M: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> +M: Xin Long <lucien.xin@gmail.com> L: linux-sctp@vger.kernel.org S: Maintained W: http://lksctp.sourceforge.net @@ -19325,6 +19338,13 @@ L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Orphan F: sound/soc/uniphier/ +SOCKET TIMESTAMPING +M: Willem de Bruijn <willemdebruijn.kernel@gmail.com> +S: Maintained +F: Documentation/networking/timestamping.rst +F: include/uapi/linux/net_tstamp.h +F: tools/testing/selftests/net/so_txtime.c + SOEKRIS NET48XX LED SUPPORT M: Chris Boot <bootc@bootc.net> S: Maintained @@ -19672,7 +19692,7 @@ F: drivers/clk/spear/ F: drivers/pinctrl/spear/ SPI NOR SUBSYSTEM -M: Tudor Ambarus <tudor.ambarus@microchip.com> +M: Tudor Ambarus <tudor.ambarus@linaro.org> M: Pratyush Yadav <pratyush@kernel.org> R: Michael Walle <michael@walle.cc> L: linux-mtd@lists.infradead.org @@ -21710,6 +21730,7 @@ F: include/uapi/linux/uvcvideo.h USB WEBCAM GADGET M: Laurent Pinchart <laurent.pinchart@ideasonboard.com> +M: Daniel Scally <dan.scally@ideasonboard.com> L: linux-usb@vger.kernel.org S: Maintained F: drivers/usb/gadget/function/*uvc* @@ -21745,6 +21766,13 @@ T: git git://linuxtv.org/media_tree.git F: Documentation/admin-guide/media/zr364xx* F: drivers/staging/media/deprecated/zr364xx/ +USER DATAGRAM PROTOCOL (UDP) +M: Willem de Bruijn <willemdebruijn.kernel@gmail.com> +S: Maintained +F: include/linux/udp.h +F: net/ipv4/udp.c +F: net/ipv6/udp.c + USER-MODE LINUX (UML) M: Richard Weinberger <richard@nod.at> M: Anton Ivanov <anton.ivanov@cambridgegreys.com> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* @@ -549,7 +549,7 @@ LDFLAGS_MODULE = CFLAGS_KERNEL = RUSTFLAGS_KERNEL = AFLAGS_KERNEL = -export LDFLAGS_vmlinux = +LDFLAGS_vmlinux = # Use USERINCLUDE when you must reference the UAPI directories only. USERINCLUDE := \ @@ -1248,6 +1248,18 @@ vmlinux.o modules.builtin.modinfo modules.builtin: vmlinux_o @: PHONY += vmlinux +# LDFLAGS_vmlinux in the top Makefile defines linker flags for the top vmlinux, +# not for decompressors. LDFLAGS_vmlinux in arch/*/boot/compressed/Makefile is +# unrelated; the decompressors just happen to have the same base name, +# arch/*/boot/compressed/vmlinux. +# Export LDFLAGS_vmlinux only to scripts/Makefile.vmlinux. +# +# _LDFLAGS_vmlinux is a workaround for the 'private export' bug: +# https://savannah.gnu.org/bugs/?61463 +# For Make > 4.4, the following simple code will work: +# vmlinux: private export LDFLAGS_vmlinux := $(LDFLAGS_vmlinux) +vmlinux: private _LDFLAGS_vmlinux := $(LDFLAGS_vmlinux) +vmlinux: export LDFLAGS_vmlinux = $(_LDFLAGS_vmlinux) vmlinux: vmlinux.o $(KBUILD_LDS) modpost $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vmlinux @@ -1533,6 +1545,7 @@ endif # *.ko are usually independent of vmlinux, but CONFIG_DEBUG_INFOBTF_MODULES # is an exception. ifdef CONFIG_DEBUG_INFO_BTF_MODULES +KBUILD_BUILTIN := 1 modules: vmlinux endif diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 4067f5169144..955b0362cdfb 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -132,7 +132,7 @@ AFLAGS_NOWARN :=$(call as-option,-Wa$(comma)-mno-warn-deprecated,-Wa$(comma)-W) ifeq ($(CONFIG_THUMB2_KERNEL),y) CFLAGS_ISA :=-Wa,-mimplicit-it=always $(AFLAGS_NOWARN) -AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb -D__thumb2__=2 +AFLAGS_ISA :=$(CFLAGS_ISA) -Wa$(comma)-mthumb CFLAGS_ISA +=-mthumb else CFLAGS_ISA :=$(call cc-option,-marm,) $(AFLAGS_NOWARN) diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index 12933eff419f..446861b6b17b 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -304,7 +304,7 @@ }; gpio0: gpio@18100 { - compatible = "marvell,armadaxp-gpio", + compatible = "marvell,armada-370-gpio", "marvell,orion-gpio"; reg = <0x18100 0x40>, <0x181c0 0x08>; reg-names = "gpio", "pwm"; @@ -323,7 +323,7 @@ }; gpio1: gpio@18140 { - compatible = "marvell,armadaxp-gpio", + compatible = "marvell,armada-370-gpio", "marvell,orion-gpio"; reg = <0x18140 0x40>, <0x181c8 0x08>; reg-names = "gpio", "pwm"; diff --git a/arch/arm/boot/dts/armada-39x.dtsi b/arch/arm/boot/dts/armada-39x.dtsi index 1e05208d9f34..9d1cac49c022 100644 --- a/arch/arm/boot/dts/armada-39x.dtsi +++ b/arch/arm/boot/dts/armada-39x.dtsi @@ -213,7 +213,7 @@ }; gpio0: gpio@18100 { - compatible = "marvell,armadaxp-gpio", "marvell,orion-gpio"; + compatible = "marvell,orion-gpio"; reg = <0x18100 0x40>; ngpios = <32>; gpio-controller; @@ -227,7 +227,7 @@ }; gpio1: gpio@18140 { - compatible = "marvell,armadaxp-gpio", "marvell,orion-gpio"; + compatible = "marvell,orion-gpio"; reg = <0x18140 0x40>; ngpios = <28>; gpio-controller; diff --git a/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts b/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts index d1971ddf06a5..7f755e5a4624 100644 --- a/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts +++ b/arch/arm/boot/dts/aspeed-bmc-ibm-bonnell.dts @@ -751,7 +751,7 @@ }; pca9849@75 { - compatible = "nxp,pca849"; + compatible = "nxp,pca9849"; reg = <0x75>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx53-ppd.dts b/arch/arm/boot/dts/imx53-ppd.dts index 37d0cffea99c..70c4a4852256 100644 --- a/arch/arm/boot/dts/imx53-ppd.dts +++ b/arch/arm/boot/dts/imx53-ppd.dts @@ -488,7 +488,7 @@ scl-gpios = <&gpio3 21 GPIO_ACTIVE_HIGH>; status = "okay"; - i2c-switch@70 { + i2c-mux@70 { compatible = "nxp,pca9547"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi index 4bc4371e6bae..4b81a975c979 100644 --- a/arch/arm/boot/dts/imx6qdl-gw560x.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw560x.dtsi @@ -632,7 +632,6 @@ &uart1 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_uart1>; - uart-has-rtscts; rts-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6ul-pico-dwarf.dts b/arch/arm/boot/dts/imx6ul-pico-dwarf.dts index 162dc259edc8..5a74c7f68eb6 100644 --- a/arch/arm/boot/dts/imx6ul-pico-dwarf.dts +++ b/arch/arm/boot/dts/imx6ul-pico-dwarf.dts @@ -32,7 +32,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx7d-pico-dwarf.dts b/arch/arm/boot/dts/imx7d-pico-dwarf.dts index 5162fe227d1e..fdc10563f147 100644 --- a/arch/arm/boot/dts/imx7d-pico-dwarf.dts +++ b/arch/arm/boot/dts/imx7d-pico-dwarf.dts @@ -32,7 +32,7 @@ }; &i2c1 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; @@ -52,7 +52,7 @@ }; &i2c4 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; diff --git a/arch/arm/boot/dts/imx7d-pico-nymph.dts b/arch/arm/boot/dts/imx7d-pico-nymph.dts index 104a85254adb..5afb1674e012 100644 --- a/arch/arm/boot/dts/imx7d-pico-nymph.dts +++ b/arch/arm/boot/dts/imx7d-pico-nymph.dts @@ -43,7 +43,7 @@ }; &i2c1 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; @@ -64,7 +64,7 @@ }; &i2c2 { - clock_frequency = <100000>; + clock-frequency = <100000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c2>; status = "okay"; diff --git a/arch/arm/boot/dts/imx7d-smegw01.dts b/arch/arm/boot/dts/imx7d-smegw01.dts index 546268b8d0b1..c0f00f5db11e 100644 --- a/arch/arm/boot/dts/imx7d-smegw01.dts +++ b/arch/arm/boot/dts/imx7d-smegw01.dts @@ -198,6 +198,7 @@ &usbotg2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_usbotg2>; + over-current-active-low; dr_mode = "host"; status = "okay"; }; @@ -374,7 +375,7 @@ pinctrl_usbotg2: usbotg2grp { fsl,pins = < - MX7D_PAD_UART3_RTS_B__USB_OTG2_OC 0x04 + MX7D_PAD_UART3_RTS_B__USB_OTG2_OC 0x5c >; }; diff --git a/arch/arm/boot/dts/nuvoton-wpcm450.dtsi b/arch/arm/boot/dts/nuvoton-wpcm450.dtsi index b637241316bb..fd671c7a1e5d 100644 --- a/arch/arm/boot/dts/nuvoton-wpcm450.dtsi +++ b/arch/arm/boot/dts/nuvoton-wpcm450.dtsi @@ -480,6 +480,7 @@ reg = <0xc8000000 0x1000>, <0xc0000000 0x4000000>; reg-names = "control", "memory"; clocks = <&clk 0>; + nuvoton,shm = <&shm>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts b/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts index 44cd72f1b1be..116e59a3b76d 100644 --- a/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts +++ b/arch/arm/boot/dts/qcom-apq8084-ifc6540.dts @@ -19,16 +19,16 @@ serial@f995e000 { status = "okay"; }; + }; +}; - sdhci@f9824900 { - bus-width = <8>; - non-removable; - status = "okay"; - }; +&sdhc_1 { + bus-width = <8>; + non-removable; + status = "okay"; +}; - sdhci@f98a4900 { - cd-gpios = <&tlmm 122 GPIO_ACTIVE_LOW>; - bus-width = <4>; - }; - }; +&sdhc_2 { + cd-gpios = <&tlmm 122 GPIO_ACTIVE_LOW>; + bus-width = <4>; }; diff --git a/arch/arm/boot/dts/qcom-apq8084.dtsi b/arch/arm/boot/dts/qcom-apq8084.dtsi index fe30abfff90a..4b0d2b4f4b6a 100644 --- a/arch/arm/boot/dts/qcom-apq8084.dtsi +++ b/arch/arm/boot/dts/qcom-apq8084.dtsi @@ -421,7 +421,7 @@ status = "disabled"; }; - mmc@f9824900 { + sdhc_1: mmc@f9824900 { compatible = "qcom,apq8084-sdhci", "qcom,sdhci-msm-v4"; reg = <0xf9824900 0x11c>, <0xf9824000 0x800>; reg-names = "hc", "core"; @@ -434,7 +434,7 @@ status = "disabled"; }; - mmc@f98a4900 { + sdhc_2: mmc@f98a4900 { compatible = "qcom,apq8084-sdhci", "qcom,sdhci-msm-v4"; reg = <0xf98a4900 0x11c>, <0xf98a4000 0x800>; reg-names = "hc", "core"; diff --git a/arch/arm/boot/dts/sam9x60.dtsi b/arch/arm/boot/dts/sam9x60.dtsi index 8f5477e307dd..37a5d96aaf64 100644 --- a/arch/arm/boot/dts/sam9x60.dtsi +++ b/arch/arm/boot/dts/sam9x60.dtsi @@ -564,7 +564,7 @@ mpddrc: mpddrc@ffffe800 { compatible = "microchip,sam9x60-ddramc", "atmel,sama5d3-ddramc"; reg = <0xffffe800 0x200>; - clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_CORE PMC_MCK>; + clocks = <&pmc PMC_TYPE_SYSTEM 2>, <&pmc PMC_TYPE_PERIPHERAL 49>; clock-names = "ddrck", "mpddr"; }; diff --git a/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi b/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi index d865ab5d866b..dd23de85100c 100644 --- a/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi +++ b/arch/arm/boot/dts/stm32mp151a-prtt1l.dtsi @@ -101,8 +101,12 @@ &qspi { pinctrl-names = "default", "sleep"; - pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>; - pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>; + pinctrl-0 = <&qspi_clk_pins_a + &qspi_bk1_pins_a + &qspi_cs1_pins_a>; + pinctrl-1 = <&qspi_clk_sleep_pins_a + &qspi_bk1_sleep_pins_a + &qspi_cs1_sleep_pins_a>; reg = <0x58003000 0x1000>, <0x70000000 0x4000000>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi index aef02e6421a3..7d11c50b9e40 100644 --- a/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi +++ b/arch/arm/boot/dts/stm32mp157c-emstamp-argon.dtsi @@ -391,8 +391,12 @@ &qspi { pinctrl-names = "default", "sleep"; - pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>; - pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>; + pinctrl-0 = <&qspi_clk_pins_a + &qspi_bk1_pins_a + &qspi_cs1_pins_a>; + pinctrl-1 = <&qspi_clk_sleep_pins_a + &qspi_bk1_sleep_pins_a + &qspi_cs1_sleep_pins_a>; reg = <0x58003000 0x1000>, <0x70000000 0x4000000>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index 002f221f1694..c06edd2eacb0 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -428,8 +428,12 @@ &qspi { pinctrl-names = "default", "sleep"; - pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>; - pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>; + pinctrl-0 = <&qspi_clk_pins_a + &qspi_bk1_pins_a + &qspi_cs1_pins_a>; + pinctrl-1 = <&qspi_clk_sleep_pins_a + &qspi_bk1_sleep_pins_a + &qspi_cs1_sleep_pins_a>; reg = <0x58003000 0x1000>, <0x70000000 0x4000000>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi index 134a798ad3f2..bb40fb46da81 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcor-som.dtsi @@ -247,8 +247,12 @@ &qspi { pinctrl-names = "default", "sleep"; - pinctrl-0 = <&qspi_clk_pins_a &qspi_bk1_pins_a>; - pinctrl-1 = <&qspi_clk_sleep_pins_a &qspi_bk1_sleep_pins_a>; + pinctrl-0 = <&qspi_clk_pins_a + &qspi_bk1_pins_a + &qspi_cs1_pins_a>; + pinctrl-1 = <&qspi_clk_sleep_pins_a + &qspi_bk1_sleep_pins_a + &qspi_cs1_sleep_pins_a>; reg = <0x58003000 0x1000>, <0x70000000 0x200000>; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts index 42ed4a04a12e..6280c5e86a12 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-b.dts @@ -345,7 +345,7 @@ }; &i2c2 { - tca9548@70 { + i2c-mux@70 { compatible = "nxp,pca9548"; pinctrl-0 = <&pinctrl_i2c_mux_reset>; pinctrl-names = "default"; diff --git a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts index f892977da9e4..c00d39562a10 100644 --- a/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts +++ b/arch/arm/boot/dts/vf610-zii-dev-rev-c.dts @@ -340,7 +340,7 @@ }; &i2c2 { - tca9548@70 { + i2c-mux@70 { compatible = "nxp,pca9548"; pinctrl-0 = <&pinctrl_i2c_mux_reset>; pinctrl-names = "default"; diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile index 971e74546fb1..13e62c7c25dc 100644 --- a/arch/arm/crypto/Makefile +++ b/arch/arm/crypto/Makefile @@ -53,7 +53,12 @@ $(obj)/%-core.S: $(src)/%-armv4.pl clean-files += poly1305-core.S sha256-core.S sha512-core.S +aflags-thumb2-$(CONFIG_THUMB2_KERNEL) := -U__thumb2__ -D__thumb2__=1 + +AFLAGS_sha256-core.o += $(aflags-thumb2-y) +AFLAGS_sha512-core.o += $(aflags-thumb2-y) + # massage the perlasm code a bit so we only get the NEON routine if we need it poly1305-aflags-$(CONFIG_CPU_V7) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=5 poly1305-aflags-$(CONFIG_KERNEL_MODE_NEON) := -U__LINUX_ARM_ARCH__ -D__LINUX_ARM_ARCH__=7 -AFLAGS_poly1305-core.o += $(poly1305-aflags-y) +AFLAGS_poly1305-core.o += $(poly1305-aflags-y) $(aflags-thumb2-y) diff --git a/arch/arm/mach-footbridge/isa-rtc.c b/arch/arm/mach-footbridge/isa-rtc.c index b8f741a3a37e..237b828dd2f1 100644 --- a/arch/arm/mach-footbridge/isa-rtc.c +++ b/arch/arm/mach-footbridge/isa-rtc.c @@ -20,7 +20,6 @@ #include <linux/init.h> #include <linux/mc146818rtc.h> -#include <linux/bcd.h> #include <linux/io.h> #include "common.h" diff --git a/arch/arm/mach-imx/cpu-imx25.c b/arch/arm/mach-imx/cpu-imx25.c index 3e63445cde06..cc86977d0a34 100644 --- a/arch/arm/mach-imx/cpu-imx25.c +++ b/arch/arm/mach-imx/cpu-imx25.c @@ -23,6 +23,7 @@ static int mx25_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx25-iim"); iim_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!iim_base); rev = readl(iim_base + MXC_IIMSREV); iounmap(iim_base); diff --git a/arch/arm/mach-imx/cpu-imx27.c b/arch/arm/mach-imx/cpu-imx27.c index bf70e13bbe9e..1d2893908368 100644 --- a/arch/arm/mach-imx/cpu-imx27.c +++ b/arch/arm/mach-imx/cpu-imx27.c @@ -28,6 +28,7 @@ static int mx27_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx27-ccm"); ccm_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!ccm_base); /* * now we have access to the IO registers. As we need diff --git a/arch/arm/mach-imx/cpu-imx31.c b/arch/arm/mach-imx/cpu-imx31.c index b9c24b851d1a..35c544924e50 100644 --- a/arch/arm/mach-imx/cpu-imx31.c +++ b/arch/arm/mach-imx/cpu-imx31.c @@ -39,6 +39,7 @@ static int mx31_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx31-iim"); iim_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!iim_base); /* read SREV register from IIM module */ diff --git a/arch/arm/mach-imx/cpu-imx35.c b/arch/arm/mach-imx/cpu-imx35.c index 80e7d8ab9f1b..1fe75b39c2d9 100644 --- a/arch/arm/mach-imx/cpu-imx35.c +++ b/arch/arm/mach-imx/cpu-imx35.c @@ -21,6 +21,7 @@ static int mx35_read_cpu_rev(void) np = of_find_compatible_node(NULL, NULL, "fsl,imx35-iim"); iim_base = of_iomap(np, 0); + of_node_put(np); BUG_ON(!iim_base); rev = imx_readl(iim_base + MXC_IIMSREV); diff --git a/arch/arm/mach-imx/cpu-imx5.c b/arch/arm/mach-imx/cpu-imx5.c index ad56263778f9..a67c89bf155d 100644 --- a/arch/arm/mach-imx/cpu-imx5.c +++ b/arch/arm/mach-imx/cpu-imx5.c @@ -28,6 +28,7 @@ static u32 imx5_read_srev_reg(const char *compat) np = of_find_compatible_node(NULL, NULL, compat); iim_base = of_iomap(np, 0); + of_node_put(np); WARN_ON(!iim_base); srev = readl(iim_base + IIM_SREV) & 0xff; diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig index 538a960257cc..7ec7ada287e0 100644 --- a/arch/arm/mach-omap1/Kconfig +++ b/arch/arm/mach-omap1/Kconfig @@ -4,6 +4,7 @@ menuconfig ARCH_OMAP1 depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 depends on CPU_LITTLE_ENDIAN depends on ATAGS + select ARCH_OMAP select ARCH_HAS_HOLES_MEMORYMODEL select ARCH_OMAP select CLKSRC_MMIO @@ -45,10 +46,6 @@ config ARCH_OMAP16XX select CPU_ARM926T select OMAP_DM_TIMER -config ARCH_OMAP1_ANY - select ARCH_OMAP - def_bool ARCH_OMAP730 || ARCH_OMAP850 || ARCH_OMAP15XX || ARCH_OMAP16XX - config ARCH_OMAP bool diff --git a/arch/arm/mach-omap1/Makefile b/arch/arm/mach-omap1/Makefile index 506074b86333..0615cb0ba580 100644 --- a/arch/arm/mach-omap1/Makefile +++ b/arch/arm/mach-omap1/Makefile @@ -3,8 +3,6 @@ # Makefile for the linux kernel. # -ifdef CONFIG_ARCH_OMAP1_ANY - # Common support obj-y := io.o id.o sram-init.o sram.o time.o irq.o mux.o flash.o \ serial.o devices.o dma.o omap-dma.o fb.o @@ -59,5 +57,3 @@ obj-$(CONFIG_ARCH_OMAP730) += gpio7xx.o obj-$(CONFIG_ARCH_OMAP850) += gpio7xx.o obj-$(CONFIG_ARCH_OMAP15XX) += gpio15xx.o obj-$(CONFIG_ARCH_OMAP16XX) += gpio16xx.o - -endif diff --git a/arch/arm/mach-omap1/gpio15xx.c b/arch/arm/mach-omap1/gpio15xx.c index c675f11de99d..61fa26efd865 100644 --- a/arch/arm/mach-omap1/gpio15xx.c +++ b/arch/arm/mach-omap1/gpio15xx.c @@ -11,6 +11,7 @@ #include <linux/gpio.h> #include <linux/platform_data/gpio-omap.h> #include <linux/soc/ti/omap1-soc.h> +#include <asm/irq.h> #include "irqs.h" diff --git a/arch/arm/mach-omap1/io.c b/arch/arm/mach-omap1/io.c index d2db9b8aed3f..0074b011a05a 100644 --- a/arch/arm/mach-omap1/io.c +++ b/arch/arm/mach-omap1/io.c @@ -22,17 +22,14 @@ * The machine specific code may provide the extra mapping besides the * default mapping provided here. */ -static struct map_desc omap_io_desc[] __initdata = { +#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) +static struct map_desc omap7xx_io_desc[] __initdata = { { .virtual = OMAP1_IO_VIRT, .pfn = __phys_to_pfn(OMAP1_IO_PHYS), .length = OMAP1_IO_SIZE, .type = MT_DEVICE - } -}; - -#if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) -static struct map_desc omap7xx_io_desc[] __initdata = { + }, { .virtual = OMAP7XX_DSP_BASE, .pfn = __phys_to_pfn(OMAP7XX_DSP_START), @@ -50,6 +47,12 @@ static struct map_desc omap7xx_io_desc[] __initdata = { #ifdef CONFIG_ARCH_OMAP15XX static struct map_desc omap1510_io_desc[] __initdata = { { + .virtual = OMAP1_IO_VIRT, + .pfn = __phys_to_pfn(OMAP1_IO_PHYS), + .length = OMAP1_IO_SIZE, + .type = MT_DEVICE + }, + { .virtual = OMAP1510_DSP_BASE, .pfn = __phys_to_pfn(OMAP1510_DSP_START), .length = OMAP1510_DSP_SIZE, @@ -66,6 +69,12 @@ static struct map_desc omap1510_io_desc[] __initdata = { #if defined(CONFIG_ARCH_OMAP16XX) static struct map_desc omap16xx_io_desc[] __initdata = { { + .virtual = OMAP1_IO_VIRT, + .pfn = __phys_to_pfn(OMAP1_IO_PHYS), + .length = OMAP1_IO_SIZE, + .type = MT_DEVICE + }, + { .virtual = OMAP16XX_DSP_BASE, .pfn = __phys_to_pfn(OMAP16XX_DSP_START), .length = OMAP16XX_DSP_SIZE, @@ -79,18 +88,9 @@ static struct map_desc omap16xx_io_desc[] __initdata = { }; #endif -/* - * Maps common IO regions for omap1 - */ -static void __init omap1_map_common_io(void) -{ - iotable_init(omap_io_desc, ARRAY_SIZE(omap_io_desc)); -} - #if defined (CONFIG_ARCH_OMAP730) || defined (CONFIG_ARCH_OMAP850) void __init omap7xx_map_io(void) { - omap1_map_common_io(); iotable_init(omap7xx_io_desc, ARRAY_SIZE(omap7xx_io_desc)); } #endif @@ -98,7 +98,6 @@ void __init omap7xx_map_io(void) #ifdef CONFIG_ARCH_OMAP15XX void __init omap15xx_map_io(void) { - omap1_map_common_io(); iotable_init(omap1510_io_desc, ARRAY_SIZE(omap1510_io_desc)); } #endif @@ -106,7 +105,6 @@ void __init omap15xx_map_io(void) #if defined(CONFIG_ARCH_OMAP16XX) void __init omap16xx_map_io(void) { - omap1_map_common_io(); iotable_init(omap16xx_io_desc, ARRAY_SIZE(omap16xx_io_desc)); } #endif diff --git a/arch/arm/mach-omap1/mcbsp.c b/arch/arm/mach-omap1/mcbsp.c index 05c25c432449..b1632cbe37e6 100644 --- a/arch/arm/mach-omap1/mcbsp.c +++ b/arch/arm/mach-omap1/mcbsp.c @@ -89,7 +89,6 @@ static struct omap_mcbsp_ops omap1_mcbsp_ops = { #define OMAP1610_MCBSP2_BASE 0xfffb1000 #define OMAP1610_MCBSP3_BASE 0xe1017000 -#if defined(CONFIG_ARCH_OMAP730) || defined(CONFIG_ARCH_OMAP850) struct resource omap7xx_mcbsp_res[][6] = { { { @@ -159,14 +158,7 @@ static struct omap_mcbsp_platform_data omap7xx_mcbsp_pdata[] = { }; #define OMAP7XX_MCBSP_RES_SZ ARRAY_SIZE(omap7xx_mcbsp_res[1]) #define OMAP7XX_MCBSP_COUNT ARRAY_SIZE(omap7xx_mcbsp_res) -#else -#define omap7xx_mcbsp_res_0 NULL -#define omap7xx_mcbsp_pdata NULL -#define OMAP7XX_MCBSP_RES_SZ 0 -#define OMAP7XX_MCBSP_COUNT 0 -#endif -#ifdef CONFIG_ARCH_OMAP15XX struct resource omap15xx_mcbsp_res[][6] = { { { @@ -266,14 +258,7 @@ static struct omap_mcbsp_platform_data omap15xx_mcbsp_pdata[] = { }; #define OMAP15XX_MCBSP_RES_SZ ARRAY_SIZE(omap15xx_mcbsp_res[1]) #define OMAP15XX_MCBSP_COUNT ARRAY_SIZE(omap15xx_mcbsp_res) -#else -#define omap15xx_mcbsp_res_0 NULL -#define omap15xx_mcbsp_pdata NULL -#define OMAP15XX_MCBSP_RES_SZ 0 -#define OMAP15XX_MCBSP_COUNT 0 -#endif -#ifdef CONFIG_ARCH_OMAP16XX struct resource omap16xx_mcbsp_res[][6] = { { { @@ -373,12 +358,6 @@ static struct omap_mcbsp_platform_data omap16xx_mcbsp_pdata[] = { }; #define OMAP16XX_MCBSP_RES_SZ ARRAY_SIZE(omap16xx_mcbsp_res[1]) #define OMAP16XX_MCBSP_COUNT ARRAY_SIZE(omap16xx_mcbsp_res) -#else -#define omap16xx_mcbsp_res_0 NULL -#define omap16xx_mcbsp_pdata NULL -#define OMAP16XX_MCBSP_RES_SZ 0 -#define OMAP16XX_MCBSP_COUNT 0 -#endif static void omap_mcbsp_register_board_cfg(struct resource *res, int res_count, struct omap_mcbsp_platform_data *config, int size) diff --git a/arch/arm/mach-omap1/pm.h b/arch/arm/mach-omap1/pm.h index d9165709c532..0d1f092821ff 100644 --- a/arch/arm/mach-omap1/pm.h +++ b/arch/arm/mach-omap1/pm.h @@ -106,13 +106,6 @@ #define OMAP7XX_IDLECT3 0xfffece24 #define OMAP7XX_IDLE_LOOP_REQUEST 0x0C00 -#if !defined(CONFIG_ARCH_OMAP730) && \ - !defined(CONFIG_ARCH_OMAP850) && \ - !defined(CONFIG_ARCH_OMAP15XX) && \ - !defined(CONFIG_ARCH_OMAP16XX) -#warning "Power management for this processor not implemented yet" -#endif - #ifndef __ASSEMBLER__ #include <linux/clk.h> diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index b90d98bae68d..03e25af6f48c 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -45,6 +45,8 @@ config MACH_PXA27X_DT config MACH_PXA3XX_DT bool "Support PXA3xx platforms from device tree" select CPU_PXA300 + select CPU_PXA310 + select CPU_PXA320 select PINCTRL select POWER_SUPPLY select PXA3xx diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c index c1494a4dee25..53f2d8774fdb 100644 --- a/arch/arm/mm/nommu.c +++ b/arch/arm/mm/nommu.c @@ -161,7 +161,7 @@ void __init paging_init(const struct machine_desc *mdesc) mpu_setup(); /* allocate the zero page. */ - zero_page = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + zero_page = (void *)memblock_alloc(PAGE_SIZE, PAGE_SIZE); if (!zero_page) panic("%s: Failed to allocate %lu bytes align=0x%lx\n", __func__, PAGE_SIZE, PAGE_SIZE); diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index fa6999e24b07..e43f6d716b4b 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -6,6 +6,7 @@ * VM_EXEC */ #include <asm/asm-offsets.h> +#include <asm/pgtable.h> #include <asm/thread_info.h> #ifdef CONFIG_CPU_V7M diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 03934808b2ed..c5ccca26a408 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -184,8 +184,6 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE - select HAVE_DYNAMIC_FTRACE_WITH_ARGS \ - if $(cc-option,-fpatchable-function-entry=2) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -972,6 +970,22 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. +config ARM64_ERRATUM_2645198 + bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption" + default y + help + This option adds the workaround for ARM Cortex-A715 erratum 2645198. + + If a Cortex-A715 cpu sees a page mapping permissions change from executable + to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the + next instruction abort caused by permission fault. + + Only user-space does executable to non-executable permission transition via + mprotect() system call. Workaround the problem by doing a break-before-make + TLB invalidation, for all changes to executable user space mappings. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts index e3486f60645a..a1f0c38ccadd 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-hc4.dts @@ -131,10 +131,6 @@ }; &usb { - phys = <&usb2_phy1>; - phy-names = "usb2-phy1"; -}; - -&usb2_phy0 { - status = "disabled"; + phys = <&usb2_phy0>, <&usb2_phy1>; + phy-names = "usb2-phy0", "usb2-phy1"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts index 5a8d85a7d161..bbdf989058ff 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1012a-qds.dts @@ -110,7 +110,7 @@ &i2c0 { status = "okay"; - pca9547@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts index 9b726c2a4842..dda27ed7aaf2 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-qds.dts @@ -89,7 +89,7 @@ &i2c0 { status = "okay"; - pca9547@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts index b2fcbba60d3a..3b0ed9305f2b 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a-qds.dts @@ -88,7 +88,7 @@ &i2c0 { status = "okay"; - pca9547@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts index 41d8b15f25a5..aa52ff73ff9e 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-qds.dts @@ -53,7 +53,7 @@ &i2c0 { status = "okay"; - i2c-switch@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts index 1bfbce69cc8b..ee8e932628d1 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-rdb.dts @@ -136,7 +136,7 @@ &i2c0 { status = "okay"; - i2c-switch@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts index ef6c8967533e..d4867d6cf47c 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a-ten64.dts @@ -245,7 +245,7 @@ &i2c3 { status = "okay"; - i2c-switch@70 { + i2c-mux@70 { compatible = "nxp,pca9540"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi index f598669e742f..52c5a43b30a0 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa-qds.dtsi @@ -103,7 +103,7 @@ &i2c0 { status = "okay"; - pca9547@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; reg = <0x77>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi index 3d9647b3da14..537cecb13dd0 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa-rdb.dtsi @@ -44,7 +44,7 @@ &i2c0 { status = "okay"; - pca9547@75 { + i2c-mux@75 { compatible = "nxp,pca9547"; reg = <0x75>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi index afb455210bd0..d32a52ab00a4 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a-cex7.dtsi @@ -54,7 +54,7 @@ &i2c0 { status = "okay"; - i2c-switch@77 { + i2c-mux@77 { compatible = "nxp,pca9547"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/imx8dxl.dtsi b/arch/arm64/boot/dts/freescale/imx8dxl.dtsi index 0c64b9194621..214f21bd0cb4 100644 --- a/arch/arm64/boot/dts/freescale/imx8dxl.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8dxl.dtsi @@ -164,7 +164,7 @@ sc_pwrkey: keys { compatible = "fsl,imx8qxp-sc-key", "fsl,imx-sc-key"; - linux,keycode = <KEY_POWER>; + linux,keycodes = <KEY_POWER>; wakeup-source; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi index 03266bd90a06..169f047fbca5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-beacon-baseboard.dtsi @@ -120,7 +120,7 @@ &ecspi2 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_espi2>; - cs-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>; + cs-gpios = <&gpio5 13 GPIO_ACTIVE_LOW>; status = "okay"; eeprom@0 { @@ -316,7 +316,7 @@ MX8MM_IOMUXC_ECSPI2_SCLK_ECSPI2_SCLK 0x82 MX8MM_IOMUXC_ECSPI2_MOSI_ECSPI2_MOSI 0x82 MX8MM_IOMUXC_ECSPI2_MISO_ECSPI2_MISO 0x82 - MX8MM_IOMUXC_ECSPI1_SS0_GPIO5_IO9 0x41 + MX8MM_IOMUXC_ECSPI2_SS0_GPIO5_IO13 0x41 >; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts index 24f61db33eba..9889319d4f04 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-data-modul-edm-sbc.dts @@ -88,6 +88,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_watchdog_gpio>; compatible = "linux,wdt-gpio"; + always-running; gpios = <&gpio1 8 GPIO_ACTIVE_HIGH>; hw_algo = "level"; /* Reset triggers in 2..3 seconds */ @@ -275,7 +276,7 @@ compatible = "rohm,bd71847"; reg = <0x4b>; #clock-cells = <0>; - clocks = <&clk_xtal32k 0>; + clocks = <&clk_xtal32k>; clock-output-names = "clk-32k-out"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pmic>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts b/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts index 74c09891600f..6357078185ed 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-nitrogen-r2.dts @@ -214,7 +214,7 @@ pinctrl-0 = <&pinctrl_i2c3>; status = "okay"; - i2cmux@70 { + i2c-mux@70 { compatible = "nxp,pca9540"; reg = <0x70>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h index 83c8f715cd90..b1f11098d248 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h +++ b/arch/arm64/boot/dts/freescale/imx8mm-pinfunc.h @@ -602,7 +602,7 @@ #define MX8MM_IOMUXC_UART1_RXD_GPIO5_IO22 0x234 0x49C 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_RXD_TPSMP_HDATA24 0x234 0x49C 0x000 0x7 0x0 #define MX8MM_IOMUXC_UART1_TXD_UART1_DCE_TX 0x238 0x4A0 0x000 0x0 0x0 -#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x0 +#define MX8MM_IOMUXC_UART1_TXD_UART1_DTE_RX 0x238 0x4A0 0x4F4 0x0 0x1 #define MX8MM_IOMUXC_UART1_TXD_ECSPI3_MOSI 0x238 0x4A0 0x000 0x1 0x0 #define MX8MM_IOMUXC_UART1_TXD_GPIO5_IO23 0x238 0x4A0 0x000 0x5 0x0 #define MX8MM_IOMUXC_UART1_TXD_TPSMP_HDATA25 0x238 0x4A0 0x000 0x7 0x0 diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso index 3ea73a6886ff..f6ad1a4b8b66 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw72xx-0x-rs232-rts.dtso @@ -33,7 +33,6 @@ pinctrl-0 = <&pinctrl_uart2>; rts-gpios = <&gpio5 29 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio5 28 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso index 2fa635e1c1a8..1f8ea20dfafc 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx-0x-rs232-rts.dtso @@ -33,7 +33,6 @@ pinctrl-0 = <&pinctrl_uart2>; rts-gpios = <&gpio5 29 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio5 28 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi index 244ef8d6cc68..7761d5671cb1 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw73xx.dtsi @@ -222,7 +222,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_bten>; cts-gpios = <&gpio5 8 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio5 9 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts index 750a1f07ecb7..64b366e83fa1 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7901.dts @@ -733,7 +733,6 @@ dtr-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; dsr-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; dcd-gpios = <&gpio1 11 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -749,7 +748,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; cts-gpios = <&gpio4 10 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio4 9 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -758,7 +756,6 @@ pinctrl-0 = <&pinctrl_uart4>, <&pinctrl_uart4_gpio>; cts-gpios = <&gpio5 11 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio5 12 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -771,6 +768,7 @@ &usbotg2 { dr_mode = "host"; vbus-supply = <®_usb2_vbus>; + over-current-active-low; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts index 32872b0b1aaf..e8bc1fccc47b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7902.dts @@ -664,7 +664,6 @@ pinctrl-0 = <&pinctrl_uart1>, <&pinctrl_uart1_gpio>; rts-gpios = <&gpio4 10 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio4 24 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; @@ -681,7 +680,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; rts-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { @@ -699,7 +697,6 @@ dtr-gpios = <&gpio4 3 GPIO_ACTIVE_LOW>; dsr-gpios = <&gpio4 4 GPIO_ACTIVE_LOW>; dcd-gpios = <&gpio4 6 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts index 8ce562246a08..acc2ba8e00a8 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-venice-gw7903.dts @@ -581,7 +581,6 @@ dtr-gpios = <&gpio1 0 GPIO_ACTIVE_LOW>; dsr-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>; dcd-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi index c2a5c2f7b204..7c3f5c54f040 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi @@ -9,6 +9,7 @@ simple-audio-card,bitclock-master = <&dailink_master>; simple-audio-card,format = "i2s"; simple-audio-card,frame-master = <&dailink_master>; + simple-audio-card,mclk-fs = <256>; simple-audio-card,name = "imx8mm-wm8904"; simple-audio-card,routing = "Headphone Jack", "HPOUTL", diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi index 73cc3fafa018..b2bcd2282170 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dev.dtsi @@ -11,6 +11,7 @@ simple-audio-card,bitclock-master = <&dailink_master>; simple-audio-card,format = "i2s"; simple-audio-card,frame-master = <&dailink_master>; + simple-audio-card,mclk-fs = <256>; simple-audio-card,name = "imx8mm-nau8822"; simple-audio-card,routing = "Headphones", "LHP", diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi index 0d454e0e2f7c..702d87621bb4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin.dtsi @@ -98,6 +98,7 @@ off-on-delay = <500000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_reg_eth>; + regulator-always-on; regulator-boot-on; regulator-max-microvolt = <3300000>; regulator-min-microvolt = <3300000>; diff --git a/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts b/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts index b9444e4a3d2d..7c12518dbc96 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts +++ b/arch/arm64/boot/dts/freescale/imx8mn-venice-gw7902.dts @@ -643,7 +643,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; rts-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>; cts-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts index d4c7ca16abd0..f2d93437084b 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-evk.dts @@ -36,8 +36,8 @@ pcie0_refclk: pcie0-refclk { compatible = "fixed-clock"; - #clock-cells = <0>; - clock-frequency = <100000000>; + #clock-cells = <0>; + clock-frequency = <100000000>; }; reg_can1_stby: regulator-can1-stby { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi index 79b290a002c1..ecc4bce6db97 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-phycore-som.dtsi @@ -99,7 +99,6 @@ regulators { buck1: BUCK1 { - regulator-compatible = "BUCK1"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <2187500>; regulator-boot-on; @@ -108,7 +107,6 @@ }; buck2: BUCK2 { - regulator-compatible = "BUCK2"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <2187500>; regulator-boot-on; @@ -119,7 +117,6 @@ }; buck4: BUCK4 { - regulator-compatible = "BUCK4"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <3400000>; regulator-boot-on; @@ -127,7 +124,6 @@ }; buck5: BUCK5 { - regulator-compatible = "BUCK5"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <3400000>; regulator-boot-on; @@ -135,7 +131,6 @@ }; buck6: BUCK6 { - regulator-compatible = "BUCK6"; regulator-min-microvolt = <600000>; regulator-max-microvolt = <3400000>; regulator-boot-on; @@ -143,7 +138,6 @@ }; ldo1: LDO1 { - regulator-compatible = "LDO1"; regulator-min-microvolt = <1600000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -151,7 +145,6 @@ }; ldo2: LDO2 { - regulator-compatible = "LDO2"; regulator-min-microvolt = <800000>; regulator-max-microvolt = <1150000>; regulator-boot-on; @@ -159,7 +152,6 @@ }; ldo3: LDO3 { - regulator-compatible = "LDO3"; regulator-min-microvolt = <800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -167,13 +159,11 @@ }; ldo4: LDO4 { - regulator-compatible = "LDO4"; regulator-min-microvolt = <800000>; regulator-max-microvolt = <3300000>; }; ldo5: LDO5 { - regulator-compatible = "LDO5"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts index ceeca4966fc5..8eb7d5ee38da 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-venice-gw74xx.dts @@ -623,7 +623,6 @@ pinctrl-0 = <&pinctrl_uart3>, <&pinctrl_uart3_gpio>; cts-gpios = <&gpio3 21 GPIO_ACTIVE_LOW>; rts-gpios = <&gpio3 22 GPIO_ACTIVE_LOW>; - uart-has-rtscts; status = "okay"; bluetooth { diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index 7a6e6221f421..03034b439c1f 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -524,6 +524,7 @@ compatible = "fsl,imx8mp-gpc"; reg = <0x303a0000 0x1000>; interrupt-parent = <&gic>; + interrupts = <GIC_SPI 87 IRQ_TYPE_LEVEL_HIGH>; interrupt-controller; #interrupt-cells = <3>; @@ -590,7 +591,7 @@ reg = <IMX8MP_POWER_DOMAIN_MIPI_PHY2>; }; - pgc_hsiomix: power-domains@17 { + pgc_hsiomix: power-domain@17 { #power-domain-cells = <0>; reg = <IMX8MP_POWER_DOMAIN_HSIOMIX>; clocks = <&clk IMX8MP_CLK_HSIO_AXI>, @@ -1297,7 +1298,7 @@ reg = <0x32f10100 0x8>, <0x381f0000 0x20>; clocks = <&clk IMX8MP_CLK_HSIO_ROOT>, - <&clk IMX8MP_CLK_USB_ROOT>; + <&clk IMX8MP_CLK_USB_SUSP>; clock-names = "hsio", "suspend"; interrupts = <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&hsio_blk_ctrl IMX8MP_HSIOBLK_PD_USB>; @@ -1310,9 +1311,9 @@ usb_dwc3_0: usb@38100000 { compatible = "snps,dwc3"; reg = <0x38100000 0x10000>; - clocks = <&clk IMX8MP_CLK_HSIO_AXI>, + clocks = <&clk IMX8MP_CLK_USB_ROOT>, <&clk IMX8MP_CLK_USB_CORE_REF>, - <&clk IMX8MP_CLK_USB_ROOT>; + <&clk IMX8MP_CLK_USB_SUSP>; clock-names = "bus_early", "ref", "suspend"; interrupts = <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>; phys = <&usb3_phy0>, <&usb3_phy0>; @@ -1339,7 +1340,7 @@ reg = <0x32f10108 0x8>, <0x382f0000 0x20>; clocks = <&clk IMX8MP_CLK_HSIO_ROOT>, - <&clk IMX8MP_CLK_USB_ROOT>; + <&clk IMX8MP_CLK_USB_SUSP>; clock-names = "hsio", "suspend"; interrupts = <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>; power-domains = <&hsio_blk_ctrl IMX8MP_HSIOBLK_PD_USB>; @@ -1352,9 +1353,9 @@ usb_dwc3_1: usb@38200000 { compatible = "snps,dwc3"; reg = <0x38200000 0x10000>; - clocks = <&clk IMX8MP_CLK_HSIO_AXI>, + clocks = <&clk IMX8MP_CLK_USB_ROOT>, <&clk IMX8MP_CLK_USB_CORE_REF>, - <&clk IMX8MP_CLK_USB_ROOT>; + <&clk IMX8MP_CLK_USB_SUSP>; clock-names = "bus_early", "ref", "suspend"; interrupts = <GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>; phys = <&usb3_phy1>, <&usb3_phy1>; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts b/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts index 9dda2a1554c3..8614c18b5998 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-nitrogen.dts @@ -133,7 +133,7 @@ pinctrl-0 = <&pinctrl_i2c1>; status = "okay"; - i2cmux@70 { + i2c-mux@70 { compatible = "nxp,pca9546"; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c1_pca9546>; @@ -216,7 +216,7 @@ pinctrl-0 = <&pinctrl_i2c4>; status = "okay"; - pca9546: i2cmux@70 { + pca9546: i2c-mux@70 { compatible = "nxp,pca9546"; reg = <0x70>; #address-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts b/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts index 5d5aa6537225..6e6182709d22 100644 --- a/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts +++ b/arch/arm64/boot/dts/freescale/imx8mq-thor96.dts @@ -339,7 +339,7 @@ bus-width = <4>; non-removable; no-sd; - no-emmc; + no-mmc; status = "okay"; brcmf: wifi@1 { @@ -359,7 +359,7 @@ cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>; bus-width = <4>; no-sdio; - no-emmc; + no-mmc; disable-wp; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts index 07d8dd8160f6..afa883389456 100644 --- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts +++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts @@ -61,7 +61,7 @@ pinctrl-0 = <&pinctrl_lpi2c1 &pinctrl_ioexp_rst>; status = "okay"; - i2c-switch@71 { + i2c-mux@71 { compatible = "nxp,pca9646", "nxp,pca9546"; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts index 69786c326db0..27f9a9f33134 100644 --- a/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx93-11x11-evk.dts @@ -74,7 +74,7 @@ pinctrl_usdhc1: usdhc1grp { fsl,pins = < - MX93_PAD_SD1_CLK__USDHC1_CLK 0x17fe + MX93_PAD_SD1_CLK__USDHC1_CLK 0x15fe MX93_PAD_SD1_CMD__USDHC1_CMD 0x13fe MX93_PAD_SD1_DATA0__USDHC1_DATA0 0x13fe MX93_PAD_SD1_DATA1__USDHC1_DATA1 0x13fe @@ -84,7 +84,7 @@ MX93_PAD_SD1_DATA5__USDHC1_DATA5 0x13fe MX93_PAD_SD1_DATA6__USDHC1_DATA6 0x13fe MX93_PAD_SD1_DATA7__USDHC1_DATA7 0x13fe - MX93_PAD_SD1_STROBE__USDHC1_STROBE 0x17fe + MX93_PAD_SD1_STROBE__USDHC1_STROBE 0x15fe >; }; @@ -102,7 +102,7 @@ pinctrl_usdhc2: usdhc2grp { fsl,pins = < - MX93_PAD_SD2_CLK__USDHC2_CLK 0x17fe + MX93_PAD_SD2_CLK__USDHC2_CLK 0x15fe MX93_PAD_SD2_CMD__USDHC2_CMD 0x13fe MX93_PAD_SD2_DATA0__USDHC2_DATA0 0x13fe MX93_PAD_SD2_DATA1__USDHC2_DATA1 0x13fe diff --git a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi index 7308f7b6b22c..8bce64069138 100644 --- a/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi +++ b/arch/arm64/boot/dts/marvell/ac5-98dx25xx.dtsi @@ -98,7 +98,7 @@ uart1: serial@12100 { compatible = "snps,dw-apb-uart"; - reg = <0x11000 0x100>; + reg = <0x12100 0x100>; reg-shift = <2>; interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>; reg-io-width = <1>; diff --git a/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi b/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi index 87c90e93667f..79de9cc395c4 100644 --- a/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8992-lg-bullhead.dtsi @@ -3,6 +3,7 @@ * Copyright (c) 2015, LGE Inc. All rights reserved. * Copyright (c) 2016, The Linux Foundation. All rights reserved. * Copyright (c) 2021, Petr Vorel <petr.vorel@gmail.com> + * Copyright (c) 2022, Dominik Kobinski <dominikkobinski314@gmail.com> */ /dts-v1/; @@ -51,6 +52,11 @@ reg = <0 0x03400000 0 0x1200000>; no-map; }; + + removed_region: reserved@5000000 { + reg = <0 0x05000000 0 0x2200000>; + no-map; + }; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts index b242c272d2af..fcca1ba94da6 100644 --- a/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts +++ b/arch/arm64/boot/dts/qcom/msm8992-xiaomi-libra.dts @@ -11,6 +11,12 @@ #include <dt-bindings/gpio/gpio.h> #include <dt-bindings/input/gpio-keys.h> +/delete-node/ &adsp_mem; +/delete-node/ &audio_mem; +/delete-node/ &mpss_mem; +/delete-node/ &peripheral_region; +/delete-node/ &rmtfs_mem; + / { model = "Xiaomi Mi 4C"; compatible = "xiaomi,libra", "qcom,msm8992"; @@ -70,25 +76,67 @@ #size-cells = <2>; ranges; - /* This is for getting crash logs using Android downstream kernels */ - ramoops@dfc00000 { - compatible = "ramoops"; - reg = <0x0 0xdfc00000 0x0 0x40000>; - console-size = <0x10000>; - record-size = <0x10000>; - ftrace-size = <0x10000>; - pmsg-size = <0x20000>; + memory_hole: hole@6400000 { + reg = <0 0x06400000 0 0x600000>; + no-map; + }; + + memory_hole2: hole2@6c00000 { + reg = <0 0x06c00000 0 0x2400000>; + no-map; + }; + + mpss_mem: mpss@9000000 { + reg = <0 0x09000000 0 0x5a00000>; + no-map; + }; + + tzapp: tzapp@ea00000 { + reg = <0 0x0ea00000 0 0x1900000>; + no-map; + }; + + mdm_rfsa_mem: mdm-rfsa@ca0b0000 { + reg = <0 0xca0b0000 0 0x10000>; + no-map; + }; + + rmtfs_mem: rmtfs@ca100000 { + compatible = "qcom,rmtfs-mem"; + reg = <0 0xca100000 0 0x180000>; + no-map; + + qcom,client-id = <1>; }; - modem_region: modem_region@9000000 { - reg = <0x0 0x9000000 0x0 0x5a00000>; + audio_mem: audio@cb400000 { + reg = <0 0xcb000000 0 0x400000>; + no-mem; + }; + + qseecom_mem: qseecom@cb400000 { + reg = <0 0xcb400000 0 0x1c00000>; + no-mem; + }; + + adsp_rfsa_mem: adsp-rfsa@cd000000 { + reg = <0 0xcd000000 0 0x10000>; no-map; }; - tzapp: modem_region@ea00000 { - reg = <0x0 0xea00000 0x0 0x1900000>; + sensor_rfsa_mem: sensor-rfsa@cd010000 { + reg = <0 0xcd010000 0 0x10000>; no-map; }; + + ramoops@dfc00000 { + compatible = "ramoops"; + reg = <0 0xdfc00000 0 0x40000>; + console-size = <0x10000>; + record-size = <0x10000>; + ftrace-size = <0x10000>; + pmsg-size = <0x20000>; + }; }; }; @@ -130,11 +178,6 @@ status = "okay"; }; -&peripheral_region { - reg = <0x0 0x7400000 0x0 0x1c00000>; - no-map; -}; - &pm8994_spmi_regulators { VDD_APC0: s8 { regulator-min-microvolt = <680000>; diff --git a/arch/arm64/boot/dts/qcom/msm8992.dtsi b/arch/arm64/boot/dts/qcom/msm8992.dtsi index 10adb4986ef1..02fc3795dbfd 100644 --- a/arch/arm64/boot/dts/qcom/msm8992.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8992.dtsi @@ -37,10 +37,6 @@ compatible = "qcom,rpmcc-msm8992", "qcom,rpmcc"; }; -&tcsr_mutex { - compatible = "qcom,sfpb-mutex"; -}; - &timer { interrupts = <GIC_PPI 2 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, <GIC_PPI 3 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_LOW)>, diff --git a/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts b/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts index 85abff0e9b3f..7b0f62144c3e 100644 --- a/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts +++ b/arch/arm64/boot/dts/qcom/msm8994-huawei-angler-rev-101.dts @@ -9,9 +9,6 @@ #include "msm8994.dtsi" -/* Angler's firmware does not report where the memory is allocated */ -/delete-node/ &cont_splash_mem; - / { model = "Huawei Nexus 6P"; compatible = "huawei,angler", "qcom,msm8994"; @@ -28,6 +25,22 @@ chosen { stdout-path = "serial0:115200n8"; }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + tzapp_mem: tzapp@4800000 { + reg = <0 0x04800000 0 0x1900000>; + no-map; + }; + + removed_region: reserved@6300000 { + reg = <0 0x06300000 0 0xD00000>; + no-map; + }; + }; }; &blsp1_uart2 { diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi index 109c9d2b684d..71cf81a8eb4d 100644 --- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi +++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi @@ -10,6 +10,7 @@ #include <dt-bindings/interconnect/qcom,sc8280xp.h> #include <dt-bindings/interrupt-controller/arm-gic.h> #include <dt-bindings/mailbox/qcom-ipcc.h> +#include <dt-bindings/phy/phy-qcom-qmp.h> #include <dt-bindings/power/qcom-rpmpd.h> #include <dt-bindings/soc/qcom,rpmh-rsc.h> #include <dt-bindings/thermal/thermal.h> @@ -762,7 +763,7 @@ <0>, <0>, <0>, - <&usb_0_ssphy>, + <&usb_0_qmpphy QMP_USB43DP_USB3_PIPE_CLK>, <0>, <0>, <0>, @@ -770,7 +771,7 @@ <0>, <0>, <0>, - <&usb_1_ssphy>, + <&usb_1_qmpphy QMP_USB43DP_USB3_PIPE_CLK>, <0>, <0>, <0>, @@ -1673,42 +1674,26 @@ }; }; - usb_0_qmpphy: phy-wrapper@88ec000 { + usb_0_qmpphy: phy@88eb000 { compatible = "qcom,sc8280xp-qmp-usb43dp-phy"; - reg = <0 0x088ec000 0 0x1e4>, - <0 0x088eb000 0 0x40>, - <0 0x088ed000 0 0x1c8>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x088eb000 0 0x4000>; clocks = <&gcc GCC_USB3_PRIM_PHY_AUX_CLK>, - <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_USB4_EUD_CLKREF_CLK>, - <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>; - clock-names = "aux", "ref_clk_src", "ref", "com_aux"; + <&gcc GCC_USB3_PRIM_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; + clock-names = "aux", "ref", "com_aux", "usb3_pipe"; + + power-domains = <&gcc USB30_PRIM_GDSC>; resets = <&gcc GCC_USB3_PHY_PRIM_BCR>, - <&gcc GCC_USB3_DP_PHY_PRIM_BCR>; + <&gcc GCC_USB4_DP_PHY_PRIM_BCR>; reset-names = "phy", "common"; - power-domains = <&gcc USB30_PRIM_GDSC>; + #clock-cells = <1>; + #phy-cells = <1>; status = "disabled"; - - usb_0_ssphy: usb3-phy@88eb400 { - reg = <0 0x088eb400 0 0x100>, - <0 0x088eb600 0 0x3ec>, - <0 0x088ec400 0 0x364>, - <0 0x088eba00 0 0x100>, - <0 0x088ebc00 0 0x3ec>, - <0 0x088ec200 0 0x18>; - #phy-cells = <0>; - #clock-cells = <0>; - clocks = <&gcc GCC_USB3_PRIM_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb0_phy_pipe_clk_src"; - }; }; usb_1_hsphy: phy@8902000 { @@ -1725,42 +1710,26 @@ status = "disabled"; }; - usb_1_qmpphy: phy-wrapper@8904000 { + usb_1_qmpphy: phy@8903000 { compatible = "qcom,sc8280xp-qmp-usb43dp-phy"; - reg = <0 0x08904000 0 0x1e4>, - <0 0x08903000 0 0x40>, - <0 0x08905000 0 0x1c8>; - #address-cells = <2>; - #size-cells = <2>; - ranges; + reg = <0 0x08903000 0 0x4000>; clocks = <&gcc GCC_USB3_SEC_PHY_AUX_CLK>, - <&rpmhcc RPMH_CXO_CLK>, <&gcc GCC_USB4_CLKREF_CLK>, - <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>; - clock-names = "aux", "ref_clk_src", "ref", "com_aux"; + <&gcc GCC_USB3_SEC_PHY_COM_AUX_CLK>, + <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; + clock-names = "aux", "ref", "com_aux", "usb3_pipe"; + + power-domains = <&gcc USB30_SEC_GDSC>; resets = <&gcc GCC_USB3_PHY_SEC_BCR>, <&gcc GCC_USB4_1_DP_PHY_PRIM_BCR>; reset-names = "phy", "common"; - power-domains = <&gcc USB30_SEC_GDSC>; + #clock-cells = <1>; + #phy-cells = <1>; status = "disabled"; - - usb_1_ssphy: usb3-phy@8903400 { - reg = <0 0x08903400 0 0x100>, - <0 0x08903600 0 0x3ec>, - <0 0x08904400 0 0x364>, - <0 0x08903a00 0 0x100>, - <0 0x08903c00 0 0x3ec>, - <0 0x08904200 0 0x18>; - #phy-cells = <0>; - #clock-cells = <0>; - clocks = <&gcc GCC_USB3_SEC_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb1_phy_pipe_clk_src"; - }; }; pmu@9091000 { @@ -1910,7 +1879,7 @@ reg = <0 0x0a600000 0 0xcd00>; interrupts = <GIC_SPI 803 IRQ_TYPE_LEVEL_HIGH>; iommus = <&apps_smmu 0x820 0x0>; - phys = <&usb_0_hsphy>, <&usb_0_ssphy>; + phys = <&usb_0_hsphy>, <&usb_0_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; }; }; @@ -1964,7 +1933,7 @@ reg = <0 0x0a800000 0 0xcd00>; interrupts = <GIC_SPI 810 IRQ_TYPE_LEVEL_HIGH>; iommus = <&apps_smmu 0x860 0x0>; - phys = <&usb_1_hsphy>, <&usb_1_ssphy>; + phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>; phy-names = "usb2-phy", "usb3-phy"; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index dab5579946f3..927032863e2f 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -334,7 +334,6 @@ exit-latency-us = <6562>; min-residency-us = <9987>; local-timer-stop; - status = "disabled"; }; }; }; diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi index 245dce24ec59..fb3cd20a82b5 100644 --- a/arch/arm64/boot/dts/qcom/sm8350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi @@ -2382,8 +2382,8 @@ <&rpmhcc RPMH_CXO_CLK>; clock-names = "iface", "core", "xo"; resets = <&gcc GCC_SDCC2_BCR>; - interconnects = <&aggre2_noc MASTER_SDCC_2 0 &mc_virt SLAVE_EBI1 0>, - <&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_SDCC_2 0>; + interconnects = <&aggre2_noc MASTER_SDCC_2 &mc_virt SLAVE_EBI1>, + <&gem_noc MASTER_APPSS_PROC &config_noc SLAVE_SDCC_2>; interconnect-names = "sdhc-ddr","cpu-sdhc"; iommus = <&apps_smmu 0x4a0 0x0>; power-domains = <&rpmhpd SM8350_CX>; diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h index 0890e4f568fb..cbb3d961123b 100644 --- a/arch/arm64/include/asm/atomic_ll_sc.h +++ b/arch/arm64/include/asm/atomic_ll_sc.h @@ -315,7 +315,7 @@ __ll_sc__cmpxchg_double##name(unsigned long old1, \ " cbnz %w0, 1b\n" \ " " #mb "\n" \ "2:" \ - : "=&r" (tmp), "=&r" (ret), "+Q" (*(unsigned long *)ptr) \ + : "=&r" (tmp), "=&r" (ret), "+Q" (*(__uint128_t *)ptr) \ : "r" (old1), "r" (old2), "r" (new1), "r" (new2) \ : cl); \ \ diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h index 52075e93de6c..a94d6dacc029 100644 --- a/arch/arm64/include/asm/atomic_lse.h +++ b/arch/arm64/include/asm/atomic_lse.h @@ -311,7 +311,7 @@ __lse__cmpxchg_double##name(unsigned long old1, \ " eor %[old2], %[old2], %[oldval2]\n" \ " orr %[old1], %[old1], %[old2]" \ : [old1] "+&r" (x0), [old2] "+&r" (x1), \ - [v] "+Q" (*(unsigned long *)ptr) \ + [v] "+Q" (*(__uint128_t *)ptr) \ : [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \ [oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \ : cl); \ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 4e8b66c74ea2..683ca3af4084 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -124,6 +124,8 @@ #define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025 #define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 +#define APPLE_CPU_PART_M2_BLIZZARD 0x032 +#define APPLE_CPU_PART_M2_AVALANCHE 0x033 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -177,6 +179,8 @@ #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) +#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) +#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 31d13a6001df..de4ff90785b2 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -48,8 +48,17 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); }) extern spinlock_t efi_rt_lock; +extern u64 *efi_rt_stack_top; efi_status_t __efi_rt_asm_wrapper(void *, const char *, ...); +/* + * efi_rt_stack_top[-1] contains the value the stack pointer had before + * switching to the EFI runtime stack. + */ +#define current_in_efi() \ + (!preemptible() && efi_rt_stack_top != NULL && \ + on_task_stack(current, READ_ONCE(efi_rt_stack_top[-1]), 1)) + #define ARCH_EFI_IRQ_FLAGS_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) /* diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 15b34fbfca66..206de10524e3 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -114,6 +114,15 @@ #define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) +#define ESR_ELx_FSC_SEA_TTW0 (0x14) +#define ESR_ELx_FSC_SEA_TTW1 (0x15) +#define ESR_ELx_FSC_SEA_TTW2 (0x16) +#define ESR_ELx_FSC_SEA_TTW3 (0x17) +#define ESR_ELx_FSC_SECC (0x18) +#define ESR_ELx_FSC_SECC_TTW0 (0x1c) +#define ESR_ELx_FSC_SECC_TTW1 (0x1d) +#define ESR_ELx_FSC_SECC_TTW2 (0x1e) +#define ESR_ELx_FSC_SECC_TTW3 (0x1f) /* ISS field definitions for Data Aborts */ #define ESR_ELx_ISV_SHIFT (24) diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index d20f5da2d76f..6a4a1ab8eb23 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep); void __init arm64_hugetlb_cma_reserve(void); +#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start +extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit +extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); + #include <asm-generic/hugetlb.h> #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 0df3fc3a0173..26b0c97df986 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -319,21 +319,6 @@ BIT(18) | \ GENMASK(16, 15)) -/* For compatibility with fault code shared with 32-bit */ -#define FSC_FAULT ESR_ELx_FSC_FAULT -#define FSC_ACCESS ESR_ELx_FSC_ACCESS -#define FSC_PERM ESR_ELx_FSC_PERM -#define FSC_SEA ESR_ELx_FSC_EXTABT -#define FSC_SEA_TTW0 (0x14) -#define FSC_SEA_TTW1 (0x15) -#define FSC_SEA_TTW2 (0x16) -#define FSC_SEA_TTW3 (0x17) -#define FSC_SECC (0x18) -#define FSC_SECC_TTW0 (0x1c) -#define FSC_SECC_TTW1 (0x1d) -#define FSC_SECC_TTW2 (0x1e) -#define FSC_SECC_TTW3 (0x1f) - /* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */ #define HPFAR_MASK (~UL(0xf)) /* diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 9bdba47f7e14..193583df2d9c 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -349,16 +349,16 @@ static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *v static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { - case FSC_SEA: - case FSC_SEA_TTW0: - case FSC_SEA_TTW1: - case FSC_SEA_TTW2: - case FSC_SEA_TTW3: - case FSC_SECC: - case FSC_SECC_TTW0: - case FSC_SECC_TTW1: - case FSC_SECC_TTW2: - case FSC_SECC_TTW3: + case ESR_ELx_FSC_EXTABT: + case ESR_ELx_FSC_SEA_TTW0: + case ESR_ELx_FSC_SEA_TTW1: + case ESR_ELx_FSC_SEA_TTW2: + case ESR_ELx_FSC_SEA_TTW3: + case ESR_ELx_FSC_SECC: + case ESR_ELx_FSC_SECC_TTW0: + case ESR_ELx_FSC_SECC_TTW1: + case ESR_ELx_FSC_SECC_TTW2: + case ESR_ELx_FSC_SECC_TTW3: return true; default: return false; @@ -373,8 +373,26 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_abt_iss1tw(vcpu)) - return true; + if (kvm_vcpu_abt_iss1tw(vcpu)) { + /* + * Only a permission fault on a S1PTW should be + * considered as a write. Otherwise, page tables baked + * in a read-only memslot will result in an exception + * being delivered in the guest. + * + * The drawback is that we end-up faulting twice if the + * guest is using any of HW AF/DB: a translation fault + * to map the page containing the PT (read only at + * first), then a permission fault to allow the flags + * to be set. + */ + switch (kvm_vcpu_trap_get_fault_type(vcpu)) { + case ESR_ELx_FSC_PERM: + return true; + default: + return false; + } + } if (kvm_vcpu_trap_is_iabt(vcpu)) return false; diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 35a159d131b5..113e20fdbb56 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -66,8 +66,8 @@ enum kvm_mode kvm_get_mode(void); DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); -extern unsigned int kvm_sve_max_vl; -int kvm_arm_init_sve(void); +extern unsigned int __ro_after_init kvm_sve_max_vl; +int __init kvm_arm_init_sve(void); u32 __attribute_const__ kvm_target_cpu(void); int kvm_reset_vcpu(struct kvm_vcpu *vcpu); @@ -877,7 +877,7 @@ int kvm_handle_cp10_id(struct kvm_vcpu *vcpu); void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); -int kvm_sys_reg_table_init(void); +int __init kvm_sys_reg_table_init(void); /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); @@ -908,9 +908,9 @@ int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); -extern unsigned int kvm_arm_vmid_bits; -int kvm_arm_vmid_alloc_init(void); -void kvm_arm_vmid_alloc_free(void); +extern unsigned int __ro_after_init kvm_arm_vmid_bits; +int __init kvm_arm_vmid_alloc_init(void); +void __init kvm_arm_vmid_alloc_free(void); void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid); void kvm_arm_vmid_clear_active(void); @@ -943,7 +943,6 @@ static inline bool kvm_system_needs_idmapped_vectors(void) void kvm_arm_vcpu_ptrauth_trap(struct kvm_vcpu *vcpu); -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} @@ -994,7 +993,7 @@ static inline void kvm_clr_pmu_events(u32 clr) {} void kvm_vcpu_load_sysregs_vhe(struct kvm_vcpu *vcpu); void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu); -int kvm_set_ipa_limit(void); +int __init kvm_set_ipa_limit(void); #define __KVM_HAVE_ARCH_VM_ALLOC struct kvm *kvm_arch_alloc_vm(void); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index e4a7e6369499..7f7c1231679e 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -163,7 +163,7 @@ int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, void __iomem **haddr); int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, void **haddr); -void free_hyp_pgds(void); +void __init free_hyp_pgds(void); void stage2_unmap_vm(struct kvm *kvm); int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu, unsigned long type); @@ -175,7 +175,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu); phys_addr_t kvm_mmu_get_httbr(void); phys_addr_t kvm_get_idmap_vector(void); -int kvm_mmu_init(u32 *hyp_va_bits); +int __init kvm_mmu_init(u32 *hyp_va_bits); static inline void *__kvm_vector_slot2addr(void *base, enum arm64_hyp_spectre_vector slot) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b4bbeed80fb6..65e78999c75d 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -681,7 +681,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) - +#define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) static inline void set_pud(pud_t *pudp, pud_t pud) { @@ -730,6 +730,7 @@ static inline pmd_t *pud_pgtable(pud_t pud) #else #define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) +#define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */ /* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */ #define pmd_set_fixmap(addr) NULL @@ -862,12 +863,12 @@ static inline bool pte_user_accessible_page(pte_t pte) static inline bool pmd_user_accessible_page(pmd_t pmd) { - return pmd_leaf(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); + return pmd_leaf(pmd) && !pmd_present_invalid(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); } static inline bool pud_user_accessible_page(pud_t pud) { - return pud_leaf(pud) && pud_user(pud); + return pud_leaf(pud) && (pud_user(pud) || pud_user_exec(pud)); } #endif @@ -1093,6 +1094,15 @@ static inline bool pud_sect_supported(void) } +#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +#define ptep_modify_prot_start ptep_modify_prot_start +extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define ptep_modify_prot_commit ptep_modify_prot_commit +extern void ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 4e5354beafb0..66ec8caa6ac0 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -106,4 +106,19 @@ static inline struct stack_info stackinfo_get_sdei_critical(void) #define stackinfo_get_sdei_critical() stackinfo_get_unknown() #endif +#ifdef CONFIG_EFI +extern u64 *efi_rt_stack_top; + +static inline struct stack_info stackinfo_get_efi(void) +{ + unsigned long high = (u64)efi_rt_stack_top; + unsigned long low = high - THREAD_SIZE; + + return (struct stack_info) { + .low = low, + .high = high, + }; +} +#endif + #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index ba4bff5ca674..2b09495499c6 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -16,7 +16,7 @@ #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE #define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES -typedef u32 uprobe_opcode_t; +typedef __le32 uprobe_opcode_t; struct arch_uprobe_task { }; diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 89ac00084f38..307faa2b4395 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2645198 + { + .desc = "ARM erratum 2645198", + .capability = ARM64_WORKAROUND_2645198, + ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715) + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2077057 { .desc = "ARM erratum 2077057", diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index a00886410537..e8ae803662cf 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -4,6 +4,7 @@ */ #include <linux/linkage.h> +#include <asm/assembler.h> SYM_FUNC_START(__efi_rt_asm_wrapper) stp x29, x30, [sp, #-112]! @@ -45,7 +46,10 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) mov x4, x6 blr x8 + mov x16, sp mov sp, x29 + str xzr, [x16, #8] // clear recorded task SP value + ldp x1, x2, [sp, #16] cmp x2, x18 ldp x29, x30, [sp], #112 @@ -70,6 +74,9 @@ SYM_FUNC_END(__efi_rt_asm_wrapper) SYM_CODE_START(__efi_rt_asm_recover) mov sp, x30 + ldr_l x16, efi_rt_stack_top // clear recorded task SP value + str xzr, [x16, #-8] + ldp x19, x20, [sp, #32] ldp x21, x22, [sp, #48] ldp x23, x24, [sp, #64] diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index fab05de2e12d..b273900f4566 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <asm/efi.h> +#include <asm/stacktrace.h> static bool region_is_misaligned(const efi_memory_desc_t *md) { @@ -154,7 +155,7 @@ asmlinkage efi_status_t __efi_rt_asm_recover(void); bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) { /* Check whether the exception occurred while running the firmware */ - if (current_work() != &efi_rts_work.work || regs->pc >= TASK_SIZE_64) + if (!current_in_efi() || regs->pc >= TASK_SIZE_64) return false; pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg); diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 353009d7f307..2e94d20c4ac7 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -8,28 +8,27 @@ #include <asm/cpufeature.h> #include <asm/mte.h> -#define for_each_mte_vma(vmi, vma) \ +#define for_each_mte_vma(cprm, i, m) \ if (system_supports_mte()) \ - for_each_vma(vmi, vma) \ - if (vma->vm_flags & VM_MTE) + for (i = 0, m = cprm->vma_meta; \ + i < cprm->vma_count; \ + i++, m = cprm->vma_meta + i) \ + if (m->flags & VM_MTE) -static unsigned long mte_vma_tag_dump_size(struct vm_area_struct *vma) +static unsigned long mte_vma_tag_dump_size(struct core_vma_metadata *m) { - if (vma->vm_flags & VM_DONTDUMP) - return 0; - - return vma_pages(vma) * MTE_PAGE_TAG_STORAGE; + return (m->dump_size >> PAGE_SHIFT) * MTE_PAGE_TAG_STORAGE; } /* Derived from dump_user_range(); start/end must be page-aligned */ static int mte_dump_tag_range(struct coredump_params *cprm, - unsigned long start, unsigned long end) + unsigned long start, unsigned long len) { int ret = 1; unsigned long addr; void *tags = NULL; - for (addr = start; addr < end; addr += PAGE_SIZE) { + for (addr = start; addr < start + len; addr += PAGE_SIZE) { struct page *page = get_dump_page(addr); /* @@ -65,7 +64,6 @@ static int mte_dump_tag_range(struct coredump_params *cprm, mte_save_page_tags(page_address(page), tags); put_page(page); if (!dump_emit(cprm, tags, MTE_PAGE_TAG_STORAGE)) { - mte_free_tag_storage(tags); ret = 0; break; } @@ -77,13 +75,13 @@ static int mte_dump_tag_range(struct coredump_params *cprm, return ret; } -Elf_Half elf_core_extra_phdrs(void) +Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm) { - struct vm_area_struct *vma; + int i; + struct core_vma_metadata *m; int vma_count = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) + for_each_mte_vma(cprm, i, m) vma_count++; return vma_count; @@ -91,18 +89,18 @@ Elf_Half elf_core_extra_phdrs(void) int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) { - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); + int i; + struct core_vma_metadata *m; - for_each_mte_vma(vmi, vma) { + for_each_mte_vma(cprm, i, m) { struct elf_phdr phdr; phdr.p_type = PT_AARCH64_MEMTAG_MTE; phdr.p_offset = offset; - phdr.p_vaddr = vma->vm_start; + phdr.p_vaddr = m->start; phdr.p_paddr = 0; - phdr.p_filesz = mte_vma_tag_dump_size(vma); - phdr.p_memsz = vma->vm_end - vma->vm_start; + phdr.p_filesz = mte_vma_tag_dump_size(m); + phdr.p_memsz = m->end - m->start; offset += phdr.p_filesz; phdr.p_flags = 0; phdr.p_align = 0; @@ -114,28 +112,25 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { - struct vm_area_struct *vma; + int i; + struct core_vma_metadata *m; size_t data_size = 0; - VMA_ITERATOR(vmi, current->mm, 0); - for_each_mte_vma(vmi, vma) - data_size += mte_vma_tag_dump_size(vma); + for_each_mte_vma(cprm, i, m) + data_size += mte_vma_tag_dump_size(m); return data_size; } int elf_core_write_extra_data(struct coredump_params *cprm) { - struct vm_area_struct *vma; - VMA_ITERATOR(vmi, current->mm, 0); - - for_each_mte_vma(vmi, vma) { - if (vma->vm_flags & VM_DONTDUMP) - continue; + int i; + struct core_vma_metadata *m; - if (!mte_dump_tag_range(cprm, vma->vm_start, vma->vm_end)) + for_each_mte_vma(cprm, i, m) { + if (!mte_dump_tag_range(cprm, m->start, m->dump_size)) return 0; } diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index dcc81e7200d4..b6ef1af0122e 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -385,7 +385,7 @@ static void task_fpsimd_load(void) WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); - if (system_supports_sve()) { + if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { case FP_STATE_FPSIMD: /* Stop tracking SVE for this task until next use. */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 2686ab157601..0c321ad23cd3 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -1357,7 +1357,7 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif -#ifdef CONFIG_ARM64_SVE +#ifdef CONFIG_ARM64_SME REGSET_SSVE, REGSET_ZA, #endif diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index e0d09bf5b01b..be279fd48248 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -281,7 +281,12 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) vl = task_get_sme_vl(current); } else { - if (!system_supports_sve()) + /* + * A SME only system use SVE for streaming mode so can + * have a SVE formatted context with a zero VL and no + * payload data. + */ + if (!system_supports_sve() && !system_supports_sme()) return -EINVAL; vl = task_get_sve_vl(current); @@ -732,7 +737,7 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; } - if (system_supports_sve()) { + if (system_supports_sve() || system_supports_sme()) { unsigned int vq = 0; if (add_all || test_thread_flag(TIF_SVE) || diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 117e2c180f3c..83154303e682 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -5,6 +5,7 @@ * Copyright (C) 2012 ARM Ltd. */ #include <linux/kernel.h> +#include <linux/efi.h> #include <linux/export.h> #include <linux/ftrace.h> #include <linux/sched.h> @@ -12,6 +13,7 @@ #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> +#include <asm/efi.h> #include <asm/irq.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> @@ -186,6 +188,13 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) : stackinfo_get_unknown(); \ }) +#define STACKINFO_EFI \ + ({ \ + ((task == current) && current_in_efi()) \ + ? stackinfo_get_efi() \ + : stackinfo_get_unknown(); \ + }) + noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) @@ -200,6 +209,9 @@ noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, STACKINFO_SDEI(normal), STACKINFO_SDEI(critical), #endif +#ifdef CONFIG_EFI + STACKINFO_EFI, +#endif }; struct unwind_state state = { .stacks = stacks, diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 05da3c8f7e88..ca6eadeb7d1a 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -21,6 +21,7 @@ if VIRTUALIZATION menuconfig KVM bool "Kernel-based Virtual Machine (KVM) support" depends on HAVE_KVM + select KVM_GENERIC_HARDWARE_ENABLING select MMU_NOTIFIER select PREEMPT_NOTIFIERS select HAVE_KVM_CPU_RELAX_INTERCEPT diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index bb24a76b4224..23346585a294 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -811,10 +811,18 @@ void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu) ptimer->host_timer_irq_flags = host_ptimer_irq_flags; } -static void kvm_timer_init_interrupt(void *info) +void kvm_timer_cpu_up(void) { enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags); - enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); + if (host_ptimer_irq) + enable_percpu_irq(host_ptimer_irq, host_ptimer_irq_flags); +} + +void kvm_timer_cpu_down(void) +{ + disable_percpu_irq(host_vtimer_irq); + if (host_ptimer_irq) + disable_percpu_irq(host_ptimer_irq); } int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value) @@ -976,18 +984,6 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, preempt_enable(); } -static int kvm_timer_starting_cpu(unsigned int cpu) -{ - kvm_timer_init_interrupt(NULL); - return 0; -} - -static int kvm_timer_dying_cpu(unsigned int cpu) -{ - disable_percpu_irq(host_vtimer_irq); - return 0; -} - static int timer_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) { if (vcpu) @@ -1117,7 +1113,7 @@ static int kvm_irq_init(struct arch_timer_kvm_info *info) return 0; } -int kvm_timer_hyp_init(bool has_gic) +int __init kvm_timer_hyp_init(bool has_gic) { struct arch_timer_kvm_info *info; int err; @@ -1185,9 +1181,6 @@ int kvm_timer_hyp_init(bool has_gic) goto out_free_irq; } - cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING, - "kvm/arm/timer:starting", kvm_timer_starting_cpu, - kvm_timer_dying_cpu); return 0; out_free_irq: free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus()); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 9c5573bc4614..698787ed87e9 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -63,16 +63,6 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; } -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -1539,7 +1529,7 @@ static int kvm_init_vector_slots(void) return 0; } -static void cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) +static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); unsigned long tcr; @@ -1682,7 +1672,15 @@ static void _kvm_arch_hardware_enable(void *discard) int kvm_arch_hardware_enable(void) { + int was_enabled = __this_cpu_read(kvm_arm_hardware_enabled); + _kvm_arch_hardware_enable(NULL); + + if (!was_enabled) { + kvm_vgic_cpu_up(); + kvm_timer_cpu_up(); + } + return 0; } @@ -1696,6 +1694,11 @@ static void _kvm_arch_hardware_disable(void *discard) void kvm_arch_hardware_disable(void) { + if (__this_cpu_read(kvm_arm_hardware_enabled)) { + kvm_timer_cpu_down(); + kvm_vgic_cpu_down(); + } + if (!is_protected_kvm_enabled()) _kvm_arch_hardware_disable(NULL); } @@ -1738,26 +1741,26 @@ static struct notifier_block hyp_init_cpu_pm_nb = { .notifier_call = hyp_init_cpu_pm_notifier, }; -static void hyp_cpu_pm_init(void) +static void __init hyp_cpu_pm_init(void) { if (!is_protected_kvm_enabled()) cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); } -static void hyp_cpu_pm_exit(void) +static void __init hyp_cpu_pm_exit(void) { if (!is_protected_kvm_enabled()) cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb); } #else -static inline void hyp_cpu_pm_init(void) +static inline void __init hyp_cpu_pm_init(void) { } -static inline void hyp_cpu_pm_exit(void) +static inline void __init hyp_cpu_pm_exit(void) { } #endif -static void init_cpu_logical_map(void) +static void __init init_cpu_logical_map(void) { unsigned int cpu; @@ -1774,7 +1777,7 @@ static void init_cpu_logical_map(void) #define init_psci_0_1_impl_state(config, what) \ config.psci_0_1_ ## what ## _implemented = psci_ops.what -static bool init_psci_relay(void) +static bool __init init_psci_relay(void) { /* * If PSCI has not been initialized, protected KVM cannot install @@ -1797,7 +1800,7 @@ static bool init_psci_relay(void) return true; } -static int init_subsystems(void) +static int __init init_subsystems(void) { int err = 0; @@ -1838,13 +1841,22 @@ static int init_subsystems(void) kvm_register_perf_callbacks(NULL); out: + if (err) + hyp_cpu_pm_exit(); + if (err || !is_protected_kvm_enabled()) on_each_cpu(_kvm_arch_hardware_disable, NULL, 1); return err; } -static void teardown_hyp_mode(void) +static void __init teardown_subsystems(void) +{ + kvm_unregister_perf_callbacks(); + hyp_cpu_pm_exit(); +} + +static void __init teardown_hyp_mode(void) { int cpu; @@ -1855,7 +1867,7 @@ static void teardown_hyp_mode(void) } } -static int do_pkvm_init(u32 hyp_va_bits) +static int __init do_pkvm_init(u32 hyp_va_bits) { void *per_cpu_base = kvm_ksym_ref(kvm_nvhe_sym(kvm_arm_hyp_percpu_base)); int ret; @@ -1891,7 +1903,7 @@ static void kvm_hyp_init_symbols(void) kvm_nvhe_sym(kvm_arm_vmid_bits) = kvm_arm_vmid_bits; } -static int kvm_hyp_init_protection(u32 hyp_va_bits) +static int __init kvm_hyp_init_protection(u32 hyp_va_bits) { void *addr = phys_to_virt(hyp_mem_base); int ret; @@ -1912,7 +1924,7 @@ static int kvm_hyp_init_protection(u32 hyp_va_bits) /** * Inits Hyp-mode on all online CPUs */ -static int init_hyp_mode(void) +static int __init init_hyp_mode(void) { u32 hyp_va_bits; int cpu; @@ -2094,7 +2106,7 @@ out_err: return err; } -static void _kvm_host_prot_finalize(void *arg) +static void __init _kvm_host_prot_finalize(void *arg) { int *err = arg; @@ -2102,7 +2114,7 @@ static void _kvm_host_prot_finalize(void *arg) WRITE_ONCE(*err, -EINVAL); } -static int pkvm_drop_host_privileges(void) +static int __init pkvm_drop_host_privileges(void) { int ret = 0; @@ -2115,7 +2127,7 @@ static int pkvm_drop_host_privileges(void) return ret; } -static int finalize_hyp_mode(void) +static int __init finalize_hyp_mode(void) { if (!is_protected_kvm_enabled()) return 0; @@ -2190,7 +2202,7 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons) /** * Initialize Hyp-mode and memory mappings on all CPUs. */ -int kvm_arch_init(void *opaque) +static __init int kvm_arm_init(void) { int err; bool in_hyp_mode; @@ -2241,7 +2253,7 @@ int kvm_arch_init(void *opaque) err = kvm_init_vector_slots(); if (err) { kvm_err("Cannot initialise vector slots\n"); - goto out_err; + goto out_hyp; } err = init_subsystems(); @@ -2252,7 +2264,7 @@ int kvm_arch_init(void *opaque) err = finalize_hyp_mode(); if (err) { kvm_err("Failed to finalize Hyp protection\n"); - goto out_hyp; + goto out_subs; } } @@ -2264,10 +2276,19 @@ int kvm_arch_init(void *opaque) kvm_info("Hyp mode initialized successfully\n"); } + /* + * FIXME: Do something reasonable if kvm_init() fails after pKVM + * hypervisor protection is finalized. + */ + err = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (err) + goto out_subs; + return 0; +out_subs: + teardown_subsystems(); out_hyp: - hyp_cpu_pm_exit(); if (!in_hyp_mode) teardown_hyp_mode(); out_err: @@ -2275,12 +2296,6 @@ out_err: return err; } -/* NOP: Compiling as a module not supported */ -void kvm_arch_exit(void) -{ - kvm_unregister_perf_callbacks(); -} - static int __init early_kvm_mode_cfg(char *arg) { if (!arg) @@ -2319,10 +2334,4 @@ enum kvm_mode kvm_get_mode(void) return kvm_mode; } -static int arm_init(void) -{ - int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); - return rc; -} - -module_init(arm_init); +module_init(kvm_arm_init); diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 5626ddb540ce..cf4c495a4321 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -1079,7 +1079,7 @@ long kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, /* uaccess failed, don't leave stale tags */ if (num_tags != MTE_GRANULES_PER_PAGE) - mte_clear_page_tags(page); + mte_clear_page_tags(maddr); set_page_mte_tagged(page); kvm_release_pfn_dirty(pfn); diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h index 1b8a2dcd712f..9ddcfe2c3e57 100644 --- a/arch/arm64/kvm/hyp/include/hyp/fault.h +++ b/arch/arm64/kvm/hyp/include/hyp/fault.h @@ -60,7 +60,7 @@ static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault) */ if (!(esr & ESR_ELx_S1PTW) && (cpus_have_final_cap(ARM64_WORKAROUND_834220) || - (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { + (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_PERM)) { if (!__translate_far_to_hpfar(far, &hpfar)) return false; } else { diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 3330d1b76bdd..07d37ff88a3f 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -367,7 +367,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) if (static_branch_unlikely(&vgic_v2_cpuif_trap)) { bool valid; - valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && + valid = kvm_vcpu_trap_get_fault_type(vcpu) == ESR_ELx_FSC_FAULT && kvm_vcpu_dabt_isvalid(vcpu) && !kvm_vcpu_abt_issea(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 31d7fa4c7c14..01352f5838a0 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -25,11 +25,11 @@ static struct kvm_pgtable *hyp_pgtable; static DEFINE_MUTEX(kvm_hyp_pgd_mutex); -static unsigned long hyp_idmap_start; -static unsigned long hyp_idmap_end; -static phys_addr_t hyp_idmap_vector; +static unsigned long __ro_after_init hyp_idmap_start; +static unsigned long __ro_after_init hyp_idmap_end; +static phys_addr_t __ro_after_init hyp_idmap_vector; -static unsigned long io_map_base; +static unsigned long __ro_after_init io_map_base; static phys_addr_t stage2_range_addr_end(phys_addr_t addr, phys_addr_t end) { @@ -280,7 +280,7 @@ static void stage2_flush_vm(struct kvm *kvm) /** * free_hyp_pgds - free Hyp-mode page tables */ -void free_hyp_pgds(void) +void __init free_hyp_pgds(void) { mutex_lock(&kvm_hyp_pgd_mutex); if (hyp_pgtable) { @@ -1212,7 +1212,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu); VM_BUG_ON(write_fault && exec_fault); - if (fault_status == FSC_PERM && !write_fault && !exec_fault) { + if (fault_status == ESR_ELx_FSC_PERM && !write_fault && !exec_fault) { kvm_err("Unexpected L2 read permission error\n"); return -EFAULT; } @@ -1277,7 +1277,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * only exception to this is when dirty logging is enabled at runtime * and a write fault needs to collapse a block entry into a table. */ - if (fault_status != FSC_PERM || (logging_active && write_fault)) { + if (fault_status != ESR_ELx_FSC_PERM || + (logging_active && write_fault)) { ret = kvm_mmu_topup_memory_cache(memcache, kvm_mmu_cache_min_pages(kvm)); if (ret) @@ -1342,7 +1343,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * backed by a THP and thus use block mapping if possible. */ if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) { - if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE) + if (fault_status == ESR_ELx_FSC_PERM && + fault_granule > PAGE_SIZE) vma_pagesize = fault_granule; else vma_pagesize = transparent_hugepage_adjust(kvm, memslot, @@ -1350,7 +1352,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, &fault_ipa); } - if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) { + if (fault_status != ESR_ELx_FSC_PERM && !device && kvm_has_mte(kvm)) { /* Check the VMM hasn't introduced a new disallowed VMA */ if (kvm_vma_mte_allowed(vma)) { sanitise_mte_tags(kvm, pfn, vma_pagesize); @@ -1376,7 +1378,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, * permissions only if vma_pagesize equals fault_granule. Otherwise, * kvm_pgtable_stage2_map() should be called to change block size. */ - if (fault_status == FSC_PERM && vma_pagesize == fault_granule) + if (fault_status == ESR_ELx_FSC_PERM && vma_pagesize == fault_granule) ret = kvm_pgtable_stage2_relax_perms(pgt, fault_ipa, prot); else ret = kvm_pgtable_stage2_map(pgt, fault_ipa, vma_pagesize, @@ -1441,7 +1443,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); is_iabt = kvm_vcpu_trap_is_iabt(vcpu); - if (fault_status == FSC_FAULT) { + if (fault_status == ESR_ELx_FSC_FAULT) { /* Beyond sanitised PARange (which is the IPA limit) */ if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit())) { kvm_inject_size_fault(vcpu); @@ -1476,8 +1478,9 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) kvm_vcpu_get_hfar(vcpu), fault_ipa); /* Check the stage-2 fault is trans. fault or write fault */ - if (fault_status != FSC_FAULT && fault_status != FSC_PERM && - fault_status != FSC_ACCESS) { + if (fault_status != ESR_ELx_FSC_FAULT && + fault_status != ESR_ELx_FSC_PERM && + fault_status != ESR_ELx_FSC_ACCESS) { kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n", kvm_vcpu_trap_get_class(vcpu), (unsigned long)kvm_vcpu_trap_get_fault(vcpu), @@ -1539,7 +1542,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu) /* Userspace should not be able to register out-of-bounds IPAs */ VM_BUG_ON(fault_ipa >= kvm_phys_size(vcpu->kvm)); - if (fault_status == FSC_ACCESS) { + if (fault_status == ESR_ELx_FSC_ACCESS) { handle_access_fault(vcpu, fault_ipa); ret = 1; goto out_unlock; @@ -1665,7 +1668,7 @@ static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = { .virt_to_phys = kvm_host_pa, }; -int kvm_mmu_init(u32 *hyp_va_bits) +int __init kvm_mmu_init(u32 *hyp_va_bits) { int err; u32 idmap_bits; diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index e0267f672b8a..2bc74739a6df 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -30,7 +30,7 @@ #include <asm/virt.h> /* Maximum phys_shift supported for any VM on this host */ -static u32 kvm_ipa_limit; +static u32 __ro_after_init kvm_ipa_limit; /* * ARMv8 Reset Values @@ -41,9 +41,9 @@ static u32 kvm_ipa_limit; #define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ PSR_AA32_I_BIT | PSR_AA32_F_BIT) -unsigned int kvm_sve_max_vl; +unsigned int __ro_after_init kvm_sve_max_vl; -int kvm_arm_init_sve(void) +int __init kvm_arm_init_sve(void) { if (system_supports_sve()) { kvm_sve_max_vl = sve_max_virtualisable_vl(); @@ -352,7 +352,7 @@ u32 get_kvm_ipa_limit(void) return kvm_ipa_limit; } -int kvm_set_ipa_limit(void) +int __init kvm_set_ipa_limit(void) { unsigned int parange; u64 mmfr0; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index d5ee52d6bf73..46d161fe08d3 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -82,7 +82,7 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg) } /* 3 bits per cache level, as per CLIDR, but non-existent caches always 0 */ -static u32 cache_levels; +static u32 __ro_after_init cache_levels; /* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */ #define CSSELR_MAX 14 @@ -646,7 +646,7 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) return; /* Only preserve PMCR_EL0.N, and reset the rest to 0 */ - pmcr = read_sysreg(pmcr_el0) & ARMV8_PMU_PMCR_N_MASK; + pmcr = read_sysreg(pmcr_el0) & (ARMV8_PMU_PMCR_N_MASK << ARMV8_PMU_PMCR_N_SHIFT); if (!kvm_supports_32bit_el0()) pmcr |= ARMV8_PMU_PMCR_LC; @@ -2733,7 +2733,7 @@ static void get_ctr_el0(struct kvm_vcpu *v, const struct sys_reg_desc *r) } /* ->val is filled in by kvm_sys_reg_table_init() */ -static struct sys_reg_desc invariant_sys_regs[] = { +static struct sys_reg_desc invariant_sys_regs[] __ro_after_init = { { SYS_DESC(SYS_MIDR_EL1), NULL, get_midr_el1 }, { SYS_DESC(SYS_REVIDR_EL1), NULL, get_revidr_el1 }, { SYS_DESC(SYS_CLIDR_EL1), NULL, get_clidr_el1 }, @@ -3057,7 +3057,7 @@ int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) return write_demux_regids(uindices); } -int kvm_sys_reg_table_init(void) +int __init kvm_sys_reg_table_init(void) { bool valid = true; unsigned int i; diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index f6d4f4052555..6c7f6ae21ec0 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -465,17 +465,15 @@ out: /* GENERIC PROBE */ -static int vgic_init_cpu_starting(unsigned int cpu) +void kvm_vgic_cpu_up(void) { enable_percpu_irq(kvm_vgic_global_state.maint_irq, 0); - return 0; } -static int vgic_init_cpu_dying(unsigned int cpu) +void kvm_vgic_cpu_down(void) { disable_percpu_irq(kvm_vgic_global_state.maint_irq); - return 0; } static irqreturn_t vgic_maintenance_handler(int irq, void *data) @@ -584,19 +582,6 @@ int kvm_vgic_hyp_init(void) return ret; } - ret = cpuhp_setup_state(CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, - "kvm/arm/vgic:starting", - vgic_init_cpu_starting, vgic_init_cpu_dying); - if (ret) { - kvm_err("Cannot register vgic CPU notifier\n"); - goto out_free_irq; - } - kvm_info("vgic interrupt IRQ%d\n", kvm_vgic_global_state.maint_irq); return 0; - -out_free_irq: - free_percpu_irq(kvm_vgic_global_state.maint_irq, - kvm_get_running_vcpus()); - return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 94a666dd1443..2642e9ce2819 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2187,7 +2187,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev, ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) | ite->collection->collection_id; val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, gpa, &val, ite_esz); + return vgic_write_guest_lock(kvm, gpa, &val, ite_esz); } /** @@ -2339,7 +2339,7 @@ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev, (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) | (dev->num_eventid_bits - 1)); val = cpu_to_le64(val); - return kvm_write_guest_lock(kvm, ptr, &val, dte_esz); + return vgic_write_guest_lock(kvm, ptr, &val, dte_esz); } /** @@ -2526,7 +2526,7 @@ static int vgic_its_save_cte(struct vgic_its *its, ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) | collection->collection_id); val = cpu_to_le64(val); - return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz); + return vgic_write_guest_lock(its->dev->kvm, gpa, &val, esz); } /* @@ -2607,7 +2607,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its) */ val = 0; BUG_ON(cte_esz > sizeof(val)); - ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); + ret = vgic_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz); return ret; } @@ -2743,7 +2743,6 @@ static int vgic_its_has_attr(struct kvm_device *dev, static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) { const struct vgic_its_abi *abi = vgic_its_get_abi(its); - struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; if (attr == KVM_DEV_ARM_VGIC_CTRL_INIT) /* Nothing to do */ @@ -2763,9 +2762,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) vgic_its_reset(kvm, its); break; case KVM_DEV_ARM_ITS_SAVE_TABLES: - dist->save_its_tables_in_progress = true; ret = abi->save_tables(its); - dist->save_its_tables_in_progress = false; break; case KVM_DEV_ARM_ITS_RESTORE_TABLES: ret = abi->restore_tables(its); @@ -2792,7 +2789,7 @@ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; - return dist->save_its_tables_in_progress; + return dist->table_write_in_progress; } static int vgic_its_set_attr(struct kvm_device *dev, diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 826ff6f2a4e7..684bdfaad4a9 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -339,7 +339,7 @@ retry: if (status) { /* clear consumed data */ val &= ~(1 << bit_nr); - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } @@ -350,26 +350,23 @@ retry: * The deactivation of the doorbell interrupt will trigger the * unmapping of the associated vPE. */ -static void unmap_all_vpes(struct vgic_dist *dist) +static void unmap_all_vpes(struct kvm *kvm) { - struct irq_desc *desc; + struct vgic_dist *dist = &kvm->arch.vgic; int i; - for (i = 0; i < dist->its_vm.nr_vpes; i++) { - desc = irq_to_desc(dist->its_vm.vpes[i]->irq); - irq_domain_deactivate_irq(irq_desc_get_irq_data(desc)); - } + for (i = 0; i < dist->its_vm.nr_vpes; i++) + free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i)); } -static void map_all_vpes(struct vgic_dist *dist) +static void map_all_vpes(struct kvm *kvm) { - struct irq_desc *desc; + struct vgic_dist *dist = &kvm->arch.vgic; int i; - for (i = 0; i < dist->its_vm.nr_vpes; i++) { - desc = irq_to_desc(dist->its_vm.vpes[i]->irq); - irq_domain_activate_irq(irq_desc_get_irq_data(desc), false); - } + for (i = 0; i < dist->its_vm.nr_vpes; i++) + WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i), + dist->its_vm.vpes[i]->irq)); } /** @@ -394,7 +391,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) * and enabling of the doorbells have already been done. */ if (kvm_vgic_global_state.has_gicv4_1) { - unmap_all_vpes(dist); + unmap_all_vpes(kvm); vlpi_avail = true; } @@ -437,14 +434,14 @@ int vgic_v3_save_pending_tables(struct kvm *kvm) else val &= ~(1 << bit_nr); - ret = kvm_write_guest_lock(kvm, ptr, &val, 1); + ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; } out: if (vlpi_avail) - map_all_vpes(dist); + map_all_vpes(kvm); return ret; } @@ -616,6 +613,8 @@ static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), {}, }; diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index ad06ba6c9b00..a413718be92b 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -222,6 +222,11 @@ void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val) *val = !!(*ptr & mask); } +int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq) +{ + return request_irq(irq, vgic_v4_doorbell_handler, 0, "vcpu", vcpu); +} + /** * vgic_v4_init - Initialize the GICv4 data structures * @kvm: Pointer to the VM being initialized @@ -283,8 +288,7 @@ int vgic_v4_init(struct kvm *kvm) irq_flags &= ~IRQ_NOAUTOEN; irq_set_status_flags(irq, irq_flags); - ret = request_irq(irq, vgic_v4_doorbell_handler, - 0, "vcpu", vcpu); + ret = vgic_v4_request_vpe_irq(vcpu, irq); if (ret) { kvm_err("failed to allocate vcpu IRQ%d\n", irq); /* diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 0c8da72953f0..7f7f3c5ed85a 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -6,6 +6,7 @@ #define __KVM_ARM_VGIC_NEW_H__ #include <linux/irqchip/arm-gic-common.h> +#include <asm/kvm_mmu.h> #define PRODUCT_ID_KVM 0x4b /* ASCII code K */ #define IMPLEMENTER_ARM 0x43b @@ -131,6 +132,19 @@ static inline bool vgic_irq_is_multi_sgi(struct vgic_irq *irq) return vgic_irq_get_lr_count(irq) > 1; } +static inline int vgic_write_guest_lock(struct kvm *kvm, gpa_t gpa, + const void *data, unsigned long len) +{ + struct vgic_dist *dist = &kvm->arch.vgic; + int ret; + + dist->table_write_in_progress = true; + ret = kvm_write_guest_lock(kvm, gpa, data, len); + dist->table_write_in_progress = false; + + return ret; +} + /* * This struct provides an intermediate representation of the fields contained * in the GICH_VMCR and ICH_VMCR registers, such that code exporting the GIC @@ -331,5 +345,6 @@ int vgic_v4_init(struct kvm *kvm); void vgic_v4_teardown(struct kvm *kvm); void vgic_v4_configure_vsgis(struct kvm *kvm); void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val); +int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq); #endif diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index d78ae63d7c15..08978d0672e7 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -16,7 +16,7 @@ #include <asm/kvm_asm.h> #include <asm/kvm_mmu.h> -unsigned int kvm_arm_vmid_bits; +unsigned int __ro_after_init kvm_arm_vmid_bits; static DEFINE_RAW_SPINLOCK(cpu_vmid_lock); static atomic64_t vmid_generation; @@ -172,7 +172,7 @@ void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid) /* * Initialize the VMID allocator */ -int kvm_arm_vmid_alloc_init(void) +int __init kvm_arm_vmid_alloc_init(void) { kvm_arm_vmid_bits = kvm_get_vmid_bits(); @@ -190,7 +190,7 @@ int kvm_arm_vmid_alloc_init(void) return 0; } -void kvm_arm_vmid_alloc_free(void) +void __init kvm_arm_vmid_alloc_free(void) { kfree(vmid_map); } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 35e9a468d13e..95364e8bdc19 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -559,3 +559,24 @@ bool __init arch_hugetlb_valid_size(unsigned long size) { return __hugetlb_valid_size(size); } + +pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return huge_ptep_clear_flush(vma, addr, ptep); + } + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 14c87e8d69d8..d77c9f56b7b4 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1630,3 +1630,24 @@ static int __init prevent_bootmem_remove_init(void) } early_initcall(prevent_bootmem_remove_init); #endif + +pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return ptep_clear_flush(vma, addr, ptep); + } + return ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index a86ee376920a..dfeb2c51e257 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -71,6 +71,7 @@ WORKAROUND_2038923 WORKAROUND_2064142 WORKAROUND_2077057 WORKAROUND_2457168 +WORKAROUND_2645198 WORKAROUND_2658417 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE diff --git a/arch/ia64/kernel/elfcore.c b/arch/ia64/kernel/elfcore.c index 94680521fbf9..8895df121540 100644 --- a/arch/ia64/kernel/elfcore.c +++ b/arch/ia64/kernel/elfcore.c @@ -7,7 +7,7 @@ #include <asm/elf.h> -Elf64_Half elf_core_extra_phdrs(void) +Elf64_Half elf_core_extra_phdrs(struct coredump_params *cprm) { return GATE_EHDR->e_phnum; } @@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { const struct elf_phdr *const gate_phdrs = (const struct elf_phdr *) (GATE_ADDR + GATE_EHDR->e_phoff); diff --git a/arch/ia64/kernel/sys_ia64.c b/arch/ia64/kernel/sys_ia64.c index f6a502e8f02c..6e948d015332 100644 --- a/arch/ia64/kernel/sys_ia64.c +++ b/arch/ia64/kernel/sys_ia64.c @@ -170,6 +170,9 @@ ia64_mremap (unsigned long addr, unsigned long old_len, unsigned long new_len, u asmlinkage long ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user *tp) { + struct timespec64 rtn_tp; + s64 tick_ns; + /* * ia64's clock_gettime() syscall is implemented as a vdso call * fsys_clock_gettime(). Currently it handles only @@ -185,8 +188,8 @@ ia64_clock_getres(const clockid_t which_clock, struct __kernel_timespec __user * switch (which_clock) { case CLOCK_REALTIME: case CLOCK_MONOTONIC: - s64 tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq); - struct timespec64 rtn_tp = ns_to_timespec64(tick_ns); + tick_ns = DIV_ROUND_UP(NSEC_PER_SEC, local_cpu_data->itc_freq); + rtn_tp = ns_to_timespec64(tick_ns); return put_timespec64(&rtn_tp, tp); } diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index 90f9d3399b2a..3418d32d4fc7 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -10,8 +10,6 @@ #define FTRACE_REGS_PLT_IDX 1 #define NR_FTRACE_PLTS 2 -#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1])) - #ifdef CONFIG_FUNCTION_TRACER #define MCOUNT_INSN_SIZE 4 /* sizeof mcount call */ diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h index c00e1512d4fa..7eedd83fd0d7 100644 --- a/arch/loongarch/include/asm/inst.h +++ b/arch/loongarch/include/asm/inst.h @@ -377,14 +377,6 @@ static inline bool unsigned_imm_check(unsigned long val, unsigned int bit) return val < (1UL << bit); } -static inline unsigned long sign_extend(unsigned long val, unsigned int idx) -{ - if (!is_imm_negative(val, idx + 1)) - return ((1UL << idx) - 1) & val; - else - return ~((1UL << idx) - 1) | val; -} - #define DEF_EMIT_REG0I26_FORMAT(NAME, OP) \ static inline void emit_##NAME(union loongarch_instruction *insn, \ int offset) \ @@ -401,6 +393,7 @@ static inline void emit_##NAME(union loongarch_instruction *insn, \ } DEF_EMIT_REG0I26_FORMAT(b, b_op) +DEF_EMIT_REG0I26_FORMAT(bl, bl_op) #define DEF_EMIT_REG1I20_FORMAT(NAME, OP) \ static inline void emit_##NAME(union loongarch_instruction *insn, \ diff --git a/arch/loongarch/include/asm/unwind.h b/arch/loongarch/include/asm/unwind.h index f2b52b9ea93d..b9dce87afd2e 100644 --- a/arch/loongarch/include/asm/unwind.h +++ b/arch/loongarch/include/asm/unwind.h @@ -8,7 +8,9 @@ #define _ASM_UNWIND_H #include <linux/sched.h> +#include <linux/ftrace.h> +#include <asm/ptrace.h> #include <asm/stacktrace.h> enum unwinder_type { @@ -20,11 +22,13 @@ struct unwind_state { char type; /* UNWINDER_XXX */ struct stack_info stack_info; struct task_struct *task; - bool first, error, is_ftrace; + bool first, error, reset; int graph_idx; unsigned long sp, pc, ra; }; +bool default_next_frame(struct unwind_state *state); + void unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs); bool unwind_next_frame(struct unwind_state *state); @@ -40,4 +44,39 @@ static inline bool unwind_error(struct unwind_state *state) return state->error; } +#define GRAPH_FAKE_OFFSET (sizeof(struct pt_regs) - offsetof(struct pt_regs, regs[1])) + +static inline unsigned long unwind_graph_addr(struct unwind_state *state, + unsigned long pc, unsigned long cfa) +{ + return ftrace_graph_ret_addr(state->task, &state->graph_idx, + pc, (unsigned long *)(cfa - GRAPH_FAKE_OFFSET)); +} + +static __always_inline void __unwind_start(struct unwind_state *state, + struct task_struct *task, struct pt_regs *regs) +{ + memset(state, 0, sizeof(*state)); + if (regs) { + state->sp = regs->regs[3]; + state->pc = regs->csr_era; + state->ra = regs->regs[1]; + } else if (task && task != current) { + state->sp = thread_saved_fp(task); + state->pc = thread_saved_ra(task); + state->ra = 0; + } else { + state->sp = (unsigned long)__builtin_frame_address(0); + state->pc = (unsigned long)__builtin_return_address(0); + state->ra = 0; + } + state->task = task; + get_stack_info(state->sp, state->task, &state->stack_info); + state->pc = unwind_graph_addr(state, state->pc, state->sp); +} + +static __always_inline unsigned long __unwind_get_return_address(struct unwind_state *state) +{ + return unwind_done(state) ? 0 : state->pc; +} #endif /* _ASM_UNWIND_H */ diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile index fcaa024a685e..c8cfbd562921 100644 --- a/arch/loongarch/kernel/Makefile +++ b/arch/loongarch/kernel/Makefile @@ -8,7 +8,7 @@ extra-y := vmlinux.lds obj-y += head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \ traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \ elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \ - alternative.o unaligned.o + alternative.o unaligned.o unwind.o obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_EFI) += efi.o diff --git a/arch/loongarch/kernel/alternative.c b/arch/loongarch/kernel/alternative.c index c5aebeac960b..4ad13847e962 100644 --- a/arch/loongarch/kernel/alternative.c +++ b/arch/loongarch/kernel/alternative.c @@ -74,7 +74,7 @@ static void __init_or_module recompute_jump(union loongarch_instruction *buf, switch (src->reg0i26_format.opcode) { case b_op: case bl_op: - jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 27); + jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 27); if (in_alt_jump(jump_addr, start, end)) return; offset = jump_addr - pc; @@ -93,7 +93,7 @@ static void __init_or_module recompute_jump(union loongarch_instruction *buf, fallthrough; case beqz_op: case bnez_op: - jump_addr = cur_pc + sign_extend((si_h << 16 | si_l) << 2, 22); + jump_addr = cur_pc + sign_extend64((si_h << 16 | si_l) << 2, 22); if (in_alt_jump(jump_addr, start, end)) return; offset = jump_addr - pc; @@ -112,7 +112,7 @@ static void __init_or_module recompute_jump(union loongarch_instruction *buf, case bge_op: case bltu_op: case bgeu_op: - jump_addr = cur_pc + sign_extend(si << 2, 17); + jump_addr = cur_pc + sign_extend64(si << 2, 17); if (in_alt_jump(jump_addr, start, end)) return; offset = jump_addr - pc; diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c index 255a09876ef2..3a3fce2d7846 100644 --- a/arch/loongarch/kernel/cpu-probe.c +++ b/arch/loongarch/kernel/cpu-probe.c @@ -94,7 +94,7 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c) c->options = LOONGARCH_CPU_CPUCFG | LOONGARCH_CPU_CSR | LOONGARCH_CPU_TLB | LOONGARCH_CPU_VINT | LOONGARCH_CPU_WATCH; - elf_hwcap |= HWCAP_LOONGARCH_CRC32; + elf_hwcap = HWCAP_LOONGARCH_CPUCFG | HWCAP_LOONGARCH_CRC32; config = read_cpucfg(LOONGARCH_CPUCFG1); if (config & CPUCFG1_UAL) { diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 75e5be807a0d..7e5c293ed89f 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -67,14 +67,17 @@ SYM_FUNC_END(except_vec_cex) .macro BUILD_HANDLER exception handler prep .align 5 SYM_FUNC_START(handle_\exception) + 666: BACKUP_T0T1 SAVE_ALL build_prep_\prep move a0, sp la.abs t0, do_\handler jirl ra, t0, 0 + 668: RESTORE_ALL_AND_RET SYM_FUNC_END(handle_\exception) + SYM_DATA(unwind_hint_\exception, .word 668b - 666b) .endm BUILD_HANDLER ade ade badv diff --git a/arch/loongarch/kernel/inst.c b/arch/loongarch/kernel/inst.c index 512579d79b22..badc59087042 100644 --- a/arch/loongarch/kernel/inst.c +++ b/arch/loongarch/kernel/inst.c @@ -58,7 +58,6 @@ u32 larch_insn_gen_nop(void) u32 larch_insn_gen_b(unsigned long pc, unsigned long dest) { long offset = dest - pc; - unsigned int immediate_l, immediate_h; union loongarch_instruction insn; if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) { @@ -66,15 +65,7 @@ u32 larch_insn_gen_b(unsigned long pc, unsigned long dest) return INSN_BREAK; } - offset >>= 2; - - immediate_l = offset & 0xffff; - offset >>= 16; - immediate_h = offset & 0x3ff; - - insn.reg0i26_format.opcode = b_op; - insn.reg0i26_format.immediate_l = immediate_l; - insn.reg0i26_format.immediate_h = immediate_h; + emit_b(&insn, offset >> 2); return insn.word; } @@ -82,7 +73,6 @@ u32 larch_insn_gen_b(unsigned long pc, unsigned long dest) u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest) { long offset = dest - pc; - unsigned int immediate_l, immediate_h; union loongarch_instruction insn; if ((offset & 3) || offset < -SZ_128M || offset >= SZ_128M) { @@ -90,15 +80,7 @@ u32 larch_insn_gen_bl(unsigned long pc, unsigned long dest) return INSN_BREAK; } - offset >>= 2; - - immediate_l = offset & 0xffff; - offset >>= 16; - immediate_h = offset & 0x3ff; - - insn.reg0i26_format.opcode = bl_op; - insn.reg0i26_format.immediate_l = immediate_l; - insn.reg0i26_format.immediate_h = immediate_h; + emit_bl(&insn, offset >> 2); return insn.word; } @@ -107,10 +89,7 @@ u32 larch_insn_gen_or(enum loongarch_gpr rd, enum loongarch_gpr rj, enum loongar { union loongarch_instruction insn; - insn.reg3_format.opcode = or_op; - insn.reg3_format.rd = rd; - insn.reg3_format.rj = rj; - insn.reg3_format.rk = rk; + emit_or(&insn, rd, rj, rk); return insn.word; } @@ -124,9 +103,7 @@ u32 larch_insn_gen_lu12iw(enum loongarch_gpr rd, int imm) { union loongarch_instruction insn; - insn.reg1i20_format.opcode = lu12iw_op; - insn.reg1i20_format.rd = rd; - insn.reg1i20_format.immediate = imm; + emit_lu12iw(&insn, rd, imm); return insn.word; } @@ -135,9 +112,7 @@ u32 larch_insn_gen_lu32id(enum loongarch_gpr rd, int imm) { union loongarch_instruction insn; - insn.reg1i20_format.opcode = lu32id_op; - insn.reg1i20_format.rd = rd; - insn.reg1i20_format.immediate = imm; + emit_lu32id(&insn, rd, imm); return insn.word; } @@ -146,10 +121,7 @@ u32 larch_insn_gen_lu52id(enum loongarch_gpr rd, enum loongarch_gpr rj, int imm) { union loongarch_instruction insn; - insn.reg2i12_format.opcode = lu52id_op; - insn.reg2i12_format.rd = rd; - insn.reg2i12_format.rj = rj; - insn.reg2i12_format.immediate = imm; + emit_lu52id(&insn, rd, rj, imm); return insn.word; } @@ -158,10 +130,7 @@ u32 larch_insn_gen_jirl(enum loongarch_gpr rd, enum loongarch_gpr rj, unsigned l { union loongarch_instruction insn; - insn.reg2i16_format.opcode = jirl_op; - insn.reg2i16_format.rd = rd; - insn.reg2i16_format.rj = rj; - insn.reg2i16_format.immediate = (dest - pc) >> 2; + emit_jirl(&insn, rj, rd, (dest - pc) >> 2); return insn.word; } diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index c583b1ef1f44..edfd220a3737 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -191,20 +191,14 @@ out: unsigned long __get_wchan(struct task_struct *task) { - unsigned long pc; + unsigned long pc = 0; struct unwind_state state; if (!try_get_task_stack(task)) return 0; - unwind_start(&state, task, NULL); - state.sp = thread_saved_fp(task); - get_stack_info(state.sp, state.task, &state.stack_info); - state.pc = thread_saved_ra(task); -#ifdef CONFIG_UNWINDER_PROLOGUE - state.type = UNWINDER_PROLOGUE; -#endif - for (; !unwind_done(&state); unwind_next_frame(&state)) { + for (unwind_start(&state, task, NULL); + !unwind_done(&state); unwind_next_frame(&state)) { pc = unwind_get_return_address(&state); if (!pc) break; diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c index 7ea62faeeadb..c38a146a973b 100644 --- a/arch/loongarch/kernel/traps.c +++ b/arch/loongarch/kernel/traps.c @@ -72,9 +72,6 @@ static void show_backtrace(struct task_struct *task, const struct pt_regs *regs, if (!task) task = current; - if (user_mode(regs)) - state.type = UNWINDER_GUESS; - printk("%sCall Trace:", loglvl); for (unwind_start(&state, task, pregs); !unwind_done(&state); unwind_next_frame(&state)) { diff --git a/arch/loongarch/kernel/unwind.c b/arch/loongarch/kernel/unwind.c new file mode 100644 index 000000000000..a463d6961344 --- /dev/null +++ b/arch/loongarch/kernel/unwind.c @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2023 Loongson Technology Corporation Limited + */ +#include <linux/kernel.h> +#include <linux/ftrace.h> + +#include <asm/unwind.h> + +bool default_next_frame(struct unwind_state *state) +{ + struct stack_info *info = &state->stack_info; + unsigned long addr; + + if (unwind_done(state)) + return false; + + do { + for (state->sp += sizeof(unsigned long); + state->sp < info->end; state->sp += sizeof(unsigned long)) { + addr = *(unsigned long *)(state->sp); + state->pc = unwind_graph_addr(state, addr, state->sp + 8); + if (__kernel_text_address(state->pc)) + return true; + } + + state->sp = info->next_sp; + + } while (!get_stack_info(state->sp, state->task, info)); + + return false; +} diff --git a/arch/loongarch/kernel/unwind_guess.c b/arch/loongarch/kernel/unwind_guess.c index e2d2e4f3001f..98379b7d4147 100644 --- a/arch/loongarch/kernel/unwind_guess.c +++ b/arch/loongarch/kernel/unwind_guess.c @@ -2,37 +2,18 @@ /* * Copyright (C) 2022 Loongson Technology Corporation Limited */ -#include <linux/kernel.h> -#include <linux/ftrace.h> - #include <asm/unwind.h> unsigned long unwind_get_return_address(struct unwind_state *state) { - if (unwind_done(state)) - return 0; - else if (state->first) - return state->pc; - - return *(unsigned long *)(state->sp); + return __unwind_get_return_address(state); } EXPORT_SYMBOL_GPL(unwind_get_return_address); void unwind_start(struct unwind_state *state, struct task_struct *task, struct pt_regs *regs) { - memset(state, 0, sizeof(*state)); - - if (regs) { - state->sp = regs->regs[3]; - state->pc = regs->csr_era; - } - - state->task = task; - state->first = true; - - get_stack_info(state->sp, state->task, &state->stack_info); - + __unwind_start(state, task, regs); if (!unwind_done(state) && !__kernel_text_address(state->pc)) unwind_next_frame(state); } @@ -40,30 +21,6 @@ EXPORT_SYMBOL_GPL(unwind_start); bool unwind_next_frame(struct unwind_state *state) { - struct stack_info *info = &state->stack_info; - unsigned long addr; - - if (unwind_done(state)) - return false; - - if (state->first) - state->first = false; - - do { - for (state->sp += sizeof(unsigned long); - state->sp < info->end; - state->sp += sizeof(unsigned long)) { - addr = *(unsigned long *)(state->sp); - state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, - addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); - if (__kernel_text_address(addr)) - return true; - } - - state->sp = info->next_sp; - - } while (!get_stack_info(state->sp, state->task, info)); - - return false; + return default_next_frame(state); } EXPORT_SYMBOL_GPL(unwind_next_frame); diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c index 0f8d1451ebb8..9095fde8e55d 100644 --- a/arch/loongarch/kernel/unwind_prologue.c +++ b/arch/loongarch/kernel/unwind_prologue.c @@ -2,61 +2,116 @@ /* * Copyright (C) 2022 Loongson Technology Corporation Limited */ +#include <linux/cpumask.h> #include <linux/ftrace.h> #include <linux/kallsyms.h> #include <asm/inst.h> +#include <asm/loongson.h> #include <asm/ptrace.h> +#include <asm/setup.h> #include <asm/unwind.h> -static inline void unwind_state_fixup(struct unwind_state *state) -{ -#ifdef CONFIG_DYNAMIC_FTRACE - static unsigned long ftrace = (unsigned long)ftrace_call + 4; - - if (state->pc == ftrace) - state->is_ftrace = true; +extern const int unwind_hint_ade; +extern const int unwind_hint_ale; +extern const int unwind_hint_bp; +extern const int unwind_hint_fpe; +extern const int unwind_hint_fpu; +extern const int unwind_hint_lsx; +extern const int unwind_hint_lasx; +extern const int unwind_hint_lbt; +extern const int unwind_hint_ri; +extern const int unwind_hint_watch; +extern unsigned long eentry; +#ifdef CONFIG_NUMA +extern unsigned long pcpu_handlers[NR_CPUS]; #endif -} -unsigned long unwind_get_return_address(struct unwind_state *state) +static inline bool scan_handlers(unsigned long entry_offset) { + int idx, offset; - if (unwind_done(state)) - return 0; - else if (state->type) - return state->pc; - else if (state->first) - return state->pc; - - return *(unsigned long *)(state->sp); + if (entry_offset >= EXCCODE_INT_START * VECSIZE) + return false; + idx = entry_offset / VECSIZE; + offset = entry_offset % VECSIZE; + switch (idx) { + case EXCCODE_ADE: + return offset == unwind_hint_ade; + case EXCCODE_ALE: + return offset == unwind_hint_ale; + case EXCCODE_BP: + return offset == unwind_hint_bp; + case EXCCODE_FPE: + return offset == unwind_hint_fpe; + case EXCCODE_FPDIS: + return offset == unwind_hint_fpu; + case EXCCODE_LSXDIS: + return offset == unwind_hint_lsx; + case EXCCODE_LASXDIS: + return offset == unwind_hint_lasx; + case EXCCODE_BTDIS: + return offset == unwind_hint_lbt; + case EXCCODE_INE: + return offset == unwind_hint_ri; + case EXCCODE_WATCH: + return offset == unwind_hint_watch; + default: + return false; + } } -EXPORT_SYMBOL_GPL(unwind_get_return_address); -static bool unwind_by_guess(struct unwind_state *state) +static inline bool fix_exception(unsigned long pc) { - struct stack_info *info = &state->stack_info; - unsigned long addr; - - for (state->sp += sizeof(unsigned long); - state->sp < info->end; - state->sp += sizeof(unsigned long)) { - addr = *(unsigned long *)(state->sp); - state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, - addr, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); - if (__kernel_text_address(addr)) +#ifdef CONFIG_NUMA + int cpu; + + for_each_possible_cpu(cpu) { + if (!pcpu_handlers[cpu]) + continue; + if (scan_handlers(pc - pcpu_handlers[cpu])) return true; } +#endif + return scan_handlers(pc - eentry); +} +/* + * As we meet ftrace_regs_entry, reset first flag like first doing + * tracing. Prologue analysis will stop soon because PC is at entry. + */ +static inline bool fix_ftrace(unsigned long pc) +{ +#ifdef CONFIG_DYNAMIC_FTRACE + return pc == (unsigned long)ftrace_call + LOONGARCH_INSN_SIZE; +#else return false; +#endif } +static inline bool unwind_state_fixup(struct unwind_state *state) +{ + if (!fix_exception(state->pc) && !fix_ftrace(state->pc)) + return false; + + state->reset = true; + return true; +} + +/* + * LoongArch function prologue is like follows, + * [instructions not use stack var] + * addi.d sp, sp, -imm + * st.d xx, sp, offset <- save callee saved regs and + * st.d yy, sp, offset save ra if function is nest. + * [others instructions] + */ static bool unwind_by_prologue(struct unwind_state *state) { long frame_ra = -1; unsigned long frame_size = 0; - unsigned long size, offset, pc = state->pc; + unsigned long size, offset, pc; struct pt_regs *regs; struct stack_info *info = &state->stack_info; union loongarch_instruction *ip, *ip_end; @@ -64,20 +119,21 @@ static bool unwind_by_prologue(struct unwind_state *state) if (state->sp >= info->end || state->sp < info->begin) return false; - if (state->is_ftrace) { - /* - * As we meet ftrace_regs_entry, reset first flag like first doing - * tracing. Prologue analysis will stop soon because PC is at entry. - */ + if (state->reset) { regs = (struct pt_regs *)state->sp; state->first = true; - state->is_ftrace = false; + state->reset = false; state->pc = regs->csr_era; state->ra = regs->regs[1]; state->sp = regs->regs[3]; return true; } + /* + * When first is not set, the PC is a return address in the previous frame. + * We need to adjust its value in case overflow to the next symbol. + */ + pc = state->pc - (state->first ? 0 : LOONGARCH_INSN_SIZE); if (!kallsyms_lookup_size_offset(pc, &size, &offset)) return false; @@ -93,6 +149,10 @@ static bool unwind_by_prologue(struct unwind_state *state) ip++; } + /* + * Can't find stack alloc action, PC may be in a leaf function. Only the + * first being true is reasonable, otherwise indicate analysis is broken. + */ if (!frame_size) { if (state->first) goto first; @@ -110,6 +170,7 @@ static bool unwind_by_prologue(struct unwind_state *state) ip++; } + /* Can't find save $ra action, PC may be in a leaf function, too. */ if (frame_ra < 0) { if (state->first) { state->sp = state->sp + frame_size; @@ -118,88 +179,47 @@ static bool unwind_by_prologue(struct unwind_state *state) return false; } - if (state->first) - state->first = false; - state->pc = *(unsigned long *)(state->sp + frame_ra); state->sp = state->sp + frame_size; goto out; first: - state->first = false; - if (state->pc == state->ra) - return false; - state->pc = state->ra; out: - unwind_state_fixup(state); - return !!__kernel_text_address(state->pc); -} - -void unwind_start(struct unwind_state *state, struct task_struct *task, - struct pt_regs *regs) -{ - memset(state, 0, sizeof(*state)); - - if (regs && __kernel_text_address(regs->csr_era)) { - state->pc = regs->csr_era; - state->sp = regs->regs[3]; - state->ra = regs->regs[1]; - state->type = UNWINDER_PROLOGUE; - } - - state->task = task; - state->first = true; - - get_stack_info(state->sp, state->task, &state->stack_info); - - if (!unwind_done(state) && !__kernel_text_address(state->pc)) - unwind_next_frame(state); + state->first = false; + return unwind_state_fixup(state) || __kernel_text_address(state->pc); } -EXPORT_SYMBOL_GPL(unwind_start); -bool unwind_next_frame(struct unwind_state *state) +static bool next_frame(struct unwind_state *state) { - struct stack_info *info = &state->stack_info; - struct pt_regs *regs; unsigned long pc; + struct pt_regs *regs; + struct stack_info *info = &state->stack_info; if (unwind_done(state)) return false; do { - switch (state->type) { - case UNWINDER_GUESS: - state->first = false; - if (unwind_by_guess(state)) - return true; - break; + if (unwind_by_prologue(state)) { + state->pc = unwind_graph_addr(state, state->pc, state->sp); + return true; + } + + if (info->type == STACK_TYPE_IRQ && info->end == state->sp) { + regs = (struct pt_regs *)info->next_sp; + pc = regs->csr_era; + + if (user_mode(regs) || !__kernel_text_address(pc)) + return false; + + state->first = true; + state->pc = pc; + state->ra = regs->regs[1]; + state->sp = regs->regs[3]; + get_stack_info(state->sp, state->task, info); - case UNWINDER_PROLOGUE: - if (unwind_by_prologue(state)) { - state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, - state->pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); - return true; - } - - if (info->type == STACK_TYPE_IRQ && - info->end == state->sp) { - regs = (struct pt_regs *)info->next_sp; - pc = regs->csr_era; - - if (user_mode(regs) || !__kernel_text_address(pc)) - return false; - - state->first = true; - state->ra = regs->regs[1]; - state->sp = regs->regs[3]; - state->pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, - pc, (unsigned long *)(state->sp - GRAPH_FAKE_OFFSET)); - get_stack_info(state->sp, state->task, info); - - return true; - } + return true; } state->sp = info->next_sp; @@ -208,4 +228,36 @@ bool unwind_next_frame(struct unwind_state *state) return false; } + +unsigned long unwind_get_return_address(struct unwind_state *state) +{ + return __unwind_get_return_address(state); +} +EXPORT_SYMBOL_GPL(unwind_get_return_address); + +void unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs) +{ + __unwind_start(state, task, regs); + state->type = UNWINDER_PROLOGUE; + state->first = true; + + /* + * The current PC is not kernel text address, we cannot find its + * relative symbol. Thus, prologue analysis will be broken. Luckily, + * we can use the default_next_frame(). + */ + if (!__kernel_text_address(state->pc)) { + state->type = UNWINDER_GUESS; + if (!unwind_done(state)) + unwind_next_frame(state); + } +} +EXPORT_SYMBOL_GPL(unwind_start); + +bool unwind_next_frame(struct unwind_state *state) +{ + return state->type == UNWINDER_PROLOGUE ? + next_frame(state) : default_next_frame(state); +} EXPORT_SYMBOL_GPL(unwind_next_frame); diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c index da3681f131c8..8bad6b0cff59 100644 --- a/arch/loongarch/mm/tlb.c +++ b/arch/loongarch/mm/tlb.c @@ -251,7 +251,7 @@ static void output_pgtable_bits_defines(void) } #ifdef CONFIG_NUMA -static unsigned long pcpu_handlers[NR_CPUS]; +unsigned long pcpu_handlers[NR_CPUS]; #endif extern long exception_handlers[VECSIZE * 128 / sizeof(long)]; diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index 5cedb28e8a40..2803c9c21ef9 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -758,7 +758,7 @@ struct kvm_mips_callbacks { void (*vcpu_reenter)(struct kvm_vcpu *vcpu); }; extern struct kvm_mips_callbacks *kvm_mips_callbacks; -int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks); +int kvm_mips_emulation_init(void); /* Debug: dump vcpu state */ int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu); @@ -888,7 +888,6 @@ extern unsigned long kvm_mips_get_ramsize(struct kvm *kvm); extern int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_mips_interrupt *irq); -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {} diff --git a/arch/mips/kvm/Kconfig b/arch/mips/kvm/Kconfig index 91d197bee9c0..29e51649203b 100644 --- a/arch/mips/kvm/Kconfig +++ b/arch/mips/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select MMU_NOTIFIER select SRCU select INTERVAL_TREE + select KVM_GENERIC_HARDWARE_ENABLING help Support for hosting Guest kernels. diff --git a/arch/mips/kvm/Makefile b/arch/mips/kvm/Makefile index 21ff75bcdbc4..805aeea2166e 100644 --- a/arch/mips/kvm/Makefile +++ b/arch/mips/kvm/Makefile @@ -17,4 +17,4 @@ kvm-$(CONFIG_CPU_LOONGSON64) += loongson_ipi.o kvm-y += vz.o obj-$(CONFIG_KVM) += kvm.o -obj-y += callback.o tlb.o +obj-y += tlb.o diff --git a/arch/mips/kvm/callback.c b/arch/mips/kvm/callback.c deleted file mode 100644 index d88aa2173fb0..000000000000 --- a/arch/mips/kvm/callback.c +++ /dev/null @@ -1,14 +0,0 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved. - * Authors: Yann Le Du <ledu@kymasys.com> - */ - -#include <linux/export.h> -#include <linux/kvm_host.h> - -struct kvm_mips_callbacks *kvm_mips_callbacks; -EXPORT_SYMBOL_GPL(kvm_mips_callbacks); diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index a25e0b73ee70..36c8991b5d39 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -135,16 +135,6 @@ void kvm_arch_hardware_disable(void) kvm_mips_callbacks->hardware_disable(); } -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - extern void kvm_init_loongson_ipi(struct kvm *kvm); int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) @@ -1015,21 +1005,6 @@ long kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) return r; } -int kvm_arch_init(void *opaque) -{ - if (kvm_mips_callbacks) { - kvm_err("kvm: module already exists\n"); - return -EEXIST; - } - - return kvm_mips_emulation_init(&kvm_mips_callbacks); -} - -void kvm_arch_exit(void) -{ - kvm_mips_callbacks = NULL; -} - int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { @@ -1646,16 +1621,21 @@ static int __init kvm_mips_init(void) if (ret) return ret; - ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); - + ret = kvm_mips_emulation_init(); if (ret) return ret; + if (boot_cpu_type() == CPU_LOONGSON64) kvm_priority_to_irq = kvm_loongson3_priority_to_irq; register_die_notifier(&kvm_mips_csr_die_notifier); + ret = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (ret) { + unregister_die_notifier(&kvm_mips_csr_die_notifier); + return ret; + } return 0; } diff --git a/arch/mips/kvm/vz.c b/arch/mips/kvm/vz.c index c706f5890a05..dafab003ea0d 100644 --- a/arch/mips/kvm/vz.c +++ b/arch/mips/kvm/vz.c @@ -3304,7 +3304,10 @@ static struct kvm_mips_callbacks kvm_vz_callbacks = { .vcpu_reenter = kvm_vz_vcpu_reenter, }; -int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks) +/* FIXME: Get rid of the callbacks now that trap-and-emulate is gone. */ +struct kvm_mips_callbacks *kvm_mips_callbacks = &kvm_vz_callbacks; + +int kvm_mips_emulation_init(void) { if (!cpu_has_vz) return -ENODEV; @@ -3318,7 +3321,5 @@ int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks) return -ENODEV; pr_info("Starting KVM with MIPS VZ extensions\n"); - - *install_callbacks = &kvm_vz_callbacks; return 0; } diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c index 4dfe1f49c5c8..6817892a2c58 100644 --- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -1303,7 +1303,7 @@ static char iodc_dbuf[4096] __page_aligned_bss; */ int pdc_iodc_print(const unsigned char *str, unsigned count) { - unsigned int i; + unsigned int i, found = 0; unsigned long flags; count = min_t(unsigned int, count, sizeof(iodc_dbuf)); @@ -1315,6 +1315,7 @@ int pdc_iodc_print(const unsigned char *str, unsigned count) iodc_dbuf[i+0] = '\r'; iodc_dbuf[i+1] = '\n'; i += 2; + found = 1; goto print; default: iodc_dbuf[i] = str[i]; @@ -1330,7 +1331,7 @@ print: __pa(pdc_result), 0, __pa(iodc_dbuf), i, 0); spin_unlock_irqrestore(&pdc_lock, flags); - return i; + return i - found; } #if !defined(BOOTLOADER) diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c index 69c62933e952..ceb45f51d52e 100644 --- a/arch/parisc/kernel/ptrace.c +++ b/arch/parisc/kernel/ptrace.c @@ -126,6 +126,12 @@ long arch_ptrace(struct task_struct *child, long request, unsigned long tmp; long ret = -EIO; + unsigned long user_regs_struct_size = sizeof(struct user_regs_struct); +#ifdef CONFIG_64BIT + if (is_compat_task()) + user_regs_struct_size /= 2; +#endif + switch (request) { /* Read the word at location addr in the USER area. For ptraced @@ -166,7 +172,7 @@ long arch_ptrace(struct task_struct *child, long request, addr >= sizeof(struct pt_regs)) break; if (addr == PT_IAOQ0 || addr == PT_IAOQ1) { - data |= 3; /* ensure userspace privilege */ + data |= PRIV_USER; /* ensure userspace privilege */ } if ((addr >= PT_GR1 && addr <= PT_GR31) || addr == PT_IAOQ0 || addr == PT_IAOQ1 || @@ -181,14 +187,14 @@ long arch_ptrace(struct task_struct *child, long request, return copy_regset_to_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_SETREGS: /* Set all gp regs in the child. */ return copy_regset_from_user(child, task_user_regset_view(current), REGSET_GENERAL, - 0, sizeof(struct user_regs_struct), + 0, user_regs_struct_size, datap); case PTRACE_GETFPREGS: /* Get the child FPU state. */ @@ -285,7 +291,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, if (addr >= sizeof(struct pt_regs)) break; if (addr == PT_IAOQ0+4 || addr == PT_IAOQ1+4) { - data |= 3; /* ensure userspace privilege */ + data |= PRIV_USER; /* ensure userspace privilege */ } if (addr >= PT_FR0 && addr <= PT_FR31 + 4) { /* Special case, fp regs are 64 bits anyway */ @@ -302,6 +308,11 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, } } break; + case PTRACE_GETREGS: + case PTRACE_SETREGS: + case PTRACE_GETFPREGS: + case PTRACE_SETFPREGS: + return arch_ptrace(child, request, addr, data); default: ret = compat_ptrace_request(child, request, addr, data); @@ -484,7 +495,7 @@ static void set_reg(struct pt_regs *regs, int num, unsigned long val) case RI(iaoq[0]): case RI(iaoq[1]): /* set 2 lowest bits to ensure userspace privilege: */ - regs->iaoq[num - RI(iaoq[0])] = val | 3; + regs->iaoq[num - RI(iaoq[0])] = val | PRIV_USER; return; case RI(sar): regs->sar = val; return; diff --git a/arch/powerpc/boot/wrapper b/arch/powerpc/boot/wrapper index af04cea82b94..352d7de24018 100755 --- a/arch/powerpc/boot/wrapper +++ b/arch/powerpc/boot/wrapper @@ -210,6 +210,10 @@ ld_version() gsub(".*version ", ""); gsub("-.*", ""); split($1,a, "."); + if( length(a[3]) == "8" ) + # a[3] is probably a date of format yyyymmdd used for release snapshots. We + # can assume it to be zero as it does not signify a new version as such. + a[3] = 0; print a[1]*100000000 + a[2]*1000000 + a[3]*10000; exit }' diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush.h b/arch/powerpc/include/asm/book3s/64/tlbflush.h index dd39313242b4..d5cd16270c5d 100644 --- a/arch/powerpc/include/asm/book3s/64/tlbflush.h +++ b/arch/powerpc/include/asm/book3s/64/tlbflush.h @@ -97,6 +97,8 @@ static inline void tlb_flush(struct mmu_gather *tlb) { if (radix_enabled()) radix__tlb_flush(tlb); + + return hash__tlb_flush(tlb); } #ifdef CONFIG_SMP diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h index 77fa88c2aed0..eb6d094083fd 100644 --- a/arch/powerpc/include/asm/hw_irq.h +++ b/arch/powerpc/include/asm/hw_irq.h @@ -173,6 +173,15 @@ static inline notrace unsigned long irq_soft_mask_or_return(unsigned long mask) return flags; } +static inline notrace unsigned long irq_soft_mask_andc_return(unsigned long mask) +{ + unsigned long flags = irq_soft_mask_return(); + + irq_soft_mask_set(flags & ~mask); + + return flags; +} + static inline unsigned long arch_local_save_flags(void) { return irq_soft_mask_return(); @@ -192,7 +201,7 @@ static inline void arch_local_irq_enable(void) static inline unsigned long arch_local_irq_save(void) { - return irq_soft_mask_set_return(IRQS_DISABLED); + return irq_soft_mask_or_return(IRQS_DISABLED); } static inline bool arch_irqs_disabled_flags(unsigned long flags) @@ -331,10 +340,11 @@ bool power_pmu_wants_prompt_pmi(void); * is a different soft-masked interrupt pending that requires hard * masking. */ -static inline bool should_hard_irq_enable(void) +static inline bool should_hard_irq_enable(struct pt_regs *regs) { if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); + WARN_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED); + WARN_ON(!(get_paca()->irq_happened & PACA_IRQ_HARD_DIS)); WARN_ON(mfmsr() & MSR_EE); } @@ -347,8 +357,17 @@ static inline bool should_hard_irq_enable(void) * * TODO: Add test for 64e */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && !power_pmu_wants_prompt_pmi()) - return false; + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) { + if (!power_pmu_wants_prompt_pmi()) + return false; + /* + * If PMIs are disabled then IRQs should be disabled as well, + * so we shouldn't see this condition, check for it just in + * case because we are about to enable PMIs. + */ + if (WARN_ON_ONCE(regs->softe & IRQS_PMI_DISABLED)) + return false; + } if (get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK) return false; @@ -358,18 +377,16 @@ static inline bool should_hard_irq_enable(void) /* * Do the hard enabling, only call this if should_hard_irq_enable is true. + * This allows PMI interrupts to profile irq handlers. */ static inline void do_hard_irq_enable(void) { - if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) { - WARN_ON(irq_soft_mask_return() == IRQS_ENABLED); - WARN_ON(get_paca()->irq_happened & PACA_IRQ_MUST_HARD_MASK); - WARN_ON(mfmsr() & MSR_EE); - } /* - * This allows PMI interrupts (and watchdog soft-NMIs) through. - * There is no other reason to enable this way. + * Asynch interrupts come in with IRQS_ALL_DISABLED, + * PACA_IRQ_HARD_DIS, and MSR[EE]=0. */ + if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) + irq_soft_mask_andc_return(IRQS_PMI_DISABLED); get_paca()->irq_happened &= ~PACA_IRQ_HARD_DIS; __hard_irq_enable(); } @@ -452,7 +469,7 @@ static inline bool arch_irq_disabled_regs(struct pt_regs *regs) return !(regs->msr & MSR_EE); } -static __always_inline bool should_hard_irq_enable(void) +static __always_inline bool should_hard_irq_enable(struct pt_regs *regs) { return false; } diff --git a/arch/powerpc/include/asm/imc-pmu.h b/arch/powerpc/include/asm/imc-pmu.h index 4f897993b710..699a88584ae1 100644 --- a/arch/powerpc/include/asm/imc-pmu.h +++ b/arch/powerpc/include/asm/imc-pmu.h @@ -137,7 +137,7 @@ struct imc_pmu { * are inited. */ struct imc_pmu_ref { - struct mutex lock; + spinlock_t lock; unsigned int id; int refc; }; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index caea15dcb91d..959f566a455c 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -876,13 +876,10 @@ struct kvm_vcpu_arch { #define __KVM_HAVE_ARCH_WQP #define __KVM_HAVE_CREATE_DEVICE -static inline void kvm_arch_hardware_disable(void) {} -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {} static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} -static inline void kvm_arch_exit(void) {} static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index eae9619b6190..6bef23d6d0e3 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -118,7 +118,6 @@ extern int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, extern int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu); extern void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu); extern int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu); -extern int kvmppc_core_check_processor_compat(void); extern int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu, struct kvm_translation *tr); diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c index f55c6fb34a3a..5712dd846263 100644 --- a/arch/powerpc/kernel/dbell.c +++ b/arch/powerpc/kernel/dbell.c @@ -27,7 +27,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(doorbell_exception) ppc_msgsync(); - if (should_hard_irq_enable()) + if (should_hard_irq_enable(regs)) do_hard_irq_enable(); kvmppc_clear_host_ipi(smp_processor_id()); diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index d438ca74e96c..fdbee1093e2b 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -864,7 +864,7 @@ _GLOBAL(load_up_spe) * SPE unavailable trap from kernel - print a message, but let * the task use SPE in the kernel until it returns to user mode. */ -KernelSPE: +SYM_FUNC_START_LOCAL(KernelSPE) lwz r3,_MSR(r1) oris r3,r3,MSR_SPE@h stw r3,_MSR(r1) /* enable use of SPE after return */ @@ -881,6 +881,7 @@ KernelSPE: #endif .align 4,0 +SYM_FUNC_END(KernelSPE) #endif /* CONFIG_SPE */ /* diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index c5b9ce887483..c9535f2760b5 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -238,7 +238,7 @@ static void __do_irq(struct pt_regs *regs, unsigned long oldsp) irq = static_call(ppc_get_irq)(); /* We can hard enable interrupts now to allow perf interrupts */ - if (should_hard_irq_enable()) + if (should_hard_irq_enable(regs)) do_hard_irq_enable(); /* And finally process it */ diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index d68de3618741..e26eb6618ae5 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -515,7 +515,7 @@ DEFINE_INTERRUPT_HANDLER_ASYNC(timer_interrupt) } /* Conditionally hard-enable interrupts. */ - if (should_hard_irq_enable()) { + if (should_hard_irq_enable(regs)) { /* * Ensure a positive value is written to the decrementer, or * else some CPUs will continue to take decrementer exceptions. diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index af8854f9eae3..52085751f5f4 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -989,10 +989,13 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image) * linux,drconf-usable-memory properties. Get an approximate on the * number of usable memory entries and use for FDT size estimation. */ - usm_entries = ((memblock_end_of_DRAM() / drmem_lmb_size()) + - (2 * (resource_size(&crashk_res) / drmem_lmb_size()))); - - extra_size = (unsigned int)(usm_entries * sizeof(u64)); + if (drmem_lmb_size()) { + usm_entries = ((memory_hotplug_max() / drmem_lmb_size()) + + (2 * (resource_size(&crashk_res) / drmem_lmb_size()))); + extra_size = (unsigned int)(usm_entries * sizeof(u64)); + } else { + extra_size = 0; + } /* * Get the number of CPU nodes in the current DT. This allows to diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c index 6d525285dbe8..57f4e7896d67 100644 --- a/arch/powerpc/kvm/book3s.c +++ b/arch/powerpc/kvm/book3s.c @@ -999,16 +999,6 @@ int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvmppc_h_logical_ci_store); -int kvmppc_core_check_processor_compat(void) -{ - /* - * We always return 0 for book3s. We check - * for compatibility while loading the HV - * or PR module - */ - return 0; -} - int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hcall) { return kvm->arch.kvm_ops->hcall_implemented(hcall); @@ -1062,7 +1052,7 @@ static int kvmppc_book3s_init(void) { int r; - r = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); if (r) return r; #ifdef CONFIG_KVM_BOOK3S_32_HANDLER diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index 0dce93ccaadf..01adffb24667 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -912,16 +912,15 @@ static int kvmppc_handle_debug(struct kvm_vcpu *vcpu) static void kvmppc_fill_pt_regs(struct pt_regs *regs) { - ulong r1, ip, msr, lr; + ulong r1, msr, lr; asm("mr %0, 1" : "=r"(r1)); asm("mflr %0" : "=r"(lr)); asm("mfmsr %0" : "=r"(msr)); - asm("bl 1f; 1: mflr %0" : "=r"(ip)); memset(regs, 0, sizeof(*regs)); regs->gpr[1] = r1; - regs->nip = ip; + regs->nip = _THIS_IP_; regs->msr = msr; regs->link = lr; } @@ -1211,7 +1210,7 @@ int kvmppc_handle_exit(struct kvm_vcpu *vcpu, unsigned int exit_nr) /* * On cores with Vector category, KVM is loaded only if CONFIG_ALTIVEC, - * see kvmppc_core_check_processor_compat(). + * see kvmppc_e500mc_check_processor_compat(). */ #ifdef CONFIG_ALTIVEC case BOOKE_INTERRUPT_ALTIVEC_UNAVAIL: diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index c8b2b4478545..b0f695428733 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -314,7 +314,7 @@ static void kvmppc_core_vcpu_put_e500(struct kvm_vcpu *vcpu) kvmppc_booke_vcpu_put(vcpu); } -int kvmppc_core_check_processor_compat(void) +static int kvmppc_e500_check_processor_compat(void) { int r; @@ -507,7 +507,7 @@ static int __init kvmppc_e500_init(void) unsigned long handler_len; unsigned long max_ivor = 0; - r = kvmppc_core_check_processor_compat(); + r = kvmppc_e500_check_processor_compat(); if (r) goto err_out; @@ -531,7 +531,7 @@ static int __init kvmppc_e500_init(void) flush_icache_range(kvmppc_booke_handlers, kvmppc_booke_handlers + ivor[max_ivor] + handler_len); - r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); if (r) goto err_out; kvm_ops_e500.owner = THIS_MODULE; diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c index 57e0ad6a2ca3..a309138927ff 100644 --- a/arch/powerpc/kvm/e500mc.c +++ b/arch/powerpc/kvm/e500mc.c @@ -168,7 +168,7 @@ static void kvmppc_core_vcpu_put_e500mc(struct kvm_vcpu *vcpu) kvmppc_booke_vcpu_put(vcpu); } -int kvmppc_core_check_processor_compat(void) +int kvmppc_e500mc_check_processor_compat(void) { int r; @@ -388,6 +388,10 @@ static int __init kvmppc_e500mc_init(void) { int r; + r = kvmppc_e500mc_check_processor_compat(); + if (r) + goto err_out; + r = kvmppc_booke_init(); if (r) goto err_out; @@ -400,7 +404,7 @@ static int __init kvmppc_e500mc_init(void) */ kvmppc_init_lpid(KVMPPC_NR_LPIDS/threads_per_core); - r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); + r = kvm_init(sizeof(struct kvmppc_vcpu_e500), 0, THIS_MODULE); if (r) goto err_out; kvm_ops_e500mc.owner = THIS_MODULE; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 04494a4fb37a..4c5405fc5538 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -435,21 +435,6 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, } EXPORT_SYMBOL_GPL(kvmppc_ld); -int kvm_arch_hardware_enable(void) -{ - return 0; -} - -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - return kvmppc_core_check_processor_compat(); -} - int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { struct kvmppc_ops *kvm_ops = NULL; @@ -2544,11 +2529,6 @@ void kvmppc_init_lpid(unsigned long nr_lpids_param) } EXPORT_SYMBOL_GPL(kvmppc_init_lpid); -int kvm_arch_init(void *opaque) -{ - return 0; -} - EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ppc_instr); void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_dentry) diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c index 80a148c57de8..44a35ed4f686 100644 --- a/arch/powerpc/mm/book3s64/hash_utils.c +++ b/arch/powerpc/mm/book3s64/hash_utils.c @@ -1012,7 +1012,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table, void hpt_clear_stress(void); static struct timer_list stress_hpt_timer; -void stress_hpt_timer_fn(struct timer_list *timer) +static void stress_hpt_timer_fn(struct timer_list *timer) { int next_cpu; diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index cac727b01799..26245aaf12b8 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -234,6 +234,14 @@ void radix__mark_rodata_ro(void) end = (unsigned long)__end_rodata; radix__change_memory_range(start, end, _PAGE_WRITE); + + for (start = PAGE_OFFSET; start < (unsigned long)_stext; start += PAGE_SIZE) { + end = start + PAGE_SIZE; + if (overlaps_interrupt_vector_text(start, end)) + radix__change_memory_range(start, end, _PAGE_WRITE); + else + break; + } } void radix__mark_initmem_nx(void) @@ -262,6 +270,22 @@ print_mapping(unsigned long start, unsigned long end, unsigned long size, bool e static unsigned long next_boundary(unsigned long addr, unsigned long end) { #ifdef CONFIG_STRICT_KERNEL_RWX + unsigned long stext_phys; + + stext_phys = __pa_symbol(_stext); + + // Relocatable kernel running at non-zero real address + if (stext_phys != 0) { + // The end of interrupts code at zero is a rodata boundary + unsigned long end_intr = __pa_symbol(__end_interrupts) - stext_phys; + if (addr < end_intr) + return end_intr; + + // Start of relocated kernel text is a rodata boundary + if (addr < stext_phys) + return stext_phys; + } + if (addr < __pa_symbol(__srwx_boundary)) return __pa_symbol(__srwx_boundary); #endif diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c index d517aba94d1b..9d229ef7f86e 100644 --- a/arch/powerpc/perf/imc-pmu.c +++ b/arch/powerpc/perf/imc-pmu.c @@ -14,6 +14,7 @@ #include <asm/cputhreads.h> #include <asm/smp.h> #include <linux/string.h> +#include <linux/spinlock.h> /* Nest IMC data structures and variables */ @@ -50,7 +51,7 @@ static int trace_imc_mem_size; * core and trace-imc */ static struct imc_pmu_ref imc_global_refc = { - .lock = __MUTEX_INITIALIZER(imc_global_refc.lock), + .lock = __SPIN_LOCK_INITIALIZER(imc_global_refc.lock), .id = 0, .refc = 0, }; @@ -400,7 +401,7 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu) get_hard_smp_processor_id(cpu)); /* * If this is the last cpu in this chip then, skip the reference - * count mutex lock and make the reference count on this chip zero. + * count lock and make the reference count on this chip zero. */ ref = get_nest_pmu_ref(cpu); if (!ref) @@ -462,15 +463,15 @@ static void nest_imc_counters_release(struct perf_event *event) /* * See if we need to disable the nest PMU. * If no events are currently in use, then we have to take a - * mutex to ensure that we don't race with another task doing + * lock to ensure that we don't race with another task doing * enable or disable the nest counters. */ ref = get_nest_pmu_ref(event->cpu); if (!ref) return; - /* Take the mutex lock for this node and then decrement the reference count */ - mutex_lock(&ref->lock); + /* Take the lock for this node and then decrement the reference count */ + spin_lock(&ref->lock); if (ref->refc == 0) { /* * The scenario where this is true is, when perf session is @@ -482,7 +483,7 @@ static void nest_imc_counters_release(struct perf_event *event) * an OPAL call to disable the engine in that node. * */ - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return; } ref->refc--; @@ -490,7 +491,7 @@ static void nest_imc_counters_release(struct perf_event *event) rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("nest-imc: Unable to stop the counters for core %d\n", node_id); return; } @@ -498,7 +499,7 @@ static void nest_imc_counters_release(struct perf_event *event) WARN(1, "nest-imc: Invalid event reference count\n"); ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); } static int nest_imc_event_init(struct perf_event *event) @@ -557,26 +558,25 @@ static int nest_imc_event_init(struct perf_event *event) /* * Get the imc_pmu_ref struct for this node. - * Take the mutex lock and then increment the count of nest pmu events - * inited. + * Take the lock and then increment the count of nest pmu events inited. */ ref = get_nest_pmu_ref(event->cpu); if (!ref) return -EINVAL; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_NEST, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("nest-imc: Unable to start the counters for node %d\n", node_id); return rc; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); event->destroy = nest_imc_counters_release; return 0; @@ -612,9 +612,8 @@ static int core_imc_mem_init(int cpu, int size) return -ENOMEM; mem_info->vbase = page_address(page); - /* Init the mutex */ core_imc_refc[core_id].id = core_id; - mutex_init(&core_imc_refc[core_id].lock); + spin_lock_init(&core_imc_refc[core_id].lock); rc = opal_imc_counters_init(OPAL_IMC_COUNTERS_CORE, __pa((void *)mem_info->vbase), @@ -703,9 +702,8 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) perf_pmu_migrate_context(&core_imc_pmu->pmu, cpu, ncpu); } else { /* - * If this is the last cpu in this core then, skip taking refernce - * count mutex lock for this core and directly zero "refc" for - * this core. + * If this is the last cpu in this core then skip taking reference + * count lock for this core and directly zero "refc" for this core. */ opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(cpu)); @@ -720,11 +718,11 @@ static int ppc_core_imc_cpu_offline(unsigned int cpu) * last cpu in this core and core-imc event running * in this cpu. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_CORE) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); } return 0; } @@ -739,7 +737,7 @@ static int core_imc_pmu_cpumask_init(void) static void reset_global_refc(struct perf_event *event) { - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); imc_global_refc.refc--; /* @@ -751,7 +749,7 @@ static void reset_global_refc(struct perf_event *event) imc_global_refc.refc = 0; imc_global_refc.id = 0; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); } static void core_imc_counters_release(struct perf_event *event) @@ -764,17 +762,17 @@ static void core_imc_counters_release(struct perf_event *event) /* * See if we need to disable the IMC PMU. * If no events are currently in use, then we have to take a - * mutex to ensure that we don't race with another task doing + * lock to ensure that we don't race with another task doing * enable or disable the core counters. */ core_id = event->cpu / threads_per_core; - /* Take the mutex lock and decrement the refernce count for this core */ + /* Take the lock and decrement the refernce count for this core */ ref = &core_imc_refc[core_id]; if (!ref) return; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { /* * The scenario where this is true is, when perf session is @@ -786,7 +784,7 @@ static void core_imc_counters_release(struct perf_event *event) * an OPAL call to disable the engine in that core. * */ - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return; } ref->refc--; @@ -794,7 +792,7 @@ static void core_imc_counters_release(struct perf_event *event) rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("IMC: Unable to stop the counters for core %d\n", core_id); return; } @@ -802,7 +800,7 @@ static void core_imc_counters_release(struct perf_event *event) WARN(1, "core-imc: Invalid event reference count\n"); ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); reset_global_refc(event); } @@ -840,7 +838,6 @@ static int core_imc_event_init(struct perf_event *event) if ((!pcmi->vbase)) return -ENODEV; - /* Get the core_imc mutex for this core */ ref = &core_imc_refc[core_id]; if (!ref) return -EINVAL; @@ -848,22 +845,22 @@ static int core_imc_event_init(struct perf_event *event) /* * Core pmu units are enabled only when it is used. * See if this is triggered for the first time. - * If yes, take the mutex lock and enable the core counters. + * If yes, take the lock and enable the core counters. * If not, just increment the count in core_imc_refc struct. */ - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { rc = opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(event->cpu)); if (rc) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("core-imc: Unable to start the counters for core %d\n", core_id); return rc; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); /* * Since the system can run either in accumulation or trace-mode @@ -874,7 +871,7 @@ static int core_imc_event_init(struct perf_event *event) * to know whether any other trace/thread imc * events are running. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_CORE) { /* * No other trace/thread imc events are running in @@ -883,10 +880,10 @@ static int core_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_CORE; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->hw.event_base = (u64)pcmi->vbase + (config & IMC_EVENT_OFFSET_MASK); event->destroy = core_imc_counters_release; @@ -958,10 +955,10 @@ static int ppc_thread_imc_cpu_offline(unsigned int cpu) mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); /* Reduce the refc if thread-imc event running on this cpu */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_THREAD) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return 0; } @@ -1001,7 +998,7 @@ static int thread_imc_event_init(struct perf_event *event) if (!target) return -EINVAL; - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); /* * Check if any other trace/core imc events are running in the * system, if not set the global id to thread-imc. @@ -1010,10 +1007,10 @@ static int thread_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_THREAD; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->pmu->task_ctx_nr = perf_sw_context; event->destroy = reset_global_refc; @@ -1135,25 +1132,25 @@ static int thread_imc_event_add(struct perf_event *event, int flags) /* * imc pmus are enabled only when it is used. * See if this is triggered for the first time. - * If yes, take the mutex lock and enable the counters. + * If yes, take the lock and enable the counters. * If not, just increment the count in ref count struct. */ ref = &core_imc_refc[core_id]; if (!ref) return -EINVAL; - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { if (opal_imc_counters_start(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("thread-imc: Unable to start the counter\ for core %d\n", core_id); return -EINVAL; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return 0; } @@ -1170,12 +1167,12 @@ static void thread_imc_event_del(struct perf_event *event, int flags) return; } - mutex_lock(&ref->lock); + spin_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("thread-imc: Unable to stop the counters\ for core %d\n", core_id); return; @@ -1183,7 +1180,7 @@ static void thread_imc_event_del(struct perf_event *event, int flags) } else if (ref->refc < 0) { ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); /* Set bit 0 of LDBAR to zero, to stop posting updates to memory */ mtspr(SPRN_LDBAR, (mfspr(SPRN_LDBAR) & (~(1UL << 63)))); @@ -1224,9 +1221,8 @@ static int trace_imc_mem_alloc(int cpu_id, int size) } } - /* Init the mutex, if not already */ trace_imc_refc[core_id].id = core_id; - mutex_init(&trace_imc_refc[core_id].lock); + spin_lock_init(&trace_imc_refc[core_id].lock); mtspr(SPRN_LDBAR, 0); return 0; @@ -1246,10 +1242,10 @@ static int ppc_trace_imc_cpu_offline(unsigned int cpu) * Reduce the refc if any trace-imc event running * on this cpu. */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == IMC_DOMAIN_TRACE) imc_global_refc.refc--; - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return 0; } @@ -1371,17 +1367,17 @@ static int trace_imc_event_add(struct perf_event *event, int flags) } mtspr(SPRN_LDBAR, ldbar_value); - mutex_lock(&ref->lock); + spin_lock(&ref->lock); if (ref->refc == 0) { if (opal_imc_counters_start(OPAL_IMC_COUNTERS_TRACE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("trace-imc: Unable to start the counters for core %d\n", core_id); return -EINVAL; } } ++ref->refc; - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); return 0; } @@ -1414,19 +1410,19 @@ static void trace_imc_event_del(struct perf_event *event, int flags) return; } - mutex_lock(&ref->lock); + spin_lock(&ref->lock); ref->refc--; if (ref->refc == 0) { if (opal_imc_counters_stop(OPAL_IMC_COUNTERS_TRACE, get_hard_smp_processor_id(smp_processor_id()))) { - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); pr_err("trace-imc: Unable to stop the counters for core %d\n", core_id); return; } } else if (ref->refc < 0) { ref->refc = 0; } - mutex_unlock(&ref->lock); + spin_unlock(&ref->lock); trace_imc_event_stop(event, flags); } @@ -1448,7 +1444,7 @@ static int trace_imc_event_init(struct perf_event *event) * no other thread is running any core/thread imc * events */ - mutex_lock(&imc_global_refc.lock); + spin_lock(&imc_global_refc.lock); if (imc_global_refc.id == 0 || imc_global_refc.id == IMC_DOMAIN_TRACE) { /* * No core/thread imc events are running in the @@ -1457,10 +1453,10 @@ static int trace_imc_event_init(struct perf_event *event) imc_global_refc.id = IMC_DOMAIN_TRACE; imc_global_refc.refc++; } else { - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); return -EBUSY; } - mutex_unlock(&imc_global_refc.lock); + spin_unlock(&imc_global_refc.lock); event->hw.idx = -1; @@ -1533,10 +1529,10 @@ static int init_nest_pmu_ref(void) i = 0; for_each_node(nid) { /* - * Mutex lock to avoid races while tracking the number of + * Take the lock to avoid races while tracking the number of * sessions using the chip's nest pmu units. */ - mutex_init(&nest_imc_refc[i].lock); + spin_lock_init(&nest_imc_refc[i].lock); /* * Loop to init the "id" with the node_id. Variable "i" initialized to diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index faf2c2177094..82153960ac00 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -80,6 +80,9 @@ ifeq ($(CONFIG_PERF_EVENTS),y) KBUILD_CFLAGS += -fno-omit-frame-pointer endif +# Avoid generating .eh_frame sections. +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables + KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi index 43bed6c0a84f..5235fd1c9cb6 100644 --- a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi @@ -328,7 +328,7 @@ bus-range = <0x0 0xff>; ranges = <0x81000000 0x0 0x60080000 0x0 0x60080000 0x0 0x10000>, /* I/O */ <0x82000000 0x0 0x60090000 0x0 0x60090000 0x0 0xff70000>, /* mem */ - <0x82000000 0x0 0x70000000 0x0 0x70000000 0x0 0x1000000>, /* mem */ + <0x82000000 0x0 0x70000000 0x0 0x70000000 0x0 0x10000000>, /* mem */ <0xc3000000 0x20 0x00000000 0x20 0x00000000 0x20 0x00000000>; /* mem prefetchable */ num-lanes = <0x8>; interrupts = <56>, <57>, <58>, <59>, <60>, <61>, <62>, <63>, <64>; diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h index 7226e2462584..2c0f4c887289 100644 --- a/arch/riscv/include/asm/alternative-macros.h +++ b/arch/riscv/include/asm/alternative-macros.h @@ -46,7 +46,7 @@ .macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, errata_id_1, enable_1, \ new_c_2, vendor_id_2, errata_id_2, enable_2 - ALTERNATIVE_CFG \old_c, \new_c_1, \vendor_id_1, \errata_id_1, \enable_1 + ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \errata_id_1, \enable_1 ALT_NEW_CONTENT \vendor_id_2, \errata_id_2, \enable_2, \new_c_2 .endm diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 86328e3acb02..64ad1937e714 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -70,7 +70,6 @@ static_assert(RISCV_ISA_EXT_ID_MAX <= RISCV_ISA_EXT_MAX); */ enum riscv_isa_ext_key { RISCV_ISA_EXT_KEY_FPU, /* For 'F' and 'D' */ - RISCV_ISA_EXT_KEY_ZIHINTPAUSE, RISCV_ISA_EXT_KEY_SVINVAL, RISCV_ISA_EXT_KEY_MAX, }; @@ -91,8 +90,6 @@ static __always_inline int riscv_isa_ext2key(int num) return RISCV_ISA_EXT_KEY_FPU; case RISCV_ISA_EXT_d: return RISCV_ISA_EXT_KEY_FPU; - case RISCV_ISA_EXT_ZIHINTPAUSE: - return RISCV_ISA_EXT_KEY_ZIHINTPAUSE; case RISCV_ISA_EXT_SVINVAL: return RISCV_ISA_EXT_KEY_SVINVAL; default: diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index 93f43a3e7886..cc7da66ee0c0 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -18,6 +18,7 @@ #include <asm/kvm_vcpu_insn.h> #include <asm/kvm_vcpu_sbi.h> #include <asm/kvm_vcpu_timer.h> +#include <asm/kvm_vcpu_pmu.h> #define KVM_MAX_VCPUS 1024 @@ -228,9 +229,11 @@ struct kvm_vcpu_arch { /* Don't run the VCPU (blocked) */ bool pause; + + /* Performance monitoring context */ + struct kvm_pmu pmu_context; }; -static inline void kvm_arch_hardware_unsetup(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} @@ -297,11 +300,11 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, int kvm_riscv_gstage_alloc_pgd(struct kvm *kvm); void kvm_riscv_gstage_free_pgd(struct kvm *kvm); void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu); -void kvm_riscv_gstage_mode_detect(void); -unsigned long kvm_riscv_gstage_mode(void); +void __init kvm_riscv_gstage_mode_detect(void); +unsigned long __init kvm_riscv_gstage_mode(void); int kvm_riscv_gstage_gpa_bits(void); -void kvm_riscv_gstage_vmid_detect(void); +void __init kvm_riscv_gstage_vmid_detect(void); unsigned long kvm_riscv_gstage_vmid_bits(void); int kvm_riscv_gstage_vmid_init(struct kvm *kvm); bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid); diff --git a/arch/riscv/include/asm/kvm_vcpu_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h new file mode 100644 index 000000000000..395518a1664e --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra <atishp@rivosinc.com> + */ + +#ifndef __KVM_VCPU_RISCV_PMU_H +#define __KVM_VCPU_RISCV_PMU_H + +#include <linux/perf/riscv_pmu.h> +#include <asm/sbi.h> + +#ifdef CONFIG_RISCV_PMU_SBI +#define RISCV_KVM_MAX_FW_CTRS 32 +#define RISCV_KVM_MAX_HW_CTRS 32 +#define RISCV_KVM_MAX_COUNTERS (RISCV_KVM_MAX_HW_CTRS + RISCV_KVM_MAX_FW_CTRS) +static_assert(RISCV_KVM_MAX_COUNTERS <= 64); + +struct kvm_fw_event { + /* Current value of the event */ + unsigned long value; + + /* Event monitoring status */ + bool started; +}; + +/* Per virtual pmu counter data */ +struct kvm_pmc { + u8 idx; + struct perf_event *perf_event; + u64 counter_val; + union sbi_pmu_ctr_info cinfo; + /* Event monitoring status */ + bool started; + /* Monitoring event ID */ + unsigned long event_idx; +}; + +/* PMU data structure per vcpu */ +struct kvm_pmu { + struct kvm_pmc pmc[RISCV_KVM_MAX_COUNTERS]; + struct kvm_fw_event fw_event[RISCV_KVM_MAX_FW_CTRS]; + /* Number of the virtual firmware counters available */ + int num_fw_ctrs; + /* Number of the virtual hardware counters available */ + int num_hw_ctrs; + /* A flag to indicate that pmu initialization is done */ + bool init_done; + /* Bit map of all the virtual counter used */ + DECLARE_BITMAP(pmc_in_use, RISCV_KVM_MAX_COUNTERS); +}; + +#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu_context) +#define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu_context)) + +#if defined(CONFIG_32BIT) +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = CSR_CYCLEH, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, \ +{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, +#else +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, +#endif + +int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid); +int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); + +int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, u64 ival, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + unsigned long eidx, u64 evtdata, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); +void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu); + +#else +struct kvm_pmu { +}; + +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = 0, .count = 0, .func = NULL }, + +static inline void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) {} +static inline int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid) +{ + return 0; +} + +static inline void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) {} +static inline void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) {} +#endif /* CONFIG_RISCV_PMU_SBI */ +#endif /* !__KVM_VCPU_RISCV_PMU_H */ diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h index f79478a85d2d..8425556af7d1 100644 --- a/arch/riscv/include/asm/kvm_vcpu_sbi.h +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -18,6 +18,13 @@ struct kvm_vcpu_sbi_context { int return_handled; }; +struct kvm_vcpu_sbi_return { + unsigned long out_val; + unsigned long err_val; + struct kvm_cpu_trap *utrap; + bool uexit; +}; + struct kvm_vcpu_sbi_extension { unsigned long extid_start; unsigned long extid_end; @@ -27,8 +34,10 @@ struct kvm_vcpu_sbi_extension { * specific error codes. */ int (*handler)(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, struct kvm_cpu_trap *utrap, - bool *exit); + struct kvm_vcpu_sbi_return *retdata); + + /* Extension specific probe function */ + unsigned long (*probe)(struct kvm_vcpu *vcpu); }; void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run); diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 4ca7fbacff42..945b7be249c1 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -169,9 +169,9 @@ enum sbi_pmu_fw_generic_events_t { SBI_PMU_FW_ILLEGAL_INSN = 4, SBI_PMU_FW_SET_TIMER = 5, SBI_PMU_FW_IPI_SENT = 6, - SBI_PMU_FW_IPI_RECVD = 7, + SBI_PMU_FW_IPI_RCVD = 7, SBI_PMU_FW_FENCE_I_SENT = 8, - SBI_PMU_FW_FENCE_I_RECVD = 9, + SBI_PMU_FW_FENCE_I_RCVD = 9, SBI_PMU_FW_SFENCE_VMA_SENT = 10, SBI_PMU_FW_SFENCE_VMA_RCVD = 11, SBI_PMU_FW_SFENCE_VMA_ASID_SENT = 12, @@ -215,6 +215,9 @@ enum sbi_pmu_ctr_type { #define SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK 0x06 #define SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK 0x01 +#define SBI_PMU_EVENT_CACHE_ID_SHIFT 3 +#define SBI_PMU_EVENT_CACHE_OP_SHIFT 1 + #define SBI_PMU_EVENT_IDX_INVALID 0xFFFFFFFF /* Flags defined for config matching function */ diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index fa70cfe507aa..14f5d27783b8 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -4,30 +4,26 @@ #ifndef __ASSEMBLY__ -#include <linux/jump_label.h> #include <asm/barrier.h> -#include <asm/hwcap.h> static inline void cpu_relax(void) { - if (!static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_ZIHINTPAUSE])) { #ifdef __riscv_muldiv - int dummy; - /* In lieu of a halt instruction, induce a long-latency stall. */ - __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); + int dummy; + /* In lieu of a halt instruction, induce a long-latency stall. */ + __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); #endif - } else { - /* - * Reduce instruction retirement. - * This assumes the PC changes. - */ -#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE - __asm__ __volatile__ ("pause"); + +#ifdef __riscv_zihintpause + /* + * Reduce instruction retirement. + * This assumes the PC changes. + */ + __asm__ __volatile__ ("pause"); #else - /* Encoding of the pause instruction */ - __asm__ __volatile__ (".4byte 0x100000F"); + /* Encoding of the pause instruction */ + __asm__ __volatile__ (".4byte 0x100000F"); #endif - } barrier(); } diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index b865046e4dbb..4bf6c449d78b 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -326,7 +326,7 @@ clear_bss_done: call soc_early_init tail start_kernel -#if CONFIG_RISCV_BOOT_SPINWAIT +#ifdef CONFIG_RISCV_BOOT_SPINWAIT .Lsecondary_start: /* Set trap vector to spin forever to help debug */ la a3, .Lsecondary_park diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index f21592d20306..41c7481afde3 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -48,6 +48,21 @@ static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) post_kprobe_handler(p, kcb, regs); } +static bool __kprobes arch_check_kprobe(struct kprobe *p) +{ + unsigned long tmp = (unsigned long)p->addr - p->offset; + unsigned long addr = (unsigned long)p->addr; + + while (tmp <= addr) { + if (tmp == addr) + return true; + + tmp += GET_INSN_LENGTH(*(u16 *)tmp); + } + + return false; +} + int __kprobes arch_prepare_kprobe(struct kprobe *p) { unsigned long probe_addr = (unsigned long)p->addr; @@ -55,6 +70,9 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) if (probe_addr & 0x1) return -EILSEQ; + if (!arch_check_kprobe(p)) + return -EILSEQ; + /* copy instruction */ p->opcode = *p->addr; diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c index d73e96f6ed7c..a20568bd1f1a 100644 --- a/arch/riscv/kernel/probes/simulate-insn.c +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -71,11 +71,11 @@ bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *reg u32 rd_index = (opcode >> 7) & 0x1f; u32 rs1_index = (opcode >> 15) & 0x1f; - ret = rv_insn_reg_set_val(regs, rd_index, addr + 4); + ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr); if (!ret) return ret; - ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr); + ret = rv_insn_reg_set_val(regs, rd_index, addr + 4); if (!ret) return ret; diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 3373df413c88..ddb2afba6d25 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -39,7 +39,6 @@ static DECLARE_COMPLETION(cpu_running); void __init smp_prepare_boot_cpu(void) { - init_cpu_topology(); } void __init smp_prepare_cpus(unsigned int max_cpus) @@ -48,6 +47,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus) int ret; unsigned int curr_cpuid; + init_cpu_topology(); + curr_cpuid = smp_processor_id(); store_cpu_topology(curr_cpuid); numa_store_cpu_info(curr_cpuid); diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig index f36a737d5f96..d5a658a047a7 100644 --- a/arch/riscv/kvm/Kconfig +++ b/arch/riscv/kvm/Kconfig @@ -20,6 +20,7 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)" depends on RISCV_SBI && MMU + select KVM_GENERIC_HARDWARE_ENABLING select MMU_NOTIFIER select PREEMPT_NOTIFIERS select KVM_MMIO diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 019df9208bdd..278e97c06e0a 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -25,3 +25,4 @@ kvm-y += vcpu_sbi_base.o kvm-y += vcpu_sbi_replace.o kvm-y += vcpu_sbi_hsm.o kvm-y += vcpu_timer.o +kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o vcpu_sbi_pmu.o diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c index 58c5489d3031..41ad7639a17b 100644 --- a/arch/riscv/kvm/main.c +++ b/arch/riscv/kvm/main.c @@ -20,16 +20,6 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - -int kvm_arch_hardware_setup(void *opaque) -{ - return 0; -} - int kvm_arch_hardware_enable(void) { unsigned long hideleg, hedeleg; @@ -49,7 +39,8 @@ int kvm_arch_hardware_enable(void) hideleg |= (1UL << IRQ_VS_EXT); csr_write(CSR_HIDELEG, hideleg); - csr_write(CSR_HCOUNTEREN, -1UL); + /* VS should access only the time counter directly. Everything else should trap */ + csr_write(CSR_HCOUNTEREN, 0x02); csr_write(CSR_HVIP, 0); @@ -70,7 +61,7 @@ void kvm_arch_hardware_disable(void) csr_write(CSR_HIDELEG, 0); } -int kvm_arch_init(void *opaque) +static int __init riscv_kvm_init(void) { const char *str; @@ -115,16 +106,7 @@ int kvm_arch_init(void *opaque) kvm_info("VMID %ld bits available\n", kvm_riscv_gstage_vmid_bits()); - return 0; -} - -void kvm_arch_exit(void) -{ -} - -static int __init riscv_kvm_init(void) -{ - return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + return kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); } module_init(riscv_kvm_init); diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c index 34b57e0be2ef..78211aed36fa 100644 --- a/arch/riscv/kvm/mmu.c +++ b/arch/riscv/kvm/mmu.c @@ -20,12 +20,12 @@ #include <asm/pgtable.h> #ifdef CONFIG_64BIT -static unsigned long gstage_mode = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT); -static unsigned long gstage_pgd_levels = 3; +static unsigned long gstage_mode __ro_after_init = (HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT); +static unsigned long gstage_pgd_levels __ro_after_init = 3; #define gstage_index_bits 9 #else -static unsigned long gstage_mode = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT); -static unsigned long gstage_pgd_levels = 2; +static unsigned long gstage_mode __ro_after_init = (HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT); +static unsigned long gstage_pgd_levels __ro_after_init = 2; #define gstage_index_bits 10 #endif @@ -585,7 +585,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (!kvm->arch.pgd) return false; - WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE); + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, &ptep, &ptep_level)) @@ -603,7 +603,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (!kvm->arch.pgd) return false; - WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE); + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); if (!gstage_get_leaf_entry(kvm, range->start << PAGE_SHIFT, &ptep, &ptep_level)) @@ -645,12 +645,12 @@ int kvm_riscv_gstage_map(struct kvm_vcpu *vcpu, if (logging || (vma->vm_flags & VM_PFNMAP)) vma_pagesize = PAGE_SIZE; - if (vma_pagesize == PMD_SIZE || vma_pagesize == PGDIR_SIZE) + if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) gfn = (gpa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT; mmap_read_unlock(current->mm); - if (vma_pagesize != PGDIR_SIZE && + if (vma_pagesize != PUD_SIZE && vma_pagesize != PMD_SIZE && vma_pagesize != PAGE_SIZE) { kvm_err("Invalid VMA page size 0x%lx\n", vma_pagesize); @@ -758,7 +758,7 @@ void kvm_riscv_gstage_update_hgatp(struct kvm_vcpu *vcpu) kvm_riscv_local_hfence_gvma_all(); } -void kvm_riscv_gstage_mode_detect(void) +void __init kvm_riscv_gstage_mode_detect(void) { #ifdef CONFIG_64BIT /* Try Sv57x4 G-stage mode */ @@ -782,7 +782,7 @@ skip_sv48x4_test: #endif } -unsigned long kvm_riscv_gstage_mode(void) +unsigned long __init kvm_riscv_gstage_mode(void) { return gstage_mode >> HGATP_MODE_SHIFT; } diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c index 309d79b3e5cd..b797f7cc0824 100644 --- a/arch/riscv/kvm/tlb.c +++ b/arch/riscv/kvm/tlb.c @@ -181,6 +181,7 @@ void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu) void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu) { + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_RCVD); local_flush_icache_all(); } @@ -264,15 +265,18 @@ void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu) d.addr, d.size, d.order); break; case KVM_RISCV_HFENCE_VVMA_ASID_GVA: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); kvm_riscv_local_hfence_vvma_asid_gva( READ_ONCE(v->vmid), d.asid, d.addr, d.size, d.order); break; case KVM_RISCV_HFENCE_VVMA_ASID_ALL: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); kvm_riscv_local_hfence_vvma_asid_all( READ_ONCE(v->vmid), d.asid); break; case KVM_RISCV_HFENCE_VVMA_GVA: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_RCVD); kvm_riscv_local_hfence_vvma_gva( READ_ONCE(v->vmid), d.addr, d.size, d.order); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 7c08567097f0..7d010b0be54e 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -138,6 +138,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) WRITE_ONCE(vcpu->arch.irqs_pending, 0); WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0); + kvm_riscv_vcpu_pmu_reset(vcpu); + vcpu->arch.hfence_head = 0; vcpu->arch.hfence_tail = 0; memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue)); @@ -194,6 +196,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) /* Setup VCPU timer */ kvm_riscv_vcpu_timer_init(vcpu); + /* setup performance monitoring */ + kvm_riscv_vcpu_pmu_init(vcpu); + /* Reset VCPU */ kvm_riscv_reset_vcpu(vcpu); @@ -216,6 +221,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) /* Cleanup VCPU timer */ kvm_riscv_vcpu_timer_deinit(vcpu); + kvm_riscv_vcpu_pmu_deinit(vcpu); + /* Free unused pages pre-allocated for G-stage page table mappings */ kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); } diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index c9f741ab26f5..4ea101a73d8b 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -160,6 +160,9 @@ void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, /* Set Guest PC to Guest exception vector */ vcpu->arch.guest_context.sepc = csr_read(CSR_VSTVEC); + + /* Set Guest privilege mode to supervisor */ + vcpu->arch.guest_context.sstatus |= SR_SPP; } /* @@ -179,6 +182,12 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, ret = -EFAULT; run->exit_reason = KVM_EXIT_UNKNOWN; switch (trap->scause) { + case EXC_INST_ILLEGAL: + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) { + kvm_riscv_vcpu_trap_redirect(vcpu, trap); + ret = 1; + } + break; case EXC_VIRTUAL_INST_FAULT: if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) ret = kvm_riscv_vcpu_virtual_insn(vcpu, run, trap); diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c index 0bb52761a3f7..f689337b78ff 100644 --- a/arch/riscv/kvm/vcpu_insn.c +++ b/arch/riscv/kvm/vcpu_insn.c @@ -213,7 +213,9 @@ struct csr_func { unsigned long wr_mask); }; -static const struct csr_func csr_funcs[] = { }; +static const struct csr_func csr_funcs[] = { + KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS +}; /** * kvm_riscv_vcpu_csr_return -- Handle CSR read/write after user space diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c new file mode 100644 index 000000000000..86391a5061dd --- /dev/null +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -0,0 +1,633 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra <atishp@rivosinc.com> + */ + +#define pr_fmt(fmt) "riscv-kvm-pmu: " fmt +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/kvm_host.h> +#include <linux/perf/riscv_pmu.h> +#include <asm/csr.h> +#include <asm/kvm_vcpu_sbi.h> +#include <asm/kvm_vcpu_pmu.h> +#include <linux/bitops.h> + +#define kvm_pmu_num_counters(pmu) ((pmu)->num_hw_ctrs + (pmu)->num_fw_ctrs) +#define get_event_type(x) (((x) & SBI_PMU_EVENT_IDX_TYPE_MASK) >> 16) +#define get_event_code(x) ((x) & SBI_PMU_EVENT_IDX_CODE_MASK) + +static enum perf_hw_id hw_event_perf_map[SBI_PMU_HW_GENERAL_MAX] = { + [SBI_PMU_HW_CPU_CYCLES] = PERF_COUNT_HW_CPU_CYCLES, + [SBI_PMU_HW_INSTRUCTIONS] = PERF_COUNT_HW_INSTRUCTIONS, + [SBI_PMU_HW_CACHE_REFERENCES] = PERF_COUNT_HW_CACHE_REFERENCES, + [SBI_PMU_HW_CACHE_MISSES] = PERF_COUNT_HW_CACHE_MISSES, + [SBI_PMU_HW_BRANCH_INSTRUCTIONS] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + [SBI_PMU_HW_BRANCH_MISSES] = PERF_COUNT_HW_BRANCH_MISSES, + [SBI_PMU_HW_BUS_CYCLES] = PERF_COUNT_HW_BUS_CYCLES, + [SBI_PMU_HW_STALLED_CYCLES_FRONTEND] = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND, + [SBI_PMU_HW_STALLED_CYCLES_BACKEND] = PERF_COUNT_HW_STALLED_CYCLES_BACKEND, + [SBI_PMU_HW_REF_CPU_CYCLES] = PERF_COUNT_HW_REF_CPU_CYCLES, +}; + +static u64 kvm_pmu_get_sample_period(struct kvm_pmc *pmc) +{ + u64 counter_val_mask = GENMASK(pmc->cinfo.width, 0); + u64 sample_period; + + if (!pmc->counter_val) + sample_period = counter_val_mask + 1; + else + sample_period = (-pmc->counter_val) & counter_val_mask; + + return sample_period; +} + +static u32 kvm_pmu_get_perf_event_type(unsigned long eidx) +{ + enum sbi_pmu_event_type etype = get_event_type(eidx); + u32 type = PERF_TYPE_MAX; + + switch (etype) { + case SBI_PMU_EVENT_TYPE_HW: + type = PERF_TYPE_HARDWARE; + break; + case SBI_PMU_EVENT_TYPE_CACHE: + type = PERF_TYPE_HW_CACHE; + break; + case SBI_PMU_EVENT_TYPE_RAW: + case SBI_PMU_EVENT_TYPE_FW: + type = PERF_TYPE_RAW; + break; + default: + break; + } + + return type; +} + +static bool kvm_pmu_is_fw_event(unsigned long eidx) +{ + return get_event_type(eidx) == SBI_PMU_EVENT_TYPE_FW; +} + +static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + perf_event_disable(pmc->perf_event); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +static u64 kvm_pmu_get_perf_event_hw_config(u32 sbi_event_code) +{ + return hw_event_perf_map[sbi_event_code]; +} + +static u64 kvm_pmu_get_perf_event_cache_config(u32 sbi_event_code) +{ + u64 config = U64_MAX; + unsigned int cache_type, cache_op, cache_result; + + /* All the cache event masks lie within 0xFF. No separate masking is necessary */ + cache_type = (sbi_event_code & SBI_PMU_EVENT_CACHE_ID_CODE_MASK) >> + SBI_PMU_EVENT_CACHE_ID_SHIFT; + cache_op = (sbi_event_code & SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK) >> + SBI_PMU_EVENT_CACHE_OP_SHIFT; + cache_result = sbi_event_code & SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK; + + if (cache_type >= PERF_COUNT_HW_CACHE_MAX || + cache_op >= PERF_COUNT_HW_CACHE_OP_MAX || + cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return config; + + config = cache_type | (cache_op << 8) | (cache_result << 16); + + return config; +} + +static u64 kvm_pmu_get_perf_event_config(unsigned long eidx, uint64_t evt_data) +{ + enum sbi_pmu_event_type etype = get_event_type(eidx); + u32 ecode = get_event_code(eidx); + u64 config = U64_MAX; + + switch (etype) { + case SBI_PMU_EVENT_TYPE_HW: + if (ecode < SBI_PMU_HW_GENERAL_MAX) + config = kvm_pmu_get_perf_event_hw_config(ecode); + break; + case SBI_PMU_EVENT_TYPE_CACHE: + config = kvm_pmu_get_perf_event_cache_config(ecode); + break; + case SBI_PMU_EVENT_TYPE_RAW: + config = evt_data & RISCV_PMU_RAW_EVENT_MASK; + break; + case SBI_PMU_EVENT_TYPE_FW: + if (ecode < SBI_PMU_FW_MAX) + config = (1ULL << 63) | ecode; + break; + default: + break; + } + + return config; +} + +static int kvm_pmu_get_fixed_pmc_index(unsigned long eidx) +{ + u32 etype = kvm_pmu_get_perf_event_type(eidx); + u32 ecode = get_event_code(eidx); + + if (etype != SBI_PMU_EVENT_TYPE_HW) + return -EINVAL; + + if (ecode == SBI_PMU_HW_CPU_CYCLES) + return 0; + else if (ecode == SBI_PMU_HW_INSTRUCTIONS) + return 2; + else + return -EINVAL; +} + +static int kvm_pmu_get_programmable_pmc_index(struct kvm_pmu *kvpmu, unsigned long eidx, + unsigned long cbase, unsigned long cmask) +{ + int ctr_idx = -1; + int i, pmc_idx; + int min, max; + + if (kvm_pmu_is_fw_event(eidx)) { + /* Firmware counters are mapped 1:1 starting from num_hw_ctrs for simplicity */ + min = kvpmu->num_hw_ctrs; + max = min + kvpmu->num_fw_ctrs; + } else { + /* First 3 counters are reserved for fixed counters */ + min = 3; + max = kvpmu->num_hw_ctrs; + } + + for_each_set_bit(i, &cmask, BITS_PER_LONG) { + pmc_idx = i + cbase; + if ((pmc_idx >= min && pmc_idx < max) && + !test_bit(pmc_idx, kvpmu->pmc_in_use)) { + ctr_idx = pmc_idx; + break; + } + } + + return ctr_idx; +} + +static int pmu_get_pmc_index(struct kvm_pmu *pmu, unsigned long eidx, + unsigned long cbase, unsigned long cmask) +{ + int ret; + + /* Fixed counters need to be have fixed mapping as they have different width */ + ret = kvm_pmu_get_fixed_pmc_index(eidx); + if (ret >= 0) + return ret; + + return kvm_pmu_get_programmable_pmc_index(pmu, eidx, cbase, cmask); +} + +static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + unsigned long *out_val) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u64 enabled, running; + int fevent_code; + + pmc = &kvpmu->pmc[cidx]; + + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + pmc->counter_val = kvpmu->fw_event[fevent_code].value; + } else if (pmc->perf_event) { + pmc->counter_val += perf_event_read_value(pmc->perf_event, &enabled, &running); + } else { + return -EINVAL; + } + *out_val = pmc->counter_val; + + return 0; +} + +static int kvm_pmu_validate_counter_mask(struct kvm_pmu *kvpmu, unsigned long ctr_base, + unsigned long ctr_mask) +{ + /* Make sure the we have a valid counter mask requested from the caller */ + if (!ctr_mask || (ctr_base + __fls(ctr_mask) >= kvm_pmu_num_counters(kvpmu))) + return -EINVAL; + + return 0; +} + +static int kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_attr *attr, + unsigned long flags, unsigned long eidx, unsigned long evtdata) +{ + struct perf_event *event; + + kvm_pmu_release_perf_event(pmc); + attr->config = kvm_pmu_get_perf_event_config(eidx, evtdata); + if (flags & SBI_PMU_CFG_FLAG_CLEAR_VALUE) { + //TODO: Do we really want to clear the value in hardware counter + pmc->counter_val = 0; + } + + /* + * Set the default sample_period for now. The guest specified value + * will be updated in the start call. + */ + attr->sample_period = kvm_pmu_get_sample_period(pmc); + + event = perf_event_create_kernel_counter(attr, -1, current, NULL, pmc); + if (IS_ERR(event)) { + pr_err("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event)); + return PTR_ERR(event); + } + + pmc->perf_event = event; + if (flags & SBI_PMU_CFG_FLAG_AUTO_START) + perf_event_enable(pmc->perf_event); + + return 0; +} + +int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_fw_event *fevent; + + if (!kvpmu || fid >= SBI_PMU_FW_MAX) + return -EINVAL; + + fevent = &kvpmu->fw_event[fid]; + if (fevent->started) + fevent->value++; + + return 0; +} + +int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int cidx, ret = KVM_INSN_CONTINUE_NEXT_SEPC; + + if (!kvpmu || !kvpmu->init_done) { + /* + * In absence of sscofpmf in the platform, the guest OS may use + * the legacy PMU driver to read cycle/instret. In that case, + * just return 0 to avoid any illegal trap. However, any other + * hpmcounter access should result in illegal trap as they must + * be access through SBI PMU only. + */ + if (csr_num == CSR_CYCLE || csr_num == CSR_INSTRET) { + *val = 0; + return ret; + } else { + return KVM_INSN_ILLEGAL_TRAP; + } + } + + /* The counter CSR are read only. Thus, any write should result in illegal traps */ + if (wr_mask) + return KVM_INSN_ILLEGAL_TRAP; + + cidx = csr_num - CSR_CYCLE; + + if (pmu_ctr_read(vcpu, cidx, val) < 0) + return KVM_INSN_ILLEGAL_TRAP; + + return ret; +} + +int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + retdata->out_val = kvm_pmu_num_counters(kvpmu); + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + if (cidx > RISCV_KVM_MAX_COUNTERS || cidx == 1) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + + retdata->out_val = kvpmu->pmc[cidx].cinfo.value; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, u64 ival, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int i, pmc_index, sbiret = 0; + struct kvm_pmc *pmc; + int fevent_code; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Start the counters that have been configured and requested by the guest */ + for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { + pmc_index = i + ctr_base; + if (!test_bit(pmc_index, kvpmu->pmc_in_use)) + continue; + pmc = &kvpmu->pmc[pmc_index]; + if (flags & SBI_PMU_START_FLAG_SET_INIT_VALUE) + pmc->counter_val = ival; + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + if (fevent_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Check if the counter was already started for some reason */ + if (kvpmu->fw_event[fevent_code].started) { + sbiret = SBI_ERR_ALREADY_STARTED; + continue; + } + + kvpmu->fw_event[fevent_code].started = true; + kvpmu->fw_event[fevent_code].value = pmc->counter_val; + } else if (pmc->perf_event) { + if (unlikely(pmc->started)) { + sbiret = SBI_ERR_ALREADY_STARTED; + continue; + } + perf_event_period(pmc->perf_event, kvm_pmu_get_sample_period(pmc)); + perf_event_enable(pmc->perf_event); + pmc->started = true; + } else { + sbiret = SBI_ERR_INVALID_PARAM; + } + } + +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int i, pmc_index, sbiret = 0; + u64 enabled, running; + struct kvm_pmc *pmc; + int fevent_code; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Stop the counters that have been configured and requested by the guest */ + for_each_set_bit(i, &ctr_mask, RISCV_MAX_COUNTERS) { + pmc_index = i + ctr_base; + if (!test_bit(pmc_index, kvpmu->pmc_in_use)) + continue; + pmc = &kvpmu->pmc[pmc_index]; + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + if (fevent_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + if (!kvpmu->fw_event[fevent_code].started) + sbiret = SBI_ERR_ALREADY_STOPPED; + + kvpmu->fw_event[fevent_code].started = false; + } else if (pmc->perf_event) { + if (pmc->started) { + /* Stop counting the counter */ + perf_event_disable(pmc->perf_event); + pmc->started = false; + } else { + sbiret = SBI_ERR_ALREADY_STOPPED; + } + + if (flags & SBI_PMU_STOP_FLAG_RESET) { + /* Relase the counter if this is a reset request */ + pmc->counter_val += perf_event_read_value(pmc->perf_event, + &enabled, &running); + kvm_pmu_release_perf_event(pmc); + } + } else { + sbiret = SBI_ERR_INVALID_PARAM; + } + if (flags & SBI_PMU_STOP_FLAG_RESET) { + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + clear_bit(pmc_index, kvpmu->pmc_in_use); + } + } + +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + unsigned long eidx, u64 evtdata, + struct kvm_vcpu_sbi_return *retdata) +{ + int ctr_idx, ret, sbiret = 0; + bool is_fevent; + unsigned long event_code; + u32 etype = kvm_pmu_get_perf_event_type(eidx); + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = NULL; + struct perf_event_attr attr = { + .type = etype, + .size = sizeof(struct perf_event_attr), + .pinned = true, + /* + * It should never reach here if the platform doesn't support the sscofpmf + * extension as mode filtering won't work without it. + */ + .exclude_host = true, + .exclude_hv = true, + .exclude_user = !!(flags & SBI_PMU_CFG_FLAG_SET_UINH), + .exclude_kernel = !!(flags & SBI_PMU_CFG_FLAG_SET_SINH), + .config1 = RISCV_PMU_CONFIG1_GUEST_EVENTS, + }; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + event_code = get_event_code(eidx); + is_fevent = kvm_pmu_is_fw_event(eidx); + if (is_fevent && event_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } + + /* + * SKIP_MATCH flag indicates the caller is aware of the assigned counter + * for this event. Just do a sanity check if it already marked used. + */ + if (flags & SBI_PMU_CFG_FLAG_SKIP_MATCH) { + if (!test_bit(ctr_base + __ffs(ctr_mask), kvpmu->pmc_in_use)) { + sbiret = SBI_ERR_FAILURE; + goto out; + } + ctr_idx = ctr_base + __ffs(ctr_mask); + } else { + ctr_idx = pmu_get_pmc_index(kvpmu, eidx, ctr_base, ctr_mask); + if (ctr_idx < 0) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } + } + + pmc = &kvpmu->pmc[ctr_idx]; + pmc->idx = ctr_idx; + + if (is_fevent) { + if (flags & SBI_PMU_CFG_FLAG_AUTO_START) + kvpmu->fw_event[event_code].started = true; + } else { + ret = kvm_pmu_create_perf_event(pmc, &attr, flags, eidx, evtdata); + if (ret) + return ret; + } + + set_bit(ctr_idx, kvpmu->pmc_in_use); + pmc->event_idx = eidx; + retdata->out_val = ctr_idx; +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret; + + ret = pmu_ctr_read(vcpu, cidx, &retdata->out_val); + if (ret == -EINVAL) + retdata->err_val = SBI_ERR_INVALID_PARAM; + + return 0; +} + +void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) +{ + int i = 0, ret, num_hw_ctrs = 0, hpm_width = 0; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + /* + * PMU functionality should be only available to guests if privilege mode + * filtering is available in the host. Otherwise, guest will always count + * events while the execution is in hypervisor mode. + */ + if (!riscv_isa_extension_available(NULL, SSCOFPMF)) + return; + + ret = riscv_pmu_get_hpm_info(&hpm_width, &num_hw_ctrs); + if (ret < 0 || !hpm_width || !num_hw_ctrs) + return; + + /* + * Increase the number of hardware counters to offset the time counter. + */ + kvpmu->num_hw_ctrs = num_hw_ctrs + 1; + kvpmu->num_fw_ctrs = SBI_PMU_FW_MAX; + memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); + + if (kvpmu->num_hw_ctrs > RISCV_KVM_MAX_HW_CTRS) { + pr_warn_once("Limiting the hardware counters to 32 as specified by the ISA"); + kvpmu->num_hw_ctrs = RISCV_KVM_MAX_HW_CTRS; + } + + /* + * There is no correlation between the logical hardware counter and virtual counters. + * However, we need to encode a hpmcounter CSR in the counter info field so that + * KVM can trap n emulate the read. This works well in the migration use case as + * KVM doesn't care if the actual hpmcounter is available in the hardware or not. + */ + for (i = 0; i < kvm_pmu_num_counters(kvpmu); i++) { + /* TIME CSR shouldn't be read from perf interface */ + if (i == 1) + continue; + pmc = &kvpmu->pmc[i]; + pmc->idx = i; + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + if (i < kvpmu->num_hw_ctrs) { + pmc->cinfo.type = SBI_PMU_CTR_TYPE_HW; + if (i < 3) + /* CY, IR counters */ + pmc->cinfo.width = 63; + else + pmc->cinfo.width = hpm_width; + /* + * The CSR number doesn't have any relation with the logical + * hardware counters. The CSR numbers are encoded sequentially + * to avoid maintaining a map between the virtual counter + * and CSR number. + */ + pmc->cinfo.csr = CSR_CYCLE + i; + } else { + pmc->cinfo.type = SBI_PMU_CTR_TYPE_FW; + pmc->cinfo.width = BITS_PER_LONG - 1; + } + } + + kvpmu->init_done = true; +} + +void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int i; + + if (!kvpmu) + return; + + for_each_set_bit(i, kvpmu->pmc_in_use, RISCV_MAX_COUNTERS) { + pmc = &kvpmu->pmc[i]; + pmc->counter_val = 0; + kvm_pmu_release_perf_event(pmc); + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + } + bitmap_zero(kvpmu->pmc_in_use, RISCV_MAX_COUNTERS); + memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); +} + +void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) +{ + kvm_riscv_vcpu_pmu_deinit(vcpu); +} diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index f96991d230bf..15fde15f9fb8 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -12,26 +12,6 @@ #include <asm/sbi.h> #include <asm/kvm_vcpu_sbi.h> -static int kvm_linux_err_map_sbi(int err) -{ - switch (err) { - case 0: - return SBI_SUCCESS; - case -EPERM: - return SBI_ERR_DENIED; - case -EINVAL: - return SBI_ERR_INVALID_PARAM; - case -EFAULT: - return SBI_ERR_INVALID_ADDRESS; - case -EOPNOTSUPP: - return SBI_ERR_NOT_SUPPORTED; - case -EALREADY: - return SBI_ERR_ALREADY_AVAILABLE; - default: - return SBI_ERR_FAILURE; - }; -} - #ifndef CONFIG_RISCV_SBI_V01 static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { .extid_start = -1UL, @@ -40,6 +20,16 @@ static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { }; #endif +#ifdef CONFIG_RISCV_PMU_SBI +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu; +#else +static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu = { + .extid_start = -1UL, + .extid_end = -1UL, + .handler = NULL, +}; +#endif + static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_v01, &vcpu_sbi_ext_base, @@ -48,6 +38,7 @@ static const struct kvm_vcpu_sbi_extension *sbi_ext[] = { &vcpu_sbi_ext_rfence, &vcpu_sbi_ext_srst, &vcpu_sbi_ext_hsm, + &vcpu_sbi_ext_pmu, &vcpu_sbi_ext_experimental, &vcpu_sbi_ext_vendor, }; @@ -125,11 +116,14 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) { int ret = 1; bool next_sepc = true; - bool userspace_exit = false; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; const struct kvm_vcpu_sbi_extension *sbi_ext; - struct kvm_cpu_trap utrap = { 0 }; - unsigned long out_val = 0; + struct kvm_cpu_trap utrap = {0}; + struct kvm_vcpu_sbi_return sbi_ret = { + .out_val = 0, + .err_val = 0, + .utrap = &utrap, + }; bool ext_is_v01 = false; sbi_ext = kvm_vcpu_sbi_find_ext(cp->a7); @@ -139,42 +133,46 @@ int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) cp->a7 <= SBI_EXT_0_1_SHUTDOWN) ext_is_v01 = true; #endif - ret = sbi_ext->handler(vcpu, run, &out_val, &utrap, &userspace_exit); + ret = sbi_ext->handler(vcpu, run, &sbi_ret); } else { /* Return error for unsupported SBI calls */ cp->a0 = SBI_ERR_NOT_SUPPORTED; goto ecall_done; } + /* + * When the SBI extension returns a Linux error code, it exits the ioctl + * loop and forwards the error to userspace. + */ + if (ret < 0) { + next_sepc = false; + goto ecall_done; + } + /* Handle special error cases i.e trap, exit or userspace forward */ - if (utrap.scause) { + if (sbi_ret.utrap->scause) { /* No need to increment sepc or exit ioctl loop */ ret = 1; - utrap.sepc = cp->sepc; - kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + sbi_ret.utrap->sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, sbi_ret.utrap); next_sepc = false; goto ecall_done; } /* Exit ioctl loop or Propagate the error code the guest */ - if (userspace_exit) { + if (sbi_ret.uexit) { next_sepc = false; ret = 0; } else { - /** - * SBI extension handler always returns an Linux error code. Convert - * it to the SBI specific error code that can be propagated the SBI - * caller. - */ - ret = kvm_linux_err_map_sbi(ret); - cp->a0 = ret; + cp->a0 = sbi_ret.err_val; ret = 1; } ecall_done: if (next_sepc) cp->sepc += 4; - if (!ext_is_v01) - cp->a1 = out_val; + /* a1 should only be updated when we continue the ioctl loop */ + if (!ext_is_v01 && ret == 1) + cp->a1 = sbi_ret.out_val; return ret; } diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c index 5d65c634d301..9945aff34c14 100644 --- a/arch/riscv/kvm/vcpu_sbi_base.c +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -14,11 +14,11 @@ #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *trap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { - int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + const struct kvm_vcpu_sbi_extension *sbi_ext; + unsigned long *out_val = &retdata->out_val; switch (cp->a6) { case SBI_EXT_BASE_GET_SPEC_VERSION: @@ -42,9 +42,12 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, * forward it to the userspace */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - *exit = true; - } else - *out_val = kvm_vcpu_sbi_find_ext(cp->a0) ? 1 : 0; + retdata->uexit = true; + } else { + sbi_ext = kvm_vcpu_sbi_find_ext(cp->a0); + *out_val = sbi_ext && sbi_ext->probe ? + sbi_ext->probe(vcpu) : !!sbi_ext; + } break; case SBI_EXT_BASE_GET_MVENDORID: *out_val = vcpu->arch.mvendorid; @@ -56,11 +59,11 @@ static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, *out_val = vcpu->arch.mimpid; break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; break; } - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = { @@ -70,17 +73,15 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = { }; static int kvm_sbi_ext_forward_handler(struct kvm_vcpu *vcpu, - struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) + struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) { /* * Both SBI experimental and vendor extensions are * unconditionally forwarded to userspace. */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - *exit = true; + retdata->uexit = true; return 0; } diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c index 2e915cafd551..7dca0e9381d9 100644 --- a/arch/riscv/kvm/vcpu_sbi_hsm.c +++ b/arch/riscv/kvm/vcpu_sbi_hsm.c @@ -21,9 +21,9 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); if (!target_vcpu) - return -EINVAL; + return SBI_ERR_INVALID_PARAM; if (!target_vcpu->arch.power_off) - return -EALREADY; + return SBI_ERR_ALREADY_AVAILABLE; reset_cntx = &target_vcpu->arch.guest_reset_context; /* start address */ @@ -42,7 +42,7 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) static int kvm_sbi_hsm_vcpu_stop(struct kvm_vcpu *vcpu) { if (vcpu->arch.power_off) - return -EINVAL; + return SBI_ERR_FAILURE; kvm_riscv_vcpu_power_off(vcpu); @@ -57,7 +57,7 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); if (!target_vcpu) - return -EINVAL; + return SBI_ERR_INVALID_PARAM; if (!target_vcpu->arch.power_off) return SBI_HSM_STATE_STARTED; else if (vcpu->stat.generic.blocking) @@ -67,9 +67,7 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) } static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) + struct kvm_vcpu_sbi_return *retdata) { int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; @@ -88,27 +86,29 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, case SBI_EXT_HSM_HART_STATUS: ret = kvm_sbi_hsm_vcpu_get_status(vcpu); if (ret >= 0) { - *out_val = ret; - ret = 0; + retdata->out_val = ret; + retdata->err_val = 0; } - break; + return 0; case SBI_EXT_HSM_HART_SUSPEND: switch (cp->a0) { case SBI_HSM_SUSPEND_RET_DEFAULT: kvm_riscv_vcpu_wfi(vcpu); break; case SBI_HSM_SUSPEND_NON_RET_DEFAULT: - ret = -EOPNOTSUPP; + ret = SBI_ERR_NOT_SUPPORTED; break; default: - ret = -EINVAL; + ret = SBI_ERR_INVALID_PARAM; } break; default: - ret = -EOPNOTSUPP; + ret = SBI_ERR_NOT_SUPPORTED; } - return ret; + retdata->err_val = ret; + + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm = { diff --git a/arch/riscv/kvm/vcpu_sbi_pmu.c b/arch/riscv/kvm/vcpu_sbi_pmu.c new file mode 100644 index 000000000000..7eca72df2cbd --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_pmu.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra <atishp@rivosinc.com> + */ + +#include <linux/errno.h> +#include <linux/err.h> +#include <linux/kvm_host.h> +#include <asm/csr.h> +#include <asm/sbi.h> +#include <asm/kvm_vcpu_sbi.h> + +static int kvm_sbi_ext_pmu_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret = 0; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + unsigned long funcid = cp->a6; + u64 temp; + + if (!kvpmu->init_done) { + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + return 0; + } + + switch (funcid) { + case SBI_EXT_PMU_NUM_COUNTERS: + ret = kvm_riscv_vcpu_pmu_num_ctrs(vcpu, retdata); + break; + case SBI_EXT_PMU_COUNTER_GET_INFO: + ret = kvm_riscv_vcpu_pmu_ctr_info(vcpu, cp->a0, retdata); + break; + case SBI_EXT_PMU_COUNTER_CFG_MATCH: +#if defined(CONFIG_32BIT) + temp = ((uint64_t)cp->a5 << 32) | cp->a4; +#else + temp = cp->a4; +#endif + /* + * This can fail if perf core framework fails to create an event. + * Forward the error to userspace because it's an error which + * happened within the host kernel. The other option would be + * to convert to an SBI error and forward to the guest. + */ + ret = kvm_riscv_vcpu_pmu_ctr_cfg_match(vcpu, cp->a0, cp->a1, + cp->a2, cp->a3, temp, retdata); + break; + case SBI_EXT_PMU_COUNTER_START: +#if defined(CONFIG_32BIT) + temp = ((uint64_t)cp->a4 << 32) | cp->a3; +#else + temp = cp->a3; +#endif + ret = kvm_riscv_vcpu_pmu_ctr_start(vcpu, cp->a0, cp->a1, cp->a2, + temp, retdata); + break; + case SBI_EXT_PMU_COUNTER_STOP: + ret = kvm_riscv_vcpu_pmu_ctr_stop(vcpu, cp->a0, cp->a1, cp->a2, retdata); + break; + case SBI_EXT_PMU_COUNTER_FW_READ: + ret = kvm_riscv_vcpu_pmu_ctr_read(vcpu, cp->a0, retdata); + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + } + + return ret; +} + +static unsigned long kvm_sbi_ext_pmu_probe(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + return kvpmu->init_done; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu = { + .extid_start = SBI_EXT_PMU, + .extid_end = SBI_EXT_PMU, + .handler = kvm_sbi_ext_pmu_handler, + .probe = kvm_sbi_ext_pmu_probe, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c index 03a0198389f0..7c4d5d38a339 100644 --- a/arch/riscv/kvm/vcpu_sbi_replace.c +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -11,19 +11,21 @@ #include <linux/kvm_host.h> #include <asm/sbi.h> #include <asm/kvm_vcpu_timer.h> +#include <asm/kvm_vcpu_pmu.h> #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { - int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; u64 next_cycle; - if (cp->a6 != SBI_EXT_TIME_SET_TIMER) - return -EINVAL; + if (cp->a6 != SBI_EXT_TIME_SET_TIMER) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_SET_TIMER); #if __riscv_xlen == 32 next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0; #else @@ -31,7 +33,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, #endif kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time = { @@ -41,8 +43,7 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time = { }; static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { int ret = 0; unsigned long i; @@ -51,9 +52,12 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, unsigned long hmask = cp->a0; unsigned long hbase = cp->a1; - if (cp->a6 != SBI_EXT_IPI_SEND_IPI) - return -EINVAL; + if (cp->a6 != SBI_EXT_IPI_SEND_IPI) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_IPI_SENT); kvm_for_each_vcpu(i, tmp, vcpu->kvm) { if (hbase != -1UL) { if (tmp->vcpu_id < hbase) @@ -64,6 +68,7 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT); if (ret < 0) break; + kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD); } return ret; @@ -76,10 +81,8 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi = { }; static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { - int ret = 0; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; unsigned long hmask = cp->a0; unsigned long hbase = cp->a1; @@ -88,6 +91,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run switch (funcid) { case SBI_EXT_RFENCE_REMOTE_FENCE_I: kvm_riscv_fence_i(vcpu->kvm, hbase, hmask); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: if (cp->a2 == 0 && cp->a3 == 0) @@ -95,6 +99,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run else kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, cp->a2, cp->a3, PAGE_SHIFT); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT); break; case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: if (cp->a2 == 0 && cp->a3 == 0) @@ -105,6 +110,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run hbase, hmask, cp->a2, cp->a3, PAGE_SHIFT, cp->a4); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_SENT); break; case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA: case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID: @@ -116,10 +122,10 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run */ break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; } - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = { @@ -130,14 +136,12 @@ const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = { static int kvm_sbi_ext_srst_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, bool *exit) + struct kvm_vcpu_sbi_return *retdata) { struct kvm_cpu_context *cp = &vcpu->arch.guest_context; unsigned long funcid = cp->a6; u32 reason = cp->a1; u32 type = cp->a0; - int ret = 0; switch (funcid) { case SBI_EXT_SRST_RESET: @@ -146,24 +150,24 @@ static int kvm_sbi_ext_srst_handler(struct kvm_vcpu *vcpu, kvm_riscv_vcpu_sbi_system_reset(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN, reason); - *exit = true; + retdata->uexit = true; break; case SBI_SRST_RESET_TYPE_COLD_REBOOT: case SBI_SRST_RESET_TYPE_WARM_REBOOT: kvm_riscv_vcpu_sbi_system_reset(vcpu, run, KVM_SYSTEM_EVENT_RESET, reason); - *exit = true; + retdata->uexit = true; break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; } break; default: - ret = -EOPNOTSUPP; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; } - return ret; + return 0; } const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst = { diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c index 489f225ee66d..8f4c4fa16227 100644 --- a/arch/riscv/kvm/vcpu_sbi_v01.c +++ b/arch/riscv/kvm/vcpu_sbi_v01.c @@ -14,9 +14,7 @@ #include <asm/kvm_vcpu_sbi.h> static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, - unsigned long *out_val, - struct kvm_cpu_trap *utrap, - bool *exit) + struct kvm_vcpu_sbi_return *retdata) { ulong hmask; int i, ret = 0; @@ -24,6 +22,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, struct kvm_vcpu *rvcpu; struct kvm *kvm = vcpu->kvm; struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_cpu_trap *utrap = retdata->utrap; switch (cp->a7) { case SBI_EXT_0_1_CONSOLE_GETCHAR: @@ -33,7 +32,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, * handled in kernel so we forward these to user-space */ kvm_riscv_vcpu_sbi_forward(vcpu, run); - *exit = true; + retdata->uexit = true; break; case SBI_EXT_0_1_SET_TIMER: #if __riscv_xlen == 32 @@ -48,8 +47,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, break; case SBI_EXT_0_1_SEND_IPI: if (cp->a0) - hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, - utrap); + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, utrap); else hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; if (utrap->scause) @@ -65,14 +63,13 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, case SBI_EXT_0_1_SHUTDOWN: kvm_riscv_vcpu_sbi_system_reset(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN, 0); - *exit = true; + retdata->uexit = true; break; case SBI_EXT_0_1_REMOTE_FENCE_I: case SBI_EXT_0_1_REMOTE_SFENCE_VMA: case SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID: if (cp->a0) - hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, - utrap); + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, utrap); else hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; if (utrap->scause) @@ -103,7 +100,7 @@ static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, } break; default: - ret = -EINVAL; + retdata->err_val = SBI_ERR_NOT_SUPPORTED; break; } diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c index 6cd93995fb65..5246da1c9167 100644 --- a/arch/riscv/kvm/vmid.c +++ b/arch/riscv/kvm/vmid.c @@ -17,10 +17,10 @@ static unsigned long vmid_version = 1; static unsigned long vmid_next; -static unsigned long vmid_bits; +static unsigned long vmid_bits __ro_after_init; static DEFINE_SPINLOCK(vmid_lock); -void kvm_riscv_gstage_vmid_detect(void) +void __init kvm_riscv_gstage_vmid_detect(void) { unsigned long old; diff --git a/arch/s390/boot/decompressor.c b/arch/s390/boot/decompressor.c index e27c2140d620..b519a1f045d8 100644 --- a/arch/s390/boot/decompressor.c +++ b/arch/s390/boot/decompressor.c @@ -23,9 +23,9 @@ #define memmove memmove #define memzero(s, n) memset((s), 0, (n)) -#ifdef CONFIG_KERNEL_BZIP2 +#if defined(CONFIG_KERNEL_BZIP2) #define BOOT_HEAP_SIZE 0x400000 -#elif CONFIG_KERNEL_ZSTD +#elif defined(CONFIG_KERNEL_ZSTD) #define BOOT_HEAP_SIZE 0x30000 #else #define BOOT_HEAP_SIZE 0x10000 @@ -80,6 +80,6 @@ void *decompress_kernel(void) void *output = (void *)decompress_offset; __decompress(_compressed_start, _compressed_end - _compressed_start, - NULL, NULL, output, 0, NULL, error); + NULL, NULL, output, vmlinux.image_size, NULL, error); return output; } diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index a7b4e1d82758..74b35ec2ad28 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -190,7 +190,6 @@ CONFIG_NFT_CT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m -CONFIG_NFT_OBJREF=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m @@ -569,6 +568,7 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +# CONFIG_LEGACY_TIOCSTI is not set CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HANGCHECK_TIMER=m @@ -660,6 +660,7 @@ CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y @@ -705,6 +706,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_INTEGRITY_PLATFORM_KEYRING=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y @@ -781,6 +783,7 @@ CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CORDIC=m CONFIG_CRYPTO_LIB_CURVE25519=m CONFIG_CRYPTO_LIB_CHACHA20POLY1305=m @@ -848,7 +851,6 @@ CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_FTRACE_STARTUP_TEST=y # CONFIG_EVENT_TRACE_STARTUP_TEST is not set @@ -870,7 +872,6 @@ CONFIG_FAIL_MAKE_REQUEST=y CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y -CONFIG_FAIL_FUNCTION=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LKDTM=m CONFIG_TEST_MIN_HEAP=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 2bc2d0fe5774..cec71268e3bc 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -181,7 +181,6 @@ CONFIG_NFT_CT=m CONFIG_NFT_LOG=m CONFIG_NFT_LIMIT=m CONFIG_NFT_NAT=m -CONFIG_NFT_OBJREF=m CONFIG_NFT_REJECT=m CONFIG_NFT_COMPAT=m CONFIG_NFT_HASH=m @@ -559,6 +558,7 @@ CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set CONFIG_LEGACY_PTY_COUNT=0 +# CONFIG_LEGACY_TIOCSTI is not set CONFIG_VIRTIO_CONSOLE=m CONFIG_HW_RANDOM_VIRTIO=m CONFIG_HANGCHECK_TIMER=m @@ -645,6 +645,7 @@ CONFIG_CONFIGFS_FS=m CONFIG_ECRYPT_FS=m CONFIG_CRAMFS=m CONFIG_SQUASHFS=m +CONFIG_SQUASHFS_CHOICE_DECOMP_BY_MOUNT=y CONFIG_SQUASHFS_XATTR=y CONFIG_SQUASHFS_LZ4=y CONFIG_SQUASHFS_LZO=y @@ -688,6 +689,7 @@ CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y CONFIG_SECURITY_LANDLOCK=y CONFIG_INTEGRITY_SIGNATURE=y CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y +CONFIG_INTEGRITY_PLATFORM_KEYRING=y CONFIG_IMA=y CONFIG_IMA_DEFAULT_HASH_SHA256=y CONFIG_IMA_WRITE_POLICY=y @@ -766,6 +768,7 @@ CONFIG_ZCRYPT=m CONFIG_PKEY=m CONFIG_CRYPTO_PAES_S390=m CONFIG_CRYPTO_DEV_VIRTIO=m +CONFIG_SYSTEM_BLACKLIST_KEYRING=y CONFIG_CORDIC=m CONFIG_PRIME_NUMBERS=m CONFIG_CRYPTO_LIB_CURVE25519=m @@ -798,7 +801,6 @@ CONFIG_STACK_TRACER=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_BLK_DEV_IO_TRACE=y -CONFIG_BPF_KPROBE_OVERRIDE=y CONFIG_HIST_TRIGGERS=y CONFIG_SAMPLES=y CONFIG_SAMPLE_TRACE_PRINTK=m diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig index ae14ab0b864d..a9c0c81d1de9 100644 --- a/arch/s390/configs/zfcpdump_defconfig +++ b/arch/s390/configs/zfcpdump_defconfig @@ -13,7 +13,6 @@ CONFIG_TUNE_ZEC12=y # CONFIG_COMPAT is not set CONFIG_NR_CPUS=2 CONFIG_HZ_100=y -# CONFIG_RELOCATABLE is not set # CONFIG_CHSC_SCH is not set # CONFIG_SCM_BUS is not set CONFIG_CRASH_DUMP=y @@ -50,6 +49,7 @@ CONFIG_ZFCP=y # CONFIG_INPUT_KEYBOARD is not set # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set +# CONFIG_LEGACY_TIOCSTI is not set # CONFIG_HVC_IUCV is not set # CONFIG_HW_RANDOM_S390 is not set # CONFIG_HMC_DRV is not set diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h index feaba12dbecb..efa103b52a1a 100644 --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -131,19 +131,21 @@ struct hws_combined_entry { struct hws_diag_entry diag; /* Diagnostic-sampling data entry */ } __packed; -struct hws_trailer_entry { - union { - struct { - unsigned int f:1; /* 0 - Block Full Indicator */ - unsigned int a:1; /* 1 - Alert request control */ - unsigned int t:1; /* 2 - Timestamp format */ - unsigned int :29; /* 3 - 31: Reserved */ - unsigned int bsdes:16; /* 32-47: size of basic SDE */ - unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ - }; - unsigned long long flags; /* 0 - 63: All indicators */ +union hws_trailer_header { + struct { + unsigned int f:1; /* 0 - Block Full Indicator */ + unsigned int a:1; /* 1 - Alert request control */ + unsigned int t:1; /* 2 - Timestamp format */ + unsigned int :29; /* 3 - 31: Reserved */ + unsigned int bsdes:16; /* 32-47: size of basic SDE */ + unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ + unsigned long long overflow; /* 64 - Overflow Count */ }; - unsigned long long overflow; /* 64 - sample Overflow count */ + __uint128_t val; +}; + +struct hws_trailer_entry { + union hws_trailer_header header; /* 0 - 15 Flags + Overflow Count */ unsigned char timestamp[16]; /* 16 - 31 timestamp */ unsigned long long reserved1; /* 32 -Reserved */ unsigned long long reserved2; /* */ @@ -290,14 +292,11 @@ static inline unsigned long sample_rate_to_freq(struct hws_qsi_info_block *qsi, return USEC_PER_SEC * qsi->cpu_speed / rate; } -#define SDB_TE_ALERT_REQ_MASK 0x4000000000000000UL -#define SDB_TE_BUFFER_FULL_MASK 0x8000000000000000UL - /* Return TOD timestamp contained in an trailer entry */ static inline unsigned long long trailer_timestamp(struct hws_trailer_entry *te) { /* TOD in STCKE format */ - if (te->t) + if (te->header.t) return *((unsigned long long *) &te->timestamp[1]); /* TOD in STCK format */ diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index 77f24262c25c..ac665b9670c5 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -4,8 +4,8 @@ * * Copyright IBM Corp. 1999, 2020 */ -#ifndef DEBUG_H -#define DEBUG_H +#ifndef _ASM_S390_DEBUG_H +#define _ASM_S390_DEBUG_H #include <linux/string.h> #include <linux/spinlock.h> @@ -487,4 +487,4 @@ void debug_register_static(debug_info_t *id, int pages_per_area, int nr_areas); #endif /* MODULE */ -#endif /* DEBUG_H */ +#endif /* _ASM_S390_DEBUG_H */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index d67ce719d16a..2bbc3d54959d 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -1031,7 +1031,6 @@ extern char sie_exit; extern int kvm_s390_gisc_register(struct kvm *kvm, u32 gisc); extern int kvm_s390_gisc_unregister(struct kvm *kvm, u32 gisc); -static inline void kvm_arch_hardware_disable(void) {} static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_free_memslot(struct kvm *kvm, diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h index cb5fc0690435..081837b391e3 100644 --- a/arch/s390/include/asm/percpu.h +++ b/arch/s390/include/asm/percpu.h @@ -31,7 +31,7 @@ pcp_op_T__ *ptr__; \ preempt_disable_notrace(); \ ptr__ = raw_cpu_ptr(&(pcp)); \ - prev__ = *ptr__; \ + prev__ = READ_ONCE(*ptr__); \ do { \ old__ = prev__; \ new__ = old__ op (val); \ diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c index fc6d5f58debe..2df94d32140c 100644 --- a/arch/s390/kernel/machine_kexec_file.c +++ b/arch/s390/kernel/machine_kexec_file.c @@ -187,8 +187,6 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->memsz = ALIGN(data->memsz, PAGE_SIZE); buf.mem = data->memsz; - if (image->type == KEXEC_TYPE_CRASH) - buf.mem += crashk_res.start; ptr = (void *)ipl_cert_list_addr; end = ptr + ipl_cert_list_size; @@ -225,6 +223,9 @@ static int kexec_file_add_ipl_report(struct kimage *image, data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr); *lc_ipl_parmblock_ptr = (__u32)buf.mem; + if (image->type == KEXEC_TYPE_CRASH) + buf.mem += crashk_res.start; + ret = kexec_add_buffer(&buf); out: return ret; diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 332a49965130..ce886a03545a 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -163,14 +163,15 @@ static void free_sampling_buffer(struct sf_buffer *sfb) static int alloc_sample_data_block(unsigned long *sdbt, gfp_t gfp_flags) { - unsigned long sdb, *trailer; + struct hws_trailer_entry *te; + unsigned long sdb; /* Allocate and initialize sample-data-block */ sdb = get_zeroed_page(gfp_flags); if (!sdb) return -ENOMEM; - trailer = trailer_entry_ptr(sdb); - *trailer = SDB_TE_ALERT_REQ_MASK; + te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb); + te->header.a = 1; /* Link SDB into the sample-data-block-table */ *sdbt = sdb; @@ -1206,7 +1207,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, "%s: Found unknown" " sampling data entry: te->f %i" " basic.def %#4x (%p)\n", __func__, - te->f, sample->def, sample); + te->header.f, sample->def, sample); /* Sample slot is not yet written or other record. * * This condition can occur if the buffer was reused @@ -1217,7 +1218,7 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, * that are not full. Stop processing if the first * invalid format was detected. */ - if (!te->f) + if (!te->header.f) break; } @@ -1227,6 +1228,16 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, } } +static inline __uint128_t __cdsg(__uint128_t *ptr, __uint128_t old, __uint128_t new) +{ + asm volatile( + " cdsg %[old],%[new],%[ptr]\n" + : [old] "+d" (old), [ptr] "+QS" (*ptr) + : [new] "d" (new) + : "memory", "cc"); + return old; +} + /* hw_perf_event_update() - Process sampling buffer * @event: The perf event * @flush_all: Flag to also flush partially filled sample-data-blocks @@ -1243,10 +1254,11 @@ static void hw_collect_samples(struct perf_event *event, unsigned long *sdbt, */ static void hw_perf_event_update(struct perf_event *event, int flush_all) { + unsigned long long event_overflow, sampl_overflow, num_sdb; + union hws_trailer_header old, prev, new; struct hw_perf_event *hwc = &event->hw; struct hws_trailer_entry *te; unsigned long *sdbt; - unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags; int done; /* @@ -1266,25 +1278,25 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) te = (struct hws_trailer_entry *) trailer_entry_ptr(*sdbt); /* Leave loop if no more work to do (block full indicator) */ - if (!te->f) { + if (!te->header.f) { done = 1; if (!flush_all) break; } /* Check the sample overflow count */ - if (te->overflow) + if (te->header.overflow) /* Account sample overflows and, if a particular limit * is reached, extend the sampling buffer. * For details, see sfb_account_overflows(). */ - sampl_overflow += te->overflow; + sampl_overflow += te->header.overflow; /* Timestamps are valid for full sample-data-blocks only */ debug_sprintf_event(sfdbg, 6, "%s: sdbt %#lx " "overflow %llu timestamp %#llx\n", - __func__, (unsigned long)sdbt, te->overflow, - (te->f) ? trailer_timestamp(te) : 0ULL); + __func__, (unsigned long)sdbt, te->header.overflow, + (te->header.f) ? trailer_timestamp(te) : 0ULL); /* Collect all samples from a single sample-data-block and * flag if an (perf) event overflow happened. If so, the PMU @@ -1294,12 +1306,16 @@ static void hw_perf_event_update(struct perf_event *event, int flush_all) num_sdb++; /* Reset trailer (using compare-double-and-swap) */ + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te_flags |= SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - te->flags, te->overflow, - te_flags, 0ULL)); + old.val = prev.val; + new.val = prev.val; + new.f = 0; + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); /* Advance to next sample-data-block */ sdbt++; @@ -1384,7 +1400,7 @@ static void aux_output_end(struct perf_output_handle *handle) range_scan = AUX_SDB_NUM_ALERT(aux); for (i = 0, idx = aux->head; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - if (!(te->flags & SDB_TE_BUFFER_FULL_MASK)) + if (!te->header.f) break; } /* i is num of SDBs which are full */ @@ -1392,7 +1408,7 @@ static void aux_output_end(struct perf_output_handle *handle) /* Remove alert indicators in the buffer */ te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags &= ~SDB_TE_ALERT_REQ_MASK; + te->header.a = 0; debug_sprintf_event(sfdbg, 6, "%s: SDBs %ld range %ld head %ld\n", __func__, i, range_scan, aux->head); @@ -1437,9 +1453,9 @@ static int aux_output_begin(struct perf_output_handle *handle, idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | - SDB_TE_ALERT_REQ_MASK); - te->overflow = 0; + te->header.f = 0; + te->header.a = 0; + te->header.overflow = 0; } /* Save the position of empty SDBs */ aux->empty_mark = aux->head + range - 1; @@ -1448,7 +1464,7 @@ static int aux_output_begin(struct perf_output_handle *handle, /* Set alert indicator */ aux->alert_mark = aux->head + range/2 - 1; te = aux_sdb_trailer(aux, aux->alert_mark); - te->flags = te->flags | SDB_TE_ALERT_REQ_MASK; + te->header.a = 1; /* Reset hardware buffer head */ head = AUX_SDB_INDEX(aux, aux->head); @@ -1475,14 +1491,17 @@ static int aux_output_begin(struct perf_output_handle *handle, static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; + union hws_trailer_header old, prev, new; struct hws_trailer_entry *te; te = aux_sdb_trailer(aux, alert_index); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - *overflow = orig_overflow = te->overflow; - if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { + old.val = prev.val; + new.val = prev.val; + *overflow = old.overflow; + if (old.f) { /* * SDB is already set by hardware. * Abort and try to set somewhere @@ -1490,10 +1509,10 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, */ return false; } - new_flags = orig_flags | SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 1; + new.overflow = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); return true; } @@ -1522,8 +1541,9 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; unsigned long i, range_scan, idx, idx_old; + union hws_trailer_header old, prev, new; + unsigned long long orig_overflow; struct hws_trailer_entry *te; debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld " @@ -1554,17 +1574,20 @@ static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, idx_old = idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); + /* READ_ONCE() 16 byte header */ + prev.val = __cdsg(&te->header.val, 0, 0); do { - orig_flags = te->flags; - orig_overflow = te->overflow; - new_flags = orig_flags & ~SDB_TE_BUFFER_FULL_MASK; + old.val = prev.val; + new.val = prev.val; + orig_overflow = old.overflow; + new.f = 0; + new.overflow = 0; if (idx == aux->alert_mark) - new_flags |= SDB_TE_ALERT_REQ_MASK; + new.a = 1; else - new_flags &= ~SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new.a = 0; + prev.val = __cdsg(&te->header.val, old.val, new.val); + } while (prev.val != old.val); *overflow += orig_overflow; } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 2b6091349daa..696c9e007a36 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -508,6 +508,7 @@ static void __init setup_lowcore_dat_on(void) { struct lowcore *abs_lc; unsigned long flags; + int i; __ctl_clear_bit(0, 28); S390_lowcore.external_new_psw.mask |= PSW_MASK_DAT; @@ -523,8 +524,8 @@ static void __init setup_lowcore_dat_on(void) abs_lc = get_abs_lowcore(&flags); abs_lc->restart_flags = RESTART_FLAG_CTLREGS; abs_lc->program_new_psw = S390_lowcore.program_new_psw; - memcpy(abs_lc->cregs_save_area, S390_lowcore.cregs_save_area, - sizeof(abs_lc->cregs_save_area)); + for (i = 0; i < 16; i++) + abs_lc->cregs_save_area[i] = S390_lowcore.cregs_save_area[i]; put_abs_lowcore(abs_lc, flags); } diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 5ea3830af0cc..cbf9c1b0beda 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -17,6 +17,8 @@ /* Handle ro_after_init data on our own. */ #define RO_AFTER_INIT_DATA +#define RUNTIME_DISCARD_EXIT + #define EMITS_PT_NOTE #include <asm-generic/vmlinux.lds.h> @@ -79,6 +81,7 @@ SECTIONS _end_amode31_refs = .; } + . = ALIGN(PAGE_SIZE); _edata = .; /* End of data section */ /* will be freed after init */ @@ -193,6 +196,7 @@ SECTIONS BSS_SECTION(PAGE_SIZE, 4 * PAGE_SIZE, PAGE_SIZE) + . = ALIGN(PAGE_SIZE); _end = . ; /* diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index bbb280633cb8..9250fde1f97d 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -83,8 +83,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union esca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -95,8 +96,9 @@ static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + union bsca_sigp_ctrl new_val = {0}, old_val; + old_val = READ_ONCE(*sigp_ctrl); new_val.scn = src_id; new_val.c = 1; old_val.c = 0; @@ -126,16 +128,18 @@ static void sca_clear_ext_call(struct kvm_vcpu *vcpu) struct esca_block *sca = vcpu->kvm->arch.sca; union esca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union esca_sigp_ctrl old = *sigp_ctrl; + union esca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } else { struct bsca_block *sca = vcpu->kvm->arch.sca; union bsca_sigp_ctrl *sigp_ctrl = &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); - union bsca_sigp_ctrl old = *sigp_ctrl; + union bsca_sigp_ctrl old; + old = READ_ONCE(*sigp_ctrl); expect = old.value; rc = cmpxchg(&sigp_ctrl->value, old.value, 0); } @@ -3412,7 +3416,7 @@ void kvm_s390_gib_destroy(void) gib = NULL; } -int kvm_s390_gib_init(u8 nisc) +int __init kvm_s390_gib_init(u8 nisc) { u32 gib_origin; int rc = 0; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 8dfda720f60d..39b36562c043 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -256,17 +256,6 @@ debug_info_t *kvm_s390_dbf; debug_info_t *kvm_s390_dbf_uv; /* Section: not file related */ -int kvm_arch_hardware_enable(void) -{ - /* every s390 is virtualization enabled ;-) */ - return 0; -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - return 0; -} - /* forward declarations */ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start, unsigned long end); @@ -329,25 +318,6 @@ static struct notifier_block kvm_clock_notifier = { .notifier_call = kvm_clock_sync, }; -int kvm_arch_hardware_setup(void *opaque) -{ - gmap_notifier.notifier_call = kvm_gmap_notifier; - gmap_register_pte_notifier(&gmap_notifier); - vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier; - gmap_register_pte_notifier(&vsie_gmap_notifier); - atomic_notifier_chain_register(&s390_epoch_delta_notifier, - &kvm_clock_notifier); - return 0; -} - -void kvm_arch_hardware_unsetup(void) -{ - gmap_unregister_pte_notifier(&gmap_notifier); - gmap_unregister_pte_notifier(&vsie_gmap_notifier); - atomic_notifier_chain_unregister(&s390_epoch_delta_notifier, - &kvm_clock_notifier); -} - static void allow_cpu_feat(unsigned long nr) { set_bit_inv(nr, kvm_s390_available_cpu_feat); @@ -385,7 +355,7 @@ static __always_inline void __insn32_query(unsigned int opcode, u8 *query) #define INSN_SORTL 0xb938 #define INSN_DFLTCC 0xb939 -static void kvm_s390_cpu_feat_init(void) +static void __init kvm_s390_cpu_feat_init(void) { int i; @@ -488,7 +458,7 @@ static void kvm_s390_cpu_feat_init(void) */ } -int kvm_arch_init(void *opaque) +static int __init __kvm_s390_init(void) { int rc = -ENOMEM; @@ -498,11 +468,11 @@ int kvm_arch_init(void *opaque) kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long)); if (!kvm_s390_dbf_uv) - goto out; + goto err_kvm_uv; if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) || debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view)) - goto out; + goto err_debug_view; kvm_s390_cpu_feat_init(); @@ -510,30 +480,49 @@ int kvm_arch_init(void *opaque) rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC); if (rc) { pr_err("A FLIC registration call failed with rc=%d\n", rc); - goto out; + goto err_flic; } if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) { rc = kvm_s390_pci_init(); if (rc) { pr_err("Unable to allocate AIFT for PCI\n"); - goto out; + goto err_pci; } } rc = kvm_s390_gib_init(GAL_ISC); if (rc) - goto out; + goto err_gib; + + gmap_notifier.notifier_call = kvm_gmap_notifier; + gmap_register_pte_notifier(&gmap_notifier); + vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier; + gmap_register_pte_notifier(&vsie_gmap_notifier); + atomic_notifier_chain_register(&s390_epoch_delta_notifier, + &kvm_clock_notifier); return 0; -out: - kvm_arch_exit(); +err_gib: + if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) + kvm_s390_pci_exit(); +err_pci: +err_flic: +err_debug_view: + debug_unregister(kvm_s390_dbf_uv); +err_kvm_uv: + debug_unregister(kvm_s390_dbf); return rc; } -void kvm_arch_exit(void) +static void __kvm_s390_exit(void) { + gmap_unregister_pte_notifier(&gmap_notifier); + gmap_unregister_pte_notifier(&vsie_gmap_notifier); + atomic_notifier_chain_unregister(&s390_epoch_delta_notifier, + &kvm_clock_notifier); + kvm_s390_gib_destroy(); if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) kvm_s390_pci_exit(); @@ -5764,7 +5753,7 @@ static inline unsigned long nonhyp_mask(int i) static int __init kvm_s390_init(void) { - int i; + int i, r; if (!sclp.has_sief2) { pr_info("SIE is not available\n"); @@ -5780,12 +5769,23 @@ static int __init kvm_s390_init(void) kvm_s390_fac_base[i] |= stfle_fac_list[i] & nonhyp_mask(i); - return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); + r = __kvm_s390_init(); + if (r) + return r; + + r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (r) { + __kvm_s390_exit(); + return r; + } + return 0; } static void __exit kvm_s390_exit(void) { kvm_exit(); + + __kvm_s390_exit(); } module_init(kvm_s390_init); diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index d48588c207d8..0261d42c7d01 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -470,7 +470,7 @@ void kvm_s390_gisa_clear(struct kvm *kvm); void kvm_s390_gisa_destroy(struct kvm *kvm); void kvm_s390_gisa_disable(struct kvm *kvm); void kvm_s390_gisa_enable(struct kvm *kvm); -int kvm_s390_gib_init(u8 nisc); +int __init kvm_s390_gib_init(u8 nisc); void kvm_s390_gib_destroy(void); /* implemented in guestdbg.c */ diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c index ec51e810e381..b124d586db55 100644 --- a/arch/s390/kvm/pci.c +++ b/arch/s390/kvm/pci.c @@ -672,7 +672,7 @@ out: return r; } -int kvm_s390_pci_init(void) +int __init kvm_s390_pci_init(void) { zpci_kvm_hook.kvm_register = kvm_s390_pci_register_kvm; zpci_kvm_hook.kvm_unregister = kvm_s390_pci_unregister_kvm; diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h index 486d06ef563f..ff0972dd5e71 100644 --- a/arch/s390/kvm/pci.h +++ b/arch/s390/kvm/pci.h @@ -60,7 +60,7 @@ void kvm_s390_pci_clear_list(struct kvm *kvm); int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args); -int kvm_s390_pci_init(void); +int __init kvm_s390_pci_init(void); void kvm_s390_pci_exit(void); static inline bool kvm_s390_pci_interp_allowed(void) diff --git a/arch/sh/include/asm/pgtable-3level.h b/arch/sh/include/asm/pgtable-3level.h index a889a3a938ba..d1ce73f3bd85 100644 --- a/arch/sh/include/asm/pgtable-3level.h +++ b/arch/sh/include/asm/pgtable-3level.h @@ -28,7 +28,7 @@ #define pmd_ERROR(e) \ printk("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) -typedef struct { +typedef union { struct { unsigned long pmd_low; unsigned long pmd_high; diff --git a/arch/sh/kernel/vmlinux.lds.S b/arch/sh/kernel/vmlinux.lds.S index 3161b9ccd2a5..b6276a3521d7 100644 --- a/arch/sh/kernel/vmlinux.lds.S +++ b/arch/sh/kernel/vmlinux.lds.S @@ -4,6 +4,7 @@ * Written by Niibe Yutaka and Paul Mundt */ OUTPUT_ARCH(sh) +#define RUNTIME_DISCARD_EXIT #include <asm/thread_info.h> #include <asm/cache.h> #include <asm/vmlinux.lds.h> diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 9cf07322875a..73ed982d4100 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -14,13 +14,13 @@ endif ifdef CONFIG_CC_IS_GCC RETPOLINE_CFLAGS := $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register) -RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) RETPOLINE_VDSO_CFLAGS := $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register) endif ifdef CONFIG_CC_IS_CLANG RETPOLINE_CFLAGS := -mretpoline-external-thunk RETPOLINE_VDSO_CFLAGS := -mretpoline endif +RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) ifdef CONFIG_RETHUNK RETHUNK_CFLAGS := -mfunction-return=thunk-extern diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S index 5521ea12f44e..aa9b96457584 100644 --- a/arch/x86/boot/bioscall.S +++ b/arch/x86/boot/bioscall.S @@ -32,7 +32,7 @@ intcall: movw %dx, %si movw %sp, %di movw $11, %cx - rep; movsd + rep; movsl /* Pop full state from the stack */ popal @@ -67,7 +67,7 @@ intcall: jz 4f movw %sp, %si movw $11, %cx - rep; movsd + rep; movsl 4: addw $44, %sp /* Restore state and return */ diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d4a314cc50d6..321a5011042d 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -180,6 +180,12 @@ void initialize_identity_maps(void *rmode) /* Load the new page-table. */ write_cr3(top_level_pgt); + + /* + * Now that the required page table mappings are established and a + * GHCB can be used, check for SNP guest/HV feature compatibility. + */ + snp_check_features(); } static pte_t *split_large_pmd(struct x86_mapping_info *info, diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index 62208ec04ca4..20118fb7c53b 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -126,6 +126,7 @@ static inline void console_init(void) #ifdef CONFIG_AMD_MEM_ENCRYPT void sev_enable(struct boot_params *bp); +void snp_check_features(void); void sev_es_shutdown_ghcb(void); extern bool sev_es_check_ghcb_fault(unsigned long address); void snp_set_page_private(unsigned long paddr); @@ -143,6 +144,7 @@ static inline void sev_enable(struct boot_params *bp) if (bp) bp->cc_blob_address = 0; } +static inline void snp_check_features(void) { } static inline void sev_es_shutdown_ghcb(void) { } static inline bool sev_es_check_ghcb_fault(unsigned long address) { diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index c93930d5ccbd..d63ad8f99f83 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -208,6 +208,23 @@ void sev_es_shutdown_ghcb(void) error("Can't unmap GHCB page"); } +static void __noreturn sev_es_ghcb_terminate(struct ghcb *ghcb, unsigned int set, + unsigned int reason, u64 exit_info_2) +{ + u64 exit_info_1 = SVM_VMGEXIT_TERM_REASON(set, reason); + + vc_ghcb_invalidate(ghcb); + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_TERM_REQUEST); + ghcb_set_sw_exit_info_1(ghcb, exit_info_1); + ghcb_set_sw_exit_info_2(ghcb, exit_info_2); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + while (true) + asm volatile("hlt\n" : : : "memory"); +} + bool sev_es_check_ghcb_fault(unsigned long address) { /* Check whether the fault was on the GHCB page */ @@ -270,6 +287,59 @@ static void enforce_vmpl0(void) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0); } +/* + * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need + * guest side implementation for proper functioning of the guest. If any + * of these features are enabled in the hypervisor but are lacking guest + * side implementation, the behavior of the guest will be undefined. The + * guest could fail in non-obvious way making it difficult to debug. + * + * As the behavior of reserved feature bits is unknown to be on the + * safe side add them to the required features mask. + */ +#define SNP_FEATURES_IMPL_REQ (MSR_AMD64_SNP_VTOM | \ + MSR_AMD64_SNP_REFLECT_VC | \ + MSR_AMD64_SNP_RESTRICTED_INJ | \ + MSR_AMD64_SNP_ALT_INJ | \ + MSR_AMD64_SNP_DEBUG_SWAP | \ + MSR_AMD64_SNP_VMPL_SSS | \ + MSR_AMD64_SNP_SECURE_TSC | \ + MSR_AMD64_SNP_VMGEXIT_PARAM | \ + MSR_AMD64_SNP_VMSA_REG_PROTECTION | \ + MSR_AMD64_SNP_RESERVED_BIT13 | \ + MSR_AMD64_SNP_RESERVED_BIT15 | \ + MSR_AMD64_SNP_RESERVED_MASK) + +/* + * SNP_FEATURES_PRESENT is the mask of SNP features that are implemented + * by the guest kernel. As and when a new feature is implemented in the + * guest kernel, a corresponding bit should be added to the mask. + */ +#define SNP_FEATURES_PRESENT (0) + +void snp_check_features(void) +{ + u64 unsupported; + + if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + return; + + /* + * Terminate the boot if hypervisor has enabled any feature lacking + * guest side implementation. Pass on the unsupported features mask through + * EXIT_INFO_2 of the GHCB protocol so that those features can be reported + * as part of the guest boot failure. + */ + unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT; + if (unsupported) { + if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb())) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); + + sev_es_ghcb_terminate(boot_ghcb, SEV_TERM_SET_GEN, + GHCB_SNP_UNSUPPORTED, unsupported); + } +} + void sev_enable(struct boot_params *bp) { unsigned int eax, ebx, ecx, edx; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index dfd2c124cdf8..73bd0d70817e 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -6339,6 +6339,7 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: pmem = true; x86_pmu.late_ack = true; memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids)); @@ -6348,6 +6349,7 @@ __init int intel_pmu_init(void) x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints; x86_pmu.extra_regs = intel_spr_extra_regs; x86_pmu.limit_period = spr_limit_period; + x86_pmu.pebs_ept = 1; x86_pmu.pebs_aliases = NULL; x86_pmu.pebs_prec_dist = true; x86_pmu.pebs_block = true; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index a2834bc93149..551741e79e03 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -41,6 +41,7 @@ * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL + * MTL * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -51,50 +52,50 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR + * TGL,TNT,RKL,ADL,RPL,SPR,MTL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML, - * ICL,TGL,RKL,ADL,RPL + * ICL,TGL,RKL,ADL,RPL,MTL * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL, * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL, - * RPL,SPR + * RPL,SPR,MTL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL, * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR + * TGL,TNT,RKL,ADL,RPL,SPR,MTL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL,RPL + * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL + * ADL,RPL,MTL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, - * TNT,RKL,ADL,RPL + * TNT,RKL,ADL,RPL,MTL * Scope: Package (physical package) * */ @@ -676,6 +677,7 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &icx_cstates), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &icx_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, &icl_cstates), @@ -686,6 +688,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_cstates), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &adl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 88e58b6ee73c..d8a404b91b7e 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2303,8 +2303,10 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; - case 4: case 5: + x86_pmu.pebs_ept = 1; + fallthrough; + case 4: x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl; x86_pmu.pebs_record_size = sizeof(struct pebs_basic); if (x86_pmu.intel_cap.pebs_baseline) { diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 6f1ccc57a692..459b1aafd4d4 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1833,6 +1833,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), {}, }; diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c index ecced3a52668..c65d8906cbcf 100644 --- a/arch/x86/events/msr.c +++ b/arch/x86/events/msr.c @@ -69,6 +69,7 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_BROADWELL_G: case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: case INTEL_FAM6_ATOM_SILVERMONT: case INTEL_FAM6_ATOM_SILVERMONT_D: @@ -107,6 +108,8 @@ static bool test_intel(int idx, void *data) case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: case INTEL_FAM6_RAPTORLAKE_S: + case INTEL_FAM6_METEORLAKE: + case INTEL_FAM6_METEORLAKE_L: if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF) return true; break; diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 65064d9f7fa6..8eb74cf386db 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -14,6 +14,7 @@ #include <asm/mmu.h> #include <asm/mpspec.h> #include <asm/x86_init.h> +#include <asm/cpufeature.h> #ifdef CONFIG_ACPI_APEI # include <asm/pgtable_types.h> @@ -63,6 +64,13 @@ extern int (*acpi_suspend_lowlevel)(void); /* Physical address to resume after wakeup */ unsigned long acpi_get_wakeup_address(void); +static inline bool acpi_skip_set_wakeup_address(void) +{ + return cpu_feature_enabled(X86_FEATURE_XENPV); +} + +#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address + /* * Check if the CPU can handle C2 and deeper */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 61012476d66e..cdb7e1492311 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -312,6 +312,9 @@ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ #define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ #define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index b049d950612f..ca97442e8d49 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -39,7 +39,20 @@ static __always_inline unsigned long native_get_debugreg(int regno) asm("mov %%db6, %0" :"=r" (val)); break; case 7: - asm("mov %%db7, %0" :"=r" (val)); + /* + * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them + * with other code. + * + * This is needed because a DR7 access can cause a #VC exception + * when running under SEV-ES. Taking a #VC exception is not a + * safe thing to do just anywhere in the entry code and + * re-ordering might place the access into an unsafe location. + * + * This happened in the NMI handler, where the DR7 read was + * re-ordered to happen before the call to sev_es_ist_enter(), + * causing stack recursion. + */ + asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER); break; default: BUG(); @@ -66,7 +79,16 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value) asm("mov %0, %%db6" ::"r" (value)); break; case 7: - asm("mov %0, %%db7" ::"r" (value)); + /* + * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them + * with other code. + * + * While is didn't happen with a DR7 write (see the DR7 read + * comment above which explains where it happened), add the + * __FORCE_ORDER here too to avoid similar problems in the + * future. + */ + asm volatile("mov %0, %%db7" ::"r" (value), __FORCE_ORDER); break; default: BUG(); diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 08e822bd7aa6..1e2fe398b66d 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -255,6 +255,9 @@ enum hv_isolation_type { /* TSC invariant control */ #define HV_X64_MSR_TSC_INVARIANT_CONTROL 0x40000118 +/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ +#define HV_EXPOSE_INVARIANT_TSC BIT_ULL(0) + /* Register name aliases for temporary compatibility */ #define HV_X64_MSR_STIMER0_COUNT HV_REGISTER_STIMER0_COUNT #define HV_X64_MSR_STIMER0_CONFIG HV_REGISTER_STIMER0_CONFIG diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 72184b0b2219..b241af4ce9b4 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -582,18 +582,14 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_MC, xenpv_exc_machine_check); /* NMI */ -#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) +#if IS_ENABLED(CONFIG_KVM_INTEL) /* - * Special NOIST entry point for VMX which invokes this on the kernel - * stack. asm_exc_nmi() requires an IST to work correctly vs. the NMI - * 'executing' marker. - * - * On 32bit this just uses the regular NMI entry point because 32-bit does - * not have ISTs. + * Special entry point for VMX which invokes this on the kernel stack, even for + * 64-bit, i.e. without using an IST. asm_exc_nmi() requires an IST to work + * correctly vs. the NMI 'executing' marker. Used for 32-bit kernels as well + * to avoid more ifdeffery. */ -DECLARE_IDTENTRY(X86_TRAP_NMI, exc_nmi_noist); -#else -#define asm_exc_nmi_noist asm_exc_nmi +DECLARE_IDTENTRY(X86_TRAP_NMI, exc_nmi_kvm_vmx); #endif DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi); diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index abccd51dcfca..8dc345cc6318 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -14,6 +14,7 @@ BUILD_BUG_ON(1) * to make a definition optional, but in this case the default will * be __static_call_return0. */ +KVM_X86_OP(check_processor_compatibility) KVM_X86_OP(hardware_enable) KVM_X86_OP(hardware_disable) KVM_X86_OP(hardware_unsetup) @@ -76,7 +77,6 @@ KVM_X86_OP(set_nmi_mask) KVM_X86_OP(enable_nmi_window) KVM_X86_OP(enable_irq_window) KVM_X86_OP_OPTIONAL(update_cr8_intercept) -KVM_X86_OP(check_apicv_inhibit_reasons) KVM_X86_OP(refresh_apicv_exec_ctrl) KVM_X86_OP_OPTIONAL(hwapic_irr_update) KVM_X86_OP_OPTIONAL(hwapic_isr_update) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f35f1ff4427b..792a6037047a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -514,6 +514,7 @@ struct kvm_pmc { #define MSR_ARCH_PERFMON_PERFCTR_MAX (MSR_ARCH_PERFMON_PERFCTR0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define MSR_ARCH_PERFMON_EVENTSEL_MAX (MSR_ARCH_PERFMON_EVENTSEL0 + KVM_INTEL_PMC_MAX_GENERIC - 1) #define KVM_PMC_MAX_FIXED 3 +#define MSR_ARCH_PERFMON_FIXED_CTR_MAX (MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1) #define KVM_AMD_PMC_MAX_GENERIC 6 struct kvm_pmu { unsigned nr_arch_gp_counters; @@ -678,6 +679,11 @@ struct kvm_vcpu_hv { } nested; }; +struct kvm_hypervisor_cpuid { + u32 base; + u32 limit; +}; + /* Xen HVM per vcpu emulation context */ struct kvm_vcpu_xen { u64 hypercall_rip; @@ -698,6 +704,7 @@ struct kvm_vcpu_xen { struct hrtimer timer; int poll_evtchn; struct timer_list poll_timer; + struct kvm_hypervisor_cpuid cpuid; }; struct kvm_queued_exception { @@ -826,7 +833,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; - u32 kvm_cpuid_base; + struct kvm_hypervisor_cpuid kvm_cpuid; u64 reserved_gpa_bits; int maxphyaddr; @@ -1022,19 +1029,30 @@ struct kvm_arch_memory_slot { }; /* - * We use as the mode the number of bits allocated in the LDR for the - * logical processor ID. It happens that these are all powers of two. - * This makes it is very easy to detect cases where the APICs are - * configured for multiple modes; in that case, we cannot use the map and - * hence cannot use kvm_irq_delivery_to_apic_fast either. + * Track the mode of the optimized logical map, as the rules for decoding the + * destination vary per mode. Enabling the optimized logical map requires all + * software-enabled local APIs to be in the same mode, each addressable APIC to + * be mapped to only one MDA, and each MDA to map to at most one APIC. */ -#define KVM_APIC_MODE_XAPIC_CLUSTER 4 -#define KVM_APIC_MODE_XAPIC_FLAT 8 -#define KVM_APIC_MODE_X2APIC 16 +enum kvm_apic_logical_mode { + /* All local APICs are software disabled. */ + KVM_APIC_MODE_SW_DISABLED, + /* All software enabled local APICs in xAPIC cluster addressing mode. */ + KVM_APIC_MODE_XAPIC_CLUSTER, + /* All software enabled local APICs in xAPIC flat addressing mode. */ + KVM_APIC_MODE_XAPIC_FLAT, + /* All software enabled local APICs in x2APIC mode. */ + KVM_APIC_MODE_X2APIC, + /* + * Optimized map disabled, e.g. not all local APICs in the same logical + * mode, same logical ID assigned to multiple APICs, etc. + */ + KVM_APIC_MODE_MAP_DISABLED, +}; struct kvm_apic_map { struct rcu_head rcu; - u8 mode; + enum kvm_apic_logical_mode logical_mode; u32 max_apic_id; union { struct kvm_lapic *xapic_flat_map[8]; @@ -1088,6 +1106,7 @@ struct kvm_hv { u64 hv_reenlightenment_control; u64 hv_tsc_emulation_control; u64 hv_tsc_emulation_status; + u64 hv_invtsc_control; /* How many vCPUs have VP index != vCPU index */ atomic_t num_mismatched_vp_indexes; @@ -1111,6 +1130,7 @@ struct msr_bitmap_range { /* Xen emulation context */ struct kvm_xen { + struct mutex xen_lock; u32 xen_version; bool long_mode; bool runstate_update_flag; @@ -1132,6 +1152,18 @@ struct kvm_x86_msr_filter { struct msr_bitmap_range ranges[16]; }; +struct kvm_x86_pmu_event_filter { + __u32 action; + __u32 nevents; + __u32 fixed_counter_bitmap; + __u32 flags; + __u32 nr_includes; + __u32 nr_excludes; + __u64 *includes; + __u64 *excludes; + __u64 events[]; +}; + enum kvm_apicv_inhibit { /********************************************************************/ @@ -1163,6 +1195,12 @@ enum kvm_apicv_inhibit { APICV_INHIBIT_REASON_BLOCKIRQ, /* + * APICv is disabled because not all vCPUs have a 1:1 mapping between + * APIC ID and vCPU, _and_ KVM is not applying its x2APIC hotplug hack. + */ + APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED, + + /* * For simplicity, the APIC acceleration is inhibited * first time either APIC ID or APIC base are changed by the guest * from their reset values. @@ -1200,6 +1238,12 @@ enum kvm_apicv_inhibit { * AVIC is disabled because SEV doesn't support it. */ APICV_INHIBIT_REASON_SEV, + + /* + * AVIC is disabled because not all vCPUs with a valid LDR have a 1:1 + * mapping between logical ID and vCPU. + */ + APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED, }; struct kvm_arch { @@ -1248,10 +1292,11 @@ struct kvm_arch { struct kvm_apic_map __rcu *apic_map; atomic_t apic_map_dirty; - /* Protects apic_access_memslot_enabled and apicv_inhibit_reasons */ - struct rw_semaphore apicv_update_lock; - bool apic_access_memslot_enabled; + bool apic_access_memslot_inhibited; + + /* Protects apicv_inhibit_reasons */ + struct rw_semaphore apicv_update_lock; unsigned long apicv_inhibit_reasons; gpa_t wall_clock; @@ -1301,7 +1346,6 @@ struct kvm_arch { u32 bsp_vcpu_id; u64 disabled_quirks; - int cpu_dirty_logging_count; enum kvm_irqchip_mode irqchip_mode; u8 nr_reserved_ioapic_pins; @@ -1337,25 +1381,16 @@ struct kvm_arch { /* Guest can access the SGX PROVISIONKEY. */ bool sgx_provisioning_allowed; - struct kvm_pmu_event_filter __rcu *pmu_event_filter; + struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; struct task_struct *nx_huge_page_recovery_thread; #ifdef CONFIG_X86_64 - /* - * Whether the TDP MMU is enabled for this VM. This contains a - * snapshot of the TDP MMU module parameter from when the VM was - * created and remains unchanged for the life of the VM. If this is - * true, TDP MMU handler functions will run for various MMU - * operations. - */ - bool tdp_mmu_enabled; - /* The number of TDP MMU pages across all roots. */ atomic64_t tdp_mmu_pages; /* - * List of kvm_mmu_page structs being used as roots. - * All kvm_mmu_page structs in the list should have + * List of struct kvm_mmu_pages being used as roots. + * All struct kvm_mmu_pages in the list should have * tdp_mmu_page set. * * For reads, this list is protected by: @@ -1519,6 +1554,8 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical) struct kvm_x86_ops { const char *name; + int (*check_processor_compatibility)(void); + int (*hardware_enable)(void); void (*hardware_disable)(void); void (*hardware_unsetup)(void); @@ -1607,6 +1644,8 @@ struct kvm_x86_ops { void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason); + const unsigned long required_apicv_inhibits; + bool allow_apicv_in_x2apic_without_x2apic_virtualization; void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(int isr); @@ -1730,9 +1769,6 @@ struct kvm_x86_nested_ops { }; struct kvm_x86_init_ops { - int (*cpu_has_kvm_support)(void); - int (*disabled_by_bios)(void); - int (*check_processor_compatibility)(void); int (*hardware_setup)(void); unsigned int (*handle_intel_pt_intr)(void); @@ -1759,6 +1795,9 @@ extern struct kvm_x86_ops kvm_x86_ops; #define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP #include <asm/kvm-x86-ops.h> +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops); +void kvm_x86_vendor_exit(void); + #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) { @@ -1981,7 +2020,7 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, bool kvm_apicv_activated(struct kvm *kvm); bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu); -void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); +void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu); void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set); void kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, @@ -2053,14 +2092,11 @@ enum { TASK_SWITCH_GATE = 3, }; -#define HF_GIF_MASK (1 << 0) -#define HF_NMI_MASK (1 << 3) -#define HF_IRET_MASK (1 << 4) -#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ +#define HF_GUEST_MASK (1 << 0) /* VCPU is in guest-mode */ #ifdef CONFIG_KVM_SMM -#define HF_SMM_MASK (1 << 6) -#define HF_SMM_INSIDE_NMI_MASK (1 << 7) +#define HF_SMM_MASK (1 << 1) +#define HF_SMM_INSIDE_NMI_MASK (1 << 2) # define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE # define KVM_ADDRESS_SPACE_NUM 2 diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 37ff47552bcb..d3fe82c5d6b6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -566,6 +566,26 @@ #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) +/* SNP feature bits enabled by the hypervisor */ +#define MSR_AMD64_SNP_VTOM BIT_ULL(3) +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) +#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) +#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) + +/* SNP feature bits reserved for future use. */ +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) + #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f /* AMD Collaborative Processor Performance Control MSRs */ diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index 04c17be9b5fd..bc5b4d788c08 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,6 +25,8 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_BIOS 0 #define MRR_APM 1 +void cpu_emergency_disable_virtualization(void); + typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_panic_self_stop(struct pt_regs *regs); void nmi_shootdown_cpus(nmi_shootdown_cb callback); diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h index 8757078d4442..3b12e6b99412 100644 --- a/arch/x86/include/asm/virtext.h +++ b/arch/x86/include/asm/virtext.h @@ -126,7 +126,21 @@ static inline void cpu_svm_disable(void) wrmsrl(MSR_VM_HSAVE_PA, 0); rdmsrl(MSR_EFER, efer); - wrmsrl(MSR_EFER, efer & ~EFER_SVME); + if (efer & EFER_SVME) { + /* + * Force GIF=1 prior to disabling SVM to ensure INIT and NMI + * aren't blocked, e.g. if a fatal error occurred between CLGI + * and STGI. Note, STGI may #UD if SVM is disabled from NMI + * context between reading EFER and executing STGI. In that + * case, GIF must already be set, otherwise the NMI would have + * been blocked, so just eat the fault. + */ + asm_volatile_goto("1: stgi\n\t" + _ASM_EXTABLE(1b, %l[fault]) + ::: "memory" : fault); +fault: + wrmsrl(MSR_EFER, efer & ~EFER_SVME); + } } /** Makes sure SVM is disabled, if it is supported on the CPU diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 16f548a661cf..5fc35f889cd1 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -38,9 +38,11 @@ extern struct start_info *xen_start_info; #include <asm/processor.h> +#define XEN_SIGNATURE "XenVMMXenVMM" + static inline uint32_t xen_cpuid_base(void) { - return hypervisor_cpuid_base("XenVMMXenVMM", 2); + return hypervisor_cpuid_base(XEN_SIGNATURE, 2); } struct pci_dev; diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index e48deab8901d..7f467fe05d42 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/ioctl.h> +#include <linux/stddef.h> #define KVM_PIO_PAGE_OFFSET 1 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2 @@ -507,8 +508,8 @@ struct kvm_nested_state { * KVM_{GET,PUT}_NESTED_STATE ioctl values. */ union { - struct kvm_vmx_nested_state_data vmx[0]; - struct kvm_svm_nested_state_data svm[0]; + __DECLARE_FLEX_ARRAY(struct kvm_vmx_nested_state_data, vmx); + __DECLARE_FLEX_ARRAY(struct kvm_svm_nested_state_data, svm); } data; }; @@ -525,6 +526,35 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) + +/* + * Masked event layout. + * Bits Description + * ---- ----------- + * 7:0 event select (low bits) + * 15:8 umask match + * 31:16 unused + * 35:32 event select (high bits) + * 36:54 unused + * 55 exclude bit + * 63:56 umask mask + */ + +#define KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, exclude) \ + (((event_select) & 0xFFULL) | (((event_select) & 0XF00ULL) << 24) | \ + (((mask) & 0xFFULL) << 56) | \ + (((match) & 0xFFULL) << 8) | \ + ((__u64)(!!(exclude)) << 55)) + +#define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ + (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) + /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ #define KVM_VCPU_TSC_CTRL 0 /* control group for the timestamp counter (TSC) */ #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h index f69c168391aa..80e1df482337 100644 --- a/arch/x86/include/uapi/asm/svm.h +++ b/arch/x86/include/uapi/asm/svm.h @@ -116,6 +116,12 @@ #define SVM_VMGEXIT_AP_CREATE 1 #define SVM_VMGEXIT_AP_DESTROY 2 #define SVM_VMGEXIT_HV_FEATURES 0x8000fffd +#define SVM_VMGEXIT_TERM_REQUEST 0x8000fffe +#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code) \ + /* SW_EXITINFO1[3:0] */ \ + (((((u64)reason_set) & 0xf)) | \ + /* SW_EXITINFO1[11:4] */ \ + ((((u64)reason_code) & 0xff) << 4)) #define SVM_VMGEXIT_UNSUPPORTED_EVENT 0x8000ffff /* Exit code reserved for hypervisor/software use */ diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c index 1f60a2b27936..fdbb5f07448f 100644 --- a/arch/x86/kernel/cpu/aperfmperf.c +++ b/arch/x86/kernel/cpu/aperfmperf.c @@ -330,7 +330,16 @@ static void __init bp_init_freq_invariance(void) static void disable_freq_invariance_workfn(struct work_struct *work) { + int cpu; + static_branch_disable(&arch_scale_freq_key); + + /* + * Set arch_freq_scale to a default value on all cpus + * This negates the effect of scaling + */ + for_each_possible_cpu(cpu) + per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE; } static DECLARE_WORK(disable_freq_invariance_work, diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 46668e255421..bfbdc072017d 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -388,7 +388,7 @@ static void __init ms_hyperv_init_platform(void) * setting of this MSR bit should happen before init_intel() * is called. */ - wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1); + wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC); setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); } diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index efe0c30d3a12..77538abeb72a 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -146,6 +146,30 @@ static inline struct rmid_entry *__rmid_entry(u32 rmid) return entry; } +static int __rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val) +{ + u64 msr_val; + + /* + * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured + * with a valid event code for supported resource type and the bits + * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, + * IA32_QM_CTR.data (bits 61:0) reports the monitored data. + * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) + * are error bits. + */ + wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); + rdmsrl(MSR_IA32_QM_CTR, msr_val); + + if (msr_val & RMID_VAL_ERROR) + return -EIO; + if (msr_val & RMID_VAL_UNAVAIL) + return -EINVAL; + + *val = msr_val; + return 0; +} + static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, u32 rmid, enum resctrl_event_id eventid) @@ -172,8 +196,12 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, struct arch_mbm_state *am; am = get_arch_mbm_state(hw_dom, rmid, eventid); - if (am) + if (am) { memset(am, 0, sizeof(*am)); + + /* Record any initial, non-zero count value. */ + __rmid_read(rmid, eventid, &am->prev_msr); + } } static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) @@ -191,25 +219,14 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct arch_mbm_state *am; u64 msr_val, chunks; + int ret; if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) return -EINVAL; - /* - * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured - * with a valid event code for supported resource type and the bits - * IA32_QM_EVTSEL.RMID (bits 41:32) are configured with valid RMID, - * IA32_QM_CTR.data (bits 61:0) reports the monitored data. - * IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) - * are error bits. - */ - wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid); - rdmsrl(MSR_IA32_QM_CTR, msr_val); - - if (msr_val & RMID_VAL_ERROR) - return -EIO; - if (msr_val & RMID_VAL_UNAVAIL) - return -EINVAL; + ret = __rmid_read(rmid, eventid, &msr_val); + if (ret) + return ret; am = get_arch_mbm_state(hw_dom, rmid, eventid); if (am) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index e5a48f05e787..5993da21d822 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -580,8 +580,10 @@ static int __rdtgroup_move_task(struct task_struct *tsk, /* * Ensure the task's closid and rmid are written before determining if * the task is current that will decide if it will be interrupted. + * This pairs with the full barrier between the rq->curr update and + * resctrl_sched_in() during context switch. */ - barrier(); + smp_mb(); /* * By now, the task's closid and rmid are set. If the task is current @@ -2402,6 +2404,14 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, WRITE_ONCE(t->rmid, to->mon.rmid); /* + * Order the closid/rmid stores above before the loads + * in task_curr(). This pairs with the full barrier + * between the rq->curr update and resctrl_sched_in() + * during context switch. + */ + smp_mb(); + + /* * If the task is on a CPU, set the CPU in the mask. * The detection is inaccurate as tasks might move or * schedule before the smp function call takes place. diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 305514431f26..cdd92ab43cda 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -37,7 +37,6 @@ #include <linux/kdebug.h> #include <asm/cpu.h> #include <asm/reboot.h> -#include <asm/virtext.h> #include <asm/intel_pt.h> #include <asm/crash.h> #include <asm/cmdline.h> @@ -81,15 +80,6 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) */ cpu_crash_vmclear_loaded_vmcss(); - /* Disable VMX or SVM if needed. - * - * We need to disable virtualization on all CPUs. - * Having VMX or SVM enabled on any CPU may break rebooting - * after the kdump kernel has finished its task. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); - /* * Disable Intel PT to stop its logging */ @@ -148,12 +138,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs) */ cpu_crash_vmclear_loaded_vmcss(); - /* Booting kdump kernel with VMX or SVM enabled won't work, - * because (among other limitations) we can't disable paging - * with the virt flags. - */ - cpu_emergency_vmxoff(); - cpu_emergency_svm_disable(); + cpu_emergency_disable_virtualization(); /* * Disable Intel PT to stop its logging diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 3aa5304200c5..4d8aff05a509 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -114,6 +114,7 @@ static void make_8259A_irq(unsigned int irq) disable_irq_nosync(irq); io_apic_irqs &= ~(1<<irq); irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq); + irq_set_status_flags(irq, IRQ_LEVEL); enable_irq(irq); lapic_assign_legacy_vector(irq, true); } diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index beb1bada1b0a..c683666876f1 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -65,8 +65,10 @@ void __init init_ISA_irqs(void) legacy_pic->init(0); - for (i = 0; i < nr_legacy_irqs(); i++) + for (i = 0; i < nr_legacy_irqs(); i++) { irq_set_chip_and_handler(i, chip, handle_level_irq); + irq_set_status_flags(i, IRQ_LEVEL); + } } void __init init_IRQ(void) diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index cec0bfa3bc04..e37faba95bb5 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -527,14 +527,14 @@ nmi_restart: mds_user_clear_cpu_buffers(); } -#if defined(CONFIG_X86_64) && IS_ENABLED(CONFIG_KVM_INTEL) -DEFINE_IDTENTRY_RAW(exc_nmi_noist) +#if IS_ENABLED(CONFIG_KVM_INTEL) +DEFINE_IDTENTRY_RAW(exc_nmi_kvm_vmx) { exc_nmi(regs); } -#endif #if IS_MODULE(CONFIG_KVM_INTEL) -EXPORT_SYMBOL_GPL(asm_exc_nmi_noist); +EXPORT_SYMBOL_GPL(asm_exc_nmi_kvm_vmx); +#endif #endif void stop_nmi(void) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index c3636ea4aa71..d03c551defcc 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -528,33 +528,29 @@ static inline void kb_wait(void) } } -static void vmxoff_nmi(int cpu, struct pt_regs *regs) -{ - cpu_emergency_vmxoff(); -} +static inline void nmi_shootdown_cpus_on_restart(void); -/* Use NMIs as IPIs to tell all CPUs to disable virtualization */ -static void emergency_vmx_disable_all(void) +static void emergency_reboot_disable_virtualization(void) { /* Just make sure we won't change CPUs while doing this */ local_irq_disable(); /* - * Disable VMX on all CPUs before rebooting, otherwise we risk hanging - * the machine, because the CPU blocks INIT when it's in VMX root. + * Disable virtualization on all CPUs before rebooting to avoid hanging + * the system, as VMX and SVM block INIT when running in the host. * * We can't take any locks and we may be on an inconsistent state, so - * use NMIs as IPIs to tell the other CPUs to exit VMX root and halt. + * use NMIs as IPIs to tell the other CPUs to disable VMX/SVM and halt. * - * Do the NMI shootdown even if VMX if off on _this_ CPU, as that - * doesn't prevent a different CPU from being in VMX root operation. + * Do the NMI shootdown even if virtualization is off on _this_ CPU, as + * other CPUs may have virtualization enabled. */ - if (cpu_has_vmx()) { - /* Safely force _this_ CPU out of VMX root operation. */ - __cpu_emergency_vmxoff(); + if (cpu_has_vmx() || cpu_has_svm(NULL)) { + /* Safely force _this_ CPU out of VMX/SVM operation. */ + cpu_emergency_disable_virtualization(); - /* Halt and exit VMX root operation on the other CPUs. */ - nmi_shootdown_cpus(vmxoff_nmi); + /* Disable VMX/SVM and halt on other CPUs. */ + nmi_shootdown_cpus_on_restart(); } } @@ -590,7 +586,7 @@ static void native_machine_emergency_restart(void) unsigned short mode; if (reboot_emergency) - emergency_vmx_disable_all(); + emergency_reboot_disable_virtualization(); tboot_shutdown(TB_SHUTDOWN_REBOOT); @@ -795,6 +791,17 @@ void machine_crash_shutdown(struct pt_regs *regs) /* This is the CPU performing the emergency shutdown work. */ int crashing_cpu = -1; +/* + * Disable virtualization, i.e. VMX or SVM, to ensure INIT is recognized during + * reboot. VMX blocks INIT if the CPU is post-VMXON, and SVM blocks INIT if + * GIF=0, i.e. if the crash occurred between CLGI and STGI. + */ +void cpu_emergency_disable_virtualization(void) +{ + cpu_emergency_vmxoff(); + cpu_emergency_svm_disable(); +} + #if defined(CONFIG_SMP) static nmi_shootdown_cb shootdown_callback; @@ -817,7 +824,14 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) return NMI_HANDLED; local_irq_disable(); - shootdown_callback(cpu, regs); + if (shootdown_callback) + shootdown_callback(cpu, regs); + + /* + * Prepare the CPU for reboot _after_ invoking the callback so that the + * callback can safely use virtualization instructions, e.g. VMCLEAR. + */ + cpu_emergency_disable_virtualization(); atomic_dec(&waiting_for_crash_ipi); /* Assume hlt works */ @@ -828,18 +842,32 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) return NMI_HANDLED; } -/* - * Halt all other CPUs, calling the specified function on each of them +/** + * nmi_shootdown_cpus - Stop other CPUs via NMI + * @callback: Optional callback to be invoked from the NMI handler + * + * The NMI handler on the remote CPUs invokes @callback, if not + * NULL, first and then disables virtualization to ensure that + * INIT is recognized during reboot. * - * This function can be used to halt all other CPUs on crash - * or emergency reboot time. The function passed as parameter - * will be called inside a NMI handler on all CPUs. + * nmi_shootdown_cpus() can only be invoked once. After the first + * invocation all other CPUs are stuck in crash_nmi_callback() and + * cannot respond to a second NMI. */ void nmi_shootdown_cpus(nmi_shootdown_cb callback) { unsigned long msecs; + local_irq_disable(); + /* + * Avoid certain doom if a shootdown already occurred; re-registering + * the NMI handler will cause list corruption, modifying the callback + * will do who knows what, etc... + */ + if (WARN_ON_ONCE(crash_ipi_issued)) + return; + /* Make a note of crashing cpu. Will be used in NMI callback. */ crashing_cpu = safe_smp_processor_id(); @@ -867,7 +895,17 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) msecs--; } - /* Leave the nmi callback set */ + /* + * Leave the nmi callback set, shootdown is a one-time thing. Clearing + * the callback could result in a NULL pointer dereference if a CPU + * (finally) responds after the timeout expires. + */ +} + +static inline void nmi_shootdown_cpus_on_restart(void) +{ + if (!crash_ipi_issued) + nmi_shootdown_cpus(NULL); } /* @@ -897,6 +935,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) /* No other CPUs to shoot down */ } +static inline void nmi_shootdown_cpus_on_restart(void) { } + void run_crash_ipi_callback(struct pt_regs *regs) { } diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 06db901fabe8..375b33ecafa2 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -32,7 +32,7 @@ #include <asm/mce.h> #include <asm/trace/irq_vectors.h> #include <asm/kexec.h> -#include <asm/virtext.h> +#include <asm/reboot.h> /* * Some notes on x86 processor bugs affecting SMP operation: @@ -122,7 +122,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) if (raw_smp_processor_id() == atomic_read(&stopping_cpu)) return NMI_HANDLED; - cpu_emergency_vmxoff(); + cpu_emergency_disable_virtualization(); stop_this_cpu(NULL); return NMI_HANDLED; @@ -134,7 +134,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) DEFINE_IDTENTRY_SYSVEC(sysvec_reboot) { ack_APIC_irq(); - cpu_emergency_vmxoff(); + cpu_emergency_disable_virtualization(); stop_this_cpu(NULL); } diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index fbeaa9ddef59..8e578311ca9d 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -49,6 +49,7 @@ config KVM select SRCU select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM + select KVM_GENERIC_HARDWARE_ENABLING help Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index b14653b61470..8f8edeaf8177 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -8,6 +8,7 @@ * Copyright 2011 Red Hat, Inc. and/or its affiliates. * Copyright IBM Corporation, 2008 */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/export.h> @@ -25,6 +26,7 @@ #include "mmu.h" #include "trace.h" #include "pmu.h" +#include "xen.h" /* * Unlike "struct cpuinfo_x86.x86_capability", kvm_cpu_caps doesn't need to be @@ -180,15 +182,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 return 0; } -static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) +static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, + const char *sig) { - u32 function; + struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; + u32 base; - vcpu->arch.kvm_cpuid_base = 0; - - for_each_possible_hypervisor_cpuid_base(function) { - entry = kvm_find_cpuid_entry(vcpu, function); + for_each_possible_hypervisor_cpuid_base(base) { + entry = kvm_find_cpuid_entry(vcpu, base); if (entry) { u32 signature[3]; @@ -197,19 +199,21 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) signature[1] = entry->ecx; signature[2] = entry->edx; - BUILD_BUG_ON(sizeof(signature) > sizeof(KVM_SIGNATURE)); - if (!memcmp(signature, KVM_SIGNATURE, sizeof(signature))) { - vcpu->arch.kvm_cpuid_base = function; + if (!memcmp(signature, sig, sizeof(signature))) { + cpuid.base = base; + cpuid.limit = entry->eax; break; } } } + + return cpuid; } static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, int nent) { - u32 base = vcpu->arch.kvm_cpuid_base; + u32 base = vcpu->arch.kvm_cpuid.base; if (!base) return NULL; @@ -439,7 +443,8 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, vcpu->arch.cpuid_entries = e2; vcpu->arch.cpuid_nent = nent; - kvm_update_kvm_cpuid_base(vcpu); + vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); + vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); kvm_vcpu_after_set_cpuid(vcpu); return 0; @@ -663,8 +668,9 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_mask(CPUID_7_1_EAX, - F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(AMX_FP16) | - F(AVX_IFMA) + F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | + F(FZRM) | F(FSRS) | F(FSRC) | + F(AMX_FP16) | F(AVX_IFMA) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, @@ -701,6 +707,10 @@ void kvm_set_cpu_caps(void) if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64)) kvm_cpu_cap_set(X86_FEATURE_GBPAGES); + kvm_cpu_cap_init_kvm_defined(CPUID_8000_0007_EDX, + SF(CONSTANT_TSC) + ); + kvm_cpu_cap_mask(CPUID_8000_0008_EBX, F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | @@ -770,16 +780,22 @@ struct kvm_cpuid_array { int nent; }; +static struct kvm_cpuid_entry2 *get_next_cpuid(struct kvm_cpuid_array *array) +{ + if (array->nent >= array->maxnent) + return NULL; + + return &array->entries[array->nent++]; +} + static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, u32 function, u32 index) { - struct kvm_cpuid_entry2 *entry; + struct kvm_cpuid_entry2 *entry = get_next_cpuid(array); - if (array->nent >= array->maxnent) + if (!entry) return NULL; - entry = &array->entries[array->nent++]; - memset(entry, 0, sizeof(*entry)); entry->function = function; entry->index = index; @@ -956,22 +972,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx = edx.full; break; } - /* - * Per Intel's SDM, the 0x1f is a superset of 0xb, - * thus they can be handled by common code. - */ case 0x1f: case 0xb: /* - * Populate entries until the level type (ECX[15:8]) of the - * previous entry is zero. Note, CPUID EAX.{0x1f,0xb}.0 is - * the starting entry, filled by the primary do_host_cpuid(). + * No topology; a valid topology is indicated by the presence + * of subleaf 1. */ - for (i = 1; entry->ecx & 0xff00; ++i) { - entry = do_host_cpuid(array, function, i); - if (!entry) - goto out; - } + entry->eax = entry->ebx = entry->ecx = 0; break; case 0xd: { u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm(); @@ -1151,8 +1158,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ - /* invariant TSC is CPUID.80000007H:EDX[8] */ - entry->edx &= (1 << 8); + cpuid_entry_override(entry, CPUID_8000_0007_EDX); + /* mask against host */ entry->edx &= boot_cpu_data.x86_power; entry->eax = entry->ebx = entry->ecx = 0; @@ -1202,6 +1209,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ebx = entry->ecx = entry->edx = 0; break; case 0x8000001e: + /* Do not return host topology information. */ + entry->eax = entry->ebx = entry->ecx = 0; + entry->edx = 0; /* reserved */ break; case 0x8000001F: if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) { @@ -1482,6 +1492,9 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) && (data & TSX_CTRL_CPUID_CLEAR)) *ebx &= ~(F(RTM) | F(HLE)); + } else if (function == 0x80000007) { + if (kvm_hv_invtsc_suppressed(vcpu)) + *edx &= ~SF(CONSTANT_TSC); } } else { *eax = *ebx = *ecx = *edx = 0; diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index c1390357126a..ee8c4c3496ed 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -4,6 +4,8 @@ * * Copyright 2016 Red Hat, Inc. and/or its affiliates. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <linux/debugfs.h> #include "lapic.h" diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 5cc3efa0e21c..baf97c56aefa 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -17,6 +17,7 @@ * * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4 */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "kvm_cache_regs.h" @@ -1633,7 +1634,7 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, case VCPU_SREG_SS: /* * segment is not a writable data segment or segment - * selector's RPL != CPL or segment selector's RPL != CPL + * selector's RPL != CPL or DPL != CPL */ if (rpl != cpl || (seg_desc.type & 0xa) != 0x2 || dpl != cpl) goto exception; @@ -1695,11 +1696,11 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, /* * segment is not a data or readable code segment or * ((segment is a data or nonconforming code segment) - * and (both RPL and CPL > DPL)) + * and ((RPL > DPL) or (CPL > DPL))) */ if ((seg_desc.type & 0xa) == 0x8 || (((seg_desc.type & 0xc) != 0xc) && - (rpl > dpl && cpl > dpl))) + (rpl > dpl || cpl > dpl))) goto exception; break; } @@ -2309,7 +2310,7 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) static int em_rsm(struct x86_emulate_ctxt *ctxt) { - if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0) + if (!ctxt->ops->is_smm(ctxt)) return emulate_ud(ctxt); if (ctxt->ops->leave_smm(ctxt)) @@ -5132,7 +5133,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) const struct x86_emulate_ops *ops = ctxt->ops; int rc = X86EMUL_CONTINUE; int saved_dst_type = ctxt->dst.type; - unsigned emul_flags; + bool is_guest_mode = ctxt->ops->is_guest_mode(ctxt); ctxt->mem_read.pos = 0; @@ -5147,7 +5148,6 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - emul_flags = ctxt->ops->get_hflags(ctxt); if (unlikely(ctxt->d & (No64|Undefined|Sse|Mmx|Intercept|CheckPerm|Priv|Prot|String))) { if ((ctxt->mode == X86EMUL_MODE_PROT64 && (ctxt->d & No64)) || @@ -5181,7 +5181,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) fetch_possible_mmx_operand(&ctxt->dst); } - if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && ctxt->intercept) { + if (unlikely(is_guest_mode) && ctxt->intercept) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_PRE_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -5210,7 +5210,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) goto done; } - if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { + if (unlikely(is_guest_mode) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_EXCEPT); if (rc != X86EMUL_CONTINUE) @@ -5264,7 +5264,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) special_insn: - if (unlikely(emul_flags & X86EMUL_GUEST_MASK) && (ctxt->d & Intercept)) { + if (unlikely(is_guest_mode) && (ctxt->d & Intercept)) { rc = emulator_check_intercept(ctxt, ctxt->intercept, X86_ICPT_POST_MEMACCESS); if (rc != X86EMUL_CONTINUE) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index e8296942a868..b28fd020066f 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -17,6 +17,7 @@ * Ben-Ami Yassour <benami@il.ibm.com> * Andrey Smetanin <asmetanin@virtuozzo.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "x86.h" #include "lapic.h" @@ -43,6 +44,24 @@ #define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, HV_VCPUS_PER_SPARSE_BANK) +/* + * As per Hyper-V TLFS, extended hypercalls start from 0x8001 + * (HvExtCallQueryCapabilities). Response of this hypercalls is a 64 bit value + * where each bit tells which extended hypercall is available besides + * HvExtCallQueryCapabilities. + * + * 0x8001 - First extended hypercall, HvExtCallQueryCapabilities, no bit + * assigned. + * + * 0x8002 - Bit 0 + * 0x8003 - Bit 1 + * .. + * 0x8041 - Bit 63 + * + * Therefore, HV_EXT_CALL_MAX = 0x8001 + 64 + */ +#define HV_EXT_CALL_MAX (HV_EXT_CALL_QUERY_CAPABILITIES + 64) + static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, bool vcpu_kick); @@ -999,6 +1018,7 @@ static bool kvm_hv_msr_partition_wide(u32 msr) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: r = true; @@ -1283,6 +1303,9 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) case HV_X64_MSR_TSC_EMULATION_STATUS: return hv_vcpu->cpuid_cache.features_eax & HV_ACCESS_REENLIGHTENMENT; + case HV_X64_MSR_TSC_INVARIANT_CONTROL: + return hv_vcpu->cpuid_cache.features_eax & + HV_ACCESS_TSC_INVARIANT; case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: return hv_vcpu->cpuid_cache.features_edx & @@ -1410,12 +1433,22 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, if (!host) return 1; break; + case HV_X64_MSR_TSC_INVARIANT_CONTROL: + /* Only bit 0 is supported */ + if (data & ~HV_EXPOSE_INVARIANT_TSC) + return 1; + + /* The feature can't be disabled from the guest */ + if (!host && hv->hv_invtsc_control && !data) + return 1; + + hv->hv_invtsc_control = data; + break; case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_set_msr(vcpu, msr, data, host); default: - vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } return 0; @@ -1536,8 +1569,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; break; default: - vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } @@ -1585,11 +1617,14 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, case HV_X64_MSR_TSC_EMULATION_STATUS: data = hv->hv_tsc_emulation_status; break; + case HV_X64_MSR_TSC_INVARIANT_CONTROL: + data = hv->hv_invtsc_control; + break; case HV_X64_MSR_SYNDBG_OPTIONS: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: return syndbg_get_msr(vcpu, msr, pdata, host); default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; } @@ -1654,7 +1689,7 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, data = APIC_BUS_FREQUENCY; break; default: - vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + kvm_pr_unimpl_rdmsr(vcpu, msr); return 1; } *pdata = data; @@ -2420,6 +2455,9 @@ static bool hv_check_hypercall_access(struct kvm_vcpu_hv *hv_vcpu, u16 code) case HVCALL_SEND_IPI: return hv_vcpu->cpuid_cache.enlightenments_eax & HV_X64_CLUSTER_IPI_RECOMMENDED; + case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX: + return hv_vcpu->cpuid_cache.features_ebx & + HV_ENABLE_EXTENDED_HYPERCALLS; default: break; } @@ -2512,14 +2550,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - vcpu->run->exit_reason = KVM_EXIT_HYPERV; - vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = hc.param; - vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; - vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; - vcpu->arch.complete_userspace_io = - kvm_hv_hypercall_complete_userspace; - return 0; + goto hypercall_userspace_exit; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: if (unlikely(hc.var_cnt)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -2578,15 +2609,14 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) ret = HV_STATUS_OPERATION_DENIED; break; } - vcpu->run->exit_reason = KVM_EXIT_HYPERV; - vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; - vcpu->run->hyperv.u.hcall.input = hc.param; - vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; - vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; - vcpu->arch.complete_userspace_io = - kvm_hv_hypercall_complete_userspace; - return 0; + goto hypercall_userspace_exit; } + case HV_EXT_CALL_QUERY_CAPABILITIES ... HV_EXT_CALL_MAX: + if (unlikely(hc.fast)) { + ret = HV_STATUS_INVALID_PARAMETER; + break; + } + goto hypercall_userspace_exit; default: ret = HV_STATUS_INVALID_HYPERCALL_CODE; break; @@ -2594,6 +2624,15 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) hypercall_complete: return kvm_hv_hypercall_complete(vcpu, ret); + +hypercall_userspace_exit: + vcpu->run->exit_reason = KVM_EXIT_HYPERV; + vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL; + vcpu->run->hyperv.u.hcall.input = hc.param; + vcpu->run->hyperv.u.hcall.params[0] = hc.ingpa; + vcpu->run->hyperv.u.hcall.params[1] = hc.outgpa; + vcpu->arch.complete_userspace_io = kvm_hv_hypercall_complete_userspace; + return 0; } void kvm_hv_init_vm(struct kvm *kvm) @@ -2733,9 +2772,11 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; ent->eax |= HV_ACCESS_FREQUENCY_MSRS; ent->eax |= HV_ACCESS_REENLIGHTENMENT; + ent->eax |= HV_ACCESS_TSC_INVARIANT; ent->ebx |= HV_POST_MESSAGES; ent->ebx |= HV_SIGNAL_EVENTS; + ent->ebx |= HV_ENABLE_EXTENDED_HYPERCALLS; ent->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 9f96414a31c5..f83b8db72b11 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -136,6 +136,33 @@ static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) HV_SYNIC_STIMER_COUNT); } +/* + * With HV_ACCESS_TSC_INVARIANT feature, invariant TSC (CPUID.80000007H:EDX[8]) + * is only observed after HV_X64_MSR_TSC_INVARIANT_CONTROL was written to. + */ +static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + /* + * If Hyper-V's invariant TSC control is not exposed to the guest, + * the invariant TSC CPUID flag is not suppressed, Windows guests were + * observed to be able to handle it correctly. Going forward, VMMs are + * encouraged to enable Hyper-V's invariant TSC control when invariant + * TSC CPUID flag is set to make KVM's behavior match genuine Hyper-V. + */ + if (!hv_vcpu || + !(hv_vcpu->cpuid_cache.features_eax & HV_ACCESS_TSC_INVARIANT)) + return false; + + /* + * If Hyper-V's invariant TSC control is exposed to the guest, KVM is + * responsible for suppressing the invariant TSC CPUID flag if the + * Hyper-V control is not enabled. + */ + return !(to_kvm_hv(vcpu->kvm)->hv_invtsc_control & HV_EXPOSE_INVARIANT_TSC); +} + void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); void kvm_hv_setup_tsc_page(struct kvm *kvm, diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index e0a7a0e7a73c..cd57a517d04a 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -30,7 +30,7 @@ * Based on QEMU and Xen. */ -#define pr_fmt(fmt) "pit: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/slab.h> @@ -351,7 +351,7 @@ static void create_pit_timer(struct kvm_pit *pit, u32 val, int is_period) if (ps->period < min_period) { pr_info_ratelimited( - "kvm: requested %lld ns " + "requested %lld ns " "i8254 timer period limited to %lld ns\n", ps->period, min_period); ps->period = min_period; diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index e1bb6218bb96..4756bcb5724f 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -26,6 +26,8 @@ * Yaozu (Eddie) Dong <Eddie.dong@intel.com> * Port from Qemu. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/mm.h> #include <linux/slab.h> #include <linux/bitops.h> @@ -35,7 +37,7 @@ #include "trace.h" #define pr_pic_unimpl(fmt, ...) \ - pr_err_ratelimited("kvm: pic: " fmt, ## __VA_ARGS__) + pr_err_ratelimited("pic: " fmt, ## __VA_ARGS__) static void pic_irq_request(struct kvm *kvm, int level); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 765943d7cfa5..042dee556125 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -26,6 +26,7 @@ * Yaozu (Eddie) Dong <eddie.dong@intel.com> * Based on Xen 3.1 code. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/kvm.h> diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index a70952eca905..b2c397dd2bc6 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -7,6 +7,7 @@ * Authors: * Yaozu (Eddie) Dong <Eddie.dong@intel.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/export.h> #include <linux/kvm_host.h> diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 3742d9adacfc..16d076a1b91a 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -8,6 +8,7 @@ * * Copyright 2010 Red Hat, Inc. and/or its affiliates. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/slab.h> @@ -56,7 +57,7 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, if (irq->dest_mode == APIC_DEST_PHYSICAL && irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) { - printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n"); + pr_info("apic: phys broadcast and lowest prio\n"); irq->delivery_mode = APIC_DM_FIXED; } @@ -199,7 +200,7 @@ int kvm_request_irq_source_id(struct kvm *kvm) irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG); if (irq_source_id >= BITS_PER_LONG) { - printk(KERN_WARNING "kvm: exhaust allocatable IRQ sources!\n"); + pr_warn("exhausted allocatable IRQ sources!\n"); irq_source_id = -EFAULT; goto unlock; } @@ -221,7 +222,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) mutex_lock(&kvm->irq_lock); if (irq_source_id < 0 || irq_source_id >= BITS_PER_LONG) { - printk(KERN_ERR "kvm: IRQ source ID out of range!\n"); + pr_err("IRQ source ID out of range!\n"); goto unlock; } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index c09174f73a34..4c91f626c058 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -76,6 +76,18 @@ static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, } /* + * kvm_register_test_and_mark_available() is a special snowflake that uses an + * arch bitop directly to avoid the explicit instrumentation that comes with + * the generic bitops. This allows code that cannot be instrumented (noinstr + * functions), e.g. the low level VM-Enter/VM-Exit paths, to cache registers. + */ +static __always_inline bool kvm_register_test_and_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return arch___test_and_set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +/* * The "raw" register helpers are only for cases where the full 64 bits of a * register are read/written irrespective of current vCPU mode. In other words, * odds are good you shouldn't be using the raw variants. diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 2d9662be8333..ab65f3a47dfd 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -220,7 +220,8 @@ struct x86_emulate_ops { void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); - unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); + bool (*is_smm)(struct x86_emulate_ctxt *ctxt); + bool (*is_guest_mode)(struct x86_emulate_ctxt *ctxt); int (*leave_smm)(struct x86_emulate_ctxt *ctxt); void (*triple_fault)(struct x86_emulate_ctxt *ctxt); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); @@ -275,10 +276,6 @@ enum x86emul_mode { X86EMUL_MODE_PROT64, /* 64-bit (long) mode. */ }; -/* These match some of the HF_* flags defined in kvm_host.h */ -#define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ -#define X86EMUL_SMM_MASK (1 << 6) - /* * fastop functions are declared as taking a never-defined fastop parameter, * so they can't be called from C directly. diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index ee4f696a0782..482d6639ef88 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -2,6 +2,7 @@ /* * KVM L1 hypervisor optimizations on Hyper-V. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <asm/mshyperv.h> diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4efdb4a4d72c..7cf4eebc9bcc 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -15,6 +15,7 @@ * * Based on Xen 3.1 code, Copyright (c) 2004, Intel Corporation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/kvm.h> @@ -166,9 +167,19 @@ static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu) return kvm_can_post_timer_interrupt(vcpu) && vcpu->mode == IN_GUEST_MODE; } +static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) +{ + return ((id >> 4) << 16) | (1 << (id & 0xf)); +} + static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, u32 dest_id, struct kvm_lapic ***cluster, u16 *mask) { - switch (map->mode) { + switch (map->logical_mode) { + case KVM_APIC_MODE_SW_DISABLED: + /* Arbitrarily use the flat map so that @cluster isn't NULL. */ + *cluster = map->xapic_flat_map; + *mask = 0; + return true; case KVM_APIC_MODE_X2APIC: { u32 offset = (dest_id >> 16) * 16; u32 max_apic_id = map->max_apic_id; @@ -193,8 +204,10 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, *cluster = map->xapic_cluster_map[(dest_id >> 4) & 0xf]; *mask = dest_id & 0xf; return true; + case KVM_APIC_MODE_MAP_DISABLED: + return false; default: - /* Not optimized. */ + WARN_ON_ONCE(1); return false; } } @@ -206,6 +219,134 @@ static void kvm_apic_map_free(struct rcu_head *rcu) kvfree(map); } +static int kvm_recalculate_phys_map(struct kvm_apic_map *new, + struct kvm_vcpu *vcpu, + bool *xapic_id_mismatch) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + u32 x2apic_id = kvm_x2apic_id(apic); + u32 xapic_id = kvm_xapic_id(apic); + u32 physical_id; + + /* + * Deliberately truncate the vCPU ID when detecting a mismatched APIC + * ID to avoid false positives if the vCPU ID, i.e. x2APIC ID, is a + * 32-bit value. Any unwanted aliasing due to truncation results will + * be detected below. + */ + if (!apic_x2apic_mode(apic) && xapic_id != (u8)vcpu->vcpu_id) + *xapic_id_mismatch = true; + + /* + * Apply KVM's hotplug hack if userspace has enable 32-bit APIC IDs. + * Allow sending events to vCPUs by their x2APIC ID even if the target + * vCPU is in legacy xAPIC mode, and silently ignore aliased xAPIC IDs + * (the x2APIC ID is truncated to 8 bits, causing IDs > 0xff to wrap + * and collide). + * + * Honor the architectural (and KVM's non-optimized) behavior if + * userspace has not enabled 32-bit x2APIC IDs. Each APIC is supposed + * to process messages independently. If multiple vCPUs have the same + * effective APIC ID, e.g. due to the x2APIC wrap or because the guest + * manually modified its xAPIC IDs, events targeting that ID are + * supposed to be recognized by all vCPUs with said ID. + */ + if (vcpu->kvm->arch.x2apic_format) { + /* See also kvm_apic_match_physical_addr(). */ + if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) && + x2apic_id <= new->max_apic_id) + new->phys_map[x2apic_id] = apic; + + if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) + new->phys_map[xapic_id] = apic; + } else { + /* + * Disable the optimized map if the physical APIC ID is already + * mapped, i.e. is aliased to multiple vCPUs. The optimized + * map requires a strict 1:1 mapping between IDs and vCPUs. + */ + if (apic_x2apic_mode(apic)) + physical_id = x2apic_id; + else + physical_id = xapic_id; + + if (new->phys_map[physical_id]) + return -EINVAL; + + new->phys_map[physical_id] = apic; + } + + return 0; +} + +static void kvm_recalculate_logical_map(struct kvm_apic_map *new, + struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + enum kvm_apic_logical_mode logical_mode; + struct kvm_lapic **cluster; + u16 mask; + u32 ldr; + + if (new->logical_mode == KVM_APIC_MODE_MAP_DISABLED) + return; + + if (!kvm_apic_sw_enabled(apic)) + return; + + ldr = kvm_lapic_get_reg(apic, APIC_LDR); + if (!ldr) + return; + + if (apic_x2apic_mode(apic)) { + logical_mode = KVM_APIC_MODE_X2APIC; + } else { + ldr = GET_APIC_LOGICAL_ID(ldr); + if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) + logical_mode = KVM_APIC_MODE_XAPIC_FLAT; + else + logical_mode = KVM_APIC_MODE_XAPIC_CLUSTER; + } + + /* + * To optimize logical mode delivery, all software-enabled APICs must + * be configured for the same mode. + */ + if (new->logical_mode == KVM_APIC_MODE_SW_DISABLED) { + new->logical_mode = logical_mode; + } else if (new->logical_mode != logical_mode) { + new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; + return; + } + + /* + * In x2APIC mode, the LDR is read-only and derived directly from the + * x2APIC ID, thus is guaranteed to be addressable. KVM reuses + * kvm_apic_map.phys_map to optimize logical mode x2APIC interrupts by + * reversing the LDR calculation to get cluster of APICs, i.e. no + * additional work is required. + */ + if (apic_x2apic_mode(apic)) { + WARN_ON_ONCE(ldr != kvm_apic_calc_x2apic_ldr(kvm_x2apic_id(apic))); + return; + } + + if (WARN_ON_ONCE(!kvm_apic_map_get_logical_dest(new, ldr, + &cluster, &mask))) { + new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; + return; + } + + if (!mask) + return; + + ldr = ffs(mask) - 1; + if (!is_power_of_2(mask) || cluster[ldr]) + new->logical_mode = KVM_APIC_MODE_MAP_DISABLED; + else + cluster[ldr] = apic; +} + /* * CLEAN -> DIRTY and UPDATE_IN_PROGRESS -> DIRTY changes happen without a lock. * @@ -224,6 +365,7 @@ void kvm_recalculate_apic_map(struct kvm *kvm) struct kvm_vcpu *vcpu; unsigned long i; u32 max_id = 255; /* enough space for any xAPIC ID */ + bool xapic_id_mismatch = false; /* Read kvm->arch.apic_map_dirty before kvm->arch.apic_map. */ if (atomic_read_acquire(&kvm->arch.apic_map_dirty) == CLEAN) @@ -256,54 +398,41 @@ void kvm_recalculate_apic_map(struct kvm *kvm) goto out; new->max_apic_id = max_id; + new->logical_mode = KVM_APIC_MODE_SW_DISABLED; kvm_for_each_vcpu(i, vcpu, kvm) { - struct kvm_lapic *apic = vcpu->arch.apic; - struct kvm_lapic **cluster; - u16 mask; - u32 ldr; - u8 xapic_id; - u32 x2apic_id; - if (!kvm_apic_present(vcpu)) continue; - xapic_id = kvm_xapic_id(apic); - x2apic_id = kvm_x2apic_id(apic); - - /* Hotplug hack: see kvm_apic_match_physical_addr(), ... */ - if ((apic_x2apic_mode(apic) || x2apic_id > 0xff) && - x2apic_id <= new->max_apic_id) - new->phys_map[x2apic_id] = apic; - /* - * ... xAPIC ID of VCPUs with APIC ID > 0xff will wrap-around, - * prevent them from masking VCPUs with APIC ID <= 0xff. - */ - if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id]) - new->phys_map[xapic_id] = apic; - - if (!kvm_apic_sw_enabled(apic)) - continue; - - ldr = kvm_lapic_get_reg(apic, APIC_LDR); - - if (apic_x2apic_mode(apic)) { - new->mode |= KVM_APIC_MODE_X2APIC; - } else if (ldr) { - ldr = GET_APIC_LOGICAL_ID(ldr); - if (kvm_lapic_get_reg(apic, APIC_DFR) == APIC_DFR_FLAT) - new->mode |= KVM_APIC_MODE_XAPIC_FLAT; - else - new->mode |= KVM_APIC_MODE_XAPIC_CLUSTER; + if (kvm_recalculate_phys_map(new, vcpu, &xapic_id_mismatch)) { + kvfree(new); + new = NULL; + goto out; } - if (!kvm_apic_map_get_logical_dest(new, ldr, &cluster, &mask)) - continue; - - if (mask) - cluster[ffs(mask) - 1] = apic; + kvm_recalculate_logical_map(new, vcpu); } out: + /* + * The optimized map is effectively KVM's internal version of APICv, + * and all unwanted aliasing that results in disabling the optimized + * map also applies to APICv. + */ + if (!new) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED); + else + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED); + + if (!new || new->logical_mode == KVM_APIC_MODE_MAP_DISABLED) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED); + else + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED); + + if (xapic_id_mismatch) + kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); + else + kvm_clear_apicv_inhibit(kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); + old = rcu_dereference_protected(kvm->arch.apic_map, lockdep_is_held(&kvm->arch.apic_map_lock)); rcu_assign_pointer(kvm->arch.apic_map, new); @@ -360,11 +489,6 @@ static inline void kvm_apic_set_dfr(struct kvm_lapic *apic, u32 val) atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); } -static inline u32 kvm_apic_calc_x2apic_ldr(u32 id) -{ - return ((id >> 4) << 16) | (1 << (id & 0xf)); -} - static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id) { u32 ldr = kvm_apic_calc_x2apic_ldr(id); @@ -941,8 +1065,7 @@ static void kvm_apic_disabled_lapic_found(struct kvm *kvm) { if (!kvm->arch.disabled_lapic_found) { kvm->arch.disabled_lapic_found = true; - printk(KERN_INFO - "Disabled LAPIC found during irq injection\n"); + pr_info("Disabled LAPIC found during irq injection\n"); } } @@ -951,7 +1074,7 @@ static bool kvm_apic_is_broadcast_dest(struct kvm *kvm, struct kvm_lapic **src, { if (kvm->arch.x2apic_broadcast_quirk_disabled) { if ((irq->dest_id == APIC_BROADCAST && - map->mode != KVM_APIC_MODE_X2APIC)) + map->logical_mode != KVM_APIC_MODE_X2APIC)) return true; if (irq->dest_id == X2APIC_BROADCAST) return true; @@ -1560,7 +1683,7 @@ static void limit_periodic_timer_frequency(struct kvm_lapic *apic) if (apic->lapic_timer.period < min_period) { pr_info_ratelimited( - "kvm: vcpu %i: requested %lld ns " + "vcpu %i: requested %lld ns " "lapic timer period limited to %lld ns\n", apic->vcpu->vcpu_id, apic->lapic_timer.period, min_period); @@ -1845,7 +1968,7 @@ static bool set_target_expiration(struct kvm_lapic *apic, u32 count_reg) deadline = apic->lapic_timer.period; else if (unlikely(deadline > apic->lapic_timer.period)) { pr_info_ratelimited( - "kvm: vcpu %i: requested lapic timer restore with " + "vcpu %i: requested lapic timer restore with " "starting count register %#x=%u (%lld ns) > initial count (%lld ns). " "Using initial count to start timer.\n", apic->vcpu->vcpu_id, @@ -2068,19 +2191,6 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val) } } -static void kvm_lapic_xapic_id_updated(struct kvm_lapic *apic) -{ - struct kvm *kvm = apic->vcpu->kvm; - - if (KVM_BUG_ON(apic_x2apic_mode(apic), kvm)) - return; - - if (kvm_xapic_id(apic) == apic->vcpu->vcpu_id) - return; - - kvm_set_apicv_inhibit(apic->vcpu->kvm, APICV_INHIBIT_REASON_APIC_ID_MODIFIED); -} - static int get_lvt_index(u32 reg) { if (reg == APIC_LVTCMCI) @@ -2101,7 +2211,6 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_ID: /* Local APIC ID */ if (!apic_x2apic_mode(apic)) { kvm_apic_set_xapic_id(apic, val >> 24); - kvm_lapic_xapic_id_updated(apic); } else { ret = 1; } @@ -2284,23 +2393,18 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) struct kvm_lapic *apic = vcpu->arch.apic; u64 val; - if (apic_x2apic_mode(apic)) { - if (KVM_BUG_ON(kvm_lapic_msr_read(apic, offset, &val), vcpu->kvm)) - return; - } else { - val = kvm_lapic_get_reg(apic, offset); - } - /* * ICR is a single 64-bit register when x2APIC is enabled. For legacy * xAPIC, ICR writes need to go down the common (slightly slower) path * to get the upper half from ICR2. */ if (apic_x2apic_mode(apic) && offset == APIC_ICR) { + val = kvm_lapic_get_reg64(apic, APIC_ICR); kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32)); trace_kvm_apic_write(APIC_ICR, val); } else { /* TODO: optimize to just emulate side effect w/o one more write */ + val = kvm_lapic_get_reg(apic, offset); kvm_lapic_reg_write(apic, offset, (u32)val); } } @@ -2398,7 +2502,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value) kvm_apic_set_x2apic_id(apic, vcpu->vcpu_id); if ((old_value ^ value) & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE)) { - kvm_vcpu_update_apicv(vcpu); + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); static_call_cond(kvm_x86_set_virtual_apic_mode)(vcpu); } @@ -2429,6 +2533,78 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) */ apic->isr_count = count_vectors(apic->regs + APIC_ISR); } + apic->highest_isr_cache = -1; +} + +int kvm_alloc_apic_access_page(struct kvm *kvm) +{ + struct page *page; + void __user *hva; + int ret = 0; + + mutex_lock(&kvm->slots_lock); + if (kvm->arch.apic_access_memslot_enabled || + kvm->arch.apic_access_memslot_inhibited) + goto out; + + hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, + APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); + if (IS_ERR(hva)) { + ret = PTR_ERR(hva); + goto out; + } + + page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); + if (is_error_page(page)) { + ret = -EFAULT; + goto out; + } + + /* + * Do not pin the page in memory, so that memory hot-unplug + * is able to migrate it. + */ + put_page(page); + kvm->arch.apic_access_memslot_enabled = true; +out: + mutex_unlock(&kvm->slots_lock); + return ret; +} +EXPORT_SYMBOL_GPL(kvm_alloc_apic_access_page); + +void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + if (!kvm->arch.apic_access_memslot_enabled) + return; + + kvm_vcpu_srcu_read_unlock(vcpu); + + mutex_lock(&kvm->slots_lock); + + if (kvm->arch.apic_access_memslot_enabled) { + __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, 0, 0); + /* + * Clear "enabled" after the memslot is deleted so that a + * different vCPU doesn't get a false negative when checking + * the flag out of slots_lock. No additional memory barrier is + * needed as modifying memslots requires waiting other vCPUs to + * drop SRCU (see above), and false positives are ok as the + * flag is rechecked after acquiring slots_lock. + */ + kvm->arch.apic_access_memslot_enabled = false; + + /* + * Mark the memslot as inhibited to prevent reallocating the + * memslot during vCPU creation, e.g. if a vCPU is hotplugged. + */ + kvm->arch.apic_access_memslot_inhibited = true; + } + + mutex_unlock(&kvm->slots_lock); + + kvm_vcpu_srcu_read_lock(vcpu); } void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -2484,7 +2660,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_lapic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } kvm_apic_update_apicv(vcpu); - apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -2756,9 +2931,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); - if (!apic_x2apic_mode(apic)) - kvm_lapic_xapic_id_updated(apic); - atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); @@ -2772,7 +2944,6 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) __start_apic_timer(apic, APIC_TMCCT); kvm_lapic_set_reg(apic, APIC_TMCCT, 0); kvm_apic_update_apicv(vcpu); - apic->highest_isr_cache = -1; if (apic->apicv_active) { static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu); static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic)); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 58c3242fcc7a..df316ede7546 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -112,6 +112,8 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, struct dest_map *dest_map); int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); void kvm_apic_update_apicv(struct kvm_vcpu *vcpu); +int kvm_alloc_apic_access_page(struct kvm *kvm); +void kvm_inhibit_apic_access_page(struct kvm_vcpu *vcpu); bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, int *r, struct dest_map *dest_map); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 6bdaacb6faa0..168c46fd8dd1 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -230,14 +230,14 @@ static inline bool kvm_shadow_root_allocated(struct kvm *kvm) } #ifdef CONFIG_X86_64 -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return kvm->arch.tdp_mmu_enabled; } +extern bool tdp_mmu_enabled; #else -static inline bool is_tdp_mmu_enabled(struct kvm *kvm) { return false; } +#define tdp_mmu_enabled false #endif static inline bool kvm_memslots_have_rmaps(struct kvm *kvm) { - return !is_tdp_mmu_enabled(kvm) || kvm_shadow_root_allocated(kvm); + return !tdp_mmu_enabled || kvm_shadow_root_allocated(kvm); } static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 835426254e76..c91ee2927dd7 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -14,6 +14,7 @@ * Yaniv Kamay <yaniv@qumranet.com> * Avi Kivity <avi@qumranet.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "irq.h" #include "ioapic.h" @@ -43,6 +44,7 @@ #include <linux/uaccess.h> #include <linux/hash.h> #include <linux/kern_levels.h> +#include <linux/kstrtox.h> #include <linux/kthread.h> #include <asm/page.h> @@ -99,6 +101,13 @@ module_param_named(flush_on_reuse, force_flush_and_sync_on_reuse, bool, 0644); */ bool tdp_enabled = false; +bool __ro_after_init tdp_mmu_allowed; + +#ifdef CONFIG_X86_64 +bool __read_mostly tdp_mmu_enabled = true; +module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0444); +#endif + static int max_huge_page_level __read_mostly; static int tdp_root_level __read_mostly; static int max_tdp_level __read_mostly; @@ -261,6 +270,17 @@ void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, kvm_flush_remote_tlbs_with_range(kvm, &range); } +static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); + +/* Flush the range of guest memory mapped by the given SPTE. */ +static void kvm_flush_remote_tlbs_sptep(struct kvm *kvm, u64 *sptep) +{ + struct kvm_mmu_page *sp = sptep_to_sp(sptep); + gfn_t gfn = kvm_mmu_page_get_gfn(sp, spte_index(sptep)); + + kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level); +} + static void mark_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 gfn, unsigned int access) { @@ -609,9 +629,14 @@ static bool mmu_spte_age(u64 *sptep) return true; } +static inline bool is_tdp_mmu_active(struct kvm_vcpu *vcpu) +{ + return tdp_mmu_enabled && vcpu->arch.mmu->root_role.direct; +} + static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) { - if (is_tdp_mmu(vcpu->arch.mmu)) { + if (is_tdp_mmu_active(vcpu)) { kvm_tdp_mmu_walk_lockless_begin(); } else { /* @@ -630,7 +655,7 @@ static void walk_shadow_page_lockless_begin(struct kvm_vcpu *vcpu) static void walk_shadow_page_lockless_end(struct kvm_vcpu *vcpu) { - if (is_tdp_mmu(vcpu->arch.mmu)) { + if (is_tdp_mmu_active(vcpu)) { kvm_tdp_mmu_walk_lockless_end(); } else { /* @@ -800,7 +825,7 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_disallow_lpage(slot, gfn); if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn, PG_LEVEL_4K)) - kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); + kvm_flush_remote_tlbs_gfn(kvm, gfn, PG_LEVEL_4K); } void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -1174,8 +1199,7 @@ static void drop_large_spte(struct kvm *kvm, u64 *sptep, bool flush) drop_spte(kvm, sptep); if (flush) - kvm_flush_remote_tlbs_with_address(kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_sptep(kvm, sptep); } /* @@ -1279,7 +1303,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, true); @@ -1312,7 +1336,7 @@ static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, false); @@ -1395,7 +1419,7 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, } } - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) write_protected |= kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn, min_level); @@ -1456,7 +1480,7 @@ restart: } if (need_flush && kvm_available_flush_tlb_with_range()) { - kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); + kvm_flush_remote_tlbs_gfn(kvm, gfn, level); return false; } @@ -1558,7 +1582,7 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) flush = kvm_handle_gfn_range(kvm, range, kvm_zap_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) flush = kvm_tdp_mmu_unmap_gfn_range(kvm, range, flush); return flush; @@ -1571,7 +1595,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) flush = kvm_handle_gfn_range(kvm, range, kvm_set_pte_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) flush |= kvm_tdp_mmu_set_spte_gfn(kvm, range); return flush; @@ -1626,8 +1650,7 @@ static void __rmap_add(struct kvm *kvm, kvm->stat.max_mmu_rmap_size = rmap_count; if (rmap_count > RMAP_RECYCLE_THRESHOLD) { kvm_zap_all_rmap_sptes(kvm, rmap_head); - kvm_flush_remote_tlbs_with_address( - kvm, sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_gfn(kvm, gfn, sp->role.level); } } @@ -1646,7 +1669,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) young = kvm_handle_gfn_range(kvm, range, kvm_age_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) young |= kvm_tdp_mmu_age_gfn_range(kvm, range); return young; @@ -1659,7 +1682,7 @@ bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) if (kvm_memslots_have_rmaps(kvm)) young = kvm_handle_gfn_range(kvm, range, kvm_test_age_rmap); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) young |= kvm_tdp_mmu_test_age_gfn(kvm, range); return young; @@ -1921,7 +1944,7 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) return true; /* TDP MMU pages do not use the MMU generation. */ - return !sp->tdp_mmu_page && + return !is_tdp_mmu_page(sp) && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } @@ -2355,7 +2378,16 @@ static void __link_shadow_page(struct kvm *kvm, mmu_page_add_parent_pte(cache, sp, sptep); - if (sp->unsync_children || sp->unsync) + /* + * The non-direct sub-pagetable must be updated before linking. For + * L1 sp, the pagetable is updated via kvm_sync_page() in + * kvm_mmu_find_shadow_page() without write-protecting the gfn, + * so sp->unsync can be true or false. For higher level non-direct + * sp, the pagetable is updated/synced via mmu_sync_children() in + * FNAME(fetch)(), so sp->unsync_children can only be false. + * WARN_ON_ONCE() if anything happens unexpectedly. + */ + if (WARN_ON_ONCE(sp->unsync_children) || sp->unsync) mark_unsync(sptep); } @@ -2383,7 +2415,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, return; drop_parent_pte(child, sptep); - kvm_flush_remote_tlbs_with_address(vcpu->kvm, child->gfn, 1); + kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); } } @@ -2867,8 +2899,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, } if (flush) - kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn, - KVM_PAGES_PER_HPAGE(level)); + kvm_flush_remote_tlbs_gfn(vcpu->kvm, gfn, level); pgprintk("%s: setting spte %llx\n", __func__, *sptep); @@ -3116,11 +3147,11 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ !is_large_pte(spte) && spte_to_child_sp(spte)->nx_huge_page_disallowed) { /* - * A small SPTE exists for this pfn, but FNAME(fetch) - * and __direct_map would like to create a large PTE - * instead: just force them to go down another level, - * patching back for them into pfn the next 9 bits of - * the address. + * A small SPTE exists for this pfn, but FNAME(fetch), + * direct_map(), or kvm_tdp_mmu_map() would like to create a + * large PTE instead: just force them to go down another level, + * patching back for them into pfn the next 9 bits of the + * address. */ u64 page_mask = KVM_PAGES_PER_HPAGE(cur_level) - KVM_PAGES_PER_HPAGE(cur_level - 1); @@ -3129,7 +3160,7 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ } } -static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +static int direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_shadow_walk_iterator it; struct kvm_mmu_page *sp; @@ -3147,7 +3178,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, *it.sptep, it.level); - base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + base_gfn = gfn_round_for_level(fault->gfn, it.level); if (it.level == fault->goal_level) break; @@ -3173,14 +3204,16 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) return ret; } -static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *tsk) +static void kvm_send_hwpoison_signal(struct kvm_memory_slot *slot, gfn_t gfn) { - send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk); + unsigned long hva = gfn_to_hva_memslot(slot, gfn); + + send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, PAGE_SHIFT, current); } -static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) +static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - if (is_sigpending_pfn(pfn)) { + if (is_sigpending_pfn(fault->pfn)) { kvm_handle_signal_exit(vcpu); return -EINTR; } @@ -3190,43 +3223,43 @@ static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) * into the spte otherwise read access on readonly gfn also can * caused mmio page fault and treat it as mmio access. */ - if (pfn == KVM_PFN_ERR_RO_FAULT) + if (fault->pfn == KVM_PFN_ERR_RO_FAULT) return RET_PF_EMULATE; - if (pfn == KVM_PFN_ERR_HWPOISON) { - kvm_send_hwpoison_signal(kvm_vcpu_gfn_to_hva(vcpu, gfn), current); + if (fault->pfn == KVM_PFN_ERR_HWPOISON) { + kvm_send_hwpoison_signal(fault->slot, fault->gfn); return RET_PF_RETRY; } return -EFAULT; } -static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, - unsigned int access) +static int kvm_handle_noslot_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, + unsigned int access) { - /* The pfn is invalid, report the error! */ - if (unlikely(is_error_pfn(fault->pfn))) - return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn); + gva_t gva = fault->is_tdp ? 0 : fault->addr; - if (unlikely(!fault->slot)) { - gva_t gva = fault->is_tdp ? 0 : fault->addr; + vcpu_cache_mmio_info(vcpu, gva, fault->gfn, + access & shadow_mmio_access_mask); - vcpu_cache_mmio_info(vcpu, gva, fault->gfn, - access & shadow_mmio_access_mask); - /* - * If MMIO caching is disabled, emulate immediately without - * touching the shadow page tables as attempting to install an - * MMIO SPTE will just be an expensive nop. Do not cache MMIO - * whose gfn is greater than host.MAXPHYADDR, any guest that - * generates such gfns is running nested and is being tricked - * by L0 userspace (you can observe gfn > L1.MAXPHYADDR if - * and only if L1's MAXPHYADDR is inaccurate with respect to - * the hardware's). - */ - if (unlikely(!enable_mmio_caching) || - unlikely(fault->gfn > kvm_mmu_max_gfn())) - return RET_PF_EMULATE; - } + /* + * If MMIO caching is disabled, emulate immediately without + * touching the shadow page tables as attempting to install an + * MMIO SPTE will just be an expensive nop. + */ + if (unlikely(!enable_mmio_caching)) + return RET_PF_EMULATE; + + /* + * Do not create an MMIO SPTE for a gfn greater than host.MAXPHYADDR, + * any guest that generates such gfns is running nested and is being + * tricked by L0 userspace (you can observe gfn > L1.MAXPHYADDR if and + * only if L1's MAXPHYADDR is inaccurate with respect to the + * hardware's). + */ + if (unlikely(fault->gfn > kvm_mmu_max_gfn())) + return RET_PF_EMULATE; return RET_PF_CONTINUE; } @@ -3350,7 +3383,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) do { u64 new_spte; - if (is_tdp_mmu(vcpu->arch.mmu)) + if (tdp_mmu_enabled) sptep = kvm_tdp_mmu_fast_pf_get_last_sptep(vcpu, fault->addr, &spte); else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); @@ -3433,8 +3466,7 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) } if (++retry_count > 4) { - printk_once(KERN_WARNING - "kvm: Fast #PF retrying more than 4 times.\n"); + pr_warn_once("Fast #PF retrying more than 4 times.\n"); break; } @@ -3596,7 +3628,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) if (r < 0) goto out_unlock; - if (is_tdp_mmu_enabled(vcpu->kvm)) { + if (tdp_mmu_enabled) { root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu); mmu->root.hpa = root; } else if (shadow_root_level >= PT64_ROOT_4LEVEL) { @@ -4026,7 +4058,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) walk_shadow_page_lockless_begin(vcpu); - if (is_tdp_mmu(vcpu->arch.mmu)) + if (is_tdp_mmu_active(vcpu)) leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else leaf = get_walk(vcpu, addr, sptes, &root); @@ -4174,7 +4206,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); } -static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; bool async; @@ -4235,12 +4267,33 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) return RET_PF_CONTINUE; } +static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, + unsigned int access) +{ + int ret; + + fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; + smp_rmb(); + + ret = __kvm_faultin_pfn(vcpu, fault); + if (ret != RET_PF_CONTINUE) + return ret; + + if (unlikely(is_error_pfn(fault->pfn))) + return kvm_handle_error_pfn(vcpu, fault); + + if (unlikely(!fault->slot)) + return kvm_handle_noslot_fault(vcpu, fault, access); + + return RET_PF_CONTINUE; +} + /* * Returns true if the page fault is stale and needs to be retried, i.e. if the * root was invalidated by a memslot update or a relevant mmu_notifier fired. */ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault, int mmu_seq) + struct kvm_page_fault *fault) { struct kvm_mmu_page *sp = to_shadow_page(vcpu->arch.mmu->root.hpa); @@ -4260,19 +4313,13 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, return true; return fault->slot && - mmu_invalidate_retry_hva(vcpu->kvm, mmu_seq, fault->hva); + mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu); - - unsigned long mmu_seq; int r; - fault->gfn = fault->addr >> PAGE_SHIFT; - fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn); - if (page_fault_handle_page_track(vcpu, fault)) return RET_PF_EMULATE; @@ -4284,41 +4331,24 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r) return r; - mmu_seq = vcpu->kvm->mmu_invalidate_seq; - smp_rmb(); - - r = kvm_faultin_pfn(vcpu, fault); - if (r != RET_PF_CONTINUE) - return r; - - r = handle_abnormal_pfn(vcpu, fault, ACC_ALL); + r = kvm_faultin_pfn(vcpu, fault, ACC_ALL); if (r != RET_PF_CONTINUE) return r; r = RET_PF_RETRY; + write_lock(&vcpu->kvm->mmu_lock); - if (is_tdp_mmu_fault) - read_lock(&vcpu->kvm->mmu_lock); - else - write_lock(&vcpu->kvm->mmu_lock); + if (is_page_fault_stale(vcpu, fault)) + goto out_unlock; - if (is_page_fault_stale(vcpu, fault, mmu_seq)) + r = make_mmu_pages_available(vcpu); + if (r) goto out_unlock; - if (is_tdp_mmu_fault) { - r = kvm_tdp_mmu_map(vcpu, fault); - } else { - r = make_mmu_pages_available(vcpu); - if (r) - goto out_unlock; - r = __direct_map(vcpu, fault); - } + r = direct_map(vcpu, fault); out_unlock: - if (is_tdp_mmu_fault) - read_unlock(&vcpu->kvm->mmu_lock); - else - write_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(fault->pfn); return r; } @@ -4366,6 +4396,42 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, } EXPORT_SYMBOL_GPL(kvm_handle_page_fault); +#ifdef CONFIG_X86_64 +static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int r; + + if (page_fault_handle_page_track(vcpu, fault)) + return RET_PF_EMULATE; + + r = fast_page_fault(vcpu, fault); + if (r != RET_PF_INVALID) + return r; + + r = mmu_topup_memory_caches(vcpu, false); + if (r) + return r; + + r = kvm_faultin_pfn(vcpu, fault, ACC_ALL); + if (r != RET_PF_CONTINUE) + return r; + + r = RET_PF_RETRY; + read_lock(&vcpu->kvm->mmu_lock); + + if (is_page_fault_stale(vcpu, fault)) + goto out_unlock; + + r = kvm_tdp_mmu_map(vcpu, fault); + +out_unlock: + read_unlock(&vcpu->kvm->mmu_lock); + kvm_release_pfn_clean(fault->pfn); + return r; +} +#endif + int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { /* @@ -4383,13 +4449,19 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) { for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) { int page_num = KVM_PAGES_PER_HPAGE(fault->max_level); - gfn_t base = (fault->addr >> PAGE_SHIFT) & ~(page_num - 1); + gfn_t base = gfn_round_for_level(fault->gfn, + fault->max_level); if (kvm_mtrr_check_gfn_range_consistency(vcpu, base, page_num)) break; } } +#ifdef CONFIG_X86_64 + if (tdp_mmu_enabled) + return kvm_tdp_mmu_page_fault(vcpu, fault); +#endif + return direct_page_fault(vcpu, fault); } @@ -4494,10 +4566,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) struct kvm_mmu *mmu = vcpu->arch.mmu; union kvm_mmu_page_role new_role = mmu->root_role; - if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role)) { - /* kvm_mmu_ensure_valid_pgd will set up a new root. */ + /* + * Return immediately if no usable root was found, kvm_mmu_reload() + * will establish a valid root prior to the next VM-Enter. + */ + if (!fast_pgd_switch(vcpu->kvm, mmu, new_pgd, new_role)) return; - } /* * It's possible that the cached previous root page is obsolete because @@ -5719,6 +5793,9 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, tdp_root_level = tdp_forced_root_level; max_tdp_level = tdp_max_root_level; +#ifdef CONFIG_X86_64 + tdp_mmu_enabled = tdp_mmu_allowed && tdp_enabled; +#endif /* * max_huge_page_level reflects KVM's MMU capabilities irrespective * of kernel support, e.g. KVM may be capable of using 1GB pages when @@ -5966,7 +6043,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * write and in the same critical section as making the reload request, * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield. */ - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_invalidate_all_roots(kvm); /* @@ -5991,7 +6068,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * Deferring the zap until the final reference to the root is put would * lead to use-after-free. */ - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_zap_invalidated_roots(kvm); } @@ -6017,9 +6094,11 @@ int kvm_mmu_init_vm(struct kvm *kvm) INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); - r = kvm_mmu_init_tdp_mmu(kvm); - if (r < 0) - return r; + if (tdp_mmu_enabled) { + r = kvm_mmu_init_tdp_mmu(kvm); + if (r < 0) + return r; + } node->track_write = kvm_mmu_pte_write; node->track_flush_slot = kvm_mmu_invalidate_zap_pages_in_memslot; @@ -6049,7 +6128,8 @@ void kvm_mmu_uninit_vm(struct kvm *kvm) kvm_page_track_unregister_notifier(kvm, node); - kvm_mmu_uninit_tdp_mmu(kvm); + if (tdp_mmu_enabled) + kvm_mmu_uninit_tdp_mmu(kvm); mmu_free_vm_memory_caches(kvm); } @@ -6103,7 +6183,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start, gfn_end, true, flush); @@ -6136,7 +6216,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, write_unlock(&kvm->mmu_lock); } - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_wrprot_slot(kvm, memslot, start_level); read_unlock(&kvm->mmu_lock); @@ -6379,7 +6459,7 @@ void kvm_mmu_try_split_huge_pages(struct kvm *kvm, u64 start, u64 end, int target_level) { - if (!is_tdp_mmu_enabled(kvm)) + if (!tdp_mmu_enabled) return; if (kvm_memslots_have_rmaps(kvm)) @@ -6400,7 +6480,7 @@ void kvm_mmu_slot_try_split_huge_pages(struct kvm *kvm, u64 start = memslot->base_gfn; u64 end = start + memslot->npages; - if (!is_tdp_mmu_enabled(kvm)) + if (!tdp_mmu_enabled) return; if (kvm_memslots_have_rmaps(kvm)) { @@ -6450,8 +6530,7 @@ restart: kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) - kvm_flush_remote_tlbs_with_address(kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_sptep(kvm, sptep); else need_tlb_flush = 1; @@ -6483,7 +6562,7 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, write_unlock(&kvm->mmu_lock); } - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); read_unlock(&kvm->mmu_lock); @@ -6518,7 +6597,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, write_unlock(&kvm->mmu_lock); } - if (is_tdp_mmu_enabled(kvm)) { + if (tdp_mmu_enabled) { read_lock(&kvm->mmu_lock); kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); read_unlock(&kvm->mmu_lock); @@ -6553,7 +6632,7 @@ restart: kvm_mmu_commit_zap_page(kvm, &invalid_list); - if (is_tdp_mmu_enabled(kvm)) + if (tdp_mmu_enabled) kvm_tdp_mmu_zap_all(kvm); write_unlock(&kvm->mmu_lock); @@ -6579,7 +6658,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) * zap all shadow pages. */ if (unlikely(gen == 0)) { - kvm_debug_ratelimited("kvm: zapping shadow pages for mmio generation wraparound\n"); + kvm_debug_ratelimited("zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_zap_all_fast(kvm); } } @@ -6684,7 +6763,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) new_val = 1; else if (sysfs_streq(val, "auto")) new_val = get_nx_auto_mode(); - else if (strtobool(val, &new_val) < 0) + else if (kstrtobool(val, &new_val) < 0) return -EINVAL; __set_nx_huge_pages(new_val); @@ -6718,6 +6797,13 @@ void __init kvm_mmu_x86_module_init(void) if (nx_huge_pages == -1) __set_nx_huge_pages(get_nx_auto_mode()); + /* + * Snapshot userspace's desire to enable the TDP MMU. Whether or not the + * TDP MMU is actually enabled is determined in kvm_configure_mmu() + * when the vendor module is loaded. + */ + tdp_mmu_allowed = tdp_mmu_enabled; + kvm_mmu_spte_module_init(); } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index dbaf6755c5a7..cc58631e2336 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -156,6 +156,11 @@ static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode; } +static inline gfn_t gfn_round_for_level(gfn_t gfn, int level) +{ + return gfn & -KVM_PAGES_PER_HPAGE(level); +} + int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, gfn_t gfn, bool can_unsync, bool prefetch); @@ -164,8 +169,17 @@ void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn); bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level); + void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, u64 start_gfn, u64 pages); + +/* Flush the given page (huge or not) of guest memory. */ +static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level) +{ + kvm_flush_remote_tlbs_with_address(kvm, gfn_round_for_level(gfn, level), + KVM_PAGES_PER_HPAGE(level)); +} + unsigned int pte_list_count(struct kvm_rmap_head *rmap_head); extern int nx_huge_pages; @@ -199,7 +213,7 @@ struct kvm_page_fault { /* * Maximum page size that can be created for this fault; input to - * FNAME(fetch), __direct_map and kvm_tdp_mmu_map. + * FNAME(fetch), direct_map() and kvm_tdp_mmu_map(). */ u8 max_level; @@ -222,6 +236,7 @@ struct kvm_page_fault { struct kvm_memory_slot *slot; /* Outputs of kvm_faultin_pfn. */ + unsigned long mmu_seq; kvm_pfn_t pfn; hva_t hva; bool map_writable; @@ -279,6 +294,11 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, }; int r; + if (vcpu->arch.mmu->root_role.direct) { + fault.gfn = fault.addr >> PAGE_SHIFT; + fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn); + } + /* * Async #PF "faults", a.k.a. prefetch faults, are not faults from the * guest perspective and have already been counted at the time of the diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 2e09d1b6249f..0a2ac438d647 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -10,6 +10,7 @@ * Author: * Xiao Guangrong <guangrong.xiao@linux.intel.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <linux/rculist.h> diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 0f6455072055..57f0b75c80f9 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -642,12 +642,12 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (WARN_ON(!VALID_PAGE(vcpu->arch.mmu->root.hpa))) goto out_gpte_changed; - for (shadow_walk_init(&it, vcpu, fault->addr); - shadow_walk_okay(&it) && it.level > gw->level; - shadow_walk_next(&it)) { + for_each_shadow_entry(vcpu, fault->addr, it) { gfn_t table_gfn; clear_sp_write_flooding_count(it.sptep); + if (it.level == gw->level) + break; table_gfn = gw->table_gfn[it.level - 2]; access = gw->pt_access[it.level - 2]; @@ -692,8 +692,6 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, trace_kvm_mmu_spte_requested(fault); for (; shadow_walk_okay(&it); shadow_walk_next(&it)) { - clear_sp_write_flooding_count(it.sptep); - /* * We cannot overwrite existing page tables with an NX * large page, as the leaf could be executable. @@ -701,7 +699,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, *it.sptep, it.level); - base_gfn = fault->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); + base_gfn = gfn_round_for_level(fault->gfn, it.level); if (it.level == fault->goal_level) break; @@ -791,7 +789,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault { struct guest_walker walker; int r; - unsigned long mmu_seq; bool is_self_change_mapping; pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code); @@ -838,14 +835,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault else fault->max_level = walker.level; - mmu_seq = vcpu->kvm->mmu_invalidate_seq; - smp_rmb(); - - r = kvm_faultin_pfn(vcpu, fault); - if (r != RET_PF_CONTINUE) - return r; - - r = handle_abnormal_pfn(vcpu, fault, walker.pte_access); + r = kvm_faultin_pfn(vcpu, fault, walker.pte_access); if (r != RET_PF_CONTINUE) return r; @@ -871,7 +861,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault r = RET_PF_RETRY; write_lock(&vcpu->kvm->mmu_lock); - if (is_page_fault_stale(vcpu, fault, mmu_seq)) + if (is_page_fault_stale(vcpu, fault)) goto out_unlock; r = make_mmu_pages_available(vcpu); @@ -937,8 +927,7 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL); if (is_shadow_present_pte(old_spte)) - kvm_flush_remote_tlbs_with_address(vcpu->kvm, - sp->gfn, KVM_PAGES_PER_HPAGE(sp->role.level)); + kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); if (!rmap_can_add(vcpu)) break; diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index c0fd7e049b4e..c15bfca3ed15 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -7,7 +7,7 @@ * Copyright (C) 2006 Qumranet, Inc. * Copyright 2020 Red Hat, Inc. and/or its affiliates. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "mmu.h" @@ -147,9 +147,9 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, WARN_ON_ONCE(!pte_access && !shadow_present_mask); if (sp->role.ad_disabled) - spte |= SPTE_TDP_AD_DISABLED_MASK; + spte |= SPTE_TDP_AD_DISABLED; else if (kvm_mmu_page_ad_need_write_protect(sp)) - spte |= SPTE_TDP_AD_WRPROT_ONLY_MASK; + spte |= SPTE_TDP_AD_WRPROT_ONLY; /* * For the EPT case, shadow_present_mask is 0 if hardware @@ -317,7 +317,7 @@ u64 make_nonleaf_spte(u64 *child_pt, bool ad_disabled) shadow_user_mask | shadow_x_mask | shadow_me_value; if (ad_disabled) - spte |= SPTE_TDP_AD_DISABLED_MASK; + spte |= SPTE_TDP_AD_DISABLED; else spte |= shadow_accessed_mask; @@ -352,7 +352,7 @@ u64 mark_spte_for_access_track(u64 spte) WARN_ONCE(spte & (SHADOW_ACC_TRACK_SAVED_BITS_MASK << SHADOW_ACC_TRACK_SAVED_BITS_SHIFT), - "kvm: Access Tracking saved bit locations are not zero\n"); + "Access Tracking saved bit locations are not zero\n"); spte |= (spte & SHADOW_ACC_TRACK_SAVED_BITS_MASK) << SHADOW_ACC_TRACK_SAVED_BITS_SHIFT; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 6f54dc9409c9..1279db2eab44 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -28,10 +28,10 @@ */ #define SPTE_TDP_AD_SHIFT 52 #define SPTE_TDP_AD_MASK (3ULL << SPTE_TDP_AD_SHIFT) -#define SPTE_TDP_AD_ENABLED_MASK (0ULL << SPTE_TDP_AD_SHIFT) -#define SPTE_TDP_AD_DISABLED_MASK (1ULL << SPTE_TDP_AD_SHIFT) -#define SPTE_TDP_AD_WRPROT_ONLY_MASK (2ULL << SPTE_TDP_AD_SHIFT) -static_assert(SPTE_TDP_AD_ENABLED_MASK == 0); +#define SPTE_TDP_AD_ENABLED (0ULL << SPTE_TDP_AD_SHIFT) +#define SPTE_TDP_AD_DISABLED (1ULL << SPTE_TDP_AD_SHIFT) +#define SPTE_TDP_AD_WRPROT_ONLY (2ULL << SPTE_TDP_AD_SHIFT) +static_assert(SPTE_TDP_AD_ENABLED == 0); #ifdef CONFIG_DYNAMIC_PHYSICAL_MASK #define SPTE_BASE_ADDR_MASK (physical_mask & ~(u64)(PAGE_SIZE-1)) @@ -164,7 +164,7 @@ extern u64 __read_mostly shadow_me_value; extern u64 __read_mostly shadow_me_mask; /* - * SPTEs in MMUs without A/D bits are marked with SPTE_TDP_AD_DISABLED_MASK; + * SPTEs in MMUs without A/D bits are marked with SPTE_TDP_AD_DISABLED; * shadow_acc_track_mask is the set of bits to be cleared in non-accessed * pages. */ @@ -266,18 +266,18 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp) static inline bool spte_ad_enabled(u64 spte) { MMU_WARN_ON(!is_shadow_present_pte(spte)); - return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED_MASK; + return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_DISABLED; } static inline bool spte_ad_need_write_protect(u64 spte) { MMU_WARN_ON(!is_shadow_present_pte(spte)); /* - * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED_MASK is '0', + * This is benign for non-TDP SPTEs as SPTE_TDP_AD_ENABLED is '0', * and non-TDP SPTEs will never set these bits. Optimize for 64-bit * TDP and do the A/D type check unconditionally. */ - return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_ENABLED_MASK; + return (spte & SPTE_TDP_AD_MASK) != SPTE_TDP_AD_ENABLED; } static inline u64 spte_shadow_accessed_mask(u64 spte) @@ -435,11 +435,11 @@ static inline void check_spte_writable_invariants(u64 spte) { if (spte & shadow_mmu_writable_mask) WARN_ONCE(!(spte & shadow_host_writable_mask), - "kvm: MMU-writable SPTE is not Host-writable: %llx", + KBUILD_MODNAME ": MMU-writable SPTE is not Host-writable: %llx", spte); else WARN_ONCE(is_writable_pte(spte), - "kvm: Writable SPTE is not MMU-writable: %llx", spte); + KBUILD_MODNAME ": Writable SPTE is not MMU-writable: %llx", spte); } static inline bool is_mmu_writable_spte(u64 spte) diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index 39b48e7d7d1a..d2eb0d4f8710 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "mmu_internal.h" #include "tdp_iter.h" @@ -15,11 +16,6 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter) iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep); } -static gfn_t round_gfn_for_level(gfn_t gfn, int level) -{ - return gfn & -KVM_PAGES_PER_HPAGE(level); -} - /* * Return the TDP iterator to the root PT and allow it to continue its * traversal over the paging structure from there. @@ -30,7 +26,7 @@ void tdp_iter_restart(struct tdp_iter *iter) iter->yielded_gfn = iter->next_last_level_gfn; iter->level = iter->root_level; - iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); + iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level); tdp_iter_refresh_sptep(iter); iter->valid = true; @@ -97,7 +93,7 @@ static bool try_step_down(struct tdp_iter *iter) iter->level--; iter->pt_path[iter->level - 1] = child_pt; - iter->gfn = round_gfn_for_level(iter->next_last_level_gfn, iter->level); + iter->gfn = gfn_round_for_level(iter->next_last_level_gfn, iter->level); tdp_iter_refresh_sptep(iter); return true; @@ -139,7 +135,7 @@ static bool try_step_up(struct tdp_iter *iter) return false; iter->level++; - iter->gfn = round_gfn_for_level(iter->gfn, iter->level); + iter->gfn = gfn_round_for_level(iter->gfn, iter->level); tdp_iter_refresh_sptep(iter); return true; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d6df38d371a0..7c25dbf32ecc 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "mmu.h" #include "mmu_internal.h" @@ -10,23 +11,15 @@ #include <asm/cmpxchg.h> #include <trace/events/kvm.h> -static bool __read_mostly tdp_mmu_enabled = true; -module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0644); - /* Initializes the TDP MMU for the VM, if enabled. */ int kvm_mmu_init_tdp_mmu(struct kvm *kvm) { struct workqueue_struct *wq; - if (!tdp_enabled || !READ_ONCE(tdp_mmu_enabled)) - return 0; - wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0); if (!wq) return -ENOMEM; - /* This should not be changed for the lifetime of the VM. */ - kvm->arch.tdp_mmu_enabled = true; INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); kvm->arch.tdp_mmu_zap_wq = wq; @@ -47,9 +40,6 @@ static __always_inline bool kvm_lockdep_assert_mmu_lock_held(struct kvm *kvm, void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) { - if (!kvm->arch.tdp_mmu_enabled) - return; - /* Also waits for any queued work items. */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); @@ -144,7 +134,7 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; - WARN_ON(!root->tdp_mmu_page); + WARN_ON(!is_tdp_mmu_page(root)); /* * The root now has refcount=0. It is valid, but readers already @@ -690,8 +680,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, if (ret) return ret; - kvm_flush_remote_tlbs_with_address(kvm, iter->gfn, - KVM_PAGES_PER_HPAGE(iter->level)); + kvm_flush_remote_tlbs_gfn(kvm, iter->gfn, iter->level); /* * No other thread can overwrite the removed SPTE as they must either @@ -1090,8 +1079,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, return RET_PF_RETRY; else if (is_shadow_present_pte(iter->old_spte) && !is_last_spte(iter->old_spte, iter->level)) - kvm_flush_remote_tlbs_with_address(vcpu->kvm, sp->gfn, - KVM_PAGES_PER_HPAGE(iter->level + 1)); + kvm_flush_remote_tlbs_gfn(vcpu->kvm, iter->gfn, iter->level); /* * If the page fault was caused by a write but the page is write diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index d3714200b932..0a63b1afabd3 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -7,6 +7,9 @@ #include "spte.h" +int kvm_mmu_init_tdp_mmu(struct kvm *kvm); +void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); + hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) @@ -68,31 +71,9 @@ u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, u64 addr, u64 *spte); #ifdef CONFIG_X86_64 -int kvm_mmu_init_tdp_mmu(struct kvm *kvm); -void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return sp->tdp_mmu_page; } - -static inline bool is_tdp_mmu(struct kvm_mmu *mmu) -{ - struct kvm_mmu_page *sp; - hpa_t hpa = mmu->root.hpa; - - if (WARN_ON(!VALID_PAGE(hpa))) - return false; - - /* - * A NULL shadow page is legal when shadowing a non-paging guest with - * PAE paging, as the MMU will be direct with root_hpa pointing at the - * pae_root page, not a shadow page. - */ - sp = to_shadow_page(hpa); - return sp && is_tdp_mmu_page(sp) && sp->root_count; -} #else -static inline int kvm_mmu_init_tdp_mmu(struct kvm *kvm) { return 0; } -static inline void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) {} static inline bool is_tdp_mmu_page(struct kvm_mmu_page *sp) { return false; } -static inline bool is_tdp_mmu(struct kvm_mmu *mmu) { return false; } #endif #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index a8502e02f479..9fac1ec03463 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -13,6 +13,7 @@ * Paolo Bonzini <pbonzini@redhat.com> * Xiao Guangrong <guangrong.xiao@linux.intel.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include <asm/mtrr.h> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index eb594620dd75..612e6c70ce2e 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -9,6 +9,7 @@ * Gleb Natapov <gleb@redhat.com> * Wei Huang <wei@redhat.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/types.h> #include <linux/kvm_host.h> @@ -28,9 +29,18 @@ struct x86_pmu_capability __read_mostly kvm_pmu_cap; EXPORT_SYMBOL_GPL(kvm_pmu_cap); -static const struct x86_cpu_id vmx_icl_pebs_cpu[] = { +/* Precise Distribution of Instructions Retired (PDIR) */ +static const struct x86_cpu_id vmx_pebs_pdir_cpu[] = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, NULL), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X, NULL), + /* Instruction-Accurate PDIR (PDIR++) */ + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, NULL), + {} +}; + +/* Precise Distribution (PDist) */ +static const struct x86_cpu_id vmx_pebs_pdist_cpu[] = { + X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, NULL), {} }; @@ -155,6 +165,28 @@ static void kvm_perf_overflow(struct perf_event *perf_event, kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } +static u64 pmc_get_pebs_precise_level(struct kvm_pmc *pmc) +{ + /* + * For some model specific pebs counters with special capabilities + * (PDIR, PDIR++, PDIST), KVM needs to raise the event precise + * level to the maximum value (currently 3, backwards compatible) + * so that the perf subsystem would assign specific hardware counter + * with that capability for vPMC. + */ + if ((pmc->idx == 0 && x86_match_cpu(vmx_pebs_pdist_cpu)) || + (pmc->idx == 32 && x86_match_cpu(vmx_pebs_pdir_cpu))) + return 3; + + /* + * The non-zero precision level of guest event makes the ordinary + * guest event becomes a guest PEBS event and triggers the host + * PEBS PMI handler to determine whether the PEBS overflow PMI + * comes from the host counters or the guest. + */ + return 1; +} + static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, bool exclude_user, bool exclude_kernel, bool intr) @@ -186,22 +218,12 @@ static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, } if (pebs) { /* - * The non-zero precision level of guest event makes the ordinary - * guest event becomes a guest PEBS event and triggers the host - * PEBS PMI handler to determine whether the PEBS overflow PMI - * comes from the host counters or the guest. - * * For most PEBS hardware events, the difference in the software * precision levels of guest and host PEBS events will not affect * the accuracy of the PEBS profiling result, because the "event IP" * in the PEBS record is calibrated on the guest side. - * - * On Icelake everything is fine. Other hardware (GLC+, TNT+) that - * could possibly care here is unsupported and needs changes. */ - attr.precise_ip = 1; - if (x86_match_cpu(vmx_icl_pebs_cpu) && pmc->idx == 32) - attr.precise_ip = 3; + attr.precise_ip = pmc_get_pebs_precise_level(pmc); } event = perf_event_create_kernel_counter(&attr, -1, current, @@ -254,48 +276,128 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) return true; } -static int cmp_u64(const void *pa, const void *pb) +static int filter_cmp(const void *pa, const void *pb, u64 mask) { - u64 a = *(u64 *)pa; - u64 b = *(u64 *)pb; + u64 a = *(u64 *)pa & mask; + u64 b = *(u64 *)pb & mask; return (a > b) - (a < b); } + +static int filter_sort_cmp(const void *pa, const void *pb) +{ + return filter_cmp(pa, pb, (KVM_PMU_MASKED_ENTRY_EVENT_SELECT | + KVM_PMU_MASKED_ENTRY_EXCLUDE)); +} + +/* + * For the event filter, searching is done on the 'includes' list and + * 'excludes' list separately rather than on the 'events' list (which + * has both). As a result the exclude bit can be ignored. + */ +static int filter_event_cmp(const void *pa, const void *pb) +{ + return filter_cmp(pa, pb, (KVM_PMU_MASKED_ENTRY_EVENT_SELECT)); +} + +static int find_filter_index(u64 *events, u64 nevents, u64 key) +{ + u64 *fe = bsearch(&key, events, nevents, sizeof(events[0]), + filter_event_cmp); + + if (!fe) + return -1; + + return fe - events; +} + +static bool is_filter_entry_match(u64 filter_event, u64 umask) +{ + u64 mask = filter_event >> (KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT - 8); + u64 match = filter_event & KVM_PMU_MASKED_ENTRY_UMASK_MATCH; + + BUILD_BUG_ON((KVM_PMU_ENCODE_MASKED_ENTRY(0, 0xff, 0, false) >> + (KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT - 8)) != + ARCH_PERFMON_EVENTSEL_UMASK); + + return (umask & mask) == match; +} + +static bool filter_contains_match(u64 *events, u64 nevents, u64 eventsel) +{ + u64 event_select = eventsel & kvm_pmu_ops.EVENTSEL_EVENT; + u64 umask = eventsel & ARCH_PERFMON_EVENTSEL_UMASK; + int i, index; + + index = find_filter_index(events, nevents, event_select); + if (index < 0) + return false; + + /* + * Entries are sorted by the event select. Walk the list in both + * directions to process all entries with the targeted event select. + */ + for (i = index; i < nevents; i++) { + if (filter_event_cmp(&events[i], &event_select)) + break; + + if (is_filter_entry_match(events[i], umask)) + return true; + } + + for (i = index - 1; i >= 0; i--) { + if (filter_event_cmp(&events[i], &event_select)) + break; + + if (is_filter_entry_match(events[i], umask)) + return true; + } + + return false; +} + +static bool is_gp_event_allowed(struct kvm_x86_pmu_event_filter *f, + u64 eventsel) +{ + if (filter_contains_match(f->includes, f->nr_includes, eventsel) && + !filter_contains_match(f->excludes, f->nr_excludes, eventsel)) + return f->action == KVM_PMU_EVENT_ALLOW; + + return f->action == KVM_PMU_EVENT_DENY; +} + +static bool is_fixed_event_allowed(struct kvm_x86_pmu_event_filter *filter, + int idx) +{ + int fixed_idx = idx - INTEL_PMC_IDX_FIXED; + + if (filter->action == KVM_PMU_EVENT_DENY && + test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap)) + return false; + if (filter->action == KVM_PMU_EVENT_ALLOW && + !test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap)) + return false; + + return true; +} + static bool check_pmu_event_filter(struct kvm_pmc *pmc) { - struct kvm_pmu_event_filter *filter; + struct kvm_x86_pmu_event_filter *filter; struct kvm *kvm = pmc->vcpu->kvm; - bool allow_event = true; - __u64 key; - int idx; if (!static_call(kvm_x86_pmu_hw_event_available)(pmc)) return false; filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu); if (!filter) - goto out; + return true; - if (pmc_is_gp(pmc)) { - key = pmc->eventsel & AMD64_RAW_EVENT_MASK_NB; - if (bsearch(&key, filter->events, filter->nevents, - sizeof(__u64), cmp_u64)) - allow_event = filter->action == KVM_PMU_EVENT_ALLOW; - else - allow_event = filter->action == KVM_PMU_EVENT_DENY; - } else { - idx = pmc->idx - INTEL_PMC_IDX_FIXED; - if (filter->action == KVM_PMU_EVENT_DENY && - test_bit(idx, (ulong *)&filter->fixed_counter_bitmap)) - allow_event = false; - if (filter->action == KVM_PMU_EVENT_ALLOW && - !test_bit(idx, (ulong *)&filter->fixed_counter_bitmap)) - allow_event = false; - } + if (pmc_is_gp(pmc)) + return is_gp_event_allowed(filter, pmc->eventsel); -out: - return allow_event; + return is_fixed_event_allowed(filter, pmc->idx); } static void reprogram_counter(struct kvm_pmc *pmc) @@ -592,47 +694,133 @@ void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) } EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event); +static bool is_masked_filter_valid(const struct kvm_x86_pmu_event_filter *filter) +{ + u64 mask = kvm_pmu_ops.EVENTSEL_EVENT | + KVM_PMU_MASKED_ENTRY_UMASK_MASK | + KVM_PMU_MASKED_ENTRY_UMASK_MATCH | + KVM_PMU_MASKED_ENTRY_EXCLUDE; + int i; + + for (i = 0; i < filter->nevents; i++) { + if (filter->events[i] & ~mask) + return false; + } + + return true; +} + +static void convert_to_masked_filter(struct kvm_x86_pmu_event_filter *filter) +{ + int i, j; + + for (i = 0, j = 0; i < filter->nevents; i++) { + /* + * Skip events that are impossible to match against a guest + * event. When filtering, only the event select + unit mask + * of the guest event is used. To maintain backwards + * compatibility, impossible filters can't be rejected :-( + */ + if (filter->events[i] & ~(kvm_pmu_ops.EVENTSEL_EVENT | + ARCH_PERFMON_EVENTSEL_UMASK)) + continue; + /* + * Convert userspace events to a common in-kernel event so + * only one code path is needed to support both events. For + * the in-kernel events use masked events because they are + * flexible enough to handle both cases. To convert to masked + * events all that's needed is to add an "all ones" umask_mask, + * (unmasked filter events don't support EXCLUDE). + */ + filter->events[j++] = filter->events[i] | + (0xFFULL << KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT); + } + + filter->nevents = j; +} + +static int prepare_filter_lists(struct kvm_x86_pmu_event_filter *filter) +{ + int i; + + if (!(filter->flags & KVM_PMU_EVENT_FLAG_MASKED_EVENTS)) + convert_to_masked_filter(filter); + else if (!is_masked_filter_valid(filter)) + return -EINVAL; + + /* + * Sort entries by event select and includes vs. excludes so that all + * entries for a given event select can be processed efficiently during + * filtering. The EXCLUDE flag uses a more significant bit than the + * event select, and so the sorted list is also effectively split into + * includes and excludes sub-lists. + */ + sort(&filter->events, filter->nevents, sizeof(filter->events[0]), + filter_sort_cmp, NULL); + + i = filter->nevents; + /* Find the first EXCLUDE event (only supported for masked events). */ + if (filter->flags & KVM_PMU_EVENT_FLAG_MASKED_EVENTS) { + for (i = 0; i < filter->nevents; i++) { + if (filter->events[i] & KVM_PMU_MASKED_ENTRY_EXCLUDE) + break; + } + } + + filter->nr_includes = i; + filter->nr_excludes = filter->nevents - filter->nr_includes; + filter->includes = filter->events; + filter->excludes = filter->events + filter->nr_includes; + + return 0; +} + int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) { - struct kvm_pmu_event_filter tmp, *filter; + struct kvm_pmu_event_filter __user *user_filter = argp; + struct kvm_x86_pmu_event_filter *filter; + struct kvm_pmu_event_filter tmp; struct kvm_vcpu *vcpu; unsigned long i; size_t size; int r; - if (copy_from_user(&tmp, argp, sizeof(tmp))) + if (copy_from_user(&tmp, user_filter, sizeof(tmp))) return -EFAULT; if (tmp.action != KVM_PMU_EVENT_ALLOW && tmp.action != KVM_PMU_EVENT_DENY) return -EINVAL; - if (tmp.flags != 0) + if (tmp.flags & ~KVM_PMU_EVENT_FLAGS_VALID_MASK) return -EINVAL; if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS) return -E2BIG; size = struct_size(filter, events, tmp.nevents); - filter = kmalloc(size, GFP_KERNEL_ACCOUNT); + filter = kzalloc(size, GFP_KERNEL_ACCOUNT); if (!filter) return -ENOMEM; + filter->action = tmp.action; + filter->nevents = tmp.nevents; + filter->fixed_counter_bitmap = tmp.fixed_counter_bitmap; + filter->flags = tmp.flags; + r = -EFAULT; - if (copy_from_user(filter, argp, size)) + if (copy_from_user(filter->events, user_filter->events, + sizeof(filter->events[0]) * filter->nevents)) goto cleanup; - /* Ensure nevents can't be changed between the user copies. */ - *filter = tmp; - - /* - * Sort the in-kernel list so that we can search it with bsearch. - */ - sort(&filter->events, filter->nevents, sizeof(__u64), cmp_u64, NULL); + r = prepare_filter_lists(filter); + if (r) + goto cleanup; mutex_lock(&kvm->lock); filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter, mutex_is_locked(&kvm->lock)); + mutex_unlock(&kvm->lock); synchronize_srcu_expedited(&kvm->srcu); BUILD_BUG_ON(sizeof(((struct kvm_pmu *)0)->reprogram_pmi) > @@ -643,8 +831,6 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) kvm_make_all_cpus_request(kvm, KVM_REQ_PMU); - mutex_unlock(&kvm->lock); - r = 0; cleanup: kfree(filter); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index cdb91009701d..79988dafb15b 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -18,12 +18,6 @@ #define VMWARE_BACKDOOR_PMC_REAL_TIME 0x10001 #define VMWARE_BACKDOOR_PMC_APPARENT_TIME 0x10002 -struct kvm_event_hw_type_mapping { - u8 eventsel; - u8 unit_mask; - unsigned event_type; -}; - struct kvm_pmu_ops { bool (*hw_event_available)(struct kvm_pmc *pmc); bool (*pmc_is_enabled)(struct kvm_pmc *pmc); @@ -40,6 +34,9 @@ struct kvm_pmu_ops { void (*reset)(struct kvm_vcpu *vcpu); void (*deliver_pmi)(struct kvm_vcpu *vcpu); void (*cleanup)(struct kvm_vcpu *vcpu); + + const u64 EVENTSEL_EVENT; + const int MAX_NR_GP_COUNTERS; }; void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops); @@ -161,7 +158,7 @@ static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) extern struct x86_pmu_capability kvm_pmu_cap; -static inline void kvm_init_pmu_capability(void) +static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) { bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL; @@ -180,6 +177,8 @@ static inline void kvm_init_pmu_capability(void) } kvm_pmu_cap.version = min(kvm_pmu_cap.version, 2); + kvm_pmu_cap.num_counters_gp = min(kvm_pmu_cap.num_counters_gp, + pmu_ops->MAX_NR_GP_COUNTERS); kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed, KVM_PMC_MAX_FIXED); } diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 042d0aca3c92..4945456fd646 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -14,6 +14,7 @@ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, CPUID_7_1_EDX, + CPUID_8000_0007_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, @@ -43,6 +44,9 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5) #define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) +/* CPUID level 0x80000007 (EDX). */ +#define KVM_X86_FEATURE_CONSTANT_TSC KVM_X86_FEATURE(CPUID_8000_0007_EDX, 8) + struct cpuid_reg { u32 function; u32 index; @@ -68,6 +72,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, [CPUID_7_1_EDX] = { 7, 1, CPUID_EDX}, + [CPUID_8000_0007_EDX] = {0x80000007, 0, CPUID_EDX}, }; /* @@ -100,6 +105,8 @@ static __always_inline u32 __feature_translate(int x86_feature) return KVM_X86_FEATURE_SGX2; else if (x86_feature == X86_FEATURE_SGX_EDECCSSA) return KVM_X86_FEATURE_SGX_EDECCSSA; + else if (x86_feature == X86_FEATURE_CONSTANT_TSC) + return KVM_X86_FEATURE_CONSTANT_TSC; return x86_feature; } diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index a9c1c2af8d94..b42111a24cc2 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "x86.h" @@ -110,8 +111,6 @@ static void check_smram_offsets(void) void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) { - BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); - trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); if (entering_smm) { diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 6919dee69f18..ca684979e90d 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -12,7 +12,7 @@ * Avi Kivity <avi@qumranet.com> */ -#define pr_fmt(fmt) "SVM: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_types.h> #include <linux/hashtable.h> @@ -53,7 +53,7 @@ static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); static u32 next_vm_id = 0; static bool next_vm_id_wrapped = 0; static DEFINE_SPINLOCK(svm_vm_data_hash_lock); -enum avic_modes avic_mode; +bool x2avic_enabled; /* * This is a wrapper of struct amd_iommu_ir_data. @@ -72,20 +72,25 @@ static void avic_activate_vmcb(struct vcpu_svm *svm) vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - /* Note: - * KVM can support hybrid-AVIC mode, where KVM emulates x2APIC - * MSR accesses, while interrupt injection to a running vCPU - * can be achieved using AVIC doorbell. The AVIC hardware still - * accelerate MMIO accesses, but this does not cause any harm - * as the guest is not supposed to access xAPIC mmio when uses x2APIC. + /* + * Note: KVM supports hybrid-AVIC mode, where KVM emulates x2APIC MSR + * accesses, while interrupt injection to a running vCPU can be + * achieved using AVIC doorbell. KVM disables the APIC access page + * (deletes the memslot) if any vCPU has x2APIC enabled, thus enabling + * AVIC in hybrid mode activates only the doorbell mechanism. */ - if (apic_x2apic_mode(svm->vcpu.arch.apic) && - avic_mode == AVIC_MODE_X2) { + if (x2avic_enabled && apic_x2apic_mode(svm->vcpu.arch.apic)) { vmcb->control.int_ctl |= X2APIC_MODE_MASK; vmcb->control.avic_physical_id |= X2AVIC_MAX_PHYSICAL_ID; /* Disabling MSR intercept for x2APIC registers */ svm_set_x2apic_msr_interception(svm, false); } else { + /* + * Flush the TLB, the guest may have inserted a non-APIC + * mapping into the TLB while AVIC was disabled. + */ + kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, &svm->vcpu); + /* For xAVIC and hybrid-xAVIC modes */ vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID; /* Enabling MSR intercept for x2APIC registers */ @@ -241,8 +246,8 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, u64 *avic_physical_id_table; struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - if ((avic_mode == AVIC_MODE_X1 && index > AVIC_MAX_PHYSICAL_ID) || - (avic_mode == AVIC_MODE_X2 && index > X2AVIC_MAX_PHYSICAL_ID)) + if ((!x2avic_enabled && index > AVIC_MAX_PHYSICAL_ID) || + (index > X2AVIC_MAX_PHYSICAL_ID)) return NULL; avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page); @@ -250,47 +255,14 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, return &avic_physical_id_table[index]; } -/* - * Note: - * AVIC hardware walks the nested page table to check permissions, - * but does not use the SPA address specified in the leaf page - * table entry since it uses address in the AVIC_BACKING_PAGE pointer - * field of the VMCB. Therefore, we set up the - * APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (4KB) here. - */ -static int avic_alloc_access_page(struct kvm *kvm) -{ - void __user *ret; - int r = 0; - - mutex_lock(&kvm->slots_lock); - - if (kvm->arch.apic_access_memslot_enabled) - goto out; - - ret = __x86_set_memory_region(kvm, - APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, - PAGE_SIZE); - if (IS_ERR(ret)) { - r = PTR_ERR(ret); - goto out; - } - - kvm->arch.apic_access_memslot_enabled = true; -out: - mutex_unlock(&kvm->slots_lock); - return r; -} - static int avic_init_backing_page(struct kvm_vcpu *vcpu) { u64 *entry, new_entry; int id = vcpu->vcpu_id; struct vcpu_svm *svm = to_svm(vcpu); - if ((avic_mode == AVIC_MODE_X1 && id > AVIC_MAX_PHYSICAL_ID) || - (avic_mode == AVIC_MODE_X2 && id > X2AVIC_MAX_PHYSICAL_ID)) + if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) || + (id > X2AVIC_MAX_PHYSICAL_ID)) return -EINVAL; if (!vcpu->arch.apic->regs) @@ -299,7 +271,13 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu) if (kvm_apicv_activated(vcpu->kvm)) { int ret; - ret = avic_alloc_access_page(vcpu->kvm); + /* + * Note, AVIC hardware walks the nested page table to check + * permissions, but does not use the SPA address specified in + * the leaf SPTE since it uses address in the AVIC_BACKING_PAGE + * pointer field of the VMCB. + */ + ret = kvm_alloc_apic_access_page(vcpu->kvm); if (ret) return ret; } @@ -339,6 +317,60 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu) put_cpu(); } + +static void avic_kick_vcpu(struct kvm_vcpu *vcpu, u32 icrl) +{ + vcpu->arch.apic->irr_pending = true; + svm_complete_interrupt_delivery(vcpu, + icrl & APIC_MODE_MASK, + icrl & APIC_INT_LEVELTRIG, + icrl & APIC_VECTOR_MASK); +} + +static void avic_kick_vcpu_by_physical_id(struct kvm *kvm, u32 physical_id, + u32 icrl) +{ + /* + * KVM inhibits AVIC if any vCPU ID diverges from the vCPUs APIC ID, + * i.e. APIC ID == vCPU ID. + */ + struct kvm_vcpu *target_vcpu = kvm_get_vcpu_by_id(kvm, physical_id); + + /* Once again, nothing to do if the target vCPU doesn't exist. */ + if (unlikely(!target_vcpu)) + return; + + avic_kick_vcpu(target_vcpu, icrl); +} + +static void avic_kick_vcpu_by_logical_id(struct kvm *kvm, u32 *avic_logical_id_table, + u32 logid_index, u32 icrl) +{ + u32 physical_id; + + if (avic_logical_id_table) { + u32 logid_entry = avic_logical_id_table[logid_index]; + + /* Nothing to do if the logical destination is invalid. */ + if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) + return; + + physical_id = logid_entry & + AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; + } else { + /* + * For x2APIC, the logical APIC ID is a read-only value that is + * derived from the x2APIC ID, thus the x2APIC ID can be found + * by reversing the calculation (stored in logid_index). Note, + * bits 31:20 of the x2APIC ID aren't propagated to the logical + * ID, but KVM limits the x2APIC ID limited to KVM_MAX_VCPU_IDS. + */ + physical_id = logid_index; + } + + avic_kick_vcpu_by_physical_id(kvm, physical_id, icrl); +} + /* * A fast-path version of avic_kick_target_vcpus(), which attempts to match * destination APIC ID to vCPU without looping through all vCPUs. @@ -346,11 +378,10 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu) static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh, u32 index) { - u32 l1_physical_id, dest; - struct kvm_vcpu *target_vcpu; int dest_mode = icrl & APIC_DEST_MASK; int shorthand = icrl & APIC_SHORT_MASK; struct kvm_svm *kvm_svm = to_kvm_svm(kvm); + u32 dest; if (shorthand != APIC_DEST_NOSHORT) return -EINVAL; @@ -367,18 +398,18 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST) return -EINVAL; - l1_physical_id = dest; - - if (WARN_ON_ONCE(l1_physical_id != index)) + if (WARN_ON_ONCE(dest != index)) return -EINVAL; + avic_kick_vcpu_by_physical_id(kvm, dest, icrl); } else { - u32 bitmap, cluster; - int logid_index; + u32 *avic_logical_id_table; + unsigned long bitmap, i; + u32 cluster; if (apic_x2apic_mode(source)) { /* 16 bit dest mask, 16 bit cluster id */ - bitmap = dest & 0xFFFF0000; + bitmap = dest & 0xFFFF; cluster = (dest >> 16) << 4; } else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) { /* 8 bit dest mask*/ @@ -390,67 +421,32 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source cluster = (dest >> 4) << 2; } + /* Nothing to do if there are no destinations in the cluster. */ if (unlikely(!bitmap)) - /* guest bug: nobody to send the logical interrupt to */ return 0; - if (!is_power_of_2(bitmap)) - /* multiple logical destinations, use slow path */ - return -EINVAL; - - logid_index = cluster + __ffs(bitmap); - - if (!apic_x2apic_mode(source)) { - u32 *avic_logical_id_table = - page_address(kvm_svm->avic_logical_id_table_page); - - u32 logid_entry = avic_logical_id_table[logid_index]; - - if (WARN_ON_ONCE(index != logid_index)) - return -EINVAL; - - /* guest bug: non existing/reserved logical destination */ - if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK))) - return 0; - - l1_physical_id = logid_entry & - AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; - } else { - /* - * For x2APIC logical mode, cannot leverage the index. - * Instead, calculate physical ID from logical ID in ICRH. - */ - int cluster = (icrh & 0xffff0000) >> 16; - int apic = ffs(icrh & 0xffff) - 1; - - /* - * If the x2APIC logical ID sub-field (i.e. icrh[15:0]) - * contains anything but a single bit, we cannot use the - * fast path, because it is limited to a single vCPU. - */ - if (apic < 0 || icrh != (1 << apic)) - return -EINVAL; + if (apic_x2apic_mode(source)) + avic_logical_id_table = NULL; + else + avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page); - l1_physical_id = (cluster << 4) + apic; - } + /* + * AVIC is inhibited if vCPUs aren't mapped 1:1 with logical + * IDs, thus each bit in the destination is guaranteed to map + * to at most one vCPU. + */ + for_each_set_bit(i, &bitmap, 16) + avic_kick_vcpu_by_logical_id(kvm, avic_logical_id_table, + cluster + i, icrl); } - target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id); - if (unlikely(!target_vcpu)) - /* guest bug: non existing vCPU is a target of this IPI*/ - return 0; - - target_vcpu->arch.apic->irr_pending = true; - svm_complete_interrupt_delivery(target_vcpu, - icrl & APIC_MODE_MASK, - icrl & APIC_INT_LEVELTRIG, - icrl & APIC_VECTOR_MASK); return 0; } static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, u32 icrl, u32 icrh, u32 index) { + u32 dest = apic_x2apic_mode(source) ? icrh : GET_XAPIC_DEST_FIELD(icrh); unsigned long i; struct kvm_vcpu *vcpu; @@ -466,21 +462,9 @@ static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source, * since entered the guest will have processed pending IRQs at VMRUN. */ kvm_for_each_vcpu(i, vcpu, kvm) { - u32 dest; - - if (apic_x2apic_mode(vcpu->arch.apic)) - dest = icrh; - else - dest = GET_XAPIC_DEST_FIELD(icrh); - if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK, - dest, icrl & APIC_DEST_MASK)) { - vcpu->arch.apic->irr_pending = true; - svm_complete_interrupt_delivery(vcpu, - icrl & APIC_MODE_MASK, - icrl & APIC_INT_LEVELTRIG, - icrl & APIC_VECTOR_MASK); - } + dest, icrl & APIC_DEST_MASK)) + avic_kick_vcpu(vcpu, icrl); } } @@ -496,14 +480,18 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) trace_kvm_avic_incomplete_ipi(vcpu->vcpu_id, icrh, icrl, id, index); switch (id) { + case AVIC_IPI_FAILURE_INVALID_TARGET: case AVIC_IPI_FAILURE_INVALID_INT_TYPE: /* * Emulate IPIs that are not handled by AVIC hardware, which - * only virtualizes Fixed, Edge-Triggered INTRs. The exit is - * a trap, e.g. ICR holds the correct value and RIP has been - * advanced, KVM is responsible only for emulating the IPI. - * Sadly, hardware may sometimes leave the BUSY flag set, in - * which case KVM needs to emulate the ICR write as well in + * only virtualizes Fixed, Edge-Triggered INTRs, and falls over + * if _any_ targets are invalid, e.g. if the logical mode mask + * is a superset of running vCPUs. + * + * The exit is a trap, e.g. ICR holds the correct value and RIP + * has been advanced, KVM is responsible only for emulating the + * IPI. Sadly, hardware may sometimes leave the BUSY flag set, + * in which case KVM needs to emulate the ICR write as well in * order to clear the BUSY flag. */ if (icrl & APIC_ICR_BUSY) @@ -519,8 +507,6 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) */ avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh, index); break; - case AVIC_IPI_FAILURE_INVALID_TARGET: - break; case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); break; @@ -541,33 +527,33 @@ unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu) static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat) { struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm); - int index; u32 *logical_apic_id_table; - int dlid = GET_APIC_LOGICAL_ID(ldr); - - if (!dlid) - return NULL; + u32 cluster, index; - if (flat) { /* flat */ - index = ffs(dlid) - 1; - if (index > 7) - return NULL; - } else { /* cluster */ - int cluster = (dlid & 0xf0) >> 4; - int apic = ffs(dlid & 0x0f) - 1; + ldr = GET_APIC_LOGICAL_ID(ldr); - if ((apic < 0) || (apic > 7) || - (cluster >= 0xf)) + if (flat) { + cluster = 0; + } else { + cluster = (ldr >> 4); + if (cluster >= 0xf) return NULL; - index = (cluster << 2) + apic; + ldr &= 0xf; } + if (!ldr || !is_power_of_2(ldr)) + return NULL; + + index = __ffs(ldr); + if (WARN_ON_ONCE(index > 7)) + return NULL; + index += (cluster << 2); logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page); return &logical_apic_id_table[index]; } -static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) +static void avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) { bool flat; u32 *entry, new_entry; @@ -575,15 +561,13 @@ static int avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr) flat = kvm_lapic_get_reg(vcpu->arch.apic, APIC_DFR) == APIC_DFR_FLAT; entry = avic_get_logical_id_entry(vcpu, ldr, flat); if (!entry) - return -EINVAL; + return; new_entry = READ_ONCE(*entry); new_entry &= ~AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK; new_entry |= (g_physical_id & AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK); new_entry |= AVIC_LOGICAL_ID_ENTRY_VALID_MASK; WRITE_ONCE(*entry, new_entry); - - return 0; } static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) @@ -601,29 +585,23 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu) clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry); } -static int avic_handle_ldr_update(struct kvm_vcpu *vcpu) +static void avic_handle_ldr_update(struct kvm_vcpu *vcpu) { - int ret = 0; struct vcpu_svm *svm = to_svm(vcpu); u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR); u32 id = kvm_xapic_id(vcpu->arch.apic); /* AVIC does not support LDR update for x2APIC */ if (apic_x2apic_mode(vcpu->arch.apic)) - return 0; + return; if (ldr == svm->ldr_reg) - return 0; + return; avic_invalidate_logical_id_entry(vcpu); - if (ldr) - ret = avic_ldr_write(vcpu, id, ldr); - - if (!ret) - svm->ldr_reg = ldr; - - return ret; + svm->ldr_reg = ldr; + avic_ldr_write(vcpu, id, ldr); } static void avic_handle_dfr_update(struct kvm_vcpu *vcpu) @@ -645,12 +623,14 @@ static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu) switch (offset) { case APIC_LDR: - if (avic_handle_ldr_update(vcpu)) - return 0; + avic_handle_ldr_update(vcpu); break; case APIC_DFR: avic_handle_dfr_update(vcpu); break; + case APIC_RRR: + /* Ignore writes to Read Remote Data, it's read-only. */ + return 1; default: break; } @@ -739,18 +719,6 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu) avic_handle_ldr_update(vcpu); } -void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu) -{ - if (!lapic_in_kernel(vcpu) || avic_mode == AVIC_MODE_NONE) - return; - - if (kvm_get_apic_mode(vcpu) == LAPIC_MODE_INVALID) { - WARN_ONCE(true, "Invalid local APIC state (vcpu_id=%d)", vcpu->vcpu_id); - return; - } - avic_refresh_apicv_exec_ctrl(vcpu); -} - static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) { int ret = 0; @@ -995,23 +963,6 @@ out: return ret; } -bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) -{ - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_ABSENT) | - BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_NESTED) | - BIT(APICV_INHIBIT_REASON_IRQWIN) | - BIT(APICV_INHIBIT_REASON_PIT_REINJ) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | - BIT(APICV_INHIBIT_REASON_SEV) | - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); - - return supported & BIT(reason); -} - - static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r) { @@ -1064,6 +1015,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) return; entry = READ_ONCE(*(svm->avic_physical_id_cache)); + WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK); entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK; entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK); @@ -1092,17 +1044,15 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu) WRITE_ONCE(*(svm->avic_physical_id_cache), entry); } - -void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb01.ptr; - bool activated = kvm_vcpu_apicv_active(vcpu); - if (!enable_apicv) + if (!lapic_in_kernel(vcpu) || !enable_apicv) return; - if (activated) { + if (kvm_vcpu_apicv_active(vcpu)) { /** * During AVIC temporary deactivation, guest could update * APIC ID, DFR and LDR registers, which would not be trapped @@ -1116,6 +1066,16 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) avic_deactivate_vmcb(svm); } vmcb_mark_dirty(vmcb, VMCB_AVIC); +} + +void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ + bool activated = kvm_vcpu_apicv_active(vcpu); + + if (!enable_apicv) + return; + + avic_refresh_virtual_apic_mode(vcpu); if (activated) avic_vcpu_load(vcpu, vcpu->cpu); @@ -1160,37 +1120,37 @@ void avic_vcpu_unblocking(struct kvm_vcpu *vcpu) * - Hypervisor can support both xAVIC and x2AVIC in the same guest. * - The mode can be switched at run-time. */ -bool avic_hardware_setup(struct kvm_x86_ops *x86_ops) +bool avic_hardware_setup(void) { if (!npt_enabled) return false; + /* AVIC is a prerequisite for x2AVIC. */ + if (!boot_cpu_has(X86_FEATURE_AVIC) && !force_avic) { + if (boot_cpu_has(X86_FEATURE_X2AVIC)) { + pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled"); + pr_warn(FW_BUG "Try enable AVIC using force_avic option"); + } + return false; + } + if (boot_cpu_has(X86_FEATURE_AVIC)) { - avic_mode = AVIC_MODE_X1; pr_info("AVIC enabled\n"); } else if (force_avic) { /* * Some older systems does not advertise AVIC support. * See Revision Guide for specific AMD processor for more detail. */ - avic_mode = AVIC_MODE_X1; pr_warn("AVIC is not supported in CPUID but force enabled"); pr_warn("Your system might crash and burn"); } /* AVIC is a prerequisite for x2AVIC. */ - if (boot_cpu_has(X86_FEATURE_X2AVIC)) { - if (avic_mode == AVIC_MODE_X1) { - avic_mode = AVIC_MODE_X2; - pr_info("x2AVIC enabled\n"); - } else { - pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled"); - pr_warn(FW_BUG "Try enable AVIC using force_avic option"); - } - } + x2avic_enabled = boot_cpu_has(X86_FEATURE_X2AVIC); + if (x2avic_enabled) + pr_info("x2AVIC enabled\n"); - if (avic_mode != AVIC_MODE_NONE) - amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); - return !!avic_mode; + return true; } diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index bc9cd7086fa9..05d38944a6c0 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -12,7 +12,7 @@ * Avi Kivity <avi@qumranet.com> */ -#define pr_fmt(fmt) "SVM: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_types.h> #include <linux/kvm_host.h> @@ -138,15 +138,13 @@ void recalc_intercepts(struct vcpu_svm *svm) c->intercepts[i] = h->intercepts[i]; if (g->int_ctl & V_INTR_MASKING_MASK) { - /* We only want the cr8 intercept bits of L1 */ - vmcb_clr_intercept(c, INTERCEPT_CR8_READ); - vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE); - /* - * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not - * affect any interrupt we may want to inject; therefore, - * interrupt window vmexits are irrelevant to L0. + * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8 + * does not affect any interrupt we may want to inject; + * therefore, writes to CR8 are irrelevant to L0, as are + * interrupt window vmexits. */ + vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE); vmcb_clr_intercept(c, INTERCEPT_VINTR); } @@ -1010,7 +1008,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb12->control.next_rip = vmcb02->control.next_rip; vmcb12->control.int_ctl = svm->nested.ctl.int_ctl; - vmcb12->control.tlb_ctl = svm->nested.ctl.tlb_ctl; vmcb12->control.event_inj = svm->nested.ctl.event_inj; vmcb12->control.event_inj_err = svm->nested.ctl.event_inj_err; @@ -1106,7 +1103,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) * to benefit from it right away. */ if (kvm_apicv_activated(vcpu->kvm)) - kvm_vcpu_update_apicv(vcpu); + __kvm_vcpu_update_apicv(vcpu); return 0; } diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 0e313fbae055..cc77a0681800 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -9,6 +9,8 @@ * * Implementation is based on pmu_intel.c file */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/types.h> #include <linux/kvm_host.h> #include <linux/perf_event.h> @@ -229,4 +231,6 @@ struct kvm_pmu_ops amd_pmu_ops __initdata = { .refresh = amd_pmu_refresh, .init = amd_pmu_init, .reset = amd_pmu_reset, + .EVENTSEL_EVENT = AMD64_EVENTSEL_EVENT, + .MAX_NR_GP_COUNTERS = KVM_AMD_PMC_MAX_GENERIC, }; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 86d6897f4806..c25aeb550cd9 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -6,6 +6,7 @@ * * Copyright 2010 Red Hat, Inc. and/or its affiliates. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_types.h> #include <linux/kvm_host.h> @@ -812,7 +813,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr, if (!IS_ALIGNED(dst_paddr, 16) || !IS_ALIGNED(paddr, 16) || !IS_ALIGNED(size, 16)) { - tpage = (void *)alloc_page(GFP_KERNEL | __GFP_ZERO); + tpage = (void *)alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!tpage) return -ENOMEM; @@ -1293,7 +1294,7 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Check if we are crossing the page boundary */ offset = params.guest_uaddr & (PAGE_SIZE - 1); - if ((params.guest_len + offset > PAGE_SIZE)) + if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE) return -EINVAL; /* Pin guest memory */ @@ -1473,7 +1474,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp) /* Check if we are crossing the page boundary */ offset = params.guest_uaddr & (PAGE_SIZE - 1); - if ((params.guest_len + offset > PAGE_SIZE)) + if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE) return -EINVAL; hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9a194aa1a75a..b43775490074 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1,4 +1,4 @@ -#define pr_fmt(fmt) "SVM: " fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> @@ -519,21 +519,37 @@ static void svm_init_osvw(struct kvm_vcpu *vcpu) vcpu->arch.osvw.status |= 1; } -static int has_svm(void) +static bool kvm_is_svm_supported(void) { + int cpu = raw_smp_processor_id(); const char *msg; + u64 vm_cr; if (!cpu_has_svm(&msg)) { - printk(KERN_INFO "has_svm: %s\n", msg); - return 0; + pr_err("SVM not supported by CPU %d, %s\n", cpu, msg); + return false; } if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) { pr_info("KVM is unsupported when running as an SEV guest\n"); - return 0; + return false; } - return 1; + rdmsrl(MSR_VM_CR, vm_cr); + if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) { + pr_err("SVM disabled (by BIOS) in MSR_VM_CR on CPU %d\n", cpu); + return false; + } + + return true; +} + +static int svm_check_processor_compat(void) +{ + if (!kvm_is_svm_supported()) + return -EIO; + + return 0; } void __svm_write_tsc_multiplier(u64 multiplier) @@ -572,10 +588,6 @@ static int svm_hardware_enable(void) if (efer & EFER_SVME) return -EBUSY; - if (!has_svm()) { - pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me); - return -EINVAL; - } sd = per_cpu_ptr(&svm_data, me); sd->asid_generation = 1; sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1; @@ -813,7 +825,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) if (intercept == svm->x2avic_msrs_intercepted) return; - if (avic_mode != AVIC_MODE_X2 || + if (!x2avic_enabled || !apic_x2apic_mode(svm->vcpu.arch.apic)) return; @@ -1326,6 +1338,9 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu) vcpu->arch.microcode_version = 0x01000065; svm->tsc_ratio_msr = kvm_caps.default_tsc_scaling_ratio; + svm->nmi_masked = false; + svm->awaiting_iret_completion = false; + if (sev_es_guest(vcpu->kvm)) sev_es_vcpu_reset(svm); } @@ -2076,7 +2091,7 @@ static void svm_handle_mce(struct kvm_vcpu *vcpu) * Erratum 383 triggered. Guest state is corrupt so kill the * guest. */ - pr_err("KVM: Guest triggered AMD Erratum 383\n"); + pr_err("Guest triggered AMD Erratum 383\n"); kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); @@ -2470,7 +2485,7 @@ static int iret_interception(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); ++vcpu->stat.nmi_window_exits; - vcpu->arch.hflags |= HF_IRET_MASK; + svm->awaiting_iret_completion = true; if (!sev_es_guest(vcpu->kvm)) { svm_clr_intercept(svm, INTERCEPT_IRET); svm->nmi_iret_rip = kvm_rip_read(vcpu); @@ -3003,8 +3018,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_IA32_DEBUGCTLMSR: if (!lbrv) { - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", - __func__, data); + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; } if (data & DEBUGCTL_RESERVED_BITS) @@ -3033,7 +3047,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: - vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); + kvm_pr_unimpl_wrmsr(vcpu, ecx, data); break; case MSR_AMD64_DE_CFG: { struct kvm_msr_entry msr_entry; @@ -3466,7 +3480,7 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) if (svm->nmi_l1_to_l2) return; - vcpu->arch.hflags |= HF_NMI_MASK; + svm->nmi_masked = true; if (!sev_es_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_IRET); ++vcpu->stat.nmi_injections; @@ -3571,7 +3585,6 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb *vmcb = svm->vmcb; - bool ret; if (!gif_set(svm)) return true; @@ -3579,10 +3592,8 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) return false; - ret = (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || - (vcpu->arch.hflags & HF_NMI_MASK); - - return ret; + return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || + svm->nmi_masked; } static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) @@ -3602,7 +3613,7 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) { - return !!(vcpu->arch.hflags & HF_NMI_MASK); + return to_svm(vcpu)->nmi_masked; } static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) @@ -3610,11 +3621,11 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) struct vcpu_svm *svm = to_svm(vcpu); if (masked) { - vcpu->arch.hflags |= HF_NMI_MASK; + svm->nmi_masked = true; if (!sev_es_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_IRET); } else { - vcpu->arch.hflags &= ~HF_NMI_MASK; + svm->nmi_masked = false; if (!sev_es_guest(vcpu->kvm)) svm_clr_intercept(svm, INTERCEPT_IRET); } @@ -3700,7 +3711,7 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if ((vcpu->arch.hflags & (HF_NMI_MASK | HF_IRET_MASK)) == HF_NMI_MASK) + if (svm->nmi_masked && !svm->awaiting_iret_completion) return; /* IRET will cause a vm exit */ if (!gif_set(svm)) { @@ -3824,10 +3835,11 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) * If we've made progress since setting HF_IRET_MASK, we've * executed an IRET and can allow NMI injection. */ - if ((vcpu->arch.hflags & HF_IRET_MASK) && + if (svm->awaiting_iret_completion && (sev_es_guest(vcpu->kvm) || kvm_rip_read(vcpu) != svm->nmi_iret_rip)) { - vcpu->arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); + svm->awaiting_iret_completion = false; + svm->nmi_masked = false; kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -4076,17 +4088,6 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, vmcb_mark_dirty(svm->vmcb, VMCB_CR); } -static int is_disabled(void) -{ - u64 vm_cr; - - rdmsrl(MSR_VM_CR, vm_cr); - if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) - return 1; - - return 0; -} - static void svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) { @@ -4098,11 +4099,6 @@ svm_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall) hypercall[2] = 0xd9; } -static int __init svm_check_processor_compat(void) -{ - return 0; -} - /* * The kvm parameter can be NULL (module initialization, or invocation before * VM creation). Be sure to check the kvm parameter before using it. @@ -4629,7 +4625,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, smap = cr4 & X86_CR4_SMAP; is_user = svm_get_cpl(vcpu) == 3; if (smap && (!smep || is_user)) { - pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n"); + pr_err_ratelimited("SEV Guest triggered AMD Erratum 1096\n"); /* * If the fault occurred in userspace, arbitrarily inject #GP @@ -4701,7 +4697,9 @@ static int svm_vm_init(struct kvm *kvm) } static struct kvm_x86_ops svm_x86_ops __initdata = { - .name = "kvm_amd", + .name = KBUILD_MODNAME, + + .check_processor_compatibility = svm_check_processor_compat, .hardware_unsetup = svm_hardware_unsetup, .hardware_enable = svm_hardware_enable, @@ -4771,10 +4769,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .enable_nmi_window = svm_enable_nmi_window, .enable_irq_window = svm_enable_irq_window, .update_cr8_intercept = svm_update_cr8_intercept, - .set_virtual_apic_mode = avic_set_virtual_apic_mode, + .set_virtual_apic_mode = avic_refresh_virtual_apic_mode, .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl, - .check_apicv_inhibit_reasons = avic_check_apicv_inhibit_reasons, .apicv_post_state_restore = avic_apicv_post_state_restore, + .required_apicv_inhibits = AVIC_REQUIRED_APICV_INHIBITS, .get_exit_info = svm_get_exit_info, @@ -4978,7 +4976,7 @@ static __init int svm_hardware_setup(void) } if (nested) { - printk(KERN_INFO "kvm: Nested Virtualization enabled\n"); + pr_info("Nested Virtualization enabled\n"); kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); } @@ -4996,7 +4994,7 @@ static __init int svm_hardware_setup(void) /* Force VM NPT level equal to the host's paging level */ kvm_configure_mmu(npt_enabled, get_npt_level(), get_npt_level(), PG_LEVEL_1G); - pr_info("kvm: Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); + pr_info("Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); /* Setup shadow_me_value and shadow_me_mask */ kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask); @@ -5022,12 +5020,14 @@ static __init int svm_hardware_setup(void) nrips = false; } - enable_apicv = avic = avic && avic_hardware_setup(&svm_x86_ops); + enable_apicv = avic = avic && avic_hardware_setup(); if (!enable_apicv) { svm_x86_ops.vcpu_blocking = NULL; svm_x86_ops.vcpu_unblocking = NULL; svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL; + } else if (!x2avic_enabled) { + svm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization = true; } if (vls) { @@ -5086,10 +5086,7 @@ err: static struct kvm_x86_init_ops svm_init_ops __initdata = { - .cpu_has_kvm_support = has_svm, - .disabled_by_bios = is_disabled, .hardware_setup = svm_hardware_setup, - .check_processor_compatibility = svm_check_processor_compat, .runtime_ops = &svm_x86_ops, .pmu_ops = &amd_pmu_ops, @@ -5097,15 +5094,37 @@ static struct kvm_x86_init_ops svm_init_ops __initdata = { static int __init svm_init(void) { + int r; + __unused_size_checks(); - return kvm_init(&svm_init_ops, sizeof(struct vcpu_svm), - __alignof__(struct vcpu_svm), THIS_MODULE); + if (!kvm_is_svm_supported()) + return -EOPNOTSUPP; + + r = kvm_x86_vendor_init(&svm_init_ops); + if (r) + return r; + + /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(sizeof(struct vcpu_svm), __alignof__(struct vcpu_svm), + THIS_MODULE); + if (r) + goto err_kvm_init; + + return 0; + +err_kvm_init: + kvm_x86_vendor_exit(); + return r; } static void __exit svm_exit(void) { kvm_exit(); + kvm_x86_vendor_exit(); } module_init(svm_init) diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 4826e6cc611b..839809972da1 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -35,14 +35,7 @@ extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; extern int vgif; extern bool intercept_smi; - -enum avic_modes { - AVIC_MODE_NONE = 0, - AVIC_MODE_X1, - AVIC_MODE_X2, -}; - -extern enum avic_modes avic_mode; +extern bool x2avic_enabled; /* * Clean bits in VMCB. @@ -237,8 +230,26 @@ struct vcpu_svm { struct svm_nested_state nested; + /* NMI mask value, used when vNMI is not enabled */ + bool nmi_masked; + + /* + * True when NMIs are still masked but guest IRET was just intercepted + * and KVM is waiting for RIP to change, which will signal that the + * intercepted IRET was retired and thus NMI can be unmasked. + */ + bool awaiting_iret_completion; + + /* + * Set when KVM is awaiting IRET completion and needs to inject NMIs as + * soon as the IRET completes (e.g. NMI is pending injection). KVM + * temporarily steals RFLAGS.TF to single-step the guest in this case + * in order to regain control as soon as the NMI-blocking condition + * goes away. + */ bool nmi_singlestep; u64 nmi_singlestep_guest_rflags; + bool nmi_l1_to_l2; unsigned long soft_int_csbase; @@ -280,6 +291,9 @@ struct vcpu_svm { bool guest_state_loaded; bool x2avic_msrs_intercepted; + + /* Guest GIF value, used when vGIF is not enabled */ + bool guest_gif; }; struct svm_cpu_data { @@ -497,7 +511,7 @@ static inline void enable_gif(struct vcpu_svm *svm) if (vmcb) vmcb->control.int_ctl |= V_GIF_MASK; else - svm->vcpu.arch.hflags |= HF_GIF_MASK; + svm->guest_gif = true; } static inline void disable_gif(struct vcpu_svm *svm) @@ -507,7 +521,7 @@ static inline void disable_gif(struct vcpu_svm *svm) if (vmcb) vmcb->control.int_ctl &= ~V_GIF_MASK; else - svm->vcpu.arch.hflags &= ~HF_GIF_MASK; + svm->guest_gif = false; } static inline bool gif_set(struct vcpu_svm *svm) @@ -517,7 +531,7 @@ static inline bool gif_set(struct vcpu_svm *svm) if (vmcb) return !!(vmcb->control.int_ctl & V_GIF_MASK); else - return !!(svm->vcpu.arch.hflags & HF_GIF_MASK); + return svm->guest_gif; } static inline bool nested_npt_enabled(struct vcpu_svm *svm) @@ -628,8 +642,23 @@ void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb); extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ - -bool avic_hardware_setup(struct kvm_x86_ops *ops); +#define AVIC_REQUIRED_APICV_INHIBITS \ +( \ + BIT(APICV_INHIBIT_REASON_DISABLE) | \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_NESTED) | \ + BIT(APICV_INHIBIT_REASON_IRQWIN) | \ + BIT(APICV_INHIBIT_REASON_PIT_REINJ) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_SEV) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED) \ +) + +bool avic_hardware_setup(void); int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); @@ -641,14 +670,13 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu); void avic_vcpu_put(struct kvm_vcpu *vcpu); void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu); void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu); -bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason); int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); void avic_ring_doorbell(struct kvm_vcpu *vcpu); unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu); -void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu); +void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu); /* sev.c */ diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 26a89d0da93e..7af8422d3382 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -2,6 +2,7 @@ /* * KVM L1 hypervisor optimizations on Hyper-V for SVM. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index 45faf84476ce..6981c1e9a809 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -34,7 +34,7 @@ static inline void svm_hv_hardware_setup(void) { if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) { - pr_info("kvm: Hyper-V enlightened NPT TLB flush enabled\n"); + pr_info(KBUILD_MODNAME ": Hyper-V enlightened NPT TLB flush enabled\n"); svm_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; svm_x86_ops.tlb_remote_flush_with_range = hv_remote_flush_tlb_with_range; @@ -43,7 +43,7 @@ static inline void svm_hv_hardware_setup(void) if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) { int cpu; - pr_info("kvm: Hyper-V Direct TLB Flush enabled\n"); + pr_info(KBUILD_MODNAME ": Hyper-V Direct TLB Flush enabled\n"); for_each_online_cpu(cpu) { struct hv_vp_assist_page *vp_ap = hv_get_vp_assist_page(cpu); diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index cd2ac9536c99..45162c1bcd8f 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -66,13 +66,13 @@ struct vmcs_config { u64 misc; struct nested_vmx_msrs nested; }; -extern struct vmcs_config vmcs_config; +extern struct vmcs_config vmcs_config __ro_after_init; struct vmx_capability { u32 ept; u32 vpid; }; -extern struct vmx_capability vmx_capability; +extern struct vmx_capability vmx_capability __ro_after_init; static inline bool cpu_has_vmx_basic_inout(void) { diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index ae03d1fe0355..22daca752797 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/errno.h> #include <linux/smp.h> @@ -361,35 +362,43 @@ enum evmcs_revision { enum evmcs_ctrl_type { EVMCS_EXIT_CTRLS, EVMCS_ENTRY_CTRLS, + EVMCS_EXEC_CTRL, EVMCS_2NDEXEC, + EVMCS_3RDEXEC, EVMCS_PINCTRL, EVMCS_VMFUNC, NR_EVMCS_CTRLS, }; -static const u32 evmcs_unsupported_ctrls[NR_EVMCS_CTRLS][NR_EVMCS_REVISIONS] = { +static const u32 evmcs_supported_ctrls[NR_EVMCS_CTRLS][NR_EVMCS_REVISIONS] = { [EVMCS_EXIT_CTRLS] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMEXIT_CTRL, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_VMEXIT_CTRL, }, [EVMCS_ENTRY_CTRLS] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMENTRY_CTRL, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_VMENTRY_CTRL, + }, + [EVMCS_EXEC_CTRL] = { + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_EXEC_CTRL, }, [EVMCS_2NDEXEC] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_2NDEXEC, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_2NDEXEC & ~SECONDARY_EXEC_TSC_SCALING, + }, + [EVMCS_3RDEXEC] = { + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_3RDEXEC, }, [EVMCS_PINCTRL] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_PINCTRL, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_PINCTRL, }, [EVMCS_VMFUNC] = { - [EVMCSv1_LEGACY] = EVMCS1_UNSUPPORTED_VMFUNC, + [EVMCSv1_LEGACY] = EVMCS1_SUPPORTED_VMFUNC, }, }; -static u32 evmcs_get_unsupported_ctls(enum evmcs_ctrl_type ctrl_type) +static u32 evmcs_get_supported_ctls(enum evmcs_ctrl_type ctrl_type) { enum evmcs_revision evmcs_rev = EVMCSv1_LEGACY; - return evmcs_unsupported_ctrls[ctrl_type][evmcs_rev]; + return evmcs_supported_ctrls[ctrl_type][evmcs_rev]; } static bool evmcs_has_perf_global_ctrl(struct kvm_vcpu *vcpu) @@ -413,7 +422,7 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * { u32 ctl_low = (u32)*pdata; u32 ctl_high = (u32)(*pdata >> 32); - u32 unsupported_ctrls; + u32 supported_ctrls; /* * Hyper-V 2016 and 2019 try using these features even when eVMCS @@ -422,27 +431,31 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * switch (msr_index) { case MSR_IA32_VMX_EXIT_CTLS: case MSR_IA32_VMX_TRUE_EXIT_CTLS: - unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_EXIT_CTRLS); + supported_ctrls = evmcs_get_supported_ctls(EVMCS_EXIT_CTRLS); if (!evmcs_has_perf_global_ctrl(vcpu)) - unsupported_ctrls |= VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; - ctl_high &= ~unsupported_ctrls; + supported_ctrls &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= supported_ctrls; break; case MSR_IA32_VMX_ENTRY_CTLS: case MSR_IA32_VMX_TRUE_ENTRY_CTLS: - unsupported_ctrls = evmcs_get_unsupported_ctls(EVMCS_ENTRY_CTRLS); + supported_ctrls = evmcs_get_supported_ctls(EVMCS_ENTRY_CTRLS); if (!evmcs_has_perf_global_ctrl(vcpu)) - unsupported_ctrls |= VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; - ctl_high &= ~unsupported_ctrls; + supported_ctrls &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL; + ctl_high &= supported_ctrls; + break; + case MSR_IA32_VMX_PROCBASED_CTLS: + case MSR_IA32_VMX_TRUE_PROCBASED_CTLS: + ctl_high &= evmcs_get_supported_ctls(EVMCS_EXEC_CTRL); break; case MSR_IA32_VMX_PROCBASED_CTLS2: - ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_2NDEXEC); + ctl_high &= evmcs_get_supported_ctls(EVMCS_2NDEXEC); break; case MSR_IA32_VMX_TRUE_PINBASED_CTLS: case MSR_IA32_VMX_PINBASED_CTLS: - ctl_high &= ~evmcs_get_unsupported_ctls(EVMCS_PINCTRL); + ctl_high &= evmcs_get_supported_ctls(EVMCS_PINCTRL); break; case MSR_IA32_VMX_VMFUNC: - ctl_low &= ~evmcs_get_unsupported_ctls(EVMCS_VMFUNC); + ctl_low &= evmcs_get_supported_ctls(EVMCS_VMFUNC); break; } @@ -452,7 +465,7 @@ void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 * static bool nested_evmcs_is_valid_controls(enum evmcs_ctrl_type ctrl_type, u32 val) { - return !(val & evmcs_get_unsupported_ctls(ctrl_type)); + return !(val & ~evmcs_get_supported_ctls(ctrl_type)); } int nested_evmcs_check_controls(struct vmcs12 *vmcs12) @@ -461,6 +474,10 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) vmcs12->pin_based_vm_exec_control))) return -EINVAL; + if (CC(!nested_evmcs_is_valid_controls(EVMCS_EXEC_CTRL, + vmcs12->cpu_based_vm_exec_control))) + return -EINVAL; + if (CC(!nested_evmcs_is_valid_controls(EVMCS_2NDEXEC, vmcs12->secondary_vm_exec_control))) return -EINVAL; @@ -488,6 +505,38 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) return 0; } +#if IS_ENABLED(CONFIG_HYPERV) +/* + * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption + * is: in case a feature has corresponding fields in eVMCS described and it was + * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a + * feature which has no corresponding eVMCS field, this likely means that KVM + * needs to be updated. + */ +#define evmcs_check_vmcs_conf(field, ctrl) \ + do { \ + typeof(vmcs_conf->field) unsupported; \ + \ + unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ + if (unsupported) { \ + pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ + (u64)unsupported); \ + vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ + } \ + } \ + while (0) + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) +{ + evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); + evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); + evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); + evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); + evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); + evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); +} +#endif + int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 571e7929d14e..78d17667e7ec 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -48,22 +48,84 @@ DECLARE_STATIC_KEY_FALSE(enable_evmcs); * Currently unsupported in KVM: * GUEST_IA32_RTIT_CTL = 0x00002814, */ -#define EVMCS1_UNSUPPORTED_PINCTRL (PIN_BASED_POSTED_INTR | \ - PIN_BASED_VMX_PREEMPTION_TIMER) -#define EVMCS1_UNSUPPORTED_EXEC_CTRL (CPU_BASED_ACTIVATE_TERTIARY_CONTROLS) -#define EVMCS1_UNSUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | \ - SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | \ - SECONDARY_EXEC_APIC_REGISTER_VIRT | \ - SECONDARY_EXEC_ENABLE_PML | \ - SECONDARY_EXEC_ENABLE_VMFUNC | \ - SECONDARY_EXEC_SHADOW_VMCS | \ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_PAUSE_LOOP_EXITING) -#define EVMCS1_UNSUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_SAVE_VMX_PREEMPTION_TIMER) -#define EVMCS1_UNSUPPORTED_VMENTRY_CTRL (0) -#define EVMCS1_UNSUPPORTED_VMFUNC (VMX_VMFUNC_EPTP_SWITCHING) + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) struct evmcs_field { u16 offset; @@ -117,9 +179,7 @@ static __always_inline int get_evmcs_offset(unsigned long field, { int offset = evmcs_field_offset(field, clean_field); - WARN_ONCE(offset < 0, "KVM: accessing unsupported EVMCS field %lx\n", - field); - + WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); return offset; } @@ -136,7 +196,7 @@ static __always_inline void evmcs_write64(unsigned long field, u64 value) current_evmcs->hv_clean_fields &= ~clean_field; } -static inline void evmcs_write32(unsigned long field, u32 value) +static __always_inline void evmcs_write32(unsigned long field, u32 value) { u16 clean_field; int offset = get_evmcs_offset(field, &clean_field); @@ -148,7 +208,7 @@ static inline void evmcs_write32(unsigned long field, u32 value) current_evmcs->hv_clean_fields &= ~clean_field; } -static inline void evmcs_write16(unsigned long field, u16 value) +static __always_inline void evmcs_write16(unsigned long field, u16 value) { u16 clean_field; int offset = get_evmcs_offset(field, &clean_field); @@ -160,7 +220,7 @@ static inline void evmcs_write16(unsigned long field, u16 value) current_evmcs->hv_clean_fields &= ~clean_field; } -static inline u64 evmcs_read64(unsigned long field) +static __always_inline u64 evmcs_read64(unsigned long field) { int offset = get_evmcs_offset(field, NULL); @@ -170,7 +230,7 @@ static inline u64 evmcs_read64(unsigned long field) return *(u64 *)((char *)current_evmcs + offset); } -static inline u32 evmcs_read32(unsigned long field) +static __always_inline u32 evmcs_read32(unsigned long field) { int offset = get_evmcs_offset(field, NULL); @@ -180,7 +240,7 @@ static inline u32 evmcs_read32(unsigned long field) return *(u32 *)((char *)current_evmcs + offset); } -static inline u16 evmcs_read16(unsigned long field) +static __always_inline u16 evmcs_read16(unsigned long field) { int offset = get_evmcs_offset(field, NULL); @@ -190,16 +250,6 @@ static inline u16 evmcs_read16(unsigned long field) return *(u16 *)((char *)current_evmcs + offset); } -static inline void evmcs_touch_msr_bitmap(void) -{ - if (unlikely(!current_evmcs)) - return; - - if (current_evmcs->hv_enlightenments_control.msr_bitmap) - current_evmcs->hv_clean_fields &= - ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; -} - static inline void evmcs_load(u64 phys_addr) { struct hv_vp_assist_page *vp_ap = @@ -211,15 +261,15 @@ static inline void evmcs_load(u64 phys_addr) vp_ap->enlighten_vmentry = 1; } +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); #else /* !IS_ENABLED(CONFIG_HYPERV) */ static __always_inline void evmcs_write64(unsigned long field, u64 value) {} -static inline void evmcs_write32(unsigned long field, u32 value) {} -static inline void evmcs_write16(unsigned long field, u16 value) {} -static inline u64 evmcs_read64(unsigned long field) { return 0; } -static inline u32 evmcs_read32(unsigned long field) { return 0; } -static inline u16 evmcs_read16(unsigned long field) { return 0; } +static __always_inline void evmcs_write32(unsigned long field, u32 value) {} +static __always_inline void evmcs_write16(unsigned long field, u16 value) {} +static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } +static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } +static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } static inline void evmcs_load(u64 phys_addr) {} -static inline void evmcs_touch_msr_bitmap(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ #define EVMPTR_INVALID (-1ULL) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d93c715cda6a..7c4f5ca405c7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/objtool.h> #include <linux/percpu.h> @@ -203,7 +204,7 @@ static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator) { /* TODO: not to reset guest simply here. */ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); - pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator); + pr_debug_ratelimited("nested vmx abort, indicator %d\n", indicator); } static inline bool vmx_control_verify(u32 control, u32 low, u32 high) @@ -5863,11 +5864,10 @@ static int handle_vmfunc(struct kvm_vcpu *vcpu) u32 function = kvm_rax_read(vcpu); /* - * VMFUNC is only supported for nested guests, but we always enable the - * secondary control for simplicity; for non-nested mode, fake that we - * didn't by injecting #UD. + * VMFUNC should never execute cleanly while L1 is active; KVM supports + * VMFUNC for nested VMs, but not for L1. */ - if (!is_guest_mode(vcpu)) { + if (WARN_ON_ONCE(!is_guest_mode(vcpu))) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -6880,6 +6880,7 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | SECONDARY_EXEC_RDRAND_EXITING | SECONDARY_EXEC_ENABLE_INVPCID | + SECONDARY_EXEC_ENABLE_VMFUNC | SECONDARY_EXEC_RDSEED_EXITING | SECONDARY_EXEC_XSAVES | SECONDARY_EXEC_TSC_SCALING | @@ -6912,18 +6913,13 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) SECONDARY_EXEC_ENABLE_PML; msrs->ept_caps |= VMX_EPT_AD_BIT; } - } - if (cpu_has_vmx_vmfunc()) { - msrs->secondary_ctls_high |= - SECONDARY_EXEC_ENABLE_VMFUNC; /* - * Advertise EPTP switching unconditionally - * since we emulate it + * Advertise EPTP switching irrespective of hardware support, + * KVM emulates it in software so long as VMFUNC is supported. */ - if (enable_ept) - msrs->vmfunc_controls = - VMX_VMFUNC_EPTP_SWITCHING; + if (cpu_has_vmx_vmfunc()) + msrs->vmfunc_controls = VMX_VMFUNC_EPTP_SWITCHING; } /* diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index e5cec07ca8d9..e8a3be0b9df9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -8,6 +8,8 @@ * Avi Kivity <avi@redhat.com> * Gleb Natapov <gleb@redhat.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/types.h> #include <linux/kvm_host.h> #include <linux/perf_event.h> @@ -20,16 +22,19 @@ #define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) -static struct kvm_event_hw_type_mapping intel_arch_events[] = { - [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, - [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, - [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, - [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, - [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, - [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, - [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, +static struct { + u8 eventsel; + u8 unit_mask; +} const intel_arch_events[] = { + [0] = { 0x3c, 0x00 }, + [1] = { 0xc0, 0x00 }, + [2] = { 0x3c, 0x01 }, + [3] = { 0x2e, 0x4f }, + [4] = { 0x2e, 0x41 }, + [5] = { 0xc4, 0x00 }, + [6] = { 0xc5, 0x00 }, /* The above index must match CPUID 0x0A.EBX bit vector */ - [7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES }, + [7] = { 0x00, 0x03 }, }; /* mapping between fixed pmc index and intel_arch_events array */ @@ -762,8 +767,7 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu) return; warn: - pr_warn_ratelimited("kvm: vcpu-%d: fail to passthrough LBR.\n", - vcpu->vcpu_id); + pr_warn_ratelimited("vcpu-%d: fail to passthrough LBR.\n", vcpu->vcpu_id); } static void intel_pmu_cleanup(struct kvm_vcpu *vcpu) @@ -810,4 +814,6 @@ struct kvm_pmu_ops intel_pmu_ops __initdata = { .reset = intel_pmu_reset, .deliver_pmi = intel_pmu_deliver_pmi, .cleanup = intel_pmu_cleanup, + .EVENTSEL_EVENT = ARCH_PERFMON_EVENTSEL_EVENT, + .MAX_NR_GP_COUNTERS = KVM_INTEL_PMC_MAX_GENERIC, }; diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index 1b56c5e5c9fb..94c38bea60e7 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -1,4 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h> #include <asm/irq_remapping.h> diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index b12da2a6dec9..aa53c98034bf 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2021 Intel Corporation. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <asm/sgx.h> @@ -164,7 +165,7 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu, if (!vcpu->kvm->arch.sgx_provisioning_allowed && (attributes & SGX_ATTR_PROVISIONKEY)) { if (sgx_12_1->eax & SGX_ATTR_PROVISIONKEY) - pr_warn_once("KVM: SGX PROVISIONKEY advertised but not allowed\n"); + pr_warn_once("SGX PROVISIONKEY advertised but not allowed\n"); kvm_inject_gp(vcpu, 0); return 1; } @@ -381,7 +382,7 @@ int handle_encls(struct kvm_vcpu *vcpu) return handle_encls_ecreate(vcpu); if (leaf == EINIT) return handle_encls_einit(vcpu); - WARN(1, "KVM: unexpected exit on ENCLS[%u]", leaf); + WARN_ONCE(1, "unexpected exit on ENCLS[%u]", leaf); vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->run->hw.hardware_exit_reason = EXIT_REASON_ENCLS; return 0; diff --git a/arch/x86/kvm/vmx/vmcs.h b/arch/x86/kvm/vmx/vmcs.h index ac290a44a693..7c1996b433e2 100644 --- a/arch/x86/kvm/vmx/vmcs.h +++ b/arch/x86/kvm/vmx/vmcs.h @@ -75,7 +75,7 @@ struct loaded_vmcs { struct vmcs_controls_shadow controls_shadow; }; -static inline bool is_intr_type(u32 intr_info, u32 type) +static __always_inline bool is_intr_type(u32 intr_info, u32 type) { const u32 mask = INTR_INFO_VALID_MASK | INTR_INFO_INTR_TYPE_MASK; @@ -146,7 +146,7 @@ static inline bool is_icebp(u32 intr_info) return is_intr_type(intr_info, INTR_TYPE_PRIV_SW_EXCEPTION); } -static inline bool is_nmi(u32 intr_info) +static __always_inline bool is_nmi(u32 intr_info) { return is_intr_type(intr_info, INTR_TYPE_NMI_INTR); } diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c index 2251b60920f8..106a72c923ca 100644 --- a/arch/x86/kvm/vmx/vmcs12.c +++ b/arch/x86/kvm/vmx/vmcs12.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "vmcs12.h" diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 766c6b3ef5ed..f550540ed54e 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -31,6 +31,39 @@ #define VCPU_R15 __VCPU_REGS_R15 * WORD_SIZE #endif +.macro VMX_DO_EVENT_IRQOFF call_insn call_target + /* + * Unconditionally create a stack frame, getting the correct RSP on the + * stack (for x86-64) would take two instructions anyways, and RBP can + * be used to restore RSP to make objtool happy (see below). + */ + push %_ASM_BP + mov %_ASM_SP, %_ASM_BP + +#ifdef CONFIG_X86_64 + /* + * Align RSP to a 16-byte boundary (to emulate CPU behavior) before + * creating the synthetic interrupt stack frame for the IRQ/NMI. + */ + and $-16, %rsp + push $__KERNEL_DS + push %rbp +#endif + pushf + push $__KERNEL_CS + \call_insn \call_target + + /* + * "Restore" RSP from RBP, even though IRET has already unwound RSP to + * the correct value. objtool doesn't know the callee will IRET and, + * without the explicit restore, thinks the stack is getting walloped. + * Using an unwind hint is problematic due to x86-64's dynamic alignment. + */ + mov %_ASM_BP, %_ASM_SP + pop %_ASM_BP + RET +.endm + .section .noinstr.text, "ax" /** @@ -69,8 +102,8 @@ SYM_FUNC_START(__vmx_vcpu_run) */ push %_ASM_ARG2 - /* Copy @flags to BL, _ASM_ARG3 is volatile. */ - mov %_ASM_ARG3B, %bl + /* Copy @flags to EBX, _ASM_ARG3 is volatile. */ + mov %_ASM_ARG3L, %ebx lea (%_ASM_SP), %_ASM_ARG2 call vmx_update_host_rsp @@ -106,7 +139,7 @@ SYM_FUNC_START(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX /* Check if vmlaunch or vmresume is needed */ - testb $VMX_RUN_VMRESUME, %bl + test $VMX_RUN_VMRESUME, %ebx /* Load guest registers. Don't clobber flags. */ mov VCPU_RCX(%_ASM_AX), %_ASM_CX @@ -128,7 +161,7 @@ SYM_FUNC_START(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX - /* Check EFLAGS.ZF from 'testb' above */ + /* Check EFLAGS.ZF from 'test VMX_RUN_VMRESUME' above */ jz .Lvmlaunch /* @@ -266,6 +299,10 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL) SYM_FUNC_END(__vmx_vcpu_run) +SYM_FUNC_START(vmx_do_nmi_irqoff) + VMX_DO_EVENT_IRQOFF call asm_exc_nmi_kvm_vmx +SYM_FUNC_END(vmx_do_nmi_irqoff) + .section .text, "ax" @@ -320,35 +357,6 @@ SYM_FUNC_START(vmread_error_trampoline) SYM_FUNC_END(vmread_error_trampoline) #endif -SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff) - /* - * Unconditionally create a stack frame, getting the correct RSP on the - * stack (for x86-64) would take two instructions anyways, and RBP can - * be used to restore RSP to make objtool happy (see below). - */ - push %_ASM_BP - mov %_ASM_SP, %_ASM_BP - -#ifdef CONFIG_X86_64 - /* - * Align RSP to a 16-byte boundary (to emulate CPU behavior) before - * creating the synthetic interrupt stack frame for the IRQ/NMI. - */ - and $-16, %rsp - push $__KERNEL_DS - push %rbp -#endif - pushf - push $__KERNEL_CS - CALL_NOSPEC _ASM_ARG1 - - /* - * "Restore" RSP from RBP, even though IRET has already unwound RSP to - * the correct value. objtool doesn't know the callee will IRET and, - * without the explicit restore, thinks the stack is getting walloped. - * Using an unwind hint is problematic due to x86-64's dynamic alignment. - */ - mov %_ASM_BP, %_ASM_SP - pop %_ASM_BP - RET -SYM_FUNC_END(vmx_do_interrupt_nmi_irqoff) +SYM_FUNC_START(vmx_do_interrupt_irqoff) + VMX_DO_EVENT_IRQOFF CALL_NOSPEC _ASM_ARG1 +SYM_FUNC_END(vmx_do_interrupt_irqoff) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index fc9008dbed33..7896acf05117 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -12,6 +12,7 @@ * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/highmem.h> #include <linux/hrtimer.h> @@ -444,36 +445,36 @@ void vmread_error(unsigned long field, bool fault) if (fault) kvm_spurious_fault(); else - vmx_insn_failed("kvm: vmread failed: field=%lx\n", field); + vmx_insn_failed("vmread failed: field=%lx\n", field); } noinline void vmwrite_error(unsigned long field, unsigned long value) { - vmx_insn_failed("kvm: vmwrite failed: field=%lx val=%lx err=%u\n", + vmx_insn_failed("vmwrite failed: field=%lx val=%lx err=%u\n", field, value, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmclear_error(struct vmcs *vmcs, u64 phys_addr) { - vmx_insn_failed("kvm: vmclear failed: %p/%llx err=%u\n", + vmx_insn_failed("vmclear failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void vmptrld_error(struct vmcs *vmcs, u64 phys_addr) { - vmx_insn_failed("kvm: vmptrld failed: %p/%llx err=%u\n", + vmx_insn_failed("vmptrld failed: %p/%llx err=%u\n", vmcs, phys_addr, vmcs_read32(VM_INSTRUCTION_ERROR)); } noinline void invvpid_error(unsigned long ext, u16 vpid, gva_t gva) { - vmx_insn_failed("kvm: invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", + vmx_insn_failed("invvpid failed: ext=0x%lx vpid=%u gva=0x%lx\n", ext, vpid, gva); } noinline void invept_error(unsigned long ext, u64 eptp, gpa_t gpa) { - vmx_insn_failed("kvm: invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", + vmx_insn_failed("invept failed: ext=0x%lx eptp=%llx gpa=0x%llx\n", ext, eptp, gpa); } @@ -488,8 +489,8 @@ static DEFINE_PER_CPU(struct list_head, loaded_vmcss_on_cpu); static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS); static DEFINE_SPINLOCK(vmx_vpid_lock); -struct vmcs_config vmcs_config; -struct vmx_capability vmx_capability; +struct vmcs_config vmcs_config __ro_after_init; +struct vmx_capability vmx_capability __ro_after_init; #define VMX_SEGMENT_FIELD(seg) \ [VCPU_SREG_##seg] = { \ @@ -523,6 +524,8 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx) static unsigned long host_idt_base; #if IS_ENABLED(CONFIG_HYPERV) +static struct kvm_x86_ops vmx_x86_ops __initdata; + static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); @@ -551,6 +554,71 @@ static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) return 0; } +static __init void hv_init_evmcs(void) +{ + int cpu; + + if (!enlightened_vmcs) + return; + + /* + * Enlightened VMCS usage should be recommended and the host needs + * to support eVMCS v1 or above. + */ + if (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && + (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= + KVM_EVMCS_VERSION) { + + /* Check that we have assist pages on all online CPUs */ + for_each_online_cpu(cpu) { + if (!hv_get_vp_assist_page(cpu)) { + enlightened_vmcs = false; + break; + } + } + + if (enlightened_vmcs) { + pr_info("Using Hyper-V Enlightened VMCS\n"); + static_branch_enable(&enable_evmcs); + } + + if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) + vmx_x86_ops.enable_l2_tlb_flush + = hv_enable_l2_tlb_flush; + + } else { + enlightened_vmcs = false; + } +} + +static void hv_reset_evmcs(void) +{ + struct hv_vp_assist_page *vp_ap; + + if (!static_branch_unlikely(&enable_evmcs)) + return; + + /* + * KVM should enable eVMCS if and only if all CPUs have a VP assist + * page, and should reject CPU onlining if eVMCS is enabled the CPU + * doesn't have a VP assist page allocated. + */ + vp_ap = hv_get_vp_assist_page(smp_processor_id()); + if (WARN_ON_ONCE(!vp_ap)) + return; + + /* + * Reset everything to support using non-enlightened VMCS access later + * (e.g. when we reload the module with enlightened_vmcs=0) + */ + vp_ap->nested_control.features.directhypercall = 0; + vp_ap->current_nested_vmcs = 0; + vp_ap->enlighten_vmentry = 0; +} + +#else /* IS_ENABLED(CONFIG_HYPERV) */ +static void hv_init_evmcs(void) {} +static void hv_reset_evmcs(void) {} #endif /* IS_ENABLED(CONFIG_HYPERV) */ /* @@ -1613,8 +1681,8 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) if (!instr_len) goto rip_updated; - WARN(exit_reason.enclave_mode, - "KVM: skipping instruction after SGX enclave VM-Exit"); + WARN_ONCE(exit_reason.enclave_mode, + "skipping instruction after SGX enclave VM-Exit"); orig_rip = kvm_rip_read(vcpu); rip = orig_rip + instr_len; @@ -2138,9 +2206,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated); if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) { - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); + kvm_pr_unimpl_wrmsr(vcpu, msr_index, data); data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR); } @@ -2448,88 +2514,6 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) } } -static __init int cpu_has_kvm_support(void) -{ - return cpu_has_vmx(); -} - -static __init int vmx_disabled_by_bios(void) -{ - return !boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || - !boot_cpu_has(X86_FEATURE_VMX); -} - -static int kvm_cpu_vmxon(u64 vmxon_pointer) -{ - u64 msr; - - cr4_set_bits(X86_CR4_VMXE); - - asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" - _ASM_EXTABLE(1b, %l[fault]) - : : [vmxon_pointer] "m"(vmxon_pointer) - : : fault); - return 0; - -fault: - WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", - rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); - cr4_clear_bits(X86_CR4_VMXE); - - return -EFAULT; -} - -static int vmx_hardware_enable(void) -{ - int cpu = raw_smp_processor_id(); - u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); - int r; - - if (cr4_read_shadow() & X86_CR4_VMXE) - return -EBUSY; - - /* - * This can happen if we hot-added a CPU but failed to allocate - * VP assist page for it. - */ - if (static_branch_unlikely(&enable_evmcs) && - !hv_get_vp_assist_page(cpu)) - return -EFAULT; - - intel_pt_handle_vmx(1); - - r = kvm_cpu_vmxon(phys_addr); - if (r) { - intel_pt_handle_vmx(0); - return r; - } - - if (enable_ept) - ept_sync_global(); - - return 0; -} - -static void vmclear_local_loaded_vmcss(void) -{ - int cpu = raw_smp_processor_id(); - struct loaded_vmcs *v, *n; - - list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), - loaded_vmcss_on_cpu_link) - __loaded_vmcs_clear(v); -} - -static void vmx_hardware_disable(void) -{ - vmclear_local_loaded_vmcss(); - - if (cpu_vmxoff()) - kvm_spurious_fault(); - - intel_pt_handle_vmx(0); -} - /* * There is no X86_FEATURE for SGX yet, but anyway we need to query CPUID * directly instead of going through cpu_has(), to ensure KVM is trapping @@ -2565,8 +2549,7 @@ static bool cpu_has_perf_global_ctrl_bug(void) return false; } -static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, - u32 msr, u32 *result) +static int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, u32 msr, u32 *result) { u32 vmx_msr_low, vmx_msr_high; u32 ctl = ctl_min | ctl_opt; @@ -2584,7 +2567,7 @@ static __init int adjust_vmx_controls(u32 ctl_min, u32 ctl_opt, return 0; } -static __init u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) +static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) { u64 allowed; @@ -2593,8 +2576,8 @@ static __init u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr) return ctl_opt & allowed; } -static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, - struct vmx_capability *vmx_cap) +static int setup_vmcs_config(struct vmcs_config *vmcs_conf, + struct vmx_capability *vmx_cap) { u32 vmx_msr_low, vmx_msr_high; u32 _pin_based_exec_control = 0; @@ -2752,9 +2735,127 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf, vmcs_conf->vmentry_ctrl = _vmentry_control; vmcs_conf->misc = misc_msr; +#if IS_ENABLED(CONFIG_HYPERV) + if (enlightened_vmcs) + evmcs_sanitize_exec_ctrls(vmcs_conf); +#endif + + return 0; +} + +static bool kvm_is_vmx_supported(void) +{ + int cpu = raw_smp_processor_id(); + + if (!cpu_has_vmx()) { + pr_err("VMX not supported by CPU %d\n", cpu); + return false; + } + + if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || + !this_cpu_has(X86_FEATURE_VMX)) { + pr_err("VMX not enabled (by BIOS) in MSR_IA32_FEAT_CTL on CPU %d\n", cpu); + return false; + } + + return true; +} + +static int vmx_check_processor_compat(void) +{ + int cpu = raw_smp_processor_id(); + struct vmcs_config vmcs_conf; + struct vmx_capability vmx_cap; + + if (!kvm_is_vmx_supported()) + return -EIO; + + if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) { + pr_err("Failed to setup VMCS config on CPU %d\n", cpu); + return -EIO; + } + if (nested) + nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); + if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config))) { + pr_err("Inconsistent VMCS config on CPU %d\n", cpu); + return -EIO; + } return 0; } +static int kvm_cpu_vmxon(u64 vmxon_pointer) +{ + u64 msr; + + cr4_set_bits(X86_CR4_VMXE); + + asm_volatile_goto("1: vmxon %[vmxon_pointer]\n\t" + _ASM_EXTABLE(1b, %l[fault]) + : : [vmxon_pointer] "m"(vmxon_pointer) + : : fault); + return 0; + +fault: + WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n", + rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr); + cr4_clear_bits(X86_CR4_VMXE); + + return -EFAULT; +} + +static int vmx_hardware_enable(void) +{ + int cpu = raw_smp_processor_id(); + u64 phys_addr = __pa(per_cpu(vmxarea, cpu)); + int r; + + if (cr4_read_shadow() & X86_CR4_VMXE) + return -EBUSY; + + /* + * This can happen if we hot-added a CPU but failed to allocate + * VP assist page for it. + */ + if (static_branch_unlikely(&enable_evmcs) && + !hv_get_vp_assist_page(cpu)) + return -EFAULT; + + intel_pt_handle_vmx(1); + + r = kvm_cpu_vmxon(phys_addr); + if (r) { + intel_pt_handle_vmx(0); + return r; + } + + if (enable_ept) + ept_sync_global(); + + return 0; +} + +static void vmclear_local_loaded_vmcss(void) +{ + int cpu = raw_smp_processor_id(); + struct loaded_vmcs *v, *n; + + list_for_each_entry_safe(v, n, &per_cpu(loaded_vmcss_on_cpu, cpu), + loaded_vmcss_on_cpu_link) + __loaded_vmcs_clear(v); +} + +static void vmx_hardware_disable(void) +{ + vmclear_local_loaded_vmcss(); + + if (cpu_vmxoff()) + kvm_spurious_fault(); + + hv_reset_evmcs(); + + intel_pt_handle_vmx(0); +} + struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) { int node = cpu_to_node(cpu); @@ -2950,9 +3051,8 @@ static void fix_rmode_seg(int seg, struct kvm_segment *save) var.type = 0x3; var.avl = 0; if (save->base & 0xf) - printk_once(KERN_WARNING "kvm: segment base is not " - "paragraph aligned when entering " - "protected mode (seg=%d)", seg); + pr_warn_once("segment base is not paragraph aligned " + "when entering protected mode (seg=%d)", seg); } vmcs_write16(sf->selector, var.selector); @@ -2982,8 +3082,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu) * vcpu. Warn the user that an update is overdue. */ if (!kvm_vmx->tss_addr) - printk_once(KERN_WARNING "kvm: KVM_SET_TSS_ADDR need to be " - "called before entering vcpu\n"); + pr_warn_once("KVM_SET_TSS_ADDR needs to be called before running vCPU\n"); vmx_segment_cache_clear(vmx); @@ -3440,18 +3539,15 @@ static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; - if (var->unusable || !var->present) - ar = 1 << 16; - else { - ar = var->type & 15; - ar |= (var->s & 1) << 4; - ar |= (var->dpl & 3) << 5; - ar |= (var->present & 1) << 7; - ar |= (var->avl & 1) << 12; - ar |= (var->l & 1) << 13; - ar |= (var->db & 1) << 14; - ar |= (var->g & 1) << 15; - } + ar = var->type & 15; + ar |= (var->s & 1) << 4; + ar |= (var->dpl & 3) << 5; + ar |= (var->present & 1) << 7; + ar |= (var->avl & 1) << 12; + ar |= (var->l & 1) << 13; + ar |= (var->db & 1) << 14; + ar |= (var->g & 1) << 15; + ar |= (var->unusable || !var->present) << 16; return ar; } @@ -3803,39 +3899,6 @@ static void seg_setup(int seg) vmcs_write32(sf->ar_bytes, ar); } -static int alloc_apic_access_page(struct kvm *kvm) -{ - struct page *page; - void __user *hva; - int ret = 0; - - mutex_lock(&kvm->slots_lock); - if (kvm->arch.apic_access_memslot_enabled) - goto out; - hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT, - APIC_DEFAULT_PHYS_BASE, PAGE_SIZE); - if (IS_ERR(hva)) { - ret = PTR_ERR(hva); - goto out; - } - - page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT); - if (is_error_page(page)) { - ret = -EFAULT; - goto out; - } - - /* - * Do not pin the page in memory, so that memory hot-unplug - * is able to migrate it. - */ - put_page(page); - kvm->arch.apic_access_memslot_enabled = true; -out: - mutex_unlock(&kvm->slots_lock); - return ret; -} - int allocate_vpid(void) { int vpid; @@ -3868,8 +3931,13 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR * bitmap has changed. */ - if (static_branch_unlikely(&enable_evmcs)) - evmcs_touch_msr_bitmap(); + if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs)) { + struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; + + if (evmcs->hv_enlightenments_control.msr_bitmap) + evmcs->hv_clean_fields &= + ~HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP; + } vmx->nested.force_msr_bitmap_recalc = true; } @@ -4522,6 +4590,12 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; + /* + * KVM doesn't support VMFUNC for L1, but the control is set in KVM's + * base configuration as KVM emulates VMFUNC[EPTP_SWITCHING] for L2. + */ + exec_control &= ~SECONDARY_EXEC_ENABLE_VMFUNC; + /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP, * in vmx_set_cr4. */ exec_control &= ~SECONDARY_EXEC_DESC; @@ -4538,7 +4612,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) * it needs to be set here when dirty logging is already active, e.g. * if this vCPU was created after dirty logging was enabled. */ - if (!vcpu->kvm->arch.cpu_dirty_logging_count) + if (!enable_pml || !atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) exec_control &= ~SECONDARY_EXEC_ENABLE_PML; if (cpu_has_vmx_xsaves()) { @@ -5102,8 +5176,13 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu) vect_info = vmx->idt_vectoring_info; intr_info = vmx_get_intr_info(vcpu); + /* + * Machine checks are handled by handle_exception_irqoff(), or by + * vmx_vcpu_run() if a #MC occurs on VM-Entry. NMIs are handled by + * vmx_vcpu_enter_exit(). + */ if (is_machine_check(intr_info) || is_nmi(intr_info)) - return 1; /* handled by handle_exception_nmi_irqoff() */ + return 1; /* * Queue the exception here instead of in handle_nm_fault_irqoff(). @@ -6793,17 +6872,8 @@ static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir)); } -void vmx_do_interrupt_nmi_irqoff(unsigned long entry); - -static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu, - unsigned long entry) -{ - bool is_nmi = entry == (unsigned long)asm_exc_nmi_noist; - - kvm_before_interrupt(vcpu, is_nmi ? KVM_HANDLING_NMI : KVM_HANDLING_IRQ); - vmx_do_interrupt_nmi_irqoff(entry); - kvm_after_interrupt(vcpu); -} +void vmx_do_interrupt_irqoff(unsigned long entry); +void vmx_do_nmi_irqoff(void); static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) { @@ -6825,9 +6895,8 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu) rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err); } -static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) +static void handle_exception_irqoff(struct vcpu_vmx *vmx) { - const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist; u32 intr_info = vmx_get_intr_info(&vmx->vcpu); /* if exit due to PF check for async PF */ @@ -6839,9 +6908,6 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx) /* Handle machine checks before interrupts are enabled */ else if (is_machine_check(intr_info)) kvm_machine_check(); - /* We need to handle NMIs before interrupts are enabled */ - else if (is_nmi(intr_info)) - handle_interrupt_nmi_irqoff(&vmx->vcpu, nmi_entry); } static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) @@ -6851,10 +6917,13 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) gate_desc *desc = (gate_desc *)host_idt_base + vector; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, - "KVM: unexpected VM-Exit interrupt info: 0x%x", intr_info)) + "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; - handle_interrupt_nmi_irqoff(vcpu, gate_offset(desc)); + kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); + vmx_do_interrupt_irqoff(gate_offset(desc)); + kvm_after_interrupt(vcpu); + vcpu->arch.at_instruction_boundary = true; } @@ -6868,7 +6937,7 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu) if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT) handle_external_interrupt_irqoff(vcpu); else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI) - handle_exception_nmi_irqoff(vmx); + handle_exception_irqoff(vmx); } /* @@ -7103,9 +7172,10 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) } static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, - struct vcpu_vmx *vmx, - unsigned long flags) + unsigned int flags) { + struct vcpu_vmx *vmx = to_vmx(vcpu); + guest_state_enter_irqoff(); /* L1D Flush includes CPU buffer clear to mitigate MDS */ @@ -7129,6 +7199,18 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, vmx_enable_fb_clear(vmx); + if (unlikely(vmx->fail)) + vmx->exit_reason.full = 0xdead; + else + vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); + + if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI && + is_nmi(vmx_get_intr_info(vcpu))) { + kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); + vmx_do_nmi_irqoff(); + kvm_after_interrupt(vcpu); + } + guest_state_exit_irqoff(); } @@ -7223,7 +7305,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) kvm_wait_lapic_expire(vcpu); /* The actual VMENTER/EXIT is in the .noinstr.text section. */ - vmx_vcpu_enter_exit(vcpu, vmx, __vmx_vcpu_run_flags(vmx)); + vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_run_flags(vmx)); /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) { @@ -7270,12 +7352,9 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx->idt_vectoring_info = 0; - if (unlikely(vmx->fail)) { - vmx->exit_reason.full = 0xdead; + if (unlikely(vmx->fail)) return EXIT_FASTPATH_NONE; - } - vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON); if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY)) kvm_machine_check(); @@ -7389,7 +7468,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) vmx->loaded_vmcs = &vmx->vmcs01; if (cpu_need_virtualize_apic_accesses(vcpu)) { - err = alloc_apic_access_page(vcpu->kvm); + err = kvm_alloc_apic_access_page(vcpu->kvm); if (err) goto free_vmcs; } @@ -7449,29 +7528,6 @@ static int vmx_vm_init(struct kvm *kvm) return 0; } -static int __init vmx_check_processor_compat(void) -{ - struct vmcs_config vmcs_conf; - struct vmx_capability vmx_cap; - - if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || - !this_cpu_has(X86_FEATURE_VMX)) { - pr_err("kvm: VMX is disabled on CPU %d\n", smp_processor_id()); - return -EIO; - } - - if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) - return -EIO; - if (nested) - nested_vmx_setup_ctls_msrs(&vmcs_conf, vmx_cap.ept); - if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) { - printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n", - smp_processor_id()); - return -EIO; - } - return 0; -} - static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { u8 cache; @@ -7943,17 +7999,20 @@ void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + if (WARN_ON_ONCE(!enable_pml)) + return; + if (is_guest_mode(vcpu)) { vmx->nested.update_vmcs01_cpu_dirty_logging = true; return; } /* - * Note, cpu_dirty_logging_count can be changed concurrent with this + * Note, nr_memslots_dirty_logging can be changed concurrent with this * code, but in that case another update request will be made and so * the guest will never run with a stale PML value. */ - if (vcpu->kvm->arch.cpu_dirty_logging_count) + if (atomic_read(&vcpu->kvm->nr_memslots_dirty_logging)) secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_ENABLE_PML); else secondary_exec_controls_clearbit(vmx, SECONDARY_EXEC_ENABLE_PML); @@ -8051,17 +8110,16 @@ static void vmx_hardware_unsetup(void) free_kvm_area(); } -static bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) -{ - ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) | - BIT(APICV_INHIBIT_REASON_ABSENT) | - BIT(APICV_INHIBIT_REASON_HYPERV) | - BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | - BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | - BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED); - - return supported & BIT(reason); -} +#define VMX_REQUIRED_APICV_INHIBITS \ +( \ + BIT(APICV_INHIBIT_REASON_DISABLE)| \ + BIT(APICV_INHIBIT_REASON_ABSENT) | \ + BIT(APICV_INHIBIT_REASON_HYPERV) | \ + BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | \ + BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \ + BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \ + BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) \ +) static void vmx_vm_destroy(struct kvm *kvm) { @@ -8071,7 +8129,9 @@ static void vmx_vm_destroy(struct kvm *kvm) } static struct kvm_x86_ops vmx_x86_ops __initdata = { - .name = "kvm_intel", + .name = KBUILD_MODNAME, + + .check_processor_compatibility = vmx_check_processor_compat, .hardware_unsetup = vmx_hardware_unsetup, @@ -8145,7 +8205,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, .apicv_post_state_restore = vmx_apicv_post_state_restore, - .check_apicv_inhibit_reasons = vmx_check_apicv_inhibit_reasons, + .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt, @@ -8291,7 +8351,7 @@ static __init int hardware_setup(void) return -EIO; if (cpu_has_perf_global_ctrl_bug()) - pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " + pr_warn_once("VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL " "does not work properly. Using workaround\n"); if (boot_cpu_has(X86_FEATURE_NX)) @@ -8299,7 +8359,7 @@ static __init int hardware_setup(void) if (boot_cpu_has(X86_FEATURE_MPX)) { rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs); - WARN_ONCE(host_bndcfgs, "KVM: BNDCFGS in host will be lost"); + WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost"); } if (!cpu_has_vmx_mpx()) @@ -8318,7 +8378,7 @@ static __init int hardware_setup(void) /* NX support is required for shadow paging. */ if (!enable_ept && !boot_cpu_has(X86_FEATURE_NX)) { - pr_err_ratelimited("kvm: NX (Execute Disable) not supported\n"); + pr_err_ratelimited("NX (Execute Disable) not supported\n"); return -EOPNOTSUPP; } @@ -8470,9 +8530,6 @@ static __init int hardware_setup(void) } static struct kvm_x86_init_ops vmx_init_ops __initdata = { - .cpu_has_kvm_support = cpu_has_kvm_support, - .disabled_by_bios = vmx_disabled_by_bios, - .check_processor_compatibility = vmx_check_processor_compat, .hardware_setup = hardware_setup, .handle_intel_pt_intr = NULL, @@ -8490,41 +8547,23 @@ static void vmx_cleanup_l1d_flush(void) l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; } -static void vmx_exit(void) +static void __vmx_exit(void) { + allow_smaller_maxphyaddr = false; + #ifdef CONFIG_KEXEC_CORE RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); #endif + vmx_cleanup_l1d_flush(); +} +static void vmx_exit(void) +{ kvm_exit(); + kvm_x86_vendor_exit(); -#if IS_ENABLED(CONFIG_HYPERV) - if (static_branch_unlikely(&enable_evmcs)) { - int cpu; - struct hv_vp_assist_page *vp_ap; - /* - * Reset everything to support using non-enlightened VMCS - * access later (e.g. when we reload the module with - * enlightened_vmcs=0) - */ - for_each_online_cpu(cpu) { - vp_ap = hv_get_vp_assist_page(cpu); - - if (!vp_ap) - continue; - - vp_ap->nested_control.features.directhypercall = 0; - vp_ap->current_nested_vmcs = 0; - vp_ap->enlighten_vmentry = 0; - } - - static_branch_disable(&enable_evmcs); - } -#endif - vmx_cleanup_l1d_flush(); - - allow_smaller_maxphyaddr = false; + __vmx_exit(); } module_exit(vmx_exit); @@ -8532,56 +8571,29 @@ static int __init vmx_init(void) { int r, cpu; -#if IS_ENABLED(CONFIG_HYPERV) + if (!kvm_is_vmx_supported()) + return -EOPNOTSUPP; + /* - * Enlightened VMCS usage should be recommended and the host needs - * to support eVMCS v1 or above. We can also disable eVMCS support - * with module parameter. + * Note, hv_init_evmcs() touches only VMX knobs, i.e. there's nothing + * to unwind if a later step fails. */ - if (enlightened_vmcs && - ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED && - (ms_hyperv.nested_features & HV_X64_ENLIGHTENED_VMCS_VERSION) >= - KVM_EVMCS_VERSION) { - - /* Check that we have assist pages on all online CPUs */ - for_each_online_cpu(cpu) { - if (!hv_get_vp_assist_page(cpu)) { - enlightened_vmcs = false; - break; - } - } - - if (enlightened_vmcs) { - pr_info("KVM: vmx: using Hyper-V Enlightened VMCS\n"); - static_branch_enable(&enable_evmcs); - } - - if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_l2_tlb_flush - = hv_enable_l2_tlb_flush; - - } else { - enlightened_vmcs = false; - } -#endif + hv_init_evmcs(); - r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); + r = kvm_x86_vendor_init(&vmx_init_ops); if (r) return r; /* - * Must be called after kvm_init() so enable_ept is properly set + * Must be called after common x86 init so enable_ept is properly set * up. Hand the parameter mitigation value in which was stored in * the pre module init parser. If no parameter was given, it will * contain 'auto' which will be turned into the default 'cond' * mitigation mode. */ r = vmx_setup_l1d_flush(vmentry_l1d_flush_param); - if (r) { - vmx_exit(); - return r; - } + if (r) + goto err_l1d_flush; vmx_setup_fb_clear_ctrl(); @@ -8605,6 +8617,21 @@ static int __init vmx_init(void) if (!enable_ept) allow_smaller_maxphyaddr = true; + /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx), + THIS_MODULE); + if (r) + goto err_kvm_init; + return 0; + +err_kvm_init: + __vmx_exit(); +err_l1d_flush: + kvm_x86_vendor_exit(); + return r; } module_init(vmx_init); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index a3da84f4ea45..2acdc54bc34b 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -640,12 +640,12 @@ BUILD_CONTROLS_SHADOW(tertiary_exec, TERTIARY_VM_EXEC_CONTROL, 64) (1 << VCPU_EXREG_EXIT_INFO_1) | \ (1 << VCPU_EXREG_EXIT_INFO_2)) -static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) +static __always_inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { return container_of(kvm, struct kvm_vmx, kvm); } -static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) +static __always_inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu) { return container_of(vcpu, struct vcpu_vmx, vcpu); } @@ -669,25 +669,23 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu); int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu); void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu); -static inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) +static __always_inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_1)) { - kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1); + if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1)) vmx->exit_qualification = vmcs_readl(EXIT_QUALIFICATION); - } + return vmx->exit_qualification; } -static inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) +static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!kvm_register_is_available(vcpu, VCPU_EXREG_EXIT_INFO_2)) { - kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2); + if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2)) vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO); - } + return vmx->exit_intr_info; } diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 842dc898c972..db95bde52998 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -100,8 +100,10 @@ static __always_inline unsigned long __vmcs_readl(unsigned long field) return value; do_fail: - WARN_ONCE(1, "kvm: vmread failed: field=%lx\n", field); - pr_warn_ratelimited("kvm: vmread failed: field=%lx\n", field); + instrumentation_begin(); + WARN_ONCE(1, KBUILD_MODNAME ": vmread failed: field=%lx\n", field); + pr_warn_ratelimited(KBUILD_MODNAME ": vmread failed: field=%lx\n", field); + instrumentation_end(); return 0; do_exception: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index da4bbd043a7b..f706621c35b8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -15,6 +15,7 @@ * Amit Shah <amit.shah@qumranet.com> * Ben-Ami Yassour <benami@il.ibm.com> */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kvm_host.h> #include "irq.h" @@ -128,6 +129,7 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu); static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); static void __get_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2); +static DEFINE_MUTEX(vendor_module_lock); struct kvm_x86_ops kvm_x86_ops __read_mostly; #define KVM_X86_OP(func) \ @@ -1417,7 +1419,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); * may depend on host virtualization features rather than host cpu features. */ -static const u32 msrs_to_save_all[] = { +static const u32 msrs_to_save_base[] = { MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_STAR, #ifdef CONFIG_X86_64 @@ -1434,6 +1436,10 @@ static const u32 msrs_to_save_all[] = { MSR_IA32_RTIT_ADDR3_A, MSR_IA32_RTIT_ADDR3_B, MSR_IA32_UMWAIT_CONTROL, + MSR_IA32_XFD, MSR_IA32_XFD_ERR, +}; + +static const u32 msrs_to_save_pmu[] = { MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1, MSR_ARCH_PERFMON_FIXED_CTR0 + 2, MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS, @@ -1458,11 +1464,10 @@ static const u32 msrs_to_save_all[] = { MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5, MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2, MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5, - - MSR_IA32_XFD, MSR_IA32_XFD_ERR, }; -static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_all)]; +static u32 msrs_to_save[ARRAY_SIZE(msrs_to_save_base) + + ARRAY_SIZE(msrs_to_save_pmu)]; static unsigned num_msrs_to_save; static const u32 emulated_msrs_all[] = { @@ -1480,7 +1485,7 @@ static const u32 emulated_msrs_all[] = { HV_X64_MSR_STIMER0_CONFIG, HV_X64_MSR_VP_ASSIST_PAGE, HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL, - HV_X64_MSR_TSC_EMULATION_STATUS, + HV_X64_MSR_TSC_EMULATION_STATUS, HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_X64_MSR_SYNDBG_OPTIONS, HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, @@ -2086,7 +2091,7 @@ static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT)) return kvm_handle_invalid_op(vcpu); - pr_warn_once("kvm: %s instruction emulated as NOP!\n", insn); + pr_warn_once("%s instruction emulated as NOP!\n", insn); return kvm_emulate_as_nop(vcpu); } int kvm_emulate_mwait(struct kvm_vcpu *vcpu) @@ -2433,7 +2438,8 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm); thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm); if (user_tsc_khz < thresh_lo || user_tsc_khz > thresh_hi) { - pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", user_tsc_khz, thresh_lo, thresh_hi); + pr_debug("requested TSC rate %u falls outside tolerance [%u,%u]\n", + user_tsc_khz, thresh_lo, thresh_hi); use_scaling = 1; } return set_tsc_khz(vcpu, user_tsc_khz, use_scaling); @@ -3158,6 +3164,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) &vcpu->hv_clock.tsc_shift, &vcpu->hv_clock.tsc_to_system_mul); vcpu->hw_tsc_khz = tgt_tsc_khz; + kvm_xen_update_tsc_info(v); } vcpu->hv_clock.tsc_timestamp = tsc_timestamp; @@ -3555,9 +3562,20 @@ static void record_steal_time(struct kvm_vcpu *vcpu) mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } +static bool kvm_is_msr_to_save(u32 msr_index) +{ + unsigned int i; + + for (i = 0; i < num_msrs_to_save; i++) { + if (msrs_to_save[i] == msr_index) + return true; + } + + return false; +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { - bool pr = false; u32 msr = msr_info->index; u64 data = msr_info->data; @@ -3603,15 +3621,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data == BIT_ULL(18)) { vcpu->arch.msr_hwcr = data; } else if (data != 0) { - vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", - data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { - vcpu_unimpl(vcpu, "unimplemented MMIO_CONF_BASE wrmsr: " - "0x%llx\n", data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } break; @@ -3791,16 +3807,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: - pr = true; - fallthrough; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_P6_EVNTSEL0 ... MSR_P6_EVNTSEL1: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); - if (pr || data != 0) - vcpu_unimpl(vcpu, "disabled perfctr wrmsr: " - "0x%x data 0x%llx\n", msr, data); + if (data) + kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_K7_CLK_CTL: /* @@ -3821,15 +3834,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. */ - if (report_ignored_msrs) - vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", - msr, data); + kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) @@ -3877,20 +3889,18 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.guest_fpu.xfd_err = data; break; #endif - case MSR_IA32_PEBS_ENABLE: - case MSR_IA32_DS_AREA: - case MSR_PEBS_DATA_CFG: - case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: + default: if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); + /* * Userspace is allowed to write '0' to MSRs that KVM reports * as to-be-saved, even if an MSRs isn't fully supported. */ - return !msr_info->host_initiated || data; - default: - if (kvm_pmu_is_valid_msr(vcpu, msr)) - return kvm_pmu_set_msr(vcpu, msr_info); + if (msr_info->host_initiated && !data && + kvm_is_msr_to_save(msr)) + break; + return KVM_MSR_RET_INVALID; } return 0; @@ -3980,20 +3990,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_DRAM_ENERGY_STATUS: /* DRAM controller */ msr_info->data = 0; break; - case MSR_IA32_PEBS_ENABLE: - case MSR_IA32_DS_AREA: - case MSR_PEBS_DATA_CFG: - case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: - if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) - return kvm_pmu_get_msr(vcpu, msr_info); - /* - * Userspace is allowed to read MSRs that KVM reports as - * to-be-saved, even if an MSR isn't fully supported. - */ - if (!msr_info->host_initiated) - return 1; - msr_info->data = 0; - break; case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3: case MSR_K7_PERFCTR0 ... MSR_K7_PERFCTR3: case MSR_P6_PERFCTR0 ... MSR_P6_PERFCTR1: @@ -4191,6 +4187,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_REENLIGHTENMENT_CONTROL: case HV_X64_MSR_TSC_EMULATION_CONTROL: case HV_X64_MSR_TSC_EMULATION_STATUS: + case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); @@ -4248,6 +4245,17 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) default: if (kvm_pmu_is_valid_msr(vcpu, msr_info->index)) return kvm_pmu_get_msr(vcpu, msr_info); + + /* + * Userspace is allowed to read MSRs that KVM reports as + * to-be-saved, even if an MSR isn't fully supported. + */ + if (msr_info->host_initiated && + kvm_is_msr_to_save(msr_info->index)) { + msr_info->data = 0; + break; + } + return KVM_MSR_RET_INVALID; } return 0; @@ -4285,8 +4293,8 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, { struct kvm_msrs msrs; struct kvm_msr_entry *entries; - int r, n; unsigned size; + int r; r = -EFAULT; if (copy_from_user(&msrs, user_msrs, sizeof(msrs))) @@ -4303,17 +4311,11 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, goto out; } - r = n = __msr_io(vcpu, &msrs, entries, do_msr); - if (r < 0) - goto out_free; + r = __msr_io(vcpu, &msrs, entries, do_msr); - r = -EFAULT; if (writeback && copy_to_user(user_msrs->entries, entries, size)) - goto out_free; - - r = n; + r = -EFAULT; -out_free: kfree(entries); out: return r; @@ -4401,6 +4403,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_SPLIT_IRQCHIP: case KVM_CAP_IMMEDIATE_EXIT: case KVM_CAP_PMU_EVENT_FILTER: + case KVM_CAP_PMU_EVENT_MASKED_EVENTS: case KVM_CAP_GET_MSR_FEATURES: case KVM_CAP_MSR_PLATFORM_INFO: case KVM_CAP_EXCEPTION_PAYLOAD: @@ -6460,7 +6463,7 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, struct kvm_x86_msr_filter *new_filter, *old_filter; bool default_allow; bool empty = true; - int r = 0; + int r; u32 i; if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK) @@ -6486,17 +6489,14 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, } mutex_lock(&kvm->lock); - - /* The per-VM filter is protected by kvm->lock... */ - old_filter = srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1); - - rcu_assign_pointer(kvm->arch.msr_filter, new_filter); + old_filter = rcu_replace_pointer(kvm->arch.msr_filter, new_filter, + mutex_is_locked(&kvm->lock)); + mutex_unlock(&kvm->lock); synchronize_srcu(&kvm->srcu); kvm_free_msr_filter(old_filter); kvm_make_all_cpus_request(kvm, KVM_REQ_MSR_FILTER_CHANGED); - mutex_unlock(&kvm->lock); return 0; } @@ -6996,83 +6996,98 @@ out: return r; } -static void kvm_init_msr_list(void) +static void kvm_probe_msr_to_save(u32 msr_index) { u32 dummy[2]; + + if (rdmsr_safe(msr_index, &dummy[0], &dummy[1])) + return; + + /* + * Even MSRs that are valid in the host may not be exposed to guests in + * some cases. + */ + switch (msr_index) { + case MSR_IA32_BNDCFGS: + if (!kvm_mpx_supported()) + return; + break; + case MSR_TSC_AUX: + if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && + !kvm_cpu_cap_has(X86_FEATURE_RDPID)) + return; + break; + case MSR_IA32_UMWAIT_CONTROL: + if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) + return; + break; + case MSR_IA32_RTIT_CTL: + case MSR_IA32_RTIT_STATUS: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) + return; + break; + case MSR_IA32_RTIT_CR3_MATCH: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) + return; + break; + case MSR_IA32_RTIT_OUTPUT_BASE: + case MSR_IA32_RTIT_OUTPUT_MASK: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && + !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) + return; + break; + case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: + if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || + (msr_index - MSR_IA32_RTIT_ADDR0_A >= + intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)) + return; + break; + case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: + if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >= + kvm_pmu_cap.num_counters_gp) + return; + break; + case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: + if (msr_index - MSR_ARCH_PERFMON_EVENTSEL0 >= + kvm_pmu_cap.num_counters_gp) + return; + break; + case MSR_ARCH_PERFMON_FIXED_CTR0 ... MSR_ARCH_PERFMON_FIXED_CTR_MAX: + if (msr_index - MSR_ARCH_PERFMON_FIXED_CTR0 >= + kvm_pmu_cap.num_counters_fixed) + return; + break; + case MSR_IA32_XFD: + case MSR_IA32_XFD_ERR: + if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) + return; + break; + default: + break; + } + + msrs_to_save[num_msrs_to_save++] = msr_index; +} + +static void kvm_init_msr_list(void) +{ unsigned i; BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3, - "Please update the fixed PMCs in msrs_to_saved_all[]"); + "Please update the fixed PMCs in msrs_to_save_pmu[]"); num_msrs_to_save = 0; num_emulated_msrs = 0; num_msr_based_features = 0; - for (i = 0; i < ARRAY_SIZE(msrs_to_save_all); i++) { - if (rdmsr_safe(msrs_to_save_all[i], &dummy[0], &dummy[1]) < 0) - continue; - - /* - * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. - */ - switch (msrs_to_save_all[i]) { - case MSR_IA32_BNDCFGS: - if (!kvm_mpx_supported()) - continue; - break; - case MSR_TSC_AUX: - if (!kvm_cpu_cap_has(X86_FEATURE_RDTSCP) && - !kvm_cpu_cap_has(X86_FEATURE_RDPID)) - continue; - break; - case MSR_IA32_UMWAIT_CONTROL: - if (!kvm_cpu_cap_has(X86_FEATURE_WAITPKG)) - continue; - break; - case MSR_IA32_RTIT_CTL: - case MSR_IA32_RTIT_STATUS: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT)) - continue; - break; - case MSR_IA32_RTIT_CR3_MATCH: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || - !intel_pt_validate_hw_cap(PT_CAP_cr3_filtering)) - continue; - break; - case MSR_IA32_RTIT_OUTPUT_BASE: - case MSR_IA32_RTIT_OUTPUT_MASK: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || - (!intel_pt_validate_hw_cap(PT_CAP_topa_output) && - !intel_pt_validate_hw_cap(PT_CAP_single_range_output))) - continue; - break; - case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B: - if (!kvm_cpu_cap_has(X86_FEATURE_INTEL_PT) || - msrs_to_save_all[i] - MSR_IA32_RTIT_ADDR0_A >= - intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2) - continue; - break; - case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX: - if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >= - min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) - continue; - break; - case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX: - if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >= - min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp)) - continue; - break; - case MSR_IA32_XFD: - case MSR_IA32_XFD_ERR: - if (!kvm_cpu_cap_has(X86_FEATURE_XFD)) - continue; - break; - default: - break; - } + for (i = 0; i < ARRAY_SIZE(msrs_to_save_base); i++) + kvm_probe_msr_to_save(msrs_to_save_base[i]); - msrs_to_save[num_msrs_to_save++] = msrs_to_save_all[i]; + if (enable_pmu) { + for (i = 0; i < ARRAY_SIZE(msrs_to_save_pmu); i++) + kvm_probe_msr_to_save(msrs_to_save_pmu[i]); } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { @@ -7699,7 +7714,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, return X86EMUL_CONTINUE; emul_write: - printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); + pr_warn_once("emulating exchange as write\n"); return emulator_write_emulated(ctxt, addr, new, bytes, exception); } @@ -8145,9 +8160,14 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked); } -static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) +static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt) +{ + return is_smm(emul_to_vcpu(ctxt)); +} + +static bool emulator_is_guest_mode(struct x86_emulate_ctxt *ctxt) { - return emul_to_vcpu(ctxt)->arch.hflags; + return is_guest_mode(emul_to_vcpu(ctxt)); } #ifndef CONFIG_KVM_SMM @@ -8216,7 +8236,8 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_fxsr = emulator_guest_has_fxsr, .guest_has_rdpid = emulator_guest_has_rdpid, .set_nmi_mask = emulator_set_nmi_mask, - .get_hflags = emulator_get_hflags, + .is_smm = emulator_is_smm, + .is_guest_mode = emulator_is_guest_mode, .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, @@ -8260,7 +8281,7 @@ static struct x86_emulate_ctxt *alloc_emulate_ctxt(struct kvm_vcpu *vcpu) ctxt = kmem_cache_zalloc(x86_emulator_cache, GFP_KERNEL_ACCOUNT); if (!ctxt) { - pr_err("kvm: failed to allocate vcpu's emulator\n"); + pr_err("failed to allocate vcpu's emulator\n"); return NULL; } @@ -8288,8 +8309,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); - ctxt->interruptibility = 0; ctxt->have_exception = false; ctxt->exception.vector = -1; @@ -9271,35 +9290,66 @@ static struct notifier_block pvclock_gtod_notifier = { }; #endif -int kvm_arch_init(void *opaque) +static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) +{ + memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); + +#define __KVM_X86_OP(func) \ + static_call_update(kvm_x86_##func, kvm_x86_ops.func); +#define KVM_X86_OP(func) \ + WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func) +#define KVM_X86_OP_OPTIONAL __KVM_X86_OP +#define KVM_X86_OP_OPTIONAL_RET0(func) \ + static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \ + (void *)__static_call_return0); +#include <asm/kvm-x86-ops.h> +#undef __KVM_X86_OP + + kvm_pmu_ops_update(ops->pmu_ops); +} + +static int kvm_x86_check_processor_compatibility(void) +{ + int cpu = smp_processor_id(); + struct cpuinfo_x86 *c = &cpu_data(cpu); + + /* + * Compatibility checks are done when loading KVM and when enabling + * hardware, e.g. during CPU hotplug, to ensure all online CPUs are + * compatible, i.e. KVM should never perform a compatibility check on + * an offline CPU. + */ + WARN_ON(!cpu_online(cpu)); + + if (__cr4_reserved_bits(cpu_has, c) != + __cr4_reserved_bits(cpu_has, &boot_cpu_data)) + return -EIO; + + return static_call(kvm_x86_check_processor_compatibility)(); +} + +static void kvm_x86_check_cpu_compat(void *ret) +{ + *(int *)ret = kvm_x86_check_processor_compatibility(); +} + +static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { - struct kvm_x86_init_ops *ops = opaque; u64 host_pat; - int r; + int r, cpu; if (kvm_x86_ops.hardware_enable) { - pr_err("kvm: already loaded vendor module '%s'\n", kvm_x86_ops.name); + pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; } - if (!ops->cpu_has_kvm_support()) { - pr_err_ratelimited("kvm: no hardware support for '%s'\n", - ops->runtime_ops->name); - return -EOPNOTSUPP; - } - if (ops->disabled_by_bios()) { - pr_err_ratelimited("kvm: support for '%s' disabled by bios\n", - ops->runtime_ops->name); - return -EOPNOTSUPP; - } - /* * KVM explicitly assumes that the guest has an FPU and * FXSAVE/FXRSTOR. For example, the KVM_GET_FPU explicitly casts the * vCPU's FPU state as a fxregs_state struct. */ if (!boot_cpu_has(X86_FEATURE_FPU) || !boot_cpu_has(X86_FEATURE_FXSR)) { - printk(KERN_ERR "kvm: inadequate fpu\n"); + pr_err("inadequate fpu\n"); return -EOPNOTSUPP; } @@ -9317,19 +9367,19 @@ int kvm_arch_init(void *opaque) */ if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) || (host_pat & GENMASK(2, 0)) != 6) { - pr_err("kvm: host PAT[0] is not WB\n"); + pr_err("host PAT[0] is not WB\n"); return -EIO; } x86_emulator_cache = kvm_alloc_emulator_cache(); if (!x86_emulator_cache) { - pr_err("kvm: failed to allocate cache for x86 emulator\n"); + pr_err("failed to allocate cache for x86 emulator\n"); return -ENOMEM; } user_return_msrs = alloc_percpu(struct kvm_user_return_msrs); if (!user_return_msrs) { - printk(KERN_ERR "kvm: failed to allocate percpu kvm_user_return_msrs\n"); + pr_err("failed to allocate percpu kvm_user_return_msrs\n"); r = -ENOMEM; goto out_free_x86_emulator_cache; } @@ -9339,13 +9389,37 @@ int kvm_arch_init(void *opaque) if (r) goto out_free_percpu; - kvm_timer_init(); - if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; } + rdmsrl_safe(MSR_EFER, &host_efer); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + rdmsrl(MSR_IA32_XSS, host_xss); + + kvm_init_pmu_capability(ops->pmu_ops); + + r = ops->hardware_setup(); + if (r != 0) + goto out_mmu_exit; + + kvm_ops_update(ops); + + for_each_online_cpu(cpu) { + smp_call_function_single(cpu, kvm_x86_check_cpu_compat, &r, 1); + if (r < 0) + goto out_unwind_ops; + } + + /* + * Point of no return! DO NOT add error paths below this point unless + * absolutely necessary, as most operations from this point forward + * require unwinding. + */ + kvm_timer_init(); + if (pi_inject_timer == -1) pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER); #ifdef CONFIG_X86_64 @@ -9355,8 +9429,35 @@ int kvm_arch_init(void *opaque) set_hv_tscchange_cb(kvm_hyperv_tsc_notifier); #endif + kvm_register_perf_callbacks(ops->handle_intel_pt_intr); + + if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) + kvm_caps.supported_xss = 0; + +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); +#undef __kvm_cpu_cap_has + + if (kvm_caps.has_tsc_control) { + /* + * Make sure the user can only configure tsc_khz values that + * fit into a signed integer. + * A min value is not calculated because it will always + * be 1 on all machines. + */ + u64 max = min(0x7fffffffULL, + __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); + kvm_caps.max_guest_tsc_khz = max; + } + kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; + kvm_init_msr_list(); return 0; +out_unwind_ops: + kvm_x86_ops.hardware_enable = NULL; + static_call(kvm_x86_hardware_unsetup)(); +out_mmu_exit: + kvm_mmu_vendor_module_exit(); out_free_percpu: free_percpu(user_return_msrs); out_free_x86_emulator_cache: @@ -9364,8 +9465,22 @@ out_free_x86_emulator_cache: return r; } -void kvm_arch_exit(void) +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) +{ + int r; + + mutex_lock(&vendor_module_lock); + r = __kvm_x86_vendor_init(ops); + mutex_unlock(&vendor_module_lock); + + return r; +} +EXPORT_SYMBOL_GPL(kvm_x86_vendor_init); + +void kvm_x86_vendor_exit(void) { + kvm_unregister_perf_callbacks(); + #ifdef CONFIG_X86_64 if (hypervisor_is_type(X86_HYPER_MS_HYPERV)) clear_hv_tscchange_cb(); @@ -9382,7 +9497,7 @@ void kvm_arch_exit(void) irq_work_sync(&pvclock_irq_work); cancel_work_sync(&pvclock_gtod_work); #endif - kvm_x86_ops.hardware_enable = NULL; + static_call(kvm_x86_hardware_unsetup)(); kvm_mmu_vendor_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_emulator_cache); @@ -9390,7 +9505,11 @@ void kvm_arch_exit(void) static_key_deferred_flush(&kvm_xen_enabled); WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); #endif + mutex_lock(&vendor_module_lock); + kvm_x86_ops.hardware_enable = NULL; + mutex_unlock(&vendor_module_lock); } +EXPORT_SYMBOL_GPL(kvm_x86_vendor_exit); static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason) { @@ -10043,7 +10162,7 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm) kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); } -void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) +void __kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; bool activate; @@ -10078,7 +10197,30 @@ out: preempt_enable(); up_read(&vcpu->kvm->arch.apicv_update_lock); } -EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); +EXPORT_SYMBOL_GPL(__kvm_vcpu_update_apicv); + +static void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) +{ + if (!lapic_in_kernel(vcpu)) + return; + + /* + * Due to sharing page tables across vCPUs, the xAPIC memslot must be + * deleted if any vCPU has xAPIC virtualization and x2APIC enabled, but + * and hardware doesn't support x2APIC virtualization. E.g. some AMD + * CPUs support AVIC but not x2APIC. KVM still allows enabling AVIC in + * this case so that KVM can the AVIC doorbell to inject interrupts to + * running vCPUs, but KVM must not create SPTEs for the APIC base as + * the vCPU would incorrectly be able to access the vAPIC page via MMIO + * despite being in x2APIC mode. For simplicity, inhibiting the APIC + * access page is sticky. + */ + if (apic_x2apic_mode(vcpu->arch.apic) && + kvm_x86_ops.allow_apicv_in_x2apic_without_x2apic_virtualization) + kvm_inhibit_apic_access_page(vcpu); + + __kvm_vcpu_update_apicv(vcpu); +} void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, enum kvm_apicv_inhibit reason, bool set) @@ -10087,7 +10229,7 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, lockdep_assert_held_write(&kvm->arch.apicv_update_lock); - if (!static_call(kvm_x86_check_apicv_inhibit_reasons)(reason)) + if (!(kvm_x86_ops.required_apicv_inhibits & BIT(reason))) return; old = new = kvm->arch.apicv_inhibit_reasons; @@ -11531,7 +11673,7 @@ static int sync_regs(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) { if (kvm_check_tsc_unstable() && kvm->created_vcpus) - pr_warn_once("kvm: SMP vm created on host with unstable TSC; " + pr_warn_once("SMP vm created on host with unstable TSC; " "guest TSC will not be reliable\n"); if (!kvm->arch.max_vcpu_ids) @@ -11608,7 +11750,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) goto free_wbinvd_dirty_mask; if (!fpu_alloc_guest_fpstate(&vcpu->arch.guest_fpu)) { - pr_err("kvm: failed to allocate vcpu's fpu\n"); + pr_err("failed to allocate vcpu's fpu\n"); goto free_emulate_ctxt; } @@ -11882,6 +12024,11 @@ int kvm_arch_hardware_enable(void) bool stable, backwards_tsc = false; kvm_user_return_msr_cpu_online(); + + ret = kvm_x86_check_processor_compatibility(); + if (ret) + return ret; + ret = static_call(kvm_x86_hardware_enable)(); if (ret != 0) return ret; @@ -11968,88 +12115,6 @@ void kvm_arch_hardware_disable(void) drop_user_return_notifiers(); } -static inline void kvm_ops_update(struct kvm_x86_init_ops *ops) -{ - memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); - -#define __KVM_X86_OP(func) \ - static_call_update(kvm_x86_##func, kvm_x86_ops.func); -#define KVM_X86_OP(func) \ - WARN_ON(!kvm_x86_ops.func); __KVM_X86_OP(func) -#define KVM_X86_OP_OPTIONAL __KVM_X86_OP -#define KVM_X86_OP_OPTIONAL_RET0(func) \ - static_call_update(kvm_x86_##func, (void *)kvm_x86_ops.func ? : \ - (void *)__static_call_return0); -#include <asm/kvm-x86-ops.h> -#undef __KVM_X86_OP - - kvm_pmu_ops_update(ops->pmu_ops); -} - -int kvm_arch_hardware_setup(void *opaque) -{ - struct kvm_x86_init_ops *ops = opaque; - int r; - - rdmsrl_safe(MSR_EFER, &host_efer); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - rdmsrl(MSR_IA32_XSS, host_xss); - - kvm_init_pmu_capability(); - - r = ops->hardware_setup(); - if (r != 0) - return r; - - kvm_ops_update(ops); - - kvm_register_perf_callbacks(ops->handle_intel_pt_intr); - - if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) - kvm_caps.supported_xss = 0; - -#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) - cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); -#undef __kvm_cpu_cap_has - - if (kvm_caps.has_tsc_control) { - /* - * Make sure the user can only configure tsc_khz values that - * fit into a signed integer. - * A min value is not calculated because it will always - * be 1 on all machines. - */ - u64 max = min(0x7fffffffULL, - __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); - kvm_caps.max_guest_tsc_khz = max; - } - kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; - kvm_init_msr_list(); - return 0; -} - -void kvm_arch_hardware_unsetup(void) -{ - kvm_unregister_perf_callbacks(); - - static_call(kvm_x86_hardware_unsetup)(); -} - -int kvm_arch_check_processor_compat(void *opaque) -{ - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); - struct kvm_x86_init_ops *ops = opaque; - - WARN_ON(!irqs_disabled()); - - if (__cr4_reserved_bits(cpu_has, c) != - __cr4_reserved_bits(cpu_has, &boot_cpu_data)) - return -EIO; - - return ops->check_processor_compatibility(); -} - bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; @@ -12222,7 +12287,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, */ hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, 0); - if (IS_ERR((void *)hva)) + if (IS_ERR_VALUE(hva)) return (void __user *)hva; } else { if (!slot || !slot->npages) @@ -12437,16 +12502,14 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable) { - struct kvm_arch *ka = &kvm->arch; + int nr_slots; if (!kvm_x86_ops.cpu_dirty_log_size) return; - if ((enable && ++ka->cpu_dirty_logging_count == 1) || - (!enable && --ka->cpu_dirty_logging_count == 0)) + nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging); + if ((enable && nr_slots == 1) || !nr_slots) kvm_make_all_cpus_request(kvm, KVM_REQ_UPDATE_CPU_DIRTY_LOGGING); - - WARN_ON_ONCE(ka->cpu_dirty_logging_count < 0); } static void kvm_mmu_slot_apply_flags(struct kvm *kvm, diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 9de72586f406..a8167b47b8c8 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -331,6 +331,18 @@ extern bool report_ignored_msrs; extern bool eager_page_split; +static inline void kvm_pr_unimpl_wrmsr(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "Unhandled WRMSR(0x%x) = 0x%llx\n", msr, data); +} + +static inline void kvm_pr_unimpl_rdmsr(struct kvm_vcpu *vcpu, u32 msr) +{ + if (report_ignored_msrs) + vcpu_unimpl(vcpu, "Unhandled RDMSR(0x%x)\n", msr); +} + static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec) { return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult, @@ -382,13 +394,13 @@ enum kvm_intr_type { KVM_HANDLING_NMI, }; -static inline void kvm_before_interrupt(struct kvm_vcpu *vcpu, - enum kvm_intr_type intr) +static __always_inline void kvm_before_interrupt(struct kvm_vcpu *vcpu, + enum kvm_intr_type intr) { WRITE_ONCE(vcpu->arch.handling_intr_from_guest, (u8)intr); } -static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) +static __always_inline void kvm_after_interrupt(struct kvm_vcpu *vcpu) { WRITE_ONCE(vcpu->arch.handling_intr_from_guest, 0); } diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 2e29bdc2949c..40edf4d1974c 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -5,6 +5,7 @@ * * KVM Xen emulation */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "x86.h" #include "xen.h" @@ -22,6 +23,9 @@ #include <xen/interface/event_channel.h> #include <xen/interface/sched.h> +#include <asm/xen/cpuid.h> + +#include "cpuid.h" #include "trace.h" static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm); @@ -271,7 +275,15 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) * Attempt to obtain the GPC lock on *both* (if there are two) * gfn_to_pfn caches that cover the region. */ - read_lock_irqsave(&gpc1->lock, flags); + if (atomic) { + local_irq_save(flags); + if (!read_trylock(&gpc1->lock)) { + local_irq_restore(flags); + return; + } + } else { + read_lock_irqsave(&gpc1->lock, flags); + } while (!kvm_gpc_check(gpc1, user_len1)) { read_unlock_irqrestore(&gpc1->lock, flags); @@ -304,9 +316,18 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) * The guest's runstate_info is split across two pages and we * need to hold and validate both GPCs simultaneously. We can * declare a lock ordering GPC1 > GPC2 because nothing else - * takes them more than one at a time. + * takes them more than one at a time. Set a subclass on the + * gpc1 lock to make lockdep shut up about it. */ - read_lock(&gpc2->lock); + lock_set_subclass(&gpc1->lock.dep_map, 1, _THIS_IP_); + if (atomic) { + if (!read_trylock(&gpc2->lock)) { + read_unlock_irqrestore(&gpc1->lock, flags); + return; + } + } else { + read_lock(&gpc2->lock); + } if (!kvm_gpc_check(gpc2, user_len2)) { read_unlock(&gpc2->lock); @@ -590,26 +611,26 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) if (!IS_ENABLED(CONFIG_64BIT) && data->u.long_mode) { r = -EINVAL; } else { - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.long_mode = !!data->u.long_mode; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; } break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); break; case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: if (data->u.vector && data->u.vector < 0x10) r = -EINVAL; else { - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.upcall_vector = data->u.vector; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; } break; @@ -619,9 +640,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_XEN_VERSION: - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.xen_version = data->u.xen_version; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; break; @@ -630,9 +651,9 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) r = -EOPNOTSUPP; break; } - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); r = 0; break; @@ -647,7 +668,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) { int r = -ENOENT; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); switch (data->type) { case KVM_XEN_ATTR_TYPE_LONG_MODE: @@ -686,7 +707,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; } - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); return r; } @@ -694,7 +715,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) { int idx, r = -ENOENT; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.xen.xen_lock); idx = srcu_read_lock(&vcpu->kvm->srcu); switch (data->type) { @@ -922,7 +943,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) } srcu_read_unlock(&vcpu->kvm->srcu, idx); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.xen.xen_lock); return r; } @@ -930,7 +951,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) { int r = -ENOENT; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.xen.xen_lock); switch (data->type) { case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: @@ -1013,7 +1034,7 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.xen.xen_lock); return r; } @@ -1106,7 +1127,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) xhc->blob_size_32 || xhc->blob_size_64)) return -EINVAL; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); if (xhc->msr && !kvm->arch.xen_hvm_config.msr) static_branch_inc(&kvm_xen_enabled.key); @@ -1115,7 +1136,7 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc)); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); return 0; } @@ -1658,15 +1679,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) mm_borrowed = true; } - /* - * For the irqfd workqueue, using the main kvm->lock mutex is - * fine since this function is invoked from kvm_set_irq() with - * no other lock held, no srcu. In future if it will be called - * directly from a vCPU thread (e.g. on hypercall for an IPI) - * then it may need to switch to using a leaf-node mutex for - * serializing the shared_info mapping. - */ - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); /* * It is theoretically possible for the page to be unmapped @@ -1695,7 +1708,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) srcu_read_unlock(&kvm->srcu, idx); } while(!rc); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); if (mm_borrowed) kthread_unuse_mm(kvm->mm); @@ -1811,7 +1824,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, int ret; /* Protect writes to evtchnfd as well as the idr lookup. */ - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); evtchnfd = idr_find(&kvm->arch.xen.evtchn_ports, port); ret = -ENOENT; @@ -1842,7 +1855,7 @@ static int kvm_xen_eventfd_update(struct kvm *kvm, } ret = 0; out_unlock: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); return ret; } @@ -1905,10 +1918,10 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, evtchnfd->deliver.port.priority = data->u.evtchn.deliver.port.priority; } - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); ret = idr_alloc(&kvm->arch.xen.evtchn_ports, evtchnfd, port, port + 1, GFP_KERNEL); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); if (ret >= 0) return 0; @@ -1926,9 +1939,9 @@ static int kvm_xen_eventfd_deassign(struct kvm *kvm, u32 port) { struct evtchnfd *evtchnfd; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); evtchnfd = idr_remove(&kvm->arch.xen.evtchn_ports, port); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); if (!evtchnfd) return -ENOENT; @@ -1946,7 +1959,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm) int i; int n = 0; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.xen.xen_lock); /* * Because synchronize_srcu() cannot be called inside the @@ -1958,7 +1971,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm) all_evtchnfds = kmalloc_array(n, sizeof(struct evtchnfd *), GFP_KERNEL); if (!all_evtchnfds) { - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); return -ENOMEM; } @@ -1967,7 +1980,7 @@ static int kvm_xen_eventfd_reset(struct kvm *kvm) all_evtchnfds[n++] = evtchnfd; idr_remove(&kvm->arch.xen.evtchn_ports, evtchnfd->send_port); } - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.xen.xen_lock); synchronize_srcu(&kvm->srcu); @@ -2067,8 +2080,32 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) del_timer_sync(&vcpu->arch.xen.poll_timer); } +void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *entry; + u32 function; + + if (!vcpu->arch.xen.cpuid.base) + return; + + function = vcpu->arch.xen.cpuid.base | XEN_CPUID_LEAF(3); + if (function > vcpu->arch.xen.cpuid.limit) + return; + + entry = kvm_find_cpuid_entry_index(vcpu, function, 1); + if (entry) { + entry->ecx = vcpu->arch.hv_clock.tsc_to_system_mul; + entry->edx = vcpu->arch.hv_clock.tsc_shift; + } + + entry = kvm_find_cpuid_entry_index(vcpu, function, 2); + if (entry) + entry->eax = vcpu->arch.hw_tsc_khz; +} + void kvm_xen_init_vm(struct kvm *kvm) { + mutex_init(&kvm->arch.xen.xen_lock); idr_init(&kvm->arch.xen.evtchn_ports); kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN); } diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index ea33d80a0c51..f8f1fe22d090 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -9,6 +9,8 @@ #ifndef __ARCH_X86_KVM_XEN_H__ #define __ARCH_X86_KVM_XEN_H__ +#include <asm/xen/hypervisor.h> + #ifdef CONFIG_KVM_XEN #include <linux/jump_label_ratelimit.h> @@ -32,6 +34,7 @@ int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe, int kvm_xen_setup_evtchn(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue); +void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu); static inline bool kvm_xen_msr_enabled(struct kvm *kvm) { @@ -135,6 +138,10 @@ static inline bool kvm_xen_timer_enabled(struct kvm_vcpu *vcpu) { return false; } + +static inline void kvm_xen_update_tsc_info(struct kvm_vcpu *vcpu) +{ +} #endif int kvm_xen_hypercall(struct kvm_vcpu *vcpu); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index d3987359d441..cb258f58fdc8 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -26,6 +26,7 @@ #include <asm/pti.h> #include <asm/text-patching.h> #include <asm/memtype.h> +#include <asm/paravirt.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -804,6 +805,9 @@ void __init poking_init(void) poking_mm = mm_alloc(); BUG_ON(!poking_mm); + /* Xen PV guests need the PGD to be pinned. */ + paravirt_arch_dup_mmap(NULL, poking_mm); + /* * Randomize the poking address, but make sure that the following page * will be mapped at the same PMD. We need 2 pages, so find space for 3, diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 46de9cf5c91d..fb4b1b5e0dea 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -387,7 +387,8 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, u8 mtrr_type, uniform; mtrr_type = mtrr_type_lookup(start, end, &uniform); - if (mtrr_type != MTRR_TYPE_WRBACK) + if (mtrr_type != MTRR_TYPE_WRBACK && + mtrr_type != MTRR_TYPE_INVALID) return _PAGE_CACHE_MODE_UC_MINUS; return _PAGE_CACHE_MODE_WB; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 758cbfe55daa..4b3efaa82ab7 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -12,6 +12,7 @@ */ #include <linux/acpi.h> +#include <linux/efi.h> #include <linux/pci.h> #include <linux/init.h> #include <linux/bitmap.h> @@ -442,17 +443,42 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used) return mcfg_res.flags; } +static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used) +{ +#ifdef CONFIG_EFI + efi_memory_desc_t *md; + u64 size, mmio_start, mmio_end; + + for_each_efi_memory_desc(md) { + if (md->type == EFI_MEMORY_MAPPED_IO) { + size = md->num_pages << EFI_PAGE_SHIFT; + mmio_start = md->phys_addr; + mmio_end = mmio_start + size; + + /* + * N.B. Caller supplies (start, start + size), + * so to match, mmio_end is the first address + * *past* the EFI_MEMORY_MAPPED_IO area. + */ + if (mmio_start <= start && end <= mmio_end) + return true; + } + } +#endif + + return false; +} + typedef bool (*check_reserved_t)(u64 start, u64 end, enum e820_type type); static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, struct pci_mmcfg_region *cfg, - struct device *dev, int with_e820) + struct device *dev, const char *method) { u64 addr = cfg->res.start; u64 size = resource_size(&cfg->res); u64 old_size = size; int num_buses; - char *method = with_e820 ? "E820" : "ACPI motherboard resources"; while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) { size >>= 1; @@ -464,10 +490,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, return false; if (dev) - dev_info(dev, "MMCONFIG at %pR reserved in %s\n", + dev_info(dev, "MMCONFIG at %pR reserved as %s\n", &cfg->res, method); else - pr_info(PREFIX "MMCONFIG at %pR reserved in %s\n", + pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n", &cfg->res, method); if (old_size != size) { @@ -500,7 +526,8 @@ static bool __ref pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early) { if (!early && !acpi_disabled) { - if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0)) + if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, + "ACPI motherboard resource")) return true; if (dev) @@ -513,6 +540,10 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e "MMCONFIG at %pR not reserved in " "ACPI motherboard resources\n", &cfg->res); + + if (is_mmconf_reserved(is_efi_mmio, cfg, dev, + "EfiMemoryMappedIO")) + return true; } /* @@ -527,7 +558,8 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e /* Don't try to do this check unless configuration type 1 is available. how about type 2 ?*/ if (raw_pci_ops) - return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1); + return is_mmconf_reserved(e820__mapped_all, cfg, dev, + "E820 entry"); return false; } diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index b94f727251b6..8babce71915f 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -392,6 +392,7 @@ static void xen_teardown_msi_irqs(struct pci_dev *dev) msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) { for (i = 0; i < msidesc->nvec_used; i++) xen_destroy_irq(msidesc->irq + i); + msidesc->irq = 0; } } @@ -433,6 +434,7 @@ static struct msi_domain_ops xen_pci_msi_domain_ops = { }; static struct msi_domain_info xen_pci_msi_domain_info = { + .flags = MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS, .ops = &xen_pci_msi_domain_ops, }; diff --git a/arch/x86/um/elfcore.c b/arch/x86/um/elfcore.c index 48a3eb09d951..650cdbbdaf45 100644 --- a/arch/x86/um/elfcore.c +++ b/arch/x86/um/elfcore.c @@ -7,7 +7,7 @@ #include <asm/elf.h> -Elf32_Half elf_core_extra_phdrs(void) +Elf32_Half elf_core_extra_phdrs(struct coredump_params *cprm) { return vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0; } @@ -60,7 +60,7 @@ int elf_core_write_extra_data(struct coredump_params *cprm) return 1; } -size_t elf_core_extra_data_size(void) +size_t elf_core_extra_data_size(struct coredump_params *cprm) { if ( vsyscall_ehdr ) { const struct elfhdr *const ehdrp = diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58db86f7b384..9bdc3b656b2c 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -134,11 +134,6 @@ static inline unsigned p2m_mid_index(unsigned long pfn) return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE; } -static inline unsigned p2m_index(unsigned long pfn) -{ - return pfn % P2M_PER_PAGE; -} - static void p2m_top_mfn_init(unsigned long *top) { unsigned i; diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h index 228e4dff5fb2..a6d09fe04831 100644 --- a/arch/xtensa/include/asm/processor.h +++ b/arch/xtensa/include/asm/processor.h @@ -154,11 +154,6 @@ struct thread_struct { unsigned long ra; /* kernel's a0: return address and window call size */ unsigned long sp; /* kernel's a1: stack pointer */ - /* struct xtensa_cpuinfo info; */ - - unsigned long bad_vaddr; /* last user fault */ - unsigned long bad_uaddr; /* last kernel fault accessing user space */ - unsigned long error_code; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct perf_event *ptrace_bp[XCHAL_NUM_IBREAK]; struct perf_event *ptrace_wp[XCHAL_NUM_DBREAK]; @@ -176,10 +171,6 @@ struct thread_struct { { \ ra: 0, \ sp: sizeof(init_stack) + (long) &init_stack, \ - /*info: {0}, */ \ - bad_vaddr: 0, \ - bad_uaddr: 0, \ - error_code: 0, \ } diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 0c25e035ff10..cd98366a9b23 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -362,8 +362,6 @@ static void do_unaligned_user(struct pt_regs *regs) __die_if_kernel("Unhandled unaligned exception in kernel", regs, SIGKILL); - current->thread.bad_vaddr = regs->excvaddr; - current->thread.error_code = -3; pr_info_ratelimited("Unaligned memory access to %08lx in '%s' " "(pid = %d, pc = %#010lx)\n", regs->excvaddr, current->comm, diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index 8c781b05c0bd..faf7cf35a0ee 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -206,8 +206,6 @@ good_area: bad_area: mmap_read_unlock(mm); if (user_mode(regs)) { - current->thread.bad_vaddr = address; - current->thread.error_code = is_write; force_sig_fault(SIGSEGV, code, (void *) address); return; } @@ -232,7 +230,6 @@ do_sigbus: /* Send a sigbus, regardless of whether we were in kernel * or user mode. */ - current->thread.bad_vaddr = address; force_sig_fault(SIGBUS, BUS_ADRERR, (void *) address); /* Kernel mode? Handle exceptions or die */ @@ -252,7 +249,6 @@ bad_page_fault(struct pt_regs *regs, unsigned long address, int sig) if ((entry = search_exception_tables(regs->pc)) != NULL) { pr_debug("%s: Exception at pc=%#010lx (%lx)\n", current->comm, regs->pc, entry->fixup); - current->thread.bad_uaddr = address; regs->pc = entry->fixup; return; } diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 1b2829e99dad..0fbde0fc0628 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -316,14 +316,12 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq) static void bfqg_get(struct bfq_group *bfqg) { - bfqg->ref++; + refcount_inc(&bfqg->ref); } static void bfqg_put(struct bfq_group *bfqg) { - bfqg->ref--; - - if (bfqg->ref == 0) + if (refcount_dec_and_test(&bfqg->ref)) kfree(bfqg); } @@ -530,7 +528,7 @@ static struct blkg_policy_data *bfq_pd_alloc(gfp_t gfp, struct request_queue *q, } /* see comments in bfq_bic_update_cgroup for why refcounting */ - bfqg_get(bfqg); + refcount_set(&bfqg->ref, 1); return &bfqg->pd; } @@ -771,8 +769,8 @@ static void __bfq_bic_change_cgroup(struct bfq_data *bfqd, * request from the old cgroup. */ bfq_put_cooperator(sync_bfqq); - bfq_release_process_ref(bfqd, sync_bfqq); bic_set_bfqq(bic, NULL, true); + bfq_release_process_ref(bfqd, sync_bfqq); } } } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index ccf2204477a5..380e9bda2e57 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5425,9 +5425,11 @@ static void bfq_check_ioprio_change(struct bfq_io_cq *bic, struct bio *bio) bfqq = bic_to_bfqq(bic, false); if (bfqq) { - bfq_release_process_ref(bfqd, bfqq); + struct bfq_queue *old_bfqq = bfqq; + bfqq = bfq_get_queue(bfqd, bio, false, bic, true); bic_set_bfqq(bic, bfqq, false); + bfq_release_process_ref(bfqd, old_bfqq); } bfqq = bic_to_bfqq(bic, true); diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index 41aa151ccc22..466e4865ace6 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -928,7 +928,7 @@ struct bfq_group { char blkg_path[128]; /* reference counter (see comments in bfq_bic_update_cgroup) */ - int ref; + refcount_t ref; /* Is bfq_group still online? */ bool online; diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index ce6a2b7d3dfb..9ac1efb053e0 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1455,6 +1455,10 @@ retry: list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) pol->pd_init_fn(blkg->pd[pol->plid]); + if (pol->pd_online_fn) + list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) + pol->pd_online_fn(blkg->pd[pol->plid]); + __set_bit(pol->plid, q->blkcg_pols); ret = 0; @@ -1997,6 +2001,10 @@ void blk_cgroup_bio_start(struct bio *bio) struct blkg_iostat_set *bis; unsigned long flags; + /* Root-level stats are sourced from system-wide IO stats */ + if (!cgroup_parent(blkcg->css.cgroup)) + return; + cpu = get_cpu(); bis = per_cpu_ptr(bio->bi_blkg->iostat_cpu, cpu); flags = u64_stats_update_begin_irqsave(&bis->sync); diff --git a/block/blk-core.c b/block/blk-core.c index 9321767470dc..b5098355d8b2 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -283,12 +283,9 @@ static void blk_free_queue(struct request_queue *q) * * Decrements the refcount of the request_queue and free it when the refcount * reaches 0. - * - * Context: Can sleep. */ void blk_put_queue(struct request_queue *q) { - might_sleep(); if (refcount_dec_and_test(&q->refs)) blk_free_queue(q); } diff --git a/block/blk-mq.c b/block/blk-mq.c index 2c49b4151da1..9c8dc70020bc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2890,6 +2890,7 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, struct blk_plug *plug, struct bio **bio, unsigned int nsegs) { struct request *rq; + enum hctx_type type, hctx_type; if (!plug) return NULL; @@ -2902,7 +2903,10 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, return NULL; } - if (blk_mq_get_hctx_type((*bio)->bi_opf) != rq->mq_hctx->type) + type = blk_mq_get_hctx_type((*bio)->bi_opf); + hctx_type = rq->mq_hctx->type; + if (type != hctx_type && + !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT)) return NULL; if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf)) return NULL; @@ -4065,8 +4069,9 @@ EXPORT_SYMBOL(blk_mq_init_queue); * blk_mq_destroy_queue - shutdown a request queue * @q: request queue to shutdown * - * This shuts down a request queue allocated by blk_mq_init_queue() and drops - * the initial reference. All future requests will failed with -ENODEV. + * This shuts down a request queue allocated by blk_mq_init_queue(). All future + * requests will be failed with -ENODEV. The caller is responsible for dropping + * the reference from blk_mq_init_queue() by calling blk_put_queue(). * * Context: can sleep */ diff --git a/certs/Makefile b/certs/Makefile index 9486ed924731..799ad7b9e68a 100644 --- a/certs/Makefile +++ b/certs/Makefile @@ -23,8 +23,8 @@ $(obj)/blacklist_hash_list: $(CONFIG_SYSTEM_BLACKLIST_HASH_LIST) FORCE targets += blacklist_hash_list quiet_cmd_extract_certs = CERT $@ - cmd_extract_certs = $(obj)/extract-cert $(extract-cert-in) $@ -extract-cert-in = $(or $(filter-out $(obj)/extract-cert, $(real-prereqs)),"") + cmd_extract_certs = $(obj)/extract-cert "$(extract-cert-in)" $@ +extract-cert-in = $(filter-out $(obj)/extract-cert, $(real-prereqs)) $(obj)/system_certificates.o: $(obj)/x509_certificate_list diff --git a/drivers/accessibility/speakup/spk_ttyio.c b/drivers/accessibility/speakup/spk_ttyio.c index 08cf8a17754b..07373b3debd1 100644 --- a/drivers/accessibility/speakup/spk_ttyio.c +++ b/drivers/accessibility/speakup/spk_ttyio.c @@ -354,6 +354,9 @@ void spk_ttyio_release(struct spk_synth *in_synth) { struct tty_struct *tty = in_synth->dev; + if (tty == NULL) + return; + tty_lock(tty); if (tty->ops->close) diff --git a/drivers/acpi/glue.c b/drivers/acpi/glue.c index 204fe94c7e45..a194f30876c5 100644 --- a/drivers/acpi/glue.c +++ b/drivers/acpi/glue.c @@ -75,7 +75,8 @@ static struct acpi_bus_type *acpi_get_bus_type(struct device *dev) } #define FIND_CHILD_MIN_SCORE 1 -#define FIND_CHILD_MAX_SCORE 2 +#define FIND_CHILD_MID_SCORE 2 +#define FIND_CHILD_MAX_SCORE 3 static int match_any(struct acpi_device *adev, void *not_used) { @@ -96,8 +97,17 @@ static int find_child_checks(struct acpi_device *adev, bool check_children) return -ENODEV; status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta); - if (status == AE_NOT_FOUND) + if (status == AE_NOT_FOUND) { + /* + * Special case: backlight device objects without _STA are + * preferred to other objects with the same _ADR value, because + * it is more likely that they are actually useful. + */ + if (adev->pnp.type.backlight) + return FIND_CHILD_MID_SCORE; + return FIND_CHILD_MIN_SCORE; + } if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED)) return -ENODEV; diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c index 998101cf16e4..3d4c4620f9f9 100644 --- a/drivers/acpi/prmt.c +++ b/drivers/acpi/prmt.c @@ -236,6 +236,11 @@ static acpi_status acpi_platformrt_space_handler(u32 function, efi_status_t status; struct prm_context_buffer context; + if (!efi_enabled(EFI_RUNTIME_SERVICES)) { + pr_err_ratelimited("PRM: EFI runtime services no longer available\n"); + return AE_NO_HANDLER; + } + /* * The returned acpi_status will always be AE_OK. Error values will be * saved in the first byte of the PRM message buffer to be used by ASL. @@ -325,6 +330,11 @@ void __init init_prmt(void) pr_info("PRM: found %u modules\n", mc); + if (!efi_enabled(EFI_RUNTIME_SERVICES)) { + pr_err("PRM: EFI runtime services unavailable\n"); + return; + } + status = acpi_install_address_space_handler(ACPI_ROOT_OBJECT, ACPI_ADR_SPACE_PLATFORM_RT, &acpi_platformrt_space_handler, diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 16dcd31d124f..192d1784e409 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -433,6 +433,13 @@ static const struct dmi_system_id asus_laptop[] = { }, }, { + .ident = "Asus ExpertBook B2402CBA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "B2402CBA"), + }, + }, + { .ident = "Asus ExpertBook B2502", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c index 274344434282..0c6f06abe3f4 100644 --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -1370,9 +1370,12 @@ static void acpi_set_pnp_ids(acpi_handle handle, struct acpi_device_pnp *pnp, * Some devices don't reliably have _HIDs & _CIDs, so add * synthetic HIDs to make sure drivers can find them. */ - if (acpi_is_video_device(handle)) + if (acpi_is_video_device(handle)) { acpi_add_id(pnp, ACPI_VIDEO_HID); - else if (acpi_bay_match(handle)) + pnp->type.backlight = 1; + break; + } + if (acpi_bay_match(handle)) acpi_add_id(pnp, ACPI_BAY_HID); else if (acpi_dock_match(handle)) acpi_add_id(pnp, ACPI_DOCK_HID); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 0b557c0d405e..4ca667251272 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -60,13 +60,17 @@ static struct notifier_block tts_notifier = { .priority = 0, }; +#ifndef acpi_skip_set_wakeup_address +#define acpi_skip_set_wakeup_address() false +#endif + static int acpi_sleep_prepare(u32 acpi_state) { #ifdef CONFIG_ACPI_SLEEP unsigned long acpi_wakeup_address; /* do we have a wakeup address for S2 and S3? */ - if (acpi_state == ACPI_STATE_S3) { + if (acpi_state == ACPI_STATE_S3 && !acpi_skip_set_wakeup_address()) { acpi_wakeup_address = acpi_get_wakeup_address(); if (!acpi_wakeup_address) return -EFAULT; diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 1b78c7434492..a8c02608dde4 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -50,6 +50,10 @@ static void acpi_video_parse_cmdline(void) acpi_backlight_cmdline = acpi_backlight_video; if (!strcmp("native", acpi_video_backlight_string)) acpi_backlight_cmdline = acpi_backlight_native; + if (!strcmp("nvidia_wmi_ec", acpi_video_backlight_string)) + acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec; + if (!strcmp("apple_gmux", acpi_video_backlight_string)) + acpi_backlight_cmdline = acpi_backlight_apple_gmux; if (!strcmp("none", acpi_video_backlight_string)) acpi_backlight_cmdline = acpi_backlight_none; } @@ -106,26 +110,6 @@ static bool nvidia_wmi_ec_supported(void) } #endif -static bool apple_gmux_backlight_present(void) -{ - struct acpi_device *adev; - struct device *dev; - - adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1); - if (!adev) - return false; - - dev = acpi_get_first_physical_node(adev); - if (!dev) - return false; - - /* - * drivers/platform/x86/apple-gmux.c only supports old style - * Apple GMUX with an IO-resource. - */ - return pnp_get_resource(to_pnp_dev(dev), IORESOURCE_IO, 0) != NULL; -} - /* Force to use vendor driver when the ACPI device is known to be * buggy */ static int video_detect_force_vendor(const struct dmi_system_id *d) @@ -513,6 +497,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, + /* Acer Aspire 4810T */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Aspire 4810T"), + }, + }, + { + .callback = video_detect_force_native, /* Acer Aspire 5738z */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Acer"), @@ -600,6 +592,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, + /* Asus U46E */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "U46E"), + }, + }, + { + .callback = video_detect_force_native, /* Asus UX303UB */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), @@ -608,6 +608,23 @@ static const struct dmi_system_id video_detect_dmi_table[] = { }, { .callback = video_detect_force_native, + /* HP EliteBook 8460p */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 8460p"), + }, + }, + { + .callback = video_detect_force_native, + /* HP Pavilion g6-1d80nr / B4U19UA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion g6 Notebook PC"), + DMI_MATCH(DMI_PRODUCT_SKU, "B4U19UA"), + }, + }, + { + .callback = video_detect_force_native, /* Samsung N150P */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), @@ -754,6 +771,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) { static DEFINE_MUTEX(init_mutex); static bool nvidia_wmi_ec_present; + static bool apple_gmux_present; static bool native_available; static bool init_done; static long video_caps; @@ -767,6 +785,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) ACPI_UINT32_MAX, find_video, NULL, &video_caps, NULL); nvidia_wmi_ec_present = nvidia_wmi_ec_supported(); + apple_gmux_present = apple_gmux_detect(NULL, NULL); init_done = true; } if (native) @@ -788,7 +807,7 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native) if (nvidia_wmi_ec_present) return acpi_backlight_nvidia_wmi_ec; - if (apple_gmux_backlight_present()) + if (apple_gmux_present) return acpi_backlight_apple_gmux; /* Use ACPI video if available, except when native should be preferred. */ diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index eceaec33af65..9695c4404e26 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -640,6 +640,7 @@ config PATA_CS5530 config PATA_CS5535 tristate "CS5535 PATA support (Experimental)" depends on PCI && (X86_32 || (X86_64 && COMPILE_TEST)) + depends on !UML help This option enables support for the NatSemi/AMD CS5535 companion chip used with the Geode processor family. diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 884ae73b11ea..2ea572628b1c 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -3109,7 +3109,7 @@ int sata_down_spd_limit(struct ata_link *link, u32 spd_limit) */ if (spd > 1) mask &= (1 << (spd - 1)) - 1; - else + else if (link->sata_spd) return -EINVAL; /* were we already at the bottom? */ diff --git a/drivers/base/property.c b/drivers/base/property.c index bbb3e499ff4a..083a95791d3b 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -997,26 +997,32 @@ struct fwnode_handle * fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { + struct fwnode_handle *ep, *port_parent = NULL; const struct fwnode_handle *parent; - struct fwnode_handle *ep; /* * If this function is in a loop and the previous iteration returned * an endpoint from fwnode->secondary, then we need to use the secondary * as parent rather than @fwnode. */ - if (prev) - parent = fwnode_graph_get_port_parent(prev); - else + if (prev) { + port_parent = fwnode_graph_get_port_parent(prev); + parent = port_parent; + } else { parent = fwnode; + } if (IS_ERR_OR_NULL(parent)) return NULL; ep = fwnode_call_ptr_op(parent, graph_get_next_endpoint, prev); if (ep) - return ep; + goto out_put_port_parent; + + ep = fwnode_graph_get_next_endpoint(parent->secondary, NULL); - return fwnode_graph_get_next_endpoint(parent->secondary, NULL); +out_put_port_parent: + fwnode_handle_put(port_parent); + return ep; } EXPORT_SYMBOL_GPL(fwnode_graph_get_next_endpoint); diff --git a/drivers/base/test/test_async_driver_probe.c b/drivers/base/test/test_async_driver_probe.c index 4d1976ca5072..929410d0dd6f 100644 --- a/drivers/base/test/test_async_driver_probe.c +++ b/drivers/base/test/test_async_driver_probe.c @@ -145,7 +145,7 @@ static int __init test_async_probe_init(void) calltime = ktime_get(); for_each_online_cpu(cpu) { nid = cpu_to_node(cpu); - pdev = &sync_dev[sync_id]; + pdev = &async_dev[async_id]; *pdev = test_platform_device_register_node("test_async_driver", async_id, diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 4cea3b08087e..2f1a92509271 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2400,6 +2400,8 @@ static void pkt_submit_bio(struct bio *bio) struct bio *split; bio = bio_split_to_limits(bio); + if (!bio) + return; pkt_dbg(2, pd, "start = %6llx stop = %6llx\n", (unsigned long long)bio->bi_iter.bi_sector, diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 78334da74d8b..5eb8c7855970 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1440,7 +1440,7 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, goto out_alloc; } - ret = ida_alloc_max(&index_ida, 1 << (MINORBITS - RNBD_PART_BITS), + ret = ida_alloc_max(&index_ida, (1 << (MINORBITS - RNBD_PART_BITS)) - 1, GFP_KERNEL); if (ret < 0) { pr_err("Failed to initialize device '%s' from session %s, allocating idr failed, err: %d\n", diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 17b677b5d3b2..6368b56eacf1 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -137,7 +137,7 @@ struct ublk_device { char *__queues; - unsigned short queue_size; + unsigned int queue_size; struct ublksrv_ctrl_dev_info dev_info; struct blk_mq_tag_set tag_set; @@ -2092,13 +2092,12 @@ static void __exit ublk_exit(void) struct ublk_device *ub; int id; - class_destroy(ublk_chr_class); - - misc_deregister(&ublk_misc); - idr_for_each_entry(&ublk_index_idr, ub, id) ublk_remove(ub); + class_destroy(ublk_chr_class); + misc_deregister(&ublk_misc); + idr_destroy(&ublk_index_idr); unregister_chrdev_region(ublk_chr_devt, UBLK_MINORS); } diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index c0227dfa4688..4807af1d5805 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -524,7 +524,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, return 0; } -static int xen_blkbk_remove(struct xenbus_device *dev) +static void xen_blkbk_remove(struct xenbus_device *dev) { struct backend_info *be = dev_get_drvdata(&dev->dev); @@ -547,8 +547,6 @@ static int xen_blkbk_remove(struct xenbus_device *dev) /* Put the reference we set in xen_blkif_alloc(). */ xen_blkif_put(be->blkif); } - - return 0; } int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt, diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index b28489290323..23ed258b57f0 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2467,7 +2467,7 @@ static void blkback_changed(struct xenbus_device *dev, } } -static int blkfront_remove(struct xenbus_device *xbdev) +static void blkfront_remove(struct xenbus_device *xbdev) { struct blkfront_info *info = dev_get_drvdata(&xbdev->dev); @@ -2488,7 +2488,6 @@ static int blkfront_remove(struct xenbus_device *xbdev) } kfree(info); - return 0; } static int blkfront_is_ready(struct xenbus_device *dev) diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 6eddc23e49d9..bbe9cf1cae27 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -2164,10 +2164,17 @@ static void qca_serdev_shutdown(struct device *dev) int timeout = msecs_to_jiffies(CMD_TRANS_TIMEOUT_MS); struct serdev_device *serdev = to_serdev_device(dev); struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev); + struct hci_uart *hu = &qcadev->serdev_hu; + struct hci_dev *hdev = hu->hdev; + struct qca_data *qca = hu->priv; const u8 ibs_wake_cmd[] = { 0xFD }; const u8 edl_reset_soc_cmd[] = { 0x01, 0x00, 0xFC, 0x01, 0x05 }; if (qcadev->btsoc_type == QCA_QCA6390) { + if (test_bit(QCA_BT_OFF, &qca->flags) || + !test_bit(HCI_RUNNING, &hdev->flags)) + return; + serdev_device_write_flush(serdev); ret = serdev_device_write_buf(serdev, ibs_wake_cmd, sizeof(ibs_wake_cmd)); diff --git a/drivers/bus/sunxi-rsb.c b/drivers/bus/sunxi-rsb.c index 3aa91aed3bf7..226e87b85116 100644 --- a/drivers/bus/sunxi-rsb.c +++ b/drivers/bus/sunxi-rsb.c @@ -857,7 +857,13 @@ static int __init sunxi_rsb_init(void) return ret; } - return platform_driver_register(&sunxi_rsb_driver); + ret = platform_driver_register(&sunxi_rsb_driver); + if (ret) { + bus_unregister(&sunxi_rsb_bus); + return ret; + } + + return 0; } module_init(sunxi_rsb_init); diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c index 379291826261..80cca3b83b22 100644 --- a/drivers/char/tpm/xen-tpmfront.c +++ b/drivers/char/tpm/xen-tpmfront.c @@ -360,14 +360,13 @@ static int tpmfront_probe(struct xenbus_device *dev, return tpm_chip_register(priv->chip); } -static int tpmfront_remove(struct xenbus_device *dev) +static void tpmfront_remove(struct xenbus_device *dev) { struct tpm_chip *chip = dev_get_drvdata(&dev->dev); struct tpm_private *priv = dev_get_drvdata(&chip->dev); tpm_chip_unregister(chip); ring_free(priv); dev_set_drvdata(&chip->dev, NULL); - return 0; } static int tpmfront_resume(struct xenbus_device *dev) diff --git a/drivers/comedi/drivers/adv_pci1760.c b/drivers/comedi/drivers/adv_pci1760.c index fcfc2e299110..27f3890f471d 100644 --- a/drivers/comedi/drivers/adv_pci1760.c +++ b/drivers/comedi/drivers/adv_pci1760.c @@ -58,7 +58,7 @@ #define PCI1760_CMD_CLR_IMB2 0x00 /* Clears IMB2 */ #define PCI1760_CMD_SET_DO 0x01 /* Set output state */ #define PCI1760_CMD_GET_DO 0x02 /* Read output status */ -#define PCI1760_CMD_GET_STATUS 0x03 /* Read current status */ +#define PCI1760_CMD_GET_STATUS 0x07 /* Read current status */ #define PCI1760_CMD_GET_FW_VER 0x0e /* Read firmware version */ #define PCI1760_CMD_GET_HW_VER 0x0f /* Read hardware version */ #define PCI1760_CMD_SET_PWM_HI(x) (0x10 + (x) * 2) /* Set "hi" period */ diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index 204e39006dda..c17bd845f5fc 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -307,6 +307,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu, max_perf = min_perf; amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true); + cpufreq_cpu_put(policy); } static int amd_get_min_freq(struct amd_cpudata *cpudata) diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c index d1801281cdd9..c11d22fd84c3 100644 --- a/drivers/cpufreq/apple-soc-cpufreq.c +++ b/drivers/cpufreq/apple-soc-cpufreq.c @@ -280,6 +280,7 @@ static int apple_soc_cpufreq_init(struct cpufreq_policy *policy) policy->cpuinfo.transition_latency = transition_latency; policy->dvfs_possible_from_any_cpu = true; policy->fast_switch_possible = true; + policy->suspend_freq = freq_table[0].frequency; if (policy_has_boost_freq(policy)) { ret = cpufreq_enable_boost_support(); @@ -321,7 +322,6 @@ static struct cpufreq_driver apple_soc_cpufreq_driver = { .flags = CPUFREQ_HAVE_GOVERNOR_PER_POLICY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV, .verify = cpufreq_generic_frequency_table_verify, - .attr = cpufreq_generic_attr, .get = apple_soc_cpufreq_get_rate, .init = apple_soc_cpufreq_init, .exit = apple_soc_cpufreq_exit, @@ -329,6 +329,7 @@ static struct cpufreq_driver apple_soc_cpufreq_driver = { .fast_switch = apple_soc_cpufreq_fast_switch, .register_em = cpufreq_register_em_with_opp, .attr = apple_soc_cpufreq_hw_attr, + .suspend = cpufreq_generic_suspend, }; static int __init apple_soc_cpufreq_module_init(void) diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c index c10fc33b29b1..b74289a95a17 100644 --- a/drivers/cpufreq/armada-37xx-cpufreq.c +++ b/drivers/cpufreq/armada-37xx-cpufreq.c @@ -445,7 +445,7 @@ static int __init armada37xx_cpufreq_driver_init(void) return -ENODEV; } - clk = clk_get(cpu_dev, 0); + clk = clk_get(cpu_dev, NULL); if (IS_ERR(clk)) { dev_err(cpu_dev, "Cannot get clock for CPU0\n"); return PTR_ERR(clk); diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 432dfb4e8027..022e3555407c 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -487,7 +487,8 @@ static unsigned int get_perf_level_count(struct cpufreq_policy *policy) cpu_data = policy->driver_data; perf_caps = &cpu_data->perf_caps; max_cap = arch_scale_cpu_capacity(cpu); - min_cap = div_u64(max_cap * perf_caps->lowest_perf, perf_caps->highest_perf); + min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf, + perf_caps->highest_perf); if ((min_cap == 0) || (max_cap < min_cap)) return 0; return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP; @@ -519,10 +520,10 @@ static int cppc_get_cpu_power(struct device *cpu_dev, cpu_data = policy->driver_data; perf_caps = &cpu_data->perf_caps; max_cap = arch_scale_cpu_capacity(cpu_dev->id); - min_cap = div_u64(max_cap * perf_caps->lowest_perf, - perf_caps->highest_perf); - - perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap; + min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf, + perf_caps->highest_perf); + perf_step = div_u64((u64)CPPC_EM_CAP_STEP * perf_caps->highest_perf, + max_cap); min_step = min_cap / CPPC_EM_CAP_STEP; max_step = max_cap / CPPC_EM_CAP_STEP; diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c index 8ab672883043..e85703651098 100644 --- a/drivers/cpufreq/cpufreq-dt-platdev.c +++ b/drivers/cpufreq/cpufreq-dt-platdev.c @@ -137,6 +137,7 @@ static const struct of_device_id blocklist[] __initconst = { { .compatible = "nvidia,tegra30", }, { .compatible = "nvidia,tegra124", }, { .compatible = "nvidia,tegra210", }, + { .compatible = "nvidia,tegra234", }, { .compatible = "qcom,apq8096", }, { .compatible = "qcom,msm8996", }, @@ -150,6 +151,7 @@ static const struct of_device_id blocklist[] __initconst = { { .compatible = "qcom,sdm845", }, { .compatible = "qcom,sm6115", }, { .compatible = "qcom,sm6350", }, + { .compatible = "qcom,sm6375", }, { .compatible = "qcom,sm8150", }, { .compatible = "qcom,sm8250", }, { .compatible = "qcom,sm8350", }, diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c index 340fed35e45d..9505a812d6a1 100644 --- a/drivers/cpufreq/qcom-cpufreq-hw.c +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -649,9 +649,10 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) { struct clk_hw_onecell_data *clk_data; struct device *dev = &pdev->dev; + struct device_node *soc_node; struct device *cpu_dev; struct clk *clk; - int ret, i, num_domains; + int ret, i, num_domains, reg_sz; clk = clk_get(dev, "xo"); if (IS_ERR(clk)) @@ -679,7 +680,21 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) return ret; /* Allocate qcom_cpufreq_data based on the available frequency domains in DT */ - num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * 4); + soc_node = of_get_parent(dev->of_node); + if (!soc_node) + return -EINVAL; + + ret = of_property_read_u32(soc_node, "#address-cells", ®_sz); + if (ret) + goto of_exit; + + ret = of_property_read_u32(soc_node, "#size-cells", &i); + if (ret) + goto of_exit; + + reg_sz += i; + + num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * reg_sz); if (num_domains <= 0) return num_domains; @@ -743,6 +758,9 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) else dev_dbg(dev, "QCOM CPUFreq HW driver initialized\n"); +of_exit: + of_node_put(soc_node); + return ret; } diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c index 53100fb9b07b..12205e2b53b4 100644 --- a/drivers/crypto/atmel-ecc.c +++ b/drivers/crypto/atmel-ecc.c @@ -3,7 +3,7 @@ * Microchip / Atmel ECC (I2C) driver. * * Copyright (c) 2017, Microchip Technology Inc. - * Author: Tudor Ambarus <tudor.ambarus@microchip.com> + * Author: Tudor Ambarus */ #include <linux/delay.h> @@ -411,6 +411,6 @@ static void __exit atmel_ecc_exit(void) module_init(atmel_ecc_init); module_exit(atmel_ecc_exit); -MODULE_AUTHOR("Tudor Ambarus <tudor.ambarus@microchip.com>"); +MODULE_AUTHOR("Tudor Ambarus"); MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/crypto/atmel-i2c.c b/drivers/crypto/atmel-i2c.c index 81ce09bedda8..55bff1e13142 100644 --- a/drivers/crypto/atmel-i2c.c +++ b/drivers/crypto/atmel-i2c.c @@ -3,7 +3,7 @@ * Microchip / Atmel ECC (I2C) driver. * * Copyright (c) 2017, Microchip Technology Inc. - * Author: Tudor Ambarus <tudor.ambarus@microchip.com> + * Author: Tudor Ambarus */ #include <linux/bitrev.h> @@ -390,6 +390,6 @@ static void __exit atmel_i2c_exit(void) module_init(atmel_i2c_init); module_exit(atmel_i2c_exit); -MODULE_AUTHOR("Tudor Ambarus <tudor.ambarus@microchip.com>"); +MODULE_AUTHOR("Tudor Ambarus"); MODULE_DESCRIPTION("Microchip / Atmel ECC (I2C) driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/crypto/atmel-i2c.h b/drivers/crypto/atmel-i2c.h index 48929efe2a5b..35f7857a7f7c 100644 --- a/drivers/crypto/atmel-i2c.h +++ b/drivers/crypto/atmel-i2c.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2017, Microchip Technology Inc. - * Author: Tudor Ambarus <tudor.ambarus@microchip.com> + * Author: Tudor Ambarus */ #ifndef __ATMEL_I2C_H__ diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index ad0849af42d7..13cde44c6086 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -736,4 +736,3 @@ module_exit(cxl_acpi_exit); MODULE_LICENSE("GPL v2"); MODULE_IMPORT_NS(CXL); MODULE_IMPORT_NS(ACPI); -MODULE_SOFTDEP("pre: cxl_pmem"); diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index f3d2169b6731..c2e4b1093788 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -227,34 +227,16 @@ static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_nvdimm_bridge *cxl_nvb, return cxl_nvd; } -static void cxl_nvd_unregister(void *_cxl_nvd) +static void cxlmd_release_nvdimm(void *_cxlmd) { - struct cxl_nvdimm *cxl_nvd = _cxl_nvd; - struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_memdev *cxlmd = _cxlmd; + struct cxl_nvdimm *cxl_nvd = cxlmd->cxl_nvd; struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb; - /* - * Either the bridge is in ->remove() context under the device_lock(), - * or cxlmd_release_nvdimm() is cancelling the bridge's release action - * for @cxl_nvd and doing it itself (while manually holding the bridge - * lock). - */ - device_lock_assert(&cxl_nvb->dev); cxl_nvd->cxlmd = NULL; cxlmd->cxl_nvd = NULL; + cxlmd->cxl_nvb = NULL; device_unregister(&cxl_nvd->dev); -} - -static void cxlmd_release_nvdimm(void *_cxlmd) -{ - struct cxl_memdev *cxlmd = _cxlmd; - struct cxl_nvdimm_bridge *cxl_nvb = cxlmd->cxl_nvb; - - device_lock(&cxl_nvb->dev); - if (cxlmd->cxl_nvd) - devm_release_action(&cxl_nvb->dev, cxl_nvd_unregister, - cxlmd->cxl_nvd); - device_unlock(&cxl_nvb->dev); put_device(&cxl_nvb->dev); } @@ -293,22 +275,6 @@ int devm_cxl_add_nvdimm(struct cxl_memdev *cxlmd) dev_dbg(&cxlmd->dev, "register %s\n", dev_name(dev)); - /* - * The two actions below arrange for @cxl_nvd to be deleted when either - * the top-level PMEM bridge goes down, or the endpoint device goes - * through ->remove(). - */ - device_lock(&cxl_nvb->dev); - if (cxl_nvb->dev.driver) - rc = devm_add_action_or_reset(&cxl_nvb->dev, cxl_nvd_unregister, - cxl_nvd); - else - rc = -ENXIO; - device_unlock(&cxl_nvb->dev); - - if (rc) - goto err_alloc; - /* @cxlmd carries a reference on @cxl_nvb until cxlmd_release_nvdimm */ return devm_add_action_or_reset(&cxlmd->dev, cxlmd_release_nvdimm, cxlmd); diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index 33083a522fd1..258004f34281 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -554,8 +554,11 @@ static bool cxl_report_and_clear(struct cxl_dev_state *cxlds) /* If multiple errors, log header points to first error from ctrl reg */ if (hweight32(status) > 1) { - addr = cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET; - fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, readl(addr))); + void __iomem *rcc_addr = + cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET; + + fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, + readl(rcc_addr))); } else { fe = status; } diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index eedefebc4283..08bbbac9a6d0 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -225,11 +225,35 @@ static int cxl_pmem_ctl(struct nvdimm_bus_descriptor *nd_desc, return cxl_pmem_nvdimm_ctl(nvdimm, cmd, buf, buf_len); } +static int detach_nvdimm(struct device *dev, void *data) +{ + struct cxl_nvdimm *cxl_nvd; + bool release = false; + + if (!is_cxl_nvdimm(dev)) + return 0; + + device_lock(dev); + if (!dev->driver) + goto out; + + cxl_nvd = to_cxl_nvdimm(dev); + if (cxl_nvd->cxlmd && cxl_nvd->cxlmd->cxl_nvb == data) + release = true; +out: + device_unlock(dev); + if (release) + device_release_driver(dev); + return 0; +} + static void unregister_nvdimm_bus(void *_cxl_nvb) { struct cxl_nvdimm_bridge *cxl_nvb = _cxl_nvb; struct nvdimm_bus *nvdimm_bus = cxl_nvb->nvdimm_bus; + bus_for_each_dev(&cxl_bus_type, NULL, cxl_nvb, detach_nvdimm); + cxl_nvb->nvdimm_bus = NULL; nvdimm_bus_unregister(nvdimm_bus); } diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index 406b4e26f538..0de0482cd36e 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -167,7 +167,7 @@ struct dma_fence *dma_fence_allocate_private_stub(void) 0, 0); set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, - &dma_fence_stub.flags); + &fence->flags); dma_fence_signal(fence); diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c index c741b6431958..8a6e6b60d66f 100644 --- a/drivers/dma/dmaengine.c +++ b/drivers/dma/dmaengine.c @@ -451,7 +451,8 @@ static int dma_chan_get(struct dma_chan *chan) /* The channel is already in use, update client count */ if (chan->client_count) { __module_get(owner); - goto out; + chan->client_count++; + return 0; } if (!try_module_get(owner)) @@ -470,11 +471,11 @@ static int dma_chan_get(struct dma_chan *chan) goto err_out; } + chan->client_count++; + if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask)) balance_ref_count(chan); -out: - chan->client_count++; return 0; err_out: diff --git a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c index a183d93bd7e2..bf85aa0979ec 100644 --- a/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c +++ b/drivers/dma/dw-axi-dmac/dw-axi-dmac-platform.c @@ -1018,6 +1018,11 @@ static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status) /* The bad descriptor currently is in the head of vc list */ vd = vchan_next_desc(&chan->vc); + if (!vd) { + dev_err(chan2dev(chan), "BUG: %s, IRQ with no descriptors\n", + axi_chan_name(chan)); + goto out; + } /* Remove the completed descriptor from issued list */ list_del(&vd->node); @@ -1032,6 +1037,7 @@ static noinline void axi_chan_handle_err(struct axi_dma_chan *chan, u32 status) /* Try to restart the controller */ axi_chan_start_first_queued(chan); +out: spin_unlock_irqrestore(&chan->vc.lock, flags); } diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 06f5d3783d77..29dbb0f52e18 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -1172,8 +1172,19 @@ static void idxd_flush_pending_descs(struct idxd_irq_entry *ie) spin_unlock(&ie->list_lock); list_for_each_entry_safe(desc, itr, &flist, list) { + struct dma_async_tx_descriptor *tx; + list_del(&desc->list); ctype = desc->completion->status ? IDXD_COMPLETE_NORMAL : IDXD_COMPLETE_ABORT; + /* + * wq is being disabled. Any remaining descriptors are + * likely to be stuck and can be dropped. callback could + * point to code that is no longer accessible, for example + * if dmatest module has been unloaded. + */ + tx = &desc->txd; + tx->callback = NULL; + tx->callback_result = NULL; idxd_dma_complete_txd(desc, ctype, true); } } @@ -1390,8 +1401,7 @@ err_res_alloc: err_irq: idxd_wq_unmap_portal(wq); err_map_portal: - rc = idxd_wq_disable(wq, false); - if (rc < 0) + if (idxd_wq_disable(wq, false)) dev_dbg(dev, "wq %s disable failed\n", dev_name(wq_confdev(wq))); err: return rc; @@ -1408,11 +1418,11 @@ void drv_disable_wq(struct idxd_wq *wq) dev_warn(dev, "Clients has claim on wq %d: %d\n", wq->id, idxd_wq_refcount(wq)); - idxd_wq_free_resources(wq); idxd_wq_unmap_portal(wq); idxd_wq_drain(wq); idxd_wq_free_irq(wq); idxd_wq_reset(wq); + idxd_wq_free_resources(wq); percpu_ref_exit(&wq->wq_active); wq->type = IDXD_WQT_NONE; wq->client_count = 0; diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c index fbea5f62dd98..b926abe4fa43 100644 --- a/drivers/dma/imx-sdma.c +++ b/drivers/dma/imx-sdma.c @@ -1521,10 +1521,12 @@ static struct sdma_desc *sdma_transfer_init(struct sdma_channel *sdmac, sdma_config_ownership(sdmac, false, true, false); if (sdma_load_context(sdmac)) - goto err_desc_out; + goto err_bd_out; return desc; +err_bd_out: + sdma_free_bd(desc); err_desc_out: kfree(desc); err_out: diff --git a/drivers/dma/lgm/lgm-dma.c b/drivers/dma/lgm/lgm-dma.c index 9b9184f964be..1709d159af7e 100644 --- a/drivers/dma/lgm/lgm-dma.c +++ b/drivers/dma/lgm/lgm-dma.c @@ -914,7 +914,7 @@ static void ldma_dev_init(struct ldma_dev *d) } } -static int ldma_cfg_init(struct ldma_dev *d) +static int ldma_parse_dt(struct ldma_dev *d) { struct fwnode_handle *fwnode = dev_fwnode(d->dev); struct ldma_port *p; @@ -1661,10 +1661,6 @@ static int intel_ldma_probe(struct platform_device *pdev) p->ldev = d; } - ret = ldma_cfg_init(d); - if (ret) - return ret; - dma_dev->dev = &pdev->dev; ch_mask = (unsigned long)d->channels_mask; @@ -1675,6 +1671,10 @@ static int intel_ldma_probe(struct platform_device *pdev) ldma_dma_init_v3X(j, d); } + ret = ldma_parse_dt(d); + if (ret) + return ret; + dma_dev->device_alloc_chan_resources = ldma_alloc_chan_resources; dma_dev->device_free_chan_resources = ldma_free_chan_resources; dma_dev->device_terminate_all = ldma_terminate_all; diff --git a/drivers/dma/ptdma/ptdma-dev.c b/drivers/dma/ptdma/ptdma-dev.c index 377da23012ac..a2bf13ff18b6 100644 --- a/drivers/dma/ptdma/ptdma-dev.c +++ b/drivers/dma/ptdma/ptdma-dev.c @@ -71,12 +71,13 @@ static int pt_core_execute_cmd(struct ptdma_desc *desc, struct pt_cmd_queue *cmd bool soc = FIELD_GET(DWORD0_SOC, desc->dw0); u8 *q_desc = (u8 *)&cmd_q->qbase[cmd_q->qidx]; u32 tail; + unsigned long flags; if (soc) { desc->dw0 |= FIELD_PREP(DWORD0_IOC, desc->dw0); desc->dw0 &= ~DWORD0_SOC; } - mutex_lock(&cmd_q->q_mutex); + spin_lock_irqsave(&cmd_q->q_lock, flags); /* Copy 32-byte command descriptor to hw queue. */ memcpy(q_desc, desc, 32); @@ -91,7 +92,7 @@ static int pt_core_execute_cmd(struct ptdma_desc *desc, struct pt_cmd_queue *cmd /* Turn the queue back on using our cached control register */ pt_start_queue(cmd_q); - mutex_unlock(&cmd_q->q_mutex); + spin_unlock_irqrestore(&cmd_q->q_lock, flags); return 0; } @@ -199,7 +200,7 @@ int pt_core_init(struct pt_device *pt) cmd_q->pt = pt; cmd_q->dma_pool = dma_pool; - mutex_init(&cmd_q->q_mutex); + spin_lock_init(&cmd_q->q_lock); /* Page alignment satisfies our needs for N <= 128 */ cmd_q->qsize = Q_SIZE(Q_DESC_SIZE); diff --git a/drivers/dma/ptdma/ptdma.h b/drivers/dma/ptdma/ptdma.h index d093c43b7d13..21b4bf895200 100644 --- a/drivers/dma/ptdma/ptdma.h +++ b/drivers/dma/ptdma/ptdma.h @@ -196,7 +196,7 @@ struct pt_cmd_queue { struct ptdma_desc *qbase; /* Aligned queue start address (per requirement) */ - struct mutex q_mutex ____cacheline_aligned; + spinlock_t q_lock ____cacheline_aligned; unsigned int qidx; unsigned int qsize; diff --git a/drivers/dma/qcom/gpi.c b/drivers/dma/qcom/gpi.c index 061add832295..59a36cbf9b5f 100644 --- a/drivers/dma/qcom/gpi.c +++ b/drivers/dma/qcom/gpi.c @@ -1756,6 +1756,7 @@ static int gpi_create_spi_tre(struct gchan *chan, struct gpi_desc *desc, tre->dword[3] = u32_encode_bits(TRE_TYPE_GO, TRE_FLAGS_TYPE); if (spi->cmd == SPI_RX) { tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_IEOB); + tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_LINK); } else if (spi->cmd == SPI_TX) { tre->dword[3] |= u32_encode_bits(1, TRE_FLAGS_CHAIN); } else { /* SPI_DUPLEX */ diff --git a/drivers/dma/tegra186-gpc-dma.c b/drivers/dma/tegra186-gpc-dma.c index 1d1180db6d4e..8f67f453a492 100644 --- a/drivers/dma/tegra186-gpc-dma.c +++ b/drivers/dma/tegra186-gpc-dma.c @@ -711,6 +711,7 @@ static int tegra_dma_terminate_all(struct dma_chan *dc) return err; } + vchan_terminate_vdesc(&tdc->dma_desc->vd); tegra_dma_disable(tdc); tdc->dma_desc = NULL; } diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c index ae39b52012b2..79da93cc77b6 100644 --- a/drivers/dma/tegra210-adma.c +++ b/drivers/dma/tegra210-adma.c @@ -221,7 +221,7 @@ static int tegra_adma_init(struct tegra_adma *tdma) int ret; /* Clear any interrupts */ - tdma_write(tdma, tdma->cdata->global_int_clear, 0x1); + tdma_write(tdma, tdma->cdata->ch_base_offset + tdma->cdata->global_int_clear, 0x1); /* Assert soft reset */ tdma_write(tdma, ADMA_GLOBAL_SOFT_RESET, 0x1); diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index ce8b80bb34d7..4c62274e0b33 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -762,11 +762,12 @@ static void udma_decrement_byte_counters(struct udma_chan *uc, u32 val) if (uc->desc->dir == DMA_DEV_TO_MEM) { udma_rchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val); udma_rchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val); - udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val); + if (uc->config.ep_type != PSIL_EP_NATIVE) + udma_rchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val); } else { udma_tchanrt_write(uc, UDMA_CHAN_RT_BCNT_REG, val); udma_tchanrt_write(uc, UDMA_CHAN_RT_SBCNT_REG, val); - if (!uc->bchan) + if (!uc->bchan && uc->config.ep_type != PSIL_EP_NATIVE) udma_tchanrt_write(uc, UDMA_CHAN_RT_PEER_BCNT_REG, val); } } diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c index a8d23cdf883e..ac09f0e5f58d 100644 --- a/drivers/dma/xilinx/xilinx_dma.c +++ b/drivers/dma/xilinx/xilinx_dma.c @@ -3143,8 +3143,10 @@ static int xilinx_dma_probe(struct platform_device *pdev) /* Initialize the channels */ for_each_child_of_node(node, child) { err = xilinx_dma_child_probe(xdev, child); - if (err < 0) + if (err < 0) { + of_node_put(child); goto error; + } } if (xdev->dma_config->dmatype == XDMA_TYPE_VDMA) { diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 19522c568aa5..0689e1510721 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -34,6 +34,9 @@ static DEFINE_MUTEX(device_ctls_mutex); static LIST_HEAD(edac_device_list); +/* Default workqueue processing interval on this instance, in msecs */ +#define DEFAULT_POLL_INTERVAL 1000 + #ifdef CONFIG_EDAC_DEBUG static void edac_device_dump_device(struct edac_device_ctl_info *edac_dev) { @@ -336,7 +339,7 @@ static void edac_device_workq_function(struct work_struct *work_req) * whole one second to save timers firing all over the period * between integral seconds */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_queue_work(&edac_dev->work, edac_dev->delay); @@ -366,7 +369,7 @@ static void edac_device_workq_setup(struct edac_device_ctl_info *edac_dev, * timers firing on sub-second basis, while they are happy * to fire together on the 1 second exactly */ - if (edac_dev->poll_msec == 1000) + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) edac_queue_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); else edac_queue_work(&edac_dev->work, edac_dev->delay); @@ -394,17 +397,16 @@ static void edac_device_workq_teardown(struct edac_device_ctl_info *edac_dev) * Then restart the workq on the new delay */ void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, - unsigned long value) + unsigned long msec) { - unsigned long jiffs = msecs_to_jiffies(value); - - if (value == 1000) - jiffs = round_jiffies_relative(value); - - edac_dev->poll_msec = value; - edac_dev->delay = jiffs; + edac_dev->poll_msec = msec; + edac_dev->delay = msecs_to_jiffies(msec); - edac_mod_work(&edac_dev->work, jiffs); + /* See comment in edac_device_workq_setup() above */ + if (edac_dev->poll_msec == DEFAULT_POLL_INTERVAL) + edac_mod_work(&edac_dev->work, round_jiffies_relative(edac_dev->delay)); + else + edac_mod_work(&edac_dev->work, edac_dev->delay); } int edac_device_alloc_index(void) @@ -443,11 +445,7 @@ int edac_device_add_device(struct edac_device_ctl_info *edac_dev) /* This instance is NOW RUNNING */ edac_dev->op_state = OP_RUNNING_POLL; - /* - * enable workq processing on this instance, - * default = 1000 msec - */ - edac_device_workq_setup(edac_dev, 1000); + edac_device_workq_setup(edac_dev, edac_dev->poll_msec ?: DEFAULT_POLL_INTERVAL); } else { edac_dev->op_state = OP_RUNNING_INTERRUPT; } diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h index 763c076d96f2..47593afdc234 100644 --- a/drivers/edac/edac_module.h +++ b/drivers/edac/edac_module.h @@ -53,7 +53,7 @@ bool edac_stop_work(struct delayed_work *work); bool edac_mod_work(struct delayed_work *work, unsigned long delay); extern void edac_device_reset_delay_period(struct edac_device_ctl_info - *edac_dev, unsigned long value); + *edac_dev, unsigned long msec); extern void edac_mc_reset_delay_period(unsigned long value); /* diff --git a/drivers/edac/highbank_mc_edac.c b/drivers/edac/highbank_mc_edac.c index 61b76ec226af..19fba258ae10 100644 --- a/drivers/edac/highbank_mc_edac.c +++ b/drivers/edac/highbank_mc_edac.c @@ -174,8 +174,10 @@ static int highbank_mc_probe(struct platform_device *pdev) drvdata = mci->pvt_info; platform_set_drvdata(pdev, mci); - if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) - return -ENOMEM; + if (!devres_open_group(&pdev->dev, NULL, GFP_KERNEL)) { + res = -ENOMEM; + goto free; + } r = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!r) { @@ -243,6 +245,7 @@ err2: edac_mc_del_mc(&pdev->dev); err: devres_release_group(&pdev->dev, NULL); +free: edac_mc_free(mci); return res; } diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c index 97a27e42dd61..c45519f59dc1 100644 --- a/drivers/edac/qcom_edac.c +++ b/drivers/edac/qcom_edac.c @@ -252,7 +252,7 @@ clear: static int dump_syn_reg(struct edac_device_ctl_info *edev_ctl, int err_type, u32 bank) { - struct llcc_drv_data *drv = edev_ctl->pvt_info; + struct llcc_drv_data *drv = edev_ctl->dev->platform_data; int ret; ret = dump_syn_reg_values(drv, bank, err_type); @@ -289,7 +289,7 @@ static irqreturn_t llcc_ecc_irq_handler(int irq, void *edev_ctl) { struct edac_device_ctl_info *edac_dev_ctl = edev_ctl; - struct llcc_drv_data *drv = edac_dev_ctl->pvt_info; + struct llcc_drv_data *drv = edac_dev_ctl->dev->platform_data; irqreturn_t irq_rc = IRQ_NONE; u32 drp_error, trp_error, i; int ret; @@ -358,7 +358,6 @@ static int qcom_llcc_edac_probe(struct platform_device *pdev) edev_ctl->dev_name = dev_name(dev); edev_ctl->ctl_name = "llcc"; edev_ctl->panic_on_ue = LLCC_ERP_PANIC_ON_UE; - edev_ctl->pvt_info = llcc_driv_data; rc = edac_device_add_device(edev_ctl); if (rc) diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c index 9c89f7d53e99..958aa4662ccb 100644 --- a/drivers/firewire/core-cdev.c +++ b/drivers/firewire/core-cdev.c @@ -819,8 +819,10 @@ static int ioctl_send_response(struct client *client, union ioctl_arg *arg) r = container_of(resource, struct inbound_transaction_resource, resource); - if (is_fcp_request(r->request)) + if (is_fcp_request(r->request)) { + kfree(r->data); goto out; + } if (a->length != fw_get_response_length(r->request)) { ret = -EINVAL; diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index f818d00bb2c6..ffdad59ec81f 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -910,6 +910,8 @@ static int do_xfer(const struct scmi_protocol_handle *ph, xfer->hdr.protocol_id, xfer->hdr.seq, xfer->hdr.poll_completion); + /* Clear any stale status */ + xfer->hdr.status = SCMI_SUCCESS; xfer->state = SCMI_XFER_SENT_OK; /* * Even though spinlocking is not needed here since no race is possible diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c index 1dfe534b8518..87b4f4d35f06 100644 --- a/drivers/firmware/arm_scmi/shmem.c +++ b/drivers/firmware/arm_scmi/shmem.c @@ -81,10 +81,11 @@ u32 shmem_read_header(struct scmi_shared_mem __iomem *shmem) void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem, struct scmi_xfer *xfer) { + size_t len = ioread32(&shmem->length); + xfer->hdr.status = ioread32(shmem->msg_payload); /* Skip the length of header and status in shmem area i.e 8 bytes */ - xfer->rx.len = min_t(size_t, xfer->rx.len, - ioread32(&shmem->length) - 8); + xfer->rx.len = min_t(size_t, xfer->rx.len, len > 8 ? len - 8 : 0); /* Take a copy to the rx buffer.. */ memcpy_fromio(xfer->rx.buf, shmem->msg_payload + 4, xfer->rx.len); @@ -93,8 +94,10 @@ void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem, void shmem_fetch_notification(struct scmi_shared_mem __iomem *shmem, size_t max_len, struct scmi_xfer *xfer) { + size_t len = ioread32(&shmem->length); + /* Skip only the length of header in shmem area i.e 4 bytes */ - xfer->rx.len = min_t(size_t, max_len, ioread32(&shmem->length) - 4); + xfer->rx.len = min_t(size_t, max_len, len > 4 ? len - 4 : 0); /* Take a copy to the rx buffer.. */ memcpy_fromio(xfer->rx.buf, shmem->msg_payload, xfer->rx.len); diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c index 33c9b81a55cd..1db975c08896 100644 --- a/drivers/firmware/arm_scmi/virtio.c +++ b/drivers/firmware/arm_scmi/virtio.c @@ -160,7 +160,6 @@ static void scmi_vio_channel_cleanup_sync(struct scmi_vio_channel *vioch) } vioch->shutdown_done = &vioch_shutdown_done; - virtio_break_device(vioch->vqueue->vdev); if (!vioch->is_rx && vioch->deferred_tx_wq) /* Cannot be kicked anymore after this...*/ vioch->deferred_tx_wq = NULL; @@ -482,6 +481,12 @@ static int virtio_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_vio_channel *vioch = cinfo->transport_info; + /* + * Break device to inhibit further traffic flowing while shutting down + * the channels: doing it later holding vioch->lock creates unsafe + * locking dependency chains as reported by LOCKDEP. + */ + virtio_break_device(vioch->vqueue->vdev); scmi_vio_channel_cleanup_sync(vioch); scmi_free_channel(cinfo, data, id); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 09716eebe8ac..1e0b016fdc2b 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -394,8 +394,8 @@ static int __init efisubsys_init(void) efi_kobj = kobject_create_and_add("efi", firmware_kobj); if (!efi_kobj) { pr_err("efi: Firmware registration failed.\n"); - destroy_workqueue(efi_rts_wq); - return -ENOMEM; + error = -ENOMEM; + goto err_destroy_wq; } if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE | @@ -443,7 +443,10 @@ err_unregister: err_put: kobject_put(efi_kobj); efi_kobj = NULL; - destroy_workqueue(efi_rts_wq); +err_destroy_wq: + if (efi_rts_wq) + destroy_workqueue(efi_rts_wq); + return error; } @@ -1004,6 +1007,8 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) /* first try to find a slot in an existing linked list entry */ for (prsv = efi_memreserve_root->next; prsv; ) { rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB); + if (!rsv) + return -ENOMEM; index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size); if (index < rsv->size) { rsv->entry[index].base = addr; diff --git a/drivers/firmware/efi/memattr.c b/drivers/firmware/efi/memattr.c index 0a9aba5f9cef..f178b2984dfb 100644 --- a/drivers/firmware/efi/memattr.c +++ b/drivers/firmware/efi/memattr.c @@ -33,7 +33,7 @@ int __init efi_memattr_init(void) return -ENOMEM; } - if (tbl->version > 1) { + if (tbl->version > 2) { pr_warn("Unexpected EFI Memory Attributes table version %d\n", tbl->version); goto unmap; diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c index 7feee3d9c2bf..1fba4e09cdcf 100644 --- a/drivers/firmware/efi/runtime-wrappers.c +++ b/drivers/firmware/efi/runtime-wrappers.c @@ -62,6 +62,7 @@ struct efi_runtime_work efi_rts_work; \ if (!efi_enabled(EFI_RUNTIME_SERVICES)) { \ pr_warn_once("EFI Runtime Services are disabled!\n"); \ + efi_rts_work.status = EFI_DEVICE_ERROR; \ goto exit; \ } \ \ diff --git a/drivers/firmware/google/coreboot_table.c b/drivers/firmware/google/coreboot_table.c index 2652c396c423..33ae94745aef 100644 --- a/drivers/firmware/google/coreboot_table.c +++ b/drivers/firmware/google/coreboot_table.c @@ -93,14 +93,19 @@ static int coreboot_table_populate(struct device *dev, void *ptr) for (i = 0; i < header->table_entries; i++) { entry = ptr_entry; - device = kzalloc(sizeof(struct device) + entry->size, GFP_KERNEL); + if (entry->size < sizeof(*entry)) { + dev_warn(dev, "coreboot table entry too small!\n"); + return -EINVAL; + } + + device = kzalloc(sizeof(device->dev) + entry->size, GFP_KERNEL); if (!device) return -ENOMEM; device->dev.parent = dev; device->dev.bus = &coreboot_bus_type; device->dev.release = coreboot_device_release; - memcpy(&device->entry, ptr_entry, entry->size); + memcpy(device->raw, ptr_entry, entry->size); switch (device->entry.tag) { case LB_TAG_CBMEM_ENTRY: diff --git a/drivers/firmware/google/coreboot_table.h b/drivers/firmware/google/coreboot_table.h index 37f4d335a606..d814dca33a08 100644 --- a/drivers/firmware/google/coreboot_table.h +++ b/drivers/firmware/google/coreboot_table.h @@ -79,6 +79,7 @@ struct coreboot_device { struct lb_cbmem_ref cbmem_ref; struct lb_cbmem_entry cbmem_entry; struct lb_framebuffer framebuffer; + DECLARE_FLEX_ARRAY(u8, raw); }; }; diff --git a/drivers/firmware/google/gsmi.c b/drivers/firmware/google/gsmi.c index 4e2575dfeb90..871bedf533a8 100644 --- a/drivers/firmware/google/gsmi.c +++ b/drivers/firmware/google/gsmi.c @@ -361,9 +361,10 @@ static efi_status_t gsmi_get_variable(efi_char16_t *name, memcpy(data, gsmi_dev.data_buf->start, *data_size); /* All variables are have the following attributes */ - *attr = EFI_VARIABLE_NON_VOLATILE | - EFI_VARIABLE_BOOTSERVICE_ACCESS | - EFI_VARIABLE_RUNTIME_ACCESS; + if (attr) + *attr = EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS; } spin_unlock_irqrestore(&gsmi_dev.lock, flags); diff --git a/drivers/firmware/psci/psci.c b/drivers/firmware/psci/psci.c index e7bcfca4159f..447ee4ea5c90 100644 --- a/drivers/firmware/psci/psci.c +++ b/drivers/firmware/psci/psci.c @@ -440,6 +440,9 @@ static const struct file_operations psci_debugfs_ops = { static int __init psci_debugfs_init(void) { + if (!invoke_psci_fn || !psci_ops.get_version) + return 0; + return PTR_ERR_OR_ZERO(debugfs_create_file("psci", 0444, NULL, NULL, &psci_debugfs_ops)); } diff --git a/drivers/fpga/intel-m10-bmc-sec-update.c b/drivers/fpga/intel-m10-bmc-sec-update.c index 79d48852825e..03f1bd81c434 100644 --- a/drivers/fpga/intel-m10-bmc-sec-update.c +++ b/drivers/fpga/intel-m10-bmc-sec-update.c @@ -574,20 +574,27 @@ static int m10bmc_sec_probe(struct platform_device *pdev) len = scnprintf(buf, SEC_UPDATE_LEN_MAX, "secure-update%d", sec->fw_name_id); sec->fw_name = kmemdup_nul(buf, len, GFP_KERNEL); - if (!sec->fw_name) - return -ENOMEM; + if (!sec->fw_name) { + ret = -ENOMEM; + goto fw_name_fail; + } fwl = firmware_upload_register(THIS_MODULE, sec->dev, sec->fw_name, &m10bmc_ops, sec); if (IS_ERR(fwl)) { dev_err(sec->dev, "Firmware Upload driver failed to start\n"); - kfree(sec->fw_name); - xa_erase(&fw_upload_xa, sec->fw_name_id); - return PTR_ERR(fwl); + ret = PTR_ERR(fwl); + goto fw_uploader_fail; } sec->fwl = fwl; return 0; + +fw_uploader_fail: + kfree(sec->fw_name); +fw_name_fail: + xa_erase(&fw_upload_xa, sec->fw_name_id); + return ret; } static int m10bmc_sec_remove(struct platform_device *pdev) diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index 357cea58ec98..f7f01982a512 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -213,9 +213,9 @@ static int s10_ops_write_init(struct fpga_manager *mgr, /* Allocate buffers from the service layer's pool. */ for (i = 0; i < NUM_SVC_BUFS; i++) { kbuf = stratix10_svc_allocate_memory(priv->chan, SVC_BUF_SIZE); - if (!kbuf) { + if (IS_ERR(kbuf)) { s10_free_buffers(mgr); - ret = -ENOMEM; + ret = PTR_ERR(kbuf); goto init_done; } diff --git a/drivers/gpio/gpio-ep93xx.c b/drivers/gpio/gpio-ep93xx.c index 2e1779709113..6cedf46efec6 100644 --- a/drivers/gpio/gpio-ep93xx.c +++ b/drivers/gpio/gpio-ep93xx.c @@ -17,6 +17,7 @@ #include <linux/slab.h> #include <linux/gpio/driver.h> #include <linux/bitops.h> +#include <linux/seq_file.h> #define EP93XX_GPIO_F_INT_STATUS 0x5c #define EP93XX_GPIO_A_INT_STATUS 0xa0 @@ -40,7 +41,6 @@ #define EP93XX_GPIO_F_IRQ_BASE 80 struct ep93xx_gpio_irq_chip { - struct irq_chip ic; u8 irq_offset; u8 int_unmasked; u8 int_enabled; @@ -148,7 +148,7 @@ static void ep93xx_gpio_f_irq_handler(struct irq_desc *desc) */ struct irq_chip *irqchip = irq_desc_get_chip(desc); unsigned int irq = irq_desc_get_irq(desc); - int port_f_idx = ((irq + 1) & 7) ^ 4; /* {19..22,47..50} -> {0..7} */ + int port_f_idx = (irq & 7) ^ 4; /* {20..23,48..51} -> {0..7} */ int gpio_irq = EP93XX_GPIO_F_IRQ_BASE + port_f_idx; chained_irq_enter(irqchip, desc); @@ -185,6 +185,7 @@ static void ep93xx_gpio_irq_mask_ack(struct irq_data *d) ep93xx_gpio_update_int_params(epg, eic); writeb(port_mask, epg->base + eic->irq_offset + EP93XX_INT_EOI_OFFSET); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void ep93xx_gpio_irq_mask(struct irq_data *d) @@ -195,6 +196,7 @@ static void ep93xx_gpio_irq_mask(struct irq_data *d) eic->int_unmasked &= ~BIT(d->irq & 7); ep93xx_gpio_update_int_params(epg, eic); + gpiochip_disable_irq(gc, irqd_to_hwirq(d)); } static void ep93xx_gpio_irq_unmask(struct irq_data *d) @@ -203,6 +205,7 @@ static void ep93xx_gpio_irq_unmask(struct irq_data *d) struct ep93xx_gpio_irq_chip *eic = to_ep93xx_gpio_irq_chip(gc); struct ep93xx_gpio *epg = gpiochip_get_data(gc); + gpiochip_enable_irq(gc, irqd_to_hwirq(d)); eic->int_unmasked |= BIT(d->irq & 7); ep93xx_gpio_update_int_params(epg, eic); } @@ -320,15 +323,25 @@ static int ep93xx_gpio_set_config(struct gpio_chip *gc, unsigned offset, return 0; } -static void ep93xx_init_irq_chip(struct device *dev, struct irq_chip *ic) +static void ep93xx_irq_print_chip(struct irq_data *data, struct seq_file *p) { - ic->irq_ack = ep93xx_gpio_irq_ack; - ic->irq_mask_ack = ep93xx_gpio_irq_mask_ack; - ic->irq_mask = ep93xx_gpio_irq_mask; - ic->irq_unmask = ep93xx_gpio_irq_unmask; - ic->irq_set_type = ep93xx_gpio_irq_type; + struct gpio_chip *gc = irq_data_get_irq_chip_data(data); + + seq_printf(p, dev_name(gc->parent)); } +static const struct irq_chip gpio_eic_irq_chip = { + .name = "ep93xx-gpio-eic", + .irq_ack = ep93xx_gpio_irq_ack, + .irq_mask = ep93xx_gpio_irq_mask, + .irq_unmask = ep93xx_gpio_irq_unmask, + .irq_mask_ack = ep93xx_gpio_irq_mask_ack, + .irq_set_type = ep93xx_gpio_irq_type, + .irq_print_chip = ep93xx_irq_print_chip, + .flags = IRQCHIP_IMMUTABLE, + GPIOCHIP_IRQ_RESOURCE_HELPERS, +}; + static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc, struct platform_device *pdev, struct ep93xx_gpio *epg, @@ -350,8 +363,6 @@ static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc, girq = &gc->irq; if (bank->has_irq || bank->has_hierarchical_irq) { - struct irq_chip *ic; - gc->set_config = ep93xx_gpio_set_config; egc->eic = devm_kcalloc(dev, 1, sizeof(*egc->eic), @@ -359,12 +370,7 @@ static int ep93xx_gpio_add_bank(struct ep93xx_gpio_chip *egc, if (!egc->eic) return -ENOMEM; egc->eic->irq_offset = bank->irq; - ic = &egc->eic->ic; - ic->name = devm_kasprintf(dev, GFP_KERNEL, "gpio-irq-%s", bank->label); - if (!ic->name) - return -ENOMEM; - ep93xx_init_irq_chip(dev, ic); - girq->chip = ic; + gpio_irq_chip_set_chip(girq, &gpio_eic_irq_chip); } if (bank->has_irq) { diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c index d5626c572d24..9d0cec4b82a3 100644 --- a/drivers/gpio/gpio-mxc.c +++ b/drivers/gpio/gpio-mxc.c @@ -18,6 +18,7 @@ #include <linux/module.h> #include <linux/platform_device.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/syscore_ops.h> #include <linux/gpio/driver.h> #include <linux/of.h> @@ -159,6 +160,7 @@ static int gpio_set_irq_type(struct irq_data *d, u32 type) { struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d); struct mxc_gpio_port *port = gc->private; + unsigned long flags; u32 bit, val; u32 gpio_idx = d->hwirq; int edge; @@ -197,6 +199,8 @@ static int gpio_set_irq_type(struct irq_data *d, u32 type) return -EINVAL; } + raw_spin_lock_irqsave(&port->gc.bgpio_lock, flags); + if (GPIO_EDGE_SEL >= 0) { val = readl(port->base + GPIO_EDGE_SEL); if (edge == GPIO_INT_BOTH_EDGES) @@ -217,15 +221,20 @@ static int gpio_set_irq_type(struct irq_data *d, u32 type) writel(1 << gpio_idx, port->base + GPIO_ISR); port->pad_type[gpio_idx] = type; - return 0; + raw_spin_unlock_irqrestore(&port->gc.bgpio_lock, flags); + + return port->gc.direction_input(&port->gc, gpio_idx); } static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio) { void __iomem *reg = port->base; + unsigned long flags; u32 bit, val; int edge; + raw_spin_lock_irqsave(&port->gc.bgpio_lock, flags); + reg += GPIO_ICR1 + ((gpio & 0x10) >> 2); /* lower or upper register */ bit = gpio & 0xf; val = readl(reg); @@ -240,9 +249,12 @@ static void mxc_flip_edge(struct mxc_gpio_port *port, u32 gpio) } else { pr_err("mxc: invalid configuration for GPIO %d: %x\n", gpio, edge); - return; + goto unlock; } writel(val | (edge << (bit << 1)), reg); + +unlock: + raw_spin_unlock_irqrestore(&port->gc.bgpio_lock, flags); } /* handle 32 interrupts in one status register */ diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index bed0380c5136..17c53f484280 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -385,7 +385,7 @@ err: } static bool acpi_gpio_irq_is_wake(struct device *parent, - struct acpi_resource_gpio *agpio) + const struct acpi_resource_gpio *agpio) { unsigned int pin = agpio->pin_table[0]; @@ -778,7 +778,7 @@ static int acpi_populate_gpio_lookup(struct acpi_resource *ares, void *data) lookup->info.pin_config = agpio->pin_config; lookup->info.debounce = agpio->debounce_timeout; lookup->info.gpioint = gpioint; - lookup->info.wake_capable = agpio->wake_capable == ACPI_WAKE_CAPABLE; + lookup->info.wake_capable = acpi_gpio_irq_is_wake(&lookup->info.adev->dev, agpio); /* * Polarity and triggering are only specified for GpioInt @@ -1104,7 +1104,8 @@ int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, in dev_dbg(&adev->dev, "IRQ %d already in use\n", irq); } - if (wake_capable) + /* avoid suspend issues with GPIOs when systems are using S3 */ + if (wake_capable && acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) *wake_capable = info.wake_capable; return irq; @@ -1623,6 +1624,19 @@ static const struct dmi_system_id gpiolib_acpi_quirks[] __initconst = { .ignore_interrupt = "AMDI0030:00@18", }, }, + { + /* + * Spurious wakeups from TP_ATTN# pin + * Found in BIOS 1.7.8 + * https://gitlab.freedesktop.org/drm/amd/-/issues/1722#note_1720627 + */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_wake = "ELAN0415:00@9", + }, + }, {} /* Terminating entry */ }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index b15091d8310d..3b5c53712d31 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -2099,7 +2099,7 @@ int amdgpu_amdkfd_map_gtt_bo_to_gart(struct amdgpu_device *adev, struct amdgpu_b } amdgpu_amdkfd_remove_eviction_fence( - bo, bo->kfd_bo->process_info->eviction_fence); + bo, bo->vm_bo->vm->process_info->eviction_fence); amdgpu_bo_unreserve(bo); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 8516c814bc9b..7b5ce00f0602 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -61,6 +61,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, amdgpu_ctx_put(p->ctx); return -ECANCELED; } + + amdgpu_sync_create(&p->sync); return 0; } @@ -452,18 +454,6 @@ static int amdgpu_syncobj_lookup_and_add(struct amdgpu_cs_parser *p, } r = amdgpu_sync_fence(&p->sync, fence); - if (r) - goto error; - - /* - * When we have an explicit dependency it might be necessary to insert a - * pipeline sync to make sure that all caches etc are flushed and the - * next job actually sees the results from the previous one. - */ - if (fence->context == p->gang_leader->base.entity->fence_context) - r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence); - -error: dma_fence_put(fence); return r; } @@ -1188,10 +1178,19 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) { struct amdgpu_fpriv *fpriv = p->filp->driver_priv; + struct drm_gpu_scheduler *sched; struct amdgpu_bo_list_entry *e; + struct dma_fence *fence; unsigned int i; int r; + r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]); + if (r) { + if (r != -ERESTARTSYS) + DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n"); + return r; + } + list_for_each_entry(e, &p->validated, tv.head) { struct amdgpu_bo *bo = ttm_to_amdgpu_bo(e->tv.bo); struct dma_resv *resv = bo->tbo.base.resv; @@ -1211,10 +1210,24 @@ static int amdgpu_cs_sync_rings(struct amdgpu_cs_parser *p) return r; } - r = amdgpu_ctx_wait_prev_fence(p->ctx, p->entities[p->gang_leader_idx]); - if (r && r != -ERESTARTSYS) - DRM_ERROR("amdgpu_ctx_wait_prev_fence failed.\n"); - return r; + sched = p->gang_leader->base.entity->rq->sched; + while ((fence = amdgpu_sync_get_fence(&p->sync))) { + struct drm_sched_fence *s_fence = to_drm_sched_fence(fence); + + /* + * When we have an dependency it might be necessary to insert a + * pipeline sync to make sure that all caches etc are flushed and the + * next job actually sees the results from the previous one + * before we start executing on the same scheduler ring. + */ + if (!s_fence || s_fence->sched != sched) + continue; + + r = amdgpu_sync_fence(&p->gang_leader->explicit_sync, fence); + if (r) + return r; + } + return 0; } static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p) @@ -1254,9 +1267,12 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, continue; fence = &p->jobs[i]->base.s_fence->scheduled; + dma_fence_get(fence); r = drm_sched_job_add_dependency(&leader->base, fence); - if (r) + if (r) { + dma_fence_put(fence); goto error_cleanup; + } } if (p->gang_size > 1) { @@ -1344,6 +1360,7 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser) { unsigned i; + amdgpu_sync_free(&parser->sync); for (i = 0; i < parser->num_post_deps; i++) { drm_syncobj_put(parser->post_deps[i].syncobj); kfree(parser->post_deps[i].chain); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index afe6af9c0138..2f28a8c02f64 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -36,6 +36,7 @@ #include <generated/utsrelease.h> #include <linux/pci-p2pdma.h> +#include <drm/drm_aperture.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_fb_helper.h> #include <drm/drm_probe_helper.h> @@ -90,6 +91,8 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); #define AMDGPU_MAX_RETRY_LIMIT 2 #define AMDGPU_RETRY_SRIOV_RESET(r) ((r) == -EBUSY || (r) == -ETIMEDOUT || (r) == -EINVAL) +static const struct drm_driver amdgpu_kms_driver; + const char *amdgpu_asic_name[] = { "TAHITI", "PITCAIRN", @@ -3687,6 +3690,11 @@ int amdgpu_device_init(struct amdgpu_device *adev, if (r) return r; + /* Get rid of things like offb */ + r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver); + if (r) + return r; + /* Enable TMZ based on IP_VERSION */ amdgpu_gmc_tmz_set(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 1353ffd08988..cd4caaa29528 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -23,7 +23,6 @@ */ #include <drm/amdgpu_drm.h> -#include <drm/drm_aperture.h> #include <drm/drm_drv.h> #include <drm/drm_fbdev_generic.h> #include <drm/drm_gem.h> @@ -2122,11 +2121,6 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, } #endif - /* Get rid of things like offb */ - ret = drm_aperture_remove_conflicting_pci_framebuffers(pdev, &amdgpu_kms_driver); - if (ret) - return ret; - adev = devm_drm_dev_alloc(&pdev->dev, &amdgpu_kms_driver, typeof(*adev), ddev); if (IS_ERR(adev)) return PTR_ERR(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 23692e5d4d13..3380daf42da8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -156,6 +156,9 @@ static bool amdgpu_gfx_is_compute_multipipe_capable(struct amdgpu_device *adev) return amdgpu_compute_multipipe == 1; } + if (adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0)) + return true; + /* FIXME: spreading the queues across pipes causes perf regressions * on POLARIS11 compute workloads */ if (adev->asic_type == CHIP_POLARIS11) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index fcb711a11a5b..3f07b1a2ce47 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -497,6 +497,7 @@ void amdgpu_vmid_free_reserved(struct amdgpu_device *adev, !--id_mgr->reserved_use_count) { /* give the reserved ID back to normal round robin */ list_add(&id_mgr->reserved->list, &id_mgr->ids_lru); + id_mgr->reserved = NULL; } vm->reserved_vmid[vmhub] = false; mutex_unlock(&id_mgr->lock); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index 9e549923622b..c3d9d75143f4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -161,8 +161,14 @@ void amdgpu_job_free_resources(struct amdgpu_job *job) struct dma_fence *f; unsigned i; - /* use sched fence if available */ - f = job->base.s_fence ? &job->base.s_fence->finished : &job->hw_fence; + /* Check if any fences where initialized */ + if (job->base.s_fence && job->base.s_fence->finished.ops) + f = &job->base.s_fence->finished; + else if (job->hw_fence.ops) + f = &job->hw_fence; + else + f = NULL; + for (i = 0; i < job->num_ibs; ++i) amdgpu_ib_free(ring->adev, &job->ibs[i], f); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 4e684c2afc70..25a68d8888e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -470,8 +470,9 @@ static bool amdgpu_bo_validate_size(struct amdgpu_device *adev, return true; fail: - DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size, - man->size); + if (man) + DRM_DEBUG("BO size %lu > total memory in domain: %llu\n", size, + man->size); return false; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c index bac7976975bd..dcd8c066bc1f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c @@ -391,8 +391,10 @@ int amdgpu_sync_push_to_job(struct amdgpu_sync *sync, struct amdgpu_job *job) dma_fence_get(f); r = drm_sched_job_add_dependency(&job->base, f); - if (r) + if (r) { + dma_fence_put(f); return r; + } } return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index faa12146635c..9fa1d814508a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -882,7 +882,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev) kfree(rsv); list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) { - drm_buddy_free_list(&mgr->mm, &rsv->blocks); + drm_buddy_free_list(&mgr->mm, &rsv->allocated); kfree(rsv); } drm_buddy_fini(&mgr->mm); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index a56c6e106d00..66eb102cd88f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -790,8 +790,8 @@ static void gfx_v11_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, * zero here */ WARN_ON(simd != 0); - /* type 2 wave data */ - dst[(*no_fields)++] = 2; + /* type 3 wave data */ + dst[(*no_fields)++] = 3; dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_STATUS); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_LO); dst[(*no_fields)++] = wave_read_ind(adev, wave, ixSQ_WAVE_PC_HI); @@ -1287,10 +1287,8 @@ static int gfx_v11_0_sw_init(void *handle) switch (adev->ip_versions[GC_HWIP][0]) { case IP_VERSION(11, 0, 0): - case IP_VERSION(11, 0, 1): case IP_VERSION(11, 0, 2): case IP_VERSION(11, 0, 3): - case IP_VERSION(11, 0, 4): adev->gfx.me.num_me = 1; adev->gfx.me.num_pipe_per_me = 1; adev->gfx.me.num_queue_per_pipe = 1; @@ -1298,6 +1296,15 @@ static int gfx_v11_0_sw_init(void *handle) adev->gfx.mec.num_pipe_per_mec = 4; adev->gfx.mec.num_queue_per_pipe = 4; break; + case IP_VERSION(11, 0, 1): + case IP_VERSION(11, 0, 4): + adev->gfx.me.num_me = 1; + adev->gfx.me.num_pipe_per_me = 1; + adev->gfx.me.num_queue_per_pipe = 1; + adev->gfx.mec.num_mec = 1; + adev->gfx.mec.num_pipe_per_mec = 4; + adev->gfx.mec.num_queue_per_pipe = 4; + break; default: adev->gfx.me.num_me = 1; adev->gfx.me.num_pipe_per_me = 1; diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c index 95548c512f4f..077c53c6cc08 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c @@ -35,6 +35,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin"); static int imu_v11_0_init_microcode(struct amdgpu_device *adev) { diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 970b066b37bb..5dff79e8f301 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -40,6 +40,8 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_2_mes1.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes.bin"); MODULE_FIRMWARE("amdgpu/gc_11_0_3_mes1.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes.bin"); +MODULE_FIRMWARE("amdgpu/gc_11_0_4_mes1.bin"); static int mes_v11_0_hw_fini(void *handle); static int mes_v11_0_kiq_hw_init(struct amdgpu_device *adev); @@ -196,7 +198,6 @@ static int mes_v11_0_add_hw_queue(struct amdgpu_mes *mes, mes_add_queue_pkt.trap_handler_addr = input->tba_addr; mes_add_queue_pkt.tma_addr = input->tma_addr; mes_add_queue_pkt.is_kfd_process = input->is_kfd_process; - mes_add_queue_pkt.trap_en = 1; /* For KFD, gds_size is re-used for queue size (needed in MES for AQL queues) */ mes_add_queue_pkt.is_aql_queue = input->is_aql_queue; diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c index 15eb3658d70e..09fdcd20cb91 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v4_3.c @@ -337,7 +337,13 @@ const struct nbio_hdp_flush_reg nbio_v4_3_hdp_flush_reg = { static void nbio_v4_3_init_registers(struct amdgpu_device *adev) { - return; + if (adev->ip_versions[NBIO_HWIP][0] == IP_VERSION(4, 3, 0)) { + uint32_t data; + + data = RREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2); + data &= ~RCC_DEV0_EPF2_STRAP2__STRAP_NO_SOFT_RESET_DEV0_F2_MASK; + WREG32_SOC15(NBIO, 0, regRCC_DEV0_EPF2_STRAP2, data); + } } static u32 nbio_v4_3_get_rom_offset(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 5562670b7b52..9eff5f41df9d 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -640,7 +640,8 @@ static int soc21_common_early_init(void *handle) AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS | AMD_CG_SUPPORT_REPEATER_FGCG | - AMD_CG_SUPPORT_GFX_MGCG; + AMD_CG_SUPPORT_GFX_MGCG | + AMD_CG_SUPPORT_HDP_SD; adev->pg_flags = AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_JPEG; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index ecb4c3abc629..c06ada0844ba 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -200,7 +200,7 @@ static int add_queue_mes(struct device_queue_manager *dqm, struct queue *q, queue_input.wptr_addr = (uint64_t)q->properties.write_ptr; if (q->wptr_bo) { - wptr_addr_off = (uint64_t)q->properties.write_ptr - (uint64_t)q->wptr_bo->kfd_bo->va; + wptr_addr_off = (uint64_t)q->properties.write_ptr & (PAGE_SIZE - 1); queue_input.wptr_mc_addr = ((uint64_t)q->wptr_bo->tbo.resource->start << PAGE_SHIFT) + wptr_addr_off; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 814f99888ab1..b94d2c1422ad 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -570,6 +570,15 @@ svm_range_vram_node_new(struct amdgpu_device *adev, struct svm_range *prange, goto reserve_bo_failed; } + if (clear) { + r = amdgpu_bo_sync_wait(bo, AMDGPU_FENCE_OWNER_KFD, false); + if (r) { + pr_debug("failed %d to sync bo\n", r); + amdgpu_bo_unreserve(bo); + goto reserve_bo_failed; + } + } + r = dma_resv_reserve_fences(bo->tbo.base.resv, 1); if (r) { pr_debug("failed %d to reserve bo\n", r); 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 1b7f20a9d4ae..31bce529f685 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1503,8 +1503,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) case IP_VERSION(3, 0, 1): case IP_VERSION(3, 1, 2): case IP_VERSION(3, 1, 3): - case IP_VERSION(3, 1, 4): - case IP_VERSION(3, 1, 5): case IP_VERSION(3, 1, 6): init_data.flags.gpu_vm_support = true; break; @@ -1730,10 +1728,6 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev) adev->dm.vblank_control_workqueue = NULL; } - for (i = 0; i < adev->dm.display_indexes_num; i++) { - drm_encoder_cleanup(&adev->dm.mst_encoders[i].base); - } - amdgpu_dm_destroy_drm_device(&adev->dm); #if defined(CONFIG_DRM_AMD_SECURE_DISPLAY) @@ -4507,6 +4501,17 @@ DEVICE_ATTR_WO(s3_debug); static int dm_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + struct amdgpu_mode_info *mode_info = &adev->mode_info; + struct atom_context *ctx = mode_info->atom_context; + int index = GetIndexIntoMasterTable(DATA, Object_Header); + u16 data_offset; + + /* if there is no object header, skip DM */ + if (!amdgpu_atom_parse_data_header(ctx, index, NULL, NULL, NULL, &data_offset)) { + adev->harvest_ip_mask |= AMD_HARVEST_IP_DMU_MASK; + dev_info(adev->dev, "No object header, skipping DM\n"); + return -ENOENT; + } switch (adev->asic_type) { #if defined(CONFIG_DRM_AMD_DC_SI) @@ -5311,8 +5316,6 @@ static void fill_stream_properties_from_drm_display_mode( timing_out->aspect_ratio = get_aspect_ratio(mode_in); - stream->output_color_space = get_output_color_space(timing_out); - stream->out_transfer_func->type = TF_TYPE_PREDEFINED; stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB; if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) { @@ -5323,6 +5326,8 @@ static void fill_stream_properties_from_drm_display_mode( adjust_colour_depth_from_display_info(timing_out, info); } } + + stream->output_color_space = get_output_color_space(timing_out); } static void fill_audio_info(struct audio_info *audio_info, @@ -8887,6 +8892,13 @@ static int dm_update_crtc_state(struct amdgpu_display_manager *dm, if (!dm_old_crtc_state->stream) goto skip_modeset; + /* Unset freesync video if it was active before */ + if (dm_old_crtc_state->freesync_config.state == VRR_STATE_ACTIVE_FIXED) { + dm_new_crtc_state->freesync_config.state = VRR_STATE_INACTIVE; + dm_new_crtc_state->freesync_config.fixed_refresh_in_uhz = 0; + } + + /* Now check if we should set freesync video mode */ if (amdgpu_freesync_vid_mode && dm_new_crtc_state->stream && is_timing_unchanged_for_freesync(new_crtc_state, old_crtc_state)) { @@ -9503,6 +9515,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, bool lock_and_validation_needed = false; struct dm_crtc_state *dm_old_crtc_state, *dm_new_crtc_state; #if defined(CONFIG_DRM_AMD_DC_DCN) + struct drm_dp_mst_topology_mgr *mgr; + struct drm_dp_mst_topology_state *mst_state; struct dsc_mst_fairness_vars vars[MAX_PIPES]; #endif @@ -9530,8 +9544,8 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, goto fail; } - if (dm_old_con_state->abm_level != - dm_new_con_state->abm_level) + if (dm_old_con_state->abm_level != dm_new_con_state->abm_level || + dm_old_con_state->scaling != dm_new_con_state->scaling) new_crtc_state->connectors_changed = true; } @@ -9751,6 +9765,28 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, lock_and_validation_needed = true; } +#if defined(CONFIG_DRM_AMD_DC_DCN) + /* set the slot info for each mst_state based on the link encoding format */ + for_each_new_mst_mgr_in_state(state, mgr, mst_state, i) { + struct amdgpu_dm_connector *aconnector; + struct drm_connector *connector; + struct drm_connector_list_iter iter; + u8 link_coding_cap; + + drm_connector_list_iter_begin(dev, &iter); + drm_for_each_connector_iter(connector, &iter) { + if (connector->index == mst_state->mgr->conn_base_id) { + aconnector = to_amdgpu_dm_connector(connector); + link_coding_cap = dc_link_dp_mst_decide_link_encoding_format(aconnector->dc_link); + drm_dp_mst_update_slots(mst_state, link_coding_cap); + + break; + } + } + drm_connector_list_iter_end(&iter); + } +#endif + /** * Streams and planes are reset when there are changes that affect * bandwidth. Anything that affects bandwidth needs to go through diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index 6994c9a1ed85..5cff56bb8f56 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -120,23 +120,50 @@ enum dc_edid_status dm_helpers_parse_edid_caps( } static void -fill_dc_mst_payload_table_from_drm(struct drm_dp_mst_topology_state *mst_state, - struct amdgpu_dm_connector *aconnector, +fill_dc_mst_payload_table_from_drm(struct dc_link *link, + bool enable, + struct drm_dp_mst_atomic_payload *target_payload, struct dc_dp_mst_stream_allocation_table *table) { struct dc_dp_mst_stream_allocation_table new_table = { 0 }; struct dc_dp_mst_stream_allocation *sa; - struct drm_dp_mst_atomic_payload *payload; + struct link_mst_stream_allocation_table copy_of_link_table = + link->mst_stream_alloc_table; + + int i; + int current_hw_table_stream_cnt = copy_of_link_table.stream_count; + struct link_mst_stream_allocation *dc_alloc; + + /* TODO: refactor to set link->mst_stream_alloc_table directly if possible.*/ + if (enable) { + dc_alloc = + ©_of_link_table.stream_allocations[current_hw_table_stream_cnt]; + dc_alloc->vcp_id = target_payload->vcpi; + dc_alloc->slot_count = target_payload->time_slots; + } else { + for (i = 0; i < copy_of_link_table.stream_count; i++) { + dc_alloc = + ©_of_link_table.stream_allocations[i]; + + if (dc_alloc->vcp_id == target_payload->vcpi) { + dc_alloc->vcp_id = 0; + dc_alloc->slot_count = 0; + break; + } + } + ASSERT(i != copy_of_link_table.stream_count); + } /* Fill payload info*/ - list_for_each_entry(payload, &mst_state->payloads, next) { - if (payload->delete) - continue; - - sa = &new_table.stream_allocations[new_table.stream_count]; - sa->slot_count = payload->time_slots; - sa->vcp_id = payload->vcpi; - new_table.stream_count++; + for (i = 0; i < MAX_CONTROLLER_NUM; i++) { + dc_alloc = + ©_of_link_table.stream_allocations[i]; + if (dc_alloc->vcp_id > 0 && dc_alloc->slot_count > 0) { + sa = &new_table.stream_allocations[new_table.stream_count]; + sa->slot_count = dc_alloc->slot_count; + sa->vcp_id = dc_alloc->vcp_id; + new_table.stream_count++; + } } /* Overwrite the old table */ @@ -185,7 +212,7 @@ bool dm_helpers_dp_mst_write_payload_allocation_table( * AUX message. The sequence is slot 1-63 allocated sequence for each * stream. AMD ASIC stream slot allocation should follow the same * sequence. copy DRM MST allocation to dc */ - fill_dc_mst_payload_table_from_drm(mst_state, aconnector, proposed_table); + fill_dc_mst_payload_table_from_drm(stream->link, enable, payload, proposed_table); return true; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 1edf7385f8d8..abdbd4352f6f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -468,7 +468,6 @@ static const struct drm_connector_helper_funcs dm_dp_mst_connector_helper_funcs static void amdgpu_dm_encoder_destroy(struct drm_encoder *encoder) { drm_encoder_cleanup(encoder); - kfree(encoder); } static const struct drm_encoder_funcs amdgpu_dm_encoder_funcs = { @@ -904,11 +903,6 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state, if (IS_ERR(mst_state)) return PTR_ERR(mst_state); - mst_state->pbn_div = dm_mst_get_pbn_divider(dc_link); -#if defined(CONFIG_DRM_AMD_DC_DCN) - drm_dp_mst_update_slots(mst_state, dc_link_dp_mst_decide_link_encoding_format(dc_link)); -#endif - /* Set up params */ for (i = 0; i < dc_state->stream_count; i++) { struct dc_dsc_policy dsc_policy = {0}; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c index 471078fc3900..652270a0b498 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c @@ -90,8 +90,8 @@ static const struct out_csc_color_matrix_type output_csc_matrix[] = { { 0xE00, 0xF349, 0xFEB7, 0x1000, 0x6CE, 0x16E3, 0x24F, 0x200, 0xFCCB, 0xF535, 0xE00, 0x1000} }, { COLOR_SPACE_YCBCR2020_TYPE, - { 0x1000, 0xF149, 0xFEB7, 0x0000, 0x0868, 0x15B2, - 0x01E6, 0x0000, 0xFB88, 0xF478, 0x1000, 0x0000} }, + { 0x1000, 0xF149, 0xFEB7, 0x1004, 0x0868, 0x15B2, + 0x01E6, 0x201, 0xFB88, 0xF478, 0x1000, 0x1004} }, { COLOR_SPACE_YCBCR709_BLACK_TYPE, { 0x0000, 0x0000, 0x0000, 0x1000, 0x0000, 0x0000, 0x0000, 0x0200, 0x0000, 0x0000, 0x0000, 0x1000} }, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 342e906ae26e..c88f044666fe 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3995,10 +3995,13 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) struct fixed31_32 avg_time_slots_per_mtp = dc_fixpt_from_int(0); int i; bool mst_mode = (link->type == dc_connection_mst_branch); + /* adjust for drm changes*/ + bool update_drm_mst_state = true; const struct link_hwss *link_hwss = get_link_hwss(link, &pipe_ctx->link_res); const struct dc_link_settings empty_link_settings = {0}; DC_LOGGER_INIT(link->ctx->logger); + /* deallocate_mst_payload is called before disable link. When mode or * disable/enable monitor, new stream is created which is not in link * stream[] yet. For this, payload is not allocated yet, so de-alloc @@ -4014,7 +4017,7 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) &empty_link_settings, avg_time_slots_per_mtp); - if (mst_mode) { + if (mst_mode || update_drm_mst_state) { /* when link is in mst mode, reply on mst manager to remove * payload */ @@ -4077,11 +4080,18 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx) stream->ctx, stream); + if (!update_drm_mst_state) + dm_helpers_dp_mst_send_payload_allocation( + stream->ctx, + stream, + false); + } + + if (update_drm_mst_state) dm_helpers_dp_mst_send_payload_allocation( stream->ctx, stream, false); - } return DC_OK; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index f9ea1e86707f..79850a68f62a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -874,8 +874,9 @@ static const struct dc_plane_cap plane_cap = { }, // 6:1 downscaling ratio: 1000/6 = 166.666 + // 4:1 downscaling ratio for ARGB888 to prevent underflow during P010 playback: 1000/4 = 250 .max_downscale_factor = { - .argb8888 = 167, + .argb8888 = 250, .nv12 = 167, .fp16 = 167 }, @@ -1763,7 +1764,7 @@ static bool dcn314_resource_construct( pool->base.underlay_pipe_index = NO_UNDERLAY_PIPE; pool->base.pipe_count = pool->base.res_cap->num_timing_generator; pool->base.mpcc_count = pool->base.res_cap->num_timing_generator; - dc->caps.max_downscale_ratio = 600; + dc->caps.max_downscale_ratio = 400; dc->caps.i2c_speed_in_khz = 100; dc->caps.i2c_speed_in_khz_hdcp = 100; dc->caps.max_cursor_size = 256; diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c index dc4649458567..a4e9fd5307c6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_init.c @@ -94,7 +94,7 @@ static const struct hw_sequencer_funcs dcn32_funcs = { .get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync, .calc_vupdate_position = dcn10_calc_vupdate_position, .apply_idle_power_optimizations = dcn32_apply_idle_power_optimizations, - .does_plane_fit_in_mall = dcn30_does_plane_fit_in_mall, + .does_plane_fit_in_mall = NULL, .set_backlight_level = dcn21_set_backlight_level, .set_abm_immediate_disable = dcn21_set_abm_immediate_disable, .hardware_release = dcn30_hardware_release, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c index 950669f2c10d..cb7c0c878423 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/display_mode_vba_314.c @@ -3183,7 +3183,7 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman } else { v->MIN_DST_Y_NEXT_START[k] = v->VTotal[k] - v->VFrontPorch[k] + v->VTotal[k] - v->VActive[k] - v->VStartup[k]; } - v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / (double)v->HTotal[k] / v->PixelClock[k], 1.0) / 4.0; + v->MIN_DST_Y_NEXT_START[k] += dml_floor(4.0 * v->TSetup[k] / ((double)v->HTotal[k] / v->PixelClock[k]), 1.0) / 4.0; if (((v->VUpdateOffsetPix[k] + v->VUpdateWidthPix[k] + v->VReadyOffsetPix[k]) / v->HTotal[k]) <= (isInterlaceTiming ? dml_floor((v->VTotal[k] - v->VActive[k] - v->VFrontPorch[k] - v->VStartup[k]) / 2.0, 1.0) : diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 4a122925c3ae..92c18bfb98b3 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -532,6 +532,9 @@ enum dmub_status dmub_srv_hw_init(struct dmub_srv *dmub, if (dmub->hw_funcs.reset) dmub->hw_funcs.reset(dmub); + /* reset the cache of the last wptr as well now that hw is reset */ + dmub->inbox1_last_wptr = 0; + cw0.offset.quad_part = inst_fb->gpu_addr; cw0.region.base = DMUB_CW0_BASE; cw0.region.top = cw0.region.base + inst_fb->size - 1; @@ -649,6 +652,15 @@ enum dmub_status dmub_srv_hw_reset(struct dmub_srv *dmub) if (dmub->hw_funcs.reset) dmub->hw_funcs.reset(dmub); + /* mailboxes have been reset in hw, so reset the sw state as well */ + dmub->inbox1_last_wptr = 0; + dmub->inbox1_rb.wrpt = 0; + dmub->inbox1_rb.rptr = 0; + dmub->outbox0_rb.wrpt = 0; + dmub->outbox0_rb.rptr = 0; + dmub->outbox1_rb.wrpt = 0; + dmub->outbox1_rb.rptr = 0; + dmub->hw_init = false; return DMUB_STATUS_OK; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 236657eece47..a9170360d7e8 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -2007,14 +2007,16 @@ static int default_attr_update(struct amdgpu_device *adev, struct amdgpu_device_ gc_ver == IP_VERSION(10, 3, 0) || gc_ver == IP_VERSION(10, 1, 2) || gc_ver == IP_VERSION(11, 0, 0) || - gc_ver == IP_VERSION(11, 0, 2))) + gc_ver == IP_VERSION(11, 0, 2) || + gc_ver == IP_VERSION(11, 0, 3))) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_dpm_dclk)) { if (!(gc_ver == IP_VERSION(10, 3, 1) || gc_ver == IP_VERSION(10, 3, 0) || gc_ver == IP_VERSION(10, 1, 2) || gc_ver == IP_VERSION(11, 0, 0) || - gc_ver == IP_VERSION(11, 0, 2))) + gc_ver == IP_VERSION(11, 0, 2) || + gc_ver == IP_VERSION(11, 0, 3))) *states = ATTR_STATE_UNSUPPORTED; } else if (DEVICE_ATTR_IS(pp_power_profile_mode)) { if (amdgpu_dpm_get_power_profile_mode(adev, NULL) == -EOPNOTSUPP) diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index ca3beb5d8f27..6ab155023592 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1500,6 +1500,20 @@ static int smu_disable_dpms(struct smu_context *smu) } /* + * For SMU 13.0.4/11, PMFW will handle the features disablement properly + * for gpu reset case. Driver involvement is unnecessary. + */ + if (amdgpu_in_reset(adev)) { + switch (adev->ip_versions[MP1_HWIP][0]) { + case IP_VERSION(13, 0, 4): + case IP_VERSION(13, 0, 11): + return 0; + default: + break; + } + } + + /* * For gpu reset, runpm and hibernation through BACO, * BACO feature has to be kept enabled. */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index 85e22210963f..5cdc07165480 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -1171,6 +1171,7 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu, int ret = 0; uint32_t apu_percent = 0; uint32_t dgpu_percent = 0; + struct amdgpu_device *adev = smu->adev; ret = smu_cmn_get_metrics_table(smu, @@ -1196,7 +1197,11 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu, *value = metrics->AverageUvdActivity / 100; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = (metrics->CurrentSocketPower << 8) / 1000; + if (((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 1)) && (adev->pm.fw_version >= 0x40000f)) || + ((adev->ip_versions[MP1_HWIP][0] == IP_VERSION(12, 0, 0)) && (adev->pm.fw_version >= 0x373200))) + *value = metrics->CurrentSocketPower << 8; + else + *value = (metrics->CurrentSocketPower << 8) / 1000; break; case METRICS_TEMPERATURE_EDGE: *value = (metrics->GfxTemperature / 100) * diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index e54b760b875b..b4373b6568ae 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -1261,7 +1261,8 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu, uint32_t speed) { struct amdgpu_device *adev = smu->adev; - uint32_t tach_period, crystal_clock_freq; + uint32_t crystal_clock_freq = 2500; + uint32_t tach_period; int ret; if (!speed) @@ -1271,7 +1272,6 @@ int smu_v13_0_set_fan_speed_rpm(struct smu_context *smu, if (ret) return ret; - crystal_clock_freq = amdgpu_asic_get_xclk(adev); tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed); WREG32_SOC15(THM, 0, regCG_TACH_CTRL, REG_SET_FIELD(RREG32_SOC15(THM, 0, regCG_TACH_CTRL), @@ -2298,6 +2298,10 @@ bool smu_v13_0_baco_is_support(struct smu_context *smu) !smu_baco->platform_support) return false; + /* return true if ASIC is in BACO state already */ + if (smu_v13_0_baco_get_state(smu) == SMU_BACO_STATE_ENTER) + return true; + if (smu_cmn_feature_is_supported(smu, SMU_FEATURE_BACO_BIT) && !smu_cmn_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT)) return false; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 9643b21c636a..cf96c3f2affe 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -145,6 +145,7 @@ static struct cmn2asic_msg_mapping smu_v13_0_0_message_map[SMU_MSG_MAX_COUNT] = MSG_MAP(SetBadMemoryPagesRetiredFlagsPerChannel, PPSMC_MSG_SetBadMemoryPagesRetiredFlagsPerChannel, 0), MSG_MAP(AllowGpo, PPSMC_MSG_SetGpoAllow, 0), + MSG_MAP(AllowIHHostInterrupt, PPSMC_MSG_AllowIHHostInterrupt, 0), }; static struct cmn2asic_mapping smu_v13_0_0_clk_map[SMU_CLK_COUNT] = { @@ -213,6 +214,7 @@ static struct cmn2asic_mapping smu_v13_0_0_feature_mask_map[SMU_FEATURE_COUNT] = FEA_MAP(SOC_PCC), [SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, [SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, + [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT}, }; static struct cmn2asic_mapping smu_v13_0_0_table_map[SMU_TABLE_COUNT] = { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index 5c6c6ad011ca..e87db7e02e8a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -192,6 +192,7 @@ static struct cmn2asic_mapping smu_v13_0_7_feature_mask_map[SMU_FEATURE_COUNT] = FEA_MAP(SOC_PCC), [SMU_FEATURE_DPM_VCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, [SMU_FEATURE_DPM_DCLK_BIT] = {1, FEATURE_MM_DPM_BIT}, + [SMU_FEATURE_PPT_BIT] = {1, FEATURE_THROTTLERS_BIT}, }; static struct cmn2asic_mapping smu_v13_0_7_table_map[SMU_TABLE_COUNT] = { diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c index a2f0860b20bb..d751820c6da6 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi-i2s-audio.c @@ -193,6 +193,7 @@ static int snd_dw_hdmi_probe(struct platform_device *pdev) struct hdmi_codec_pdata pdata; struct platform_device *platform; + memset(&pdata, 0, sizeof(pdata)); pdata.ops = &dw_hdmi_i2s_ops; pdata.i2s = 1; pdata.max_i2s_channels = 8; diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 51a46689cda7..4ca37261584a 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -3372,6 +3372,9 @@ void drm_dp_remove_payload(struct drm_dp_mst_topology_mgr *mgr, mgr->payload_count--; mgr->next_start_slot -= payload->time_slots; + + if (payload->delete) + drm_dp_mst_put_port_malloc(payload->port); } EXPORT_SYMBOL(drm_dp_remove_payload); @@ -4327,7 +4330,6 @@ int drm_dp_atomic_release_time_slots(struct drm_atomic_state *state, drm_dbg_atomic(mgr->dev, "[MST PORT:%p] TU %d -> 0\n", port, payload->time_slots); if (!payload->delete) { - drm_dp_mst_put_port_malloc(port); payload->pbn = 0; payload->delete = true; topology_state->payload_mask &= ~BIT(payload->vcpi - 1); diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c index 11bb59399471..3d1f50f481cf 100644 --- a/drivers/gpu/drm/drm_buddy.c +++ b/drivers/gpu/drm/drm_buddy.c @@ -38,6 +38,25 @@ static void drm_block_free(struct drm_buddy *mm, kmem_cache_free(slab_blocks, block); } +static void list_insert_sorted(struct drm_buddy *mm, + struct drm_buddy_block *block) +{ + struct drm_buddy_block *node; + struct list_head *head; + + head = &mm->free_list[drm_buddy_block_order(block)]; + if (list_empty(head)) { + list_add(&block->link, head); + return; + } + + list_for_each_entry(node, head, link) + if (drm_buddy_block_offset(block) < drm_buddy_block_offset(node)) + break; + + __list_add(&block->link, node->link.prev, &node->link); +} + static void mark_allocated(struct drm_buddy_block *block) { block->header &= ~DRM_BUDDY_HEADER_STATE; @@ -52,8 +71,7 @@ static void mark_free(struct drm_buddy *mm, block->header &= ~DRM_BUDDY_HEADER_STATE; block->header |= DRM_BUDDY_FREE; - list_add(&block->link, - &mm->free_list[drm_buddy_block_order(block)]); + list_insert_sorted(mm, block); } static void mark_split(struct drm_buddy_block *block) @@ -387,20 +405,26 @@ err_undo: } static struct drm_buddy_block * -get_maxblock(struct list_head *head) +get_maxblock(struct drm_buddy *mm, unsigned int order) { struct drm_buddy_block *max_block = NULL, *node; + unsigned int i; - max_block = list_first_entry_or_null(head, - struct drm_buddy_block, - link); - if (!max_block) - return NULL; + for (i = order; i <= mm->max_order; ++i) { + if (!list_empty(&mm->free_list[i])) { + node = list_last_entry(&mm->free_list[i], + struct drm_buddy_block, + link); + if (!max_block) { + max_block = node; + continue; + } - list_for_each_entry(node, head, link) { - if (drm_buddy_block_offset(node) > - drm_buddy_block_offset(max_block)) - max_block = node; + if (drm_buddy_block_offset(node) > + drm_buddy_block_offset(max_block)) { + max_block = node; + } + } } return max_block; @@ -412,20 +436,23 @@ alloc_from_freelist(struct drm_buddy *mm, unsigned long flags) { struct drm_buddy_block *block = NULL; - unsigned int i; + unsigned int tmp; int err; - for (i = order; i <= mm->max_order; ++i) { - if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) { - block = get_maxblock(&mm->free_list[i]); - if (block) - break; - } else { - block = list_first_entry_or_null(&mm->free_list[i], - struct drm_buddy_block, - link); - if (block) - break; + if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) { + block = get_maxblock(mm, order); + if (block) + /* Store the obtained block order */ + tmp = drm_buddy_block_order(block); + } else { + for (tmp = order; tmp <= mm->max_order; ++tmp) { + if (!list_empty(&mm->free_list[tmp])) { + block = list_last_entry(&mm->free_list[tmp], + struct drm_buddy_block, + link); + if (block) + break; + } } } @@ -434,18 +461,18 @@ alloc_from_freelist(struct drm_buddy *mm, BUG_ON(!drm_buddy_block_is_free(block)); - while (i != order) { + while (tmp != order) { err = split_block(mm, block); if (unlikely(err)) goto err_undo; block = block->right; - i--; + tmp--; } return block; err_undo: - if (i != order) + if (tmp != order) __drm_buddy_free(mm, block); return ERR_PTR(err); } diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c index b3a731b9170a..0d0c26ebab90 100644 --- a/drivers/gpu/drm/drm_fb_helper.c +++ b/drivers/gpu/drm/drm_fb_helper.c @@ -30,7 +30,9 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/console.h> +#include <linux/pci.h> #include <linux/sysrq.h> +#include <linux/vga_switcheroo.h> #include <drm/drm_atomic.h> #include <drm/drm_drv.h> @@ -1909,6 +1911,11 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper, return ret; strcpy(fb_helper->fb->comm, "[fbcon]"); + + /* Set the fb info for vgaswitcheroo clients. Does nothing otherwise. */ + if (dev_is_pci(dev->dev)) + vga_switcheroo_client_fb_set(to_pci_dev(dev->dev), fb_helper->info); + return 0; } diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c index ab8695669279..593aa3283792 100644 --- a/drivers/gpu/drm/drm_fbdev_generic.c +++ b/drivers/gpu/drm/drm_fbdev_generic.c @@ -171,11 +171,6 @@ static const struct fb_ops drm_fbdev_fb_ops = { .fb_imageblit = drm_fbdev_fb_imageblit, }; -static struct fb_deferred_io drm_fbdev_defio = { - .delay = HZ / 20, - .deferred_io = drm_fb_helper_deferred_io, -}; - /* * This function uses the client API to create a framebuffer backed by a dumb buffer. */ @@ -222,8 +217,14 @@ static int drm_fbdev_fb_probe(struct drm_fb_helper *fb_helper, return -ENOMEM; fbi->flags |= FBINFO_VIRTFB | FBINFO_READS_FAST; - fbi->fbdefio = &drm_fbdev_defio; - fb_deferred_io_init(fbi); + /* Set a default deferred I/O handler */ + fb_helper->fbdefio.delay = HZ / 20; + fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io; + + fbi->fbdefio = &fb_helper->fbdefio; + ret = fb_deferred_io_init(fbi); + if (ret) + return ret; } else { /* buffer is mapped for HW framebuffer */ ret = drm_client_buffer_vmap(fb_helper->buffer, &map); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 52d8800a8ab8..3659f0465a72 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -304,6 +304,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGM"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Lenovo Ideapad D330-10IGL (HD) */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo ideapad D330-10IGL"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* Lenovo Yoga Book X90F / X91F / X91L */ .matches = { /* Non exact match to match all versions */ diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c index 7de37f8c68fd..83229a031af0 100644 --- a/drivers/gpu/drm/drm_vma_manager.c +++ b/drivers/gpu/drm/drm_vma_manager.c @@ -240,27 +240,8 @@ void drm_vma_offset_remove(struct drm_vma_offset_manager *mgr, } EXPORT_SYMBOL(drm_vma_offset_remove); -/** - * drm_vma_node_allow - Add open-file to list of allowed users - * @node: Node to modify - * @tag: Tag of file to remove - * - * Add @tag to the list of allowed open-files for this node. If @tag is - * already on this list, the ref-count is incremented. - * - * The list of allowed-users is preserved across drm_vma_offset_add() and - * drm_vma_offset_remove() calls. You may even call it if the node is currently - * not added to any offset-manager. - * - * You must remove all open-files the same number of times as you added them - * before destroying the node. Otherwise, you will leak memory. - * - * This is locked against concurrent access internally. - * - * RETURNS: - * 0 on success, negative error code on internal failure (out-of-mem) - */ -int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag) +static int vma_node_allow(struct drm_vma_offset_node *node, + struct drm_file *tag, bool ref_counted) { struct rb_node **iter; struct rb_node *parent = NULL; @@ -282,7 +263,8 @@ int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag) entry = rb_entry(*iter, struct drm_vma_offset_file, vm_rb); if (tag == entry->vm_tag) { - entry->vm_count++; + if (ref_counted) + entry->vm_count++; goto unlock; } else if (tag > entry->vm_tag) { iter = &(*iter)->rb_right; @@ -307,9 +289,59 @@ unlock: kfree(new); return ret; } + +/** + * drm_vma_node_allow - Add open-file to list of allowed users + * @node: Node to modify + * @tag: Tag of file to remove + * + * Add @tag to the list of allowed open-files for this node. If @tag is + * already on this list, the ref-count is incremented. + * + * The list of allowed-users is preserved across drm_vma_offset_add() and + * drm_vma_offset_remove() calls. You may even call it if the node is currently + * not added to any offset-manager. + * + * You must remove all open-files the same number of times as you added them + * before destroying the node. Otherwise, you will leak memory. + * + * This is locked against concurrent access internally. + * + * RETURNS: + * 0 on success, negative error code on internal failure (out-of-mem) + */ +int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag) +{ + return vma_node_allow(node, tag, true); +} EXPORT_SYMBOL(drm_vma_node_allow); /** + * drm_vma_node_allow_once - Add open-file to list of allowed users + * @node: Node to modify + * @tag: Tag of file to remove + * + * Add @tag to the list of allowed open-files for this node. + * + * The list of allowed-users is preserved across drm_vma_offset_add() and + * drm_vma_offset_remove() calls. You may even call it if the node is currently + * not added to any offset-manager. + * + * This is not ref-counted unlike drm_vma_node_allow() hence drm_vma_node_revoke() + * should only be called once after this. + * + * This is locked against concurrent access internally. + * + * RETURNS: + * 0 on success, negative error code on internal failure (out-of-mem) + */ +int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag) +{ + return vma_node_allow(node, tag, false); +} +EXPORT_SYMBOL(drm_vma_node_allow_once); + +/** * drm_vma_node_revoke - Remove open-file from list of allowed users * @node: Node to modify * @tag: Tag of file to remove diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index b74e36d76013..407a477939e5 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -1319,7 +1319,7 @@ static const struct intel_cdclk_vals adlp_cdclk_table[] = { { .refclk = 24000, .cdclk = 192000, .divider = 2, .ratio = 16 }, { .refclk = 24000, .cdclk = 312000, .divider = 2, .ratio = 26 }, { .refclk = 24000, .cdclk = 552000, .divider = 2, .ratio = 46 }, - { .refclk = 24400, .cdclk = 648000, .divider = 2, .ratio = 54 }, + { .refclk = 24000, .cdclk = 648000, .divider = 2, .ratio = 54 }, { .refclk = 38400, .cdclk = 179200, .divider = 3, .ratio = 14 }, { .refclk = 38400, .cdclk = 192000, .divider = 2, .ratio = 10 }, diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index 76490cc59d8f..7d07fa3123ec 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -1627,7 +1627,7 @@ static int skl_check_main_surface(struct intel_plane_state *plane_state) u32 offset; int ret; - if (w > max_width || w < min_width || h > max_height) { + if (w > max_width || w < min_width || h > max_height || h < 1) { drm_dbg_kms(&dev_priv->drm, "requested Y/RGB source size %dx%d outside limits (min: %dx1 max: %dx%d)\n", w, h, min_width, max_width, max_height); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index 7f2831efc798..e4b78ab4773b 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -1688,6 +1688,10 @@ void i915_gem_init__contexts(struct drm_i915_private *i915) init_contexts(&i915->gem.contexts); } +/* + * Note that this implicitly consumes the ctx reference, by placing + * the ctx in the context_xa. + */ static void gem_context_register(struct i915_gem_context *ctx, struct drm_i915_file_private *fpriv, u32 id) @@ -1703,10 +1707,6 @@ static void gem_context_register(struct i915_gem_context *ctx, snprintf(ctx->name, sizeof(ctx->name), "%s[%d]", current->comm, pid_nr(ctx->pid)); - /* And finally expose ourselves to userspace via the idr */ - old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL); - WARN_ON(old); - spin_lock(&ctx->client->ctx_lock); list_add_tail_rcu(&ctx->client_link, &ctx->client->ctx_list); spin_unlock(&ctx->client->ctx_lock); @@ -1714,6 +1714,10 @@ static void gem_context_register(struct i915_gem_context *ctx, spin_lock(&i915->gem.contexts.lock); list_add_tail(&ctx->link, &i915->gem.contexts.list); spin_unlock(&i915->gem.contexts.lock); + + /* And finally expose ourselves to userspace via the idr */ + old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL); + WARN_ON(old); } int i915_gem_context_open(struct drm_i915_private *i915, @@ -1857,11 +1861,19 @@ static int get_ppgtt(struct drm_i915_file_private *file_priv, vm = ctx->vm; GEM_BUG_ON(!vm); + /* + * Get a reference for the allocated handle. Once the handle is + * visible in the vm_xa table, userspace could try to close it + * from under our feet, so we need to hold the extra reference + * first. + */ + i915_vm_get(vm); + err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL); - if (err) + if (err) { + i915_vm_put(vm); return err; - - i915_vm_get(vm); + } GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */ args->value = id; @@ -2199,14 +2211,22 @@ finalize_create_context_locked(struct drm_i915_file_private *file_priv, if (IS_ERR(ctx)) return ctx; + /* + * One for the xarray and one for the caller. We need to grab + * the reference *prior* to making the ctx visble to userspace + * in gem_context_register(), as at any point after that + * userspace can try to race us with another thread destroying + * the context under our feet. + */ + i915_gem_context_get(ctx); + gem_context_register(ctx, file_priv, id); old = xa_erase(&file_priv->proto_context_xa, id); GEM_BUG_ON(old != pc); proto_context_close(file_priv->dev_priv, pc); - /* One for the xarray and one for the caller */ - return i915_gem_context_get(ctx); + return ctx; } struct i915_gem_context * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 0ad44f3868de..c7c252d4d366 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -697,7 +697,7 @@ insert: GEM_BUG_ON(lookup_mmo(obj, mmap_type) != mmo); out: if (file) - drm_vma_node_allow(&mmo->vma_node, file); + drm_vma_node_allow_once(&mmo->vma_node, file); return mmo; err: diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index fd42b89b7162..bc21b1c2350a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -305,10 +305,6 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, spin_unlock(&obj->vma.lock); obj->tiling_and_stride = tiling | stride; - i915_gem_object_unlock(obj); - - /* Force the fence to be reacquired for GTT access */ - i915_gem_object_release_mmap_gtt(obj); /* Try to preallocate memory required to save swizzling on put-pages */ if (i915_gem_object_needs_bit17_swizzle(obj)) { @@ -321,6 +317,11 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, obj->bit_17 = NULL; } + i915_gem_object_unlock(obj); + + /* Force the fence to be reacquired for GTT access */ + i915_gem_object_release_mmap_gtt(obj); + return 0; } diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index beaf27e09e8a..977dead10ab5 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -1847,7 +1847,7 @@ static int igt_shrink_thp(void *arg) I915_SHRINK_ACTIVE); i915_vma_unpin(vma); if (err) - goto out_put; + goto out_wf; /* * Now that the pages are *unpinned* shrinking should invoke @@ -1863,19 +1863,19 @@ static int igt_shrink_thp(void *arg) pr_err("unexpected pages mismatch, should_swap=%s\n", str_yes_no(should_swap)); err = -EINVAL; - goto out_put; + goto out_wf; } if (should_swap == (obj->mm.page_sizes.sg || obj->mm.page_sizes.phys)) { pr_err("unexpected residual page-size bits, should_swap=%s\n", str_yes_no(should_swap)); err = -EINVAL; - goto out_put; + goto out_wf; } err = i915_vma_pin(vma, 0, 0, flags); if (err) - goto out_put; + goto out_wf; while (n--) { err = cpu_check(obj, n, 0xdeadbeaf); diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index e94365b08f1e..2aa63ec521b8 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -528,7 +528,7 @@ retry: return rq; } -struct i915_request *intel_context_find_active_request(struct intel_context *ce) +struct i915_request *intel_context_get_active_request(struct intel_context *ce) { struct intel_context *parent = intel_context_to_parent(ce); struct i915_request *rq, *active = NULL; @@ -552,6 +552,8 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce) active = rq; } + if (active) + active = i915_request_get_rcu(active); spin_unlock_irqrestore(&parent->guc_state.lock, flags); return active; diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index fb62b7b8cbcd..0a8d553da3f4 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -268,8 +268,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce, struct i915_request *intel_context_create_request(struct intel_context *ce); -struct i915_request * -intel_context_find_active_request(struct intel_context *ce); +struct i915_request *intel_context_get_active_request(struct intel_context *ce); static inline bool intel_context_is_barrier(const struct intel_context *ce) { diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index cbc8b857d5f7..7a4504ea35c3 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -248,8 +248,8 @@ void intel_engine_dump_active_requests(struct list_head *requests, ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine, ktime_t *now); -struct i915_request * -intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine); +void intel_engine_get_hung_entity(struct intel_engine_cs *engine, + struct intel_context **ce, struct i915_request **rq); u32 intel_engine_context_size(struct intel_gt *gt, u8 class); struct intel_context * diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index c33e0d72d670..d37931e16fd9 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -2094,17 +2094,6 @@ static void print_request_ring(struct drm_printer *m, struct i915_request *rq) } } -static unsigned long list_count(struct list_head *list) -{ - struct list_head *pos; - unsigned long count = 0; - - list_for_each(pos, list) - count++; - - return count; -} - static unsigned long read_ul(void *p, size_t x) { return *(unsigned long *)(p + x); @@ -2196,11 +2185,11 @@ void intel_engine_dump_active_requests(struct list_head *requests, } } -static void engine_dump_active_requests(struct intel_engine_cs *engine, struct drm_printer *m) +static void engine_dump_active_requests(struct intel_engine_cs *engine, + struct drm_printer *m) { + struct intel_context *hung_ce = NULL; struct i915_request *hung_rq = NULL; - struct intel_context *ce; - bool guc; /* * No need for an engine->irq_seqno_barrier() before the seqno reads. @@ -2209,27 +2198,22 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d * But the intention here is just to report an instantaneous snapshot * so that's fine. */ - lockdep_assert_held(&engine->sched_engine->lock); + intel_engine_get_hung_entity(engine, &hung_ce, &hung_rq); drm_printf(m, "\tRequests:\n"); - guc = intel_uc_uses_guc_submission(&engine->gt->uc); - if (guc) { - ce = intel_engine_get_hung_context(engine); - if (ce) - hung_rq = intel_context_find_active_request(ce); - } else { - hung_rq = intel_engine_execlist_find_hung_request(engine); - } - if (hung_rq) engine_dump_request(hung_rq, m, "\t\thung"); + else if (hung_ce) + drm_printf(m, "\t\tGot hung ce but no hung rq!\n"); - if (guc) + if (intel_uc_uses_guc_submission(&engine->gt->uc)) intel_guc_dump_active_requests(engine, hung_rq, m); else - intel_engine_dump_active_requests(&engine->sched_engine->requests, - hung_rq, m); + intel_execlists_dump_active_requests(engine, hung_rq, m); + + if (hung_rq) + i915_request_put(hung_rq); } void intel_engine_dump(struct intel_engine_cs *engine, @@ -2239,7 +2223,6 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct i915_gpu_error * const error = &engine->i915->gpu_error; struct i915_request *rq; intel_wakeref_t wakeref; - unsigned long flags; ktime_t dummy; if (header) { @@ -2276,13 +2259,8 @@ void intel_engine_dump(struct intel_engine_cs *engine, i915_reset_count(error)); print_properties(engine, m); - spin_lock_irqsave(&engine->sched_engine->lock, flags); engine_dump_active_requests(engine, m); - drm_printf(m, "\tOn hold?: %lu\n", - list_count(&engine->sched_engine->hold)); - spin_unlock_irqrestore(&engine->sched_engine->lock, flags); - drm_printf(m, "\tMMIO base: 0x%08x\n", engine->mmio_base); wakeref = intel_runtime_pm_get_if_in_use(engine->uncore->rpm); if (wakeref) { @@ -2328,8 +2306,7 @@ intel_engine_create_virtual(struct intel_engine_cs **siblings, return siblings[0]->cops->create_virtual(siblings, count, flags); } -struct i915_request * -intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine) +static struct i915_request *engine_execlist_find_hung_request(struct intel_engine_cs *engine) { struct i915_request *request, *active = NULL; @@ -2381,6 +2358,33 @@ intel_engine_execlist_find_hung_request(struct intel_engine_cs *engine) return active; } +void intel_engine_get_hung_entity(struct intel_engine_cs *engine, + struct intel_context **ce, struct i915_request **rq) +{ + unsigned long flags; + + *ce = intel_engine_get_hung_context(engine); + if (*ce) { + intel_engine_clear_hung_context(engine); + + *rq = intel_context_get_active_request(*ce); + return; + } + + /* + * Getting here with GuC enabled means it is a forced error capture + * with no actual hang. So, no need to attempt the execlist search. + */ + if (intel_uc_uses_guc_submission(&engine->gt->uc)) + return; + + spin_lock_irqsave(&engine->sched_engine->lock, flags); + *rq = engine_execlist_find_hung_request(engine); + if (*rq) + *rq = i915_request_get_rcu(*rq); + spin_unlock_irqrestore(&engine->sched_engine->lock, flags); +} + void xehp_enable_ccs_engines(struct intel_engine_cs *engine) { /* diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 2daffa7c7dfd..21cb5b69d82e 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -4148,6 +4148,33 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, spin_unlock_irqrestore(&sched_engine->lock, flags); } +static unsigned long list_count(struct list_head *list) +{ + struct list_head *pos; + unsigned long count = 0; + + list_for_each(pos, list) + count++; + + return count; +} + +void intel_execlists_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m) +{ + unsigned long flags; + + spin_lock_irqsave(&engine->sched_engine->lock, flags); + + intel_engine_dump_active_requests(&engine->sched_engine->requests, hung_rq, m); + + drm_printf(m, "\tOn hold?: %lu\n", + list_count(&engine->sched_engine->hold)); + + spin_unlock_irqrestore(&engine->sched_engine->lock, flags); +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftest_execlists.c" #endif diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h index a1aa92c983a5..d2c7d45ea062 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.h +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.h @@ -32,6 +32,10 @@ void intel_execlists_show_requests(struct intel_engine_cs *engine, int indent), unsigned int max); +void intel_execlists_dump_active_requests(struct intel_engine_cs *engine, + struct i915_request *hung_rq, + struct drm_printer *m); + bool intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index c3cd92691795..a5454af2a9cf 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -406,10 +406,10 @@ #define GEN9_WM_CHICKEN3 _MMIO(0x5588) #define GEN9_FACTOR_IN_CLR_VAL_HIZ (1 << 9) -#define CHICKEN_RASTER_1 _MMIO(0x6204) +#define CHICKEN_RASTER_1 MCR_REG(0x6204) #define DIS_SF_ROUND_NEAREST_EVEN REG_BIT(8) -#define CHICKEN_RASTER_2 _MMIO(0x6208) +#define CHICKEN_RASTER_2 MCR_REG(0x6208) #define TBIMR_FAST_CLIP REG_BIT(5) #define VFLSKPD MCR_REG(0x62a8) @@ -429,9 +429,10 @@ #define RC_OP_FLUSH_ENABLE (1 << 0) #define HIZ_RAW_STALL_OPT_DISABLE (1 << 2) #define CACHE_MODE_1 _MMIO(0x7004) /* IVB+ */ -#define PIXEL_SUBSPAN_COLLECT_OPT_DISABLE (1 << 6) -#define GEN8_4x4_STC_OPTIMIZATION_DISABLE (1 << 6) -#define GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE (1 << 1) +#define MSAA_OPTIMIZATION_REDUC_DISABLE REG_BIT(11) +#define PIXEL_SUBSPAN_COLLECT_OPT_DISABLE REG_BIT(6) +#define GEN8_4x4_STC_OPTIMIZATION_DISABLE REG_BIT(6) +#define GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE REG_BIT(1) #define GEN7_GT_MODE _MMIO(0x7008) #define GEN9_IZ_HASHING_MASK(slice) (0x3 << ((slice) * 2)) @@ -457,6 +458,9 @@ #define GEN8_L3CNTLREG _MMIO(0x7034) #define GEN8_ERRDETBCTRL (1 << 9) +#define PSS_MODE2 _MMIO(0x703c) +#define SCOREBOARD_STALL_FLUSH_CONTROL REG_BIT(5) + #define GEN7_SC_INSTDONE _MMIO(0x7100) #define GEN12_SC_INSTDONE_EXTRA _MMIO(0x7104) #define GEN12_SC_INSTDONE_EXTRA2 _MMIO(0x7108) diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 7771a19008c6..bbeeb6dde7ae 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -288,39 +288,6 @@ static const u8 dg2_xcs_offsets[] = { END }; -static const u8 mtl_xcs_offsets[] = { - NOP(1), - LRI(13, POSTED), - REG16(0x244), - REG(0x034), - REG(0x030), - REG(0x038), - REG(0x03c), - REG(0x168), - REG(0x140), - REG(0x110), - REG(0x1c0), - REG(0x1c4), - REG(0x1c8), - REG(0x180), - REG16(0x2b4), - NOP(4), - - NOP(1), - LRI(9, POSTED), - REG16(0x3a8), - REG16(0x28c), - REG16(0x288), - REG16(0x284), - REG16(0x280), - REG16(0x27c), - REG16(0x278), - REG16(0x274), - REG16(0x270), - - END -}; - static const u8 gen8_rcs_offsets[] = { NOP(1), LRI(14, POSTED), @@ -739,9 +706,7 @@ static const u8 *reg_offsets(const struct intel_engine_cs *engine) else return gen8_rcs_offsets; } else { - if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 70)) - return mtl_xcs_offsets; - else if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) + if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 55)) return dg2_xcs_offsets; else if (GRAPHICS_VER(engine->i915) >= 12) return gen12_xcs_offsets; diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c index 24736ebee17c..78dc5e493c62 100644 --- a/drivers/gpu/drm/i915/gt/intel_reset.c +++ b/drivers/gpu/drm/i915/gt/intel_reset.c @@ -278,6 +278,7 @@ out: static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask) { struct intel_uncore *uncore = gt->uncore; + int loops = 2; int err; /* @@ -285,18 +286,39 @@ static int gen6_hw_domain_reset(struct intel_gt *gt, u32 hw_domain_mask) * for fifo space for the write or forcewake the chip for * the read */ - intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask); + do { + intel_uncore_write_fw(uncore, GEN6_GDRST, hw_domain_mask); - /* Wait for the device to ack the reset requests */ - err = __intel_wait_for_register_fw(uncore, - GEN6_GDRST, hw_domain_mask, 0, - 500, 0, - NULL); + /* + * Wait for the device to ack the reset requests. + * + * On some platforms, e.g. Jasperlake, we see that the + * engine register state is not cleared until shortly after + * GDRST reports completion, causing a failure as we try + * to immediately resume while the internal state is still + * in flux. If we immediately repeat the reset, the second + * reset appears to serialise with the first, and since + * it is a no-op, the registers should retain their reset + * value. However, there is still a concern that upon + * leaving the second reset, the internal engine state + * is still in flux and not ready for resuming. + */ + err = __intel_wait_for_register_fw(uncore, GEN6_GDRST, + hw_domain_mask, 0, + 2000, 0, + NULL); + } while (err == 0 && --loops); if (err) GT_TRACE(gt, "Wait for 0x%08x engines reset failed\n", hw_domain_mask); + /* + * As we have observed that the engine state is still volatile + * after GDRST is acked, impose a small delay to let everything settle. + */ + udelay(50); + return err; } diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 2afb4f80a954..949c19339015 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -645,7 +645,7 @@ static void icl_ctx_workarounds_init(struct intel_engine_cs *engine, static void dg2_ctx_gt_tuning_init(struct intel_engine_cs *engine, struct i915_wa_list *wal) { - wa_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP); + wa_mcr_masked_en(wal, CHICKEN_RASTER_2, TBIMR_FAST_CLIP); wa_mcr_write_clr_set(wal, XEHP_L3SQCREG5, L3_PWM_TIMER_INIT_VAL_MASK, REG_FIELD_PREP(L3_PWM_TIMER_INIT_VAL_MASK, 0x7f)); wa_mcr_add(wal, @@ -771,11 +771,19 @@ static void dg2_ctx_workarounds_init(struct intel_engine_cs *engine, /* Wa_14014947963:dg2 */ if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_B0, STEP_FOREVER) || - IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915)) + IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915)) wa_masked_field_set(wal, VF_PREEMPTION, PREEMPTION_VERTEX_COUNT, 0x4000); + /* Wa_18018764978:dg2 */ + if (IS_DG2_GRAPHICS_STEP(engine->i915, G10, STEP_C0, STEP_FOREVER) || + IS_DG2_G11(engine->i915) || IS_DG2_G12(engine->i915)) + wa_masked_en(wal, PSS_MODE2, SCOREBOARD_STALL_FLUSH_CONTROL); + /* Wa_15010599737:dg2 */ - wa_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN); + wa_mcr_masked_en(wal, CHICKEN_RASTER_1, DIS_SF_ROUND_NEAREST_EVEN); + + /* Wa_18019271663:dg2 */ + wa_masked_en(wal, CACHE_MODE_1, MSAA_OPTIMIZATION_REDUC_DISABLE); } static void fakewa_disable_nestedbb_mode(struct intel_engine_cs *engine, diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 0a42f1807f52..c10977cb06b9 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -1702,7 +1702,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st goto next_context; guilty = false; - rq = intel_context_find_active_request(ce); + rq = intel_context_get_active_request(ce); if (!rq) { head = ce->ring->tail; goto out_replay; @@ -1715,6 +1715,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st head = intel_ring_wrap(ce->ring, rq->head); __i915_request_reset(rq, guilty); + i915_request_put(rq); out_replay: guc_reset_state(ce, head, guilty); next_context: @@ -4817,6 +4818,8 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) xa_lock_irqsave(&guc->context_lookup, flags); xa_for_each(&guc->context_lookup, index, ce) { + bool found; + if (!kref_get_unless_zero(&ce->ref)) continue; @@ -4833,10 +4836,18 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) goto next; } + found = false; + spin_lock(&ce->guc_state.lock); list_for_each_entry(rq, &ce->guc_state.requests, sched.link) { if (i915_test_request_state(rq) != I915_REQUEST_ACTIVE) continue; + found = true; + break; + } + spin_unlock(&ce->guc_state.lock); + + if (found) { intel_engine_set_hung_context(engine, ce); /* Can only cope with one hang at a time... */ @@ -4844,6 +4855,7 @@ void intel_guc_find_hung_context(struct intel_engine_cs *engine) xa_lock(&guc->context_lookup); goto done; } + next: intel_context_put(ce); xa_lock(&guc->context_lookup); diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index 69103ae37779..61c38fc734cf 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -1069,12 +1069,9 @@ static int i915_driver_open(struct drm_device *dev, struct drm_file *file) */ static void i915_driver_lastclose(struct drm_device *dev) { - struct drm_i915_private *i915 = to_i915(dev); - intel_fbdev_restore_mode(dev); - if (HAS_DISPLAY(i915)) - vga_switcheroo_process_delayed_switch(); + vga_switcheroo_process_delayed_switch(); } static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file) diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 9d5d5a397b64..b20bd6365615 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1596,43 +1596,20 @@ capture_engine(struct intel_engine_cs *engine, { struct intel_engine_capture_vma *capture = NULL; struct intel_engine_coredump *ee; - struct intel_context *ce; + struct intel_context *ce = NULL; struct i915_request *rq = NULL; - unsigned long flags; ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL, dump_flags); if (!ee) return NULL; - ce = intel_engine_get_hung_context(engine); - if (ce) { - intel_engine_clear_hung_context(engine); - rq = intel_context_find_active_request(ce); - if (!rq || !i915_request_started(rq)) - goto no_request_capture; - } else { - /* - * Getting here with GuC enabled means it is a forced error capture - * with no actual hang. So, no need to attempt the execlist search. - */ - if (!intel_uc_uses_guc_submission(&engine->gt->uc)) { - spin_lock_irqsave(&engine->sched_engine->lock, flags); - rq = intel_engine_execlist_find_hung_request(engine); - spin_unlock_irqrestore(&engine->sched_engine->lock, - flags); - } - } - if (rq) - rq = i915_request_get_rcu(rq); - - if (!rq) + intel_engine_get_hung_entity(engine, &ce, &rq); + if (!rq || !i915_request_started(rq)) goto no_request_capture; capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL); - if (!capture) { - i915_request_put(rq); + if (!capture) goto no_request_capture; - } if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE) intel_guc_capture_get_matching_node(engine->gt, ee, ce); @@ -1642,6 +1619,8 @@ capture_engine(struct intel_engine_cs *engine, return ee; no_request_capture: + if (rq) + i915_request_put(rq); kfree(ee); return NULL; } diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index ccd1f864aa19..4fada7ebe8d8 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -423,7 +423,8 @@ static const struct intel_device_info ilk_m_info = { .has_coherent_ggtt = true, \ .has_llc = 1, \ .has_rc6 = 1, \ - .has_rc6p = 1, \ + /* snb does support rc6p, but enabling it causes various issues */ \ + .has_rc6p = 0, \ .has_rps = true, \ .dma_mask_size = 40, \ .__runtime.ppgtt_type = INTEL_PPGTT_ALIASING, \ diff --git a/drivers/gpu/drm/i915/i915_switcheroo.c b/drivers/gpu/drm/i915/i915_switcheroo.c index 23777d500cdf..f45bd6b6cede 100644 --- a/drivers/gpu/drm/i915/i915_switcheroo.c +++ b/drivers/gpu/drm/i915/i915_switcheroo.c @@ -19,6 +19,10 @@ static void i915_switcheroo_set_state(struct pci_dev *pdev, dev_err(&pdev->dev, "DRM not initialized, aborting switch.\n"); return; } + if (!HAS_DISPLAY(i915)) { + dev_err(&pdev->dev, "Device state not initialized, aborting switch.\n"); + return; + } if (state == VGA_SWITCHEROO_ON) { drm_info(&i915->drm, "switched on\n"); @@ -44,7 +48,7 @@ static bool i915_switcheroo_can_switch(struct pci_dev *pdev) * locking inversion with the driver load path. And the access here is * completely racy anyway. So don't bother with locking for now. */ - return i915 && atomic_read(&i915->drm.open_count) == 0; + return i915 && HAS_DISPLAY(i915) && atomic_read(&i915->drm.open_count) == 0; } static const struct vga_switcheroo_client_ops i915_switcheroo_ops = { diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 3a33be5401ed..135390d975b6 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -2116,7 +2116,7 @@ int i915_vma_unbind_async(struct i915_vma *vma, bool trylock_vm) if (!obj->mm.rsgt) return -EBUSY; - err = dma_resv_reserve_fences(obj->base.resv, 1); + err = dma_resv_reserve_fences(obj->base.resv, 2); if (err) return -EBUSY; diff --git a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c index 310fb83c527e..2990dd4d4a0d 100644 --- a/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c +++ b/drivers/gpu/drm/i915/selftests/intel_scheduler_helpers.c @@ -28,8 +28,7 @@ struct intel_engine_cs *intel_selftest_find_any_engine(struct intel_gt *gt) int intel_selftest_modify_policy(struct intel_engine_cs *engine, struct intel_selftest_saved_policy *saved, - u32 modify_type) - + enum selftest_scheduler_modify modify_type) { int err; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 6484b97c5344..f3c9600221d4 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -876,7 +876,8 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) #define GBIF_CLIENT_HALT_MASK BIT(0) #define GBIF_ARB_HALT_MASK BIT(1) -static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu) +static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, + bool gx_off) { struct msm_gpu *gpu = &adreno_gpu->base; @@ -889,9 +890,11 @@ static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu) return; } - /* Halt the gx side of GBIF */ - gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1); - spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1); + if (gx_off) { + /* Halt the gx side of GBIF */ + gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1); + spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1); + } /* Halt new client requests on GBIF */ gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); @@ -929,7 +932,7 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu) /* Halt the gmu cm3 core */ gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1); - a6xx_bus_clear_pending_transactions(adreno_gpu); + a6xx_bus_clear_pending_transactions(adreno_gpu, true); /* Reset GPU core blocks */ gpu_write(gpu, REG_A6XX_RBBM_SW_RESET_CMD, 1); @@ -1083,7 +1086,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) return; } - a6xx_bus_clear_pending_transactions(adreno_gpu); + a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung); /* tell the GMU we want to slumber */ ret = a6xx_gmu_notify_slumber(gmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 36c8fb699b56..3be0f2928b57 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1270,6 +1270,12 @@ static void a6xx_recover(struct msm_gpu *gpu) if (hang_debug) a6xx_dump(gpu); + /* + * To handle recovery specific sequences during the rpm suspend we are + * about to trigger + */ + a6xx_gpu->hung = true; + /* Halt SQE first */ gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3); @@ -1312,6 +1318,7 @@ static void a6xx_recover(struct msm_gpu *gpu) mutex_unlock(&gpu->active_lock); msm_gpu_hw_init(gpu); + a6xx_gpu->hung = false; } static const char *a6xx_uche_fault_block(struct msm_gpu *gpu, u32 mid) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index ab853f61db63..eea2e60ce3b7 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -32,6 +32,7 @@ struct a6xx_gpu { void *llc_slice; void *htw_llc_slice; bool have_mmu500; + bool hung; }; #define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base) diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 628806423f7d..36f062c7582f 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -551,13 +551,14 @@ static int adreno_bind(struct device *dev, struct device *master, void *data) return 0; } +static int adreno_system_suspend(struct device *dev); static void adreno_unbind(struct device *dev, struct device *master, void *data) { struct msm_drm_private *priv = dev_get_drvdata(master); struct msm_gpu *gpu = dev_to_gpu(dev); - pm_runtime_force_suspend(dev); + WARN_ON_ONCE(adreno_system_suspend(dev)); gpu->funcs->destroy(gpu); priv->gpu_pdev = NULL; @@ -609,7 +610,7 @@ static int adreno_remove(struct platform_device *pdev) static void adreno_shutdown(struct platform_device *pdev) { - pm_runtime_force_suspend(&pdev->dev); + WARN_ON_ONCE(adreno_system_suspend(&pdev->dev)); } static const struct of_device_id dt_match[] = { diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 57586c794b84..3605f095b2de 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -352,6 +352,8 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, /* Ensure string is null terminated: */ str[len] = '\0'; + mutex_lock(&gpu->lock); + if (param == MSM_PARAM_COMM) { paramp = &ctx->comm; } else { @@ -361,6 +363,8 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, kfree(*paramp); *paramp = str; + mutex_unlock(&gpu->lock); + return 0; } case MSM_PARAM_SYSPROF: diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 5d4b1c95033f..b4f9b1343d63 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -29,11 +29,9 @@ enum { ADRENO_FW_MAX, }; -enum adreno_quirks { - ADRENO_QUIRK_TWO_PASS_USE_WFI = 1, - ADRENO_QUIRK_FAULT_DETECT_MASK = 2, - ADRENO_QUIRK_LMLOADKILL_DISABLE = 3, -}; +#define ADRENO_QUIRK_TWO_PASS_USE_WFI BIT(0) +#define ADRENO_QUIRK_FAULT_DETECT_MASK BIT(1) +#define ADRENO_QUIRK_LMLOADKILL_DISABLE BIT(2) struct adreno_rev { uint8_t core; @@ -65,7 +63,7 @@ struct adreno_info { const char *name; const char *fw[ADRENO_FW_MAX]; uint32_t gmem; - enum adreno_quirks quirks; + u64 quirks; struct msm_gpu *(*init)(struct drm_device *dev); const char *zapfw; u32 inactive_period; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 7cbcef6efe17..62f6ff6abf41 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -132,7 +132,6 @@ static void dpu_encoder_phys_wb_set_qos(struct dpu_encoder_phys *phys_enc) * dpu_encoder_phys_wb_setup_fb - setup output framebuffer * @phys_enc: Pointer to physical encoder * @fb: Pointer to output framebuffer - * @wb_roi: Pointer to output region of interest */ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, struct drm_framebuffer *fb) @@ -692,7 +691,7 @@ static void dpu_encoder_phys_wb_init_ops(struct dpu_encoder_phys_ops *ops) /** * dpu_encoder_phys_wb_init - initialize writeback encoder - * @init: Pointer to init info structure with initialization params + * @p: Pointer to init info structure with initialization params */ struct dpu_encoder_phys *dpu_encoder_phys_wb_init( struct dpu_enc_phys_init_params *p) diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c index d030a93a08c3..cc3efed593aa 100644 --- a/drivers/gpu/drm/msm/dp/dp_aux.c +++ b/drivers/gpu/drm/msm/dp/dp_aux.c @@ -423,6 +423,10 @@ void dp_aux_isr(struct drm_dp_aux *dp_aux) isr = dp_catalog_aux_get_irq(aux->catalog); + /* no interrupts pending, return immediately */ + if (!isr) + return; + if (!aux->cmd_busy) return; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 4d3fdc806bef..97372bb241d8 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -532,11 +532,19 @@ static int msm_hdmi_dev_probe(struct platform_device *pdev) ret = devm_pm_runtime_enable(&pdev->dev); if (ret) - return ret; + goto err_put_phy; platform_set_drvdata(pdev, hdmi); - return component_add(&pdev->dev, &msm_hdmi_ops); + ret = component_add(&pdev->dev, &msm_hdmi_ops); + if (ret) + goto err_put_phy; + + return 0; + +err_put_phy: + msm_hdmi_put_phy(hdmi); + return ret; } static int msm_hdmi_dev_remove(struct platform_device *pdev) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 8b0b0ac74a6f..45e81eb148a8 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -1278,7 +1278,7 @@ void msm_drv_shutdown(struct platform_device *pdev) * msm_drm_init, drm_dev->registered is used as an indicator that the * shutdown will be successful. */ - if (drm && drm->registered) + if (drm && drm->registered && priv->kms) drm_atomic_helper_shutdown(drm); } diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 30ed45af76ad..380249500325 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -335,6 +335,8 @@ static void get_comm_cmdline(struct msm_gem_submit *submit, char **comm, char ** struct msm_file_private *ctx = submit->queue->ctx; struct task_struct *task; + WARN_ON(!mutex_is_locked(&submit->gpu->lock)); + /* Note that kstrdup will return NULL if argument is NULL: */ *comm = kstrdup(ctx->comm, GFP_KERNEL); *cmd = kstrdup(ctx->cmdline, GFP_KERNEL); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 651786bc55e5..732295e25683 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -376,10 +376,18 @@ struct msm_file_private { */ int sysprof; - /** comm: Overridden task comm, see MSM_PARAM_COMM */ + /** + * comm: Overridden task comm, see MSM_PARAM_COMM + * + * Accessed under msm_gpu::lock + */ char *comm; - /** cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE */ + /** + * cmdline: Overridden task cmdline, see MSM_PARAM_CMDLINE + * + * Accessed under msm_gpu::lock + */ char *cmdline; /** diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 86b28add1fff..2527afef9c19 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -47,15 +47,17 @@ struct msm_mdss { static int msm_mdss_parse_data_bus_icc_path(struct device *dev, struct msm_mdss *msm_mdss) { - struct icc_path *path0 = of_icc_get(dev, "mdp0-mem"); - struct icc_path *path1 = of_icc_get(dev, "mdp1-mem"); + struct icc_path *path0; + struct icc_path *path1; + path0 = of_icc_get(dev, "mdp0-mem"); if (IS_ERR_OR_NULL(path0)) return PTR_ERR_OR_ZERO(path0); msm_mdss->path[0] = path0; msm_mdss->num_paths = 1; + path1 = of_icc_get(dev, "mdp1-mem"); if (!IS_ERR_OR_NULL(path1)) { msm_mdss->path[1] = path1; msm_mdss->num_paths++; diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h index 40768373cdd9..c5a4f49ee206 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h @@ -97,6 +97,7 @@ int gp100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct n int gp102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int gp10b_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int gv100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); +int tu102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int ga100_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); int ga102_fb_new(struct nvkm_device *, enum nvkm_subdev_type, int inst, struct nvkm_fb **); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c deleted file mode 100644 index e87de7906f78..000000000000 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ /dev/null @@ -1,613 +0,0 @@ -/* - * Copyright © 2007 David Airlie - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice (including the next - * paragraph) shall be included in all copies or substantial portions of the - * Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER - * DEALINGS IN THE SOFTWARE. - * - * Authors: - * David Airlie - */ - -#include <linux/module.h> -#include <linux/kernel.h> -#include <linux/errno.h> -#include <linux/string.h> -#include <linux/mm.h> -#include <linux/tty.h> -#include <linux/sysrq.h> -#include <linux/delay.h> -#include <linux/init.h> -#include <linux/screen_info.h> -#include <linux/vga_switcheroo.h> -#include <linux/console.h> - -#include <drm/drm_crtc.h> -#include <drm/drm_crtc_helper.h> -#include <drm/drm_probe_helper.h> -#include <drm/drm_fb_helper.h> -#include <drm/drm_fourcc.h> -#include <drm/drm_atomic.h> - -#include "nouveau_drv.h" -#include "nouveau_gem.h" -#include "nouveau_bo.h" -#include "nouveau_fbcon.h" -#include "nouveau_chan.h" -#include "nouveau_vmm.h" - -#include "nouveau_crtc.h" - -MODULE_PARM_DESC(nofbaccel, "Disable fbcon acceleration"); -int nouveau_nofbaccel = 0; -module_param_named(nofbaccel, nouveau_nofbaccel, int, 0400); - -MODULE_PARM_DESC(fbcon_bpp, "fbcon bits-per-pixel (default: auto)"); -static int nouveau_fbcon_bpp; -module_param_named(fbcon_bpp, nouveau_fbcon_bpp, int, 0400); - -static void -nouveau_fbcon_fillrect(struct fb_info *info, const struct fb_fillrect *rect) -{ - struct nouveau_fbdev *fbcon = info->par; - struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); - struct nvif_device *device = &drm->client.device; - int ret; - - if (info->state != FBINFO_STATE_RUNNING) - return; - - ret = -ENODEV; - if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) && - mutex_trylock(&drm->client.mutex)) { - if (device->info.family < NV_DEVICE_INFO_V0_TESLA) - ret = nv04_fbcon_fillrect(info, rect); - else - if (device->info.family < NV_DEVICE_INFO_V0_FERMI) - ret = nv50_fbcon_fillrect(info, rect); - else - ret = nvc0_fbcon_fillrect(info, rect); - mutex_unlock(&drm->client.mutex); - } - - if (ret == 0) - return; - - if (ret != -ENODEV) - nouveau_fbcon_gpu_lockup(info); - drm_fb_helper_cfb_fillrect(info, rect); -} - -static void -nouveau_fbcon_copyarea(struct fb_info *info, const struct fb_copyarea *image) -{ - struct nouveau_fbdev *fbcon = info->par; - struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); - struct nvif_device *device = &drm->client.device; - int ret; - - if (info->state != FBINFO_STATE_RUNNING) - return; - - ret = -ENODEV; - if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) && - mutex_trylock(&drm->client.mutex)) { - if (device->info.family < NV_DEVICE_INFO_V0_TESLA) - ret = nv04_fbcon_copyarea(info, image); - else - if (device->info.family < NV_DEVICE_INFO_V0_FERMI) - ret = nv50_fbcon_copyarea(info, image); - else - ret = nvc0_fbcon_copyarea(info, image); - mutex_unlock(&drm->client.mutex); - } - - if (ret == 0) - return; - - if (ret != -ENODEV) - nouveau_fbcon_gpu_lockup(info); - drm_fb_helper_cfb_copyarea(info, image); -} - -static void -nouveau_fbcon_imageblit(struct fb_info *info, const struct fb_image *image) -{ - struct nouveau_fbdev *fbcon = info->par; - struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); - struct nvif_device *device = &drm->client.device; - int ret; - - if (info->state != FBINFO_STATE_RUNNING) - return; - - ret = -ENODEV; - if (!in_interrupt() && !(info->flags & FBINFO_HWACCEL_DISABLED) && - mutex_trylock(&drm->client.mutex)) { - if (device->info.family < NV_DEVICE_INFO_V0_TESLA) - ret = nv04_fbcon_imageblit(info, image); - else - if (device->info.family < NV_DEVICE_INFO_V0_FERMI) - ret = nv50_fbcon_imageblit(info, image); - else - ret = nvc0_fbcon_imageblit(info, image); - mutex_unlock(&drm->client.mutex); - } - - if (ret == 0) - return; - - if (ret != -ENODEV) - nouveau_fbcon_gpu_lockup(info); - drm_fb_helper_cfb_imageblit(info, image); -} - -static int -nouveau_fbcon_sync(struct fb_info *info) -{ - struct nouveau_fbdev *fbcon = info->par; - struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); - struct nouveau_channel *chan = drm->channel; - int ret; - - if (!chan || !chan->accel_done || in_interrupt() || - info->state != FBINFO_STATE_RUNNING || - info->flags & FBINFO_HWACCEL_DISABLED) - return 0; - - if (!mutex_trylock(&drm->client.mutex)) - return 0; - - ret = nouveau_channel_idle(chan); - mutex_unlock(&drm->client.mutex); - if (ret) { - nouveau_fbcon_gpu_lockup(info); - return 0; - } - - chan->accel_done = false; - return 0; -} - -static int -nouveau_fbcon_open(struct fb_info *info, int user) -{ - struct nouveau_fbdev *fbcon = info->par; - struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); - int ret = pm_runtime_get_sync(drm->dev->dev); - if (ret < 0 && ret != -EACCES) { - pm_runtime_put(drm->dev->dev); - return ret; - } - return 0; -} - -static int -nouveau_fbcon_release(struct fb_info *info, int user) -{ - struct nouveau_fbdev *fbcon = info->par; - struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); - pm_runtime_put(drm->dev->dev); - return 0; -} - -static const struct fb_ops nouveau_fbcon_ops = { - .owner = THIS_MODULE, - DRM_FB_HELPER_DEFAULT_OPS, - .fb_open = nouveau_fbcon_open, - .fb_release = nouveau_fbcon_release, - .fb_fillrect = nouveau_fbcon_fillrect, - .fb_copyarea = nouveau_fbcon_copyarea, - .fb_imageblit = nouveau_fbcon_imageblit, - .fb_sync = nouveau_fbcon_sync, -}; - -static const struct fb_ops nouveau_fbcon_sw_ops = { - .owner = THIS_MODULE, - DRM_FB_HELPER_DEFAULT_OPS, - .fb_open = nouveau_fbcon_open, - .fb_release = nouveau_fbcon_release, - .fb_fillrect = drm_fb_helper_cfb_fillrect, - .fb_copyarea = drm_fb_helper_cfb_copyarea, - .fb_imageblit = drm_fb_helper_cfb_imageblit, -}; - -void -nouveau_fbcon_accel_save_disable(struct drm_device *dev) -{ - struct nouveau_drm *drm = nouveau_drm(dev); - if (drm->fbcon && drm->fbcon->helper.info) { - drm->fbcon->saved_flags = drm->fbcon->helper.info->flags; - drm->fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED; - } -} - -void -nouveau_fbcon_accel_restore(struct drm_device *dev) -{ - struct nouveau_drm *drm = nouveau_drm(dev); - if (drm->fbcon && drm->fbcon->helper.info) - drm->fbcon->helper.info->flags = drm->fbcon->saved_flags; -} - -static void -nouveau_fbcon_accel_fini(struct drm_device *dev) -{ - struct nouveau_drm *drm = nouveau_drm(dev); - struct nouveau_fbdev *fbcon = drm->fbcon; - if (fbcon && drm->channel) { - console_lock(); - if (fbcon->helper.info) - fbcon->helper.info->flags |= FBINFO_HWACCEL_DISABLED; - console_unlock(); - nouveau_channel_idle(drm->channel); - nvif_object_dtor(&fbcon->twod); - nvif_object_dtor(&fbcon->blit); - nvif_object_dtor(&fbcon->gdi); - nvif_object_dtor(&fbcon->patt); - nvif_object_dtor(&fbcon->rop); - nvif_object_dtor(&fbcon->clip); - nvif_object_dtor(&fbcon->surf2d); - } -} - -static void -nouveau_fbcon_accel_init(struct drm_device *dev) -{ - struct nouveau_drm *drm = nouveau_drm(dev); - struct nouveau_fbdev *fbcon = drm->fbcon; - struct fb_info *info = fbcon->helper.info; - int ret; - - if (drm->client.device.info.family < NV_DEVICE_INFO_V0_TESLA) - ret = nv04_fbcon_accel_init(info); - else - if (drm->client.device.info.family < NV_DEVICE_INFO_V0_FERMI) - ret = nv50_fbcon_accel_init(info); - else - ret = nvc0_fbcon_accel_init(info); - - if (ret == 0) - info->fbops = &nouveau_fbcon_ops; -} - -static void -nouveau_fbcon_zfill(struct drm_device *dev, struct nouveau_fbdev *fbcon) -{ - struct fb_info *info = fbcon->helper.info; - struct fb_fillrect rect; - - /* Clear the entire fbcon. The drm will program every connector - * with it's preferred mode. If the sizes differ, one display will - * quite likely have garbage around the console. - */ - rect.dx = rect.dy = 0; - rect.width = info->var.xres_virtual; - rect.height = info->var.yres_virtual; - rect.color = 0; - rect.rop = ROP_COPY; - info->fbops->fb_fillrect(info, &rect); -} - -static int -nouveau_fbcon_create(struct drm_fb_helper *helper, - struct drm_fb_helper_surface_size *sizes) -{ - struct nouveau_fbdev *fbcon = - container_of(helper, struct nouveau_fbdev, helper); - struct drm_device *dev = fbcon->helper.dev; - struct nouveau_drm *drm = nouveau_drm(dev); - struct nvif_device *device = &drm->client.device; - struct fb_info *info; - struct drm_framebuffer *fb; - struct nouveau_channel *chan; - struct nouveau_bo *nvbo; - struct drm_mode_fb_cmd2 mode_cmd = {}; - int ret; - - mode_cmd.width = sizes->surface_width; - mode_cmd.height = sizes->surface_height; - - mode_cmd.pitches[0] = mode_cmd.width * (sizes->surface_bpp >> 3); - mode_cmd.pitches[0] = roundup(mode_cmd.pitches[0], 256); - - mode_cmd.pixel_format = drm_mode_legacy_fb_format(sizes->surface_bpp, - sizes->surface_depth); - - ret = nouveau_gem_new(&drm->client, mode_cmd.pitches[0] * - mode_cmd.height, 0, NOUVEAU_GEM_DOMAIN_VRAM, - 0, 0x0000, &nvbo); - if (ret) { - NV_ERROR(drm, "failed to allocate framebuffer\n"); - goto out; - } - - ret = nouveau_framebuffer_new(dev, &mode_cmd, &nvbo->bo.base, &fb); - if (ret) - goto out_unref; - - ret = nouveau_bo_pin(nvbo, NOUVEAU_GEM_DOMAIN_VRAM, false); - if (ret) { - NV_ERROR(drm, "failed to pin fb: %d\n", ret); - goto out_unref; - } - - ret = nouveau_bo_map(nvbo); - if (ret) { - NV_ERROR(drm, "failed to map fb: %d\n", ret); - goto out_unpin; - } - - chan = nouveau_nofbaccel ? NULL : drm->channel; - if (chan && device->info.family >= NV_DEVICE_INFO_V0_TESLA) { - ret = nouveau_vma_new(nvbo, chan->vmm, &fbcon->vma); - if (ret) { - NV_ERROR(drm, "failed to map fb into chan: %d\n", ret); - chan = NULL; - } - } - - info = drm_fb_helper_alloc_info(helper); - if (IS_ERR(info)) { - ret = PTR_ERR(info); - goto out_unlock; - } - - /* setup helper */ - fbcon->helper.fb = fb; - - if (!chan) - info->flags = FBINFO_HWACCEL_DISABLED; - else - info->flags = FBINFO_HWACCEL_COPYAREA | - FBINFO_HWACCEL_FILLRECT | - FBINFO_HWACCEL_IMAGEBLIT; - info->fbops = &nouveau_fbcon_sw_ops; - info->fix.smem_start = nvbo->bo.resource->bus.offset; - info->fix.smem_len = nvbo->bo.base.size; - - info->screen_base = nvbo_kmap_obj_iovirtual(nvbo); - info->screen_size = nvbo->bo.base.size; - - drm_fb_helper_fill_info(info, &fbcon->helper, sizes); - - /* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */ - - if (chan) - nouveau_fbcon_accel_init(dev); - nouveau_fbcon_zfill(dev, fbcon); - - /* To allow resizeing without swapping buffers */ - NV_INFO(drm, "allocated %dx%d fb: 0x%llx, bo %p\n", - fb->width, fb->height, nvbo->offset, nvbo); - - if (dev_is_pci(dev->dev)) - vga_switcheroo_client_fb_set(to_pci_dev(dev->dev), info); - - return 0; - -out_unlock: - if (chan) - nouveau_vma_del(&fbcon->vma); - nouveau_bo_unmap(nvbo); -out_unpin: - nouveau_bo_unpin(nvbo); -out_unref: - nouveau_bo_ref(NULL, &nvbo); -out: - return ret; -} - -static int -nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon) -{ - struct drm_framebuffer *fb = fbcon->helper.fb; - struct nouveau_bo *nvbo; - - drm_fb_helper_unregister_info(&fbcon->helper); - drm_fb_helper_fini(&fbcon->helper); - - if (fb && fb->obj[0]) { - nvbo = nouveau_gem_object(fb->obj[0]); - nouveau_vma_del(&fbcon->vma); - nouveau_bo_unmap(nvbo); - nouveau_bo_unpin(nvbo); - drm_framebuffer_put(fb); - } - - return 0; -} - -void nouveau_fbcon_gpu_lockup(struct fb_info *info) -{ - struct nouveau_fbdev *fbcon = info->par; - struct nouveau_drm *drm = nouveau_drm(fbcon->helper.dev); - - NV_ERROR(drm, "GPU lockup - switching to software fbcon\n"); - info->flags |= FBINFO_HWACCEL_DISABLED; -} - -static const struct drm_fb_helper_funcs nouveau_fbcon_helper_funcs = { - .fb_probe = nouveau_fbcon_create, -}; - -static void -nouveau_fbcon_set_suspend_work(struct work_struct *work) -{ - struct nouveau_drm *drm = container_of(work, typeof(*drm), fbcon_work); - int state = READ_ONCE(drm->fbcon_new_state); - - if (state == FBINFO_STATE_RUNNING) - pm_runtime_get_sync(drm->dev->dev); - - console_lock(); - if (state == FBINFO_STATE_RUNNING) - nouveau_fbcon_accel_restore(drm->dev); - drm_fb_helper_set_suspend(&drm->fbcon->helper, state); - if (state != FBINFO_STATE_RUNNING) - nouveau_fbcon_accel_save_disable(drm->dev); - console_unlock(); - - if (state == FBINFO_STATE_RUNNING) { - nouveau_fbcon_hotplug_resume(drm->fbcon); - pm_runtime_mark_last_busy(drm->dev->dev); - pm_runtime_put_autosuspend(drm->dev->dev); - } -} - -void -nouveau_fbcon_set_suspend(struct drm_device *dev, int state) -{ - struct nouveau_drm *drm = nouveau_drm(dev); - - if (!drm->fbcon) - return; - - drm->fbcon_new_state = state; - /* Since runtime resume can happen as a result of a sysfs operation, - * it's possible we already have the console locked. So handle fbcon - * init/deinit from a seperate work thread - */ - schedule_work(&drm->fbcon_work); -} - -void -nouveau_fbcon_output_poll_changed(struct drm_device *dev) -{ - struct nouveau_drm *drm = nouveau_drm(dev); - struct nouveau_fbdev *fbcon = drm->fbcon; - int ret; - - if (!fbcon) - return; - - mutex_lock(&fbcon->hotplug_lock); - - ret = pm_runtime_get(dev->dev); - if (ret == 1 || ret == -EACCES) { - drm_fb_helper_hotplug_event(&fbcon->helper); - - pm_runtime_mark_last_busy(dev->dev); - pm_runtime_put_autosuspend(dev->dev); - } else if (ret == 0) { - /* If the GPU was already in the process of suspending before - * this event happened, then we can't block here as we'll - * deadlock the runtime pmops since they wait for us to - * finish. So, just defer this event for when we runtime - * resume again. It will be handled by fbcon_work. - */ - NV_DEBUG(drm, "fbcon HPD event deferred until runtime resume\n"); - fbcon->hotplug_waiting = true; - pm_runtime_put_noidle(drm->dev->dev); - } else { - DRM_WARN("fbcon HPD event lost due to RPM failure: %d\n", - ret); - } - - mutex_unlock(&fbcon->hotplug_lock); -} - -void -nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon) -{ - struct nouveau_drm *drm; - - if (!fbcon) - return; - drm = nouveau_drm(fbcon->helper.dev); - - mutex_lock(&fbcon->hotplug_lock); - if (fbcon->hotplug_waiting) { - fbcon->hotplug_waiting = false; - - NV_DEBUG(drm, "Handling deferred fbcon HPD events\n"); - drm_fb_helper_hotplug_event(&fbcon->helper); - } - mutex_unlock(&fbcon->hotplug_lock); -} - -int -nouveau_fbcon_init(struct drm_device *dev) -{ - struct nouveau_drm *drm = nouveau_drm(dev); - struct nouveau_fbdev *fbcon; - int preferred_bpp = nouveau_fbcon_bpp; - int ret; - - if (!dev->mode_config.num_crtc || - (to_pci_dev(dev->dev)->class >> 8) != PCI_CLASS_DISPLAY_VGA) - return 0; - - fbcon = kzalloc(sizeof(struct nouveau_fbdev), GFP_KERNEL); - if (!fbcon) - return -ENOMEM; - - drm->fbcon = fbcon; - INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work); - mutex_init(&fbcon->hotplug_lock); - - drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs); - - ret = drm_fb_helper_init(dev, &fbcon->helper); - if (ret) - goto free; - - if (preferred_bpp != 8 && preferred_bpp != 16 && preferred_bpp != 32) { - if (drm->client.device.info.ram_size <= 32 * 1024 * 1024) - preferred_bpp = 8; - else - if (drm->client.device.info.ram_size <= 64 * 1024 * 1024) - preferred_bpp = 16; - else - preferred_bpp = 32; - } - - /* disable all the possible outputs/crtcs before entering KMS mode */ - if (!drm_drv_uses_atomic_modeset(dev)) - drm_helper_disable_unused_functions(dev); - - ret = drm_fb_helper_initial_config(&fbcon->helper, preferred_bpp); - if (ret) - goto fini; - - if (fbcon->helper.info) - fbcon->helper.info->pixmap.buf_align = 4; - return 0; - -fini: - drm_fb_helper_fini(&fbcon->helper); -free: - kfree(fbcon); - drm->fbcon = NULL; - return ret; -} - -void -nouveau_fbcon_fini(struct drm_device *dev) -{ - struct nouveau_drm *drm = nouveau_drm(dev); - - if (!drm->fbcon) - return; - - drm_kms_helper_poll_fini(dev); - nouveau_fbcon_accel_fini(dev); - nouveau_fbcon_destroy(dev, drm->fbcon); - kfree(drm->fbcon); - drm->fbcon = NULL; -} diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c index fcf2a002f6cb..91fb494d4009 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c @@ -151,6 +151,9 @@ nvkm_firmware_mem_page(struct nvkm_memory *memory) static enum nvkm_memory_target nvkm_firmware_mem_target(struct nvkm_memory *memory) { + if (nvkm_firmware_mem(memory)->device->func->tegra) + return NVKM_MEM_TARGET_NCOH; + return NVKM_MEM_TARGET_HOST; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 364fea320cb3..1c81e5b34d29 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2405,7 +2405,7 @@ nv162_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2440,7 +2440,7 @@ nv164_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2475,7 +2475,7 @@ nv166_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2510,7 +2510,7 @@ nv167_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, @@ -2545,7 +2545,7 @@ nv168_chipset = { .bus = { 0x00000001, gf100_bus_new }, .devinit = { 0x00000001, tu102_devinit_new }, .fault = { 0x00000001, tu102_fault_new }, - .fb = { 0x00000001, gv100_fb_new }, + .fb = { 0x00000001, tu102_fb_new }, .fuse = { 0x00000001, gm107_fuse_new }, .gpio = { 0x00000001, gk104_gpio_new }, .gsp = { 0x00000001, gv100_gsp_new }, diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c index 393ade9f7e6c..b7da3ab44c27 100644 --- a/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/falcon/gm200.c @@ -48,6 +48,16 @@ gm200_flcn_pio_dmem_rd(struct nvkm_falcon *falcon, u8 port, const u8 *img, int l img += 4; len -= 4; } + + /* Sigh. Tegra PMU FW's init message... */ + if (len) { + u32 data = nvkm_falcon_rd32(falcon, 0x1c4 + (port * 8)); + + while (len--) { + *(u8 *)img++ = data & 0xff; + data >>= 8; + } + } } static void @@ -64,6 +74,8 @@ gm200_flcn_pio_dmem_wr(struct nvkm_falcon *falcon, u8 port, const u8 *img, int l img += 4; len -= 4; } + + WARN_ON(len); } static void @@ -74,7 +86,7 @@ gm200_flcn_pio_dmem_wr_init(struct nvkm_falcon *falcon, u8 port, bool sec, u32 d const struct nvkm_falcon_func_pio gm200_flcn_dmem_pio = { - .min = 4, + .min = 1, .max = 0x100, .wr_init = gm200_flcn_pio_dmem_wr_init, .wr = gm200_flcn_pio_dmem_wr, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c index 634f64f88fc8..81a1ad2c88a7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c @@ -65,10 +65,33 @@ tu102_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq) return ret; } +static int +tu102_devinit_wait(struct nvkm_device *device) +{ + unsigned timeout = 50 + 2000; + + do { + if (nvkm_rd32(device, 0x118128) & 0x00000001) { + if ((nvkm_rd32(device, 0x118234) & 0x000000ff) == 0xff) + return 0; + } + + usleep_range(1000, 2000); + } while (timeout--); + + return -ETIMEDOUT; +} + int tu102_devinit_post(struct nvkm_devinit *base, bool post) { struct nv50_devinit *init = nv50_devinit(base); + int ret; + + ret = tu102_devinit_wait(init->base.subdev.device); + if (ret) + return ret; + gm200_devinit_preos(init, post); return 0; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild index 5d0bab8ecb43..6ba5120a2ebe 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild @@ -32,6 +32,7 @@ nvkm-y += nvkm/subdev/fb/gp100.o nvkm-y += nvkm/subdev/fb/gp102.o nvkm-y += nvkm/subdev/fb/gp10b.o nvkm-y += nvkm/subdev/fb/gv100.o +nvkm-y += nvkm/subdev/fb/tu102.o nvkm-y += nvkm/subdev/fb/ga100.o nvkm-y += nvkm/subdev/fb/ga102.o diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c index 8b7c8ea5e8a5..5a21b0ae4595 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c @@ -40,12 +40,6 @@ ga102_fb_vpr_scrub(struct nvkm_fb *fb) return ret; } -static bool -ga102_fb_vpr_scrub_required(struct nvkm_fb *fb) -{ - return (nvkm_rd32(fb->subdev.device, 0x1fa80c) & 0x00000010) != 0; -} - static const struct nvkm_fb_func ga102_fb = { .dtor = gf100_fb_dtor, @@ -56,7 +50,7 @@ ga102_fb = { .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, .ram_new = ga102_ram_new, .default_bigpage = 16, - .vpr.scrub_required = ga102_fb_vpr_scrub_required, + .vpr.scrub_required = tu102_fb_vpr_scrub_required, .vpr.scrub = ga102_fb_vpr_scrub, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c index 1f0126437c1a..0e3c0a8f5d71 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c @@ -49,8 +49,3 @@ gv100_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, s } MODULE_FIRMWARE("nvidia/gv100/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin"); -MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h index ac03eac0f261..f517751f94ac 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h @@ -89,4 +89,6 @@ bool gp102_fb_vpr_scrub_required(struct nvkm_fb *); int gp102_fb_vpr_scrub(struct nvkm_fb *); int gv100_fb_init_page(struct nvkm_fb *); + +bool tu102_fb_vpr_scrub_required(struct nvkm_fb *); #endif diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c new file mode 100644 index 000000000000..be82af0364ee --- /dev/null +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/tu102.c @@ -0,0 +1,55 @@ +/* + * Copyright 2018 Red Hat Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ +#include "gf100.h" +#include "ram.h" + +bool +tu102_fb_vpr_scrub_required(struct nvkm_fb *fb) +{ + return (nvkm_rd32(fb->subdev.device, 0x1fa80c) & 0x00000010) != 0; +} + +static const struct nvkm_fb_func +tu102_fb = { + .dtor = gf100_fb_dtor, + .oneinit = gf100_fb_oneinit, + .init = gm200_fb_init, + .init_page = gv100_fb_init_page, + .init_unkn = gp100_fb_init_unkn, + .sysmem.flush_page_init = gf100_fb_sysmem_flush_page_init, + .vpr.scrub_required = tu102_fb_vpr_scrub_required, + .vpr.scrub = gp102_fb_vpr_scrub, + .ram_new = gp100_ram_new, + .default_bigpage = 16, +}; + +int +tu102_fb_new(struct nvkm_device *device, enum nvkm_subdev_type type, int inst, struct nvkm_fb **pfb) +{ + return gp102_fb_new_(&tu102_fb, device, type, inst, pfb); +} + +MODULE_FIRMWARE("nvidia/tu102/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu104/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu106/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu116/nvdec/scrubber.bin"); +MODULE_FIRMWARE("nvidia/tu117/nvdec/scrubber.bin"); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c index a72403777329..2ed04da3621d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gm20b.c @@ -225,7 +225,7 @@ gm20b_pmu_init(struct nvkm_pmu *pmu) pmu->initmsg_received = false; - nvkm_falcon_load_dmem(falcon, &args, addr_args, sizeof(args), 0); + nvkm_falcon_pio_wr(falcon, (u8 *)&args, 0, 0, DMEM, addr_args, sizeof(args), 0, false); nvkm_falcon_start(falcon); return 0; } diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 857a2f0420d7..c924f1124ebc 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1193,14 +1193,11 @@ static int boe_panel_enter_sleep_mode(struct boe_panel *boe) return 0; } -static int boe_panel_unprepare(struct drm_panel *panel) +static int boe_panel_disable(struct drm_panel *panel) { struct boe_panel *boe = to_boe_panel(panel); int ret; - if (!boe->prepared) - return 0; - ret = boe_panel_enter_sleep_mode(boe); if (ret < 0) { dev_err(panel->dev, "failed to set panel off: %d\n", ret); @@ -1209,6 +1206,16 @@ static int boe_panel_unprepare(struct drm_panel *panel) msleep(150); + return 0; +} + +static int boe_panel_unprepare(struct drm_panel *panel) +{ + struct boe_panel *boe = to_boe_panel(panel); + + if (!boe->prepared) + return 0; + if (boe->desc->discharge_on_disable) { regulator_disable(boe->avee); regulator_disable(boe->avdd); @@ -1528,6 +1535,7 @@ static enum drm_panel_orientation boe_panel_get_orientation(struct drm_panel *pa } static const struct drm_panel_funcs boe_panel_funcs = { + .disable = boe_panel_disable, .unprepare = boe_panel_unprepare, .prepare = boe_panel_prepare, .enable = boe_panel_enable, diff --git a/drivers/gpu/drm/panfrost/Kconfig b/drivers/gpu/drm/panfrost/Kconfig index 079600328be1..e6403a9d66ad 100644 --- a/drivers/gpu/drm/panfrost/Kconfig +++ b/drivers/gpu/drm/panfrost/Kconfig @@ -3,7 +3,8 @@ config DRM_PANFROST tristate "Panfrost (DRM support for ARM Mali Midgard/Bifrost GPUs)" depends on DRM - depends on ARM || ARM64 || (COMPILE_TEST && !GENERIC_ATOMIC64) + depends on ARM || ARM64 || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE depends on MMU select DRM_SCHED select IOMMU_SUPPORT diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c index 53464afc2b9a..91f69e62430b 100644 --- a/drivers/gpu/drm/solomon/ssd130x.c +++ b/drivers/gpu/drm/solomon/ssd130x.c @@ -656,18 +656,8 @@ static const struct drm_crtc_helper_funcs ssd130x_crtc_helper_funcs = { .atomic_check = drm_crtc_helper_atomic_check, }; -static void ssd130x_crtc_reset(struct drm_crtc *crtc) -{ - struct drm_device *drm = crtc->dev; - struct ssd130x_device *ssd130x = drm_to_ssd130x(drm); - - ssd130x_init(ssd130x); - - drm_atomic_helper_crtc_reset(crtc); -} - static const struct drm_crtc_funcs ssd130x_crtc_funcs = { - .reset = ssd130x_crtc_reset, + .reset = drm_atomic_helper_crtc_reset, .destroy = drm_crtc_cleanup, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, @@ -686,6 +676,12 @@ static void ssd130x_encoder_helper_atomic_enable(struct drm_encoder *encoder, if (ret) return; + ret = ssd130x_init(ssd130x); + if (ret) { + ssd130x_power_off(ssd130x); + return; + } + ssd130x_write_cmd(ssd130x, 1, SSD130X_DISPLAY_ON); backlight_enable(ssd130x->bl_dev); diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index ba3aa0a0fc43..da5493f789df 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -173,7 +173,7 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, clear = src_iter->ops->maps_tt && (!ttm || !ttm_tt_is_populated(ttm)); if (!(clear && ttm && !(ttm->page_flags & TTM_TT_FLAG_ZERO_ALLOC))) - ttm_move_memcpy(clear, ttm->num_pages, dst_iter, src_iter); + ttm_move_memcpy(clear, PFN_UP(dst_mem->size), dst_iter, src_iter); if (!src_iter->ops->maps_tt) ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, src_mem); diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index 43d9b3a6a352..c5947ed8cc81 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -179,6 +179,7 @@ static void vc4_bo_destroy(struct vc4_bo *bo) bo->validated_shader = NULL; } + mutex_destroy(&bo->madv_lock); drm_gem_dma_free(&bo->base); } @@ -394,7 +395,6 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size) { struct vc4_dev *vc4 = to_vc4_dev(dev); struct vc4_bo *bo; - int ret; if (WARN_ON_ONCE(vc4->is_vc5)) return ERR_PTR(-ENODEV); @@ -406,9 +406,7 @@ struct drm_gem_object *vc4_create_object(struct drm_device *dev, size_t size) bo->madv = VC4_MADV_WILLNEED; refcount_set(&bo->usecnt, 0); - ret = drmm_mutex_init(dev, &bo->madv_lock); - if (ret) - return ERR_PTR(ret); + mutex_init(&bo->madv_lock); mutex_lock(&vc4->bo_lock); bo->label = VC4_BO_TYPE_KERNEL; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 12a00d644b61..55744216392b 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -3018,7 +3018,8 @@ static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi) } vc4_hdmi->cec_adap = cec_allocate_adapter(&vc4_hdmi_cec_adap_ops, - vc4_hdmi, "vc4", + vc4_hdmi, + vc4_hdmi->variant->card_name, CEC_CAP_DEFAULTS | CEC_CAP_CONNECTOR_INFO, 1); ret = PTR_ERR_OR_ZERO(vc4_hdmi->cec_adap); diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 5d05093014ac..9f4a90493aea 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -358,10 +358,18 @@ static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data, drm_gem_object_release(obj); return ret; } - drm_gem_object_put(obj); rc->res_handle = qobj->hw_res_handle; /* similiar to a VM address */ rc->bo_handle = handle; + + /* + * The handle owns the reference now. But we must drop our + * remaining reference *after* we no longer need to dereference + * the obj. Otherwise userspace could guess the handle and + * race closing it from another thread. + */ + drm_gem_object_put(obj); + return 0; } @@ -723,11 +731,18 @@ static int virtio_gpu_resource_create_blob_ioctl(struct drm_device *dev, drm_gem_object_release(obj); return ret; } - drm_gem_object_put(obj); rc_blob->res_handle = bo->hw_res_handle; rc_blob->bo_handle = handle; + /* + * The handle owns the reference now. But we must drop our + * remaining reference *after* we no longer need to dereference + * the obj. Otherwise userspace could guess the handle and + * race closing it from another thread. + */ + drm_gem_object_put(obj); + return 0; } diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.c b/drivers/gpu/drm/vmwgfx/ttm_object.c index 932b125ebf3d..ddf8373c1d77 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_object.c +++ b/drivers/gpu/drm/vmwgfx/ttm_object.c @@ -254,40 +254,6 @@ void ttm_base_object_unref(struct ttm_base_object **p_base) kref_put(&base->refcount, ttm_release_base); } -/** - * ttm_base_object_noref_lookup - look up a base object without reference - * @tfile: The struct ttm_object_file the object is registered with. - * @key: The object handle. - * - * This function looks up a ttm base object and returns a pointer to it - * without refcounting the pointer. The returned pointer is only valid - * until ttm_base_object_noref_release() is called, and the object - * pointed to by the returned pointer may be doomed. Any persistent usage - * of the object requires a refcount to be taken using kref_get_unless_zero(). - * Iff this function returns successfully it needs to be paired with - * ttm_base_object_noref_release() and no sleeping- or scheduling functions - * may be called inbetween these function callse. - * - * Return: A pointer to the object if successful or NULL otherwise. - */ -struct ttm_base_object * -ttm_base_object_noref_lookup(struct ttm_object_file *tfile, uint64_t key) -{ - struct vmwgfx_hash_item *hash; - int ret; - - rcu_read_lock(); - ret = ttm_tfile_find_ref_rcu(tfile, key, &hash); - if (ret) { - rcu_read_unlock(); - return NULL; - } - - __release(RCU); - return hlist_entry(hash, struct ttm_ref_object, hash)->obj; -} -EXPORT_SYMBOL(ttm_base_object_noref_lookup); - struct ttm_base_object *ttm_base_object_lookup(struct ttm_object_file *tfile, uint64_t key) { @@ -295,15 +261,16 @@ struct ttm_base_object *ttm_base_object_lookup(struct ttm_object_file *tfile, struct vmwgfx_hash_item *hash; int ret; - rcu_read_lock(); - ret = ttm_tfile_find_ref_rcu(tfile, key, &hash); + spin_lock(&tfile->lock); + ret = ttm_tfile_find_ref(tfile, key, &hash); if (likely(ret == 0)) { base = hlist_entry(hash, struct ttm_ref_object, hash)->obj; if (!kref_get_unless_zero(&base->refcount)) base = NULL; } - rcu_read_unlock(); + spin_unlock(&tfile->lock); + return base; } diff --git a/drivers/gpu/drm/vmwgfx/ttm_object.h b/drivers/gpu/drm/vmwgfx/ttm_object.h index f0ebbe340ad6..8098a3846bae 100644 --- a/drivers/gpu/drm/vmwgfx/ttm_object.h +++ b/drivers/gpu/drm/vmwgfx/ttm_object.h @@ -307,18 +307,4 @@ extern int ttm_prime_handle_to_fd(struct ttm_object_file *tfile, #define ttm_prime_object_kfree(__obj, __prime) \ kfree_rcu(__obj, __prime.base.rhead) -struct ttm_base_object * -ttm_base_object_noref_lookup(struct ttm_object_file *tfile, uint64_t key); - -/** - * ttm_base_object_noref_release - release a base object pointer looked up - * without reference - * - * Releases a base object pointer looked up with ttm_base_object_noref_lookup(). - */ -static inline void ttm_base_object_noref_release(void) -{ - __acquire(RCU); - rcu_read_unlock(); -} #endif diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index 321c551784a1..aa1cd5126a32 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -716,44 +716,6 @@ int vmw_user_bo_lookup(struct drm_file *filp, } /** - * vmw_user_bo_noref_lookup - Look up a vmw user buffer object without reference - * @filp: The TTM object file the handle is registered with. - * @handle: The user buffer object handle. - * - * This function looks up a struct vmw_bo and returns a pointer to the - * struct vmw_buffer_object it derives from without refcounting the pointer. - * The returned pointer is only valid until vmw_user_bo_noref_release() is - * called, and the object pointed to by the returned pointer may be doomed. - * Any persistent usage of the object requires a refcount to be taken using - * ttm_bo_reference_unless_doomed(). Iff this function returns successfully it - * needs to be paired with vmw_user_bo_noref_release() and no sleeping- - * or scheduling functions may be called in between these function calls. - * - * Return: A struct vmw_buffer_object pointer if successful or negative - * error pointer on failure. - */ -struct vmw_buffer_object * -vmw_user_bo_noref_lookup(struct drm_file *filp, u32 handle) -{ - struct vmw_buffer_object *vmw_bo; - struct ttm_buffer_object *bo; - struct drm_gem_object *gobj = drm_gem_object_lookup(filp, handle); - - if (!gobj) { - DRM_ERROR("Invalid buffer object handle 0x%08lx.\n", - (unsigned long)handle); - return ERR_PTR(-ESRCH); - } - vmw_bo = gem_to_vmw_bo(gobj); - bo = ttm_bo_get_unless_zero(&vmw_bo->base); - vmw_bo = vmw_buffer_object(bo); - drm_gem_object_put(gobj); - - return vmw_bo; -} - - -/** * vmw_bo_fence_single - Utility function to fence a single TTM buffer * object without unreserving it. * diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index b062b020b378..5acbf5849b27 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -830,12 +830,7 @@ extern int vmw_user_resource_lookup_handle( uint32_t handle, const struct vmw_user_resource_conv *converter, struct vmw_resource **p_res); -extern struct vmw_resource * -vmw_user_resource_noref_lookup_handle(struct vmw_private *dev_priv, - struct ttm_object_file *tfile, - uint32_t handle, - const struct vmw_user_resource_conv * - converter); + extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data, @@ -875,15 +870,6 @@ static inline bool vmw_resource_mob_attached(const struct vmw_resource *res) } /** - * vmw_user_resource_noref_release - release a user resource pointer looked up - * without reference - */ -static inline void vmw_user_resource_noref_release(void) -{ - ttm_base_object_noref_release(); -} - -/** * Buffer object helper functions - vmwgfx_bo.c */ extern int vmw_bo_pin_in_placement(struct vmw_private *vmw_priv, @@ -934,8 +920,6 @@ extern void vmw_bo_unmap(struct vmw_buffer_object *vbo); extern void vmw_bo_move_notify(struct ttm_buffer_object *bo, struct ttm_resource *mem); extern void vmw_bo_swap_notify(struct ttm_buffer_object *bo); -extern struct vmw_buffer_object * -vmw_user_bo_noref_lookup(struct drm_file *filp, u32 handle); /** * vmw_bo_adjust_prio - Adjust the buffer object eviction priority diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index a5379f6fb5ab..a44d53e33cdb 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -290,20 +290,26 @@ static void vmw_execbuf_rcache_update(struct vmw_res_cache_entry *rcache, rcache->valid_handle = 0; } +enum vmw_val_add_flags { + vmw_val_add_flag_none = 0, + vmw_val_add_flag_noctx = 1 << 0, +}; + /** - * vmw_execbuf_res_noref_val_add - Add a resource described by an unreferenced - * rcu-protected pointer to the validation list. + * vmw_execbuf_res_val_add - Add a resource to the validation list. * * @sw_context: Pointer to the software context. * @res: Unreferenced rcu-protected pointer to the resource. * @dirty: Whether to change dirty status. + * @flags: specifies whether to use the context or not * * Returns: 0 on success. Negative error code on failure. Typical error codes * are %-EINVAL on inconsistency and %-ESRCH if the resource was doomed. */ -static int vmw_execbuf_res_noref_val_add(struct vmw_sw_context *sw_context, - struct vmw_resource *res, - u32 dirty) +static int vmw_execbuf_res_val_add(struct vmw_sw_context *sw_context, + struct vmw_resource *res, + u32 dirty, + u32 flags) { struct vmw_private *dev_priv = res->dev_priv; int ret; @@ -318,24 +324,30 @@ static int vmw_execbuf_res_noref_val_add(struct vmw_sw_context *sw_context, if (dirty) vmw_validation_res_set_dirty(sw_context->ctx, rcache->private, dirty); - vmw_user_resource_noref_release(); return 0; } - priv_size = vmw_execbuf_res_size(dev_priv, res_type); - ret = vmw_validation_add_resource(sw_context->ctx, res, priv_size, - dirty, (void **)&ctx_info, - &first_usage); - vmw_user_resource_noref_release(); - if (ret) - return ret; + if ((flags & vmw_val_add_flag_noctx) != 0) { + ret = vmw_validation_add_resource(sw_context->ctx, res, 0, dirty, + (void **)&ctx_info, NULL); + if (ret) + return ret; - if (priv_size && first_usage) { - ret = vmw_cmd_ctx_first_setup(dev_priv, sw_context, res, - ctx_info); - if (ret) { - VMW_DEBUG_USER("Failed first usage context setup.\n"); + } else { + priv_size = vmw_execbuf_res_size(dev_priv, res_type); + ret = vmw_validation_add_resource(sw_context->ctx, res, priv_size, + dirty, (void **)&ctx_info, + &first_usage); + if (ret) return ret; + + if (priv_size && first_usage) { + ret = vmw_cmd_ctx_first_setup(dev_priv, sw_context, res, + ctx_info); + if (ret) { + VMW_DEBUG_USER("Failed first usage context setup.\n"); + return ret; + } } } @@ -344,43 +356,6 @@ static int vmw_execbuf_res_noref_val_add(struct vmw_sw_context *sw_context, } /** - * vmw_execbuf_res_noctx_val_add - Add a non-context resource to the resource - * validation list if it's not already on it - * - * @sw_context: Pointer to the software context. - * @res: Pointer to the resource. - * @dirty: Whether to change dirty status. - * - * Returns: Zero on success. Negative error code on failure. - */ -static int vmw_execbuf_res_noctx_val_add(struct vmw_sw_context *sw_context, - struct vmw_resource *res, - u32 dirty) -{ - struct vmw_res_cache_entry *rcache; - enum vmw_res_type res_type = vmw_res_type(res); - void *ptr; - int ret; - - rcache = &sw_context->res_cache[res_type]; - if (likely(rcache->valid && rcache->res == res)) { - if (dirty) - vmw_validation_res_set_dirty(sw_context->ctx, - rcache->private, dirty); - return 0; - } - - ret = vmw_validation_add_resource(sw_context->ctx, res, 0, dirty, - &ptr, NULL); - if (ret) - return ret; - - vmw_execbuf_rcache_update(rcache, res, ptr); - - return 0; -} - -/** * vmw_view_res_val_add - Add a view and the surface it's pointing to to the * validation list * @@ -398,13 +373,13 @@ static int vmw_view_res_val_add(struct vmw_sw_context *sw_context, * First add the resource the view is pointing to, otherwise it may be * swapped out when the view is validated. */ - ret = vmw_execbuf_res_noctx_val_add(sw_context, vmw_view_srf(view), - vmw_view_dirtying(view)); + ret = vmw_execbuf_res_val_add(sw_context, vmw_view_srf(view), + vmw_view_dirtying(view), vmw_val_add_flag_noctx); if (ret) return ret; - return vmw_execbuf_res_noctx_val_add(sw_context, view, - VMW_RES_DIRTY_NONE); + return vmw_execbuf_res_val_add(sw_context, view, VMW_RES_DIRTY_NONE, + vmw_val_add_flag_noctx); } /** @@ -475,8 +450,9 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv, if (IS_ERR(res)) continue; - ret = vmw_execbuf_res_noctx_val_add(sw_context, res, - VMW_RES_DIRTY_SET); + ret = vmw_execbuf_res_val_add(sw_context, res, + VMW_RES_DIRTY_SET, + vmw_val_add_flag_noctx); if (unlikely(ret != 0)) return ret; } @@ -490,9 +466,9 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv, if (vmw_res_type(entry->res) == vmw_res_view) ret = vmw_view_res_val_add(sw_context, entry->res); else - ret = vmw_execbuf_res_noctx_val_add - (sw_context, entry->res, - vmw_binding_dirtying(entry->bt)); + ret = vmw_execbuf_res_val_add(sw_context, entry->res, + vmw_binding_dirtying(entry->bt), + vmw_val_add_flag_noctx); if (unlikely(ret != 0)) break; } @@ -658,7 +634,8 @@ vmw_cmd_res_check(struct vmw_private *dev_priv, { struct vmw_res_cache_entry *rcache = &sw_context->res_cache[res_type]; struct vmw_resource *res; - int ret; + int ret = 0; + bool needs_unref = false; if (p_res) *p_res = NULL; @@ -683,17 +660,18 @@ vmw_cmd_res_check(struct vmw_private *dev_priv, if (ret) return ret; - res = vmw_user_resource_noref_lookup_handle - (dev_priv, sw_context->fp->tfile, *id_loc, converter); - if (IS_ERR(res)) { + ret = vmw_user_resource_lookup_handle + (dev_priv, sw_context->fp->tfile, *id_loc, converter, &res); + if (ret != 0) { VMW_DEBUG_USER("Could not find/use resource 0x%08x.\n", (unsigned int) *id_loc); - return PTR_ERR(res); + return ret; } + needs_unref = true; - ret = vmw_execbuf_res_noref_val_add(sw_context, res, dirty); + ret = vmw_execbuf_res_val_add(sw_context, res, dirty, vmw_val_add_flag_none); if (unlikely(ret != 0)) - return ret; + goto res_check_done; if (rcache->valid && rcache->res == res) { rcache->valid_handle = true; @@ -708,7 +686,11 @@ vmw_cmd_res_check(struct vmw_private *dev_priv, if (p_res) *p_res = res; - return 0; +res_check_done: + if (needs_unref) + vmw_resource_unreference(&res); + + return ret; } /** @@ -1171,9 +1153,9 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, int ret; vmw_validation_preload_bo(sw_context->ctx); - vmw_bo = vmw_user_bo_noref_lookup(sw_context->filp, handle); - if (IS_ERR(vmw_bo)) { - VMW_DEBUG_USER("Could not find or use MOB buffer.\n"); + ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo); + if (ret != 0) { + drm_dbg(&dev_priv->drm, "Could not find or use MOB buffer.\n"); return PTR_ERR(vmw_bo); } ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, true, false); @@ -1225,9 +1207,9 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, int ret; vmw_validation_preload_bo(sw_context->ctx); - vmw_bo = vmw_user_bo_noref_lookup(sw_context->filp, handle); - if (IS_ERR(vmw_bo)) { - VMW_DEBUG_USER("Could not find or use GMR region.\n"); + ret = vmw_user_bo_lookup(sw_context->filp, handle, &vmw_bo); + if (ret != 0) { + drm_dbg(&dev_priv->drm, "Could not find or use GMR region.\n"); return PTR_ERR(vmw_bo); } ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo, false, false); @@ -2025,8 +2007,9 @@ static int vmw_cmd_set_shader(struct vmw_private *dev_priv, res = vmw_shader_lookup(vmw_context_res_man(ctx), cmd->body.shid, cmd->body.type); if (!IS_ERR(res)) { - ret = vmw_execbuf_res_noctx_val_add(sw_context, res, - VMW_RES_DIRTY_NONE); + ret = vmw_execbuf_res_val_add(sw_context, res, + VMW_RES_DIRTY_NONE, + vmw_val_add_flag_noctx); if (unlikely(ret != 0)) return ret; @@ -2273,8 +2256,9 @@ static int vmw_cmd_dx_set_shader(struct vmw_private *dev_priv, return PTR_ERR(res); } - ret = vmw_execbuf_res_noctx_val_add(sw_context, res, - VMW_RES_DIRTY_NONE); + ret = vmw_execbuf_res_val_add(sw_context, res, + VMW_RES_DIRTY_NONE, + vmw_val_add_flag_noctx); if (ret) return ret; } @@ -2777,8 +2761,8 @@ static int vmw_cmd_dx_bind_shader(struct vmw_private *dev_priv, return PTR_ERR(res); } - ret = vmw_execbuf_res_noctx_val_add(sw_context, res, - VMW_RES_DIRTY_NONE); + ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE, + vmw_val_add_flag_noctx); if (ret) { VMW_DEBUG_USER("Error creating resource validation node.\n"); return ret; @@ -3098,8 +3082,8 @@ static int vmw_cmd_dx_bind_streamoutput(struct vmw_private *dev_priv, vmw_dx_streamoutput_set_size(res, cmd->body.sizeInBytes); - ret = vmw_execbuf_res_noctx_val_add(sw_context, res, - VMW_RES_DIRTY_NONE); + ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE, + vmw_val_add_flag_noctx); if (ret) { DRM_ERROR("Error creating resource validation node.\n"); return ret; @@ -3148,8 +3132,8 @@ static int vmw_cmd_dx_set_streamoutput(struct vmw_private *dev_priv, return 0; } - ret = vmw_execbuf_res_noctx_val_add(sw_context, res, - VMW_RES_DIRTY_NONE); + ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_NONE, + vmw_val_add_flag_noctx); if (ret) { DRM_ERROR("Error creating resource validation node.\n"); return ret; @@ -4066,22 +4050,26 @@ static int vmw_execbuf_tie_context(struct vmw_private *dev_priv, if (ret) return ret; - res = vmw_user_resource_noref_lookup_handle + ret = vmw_user_resource_lookup_handle (dev_priv, sw_context->fp->tfile, handle, - user_context_converter); - if (IS_ERR(res)) { + user_context_converter, &res); + if (ret != 0) { VMW_DEBUG_USER("Could not find or user DX context 0x%08x.\n", (unsigned int) handle); - return PTR_ERR(res); + return ret; } - ret = vmw_execbuf_res_noref_val_add(sw_context, res, VMW_RES_DIRTY_SET); - if (unlikely(ret != 0)) + ret = vmw_execbuf_res_val_add(sw_context, res, VMW_RES_DIRTY_SET, + vmw_val_add_flag_none); + if (unlikely(ret != 0)) { + vmw_resource_unreference(&res); return ret; + } sw_context->dx_ctx_node = vmw_execbuf_info_from_res(sw_context, res); sw_context->man = vmw_context_res_man(res); + vmw_resource_unreference(&res); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h b/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h index 4f40167ad61f..4f40167ad61f 100755..100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg_arm64.h diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index f66caa540e14..c7d645e5ec7b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -281,39 +281,6 @@ out_bad_resource: return ret; } -/** - * vmw_user_resource_noref_lookup_handle - lookup a struct resource from a - * TTM user-space handle and perform basic type checks - * - * @dev_priv: Pointer to a device private struct - * @tfile: Pointer to a struct ttm_object_file identifying the caller - * @handle: The TTM user-space handle - * @converter: Pointer to an object describing the resource type - * - * If the handle can't be found or is associated with an incorrect resource - * type, -EINVAL will be returned. - */ -struct vmw_resource * -vmw_user_resource_noref_lookup_handle(struct vmw_private *dev_priv, - struct ttm_object_file *tfile, - uint32_t handle, - const struct vmw_user_resource_conv - *converter) -{ - struct ttm_base_object *base; - - base = ttm_base_object_noref_lookup(tfile, handle); - if (!base) - return ERR_PTR(-ESRCH); - - if (unlikely(ttm_base_object_type(base) != converter->object_type)) { - ttm_base_object_noref_release(); - return ERR_PTR(-EINVAL); - } - - return converter->base_obj_to_res(base); -} - /* * Helper function that looks either a surface or bo. * diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c index 0d8e6bd1ccbf..90996c108146 100644 --- a/drivers/gpu/drm/xen/xen_drm_front.c +++ b/drivers/gpu/drm/xen/xen_drm_front.c @@ -717,7 +717,7 @@ static int xen_drv_probe(struct xenbus_device *xb_dev, return xenbus_switch_state(xb_dev, XenbusStateInitialising); } -static int xen_drv_remove(struct xenbus_device *dev) +static void xen_drv_remove(struct xenbus_device *dev) { struct xen_drm_front_info *front_info = dev_get_drvdata(&dev->dev); int to = 100; @@ -751,7 +751,6 @@ static int xen_drv_remove(struct xenbus_device *dev) xen_drm_drv_fini(front_info); xenbus_frontend_closed(dev); - return 0; } static const struct xenbus_device_id xen_driver_ids[] = { diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c index ab125f79408f..1fb0f7105fb2 100644 --- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c +++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c @@ -282,7 +282,7 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata) } rc = mp2_ops->get_rep_desc(cl_idx, cl_data->report_descr[i]); if (rc) - return rc; + goto cleanup; mp2_ops->start(privdata, info); status = amd_sfh_wait_for_response (privdata, cl_data->sensor_idx[i], SENSOR_ENABLED); diff --git a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c index 4da2f9f62aba..a1d6e08fab7d 100644 --- a/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c +++ b/drivers/hid/amd-sfh-hid/sfh1_1/amd_sfh_init.c @@ -160,7 +160,7 @@ static int amd_sfh1_1_hid_client_init(struct amd_mp2_dev *privdata) } rc = mp2_ops->get_rep_desc(cl_idx, cl_data->report_descr[i]); if (rc) - return rc; + goto cleanup; writel(0, privdata->mmio + AMD_P2C_MSG(0)); mp2_ops->start(privdata, info); diff --git a/drivers/hid/hid-betopff.c b/drivers/hid/hid-betopff.c index 467d789f9bc2..25ed7b9a917e 100644 --- a/drivers/hid/hid-betopff.c +++ b/drivers/hid/hid-betopff.c @@ -60,7 +60,6 @@ static int betopff_init(struct hid_device *hid) struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; struct input_dev *dev; - int field_count = 0; int error; int i, j; @@ -86,19 +85,21 @@ static int betopff_init(struct hid_device *hid) * ----------------------------------------- * Do init them with default value. */ + if (report->maxfield < 4) { + hid_err(hid, "not enough fields in the report: %d\n", + report->maxfield); + return -ENODEV; + } for (i = 0; i < report->maxfield; i++) { + if (report->field[i]->report_count < 1) { + hid_err(hid, "no values in the field\n"); + return -ENODEV; + } for (j = 0; j < report->field[i]->report_count; j++) { report->field[i]->value[j] = 0x00; - field_count++; } } - if (field_count < 4) { - hid_err(hid, "not enough fields in the report: %d\n", - field_count); - return -ENODEV; - } - betopff = kzalloc(sizeof(*betopff), GFP_KERNEL); if (!betopff) return -ENOMEM; diff --git a/drivers/hid/hid-bigbenff.c b/drivers/hid/hid-bigbenff.c index e8c5e3ac9fff..e8b16665860d 100644 --- a/drivers/hid/hid-bigbenff.c +++ b/drivers/hid/hid-bigbenff.c @@ -344,6 +344,11 @@ static int bigben_probe(struct hid_device *hid, } report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list; + if (list_empty(report_list)) { + hid_err(hid, "no output report found\n"); + error = -ENODEV; + goto error_hw_stop; + } bigben->report = list_entry(report_list->next, struct hid_report, list); diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index bd47628da6be..3e1803592bd4 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -993,8 +993,8 @@ struct hid_report *hid_validate_values(struct hid_device *hid, * Validating on id 0 means we should examine the first * report in the list. */ - report = list_entry( - hid->report_enum[type].report_list.next, + report = list_first_entry_or_null( + &hid->report_enum[type].report_list, struct hid_report, list); } else { report = hid->report_enum[type].report_id_hash[id]; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 82713ef3aaa6..0f8c11842a3a 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -274,7 +274,6 @@ #define USB_DEVICE_ID_CH_AXIS_295 0x001c #define USB_VENDOR_ID_CHERRY 0x046a -#define USB_DEVICE_ID_CHERRY_MOUSE_000C 0x000c #define USB_DEVICE_ID_CHERRY_CYMOTION 0x0023 #define USB_DEVICE_ID_CHERRY_CYMOTION_SOLAR 0x0027 @@ -1295,6 +1294,7 @@ #define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G540 0x0075 #define USB_DEVICE_ID_UGEE_XPPEN_TABLET_G640 0x0094 #define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01 0x0042 +#define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2 0x0905 #define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L 0x0935 #define USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_S 0x0909 #define USB_DEVICE_ID_UGEE_XPPEN_TABLET_STAR06 0x0078 diff --git a/drivers/hid/hid-playstation.c b/drivers/hid/hid-playstation.c index f399bf0d3c8c..27c40894acab 100644 --- a/drivers/hid/hid-playstation.c +++ b/drivers/hid/hid-playstation.c @@ -944,6 +944,7 @@ ATTRIBUTE_GROUPS(ps_device); static int dualsense_get_calibration_data(struct dualsense *ds) { + struct hid_device *hdev = ds->base.hdev; short gyro_pitch_bias, gyro_pitch_plus, gyro_pitch_minus; short gyro_yaw_bias, gyro_yaw_plus, gyro_yaw_minus; short gyro_roll_bias, gyro_roll_plus, gyro_roll_minus; @@ -954,6 +955,7 @@ static int dualsense_get_calibration_data(struct dualsense *ds) int speed_2x; int range_2g; int ret = 0; + int i; uint8_t *buf; buf = kzalloc(DS_FEATURE_REPORT_CALIBRATION_SIZE, GFP_KERNEL); @@ -1006,6 +1008,21 @@ static int dualsense_get_calibration_data(struct dualsense *ds) ds->gyro_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus; /* + * Sanity check gyro calibration data. This is needed to prevent crashes + * during report handling of virtual, clone or broken devices not implementing + * calibration data properly. + */ + for (i = 0; i < ARRAY_SIZE(ds->gyro_calib_data); i++) { + if (ds->gyro_calib_data[i].sens_denom == 0) { + hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.", + ds->gyro_calib_data[i].abs_code); + ds->gyro_calib_data[i].bias = 0; + ds->gyro_calib_data[i].sens_numer = DS_GYRO_RANGE; + ds->gyro_calib_data[i].sens_denom = S16_MAX; + } + } + + /* * Set accelerometer calibration and normalization parameters. * Data values will be normalized to 1/DS_ACC_RES_PER_G g. */ @@ -1027,6 +1044,21 @@ static int dualsense_get_calibration_data(struct dualsense *ds) ds->accel_calib_data[2].sens_numer = 2*DS_ACC_RES_PER_G; ds->accel_calib_data[2].sens_denom = range_2g; + /* + * Sanity check accelerometer calibration data. This is needed to prevent crashes + * during report handling of virtual, clone or broken devices not implementing calibration + * data properly. + */ + for (i = 0; i < ARRAY_SIZE(ds->accel_calib_data); i++) { + if (ds->accel_calib_data[i].sens_denom == 0) { + hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.", + ds->accel_calib_data[i].abs_code); + ds->accel_calib_data[i].bias = 0; + ds->accel_calib_data[i].sens_numer = DS_ACC_RANGE; + ds->accel_calib_data[i].sens_denom = S16_MAX; + } + } + err_free: kfree(buf); return ret; @@ -1737,6 +1769,7 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4) int speed_2x; int range_2g; int ret = 0; + int i; uint8_t *buf; if (ds4->base.hdev->bus == BUS_USB) { @@ -1831,6 +1864,21 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4) ds4->gyro_calib_data[2].sens_denom = gyro_roll_plus - gyro_roll_minus; /* + * Sanity check gyro calibration data. This is needed to prevent crashes + * during report handling of virtual, clone or broken devices not implementing + * calibration data properly. + */ + for (i = 0; i < ARRAY_SIZE(ds4->gyro_calib_data); i++) { + if (ds4->gyro_calib_data[i].sens_denom == 0) { + hid_warn(hdev, "Invalid gyro calibration data for axis (%d), disabling calibration.", + ds4->gyro_calib_data[i].abs_code); + ds4->gyro_calib_data[i].bias = 0; + ds4->gyro_calib_data[i].sens_numer = DS4_GYRO_RANGE; + ds4->gyro_calib_data[i].sens_denom = S16_MAX; + } + } + + /* * Set accelerometer calibration and normalization parameters. * Data values will be normalized to 1/DS4_ACC_RES_PER_G g. */ @@ -1852,6 +1900,21 @@ static int dualshock4_get_calibration_data(struct dualshock4 *ds4) ds4->accel_calib_data[2].sens_numer = 2*DS4_ACC_RES_PER_G; ds4->accel_calib_data[2].sens_denom = range_2g; + /* + * Sanity check accelerometer calibration data. This is needed to prevent crashes + * during report handling of virtual, clone or broken devices not implementing calibration + * data properly. + */ + for (i = 0; i < ARRAY_SIZE(ds4->accel_calib_data); i++) { + if (ds4->accel_calib_data[i].sens_denom == 0) { + hid_warn(hdev, "Invalid accelerometer calibration data for axis (%d), disabling calibration.", + ds4->accel_calib_data[i].abs_code); + ds4->accel_calib_data[i].bias = 0; + ds4->accel_calib_data[i].sens_numer = DS4_ACC_RANGE; + ds4->accel_calib_data[i].sens_denom = S16_MAX; + } + } + err_free: kfree(buf); return ret; diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index 0e9702c7f7d6..be3ad02573de 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -54,7 +54,6 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_FLIGHT_SIM_YOKE), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_PEDALS), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_PRO_THROTTLE), HID_QUIRK_NOGET }, - { HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_MOUSE_000C), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K65RGB_RAPIDFIRE), HID_QUIRK_NO_INIT_REPORTS | HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CORSAIR, USB_DEVICE_ID_CORSAIR_K70RGB), HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 7fa6fe04f1b2..cfbbc39807a6 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -526,6 +526,8 @@ static const struct hid_device_id uclogic_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, + USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2) }, + { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L) }, { HID_USB_DEVICE(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_S) }, diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index cd1233d7e253..3c5eea3df328 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -1656,6 +1656,8 @@ int uclogic_params_init(struct uclogic_params *params, case VID_PID(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_PARBLO_A610_PRO): case VID_PID(USB_VENDOR_ID_UGEE, + USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO01_V2): + case VID_PID(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_L): case VID_PID(USB_VENDOR_ID_UGEE, USB_DEVICE_ID_UGEE_XPPEN_TABLET_DECO_PRO_S): diff --git a/drivers/hid/intel-ish-hid/ishtp/dma-if.c b/drivers/hid/intel-ish-hid/ishtp/dma-if.c index 40554c8daca0..00046cbfd4ed 100644 --- a/drivers/hid/intel-ish-hid/ishtp/dma-if.c +++ b/drivers/hid/intel-ish-hid/ishtp/dma-if.c @@ -104,6 +104,11 @@ void *ishtp_cl_get_dma_send_buf(struct ishtp_device *dev, int required_slots = (size / DMA_SLOT_SIZE) + 1 * (size % DMA_SLOT_SIZE != 0); + if (!dev->ishtp_dma_tx_map) { + dev_err(dev->devc, "Fail to allocate Tx map\n"); + return NULL; + } + spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags); for (i = 0; i <= (dev->ishtp_dma_num_slots - required_slots); i++) { free = 1; @@ -150,6 +155,11 @@ void ishtp_cl_release_dma_acked_mem(struct ishtp_device *dev, return; } + if (!dev->ishtp_dma_tx_map) { + dev_err(dev->devc, "Fail to allocate Tx map\n"); + return; + } + i = (msg_addr - dev->ishtp_host_dma_tx_buf) / DMA_SLOT_SIZE; spin_lock_irqsave(&dev->ishtp_dma_tx_lock, flags); for (j = 0; j < acked_slots; j++) { diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index cbe43e2567a7..64ac5bdee3a6 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1963,7 +1963,7 @@ static void hv_balloon_debugfs_init(struct hv_dynmem_device *b) static void hv_balloon_debugfs_exit(struct hv_dynmem_device *b) { - debugfs_remove(debugfs_lookup("hv-balloon", NULL)); + debugfs_lookup_and_remove("hv-balloon", NULL); } #else diff --git a/drivers/i2c/busses/i2c-axxia.c b/drivers/i2c/busses/i2c-axxia.c index bdf3b50de8ad..c1c74ce08407 100644 --- a/drivers/i2c/busses/i2c-axxia.c +++ b/drivers/i2c/busses/i2c-axxia.c @@ -118,7 +118,7 @@ #define SDA_HOLD_TIME 0x90 /** - * axxia_i2c_dev - I2C device context + * struct axxia_i2c_dev - I2C device context * @base: pointer to register struct * @msg: pointer to current message * @msg_r: pointer to current read message (sequence transfer) diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index a3240ece55b2..581e02cc979a 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -351,7 +351,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset) * * If your hardware is free from tHD;STA issue, try this one. */ - return DIV_ROUND_CLOSEST(ic_clk * tSYMBOL, MICRO) - 8 + offset; + return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * tSYMBOL, MICRO) - + 8 + offset; else /* * Conditional expression: @@ -367,7 +368,8 @@ u32 i2c_dw_scl_hcnt(u32 ic_clk, u32 tSYMBOL, u32 tf, int cond, int offset) * The reason why we need to take into account "tf" here, * is the same as described in i2c_dw_scl_lcnt(). */ - return DIV_ROUND_CLOSEST(ic_clk * (tSYMBOL + tf), MICRO) - 3 + offset; + return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tSYMBOL + tf), MICRO) - + 3 + offset; } u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset) @@ -383,7 +385,8 @@ u32 i2c_dw_scl_lcnt(u32 ic_clk, u32 tLOW, u32 tf, int offset) * account the fall time of SCL signal (tf). Default tf value * should be 0.3 us, for safety. */ - return DIV_ROUND_CLOSEST(ic_clk * (tLOW + tf), MICRO) - 1 + offset; + return DIV_ROUND_CLOSEST_ULL((u64)ic_clk * (tLOW + tf), MICRO) - + 1 + offset; } int i2c_dw_set_sda_hold(struct dw_i2c_dev *dev) diff --git a/drivers/i2c/busses/i2c-designware-pcidrv.c b/drivers/i2c/busses/i2c-designware-pcidrv.c index e499f96506c5..782fe1ef3ca1 100644 --- a/drivers/i2c/busses/i2c-designware-pcidrv.c +++ b/drivers/i2c/busses/i2c-designware-pcidrv.c @@ -396,6 +396,8 @@ static const struct pci_device_id i2_designware_pci_ids[] = { { PCI_VDEVICE(ATI, 0x73a4), navi_amd }, { PCI_VDEVICE(ATI, 0x73e4), navi_amd }, { PCI_VDEVICE(ATI, 0x73c4), navi_amd }, + { PCI_VDEVICE(ATI, 0x7444), navi_amd }, + { PCI_VDEVICE(ATI, 0x7464), navi_amd }, { 0,} }; MODULE_DEVICE_TABLE(pci, i2_designware_pci_ids); diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index ba043b547393..74182db03a88 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -351,13 +351,11 @@ static int dw_i2c_plat_probe(struct platform_device *pdev) if (dev->flags & ACCESS_NO_IRQ_SUSPEND) { dev_pm_set_driver_flags(&pdev->dev, - DPM_FLAG_SMART_PREPARE | - DPM_FLAG_MAY_SKIP_RESUME); + DPM_FLAG_SMART_PREPARE); } else { dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_SMART_PREPARE | - DPM_FLAG_SMART_SUSPEND | - DPM_FLAG_MAY_SKIP_RESUME); + DPM_FLAG_SMART_SUSPEND); } device_enable_async_suspend(&pdev->dev); @@ -419,21 +417,8 @@ static int dw_i2c_plat_prepare(struct device *dev) */ return !has_acpi_companion(dev); } - -static void dw_i2c_plat_complete(struct device *dev) -{ - /* - * The device can only be in runtime suspend at this point if it has not - * been resumed throughout the ending system suspend/resume cycle, so if - * the platform firmware might mess up with it, request the runtime PM - * framework to resume it. - */ - if (pm_runtime_suspended(dev) && pm_resume_via_firmware()) - pm_request_resume(dev); -} #else #define dw_i2c_plat_prepare NULL -#define dw_i2c_plat_complete NULL #endif #ifdef CONFIG_PM @@ -483,7 +468,6 @@ static int __maybe_unused dw_i2c_plat_resume(struct device *dev) static const struct dev_pm_ops dw_i2c_dev_pm_ops = { .prepare = dw_i2c_plat_prepare, - .complete = dw_i2c_plat_complete, SET_LATE_SYSTEM_SLEEP_PM_OPS(dw_i2c_plat_suspend, dw_i2c_plat_resume) SET_RUNTIME_PM_OPS(dw_i2c_plat_runtime_suspend, dw_i2c_plat_runtime_resume, NULL) }; diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c index 5af5cffc444e..d113bed79545 100644 --- a/drivers/i2c/busses/i2c-mxs.c +++ b/drivers/i2c/busses/i2c-mxs.c @@ -826,8 +826,8 @@ static int mxs_i2c_probe(struct platform_device *pdev) /* Setup the DMA */ i2c->dmach = dma_request_chan(dev, "rx-tx"); if (IS_ERR(i2c->dmach)) { - dev_err(dev, "Failed to request dma\n"); - return PTR_ERR(i2c->dmach); + return dev_err_probe(dev, PTR_ERR(i2c->dmach), + "Failed to request dma\n"); } platform_set_drvdata(pdev, i2c); diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index d1658ed76562..b31cf4f18f85 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -80,7 +80,7 @@ enum { #define DEFAULT_SCL_RATE (100 * 1000) /* Hz */ /** - * struct i2c_spec_values: + * struct i2c_spec_values - I2C specification values for various modes * @min_hold_start_ns: min hold time (repeated) START condition * @min_low_ns: min LOW period of the SCL clock * @min_high_ns: min HIGH period of the SCL cloc @@ -136,7 +136,7 @@ static const struct i2c_spec_values fast_mode_plus_spec = { }; /** - * struct rk3x_i2c_calced_timings: + * struct rk3x_i2c_calced_timings - calculated V1 timings * @div_low: Divider output for low * @div_high: Divider output for high * @tuning: Used to adjust setup/hold data time, @@ -159,7 +159,7 @@ enum rk3x_i2c_state { }; /** - * struct rk3x_i2c_soc_data: + * struct rk3x_i2c_soc_data - SOC-specific data * @grf_offset: offset inside the grf regmap for setting the i2c type * @calc_timings: Callback function for i2c timing information calculated */ @@ -239,7 +239,8 @@ static inline void rk3x_i2c_clean_ipd(struct rk3x_i2c *i2c) } /** - * Generate a START condition, which triggers a REG_INT_START interrupt. + * rk3x_i2c_start - Generate a START condition, which triggers a REG_INT_START interrupt. + * @i2c: target controller data */ static void rk3x_i2c_start(struct rk3x_i2c *i2c) { @@ -258,8 +259,8 @@ static void rk3x_i2c_start(struct rk3x_i2c *i2c) } /** - * Generate a STOP condition, which triggers a REG_INT_STOP interrupt. - * + * rk3x_i2c_stop - Generate a STOP condition, which triggers a REG_INT_STOP interrupt. + * @i2c: target controller data * @error: Error code to return in rk3x_i2c_xfer */ static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error) @@ -298,7 +299,8 @@ static void rk3x_i2c_stop(struct rk3x_i2c *i2c, int error) } /** - * Setup a read according to i2c->msg + * rk3x_i2c_prepare_read - Setup a read according to i2c->msg + * @i2c: target controller data */ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c) { @@ -329,7 +331,8 @@ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c) } /** - * Fill the transmit buffer with data from i2c->msg + * rk3x_i2c_fill_transmit_buf - Fill the transmit buffer with data from i2c->msg + * @i2c: target controller data */ static void rk3x_i2c_fill_transmit_buf(struct rk3x_i2c *i2c) { @@ -532,11 +535,10 @@ out: } /** - * Get timing values of I2C specification - * + * rk3x_i2c_get_spec - Get timing values of I2C specification * @speed: Desired SCL frequency * - * Returns: Matched i2c spec values. + * Return: Matched i2c_spec_values. */ static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed) { @@ -549,13 +551,12 @@ static const struct i2c_spec_values *rk3x_i2c_get_spec(unsigned int speed) } /** - * Calculate divider values for desired SCL frequency - * + * rk3x_i2c_v0_calc_timings - Calculate divider values for desired SCL frequency * @clk_rate: I2C input clock rate * @t: Known I2C timing information * @t_calc: Caculated rk3x private timings that would be written into regs * - * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case + * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case * a best-effort divider value is returned in divs. If the target rate is * too high, we silently use the highest possible rate. */ @@ -710,13 +711,12 @@ static int rk3x_i2c_v0_calc_timings(unsigned long clk_rate, } /** - * Calculate timing values for desired SCL frequency - * + * rk3x_i2c_v1_calc_timings - Calculate timing values for desired SCL frequency * @clk_rate: I2C input clock rate * @t: Known I2C timing information * @t_calc: Caculated rk3x private timings that would be written into regs * - * Returns: 0 on success, -EINVAL if the goal SCL rate is too slow. In that case + * Return: %0 on success, -%EINVAL if the goal SCL rate is too slow. In that case * a best-effort divider value is returned in divs. If the target rate is * too high, we silently use the highest possible rate. * The following formulas are v1's method to calculate timings. @@ -960,14 +960,14 @@ static int rk3x_i2c_clk_notifier_cb(struct notifier_block *nb, unsigned long } /** - * Setup I2C registers for an I2C operation specified by msgs, num. - * - * Must be called with i2c->lock held. - * + * rk3x_i2c_setup - Setup I2C registers for an I2C operation specified by msgs, num. + * @i2c: target controller data * @msgs: I2C msgs to process * @num: Number of msgs * - * returns: Number of I2C msgs processed or negative in case of error + * Must be called with i2c->lock held. + * + * Return: Number of I2C msgs processed or negative in case of error */ static int rk3x_i2c_setup(struct rk3x_i2c *i2c, struct i2c_msg *msgs, int num) { diff --git a/drivers/iio/accel/hid-sensor-accel-3d.c b/drivers/iio/accel/hid-sensor-accel-3d.c index a2def6f9380a..5eac7ea19993 100644 --- a/drivers/iio/accel/hid-sensor-accel-3d.c +++ b/drivers/iio/accel/hid-sensor-accel-3d.c @@ -280,6 +280,7 @@ static int accel_3d_capture_sample(struct hid_sensor_hub_device *hsdev, hid_sensor_convert_timestamp( &accel_state->common_attributes, *(int64_t *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/adc/berlin2-adc.c b/drivers/iio/adc/berlin2-adc.c index 3d2e8b4db61a..a4e7c7eff5ac 100644 --- a/drivers/iio/adc/berlin2-adc.c +++ b/drivers/iio/adc/berlin2-adc.c @@ -298,8 +298,10 @@ static int berlin2_adc_probe(struct platform_device *pdev) int ret; indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*priv)); - if (!indio_dev) + if (!indio_dev) { + of_node_put(parent_np); return -ENOMEM; + } priv = iio_priv(indio_dev); diff --git a/drivers/iio/adc/imx8qxp-adc.c b/drivers/iio/adc/imx8qxp-adc.c index 36777b827165..f5a0fc9e64c5 100644 --- a/drivers/iio/adc/imx8qxp-adc.c +++ b/drivers/iio/adc/imx8qxp-adc.c @@ -86,6 +86,8 @@ #define IMX8QXP_ADC_TIMEOUT msecs_to_jiffies(100) +#define IMX8QXP_ADC_MAX_FIFO_SIZE 16 + struct imx8qxp_adc { struct device *dev; void __iomem *regs; @@ -95,6 +97,7 @@ struct imx8qxp_adc { /* Serialise ADC channel reads */ struct mutex lock; struct completion completion; + u32 fifo[IMX8QXP_ADC_MAX_FIFO_SIZE]; }; #define IMX8QXP_ADC_CHAN(_idx) { \ @@ -238,8 +241,7 @@ static int imx8qxp_adc_read_raw(struct iio_dev *indio_dev, return ret; } - *val = FIELD_GET(IMX8QXP_ADC_RESFIFO_VAL_MASK, - readl(adc->regs + IMX8QXP_ADR_ADC_RESFIFO)); + *val = adc->fifo[0]; mutex_unlock(&adc->lock); return IIO_VAL_INT; @@ -265,10 +267,15 @@ static irqreturn_t imx8qxp_adc_isr(int irq, void *dev_id) { struct imx8qxp_adc *adc = dev_id; u32 fifo_count; + int i; fifo_count = FIELD_GET(IMX8QXP_ADC_FCTRL_FCOUNT_MASK, readl(adc->regs + IMX8QXP_ADR_ADC_FCTRL)); + for (i = 0; i < fifo_count; i++) + adc->fifo[i] = FIELD_GET(IMX8QXP_ADC_RESFIFO_VAL_MASK, + readl_relaxed(adc->regs + IMX8QXP_ADR_ADC_RESFIFO)); + if (fifo_count) complete(&adc->completion); diff --git a/drivers/iio/adc/stm32-dfsdm-adc.c b/drivers/iio/adc/stm32-dfsdm-adc.c index 6d21ea84fa82..a428bdb567d5 100644 --- a/drivers/iio/adc/stm32-dfsdm-adc.c +++ b/drivers/iio/adc/stm32-dfsdm-adc.c @@ -1520,6 +1520,7 @@ static const struct of_device_id stm32_dfsdm_adc_match[] = { }, {} }; +MODULE_DEVICE_TABLE(of, stm32_dfsdm_adc_match); static int stm32_dfsdm_adc_probe(struct platform_device *pdev) { diff --git a/drivers/iio/adc/twl6030-gpadc.c b/drivers/iio/adc/twl6030-gpadc.c index f53e8558b560..32873fb5f367 100644 --- a/drivers/iio/adc/twl6030-gpadc.c +++ b/drivers/iio/adc/twl6030-gpadc.c @@ -57,6 +57,18 @@ #define TWL6030_GPADCS BIT(1) #define TWL6030_GPADCR BIT(0) +#define USB_VBUS_CTRL_SET 0x04 +#define USB_ID_CTRL_SET 0x06 + +#define TWL6030_MISC1 0xE4 +#define VBUS_MEAS 0x01 +#define ID_MEAS 0x01 + +#define VAC_MEAS 0x04 +#define VBAT_MEAS 0x02 +#define BB_MEAS 0x01 + + /** * struct twl6030_chnl_calib - channel calibration * @gain: slope coefficient for ideal curve @@ -927,6 +939,26 @@ static int twl6030_gpadc_probe(struct platform_device *pdev) return ret; } + ret = twl_i2c_write_u8(TWL_MODULE_USB, VBUS_MEAS, USB_VBUS_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL_MODULE_USB, ID_MEAS, USB_ID_CTRL_SET); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + + ret = twl_i2c_write_u8(TWL6030_MODULE_ID0, + VBAT_MEAS | BB_MEAS | VAC_MEAS, + TWL6030_MISC1); + if (ret < 0) { + dev_err(dev, "failed to wire up inputs\n"); + return ret; + } + indio_dev->name = DRIVER_NAME; indio_dev->info = &twl6030_gpadc_iio_info; indio_dev->modes = INDIO_DIRECT_MODE; diff --git a/drivers/iio/adc/xilinx-ams.c b/drivers/iio/adc/xilinx-ams.c index 5b4bdf3a26bb..a507d2e17079 100644 --- a/drivers/iio/adc/xilinx-ams.c +++ b/drivers/iio/adc/xilinx-ams.c @@ -1329,7 +1329,7 @@ static int ams_parse_firmware(struct iio_dev *indio_dev) dev_channels = devm_krealloc(dev, ams_channels, dev_size, GFP_KERNEL); if (!dev_channels) - ret = -ENOMEM; + return -ENOMEM; indio_dev->channels = dev_channels; indio_dev->num_channels = num_channels; diff --git a/drivers/iio/gyro/hid-sensor-gyro-3d.c b/drivers/iio/gyro/hid-sensor-gyro-3d.c index 8f0ad022c7f1..698c50da1f10 100644 --- a/drivers/iio/gyro/hid-sensor-gyro-3d.c +++ b/drivers/iio/gyro/hid-sensor-gyro-3d.c @@ -231,6 +231,7 @@ static int gyro_3d_capture_sample(struct hid_sensor_hub_device *hsdev, gyro_state->timestamp = hid_sensor_convert_timestamp(&gyro_state->common_attributes, *(s64 *)raw_data); + ret = 0; break; default: break; diff --git a/drivers/iio/imu/fxos8700_core.c b/drivers/iio/imu/fxos8700_core.c index 423cfe526f2a..6d189c4b9ff9 100644 --- a/drivers/iio/imu/fxos8700_core.c +++ b/drivers/iio/imu/fxos8700_core.c @@ -10,6 +10,7 @@ #include <linux/regmap.h> #include <linux/acpi.h> #include <linux/bitops.h> +#include <linux/bitfield.h> #include <linux/iio/iio.h> #include <linux/iio/sysfs.h> @@ -144,9 +145,8 @@ #define FXOS8700_NVM_DATA_BNK0 0xa7 /* Bit definitions for FXOS8700_CTRL_REG1 */ -#define FXOS8700_CTRL_ODR_MSK 0x38 #define FXOS8700_CTRL_ODR_MAX 0x00 -#define FXOS8700_CTRL_ODR_MIN GENMASK(4, 3) +#define FXOS8700_CTRL_ODR_MSK GENMASK(5, 3) /* Bit definitions for FXOS8700_M_CTRL_REG1 */ #define FXOS8700_HMS_MASK GENMASK(1, 0) @@ -320,7 +320,7 @@ static enum fxos8700_sensor fxos8700_to_sensor(enum iio_chan_type iio_type) switch (iio_type) { case IIO_ACCEL: return FXOS8700_ACCEL; - case IIO_ANGL_VEL: + case IIO_MAGN: return FXOS8700_MAGN; default: return -EINVAL; @@ -345,15 +345,35 @@ static int fxos8700_set_active_mode(struct fxos8700_data *data, static int fxos8700_set_scale(struct fxos8700_data *data, enum fxos8700_sensor t, int uscale) { - int i; + int i, ret, val; + bool active_mode; static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale); struct device *dev = regmap_get_device(data->regmap); if (t == FXOS8700_MAGN) { - dev_err(dev, "Magnetometer scale is locked at 1200uT\n"); + dev_err(dev, "Magnetometer scale is locked at 0.001Gs\n"); return -EINVAL; } + /* + * When device is in active mode, it failed to set an ACCEL + * full-scale range(2g/4g/8g) in FXOS8700_XYZ_DATA_CFG. + * This is not align with the datasheet, but it is a fxos8700 + * chip behavier. Set the device in standby mode before setting + * an ACCEL full-scale range. + */ + ret = regmap_read(data->regmap, FXOS8700_CTRL_REG1, &val); + if (ret) + return ret; + + active_mode = val & FXOS8700_ACTIVE; + if (active_mode) { + ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1, + val & ~FXOS8700_ACTIVE); + if (ret) + return ret; + } + for (i = 0; i < scale_num; i++) if (fxos8700_accel_scale[i].uscale == uscale) break; @@ -361,8 +381,12 @@ static int fxos8700_set_scale(struct fxos8700_data *data, if (i == scale_num) return -EINVAL; - return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, + ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, fxos8700_accel_scale[i].bits); + if (ret) + return ret; + return regmap_write(data->regmap, FXOS8700_CTRL_REG1, + active_mode); } static int fxos8700_get_scale(struct fxos8700_data *data, @@ -372,7 +396,7 @@ static int fxos8700_get_scale(struct fxos8700_data *data, static const int scale_num = ARRAY_SIZE(fxos8700_accel_scale); if (t == FXOS8700_MAGN) { - *uscale = 1200; /* Magnetometer is locked at 1200uT */ + *uscale = 1000; /* Magnetometer is locked at 0.001Gs */ return 0; } @@ -394,22 +418,61 @@ static int fxos8700_get_data(struct fxos8700_data *data, int chan_type, int axis, int *val) { u8 base, reg; + s16 tmp; int ret; - enum fxos8700_sensor type = fxos8700_to_sensor(chan_type); - base = type ? FXOS8700_OUT_X_MSB : FXOS8700_M_OUT_X_MSB; + /* + * Different register base addresses varies with channel types. + * This bug hasn't been noticed before because using an enum is + * really hard to read. Use an a switch statement to take over that. + */ + switch (chan_type) { + case IIO_ACCEL: + base = FXOS8700_OUT_X_MSB; + break; + case IIO_MAGN: + base = FXOS8700_M_OUT_X_MSB; + break; + default: + return -EINVAL; + } /* Block read 6 bytes of device output registers to avoid data loss */ ret = regmap_bulk_read(data->regmap, base, data->buf, - FXOS8700_DATA_BUF_SIZE); + sizeof(data->buf)); if (ret) return ret; /* Convert axis to buffer index */ reg = axis - IIO_MOD_X; + /* + * Convert to native endianness. The accel data and magn data + * are signed, so a forced type conversion is needed. + */ + tmp = be16_to_cpu(data->buf[reg]); + + /* + * ACCEL output data registers contain the X-axis, Y-axis, and Z-axis + * 14-bit left-justified sample data and MAGN output data registers + * contain the X-axis, Y-axis, and Z-axis 16-bit sample data. Apply + * a signed 2 bits right shift to the readback raw data from ACCEL + * output data register and keep that from MAGN sensor as the origin. + * Value should be extended to 32 bit. + */ + switch (chan_type) { + case IIO_ACCEL: + tmp = tmp >> 2; + break; + case IIO_MAGN: + /* Nothing to do */ + break; + default: + return -EINVAL; + } + /* Convert to native endianness */ - *val = sign_extend32(be16_to_cpu(data->buf[reg]), 15); + *val = sign_extend32(tmp, 15); return 0; } @@ -445,10 +508,9 @@ static int fxos8700_set_odr(struct fxos8700_data *data, enum fxos8700_sensor t, if (i >= odr_num) return -EINVAL; - return regmap_update_bits(data->regmap, - FXOS8700_CTRL_REG1, - FXOS8700_CTRL_ODR_MSK + FXOS8700_ACTIVE, - fxos8700_odr[i].bits << 3 | active_mode); + val &= ~FXOS8700_CTRL_ODR_MSK; + val |= FIELD_PREP(FXOS8700_CTRL_ODR_MSK, fxos8700_odr[i].bits) | FXOS8700_ACTIVE; + return regmap_write(data->regmap, FXOS8700_CTRL_REG1, val); } static int fxos8700_get_odr(struct fxos8700_data *data, enum fxos8700_sensor t, @@ -461,7 +523,7 @@ static int fxos8700_get_odr(struct fxos8700_data *data, enum fxos8700_sensor t, if (ret) return ret; - val &= FXOS8700_CTRL_ODR_MSK; + val = FIELD_GET(FXOS8700_CTRL_ODR_MSK, val); for (i = 0; i < odr_num; i++) if (val == fxos8700_odr[i].bits) @@ -526,7 +588,7 @@ static IIO_CONST_ATTR(in_accel_sampling_frequency_available, static IIO_CONST_ATTR(in_magn_sampling_frequency_available, "1.5625 6.25 12.5 50 100 200 400 800"); static IIO_CONST_ATTR(in_accel_scale_available, "0.000244 0.000488 0.000976"); -static IIO_CONST_ATTR(in_magn_scale_available, "0.000001200"); +static IIO_CONST_ATTR(in_magn_scale_available, "0.001000"); static struct attribute *fxos8700_attrs[] = { &iio_const_attr_in_accel_sampling_frequency_available.dev_attr.attr, @@ -592,14 +654,19 @@ static int fxos8700_chip_init(struct fxos8700_data *data, bool use_spi) if (ret) return ret; - /* Max ODR (800Hz individual or 400Hz hybrid), active mode */ - ret = regmap_write(data->regmap, FXOS8700_CTRL_REG1, - FXOS8700_CTRL_ODR_MAX | FXOS8700_ACTIVE); + /* + * Set max full-scale range (+/-8G) for ACCEL sensor in chip + * initialization then activate the device. + */ + ret = regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G); if (ret) return ret; - /* Set for max full-scale range (+/-8G) */ - return regmap_write(data->regmap, FXOS8700_XYZ_DATA_CFG, MODE_8G); + /* Max ODR (800Hz individual or 400Hz hybrid), active mode */ + return regmap_update_bits(data->regmap, FXOS8700_CTRL_REG1, + FXOS8700_CTRL_ODR_MSK | FXOS8700_ACTIVE, + FIELD_PREP(FXOS8700_CTRL_ODR_MSK, FXOS8700_CTRL_ODR_MAX) | + FXOS8700_ACTIVE); } static void fxos8700_chip_uninit(void *data) diff --git a/drivers/iio/imu/st_lsm6dsx/Kconfig b/drivers/iio/imu/st_lsm6dsx/Kconfig index f6660847fb58..8c16cdacf2f2 100644 --- a/drivers/iio/imu/st_lsm6dsx/Kconfig +++ b/drivers/iio/imu/st_lsm6dsx/Kconfig @@ -4,6 +4,7 @@ config IIO_ST_LSM6DSX tristate "ST_LSM6DSx driver for STM 6-axis IMU MEMS sensors" depends on (I2C || SPI || I3C) select IIO_BUFFER + select IIO_TRIGGERED_BUFFER select IIO_KFIFO_BUF select IIO_ST_LSM6DSX_I2C if (I2C) select IIO_ST_LSM6DSX_SPI if (SPI_MASTER) diff --git a/drivers/iio/light/cm32181.c b/drivers/iio/light/cm32181.c index 001055d09750..b1674a5bfa36 100644 --- a/drivers/iio/light/cm32181.c +++ b/drivers/iio/light/cm32181.c @@ -440,6 +440,8 @@ static int cm32181_probe(struct i2c_client *client) if (!indio_dev) return -ENOMEM; + i2c_set_clientdata(client, indio_dev); + /* * Some ACPI systems list 2 I2C resources for the CM3218 sensor, the * SMBus Alert Response Address (ARA, 0x0c) and the actual I2C address. @@ -460,8 +462,6 @@ static int cm32181_probe(struct i2c_client *client) return PTR_ERR(client); } - i2c_set_clientdata(client, indio_dev); - cm32181 = iio_priv(indio_dev); cm32181->client = client; cm32181->dev = dev; @@ -490,7 +490,8 @@ static int cm32181_probe(struct i2c_client *client) static int cm32181_suspend(struct device *dev) { - struct i2c_client *client = to_i2c_client(dev); + struct cm32181_chip *cm32181 = iio_priv(dev_get_drvdata(dev)); + struct i2c_client *client = cm32181->client; return i2c_smbus_write_word_data(client, CM32181_REG_ADDR_CMD, CM32181_CMD_ALS_DISABLE); @@ -498,8 +499,8 @@ static int cm32181_suspend(struct device *dev) static int cm32181_resume(struct device *dev) { - struct i2c_client *client = to_i2c_client(dev); struct cm32181_chip *cm32181 = iio_priv(dev_get_drvdata(dev)); + struct i2c_client *client = cm32181->client; return i2c_smbus_write_word_data(client, CM32181_REG_ADDR_CMD, cm32181->conf_regs[CM32181_REG_ADDR_CMD]); diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c index 26b021f43ba4..11b1c1603aeb 100644 --- a/drivers/infiniband/core/verbs.c +++ b/drivers/infiniband/core/verbs.c @@ -2957,15 +2957,18 @@ EXPORT_SYMBOL(__rdma_block_iter_start); bool __rdma_block_iter_next(struct ib_block_iter *biter) { unsigned int block_offset; + unsigned int sg_delta; if (!biter->__sg_nents || !biter->__sg) return false; biter->__dma_addr = sg_dma_address(biter->__sg) + biter->__sg_advance; block_offset = biter->__dma_addr & (BIT_ULL(biter->__pg_bit) - 1); - biter->__sg_advance += BIT_ULL(biter->__pg_bit) - block_offset; + sg_delta = BIT_ULL(biter->__pg_bit) - block_offset; - if (biter->__sg_advance >= sg_dma_len(biter->__sg)) { + if (sg_dma_len(biter->__sg) - biter->__sg_advance > sg_delta) { + biter->__sg_advance += sg_delta; + } else { biter->__sg_advance = 0; biter->__sg = sg_next(biter->__sg); biter->__sg_nents--; diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c index 186d30291260..b02f2f0809c8 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c @@ -23,18 +23,25 @@ static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata, static bool tid_rb_invalidate(struct mmu_interval_notifier *mni, const struct mmu_notifier_range *range, unsigned long cur_seq); +static bool tid_cover_invalidate(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq); static int program_rcvarray(struct hfi1_filedata *fd, struct tid_user_buf *, struct tid_group *grp, unsigned int start, u16 count, u32 *tidlist, unsigned int *tididx, unsigned int *pmapped); -static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo, - struct tid_group **grp); +static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo); +static void __clear_tid_node(struct hfi1_filedata *fd, + struct tid_rb_node *node); static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node); static const struct mmu_interval_notifier_ops tid_mn_ops = { .invalidate = tid_rb_invalidate, }; +static const struct mmu_interval_notifier_ops tid_cover_ops = { + .invalidate = tid_cover_invalidate, +}; /* * Initialize context and file private data needed for Expected @@ -253,53 +260,65 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, tididx = 0, mapped, mapped_pages = 0; u32 *tidlist = NULL; struct tid_user_buf *tidbuf; + unsigned long mmu_seq = 0; if (!PAGE_ALIGNED(tinfo->vaddr)) return -EINVAL; + if (tinfo->length == 0) + return -EINVAL; tidbuf = kzalloc(sizeof(*tidbuf), GFP_KERNEL); if (!tidbuf) return -ENOMEM; + mutex_init(&tidbuf->cover_mutex); tidbuf->vaddr = tinfo->vaddr; tidbuf->length = tinfo->length; tidbuf->psets = kcalloc(uctxt->expected_count, sizeof(*tidbuf->psets), GFP_KERNEL); if (!tidbuf->psets) { - kfree(tidbuf); - return -ENOMEM; + ret = -ENOMEM; + goto fail_release_mem; + } + + if (fd->use_mn) { + ret = mmu_interval_notifier_insert( + &tidbuf->notifier, current->mm, + tidbuf->vaddr, tidbuf->npages * PAGE_SIZE, + &tid_cover_ops); + if (ret) + goto fail_release_mem; + mmu_seq = mmu_interval_read_begin(&tidbuf->notifier); } pinned = pin_rcv_pages(fd, tidbuf); if (pinned <= 0) { - kfree(tidbuf->psets); - kfree(tidbuf); - return pinned; + ret = (pinned < 0) ? pinned : -ENOSPC; + goto fail_unpin; } /* Find sets of physically contiguous pages */ tidbuf->n_psets = find_phys_blocks(tidbuf, pinned); - /* - * We don't need to access this under a lock since tid_used is per - * process and the same process cannot be in hfi1_user_exp_rcv_clear() - * and hfi1_user_exp_rcv_setup() at the same time. - */ + /* Reserve the number of expected tids to be used. */ spin_lock(&fd->tid_lock); if (fd->tid_used + tidbuf->n_psets > fd->tid_limit) pageset_count = fd->tid_limit - fd->tid_used; else pageset_count = tidbuf->n_psets; + fd->tid_used += pageset_count; spin_unlock(&fd->tid_lock); - if (!pageset_count) - goto bail; + if (!pageset_count) { + ret = -ENOSPC; + goto fail_unreserve; + } ngroups = pageset_count / dd->rcv_entries.group_size; tidlist = kcalloc(pageset_count, sizeof(*tidlist), GFP_KERNEL); if (!tidlist) { ret = -ENOMEM; - goto nomem; + goto fail_unreserve; } tididx = 0; @@ -395,43 +414,78 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd, } unlock: mutex_unlock(&uctxt->exp_mutex); -nomem: hfi1_cdbg(TID, "total mapped: tidpairs:%u pages:%u (%d)", tididx, mapped_pages, ret); - if (tididx) { - spin_lock(&fd->tid_lock); - fd->tid_used += tididx; - spin_unlock(&fd->tid_lock); - tinfo->tidcnt = tididx; - tinfo->length = mapped_pages * PAGE_SIZE; - - if (copy_to_user(u64_to_user_ptr(tinfo->tidlist), - tidlist, sizeof(tidlist[0]) * tididx)) { - /* - * On failure to copy to the user level, we need to undo - * everything done so far so we don't leak resources. - */ - tinfo->tidlist = (unsigned long)&tidlist; - hfi1_user_exp_rcv_clear(fd, tinfo); - tinfo->tidlist = 0; - ret = -EFAULT; - goto bail; + + /* fail if nothing was programmed, set error if none provided */ + if (tididx == 0) { + if (ret >= 0) + ret = -ENOSPC; + goto fail_unreserve; + } + + /* adjust reserved tid_used to actual count */ + spin_lock(&fd->tid_lock); + fd->tid_used -= pageset_count - tididx; + spin_unlock(&fd->tid_lock); + + /* unpin all pages not covered by a TID */ + unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, pinned - mapped_pages, + false); + + if (fd->use_mn) { + /* check for an invalidate during setup */ + bool fail = false; + + mutex_lock(&tidbuf->cover_mutex); + fail = mmu_interval_read_retry(&tidbuf->notifier, mmu_seq); + mutex_unlock(&tidbuf->cover_mutex); + + if (fail) { + ret = -EBUSY; + goto fail_unprogram; } } - /* - * If not everything was mapped (due to insufficient RcvArray entries, - * for example), unpin all unmapped pages so we can pin them nex time. - */ - if (mapped_pages != pinned) - unpin_rcv_pages(fd, tidbuf, NULL, mapped_pages, - (pinned - mapped_pages), false); -bail: + tinfo->tidcnt = tididx; + tinfo->length = mapped_pages * PAGE_SIZE; + + if (copy_to_user(u64_to_user_ptr(tinfo->tidlist), + tidlist, sizeof(tidlist[0]) * tididx)) { + ret = -EFAULT; + goto fail_unprogram; + } + + if (fd->use_mn) + mmu_interval_notifier_remove(&tidbuf->notifier); + kfree(tidbuf->pages); kfree(tidbuf->psets); + kfree(tidbuf); kfree(tidlist); + return 0; + +fail_unprogram: + /* unprogram, unmap, and unpin all allocated TIDs */ + tinfo->tidlist = (unsigned long)tidlist; + hfi1_user_exp_rcv_clear(fd, tinfo); + tinfo->tidlist = 0; + pinned = 0; /* nothing left to unpin */ + pageset_count = 0; /* nothing left reserved */ +fail_unreserve: + spin_lock(&fd->tid_lock); + fd->tid_used -= pageset_count; + spin_unlock(&fd->tid_lock); +fail_unpin: + if (fd->use_mn) + mmu_interval_notifier_remove(&tidbuf->notifier); + if (pinned > 0) + unpin_rcv_pages(fd, tidbuf, NULL, 0, pinned, false); +fail_release_mem: kfree(tidbuf->pages); + kfree(tidbuf->psets); kfree(tidbuf); - return ret > 0 ? 0 : ret; + kfree(tidlist); + return ret; } int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd, @@ -452,7 +506,7 @@ int hfi1_user_exp_rcv_clear(struct hfi1_filedata *fd, mutex_lock(&uctxt->exp_mutex); for (tididx = 0; tididx < tinfo->tidcnt; tididx++) { - ret = unprogram_rcvarray(fd, tidinfo[tididx], NULL); + ret = unprogram_rcvarray(fd, tidinfo[tididx]); if (ret) { hfi1_cdbg(TID, "Failed to unprogram rcv array %d", ret); @@ -706,6 +760,7 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd, } node->fdata = fd; + mutex_init(&node->invalidate_mutex); node->phys = page_to_phys(pages[0]); node->npages = npages; node->rcventry = rcventry; @@ -721,11 +776,6 @@ static int set_rcvarray_entry(struct hfi1_filedata *fd, &tid_mn_ops); if (ret) goto out_unmap; - /* - * FIXME: This is in the wrong order, the notifier should be - * established before the pages are pinned by pin_rcv_pages. - */ - mmu_interval_read_begin(&node->notifier); } fd->entry_to_rb[node->rcventry - uctxt->expected_base] = node; @@ -745,8 +795,7 @@ out_unmap: return -EFAULT; } -static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo, - struct tid_group **grp) +static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo) { struct hfi1_ctxtdata *uctxt = fd->uctxt; struct hfi1_devdata *dd = uctxt->dd; @@ -769,9 +818,6 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo, if (!node || node->rcventry != (uctxt->expected_base + rcventry)) return -EBADF; - if (grp) - *grp = node->grp; - if (fd->use_mn) mmu_interval_notifier_remove(&node->notifier); cacheless_tid_rb_remove(fd, node); @@ -779,23 +825,34 @@ static int unprogram_rcvarray(struct hfi1_filedata *fd, u32 tidinfo, return 0; } -static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node) +static void __clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node) { struct hfi1_ctxtdata *uctxt = fd->uctxt; struct hfi1_devdata *dd = uctxt->dd; + mutex_lock(&node->invalidate_mutex); + if (node->freed) + goto done; + node->freed = true; + trace_hfi1_exp_tid_unreg(uctxt->ctxt, fd->subctxt, node->rcventry, node->npages, node->notifier.interval_tree.start, node->phys, node->dma_addr); - /* - * Make sure device has seen the write before we unpin the - * pages. - */ + /* Make sure device has seen the write before pages are unpinned */ hfi1_put_tid(dd, node->rcventry, PT_INVALID_FLUSH, 0, 0); unpin_rcv_pages(fd, NULL, node, 0, node->npages, true); +done: + mutex_unlock(&node->invalidate_mutex); +} + +static void clear_tid_node(struct hfi1_filedata *fd, struct tid_rb_node *node) +{ + struct hfi1_ctxtdata *uctxt = fd->uctxt; + + __clear_tid_node(fd, node); node->grp->used--; node->grp->map &= ~(1 << (node->rcventry - node->grp->base)); @@ -854,10 +911,16 @@ static bool tid_rb_invalidate(struct mmu_interval_notifier *mni, if (node->freed) return true; + /* take action only if unmapping */ + if (range->event != MMU_NOTIFY_UNMAP) + return true; + trace_hfi1_exp_tid_inval(uctxt->ctxt, fdata->subctxt, node->notifier.interval_tree.start, node->rcventry, node->npages, node->dma_addr); - node->freed = true; + + /* clear the hardware rcvarray entry */ + __clear_tid_node(fdata, node); spin_lock(&fdata->invalid_lock); if (fdata->invalid_tid_idx < uctxt->expected_count) { @@ -887,6 +950,23 @@ static bool tid_rb_invalidate(struct mmu_interval_notifier *mni, return true; } +static bool tid_cover_invalidate(struct mmu_interval_notifier *mni, + const struct mmu_notifier_range *range, + unsigned long cur_seq) +{ + struct tid_user_buf *tidbuf = + container_of(mni, struct tid_user_buf, notifier); + + /* take action only if unmapping */ + if (range->event == MMU_NOTIFY_UNMAP) { + mutex_lock(&tidbuf->cover_mutex); + mmu_interval_set_seq(mni, cur_seq); + mutex_unlock(&tidbuf->cover_mutex); + } + + return true; +} + static void cacheless_tid_rb_remove(struct hfi1_filedata *fdata, struct tid_rb_node *tnode) { diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.h b/drivers/infiniband/hw/hfi1/user_exp_rcv.h index 8c53e416bf84..f8ee997d0050 100644 --- a/drivers/infiniband/hw/hfi1/user_exp_rcv.h +++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.h @@ -16,6 +16,8 @@ struct tid_pageset { }; struct tid_user_buf { + struct mmu_interval_notifier notifier; + struct mutex cover_mutex; unsigned long vaddr; unsigned long length; unsigned int npages; @@ -27,6 +29,7 @@ struct tid_user_buf { struct tid_rb_node { struct mmu_interval_notifier notifier; struct hfi1_filedata *fdata; + struct mutex invalidate_mutex; /* covers hw removal */ unsigned long phys; struct tid_group *grp; u32 rcventry; diff --git a/drivers/infiniband/sw/rxe/rxe_param.h b/drivers/infiniband/sw/rxe/rxe_param.h index a754fc902e3d..7b41d79e72b2 100644 --- a/drivers/infiniband/sw/rxe/rxe_param.h +++ b/drivers/infiniband/sw/rxe/rxe_param.h @@ -98,11 +98,11 @@ enum rxe_device_param { RXE_MAX_SRQ = DEFAULT_MAX_VALUE - RXE_MIN_SRQ_INDEX, RXE_MIN_MR_INDEX = 0x00000001, - RXE_MAX_MR_INDEX = DEFAULT_MAX_VALUE, - RXE_MAX_MR = DEFAULT_MAX_VALUE - RXE_MIN_MR_INDEX, - RXE_MIN_MW_INDEX = 0x00010001, - RXE_MAX_MW_INDEX = 0x00020000, - RXE_MAX_MW = 0x00001000, + RXE_MAX_MR_INDEX = DEFAULT_MAX_VALUE >> 1, + RXE_MAX_MR = RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX, + RXE_MIN_MW_INDEX = RXE_MAX_MR_INDEX + 1, + RXE_MAX_MW_INDEX = DEFAULT_MAX_VALUE, + RXE_MAX_MW = RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX, RXE_MAX_PKT_PER_ACK = 64, diff --git a/drivers/infiniband/sw/rxe/rxe_pool.c b/drivers/infiniband/sw/rxe/rxe_pool.c index f50620f5a0a1..1151c0b5ccea 100644 --- a/drivers/infiniband/sw/rxe/rxe_pool.c +++ b/drivers/infiniband/sw/rxe/rxe_pool.c @@ -23,16 +23,16 @@ static const struct rxe_type_info { .size = sizeof(struct rxe_ucontext), .elem_offset = offsetof(struct rxe_ucontext, elem), .min_index = 1, - .max_index = UINT_MAX, - .max_elem = UINT_MAX, + .max_index = RXE_MAX_UCONTEXT, + .max_elem = RXE_MAX_UCONTEXT, }, [RXE_TYPE_PD] = { .name = "pd", .size = sizeof(struct rxe_pd), .elem_offset = offsetof(struct rxe_pd, elem), .min_index = 1, - .max_index = UINT_MAX, - .max_elem = UINT_MAX, + .max_index = RXE_MAX_PD, + .max_elem = RXE_MAX_PD, }, [RXE_TYPE_AH] = { .name = "ah", @@ -40,7 +40,7 @@ static const struct rxe_type_info { .elem_offset = offsetof(struct rxe_ah, elem), .min_index = RXE_MIN_AH_INDEX, .max_index = RXE_MAX_AH_INDEX, - .max_elem = RXE_MAX_AH_INDEX - RXE_MIN_AH_INDEX + 1, + .max_elem = RXE_MAX_AH, }, [RXE_TYPE_SRQ] = { .name = "srq", @@ -49,7 +49,7 @@ static const struct rxe_type_info { .cleanup = rxe_srq_cleanup, .min_index = RXE_MIN_SRQ_INDEX, .max_index = RXE_MAX_SRQ_INDEX, - .max_elem = RXE_MAX_SRQ_INDEX - RXE_MIN_SRQ_INDEX + 1, + .max_elem = RXE_MAX_SRQ, }, [RXE_TYPE_QP] = { .name = "qp", @@ -58,7 +58,7 @@ static const struct rxe_type_info { .cleanup = rxe_qp_cleanup, .min_index = RXE_MIN_QP_INDEX, .max_index = RXE_MAX_QP_INDEX, - .max_elem = RXE_MAX_QP_INDEX - RXE_MIN_QP_INDEX + 1, + .max_elem = RXE_MAX_QP, }, [RXE_TYPE_CQ] = { .name = "cq", @@ -66,8 +66,8 @@ static const struct rxe_type_info { .elem_offset = offsetof(struct rxe_cq, elem), .cleanup = rxe_cq_cleanup, .min_index = 1, - .max_index = UINT_MAX, - .max_elem = UINT_MAX, + .max_index = RXE_MAX_CQ, + .max_elem = RXE_MAX_CQ, }, [RXE_TYPE_MR] = { .name = "mr", @@ -76,7 +76,7 @@ static const struct rxe_type_info { .cleanup = rxe_mr_cleanup, .min_index = RXE_MIN_MR_INDEX, .max_index = RXE_MAX_MR_INDEX, - .max_elem = RXE_MAX_MR_INDEX - RXE_MIN_MR_INDEX + 1, + .max_elem = RXE_MAX_MR, }, [RXE_TYPE_MW] = { .name = "mw", @@ -85,7 +85,7 @@ static const struct rxe_type_info { .cleanup = rxe_mw_cleanup, .min_index = RXE_MIN_MW_INDEX, .max_index = RXE_MAX_MW_INDEX, - .max_elem = RXE_MAX_MW_INDEX - RXE_MIN_MW_INDEX + 1, + .max_elem = RXE_MAX_MW, }, }; diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c index 8d8ebdc2039b..67f1c7364c95 100644 --- a/drivers/input/misc/xen-kbdfront.c +++ b/drivers/input/misc/xen-kbdfront.c @@ -51,7 +51,7 @@ module_param_array(ptr_size, int, NULL, 0444); MODULE_PARM_DESC(ptr_size, "Pointing device width, height in pixels (default 800,600)"); -static int xenkbd_remove(struct xenbus_device *); +static void xenkbd_remove(struct xenbus_device *); static int xenkbd_connect_backend(struct xenbus_device *, struct xenkbd_info *); static void xenkbd_disconnect_backend(struct xenkbd_info *); @@ -404,7 +404,7 @@ static int xenkbd_resume(struct xenbus_device *dev) return xenkbd_connect_backend(dev, info); } -static int xenkbd_remove(struct xenbus_device *dev) +static void xenkbd_remove(struct xenbus_device *dev) { struct xenkbd_info *info = dev_get_drvdata(&dev->dev); @@ -417,7 +417,6 @@ static int xenkbd_remove(struct xenbus_device *dev) input_unregister_device(info->mtouch); free_page((unsigned long)info->page); kfree(info); - return 0; } static int xenkbd_connect_backend(struct xenbus_device *dev, diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index b0f776448a1c..fa021af8506e 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -192,7 +192,6 @@ static const char * const smbus_pnp_ids[] = { "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ - "SYN3286", /* HP Laptop 15-da3001TU */ NULL }; diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 46f8a694291e..efc61736099b 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -1240,6 +1240,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { }, { .matches = { + DMI_MATCH(DMI_BOARD_NAME, "PCX0DX"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { DMI_MATCH(DMI_BOARD_NAME, "X170SM"), }, .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | diff --git a/drivers/interconnect/qcom/icc-rpm.c b/drivers/interconnect/qcom/icc-rpm.c index ba6781f54ab7..df3196f72536 100644 --- a/drivers/interconnect/qcom/icc-rpm.c +++ b/drivers/interconnect/qcom/icc-rpm.c @@ -488,7 +488,7 @@ int qnoc_probe(struct platform_device *pdev) } regmap_done: - ret = devm_clk_bulk_get(dev, qp->num_clks, qp->bus_clks); + ret = devm_clk_bulk_get_optional(dev, qp->num_clks, qp->bus_clks); if (ret) return ret; diff --git a/drivers/interconnect/qcom/msm8996.c b/drivers/interconnect/qcom/msm8996.c index c2903ae3b3bc..25a1a32bc611 100644 --- a/drivers/interconnect/qcom/msm8996.c +++ b/drivers/interconnect/qcom/msm8996.c @@ -33,6 +33,13 @@ static const char * const bus_a0noc_clocks[] = { "aggre0_noc_mpu_cfg" }; +static const char * const bus_a2noc_clocks[] = { + "bus", + "bus_a", + "aggre2_ufs_axi", + "ufs_axi" +}; + static const u16 mas_a0noc_common_links[] = { MSM8996_SLAVE_A0NOC_SNOC }; @@ -1806,7 +1813,7 @@ static const struct regmap_config msm8996_a0noc_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0x9000, + .max_register = 0x6000, .fast_io = true }; @@ -1830,7 +1837,7 @@ static const struct regmap_config msm8996_a1noc_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0x7000, + .max_register = 0x5000, .fast_io = true }; @@ -1851,7 +1858,7 @@ static const struct regmap_config msm8996_a2noc_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0xa000, + .max_register = 0x7000, .fast_io = true }; @@ -1859,6 +1866,8 @@ static const struct qcom_icc_desc msm8996_a2noc = { .type = QCOM_ICC_NOC, .nodes = a2noc_nodes, .num_nodes = ARRAY_SIZE(a2noc_nodes), + .clocks = bus_a2noc_clocks, + .num_clocks = ARRAY_SIZE(bus_a2noc_clocks), .regmap_cfg = &msm8996_a2noc_regmap_config }; @@ -1877,7 +1886,7 @@ static const struct regmap_config msm8996_bimc_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0x62000, + .max_register = 0x5a000, .fast_io = true }; @@ -1988,7 +1997,7 @@ static const struct regmap_config msm8996_mnoc_regmap_config = { .reg_bits = 32, .reg_stride = 4, .val_bits = 32, - .max_register = 0x20000, + .max_register = 0x1c000, .fast_io = true }; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index ab160198edd6..f2425b0f0cd6 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -3858,7 +3858,9 @@ static int arm_smmu_device_remove(struct platform_device *pdev) static void arm_smmu_device_shutdown(struct platform_device *pdev) { - arm_smmu_device_remove(pdev); + struct arm_smmu_device *smmu = platform_get_drvdata(pdev); + + arm_smmu_device_disable(smmu); } static const struct of_device_id arm_smmu_of_match[] = { diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 719fbca1fe52..2ff7a72cf377 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -1316,8 +1316,14 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap) switch (cap) { case IOMMU_CAP_CACHE_COHERENCY: - /* Assume that a coherent TCU implies coherent TBUs */ - return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK; + /* + * It's overwhelmingly the case in practice that when the pagetable + * walk interface is connected to a coherent interconnect, all the + * translation interfaces are too. Furthermore if the device is + * natively coherent, then its translation interface must also be. + */ + return cfg->smmu->features & ARM_SMMU_FEAT_COHERENT_WALK || + device_get_dma_attr(dev) == DEV_DMA_COHERENT; case IOMMU_CAP_NOEXEC: return true; default: @@ -2185,19 +2191,16 @@ static int arm_smmu_device_probe(struct platform_device *pdev) return 0; } -static int arm_smmu_device_remove(struct platform_device *pdev) +static void arm_smmu_device_shutdown(struct platform_device *pdev) { struct arm_smmu_device *smmu = platform_get_drvdata(pdev); if (!smmu) - return -ENODEV; + return; if (!bitmap_empty(smmu->context_map, ARM_SMMU_MAX_CBS)) dev_notice(&pdev->dev, "disabling translation\n"); - iommu_device_unregister(&smmu->iommu); - iommu_device_sysfs_remove(&smmu->iommu); - arm_smmu_rpm_get(smmu); /* Turn the thing off */ arm_smmu_gr0_write(smmu, ARM_SMMU_GR0_sCR0, ARM_SMMU_sCR0_CLIENTPD); @@ -2209,12 +2212,21 @@ static int arm_smmu_device_remove(struct platform_device *pdev) clk_bulk_disable(smmu->num_clks, smmu->clks); clk_bulk_unprepare(smmu->num_clks, smmu->clks); - return 0; } -static void arm_smmu_device_shutdown(struct platform_device *pdev) +static int arm_smmu_device_remove(struct platform_device *pdev) { - arm_smmu_device_remove(pdev); + struct arm_smmu_device *smmu = platform_get_drvdata(pdev); + + if (!smmu) + return -ENODEV; + + iommu_device_unregister(&smmu->iommu); + iommu_device_sysfs_remove(&smmu->iommu); + + arm_smmu_device_shutdown(pdev); + + return 0; } static int __maybe_unused arm_smmu_runtime_resume(struct device *dev) diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index de91dd88705b..5f6a85aea501 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3185,14 +3185,16 @@ EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner); */ int iommu_device_claim_dma_owner(struct device *dev, void *owner) { - struct iommu_group *group = iommu_group_get(dev); + struct iommu_group *group; int ret = 0; - if (!group) - return -ENODEV; if (WARN_ON(!owner)) return -EINVAL; + group = iommu_group_get(dev); + if (!group) + return -ENODEV; + mutex_lock(&group->mutex); if (group->owner_cnt) { if (group->owner != owner) { diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c index a44ad92fc5eb..fe452ce46642 100644 --- a/drivers/iommu/iova.c +++ b/drivers/iommu/iova.c @@ -197,7 +197,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad, curr = __get_cached_rbnode(iovad, limit_pfn); curr_iova = to_iova(curr); - retry_pfn = curr_iova->pfn_hi + 1; + retry_pfn = curr_iova->pfn_hi; retry: do { @@ -211,7 +211,7 @@ retry: if (high_pfn < size || new_pfn < low_pfn) { if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) { high_pfn = limit_pfn; - low_pfn = retry_pfn; + low_pfn = retry_pfn + 1; curr = iova_find_limit(iovad, limit_pfn); curr_iova = to_iova(curr); goto retry; diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 69682ee068d2..ca581ff1c769 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -683,7 +683,7 @@ static int mtk_iommu_v1_probe(struct platform_device *pdev) ret = iommu_device_sysfs_add(&data->iommu, &pdev->dev, NULL, dev_name(&pdev->dev)); if (ret) - return ret; + goto out_clk_unprepare; ret = iommu_device_register(&data->iommu, &mtk_iommu_v1_ops, dev); if (ret) @@ -698,6 +698,8 @@ out_dev_unreg: iommu_device_unregister(&data->iommu); out_sysfs_remove: iommu_device_sysfs_remove(&data->iommu); +out_clk_unprepare: + clk_disable_unprepare(data->bclk); return ret; } diff --git a/drivers/md/bcache/bcache_ondisk.h b/drivers/md/bcache/bcache_ondisk.h index 97413586195b..f96034e0ba4f 100644 --- a/drivers/md/bcache/bcache_ondisk.h +++ b/drivers/md/bcache/bcache_ondisk.h @@ -106,7 +106,8 @@ static inline unsigned long bkey_bytes(const struct bkey *k) return bkey_u64s(k) * sizeof(__u64); } -#define bkey_copy(_dest, _src) memcpy(_dest, _src, bkey_bytes(_src)) +#define bkey_copy(_dest, _src) unsafe_memcpy(_dest, _src, bkey_bytes(_src), \ + /* bkey is always padded */) static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src) { diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index e5da469a4235..c182c21de2e8 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -149,7 +149,8 @@ add: bytes, GFP_KERNEL); if (!i) return -ENOMEM; - memcpy(&i->j, j, bytes); + unsafe_memcpy(&i->j, j, bytes, + /* "bytes" was calculated by set_bytes() above */); /* Add to the location after 'where' points to */ list_add(&i->list, where); ret = 1; diff --git a/drivers/md/md.c b/drivers/md/md.c index 8af639296b3c..02b0240e7c71 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -3644,7 +3644,7 @@ EXPORT_SYMBOL_GPL(md_rdev_init); */ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int super_minor) { - static struct md_rdev *claim_rdev; /* just for claiming the bdev */ + static struct md_rdev claim_rdev; /* just for claiming the bdev */ struct md_rdev *rdev; sector_t size; int err; @@ -3662,7 +3662,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe rdev->bdev = blkdev_get_by_dev(newdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, - super_format == -2 ? claim_rdev : rdev); + super_format == -2 ? &claim_rdev : rdev); if (IS_ERR(rdev->bdev)) { pr_warn("md: could not open device unknown-block(%u,%u).\n", MAJOR(newdev), MINOR(newdev)); diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index fc3758a5bc1c..53e495223ea0 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -2149,8 +2149,6 @@ int vb2_core_streamon(struct vb2_queue *q, unsigned int type) if (ret) return ret; - q->streaming = 1; - /* * Tell driver to start streaming provided sufficient buffers * are available. @@ -2161,12 +2159,13 @@ int vb2_core_streamon(struct vb2_queue *q, unsigned int type) goto unprepare; } + q->streaming = 1; + dprintk(q, 3, "successful\n"); return 0; unprepare: call_void_qop(q, unprepare_streaming, q); - q->streaming = 0; return ret; } EXPORT_SYMBOL_GPL(vb2_core_streamon); diff --git a/drivers/media/v4l2-core/v4l2-ctrls-api.c b/drivers/media/v4l2-core/v4l2-ctrls-api.c index 3d3b6dc24ca6..002ea6588edf 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-api.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-api.c @@ -150,8 +150,8 @@ static int user_to_new(struct v4l2_ext_control *c, struct v4l2_ctrl *ctrl) * then return an error. */ if (strlen(ctrl->p_new.p_char) == ctrl->maximum && last) - ctrl->is_new = 1; return -ERANGE; + ctrl->is_new = 1; } return ret; default: diff --git a/drivers/memory/atmel-sdramc.c b/drivers/memory/atmel-sdramc.c index 9c49d00c2a96..ea6e9e1eaf04 100644 --- a/drivers/memory/atmel-sdramc.c +++ b/drivers/memory/atmel-sdramc.c @@ -47,19 +47,17 @@ static int atmel_ramc_probe(struct platform_device *pdev) caps = of_device_get_match_data(&pdev->dev); if (caps->has_ddrck) { - clk = devm_clk_get(&pdev->dev, "ddrck"); + clk = devm_clk_get_enabled(&pdev->dev, "ddrck"); if (IS_ERR(clk)) return PTR_ERR(clk); - clk_prepare_enable(clk); } if (caps->has_mpddr_clk) { - clk = devm_clk_get(&pdev->dev, "mpddr"); + clk = devm_clk_get_enabled(&pdev->dev, "mpddr"); if (IS_ERR(clk)) { pr_err("AT91 RAMC: couldn't get mpddr clock\n"); return PTR_ERR(clk); } - clk_prepare_enable(clk); } return 0; diff --git a/drivers/memory/mvebu-devbus.c b/drivers/memory/mvebu-devbus.c index 8450638e8670..efc6c08db2b7 100644 --- a/drivers/memory/mvebu-devbus.c +++ b/drivers/memory/mvebu-devbus.c @@ -280,10 +280,9 @@ static int mvebu_devbus_probe(struct platform_device *pdev) if (IS_ERR(devbus->base)) return PTR_ERR(devbus->base); - clk = devm_clk_get(&pdev->dev, NULL); + clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(clk)) return PTR_ERR(clk); - clk_prepare_enable(clk); /* * Obtain clock period in picoseconds, diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c index 57d9f91fe89b..d78f73db37c8 100644 --- a/drivers/memory/omap-gpmc.c +++ b/drivers/memory/omap-gpmc.c @@ -1918,7 +1918,8 @@ int gpmc_cs_program_settings(int cs, struct gpmc_settings *p) } } - if (p->wait_pin > gpmc_nr_waitpins) { + if (p->wait_pin != GPMC_WAITPIN_INVALID && + p->wait_pin > gpmc_nr_waitpins) { pr_err("%s: invalid wait-pin (%d)\n", __func__, p->wait_pin); return -EINVAL; } diff --git a/drivers/memory/tegra/tegra186.c b/drivers/memory/tegra/tegra186.c index 62477e592bf5..7bb73f06fad3 100644 --- a/drivers/memory/tegra/tegra186.c +++ b/drivers/memory/tegra/tegra186.c @@ -22,32 +22,6 @@ #define MC_SID_STREAMID_SECURITY_WRITE_ACCESS_DISABLED BIT(16) #define MC_SID_STREAMID_SECURITY_OVERRIDE BIT(8) -static void tegra186_mc_program_sid(struct tegra_mc *mc) -{ - unsigned int i; - - for (i = 0; i < mc->soc->num_clients; i++) { - const struct tegra_mc_client *client = &mc->soc->clients[i]; - u32 override, security; - - override = readl(mc->regs + client->regs.sid.override); - security = readl(mc->regs + client->regs.sid.security); - - dev_dbg(mc->dev, "client %s: override: %x security: %x\n", - client->name, override, security); - - dev_dbg(mc->dev, "setting SID %u for %s\n", client->sid, - client->name); - writel(client->sid, mc->regs + client->regs.sid.override); - - override = readl(mc->regs + client->regs.sid.override); - security = readl(mc->regs + client->regs.sid.security); - - dev_dbg(mc->dev, "client %s: override: %x security: %x\n", - client->name, override, security); - } -} - static int tegra186_mc_probe(struct tegra_mc *mc) { struct platform_device *pdev = to_platform_device(mc->dev); @@ -85,8 +59,6 @@ populate: if (err < 0) return err; - tegra186_mc_program_sid(mc); - return 0; } @@ -95,13 +67,6 @@ static void tegra186_mc_remove(struct tegra_mc *mc) of_platform_depopulate(mc->dev); } -static int tegra186_mc_resume(struct tegra_mc *mc) -{ - tegra186_mc_program_sid(mc); - - return 0; -} - #if IS_ENABLED(CONFIG_IOMMU_API) static void tegra186_mc_client_sid_override(struct tegra_mc *mc, const struct tegra_mc_client *client, @@ -173,7 +138,6 @@ static int tegra186_mc_probe_device(struct tegra_mc *mc, struct device *dev) const struct tegra_mc_ops tegra186_mc_ops = { .probe = tegra186_mc_probe, .remove = tegra186_mc_remove, - .resume = tegra186_mc_resume, .probe_device = tegra186_mc_probe_device, .handle_irq = tegra30_mc_handle_irq, }; diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index c9902a1dcf5d..5310606113fe 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -321,7 +321,7 @@ static void fastrpc_free_map(struct kref *ref) perm.vmid = QCOM_SCM_VMID_HLOS; perm.perm = QCOM_SCM_PERM_RWX; err = qcom_scm_assign_mem(map->phys, map->size, - &(map->fl->cctx->vmperms[0].vmid), &perm, 1); + &map->fl->cctx->perms, &perm, 1); if (err) { dev_err(map->fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d", map->phys, map->size, err); @@ -334,6 +334,13 @@ static void fastrpc_free_map(struct kref *ref) dma_buf_put(map->buf); } + if (map->fl) { + spin_lock(&map->fl->lock); + list_del(&map->node); + spin_unlock(&map->fl->lock); + map->fl = NULL; + } + kfree(map); } @@ -343,38 +350,41 @@ static void fastrpc_map_put(struct fastrpc_map *map) kref_put(&map->refcount, fastrpc_free_map); } -static void fastrpc_map_get(struct fastrpc_map *map) +static int fastrpc_map_get(struct fastrpc_map *map) { - if (map) - kref_get(&map->refcount); + if (!map) + return -ENOENT; + + return kref_get_unless_zero(&map->refcount) ? 0 : -ENOENT; } static int fastrpc_map_lookup(struct fastrpc_user *fl, int fd, - struct fastrpc_map **ppmap) + struct fastrpc_map **ppmap, bool take_ref) { + struct fastrpc_session_ctx *sess = fl->sctx; struct fastrpc_map *map = NULL; + int ret = -ENOENT; - mutex_lock(&fl->mutex); + spin_lock(&fl->lock); list_for_each_entry(map, &fl->maps, node) { - if (map->fd == fd) { - *ppmap = map; - mutex_unlock(&fl->mutex); - return 0; - } - } - mutex_unlock(&fl->mutex); - - return -ENOENT; -} + if (map->fd != fd) + continue; -static int fastrpc_map_find(struct fastrpc_user *fl, int fd, - struct fastrpc_map **ppmap) -{ - int ret = fastrpc_map_lookup(fl, fd, ppmap); + if (take_ref) { + ret = fastrpc_map_get(map); + if (ret) { + dev_dbg(sess->dev, "%s: Failed to get map fd=%d ret=%d\n", + __func__, fd, ret); + break; + } + } - if (!ret) - fastrpc_map_get(*ppmap); + *ppmap = map; + ret = 0; + break; + } + spin_unlock(&fl->lock); return ret; } @@ -746,7 +756,7 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd, struct fastrpc_map *map = NULL; int err = 0; - if (!fastrpc_map_find(fl, fd, ppmap)) + if (!fastrpc_map_lookup(fl, fd, ppmap, true)) return 0; map = kzalloc(sizeof(*map), GFP_KERNEL); @@ -788,10 +798,8 @@ static int fastrpc_map_create(struct fastrpc_user *fl, int fd, * If subsystem VMIDs are defined in DTSI, then do * hyp_assign from HLOS to those VM(s) */ - unsigned int perms = BIT(QCOM_SCM_VMID_HLOS); - map->attr = attr; - err = qcom_scm_assign_mem(map->phys, (u64)map->size, &perms, + err = qcom_scm_assign_mem(map->phys, (u64)map->size, &fl->cctx->perms, fl->cctx->vmperms, fl->cctx->vmcount); if (err) { dev_err(sess->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d", @@ -1070,7 +1078,7 @@ static int fastrpc_put_args(struct fastrpc_invoke_ctx *ctx, for (i = 0; i < FASTRPC_MAX_FDLIST; i++) { if (!fdlist[i]) break; - if (!fastrpc_map_lookup(fl, (int)fdlist[i], &mmap)) + if (!fastrpc_map_lookup(fl, (int)fdlist[i], &mmap, false)) fastrpc_map_put(mmap); } @@ -1258,10 +1266,9 @@ static int fastrpc_init_create_static_process(struct fastrpc_user *fl, /* Map if we have any heap VMIDs associated with this ADSP Static Process. */ if (fl->cctx->vmcount) { - unsigned int perms = BIT(QCOM_SCM_VMID_HLOS); - err = qcom_scm_assign_mem(fl->cctx->remote_heap->phys, - (u64)fl->cctx->remote_heap->size, &perms, + (u64)fl->cctx->remote_heap->size, + &fl->cctx->perms, fl->cctx->vmperms, fl->cctx->vmcount); if (err) { dev_err(fl->sctx->dev, "Failed to assign memory with phys 0x%llx size 0x%llx err %d", @@ -1309,7 +1316,7 @@ err_invoke: perm.perm = QCOM_SCM_PERM_RWX; err = qcom_scm_assign_mem(fl->cctx->remote_heap->phys, (u64)fl->cctx->remote_heap->size, - &(fl->cctx->vmperms[0].vmid), &perm, 1); + &fl->cctx->perms, &perm, 1); if (err) dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d", fl->cctx->remote_heap->phys, fl->cctx->remote_heap->size, err); @@ -1433,12 +1440,7 @@ err_invoke: fl->init_mem = NULL; fastrpc_buf_free(imem); err_alloc: - if (map) { - spin_lock(&fl->lock); - list_del(&map->node); - spin_unlock(&fl->lock); - fastrpc_map_put(map); - } + fastrpc_map_put(map); err: kfree(args); @@ -1514,10 +1516,8 @@ static int fastrpc_device_release(struct inode *inode, struct file *file) fastrpc_context_put(ctx); } - list_for_each_entry_safe(map, m, &fl->maps, node) { - list_del(&map->node); + list_for_each_entry_safe(map, m, &fl->maps, node) fastrpc_map_put(map); - } list_for_each_entry_safe(buf, b, &fl->mmaps, node) { list_del(&buf->node); @@ -1894,12 +1894,11 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp) /* Add memory to static PD pool, protection thru hypervisor */ if (req.flags != ADSP_MMAP_REMOTE_HEAP_ADDR && fl->cctx->vmcount) { struct qcom_scm_vmperm perm; - int err = 0; perm.vmid = QCOM_SCM_VMID_HLOS; perm.perm = QCOM_SCM_PERM_RWX; err = qcom_scm_assign_mem(buf->phys, buf->size, - &(fl->cctx->vmperms[0].vmid), &perm, 1); + &fl->cctx->perms, &perm, 1); if (err) { dev_err(fl->sctx->dev, "Failed to assign memory phys 0x%llx size 0x%llx err %d", buf->phys, buf->size, err); diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 4a08b624910a..a81b890c7ee6 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -702,13 +702,15 @@ void *mei_cldev_dma_map(struct mei_cl_device *cldev, u8 buffer_id, size_t size) if (cl->state == MEI_FILE_UNINITIALIZED) { ret = mei_cl_link(cl); if (ret) - goto out; + goto notlinked; /* update pointers */ cl->cldev = cldev; } ret = mei_cl_dma_alloc_and_map(cl, NULL, buffer_id, size); -out: + if (ret) + mei_cl_unlink(cl); +notlinked: mutex_unlock(&bus->device_lock); if (ret) return ERR_PTR(ret); @@ -758,7 +760,7 @@ int mei_cldev_enable(struct mei_cl_device *cldev) if (cl->state == MEI_FILE_UNINITIALIZED) { ret = mei_cl_link(cl); if (ret) - goto out; + goto notlinked; /* update pointers */ cl->cldev = cldev; } @@ -785,6 +787,9 @@ int mei_cldev_enable(struct mei_cl_device *cldev) } out: + if (ret) + mei_cl_unlink(cl); +notlinked: mutex_unlock(&bus->device_lock); return ret; @@ -1277,7 +1282,6 @@ static void mei_cl_bus_dev_release(struct device *dev) mei_cl_flush_queues(cldev->cl, NULL); mei_me_cl_put(cldev->me_cl); mei_dev_bus_put(cldev->bus); - mei_cl_unlink(cldev->cl); kfree(cldev->cl); kfree(cldev); } diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 99966cd3e7d8..bdc65d50b945 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -111,6 +111,8 @@ #define MEI_DEV_ID_RPL_S 0x7A68 /* Raptor Lake Point S */ +#define MEI_DEV_ID_MTL_M 0x7E70 /* Meteor Lake Point M */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 704cd0caa172..5bf0d50d55a0 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -118,6 +118,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_RPL_S, MEI_ME_PCH15_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_MTL_M, MEI_ME_PCH15_CFG)}, + /* required last entry */ {0, } }; diff --git a/drivers/misc/vmw_vmci/vmci_guest.c b/drivers/misc/vmw_vmci/vmci_guest.c index aa7b05de97dd..4f8d962bb5b2 100644 --- a/drivers/misc/vmw_vmci/vmci_guest.c +++ b/drivers/misc/vmw_vmci/vmci_guest.c @@ -56,8 +56,6 @@ struct vmci_guest_device { bool exclusive_vectors; - struct tasklet_struct datagram_tasklet; - struct tasklet_struct bm_tasklet; struct wait_queue_head inout_wq; void *data_buffer; @@ -304,9 +302,8 @@ static int vmci_check_host_caps(struct pci_dev *pdev) * This function assumes that it has exclusive access to the data * in register(s) for the duration of the call. */ -static void vmci_dispatch_dgs(unsigned long data) +static void vmci_dispatch_dgs(struct vmci_guest_device *vmci_dev) { - struct vmci_guest_device *vmci_dev = (struct vmci_guest_device *)data; u8 *dg_in_buffer = vmci_dev->data_buffer; struct vmci_datagram *dg; size_t dg_in_buffer_size = VMCI_MAX_DG_SIZE; @@ -465,10 +462,8 @@ static void vmci_dispatch_dgs(unsigned long data) * Scans the notification bitmap for raised flags, clears them * and handles the notifications. */ -static void vmci_process_bitmap(unsigned long data) +static void vmci_process_bitmap(struct vmci_guest_device *dev) { - struct vmci_guest_device *dev = (struct vmci_guest_device *)data; - if (!dev->notification_bitmap) { dev_dbg(dev->dev, "No bitmap present in %s\n", __func__); return; @@ -486,13 +481,13 @@ static irqreturn_t vmci_interrupt(int irq, void *_dev) struct vmci_guest_device *dev = _dev; /* - * If we are using MSI-X with exclusive vectors then we simply schedule - * the datagram tasklet, since we know the interrupt was meant for us. + * If we are using MSI-X with exclusive vectors then we simply call + * vmci_dispatch_dgs(), since we know the interrupt was meant for us. * Otherwise we must read the ICR to determine what to do. */ if (dev->exclusive_vectors) { - tasklet_schedule(&dev->datagram_tasklet); + vmci_dispatch_dgs(dev); } else { unsigned int icr; @@ -502,12 +497,12 @@ static irqreturn_t vmci_interrupt(int irq, void *_dev) return IRQ_NONE; if (icr & VMCI_ICR_DATAGRAM) { - tasklet_schedule(&dev->datagram_tasklet); + vmci_dispatch_dgs(dev); icr &= ~VMCI_ICR_DATAGRAM; } if (icr & VMCI_ICR_NOTIFICATION) { - tasklet_schedule(&dev->bm_tasklet); + vmci_process_bitmap(dev); icr &= ~VMCI_ICR_NOTIFICATION; } @@ -536,7 +531,7 @@ static irqreturn_t vmci_interrupt_bm(int irq, void *_dev) struct vmci_guest_device *dev = _dev; /* For MSI-X we can just assume it was meant for us. */ - tasklet_schedule(&dev->bm_tasklet); + vmci_process_bitmap(dev); return IRQ_HANDLED; } @@ -638,10 +633,6 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, vmci_dev->iobase = iobase; vmci_dev->mmio_base = mmio_base; - tasklet_init(&vmci_dev->datagram_tasklet, - vmci_dispatch_dgs, (unsigned long)vmci_dev); - tasklet_init(&vmci_dev->bm_tasklet, - vmci_process_bitmap, (unsigned long)vmci_dev); init_waitqueue_head(&vmci_dev->inout_wq); if (mmio_base != NULL) { @@ -808,8 +799,9 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, * Request IRQ for legacy or MSI interrupts, or for first * MSI-X vector. */ - error = request_irq(pci_irq_vector(pdev, 0), vmci_interrupt, - IRQF_SHARED, KBUILD_MODNAME, vmci_dev); + error = request_threaded_irq(pci_irq_vector(pdev, 0), NULL, + vmci_interrupt, IRQF_SHARED, + KBUILD_MODNAME, vmci_dev); if (error) { dev_err(&pdev->dev, "Irq %u in use: %d\n", pci_irq_vector(pdev, 0), error); @@ -823,9 +815,9 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, * between the vectors. */ if (vmci_dev->exclusive_vectors) { - error = request_irq(pci_irq_vector(pdev, 1), - vmci_interrupt_bm, 0, KBUILD_MODNAME, - vmci_dev); + error = request_threaded_irq(pci_irq_vector(pdev, 1), NULL, + vmci_interrupt_bm, 0, + KBUILD_MODNAME, vmci_dev); if (error) { dev_err(&pdev->dev, "Failed to allocate irq %u: %d\n", @@ -833,9 +825,11 @@ static int vmci_guest_probe_device(struct pci_dev *pdev, goto err_free_irq; } if (caps_in_use & VMCI_CAPS_DMA_DATAGRAM) { - error = request_irq(pci_irq_vector(pdev, 2), - vmci_interrupt_dma_datagram, - 0, KBUILD_MODNAME, vmci_dev); + error = request_threaded_irq(pci_irq_vector(pdev, 2), + NULL, + vmci_interrupt_dma_datagram, + 0, KBUILD_MODNAME, + vmci_dev); if (error) { dev_err(&pdev->dev, "Failed to allocate irq %u: %d\n", @@ -871,8 +865,6 @@ err_free_bm_irq: err_free_irq: free_irq(pci_irq_vector(pdev, 0), vmci_dev); - tasklet_kill(&vmci_dev->datagram_tasklet); - tasklet_kill(&vmci_dev->bm_tasklet); err_disable_msi: pci_free_irq_vectors(pdev); @@ -943,9 +935,6 @@ static void vmci_guest_remove_device(struct pci_dev *pdev) free_irq(pci_irq_vector(pdev, 0), vmci_dev); pci_free_irq_vectors(pdev); - tasklet_kill(&vmci_dev->datagram_tasklet); - tasklet_kill(&vmci_dev->bm_tasklet); - if (vmci_dev->notification_bitmap) { /* * The device reset above cleared the bitmap state of the diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 89ef0c80ac37..9e73c34b6401 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -107,6 +107,7 @@ #define ESDHC_TUNING_START_TAP_DEFAULT 0x1 #define ESDHC_TUNING_START_TAP_MASK 0x7f #define ESDHC_TUNING_CMD_CRC_CHECK_DISABLE (1 << 7) +#define ESDHC_TUNING_STEP_DEFAULT 0x1 #define ESDHC_TUNING_STEP_MASK 0x00070000 #define ESDHC_TUNING_STEP_SHIFT 16 @@ -1368,7 +1369,7 @@ static void sdhci_esdhc_imx_hwinit(struct sdhci_host *host) struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host); struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host); struct cqhci_host *cq_host = host->mmc->cqe_private; - int tmp; + u32 tmp; if (esdhc_is_usdhc(imx_data)) { /* @@ -1423,17 +1424,24 @@ static void sdhci_esdhc_imx_hwinit(struct sdhci_host *host) if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) { tmp = readl(host->ioaddr + ESDHC_TUNING_CTRL); - tmp |= ESDHC_STD_TUNING_EN | - ESDHC_TUNING_START_TAP_DEFAULT; - if (imx_data->boarddata.tuning_start_tap) { - tmp &= ~ESDHC_TUNING_START_TAP_MASK; + tmp |= ESDHC_STD_TUNING_EN; + + /* + * ROM code or bootloader may config the start tap + * and step, unmask them first. + */ + tmp &= ~(ESDHC_TUNING_START_TAP_MASK | ESDHC_TUNING_STEP_MASK); + if (imx_data->boarddata.tuning_start_tap) tmp |= imx_data->boarddata.tuning_start_tap; - } + else + tmp |= ESDHC_TUNING_START_TAP_DEFAULT; if (imx_data->boarddata.tuning_step) { - tmp &= ~ESDHC_TUNING_STEP_MASK; tmp |= imx_data->boarddata.tuning_step << ESDHC_TUNING_STEP_SHIFT; + } else { + tmp |= ESDHC_TUNING_STEP_DEFAULT + << ESDHC_TUNING_STEP_SHIFT; } /* Disable the CMD CRC check for tuning, if not, need to diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index b16e12e62e72..3db9f32d6a7b 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1492,9 +1492,11 @@ static int sunxi_mmc_remove(struct platform_device *pdev) struct sunxi_mmc_host *host = mmc_priv(mmc); mmc_remove_host(mmc); - pm_runtime_force_suspend(&pdev->dev); - disable_irq(host->irq); - sunxi_mmc_disable(host); + pm_runtime_disable(&pdev->dev); + if (!pm_runtime_status_suspended(&pdev->dev)) { + disable_irq(host->irq); + sunxi_mmc_disable(host); + } dma_free_coherent(&pdev->dev, PAGE_SIZE, host->sg_cpu, host->sg_dma); mmc_free_host(mmc); diff --git a/drivers/mtd/parsers/scpart.c b/drivers/mtd/parsers/scpart.c index 02601bb33de4..6e5e11c37078 100644 --- a/drivers/mtd/parsers/scpart.c +++ b/drivers/mtd/parsers/scpart.c @@ -50,7 +50,7 @@ static int scpart_scan_partmap(struct mtd_info *master, loff_t partmap_offs, int cnt = 0; int res = 0; int res2; - loff_t offs; + uint32_t offs; size_t retlen; struct sc_part_desc *pdesc = NULL; struct sc_part_desc *tmpdesc; diff --git a/drivers/mtd/parsers/tplink_safeloader.c b/drivers/mtd/parsers/tplink_safeloader.c index f601e7bd8627..1c689dafca2a 100644 --- a/drivers/mtd/parsers/tplink_safeloader.c +++ b/drivers/mtd/parsers/tplink_safeloader.c @@ -91,7 +91,7 @@ static int mtd_parser_tplink_safeloader_parse(struct mtd_info *mtd, buf = mtd_parser_tplink_safeloader_read_table(mtd); if (!buf) { err = -ENOENT; - goto err_out; + goto err_free_parts; } for (idx = 0, offset = TPLINK_SAFELOADER_DATA_OFFSET; @@ -118,6 +118,8 @@ static int mtd_parser_tplink_safeloader_parse(struct mtd_info *mtd, err_free: for (idx -= 1; idx >= 0; idx--) kfree(parts[idx].name); +err_free_parts: + kfree(parts); err_out: return err; }; diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c index d8703d7dfd0a..d67c926bca8b 100644 --- a/drivers/mtd/spi-nor/core.c +++ b/drivers/mtd/spi-nor/core.c @@ -10,6 +10,7 @@ #include <linux/err.h> #include <linux/errno.h> #include <linux/module.h> +#include <linux/delay.h> #include <linux/device.h> #include <linux/mutex.h> #include <linux/math64.h> diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c index 3585f02575df..57eeb066a945 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ethtool.c @@ -48,6 +48,7 @@ mcp251xfd_ring_set_ringparam(struct net_device *ndev, priv->rx_obj_num = layout.cur_rx; priv->rx_obj_num_coalesce_irq = layout.rx_coalesce; priv->tx->obj_num = layout.cur_tx; + priv->tx_obj_num_coalesce_irq = layout.tx_coalesce; return 0; } diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index c26755f662c1..f6f3b43dfb06 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -35,12 +35,13 @@ config NET_DSA_LANTIQ_GSWIP the xrx200 / VR9 SoC. config NET_DSA_MT7530 - tristate "MediaTek MT753x and MT7621 Ethernet switch support" + tristate "MediaTek MT7530 and MT7531 Ethernet switch support" select NET_DSA_TAG_MTK select MEDIATEK_GE_PHY help - This enables support for the MediaTek MT7530, MT7531, and MT7621 - Ethernet switch chips. + This enables support for the MediaTek MT7530 and MT7531 Ethernet + switch chips. Multi-chip module MT7530 in MT7621AT, MT7621DAT, + MT7621ST and MT7623AI SoCs is supported. config NET_DSA_MV88E6060 tristate "Marvell 88E6060 ethernet switch chip support" diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 47b54ecf2c6f..6178a96e389f 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -540,10 +540,10 @@ int ksz9477_fdb_del(struct ksz_device *dev, int port, ksz_read32(dev, REG_SW_ALU_VAL_D, &alu_table[3]); /* clear forwarding port */ - alu_table[2] &= ~BIT(port); + alu_table[1] &= ~BIT(port); /* if there is no port to forward, clear table */ - if ((alu_table[2] & ALU_V_PORT_MAP) == 0) { + if ((alu_table[1] & ALU_V_PORT_MAP) == 0) { alu_table[0] = 0; alu_table[1] = 0; alu_table[2] = 0; diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index c1a633ca1e6d..e315f669ec06 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -104,7 +104,7 @@ static const struct of_device_id ksz9477_dt_ids[] = { }, { .compatible = "microchip,ksz8563", - .data = &ksz_switch_chips[KSZ9893] + .data = &ksz_switch_chips[KSZ8563] }, { .compatible = "microchip,ksz9567", diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 0805f249fff2..c26b8597945b 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -356,7 +356,7 @@ static int adin1110_read_fifo(struct adin1110_port_priv *port_priv) if ((port_priv->flags & IFF_ALLMULTI && rxb->pkt_type == PACKET_MULTICAST) || (port_priv->flags & IFF_BROADCAST && rxb->pkt_type == PACKET_BROADCAST)) - rxb->offload_fwd_mark = 1; + rxb->offload_fwd_mark = port_priv->priv->forwarding; netif_rx(rxb); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index 3936543a74d8..4030d619e84f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -524,19 +524,28 @@ static void xgbe_disable_vxlan(struct xgbe_prv_data *pdata) netif_dbg(pdata, drv, pdata->netdev, "VXLAN acceleration disabled\n"); } +static unsigned int xgbe_get_fc_queue_count(struct xgbe_prv_data *pdata) +{ + unsigned int max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; + + /* From MAC ver 30H the TFCR is per priority, instead of per queue */ + if (XGMAC_GET_BITS(pdata->hw_feat.version, MAC_VR, SNPSVER) >= 0x30) + return max_q_count; + else + return min_t(unsigned int, pdata->tx_q_count, max_q_count); +} + static int xgbe_disable_tx_flow_control(struct xgbe_prv_data *pdata) { - unsigned int max_q_count, q_count; unsigned int reg, reg_val; - unsigned int i; + unsigned int i, q_count; /* Clear MTL flow control */ for (i = 0; i < pdata->rx_q_count; i++) XGMAC_MTL_IOWRITE_BITS(pdata, i, MTL_Q_RQOMR, EHFC, 0); /* Clear MAC flow control */ - max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + q_count = xgbe_get_fc_queue_count(pdata); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg); @@ -553,9 +562,8 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata) { struct ieee_pfc *pfc = pdata->pfc; struct ieee_ets *ets = pdata->ets; - unsigned int max_q_count, q_count; unsigned int reg, reg_val; - unsigned int i; + unsigned int i, q_count; /* Set MTL flow control */ for (i = 0; i < pdata->rx_q_count; i++) { @@ -579,8 +587,7 @@ static int xgbe_enable_tx_flow_control(struct xgbe_prv_data *pdata) } /* Set MAC flow control */ - max_q_count = XGMAC_MAX_FLOW_CONTROL_QUEUES; - q_count = min_t(unsigned int, pdata->tx_q_count, max_q_count); + q_count = xgbe_get_fc_queue_count(pdata); reg = MAC_Q0TFCR; for (i = 0; i < q_count; i++) { reg_val = XGMAC_IOREAD(pdata, reg); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 0c5c1b155683..43fdd111235a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -496,6 +496,7 @@ static enum xgbe_an xgbe_an73_tx_training(struct xgbe_prv_data *pdata, reg |= XGBE_KR_TRAINING_ENABLE; reg |= XGBE_KR_TRAINING_START; XMDIO_WRITE(pdata, MDIO_MMD_PMAPMD, MDIO_PMA_10GBR_PMD_CTRL, reg); + pdata->kr_start_time = jiffies; netif_dbg(pdata, link, pdata->netdev, "KR training initiated\n"); @@ -632,6 +633,8 @@ static enum xgbe_an xgbe_an73_incompat_link(struct xgbe_prv_data *pdata) xgbe_switch_mode(pdata); + pdata->an_result = XGBE_AN_READY; + xgbe_an_restart(pdata); return XGBE_AN_INCOMPAT_LINK; @@ -1275,9 +1278,30 @@ static bool xgbe_phy_aneg_done(struct xgbe_prv_data *pdata) static void xgbe_check_link_timeout(struct xgbe_prv_data *pdata) { unsigned long link_timeout; + unsigned long kr_time; + int wait; link_timeout = pdata->link_check + (XGBE_LINK_TIMEOUT * HZ); if (time_after(jiffies, link_timeout)) { + if ((xgbe_cur_mode(pdata) == XGBE_MODE_KR) && + pdata->phy.autoneg == AUTONEG_ENABLE) { + /* AN restart should not happen while KR training is in progress. + * The while loop ensures no AN restart during KR training, + * waits up to 500ms and AN restart is triggered only if KR + * training is failed. + */ + wait = XGBE_KR_TRAINING_WAIT_ITER; + while (wait--) { + kr_time = pdata->kr_start_time + + msecs_to_jiffies(XGBE_AN_MS_TIMEOUT); + if (time_after(jiffies, kr_time)) + break; + /* AN restart is not required, if AN result is COMPLETE */ + if (pdata->an_result == XGBE_AN_COMPLETE) + return; + usleep_range(10000, 11000); + } + } netif_dbg(pdata, link, pdata->netdev, "AN link timeout\n"); xgbe_phy_config_aneg(pdata); } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index 71f24cb47935..7a41367c437d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -290,6 +290,7 @@ /* Auto-negotiation */ #define XGBE_AN_MS_TIMEOUT 500 #define XGBE_LINK_TIMEOUT 5 +#define XGBE_KR_TRAINING_WAIT_ITER 50 #define XGBE_SGMII_AN_LINK_STATUS BIT(1) #define XGBE_SGMII_AN_LINK_SPEED (BIT(2) | BIT(3)) @@ -1280,6 +1281,7 @@ struct xgbe_prv_data { unsigned int parallel_detect; unsigned int fec_ability; unsigned long an_start; + unsigned long kr_start_time; enum xgbe_an_mode an_mode; /* I2C support */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 16ce7a90610c..240a7e8a7652 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -993,7 +993,7 @@ static struct sk_buff *bnxt_rx_multi_page_skb(struct bnxt *bp, DMA_ATTR_WEAK_ORDERING); skb = build_skb(page_address(page), PAGE_SIZE); if (!skb) { - __free_page(page); + page_pool_recycle_direct(rxr->page_pool, page); return NULL; } skb_mark_for_recycle(skb); @@ -1031,7 +1031,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, skb = napi_alloc_skb(&rxr->bnapi->napi, payload); if (!skb) { - __free_page(page); + page_pool_recycle_direct(rxr->page_pool, page); return NULL; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index cbf17fcfb7ab..ec573127b707 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -3969,7 +3969,7 @@ void bnxt_ethtool_init(struct bnxt *bp) test_info->timeout = HWRM_CMD_TIMEOUT; for (i = 0; i < bp->num_tests; i++) { char *str = test_info->string[i]; - char *fw_str = resp->test0_name + i * 32; + char *fw_str = resp->test_name[i]; if (i == BNXT_MACLPBK_TEST_IDX) { strcpy(str, "Mac loopback test (offline)"); @@ -3980,14 +3980,9 @@ void bnxt_ethtool_init(struct bnxt *bp) } else if (i == BNXT_IRQ_TEST_IDX) { strcpy(str, "Interrupt_test (offline)"); } else { - strscpy(str, fw_str, ETH_GSTRING_LEN); - strncat(str, " test", ETH_GSTRING_LEN - strlen(str)); - if (test_info->offline_mask & (1 << i)) - strncat(str, " (offline)", - ETH_GSTRING_LEN - strlen(str)); - else - strncat(str, " (online)", - ETH_GSTRING_LEN - strlen(str)); + snprintf(str, ETH_GSTRING_LEN, "%s test (%s)", + fw_str, test_info->offline_mask & (1 << i) ? + "offline" : "online"); } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 2686a714a59f..a5408879e077 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -10249,14 +10249,7 @@ struct hwrm_selftest_qlist_output { u8 unused_0; __le16 test_timeout; u8 unused_1[2]; - char test0_name[32]; - char test1_name[32]; - char test2_name[32]; - char test3_name[32]; - char test4_name[32]; - char test5_name[32]; - char test6_name[32]; - char test7_name[32]; + char test_name[8][32]; u8 eyescope_target_BER_support; #define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E8_SUPPORTED 0x0UL #define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E9_SUPPORTED 0x1UL diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 59debdc344a5..58747292521d 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -11166,7 +11166,7 @@ static void tg3_reset_task(struct work_struct *work) rtnl_lock(); tg3_full_lock(tp, 0); - if (!netif_running(tp->dev)) { + if (tp->pcierr_recovery || !netif_running(tp->dev)) { tg3_flag_clear(tp, RESET_TASK_PENDING); tg3_full_unlock(tp); rtnl_unlock(); @@ -18101,6 +18101,9 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, netdev_info(netdev, "PCI I/O error detected\n"); + /* Want to make sure that the reset task doesn't run */ + tg3_reset_task_cancel(tp); + rtnl_lock(); /* Could be second call or maybe we don't have netdev yet */ @@ -18117,9 +18120,6 @@ static pci_ers_result_t tg3_io_error_detected(struct pci_dev *pdev, tg3_timer_stop(tp); - /* Want to make sure that the reset task doesn't run */ - tg3_reset_task_cancel(tp); - netif_device_detach(netdev); /* Clean up software state, even if MMIO is blocked */ diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 95667b979fab..72e42820713d 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -2187,7 +2187,6 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb) || skb_is_nonlinear(*skb); int padlen = ETH_ZLEN - (*skb)->len; - int headroom = skb_headroom(*skb); int tailroom = skb_tailroom(*skb); struct sk_buff *nskb; u32 fcs; @@ -2201,9 +2200,6 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) /* FCS could be appeded to tailroom. */ if (tailroom >= ETH_FCS_LEN) goto add_fcs; - /* FCS could be appeded by moving data to headroom. */ - else if (!cloned && headroom + tailroom >= ETH_FCS_LEN) - padlen = 0; /* No room for FCS, need to reallocate skb. */ else padlen = ETH_FCS_LEN; @@ -2212,10 +2208,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) padlen += ETH_FCS_LEN; } - if (!cloned && headroom + tailroom >= padlen) { - (*skb)->data = memmove((*skb)->head, (*skb)->data, (*skb)->len); - skb_set_tail_pointer(*skb, (*skb)->len); - } else { + if (cloned || tailroom < padlen) { nskb = skb_copy_expand(*skb, 0, padlen, GFP_ATOMIC); if (!nskb) return -ENOMEM; diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index bf0190e1d2ea..00e2108f2ca4 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -450,7 +450,7 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, /* ring full, shall not happen because queue is stopped if full * below */ - netif_stop_queue(tx->adapter->netdev); + netif_stop_subqueue(tx->adapter->netdev, tx->queue_index); spin_unlock_irqrestore(&tx->lock, flags); @@ -493,7 +493,7 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, if (tsnep_tx_desc_available(tx) < (MAX_SKB_FRAGS + 1)) { /* ring can get full with next frame */ - netif_stop_queue(tx->adapter->netdev); + netif_stop_subqueue(tx->adapter->netdev, tx->queue_index); } spin_unlock_irqrestore(&tx->lock, flags); @@ -503,11 +503,14 @@ static netdev_tx_t tsnep_xmit_frame_ring(struct sk_buff *skb, static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) { + struct tsnep_tx_entry *entry; + struct netdev_queue *nq; unsigned long flags; int budget = 128; - struct tsnep_tx_entry *entry; - int count; int length; + int count; + + nq = netdev_get_tx_queue(tx->adapter->netdev, tx->queue_index); spin_lock_irqsave(&tx->lock, flags); @@ -564,8 +567,8 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget) } while (likely(budget)); if ((tsnep_tx_desc_available(tx) >= ((MAX_SKB_FRAGS + 1) * 2)) && - netif_queue_stopped(tx->adapter->netdev)) { - netif_wake_queue(tx->adapter->netdev); + netif_tx_queue_stopped(nq)) { + netif_tx_wake_queue(nq); } spin_unlock_irqrestore(&tx->lock, flags); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 3f8032947d86..027fff9f7db0 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2410,6 +2410,9 @@ static int dpaa_eth_poll(struct napi_struct *napi, int budget) cleaned = qman_p_poll_dqrr(np->p, budget); + if (np->xdp_act & XDP_REDIRECT) + xdp_do_flush(); + if (cleaned < budget) { napi_complete_done(napi, cleaned); qman_p_irqsource_add(np->p, QM_PIRQ_DQRI); @@ -2417,9 +2420,6 @@ static int dpaa_eth_poll(struct napi_struct *napi, int budget) qman_p_irqsource_add(np->p, QM_PIRQ_DQRI); } - if (np->xdp_act & XDP_REDIRECT) - xdp_do_flush(); - return cleaned; } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 0c35abb7d065..2e79d18fc3c7 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1993,10 +1993,15 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget) if (rx_cleaned >= budget || txconf_cleaned >= DPAA2_ETH_TXCONF_PER_NAPI) { work_done = budget; + if (ch->xdp.res & XDP_REDIRECT) + xdp_do_flush(); goto out; } } while (store_cleaned); + if (ch->xdp.res & XDP_REDIRECT) + xdp_do_flush(); + /* Update NET DIM with the values for this CDAN */ dpaa2_io_update_net_dim(ch->dpio, ch->stats.frames_per_cdan, ch->stats.bytes_per_cdan); @@ -2032,9 +2037,7 @@ out: txc_fq->dq_bytes = 0; } - if (ch->xdp.res & XDP_REDIRECT) - xdp_do_flush_map(); - else if (rx_cleaned && ch->xdp.res & XDP_TX) + if (rx_cleaned && ch->xdp.res & XDP_TX) dpaa2_eth_xdp_tx_flush(priv, ch, &priv->fq[flowid]); return work_done; diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 3a79ead5219a..e96449eedfb5 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -2290,14 +2290,14 @@ static void enetc_tx_onestep_tstamp(struct work_struct *work) priv = container_of(work, struct enetc_ndev_priv, tx_onestep_tstamp); - netif_tx_lock(priv->ndev); + netif_tx_lock_bh(priv->ndev); clear_bit_unlock(ENETC_TX_ONESTEP_TSTAMP_IN_PROGRESS, &priv->flags); skb = skb_dequeue(&priv->tx_skbs); if (skb) enetc_start_xmit(skb, priv->ndev); - netif_tx_unlock(priv->ndev); + netif_tx_unlock_bh(priv->ndev); } static void enetc_tx_onestep_tstamp_init(struct enetc_ndev_priv *priv) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 644f3c963730..2341597408d1 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3191,7 +3191,7 @@ static void fec_enet_free_buffers(struct net_device *ndev) for (q = 0; q < fep->num_rx_queues; q++) { rxq = fep->rx_queue[q]; for (i = 0; i < rxq->bd.ring_size; i++) - page_pool_release_page(rxq->page_pool, rxq->rx_skb_info[i].page); + page_pool_put_full_page(rxq->page_pool, rxq->rx_skb_info[i].page, false); for (i = 0; i < XDP_STATS_TOTAL; i++) rxq->stats[i] = 0; diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c index 9349f841bd06..587ad81a2dc3 100644 --- a/drivers/net/ethernet/freescale/fman/fman_memac.c +++ b/drivers/net/ethernet/freescale/fman/fman_memac.c @@ -1055,6 +1055,9 @@ static struct phylink_pcs *memac_pcs_create(struct device_node *mac_node, return ERR_PTR(-EPROBE_DEFER); pcs = lynx_pcs_create(mdiodev); + if (!pcs) + mdio_device_free(mdiodev); + return pcs; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 081bd2c3f289..e84e5be8e59e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -3130,7 +3130,7 @@ static int hclgevf_set_channels(struct hnae3_handle *handle, u32 new_tqps_num, hclgevf_update_rss_size(handle, new_tqps_num); - hclge_comm_get_rss_tc_info(cur_rss_size, hdev->hw_tc_map, + hclge_comm_get_rss_tc_info(kinfo->rss_size, hdev->hw_tc_map, tc_offset, tc_valid, tc_size); ret = hclge_comm_set_rss_tc_mode(&hdev->hw.hw, tc_offset, tc_valid, tc_size); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 0d1bab4ac1b0..2a9f1eeeb701 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -249,6 +249,7 @@ struct iavf_cloud_filter { /* board specific private data structure */ struct iavf_adapter { + struct workqueue_struct *wq; struct work_struct reset_task; struct work_struct adminq_task; struct delayed_work client_task; @@ -459,7 +460,6 @@ struct iavf_device { /* needed by iavf_ethtool.c */ extern char iavf_driver_name[]; -extern struct workqueue_struct *iavf_wq; static inline const char *iavf_state_str(enum iavf_state_t state) { diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index d79ead5e8d0c..6f171d1d85b7 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -532,7 +532,7 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) if (changed_flags & IAVF_FLAG_LEGACY_RX) { if (netif_running(netdev)) { adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(iavf_wq, &adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); } } @@ -672,7 +672,7 @@ static int iavf_set_ringparam(struct net_device *netdev, if (netif_running(netdev)) { adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(iavf_wq, &adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); } return 0; @@ -1433,7 +1433,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; spin_unlock_bh(&adapter->fdir_fltr_lock); - mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); ret: if (err && fltr) @@ -1474,7 +1474,7 @@ static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx spin_unlock_bh(&adapter->fdir_fltr_lock); if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) - mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); return err; } @@ -1658,7 +1658,7 @@ iavf_set_adv_rss_hash_opt(struct iavf_adapter *adapter, spin_unlock_bh(&adapter->adv_rss_lock); if (!err) - mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); mutex_unlock(&adapter->crit_lock); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index c4e451ef7942..4b09785d2147 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -49,7 +49,6 @@ MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver") MODULE_LICENSE("GPL v2"); static const struct net_device_ops iavf_netdev_ops; -struct workqueue_struct *iavf_wq; int iavf_status_to_errno(enum iavf_status status) { @@ -277,7 +276,7 @@ void iavf_schedule_reset(struct iavf_adapter *adapter) if (!(adapter->flags & (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(iavf_wq, &adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); } } @@ -291,7 +290,7 @@ void iavf_schedule_reset(struct iavf_adapter *adapter) void iavf_schedule_request_stats(struct iavf_adapter *adapter) { adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS; - mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } /** @@ -411,7 +410,7 @@ static irqreturn_t iavf_msix_aq(int irq, void *data) if (adapter->state != __IAVF_REMOVE) /* schedule work on the private workqueue */ - queue_work(iavf_wq, &adapter->adminq_task); + queue_work(adapter->wq, &adapter->adminq_task); return IRQ_HANDLED; } @@ -1034,7 +1033,7 @@ int iavf_replace_primary_mac(struct iavf_adapter *adapter, /* schedule the watchdog task to immediately process the request */ if (f) { - queue_work(iavf_wq, &adapter->watchdog_task.work); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); return 0; } return -ENOMEM; @@ -1257,7 +1256,7 @@ static void iavf_up_complete(struct iavf_adapter *adapter) adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES; if (CLIENT_ENABLED(adapter)) adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN; - mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } /** @@ -1414,7 +1413,7 @@ void iavf_down(struct iavf_adapter *adapter) adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; } - mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } /** @@ -2248,7 +2247,7 @@ iavf_set_vlan_offload_features(struct iavf_adapter *adapter, if (aq_required) { adapter->aq_required |= aq_required; - mod_delayed_work(iavf_wq, &adapter->watchdog_task, 0); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } } @@ -2693,6 +2692,15 @@ static void iavf_watchdog_task(struct work_struct *work) goto restart_watchdog; } + if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && + adapter->netdev_registered && + !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) && + rtnl_trylock()) { + netdev_update_features(adapter->netdev); + rtnl_unlock(); + adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; + } + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) iavf_change_state(adapter, __IAVF_COMM_FAILED); @@ -2700,7 +2708,7 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; mutex_unlock(&adapter->crit_lock); - queue_work(iavf_wq, &adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); return; } @@ -2708,31 +2716,31 @@ static void iavf_watchdog_task(struct work_struct *work) case __IAVF_STARTUP: iavf_startup(adapter); mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, &adapter->watchdog_task, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_VERSION_CHECK: iavf_init_version_check(adapter); mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, &adapter->watchdog_task, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_GET_RESOURCES: iavf_init_get_resources(adapter); mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, &adapter->watchdog_task, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_EXTENDED_CAPS: iavf_init_process_extended_caps(adapter); mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, &adapter->watchdog_task, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_CONFIG_ADAPTER: iavf_init_config_adapter(adapter); mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, &adapter->watchdog_task, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_FAILED: @@ -2751,14 +2759,14 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; iavf_shutdown_adminq(hw); mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, (5 * HZ)); return; } /* Try again from failed step*/ iavf_change_state(adapter, adapter->last_state); mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ); return; case __IAVF_COMM_FAILED: if (test_bit(__IAVF_IN_REMOVE_TASK, @@ -2789,13 +2797,14 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(10)); return; case __IAVF_RESETTING: mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, + HZ * 2); return; case __IAVF_DOWN: case __IAVF_DOWN_PENDING: @@ -2834,9 +2843,9 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); - queue_work(iavf_wq, &adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); mutex_unlock(&adapter->crit_lock); - queue_delayed_work(iavf_wq, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); return; } @@ -2845,12 +2854,13 @@ static void iavf_watchdog_task(struct work_struct *work) mutex_unlock(&adapter->crit_lock); restart_watchdog: if (adapter->state >= __IAVF_DOWN) - queue_work(iavf_wq, &adapter->adminq_task); + queue_work(adapter->wq, &adapter->adminq_task); if (adapter->aq_required) - queue_delayed_work(iavf_wq, &adapter->watchdog_task, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(20)); else - queue_delayed_work(iavf_wq, &adapter->watchdog_task, HZ * 2); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, + HZ * 2); } /** @@ -2952,7 +2962,7 @@ static void iavf_reset_task(struct work_struct *work) */ if (!mutex_trylock(&adapter->crit_lock)) { if (adapter->state != __IAVF_REMOVE) - queue_work(iavf_wq, &adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); goto reset_finish; } @@ -3116,7 +3126,7 @@ continue_reset: bitmap_clear(adapter->vsi.active_cvlans, 0, VLAN_N_VID); bitmap_clear(adapter->vsi.active_svlans, 0, VLAN_N_VID); - mod_delayed_work(iavf_wq, &adapter->watchdog_task, 2); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 2); /* We were running when the reset started, so we need to restore some * state here. @@ -3208,7 +3218,7 @@ static void iavf_adminq_task(struct work_struct *work) if (adapter->state == __IAVF_REMOVE) return; - queue_work(iavf_wq, &adapter->adminq_task); + queue_work(adapter->wq, &adapter->adminq_task); goto out; } @@ -3232,24 +3242,6 @@ 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) @@ -3850,7 +3842,7 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", - be32_to_cpu(match.mask->dst)); + be32_to_cpu(match.mask->src)); return -EINVAL; } } @@ -4349,7 +4341,7 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) if (netif_running(netdev)) { adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(iavf_wq, &adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); } return 0; @@ -4898,6 +4890,13 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw = &adapter->hw; hw->back = adapter; + adapter->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, + iavf_driver_name); + if (!adapter->wq) { + err = -ENOMEM; + goto err_alloc_wq; + } + adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1; iavf_change_state(adapter, __IAVF_STARTUP); @@ -4942,7 +4941,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->adminq_task, iavf_adminq_task); INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task); INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); - queue_delayed_work(iavf_wq, &adapter->watchdog_task, + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); /* Setup the wait queue for indicating transition to down status */ @@ -4954,6 +4953,8 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; err_ioremap: + destroy_workqueue(adapter->wq); +err_alloc_wq: free_netdev(netdev); err_alloc_etherdev: pci_disable_pcie_error_reporting(pdev); @@ -5023,7 +5024,7 @@ static int __maybe_unused iavf_resume(struct device *dev_d) return err; } - queue_work(iavf_wq, &adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); netif_device_attach(adapter->netdev); @@ -5170,6 +5171,8 @@ static void iavf_remove(struct pci_dev *pdev) } spin_unlock_bh(&adapter->adv_rss_lock); + destroy_workqueue(adapter->wq); + free_netdev(netdev); pci_disable_pcie_error_reporting(pdev); @@ -5196,24 +5199,11 @@ static struct pci_driver iavf_driver = { **/ static int __init iavf_init_module(void) { - int ret; - pr_info("iavf: %s\n", iavf_driver_string); pr_info("%s\n", iavf_copyright); - iavf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, - iavf_driver_name); - if (!iavf_wq) { - pr_err("%s: Failed to create workqueue\n", iavf_driver_name); - return -ENOMEM; - } - - ret = pci_register_driver(&iavf_driver); - if (ret) - destroy_workqueue(iavf_wq); - - return ret; + return pci_register_driver(&iavf_driver); } module_init(iavf_init_module); @@ -5227,7 +5217,6 @@ module_init(iavf_init_module); static void __exit iavf_exit_module(void) { pci_unregister_driver(&iavf_driver); - destroy_workqueue(iavf_wq); } module_exit(iavf_exit_module); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 24a701fd140e..365ca0c710c4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1952,7 +1952,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) { adapter->flags |= IAVF_FLAG_RESET_PENDING; dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); - queue_work(iavf_wq, &adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); } break; default: @@ -2226,6 +2226,14 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; + + /* 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); + was_mac_changed = !ether_addr_equal(netdev->dev_addr, adapter->hw.mac.addr); diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 2f0b604abc5e..713069f809ec 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -880,7 +880,7 @@ void ice_set_ethtool_repr_ops(struct net_device *netdev); void ice_set_ethtool_safe_mode_ops(struct net_device *netdev); u16 ice_get_avail_txq_count(struct ice_pf *pf); u16 ice_get_avail_rxq_count(struct ice_pf *pf); -int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx); +int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked); void ice_update_vsi_stats(struct ice_vsi *vsi); void ice_update_pf_stats(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index 4f24d441c35e..0a55c552189a 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -441,7 +441,7 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked) goto out; } - ice_pf_dcb_recfg(pf); + ice_pf_dcb_recfg(pf, false); out: /* enable previously downed VSIs */ @@ -731,12 +731,13 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf) /** * ice_pf_dcb_recfg - Reconfigure all VEBs and VSIs * @pf: pointer to the PF struct + * @locked: is adev device lock held * * Assumed caller has already disabled all VSIs before * calling this function. Reconfiguring DCB based on * local_dcbx_cfg. */ -void ice_pf_dcb_recfg(struct ice_pf *pf) +void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) { struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->qos_cfg.local_dcbx_cfg; struct iidc_event *event; @@ -783,14 +784,16 @@ void ice_pf_dcb_recfg(struct ice_pf *pf) if (vsi->type == ICE_VSI_PF) ice_dcbnl_set_all(vsi); } - /* Notify the AUX drivers that TC change is finished */ - event = kzalloc(sizeof(*event), GFP_KERNEL); - if (!event) - return; + if (!locked) { + /* Notify the AUX drivers that TC change is finished */ + event = kzalloc(sizeof(*event), GFP_KERNEL); + if (!event) + return; - set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); - ice_send_event_to_aux(pf, event); - kfree(event); + set_bit(IIDC_EVENT_AFTER_TC_CHANGE, event->type); + ice_send_event_to_aux(pf, event); + kfree(event); + } } /** @@ -1044,7 +1047,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, } /* changes in configuration update VSI */ - ice_pf_dcb_recfg(pf); + ice_pf_dcb_recfg(pf, false); /* enable previously downed VSIs */ ice_dcb_ena_dis_vsi(pf, true, true); diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 4c421c842a13..800879a88c5e 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -23,7 +23,7 @@ u8 ice_dcb_get_tc(struct ice_vsi *vsi, int queue_index); int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked); int ice_dcb_bwchk(struct ice_pf *pf, struct ice_dcbx_cfg *dcbcfg); -void ice_pf_dcb_recfg(struct ice_pf *pf); +void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked); void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi); int ice_init_pf_dcb(struct ice_pf *pf, bool locked); void ice_update_dcb_stats(struct ice_pf *pf); @@ -128,7 +128,7 @@ static inline u8 ice_get_pfc_mode(struct ice_pf *pf) return 0; } -static inline void ice_pf_dcb_recfg(struct ice_pf *pf) { } +static inline void ice_pf_dcb_recfg(struct ice_pf *pf, bool locked) { } static inline void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { } static inline void ice_update_dcb_stats(struct ice_pf *pf) { } static inline void diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 4191994d8f3a..a359f1610fc1 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3641,7 +3641,9 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; int new_rx = 0, new_tx = 0; + bool locked = false; u32 curr_combined; + int ret = 0; /* do not support changing channels in Safe Mode */ if (ice_is_safe_mode(pf)) { @@ -3705,15 +3707,33 @@ static int ice_set_channels(struct net_device *dev, struct ethtool_channels *ch) return -EINVAL; } - ice_vsi_recfg_qs(vsi, new_rx, new_tx); + if (pf->adev) { + mutex_lock(&pf->adev_mutex); + device_lock(&pf->adev->dev); + locked = true; + if (pf->adev->dev.driver) { + netdev_err(dev, "Cannot change channels when RDMA is active\n"); + ret = -EBUSY; + goto adev_unlock; + } + } + + ice_vsi_recfg_qs(vsi, new_rx, new_tx, locked); - if (!netif_is_rxfh_configured(dev)) - return ice_vsi_set_dflt_rss_lut(vsi, new_rx); + if (!netif_is_rxfh_configured(dev)) { + ret = ice_vsi_set_dflt_rss_lut(vsi, new_rx); + goto adev_unlock; + } /* Update rss_size due to change in Rx queues */ vsi->rss_size = ice_get_valid_rss_size(&pf->hw, new_rx); - return 0; +adev_unlock: + if (locked) { + device_unlock(&pf->adev->dev); + mutex_unlock(&pf->adev_mutex); + } + return ret; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index b5a7f246d230..43e199b5b513 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -363,6 +363,7 @@ ice_gnss_tty_write(struct tty_struct *tty, const unsigned char *buf, int count) /* Send the data out to a hardware port */ write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL); if (!write_buf) { + kfree(cmd_buf); err = -ENOMEM; goto exit; } @@ -460,6 +461,9 @@ static struct tty_driver *ice_gnss_create_tty_driver(struct ice_pf *pf) for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) { pf->gnss_tty_port[i] = kzalloc(sizeof(*pf->gnss_tty_port[i]), GFP_KERNEL); + if (!pf->gnss_tty_port[i]) + goto err_out; + pf->gnss_serial[i] = NULL; tty_port_init(pf->gnss_tty_port[i]); @@ -469,21 +473,23 @@ static struct tty_driver *ice_gnss_create_tty_driver(struct ice_pf *pf) err = tty_register_driver(tty_driver); if (err) { dev_err(dev, "Failed to register TTY driver err=%d\n", err); - - for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) { - tty_port_destroy(pf->gnss_tty_port[i]); - kfree(pf->gnss_tty_port[i]); - } - kfree(ttydrv_name); - tty_driver_kref_put(pf->ice_gnss_tty_driver); - - return NULL; + goto err_out; } for (i = 0; i < ICE_GNSS_TTY_MINOR_DEVICES; i++) dev_info(dev, "%s%d registered\n", ttydrv_name, i); return tty_driver; + +err_out: + while (i--) { + tty_port_destroy(pf->gnss_tty_port[i]); + kfree(pf->gnss_tty_port[i]); + } + kfree(ttydrv_name); + tty_driver_kref_put(pf->ice_gnss_tty_driver); + + return NULL; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 94aa834cd9a6..a596e07b3ce9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -3235,9 +3235,6 @@ int ice_vsi_release(struct ice_vsi *vsi) } } - if (vsi->type == ICE_VSI_PF) - ice_devlink_destroy_pf_port(pf); - if (vsi->type == ICE_VSI_VF && vsi->agg_node && vsi->agg_node->valid) vsi->agg_node->num_vsis--; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index a9a7f8b52140..5f86e4111fa9 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4195,12 +4195,13 @@ bool ice_is_wol_supported(struct ice_hw *hw) * @vsi: VSI being changed * @new_rx: new number of Rx queues * @new_tx: new number of Tx queues + * @locked: is adev device_lock held * * Only change the number of queues if new_tx, or new_rx is non-0. * * Returns 0 on success. */ -int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) +int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked) { struct ice_pf *pf = vsi->back; int err = 0, timeout = 50; @@ -4229,7 +4230,7 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx) ice_vsi_close(vsi); ice_vsi_rebuild(vsi, false); - ice_pf_dcb_recfg(pf); + ice_pf_dcb_recfg(pf, locked); ice_vsi_open(vsi); done: clear_bit(ICE_CFG_BUSY, pf->state); @@ -4590,7 +4591,7 @@ static void ice_print_wake_reason(struct ice_pf *pf) } /** - * ice_register_netdev - register netdev and devlink port + * ice_register_netdev - register netdev * @pf: pointer to the PF struct */ static int ice_register_netdev(struct ice_pf *pf) @@ -4602,11 +4603,6 @@ static int ice_register_netdev(struct ice_pf *pf) if (!vsi || !vsi->netdev) return -EIO; - err = ice_devlink_create_pf_port(pf); - if (err) - goto err_devlink_create; - - SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); err = register_netdev(vsi->netdev); if (err) goto err_register_netdev; @@ -4617,8 +4613,6 @@ static int ice_register_netdev(struct ice_pf *pf) return 0; err_register_netdev: - ice_devlink_destroy_pf_port(pf); -err_devlink_create: free_netdev(vsi->netdev); vsi->netdev = NULL; clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); @@ -4636,6 +4630,7 @@ static int ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { struct device *dev = &pdev->dev; + struct ice_vsi *vsi; struct ice_pf *pf; struct ice_hw *hw; int i, err; @@ -4918,6 +4913,18 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) pcie_print_link_status(pf->pdev); probe_done: + err = ice_devlink_create_pf_port(pf); + if (err) + goto err_create_pf_port; + + vsi = ice_get_main_vsi(pf); + if (!vsi || !vsi->netdev) { + err = -EINVAL; + goto err_netdev_reg; + } + + SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port); + err = ice_register_netdev(pf); if (err) goto err_netdev_reg; @@ -4955,6 +4962,8 @@ err_init_aux_unroll: err_devlink_reg_param: ice_devlink_unregister_params(pf); err_netdev_reg: + ice_devlink_destroy_pf_port(pf); +err_create_pf_port: err_send_version_unroll: ice_vsi_release_all(pf); err_alloc_sw_unroll: @@ -5083,6 +5092,7 @@ static void ice_remove(struct pci_dev *pdev) ice_setup_mc_magic_wake(pf); ice_vsi_release_all(pf); mutex_destroy(&(&pf->hw)->fdir_fltr_lock); + ice_devlink_destroy_pf_port(pf); ice_set_wake(pf); ice_free_irq_msix_misc(pf); ice_for_each_vsi(pf, i) { diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index a7b22639cfcd..e9747ec5ac0b 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -475,7 +475,9 @@ #define IGC_TSAUXC_EN_TT0 BIT(0) /* Enable target time 0. */ #define IGC_TSAUXC_EN_TT1 BIT(1) /* Enable target time 1. */ #define IGC_TSAUXC_EN_CLK0 BIT(2) /* Enable Configurable Frequency Clock 0. */ +#define IGC_TSAUXC_ST0 BIT(4) /* Start Clock 0 Toggle on Target Time 0. */ #define IGC_TSAUXC_EN_CLK1 BIT(5) /* Enable Configurable Frequency Clock 1. */ +#define IGC_TSAUXC_ST1 BIT(7) /* Start Clock 1 Toggle on Target Time 1. */ #define IGC_TSAUXC_EN_TS0 BIT(8) /* Enable hardware timestamp 0. */ #define IGC_TSAUXC_AUTT0 BIT(9) /* Auxiliary Timestamp Taken. */ #define IGC_TSAUXC_EN_TS1 BIT(10) /* Enable hardware timestamp 0. */ diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 8dbb9f903ca7..4e10ced736db 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -322,7 +322,7 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, ts = ns_to_timespec64(ns); if (rq->perout.index == 1) { if (use_freq) { - tsauxc_mask = IGC_TSAUXC_EN_CLK1; + tsauxc_mask = IGC_TSAUXC_EN_CLK1 | IGC_TSAUXC_ST1; tsim_mask = 0; } else { tsauxc_mask = IGC_TSAUXC_EN_TT1; @@ -333,7 +333,7 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, freqout = IGC_FREQOUT1; } else { if (use_freq) { - tsauxc_mask = IGC_TSAUXC_EN_CLK0; + tsauxc_mask = IGC_TSAUXC_EN_CLK0 | IGC_TSAUXC_ST0; tsim_mask = 0; } else { tsauxc_mask = IGC_TSAUXC_EN_TT0; @@ -347,10 +347,12 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, tsauxc = rd32(IGC_TSAUXC); tsim = rd32(IGC_TSIM); if (rq->perout.index == 1) { - tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1); + tsauxc &= ~(IGC_TSAUXC_EN_TT1 | IGC_TSAUXC_EN_CLK1 | + IGC_TSAUXC_ST1); tsim &= ~IGC_TSICR_TT1; } else { - tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0); + tsauxc &= ~(IGC_TSAUXC_EN_TT0 | IGC_TSAUXC_EN_CLK0 | + IGC_TSAUXC_ST0); tsim &= ~IGC_TSICR_TT0; } if (on) { @@ -415,10 +417,12 @@ static int igc_ptp_verify_pin(struct ptp_clock_info *ptp, unsigned int pin, * * We need to convert the system time value stored in the RX/TXSTMP registers * into a hwtstamp which can be used by the upper level timestamping functions. + * + * Returns 0 on success. **/ -static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, - struct skb_shared_hwtstamps *hwtstamps, - u64 systim) +static int igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, + struct skb_shared_hwtstamps *hwtstamps, + u64 systim) { switch (adapter->hw.mac.type) { case igc_i225: @@ -428,8 +432,9 @@ static void igc_ptp_systim_to_hwtstamp(struct igc_adapter *adapter, systim & 0xFFFFFFFF); break; default: - break; + return -EINVAL; } + return 0; } /** @@ -650,7 +655,8 @@ static void igc_ptp_tx_hwtstamp(struct igc_adapter *adapter) regval = rd32(IGC_TXSTMPL); regval |= (u64)rd32(IGC_TXSTMPH) << 32; - igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + if (igc_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval)) + return; switch (adapter->link_speed) { case SPEED_10: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 24aa97f993ca..123dca9ce468 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -855,9 +855,11 @@ static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn) rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn); if (rp_pdev && rp_pdev->subordinate) { bus = rp_pdev->subordinate->number; + pci_dev_put(rp_pdev); return pci_get_domain_bus_and_slot(0, bus, 0); } + pci_dev_put(rp_pdev); return NULL; } @@ -874,6 +876,7 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) struct ixgbe_adapter *adapter = hw->back; struct pci_dev *pdev = adapter->pdev; struct pci_dev *func0_pdev; + bool has_mii = false; /* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices * are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0 @@ -884,15 +887,16 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0)); if (func0_pdev) { if (func0_pdev == pdev) - return true; - else - return false; + has_mii = true; + goto out; } func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0)); if (func0_pdev == pdev) - return true; + has_mii = true; - return false; +out: + pci_dev_put(func0_pdev); + return has_mii; } /** diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index b2b71fe80d61..724df6398bbe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -774,9 +774,9 @@ int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable) cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_CFG); if (enable) - cfg |= CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN; + cfg |= DATA_PKT_RX_EN | DATA_PKT_TX_EN; else - cfg &= ~(CMR_EN | DATA_PKT_RX_EN | DATA_PKT_TX_EN); + cfg &= ~(DATA_PKT_RX_EN | DATA_PKT_TX_EN); cgx_write(cgx, lmac_id, CGXX_CMRX_CFG, cfg); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index fb2d37676d84..5a20d93004c7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -26,7 +26,6 @@ #define CMR_P2X_SEL_SHIFT 59ULL #define CMR_P2X_SEL_NIX0 1ULL #define CMR_P2X_SEL_NIX1 2ULL -#define CMR_EN BIT_ULL(55) #define DATA_PKT_TX_EN BIT_ULL(53) #define DATA_PKT_RX_EN BIT_ULL(54) #define CGX_LMAC_TYPE_SHIFT 40 diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index bda1a6fa2ec4..e4407f09c9d3 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -1500,6 +1500,9 @@ static const struct devlink_param rvu_af_dl_params[] = { BIT(DEVLINK_PARAM_CMODE_RUNTIME), rvu_af_dl_dwrr_mtu_get, rvu_af_dl_dwrr_mtu_set, rvu_af_dl_dwrr_mtu_validate), +}; + +static const struct devlink_param rvu_af_dl_param_exact_match[] = { DEVLINK_PARAM_DRIVER(RVU_AF_DEVLINK_PARAM_ID_NPC_EXACT_FEATURE_DISABLE, "npc_exact_feature_disable", DEVLINK_PARAM_TYPE_STRING, BIT(DEVLINK_PARAM_CMODE_RUNTIME), @@ -1556,7 +1559,6 @@ int rvu_register_dl(struct rvu *rvu) { struct rvu_devlink *rvu_dl; struct devlink *dl; - size_t size; int err; dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink), @@ -1578,21 +1580,32 @@ int rvu_register_dl(struct rvu *rvu) goto err_dl_health; } + err = devlink_params_register(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); + if (err) { + dev_err(rvu->dev, + "devlink params register failed with error %d", err); + goto err_dl_health; + } + /* Register exact match devlink only for CN10K-B */ - size = ARRAY_SIZE(rvu_af_dl_params); if (!rvu_npc_exact_has_match_table(rvu)) - size -= 1; + goto done; - err = devlink_params_register(dl, rvu_af_dl_params, size); + err = devlink_params_register(dl, rvu_af_dl_param_exact_match, + ARRAY_SIZE(rvu_af_dl_param_exact_match)); if (err) { dev_err(rvu->dev, - "devlink params register failed with error %d", err); - goto err_dl_health; + "devlink exact match params register failed with error %d", err); + goto err_dl_exact_match; } +done: devlink_register(dl); return 0; +err_dl_exact_match: + devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); + err_dl_health: rvu_health_reporters_destroy(rvu); devlink_free(dl); @@ -1605,8 +1618,14 @@ void rvu_unregister_dl(struct rvu *rvu) struct devlink *dl = rvu_dl->dl; devlink_unregister(dl); - devlink_params_unregister(dl, rvu_af_dl_params, - ARRAY_SIZE(rvu_af_dl_params)); + + devlink_params_unregister(dl, rvu_af_dl_params, ARRAY_SIZE(rvu_af_dl_params)); + + /* Unregister exact match devlink only for CN10K-B */ + if (rvu_npc_exact_has_match_table(rvu)) + devlink_params_unregister(dl, rvu_af_dl_param_exact_match, + ARRAY_SIZE(rvu_af_dl_param_exact_match)); + rvu_health_reporters_destroy(rvu); devlink_free(dl); } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 88f8772a61cd..8a41ad8ca04f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1012,7 +1012,6 @@ static void otx2_pool_refill_task(struct work_struct *work) rbpool = cq->rbpool; free_ptrs = cq->pool_ptrs; - get_cpu(); while (cq->pool_ptrs) { if (otx2_alloc_rbuf(pfvf, rbpool, &bufptr)) { /* Schedule a WQ if we fails to free atleast half of the @@ -1032,7 +1031,6 @@ static void otx2_pool_refill_task(struct work_struct *work) pfvf->hw_ops->aura_freeptr(pfvf, qidx, bufptr + OTX2_HEAD_ROOM); cq->pool_ptrs--; } - put_cpu(); cq->refill_task_sched = false; } @@ -1370,7 +1368,6 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf) if (err) goto fail; - get_cpu(); /* Allocate pointers and free them to aura/pool */ for (qidx = 0; qidx < hw->tot_tx_queues; qidx++) { pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_SQ, qidx); @@ -1394,7 +1391,6 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf) } err_mem: - put_cpu(); return err ? -ENOMEM : 0; fail: @@ -1435,21 +1431,18 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf) if (err) goto fail; - get_cpu(); /* Allocate pointers and free them to aura/pool */ for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) { pool = &pfvf->qset.pool[pool_id]; for (ptr = 0; ptr < num_ptrs; ptr++) { err = otx2_alloc_rbuf(pfvf, pool, &bufptr); if (err) - goto err_mem; + return -ENOMEM; pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr + OTX2_HEAD_ROOM); } } -err_mem: - put_cpu(); - return err ? -ENOMEM : 0; + return 0; fail: otx2_mbox_reset(&pfvf->mbox.mbox, 0); otx2_aura_pool_free(pfvf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 5bee3c3a7ce4..3d22cc6a2804 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -736,8 +736,10 @@ static inline void cn10k_aura_freeptr(void *dev, int aura, u64 buf) u64 ptrs[2]; ptrs[1] = buf; + get_cpu(); /* Free only one buffer at time during init and teardown */ __cn10k_aura_freeptr(pfvf, aura, ptrs, 2); + put_cpu(); } /* Alloc pointer from pool/aura */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 86653bb8e403..7f8ffbf79cf7 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -758,6 +758,8 @@ static void otx2vf_remove(struct pci_dev *pdev) if (vf->otx2_wq) destroy_workqueue(vf->otx2_wq); otx2_ptp_destroy(vf); + otx2_mcam_flow_del(vf); + otx2_shutdown_tc(vf); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); if (test_bit(CN10K_LMTST, &vf->hw.cap_flag)) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index e3de9a53b2d9..d56eda6397a4 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3177,7 +3177,8 @@ static int mtk_open(struct net_device *dev) struct mtk_eth *eth = mac->hw; int i, err; - if (mtk_uses_dsa(dev) && !eth->prog) { + if ((mtk_uses_dsa(dev) && !eth->prog) && + !(mac->id == 1 && MTK_HAS_CAPS(eth->soc->caps, MTK_GMAC1_TRGMII))) { for (i = 0; i < ARRAY_SIZE(eth->dsa_meta); i++) { struct metadata_dst *md_dst = eth->dsa_meta[i]; @@ -3194,7 +3195,8 @@ static int mtk_open(struct net_device *dev) } } else { /* Hardware special tag parsing needs to be disabled if at least - * one MAC does not use DSA. + * one MAC does not use DSA, or the second MAC of the MT7621 and + * MT7623 SoCs is being used. */ u32 val = mtk_r32(eth, MTK_CDMP_IG_CTRL); val &= ~MTK_CDMP_STAG_EN; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 18a50529ce7b..2d9186d32bc0 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -519,7 +519,7 @@ #define SGMII_SPEED_10 FIELD_PREP(SGMII_SPEED_MASK, 0) #define SGMII_SPEED_100 FIELD_PREP(SGMII_SPEED_MASK, 1) #define SGMII_SPEED_1000 FIELD_PREP(SGMII_SPEED_MASK, 2) -#define SGMII_DUPLEX_FULL BIT(4) +#define SGMII_DUPLEX_HALF BIT(4) #define SGMII_IF_MODE_BIT5 BIT(5) #define SGMII_REMOTE_FAULT_DIS BIT(8) #define SGMII_CODE_SYNC_SET_VAL BIT(9) @@ -1036,11 +1036,13 @@ struct mtk_soc_data { * @regmap: The register map pointing at the range used to setup * SGMII modes * @ana_rgc3: The offset refers to register ANA_RGC3 related to regmap + * @interface: Currently configured interface mode * @pcs: Phylink PCS structure */ struct mtk_pcs { struct regmap *regmap; u32 ana_rgc3; + phy_interface_t interface; struct phylink_pcs pcs; }; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.c b/drivers/net/ethernet/mediatek/mtk_ppe.c index 269208a841c7..1ff024f42444 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe.c @@ -615,8 +615,7 @@ mtk_foe_entry_commit_subflow(struct mtk_ppe *ppe, struct mtk_flow_entry *entry, u32 ib1_mask = mtk_get_ib1_pkt_type_mask(ppe->eth) | MTK_FOE_IB1_UDP; int type; - flow_info = kzalloc(offsetof(struct mtk_flow_entry, l2_data.end), - GFP_ATOMIC); + flow_info = kzalloc(sizeof(*flow_info), GFP_ATOMIC); if (!flow_info) return; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe.h b/drivers/net/ethernet/mediatek/mtk_ppe.h index ea64fac1d425..b5e432031340 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe.h +++ b/drivers/net/ethernet/mediatek/mtk_ppe.h @@ -279,7 +279,6 @@ struct mtk_flow_entry { struct { struct mtk_flow_entry *base_flow; struct hlist_node list; - struct {} end; } l2_data; }; struct rhash_head node; diff --git a/drivers/net/ethernet/mediatek/mtk_sgmii.c b/drivers/net/ethernet/mediatek/mtk_sgmii.c index 5c286f2c9418..bb00de1003ac 100644 --- a/drivers/net/ethernet/mediatek/mtk_sgmii.c +++ b/drivers/net/ethernet/mediatek/mtk_sgmii.c @@ -43,11 +43,6 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, int advertise, link_timer; bool changed, use_an; - if (interface == PHY_INTERFACE_MODE_2500BASEX) - rgc3 = RG_PHY_SPEED_3_125G; - else - rgc3 = 0; - advertise = phylink_mii_c22_pcs_encode_advertisement(interface, advertising); if (advertise < 0) @@ -88,9 +83,22 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, bmcr = 0; } - /* Configure the underlying interface speed */ - regmap_update_bits(mpcs->regmap, mpcs->ana_rgc3, - RG_PHY_SPEED_3_125G, rgc3); + if (mpcs->interface != interface) { + /* PHYA power down */ + regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, + SGMII_PHYA_PWD, SGMII_PHYA_PWD); + + if (interface == PHY_INTERFACE_MODE_2500BASEX) + rgc3 = RG_PHY_SPEED_3_125G; + else + rgc3 = 0; + + /* Configure the underlying interface speed */ + regmap_update_bits(mpcs->regmap, mpcs->ana_rgc3, + RG_PHY_SPEED_3_125G, rgc3); + + mpcs->interface = interface; + } /* Update the advertisement, noting whether it has changed */ regmap_update_bits_check(mpcs->regmap, SGMSYS_PCS_ADVERTISE, @@ -108,9 +116,17 @@ static int mtk_pcs_config(struct phylink_pcs *pcs, unsigned int mode, regmap_update_bits(mpcs->regmap, SGMSYS_PCS_CONTROL_1, SGMII_AN_RESTART | SGMII_AN_ENABLE, bmcr); - /* Release PHYA power down state */ - regmap_update_bits(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, - SGMII_PHYA_PWD, 0); + /* Release PHYA power down state + * Only removing bit SGMII_PHYA_PWD isn't enough. + * There are cases when the SGMII_PHYA_PWD register contains 0x9 which + * prevents SGMII from working. The SGMII still shows link but no traffic + * can flow. Writing 0x0 to the PHYA_PWD register fix the issue. 0x0 was + * taken from a good working state of the SGMII interface. + * Unknown how much the QPHY needs but it is racy without a sleep. + * Tested on mt7622 & mt7986. + */ + usleep_range(50, 100); + regmap_write(mpcs->regmap, SGMSYS_QPHY_PWR_STATE_CTRL, 0); return changed; } @@ -138,11 +154,11 @@ static void mtk_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, else sgm_mode = SGMII_SPEED_1000; - if (duplex == DUPLEX_FULL) - sgm_mode |= SGMII_DUPLEX_FULL; + if (duplex != DUPLEX_FULL) + sgm_mode |= SGMII_DUPLEX_HALF; regmap_update_bits(mpcs->regmap, SGMSYS_SGMII_MODE, - SGMII_DUPLEX_FULL | SGMII_SPEED_MASK, + SGMII_DUPLEX_HALF | SGMII_SPEED_MASK, sgm_mode); } } @@ -171,6 +187,8 @@ int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *r, u32 ana_rgc3) return PTR_ERR(ss->pcs[i].regmap); ss->pcs[i].pcs.ops = &mtk_pcs_ops; + ss->pcs[i].pcs.poll = true; + ss->pcs[i].interface = PHY_INTERFACE_MODE_NA; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index d3ca745d107d..c837103a9ee3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -2176,15 +2176,9 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) return -EINVAL; } - cmd->stats = kvcalloc(MLX5_CMD_OP_MAX, sizeof(*cmd->stats), GFP_KERNEL); - if (!cmd->stats) - return -ENOMEM; - cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0); - if (!cmd->pool) { - err = -ENOMEM; - goto dma_pool_err; - } + if (!cmd->pool) + return -ENOMEM; err = alloc_cmd_page(dev, cmd); if (err) @@ -2268,8 +2262,6 @@ err_free_page: err_free_pool: dma_pool_destroy(cmd->pool); -dma_pool_err: - kvfree(cmd->stats); return err; } @@ -2282,7 +2274,6 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev) destroy_msg_cache(dev); free_cmd_page(dev, cmd); dma_pool_destroy(cmd->pool); - kvfree(cmd->stats); } void mlx5_cmd_set_state(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c b/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c index 6dac76fa58a3..09d441ecb9f6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/htb.c @@ -637,7 +637,7 @@ mlx5e_htb_update_children(struct mlx5e_htb *htb, struct mlx5e_qos_node *node, if (child->bw_share == old_bw_share) continue; - err_one = mlx5_qos_update_node(htb->mdev, child->hw_id, child->bw_share, + err_one = mlx5_qos_update_node(htb->mdev, child->bw_share, child->max_average_bw, child->hw_id); if (!err && err_one) { err = err_one; @@ -671,7 +671,7 @@ mlx5e_htb_node_modify(struct mlx5e_htb *htb, u16 classid, u64 rate, u64 ceil, mlx5e_htb_convert_rate(htb, rate, node->parent, &bw_share); mlx5e_htb_convert_ceil(htb, ceil, &max_average_bw); - err = mlx5_qos_update_node(htb->mdev, node->parent->hw_id, bw_share, + err = mlx5_qos_update_node(htb->mdev, bw_share, max_average_bw, node->hw_id); if (err) { NL_SET_ERR_MSG_MOD(extack, "Firmware error when modifying a node."); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 585bdc8383ee..4ad19c981294 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -578,7 +578,6 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa { enum mlx5e_mpwrq_umr_mode umr_mode = mlx5e_mpwrq_umr_mode(mdev, xsk); u8 page_shift = mlx5e_mpwrq_page_shift(mdev, xsk); - bool unaligned = xsk ? xsk->unaligned : false; u16 max_mtu_pkts; if (!mlx5e_check_fragmented_striding_rq_cap(mdev, page_shift, umr_mode)) @@ -591,7 +590,7 @@ int mlx5e_mpwrq_validate_xsk(struct mlx5_core_dev *mdev, struct mlx5e_params *pa * needed number of WQEs exceeds the maximum. */ max_mtu_pkts = min_t(u8, MLX5E_PARAMS_MAXIMUM_LOG_RQ_SIZE, - mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, unaligned)); + mlx5e_mpwrq_max_log_rq_pkts(mdev, page_shift, xsk->unaligned)); if (params->log_rq_mtu_frames > max_mtu_pkts) { mlx5_core_err(mdev, "Current RQ length %d is too big for XSK with given frame size %u\n", 1 << params->log_rq_mtu_frames, xsk->chunk_size); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c index 512d43148922..c4378afdec09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/police.c @@ -34,12 +34,6 @@ static int police_act_validate(const struct flow_action_entry *act, return -EOPNOTSUPP; } - if (act->police.rate_pkt_ps) { - NL_SET_ERR_MSG_MOD(extack, - "QoS offload not support packets per second"); - return -EOPNOTSUPP; - } - return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c index 8d7d761482d2..50b60fd00946 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/post_meter.c @@ -127,6 +127,7 @@ mlx5e_post_meter_add_rule(struct mlx5e_priv *priv, attr->counter = act_counter; attr->flags |= MLX5_ATTR_FLAG_NO_IN_PORT; + attr->inner_match_level = MLX5_MATCH_NONE; attr->outer_match_level = MLX5_MATCH_NONE; attr->chain = 0; attr->prio = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c index 1cbd2eb9d04f..f2c2c752bd1c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/sample.c @@ -477,7 +477,6 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, struct mlx5e_sample_flow *sample_flow; struct mlx5e_sample_attr *sample_attr; struct mlx5_flow_attr *pre_attr; - u32 tunnel_id = attr->tunnel_id; struct mlx5_eswitch *esw; u32 default_tbl_id; u32 obj_id; @@ -522,7 +521,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, restore_obj.sample.group_id = sample_attr->group_num; restore_obj.sample.rate = sample_attr->rate; restore_obj.sample.trunc_size = sample_attr->trunc_size; - restore_obj.sample.tunnel_id = tunnel_id; + restore_obj.sample.tunnel_id = attr->tunnel_id; err = mapping_add(esw->offloads.reg_c0_obj_pool, &restore_obj, &obj_id); if (err) goto err_obj_id; @@ -548,7 +547,7 @@ mlx5e_tc_sample_offload(struct mlx5e_tc_psample *tc_psample, /* For decap action, do decap in the original flow table instead of the * default flow table. */ - if (tunnel_id) + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_DECAP) pre_attr->action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; pre_attr->modify_hdr = sample_flow->restore->modify_hdr; pre_attr->flags = MLX5_ATTR_FLAG_SAMPLE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c index fd07c4cbfd1d..1f62c702b625 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c @@ -88,6 +88,8 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[], struct udphdr *udp = (struct udphdr *)(buf); struct vxlanhdr *vxh; + if (tun_key->tun_flags & TUNNEL_VXLAN_OPT) + return -EOPNOTSUPP; vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr)); *ip_proto = IPPROTO_UDP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index a92e19c4c499..8bed9c361075 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -122,11 +122,8 @@ struct mlx5e_ipsec_aso { u8 ctx[MLX5_ST_SZ_BYTES(ipsec_aso)]; dma_addr_t dma_addr; struct mlx5_aso *aso; - /* IPsec ASO caches data on every query call, - * so in nested calls, we can use this boolean to save - * recursive calls to mlx5e_ipsec_aso_query() - */ - u8 use_cache : 1; + /* Protect ASO WQ access, as it is global to whole IPsec */ + spinlock_t lock; }; struct mlx5e_ipsec { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c index 8e3614218fc4..2461462b7b99 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c @@ -320,7 +320,6 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work) if (ret) goto unlock; - aso->use_cache = true; if (attrs->esn_trigger && !MLX5_GET(ipsec_aso, aso->ctx, esn_event_arm)) { u32 mode_param = MLX5_GET(ipsec_aso, aso->ctx, mode_parameter); @@ -333,7 +332,6 @@ static void mlx5e_ipsec_handle_event(struct work_struct *_work) !MLX5_GET(ipsec_aso, aso->ctx, hard_lft_arm) || !MLX5_GET(ipsec_aso, aso->ctx, remove_flow_enable)) xfrm_state_check_expire(sa_entry->x); - aso->use_cache = false; unlock: spin_unlock(&sa_entry->x->lock); @@ -398,6 +396,7 @@ int mlx5e_ipsec_aso_init(struct mlx5e_ipsec *ipsec) goto err_aso_create; } + spin_lock_init(&aso->lock); ipsec->nb.notifier_call = mlx5e_ipsec_event; mlx5_notifier_register(mdev, &ipsec->nb); @@ -456,13 +455,12 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, struct mlx5e_hw_objs *res; struct mlx5_aso_wqe *wqe; u8 ds_cnt; + int ret; lockdep_assert_held(&sa_entry->x->lock); - if (aso->use_cache) - return 0; - res = &mdev->mlx5e_res.hw_objs; + spin_lock_bh(&aso->lock); memset(aso->ctx, 0, sizeof(aso->ctx)); wqe = mlx5_aso_get_wqe(aso->aso); ds_cnt = DIV_ROUND_UP(sizeof(*wqe), MLX5_SEND_WQE_DS); @@ -477,7 +475,9 @@ int mlx5e_ipsec_aso_query(struct mlx5e_ipsec_sa_entry *sa_entry, mlx5e_ipsec_aso_copy(ctrl, data); mlx5_aso_post_wqe(aso->aso, false, &wqe->ctrl); - return mlx5_aso_poll_cq(aso->aso, false); + ret = mlx5_aso_poll_cq(aso->aso, false); + spin_unlock_bh(&aso->lock); + return ret; } void mlx5e_ipsec_aso_update_curlft(struct mlx5e_ipsec_sa_entry *sa_entry, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 9369a580743e..7f6b940830b3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -62,6 +62,7 @@ struct mlx5e_macsec_sa { u32 enc_key_id; u32 next_pn; sci_t sci; + ssci_t ssci; salt_t salt; struct rhash_head hash; @@ -358,7 +359,6 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_macsec_obj_attrs obj_attrs; union mlx5e_macsec_rule *macsec_rule; - struct macsec_key *key; int err; obj_attrs.next_pn = sa->next_pn; @@ -368,13 +368,9 @@ static int mlx5e_macsec_init_sa(struct macsec_context *ctx, obj_attrs.aso_pdn = macsec->aso.pdn; obj_attrs.epn_state = sa->epn_state; - key = (is_tx) ? &ctx->sa.tx_sa->key : &ctx->sa.rx_sa->key; - if (sa->epn_state.epn_enabled) { - obj_attrs.ssci = (is_tx) ? cpu_to_be32((__force u32)ctx->sa.tx_sa->ssci) : - cpu_to_be32((__force u32)ctx->sa.rx_sa->ssci); - - memcpy(&obj_attrs.salt, &key->salt, sizeof(key->salt)); + obj_attrs.ssci = cpu_to_be32((__force u32)sa->ssci); + memcpy(&obj_attrs.salt, &sa->salt, sizeof(sa->salt)); } obj_attrs.replay_window = ctx->secy->replay_window; @@ -499,10 +495,11 @@ mlx5e_macsec_get_macsec_device_context(const struct mlx5e_macsec *macsec, } static void update_macsec_epn(struct mlx5e_macsec_sa *sa, const struct macsec_key *key, - const pn_t *next_pn_halves) + const pn_t *next_pn_halves, ssci_t ssci) { struct mlx5e_macsec_epn_state *epn_state = &sa->epn_state; + sa->ssci = ssci; sa->salt = key->salt; epn_state->epn_enabled = 1; epn_state->epn_msb = next_pn_halves->upper; @@ -550,7 +547,8 @@ static int mlx5e_macsec_add_txsa(struct macsec_context *ctx) tx_sa->assoc_num = assoc_num; if (secy->xpn) - update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves); + update_macsec_epn(tx_sa, &ctx_tx_sa->key, &ctx_tx_sa->next_pn_halves, + ctx_tx_sa->ssci); err = mlx5_create_encryption_key(mdev, ctx->sa.key, secy->key_len, MLX5_ACCEL_OBJ_MACSEC_KEY, @@ -945,7 +943,8 @@ static int mlx5e_macsec_add_rxsa(struct macsec_context *ctx) rx_sa->fs_id = rx_sc->sc_xarray_element->fs_id; if (ctx->secy->xpn) - update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves); + update_macsec_epn(rx_sa, &ctx_rx_sa->key, &ctx_rx_sa->next_pn_halves, + ctx_rx_sa->ssci); err = mlx5_create_encryption_key(mdev, ctx->sa.key, ctx->secy->key_len, MLX5_ACCEL_OBJ_MACSEC_KEY, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index cff5f2e29e1e..abcc614b6191 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -4084,6 +4084,9 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, struct mlx5e_vlan_table *vlan; struct mlx5e_params *params; + if (!netif_device_present(netdev)) + return features; + vlan = mlx5e_fs_get_vlan(priv->fs); mutex_lock(&priv->state_lock); params = &priv->channels.params; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 75b9e1528fd2..7d90e5b72854 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -191,7 +191,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep) if (err) { netdev_warn(priv->netdev, "vport %d error %d reading stats\n", rep->vport, err); - return; + goto out; } #define MLX5_GET_CTR(p, x) \ @@ -241,6 +241,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(vport_rep) rep_stats->tx_vport_rdma_multicast_bytes = MLX5_GET_CTR(out, received_ib_multicast.octets); +out: kvfree(out); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index c8820ab22169..3df455f6b168 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -2419,7 +2419,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, priv = mlx5i_epriv(netdev); tstamp = &priv->tstamp; - stats = rq->stats; + stats = &priv->channel_stats[rq->ix]->rq; flags_rqpn = be32_to_cpu(cqe->flags_rqpn); g = (flags_rqpn >> 28) & 3; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9af2aa2922f5..243d5d7750be 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -166,6 +166,7 @@ struct mlx5_fs_chains *mlx5e_nic_chains(struct mlx5e_tc_table *tc) * it's different than the ht->mutex here. */ static struct lock_class_key tc_ht_lock_key; +static struct lock_class_key tc_ht_wq_key; static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow); static void free_flow_post_acts(struct mlx5e_tc_flow *flow); @@ -1301,7 +1302,6 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); - mlx5e_mod_hdr_dealloc(&parse_attr->mod_hdr_acts); if (err) return err; } @@ -1359,8 +1359,10 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, } mutex_unlock(&tc->t_lock); - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) + if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { + mlx5e_mod_hdr_dealloc(&attr->parse_attr->mod_hdr_acts); mlx5e_detach_mod_hdr(priv, flow); + } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) mlx5_fc_destroy(priv->mdev, attr->counter); @@ -5181,6 +5183,7 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) return err; lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key); + lockdep_init_map(&tc->ht.run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0); mapping_id = mlx5_query_nic_system_image_guid(dev); @@ -5287,6 +5290,7 @@ int mlx5e_tc_ht_init(struct rhashtable *tc_ht) return err; lockdep_set_class(&tc_ht->mutex, &tc_ht_lock_key); + lockdep_init_map(&tc_ht->run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c index 4f8a24d84a86..75015d370922 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c @@ -22,15 +22,13 @@ struct mlx5_esw_rate_group { }; static int esw_qos_tsar_config(struct mlx5_core_dev *dev, u32 *sched_ctx, - u32 parent_ix, u32 tsar_ix, - u32 max_rate, u32 bw_share) + u32 tsar_ix, u32 max_rate, u32 bw_share) { u32 bitmask = 0; if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) return -EOPNOTSUPP; - MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_ix); MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate); MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW; @@ -51,7 +49,7 @@ static int esw_qos_group_config(struct mlx5_eswitch *esw, struct mlx5_esw_rate_g int err; err = esw_qos_tsar_config(dev, sched_ctx, - esw->qos.root_tsar_ix, group->tsar_ix, + group->tsar_ix, max_rate, bw_share); if (err) NL_SET_ERR_MSG_MOD(extack, "E-Switch modify group TSAR element failed"); @@ -67,23 +65,13 @@ static int esw_qos_vport_config(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) { u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; - struct mlx5_esw_rate_group *group = vport->qos.group; struct mlx5_core_dev *dev = esw->dev; - u32 parent_tsar_ix; - void *vport_elem; int err; if (!vport->qos.enabled) return -EIO; - parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix; - MLX5_SET(scheduling_context, sched_ctx, element_type, - SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT); - vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, - element_attributes); - MLX5_SET(vport_element, vport_elem, vport_number, vport->vport); - - err = esw_qos_tsar_config(dev, sched_ctx, parent_tsar_ix, vport->qos.esw_tsar_ix, + err = esw_qos_tsar_config(dev, sched_ctx, vport->qos.esw_tsar_ix, max_rate, bw_share); if (err) { esw_warn(esw->dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 0dfd5742c6fe..9daf55e90367 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1464,6 +1464,7 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) mlx5_lag_disable_change(esw->dev); down_write(&esw->mode_lock); mlx5_eswitch_disable_locked(esw); + esw->mode = MLX5_ESWITCH_LEGACY; up_write(&esw->mode_lock); mlx5_lag_enable_change(esw->dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index e455b215c708..c981fa77f439 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -143,7 +143,7 @@ mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw, if (mlx5_esw_indir_table_decap_vport(attr)) vport = mlx5_esw_indir_table_decap_vport(attr); - if (attr && !attr->chain && esw_attr->int_port) + if (!attr->chain && esw_attr && esw_attr->int_port) metadata = mlx5e_tc_int_port_get_metadata_for_match(esw_attr->int_port); else @@ -4143,8 +4143,6 @@ int mlx5_devlink_port_fn_migratable_set(struct devlink_port *port, bool enable, } hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); - memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability), - MLX5_UN_SZ_BYTES(hca_cap_union)); MLX5_SET(cmd_hca_cap_2, hca_caps, migratable, 1); err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport->vport, @@ -4236,8 +4234,6 @@ int mlx5_devlink_port_fn_roce_set(struct devlink_port *port, bool enable, } hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability); - memcpy(hca_caps, MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability), - MLX5_UN_SZ_BYTES(hca_cap_union)); MLX5_SET(cmd_hca_cap, hca_caps, roce, enable); err = mlx5_vport_set_other_func_cap(esw->dev, hca_caps, vport_num, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 96417c5feed7..879555ba847d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -677,6 +677,7 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work) mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) { mlx5_core_err(dev, "health works are not permitted at this stage\n"); + mutex_unlock(&dev->intf_state_mutex); return; } mutex_unlock(&dev->intf_state_mutex); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index c247cca154e9..eff92dc0927c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -90,9 +90,21 @@ static void mlx5i_get_ringparam(struct net_device *dev, static int mlx5i_set_channels(struct net_device *dev, struct ethtool_channels *ch) { - struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct mlx5i_priv *ipriv = netdev_priv(dev); + struct mlx5e_priv *epriv = mlx5i_epriv(dev); + + /* rtnl lock protects from race between this ethtool op and sub + * interface ndo_init/uninit. + */ + ASSERT_RTNL(); + if (ipriv->num_sub_interfaces > 0) { + mlx5_core_warn(epriv->mdev, + "can't change number of channels for interfaces with sub interfaces (%u)\n", + ipriv->num_sub_interfaces); + return -EINVAL; + } - return mlx5e_ethtool_set_channels(priv, ch); + return mlx5e_ethtool_set_channels(epriv, ch); } static void mlx5i_get_channels(struct net_device *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 2c73c8445e63..911cf4d23964 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -160,6 +160,44 @@ void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->tx_dropped = sstats->tx_queue_dropped; } +struct net_device *mlx5i_parent_get(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv, *parent_ipriv; + struct net_device *parent_dev; + int parent_ifindex; + + ipriv = priv->ppriv; + + parent_ifindex = netdev->netdev_ops->ndo_get_iflink(netdev); + parent_dev = dev_get_by_index(dev_net(netdev), parent_ifindex); + if (!parent_dev) + return NULL; + + parent_ipriv = netdev_priv(parent_dev); + + ASSERT_RTNL(); + parent_ipriv->num_sub_interfaces++; + + ipriv->parent_dev = parent_dev; + + return parent_dev; +} + +void mlx5i_parent_put(struct net_device *netdev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(netdev); + struct mlx5i_priv *ipriv, *parent_ipriv; + + ipriv = priv->ppriv; + parent_ipriv = netdev_priv(ipriv->parent_dev); + + ASSERT_RTNL(); + parent_ipriv->num_sub_interfaces--; + + dev_put(ipriv->parent_dev); +} + int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index 99d46fda9f82..f3f2af972020 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -54,9 +54,11 @@ struct mlx5i_priv { struct rdma_netdev rn; /* keep this first */ u32 qpn; bool sub_interface; + u32 num_sub_interfaces; u32 qkey; u16 pkey_index; struct mlx5i_pkey_qpn_ht *qpn_htbl; + struct net_device *parent_dev; char *mlx5e_priv[]; }; @@ -117,5 +119,9 @@ void mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_av *av, u32 dqpn, u32 dqkey, bool xmit_more); void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); +/* Reference management for child to parent interfaces. */ +struct net_device *mlx5i_parent_get(struct net_device *netdev); +void mlx5i_parent_put(struct net_device *netdev); + #endif /* CONFIG_MLX5_CORE_IPOIB */ #endif /* __MLX5E_IPOB_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 4d9c9e49645c..03e681297937 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -158,21 +158,28 @@ static int mlx5i_pkey_dev_init(struct net_device *dev) struct mlx5e_priv *priv = mlx5i_epriv(dev); struct mlx5i_priv *ipriv, *parent_ipriv; struct net_device *parent_dev; - int parent_ifindex; ipriv = priv->ppriv; - /* Get QPN to netdevice hash table from parent */ - parent_ifindex = dev->netdev_ops->ndo_get_iflink(dev); - parent_dev = dev_get_by_index(dev_net(dev), parent_ifindex); + /* Link to parent */ + parent_dev = mlx5i_parent_get(dev); if (!parent_dev) { mlx5_core_warn(priv->mdev, "failed to get parent device\n"); return -EINVAL; } + if (dev->num_rx_queues < parent_dev->real_num_rx_queues) { + mlx5_core_warn(priv->mdev, + "failed to create child device with rx queues [%d] less than parent's [%d]\n", + dev->num_rx_queues, + parent_dev->real_num_rx_queues); + mlx5i_parent_put(dev); + return -EINVAL; + } + + /* Get QPN to netdevice hash table from parent */ parent_ipriv = netdev_priv(parent_dev); ipriv->qpn_htbl = parent_ipriv->qpn_htbl; - dev_put(parent_dev); return mlx5i_dev_init(dev); } @@ -184,6 +191,7 @@ static int mlx5i_pkey_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void mlx5i_pkey_dev_cleanup(struct net_device *netdev) { + mlx5i_parent_put(netdev); return mlx5i_dev_cleanup(netdev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 69cfe60c558a..69318b143268 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -681,7 +681,7 @@ static int mlx5_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin, static const struct ptp_clock_info mlx5_ptp_clock_info = { .owner = THIS_MODULE, .name = "mlx5_ptp", - .max_adj = 100000000, + .max_adj = 50000000, .n_alarm = 0, .n_ext_ts = 0, .n_per_out = 0, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index df134f6d32dc..3d5f2a4b1fed 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -2098,7 +2098,7 @@ static void mlx5_core_verify_params(void) } } -static int __init init(void) +static int __init mlx5_init(void) { int err; @@ -2133,7 +2133,7 @@ err_debug: return err; } -static void __exit cleanup(void) +static void __exit mlx5_cleanup(void) { mlx5e_cleanup(); mlx5_sf_driver_unregister(); @@ -2141,5 +2141,5 @@ static void __exit cleanup(void) mlx5_unregister_debugfs(); } -module_init(init); -module_exit(cleanup); +module_init(mlx5_init); +module_exit(mlx5_cleanup); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/qos.c index 0777be24a307..8bce730b5c5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qos.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qos.c @@ -62,13 +62,12 @@ int mlx5_qos_create_root_node(struct mlx5_core_dev *mdev, u32 *id) return mlx5_qos_create_inner_node(mdev, MLX5_QOS_DEFAULT_DWRR_UID, 0, 0, id); } -int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id, +int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 bw_share, u32 max_avg_bw, u32 id) { u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; u32 bitmask = 0; - MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id); MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share); MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_avg_bw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/qos.h index 125e4e47e6f7..624ce822b7f5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qos.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/qos.h @@ -23,7 +23,7 @@ int mlx5_qos_create_leaf_node(struct mlx5_core_dev *mdev, u32 parent_id, int mlx5_qos_create_inner_node(struct mlx5_core_dev *mdev, u32 parent_id, u32 bw_share, u32 max_avg_bw, u32 *id); int mlx5_qos_create_root_node(struct mlx5_core_dev *mdev, u32 *id); -int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 parent_id, u32 bw_share, +int mlx5_qos_update_node(struct mlx5_core_dev *mdev, u32 bw_share, u32 max_avg_bw, u32 id); int mlx5_qos_destroy_node(struct mlx5_core_dev *mdev, u32 id); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c index 74cbe53ee9db..b851141e03de 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -3,7 +3,12 @@ #include "dr_types.h" +#if defined(CONFIG_FRAME_WARN) && (CONFIG_FRAME_WARN < 2048) +/* don't try to optimize STE allocation if the stack is too constaraining */ +#define DR_RULE_MAX_STES_OPTIMIZED 0 +#else #define DR_RULE_MAX_STES_OPTIMIZED 5 +#endif #define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES) static int dr_rule_append_to_miss_list(struct mlx5dr_domain *dmn, @@ -1218,10 +1223,7 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule, mlx5dr_domain_nic_unlock(nic_dmn); - if (unlikely(!hw_ste_arr_is_opt)) - kfree(hw_ste_arr); - - return 0; + goto out; free_rule: dr_rule_clean_rule_members(rule, nic_rule); @@ -1238,6 +1240,7 @@ remove_from_nic_tbl: free_hw_ste: mlx5dr_domain_nic_unlock(nic_dmn); +out: if (unlikely(!hw_ste_arr_is_opt)) kfree(hw_ste_arr); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index c22c3ac4e2a1..09e32778b012 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2951,7 +2951,7 @@ struct mlxsw_sp_nexthop_group_info { gateway:1, /* routes using the group use a gateway */ is_resilient:1; struct list_head list; /* member in nh_res_grp_list */ - struct mlxsw_sp_nexthop nexthops[0]; + struct mlxsw_sp_nexthop nexthops[]; #define nh_rif nexthops[0].rif }; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index 5314c064ceae..55b484b10562 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -608,12 +608,12 @@ allocate_new: lan966x_fdma_rx_reload(rx); } - if (counter < weight && napi_complete_done(napi, counter)) - lan_wr(0xff, lan966x, FDMA_INTR_DB_ENA); - if (redirect) xdp_do_flush(); + if (counter < weight && napi_complete_done(napi, counter)) + lan_wr(0xff, lan966x, FDMA_INTR_DB_ENA); + return counter; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index cadde20505ba..580c91d24a52 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -1043,11 +1043,6 @@ static int lan966x_probe(struct platform_device *pdev) lan966x->base_mac[5] &= 0xf0; } - ports = device_get_named_child_node(&pdev->dev, "ethernet-ports"); - if (!ports) - return dev_err_probe(&pdev->dev, -ENODEV, - "no ethernet-ports child found\n"); - err = lan966x_create_targets(pdev, lan966x); if (err) return dev_err_probe(&pdev->dev, err, @@ -1125,6 +1120,11 @@ static int lan966x_probe(struct platform_device *pdev) } } + ports = device_get_named_child_node(&pdev->dev, "ethernet-ports"); + if (!ports) + return dev_err_probe(&pdev->dev, -ENODEV, + "no ethernet-ports child found\n"); + /* init switch */ lan966x_init(lan966x); lan966x_stats_init(lan966x); @@ -1162,6 +1162,8 @@ static int lan966x_probe(struct platform_device *pdev) goto cleanup_ports; } + fwnode_handle_put(ports); + lan966x_mdb_init(lan966x); err = lan966x_fdb_init(lan966x); if (err) @@ -1191,6 +1193,7 @@ cleanup_fdb: lan966x_fdb_deinit(lan966x); cleanup_ports: + fwnode_handle_put(ports); fwnode_handle_put(portnp); lan966x_cleanup_ports(lan966x); diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c index f9ebfaafbebc..a8348437dd87 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ptp.c @@ -1073,6 +1073,9 @@ void lan966x_ptp_deinit(struct lan966x *lan966x) struct lan966x_port *port; int i; + if (!lan966x->ptp) + return; + for (i = 0; i < lan966x->num_phys_ports; i++) { port = lan966x->ports[i]; if (!port) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c index d8dc9fbb81e1..a54c0426a35f 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vcap_impl.c @@ -95,10 +95,7 @@ lan966x_vcap_is2_get_port_keysets(struct net_device *dev, int lookup, bool found = false; u32 val; - /* Check if the port keyset selection is enabled */ val = lan_rd(lan966x, ANA_VCAP_S2_CFG(port->chip_port)); - if (!ANA_VCAP_S2_CFG_ENA_GET(val)) - return -ENOENT; /* Collect all keysets for the port in a list */ if (l3_proto == ETH_P_ALL) diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index e708c2d04983..b144f2237748 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -1259,13 +1259,20 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) gic->handler = NULL; gic->arg = NULL; + if (!i) + snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_hwc@pci:%s", + pci_name(pdev)); + else + snprintf(gic->name, MANA_IRQ_NAME_SZ, "mana_q%d@pci:%s", + i - 1, pci_name(pdev)); + irq = pci_irq_vector(pdev, i); if (irq < 0) { err = irq; goto free_mask; } - err = request_irq(irq, mana_gd_intr, 0, "mana_intr", gic); + err = request_irq(irq, mana_gd_intr, 0, gic->name, gic); if (err) goto free_mask; irq_set_affinity_and_hint(irq, req_mask); diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index a8678d5612ee..060a77f2265d 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -460,6 +460,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, sizeof(struct nfp_tun_neigh_v4); unsigned long cookie = (unsigned long)neigh; struct nfp_flower_priv *priv = app->priv; + struct nfp_tun_neigh_lag lag_info; struct nfp_neigh_entry *nn_entry; u32 port_id; u8 mtype; @@ -468,6 +469,11 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, if (!port_id) return; + if ((port_id & NFP_FL_LAG_OUT) == NFP_FL_LAG_OUT) { + memset(&lag_info, 0, sizeof(struct nfp_tun_neigh_lag)); + nfp_flower_lag_get_info_from_netdev(app, netdev, &lag_info); + } + spin_lock_bh(&priv->predt_lock); nn_entry = rhashtable_lookup_fast(&priv->neigh_table, &cookie, neigh_table_params); @@ -515,7 +521,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app, neigh_ha_snapshot(common->dst_addr, neigh, netdev); if ((port_id & NFP_FL_LAG_OUT) == NFP_FL_LAG_OUT) - nfp_flower_lag_get_info_from_netdev(app, netdev, lag); + memcpy(lag, &lag_info, sizeof(struct nfp_tun_neigh_lag)); common->port_id = cpu_to_be32(port_id); if (rhashtable_insert_fast(&priv->neigh_table, diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 7c2af482192d..cb1746bc0e0c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1438,6 +1438,10 @@ int qede_poll(struct napi_struct *napi, int budget) rx_work_done = (likely(fp->type & QEDE_FASTPATH_RX) && qede_has_rx_work(fp->rxq)) ? qede_rx_int(fp, budget) : 0; + + if (fp->xdp_xmit & QEDE_XDP_REDIRECT) + xdp_do_flush(); + /* Handle case where we are called by netpoll with a budget of 0 */ if (rx_work_done < budget || !budget) { if (!qede_poll_is_more_work(fp)) { @@ -1457,9 +1461,6 @@ int qede_poll(struct napi_struct *napi, int budget) qede_update_tx_producer(fp->xdp_tx); } - if (fp->xdp_xmit & QEDE_XDP_REDIRECT) - xdp_do_flush_map(); - return rx_work_done; } diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 24592d972523..dadd61bccfe7 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -1996,10 +1996,7 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii) /* 8168F family. */ { 0x7c8, 0x488, RTL_GIGA_MAC_VER_38 }, - /* It seems this chip version never made it to - * the wild. Let's disable detection. - * { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 }, - */ + { 0x7cf, 0x481, RTL_GIGA_MAC_VER_36 }, { 0x7cf, 0x480, RTL_GIGA_MAC_VER_35 }, /* 8168E family. */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index b4e0fc7f65bd..0f54849a3823 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1101,14 +1101,14 @@ static void ravb_error_interrupt(struct net_device *ndev) ravb_write(ndev, ~(EIS_QFS | EIS_RESERVED), EIS); if (eis & EIS_QFS) { ris2 = ravb_read(ndev, RIS2); - ravb_write(ndev, ~(RIS2_QFF0 | RIS2_RFFF | RIS2_RESERVED), + ravb_write(ndev, ~(RIS2_QFF0 | RIS2_QFF1 | RIS2_RFFF | RIS2_RESERVED), RIS2); /* Receive Descriptor Empty int */ if (ris2 & RIS2_QFF0) priv->stats[RAVB_BE].rx_over_errors++; - /* Receive Descriptor Empty int */ + /* Receive Descriptor Empty int */ if (ris2 & RIS2_QFF1) priv->stats[RAVB_NC].rx_over_errors++; @@ -2973,6 +2973,9 @@ static int __maybe_unused ravb_suspend(struct device *dev) else ret = ravb_close(ndev); + if (priv->info->ccc_gac) + ravb_ptp_stop(ndev); + return ret; } @@ -3011,6 +3014,9 @@ static int __maybe_unused ravb_resume(struct device *dev) /* Restore descriptor base address table */ ravb_write(ndev, priv->desc_bat_dma, DBAT); + if (priv->info->ccc_gac) + ravb_ptp_init(ndev, priv->pdev); + if (netif_running(ndev)) { if (priv->wol_enabled) { ret = ravb_wol_restore(ndev); diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 6441892636db..2370c7797a0a 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -1074,8 +1074,11 @@ static struct device_node *rswitch_get_port_node(struct rswitch_device *rdev) port = NULL; goto out; } - if (index == rdev->etha->index) + if (index == rdev->etha->index) { + if (!of_device_is_available(port)) + port = NULL; break; + } } out: @@ -1106,7 +1109,7 @@ static int rswitch_etha_get_params(struct rswitch_device *rdev) port = rswitch_get_port_node(rdev); if (!port) - return -ENODEV; + return 0; /* ignored */ err = of_get_phy_mode(port, &rdev->etha->phy_interface); of_node_put(port); @@ -1324,13 +1327,13 @@ static int rswitch_ether_port_init_all(struct rswitch_private *priv) { int i, err; - for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + rswitch_for_each_enabled_port(priv, i) { err = rswitch_ether_port_init_one(priv->rdev[i]); if (err) goto err_init_one; } - for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + rswitch_for_each_enabled_port(priv, i) { err = rswitch_serdes_init(priv->rdev[i]); if (err) goto err_serdes; @@ -1339,12 +1342,12 @@ static int rswitch_ether_port_init_all(struct rswitch_private *priv) return 0; err_serdes: - for (i--; i >= 0; i--) + rswitch_for_each_enabled_port_continue_reverse(priv, i) rswitch_serdes_deinit(priv->rdev[i]); i = RSWITCH_NUM_PORTS; err_init_one: - for (i--; i >= 0; i--) + rswitch_for_each_enabled_port_continue_reverse(priv, i) rswitch_ether_port_deinit_one(priv->rdev[i]); return err; @@ -1608,6 +1611,7 @@ static int rswitch_device_alloc(struct rswitch_private *priv, int index) netif_napi_add(ndev, &rdev->napi, rswitch_poll); port = rswitch_get_port_node(rdev); + rdev->disabled = !port; err = of_get_ethdev_address(port, ndev); of_node_put(port); if (err) { @@ -1707,16 +1711,16 @@ static int rswitch_init(struct rswitch_private *priv) if (err) goto err_ether_port_init_all; - for (i = 0; i < RSWITCH_NUM_PORTS; i++) { + rswitch_for_each_enabled_port(priv, i) { err = register_netdev(priv->rdev[i]->ndev); if (err) { - for (i--; i >= 0; i--) + rswitch_for_each_enabled_port_continue_reverse(priv, i) unregister_netdev(priv->rdev[i]->ndev); goto err_register_netdev; } } - for (i = 0; i < RSWITCH_NUM_PORTS; i++) + rswitch_for_each_enabled_port(priv, i) netdev_info(priv->rdev[i]->ndev, "MAC address %pM\n", priv->rdev[i]->ndev->dev_addr); diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index edbdd1b98d3d..49efb0f31c77 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -13,6 +13,17 @@ #define RSWITCH_MAX_NUM_QUEUES 128 #define RSWITCH_NUM_PORTS 3 +#define rswitch_for_each_enabled_port(priv, i) \ + for (i = 0; i < RSWITCH_NUM_PORTS; i++) \ + if (priv->rdev[i]->disabled) \ + continue; \ + else + +#define rswitch_for_each_enabled_port_continue_reverse(priv, i) \ + for (i--; i >= 0; i--) \ + if (priv->rdev[i]->disabled) \ + continue; \ + else #define TX_RING_SIZE 1024 #define RX_RING_SIZE 1024 @@ -938,6 +949,7 @@ struct rswitch_device { struct rswitch_gwca_queue *tx_queue; struct rswitch_gwca_queue *rx_queue; u8 ts_tag; + bool disabled; int port; struct rswitch_etha *etha; diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 0556542d7a6b..3a86f1213a05 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1003,8 +1003,11 @@ static int efx_pci_probe_post_io(struct efx_nic *efx) /* Determine netdevice features */ net_dev->features |= (efx->type->offload_features | NETIF_F_SG | NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_RXALL); - if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) + if (efx->type->offload_features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) { net_dev->features |= NETIF_F_TSO6; + if (efx_has_cap(efx, TX_TSO_V2_ENCAP)) + net_dev->hw_enc_features |= NETIF_F_TSO6; + } /* Check whether device supports TSO */ if (!efx->type->tso_versions || !efx->type->tso_versions(efx)) net_dev->features &= ~NETIF_F_ALL_TSO; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index d42e1afb6521..2f7d8e4561d9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -90,7 +90,6 @@ struct mediatek_dwmac_plat_data { struct mediatek_dwmac_variant { int (*dwmac_set_phy_interface)(struct mediatek_dwmac_plat_data *plat); int (*dwmac_set_delay)(struct mediatek_dwmac_plat_data *plat); - void (*dwmac_fix_mac_speed)(void *priv, unsigned int speed); /* clock ids to be requested */ const char * const *clk_list; @@ -443,32 +442,9 @@ static int mt8195_set_delay(struct mediatek_dwmac_plat_data *plat) return 0; } -static void mt8195_fix_mac_speed(void *priv, unsigned int speed) -{ - struct mediatek_dwmac_plat_data *priv_plat = priv; - - if ((phy_interface_mode_is_rgmii(priv_plat->phy_mode))) { - /* prefer 2ns fixed delay which is controlled by TXC_PHASE_CTRL, - * when link speed is 1Gbps with RGMII interface, - * Fall back to delay macro circuit for 10/100Mbps link speed. - */ - if (speed == SPEED_1000) - regmap_update_bits(priv_plat->peri_regmap, - MT8195_PERI_ETH_CTRL0, - MT8195_RGMII_TXC_PHASE_CTRL | - MT8195_DLY_GTXC_ENABLE | - MT8195_DLY_GTXC_INV | - MT8195_DLY_GTXC_STAGES, - MT8195_RGMII_TXC_PHASE_CTRL); - else - mt8195_set_delay(priv_plat); - } -} - static const struct mediatek_dwmac_variant mt8195_gmac_variant = { .dwmac_set_phy_interface = mt8195_set_interface, .dwmac_set_delay = mt8195_set_delay, - .dwmac_fix_mac_speed = mt8195_fix_mac_speed, .clk_list = mt8195_dwmac_clk_l, .num_clks = ARRAY_SIZE(mt8195_dwmac_clk_l), .dma_bit_mask = 35, @@ -619,8 +595,6 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, plat->bsp_priv = priv_plat; plat->init = mediatek_dwmac_init; plat->clks_config = mediatek_dwmac_clks_config; - if (priv_plat->variant->dwmac_fix_mac_speed) - plat->fix_mac_speed = priv_plat->variant->dwmac_fix_mac_speed; plat->safety_feat_cfg = devm_kzalloc(&pdev->dev, sizeof(*plat->safety_feat_cfg), diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index 835caa15d55f..732774645c1a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -560,6 +560,8 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->has_gmac4 = 1; plat_dat->pmt = 1; plat_dat->tso_en = of_property_read_bool(np, "snps,tso"); + if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) + plat_dat->rx_clk_runs_in_lpi = 1; ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index 9c2d40f853ed..413f66017219 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -186,11 +186,25 @@ static void dwmac5_handle_dma_err(struct net_device *ndev, int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp, struct stmmac_safety_feature_cfg *safety_feat_cfg) { + struct stmmac_safety_feature_cfg all_safety_feats = { + .tsoee = 1, + .mrxpee = 1, + .mestee = 1, + .mrxee = 1, + .mtxee = 1, + .epsi = 1, + .edpp = 1, + .prtyen = 1, + .tmouten = 1, + }; u32 value; if (!asp) return -EINVAL; + if (!safety_feat_cfg) + safety_feat_cfg = &all_safety_feats; + /* 1. Enable Safety Features */ value = readl(ioaddr + MTL_ECC_CONTROL); value |= MEEAO; /* MTL ECC Error Addr Status Override */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index f453b0d09366..35c8dd92d369 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -551,16 +551,16 @@ static void stmmac_get_per_qstats(struct stmmac_priv *priv, u64 *data) p = (char *)priv + offsetof(struct stmmac_priv, xstats.txq_stats[q].tx_pkt_n); for (stat = 0; stat < STMMAC_TXQ_STATS; stat++) { - *data++ = (*(u64 *)p); - p += sizeof(u64 *); + *data++ = (*(unsigned long *)p); + p += sizeof(unsigned long); } } for (q = 0; q < rx_cnt; q++) { p = (char *)priv + offsetof(struct stmmac_priv, xstats.rxq_stats[q].rx_pkt_n); for (stat = 0; stat < STMMAC_RXQ_STATS; stat++) { - *data++ = (*(u64 *)p); - p += sizeof(u64 *); + *data++ = (*(unsigned long *)p); + p += sizeof(unsigned long); } } } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c6951c976f5d..1a5b8dab5e9b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1080,7 +1080,8 @@ static void stmmac_mac_link_up(struct phylink_config *config, stmmac_mac_set(priv, priv->ioaddr, true); if (phy && priv->dma_cap.eee) { - priv->eee_active = phy_init_eee(phy, 1) >= 0; + priv->eee_active = + phy_init_eee(phy, !priv->plat->rx_clk_runs_in_lpi) >= 0; priv->eee_enabled = stmmac_eee_init(priv); priv->tx_lpi_enabled = priv->eee_enabled; stmmac_set_eee_pls(priv, priv->hw, true); @@ -1150,6 +1151,11 @@ static int stmmac_init_phy(struct net_device *dev) int addr = priv->plat->phy_addr; struct phy_device *phydev; + if (addr < 0) { + netdev_err(priv->dev, "no phy found\n"); + return -ENODEV; + } + phydev = mdiobus_get_phy(priv->mii, addr); if (!phydev) { netdev_err(priv->dev, "no phy at addr %d\n", addr); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index fc06ddeac0d5..b4388ca8d211 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -210,7 +210,10 @@ static int stmmac_enable(struct ptp_clock_info *ptp, } writel(acr_value, ptpaddr + PTP_ACR); mutex_unlock(&priv->aux_ts_lock); - ret = 0; + /* wait for auxts fifo clear to finish */ + ret = readl_poll_timeout(ptpaddr + PTP_ACR, acr_value, + !(acr_value & PTP_ACR_ATSFC), + 10, 10000); break; default: diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 9352dad58996..e02d1e3ef672 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -987,9 +987,6 @@ static void netvsc_copy_to_send_buf(struct netvsc_device *net_device, void netvsc_dma_unmap(struct hv_device *hv_dev, struct hv_netvsc_packet *packet) { - u32 page_count = packet->cp_partial ? - packet->page_buf_cnt - packet->rmsg_pgcnt : - packet->page_buf_cnt; int i; if (!hv_is_isolation_supported()) @@ -998,7 +995,7 @@ void netvsc_dma_unmap(struct hv_device *hv_dev, if (!packet->dma_range) return; - for (i = 0; i < page_count; i++) + for (i = 0; i < packet->page_buf_cnt; i++) dma_unmap_single(&hv_dev->device, packet->dma_range[i].dma, packet->dma_range[i].mapping_size, DMA_TO_DEVICE); @@ -1028,9 +1025,7 @@ static int netvsc_dma_map(struct hv_device *hv_dev, struct hv_netvsc_packet *packet, struct hv_page_buffer *pb) { - u32 page_count = packet->cp_partial ? - packet->page_buf_cnt - packet->rmsg_pgcnt : - packet->page_buf_cnt; + u32 page_count = packet->page_buf_cnt; dma_addr_t dma; int i; diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c index 7552c400961e..b83390c48615 100644 --- a/drivers/net/ipa/data/ipa_data-v4.7.c +++ b/drivers/net/ipa/data/ipa_data-v4.7.c @@ -357,7 +357,7 @@ static const struct ipa_mem ipa_mem_local_data[] = { static const struct ipa_mem_data ipa_mem_data = { .local_count = ARRAY_SIZE(ipa_mem_local_data), .local = ipa_mem_local_data, - .imem_addr = 0x146a9000, + .imem_addr = 0x146a8000, .imem_size = 0x00002000, .smem_id = 497, .smem_size = 0x00009000, diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c index d458a35839cc..c1b3977e1ae4 100644 --- a/drivers/net/ipa/ipa_interrupt.c +++ b/drivers/net/ipa/ipa_interrupt.c @@ -127,6 +127,16 @@ out_power_put: return IRQ_HANDLED; } +void ipa_interrupt_irq_disable(struct ipa *ipa) +{ + disable_irq(ipa->interrupt->irq); +} + +void ipa_interrupt_irq_enable(struct ipa *ipa) +{ + enable_irq(ipa->interrupt->irq); +} + /* Common function used to enable/disable TX_SUSPEND for an endpoint */ static void ipa_interrupt_suspend_control(struct ipa_interrupt *interrupt, u32 endpoint_id, bool enable) diff --git a/drivers/net/ipa/ipa_interrupt.h b/drivers/net/ipa/ipa_interrupt.h index f31fd9965fdc..8a1bd5b89393 100644 --- a/drivers/net/ipa/ipa_interrupt.h +++ b/drivers/net/ipa/ipa_interrupt.h @@ -86,6 +86,22 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt); void ipa_interrupt_simulate_suspend(struct ipa_interrupt *interrupt); /** + * ipa_interrupt_irq_enable() - Enable IPA interrupts + * @ipa: IPA pointer + * + * This enables the IPA interrupt line + */ +void ipa_interrupt_irq_enable(struct ipa *ipa); + +/** + * ipa_interrupt_irq_disable() - Disable IPA interrupts + * @ipa: IPA pointer + * + * This disables the IPA interrupt line + */ +void ipa_interrupt_irq_disable(struct ipa *ipa); + +/** * ipa_interrupt_config() - Configure the IPA interrupt framework * @ipa: IPA pointer * diff --git a/drivers/net/ipa/ipa_power.c b/drivers/net/ipa/ipa_power.c index 8420f93128a2..8057be8cda80 100644 --- a/drivers/net/ipa/ipa_power.c +++ b/drivers/net/ipa/ipa_power.c @@ -181,6 +181,17 @@ static int ipa_suspend(struct device *dev) __set_bit(IPA_POWER_FLAG_SYSTEM, ipa->power->flags); + /* Increment the disable depth to ensure that the IRQ won't + * be re-enabled until the matching _enable call in + * ipa_resume(). We do this to ensure that the interrupt + * handler won't run whilst PM runtime is disabled. + * + * Note that disabling the IRQ is NOT the same as disabling + * irq wake. If wakeup is enabled for the IPA then the IRQ + * will still cause the system to wake up, see irq_set_irq_wake(). + */ + ipa_interrupt_irq_disable(ipa); + return pm_runtime_force_suspend(dev); } @@ -193,6 +204,12 @@ static int ipa_resume(struct device *dev) __clear_bit(IPA_POWER_FLAG_SYSTEM, ipa->power->flags); + /* Now that PM runtime is enabled again it's safe + * to turn the IRQ back on and process any data + * that was received during suspend. + */ + ipa_interrupt_irq_enable(ipa); + return ret; } diff --git a/drivers/net/mdio/mdio-mux-meson-g12a.c b/drivers/net/mdio/mdio-mux-meson-g12a.c index 4a2e94faf57e..c4542ecf5623 100644 --- a/drivers/net/mdio/mdio-mux-meson-g12a.c +++ b/drivers/net/mdio/mdio-mux-meson-g12a.c @@ -4,6 +4,7 @@ */ #include <linux/bitfield.h> +#include <linux/delay.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/device.h> @@ -150,6 +151,7 @@ static const struct clk_ops g12a_ephy_pll_ops = { static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv) { + u32 value; int ret; /* Enable the phy clock */ @@ -163,18 +165,25 @@ static int g12a_enable_internal_mdio(struct g12a_mdio_mux *priv) /* Initialize ephy control */ writel(EPHY_G12A_ID, priv->regs + ETH_PHY_CNTL0); - writel(FIELD_PREP(PHY_CNTL1_ST_MODE, 3) | - FIELD_PREP(PHY_CNTL1_ST_PHYADD, EPHY_DFLT_ADD) | - FIELD_PREP(PHY_CNTL1_MII_MODE, EPHY_MODE_RMII) | - PHY_CNTL1_CLK_EN | - PHY_CNTL1_CLKFREQ | - PHY_CNTL1_PHY_ENB, - priv->regs + ETH_PHY_CNTL1); + + /* Make sure we get a 0 -> 1 transition on the enable bit */ + value = FIELD_PREP(PHY_CNTL1_ST_MODE, 3) | + FIELD_PREP(PHY_CNTL1_ST_PHYADD, EPHY_DFLT_ADD) | + FIELD_PREP(PHY_CNTL1_MII_MODE, EPHY_MODE_RMII) | + PHY_CNTL1_CLK_EN | + PHY_CNTL1_CLKFREQ; + writel(value, priv->regs + ETH_PHY_CNTL1); writel(PHY_CNTL2_USE_INTERNAL | PHY_CNTL2_SMI_SRC_MAC | PHY_CNTL2_RX_CLK_EPHY, priv->regs + ETH_PHY_CNTL2); + value |= PHY_CNTL1_PHY_ENB; + writel(value, priv->regs + ETH_PHY_CNTL1); + + /* The phy needs a bit of time to power up */ + mdelay(10); + return 0; } diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index a6f05e35d91f..b7cb71817780 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -233,7 +233,8 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_ENERGY_DET_INT_EN | DP83822_LINK_QUAL_INT_EN); - if (!dp83822->fx_enabled) + /* Private data pointer is NULL on DP83825/26 */ + if (!dp83822 || !dp83822->fx_enabled) misr_status |= DP83822_ANEG_COMPLETE_INT_EN | DP83822_DUP_MODE_CHANGE_INT_EN | DP83822_SPEED_CHANGED_INT_EN; @@ -253,7 +254,8 @@ static int dp83822_config_intr(struct phy_device *phydev) DP83822_PAGE_RX_INT_EN | DP83822_EEE_ERROR_CHANGE_INT_EN); - if (!dp83822->fx_enabled) + /* Private data pointer is NULL on DP83825/26 */ + if (!dp83822 || !dp83822->fx_enabled) misr_status |= DP83822_ANEG_ERR_INT_EN | DP83822_WOL_PKT_INT_EN; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 1cd604cd1fa1..16e021b477f0 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -108,7 +108,12 @@ EXPORT_SYMBOL(mdiobus_unregister_device); struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr) { - struct mdio_device *mdiodev = bus->mdio_map[addr]; + struct mdio_device *mdiodev; + + if (addr < 0 || addr >= ARRAY_SIZE(bus->mdio_map)) + return NULL; + + mdiodev = bus->mdio_map[addr]; if (!mdiodev) return NULL; diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c index c49062ad72c6..5e41658b1e2f 100644 --- a/drivers/net/phy/meson-gxl.c +++ b/drivers/net/phy/meson-gxl.c @@ -271,6 +271,8 @@ static struct phy_driver meson_gxl_phy[] = { .handle_interrupt = meson_gxl_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, + .read_mmd = genphy_read_mmd_unsupported, + .write_mmd = genphy_write_mmd_unsupported, }, }; diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 716870a4499c..607aa786c8cb 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1517,7 +1517,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, * another mac interface, so we should create a device link between * phy dev and mac dev. */ - if (phydev->mdio.bus->parent && dev->dev.parent != phydev->mdio.bus->parent) + if (dev && phydev->mdio.bus->parent && dev->dev.parent != phydev->mdio.bus->parent) phydev->devlink = device_link_add(dev->dev.parent, &phydev->mdio.dev, DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index fcd43d62d86b..d10606f257c4 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1044,7 +1044,6 @@ static int team_port_enter(struct team *team, struct team_port *port) goto err_port_enter; } } - port->dev->priv_flags |= IFF_NO_ADDRCONF; return 0; @@ -1058,7 +1057,6 @@ static void team_port_leave(struct team *team, struct team_port *port) { if (team->ops.port_leave) team->ops.port_leave(team, port); - port->dev->priv_flags &= ~IFF_NO_ADDRCONF; dev_put(team->dev); } diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 8911cd2ed534..c140edb4b648 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -1008,6 +1008,12 @@ static const struct usb_device_id products[] = { USB_CDC_PROTO_NONE), .driver_info = (unsigned long)&wwan_info, }, { + /* Cinterion PLS62-W modem by GEMALTO/THALES */ + USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x005b, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, + USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&wwan_info, +}, { /* Cinterion PLS83/PLS63 modem by GEMALTO/THALES */ USB_DEVICE_AND_INTERFACE_INFO(0x1e2d, 0x0069, USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index a481a1d831e2..23da1d9dafd1 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9836,6 +9836,7 @@ static const struct usb_device_id rtl8152_table[] = { REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07ab), REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x07c6), REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927), + REALTEK_USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0c5e), REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101), REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x304f), REALTEK_USB_DEVICE(VENDOR_ID_LENOVO, 0x3054), diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c index 5a53e63d33a6..3164451e1010 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 || len > skb->len) + if (len > ETH_FRAME_LEN || len > skb->len || len < 0) return 0; /* the last packet of current skb */ diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 7723b2a49d8e..61e33e4dd0cd 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1677,13 +1677,13 @@ static int virtnet_poll(struct napi_struct *napi, int budget) received = virtnet_receive(rq, budget, &xdp_xmit); + if (xdp_xmit & VIRTIO_XDP_REDIR) + xdp_do_flush(); + /* Out of packets? */ if (received < budget) virtqueue_napi_complete(napi, rq->vq, received); - if (xdp_xmit & VIRTIO_XDP_REDIR) - xdp_do_flush(); - if (xdp_xmit & VIRTIO_XDP_TX) { sq = virtnet_xdp_get_sq(vi); if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) { @@ -1877,8 +1877,10 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) */ if (sq->vq->num_free < 2+MAX_SKB_FRAGS) { netif_stop_subqueue(dev, qnum); - if (!use_napi && - unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { + if (use_napi) { + if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) + virtqueue_napi_schedule(&sq->napi, sq->vq); + } else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) { /* More just got used, free them then recheck. */ free_old_xmit_skbs(sq, false); if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) { @@ -2156,8 +2158,8 @@ static int virtnet_close(struct net_device *dev) cancel_delayed_work_sync(&vi->refill); for (i = 0; i < vi->max_queue_pairs; i++) { - xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); napi_disable(&vi->rq[i].napi); + xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); virtnet_napi_tx_disable(&vi->sq[i].napi); } diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 22edea6ca4b8..1c53b5546927 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -1243,9 +1243,11 @@ static int ucc_hdlc_probe(struct platform_device *pdev) free_dev: free_netdev(dev); undo_uhdlc_init: - iounmap(utdm->siram); + if (utdm) + iounmap(utdm->siram); unmap_si_regs: - iounmap(utdm->si_regs); + if (utdm) + iounmap(utdm->si_regs); free_utdm: if (uhdlc_priv->tsa) kfree(utdm); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index bff3128c2f26..b115902eb475 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -7937,6 +7937,9 @@ cfg80211_set_channel(struct wiphy *wiphy, struct net_device *dev, struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy); struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg)); + if (chan->flags & IEEE80211_CHAN_DISABLED) + return -EINVAL; + /* set_channel */ chspec = channel_to_chanspec(&cfg->d11inf, chan); if (chspec != INVCHANSPEC) { @@ -7961,7 +7964,7 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev, struct brcmf_if *ifp = netdev_priv(cfg_to_ndev(cfg)); struct brcmf_dump_survey survey = {}; struct ieee80211_supported_band *band; - struct ieee80211_channel *chan; + enum nl80211_band band_id; struct cca_msrmnt_query req; u32 noise; int err; @@ -7974,26 +7977,25 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev, return -EBUSY; } - band = wiphy->bands[NL80211_BAND_2GHZ]; - if (band && idx >= band->n_channels) { - idx -= band->n_channels; - band = NULL; - } + for (band_id = 0; band_id < NUM_NL80211_BANDS; band_id++) { + band = wiphy->bands[band_id]; + if (!band) + continue; + if (idx >= band->n_channels) { + idx -= band->n_channels; + continue; + } - if (!band || idx >= band->n_channels) { - band = wiphy->bands[NL80211_BAND_5GHZ]; - if (idx >= band->n_channels) - return -ENOENT; + info->channel = &band->channels[idx]; + break; } + if (band_id == NUM_NL80211_BANDS) + return -ENOENT; /* Setting current channel to the requested channel */ - chan = &band->channels[idx]; - err = cfg80211_set_channel(wiphy, ndev, chan, NL80211_CHAN_HT20); - if (err) { - info->channel = chan; - info->filled = 0; + info->filled = 0; + if (cfg80211_set_channel(wiphy, ndev, info->channel, NL80211_CHAN_HT20)) return 0; - } /* Disable mpc */ brcmf_set_mpc(ifp, 0); @@ -8028,7 +8030,6 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev, if (err) goto exit; - info->channel = chan; info->noise = noise; info->time = ACS_MSRMNT_DELAY; info->time_busy = ACS_MSRMNT_DELAY - survey.idle; @@ -8040,7 +8041,7 @@ brcmf_cfg80211_dump_survey(struct wiphy *wiphy, struct net_device *ndev, SURVEY_INFO_TIME_TX; brcmf_dbg(INFO, "OBSS dump: channel %d: survey duration %d\n", - ieee80211_frequency_to_channel(chan->center_freq), + ieee80211_frequency_to_channel(info->channel->center_freq), ACS_MSRMNT_DELAY); brcmf_dbg(INFO, "noise(%d) busy(%llu) rx(%llu) tx(%llu)\n", info->noise, info->time_busy, info->time_rx, info->time_tx); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c index a83699de01ec..fdd0c9abc1a1 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/of.c @@ -79,7 +79,8 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type, /* Apple ARM64 platforms have their own idea of board type, passed in * via the device tree. They also have an antenna SKU parameter */ - if (!of_property_read_string(np, "brcm,board-type", &prop)) + err = of_property_read_string(np, "brcm,board-type", &prop); + if (!err) settings->board_type = prop; if (!of_property_read_string(np, "apple,antenna-sku", &prop)) @@ -87,7 +88,7 @@ void brcmf_of_probe(struct device *dev, enum brcmf_bus_type bus_type, /* Set board-type to the first string of the machine compatible prop */ root = of_find_node_by_path("/"); - if (root && !settings->board_type) { + if (root && err) { char *board_type; const char *tmp; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c index ae57a9a3ab05..b67f6d0810b6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pcie.c @@ -1228,7 +1228,7 @@ static int brcmf_pcie_init_ringbuffers(struct brcmf_pciedev_info *devinfo) BRCMF_NROF_H2D_COMMON_MSGRINGS; max_completionrings = BRCMF_NROF_D2H_COMMON_MSGRINGS; } - if (max_flowrings > 256) { + if (max_flowrings > 512) { brcmf_err(bus, "invalid max_flowrings(%d)\n", max_flowrings); return -EIO; } diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index f795548562f5..06161815c180 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -206,71 +206,103 @@ mt76_dma_queue_reset(struct mt76_dev *dev, struct mt76_queue *q) } static int +mt76_dma_add_rx_buf(struct mt76_dev *dev, struct mt76_queue *q, + struct mt76_queue_buf *buf, void *data) +{ + struct mt76_desc *desc = &q->desc[q->head]; + struct mt76_queue_entry *entry = &q->entry[q->head]; + struct mt76_txwi_cache *txwi = NULL; + u32 buf1 = 0, ctrl; + int idx = q->head; + int rx_token; + + ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len); + + if ((q->flags & MT_QFLAG_WED) && + FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX) { + txwi = mt76_get_rxwi(dev); + if (!txwi) + return -ENOMEM; + + rx_token = mt76_rx_token_consume(dev, data, txwi, buf->addr); + if (rx_token < 0) { + mt76_put_rxwi(dev, txwi); + return -ENOMEM; + } + + buf1 |= FIELD_PREP(MT_DMA_CTL_TOKEN, rx_token); + ctrl |= MT_DMA_CTL_TO_HOST; + } + + WRITE_ONCE(desc->buf0, cpu_to_le32(buf->addr)); + WRITE_ONCE(desc->buf1, cpu_to_le32(buf1)); + WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl)); + WRITE_ONCE(desc->info, 0); + + entry->dma_addr[0] = buf->addr; + entry->dma_len[0] = buf->len; + entry->txwi = txwi; + entry->buf = data; + entry->wcid = 0xffff; + entry->skip_buf1 = true; + q->head = (q->head + 1) % q->ndesc; + q->queued++; + + return idx; +} + +static int mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q, struct mt76_queue_buf *buf, int nbufs, u32 info, struct sk_buff *skb, void *txwi) { struct mt76_queue_entry *entry; struct mt76_desc *desc; - u32 ctrl; int i, idx = -1; + u32 ctrl, next; + + if (txwi) { + q->entry[q->head].txwi = DMA_DUMMY_DATA; + q->entry[q->head].skip_buf0 = true; + } for (i = 0; i < nbufs; i += 2, buf += 2) { u32 buf0 = buf[0].addr, buf1 = 0; idx = q->head; - q->head = (q->head + 1) % q->ndesc; + next = (q->head + 1) % q->ndesc; desc = &q->desc[idx]; entry = &q->entry[idx]; - if ((q->flags & MT_QFLAG_WED) && - FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX) { - struct mt76_txwi_cache *t = txwi; - int rx_token; - - if (!t) - return -ENOMEM; - - rx_token = mt76_rx_token_consume(dev, (void *)skb, t, - buf[0].addr); - buf1 |= FIELD_PREP(MT_DMA_CTL_TOKEN, rx_token); - ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len) | - MT_DMA_CTL_TO_HOST; - } else { - if (txwi) { - q->entry[q->head].txwi = DMA_DUMMY_DATA; - q->entry[q->head].skip_buf0 = true; - } - - if (buf[0].skip_unmap) - entry->skip_buf0 = true; - entry->skip_buf1 = i == nbufs - 1; - - entry->dma_addr[0] = buf[0].addr; - entry->dma_len[0] = buf[0].len; - - ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len); - if (i < nbufs - 1) { - entry->dma_addr[1] = buf[1].addr; - entry->dma_len[1] = buf[1].len; - buf1 = buf[1].addr; - ctrl |= FIELD_PREP(MT_DMA_CTL_SD_LEN1, buf[1].len); - if (buf[1].skip_unmap) - entry->skip_buf1 = true; - } - - if (i == nbufs - 1) - ctrl |= MT_DMA_CTL_LAST_SEC0; - else if (i == nbufs - 2) - ctrl |= MT_DMA_CTL_LAST_SEC1; + if (buf[0].skip_unmap) + entry->skip_buf0 = true; + entry->skip_buf1 = i == nbufs - 1; + + entry->dma_addr[0] = buf[0].addr; + entry->dma_len[0] = buf[0].len; + + ctrl = FIELD_PREP(MT_DMA_CTL_SD_LEN0, buf[0].len); + if (i < nbufs - 1) { + entry->dma_addr[1] = buf[1].addr; + entry->dma_len[1] = buf[1].len; + buf1 = buf[1].addr; + ctrl |= FIELD_PREP(MT_DMA_CTL_SD_LEN1, buf[1].len); + if (buf[1].skip_unmap) + entry->skip_buf1 = true; } + if (i == nbufs - 1) + ctrl |= MT_DMA_CTL_LAST_SEC0; + else if (i == nbufs - 2) + ctrl |= MT_DMA_CTL_LAST_SEC1; + WRITE_ONCE(desc->buf0, cpu_to_le32(buf0)); WRITE_ONCE(desc->buf1, cpu_to_le32(buf1)); WRITE_ONCE(desc->info, cpu_to_le32(info)); WRITE_ONCE(desc->ctrl, cpu_to_le32(ctrl)); + q->head = next; q->queued++; } @@ -577,17 +609,9 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q) spin_lock_bh(&q->lock); while (q->queued < q->ndesc - 1) { - struct mt76_txwi_cache *t = NULL; struct mt76_queue_buf qbuf; void *buf = NULL; - if ((q->flags & MT_QFLAG_WED) && - FIELD_GET(MT_QFLAG_WED_TYPE, q->flags) == MT76_WED_Q_RX) { - t = mt76_get_rxwi(dev); - if (!t) - break; - } - buf = page_frag_alloc(rx_page, q->buf_size, GFP_ATOMIC); if (!buf) break; @@ -601,7 +625,12 @@ mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q) qbuf.addr = addr + offset; qbuf.len = len - offset; qbuf.skip_unmap = false; - mt76_dma_add_buf(dev, q, &qbuf, 1, 0, buf, t); + if (mt76_dma_add_rx_buf(dev, q, &qbuf, buf) < 0) { + dma_unmap_single(dev->dma_dev, addr, len, + DMA_FROM_DEVICE); + skb_free_frag(buf); + break; + } frames++; } diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c index 0a95c3da241b..8388e2a65853 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mmio.c @@ -653,6 +653,13 @@ static u32 mt7915_mmio_wed_init_rx_buf(struct mtk_wed_device *wed, int size) desc->buf0 = cpu_to_le32(phy_addr); token = mt76_rx_token_consume(&dev->mt76, ptr, t, phy_addr); + if (token < 0) { + dma_unmap_single(dev->mt76.dma_dev, phy_addr, + wed->wlan.rx_size, DMA_TO_DEVICE); + skb_free_frag(ptr); + goto unmap; + } + desc->token |= cpu_to_le32(FIELD_PREP(MT_DMA_CTL_TOKEN, token)); desc++; diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index 24568b98ed9d..1f309d05380a 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -764,11 +764,12 @@ int mt76_rx_token_consume(struct mt76_dev *dev, void *ptr, spin_lock_bh(&dev->rx_token_lock); token = idr_alloc(&dev->rx_token, t, 0, dev->rx_token_size, GFP_ATOMIC); + if (token >= 0) { + t->ptr = ptr; + t->dma_addr = phys; + } spin_unlock_bh(&dev->rx_token_lock); - t->ptr = ptr; - t->dma_addr = phys; - return token; } EXPORT_SYMBOL_GPL(mt76_rx_token_consume); diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 82a7458e01ae..bf72e5fd39cf 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -696,8 +696,8 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len) struct rndis_query *get; struct rndis_query_c *get_c; } u; - int ret, buflen; - int resplen, respoffs, copylen; + int ret; + size_t buflen, resplen, respoffs, copylen; buflen = *len + sizeof(*u.get); if (buflen < CONTROL_BUFFER_SIZE) @@ -732,22 +732,15 @@ static int rndis_query_oid(struct usbnet *dev, u32 oid, void *data, int *len) if (respoffs > buflen) { /* Device returned data offset outside buffer, error. */ - netdev_dbg(dev->net, "%s(%s): received invalid " - "data offset: %d > %d\n", __func__, - oid_to_string(oid), respoffs, buflen); + netdev_dbg(dev->net, + "%s(%s): received invalid data offset: %zu > %zu\n", + __func__, oid_to_string(oid), respoffs, buflen); ret = -EINVAL; goto exit_unlock; } - if ((resplen + respoffs) > buflen) { - /* Device would have returned more data if buffer would - * have been big enough. Copy just the bits that we got. - */ - copylen = buflen - respoffs; - } else { - copylen = resplen; - } + copylen = min(resplen, buflen - respoffs); if (copylen > *len) copylen = *len; diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c index 7eff3531b9a5..7ff33c1d6ac7 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif.c @@ -152,6 +152,15 @@ static irqreturn_t t7xx_dpmaif_isr_handler(int irq, void *data) } t7xx_pcie_mac_clear_int(dpmaif_ctrl->t7xx_dev, isr_para->pcie_int); + + return IRQ_WAKE_THREAD; +} + +static irqreturn_t t7xx_dpmaif_isr_thread(int irq, void *data) +{ + struct dpmaif_isr_para *isr_para = data; + struct dpmaif_ctrl *dpmaif_ctrl = isr_para->dpmaif_ctrl; + t7xx_dpmaif_irq_cb(isr_para); t7xx_pcie_mac_set_int(dpmaif_ctrl->t7xx_dev, isr_para->pcie_int); return IRQ_HANDLED; @@ -188,7 +197,7 @@ static void t7xx_dpmaif_register_pcie_irq(struct dpmaif_ctrl *dpmaif_ctrl) t7xx_pcie_mac_clear_int(t7xx_dev, int_type); t7xx_dev->intr_handler[int_type] = t7xx_dpmaif_isr_handler; - t7xx_dev->intr_thread[int_type] = NULL; + t7xx_dev->intr_thread[int_type] = t7xx_dpmaif_isr_thread; t7xx_dev->callback_param[int_type] = isr_para; t7xx_pcie_mac_clear_int_status(t7xx_dev, int_type); diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c index aa2174a10437..f4ff2198b5ef 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c @@ -840,14 +840,13 @@ int t7xx_dpmaif_napi_rx_poll(struct napi_struct *napi, const int budget) if (!rxq->que_started) { atomic_set(&rxq->rx_processing, 0); + pm_runtime_put_autosuspend(rxq->dpmaif_ctrl->dev); dev_err(rxq->dpmaif_ctrl->dev, "Work RXQ: %d has not been started\n", rxq->index); return work_done; } - if (!rxq->sleep_lock_pending) { - pm_runtime_get_noresume(rxq->dpmaif_ctrl->dev); + if (!rxq->sleep_lock_pending) t7xx_pci_disable_sleep(t7xx_dev); - } ret = try_wait_for_completion(&t7xx_dev->sleep_lock_acquire); if (!ret) { @@ -876,22 +875,22 @@ int t7xx_dpmaif_napi_rx_poll(struct napi_struct *napi, const int budget) napi_complete_done(napi, work_done); t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); t7xx_dpmaif_dlq_unmask_rx_done(&rxq->dpmaif_ctrl->hw_info, rxq->index); + t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev); + pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev); + pm_runtime_put_autosuspend(rxq->dpmaif_ctrl->dev); + atomic_set(&rxq->rx_processing, 0); } else { t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); } - t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev); - pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev); - pm_runtime_put_noidle(rxq->dpmaif_ctrl->dev); - atomic_set(&rxq->rx_processing, 0); - return work_done; } void t7xx_dpmaif_irq_rx_done(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int que_mask) { struct dpmaif_rx_queue *rxq; - int qno; + struct dpmaif_ctrl *ctrl; + int qno, ret; qno = ffs(que_mask) - 1; if (qno < 0 || qno > DPMAIF_RXQ_NUM - 1) { @@ -900,6 +899,18 @@ void t7xx_dpmaif_irq_rx_done(struct dpmaif_ctrl *dpmaif_ctrl, const unsigned int } rxq = &dpmaif_ctrl->rxq[qno]; + ctrl = rxq->dpmaif_ctrl; + /* We need to make sure that the modem has been resumed before + * calling napi. This can't be done inside the polling function + * as we could be blocked waiting for device to be resumed, + * which can't be done from softirq context the poll function + * is running in. + */ + ret = pm_runtime_resume_and_get(ctrl->dev); + if (ret < 0 && ret != -EACCES) { + dev_err(ctrl->dev, "Failed to resume device: %d\n", ret); + return; + } napi_schedule(&rxq->napi); } diff --git a/drivers/net/wwan/t7xx/t7xx_netdev.c b/drivers/net/wwan/t7xx/t7xx_netdev.c index 494a28e386a3..3ef4a8a4f8fd 100644 --- a/drivers/net/wwan/t7xx/t7xx_netdev.c +++ b/drivers/net/wwan/t7xx/t7xx_netdev.c @@ -27,6 +27,7 @@ #include <linux/list.h> #include <linux/netdev_features.h> #include <linux/netdevice.h> +#include <linux/pm_runtime.h> #include <linux/skbuff.h> #include <linux/types.h> #include <linux/wwan.h> @@ -45,12 +46,25 @@ static void t7xx_ccmni_enable_napi(struct t7xx_ccmni_ctrl *ctlb) { - int i; + struct dpmaif_ctrl *ctrl; + int i, ret; + + ctrl = ctlb->hif_ctrl; if (ctlb->is_napi_en) return; for (i = 0; i < RXQ_NUM; i++) { + /* The usage count has to be bumped every time before calling + * napi_schedule. It will be decresed in the poll routine, + * right after napi_complete_done is called. + */ + ret = pm_runtime_resume_and_get(ctrl->dev); + if (ret < 0) { + dev_err(ctrl->dev, "Failed to resume device: %d\n", + ret); + return; + } napi_enable(ctlb->napi[i]); napi_schedule(ctlb->napi[i]); } diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c index 871f2a27a398..226fc1703e90 100644 --- a/drivers/net/wwan/t7xx/t7xx_pci.c +++ b/drivers/net/wwan/t7xx/t7xx_pci.c @@ -121,6 +121,8 @@ void t7xx_pci_pm_init_late(struct t7xx_pci_dev *t7xx_dev) iowrite32(T7XX_L1_BIT(0), IREG_BASE(t7xx_dev) + ENABLE_ASPM_LOWPWR); atomic_set(&t7xx_dev->md_pm_state, MTK_PM_RESUMED); + pm_runtime_mark_last_busy(&t7xx_dev->pdev->dev); + pm_runtime_allow(&t7xx_dev->pdev->dev); pm_runtime_put_noidle(&t7xx_dev->pdev->dev); } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index c1ba4294f364..001636901dda 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -977,7 +977,7 @@ static int read_xenbus_vif_flags(struct backend_info *be) return 0; } -static int netback_remove(struct xenbus_device *dev) +static void netback_remove(struct xenbus_device *dev) { struct backend_info *be = dev_get_drvdata(&dev->dev); @@ -992,7 +992,6 @@ static int netback_remove(struct xenbus_device *dev) kfree(be->hotplug_script); kfree(be); dev_set_drvdata(&dev->dev, NULL); - return 0; } /* diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 14aec417fa06..12b074286df9 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -2646,7 +2646,7 @@ static void xennet_bus_close(struct xenbus_device *dev) } while (!ret); } -static int xennet_remove(struct xenbus_device *dev) +static void xennet_remove(struct xenbus_device *dev) { struct netfront_info *info = dev_get_drvdata(&dev->dev); @@ -2662,8 +2662,6 @@ static int xennet_remove(struct xenbus_device *dev) rtnl_unlock(); } xennet_free_netdev(info->netdev); - - return 0; } static const struct xenbus_device_id netfront_ids[] = { diff --git a/drivers/nfc/pn533/usb.c b/drivers/nfc/pn533/usb.c index 6f71ac72012e..ed9c5e2cf3ad 100644 --- a/drivers/nfc/pn533/usb.c +++ b/drivers/nfc/pn533/usb.c @@ -153,10 +153,17 @@ static int pn533_usb_send_ack(struct pn533 *dev, gfp_t flags) return usb_submit_urb(phy->ack_urb, flags); } +struct pn533_out_arg { + struct pn533_usb_phy *phy; + struct completion done; +}; + static int pn533_usb_send_frame(struct pn533 *dev, struct sk_buff *out) { struct pn533_usb_phy *phy = dev->phy; + struct pn533_out_arg arg; + void *cntx; int rc; if (phy->priv == NULL) @@ -168,10 +175,17 @@ static int pn533_usb_send_frame(struct pn533 *dev, print_hex_dump_debug("PN533 TX: ", DUMP_PREFIX_NONE, 16, 1, out->data, out->len, false); + init_completion(&arg.done); + cntx = phy->out_urb->context; + phy->out_urb->context = &arg; + rc = usb_submit_urb(phy->out_urb, GFP_KERNEL); if (rc) return rc; + wait_for_completion(&arg.done); + phy->out_urb->context = cntx; + if (dev->protocol_type == PN533_PROTO_REQ_RESP) { /* request for response for sent packet directly */ rc = pn533_submit_urb_for_response(phy, GFP_KERNEL); @@ -408,7 +422,31 @@ static int pn533_acr122_poweron_rdr(struct pn533_usb_phy *phy) return arg.rc; } -static void pn533_send_complete(struct urb *urb) +static void pn533_out_complete(struct urb *urb) +{ + struct pn533_out_arg *arg = urb->context; + struct pn533_usb_phy *phy = arg->phy; + + switch (urb->status) { + case 0: + break; /* success */ + case -ECONNRESET: + case -ENOENT: + dev_dbg(&phy->udev->dev, + "The urb has been stopped (status %d)\n", + urb->status); + break; + case -ESHUTDOWN: + default: + nfc_err(&phy->udev->dev, + "Urb failure (status %d)\n", + urb->status); + } + + complete(&arg->done); +} + +static void pn533_ack_complete(struct urb *urb) { struct pn533_usb_phy *phy = urb->context; @@ -496,10 +534,10 @@ static int pn533_usb_probe(struct usb_interface *interface, usb_fill_bulk_urb(phy->out_urb, phy->udev, usb_sndbulkpipe(phy->udev, out_endpoint), - NULL, 0, pn533_send_complete, phy); + NULL, 0, pn533_out_complete, phy); usb_fill_bulk_urb(phy->ack_urb, phy->udev, usb_sndbulkpipe(phy->udev, out_endpoint), - NULL, 0, pn533_send_complete, phy); + NULL, 0, pn533_ack_complete, phy); switch (id->driver_info) { case PN533_DEVICE_STD: diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index e36aeb50b4ed..b317ce6c4ec3 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -829,7 +829,23 @@ static void apple_nvme_disable(struct apple_nvme *anv, bool shutdown) apple_nvme_remove_cq(anv); } - nvme_disable_ctrl(&anv->ctrl, shutdown); + /* + * Always disable the NVMe controller after shutdown. + * We need to do this to bring it back up later anyway, and we + * can't do it while the firmware is not running (e.g. in the + * resume reset path before RTKit is initialized), so for Apple + * controllers it makes sense to unconditionally do it here. + * Additionally, this sequence of events is reliable, while + * others (like disabling after bringing back the firmware on + * resume) seem to run into trouble under some circumstances. + * + * Both U-Boot and m1n1 also use this convention (i.e. an ANS + * NVMe controller is handed off with firmware shut down, in an + * NVMe disabled state, after a clean shutdown). + */ + if (shutdown) + nvme_disable_ctrl(&anv->ctrl, shutdown); + nvme_disable_ctrl(&anv->ctrl, false); } WRITE_ONCE(anv->ioq.enabled, false); @@ -985,11 +1001,11 @@ static void apple_nvme_reset_work(struct work_struct *work) goto out; } - if (anv->ctrl.ctrl_config & NVME_CC_ENABLE) - apple_nvme_disable(anv, false); - /* RTKit must be shut down cleanly for the (soft)-reset to work */ if (apple_rtkit_is_running(anv->rtk)) { + /* reset the controller if it is enabled */ + if (anv->ctrl.ctrl_config & NVME_CC_ENABLE) + apple_nvme_disable(anv, false); dev_dbg(anv->dev, "Trying to shut down RTKit before reset."); ret = apple_rtkit_shutdown(anv->rtk); if (ret) @@ -1493,7 +1509,7 @@ static int apple_nvme_probe(struct platform_device *pdev) } ret = nvme_init_ctrl(&anv->ctrl, anv->dev, &nvme_ctrl_ops, - NVME_QUIRK_SKIP_CID_GEN); + NVME_QUIRK_SKIP_CID_GEN | NVME_QUIRK_IDENTIFY_CNS); if (ret) { dev_err_probe(dev, ret, "Failed to initialize nvme_ctrl"); goto put_dev; diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index 4424f53a8a0a..b57630d1d3b8 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -45,6 +45,8 @@ struct nvme_dhchap_queue_context { int sess_key_len; }; +struct workqueue_struct *nvme_auth_wq; + #define nvme_auth_flags_from_qid(qid) \ (qid == 0) ? 0 : BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_RESERVED #define nvme_auth_queue_from_qid(ctrl, qid) \ @@ -866,7 +868,7 @@ int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid) chap = &ctrl->dhchap_ctxs[qid]; cancel_work_sync(&chap->auth_work); - queue_work(nvme_wq, &chap->auth_work); + queue_work(nvme_auth_wq, &chap->auth_work); return 0; } EXPORT_SYMBOL_GPL(nvme_auth_negotiate); @@ -1008,10 +1010,15 @@ EXPORT_SYMBOL_GPL(nvme_auth_free); int __init nvme_init_auth(void) { + nvme_auth_wq = alloc_workqueue("nvme-auth-wq", + WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); + if (!nvme_auth_wq) + return -ENOMEM; + nvme_chap_buf_cache = kmem_cache_create("nvme-chap-buf-cache", CHAP_BUF_SIZE, 0, SLAB_HWCACHE_ALIGN, NULL); if (!nvme_chap_buf_cache) - return -ENOMEM; + goto err_destroy_workqueue; nvme_chap_buf_pool = mempool_create(16, mempool_alloc_slab, mempool_free_slab, nvme_chap_buf_cache); @@ -1021,6 +1028,8 @@ int __init nvme_init_auth(void) return 0; err_destroy_chap_buf_cache: kmem_cache_destroy(nvme_chap_buf_cache); +err_destroy_workqueue: + destroy_workqueue(nvme_auth_wq); return -ENOMEM; } @@ -1028,4 +1037,5 @@ void __exit nvme_exit_auth(void) { mempool_destroy(nvme_chap_buf_pool); kmem_cache_destroy(nvme_chap_buf_cache); + destroy_workqueue(nvme_auth_wq); } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 7be562a4e1aa..8b6421141162 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1093,7 +1093,7 @@ u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u8 opcode) if (ns) { if (ns->head->effects) effects = le32_to_cpu(ns->head->effects->iocs[opcode]); - if (ns->head->ids.csi == NVME_CAP_CSS_NVM) + if (ns->head->ids.csi == NVME_CSI_NVM) effects |= nvme_known_nvm_effects(opcode); if (effects & ~(NVME_CMD_EFFECTS_CSUPP | NVME_CMD_EFFECTS_LBCC)) dev_warn_once(ctrl->device, @@ -4921,7 +4921,9 @@ out_cleanup_admin_q: blk_mq_destroy_queue(ctrl->admin_q); blk_put_queue(ctrl->admin_q); out_free_tagset: - blk_mq_free_tag_set(ctrl->admin_tagset); + blk_mq_free_tag_set(set); + ctrl->admin_q = NULL; + ctrl->fabrics_q = NULL; return ret; } EXPORT_SYMBOL_GPL(nvme_alloc_admin_tag_set); @@ -4983,6 +4985,7 @@ int nvme_alloc_io_tag_set(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set, out_free_tag_set: blk_mq_free_tag_set(set); + ctrl->connect_q = NULL; return ret; } EXPORT_SYMBOL_GPL(nvme_alloc_io_tag_set); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 4564f16a0b20..456ee42a6133 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -3521,13 +3521,6 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, nvme_fc_init_queue(ctrl, 0); - ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set, - &nvme_fc_admin_mq_ops, - struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv, - ctrl->lport->ops->fcprqst_priv_sz)); - if (ret) - goto out_free_queues; - /* * Would have been nice to init io queues tag set as well. * However, we require interaction from the controller @@ -3537,10 +3530,17 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_fc_ctrl_ops, 0); if (ret) - goto out_cleanup_tagset; + goto out_free_queues; /* at this point, teardown path changes to ref counting on nvme ctrl */ + ret = nvme_alloc_admin_tag_set(&ctrl->ctrl, &ctrl->admin_tag_set, + &nvme_fc_admin_mq_ops, + struct_size((struct nvme_fcp_op_w_sgl *)NULL, priv, + ctrl->lport->ops->fcprqst_priv_sz)); + if (ret) + goto fail_ctrl; + spin_lock_irqsave(&rport->lock, flags); list_add_tail(&ctrl->ctrl_list, &rport->ctrl_list); spin_unlock_irqrestore(&rport->lock, flags); @@ -3592,8 +3592,6 @@ fail_ctrl: return ERR_PTR(-EIO); -out_cleanup_tagset: - nvme_remove_admin_tag_set(&ctrl->ctrl); out_free_queues: kfree(ctrl->queues); out_free_ida: diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index a8639919237e..06f52db34be9 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -8,8 +8,13 @@ #include <linux/io_uring.h> #include "nvme.h" +enum { + NVME_IOCTL_VEC = (1 << 0), + NVME_IOCTL_PARTITION = (1 << 1), +}; + static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, - fmode_t mode) + unsigned int flags, fmode_t mode) { u32 effects; @@ -17,6 +22,13 @@ static bool nvme_cmd_allowed(struct nvme_ns *ns, struct nvme_command *c, return true; /* + * Do not allow unprivileged passthrough on partitions, as that allows an + * escape from the containment of the partition. + */ + if (flags & NVME_IOCTL_PARTITION) + return false; + + /* * Do not allow unprivileged processes to send vendor specific or fabrics * commands as we can't be sure about their effects. */ @@ -150,7 +162,7 @@ static struct request *nvme_alloc_user_request(struct request_queue *q, static int nvme_map_user_request(struct request *req, u64 ubuffer, unsigned bufflen, void __user *meta_buffer, unsigned meta_len, u32 meta_seed, void **metap, struct io_uring_cmd *ioucmd, - bool vec) + unsigned int flags) { struct request_queue *q = req->q; struct nvme_ns *ns = q->queuedata; @@ -163,7 +175,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, struct iov_iter iter; /* fixedbufs is only for non-vectored io */ - if (WARN_ON_ONCE(vec)) + if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC)) return -EINVAL; ret = io_uring_cmd_import_fixed(ubuffer, bufflen, rq_data_dir(req), &iter, ioucmd); @@ -172,8 +184,8 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer, ret = blk_rq_map_user_iov(q, req, NULL, &iter, GFP_KERNEL); } else { ret = blk_rq_map_user_io(req, NULL, nvme_to_user_ptr(ubuffer), - bufflen, GFP_KERNEL, vec, 0, 0, - rq_data_dir(req)); + bufflen, GFP_KERNEL, flags & NVME_IOCTL_VEC, 0, + 0, rq_data_dir(req)); } if (ret) @@ -203,9 +215,9 @@ out: } static int nvme_submit_user_cmd(struct request_queue *q, - struct nvme_command *cmd, u64 ubuffer, - unsigned bufflen, void __user *meta_buffer, unsigned meta_len, - u32 meta_seed, u64 *result, unsigned timeout, bool vec) + struct nvme_command *cmd, u64 ubuffer, unsigned bufflen, + void __user *meta_buffer, unsigned meta_len, u32 meta_seed, + u64 *result, unsigned timeout, unsigned int flags) { struct nvme_ctrl *ctrl; struct request *req; @@ -221,7 +233,7 @@ static int nvme_submit_user_cmd(struct request_queue *q, req->timeout = timeout; if (ubuffer && bufflen) { ret = nvme_map_user_request(req, ubuffer, bufflen, meta_buffer, - meta_len, meta_seed, &meta, NULL, vec); + meta_len, meta_seed, &meta, NULL, flags); if (ret) return ret; } @@ -304,10 +316,8 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio) c.rw.apptag = cpu_to_le16(io.apptag); c.rw.appmask = cpu_to_le16(io.appmask); - return nvme_submit_user_cmd(ns->queue, &c, - io.addr, length, - metadata, meta_len, lower_32_bits(io.slba), NULL, 0, - false); + return nvme_submit_user_cmd(ns->queue, &c, io.addr, length, metadata, + meta_len, lower_32_bits(io.slba), NULL, 0, 0); } static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl, @@ -325,7 +335,8 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl, } static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, - struct nvme_passthru_cmd __user *ucmd, fmode_t mode) + struct nvme_passthru_cmd __user *ucmd, unsigned int flags, + fmode_t mode) { struct nvme_passthru_cmd cmd; struct nvme_command c; @@ -353,16 +364,15 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.cdw14 = cpu_to_le32(cmd.cdw14); c.common.cdw15 = cpu_to_le32(cmd.cdw15); - if (!nvme_cmd_allowed(ns, &c, mode)) + if (!nvme_cmd_allowed(ns, &c, 0, mode)) return -EACCES; if (cmd.timeout_ms) timeout = msecs_to_jiffies(cmd.timeout_ms); status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, - cmd.addr, cmd.data_len, - nvme_to_user_ptr(cmd.metadata), cmd.metadata_len, - 0, &result, timeout, false); + cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata), + cmd.metadata_len, 0, &result, timeout, 0); if (status >= 0) { if (put_user(result, &ucmd->result)) @@ -373,8 +383,8 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns, } static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, - struct nvme_passthru_cmd64 __user *ucmd, bool vec, - fmode_t mode) + struct nvme_passthru_cmd64 __user *ucmd, unsigned int flags, + fmode_t mode) { struct nvme_passthru_cmd64 cmd; struct nvme_command c; @@ -401,16 +411,15 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.cdw14 = cpu_to_le32(cmd.cdw14); c.common.cdw15 = cpu_to_le32(cmd.cdw15); - if (!nvme_cmd_allowed(ns, &c, mode)) + if (!nvme_cmd_allowed(ns, &c, flags, mode)) return -EACCES; if (cmd.timeout_ms) timeout = msecs_to_jiffies(cmd.timeout_ms); status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c, - cmd.addr, cmd.data_len, - nvme_to_user_ptr(cmd.metadata), cmd.metadata_len, - 0, &cmd.result, timeout, vec); + cmd.addr, cmd.data_len, nvme_to_user_ptr(cmd.metadata), + cmd.metadata_len, 0, &cmd.result, timeout, flags); if (status >= 0) { if (put_user(cmd.result, &ucmd->result)) @@ -571,7 +580,7 @@ static int nvme_uring_cmd_io(struct nvme_ctrl *ctrl, struct nvme_ns *ns, c.common.cdw14 = cpu_to_le32(READ_ONCE(cmd->cdw14)); c.common.cdw15 = cpu_to_le32(READ_ONCE(cmd->cdw15)); - if (!nvme_cmd_allowed(ns, &c, ioucmd->file->f_mode)) + if (!nvme_cmd_allowed(ns, &c, 0, ioucmd->file->f_mode)) return -EACCES; d.metadata = READ_ONCE(cmd->metadata); @@ -641,9 +650,9 @@ static int nvme_ctrl_ioctl(struct nvme_ctrl *ctrl, unsigned int cmd, { switch (cmd) { case NVME_IOCTL_ADMIN_CMD: - return nvme_user_cmd(ctrl, NULL, argp, mode); + return nvme_user_cmd(ctrl, NULL, argp, 0, mode); case NVME_IOCTL_ADMIN64_CMD: - return nvme_user_cmd64(ctrl, NULL, argp, false, mode); + return nvme_user_cmd64(ctrl, NULL, argp, 0, mode); default: return sed_ioctl(ctrl->opal_dev, cmd, argp); } @@ -668,14 +677,14 @@ struct nvme_user_io32 { #endif /* COMPAT_FOR_U64_ALIGNMENT */ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd, - void __user *argp, fmode_t mode) + void __user *argp, unsigned int flags, fmode_t mode) { switch (cmd) { case NVME_IOCTL_ID: force_successful_syscall_return(); return ns->head->ns_id; case NVME_IOCTL_IO_CMD: - return nvme_user_cmd(ns->ctrl, ns, argp, mode); + return nvme_user_cmd(ns->ctrl, ns, argp, flags, mode); /* * struct nvme_user_io can have different padding on some 32-bit ABIs. * Just accept the compat version as all fields that are used are the @@ -686,37 +695,40 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd, #endif case NVME_IOCTL_SUBMIT_IO: return nvme_submit_io(ns, argp); - case NVME_IOCTL_IO64_CMD: - return nvme_user_cmd64(ns->ctrl, ns, argp, false, mode); case NVME_IOCTL_IO64_CMD_VEC: - return nvme_user_cmd64(ns->ctrl, ns, argp, true, mode); + flags |= NVME_IOCTL_VEC; + fallthrough; + case NVME_IOCTL_IO64_CMD: + return nvme_user_cmd64(ns->ctrl, ns, argp, flags, mode); default: return -ENOTTY; } } -static int __nvme_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *arg, - fmode_t mode) -{ - if (is_ctrl_ioctl(cmd)) - return nvme_ctrl_ioctl(ns->ctrl, cmd, arg, mode); - return nvme_ns_ioctl(ns, cmd, arg, mode); -} - int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct nvme_ns *ns = bdev->bd_disk->private_data; + void __user *argp = (void __user *)arg; + unsigned int flags = 0; - return __nvme_ioctl(ns, cmd, (void __user *)arg, mode); + if (bdev_is_partition(bdev)) + flags |= NVME_IOCTL_PARTITION; + + if (is_ctrl_ioctl(cmd)) + return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, mode); + return nvme_ns_ioctl(ns, cmd, argp, flags, mode); } long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct nvme_ns *ns = container_of(file_inode(file)->i_cdev, struct nvme_ns, cdev); + void __user *argp = (void __user *)arg; - return __nvme_ioctl(ns, cmd, (void __user *)arg, file->f_mode); + if (is_ctrl_ioctl(cmd)) + return nvme_ctrl_ioctl(ns->ctrl, cmd, argp, file->f_mode); + return nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode); } static int nvme_uring_cmd_checks(unsigned int issue_flags) @@ -806,6 +818,10 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, void __user *argp = (void __user *)arg; struct nvme_ns *ns; int srcu_idx, ret = -EWOULDBLOCK; + unsigned int flags = 0; + + if (bdev_is_partition(bdev)) + flags |= NVME_IOCTL_PARTITION; srcu_idx = srcu_read_lock(&head->srcu); ns = nvme_find_path(head); @@ -821,7 +837,7 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx, mode); - ret = nvme_ns_ioctl(ns, cmd, argp, mode); + ret = nvme_ns_ioctl(ns, cmd, argp, flags, mode); out_unlock: srcu_read_unlock(&head->srcu, srcu_idx); return ret; @@ -846,7 +862,7 @@ long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd, return nvme_ns_head_ctrl_ioctl(ns, cmd, argp, head, srcu_idx, file->f_mode); - ret = nvme_ns_ioctl(ns, cmd, argp, file->f_mode); + ret = nvme_ns_ioctl(ns, cmd, argp, 0, file->f_mode); out_unlock: srcu_read_unlock(&head->srcu, srcu_idx); return ret; @@ -945,7 +961,7 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp, kref_get(&ns->kref); up_read(&ctrl->namespaces_rwsem); - ret = nvme_user_cmd(ctrl, ns, argp, mode); + ret = nvme_user_cmd(ctrl, ns, argp, 0, mode); nvme_put_ns(ns); return ret; @@ -962,9 +978,9 @@ long nvme_dev_ioctl(struct file *file, unsigned int cmd, switch (cmd) { case NVME_IOCTL_ADMIN_CMD: - return nvme_user_cmd(ctrl, NULL, argp, file->f_mode); + return nvme_user_cmd(ctrl, NULL, argp, 0, file->f_mode); case NVME_IOCTL_ADMIN64_CMD: - return nvme_user_cmd64(ctrl, NULL, argp, false, file->f_mode); + return nvme_user_cmd64(ctrl, NULL, argp, 0, file->f_mode); case NVME_IOCTL_IO_CMD: return nvme_dev_user_cmd(ctrl, argp, file->f_mode); case NVME_IOCTL_RESET: diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index b13baccedb4a..c734934c407c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1362,7 +1362,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) else nvme_poll_irqdisable(nvmeq); - if (blk_mq_request_completed(req)) { + if (blk_mq_rq_state(req) != MQ_RQ_IN_FLIGHT) { dev_warn(dev->ctrl.device, "I/O %d QID %d timeout, completion polled\n", req->tag, nvmeq->qid); @@ -2533,7 +2533,7 @@ static int nvme_pci_enable(struct nvme_dev *dev) */ result = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); if (result < 0) - return result; + goto disable; dev->ctrl.cap = lo_hi_readq(dev->bar + NVME_REG_CAP); @@ -2586,8 +2586,13 @@ static int nvme_pci_enable(struct nvme_dev *dev) pci_enable_pcie_error_reporting(pdev); pci_save_state(pdev); - return nvme_pci_configure_admin_queue(dev); + result = nvme_pci_configure_admin_queue(dev); + if (result) + goto free_irq; + return result; + free_irq: + pci_free_irq_vectors(pdev); disable: pci_disable_device(pdev); return result; @@ -3097,6 +3102,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id) nvme_start_ctrl(&dev->ctrl); nvme_put_ctrl(&dev->ctrl); + flush_work(&dev->ctrl.scan_work); return 0; out_disable: @@ -3495,7 +3501,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_SINGLE_VECTOR | NVME_QUIRK_128_BYTES_SQES | NVME_QUIRK_SHARED_TAGS | - NVME_QUIRK_SKIP_CID_GEN }, + NVME_QUIRK_SKIP_CID_GEN | + NVME_QUIRK_IDENTIFY_CNS }, { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) }, { 0, } }; diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index ab2627e17bb9..1ab6601fdd5c 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1685,8 +1685,10 @@ nvmet_fc_ls_create_association(struct nvmet_fc_tgtport *tgtport, else { queue = nvmet_fc_alloc_target_queue(iod->assoc, 0, be16_to_cpu(rqst->assoc_cmd.sqsize)); - if (!queue) + if (!queue) { ret = VERR_QUEUE_ALLOC_FAIL; + nvmet_fc_tgt_a_put(iod->assoc); + } } } diff --git a/drivers/nvmem/brcm_nvram.c b/drivers/nvmem/brcm_nvram.c index 34130449f2d2..39aa27942f28 100644 --- a/drivers/nvmem/brcm_nvram.c +++ b/drivers/nvmem/brcm_nvram.c @@ -98,6 +98,9 @@ static int brcm_nvram_parse(struct brcm_nvram *priv) len = le32_to_cpu(header.len); data = kzalloc(len, GFP_KERNEL); + if (!data) + return -ENOMEM; + memcpy_fromio(data, priv->base, len); data[len - 1] = '\0'; diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 321d7d63e068..34ee9d36ee7b 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -770,31 +770,32 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) return ERR_PTR(rval); } - if (config->wp_gpio) - nvmem->wp_gpio = config->wp_gpio; - else if (!config->ignore_wp) + nvmem->id = rval; + + nvmem->dev.type = &nvmem_provider_type; + nvmem->dev.bus = &nvmem_bus_type; + nvmem->dev.parent = config->dev; + + device_initialize(&nvmem->dev); + + if (!config->ignore_wp) nvmem->wp_gpio = gpiod_get_optional(config->dev, "wp", GPIOD_OUT_HIGH); if (IS_ERR(nvmem->wp_gpio)) { - ida_free(&nvmem_ida, nvmem->id); rval = PTR_ERR(nvmem->wp_gpio); - kfree(nvmem); - return ERR_PTR(rval); + nvmem->wp_gpio = NULL; + goto err_put_device; } kref_init(&nvmem->refcnt); INIT_LIST_HEAD(&nvmem->cells); - nvmem->id = rval; nvmem->owner = config->owner; if (!nvmem->owner && config->dev->driver) nvmem->owner = config->dev->driver->owner; nvmem->stride = config->stride ?: 1; nvmem->word_size = config->word_size ?: 1; nvmem->size = config->size; - nvmem->dev.type = &nvmem_provider_type; - nvmem->dev.bus = &nvmem_bus_type; - nvmem->dev.parent = config->dev; nvmem->root_only = config->root_only; nvmem->priv = config->priv; nvmem->type = config->type; @@ -822,11 +823,8 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) break; } - if (rval) { - ida_free(&nvmem_ida, nvmem->id); - kfree(nvmem); - return ERR_PTR(rval); - } + if (rval) + goto err_put_device; nvmem->read_only = device_property_present(config->dev, "read-only") || config->read_only || !nvmem->reg_write; @@ -835,28 +833,22 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->dev.groups = nvmem_dev_groups; #endif - dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); - - rval = device_register(&nvmem->dev); - if (rval) - goto err_put_device; - if (nvmem->nkeepout) { rval = nvmem_validate_keepouts(nvmem); if (rval) - goto err_device_del; + goto err_put_device; } if (config->compat) { rval = nvmem_sysfs_setup_compat(nvmem, config); if (rval) - goto err_device_del; + goto err_put_device; } if (config->cells) { rval = nvmem_add_cells(nvmem, config->cells, config->ncells); if (rval) - goto err_teardown_compat; + goto err_remove_cells; } rval = nvmem_add_cells_from_table(nvmem); @@ -867,17 +859,20 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) if (rval) goto err_remove_cells; + dev_dbg(&nvmem->dev, "Registering nvmem device %s\n", config->name); + + rval = device_add(&nvmem->dev); + if (rval) + goto err_remove_cells; + blocking_notifier_call_chain(&nvmem_notifier, NVMEM_ADD, nvmem); return nvmem; err_remove_cells: nvmem_device_remove_all_cells(nvmem); -err_teardown_compat: if (config->compat) nvmem_sysfs_remove_compat(nvmem, config); -err_device_del: - device_del(&nvmem->dev); err_put_device: put_device(&nvmem->dev); @@ -1242,16 +1237,21 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np, const char *id) if (!cell_np) return ERR_PTR(-ENOENT); - nvmem_np = of_get_next_parent(cell_np); - if (!nvmem_np) + nvmem_np = of_get_parent(cell_np); + if (!nvmem_np) { + of_node_put(cell_np); return ERR_PTR(-EINVAL); + } nvmem = __nvmem_device_get(nvmem_np, device_match_of_node); of_node_put(nvmem_np); - if (IS_ERR(nvmem)) + if (IS_ERR(nvmem)) { + of_node_put(cell_np); return ERR_CAST(nvmem); + } cell_entry = nvmem_find_cell_entry_by_node(nvmem, cell_np); + of_node_put(cell_np); if (!cell_entry) { __nvmem_device_put(nvmem); return ERR_PTR(-ENOENT); diff --git a/drivers/nvmem/qcom-spmi-sdam.c b/drivers/nvmem/qcom-spmi-sdam.c index 4fcb63507ecd..8499892044b7 100644 --- a/drivers/nvmem/qcom-spmi-sdam.c +++ b/drivers/nvmem/qcom-spmi-sdam.c @@ -166,6 +166,7 @@ static const struct of_device_id sdam_match_table[] = { { .compatible = "qcom,spmi-sdam" }, {}, }; +MODULE_DEVICE_TABLE(of, sdam_match_table); static struct platform_driver sdam_driver = { .driver = { diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 5750e1f4bcdb..92dfe4cb10e3 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -41,8 +41,21 @@ static int sunxi_sid_read(void *context, unsigned int offset, void *val, size_t bytes) { struct sunxi_sid *sid = context; + u32 word; + + /* .stride = 4 so offset is guaranteed to be aligned */ + __ioread32_copy(val, sid->base + sid->value_offset + offset, bytes / 4); - memcpy_fromio(val, sid->base + sid->value_offset + offset, bytes); + val += round_down(bytes, 4); + offset += round_down(bytes, 4); + bytes = bytes % 4; + + if (!bytes) + return 0; + + /* Handle any trailing bytes */ + word = readl_relaxed(sid->base + sid->value_offset + offset); + memcpy(val, &word, bytes); return 0; } diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index f08b25195ae7..d1a68b6d03b3 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -26,7 +26,6 @@ #include <linux/serial_core.h> #include <linux/sysfs.h> #include <linux/random.h> -#include <linux/kmemleak.h> #include <asm/setup.h> /* for COMMAND_LINE_SIZE */ #include <asm/page.h> @@ -525,12 +524,9 @@ static int __init __reserved_mem_reserve_reg(unsigned long node, size = dt_mem_next_cell(dt_root_size_cells, &prop); if (size && - early_init_dt_reserve_memory(base, size, nomap) == 0) { + early_init_dt_reserve_memory(base, size, nomap) == 0) pr_debug("Reserved memory: reserved region for node '%s': base %pa, size %lu MiB\n", uname, &base, (unsigned long)(size / SZ_1M)); - if (!nomap) - kmemleak_alloc_phys(base, size, 0); - } else pr_err("Reserved memory: failed to reserve memory for node '%s': base %pa, size %lu MiB\n", uname, &base, (unsigned long)(size / SZ_1M)); diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c index d6af5726ddf3..2a18f7ba2398 100644 --- a/drivers/parisc/pdc_stable.c +++ b/drivers/parisc/pdc_stable.c @@ -274,8 +274,7 @@ pdcspath_hwpath_write(struct pdcspath_entry *entry, const char *buf, size_t coun /* We'll use a local copy of buf */ count = min_t(size_t, count, sizeof(in)-1); - strncpy(in, buf, count); - in[count] = '\0'; + strscpy(in, buf, count + 1); /* Let's clean up the target. 0xff is a blank pattern */ memset(&hwpath, 0xff, sizeof(hwpath)); @@ -388,8 +387,7 @@ pdcspath_layer_write(struct pdcspath_entry *entry, const char *buf, size_t count /* We'll use a local copy of buf */ count = min_t(size_t, count, sizeof(in)-1); - strncpy(in, buf, count); - in[count] = '\0'; + strscpy(in, buf, count + 1); /* Let's clean up the target. 0 is a blank pattern */ memset(&layers, 0, sizeof(layers)); @@ -756,8 +754,7 @@ static ssize_t pdcs_auto_write(struct kobject *kobj, /* We'll use a local copy of buf */ count = min_t(size_t, count, sizeof(in)-1); - strncpy(in, buf, count); - in[count] = '\0'; + strscpy(in, buf, count + 1); /* Current flags are stored in primary boot path entry */ pathentry = &pdcspath_entry_primary; diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index a0d2713f0e88..99ec91e2a5cf 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -225,7 +225,7 @@ config PCIE_ARTPEC6_EP config PCIE_BT1 tristate "Baikal-T1 PCIe controller" depends on MIPS_BAIKAL_T1 || COMPILE_TEST - depends on PCI_MSI_IRQ_DOMAIN + depends on PCI_MSI select PCIE_DW_HOST help Enables support for the PCIe controller in the Baikal-T1 SoC to work diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 7378e2f3e525..fcd029ca2eb1 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -1055,14 +1055,12 @@ out: return err; } -static int pcifront_xenbus_remove(struct xenbus_device *xdev) +static void pcifront_xenbus_remove(struct xenbus_device *xdev) { struct pcifront_device *pdev = dev_get_drvdata(&xdev->dev); if (pdev) free_pdev(pdev); - - return 0; } static const struct xenbus_device_id xenpci_ids[] = { diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index b80a9b74662b..1deb61b22bc7 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -1576,7 +1576,6 @@ static int arm_cmn_event_init(struct perf_event *event) hw->dn++; continue; } - hw->dtcs_used |= arm_cmn_node_to_xp(cmn, dn)->dtc; hw->num_dns++; if (bynodeid) break; @@ -1589,6 +1588,12 @@ static int arm_cmn_event_init(struct perf_event *event) nodeid, nid.x, nid.y, nid.port, nid.dev, type); return -EINVAL; } + /* + * Keep assuming non-cycles events count in all DTC domains; turns out + * it's hard to make a worthwhile optimisation around this, short of + * going all-in with domain-local counter allocation as well. + */ + hw->dtcs_used = (1U << cmn->num_dtcs) - 1; return arm_cmn_validate_group(cmn, event); } diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index f6507efe2a58..71174fa593f4 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -44,7 +44,7 @@ static const struct attribute_group *riscv_pmu_attr_groups[] = { }; /* - * RISC-V doesn't have hetergenous harts yet. This need to be part of + * RISC-V doesn't have heterogeneous harts yet. This need to be part of * per_cpu in case of harts with different pmu counters */ static union sbi_pmu_ctr_info *pmu_ctr_list; @@ -52,6 +52,9 @@ static bool riscv_pmu_use_irq; static unsigned int riscv_pmu_irq_num; static unsigned int riscv_pmu_irq; +/* Cache the available counters in a bitmask */ +static unsigned long cmask; + struct sbi_pmu_event_data { union { union { @@ -267,6 +270,58 @@ static bool pmu_sbi_ctr_is_fw(int cidx) return (info->type == SBI_PMU_CTR_TYPE_FW) ? true : false; } +/* + * Returns the counter width of a programmable counter and number of hardware + * counters. As we don't support heterogeneous CPUs yet, it is okay to just + * return the counter width of the first programmable counter. + */ +int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr) +{ + int i; + union sbi_pmu_ctr_info *info; + u32 hpm_width = 0, hpm_count = 0; + + if (!cmask) + return -EINVAL; + + for_each_set_bit(i, &cmask, RISCV_MAX_COUNTERS) { + info = &pmu_ctr_list[i]; + if (!info) + continue; + if (!hpm_width && info->csr != CSR_CYCLE && info->csr != CSR_INSTRET) + hpm_width = info->width; + if (info->type == SBI_PMU_CTR_TYPE_HW) + hpm_count++; + } + + *hw_ctr_width = hpm_width; + *num_hw_ctr = hpm_count; + + return 0; +} +EXPORT_SYMBOL_GPL(riscv_pmu_get_hpm_info); + +static unsigned long pmu_sbi_get_filter_flags(struct perf_event *event) +{ + unsigned long cflags = 0; + bool guest_events = false; + + if (event->attr.config1 & RISCV_PMU_CONFIG1_GUEST_EVENTS) + guest_events = true; + if (event->attr.exclude_kernel) + cflags |= guest_events ? SBI_PMU_CFG_FLAG_SET_VSINH : SBI_PMU_CFG_FLAG_SET_SINH; + if (event->attr.exclude_user) + cflags |= guest_events ? SBI_PMU_CFG_FLAG_SET_VUINH : SBI_PMU_CFG_FLAG_SET_UINH; + if (guest_events && event->attr.exclude_hv) + cflags |= SBI_PMU_CFG_FLAG_SET_SINH; + if (event->attr.exclude_host) + cflags |= SBI_PMU_CFG_FLAG_SET_UINH | SBI_PMU_CFG_FLAG_SET_SINH; + if (event->attr.exclude_guest) + cflags |= SBI_PMU_CFG_FLAG_SET_VSINH | SBI_PMU_CFG_FLAG_SET_VUINH; + + return cflags; +} + static int pmu_sbi_ctr_get_idx(struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -277,11 +332,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) uint64_t cbase = 0; unsigned long cflags = 0; - if (event->attr.exclude_kernel) - cflags |= SBI_PMU_CFG_FLAG_SET_SINH; - if (event->attr.exclude_user) - cflags |= SBI_PMU_CFG_FLAG_SET_UINH; - + cflags = pmu_sbi_get_filter_flags(event); /* retrieve the available counter index */ #if defined(CONFIG_32BIT) ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, @@ -812,7 +863,6 @@ static void riscv_pmu_destroy(struct riscv_pmu *pmu) static int pmu_sbi_device_probe(struct platform_device *pdev) { struct riscv_pmu *pmu = NULL; - unsigned long cmask = 0; int ret = -ENODEV; int num_counters; diff --git a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c index 7585e8080b77..afc63552ecaf 100644 --- a/drivers/phy/freescale/phy-fsl-imx8m-pcie.c +++ b/drivers/phy/freescale/phy-fsl-imx8m-pcie.c @@ -255,7 +255,7 @@ static int imx8_pcie_phy_probe(struct platform_device *pdev) imx8_phy->perst = devm_reset_control_get_exclusive(dev, "perst"); if (IS_ERR(imx8_phy->perst)) - dev_err_probe(dev, PTR_ERR(imx8_phy->perst), + return dev_err_probe(dev, PTR_ERR(imx8_phy->perst), "Failed to get PCIE PHY PERST control\n"); } diff --git a/drivers/phy/phy-can-transceiver.c b/drivers/phy/phy-can-transceiver.c index 95c6dbb52da7..ce511ad5d369 100644 --- a/drivers/phy/phy-can-transceiver.c +++ b/drivers/phy/phy-can-transceiver.c @@ -99,6 +99,7 @@ static int can_transceiver_phy_probe(struct platform_device *pdev) struct gpio_desc *standby_gpio; struct gpio_desc *enable_gpio; u32 max_bitrate = 0; + int err; can_transceiver_phy = devm_kzalloc(dev, sizeof(struct can_transceiver_phy), GFP_KERNEL); if (!can_transceiver_phy) @@ -124,8 +125,8 @@ static int can_transceiver_phy_probe(struct platform_device *pdev) return PTR_ERR(phy); } - device_property_read_u32(dev, "max-bitrate", &max_bitrate); - if (!max_bitrate) + err = device_property_read_u32(dev, "max-bitrate", &max_bitrate); + if ((err != -EINVAL) && !max_bitrate) dev_warn(dev, "Invalid value for transceiver max bitrate. Ignoring bitrate limit\n"); phy->attrs.max_link_rate = max_bitrate; diff --git a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c index 8807e59a1162..a52a9bf13b75 100644 --- a/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c +++ b/drivers/phy/qualcomm/phy-qcom-usb-hs-28nm.c @@ -401,26 +401,13 @@ static const struct hsphy_init_seq init_seq_femtophy[] = { HSPHY_INIT_CFG(0x90, 0x60, 0), }; -static const struct hsphy_init_seq init_seq_mdm9607[] = { - HSPHY_INIT_CFG(0x80, 0x44, 0), - HSPHY_INIT_CFG(0x81, 0x38, 0), - HSPHY_INIT_CFG(0x82, 0x24, 0), - HSPHY_INIT_CFG(0x83, 0x13, 0), -}; - static const struct hsphy_data hsphy_data_femtophy = { .init_seq = init_seq_femtophy, .init_seq_num = ARRAY_SIZE(init_seq_femtophy), }; -static const struct hsphy_data hsphy_data_mdm9607 = { - .init_seq = init_seq_mdm9607, - .init_seq_num = ARRAY_SIZE(init_seq_mdm9607), -}; - static const struct of_device_id qcom_snps_hsphy_match[] = { { .compatible = "qcom,usb-hs-28nm-femtophy", .data = &hsphy_data_femtophy, }, - { .compatible = "qcom,usb-hs-28nm-mdm9607", .data = &hsphy_data_mdm9607, }, { }, }; MODULE_DEVICE_TABLE(of, qcom_snps_hsphy_match); diff --git a/drivers/phy/renesas/r8a779f0-ether-serdes.c b/drivers/phy/renesas/r8a779f0-ether-serdes.c index ec6594e6dc27..e7588a940d69 100644 --- a/drivers/phy/renesas/r8a779f0-ether-serdes.c +++ b/drivers/phy/renesas/r8a779f0-ether-serdes.c @@ -126,7 +126,7 @@ r8a779f0_eth_serdes_chan_setting(struct r8a779f0_eth_serdes_channel *channel) r8a779f0_eth_serdes_write32(channel->addr, 0x0160, 0x180, 0x0007); r8a779f0_eth_serdes_write32(channel->addr, 0x01ac, 0x180, 0x0000); r8a779f0_eth_serdes_write32(channel->addr, 0x00c4, 0x180, 0x0310); - r8a779f0_eth_serdes_write32(channel->addr, 0x00c8, 0x380, 0x0101); + r8a779f0_eth_serdes_write32(channel->addr, 0x00c8, 0x180, 0x0101); ret = r8a779f0_eth_serdes_reg_wait(channel, 0x00c8, 0x0180, BIT(0), 0); if (ret) return ret; diff --git a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c index e6ededc51523..a0bc10aa7961 100644 --- a/drivers/phy/rockchip/phy-rockchip-inno-usb2.c +++ b/drivers/phy/rockchip/phy-rockchip-inno-usb2.c @@ -485,8 +485,10 @@ static int rockchip_usb2phy_power_on(struct phy *phy) return ret; ret = property_enable(base, &rport->port_cfg->phy_sus, false); - if (ret) + if (ret) { + clk_disable_unprepare(rphy->clk480m); return ret; + } /* waiting for the utmi_clk to become stable */ usleep_range(1500, 2000); diff --git a/drivers/phy/sunplus/phy-sunplus-usb2.c b/drivers/phy/sunplus/phy-sunplus-usb2.c index e827b79f6d49..56de41091d63 100644 --- a/drivers/phy/sunplus/phy-sunplus-usb2.c +++ b/drivers/phy/sunplus/phy-sunplus-usb2.c @@ -254,6 +254,9 @@ static int sp_usb_phy_probe(struct platform_device *pdev) return PTR_ERR(usbphy->phy_regs); usbphy->moon4_res_mem = platform_get_resource_byname(pdev, IORESOURCE_MEM, "moon4"); + if (!usbphy->moon4_res_mem) + return -EINVAL; + usbphy->moon4_regs = devm_ioremap(&pdev->dev, usbphy->moon4_res_mem->start, resource_size(usbphy->moon4_res_mem)); if (!usbphy->moon4_regs) diff --git a/drivers/phy/ti/Kconfig b/drivers/phy/ti/Kconfig index 15a3bcf32308..b905902d5750 100644 --- a/drivers/phy/ti/Kconfig +++ b/drivers/phy/ti/Kconfig @@ -23,7 +23,7 @@ config PHY_DM816X_USB config PHY_AM654_SERDES tristate "TI AM654 SERDES support" - depends on OF && ARCH_K3 || COMPILE_TEST + depends on OF && (ARCH_K3 || COMPILE_TEST) depends on COMMON_CLK select GENERIC_PHY select MULTIPLEXER @@ -35,7 +35,7 @@ config PHY_AM654_SERDES config PHY_J721E_WIZ tristate "TI J721E WIZ (SERDES Wrapper) support" - depends on OF && ARCH_K3 || COMPILE_TEST + depends on OF && (ARCH_K3 || COMPILE_TEST) depends on HAS_IOMEM && OF_ADDRESS depends on COMMON_CLK select GENERIC_PHY diff --git a/drivers/pinctrl/nomadik/pinctrl-ab8500.c b/drivers/pinctrl/nomadik/pinctrl-ab8500.c index 3106a21cd277..d7b244df058f 100644 --- a/drivers/pinctrl/nomadik/pinctrl-ab8500.c +++ b/drivers/pinctrl/nomadik/pinctrl-ab8500.c @@ -6,9 +6,10 @@ */ #include <linux/kernel.h> -#include <linux/gpio/driver.h> #include <linux/pinctrl/pinctrl.h> + #include <linux/mfd/abx500/ab8500.h> + #include "pinctrl-abx500.h" /* All the pins that can be used for GPIO and some other functions */ diff --git a/drivers/pinctrl/nomadik/pinctrl-ab8505.c b/drivers/pinctrl/nomadik/pinctrl-ab8505.c index b93af1fb37f0..45aa958b573e 100644 --- a/drivers/pinctrl/nomadik/pinctrl-ab8505.c +++ b/drivers/pinctrl/nomadik/pinctrl-ab8505.c @@ -6,9 +6,10 @@ */ #include <linux/kernel.h> -#include <linux/gpio/driver.h> #include <linux/pinctrl/pinctrl.h> + #include <linux/mfd/abx500/ab8500.h> + #include "pinctrl-abx500.h" /* All the pins that can be used for GPIO and some other functions */ diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c index 7aa534576a45..28c3403df1b0 100644 --- a/drivers/pinctrl/nomadik/pinctrl-abx500.c +++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c @@ -6,33 +6,37 @@ * * Driver allows to use AxB5xx unused pins to be used as GPIO */ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/slab.h> -#include <linux/init.h> +#include <linux/bitops.h> #include <linux/err.h> -#include <linux/of.h> -#include <linux/of_device.h> -#include <linux/platform_device.h> #include <linux/gpio/driver.h> +#include <linux/init.h> +#include <linux/interrupt.h> #include <linux/irq.h> #include <linux/irqdomain.h> -#include <linux/interrupt.h> -#include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/types.h> + #include <linux/mfd/abx500.h> #include <linux/mfd/abx500/ab8500.h> -#include <linux/pinctrl/pinctrl.h> + #include <linux/pinctrl/consumer.h> -#include <linux/pinctrl/pinmux.h> -#include <linux/pinctrl/pinconf.h> -#include <linux/pinctrl/pinconf-generic.h> #include <linux/pinctrl/machine.h> +#include <linux/pinctrl/pinconf-generic.h> +#include <linux/pinctrl/pinconf.h> +#include <linux/pinctrl/pinctrl.h> +#include <linux/pinctrl/pinmux.h> -#include "pinctrl-abx500.h" #include "../core.h" #include "../pinconf.h" #include "../pinctrl-utils.h" +#include "pinctrl-abx500.h" + /* * GPIO registers offset * Bank: 0x10 diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.h b/drivers/pinctrl/nomadik/pinctrl-abx500.h index 90bb12fe8073..d67522084675 100644 --- a/drivers/pinctrl/nomadik/pinctrl-abx500.h +++ b/drivers/pinctrl/nomadik/pinctrl-abx500.h @@ -2,6 +2,10 @@ #ifndef PINCTRL_PINCTRL_ABx500_H #define PINCTRL_PINCTRL_ABx500_H +#include <linux/types.h> + +struct pinctrl_pin_desc; + /* Package definitions */ #define PINCTRL_AB8500 0 #define PINCTRL_AB8505 1 diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik-db8500.c b/drivers/pinctrl/nomadik/pinctrl-nomadik-db8500.c index 758d21f0a850..490e0959e8be 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik-db8500.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik-db8500.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> +#include <linux/types.h> + #include <linux/pinctrl/pinctrl.h> + #include "pinctrl-nomadik.h" /* All the pins that can be used for GPIO and some other functions */ diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c b/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c index c0d7c86d0939..1552222ac68e 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik-stn8815.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> +#include <linux/types.h> + #include <linux/pinctrl/pinctrl.h> + #include "pinctrl-nomadik.h" /* All the pins that can be used for GPIO and some other functions */ diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c index f7d02513d8cc..86a638077a69 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c @@ -7,30 +7,34 @@ * Rewritten based on work by Prafulla WADASKAR <prafulla.wadaskar@st.com> * Copyright (C) 2011-2013 Linus Walleij <linus.walleij@linaro.org> */ -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/device.h> -#include <linux/platform_device.h> -#include <linux/io.h> +#include <linux/bitops.h> #include <linux/clk.h> +#include <linux/device.h> #include <linux/err.h> #include <linux/gpio/driver.h> -#include <linux/spinlock.h> +#include <linux/init.h> #include <linux/interrupt.h> -#include <linux/slab.h> -#include <linux/of_device.h> +#include <linux/io.h> +#include <linux/kernel.h> #include <linux/of_address.h> -#include <linux/bitops.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> +#include <linux/seq_file.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +/* Since we request GPIOs from ourself */ +#include <linux/pinctrl/consumer.h> #include <linux/pinctrl/machine.h> +#include <linux/pinctrl/pinconf.h> #include <linux/pinctrl/pinctrl.h> #include <linux/pinctrl/pinmux.h> -#include <linux/pinctrl/pinconf.h> -/* Since we request GPIOs from ourself */ -#include <linux/pinctrl/consumer.h> -#include "pinctrl-nomadik.h" + #include "../core.h" #include "../pinctrl-utils.h" +#include "pinctrl-nomadik.h" + /* * The GPIO module in the Nomadik family of Systems-on-Chip is an * AMBA device, managing 32 pins and alternate functions. The logic block @@ -907,8 +911,6 @@ static int nmk_gpio_get_mode(struct nmk_gpio_chip *nmk_chip, int offset) return (afunc ? NMK_GPIO_ALT_A : 0) | (bfunc ? NMK_GPIO_ALT_B : 0); } -#include <linux/seq_file.h> - static void nmk_gpio_dbg_show_one(struct seq_file *s, struct pinctrl_dev *pctldev, struct gpio_chip *chip, unsigned offset, unsigned gpio) diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.h b/drivers/pinctrl/nomadik/pinctrl-nomadik.h index 84e297757335..1ef2559bc571 100644 --- a/drivers/pinctrl/nomadik/pinctrl-nomadik.h +++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.h @@ -2,6 +2,11 @@ #ifndef PINCTRL_PINCTRL_NOMADIK_H #define PINCTRL_PINCTRL_NOMADIK_H +#include <linux/kernel.h> +#include <linux/types.h> + +#include <linux/pinctrl/pinctrl.h> + /* Package definitions */ #define PINCTRL_NMK_STN8815 0 #define PINCTRL_NMK_DB8500 1 diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c index da974ff2d75d..5eeac92f610a 100644 --- a/drivers/pinctrl/pinctrl-rockchip.c +++ b/drivers/pinctrl/pinctrl-rockchip.c @@ -926,19 +926,19 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = { RK_MUXROUTE_PMU(0, RK_PB5, 4, 0x0110, WRITE_MASK_VAL(3, 2, 1)), /* PWM1 IO mux M1 */ RK_MUXROUTE_PMU(0, RK_PC1, 1, 0x0110, WRITE_MASK_VAL(5, 4, 0)), /* PWM2 IO mux M0 */ RK_MUXROUTE_PMU(0, RK_PB6, 4, 0x0110, WRITE_MASK_VAL(5, 4, 1)), /* PWM2 IO mux M1 */ - RK_MUXROUTE_PMU(0, RK_PB3, 2, 0x0300, WRITE_MASK_VAL(0, 0, 0)), /* CAN0 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PB3, 2, 0x0300, WRITE_MASK_VAL(0, 0, 0)), /* CAN0 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PA1, 4, 0x0300, WRITE_MASK_VAL(0, 0, 1)), /* CAN0 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PA1, 3, 0x0300, WRITE_MASK_VAL(2, 2, 0)), /* CAN1 IO mux M0 */ RK_MUXROUTE_GRF(4, RK_PC3, 3, 0x0300, WRITE_MASK_VAL(2, 2, 1)), /* CAN1 IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PB5, 3, 0x0300, WRITE_MASK_VAL(4, 4, 0)), /* CAN2 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PB2, 4, 0x0300, WRITE_MASK_VAL(4, 4, 1)), /* CAN2 IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PC4, 1, 0x0300, WRITE_MASK_VAL(6, 6, 0)), /* HPDIN IO mux M0 */ - RK_MUXROUTE_PMU(0, RK_PC2, 2, 0x0300, WRITE_MASK_VAL(6, 6, 1)), /* HPDIN IO mux M1 */ + RK_MUXROUTE_GRF(0, RK_PC2, 2, 0x0300, WRITE_MASK_VAL(6, 6, 1)), /* HPDIN IO mux M1 */ RK_MUXROUTE_GRF(3, RK_PB1, 3, 0x0300, WRITE_MASK_VAL(8, 8, 0)), /* GMAC1 IO mux M0 */ RK_MUXROUTE_GRF(4, RK_PA7, 3, 0x0300, WRITE_MASK_VAL(8, 8, 1)), /* GMAC1 IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PD1, 1, 0x0300, WRITE_MASK_VAL(10, 10, 0)), /* HDMITX IO mux M0 */ - RK_MUXROUTE_PMU(0, RK_PC7, 1, 0x0300, WRITE_MASK_VAL(10, 10, 1)), /* HDMITX IO mux M1 */ - RK_MUXROUTE_PMU(0, RK_PB6, 1, 0x0300, WRITE_MASK_VAL(14, 14, 0)), /* I2C2 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PC7, 1, 0x0300, WRITE_MASK_VAL(10, 10, 1)), /* HDMITX IO mux M1 */ + RK_MUXROUTE_GRF(0, RK_PB6, 1, 0x0300, WRITE_MASK_VAL(14, 14, 0)), /* I2C2 IO mux M0 */ RK_MUXROUTE_GRF(4, RK_PB4, 1, 0x0300, WRITE_MASK_VAL(14, 14, 1)), /* I2C2 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PA0, 1, 0x0304, WRITE_MASK_VAL(0, 0, 0)), /* I2C3 IO mux M0 */ RK_MUXROUTE_GRF(3, RK_PB6, 4, 0x0304, WRITE_MASK_VAL(0, 0, 1)), /* I2C3 IO mux M1 */ @@ -964,7 +964,7 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = { RK_MUXROUTE_GRF(4, RK_PC3, 1, 0x0308, WRITE_MASK_VAL(12, 12, 1)), /* PWM15 IO mux M1 */ RK_MUXROUTE_GRF(3, RK_PD2, 3, 0x0308, WRITE_MASK_VAL(14, 14, 0)), /* SDMMC2 IO mux M0 */ RK_MUXROUTE_GRF(3, RK_PA5, 5, 0x0308, WRITE_MASK_VAL(14, 14, 1)), /* SDMMC2 IO mux M1 */ - RK_MUXROUTE_PMU(0, RK_PB5, 2, 0x030c, WRITE_MASK_VAL(0, 0, 0)), /* SPI0 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PB5, 2, 0x030c, WRITE_MASK_VAL(0, 0, 0)), /* SPI0 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PD3, 3, 0x030c, WRITE_MASK_VAL(0, 0, 1)), /* SPI0 IO mux M1 */ RK_MUXROUTE_GRF(2, RK_PB5, 3, 0x030c, WRITE_MASK_VAL(2, 2, 0)), /* SPI1 IO mux M0 */ RK_MUXROUTE_GRF(3, RK_PC3, 3, 0x030c, WRITE_MASK_VAL(2, 2, 1)), /* SPI1 IO mux M1 */ @@ -973,8 +973,8 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = { RK_MUXROUTE_GRF(4, RK_PB3, 4, 0x030c, WRITE_MASK_VAL(6, 6, 0)), /* SPI3 IO mux M0 */ RK_MUXROUTE_GRF(4, RK_PC2, 2, 0x030c, WRITE_MASK_VAL(6, 6, 1)), /* SPI3 IO mux M1 */ RK_MUXROUTE_GRF(2, RK_PB4, 2, 0x030c, WRITE_MASK_VAL(8, 8, 0)), /* UART1 IO mux M0 */ - RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(8, 8, 1)), /* UART1 IO mux M1 */ - RK_MUXROUTE_PMU(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(10, 10, 0)), /* UART2 IO mux M0 */ + RK_MUXROUTE_GRF(3, RK_PD6, 4, 0x030c, WRITE_MASK_VAL(8, 8, 1)), /* UART1 IO mux M1 */ + RK_MUXROUTE_GRF(0, RK_PD1, 1, 0x030c, WRITE_MASK_VAL(10, 10, 0)), /* UART2 IO mux M0 */ RK_MUXROUTE_GRF(1, RK_PD5, 2, 0x030c, WRITE_MASK_VAL(10, 10, 1)), /* UART2 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PA1, 2, 0x030c, WRITE_MASK_VAL(12, 12, 0)), /* UART3 IO mux M0 */ RK_MUXROUTE_GRF(3, RK_PB7, 4, 0x030c, WRITE_MASK_VAL(12, 12, 1)), /* UART3 IO mux M1 */ @@ -1004,13 +1004,13 @@ static struct rockchip_mux_route_data rk3568_mux_route_data[] = { RK_MUXROUTE_GRF(3, RK_PD6, 5, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PA0, 4, 0x0314, WRITE_MASK_VAL(1, 0, 1)), /* PDM IO mux M1 */ RK_MUXROUTE_GRF(3, RK_PC4, 5, 0x0314, WRITE_MASK_VAL(1, 0, 2)), /* PDM IO mux M2 */ - RK_MUXROUTE_PMU(0, RK_PA5, 3, 0x0314, WRITE_MASK_VAL(3, 2, 0)), /* PCIE20 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PA5, 3, 0x0314, WRITE_MASK_VAL(3, 2, 0)), /* PCIE20 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PD0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 1)), /* PCIE20 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PB0, 4, 0x0314, WRITE_MASK_VAL(3, 2, 2)), /* PCIE20 IO mux M2 */ - RK_MUXROUTE_PMU(0, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(5, 4, 0)), /* PCIE30X1 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PA4, 3, 0x0314, WRITE_MASK_VAL(5, 4, 0)), /* PCIE30X1 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PD2, 4, 0x0314, WRITE_MASK_VAL(5, 4, 1)), /* PCIE30X1 IO mux M1 */ RK_MUXROUTE_GRF(1, RK_PA5, 4, 0x0314, WRITE_MASK_VAL(5, 4, 2)), /* PCIE30X1 IO mux M2 */ - RK_MUXROUTE_PMU(0, RK_PA6, 2, 0x0314, WRITE_MASK_VAL(7, 6, 0)), /* PCIE30X2 IO mux M0 */ + RK_MUXROUTE_GRF(0, RK_PA6, 2, 0x0314, WRITE_MASK_VAL(7, 6, 0)), /* PCIE30X2 IO mux M0 */ RK_MUXROUTE_GRF(2, RK_PD4, 4, 0x0314, WRITE_MASK_VAL(7, 6, 1)), /* PCIE30X2 IO mux M1 */ RK_MUXROUTE_GRF(4, RK_PC2, 4, 0x0314, WRITE_MASK_VAL(7, 6, 2)), /* PCIE30X2 IO mux M2 */ }; @@ -2436,10 +2436,19 @@ static int rockchip_get_pull(struct rockchip_pin_bank *bank, int pin_num) case RK3308: case RK3368: case RK3399: + case RK3568: case RK3588: pull_type = bank->pull_type[pin_num / 8]; data >>= bit; data &= (1 << RK3188_PULL_BITS_PER_PIN) - 1; + /* + * In the TRM, pull-up being 1 for everything except the GPIO0_D3-D6, + * where that pull up value becomes 3. + */ + if (ctrl->type == RK3568 && bank->bank_num == 0 && pin_num >= 27 && pin_num <= 30) { + if (data == 3) + data = 1; + } return rockchip_pull_list[pull_type][data]; default: @@ -2497,7 +2506,7 @@ static int rockchip_set_pull(struct rockchip_pin_bank *bank, } } /* - * In the TRM, pull-up being 1 for everything except the GPIO0_D0-D6, + * In the TRM, pull-up being 1 for everything except the GPIO0_D3-D6, * where that pull up value becomes 3. */ if (ctrl->type == RK3568 && bank->bank_num == 0 && pin_num >= 27 && pin_num <= 30) { diff --git a/drivers/pinctrl/sunplus/sppctl.c b/drivers/pinctrl/sunplus/sppctl.c index 2b3335ab56c6..25101293268f 100644 --- a/drivers/pinctrl/sunplus/sppctl.c +++ b/drivers/pinctrl/sunplus/sppctl.c @@ -499,7 +499,6 @@ static int sppctl_gpio_set_config(struct gpio_chip *chip, unsigned int offset, return 0; } -#ifdef CONFIG_DEBUG_FS static void sppctl_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) { const char *label; @@ -521,7 +520,6 @@ static void sppctl_gpio_dbg_show(struct seq_file *s, struct gpio_chip *chip) seq_puts(s, "\n"); } } -#endif static int sppctl_gpio_new(struct platform_device *pdev, struct sppctl_pdata *pctl) { @@ -550,9 +548,8 @@ static int sppctl_gpio_new(struct platform_device *pdev, struct sppctl_pdata *pc gchip->get = sppctl_gpio_get; gchip->set = sppctl_gpio_set; gchip->set_config = sppctl_gpio_set_config; -#ifdef CONFIG_DEBUG_FS - gchip->dbg_show = sppctl_gpio_dbg_show; -#endif + gchip->dbg_show = IS_ENABLED(CONFIG_DEBUG_FS) ? + sppctl_gpio_dbg_show : NULL; gchip->base = -1; gchip->ngpio = sppctl_gpio_list_sz; gchip->names = sppctl_gpio_list_s; diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c index 43e765199137..c6537a1b3a2e 100644 --- a/drivers/platform/surface/aggregator/controller.c +++ b/drivers/platform/surface/aggregator/controller.c @@ -1700,8 +1700,10 @@ int ssam_request_sync(struct ssam_controller *ctrl, return status; status = ssam_request_sync_init(rqst, spec->flags); - if (status) + if (status) { + ssam_request_sync_free(rqst); return status; + } ssam_request_sync_set_resp(rqst, rsp); diff --git a/drivers/platform/surface/aggregator/ssh_request_layer.c b/drivers/platform/surface/aggregator/ssh_request_layer.c index f5565570f16c..69132976d297 100644 --- a/drivers/platform/surface/aggregator/ssh_request_layer.c +++ b/drivers/platform/surface/aggregator/ssh_request_layer.c @@ -916,6 +916,20 @@ static void ssh_rtl_rx_command(struct ssh_ptl *p, const struct ssam_span *data) if (sshp_parse_command(dev, data, &command, &command_data)) return; + /* + * Check if the message was intended for us. If not, drop it. + * + * Note: We will need to change this to handle debug messages. On newer + * generation devices, these seem to be sent to tid_out=0x03. We as + * host can still receive them as they can be forwarded via an override + * option on SAM, but doing so does not change tid_out=0x00. + */ + if (command->tid_out != 0x00) { + rtl_warn(rtl, "rtl: dropping message not intended for us (tid = %#04x)\n", + command->tid_out); + return; + } + if (ssh_rqid_is_event(get_unaligned_le16(&command->rqid))) ssh_rtl_rx_event(rtl, command, &command_data); else diff --git a/drivers/platform/x86/amd/Kconfig b/drivers/platform/x86/amd/Kconfig index a825af8126c8..2ce8cb2170df 100644 --- a/drivers/platform/x86/amd/Kconfig +++ b/drivers/platform/x86/amd/Kconfig @@ -8,6 +8,7 @@ source "drivers/platform/x86/amd/pmf/Kconfig" config AMD_PMC tristate "AMD SoC PMC driver" depends on ACPI && PCI && RTC_CLASS + select SERIO help The driver provides support for AMD Power Management Controller primarily responsible for S2Idle transactions that are driven from diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c index 439d282aafd1..3cbb01ec10e3 100644 --- a/drivers/platform/x86/amd/pmc.c +++ b/drivers/platform/x86/amd/pmc.c @@ -22,6 +22,7 @@ #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/rtc.h> +#include <linux/serio.h> #include <linux/suspend.h> #include <linux/seq_file.h> #include <linux/uaccess.h> @@ -160,6 +161,10 @@ static bool enable_stb; module_param(enable_stb, bool, 0644); MODULE_PARM_DESC(enable_stb, "Enable the STB debug mechanism"); +static bool disable_workarounds; +module_param(disable_workarounds, bool, 0644); +MODULE_PARM_DESC(disable_workarounds, "Disable workarounds for platform bugs"); + static struct amd_pmc_dev pmc; static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, u32 arg, u32 *data, u8 msg, bool ret); static int amd_pmc_read_stb(struct amd_pmc_dev *dev, u32 *buf); @@ -653,6 +658,33 @@ static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev) return -EINVAL; } +static int amd_pmc_czn_wa_irq1(struct amd_pmc_dev *pdev) +{ + struct device *d; + int rc; + + if (!pdev->major) { + rc = amd_pmc_get_smu_version(pdev); + if (rc) + return rc; + } + + if (pdev->major > 64 || (pdev->major == 64 && pdev->minor > 65)) + return 0; + + d = bus_find_device_by_name(&serio_bus, NULL, "serio0"); + if (!d) + return 0; + if (device_may_wakeup(d)) { + dev_info_once(d, "Disabling IRQ1 wakeup source to avoid platform firmware bug\n"); + disable_irq_wake(1); + device_set_wakeup_enable(d, false); + } + put_device(d); + + return 0; +} + static int amd_pmc_verify_czn_rtc(struct amd_pmc_dev *pdev, u32 *arg) { struct rtc_device *rtc_device; @@ -715,8 +747,8 @@ static void amd_pmc_s2idle_prepare(void) /* Reset and Start SMU logging - to monitor the s0i3 stats */ amd_pmc_setup_smu_logging(pdev); - /* Activate CZN specific RTC functionality */ - if (pdev->cpu_id == AMD_CPU_ID_CZN) { + /* Activate CZN specific platform bug workarounds */ + if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) { rc = amd_pmc_verify_czn_rtc(pdev, &arg); if (rc) { dev_err(pdev->dev, "failed to set RTC: %d\n", rc); @@ -782,6 +814,25 @@ static struct acpi_s2idle_dev_ops amd_pmc_s2idle_dev_ops = { .check = amd_pmc_s2idle_check, .restore = amd_pmc_s2idle_restore, }; + +static int __maybe_unused amd_pmc_suspend_handler(struct device *dev) +{ + struct amd_pmc_dev *pdev = dev_get_drvdata(dev); + + if (pdev->cpu_id == AMD_CPU_ID_CZN && !disable_workarounds) { + int rc = amd_pmc_czn_wa_irq1(pdev); + + if (rc) { + dev_err(pdev->dev, "failed to adjust keyboard wakeup: %d\n", rc); + return rc; + } + } + + return 0; +} + +static SIMPLE_DEV_PM_OPS(amd_pmc_pm, amd_pmc_suspend_handler, NULL); + #endif static const struct pci_device_id pmc_pci_ids[] = { @@ -932,7 +983,7 @@ static int amd_pmc_probe(struct platform_device *pdev) if (enable_stb && (dev->cpu_id == AMD_CPU_ID_YC || dev->cpu_id == AMD_CPU_ID_CB)) { err = amd_pmc_s2d_init(dev); if (err) - return err; + goto err_pci_dev_put; } platform_set_drvdata(pdev, dev); @@ -980,6 +1031,9 @@ static struct platform_driver amd_pmc_driver = { .name = "amd_pmc", .acpi_match_table = amd_pmc_acpi_ids, .dev_groups = pmc_groups, +#ifdef CONFIG_SUSPEND + .pm = &amd_pmc_pm, +#endif }, .probe = amd_pmc_probe, .remove = amd_pmc_remove, diff --git a/drivers/platform/x86/amd/pmf/auto-mode.c b/drivers/platform/x86/amd/pmf/auto-mode.c index 644af42e07cf..96a8e1832c05 100644 --- a/drivers/platform/x86/amd/pmf/auto-mode.c +++ b/drivers/platform/x86/amd/pmf/auto-mode.c @@ -275,13 +275,8 @@ int amd_pmf_reset_amt(struct amd_pmf_dev *dev) */ if (is_apmf_func_supported(dev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) { - int mode = amd_pmf_get_pprof_modes(dev); - - if (mode < 0) - return mode; - dev_dbg(dev->dev, "resetting AMT thermals\n"); - amd_pmf_update_slider(dev, SLIDER_OP_SET, mode, NULL); + amd_pmf_set_sps_power_limits(dev); } return 0; } @@ -299,7 +294,5 @@ void amd_pmf_deinit_auto_mode(struct amd_pmf_dev *dev) void amd_pmf_init_auto_mode(struct amd_pmf_dev *dev) { amd_pmf_load_defaults_auto_mode(dev); - /* update the thermal limits for Automode */ - amd_pmf_set_automode(dev, config_store.current_mode, NULL); amd_pmf_init_metrics_table(dev); } diff --git a/drivers/platform/x86/amd/pmf/cnqf.c b/drivers/platform/x86/amd/pmf/cnqf.c index 3f9731a2ac28..4beb22a19466 100644 --- a/drivers/platform/x86/amd/pmf/cnqf.c +++ b/drivers/platform/x86/amd/pmf/cnqf.c @@ -103,7 +103,7 @@ int amd_pmf_trans_cnqf(struct amd_pmf_dev *dev, int socket_power, ktime_t time_l src = amd_pmf_cnqf_get_power_source(dev); - if (dev->current_profile == PLATFORM_PROFILE_BALANCED) { + if (is_pprof_balanced(dev)) { amd_pmf_set_cnqf(dev, src, config_store.current_mode, NULL); } else { /* @@ -307,13 +307,9 @@ static ssize_t cnqf_enable_store(struct device *dev, const char *buf, size_t count) { struct amd_pmf_dev *pdev = dev_get_drvdata(dev); - int mode, result, src; + int result, src; bool input; - mode = amd_pmf_get_pprof_modes(pdev); - if (mode < 0) - return mode; - result = kstrtobool(buf, &input); if (result) return result; @@ -321,11 +317,11 @@ static ssize_t cnqf_enable_store(struct device *dev, src = amd_pmf_cnqf_get_power_source(pdev); pdev->cnqf_enabled = input; - if (pdev->cnqf_enabled && pdev->current_profile == PLATFORM_PROFILE_BALANCED) { + if (pdev->cnqf_enabled && is_pprof_balanced(pdev)) { amd_pmf_set_cnqf(pdev, src, config_store.current_mode, NULL); } else { if (is_apmf_func_supported(pdev, APMF_FUNC_STATIC_SLIDER_GRANULAR)) - amd_pmf_update_slider(pdev, SLIDER_OP_SET, mode, NULL); + amd_pmf_set_sps_power_limits(pdev); } dev_dbg(pdev->dev, "Received CnQF %s\n", input ? "on" : "off"); @@ -386,7 +382,7 @@ int amd_pmf_init_cnqf(struct amd_pmf_dev *dev) dev->cnqf_enabled = amd_pmf_check_flags(dev); /* update the thermal for CnQF */ - if (dev->cnqf_enabled && dev->current_profile == PLATFORM_PROFILE_BALANCED) { + if (dev->cnqf_enabled && is_pprof_balanced(dev)) { src = amd_pmf_cnqf_get_power_source(dev); amd_pmf_set_cnqf(dev, src, config_store.current_mode, NULL); } diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index a5f5a4bcff6d..da23639071d7 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -58,6 +58,25 @@ static bool force_load; module_param(force_load, bool, 0444); MODULE_PARM_DESC(force_load, "Force load this driver on supported older platforms (experimental)"); +static int amd_pmf_pwr_src_notify_call(struct notifier_block *nb, unsigned long event, void *data) +{ + struct amd_pmf_dev *pmf = container_of(nb, struct amd_pmf_dev, pwr_src_notifier); + + if (event != PSY_EVENT_PROP_CHANGED) + return NOTIFY_OK; + + if (is_apmf_func_supported(pmf, APMF_FUNC_AUTO_MODE) || + is_apmf_func_supported(pmf, APMF_FUNC_DYN_SLIDER_DC) || + is_apmf_func_supported(pmf, APMF_FUNC_DYN_SLIDER_AC)) { + if ((pmf->amt_enabled || pmf->cnqf_enabled) && is_pprof_balanced(pmf)) + return NOTIFY_DONE; + } + + amd_pmf_set_sps_power_limits(pmf); + + return NOTIFY_OK; +} + static int current_power_limits_show(struct seq_file *seq, void *unused) { struct amd_pmf_dev *dev = seq->private; @@ -366,14 +385,18 @@ static int amd_pmf_probe(struct platform_device *pdev) if (!dev->regbase) return -ENOMEM; + mutex_init(&dev->lock); + mutex_init(&dev->update_mutex); + apmf_acpi_init(dev); platform_set_drvdata(pdev, dev); amd_pmf_init_features(dev); apmf_install_handler(dev); amd_pmf_dbgfs_register(dev); - mutex_init(&dev->lock); - mutex_init(&dev->update_mutex); + dev->pwr_src_notifier.notifier_call = amd_pmf_pwr_src_notify_call; + power_supply_reg_notifier(&dev->pwr_src_notifier); + dev_info(dev->dev, "registered PMF device successfully\n"); return 0; @@ -383,11 +406,12 @@ static int amd_pmf_remove(struct platform_device *pdev) { struct amd_pmf_dev *dev = platform_get_drvdata(pdev); - mutex_destroy(&dev->lock); - mutex_destroy(&dev->update_mutex); + power_supply_unreg_notifier(&dev->pwr_src_notifier); amd_pmf_deinit_features(dev); apmf_acpi_deinit(dev); amd_pmf_dbgfs_unregister(dev); + mutex_destroy(&dev->lock); + mutex_destroy(&dev->update_mutex); kfree(dev->buf); return 0; } diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h index 84bbe2c6ea61..06c30cdc0573 100644 --- a/drivers/platform/x86/amd/pmf/pmf.h +++ b/drivers/platform/x86/amd/pmf/pmf.h @@ -169,6 +169,7 @@ struct amd_pmf_dev { struct mutex update_mutex; /* protects race between ACPI handler and metrics thread */ bool cnqf_enabled; bool cnqf_supported; + struct notifier_block pwr_src_notifier; }; struct apmf_sps_prop_granular { @@ -391,9 +392,11 @@ int amd_pmf_init_sps(struct amd_pmf_dev *dev); void amd_pmf_deinit_sps(struct amd_pmf_dev *dev); int apmf_get_static_slider_granular(struct amd_pmf_dev *pdev, struct apmf_static_slider_granular_output *output); +bool is_pprof_balanced(struct amd_pmf_dev *pmf); int apmf_update_fan_idx(struct amd_pmf_dev *pdev, bool manual, u32 idx); +int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf); /* Auto Mode Layer */ int apmf_get_auto_mode_def(struct amd_pmf_dev *pdev, struct apmf_auto_mode *data); diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c index dba7e36962dc..bed762d47a14 100644 --- a/drivers/platform/x86/amd/pmf/sps.c +++ b/drivers/platform/x86/amd/pmf/sps.c @@ -70,6 +70,24 @@ void amd_pmf_update_slider(struct amd_pmf_dev *dev, bool op, int idx, } } +int amd_pmf_set_sps_power_limits(struct amd_pmf_dev *pmf) +{ + int mode; + + mode = amd_pmf_get_pprof_modes(pmf); + if (mode < 0) + return mode; + + amd_pmf_update_slider(pmf, SLIDER_OP_SET, mode, NULL); + + return 0; +} + +bool is_pprof_balanced(struct amd_pmf_dev *pmf) +{ + return (pmf->current_profile == PLATFORM_PROFILE_BALANCED) ? true : false; +} + static int amd_pmf_profile_get(struct platform_profile_handler *pprof, enum platform_profile_option *profile) { @@ -105,15 +123,10 @@ static int amd_pmf_profile_set(struct platform_profile_handler *pprof, enum platform_profile_option profile) { struct amd_pmf_dev *pmf = container_of(pprof, struct amd_pmf_dev, pprof); - int mode; pmf->current_profile = profile; - mode = amd_pmf_get_pprof_modes(pmf); - if (mode < 0) - return mode; - amd_pmf_update_slider(pmf, SLIDER_OP_SET, mode, NULL); - return 0; + return amd_pmf_set_sps_power_limits(pmf); } int amd_pmf_init_sps(struct amd_pmf_dev *dev) @@ -123,6 +136,9 @@ int amd_pmf_init_sps(struct amd_pmf_dev *dev) dev->current_profile = PLATFORM_PROFILE_BALANCED; amd_pmf_load_defaults_sps(dev); + /* update SPS balanced power mode thermals */ + amd_pmf_set_sps_power_limits(dev); + dev->pprof.profile_get = amd_pmf_profile_get; dev->pprof.profile_set = amd_pmf_profile_set; diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c index ca33df7ea550..9333f82cfa8a 100644 --- a/drivers/platform/x86/apple-gmux.c +++ b/drivers/platform/x86/apple-gmux.c @@ -64,29 +64,6 @@ struct apple_gmux_data { static struct apple_gmux_data *apple_gmux_data; -/* - * gmux port offsets. Many of these are not yet used, but may be in the - * future, and it's useful to have them documented here anyhow. - */ -#define GMUX_PORT_VERSION_MAJOR 0x04 -#define GMUX_PORT_VERSION_MINOR 0x05 -#define GMUX_PORT_VERSION_RELEASE 0x06 -#define GMUX_PORT_SWITCH_DISPLAY 0x10 -#define GMUX_PORT_SWITCH_GET_DISPLAY 0x11 -#define GMUX_PORT_INTERRUPT_ENABLE 0x14 -#define GMUX_PORT_INTERRUPT_STATUS 0x16 -#define GMUX_PORT_SWITCH_DDC 0x28 -#define GMUX_PORT_SWITCH_EXTERNAL 0x40 -#define GMUX_PORT_SWITCH_GET_EXTERNAL 0x41 -#define GMUX_PORT_DISCRETE_POWER 0x50 -#define GMUX_PORT_MAX_BRIGHTNESS 0x70 -#define GMUX_PORT_BRIGHTNESS 0x74 -#define GMUX_PORT_VALUE 0xc2 -#define GMUX_PORT_READ 0xd0 -#define GMUX_PORT_WRITE 0xd4 - -#define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4) - #define GMUX_INTERRUPT_ENABLE 0xff #define GMUX_INTERRUPT_DISABLE 0x00 @@ -249,23 +226,6 @@ static void gmux_write32(struct apple_gmux_data *gmux_data, int port, gmux_pio_write32(gmux_data, port, val); } -static bool gmux_is_indexed(struct apple_gmux_data *gmux_data) -{ - u16 val; - - outb(0xaa, gmux_data->iostart + 0xcc); - outb(0x55, gmux_data->iostart + 0xcd); - outb(0x00, gmux_data->iostart + 0xce); - - val = inb(gmux_data->iostart + 0xcc) | - (inb(gmux_data->iostart + 0xcd) << 8); - - if (val == 0x55aa) - return true; - - return false; -} - /** * DOC: Backlight control * @@ -605,60 +565,43 @@ static int gmux_probe(struct pnp_dev *pnp, const struct pnp_device_id *id) int ret = -ENXIO; acpi_status status; unsigned long long gpe; + bool indexed = false; + u32 version; if (apple_gmux_data) return -EBUSY; + if (!apple_gmux_detect(pnp, &indexed)) { + pr_info("gmux device not present\n"); + return -ENODEV; + } + gmux_data = kzalloc(sizeof(*gmux_data), GFP_KERNEL); if (!gmux_data) return -ENOMEM; pnp_set_drvdata(pnp, gmux_data); res = pnp_get_resource(pnp, IORESOURCE_IO, 0); - if (!res) { - pr_err("Failed to find gmux I/O resource\n"); - goto err_free; - } - gmux_data->iostart = res->start; gmux_data->iolen = resource_size(res); - if (gmux_data->iolen < GMUX_MIN_IO_LEN) { - pr_err("gmux I/O region too small (%lu < %u)\n", - gmux_data->iolen, GMUX_MIN_IO_LEN); - goto err_free; - } - if (!request_region(gmux_data->iostart, gmux_data->iolen, "Apple gmux")) { pr_err("gmux I/O already in use\n"); goto err_free; } - /* - * Invalid version information may indicate either that the gmux - * device isn't present or that it's a new one that uses indexed - * io - */ - - ver_major = gmux_read8(gmux_data, GMUX_PORT_VERSION_MAJOR); - ver_minor = gmux_read8(gmux_data, GMUX_PORT_VERSION_MINOR); - ver_release = gmux_read8(gmux_data, GMUX_PORT_VERSION_RELEASE); - if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) { - if (gmux_is_indexed(gmux_data)) { - u32 version; - mutex_init(&gmux_data->index_lock); - gmux_data->indexed = true; - version = gmux_read32(gmux_data, - GMUX_PORT_VERSION_MAJOR); - ver_major = (version >> 24) & 0xff; - ver_minor = (version >> 16) & 0xff; - ver_release = (version >> 8) & 0xff; - } else { - pr_info("gmux device not present\n"); - ret = -ENODEV; - goto err_release; - } + if (indexed) { + mutex_init(&gmux_data->index_lock); + gmux_data->indexed = true; + version = gmux_read32(gmux_data, GMUX_PORT_VERSION_MAJOR); + ver_major = (version >> 24) & 0xff; + ver_minor = (version >> 16) & 0xff; + ver_release = (version >> 8) & 0xff; + } else { + ver_major = gmux_read8(gmux_data, GMUX_PORT_VERSION_MAJOR); + ver_minor = gmux_read8(gmux_data, GMUX_PORT_VERSION_MINOR); + ver_release = gmux_read8(gmux_data, GMUX_PORT_VERSION_RELEASE); } pr_info("Found gmux version %d.%d.%d [%s]\n", ver_major, ver_minor, ver_release, (gmux_data->indexed ? "indexed" : "classic")); diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index c685a705b73d..cb15acdf14a3 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -121,6 +121,10 @@ static struct quirk_entry quirk_asus_tablet_mode = { .tablet_switch_mode = asus_wmi_lid_flip_rog_devid, }; +static struct quirk_entry quirk_asus_ignore_fan = { + .wmi_ignore_fan = true, +}; + static int dmi_matched(const struct dmi_system_id *dmi) { pr_info("Identified laptop model '%s'\n", dmi->ident); @@ -473,6 +477,15 @@ static const struct dmi_system_id asus_quirks[] = { }, .driver_data = &quirk_asus_tablet_mode, }, + { + .callback = dmi_matched, + .ident = "ASUS VivoBook E410MA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "E410MA"), + }, + .driver_data = &quirk_asus_ignore_fan, + }, {}, }; @@ -511,6 +524,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x30, { KEY_VOLUMEUP } }, { KE_KEY, 0x31, { KEY_VOLUMEDOWN } }, { KE_KEY, 0x32, { KEY_MUTE } }, + { KE_KEY, 0x33, { KEY_SCREENLOCK } }, { KE_KEY, 0x35, { KEY_SCREENLOCK } }, { KE_KEY, 0x38, { KEY_PROG3 } }, /* Armoury Crate */ { KE_KEY, 0x40, { KEY_PREVIOUSSONG } }, @@ -544,6 +558,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x7D, { KEY_BLUETOOTH } }, /* Bluetooth Enable */ { KE_KEY, 0x7E, { KEY_BLUETOOTH } }, /* Bluetooth Disable */ { KE_KEY, 0x82, { KEY_CAMERA } }, + { KE_KEY, 0x85, { KEY_CAMERA } }, { KE_KEY, 0x86, { KEY_PROG1 } }, /* MyASUS Key */ { KE_KEY, 0x88, { KEY_RFKILL } }, /* Radio Toggle Key */ { KE_KEY, 0x8A, { KEY_PROG1 } }, /* Color enhancement mode */ diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 6f81b2844dcb..1038dfdcdd32 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -225,6 +225,7 @@ struct asus_wmi { int tablet_switch_event_code; u32 tablet_switch_dev_id; + bool tablet_switch_inverted; enum fan_type fan_type; enum fan_type gpu_fan_type; @@ -493,6 +494,13 @@ static bool asus_wmi_dev_is_present(struct asus_wmi *asus, u32 dev_id) } /* Input **********************************************************************/ +static void asus_wmi_tablet_sw_report(struct asus_wmi *asus, bool value) +{ + input_report_switch(asus->inputdev, SW_TABLET_MODE, + asus->tablet_switch_inverted ? !value : value); + input_sync(asus->inputdev); +} + static void asus_wmi_tablet_sw_init(struct asus_wmi *asus, u32 dev_id, int event_code) { struct device *dev = &asus->platform_device->dev; @@ -501,7 +509,7 @@ static void asus_wmi_tablet_sw_init(struct asus_wmi *asus, u32 dev_id, int event result = asus_wmi_get_devstate_simple(asus, dev_id); if (result >= 0) { input_set_capability(asus->inputdev, EV_SW, SW_TABLET_MODE); - input_report_switch(asus->inputdev, SW_TABLET_MODE, result); + asus_wmi_tablet_sw_report(asus, result); asus->tablet_switch_dev_id = dev_id; asus->tablet_switch_event_code = event_code; } else if (result == -ENODEV) { @@ -534,6 +542,7 @@ static int asus_wmi_input_init(struct asus_wmi *asus) case asus_wmi_no_tablet_switch: break; case asus_wmi_kbd_dock_devid: + asus->tablet_switch_inverted = true; asus_wmi_tablet_sw_init(asus, ASUS_WMI_DEVID_KBD_DOCK, NOTIFY_KBD_DOCK_CHANGE); break; case asus_wmi_lid_flip_devid: @@ -573,10 +582,8 @@ static void asus_wmi_tablet_mode_get_state(struct asus_wmi *asus) return; result = asus_wmi_get_devstate_simple(asus, asus->tablet_switch_dev_id); - if (result >= 0) { - input_report_switch(asus->inputdev, SW_TABLET_MODE, result); - input_sync(asus->inputdev); - } + if (result >= 0) + asus_wmi_tablet_sw_report(asus, result); } /* dGPU ********************************************************************/ @@ -2243,7 +2250,9 @@ static int asus_wmi_fan_init(struct asus_wmi *asus) asus->fan_type = FAN_TYPE_NONE; asus->agfn_pwm = -1; - if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL)) + if (asus->driver->quirks->wmi_ignore_fan) + asus->fan_type = FAN_TYPE_NONE; + else if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_CPU_FAN_CTRL)) asus->fan_type = FAN_TYPE_SPEC83; else if (asus_wmi_has_agfn_fan(asus)) asus->fan_type = FAN_TYPE_AGFN; @@ -2436,6 +2445,9 @@ static int fan_curve_check_present(struct asus_wmi *asus, bool *available, *available = false; + if (asus->fan_type == FAN_TYPE_NONE) + return 0; + err = fan_curve_get_factory_default(asus, fan_dev); if (err) { return 0; diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h index 65316998b898..a478ebfd34df 100644 --- a/drivers/platform/x86/asus-wmi.h +++ b/drivers/platform/x86/asus-wmi.h @@ -38,6 +38,7 @@ struct quirk_entry { bool store_backlight_power; bool wmi_backlight_set_devstate; bool wmi_force_als_set; + bool wmi_ignore_fan; enum asus_wmi_tablet_switch_mode tablet_switch_mode; int wapf; /* diff --git a/drivers/platform/x86/dell/dell-wmi-base.c b/drivers/platform/x86/dell/dell-wmi-base.c index 0a259a27459f..502783a7adb1 100644 --- a/drivers/platform/x86/dell/dell-wmi-base.c +++ b/drivers/platform/x86/dell/dell-wmi-base.c @@ -261,6 +261,9 @@ static const struct key_entry dell_wmi_keymap_type_0010[] = { { KE_KEY, 0x57, { KEY_BRIGHTNESSDOWN } }, { KE_KEY, 0x58, { KEY_BRIGHTNESSUP } }, + /*Speaker Mute*/ + { KE_KEY, 0x109, { KEY_MUTE} }, + /* Mic mute */ { KE_KEY, 0x150, { KEY_MICMUTE } }, diff --git a/drivers/platform/x86/dell/dell-wmi-privacy.c b/drivers/platform/x86/dell/dell-wmi-privacy.c index c82b3d6867c5..c517bd45dd32 100644 --- a/drivers/platform/x86/dell/dell-wmi-privacy.c +++ b/drivers/platform/x86/dell/dell-wmi-privacy.c @@ -61,7 +61,7 @@ static const struct key_entry dell_wmi_keymap_type_0012[] = { /* privacy mic mute */ { KE_KEY, 0x0001, { KEY_MICMUTE } }, /* privacy camera mute */ - { KE_SW, 0x0002, { SW_CAMERA_LENS_COVER } }, + { KE_VSW, 0x0002, { SW_CAMERA_LENS_COVER } }, { KE_END, 0}, }; @@ -115,11 +115,15 @@ bool dell_privacy_process_event(int type, int code, int status) switch (code) { case DELL_PRIVACY_AUDIO_EVENT: /* Mic mute */ - case DELL_PRIVACY_CAMERA_EVENT: /* Camera mute */ priv->last_status = status; sparse_keymap_report_entry(priv->input_dev, key, 1, true); ret = true; break; + case DELL_PRIVACY_CAMERA_EVENT: /* Camera mute */ + priv->last_status = status; + sparse_keymap_report_entry(priv->input_dev, key, !(status & CAMERA_STATUS), false); + ret = true; + break; default: dev_dbg(&priv->wdev->dev, "unknown event type 0x%04x 0x%04x\n", type, code); } @@ -292,7 +296,7 @@ static int dell_privacy_wmi_probe(struct wmi_device *wdev, const void *context) { struct privacy_wmi_data *priv; struct key_entry *keymap; - int ret, i; + int ret, i, j; ret = wmi_has_guid(DELL_PRIVACY_GUID); if (!ret) @@ -304,6 +308,11 @@ static int dell_privacy_wmi_probe(struct wmi_device *wdev, const void *context) dev_set_drvdata(&wdev->dev, priv); priv->wdev = wdev; + + ret = get_current_status(priv->wdev); + if (ret) + return ret; + /* create evdev passing interface */ priv->input_dev = devm_input_allocate_device(&wdev->dev); if (!priv->input_dev) @@ -318,9 +327,20 @@ static int dell_privacy_wmi_probe(struct wmi_device *wdev, const void *context) /* remap the keymap code with Dell privacy key type 0x12 as prefix * KEY_MICMUTE scancode will be reported as 0x120001 */ - for (i = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0012); i++) { - keymap[i] = dell_wmi_keymap_type_0012[i]; - keymap[i].code |= (0x0012 << 16); + for (i = 0, j = 0; i < ARRAY_SIZE(dell_wmi_keymap_type_0012); i++) { + /* + * Unlike keys where only presses matter, userspace may act + * on switches in both of their positions. Only register + * SW_CAMERA_LENS_COVER if it is actually there. + */ + if (dell_wmi_keymap_type_0012[i].type == KE_VSW && + dell_wmi_keymap_type_0012[i].sw.code == SW_CAMERA_LENS_COVER && + !(priv->features_present & BIT(DELL_PRIVACY_TYPE_CAMERA))) + continue; + + keymap[j] = dell_wmi_keymap_type_0012[i]; + keymap[j].code |= (0x0012 << 16); + j++; } ret = sparse_keymap_setup(priv->input_dev, keymap, NULL); kfree(keymap); @@ -331,11 +351,12 @@ static int dell_privacy_wmi_probe(struct wmi_device *wdev, const void *context) priv->input_dev->name = "Dell Privacy Driver"; priv->input_dev->id.bustype = BUS_HOST; - ret = input_register_device(priv->input_dev); - if (ret) - return ret; + /* Report initial camera-cover status */ + if (priv->features_present & BIT(DELL_PRIVACY_TYPE_CAMERA)) + input_report_switch(priv->input_dev, SW_CAMERA_LENS_COVER, + !(priv->last_status & CAMERA_STATUS)); - ret = get_current_status(priv->wdev); + ret = input_register_device(priv->input_dev); if (ret) return ret; diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c index 5e7e6659a849..322cfaeda17b 100644 --- a/drivers/platform/x86/gigabyte-wmi.c +++ b/drivers/platform/x86/gigabyte-wmi.c @@ -141,6 +141,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev) static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = { DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H-CF"), + DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M DS3H WIFI-CF"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B450M S2H V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE AX V2"), DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"), diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 0a99058be813..2ef201b625b3 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -90,6 +90,7 @@ enum hp_wmi_event_ids { HPWMI_PEAKSHIFT_PERIOD = 0x0F, HPWMI_BATTERY_CHARGE_PERIOD = 0x10, HPWMI_SANITIZATION_MODE = 0x17, + HPWMI_OMEN_KEY = 0x1D, HPWMI_SMART_EXPERIENCE_APP = 0x21, }; @@ -216,6 +217,8 @@ static const struct key_entry hp_wmi_keymap[] = { { KE_KEY, 0x213b, { KEY_INFO } }, { KE_KEY, 0x2169, { KEY_ROTATE_DISPLAY } }, { KE_KEY, 0x216a, { KEY_SETUP } }, + { KE_KEY, 0x21a5, { KEY_PROG2 } }, /* HP Omen Key */ + { KE_KEY, 0x21a7, { KEY_FN_ESC } }, { KE_KEY, 0x21a9, { KEY_TOUCHPAD_OFF } }, { KE_KEY, 0x121a9, { KEY_TOUCHPAD_ON } }, { KE_KEY, 0x231b, { KEY_HELP } }, @@ -548,7 +551,7 @@ static int __init hp_wmi_enable_hotkeys(void) static int hp_wmi_set_block(void *data, bool blocked) { - enum hp_wmi_radio r = (enum hp_wmi_radio) data; + enum hp_wmi_radio r = (long)data; int query = BIT(r + 8) | ((!blocked) << r); int ret; @@ -810,6 +813,7 @@ static void hp_wmi_notify(u32 value, void *context) case HPWMI_SMART_ADAPTER: break; case HPWMI_BEZEL_BUTTON: + case HPWMI_OMEN_KEY: key_code = hp_wmi_read_int(HPWMI_HOTKEY_QUERY); if (key_code < 0) break; diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index 435d2d3d903b..0eb5bfdd823a 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1621,6 +1621,12 @@ static const struct dmi_system_id set_fn_lock_led_list[] = { DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Legion R7000P2020H"), } }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo Legion 5 15ARH05"), + } + }, {} }; diff --git a/drivers/platform/x86/intel/int3472/clk_and_regulator.c b/drivers/platform/x86/intel/int3472/clk_and_regulator.c index b2342b3d78c7..74dc2cff799e 100644 --- a/drivers/platform/x86/intel/int3472/clk_and_regulator.c +++ b/drivers/platform/x86/intel/int3472/clk_and_regulator.c @@ -181,6 +181,9 @@ int skl_int3472_register_regulator(struct int3472_discrete_device *int3472, return PTR_ERR(int3472->regulator.gpio); } + /* Ensure the pin is in output mode and non-active state */ + gpiod_direction_output(int3472->regulator.gpio, 0); + cfg.dev = &int3472->adev->dev; cfg.init_data = &init_data; cfg.ena_gpiod = int3472->regulator.gpio; diff --git a/drivers/platform/x86/intel/int3472/discrete.c b/drivers/platform/x86/intel/int3472/discrete.c index 974a132db651..c42c3faa2c32 100644 --- a/drivers/platform/x86/intel/int3472/discrete.c +++ b/drivers/platform/x86/intel/int3472/discrete.c @@ -168,6 +168,8 @@ static int skl_int3472_map_gpio_to_clk(struct int3472_discrete_device *int3472, return (PTR_ERR(gpio)); int3472->clock.ena_gpio = gpio; + /* Ensure the pin is in output mode and non-active state */ + gpiod_direction_output(int3472->clock.ena_gpio, 0); break; case INT3472_GPIO_TYPE_PRIVACY_LED: gpio = acpi_get_and_request_gpiod(path, pin, "int3472,privacy-led"); @@ -175,6 +177,8 @@ static int skl_int3472_map_gpio_to_clk(struct int3472_discrete_device *int3472, return (PTR_ERR(gpio)); int3472->clock.led_gpio = gpio; + /* Ensure the pin is in output mode and non-active state */ + gpiod_direction_output(int3472->clock.led_gpio, 0); break; default: dev_err(int3472->dev, "Invalid GPIO type 0x%02x for clock\n", type); diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index f1d802f6ec3f..3a15d32d7644 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -1029,6 +1029,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = { X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, adl_core_init), X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, adl_core_init), X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE, mtl_core_init), + X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, mtl_core_init), {} }; diff --git a/drivers/platform/x86/simatic-ipc.c b/drivers/platform/x86/simatic-ipc.c index ca76076fc706..b3622419cd1a 100644 --- a/drivers/platform/x86/simatic-ipc.c +++ b/drivers/platform/x86/simatic-ipc.c @@ -46,7 +46,8 @@ static struct { {SIMATIC_IPC_IPC427D, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_NONE}, {SIMATIC_IPC_IPC427E, SIMATIC_IPC_DEVICE_427E, SIMATIC_IPC_DEVICE_427E}, {SIMATIC_IPC_IPC477E, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_427E}, - {SIMATIC_IPC_IPC427G, SIMATIC_IPC_DEVICE_227G, SIMATIC_IPC_DEVICE_227G}, + {SIMATIC_IPC_IPCBX_39A, SIMATIC_IPC_DEVICE_227G, SIMATIC_IPC_DEVICE_227G}, + {SIMATIC_IPC_IPCPX_39A, SIMATIC_IPC_DEVICE_NONE, SIMATIC_IPC_DEVICE_227G}, }; static int register_platform_devices(u32 station_id) diff --git a/drivers/platform/x86/sony-laptop.c b/drivers/platform/x86/sony-laptop.c index 7156ae2ad196..537d6a2d0781 100644 --- a/drivers/platform/x86/sony-laptop.c +++ b/drivers/platform/x86/sony-laptop.c @@ -1887,14 +1887,21 @@ static int sony_nc_kbd_backlight_setup(struct platform_device *pd, break; } - ret = sony_call_snc_handle(handle, probe_base, &result); - if (ret) - return ret; + /* + * Only probe if there is a separate probe_base, otherwise the probe call + * is equivalent to __sony_nc_kbd_backlight_mode_set(0), resulting in + * the keyboard backlight being turned off. + */ + if (probe_base) { + ret = sony_call_snc_handle(handle, probe_base, &result); + if (ret) + return ret; - if ((handle == 0x0137 && !(result & 0x02)) || - !(result & 0x01)) { - dprintk("no backlight keyboard found\n"); - return 0; + if ((handle == 0x0137 && !(result & 0x02)) || + !(result & 0x01)) { + dprintk("no backlight keyboard found\n"); + return 0; + } } kbdbl_ctl = kzalloc(sizeof(*kbdbl_ctl), GFP_KERNEL); diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 1195293b22fd..32c10457399e 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -5563,7 +5563,7 @@ static int light_sysfs_set(struct led_classdev *led_cdev, static enum led_brightness light_sysfs_get(struct led_classdev *led_cdev) { - return (light_get_status() == 1) ? LED_FULL : LED_OFF; + return (light_get_status() == 1) ? LED_ON : LED_OFF; } static struct tpacpi_led_classdev tpacpi_led_thinklight = { @@ -10311,9 +10311,11 @@ static DEFINE_MUTEX(dytc_mutex); static int dytc_capabilities; static bool dytc_mmc_get_available; -static int convert_dytc_to_profile(int dytcmode, enum platform_profile_option *profile) +static int convert_dytc_to_profile(int funcmode, int dytcmode, + enum platform_profile_option *profile) { - if (dytc_capabilities & BIT(DYTC_FC_MMC)) { + switch (funcmode) { + case DYTC_FUNCTION_MMC: switch (dytcmode) { case DYTC_MODE_MMC_LOWPOWER: *profile = PLATFORM_PROFILE_LOW_POWER; @@ -10329,8 +10331,7 @@ static int convert_dytc_to_profile(int dytcmode, enum platform_profile_option *p return -EINVAL; } return 0; - } - if (dytc_capabilities & BIT(DYTC_FC_PSC)) { + case DYTC_FUNCTION_PSC: switch (dytcmode) { case DYTC_MODE_PSC_LOWPOWER: *profile = PLATFORM_PROFILE_LOW_POWER; @@ -10344,6 +10345,14 @@ static int convert_dytc_to_profile(int dytcmode, enum platform_profile_option *p default: /* Unknown mode */ return -EINVAL; } + return 0; + case DYTC_FUNCTION_AMT: + /* For now return balanced. It's the closest we have to 'auto' */ + *profile = PLATFORM_PROFILE_BALANCED; + return 0; + default: + /* Unknown function */ + return -EOPNOTSUPP; } return 0; } @@ -10487,11 +10496,11 @@ static int dytc_profile_set(struct platform_profile_handler *pprof, if (err) goto unlock; } - } - if (dytc_capabilities & BIT(DYTC_FC_PSC)) { + } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) { err = dytc_command(DYTC_SET_COMMAND(DYTC_FUNCTION_PSC, perfmode, 1), &output); if (err) goto unlock; + /* system supports AMT, activate it when on balanced */ if (dytc_capabilities & BIT(DYTC_FC_AMT)) dytc_control_amt(profile == PLATFORM_PROFILE_BALANCED); @@ -10507,7 +10516,7 @@ static void dytc_profile_refresh(void) { enum platform_profile_option profile; int output, err = 0; - int perfmode; + int perfmode, funcmode; mutex_lock(&dytc_mutex); if (dytc_capabilities & BIT(DYTC_FC_MMC)) { @@ -10515,15 +10524,18 @@ static void dytc_profile_refresh(void) err = dytc_command(DYTC_CMD_MMC_GET, &output); else err = dytc_cql_command(DYTC_CMD_GET, &output); - } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) + funcmode = DYTC_FUNCTION_MMC; + } else if (dytc_capabilities & BIT(DYTC_FC_PSC)) { err = dytc_command(DYTC_CMD_GET, &output); - + /* Check if we are PSC mode, or have AMT enabled */ + funcmode = (output >> DYTC_GET_FUNCTION_BIT) & 0xF; + } mutex_unlock(&dytc_mutex); if (err) return; perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF; - convert_dytc_to_profile(perfmode, &profile); + convert_dytc_to_profile(funcmode, perfmode, &profile); if (profile != dytc_current_profile) { dytc_current_profile = profile; platform_profile_notify(); diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index baae3120efd0..13802a3c3591 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -264,6 +264,23 @@ static const struct ts_dmi_data connect_tablet9_data = { .properties = connect_tablet9_props, }; +static const struct property_entry csl_panther_tab_hd_props[] = { + PROPERTY_ENTRY_U32("touchscreen-min-x", 1), + PROPERTY_ENTRY_U32("touchscreen-min-y", 20), + PROPERTY_ENTRY_U32("touchscreen-size-x", 1980), + PROPERTY_ENTRY_U32("touchscreen-size-y", 1526), + PROPERTY_ENTRY_BOOL("touchscreen-inverted-y"), + PROPERTY_ENTRY_BOOL("touchscreen-swapped-x-y"), + PROPERTY_ENTRY_STRING("firmware-name", "gsl1680-csl-panther-tab-hd.fw"), + PROPERTY_ENTRY_U32("silead,max-fingers", 10), + { } +}; + +static const struct ts_dmi_data csl_panther_tab_hd_data = { + .acpi_name = "MSSL1680:00", + .properties = csl_panther_tab_hd_props, +}; + static const struct property_entry cube_iwork8_air_props[] = { PROPERTY_ENTRY_U32("touchscreen-min-x", 1), PROPERTY_ENTRY_U32("touchscreen-min-y", 3), @@ -1081,6 +1098,15 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* Chuwi Vi8 (CWI501) */ + .driver_data = (void *)&chuwi_vi8_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_MATCH(DMI_PRODUCT_NAME, "i86"), + DMI_MATCH(DMI_BIOS_VERSION, "CHUWI.W86JLBNR01"), + }, + }, + { /* Chuwi Vi8 (CWI506) */ .driver_data = (void *)&chuwi_vi8_data, .matches = { @@ -1125,6 +1151,14 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, }, { + /* CSL Panther Tab HD */ + .driver_data = (void *)&csl_panther_tab_hd_data, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "CSL Computer GmbH & Co. KG"), + DMI_MATCH(DMI_PRODUCT_NAME, "CSL Panther Tab HD"), + }, + }, + { /* CUBE iwork8 Air */ .driver_data = (void *)&cube_iwork8_air_data, .matches = { diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c index e01b32d1fa17..00828f5baa97 100644 --- a/drivers/regulator/da9211-regulator.c +++ b/drivers/regulator/da9211-regulator.c @@ -498,6 +498,12 @@ static int da9211_i2c_probe(struct i2c_client *i2c) chip->chip_irq = i2c->irq; + ret = da9211_regulator_init(chip); + if (ret < 0) { + dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); + return ret; + } + if (chip->chip_irq != 0) { ret = devm_request_threaded_irq(chip->dev, chip->chip_irq, NULL, da9211_irq_handler, @@ -512,11 +518,6 @@ static int da9211_i2c_probe(struct i2c_client *i2c) dev_warn(chip->dev, "No IRQ configured\n"); } - ret = da9211_regulator_init(chip); - - if (ret < 0) - dev_err(chip->dev, "Failed to initialize regulator: %d\n", ret); - return ret; } diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c index 43b5b9377714..ae6021390143 100644 --- a/drivers/regulator/qcom-rpmh-regulator.c +++ b/drivers/regulator/qcom-rpmh-regulator.c @@ -1016,7 +1016,7 @@ static const struct rpmh_vreg_init_data pm8550_vreg_data[] = { RPMH_VREG("ldo8", "ldo%s8", &pmic5_pldo_lv, "vdd-l8-l9"), RPMH_VREG("ldo9", "ldo%s9", &pmic5_pldo, "vdd-l8-l9"), RPMH_VREG("ldo10", "ldo%s10", &pmic5_nldo, "vdd-l1-l4-l10"), - RPMH_VREG("ldo11", "ldo%s11", &pmic5_pldo, "vdd-l11"), + RPMH_VREG("ldo11", "ldo%s11", &pmic5_nldo, "vdd-l11"), RPMH_VREG("ldo12", "ldo%s12", &pmic5_pldo, "vdd-l12"), RPMH_VREG("ldo13", "ldo%s13", &pmic5_pldo, "vdd-l2-l13-l14"), RPMH_VREG("ldo14", "ldo%s14", &pmic5_pldo, "vdd-l2-l13-l14"), diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig index de176c2fbad9..2a52c990d4fe 100644 --- a/drivers/reset/Kconfig +++ b/drivers/reset/Kconfig @@ -257,7 +257,7 @@ config RESET_SUNXI config RESET_TI_SCI tristate "TI System Control Interface (TI-SCI) reset driver" - depends on TI_SCI_PROTOCOL || COMPILE_TEST + depends on TI_SCI_PROTOCOL || (COMPILE_TEST && TI_SCI_PROTOCOL=n) help This enables the reset driver support over TI System Control Interface available on some new TI's SoCs. If you wish to use reset resources diff --git a/drivers/reset/reset-uniphier-glue.c b/drivers/reset/reset-uniphier-glue.c index 146fd5d45e99..15abac9fc72c 100644 --- a/drivers/reset/reset-uniphier-glue.c +++ b/drivers/reset/reset-uniphier-glue.c @@ -47,7 +47,6 @@ static int uniphier_glue_reset_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; struct uniphier_glue_reset_priv *priv; struct resource *res; - resource_size_t size; int i, ret; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); @@ -60,7 +59,6 @@ static int uniphier_glue_reset_probe(struct platform_device *pdev) return -EINVAL; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - size = resource_size(res); priv->rdata.membase = devm_ioremap_resource(dev, res); if (IS_ERR(priv->rdata.membase)) return PTR_ERR(priv->rdata.membase); @@ -96,7 +94,7 @@ static int uniphier_glue_reset_probe(struct platform_device *pdev) spin_lock_init(&priv->rdata.lock); priv->rdata.rcdev.owner = THIS_MODULE; - priv->rdata.rcdev.nr_resets = size * BITS_PER_BYTE; + priv->rdata.rcdev.nr_resets = resource_size(res) * BITS_PER_BYTE; priv->rdata.rcdev.ops = &reset_simple_ops; priv->rdata.rcdev.of_node = dev->of_node; priv->rdata.active_low = true; diff --git a/drivers/rtc/rtc-efi.c b/drivers/rtc/rtc-efi.c index e991cccdb6e9..1e8bc6cc1e12 100644 --- a/drivers/rtc/rtc-efi.c +++ b/drivers/rtc/rtc-efi.c @@ -188,9 +188,10 @@ static int efi_set_time(struct device *dev, struct rtc_time *tm) static int efi_procfs(struct device *dev, struct seq_file *seq) { - efi_time_t eft, alm; - efi_time_cap_t cap; - efi_bool_t enabled, pending; + efi_time_t eft, alm; + efi_time_cap_t cap; + efi_bool_t enabled, pending; + struct rtc_device *rtc = dev_get_drvdata(dev); memset(&eft, 0, sizeof(eft)); memset(&alm, 0, sizeof(alm)); @@ -213,23 +214,25 @@ static int efi_procfs(struct device *dev, struct seq_file *seq) /* XXX fixme: convert to string? */ seq_printf(seq, "Timezone\t: %u\n", eft.timezone); - seq_printf(seq, - "Alarm Time\t: %u:%u:%u.%09u\n" - "Alarm Date\t: %u-%u-%u\n" - "Alarm Daylight\t: %u\n" - "Enabled\t\t: %s\n" - "Pending\t\t: %s\n", - alm.hour, alm.minute, alm.second, alm.nanosecond, - alm.year, alm.month, alm.day, - alm.daylight, - enabled == 1 ? "yes" : "no", - pending == 1 ? "yes" : "no"); - - if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE) - seq_puts(seq, "Timezone\t: unspecified\n"); - else - /* XXX fixme: convert to string? */ - seq_printf(seq, "Timezone\t: %u\n", alm.timezone); + if (test_bit(RTC_FEATURE_ALARM, rtc->features)) { + seq_printf(seq, + "Alarm Time\t: %u:%u:%u.%09u\n" + "Alarm Date\t: %u-%u-%u\n" + "Alarm Daylight\t: %u\n" + "Enabled\t\t: %s\n" + "Pending\t\t: %s\n", + alm.hour, alm.minute, alm.second, alm.nanosecond, + alm.year, alm.month, alm.day, + alm.daylight, + enabled == 1 ? "yes" : "no", + pending == 1 ? "yes" : "no"); + + if (eft.timezone == EFI_UNSPECIFIED_TIMEZONE) + seq_puts(seq, "Timezone\t: unspecified\n"); + else + /* XXX fixme: convert to string? */ + seq_printf(seq, "Timezone\t: %u\n", alm.timezone); + } /* * now prints the capabilities @@ -269,7 +272,10 @@ static int __init efi_rtc_probe(struct platform_device *dev) rtc->ops = &efi_rtc_ops; clear_bit(RTC_FEATURE_UPDATE_INTERRUPT, rtc->features); - set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features); + if (efi_rt_services_supported(EFI_RT_SUPPORTED_WAKEUP_SERVICES)) + set_bit(RTC_FEATURE_ALARM_WAKEUP_ONLY, rtc->features); + else + clear_bit(RTC_FEATURE_ALARM, rtc->features); device_init_wakeup(&dev->dev, true); diff --git a/drivers/rtc/rtc-sunplus.c b/drivers/rtc/rtc-sunplus.c index e8e2ab1103fc..4b578e4d44f6 100644 --- a/drivers/rtc/rtc-sunplus.c +++ b/drivers/rtc/rtc-sunplus.c @@ -240,8 +240,8 @@ static int sp_rtc_probe(struct platform_device *plat_dev) if (IS_ERR(sp_rtc->reg_base)) return dev_err_probe(&plat_dev->dev, PTR_ERR(sp_rtc->reg_base), "%s devm_ioremap_resource fail\n", RTC_REG_NAME); - dev_dbg(&plat_dev->dev, "res = 0x%x, reg_base = 0x%lx\n", - sp_rtc->res->start, (unsigned long)sp_rtc->reg_base); + dev_dbg(&plat_dev->dev, "res = %pR, reg_base = %p\n", + sp_rtc->res, sp_rtc->reg_base); sp_rtc->irq = platform_get_irq(plat_dev, 0); if (sp_rtc->irq < 0) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index 49cc18a87473..29a2865b8e2e 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -981,6 +981,9 @@ queue_rtpg: * * Returns true if and only if alua_rtpg_work() will be called asynchronously. * That function is responsible for calling @qdata->fn(). + * + * Context: may be called from atomic context (alua_check()) only if the caller + * holds an sdev reference. */ static bool alua_rtpg_queue(struct alua_port_group *pg, struct scsi_device *sdev, @@ -989,8 +992,6 @@ static bool alua_rtpg_queue(struct alua_port_group *pg, int start_queue = 0; unsigned long flags; - might_sleep(); - if (WARN_ON_ONCE(!pg) || scsi_device_get(sdev)) return false; diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index 41ba22f6c7f0..8c038ccf1c09 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -162,7 +162,7 @@ static void hisi_sas_slot_index_clear(struct hisi_hba *hisi_hba, int slot_idx) static void hisi_sas_slot_index_free(struct hisi_hba *hisi_hba, int slot_idx) { if (hisi_hba->hw->slot_index_alloc || - slot_idx >= HISI_SAS_UNRESERVED_IPTT) { + slot_idx < HISI_SAS_RESERVED_IPTT) { spin_lock(&hisi_hba->lock); hisi_sas_slot_index_clear(hisi_hba, slot_idx); spin_unlock(&hisi_hba->lock); @@ -704,7 +704,7 @@ static int hisi_sas_init_device(struct domain_device *device) int_to_scsilun(0, &lun); while (retry-- > 0) { - rc = sas_clear_task_set(device, lun.scsi_lun); + rc = sas_abort_task_set(device, lun.scsi_lun); if (rc == TMF_RESP_FUNC_COMPLETE) { hisi_sas_release_task(hisi_hba, device); break; @@ -1316,7 +1316,7 @@ static void hisi_sas_refresh_port_id(struct hisi_hba *hisi_hba) device->linkrate = phy->sas_phy.linkrate; hisi_hba->hw->setup_itct(hisi_hba, sas_dev); - } else + } else if (!port->port_attached) port->id = 0xff; } } diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 4dbf51e2623a..f6da34850af9 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -5850,7 +5850,7 @@ static int hpsa_scsi_host_alloc(struct ctlr_info *h) { struct Scsi_Host *sh; - sh = scsi_host_alloc(&hpsa_driver_template, sizeof(h)); + sh = scsi_host_alloc(&hpsa_driver_template, sizeof(struct ctlr_info)); if (sh == NULL) { dev_err(&h->pdev->dev, "scsi_host_alloc failed\n"); return -ENOMEM; diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 1d1cf641937c..0454d94e8cf0 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -849,7 +849,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, enum iscsi_host_param param, char *buf) { struct iscsi_sw_tcp_host *tcp_sw_host = iscsi_host_priv(shost); - struct iscsi_session *session = tcp_sw_host->session; + struct iscsi_session *session; struct iscsi_conn *conn; struct iscsi_tcp_conn *tcp_conn; struct iscsi_sw_tcp_conn *tcp_sw_conn; @@ -859,6 +859,7 @@ static int iscsi_sw_tcp_host_get_param(struct Scsi_Host *shost, switch (param) { case ISCSI_HOST_PARAM_IPADDRESS: + session = tcp_sw_host->session; if (!session) return -ENOTCONN; @@ -959,11 +960,13 @@ iscsi_sw_tcp_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max, if (!cls_session) goto remove_host; session = cls_session->dd_data; - tcp_sw_host = iscsi_host_priv(shost); - tcp_sw_host->session = session; if (iscsi_tcp_r2tpool_alloc(session)) goto remove_session; + + /* We are now fully setup so expose the session to sysfs. */ + tcp_sw_host = iscsi_host_priv(shost); + tcp_sw_host->session = session; return cls_session; remove_session: @@ -983,10 +986,17 @@ static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session) if (WARN_ON_ONCE(session->leadconn)) return; + iscsi_session_remove(cls_session); + /* + * Our get_host_param needs to access the session, so remove the + * host from sysfs before freeing the session to make sure userspace + * is no longer accessing the callout. + */ + iscsi_host_remove(shost, false); + iscsi_tcp_r2tpool_free(cls_session->dd_data); - iscsi_session_teardown(cls_session); - iscsi_host_remove(shost, false); + iscsi_session_free(cls_session); iscsi_host_free(shost); } diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index ef2fc860257e..127f3d7f19dc 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -3104,17 +3104,32 @@ dec_session_count: } EXPORT_SYMBOL_GPL(iscsi_session_setup); -/** - * iscsi_session_teardown - destroy session, host, and cls_session - * @cls_session: iscsi session +/* + * issi_session_remove - Remove session from iSCSI class. */ -void iscsi_session_teardown(struct iscsi_cls_session *cls_session) +void iscsi_session_remove(struct iscsi_cls_session *cls_session) { struct iscsi_session *session = cls_session->dd_data; - struct module *owner = cls_session->transport->owner; struct Scsi_Host *shost = session->host; iscsi_remove_session(cls_session); + /* + * host removal only has to wait for its children to be removed from + * sysfs, and iscsi_tcp needs to do iscsi_host_remove before freeing + * the session, so drop the session count here. + */ + iscsi_host_dec_session_cnt(shost); +} +EXPORT_SYMBOL_GPL(iscsi_session_remove); + +/** + * iscsi_session_free - Free iscsi session and it's resources + * @cls_session: iscsi session + */ +void iscsi_session_free(struct iscsi_cls_session *cls_session) +{ + struct iscsi_session *session = cls_session->dd_data; + struct module *owner = cls_session->transport->owner; iscsi_pool_free(&session->cmdpool); kfree(session->password); @@ -3132,10 +3147,19 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) kfree(session->discovery_parent_type); iscsi_free_session(cls_session); - - iscsi_host_dec_session_cnt(shost); module_put(owner); } +EXPORT_SYMBOL_GPL(iscsi_session_free); + +/** + * iscsi_session_teardown - destroy session and cls_session + * @cls_session: iscsi session + */ +void iscsi_session_teardown(struct iscsi_cls_session *cls_session) +{ + iscsi_session_remove(cls_session); + iscsi_session_free(cls_session); +} EXPORT_SYMBOL_GPL(iscsi_session_teardown); /** diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c index 1ccce706167a..5e80225b5308 100644 --- a/drivers/scsi/libsas/sas_ata.c +++ b/drivers/scsi/libsas/sas_ata.c @@ -889,7 +889,9 @@ void sas_ata_device_link_abort(struct domain_device *device, bool force_reset) { struct ata_port *ap = device->sata_dev.ap; struct ata_link *link = &ap->link; + unsigned long flags; + spin_lock_irqsave(ap->lock, flags); device->sata_dev.fis[2] = ATA_ERR | ATA_DRDY; /* tf status */ device->sata_dev.fis[3] = ATA_ABORTED; /* tf error */ @@ -897,6 +899,7 @@ void sas_ata_device_link_abort(struct domain_device *device, bool force_reset) if (force_reset) link->eh_info.action |= ATA_EH_RESET; ata_link_abort(link); + spin_unlock_irqrestore(ap->lock, flags); } EXPORT_SYMBOL_GPL(sas_ata_device_link_abort); diff --git a/drivers/scsi/mpi3mr/Makefile b/drivers/scsi/mpi3mr/Makefile index ef86ca46646b..3bf8cf34e1c3 100644 --- a/drivers/scsi/mpi3mr/Makefile +++ b/drivers/scsi/mpi3mr/Makefile @@ -1,5 +1,5 @@ # mpi3mr makefile -obj-m += mpi3mr.o +obj-$(CONFIG_SCSI_MPI3MR) += mpi3mr.o mpi3mr-y += mpi3mr_os.o \ mpi3mr_fw.o \ mpi3mr_app.o \ diff --git a/drivers/scsi/mpi3mr/mpi3mr_fw.c b/drivers/scsi/mpi3mr/mpi3mr_fw.c index 0c4aabaefdcc..286a44506578 100644 --- a/drivers/scsi/mpi3mr/mpi3mr_fw.c +++ b/drivers/scsi/mpi3mr/mpi3mr_fw.c @@ -3633,8 +3633,7 @@ int mpi3mr_setup_resources(struct mpi3mr_ioc *mrioc) int i, retval = 0, capb = 0; u16 message_control; u64 dma_mask = mrioc->dma_mask ? mrioc->dma_mask : - (((dma_get_required_mask(&pdev->dev) > DMA_BIT_MASK(32)) && - (sizeof(dma_addr_t) > 4)) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32)); + ((sizeof(dma_addr_t) > 4) ? DMA_BIT_MASK(64) : DMA_BIT_MASK(32)); if (pci_enable_device_mem(pdev)) { ioc_err(mrioc, "pci_enable_device_mem: failed\n"); diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 4e981ccaac41..69061545d9d2 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2992,8 +2992,7 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev) struct sysinfo s; u64 coherent_dma_mask, dma_mask; - if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 || - dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) { + if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4) { ioc->dma_mask = 32; coherent_dma_mask = dma_mask = DMA_BIT_MASK(32); /* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */ diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c index 1426b9b03612..9feb0323bc44 100644 --- a/drivers/scsi/scsi.c +++ b/drivers/scsi/scsi.c @@ -588,8 +588,6 @@ void scsi_device_put(struct scsi_device *sdev) { struct module *mod = sdev->host->hostt->module; - might_sleep(); - put_device(&sdev->sdev_gendev); module_put(mod); } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index cc6953809a24..8553277effb3 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -1511,8 +1511,6 @@ static int inquiry_vpd_b0(unsigned char *arr) put_unaligned_be64(sdebug_write_same_length, &arr[32]); return 0x3c; /* Mandatory page length for Logical Block Provisioning */ - - return sizeof(vpdb0_data); } /* Block device characteristics VPD page (SBC-3) */ diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index a7960ad2d386..2aa2c2aee6e7 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -231,6 +231,11 @@ scsi_abort_command(struct scsi_cmnd *scmd) struct Scsi_Host *shost = sdev->host; unsigned long flags; + if (!shost->hostt->eh_abort_handler) { + /* No abort handler, fail command directly */ + return FAILED; + } + if (scmd->eh_eflags & SCSI_EH_ABORT_SCHEDULED) { /* * Retry after abort failed, escalate to next level. diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c index 7a6904a3928e..f9b18fdc7b3c 100644 --- a/drivers/scsi/scsi_scan.c +++ b/drivers/scsi/scsi_scan.c @@ -1232,8 +1232,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * that no LUN is present, so don't add sdev in these cases. * Two specific examples are: * 1) NetApp targets: return PQ=1, PDT=0x1f - * 2) IBM/2145 targets: return PQ=1, PDT=0 - * 3) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved" + * 2) USB UFI: returns PDT=0x1f, with the PQ bits being "reserved" * in the UFI 1.0 spec (we cannot rely on reserved bits). * * References: @@ -1247,8 +1246,8 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget, * PDT=00h Direct-access device (floppy) * PDT=1Fh none (no FDD connected to the requested logical unit) */ - if (((result[0] >> 5) == 1 || - (starget->pdt_1f_for_no_lun && (result[0] & 0x1f) == 0x1f)) && + if (((result[0] >> 5) == 1 || starget->pdt_1f_for_no_lun) && + (result[0] & 0x1f) == 0x1f && !scsi_is_wlun(lun)) { SCSI_LOG_SCAN_BUS(3, sdev_printk(KERN_INFO, sdev, "scsi scan: peripheral device type" diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 981d1bab2120..8ef9a5494340 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -451,6 +451,8 @@ static void scsi_device_dev_release(struct device *dev) struct scsi_vpd *vpd_pgb0 = NULL, *vpd_pgb1 = NULL, *vpd_pgb2 = NULL; unsigned long flags; + might_sleep(); + scsi_dh_release_device(sdev); parent = sdev->sdev_gendev.parent; diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 13cfd3e317cc..b9b97300e3b3 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -1677,6 +1677,13 @@ static const char *iscsi_session_state_name(int state) return name; } +static char *iscsi_session_target_state_name[] = { + [ISCSI_SESSION_TARGET_UNBOUND] = "UNBOUND", + [ISCSI_SESSION_TARGET_ALLOCATED] = "ALLOCATED", + [ISCSI_SESSION_TARGET_SCANNED] = "SCANNED", + [ISCSI_SESSION_TARGET_UNBINDING] = "UNBINDING", +}; + int iscsi_session_chkready(struct iscsi_cls_session *session) { int err; @@ -1786,9 +1793,13 @@ static int iscsi_user_scan_session(struct device *dev, void *data) if ((scan_data->channel == SCAN_WILD_CARD || scan_data->channel == 0) && (scan_data->id == SCAN_WILD_CARD || - scan_data->id == id)) + scan_data->id == id)) { scsi_scan_target(&session->dev, 0, id, scan_data->lun, scan_data->rescan); + spin_lock_irqsave(&session->lock, flags); + session->target_state = ISCSI_SESSION_TARGET_SCANNED; + spin_unlock_irqrestore(&session->lock, flags); + } } user_scan_exit: @@ -1961,31 +1972,41 @@ static void __iscsi_unbind_session(struct work_struct *work) struct iscsi_cls_host *ihost = shost->shost_data; unsigned long flags; unsigned int target_id; + bool remove_target = true; ISCSI_DBG_TRANS_SESSION(session, "Unbinding session\n"); /* Prevent new scans and make sure scanning is not in progress */ mutex_lock(&ihost->mutex); spin_lock_irqsave(&session->lock, flags); - if (session->target_id == ISCSI_MAX_TARGET) { + if (session->target_state == ISCSI_SESSION_TARGET_ALLOCATED) { + remove_target = false; + } else if (session->target_state != ISCSI_SESSION_TARGET_SCANNED) { spin_unlock_irqrestore(&session->lock, flags); mutex_unlock(&ihost->mutex); - goto unbind_session_exit; + ISCSI_DBG_TRANS_SESSION(session, + "Skipping target unbinding: Session is unbound/unbinding.\n"); + return; } + session->target_state = ISCSI_SESSION_TARGET_UNBINDING; target_id = session->target_id; session->target_id = ISCSI_MAX_TARGET; spin_unlock_irqrestore(&session->lock, flags); mutex_unlock(&ihost->mutex); - scsi_remove_target(&session->dev); + if (remove_target) + scsi_remove_target(&session->dev); if (session->ida_used) ida_free(&iscsi_sess_ida, target_id); -unbind_session_exit: iscsi_session_event(session, ISCSI_KEVENT_UNBIND_SESSION); ISCSI_DBG_TRANS_SESSION(session, "Completed target removal\n"); + + spin_lock_irqsave(&session->lock, flags); + session->target_state = ISCSI_SESSION_TARGET_UNBOUND; + spin_unlock_irqrestore(&session->lock, flags); } static void __iscsi_destroy_session(struct work_struct *work) @@ -2062,6 +2083,9 @@ int iscsi_add_session(struct iscsi_cls_session *session, unsigned int target_id) session->ida_used = true; } else session->target_id = target_id; + spin_lock_irqsave(&session->lock, flags); + session->target_state = ISCSI_SESSION_TARGET_ALLOCATED; + spin_unlock_irqrestore(&session->lock, flags); dev_set_name(&session->dev, "session%u", session->sid); err = device_add(&session->dev); @@ -4370,6 +4394,19 @@ iscsi_session_attr(discovery_parent_idx, ISCSI_PARAM_DISCOVERY_PARENT_IDX, 0); iscsi_session_attr(discovery_parent_type, ISCSI_PARAM_DISCOVERY_PARENT_TYPE, 0); static ssize_t +show_priv_session_target_state(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct iscsi_cls_session *session = iscsi_dev_to_session(dev->parent); + + return sysfs_emit(buf, "%s\n", + iscsi_session_target_state_name[session->target_state]); +} + +static ISCSI_CLASS_ATTR(priv_sess, target_state, S_IRUGO, + show_priv_session_target_state, NULL); + +static ssize_t show_priv_session_state(struct device *dev, struct device_attribute *attr, char *buf) { @@ -4471,6 +4508,7 @@ static struct attribute *iscsi_session_attrs[] = { &dev_attr_sess_boot_target.attr, &dev_attr_priv_sess_recovery_tmo.attr, &dev_attr_priv_sess_state.attr, + &dev_attr_priv_sess_target_state.attr, &dev_attr_priv_sess_creator.attr, &dev_attr_sess_chap_out_idx.attr, &dev_attr_sess_chap_in_idx.attr, @@ -4584,6 +4622,8 @@ static umode_t iscsi_session_attr_is_visible(struct kobject *kobj, return S_IRUGO | S_IWUSR; else if (attr == &dev_attr_priv_sess_state.attr) return S_IRUGO; + else if (attr == &dev_attr_priv_sess_target_state.attr) + return S_IRUGO; else if (attr == &dev_attr_priv_sess_creator.attr) return S_IRUGO; else if (attr == &dev_attr_priv_sess_target_id.attr) diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index d7a84c0bfaeb..22705eb781b0 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -1823,6 +1823,9 @@ static int storvsc_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *scmnd) ret = storvsc_do_io(dev, cmd_request, get_cpu()); put_cpu(); + if (ret) + scsi_dma_unmap(scmnd); + if (ret == -EAGAIN) { /* no more space */ ret = SCSI_MLQUEUE_DEVICE_BUSY; diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 66b316d173b0..71a3bb83984c 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -995,7 +995,7 @@ static int scsifront_suspend(struct xenbus_device *dev) return err; } -static int scsifront_remove(struct xenbus_device *dev) +static void scsifront_remove(struct xenbus_device *dev) { struct vscsifrnt_info *info = dev_get_drvdata(&dev->dev); @@ -1011,8 +1011,6 @@ static int scsifront_remove(struct xenbus_device *dev) scsifront_free_ring(info); scsi_host_put(info->host); - - return 0; } static void scsifront_disconnect(struct vscsifrnt_info *info) diff --git a/drivers/soc/imx/imx8mp-blk-ctrl.c b/drivers/soc/imx/imx8mp-blk-ctrl.c index 0e3b6ba22f94..0f13853901df 100644 --- a/drivers/soc/imx/imx8mp-blk-ctrl.c +++ b/drivers/soc/imx/imx8mp-blk-ctrl.c @@ -212,7 +212,7 @@ static void imx8mp_hdmi_blk_ctrl_power_on(struct imx8mp_blk_ctrl *bc, break; case IMX8MP_HDMIBLK_PD_LCDIF: regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0, - BIT(7) | BIT(16) | BIT(17) | BIT(18) | + BIT(16) | BIT(17) | BIT(18) | BIT(19) | BIT(20)); regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(11)); regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, @@ -241,6 +241,7 @@ static void imx8mp_hdmi_blk_ctrl_power_on(struct imx8mp_blk_ctrl *bc, regmap_set_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(1)); break; case IMX8MP_HDMIBLK_PD_HDMI_TX_PHY: + regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(7)); regmap_set_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(22) | BIT(24)); regmap_set_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(12)); regmap_clear_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(3)); @@ -270,7 +271,7 @@ static void imx8mp_hdmi_blk_ctrl_power_off(struct imx8mp_blk_ctrl *bc, BIT(4) | BIT(5) | BIT(6)); regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(11)); regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0, - BIT(7) | BIT(16) | BIT(17) | BIT(18) | + BIT(16) | BIT(17) | BIT(18) | BIT(19) | BIT(20)); break; case IMX8MP_HDMIBLK_PD_PAI: @@ -298,6 +299,7 @@ static void imx8mp_hdmi_blk_ctrl_power_off(struct imx8mp_blk_ctrl *bc, case IMX8MP_HDMIBLK_PD_HDMI_TX_PHY: regmap_set_bits(bc->regmap, HDMI_TX_CONTROL0, BIT(3)); regmap_clear_bits(bc->regmap, HDMI_RTX_RESET_CTL0, BIT(12)); + regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL0, BIT(7)); regmap_clear_bits(bc->regmap, HDMI_RTX_CLK_CTL1, BIT(22) | BIT(24)); break; case IMX8MP_HDMIBLK_PD_HDCP: @@ -590,7 +592,6 @@ static int imx8mp_blk_ctrl_probe(struct platform_device *pdev) ret = PTR_ERR(domain->power_dev); goto cleanup_pds; } - dev_set_name(domain->power_dev, "%s", data->name); domain->genpd.name = data->name; domain->genpd.power_on = imx8mp_blk_ctrl_power_on; diff --git a/drivers/soc/imx/soc-imx8m.c b/drivers/soc/imx/soc-imx8m.c index 28144c699b0c..32ed9dc88e45 100644 --- a/drivers/soc/imx/soc-imx8m.c +++ b/drivers/soc/imx/soc-imx8m.c @@ -66,8 +66,8 @@ static u32 __init imx8mq_soc_revision(void) ocotp_base = of_iomap(np, 0); WARN_ON(!ocotp_base); clk = of_clk_get_by_name(np, NULL); - if (!clk) { - WARN_ON(!clk); + if (IS_ERR(clk)) { + WARN_ON(IS_ERR(clk)); return 0; } diff --git a/drivers/soc/qcom/apr.c b/drivers/soc/qcom/apr.c index cd44f17dad3d..d51abb462ae5 100644 --- a/drivers/soc/qcom/apr.c +++ b/drivers/soc/qcom/apr.c @@ -461,9 +461,10 @@ static int apr_add_device(struct device *dev, struct device_node *np, goto out; } + /* Protection domain is optional, it does not exist on older platforms */ ret = of_property_read_string_index(np, "qcom,protection-domain", 1, &adev->service_path); - if (ret < 0) { + if (ret < 0 && ret != -EINVAL) { dev_err(dev, "Failed to read second value of qcom,protection-domain\n"); goto out; } diff --git a/drivers/soc/qcom/cpr.c b/drivers/soc/qcom/cpr.c index e9b854ed1bdf..144ea68e0920 100644 --- a/drivers/soc/qcom/cpr.c +++ b/drivers/soc/qcom/cpr.c @@ -1708,12 +1708,16 @@ static int cpr_probe(struct platform_device *pdev) ret = of_genpd_add_provider_simple(dev->of_node, &drv->pd); if (ret) - return ret; + goto err_remove_genpd; platform_set_drvdata(pdev, drv); cpr_debugfs_init(drv); return 0; + +err_remove_genpd: + pm_genpd_remove(&drv->pd); + return ret; } static int cpr_remove(struct platform_device *pdev) diff --git a/drivers/spi/spi-cadence-xspi.c b/drivers/spi/spi-cadence-xspi.c index 520b4cc69cdc..91db3c973167 100644 --- a/drivers/spi/spi-cadence-xspi.c +++ b/drivers/spi/spi-cadence-xspi.c @@ -177,7 +177,10 @@ #define CDNS_XSPI_CMD_FLD_DSEQ_CMD_3(op) ( \ FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_DCNT_H, \ ((op)->data.nbytes >> 16) & 0xffff) | \ - FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, (op)->dummy.nbytes * 8)) + FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R3_NUM_OF_DUMMY, \ + (op)->dummy.buswidth != 0 ? \ + (((op)->dummy.nbytes * 8) / (op)->dummy.buswidth) : \ + 0)) #define CDNS_XSPI_CMD_FLD_DSEQ_CMD_4(op, chipsel) ( \ FIELD_PREP(CDNS_XSPI_CMD_DSEQ_R4_BANK, chipsel) | \ diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c index 6de8360e5c2a..9eab6c20dbc5 100644 --- a/drivers/spi/spi-mt65xx.c +++ b/drivers/spi/spi-mt65xx.c @@ -1253,6 +1253,11 @@ static int mtk_spi_probe(struct platform_device *pdev) dev_notice(dev, "SPI dma_set_mask(%d) failed, ret:%d\n", addr_bits, ret); + ret = devm_request_irq(dev, irq, mtk_spi_interrupt, + IRQF_TRIGGER_NONE, dev_name(dev), master); + if (ret) + return dev_err_probe(dev, ret, "failed to register irq\n"); + pm_runtime_enable(dev); ret = devm_spi_register_master(dev, master); @@ -1261,13 +1266,6 @@ static int mtk_spi_probe(struct platform_device *pdev) return dev_err_probe(dev, ret, "failed to register master\n"); } - ret = devm_request_irq(dev, irq, mtk_spi_interrupt, - IRQF_TRIGGER_NONE, dev_name(dev), master); - if (ret) { - pm_runtime_disable(dev); - return dev_err_probe(dev, ret, "failed to register irq\n"); - } - return 0; } diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index 3cc7bb4d03de..15f174f4e056 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2310,7 +2310,7 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi, if (!of_property_read_u32(nc, "spi-max-frequency", &value)) spi->max_speed_hz = value; - if (!of_property_read_u16(nc, "spi-cs-setup-ns", &cs_setup)) { + if (!of_property_read_u16(nc, "spi-cs-setup-delay-ns", &cs_setup)) { spi->cs_setup.value = cs_setup; spi->cs_setup.unit = SPI_DELAY_UNIT_NSECS; } diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c index 6313e7d0cdf8..1935ca613447 100644 --- a/drivers/spi/spidev.c +++ b/drivers/spi/spidev.c @@ -68,7 +68,7 @@ static_assert(N_SPI_MINORS > 0 && N_SPI_MINORS <= 256); struct spidev_data { dev_t devt; - spinlock_t spi_lock; + struct mutex spi_lock; struct spi_device *spi; struct list_head device_entry; @@ -95,9 +95,8 @@ spidev_sync(struct spidev_data *spidev, struct spi_message *message) int status; struct spi_device *spi; - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); spi = spidev->spi; - spin_unlock_irq(&spidev->spi_lock); if (spi == NULL) status = -ESHUTDOWN; @@ -107,6 +106,7 @@ spidev_sync(struct spidev_data *spidev, struct spi_message *message) if (status == 0) status = message->actual_length; + mutex_unlock(&spidev->spi_lock); return status; } @@ -359,12 +359,12 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) * we issue this ioctl. */ spidev = filp->private_data; - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); spi = spi_dev_get(spidev->spi); - spin_unlock_irq(&spidev->spi_lock); - - if (spi == NULL) + if (spi == NULL) { + mutex_unlock(&spidev->spi_lock); return -ESHUTDOWN; + } /* use the buffer lock here for triple duty: * - prevent I/O (from us) so calling spi_setup() is safe; @@ -508,6 +508,7 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) mutex_unlock(&spidev->buf_lock); spi_dev_put(spi); + mutex_unlock(&spidev->spi_lock); return retval; } @@ -529,12 +530,12 @@ spidev_compat_ioc_message(struct file *filp, unsigned int cmd, * we issue this ioctl. */ spidev = filp->private_data; - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); spi = spi_dev_get(spidev->spi); - spin_unlock_irq(&spidev->spi_lock); - - if (spi == NULL) + if (spi == NULL) { + mutex_unlock(&spidev->spi_lock); return -ESHUTDOWN; + } /* SPI_IOC_MESSAGE needs the buffer locked "normally" */ mutex_lock(&spidev->buf_lock); @@ -561,6 +562,7 @@ spidev_compat_ioc_message(struct file *filp, unsigned int cmd, done: mutex_unlock(&spidev->buf_lock); spi_dev_put(spi); + mutex_unlock(&spidev->spi_lock); return retval; } @@ -601,7 +603,6 @@ static int spidev_open(struct inode *inode, struct file *filp) if (!spidev->tx_buffer) { spidev->tx_buffer = kmalloc(bufsiz, GFP_KERNEL); if (!spidev->tx_buffer) { - dev_dbg(&spidev->spi->dev, "open/ENOMEM\n"); status = -ENOMEM; goto err_find_dev; } @@ -610,7 +611,6 @@ static int spidev_open(struct inode *inode, struct file *filp) if (!spidev->rx_buffer) { spidev->rx_buffer = kmalloc(bufsiz, GFP_KERNEL); if (!spidev->rx_buffer) { - dev_dbg(&spidev->spi->dev, "open/ENOMEM\n"); status = -ENOMEM; goto err_alloc_rx_buf; } @@ -640,10 +640,10 @@ static int spidev_release(struct inode *inode, struct file *filp) spidev = filp->private_data; filp->private_data = NULL; - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); /* ... after we unbound from the underlying device? */ dofree = (spidev->spi == NULL); - spin_unlock_irq(&spidev->spi_lock); + mutex_unlock(&spidev->spi_lock); /* last close? */ spidev->users--; @@ -776,7 +776,7 @@ static int spidev_probe(struct spi_device *spi) /* Initialize the driver data */ spidev->spi = spi; - spin_lock_init(&spidev->spi_lock); + mutex_init(&spidev->spi_lock); mutex_init(&spidev->buf_lock); INIT_LIST_HEAD(&spidev->device_entry); @@ -821,9 +821,9 @@ static void spidev_remove(struct spi_device *spi) /* prevent new opens */ mutex_lock(&device_list_lock); /* make sure ops on existing fds can abort cleanly */ - spin_lock_irq(&spidev->spi_lock); + mutex_lock(&spidev->spi_lock); spidev->spi = NULL; - spin_unlock_irq(&spidev->spi_lock); + mutex_unlock(&spidev->spi_lock); list_del(&spidev->device_entry); device_destroy(spidev_class, spidev->devt); diff --git a/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h b/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h index db1441c0cc66..690ab7165b2c 100644 --- a/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h +++ b/drivers/staging/vc04_services/include/linux/raspberrypi/vchiq.h @@ -86,7 +86,7 @@ struct vchiq_service_params_kernel { struct vchiq_instance; -extern enum vchiq_status vchiq_initialise(struct vchiq_instance **pinstance); +extern int vchiq_initialise(struct vchiq_instance **pinstance); extern enum vchiq_status vchiq_shutdown(struct vchiq_instance *instance); extern enum vchiq_status vchiq_connect(struct vchiq_instance *instance); extern enum vchiq_status vchiq_open_service(struct vchiq_instance *instance, diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h index 2851ef6b9cd0..cd20eb18f275 100644 --- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h +++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.h @@ -100,10 +100,10 @@ vchiq_dump_platform_use_state(struct vchiq_state *state); extern void vchiq_dump_service_use_state(struct vchiq_state *state); -extern enum vchiq_status +extern int vchiq_use_internal(struct vchiq_state *state, struct vchiq_service *service, enum USE_TYPE_E use_type); -extern enum vchiq_status +extern int vchiq_release_internal(struct vchiq_state *state, struct vchiq_service *service); diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c index bac111456fa1..2b95b4550a63 100644 --- a/drivers/target/target_core_tmr.c +++ b/drivers/target/target_core_tmr.c @@ -73,8 +73,8 @@ static bool __target_check_io_state(struct se_cmd *se_cmd, { struct se_session *sess = se_cmd->se_sess; - assert_spin_locked(&sess->sess_cmd_lock); - WARN_ON_ONCE(!irqs_disabled()); + lockdep_assert_held(&sess->sess_cmd_lock); + /* * If command already reached CMD_T_COMPLETE state within * target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown, diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c index 62c0aa5d0783..0a4eaa307156 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c @@ -44,11 +44,13 @@ static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone, int trip, int *temp) { struct int34x_thermal_zone *d = zone->devdata; - int i; + int i, ret = 0; if (d->override_ops && d->override_ops->get_trip_temp) return d->override_ops->get_trip_temp(zone, trip, temp); + mutex_lock(&d->trip_mutex); + if (trip < d->aux_trip_nr) *temp = d->aux_trips[trip]; else if (trip == d->crt_trip_id) @@ -66,10 +68,12 @@ static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone, } } if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT) - return -EINVAL; + ret = -EINVAL; } - return 0; + mutex_unlock(&d->trip_mutex); + + return ret; } static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, @@ -77,11 +81,13 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, enum thermal_trip_type *type) { struct int34x_thermal_zone *d = zone->devdata; - int i; + int i, ret = 0; if (d->override_ops && d->override_ops->get_trip_type) return d->override_ops->get_trip_type(zone, trip, type); + mutex_lock(&d->trip_mutex); + if (trip < d->aux_trip_nr) *type = THERMAL_TRIP_PASSIVE; else if (trip == d->crt_trip_id) @@ -99,10 +105,12 @@ static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone, } } if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT) - return -EINVAL; + ret = -EINVAL; } - return 0; + mutex_unlock(&d->trip_mutex); + + return ret; } static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone, @@ -180,6 +188,8 @@ int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone) int trip_cnt = int34x_zone->aux_trip_nr; int i; + mutex_lock(&int34x_zone->trip_mutex); + int34x_zone->crt_trip_id = -1; if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_CRT", &int34x_zone->crt_temp)) @@ -207,6 +217,8 @@ int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone) int34x_zone->act_trips[i].valid = true; } + mutex_unlock(&int34x_zone->trip_mutex); + return trip_cnt; } EXPORT_SYMBOL_GPL(int340x_thermal_read_trips); @@ -230,6 +242,8 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev, if (!int34x_thermal_zone) return ERR_PTR(-ENOMEM); + mutex_init(&int34x_thermal_zone->trip_mutex); + int34x_thermal_zone->adev = adev; int34x_thermal_zone->override_ops = override_ops; @@ -281,6 +295,7 @@ err_thermal_zone: acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); kfree(int34x_thermal_zone->aux_trips); err_trip_alloc: + mutex_destroy(&int34x_thermal_zone->trip_mutex); kfree(int34x_thermal_zone); return ERR_PTR(ret); } @@ -292,6 +307,7 @@ void int340x_thermal_zone_remove(struct int34x_thermal_zone thermal_zone_device_unregister(int34x_thermal_zone->zone); acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table); kfree(int34x_thermal_zone->aux_trips); + mutex_destroy(&int34x_thermal_zone->trip_mutex); kfree(int34x_thermal_zone); } EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove); diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h index 3b4971df1b33..8f9872afd0d3 100644 --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h @@ -32,6 +32,7 @@ struct int34x_thermal_zone { struct thermal_zone_device_ops *override_ops; void *priv_data; struct acpi_lpat_conversion_table *lpat_table; + struct mutex trip_mutex; }; struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *, diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index f17ab2316dbd..77bd47d976a2 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -909,15 +909,20 @@ __thermal_cooling_device_register(struct device_node *np, cdev->devdata = devdata; ret = cdev->ops->get_max_state(cdev, &cdev->max_state); - if (ret) - goto out_kfree_type; + if (ret) { + kfree(cdev->type); + goto out_ida_remove; + } thermal_cooling_device_setup_sysfs(cdev); + ret = dev_set_name(&cdev->device, "cooling_device%d", cdev->id); if (ret) { + kfree(cdev->type); thermal_cooling_device_destroy_sysfs(cdev); - goto out_kfree_type; + goto out_ida_remove; } + ret = device_register(&cdev->device); if (ret) goto out_kfree_type; @@ -943,6 +948,8 @@ out_kfree_type: thermal_cooling_device_destroy_sysfs(cdev); kfree(cdev->type); put_device(&cdev->device); + + /* thermal_release() takes care of the rest */ cdev = NULL; out_ida_remove: ida_free(&thermal_cdev_ida, id); diff --git a/drivers/thunderbolt/retimer.c b/drivers/thunderbolt/retimer.c index 81252e31014a..56008eb91e2e 100644 --- a/drivers/thunderbolt/retimer.c +++ b/drivers/thunderbolt/retimer.c @@ -427,13 +427,6 @@ int tb_retimer_scan(struct tb_port *port, bool add) { u32 status[TB_MAX_RETIMER_INDEX + 1] = {}; int ret, i, last_idx = 0; - struct usb4_port *usb4; - - usb4 = port->usb4; - if (!usb4) - return 0; - - pm_runtime_get_sync(&usb4->dev); /* * Send broadcast RT to make sure retimer indices facing this @@ -441,7 +434,7 @@ int tb_retimer_scan(struct tb_port *port, bool add) */ ret = usb4_port_enumerate_retimers(port); if (ret) - goto out; + return ret; /* * Enable sideband channel for each retimer. We can do this @@ -471,12 +464,11 @@ int tb_retimer_scan(struct tb_port *port, bool add) break; } - if (!last_idx) { - ret = 0; - goto out; - } + if (!last_idx) + return 0; /* Add on-board retimers if they do not exist already */ + ret = 0; for (i = 1; i <= last_idx; i++) { struct tb_retimer *rt; @@ -490,10 +482,6 @@ int tb_retimer_scan(struct tb_port *port, bool add) } } -out: - pm_runtime_mark_last_busy(&usb4->dev); - pm_runtime_put_autosuspend(&usb4->dev); - return ret; } diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 462845804427..3f1ab30c4fb1 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -628,11 +628,15 @@ static void tb_scan_port(struct tb_port *port) * Downstream switch is reachable through two ports. * Only scan on the primary port (link_nr == 0). */ + + if (port->usb4) + pm_runtime_get_sync(&port->usb4->dev); + if (tb_wait_for_port(port, false) <= 0) - return; + goto out_rpm_put; if (port->remote) { tb_port_dbg(port, "port already has a remote\n"); - return; + goto out_rpm_put; } tb_retimer_scan(port, true); @@ -647,12 +651,12 @@ static void tb_scan_port(struct tb_port *port) */ if (PTR_ERR(sw) == -EIO || PTR_ERR(sw) == -EADDRNOTAVAIL) tb_scan_xdomain(port); - return; + goto out_rpm_put; } if (tb_switch_configure(sw)) { tb_switch_put(sw); - return; + goto out_rpm_put; } /* @@ -681,7 +685,7 @@ static void tb_scan_port(struct tb_port *port) if (tb_switch_add(sw)) { tb_switch_put(sw); - return; + goto out_rpm_put; } /* Link the switches using both links if available */ @@ -733,6 +737,12 @@ static void tb_scan_port(struct tb_port *port) tb_add_dp_resources(sw); tb_scan_switch(sw); + +out_rpm_put: + if (port->usb4) { + pm_runtime_mark_last_busy(&port->usb4->dev); + pm_runtime_put_autosuspend(&port->usb4->dev); + } } static void tb_deactivate_and_free_tunnel(struct tb_tunnel *tunnel) diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 2c3cf7fc3357..1fc3c29b24f8 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -1275,7 +1275,7 @@ static void tb_usb3_reclaim_available_bandwidth(struct tb_tunnel *tunnel, return; } else if (!ret) { /* Use maximum link rate if the link valid is not set */ - ret = usb4_usb3_port_max_link_rate(tunnel->src_port); + ret = tb_usb3_max_link_rate(tunnel->dst_port, tunnel->src_port); if (ret < 0) { tb_tunnel_warn(tunnel, "failed to read maximum link rate\n"); return; diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index cfa83486c9da..3c51e47dd86b 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -1419,12 +1419,19 @@ static int tb_xdomain_get_properties(struct tb_xdomain *xd) * registered, we notify the userspace that it has changed. */ if (!update) { - struct tb_port *port; + /* + * Now disable lane 1 if bonding was not enabled. Do + * this only if bonding was possible at the beginning + * (that is we are the connection manager and there are + * two lanes). + */ + if (xd->bonding_possible) { + struct tb_port *port; - /* Now disable lane 1 if bonding was not enabled */ - port = tb_port_at(xd->route, tb_xdomain_parent(xd)); - if (!port->bonded) - tb_port_disable(port->dual_link_port); + port = tb_port_at(xd->route, tb_xdomain_parent(xd)); + if (!port->bonded) + tb_port_disable(port->dual_link_port); + } if (device_add(&xd->dev)) { dev_err(&xd->dev, "failed to add XDomain device\n"); diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c index 7c23112dc923..5bddb2f5e931 100644 --- a/drivers/tty/hvc/hvc_xen.c +++ b/drivers/tty/hvc/hvc_xen.c @@ -52,17 +52,22 @@ static DEFINE_SPINLOCK(xencons_lock); static struct xencons_info *vtermno_to_xencons(int vtermno) { - struct xencons_info *entry, *n, *ret = NULL; + struct xencons_info *entry, *ret = NULL; + unsigned long flags; - if (list_empty(&xenconsoles)) - return NULL; + spin_lock_irqsave(&xencons_lock, flags); + if (list_empty(&xenconsoles)) { + spin_unlock_irqrestore(&xencons_lock, flags); + return NULL; + } - list_for_each_entry_safe(entry, n, &xenconsoles, list) { + list_for_each_entry(entry, &xenconsoles, list) { if (entry->vtermno == vtermno) { ret = entry; break; } } + spin_unlock_irqrestore(&xencons_lock, flags); return ret; } @@ -223,7 +228,7 @@ static int xen_hvm_console_init(void) { int r; uint64_t v = 0; - unsigned long gfn; + unsigned long gfn, flags; struct xencons_info *info; if (!xen_hvm_domain()) @@ -258,9 +263,9 @@ static int xen_hvm_console_init(void) goto err; info->vtermno = HVC_COOKIE; - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_add_tail(&info->list, &xenconsoles); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; err: @@ -283,6 +288,7 @@ static int xencons_info_pv_init(struct xencons_info *info, int vtermno) static int xen_pv_console_init(void) { struct xencons_info *info; + unsigned long flags; if (!xen_pv_domain()) return -ENODEV; @@ -299,9 +305,9 @@ static int xen_pv_console_init(void) /* already configured */ return 0; } - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); xencons_info_pv_init(info, HVC_COOKIE); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; } @@ -309,6 +315,7 @@ static int xen_pv_console_init(void) static int xen_initial_domain_console_init(void) { struct xencons_info *info; + unsigned long flags; if (!xen_initial_domain()) return -ENODEV; @@ -323,9 +330,9 @@ static int xen_initial_domain_console_init(void) info->irq = bind_virq_to_irq(VIRQ_CONSOLE, 0, false); info->vtermno = HVC_COOKIE; - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_add_tail(&info->list, &xenconsoles); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; } @@ -380,10 +387,12 @@ static void xencons_free(struct xencons_info *info) static int xen_console_remove(struct xencons_info *info) { + unsigned long flags; + xencons_disconnect_backend(info); - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_del(&info->list); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); if (info->xbdev != NULL) xencons_free(info); else { @@ -394,9 +403,9 @@ static int xen_console_remove(struct xencons_info *info) return 0; } -static int xencons_remove(struct xenbus_device *dev) +static void xencons_remove(struct xenbus_device *dev) { - return xen_console_remove(dev_get_drvdata(&dev->dev)); + xen_console_remove(dev_get_drvdata(&dev->dev)); } static int xencons_connect_backend(struct xenbus_device *dev, @@ -464,6 +473,7 @@ static int xencons_probe(struct xenbus_device *dev, { int ret, devid; struct xencons_info *info; + unsigned long flags; devid = dev->nodename[strlen(dev->nodename) - 1] - '0'; if (devid == 0) @@ -482,9 +492,9 @@ static int xencons_probe(struct xenbus_device *dev, ret = xencons_connect_backend(dev, info); if (ret < 0) goto error; - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_add_tail(&info->list, &xenconsoles); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); return 0; @@ -584,10 +594,12 @@ static int __init xen_hvc_init(void) info->hvc = hvc_alloc(HVC_COOKIE, info->irq, ops, 256); if (IS_ERR(info->hvc)) { + unsigned long flags; + r = PTR_ERR(info->hvc); - spin_lock(&xencons_lock); + spin_lock_irqsave(&xencons_lock, flags); list_del(&info->list); - spin_unlock(&xencons_lock); + spin_unlock_irqrestore(&xencons_lock, flags); if (info->irq) unbind_from_irqhandler(info->irq, NULL); kfree(info); diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c index 37d6af2ec427..7fa66501792d 100644 --- a/drivers/tty/serial/8250/8250_dma.c +++ b/drivers/tty/serial/8250/8250_dma.c @@ -43,15 +43,23 @@ static void __dma_rx_complete(struct uart_8250_port *p) struct uart_8250_dma *dma = p->dma; struct tty_port *tty_port = &p->port.state->port; struct dma_tx_state state; + enum dma_status dma_status; int count; - dma->rx_running = 0; - dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + /* + * New DMA Rx can be started during the completion handler before it + * could acquire port's lock and it might still be ongoing. Don't to + * anything in such case. + */ + dma_status = dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state); + if (dma_status == DMA_IN_PROGRESS) + return; count = dma->rx_size - state.residue; tty_insert_flip_string(tty_port, dma->rx_buf, count); p->port.icount.rx += count; + dma->rx_running = 0; tty_flip_buffer_push(tty_port); } @@ -62,9 +70,14 @@ static void dma_rx_complete(void *param) struct uart_8250_dma *dma = p->dma; unsigned long flags; - __dma_rx_complete(p); - spin_lock_irqsave(&p->port.lock, flags); + if (dma->rx_running) + __dma_rx_complete(p); + + /* + * Cannot be combined with the previous check because __dma_rx_complete() + * changes dma->rx_running. + */ if (!dma->rx_running && (serial_lsr_in(p) & UART_LSR_DR)) p->dma->rx_dma(p); spin_unlock_irqrestore(&p->port.lock, flags); diff --git a/drivers/tty/serial/8250/8250_exar.c b/drivers/tty/serial/8250/8250_exar.c index 314a05e009df..64770c62bbec 100644 --- a/drivers/tty/serial/8250/8250_exar.c +++ b/drivers/tty/serial/8250/8250_exar.c @@ -43,6 +43,12 @@ #define PCI_DEVICE_ID_EXAR_XR17V4358 0x4358 #define PCI_DEVICE_ID_EXAR_XR17V8358 0x8358 +#define PCI_DEVICE_ID_SEALEVEL_710xC 0x1001 +#define PCI_DEVICE_ID_SEALEVEL_720xC 0x1002 +#define PCI_DEVICE_ID_SEALEVEL_740xC 0x1004 +#define PCI_DEVICE_ID_SEALEVEL_780xC 0x1008 +#define PCI_DEVICE_ID_SEALEVEL_716xC 0x1010 + #define UART_EXAR_INT0 0x80 #define UART_EXAR_8XMODE 0x88 /* 8X sampling rate select */ #define UART_EXAR_SLEEP 0x8b /* Sleep mode */ @@ -638,6 +644,8 @@ exar_pci_probe(struct pci_dev *pcidev, const struct pci_device_id *ent) nr_ports = BIT(((pcidev->device & 0x38) >> 3) - 1); else if (board->num_ports) nr_ports = board->num_ports; + else if (pcidev->vendor == PCI_VENDOR_ID_SEALEVEL) + nr_ports = pcidev->device & 0xff; else nr_ports = pcidev->device & 0x0f; @@ -864,6 +872,12 @@ static const struct pci_device_id exar_pci_tbl[] = { EXAR_DEVICE(COMMTECH, 4224PCI335, pbn_fastcom335_4), EXAR_DEVICE(COMMTECH, 2324PCI335, pbn_fastcom335_4), EXAR_DEVICE(COMMTECH, 2328PCI335, pbn_fastcom335_8), + + EXAR_DEVICE(SEALEVEL, 710xC, pbn_exar_XR17V35x), + EXAR_DEVICE(SEALEVEL, 720xC, pbn_exar_XR17V35x), + EXAR_DEVICE(SEALEVEL, 740xC, pbn_exar_XR17V35x), + EXAR_DEVICE(SEALEVEL, 780xC, pbn_exar_XR17V35x), + EXAR_DEVICE(SEALEVEL, 716xC, pbn_exar_XR17V35x), { 0, } }; MODULE_DEVICE_TABLE(pci, exar_pci_tbl); diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c index d75c39f4622b..d8c2f3455eeb 100644 --- a/drivers/tty/serial/amba-pl011.c +++ b/drivers/tty/serial/amba-pl011.c @@ -1466,6 +1466,10 @@ static bool pl011_tx_chars(struct uart_amba_port *uap, bool from_irq) struct circ_buf *xmit = &uap->port.state->xmit; int count = uap->fifosize >> 1; + if ((uap->port.rs485.flags & SER_RS485_ENABLED) && + !uap->rs485_tx_started) + pl011_rs485_tx_start(uap); + if (uap->port.x_char) { if (!pl011_tx_char(uap, uap->port.x_char, from_irq)) return true; @@ -1477,10 +1481,6 @@ static bool pl011_tx_chars(struct uart_amba_port *uap, bool from_irq) return false; } - if ((uap->port.rs485.flags & SER_RS485_ENABLED) && - !uap->rs485_tx_started) - pl011_rs485_tx_start(uap); - /* If we are using DMA mode, try to send some characters. */ if (pl011_dma_tx_irq(uap)) return true; diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c index f1c06e12efa0..9cd7479b03c0 100644 --- a/drivers/tty/serial/atmel_serial.c +++ b/drivers/tty/serial/atmel_serial.c @@ -2657,13 +2657,7 @@ static void __init atmel_console_get_options(struct uart_port *port, int *baud, else if (mr == ATMEL_US_PAR_ODD) *parity = 'o'; - /* - * The serial core only rounds down when matching this to a - * supported baud rate. Make sure we don't end up slightly - * lower than one of those, as it would make us fall through - * to a much lower baud rate than we really want. - */ - *baud = port->uartclk / (16 * (quot - 1)); + *baud = port->uartclk / (16 * quot); } static int __init atmel_console_setup(struct console *co, char *options) diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c index a3ed9b34e2ab..7ce7bb164005 100644 --- a/drivers/tty/serial/kgdboc.c +++ b/drivers/tty/serial/kgdboc.c @@ -171,6 +171,7 @@ static int configure_kgdboc(void) int err = -ENODEV; char *cptr = config; struct console *cons; + int cookie; if (!strlen(config) || isspace(config[0])) { err = 0; @@ -189,20 +190,9 @@ static int configure_kgdboc(void) if (kgdboc_register_kbd(&cptr)) goto do_register; - /* - * tty_find_polling_driver() can call uart_set_options() - * (via poll_init) to configure the uart. Take the console_list_lock - * in order to synchronize against register_console(), which can also - * configure the uart via uart_set_options(). This also allows safe - * traversal of the console list. - */ - console_list_lock(); - p = tty_find_polling_driver(cptr, &tty_line); - if (!p) { - console_list_unlock(); + if (!p) goto noconfig; - } /* * Take console_lock to serialize device() callback with @@ -211,7 +201,8 @@ static int configure_kgdboc(void) */ console_lock(); - for_each_console(cons) { + cookie = console_srcu_read_lock(); + for_each_console_srcu(cons) { int idx; if (cons->device && cons->device(cons, &idx) == p && idx == tty_line) { @@ -219,11 +210,10 @@ static int configure_kgdboc(void) break; } } + console_srcu_read_unlock(cookie); console_unlock(); - console_list_unlock(); - kgdb_tty_driver = p; kgdb_tty_line = tty_line; diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c index 3d54a43768cd..9576ba8bbc40 100644 --- a/drivers/tty/serial/pch_uart.c +++ b/drivers/tty/serial/pch_uart.c @@ -749,7 +749,7 @@ static void pch_dma_tx_complete(void *arg) uart_xmit_advance(port, sg_dma_len(sg)); async_tx_ack(priv->desc_tx); - dma_unmap_sg(port->dev, sg, priv->orig_nent, DMA_TO_DEVICE); + dma_unmap_sg(port->dev, priv->sg_tx_p, priv->orig_nent, DMA_TO_DEVICE); priv->tx_dma_use = 0; priv->nent = 0; priv->orig_nent = 0; diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c index b487823f0e61..57f04f8bf504 100644 --- a/drivers/tty/serial/qcom_geni_serial.c +++ b/drivers/tty/serial/qcom_geni_serial.c @@ -864,9 +864,10 @@ out_unlock: return IRQ_HANDLED; } -static void get_tx_fifo_size(struct qcom_geni_serial_port *port) +static int setup_fifos(struct qcom_geni_serial_port *port) { struct uart_port *uport; + u32 old_rx_fifo_depth = port->rx_fifo_depth; uport = &port->uport; port->tx_fifo_depth = geni_se_get_tx_fifo_depth(&port->se); @@ -874,6 +875,16 @@ static void get_tx_fifo_size(struct qcom_geni_serial_port *port) port->rx_fifo_depth = geni_se_get_rx_fifo_depth(&port->se); uport->fifosize = (port->tx_fifo_depth * port->tx_fifo_width) / BITS_PER_BYTE; + + if (port->rx_fifo && (old_rx_fifo_depth != port->rx_fifo_depth) && port->rx_fifo_depth) { + port->rx_fifo = devm_krealloc(uport->dev, port->rx_fifo, + port->rx_fifo_depth * sizeof(u32), + GFP_KERNEL); + if (!port->rx_fifo) + return -ENOMEM; + } + + return 0; } @@ -888,6 +899,7 @@ static int qcom_geni_serial_port_setup(struct uart_port *uport) u32 rxstale = DEFAULT_BITS_PER_CHAR * STALE_TIMEOUT; u32 proto; u32 pin_swap; + int ret; proto = geni_se_read_proto(&port->se); if (proto != GENI_SE_UART) { @@ -897,7 +909,9 @@ static int qcom_geni_serial_port_setup(struct uart_port *uport) qcom_geni_serial_stop_rx(uport); - get_tx_fifo_size(port); + ret = setup_fifos(port); + if (ret) + return ret; writel(rxstale, uport->membase + SE_UART_RX_STALE_CNT); @@ -1516,7 +1530,7 @@ static int qcom_geni_serial_remove(struct platform_device *pdev) return 0; } -static int __maybe_unused qcom_geni_serial_sys_suspend(struct device *dev) +static int qcom_geni_serial_sys_suspend(struct device *dev) { struct qcom_geni_serial_port *port = dev_get_drvdata(dev); struct uart_port *uport = &port->uport; @@ -1533,7 +1547,7 @@ static int __maybe_unused qcom_geni_serial_sys_suspend(struct device *dev) return uart_suspend_port(private_data->drv, uport); } -static int __maybe_unused qcom_geni_serial_sys_resume(struct device *dev) +static int qcom_geni_serial_sys_resume(struct device *dev) { int ret; struct qcom_geni_serial_port *port = dev_get_drvdata(dev); @@ -1581,10 +1595,12 @@ static int qcom_geni_serial_sys_hib_resume(struct device *dev) } static const struct dev_pm_ops qcom_geni_serial_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(qcom_geni_serial_sys_suspend, - qcom_geni_serial_sys_resume) - .restore = qcom_geni_serial_sys_hib_resume, - .thaw = qcom_geni_serial_sys_hib_resume, + .suspend = pm_sleep_ptr(qcom_geni_serial_sys_suspend), + .resume = pm_sleep_ptr(qcom_geni_serial_sys_resume), + .freeze = pm_sleep_ptr(qcom_geni_serial_sys_suspend), + .poweroff = pm_sleep_ptr(qcom_geni_serial_sys_suspend), + .restore = pm_sleep_ptr(qcom_geni_serial_sys_hib_resume), + .thaw = pm_sleep_ptr(qcom_geni_serial_sys_hib_resume), }; static const struct of_device_id qcom_geni_serial_match_table[] = { diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index b9fbbee598b8..ec874f3a567c 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -2212,6 +2212,9 @@ EXPORT_SYMBOL_GPL(uart_parse_options); * @parity: parity character - 'n' (none), 'o' (odd), 'e' (even) * @bits: number of data bits * @flow: flow control character - 'r' (rts) + * + * Locking: Caller must hold console_list_lock in order to serialize + * early initialization of the serial-console lock. */ int uart_set_options(struct uart_port *port, struct console *co, @@ -2619,7 +2622,9 @@ static int uart_poll_init(struct tty_driver *driver, int line, char *options) if (!ret && options) { uart_parse_options(options, &baud, &parity, &bits, &flow); + console_list_lock(); ret = uart_set_options(port, NULL, baud, parity, bits, flow); + console_list_unlock(); } out: mutex_unlock(&tport->mutex); diff --git a/drivers/tty/serial/stm32-usart.c b/drivers/tty/serial/stm32-usart.c index a1490033aa16..409e91d6829a 100644 --- a/drivers/tty/serial/stm32-usart.c +++ b/drivers/tty/serial/stm32-usart.c @@ -797,25 +797,11 @@ static irqreturn_t stm32_usart_interrupt(int irq, void *ptr) spin_unlock(&port->lock); } - if (stm32_usart_rx_dma_enabled(port)) - return IRQ_WAKE_THREAD; - else - return IRQ_HANDLED; -} - -static irqreturn_t stm32_usart_threaded_interrupt(int irq, void *ptr) -{ - struct uart_port *port = ptr; - struct tty_port *tport = &port->state->port; - struct stm32_port *stm32_port = to_stm32_port(port); - unsigned int size; - unsigned long flags; - /* Receiver timeout irq for DMA RX */ - if (!stm32_port->throttled) { - spin_lock_irqsave(&port->lock, flags); + if (stm32_usart_rx_dma_enabled(port) && !stm32_port->throttled) { + spin_lock(&port->lock); size = stm32_usart_receive_chars(port, false); - uart_unlock_and_check_sysrq_irqrestore(port, flags); + uart_unlock_and_check_sysrq(port); if (size) tty_flip_buffer_push(tport); } @@ -1015,10 +1001,8 @@ static int stm32_usart_startup(struct uart_port *port) u32 val; int ret; - ret = request_threaded_irq(port->irq, stm32_usart_interrupt, - stm32_usart_threaded_interrupt, - IRQF_ONESHOT | IRQF_NO_SUSPEND, - name, port); + ret = request_irq(port->irq, stm32_usart_interrupt, + IRQF_NO_SUSPEND, name, port); if (ret) return ret; @@ -1601,13 +1585,6 @@ static int stm32_usart_of_dma_rx_probe(struct stm32_port *stm32port, struct dma_slave_config config; int ret; - /* - * Using DMA and threaded handler for the console could lead to - * deadlocks. - */ - if (uart_console(port)) - return -ENODEV; - stm32port->rx_buf = dma_alloc_coherent(dev, RX_BUF_L, &stm32port->rx_dma_buf, GFP_KERNEL); diff --git a/drivers/tty/vt/vc_screen.c b/drivers/tty/vt/vc_screen.c index 1850bacdb5b0..f566eb1839dc 100644 --- a/drivers/tty/vt/vc_screen.c +++ b/drivers/tty/vt/vc_screen.c @@ -386,10 +386,6 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) uni_mode = use_unicode(inode); attr = use_attributes(inode); - ret = -ENXIO; - vc = vcs_vc(inode, &viewed); - if (!vc) - goto unlock_out; ret = -EINVAL; if (pos < 0) @@ -407,6 +403,11 @@ vcs_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) unsigned int this_round, skip = 0; int size; + ret = -ENXIO; + vc = vcs_vc(inode, &viewed); + if (!vc) + goto unlock_out; + /* Check whether we are above size each round, * as copy_to_user at the end of this loop * could sleep. diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index e18c9f4463ec..3a1c4d31e010 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -1234,12 +1234,14 @@ static int ufshcd_clock_scaling_prepare(struct ufs_hba *hba) * clock scaling is in progress */ ufshcd_scsi_block_requests(hba); + mutex_lock(&hba->wb_mutex); down_write(&hba->clk_scaling_lock); if (!hba->clk_scaling.is_allowed || ufshcd_wait_for_doorbell_clr(hba, DOORBELL_CLR_TOUT_US)) { ret = -EBUSY; up_write(&hba->clk_scaling_lock); + mutex_unlock(&hba->wb_mutex); ufshcd_scsi_unblock_requests(hba); goto out; } @@ -1251,12 +1253,16 @@ out: return ret; } -static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, bool writelock) +static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, int err, bool scale_up) { - if (writelock) - up_write(&hba->clk_scaling_lock); - else - up_read(&hba->clk_scaling_lock); + up_write(&hba->clk_scaling_lock); + + /* Enable Write Booster if we have scaled up else disable it */ + if (ufshcd_enable_wb_if_scaling_up(hba) && !err) + ufshcd_wb_toggle(hba, scale_up); + + mutex_unlock(&hba->wb_mutex); + ufshcd_scsi_unblock_requests(hba); ufshcd_release(hba); } @@ -1273,7 +1279,6 @@ static void ufshcd_clock_scaling_unprepare(struct ufs_hba *hba, bool writelock) static int ufshcd_devfreq_scale(struct ufs_hba *hba, bool scale_up) { int ret = 0; - bool is_writelock = true; ret = ufshcd_clock_scaling_prepare(hba); if (ret) @@ -1302,15 +1307,8 @@ static int ufshcd_devfreq_scale(struct ufs_hba *hba, bool scale_up) } } - /* Enable Write Booster if we have scaled up else disable it */ - if (ufshcd_enable_wb_if_scaling_up(hba)) { - downgrade_write(&hba->clk_scaling_lock); - is_writelock = false; - ufshcd_wb_toggle(hba, scale_up); - } - out_unprepare: - ufshcd_clock_scaling_unprepare(hba, is_writelock); + ufshcd_clock_scaling_unprepare(hba, ret, scale_up); return ret; } @@ -6056,11 +6054,21 @@ void ufshcd_schedule_eh_work(struct ufs_hba *hba) } } +static void ufshcd_force_error_recovery(struct ufs_hba *hba) +{ + spin_lock_irq(hba->host->host_lock); + hba->force_reset = true; + ufshcd_schedule_eh_work(hba); + spin_unlock_irq(hba->host->host_lock); +} + static void ufshcd_clk_scaling_allow(struct ufs_hba *hba, bool allow) { + mutex_lock(&hba->wb_mutex); down_write(&hba->clk_scaling_lock); hba->clk_scaling.is_allowed = allow; up_write(&hba->clk_scaling_lock); + mutex_unlock(&hba->wb_mutex); } static void ufshcd_clk_scaling_suspend(struct ufs_hba *hba, bool suspend) @@ -9083,6 +9091,15 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) if (!hba->dev_info.b_rpm_dev_flush_capable) { ret = ufshcd_set_dev_pwr_mode(hba, req_dev_pwr_mode); + if (ret && pm_op != UFS_SHUTDOWN_PM) { + /* + * If return err in suspend flow, IO will hang. + * Trigger error handler and break suspend for + * error recovery. + */ + ufshcd_force_error_recovery(hba); + ret = -EBUSY; + } if (ret) goto enable_scaling; } @@ -9094,6 +9111,15 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op) */ check_for_bkops = !ufshcd_is_ufs_dev_deepsleep(hba); ret = ufshcd_link_state_transition(hba, req_link_state, check_for_bkops); + if (ret && pm_op != UFS_SHUTDOWN_PM) { + /* + * If return err in suspend flow, IO will hang. + * Trigger error handler and break suspend for + * error recovery. + */ + ufshcd_force_error_recovery(hba); + ret = -EBUSY; + } if (ret) goto set_dev_active; @@ -9767,6 +9793,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq) /* Initialize mutex for exception event control */ mutex_init(&hba->ee_ctrl_mutex); + mutex_init(&hba->wb_mutex); init_rwsem(&hba->clk_scaling_lock); ufshcd_init_clk_gating(hba); diff --git a/drivers/usb/cdns3/cdns3-gadget.c b/drivers/usb/cdns3/cdns3-gadget.c index 5adcb349718c..ccfaebca6faa 100644 --- a/drivers/usb/cdns3/cdns3-gadget.c +++ b/drivers/usb/cdns3/cdns3-gadget.c @@ -2614,6 +2614,7 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep, u8 req_on_hw_ring = 0; unsigned long flags; int ret = 0; + int val; if (!ep || !request || !ep->desc) return -EINVAL; @@ -2649,6 +2650,13 @@ found: /* Update ring only if removed request is on pending_req_list list */ if (req_on_hw_ring && link_trb) { + /* Stop DMA */ + writel(EP_CMD_DFLUSH, &priv_dev->regs->ep_cmd); + + /* wait for DFLUSH cleared */ + readl_poll_timeout_atomic(&priv_dev->regs->ep_cmd, val, + !(val & EP_CMD_DFLUSH), 1, 1000); + link_trb->buffer = cpu_to_le32(TRB_BUFFER(priv_ep->trb_pool_dma + ((priv_req->end_trb + 1) * TRB_SIZE))); link_trb->control = cpu_to_le32((le32_to_cpu(link_trb->control) & TRB_CYCLE) | @@ -2660,6 +2668,10 @@ found: cdns3_gadget_giveback(priv_ep, priv_req, -ECONNRESET); + req = cdns3_next_request(&priv_ep->pending_req_list); + if (req) + cdns3_rearm_transfer(priv_ep, 1); + not_found: spin_unlock_irqrestore(&priv_dev->lock, flags); return ret; diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c index 484b1cd23431..27c601296130 100644 --- a/drivers/usb/chipidea/core.c +++ b/drivers/usb/chipidea/core.c @@ -1294,12 +1294,12 @@ static void ci_extcon_wakeup_int(struct ci_hdrc *ci) cable_id = &ci->platdata->id_extcon; cable_vbus = &ci->platdata->vbus_extcon; - if ((!IS_ERR(cable_id->edev) || !IS_ERR(ci->role_switch)) + if ((!IS_ERR(cable_id->edev) || ci->role_switch) && ci->is_otg && (otgsc & OTGSC_IDIE) && (otgsc & OTGSC_IDIS)) ci_irq(ci); - if ((!IS_ERR(cable_vbus->edev) || !IS_ERR(ci->role_switch)) + if ((!IS_ERR(cable_vbus->edev) || ci->role_switch) && ci->is_otg && (otgsc & OTGSC_BSVIE) && (otgsc & OTGSC_BSVIS)) ci_irq(ci); diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 77e73fc8d673..9eca403af2a8 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -44,6 +44,9 @@ #define USB_PRODUCT_USB5534B 0x5534 #define USB_VENDOR_CYPRESS 0x04b4 #define USB_PRODUCT_CY7C65632 0x6570 +#define USB_VENDOR_TEXAS_INSTRUMENTS 0x0451 +#define USB_PRODUCT_TUSB8041_USB3 0x8140 +#define USB_PRODUCT_TUSB8041_USB2 0x8142 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND 0x01 #define HUB_QUIRK_DISABLE_AUTOSUSPEND 0x02 @@ -5854,6 +5857,16 @@ static const struct usb_device_id hub_id_table[] = { .idVendor = USB_VENDOR_GENESYS_LOGIC, .bInterfaceClass = USB_CLASS_HUB, .driver_info = HUB_QUIRK_CHECK_PORT_AUTOSUSPEND}, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT, + .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS, + .idProduct = USB_PRODUCT_TUSB8041_USB2, + .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, + { .match_flags = USB_DEVICE_ID_MATCH_VENDOR + | USB_DEVICE_ID_MATCH_PRODUCT, + .idVendor = USB_VENDOR_TEXAS_INSTRUMENTS, + .idProduct = USB_PRODUCT_TUSB8041_USB3, + .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND}, { .match_flags = USB_DEVICE_ID_MATCH_DEV_CLASS, .bDeviceClass = USB_CLASS_HUB}, { .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS, diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c index 6d93428432f1..533baa85083c 100644 --- a/drivers/usb/core/usb-acpi.c +++ b/drivers/usb/core/usb-acpi.c @@ -37,6 +37,71 @@ bool usb_acpi_power_manageable(struct usb_device *hdev, int index) } EXPORT_SYMBOL_GPL(usb_acpi_power_manageable); +#define UUID_USB_CONTROLLER_DSM "ce2ee385-00e6-48cb-9f05-2edb927c4899" +#define USB_DSM_DISABLE_U1_U2_FOR_PORT 5 + +/** + * usb_acpi_port_lpm_incapable - check if lpm should be disabled for a port. + * @hdev: USB device belonging to the usb hub + * @index: zero based port index + * + * Some USB3 ports may not support USB3 link power management U1/U2 states + * due to different retimer setup. ACPI provides _DSM method which returns 0x01 + * if U1 and U2 states should be disabled. Evaluate _DSM with: + * Arg0: UUID = ce2ee385-00e6-48cb-9f05-2edb927c4899 + * Arg1: Revision ID = 0 + * Arg2: Function Index = 5 + * Arg3: (empty) + * + * Return 1 if USB3 port is LPM incapable, negative on error, otherwise 0 + */ + +int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index) +{ + union acpi_object *obj; + acpi_handle port_handle; + int port1 = index + 1; + guid_t guid; + int ret; + + ret = guid_parse(UUID_USB_CONTROLLER_DSM, &guid); + if (ret) + return ret; + + port_handle = usb_get_hub_port_acpi_handle(hdev, port1); + if (!port_handle) { + dev_dbg(&hdev->dev, "port-%d no acpi handle\n", port1); + return -ENODEV; + } + + if (!acpi_check_dsm(port_handle, &guid, 0, + BIT(USB_DSM_DISABLE_U1_U2_FOR_PORT))) { + dev_dbg(&hdev->dev, "port-%d no _DSM function %d\n", + port1, USB_DSM_DISABLE_U1_U2_FOR_PORT); + return -ENODEV; + } + + obj = acpi_evaluate_dsm(port_handle, &guid, 0, + USB_DSM_DISABLE_U1_U2_FOR_PORT, NULL); + + if (!obj) + return -ENODEV; + + if (obj->type != ACPI_TYPE_INTEGER) { + dev_dbg(&hdev->dev, "evaluate port-%d _DSM failed\n", port1); + ACPI_FREE(obj); + return -EINVAL; + } + + if (obj->integer.value == 0x01) + ret = 1; + + ACPI_FREE(obj); + + return ret; +} +EXPORT_SYMBOL_GPL(usb_acpi_port_lpm_incapable); + /** * usb_acpi_set_power_state - control usb port's power via acpi power * resource diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig index b2f72b0e75c6..be954a9abbe0 100644 --- a/drivers/usb/dwc3/Kconfig +++ b/drivers/usb/dwc3/Kconfig @@ -3,6 +3,7 @@ config USB_DWC3 tristate "DesignWare USB3 DRD Core Support" depends on (USB || USB_GADGET) && HAS_DMA + depends on (EXTCON || EXTCON=n) select USB_XHCI_PLATFORM if USB_XHCI_HCD select USB_ROLE_SWITCH if USB_DWC3_DUAL_ROLE help @@ -44,7 +45,6 @@ config USB_DWC3_GADGET config USB_DWC3_DUAL_ROLE bool "Dual Role mode" depends on ((USB=y || USB=USB_DWC3) && (USB_GADGET=y || USB_GADGET=USB_DWC3)) - depends on (EXTCON=y || EXTCON=USB_DWC3) help This is the default mode of working of DWC3 controller where both host and gadget features are enabled. diff --git a/drivers/usb/dwc3/dwc3-qcom.c b/drivers/usb/dwc3/dwc3-qcom.c index b0a0351d2d8b..959fc925ca7c 100644 --- a/drivers/usb/dwc3/dwc3-qcom.c +++ b/drivers/usb/dwc3/dwc3-qcom.c @@ -901,7 +901,7 @@ static int dwc3_qcom_probe(struct platform_device *pdev) qcom->mode = usb_get_dr_mode(&qcom->dwc3->dev); /* enable vbus override for device mode */ - if (qcom->mode == USB_DR_MODE_PERIPHERAL) + if (qcom->mode != USB_DR_MODE_HOST) dwc3_qcom_vbus_override_enable(qcom, true); /* register extcon to override sw_vbus on Vbus change later */ diff --git a/drivers/usb/fotg210/fotg210-udc.c b/drivers/usb/fotg210/fotg210-udc.c index 87cca81bf4ac..eb076746f032 100644 --- a/drivers/usb/fotg210/fotg210-udc.c +++ b/drivers/usb/fotg210/fotg210-udc.c @@ -1014,7 +1014,6 @@ static int fotg210_udc_start(struct usb_gadget *g, int ret; /* hook up the driver */ - driver->driver.bus = NULL; fotg210->driver = driver; if (!IS_ERR_OR_NULL(fotg210->phy)) { diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c index 96121d1c8df4..0853536cbf2e 100644 --- a/drivers/usb/gadget/configfs.c +++ b/drivers/usb/gadget/configfs.c @@ -393,6 +393,7 @@ static void gadget_info_attr_release(struct config_item *item) WARN_ON(!list_empty(&gi->string_list)); WARN_ON(!list_empty(&gi->available_func)); kfree(gi->composite.gadget_driver.function); + kfree(gi->composite.gadget_driver.driver.name); kfree(gi); } @@ -1572,7 +1573,6 @@ static const struct usb_gadget_driver configfs_driver_template = { .max_speed = USB_SPEED_SUPER_PLUS, .driver = { .owner = THIS_MODULE, - .name = "configfs-gadget", }, .match_existing_only = 1, }; @@ -1623,13 +1623,21 @@ static struct config_group *gadgets_make( gi->composite.gadget_driver = configfs_driver_template; + gi->composite.gadget_driver.driver.name = kasprintf(GFP_KERNEL, + "configfs-gadget.%s", name); + if (!gi->composite.gadget_driver.driver.name) + goto err; + gi->composite.gadget_driver.function = kstrdup(name, GFP_KERNEL); gi->composite.name = gi->composite.gadget_driver.function; if (!gi->composite.gadget_driver.function) - goto err; + goto out_free_driver_name; return &gi->group; + +out_free_driver_name: + kfree(gi->composite.gadget_driver.driver.name); err: kfree(gi); return ERR_PTR(-ENOMEM); diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 73dc10a77cde..8ad354741380 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -279,6 +279,11 @@ static int __ffs_ep0_queue_wait(struct ffs_data *ffs, char *data, size_t len) struct usb_request *req = ffs->ep0req; int ret; + if (!req) { + spin_unlock_irq(&ffs->ev.waitq.lock); + return -EINVAL; + } + req->zero = len < le16_to_cpu(ffs->ev.setup.wLength); spin_unlock_irq(&ffs->ev.waitq.lock); @@ -1892,10 +1897,14 @@ static void functionfs_unbind(struct ffs_data *ffs) ENTER(); if (!WARN_ON(!ffs->gadget)) { + /* dequeue before freeing ep0req */ + usb_ep_dequeue(ffs->gadget->ep0, ffs->ep0req); + mutex_lock(&ffs->mutex); usb_ep_free_request(ffs->gadget->ep0, ffs->ep0req); ffs->ep0req = NULL; ffs->gadget = NULL; clear_bit(FFS_FL_BOUND, &ffs->flags); + mutex_unlock(&ffs->mutex); ffs_data_put(ffs); } } diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index c36bcfa0e9b4..424bb3b666db 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -83,7 +83,9 @@ static inline struct f_ncm *func_to_ncm(struct usb_function *f) /* peak (theoretical) bulk transfer rate in bits-per-second */ static inline unsigned ncm_bitrate(struct usb_gadget *g) { - if (gadget_is_superspeed(g) && g->speed >= USB_SPEED_SUPER_PLUS) + if (!g) + return 0; + else if (gadget_is_superspeed(g) && g->speed >= USB_SPEED_SUPER_PLUS) return 4250000000U; else if (gadget_is_superspeed(g) && g->speed == USB_SPEED_SUPER) return 3750000000U; diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c index 08726e4c68a5..0219cd79493a 100644 --- a/drivers/usb/gadget/function/f_uac2.c +++ b/drivers/usb/gadget/function/f_uac2.c @@ -1142,6 +1142,7 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn) } std_as_out_if0_desc.bInterfaceNumber = ret; std_as_out_if1_desc.bInterfaceNumber = ret; + std_as_out_if1_desc.bNumEndpoints = 1; uac2->as_out_intf = ret; uac2->as_out_alt = 0; diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 01c3ead7d1b4..d605bc2e7e8f 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -229,6 +229,7 @@ static void put_ep (struct ep_data *data) */ static const char *CHIP; +static DEFINE_MUTEX(sb_mutex); /* Serialize superblock operations */ /*----------------------------------------------------------------------*/ @@ -2010,13 +2011,20 @@ gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct dev_data *dev; + int rc; - if (the_device) - return -ESRCH; + mutex_lock(&sb_mutex); + + if (the_device) { + rc = -ESRCH; + goto Done; + } CHIP = usb_get_gadget_udc_name(); - if (!CHIP) - return -ENODEV; + if (!CHIP) { + rc = -ENODEV; + goto Done; + } /* superblock */ sb->s_blocksize = PAGE_SIZE; @@ -2053,13 +2061,17 @@ gadgetfs_fill_super (struct super_block *sb, struct fs_context *fc) * from binding to a controller. */ the_device = dev; - return 0; + rc = 0; + goto Done; -Enomem: + Enomem: kfree(CHIP); CHIP = NULL; + rc = -ENOMEM; - return -ENOMEM; + Done: + mutex_unlock(&sb_mutex); + return rc; } /* "mount -t gadgetfs path /dev/gadget" ends up here */ @@ -2081,6 +2093,7 @@ static int gadgetfs_init_fs_context(struct fs_context *fc) static void gadgetfs_kill_sb (struct super_block *sb) { + mutex_lock(&sb_mutex); kill_litter_super (sb); if (the_device) { put_dev (the_device); @@ -2088,6 +2101,7 @@ gadgetfs_kill_sb (struct super_block *sb) } kfree(CHIP); CHIP = NULL; + mutex_unlock(&sb_mutex); } /*----------------------------------------------------------------------*/ diff --git a/drivers/usb/gadget/legacy/webcam.c b/drivers/usb/gadget/legacy/webcam.c index 53e38f87472b..c06dd1af7a0c 100644 --- a/drivers/usb/gadget/legacy/webcam.c +++ b/drivers/usb/gadget/legacy/webcam.c @@ -293,6 +293,7 @@ static const struct uvc_descriptor_header * const uvc_fs_streaming_cls[] = { (const struct uvc_descriptor_header *) &uvc_format_yuv, (const struct uvc_descriptor_header *) &uvc_frame_yuv_360p, (const struct uvc_descriptor_header *) &uvc_frame_yuv_720p, + (const struct uvc_descriptor_header *) &uvc_color_matching, (const struct uvc_descriptor_header *) &uvc_format_mjpg, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p, @@ -305,6 +306,7 @@ static const struct uvc_descriptor_header * const uvc_hs_streaming_cls[] = { (const struct uvc_descriptor_header *) &uvc_format_yuv, (const struct uvc_descriptor_header *) &uvc_frame_yuv_360p, (const struct uvc_descriptor_header *) &uvc_frame_yuv_720p, + (const struct uvc_descriptor_header *) &uvc_color_matching, (const struct uvc_descriptor_header *) &uvc_format_mjpg, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p, @@ -317,6 +319,7 @@ static const struct uvc_descriptor_header * const uvc_ss_streaming_cls[] = { (const struct uvc_descriptor_header *) &uvc_format_yuv, (const struct uvc_descriptor_header *) &uvc_frame_yuv_360p, (const struct uvc_descriptor_header *) &uvc_frame_yuv_720p, + (const struct uvc_descriptor_header *) &uvc_color_matching, (const struct uvc_descriptor_header *) &uvc_format_mjpg, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_360p, (const struct uvc_descriptor_header *) &uvc_frame_mjpg_720p, diff --git a/drivers/usb/gadget/udc/bcm63xx_udc.c b/drivers/usb/gadget/udc/bcm63xx_udc.c index 2cdb07905bde..d04d72f5816e 100644 --- a/drivers/usb/gadget/udc/bcm63xx_udc.c +++ b/drivers/usb/gadget/udc/bcm63xx_udc.c @@ -1830,7 +1830,6 @@ static int bcm63xx_udc_start(struct usb_gadget *gadget, bcm63xx_select_phy_mode(udc, true); udc->driver = driver; - driver->driver.bus = NULL; udc->gadget.dev.of_node = udc->dev->of_node; spin_unlock_irqrestore(&udc->lock, flags); diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index bf745358e28e..3b1cc8fa30c8 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -2285,7 +2285,6 @@ static int fsl_qe_start(struct usb_gadget *gadget, /* lock is needed but whether should use this lock or another */ spin_lock_irqsave(&udc->lock, flags); - driver->driver.bus = NULL; /* hook up the driver */ udc->driver = driver; udc->gadget.speed = driver->max_speed; diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c index 50435e804118..a67873a074b7 100644 --- a/drivers/usb/gadget/udc/fsl_udc_core.c +++ b/drivers/usb/gadget/udc/fsl_udc_core.c @@ -1943,7 +1943,6 @@ static int fsl_udc_start(struct usb_gadget *g, /* lock is needed but whether should use this lock or another */ spin_lock_irqsave(&udc_controller->lock, flags); - driver->driver.bus = NULL; /* hook up the driver */ udc_controller->driver = driver; spin_unlock_irqrestore(&udc_controller->lock, flags); diff --git a/drivers/usb/gadget/udc/fusb300_udc.c b/drivers/usb/gadget/udc/fusb300_udc.c index 9af8b415f303..5954800d652c 100644 --- a/drivers/usb/gadget/udc/fusb300_udc.c +++ b/drivers/usb/gadget/udc/fusb300_udc.c @@ -1311,7 +1311,6 @@ static int fusb300_udc_start(struct usb_gadget *g, struct fusb300 *fusb300 = to_fusb300(g); /* hook up the driver */ - driver->driver.bus = NULL; fusb300->driver = driver; return 0; diff --git a/drivers/usb/gadget/udc/goku_udc.c b/drivers/usb/gadget/udc/goku_udc.c index bdc56b24b5c9..5ffb3d5c635b 100644 --- a/drivers/usb/gadget/udc/goku_udc.c +++ b/drivers/usb/gadget/udc/goku_udc.c @@ -1375,7 +1375,6 @@ static int goku_udc_start(struct usb_gadget *g, struct goku_udc *dev = to_goku_udc(g); /* hook up the driver */ - driver->driver.bus = NULL; dev->driver = driver; /* diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c index 22096f8505de..85cdc0af3bf9 100644 --- a/drivers/usb/gadget/udc/gr_udc.c +++ b/drivers/usb/gadget/udc/gr_udc.c @@ -1906,7 +1906,6 @@ static int gr_udc_start(struct usb_gadget *gadget, spin_lock(&dev->lock); /* Hook up the driver */ - driver->driver.bus = NULL; dev->driver = driver; /* Get ready for host detection */ diff --git a/drivers/usb/gadget/udc/m66592-udc.c b/drivers/usb/gadget/udc/m66592-udc.c index c7e421b449f3..06e21cee431b 100644 --- a/drivers/usb/gadget/udc/m66592-udc.c +++ b/drivers/usb/gadget/udc/m66592-udc.c @@ -1454,7 +1454,6 @@ static int m66592_udc_start(struct usb_gadget *g, struct m66592 *m66592 = to_m66592(g); /* hook up the driver */ - driver->driver.bus = NULL; m66592->driver = driver; m66592_bset(m66592, M66592_VBSE | M66592_URST, M66592_INTENB0); diff --git a/drivers/usb/gadget/udc/max3420_udc.c b/drivers/usb/gadget/udc/max3420_udc.c index 3074da00c3df..ddf0ed3eb4f2 100644 --- a/drivers/usb/gadget/udc/max3420_udc.c +++ b/drivers/usb/gadget/udc/max3420_udc.c @@ -1108,7 +1108,6 @@ static int max3420_udc_start(struct usb_gadget *gadget, spin_lock_irqsave(&udc->lock, flags); /* hook up the driver */ - driver->driver.bus = NULL; udc->driver = driver; udc->gadget.speed = USB_SPEED_FULL; diff --git a/drivers/usb/gadget/udc/mv_u3d_core.c b/drivers/usb/gadget/udc/mv_u3d_core.c index 598654a3cb41..411b6179782c 100644 --- a/drivers/usb/gadget/udc/mv_u3d_core.c +++ b/drivers/usb/gadget/udc/mv_u3d_core.c @@ -1243,7 +1243,6 @@ static int mv_u3d_start(struct usb_gadget *g, } /* hook up the driver ... */ - driver->driver.bus = NULL; u3d->driver = driver; u3d->ep0_dir = USB_DIR_OUT; diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c index fdb17d86cd65..b397f3a848cf 100644 --- a/drivers/usb/gadget/udc/mv_udc_core.c +++ b/drivers/usb/gadget/udc/mv_udc_core.c @@ -1359,7 +1359,6 @@ static int mv_udc_start(struct usb_gadget *gadget, spin_lock_irqsave(&udc->lock, flags); /* hook up the driver ... */ - driver->driver.bus = NULL; udc->driver = driver; udc->usb_state = USB_STATE_ATTACHED; diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 84605a4d0715..538c1b9a2883 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -1451,7 +1451,6 @@ static int net2272_start(struct usb_gadget *_gadget, dev->ep[i].irqs = 0; /* hook up the driver ... */ dev->softconnect = 1; - driver->driver.bus = NULL; dev->driver = driver; /* ... then enable host detection and ep0; and we're ready diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index d6a68631354a..1b929c519cd7 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -2423,7 +2423,6 @@ static int net2280_start(struct usb_gadget *_gadget, dev->ep[i].irqs = 0; /* hook up the driver ... */ - driver->driver.bus = NULL; dev->driver = driver; retval = device_create_file(&dev->pdev->dev, &dev_attr_function); diff --git a/drivers/usb/gadget/udc/omap_udc.c b/drivers/usb/gadget/udc/omap_udc.c index bea346e362b2..f660ebfa1379 100644 --- a/drivers/usb/gadget/udc/omap_udc.c +++ b/drivers/usb/gadget/udc/omap_udc.c @@ -2066,7 +2066,6 @@ static int omap_udc_start(struct usb_gadget *g, udc->softconnect = 1; /* hook up the driver */ - driver->driver.bus = NULL; udc->driver = driver; spin_unlock_irqrestore(&udc->lock, flags); diff --git a/drivers/usb/gadget/udc/pch_udc.c b/drivers/usb/gadget/udc/pch_udc.c index 9bb7a9d7a2fb..4f8617210d85 100644 --- a/drivers/usb/gadget/udc/pch_udc.c +++ b/drivers/usb/gadget/udc/pch_udc.c @@ -2908,7 +2908,6 @@ static int pch_udc_start(struct usb_gadget *g, { struct pch_udc_dev *dev = to_pch_udc(g); - driver->driver.bus = NULL; dev->driver = driver; /* get ready for ep0 traffic */ diff --git a/drivers/usb/gadget/udc/snps_udc_core.c b/drivers/usb/gadget/udc/snps_udc_core.c index 52ea4dcf6a92..2fc5d4d277bc 100644 --- a/drivers/usb/gadget/udc/snps_udc_core.c +++ b/drivers/usb/gadget/udc/snps_udc_core.c @@ -1933,7 +1933,6 @@ static int amd5536_udc_start(struct usb_gadget *g, struct udc *dev = to_amd5536_udc(g); u32 tmp; - driver->driver.bus = NULL; dev->driver = driver; /* Some gadget drivers use both ep0 directions. diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c index 9cea785934e5..38d06e5abfbb 100644 --- a/drivers/usb/host/ehci-fsl.c +++ b/drivers/usb/host/ehci-fsl.c @@ -29,7 +29,7 @@ #include "ehci-fsl.h" #define DRIVER_DESC "Freescale EHCI Host controller driver" -#define DRV_NAME "ehci-fsl" +#define DRV_NAME "fsl-ehci" static struct hc_driver __read_mostly fsl_ehci_hc_driver; diff --git a/drivers/usb/host/xen-hcd.c b/drivers/usb/host/xen-hcd.c index de1b09158318..46fdab940092 100644 --- a/drivers/usb/host/xen-hcd.c +++ b/drivers/usb/host/xen-hcd.c @@ -1530,15 +1530,13 @@ static void xenhcd_backend_changed(struct xenbus_device *dev, } } -static int xenhcd_remove(struct xenbus_device *dev) +static void xenhcd_remove(struct xenbus_device *dev) { struct xenhcd_info *info = dev_get_drvdata(&dev->dev); struct usb_hcd *hcd = xenhcd_info_to_hcd(info); xenhcd_destroy_rings(info); usb_put_hcd(hcd); - - return 0; } static int xenhcd_probe(struct xenbus_device *dev, diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c index 79d679b3e076..fb988e4ea924 100644 --- a/drivers/usb/host/xhci-pci.c +++ b/drivers/usb/host/xhci-pci.c @@ -78,9 +78,12 @@ static const char hcd_name[] = "xhci_hcd"; static struct hc_driver __read_mostly xhci_pci_hc_driver; static int xhci_pci_setup(struct usb_hcd *hcd); +static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, + struct usb_tt *tt, gfp_t mem_flags); static const struct xhci_driver_overrides xhci_pci_overrides __initconst = { .reset = xhci_pci_setup, + .update_hub_device = xhci_pci_update_hub_device, }; /* called after powerup, by probe or system-pm "wakeup" */ @@ -352,8 +355,38 @@ static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) NULL); ACPI_FREE(obj); } + +static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev) +{ + struct xhci_hcd *xhci = hcd_to_xhci(hcd); + struct xhci_hub *rhub = &xhci->usb3_rhub; + int ret; + int i; + + /* This is not the usb3 roothub we are looking for */ + if (hcd != rhub->hcd) + return; + + if (hdev->maxchild > rhub->num_ports) { + dev_err(&hdev->dev, "USB3 roothub port number mismatch\n"); + return; + } + + for (i = 0; i < hdev->maxchild; i++) { + ret = usb_acpi_port_lpm_incapable(hdev, i); + + dev_dbg(&hdev->dev, "port-%d disable U1/U2 _DSM: %d\n", i + 1, ret); + + if (ret >= 0) { + rhub->ports[i]->lpm_incapable = ret; + continue; + } + } +} + #else static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { } +static void xhci_find_lpm_incapable_ports(struct usb_hcd *hcd, struct usb_device *hdev) { } #endif /* CONFIG_ACPI */ /* called during probe() after chip reset completes */ @@ -386,6 +419,16 @@ static int xhci_pci_setup(struct usb_hcd *hcd) return xhci_pci_reinit(xhci, pdev); } +static int xhci_pci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, + struct usb_tt *tt, gfp_t mem_flags) +{ + /* Check if acpi claims some USB3 roothub ports are lpm incapable */ + if (!hdev->parent) + xhci_find_lpm_incapable_ports(hcd, hdev); + + return xhci_update_hub_device(hcd, hdev, tt, mem_flags); +} + /* * We need to register our own PCI probe function (instead of the USB core's * function) in order to create a second roothub under xHCI. @@ -455,6 +498,8 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) if (xhci->quirks & XHCI_DEFAULT_PM_RUNTIME_ALLOW) pm_runtime_allow(&dev->dev); + dma_set_max_seg_size(&dev->dev, UINT_MAX); + return 0; put_usb3_hcd: diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index ddc30037f9ce..f5b0e1ce22af 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -1169,7 +1169,10 @@ static void xhci_kill_endpoint_urbs(struct xhci_hcd *xhci, struct xhci_virt_ep *ep; struct xhci_ring *ring; - ep = &xhci->devs[slot_id]->eps[ep_index]; + ep = xhci_get_virt_ep(xhci, slot_id, ep_index); + if (!ep) + return; + if ((ep->ep_state & EP_HAS_STREAMS) || (ep->ep_state & EP_GETTING_NO_STREAMS)) { int stream_id; diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 79d7931c048a..2b280beb0011 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3974,6 +3974,7 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); struct xhci_virt_device *virt_dev; struct xhci_slot_ctx *slot_ctx; + unsigned long flags; int i, ret; /* @@ -4000,7 +4001,11 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) virt_dev->eps[i].ep_state &= ~EP_STOP_CMD_PENDING; virt_dev->udev = NULL; xhci_disable_slot(xhci, udev->slot_id); + + spin_lock_irqsave(&xhci->lock, flags); xhci_free_virt_device(xhci, udev->slot_id); + spin_unlock_irqrestore(&xhci->lock, flags); + } int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) @@ -5044,6 +5049,7 @@ static int xhci_enable_usb3_lpm_timeout(struct usb_hcd *hcd, struct usb_device *udev, enum usb3_link_state state) { struct xhci_hcd *xhci; + struct xhci_port *port; u16 hub_encoded_timeout; int mel; int ret; @@ -5060,6 +5066,13 @@ static int xhci_enable_usb3_lpm_timeout(struct usb_hcd *hcd, if (xhci_check_tier_policy(xhci, udev, state) < 0) return USB3_LPM_DISABLED; + /* If connected to root port then check port can handle lpm */ + if (udev->parent && !udev->parent->parent) { + port = xhci->usb3_rhub.ports[udev->portnum - 1]; + if (port->lpm_incapable) + return USB3_LPM_DISABLED; + } + hub_encoded_timeout = xhci_calculate_lpm_timeout(hcd, udev, state); mel = calculate_max_exit_latency(udev, state, hub_encoded_timeout); if (mel < 0) { @@ -5119,7 +5132,7 @@ static int xhci_disable_usb3_lpm_timeout(struct usb_hcd *hcd, /* Once a hub descriptor is fetched for a device, we need to update the xHC's * internal data structures for the device. */ -static int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, +int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, struct usb_tt *tt, gfp_t mem_flags) { struct xhci_hcd *xhci = hcd_to_xhci(hcd); @@ -5219,6 +5232,7 @@ static int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, xhci_free_command(xhci, config_cmd); return ret; } +EXPORT_SYMBOL_GPL(xhci_update_hub_device); static int xhci_get_frame(struct usb_hcd *hcd) { @@ -5502,6 +5516,8 @@ void xhci_init_driver(struct hc_driver *drv, drv->check_bandwidth = over->check_bandwidth; if (over->reset_bandwidth) drv->reset_bandwidth = over->reset_bandwidth; + if (over->update_hub_device) + drv->update_hub_device = over->update_hub_device; } } EXPORT_SYMBOL_GPL(xhci_init_driver); diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index c9f06c5e4e9d..dcee7f3207ad 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -1735,6 +1735,7 @@ struct xhci_port { int hcd_portnum; struct xhci_hub *rhub; struct xhci_port_cap *port_cap; + unsigned int lpm_incapable:1; }; struct xhci_hub { @@ -1943,6 +1944,8 @@ struct xhci_driver_overrides { struct usb_host_endpoint *ep); int (*check_bandwidth)(struct usb_hcd *, struct usb_device *); void (*reset_bandwidth)(struct usb_hcd *, struct usb_device *); + int (*update_hub_device)(struct usb_hcd *hcd, struct usb_device *hdev, + struct usb_tt *tt, gfp_t mem_flags); }; #define XHCI_CFC_DELAY 10 @@ -2122,6 +2125,8 @@ int xhci_drop_endpoint(struct usb_hcd *hcd, struct usb_device *udev, struct usb_host_endpoint *ep); int xhci_check_bandwidth(struct usb_hcd *hcd, struct usb_device *udev); void xhci_reset_bandwidth(struct usb_hcd *hcd, struct usb_device *udev); +int xhci_update_hub_device(struct usb_hcd *hcd, struct usb_device *hdev, + struct usb_tt *tt, gfp_t mem_flags); int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id); int xhci_ext_cap_init(struct xhci_hcd *xhci); diff --git a/drivers/usb/misc/iowarrior.c b/drivers/usb/misc/iowarrior.c index f9427a67789c..1e3df27bab58 100644 --- a/drivers/usb/misc/iowarrior.c +++ b/drivers/usb/misc/iowarrior.c @@ -814,7 +814,7 @@ static int iowarrior_probe(struct usb_interface *interface, break; case USB_DEVICE_ID_CODEMERCS_IOW100: - dev->report_size = 13; + dev->report_size = 12; break; } } diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c index 94e7966e199d..969c4c4f2ae9 100644 --- a/drivers/usb/misc/onboard_usb_hub.c +++ b/drivers/usb/misc/onboard_usb_hub.c @@ -27,7 +27,10 @@ #include "onboard_usb_hub.h" +static void onboard_hub_attach_usb_driver(struct work_struct *work); + static struct usb_device_driver onboard_hub_usbdev_driver; +static DECLARE_WORK(attach_usb_driver_work, onboard_hub_attach_usb_driver); /************************** Platform driver **************************/ @@ -45,7 +48,6 @@ struct onboard_hub { bool is_powered_on; bool going_away; struct list_head udev_list; - struct work_struct attach_usb_driver_work; struct mutex lock; }; @@ -271,8 +273,7 @@ static int onboard_hub_probe(struct platform_device *pdev) * This needs to be done deferred to avoid self-deadlocks on systems * with nested onboard hubs. */ - INIT_WORK(&hub->attach_usb_driver_work, onboard_hub_attach_usb_driver); - schedule_work(&hub->attach_usb_driver_work); + schedule_work(&attach_usb_driver_work); return 0; } @@ -285,9 +286,6 @@ static int onboard_hub_remove(struct platform_device *pdev) hub->going_away = true; - if (&hub->attach_usb_driver_work != current_work()) - cancel_work_sync(&hub->attach_usb_driver_work); - mutex_lock(&hub->lock); /* unbind the USB devices to avoid dangling references to this device */ @@ -433,13 +431,13 @@ static int __init onboard_hub_init(void) { int ret; - ret = platform_driver_register(&onboard_hub_driver); + ret = usb_register_device_driver(&onboard_hub_usbdev_driver, THIS_MODULE); if (ret) return ret; - ret = usb_register_device_driver(&onboard_hub_usbdev_driver, THIS_MODULE); + ret = platform_driver_register(&onboard_hub_driver); if (ret) - platform_driver_unregister(&onboard_hub_driver); + usb_deregister_device_driver(&onboard_hub_usbdev_driver); return ret; } @@ -449,6 +447,8 @@ static void __exit onboard_hub_exit(void) { usb_deregister_device_driver(&onboard_hub_usbdev_driver); platform_driver_unregister(&onboard_hub_driver); + + cancel_work_sync(&attach_usb_driver_work); } module_exit(onboard_hub_exit); diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c index 476f55d1fec3..44a21ec865fb 100644 --- a/drivers/usb/musb/omap2430.c +++ b/drivers/usb/musb/omap2430.c @@ -411,8 +411,10 @@ static int omap2430_probe(struct platform_device *pdev) memset(musb_res, 0, sizeof(*musb_res) * ARRAY_SIZE(musb_res)); res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) + if (!res) { + ret = -EINVAL; goto err2; + } musb_res[i].start = res->start; musb_res[i].end = res->end; diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 67372acc2352..832ad592b7ef 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -60,6 +60,7 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x0846, 0x1100) }, /* NetGear Managed Switch M4100 series, M5300 series, M7100 series */ { USB_DEVICE(0x08e6, 0x5501) }, /* Gemalto Prox-PU/CU contactless smartcard reader */ { USB_DEVICE(0x08FD, 0x000A) }, /* Digianswer A/S , ZigBee/802.15.4 MAC Device */ + { USB_DEVICE(0x0908, 0x0070) }, /* Siemens SCALANCE LPE-9000 USB Serial Console */ { USB_DEVICE(0x0908, 0x01FF) }, /* Siemens RUGGEDCOM USB Serial Console */ { USB_DEVICE(0x0988, 0x0578) }, /* Teraoka AD2000 */ { USB_DEVICE(0x0B00, 0x3070) }, /* Ingenico 3070 */ diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index dee79c7d82d5..ee5ac4ef7e16 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -255,10 +255,16 @@ static void option_instat_callback(struct urb *urb); #define QUECTEL_PRODUCT_EP06 0x0306 #define QUECTEL_PRODUCT_EM05G 0x030a #define QUECTEL_PRODUCT_EM060K 0x030b +#define QUECTEL_PRODUCT_EM05G_CS 0x030c +#define QUECTEL_PRODUCT_EM05CN_SG 0x0310 #define QUECTEL_PRODUCT_EM05G_SG 0x0311 +#define QUECTEL_PRODUCT_EM05CN 0x0312 +#define QUECTEL_PRODUCT_EM05G_GR 0x0313 +#define QUECTEL_PRODUCT_EM05G_RS 0x0314 #define QUECTEL_PRODUCT_EM12 0x0512 #define QUECTEL_PRODUCT_RM500Q 0x0800 #define QUECTEL_PRODUCT_RM520N 0x0801 +#define QUECTEL_PRODUCT_EC200U 0x0901 #define QUECTEL_PRODUCT_EC200S_CN 0x6002 #define QUECTEL_PRODUCT_EC200T 0x6026 #define QUECTEL_PRODUCT_RM500K 0x7001 @@ -1159,8 +1165,18 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff), .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN, 0xff), + .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05CN_SG, 0xff), + .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G, 0xff), .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_CS, 0xff), + .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_GR, 0xff), + .driver_info = RSVD(6) | ZLP }, + { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_RS, 0xff), + .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_INTERFACE_CLASS(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM05G_SG, 0xff), .driver_info = RSVD(6) | ZLP }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM060K, 0xff, 0x00, 0x40) }, @@ -1180,6 +1196,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM520N, 0xff, 0, 0) }, + { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200U, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200S_CN, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC200T, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_RM500K, 0xff, 0x00, 0x00) }, diff --git a/drivers/usb/storage/uas-detect.h b/drivers/usb/storage/uas-detect.h index 3f720faa6f97..d73282c0ec50 100644 --- a/drivers/usb/storage/uas-detect.h +++ b/drivers/usb/storage/uas-detect.h @@ -116,6 +116,19 @@ static int uas_use_uas_driver(struct usb_interface *intf, if (le16_to_cpu(udev->descriptor.idVendor) == 0x0bc2) flags |= US_FL_NO_ATA_1X; + /* + * RTL9210-based enclosure from HIKSEMI, MD202 reportedly have issues + * with UAS. This isn't distinguishable with just idVendor and + * idProduct, use manufacturer and product too. + * + * Reported-by: Hongling Zeng <zenghongling@kylinos.cn> + */ + if (le16_to_cpu(udev->descriptor.idVendor) == 0x0bda && + le16_to_cpu(udev->descriptor.idProduct) == 0x9210 && + (udev->manufacturer && !strcmp(udev->manufacturer, "HIKSEMI")) && + (udev->product && !strcmp(udev->product, "MD202"))) + flags |= US_FL_IGNORE_UAS; + usb_stor_adjust_quirks(udev, &flags); if (flags & US_FL_IGNORE_UAS) { diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h index 251778d14e2d..c7b763d6d102 100644 --- a/drivers/usb/storage/unusual_uas.h +++ b/drivers/usb/storage/unusual_uas.h @@ -83,13 +83,6 @@ UNUSUAL_DEV(0x0bc2, 0x331a, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_NO_REPORT_LUNS), -/* Reported-by: Hongling Zeng <zenghongling@kylinos.cn> */ -UNUSUAL_DEV(0x0bda, 0x9210, 0x0000, 0x9999, - "Hiksemi", - "External HDD", - USB_SC_DEVICE, USB_PR_DEVICE, NULL, - US_FL_IGNORE_UAS), - /* Reported-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> */ UNUSUAL_DEV(0x13fd, 0x3940, 0x0000, 0x9999, "Initio Corporation", diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index de66a2949e33..9a6860285fbe 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -419,6 +419,18 @@ static const char * const pin_assignments[] = { [DP_PIN_ASSIGN_F] = "F", }; +/* + * Helper function to extract a peripheral's currently supported + * Pin Assignments from its DisplayPort alternate mode state. + */ +static u8 get_current_pin_assignments(struct dp_altmode *dp) +{ + if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_UFP_U_AS_DFP_D) + return DP_CAP_PIN_ASSIGN_DFP_D(dp->alt->vdo); + else + return DP_CAP_PIN_ASSIGN_UFP_D(dp->alt->vdo); +} + static ssize_t pin_assignment_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) @@ -445,10 +457,7 @@ pin_assignment_store(struct device *dev, struct device_attribute *attr, goto out_unlock; } - if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D) - assignments = DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo); - else - assignments = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo); + assignments = get_current_pin_assignments(dp); if (!(DP_CONF_GET_PIN_ASSIGN(conf) & assignments)) { ret = -EINVAL; @@ -485,10 +494,7 @@ static ssize_t pin_assignment_show(struct device *dev, cur = get_count_order(DP_CONF_GET_PIN_ASSIGN(dp->data.conf)); - if (DP_CONF_CURRENTLY(dp->data.conf) == DP_CONF_DFP_D) - assignments = DP_CAP_UFP_D_PIN_ASSIGN(dp->alt->vdo); - else - assignments = DP_CAP_DFP_D_PIN_ASSIGN(dp->alt->vdo); + assignments = get_current_pin_assignments(dp); for (i = 0; assignments; assignments >>= 1, i++) { if (assignments & 1) { diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 904c7b4ce2f0..59b366b5c614 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4594,14 +4594,13 @@ static void run_state_machine(struct tcpm_port *port) tcpm_set_state(port, ready_state(port), 0); break; case DR_SWAP_CHANGE_DR: - if (port->data_role == TYPEC_HOST) { - tcpm_unregister_altmodes(port); + tcpm_unregister_altmodes(port); + if (port->data_role == TYPEC_HOST) tcpm_set_roles(port, true, port->pwr_role, TYPEC_DEVICE); - } else { + else tcpm_set_roles(port, true, port->pwr_role, TYPEC_HOST); - } tcpm_ams_finish(port); tcpm_set_state(port, ready_state(port), 0); break; diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index eabe519013e7..1cf8947c6d66 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -187,6 +187,7 @@ EXPORT_SYMBOL_GPL(ucsi_send_command); struct ucsi_work { struct delayed_work work; + struct list_head node; unsigned long delay; unsigned int count; struct ucsi_connector *con; @@ -202,6 +203,7 @@ static void ucsi_poll_worker(struct work_struct *work) mutex_lock(&con->lock); if (!con->partner) { + list_del(&uwork->node); mutex_unlock(&con->lock); kfree(uwork); return; @@ -209,10 +211,12 @@ static void ucsi_poll_worker(struct work_struct *work) ret = uwork->cb(con); - if (uwork->count-- && (ret == -EBUSY || ret == -ETIMEDOUT)) + if (uwork->count-- && (ret == -EBUSY || ret == -ETIMEDOUT)) { queue_delayed_work(con->wq, &uwork->work, uwork->delay); - else + } else { + list_del(&uwork->node); kfree(uwork); + } mutex_unlock(&con->lock); } @@ -236,6 +240,7 @@ static int ucsi_partner_task(struct ucsi_connector *con, uwork->con = con; uwork->cb = cb; + list_add_tail(&uwork->node, &con->partner_tasks); queue_delayed_work(con->wq, &uwork->work, delay); return 0; @@ -1056,6 +1061,7 @@ static int ucsi_register_port(struct ucsi *ucsi, int index) INIT_WORK(&con->work, ucsi_handle_connector_change); init_completion(&con->complete); mutex_init(&con->lock); + INIT_LIST_HEAD(&con->partner_tasks); con->num = index + 1; con->ucsi = ucsi; @@ -1263,6 +1269,9 @@ err_unregister: con->port = NULL; } + kfree(ucsi->connector); + ucsi->connector = NULL; + err_reset: memset(&ucsi->cap, 0, sizeof(ucsi->cap)); ucsi_reset_ppm(ucsi); @@ -1294,7 +1303,8 @@ static void ucsi_resume_work(struct work_struct *work) int ucsi_resume(struct ucsi *ucsi) { - queue_work(system_long_wq, &ucsi->resume_work); + if (ucsi->connector) + queue_work(system_long_wq, &ucsi->resume_work); return 0; } EXPORT_SYMBOL_GPL(ucsi_resume); @@ -1414,14 +1424,29 @@ void ucsi_unregister(struct ucsi *ucsi) /* Disable notifications */ ucsi->ops->async_write(ucsi, UCSI_CONTROL, &cmd, sizeof(cmd)); + if (!ucsi->connector) + return; + for (i = 0; i < ucsi->cap.num_connectors; i++) { cancel_work_sync(&ucsi->connector[i].work); ucsi_unregister_partner(&ucsi->connector[i]); ucsi_unregister_altmodes(&ucsi->connector[i], UCSI_RECIPIENT_CON); ucsi_unregister_port_psy(&ucsi->connector[i]); - if (ucsi->connector[i].wq) + + if (ucsi->connector[i].wq) { + struct ucsi_work *uwork; + + mutex_lock(&ucsi->connector[i].lock); + /* + * queue delayed items immediately so they can execute + * and free themselves before the wq is destroyed + */ + list_for_each_entry(uwork, &ucsi->connector[i].partner_tasks, node) + mod_delayed_work(ucsi->connector[i].wq, &uwork->work, 0); + mutex_unlock(&ucsi->connector[i].lock); destroy_workqueue(ucsi->connector[i].wq); + } typec_unregister_port(ucsi->connector[i].port); } diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index c968474ee547..60ce9fb6e745 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -322,6 +322,7 @@ struct ucsi_connector { struct work_struct work; struct completion complete; struct workqueue_struct *wq; + struct list_head partner_tasks; struct typec_port *port; struct typec_partner *partner; diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c index f9c0044c6442..44b29289aa19 100644 --- a/drivers/vdpa/ifcvf/ifcvf_main.c +++ b/drivers/vdpa/ifcvf/ifcvf_main.c @@ -849,7 +849,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = ifcvf_init_hw(vf, pdev); if (ret) { IFCVF_ERR(pdev, "Failed to init IFCVF hw\n"); - return ret; + goto err; } for (i = 0; i < vf->nr_vring; i++) diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index 23c24fe98c00..2209372f236d 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -1856,24 +1856,33 @@ unwind: * significantly boosts non-hugetlbfs mappings and doesn't seem to hurt when * hugetlbfs is in use. */ -static void vfio_test_domain_fgsp(struct vfio_domain *domain) +static void vfio_test_domain_fgsp(struct vfio_domain *domain, struct list_head *regions) { - struct page *pages; int ret, order = get_order(PAGE_SIZE * 2); + struct vfio_iova *region; + struct page *pages; + dma_addr_t start; pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); if (!pages) return; - ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2, - IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE); - if (!ret) { - size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE); + list_for_each_entry(region, regions, list) { + start = ALIGN(region->start, PAGE_SIZE * 2); + if (start >= region->end || (region->end - start < PAGE_SIZE * 2)) + continue; - if (unmapped == PAGE_SIZE) - iommu_unmap(domain->domain, PAGE_SIZE, PAGE_SIZE); - else - domain->fgsp = true; + ret = iommu_map(domain->domain, start, page_to_phys(pages), PAGE_SIZE * 2, + IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE); + if (!ret) { + size_t unmapped = iommu_unmap(domain->domain, start, PAGE_SIZE); + + if (unmapped == PAGE_SIZE) + iommu_unmap(domain->domain, start + PAGE_SIZE, PAGE_SIZE); + else + domain->fgsp = true; + } + break; } __free_pages(pages, order); @@ -2326,7 +2335,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, } } - vfio_test_domain_fgsp(domain); + vfio_test_domain_fgsp(domain, &iova_copy); /* replay mappings on new domains */ ret = vfio_iommu_replay(iommu, domain); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 9af19b0cf3b7..4c538b30fd76 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1511,6 +1511,9 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) nvq = &n->vqs[index]; mutex_lock(&vq->mutex); + if (fd == -1) + vhost_clear_msg(&n->dev); + /* Verify that ring has been setup correctly. */ if (!vhost_vq_access_ok(vq)) { r = -EFAULT; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index dca6346d75b3..d5ecb8876fc9 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -80,7 +80,7 @@ struct vhost_scsi_cmd { struct scatterlist *tvc_prot_sgl; struct page **tvc_upages; /* Pointer to response header iovec */ - struct iovec tvc_resp_iov; + struct iovec *tvc_resp_iov; /* Pointer to vhost_scsi for our device */ struct vhost_scsi *tvc_vhost; /* Pointer to vhost_virtqueue for the cmd */ @@ -563,7 +563,7 @@ static void vhost_scsi_complete_cmd_work(struct vhost_work *work) memcpy(v_rsp.sense, cmd->tvc_sense_buf, se_cmd->scsi_sense_length); - iov_iter_init(&iov_iter, ITER_DEST, &cmd->tvc_resp_iov, + iov_iter_init(&iov_iter, ITER_DEST, cmd->tvc_resp_iov, cmd->tvc_in_iovs, sizeof(v_rsp)); ret = copy_to_iter(&v_rsp, sizeof(v_rsp), &iov_iter); if (likely(ret == sizeof(v_rsp))) { @@ -594,6 +594,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, struct vhost_scsi_cmd *cmd; struct vhost_scsi_nexus *tv_nexus; struct scatterlist *sg, *prot_sg; + struct iovec *tvc_resp_iov; struct page **pages; int tag; @@ -613,6 +614,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, sg = cmd->tvc_sgl; prot_sg = cmd->tvc_prot_sgl; pages = cmd->tvc_upages; + tvc_resp_iov = cmd->tvc_resp_iov; memset(cmd, 0, sizeof(*cmd)); cmd->tvc_sgl = sg; cmd->tvc_prot_sgl = prot_sg; @@ -625,6 +627,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, cmd->tvc_data_direction = data_direction; cmd->tvc_nexus = tv_nexus; cmd->inflight = vhost_scsi_get_inflight(vq); + cmd->tvc_resp_iov = tvc_resp_iov; memcpy(cmd->tvc_cdb, cdb, VHOST_SCSI_MAX_CDB_SIZE); @@ -935,7 +938,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) struct iov_iter in_iter, prot_iter, data_iter; u64 tag; u32 exp_data_len, data_direction; - int ret, prot_bytes, c = 0; + int ret, prot_bytes, i, c = 0; u16 lun; u8 task_attr; bool t10_pi = vhost_has_feature(vq, VIRTIO_SCSI_F_T10_PI); @@ -1092,7 +1095,8 @@ vhost_scsi_handle_vq(struct vhost_scsi *vs, struct vhost_virtqueue *vq) } cmd->tvc_vhost = vs; cmd->tvc_vq = vq; - cmd->tvc_resp_iov = vq->iov[vc.out]; + for (i = 0; i < vc.in ; i++) + cmd->tvc_resp_iov[i] = vq->iov[vc.out + i]; cmd->tvc_in_iovs = vc.in; pr_debug("vhost_scsi got command opcode: %#02x, lun: %d\n", @@ -1461,6 +1465,7 @@ static void vhost_scsi_destroy_vq_cmds(struct vhost_virtqueue *vq) kfree(tv_cmd->tvc_sgl); kfree(tv_cmd->tvc_prot_sgl); kfree(tv_cmd->tvc_upages); + kfree(tv_cmd->tvc_resp_iov); } sbitmap_free(&svq->scsi_tags); @@ -1508,6 +1513,14 @@ static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) goto out; } + tv_cmd->tvc_resp_iov = kcalloc(UIO_MAXIOV, + sizeof(struct iovec), + GFP_KERNEL); + if (!tv_cmd->tvc_resp_iov) { + pr_err("Unable to allocate tv_cmd->tvc_resp_iov\n"); + goto out; + } + tv_cmd->tvc_prot_sgl = kcalloc(VHOST_SCSI_PREALLOC_PROT_SGLS, sizeof(struct scatterlist), GFP_KERNEL); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index cbe72bfd2f1f..43c9770b86e5 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -661,7 +661,7 @@ void vhost_dev_stop(struct vhost_dev *dev) } EXPORT_SYMBOL_GPL(vhost_dev_stop); -static void vhost_clear_msg(struct vhost_dev *dev) +void vhost_clear_msg(struct vhost_dev *dev) { struct vhost_msg_node *node, *n; @@ -679,6 +679,7 @@ static void vhost_clear_msg(struct vhost_dev *dev) spin_unlock(&dev->iotlb_lock); } +EXPORT_SYMBOL_GPL(vhost_clear_msg); void vhost_dev_cleanup(struct vhost_dev *dev) { diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index d9109107af08..790b296271f1 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -181,6 +181,7 @@ long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp); long vhost_vring_ioctl(struct vhost_dev *d, unsigned int ioctl, void __user *argp); bool vhost_vq_access_ok(struct vhost_virtqueue *vq); bool vhost_log_access_ok(struct vhost_dev *); +void vhost_clear_msg(struct vhost_dev *dev); int vhost_get_vq_desc(struct vhost_virtqueue *, struct iovec iov[], unsigned int iov_count, diff --git a/drivers/video/fbdev/atmel_lcdfb.c b/drivers/video/fbdev/atmel_lcdfb.c index 1fc8de4ecbeb..8187a7c4f910 100644 --- a/drivers/video/fbdev/atmel_lcdfb.c +++ b/drivers/video/fbdev/atmel_lcdfb.c @@ -49,7 +49,6 @@ struct atmel_lcdfb_info { struct clk *lcdc_clk; struct backlight_device *backlight; - u8 bl_power; u8 saved_lcdcon; u32 pseudo_palette[16]; @@ -109,22 +108,7 @@ static u32 contrast_ctr = ATMEL_LCDC_PS_DIV8 static int atmel_bl_update_status(struct backlight_device *bl) { struct atmel_lcdfb_info *sinfo = bl_get_data(bl); - int power = sinfo->bl_power; - int brightness = bl->props.brightness; - - /* REVISIT there may be a meaningful difference between - * fb_blank and power ... there seem to be some cases - * this doesn't handle correctly. - */ - if (bl->props.fb_blank != sinfo->bl_power) - power = bl->props.fb_blank; - else if (bl->props.power != sinfo->bl_power) - power = bl->props.power; - - if (brightness < 0 && power == FB_BLANK_UNBLANK) - brightness = lcdc_readl(sinfo, ATMEL_LCDC_CONTRAST_VAL); - else if (power != FB_BLANK_UNBLANK) - brightness = 0; + int brightness = backlight_get_brightness(bl); lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_VAL, brightness); if (contrast_ctr & ATMEL_LCDC_POL_POSITIVE) @@ -133,8 +117,6 @@ static int atmel_bl_update_status(struct backlight_device *bl) else lcdc_writel(sinfo, ATMEL_LCDC_CONTRAST_CTR, contrast_ctr); - bl->props.fb_blank = bl->props.power = sinfo->bl_power = power; - return 0; } @@ -155,8 +137,6 @@ static void init_backlight(struct atmel_lcdfb_info *sinfo) struct backlight_properties props; struct backlight_device *bl; - sinfo->bl_power = FB_BLANK_UNBLANK; - if (sinfo->backlight) return; diff --git a/drivers/video/fbdev/aty/aty128fb.c b/drivers/video/fbdev/aty/aty128fb.c index dd31b9d7d337..36a9ac05a340 100644 --- a/drivers/video/fbdev/aty/aty128fb.c +++ b/drivers/video/fbdev/aty/aty128fb.c @@ -1766,12 +1766,10 @@ static int aty128_bl_update_status(struct backlight_device *bd) unsigned int reg = aty_ld_le32(LVDS_GEN_CNTL); int level; - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK || - !par->lcd_on) + if (!par->lcd_on) level = 0; else - level = bd->props.brightness; + level = backlight_get_brightness(bd); reg |= LVDS_BL_MOD_EN | LVDS_BLON; if (level > 0) { diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index d59215a4992e..b02e4e645035 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -2219,13 +2219,7 @@ static int aty_bl_update_status(struct backlight_device *bd) { struct atyfb_par *par = bl_get_data(bd); unsigned int reg = aty_ld_lcd(LCD_MISC_CNTL, par); - int level; - - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; + int level = backlight_get_brightness(bd); reg |= (BLMOD_EN | BIASMOD_EN); if (level > 0) { diff --git a/drivers/video/fbdev/aty/radeon_backlight.c b/drivers/video/fbdev/aty/radeon_backlight.c index d2c1263ad260..427adc838f77 100644 --- a/drivers/video/fbdev/aty/radeon_backlight.c +++ b/drivers/video/fbdev/aty/radeon_backlight.c @@ -57,11 +57,7 @@ static int radeon_bl_update_status(struct backlight_device *bd) * backlight. This provides some greater power saving and the display * is useless without backlight anyway. */ - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; + level = backlight_get_brightness(bd); del_timer_sync(&rinfo->lvds_timer); radeon_engine_idle(); diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c index 14a7d404062c..1b14c21af2b7 100644 --- a/drivers/video/fbdev/core/fbcon.c +++ b/drivers/video/fbdev/core/fbcon.c @@ -2495,9 +2495,12 @@ static int fbcon_set_font(struct vc_data *vc, struct console_font *font, h > FBCON_SWAP(info->var.rotate, info->var.yres, info->var.xres)) return -EINVAL; + if (font->width > 32 || font->height > 32) + return -EINVAL; + /* Make sure drawing engine can handle the font */ - if (!(info->pixmap.blit_x & (1 << (font->width - 1))) || - !(info->pixmap.blit_y & (1 << (font->height - 1)))) + if (!(info->pixmap.blit_x & BIT(font->width - 1)) || + !(info->pixmap.blit_y & BIT(font->height - 1))) return -EINVAL; /* Make sure driver can handle the font length */ diff --git a/drivers/video/fbdev/core/fbmon.c b/drivers/video/fbdev/core/fbmon.c index b0e690f41025..79e5bfbdd34c 100644 --- a/drivers/video/fbdev/core/fbmon.c +++ b/drivers/video/fbdev/core/fbmon.c @@ -1050,7 +1050,7 @@ static u32 fb_get_vblank(u32 hfreq) } /** - * fb_get_hblank_by_freq - get horizontal blank time given hfreq + * fb_get_hblank_by_hfreq - get horizontal blank time given hfreq * @hfreq: horizontal freq * @xres: horizontal resolution in pixels * diff --git a/drivers/video/fbdev/mx3fb.c b/drivers/video/fbdev/mx3fb.c index b945b68984b9..76771e126d0a 100644 --- a/drivers/video/fbdev/mx3fb.c +++ b/drivers/video/fbdev/mx3fb.c @@ -283,12 +283,7 @@ static int mx3fb_bl_get_brightness(struct backlight_device *bl) static int mx3fb_bl_update_status(struct backlight_device *bl) { struct mx3fb_data *fbd = bl_get_data(bl); - int brightness = bl->props.brightness; - - if (bl->props.power != FB_BLANK_UNBLANK) - brightness = 0; - if (bl->props.fb_blank != FB_BLANK_UNBLANK) - brightness = 0; + int brightness = backlight_get_brightness(bl); fbd->backlight_level = (fbd->backlight_level & ~0xFF) | brightness; diff --git a/drivers/video/fbdev/nvidia/nv_backlight.c b/drivers/video/fbdev/nvidia/nv_backlight.c index 2ce53529f636..503a7a683855 100644 --- a/drivers/video/fbdev/nvidia/nv_backlight.c +++ b/drivers/video/fbdev/nvidia/nv_backlight.c @@ -49,17 +49,11 @@ static int nvidia_bl_update_status(struct backlight_device *bd) { struct nvidia_par *par = bl_get_data(bd); u32 tmp_pcrt, tmp_pmc, fpcontrol; - int level; + int level = backlight_get_brightness(bd); if (!par->FlatPanel) return 0; - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; - tmp_pmc = NV_RD32(par->PMC, 0x10F0) & 0x0000FFFF; tmp_pcrt = NV_RD32(par->PCRTC0, 0x081C) & 0xFFFFFFFC; fpcontrol = NV_RD32(par->PRAMDAC, 0x0848) & 0xCFFFFFCC; diff --git a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c index 4fc4b26a8d30..ba94a0a7bd4f 100644 --- a/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c +++ b/drivers/video/fbdev/omap2/omapfb/displays/panel-dsi-cm.c @@ -331,13 +331,7 @@ static int dsicm_bl_update_status(struct backlight_device *dev) struct panel_drv_data *ddata = dev_get_drvdata(&dev->dev); struct omap_dss_device *in = ddata->in; int r; - int level; - - if (dev->props.fb_blank == FB_BLANK_UNBLANK && - dev->props.power == FB_BLANK_UNBLANK) - level = dev->props.brightness; - else - level = 0; + int level = backlight_get_brightness(dev); dev_dbg(&ddata->pdev->dev, "update brightness to %d\n", level); diff --git a/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c index bc5a44c2a144..ae937854403b 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/display-sysfs.c @@ -10,6 +10,7 @@ #define DSS_SUBSYS_NAME "DISPLAY" #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/module.h> #include <linux/platform_device.h> #include <linux/sysfs.h> @@ -36,7 +37,7 @@ static ssize_t display_enabled_store(struct omap_dss_device *dssdev, int r; bool enable; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; @@ -73,7 +74,7 @@ static ssize_t display_tear_store(struct omap_dss_device *dssdev, if (!dssdev->driver->enable_te || !dssdev->driver->get_te) return -ENOENT; - r = strtobool(buf, &te); + r = kstrtobool(buf, &te); if (r) return r; @@ -183,7 +184,7 @@ static ssize_t display_mirror_store(struct omap_dss_device *dssdev, if (!dssdev->driver->set_mirror || !dssdev->driver->get_mirror) return -ENOENT; - r = strtobool(buf, &mirror); + r = kstrtobool(buf, &mirror); if (r) return r; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c index ba21c4a2633d..1b644be5fe2e 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/manager-sysfs.c @@ -10,6 +10,7 @@ #define DSS_SUBSYS_NAME "MANAGER" #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/platform_device.h> @@ -246,7 +247,7 @@ static ssize_t manager_trans_key_enabled_store(struct omap_overlay_manager *mgr, bool enable; int r; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; @@ -290,7 +291,7 @@ static ssize_t manager_alpha_blending_enabled_store( if(!dss_has_feature(FEAT_ALPHA_FIXED_ZORDER)) return -ENODEV; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; @@ -329,7 +330,7 @@ static ssize_t manager_cpr_enable_store(struct omap_overlay_manager *mgr, if (!dss_has_feature(FEAT_CPR)) return -ENODEV; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; diff --git a/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c b/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c index 601c0beb6de9..1da4fb1c77b4 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/overlay-sysfs.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/sysfs.h> #include <linux/kobject.h> +#include <linux/kstrtox.h> #include <linux/platform_device.h> #include <video/omapfb_dss.h> @@ -210,7 +211,7 @@ static ssize_t overlay_enabled_store(struct omap_overlay *ovl, const char *buf, int r; bool enable; - r = strtobool(buf, &enable); + r = kstrtobool(buf, &enable); if (r) return r; diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c b/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c index 06dc41aa0354..831b2c2fbdf9 100644 --- a/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c +++ b/drivers/video/fbdev/omap2/omapfb/omapfb-sysfs.c @@ -15,6 +15,7 @@ #include <linux/uaccess.h> #include <linux/platform_device.h> #include <linux/kernel.h> +#include <linux/kstrtox.h> #include <linux/mm.h> #include <linux/omapfb.h> @@ -96,7 +97,7 @@ static ssize_t store_mirror(struct device *dev, int r; struct fb_var_screeninfo new_var; - r = strtobool(buf, &mirror); + r = kstrtobool(buf, &mirror); if (r) return r; diff --git a/drivers/video/fbdev/riva/fbdev.c b/drivers/video/fbdev/riva/fbdev.c index 644278146d3b..41edc6e79460 100644 --- a/drivers/video/fbdev/riva/fbdev.c +++ b/drivers/video/fbdev/riva/fbdev.c @@ -293,13 +293,7 @@ static int riva_bl_update_status(struct backlight_device *bd) { struct riva_par *par = bl_get_data(bd); U032 tmp_pcrt, tmp_pmc; - int level; - - if (bd->props.power != FB_BLANK_UNBLANK || - bd->props.fb_blank != FB_BLANK_UNBLANK) - level = 0; - else - level = bd->props.brightness; + int level = backlight_get_brightness(bd); tmp_pmc = NV_RD32(par->riva.PMC, 0x10F0) & 0x0000FFFF; tmp_pcrt = NV_RD32(par->riva.PCRTC0, 0x081C) & 0xFFFFFFFC; diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c index 8752d389e382..d7f3e6281ce4 100644 --- a/drivers/video/fbdev/xen-fbfront.c +++ b/drivers/video/fbdev/xen-fbfront.c @@ -67,7 +67,7 @@ MODULE_PARM_DESC(video, "Video memory size in MB, width, height in pixels (default 2,800,600)"); static void xenfb_make_preferred_console(void); -static int xenfb_remove(struct xenbus_device *); +static void xenfb_remove(struct xenbus_device *); static void xenfb_init_shared_page(struct xenfb_info *, struct fb_info *); static int xenfb_connect_backend(struct xenbus_device *, struct xenfb_info *); static void xenfb_disconnect_backend(struct xenfb_info *); @@ -523,7 +523,7 @@ static int xenfb_resume(struct xenbus_device *dev) return xenfb_connect_backend(dev, info); } -static int xenfb_remove(struct xenbus_device *dev) +static void xenfb_remove(struct xenbus_device *dev) { struct xenfb_info *info = dev_get_drvdata(&dev->dev); @@ -538,8 +538,6 @@ static int xenfb_remove(struct xenbus_device *dev) vfree(info->gfns); vfree(info->fb); kfree(info); - - return 0; } static unsigned long vmalloc_to_gfn(void *address) diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c index f2ae2e563dc5..4a2ddf730a3a 100644 --- a/drivers/w1/w1.c +++ b/drivers/w1/w1.c @@ -1166,6 +1166,8 @@ int w1_process(void *data) /* remainder if it woke up early */ unsigned long jremain = 0; + atomic_inc(&dev->refcnt); + for (;;) { if (!jremain && dev->search_count) { @@ -1193,8 +1195,10 @@ int w1_process(void *data) */ mutex_unlock(&dev->list_mutex); - if (kthread_should_stop()) + if (kthread_should_stop()) { + __set_current_state(TASK_RUNNING); break; + } /* Only sleep when the search is active. */ if (dev->search_count) { diff --git a/drivers/w1/w1_int.c b/drivers/w1/w1_int.c index b3e1792d9c49..3a71c5eb2f83 100644 --- a/drivers/w1/w1_int.c +++ b/drivers/w1/w1_int.c @@ -51,10 +51,9 @@ static struct w1_master *w1_alloc_dev(u32 id, int slave_count, int slave_ttl, dev->search_count = w1_search_count; dev->enable_pullup = w1_enable_pullup; - /* 1 for w1_process to decrement - * 1 for __w1_remove_master_device to decrement + /* For __w1_remove_master_device to decrement */ - atomic_set(&dev->refcnt, 2); + atomic_set(&dev->refcnt, 1); INIT_LIST_HEAD(&dev->slist); INIT_LIST_HEAD(&dev->async_list); diff --git a/drivers/watchdog/diag288_wdt.c b/drivers/watchdog/diag288_wdt.c index 4cb10877017c..6ca5d9515d85 100644 --- a/drivers/watchdog/diag288_wdt.c +++ b/drivers/watchdog/diag288_wdt.c @@ -86,7 +86,7 @@ static int __diag288(unsigned int func, unsigned int timeout, "1:\n" EX_TABLE(0b, 1b) : "+d" (err) : "d"(__func), "d"(__timeout), - "d"(__action), "d"(__len) : "1", "cc"); + "d"(__action), "d"(__len) : "1", "cc", "memory"); return err; } @@ -268,12 +268,21 @@ static int __init diag288_init(void) char ebc_begin[] = { 194, 197, 199, 201, 213 }; + char *ebc_cmd; watchdog_set_nowayout(&wdt_dev, nowayout_info); if (MACHINE_IS_VM) { - if (__diag288_vm(WDT_FUNC_INIT, 15, - ebc_begin, sizeof(ebc_begin)) != 0) { + ebc_cmd = kmalloc(sizeof(ebc_begin), GFP_KERNEL); + if (!ebc_cmd) { + pr_err("The watchdog cannot be initialized\n"); + return -ENOMEM; + } + memcpy(ebc_cmd, ebc_begin, sizeof(ebc_begin)); + ret = __diag288_vm(WDT_FUNC_INIT, 15, + ebc_cmd, sizeof(ebc_begin)); + kfree(ebc_cmd); + if (ret != 0) { pr_err("The watchdog cannot be initialized\n"); return -EINVAL; } diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index 28b2a1fa25ab..0d4f8f4f4948 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -1181,9 +1181,8 @@ static void pvcalls_back_changed(struct xenbus_device *dev, } } -static int pvcalls_back_remove(struct xenbus_device *dev) +static void pvcalls_back_remove(struct xenbus_device *dev) { - return 0; } static int pvcalls_back_uevent(struct xenbus_device *xdev, diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 1826e8e67125..d5d589bda243 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -225,6 +225,8 @@ again: return IRQ_HANDLED; } +static void free_active_ring(struct sock_mapping *map); + static void pvcalls_front_free_map(struct pvcalls_bedata *bedata, struct sock_mapping *map) { @@ -240,7 +242,7 @@ static void pvcalls_front_free_map(struct pvcalls_bedata *bedata, for (i = 0; i < (1 << PVCALLS_RING_ORDER); i++) gnttab_end_foreign_access(map->active.ring->ref[i], NULL); gnttab_end_foreign_access(map->active.ref, NULL); - free_page((unsigned long)map->active.ring); + free_active_ring(map); kfree(map); } @@ -1085,7 +1087,7 @@ static const struct xenbus_device_id pvcalls_front_ids[] = { { "" } }; -static int pvcalls_front_remove(struct xenbus_device *dev) +static void pvcalls_front_remove(struct xenbus_device *dev) { struct pvcalls_bedata *bedata; struct sock_mapping *map = NULL, *n; @@ -1121,7 +1123,6 @@ static int pvcalls_front_remove(struct xenbus_device *dev) kfree(bedata->ring.sring); kfree(bedata); xenbus_switch_state(dev, XenbusStateClosed); - return 0; } static int pvcalls_front_probe(struct xenbus_device *dev, diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index d171091eec12..b11e401f1b1e 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -716,14 +716,12 @@ out: return err; } -static int xen_pcibk_xenbus_remove(struct xenbus_device *dev) +static void xen_pcibk_xenbus_remove(struct xenbus_device *dev) { struct xen_pcibk_device *pdev = dev_get_drvdata(&dev->dev); if (pdev != NULL) free_pdev(pdev); - - return 0; } static const struct xenbus_device_id xen_pcibk_ids[] = { diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 6106ed93817d..954188b0b858 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -1249,7 +1249,7 @@ static void scsiback_release_translation_entry(struct vscsibk_info *info) spin_unlock_irqrestore(&info->v2p_lock, flags); } -static int scsiback_remove(struct xenbus_device *dev) +static void scsiback_remove(struct xenbus_device *dev) { struct vscsibk_info *info = dev_get_drvdata(&dev->dev); @@ -1261,8 +1261,6 @@ static int scsiback_remove(struct xenbus_device *dev) gnttab_page_cache_shrink(&info->free_pages, 0); dev_set_drvdata(&dev->dev, NULL); - - return 0; } static int scsiback_probe(struct xenbus_device *dev, diff --git a/fs/affs/file.c b/fs/affs/file.c index cefa222f7881..8daeed31e1af 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -880,7 +880,7 @@ affs_truncate(struct inode *inode) if (inode->i_size > AFFS_I(inode)->mmu_private) { struct address_space *mapping = inode->i_mapping; struct page *page; - void *fsdata; + void *fsdata = NULL; loff_t isize = inode->i_size; int res; diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c index 7dcd59693a0c..d4ddb20d6732 100644 --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@ -13,6 +13,8 @@ #include "internal.h" #include "afs_cm.h" #include "protocol_yfs.h" +#define RXRPC_TRACE_ONLY_DEFINE_ENUMS +#include <trace/events/rxrpc.h> static int afs_deliver_cb_init_call_back_state(struct afs_call *); static int afs_deliver_cb_init_call_back_state3(struct afs_call *); @@ -191,7 +193,7 @@ static void afs_cm_destructor(struct afs_call *call) * Abort a service call from within an action function. */ static void afs_abort_service_call(struct afs_call *call, u32 abort_code, int error, - const char *why) + enum rxrpc_abort_reason why) { rxrpc_kernel_abort_call(call->net->socket, call->rxcall, abort_code, error, why); @@ -469,7 +471,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work) if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0) afs_send_empty_reply(call); else - afs_abort_service_call(call, 1, 1, "K-1"); + afs_abort_service_call(call, 1, 1, afs_abort_probeuuid_negative); afs_put_call(call); _leave(""); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index c62939e5ea1f..7817e2b860e5 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -13,6 +13,8 @@ #include "internal.h" #include "afs_cm.h" #include "protocol_yfs.h" +#define RXRPC_TRACE_ONLY_DEFINE_ENUMS +#include <trace/events/rxrpc.h> struct workqueue_struct *afs_async_calls; @@ -397,7 +399,8 @@ void afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, gfp_t gfp) error_do_abort: if (ret != -ECONNABORTED) { rxrpc_kernel_abort_call(call->net->socket, rxcall, - RX_USER_ABORT, ret, "KSD"); + RX_USER_ABORT, ret, + afs_abort_send_data_error); } else { len = 0; iov_iter_kvec(&msg.msg_iter, ITER_DEST, NULL, 0, 0); @@ -527,7 +530,8 @@ static void afs_deliver_to_call(struct afs_call *call) case -ENOTSUPP: abort_code = RXGEN_OPCODE; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - abort_code, ret, "KIV"); + abort_code, ret, + afs_abort_op_not_supported); goto local_abort; case -EIO: pr_err("kAFS: Call %u in bad state %u\n", @@ -542,12 +546,14 @@ static void afs_deliver_to_call(struct afs_call *call) if (state != AFS_CALL_CL_AWAIT_REPLY) abort_code = RXGEN_SS_UNMARSHAL; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - abort_code, ret, "KUM"); + abort_code, ret, + afs_abort_unmarshal_error); goto local_abort; default: abort_code = RX_CALL_DEAD; rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - abort_code, ret, "KER"); + abort_code, ret, + afs_abort_general_error); goto local_abort; } } @@ -619,7 +625,8 @@ long afs_wait_for_call_to_complete(struct afs_call *call, /* Kill off the call if it's still live. */ _debug("call interrupted"); if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall, - RX_USER_ABORT, -EINTR, "KWI")) + RX_USER_ABORT, -EINTR, + afs_abort_interrupted)) afs_set_call_complete(call, -EINTR, 0); } } @@ -836,7 +843,8 @@ void afs_send_empty_reply(struct afs_call *call) case -ENOMEM: _debug("oom"); rxrpc_kernel_abort_call(net->socket, call->rxcall, - RXGEN_SS_MARSHAL, -ENOMEM, "KOO"); + RXGEN_SS_MARSHAL, -ENOMEM, + afs_abort_oom); fallthrough; default: _leave(" [error]"); @@ -878,7 +886,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) if (n == -ENOMEM) { _debug("oom"); rxrpc_kernel_abort_call(net->socket, call->rxcall, - RXGEN_SS_MARSHAL, -ENOMEM, "KOO"); + RXGEN_SS_MARSHAL, -ENOMEM, + afs_abort_oom); } _leave(" [error]"); } @@ -900,6 +909,7 @@ int afs_extract_data(struct afs_call *call, bool want_more) ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, iter, &call->iov_len, want_more, &remote_abort, &call->service_id); + trace_afs_receive_data(call, call->iter, want_more, ret); if (ret == 0 || ret == -EAGAIN) return ret; diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index de63572a9404..9a780fafc539 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -2034,7 +2034,7 @@ static int elf_core_dump(struct coredump_params *cprm) * The number of segs are recored into ELF header as 16bit value. * Please check DEFAULT_MAX_MAP_COUNT definition when you modify here. */ - segs = cprm->vma_count + elf_core_extra_phdrs(); + segs = cprm->vma_count + elf_core_extra_phdrs(cprm); /* for notes section */ segs++; @@ -2074,7 +2074,7 @@ static int elf_core_dump(struct coredump_params *cprm) dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE); offset += cprm->vma_data_size; - offset += elf_core_extra_data_size(); + offset += elf_core_extra_data_size(cprm); e_shoff = offset; if (e_phnum == PN_XNUM) { diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 096e3520a0b1..a05eafcacfb2 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1509,7 +1509,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) tmp->next = thread_list; thread_list = tmp; - segs = cprm->vma_count + elf_core_extra_phdrs(); + segs = cprm->vma_count + elf_core_extra_phdrs(cprm); /* for notes section */ segs++; @@ -1555,7 +1555,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE); offset += cprm->vma_data_size; - offset += elf_core_extra_data_size(); + offset += elf_core_extra_data_size(cprm); e_shoff = offset; if (e_phnum == PN_XNUM) { diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8aeaada1fcae..3aa04224315e 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -367,7 +367,14 @@ error: btrfs_print_tree(eb, 0); btrfs_err(fs_info, "block=%llu write time tree block corruption detected", eb->start); - WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); + /* + * Be noisy if this is an extent buffer from a log tree. We don't abort + * a transaction in case there's a bad log tree extent buffer, we just + * fallback to a transaction commit. Still we want to know when there is + * a bad log tree extent buffer, as that may signal a bug somewhere. + */ + WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG) || + btrfs_header_owner(eb) == BTRFS_TREE_LOG_OBJECTID); return ret; } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 834bbcb91102..af046d22300e 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3541,6 +3541,7 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence) struct extent_buffer *leaf = path->nodes[0]; struct btrfs_file_extent_item *extent; u64 extent_end; + u8 type; if (path->slots[0] >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); @@ -3596,10 +3597,16 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence) extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); + type = btrfs_file_extent_type(leaf, extent); - if (btrfs_file_extent_disk_bytenr(leaf, extent) == 0 || - btrfs_file_extent_type(leaf, extent) == - BTRFS_FILE_EXTENT_PREALLOC) { + /* + * Can't access the extent's disk_bytenr field if this is an + * inline extent, since at that offset, it's where the extent + * data starts. + */ + if (type == BTRFS_FILE_EXTENT_PREALLOC || + (type == BTRFS_FILE_EXTENT_REG && + btrfs_file_extent_disk_bytenr(leaf, extent) == 0)) { /* * Explicit hole or prealloc extent, search for delalloc. * A prealloc extent is treated like a hole. diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index a749367e5ae2..37b86acfcbcf 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -119,6 +119,12 @@ enum { /* Indicate that we want to commit the transaction. */ BTRFS_FS_NEED_TRANS_COMMIT, + /* + * Indicate metadata over-commit is disabled. This is set when active + * zone tracking is needed. + */ + BTRFS_FS_NO_OVERCOMMIT, + #if BITS_PER_LONG == 32 /* Indicate if we have error/warn message printed on 32bit systems */ BTRFS_FS_32BIT_ERROR, diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index d275bf24b250..af97413abcf4 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2765,9 +2765,19 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) /* * Old roots should be searched when inserting qgroup - * extent record + * extent record. + * + * But for INCONSISTENT (NO_ACCOUNTING) -> rescan case, + * we may have some record inserted during + * NO_ACCOUNTING (thus no old_roots populated), but + * later we start rescan, which clears NO_ACCOUNTING, + * leaving some inserted records without old_roots + * populated. + * + * Those cases are rare and should not cause too much + * time spent during commit_transaction(). */ - if (WARN_ON(!record->old_roots)) { + if (!record->old_roots) { /* Search commit root to find old_roots */ ret = btrfs_find_all_roots(&ctx, false); if (ret < 0) @@ -3357,6 +3367,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) int err = -ENOMEM; int ret = 0; bool stopped = false; + bool did_leaf_rescans = false; path = btrfs_alloc_path(); if (!path) @@ -3377,6 +3388,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work) } err = qgroup_rescan_leaf(trans, path); + did_leaf_rescans = true; if (err > 0) btrfs_commit_transaction(trans); @@ -3397,16 +3409,23 @@ out: mutex_unlock(&fs_info->qgroup_rescan_lock); /* - * only update status, since the previous part has already updated the - * qgroup info. + * Only update status, since the previous part has already updated the + * qgroup info, and only if we did any actual work. This also prevents + * race with a concurrent quota disable, which has already set + * fs_info->quota_root to NULL and cleared BTRFS_FS_QUOTA_ENABLED at + * btrfs_quota_disable(). */ - trans = btrfs_start_transaction(fs_info->quota_root, 1); - if (IS_ERR(trans)) { - err = PTR_ERR(trans); + if (did_leaf_rescans) { + trans = btrfs_start_transaction(fs_info->quota_root, 1); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + trans = NULL; + btrfs_err(fs_info, + "fail to start transaction for status update: %d", + err); + } + } else { trans = NULL; - btrfs_err(fs_info, - "fail to start transaction for status update: %d", - err); } mutex_lock(&fs_info->qgroup_rescan_lock); diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index d28ee4e36f3d..69c09508afb5 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -407,7 +407,8 @@ int btrfs_can_overcommit(struct btrfs_fs_info *fs_info, return 0; used = btrfs_space_info_used(space_info, true); - if (btrfs_is_zoned(fs_info) && (space_info->flags & BTRFS_BLOCK_GROUP_METADATA)) + if (test_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags) && + (space_info->flags & BTRFS_BLOCK_GROUP_METADATA)) avail = 0; else avail = calc_available_free_space(fs_info, space_info, flush); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index fb52aa060093..d43261545264 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2980,7 +2980,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, ret = 0; if (ret) { blk_finish_plug(&plug); - btrfs_abort_transaction(trans, ret); btrfs_set_log_full_commit(trans); mutex_unlock(&root->log_mutex); goto out; @@ -3045,15 +3044,12 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, blk_finish_plug(&plug); btrfs_set_log_full_commit(trans); - - if (ret != -ENOSPC) { - btrfs_abort_transaction(trans, ret); - mutex_unlock(&log_root_tree->log_mutex); - goto out; - } + if (ret != -ENOSPC) + btrfs_err(fs_info, + "failed to update log for root %llu ret %d", + root->root_key.objectid, ret); btrfs_wait_tree_log_extents(log, mark); mutex_unlock(&log_root_tree->log_mutex); - ret = BTRFS_LOG_FORCE_COMMIT; goto out; } @@ -3112,7 +3108,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, goto out_wake_log_root; } else if (ret) { btrfs_set_log_full_commit(trans); - btrfs_abort_transaction(trans, ret); mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } @@ -3826,7 +3821,10 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, path->slots[0]); if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; + } else if (ret < 0) { + err = ret; } + goto done; } @@ -3846,19 +3844,34 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans, */ if (tmp.type == BTRFS_DIR_INDEX_KEY) last_old_dentry_offset = tmp.offset; + } else if (ret < 0) { + err = ret; + goto done; } + btrfs_release_path(path); /* - * Find the first key from this transaction again. See the note for - * log_new_dir_dentries, if we're logging a directory recursively we - * won't be holding its i_mutex, which means we can modify the directory - * while we're logging it. If we remove an entry between our first - * search and this search we'll not find the key again and can just - * bail. + * Find the first key from this transaction again or the one we were at + * in the loop below in case we had to reschedule. We may be logging the + * directory without holding its VFS lock, which happen when logging new + * dentries (through log_new_dir_dentries()) or in some cases when we + * need to log the parent directory of an inode. This means a dir index + * key might be deleted from the inode's root, and therefore we may not + * find it anymore. If we can't find it, just move to the next key. We + * can not bail out and ignore, because if we do that we will simply + * not log dir index keys that come after the one that was just deleted + * and we can end up logging a dir index range that ends at (u64)-1 + * (@last_offset is initialized to that), resulting in removing dir + * entries we should not remove at log replay time. */ search: ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0); + if (ret > 0) + ret = btrfs_next_item(root, path); + if (ret < 0) + err = ret; + /* If ret is 1, there are no more keys in the inode's root. */ if (ret != 0) goto done; @@ -5580,8 +5593,10 @@ static int add_conflicting_inode(struct btrfs_trans_handle *trans, * LOG_INODE_EXISTS mode) and slow down other fsyncs or transaction * commits. */ - if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) + if (ctx->num_conflict_inodes >= MAX_CONFLICT_INODES) { + btrfs_set_log_full_commit(trans); return BTRFS_LOG_FORCE_COMMIT; + } inode = btrfs_iget(root->fs_info->sb, ino, root); /* diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index aa25fa335d3e..bcfef75b97da 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -768,8 +768,11 @@ static noinline struct btrfs_device *device_list_add(const char *path, BTRFS_SUPER_FLAG_CHANGING_FSID_V2); error = lookup_bdev(path, &path_devt); - if (error) + if (error) { + btrfs_err(NULL, "failed to lookup block device for path %s: %d", + path, error); return ERR_PTR(error); + } if (fsid_change_in_progress) { if (!has_metadata_uuid) @@ -836,6 +839,9 @@ static noinline struct btrfs_device *device_list_add(const char *path, unsigned int nofs_flag; if (fs_devices->opened) { + btrfs_err(NULL, + "device %s belongs to fsid %pU, and the fs is already mounted", + path, fs_devices->fsid); mutex_unlock(&fs_devices->device_list_mutex); return ERR_PTR(-EBUSY); } @@ -905,6 +911,9 @@ static noinline struct btrfs_device *device_list_add(const char *path, * generation are equal. */ mutex_unlock(&fs_devices->device_list_mutex); + btrfs_err(NULL, +"device %s already registered with a higher generation, found %llu expect %llu", + path, found_transid, device->generation); return ERR_PTR(-EEXIST); } @@ -2005,42 +2014,42 @@ static u64 btrfs_num_devices(struct btrfs_fs_info *fs_info) return num_devices; } +static void btrfs_scratch_superblock(struct btrfs_fs_info *fs_info, + struct block_device *bdev, int copy_num) +{ + struct btrfs_super_block *disk_super; + const size_t len = sizeof(disk_super->magic); + const u64 bytenr = btrfs_sb_offset(copy_num); + int ret; + + disk_super = btrfs_read_disk_super(bdev, bytenr, bytenr); + if (IS_ERR(disk_super)) + return; + + memset(&disk_super->magic, 0, len); + folio_mark_dirty(virt_to_folio(disk_super)); + btrfs_release_disk_super(disk_super); + + ret = sync_blockdev_range(bdev, bytenr, bytenr + len - 1); + if (ret) + btrfs_warn(fs_info, "error clearing superblock number %d (%d)", + copy_num, ret); +} + void btrfs_scratch_superblocks(struct btrfs_fs_info *fs_info, struct block_device *bdev, const char *device_path) { - struct btrfs_super_block *disk_super; int copy_num; if (!bdev) return; for (copy_num = 0; copy_num < BTRFS_SUPER_MIRROR_MAX; copy_num++) { - struct page *page; - int ret; - - disk_super = btrfs_read_dev_one_super(bdev, copy_num, false); - if (IS_ERR(disk_super)) - continue; - - if (bdev_is_zoned(bdev)) { + if (bdev_is_zoned(bdev)) btrfs_reset_sb_log_zones(bdev, copy_num); - continue; - } - - memset(&disk_super->magic, 0, sizeof(disk_super->magic)); - - page = virt_to_page(disk_super); - set_page_dirty(page); - lock_page(page); - /* write_on_page() unlocks the page */ - ret = write_one_page(page); - if (ret) - btrfs_warn(fs_info, - "error clearing superblock number %d (%d)", - copy_num, ret); - btrfs_release_disk_super(disk_super); - + else + btrfs_scratch_superblock(fs_info, bdev, copy_num); } /* Notify udev that device has changed */ diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index a759668477bb..1f503e8e42d4 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -539,6 +539,8 @@ int btrfs_get_dev_zone_info(struct btrfs_device *device, bool populate_cache) } atomic_set(&zone_info->active_zones_left, max_active_zones - nactive); + /* Overcommit does not work well with active zone tacking. */ + set_bit(BTRFS_FS_NO_OVERCOMMIT, &fs_info->flags); } /* Validate superblock log */ diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8c74871e37c9..cac4083e387a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -305,7 +305,7 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) struct inode *inode = rreq->inode; struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); - struct ceph_osd_request *req; + struct ceph_osd_request *req = NULL; struct ceph_vino vino = ceph_vino(inode); struct iov_iter iter; struct page **pages; @@ -313,6 +313,11 @@ static void ceph_netfs_issue_read(struct netfs_io_subrequest *subreq) int err = 0; u64 len = subreq->len; + if (ceph_inode_is_shutdown(inode)) { + err = -EIO; + goto out; + } + if (ceph_has_inline_data(ci) && ceph_netfs_issue_op_inline(subreq)) return; @@ -563,6 +568,9 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) dout("writepage %p idx %lu\n", page, page->index); + if (ceph_inode_is_shutdown(inode)) + return -EIO; + /* verify this is a writeable snap context */ snapc = page_snap_context(page); if (!snapc) { @@ -1643,7 +1651,7 @@ int ceph_uninline_data(struct file *file) struct ceph_inode_info *ci = ceph_inode(inode); struct ceph_fs_client *fsc = ceph_inode_to_client(inode); struct ceph_osd_request *req = NULL; - struct ceph_cap_flush *prealloc_cf; + struct ceph_cap_flush *prealloc_cf = NULL; struct folio *folio = NULL; u64 inline_version = CEPH_INLINE_NONE; struct page *pages[1]; @@ -1657,6 +1665,11 @@ int ceph_uninline_data(struct file *file) dout("uninline_data %p %llx.%llx inline_version %llu\n", inode, ceph_vinop(inode), inline_version); + if (ceph_inode_is_shutdown(inode)) { + err = -EIO; + goto out; + } + if (inline_version == CEPH_INLINE_NONE) return 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index f75ad432f375..210e40037881 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -4078,6 +4078,7 @@ void ceph_handle_caps(struct ceph_mds_session *session, void *p, *end; struct cap_extra_info extra_info = {}; bool queue_trunc; + bool close_sessions = false; dout("handle_caps from mds%d\n", session->s_mds); @@ -4215,9 +4216,13 @@ void ceph_handle_caps(struct ceph_mds_session *session, realm = NULL; if (snaptrace_len) { down_write(&mdsc->snap_rwsem); - ceph_update_snap_trace(mdsc, snaptrace, - snaptrace + snaptrace_len, - false, &realm); + if (ceph_update_snap_trace(mdsc, snaptrace, + snaptrace + snaptrace_len, + false, &realm)) { + up_write(&mdsc->snap_rwsem); + close_sessions = true; + goto done; + } downgrade_write(&mdsc->snap_rwsem); } else { down_read(&mdsc->snap_rwsem); @@ -4277,6 +4282,11 @@ done_unlocked: iput(inode); out: ceph_put_string(extra_info.pool_ns); + + /* Defer closing the sessions after s_mutex lock being released */ + if (close_sessions) + ceph_mdsc_close_sessions(mdsc); + return; flush_cap_releases: diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 764598e1efd9..b5cff85925a1 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2011,6 +2011,9 @@ static int ceph_zero_partial_object(struct inode *inode, loff_t zero = 0; int op; + if (ceph_inode_is_shutdown(inode)) + return -EIO; + if (!length) { op = offset ? CEPH_OSD_OP_DELETE : CEPH_OSD_OP_TRUNCATE; length = &zero; diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 26a0a8b9975e..e163f58ff3c5 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -806,6 +806,9 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc, { struct ceph_mds_session *s; + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) + return ERR_PTR(-EIO); + if (mds >= mdsc->mdsmap->possible_max_rank) return ERR_PTR(-EINVAL); @@ -1478,6 +1481,9 @@ static int __open_session(struct ceph_mds_client *mdsc, int mstate; int mds = session->s_mds; + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) + return -EIO; + /* wait for mds to go active? */ mstate = ceph_mdsmap_get_state(mdsc->mdsmap, mds); dout("open_session to mds%d (%s)\n", mds, @@ -2860,6 +2866,11 @@ static void __do_request(struct ceph_mds_client *mdsc, return; } + if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_FENCE_IO) { + dout("do_request metadata corrupted\n"); + err = -EIO; + goto finish; + } if (req->r_timeout && time_after_eq(jiffies, req->r_started + req->r_timeout)) { dout("do_request timed out\n"); @@ -3245,6 +3256,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) u64 tid; int err, result; int mds = session->s_mds; + bool close_sessions = false; if (msg->front.iov_len < sizeof(*head)) { pr_err("mdsc_handle_reply got corrupt (short) reply\n"); @@ -3351,10 +3363,17 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg) realm = NULL; if (rinfo->snapblob_len) { down_write(&mdsc->snap_rwsem); - ceph_update_snap_trace(mdsc, rinfo->snapblob, + err = ceph_update_snap_trace(mdsc, rinfo->snapblob, rinfo->snapblob + rinfo->snapblob_len, le32_to_cpu(head->op) == CEPH_MDS_OP_RMSNAP, &realm); + if (err) { + up_write(&mdsc->snap_rwsem); + close_sessions = true; + if (err == -EIO) + ceph_msg_dump(msg); + goto out_err; + } downgrade_write(&mdsc->snap_rwsem); } else { down_read(&mdsc->snap_rwsem); @@ -3412,6 +3431,10 @@ out_err: req->r_end_latency, err); out: ceph_mdsc_put_request(req); + + /* Defer closing the sessions after s_mutex lock being released */ + if (close_sessions) + ceph_mdsc_close_sessions(mdsc); return; } @@ -5011,7 +5034,7 @@ static bool done_closing_sessions(struct ceph_mds_client *mdsc, int skipped) } /* - * called after sb is ro. + * called after sb is ro or when metadata corrupted. */ void ceph_mdsc_close_sessions(struct ceph_mds_client *mdsc) { @@ -5301,7 +5324,8 @@ static void mds_peer_reset(struct ceph_connection *con) struct ceph_mds_client *mdsc = s->s_mdsc; pr_warn("mds%d closed our session\n", s->s_mds); - send_mds_reconnect(mdsc, s); + if (READ_ONCE(mdsc->fsc->mount_state) != CEPH_MOUNT_FENCE_IO) + send_mds_reconnect(mdsc, s); } static void mds_dispatch(struct ceph_connection *con, struct ceph_msg *msg) diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index e4151852184e..87007203f130 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/ceph/ceph_debug.h> +#include <linux/fs.h> #include <linux/sort.h> #include <linux/slab.h> #include <linux/iversion.h> @@ -766,8 +767,10 @@ int ceph_update_snap_trace(struct ceph_mds_client *mdsc, struct ceph_snap_realm *realm; struct ceph_snap_realm *first_realm = NULL; struct ceph_snap_realm *realm_to_rebuild = NULL; + struct ceph_client *client = mdsc->fsc->client; int rebuild_snapcs; int err = -ENOMEM; + int ret; LIST_HEAD(dirty_realms); lockdep_assert_held_write(&mdsc->snap_rwsem); @@ -884,6 +887,27 @@ fail: if (first_realm) ceph_put_snap_realm(mdsc, first_realm); pr_err("%s error %d\n", __func__, err); + + /* + * When receiving a corrupted snap trace we don't know what + * exactly has happened in MDS side. And we shouldn't continue + * writing to OSD, which may corrupt the snapshot contents. + * + * Just try to blocklist this kclient and then this kclient + * must be remounted to continue after the corrupted metadata + * fixed in the MDS side. + */ + WRITE_ONCE(mdsc->fsc->mount_state, CEPH_MOUNT_FENCE_IO); + ret = ceph_monc_blocklist_add(&client->monc, &client->msgr.inst.addr); + if (ret) + pr_err("%s failed to blocklist %s: %d\n", __func__, + ceph_pr_addr(&client->msgr.inst.addr), ret); + + WARN(1, "%s: %s%sdo remount to continue%s", + __func__, ret ? "" : ceph_pr_addr(&client->msgr.inst.addr), + ret ? "" : " was blocklisted, ", + err == -EIO ? " after corrupted snaptrace is fixed" : ""); + return err; } @@ -984,6 +1008,7 @@ void ceph_handle_snap(struct ceph_mds_client *mdsc, __le64 *split_inos = NULL, *split_realms = NULL; int i; int locked_rwsem = 0; + bool close_sessions = false; /* decode */ if (msg->front.iov_len < sizeof(*h)) @@ -1092,8 +1117,12 @@ skip_inode: * update using the provided snap trace. if we are deleting a * snap, we can avoid queueing cap_snaps. */ - ceph_update_snap_trace(mdsc, p, e, - op == CEPH_SNAP_OP_DESTROY, NULL); + if (ceph_update_snap_trace(mdsc, p, e, + op == CEPH_SNAP_OP_DESTROY, + NULL)) { + close_sessions = true; + goto bad; + } if (op == CEPH_SNAP_OP_SPLIT) /* we took a reference when we created the realm, above */ @@ -1112,6 +1141,9 @@ bad: out: if (locked_rwsem) up_write(&mdsc->snap_rwsem); + + if (close_sessions) + ceph_mdsc_close_sessions(mdsc); return; } diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 0ed3be75bb9a..07c6906cda70 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -100,6 +100,17 @@ struct ceph_mount_options { char *mon_addr; }; +/* mount state */ +enum { + CEPH_MOUNT_MOUNTING, + CEPH_MOUNT_MOUNTED, + CEPH_MOUNT_UNMOUNTING, + CEPH_MOUNT_UNMOUNTED, + CEPH_MOUNT_SHUTDOWN, + CEPH_MOUNT_RECOVER, + CEPH_MOUNT_FENCE_IO, +}; + #define CEPH_ASYNC_CREATE_CONFLICT_BITS 8 struct ceph_fs_client { diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 5db73c0f792a..cbc18b4a9cb2 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -278,6 +278,7 @@ build_avpair_blob(struct cifs_ses *ses, const struct nls_table *nls_cp) * ( for NTLMSSP_AV_NB_DOMAIN_NAME followed by NTLMSSP_AV_EOL ) + * unicode length of a netbios domain name */ + kfree_sensitive(ses->auth_key.response); ses->auth_key.len = size + 2 * dlen; ses->auth_key.response = kzalloc(ses->auth_key.len, GFP_KERNEL); if (!ses->auth_key.response) { diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index d371259d6808..b2a04b4e89a5 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2606,11 +2606,14 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx) INIT_LIST_HEAD(&tcon->pending_opens); tcon->status = TID_GOOD; - /* schedule query interfaces poll */ INIT_DELAYED_WORK(&tcon->query_interfaces, smb2_query_server_interfaces); - queue_delayed_work(cifsiod_wq, &tcon->query_interfaces, - (SMB_INTERFACE_POLL_INTERVAL * HZ)); + if (ses->server->dialect >= SMB30_PROT_ID && + (ses->server->capabilities & SMB2_GLOBAL_CAP_MULTI_CHANNEL)) { + /* schedule query interfaces poll */ + queue_delayed_work(cifsiod_wq, &tcon->query_interfaces, + (SMB_INTERFACE_POLL_INTERVAL * HZ)); + } spin_lock(&cifs_tcp_ses_lock); list_add(&tcon->tcon_list, &ses->tcon_list); diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 43ad1176dcb9..ac86bd0ebd63 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -269,7 +269,7 @@ static int dfscache_proc_show(struct seq_file *m, void *v) list_for_each_entry(t, &ce->tlist, list) { seq_printf(m, " %s%s\n", t->name, - ce->tgthint == t ? " (target hint)" : ""); + READ_ONCE(ce->tgthint) == t ? " (target hint)" : ""); } } } @@ -321,7 +321,7 @@ static inline void dump_tgts(const struct cache_entry *ce) cifs_dbg(FYI, "target list:\n"); list_for_each_entry(t, &ce->tlist, list) { cifs_dbg(FYI, " %s%s\n", t->name, - ce->tgthint == t ? " (target hint)" : ""); + READ_ONCE(ce->tgthint) == t ? " (target hint)" : ""); } } @@ -427,7 +427,7 @@ static int cache_entry_hash(const void *data, int size, unsigned int *hash) /* Return target hint of a DFS cache entry */ static inline char *get_tgt_name(const struct cache_entry *ce) { - struct cache_dfs_tgt *t = ce->tgthint; + struct cache_dfs_tgt *t = READ_ONCE(ce->tgthint); return t ? t->name : ERR_PTR(-ENOENT); } @@ -470,6 +470,7 @@ static struct cache_dfs_tgt *alloc_target(const char *name, int path_consumed) static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs, struct cache_entry *ce, const char *tgthint) { + struct cache_dfs_tgt *target; int i; ce->ttl = max_t(int, refs[0].ttl, CACHE_MIN_TTL); @@ -496,8 +497,9 @@ static int copy_ref_data(const struct dfs_info3_param *refs, int numrefs, ce->numtgts++; } - ce->tgthint = list_first_entry_or_null(&ce->tlist, - struct cache_dfs_tgt, list); + target = list_first_entry_or_null(&ce->tlist, struct cache_dfs_tgt, + list); + WRITE_ONCE(ce->tgthint, target); return 0; } @@ -558,7 +560,8 @@ static void remove_oldest_entry_locked(void) } /* Add a new DFS cache entry */ -static int add_cache_entry_locked(struct dfs_info3_param *refs, int numrefs) +static struct cache_entry *add_cache_entry_locked(struct dfs_info3_param *refs, + int numrefs) { int rc; struct cache_entry *ce; @@ -573,11 +576,11 @@ static int add_cache_entry_locked(struct dfs_info3_param *refs, int numrefs) rc = cache_entry_hash(refs[0].path_name, strlen(refs[0].path_name), &hash); if (rc) - return rc; + return ERR_PTR(rc); ce = alloc_cache_entry(refs, numrefs); if (IS_ERR(ce)) - return PTR_ERR(ce); + return ce; spin_lock(&cache_ttl_lock); if (!cache_ttl) { @@ -594,7 +597,7 @@ static int add_cache_entry_locked(struct dfs_info3_param *refs, int numrefs) atomic_inc(&cache_count); - return 0; + return ce; } /* Check if two DFS paths are equal. @s1 and @s2 are expected to be in @cache_cp's charset */ @@ -641,7 +644,9 @@ static struct cache_entry *__lookup_cache_entry(const char *path, unsigned int h * * Use whole path components in the match. Must be called with htable_rw_lock held. * + * Return cached entry if successful. * Return ERR_PTR(-ENOENT) if the entry is not found. + * Return error ptr otherwise. */ static struct cache_entry *lookup_cache_entry(const char *path) { @@ -711,14 +716,15 @@ void dfs_cache_destroy(void) static int update_cache_entry_locked(struct cache_entry *ce, const struct dfs_info3_param *refs, int numrefs) { + struct cache_dfs_tgt *target; + char *th = NULL; int rc; - char *s, *th = NULL; WARN_ON(!rwsem_is_locked(&htable_rw_lock)); - if (ce->tgthint) { - s = ce->tgthint->name; - th = kstrdup(s, GFP_ATOMIC); + target = READ_ONCE(ce->tgthint); + if (target) { + th = kstrdup(target->name, GFP_ATOMIC); if (!th) return -ENOMEM; } @@ -767,51 +773,75 @@ static int get_dfs_referral(const unsigned int xid, struct cifs_ses *ses, const * * For interlinks, cifs_mount() and expand_dfs_referral() are supposed to * handle them properly. + * + * On success, return entry with acquired lock for reading, otherwise error ptr. */ -static int cache_refresh_path(const unsigned int xid, struct cifs_ses *ses, const char *path) +static struct cache_entry *cache_refresh_path(const unsigned int xid, + struct cifs_ses *ses, + const char *path, + bool force_refresh) { - int rc; - struct cache_entry *ce; struct dfs_info3_param *refs = NULL; + struct cache_entry *ce; int numrefs = 0; - bool newent = false; + int rc; cifs_dbg(FYI, "%s: search path: %s\n", __func__, path); - down_write(&htable_rw_lock); + down_read(&htable_rw_lock); ce = lookup_cache_entry(path); if (!IS_ERR(ce)) { - if (!cache_entry_expired(ce)) { - dump_ce(ce); - up_write(&htable_rw_lock); - return 0; - } - } else { - newent = true; + if (!force_refresh && !cache_entry_expired(ce)) + return ce; + } else if (PTR_ERR(ce) != -ENOENT) { + up_read(&htable_rw_lock); + return ce; } /* - * Either the entry was not found, or it is expired. + * Unlock shared access as we don't want to hold any locks while getting + * a new referral. The @ses used for performing the I/O could be + * reconnecting and it acquires @htable_rw_lock to look up the dfs cache + * in order to failover -- if necessary. + */ + up_read(&htable_rw_lock); + + /* + * Either the entry was not found, or it is expired, or it is a forced + * refresh. * Request a new DFS referral in order to create or update a cache entry. */ rc = get_dfs_referral(xid, ses, path, &refs, &numrefs); - if (rc) - goto out_unlock; + if (rc) { + ce = ERR_PTR(rc); + goto out; + } dump_refs(refs, numrefs); - if (!newent) { - rc = update_cache_entry_locked(ce, refs, numrefs); - goto out_unlock; + down_write(&htable_rw_lock); + /* Re-check as another task might have it added or refreshed already */ + ce = lookup_cache_entry(path); + if (!IS_ERR(ce)) { + if (force_refresh || cache_entry_expired(ce)) { + rc = update_cache_entry_locked(ce, refs, numrefs); + if (rc) + ce = ERR_PTR(rc); + } + } else if (PTR_ERR(ce) == -ENOENT) { + ce = add_cache_entry_locked(refs, numrefs); } - rc = add_cache_entry_locked(refs, numrefs); + if (IS_ERR(ce)) { + up_write(&htable_rw_lock); + goto out; + } -out_unlock: - up_write(&htable_rw_lock); + downgrade_write(&htable_rw_lock); +out: free_dfs_info_array(refs, numrefs); - return rc; + return ce; } /* @@ -878,7 +908,7 @@ static int get_targets(struct cache_entry *ce, struct dfs_cache_tgt_list *tl) } it->it_path_consumed = t->path_consumed; - if (ce->tgthint == t) + if (READ_ONCE(ce->tgthint) == t) list_add(&it->it_list, head); else list_add_tail(&it->it_list, head); @@ -931,15 +961,8 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nl if (IS_ERR(npath)) return PTR_ERR(npath); - rc = cache_refresh_path(xid, ses, npath); - if (rc) - goto out_free_path; - - down_read(&htable_rw_lock); - - ce = lookup_cache_entry(npath); + ce = cache_refresh_path(xid, ses, npath, false); if (IS_ERR(ce)) { - up_read(&htable_rw_lock); rc = PTR_ERR(ce); goto out_free_path; } @@ -1003,72 +1026,6 @@ out_unlock: } /** - * dfs_cache_update_tgthint - update target hint of a DFS cache entry - * - * If it doesn't find the cache entry, then it will get a DFS referral for @path - * and create a new entry. - * - * In case the cache entry exists but expired, it will get a DFS referral - * for @path and then update the respective cache entry. - * - * @xid: syscall id - * @ses: smb session - * @cp: codepage - * @remap: type of character remapping for paths - * @path: path to lookup in DFS referral cache - * @it: DFS target iterator - * - * Return zero if the target hint was updated successfully, otherwise non-zero. - */ -int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses, - const struct nls_table *cp, int remap, const char *path, - const struct dfs_cache_tgt_iterator *it) -{ - int rc; - const char *npath; - struct cache_entry *ce; - struct cache_dfs_tgt *t; - - npath = dfs_cache_canonical_path(path, cp, remap); - if (IS_ERR(npath)) - return PTR_ERR(npath); - - cifs_dbg(FYI, "%s: update target hint - path: %s\n", __func__, npath); - - rc = cache_refresh_path(xid, ses, npath); - if (rc) - goto out_free_path; - - down_write(&htable_rw_lock); - - ce = lookup_cache_entry(npath); - if (IS_ERR(ce)) { - rc = PTR_ERR(ce); - goto out_unlock; - } - - t = ce->tgthint; - - if (likely(!strcasecmp(it->it_name, t->name))) - goto out_unlock; - - list_for_each_entry(t, &ce->tlist, list) { - if (!strcasecmp(t->name, it->it_name)) { - ce->tgthint = t; - cifs_dbg(FYI, "%s: new target hint: %s\n", __func__, - it->it_name); - break; - } - } - -out_unlock: - up_write(&htable_rw_lock); -out_free_path: - kfree(npath); - return rc; -} - -/** * dfs_cache_noreq_update_tgthint - update target hint of a DFS cache entry * without sending any requests to the currently connected server. * @@ -1092,21 +1049,20 @@ void dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt cifs_dbg(FYI, "%s: path: %s\n", __func__, path); - if (!down_write_trylock(&htable_rw_lock)) - return; + down_read(&htable_rw_lock); ce = lookup_cache_entry(path); if (IS_ERR(ce)) goto out_unlock; - t = ce->tgthint; + t = READ_ONCE(ce->tgthint); if (unlikely(!strcasecmp(it->it_name, t->name))) goto out_unlock; list_for_each_entry(t, &ce->tlist, list) { if (!strcasecmp(t->name, it->it_name)) { - ce->tgthint = t; + WRITE_ONCE(ce->tgthint, t); cifs_dbg(FYI, "%s: new target hint: %s\n", __func__, it->it_name); break; @@ -1114,7 +1070,7 @@ void dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt } out_unlock: - up_write(&htable_rw_lock); + up_read(&htable_rw_lock); } /** @@ -1299,7 +1255,6 @@ static bool target_share_equal(struct TCP_Server_Info *server, const char *s1, c * Resolve share's hostname and check if server address matches. Otherwise just ignore it * as we could not have upcall to resolve hostname or failed to convert ip address. */ - match = true; extract_unc_hostname(s1, &host, &hostlen); scnprintf(unc, sizeof(unc), "\\\\%.*s", (int)hostlen, host); @@ -1321,35 +1276,37 @@ static bool target_share_equal(struct TCP_Server_Info *server, const char *s1, c * Mark dfs tcon for reconnecting when the currently connected tcon does not match any of the new * target shares in @refs. */ -static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cache_tgt_list *tl, - const struct dfs_info3_param *refs, int numrefs) +static void mark_for_reconnect_if_needed(struct TCP_Server_Info *server, + struct dfs_cache_tgt_list *old_tl, + struct dfs_cache_tgt_list *new_tl) { - struct dfs_cache_tgt_iterator *it; - int i; - - for (it = dfs_cache_get_tgt_iterator(tl); it; it = dfs_cache_get_next_tgt(tl, it)) { - for (i = 0; i < numrefs; i++) { - if (target_share_equal(tcon->ses->server, dfs_cache_get_tgt_name(it), - refs[i].node_name)) + struct dfs_cache_tgt_iterator *oit, *nit; + + for (oit = dfs_cache_get_tgt_iterator(old_tl); oit; + oit = dfs_cache_get_next_tgt(old_tl, oit)) { + for (nit = dfs_cache_get_tgt_iterator(new_tl); nit; + nit = dfs_cache_get_next_tgt(new_tl, nit)) { + if (target_share_equal(server, + dfs_cache_get_tgt_name(oit), + dfs_cache_get_tgt_name(nit))) return; } } cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__); - cifs_signal_cifsd_for_reconnect(tcon->ses->server, true); + cifs_signal_cifsd_for_reconnect(server, true); } /* Refresh dfs referral of tcon and mark it for reconnect if needed */ static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_refresh) { - struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl); + struct dfs_cache_tgt_list old_tl = DFS_CACHE_TGT_LIST_INIT(old_tl); + struct dfs_cache_tgt_list new_tl = DFS_CACHE_TGT_LIST_INIT(new_tl); struct cifs_ses *ses = CIFS_DFS_ROOT_SES(tcon->ses); struct cifs_tcon *ipc = ses->tcon_ipc; - struct dfs_info3_param *refs = NULL; bool needs_refresh = false; struct cache_entry *ce; unsigned int xid; - int numrefs = 0; int rc = 0; xid = get_xid(); @@ -1358,9 +1315,8 @@ static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_r ce = lookup_cache_entry(path); needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce); if (!IS_ERR(ce)) { - rc = get_targets(ce, &tl); - if (rc) - cifs_dbg(FYI, "%s: could not get dfs targets: %d\n", __func__, rc); + rc = get_targets(ce, &old_tl); + cifs_dbg(FYI, "%s: get_targets: %d\n", __func__, rc); } up_read(&htable_rw_lock); @@ -1377,26 +1333,18 @@ static int __refresh_tcon(const char *path, struct cifs_tcon *tcon, bool force_r } spin_unlock(&ipc->tc_lock); - rc = get_dfs_referral(xid, ses, path, &refs, &numrefs); - if (!rc) { - /* Create or update a cache entry with the new referral */ - dump_refs(refs, numrefs); - - down_write(&htable_rw_lock); - ce = lookup_cache_entry(path); - if (IS_ERR(ce)) - add_cache_entry_locked(refs, numrefs); - else if (force_refresh || cache_entry_expired(ce)) - update_cache_entry_locked(ce, refs, numrefs); - up_write(&htable_rw_lock); - - mark_for_reconnect_if_needed(tcon, &tl, refs, numrefs); + ce = cache_refresh_path(xid, ses, path, true); + if (!IS_ERR(ce)) { + rc = get_targets(ce, &new_tl); + up_read(&htable_rw_lock); + cifs_dbg(FYI, "%s: get_targets: %d\n", __func__, rc); + mark_for_reconnect_if_needed(tcon->ses->server, &old_tl, &new_tl); } out: free_xid(xid); - dfs_cache_free_tgts(&tl); - free_dfs_info_array(refs, numrefs); + dfs_cache_free_tgts(&old_tl); + dfs_cache_free_tgts(&new_tl); return rc; } diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h index f7cff0be9327..be3b5a44cf82 100644 --- a/fs/cifs/dfs_cache.h +++ b/fs/cifs/dfs_cache.h @@ -35,9 +35,6 @@ int dfs_cache_find(const unsigned int xid, struct cifs_ses *ses, const struct nl struct dfs_cache_tgt_list *tgt_list); int dfs_cache_noreq_find(const char *path, struct dfs_info3_param *ref, struct dfs_cache_tgt_list *tgt_list); -int dfs_cache_update_tgthint(const unsigned int xid, struct cifs_ses *ses, - const struct nls_table *cp, int remap, const char *path, - const struct dfs_cache_tgt_iterator *it); void dfs_cache_noreq_update_tgthint(const char *path, const struct dfs_cache_tgt_iterator *it); int dfs_cache_get_tgt_referral(const char *path, const struct dfs_cache_tgt_iterator *it, struct dfs_info3_param *ref); diff --git a/fs/cifs/link.c b/fs/cifs/link.c index bd374feeccaa..a5a097a69983 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -428,6 +428,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon, oparms.disposition = FILE_CREATE; oparms.fid = &fid; oparms.reconnect = false; + oparms.mode = 0644; rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL, NULL, NULL); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 0b842a07e157..c47b254f0d1e 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -815,6 +815,7 @@ int decode_ntlmssp_challenge(char *bcc_ptr, int blob_len, return -EINVAL; } if (tilen) { + kfree_sensitive(ses->auth_key.response); ses->auth_key.response = kmemdup(bcc_ptr + tioffset, tilen, GFP_KERNEL); if (!ses->auth_key.response) { @@ -1428,6 +1429,7 @@ sess_auth_kerberos(struct sess_data *sess_data) goto out_put_spnego_key; } + kfree_sensitive(ses->auth_key.response); ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, GFP_KERNEL); if (!ses->auth_key.response) { diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index 50480751e521..4cb364454e13 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -562,17 +562,20 @@ static int cifs_query_path_info(const unsigned int xid, struct cifs_tcon *tcon, if ((rc == -EOPNOTSUPP) || (rc == -EINVAL)) { rc = SMBQueryInformation(xid, tcon, full_path, &fi, cifs_sb->local_nls, cifs_remap(cifs_sb)); - if (!rc) - move_cifs_info_to_smb2(&data->fi, &fi); *adjustTZ = true; } - if (!rc && (le32_to_cpu(fi.Attributes) & ATTR_REPARSE)) { + if (!rc) { int tmprc; int oplock = 0; struct cifs_fid fid; struct cifs_open_parms oparms; + move_cifs_info_to_smb2(&data->fi, &fi); + + if (!(le32_to_cpu(fi.Attributes) & ATTR_REPARSE)) + return 0; + oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = FILE_READ_ATTRIBUTES; @@ -716,17 +719,25 @@ cifs_mkdir_setinfo(struct inode *inode, const char *full_path, static int cifs_open_file(const unsigned int xid, struct cifs_open_parms *oparms, __u32 *oplock, void *buf) { - FILE_ALL_INFO *fi = buf; + struct cifs_open_info_data *data = buf; + FILE_ALL_INFO fi = {}; + int rc; if (!(oparms->tcon->ses->capabilities & CAP_NT_SMBS)) - return SMBLegacyOpen(xid, oparms->tcon, oparms->path, - oparms->disposition, - oparms->desired_access, - oparms->create_options, - &oparms->fid->netfid, oplock, fi, - oparms->cifs_sb->local_nls, - cifs_remap(oparms->cifs_sb)); - return CIFS_open(xid, oparms, oplock, fi); + rc = SMBLegacyOpen(xid, oparms->tcon, oparms->path, + oparms->disposition, + oparms->desired_access, + oparms->create_options, + &oparms->fid->netfid, oplock, &fi, + oparms->cifs_sb->local_nls, + cifs_remap(oparms->cifs_sb)); + else + rc = CIFS_open(xid, oparms, oplock, &fi); + + if (!rc && data) + move_cifs_info_to_smb2(&data->fi, &fi); + + return rc; } static void @@ -1050,7 +1061,7 @@ cifs_make_node(unsigned int xid, struct inode *inode, struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct inode *newinode = NULL; int rc = -EPERM; - FILE_ALL_INFO *buf = NULL; + struct cifs_open_info_data buf = {}; struct cifs_io_parms io_parms; __u32 oplock = 0; struct cifs_fid fid; @@ -1082,14 +1093,14 @@ cifs_make_node(unsigned int xid, struct inode *inode, cifs_sb->local_nls, cifs_remap(cifs_sb)); if (rc) - goto out; + return rc; rc = cifs_get_inode_info_unix(&newinode, full_path, inode->i_sb, xid); if (rc == 0) d_instantiate(dentry, newinode); - goto out; + return rc; } /* @@ -1097,19 +1108,13 @@ cifs_make_node(unsigned int xid, struct inode *inode, * support block and char device (no socket & fifo) */ if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_UNX_EMUL)) - goto out; + return rc; if (!S_ISCHR(mode) && !S_ISBLK(mode)) - goto out; + return rc; cifs_dbg(FYI, "sfu compat create special file\n"); - buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL); - if (buf == NULL) { - rc = -ENOMEM; - goto out; - } - oparms.tcon = tcon; oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_WRITE; @@ -1124,21 +1129,21 @@ cifs_make_node(unsigned int xid, struct inode *inode, oplock = REQ_OPLOCK; else oplock = 0; - rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, buf); + rc = tcon->ses->server->ops->open(xid, &oparms, &oplock, &buf); if (rc) - goto out; + return rc; /* * BB Do not bother to decode buf since no local inode yet to put * timestamps in, but we can reuse it safely. */ - pdev = (struct win_dev *)buf; + pdev = (struct win_dev *)&buf.fi; io_parms.pid = current->tgid; io_parms.tcon = tcon; io_parms.offset = 0; io_parms.length = sizeof(struct win_dev); - iov[1].iov_base = buf; + iov[1].iov_base = &buf.fi; iov[1].iov_len = sizeof(struct win_dev); if (S_ISCHR(mode)) { memcpy(pdev->type, "IntxCHR", 8); @@ -1157,8 +1162,8 @@ cifs_make_node(unsigned int xid, struct inode *inode, d_drop(dentry); /* FIXME: add code here to set EAs */ -out: - kfree(buf); + + cifs_free_open_info(&buf); return rc; } diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2c484d47c592..2c9ffa921e6f 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1453,6 +1453,7 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) /* keep session key if binding */ if (!is_binding) { + kfree_sensitive(ses->auth_key.response); ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len, GFP_KERNEL); if (!ses->auth_key.response) { @@ -1482,8 +1483,11 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data) out_put_spnego_key: key_invalidate(spnego_key); key_put(spnego_key); - if (rc) + if (rc) { kfree_sensitive(ses->auth_key.response); + ses->auth_key.response = NULL; + ses->auth_key.len = 0; + } out: sess_data->result = rc; sess_data->func = NULL; @@ -4159,12 +4163,15 @@ smb2_readv_callback(struct mid_q_entry *mid) (struct smb2_hdr *)rdata->iov[0].iov_base; struct cifs_credits credits = { .value = 0, .instance = 0 }; struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], - .rq_nvec = 1, - .rq_pages = rdata->pages, - .rq_offset = rdata->page_offset, - .rq_npages = rdata->nr_pages, - .rq_pagesz = rdata->pagesz, - .rq_tailsz = rdata->tailsz }; + .rq_nvec = 1, }; + + if (rdata->got_bytes) { + rqst.rq_pages = rdata->pages; + rqst.rq_offset = rdata->page_offset; + rqst.rq_npages = rdata->nr_pages; + rqst.rq_pagesz = rdata->pagesz; + rqst.rq_tailsz = rdata->tailsz; + } WARN_ONCE(rdata->server != mid->server, "rdata server %p != mid server %p", diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 90789aaa6567..8c816b25ce7c 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -1405,6 +1405,7 @@ void smbd_destroy(struct TCP_Server_Info *server) destroy_workqueue(info->workqueue); log_rdma_event(INFO, "rdma session destroyed\n"); kfree(info); + server->smbd_conn = NULL; } /* diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 481788c24a68..626a615dafc2 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -577,26 +577,25 @@ static int erofs_fc_parse_param(struct fs_context *fc, } ++ctx->devs->extra_devices; break; - case Opt_fsid: #ifdef CONFIG_EROFS_FS_ONDEMAND + case Opt_fsid: kfree(ctx->fsid); ctx->fsid = kstrdup(param->string, GFP_KERNEL); if (!ctx->fsid) return -ENOMEM; -#else - errorfc(fc, "fsid option not supported"); -#endif break; case Opt_domain_id: -#ifdef CONFIG_EROFS_FS_ONDEMAND kfree(ctx->domain_id); ctx->domain_id = kstrdup(param->string, GFP_KERNEL); if (!ctx->domain_id) return -ENOMEM; + break; #else - errorfc(fc, "domain_id option not supported"); -#endif + case Opt_fsid: + case Opt_domain_id: + errorfc(fc, "%s option not supported", erofs_fs_parameters[opt].name); break; +#endif default: return -ENOPARAM; } diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index ccf7c55d477f..5200bb86e264 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1032,12 +1032,12 @@ static int z_erofs_decompress_pcluster(struct z_erofs_decompress_backend *be, if (!be->decompressed_pages) be->decompressed_pages = - kvcalloc(be->nr_pages, sizeof(struct page *), - GFP_KERNEL | __GFP_NOFAIL); + kcalloc(be->nr_pages, sizeof(struct page *), + GFP_KERNEL | __GFP_NOFAIL); if (!be->compressed_pages) be->compressed_pages = - kvcalloc(pclusterpages, sizeof(struct page *), - GFP_KERNEL | __GFP_NOFAIL); + kcalloc(pclusterpages, sizeof(struct page *), + GFP_KERNEL | __GFP_NOFAIL); z_erofs_parse_out_bvecs(be); err2 = z_erofs_parse_in_bvecs(be, &overlapped); @@ -1085,7 +1085,7 @@ out: } if (be->compressed_pages < be->onstack_pages || be->compressed_pages >= be->onstack_pages + Z_EROFS_ONSTACK_PAGES) - kvfree(be->compressed_pages); + kfree(be->compressed_pages); z_erofs_fill_other_copies(be, err); for (i = 0; i < be->nr_pages; ++i) { @@ -1104,7 +1104,7 @@ out: } if (be->decompressed_pages != be->onstack_pages) - kvfree(be->decompressed_pages); + kfree(be->decompressed_pages); pcl->length = 0; pcl->partial = true; diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 0150570c33aa..98fb90b9af71 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -793,12 +793,16 @@ static int z_erofs_iomap_begin_report(struct inode *inode, loff_t offset, iomap->type = IOMAP_HOLE; iomap->addr = IOMAP_NULL_ADDR; /* - * No strict rule how to describe extents for post EOF, yet - * we need do like below. Otherwise, iomap itself will get + * No strict rule on how to describe extents for post EOF, yet + * we need to do like below. Otherwise, iomap itself will get * into an endless loop on post EOF. + * + * Calculate the effective offset by subtracting extent start + * (map.m_la) from the requested offset, and add it to length. + * (NB: offset >= map.m_la always) */ if (iomap->offset >= inode->i_size) - iomap->length = length + map.m_la - offset; + iomap->length = length + offset - map.m_la; } iomap->flags = 0; return 0; diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 7decaaf27e82..a2f04a3808db 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -81,6 +81,8 @@ ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *, struct mb_cache_entry **); static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, size_t value_count); +static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value, + size_t value_count); static void ext4_xattr_rehash(struct ext4_xattr_header *); static const struct xattr_handler * const ext4_xattr_handler_map[] = { @@ -470,8 +472,22 @@ ext4_xattr_inode_verify_hashes(struct inode *ea_inode, tmp_data = cpu_to_le32(hash); e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len, &tmp_data, 1); + /* All good? */ + if (e_hash == entry->e_hash) + return 0; + + /* + * Not good. Maybe the entry hash was calculated + * using the buggy signed char version? + */ + e_hash = ext4_xattr_hash_entry_signed(entry->e_name, entry->e_name_len, + &tmp_data, 1); + /* Still no match - bad */ if (e_hash != entry->e_hash) return -EFSCORRUPTED; + + /* Let people know about old hash */ + pr_warn_once("ext4: filesystem with signed xattr name hash"); } return 0; } @@ -3081,7 +3097,29 @@ static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, while (name_len--) { hash = (hash << NAME_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ - *name++; + (unsigned char)*name++; + } + while (value_count--) { + hash = (hash << VALUE_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ + le32_to_cpu(*value++); + } + return cpu_to_le32(hash); +} + +/* + * ext4_xattr_hash_entry_signed() + * + * Compute the hash of an extended attribute incorrectly. + */ +static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value, size_t value_count) +{ + __u32 hash = 0; + + while (name_len--) { + hash = (hash << NAME_HASH_SHIFT) ^ + (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ + (signed char)*name++; } while (value_count--) { hash = (hash << VALUE_HASH_SHIFT) ^ diff --git a/fs/freevxfs/Kconfig b/fs/freevxfs/Kconfig index c05c71d57291..0e2fc08f7de4 100644 --- a/fs/freevxfs/Kconfig +++ b/fs/freevxfs/Kconfig @@ -8,7 +8,7 @@ config VXFS_FS of SCO UnixWare (and possibly others) and optionally available for Sunsoft Solaris, HP-UX and many other operating systems. However these particular OS implementations of vxfs may differ in on-disk - data endianess and/or superblock offset. The vxfs module has been + data endianness and/or superblock offset. The vxfs module has been tested with SCO UnixWare and HP-UX B.10.20 (pa-risc 1.1 arch.) Currently only readonly access is supported and VxFX versions 2, 3 and 4. Tests were performed with HP-UX VxFS version 3. diff --git a/fs/fscache/volume.c b/fs/fscache/volume.c index ab8ceddf9efa..cdf991bdd9de 100644 --- a/fs/fscache/volume.c +++ b/fs/fscache/volume.c @@ -141,13 +141,14 @@ static bool fscache_is_acquire_pending(struct fscache_volume *volume) static void fscache_wait_on_volume_collision(struct fscache_volume *candidate, unsigned int collidee_debug_id) { - wait_var_event_timeout(&candidate->flags, - !fscache_is_acquire_pending(candidate), 20 * HZ); + wait_on_bit_timeout(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING, + TASK_UNINTERRUPTIBLE, 20 * HZ); if (fscache_is_acquire_pending(candidate)) { pr_notice("Potential volume collision new=%08x old=%08x", candidate->debug_id, collidee_debug_id); fscache_stat(&fscache_n_volumes_collision); - wait_var_event(&candidate->flags, !fscache_is_acquire_pending(candidate)); + wait_on_bit(&candidate->flags, FSCACHE_VOLUME_ACQUIRE_PENDING, + TASK_UNINTERRUPTIBLE); } } @@ -279,8 +280,7 @@ static void fscache_create_volume_work(struct work_struct *work) fscache_end_cache_access(volume->cache, fscache_access_acquire_volume_end); - clear_bit_unlock(FSCACHE_VOLUME_CREATING, &volume->flags); - wake_up_bit(&volume->flags, FSCACHE_VOLUME_CREATING); + clear_and_wake_up_bit(FSCACHE_VOLUME_CREATING, &volume->flags); fscache_put_volume(volume, fscache_volume_put_create_work); } @@ -347,8 +347,8 @@ static void fscache_wake_pending_volume(struct fscache_volume *volume, hlist_bl_for_each_entry(cursor, p, h, hash_link) { if (fscache_volume_same(cursor, volume)) { fscache_see_volume(cursor, fscache_volume_see_hash_wake); - clear_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, &cursor->flags); - wake_up_bit(&cursor->flags, FSCACHE_VOLUME_ACQUIRE_PENDING); + clear_and_wake_up_bit(FSCACHE_VOLUME_ACQUIRE_PENDING, + &cursor->flags); return; } } diff --git a/fs/fuse/acl.c b/fs/fuse/acl.c index a4850aee2639..ad670369955f 100644 --- a/fs/fuse/acl.c +++ b/fs/fuse/acl.c @@ -11,9 +11,10 @@ #include <linux/posix_acl.h> #include <linux/posix_acl_xattr.h> -struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu) +static struct posix_acl *__fuse_get_acl(struct fuse_conn *fc, + struct user_namespace *mnt_userns, + struct inode *inode, int type, bool rcu) { - struct fuse_conn *fc = get_fuse_conn(inode); int size; const char *name; void *value = NULL; @@ -25,7 +26,7 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu) if (fuse_is_bad(inode)) return ERR_PTR(-EIO); - if (!fc->posix_acl || fc->no_getxattr) + if (fc->no_getxattr) return NULL; if (type == ACL_TYPE_ACCESS) @@ -53,6 +54,46 @@ struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu) return acl; } +static inline bool fuse_no_acl(const struct fuse_conn *fc, + const struct inode *inode) +{ + /* + * Refuse interacting with POSIX ACLs for daemons that + * don't support FUSE_POSIX_ACL and are not mounted on + * the host to retain backwards compatibility. + */ + return !fc->posix_acl && (i_user_ns(inode) != &init_user_ns); +} + +struct posix_acl *fuse_get_acl(struct user_namespace *mnt_userns, + struct dentry *dentry, int type) +{ + struct inode *inode = d_inode(dentry); + struct fuse_conn *fc = get_fuse_conn(inode); + + if (fuse_no_acl(fc, inode)) + return ERR_PTR(-EOPNOTSUPP); + + return __fuse_get_acl(fc, mnt_userns, inode, type, false); +} + +struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu) +{ + struct fuse_conn *fc = get_fuse_conn(inode); + + /* + * FUSE daemons before FUSE_POSIX_ACL was introduced could get and set + * POSIX ACLs without them being used for permission checking by the + * vfs. Retain that behavior for backwards compatibility as there are + * filesystems that do all permission checking for acls in the daemon + * and not in the kernel. + */ + if (!fc->posix_acl) + return NULL; + + return __fuse_get_acl(fc, &init_user_ns, inode, type, rcu); +} + int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, struct posix_acl *acl, int type) { @@ -64,7 +105,7 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, if (fuse_is_bad(inode)) return -EIO; - if (!fc->posix_acl || fc->no_setxattr) + if (fc->no_setxattr || fuse_no_acl(fc, inode)) return -EOPNOTSUPP; if (type == ACL_TYPE_ACCESS) @@ -99,7 +140,13 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, return ret; } - if (!vfsgid_in_group_p(i_gid_into_vfsgid(&init_user_ns, inode)) && + /* + * Fuse daemons without FUSE_POSIX_ACL never changed the passed + * through POSIX ACLs. Such daemons don't expect setgid bits to + * be stripped. + */ + if (fc->posix_acl && + !vfsgid_in_group_p(i_gid_into_vfsgid(&init_user_ns, inode)) && !capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_FSETID)) extra_flags |= FUSE_SETXATTR_ACL_KILL_SGID; @@ -108,8 +155,15 @@ int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, } else { ret = fuse_removexattr(inode, name); } - forget_all_cached_acls(inode); - fuse_invalidate_attr(inode); + + if (fc->posix_acl) { + /* + * Fuse daemons without FUSE_POSIX_ACL never cached POSIX ACLs + * and didn't invalidate attributes. Retain that behavior. + */ + forget_all_cached_acls(inode); + fuse_invalidate_attr(inode); + } return ret; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index cd1a071b625a..2725fb54328e 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1942,7 +1942,8 @@ static const struct inode_operations fuse_dir_inode_operations = { .permission = fuse_permission, .getattr = fuse_getattr, .listxattr = fuse_listxattr, - .get_inode_acl = fuse_get_acl, + .get_inode_acl = fuse_get_inode_acl, + .get_acl = fuse_get_acl, .set_acl = fuse_set_acl, .fileattr_get = fuse_fileattr_get, .fileattr_set = fuse_fileattr_set, @@ -1964,7 +1965,8 @@ static const struct inode_operations fuse_common_inode_operations = { .permission = fuse_permission, .getattr = fuse_getattr, .listxattr = fuse_listxattr, - .get_inode_acl = fuse_get_acl, + .get_inode_acl = fuse_get_inode_acl, + .get_acl = fuse_get_acl, .set_acl = fuse_set_acl, .fileattr_get = fuse_fileattr_get, .fileattr_set = fuse_fileattr_set, diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index c673faefdcb9..46797a171a84 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1264,11 +1264,11 @@ ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value, ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size); int fuse_removexattr(struct inode *inode, const char *name); extern const struct xattr_handler *fuse_xattr_handlers[]; -extern const struct xattr_handler *fuse_acl_xattr_handlers[]; -extern const struct xattr_handler *fuse_no_acl_xattr_handlers[]; struct posix_acl; -struct posix_acl *fuse_get_acl(struct inode *inode, int type, bool rcu); +struct posix_acl *fuse_get_inode_acl(struct inode *inode, int type, bool rcu); +struct posix_acl *fuse_get_acl(struct user_namespace *mnt_userns, + struct dentry *dentry, int type); int fuse_set_acl(struct user_namespace *mnt_userns, struct dentry *dentry, struct posix_acl *acl, int type); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 6b3beda16c1b..de9b9ec5ce81 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -311,7 +311,8 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, fuse_dax_dontcache(inode, attr->flags); } -static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr) +static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr, + struct fuse_conn *fc) { inode->i_mode = attr->mode & S_IFMT; inode->i_size = attr->size; @@ -333,6 +334,12 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr) new_decode_dev(attr->rdev)); } else BUG(); + /* + * Ensure that we don't cache acls for daemons without FUSE_POSIX_ACL + * so they see the exact same behavior as before. + */ + if (!fc->posix_acl) + inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE; } static int fuse_inode_eq(struct inode *inode, void *_nodeidp) @@ -372,7 +379,7 @@ struct inode *fuse_iget(struct super_block *sb, u64 nodeid, if (!inode) return NULL; - fuse_init_inode(inode, attr); + fuse_init_inode(inode, attr, fc); get_fuse_inode(inode)->nodeid = nodeid; inode->i_flags |= S_AUTOMOUNT; goto done; @@ -388,7 +395,7 @@ retry: if (!fc->writeback_cache || !S_ISREG(attr->mode)) inode->i_flags |= S_NOCMTIME; inode->i_generation = generation; - fuse_init_inode(inode, attr); + fuse_init_inode(inode, attr, fc); unlock_new_inode(inode); } else if (fuse_stale_inode(inode, generation, attr)) { /* nodeid was reused, any I/O on the old inode should fail */ @@ -1174,7 +1181,6 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, if ((flags & FUSE_POSIX_ACL)) { fc->default_permissions = 1; fc->posix_acl = 1; - fm->sb->s_xattr = fuse_acl_xattr_handlers; } if (flags & FUSE_CACHE_SYMLINKS) fc->cache_symlinks = 1; @@ -1420,13 +1426,6 @@ static void fuse_sb_defaults(struct super_block *sb) if (sb->s_user_ns != &init_user_ns) sb->s_iflags |= SB_I_UNTRUSTED_MOUNTER; sb->s_flags &= ~(SB_NOSEC | SB_I_VERSION); - - /* - * If we are not in the initial user namespace posix - * acls must be translated. - */ - if (sb->s_user_ns != &init_user_ns) - sb->s_xattr = fuse_no_acl_xattr_handlers; } static int fuse_fill_super_submount(struct super_block *sb, diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c index 0d3e7177fce0..9fe571ab569e 100644 --- a/fs/fuse/xattr.c +++ b/fs/fuse/xattr.c @@ -203,27 +203,6 @@ static int fuse_xattr_set(const struct xattr_handler *handler, return fuse_setxattr(inode, name, value, size, flags, 0); } -static bool no_xattr_list(struct dentry *dentry) -{ - return false; -} - -static int no_xattr_get(const struct xattr_handler *handler, - struct dentry *dentry, struct inode *inode, - const char *name, void *value, size_t size) -{ - return -EOPNOTSUPP; -} - -static int no_xattr_set(const struct xattr_handler *handler, - struct user_namespace *mnt_userns, - struct dentry *dentry, struct inode *nodee, - const char *name, const void *value, - size_t size, int flags) -{ - return -EOPNOTSUPP; -} - static const struct xattr_handler fuse_xattr_handler = { .prefix = "", .get = fuse_xattr_get, @@ -234,33 +213,3 @@ const struct xattr_handler *fuse_xattr_handlers[] = { &fuse_xattr_handler, NULL }; - -const struct xattr_handler *fuse_acl_xattr_handlers[] = { - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, - &fuse_xattr_handler, - NULL -}; - -static const struct xattr_handler fuse_no_acl_access_xattr_handler = { - .name = XATTR_NAME_POSIX_ACL_ACCESS, - .flags = ACL_TYPE_ACCESS, - .list = no_xattr_list, - .get = no_xattr_get, - .set = no_xattr_set, -}; - -static const struct xattr_handler fuse_no_acl_default_xattr_handler = { - .name = XATTR_NAME_POSIX_ACL_DEFAULT, - .flags = ACL_TYPE_ACCESS, - .list = no_xattr_list, - .get = no_xattr_get, - .set = no_xattr_set, -}; - -const struct xattr_handler *fuse_no_acl_xattr_handlers[] = { - &fuse_no_acl_access_xattr_handler, - &fuse_no_acl_default_xattr_handler, - &fuse_xattr_handler, - NULL -}; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 723639376ae2..61323deb80bc 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -80,6 +80,15 @@ void gfs2_remove_from_ail(struct gfs2_bufdata *bd) brelse(bd->bd_bh); } +static int __gfs2_writepage(struct page *page, struct writeback_control *wbc, + void *data) +{ + struct address_space *mapping = data; + int ret = mapping->a_ops->writepage(page, wbc); + mapping_set_error(mapping, ret); + return ret; +} + /** * gfs2_ail1_start_one - Start I/O on a transaction * @sdp: The superblock @@ -131,7 +140,7 @@ __acquires(&sdp->sd_ail_lock) if (!mapping) continue; spin_unlock(&sdp->sd_ail_lock); - ret = filemap_fdatawrite_wbc(mapping, wbc); + ret = write_cache_pages(mapping, wbc, __gfs2_writepage, mapping); if (need_resched()) { blk_finish_plug(plug); cond_resched(); diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c index 2a39ffb8423b..6e61b5bc7d86 100644 --- a/fs/ksmbd/auth.c +++ b/fs/ksmbd/auth.c @@ -322,7 +322,8 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob, dn_off = le32_to_cpu(authblob->DomainName.BufferOffset); dn_len = le16_to_cpu(authblob->DomainName.Length); - if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len) + if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len || + nt_len < CIFS_ENCPWD_SIZE) return -EINVAL; /* TODO : use domain name that imported from configuration file */ diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 12be8386446a..56be077e5d8a 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -280,7 +280,7 @@ int ksmbd_conn_handler_loop(void *p) { struct ksmbd_conn *conn = (struct ksmbd_conn *)p; struct ksmbd_transport *t = conn->transport; - unsigned int pdu_size; + unsigned int pdu_size, max_allowed_pdu_size; char hdr_buf[4] = {0,}; int size; @@ -305,20 +305,36 @@ int ksmbd_conn_handler_loop(void *p) pdu_size = get_rfc1002_len(hdr_buf); ksmbd_debug(CONN, "RFC1002 header %u bytes\n", pdu_size); + if (conn->status == KSMBD_SESS_GOOD) + max_allowed_pdu_size = + SMB3_MAX_MSGSIZE + conn->vals->max_write_size; + else + max_allowed_pdu_size = SMB3_MAX_MSGSIZE; + + if (pdu_size > max_allowed_pdu_size) { + pr_err_ratelimited("PDU length(%u) excceed maximum allowed pdu size(%u) on connection(%d)\n", + pdu_size, max_allowed_pdu_size, + conn->status); + break; + } + /* * Check if pdu size is valid (min : smb header size, * max : 0x00FFFFFF). */ if (pdu_size < __SMB2_HEADER_STRUCTURE_SIZE || pdu_size > MAX_STREAM_PROT_LEN) { - continue; + break; } /* 4 for rfc1002 length field */ size = pdu_size + 4; - conn->request_buf = kvmalloc(size, GFP_KERNEL); + conn->request_buf = kvmalloc(size, + GFP_KERNEL | + __GFP_NOWARN | + __GFP_NORETRY); if (!conn->request_buf) - continue; + break; memcpy(conn->request_buf, hdr_buf, sizeof(hdr_buf)); if (!ksmbd_smb_request(conn)) diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/ksmbd/ksmbd_netlink.h index b6bd8311e6b4..fb8b2d566efb 100644 --- a/fs/ksmbd/ksmbd_netlink.h +++ b/fs/ksmbd/ksmbd_netlink.h @@ -106,7 +106,8 @@ struct ksmbd_startup_request { __u32 sub_auth[3]; /* Subauth value for Security ID */ __u32 smb2_max_credits; /* MAX credits */ __u32 smbd_max_io_size; /* smbd read write size */ - __u32 reserved[127]; /* Reserved room */ + __u32 max_connections; /* Number of maximum simultaneous connections */ + __u32 reserved[126]; /* Reserved room */ __u32 ifc_list_sz; /* interfaces list size */ __s8 ____payload[]; }; diff --git a/fs/ksmbd/ndr.c b/fs/ksmbd/ndr.c index 0ae8d08d85a8..4d9e0b54e3db 100644 --- a/fs/ksmbd/ndr.c +++ b/fs/ksmbd/ndr.c @@ -242,7 +242,7 @@ int ndr_decode_dos_attr(struct ndr *n, struct xattr_dos_attrib *da) return ret; if (da->version != 3 && da->version != 4) { - pr_err("v%d version is not supported\n", da->version); + ksmbd_debug(VFS, "v%d version is not supported\n", da->version); return -EINVAL; } @@ -251,7 +251,7 @@ int ndr_decode_dos_attr(struct ndr *n, struct xattr_dos_attrib *da) return ret; if (da->version != version2) { - pr_err("ndr version mismatched(version: %d, version2: %d)\n", + ksmbd_debug(VFS, "ndr version mismatched(version: %d, version2: %d)\n", da->version, version2); return -EINVAL; } @@ -457,7 +457,7 @@ int ndr_decode_v4_ntacl(struct ndr *n, struct xattr_ntacl *acl) if (ret) return ret; if (acl->version != 4) { - pr_err("v%d version is not supported\n", acl->version); + ksmbd_debug(VFS, "v%d version is not supported\n", acl->version); return -EINVAL; } @@ -465,7 +465,7 @@ int ndr_decode_v4_ntacl(struct ndr *n, struct xattr_ntacl *acl) if (ret) return ret; if (acl->version != version2) { - pr_err("ndr version mismatched(version: %d, version2: %d)\n", + ksmbd_debug(VFS, "ndr version mismatched(version: %d, version2: %d)\n", acl->version, version2); return -EINVAL; } diff --git a/fs/ksmbd/server.h b/fs/ksmbd/server.h index ac9d932f8c8a..db7278181760 100644 --- a/fs/ksmbd/server.h +++ b/fs/ksmbd/server.h @@ -41,6 +41,7 @@ struct ksmbd_server_config { unsigned int share_fake_fscaps; struct smb_sid domain_sid; unsigned int auth_mechs; + unsigned int max_connections; char *conf[SERVER_CONF_WORK_GROUP + 1]; }; diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 14d7f3599c63..d681f91947d9 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -1928,13 +1928,13 @@ int smb2_tree_connect(struct ksmbd_work *work) if (conn->posix_ext_supported) status.tree_conn->posix_extensions = true; -out_err1: rsp->StructureSize = cpu_to_le16(16); + inc_rfc1001_len(work->response_buf, 16); +out_err1: rsp->Capabilities = 0; rsp->Reserved = 0; /* default manual caching */ rsp->ShareFlags = SMB2_SHAREFLAG_MANUAL_CACHING; - inc_rfc1001_len(work->response_buf, 16); if (!IS_ERR(treename)) kfree(treename); @@ -1967,6 +1967,9 @@ out_err1: rsp->hdr.Status = STATUS_ACCESS_DENIED; } + if (status.ret != KSMBD_TREE_CONN_STATUS_OK) + smb2_set_err_rsp(work); + return rc; } @@ -8660,6 +8663,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; + struct ksmbd_session *sess = work->sess; struct smb2_hdr *rsp = smb2_get_msg(work->response_buf); if (conn->dialect < SMB30_PROT_ID) @@ -8669,6 +8673,7 @@ bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work) rsp = ksmbd_resp_buf_next(work); if (le16_to_cpu(rsp->Command) == SMB2_SESSION_SETUP_HE && + sess->user && !user_guest(sess->user) && rsp->Status == STATUS_SUCCESS) return true; return false; diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index aa5dbe54f5a1..0c8a770fe318 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -24,8 +24,9 @@ #define SMB21_DEFAULT_IOSIZE (1024 * 1024) #define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024) -#define SMB3_MIN_IOSIZE (64 * 1024) -#define SMB3_MAX_IOSIZE (8 * 1024 * 1024) +#define SMB3_MIN_IOSIZE (64 * 1024) +#define SMB3_MAX_IOSIZE (8 * 1024 * 1024) +#define SMB3_MAX_MSGSIZE (4 * 4096) /* * Definitions for SMB2 Protocol Data Units (network frames) diff --git a/fs/ksmbd/transport_ipc.c b/fs/ksmbd/transport_ipc.c index c9aca21637d5..40c721f9227e 100644 --- a/fs/ksmbd/transport_ipc.c +++ b/fs/ksmbd/transport_ipc.c @@ -308,6 +308,9 @@ static int ipc_server_config_on_startup(struct ksmbd_startup_request *req) if (req->smbd_max_io_size) init_smbd_max_io_size(req->smbd_max_io_size); + if (req->max_connections) + server_conf.max_connections = req->max_connections; + ret = ksmbd_set_netbios_name(req->netbios_name); ret |= ksmbd_set_server_string(req->server_string); ret |= ksmbd_set_work_group(req->work_group); diff --git a/fs/ksmbd/transport_tcp.c b/fs/ksmbd/transport_tcp.c index 63d55f543bd2..603893fd87f5 100644 --- a/fs/ksmbd/transport_tcp.c +++ b/fs/ksmbd/transport_tcp.c @@ -15,6 +15,8 @@ #define IFACE_STATE_DOWN BIT(0) #define IFACE_STATE_CONFIGURED BIT(1) +static atomic_t active_num_conn; + struct interface { struct task_struct *ksmbd_kthread; struct socket *ksmbd_socket; @@ -185,8 +187,10 @@ static int ksmbd_tcp_new_connection(struct socket *client_sk) struct tcp_transport *t; t = alloc_transport(client_sk); - if (!t) + if (!t) { + sock_release(client_sk); return -ENOMEM; + } csin = KSMBD_TCP_PEER_SOCKADDR(KSMBD_TRANS(t)->conn); if (kernel_getpeername(client_sk, csin) < 0) { @@ -239,6 +243,15 @@ static int ksmbd_kthread_fn(void *p) continue; } + if (server_conf.max_connections && + atomic_inc_return(&active_num_conn) >= server_conf.max_connections) { + pr_info_ratelimited("Limit the maximum number of connections(%u)\n", + atomic_read(&active_num_conn)); + atomic_dec(&active_num_conn); + sock_release(client_sk); + continue; + } + ksmbd_debug(CONN, "connect success: accepted new connection\n"); client_sk->sk->sk_rcvtimeo = KSMBD_TCP_RECV_TIMEOUT; client_sk->sk->sk_sndtimeo = KSMBD_TCP_SEND_TIMEOUT; @@ -295,6 +308,7 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, struct msghdr ksmbd_msg; struct kvec *iov; struct ksmbd_conn *conn = KSMBD_TRANS(t)->conn; + int max_retry = 2; iov = get_conn_iovec(t, nr_segs); if (!iov) @@ -321,9 +335,11 @@ static int ksmbd_tcp_readv(struct tcp_transport *t, struct kvec *iov_orig, } else if (conn->status == KSMBD_SESS_NEED_RECONNECT) { total_read = -EAGAIN; break; - } else if (length == -ERESTARTSYS || length == -EAGAIN) { + } else if ((length == -ERESTARTSYS || length == -EAGAIN) && + max_retry) { usleep_range(1000, 2000); length = 0; + max_retry--; continue; } else if (length <= 0) { total_read = -EAGAIN; @@ -365,6 +381,8 @@ static int ksmbd_tcp_writev(struct ksmbd_transport *t, struct kvec *iov, static void ksmbd_tcp_disconnect(struct ksmbd_transport *t) { free_transport(TCP_TRANS(t)); + if (server_conf.max_connections) + atomic_dec(&active_num_conn); } static void tcp_destroy_socket(struct socket *ksmbd_socket) diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 45b2c9e3f636..c0950edb26b0 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -662,6 +662,39 @@ static struct shrinker nfsd_file_shrinker = { }; /** + * nfsd_file_cond_queue - conditionally unhash and queue a nfsd_file + * @nf: nfsd_file to attempt to queue + * @dispose: private list to queue successfully-put objects + * + * Unhash an nfsd_file, try to get a reference to it, and then put that + * reference. If it's the last reference, queue it to the dispose list. + */ +static void +nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) + __must_hold(RCU) +{ + int decrement = 1; + + /* If we raced with someone else unhashing, ignore it */ + if (!nfsd_file_unhash(nf)) + return; + + /* If we can't get a reference, ignore it */ + if (!nfsd_file_get(nf)) + return; + + /* Extra decrement if we remove from the LRU */ + if (nfsd_file_lru_remove(nf)) + ++decrement; + + /* If refcount goes to 0, then put on the dispose list */ + if (refcount_sub_and_test(decrement, &nf->nf_ref)) { + list_add(&nf->nf_lru, dispose); + trace_nfsd_file_closing(nf); + } +} + +/** * nfsd_file_queue_for_close: try to close out any open nfsd_files for an inode * @inode: inode on which to close out nfsd_files * @dispose: list on which to gather nfsd_files to close out @@ -688,30 +721,11 @@ nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) rcu_read_lock(); do { - int decrement = 1; - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, nfsd_file_rhash_params); if (!nf) break; - - /* If we raced with someone else unhashing, ignore it */ - if (!nfsd_file_unhash(nf)) - continue; - - /* If we can't get a reference, ignore it */ - if (!nfsd_file_get(nf)) - continue; - - /* Extra decrement if we remove from the LRU */ - if (nfsd_file_lru_remove(nf)) - ++decrement; - - /* If refcount goes to 0, then put on the dispose list */ - if (refcount_sub_and_test(decrement, &nf->nf_ref)) { - list_add(&nf->nf_lru, dispose); - trace_nfsd_file_closing(nf); - } + nfsd_file_cond_queue(nf, dispose); } while (1); rcu_read_unlock(); } @@ -928,11 +942,8 @@ __nfsd_file_cache_purge(struct net *net) nf = rhashtable_walk_next(&iter); while (!IS_ERR_OR_NULL(nf)) { - if (!net || nf->nf_net == net) { - nfsd_file_unhash(nf); - nfsd_file_lru_remove(nf); - list_add(&nf->nf_lru, &dispose); - } + if (!net || nf->nf_net == net) + nfsd_file_cond_queue(nf, &dispose); nf = rhashtable_walk_next(&iter); } @@ -1071,8 +1082,8 @@ nfsd_file_is_cached(struct inode *inode) static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **pnf, - bool open, bool want_gc) + unsigned int may_flags, struct file *file, + struct nfsd_file **pnf, bool want_gc) { struct nfsd_file_lookup_key key = { .type = NFSD_FILE_KEY_FULL, @@ -1147,8 +1158,7 @@ wait_for_construction: status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); out: if (status == nfs_ok) { - if (open) - this_cpu_inc(nfsd_file_acquisitions); + this_cpu_inc(nfsd_file_acquisitions); *pnf = nf; } else { if (refcount_dec_and_test(&nf->nf_ref)) @@ -1158,20 +1168,23 @@ out: out_status: put_cred(key.cred); - if (open) - trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); + trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); return status; open_file: trace_nfsd_file_alloc(nf); nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode); if (nf->nf_mark) { - if (open) { + if (file) { + get_file(file); + nf->nf_file = file; + status = nfs_ok; + trace_nfsd_file_opened(nf, status); + } else { status = nfsd_open_verified(rqstp, fhp, may_flags, &nf->nf_file); trace_nfsd_file_open(nf, status); - } else - status = nfs_ok; + } } else status = nfserr_jukebox; /* @@ -1207,7 +1220,7 @@ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, true); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true); } /** @@ -1228,28 +1241,30 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, false); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false); } /** - * nfsd_file_create - Get a struct nfsd_file, do not open + * nfsd_file_acquire_opened - Get a struct nfsd_file using existing open file * @rqstp: the RPC transaction being executed * @fhp: the NFS filehandle of the file just created * @may_flags: NFSD_MAY_ settings for the file + * @file: cached, already-open file (may be NULL) * @pnf: OUT: new or found "struct nfsd_file" object * - * The nfsd_file_object returned by this API is reference-counted - * but not garbage-collected. The object is released immediately - * one RCU grace period after the final nfsd_file_put(). + * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist, + * and @file is non-NULL, use it to instantiate a new nfsd_file instead of + * opening a new one. * * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in * network byte order is returned. */ __be32 -nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **pnf) +nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct file *file, + struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false, false); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false); } /* diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index b7efb2c3ddb1..41516a4263ea 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -60,7 +60,8 @@ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **nfp); __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **nfp); -__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **nfp); +__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct file *file, + struct nfsd_file **nfp); int nfsd_file_cache_stats_show(struct seq_file *m, void *v); #endif /* _FS_NFSD_FILECACHE_H */ diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 8c854ba3285b..51a4b7885cae 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -195,7 +195,7 @@ struct nfsd_net { atomic_t nfsd_courtesy_clients; struct shrinker nfsd_client_shrinker; - struct delayed_work nfsd_shrinker_work; + struct work_struct nfsd_shrinker_work; }; /* Simple check to find out if a given net was properly initialized */ diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index bd880d55f565..f189ba7995f5 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -937,7 +937,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * the client wants us to do more in this compound: */ if (!nfsd4_last_compound_op(rqstp)) - __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* check stateid */ status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, @@ -1318,6 +1318,7 @@ try_again: /* allow 20secs for mount/unmount for now - revisit */ if (signal_pending(current) || (schedule_timeout(20*HZ) == 0)) { + finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); return nfserr_eagain; } @@ -2607,12 +2608,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) cstate->minorversion = args->minorversion; fh_init(current_fh, NFS4_FHSIZE); fh_init(save_fh, NFS4_FHSIZE); - /* * Don't use the deferral mechanism for NFSv4; compounds make it * too hard to avoid non-idempotency problems. */ - __clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); /* * According to RFC3010, this takes precedence over all other errors. @@ -2734,7 +2734,7 @@ encode_op: out: cstate->status = status; /* Reset deferral mechanism for RPC deferrals */ - __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); return rpc_success; } diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 7b2ee535ade8..4ef529379065 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -4411,7 +4411,7 @@ nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) if (!count) count = atomic_long_read(&num_delegations); if (count) - mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0); + queue_work(laundry_wq, &nn->nfsd_shrinker_work); return (unsigned long)count; } @@ -4421,7 +4421,7 @@ nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) return SHRINK_STOP; } -int +void nfsd4_init_leases_net(struct nfsd_net *nn) { struct sysinfo si; @@ -4443,16 +4443,6 @@ nfsd4_init_leases_net(struct nfsd_net *nn) nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); atomic_set(&nn->nfsd_courtesy_clients, 0); - nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; - nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; - nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; - return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"); -} - -void -nfsd4_leases_net_shutdown(struct nfsd_net *nn) -{ - unregister_shrinker(&nn->nfsd_client_shrinker); } static void init_nfs4_replay(struct nfs4_replay *rp) @@ -5262,18 +5252,10 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, if (!fp->fi_fds[oflag]) { spin_unlock(&fp->fi_lock); - if (!open->op_filp) { - status = nfsd_file_acquire(rqstp, cur_fh, access, &nf); - if (status != nfs_ok) - goto out_put_access; - } else { - status = nfsd_file_create(rqstp, cur_fh, access, &nf); - if (status != nfs_ok) - goto out_put_access; - nf->nf_file = open->op_filp; - open->op_filp = NULL; - trace_nfsd_file_create(rqstp, access, nf); - } + status = nfsd_file_acquire_opened(rqstp, cur_fh, access, + open->op_filp, &nf); + if (status != nfs_ok) + goto out_put_access; spin_lock(&fp->fi_lock); if (!fp->fi_fds[oflag]) { @@ -6243,8 +6225,7 @@ deleg_reaper(struct nfsd_net *nn) static void nfsd4_state_shrinker_worker(struct work_struct *work) { - struct delayed_work *dwork = to_delayed_work(work); - struct nfsd_net *nn = container_of(dwork, struct nfsd_net, + struct nfsd_net *nn = container_of(work, struct nfsd_net, nfsd_shrinker_work); courtesy_client_reaper(nn); @@ -8074,11 +8055,20 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->blocked_locks_lru); INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); - INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); + INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); + nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; + + if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client")) + goto err_shrinker; return 0; +err_shrinker: + put_net(net); + kfree(nn->sessionid_hashtbl); err_sessionid: kfree(nn->unconf_id_hashtbl); err_unconf_id: @@ -8171,6 +8161,8 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + unregister_shrinker(&nn->nfsd_client_shrinker); + cancel_work(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index ebb4d02a42ce..97edb32be77f 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2523,7 +2523,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE; if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) - __clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); return true; } diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index d1e581a60480..c2577ee7ffb2 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -1457,9 +1457,7 @@ static __net_init int nfsd_init_net(struct net *net) goto out_idmap_error; nn->nfsd_versions = NULL; nn->nfsd4_minorversions = NULL; - retval = nfsd4_init_leases_net(nn); - if (retval) - goto out_drc_error; + nfsd4_init_leases_net(nn); retval = nfsd_reply_cache_init(nn); if (retval) goto out_cache_error; @@ -1469,8 +1467,6 @@ static __net_init int nfsd_init_net(struct net *net) return 0; out_cache_error: - nfsd4_leases_net_shutdown(nn); -out_drc_error: nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); @@ -1486,7 +1482,6 @@ static __net_exit void nfsd_exit_net(struct net *net) nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); - nfsd4_leases_net_shutdown(nn); } static struct pernet_operations nfsd_net_ops = { diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 93b42ef9ed91..fa0144a74267 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -504,8 +504,7 @@ extern void unregister_cld_notifier(void); extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn); #endif -extern int nfsd4_init_leases_net(struct nfsd_net *nn); -extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn); +extern void nfsd4_init_leases_net(struct nfsd_net *nn); #else /* CONFIG_NFSD_V4 */ static inline int nfsd4_is_junction(struct dentry *dentry) @@ -513,8 +512,7 @@ static inline int nfsd4_is_junction(struct dentry *dentry) return 0; } -static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; }; -static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {}; +static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { }; #define register_cld_notifier() 0 #define unregister_cld_notifier() do { } while(0) diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index a5570cf75f3f..9744443c3965 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -211,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - __set_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -246,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - __set_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index c852ae8eaf37..8f9c82d9e075 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -981,43 +981,6 @@ TRACE_EVENT(nfsd_file_acquire, ) ); -TRACE_EVENT(nfsd_file_create, - TP_PROTO( - const struct svc_rqst *rqstp, - unsigned int may_flags, - const struct nfsd_file *nf - ), - - TP_ARGS(rqstp, may_flags, nf), - - TP_STRUCT__entry( - __field(const void *, nf_inode) - __field(const void *, nf_file) - __field(unsigned long, may_flags) - __field(unsigned long, nf_flags) - __field(unsigned long, nf_may) - __field(unsigned int, nf_ref) - __field(u32, xid) - ), - - TP_fast_assign( - __entry->nf_inode = nf->nf_inode; - __entry->nf_file = nf->nf_file; - __entry->may_flags = may_flags; - __entry->nf_flags = nf->nf_flags; - __entry->nf_may = nf->nf_may; - __entry->nf_ref = refcount_read(&nf->nf_ref); - __entry->xid = be32_to_cpu(rqstp->rq_xid); - ), - - TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p", - __entry->xid, __entry->nf_inode, - show_nfsd_may_flags(__entry->may_flags), - __entry->nf_ref, show_nf_flags(__entry->nf_flags), - show_nfsd_may_flags(__entry->nf_may), __entry->nf_file - ) -); - TRACE_EVENT(nfsd_file_insert_err, TP_PROTO( const struct svc_rqst *rqstp, @@ -1079,8 +1042,8 @@ TRACE_EVENT(nfsd_file_cons_err, ) ); -TRACE_EVENT(nfsd_file_open, - TP_PROTO(struct nfsd_file *nf, __be32 status), +DECLARE_EVENT_CLASS(nfsd_file_open_class, + TP_PROTO(const struct nfsd_file *nf, __be32 status), TP_ARGS(nf, status), TP_STRUCT__entry( __field(void *, nf_inode) /* cannot be dereferenced */ @@ -1104,6 +1067,17 @@ TRACE_EVENT(nfsd_file_open, __entry->nf_file) ) +#define DEFINE_NFSD_FILE_OPEN_EVENT(name) \ +DEFINE_EVENT(nfsd_file_open_class, name, \ + TP_PROTO( \ + const struct nfsd_file *nf, \ + __be32 status \ + ), \ + TP_ARGS(nf, status)) + +DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_open); +DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_opened); + TRACE_EVENT(nfsd_file_is_cached, TP_PROTO( const struct inode *inode, diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index b9d15c3df3cc..40ce92a332fe 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -480,9 +480,18 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, &bh, &submit_ptr); if (ret) { - if (ret != -EEXIST) - return ret; - goto out_check; + if (likely(ret == -EEXIST)) + goto out_check; + if (ret == -ENOENT) { + /* + * Block address translation failed due to invalid + * value of 'ptr'. In this case, return internal code + * -EINVAL (broken bmap) to notify bmap layer of fatal + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } if (ra) { diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 6e4e65ee050d..c14e90764e35 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -792,7 +792,7 @@ static int ovl_copy_up_tmpfile(struct ovl_copy_up_ctx *c) if (!c->metacopy && c->stat.size) { err = ovl_copy_up_file(ofs, c->dentry, tmpfile, c->stat.size); if (err) - return err; + goto out_fput; } err = ovl_copy_up_metadata(c, temp); @@ -1011,6 +1011,10 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry, if (err) return err; + if (!kuid_has_mapping(current_user_ns(), ctx.stat.uid) || + !kgid_has_mapping(current_user_ns(), ctx.stat.gid)) + return -EOVERFLOW; + ctx.metacopy = ovl_need_meta_copy_up(dentry, ctx.stat.mode, flags); if (parent) { diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index e35a0398db63..af1c49ae11b1 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -745,9 +745,7 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, page = pfn_swap_entry_to_page(swpent); } if (page) { - int mapcount = page_mapcount(page); - - if (mapcount >= 2) + if (page_mapcount(page) >= 2 || hugetlb_pmd_shared(pte)) mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h index b3fdc8212c5f..95f8e8901768 100644 --- a/fs/squashfs/squashfs_fs.h +++ b/fs/squashfs/squashfs_fs.h @@ -183,7 +183,7 @@ static inline int squashfs_block_size(__le32 raw) #define SQUASHFS_ID_BLOCK_BYTES(A) (SQUASHFS_ID_BLOCKS(A) *\ sizeof(u64)) /* xattr id lookup table defines */ -#define SQUASHFS_XATTR_BYTES(A) ((A) * sizeof(struct squashfs_xattr_id)) +#define SQUASHFS_XATTR_BYTES(A) (((u64) (A)) * sizeof(struct squashfs_xattr_id)) #define SQUASHFS_XATTR_BLOCK(A) (SQUASHFS_XATTR_BYTES(A) / \ SQUASHFS_METADATA_SIZE) diff --git a/fs/squashfs/squashfs_fs_sb.h b/fs/squashfs/squashfs_fs_sb.h index 659082e9e51d..72f6f4b37863 100644 --- a/fs/squashfs/squashfs_fs_sb.h +++ b/fs/squashfs/squashfs_fs_sb.h @@ -63,7 +63,7 @@ struct squashfs_sb_info { long long bytes_used; unsigned int inodes; unsigned int fragments; - int xattr_ids; + unsigned int xattr_ids; unsigned int ids; bool panic_on_errors; const struct squashfs_decompressor_thread_ops *thread_ops; diff --git a/fs/squashfs/xattr.h b/fs/squashfs/xattr.h index d8a270d3ac4c..f1a463d8bfa0 100644 --- a/fs/squashfs/xattr.h +++ b/fs/squashfs/xattr.h @@ -10,12 +10,12 @@ #ifdef CONFIG_SQUASHFS_XATTR extern __le64 *squashfs_read_xattr_id_table(struct super_block *, u64, - u64 *, int *); + u64 *, unsigned int *); extern int squashfs_xattr_lookup(struct super_block *, unsigned int, int *, unsigned int *, unsigned long long *); #else static inline __le64 *squashfs_read_xattr_id_table(struct super_block *sb, - u64 start, u64 *xattr_table_start, int *xattr_ids) + u64 start, u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_xattr_id_table *id_table; diff --git a/fs/squashfs/xattr_id.c b/fs/squashfs/xattr_id.c index 087cab8c78f4..b88d19e9581e 100644 --- a/fs/squashfs/xattr_id.c +++ b/fs/squashfs/xattr_id.c @@ -56,7 +56,7 @@ int squashfs_xattr_lookup(struct super_block *sb, unsigned int index, * Read uncompressed xattr id lookup table indexes from disk into memory */ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, - u64 *xattr_table_start, int *xattr_ids) + u64 *xattr_table_start, unsigned int *xattr_ids) { struct squashfs_sb_info *msblk = sb->s_fs_info; unsigned int len, indexes; @@ -76,7 +76,7 @@ __le64 *squashfs_read_xattr_id_table(struct super_block *sb, u64 table_start, /* Sanity check values */ /* there is always at least one xattr id */ - if (*xattr_ids == 0) + if (*xattr_ids <= 0) return ERR_PTR(-EINVAL); len = SQUASHFS_XATTR_BLOCK_BYTES(*xattr_ids); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 98ac37e34e3d..cc694846617a 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -108,6 +108,21 @@ static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx) return ctx->features & UFFD_FEATURE_INITIALIZED; } +static void userfaultfd_set_vm_flags(struct vm_area_struct *vma, + vm_flags_t flags) +{ + const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP; + + vma->vm_flags = flags; + /* + * For shared mappings, we want to enable writenotify while + * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply + * recalculate vma->vm_page_prot whenever userfaultfd-wp changes. + */ + if ((vma->vm_flags & VM_SHARED) && uffd_wp_changed) + vma_set_page_prot(vma); +} + static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode, int wake_flags, void *key) { @@ -618,7 +633,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, for_each_vma(vmi, vma) { if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~__VM_UFFD_FLAGS; + userfaultfd_set_vm_flags(vma, + vma->vm_flags & ~__VM_UFFD_FLAGS); } } mmap_write_unlock(mm); @@ -652,7 +668,7 @@ int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs) octx = vma->vm_userfaultfd_ctx.ctx; if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~__VM_UFFD_FLAGS; + userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); return 0; } @@ -733,7 +749,7 @@ void mremap_userfaultfd_prep(struct vm_area_struct *vma, } else { /* Drop uffd context if remap feature not enabled */ vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; - vma->vm_flags &= ~__VM_UFFD_FLAGS; + userfaultfd_set_vm_flags(vma, vma->vm_flags & ~__VM_UFFD_FLAGS); } } @@ -895,7 +911,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) prev = vma; } - vma->vm_flags = new_flags; + userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } mmap_write_unlock(mm); @@ -1463,7 +1479,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, * the next vma was merged into the current one and * the current one has not been updated yet. */ - vma->vm_flags = new_flags; + userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx.ctx = ctx; if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma)) @@ -1651,7 +1667,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, * the next vma was merged into the current one and * the current one has not been updated yet. */ - vma->vm_flags = new_flags; + userfaultfd_set_vm_flags(vma, new_flags); vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; skip: diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 4c16c8c31fcb..35f574421670 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4666,7 +4666,12 @@ xfs_btree_space_to_height( const unsigned int *limits, unsigned long long leaf_blocks) { - unsigned long long node_blocks = limits[1]; + /* + * The root btree block can have fewer than minrecs pointers in it + * because the tree might not be big enough to require that amount of + * fanout. Hence it has a minimum size of 2 pointers, not limits[1]. + */ + unsigned long long node_blocks = 2; unsigned long long blocks_left = leaf_blocks - 1; unsigned int height = 1; diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index ad22a003f959..f3d328e4a440 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -236,6 +236,7 @@ xfs_extent_busy_update_extent( * */ busyp->bno = fend; + busyp->length = bend - fend; } else if (bbno < fbno) { /* * Case 8: diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index f35e2cee5265..ddeaccc04aec 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1853,12 +1853,20 @@ xfs_inodegc_worker( struct xfs_inodegc, work); struct llist_node *node = llist_del_all(&gc->list); struct xfs_inode *ip, *n; + unsigned int nofs_flag; WRITE_ONCE(gc->items, 0); if (!node) return; + /* + * We can allocate memory here while doing writeback on behalf of + * memory reclaim. To avoid memory allocation deadlocks set the + * task-wide nofs context for the following operations. + */ + nofs_flag = memalloc_nofs_save(); + ip = llist_entry(node, struct xfs_inode, i_gclist); trace_xfs_inodegc_worker(ip->i_mount, READ_ONCE(gc->shrinker_hits)); @@ -1867,6 +1875,8 @@ xfs_inodegc_worker( xfs_iflags_set(ip, XFS_INACTIVATING); xfs_inodegc_inactivate(ip); } + + memalloc_nofs_restore(nofs_flag); } /* diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 13f1b2add390..736510bc241b 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -754,7 +754,7 @@ xfs_bulkstat_fmt( static int xfs_bulk_ireq_setup( struct xfs_mount *mp, - struct xfs_bulk_ireq *hdr, + const struct xfs_bulk_ireq *hdr, struct xfs_ibulk *breq, void __user *ubuffer) { @@ -780,7 +780,7 @@ xfs_bulk_ireq_setup( switch (hdr->ino) { case XFS_BULK_IREQ_SPECIAL_ROOT: - hdr->ino = mp->m_sb.sb_rootino; + breq->startino = mp->m_sb.sb_rootino; break; default: return -EINVAL; diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 669c1bc5c3a7..fc1946f80a4a 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -83,7 +83,7 @@ xfs_iomap_valid( return true; } -const struct iomap_page_ops xfs_iomap_page_ops = { +static const struct iomap_page_ops xfs_iomap_page_ops = { .iomap_valid = xfs_iomap_valid, }; diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c index ff53d40a2dae..e2c542f6dcd4 100644 --- a/fs/xfs/xfs_qm.c +++ b/fs/xfs/xfs_qm.c @@ -68,7 +68,7 @@ restart: while (1) { struct xfs_dquot *batch[XFS_DQ_LOOKUP_BATCH]; - int error = 0; + int error; int i; mutex_lock(&qi->qi_tree_lock); diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index fe46bce8cae6..5535778a98f9 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -416,8 +416,6 @@ xfs_reflink_fill_cow_hole( goto convert; } - ASSERT(cmap->br_startoff > imap->br_startoff); - /* Allocate the entire reservation as unwritten blocks. */ nimaps = 1; error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount, diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index 2c53fbb8d918..a9c5c3f720ad 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -442,6 +442,10 @@ static int zonefs_io_error_cb(struct blk_zone *zone, unsigned int idx, data_size = zonefs_check_zone_condition(inode, zone, false, false); } + } else if (sbi->s_mount_opts & ZONEFS_MNTOPT_ERRORS_RO && + data_size > isize) { + /* Do not expose garbage data */ + data_size = isize; } /* @@ -805,6 +809,24 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) ret = submit_bio_wait(bio); + /* + * If the file zone was written underneath the file system, the zone + * write pointer may not be where we expect it to be, but the zone + * append write can still succeed. So check manually that we wrote where + * we intended to, that is, at zi->i_wpoffset. + */ + if (!ret) { + sector_t wpsector = + zi->i_zsector + (zi->i_wpoffset >> SECTOR_SHIFT); + + if (bio->bi_iter.bi_sector != wpsector) { + zonefs_warn(inode->i_sb, + "Corrupted write pointer %llu for zone at %llu\n", + wpsector, zi->i_zsector); + ret = -EIO; + } + } + zonefs_file_write_dio_end_io(iocb, size, ret, 0); trace_zonefs_file_dio_append(inode, size, ret); diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index cd3b75e08ec3..e44be31115a6 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -230,7 +230,8 @@ struct acpi_pnp_type { u32 hardware_id:1; u32 bus_address:1; u32 platform_id:1; - u32 reserved:29; + u32 backlight:1; + u32 reserved:28; }; struct acpi_device_pnp { diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h index b111dc7ada78..095370ef029d 100644 --- a/include/drm/drm_fb_helper.h +++ b/include/drm/drm_fb_helper.h @@ -208,6 +208,18 @@ struct drm_fb_helper { * the smem_start field should always be cleared to zero. */ bool hint_leak_smem_start; + +#ifdef CONFIG_FB_DEFERRED_IO + /** + * @fbdefio: + * + * Temporary storage for the driver's FB deferred I/O handler. If the + * driver uses the DRM fbdev emulation layer, this is set by the core + * to a generic deferred I/O handler if a driver is preferring to use + * a shadow buffer. + */ + struct fb_deferred_io fbdefio; +#endif }; static inline struct drm_fb_helper * diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h index 4f8c35206f7c..6c2a2f21dbf0 100644 --- a/include/drm/drm_vma_manager.h +++ b/include/drm/drm_vma_manager.h @@ -74,6 +74,7 @@ void drm_vma_offset_remove(struct drm_vma_offset_manager *mgr, struct drm_vma_offset_node *node); int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag); +int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag); void drm_vma_node_revoke(struct drm_vma_offset_node *node, struct drm_file *tag); bool drm_vma_node_is_allowed(struct drm_vma_offset_node *node, diff --git a/include/kunit/test.h b/include/kunit/test.h index 87ea90576b50..08d3559dd703 100644 --- a/include/kunit/test.h +++ b/include/kunit/test.h @@ -303,7 +303,6 @@ static inline int kunit_run_all_tests(void) */ #define kunit_test_init_section_suites(__suites...) \ __kunit_test_suites(CONCATENATE(__UNIQUE_ID(array), _probe), \ - CONCATENATE(__UNIQUE_ID(suites), _probe), \ ##__suites) #define kunit_test_init_section_suite(suite) \ @@ -683,8 +682,9 @@ do { \ .right_text = #right, \ }; \ \ - if (likely(memcmp(__left, __right, __size) op 0)) \ - break; \ + if (likely(__left && __right)) \ + if (likely(memcmp(__left, __right, __size) op 0)) \ + break; \ \ _KUNIT_FAILED(test, \ assert_type, \ diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index cd6d8f260eab..71916de7c6c4 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -60,7 +60,7 @@ struct arch_timer_cpu { bool enabled; }; -int kvm_timer_hyp_init(bool); +int __init kvm_timer_hyp_init(bool has_gic); int kvm_timer_enable(struct kvm_vcpu *vcpu); int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu); @@ -104,4 +104,8 @@ void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, u32 timer_get_ctl(struct arch_timer_context *ctxt); u64 timer_get_cval(struct arch_timer_context *ctxt); +/* CPU HP callbacks */ +void kvm_timer_cpu_up(void); +void kvm_timer_cpu_down(void); + #endif diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 9270cd87da3f..d3ad51fde9db 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -263,7 +263,7 @@ struct vgic_dist { struct vgic_io_device dist_iodev; bool has_its; - bool save_its_tables_in_progress; + bool table_write_in_progress; /* * Contains the attributes and gpa of the LPI configuration table. @@ -432,4 +432,8 @@ int vgic_v4_load(struct kvm_vcpu *vcpu); void vgic_v4_commit(struct kvm_vcpu *vcpu); int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db); +/* CPU HP callbacks */ +void kvm_vgic_cpu_up(void); +void kvm_vgic_cpu_down(void); + #endif /* __KVM_ARM_VGIC_H */ diff --git a/include/linux/apple-gmux.h b/include/linux/apple-gmux.h index ddb10aa67b14..1f68b49bcd68 100644 --- a/include/linux/apple-gmux.h +++ b/include/linux/apple-gmux.h @@ -8,18 +8,118 @@ #define LINUX_APPLE_GMUX_H #include <linux/acpi.h> +#include <linux/io.h> +#include <linux/pnp.h> #define GMUX_ACPI_HID "APP000B" +/* + * gmux port offsets. Many of these are not yet used, but may be in the + * future, and it's useful to have them documented here anyhow. + */ +#define GMUX_PORT_VERSION_MAJOR 0x04 +#define GMUX_PORT_VERSION_MINOR 0x05 +#define GMUX_PORT_VERSION_RELEASE 0x06 +#define GMUX_PORT_SWITCH_DISPLAY 0x10 +#define GMUX_PORT_SWITCH_GET_DISPLAY 0x11 +#define GMUX_PORT_INTERRUPT_ENABLE 0x14 +#define GMUX_PORT_INTERRUPT_STATUS 0x16 +#define GMUX_PORT_SWITCH_DDC 0x28 +#define GMUX_PORT_SWITCH_EXTERNAL 0x40 +#define GMUX_PORT_SWITCH_GET_EXTERNAL 0x41 +#define GMUX_PORT_DISCRETE_POWER 0x50 +#define GMUX_PORT_MAX_BRIGHTNESS 0x70 +#define GMUX_PORT_BRIGHTNESS 0x74 +#define GMUX_PORT_VALUE 0xc2 +#define GMUX_PORT_READ 0xd0 +#define GMUX_PORT_WRITE 0xd4 + +#define GMUX_MIN_IO_LEN (GMUX_PORT_BRIGHTNESS + 4) + #if IS_ENABLED(CONFIG_APPLE_GMUX) +static inline bool apple_gmux_is_indexed(unsigned long iostart) +{ + u16 val; + + outb(0xaa, iostart + 0xcc); + outb(0x55, iostart + 0xcd); + outb(0x00, iostart + 0xce); + + val = inb(iostart + 0xcc) | (inb(iostart + 0xcd) << 8); + if (val == 0x55aa) + return true; + + return false; +} /** - * apple_gmux_present() - detect if gmux is built into the machine + * apple_gmux_detect() - detect if gmux is built into the machine + * + * @pnp_dev: Device to probe or NULL to use the first matching device + * @indexed_ret: Returns (by reference) if the gmux is indexed or not + * + * Detect if a supported gmux device is present by actually probing it. + * This avoids the false positives returned on some models by + * apple_gmux_present(). + * + * Return: %true if a supported gmux ACPI device is detected and the kernel + * was configured with CONFIG_APPLE_GMUX, %false otherwise. + */ +static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret) +{ + u8 ver_major, ver_minor, ver_release; + struct device *dev = NULL; + struct acpi_device *adev; + struct resource *res; + bool indexed = false; + bool ret = false; + + if (!pnp_dev) { + adev = acpi_dev_get_first_match_dev(GMUX_ACPI_HID, NULL, -1); + if (!adev) + return false; + + dev = get_device(acpi_get_first_physical_node(adev)); + acpi_dev_put(adev); + if (!dev) + return false; + + pnp_dev = to_pnp_dev(dev); + } + + res = pnp_get_resource(pnp_dev, IORESOURCE_IO, 0); + if (!res || resource_size(res) < GMUX_MIN_IO_LEN) + goto out; + + /* + * Invalid version information may indicate either that the gmux + * device isn't present or that it's a new one that uses indexed io. + */ + ver_major = inb(res->start + GMUX_PORT_VERSION_MAJOR); + ver_minor = inb(res->start + GMUX_PORT_VERSION_MINOR); + ver_release = inb(res->start + GMUX_PORT_VERSION_RELEASE); + if (ver_major == 0xff && ver_minor == 0xff && ver_release == 0xff) { + indexed = apple_gmux_is_indexed(res->start); + if (!indexed) + goto out; + } + + if (indexed_ret) + *indexed_ret = indexed; + + ret = true; +out: + put_device(dev); + return ret; +} + +/** + * apple_gmux_present() - check if gmux ACPI device is present * * Drivers may use this to activate quirks specific to dual GPU MacBook Pros * and Mac Pros, e.g. for deferred probing, runtime pm and backlight. * - * Return: %true if gmux is present and the kernel was configured + * Return: %true if gmux ACPI device is present and the kernel was configured * with CONFIG_APPLE_GMUX, %false otherwise. */ static inline bool apple_gmux_present(void) @@ -34,6 +134,11 @@ static inline bool apple_gmux_present(void) return false; } +static inline bool apple_gmux_detect(struct pnp_dev *pnp_dev, bool *indexed_ret) +{ + return false; +} + #endif /* !CONFIG_APPLE_GMUX */ #endif /* LINUX_APPLE_GMUX_H */ diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3de24cfb7a3d..634d37a599fa 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1832,7 +1832,7 @@ void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); -void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); +void bpf_prog_free_id(struct bpf_prog *prog); void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock); struct btf_field *btf_record_find(const struct btf_record *rec, diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 00af2c98da75..4497d0a6772c 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -99,16 +99,6 @@ struct ceph_options { #define CEPH_AUTH_NAME_DEFAULT "guest" -/* mount state */ -enum { - CEPH_MOUNT_MOUNTING, - CEPH_MOUNT_MOUNTED, - CEPH_MOUNT_UNMOUNTING, - CEPH_MOUNT_UNMOUNTED, - CEPH_MOUNT_SHUTDOWN, - CEPH_MOUNT_RECOVER, -}; - static inline unsigned long ceph_timeout_jiffies(unsigned long timeout) { return timeout ?: MAX_SCHEDULE_TIMEOUT; diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6c6859bfc454..5b2f8147d1ae 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -187,10 +187,6 @@ enum cpuhp_state { CPUHP_AP_CSKY_TIMER_STARTING, CPUHP_AP_TI_GP_TIMER_STARTING, CPUHP_AP_HYPERV_TIMER_STARTING, - CPUHP_AP_KVM_STARTING, - CPUHP_AP_KVM_ARM_VGIC_INIT_STARTING, - CPUHP_AP_KVM_ARM_VGIC_STARTING, - CPUHP_AP_KVM_ARM_TIMER_STARTING, /* Must be the last timer callback */ CPUHP_AP_DUMMY_TIMER_STARTING, CPUHP_AP_ARM_XEN_STARTING, @@ -205,6 +201,7 @@ enum cpuhp_state { /* Online section invoked on the hotplugged CPU from the hotplug thread */ CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_KVM_ONLINE, CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, diff --git a/include/linux/efi.h b/include/linux/efi.h index 4b27519143f5..98598bd1d2fa 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -668,7 +668,8 @@ extern struct efi { #define EFI_RT_SUPPORTED_ALL 0x3fff -#define EFI_RT_SUPPORTED_TIME_SERVICES 0x000f +#define EFI_RT_SUPPORTED_TIME_SERVICES 0x0003 +#define EFI_RT_SUPPORTED_WAKEUP_SERVICES 0x000c #define EFI_RT_SUPPORTED_VARIABLE_SERVICES 0x0070 extern struct mm_struct efi_mm; diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h index 9ec81290e3c8..bd5560542c79 100644 --- a/include/linux/elfcore.h +++ b/include/linux/elfcore.h @@ -105,14 +105,14 @@ int elf_core_copy_task_fpregs(struct task_struct *t, elf_fpregset_t *fpu); * Dumping its extra ELF program headers includes all the other information * a debugger needs to easily find how the gate DSO was being used. */ -extern Elf_Half elf_core_extra_phdrs(void); +extern Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm); extern int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset); extern int elf_core_write_extra_data(struct coredump_params *cprm); -extern size_t elf_core_extra_data_size(void); +extern size_t elf_core_extra_data_size(struct coredump_params *cprm); #else -static inline Elf_Half elf_core_extra_phdrs(void) +static inline Elf_Half elf_core_extra_phdrs(struct coredump_params *cprm) { return 0; } @@ -127,7 +127,7 @@ static inline int elf_core_write_extra_data(struct coredump_params *cprm) return 1; } -static inline size_t elf_core_extra_data_size(void) +static inline size_t elf_core_extra_data_size(struct coredump_params *cprm) { return 0; } diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h index b986e267d149..b09f443d3ab9 100644 --- a/include/linux/firmware/xlnx-zynqmp.h +++ b/include/linux/firmware/xlnx-zynqmp.h @@ -545,8 +545,8 @@ int zynqmp_pm_request_wake(const u32 node, const u64 address, const enum zynqmp_pm_request_ack ack); int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode); -int zynqmp_pm_set_rpu_mode(u32 node_id, u32 arg1); -int zynqmp_pm_set_tcm_config(u32 node_id, u32 arg1); +int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode); +int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode); int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value); int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config, u32 value); @@ -845,12 +845,12 @@ static inline int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mo return -ENODEV; } -static inline int zynqmp_pm_set_rpu_mode(u32 node_id, u32 arg1) +static inline int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode) { return -ENODEV; } -static inline int zynqmp_pm_set_tcm_config(u32 node_id, u32 arg1) +static inline int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode) { return -ENODEV; } diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h index 034b1106d022..e098f38422af 100644 --- a/include/linux/highmem-internal.h +++ b/include/linux/highmem-internal.h @@ -200,7 +200,7 @@ static inline void *kmap_local_pfn(unsigned long pfn) static inline void __kunmap_local(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP - kunmap_flush_on_unmap(addr); + kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif } @@ -227,7 +227,7 @@ static inline void *kmap_atomic_pfn(unsigned long pfn) static inline void __kunmap_atomic(const void *addr) { #ifdef ARCH_HAS_FLUSH_ON_KUNMAP - kunmap_flush_on_unmap(addr); + kunmap_flush_on_unmap(PTR_ALIGN_DOWN(addr, PAGE_SIZE)); #endif pagefault_enable(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 551834cd5299..db194e2ba69f 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -7,6 +7,7 @@ #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> +#include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> @@ -1187,6 +1188,18 @@ static inline __init void hugetlb_cma_reserve(int order) } #endif +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return page_count(virt_to_page(pte)) > 1; +} +#else +static inline bool hugetlb_pmd_shared(pte_t *pte) +{ + return false; +} +#endif + bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4f26b244f6d0..8ada23756b0e 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -324,7 +324,7 @@ struct kvm_vcpu { #endif int cpu; int vcpu_id; /* id given by userspace at creation */ - int vcpu_idx; /* index in kvm->vcpus array */ + int vcpu_idx; /* index into kvm->vcpu_array */ int ____srcu_idx; /* Don't use this directly. You've been warned. */ #ifdef CONFIG_PROVE_RCU int srcu_depth; @@ -956,8 +956,7 @@ static inline void kvm_irqfd_exit(void) { } #endif -int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, - struct module *module); +int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module); void kvm_exit(void); void kvm_get_kvm(struct kvm *kvm); @@ -1354,7 +1353,7 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu); void kvm_vcpu_kick(struct kvm_vcpu *vcpu); int kvm_vcpu_yield_to(struct kvm_vcpu *target); -void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool usermode_vcpu_not_eligible); +void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode); void kvm_flush_remote_tlbs(struct kvm *kvm); @@ -1423,9 +1422,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg); int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu); -int kvm_arch_init(void *opaque); -void kvm_arch_exit(void); - void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu); void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu); @@ -1445,11 +1441,10 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {} #endif +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING int kvm_arch_hardware_enable(void); void kvm_arch_hardware_disable(void); -int kvm_arch_hardware_setup(void *opaque); -void kvm_arch_hardware_unsetup(void); -int kvm_arch_check_processor_compat(void *opaque); +#endif int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); @@ -1466,7 +1461,7 @@ int kvm_arch_create_vm_debugfs(struct kvm *kvm); */ static inline struct kvm *kvm_arch_alloc_vm(void) { - return kzalloc(sizeof(struct kvm), GFP_KERNEL); + return kzalloc(sizeof(struct kvm), GFP_KERNEL_ACCOUNT); } #endif @@ -2081,7 +2076,9 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu) } } +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING extern bool kvm_rebooting; +#endif extern unsigned int halt_poll_ns; extern unsigned int halt_poll_ns_grow; diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index d3c8203cab6c..85dc9b88ea37 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1666,10 +1666,13 @@ void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { + struct mem_cgroup *memcg; + if (mem_cgroup_disabled()) return; - if (unlikely(&folio_memcg(folio)->css != wb->memcg_css)) + memcg = folio_memcg(folio); + if (unlikely(memcg && &memcg->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(folio, wb); } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index d476255c9a3f..76ef2e4fde38 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -315,7 +315,7 @@ struct mlx5_cmd { struct mlx5_cmd_debug dbg; struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES]; int checksum_disabled; - struct mlx5_cmd_stats *stats; + struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX]; }; struct mlx5_cmd_mailbox { diff --git a/include/linux/mm.h b/include/linux/mm.h index f3f196e4d66d..8f857163ac89 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1270,10 +1270,10 @@ static inline void folio_put_refs(struct folio *folio, int refs) __folio_put(folio); } -/** - * release_pages - release an array of pages or folios +/* + * union release_pages_arg - an array of pages or folios * - * This just releases a simple array of multiple pages, and + * release_pages() releases a simple array of multiple pages, and * accepts various different forms of said page array: either * a regular old boring array of pages, an array of folios, or * an array of encoded page pointers. diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index e8ed225d8f7c..ff3f3f23f649 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -413,8 +413,7 @@ static inline void free_anon_vma_name(struct vm_area_struct *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); + anon_vma_name_put(vma->anon_name); } static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 3b8475007734..9757067c3053 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -581,7 +581,7 @@ struct vm_area_struct { /* * For private and shared anonymous mappings, a pointer to a null * terminated string containing the name given to the vma, or NULL if - * unnamed. Serialized by mmap_sem. Use anon_vma_name to access. + * unnamed. Serialized by mmap_lock. Use anon_vma_name to access. */ struct anon_vma_name *anon_name; #endif diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index 25765556223a..a3f8cdca90c8 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -7,7 +7,6 @@ #define __LINUX_MTD_SPI_NOR_H #include <linux/bitops.h> -#include <linux/mtd/cfi.h> #include <linux/mtd/mtd.h> #include <linux/spi/spi-mem.h> diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h index 50caa117cb62..bb15c9234e21 100644 --- a/include/linux/nvmem-provider.h +++ b/include/linux/nvmem-provider.h @@ -70,7 +70,6 @@ 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 * @ignore_wp: Write Protect pin is managed by the provider. * * Note: A default "nvmem<id>" name will be assigned to the device if @@ -85,7 +84,6 @@ struct nvmem_config { const char *name; int id; struct module *owner; - struct gpio_desc *wp_gpio; const struct nvmem_cell_info *cells; int ncells; const struct nvmem_keepout *keepout; diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h index 2e677e6ad09f..d7c2d33baa7f 100644 --- a/include/linux/page_ref.h +++ b/include/linux/page_ref.h @@ -301,7 +301,7 @@ static inline bool folio_ref_try_add_rcu(struct folio *folio, int count) * * You can also use this function if you're holding a lock that prevents * pages being frozen & removed; eg the i_pages lock for the page cache - * or the mmap_sem or page table lock for page tables. In this case, + * or the mmap_lock or page table lock for page tables. In this case, * it will always succeed, and you could have used a plain folio_get(), * but it's sometimes more convenient to have a common function called * from both locked and RCU-protected contexts. diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index e17e86ad6f3a..43fc892aa7d9 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -26,6 +26,8 @@ #define RISCV_PMU_STOP_FLAG_RESET 1 +#define RISCV_PMU_CONFIG1_GUEST_EVENTS 0x1 + struct cpu_hw_events { /* currently enabled events */ int n_events; @@ -73,6 +75,9 @@ void riscv_pmu_legacy_skip_init(void); static inline void riscv_pmu_legacy_skip_init(void) {}; #endif struct riscv_pmu *riscv_pmu_alloc(void); +#ifdef CONFIG_RISCV_PMU_SBI +int riscv_pmu_get_hpm_info(u32 *hw_ctr_width, u32 *num_hw_ctr); +#endif #endif /* CONFIG_RISCV_PMU */ diff --git a/include/linux/platform_data/x86/simatic-ipc.h b/include/linux/platform_data/x86/simatic-ipc.h index 632320ec8f08..a48bb5240977 100644 --- a/include/linux/platform_data/x86/simatic-ipc.h +++ b/include/linux/platform_data/x86/simatic-ipc.h @@ -32,7 +32,8 @@ enum simatic_ipc_station_ids { SIMATIC_IPC_IPC477E = 0x00000A02, SIMATIC_IPC_IPC127E = 0x00000D01, SIMATIC_IPC_IPC227G = 0x00000F01, - SIMATIC_IPC_IPC427G = 0x00001001, + SIMATIC_IPC_IPCBX_39A = 0x00001001, + SIMATIC_IPC_IPCPX_39A = 0x00001002, }; static inline u32 simatic_ipc_get_station_id(u8 *data, int max_len) diff --git a/include/linux/soc/ti/omap1-io.h b/include/linux/soc/ti/omap1-io.h index f7f12728d4a6..9a60f45899d3 100644 --- a/include/linux/soc/ti/omap1-io.h +++ b/include/linux/soc/ti/omap1-io.h @@ -5,7 +5,7 @@ #ifndef __ASSEMBLER__ #include <linux/types.h> -#ifdef CONFIG_ARCH_OMAP1_ANY +#ifdef CONFIG_ARCH_OMAP1 /* * NOTE: Please use ioremap + __raw_read/write where possible instead of these */ @@ -15,7 +15,7 @@ extern u32 omap_readl(u32 pa); extern void omap_writeb(u8 v, u32 pa); extern void omap_writew(u16 v, u32 pa); extern void omap_writel(u32 v, u32 pa); -#else +#elif defined(CONFIG_COMPILE_TEST) static inline u8 omap_readb(u32 pa) { return 0; } static inline u16 omap_readw(u32 pa) { return 0; } static inline u32 omap_readl(u32 pa) { return 0; } diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 1341f7d62da4..be48f1cb1878 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -476,6 +476,15 @@ extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) +extern int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock); +#define atomic_dec_and_raw_lock(atomic, lock) \ + __cond_lock(lock, _atomic_dec_and_raw_lock(atomic, lock)) + +extern int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, + unsigned long *flags); +#define atomic_dec_and_raw_lock_irqsave(atomic, lock, flags) \ + __cond_lock(lock, _atomic_dec_and_raw_lock_irqsave(atomic, lock, &(flags))) + int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 83ca2e8eb6b5..a152678b82b7 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -252,6 +252,7 @@ struct plat_stmmacenet_data { int rss_en; int mac_port_sel_speed; bool en_tx_lpi_clockgating; + bool rx_clk_runs_in_lpi; int has_xgmac; bool vlan_fail_q_en; u8 vlan_fail_q; diff --git a/include/linux/swap.h b/include/linux/swap.h index 2787b84eaf12..0ceed49516ad 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -418,8 +418,7 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options, - nodemask_t *nodemask); + unsigned int reclaim_options); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, diff --git a/include/linux/tpm_eventlog.h b/include/linux/tpm_eventlog.h index 20c0ff54b7a0..7d68a5cc5881 100644 --- a/include/linux/tpm_eventlog.h +++ b/include/linux/tpm_eventlog.h @@ -198,8 +198,8 @@ static __always_inline int __calc_tpm2_event_size(struct tcg_pcr_event2_head *ev * The loop below will unmap these fields if the log is larger than * one page, so save them here for reference: */ - count = READ_ONCE(event->count); - event_type = READ_ONCE(event->event_type); + count = event->count; + event_type = event->event_type; /* Verify that it's the log header */ if (event_header->pcr_idx != 0 || diff --git a/include/linux/usb.h b/include/linux/usb.h index 7d5325d47c45..86d1c8e79566 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -267,16 +267,15 @@ static inline void *usb_get_intfdata(struct usb_interface *intf) } /** - * usb_set_intfdata() - associate driver-specific data with the interface - * @intf: the usb interface - * @data: pointer to the device priv structure or %NULL + * usb_set_intfdata() - associate driver-specific data with an interface + * @intf: USB interface + * @data: driver data * - * Drivers should use this function in their probe() to associate their - * driver-specific data with the usb interface. + * Drivers can use this function in their probe() callbacks to associate + * driver-specific data with an interface. * - * When disconnecting, the core will take care of setting @intf back to %NULL, - * so no actions are needed on the driver side. The interface should not be set - * to %NULL before all actions completed (e.g. no outsanding URB remaining). + * Note that there is generally no need to clear the driver-data pointer even + * if some drivers do so for historical or implementation-specific reasons. */ static inline void usb_set_intfdata(struct usb_interface *intf, void *data) { @@ -774,11 +773,14 @@ extern struct device *usb_intf_get_dma_device(struct usb_interface *intf); extern int usb_acpi_set_power_state(struct usb_device *hdev, int index, bool enable); extern bool usb_acpi_power_manageable(struct usb_device *hdev, int index); +extern int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index); #else static inline int usb_acpi_set_power_state(struct usb_device *hdev, int index, bool enable) { return 0; } static inline bool usb_acpi_power_manageable(struct usb_device *hdev, int index) { return true; } +static inline int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index) + { return 0; } #endif /* USB autosuspend and autoresume */ diff --git a/include/linux/util_macros.h b/include/linux/util_macros.h index 72299f261b25..43db6e47503c 100644 --- a/include/linux/util_macros.h +++ b/include/linux/util_macros.h @@ -38,4 +38,16 @@ */ #define find_closest_descending(x, a, as) __find_closest(x, a, as, >=) +/** + * is_insidevar - check if the @ptr points inside the @var memory range. + * @ptr: the pointer to a memory address. + * @var: the variable which address and size identify the memory range. + * + * Evaluates to true if the address in @ptr lies within the memory + * range allocated to @var. + */ +#define is_insidevar(ptr, var) \ + ((uintptr_t)(ptr) >= (uintptr_t)(var) && \ + (uintptr_t)(ptr) < (uintptr_t)(var) + sizeof(var)) + #endif diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index d5a5ae926380..ba717eac0229 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -15,6 +15,7 @@ struct key; struct sock; struct socket; struct rxrpc_call; +enum rxrpc_abort_reason; enum rxrpc_interruptibility { RXRPC_INTERRUPTIBLE, /* Call is interruptible */ @@ -55,7 +56,7 @@ int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *, int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *, struct iov_iter *, size_t *, bool, u32 *, u16 *); bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *, - u32, int, const char *); + u32, int, enum rxrpc_abort_reason); void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *); void rxrpc_kernel_get_peer(struct socket *, struct rxrpc_call *, struct sockaddr_rxrpc *); diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 689da327ce2e..e3235b9c02c2 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1832,8 +1832,6 @@ struct ieee80211_vif_cfg { * @drv_priv: data area for driver use, will always be aligned to * sizeof(void \*). * @txq: the multicast data TX queue - * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped, - * protected by fq->lock. * @offload_flags: 802.3 -> 802.11 enapsulation offload flags, see * &enum ieee80211_offload_flags. * @mbssid_tx_vif: Pointer to the transmitting interface if MBSSID is enabled. @@ -1863,8 +1861,6 @@ struct ieee80211_vif { bool probe_req_reg; bool rx_mcast_action_reg; - bool txqs_stopped[IEEE80211_NUM_ACS]; - struct ieee80211_vif *mbssid_tx_vif; /* must be last */ diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index b3ba04615caa..56189e4252da 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -336,9 +336,12 @@ struct gdma_queue_spec { }; }; +#define MANA_IRQ_NAME_SZ 32 + struct gdma_irq_context { void (*handler)(void *arg); void *arg; + char name[MANA_IRQ_NAME_SZ]; }; struct gdma_context { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index d5517719af4e..af4aa66aaa4e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1288,4 +1288,11 @@ void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx); int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); +/* Make sure qdisc is no longer in SCHED state. */ +static inline void qdisc_synchronize(const struct Qdisc *q) +{ + while (test_bit(__QDISC_STATE_SCHED, &q->state)) + msleep(1); +} + #endif diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index 695eebc6f2c8..e39fb0736ade 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -422,6 +422,8 @@ extern int iscsi_host_get_max_scsi_cmds(struct Scsi_Host *shost, extern struct iscsi_cls_session * iscsi_session_setup(struct iscsi_transport *, struct Scsi_Host *shost, uint16_t, int, int, uint32_t, unsigned int); +void iscsi_session_remove(struct iscsi_cls_session *cls_session); +void iscsi_session_free(struct iscsi_cls_session *cls_session); extern void iscsi_session_teardown(struct iscsi_cls_session *); extern void iscsi_session_recovery_timedout(struct iscsi_cls_session *); extern int iscsi_set_param(struct iscsi_cls_conn *cls_conn, diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h index cab52b0f11d0..34c03707fb6e 100644 --- a/include/scsi/scsi_transport_iscsi.h +++ b/include/scsi/scsi_transport_iscsi.h @@ -236,6 +236,14 @@ enum { ISCSI_SESSION_FREE, }; +enum { + ISCSI_SESSION_TARGET_UNBOUND, + ISCSI_SESSION_TARGET_ALLOCATED, + ISCSI_SESSION_TARGET_SCANNED, + ISCSI_SESSION_TARGET_UNBINDING, + ISCSI_SESSION_TARGET_MAX, +}; + #define ISCSI_MAX_TARGET -1 struct iscsi_cls_session { @@ -264,6 +272,7 @@ struct iscsi_cls_session { */ pid_t creator; int state; + int target_state; /* session target bind state */ int sid; /* session id */ void *dd_data; /* LLD private data */ struct device dev; /* sysfs transport/container device */ diff --git a/include/soc/bcm2835/raspberrypi-firmware.h b/include/soc/bcm2835/raspberrypi-firmware.h index ab955591cb72..73cac8d0287e 100644 --- a/include/soc/bcm2835/raspberrypi-firmware.h +++ b/include/soc/bcm2835/raspberrypi-firmware.h @@ -170,7 +170,7 @@ struct rpi_firmware_clk_rate_request { #define RPI_FIRMWARE_CLK_RATE_REQUEST(_id) \ { \ - .id = _id, \ + .id = cpu_to_le32(_id), \ } #if IS_ENABLED(CONFIG_RASPBERRYPI_FIRMWARE) diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 5f9dd7389536..283db0ea3db4 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -16,7 +16,107 @@ /* * Declare tracing information enums and their string mappings for display. */ +#define rxrpc_abort_reasons \ + /* AFS errors */ \ + EM(afs_abort_general_error, "afs-error") \ + EM(afs_abort_interrupted, "afs-intr") \ + EM(afs_abort_oom, "afs-oom") \ + EM(afs_abort_op_not_supported, "afs-op-notsupp") \ + EM(afs_abort_probeuuid_negative, "afs-probeuuid-neg") \ + EM(afs_abort_send_data_error, "afs-send-data") \ + EM(afs_abort_unmarshal_error, "afs-unmarshal") \ + /* rxperf errors */ \ + EM(rxperf_abort_general_error, "rxperf-error") \ + EM(rxperf_abort_oom, "rxperf-oom") \ + EM(rxperf_abort_op_not_supported, "rxperf-op-notsupp") \ + EM(rxperf_abort_unmarshal_error, "rxperf-unmarshal") \ + /* RxKAD security errors */ \ + EM(rxkad_abort_1_short_check, "rxkad1-short-check") \ + EM(rxkad_abort_1_short_data, "rxkad1-short-data") \ + EM(rxkad_abort_1_short_encdata, "rxkad1-short-encdata") \ + EM(rxkad_abort_1_short_header, "rxkad1-short-hdr") \ + EM(rxkad_abort_2_short_check, "rxkad2-short-check") \ + EM(rxkad_abort_2_short_data, "rxkad2-short-data") \ + EM(rxkad_abort_2_short_header, "rxkad2-short-hdr") \ + EM(rxkad_abort_2_short_len, "rxkad2-short-len") \ + EM(rxkad_abort_bad_checksum, "rxkad2-bad-cksum") \ + EM(rxkad_abort_chall_key_expired, "rxkad-chall-key-exp") \ + EM(rxkad_abort_chall_level, "rxkad-chall-level") \ + EM(rxkad_abort_chall_no_key, "rxkad-chall-nokey") \ + EM(rxkad_abort_chall_short, "rxkad-chall-short") \ + EM(rxkad_abort_chall_version, "rxkad-chall-version") \ + EM(rxkad_abort_resp_bad_callid, "rxkad-resp-bad-callid") \ + EM(rxkad_abort_resp_bad_checksum, "rxkad-resp-bad-cksum") \ + EM(rxkad_abort_resp_bad_param, "rxkad-resp-bad-param") \ + EM(rxkad_abort_resp_call_ctr, "rxkad-resp-call-ctr") \ + EM(rxkad_abort_resp_call_state, "rxkad-resp-call-state") \ + EM(rxkad_abort_resp_key_expired, "rxkad-resp-key-exp") \ + EM(rxkad_abort_resp_key_rejected, "rxkad-resp-key-rej") \ + EM(rxkad_abort_resp_level, "rxkad-resp-level") \ + EM(rxkad_abort_resp_nokey, "rxkad-resp-nokey") \ + EM(rxkad_abort_resp_ooseq, "rxkad-resp-ooseq") \ + EM(rxkad_abort_resp_short, "rxkad-resp-short") \ + EM(rxkad_abort_resp_short_tkt, "rxkad-resp-short-tkt") \ + EM(rxkad_abort_resp_tkt_aname, "rxkad-resp-tk-aname") \ + EM(rxkad_abort_resp_tkt_expired, "rxkad-resp-tk-exp") \ + EM(rxkad_abort_resp_tkt_future, "rxkad-resp-tk-future") \ + EM(rxkad_abort_resp_tkt_inst, "rxkad-resp-tk-inst") \ + EM(rxkad_abort_resp_tkt_len, "rxkad-resp-tk-len") \ + EM(rxkad_abort_resp_tkt_realm, "rxkad-resp-tk-realm") \ + EM(rxkad_abort_resp_tkt_short, "rxkad-resp-tk-short") \ + EM(rxkad_abort_resp_tkt_sinst, "rxkad-resp-tk-sinst") \ + EM(rxkad_abort_resp_tkt_sname, "rxkad-resp-tk-sname") \ + EM(rxkad_abort_resp_unknown_tkt, "rxkad-resp-unknown-tkt") \ + EM(rxkad_abort_resp_version, "rxkad-resp-version") \ + /* rxrpc errors */ \ + EM(rxrpc_abort_call_improper_term, "call-improper-term") \ + EM(rxrpc_abort_call_reset, "call-reset") \ + EM(rxrpc_abort_call_sendmsg, "call-sendmsg") \ + EM(rxrpc_abort_call_sock_release, "call-sock-rel") \ + EM(rxrpc_abort_call_sock_release_tba, "call-sock-rel-tba") \ + EM(rxrpc_abort_call_timeout, "call-timeout") \ + EM(rxrpc_abort_no_service_key, "no-serv-key") \ + EM(rxrpc_abort_nomem, "nomem") \ + EM(rxrpc_abort_service_not_offered, "serv-not-offered") \ + EM(rxrpc_abort_shut_down, "shut-down") \ + EM(rxrpc_abort_unsupported_security, "unsup-sec") \ + EM(rxrpc_badmsg_bad_abort, "bad-abort") \ + EM(rxrpc_badmsg_bad_jumbo, "bad-jumbo") \ + EM(rxrpc_badmsg_short_ack, "short-ack") \ + EM(rxrpc_badmsg_short_ack_info, "short-ack-info") \ + EM(rxrpc_badmsg_short_hdr, "short-hdr") \ + EM(rxrpc_badmsg_unsupported_packet, "unsup-pkt") \ + EM(rxrpc_badmsg_zero_call, "zero-call") \ + EM(rxrpc_badmsg_zero_seq, "zero-seq") \ + EM(rxrpc_badmsg_zero_service, "zero-service") \ + EM(rxrpc_eproto_ackr_outside_window, "ackr-out-win") \ + EM(rxrpc_eproto_ackr_sack_overflow, "ackr-sack-over") \ + EM(rxrpc_eproto_ackr_short_sack, "ackr-short-sack") \ + EM(rxrpc_eproto_ackr_zero, "ackr-zero") \ + EM(rxrpc_eproto_bad_upgrade, "bad-upgrade") \ + EM(rxrpc_eproto_data_after_last, "data-after-last") \ + EM(rxrpc_eproto_different_last, "diff-last") \ + EM(rxrpc_eproto_early_reply, "early-reply") \ + EM(rxrpc_eproto_improper_term, "improper-term") \ + EM(rxrpc_eproto_no_client_call, "no-cl-call") \ + EM(rxrpc_eproto_no_client_conn, "no-cl-conn") \ + EM(rxrpc_eproto_no_service_call, "no-sv-call") \ + EM(rxrpc_eproto_reupgrade, "re-upgrade") \ + EM(rxrpc_eproto_rxnull_challenge, "rxnull-chall") \ + EM(rxrpc_eproto_rxnull_response, "rxnull-resp") \ + EM(rxrpc_eproto_tx_rot_last, "tx-rot-last") \ + EM(rxrpc_eproto_unexpected_ack, "unex-ack") \ + EM(rxrpc_eproto_unexpected_ackall, "unex-ackall") \ + EM(rxrpc_eproto_unexpected_implicit_end, "unex-impl-end") \ + EM(rxrpc_eproto_unexpected_reply, "unex-reply") \ + EM(rxrpc_eproto_wrong_security, "wrong-sec") \ + EM(rxrpc_recvmsg_excess_data, "recvmsg-excess") \ + EM(rxrpc_recvmsg_short_data, "recvmsg-short") \ + E_(rxrpc_sendmsg_late_send, "sendmsg-late") + #define rxrpc_call_poke_traces \ + EM(rxrpc_call_poke_abort, "Abort") \ + EM(rxrpc_call_poke_complete, "Compl") \ EM(rxrpc_call_poke_error, "Error") \ EM(rxrpc_call_poke_idle, "Idle") \ EM(rxrpc_call_poke_start, "Start") \ @@ -26,6 +126,7 @@ #define rxrpc_skb_traces \ EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \ EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ + EM(rxrpc_skb_get_conn_secured, "GET conn-secd") \ EM(rxrpc_skb_get_conn_work, "GET conn-work") \ EM(rxrpc_skb_get_local_work, "GET locl-work") \ EM(rxrpc_skb_get_reject_work, "GET rej-work ") \ @@ -35,6 +136,7 @@ EM(rxrpc_skb_new_error_report, "NEW error-rpt") \ EM(rxrpc_skb_new_jumbo_subpacket, "NEW jumbo-sub") \ EM(rxrpc_skb_new_unshared, "NEW unshared ") \ + EM(rxrpc_skb_put_conn_secured, "PUT conn-secd") \ EM(rxrpc_skb_put_conn_work, "PUT conn-work") \ EM(rxrpc_skb_put_error_report, "PUT error-rep") \ EM(rxrpc_skb_put_input, "PUT input ") \ @@ -76,7 +178,6 @@ #define rxrpc_peer_traces \ EM(rxrpc_peer_free, "FREE ") \ EM(rxrpc_peer_get_accept, "GET accept ") \ - EM(rxrpc_peer_get_activate_call, "GET act-call") \ EM(rxrpc_peer_get_bundle, "GET bundle ") \ EM(rxrpc_peer_get_client_conn, "GET cln-conn") \ EM(rxrpc_peer_get_input, "GET input ") \ @@ -89,7 +190,6 @@ EM(rxrpc_peer_put_bundle, "PUT bundle ") \ EM(rxrpc_peer_put_call, "PUT call ") \ EM(rxrpc_peer_put_conn, "PUT conn ") \ - EM(rxrpc_peer_put_discard_tmp, "PUT disc-tmp") \ EM(rxrpc_peer_put_input, "PUT input ") \ EM(rxrpc_peer_put_input_error, "PUT inpt-err") \ E_(rxrpc_peer_put_keepalive, "PUT keepaliv") @@ -99,6 +199,7 @@ EM(rxrpc_bundle_get_client_call, "GET clt-call") \ EM(rxrpc_bundle_get_client_conn, "GET clt-conn") \ EM(rxrpc_bundle_get_service_conn, "GET svc-conn") \ + EM(rxrpc_bundle_put_call, "PUT call ") \ EM(rxrpc_bundle_put_conn, "PUT conn ") \ EM(rxrpc_bundle_put_discard, "PUT discard ") \ E_(rxrpc_bundle_new, "NEW ") @@ -109,14 +210,14 @@ EM(rxrpc_conn_get_call_input, "GET inp-call") \ EM(rxrpc_conn_get_conn_input, "GET inp-conn") \ EM(rxrpc_conn_get_idle, "GET idle ") \ - EM(rxrpc_conn_get_poke, "GET poke ") \ + EM(rxrpc_conn_get_poke_abort, "GET pk-abort") \ + EM(rxrpc_conn_get_poke_timer, "GET poke ") \ EM(rxrpc_conn_get_service_conn, "GET svc-conn") \ EM(rxrpc_conn_new_client, "NEW client ") \ EM(rxrpc_conn_new_service, "NEW service ") \ EM(rxrpc_conn_put_call, "PUT call ") \ EM(rxrpc_conn_put_call_input, "PUT inp-call") \ EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \ - EM(rxrpc_conn_put_discard, "PUT discard ") \ EM(rxrpc_conn_put_discard_idle, "PUT disc-idl") \ EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \ EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \ @@ -124,10 +225,10 @@ EM(rxrpc_conn_put_service_reaped, "PUT svc-reap") \ EM(rxrpc_conn_put_unbundle, "PUT unbundle") \ EM(rxrpc_conn_put_unidle, "PUT unidle ") \ + EM(rxrpc_conn_put_work, "PUT work ") \ EM(rxrpc_conn_queue_challenge, "QUE chall ") \ EM(rxrpc_conn_queue_retry_work, "QUE retry-wk") \ EM(rxrpc_conn_queue_rx_work, "QUE rx-work ") \ - EM(rxrpc_conn_queue_timer, "QUE timer ") \ EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \ EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \ E_(rxrpc_conn_see_work, "SEE work ") @@ -138,16 +239,16 @@ EM(rxrpc_client_chan_activate, "ChActv") \ EM(rxrpc_client_chan_disconnect, "ChDisc") \ EM(rxrpc_client_chan_pass, "ChPass") \ - EM(rxrpc_client_chan_wait_failed, "ChWtFl") \ EM(rxrpc_client_cleanup, "Clean ") \ EM(rxrpc_client_discard, "Discar") \ - EM(rxrpc_client_duplicate, "Duplic") \ EM(rxrpc_client_exposed, "Expose") \ EM(rxrpc_client_replace, "Replac") \ + EM(rxrpc_client_queue_new_call, "Q-Call") \ EM(rxrpc_client_to_active, "->Actv") \ E_(rxrpc_client_to_idle, "->Idle") #define rxrpc_call_traces \ + EM(rxrpc_call_get_io_thread, "GET iothread") \ EM(rxrpc_call_get_input, "GET input ") \ EM(rxrpc_call_get_kernel_service, "GET krnl-srv") \ EM(rxrpc_call_get_notify_socket, "GET notify ") \ @@ -160,6 +261,7 @@ EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ EM(rxrpc_call_put_discard_error, "PUT disc-err") \ + EM(rxrpc_call_put_io_thread, "PUT iothread") \ EM(rxrpc_call_put_input, "PUT input ") \ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ @@ -169,10 +271,12 @@ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ + EM(rxrpc_call_put_userid, "PUT user-id ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ EM(rxrpc_call_see_connected, "SEE connect ") \ + EM(rxrpc_call_see_disconnected, "SEE disconn ") \ EM(rxrpc_call_see_distribute_error, "SEE dist-err") \ EM(rxrpc_call_see_input, "SEE input ") \ EM(rxrpc_call_see_release, "SEE release ") \ @@ -376,6 +480,7 @@ #define EM(a, b) a, #define E_(a, b) a +enum rxrpc_abort_reason { rxrpc_abort_reasons } __mode(byte); enum rxrpc_bundle_trace { rxrpc_bundle_traces } __mode(byte); enum rxrpc_call_poke_trace { rxrpc_call_poke_traces } __mode(byte); enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte); @@ -404,9 +509,13 @@ enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); */ #undef EM #undef E_ + +#ifndef RXRPC_TRACE_ONLY_DEFINE_ENUMS + #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a); +rxrpc_abort_reasons; rxrpc_bundle_traces; rxrpc_call_poke_traces; rxrpc_call_traces; @@ -657,14 +766,14 @@ TRACE_EVENT(rxrpc_rx_done, ); TRACE_EVENT(rxrpc_abort, - TP_PROTO(unsigned int call_nr, const char *why, u32 cid, u32 call_id, - rxrpc_seq_t seq, int abort_code, int error), + TP_PROTO(unsigned int call_nr, enum rxrpc_abort_reason why, + u32 cid, u32 call_id, rxrpc_seq_t seq, int abort_code, int error), TP_ARGS(call_nr, why, cid, call_id, seq, abort_code, error), TP_STRUCT__entry( __field(unsigned int, call_nr ) - __array(char, why, 4 ) + __field(enum rxrpc_abort_reason, why ) __field(u32, cid ) __field(u32, call_id ) __field(rxrpc_seq_t, seq ) @@ -673,8 +782,8 @@ TRACE_EVENT(rxrpc_abort, ), TP_fast_assign( - memcpy(__entry->why, why, 4); __entry->call_nr = call_nr; + __entry->why = why; __entry->cid = cid; __entry->call_id = call_id; __entry->abort_code = abort_code; @@ -685,7 +794,8 @@ TRACE_EVENT(rxrpc_abort, TP_printk("c=%08x %08x:%08x s=%u a=%d e=%d %s", __entry->call_nr, __entry->cid, __entry->call_id, __entry->seq, - __entry->abort_code, __entry->error, __entry->why) + __entry->abort_code, __entry->error, + __print_symbolic(__entry->why, rxrpc_abort_reasons)) ); TRACE_EVENT(rxrpc_call_complete, @@ -1521,30 +1631,6 @@ TRACE_EVENT(rxrpc_improper_term, __entry->abort_code) ); -TRACE_EVENT(rxrpc_rx_eproto, - TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial, - const char *why), - - TP_ARGS(call, serial, why), - - TP_STRUCT__entry( - __field(unsigned int, call ) - __field(rxrpc_serial_t, serial ) - __field(const char *, why ) - ), - - TP_fast_assign( - __entry->call = call ? call->debug_id : 0; - __entry->serial = serial; - __entry->why = why; - ), - - TP_printk("c=%08x EPROTO %08x %s", - __entry->call, - __entry->serial, - __entry->why) - ); - TRACE_EVENT(rxrpc_connect_call, TP_PROTO(struct rxrpc_call *call), @@ -1842,6 +1928,8 @@ TRACE_EVENT(rxrpc_call_poked, #undef EM #undef E_ + +#endif /* RXRPC_TRACE_ONLY_DEFINE_ENUMS */ #endif /* _TRACE_RXRPC_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index d2f30463c133..d77aef872a0a 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1183,6 +1183,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 #define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 +#define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h index c742469afe21..2d6f80d75ae7 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h @@ -15,8 +15,7 @@ enum sctp_conntrack { SCTP_CONNTRACK_SHUTDOWN_RECD, SCTP_CONNTRACK_SHUTDOWN_ACK_SENT, SCTP_CONNTRACK_HEARTBEAT_SENT, - SCTP_CONNTRACK_HEARTBEAT_ACKED, - SCTP_CONNTRACK_DATA_SENT, + SCTP_CONNTRACK_HEARTBEAT_ACKED, /* no longer used */ SCTP_CONNTRACK_MAX }; diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h index 94e74034706d..aa805e6d4e28 100644 --- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h +++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h @@ -94,8 +94,7 @@ enum ctattr_timeout_sctp { CTA_TIMEOUT_SCTP_SHUTDOWN_RECD, CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_SENT, - CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, - CTA_TIMEOUT_SCTP_DATA_SENT, + CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, /* no longer used */ __CTA_TIMEOUT_SCTP_MAX }; #define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1) diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 3511095c2702..42a40ad3fb62 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -58,7 +58,7 @@ #define PSCI_1_1_FN_SYSTEM_RESET2 PSCI_0_2_FN(18) #define PSCI_1_1_FN_MEM_PROTECT PSCI_0_2_FN(19) -#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(19) +#define PSCI_1_1_FN_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN(20) #define PSCI_1_0_FN64_CPU_DEFAULT_SUSPEND PSCI_0_2_FN64(12) #define PSCI_1_0_FN64_NODE_HW_STATE PSCI_0_2_FN64(13) @@ -67,7 +67,7 @@ #define PSCI_1_0_FN64_STAT_COUNT PSCI_0_2_FN64(17) #define PSCI_1_1_FN64_SYSTEM_RESET2 PSCI_0_2_FN64(18) -#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(19) +#define PSCI_1_1_FN64_MEM_PROTECT_CHECK_RANGE PSCI_0_2_FN64(20) /* PSCI v0.2 power state encoding for CPU_SUSPEND function */ #define PSCI_0_2_POWER_STATE_ID_MASK 0xffff diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 5cf81dff60aa..727084cd79be 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -808,6 +808,7 @@ struct ufs_hba_monitor { * @urgent_bkops_lvl: keeps track of urgent bkops level for device * @is_urgent_bkops_lvl_checked: keeps track if the urgent bkops level for * device is known or not. + * @wb_mutex: used to serialize devfreq and sysfs write booster toggling * @clk_scaling_lock: used to serialize device commands and clock scaling * @desc_size: descriptor sizes reported by device * @scsi_block_reqs_cnt: reference counting for scsi block requests @@ -951,6 +952,7 @@ struct ufs_hba { enum bkops_status urgent_bkops_lvl; bool is_urgent_bkops_lvl_checked; + struct mutex wb_mutex; struct rw_semaphore clk_scaling_lock; unsigned char desc_size[QUERY_DESC_IDN_MAX]; atomic_t scsi_block_reqs_cnt; diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index eaa932b99d8a..ad4fb4eab753 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -117,7 +117,7 @@ struct xenbus_driver { const struct xenbus_device_id *id); void (*otherend_changed)(struct xenbus_device *dev, enum xenbus_state backend_state); - int (*remove)(struct xenbus_device *dev); + void (*remove)(struct xenbus_device *dev); int (*suspend)(struct xenbus_device *dev); int (*resume)(struct xenbus_device *dev); int (*uevent)(struct xenbus_device *, struct kobj_uevent_env *); diff --git a/init/Kconfig b/init/Kconfig index 7e5c3ddc341d..44e90b28a30f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -204,7 +204,7 @@ config LOCALVERSION_AUTO appended after any matching localversion* files, and after the value set in CONFIG_LOCALVERSION. - (The actual string used here is the first eight characters produced + (The actual string used here is the first 12 characters produced by running the command: $ git rev-parse --verify HEAD @@ -776,7 +776,7 @@ config PRINTK_SAFE_LOG_BUF_SHIFT depends on PRINTK help Select the size of an alternate printk per-CPU buffer where messages - printed from usafe contexts are temporary stored. One example would + printed from unsafe contexts are temporary stored. One example would be NMI messages, another one - printk recursion. The messages are copied to the main log buffer in a safe context to avoid a deadlock. The value defines the size as a power of 2. @@ -894,13 +894,17 @@ config CC_IMPLICIT_FALLTHROUGH default "-Wimplicit-fallthrough=5" if CC_IS_GCC && $(cc-option,-Wimplicit-fallthrough=5) default "-Wimplicit-fallthrough" if CC_IS_CLANG && $(cc-option,-Wunreachable-code-fallthrough) -# Currently, disable gcc-12 array-bounds globally. +# Currently, disable gcc-11,12 array-bounds globally. # We may want to target only particular configurations some day. +config GCC11_NO_ARRAY_BOUNDS + def_bool y + config GCC12_NO_ARRAY_BOUNDS def_bool y config CC_NO_ARRAY_BOUNDS bool + default y if CC_IS_GCC && GCC_VERSION >= 110000 && GCC_VERSION < 120000 && GCC11_NO_ARRAY_BOUNDS default y if CC_IS_GCC && GCC_VERSION >= 120000 && GCC_VERSION < 130000 && GCC12_NO_ARRAY_BOUNDS # diff --git a/init/Makefile b/init/Makefile index 8316c23bead2..26de459006c4 100644 --- a/init/Makefile +++ b/init/Makefile @@ -59,3 +59,4 @@ include/generated/utsversion.h: FORCE $(obj)/version-timestamp.o: include/generated/utsversion.h CFLAGS_version-timestamp.o := -include include/generated/utsversion.h +KASAN_SANITIZE_version-timestamp.o := n diff --git a/init/version-timestamp.c b/init/version-timestamp.c index 179e93bae539..043cbf80a766 100644 --- a/init/version-timestamp.c +++ b/init/version-timestamp.c @@ -2,7 +2,6 @@ #include <generated/compile.h> #include <generated/utsrelease.h> -#include <linux/version.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/uts.h> diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index 2e04850a657b..882bd56b01ed 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -170,12 +170,11 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, xa_for_each(&ctx->personalities, index, cred) io_uring_show_cred(m, index, cred); } - if (has_lock) - mutex_unlock(&ctx->uring_lock); seq_puts(m, "PollList:\n"); for (i = 0; i < (1U << ctx->cancel_table.hash_bits); i++) { struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i]; + struct io_hash_bucket *hbl = &ctx->cancel_table_locked.hbs[i]; struct io_kiocb *req; spin_lock(&hb->lock); @@ -183,8 +182,17 @@ static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, seq_printf(m, " op=%d, task_works=%d\n", req->opcode, task_work_pending(req->task)); spin_unlock(&hb->lock); + + if (!has_lock) + continue; + hlist_for_each_entry(req, &hbl->list, hash_node) + seq_printf(m, " op=%d, task_works=%d\n", req->opcode, + task_work_pending(req->task)); } + if (has_lock) + mutex_unlock(&ctx->uring_lock); + seq_puts(m, "CqOverflowList:\n"); spin_lock(&ctx->completion_lock); list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) { diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 992dcd9f8c4c..411bb2d1acd4 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -1230,7 +1230,12 @@ static void io_wq_cancel_tw_create(struct io_wq *wq) worker = container_of(cb, struct io_worker, create_work); io_worker_cancel_cb(worker); - kfree(worker); + /* + * Only the worker continuation helper has worker allocated and + * hence needs freeing. + */ + if (cb->func == create_worker_cont) + kfree(worker); } } diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 2ac1cd8d23ea..db623b3185c8 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1765,17 +1765,12 @@ queue: } spin_unlock(&ctx->completion_lock); - ret = io_req_prep_async(req); - if (ret) { -fail: - io_req_defer_failed(req, ret); - return; - } io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); if (!de) { ret = -ENOMEM; - goto fail; + io_req_defer_failed(req, ret); + return; } spin_lock(&ctx->completion_lock); @@ -2048,13 +2043,16 @@ static void io_queue_sqe_fallback(struct io_kiocb *req) req->flags &= ~REQ_F_HARDLINK; req->flags |= REQ_F_LINK; io_req_defer_failed(req, req->cqe.res); - } else if (unlikely(req->ctx->drain_active)) { - io_drain_req(req); } else { int ret = io_req_prep_async(req); - if (unlikely(ret)) + if (unlikely(ret)) { io_req_defer_failed(req, ret); + return; + } + + if (unlikely(req->ctx->drain_active)) + io_drain_req(req); else io_queue_iowq(req, NULL); } @@ -3674,7 +3672,7 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !(ctx->flags & IORING_SETUP_R_DISABLED)) - ctx->submitter_task = get_task_struct(current); + WRITE_ONCE(ctx->submitter_task, get_task_struct(current)); file = io_uring_get_file(ctx); if (IS_ERR(file)) { @@ -3868,7 +3866,7 @@ static int io_register_enable_rings(struct io_ring_ctx *ctx) return -EBADFD; if (ctx->flags & IORING_SETUP_SINGLE_ISSUER && !ctx->submitter_task) - ctx->submitter_task = get_task_struct(current); + WRITE_ONCE(ctx->submitter_task, get_task_struct(current)); if (ctx->restrictions.registered) ctx->restricted = 1; diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c index 2d3cd945a531..15602a136821 100644 --- a/io_uring/msg_ring.c +++ b/io_uring/msg_ring.c @@ -25,6 +25,28 @@ struct io_msg { u32 flags; }; +static void io_double_unlock_ctx(struct io_ring_ctx *octx) +{ + mutex_unlock(&octx->uring_lock); +} + +static int io_double_lock_ctx(struct io_ring_ctx *octx, + unsigned int issue_flags) +{ + /* + * To ensure proper ordering between the two ctxs, we can only + * attempt a trylock on the target. If that fails and we already have + * the source ctx lock, punt to io-wq. + */ + if (!(issue_flags & IO_URING_F_UNLOCKED)) { + if (!mutex_trylock(&octx->uring_lock)) + return -EAGAIN; + return 0; + } + mutex_lock(&octx->uring_lock); + return 0; +} + void io_msg_ring_cleanup(struct io_kiocb *req) { struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); @@ -36,6 +58,29 @@ void io_msg_ring_cleanup(struct io_kiocb *req) msg->src_file = NULL; } +static inline bool io_msg_need_remote(struct io_ring_ctx *target_ctx) +{ + if (!target_ctx->task_complete) + return false; + return current != target_ctx->submitter_task; +} + +static int io_msg_exec_remote(struct io_kiocb *req, task_work_func_t func) +{ + struct io_ring_ctx *ctx = req->file->private_data; + struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + struct task_struct *task = READ_ONCE(ctx->submitter_task); + + if (unlikely(!task)) + return -EOWNERDEAD; + + init_task_work(&msg->tw, func); + if (task_work_add(ctx->submitter_task, &msg->tw, TWA_SIGNAL)) + return -EOWNERDEAD; + + return IOU_ISSUE_SKIP_COMPLETE; +} + static void io_msg_tw_complete(struct callback_head *head) { struct io_msg *msg = container_of(head, struct io_msg, tw); @@ -43,61 +88,54 @@ static void io_msg_tw_complete(struct callback_head *head) struct io_ring_ctx *target_ctx = req->file->private_data; int ret = 0; - if (current->flags & PF_EXITING) + if (current->flags & PF_EXITING) { ret = -EOWNERDEAD; - else if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) - ret = -EOVERFLOW; + } else { + /* + * If the target ring is using IOPOLL mode, then we need to be + * holding the uring_lock for posting completions. Other ring + * types rely on the regular completion locking, which is + * handled while posting. + */ + if (target_ctx->flags & IORING_SETUP_IOPOLL) + mutex_lock(&target_ctx->uring_lock); + if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) + ret = -EOVERFLOW; + if (target_ctx->flags & IORING_SETUP_IOPOLL) + mutex_unlock(&target_ctx->uring_lock); + } if (ret < 0) req_set_fail(req); io_req_queue_tw_complete(req, ret); } -static int io_msg_ring_data(struct io_kiocb *req) +static int io_msg_ring_data(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *target_ctx = req->file->private_data; struct io_msg *msg = io_kiocb_to_cmd(req, struct io_msg); + int ret; if (msg->src_fd || msg->dst_fd || msg->flags) return -EINVAL; + if (target_ctx->flags & IORING_SETUP_R_DISABLED) + return -EBADFD; - if (target_ctx->task_complete && current != target_ctx->submitter_task) { - init_task_work(&msg->tw, io_msg_tw_complete); - if (task_work_add(target_ctx->submitter_task, &msg->tw, - TWA_SIGNAL_NO_IPI)) - return -EOWNERDEAD; - - atomic_or(IORING_SQ_TASKRUN, &target_ctx->rings->sq_flags); - return IOU_ISSUE_SKIP_COMPLETE; - } - - if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) - return 0; + if (io_msg_need_remote(target_ctx)) + return io_msg_exec_remote(req, io_msg_tw_complete); - return -EOVERFLOW; -} - -static void io_double_unlock_ctx(struct io_ring_ctx *octx, - unsigned int issue_flags) -{ - mutex_unlock(&octx->uring_lock); -} - -static int io_double_lock_ctx(struct io_ring_ctx *octx, - unsigned int issue_flags) -{ - /* - * To ensure proper ordering between the two ctxs, we can only - * attempt a trylock on the target. If that fails and we already have - * the source ctx lock, punt to io-wq. - */ - if (!(issue_flags & IO_URING_F_UNLOCKED)) { - if (!mutex_trylock(&octx->uring_lock)) + ret = -EOVERFLOW; + if (target_ctx->flags & IORING_SETUP_IOPOLL) { + if (unlikely(io_double_lock_ctx(target_ctx, issue_flags))) return -EAGAIN; - return 0; + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) + ret = 0; + io_double_unlock_ctx(target_ctx); + } else { + if (io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) + ret = 0; } - mutex_lock(&octx->uring_lock); - return 0; + return ret; } static struct file *io_msg_grab_file(struct io_kiocb *req, unsigned int issue_flags) @@ -148,7 +186,7 @@ static int io_msg_install_complete(struct io_kiocb *req, unsigned int issue_flag if (!io_post_aux_cqe(target_ctx, msg->user_data, msg->len, 0)) ret = -EOVERFLOW; out_unlock: - io_double_unlock_ctx(target_ctx, issue_flags); + io_double_unlock_ctx(target_ctx); return ret; } @@ -174,6 +212,8 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) if (target_ctx == ctx) return -EINVAL; + if (target_ctx->flags & IORING_SETUP_R_DISABLED) + return -EBADFD; if (!src_file) { src_file = io_msg_grab_file(req, issue_flags); if (!src_file) @@ -182,14 +222,8 @@ static int io_msg_send_fd(struct io_kiocb *req, unsigned int issue_flags) req->flags |= REQ_F_NEED_CLEANUP; } - if (target_ctx->task_complete && current != target_ctx->submitter_task) { - init_task_work(&msg->tw, io_msg_tw_fd_complete); - if (task_work_add(target_ctx->submitter_task, &msg->tw, - TWA_SIGNAL)) - return -EOWNERDEAD; - - return IOU_ISSUE_SKIP_COMPLETE; - } + if (io_msg_need_remote(target_ctx)) + return io_msg_exec_remote(req, io_msg_tw_fd_complete); return io_msg_install_complete(req, issue_flags); } @@ -224,7 +258,7 @@ int io_msg_ring(struct io_kiocb *req, unsigned int issue_flags) switch (msg->cmd) { case IORING_MSG_DATA: - ret = io_msg_ring_data(req); + ret = io_msg_ring_data(req, issue_flags); break; case IORING_MSG_SEND_FD: ret = io_msg_send_fd(req, issue_flags); diff --git a/io_uring/net.c b/io_uring/net.c index fbc34a7c2743..90326b279965 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -62,6 +62,7 @@ struct io_sr_msg { u16 flags; /* initialised and used only by !msg send variants */ u16 addr_len; + u16 buf_group; void __user *addr; /* used only for send zerocopy */ struct io_kiocb *notif; @@ -580,6 +581,15 @@ int io_recvmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) if (req->opcode == IORING_OP_RECV && sr->len) return -EINVAL; req->flags |= REQ_F_APOLL_MULTISHOT; + /* + * Store the buffer group for this multishot receive separately, + * as if we end up doing an io-wq based issue that selects a + * buffer, it has to be committed immediately and that will + * clear ->buf_list. This means we lose the link to the buffer + * list, and the eventual buffer put on completion then cannot + * restore it. + */ + sr->buf_group = req->buf_index; } #ifdef CONFIG_COMPAT @@ -596,6 +606,7 @@ static inline void io_recv_prep_retry(struct io_kiocb *req) sr->done_io = 0; sr->len = 0; /* get from the provided buffer */ + req->buf_index = sr->buf_group; } /* diff --git a/io_uring/poll.c b/io_uring/poll.c index ee7da6150ec4..2ac1366adbd7 100644 --- a/io_uring/poll.c +++ b/io_uring/poll.c @@ -223,21 +223,22 @@ enum { IOU_POLL_DONE = 0, IOU_POLL_NO_ACTION = 1, IOU_POLL_REMOVE_POLL_USE_RES = 2, + IOU_POLL_REISSUE = 3, }; /* * All poll tw should go through this. Checks for poll events, manages * references, does rewait, etc. * - * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action require, - * which is either spurious wakeup or multishot CQE is served. - * IOU_POLL_DONE when it's done with the request, then the mask is stored in req->cqe.res. - * IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot poll and that the result - * is stored in req->cqe. + * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action + * require, which is either spurious wakeup or multishot CQE is served. + * IOU_POLL_DONE when it's done with the request, then the mask is stored in + * req->cqe.res. IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot + * poll and that the result is stored in req->cqe. */ static int io_poll_check_events(struct io_kiocb *req, bool *locked) { - int v, ret; + int v; /* req->task == current here, checking PF_EXITING is safe */ if (unlikely(req->task->flags & PF_EXITING)) @@ -276,10 +277,19 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) if (!req->cqe.res) { struct poll_table_struct pt = { ._key = req->apoll_events }; req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events; + /* + * We got woken with a mask, but someone else got to + * it first. The above vfs_poll() doesn't add us back + * to the waitqueue, so if we get nothing back, we + * should be safe and attempt a reissue. + */ + if (unlikely(!req->cqe.res)) { + /* Multishot armed need not reissue */ + if (!(req->apoll_events & EPOLLONESHOT)) + continue; + return IOU_POLL_REISSUE; + } } - - if ((unlikely(!req->cqe.res))) - continue; if (req->apoll_events & EPOLLONESHOT) return IOU_POLL_DONE; @@ -294,7 +304,7 @@ static int io_poll_check_events(struct io_kiocb *req, bool *locked) return IOU_POLL_REMOVE_POLL_USE_RES; } } else { - ret = io_poll_issue(req, locked); + int ret = io_poll_issue(req, locked); if (ret == IOU_STOP_MULTISHOT) return IOU_POLL_REMOVE_POLL_USE_RES; if (ret < 0) @@ -330,6 +340,9 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) poll = io_kiocb_to_cmd(req, struct io_poll); req->cqe.res = mangle_poll(req->cqe.res & poll->events); + } else if (ret == IOU_POLL_REISSUE) { + io_req_task_submit(req, locked); + return; } else if (ret != IOU_POLL_REMOVE_POLL_USE_RES) { req->cqe.res = ret; req_set_fail(req); @@ -342,7 +355,7 @@ static void io_poll_task_func(struct io_kiocb *req, bool *locked) if (ret == IOU_POLL_REMOVE_POLL_USE_RES) io_req_task_complete(req, locked); - else if (ret == IOU_POLL_DONE) + else if (ret == IOU_POLL_DONE || ret == IOU_POLL_REISSUE) io_req_task_submit(req, locked); else io_req_defer_failed(req, ret); @@ -533,6 +546,14 @@ static bool io_poll_can_finish_inline(struct io_kiocb *req, return pt->owning || io_poll_get_ownership(req); } +static void io_poll_add_hash(struct io_kiocb *req) +{ + if (req->flags & REQ_F_HASH_LOCKED) + io_poll_req_insert_locked(req); + else + io_poll_req_insert(req); +} + /* * Returns 0 when it's handed over for polling. The caller owns the requests if * it returns non-zero, but otherwise should not touch it. Negative values @@ -591,18 +612,17 @@ static int __io_arm_poll_handler(struct io_kiocb *req, if (mask && ((poll->events & (EPOLLET|EPOLLONESHOT)) == (EPOLLET|EPOLLONESHOT))) { - if (!io_poll_can_finish_inline(req, ipt)) + if (!io_poll_can_finish_inline(req, ipt)) { + io_poll_add_hash(req); return 0; + } io_poll_remove_entries(req); ipt->result_mask = mask; /* no one else has access to the req, forget about the ref */ return 1; } - if (req->flags & REQ_F_HASH_LOCKED) - io_poll_req_insert_locked(req); - else - io_poll_req_insert(req); + io_poll_add_hash(req); if (mask && (poll->events & EPOLLET) && io_poll_can_finish_inline(req, ipt)) { diff --git a/io_uring/rw.c b/io_uring/rw.c index 8227af2e1c0f..9c3ddd46a1ad 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -1062,7 +1062,11 @@ int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) continue; req->cqe.flags = io_put_kbuf(req, 0); - io_fill_cqe_req(req->ctx, req); + if (unlikely(!__io_fill_cqe_req(ctx, req))) { + spin_lock(&ctx->completion_lock); + io_req_cqe_overflow(req); + spin_unlock(&ctx->completion_lock); + } } if (unlikely(!nr_events)) diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index a4a41ee3e80b..e14c822f8911 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -51,7 +51,6 @@ BTF_SET_END(bpf_lsm_current_hooks) */ BTF_SET_START(bpf_lsm_locked_sockopt_hooks) #ifdef CONFIG_SECURITY_NETWORK -BTF_ID(func, bpf_lsm_socket_sock_rcv_skb) BTF_ID(func, bpf_lsm_sock_graft) BTF_ID(func, bpf_lsm_inet_csk_clone) BTF_ID(func, bpf_lsm_inet_conn_established) diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index f7dd8af06413..b7017cae6fd1 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -7782,9 +7782,9 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c sort(tab->dtors, tab->cnt, sizeof(tab->dtors[0]), btf_id_cmp_func, NULL); - return 0; end: - btf_free_dtor_kfunc_tab(btf); + if (ret) + btf_free_dtor_kfunc_tab(btf); btf_put(btf); return ret; } diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 5aa2b5525f79..66bded144377 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -152,7 +152,7 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab, { unsigned long flags; - hash = hash & HASHTAB_MAP_LOCK_MASK; + hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); preempt_disable(); if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) { @@ -171,7 +171,7 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab, struct bucket *b, u32 hash, unsigned long flags) { - hash = hash & HASHTAB_MAP_LOCK_MASK; + hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); raw_spin_unlock_irqrestore(&b->raw_lock, flags); __this_cpu_dec(*(htab->map_locked[hash])); preempt_enable(); diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index ebcc3dd0fa19..1db156405b68 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -71,7 +71,7 @@ static int bpf_mem_cache_idx(size_t size) if (size <= 192) return size_index[(size - 1) / 8] - 1; - return fls(size - 1) - 1; + return fls(size - 1) - 2; } #define NUM_CACHES 11 diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 13e4efc971e6..190d9f9dc987 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -216,9 +216,6 @@ static void __bpf_prog_offload_destroy(struct bpf_prog *prog) if (offload->dev_state) offload->offdev->ops->destroy(prog); - /* Make sure BPF_PROG_GET_NEXT_ID can't find this dead program */ - bpf_prog_free_id(prog, true); - list_del_init(&offload->offloads); kfree(offload); prog->aux->offload = NULL; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 64131f88c553..ecca9366c7a6 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1972,7 +1972,7 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) return; if (audit_enabled == AUDIT_OFF) return; - if (op == BPF_AUDIT_LOAD) + if (!in_irq() && !irqs_disabled()) ctx = audit_context(); ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_BPF); if (unlikely(!ab)) @@ -2001,7 +2001,7 @@ static int bpf_prog_alloc_id(struct bpf_prog *prog) return id > 0 ? 0 : id; } -void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) +void bpf_prog_free_id(struct bpf_prog *prog) { unsigned long flags; @@ -2013,18 +2013,10 @@ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) if (!prog->aux->id) return; - if (do_idr_lock) - spin_lock_irqsave(&prog_idr_lock, flags); - else - __acquire(&prog_idr_lock); - + spin_lock_irqsave(&prog_idr_lock, flags); idr_remove(&prog_idr, prog->aux->id); prog->aux->id = 0; - - if (do_idr_lock) - spin_unlock_irqrestore(&prog_idr_lock, flags); - else - __release(&prog_idr_lock); + spin_unlock_irqrestore(&prog_idr_lock, flags); } static void __bpf_prog_put_rcu(struct rcu_head *rcu) @@ -2067,17 +2059,15 @@ static void bpf_prog_put_deferred(struct work_struct *work) prog = aux->prog; perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0); bpf_audit_prog(prog, BPF_AUDIT_UNLOAD); + bpf_prog_free_id(prog); __bpf_prog_put_noref(prog, true); } -static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) +static void __bpf_prog_put(struct bpf_prog *prog) { struct bpf_prog_aux *aux = prog->aux; if (atomic64_dec_and_test(&aux->refcnt)) { - /* bpf_prog_free_id() must be called first */ - bpf_prog_free_id(prog, do_idr_lock); - if (in_irq() || irqs_disabled()) { INIT_WORK(&aux->work, bpf_prog_put_deferred); schedule_work(&aux->work); @@ -2089,7 +2079,7 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) void bpf_prog_put(struct bpf_prog *prog) { - __bpf_prog_put(prog, true); + __bpf_prog_put(prog); } EXPORT_SYMBOL_GPL(bpf_prog_put); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 85f96c1e9f62..7ee218827259 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2748,6 +2748,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, */ if (insn->src_reg == 0 && is_callback_calling_function(insn->imm)) return -ENOTSUPP; + /* kfunc with imm==0 is invalid and fixup_kfunc_call will + * catch this error later. Make backtracking conservative + * with ENOTSUPP. + */ + if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0) + return -ENOTSUPP; /* regular helper call sets R0 */ *reg_mask &= ~1; if (*reg_mask & 0x3f) { @@ -3237,13 +3243,24 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } +/* Copy src state preserving dst->parent and dst->live fields */ +static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) +{ + struct bpf_reg_state *parent = dst->parent; + enum bpf_reg_liveness live = dst->live; + + *dst = *src; + dst->parent = parent; + dst->live = live; +} + static void save_register_state(struct bpf_func_state *state, int spi, struct bpf_reg_state *reg, int size) { int i; - state->stack[spi].spilled_ptr = *reg; + copy_register_state(&state->stack[spi].spilled_ptr, reg); if (size == BPF_REG_SIZE) state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN; @@ -3289,7 +3306,9 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, bool sanitize = reg && is_spillable_regtype(reg->type); for (i = 0; i < size; i++) { - if (state->stack[spi].slot_type[i] == STACK_INVALID) { + u8 type = state->stack[spi].slot_type[i]; + + if (type != STACK_MISC && type != STACK_ZERO) { sanitize = true; break; } @@ -3569,7 +3588,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, */ s32 subreg_def = state->regs[dst_regno].subreg_def; - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; } else { for (i = 0; i < size; i++) { @@ -3590,7 +3609,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno >= 0) { /* restore register state from stack */ - state->regs[dst_regno] = *reg; + copy_register_state(&state->regs[dst_regno], reg); /* mark reg as written since spilled pointer state likely * has its liveness marks cleared by is_state_visited() * which resets stack/reg liveness for state transitions @@ -9584,7 +9603,7 @@ do_sim: */ if (!ptr_is_dst_reg) { tmp = *dst_reg; - *dst_reg = *ptr_reg; + copy_register_state(dst_reg, ptr_reg); } ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx); @@ -10837,7 +10856,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) * to propagate min/max range. */ src_reg->id = ++env->id_gen; - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; } else { @@ -10848,7 +10867,7 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) insn->src_reg); return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { - *dst_reg = *src_reg; + copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared otherwise * dst_reg min/max could be incorrectly * propagated into src_reg by find_equal_scalars() @@ -11647,7 +11666,7 @@ static void find_equal_scalars(struct bpf_verifier_state *vstate, bpf_for_each_reg_in_vstate(vstate, state, reg, ({ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id) - *reg = *known_reg; + copy_register_state(reg, known_reg); })); } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a29c0b13706b..205dc9edcaa9 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1346,7 +1346,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd, * A parent can be left with no CPU as long as there is no * task directly associated with the parent partition. */ - if (!cpumask_intersects(cs->cpus_allowed, parent->effective_cpus) && + if (cpumask_subset(parent->effective_cpus, cs->cpus_allowed) && partition_is_populated(parent, cs)) return PERR_NOCPUS; @@ -2324,6 +2324,7 @@ out: new_prs = -new_prs; spin_lock_irq(&callback_lock); cs->partition_root_state = new_prs; + WRITE_ONCE(cs->prs_err, err); spin_unlock_irq(&callback_lock); /* * Update child cpusets, if present. diff --git a/kernel/events/core.c b/kernel/events/core.c index d56328e5080e..c4be13e50547 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4813,19 +4813,17 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx, cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu); epc = &cpc->epc; - + raw_spin_lock_irq(&ctx->lock); if (!epc->ctx) { atomic_set(&epc->refcount, 1); epc->embedded = 1; - raw_spin_lock_irq(&ctx->lock); list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list); epc->ctx = ctx; - raw_spin_unlock_irq(&ctx->lock); } else { WARN_ON_ONCE(epc->ctx != ctx); atomic_inc(&epc->refcount); } - + raw_spin_unlock_irq(&ctx->lock); return epc; } @@ -4896,33 +4894,30 @@ static void free_epc_rcu(struct rcu_head *head) static void put_pmu_ctx(struct perf_event_pmu_context *epc) { + struct perf_event_context *ctx = epc->ctx; unsigned long flags; - if (!atomic_dec_and_test(&epc->refcount)) + /* + * XXX + * + * lockdep_assert_held(&ctx->mutex); + * + * can't because of the call-site in _free_event()/put_event() + * which isn't always called under ctx->mutex. + */ + if (!atomic_dec_and_raw_lock_irqsave(&epc->refcount, &ctx->lock, flags)) return; - if (epc->ctx) { - struct perf_event_context *ctx = epc->ctx; + WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry)); - /* - * XXX - * - * lockdep_assert_held(&ctx->mutex); - * - * can't because of the call-site in _free_event()/put_event() - * which isn't always called under ctx->mutex. - */ - - WARN_ON_ONCE(list_empty(&epc->pmu_ctx_entry)); - raw_spin_lock_irqsave(&ctx->lock, flags); - list_del_init(&epc->pmu_ctx_entry); - epc->ctx = NULL; - raw_spin_unlock_irqrestore(&ctx->lock, flags); - } + list_del_init(&epc->pmu_ctx_entry); + epc->ctx = NULL; WARN_ON_ONCE(!list_empty(&epc->pinned_active)); WARN_ON_ONCE(!list_empty(&epc->flexible_active)); + raw_spin_unlock_irqrestore(&ctx->lock, flags); + if (epc->embedded) return; diff --git a/kernel/gen_kheaders.sh b/kernel/gen_kheaders.sh index 473036b43c83..81b97f0f6556 100755 --- a/kernel/gen_kheaders.sh +++ b/kernel/gen_kheaders.sh @@ -14,6 +14,8 @@ include/ arch/$SRCARCH/include/ " +type cpio > /dev/null + # Support incremental builds by skipping archive generation # if timestamps of files being archived are not changed. diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 8fe1da9614ee..798a9042421f 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -114,7 +114,7 @@ void irq_domain_free_fwnode(struct fwnode_handle *fwnode) { struct irqchip_fwid *fwid; - if (WARN_ON(!is_fwnode_irqchip(fwnode))) + if (!fwnode || WARN_ON(!is_fwnode_irqchip(fwnode))) return; fwid = container_of(fwnode, struct irqchip_fwid, fwnode); @@ -1915,7 +1915,7 @@ static void debugfs_add_domain_dir(struct irq_domain *d) static void debugfs_remove_domain_dir(struct irq_domain *d) { - debugfs_remove(debugfs_lookup(d->name, domain_dir)); + debugfs_lookup_and_remove(d->name, domain_dir); } void __init irq_domain_debugfs_init(struct dentry *root) diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 955267bbc2be..783a3e6a0b10 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -1000,7 +1000,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid, fail: msi_unlock_descs(dev); free_fwnode: - kfree(fwnode); + irq_domain_free_fwnode(fwnode); free_bundle: kfree(bundle); return false; @@ -1013,6 +1013,7 @@ free_bundle: */ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid) { + struct fwnode_handle *fwnode = NULL; struct msi_domain_info *info; struct irq_domain *domain; @@ -1025,7 +1026,10 @@ void msi_remove_device_irq_domain(struct device *dev, unsigned int domid) dev->msi.data->__domains[domid].domain = NULL; info = domain->host_data; + if (irq_domain_is_msi_device(domain)) + fwnode = domain->fwnode; irq_domain_remove(domain); + irq_domain_free_fwnode(fwnode); kfree(container_of(info, struct msi_domain_template, info)); unlock: diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index f35d9cc1aab1..bfbc12da3326 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -157,14 +157,11 @@ static void test_kallsyms_compression_ratio(void) static int lookup_name(void *data, const char *name, struct module *mod, unsigned long addr) { u64 t0, t1, t; - unsigned long flags; struct test_stat *stat = (struct test_stat *)data; - local_irq_save(flags); - t0 = sched_clock(); + t0 = ktime_get_ns(); (void)kallsyms_lookup_name(name); - t1 = sched_clock(); - local_irq_restore(flags); + t1 = ktime_get_ns(); t = t1 - t0; if (t < stat->min) @@ -234,18 +231,15 @@ static int find_symbol(void *data, const char *name, struct module *mod, unsigne static void test_perf_kallsyms_on_each_symbol(void) { u64 t0, t1; - unsigned long flags; struct test_stat stat; memset(&stat, 0, sizeof(stat)); stat.max = INT_MAX; stat.name = stub_name; stat.perf = 1; - local_irq_save(flags); - t0 = sched_clock(); + t0 = ktime_get_ns(); kallsyms_on_each_symbol(find_symbol, &stat); - t1 = sched_clock(); - local_irq_restore(flags); + t1 = ktime_get_ns(); pr_info("kallsyms_on_each_symbol() traverse all: %lld ns\n", t1 - t0); } @@ -270,17 +264,14 @@ static int match_symbol(void *data, unsigned long addr) static void test_perf_kallsyms_on_each_match_symbol(void) { u64 t0, t1; - unsigned long flags; struct test_stat stat; memset(&stat, 0, sizeof(stat)); stat.max = INT_MAX; stat.name = stub_name; - local_irq_save(flags); - t0 = sched_clock(); + t0 = ktime_get_ns(); kallsyms_on_each_match_symbol(match_symbol, stat.name, &stat); - t1 = sched_clock(); - local_irq_restore(flags); + t1 = ktime_get_ns(); pr_info("kallsyms_on_each_match_symbol() traverse all: %lld ns\n", t1 - t0); } diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c index dcec1b743c69..a60c561724be 100644 --- a/kernel/kcsan/kcsan_test.c +++ b/kernel/kcsan/kcsan_test.c @@ -159,7 +159,7 @@ static bool __report_matches(const struct expect_report *r) const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT; bool ret = false; unsigned long flags; - typeof(observed.lines) expect; + typeof(*observed.lines) *expect; const char *end; char *cur; int i; @@ -168,6 +168,10 @@ static bool __report_matches(const struct expect_report *r) if (!report_available()) return false; + expect = kmalloc(sizeof(observed.lines), GFP_KERNEL); + if (WARN_ON(!expect)) + return false; + /* Generate expected report contents. */ /* Title */ @@ -253,6 +257,7 @@ static bool __report_matches(const struct expect_report *r) strstr(observed.lines[2], expect[1]))); out: spin_unlock_irqrestore(&observed.lock, flags); + kfree(expect); return ret; } diff --git a/kernel/module/main.c b/kernel/module/main.c index 48568a0f5651..4ac3fe43e6c8 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2393,7 +2393,8 @@ static bool finished_loading(const char *name) sched_annotate_sleep(); mutex_lock(&module_mutex); mod = find_module_all(name, strlen(name), true); - ret = !mod || mod->state == MODULE_STATE_LIVE; + ret = !mod || mod->state == MODULE_STATE_LIVE + || mod->state == MODULE_STATE_GOING; mutex_unlock(&module_mutex); return ret; @@ -2569,20 +2570,35 @@ static int add_unformed_module(struct module *mod) mod->state = MODULE_STATE_UNFORMED; -again: mutex_lock(&module_mutex); old = find_module_all(mod->name, strlen(mod->name), true); if (old != NULL) { - if (old->state != MODULE_STATE_LIVE) { + if (old->state == MODULE_STATE_COMING + || old->state == MODULE_STATE_UNFORMED) { /* Wait in case it fails to load. */ mutex_unlock(&module_mutex); err = wait_event_interruptible(module_wq, finished_loading(mod->name)); if (err) goto out_unlocked; - goto again; + + /* The module might have gone in the meantime. */ + mutex_lock(&module_mutex); + old = find_module_all(mod->name, strlen(mod->name), + true); } - err = -EEXIST; + + /* + * We are here only when the same module was being loaded. Do + * not try to load it again right now. It prevents long delays + * caused by serialized module load failures. It might happen + * when more devices of the same type trigger load of + * a particular module. + */ + if (old && old->state == MODULE_STATE_LIVE) + err = -EEXIST; + else + err = -EBUSY; goto out; } mod_update_bounds(mod); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 7decf1e9c486..a5ed2e53547c 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -123,6 +123,7 @@ bool console_srcu_read_lock_is_held(void) { return srcu_read_lock_held(&console_srcu); } +EXPORT_SYMBOL(console_srcu_read_lock_is_held); #endif enum devkmsg_log_bits { @@ -1891,6 +1892,7 @@ static void console_lock_spinning_enable(void) /** * console_lock_spinning_disable_and_check - mark end of code where another * thread was able to busy wait and check if there is a waiter + * @cookie: cookie returned from console_srcu_read_lock() * * This is called at the end of the section where spinning is allowed. * It has two functions. First, it is a signal that it is no longer diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 25b582b6ee5f..e838feb6adc5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2604,27 +2604,71 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) .user_mask = NULL, .flags = SCA_USER, /* clear the user requested mask */ }; + union cpumask_rcuhead { + cpumask_t cpumask; + struct rcu_head rcu; + }; __do_set_cpus_allowed(p, &ac); - kfree(ac.user_mask); + + /* + * Because this is called with p->pi_lock held, it is not possible + * to use kfree() here (when PREEMPT_RT=y), therefore punt to using + * kfree_rcu(). + */ + kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu); +} + +static cpumask_t *alloc_user_cpus_ptr(int node) +{ + /* + * See do_set_cpus_allowed() above for the rcu_head usage. + */ + int size = max_t(int, cpumask_size(), sizeof(struct rcu_head)); + + return kmalloc_node(size, GFP_KERNEL, node); } int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { + cpumask_t *user_mask; unsigned long flags; - if (!src->user_cpus_ptr) + /* + * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's + * may differ by now due to racing. + */ + dst->user_cpus_ptr = NULL; + + /* + * This check is racy and losing the race is a valid situation. + * It is not worth the extra overhead of taking the pi_lock on + * every fork/clone. + */ + if (data_race(!src->user_cpus_ptr)) return 0; - dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node); - if (!dst->user_cpus_ptr) + user_mask = alloc_user_cpus_ptr(node); + if (!user_mask) return -ENOMEM; - /* Use pi_lock to protect content of user_cpus_ptr */ + /* + * Use pi_lock to protect content of user_cpus_ptr + * + * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent + * do_set_cpus_allowed(). + */ raw_spin_lock_irqsave(&src->pi_lock, flags); - cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr); + if (src->user_cpus_ptr) { + swap(dst->user_cpus_ptr, user_mask); + cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr); + } raw_spin_unlock_irqrestore(&src->pi_lock, flags); + + if (unlikely(user_mask)) + kfree(user_mask); + return 0; } @@ -3581,6 +3625,11 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) return false; } +static inline cpumask_t *alloc_user_cpus_ptr(int node) +{ + return NULL; +} + #endif /* !CONFIG_SMP */ static void @@ -5504,7 +5553,9 @@ void scheduler_tick(void) unsigned long thermal_pressure; u64 resched_latency; - arch_scale_freq_tick(); + if (housekeeping_cpu(cpu, HK_TYPE_TICK)) + arch_scale_freq_tick(); + sched_clock_tick(); rq_lock(rq, &rf); @@ -8239,12 +8290,18 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) if (retval) goto out_put_task; - user_mask = kmalloc(cpumask_size(), GFP_KERNEL); - if (!user_mask) { + /* + * With non-SMP configs, user_cpus_ptr/user_mask isn't used and + * alloc_user_cpus_ptr() returns NULL. + */ + user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE); + if (user_mask) { + cpumask_copy(user_mask, in_mask); + } else if (IS_ENABLED(CONFIG_SMP)) { retval = -ENOMEM; goto out_put_task; } - cpumask_copy(user_mask, in_mask); + ac = (struct affinity_context){ .new_mask = in_mask, .user_mask = user_mask, diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c36aa54ae071..0f8736991427 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7229,10 +7229,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) eenv_task_busy_time(&eenv, p, prev_cpu); for (; pd; pd = pd->next) { + unsigned long util_min = p_util_min, util_max = p_util_max; unsigned long cpu_cap, cpu_thermal_cap, util; unsigned long cur_delta, max_spare_cap = 0; unsigned long rq_util_min, rq_util_max; - unsigned long util_min, util_max; unsigned long prev_spare_cap = 0; int max_spare_cap_cpu = -1; unsigned long base_energy; @@ -7251,6 +7251,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) eenv.pd_cap = 0; for_each_cpu(cpu, cpus) { + struct rq *rq = cpu_rq(cpu); + eenv.pd_cap += cpu_thermal_cap; if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) @@ -7269,24 +7271,19 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) * much capacity we can get out of the CPU; this is * aligned with sched_cpu_util(). */ - if (uclamp_is_used()) { - if (uclamp_rq_is_idle(cpu_rq(cpu))) { - util_min = p_util_min; - util_max = p_util_max; - } else { - /* - * Open code uclamp_rq_util_with() except for - * the clamp() part. Ie: apply max aggregation - * only. util_fits_cpu() logic requires to - * operate on non clamped util but must use the - * max-aggregated uclamp_{min, max}. - */ - rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); - rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); - - util_min = max(rq_util_min, p_util_min); - util_max = max(rq_util_max, p_util_max); - } + if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) { + /* + * Open code uclamp_rq_util_with() except for + * the clamp() part. Ie: apply max aggregation + * only. util_fits_cpu() logic requires to + * operate on non clamped util but must use the + * max-aggregated uclamp_{min, max}. + */ + rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN); + rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX); + + util_min = max(rq_util_min, p_util_min); + util_max = max(rq_util_max, p_util_max); } if (!util_fits_cpu(util, util_min, util_max, cpu)) continue; @@ -8871,16 +8868,23 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) * * Thermal pressure will impact all cpus in this perf domain * equally. */ - if (static_branch_unlikely(&sched_asym_cpucapacity)) { + if (sched_energy_enabled()) { unsigned long inv_cap = capacity_orig - thermal_load_avg(rq); - struct perf_domain *pd = rcu_dereference(rq->rd->pd); + struct perf_domain *pd; + rcu_read_lock(); + + pd = rcu_dereference(rq->rd->pd); rq->cpu_capacity_inverted = 0; for (; pd; pd = pd->next) { struct cpumask *pd_span = perf_domain_span(pd); unsigned long pd_cap_orig, pd_cap; + /* We can't be inverted against our own pd */ + if (cpumask_test_cpu(cpu_of(rq), pd_span)) + continue; + cpu = cpumask_any(pd_span); pd_cap_orig = arch_scale_cpu_capacity(cpu); @@ -8905,6 +8909,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) break; } } + + rcu_read_unlock(); } trace_sched_cpu_capacity_tp(rq); diff --git a/kernel/sys.c b/kernel/sys.c index 5fd54bf0e886..88b31f096fb2 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1442,6 +1442,8 @@ static int do_prlimit(struct task_struct *tsk, unsigned int resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); + if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 475ecceda768..5e2c2c26b3cc 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -18,7 +18,7 @@ #include "tick-internal.h" /** - * tick_program_event + * tick_program_event - program the CPU local timer device for the next event */ int tick_program_event(ktime_t expires, int force) { @@ -99,7 +99,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) } /** - * tick_check_oneshot_mode - check whether the system is in oneshot mode + * tick_oneshot_mode_active - check whether the system is in oneshot mode * * returns 1 when either nohz or highres are enabled. otherwise 0. */ diff --git a/kernel/time/time.c b/kernel/time/time.c index 526257b3727c..f4198af60fee 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -462,7 +462,7 @@ struct __kernel_old_timeval ns_to_kernel_old_timeval(s64 nsec) EXPORT_SYMBOL(ns_to_kernel_old_timeval); /** - * set_normalized_timespec - set timespec sec and nsec parts and normalize + * set_normalized_timespec64 - set timespec sec and nsec parts and normalize * * @ts: pointer to timespec variable to be set * @sec: seconds to set @@ -526,7 +526,7 @@ struct timespec64 ns_to_timespec64(s64 nsec) EXPORT_SYMBOL(ns_to_timespec64); /** - * msecs_to_jiffies: - convert milliseconds to jiffies + * __msecs_to_jiffies: - convert milliseconds to jiffies * @m: time in milliseconds * * conversion is done as follows: @@ -541,12 +541,12 @@ EXPORT_SYMBOL(ns_to_timespec64); * handling any 32-bit overflows. * for the details see __msecs_to_jiffies() * - * msecs_to_jiffies() checks for the passed in value being a constant + * __msecs_to_jiffies() checks for the passed in value being a constant * via __builtin_constant_p() allowing gcc to eliminate most of the * code, __msecs_to_jiffies() is called if the value passed does not * allow constant folding and the actual conversion must be done at * runtime. - * the _msecs_to_jiffies helpers are the HZ dependent conversion + * The _msecs_to_jiffies helpers are the HZ dependent conversion * routines found in include/linux/jiffies.h */ unsigned long __msecs_to_jiffies(const unsigned int m) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index f72b9f1de178..5579ead449f2 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1590,10 +1590,10 @@ void __weak read_persistent_clock64(struct timespec64 *ts) /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. + * @wall_time: current time as returned by persistent clock + * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. - * @wall_time: - current time as returned by persistent clock - * @boot_offset: - offset that is defined as wall_time - boot_time * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't @@ -1701,7 +1701,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) -/** +/* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource @@ -1722,7 +1722,7 @@ bool timekeeping_rtc_skipresume(void) return !suspend_timing_needed; } -/** +/* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 197545241ab8..d7043043f59c 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -933,8 +933,8 @@ config RING_BUFFER_RECORD_RECURSION default y help The ring buffer has its own internal recursion. Although when - recursion happens it wont cause harm because of the protection, - but it does cause an unwanted overhead. Enabling this option will + recursion happens it won't cause harm because of the protection, + but it does cause unwanted overhead. Enabling this option will place where recursion was detected into the ftrace "recursed_functions" file. @@ -1017,8 +1017,8 @@ config RING_BUFFER_STARTUP_TEST The test runs for 10 seconds. This will slow your boot time by at least 10 more seconds. - At the end of the test, statics and more checks are done. - It will output the stats of each per cpu buffer. What + At the end of the test, statistics and more checks are done. + It will output the stats of each per cpu buffer: What was written, the sizes, what was read, what was lost, and other similar details. diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 3bbd3f0c810c..c09792c551bf 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -833,6 +833,7 @@ static void do_bpf_send_signal(struct irq_work *entry) work = container_of(entry, struct send_signal_irq_work, irq_work); group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, work->type); + put_task_struct(work->task); } static int bpf_send_signal_common(u32 sig, enum pid_type type) @@ -848,6 +849,9 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) return -EPERM; if (unlikely(!nmi_uaccess_okay())) return -EPERM; + /* Task should not be pid=1 to avoid kernel panic. */ + if (unlikely(is_global_init(current))) + return -EPERM; if (irqs_disabled()) { /* Do an early check on signal validity. Otherwise, @@ -864,7 +868,7 @@ static int bpf_send_signal_common(u32 sig, enum pid_type type) * to the irq_work. The current task may change when queued * irq works get executed. */ - work->task = current; + work->task = get_task_struct(current); work->sig = sig; work->type = type; irq_work_queue(&work->irq_work); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 442438b93fe9..750aa3f08b25 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1248,12 +1248,17 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash) call_rcu(&hash->rcu, __free_ftrace_hash_rcu); } +/** + * ftrace_free_filter - remove all filters for an ftrace_ops + * @ops - the ops to remove the filters from + */ void ftrace_free_filter(struct ftrace_ops *ops) { ftrace_ops_init(ops); free_ftrace_hash(ops->func_hash->filter_hash); free_ftrace_hash(ops->func_hash->notrace_hash); } +EXPORT_SYMBOL_GPL(ftrace_free_filter); static struct ftrace_hash *alloc_ftrace_hash(int size_bits) { @@ -5839,6 +5844,10 @@ EXPORT_SYMBOL_GPL(modify_ftrace_direct_multi); * * Filters denote which functions should be enabled when tracing is enabled * If @ip is NULL, it fails to update filter. + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). */ int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, int remove, int reset) @@ -5858,7 +5867,11 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); * * Filters denote which functions should be enabled when tracing is enabled * If @ips array or any ip specified within is NULL , it fails to update filter. - */ + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). +*/ int ftrace_set_filter_ips(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt, int remove, int reset) { @@ -5900,6 +5913,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, * * Filters denote which functions should be enabled when tracing is enabled. * If @buf is NULL and reset is set, all functions will be enabled for tracing. + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). */ int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) @@ -5919,6 +5936,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter); * Notrace Filters denote which functions should not be enabled when tracing * is enabled. If @buf is NULL and reset is set, all functions will be enabled * for tracing. + * + * This can allocate memory which must be freed before @ops can be freed, + * either by removing each filtered addr or by using + * ftrace_free_filter(@ops). */ int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf, int len, int reset) diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 6c97cc2d754a..7e9061828c24 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -516,7 +516,7 @@ static ssize_t enabled_monitors_write(struct file *filp, const char __user *user struct rv_monitor_def *mdef; int retval = -EINVAL; bool enable = true; - char *ptr = buff; + char *ptr; int len; if (count < 1 || count > MAX_RV_MONITOR_NAME_SIZE + 1) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a555a861b978..78ed5f1baa8c 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -10295,6 +10295,8 @@ void __init early_trace_init(void) static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); + + init_events(); } void __init trace_init(void) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index e46a49269be2..4eb6d6b97a9f 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1490,6 +1490,7 @@ extern void trace_event_enable_cmd_record(bool enable); extern void trace_event_enable_tgid_record(bool enable); extern int event_trace_init(void); +extern int init_events(void); extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr); extern int event_trace_del_tracer(struct trace_array *tr); extern void __trace_early_add_events(struct trace_array *tr); diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 96acc2b71ac7..e095c3b3a50d 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -128,7 +128,7 @@ static bool is_not(const char *str) } /** - * prog_entry - a singe entry in the filter program + * struct prog_entry - a singe entry in the filter program * @target: Index to jump to on a branch (actually one minus the index) * @when_to_branch: The value of the result of the predicate to do a branch * @pred: The predicate to execute. @@ -140,16 +140,16 @@ struct prog_entry { }; /** - * update_preds- assign a program entry a label target + * update_preds - assign a program entry a label target * @prog: The program array * @N: The index of the current entry in @prog - * @when_to_branch: What to assign a program entry for its branch condition + * @invert: What to assign a program entry for its branch condition * * The program entry at @N has a target that points to the index of a program * entry that can have its target and when_to_branch fields updated. * Update the current program entry denoted by index @N target field to be * that of the updated entry. This will denote the entry to update if - * we are processing an "||" after an "&&" + * we are processing an "||" after an "&&". */ static void update_preds(struct prog_entry *prog, int N, int invert) { diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index fcaf226b7744..5edbf6b1da3f 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -1988,6 +1988,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, hist_field->fn_num = flags & HIST_FIELD_FL_LOG2 ? HIST_FIELD_FN_LOG2 : HIST_FIELD_FN_BUCKET; hist_field->operands[0] = create_hist_field(hist_data, field, fl, NULL); + if (!hist_field->operands[0]) + goto free; hist_field->size = hist_field->operands[0]->size; hist_field->type = kstrdup_const(hist_field->operands[0]->type, GFP_KERNEL); if (!hist_field->type) diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index 94c1b5eb1dc0..210e1f168392 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -147,9 +147,8 @@ static void osnoise_unregister_instance(struct trace_array *tr) * register/unregister serialization is provided by trace's * trace_types_lock. */ - lockdep_assert_held(&trace_types_lock); - - list_for_each_entry_rcu(inst, &osnoise_instances, list) { + list_for_each_entry_rcu(inst, &osnoise_instances, list, + lockdep_is_held(&trace_types_lock)) { if (inst->tr == tr) { list_del_rcu(&inst->list); found = 1; diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 57a13b61f186..bd475a00f96d 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1535,7 +1535,7 @@ static struct trace_event *events[] __initdata = { NULL }; -__init static int init_events(void) +__init int init_events(void) { struct trace_event *event; int i, ret; @@ -1548,4 +1548,3 @@ __init static int init_events(void) return 0; } -early_initcall(init_events); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 881c3f84e88a..02ee440f7be3 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -754,6 +754,7 @@ config DEBUG_KMEMLEAK select KALLSYMS select CRC32 select STACKDEPOT + select STACKDEPOT_ALWAYS_INIT if !DEBUG_KMEMLEAK_DEFAULT_OFF help Say Y here if you want to enable the memory leak detector. The memory allocation/freeing is traced in a way @@ -1207,7 +1208,7 @@ config SCHED_DEBUG depends on DEBUG_KERNEL && PROC_FS default y help - If you say Y here, the /proc/sched_debug file will be provided + If you say Y here, the /sys/kernel/debug/sched file will be provided that can help debug the scheduler. The runtime overhead of this option is minimal. @@ -1917,7 +1918,7 @@ config FUNCTION_ERROR_INJECTION help Add fault injections into various functions that are annotated with ALLOW_ERROR_INJECTION() in the kernel. BPF may also modify the return - value of theses functions. This is useful to test error paths of code. + value of these functions. This is useful to test error paths of code. If unsure, say N @@ -2566,6 +2567,15 @@ config MEMCPY_KUNIT_TEST If unsure, say N. +config MEMCPY_SLOW_KUNIT_TEST + bool "Include exhaustive memcpy tests" + depends on MEMCPY_KUNIT_TEST + default y + help + Some memcpy tests are quite exhaustive in checking for overlaps + and bit ranges. These can be very slow, so they are split out + as a separate config, in case they need to be disabled. + config IS_SIGNED_TYPE_KUNIT_TEST tristate "Test is_signed_type() macro" if !KUNIT_ALL_TESTS depends on KUNIT diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan index 375575a5a0e3..4dedd61e5192 100644 --- a/lib/Kconfig.kcsan +++ b/lib/Kconfig.kcsan @@ -194,7 +194,7 @@ config KCSAN_WEAK_MEMORY Enable support for modeling a subset of weak memory, which allows detecting a subset of data races due to missing memory barriers. - Depends on KCSAN_STRICT, because the options strenghtening certain + Depends on KCSAN_STRICT, because the options strengthening certain plain accesses by default (depending on !KCSAN_STRICT) reduce the ability to detect any data races invoving reordered accesses, in particular reordered writes. diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c index 9555b68bb774..1dcca8f2e194 100644 --- a/lib/dec_and_lock.c +++ b/lib/dec_and_lock.c @@ -49,3 +49,34 @@ int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, return 0; } EXPORT_SYMBOL(_atomic_dec_and_lock_irqsave); + +int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + + /* Otherwise do it the slow way */ + raw_spin_lock(lock); + if (atomic_dec_and_test(atomic)) + return 1; + raw_spin_unlock(lock); + return 0; +} +EXPORT_SYMBOL(_atomic_dec_and_raw_lock); + +int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, + unsigned long *flags) +{ + /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */ + if (atomic_add_unless(atomic, -1, 1)) + return 0; + + /* Otherwise do it the slow way */ + raw_spin_lock_irqsave(lock, *flags); + if (atomic_dec_and_test(atomic)) + return 1; + raw_spin_unlock_irqrestore(lock, *flags); + return 0; +} +EXPORT_SYMBOL(_atomic_dec_and_raw_lock_irqsave); diff --git a/lib/kunit/assert.c b/lib/kunit/assert.c index f5b50babe38d..05a09652f5a1 100644 --- a/lib/kunit/assert.c +++ b/lib/kunit/assert.c @@ -241,24 +241,34 @@ void kunit_mem_assert_format(const struct kunit_assert *assert, mem_assert = container_of(assert, struct kunit_mem_assert, assert); - string_stream_add(stream, - KUNIT_SUBTEST_INDENT "Expected %s %s %s, but\n", - mem_assert->text->left_text, - mem_assert->text->operation, - mem_assert->text->right_text); + if (!mem_assert->left_value) { + string_stream_add(stream, + KUNIT_SUBTEST_INDENT "Expected %s is not null, but is\n", + mem_assert->text->left_text); + } else if (!mem_assert->right_value) { + string_stream_add(stream, + KUNIT_SUBTEST_INDENT "Expected %s is not null, but is\n", + mem_assert->text->right_text); + } else { + string_stream_add(stream, + KUNIT_SUBTEST_INDENT "Expected %s %s %s, but\n", + mem_assert->text->left_text, + mem_assert->text->operation, + mem_assert->text->right_text); - string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n", - mem_assert->text->left_text); - kunit_assert_hexdump(stream, mem_assert->left_value, - mem_assert->right_value, mem_assert->size); + string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n", + mem_assert->text->left_text); + kunit_assert_hexdump(stream, mem_assert->left_value, + mem_assert->right_value, mem_assert->size); - string_stream_add(stream, "\n"); + string_stream_add(stream, "\n"); - string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n", - mem_assert->text->right_text); - kunit_assert_hexdump(stream, mem_assert->right_value, - mem_assert->left_value, mem_assert->size); + string_stream_add(stream, KUNIT_SUBSUBTEST_INDENT "%s ==\n", + mem_assert->text->right_text); + kunit_assert_hexdump(stream, mem_assert->right_value, + mem_assert->left_value, mem_assert->size); - kunit_assert_print_msg(message, stream); + kunit_assert_print_msg(message, stream); + } } EXPORT_SYMBOL_GPL(kunit_mem_assert_format); diff --git a/lib/kunit/test.c b/lib/kunit/test.c index c9ebf975e56b..890ba5b3a981 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -21,6 +21,7 @@ #include "try-catch-impl.h" DEFINE_STATIC_KEY_FALSE(kunit_running); +EXPORT_SYMBOL_GPL(kunit_running); #if IS_BUILTIN(CONFIG_KUNIT) /* diff --git a/lib/lockref.c b/lib/lockref.c index 45e93ece8ba0..2afe4c5d8919 100644 --- a/lib/lockref.c +++ b/lib/lockref.c @@ -23,7 +23,6 @@ } \ if (!--retry) \ break; \ - cpu_relax(); \ } \ } while (0) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 26e2045d3cda..5a976393c9ae 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -670,12 +670,13 @@ static inline unsigned long mte_pivot(const struct maple_enode *mn, unsigned char piv) { struct maple_node *node = mte_to_node(mn); + enum maple_type type = mte_node_type(mn); - if (piv >= mt_pivots[piv]) { + if (piv >= mt_pivots[type]) { WARN_ON(1); return 0; } - switch (mte_node_type(mn)) { + switch (type) { case maple_arange_64: return node->ma64.pivot[piv]; case maple_range_64: @@ -4887,7 +4888,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; - unsigned long max, min, index; + unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) @@ -4909,8 +4910,7 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); - index = mas->index; - while (index <= max) { + while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; @@ -4941,10 +4941,8 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) min = mas_safe_min(mas, pivots, offset); } - if (unlikely(index > max)) { - mas_set_err(mas, -EBUSY); - return false; - } + if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) + goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; @@ -4961,9 +4959,11 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size) return false; ascend: - if (mte_is_root(mas->node)) - mas_set_err(mas, -EBUSY); + if (!mte_is_root(mas->node)) + return false; +no_space: + mas_set_err(mas, -EBUSY); return false; } diff --git a/lib/memcpy_kunit.c b/lib/memcpy_kunit.c index 89128551448d..887926f04731 100644 --- a/lib/memcpy_kunit.c +++ b/lib/memcpy_kunit.c @@ -309,6 +309,8 @@ static void set_random_nonzero(struct kunit *test, u8 *byte) static void init_large(struct kunit *test) { + if (!IS_ENABLED(CONFIG_MEMCPY_SLOW_KUNIT_TEST)) + kunit_skip(test, "Slow test skipped. Enable with CONFIG_MEMCPY_SLOW_KUNIT_TEST=y"); /* Get many bit patterns. */ get_random_bytes(large_src, ARRAY_SIZE(large_src)); diff --git a/lib/nlattr.c b/lib/nlattr.c index 9055e8b4d144..489e15bde5c1 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -10,6 +10,7 @@ #include <linux/kernel.h> #include <linux/errno.h> #include <linux/jiffies.h> +#include <linux/nospec.h> #include <linux/skbuff.h> #include <linux/string.h> #include <linux/types.h> @@ -381,6 +382,7 @@ static int validate_nla(const struct nlattr *nla, int maxtype, if (type <= 0 || type > maxtype) return 0; + type = array_index_nospec(type, maxtype + 1); pt = &policy[type]; BUG_ON(pt->type > NLA_TYPE_MAX); @@ -596,6 +598,7 @@ static int __nla_validate_parse(const struct nlattr *head, int len, int maxtype, } continue; } + type = array_index_nospec(type, maxtype + 1); if (policy) { int err = validate_nla(nla, maxtype, policy, validate, extack, depth); diff --git a/lib/scatterlist.c b/lib/scatterlist.c index f72aa50c6654..8d7519a8f308 100644 --- a/lib/scatterlist.c +++ b/lib/scatterlist.c @@ -470,22 +470,27 @@ int sg_alloc_append_table_from_pages(struct sg_append_table *sgt_append, return -EOPNOTSUPP; if (sgt_append->prv) { + unsigned long next_pfn = (page_to_phys(sg_page(sgt_append->prv)) + + sgt_append->prv->offset + sgt_append->prv->length) / PAGE_SIZE; + if (WARN_ON(offset)) return -EINVAL; /* Merge contiguous pages into the last SG */ prv_len = sgt_append->prv->length; - last_pg = sg_page(sgt_append->prv); - while (n_pages && pages_are_mergeable(pages[0], last_pg)) { - if (sgt_append->prv->length + PAGE_SIZE > max_segment) - break; - sgt_append->prv->length += PAGE_SIZE; - last_pg = pages[0]; - pages++; - n_pages--; + if (page_to_pfn(pages[0]) == next_pfn) { + last_pg = pfn_to_page(next_pfn - 1); + while (n_pages && pages_are_mergeable(pages[0], last_pg)) { + if (sgt_append->prv->length + PAGE_SIZE > max_segment) + break; + sgt_append->prv->length += PAGE_SIZE; + last_pg = pages[0]; + pages++; + n_pages--; + } + if (!n_pages) + goto out; } - if (!n_pages) - goto out; } /* compute number of contiguous chunks */ diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 497fc93ccf9e..ec847bf4dcb4 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -2517,6 +2517,91 @@ static noinline void check_bnode_min_spanning(struct maple_tree *mt) mt_set_non_kernel(0); } +static noinline void check_empty_area_window(struct maple_tree *mt) +{ + unsigned long i, nr_entries = 20; + MA_STATE(mas, mt, 0, 0); + + for (i = 1; i <= nr_entries; i++) + mtree_store_range(mt, i*10, i*10 + 9, + xa_mk_value(i), GFP_KERNEL); + + /* Create another hole besides the one at 0 */ + mtree_store_range(mt, 160, 169, NULL, GFP_KERNEL); + + /* Check lower bounds that don't fit */ + rcu_read_lock(); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 10) != -EBUSY); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 6, 90, 5) != -EBUSY); + + /* Check lower bound that does fit */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 90, 5) != 0); + MT_BUG_ON(mt, mas.index != 5); + MT_BUG_ON(mt, mas.last != 9); + rcu_read_unlock(); + + /* Check one gap that doesn't fit and one that does */ + rcu_read_lock(); + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 5, 217, 9) != 0); + MT_BUG_ON(mt, mas.index != 161); + MT_BUG_ON(mt, mas.last != 169); + + /* Check one gap that does fit above the min */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 3) != 0); + MT_BUG_ON(mt, mas.index != 216); + MT_BUG_ON(mt, mas.last != 218); + + /* Check size that doesn't fit any gap */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 218, 16) != -EBUSY); + + /* + * Check size that doesn't fit the lower end of the window but + * does fit the gap + */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 167, 200, 4) != -EBUSY); + + /* + * Check size that doesn't fit the upper end of the window but + * does fit the gap + */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area_rev(&mas, 100, 162, 4) != -EBUSY); + + /* Check mas_empty_area forward */ + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 9) != 0); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 8); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 4) != 0); + MT_BUG_ON(mt, mas.index != 0); + MT_BUG_ON(mt, mas.last != 3); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 100, 11) != -EBUSY); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 5, 100, 6) != -EBUSY); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 0, 8, 10) != -EBUSY); + + mas_reset(&mas); + mas_empty_area(&mas, 100, 165, 3); + + mas_reset(&mas); + MT_BUG_ON(mt, mas_empty_area(&mas, 100, 163, 6) != -EBUSY); + rcu_read_unlock(); +} + static DEFINE_MTREE(tree); static int maple_tree_seed(void) { @@ -2765,6 +2850,10 @@ static int maple_tree_seed(void) check_bnode_min_spanning(&tree); mtree_destroy(&tree); + mt_init_flags(&tree, MT_FLAGS_ALLOC_RANGE); + check_empty_area_window(&tree); + mtree_destroy(&tree); + #if defined(BENCH) skip: #endif diff --git a/lib/win_minmax.c b/lib/win_minmax.c index 6bdc1cd15f76..ec10506834b6 100644 --- a/lib/win_minmax.c +++ b/lib/win_minmax.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/** +/* * lib/minmax.c: windowed min/max tracker * * Kathleen Nichols' algorithm for tracking the minimum (or maximum) diff --git a/mm/compaction.c b/mm/compaction.c index ca1603524bbe..8238e83385a7 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1839,6 +1839,7 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc) pfn = cc->zone->zone_start_pfn; cc->fast_search_fail = 0; found_block = true; + set_pageblock_skip(freepage); break; } } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index db895230ee7e..bdbfeb6fb393 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -94,6 +94,8 @@ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); +static void hugetlb_unshare_pmds(struct vm_area_struct *vma, + unsigned long start, unsigned long end); static inline bool subpool_is_free(struct hugepage_subpool *spool) { @@ -1181,7 +1183,7 @@ void hugetlb_dup_vma_private(struct vm_area_struct *vma) /* * Reset and decrement one ref on hugepage private reservation. - * Called with mm->mmap_sem writer semaphore held. + * Called with mm->mmap_lock writer semaphore held. * This function should be only used by move_vma() and operate on * same sized vma. It should never come here with last ref on the * reservation. @@ -4834,6 +4836,25 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; + + /* + * PMD sharing is only possible for PUD_SIZE-aligned address ranges + * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this + * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. + */ + if (addr & ~PUD_MASK) { + /* + * hugetlb_vm_op_split is called right before we attempt to + * split the VMA. We will need to unshare PMDs in the old and + * new VMAs, so let's unshare before we split. + */ + unsigned long floor = addr & PUD_MASK; + unsigned long ceil = floor + PUD_SIZE; + + if (floor >= vma->vm_start && ceil <= vma->vm_end) + hugetlb_unshare_pmds(vma, floor, ceil); + } + return 0; } @@ -5030,6 +5051,9 @@ again: entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry); } else if (unlikely(is_pte_marker(entry))) { + /* No swap on hugetlb */ + WARN_ON_ONCE( + is_swapin_error_entry(pte_to_swp_entry(entry))); /* * We copy the pte marker only if the dst vma has * uffd-wp enabled. @@ -5131,7 +5155,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, /* * We don't have to worry about the ordering of src and dst ptlocks - * because exclusive mmap_sem (or the i_mmap_lock) prevents deadlock. + * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock. */ if (src_ptl != dst_ptl) spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); @@ -6639,8 +6663,17 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, spinlock_t *ptl; ptep = huge_pte_offset(mm, address, psize); if (!ptep) { - address |= last_addr_mask; - continue; + if (!uffd_wp) { + address |= last_addr_mask; + continue; + } + /* + * Userfaultfd wr-protect requires pgtable + * pre-allocations to install pte markers. + */ + ptep = huge_pte_alloc(mm, vma, address, psize); + if (!ptep) + break; } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, vma, address, ptep)) { @@ -6658,16 +6691,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, } pte = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { - spin_unlock(ptl); - continue; - } - if (unlikely(is_hugetlb_entry_migration(pte))) { + /* Nothing to do. */ + } else if (unlikely(is_hugetlb_entry_migration(pte))) { swp_entry_t entry = pte_to_swp_entry(pte); struct page *page = pfn_swap_entry_to_page(entry); + pte_t newpte = pte; - if (!is_readable_migration_entry(entry)) { - pte_t newpte; - + if (is_writable_migration_entry(entry)) { if (PageAnon(page)) entry = make_readable_exclusive_migration_entry( swp_offset(entry)); @@ -6675,25 +6705,22 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, entry = make_readable_migration_entry( swp_offset(entry)); newpte = swp_entry_to_pte(entry); - if (uffd_wp) - newpte = pte_swp_mkuffd_wp(newpte); - else if (uffd_wp_resolve) - newpte = pte_swp_clear_uffd_wp(newpte); - set_huge_pte_at(mm, address, ptep, newpte); pages++; } - spin_unlock(ptl); - continue; - } - if (unlikely(pte_marker_uffd_wp(pte))) { - /* - * This is changing a non-present pte into a none pte, - * no need for huge_ptep_modify_prot_start/commit(). - */ + + if (uffd_wp) + newpte = pte_swp_mkuffd_wp(newpte); + else if (uffd_wp_resolve) + newpte = pte_swp_clear_uffd_wp(newpte); + if (!pte_same(pte, newpte)) + set_huge_pte_at(mm, address, ptep, newpte); + } else if (unlikely(is_pte_marker(pte))) { + /* No other markers apply for now. */ + WARN_ON_ONCE(!pte_marker_uffd_wp(pte)); if (uffd_wp_resolve) + /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); - } - if (!huge_pte_none(pte)) { + } else if (!huge_pte_none(pte)) { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); @@ -7328,26 +7355,21 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re } } -/* - * This function will unconditionally remove all the shared pmd pgtable entries - * within the specific vma for a hugetlbfs memory range. - */ -void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) +static void hugetlb_unshare_pmds(struct vm_area_struct *vma, + unsigned long start, + unsigned long end) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; - unsigned long address, start, end; + unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; - start = ALIGN(vma->vm_start, PUD_SIZE); - end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); - if (start >= end) return; @@ -7379,6 +7401,16 @@ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) mmu_notifier_invalidate_range_end(&range); } +/* + * This function will unconditionally remove all the shared pmd pgtable entries + * within the specific vma for a hugetlbfs memory range. + */ +void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) +{ + hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), + ALIGN_DOWN(vma->vm_end, PUD_SIZE)); +} + #ifdef CONFIG_CMA static bool cma_reserve_called __initdata; diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 1d02757e90a3..22598b20c7b7 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(kasan_restore_multi_shot); * Whether the KASAN KUnit test suite is currently being executed. * Updated in kasan_test.c. */ -bool kasan_kunit_executing; +static bool kasan_kunit_executing; void kasan_kunit_test_suite_start(void) { diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 5cb401aa2b9d..90acfea40c13 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -847,6 +847,10 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, return SCAN_SUCCEED; } +/* + * See pmd_trans_unstable() for how the result may change out from + * underneath us, even if we hold mmap_lock in read. + */ static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) @@ -865,8 +869,12 @@ static int find_pmd_or_thp_or_none(struct mm_struct *mm, #endif if (pmd_none(pmde)) return SCAN_PMD_NONE; + if (!pmd_present(pmde)) + return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; + if (pmd_devmap(pmde)) + return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; @@ -1460,14 +1468,6 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false)) return SCAN_VMA_CHECK; - /* - * Symmetry with retract_page_tables(): Exclude MAP_PRIVATE mappings - * that got written to. Without this, we'd have to also lock the - * anon_vma if one exists. - */ - if (vma->anon_vma) - return SCAN_VMA_CHECK; - /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; @@ -1567,8 +1567,14 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, } /* step 4: remove pte entries */ + /* we make no change to anon, but protect concurrent anon page lookup */ + if (vma->anon_vma) + anon_vma_lock_write(vma->anon_vma); + collapse_and_free_pmd(mm, vma, haddr, pmd); + if (vma->anon_vma) + anon_vma_unlock_write(vma->anon_vma); i_mmap_unlock_write(vma->vm_file->f_mapping); maybe_install_pmd: @@ -1644,7 +1650,7 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, * has higher cost too. It would also probably require locking * the anon_vma. */ - if (vma->anon_vma) { + if (READ_ONCE(vma->anon_vma)) { result = SCAN_PAGE_ANON; goto next; } @@ -1673,6 +1679,18 @@ static int retract_page_tables(struct address_space *mapping, pgoff_t pgoff, if ((cc->is_khugepaged || is_target) && mmap_write_trylock(mm)) { /* + * Re-check whether we have an ->anon_vma, because + * collapse_and_free_pmd() requires that either no + * ->anon_vma exists or the anon_vma is locked. + * We already checked ->anon_vma above, but that check + * is racy because ->anon_vma can be populated under the + * mmap lock in read mode. + */ + if (vma->anon_vma) { + result = SCAN_PAGE_ANON; + goto unlock_next; + } + /* * When a vma is registered with uffd-wp, we can't * recycle the pmd pgtable because there can be pte * markers installed. Skip it only, so the rest mm/vma @@ -2649,7 +2667,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, goto out_nolock; } - hend = vma->vm_end & HPAGE_PMD_MASK; + hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 92f670edbf51..55dc8b8b0616 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -2070,8 +2070,10 @@ static int __init kmemleak_boot_config(char *str) return -EINVAL; if (strcmp(str, "off") == 0) kmemleak_disable(); - else if (strcmp(str, "on") == 0) + else if (strcmp(str, "on") == 0) { kmemleak_skip_disable = 1; + stack_depot_want_early_init(); + } else return -EINVAL; return 0; @@ -2093,7 +2095,6 @@ void __init kmemleak_init(void) if (kmemleak_error) return; - stack_depot_init(); jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE); jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000); diff --git a/mm/madvise.c b/mm/madvise.c index a56a6d17e201..b6ea204d4e23 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -130,7 +130,7 @@ static int replace_anon_vma_name(struct vm_area_struct *vma, #endif /* CONFIG_ANON_VMA_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; + * necessary. Must be called with mmap_lock 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. */ diff --git a/mm/memblock.c b/mm/memblock.c index d036c7861310..685e30e6d27c 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1640,7 +1640,13 @@ void __init memblock_free_late(phys_addr_t base, phys_addr_t size) end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { - memblock_free_pages(pfn_to_page(cursor), cursor, 0); + /* + * Reserved pages are always initialized by the end of + * memblock_free_all() (by memmap_init() and, if deferred + * initialization is enabled, memmap_init_reserved_pages()), so + * these pages can be released directly to the buddy allocator. + */ + __free_pages_core(pfn_to_page(cursor), 0); totalram_pages_inc(); } } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ab457f0394ab..73afff8062f9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -63,7 +63,6 @@ #include <linux/resume_user_mode.h> #include <linux/psi.h> #include <linux/seq_buf.h> -#include <linux/parser.h> #include "internal.h" #include <net/sock.h> #include <net/ip.h> @@ -2393,8 +2392,7 @@ static unsigned long reclaim_high(struct mem_cgroup *memcg, psi_memstall_enter(&pflags); nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, - MEMCG_RECLAIM_MAY_SWAP, - NULL); + MEMCG_RECLAIM_MAY_SWAP); psi_memstall_leave(&pflags); } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); @@ -2685,8 +2683,7 @@ retry: psi_memstall_enter(&pflags); nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, - gfp_mask, reclaim_options, - NULL); + gfp_mask, reclaim_options); psi_memstall_leave(&pflags); if (mem_cgroup_margin(mem_over_limit) >= nr_pages) @@ -3506,8 +3503,7 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg, } if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP, - NULL)) { + memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) { ret = -EBUSY; break; } @@ -3618,8 +3614,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg) return -EINTR; if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL, - MEMCG_RECLAIM_MAY_SWAP, - NULL)) + MEMCG_RECLAIM_MAY_SWAP)) nr_retries--; } @@ -6429,8 +6424,7 @@ static ssize_t memory_high_write(struct kernfs_open_file *of, } reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, - NULL); + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP); if (!reclaimed && !nr_retries--) break; @@ -6479,8 +6473,7 @@ static ssize_t memory_max_write(struct kernfs_open_file *of, if (nr_reclaims) { if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max, - GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP, - NULL)) + GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP)) nr_reclaims--; continue; } @@ -6603,54 +6596,21 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of, return nbytes; } -enum { - MEMORY_RECLAIM_NODES = 0, - MEMORY_RECLAIM_NULL, -}; - -static const match_table_t if_tokens = { - { MEMORY_RECLAIM_NODES, "nodes=%s" }, - { MEMORY_RECLAIM_NULL, NULL }, -}; - static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); unsigned int nr_retries = MAX_RECLAIM_RETRIES; unsigned long nr_to_reclaim, nr_reclaimed = 0; - unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP | - MEMCG_RECLAIM_PROACTIVE; - char *old_buf, *start; - substring_t args[MAX_OPT_ARGS]; - int token; - char value[256]; - nodemask_t nodemask = NODE_MASK_ALL; - - buf = strstrip(buf); - - old_buf = buf; - nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE; - if (buf == old_buf) - return -EINVAL; + unsigned int reclaim_options; + int err; buf = strstrip(buf); + err = page_counter_memparse(buf, "", &nr_to_reclaim); + if (err) + return err; - while ((start = strsep(&buf, " ")) != NULL) { - if (!strlen(start)) - continue; - token = match_token(start, if_tokens, args); - match_strlcpy(value, args, sizeof(value)); - switch (token) { - case MEMORY_RECLAIM_NODES: - if (nodelist_parse(value, nodemask) < 0) - return -EINVAL; - break; - default: - return -EINVAL; - } - } - + reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE; while (nr_reclaimed < nr_to_reclaim) { unsigned long reclaimed; @@ -6667,8 +6627,7 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf, reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_to_reclaim - nr_reclaimed, - GFP_KERNEL, reclaim_options, - &nodemask); + GFP_KERNEL, reclaim_options); if (!reclaimed && !nr_retries--) return -EAGAIN; diff --git a/mm/memory.c b/mm/memory.c index aad226daf41b..3e836fecd035 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -828,12 +828,8 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, return -EBUSY; return -ENOENT; } else if (is_pte_marker_entry(entry)) { - /* - * We're copying the pgtable should only because dst_vma has - * uffd-wp enabled, do sanity check. - */ - WARN_ON_ONCE(!userfaultfd_wp(dst_vma)); - set_pte_at(dst_mm, addr, dst_pte, pte); + if (is_swapin_error_entry(entry) || userfaultfd_wp(dst_vma)) + set_pte_at(dst_mm, addr, dst_pte, pte); return 0; } if (!userfaultfd_wp(dst_vma)) @@ -3629,8 +3625,12 @@ static vm_fault_t pte_marker_clear(struct vm_fault *vmf) /* * Be careful so that we will only recover a special uffd-wp pte into a * none pte. Otherwise it means the pte could have changed, so retry. + * + * This should also cover the case where e.g. the pte changed + * quickly from a PTE_MARKER_UFFD_WP into PTE_MARKER_SWAPIN_ERROR. + * So is_pte_marker() check is not enough to safely drop the pte. */ - if (is_pte_marker(*vmf->pte)) + if (pte_same(vmf->orig_pte, *vmf->pte)) pte_clear(vmf->vma->vm_mm, vmf->address, vmf->pte); pte_unmap_unlock(vmf->pte, vmf->ptl); return 0; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 02c8a712282f..f940395667c8 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -600,7 +600,8 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || - (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) { + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && + !hugetlb_pmd_shared(pte))) { if (isolate_hugetlb(page, qp->pagelist) && (flags & MPOL_MF_STRICT)) /* diff --git a/mm/mmap.c b/mm/mmap.c index 87d929316d57..425a9349e610 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1524,6 +1524,10 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) if (vma_soft_dirty_enabled(vma) && !is_vm_hugetlb_page(vma)) return 1; + /* Do we need write faults for uffd-wp tracking? */ + if (userfaultfd_wp(vma)) + return 1; + /* Specialty mapping? */ if (vm_flags & VM_PFNMAP) return 0; @@ -2290,7 +2294,7 @@ static inline int munmap_sidetree(struct vm_area_struct *vma, * @start: The aligned start address to munmap. * @end: The aligned end address to munmap. * @uf: The userfaultfd list_head - * @downgrade: Set to true to attempt a write downgrade of the mmap_sem + * @downgrade: Set to true to attempt a write downgrade of the mmap_lock * * If @downgrade is true, check return code for potential release of the lock. */ @@ -2465,7 +2469,7 @@ map_count_exceeded: * @len: The length of the range to munmap * @uf: The userfaultfd list_head * @downgrade: set to true if the user wants to attempt to write_downgrade the - * mmap_sem + * mmap_lock * * This function takes a @mas that is either pointing to the previous VMA or set * to MA_START and sets it up to remove the mapping(s). The @len will be diff --git a/mm/mprotect.c b/mm/mprotect.c index 908df12caa26..61cf60015a8b 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -245,7 +245,13 @@ static unsigned long change_pte_range(struct mmu_gather *tlb, newpte = pte_swp_mksoft_dirty(newpte); if (pte_swp_uffd_wp(oldpte)) newpte = pte_swp_mkuffd_wp(newpte); - } else if (pte_marker_entry_uffd_wp(entry)) { + } else if (is_pte_marker_entry(entry)) { + /* + * Ignore swapin errors unconditionally, + * because any access should sigbus anyway. + */ + if (is_swapin_error_entry(entry)) + continue; /* * If this is uffd-wp pte marker and we'd like * to unprotect it, drop it; the next page diff --git a/mm/mremap.c b/mm/mremap.c index fe587c5d6591..930f65c315c0 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -1027,16 +1027,29 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, } /* - * Function vma_merge() is called on the extension we are adding to - * the already existing vma, vma_merge() will merge this extension with - * the already existing vma (expand operation itself) and possibly also - * with the next vma if it becomes adjacent to the expanded vma and - * otherwise compatible. + * Function vma_merge() is called on the extension we + * are adding to the already existing vma, vma_merge() + * will merge this extension with the already existing + * vma (expand operation itself) and possibly also with + * the next vma if it becomes adjacent to the expanded + * vma and otherwise compatible. + * + * However, vma_merge() can currently fail due to + * is_mergeable_vma() check for vm_ops->close (see the + * comment there). Yet this should not prevent vma + * expanding, so perform a simple expand for such vma. + * Ideally the check for close op should be only done + * when a vma would be actually removed due to a merge. */ - vma = vma_merge(mm, vma, extension_start, extension_end, + if (!vma->vm_ops || !vma->vm_ops->close) { + vma = vma_merge(mm, vma, extension_start, extension_end, vma->vm_flags, vma->anon_vma, vma->vm_file, extension_pgoff, vma_policy(vma), vma->vm_userfaultfd_ctx, anon_vma_name(vma)); + } else if (vma_adjust(vma, vma->vm_start, addr + new_len, + vma->vm_pgoff, NULL)) { + vma = NULL; + } if (!vma) { vm_unacct_memory(pages); ret = -ENOMEM; diff --git a/mm/nommu.c b/mm/nommu.c index 214c70e1d059..5b83938ecb67 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -559,7 +559,6 @@ void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas) static void setup_vma_to_mm(struct vm_area_struct *vma, struct mm_struct *mm) { - mm->map_count++; vma->vm_mm = mm; /* add the VMA to the mapping */ @@ -587,6 +586,7 @@ static void mas_add_vma_to_mm(struct ma_state *mas, struct mm_struct *mm, BUG_ON(!vma->vm_region); setup_vma_to_mm(vma, mm); + mm->map_count++; /* add the VMA to the tree */ vma_mas_store(vma, mas); @@ -1240,6 +1240,7 @@ share: error_just_free: up_write(&nommu_region_sem); error: + mas_destroy(&mas); if (region->vm_file) fput(region->vm_file); kmem_cache_free(vm_region_jar, region); @@ -1250,7 +1251,6 @@ error: sharing_violation: up_write(&nommu_region_sem); - mas_destroy(&mas); pr_warn("Attempt to share mismatched mappings\n"); ret = -EINVAL; goto error; @@ -1347,6 +1347,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, if (vma->vm_file) return -ENOMEM; + mm = vma->vm_mm; if (mm->map_count >= sysctl_max_map_count) return -ENOMEM; @@ -1398,6 +1399,7 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, mas_set_range(&mas, vma->vm_start, vma->vm_end - 1); mas_store(&mas, vma); vma_mas_store(new, &mas); + mm->map_count++; return 0; err_mas_preallocate: @@ -1509,7 +1511,8 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, struct list erase_whole_vma: if (delete_vma_from_mm(vma)) ret = -ENOMEM; - delete_vma(mm, vma); + else + delete_vma(mm, vma); return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index c301487be5fb..0005ab2c29af 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -478,12 +478,10 @@ bool shmem_is_huge(struct vm_area_struct *vma, struct inode *inode, if (vma && ((vma->vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))) return false; - if (shmem_huge_force) - return true; - if (shmem_huge == SHMEM_HUGE_FORCE) - return true; if (shmem_huge == SHMEM_HUGE_DENY) return false; + if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE) + return true; switch (SHMEM_SB(inode->i_sb)->huge) { case SHMEM_HUGE_ALWAYS: diff --git a/mm/slab.c b/mm/slab.c index 7a269db050ee..29300fc1289a 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2211,6 +2211,8 @@ static int drain_freelist(struct kmem_cache *cache, raw_spin_unlock_irq(&n->list_lock); slab_destroy(cache, slab); nr_freed++; + + cond_resched(); } out: return nr_freed; diff --git a/mm/swapfile.c b/mm/swapfile.c index 908a529bca12..4fa440e87cd6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1100,6 +1100,7 @@ start_over: goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); + cond_resched(); spin_lock(&swap_avail_lock); nextsi: diff --git a/mm/vmscan.c b/mm/vmscan.c index bd6637fcd8f9..bf3eedf0209c 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -3323,13 +3323,16 @@ void lru_gen_migrate_mm(struct mm_struct *mm) if (mem_cgroup_disabled()) return; + /* migration can happen before addition */ + if (!mm->lru_gen.memcg) + return; + rcu_read_lock(); memcg = mem_cgroup_from_task(task); rcu_read_unlock(); if (memcg == mm->lru_gen.memcg) return; - VM_WARN_ON_ONCE(!mm->lru_gen.memcg); VM_WARN_ON_ONCE(list_empty(&mm->lru_gen.list)); lru_gen_del_mm(mm); @@ -6754,8 +6757,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg, unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, - unsigned int reclaim_options, - nodemask_t *nodemask) + unsigned int reclaim_options) { unsigned long nr_reclaimed; unsigned int noreclaim_flag; @@ -6770,7 +6772,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, .may_unmap = 1, .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP), .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE), - .nodemask = nodemask, }; /* * Traverse the ZONELIST_FALLBACK zonelist of the current node to put diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9445bee6b014..702bc3fd687a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -113,7 +113,23 @@ * have room for two bit at least. */ #define OBJ_ALLOCATED_TAG 1 -#define OBJ_TAG_BITS 1 + +#ifdef CONFIG_ZPOOL +/* + * The second least-significant bit in the object's header identifies if the + * value stored at the header is a deferred handle from the last reclaim + * attempt. + * + * As noted above, this is valid because we have room for two bits. + */ +#define OBJ_DEFERRED_HANDLE_TAG 2 +#define OBJ_TAG_BITS 2 +#define OBJ_TAG_MASK (OBJ_ALLOCATED_TAG | OBJ_DEFERRED_HANDLE_TAG) +#else +#define OBJ_TAG_BITS 1 +#define OBJ_TAG_MASK OBJ_ALLOCATED_TAG +#endif /* CONFIG_ZPOOL */ + #define OBJ_INDEX_BITS (BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS) #define OBJ_INDEX_MASK ((_AC(1, UL) << OBJ_INDEX_BITS) - 1) @@ -222,6 +238,12 @@ struct link_free { * Handle of allocated object. */ unsigned long handle; +#ifdef CONFIG_ZPOOL + /* + * Deferred handle of a reclaimed object. + */ + unsigned long deferred_handle; +#endif }; }; @@ -272,8 +294,6 @@ struct zspage { /* links the zspage to the lru list in the pool */ struct list_head lru; bool under_reclaim; - /* list of unfreed handles whose objects have been reclaimed */ - unsigned long *deferred_handles; #endif struct zs_pool *pool; @@ -897,7 +917,8 @@ static unsigned long handle_to_obj(unsigned long handle) return *(unsigned long *)handle; } -static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) +static bool obj_tagged(struct page *page, void *obj, unsigned long *phandle, + int tag) { unsigned long handle; struct zspage *zspage = get_zspage(page); @@ -908,13 +929,27 @@ static bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) } else handle = *(unsigned long *)obj; - if (!(handle & OBJ_ALLOCATED_TAG)) + if (!(handle & tag)) return false; - *phandle = handle & ~OBJ_ALLOCATED_TAG; + /* Clear all tags before returning the handle */ + *phandle = handle & ~OBJ_TAG_MASK; return true; } +static inline bool obj_allocated(struct page *page, void *obj, unsigned long *phandle) +{ + return obj_tagged(page, obj, phandle, OBJ_ALLOCATED_TAG); +} + +#ifdef CONFIG_ZPOOL +static bool obj_stores_deferred_handle(struct page *page, void *obj, + unsigned long *phandle) +{ + return obj_tagged(page, obj, phandle, OBJ_DEFERRED_HANDLE_TAG); +} +#endif + static void reset_page(struct page *page) { __ClearPageMovable(page); @@ -946,22 +981,36 @@ unlock: } #ifdef CONFIG_ZPOOL +static unsigned long find_deferred_handle_obj(struct size_class *class, + struct page *page, int *obj_idx); + /* * Free all the deferred handles whose objects are freed in zs_free. */ -static void free_handles(struct zs_pool *pool, struct zspage *zspage) +static void free_handles(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) { - unsigned long handle = (unsigned long)zspage->deferred_handles; + int obj_idx = 0; + struct page *page = get_first_page(zspage); + unsigned long handle; - while (handle) { - unsigned long nxt_handle = handle_to_obj(handle); + while (1) { + handle = find_deferred_handle_obj(class, page, &obj_idx); + if (!handle) { + page = get_next_page(page); + if (!page) + break; + obj_idx = 0; + continue; + } cache_free_handle(pool, handle); - handle = nxt_handle; + obj_idx++; } } #else -static inline void free_handles(struct zs_pool *pool, struct zspage *zspage) {} +static inline void free_handles(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) {} #endif static void __free_zspage(struct zs_pool *pool, struct size_class *class, @@ -979,7 +1028,7 @@ static void __free_zspage(struct zs_pool *pool, struct size_class *class, VM_BUG_ON(fg != ZS_EMPTY); /* Free all deferred handles from zs_free */ - free_handles(pool, zspage); + free_handles(pool, class, zspage); next = page = get_first_page(zspage); do { @@ -1067,7 +1116,6 @@ static void init_zspage(struct size_class *class, struct zspage *zspage) #ifdef CONFIG_ZPOOL INIT_LIST_HEAD(&zspage->lru); zspage->under_reclaim = false; - zspage->deferred_handles = NULL; #endif set_freeobj(zspage, 0); @@ -1568,7 +1616,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size, gfp_t gfp) } EXPORT_SYMBOL_GPL(zs_malloc); -static void obj_free(int class_size, unsigned long obj) +static void obj_free(int class_size, unsigned long obj, unsigned long *handle) { struct link_free *link; struct zspage *zspage; @@ -1582,15 +1630,29 @@ static void obj_free(int class_size, unsigned long obj) zspage = get_zspage(f_page); vaddr = kmap_atomic(f_page); - - /* Insert this object in containing zspage's freelist */ link = (struct link_free *)(vaddr + f_offset); - if (likely(!ZsHugePage(zspage))) - link->next = get_freeobj(zspage) << OBJ_TAG_BITS; - else - f_page->index = 0; + + if (handle) { +#ifdef CONFIG_ZPOOL + /* Stores the (deferred) handle in the object's header */ + *handle |= OBJ_DEFERRED_HANDLE_TAG; + *handle &= ~OBJ_ALLOCATED_TAG; + + if (likely(!ZsHugePage(zspage))) + link->deferred_handle = *handle; + else + f_page->index = *handle; +#endif + } else { + /* Insert this object in containing zspage's freelist */ + if (likely(!ZsHugePage(zspage))) + link->next = get_freeobj(zspage) << OBJ_TAG_BITS; + else + f_page->index = 0; + set_freeobj(zspage, f_objidx); + } + kunmap_atomic(vaddr); - set_freeobj(zspage, f_objidx); mod_zspage_inuse(zspage, -1); } @@ -1615,7 +1677,6 @@ void zs_free(struct zs_pool *pool, unsigned long handle) zspage = get_zspage(f_page); class = zspage_class(pool, zspage); - obj_free(class->size, obj); class_stat_dec(class, OBJ_USED, 1); #ifdef CONFIG_ZPOOL @@ -1624,15 +1685,15 @@ void zs_free(struct zs_pool *pool, unsigned long handle) * Reclaim needs the handles during writeback. It'll free * them along with the zspage when it's done with them. * - * Record current deferred handle at the memory location - * whose address is given by handle. + * Record current deferred handle in the object's header. */ - record_obj(handle, (unsigned long)zspage->deferred_handles); - zspage->deferred_handles = (unsigned long *)handle; + obj_free(class->size, obj, &handle); spin_unlock(&pool->lock); return; } #endif + obj_free(class->size, obj, NULL); + fullness = fix_fullness_group(class, zspage); if (fullness == ZS_EMPTY) free_zspage(pool, class, zspage); @@ -1713,11 +1774,11 @@ static void zs_object_copy(struct size_class *class, unsigned long dst, } /* - * Find alloced object in zspage from index object and + * Find object with a certain tag in zspage from index object and * return handle. */ -static unsigned long find_alloced_obj(struct size_class *class, - struct page *page, int *obj_idx) +static unsigned long find_tagged_obj(struct size_class *class, + struct page *page, int *obj_idx, int tag) { unsigned int offset; int index = *obj_idx; @@ -1728,7 +1789,7 @@ static unsigned long find_alloced_obj(struct size_class *class, offset += class->size * index; while (offset < PAGE_SIZE) { - if (obj_allocated(page, addr + offset, &handle)) + if (obj_tagged(page, addr + offset, &handle, tag)) break; offset += class->size; @@ -1742,6 +1803,28 @@ static unsigned long find_alloced_obj(struct size_class *class, return handle; } +/* + * Find alloced object in zspage from index object and + * return handle. + */ +static unsigned long find_alloced_obj(struct size_class *class, + struct page *page, int *obj_idx) +{ + return find_tagged_obj(class, page, obj_idx, OBJ_ALLOCATED_TAG); +} + +#ifdef CONFIG_ZPOOL +/* + * Find object storing a deferred handle in header in zspage from index object + * and return handle. + */ +static unsigned long find_deferred_handle_obj(struct size_class *class, + struct page *page, int *obj_idx) +{ + return find_tagged_obj(class, page, obj_idx, OBJ_DEFERRED_HANDLE_TAG); +} +#endif + struct zs_compact_control { /* Source spage for migration which could be a subpage of zspage */ struct page *s_page; @@ -1784,7 +1867,7 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, zs_object_copy(class, free_obj, used_obj); obj_idx++; record_obj(handle, free_obj); - obj_free(class->size, used_obj); + obj_free(class->size, used_obj, NULL); } /* Remember last position in this iteration */ @@ -2478,6 +2561,90 @@ void zs_destroy_pool(struct zs_pool *pool) EXPORT_SYMBOL_GPL(zs_destroy_pool); #ifdef CONFIG_ZPOOL +static void restore_freelist(struct zs_pool *pool, struct size_class *class, + struct zspage *zspage) +{ + unsigned int obj_idx = 0; + unsigned long handle, off = 0; /* off is within-page offset */ + struct page *page = get_first_page(zspage); + struct link_free *prev_free = NULL; + void *prev_page_vaddr = NULL; + + /* in case no free object found */ + set_freeobj(zspage, (unsigned int)(-1UL)); + + while (page) { + void *vaddr = kmap_atomic(page); + struct page *next_page; + + while (off < PAGE_SIZE) { + void *obj_addr = vaddr + off; + + /* skip allocated object */ + if (obj_allocated(page, obj_addr, &handle)) { + obj_idx++; + off += class->size; + continue; + } + + /* free deferred handle from reclaim attempt */ + if (obj_stores_deferred_handle(page, obj_addr, &handle)) + cache_free_handle(pool, handle); + + if (prev_free) + prev_free->next = obj_idx << OBJ_TAG_BITS; + else /* first free object found */ + set_freeobj(zspage, obj_idx); + + prev_free = (struct link_free *)vaddr + off / sizeof(*prev_free); + /* if last free object in a previous page, need to unmap */ + if (prev_page_vaddr) { + kunmap_atomic(prev_page_vaddr); + prev_page_vaddr = NULL; + } + + obj_idx++; + off += class->size; + } + + /* + * Handle the last (full or partial) object on this page. + */ + next_page = get_next_page(page); + if (next_page) { + if (!prev_free || prev_page_vaddr) { + /* + * There is no free object in this page, so we can safely + * unmap it. + */ + kunmap_atomic(vaddr); + } else { + /* update prev_page_vaddr since prev_free is on this page */ + prev_page_vaddr = vaddr; + } + } else { /* this is the last page */ + if (prev_free) { + /* + * Reset OBJ_TAG_BITS bit to last link to tell + * whether it's allocated object or not. + */ + prev_free->next = -1UL << OBJ_TAG_BITS; + } + + /* unmap previous page (if not done yet) */ + if (prev_page_vaddr) { + kunmap_atomic(prev_page_vaddr); + prev_page_vaddr = NULL; + } + + kunmap_atomic(vaddr); + } + + page = next_page; + off %= PAGE_SIZE; + } +} + static int zs_reclaim_page(struct zs_pool *pool, unsigned int retries) { int i, obj_idx, ret = 0; @@ -2561,6 +2728,12 @@ next: return 0; } + /* + * Eviction fails on one of the handles, so we need to restore zspage. + * We need to rebuild its freelist (and free stored deferred handles), + * put it back to the correct size class, and add it to the LRU list. + */ + restore_freelist(pool, class, zspage); putback_zspage(class, zspage); list_add(&zspage->lru, &pool->lru); unlock_zspage(zspage); diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 9630b1275557..82c7005ede65 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -305,13 +305,12 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) kfree(priv); } -static int xen_9pfs_front_remove(struct xenbus_device *dev) +static void xen_9pfs_front_remove(struct xenbus_device *dev) { struct xen_9pfs_front_priv *priv = dev_get_drvdata(&dev->dev); dev_set_drvdata(&dev->dev, NULL); xen_9pfs_front_free(priv); - return 0; } static int xen_9pfs_front_alloc_dataring(struct xenbus_device *dev, diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index d3e542c2fc3e..acf563fbdfd9 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -821,6 +821,7 @@ static void terminate_big_destroy(struct hci_dev *hdev, void *data, int err) static int hci_le_terminate_big(struct hci_dev *hdev, u8 big, u8 bis) { struct iso_list_data *d; + int ret; bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", big, bis); @@ -831,8 +832,12 @@ static int hci_le_terminate_big(struct hci_dev *hdev, u8 big, u8 bis) d->big = big; d->bis = bis; - return hci_cmd_sync_queue(hdev, terminate_big_sync, d, - terminate_big_destroy); + ret = hci_cmd_sync_queue(hdev, terminate_big_sync, d, + terminate_big_destroy); + if (ret) + kfree(d); + + return ret; } static int big_terminate_sync(struct hci_dev *hdev, void *data) @@ -857,6 +862,7 @@ static int big_terminate_sync(struct hci_dev *hdev, void *data) static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle) { struct iso_list_data *d; + int ret; bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, sync_handle); @@ -867,8 +873,12 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, u16 sync_handle) d->big = big; d->sync_handle = sync_handle; - return hci_cmd_sync_queue(hdev, big_terminate_sync, d, - terminate_big_destroy); + ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, + terminate_big_destroy); + if (ret) + kfree(d); + + return ret; } /* Cleanup BIS connection diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 0594af4e37ca..ad92a4be5851 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3848,8 +3848,11 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, conn->handle, conn->link); /* Create CIS if LE is already connected */ - if (conn->link && conn->link->state == BT_CONNECTED) + if (conn->link && conn->link->state == BT_CONNECTED) { + rcu_read_unlock(); hci_le_create_cis(conn->link); + rcu_read_lock(); + } if (i == rp->num_handles) break; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 9e2d7e4b850c..117eedb6f709 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -3572,7 +3572,7 @@ static const struct hci_init_stage hci_init2[] = { static int hci_le_read_buffer_size_sync(struct hci_dev *hdev) { /* Use Read LE Buffer Size V2 if supported */ - if (hdev->commands[41] & 0x20) + if (iso_capable(hdev) && hdev->commands[41] & 0x20) return __hci_cmd_sync_status(hdev, HCI_OP_LE_READ_BUFFER_SIZE_V2, 0, NULL, HCI_CMD_TIMEOUT); @@ -3597,10 +3597,10 @@ static int hci_le_read_supported_states_sync(struct hci_dev *hdev) /* LE Controller init stage 2 command sequence */ static const struct hci_init_stage le_init2[] = { - /* HCI_OP_LE_READ_BUFFER_SIZE */ - HCI_INIT(hci_le_read_buffer_size_sync), /* HCI_OP_LE_READ_LOCAL_FEATURES */ HCI_INIT(hci_le_read_local_features_sync), + /* HCI_OP_LE_READ_BUFFER_SIZE */ + HCI_INIT(hci_le_read_buffer_size_sync), /* HCI_OP_LE_READ_SUPPORTED_STATES */ HCI_INIT(hci_le_read_supported_states_sync), {} @@ -6187,20 +6187,13 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy, static int _update_adv_data_sync(struct hci_dev *hdev, void *data) { - u8 instance = *(u8 *)data; - - kfree(data); + u8 instance = PTR_ERR(data); return hci_update_adv_data_sync(hdev, instance); } int hci_update_adv_data(struct hci_dev *hdev, u8 instance) { - u8 *inst_ptr = kmalloc(1, GFP_KERNEL); - - if (!inst_ptr) - return -ENOMEM; - - *inst_ptr = instance; - return hci_cmd_sync_queue(hdev, _update_adv_data_sync, inst_ptr, NULL); + return hci_cmd_sync_queue(hdev, _update_adv_data_sync, + ERR_PTR(instance), NULL); } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 035bb5d25f85..24444b502e58 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -289,15 +289,15 @@ static int iso_connect_bis(struct sock *sk) hci_dev_unlock(hdev); hci_dev_put(hdev); + err = iso_chan_add(conn, sk, NULL); + if (err) + return err; + lock_sock(sk); /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); - err = iso_chan_add(conn, sk, NULL); - if (err) - goto release; - if (hcon->state == BT_CONNECTED) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; @@ -306,7 +306,6 @@ static int iso_connect_bis(struct sock *sk) iso_sock_set_timer(sk, sk->sk_sndtimeo); } -release: release_sock(sk); return err; @@ -372,15 +371,15 @@ static int iso_connect_cis(struct sock *sk) hci_dev_unlock(hdev); hci_dev_put(hdev); + err = iso_chan_add(conn, sk, NULL); + if (err) + return err; + lock_sock(sk); /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); - err = iso_chan_add(conn, sk, NULL); - if (err) - goto release; - if (hcon->state == BT_CONNECTED) { iso_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; @@ -392,7 +391,6 @@ static int iso_connect_cis(struct sock *sk) iso_sock_set_timer(sk, sk->sk_sndtimeo); } -release: release_sock(sk); return err; @@ -895,13 +893,10 @@ static int iso_listen_bis(struct sock *sk) if (!hdev) return -EHOSTUNREACH; - hci_dev_lock(hdev); - err = hci_pa_create_sync(hdev, &iso_pi(sk)->dst, le_addr_type(iso_pi(sk)->dst_type), iso_pi(sk)->bc_sid); - hci_dev_unlock(hdev); hci_dev_put(hdev); return err; @@ -1432,33 +1427,29 @@ static void iso_conn_ready(struct iso_conn *conn) struct sock *parent; struct sock *sk = conn->sk; struct hci_ev_le_big_sync_estabilished *ev; + struct hci_conn *hcon; BT_DBG("conn %p", conn); if (sk) { iso_sock_ready(conn->sk); } else { - iso_conn_lock(conn); - - if (!conn->hcon) { - iso_conn_unlock(conn); + hcon = conn->hcon; + if (!hcon) return; - } - ev = hci_recv_event_data(conn->hcon->hdev, + ev = hci_recv_event_data(hcon->hdev, HCI_EVT_LE_BIG_SYNC_ESTABILISHED); if (ev) - parent = iso_get_sock_listen(&conn->hcon->src, - &conn->hcon->dst, + parent = iso_get_sock_listen(&hcon->src, + &hcon->dst, iso_match_big, ev); else - parent = iso_get_sock_listen(&conn->hcon->src, + parent = iso_get_sock_listen(&hcon->src, BDADDR_ANY, NULL, NULL); - if (!parent) { - iso_conn_unlock(conn); + if (!parent) return; - } lock_sock(parent); @@ -1466,30 +1457,29 @@ static void iso_conn_ready(struct iso_conn *conn) BTPROTO_ISO, GFP_ATOMIC, 0); if (!sk) { release_sock(parent); - iso_conn_unlock(conn); return; } iso_sock_init(sk, parent); - bacpy(&iso_pi(sk)->src, &conn->hcon->src); - iso_pi(sk)->src_type = conn->hcon->src_type; + bacpy(&iso_pi(sk)->src, &hcon->src); + iso_pi(sk)->src_type = hcon->src_type; /* If hcon has no destination address (BDADDR_ANY) it means it * was created by HCI_EV_LE_BIG_SYNC_ESTABILISHED so we need to * initialize using the parent socket destination address. */ - if (!bacmp(&conn->hcon->dst, BDADDR_ANY)) { - bacpy(&conn->hcon->dst, &iso_pi(parent)->dst); - conn->hcon->dst_type = iso_pi(parent)->dst_type; - conn->hcon->sync_handle = iso_pi(parent)->sync_handle; + if (!bacmp(&hcon->dst, BDADDR_ANY)) { + bacpy(&hcon->dst, &iso_pi(parent)->dst); + hcon->dst_type = iso_pi(parent)->dst_type; + hcon->sync_handle = iso_pi(parent)->sync_handle; } - bacpy(&iso_pi(sk)->dst, &conn->hcon->dst); - iso_pi(sk)->dst_type = conn->hcon->dst_type; + bacpy(&iso_pi(sk)->dst, &hcon->dst); + iso_pi(sk)->dst_type = hcon->dst_type; - hci_conn_hold(conn->hcon); - __iso_chan_add(conn, sk, parent); + hci_conn_hold(hcon); + iso_chan_add(conn, sk, parent); if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) sk->sk_state = BT_CONNECT2; @@ -1500,8 +1490,6 @@ static void iso_conn_ready(struct iso_conn *conn) parent->sk_data_ready(parent); release_sock(parent); - - iso_conn_unlock(conn); } } diff --git a/net/bluetooth/mgmt_util.h b/net/bluetooth/mgmt_util.h index 6a8b7e84293d..bdf978605d5a 100644 --- a/net/bluetooth/mgmt_util.h +++ b/net/bluetooth/mgmt_util.h @@ -27,7 +27,7 @@ struct mgmt_mesh_tx { struct sock *sk; u8 handle; u8 instance; - u8 param[sizeof(struct mgmt_cp_mesh_send) + 29]; + u8 param[sizeof(struct mgmt_cp_mesh_send) + 31]; }; struct mgmt_pending_cmd { diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 21e24da4847f..4397e14ff560 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -391,6 +391,7 @@ static int rfcomm_sock_connect(struct socket *sock, struct sockaddr *addr, int a addr->sa_family != AF_BLUETOOTH) return -EINVAL; + sock_hold(sk); lock_sock(sk); if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { @@ -410,14 +411,18 @@ static int rfcomm_sock_connect(struct socket *sock, struct sockaddr *addr, int a d->sec_level = rfcomm_pi(sk)->sec_level; d->role_switch = rfcomm_pi(sk)->role_switch; + /* Drop sock lock to avoid potential deadlock with the RFCOMM lock */ + release_sock(sk); err = rfcomm_dlc_open(d, &rfcomm_pi(sk)->src, &sa->rc_bdaddr, sa->rc_channel); - if (!err) + lock_sock(sk); + if (!err && !sock_flag(sk, SOCK_ZAPPED)) err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); done: release_sock(sk); + sock_put(sk); return err; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index f20f4373ff40..9554abcfd5b4 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -871,6 +871,7 @@ static unsigned int ip_sabotage_in(void *priv, if (nf_bridge && !nf_bridge->in_prerouting && !netif_is_l3_master(skb->dev) && !netif_is_l3_slave(skb->dev)) { + nf_bridge_info_free(skb); state->okfn(state->net, state->sk, skb); return NF_STOLEN; } diff --git a/net/can/isotp.c b/net/can/isotp.c index 608f8c24ae46..fc81d77724a1 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -140,7 +140,7 @@ struct isotp_sock { canid_t rxid; ktime_t tx_gap; ktime_t lastrxcf_tstamp; - struct hrtimer rxtimer, txtimer; + struct hrtimer rxtimer, txtimer, txfrtimer; struct can_isotp_options opt; struct can_isotp_fc_options rxfc, txfc; struct can_isotp_ll_options ll; @@ -871,7 +871,7 @@ static void isotp_rcv_echo(struct sk_buff *skb, void *data) } /* start timer to send next consecutive frame with correct delay */ - hrtimer_start(&so->txtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); + hrtimer_start(&so->txfrtimer, so->tx_gap, HRTIMER_MODE_REL_SOFT); } static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) @@ -879,49 +879,39 @@ static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer) struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, txtimer); struct sock *sk = &so->sk; - enum hrtimer_restart restart = HRTIMER_NORESTART; - switch (so->tx.state) { - case ISOTP_SENDING: - - /* cfecho should be consumed by isotp_rcv_echo() here */ - if (!so->cfecho) { - /* start timeout for unlikely lost echo skb */ - hrtimer_set_expires(&so->txtimer, - ktime_add(ktime_get(), - ktime_set(ISOTP_ECHO_TIMEOUT, 0))); - restart = HRTIMER_RESTART; + /* don't handle timeouts in IDLE state */ + if (so->tx.state == ISOTP_IDLE) + return HRTIMER_NORESTART; - /* push out the next consecutive frame */ - isotp_send_cframe(so); - break; - } + /* we did not get any flow control or echo frame in time */ - /* cfecho has not been cleared in isotp_rcv_echo() */ - pr_notice_once("can-isotp: cfecho %08X timeout\n", so->cfecho); - fallthrough; + /* report 'communication error on send' */ + sk->sk_err = ECOMM; + if (!sock_flag(sk, SOCK_DEAD)) + sk_error_report(sk); - case ISOTP_WAIT_FC: - case ISOTP_WAIT_FIRST_FC: + /* reset tx state */ + so->tx.state = ISOTP_IDLE; + wake_up_interruptible(&so->wait); - /* we did not get any flow control frame in time */ + return HRTIMER_NORESTART; +} - /* report 'communication error on send' */ - sk->sk_err = ECOMM; - if (!sock_flag(sk, SOCK_DEAD)) - sk_error_report(sk); +static enum hrtimer_restart isotp_txfr_timer_handler(struct hrtimer *hrtimer) +{ + struct isotp_sock *so = container_of(hrtimer, struct isotp_sock, + txfrtimer); - /* reset tx state */ - so->tx.state = ISOTP_IDLE; - wake_up_interruptible(&so->wait); - break; + /* start echo timeout handling and cover below protocol error */ + hrtimer_start(&so->txtimer, ktime_set(ISOTP_ECHO_TIMEOUT, 0), + HRTIMER_MODE_REL_SOFT); - default: - WARN_ONCE(1, "can-isotp: tx timer state %08X cfecho %08X\n", - so->tx.state, so->cfecho); - } + /* cfecho should be consumed by isotp_rcv_echo() here */ + if (so->tx.state == ISOTP_SENDING && !so->cfecho) + isotp_send_cframe(so); - return restart; + return HRTIMER_NORESTART; } static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) @@ -1162,6 +1152,10 @@ static int isotp_release(struct socket *sock) /* wait for complete transmission of current pdu */ wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE); + /* force state machines to be idle also when a signal occurred */ + so->tx.state = ISOTP_IDLE; + so->rx.state = ISOTP_IDLE; + spin_lock(&isotp_notifier_lock); while (isotp_busy_notifier == so) { spin_unlock(&isotp_notifier_lock); @@ -1194,6 +1188,7 @@ static int isotp_release(struct socket *sock) } } + hrtimer_cancel(&so->txfrtimer); hrtimer_cancel(&so->txtimer); hrtimer_cancel(&so->rxtimer); @@ -1597,6 +1592,8 @@ static int isotp_init(struct sock *sk) so->rxtimer.function = isotp_rx_timer_handler; hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); so->txtimer.function = isotp_tx_timer_handler; + hrtimer_init(&so->txfrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT); + so->txfrtimer.function = isotp_txfr_timer_handler; init_waitqueue_head(&so->wait); spin_lock_init(&so->rx_lock); diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c index 5c722b55fe23..fce9b9ebf13f 100644 --- a/net/can/j1939/transport.c +++ b/net/can/j1939/transport.c @@ -1092,10 +1092,6 @@ static bool j1939_session_deactivate(struct j1939_session *session) bool active; j1939_session_list_lock(priv); - /* This function should be called with a session ref-count of at - * least 2. - */ - WARN_ON_ONCE(kref_read(&session->kref) < 2); active = j1939_session_deactivate_locked(session); j1939_session_list_unlock(priv); diff --git a/net/can/raw.c b/net/can/raw.c index 81071cdb0301..ba86782ba8bb 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -132,8 +132,8 @@ static void raw_rcv(struct sk_buff *oskb, void *data) return; /* make sure to not pass oversized frames to the socket */ - if ((can_is_canfd_skb(oskb) && !ro->fd_frames && !ro->xl_frames) || - (can_is_canxl_skb(oskb) && !ro->xl_frames)) + if ((!ro->fd_frames && can_is_canfd_skb(oskb)) || + (!ro->xl_frames && can_is_canxl_skb(oskb))) return; /* eliminate multiple filter matches for the same skb */ @@ -670,6 +670,11 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (copy_from_sockptr(&ro->fd_frames, optval, optlen)) return -EFAULT; + /* Enabling CAN XL includes CAN FD */ + if (ro->xl_frames && !ro->fd_frames) { + ro->fd_frames = ro->xl_frames; + return -EINVAL; + } break; case CAN_RAW_XL_FRAMES: @@ -679,6 +684,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, if (copy_from_sockptr(&ro->xl_frames, optval, optlen)) return -EFAULT; + /* Enabling CAN XL includes CAN FD */ + if (ro->xl_frames) + ro->fd_frames = ro->xl_frames; break; case CAN_RAW_JOIN_FILTERS: @@ -786,6 +794,25 @@ static int raw_getsockopt(struct socket *sock, int level, int optname, return 0; } +static bool raw_bad_txframe(struct raw_sock *ro, struct sk_buff *skb, int mtu) +{ + /* Classical CAN -> no checks for flags and device capabilities */ + if (can_is_can_skb(skb)) + return false; + + /* CAN FD -> needs to be enabled and a CAN FD or CAN XL device */ + if (ro->fd_frames && can_is_canfd_skb(skb) && + (mtu == CANFD_MTU || can_is_canxl_dev_mtu(mtu))) + return false; + + /* CAN XL -> needs to be enabled and a CAN XL device */ + if (ro->xl_frames && can_is_canxl_skb(skb) && + can_is_canxl_dev_mtu(mtu)) + return false; + + return true; +} + static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) { struct sock *sk = sock->sk; @@ -833,20 +860,8 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) goto free_skb; err = -EINVAL; - if (ro->xl_frames && can_is_canxl_dev_mtu(dev->mtu)) { - /* CAN XL, CAN FD and Classical CAN */ - if (!can_is_canxl_skb(skb) && !can_is_canfd_skb(skb) && - !can_is_can_skb(skb)) - goto free_skb; - } else if (ro->fd_frames && dev->mtu == CANFD_MTU) { - /* CAN FD and Classical CAN */ - if (!can_is_canfd_skb(skb) && !can_is_can_skb(skb)) - goto free_skb; - } else { - /* Classical CAN */ - if (!can_is_can_skb(skb)) - goto free_skb; - } + if (raw_bad_txframe(ro, skb, dev->mtu)) + goto free_skb; sockcm_init(&sockc, sk); if (msg->msg_controllen) { diff --git a/net/core/gro.c b/net/core/gro.c index fd8c6a7e8d3e..4bac7ea6e025 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -162,6 +162,15 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb) struct sk_buff *lp; int segs; + /* Do not splice page pool based packets w/ non-page pool + * packets. This can result in reference count issues as page + * pool pages will not decrement the reference count and will + * instead be immediately returned to the pool or have frag + * count decremented. + */ + if (p->pp_recycle != skb->pp_recycle) + return -ETOOMANYREFS; + /* pairs with WRITE_ONCE() in netif_set_gro_max_size() */ gro_max_size = READ_ONCE(p->dev->gro_max_size); @@ -505,8 +514,9 @@ found_ptype: NAPI_GRO_CB(skb)->count = 1; if (unlikely(skb_is_gso(skb))) { NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs; - /* Only support TCP at the moment. */ - if (!skb_is_gso_tcp(skb)) + /* Only support TCP and non DODGY users. */ + if (!skb_is_gso_tcp(skb) || + (skb_shinfo(skb)->gso_type & SKB_GSO_DODGY)) NAPI_GRO_CB(skb)->flush = 1; } diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 5581d22cc191..078a0a420c8a 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -137,12 +137,12 @@ static int ops_init(const struct pernet_operations *ops, struct net *net) return 0; if (ops->id && ops->size) { -cleanup: ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; } +cleanup: kfree(data); out: diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 4a0eb5593275..a31ff4d83ecc 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4100,7 +4100,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, skb_shinfo(skb)->frag_list = NULL; - do { + while (list_skb) { nskb = list_skb; list_skb = list_skb->next; @@ -4146,8 +4146,7 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb, if (skb_needs_linearize(nskb, features) && __skb_linearize(nskb)) goto err_linearize; - - } while (list_skb); + } skb->truesize = skb->truesize - delta_truesize; skb->data_len = skb->data_len - delta_len; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 22fa2c5bc6ec..a68a7290a3b2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1569,15 +1569,16 @@ void sock_map_unhash(struct sock *sk) psock = sk_psock(sk); if (unlikely(!psock)) { rcu_read_unlock(); - if (sk->sk_prot->unhash) - sk->sk_prot->unhash(sk); - return; + saved_unhash = READ_ONCE(sk->sk_prot)->unhash; + } else { + saved_unhash = psock->saved_unhash; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); } - - saved_unhash = psock->saved_unhash; - sock_map_remove_links(sk, psock); - rcu_read_unlock(); - saved_unhash(sk); + if (WARN_ON_ONCE(saved_unhash == sock_map_unhash)) + return; + if (saved_unhash) + saved_unhash(sk); } EXPORT_SYMBOL_GPL(sock_map_unhash); @@ -1590,17 +1591,18 @@ void sock_map_destroy(struct sock *sk) psock = sk_psock_get(sk); if (unlikely(!psock)) { rcu_read_unlock(); - if (sk->sk_prot->destroy) - sk->sk_prot->destroy(sk); - return; + saved_destroy = READ_ONCE(sk->sk_prot)->destroy; + } else { + saved_destroy = psock->saved_destroy; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); + sk_psock_stop(psock); + sk_psock_put(sk, psock); } - - saved_destroy = psock->saved_destroy; - sock_map_remove_links(sk, psock); - rcu_read_unlock(); - sk_psock_stop(psock); - sk_psock_put(sk, psock); - saved_destroy(sk); + if (WARN_ON_ONCE(saved_destroy == sock_map_destroy)) + return; + if (saved_destroy) + saved_destroy(sk); } EXPORT_SYMBOL_GPL(sock_map_destroy); @@ -1615,16 +1617,21 @@ void sock_map_close(struct sock *sk, long timeout) if (unlikely(!psock)) { rcu_read_unlock(); release_sock(sk); - return sk->sk_prot->close(sk, timeout); + saved_close = READ_ONCE(sk->sk_prot)->close; + } else { + saved_close = psock->saved_close; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); + sk_psock_stop(psock); + release_sock(sk); + cancel_work_sync(&psock->work); + sk_psock_put(sk, psock); } - - saved_close = psock->saved_close; - sock_map_remove_links(sk, psock); - rcu_read_unlock(); - sk_psock_stop(psock); - release_sock(sk); - cancel_work_sync(&psock->work); - sk_psock_put(sk, psock); + /* Make sure we do not recurse. This is a bug. + * Leak the socket instead of crashing on a stack overflow. + */ + if (WARN_ON_ONCE(saved_close == sock_map_close)) + return; saved_close(sk, timeout); } EXPORT_SYMBOL_GPL(sock_map_close); diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c index ebe6145aed3f..be260ab34e58 100644 --- a/net/ethtool/rss.c +++ b/net/ethtool/rss.c @@ -122,10 +122,13 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, { const struct rss_reply_data *data = RSS_REPDATA(reply_base); - if (nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc) || - nla_put(skb, ETHTOOL_A_RSS_INDIR, - sizeof(u32) * data->indir_size, data->indir_table) || - nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey)) + if ((data->hfunc && + nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) || + (data->indir_size && + nla_put(skb, ETHTOOL_A_RSS_INDIR, + sizeof(u32) * data->indir_size, data->indir_table)) || + (data->hkey_size && + nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey))) return -EMSGSIZE; return 0; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ce9ff3c62e84..3bb890a40ed7 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -30,6 +30,7 @@ #include <linux/slab.h> #include <linux/netlink.h> #include <linux/hash.h> +#include <linux/nospec.h> #include <net/arp.h> #include <net/inet_dscp.h> @@ -1022,6 +1023,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) if (type > RTAX_MAX) return false; + type = array_index_nospec(type, RTAX_MAX + 1); if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX]; bool ecn_ca = false; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 24a38b56fab9..f58d73888638 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -650,8 +650,20 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_nulls_del_node_init_rcu(osk); - } else if (found_dup_sk) { + ret = sk_hashed(osk); + if (ret) { + /* Before deleting the node, we insert a new one to make + * sure that the look-up-sk process would not miss either + * of them and that at least one node would exist in ehash + * table all the time. Otherwise there's a tiny chance + * that lookup process could find nothing in ehash table. + */ + __sk_nulls_add_node_tail_rcu(sk, list); + sk_nulls_del_node_init_rcu(osk); + } + goto unlock; + } + if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -660,6 +672,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); +unlock: spin_unlock(lock); return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 1d77d992e6e7..beed32fff484 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -91,10 +91,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_head_rcu(&tw->tw_node, list); + hlist_nulls_add_tail_rcu(&tw->tw_node, list); } static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -147,7 +147,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); - inet_twsk_add_node_rcu(tw, &ehead->chain); + inet_twsk_add_node_tail_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c index 7fcfdfd8f9de..0e3ee1532848 100644 --- a/net/ipv4/metrics.c +++ b/net/ipv4/metrics.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/netlink.h> +#include <linux/nospec.h> #include <linux/rtnetlink.h> #include <linux/types.h> #include <net/ip.h> @@ -25,6 +26,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, return -EINVAL; } + type = array_index_nospec(type, RTAX_MAX + 1); if (type == RTAX_CC_ALGO) { char tmp[TCP_CA_NAME_MAX]; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c567d5e8053e..33f559f491c8 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -435,6 +435,7 @@ void tcp_init_sock(struct sock *sk) /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; + tp->rate_app_limited = 1; /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. @@ -3178,6 +3179,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->plb_rehash = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; + tp->rate_app_limited = 1; tp->rack.mstamp = 0; tp->rack.advanced = 0; tp->rack.reo_wnd_steps = 1; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 94aad3870c5f..cf26d65ca389 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -6,6 +6,7 @@ #include <linux/bpf.h> #include <linux/init.h> #include <linux/wait.h> +#include <linux/util_macros.h> #include <net/inet_common.h> #include <net/tls.h> @@ -639,10 +640,9 @@ EXPORT_SYMBOL_GPL(tcp_bpf_update_proto); */ void tcp_bpf_clone(const struct sock *sk, struct sock *newsk) { - int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; struct proto *prot = newsk->sk_prot; - if (prot == &tcp_bpf_prots[family][TCP_BPF_BASE]) + if (is_insidevar(prot, tcp_bpf_prots)) newsk->sk_prot = sk->sk_prot_creator; } #endif /* CONFIG_BPF_SYSCALL */ diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 05b6077b9f2c..2aa442128630 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -139,7 +139,7 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops) if (sk->sk_socket) clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); - err = -EINVAL; + err = -ENOTCONN; if (!ulp_ops->clone && sk->sk_state == TCP_LISTEN) goto out_err; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f7a84a4acffc..faa47f9ea73a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3127,17 +3127,17 @@ static void add_v4_addrs(struct inet6_dev *idev) offset = sizeof(struct in6_addr) - 4; memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4); - if (idev->dev->flags&IFF_POINTOPOINT) { + if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) { + scope = IPV6_ADDR_COMPATv4; + plen = 96; + pflags |= RTF_NONEXTHOP; + } else { if (idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_NONE) return; addr.s6_addr32[0] = htonl(0xfe800000); scope = IFA_LINK; plen = 64; - } else { - scope = IPV6_ADDR_COMPATv4; - plen = 96; - pflags |= RTF_NONEXTHOP; } if (addr.s6_addr32[3]) { @@ -3447,6 +3447,30 @@ static void addrconf_gre_config(struct net_device *dev) } #endif +static void addrconf_init_auto_addrs(struct net_device *dev) +{ + switch (dev->type) { +#if IS_ENABLED(CONFIG_IPV6_SIT) + case ARPHRD_SIT: + addrconf_sit_config(dev); + break; +#endif +#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) + case ARPHRD_IP6GRE: + case ARPHRD_IPGRE: + addrconf_gre_config(dev); + break; +#endif + case ARPHRD_LOOPBACK: + init_loopback(dev); + break; + + default: + addrconf_dev_config(dev); + break; + } +} + static int fixup_permanent_addr(struct net *net, struct inet6_dev *idev, struct inet6_ifaddr *ifp) @@ -3615,26 +3639,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, run_pending = 1; } - switch (dev->type) { -#if IS_ENABLED(CONFIG_IPV6_SIT) - case ARPHRD_SIT: - addrconf_sit_config(dev); - break; -#endif -#if IS_ENABLED(CONFIG_NET_IPGRE) || IS_ENABLED(CONFIG_IPV6_GRE) - case ARPHRD_IP6GRE: - case ARPHRD_IPGRE: - addrconf_gre_config(dev); - break; -#endif - case ARPHRD_LOOPBACK: - init_loopback(dev); - break; - - default: - addrconf_dev_config(dev); - break; - } + addrconf_init_auto_addrs(dev); if (!IS_ERR_OR_NULL(idev)) { if (run_pending) @@ -6397,7 +6402,7 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, if (idev->cnf.addr_gen_mode != new_val) { idev->cnf.addr_gen_mode = new_val; - addrconf_dev_config(idev->dev); + addrconf_init_auto_addrs(idev->dev); } } else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) { struct net_device *dev; @@ -6408,7 +6413,7 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write, if (idev && idev->cnf.addr_gen_mode != new_val) { idev->cnf.addr_gen_mode = new_val; - addrconf_dev_config(idev->dev); + addrconf_init_auto_addrs(idev->dev); } } } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 60fd91bb5171..c314fdde0097 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -547,7 +547,20 @@ int ip6_forward(struct sk_buff *skb) pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) { int proxied = ip6_forward_proxy_check(skb); if (proxied > 0) { - hdr->hop_limit--; + /* It's tempting to decrease the hop limit + * here by 1, as we do at the end of the + * function too. + * + * But that would be incorrect, as proxying is + * not forwarding. The ip6_input function + * will handle this packet locally, and it + * depends on the hop limit being unchanged. + * + * One example is the NDP hop limit, that + * always has to stay 255, but other would be + * similar checks around RA packets, where the + * user can even change the desired limit. + */ return ip6_input(skb); } else if (proxied < 0) { __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a06a9f847db5..ada087b50541 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -505,6 +505,7 @@ csum_copy_err: static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { + struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; @@ -522,6 +523,9 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; + opt = inet6_sk(sk)->cork.opt; + total_len -= opt ? opt->opt_flen : 0; + if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 9a1415fe3fa7..03608d3ded4b 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -104,9 +104,9 @@ static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ static unsigned int l2tp_net_id; struct l2tp_net { - struct list_head l2tp_tunnel_list; - /* Lock for write access to l2tp_tunnel_list */ - spinlock_t l2tp_tunnel_list_lock; + /* Lock for write access to l2tp_tunnel_idr */ + spinlock_t l2tp_tunnel_idr_lock; + struct idr l2tp_tunnel_idr; struct hlist_head l2tp_session_hlist[L2TP_HASH_SIZE_2]; /* Lock for write access to l2tp_session_hlist */ spinlock_t l2tp_session_hlist_lock; @@ -208,13 +208,10 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (tunnel->tunnel_id == tunnel_id && - refcount_inc_not_zero(&tunnel->ref_count)) { - rcu_read_unlock_bh(); - - return tunnel; - } + tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id); + if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) { + rcu_read_unlock_bh(); + return tunnel; } rcu_read_unlock_bh(); @@ -224,13 +221,14 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_get); struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) { - const struct l2tp_net *pn = l2tp_pernet(net); + struct l2tp_net *pn = l2tp_pernet(net); + unsigned long tunnel_id, tmp; struct l2tp_tunnel *tunnel; int count = 0; rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - if (++count > nth && + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel && ++count > nth && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; @@ -1043,7 +1041,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); - bh_lock_sock(sk); + bh_lock_sock_nested(sk); if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; @@ -1227,6 +1225,15 @@ static void l2tp_udp_encap_destroy(struct sock *sk) l2tp_tunnel_delete(tunnel); } +static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) +{ + struct l2tp_net *pn = l2tp_pernet(net); + + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); +} + /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { @@ -1234,7 +1241,6 @@ static void l2tp_tunnel_del_work(struct work_struct *work) del_work); struct sock *sk = tunnel->sock; struct socket *sock = sk->sk_socket; - struct l2tp_net *pn; l2tp_tunnel_closeall(tunnel); @@ -1248,12 +1254,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work) } } - /* Remove the tunnel struct from the tunnel list */ - pn = l2tp_pernet(tunnel->l2tp_net); - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_del_rcu(&tunnel->list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - + l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ l2tp_tunnel_dec_refcount(tunnel); @@ -1384,8 +1385,6 @@ out: return err; } -static struct lock_class_key l2tp_socket_class; - int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp) { @@ -1455,12 +1454,19 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net, int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg) { - struct l2tp_tunnel *tunnel_walk; - struct l2tp_net *pn; + struct l2tp_net *pn = l2tp_pernet(net); + u32 tunnel_id = tunnel->tunnel_id; struct socket *sock; struct sock *sk; int ret; + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id, + GFP_ATOMIC); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); + if (ret) + return ret == -ENOSPC ? -EEXIST : ret; + if (tunnel->fd < 0) { ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id, tunnel->peer_tunnel_id, cfg, @@ -1474,6 +1480,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, } sk = sock->sk; + lock_sock(sk); write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) @@ -1481,24 +1488,6 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, rcu_assign_sk_user_data(sk, tunnel); write_unlock_bh(&sk->sk_callback_lock); - tunnel->l2tp_net = net; - pn = l2tp_pernet(net); - - sock_hold(sk); - tunnel->sock = sk; - - spin_lock_bh(&pn->l2tp_tunnel_list_lock); - list_for_each_entry(tunnel_walk, &pn->l2tp_tunnel_list, list) { - if (tunnel_walk->tunnel_id == tunnel->tunnel_id) { - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - sock_put(sk); - ret = -EEXIST; - goto err_sock; - } - } - list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list); - spin_unlock_bh(&pn->l2tp_tunnel_list_lock); - if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { .sk_user_data = tunnel, @@ -1512,9 +1501,16 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; - lockdep_set_class_and_name(&sk->sk_lock.slock, &l2tp_socket_class, - "l2tp_sock"); sk->sk_allocation = GFP_ATOMIC; + release_sock(sk); + + sock_hold(sk); + tunnel->sock = sk; + tunnel->l2tp_net = net; + + spin_lock_bh(&pn->l2tp_tunnel_idr_lock); + idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id); + spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); trace_register_tunnel(tunnel); @@ -1523,17 +1519,16 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, return 0; -err_sock: - write_lock_bh(&sk->sk_callback_lock); - rcu_assign_sk_user_data(sk, NULL); err_inval_sock: write_unlock_bh(&sk->sk_callback_lock); + release_sock(sk); if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); err: + l2tp_tunnel_remove(net, tunnel); return ret; } EXPORT_SYMBOL_GPL(l2tp_tunnel_register); @@ -1647,8 +1642,8 @@ static __net_init int l2tp_init_net(struct net *net) struct l2tp_net *pn = net_generic(net, l2tp_net_id); int hash; - INIT_LIST_HEAD(&pn->l2tp_tunnel_list); - spin_lock_init(&pn->l2tp_tunnel_list_lock); + idr_init(&pn->l2tp_tunnel_idr); + spin_lock_init(&pn->l2tp_tunnel_idr_lock); for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) INIT_HLIST_HEAD(&pn->l2tp_session_hlist[hash]); @@ -1662,11 +1657,13 @@ static __net_exit void l2tp_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; + unsigned long tunnel_id, tmp; int hash; rcu_read_lock_bh(); - list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) { - l2tp_tunnel_delete(tunnel); + idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { + if (tunnel) + l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); @@ -1676,6 +1673,7 @@ static __net_exit void l2tp_exit_net(struct net *net) for (hash = 0; hash < L2TP_HASH_SIZE_2; hash++) WARN_ON_ONCE(!hlist_empty(&pn->l2tp_session_hlist[hash])); + idr_destroy(&pn->l2tp_tunnel_idr); } static struct pernet_operations l2tp_net_ops = { diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 9c40f8d3bce8..f9514bacbd4a 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -491,7 +491,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; struct ieee80211_local *local = sta->local; - struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_sub_if_data *sdata; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .action = IEEE80211_AMPDU_TX_START, @@ -511,8 +511,6 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ clear_bit(HT_AGG_STATE_WANT_START, &tid_tx->state); - ieee80211_agg_stop_txq(sta, tid); - /* * Make sure no packets are being processed. This ensures that * we have a valid starting sequence number and that in-flight @@ -521,6 +519,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ synchronize_net(); + sdata = sta->sdata; params.ssn = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, ¶ms); tid_tx->ssn = params.ssn; @@ -534,6 +533,9 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state); } else if (ret) { + if (!sdata) + return; + ht_dbg(sdata, "BA request denied - HW unavailable for %pM tid %d\n", sta->sta.addr, tid); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 8f9a2ab502b3..672eff6f5d32 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -147,6 +147,7 @@ static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata, link_conf->bssid_index = 0; link_conf->nontransmitted = false; link_conf->ema_ap = false; + link_conf->bssid_indicator = 0; if (sdata->vif.type != NL80211_IFTYPE_AP || !params.tx_wdev) return -EINVAL; @@ -1511,6 +1512,12 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, kfree(link_conf->ftmr_params); link_conf->ftmr_params = NULL; + sdata->vif.mbssid_tx_vif = NULL; + link_conf->bssid_index = 0; + link_conf->nontransmitted = false; + link_conf->ema_ap = false; + link_conf->bssid_indicator = 0; + __sta_info_flush(sdata, true); ieee80211_free_keys(sdata, true); diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 7a3d7893e19d..f1914bf39f0e 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -167,7 +167,7 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, continue; txqi = to_txq_info(sta->sta.txq[i]); p += scnprintf(p, bufsz + buf - p, - "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n", + "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s%s)\n", txqi->txq.tid, txqi->txq.ac, txqi->tin.backlog_bytes, @@ -182,7 +182,8 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, txqi->flags, test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ? "STOP" : "RUN", test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags) ? " AMPDU" : "", - test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : ""); + test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : "", + test_bit(IEEE80211_TXQ_DIRTY, &txqi->flags) ? " DIRTY" : ""); } rcu_read_unlock(); diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index d737db4e07e2..cfb09e4aed4d 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -392,6 +392,9 @@ int drv_ampdu_action(struct ieee80211_local *local, might_sleep(); + if (!sdata) + return -EIO; + sdata = get_bss_sdata(sdata); if (!check_sdata_in_driver(sdata)) return -EIO; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 809bad53e15b..5d13a3dfd366 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1199,7 +1199,7 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, /* In reconfig don't transmit now, but mark for waking later */ if (local->in_reconfig) { - set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txq->flags); + set_bit(IEEE80211_TXQ_DIRTY, &txq->flags); return; } diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 83bc41346ae7..5315ab750280 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -391,6 +391,37 @@ void ieee80211_ba_session_work(struct work_struct *work) tid_tx = sta->ampdu_mlme.tid_start_tx[tid]; if (!blocked && tid_tx) { + struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]); + struct ieee80211_sub_if_data *sdata = + vif_to_sdata(txqi->txq.vif); + struct fq *fq = &sdata->local->fq; + + spin_lock_bh(&fq->lock); + + /* Allow only frags to be dequeued */ + set_bit(IEEE80211_TXQ_STOP, &txqi->flags); + + if (!skb_queue_empty(&txqi->frags)) { + /* Fragmented Tx is ongoing, wait for it to + * finish. Reschedule worker to retry later. + */ + + spin_unlock_bh(&fq->lock); + spin_unlock_bh(&sta->lock); + + /* Give the task working on the txq a chance + * to send out the queued frags + */ + synchronize_net(); + + mutex_unlock(&sta->ampdu_mlme.mtx); + + ieee80211_queue_work(&sdata->local->hw, work); + return; + } + + spin_unlock_bh(&fq->lock); + /* * Assign it over to the normal tid_tx array * where it "goes live". diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 63ff0d2524b6..d16606e84e22 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -838,7 +838,7 @@ enum txq_info_flags { IEEE80211_TXQ_STOP, IEEE80211_TXQ_AMPDU, IEEE80211_TXQ_NO_AMSDU, - IEEE80211_TXQ_STOP_NETIF_TX, + IEEE80211_TXQ_DIRTY, }; /** diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d49a5906a943..23ed13f15067 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -364,7 +364,9 @@ static int ieee80211_check_concurrent_iface(struct ieee80211_sub_if_data *sdata, /* No support for VLAN with MLO yet */ if (iftype == NL80211_IFTYPE_AP_VLAN && - nsdata->wdev.use_4addr) + sdata->wdev.use_4addr && + nsdata->vif.type == NL80211_IFTYPE_AP && + nsdata->vif.valid_links) return -EOPNOTSUPP; /* @@ -2195,7 +2197,6 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ret = cfg80211_register_netdevice(ndev); if (ret) { - ieee80211_if_free(ndev); free_netdev(ndev); return ret; } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 7e3ab6e1b28f..c6562a6d2503 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4049,6 +4049,58 @@ static void ieee80211_invoke_rx_handlers(struct ieee80211_rx_data *rx) #undef CALL_RXH } +static bool +ieee80211_rx_is_valid_sta_link_id(struct ieee80211_sta *sta, u8 link_id) +{ + if (!sta->mlo) + return false; + + return !!(sta->valid_links & BIT(link_id)); +} + +static bool ieee80211_rx_data_set_link(struct ieee80211_rx_data *rx, + u8 link_id) +{ + rx->link_id = link_id; + rx->link = rcu_dereference(rx->sdata->link[link_id]); + + if (!rx->sta) + return rx->link; + + if (!ieee80211_rx_is_valid_sta_link_id(&rx->sta->sta, link_id)) + return false; + + rx->link_sta = rcu_dereference(rx->sta->link[link_id]); + + return rx->link && rx->link_sta; +} + +static bool ieee80211_rx_data_set_sta(struct ieee80211_rx_data *rx, + struct ieee80211_sta *pubsta, + int link_id) +{ + struct sta_info *sta; + + sta = container_of(pubsta, struct sta_info, sta); + + rx->link_id = link_id; + rx->sta = sta; + + if (sta) { + rx->local = sta->sdata->local; + if (!rx->sdata) + rx->sdata = sta->sdata; + rx->link_sta = &sta->deflink; + } + + if (link_id < 0) + rx->link = &rx->sdata->deflink; + else if (!ieee80211_rx_data_set_link(rx, link_id)) + return false; + + return true; +} + /* * This function makes calls into the RX path, therefore * it has to be invoked under RCU read lock. @@ -4057,16 +4109,19 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) { struct sk_buff_head frames; struct ieee80211_rx_data rx = { - .sta = sta, - .sdata = sta->sdata, - .local = sta->local, /* This is OK -- must be QoS data frame */ .security_idx = tid, .seqno_idx = tid, - .link_id = -1, }; struct tid_ampdu_rx *tid_agg_rx; - u8 link_id; + int link_id = -1; + + /* FIXME: statistics won't be right with this */ + if (sta->sta.valid_links) + link_id = ffs(sta->sta.valid_links) - 1; + + if (!ieee80211_rx_data_set_sta(&rx, &sta->sta, link_id)) + return; tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]); if (!tid_agg_rx) @@ -4086,10 +4141,6 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) }; drv_event_callback(rx.local, rx.sdata, &event); } - /* FIXME: statistics won't be right with this */ - link_id = sta->sta.valid_links ? ffs(sta->sta.valid_links) - 1 : 0; - rx.link = rcu_dereference(sta->sdata->link[link_id]); - rx.link_sta = rcu_dereference(sta->link[link_id]); ieee80211_rx_handlers(&rx, &frames); } @@ -4105,7 +4156,6 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, /* This is OK -- must be QoS data frame */ .security_idx = tid, .seqno_idx = tid, - .link_id = -1, }; int i, diff; @@ -4116,10 +4166,8 @@ void ieee80211_mark_rx_ba_filtered_frames(struct ieee80211_sta *pubsta, u8 tid, sta = container_of(pubsta, struct sta_info, sta); - rx.sta = sta; - rx.sdata = sta->sdata; - rx.link = &rx.sdata->deflink; - rx.local = sta->local; + if (!ieee80211_rx_data_set_sta(&rx, pubsta, -1)) + return; rcu_read_lock(); tid_agg_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[tid]); @@ -4506,15 +4554,6 @@ void ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata) mutex_unlock(&local->sta_mtx); } -static bool -ieee80211_rx_is_valid_sta_link_id(struct ieee80211_sta *sta, u8 link_id) -{ - if (!sta->mlo) - return false; - - return !!(sta->valid_links & BIT(link_id)); -} - static void ieee80211_rx_8023(struct ieee80211_rx_data *rx, struct ieee80211_fast_rx *fast_rx, int orig_len) @@ -4625,7 +4664,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, struct sk_buff *skb = rx->skb; struct ieee80211_hdr *hdr = (void *)skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - struct sta_info *sta = rx->sta; int orig_len = skb->len; int hdrlen = ieee80211_hdrlen(hdr->frame_control); int snap_offs = hdrlen; @@ -4637,7 +4675,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, u8 da[ETH_ALEN]; u8 sa[ETH_ALEN]; } addrs __aligned(2); - struct link_sta_info *link_sta; struct ieee80211_sta_rx_stats *stats; /* for parallel-rx, we need to have DUP_VALIDATED, otherwise we write @@ -4740,18 +4777,10 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, drop: dev_kfree_skb(skb); - if (rx->link_id >= 0) { - link_sta = rcu_dereference(sta->link[rx->link_id]); - if (!link_sta) - return true; - } else { - link_sta = &sta->deflink; - } - if (fast_rx->uses_rss) - stats = this_cpu_ptr(link_sta->pcpu_rx_stats); + stats = this_cpu_ptr(rx->link_sta->pcpu_rx_stats); else - stats = &link_sta->rx_stats; + stats = &rx->link_sta->rx_stats; stats->dropped++; return true; @@ -4769,8 +4798,8 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, struct ieee80211_local *local = rx->local; struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_hdr *hdr = (void *)skb->data; - struct link_sta_info *link_sta = NULL; - struct ieee80211_link_data *link; + struct link_sta_info *link_sta = rx->link_sta; + struct ieee80211_link_data *link = rx->link; rx->skb = skb; @@ -4792,35 +4821,6 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, if (!ieee80211_accept_frame(rx)) return false; - if (rx->link_id >= 0) { - link = rcu_dereference(rx->sdata->link[rx->link_id]); - - /* we might race link removal */ - if (!link) - return true; - rx->link = link; - - if (rx->sta) { - rx->link_sta = - rcu_dereference(rx->sta->link[rx->link_id]); - if (!rx->link_sta) - return true; - } - } else { - if (rx->sta) - rx->link_sta = &rx->sta->deflink; - - rx->link = &sdata->deflink; - } - - if (unlikely(!is_multicast_ether_addr(hdr->addr1) && - rx->link_id >= 0 && rx->sta && rx->sta->sta.mlo)) { - link_sta = rcu_dereference(rx->sta->link[rx->link_id]); - - if (WARN_ON_ONCE(!link_sta)) - return true; - } - if (!consume) { struct skb_shared_hwtstamps *shwt; @@ -4838,9 +4838,12 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, */ shwt = skb_hwtstamps(rx->skb); shwt->hwtstamp = skb_hwtstamps(skb)->hwtstamp; + + /* Update the hdr pointer to the new skb for translation below */ + hdr = (struct ieee80211_hdr *)rx->skb->data; } - if (unlikely(link_sta)) { + if (unlikely(rx->sta && rx->sta->sta.mlo)) { /* translate to MLD addresses */ if (ether_addr_equal(link->conf->addr, hdr->addr1)) ether_addr_copy(hdr->addr1, rx->sdata->vif.addr); @@ -4870,6 +4873,7 @@ static void __ieee80211_rx_handle_8023(struct ieee80211_hw *hw, struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_fast_rx *fast_rx; struct ieee80211_rx_data rx; + int link_id = -1; memset(&rx, 0, sizeof(rx)); rx.skb = skb; @@ -4886,12 +4890,8 @@ static void __ieee80211_rx_handle_8023(struct ieee80211_hw *hw, if (!pubsta) goto drop; - rx.sta = container_of(pubsta, struct sta_info, sta); - rx.sdata = rx.sta->sdata; - - if (status->link_valid && - !ieee80211_rx_is_valid_sta_link_id(pubsta, status->link_id)) - goto drop; + if (status->link_valid) + link_id = status->link_id; /* * TODO: Should the frame be dropped if the right link_id is not @@ -4900,19 +4900,8 @@ static void __ieee80211_rx_handle_8023(struct ieee80211_hw *hw, * link_id is used only for stats purpose and updating the stats on * the deflink is fine? */ - if (status->link_valid) - rx.link_id = status->link_id; - - if (rx.link_id >= 0) { - struct ieee80211_link_data *link; - - link = rcu_dereference(rx.sdata->link[rx.link_id]); - if (!link) - goto drop; - rx.link = link; - } else { - rx.link = &rx.sdata->deflink; - } + if (!ieee80211_rx_data_set_sta(&rx, pubsta, link_id)) + goto drop; fast_rx = rcu_dereference(rx.sta->fast_rx); if (!fast_rx) @@ -4930,6 +4919,8 @@ static bool ieee80211_rx_for_interface(struct ieee80211_rx_data *rx, { struct link_sta_info *link_sta; struct ieee80211_hdr *hdr = (void *)skb->data; + struct sta_info *sta; + int link_id = -1; /* * Look up link station first, in case there's a @@ -4939,24 +4930,19 @@ static bool ieee80211_rx_for_interface(struct ieee80211_rx_data *rx, */ link_sta = link_sta_info_get_bss(rx->sdata, hdr->addr2); if (link_sta) { - rx->sta = link_sta->sta; - rx->link_id = link_sta->link_id; + sta = link_sta->sta; + link_id = link_sta->link_id; } else { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); - rx->sta = sta_info_get_bss(rx->sdata, hdr->addr2); - if (rx->sta) { - if (status->link_valid && - !ieee80211_rx_is_valid_sta_link_id(&rx->sta->sta, - status->link_id)) - return false; - - rx->link_id = status->link_valid ? status->link_id : -1; - } else { - rx->link_id = -1; - } + sta = sta_info_get_bss(rx->sdata, hdr->addr2); + if (status->link_valid) + link_id = status->link_id; } + if (!ieee80211_rx_data_set_sta(rx, &sta->sta, link_id)) + return false; + return ieee80211_prepare_and_rx_handle(rx, skb, consume); } @@ -5015,19 +5001,15 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, if (ieee80211_is_data(fc)) { struct sta_info *sta, *prev_sta; - u8 link_id = status->link_id; + int link_id = -1; - if (pubsta) { - rx.sta = container_of(pubsta, struct sta_info, sta); - rx.sdata = rx.sta->sdata; + if (status->link_valid) + link_id = status->link_id; - if (status->link_valid && - !ieee80211_rx_is_valid_sta_link_id(pubsta, link_id)) + if (pubsta) { + if (!ieee80211_rx_data_set_sta(&rx, pubsta, link_id)) goto out; - if (status->link_valid) - rx.link_id = status->link_id; - /* * In MLO connection, fetch the link_id using addr2 * when the driver does not pass link_id in status. @@ -5045,7 +5027,7 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, if (!link_sta) goto out; - rx.link_id = link_sta->link_id; + ieee80211_rx_data_set_link(&rx, link_sta->link_id); } if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) @@ -5061,30 +5043,27 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw, continue; } - if ((status->link_valid && - !ieee80211_rx_is_valid_sta_link_id(&prev_sta->sta, - link_id)) || - (!status->link_valid && prev_sta->sta.mlo)) + rx.sdata = prev_sta->sdata; + if (!ieee80211_rx_data_set_sta(&rx, &prev_sta->sta, + link_id)) + goto out; + + if (!status->link_valid && prev_sta->sta.mlo) continue; - rx.link_id = status->link_valid ? link_id : -1; - rx.sta = prev_sta; - rx.sdata = prev_sta->sdata; ieee80211_prepare_and_rx_handle(&rx, skb, false); prev_sta = sta; } if (prev_sta) { - if ((status->link_valid && - !ieee80211_rx_is_valid_sta_link_id(&prev_sta->sta, - link_id)) || - (!status->link_valid && prev_sta->sta.mlo)) + rx.sdata = prev_sta->sdata; + if (!ieee80211_rx_data_set_sta(&rx, &prev_sta->sta, + link_id)) goto out; - rx.link_id = status->link_valid ? link_id : -1; - rx.sta = prev_sta; - rx.sdata = prev_sta->sdata; + if (!status->link_valid && prev_sta->sta.mlo) + goto out; if (ieee80211_prepare_and_rx_handle(&rx, skb, true)) return; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 2171cd1ca807..defe97a31724 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1129,7 +1129,6 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, struct sk_buff *purge_skb = NULL; if (test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) { - info->flags |= IEEE80211_TX_CTL_AMPDU; reset_agg_timer = true; } else if (test_bit(HT_AGG_STATE_WANT_START, &tid_tx->state)) { /* @@ -1161,7 +1160,6 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx, if (!tid_tx) { /* do nothing, let packet pass through */ } else if (test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) { - info->flags |= IEEE80211_TX_CTL_AMPDU; reset_agg_timer = true; } else { queued = true; @@ -3677,8 +3675,7 @@ static void __ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, info->band = fast_tx->band; info->control.vif = &sdata->vif; info->flags = IEEE80211_TX_CTL_FIRST_FRAGMENT | - IEEE80211_TX_CTL_DONTFRAG | - (ampdu ? IEEE80211_TX_CTL_AMPDU : 0); + IEEE80211_TX_CTL_DONTFRAG; info->control.flags = IEEE80211_TX_CTRL_FAST_XMIT | u32_encode_bits(IEEE80211_LINK_UNSPECIFIED, IEEE80211_TX_CTRL_MLO_LINK); @@ -3783,6 +3780,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_tx_data tx; ieee80211_tx_result r; struct ieee80211_vif *vif = txq->vif; + int q = vif->hw_queue[txq->ac]; + bool q_stopped; WARN_ON_ONCE(softirq_count() == 0); @@ -3790,17 +3789,18 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, return NULL; begin: - spin_lock_bh(&fq->lock); - - if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags) || - test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags)) - goto out; + spin_lock(&local->queue_stop_reason_lock); + q_stopped = local->queue_stop_reasons[q]; + spin_unlock(&local->queue_stop_reason_lock); - if (vif->txqs_stopped[txq->ac]) { - set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags); - goto out; + if (unlikely(q_stopped)) { + /* mark for waking later */ + set_bit(IEEE80211_TXQ_DIRTY, &txqi->flags); + return NULL; } + spin_lock_bh(&fq->lock); + /* Make sure fragments stay together. */ skb = __skb_dequeue(&txqi->frags); if (unlikely(skb)) { @@ -3810,6 +3810,9 @@ begin: IEEE80211_SKB_CB(skb)->control.flags &= ~IEEE80211_TX_INTCFL_NEED_TXPROCESSING; } else { + if (unlikely(test_bit(IEEE80211_TXQ_STOP, &txqi->flags))) + goto out; + skb = fq_tin_dequeue(fq, tin, fq_tin_dequeue_func); } @@ -3860,9 +3863,8 @@ begin: } if (test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags)) - info->flags |= IEEE80211_TX_CTL_AMPDU; - else - info->flags &= ~IEEE80211_TX_CTL_AMPDU; + info->flags |= (IEEE80211_TX_CTL_AMPDU | + IEEE80211_TX_CTL_DONTFRAG); if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) { if (!ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { @@ -4596,8 +4598,6 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, info = IEEE80211_SKB_CB(skb); memset(info, 0, sizeof(*info)); - if (tid_tx) - info->flags |= IEEE80211_TX_CTL_AMPDU; info->hw_queue = sdata->vif.hw_queue[queue]; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 6f5407038459..261ac667887f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -292,22 +292,12 @@ static void wake_tx_push_queue(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct ieee80211_txq *queue) { - int q = sdata->vif.hw_queue[queue->ac]; struct ieee80211_tx_control control = { .sta = queue->sta, }; struct sk_buff *skb; - unsigned long flags; - bool q_stopped; while (1) { - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - q_stopped = local->queue_stop_reasons[q]; - spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); - - if (q_stopped) - break; - skb = ieee80211_tx_dequeue(&local->hw, queue); if (!skb) break; @@ -347,8 +337,6 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) local_bh_disable(); spin_lock(&fq->lock); - sdata->vif.txqs_stopped[ac] = false; - if (!test_bit(SDATA_STATE_RUNNING, &sdata->state)) goto out; @@ -370,7 +358,7 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) if (ac != txq->ac) continue; - if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, + if (!test_and_clear_bit(IEEE80211_TXQ_DIRTY, &txqi->flags)) continue; @@ -385,7 +373,7 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) txqi = to_txq_info(vif->txq); - if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags) || + if (!test_and_clear_bit(IEEE80211_TXQ_DIRTY, &txqi->flags) || (ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac) goto out; @@ -517,8 +505,6 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, bool refcounted) { struct ieee80211_local *local = hw_to_local(hw); - struct ieee80211_sub_if_data *sdata; - int n_acs = IEEE80211_NUM_ACS; trace_stop_queue(local, queue, reason); @@ -530,29 +516,7 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, else local->q_stop_reasons[queue][reason]++; - if (__test_and_set_bit(reason, &local->queue_stop_reasons[queue])) - return; - - if (local->hw.queues < IEEE80211_NUM_ACS) - n_acs = 1; - - rcu_read_lock(); - list_for_each_entry_rcu(sdata, &local->interfaces, list) { - int ac; - - if (!sdata->dev) - continue; - - for (ac = 0; ac < n_acs; ac++) { - if (sdata->vif.hw_queue[ac] == queue || - sdata->vif.cab_queue == queue) { - spin_lock(&local->fq.lock); - sdata->vif.txqs_stopped[ac] = true; - spin_unlock(&local->fq.lock); - } - } - } - rcu_read_unlock(); + set_bit(reason, &local->queue_stop_reasons[queue]); } void ieee80211_stop_queue_by_reason(struct ieee80211_hw *hw, int queue, diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c index c2aae2a6d6a6..97bb4401dd3e 100644 --- a/net/mac802154/rx.c +++ b/net/mac802154/rx.c @@ -213,7 +213,6 @@ __ieee802154_rx_handle_packet(struct ieee802154_local *local, ret = ieee802154_parse_frame_start(skb, &hdr); if (ret) { pr_debug("got invalid frame\n"); - kfree_skb(skb); return; } diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index fc9e728b6333..3150f3f0c872 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -544,9 +544,6 @@ static int mctp_sk_init(struct sock *sk) static void mctp_sk_close(struct sock *sk, long timeout) { - struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); - - del_timer_sync(&msk->key_expiry); sk_common_release(sk); } @@ -580,7 +577,19 @@ static void mctp_sk_unhash(struct sock *sk) spin_lock_irqsave(&key->lock, fl2); __mctp_key_remove(key, net, fl2, MCTP_TRACE_KEY_CLOSED); } + sock_set_flag(sk, SOCK_DEAD); spin_unlock_irqrestore(&net->mctp.keys_lock, flags); + + /* Since there are no more tag allocations (we have removed all of the + * keys), stop any pending expiry events. the timer cannot be re-queued + * as the sk is no longer observable + */ + del_timer_sync(&msk->key_expiry); +} + +static void mctp_sk_destruct(struct sock *sk) +{ + skb_queue_purge(&sk->sk_receive_queue); } static struct proto mctp_proto = { @@ -619,6 +628,7 @@ static int mctp_pf_create(struct net *net, struct socket *sock, return -ENOMEM; sock_init_data(sock, sk); + sk->sk_destruct = mctp_sk_destruct; rc = 0; if (sk->sk_prot->init) diff --git a/net/mctp/route.c b/net/mctp/route.c index f9a80b82dc51..f51a05ec7162 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -147,6 +147,7 @@ static struct mctp_sk_key *mctp_key_alloc(struct mctp_sock *msk, key->valid = true; spin_lock_init(&key->lock); refcount_set(&key->refs, 1); + sock_hold(key->sk); return key; } @@ -165,6 +166,7 @@ void mctp_key_unref(struct mctp_sk_key *key) mctp_dev_release_key(key->dev, key); spin_unlock_irqrestore(&key->lock, flags); + sock_put(key->sk); kfree(key); } @@ -177,6 +179,11 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk) spin_lock_irqsave(&net->mctp.keys_lock, flags); + if (sock_flag(&msk->sk, SOCK_DEAD)) { + rc = -EINVAL; + goto out_unlock; + } + hlist_for_each_entry(tmp, &net->mctp.keys, hlist) { if (mctp_key_match(tmp, key->local_addr, key->peer_addr, key->tag)) { @@ -198,6 +205,7 @@ static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk) hlist_add_head(&key->sklist, &msk->keys); } +out_unlock: spin_unlock_irqrestore(&net->mctp.keys_lock, flags); return rc; @@ -315,8 +323,8 @@ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb) static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) { + struct mctp_sk_key *key, *any_key = NULL; struct net *net = dev_net(skb->dev); - struct mctp_sk_key *key; struct mctp_sock *msk; struct mctp_hdr *mh; unsigned long f; @@ -361,13 +369,11 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * key for reassembly - we'll create a more specific * one for future packets if required (ie, !EOM). */ - key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f); - if (key) { - msk = container_of(key->sk, + any_key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY, &f); + if (any_key) { + msk = container_of(any_key->sk, struct mctp_sock, sk); - spin_unlock_irqrestore(&key->lock, f); - mctp_key_unref(key); - key = NULL; + spin_unlock_irqrestore(&any_key->lock, f); } } @@ -419,14 +425,14 @@ static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb) * this function. */ rc = mctp_key_add(key, msk); - if (rc) { - kfree(key); - } else { + if (!rc) trace_mctp_key_acquire(key); - /* we don't need to release key->lock on exit */ - mctp_key_unref(key); - } + /* we don't need to release key->lock on exit, so + * clean up here and suppress the unlock via + * setting to NULL + */ + mctp_key_unref(key); key = NULL; } else { @@ -473,6 +479,8 @@ out_unlock: spin_unlock_irqrestore(&key->lock, f); mctp_key_unref(key); } + if (any_key) + mctp_key_unref(any_key); out: if (rc) kfree_skb(skb); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 45e2a48397b9..70f0ced3ca86 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -420,6 +420,31 @@ void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) } } +/* if sk is ipv4 or ipv6_only allows only same-family local and remote addresses, + * otherwise allow any matching local/remote pair + */ +bool mptcp_pm_addr_families_match(const struct sock *sk, + const struct mptcp_addr_info *loc, + const struct mptcp_addr_info *rem) +{ + bool mptcp_is_v4 = sk->sk_family == AF_INET; + +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + bool loc_is_v4 = loc->family == AF_INET || ipv6_addr_v4mapped(&loc->addr6); + bool rem_is_v4 = rem->family == AF_INET || ipv6_addr_v4mapped(&rem->addr6); + + if (mptcp_is_v4) + return loc_is_v4 && rem_is_v4; + + if (ipv6_only_sock(sk)) + return !loc_is_v4 && !rem_is_v4; + + return loc_is_v4 == rem_is_v4; +#else + return mptcp_is_v4 && loc->family == AF_INET && rem->family == AF_INET; +#endif +} + void mptcp_pm_data_reset(struct mptcp_sock *msk) { u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk)); diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 65dcc55a8ad8..ea6ad9da7493 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -294,6 +294,13 @@ int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) } sk = (struct sock *)msk; + + if (!mptcp_pm_addr_families_match(sk, &addr_l, &addr_r)) { + GENL_SET_ERR_MSG(info, "families mismatch"); + err = -EINVAL; + goto create_err; + } + lock_sock(sk); err = __mptcp_subflow_connect(sk, &addr_l, &addr_r); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b7ad030dfe89..8cd6cc67c2c5 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -98,7 +98,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) struct socket *ssock; int err; - err = mptcp_subflow_create_socket(sk, &ssock); + err = mptcp_subflow_create_socket(sk, sk->sk_family, &ssock); if (err) return err; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index a0d1658ce59e..601469249da8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -641,7 +641,8 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a, /* called with sk socket lock held */ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, const struct mptcp_addr_info *remote); -int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock); +int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, + struct socket **new_sock); void mptcp_info2sockaddr(const struct mptcp_addr_info *info, struct sockaddr_storage *addr, unsigned short family); @@ -776,6 +777,9 @@ int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info, int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info, bool require_family, struct mptcp_pm_addr_entry *entry); +bool mptcp_pm_addr_families_match(const struct sock *sk, + const struct mptcp_addr_info *loc, + const struct mptcp_addr_info *rem); void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk); void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk); void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index bd387d4b5a38..ec54413fb31f 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1547,7 +1547,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, if (!mptcp_is_fully_established(sk)) goto err_out; - err = mptcp_subflow_create_socket(sk, &sf); + err = mptcp_subflow_create_socket(sk, loc->family, &sf); if (err) goto err_out; @@ -1660,7 +1660,9 @@ static void mptcp_subflow_ops_undo_override(struct sock *ssk) #endif ssk->sk_prot = &tcp_prot; } -int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) + +int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, + struct socket **new_sock) { struct mptcp_subflow_context *subflow; struct net *net = sock_net(sk); @@ -1673,8 +1675,7 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock) if (unlikely(!sk->sk_socket)) return -EINVAL; - err = sock_create_kern(net, sk->sk_family, SOCK_STREAM, IPPROTO_TCP, - &sf); + err = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP, &sf); if (err) return err; diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index a8ce04a4bb72..e4fa00abde6a 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -308,8 +308,8 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], return -IPSET_ERR_BITMAP_RANGE; pr_debug("mask_bits %u, netmask %u\n", mask_bits, netmask); - hosts = 2 << (32 - netmask - 1); - elements = 2 << (netmask - mask_bits - 1); + hosts = 2U << (32 - netmask - 1); + elements = 2UL << (netmask - mask_bits - 1); } if (elements > IPSET_BITMAP_MAX_RANGE + 1) return -IPSET_ERR_BITMAP_RANGE_SIZE; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index d88b92a8ffca..011d414038ea 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -27,22 +27,16 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_timeout.h> -/* FIXME: Examine ipfilter's timeouts and conntrack transitions more - closely. They're more complex. --RR - - And so for me for SCTP :D -Kiran */ - static const char *const sctp_conntrack_names[] = { - "NONE", - "CLOSED", - "COOKIE_WAIT", - "COOKIE_ECHOED", - "ESTABLISHED", - "SHUTDOWN_SENT", - "SHUTDOWN_RECD", - "SHUTDOWN_ACK_SENT", - "HEARTBEAT_SENT", - "HEARTBEAT_ACKED", + [SCTP_CONNTRACK_NONE] = "NONE", + [SCTP_CONNTRACK_CLOSED] = "CLOSED", + [SCTP_CONNTRACK_COOKIE_WAIT] = "COOKIE_WAIT", + [SCTP_CONNTRACK_COOKIE_ECHOED] = "COOKIE_ECHOED", + [SCTP_CONNTRACK_ESTABLISHED] = "ESTABLISHED", + [SCTP_CONNTRACK_SHUTDOWN_SENT] = "SHUTDOWN_SENT", + [SCTP_CONNTRACK_SHUTDOWN_RECD] = "SHUTDOWN_RECD", + [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = "SHUTDOWN_ACK_SENT", + [SCTP_CONNTRACK_HEARTBEAT_SENT] = "HEARTBEAT_SENT", }; #define SECS * HZ @@ -54,13 +48,11 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_CLOSED] = 10 SECS, [SCTP_CONNTRACK_COOKIE_WAIT] = 3 SECS, [SCTP_CONNTRACK_COOKIE_ECHOED] = 3 SECS, - [SCTP_CONNTRACK_ESTABLISHED] = 5 DAYS, + [SCTP_CONNTRACK_ESTABLISHED] = 210 SECS, [SCTP_CONNTRACK_SHUTDOWN_SENT] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_RECD] = 300 SECS / 1000, [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, - [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, - [SCTP_CONNTRACK_DATA_SENT] = 30 SECS, }; #define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 @@ -74,8 +66,6 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { #define sSR SCTP_CONNTRACK_SHUTDOWN_RECD #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sHS SCTP_CONNTRACK_HEARTBEAT_SENT -#define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED -#define sDS SCTP_CONNTRACK_DATA_SENT #define sIV SCTP_CONNTRACK_MAX /* @@ -98,10 +88,6 @@ SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. -HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK/DATA/SACK in the direction - opposite to that of the HEARTBEAT/DATA chunk. Secondary connection - is established. -DATA_SENT - We have seen a DATA/SACK in a new flow. */ /* TODO @@ -115,38 +101,36 @@ cookie echoed to closed. */ /* SCTP conntrack state transitions */ -static const u8 sctp_conntracks[2][12][SCTP_CONNTRACK_MAX] = { +static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA, sCW}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS, sCL}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA, sSA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA, sCL}, -/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, -/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, -/* data/sack */ {sDS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL, sIV}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR, sIV}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA, sIV}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA, sIV}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA, sIV}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA, sIV}, -/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sHA}, -/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, -/* data/sack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sES}, } }; @@ -158,6 +142,7 @@ static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct) } #endif +/* do_basic_checks ensures sch->length > 0, do not use before */ #define for_each_sctp_chunk(skb, sch, _sch, offset, dataoff, count) \ for ((offset) = (dataoff) + sizeof(struct sctphdr), (count) = 0; \ (offset) < (skb)->len && \ @@ -258,11 +243,6 @@ static int sctp_new_state(enum ip_conntrack_dir dir, pr_debug("SCTP_CID_HEARTBEAT_ACK"); i = 10; break; - case SCTP_CID_DATA: - case SCTP_CID_SACK: - pr_debug("SCTP_CID_DATA/SACK"); - i = 11; - break; default: /* Other chunks like DATA or SACK do not change the state */ pr_debug("Unknown chunk type, Will stay in %s\n", @@ -316,9 +296,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, ih->init_tag); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag; - } else if (sch->type == SCTP_CID_HEARTBEAT || - sch->type == SCTP_CID_DATA || - sch->type == SCTP_CID_SACK) { + } else if (sch->type == SCTP_CID_HEARTBEAT) { pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; @@ -404,19 +382,19 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, if (!sctp_new(ct, skb, sh, dataoff)) return -NF_ACCEPT; - } else { - /* Check the verification tag (Sec 8.5) */ - if (!test_bit(SCTP_CID_INIT, map) && - !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && - !test_bit(SCTP_CID_COOKIE_ECHO, map) && - !test_bit(SCTP_CID_ABORT, map) && - !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && - !test_bit(SCTP_CID_HEARTBEAT, map) && - !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && - sh->vtag != ct->proto.sctp.vtag[dir]) { - pr_debug("Verification tag check failed\n"); - goto out; - } + } + + /* Check the verification tag (Sec 8.5) */ + if (!test_bit(SCTP_CID_INIT, map) && + !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && + !test_bit(SCTP_CID_COOKIE_ECHO, map) && + !test_bit(SCTP_CID_ABORT, map) && + !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && + !test_bit(SCTP_CID_HEARTBEAT, map) && + !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && + sh->vtag != ct->proto.sctp.vtag[dir]) { + pr_debug("Verification tag check failed\n"); + goto out; } old_state = new_state = SCTP_CONNTRACK_NONE; @@ -424,22 +402,29 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Special cases of Verification tag check (Sec 8.5.1) */ if (sch->type == SCTP_CID_INIT) { - /* Sec 8.5.1 (A) */ + /* (A) vtag MUST be zero */ if (sh->vtag != 0) goto out_unlock; } else if (sch->type == SCTP_CID_ABORT) { - /* Sec 8.5.1 (B) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir]) + /* (B) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_SHUTDOWN_COMPLETE) { - /* Sec 8.5.1 (C) */ - if (sh->vtag != ct->proto.sctp.vtag[dir] && - sh->vtag != ct->proto.sctp.vtag[!dir] && - sch->flags & SCTP_CHUNK_FLAG_T) + /* (C) vtag MUST match own vtag if T flag is unset OR + * MUST match peer's vtag if T flag is set + */ + if ((!(sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[dir]) || + ((sch->flags & SCTP_CHUNK_FLAG_T) && + sh->vtag != ct->proto.sctp.vtag[!dir])) goto out_unlock; } else if (sch->type == SCTP_CID_COOKIE_ECHO) { - /* Sec 8.5.1 (D) */ + /* (D) vtag must be same as init_vtag as found in INIT_ACK */ if (sh->vtag != ct->proto.sctp.vtag[dir]) goto out_unlock; } else if (sch->type == SCTP_CID_HEARTBEAT) { @@ -476,11 +461,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } - } else if (sch->type == SCTP_CID_DATA || sch->type == SCTP_CID_SACK) { - if (ct->proto.sctp.vtag[dir] == 0) { - pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir); - ct->proto.sctp.vtag[dir] = sh->vtag; - } } old_state = ct->proto.sctp.state; @@ -518,8 +498,12 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } ct->proto.sctp.state = new_state; - if (old_state != new_state) + if (old_state != new_state) { nf_conntrack_event_cache(IPCT_PROTOINFO, ct); + if (new_state == SCTP_CONNTRACK_ESTABLISHED && + !test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) + nf_conntrack_event_cache(IPCT_ASSURED, ct); + } } spin_unlock_bh(&ct->lock); @@ -533,14 +517,6 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]); - if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED && - dir == IP_CT_DIR_REPLY && - new_state == SCTP_CONNTRACK_ESTABLISHED) { - pr_debug("Setting assured bit\n"); - set_bit(IPS_ASSURED_BIT, &ct->status); - nf_conntrack_event_cache(IPCT_ASSURED, ct); - } - return NF_ACCEPT; out_unlock: @@ -701,7 +677,6 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, - [CTA_TIMEOUT_SCTP_DATA_SENT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 656631083177..3ac1af6f59fc 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1068,6 +1068,13 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, ct->proto.tcp.last_flags |= IP_CT_EXP_CHALLENGE_ACK; } + + /* possible challenge ack reply to syn */ + if (old_state == TCP_CONNTRACK_SYN_SENT && + index == TCP_ACK_SET && + dir == IP_CT_DIR_REPLY) + ct->proto.tcp.last_ack = ntohl(th->ack_seq); + spin_unlock_bh(&ct->lock); nf_ct_l4proto_log_invalid(skb, ct, state, "packet (index %d) in dir %d ignored, state %s", @@ -1193,6 +1200,14 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct, * segments we ignored. */ goto in_window; } + + /* Reset in response to a challenge-ack we let through earlier */ + if (old_state == TCP_CONNTRACK_SYN_SENT && + ct->proto.tcp.last_index == TCP_ACK_SET && + ct->proto.tcp.last_dir == IP_CT_DIR_REPLY && + ntohl(th->seq) == ct->proto.tcp.last_ack) + goto in_window; + break; default: /* Keep compilers happy. */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 0250725e38a4..460294bd4b60 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -601,8 +601,6 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, - NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED, - NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, @@ -887,18 +885,6 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { - .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT] = { - .procname = "nf_conntrack_sctp_timeout_data_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { @@ -1042,8 +1028,6 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, XASSIGN(SHUTDOWN_RECD, sn); XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); - XASSIGN(HEARTBEAT_ACKED, sn); - XASSIGN(DATA_SENT, sn); #undef XASSIGN #endif } diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 17b418a5a593..3a3c7746e88f 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -63,7 +63,7 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) return false; if (offset + len > VLAN_ETH_HLEN + vlan_hlen) - ethlen -= offset + len - VLAN_ETH_HLEN + vlan_hlen; + ethlen -= offset + len - VLAN_ETH_HLEN - vlan_hlen; memcpy(dst_u8, vlanh + offset - vlan_hlen, ethlen); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 7325bee7d144..19ea4d3c3553 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -38,10 +38,12 @@ static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) return !nft_rbtree_interval_end(rbe); } -static bool nft_rbtree_equal(const struct nft_set *set, const void *this, - const struct nft_rbtree_elem *interval) +static int nft_rbtree_cmp(const struct nft_set *set, + const struct nft_rbtree_elem *e1, + const struct nft_rbtree_elem *e2) { - return memcmp(this, nft_set_ext_key(&interval->ext), set->klen) == 0; + return memcmp(nft_set_ext_key(&e1->ext), nft_set_ext_key(&e2->ext), + set->klen); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, @@ -52,7 +54,6 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set const struct nft_rbtree_elem *rbe, *interval = NULL; u8 genmask = nft_genmask_cur(net); const struct rb_node *parent; - const void *this; int d; parent = rcu_dereference_raw(priv->root.rb_node); @@ -62,12 +63,11 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set rbe = rb_entry(parent, struct nft_rbtree_elem, node); - this = nft_set_ext_key(&rbe->ext); - d = memcmp(this, key, set->klen); + d = memcmp(nft_set_ext_key(&rbe->ext), key, set->klen); if (d < 0) { parent = rcu_dereference_raw(parent->rb_left); if (interval && - nft_rbtree_equal(set, this, interval) && + !nft_rbtree_cmp(set, rbe, interval) && nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; @@ -215,154 +215,216 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, return rbe; } +static int nft_rbtree_gc_elem(const struct nft_set *__set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) +{ + struct nft_set *set = (struct nft_set *)__set; + struct rb_node *prev = rb_prev(&rbe->node); + struct nft_rbtree_elem *rbe_prev; + struct nft_set_gc_batch *gcb; + + gcb = nft_set_gc_batch_check(set, NULL, GFP_ATOMIC); + if (!gcb) + return -ENOMEM; + + /* search for expired end interval coming before this element. */ + do { + rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); + if (nft_rbtree_interval_end(rbe_prev)) + break; + + prev = rb_prev(prev); + } while (prev != NULL); + + rb_erase(&rbe_prev->node, &priv->root); + rb_erase(&rbe->node, &priv->root); + atomic_sub(2, &set->nelems); + + nft_set_gc_batch_add(gcb, rbe); + nft_set_gc_batch_complete(gcb); + + return 0; +} + +static bool nft_rbtree_update_first(const struct nft_set *set, + struct nft_rbtree_elem *rbe, + struct rb_node *first) +{ + struct nft_rbtree_elem *first_elem; + + first_elem = rb_entry(first, struct nft_rbtree_elem, node); + /* this element is closest to where the new element is to be inserted: + * update the first element for the node list path. + */ + if (nft_rbtree_cmp(set, rbe, first_elem) < 0) + return true; + + return false; +} + static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, struct nft_set_ext **ext) { - bool overlap = false, dup_end_left = false, dup_end_right = false; + struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; + struct rb_node *node, *parent, **p, *first = NULL; struct nft_rbtree *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); - struct nft_rbtree_elem *rbe; - struct rb_node *parent, **p; - int d; + int d, err; - /* Detect overlaps as we descend the tree. Set the flag in these cases: - * - * a1. _ _ __>| ?_ _ __| (insert end before existing end) - * a2. _ _ ___| ?_ _ _>| (insert end after existing end) - * a3. _ _ ___? >|_ _ __| (insert start before existing end) - * - * and clear it later on, as we eventually reach the points indicated by - * '?' above, in the cases described below. We'll always meet these - * later, locally, due to tree ordering, and overlaps for the intervals - * that are the closest together are always evaluated last. - * - * b1. _ _ __>| !_ _ __| (insert end before existing start) - * b2. _ _ ___| !_ _ _>| (insert end after existing start) - * b3. _ _ ___! >|_ _ __| (insert start after existing end, as a leaf) - * '--' no nodes falling in this range - * b4. >|_ _ ! (insert start before existing start) - * - * Case a3. resolves to b3.: - * - if the inserted start element is the leftmost, because the '0' - * element in the tree serves as end element - * - otherwise, if an existing end is found immediately to the left. If - * there are existing nodes in between, we need to further descend the - * tree before we can conclude the new start isn't causing an overlap - * - * or to b4., which, preceded by a3., means we already traversed one or - * more existing intervals entirely, from the right. - * - * For a new, rightmost pair of elements, we'll hit cases b3. and b2., - * in that order. - * - * The flag is also cleared in two special cases: - * - * b5. |__ _ _!|<_ _ _ (insert start right before existing end) - * b6. |__ _ >|!__ _ _ (insert end right after existing start) - * - * which always happen as last step and imply that no further - * overlapping is possible. - * - * Another special case comes from the fact that start elements matching - * an already existing start element are allowed: insertion is not - * performed but we return -EEXIST in that case, and the error will be - * cleared by the caller if NLM_F_EXCL is not present in the request. - * This way, request for insertion of an exact overlap isn't reported as - * error to userspace if not desired. - * - * However, if the existing start matches a pre-existing start, but the - * end element doesn't match the corresponding pre-existing end element, - * we need to report a partial overlap. This is a local condition that - * can be noticed without need for a tracking flag, by checking for a - * local duplicated end for a corresponding start, from left and right, - * separately. + /* Descend the tree to search for an existing element greater than the + * key value to insert that is greater than the new element. This is the + * first element to walk the ordered elements to find possible overlap. */ - parent = NULL; p = &priv->root.rb_node; while (*p != NULL) { parent = *p; rbe = rb_entry(parent, struct nft_rbtree_elem, node); - d = memcmp(nft_set_ext_key(&rbe->ext), - nft_set_ext_key(&new->ext), - set->klen); + d = nft_rbtree_cmp(set, rbe, new); + if (d < 0) { p = &parent->rb_left; - - if (nft_rbtree_interval_start(new)) { - if (nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext) && !*p) - overlap = false; - } else { - if (dup_end_left && !*p) - return -ENOTEMPTY; - - overlap = nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, - genmask) && - !nft_set_elem_expired(&rbe->ext); - - if (overlap) { - dup_end_right = true; - continue; - } - } } else if (d > 0) { - p = &parent->rb_right; + if (!first || + nft_rbtree_update_first(set, rbe, first)) + first = &rbe->node; - if (nft_rbtree_interval_end(new)) { - if (dup_end_right && !*p) - return -ENOTEMPTY; - - overlap = nft_rbtree_interval_end(rbe) && - nft_set_elem_active(&rbe->ext, - genmask) && - !nft_set_elem_expired(&rbe->ext); - - if (overlap) { - dup_end_left = true; - continue; - } - } else if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) { - overlap = nft_rbtree_interval_end(rbe); - } + p = &parent->rb_right; } else { - if (nft_rbtree_interval_end(rbe) && - nft_rbtree_interval_start(new)) { + if (nft_rbtree_interval_end(rbe)) p = &parent->rb_left; - - if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) - overlap = false; - } else if (nft_rbtree_interval_start(rbe) && - nft_rbtree_interval_end(new)) { + else p = &parent->rb_right; + } + } + + if (!first) + first = rb_first(&priv->root); + + /* Detect overlap by going through the list of valid tree nodes. + * Values stored in the tree are in reversed order, starting from + * highest to lowest value. + */ + for (node = first; node != NULL; node = rb_next(node)) { + rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) - overlap = false; - } else if (nft_set_elem_active(&rbe->ext, genmask) && - !nft_set_elem_expired(&rbe->ext)) { - *ext = &rbe->ext; - return -EEXIST; - } else { - overlap = false; - if (nft_rbtree_interval_end(rbe)) - p = &parent->rb_left; - else - p = &parent->rb_right; + if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* perform garbage collection to avoid bogus overlap reports. */ + if (nft_set_elem_expired(&rbe->ext)) { + err = nft_rbtree_gc_elem(set, priv, rbe); + if (err < 0) + return err; + + continue; + } + + d = nft_rbtree_cmp(set, rbe, new); + if (d == 0) { + /* Matching end element: no need to look for an + * overlapping greater or equal element. + */ + if (nft_rbtree_interval_end(rbe)) { + rbe_le = rbe; + break; + } + + /* first element that is greater or equal to key value. */ + if (!rbe_ge) { + rbe_ge = rbe; + continue; + } + + /* this is a closer more or equal element, update it. */ + if (nft_rbtree_cmp(set, rbe_ge, new) != 0) { + rbe_ge = rbe; + continue; + } + + /* element is equal to key value, make sure flags are + * the same, an existing more or equal start element + * must not be replaced by more or equal end element. + */ + if ((nft_rbtree_interval_start(new) && + nft_rbtree_interval_start(rbe_ge)) || + (nft_rbtree_interval_end(new) && + nft_rbtree_interval_end(rbe_ge))) { + rbe_ge = rbe; + continue; } + } else if (d > 0) { + /* annotate element greater than the new element. */ + rbe_ge = rbe; + continue; + } else if (d < 0) { + /* annotate element less than the new element. */ + rbe_le = rbe; + break; } + } - dup_end_left = dup_end_right = false; + /* - new start element matching existing start element: full overlap + * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. + */ + if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && + nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { + *ext = &rbe_ge->ext; + return -EEXIST; } - if (overlap) + /* - new end element matching existing end element: full overlap + * reported as -EEXIST, cleared by caller if NLM_F_EXCL is not given. + */ + if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && + nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { + *ext = &rbe_le->ext; + return -EEXIST; + } + + /* - new start element with existing closest, less or equal key value + * being a start element: partial overlap, reported as -ENOTEMPTY. + * Anonymous sets allow for two consecutive start element since they + * are constant, skip them to avoid bogus overlap reports. + */ + if (!nft_set_is_anonymous(set) && rbe_le && + nft_rbtree_interval_start(rbe_le) && nft_rbtree_interval_start(new)) + return -ENOTEMPTY; + + /* - new end element with existing closest, less or equal key value + * being a end element: partial overlap, reported as -ENOTEMPTY. + */ + if (rbe_le && + nft_rbtree_interval_end(rbe_le) && nft_rbtree_interval_end(new)) return -ENOTEMPTY; + /* - new end element with existing closest, greater or equal key value + * being an end element: partial overlap, reported as -ENOTEMPTY + */ + if (rbe_ge && + nft_rbtree_interval_end(rbe_ge) && nft_rbtree_interval_end(new)) + return -ENOTEMPTY; + + /* Accepted element: pick insertion point depending on key value */ + parent = NULL; + p = &priv->root.rb_node; + while (*p != NULL) { + parent = *p; + rbe = rb_entry(parent, struct nft_rbtree_elem, node); + d = nft_rbtree_cmp(set, rbe, new); + + if (d < 0) + p = &parent->rb_left; + else if (d > 0) + p = &parent->rb_right; + else if (nft_rbtree_interval_end(rbe)) + p = &parent->rb_left; + else + p = &parent->rb_right; + } + rb_link_node_rcu(&new->node, parent, p); rb_insert_color(&new->node, &priv->root); return 0; @@ -501,23 +563,37 @@ static void nft_rbtree_gc(struct work_struct *work) struct nft_rbtree *priv; struct rb_node *node; struct nft_set *set; + struct net *net; + u8 genmask; priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); + net = read_pnet(&set->net); + genmask = nft_genmask_cur(net); write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { rbe = rb_entry(node, struct nft_rbtree_elem, node); + if (!nft_set_elem_active(&rbe->ext, genmask)) + continue; + + /* elements are reversed in the rbtree for historical reasons, + * from highest to lowest value, that is why end element is + * always visited before the start element. + */ if (nft_rbtree_interval_end(rbe)) { rbe_end = rbe; continue; } if (!nft_set_elem_expired(&rbe->ext)) continue; - if (nft_set_elem_mark_busy(&rbe->ext)) + + if (nft_set_elem_mark_busy(&rbe->ext)) { + rbe_end = NULL; continue; + } if (rbe_prev) { rb_erase(&rbe_prev->node, &priv->root); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index bca2a470ccad..c64277659753 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -580,7 +580,9 @@ static int netlink_insert(struct sock *sk, u32 portid) if (nlk_sk(sk)->bound) goto err; - nlk_sk(sk)->portid = portid; + /* portid can be read locklessly from netlink_getname(). */ + WRITE_ONCE(nlk_sk(sk)->portid, portid); + sock_hold(sk); err = __netlink_insert(table, sk); @@ -1096,9 +1098,11 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, return -EINVAL; if (addr->sa_family == AF_UNSPEC) { - sk->sk_state = NETLINK_UNCONNECTED; - nlk->dst_portid = 0; - nlk->dst_group = 0; + /* paired with READ_ONCE() in netlink_getsockbyportid() */ + WRITE_ONCE(sk->sk_state, NETLINK_UNCONNECTED); + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, 0); + WRITE_ONCE(nlk->dst_group, 0); return 0; } if (addr->sa_family != AF_NETLINK) @@ -1119,9 +1123,11 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, err = netlink_autobind(sock); if (err == 0) { - sk->sk_state = NETLINK_CONNECTED; - nlk->dst_portid = nladdr->nl_pid; - nlk->dst_group = ffs(nladdr->nl_groups); + /* paired with READ_ONCE() in netlink_getsockbyportid() */ + WRITE_ONCE(sk->sk_state, NETLINK_CONNECTED); + /* dst_portid and dst_group can be read locklessly */ + WRITE_ONCE(nlk->dst_portid, nladdr->nl_pid); + WRITE_ONCE(nlk->dst_group, ffs(nladdr->nl_groups)); } return err; @@ -1138,10 +1144,12 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, nladdr->nl_pad = 0; if (peer) { - nladdr->nl_pid = nlk->dst_portid; - nladdr->nl_groups = netlink_group_mask(nlk->dst_group); + /* Paired with WRITE_ONCE() in netlink_connect() */ + nladdr->nl_pid = READ_ONCE(nlk->dst_portid); + nladdr->nl_groups = netlink_group_mask(READ_ONCE(nlk->dst_group)); } else { - nladdr->nl_pid = nlk->portid; + /* Paired with WRITE_ONCE() in netlink_insert() */ + nladdr->nl_pid = READ_ONCE(nlk->portid); netlink_lock_table(); nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; netlink_unlock_table(); @@ -1168,8 +1176,9 @@ static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); - if (sock->sk_state == NETLINK_CONNECTED && - nlk->dst_portid != nlk_sk(ssk)->portid) { + /* dst_portid and sk_state can be changed in netlink_connect() */ + if (READ_ONCE(sock->sk_state) == NETLINK_CONNECTED && + READ_ONCE(nlk->dst_portid) != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } @@ -1886,8 +1895,9 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) goto out; netlink_skb_flags |= NETLINK_SKB_DST; } else { - dst_portid = nlk->dst_portid; - dst_group = nlk->dst_group; + /* Paired with WRITE_ONCE() in netlink_connect() */ + dst_portid = READ_ONCE(nlk->dst_portid); + dst_group = READ_ONCE(nlk->dst_group); } /* Paired with WRITE_ONCE() in netlink_insert() */ diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 6f7f4392cffb..5a4cb796150f 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -400,6 +400,11 @@ static int nr_listen(struct socket *sock, int backlog) struct sock *sk = sock->sk; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { memset(&nr_sk(sk)->user_addr, 0, AX25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index a8da88db7893..4e7c968cde2d 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -121,6 +121,7 @@ static void nr_heartbeat_expiry(struct timer_list *t) is accepted() it isn't 'dead' so doesn't get removed. */ if (sock_flag(sk, SOCK_DESTROY) || (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { + sock_hold(sk); bh_unlock_sock(sk); nr_destroy_socket(sk); goto out; diff --git a/net/nfc/llcp_core.c b/net/nfc/llcp_core.c index 3364caabef8b..a27e1842b2a0 100644 --- a/net/nfc/llcp_core.c +++ b/net/nfc/llcp_core.c @@ -157,6 +157,7 @@ static void local_cleanup(struct nfc_llcp_local *local) cancel_work_sync(&local->rx_work); cancel_work_sync(&local->timeout_work); kfree_skb(local->rx_pending); + local->rx_pending = NULL; del_timer_sync(&local->sdreq_timer); cancel_work_sync(&local->sdreq_timeout_work); nfc_llcp_free_sdp_tlv_list(&local->pending_sdreqs); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index a71795355aec..fcee6012293b 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -1004,14 +1004,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) key = kzalloc(sizeof(*key), GFP_KERNEL); if (!key) { error = -ENOMEM; - goto err_kfree_key; + goto err_kfree_flow; } ovs_match_init(&match, key, false, &mask); error = ovs_nla_get_match(net, &match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK], log); if (error) - goto err_kfree_flow; + goto err_kfree_key; ovs_flow_mask_key(&new_flow->key, key, true, &mask); @@ -1019,14 +1019,14 @@ static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) error = ovs_nla_get_identifier(&new_flow->id, a[OVS_FLOW_ATTR_UFID], key, log); if (error) - goto err_kfree_flow; + goto err_kfree_key; /* Validate actions. */ error = ovs_nla_copy_actions(net, a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, &acts, log); if (error) { OVS_NLERR(log, "Flow actions may not be safe on all matching packets."); - goto err_kfree_flow; + goto err_kfree_key; } reply = ovs_flow_cmd_alloc_info(acts, &new_flow->id, info, false, @@ -1126,10 +1126,10 @@ err_unlock_ovs: kfree_skb(reply); err_kfree_acts: ovs_nla_free_flow_actions(acts); -err_kfree_flow: - ovs_flow_free(new_flow, false); err_kfree_key: kfree(key); +err_kfree_flow: + ovs_flow_free(new_flow, false); error: return error; } diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 1990d496fcfc..e595079c2caf 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -83,7 +83,10 @@ static struct qrtr_node *node_get(unsigned int node_id) node->id = node_id; - radix_tree_insert(&nodes, node_id, node); + if (radix_tree_insert(&nodes, node_id, node)) { + kfree(node); + return NULL; + } return node; } diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 36fefc3957d7..ca2b17f32670 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -488,6 +488,12 @@ static int rose_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; + lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + release_sock(sk); + return -EINVAL; + } + if (sk->sk_state != TCP_LISTEN) { struct rose_sock *rose = rose_sk(sk); @@ -497,8 +503,10 @@ static int rose_listen(struct socket *sock, int backlog) memset(rose->dest_digis, 0, AX25_ADDR_LEN * ROSE_MAX_DIGIS); sk->sk_max_ack_backlog = backlog; sk->sk_state = TCP_LISTEN; + release_sock(sk); return 0; } + release_sock(sk); return -EOPNOTSUPP; } diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index e76d3459d78e..ac5caf5a48e1 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -10,6 +10,7 @@ rxrpc-y := \ call_accept.o \ call_event.o \ call_object.o \ + call_state.o \ conn_client.o \ conn_event.o \ conn_object.o \ diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 7ea576f6ba4b..ebbd4a1c3f86 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -155,10 +155,10 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) if (service_id) { write_lock(&local->services_lock); - if (rcu_access_pointer(local->service)) + if (local->service) goto service_in_use; rx->local = local; - rcu_assign_pointer(local->service, rx); + local->service = rx; write_unlock(&local->services_lock); rx->sk.sk_state = RXRPC_SERVER_BOUND; @@ -328,7 +328,6 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, mutex_unlock(&call->user_mutex); } - rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp); _leave(" = %p", call); return call; } @@ -374,13 +373,17 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call); * @sock: The socket the call is on * @call: The call to check * - * Allow a kernel service to find out whether a call is still alive - - * ie. whether it has completed. + * Allow a kernel service to find out whether a call is still alive - whether + * it has completed successfully and all received data has been consumed. */ bool rxrpc_kernel_check_life(const struct socket *sock, const struct rxrpc_call *call) { - return call->state != RXRPC_CALL_COMPLETE; + if (!rxrpc_call_is_complete(call)) + return true; + if (call->completion != RXRPC_CALL_SUCCEEDED) + return false; + return !skb_queue_empty(&call->recvmsg_queue); } EXPORT_SYMBOL(rxrpc_kernel_check_life); @@ -872,9 +875,9 @@ static int rxrpc_release_sock(struct sock *sk) sk->sk_state = RXRPC_CLOSE; - if (rx->local && rcu_access_pointer(rx->local->service) == rx) { + if (rx->local && rx->local->service == rx) { write_lock(&rx->local->services_lock); - rcu_assign_pointer(rx->local->service, NULL); + rx->local->service = NULL; write_unlock(&rx->local->services_lock); } @@ -957,16 +960,9 @@ static const struct net_proto_family rxrpc_family_ops = { static int __init af_rxrpc_init(void) { int ret = -1; - unsigned int tmp; BUILD_BUG_ON(sizeof(struct rxrpc_skb_priv) > sizeof_field(struct sk_buff, cb)); - get_random_bytes(&tmp, sizeof(tmp)); - tmp &= 0x3fffffff; - if (tmp == 0) - tmp = 1; - idr_set_cursor(&rxrpc_client_conn_ids, tmp); - ret = -ENOMEM; rxrpc_call_jar = kmem_cache_create( "rxrpc_call_jar", sizeof(struct rxrpc_call), 0, @@ -1062,7 +1058,6 @@ static void __exit af_rxrpc_exit(void) * are released. */ rcu_barrier(); - rxrpc_destroy_client_conn_ids(); destroy_workqueue(rxrpc_workqueue); rxrpc_exit_security(); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 18092526d3c8..433060cade03 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -38,6 +38,7 @@ struct rxrpc_txbuf; enum rxrpc_skb_mark { RXRPC_SKB_MARK_PACKET, /* Received packet */ RXRPC_SKB_MARK_ERROR, /* Error notification */ + RXRPC_SKB_MARK_SERVICE_CONN_SECURED, /* Service connection response has been verified */ RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */ }; @@ -75,13 +76,7 @@ struct rxrpc_net { bool live; - bool kill_all_client_conns; atomic_t nr_client_conns; - spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ - struct mutex client_conn_discard_lock; /* Prevent multiple discarders */ - struct list_head idle_client_conns; - struct work_struct client_conn_reaper; - struct timer_list client_conn_reap_timer; struct hlist_head local_endpoints; struct mutex local_mutex; /* Lock for ->local_endpoints */ @@ -202,6 +197,7 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { + struct rxrpc_connection *conn; /* Connection referred to (poke packet) */ u16 offset; /* Offset of data */ u16 len; /* Length of data */ u8 flags; @@ -262,13 +258,11 @@ struct rxrpc_security { /* respond to a challenge */ int (*respond_to_challenge)(struct rxrpc_connection *, - struct sk_buff *, - u32 *); + struct sk_buff *); /* verify a response */ int (*verify_response)(struct rxrpc_connection *, - struct sk_buff *, - u32 *); + struct sk_buff *); /* clear connection security */ void (*clear)(struct rxrpc_connection *); @@ -283,22 +277,34 @@ struct rxrpc_local { struct rcu_head rcu; atomic_t active_users; /* Number of users of the local endpoint */ refcount_t ref; /* Number of references to the structure */ - struct rxrpc_net *rxnet; /* The network ns in which this resides */ + struct net *net; /* The network namespace */ + struct rxrpc_net *rxnet; /* Our bits in the network namespace */ struct hlist_node link; struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; struct completion io_thread_ready; /* Indication that the I/O thread started */ - struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ + struct rxrpc_sock *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head rx_queue; /* Received packets */ + struct list_head conn_attend_q; /* Conns requiring immediate attention */ struct list_head call_attend_q; /* Calls requiring immediate attention */ + struct rb_root client_bundles; /* Client connection bundles by socket params */ spinlock_t client_bundles_lock; /* Lock for client_bundles */ + bool kill_all_client_conns; + struct list_head idle_client_conns; + struct timer_list client_conn_reap_timer; + unsigned long client_conn_flags; +#define RXRPC_CLIENT_CONN_REAP_TIMER 0 /* The client conn reap timer expired */ + spinlock_t lock; /* access lock */ rwlock_t services_lock; /* lock for services list */ int debug_id; /* debug ID for printks */ bool dead; bool service_closed; /* Service socket closed */ + struct idr conn_ids; /* List of connection IDs */ + struct list_head new_client_calls; /* Newly created client calls need connection */ + spinlock_t client_call_lock; /* Lock for ->new_client_calls */ struct sockaddr_rxrpc srx; /* local address */ }; @@ -356,7 +362,6 @@ struct rxrpc_conn_proto { struct rxrpc_conn_parameters { struct rxrpc_local *local; /* Representation of local endpoint */ - struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* Security details */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ @@ -365,10 +370,21 @@ struct rxrpc_conn_parameters { }; /* + * Call completion condition (state == RXRPC_CALL_COMPLETE). + */ +enum rxrpc_call_completion { + RXRPC_CALL_SUCCEEDED, /* - Normal termination */ + RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ + RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ + RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ + RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ + NR__RXRPC_CALL_COMPLETIONS +}; + +/* * Bits in the connection flags. */ enum rxrpc_conn_flag { - RXRPC_CONN_HAS_IDR, /* Has a client conn ID assigned */ RXRPC_CONN_IN_SERVICE_CONNS, /* Conn is in peer->service_conns */ RXRPC_CONN_DONT_REUSE, /* Don't reuse this connection */ RXRPC_CONN_PROBING_FOR_UPGRADE, /* Probing for service upgrade */ @@ -388,6 +404,7 @@ enum rxrpc_conn_flag { */ enum rxrpc_conn_event { RXRPC_CONN_EV_CHALLENGE, /* Send challenge packet */ + RXRPC_CONN_EV_ABORT_CALLS, /* Abort attached calls */ }; /* @@ -395,13 +412,13 @@ enum rxrpc_conn_event { */ enum rxrpc_conn_proto_state { RXRPC_CONN_UNUSED, /* Connection not yet attempted */ + RXRPC_CONN_CLIENT_UNSECURED, /* Client connection needs security init */ RXRPC_CONN_CLIENT, /* Client connection */ RXRPC_CONN_SERVICE_PREALLOC, /* Service connection preallocation */ RXRPC_CONN_SERVICE_UNSECURED, /* Service unsecured connection */ RXRPC_CONN_SERVICE_CHALLENGING, /* Service challenging for security */ RXRPC_CONN_SERVICE, /* Service secured connection */ - RXRPC_CONN_REMOTELY_ABORTED, /* Conn aborted by peer */ - RXRPC_CONN_LOCALLY_ABORTED, /* Conn aborted locally */ + RXRPC_CONN_ABORTED, /* Conn aborted */ RXRPC_CONN__NR_STATES }; @@ -412,17 +429,16 @@ struct rxrpc_bundle { struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ struct key *key; /* Security details */ + const struct rxrpc_security *security; /* applied security module */ refcount_t ref; atomic_t active; /* Number of active users */ unsigned int debug_id; u32 security_level; /* Security level selected */ u16 service_id; /* Service ID for this connection */ bool try_upgrade; /* True if the bundle is attempting upgrade */ - bool alloc_conn; /* True if someone's getting a conn */ bool exclusive; /* T if conn is exclusive */ bool upgrade; /* T if service ID can be upgraded */ - short alloc_error; /* Error from last conn allocation */ - spinlock_t channel_lock; + unsigned short alloc_error; /* Error from last conn allocation */ struct rb_node local_node; /* Node in local->client_conns */ struct list_head waiting_calls; /* Calls waiting for channels */ unsigned long avail_chans; /* Mask of available channels */ @@ -440,6 +456,7 @@ struct rxrpc_connection { struct rxrpc_peer *peer; /* Remote endpoint */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ struct key *key; /* Security details */ + struct list_head attend_link; /* Link in local->conn_attend_q */ refcount_t ref; atomic_t active; /* Active count for service conns */ @@ -449,7 +466,7 @@ struct rxrpc_connection { unsigned char act_chans; /* Mask of active channels */ struct rxrpc_channel { unsigned long final_ack_at; /* Time at which to issue final ACK */ - struct rxrpc_call __rcu *call; /* Active call */ + struct rxrpc_call *call; /* Active call */ unsigned int call_debug_id; /* call->debug_id */ u32 call_id; /* ID of current call */ u32 call_counter; /* Call ID counter */ @@ -470,6 +487,7 @@ struct rxrpc_connection { struct list_head link; /* link in master connection list */ struct sk_buff_head rx_queue; /* received conn-level packets */ + struct mutex security_lock; /* Lock for security management */ const struct rxrpc_security *security; /* applied security module */ union { struct { @@ -483,7 +501,8 @@ struct rxrpc_connection { unsigned long idle_timestamp; /* Time at which last became idle */ spinlock_t state_lock; /* state-change lock */ enum rxrpc_conn_proto_state state; /* current state of connection */ - u32 abort_code; /* Abort code of connection abort */ + enum rxrpc_call_completion completion; /* Completion condition */ + s32 abort_code; /* Abort code of connection abort */ int debug_id; /* debug ID for printks */ atomic_t serial; /* packet serial number counter */ unsigned int hi_serial; /* highest serial number received */ @@ -527,7 +546,8 @@ enum rxrpc_call_flag { RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */ - RXRPC_CALL_RX_IS_IDLE, /* Reception is idle - send an ACK */ + RXRPC_CALL_RX_IS_IDLE, /* recvmsg() is idle - send an ACK */ + RXRPC_CALL_RECVMSG_READ_ALL, /* recvmsg() read all of the received data */ }; /* @@ -558,18 +578,6 @@ enum rxrpc_call_state { }; /* - * Call completion condition (state == RXRPC_CALL_COMPLETE). - */ -enum rxrpc_call_completion { - RXRPC_CALL_SUCCEEDED, /* - Normal termination */ - RXRPC_CALL_REMOTELY_ABORTED, /* - call aborted by peer */ - RXRPC_CALL_LOCALLY_ABORTED, /* - call aborted locally on error or close */ - RXRPC_CALL_LOCAL_ERROR, /* - call failed due to local error */ - RXRPC_CALL_NETWORK_ERROR, /* - call terminated by network error */ - NR__RXRPC_CALL_COMPLETIONS -}; - -/* * Call Tx congestion management modes. */ enum rxrpc_congest_mode { @@ -587,6 +595,7 @@ enum rxrpc_congest_mode { struct rxrpc_call { struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ + struct rxrpc_bundle *bundle; /* Connection bundle to use */ struct rxrpc_peer *peer; /* Peer record for remote address */ struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_sock __rcu *socket; /* socket responsible */ @@ -609,7 +618,7 @@ struct rxrpc_call { struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ - struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */ + struct list_head wait_link; /* Link in local->new_client_calls */ struct hlist_node error_link; /* link in error distribution list */ struct list_head accept_link; /* Link in rx->acceptq */ struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ @@ -623,10 +632,13 @@ struct rxrpc_call { unsigned long flags; unsigned long events; spinlock_t notify_lock; /* Kernel notification lock */ - rwlock_t state_lock; /* lock for state transition */ - u32 abort_code; /* Local/remote abort code */ + unsigned int send_abort_why; /* Why the abort [enum rxrpc_abort_reason] */ + s32 send_abort; /* Abort code to be sent */ + short send_abort_err; /* Error to be associated with the abort */ + rxrpc_seq_t send_abort_seq; /* DATA packet that incurred the abort (or 0) */ + s32 abort_code; /* Local/remote abort code */ int error; /* Local error incurred */ - enum rxrpc_call_state state; /* current state of call */ + enum rxrpc_call_state _state; /* Current state of call (needs barrier) */ enum rxrpc_call_completion completion; /* Call completion condition */ refcount_t ref; u8 security_ix; /* Security type */ @@ -812,9 +824,11 @@ extern struct workqueue_struct *rxrpc_workqueue; */ int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); -int rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_peer *, - struct rxrpc_connection *, struct sockaddr_rxrpc *, - struct sk_buff *); +bool rxrpc_new_incoming_call(struct rxrpc_local *local, + struct rxrpc_peer *peer, + struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb); void rxrpc_accept_incoming_calls(struct rxrpc_local *); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); @@ -834,7 +848,7 @@ void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long now, enum rxrpc_timer_trace why); -void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); +bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); /* * call_object.c @@ -851,6 +865,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, struct sockaddr_rxrpc *, struct rxrpc_call_params *, gfp_t, unsigned int); +void rxrpc_start_call_timer(struct rxrpc_call *call); void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); @@ -873,32 +888,88 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call) } /* + * call_state.c + */ +bool rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error); +bool rxrpc_call_completed(struct rxrpc_call *call); +bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why); +void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl, + int error); + +static inline void rxrpc_set_call_state(struct rxrpc_call *call, + enum rxrpc_call_state state) +{ + /* Order write of completion info before write of ->state. */ + smp_store_release(&call->_state, state); + wake_up(&call->waitq); +} + +static inline enum rxrpc_call_state __rxrpc_call_state(const struct rxrpc_call *call) +{ + return call->_state; /* Only inside I/O thread */ +} + +static inline bool __rxrpc_call_is_complete(const struct rxrpc_call *call) +{ + return __rxrpc_call_state(call) == RXRPC_CALL_COMPLETE; +} + +static inline enum rxrpc_call_state rxrpc_call_state(const struct rxrpc_call *call) +{ + /* Order read ->state before read of completion info. */ + return smp_load_acquire(&call->_state); +} + +static inline bool rxrpc_call_is_complete(const struct rxrpc_call *call) +{ + return rxrpc_call_state(call) == RXRPC_CALL_COMPLETE; +} + +static inline bool rxrpc_call_has_failed(const struct rxrpc_call *call) +{ + return rxrpc_call_is_complete(call) && call->completion != RXRPC_CALL_SUCCEEDED; +} + +/* * conn_client.c */ extern unsigned int rxrpc_reap_client_connections; extern unsigned long rxrpc_conn_idle_client_expiry; extern unsigned long rxrpc_conn_idle_client_fast_expiry; -extern struct idr rxrpc_client_conn_ids; -void rxrpc_destroy_client_conn_ids(void); +void rxrpc_purge_client_connections(struct rxrpc_local *local); struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); -int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, - struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, - gfp_t); +int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp); +void rxrpc_connect_client_calls(struct rxrpc_local *local); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); +void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); -void rxrpc_discard_expired_client_conns(struct work_struct *); -void rxrpc_destroy_all_client_connections(struct rxrpc_net *); +void rxrpc_discard_expired_client_conns(struct rxrpc_local *local); void rxrpc_clean_up_local_conns(struct rxrpc_local *); /* * conn_event.c */ +void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, struct sk_buff *skb, + unsigned int channel); +int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, + s32 abort_code, int err, enum rxrpc_abort_reason why); void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); -int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); +bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); +void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb); + +static inline bool rxrpc_is_conn_aborted(const struct rxrpc_connection *conn) +{ + /* Order reading the abort info after the state check. */ + return smp_load_acquire(&conn->state) == RXRPC_CONN_ABORTED; +} /* * conn_object.c @@ -906,6 +977,7 @@ int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); extern unsigned int rxrpc_connection_expiry; extern unsigned int rxrpc_closed_conn_expiry; +void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why); struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t); struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *, struct sockaddr_rxrpc *, @@ -961,12 +1033,19 @@ void rxrpc_implicit_end_call(struct rxrpc_call *, struct sk_buff *); */ int rxrpc_encap_rcv(struct sock *, struct sk_buff *); void rxrpc_error_report(struct sock *); +bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, + s32 abort_code, int err); int rxrpc_io_thread(void *data); static inline void rxrpc_wake_up_io_thread(struct rxrpc_local *local) { wake_up_process(local->io_thread); } +static inline bool rxrpc_protocol_error(struct sk_buff *skb, enum rxrpc_abort_reason why) +{ + return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EPROTO); +} + /* * insecure.c */ @@ -1048,6 +1127,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); +void rxrpc_send_conn_abort(struct rxrpc_connection *conn); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb); @@ -1063,12 +1143,11 @@ void rxrpc_peer_keepalive_worker(struct work_struct *); */ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); -struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *, - struct sockaddr_rxrpc *, gfp_t); +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, + struct sockaddr_rxrpc *srx, gfp_t gfp); struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t, enum rxrpc_peer_trace); -void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *, - struct rxrpc_peer *); +void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer); void rxrpc_destroy_all_peers(struct rxrpc_net *); struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *, enum rxrpc_peer_trace); @@ -1086,33 +1165,22 @@ extern const struct seq_operations rxrpc_local_seq_ops; * recvmsg.c */ void rxrpc_notify_socket(struct rxrpc_call *); -bool __rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int); -bool rxrpc_set_call_completion(struct rxrpc_call *, enum rxrpc_call_completion, u32, int); -bool __rxrpc_call_completed(struct rxrpc_call *); -bool rxrpc_call_completed(struct rxrpc_call *); -bool __rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int); -bool rxrpc_abort_call(const char *, struct rxrpc_call *, rxrpc_seq_t, u32, int); int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* * Abort a call due to a protocol error. */ -static inline bool __rxrpc_abort_eproto(struct rxrpc_call *call, - struct sk_buff *skb, - const char *eproto_why, - const char *why, - u32 abort_code) +static inline int rxrpc_abort_eproto(struct rxrpc_call *call, + struct sk_buff *skb, + s32 abort_code, + enum rxrpc_abort_reason why) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - trace_rxrpc_rx_eproto(call, sp->hdr.serial, eproto_why); - return rxrpc_abort_call(why, call, sp->hdr.seq, abort_code, -EPROTO); + rxrpc_abort_call(call, sp->hdr.seq, abort_code, -EPROTO, why); + return -EPROTO; } -#define rxrpc_abort_eproto(call, skb, eproto_why, abort_why, abort_code) \ - __rxrpc_abort_eproto((call), (skb), tracepoint_string(eproto_why), \ - (abort_why), (abort_code)) - /* * rtt.c */ @@ -1144,6 +1212,8 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *, /* * sendmsg.c */ +bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, + enum rxrpc_abort_reason why); int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t); /* diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index c02401656fa9..3e8689fdc437 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -99,7 +99,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, if (!call) return -ENOMEM; call->flags |= (1 << RXRPC_CALL_IS_SERVICE); - call->state = RXRPC_CALL_SERVER_PREALLOC; + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_PREALLOC); __set_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events); trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), @@ -280,7 +280,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, (peer_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); - rxrpc_new_incoming_peer(rx, local, peer); + rxrpc_new_incoming_peer(local, peer); } /* Now allocate and set up the connection */ @@ -326,11 +326,11 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, * If we want to report an error, we mark the skb with the packet type and * abort code and return false. */ -int rxrpc_new_incoming_call(struct rxrpc_local *local, - struct rxrpc_peer *peer, - struct rxrpc_connection *conn, - struct sockaddr_rxrpc *peer_srx, - struct sk_buff *skb) +bool rxrpc_new_incoming_call(struct rxrpc_local *local, + struct rxrpc_peer *peer, + struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb) { const struct rxrpc_security *sec = NULL; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -339,18 +339,17 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local, _enter(""); - /* Don't set up a call for anything other than the first DATA packet. */ - if (sp->hdr.seq != 1 || - sp->hdr.type != RXRPC_PACKET_TYPE_DATA) - return 0; /* Just discard */ + /* Don't set up a call for anything other than a DATA packet. */ + if (sp->hdr.type != RXRPC_PACKET_TYPE_DATA) + return rxrpc_protocol_error(skb, rxrpc_eproto_no_service_call); - rcu_read_lock(); + read_lock(&local->services_lock); /* Weed out packets to services we're not offering. Packets that would * begin a call are explicitly rejected and the rest are just * discarded. */ - rx = rcu_dereference(local->service); + rx = local->service; if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && sp->hdr.serviceId != rx->second_service) ) { @@ -363,16 +362,14 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local, if (!conn) { sec = rxrpc_get_incoming_security(rx, skb); if (!sec) - goto reject; + goto unsupported_security; } spin_lock(&rx->incoming_lock); if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED || rx->sk.sk_state == RXRPC_CLOSE) { - trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber, - sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN); - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; - skb->priority = RX_INVALID_OPERATION; + rxrpc_direct_abort(skb, rxrpc_abort_shut_down, + RX_INVALID_OPERATION, -ESHUTDOWN); goto no_call; } @@ -402,7 +399,7 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local, spin_unlock(&conn->state_lock); spin_unlock(&rx->incoming_lock); - rcu_read_unlock(); + read_unlock(&local->services_lock); if (hlist_unhashed(&call->error_link)) { spin_lock(&call->peer->lock); @@ -413,22 +410,24 @@ int rxrpc_new_incoming_call(struct rxrpc_local *local, _leave(" = %p{%d}", call, call->debug_id); rxrpc_input_call_event(call, skb); rxrpc_put_call(call, rxrpc_call_put_input); - return 0; + return true; unsupported_service: - trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EOPNOTSUPP); - skb->priority = RX_INVALID_OPERATION; - goto reject; + read_unlock(&local->services_lock); + return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, + RX_INVALID_OPERATION, -EOPNOTSUPP); +unsupported_security: + read_unlock(&local->services_lock); + return rxrpc_direct_abort(skb, rxrpc_abort_service_not_offered, + RX_INVALID_OPERATION, -EKEYREJECTED); no_call: spin_unlock(&rx->incoming_lock); -reject: - rcu_read_unlock(); + read_unlock(&local->services_lock); _leave(" = f [%u]", skb->mark); - return -EPROTO; + return false; discard: - rcu_read_unlock(); - return 0; + read_unlock(&local->services_lock); + return true; } /* diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index b2cf448fb02c..1abdef15debc 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -251,6 +251,41 @@ out: _leave(""); } +/* + * Start transmitting the reply to a service. This cancels the need to ACK the + * request if we haven't yet done so. + */ +static void rxrpc_begin_service_reply(struct rxrpc_call *call) +{ + unsigned long now = jiffies; + + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SEND_REPLY); + WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); + if (call->ackr_reason == RXRPC_ACK_DELAY) + call->ackr_reason = 0; + trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); +} + +/* + * Close the transmission phase. After this point there is no more data to be + * transmitted in the call. + */ +static void rxrpc_close_tx_phase(struct rxrpc_call *call) +{ + _debug("________awaiting reply/ACK__________"); + + switch (__rxrpc_call_state(call)) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY); + break; + case RXRPC_CALL_SERVER_SEND_REPLY: + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_AWAIT_ACK); + break; + default: + break; + } +} + static bool rxrpc_tx_window_has_space(struct rxrpc_call *call) { unsigned int winsize = min_t(unsigned int, call->tx_winsize, @@ -270,9 +305,11 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) { struct rxrpc_txbuf *txb; - if (rxrpc_is_client_call(call) && - !test_bit(RXRPC_CALL_EXPOSED, &call->flags)) + if (!test_bit(RXRPC_CALL_EXPOSED, &call->flags)) { + if (list_empty(&call->tx_sendmsg)) + return; rxrpc_expose_client_call(call); + } while ((txb = list_first_entry_or_null(&call->tx_sendmsg, struct rxrpc_txbuf, call_link))) { @@ -283,6 +320,9 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) call->tx_top = txb->seq; list_add_tail(&txb->call_link, &call->tx_buffer); + if (txb->wire.flags & RXRPC_LAST_PACKET) + rxrpc_close_tx_phase(call); + rxrpc_transmit_one(call, txb); if (!rxrpc_tx_window_has_space(call)) @@ -292,16 +332,15 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) static void rxrpc_transmit_some_data(struct rxrpc_call *call) { - switch (call->state) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_SERVER_ACK_REQUEST: if (list_empty(&call->tx_sendmsg)) return; + rxrpc_begin_service_reply(call); fallthrough; case RXRPC_CALL_SERVER_SEND_REPLY: - case RXRPC_CALL_SERVER_AWAIT_ACK: case RXRPC_CALL_CLIENT_SEND_REQUEST: - case RXRPC_CALL_CLIENT_AWAIT_REPLY: if (!rxrpc_tx_window_has_space(call)) return; if (list_empty(&call->tx_sendmsg)) { @@ -331,21 +370,31 @@ static void rxrpc_send_initial_ping(struct rxrpc_call *call) /* * Handle retransmission and deferred ACK/abort generation. */ -void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) +bool rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { unsigned long now, next, t; rxrpc_serial_t ackr_serial; bool resend = false, expired = false; + s32 abort_code; rxrpc_see_call(call, rxrpc_call_see_input); //printk("\n--------------------\n"); _enter("{%d,%s,%lx}", - call->debug_id, rxrpc_call_states[call->state], call->events); + call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)], + call->events); - if (call->state == RXRPC_CALL_COMPLETE) + if (__rxrpc_call_is_complete(call)) goto out; + /* Handle abort request locklessly, vs rxrpc_propose_abort(). */ + abort_code = smp_load_acquire(&call->send_abort); + if (abort_code) { + rxrpc_abort_call(call, 0, call->send_abort, call->send_abort_err, + call->send_abort_why); + goto out; + } + if (skb && skb->mark == RXRPC_SKB_MARK_ERROR) goto out; @@ -358,7 +407,7 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) } t = READ_ONCE(call->expect_req_by); - if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST && + if (__rxrpc_call_state(call) == RXRPC_CALL_SERVER_RECV_REQUEST && time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now); expired = true; @@ -429,11 +478,12 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && (int)call->conn->hi_serial - (int)call->rx_serial > 0) { trace_rxrpc_call_reset(call); - rxrpc_abort_call("EXP", call, 0, RX_CALL_DEAD, -ECONNRESET); + rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ECONNRESET, + rxrpc_abort_call_reset); } else { - rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME); + rxrpc_abort_call(call, 0, RX_CALL_TIMEOUT, -ETIME, + rxrpc_abort_call_timeout); } - rxrpc_send_abort_packet(call); goto out; } @@ -441,7 +491,7 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_lost_ack); - if (resend && call->state != RXRPC_CALL_CLIENT_RECV_REPLY) + if (resend && __rxrpc_call_state(call) != RXRPC_CALL_CLIENT_RECV_REPLY) rxrpc_resend(call, NULL); if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) @@ -453,7 +503,7 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_propose_ack_input_data); /* Make sure the timer is restarted */ - if (call->state != RXRPC_CALL_COMPLETE) { + if (!__rxrpc_call_is_complete(call)) { next = call->expect_rx_by; #define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; } @@ -474,9 +524,15 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) } out: - if (call->state == RXRPC_CALL_COMPLETE) + if (__rxrpc_call_is_complete(call)) { del_timer_sync(&call->timer); + if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) + rxrpc_disconnect_call(call); + if (call->security) + call->security->free_call_crypto(call); + } if (call->acks_hard_ack != call->tx_bottom) rxrpc_shrink_call_tx_buffer(call); _leave(""); + return true; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 89dcf60b1158..f3c9f0201c15 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -50,7 +50,7 @@ void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) struct rxrpc_local *local = call->local; bool busy; - if (call->state < RXRPC_CALL_COMPLETE) { + if (!test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) { spin_lock_bh(&local->lock); busy = !list_empty(&call->attend_link); trace_rxrpc_poke_call(call, busy, what); @@ -69,7 +69,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) _enter("%d", call->debug_id); - if (call->state < RXRPC_CALL_COMPLETE) { + if (!__rxrpc_call_is_complete(call)) { trace_rxrpc_timer_expired(call, jiffies); rxrpc_poke_call(call, rxrpc_call_poke_timer); } @@ -150,7 +150,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, timer_setup(&call->timer, rxrpc_call_timer_expired, 0); INIT_WORK(&call->destroyer, rxrpc_destroy_call); INIT_LIST_HEAD(&call->link); - INIT_LIST_HEAD(&call->chan_wait_link); + INIT_LIST_HEAD(&call->wait_link); INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); @@ -162,7 +162,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, init_waitqueue_head(&call->waitq); spin_lock_init(&call->notify_lock); spin_lock_init(&call->tx_lock); - rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; call->tx_total_len = -1; @@ -211,7 +210,6 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, now = ktime_get_real(); call->acks_latest_ts = now; call->cong_tstamp = now; - call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; call->dest_srx = *srx; call->interruptibility = p->interruptibility; call->tx_total_len = p->tx_total_len; @@ -227,11 +225,13 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, ret = rxrpc_init_client_call_security(call); if (ret < 0) { - __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, ret); rxrpc_put_call(call, rxrpc_call_put_discard_error); return ERR_PTR(ret); } + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_CONN); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), p->user_call_ID, rxrpc_call_new_client); @@ -242,7 +242,7 @@ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, /* * Initiate the call ack/resend/expiry timer. */ -static void rxrpc_start_call_timer(struct rxrpc_call *call) +void rxrpc_start_call_timer(struct rxrpc_call *call) { unsigned long now = jiffies; unsigned long j = now + MAX_JIFFY_OFFSET; @@ -287,6 +287,39 @@ static void rxrpc_put_call_slot(struct rxrpc_call *call) } /* + * Start the process of connecting a call. We obtain a peer and a connection + * bundle, but the actual association of a call with a connection is offloaded + * to the I/O thread to simplify locking. + */ +static int rxrpc_connect_call(struct rxrpc_call *call, gfp_t gfp) +{ + struct rxrpc_local *local = call->local; + int ret = -ENOMEM; + + _enter("{%d,%lx},", call->debug_id, call->user_call_ID); + + call->peer = rxrpc_lookup_peer(local, &call->dest_srx, gfp); + if (!call->peer) + goto error; + + ret = rxrpc_look_up_bundle(call, gfp); + if (ret < 0) + goto error; + + trace_rxrpc_client(NULL, -1, rxrpc_client_queue_new_call); + rxrpc_get_call(call, rxrpc_call_get_io_thread); + spin_lock(&local->client_call_lock); + list_add_tail(&call->wait_link, &local->new_client_calls); + spin_unlock(&local->client_call_lock); + rxrpc_wake_up_io_thread(local); + return 0; + +error: + __set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + return ret; +} + +/* * Set up a call for the given parameters. * - Called with the socket lock held, which it must release. * - If it returns a call, the call's lock will need releasing by the caller. @@ -365,14 +398,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, /* Set up or get a connection record and set the protocol parameters, * including channel number and call ID. */ - ret = rxrpc_connect_call(rx, call, cp, srx, gfp); + ret = rxrpc_connect_call(call, gfp); if (ret < 0) goto error_attached_to_socket; - rxrpc_see_call(call, rxrpc_call_see_connected); - - rxrpc_start_call_timer(call); - _leave(" = %p [new]", call); return call; @@ -384,27 +413,23 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, error_dup_user_ID: write_unlock(&rx->call_lock); release_sock(&rx->sk); - __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, -EEXIST); + rxrpc_prefail_call(call, RXRPC_CALL_LOCAL_ERROR, -EEXIST); trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0, rxrpc_call_see_userid_exists); - rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put_userid_exists); _leave(" = -EEXIST"); return ERR_PTR(-EEXIST); /* We got an error, but the call is attached to the socket and is in - * need of release. However, we might now race with recvmsg() when - * completing the call queues it. Return 0 from sys_sendmsg() and + * need of release. However, we might now race with recvmsg() when it + * completion notifies the socket. Return 0 from sys_sendmsg() and * leave the error to recvmsg() to deal with. */ error_attached_to_socket: trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret, rxrpc_call_see_connect_failed); - set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); - __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); _leave(" = c=%08x [err]", call->debug_id); return call; } @@ -427,32 +452,32 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, call->call_id = sp->hdr.callNumber; call->dest_srx.srx_service = sp->hdr.serviceId; call->cid = sp->hdr.cid; - call->state = RXRPC_CALL_SERVER_SECURING; call->cong_tstamp = skb->tstamp; + __set_bit(RXRPC_CALL_EXPOSED, &call->flags); + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING); + spin_lock(&conn->state_lock); switch (conn->state) { case RXRPC_CONN_SERVICE_UNSECURED: case RXRPC_CONN_SERVICE_CHALLENGING: - call->state = RXRPC_CALL_SERVER_SECURING; + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_SECURING); break; case RXRPC_CONN_SERVICE: - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST); break; - case RXRPC_CONN_REMOTELY_ABORTED: - __rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, - conn->abort_code, conn->error); - break; - case RXRPC_CONN_LOCALLY_ABORTED: - __rxrpc_abort_call("CON", call, 1, - conn->abort_code, conn->error); + case RXRPC_CONN_ABORTED: + rxrpc_set_call_completion(call, conn->completion, + conn->abort_code, conn->error); break; default: BUG(); } + rxrpc_get_call(call, rxrpc_call_get_io_thread); + /* Set the channel for this call. We don't get channel_lock as we're * only defending against the data_ready handler (which we're called * from) and the RESPONSE packet parser (which is only really @@ -462,7 +487,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, chan = sp->hdr.cid & RXRPC_CHANNELMASK; conn->channels[chan].call_counter = call->call_id; conn->channels[chan].call_id = call->call_id; - rcu_assign_pointer(conn->channels[chan].call, call); + conn->channels[chan].call = call; spin_unlock(&conn->state_lock); spin_lock(&conn->peer->lock); @@ -522,20 +547,17 @@ static void rxrpc_cleanup_ring(struct rxrpc_call *call) void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; - bool put = false; + bool put = false, putu = false; _enter("{%d,%d}", call->debug_id, refcount_read(&call->ref)); trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), call->flags, rxrpc_call_see_release); - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); - if (test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags)) BUG(); rxrpc_put_call_slot(call); - del_timer_sync(&call->timer); /* Make sure we don't get any more notifications */ write_lock(&rx->recvmsg_lock); @@ -560,7 +582,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) if (test_and_clear_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { rb_erase(&call->sock_node, &rx->calls); memset(&call->sock_node, 0xdd, sizeof(call->sock_node)); - rxrpc_put_call(call, rxrpc_call_put_userid_exists); + putu = true; } list_del(&call->sock_link); @@ -568,10 +590,9 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); - if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) - rxrpc_disconnect_call(call); - if (call->security) - call->security->free_call_crypto(call); + if (putu) + rxrpc_put_call(call, rxrpc_call_put_userid); + _leave(""); } @@ -588,7 +609,8 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) call = list_entry(rx->to_be_accepted.next, struct rxrpc_call, accept_link); list_del(&call->accept_link); - rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET); + rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, + rxrpc_abort_call_sock_release_tba); rxrpc_put_call(call, rxrpc_call_put_release_sock_tba); } @@ -596,8 +618,8 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) call = list_entry(rx->sock_calls.next, struct rxrpc_call, sock_link); rxrpc_get_call(call, rxrpc_call_get_release_sock); - rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET); - rxrpc_send_abort_packet(call); + rxrpc_propose_abort(call, RX_CALL_DEAD, -ECONNRESET, + rxrpc_abort_call_sock_release); rxrpc_release_call(rx, call); rxrpc_put_call(call, rxrpc_call_put_release_sock); } @@ -620,7 +642,7 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why) dead = __refcount_dec_and_test(&call->ref, &r); trace_rxrpc_call(debug_id, r - 1, 0, why); if (dead) { - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); + ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE); if (!list_empty(&call->link)) { spin_lock(&rxnet->call_lock); @@ -669,6 +691,8 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); rxrpc_put_connection(call->conn, rxrpc_conn_put_call); + rxrpc_deactivate_bundle(call->bundle); + rxrpc_put_bundle(call->bundle, rxrpc_bundle_put_call); rxrpc_put_peer(call->peer, rxrpc_peer_put_call); rxrpc_put_local(call->local, rxrpc_local_put_call); call_rcu(&call->rcu, rxrpc_rcu_free_call); @@ -681,7 +705,7 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) { memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); - ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); + ASSERTCMP(__rxrpc_call_state(call), ==, RXRPC_CALL_COMPLETE); ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); del_timer(&call->timer); @@ -719,7 +743,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", call, refcount_read(&call->ref), - rxrpc_call_states[call->state], + rxrpc_call_states[__rxrpc_call_state(call)], call->flags, call->events); spin_unlock(&rxnet->call_lock); diff --git a/net/rxrpc/call_state.c b/net/rxrpc/call_state.c new file mode 100644 index 000000000000..6afb54373ebb --- /dev/null +++ b/net/rxrpc/call_state.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Call state changing functions. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#include "ar-internal.h" + +/* + * Transition a call to the complete state. + */ +bool rxrpc_set_call_completion(struct rxrpc_call *call, + enum rxrpc_call_completion compl, + u32 abort_code, + int error) +{ + if (__rxrpc_call_state(call) == RXRPC_CALL_COMPLETE) + return false; + + call->abort_code = abort_code; + call->error = error; + call->completion = compl; + /* Allow reader of completion state to operate locklessly */ + rxrpc_set_call_state(call, RXRPC_CALL_COMPLETE); + trace_rxrpc_call_complete(call); + wake_up(&call->waitq); + rxrpc_notify_socket(call); + return true; +} + +/* + * Record that a call successfully completed. + */ +bool rxrpc_call_completed(struct rxrpc_call *call) +{ + return rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); +} + +/* + * Record that a call is locally aborted. + */ +bool rxrpc_abort_call(struct rxrpc_call *call, rxrpc_seq_t seq, + u32 abort_code, int error, enum rxrpc_abort_reason why) +{ + trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq, + abort_code, error); + if (!rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED, + abort_code, error)) + return false; + if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) + rxrpc_send_abort_packet(call); + return true; +} + +/* + * Record that a call errored out before even getting off the ground, thereby + * setting the state to allow it to be destroyed. + */ +void rxrpc_prefail_call(struct rxrpc_call *call, enum rxrpc_call_completion compl, + int error) +{ + call->abort_code = RX_CALL_DEAD; + call->error = error; + call->completion = compl; + call->_state = RXRPC_CALL_COMPLETE; + trace_rxrpc_call_complete(call); + WARN_ON_ONCE(__test_and_set_bit(RXRPC_CALL_RELEASED, &call->flags)); +} diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 87efa0373aed..981ca5b98bcb 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -34,104 +34,59 @@ __read_mostly unsigned int rxrpc_reap_client_connections = 900; __read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ; __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ; -/* - * We use machine-unique IDs for our client connections. - */ -DEFINE_IDR(rxrpc_client_conn_ids); -static DEFINE_SPINLOCK(rxrpc_conn_id_lock); - -static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); - -/* - * Get a connection ID and epoch for a client connection from the global pool. - * The connection struct pointer is then recorded in the idr radix tree. The - * epoch doesn't change until the client is rebooted (or, at least, unless the - * module is unloaded). - */ -static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, - gfp_t gfp) +static void rxrpc_activate_bundle(struct rxrpc_bundle *bundle) { - struct rxrpc_net *rxnet = conn->rxnet; - int id; - - _enter(""); - - idr_preload(gfp); - spin_lock(&rxrpc_conn_id_lock); - - id = idr_alloc_cyclic(&rxrpc_client_conn_ids, conn, - 1, 0x40000000, GFP_NOWAIT); - if (id < 0) - goto error; - - spin_unlock(&rxrpc_conn_id_lock); - idr_preload_end(); - - conn->proto.epoch = rxnet->epoch; - conn->proto.cid = id << RXRPC_CIDSHIFT; - set_bit(RXRPC_CONN_HAS_IDR, &conn->flags); - _leave(" [CID %x]", conn->proto.cid); - return 0; - -error: - spin_unlock(&rxrpc_conn_id_lock); - idr_preload_end(); - _leave(" = %d", id); - return id; + atomic_inc(&bundle->active); } /* - * Release a connection ID for a client connection from the global pool. + * Release a connection ID for a client connection. */ -static void rxrpc_put_client_connection_id(struct rxrpc_connection *conn) +static void rxrpc_put_client_connection_id(struct rxrpc_local *local, + struct rxrpc_connection *conn) { - if (test_bit(RXRPC_CONN_HAS_IDR, &conn->flags)) { - spin_lock(&rxrpc_conn_id_lock); - idr_remove(&rxrpc_client_conn_ids, - conn->proto.cid >> RXRPC_CIDSHIFT); - spin_unlock(&rxrpc_conn_id_lock); - } + idr_remove(&local->conn_ids, conn->proto.cid >> RXRPC_CIDSHIFT); } /* * Destroy the client connection ID tree. */ -void rxrpc_destroy_client_conn_ids(void) +static void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local) { struct rxrpc_connection *conn; int id; - if (!idr_is_empty(&rxrpc_client_conn_ids)) { - idr_for_each_entry(&rxrpc_client_conn_ids, conn, id) { + if (!idr_is_empty(&local->conn_ids)) { + idr_for_each_entry(&local->conn_ids, conn, id) { pr_err("AF_RXRPC: Leaked client conn %p {%d}\n", conn, refcount_read(&conn->ref)); } BUG(); } - idr_destroy(&rxrpc_client_conn_ids); + idr_destroy(&local->conn_ids); } /* * Allocate a connection bundle. */ -static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, +static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call, gfp_t gfp) { struct rxrpc_bundle *bundle; bundle = kzalloc(sizeof(*bundle), gfp); if (bundle) { - bundle->local = cp->local; - bundle->peer = rxrpc_get_peer(cp->peer, rxrpc_peer_get_bundle); - bundle->key = cp->key; - bundle->exclusive = cp->exclusive; - bundle->upgrade = cp->upgrade; - bundle->service_id = cp->service_id; - bundle->security_level = cp->security_level; + bundle->local = call->local; + bundle->peer = rxrpc_get_peer(call->peer, rxrpc_peer_get_bundle); + bundle->key = key_get(call->key); + bundle->security = call->security; + bundle->exclusive = test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags); + bundle->upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags); + bundle->service_id = call->dest_srx.srx_service; + bundle->security_level = call->security_level; refcount_set(&bundle->ref, 1); atomic_set(&bundle->active, 1); - spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_new); } @@ -152,84 +107,87 @@ static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) { trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free); rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle); + key_put(bundle->key); kfree(bundle); } void rxrpc_put_bundle(struct rxrpc_bundle *bundle, enum rxrpc_bundle_trace why) { - unsigned int id = bundle->debug_id; + unsigned int id; bool dead; int r; - dead = __refcount_dec_and_test(&bundle->ref, &r); - trace_rxrpc_bundle(id, r - 1, why); - if (dead) - rxrpc_free_bundle(bundle); + if (bundle) { + id = bundle->debug_id; + dead = __refcount_dec_and_test(&bundle->ref, &r); + trace_rxrpc_bundle(id, r - 1, why); + if (dead) + rxrpc_free_bundle(bundle); + } +} + +/* + * Get rid of outstanding client connection preallocations when a local + * endpoint is destroyed. + */ +void rxrpc_purge_client_connections(struct rxrpc_local *local) +{ + rxrpc_destroy_client_conn_ids(local); } /* * Allocate a client connection. */ static struct rxrpc_connection * -rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) +rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle) { struct rxrpc_connection *conn; - struct rxrpc_net *rxnet = bundle->local->rxnet; - int ret; + struct rxrpc_local *local = bundle->local; + struct rxrpc_net *rxnet = local->rxnet; + int id; _enter(""); - conn = rxrpc_alloc_connection(rxnet, gfp); - if (!conn) { - _leave(" = -ENOMEM"); + conn = rxrpc_alloc_connection(rxnet, GFP_ATOMIC | __GFP_NOWARN); + if (!conn) return ERR_PTR(-ENOMEM); + + id = idr_alloc_cyclic(&local->conn_ids, conn, 1, 0x40000000, + GFP_ATOMIC | __GFP_NOWARN); + if (id < 0) { + kfree(conn); + return ERR_PTR(id); } refcount_set(&conn->ref, 1); - conn->bundle = bundle; - conn->local = bundle->local; - conn->peer = bundle->peer; - conn->key = bundle->key; + conn->proto.cid = id << RXRPC_CIDSHIFT; + conn->proto.epoch = local->rxnet->epoch; + conn->out_clientflag = RXRPC_CLIENT_INITIATED; + conn->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn); + conn->local = rxrpc_get_local(bundle->local, rxrpc_local_get_client_conn); + conn->peer = rxrpc_get_peer(bundle->peer, rxrpc_peer_get_client_conn); + conn->key = key_get(bundle->key); + conn->security = bundle->security; conn->exclusive = bundle->exclusive; conn->upgrade = bundle->upgrade; conn->orig_service_id = bundle->service_id; conn->security_level = bundle->security_level; - conn->out_clientflag = RXRPC_CLIENT_INITIATED; - conn->state = RXRPC_CONN_CLIENT; + conn->state = RXRPC_CONN_CLIENT_UNSECURED; conn->service_id = conn->orig_service_id; - ret = rxrpc_get_client_connection_id(conn, gfp); - if (ret < 0) - goto error_0; - - ret = rxrpc_init_client_conn_security(conn); - if (ret < 0) - goto error_1; + if (conn->security == &rxrpc_no_security) + conn->state = RXRPC_CONN_CLIENT; atomic_inc(&rxnet->nr_conns); write_lock(&rxnet->conn_lock); list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn); - rxrpc_get_peer(conn->peer, rxrpc_peer_get_client_conn); - rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); - key_get(conn->key); - - trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), - rxrpc_conn_new_client); + rxrpc_see_connection(conn, rxrpc_conn_new_client); atomic_inc(&rxnet->nr_client_conns); trace_rxrpc_client(conn, -1, rxrpc_client_alloc); - _leave(" = %p", conn); return conn; - -error_1: - rxrpc_put_client_connection_id(conn); -error_0: - kfree(conn); - _leave(" = %d", ret); - return ERR_PTR(ret); } /* @@ -247,7 +205,8 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags)) goto dont_reuse; - if (conn->state != RXRPC_CONN_CLIENT || + if ((conn->state != RXRPC_CONN_CLIENT_UNSECURED && + conn->state != RXRPC_CONN_CLIENT) || conn->proto.epoch != rxnet->epoch) goto mark_dont_reuse; @@ -257,7 +216,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) * times the maximum number of client conns away from the current * allocation point to try and keep the IDs concentrated. */ - id_cursor = idr_get_cursor(&rxrpc_client_conn_ids); + id_cursor = idr_get_cursor(&conn->local->conn_ids); id = conn->proto.cid >> RXRPC_CIDSHIFT; distance = id - id_cursor; if (distance < 0) @@ -278,20 +237,23 @@ dont_reuse: * Look up the conn bundle that matches the connection parameters, adding it if * it doesn't yet exist. */ -static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *cp, - gfp_t gfp) +int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp) { static atomic_t rxrpc_bundle_id; struct rxrpc_bundle *bundle, *candidate; - struct rxrpc_local *local = cp->local; + struct rxrpc_local *local = call->local; struct rb_node *p, **pp, *parent; long diff; + bool upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags); _enter("{%px,%x,%u,%u}", - cp->peer, key_serial(cp->key), cp->security_level, cp->upgrade); + call->peer, key_serial(call->key), call->security_level, + upgrade); - if (cp->exclusive) - return rxrpc_alloc_bundle(cp, gfp); + if (test_bit(RXRPC_CALL_EXCLUSIVE, &call->flags)) { + call->bundle = rxrpc_alloc_bundle(call, gfp); + return call->bundle ? 0 : -ENOMEM; + } /* First, see if the bundle is already there. */ _debug("search 1"); @@ -300,11 +262,11 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c while (p) { bundle = rb_entry(p, struct rxrpc_bundle, local_node); -#define cmp(X) ((long)bundle->X - (long)cp->X) - diff = (cmp(peer) ?: - cmp(key) ?: - cmp(security_level) ?: - cmp(upgrade)); +#define cmp(X, Y) ((long)(X) - (long)(Y)) + diff = (cmp(bundle->peer, call->peer) ?: + cmp(bundle->key, call->key) ?: + cmp(bundle->security_level, call->security_level) ?: + cmp(bundle->upgrade, upgrade)); #undef cmp if (diff < 0) p = p->rb_left; @@ -317,9 +279,9 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c _debug("not found"); /* It wasn't. We need to add one. */ - candidate = rxrpc_alloc_bundle(cp, gfp); + candidate = rxrpc_alloc_bundle(call, gfp); if (!candidate) - return NULL; + return -ENOMEM; _debug("search 2"); spin_lock(&local->client_bundles_lock); @@ -329,11 +291,11 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c parent = *pp; bundle = rb_entry(parent, struct rxrpc_bundle, local_node); -#define cmp(X) ((long)bundle->X - (long)cp->X) - diff = (cmp(peer) ?: - cmp(key) ?: - cmp(security_level) ?: - cmp(upgrade)); +#define cmp(X, Y) ((long)(X) - (long)(Y)) + diff = (cmp(bundle->peer, call->peer) ?: + cmp(bundle->key, call->key) ?: + cmp(bundle->security_level, call->security_level) ?: + cmp(bundle->upgrade, upgrade)); #undef cmp if (diff < 0) pp = &(*pp)->rb_left; @@ -347,178 +309,89 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id); rb_link_node(&candidate->local_node, parent, pp); rb_insert_color(&candidate->local_node, &local->client_bundles); - rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call); + call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call); spin_unlock(&local->client_bundles_lock); - _leave(" = %u [new]", candidate->debug_id); - return candidate; + _leave(" = B=%u [new]", call->bundle->debug_id); + return 0; found_bundle_free: rxrpc_free_bundle(candidate); found_bundle: - rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call); - atomic_inc(&bundle->active); + call->bundle = rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call); + rxrpc_activate_bundle(bundle); spin_unlock(&local->client_bundles_lock); - _leave(" = %u [found]", bundle->debug_id); - return bundle; -} - -/* - * Create or find a client bundle to use for a call. - * - * If we return with a connection, the call will be on its waiting list. It's - * left to the caller to assign a channel and wake up the call. - */ -static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) -{ - struct rxrpc_bundle *bundle; - - _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - - cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp); - if (!cp->peer) - goto error; - - call->tx_last_sent = ktime_get_real(); - call->cong_ssthresh = cp->peer->cong_ssthresh; - if (call->cong_cwnd >= call->cong_ssthresh) - call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; - else - call->cong_mode = RXRPC_CALL_SLOW_START; - if (cp->upgrade) - __set_bit(RXRPC_CALL_UPGRADE, &call->flags); - - /* Find the client connection bundle. */ - bundle = rxrpc_look_up_bundle(cp, gfp); - if (!bundle) - goto error; - - /* Get this call queued. Someone else may activate it whilst we're - * lining up a new connection, but that's fine. - */ - spin_lock(&bundle->channel_lock); - list_add_tail(&call->chan_wait_link, &bundle->waiting_calls); - spin_unlock(&bundle->channel_lock); - - _leave(" = [B=%x]", bundle->debug_id); - return bundle; - -error: - _leave(" = -ENOMEM"); - return ERR_PTR(-ENOMEM); + _leave(" = B=%u [found]", call->bundle->debug_id); + return 0; } /* * Allocate a new connection and add it into a bundle. */ -static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) - __releases(bundle->channel_lock) +static bool rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, + unsigned int slot) { - struct rxrpc_connection *candidate = NULL, *old = NULL; - bool conflict; - int i; - - _enter(""); - - conflict = bundle->alloc_conn; - if (!conflict) - bundle->alloc_conn = true; - spin_unlock(&bundle->channel_lock); - if (conflict) { - _leave(" [conf]"); - return; - } - - candidate = rxrpc_alloc_client_connection(bundle, gfp); - - spin_lock(&bundle->channel_lock); - bundle->alloc_conn = false; - - if (IS_ERR(candidate)) { - bundle->alloc_error = PTR_ERR(candidate); - spin_unlock(&bundle->channel_lock); - _leave(" [err %ld]", PTR_ERR(candidate)); - return; - } - - bundle->alloc_error = 0; - - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) { - unsigned int shift = i * RXRPC_MAXCALLS; - int j; - - old = bundle->conns[i]; - if (!rxrpc_may_reuse_conn(old)) { - if (old) - trace_rxrpc_client(old, -1, rxrpc_client_replace); - candidate->bundle_shift = shift; - atomic_inc(&bundle->active); - bundle->conns[i] = candidate; - for (j = 0; j < RXRPC_MAXCALLS; j++) - set_bit(shift + j, &bundle->avail_chans); - candidate = NULL; - break; - } + struct rxrpc_connection *conn, *old; + unsigned int shift = slot * RXRPC_MAXCALLS; + unsigned int i; - old = NULL; + old = bundle->conns[slot]; + if (old) { + bundle->conns[slot] = NULL; + trace_rxrpc_client(old, -1, rxrpc_client_replace); + rxrpc_put_connection(old, rxrpc_conn_put_noreuse); } - spin_unlock(&bundle->channel_lock); - - if (candidate) { - _debug("discard C=%x", candidate->debug_id); - trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate); - rxrpc_put_connection(candidate, rxrpc_conn_put_discard); + conn = rxrpc_alloc_client_connection(bundle); + if (IS_ERR(conn)) { + bundle->alloc_error = PTR_ERR(conn); + return false; } - rxrpc_put_connection(old, rxrpc_conn_put_noreuse); - _leave(""); + rxrpc_activate_bundle(bundle); + conn->bundle_shift = shift; + bundle->conns[slot] = conn; + for (i = 0; i < RXRPC_MAXCALLS; i++) + set_bit(shift + i, &bundle->avail_chans); + return true; } /* * Add a connection to a bundle if there are no usable connections or we have * connections waiting for extra capacity. */ -static void rxrpc_maybe_add_conn(struct rxrpc_bundle *bundle, gfp_t gfp) +static bool rxrpc_bundle_has_space(struct rxrpc_bundle *bundle) { - struct rxrpc_call *call; - int i, usable; + int slot = -1, i, usable; _enter(""); - spin_lock(&bundle->channel_lock); + bundle->alloc_error = 0; /* See if there are any usable connections. */ usable = 0; - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) + for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) { if (rxrpc_may_reuse_conn(bundle->conns[i])) usable++; - - if (!usable && !list_empty(&bundle->waiting_calls)) { - call = list_first_entry(&bundle->waiting_calls, - struct rxrpc_call, chan_wait_link); - if (test_bit(RXRPC_CALL_UPGRADE, &call->flags)) - bundle->try_upgrade = true; + else if (slot == -1) + slot = i; } + if (!usable && bundle->upgrade) + bundle->try_upgrade = true; + if (!usable) goto alloc_conn; if (!bundle->avail_chans && !bundle->try_upgrade && - !list_empty(&bundle->waiting_calls) && usable < ARRAY_SIZE(bundle->conns)) goto alloc_conn; - spin_unlock(&bundle->channel_lock); _leave(""); - return; + return usable; alloc_conn: - return rxrpc_add_conn_to_bundle(bundle, gfp); + return slot >= 0 ? rxrpc_add_conn_to_bundle(bundle, slot) : false; } /* @@ -532,11 +405,13 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, struct rxrpc_channel *chan = &conn->channels[channel]; struct rxrpc_bundle *bundle = conn->bundle; struct rxrpc_call *call = list_entry(bundle->waiting_calls.next, - struct rxrpc_call, chan_wait_link); + struct rxrpc_call, wait_link); u32 call_id = chan->call_counter + 1; _enter("C=%x,%u", conn->debug_id, channel); + list_del_init(&call->wait_link); + trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate); /* Cancel the final ACK on the previous call if it hasn't been sent yet @@ -546,68 +421,50 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, clear_bit(conn->bundle_shift + channel, &bundle->avail_chans); rxrpc_see_call(call, rxrpc_call_see_activate_client); - list_del_init(&call->chan_wait_link); - call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call); call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call); call->cid = conn->proto.cid | channel; call->call_id = call_id; call->dest_srx.srx_service = conn->service_id; - - trace_rxrpc_connect_call(call); - - write_lock(&call->state_lock); - call->state = RXRPC_CALL_CLIENT_SEND_REQUEST; - write_unlock(&call->state_lock); - - /* Paired with the read barrier in rxrpc_connect_call(). This orders - * cid and epoch in the connection wrt to call_id without the need to - * take the channel_lock. - * - * We provisionally assign a callNumber at this point, but we don't - * confirm it until the call is about to be exposed. - * - * TODO: Pair with a barrier in the data_ready handler when that looks - * at the call ID through a connection channel. - */ - smp_wmb(); + call->cong_ssthresh = call->peer->cong_ssthresh; + if (call->cong_cwnd >= call->cong_ssthresh) + call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; + else + call->cong_mode = RXRPC_CALL_SLOW_START; chan->call_id = call_id; chan->call_debug_id = call->debug_id; - rcu_assign_pointer(chan->call, call); + chan->call = call; + + rxrpc_see_call(call, rxrpc_call_see_connected); + trace_rxrpc_connect_call(call); + call->tx_last_sent = ktime_get_real(); + rxrpc_start_call_timer(call); + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_SEND_REQUEST); wake_up(&call->waitq); } /* * Remove a connection from the idle list if it's on it. */ -static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn) +static void rxrpc_unidle_conn(struct rxrpc_connection *conn) { - struct rxrpc_net *rxnet = bundle->local->rxnet; - bool drop_ref; - if (!list_empty(&conn->cache_link)) { - drop_ref = false; - spin_lock(&rxnet->client_conn_cache_lock); - if (!list_empty(&conn->cache_link)) { - list_del_init(&conn->cache_link); - drop_ref = true; - } - spin_unlock(&rxnet->client_conn_cache_lock); - if (drop_ref) - rxrpc_put_connection(conn, rxrpc_conn_put_unidle); + list_del_init(&conn->cache_link); + rxrpc_put_connection(conn, rxrpc_conn_put_unidle); } } /* - * Assign channels and callNumbers to waiting calls with channel_lock - * held by caller. + * Assign channels and callNumbers to waiting calls. */ -static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle) +static void rxrpc_activate_channels(struct rxrpc_bundle *bundle) { struct rxrpc_connection *conn; unsigned long avail, mask; unsigned int channel, slot; + trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans); + if (bundle->try_upgrade) mask = 1; else @@ -627,7 +484,7 @@ static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle) if (bundle->try_upgrade) set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags); - rxrpc_unidle_conn(bundle, conn); + rxrpc_unidle_conn(conn); channel &= (RXRPC_MAXCALLS - 1); conn->act_chans |= 1 << channel; @@ -636,132 +493,24 @@ static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle) } /* - * Assign channels and callNumbers to waiting calls. - */ -static void rxrpc_activate_channels(struct rxrpc_bundle *bundle) -{ - _enter("B=%x", bundle->debug_id); - - trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans); - - if (!bundle->avail_chans) - return; - - spin_lock(&bundle->channel_lock); - rxrpc_activate_channels_locked(bundle); - spin_unlock(&bundle->channel_lock); - _leave(""); -} - -/* - * Wait for a callNumber and a channel to be granted to a call. - */ -static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle, - struct rxrpc_call *call, gfp_t gfp) -{ - DECLARE_WAITQUEUE(myself, current); - int ret = 0; - - _enter("%d", call->debug_id); - - if (!gfpflags_allow_blocking(gfp)) { - rxrpc_maybe_add_conn(bundle, gfp); - rxrpc_activate_channels(bundle); - ret = bundle->alloc_error ?: -EAGAIN; - goto out; - } - - add_wait_queue_exclusive(&call->waitq, &myself); - for (;;) { - rxrpc_maybe_add_conn(bundle, gfp); - rxrpc_activate_channels(bundle); - ret = bundle->alloc_error; - if (ret < 0) - break; - - switch (call->interruptibility) { - case RXRPC_INTERRUPTIBLE: - case RXRPC_PREINTERRUPTIBLE: - set_current_state(TASK_INTERRUPTIBLE); - break; - case RXRPC_UNINTERRUPTIBLE: - default: - set_current_state(TASK_UNINTERRUPTIBLE); - break; - } - if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_AWAIT_CONN) - break; - if ((call->interruptibility == RXRPC_INTERRUPTIBLE || - call->interruptibility == RXRPC_PREINTERRUPTIBLE) && - signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } - schedule(); - } - remove_wait_queue(&call->waitq, &myself); - __set_current_state(TASK_RUNNING); - -out: - _leave(" = %d", ret); - return ret; -} - -/* - * find a connection for a call - * - called in process context with IRQs enabled + * Connect waiting channels (called from the I/O thread). */ -int rxrpc_connect_call(struct rxrpc_sock *rx, - struct rxrpc_call *call, - struct rxrpc_conn_parameters *cp, - struct sockaddr_rxrpc *srx, - gfp_t gfp) +void rxrpc_connect_client_calls(struct rxrpc_local *local) { - struct rxrpc_bundle *bundle; - struct rxrpc_net *rxnet = cp->local->rxnet; - int ret = 0; - - _enter("{%d,%lx},", call->debug_id, call->user_call_ID); - - rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper); + struct rxrpc_call *call; - bundle = rxrpc_prep_call(rx, call, cp, srx, gfp); - if (IS_ERR(bundle)) { - ret = PTR_ERR(bundle); - goto out; - } + while ((call = list_first_entry_or_null(&local->new_client_calls, + struct rxrpc_call, wait_link)) + ) { + struct rxrpc_bundle *bundle = call->bundle; - if (call->state == RXRPC_CALL_CLIENT_AWAIT_CONN) { - ret = rxrpc_wait_for_channel(bundle, call, gfp); - if (ret < 0) - goto wait_failed; - } + spin_lock(&local->client_call_lock); + list_move_tail(&call->wait_link, &bundle->waiting_calls); + spin_unlock(&local->client_call_lock); -granted_channel: - /* Paired with the write barrier in rxrpc_activate_one_channel(). */ - smp_rmb(); - -out_put_bundle: - rxrpc_deactivate_bundle(bundle); - rxrpc_put_bundle(bundle, rxrpc_bundle_get_client_call); -out: - _leave(" = %d", ret); - return ret; - -wait_failed: - spin_lock(&bundle->channel_lock); - list_del_init(&call->chan_wait_link); - spin_unlock(&bundle->channel_lock); - - if (call->state != RXRPC_CALL_CLIENT_AWAIT_CONN) { - ret = 0; - goto granted_channel; + if (rxrpc_bundle_has_space(bundle)) + rxrpc_activate_channels(bundle); } - - trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed); - rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); - rxrpc_disconnect_client_call(bundle, call); - goto out_put_bundle; } /* @@ -794,14 +543,14 @@ void rxrpc_expose_client_call(struct rxrpc_call *call) /* * Set the reap timer. */ -static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet) +static void rxrpc_set_client_reap_timer(struct rxrpc_local *local) { - if (!rxnet->kill_all_client_conns) { + if (!local->kill_all_client_conns) { unsigned long now = jiffies; unsigned long reap_at = now + rxrpc_conn_idle_client_expiry; - if (rxnet->live) - timer_reduce(&rxnet->client_conn_reap_timer, reap_at); + if (local->rxnet->live) + timer_reduce(&local->client_conn_reap_timer, reap_at); } } @@ -812,16 +561,13 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call { struct rxrpc_connection *conn; struct rxrpc_channel *chan = NULL; - struct rxrpc_net *rxnet = bundle->local->rxnet; + struct rxrpc_local *local = bundle->local; unsigned int channel; bool may_reuse; u32 cid; _enter("c=%x", call->debug_id); - spin_lock(&bundle->channel_lock); - set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); - /* Calls that have never actually been assigned a channel can simply be * discarded. */ @@ -830,8 +576,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call _debug("call is waiting"); ASSERTCMP(call->call_id, ==, 0); ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags)); - list_del_init(&call->chan_wait_link); - goto out; + list_del_init(&call->wait_link); + return; } cid = call->cid; @@ -839,10 +585,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call chan = &conn->channels[channel]; trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); - if (rcu_access_pointer(chan->call) != call) { - spin_unlock(&bundle->channel_lock); - BUG(); - } + if (WARN_ON(chan->call != call)) + return; may_reuse = rxrpc_may_reuse_conn(conn); @@ -863,16 +607,15 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call trace_rxrpc_client(conn, channel, rxrpc_client_to_active); bundle->try_upgrade = false; if (may_reuse) - rxrpc_activate_channels_locked(bundle); + rxrpc_activate_channels(bundle); } - } /* See if we can pass the channel directly to another call. */ if (may_reuse && !list_empty(&bundle->waiting_calls)) { trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass); rxrpc_activate_one_channel(conn, channel); - goto out; + return; } /* Schedule the final ACK to be transmitted in a short while so that it @@ -890,7 +633,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call } /* Deactivate the channel. */ - rcu_assign_pointer(chan->call, NULL); + chan->call = NULL; set_bit(conn->bundle_shift + channel, &conn->bundle->avail_chans); conn->act_chans &= ~(1 << channel); @@ -903,17 +646,10 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call conn->idle_timestamp = jiffies; rxrpc_get_connection(conn, rxrpc_conn_get_idle); - spin_lock(&rxnet->client_conn_cache_lock); - list_move_tail(&conn->cache_link, &rxnet->idle_client_conns); - spin_unlock(&rxnet->client_conn_cache_lock); + list_move_tail(&conn->cache_link, &local->idle_client_conns); - rxrpc_set_client_reap_timer(rxnet); + rxrpc_set_client_reap_timer(local); } - -out: - spin_unlock(&bundle->channel_lock); - _leave(""); - return; } /* @@ -923,7 +659,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) { struct rxrpc_bundle *bundle = conn->bundle; unsigned int bindex; - bool need_drop = false; int i; _enter("C=%x", conn->debug_id); @@ -931,18 +666,13 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) rxrpc_process_delayed_final_acks(conn, true); - spin_lock(&bundle->channel_lock); bindex = conn->bundle_shift / RXRPC_MAXCALLS; if (bundle->conns[bindex] == conn) { _debug("clear slot %u", bindex); bundle->conns[bindex] = NULL; for (i = 0; i < RXRPC_MAXCALLS; i++) clear_bit(conn->bundle_shift + i, &bundle->avail_chans); - need_drop = true; - } - spin_unlock(&bundle->channel_lock); - - if (need_drop) { + rxrpc_put_client_connection_id(bundle->local, conn); rxrpc_deactivate_bundle(bundle); rxrpc_put_connection(conn, rxrpc_conn_put_unbundle); } @@ -951,11 +681,15 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) /* * Drop the active count on a bundle. */ -static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) +void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) { - struct rxrpc_local *local = bundle->local; + struct rxrpc_local *local; bool need_put = false; + if (!bundle) + return; + + local = bundle->local; if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) { if (!bundle->exclusive) { _debug("erase bundle"); @@ -982,7 +716,7 @@ void rxrpc_kill_client_conn(struct rxrpc_connection *conn) trace_rxrpc_client(conn, -1, rxrpc_client_cleanup); atomic_dec(&rxnet->nr_client_conns); - rxrpc_put_client_connection_id(conn); + rxrpc_put_client_connection_id(local, conn); } /* @@ -992,42 +726,26 @@ void rxrpc_kill_client_conn(struct rxrpc_connection *conn) * This may be called from conn setup or from a work item so cannot be * considered non-reentrant. */ -void rxrpc_discard_expired_client_conns(struct work_struct *work) +void rxrpc_discard_expired_client_conns(struct rxrpc_local *local) { struct rxrpc_connection *conn; - struct rxrpc_net *rxnet = - container_of(work, struct rxrpc_net, client_conn_reaper); unsigned long expiry, conn_expires_at, now; unsigned int nr_conns; _enter(""); - if (list_empty(&rxnet->idle_client_conns)) { - _leave(" [empty]"); - return; - } - - /* Don't double up on the discarding */ - if (!mutex_trylock(&rxnet->client_conn_discard_lock)) { - _leave(" [already]"); - return; - } - /* We keep an estimate of what the number of conns ought to be after * we've discarded some so that we don't overdo the discarding. */ - nr_conns = atomic_read(&rxnet->nr_client_conns); + nr_conns = atomic_read(&local->rxnet->nr_client_conns); next: - spin_lock(&rxnet->client_conn_cache_lock); - - if (list_empty(&rxnet->idle_client_conns)) - goto out; - - conn = list_entry(rxnet->idle_client_conns.next, - struct rxrpc_connection, cache_link); + conn = list_first_entry_or_null(&local->idle_client_conns, + struct rxrpc_connection, cache_link); + if (!conn) + return; - if (!rxnet->kill_all_client_conns) { + if (!local->kill_all_client_conns) { /* If the number of connections is over the reap limit, we * expedite discard by reducing the expiry timeout. We must, * however, have at least a short grace period to be able to do @@ -1050,8 +768,6 @@ next: trace_rxrpc_client(conn, -1, rxrpc_client_discard); list_del_init(&conn->cache_link); - spin_unlock(&rxnet->client_conn_cache_lock); - rxrpc_unbundle_conn(conn); /* Drop the ->cache_link ref */ rxrpc_put_connection(conn, rxrpc_conn_put_discard_idle); @@ -1068,31 +784,8 @@ not_yet_expired: * then things get messier. */ _debug("not yet"); - if (!rxnet->kill_all_client_conns) - timer_reduce(&rxnet->client_conn_reap_timer, conn_expires_at); - -out: - spin_unlock(&rxnet->client_conn_cache_lock); - mutex_unlock(&rxnet->client_conn_discard_lock); - _leave(""); -} - -/* - * Preemptively destroy all the client connection records rather than waiting - * for them to time out - */ -void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet) -{ - _enter(""); - - spin_lock(&rxnet->client_conn_cache_lock); - rxnet->kill_all_client_conns = true; - spin_unlock(&rxnet->client_conn_cache_lock); - - del_timer_sync(&rxnet->client_conn_reap_timer); - - if (!rxrpc_queue_work(&rxnet->client_conn_reaper)) - _debug("destroy: queue failed"); + if (!local->kill_all_client_conns) + timer_reduce(&local->client_conn_reap_timer, conn_expires_at); _leave(""); } @@ -1102,29 +795,19 @@ void rxrpc_destroy_all_client_connections(struct rxrpc_net *rxnet) */ void rxrpc_clean_up_local_conns(struct rxrpc_local *local) { - struct rxrpc_connection *conn, *tmp; - struct rxrpc_net *rxnet = local->rxnet; - LIST_HEAD(graveyard); + struct rxrpc_connection *conn; _enter(""); - spin_lock(&rxnet->client_conn_cache_lock); - - list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns, - cache_link) { - if (conn->local == local) { - atomic_dec(&conn->active); - trace_rxrpc_client(conn, -1, rxrpc_client_discard); - list_move(&conn->cache_link, &graveyard); - } - } + local->kill_all_client_conns = true; - spin_unlock(&rxnet->client_conn_cache_lock); + del_timer_sync(&local->client_conn_reap_timer); - while (!list_empty(&graveyard)) { - conn = list_entry(graveyard.next, - struct rxrpc_connection, cache_link); + while ((conn = list_first_entry_or_null(&local->idle_client_conns, + struct rxrpc_connection, cache_link))) { list_del_init(&conn->cache_link); + atomic_dec(&conn->active); + trace_rxrpc_client(conn, -1, rxrpc_client_discard); rxrpc_unbundle_conn(conn); rxrpc_put_connection(conn, rxrpc_conn_put_local_dead); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 480364bcbf85..44414e724415 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -17,11 +17,65 @@ #include "ar-internal.h" /* + * Set the completion state on an aborted connection. + */ +static bool rxrpc_set_conn_aborted(struct rxrpc_connection *conn, struct sk_buff *skb, + s32 abort_code, int err, + enum rxrpc_call_completion compl) +{ + bool aborted = false; + + if (conn->state != RXRPC_CONN_ABORTED) { + spin_lock(&conn->state_lock); + if (conn->state != RXRPC_CONN_ABORTED) { + conn->abort_code = abort_code; + conn->error = err; + conn->completion = compl; + /* Order the abort info before the state change. */ + smp_store_release(&conn->state, RXRPC_CONN_ABORTED); + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); + set_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events); + aborted = true; + } + spin_unlock(&conn->state_lock); + } + + return aborted; +} + +/* + * Mark a socket buffer to indicate that the connection it's on should be aborted. + */ +int rxrpc_abort_conn(struct rxrpc_connection *conn, struct sk_buff *skb, + s32 abort_code, int err, enum rxrpc_abort_reason why) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + if (rxrpc_set_conn_aborted(conn, skb, abort_code, err, + RXRPC_CALL_LOCALLY_ABORTED)) { + trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber, + sp->hdr.seq, abort_code, err); + rxrpc_poke_conn(conn, rxrpc_conn_get_poke_abort); + } + return -EPROTO; +} + +/* + * Mark a connection as being remotely aborted. + */ +static bool rxrpc_input_conn_abort(struct rxrpc_connection *conn, + struct sk_buff *skb) +{ + return rxrpc_set_conn_aborted(conn, skb, skb->priority, -ECONNABORTED, + RXRPC_CALL_REMOTELY_ABORTED); +} + +/* * Retransmit terminal ACK or ABORT of the previous call. */ -static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, - struct sk_buff *skb, - unsigned int channel) +void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, + struct sk_buff *skb, + unsigned int channel) { struct rxrpc_skb_priv *sp = skb ? rxrpc_skb(skb) : NULL; struct rxrpc_channel *chan; @@ -46,9 +100,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, /* If the last call got moved on whilst we were waiting to run, just * ignore this packet. */ - call_id = READ_ONCE(chan->last_call); - /* Sync with __rxrpc_disconnect_call() */ - smp_rmb(); + call_id = chan->last_call; if (skb && call_id != sp->hdr.callNumber) return; @@ -65,9 +117,12 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[2].iov_base = &ack_info; iov[2].iov_len = sizeof(ack_info); + serial = atomic_inc_return(&conn->serial); + pkt.whdr.epoch = htonl(conn->proto.epoch); pkt.whdr.cid = htonl(conn->proto.cid | channel); pkt.whdr.callNumber = htonl(call_id); + pkt.whdr.serial = htonl(serial); pkt.whdr.seq = 0; pkt.whdr.type = chan->last_type; pkt.whdr.flags = conn->out_clientflag; @@ -104,31 +159,15 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, iov[0].iov_len += sizeof(pkt.ack); len += sizeof(pkt.ack) + 3 + sizeof(ack_info); ioc = 3; - break; - - default: - return; - } - - /* Resync with __rxrpc_disconnect_call() and check that the last call - * didn't get advanced whilst we were filling out the packets. - */ - smp_rmb(); - if (READ_ONCE(chan->last_call) != call_id) - return; - - serial = atomic_inc_return(&conn->serial); - pkt.whdr.serial = htonl(serial); - switch (chan->last_type) { - case RXRPC_PACKET_TYPE_ABORT: - break; - case RXRPC_PACKET_TYPE_ACK: trace_rxrpc_tx_ack(chan->call_debug_id, serial, ntohl(pkt.ack.firstPacket), ntohl(pkt.ack.serial), pkt.ack.reason, 0); break; + + default: + return; } ret = kernel_sendmsg(conn->local->socket, &msg, iov, ioc, len); @@ -146,131 +185,34 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, /* * pass a connection-level abort onto all calls on that connection */ -static void rxrpc_abort_calls(struct rxrpc_connection *conn, - enum rxrpc_call_completion compl, - rxrpc_serial_t serial) +static void rxrpc_abort_calls(struct rxrpc_connection *conn) { struct rxrpc_call *call; int i; _enter("{%d},%x", conn->debug_id, conn->abort_code); - spin_lock(&conn->bundle->channel_lock); - for (i = 0; i < RXRPC_MAXCALLS; i++) { - call = rcu_dereference_protected( - conn->channels[i].call, - lockdep_is_held(&conn->bundle->channel_lock)); - if (call) { - if (compl == RXRPC_CALL_LOCALLY_ABORTED) - trace_rxrpc_abort(call->debug_id, - "CON", call->cid, - call->call_id, 0, + call = conn->channels[i].call; + if (call) + rxrpc_set_call_completion(call, + conn->completion, conn->abort_code, conn->error); - else - trace_rxrpc_rx_abort(call, serial, - conn->abort_code); - rxrpc_set_call_completion(call, compl, - conn->abort_code, - conn->error); - } } - spin_unlock(&conn->bundle->channel_lock); _leave(""); } /* - * generate a connection-level abort - */ -static int rxrpc_abort_connection(struct rxrpc_connection *conn, - int error, u32 abort_code) -{ - struct rxrpc_wire_header whdr; - struct msghdr msg; - struct kvec iov[2]; - __be32 word; - size_t len; - u32 serial; - int ret; - - _enter("%d,,%u,%u", conn->debug_id, error, abort_code); - - /* generate a connection-level abort */ - spin_lock(&conn->state_lock); - if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { - spin_unlock(&conn->state_lock); - _leave(" = 0 [already dead]"); - return 0; - } - - conn->error = error; - conn->abort_code = abort_code; - conn->state = RXRPC_CONN_LOCALLY_ABORTED; - set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - spin_unlock(&conn->state_lock); - - msg.msg_name = &conn->peer->srx.transport; - msg.msg_namelen = conn->peer->srx.transport_len; - msg.msg_control = NULL; - msg.msg_controllen = 0; - msg.msg_flags = 0; - - whdr.epoch = htonl(conn->proto.epoch); - whdr.cid = htonl(conn->proto.cid); - whdr.callNumber = 0; - whdr.seq = 0; - whdr.type = RXRPC_PACKET_TYPE_ABORT; - whdr.flags = conn->out_clientflag; - whdr.userStatus = 0; - whdr.securityIndex = conn->security_ix; - whdr._rsvd = 0; - whdr.serviceId = htons(conn->service_id); - - word = htonl(conn->abort_code); - - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); - iov[1].iov_base = &word; - iov[1].iov_len = sizeof(word); - - len = iov[0].iov_len + iov[1].iov_len; - - serial = atomic_inc_return(&conn->serial); - rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial); - whdr.serial = htonl(serial); - - ret = kernel_sendmsg(conn->local->socket, &msg, iov, 2, len); - if (ret < 0) { - trace_rxrpc_tx_fail(conn->debug_id, serial, ret, - rxrpc_tx_point_conn_abort); - _debug("sendmsg failed: %d", ret); - return -EAGAIN; - } - - trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort); - - conn->peer->last_tx_at = ktime_get_seconds(); - - _leave(" = 0"); - return 0; -} - -/* * mark a call as being on a now-secured channel * - must be called with BH's disabled. */ static void rxrpc_call_is_secure(struct rxrpc_call *call) { - _enter("%p", call); - if (call) { - write_lock(&call->state_lock); - if (call->state == RXRPC_CALL_SERVER_SECURING) { - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - rxrpc_notify_socket(call); - } - write_unlock(&call->state_lock); + if (call && __rxrpc_call_state(call) == RXRPC_CALL_SERVER_SECURING) { + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_RECV_REQUEST); + rxrpc_notify_socket(call); } } @@ -278,44 +220,22 @@ static void rxrpc_call_is_secure(struct rxrpc_call *call) * connection-level Rx packet processor */ static int rxrpc_process_event(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - int loop, ret; + int ret; - if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { - _leave(" = -ECONNABORTED [%u]", conn->state); + if (conn->state == RXRPC_CONN_ABORTED) return -ECONNABORTED; - } _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); switch (sp->hdr.type) { - case RXRPC_PACKET_TYPE_DATA: - case RXRPC_PACKET_TYPE_ACK: - rxrpc_conn_retransmit_call(conn, skb, - sp->hdr.cid & RXRPC_CHANNELMASK); - return 0; - - case RXRPC_PACKET_TYPE_BUSY: - /* Just ignore BUSY packets for now. */ - return 0; - - case RXRPC_PACKET_TYPE_ABORT: - conn->error = -ECONNABORTED; - conn->abort_code = skb->priority; - conn->state = RXRPC_CONN_REMOTELY_ABORTED; - set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); - return -ECONNABORTED; - case RXRPC_PACKET_TYPE_CHALLENGE: - return conn->security->respond_to_challenge(conn, skb, - _abort_code); + return conn->security->respond_to_challenge(conn, skb); case RXRPC_PACKET_TYPE_RESPONSE: - ret = conn->security->verify_response(conn, skb, _abort_code); + ret = conn->security->verify_response(conn, skb); if (ret < 0) return ret; @@ -324,27 +244,25 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, if (ret < 0) return ret; - spin_lock(&conn->bundle->channel_lock); spin_lock(&conn->state_lock); - - if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) { + if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) conn->state = RXRPC_CONN_SERVICE; - spin_unlock(&conn->state_lock); - for (loop = 0; loop < RXRPC_MAXCALLS; loop++) - rxrpc_call_is_secure( - rcu_dereference_protected( - conn->channels[loop].call, - lockdep_is_held(&conn->bundle->channel_lock))); - } else { - spin_unlock(&conn->state_lock); - } + spin_unlock(&conn->state_lock); - spin_unlock(&conn->bundle->channel_lock); + if (conn->state == RXRPC_CONN_SERVICE) { + /* Offload call state flipping to the I/O thread. As + * we've already received the packet, put it on the + * front of the queue. + */ + skb->mark = RXRPC_SKB_MARK_SERVICE_CONN_SECURED; + rxrpc_get_skb(skb, rxrpc_skb_get_conn_secured); + skb_queue_head(&conn->local->rx_queue, skb); + rxrpc_wake_up_io_thread(conn->local); + } return 0; default: - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("bad_conn_pkt")); + WARN_ON_ONCE(1); return -EPROTO; } } @@ -354,26 +272,9 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, */ static void rxrpc_secure_connection(struct rxrpc_connection *conn) { - u32 abort_code; - int ret; - - _enter("{%d}", conn->debug_id); - - ASSERT(conn->security_ix != 0); - - if (conn->security->issue_challenge(conn) < 0) { - abort_code = RX_CALL_DEAD; - ret = -ENOMEM; - goto abort; - } - - _leave(""); - return; - -abort: - _debug("abort %d, %d", ret, abort_code); - rxrpc_abort_connection(conn, ret, abort_code); - _leave(" [aborted]"); + if (conn->security->issue_challenge(conn) < 0) + rxrpc_abort_conn(conn, NULL, RX_CALL_DEAD, -ENOMEM, + rxrpc_abort_nomem); } /* @@ -395,9 +296,7 @@ again: if (!test_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags)) continue; - smp_rmb(); /* vs rxrpc_disconnect_client_call */ - ack_at = READ_ONCE(chan->final_ack_at); - + ack_at = chan->final_ack_at; if (time_before(j, ack_at) && !force) { if (time_before(ack_at, next_j)) { next_j = ack_at; @@ -424,47 +323,27 @@ again: static void rxrpc_do_process_connection(struct rxrpc_connection *conn) { struct sk_buff *skb; - u32 abort_code = RX_PROTOCOL_ERROR; int ret; if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events)) rxrpc_secure_connection(conn); - /* Process delayed ACKs whose time has come. */ - if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) - rxrpc_process_delayed_final_acks(conn, false); - /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { rxrpc_see_skb(skb, rxrpc_skb_see_conn_work); - ret = rxrpc_process_event(conn, skb, &abort_code); + ret = rxrpc_process_event(conn, skb); switch (ret) { - case -EPROTO: - case -EKEYEXPIRED: - case -EKEYREJECTED: - goto protocol_error; case -ENOMEM: case -EAGAIN: - goto requeue_and_leave; - case -ECONNABORTED: + skb_queue_head(&conn->rx_queue, skb); + rxrpc_queue_conn(conn, rxrpc_conn_queue_retry_work); + break; default: rxrpc_free_skb(skb, rxrpc_skb_put_conn_work); break; } } - - return; - -requeue_and_leave: - skb_queue_head(&conn->rx_queue, skb); - return; - -protocol_error: - if (rxrpc_abort_connection(conn, ret, abort_code) < 0) - goto requeue_and_leave; - rxrpc_free_skb(skb, rxrpc_skb_put_conn_work); - return; } void rxrpc_process_connection(struct work_struct *work) @@ -498,44 +377,59 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, /* * Input a connection-level packet. */ -int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) +bool rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { - _leave(" = -ECONNABORTED [%u]", conn->state); - return -ECONNABORTED; - } - - _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); - switch (sp->hdr.type) { - case RXRPC_PACKET_TYPE_DATA: - case RXRPC_PACKET_TYPE_ACK: - rxrpc_conn_retransmit_call(conn, skb, - sp->hdr.cid & RXRPC_CHANNELMASK); - return 0; - case RXRPC_PACKET_TYPE_BUSY: /* Just ignore BUSY packets for now. */ - return 0; + return true; case RXRPC_PACKET_TYPE_ABORT: - conn->error = -ECONNABORTED; - conn->abort_code = skb->priority; - conn->state = RXRPC_CONN_REMOTELY_ABORTED; - set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); - rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); - return -ECONNABORTED; + if (rxrpc_is_conn_aborted(conn)) + return true; + rxrpc_input_conn_abort(conn, skb); + rxrpc_abort_calls(conn); + return true; case RXRPC_PACKET_TYPE_CHALLENGE: case RXRPC_PACKET_TYPE_RESPONSE: + if (rxrpc_is_conn_aborted(conn)) { + if (conn->completion == RXRPC_CALL_LOCALLY_ABORTED) + rxrpc_send_conn_abort(conn); + return true; + } rxrpc_post_packet_to_conn(conn, skb); - return 0; + return true; default: - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("bad_conn_pkt")); - return -EPROTO; + WARN_ON_ONCE(1); + return true; } } + +/* + * Input a connection event. + */ +void rxrpc_input_conn_event(struct rxrpc_connection *conn, struct sk_buff *skb) +{ + unsigned int loop; + + if (test_and_clear_bit(RXRPC_CONN_EV_ABORT_CALLS, &conn->events)) + rxrpc_abort_calls(conn); + + switch (skb->mark) { + case RXRPC_SKB_MARK_SERVICE_CONN_SECURED: + if (conn->state != RXRPC_CONN_SERVICE) + break; + + for (loop = 0; loop < RXRPC_MAXCALLS; loop++) + rxrpc_call_is_secure(conn->channels[loop].call); + break; + } + + /* Process delayed ACKs whose time has come. */ + if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK) + rxrpc_process_delayed_final_acks(conn, false); +} diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 3c8f83dacb2b..ac85d4644a3c 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -23,12 +23,30 @@ static void rxrpc_clean_up_connection(struct work_struct *work); static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, unsigned long reap_at); +void rxrpc_poke_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) +{ + struct rxrpc_local *local = conn->local; + bool busy; + + if (WARN_ON_ONCE(!local)) + return; + + spin_lock_bh(&local->lock); + busy = !list_empty(&conn->attend_link); + if (!busy) { + rxrpc_get_connection(conn, why); + list_add_tail(&conn->attend_link, &local->conn_attend_q); + } + spin_unlock_bh(&local->lock); + rxrpc_wake_up_io_thread(local); +} + static void rxrpc_connection_timer(struct timer_list *timer) { struct rxrpc_connection *conn = container_of(timer, struct rxrpc_connection, timer); - rxrpc_queue_conn(conn, rxrpc_conn_queue_timer); + rxrpc_poke_conn(conn, rxrpc_conn_get_poke_timer); } /* @@ -49,6 +67,7 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, INIT_WORK(&conn->destructor, rxrpc_clean_up_connection); INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); + mutex_init(&conn->security_lock); skb_queue_head_init(&conn->rx_queue); conn->rxnet = rxnet; conn->security = &rxrpc_no_security; @@ -82,10 +101,10 @@ struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *lo _enter(",%x", sp->hdr.cid & RXRPC_CIDMASK); - /* Look up client connections by connection ID alone as their IDs are - * unique for this machine. + /* Look up client connections by connection ID alone as their + * IDs are unique for this machine. */ - conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); + conn = idr_find(&local->conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); if (!conn || refcount_read(&conn->ref) == 0) { _debug("no conn"); goto not_found; @@ -139,7 +158,7 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, _enter("%d,%x", conn->debug_id, call->cid); - if (rcu_access_pointer(chan->call) == call) { + if (chan->call == call) { /* Save the result of the call so that we can repeat it if necessary * through the channel, whilst disposing of the actual call record. */ @@ -159,12 +178,9 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, break; } - /* Sync with rxrpc_conn_retransmit(). */ - smp_wmb(); chan->last_call = chan->call_id; chan->call_id = chan->call_counter; - - rcu_assign_pointer(chan->call, NULL); + chan->call = NULL; } _leave(""); @@ -178,6 +194,9 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + rxrpc_see_call(call, rxrpc_call_see_disconnected); + call->peer->cong_ssthresh = call->cong_ssthresh; if (!hlist_unhashed(&call->error_link)) { @@ -186,18 +205,17 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) spin_unlock(&call->peer->lock); } - if (rxrpc_is_client_call(call)) - return rxrpc_disconnect_client_call(conn->bundle, call); - - spin_lock(&conn->bundle->channel_lock); - __rxrpc_disconnect_call(conn, call); - spin_unlock(&conn->bundle->channel_lock); + if (rxrpc_is_client_call(call)) { + rxrpc_disconnect_client_call(call->bundle, call); + } else { + __rxrpc_disconnect_call(conn, call); + conn->idle_timestamp = jiffies; + if (atomic_dec_and_test(&conn->active)) + rxrpc_set_service_reap_timer(conn->rxnet, + jiffies + rxrpc_connection_expiry); + } - set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); - conn->idle_timestamp = jiffies; - if (atomic_dec_and_test(&conn->active)) - rxrpc_set_service_reap_timer(conn->rxnet, - jiffies + rxrpc_connection_expiry); + rxrpc_put_call(call, rxrpc_call_put_io_thread); } /* @@ -293,10 +311,10 @@ static void rxrpc_clean_up_connection(struct work_struct *work) container_of(work, struct rxrpc_connection, destructor); struct rxrpc_net *rxnet = conn->rxnet; - ASSERT(!rcu_access_pointer(conn->channels[0].call) && - !rcu_access_pointer(conn->channels[1].call) && - !rcu_access_pointer(conn->channels[2].call) && - !rcu_access_pointer(conn->channels[3].call)); + ASSERT(!conn->channels[0].call && + !conn->channels[1].call && + !conn->channels[2].call && + !conn->channels[3].call); ASSERT(list_empty(&conn->cache_link)); del_timer_sync(&conn->timer); @@ -447,7 +465,6 @@ void rxrpc_destroy_all_connections(struct rxrpc_net *rxnet) _enter(""); atomic_dec(&rxnet->nr_conns); - rxrpc_destroy_all_client_connections(rxnet); del_timer_sync(&rxnet->service_conn_reap_timer); rxrpc_queue_work(&rxnet->service_conn_reaper); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 2a55a88b2a5b..f30323de82bd 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -11,7 +11,6 @@ static struct rxrpc_bundle rxrpc_service_dummy_bundle = { .ref = REFCOUNT_INIT(1), .debug_id = UINT_MAX, - .channel_lock = __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock), }; /* diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index d0e20e946e48..367927a99881 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -9,11 +9,10 @@ #include "ar-internal.h" -static void rxrpc_proto_abort(const char *why, - struct rxrpc_call *call, rxrpc_seq_t seq) +static void rxrpc_proto_abort(struct rxrpc_call *call, rxrpc_seq_t seq, + enum rxrpc_abort_reason why) { - if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) - rxrpc_send_abort_packet(call); + rxrpc_abort_call(call, seq, RX_PROTOCOL_ERROR, -EBADMSG, why); } /* @@ -185,7 +184,7 @@ void rxrpc_congestion_degrade(struct rxrpc_call *call) if (call->cong_mode != RXRPC_CALL_SLOW_START && call->cong_mode != RXRPC_CALL_CONGEST_AVOIDANCE) return; - if (call->state == RXRPC_CALL_CLIENT_AWAIT_REPLY) + if (__rxrpc_call_state(call) == RXRPC_CALL_CLIENT_AWAIT_REPLY) return; rtt = ns_to_ktime(call->peer->srtt_us * (1000 / 8)); @@ -250,47 +249,34 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, * This occurs when we get an ACKALL packet, the first DATA packet of a reply, * or a final ACK packet. */ -static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, - const char *abort_why) +static void rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, + enum rxrpc_abort_reason abort_why) { - unsigned int state; - ASSERT(test_bit(RXRPC_CALL_TX_LAST, &call->flags)); - write_lock(&call->state_lock); - - state = call->state; - switch (state) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: - if (reply_begun) - call->state = state = RXRPC_CALL_CLIENT_RECV_REPLY; - else - call->state = state = RXRPC_CALL_CLIENT_AWAIT_REPLY; + if (reply_begun) { + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_RECV_REPLY); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); + break; + } + + rxrpc_set_call_state(call, RXRPC_CALL_CLIENT_AWAIT_REPLY); + trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply); break; case RXRPC_CALL_SERVER_AWAIT_ACK: - __rxrpc_call_completed(call); - state = call->state; + rxrpc_call_completed(call); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); break; default: - goto bad_state; + kdebug("end_tx %s", rxrpc_call_states[__rxrpc_call_state(call)]); + rxrpc_proto_abort(call, call->tx_top, abort_why); + break; } - - write_unlock(&call->state_lock); - if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY) - trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply); - else - trace_rxrpc_txqueue(call, rxrpc_txqueue_end); - _leave(" = ok"); - return true; - -bad_state: - write_unlock(&call->state_lock); - kdebug("end_tx %s", rxrpc_call_states[call->state]); - rxrpc_proto_abort(abort_why, call, call->tx_top); - return false; } /* @@ -305,18 +291,48 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) if (call->ackr_reason) { now = jiffies; timo = now + MAX_JIFFY_OFFSET; - WRITE_ONCE(call->resend_at, timo); + WRITE_ONCE(call->delay_ack_at, timo); trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); } if (!test_bit(RXRPC_CALL_TX_LAST, &call->flags)) { if (!rxrpc_rotate_tx_window(call, top, &summary)) { - rxrpc_proto_abort("TXL", call, top); + rxrpc_proto_abort(call, top, rxrpc_eproto_early_reply); return false; } } - return rxrpc_end_tx_phase(call, true, "ETD"); + + rxrpc_end_tx_phase(call, true, rxrpc_eproto_unexpected_reply); + return true; +} + +/* + * End the packet reception phase. + */ +static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) +{ + rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); + + _enter("%d,%s", call->debug_id, rxrpc_call_states[__rxrpc_call_state(call)]); + + trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); + + switch (__rxrpc_call_state(call)) { + case RXRPC_CALL_CLIENT_RECV_REPLY: + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); + rxrpc_call_completed(call); + break; + + case RXRPC_CALL_SERVER_RECV_REQUEST: + rxrpc_set_call_state(call, RXRPC_CALL_SERVER_ACK_REQUEST); + call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_processing_op); + break; + + default: + break; + } } static void rxrpc_input_update_ack_window(struct rxrpc_call *call, @@ -337,8 +353,9 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, __skb_queue_tail(&call->recvmsg_queue, skb); rxrpc_input_update_ack_window(call, window, wtop); - trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq); + if (last) + rxrpc_end_rx_phase(call, sp->hdr.serial); } /* @@ -366,17 +383,14 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, if (last) { if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq + 1 != wtop) { - rxrpc_proto_abort("LSN", call, seq); - return; - } + seq + 1 != wtop) + return rxrpc_proto_abort(call, seq, rxrpc_eproto_different_last); } else { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && after_eq(seq, wtop)) { pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n", call->debug_id, seq, window, wtop, wlimit); - rxrpc_proto_abort("LSA", call, seq); - return; + return rxrpc_proto_abort(call, seq, rxrpc_eproto_data_after_last); } } @@ -550,7 +564,6 @@ protocol_error: static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - enum rxrpc_call_state state; rxrpc_serial_t serial = sp->hdr.serial; rxrpc_seq_t seq0 = sp->hdr.seq; @@ -558,11 +571,20 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) atomic64_read(&call->ackr_window), call->rx_highest_seq, skb->len, seq0); - state = READ_ONCE(call->state); - if (state >= RXRPC_CALL_COMPLETE) + if (__rxrpc_call_is_complete(call)) return; - if (state == RXRPC_CALL_SERVER_RECV_REQUEST) { + switch (__rxrpc_call_state(call)) { + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + /* Received data implicitly ACKs all of the request + * packets we sent when we're acting as a client. + */ + if (!rxrpc_receiving_reply(call)) + goto out_notify; + break; + + case RXRPC_CALL_SERVER_RECV_REQUEST: { unsigned long timo = READ_ONCE(call->next_req_timo); unsigned long now, expect_req_by; @@ -573,18 +595,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_reduce_call_timer(call, expect_req_by, now, rxrpc_timer_set_for_idle); } + break; } - /* Received data implicitly ACKs all of the request packets we sent - * when we're acting as a client. - */ - if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || - state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && - !rxrpc_receiving_reply(call)) - goto out_notify; + default: + break; + } if (!rxrpc_input_split_jumbo(call, skb)) { - rxrpc_proto_abort("VLD", call, sp->hdr.seq); + rxrpc_proto_abort(call, sp->hdr.seq, rxrpc_badmsg_bad_jumbo); goto out_notify; } skb = NULL; @@ -765,7 +784,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) offset = sizeof(struct rxrpc_wire_header); if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) - return rxrpc_proto_abort("XAK", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack); offset += sizeof(ack); ack_serial = sp->hdr.serial; @@ -845,7 +864,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) ioffset = offset + nr_acks + 3; if (skb->len >= ioffset + sizeof(info) && skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) - return rxrpc_proto_abort("XAI", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_badmsg_short_ack_info); if (nr_acks > 0) skb_condense(skb); @@ -868,10 +887,10 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_input_ackinfo(call, skb, &info); if (first_soft_ack == 0) - return rxrpc_proto_abort("AK0", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_zero); /* Ignore ACKs unless we are or have just been transmitting. */ - switch (READ_ONCE(call->state)) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_CLIENT_SEND_REQUEST: case RXRPC_CALL_CLIENT_AWAIT_REPLY: case RXRPC_CALL_SERVER_SEND_REPLY: @@ -883,20 +902,20 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (before(hard_ack, call->acks_hard_ack) || after(hard_ack, call->tx_top)) - return rxrpc_proto_abort("AKW", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_outside_window); if (nr_acks > call->tx_top - hard_ack) - return rxrpc_proto_abort("AKN", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_sack_overflow); if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { - rxrpc_end_tx_phase(call, false, "ETA"); + rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack); return; } } if (nr_acks > 0) { if (offset > (int)skb->len - nr_acks) - return rxrpc_proto_abort("XSA", call, 0); + return rxrpc_proto_abort(call, 0, rxrpc_eproto_ackr_short_sack); rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, nr_acks, &summary); } @@ -918,7 +937,7 @@ static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ack_summary summary = { 0 }; if (rxrpc_rotate_tx_window(call, call->tx_top, &summary)) - rxrpc_end_tx_phase(call, false, "ETL"); + rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ackall); } /* @@ -963,27 +982,23 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: - rxrpc_input_data(call, skb); - break; + return rxrpc_input_data(call, skb); case RXRPC_PACKET_TYPE_ACK: - rxrpc_input_ack(call, skb); - break; + return rxrpc_input_ack(call, skb); case RXRPC_PACKET_TYPE_BUSY: /* Just ignore BUSY packets from the server; the retry and * lifespan timers will take care of business. BUSY packets * from the client don't make sense. */ - break; + return; case RXRPC_PACKET_TYPE_ABORT: - rxrpc_input_abort(call, skb); - break; + return rxrpc_input_abort(call, skb); case RXRPC_PACKET_TYPE_ACKALL: - rxrpc_input_ackall(call, skb); - break; + return rxrpc_input_ackall(call, skb); default: break; @@ -998,24 +1013,18 @@ void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) */ void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) { - struct rxrpc_connection *conn = call->conn; - - switch (READ_ONCE(call->state)) { + switch (__rxrpc_call_state(call)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); fallthrough; case RXRPC_CALL_COMPLETE: break; default: - if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) - rxrpc_send_abort_packet(call); + rxrpc_abort_call(call, 0, RX_CALL_DEAD, -ESHUTDOWN, + rxrpc_eproto_improper_term); trace_rxrpc_improper_term(call); break; } rxrpc_input_call_event(call, skb); - - spin_lock(&conn->bundle->channel_lock); - __rxrpc_disconnect_call(conn, call); - spin_unlock(&conn->bundle->channel_lock); } diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 0eb8471bfc53..34353b6e584b 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -43,25 +43,17 @@ static void none_free_call_crypto(struct rxrpc_call *call) } static int none_respond_to_challenge(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("chall_none")); - return -EPROTO; + return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, + rxrpc_eproto_rxnull_challenge); } static int none_verify_response(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("resp_none")); - return -EPROTO; + return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, + rxrpc_eproto_rxnull_response); } static void none_clear(struct rxrpc_connection *conn) diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 1ad067d66fb6..9e9dfb2fc559 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -67,9 +67,31 @@ void rxrpc_error_report(struct sock *sk) } /* + * Directly produce an abort from a packet. + */ +bool rxrpc_direct_abort(struct sk_buff *skb, enum rxrpc_abort_reason why, + s32 abort_code, int err) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + trace_rxrpc_abort(0, why, sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + abort_code, err); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = abort_code; + return false; +} + +static bool rxrpc_bad_message(struct sk_buff *skb, enum rxrpc_abort_reason why) +{ + return rxrpc_direct_abort(skb, why, RX_PROTOCOL_ERROR, -EBADMSG); +} + +#define just_discard true + +/* * Process event packets targeted at a local endpoint. */ -static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb) +static bool rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); char v; @@ -81,22 +103,21 @@ static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb) if (v == 0) rxrpc_send_version_request(local, &sp->hdr, skb); } + + return true; } /* * Extract the wire header from a packet and translate the byte order. */ -static noinline -int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) +static bool rxrpc_extract_header(struct rxrpc_skb_priv *sp, + struct sk_buff *skb) { struct rxrpc_wire_header whdr; /* dig out the RxRPC connection details */ - if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) { - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, - tracepoint_string("bad_hdr")); - return -EBADMSG; - } + if (skb_copy_bits(skb, 0, &whdr, sizeof(whdr)) < 0) + return rxrpc_bad_message(skb, rxrpc_badmsg_short_hdr); memset(sp, 0, sizeof(*sp)); sp->hdr.epoch = ntohl(whdr.epoch); @@ -110,7 +131,7 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb) sp->hdr.securityIndex = whdr.securityIndex; sp->hdr._rsvd = ntohs(whdr._rsvd); sp->hdr.serviceId = ntohs(whdr.serviceId); - return 0; + return true; } /* @@ -130,28 +151,28 @@ static bool rxrpc_extract_abort(struct sk_buff *skb) /* * Process packets received on the local endpoint */ -static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) +static bool rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) { struct rxrpc_connection *conn; struct sockaddr_rxrpc peer_srx; struct rxrpc_skb_priv *sp; struct rxrpc_peer *peer = NULL; struct sk_buff *skb = *_skb; - int ret = 0; + bool ret = false; skb_pull(skb, sizeof(struct udphdr)); sp = rxrpc_skb(skb); /* dig out the RxRPC connection details */ - if (rxrpc_extract_header(sp, skb) < 0) - goto bad_message; + if (!rxrpc_extract_header(sp, skb)) + return just_discard; if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - return 0; + return just_discard; } } @@ -160,28 +181,28 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: if (rxrpc_to_client(sp)) - return 0; - rxrpc_input_version(local, skb); - return 0; + return just_discard; + return rxrpc_input_version(local, skb); case RXRPC_PACKET_TYPE_BUSY: if (rxrpc_to_server(sp)) - return 0; + return just_discard; fallthrough; case RXRPC_PACKET_TYPE_ACK: case RXRPC_PACKET_TYPE_ACKALL: if (sp->hdr.callNumber == 0) - goto bad_message; + return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call); break; case RXRPC_PACKET_TYPE_ABORT: if (!rxrpc_extract_abort(skb)) - return 0; /* Just discard if malformed */ + return just_discard; /* Just discard if malformed */ break; case RXRPC_PACKET_TYPE_DATA: - if (sp->hdr.callNumber == 0 || - sp->hdr.seq == 0) - goto bad_message; + if (sp->hdr.callNumber == 0) + return rxrpc_bad_message(skb, rxrpc_badmsg_zero_call); + if (sp->hdr.seq == 0) + return rxrpc_bad_message(skb, rxrpc_badmsg_zero_seq); /* Unshare the packet so that it can be modified for in-place * decryption. @@ -191,7 +212,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) if (!skb) { rxrpc_eaten_skb(*_skb, rxrpc_skb_eaten_by_unshare_nomem); *_skb = NULL; - return 0; + return just_discard; } if (skb != *_skb) { @@ -205,28 +226,28 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) case RXRPC_PACKET_TYPE_CHALLENGE: if (rxrpc_to_server(sp)) - return 0; + return just_discard; break; case RXRPC_PACKET_TYPE_RESPONSE: if (rxrpc_to_client(sp)) - return 0; + return just_discard; break; /* Packet types 9-11 should just be ignored. */ case RXRPC_PACKET_TYPE_PARAMS: case RXRPC_PACKET_TYPE_10: case RXRPC_PACKET_TYPE_11: - return 0; + return just_discard; default: - goto bad_message; + return rxrpc_bad_message(skb, rxrpc_badmsg_unsupported_packet); } if (sp->hdr.serviceId == 0) - goto bad_message; + return rxrpc_bad_message(skb, rxrpc_badmsg_zero_service); if (WARN_ON_ONCE(rxrpc_extract_addr_from_skb(&peer_srx, skb) < 0)) - return true; /* Unsupported address type - discard. */ + return just_discard; /* Unsupported address type. */ if (peer_srx.transport.family != local->srx.transport.family && (peer_srx.transport.family == AF_INET && @@ -234,7 +255,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n", peer_srx.transport.family, local->srx.transport.family); - return true; /* Wrong address type - discard. */ + return just_discard; /* Wrong address type. */ } if (rxrpc_to_client(sp)) { @@ -242,12 +263,8 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) conn = rxrpc_find_client_connection_rcu(local, &peer_srx, skb); conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input); rcu_read_unlock(); - if (!conn) { - trace_rxrpc_abort(0, "NCC", sp->hdr.cid, - sp->hdr.callNumber, sp->hdr.seq, - RXKADINCONSISTENCY, EBADMSG); - goto protocol_error; - } + if (!conn) + return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_conn); ret = rxrpc_input_packet_on_conn(conn, &peer_srx, skb); rxrpc_put_connection(conn, rxrpc_conn_put_call_input); @@ -280,19 +297,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) ret = rxrpc_new_incoming_call(local, peer, NULL, &peer_srx, skb); rxrpc_put_peer(peer, rxrpc_peer_put_input); - if (ret < 0) - goto reject_packet; - return 0; - -bad_message: - trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_PROTOCOL_ERROR, EBADMSG); -protocol_error: - skb->priority = RX_PROTOCOL_ERROR; - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; -reject_packet: - rxrpc_reject_packet(local, skb); - return 0; + return ret; } /* @@ -306,21 +311,23 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, struct rxrpc_channel *chan; struct rxrpc_call *call = NULL; unsigned int channel; + bool ret; if (sp->hdr.securityIndex != conn->security_ix) - goto wrong_security; + return rxrpc_direct_abort(skb, rxrpc_eproto_wrong_security, + RXKADINCONSISTENCY, -EBADMSG); if (sp->hdr.serviceId != conn->service_id) { int old_id; if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) - goto reupgrade; + return rxrpc_protocol_error(skb, rxrpc_eproto_reupgrade); + old_id = cmpxchg(&conn->service_id, conn->orig_service_id, sp->hdr.serviceId); - if (old_id != conn->orig_service_id && old_id != sp->hdr.serviceId) - goto reupgrade; + return rxrpc_protocol_error(skb, rxrpc_eproto_bad_upgrade); } if (after(sp->hdr.serial, conn->hi_serial)) @@ -336,19 +343,19 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, /* Ignore really old calls */ if (sp->hdr.callNumber < chan->last_call) - return 0; + return just_discard; if (sp->hdr.callNumber == chan->last_call) { if (chan->call || sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) - return 0; + return just_discard; /* For the previous service call, if completed successfully, we * discard all further packets. */ if (rxrpc_conn_is_service(conn) && chan->last_type == RXRPC_PACKET_TYPE_ACK) - return 0; + return just_discard; /* But otherwise we need to retransmit the final packet from * data cached in the connection record. @@ -358,19 +365,17 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, sp->hdr.seq, sp->hdr.serial, sp->hdr.flags); - rxrpc_input_conn_packet(conn, skb); - return 0; + rxrpc_conn_retransmit_call(conn, skb, channel); + return just_discard; } - rcu_read_lock(); - call = rxrpc_try_get_call(rcu_dereference(chan->call), - rxrpc_call_get_input); - rcu_read_unlock(); + call = rxrpc_try_get_call(chan->call, rxrpc_call_get_input); if (sp->hdr.callNumber > chan->call_id) { if (rxrpc_to_client(sp)) { rxrpc_put_call(call, rxrpc_call_put_input); - goto reject_packet; + return rxrpc_protocol_error(skb, + rxrpc_eproto_unexpected_implicit_end); } if (call) { @@ -382,38 +387,14 @@ static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, if (!call) { if (rxrpc_to_client(sp)) - goto bad_message; - if (rxrpc_new_incoming_call(conn->local, conn->peer, conn, - peer_srx, skb) == 0) - return 0; - goto reject_packet; + return rxrpc_protocol_error(skb, rxrpc_eproto_no_client_call); + return rxrpc_new_incoming_call(conn->local, conn->peer, conn, + peer_srx, skb); } - rxrpc_input_call_event(call, skb); + ret = rxrpc_input_call_event(call, skb); rxrpc_put_call(call, rxrpc_call_put_input); - return 0; - -wrong_security: - trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RXKADINCONSISTENCY, EBADMSG); - skb->priority = RXKADINCONSISTENCY; - goto post_abort; - -reupgrade: - trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_PROTOCOL_ERROR, EBADMSG); - goto protocol_error; - -bad_message: - trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_PROTOCOL_ERROR, EBADMSG); -protocol_error: - skb->priority = RX_PROTOCOL_ERROR; -post_abort: - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; -reject_packet: - rxrpc_reject_packet(conn->local, skb); - return 0; + return ret; } /* @@ -421,6 +402,7 @@ reject_packet: */ int rxrpc_io_thread(void *data) { + struct rxrpc_connection *conn; struct sk_buff_head rx_queue; struct rxrpc_local *local = data; struct rxrpc_call *call; @@ -436,6 +418,24 @@ int rxrpc_io_thread(void *data) for (;;) { rxrpc_inc_stat(local->rxnet, stat_io_loop); + /* Deal with connections that want immediate attention. */ + conn = list_first_entry_or_null(&local->conn_attend_q, + struct rxrpc_connection, + attend_link); + if (conn) { + spin_lock_bh(&local->lock); + list_del_init(&conn->attend_link); + spin_unlock_bh(&local->lock); + + rxrpc_input_conn_event(conn, NULL); + rxrpc_put_connection(conn, rxrpc_conn_put_poke); + continue; + } + + if (test_and_clear_bit(RXRPC_CLIENT_CONN_REAP_TIMER, + &local->client_conn_flags)) + rxrpc_discard_expired_client_conns(local); + /* Deal with calls that want immediate attention. */ if ((call = list_first_entry_or_null(&local->call_attend_q, struct rxrpc_call, @@ -450,12 +450,17 @@ int rxrpc_io_thread(void *data) continue; } + if (!list_empty(&local->new_client_calls)) + rxrpc_connect_client_calls(local); + /* Process received packets and errors. */ if ((skb = __skb_dequeue(&rx_queue))) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); switch (skb->mark) { case RXRPC_SKB_MARK_PACKET: skb->priority = 0; - rxrpc_input_packet(local, &skb); + if (!rxrpc_input_packet(local, &skb)) + rxrpc_reject_packet(local, skb); trace_rxrpc_rx_done(skb->mark, skb->priority); rxrpc_free_skb(skb, rxrpc_skb_put_input); break; @@ -463,6 +468,11 @@ int rxrpc_io_thread(void *data) rxrpc_input_error(local, skb); rxrpc_free_skb(skb, rxrpc_skb_put_error_report); break; + case RXRPC_SKB_MARK_SERVICE_CONN_SECURED: + rxrpc_input_conn_event(sp->conn, skb); + rxrpc_put_connection(sp->conn, rxrpc_conn_put_poke); + rxrpc_free_skb(skb, rxrpc_skb_put_conn_secured); + break; default: WARN_ON_ONCE(1); rxrpc_free_skb(skb, rxrpc_skb_put_unknown); @@ -481,7 +491,11 @@ int rxrpc_io_thread(void *data) set_current_state(TASK_INTERRUPTIBLE); should_stop = kthread_should_stop(); if (!skb_queue_empty(&local->rx_queue) || - !list_empty(&local->call_attend_q)) { + !list_empty(&local->call_attend_q) || + !list_empty(&local->conn_attend_q) || + !list_empty(&local->new_client_calls) || + test_bit(RXRPC_CLIENT_CONN_REAP_TIMER, + &local->client_conn_flags)) { __set_current_state(TASK_RUNNING); continue; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 270b63d8f37a..b8eaca5d9f22 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -82,31 +82,59 @@ static long rxrpc_local_cmp_key(const struct rxrpc_local *local, } } +static void rxrpc_client_conn_reap_timeout(struct timer_list *timer) +{ + struct rxrpc_local *local = + container_of(timer, struct rxrpc_local, client_conn_reap_timer); + + if (local->kill_all_client_conns && + test_and_set_bit(RXRPC_CLIENT_CONN_REAP_TIMER, &local->client_conn_flags)) + rxrpc_wake_up_io_thread(local); +} + /* * Allocate a new local endpoint. */ -static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, +static struct rxrpc_local *rxrpc_alloc_local(struct net *net, const struct sockaddr_rxrpc *srx) { struct rxrpc_local *local; + u32 tmp; local = kzalloc(sizeof(struct rxrpc_local), GFP_KERNEL); if (local) { refcount_set(&local->ref, 1); atomic_set(&local->active_users, 1); - local->rxnet = rxnet; + local->net = net; + local->rxnet = rxrpc_net(net); INIT_HLIST_NODE(&local->link); init_rwsem(&local->defrag_sem); init_completion(&local->io_thread_ready); skb_queue_head_init(&local->rx_queue); + INIT_LIST_HEAD(&local->conn_attend_q); INIT_LIST_HEAD(&local->call_attend_q); + local->client_bundles = RB_ROOT; spin_lock_init(&local->client_bundles_lock); + local->kill_all_client_conns = false; + INIT_LIST_HEAD(&local->idle_client_conns); + timer_setup(&local->client_conn_reap_timer, + rxrpc_client_conn_reap_timeout, 0); + spin_lock_init(&local->lock); rwlock_init(&local->services_lock); local->debug_id = atomic_inc_return(&rxrpc_debug_id); memcpy(&local->srx, srx, sizeof(*srx)); local->srx.srx_service = 0; + idr_init(&local->conn_ids); + get_random_bytes(&tmp, sizeof(tmp)); + tmp &= 0x3fffffff; + if (tmp == 0) + tmp = 1; + idr_set_cursor(&local->conn_ids, tmp); + INIT_LIST_HEAD(&local->new_client_calls); + spin_lock_init(&local->client_call_lock); + trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, 1); } @@ -248,7 +276,7 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, goto found; } - local = rxrpc_alloc_local(rxnet, srx); + local = rxrpc_alloc_local(net, srx); if (!local) goto nomem; @@ -407,6 +435,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local) * local endpoint. */ rxrpc_purge_queue(&local->rx_queue); + rxrpc_purge_client_connections(local); } /* diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 5905530e2f33..a0319c040c25 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -10,15 +10,6 @@ unsigned int rxrpc_net_id; -static void rxrpc_client_conn_reap_timeout(struct timer_list *timer) -{ - struct rxrpc_net *rxnet = - container_of(timer, struct rxrpc_net, client_conn_reap_timer); - - if (rxnet->live) - rxrpc_queue_work(&rxnet->client_conn_reaper); -} - static void rxrpc_service_conn_reap_timeout(struct timer_list *timer) { struct rxrpc_net *rxnet = @@ -63,14 +54,6 @@ static __net_init int rxrpc_init_net(struct net *net) rxrpc_service_conn_reap_timeout, 0); atomic_set(&rxnet->nr_client_conns, 0); - rxnet->kill_all_client_conns = false; - spin_lock_init(&rxnet->client_conn_cache_lock); - mutex_init(&rxnet->client_conn_discard_lock); - INIT_LIST_HEAD(&rxnet->idle_client_conns); - INIT_WORK(&rxnet->client_conn_reaper, - rxrpc_discard_expired_client_conns); - timer_setup(&rxnet->client_conn_reap_timer, - rxrpc_client_conn_reap_timeout, 0); INIT_HLIST_HEAD(&rxnet->local_endpoints); mutex_init(&rxnet->local_mutex); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 3d8c9f830ee0..a9746be29634 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -261,7 +261,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) rxrpc_tx_point_call_ack); rxrpc_tx_backoff(call, ret); - if (call->state < RXRPC_CALL_COMPLETE) { + if (!__rxrpc_call_is_complete(call)) { if (ret < 0) rxrpc_cancel_rtt_probe(call, serial, rtt_slot); rxrpc_set_keepalive(call); @@ -545,6 +545,62 @@ send_fragmentable: } /* + * Transmit a connection-level abort. + */ +void rxrpc_send_conn_abort(struct rxrpc_connection *conn) +{ + struct rxrpc_wire_header whdr; + struct msghdr msg; + struct kvec iov[2]; + __be32 word; + size_t len; + u32 serial; + int ret; + + msg.msg_name = &conn->peer->srx.transport; + msg.msg_namelen = conn->peer->srx.transport_len; + msg.msg_control = NULL; + msg.msg_controllen = 0; + msg.msg_flags = 0; + + whdr.epoch = htonl(conn->proto.epoch); + whdr.cid = htonl(conn->proto.cid); + whdr.callNumber = 0; + whdr.seq = 0; + whdr.type = RXRPC_PACKET_TYPE_ABORT; + whdr.flags = conn->out_clientflag; + whdr.userStatus = 0; + whdr.securityIndex = conn->security_ix; + whdr._rsvd = 0; + whdr.serviceId = htons(conn->service_id); + + word = htonl(conn->abort_code); + + iov[0].iov_base = &whdr; + iov[0].iov_len = sizeof(whdr); + iov[1].iov_base = &word; + iov[1].iov_len = sizeof(word); + + len = iov[0].iov_len + iov[1].iov_len; + + serial = atomic_inc_return(&conn->serial); + whdr.serial = htonl(serial); + + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); + ret = do_udp_sendmsg(conn->local->socket, &msg, len); + if (ret < 0) { + trace_rxrpc_tx_fail(conn->debug_id, serial, ret, + rxrpc_tx_point_conn_abort); + _debug("sendmsg failed: %d", ret); + return; + } + + trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort); + + conn->peer->last_tx_at = ktime_get_seconds(); +} + +/* * Reject a packet through the local endpoint. */ void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) @@ -667,7 +723,7 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) static inline void rxrpc_instant_resend(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { - if (call->state < RXRPC_CALL_COMPLETE) + if (!__rxrpc_call_is_complete(call)) kdebug("resend"); } diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 4eecea2be307..8d7a715a0bb1 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -147,10 +147,10 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *local, * assess the MTU size for the network interface through which this peer is * reached */ -static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx, +static void rxrpc_assess_MTU_size(struct rxrpc_local *local, struct rxrpc_peer *peer) { - struct net *net = sock_net(&rx->sk); + struct net *net = local->net; struct dst_entry *dst; struct rtable *rt; struct flowi fl; @@ -236,11 +236,11 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp, /* * Initialise peer record. */ -static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer, +static void rxrpc_init_peer(struct rxrpc_local *local, struct rxrpc_peer *peer, unsigned long hash_key) { peer->hash_key = hash_key; - rxrpc_assess_MTU_size(rx, peer); + rxrpc_assess_MTU_size(local, peer); peer->mtu = peer->if_mtu; peer->rtt_last_req = ktime_get_real(); @@ -272,8 +272,7 @@ static void rxrpc_init_peer(struct rxrpc_sock *rx, struct rxrpc_peer *peer, /* * Set up a new peer. */ -static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, - struct rxrpc_local *local, +static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, unsigned long hash_key, gfp_t gfp) @@ -285,7 +284,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, peer = rxrpc_alloc_peer(local, gfp, rxrpc_peer_new_client); if (peer) { memcpy(&peer->srx, srx, sizeof(*srx)); - rxrpc_init_peer(rx, peer, hash_key); + rxrpc_init_peer(local, peer, hash_key); } _leave(" = %p", peer); @@ -304,14 +303,13 @@ static void rxrpc_free_peer(struct rxrpc_peer *peer) * since we've already done a search in the list from the non-reentrant context * (the data_ready handler) that is the only place we can add new peers. */ -void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, - struct rxrpc_peer *peer) +void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer) { struct rxrpc_net *rxnet = local->rxnet; unsigned long hash_key; hash_key = rxrpc_peer_hash_key(local, &peer->srx); - rxrpc_init_peer(rx, peer, hash_key); + rxrpc_init_peer(local, peer, hash_key); spin_lock(&rxnet->peer_hash_lock); hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key); @@ -322,8 +320,7 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, /* * obtain a remote transport endpoint for the specified address */ -struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, - struct rxrpc_local *local, +struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *local, struct sockaddr_rxrpc *srx, gfp_t gfp) { struct rxrpc_peer *peer, *candidate; @@ -343,7 +340,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, /* The peer is not yet present in hash - create a candidate * for a new record and then redo the search. */ - candidate = rxrpc_create_peer(rx, local, srx, hash_key, gfp); + candidate = rxrpc_create_peer(local, srx, hash_key, gfp); if (!candidate) { _leave(" = NULL [nomem]"); return NULL; diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 3a59591ec061..750158a085cd 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -12,13 +12,13 @@ static const char *const rxrpc_conn_states[RXRPC_CONN__NR_STATES] = { [RXRPC_CONN_UNUSED] = "Unused ", + [RXRPC_CONN_CLIENT_UNSECURED] = "ClUnsec ", [RXRPC_CONN_CLIENT] = "Client ", [RXRPC_CONN_SERVICE_PREALLOC] = "SvPrealc", [RXRPC_CONN_SERVICE_UNSECURED] = "SvUnsec ", [RXRPC_CONN_SERVICE_CHALLENGING] = "SvChall ", [RXRPC_CONN_SERVICE] = "SvSecure", - [RXRPC_CONN_REMOTELY_ABORTED] = "RmtAbort", - [RXRPC_CONN_LOCALLY_ABORTED] = "LocAbort", + [RXRPC_CONN_ABORTED] = "Aborted ", }; /* @@ -51,6 +51,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_local *local; struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + enum rxrpc_call_state state; unsigned long timeout = 0; rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; @@ -75,7 +76,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) sprintf(rbuff, "%pISpc", &call->dest_srx.transport); - if (call->state != RXRPC_CALL_SERVER_PREALLOC) { + state = rxrpc_call_state(call); + if (state != RXRPC_CALL_SERVER_PREALLOC) { timeout = READ_ONCE(call->expect_rx_by); timeout -= jiffies; } @@ -92,7 +94,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call->call_id, rxrpc_is_service_call(call) ? "Svc" : "Clt", refcount_read(&call->ref), - rxrpc_call_states[call->state], + rxrpc_call_states[state], call->abort_code, call->debug_id, acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack, @@ -143,6 +145,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) { struct rxrpc_connection *conn; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); + const char *state; char lbuff[50], rbuff[50]; if (v == &rxnet->conn_proc_list) { @@ -163,9 +166,11 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) } sprintf(lbuff, "%pISpc", &conn->local->srx.transport); - sprintf(rbuff, "%pISpc", &conn->peer->srx.transport); print: + state = rxrpc_is_conn_aborted(conn) ? + rxrpc_call_completions[conn->completion] : + rxrpc_conn_states[conn->state]; seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %s %3u %3d" " %s %08x %08x %08x %08x %08x %08x %08x\n", @@ -176,7 +181,7 @@ print: rxrpc_conn_is_service(conn) ? "Svc" : "Clt", refcount_read(&conn->ref), atomic_read(&conn->active), - rxrpc_conn_states[conn->state], + state, key_serial(conn->key), atomic_read(&conn->serial), conn->hi_serial, diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 6ebd6440a2b7..dd54ceee7bcc 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -59,85 +59,6 @@ void rxrpc_notify_socket(struct rxrpc_call *call) } /* - * Transition a call to the complete state. - */ -bool __rxrpc_set_call_completion(struct rxrpc_call *call, - enum rxrpc_call_completion compl, - u32 abort_code, - int error) -{ - if (call->state < RXRPC_CALL_COMPLETE) { - call->abort_code = abort_code; - call->error = error; - call->completion = compl; - call->state = RXRPC_CALL_COMPLETE; - trace_rxrpc_call_complete(call); - wake_up(&call->waitq); - rxrpc_notify_socket(call); - return true; - } - return false; -} - -bool rxrpc_set_call_completion(struct rxrpc_call *call, - enum rxrpc_call_completion compl, - u32 abort_code, - int error) -{ - bool ret = false; - - if (call->state < RXRPC_CALL_COMPLETE) { - write_lock(&call->state_lock); - ret = __rxrpc_set_call_completion(call, compl, abort_code, error); - write_unlock(&call->state_lock); - } - return ret; -} - -/* - * Record that a call successfully completed. - */ -bool __rxrpc_call_completed(struct rxrpc_call *call) -{ - return __rxrpc_set_call_completion(call, RXRPC_CALL_SUCCEEDED, 0, 0); -} - -bool rxrpc_call_completed(struct rxrpc_call *call) -{ - bool ret = false; - - if (call->state < RXRPC_CALL_COMPLETE) { - write_lock(&call->state_lock); - ret = __rxrpc_call_completed(call); - write_unlock(&call->state_lock); - } - return ret; -} - -/* - * Record that a call is locally aborted. - */ -bool __rxrpc_abort_call(const char *why, struct rxrpc_call *call, - rxrpc_seq_t seq, u32 abort_code, int error) -{ - trace_rxrpc_abort(call->debug_id, why, call->cid, call->call_id, seq, - abort_code, error); - return __rxrpc_set_call_completion(call, RXRPC_CALL_LOCALLY_ABORTED, - abort_code, error); -} - -bool rxrpc_abort_call(const char *why, struct rxrpc_call *call, - rxrpc_seq_t seq, u32 abort_code, int error) -{ - bool ret; - - write_lock(&call->state_lock); - ret = __rxrpc_abort_call(why, call, seq, abort_code, error); - write_unlock(&call->state_lock); - return ret; -} - -/* * Pass a call terminating message to userspace. */ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) @@ -168,7 +89,7 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) ret = put_cmsg(msg, SOL_RXRPC, RXRPC_LOCAL_ERROR, 4, &tmp); break; default: - pr_err("Invalid terminal call state %u\n", call->state); + pr_err("Invalid terminal call state %u\n", call->completion); BUG(); break; } @@ -180,41 +101,6 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) } /* - * End the packet reception phase. - */ -static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) -{ - rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); - - _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]); - - trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); - - if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) - rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); - - write_lock(&call->state_lock); - - switch (call->state) { - case RXRPC_CALL_CLIENT_RECV_REPLY: - __rxrpc_call_completed(call); - write_unlock(&call->state_lock); - break; - - case RXRPC_CALL_SERVER_RECV_REQUEST: - call->state = RXRPC_CALL_SERVER_ACK_REQUEST; - call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; - write_unlock(&call->state_lock); - rxrpc_propose_delay_ACK(call, serial, - rxrpc_propose_ack_processing_op); - break; - default: - write_unlock(&call->state_lock); - break; - } -} - -/* * Discard a packet we've used up and advance the Rx window by one. */ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) @@ -244,10 +130,9 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate, serial, call->rx_consumed); - if (last) { - rxrpc_end_rx_phase(call, serial); - return; - } + + if (last) + set_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags); /* Check to see if there's an ACK that needs sending. */ acked = atomic_add_return(call->rx_consumed - old_consumed, @@ -272,7 +157,8 @@ static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb) /* * Deliver messages to a call. This keeps processing packets until the buffer * is filled and we find either more DATA (returns 0) or the end of the DATA - * (returns 1). If more packets are required, it returns -EAGAIN. + * (returns 1). If more packets are required, it returns -EAGAIN and if the + * call has failed it returns -EIO. */ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, struct msghdr *msg, struct iov_iter *iter, @@ -288,7 +174,13 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; - if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { + if (rxrpc_call_has_failed(call)) { + seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; + ret = -EIO; + goto done; + } + + if (test_bit(RXRPC_CALL_RECVMSG_READ_ALL, &call->flags)) { seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; ret = 1; goto done; @@ -312,14 +204,15 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (rx_pkt_offset == 0) { ret2 = rxrpc_verify_data(call, skb); - rx_pkt_offset = sp->offset; - rx_pkt_len = sp->len; trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, - rx_pkt_offset, rx_pkt_len, ret2); + sp->offset, sp->len, ret2); if (ret2 < 0) { + kdebug("verify = %d", ret2); ret = ret2; goto out; } + rx_pkt_offset = sp->offset; + rx_pkt_len = sp->len; } else { trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, rx_pkt_offset, rx_pkt_len, 0); @@ -494,36 +387,36 @@ try_again: msg->msg_namelen = len; } - switch (READ_ONCE(call->state)) { - case RXRPC_CALL_CLIENT_RECV_REPLY: - case RXRPC_CALL_SERVER_RECV_REQUEST: - case RXRPC_CALL_SERVER_ACK_REQUEST: - ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len, - flags, &copied); - if (ret == -EAGAIN) - ret = 0; - - if (!skb_queue_empty(&call->recvmsg_queue)) - rxrpc_notify_socket(call); - break; - default: + ret = rxrpc_recvmsg_data(sock, call, msg, &msg->msg_iter, len, + flags, &copied); + if (ret == -EAGAIN) ret = 0; - break; - } - + if (ret == -EIO) + goto call_failed; if (ret < 0) goto error_unlock_call; - if (call->state == RXRPC_CALL_COMPLETE) { - ret = rxrpc_recvmsg_term(call, msg); - if (ret < 0) - goto error_unlock_call; - if (!(flags & MSG_PEEK)) - rxrpc_release_call(rx, call); - msg->msg_flags |= MSG_EOR; - ret = 1; - } + if (rxrpc_call_is_complete(call) && + skb_queue_empty(&call->recvmsg_queue)) + goto call_complete; + if (rxrpc_call_has_failed(call)) + goto call_failed; + rxrpc_notify_socket(call); + goto not_yet_complete; + +call_failed: + rxrpc_purge_queue(&call->recvmsg_queue); +call_complete: + ret = rxrpc_recvmsg_term(call, msg); + if (ret < 0) + goto error_unlock_call; + if (!(flags & MSG_PEEK)) + rxrpc_release_call(rx, call); + msg->msg_flags |= MSG_EOR; + ret = 1; + +not_yet_complete: if (ret == 0) msg->msg_flags |= MSG_MORE; else @@ -586,49 +479,34 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, size_t offset = 0; int ret; - _enter("{%d,%s},%zu,%d", - call->debug_id, rxrpc_call_states[call->state], - *_len, want_more); - - ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_SECURING); + _enter("{%d},%zu,%d", call->debug_id, *_len, want_more); mutex_lock(&call->user_mutex); - switch (READ_ONCE(call->state)) { - case RXRPC_CALL_CLIENT_RECV_REPLY: - case RXRPC_CALL_SERVER_RECV_REQUEST: - case RXRPC_CALL_SERVER_ACK_REQUEST: - ret = rxrpc_recvmsg_data(sock, call, NULL, iter, - *_len, 0, &offset); - *_len -= offset; - if (ret < 0) - goto out; - - /* We can only reach here with a partially full buffer if we - * have reached the end of the data. We must otherwise have a - * full buffer or have been given -EAGAIN. - */ - if (ret == 1) { - if (iov_iter_count(iter) > 0) - goto short_data; - if (!want_more) - goto read_phase_complete; - ret = 0; - goto out; - } - - if (!want_more) - goto excess_data; + ret = rxrpc_recvmsg_data(sock, call, NULL, iter, *_len, 0, &offset); + *_len -= offset; + if (ret == -EIO) + goto call_failed; + if (ret < 0) goto out; - case RXRPC_CALL_COMPLETE: - goto call_complete; - - default: - ret = -EINPROGRESS; + /* We can only reach here with a partially full buffer if we have + * reached the end of the data. We must otherwise have a full buffer + * or have been given -EAGAIN. + */ + if (ret == 1) { + if (iov_iter_count(iter) > 0) + goto short_data; + if (!want_more) + goto read_phase_complete; + ret = 0; goto out; } + if (!want_more) + goto excess_data; + goto out; + read_phase_complete: ret = 1; out: @@ -639,14 +517,18 @@ out: return ret; short_data: - trace_rxrpc_rx_eproto(call, 0, tracepoint_string("short_data")); + trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_short_data, + call->cid, call->call_id, call->rx_consumed, + 0, -EBADMSG); ret = -EBADMSG; goto out; excess_data: - trace_rxrpc_rx_eproto(call, 0, tracepoint_string("excess_data")); + trace_rxrpc_abort(call->debug_id, rxrpc_recvmsg_excess_data, + call->cid, call->call_id, call->rx_consumed, + 0, -EMSGSIZE); ret = -EMSGSIZE; goto out; -call_complete: +call_failed: *_abort = call->abort_code; ret = call->error; if (call->completion == RXRPC_CALL_SUCCEEDED) { diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index d1233720e05f..1bf571a66e02 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -411,18 +411,15 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist sg[16]; - bool aborted; u32 data_size, buf; u16 check; int ret; _enter(""); - if (sp->len < 8) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H", - RXKADSEALEDINCON); - goto protocol_error; - } + if (sp->len < 8) + return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_1_short_header); /* Decrypt the skbuff in-place. TODO: We really want to decrypt * directly into the target buffer. @@ -442,11 +439,9 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_zero(req); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1", - RXKADDATALEN); - goto protocol_error; - } + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) + return rxrpc_abort_eproto(call, skb, RXKADDATALEN, + rxkad_abort_1_short_encdata); sp->offset += sizeof(sechdr); sp->len -= sizeof(sechdr); @@ -456,26 +451,16 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, check = buf >> 16; check ^= seq ^ call->call_id; check &= 0xffff; - if (check != 0) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_check", "V1C", - RXKADSEALEDINCON); - goto protocol_error; - } - - if (data_size > sp->len) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L", - RXKADDATALEN); - goto protocol_error; - } + if (check != 0) + return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_1_short_check); + if (data_size > sp->len) + return rxrpc_abort_eproto(call, skb, RXKADDATALEN, + rxkad_abort_1_short_data); sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; - -protocol_error: - if (aborted) - rxrpc_send_abort_packet(call); - return -EPROTO; } /* @@ -490,18 +475,15 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; - bool aborted; u32 data_size, buf; u16 check; int nsg, ret; _enter(",{%d}", sp->len); - if (sp->len < 8) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H", - RXKADSEALEDINCON); - goto protocol_error; - } + if (sp->len < 8) + return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_2_short_header); /* Decrypt the skbuff in-place. TODO: We really want to decrypt * directly into the target buffer. @@ -513,7 +495,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, } else { sg = kmalloc_array(nsg, sizeof(*sg), GFP_NOIO); if (!sg) - goto nomem; + return -ENOMEM; } sg_init_table(sg, nsg); @@ -537,11 +519,9 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, kfree(sg); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2", - RXKADDATALEN); - goto protocol_error; - } + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) + return rxrpc_abort_eproto(call, skb, RXKADDATALEN, + rxkad_abort_2_short_len); sp->offset += sizeof(sechdr); sp->len -= sizeof(sechdr); @@ -551,30 +531,17 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, check = buf >> 16; check ^= seq ^ call->call_id; check &= 0xffff; - if (check != 0) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_check", "V2C", - RXKADSEALEDINCON); - goto protocol_error; - } + if (check != 0) + return rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_2_short_check); - if (data_size > sp->len) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L", - RXKADDATALEN); - goto protocol_error; - } + if (data_size > sp->len) + return rxrpc_abort_eproto(call, skb, RXKADDATALEN, + rxkad_abort_2_short_data); sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; - -protocol_error: - if (aborted) - rxrpc_send_abort_packet(call); - return -EPROTO; - -nomem: - _leave(" = -ENOMEM"); - return -ENOMEM; } /* @@ -590,7 +557,6 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) __be32 buf[2]; } crypto __aligned(8); rxrpc_seq_t seq = sp->hdr.seq; - bool aborted; int ret; u16 cksum; u32 x, y; @@ -627,9 +593,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) cksum = 1; /* zero checksums are not permitted */ if (cksum != sp->hdr.cksum) { - aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK", - RXKADSEALEDINCON); - goto protocol_error; + ret = rxrpc_abort_eproto(call, skb, RXKADSEALEDINCON, + rxkad_abort_bad_checksum); + goto out; } switch (call->conn->security_level) { @@ -647,13 +613,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) break; } +out: skcipher_request_free(req); return ret; - -protocol_error: - if (aborted) - rxrpc_send_abort_packet(call); - return -EPROTO; } /* @@ -821,34 +783,30 @@ static int rxkad_encrypt_response(struct rxrpc_connection *conn, * respond to a challenge packet */ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { const struct rxrpc_key_token *token; struct rxkad_challenge challenge; struct rxkad_response *resp; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - const char *eproto; - u32 version, nonce, min_level, abort_code; - int ret; + u32 version, nonce, min_level; + int ret = -EPROTO; _enter("{%d,%x}", conn->debug_id, key_serial(conn->key)); - eproto = tracepoint_string("chall_no_key"); - abort_code = RX_PROTOCOL_ERROR; if (!conn->key) - goto protocol_error; + return rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO, + rxkad_abort_chall_no_key); - abort_code = RXKADEXPIRED; ret = key_validate(conn->key); if (ret < 0) - goto other_error; + return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret, + rxkad_abort_chall_key_expired); - eproto = tracepoint_string("chall_short"); - abort_code = RXKADPACKETSHORT; if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), &challenge, sizeof(challenge)) < 0) - goto protocol_error; + return rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, + rxkad_abort_chall_short); version = ntohl(challenge.version); nonce = ntohl(challenge.nonce); @@ -856,15 +814,13 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, nonce, min_level); - eproto = tracepoint_string("chall_ver"); - abort_code = RXKADINCONSISTENCY; if (version != RXKAD_VERSION) - goto protocol_error; + return rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO, + rxkad_abort_chall_version); - abort_code = RXKADLEVELFAIL; - ret = -EACCES; if (conn->security_level < min_level) - goto other_error; + return rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EACCES, + rxkad_abort_chall_level); token = conn->key->payload.data[0]; @@ -893,13 +849,6 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, ret = rxkad_send_response(conn, &sp->hdr, resp, token->kad); kfree(resp); return ret; - -protocol_error: - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); - ret = -EPROTO; -other_error: - *_abort_code = abort_code; - return ret; } /* @@ -910,20 +859,15 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, struct sk_buff *skb, void *ticket, size_t ticket_len, struct rxrpc_crypt *_session_key, - time64_t *_expiry, - u32 *_abort_code) + time64_t *_expiry) { struct skcipher_request *req; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv, key; struct scatterlist sg[1]; struct in_addr addr; unsigned int life; - const char *eproto; time64_t issue, now; bool little_endian; - int ret; - u32 abort_code; u8 *p, *q, *name, *end; _enter("{%d},{%x}", conn->debug_id, key_serial(server_key)); @@ -935,10 +879,9 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, memcpy(&iv, &server_key->payload.data[2], sizeof(iv)); - ret = -ENOMEM; req = skcipher_request_alloc(server_key->payload.data[0], GFP_NOFS); if (!req) - goto temporary_error; + return -ENOMEM; sg_init_one(&sg[0], ticket, ticket_len); skcipher_request_set_callback(req, 0, NULL, NULL); @@ -949,18 +892,21 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, p = ticket; end = p + ticket_len; -#define Z(field) \ - ({ \ - u8 *__str = p; \ - eproto = tracepoint_string("rxkad_bad_"#field); \ - q = memchr(p, 0, end - p); \ - if (!q || q - p > (field##_SZ)) \ - goto bad_ticket; \ - for (; p < q; p++) \ - if (!isprint(*p)) \ - goto bad_ticket; \ - p++; \ - __str; \ +#define Z(field, fieldl) \ + ({ \ + u8 *__str = p; \ + q = memchr(p, 0, end - p); \ + if (!q || q - p > field##_SZ) \ + return rxrpc_abort_conn( \ + conn, skb, RXKADBADTICKET, -EPROTO, \ + rxkad_abort_resp_tkt_##fieldl); \ + for (; p < q; p++) \ + if (!isprint(*p)) \ + return rxrpc_abort_conn( \ + conn, skb, RXKADBADTICKET, -EPROTO, \ + rxkad_abort_resp_tkt_##fieldl); \ + p++; \ + __str; \ }) /* extract the ticket flags */ @@ -969,20 +915,20 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, p++; /* extract the authentication name */ - name = Z(ANAME); + name = Z(ANAME, aname); _debug("KIV ANAME: %s", name); /* extract the principal's instance */ - name = Z(INST); + name = Z(INST, inst); _debug("KIV INST : %s", name); /* extract the principal's authentication domain */ - name = Z(REALM); + name = Z(REALM, realm); _debug("KIV REALM: %s", name); - eproto = tracepoint_string("rxkad_bad_len"); if (end - p < 4 + 8 + 4 + 2) - goto bad_ticket; + return rxrpc_abort_conn(conn, skb, RXKADBADTICKET, -EPROTO, + rxkad_abort_resp_tkt_short); /* get the IPv4 address of the entity that requested the ticket */ memcpy(&addr, p, sizeof(addr)); @@ -1014,38 +960,23 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn, _debug("KIV ISSUE: %llx [%llx]", issue, now); /* check the ticket is in date */ - if (issue > now) { - abort_code = RXKADNOAUTH; - ret = -EKEYREJECTED; - goto other_error; - } - - if (issue < now - life) { - abort_code = RXKADEXPIRED; - ret = -EKEYEXPIRED; - goto other_error; - } + if (issue > now) + return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, -EKEYREJECTED, + rxkad_abort_resp_tkt_future); + if (issue < now - life) + return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, -EKEYEXPIRED, + rxkad_abort_resp_tkt_expired); *_expiry = issue + life; /* get the service name */ - name = Z(SNAME); + name = Z(SNAME, sname); _debug("KIV SNAME: %s", name); /* get the service instance name */ - name = Z(INST); + name = Z(INST, sinst); _debug("KIV SINST: %s", name); return 0; - -bad_ticket: - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); - abort_code = RXKADBADTICKET; - ret = -EPROTO; -other_error: - *_abort_code = abort_code; - return ret; -temporary_error: - return ret; } /* @@ -1086,17 +1017,15 @@ static void rxkad_decrypt_response(struct rxrpc_connection *conn, * verify a response */ static int rxkad_verify_response(struct rxrpc_connection *conn, - struct sk_buff *skb, - u32 *_abort_code) + struct sk_buff *skb) { struct rxkad_response *response; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt session_key; struct key *server_key; - const char *eproto; time64_t expiry; void *ticket; - u32 abort_code, version, kvno, ticket_len, level; + u32 version, kvno, ticket_len, level; __be32 csum; int ret, i; @@ -1104,22 +1033,18 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, server_key = rxrpc_look_up_server_security(conn, skb, 0, 0); if (IS_ERR(server_key)) { - switch (PTR_ERR(server_key)) { + ret = PTR_ERR(server_key); + switch (ret) { case -ENOKEY: - abort_code = RXKADUNKNOWNKEY; - break; + return rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, ret, + rxkad_abort_resp_nokey); case -EKEYEXPIRED: - abort_code = RXKADEXPIRED; - break; + return rxrpc_abort_conn(conn, skb, RXKADEXPIRED, ret, + rxkad_abort_resp_key_expired); default: - abort_code = RXKADNOAUTH; - break; + return rxrpc_abort_conn(conn, skb, RXKADNOAUTH, ret, + rxkad_abort_resp_key_rejected); } - trace_rxrpc_abort(0, "SVK", - sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - abort_code, PTR_ERR(server_key)); - *_abort_code = abort_code; - return -EPROTO; } ret = -ENOMEM; @@ -1127,11 +1052,12 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, if (!response) goto temporary_error; - eproto = tracepoint_string("rxkad_rsp_short"); - abort_code = RXKADPACKETSHORT; if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), - response, sizeof(*response)) < 0) + response, sizeof(*response)) < 0) { + rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, + rxkad_abort_resp_short); goto protocol_error; + } version = ntohl(response->version); ticket_len = ntohl(response->ticket_len); @@ -1139,20 +1065,23 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, trace_rxrpc_rx_response(conn, sp->hdr.serial, version, kvno, ticket_len); - eproto = tracepoint_string("rxkad_rsp_ver"); - abort_code = RXKADINCONSISTENCY; - if (version != RXKAD_VERSION) + if (version != RXKAD_VERSION) { + rxrpc_abort_conn(conn, skb, RXKADINCONSISTENCY, -EPROTO, + rxkad_abort_resp_version); goto protocol_error; + } - eproto = tracepoint_string("rxkad_rsp_tktlen"); - abort_code = RXKADTICKETLEN; - if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN) + if (ticket_len < 4 || ticket_len > MAXKRB5TICKETLEN) { + rxrpc_abort_conn(conn, skb, RXKADTICKETLEN, -EPROTO, + rxkad_abort_resp_tkt_len); goto protocol_error; + } - eproto = tracepoint_string("rxkad_rsp_unkkey"); - abort_code = RXKADUNKNOWNKEY; - if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5) + if (kvno >= RXKAD_TKT_TYPE_KERBEROS_V5) { + rxrpc_abort_conn(conn, skb, RXKADUNKNOWNKEY, -EPROTO, + rxkad_abort_resp_unknown_tkt); goto protocol_error; + } /* extract the kerberos ticket and decrypt and decode it */ ret = -ENOMEM; @@ -1160,15 +1089,15 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, if (!ticket) goto temporary_error_free_resp; - eproto = tracepoint_string("rxkad_tkt_short"); - abort_code = RXKADPACKETSHORT; - ret = skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), - ticket, ticket_len); - if (ret < 0) - goto temporary_error_free_ticket; + if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), + ticket, ticket_len) < 0) { + rxrpc_abort_conn(conn, skb, RXKADPACKETSHORT, -EPROTO, + rxkad_abort_resp_short_tkt); + goto protocol_error; + } ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len, - &session_key, &expiry, _abort_code); + &session_key, &expiry); if (ret < 0) goto temporary_error_free_ticket; @@ -1176,56 +1105,61 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, * response */ rxkad_decrypt_response(conn, response, &session_key); - eproto = tracepoint_string("rxkad_rsp_param"); - abort_code = RXKADSEALEDINCON; - if (ntohl(response->encrypted.epoch) != conn->proto.epoch) - goto protocol_error_free; - if (ntohl(response->encrypted.cid) != conn->proto.cid) - goto protocol_error_free; - if (ntohl(response->encrypted.securityIndex) != conn->security_ix) + if (ntohl(response->encrypted.epoch) != conn->proto.epoch || + ntohl(response->encrypted.cid) != conn->proto.cid || + ntohl(response->encrypted.securityIndex) != conn->security_ix) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_bad_param); goto protocol_error_free; + } + csum = response->encrypted.checksum; response->encrypted.checksum = 0; rxkad_calc_response_checksum(response); - eproto = tracepoint_string("rxkad_rsp_csum"); - if (response->encrypted.checksum != csum) + if (response->encrypted.checksum != csum) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_bad_checksum); goto protocol_error_free; + } - spin_lock(&conn->bundle->channel_lock); for (i = 0; i < RXRPC_MAXCALLS; i++) { - struct rxrpc_call *call; u32 call_id = ntohl(response->encrypted.call_id[i]); + u32 counter = READ_ONCE(conn->channels[i].call_counter); + + if (call_id > INT_MAX) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_bad_callid); + goto protocol_error_free; + } - eproto = tracepoint_string("rxkad_rsp_callid"); - if (call_id > INT_MAX) - goto protocol_error_unlock; - - eproto = tracepoint_string("rxkad_rsp_callctr"); - if (call_id < conn->channels[i].call_counter) - goto protocol_error_unlock; - - eproto = tracepoint_string("rxkad_rsp_callst"); - if (call_id > conn->channels[i].call_counter) { - call = rcu_dereference_protected( - conn->channels[i].call, - lockdep_is_held(&conn->bundle->channel_lock)); - if (call && call->state < RXRPC_CALL_COMPLETE) - goto protocol_error_unlock; + if (call_id < counter) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_call_ctr); + goto protocol_error_free; + } + + if (call_id > counter) { + if (conn->channels[i].call) { + rxrpc_abort_conn(conn, skb, RXKADSEALEDINCON, -EPROTO, + rxkad_abort_resp_call_state); + goto protocol_error_free; + } conn->channels[i].call_counter = call_id; } } - spin_unlock(&conn->bundle->channel_lock); - eproto = tracepoint_string("rxkad_rsp_seq"); - abort_code = RXKADOUTOFSEQUENCE; - if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1) + if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1) { + rxrpc_abort_conn(conn, skb, RXKADOUTOFSEQUENCE, -EPROTO, + rxkad_abort_resp_ooseq); goto protocol_error_free; + } - eproto = tracepoint_string("rxkad_rsp_level"); - abort_code = RXKADLEVELFAIL; level = ntohl(response->encrypted.level); - if (level > RXRPC_SECURITY_ENCRYPT) + if (level > RXRPC_SECURITY_ENCRYPT) { + rxrpc_abort_conn(conn, skb, RXKADLEVELFAIL, -EPROTO, + rxkad_abort_resp_level); goto protocol_error_free; + } conn->security_level = level; /* create a key to hold the security data and expiration time - after @@ -1240,15 +1174,11 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, _leave(" = 0"); return 0; -protocol_error_unlock: - spin_unlock(&conn->bundle->channel_lock); protocol_error_free: kfree(ticket); protocol_error: kfree(response); - trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto); key_put(server_key); - *_abort_code = abort_code; return -EPROTO; temporary_error_free_ticket: diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c index d33a109e846c..16dcabb71ebe 100644 --- a/net/rxrpc/rxperf.c +++ b/net/rxrpc/rxperf.c @@ -10,6 +10,8 @@ #include <linux/slab.h> #include <net/sock.h> #include <net/af_rxrpc.h> +#define RXRPC_TRACE_ONLY_DEFINE_ENUMS +#include <trace/events/rxrpc.h> MODULE_DESCRIPTION("rxperf test server (afs)"); MODULE_AUTHOR("Red Hat, Inc."); @@ -307,12 +309,14 @@ static void rxperf_deliver_to_call(struct work_struct *work) case -EOPNOTSUPP: abort_code = RXGEN_OPCODE; rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - abort_code, ret, "GOP"); + abort_code, ret, + rxperf_abort_op_not_supported); goto call_complete; case -ENOTSUPP: abort_code = RX_USER_ABORT; rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - abort_code, ret, "GUA"); + abort_code, ret, + rxperf_abort_op_not_supported); goto call_complete; case -EIO: pr_err("Call %u in bad state %u\n", @@ -324,11 +328,13 @@ static void rxperf_deliver_to_call(struct work_struct *work) case -ENOMEM: case -EFAULT: rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - RXGEN_SS_UNMARSHAL, ret, "GUM"); + RXGEN_SS_UNMARSHAL, ret, + rxperf_abort_unmarshal_error); goto call_complete; default: rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - RX_CALL_DEAD, ret, "GER"); + RX_CALL_DEAD, ret, + rxperf_abort_general_error); goto call_complete; } } @@ -523,7 +529,8 @@ static int rxperf_process_call(struct rxperf_call *call) if (n == -ENOMEM) rxrpc_kernel_abort_call(rxperf_socket, call->rxcall, - RXGEN_SS_MARSHAL, -ENOMEM, "GOM"); + RXGEN_SS_MARSHAL, -ENOMEM, + rxperf_abort_oom); return n; } diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index ab968f65a490..cb8dd1d3b1d4 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -97,38 +97,31 @@ found: */ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) { - const struct rxrpc_security *sec; struct rxrpc_key_token *token; struct key *key = conn->key; - int ret; + int ret = 0; _enter("{%d},{%x}", conn->debug_id, key_serial(key)); - if (!key) - return 0; - - ret = key_validate(key); - if (ret < 0) - return ret; - for (token = key->payload.data[0]; token; token = token->next) { - sec = rxrpc_security_lookup(token->security_index); - if (sec) + if (token->security_index == conn->security->security_index) goto found; } return -EKEYREJECTED; found: - conn->security = sec; - - ret = conn->security->init_connection_security(conn, token); - if (ret < 0) { - conn->security = &rxrpc_no_security; - return ret; + mutex_lock(&conn->security_lock); + if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) { + ret = conn->security->init_connection_security(conn, token); + if (ret == 0) { + spin_lock(&conn->state_lock); + if (conn->state == RXRPC_CONN_CLIENT_UNSECURED) + conn->state = RXRPC_CONN_CLIENT; + spin_unlock(&conn->state_lock); + } } - - _leave(" = 0"); - return 0; + mutex_unlock(&conn->security_lock); + return ret; } /* @@ -144,21 +137,15 @@ const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *rx, sec = rxrpc_security_lookup(sp->hdr.securityIndex); if (!sec) { - trace_rxrpc_abort(0, "SVS", - sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EKEYREJECTED); - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; - skb->priority = RX_INVALID_OPERATION; + rxrpc_direct_abort(skb, rxrpc_abort_unsupported_security, + RX_INVALID_OPERATION, -EKEYREJECTED); return NULL; } if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE && !rx->securities) { - trace_rxrpc_abort(0, "SVR", - sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EKEYREJECTED); - skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; - skb->priority = sec->no_key_abort; + rxrpc_direct_abort(skb, rxrpc_abort_no_service_key, + sec->no_key_abort, -EKEYREJECTED); return NULL; } @@ -191,9 +178,9 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn, sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex); - rcu_read_lock(); + read_lock(&conn->local->services_lock); - rx = rcu_dereference(conn->local->service); + rx = conn->local->service; if (!rx) goto out; @@ -215,6 +202,6 @@ struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn, } out: - rcu_read_unlock(); + read_unlock(&conn->local->services_lock); return key; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index cde1e65f16b4..da49fcf1c456 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -18,6 +18,81 @@ #include "ar-internal.h" /* + * Propose an abort to be made in the I/O thread. + */ +bool rxrpc_propose_abort(struct rxrpc_call *call, s32 abort_code, int error, + enum rxrpc_abort_reason why) +{ + _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why); + + if (!call->send_abort && !rxrpc_call_is_complete(call)) { + call->send_abort_why = why; + call->send_abort_err = error; + call->send_abort_seq = 0; + /* Request abort locklessly vs rxrpc_input_call_event(). */ + smp_store_release(&call->send_abort, abort_code); + rxrpc_poke_call(call, rxrpc_call_poke_abort); + return true; + } + + return false; +} + +/* + * Wait for a call to become connected. Interruption here doesn't cause the + * call to be aborted. + */ +static int rxrpc_wait_to_be_connected(struct rxrpc_call *call, long *timeo) +{ + DECLARE_WAITQUEUE(myself, current); + int ret = 0; + + _enter("%d", call->debug_id); + + if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) + return call->error; + + add_wait_queue_exclusive(&call->waitq, &myself); + + for (;;) { + ret = call->error; + if (ret < 0) + break; + + switch (call->interruptibility) { + case RXRPC_INTERRUPTIBLE: + case RXRPC_PREINTERRUPTIBLE: + set_current_state(TASK_INTERRUPTIBLE); + break; + case RXRPC_UNINTERRUPTIBLE: + default: + set_current_state(TASK_UNINTERRUPTIBLE); + break; + } + if (rxrpc_call_state(call) != RXRPC_CALL_CLIENT_AWAIT_CONN) { + ret = call->error; + break; + } + if ((call->interruptibility == RXRPC_INTERRUPTIBLE || + call->interruptibility == RXRPC_PREINTERRUPTIBLE) && + signal_pending(current)) { + ret = sock_intr_errno(*timeo); + break; + } + *timeo = schedule_timeout(*timeo); + } + + remove_wait_queue(&call->waitq, &myself); + __set_current_state(TASK_RUNNING); + + if (ret == 0 && rxrpc_call_is_complete(call)) + ret = call->error; + + _leave(" = %d", ret); + return ret; +} + +/* * Return true if there's sufficient Tx queue space. */ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) @@ -39,7 +114,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, if (rxrpc_check_tx_space(call, NULL)) return 0; - if (call->state >= RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) return call->error; if (signal_pending(current)) @@ -74,7 +149,7 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, if (rxrpc_check_tx_space(call, &tx_win)) return 0; - if (call->state >= RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) return call->error; if (timeout == 0 && @@ -103,7 +178,7 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, if (rxrpc_check_tx_space(call, NULL)) return 0; - if (call->state >= RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) return call->error; trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); @@ -168,7 +243,6 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, struct rxrpc_txbuf *txb, rxrpc_notify_end_tx_t notify_end_tx) { - unsigned long now; rxrpc_seq_t seq = txb->seq; bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke; @@ -191,36 +265,10 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, poke = list_empty(&call->tx_sendmsg); list_add_tail(&txb->call_link, &call->tx_sendmsg); call->tx_prepared = seq; + if (last) + rxrpc_notify_end_tx(rx, call, notify_end_tx); spin_unlock(&call->tx_lock); - if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { - _debug("________awaiting reply/ACK__________"); - write_lock(&call->state_lock); - switch (call->state) { - case RXRPC_CALL_CLIENT_SEND_REQUEST: - call->state = RXRPC_CALL_CLIENT_AWAIT_REPLY; - rxrpc_notify_end_tx(rx, call, notify_end_tx); - break; - case RXRPC_CALL_SERVER_ACK_REQUEST: - call->state = RXRPC_CALL_SERVER_SEND_REPLY; - now = jiffies; - WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); - if (call->ackr_reason == RXRPC_ACK_DELAY) - call->ackr_reason = 0; - trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); - if (!last) - break; - fallthrough; - case RXRPC_CALL_SERVER_SEND_REPLY: - call->state = RXRPC_CALL_SERVER_AWAIT_ACK; - rxrpc_notify_end_tx(rx, call, notify_end_tx); - break; - default: - break; - } - write_unlock(&call->state_lock); - } - if (poke) rxrpc_poke_call(call, rxrpc_call_poke_start); } @@ -245,6 +293,16 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + ret = rxrpc_wait_to_be_connected(call, &timeo); + if (ret < 0) + return ret; + + if (call->conn->state == RXRPC_CONN_CLIENT_UNSECURED) { + ret = rxrpc_init_client_conn_security(call->conn); + if (ret < 0) + return ret; + } + /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -252,15 +310,20 @@ reload: ret = -EPIPE; if (sk->sk_shutdown & SEND_SHUTDOWN) goto maybe_error; - state = READ_ONCE(call->state); + state = rxrpc_call_state(call); ret = -ESHUTDOWN; if (state >= RXRPC_CALL_COMPLETE) goto maybe_error; ret = -EPROTO; if (state != RXRPC_CALL_CLIENT_SEND_REQUEST && state != RXRPC_CALL_SERVER_ACK_REQUEST && - state != RXRPC_CALL_SERVER_SEND_REPLY) + state != RXRPC_CALL_SERVER_SEND_REPLY) { + /* Request phase complete for this client call */ + trace_rxrpc_abort(call->debug_id, rxrpc_sendmsg_late_send, + call->cid, call->call_id, call->rx_consumed, + 0, -EPROTO); goto maybe_error; + } ret = -EMSGSIZE; if (call->tx_total_len != -1) { @@ -329,7 +392,7 @@ reload: /* check for the far side aborting the call or a network error * occurring */ - if (call->state == RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) goto call_terminated; /* add the packet to the send queue if it's now full */ @@ -354,12 +417,9 @@ reload: success: ret = copied; - if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) { - read_lock(&call->state_lock); - if (call->error < 0) - ret = call->error; - read_unlock(&call->state_lock); - } + if (rxrpc_call_is_complete(call) && + call->error < 0) + ret = call->error; out: call->tx_pending = txb; _leave(" = %d", ret); @@ -543,7 +603,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, atomic_inc_return(&rxrpc_debug_id)); /* The socket is now unlocked */ - rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp); _leave(" = %p\n", call); return call; } @@ -556,7 +615,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) { - enum rxrpc_call_state state; struct rxrpc_call *call; unsigned long now, j; bool dropped_lock = false; @@ -598,10 +656,10 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) return PTR_ERR(call); /* ... and we have the call lock. */ ret = 0; - if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) + if (rxrpc_call_is_complete(call)) goto out_put_unlock; } else { - switch (READ_ONCE(call->state)) { + switch (rxrpc_call_state(call)) { case RXRPC_CALL_UNINITIALISED: case RXRPC_CALL_CLIENT_AWAIT_CONN: case RXRPC_CALL_SERVER_PREALLOC: @@ -655,17 +713,13 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) break; } - state = READ_ONCE(call->state); - _debug("CALL %d USR %lx ST %d on CONN %p", - call->debug_id, call->user_call_ID, state, call->conn); - - if (state >= RXRPC_CALL_COMPLETE) { + if (rxrpc_call_is_complete(call)) { /* it's too late for this call */ ret = -ESHUTDOWN; } else if (p.command == RXRPC_CMD_SEND_ABORT) { + rxrpc_propose_abort(call, p.abort_code, -ECONNABORTED, + rxrpc_abort_call_sendmsg); ret = 0; - if (rxrpc_abort_call("CMD", call, 0, p.abort_code, -ECONNABORTED)) - ret = rxrpc_send_abort_packet(call); } else if (p.command != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; } else { @@ -705,34 +759,17 @@ int rxrpc_kernel_send_data(struct socket *sock, struct rxrpc_call *call, bool dropped_lock = false; int ret; - _enter("{%d,%s},", call->debug_id, rxrpc_call_states[call->state]); + _enter("{%d},", call->debug_id); ASSERTCMP(msg->msg_name, ==, NULL); ASSERTCMP(msg->msg_control, ==, NULL); mutex_lock(&call->user_mutex); - _debug("CALL %d USR %lx ST %d on CONN %p", - call->debug_id, call->user_call_ID, call->state, call->conn); - - switch (READ_ONCE(call->state)) { - case RXRPC_CALL_CLIENT_SEND_REQUEST: - case RXRPC_CALL_SERVER_ACK_REQUEST: - case RXRPC_CALL_SERVER_SEND_REPLY: - ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len, - notify_end_tx, &dropped_lock); - break; - case RXRPC_CALL_COMPLETE: - read_lock(&call->state_lock); + ret = rxrpc_send_data(rxrpc_sk(sock->sk), call, msg, len, + notify_end_tx, &dropped_lock); + if (ret == -ESHUTDOWN) ret = call->error; - read_unlock(&call->state_lock); - break; - default: - /* Request phase complete for this client call */ - trace_rxrpc_rx_eproto(call, 0, tracepoint_string("late_send")); - ret = -EPROTO; - break; - } if (!dropped_lock) mutex_unlock(&call->user_mutex); @@ -747,24 +784,20 @@ EXPORT_SYMBOL(rxrpc_kernel_send_data); * @call: The call to be aborted * @abort_code: The abort code to stick into the ABORT packet * @error: Local error value - * @why: 3-char string indicating why. + * @why: Indication as to why. * * Allow a kernel service to abort a call, if it's still in an abortable state * and return true if the call was aborted, false if it was already complete. */ bool rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, - u32 abort_code, int error, const char *why) + u32 abort_code, int error, enum rxrpc_abort_reason why) { bool aborted; - _enter("{%d},%d,%d,%s", call->debug_id, abort_code, error, why); + _enter("{%d},%d,%d,%u", call->debug_id, abort_code, error, why); mutex_lock(&call->user_mutex); - - aborted = rxrpc_abort_call(why, call, 0, abort_code, error); - if (aborted) - rxrpc_send_abort_packet(call); - + aborted = rxrpc_propose_abort(call, abort_code, error, why); mutex_unlock(&call->user_mutex); return aborted; } diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index ff47ce4d3968..6b26bdb999d7 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -134,6 +134,11 @@ static int valid_label(const struct nlattr *attr, { const u32 *label = nla_data(attr); + if (nla_len(attr) != sizeof(*label)) { + NL_SET_ERR_MSG_MOD(extack, "Invalid MPLS label length"); + return -EINVAL; + } + if (*label & ~MPLS_LABEL_MASK || *label == MPLS_LABEL_IMPLNULL) { NL_SET_ERR_MSG_MOD(extack, "MPLS label out of range"); return -EINVAL; @@ -145,7 +150,8 @@ static int valid_label(const struct nlattr *attr, static const struct nla_policy mpls_policy[TCA_MPLS_MAX + 1] = { [TCA_MPLS_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_mpls)), [TCA_MPLS_PROTO] = { .type = NLA_U16 }, - [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_U32, valid_label), + [TCA_MPLS_LABEL] = NLA_POLICY_VALIDATE_FN(NLA_BINARY, + valid_label), [TCA_MPLS_TC] = NLA_POLICY_RANGE(NLA_U8, 0, 7), [TCA_MPLS_TTL] = NLA_POLICY_MIN(NLA_U8, 1), [TCA_MPLS_BOS] = NLA_POLICY_RANGE(NLA_U8, 0, 1), diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 2317db02c764..72d2c204d5f3 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1133,6 +1133,11 @@ skip: return -ENOENT; } + if (new && new->ops == &noqueue_qdisc_ops) { + NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class"); + return -EINVAL; + } + err = cops->graft(parent, cl, new, &old, extack); if (err) return err; diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index a661b062cca8..872d127c9db4 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -377,6 +377,7 @@ static int gred_offload_dump_stats(struct Qdisc *sch) /* Even if driver returns failure adjust the stats - in case offload * ended but driver still wants to adjust the values. */ + sch_tree_lock(sch); for (i = 0; i < MAX_DPs; i++) { if (!table->tab[i]) continue; @@ -393,6 +394,7 @@ static int gred_offload_dump_stats(struct Qdisc *sch) sch->qstats.overlimits += hw_stats->stats.qstats[i].overlimits; } _bstats_update(&sch->bstats, bytes, packets); + sch_tree_unlock(sch); kfree(hw_stats); return ret; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 2238edece1a4..cc28e41fb745 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -431,7 +431,10 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) while (cl->cmode == HTB_MAY_BORROW && p && mask) { m = mask; while (m) { - int prio = ffz(~m); + unsigned int prio = ffz(~m); + + if (WARN_ON_ONCE(prio > ARRAY_SIZE(p->inner.clprio))) + break; m &= ~(1 << prio); if (p->inner.clprio[prio].feed.rb_node) @@ -1549,7 +1552,7 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, struct tc_htb_qopt_offload offload_opt; struct netdev_queue *dev_queue; struct Qdisc *q = cl->leaf.q; - struct Qdisc *old = NULL; + struct Qdisc *old; int err; if (cl->level) @@ -1557,14 +1560,17 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, WARN_ON(!q); dev_queue = htb_offload_get_queue(cl); - old = htb_graft_helper(dev_queue, NULL); - if (destroying) - /* Before HTB is destroyed, the kernel grafts noop_qdisc to - * all queues. + /* When destroying, caller qdisc_graft grafts the new qdisc and invokes + * qdisc_put for the qdisc being destroyed. htb_destroy_class_offload + * does not need to graft or qdisc_put the qdisc being destroyed. + */ + if (!destroying) { + old = htb_graft_helper(dev_queue, NULL); + /* Last qdisc grafted should be the same as cl->leaf.q when + * calling htb_delete. */ - WARN_ON(!(old->flags & TCQ_F_BUILTIN)); - else WARN_ON(old != q); + } if (cl->parent) { _bstats_update(&cl->parent->bstats_bias, @@ -1581,10 +1587,12 @@ static int htb_destroy_class_offload(struct Qdisc *sch, struct htb_class *cl, }; err = htb_offload(qdisc_dev(sch), &offload_opt); - if (!err || destroying) - qdisc_put(old); - else - htb_graft_helper(dev_queue, old); + if (!destroying) { + if (!err) + qdisc_put(old); + else + htb_graft_helper(dev_queue, old); + } if (last_child) return err; diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 570389f6cdd7..c322a61eaeea 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1700,6 +1700,7 @@ static void taprio_reset(struct Qdisc *sch) int i; hrtimer_cancel(&q->advance_timer); + if (q->qdiscs) { for (i = 0; i < dev->num_tx_queues; i++) if (q->qdiscs[i]) @@ -1720,6 +1721,7 @@ static void taprio_destroy(struct Qdisc *sch) * happens in qdisc_create(), after taprio_init() has been called. */ hrtimer_cancel(&q->advance_timer); + qdisc_synchronize(sch); taprio_disable_offload(dev, q, NULL); diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 59e653b528b1..6b95d3ba8fe1 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -73,6 +73,12 @@ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, } } + /* If somehow no addresses were found that can be used with this + * scope, it's an error. + */ + if (list_empty(&dest->address_list)) + error = -ENETUNREACH; + out: if (error) sctp_bind_addr_clean(dest); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index ca1eba95c293..2f66a2006517 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -196,9 +196,7 @@ void sctp_transport_reset_hb_timer(struct sctp_transport *transport) /* When a data chunk is sent, reset the heartbeat interval. */ expires = jiffies + sctp_transport_timeout(transport); - if ((time_before(transport->hb_timer.expires, expires) || - !timer_pending(&transport->hb_timer)) && - !mod_timer(&transport->hb_timer, + if (!mod_timer(&transport->hb_timer, expires + get_random_u32_below(transport->rto))) sctp_transport_hold(transport); } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 148bb0a7fa5b..acb822b23af1 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -923,7 +923,7 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g * rejecting the server-computed MIC in this somewhat rare case, * do not use splice with the GSS integrity service. */ - __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* Did we already verify the signature on the original pass through? */ if (rqstp->rq_deferred) @@ -990,7 +990,7 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs int pad, remaining_len, offset; u32 rseqno; - __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); priv_len = svc_getnl(&buf->head[0]); if (rqstp->rq_deferred) { diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index 85f0c3cfc877..f06622814a95 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1243,10 +1243,10 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv) goto err_short_len; /* Will be turned off by GSS integrity and privacy services */ - __set_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + set_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* Will be turned off only when NFSv4 Sessions are used */ - __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); - __clear_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + clear_bit(RQ_DROPME, &rqstp->rq_flags); svc_putu32(resv, rqstp->rq_xid); diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 2106003645a7..c2ce12538008 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -1238,7 +1238,7 @@ static struct cache_deferred_req *svc_defer(struct cache_req *req) trace_svc_defer(rqstp); svc_xprt_get(rqstp->rq_xprt); dr->xprt = rqstp->rq_xprt; - __set_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_DROPME, &rqstp->rq_flags); dr->handle.revisit = svc_revisit; return &dr->handle; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 015714398007..815baf308236 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -298,9 +298,9 @@ static void svc_sock_setbufsize(struct svc_sock *svsk, unsigned int nreqs) static void svc_sock_secure_port(struct svc_rqst *rqstp) { if (svc_port_is_privileged(svc_addr(rqstp))) - __set_bit(RQ_SECURE, &rqstp->rq_flags); + set_bit(RQ_SECURE, &rqstp->rq_flags); else - __clear_bit(RQ_SECURE, &rqstp->rq_flags); + clear_bit(RQ_SECURE, &rqstp->rq_flags); } /* @@ -1008,9 +1008,9 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp) rqstp->rq_xprt_ctxt = NULL; rqstp->rq_prot = IPPROTO_TCP; if (test_bit(XPT_LOCAL, &svsk->sk_xprt.xpt_flags)) - __set_bit(RQ_LOCAL, &rqstp->rq_flags); + set_bit(RQ_LOCAL, &rqstp->rq_flags); else - __clear_bit(RQ_LOCAL, &rqstp->rq_flags); + clear_bit(RQ_LOCAL, &rqstp->rq_flags); p = (__be32 *)rqstp->rq_arg.head[0].iov_base; calldir = p[1]; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 199fa012f18a..94b20fb47135 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -602,7 +602,7 @@ static int svc_rdma_has_wspace(struct svc_xprt *xprt) static void svc_rdma_secure_port(struct svc_rqst *rqstp) { - __set_bit(RQ_SECURE, &rqstp->rq_flags); + set_bit(RQ_SECURE, &rqstp->rq_flags); } static void svc_rdma_kill_temp_xprt(struct svc_xprt *xprt) diff --git a/net/tipc/node.c b/net/tipc/node.c index 49ddc484c4fe..5e000fde8067 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1179,8 +1179,9 @@ void tipc_node_check_dest(struct net *net, u32 addr, bool addr_match = false; bool sign_match = false; bool link_up = false; + bool link_is_reset = false; bool accept_addr = false; - bool reset = true; + bool reset = false; char *if_name; unsigned long intv; u16 session; @@ -1200,14 +1201,14 @@ void tipc_node_check_dest(struct net *net, u32 addr, /* Prepare to validate requesting node's signature and media address */ l = le->link; link_up = l && tipc_link_is_up(l); + link_is_reset = l && tipc_link_is_reset(l); addr_match = l && !memcmp(&le->maddr, maddr, sizeof(*maddr)); sign_match = (signature == n->signature); /* These three flags give us eight permutations: */ if (sign_match && addr_match && link_up) { - /* All is fine. Do nothing. */ - reset = false; + /* All is fine. Ignore requests. */ /* Peer node is not a container/local namespace */ if (!n->peer_hash_mix) n->peer_hash_mix = hash_mixes; @@ -1232,6 +1233,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, */ accept_addr = true; *respond = true; + reset = true; } else if (!sign_match && addr_match && link_up) { /* Peer node rebooted. Two possibilities: * - Delayed re-discovery; this link endpoint has already @@ -1263,6 +1265,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, n->signature = signature; accept_addr = true; *respond = true; + reset = true; } if (!accept_addr) @@ -1291,6 +1294,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, tipc_link_fsm_evt(l, LINK_RESET_EVT); if (n->state == NODE_FAILINGOVER) tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT); + link_is_reset = tipc_link_is_reset(l); le->link = l; n->link_cnt++; tipc_node_calculate_timer(n, l); @@ -1303,7 +1307,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, memcpy(&le->maddr, maddr, sizeof(*maddr)); exit: tipc_node_write_unlock(n); - if (reset && l && !tipc_link_is_reset(l)) + if (reset && !link_is_reset) tipc_node_link_down(n, b->identity, false); tipc_node_put(n); } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9ed978634125..a83d2b4275fa 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2427,7 +2427,7 @@ static bool tls_is_tx_ready(struct tls_sw_context_tx *ctx) { struct tls_rec *rec; - rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); + rec = list_first_entry_or_null(&ctx->tx_list, struct tls_rec, list); if (!rec) return false; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 3b55502b2965..5c7ad301d742 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -482,6 +482,12 @@ static int x25_listen(struct socket *sock, int backlog) int rc = -EOPNOTSUPP; lock_sock(sk); + if (sock->state != SS_UNCONNECTED) { + rc = -EINVAL; + release_sock(sk); + return rc; + } + if (sk->sk_state != TCP_LISTEN) { memset(&x25_sk(sk)->dest_addr, 0, X25_ADDR_LEN); sk->sk_max_ack_backlog = backlog; diff --git a/rust/kernel/print.rs b/rust/kernel/print.rs index 29bf9c2e8aee..30103325696d 100644 --- a/rust/kernel/print.rs +++ b/rust/kernel/print.rs @@ -142,17 +142,24 @@ pub fn call_printk_cont(args: fmt::Arguments<'_>) { macro_rules! print_macro ( // The non-continuation cases (most of them, e.g. `INFO`). ($format_string:path, false, $($arg:tt)+) => ( - // SAFETY: This hidden macro should only be called by the documented - // printing macros which ensure the format string is one of the fixed - // ones. All `__LOG_PREFIX`s are null-terminated as they are generated - // by the `module!` proc macro or fixed values defined in a kernel - // crate. - unsafe { - $crate::print::call_printk( - &$format_string, - crate::__LOG_PREFIX, - format_args!($($arg)+), - ); + // To remain sound, `arg`s must be expanded outside the `unsafe` block. + // Typically one would use a `let` binding for that; however, `format_args!` + // takes borrows on the arguments, but does not extend the scope of temporaries. + // Therefore, a `match` expression is used to keep them around, since + // the scrutinee is kept until the end of the `match`. + match format_args!($($arg)+) { + // SAFETY: This hidden macro should only be called by the documented + // printing macros which ensure the format string is one of the fixed + // ones. All `__LOG_PREFIX`s are null-terminated as they are generated + // by the `module!` proc macro or fixed values defined in a kernel + // crate. + args => unsafe { + $crate::print::call_printk( + &$format_string, + crate::__LOG_PREFIX, + args, + ); + } } ); diff --git a/samples/ftrace/ftrace-direct-multi-modify.c b/samples/ftrace/ftrace-direct-multi-modify.c index d52370cad0b6..a825dbd2c9cf 100644 --- a/samples/ftrace/ftrace-direct-multi-modify.c +++ b/samples/ftrace/ftrace-direct-multi-modify.c @@ -152,6 +152,7 @@ static void __exit ftrace_direct_multi_exit(void) { kthread_stop(simple_tsk); unregister_ftrace_direct_multi(&direct, my_tramp); + ftrace_free_filter(&direct); } module_init(ftrace_direct_multi_init); diff --git a/samples/ftrace/ftrace-direct-multi.c b/samples/ftrace/ftrace-direct-multi.c index ec1088922517..d955a2650605 100644 --- a/samples/ftrace/ftrace-direct-multi.c +++ b/samples/ftrace/ftrace-direct-multi.c @@ -79,6 +79,7 @@ static int __init ftrace_direct_multi_init(void) static void __exit ftrace_direct_multi_exit(void) { unregister_ftrace_direct_multi(&direct, (unsigned long) my_tramp); + ftrace_free_filter(&direct); } module_init(ftrace_direct_multi_init); diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst index 836391e5d209..4815a8e32227 100644 --- a/scripts/Makefile.modinst +++ b/scripts/Makefile.modinst @@ -66,9 +66,13 @@ endif # Don't stop modules_install even if we can't sign external modules. # ifeq ($(CONFIG_MODULE_SIG_ALL),y) +ifeq ($(filter pkcs11:%, $(CONFIG_MODULE_SIG_KEY)),) sig-key := $(if $(wildcard $(CONFIG_MODULE_SIG_KEY)),,$(srctree)/)$(CONFIG_MODULE_SIG_KEY) +else +sig-key := $(CONFIG_MODULE_SIG_KEY) +endif quiet_cmd_sign = SIGN $@ - cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) $(sig-key) certs/signing_key.x509 $@ \ + cmd_sign = scripts/sign-file $(CONFIG_MODULE_SIG_HASH) "$(sig-key)" certs/signing_key.x509 $@ \ $(if $(KBUILD_EXTMOD),|| true) else quiet_cmd_sign := diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux index 49946cb96844..10176dec97ea 100644 --- a/scripts/Makefile.vmlinux +++ b/scripts/Makefile.vmlinux @@ -18,6 +18,7 @@ quiet_cmd_cc_o_c = CC $@ $(call if_changed_dep,cc_o_c) ifdef CONFIG_MODULES +KASAN_SANITIZE_.vmlinux.export.o := n targets += .vmlinux.export.o vmlinux: .vmlinux.export.o endif diff --git a/scripts/atomic/atomics.tbl b/scripts/atomic/atomics.tbl index fbee2f6190d9..fbee2f6190d9 100755..100644 --- a/scripts/atomic/atomics.tbl +++ b/scripts/atomic/atomics.tbl diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h index 9a1895747b15..84c730da36dd 100644 --- a/scripts/gcc-plugins/gcc-common.h +++ b/scripts/gcc-plugins/gcc-common.h @@ -71,7 +71,9 @@ #include "varasm.h" #include "stor-layout.h" #include "internal-fn.h" +#include "gimple.h" #include "gimple-expr.h" +#include "gimple-iterator.h" #include "gimple-fold.h" #include "context.h" #include "tree-ssa-alias.h" @@ -85,10 +87,8 @@ #include "tree-eh.h" #include "stmt.h" #include "gimplify.h" -#include "gimple.h" #include "tree-phinodes.h" #include "tree-cfg.h" -#include "gimple-iterator.h" #include "gimple-ssa.h" #include "ssa-iterators.h" diff --git a/scripts/jobserver-exec b/scripts/jobserver-exec index 4192855f5b8b..7eca035472d3 100755 --- a/scripts/jobserver-exec +++ b/scripts/jobserver-exec @@ -26,11 +26,20 @@ try: # If the MAKEFLAGS variable contains multiple instances of the # --jobserver-auth= option, the last one is relevant. fds = opts[-1].split("=", 1)[1] - reader, writer = [int(x) for x in fds.split(",", 1)] - # Open a private copy of reader to avoid setting nonblocking - # on an unexpecting process with the same reader fd. - reader = os.open("/proc/self/fd/%d" % (reader), - os.O_RDONLY | os.O_NONBLOCK) + + # Starting with GNU Make 4.4, named pipes are used for reader and writer. + # Example argument: --jobserver-auth=fifo:/tmp/GMfifo8134 + _, _, path = fds.partition('fifo:') + + if path: + reader = os.open(path, os.O_RDONLY | os.O_NONBLOCK) + writer = os.open(path, os.O_WRONLY) + else: + reader, writer = [int(x) for x in fds.split(",", 1)] + # Open a private copy of reader to avoid setting nonblocking + # on an unexpecting process with the same reader fd. + reader = os.open("/proc/self/fd/%d" % (reader), + os.O_RDONLY | os.O_NONBLOCK) # Read out as many jobserver slots as possible. while True: diff --git a/scripts/kconfig/.gitignore b/scripts/kconfig/.gitignore index c8a3f9cd52f0..0b2ff775b2e3 100644 --- a/scripts/kconfig/.gitignore +++ b/scripts/kconfig/.gitignore @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only /conf /[gmnq]conf +/[gmnq]conf-bin /[gmnq]conf-cflags /[gmnq]conf-libs -/qconf-bin /qconf-moc.cc diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 0b1d15efaeb0..af1c96198f49 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -209,7 +209,7 @@ $(obj)/gconf: | $(obj)/gconf-libs $(obj)/gconf.o: | $(obj)/gconf-cflags # check if necessary packages are available, and configure build flags -cmd_conf_cfg = $< $(addprefix $(obj)/$*conf-, cflags libs bin) +cmd_conf_cfg = $< $(addprefix $(obj)/$*conf-, cflags libs bin); touch $(obj)/$*conf-bin $(obj)/%conf-cflags $(obj)/%conf-libs $(obj)/%conf-bin: $(src)/%conf-cfg.sh $(call cmd,conf_cfg) diff --git a/scripts/package/mkspec b/scripts/package/mkspec index adab28fa7f89..094e52c979a8 100755 --- a/scripts/package/mkspec +++ b/scripts/package/mkspec @@ -1,7 +1,7 @@ #!/bin/sh # # Output a simple RPM spec file. -# This version assumes a minimum of RPM 4.0.3. +# This version assumes a minimum of RPM 4.13 # # The only gothic bit here is redefining install_post to avoid # stripping the symbols from files in the kernel which we want diff --git a/scripts/tracing/ftrace-bisect.sh b/scripts/tracing/ftrace-bisect.sh index 926701162bc8..bb4f59262bbe 100755 --- a/scripts/tracing/ftrace-bisect.sh +++ b/scripts/tracing/ftrace-bisect.sh @@ -12,7 +12,7 @@ # (note, if this is a problem with function_graph tracing, then simply # replace "function" with "function_graph" in the following steps). # -# # cd /sys/kernel/debug/tracing +# # cd /sys/kernel/tracing # # echo schedule > set_ftrace_filter # # echo function > current_tracer # @@ -20,22 +20,40 @@ # # # echo nop > current_tracer # -# # cat available_filter_functions > ~/full-file +# Starting with v5.1 this can be done with numbers, making it much faster: +# +# The old (slow) way, for kernels before v5.1. +# +# [old-way] # cat available_filter_functions > ~/full-file +# +# [old-way] *** Note *** this process will take several minutes to update the +# [old-way] filters. Setting multiple functions is an O(n^2) operation, and we +# [old-way] are dealing with thousands of functions. So go have coffee, talk +# [old-way] with your coworkers, read facebook. And eventually, this operation +# [old-way] will end. +# +# The new way (using numbers) is an O(n) operation, and usually takes less than a second. +# +# seq `wc -l available_filter_functions | cut -d' ' -f1` > ~/full-file +# +# This will create a sequence of numbers that match the functions in +# available_filter_functions, and when echoing in a number into the +# set_ftrace_filter file, it will enable the corresponding function in +# O(1) time. Making enabling all functions O(n) where n is the number of +# functions to enable. +# +# For either the new or old way, the rest of the operations remain the same. +# # # ftrace-bisect ~/full-file ~/test-file ~/non-test-file # # cat ~/test-file > set_ftrace_filter # -# *** Note *** this will take several minutes. Setting multiple functions is -# an O(n^2) operation, and we are dealing with thousands of functions. So go -# have coffee, talk with your coworkers, read facebook. And eventually, this -# operation will end. -# # # echo function > current_tracer # # If it crashes, we know that ~/test-file has a bad function. # # Reboot back to test kernel. # -# # cd /sys/kernel/debug/tracing +# # cd /sys/kernel/tracing # # mv ~/test-file ~/full-file # # If it didn't crash. diff --git a/security/tomoyo/Kconfig b/security/tomoyo/Kconfig index b9f867100a9f..fad75be5f381 100644 --- a/security/tomoyo/Kconfig +++ b/security/tomoyo/Kconfig @@ -6,13 +6,11 @@ config SECURITY_TOMOYO select SECURITYFS select SECURITY_PATH select SECURITY_NETWORK - select SRCU - select BUILD_BIN2C default n help This selects TOMOYO Linux, pathname-based access control. Required userspace tools and further information may be - found at <http://tomoyo.sourceforge.jp/>. + found at <https://tomoyo.osdn.jp/>. If you are unsure how to answer this question, answer N. config SECURITY_TOMOYO_MAX_ACCEPT_ENTRY diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile index cca5a3012fee..884ff155edc3 100644 --- a/security/tomoyo/Makefile +++ b/security/tomoyo/Makefile @@ -2,15 +2,18 @@ obj-y = audit.o common.o condition.o domain.o environ.o file.o gc.o group.o load_policy.o memory.o mount.o network.o realpath.o securityfs_if.o tomoyo.o util.o targets += builtin-policy.h -define do_policy -echo "static char tomoyo_builtin_$(1)[] __initdata ="; \ -$(objtree)/scripts/bin2c <$(firstword $(wildcard $(obj)/policy/$(1).conf $(srctree)/$(src)/policy/$(1).conf.default) /dev/null); \ -echo ";" -endef -quiet_cmd_policy = POLICY $@ - cmd_policy = ($(call do_policy,profile); $(call do_policy,exception_policy); $(call do_policy,domain_policy); $(call do_policy,manager); $(call do_policy,stat)) >$@ -$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(src)/policy/*.conf.default) FORCE +quiet_cmd_policy = POLICY $@ + cmd_policy = { \ + $(foreach x, profile exception_policy domain_policy manager stat, \ + printf 'static char tomoyo_builtin_$x[] __initdata =\n'; \ + sed -e 's/\\/\\\\/g' -e 's/\"/\\"/g' -e 's/\(.*\)/\t"\1\\n"/' -- $(firstword $(filter %/$x.conf %/$x.conf.default, $^) /dev/null); \ + printf '\t"";\n';) \ + } > $@ + +$(obj)/builtin-policy.h: $(wildcard $(obj)/policy/*.conf $(srctree)/$(src)/policy/*.conf.default) FORCE $(call if_changed,policy) +ifndef CONFIG_SECURITY_TOMOYO_INSECURE_BUILTIN_SETTING $(obj)/common.o: $(obj)/builtin-policy.h +endif diff --git a/sound/core/control.c b/sound/core/control.c index 50e7ba66f187..82aa1af1d1d8 100644 --- a/sound/core/control.c +++ b/sound/core/control.c @@ -1203,14 +1203,19 @@ static int snd_ctl_elem_read(struct snd_card *card, const u32 pattern = 0xdeadbeef; int ret; + down_read(&card->controls_rwsem); kctl = snd_ctl_find_id(card, &control->id); - if (kctl == NULL) - return -ENOENT; + if (kctl == NULL) { + ret = -ENOENT; + goto unlock; + } index_offset = snd_ctl_get_ioff(kctl, &control->id); vd = &kctl->vd[index_offset]; - if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL) - return -EPERM; + if (!(vd->access & SNDRV_CTL_ELEM_ACCESS_READ) || kctl->get == NULL) { + ret = -EPERM; + goto unlock; + } snd_ctl_build_ioff(&control->id, kctl, index_offset); @@ -1220,7 +1225,7 @@ static int snd_ctl_elem_read(struct snd_card *card, info.id = control->id; ret = __snd_ctl_elem_info(card, kctl, &info, NULL); if (ret < 0) - return ret; + goto unlock; #endif if (!snd_ctl_skip_validation(&info)) @@ -1230,7 +1235,7 @@ static int snd_ctl_elem_read(struct snd_card *card, ret = kctl->get(kctl, control); snd_power_unref(card); if (ret < 0) - return ret; + goto unlock; if (!snd_ctl_skip_validation(&info) && sanity_check_elem_value(card, control, &info, pattern) < 0) { dev_err(card->dev, @@ -1238,8 +1243,11 @@ static int snd_ctl_elem_read(struct snd_card *card, control->id.iface, control->id.device, control->id.subdevice, control->id.name, control->id.index); - return -EINVAL; + ret = -EINVAL; + goto unlock; } +unlock: + up_read(&card->controls_rwsem); return ret; } @@ -1253,9 +1261,7 @@ static int snd_ctl_elem_read_user(struct snd_card *card, if (IS_ERR(control)) return PTR_ERR(control); - down_read(&card->controls_rwsem); result = snd_ctl_elem_read(card, control); - up_read(&card->controls_rwsem); if (result < 0) goto error; diff --git a/sound/core/control_led.c b/sound/core/control_led.c index f975cc85772b..3cadd40100f3 100644 --- a/sound/core/control_led.c +++ b/sound/core/control_led.c @@ -530,12 +530,11 @@ static ssize_t set_led_id(struct snd_ctl_led_card *led_card, const char *buf, si bool attach) { char buf2[256], *s, *os; - size_t len = max(sizeof(s) - 1, count); struct snd_ctl_elem_id id; int err; - strncpy(buf2, buf, len); - buf2[len] = '\0'; + if (strscpy(buf2, buf, sizeof(buf2)) < 0) + return -E2BIG; memset(&id, 0, sizeof(id)); id.iface = SNDRV_CTL_ELEM_IFACE_MIXER; s = buf2; diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c index 81025f50a542..f901504b5afc 100644 --- a/sound/core/memalloc.c +++ b/sound/core/memalloc.c @@ -541,16 +541,15 @@ static void *snd_dma_noncontig_alloc(struct snd_dma_buffer *dmab, size_t size) struct sg_table *sgt; void *p; +#ifdef CONFIG_SND_DMA_SGBUF + if (cpu_feature_enabled(X86_FEATURE_XENPV)) + return snd_dma_sg_fallback_alloc(dmab, size); +#endif sgt = dma_alloc_noncontiguous(dmab->dev.dev, size, dmab->dev.dir, DEFAULT_GFP, 0); #ifdef CONFIG_SND_DMA_SGBUF - if (!sgt && !get_dma_ops(dmab->dev.dev)) { - if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) - dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; - else - dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK; + if (!sgt && !get_dma_ops(dmab->dev.dev)) return snd_dma_sg_fallback_alloc(dmab, size); - } #endif if (!sgt) return NULL; @@ -717,19 +716,38 @@ static const struct snd_malloc_ops snd_dma_sg_wc_ops = { /* Fallback SG-buffer allocations for x86 */ struct snd_dma_sg_fallback { + bool use_dma_alloc_coherent; size_t count; struct page **pages; + /* DMA address array; the first page contains #pages in ~PAGE_MASK */ + dma_addr_t *addrs; }; static void __snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab, struct snd_dma_sg_fallback *sgbuf) { - bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; - size_t i; - - for (i = 0; i < sgbuf->count && sgbuf->pages[i]; i++) - do_free_pages(page_address(sgbuf->pages[i]), PAGE_SIZE, wc); + size_t i, size; + + if (sgbuf->pages && sgbuf->addrs) { + i = 0; + while (i < sgbuf->count) { + if (!sgbuf->pages[i] || !sgbuf->addrs[i]) + break; + size = sgbuf->addrs[i] & ~PAGE_MASK; + if (WARN_ON(!size)) + break; + if (sgbuf->use_dma_alloc_coherent) + dma_free_coherent(dmab->dev.dev, size << PAGE_SHIFT, + page_address(sgbuf->pages[i]), + sgbuf->addrs[i] & PAGE_MASK); + else + do_free_pages(page_address(sgbuf->pages[i]), + size << PAGE_SHIFT, false); + i += size; + } + } kvfree(sgbuf->pages); + kvfree(sgbuf->addrs); kfree(sgbuf); } @@ -738,24 +756,36 @@ static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) struct snd_dma_sg_fallback *sgbuf; struct page **pagep, *curp; size_t chunk, npages; + dma_addr_t *addrp; dma_addr_t addr; void *p; - bool wc = dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; + + /* correct the type */ + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_SG) + dmab->dev.type = SNDRV_DMA_TYPE_DEV_SG_FALLBACK; + else if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG) + dmab->dev.type = SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK; sgbuf = kzalloc(sizeof(*sgbuf), GFP_KERNEL); if (!sgbuf) return NULL; + sgbuf->use_dma_alloc_coherent = cpu_feature_enabled(X86_FEATURE_XENPV); size = PAGE_ALIGN(size); sgbuf->count = size >> PAGE_SHIFT; sgbuf->pages = kvcalloc(sgbuf->count, sizeof(*sgbuf->pages), GFP_KERNEL); - if (!sgbuf->pages) + sgbuf->addrs = kvcalloc(sgbuf->count, sizeof(*sgbuf->addrs), GFP_KERNEL); + if (!sgbuf->pages || !sgbuf->addrs) goto error; pagep = sgbuf->pages; - chunk = size; + addrp = sgbuf->addrs; + chunk = (PAGE_SIZE - 1) << PAGE_SHIFT; /* to fit in low bits in addrs */ while (size > 0) { chunk = min(size, chunk); - p = do_alloc_pages(dmab->dev.dev, chunk, &addr, wc); + if (sgbuf->use_dma_alloc_coherent) + p = dma_alloc_coherent(dmab->dev.dev, chunk, &addr, DEFAULT_GFP); + else + p = do_alloc_pages(dmab->dev.dev, chunk, &addr, false); if (!p) { if (chunk <= PAGE_SIZE) goto error; @@ -767,17 +797,25 @@ static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) size -= chunk; /* fill pages */ npages = chunk >> PAGE_SHIFT; + *addrp = npages; /* store in lower bits */ curp = virt_to_page(p); - while (npages--) + while (npages--) { *pagep++ = curp++; + *addrp++ |= addr; + addr += PAGE_SIZE; + } } p = vmap(sgbuf->pages, sgbuf->count, VM_MAP, PAGE_KERNEL); if (!p) goto error; + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wc(sgbuf->pages, sgbuf->count); + dmab->private_data = sgbuf; /* store the first page address for convenience */ - dmab->addr = snd_sgbuf_get_addr(dmab, 0); + dmab->addr = sgbuf->addrs[0] & PAGE_MASK; return p; error: @@ -787,10 +825,23 @@ static void *snd_dma_sg_fallback_alloc(struct snd_dma_buffer *dmab, size_t size) static void snd_dma_sg_fallback_free(struct snd_dma_buffer *dmab) { + struct snd_dma_sg_fallback *sgbuf = dmab->private_data; + + if (dmab->dev.type == SNDRV_DMA_TYPE_DEV_WC_SG_FALLBACK) + set_pages_array_wb(sgbuf->pages, sgbuf->count); vunmap(dmab->area); __snd_dma_sg_fallback_free(dmab, dmab->private_data); } +static dma_addr_t snd_dma_sg_fallback_get_addr(struct snd_dma_buffer *dmab, + size_t offset) +{ + struct snd_dma_sg_fallback *sgbuf = dmab->private_data; + size_t index = offset >> PAGE_SHIFT; + + return (sgbuf->addrs[index] & PAGE_MASK) | (offset & ~PAGE_MASK); +} + static int snd_dma_sg_fallback_mmap(struct snd_dma_buffer *dmab, struct vm_area_struct *area) { @@ -805,8 +856,8 @@ static const struct snd_malloc_ops snd_dma_sg_fallback_ops = { .alloc = snd_dma_sg_fallback_alloc, .free = snd_dma_sg_fallback_free, .mmap = snd_dma_sg_fallback_mmap, + .get_addr = snd_dma_sg_fallback_get_addr, /* reuse vmalloc helpers */ - .get_addr = snd_dma_vmalloc_get_addr, .get_page = snd_dma_vmalloc_get_page, .get_chunk_size = snd_dma_vmalloc_get_chunk_size, }; diff --git a/sound/firewire/motu/motu-hwdep.c b/sound/firewire/motu/motu-hwdep.c index a900fc0e7644..88d1f4b56e4b 100644 --- a/sound/firewire/motu/motu-hwdep.c +++ b/sound/firewire/motu/motu-hwdep.c @@ -87,6 +87,10 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, return -EFAULT; count = consumed; + } else { + spin_unlock_irq(&motu->lock); + + count = 0; } return count; diff --git a/sound/pci/hda/cs35l41_hda.c b/sound/pci/hda/cs35l41_hda.c index 91842c0c8c74..f7815ee24f83 100644 --- a/sound/pci/hda/cs35l41_hda.c +++ b/sound/pci/hda/cs35l41_hda.c @@ -598,8 +598,8 @@ static int cs35l41_system_suspend(struct device *dev) dev_dbg(cs35l41->dev, "System Suspend\n"); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { - dev_err(cs35l41->dev, "System Suspend not supported\n"); - return -EINVAL; + dev_err_once(cs35l41->dev, "System Suspend not supported\n"); + return 0; /* don't block the whole system suspend */ } ret = pm_runtime_force_suspend(dev); @@ -624,8 +624,8 @@ static int cs35l41_system_resume(struct device *dev) dev_dbg(cs35l41->dev, "System Resume\n"); if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) { - dev_err(cs35l41->dev, "System Resume not supported\n"); - return -EINVAL; + dev_err_once(cs35l41->dev, "System Resume not supported\n"); + return 0; /* don't block the whole system resume */ } if (cs35l41->reset_gpio) { @@ -647,6 +647,15 @@ static int cs35l41_system_resume(struct device *dev) return ret; } +static int cs35l41_runtime_idle(struct device *dev) +{ + struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); + + if (cs35l41->hw_cfg.bst_type == CS35L41_EXT_BOOST_NO_VSPK_SWITCH) + return -EBUSY; /* suspend not supported yet on this model */ + return 0; +} + static int cs35l41_runtime_suspend(struct device *dev) { struct cs35l41_hda *cs35l41 = dev_get_drvdata(dev); @@ -1536,7 +1545,8 @@ void cs35l41_hda_remove(struct device *dev) EXPORT_SYMBOL_NS_GPL(cs35l41_hda_remove, SND_HDA_SCODEC_CS35L41); const struct dev_pm_ops cs35l41_hda_pm_ops = { - RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume, NULL) + RUNTIME_PM_OPS(cs35l41_runtime_suspend, cs35l41_runtime_resume, + cs35l41_runtime_idle) SYSTEM_SLEEP_PM_OPS(cs35l41_system_suspend, cs35l41_system_resume) }; EXPORT_SYMBOL_NS_GPL(cs35l41_hda_pm_ops, SND_HDA_SCODEC_CS35L41); diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 1a868dd9dc4b..890c2f7c33fc 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -144,6 +144,7 @@ static int hda_codec_driver_probe(struct device *dev) error: snd_hda_codec_cleanup_for_unbind(codec); + codec->preset = NULL; return err; } @@ -166,6 +167,7 @@ static int hda_codec_driver_remove(struct device *dev) if (codec->patch_ops.free) codec->patch_ops.free(codec); snd_hda_codec_cleanup_for_unbind(codec); + codec->preset = NULL; module_put(dev->driver->owner); return 0; } diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index edd653ece70d..ac1cc7c5290e 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -795,7 +795,6 @@ void snd_hda_codec_cleanup_for_unbind(struct hda_codec *codec) snd_array_free(&codec->cvt_setups); snd_array_free(&codec->spdif_out); snd_array_free(&codec->verbs); - codec->preset = NULL; codec->follower_dig_outs = NULL; codec->spdif_status_reset = 0; snd_array_free(&codec->mixers); diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c index 386dd9d9143f..9ea633fe9339 100644 --- a/sound/pci/hda/patch_hdmi.c +++ b/sound/pci/hda/patch_hdmi.c @@ -1981,6 +1981,7 @@ static const struct snd_pci_quirk force_connect_list[] = { SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1), SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1), SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1), + SND_PCI_QUIRK(0x103c, 0x8715, "HP", 1), SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1), SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1), {} diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3794b522c222..db9518de9343 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3564,6 +3564,15 @@ static void alc256_init(struct hda_codec *codec) hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; + if (spec->ultra_low_power) { + alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1); + alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2); + alc_update_coef_idx(codec, 0x08, 7<<4, 0); + alc_update_coef_idx(codec, 0x3b, 1<<15, 0); + alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6); + msleep(30); + } + if (!hp_pin) hp_pin = 0x21; @@ -3575,14 +3584,6 @@ static void alc256_init(struct hda_codec *codec) msleep(2); alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */ - if (spec->ultra_low_power) { - alc_update_coef_idx(codec, 0x03, 1<<1, 1<<1); - alc_update_coef_idx(codec, 0x08, 3<<2, 3<<2); - alc_update_coef_idx(codec, 0x08, 7<<4, 0); - alc_update_coef_idx(codec, 0x3b, 1<<15, 0); - alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6); - msleep(30); - } snd_hda_codec_write(codec, hp_pin, 0, AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); @@ -3713,6 +3714,13 @@ static void alc225_init(struct hda_codec *codec) hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp1_pin_sense, hp2_pin_sense; + if (spec->ultra_low_power) { + alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2); + alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6); + alc_update_coef_idx(codec, 0x33, 1<<11, 0); + msleep(30); + } + if (spec->codec_variant != ALC269_TYPE_ALC287 && spec->codec_variant != ALC269_TYPE_ALC245) /* required only at boot or S3 and S4 resume time */ @@ -3734,12 +3742,6 @@ static void alc225_init(struct hda_codec *codec) msleep(2); alc_update_coefex_idx(codec, 0x57, 0x04, 0x0007, 0x1); /* Low power */ - if (spec->ultra_low_power) { - alc_update_coef_idx(codec, 0x08, 0x0f << 2, 3<<2); - alc_update_coef_idx(codec, 0x0e, 7<<6, 7<<6); - alc_update_coef_idx(codec, 0x33, 1<<11, 0); - msleep(30); - } if (hp1_pin_sense || spec->ultra_low_power) snd_hda_codec_write(codec, hp_pin, 0, @@ -4644,6 +4646,16 @@ static void alc285_fixup_hp_coef_micmute_led(struct hda_codec *codec, } } +static void alc285_fixup_hp_gpio_micmute_led(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + + if (action == HDA_FIXUP_ACT_PRE_PROBE) + spec->micmute_led_polarity = 1; + alc_fixup_hp_gpio_led(codec, action, 0, 0x04); +} + static void alc236_fixup_hp_coef_micmute_led(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -4665,6 +4677,13 @@ static void alc285_fixup_hp_mute_led(struct hda_codec *codec, alc285_fixup_hp_coef_micmute_led(codec, fix, action); } +static void alc285_fixup_hp_spectre_x360_mute_led(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + alc285_fixup_hp_mute_led_coefbit(codec, fix, action); + alc285_fixup_hp_gpio_micmute_led(codec, fix, action); +} + static void alc236_fixup_hp_mute_led(struct hda_codec *codec, const struct hda_fixup *fix, int action) { @@ -7106,6 +7125,7 @@ enum { ALC285_FIXUP_ASUS_G533Z_PINS, ALC285_FIXUP_HP_GPIO_LED, ALC285_FIXUP_HP_MUTE_LED, + ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED, ALC236_FIXUP_HP_GPIO_LED, ALC236_FIXUP_HP_MUTE_LED, ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF, @@ -8486,6 +8506,10 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc285_fixup_hp_mute_led, }, + [ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc285_fixup_hp_spectre_x360_mute_led, + }, [ALC236_FIXUP_HP_GPIO_LED] = { .type = HDA_FIXUP_FUNC, .v.func = alc236_fixup_hp_gpio_led, @@ -9178,6 +9202,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1025, 0x142b, "Acer Swift SF314-42", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1430, "Acer TravelMate B311R-31", ALC256_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1025, 0x1466, "Acer Aspire A515-56", ALC255_FIXUP_ACER_HEADPHONE_AND_MIC), + SND_PCI_QUIRK(0x1025, 0x1534, "Acer Predator PH315-54", ALC255_FIXUP_ACER_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z), SND_PCI_QUIRK(0x1028, 0x053c, "Dell Latitude E5430", ALC292_FIXUP_DELL_E7X), SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS), @@ -9239,6 +9264,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x0b1a, "Dell Precision 5570", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x0b37, "Dell Inspiron 16 Plus 7620 2-in-1", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), SND_PCI_QUIRK(0x1028, 0x0b71, "Dell Inspiron 16 Plus 7620", ALC295_FIXUP_DELL_INSPIRON_TOP_SPEAKERS), + SND_PCI_QUIRK(0x1028, 0x0c03, "Dell Precision 5340", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0c19, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1a, "Dell Precision 3340", ALC236_FIXUP_DELL_DUAL_CODECS), SND_PCI_QUIRK(0x1028, 0x0c1b, "Dell Precision 3440", ALC236_FIXUP_DELL_DUAL_CODECS), @@ -9327,6 +9353,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x86c7, "HP Envy AiO 32", ALC274_FIXUP_HP_ENVY_GPIO), SND_PCI_QUIRK(0x103c, 0x86e7, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), SND_PCI_QUIRK(0x103c, 0x86e8, "HP Spectre x360 15-eb0xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1), + SND_PCI_QUIRK(0x103c, 0x86f9, "HP Spectre x360 13-aw0xxx", ALC285_FIXUP_HP_SPECTRE_X360_MUTE_LED), SND_PCI_QUIRK(0x103c, 0x8716, "HP Elite Dragonfly G2 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8720, "HP EliteBook x360 1040 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_AMP_INIT), SND_PCI_QUIRK(0x103c, 0x8724, "HP EliteBook 850 G7", ALC285_FIXUP_HP_GPIO_LED), @@ -9406,6 +9433,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b5d, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x8b5e, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8b92, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8bf0, "HP", ALC236_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c index aea7fae2ca4b..2994f85bc1b9 100644 --- a/sound/pci/hda/patch_via.c +++ b/sound/pci/hda/patch_via.c @@ -819,6 +819,9 @@ static int add_secret_dac_path(struct hda_codec *codec) return 0; nums = snd_hda_get_connections(codec, spec->gen.mixer_nid, conn, ARRAY_SIZE(conn) - 1); + if (nums < 0) + return nums; + for (i = 0; i < nums; i++) { if (get_wcaps_type(get_wcaps(codec, conn[i])) == AC_WID_AUD_OUT) return 0; diff --git a/sound/soc/amd/acp-es8336.c b/sound/soc/amd/acp-es8336.c index 2fe8df86053a..89499542c803 100644 --- a/sound/soc/amd/acp-es8336.c +++ b/sound/soc/amd/acp-es8336.c @@ -198,9 +198,11 @@ static int st_es8336_late_probe(struct snd_soc_card *card) int ret; adev = acpi_dev_get_first_match_dev("ESSX8336", NULL, -1); - if (adev) - put_device(&adev->dev); + if (!adev) + return -ENODEV; + codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); if (!codec_dev) dev_err(card->dev, "can not find codec dev\n"); diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c index 1f0b5527c594..36314753923b 100644 --- a/sound/soc/amd/yc/acp6x-mach.c +++ b/sound/soc/amd/yc/acp6x-mach.c @@ -209,6 +209,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { { .driver_data = &acp6x_card, .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "M5402RA"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Alienware"), DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m17 R5 AMD"), } @@ -220,6 +227,34 @@ static const struct dmi_system_id yc_acp_quirk_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 14 2022"), } }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "TIMI"), + DMI_MATCH(DMI_PRODUCT_NAME, "Redmi Book Pro 15 2022"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "Razer"), + DMI_MATCH(DMI_PRODUCT_NAME, "Blade 14 (2022) - RZ09-0427"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "RB"), + DMI_MATCH(DMI_PRODUCT_NAME, "Swift SFA16-41"), + } + }, + { + .driver_data = &acp6x_card, + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "IRBIS"), + DMI_MATCH(DMI_PRODUCT_NAME, "15NBC1011"), + } + }, {} }; diff --git a/sound/soc/codecs/cs42l56.c b/sound/soc/codecs/cs42l56.c index 26066682c983..3b0e715549c9 100644 --- a/sound/soc/codecs/cs42l56.c +++ b/sound/soc/codecs/cs42l56.c @@ -1191,18 +1191,12 @@ static int cs42l56_i2c_probe(struct i2c_client *i2c_client) if (pdata) { cs42l56->pdata = *pdata; } else { - pdata = devm_kzalloc(&i2c_client->dev, sizeof(*pdata), - GFP_KERNEL); - if (!pdata) - return -ENOMEM; - if (i2c_client->dev.of_node) { ret = cs42l56_handle_of_data(i2c_client, &cs42l56->pdata); if (ret != 0) return ret; } - cs42l56->pdata = *pdata; } if (cs42l56->pdata.gpio_nreset) { diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c index 9ddf6a35e91c..9ddf6a35e91c 100755..100644 --- a/sound/soc/codecs/es8326.c +++ b/sound/soc/codecs/es8326.c diff --git a/sound/soc/codecs/es8326.h b/sound/soc/codecs/es8326.h index 8e5ffe5ee10d..8e5ffe5ee10d 100755..100644 --- a/sound/soc/codecs/es8326.h +++ b/sound/soc/codecs/es8326.h diff --git a/sound/soc/codecs/rt9120.c b/sound/soc/codecs/rt9120.c index 644300e88b4c..fcf4fbaed3c7 100644 --- a/sound/soc/codecs/rt9120.c +++ b/sound/soc/codecs/rt9120.c @@ -177,8 +177,20 @@ static int rt9120_codec_probe(struct snd_soc_component *comp) return 0; } +static int rt9120_codec_suspend(struct snd_soc_component *comp) +{ + return pm_runtime_force_suspend(comp->dev); +} + +static int rt9120_codec_resume(struct snd_soc_component *comp) +{ + return pm_runtime_force_resume(comp->dev); +} + static const struct snd_soc_component_driver rt9120_component_driver = { .probe = rt9120_codec_probe, + .suspend = rt9120_codec_suspend, + .resume = rt9120_codec_resume, .controls = rt9120_snd_controls, .num_controls = ARRAY_SIZE(rt9120_snd_controls), .dapm_widgets = rt9120_dapm_widgets, diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c index ca6a01a230af..791d8738d1c0 100644 --- a/sound/soc/codecs/wm8904.c +++ b/sound/soc/codecs/wm8904.c @@ -697,6 +697,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w, int dcs_mask; int dcs_l, dcs_r; int dcs_l_reg, dcs_r_reg; + int an_out_reg; int timeout; int pwr_reg; @@ -712,6 +713,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w, dcs_mask = WM8904_DCS_ENA_CHAN_0 | WM8904_DCS_ENA_CHAN_1; dcs_r_reg = WM8904_DC_SERVO_8; dcs_l_reg = WM8904_DC_SERVO_9; + an_out_reg = WM8904_ANALOGUE_OUT1_LEFT; dcs_l = 0; dcs_r = 1; break; @@ -720,6 +722,7 @@ static int out_pga_event(struct snd_soc_dapm_widget *w, dcs_mask = WM8904_DCS_ENA_CHAN_2 | WM8904_DCS_ENA_CHAN_3; dcs_r_reg = WM8904_DC_SERVO_6; dcs_l_reg = WM8904_DC_SERVO_7; + an_out_reg = WM8904_ANALOGUE_OUT2_LEFT; dcs_l = 2; dcs_r = 3; break; @@ -792,6 +795,10 @@ static int out_pga_event(struct snd_soc_dapm_widget *w, snd_soc_component_update_bits(component, reg, WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP, WM8904_HPL_ENA_OUTP | WM8904_HPR_ENA_OUTP); + + /* Update volume, requires PGA to be powered */ + val = snd_soc_component_read(component, an_out_reg); + snd_soc_component_write(component, an_out_reg, val); break; case SND_SOC_DAPM_POST_PMU: diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c index 966ba4909204..58fdb4e9fd97 100644 --- a/sound/soc/codecs/wsa883x.c +++ b/sound/soc/codecs/wsa883x.c @@ -1359,8 +1359,8 @@ static struct snd_soc_dai_driver wsa883x_dais[] = { .stream_name = "SPKR Playback", .rates = WSA883X_RATES | WSA883X_FRAC_RATES, .formats = WSA883X_FORMATS, - .rate_max = 8000, - .rate_min = 352800, + .rate_min = 8000, + .rate_max = 352800, .channels_min = 1, .channels_max = 1, }, diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c index c836848ef0a6..8d14b5593658 100644 --- a/sound/soc/fsl/fsl-asoc-card.c +++ b/sound/soc/fsl/fsl-asoc-card.c @@ -121,11 +121,11 @@ static const struct snd_soc_dapm_route audio_map[] = { static const struct snd_soc_dapm_route audio_map_ac97[] = { /* 1st half -- Normal DAPM routes */ - {"Playback", NULL, "AC97 Playback"}, - {"AC97 Capture", NULL, "Capture"}, + {"AC97 Playback", NULL, "CPU AC97 Playback"}, + {"CPU AC97 Capture", NULL, "AC97 Capture"}, /* 2nd half -- ASRC DAPM routes */ - {"AC97 Playback", NULL, "ASRC-Playback"}, - {"ASRC-Capture", NULL, "AC97 Capture"}, + {"CPU AC97 Playback", NULL, "ASRC-Playback"}, + {"ASRC-Capture", NULL, "CPU AC97 Capture"}, }; static const struct snd_soc_dapm_route audio_map_tx[] = { diff --git a/sound/soc/fsl/fsl_micfil.c b/sound/soc/fsl/fsl_micfil.c index 7b17f152bbf3..94341e4352b3 100644 --- a/sound/soc/fsl/fsl_micfil.c +++ b/sound/soc/fsl/fsl_micfil.c @@ -315,21 +315,21 @@ static int hwvad_detected(struct snd_kcontrol *kcontrol, static const struct snd_kcontrol_new fsl_micfil_snd_controls[] = { SOC_SINGLE_SX_TLV("CH0 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(0), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(0), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH1 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(1), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(1), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH2 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(2), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(2), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH3 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(3), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(3), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH4 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(4), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(4), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH5 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(5), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(5), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH6 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(6), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(6), 0x8, 0xF, gain_tlv), SOC_SINGLE_SX_TLV("CH7 Volume", REG_MICFIL_OUT_CTRL, - MICFIL_OUTGAIN_CHX_SHIFT(7), 0xF, 0x7, gain_tlv), + MICFIL_OUTGAIN_CHX_SHIFT(7), 0x8, 0xF, gain_tlv), SOC_ENUM_EXT("MICFIL Quality Select", fsl_micfil_quality_enum, micfil_quality_get, micfil_quality_set), diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c index c9e0e31d5b34..46a53551b955 100644 --- a/sound/soc/fsl/fsl_ssi.c +++ b/sound/soc/fsl/fsl_ssi.c @@ -1189,14 +1189,14 @@ static struct snd_soc_dai_driver fsl_ssi_ac97_dai = { .symmetric_channels = 1, .probe = fsl_ssi_dai_probe, .playback = { - .stream_name = "AC97 Playback", + .stream_name = "CPU AC97 Playback", .channels_min = 2, .channels_max = 2, .rates = SNDRV_PCM_RATE_8000_48000, .formats = SNDRV_PCM_FMTBIT_S16 | SNDRV_PCM_FMTBIT_S20, }, .capture = { - .stream_name = "AC97 Capture", + .stream_name = "CPU AC97 Capture", .channels_min = 2, .channels_max = 2, .rates = SNDRV_PCM_RATE_48000, diff --git a/sound/soc/intel/avs/core.c b/sound/soc/intel/avs/core.c index 2ca24273c491..637501850728 100644 --- a/sound/soc/intel/avs/core.c +++ b/sound/soc/intel/avs/core.c @@ -481,6 +481,29 @@ err_remap_bar0: return ret; } +static void avs_pci_shutdown(struct pci_dev *pci) +{ + struct hdac_bus *bus = pci_get_drvdata(pci); + struct avs_dev *adev = hdac_to_avs(bus); + + cancel_work_sync(&adev->probe_work); + avs_ipc_block(adev->ipc); + + snd_hdac_stop_streams(bus); + avs_dsp_op(adev, int_control, false); + snd_hdac_ext_bus_ppcap_int_enable(bus, false); + snd_hdac_ext_bus_link_power_down_all(bus); + + snd_hdac_bus_stop_chip(bus); + snd_hdac_display_power(bus, HDA_CODEC_IDX_CONTROLLER, false); + + if (avs_platattr_test(adev, CLDMA)) + pci_free_irq(pci, 0, &code_loader); + pci_free_irq(pci, 0, adev); + pci_free_irq(pci, 0, bus); + pci_free_irq_vectors(pci); +} + static void avs_pci_remove(struct pci_dev *pci) { struct hdac_device *hdev, *save; @@ -739,6 +762,7 @@ static struct pci_driver avs_pci_driver = { .id_table = avs_ids, .probe = avs_pci_probe, .remove = avs_pci_remove, + .shutdown = avs_pci_shutdown, .driver = { .pm = &avs_dev_pm, }, diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig index a472de1909f4..99308ed85277 100644 --- a/sound/soc/intel/boards/Kconfig +++ b/sound/soc/intel/boards/Kconfig @@ -554,10 +554,12 @@ config SND_SOC_INTEL_SOF_NAU8825_MACH select SND_SOC_RT1015P select SND_SOC_MAX98373_I2C select SND_SOC_MAX98357A + select SND_SOC_NAU8315 select SND_SOC_DMIC select SND_SOC_HDAC_HDMI select SND_SOC_INTEL_HDA_DSP_COMMON select SND_SOC_INTEL_SOF_MAXIM_COMMON + select SND_SOC_INTEL_SOF_REALTEK_COMMON help This adds support for ASoC machine driver for SOF platforms with nau8825 codec. diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c index 09d1f0f6d686..df157b01df8b 100644 --- a/sound/soc/intel/boards/bytcht_es8316.c +++ b/sound/soc/intel/boards/bytcht_es8316.c @@ -497,21 +497,28 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) if (adev) { snprintf(codec_name, sizeof(codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); byt_cht_es8316_dais[dai_index].codecs->name = codec_name; } else { dev_err(dev, "Error cannot find '%s' dev\n", mach->id); return -ENXIO; } + codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); + if (!codec_dev) + return -EPROBE_DEFER; + priv->codec_dev = get_device(codec_dev); + /* override platform name, if required */ byt_cht_es8316_card.dev = dev; platform_name = mach->mach_params.platform; ret = snd_soc_fixup_dai_links_platform_name(&byt_cht_es8316_card, platform_name); - if (ret) + if (ret) { + put_device(codec_dev); return ret; + } /* Check for BYTCR or other platform and setup quirks */ dmi_id = dmi_first_match(byt_cht_es8316_quirk_table); @@ -539,13 +546,10 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev) /* get the clock */ priv->mclk = devm_clk_get(dev, "pmc_plt_clk_3"); - if (IS_ERR(priv->mclk)) + if (IS_ERR(priv->mclk)) { + put_device(codec_dev); return dev_err_probe(dev, PTR_ERR(priv->mclk), "clk_get pmc_plt_clk_3 failed\n"); - - codec_dev = acpi_get_first_physical_node(adev); - if (!codec_dev) - return -EPROBE_DEFER; - priv->codec_dev = get_device(codec_dev); + } if (quirk & BYT_CHT_ES8316_JD_INVERTED) props[cnt++] = PROPERTY_ENTRY_BOOL("everest,jack-detect-inverted"); diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c index 4699ca79f3ea..79e0039c79a3 100644 --- a/sound/soc/intel/boards/bytcr_rt5640.c +++ b/sound/soc/intel/boards/bytcr_rt5640.c @@ -1636,13 +1636,18 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) if (adev) { snprintf(byt_rt5640_codec_name, sizeof(byt_rt5640_codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); byt_rt5640_dais[dai_index].codecs->name = byt_rt5640_codec_name; } else { dev_err(dev, "Error cannot find '%s' dev\n", mach->id); return -ENXIO; } + codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); + if (!codec_dev) + return -EPROBE_DEFER; + priv->codec_dev = get_device(codec_dev); + /* * swap SSP0 if bytcr is detected * (will be overridden if DMI quirk is detected) @@ -1717,11 +1722,6 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev) byt_rt5640_quirk = quirk_override; } - codec_dev = acpi_get_first_physical_node(adev); - if (!codec_dev) - return -EPROBE_DEFER; - priv->codec_dev = get_device(codec_dev); - if (byt_rt5640_quirk & BYT_RT5640_JD_HP_ELITEP_1000G2) { acpi_dev_add_driver_gpios(ACPI_COMPANION(priv->codec_dev), byt_rt5640_hp_elitepad_1000g2_gpios); diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c index 81ac6eeda2e6..8fca9b82d4d0 100644 --- a/sound/soc/intel/boards/bytcr_rt5651.c +++ b/sound/soc/intel/boards/bytcr_rt5651.c @@ -922,7 +922,6 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) if (adev) { snprintf(byt_rt5651_codec_name, sizeof(byt_rt5651_codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); byt_rt5651_dais[dai_index].codecs->name = byt_rt5651_codec_name; } else { dev_err(dev, "Error cannot find '%s' dev\n", mach->id); @@ -930,6 +929,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev) } codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); if (!codec_dev) return -EPROBE_DEFER; priv->codec_dev = get_device(codec_dev); diff --git a/sound/soc/intel/boards/bytcr_wm5102.c b/sound/soc/intel/boards/bytcr_wm5102.c index 1669eb3bd80f..c0706537f673 100644 --- a/sound/soc/intel/boards/bytcr_wm5102.c +++ b/sound/soc/intel/boards/bytcr_wm5102.c @@ -411,9 +411,9 @@ static int snd_byt_wm5102_mc_probe(struct platform_device *pdev) return -ENOENT; } snprintf(codec_name, sizeof(codec_name), "spi-%s", acpi_dev_name(adev)); - put_device(&adev->dev); codec_dev = bus_find_device_by_name(&spi_bus_type, NULL, codec_name); + acpi_dev_put(adev); if (!codec_dev) return -EPROBE_DEFER; diff --git a/sound/soc/intel/boards/sof_cs42l42.c b/sound/soc/intel/boards/sof_cs42l42.c index e38bd2831e6a..e9d190cb13b0 100644 --- a/sound/soc/intel/boards/sof_cs42l42.c +++ b/sound/soc/intel/boards/sof_cs42l42.c @@ -336,6 +336,9 @@ static int create_spk_amp_dai_links(struct device *dev, links[*id].platforms = platform_component; links[*id].num_platforms = ARRAY_SIZE(platform_component); links[*id].dpcm_playback = 1; + /* firmware-generated echo reference */ + links[*id].dpcm_capture = 1; + links[*id].no_pcm = 1; links[*id].cpus = &cpus[*id]; links[*id].num_cpus = 1; diff --git a/sound/soc/intel/boards/sof_es8336.c b/sound/soc/intel/boards/sof_es8336.c index 773e5d1d87d4..894b6610b9e2 100644 --- a/sound/soc/intel/boards/sof_es8336.c +++ b/sound/soc/intel/boards/sof_es8336.c @@ -681,7 +681,6 @@ static int sof_es8336_probe(struct platform_device *pdev) if (adev) { snprintf(codec_name, sizeof(codec_name), "i2c-%s", acpi_dev_name(adev)); - put_device(&adev->dev); dai_links[0].codecs->name = codec_name; /* also fixup codec dai name if relevant */ @@ -692,16 +691,19 @@ static int sof_es8336_probe(struct platform_device *pdev) return -ENXIO; } - ret = snd_soc_fixup_dai_links_platform_name(&sof_es8336_card, - mach->mach_params.platform); - if (ret) - return ret; - codec_dev = acpi_get_first_physical_node(adev); + acpi_dev_put(adev); if (!codec_dev) return -EPROBE_DEFER; priv->codec_dev = get_device(codec_dev); + ret = snd_soc_fixup_dai_links_platform_name(&sof_es8336_card, + mach->mach_params.platform); + if (ret) { + put_device(codec_dev); + return ret; + } + if (quirk & SOF_ES8336_JD_INVERTED) props[cnt++] = PROPERTY_ENTRY_BOOL("everest,jack-detect-inverted"); diff --git a/sound/soc/intel/boards/sof_nau8825.c b/sound/soc/intel/boards/sof_nau8825.c index 27880224359d..6794a0249a9a 100644 --- a/sound/soc/intel/boards/sof_nau8825.c +++ b/sound/soc/intel/boards/sof_nau8825.c @@ -48,6 +48,7 @@ #define SOF_MAX98373_SPEAKER_AMP_PRESENT BIT(15) #define SOF_MAX98360A_SPEAKER_AMP_PRESENT BIT(16) #define SOF_RT1015P_SPEAKER_AMP_PRESENT BIT(17) +#define SOF_NAU8318_SPEAKER_AMP_PRESENT BIT(18) static unsigned long sof_nau8825_quirk = SOF_NAU8825_SSP_CODEC(0); @@ -338,6 +339,13 @@ static struct snd_soc_dai_link_component rt1019p_component[] = { } }; +static struct snd_soc_dai_link_component nau8318_components[] = { + { + .name = "NVTN2012:00", + .dai_name = "nau8315-hifi", + } +}; + static struct snd_soc_dai_link_component dummy_component[] = { { .name = "snd-soc-dummy", @@ -479,13 +487,16 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].num_codecs = ARRAY_SIZE(max_98373_components); links[id].init = max_98373_spk_codec_init; links[id].ops = &max_98373_ops; - /* feedback stream */ - links[id].dpcm_capture = 1; } else if (sof_nau8825_quirk & SOF_MAX98360A_SPEAKER_AMP_PRESENT) { max_98360a_dai_link(&links[id]); } else if (sof_nau8825_quirk & SOF_RT1015P_SPEAKER_AMP_PRESENT) { sof_rt1015p_dai_link(&links[id]); + } else if (sof_nau8825_quirk & + SOF_NAU8318_SPEAKER_AMP_PRESENT) { + links[id].codecs = nau8318_components; + links[id].num_codecs = ARRAY_SIZE(nau8318_components); + links[id].init = speaker_codec_init; } else { goto devm_err; } @@ -493,6 +504,9 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].platforms = platform_component; links[id].num_platforms = ARRAY_SIZE(platform_component); links[id].dpcm_playback = 1; + /* feedback stream or firmware-generated echo reference */ + links[id].dpcm_capture = 1; + links[id].no_pcm = 1; links[id].cpus = &cpus[id]; links[id].num_cpus = 1; @@ -618,7 +632,7 @@ static const struct platform_device_id board_ids[] = { }, { - .name = "adl_rt1019p_nau8825", + .name = "adl_rt1019p_8825", .driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) | SOF_SPEAKER_AMP_PRESENT | SOF_RT1019P_SPEAKER_AMP_PRESENT | @@ -626,7 +640,7 @@ static const struct platform_device_id board_ids[] = { SOF_NAU8825_NUM_HDMIDEV(4)), }, { - .name = "adl_max98373_nau8825", + .name = "adl_max98373_8825", .driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) | SOF_SPEAKER_AMP_PRESENT | SOF_MAX98373_SPEAKER_AMP_PRESENT | @@ -637,7 +651,7 @@ static const struct platform_device_id board_ids[] = { }, { /* The limitation of length of char array, shorten the name */ - .name = "adl_mx98360a_nau8825", + .name = "adl_mx98360a_8825", .driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) | SOF_SPEAKER_AMP_PRESENT | SOF_MAX98360A_SPEAKER_AMP_PRESENT | @@ -648,7 +662,7 @@ static const struct platform_device_id board_ids[] = { }, { - .name = "adl_rt1015p_nau8825", + .name = "adl_rt1015p_8825", .driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) | SOF_SPEAKER_AMP_PRESENT | SOF_RT1015P_SPEAKER_AMP_PRESENT | @@ -657,6 +671,16 @@ static const struct platform_device_id board_ids[] = { SOF_BT_OFFLOAD_SSP(2) | SOF_SSP_BT_OFFLOAD_PRESENT), }, + { + .name = "adl_nau8318_8825", + .driver_data = (kernel_ulong_t)(SOF_NAU8825_SSP_CODEC(0) | + SOF_SPEAKER_AMP_PRESENT | + SOF_NAU8318_SPEAKER_AMP_PRESENT | + SOF_NAU8825_SSP_AMP(1) | + SOF_NAU8825_NUM_HDMIDEV(4) | + SOF_BT_OFFLOAD_SSP(2) | + SOF_SSP_BT_OFFLOAD_PRESENT), + }, { } }; MODULE_DEVICE_TABLE(platform, board_ids); diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c index 2eabc4b0fafa..71a11d747622 100644 --- a/sound/soc/intel/boards/sof_rt5682.c +++ b/sound/soc/intel/boards/sof_rt5682.c @@ -761,8 +761,6 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].num_codecs = ARRAY_SIZE(max_98373_components); links[id].init = max_98373_spk_codec_init; links[id].ops = &max_98373_ops; - /* feedback stream */ - links[id].dpcm_capture = 1; } else if (sof_rt5682_quirk & SOF_MAX98360A_SPEAKER_AMP_PRESENT) { max_98360a_dai_link(&links[id]); @@ -789,6 +787,9 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, links[id].platforms = platform_component; links[id].num_platforms = ARRAY_SIZE(platform_component); links[id].dpcm_playback = 1; + /* feedback stream or firmware-generated echo reference */ + links[id].dpcm_capture = 1; + links[id].no_pcm = 1; links[id].cpus = &cpus[id]; links[id].num_cpus = 1; diff --git a/sound/soc/intel/boards/sof_ssp_amp.c b/sound/soc/intel/boards/sof_ssp_amp.c index 94d25aeb6e7c..7b74f122e340 100644 --- a/sound/soc/intel/boards/sof_ssp_amp.c +++ b/sound/soc/intel/boards/sof_ssp_amp.c @@ -258,13 +258,12 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev, sof_rt1308_dai_link(&links[id]); } else if (sof_ssp_amp_quirk & SOF_CS35L41_SPEAKER_AMP_PRESENT) { cs35l41_set_dai_link(&links[id]); - - /* feedback from amplifier */ - links[id].dpcm_capture = 1; } links[id].platforms = platform_component; links[id].num_platforms = ARRAY_SIZE(platform_component); links[id].dpcm_playback = 1; + /* feedback from amplifier or firmware-generated echo reference */ + links[id].dpcm_capture = 1; links[id].no_pcm = 1; links[id].cpus = &cpus[id]; links[id].num_cpus = 1; diff --git a/sound/soc/intel/common/soc-acpi-intel-adl-match.c b/sound/soc/intel/common/soc-acpi-intel-adl-match.c index 60aee56f94bd..56ee5fef66a8 100644 --- a/sound/soc/intel/common/soc-acpi-intel-adl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-adl-match.c @@ -450,6 +450,11 @@ static const struct snd_soc_acpi_codecs adl_lt6911_hdmi = { .codecs = {"INTC10B0"} }; +static const struct snd_soc_acpi_codecs adl_nau8318_amp = { + .num_codecs = 1, + .codecs = {"NVTN2012"} +}; + struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_machines[] = { { .comp_ids = &adl_rt5682_rt5682s_hp, @@ -474,21 +479,21 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_machines[] = { }, { .id = "10508825", - .drv_name = "adl_rt1019p_nau8825", + .drv_name = "adl_rt1019p_8825", .machine_quirk = snd_soc_acpi_codec_list, .quirk_data = &adl_rt1019p_amp, .sof_tplg_filename = "sof-adl-rt1019-nau8825.tplg", }, { .id = "10508825", - .drv_name = "adl_max98373_nau8825", + .drv_name = "adl_max98373_8825", .machine_quirk = snd_soc_acpi_codec_list, .quirk_data = &adl_max98373_amp, .sof_tplg_filename = "sof-adl-max98373-nau8825.tplg", }, { .id = "10508825", - .drv_name = "adl_mx98360a_nau8825", + .drv_name = "adl_mx98360a_8825", .machine_quirk = snd_soc_acpi_codec_list, .quirk_data = &adl_max98360a_amp, .sof_tplg_filename = "sof-adl-max98360a-nau8825.tplg", @@ -502,13 +507,20 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_adl_machines[] = { }, { .id = "10508825", - .drv_name = "adl_rt1015p_nau8825", + .drv_name = "adl_rt1015p_8825", .machine_quirk = snd_soc_acpi_codec_list, .quirk_data = &adl_rt1015p_amp, .sof_tplg_filename = "sof-adl-rt1015-nau8825.tplg", }, { .id = "10508825", + .drv_name = "adl_nau8318_8825", + .machine_quirk = snd_soc_acpi_codec_list, + .quirk_data = &adl_nau8318_amp, + .sof_tplg_filename = "sof-adl-nau8318-nau8825.tplg", + }, + { + .id = "10508825", .drv_name = "sof_nau8825", .sof_tplg_filename = "sof-adl-nau8825.tplg", }, diff --git a/sound/soc/intel/common/soc-acpi-intel-rpl-match.c b/sound/soc/intel/common/soc-acpi-intel-rpl-match.c index 31b43116e3d8..07f96a11ea2f 100644 --- a/sound/soc/intel/common/soc-acpi-intel-rpl-match.c +++ b/sound/soc/intel/common/soc-acpi-intel-rpl-match.c @@ -203,6 +203,25 @@ static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link2_rt1316_link01_rt71 {} }; +static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link2_rt1316_link01[] = { + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(rt711_sdca_2_adr), + .adr_d = rt711_sdca_2_adr, + }, + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(rt1316_0_group2_adr), + .adr_d = rt1316_0_group2_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(rt1316_1_group2_adr), + .adr_d = rt1316_1_group2_adr, + }, + {} +}; + static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12_rt714_link3[] = { { .mask = BIT(0), @@ -227,6 +246,25 @@ static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12_rt71 {} }; +static const struct snd_soc_acpi_link_adr rpl_sdw_rt711_link0_rt1318_link12[] = { + { + .mask = BIT(0), + .num_adr = ARRAY_SIZE(rt711_sdca_0_adr), + .adr_d = rt711_sdca_0_adr, + }, + { + .mask = BIT(1), + .num_adr = ARRAY_SIZE(rt1318_1_group1_adr), + .adr_d = rt1318_1_group1_adr, + }, + { + .mask = BIT(2), + .num_adr = ARRAY_SIZE(rt1318_2_group1_adr), + .adr_d = rt1318_2_group1_adr, + }, + {} +}; + static const struct snd_soc_acpi_link_adr rpl_sdw_rt1316_link12_rt714_link0[] = { { .mask = BIT(1), @@ -272,12 +310,24 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_rpl_sdw_machines[] = { .sof_tplg_filename = "sof-rpl-rt711-l0-rt1318-l12-rt714-l3.tplg", }, { + .link_mask = 0x7, /* rt711 on link0 & two rt1318s on link1 and link2 */ + .links = rpl_sdw_rt711_link0_rt1318_link12, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-rpl-rt711-l0-rt1318-l12.tplg", + }, + { .link_mask = 0x7, /* rt714 on link0 & two rt1316s on link1 and link2 */ .links = rpl_sdw_rt1316_link12_rt714_link0, .drv_name = "sof_sdw", .sof_tplg_filename = "sof-rpl-rt1316-l12-rt714-l0.tplg", }, { + .link_mask = 0x7, /* rt711 on link2 & two rt1316s on link0 and link1 */ + .links = rpl_sdw_rt711_link2_rt1316_link01, + .drv_name = "sof_sdw", + .sof_tplg_filename = "sof-rpl-rt711-l2-rt1316-l01.tplg", + }, + { .link_mask = 0x1, /* link0 required */ .links = rpl_rvp, .drv_name = "sof_sdw", diff --git a/sound/soc/mediatek/Kconfig b/sound/soc/mediatek/Kconfig index 363fa4d47680..b027fba8233d 100644 --- a/sound/soc/mediatek/Kconfig +++ b/sound/soc/mediatek/Kconfig @@ -182,10 +182,12 @@ config SND_SOC_MT8186_MT6366_DA7219_MAX98357 If unsure select "N". config SND_SOC_MT8186_MT6366_RT1019_RT5682S - tristate "ASoC Audio driver for MT8186 with RT1019 RT5682S codec" + tristate "ASoC Audio driver for MT8186 with RT1019 RT5682S MAX98357A/MAX98360 codec" depends on I2C && GPIOLIB depends on SND_SOC_MT8186 && MTK_PMIC_WRAP + select SND_SOC_MAX98357A select SND_SOC_MT6358 + select SND_SOC_MAX98357A select SND_SOC_RT1015P select SND_SOC_RT5682S select SND_SOC_BT_SCO diff --git a/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c b/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c index 8f77a0bc1dc8..af44e331dae8 100644 --- a/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c +++ b/sound/soc/mediatek/mt8186/mt8186-mt6366-rt1019-rt5682s.c @@ -1083,6 +1083,21 @@ static struct snd_soc_card mt8186_mt6366_rt1019_rt5682s_soc_card = { .num_configs = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_codec_conf), }; +static struct snd_soc_card mt8186_mt6366_rt5682s_max98360_soc_card = { + .name = "mt8186_rt5682s_max98360", + .owner = THIS_MODULE, + .dai_link = mt8186_mt6366_rt1019_rt5682s_dai_links, + .num_links = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_dai_links), + .controls = mt8186_mt6366_rt1019_rt5682s_controls, + .num_controls = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_controls), + .dapm_widgets = mt8186_mt6366_rt1019_rt5682s_widgets, + .num_dapm_widgets = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_widgets), + .dapm_routes = mt8186_mt6366_rt1019_rt5682s_routes, + .num_dapm_routes = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_routes), + .codec_conf = mt8186_mt6366_rt1019_rt5682s_codec_conf, + .num_configs = ARRAY_SIZE(mt8186_mt6366_rt1019_rt5682s_codec_conf), +}; + static int mt8186_mt6366_rt1019_rt5682s_dev_probe(struct platform_device *pdev) { struct snd_soc_card *card; @@ -1232,9 +1247,14 @@ err_adsp_node: #if IS_ENABLED(CONFIG_OF) static const struct of_device_id mt8186_mt6366_rt1019_rt5682s_dt_match[] = { - { .compatible = "mediatek,mt8186-mt6366-rt1019-rt5682s-sound", + { + .compatible = "mediatek,mt8186-mt6366-rt1019-rt5682s-sound", .data = &mt8186_mt6366_rt1019_rt5682s_soc_card, }, + { + .compatible = "mediatek,mt8186-mt6366-rt5682s-max98360-sound", + .data = &mt8186_mt6366_rt5682s_max98360_soc_card, + }, {} }; MODULE_DEVICE_TABLE(of, mt8186_mt6366_rt1019_rt5682s_dt_match); diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig index 96a6d4731e6f..e7b00d1d9e99 100644 --- a/sound/soc/qcom/Kconfig +++ b/sound/soc/qcom/Kconfig @@ -2,7 +2,6 @@ menuconfig SND_SOC_QCOM tristate "ASoC support for QCOM platforms" depends on ARCH_QCOM || COMPILE_TEST - imply SND_SOC_QCOM_COMMON help Say Y or M if you want to add support to use audio devices in Qualcomm Technologies SOC-based platforms. @@ -60,14 +59,16 @@ config SND_SOC_STORM config SND_SOC_APQ8016_SBC tristate "SoC Audio support for APQ8016 SBC platforms" select SND_SOC_LPASS_APQ8016 - depends on SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_COMMON help Support for Qualcomm Technologies LPASS audio block in APQ8016 SOC-based systems. Say Y if you want to use audio devices on MI2S. config SND_SOC_QCOM_COMMON - depends on SOUNDWIRE + tristate + +config SND_SOC_QCOM_SDW tristate config SND_SOC_QDSP6_COMMON @@ -144,7 +145,7 @@ config SND_SOC_MSM8996 depends on QCOM_APR depends on COMMON_CLK select SND_SOC_QDSP6 - depends on SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_COMMON help Support for Qualcomm Technologies LPASS audio block in APQ8096 SoC-based systems. @@ -155,7 +156,7 @@ config SND_SOC_SDM845 depends on QCOM_APR && I2C && SOUNDWIRE depends on COMMON_CLK select SND_SOC_QDSP6 - depends on SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_COMMON select SND_SOC_RT5663 select SND_SOC_MAX98927 imply SND_SOC_CROS_EC_CODEC @@ -169,7 +170,8 @@ config SND_SOC_SM8250 depends on QCOM_APR && SOUNDWIRE depends on COMMON_CLK select SND_SOC_QDSP6 - depends on SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_SDW help To add support for audio on Qualcomm Technologies Inc. SM8250 SoC-based systems. @@ -180,7 +182,8 @@ config SND_SOC_SC8280XP depends on QCOM_APR && SOUNDWIRE depends on COMMON_CLK select SND_SOC_QDSP6 - depends on SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_SDW help To add support for audio on Qualcomm Technologies Inc. SC8280XP SoC-based systems. @@ -190,7 +193,7 @@ config SND_SOC_SC7180 tristate "SoC Machine driver for SC7180 boards" depends on I2C && GPIOLIB depends on SOUNDWIRE || SOUNDWIRE=n - depends on SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_COMMON select SND_SOC_LPASS_SC7180 select SND_SOC_MAX98357A select SND_SOC_RT5682_I2C @@ -204,7 +207,7 @@ config SND_SOC_SC7180 config SND_SOC_SC7280 tristate "SoC Machine driver for SC7280 boards" depends on I2C && SOUNDWIRE - depends on SND_SOC_QCOM_COMMON + select SND_SOC_QCOM_COMMON select SND_SOC_LPASS_SC7280 select SND_SOC_MAX98357A select SND_SOC_WCD938X_SDW diff --git a/sound/soc/qcom/Makefile b/sound/soc/qcom/Makefile index 8b97172cf990..254350d9dc06 100644 --- a/sound/soc/qcom/Makefile +++ b/sound/soc/qcom/Makefile @@ -28,6 +28,7 @@ snd-soc-sdm845-objs := sdm845.o snd-soc-sm8250-objs := sm8250.o snd-soc-sc8280xp-objs := sc8280xp.o snd-soc-qcom-common-objs := common.o +snd-soc-qcom-sdw-objs := sdw.o obj-$(CONFIG_SND_SOC_STORM) += snd-soc-storm.o obj-$(CONFIG_SND_SOC_APQ8016_SBC) += snd-soc-apq8016-sbc.o @@ -38,6 +39,7 @@ obj-$(CONFIG_SND_SOC_SC8280XP) += snd-soc-sc8280xp.o obj-$(CONFIG_SND_SOC_SDM845) += snd-soc-sdm845.o obj-$(CONFIG_SND_SOC_SM8250) += snd-soc-sm8250.o obj-$(CONFIG_SND_SOC_QCOM_COMMON) += snd-soc-qcom-common.o +obj-$(CONFIG_SND_SOC_QCOM_SDW) += snd-soc-qcom-sdw.o #DSP lib obj-$(CONFIG_SND_SOC_QDSP6) += qdsp6/ diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c index 49c74c1662a3..96fe80241fb4 100644 --- a/sound/soc/qcom/common.c +++ b/sound/soc/qcom/common.c @@ -180,120 +180,6 @@ err_put_np: } EXPORT_SYMBOL_GPL(qcom_snd_parse_of); -int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream, - struct sdw_stream_runtime *sruntime, - bool *stream_prepared) -{ - struct snd_soc_pcm_runtime *rtd = substream->private_data; - struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0); - int ret; - - if (!sruntime) - return 0; - - switch (cpu_dai->id) { - case WSA_CODEC_DMA_RX_0: - case WSA_CODEC_DMA_RX_1: - case RX_CODEC_DMA_RX_0: - case RX_CODEC_DMA_RX_1: - case TX_CODEC_DMA_TX_0: - case TX_CODEC_DMA_TX_1: - case TX_CODEC_DMA_TX_2: - case TX_CODEC_DMA_TX_3: - break; - default: - return 0; - } - - if (*stream_prepared) { - sdw_disable_stream(sruntime); - sdw_deprepare_stream(sruntime); - *stream_prepared = false; - } - - ret = sdw_prepare_stream(sruntime); - if (ret) - return ret; - - /** - * NOTE: there is a strict hw requirement about the ordering of port - * enables and actual WSA881x PA enable. PA enable should only happen - * after soundwire ports are enabled if not DC on the line is - * accumulated resulting in Click/Pop Noise - * PA enable/mute are handled as part of codec DAPM and digital mute. - */ - - ret = sdw_enable_stream(sruntime); - if (ret) { - sdw_deprepare_stream(sruntime); - return ret; - } - *stream_prepared = true; - - return ret; -} -EXPORT_SYMBOL_GPL(qcom_snd_sdw_prepare); - -int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params, - struct sdw_stream_runtime **psruntime) -{ - struct snd_soc_pcm_runtime *rtd = substream->private_data; - struct snd_soc_dai *codec_dai; - struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0); - struct sdw_stream_runtime *sruntime; - int i; - - switch (cpu_dai->id) { - case WSA_CODEC_DMA_RX_0: - case RX_CODEC_DMA_RX_0: - case RX_CODEC_DMA_RX_1: - case TX_CODEC_DMA_TX_0: - case TX_CODEC_DMA_TX_1: - case TX_CODEC_DMA_TX_2: - case TX_CODEC_DMA_TX_3: - for_each_rtd_codec_dais(rtd, i, codec_dai) { - sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream); - if (sruntime != ERR_PTR(-ENOTSUPP)) - *psruntime = sruntime; - } - break; - } - - return 0; - -} -EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_params); - -int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream, - struct sdw_stream_runtime *sruntime, bool *stream_prepared) -{ - struct snd_soc_pcm_runtime *rtd = substream->private_data; - struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0); - - switch (cpu_dai->id) { - case WSA_CODEC_DMA_RX_0: - case WSA_CODEC_DMA_RX_1: - case RX_CODEC_DMA_RX_0: - case RX_CODEC_DMA_RX_1: - case TX_CODEC_DMA_TX_0: - case TX_CODEC_DMA_TX_1: - case TX_CODEC_DMA_TX_2: - case TX_CODEC_DMA_TX_3: - if (sruntime && *stream_prepared) { - sdw_disable_stream(sruntime); - sdw_deprepare_stream(sruntime); - *stream_prepared = false; - } - break; - default: - break; - } - - return 0; -} -EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_free); - int qcom_snd_wcd_jack_setup(struct snd_soc_pcm_runtime *rtd, struct snd_soc_jack *jack, bool *jack_setup) { diff --git a/sound/soc/qcom/common.h b/sound/soc/qcom/common.h index 3ef5bb6d12df..d7f80ee5ae26 100644 --- a/sound/soc/qcom/common.h +++ b/sound/soc/qcom/common.h @@ -5,19 +5,9 @@ #define __QCOM_SND_COMMON_H__ #include <sound/soc.h> -#include <linux/soundwire/sdw.h> int qcom_snd_parse_of(struct snd_soc_card *card); int qcom_snd_wcd_jack_setup(struct snd_soc_pcm_runtime *rtd, struct snd_soc_jack *jack, bool *jack_setup); -int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream, - struct sdw_stream_runtime *runtime, - bool *stream_prepared); -int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params, - struct sdw_stream_runtime **psruntime); -int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream, - struct sdw_stream_runtime *sruntime, - bool *stream_prepared); #endif diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c index 54353842dc07..dbdaaa85ce48 100644 --- a/sound/soc/qcom/lpass-cpu.c +++ b/sound/soc/qcom/lpass-cpu.c @@ -1037,10 +1037,11 @@ static void of_lpass_cpu_parse_dai_data(struct device *dev, struct lpass_data *data) { struct device_node *node; - int ret, id; + int ret, i, id; /* Allow all channels by default for backwards compatibility */ - for (id = 0; id < data->variant->num_dai; id++) { + for (i = 0; i < data->variant->num_dai; i++) { + id = data->variant->dai_driver[i].id; data->mi2s_playback_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH; data->mi2s_capture_sd_mode[id] = LPAIF_I2SCTL_MODE_8CH; } diff --git a/sound/soc/qcom/sc8280xp.c b/sound/soc/qcom/sc8280xp.c index ade44ad7c585..14d9fea33d16 100644 --- a/sound/soc/qcom/sc8280xp.c +++ b/sound/soc/qcom/sc8280xp.c @@ -12,6 +12,7 @@ #include <linux/input-event-codes.h> #include "qdsp6/q6afe.h" #include "common.h" +#include "sdw.h" #define DRIVER_NAME "sc8280xp" diff --git a/sound/soc/qcom/sdw.c b/sound/soc/qcom/sdw.c new file mode 100644 index 000000000000..10249519a39e --- /dev/null +++ b/sound/soc/qcom/sdw.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2018, Linaro Limited. +// Copyright (c) 2018, The Linux Foundation. All rights reserved. + +#include <linux/module.h> +#include <sound/soc.h> +#include "qdsp6/q6afe.h" +#include "sdw.h" + +int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream, + struct sdw_stream_runtime *sruntime, + bool *stream_prepared) +{ + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0); + int ret; + + if (!sruntime) + return 0; + + switch (cpu_dai->id) { + case WSA_CODEC_DMA_RX_0: + case WSA_CODEC_DMA_RX_1: + case RX_CODEC_DMA_RX_0: + case RX_CODEC_DMA_RX_1: + case TX_CODEC_DMA_TX_0: + case TX_CODEC_DMA_TX_1: + case TX_CODEC_DMA_TX_2: + case TX_CODEC_DMA_TX_3: + break; + default: + return 0; + } + + if (*stream_prepared) { + sdw_disable_stream(sruntime); + sdw_deprepare_stream(sruntime); + *stream_prepared = false; + } + + ret = sdw_prepare_stream(sruntime); + if (ret) + return ret; + + /** + * NOTE: there is a strict hw requirement about the ordering of port + * enables and actual WSA881x PA enable. PA enable should only happen + * after soundwire ports are enabled if not DC on the line is + * accumulated resulting in Click/Pop Noise + * PA enable/mute are handled as part of codec DAPM and digital mute. + */ + + ret = sdw_enable_stream(sruntime); + if (ret) { + sdw_deprepare_stream(sruntime); + return ret; + } + *stream_prepared = true; + + return ret; +} +EXPORT_SYMBOL_GPL(qcom_snd_sdw_prepare); + +int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct sdw_stream_runtime **psruntime) +{ + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct snd_soc_dai *codec_dai; + struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0); + struct sdw_stream_runtime *sruntime; + int i; + + switch (cpu_dai->id) { + case WSA_CODEC_DMA_RX_0: + case RX_CODEC_DMA_RX_0: + case RX_CODEC_DMA_RX_1: + case TX_CODEC_DMA_TX_0: + case TX_CODEC_DMA_TX_1: + case TX_CODEC_DMA_TX_2: + case TX_CODEC_DMA_TX_3: + for_each_rtd_codec_dais(rtd, i, codec_dai) { + sruntime = snd_soc_dai_get_stream(codec_dai, substream->stream); + if (sruntime != ERR_PTR(-ENOTSUPP)) + *psruntime = sruntime; + } + break; + } + + return 0; + +} +EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_params); + +int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream, + struct sdw_stream_runtime *sruntime, bool *stream_prepared) +{ + struct snd_soc_pcm_runtime *rtd = substream->private_data; + struct snd_soc_dai *cpu_dai = asoc_rtd_to_cpu(rtd, 0); + + switch (cpu_dai->id) { + case WSA_CODEC_DMA_RX_0: + case WSA_CODEC_DMA_RX_1: + case RX_CODEC_DMA_RX_0: + case RX_CODEC_DMA_RX_1: + case TX_CODEC_DMA_TX_0: + case TX_CODEC_DMA_TX_1: + case TX_CODEC_DMA_TX_2: + case TX_CODEC_DMA_TX_3: + if (sruntime && *stream_prepared) { + sdw_disable_stream(sruntime); + sdw_deprepare_stream(sruntime); + *stream_prepared = false; + } + break; + default: + break; + } + + return 0; +} +EXPORT_SYMBOL_GPL(qcom_snd_sdw_hw_free); +MODULE_LICENSE("GPL v2"); diff --git a/sound/soc/qcom/sdw.h b/sound/soc/qcom/sdw.h new file mode 100644 index 000000000000..d74cbb84da13 --- /dev/null +++ b/sound/soc/qcom/sdw.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (c) 2018, The Linux Foundation. All rights reserved. + +#ifndef __QCOM_SND_SDW_H__ +#define __QCOM_SND_SDW_H__ + +#include <linux/soundwire/sdw.h> + +int qcom_snd_sdw_prepare(struct snd_pcm_substream *substream, + struct sdw_stream_runtime *runtime, + bool *stream_prepared); +int qcom_snd_sdw_hw_params(struct snd_pcm_substream *substream, + struct snd_pcm_hw_params *params, + struct sdw_stream_runtime **psruntime); +int qcom_snd_sdw_hw_free(struct snd_pcm_substream *substream, + struct sdw_stream_runtime *sruntime, + bool *stream_prepared); +#endif diff --git a/sound/soc/qcom/sm8250.c b/sound/soc/qcom/sm8250.c index 8dbe9ef41b1c..9626a9ef78c2 100644 --- a/sound/soc/qcom/sm8250.c +++ b/sound/soc/qcom/sm8250.c @@ -12,6 +12,7 @@ #include <linux/input-event-codes.h> #include "qdsp6/q6afe.h" #include "common.h" +#include "sdw.h" #define DRIVER_NAME "sm8250" #define MI2S_BCLK_RATE 1536000 diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c index d9a3ce7b69e1..ade0507328af 100644 --- a/sound/soc/sof/debug.c +++ b/sound/soc/sof/debug.c @@ -353,7 +353,9 @@ int snd_sof_dbg_init(struct snd_sof_dev *sdev) return err; } - return 0; + return snd_sof_debugfs_buf_item(sdev, &sdev->fw_state, + sizeof(sdev->fw_state), + "fw_state", 0444); } EXPORT_SYMBOL_GPL(snd_sof_dbg_init); diff --git a/sound/soc/sof/ipc4-mtrace.c b/sound/soc/sof/ipc4-mtrace.c index 70dea8ae706e..0ec6ef681012 100644 --- a/sound/soc/sof/ipc4-mtrace.c +++ b/sound/soc/sof/ipc4-mtrace.c @@ -344,9 +344,10 @@ static ssize_t sof_ipc4_priority_mask_dfs_write(struct file *file, size_t count, loff_t *ppos) { struct sof_mtrace_priv *priv = file->private_data; - int id, ret; + unsigned int id; char *buf; u32 mask; + int ret; /* * To update Nth mask entry, write: @@ -357,9 +358,9 @@ static ssize_t sof_ipc4_priority_mask_dfs_write(struct file *file, if (IS_ERR(buf)) return PTR_ERR(buf); - ret = sscanf(buf, "%d,0x%x", &id, &mask); + ret = sscanf(buf, "%u,0x%x", &id, &mask); if (ret != 2) { - ret = sscanf(buf, "%d,%x", &id, &mask); + ret = sscanf(buf, "%u,%x", &id, &mask); if (ret != 2) { ret = -EINVAL; goto out; diff --git a/sound/soc/sof/pm.c b/sound/soc/sof/pm.c index df740be645e8..8722bbd7fd3d 100644 --- a/sound/soc/sof/pm.c +++ b/sound/soc/sof/pm.c @@ -182,7 +182,7 @@ static int sof_suspend(struct device *dev, bool runtime_suspend) const struct sof_ipc_pm_ops *pm_ops = sdev->ipc->ops->pm; const struct sof_ipc_tplg_ops *tplg_ops = sdev->ipc->ops->tplg; pm_message_t pm_state; - u32 target_state = 0; + u32 target_state = snd_sof_dsp_power_target(sdev); int ret; /* do nothing if dsp suspend callback is not set */ @@ -192,6 +192,9 @@ static int sof_suspend(struct device *dev, bool runtime_suspend) if (runtime_suspend && !sof_ops(sdev)->runtime_suspend) return 0; + if (tplg_ops && tplg_ops->tear_down_all_pipelines) + tplg_ops->tear_down_all_pipelines(sdev, false); + if (sdev->fw_state != SOF_FW_BOOT_COMPLETE) goto suspend; @@ -206,7 +209,6 @@ static int sof_suspend(struct device *dev, bool runtime_suspend) } } - target_state = snd_sof_dsp_power_target(sdev); pm_state.event = target_state; /* Skip to platform-specific suspend if DSP is entering D0 */ @@ -217,9 +219,6 @@ static int sof_suspend(struct device *dev, bool runtime_suspend) goto suspend; } - if (tplg_ops->tear_down_all_pipelines) - tplg_ops->tear_down_all_pipelines(sdev, false); - /* suspend DMA trace */ sof_fw_trace_suspend(sdev, pm_state); diff --git a/sound/soc/sof/sof-audio.c b/sound/soc/sof/sof-audio.c index 7306a2649857..865c367eb2f2 100644 --- a/sound/soc/sof/sof-audio.c +++ b/sound/soc/sof/sof-audio.c @@ -271,9 +271,9 @@ sof_unprepare_widgets_in_path(struct snd_sof_dev *sdev, struct snd_soc_dapm_widg struct snd_sof_widget *swidget = widget->dobj.private; struct snd_soc_dapm_path *p; - /* return if the widget is in use or if it is already unprepared */ - if (!swidget->prepared || swidget->use_count > 1) - return; + /* skip if the widget is in use or if it is already unprepared */ + if (!swidget || !swidget->prepared || swidget->use_count > 0) + goto sink_unprepare; if (widget_ops[widget->id].ipc_unprepare) /* unprepare the source widget */ @@ -281,6 +281,7 @@ sof_unprepare_widgets_in_path(struct snd_sof_dev *sdev, struct snd_soc_dapm_widg swidget->prepared = false; +sink_unprepare: /* unprepare all widgets in the sink paths */ snd_soc_dapm_widget_for_each_sink_path(widget, p) { if (!p->walking && p->sink->dobj.private) { @@ -303,7 +304,7 @@ sof_prepare_widgets_in_path(struct snd_sof_dev *sdev, struct snd_soc_dapm_widget struct snd_soc_dapm_path *p; int ret; - if (!widget_ops[widget->id].ipc_prepare || swidget->prepared) + if (!swidget || !widget_ops[widget->id].ipc_prepare || swidget->prepared) goto sink_prepare; /* prepare the source widget */ @@ -326,7 +327,8 @@ sink_prepare: p->walking = false; if (ret < 0) { /* unprepare the source widget */ - if (widget_ops[widget->id].ipc_unprepare && swidget->prepared) { + if (widget_ops[widget->id].ipc_unprepare && + swidget && swidget->prepared) { widget_ops[widget->id].ipc_unprepare(swidget); swidget->prepared = false; } @@ -429,11 +431,11 @@ sof_walk_widgets_in_order(struct snd_sof_dev *sdev, struct snd_soc_dapm_widget_l for_each_dapm_widgets(list, i, widget) { /* starting widget for playback is AIF type */ - if (dir == SNDRV_PCM_STREAM_PLAYBACK && !WIDGET_IS_AIF(widget->id)) + if (dir == SNDRV_PCM_STREAM_PLAYBACK && widget->id != snd_soc_dapm_aif_in) continue; /* starting widget for capture is DAI type */ - if (dir == SNDRV_PCM_STREAM_CAPTURE && !WIDGET_IS_DAI(widget->id)) + if (dir == SNDRV_PCM_STREAM_CAPTURE && widget->id != snd_soc_dapm_dai_out) continue; switch (op) { diff --git a/sound/usb/implicit.c b/sound/usb/implicit.c index 41ac7185b42b..4727043fd745 100644 --- a/sound/usb/implicit.c +++ b/sound/usb/implicit.c @@ -471,7 +471,7 @@ snd_usb_find_implicit_fb_sync_format(struct snd_usb_audio *chip, subs = find_matching_substream(chip, stream, target->sync_ep, target->fmt_type); if (!subs) - return sync_fmt; + goto end; high_score = 0; list_for_each_entry(fp, &subs->fmt_list, list) { @@ -485,6 +485,7 @@ snd_usb_find_implicit_fb_sync_format(struct snd_usb_audio *chip, } } + end: if (fixed_rate) *fixed_rate = snd_usb_pcm_has_fixed_rate(subs); return sync_fmt; diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 99a66d0ef5b2..d959da7a1afb 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -160,9 +160,12 @@ find_substream_format(struct snd_usb_substream *subs, bool snd_usb_pcm_has_fixed_rate(struct snd_usb_substream *subs) { const struct audioformat *fp; - struct snd_usb_audio *chip = subs->stream->chip; + struct snd_usb_audio *chip; int rate = -1; + if (!subs) + return false; + chip = subs->stream->chip; if (!(chip->quirk_flags & QUIRK_FLAG_FIXED_RATE)) return false; list_for_each_entry(fp, &subs->fmt_list, list) { @@ -525,6 +528,8 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream, if (snd_usb_endpoint_compatible(chip, subs->data_endpoint, fmt, hw_params)) goto unlock; + if (stop_endpoints(subs, false)) + sync_pending_stops(subs); close_endpoints(chip, subs); } @@ -787,11 +792,27 @@ static int apply_hw_params_minmax(struct snd_interval *it, unsigned int rmin, return changed; } +/* get the specified endpoint object that is being used by other streams + * (i.e. the parameter is locked) + */ +static const struct snd_usb_endpoint * +get_endpoint_in_use(struct snd_usb_audio *chip, int endpoint, + const struct snd_usb_endpoint *ref_ep) +{ + const struct snd_usb_endpoint *ep; + + ep = snd_usb_get_endpoint(chip, endpoint); + if (ep && ep->cur_audiofmt && (ep != ref_ep || ep->opened > 1)) + return ep; + return NULL; +} + static int hw_rule_rate(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_usb_substream *subs = rule->private; struct snd_usb_audio *chip = subs->stream->chip; + const struct snd_usb_endpoint *ep; const struct audioformat *fp; struct snd_interval *it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE); unsigned int rmin, rmax, r; @@ -803,6 +824,29 @@ static int hw_rule_rate(struct snd_pcm_hw_params *params, list_for_each_entry(fp, &subs->fmt_list, list) { if (!hw_check_valid_format(subs, params, fp)) continue; + + ep = get_endpoint_in_use(chip, fp->endpoint, + subs->data_endpoint); + if (ep) { + hwc_debug("rate limit %d for ep#%x\n", + ep->cur_rate, fp->endpoint); + rmin = min(rmin, ep->cur_rate); + rmax = max(rmax, ep->cur_rate); + continue; + } + + if (fp->implicit_fb) { + ep = get_endpoint_in_use(chip, fp->sync_ep, + subs->sync_endpoint); + if (ep) { + hwc_debug("rate limit %d for sync_ep#%x\n", + ep->cur_rate, fp->sync_ep); + rmin = min(rmin, ep->cur_rate); + rmax = max(rmax, ep->cur_rate); + continue; + } + } + r = snd_usb_endpoint_get_clock_rate(chip, fp->clock); if (r > 0) { if (!snd_interval_test(it, r)) @@ -872,6 +916,8 @@ static int hw_rule_format(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_usb_substream *subs = rule->private; + struct snd_usb_audio *chip = subs->stream->chip; + const struct snd_usb_endpoint *ep; const struct audioformat *fp; struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); u64 fbits; @@ -881,6 +927,27 @@ static int hw_rule_format(struct snd_pcm_hw_params *params, list_for_each_entry(fp, &subs->fmt_list, list) { if (!hw_check_valid_format(subs, params, fp)) continue; + + ep = get_endpoint_in_use(chip, fp->endpoint, + subs->data_endpoint); + if (ep) { + hwc_debug("format limit %d for ep#%x\n", + ep->cur_format, fp->endpoint); + fbits |= pcm_format_to_bits(ep->cur_format); + continue; + } + + if (fp->implicit_fb) { + ep = get_endpoint_in_use(chip, fp->sync_ep, + subs->sync_endpoint); + if (ep) { + hwc_debug("format limit %d for sync_ep#%x\n", + ep->cur_format, fp->sync_ep); + fbits |= pcm_format_to_bits(ep->cur_format); + continue; + } + } + fbits |= fp->formats; } return apply_hw_params_format_bits(fmt, fbits); @@ -913,98 +980,95 @@ static int hw_rule_period_time(struct snd_pcm_hw_params *params, return apply_hw_params_minmax(it, pmin, UINT_MAX); } -/* get the EP or the sync EP for implicit fb when it's already set up */ -static const struct snd_usb_endpoint * -get_sync_ep_from_substream(struct snd_usb_substream *subs) -{ - struct snd_usb_audio *chip = subs->stream->chip; - const struct audioformat *fp; - const struct snd_usb_endpoint *ep; - - list_for_each_entry(fp, &subs->fmt_list, list) { - ep = snd_usb_get_endpoint(chip, fp->endpoint); - if (ep && ep->cur_audiofmt) { - /* if EP is already opened solely for this substream, - * we still allow us to change the parameter; otherwise - * this substream has to follow the existing parameter - */ - if (ep->cur_audiofmt != subs->cur_audiofmt || ep->opened > 1) - return ep; - } - if (!fp->implicit_fb) - continue; - /* for the implicit fb, check the sync ep as well */ - ep = snd_usb_get_endpoint(chip, fp->sync_ep); - if (ep && ep->cur_audiofmt) - return ep; - } - return NULL; -} - /* additional hw constraints for implicit feedback mode */ -static int hw_rule_format_implicit_fb(struct snd_pcm_hw_params *params, - struct snd_pcm_hw_rule *rule) -{ - struct snd_usb_substream *subs = rule->private; - const struct snd_usb_endpoint *ep; - struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT); - - ep = get_sync_ep_from_substream(subs); - if (!ep) - return 0; - - hwc_debug("applying %s\n", __func__); - return apply_hw_params_format_bits(fmt, pcm_format_to_bits(ep->cur_format)); -} - -static int hw_rule_rate_implicit_fb(struct snd_pcm_hw_params *params, - struct snd_pcm_hw_rule *rule) -{ - struct snd_usb_substream *subs = rule->private; - const struct snd_usb_endpoint *ep; - struct snd_interval *it; - - ep = get_sync_ep_from_substream(subs); - if (!ep) - return 0; - - hwc_debug("applying %s\n", __func__); - it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_RATE); - return apply_hw_params_minmax(it, ep->cur_rate, ep->cur_rate); -} - static int hw_rule_period_size_implicit_fb(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_usb_substream *subs = rule->private; + struct snd_usb_audio *chip = subs->stream->chip; + const struct audioformat *fp; const struct snd_usb_endpoint *ep; struct snd_interval *it; + unsigned int rmin, rmax; - ep = get_sync_ep_from_substream(subs); - if (!ep) - return 0; - - hwc_debug("applying %s\n", __func__); it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIOD_SIZE); - return apply_hw_params_minmax(it, ep->cur_period_frames, - ep->cur_period_frames); + hwc_debug("hw_rule_period_size: (%u,%u)\n", it->min, it->max); + rmin = UINT_MAX; + rmax = 0; + list_for_each_entry(fp, &subs->fmt_list, list) { + if (!hw_check_valid_format(subs, params, fp)) + continue; + ep = get_endpoint_in_use(chip, fp->endpoint, + subs->data_endpoint); + if (ep) { + hwc_debug("period size limit %d for ep#%x\n", + ep->cur_period_frames, fp->endpoint); + rmin = min(rmin, ep->cur_period_frames); + rmax = max(rmax, ep->cur_period_frames); + continue; + } + + if (fp->implicit_fb) { + ep = get_endpoint_in_use(chip, fp->sync_ep, + subs->sync_endpoint); + if (ep) { + hwc_debug("period size limit %d for sync_ep#%x\n", + ep->cur_period_frames, fp->sync_ep); + rmin = min(rmin, ep->cur_period_frames); + rmax = max(rmax, ep->cur_period_frames); + continue; + } + } + } + + if (!rmax) + return 0; /* no limit by implicit fb */ + return apply_hw_params_minmax(it, rmin, rmax); } static int hw_rule_periods_implicit_fb(struct snd_pcm_hw_params *params, struct snd_pcm_hw_rule *rule) { struct snd_usb_substream *subs = rule->private; + struct snd_usb_audio *chip = subs->stream->chip; + const struct audioformat *fp; const struct snd_usb_endpoint *ep; struct snd_interval *it; + unsigned int rmin, rmax; - ep = get_sync_ep_from_substream(subs); - if (!ep) - return 0; - - hwc_debug("applying %s\n", __func__); it = hw_param_interval(params, SNDRV_PCM_HW_PARAM_PERIODS); - return apply_hw_params_minmax(it, ep->cur_buffer_periods, - ep->cur_buffer_periods); + hwc_debug("hw_rule_periods: (%u,%u)\n", it->min, it->max); + rmin = UINT_MAX; + rmax = 0; + list_for_each_entry(fp, &subs->fmt_list, list) { + if (!hw_check_valid_format(subs, params, fp)) + continue; + ep = get_endpoint_in_use(chip, fp->endpoint, + subs->data_endpoint); + if (ep) { + hwc_debug("periods limit %d for ep#%x\n", + ep->cur_buffer_periods, fp->endpoint); + rmin = min(rmin, ep->cur_buffer_periods); + rmax = max(rmax, ep->cur_buffer_periods); + continue; + } + + if (fp->implicit_fb) { + ep = get_endpoint_in_use(chip, fp->sync_ep, + subs->sync_endpoint); + if (ep) { + hwc_debug("periods limit %d for sync_ep#%x\n", + ep->cur_buffer_periods, fp->sync_ep); + rmin = min(rmin, ep->cur_buffer_periods); + rmax = max(rmax, ep->cur_buffer_periods); + continue; + } + } + } + + if (!rmax) + return 0; /* no limit by implicit fb */ + return apply_hw_params_minmax(it, rmin, rmax); } /* @@ -1113,16 +1177,6 @@ static int setup_hw_info(struct snd_pcm_runtime *runtime, struct snd_usb_substre return err; /* additional hw constraints for implicit fb */ - err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_FORMAT, - hw_rule_format_implicit_fb, subs, - SNDRV_PCM_HW_PARAM_FORMAT, -1); - if (err < 0) - return err; - err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_RATE, - hw_rule_rate_implicit_fb, subs, - SNDRV_PCM_HW_PARAM_RATE, -1); - if (err < 0) - return err; err = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, hw_rule_period_size_implicit_fb, subs, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, -1); diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 3d13fdf7590c..3ecd1ba7fd4b 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2152,6 +2152,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = { QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x0525, 0xa4ad, /* Hamedal C20 usb camero */ QUIRK_FLAG_IFACE_SKIP_CLOSE), + DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */ + QUIRK_FLAG_FIXED_RATE), DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */ QUIRK_FLAG_FIXED_RATE), diff --git a/sound/usb/stream.c b/sound/usb/stream.c index f75601ca2d52..f10f4e6d3fb8 100644 --- a/sound/usb/stream.c +++ b/sound/usb/stream.c @@ -1222,6 +1222,12 @@ static int __snd_usb_parse_audio_interface(struct snd_usb_audio *chip, if (err < 0) return err; } + + /* try to set the interface... */ + usb_set_interface(chip->dev, iface_no, 0); + snd_usb_init_pitch(chip, fp); + snd_usb_init_sample_rate(chip, fp, fp->rate_max); + usb_set_interface(chip->dev, iface_no, altno); } return 0; } diff --git a/sound/xen/xen_snd_front.c b/sound/xen/xen_snd_front.c index 4041748c12e5..b66e037710d0 100644 --- a/sound/xen/xen_snd_front.c +++ b/sound/xen/xen_snd_front.c @@ -311,7 +311,7 @@ static int xen_drv_probe(struct xenbus_device *xb_dev, return xenbus_switch_state(xb_dev, XenbusStateInitialising); } -static int xen_drv_remove(struct xenbus_device *dev) +static void xen_drv_remove(struct xenbus_device *dev) { struct xen_snd_front_info *front_info = dev_get_drvdata(&dev->dev); int to = 100; @@ -345,7 +345,6 @@ static int xen_drv_remove(struct xenbus_device *dev) xen_snd_drv_fini(front_info); xenbus_frontend_closed(dev); - return 0; } static const struct xenbus_device_id xen_drv_ids[] = { diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index abc418650fec..683ca3af4084 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -41,7 +41,7 @@ (((midr) & MIDR_IMPLEMENTOR_MASK) >> MIDR_IMPLEMENTOR_SHIFT) #define MIDR_CPU_MODEL(imp, partnum) \ - (((imp) << MIDR_IMPLEMENTOR_SHIFT) | \ + ((_AT(u32, imp) << MIDR_IMPLEMENTOR_SHIFT) | \ (0xf << MIDR_ARCHITECTURE_SHIFT) | \ ((partnum) << MIDR_PARTNUM_SHIFT)) @@ -80,6 +80,7 @@ #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_A715 0xD4D #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B @@ -123,6 +124,8 @@ #define APPLE_CPU_PART_M1_FIRESTORM_PRO 0x025 #define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028 #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 +#define APPLE_CPU_PART_M2_BLIZZARD 0x032 +#define APPLE_CPU_PART_M2_AVALANCHE 0x033 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -142,6 +145,7 @@ #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_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715) #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) @@ -175,6 +179,8 @@ #define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO) #define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX) #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) +#define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) +#define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 316917b98707..a7a857f1784d 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -43,6 +43,7 @@ #define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_DIRTY_LOG_PAGE_OFFSET 64 #define KVM_REG_SIZE(id) \ (1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT)) diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 649e50a8f9dd..e48deab8901d 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -206,6 +206,8 @@ struct kvm_msr_list { struct kvm_msr_filter_range { #define KVM_MSR_FILTER_READ (1 << 0) #define KVM_MSR_FILTER_WRITE (1 << 1) +#define KVM_MSR_FILTER_RANGE_VALID_MASK (KVM_MSR_FILTER_READ | \ + KVM_MSR_FILTER_WRITE) __u32 flags; __u32 nmsrs; /* number of msrs in bitmap */ __u32 base; /* MSR index the bitmap starts at */ @@ -214,8 +216,11 @@ struct kvm_msr_filter_range { #define KVM_MSR_FILTER_MAX_RANGES 16 struct kvm_msr_filter { +#ifndef __KERNEL__ #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0) +#endif #define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0) +#define KVM_MSR_FILTER_VALID_MASK (KVM_MSR_FILTER_DEFAULT_DENY) __u32 flags; struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES]; }; diff --git a/tools/gpio/gpio-event-mon.c b/tools/gpio/gpio-event-mon.c index 6c122952c589..5dee2b98ab60 100644 --- a/tools/gpio/gpio-event-mon.c +++ b/tools/gpio/gpio-event-mon.c @@ -86,6 +86,7 @@ int monitor_device(const char *device_name, gpiotools_test_bit(values.bits, i)); } + i = 0; while (1) { struct gpio_v2_line_event event; diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h index cc7070c7439b..b4898ff085de 100644 --- a/tools/include/linux/build_bug.h +++ b/tools/include/linux/build_bug.h @@ -79,4 +79,13 @@ #define __static_assert(expr, msg, ...) _Static_assert(expr, msg) #endif // static_assert + +/* + * Compile time check that field has an expected offset + */ +#define ASSERT_STRUCT_OFFSET(type, field, expected_offset) \ + BUILD_BUG_ON_MSG(offsetof(type, field) != (expected_offset), \ + "Offset of " #field " in " #type " has changed.") + + #endif /* _LINUX_BUILD_BUG_H */ diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h index 5fc5b8029bff..7380093ba9e7 100644 --- a/tools/include/nolibc/arch-mips.h +++ b/tools/include/nolibc/arch-mips.h @@ -192,6 +192,7 @@ struct sys_stat_struct { __asm__ (".section .text\n" ".weak __start\n" ".set nomips16\n" + ".set push\n" ".set noreorder\n" ".option pic0\n" ".ent __start\n" @@ -210,6 +211,7 @@ __asm__ (".section .text\n" "li $v0, 4001\n" // NR_exit == 4001 "syscall\n" ".end __start\n" + ".set pop\n" ""); #endif // _NOLIBC_ARCH_MIPS_H diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h index ba04771cb3a3..a3bdd9803f8c 100644 --- a/tools/include/nolibc/arch-riscv.h +++ b/tools/include/nolibc/arch-riscv.h @@ -11,13 +11,13 @@ #define O_RDONLY 0 #define O_WRONLY 1 #define O_RDWR 2 -#define O_CREAT 0x100 -#define O_EXCL 0x200 -#define O_NOCTTY 0x400 -#define O_TRUNC 0x1000 -#define O_APPEND 0x2000 -#define O_NONBLOCK 0x4000 -#define O_DIRECTORY 0x200000 +#define O_CREAT 0x40 +#define O_EXCL 0x80 +#define O_NOCTTY 0x100 +#define O_TRUNC 0x200 +#define O_APPEND 0x400 +#define O_NONBLOCK 0x800 +#define O_DIRECTORY 0x10000 struct sys_stat_struct { unsigned long st_dev; /* Device. */ diff --git a/tools/include/nolibc/ctype.h b/tools/include/nolibc/ctype.h index e3000b2992d7..6f90706d0644 100644 --- a/tools/include/nolibc/ctype.h +++ b/tools/include/nolibc/ctype.h @@ -96,4 +96,7 @@ int ispunct(int c) return isgraph(c) && !isalnum(c); } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_CTYPE_H */ diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h index 06893d6dfb7a..9dc4919c769b 100644 --- a/tools/include/nolibc/errno.h +++ b/tools/include/nolibc/errno.h @@ -24,4 +24,7 @@ static int errno; */ #define MAX_ERRNO 4095 +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_ERRNO_H */ diff --git a/tools/include/nolibc/signal.h b/tools/include/nolibc/signal.h index ef47e71e2be3..137552216e46 100644 --- a/tools/include/nolibc/signal.h +++ b/tools/include/nolibc/signal.h @@ -19,4 +19,7 @@ int raise(int signal) return sys_kill(sys_getpid(), signal); } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_SIGNAL_H */ diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h index a3cebc4bc3ac..96ac8afc5aee 100644 --- a/tools/include/nolibc/stdio.h +++ b/tools/include/nolibc/stdio.h @@ -303,4 +303,7 @@ void perror(const char *msg) fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno); } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_STDIO_H */ diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h index 92378c4b9660..a24000d1e822 100644 --- a/tools/include/nolibc/stdlib.h +++ b/tools/include/nolibc/stdlib.h @@ -419,4 +419,7 @@ char *u64toa(uint64_t in) return itoa_buffer; } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_STDLIB_H */ diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index ad97c0d522b8..fffdaf6ff467 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -88,8 +88,11 @@ void *memset(void *dst, int b, size_t len) { char *p = dst; - while (len--) + while (len--) { + /* prevent gcc from recognizing memset() here */ + asm volatile(""); *(p++) = b; + } return dst; } @@ -285,4 +288,7 @@ char *strrchr(const char *s, int c) return (char *)ret; } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_STRING_H */ diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h index ce3ee03aa679..78473d34e27c 100644 --- a/tools/include/nolibc/sys.h +++ b/tools/include/nolibc/sys.h @@ -1243,5 +1243,7 @@ ssize_t write(int fd, const void *buf, size_t count) return ret; } +/* make sure to include all global symbols */ +#include "nolibc.h" #endif /* _NOLIBC_SYS_H */ diff --git a/tools/include/nolibc/time.h b/tools/include/nolibc/time.h index d18b7661fdd7..84655361b9ad 100644 --- a/tools/include/nolibc/time.h +++ b/tools/include/nolibc/time.h @@ -25,4 +25,7 @@ time_t time(time_t *tptr) return tv.tv_sec; } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_TIME_H */ diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h index 959997034e55..fbbc0e68c001 100644 --- a/tools/include/nolibc/types.h +++ b/tools/include/nolibc/types.h @@ -26,13 +26,13 @@ #define S_IFSOCK 0140000 #define S_IFMT 0170000 -#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR) -#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR) -#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK) -#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG) -#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO) -#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK) -#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK) +#define S_ISDIR(mode) (((mode) & S_IFMT) == S_IFDIR) +#define S_ISCHR(mode) (((mode) & S_IFMT) == S_IFCHR) +#define S_ISBLK(mode) (((mode) & S_IFMT) == S_IFBLK) +#define S_ISREG(mode) (((mode) & S_IFMT) == S_IFREG) +#define S_ISFIFO(mode) (((mode) & S_IFMT) == S_IFIFO) +#define S_ISLNK(mode) (((mode) & S_IFMT) == S_IFLNK) +#define S_ISSOCK(mode) (((mode) & S_IFMT) == S_IFSOCK) /* dirent types */ #define DT_UNKNOWN 0x0 @@ -89,39 +89,46 @@ #define EXIT_SUCCESS 0 #define EXIT_FAILURE 1 +#define FD_SETIDXMASK (8 * sizeof(unsigned long)) +#define FD_SETBITMASK (8 * sizeof(unsigned long)-1) + /* for select() */ typedef struct { - uint32_t fd32[(FD_SETSIZE + 31) / 32]; + unsigned long fds[(FD_SETSIZE + FD_SETBITMASK) / FD_SETIDXMASK]; } fd_set; -#define FD_CLR(fd, set) do { \ - fd_set *__set = (set); \ - int __fd = (fd); \ - if (__fd >= 0) \ - __set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \ +#define FD_CLR(fd, set) do { \ + fd_set *__set = (set); \ + int __fd = (fd); \ + if (__fd >= 0) \ + __set->fds[__fd / FD_SETIDXMASK] &= \ + ~(1U << (__fd & FX_SETBITMASK)); \ } while (0) -#define FD_SET(fd, set) do { \ - fd_set *__set = (set); \ - int __fd = (fd); \ - if (__fd >= 0) \ - __set->fd32[__fd / 32] |= 1U << (__fd & 31); \ +#define FD_SET(fd, set) do { \ + fd_set *__set = (set); \ + int __fd = (fd); \ + if (__fd >= 0) \ + __set->fds[__fd / FD_SETIDXMASK] |= \ + 1 << (__fd & FD_SETBITMASK); \ } while (0) -#define FD_ISSET(fd, set) ({ \ - fd_set *__set = (set); \ - int __fd = (fd); \ - int __r = 0; \ - if (__fd >= 0) \ - __r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \ - __r; \ +#define FD_ISSET(fd, set) ({ \ + fd_set *__set = (set); \ + int __fd = (fd); \ + int __r = 0; \ + if (__fd >= 0) \ + __r = !!(__set->fds[__fd / FD_SETIDXMASK] & \ +1U << (__fd & FD_SET_BITMASK)); \ + __r; \ }) -#define FD_ZERO(set) do { \ - fd_set *__set = (set); \ - int __idx; \ - for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \ - __set->fd32[__idx] = 0; \ +#define FD_ZERO(set) do { \ + fd_set *__set = (set); \ + int __idx; \ + int __size = (FD_SETSIZE+FD_SETBITMASK) / FD_SETIDXMASK;\ + for (__idx = 0; __idx < __size; __idx++) \ + __set->fds[__idx] = 0; \ } while (0) /* for poll() */ @@ -202,4 +209,7 @@ struct stat { }) #endif +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_TYPES_H */ diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h index 1c25e20ee360..1cfcd52106a4 100644 --- a/tools/include/nolibc/unistd.h +++ b/tools/include/nolibc/unistd.h @@ -51,4 +51,7 @@ int tcsetpgrp(int fd, pid_t pid) return ioctl(fd, TIOCSPGRP, &pid); } +/* make sure to include all global symbols */ +#include "nolibc.h" + #endif /* _NOLIBC_UNISTD_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 20522d4ba1e0..55155e262646 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1767,6 +1767,7 @@ struct kvm_xen_hvm_attr { __u8 runstate_update_flag; struct { __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) } shared_info; struct { __u32 send_port; @@ -1798,6 +1799,7 @@ struct kvm_xen_hvm_attr { } u; }; + /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 @@ -1823,6 +1825,7 @@ struct kvm_xen_vcpu_attr { __u16 pad[3]; union { __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) __u64 pad[8]; struct { __u64 state; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 4350be739f4f..4b7c8b33069e 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -427,6 +427,15 @@ static int decode_instructions(struct objtool_file *file) if (func->type != STT_NOTYPE && func->type != STT_FUNC) continue; + if (func->offset == sec->sh.sh_size) { + /* Heuristic: likely an "end" symbol */ + if (func->type == STT_NOTYPE) + continue; + WARN("%s(): STT_FUNC at end of section", + func->name); + return -1; + } + if (func->return_thunk || func->alias != func) continue; diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index c2504c39bdcb..5b8784675903 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -589,6 +589,8 @@ ifndef NO_LIBELF $(call feature_check,libbpf-bpf_program__set_insns) ifeq ($(feature-libbpf-bpf_program__set_insns), 1) CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS + else + dummy := $(error Error: libbpf devel library needs to be >= 0.8.0 to build with LIBBPF_DYNAMIC, update or build statically with the version that comes with the kernel sources); endif $(call feature_check,libbpf-btf__raw_data) ifeq ($(feature-libbpf-btf__raw_data), 1) @@ -602,6 +604,8 @@ ifndef NO_LIBELF dummy := $(error Error: No libbpf devel library found, please install libbpf-devel); endif else + # Libbpf will be built as a static library from tools/lib/bpf. + LIBBPF_STATIC := 1 CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM @@ -1314,14 +1318,6 @@ tip_instdir_SQ = $(subst ','\'',$(tip_instdir)) export perfexec_instdir_SQ -# If we install to $(HOME) we keep the traceevent default: -# $(HOME)/.traceevent/plugins -# Otherwise we install plugins into the global $(libdir). -ifdef DESTDIR -plugindir=$(libdir)/traceevent/plugins -plugindir_SQ= $(subst ','\'',$(plugindir)) -endif - print_var = $(eval $(print_var_code)) $(info $(MSG)) define print_var_code MSG = $(shell printf '...%40s: %s' $(1) $($(1))) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 1e32c93b8042..b7d9c4206230 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -303,10 +303,12 @@ ifneq ($(OUTPUT),) else LIBBPF_OUTPUT = $(CURDIR)/libbpf endif -LIBBPF_DESTDIR = $(LIBBPF_OUTPUT) -LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include -LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a -CFLAGS += -I$(LIBBPF_OUTPUT)/include +ifdef LIBBPF_STATIC + LIBBPF_DESTDIR = $(LIBBPF_OUTPUT) + LIBBPF_INCLUDE = $(LIBBPF_DESTDIR)/include + LIBBPF = $(LIBBPF_OUTPUT)/libbpf.a + CFLAGS += -I$(LIBBPF_OUTPUT)/include +endif ifneq ($(OUTPUT),) LIBSUBCMD_OUTPUT = $(abspath $(OUTPUT))/libsubcmd @@ -393,10 +395,8 @@ endif export PERL_PATH PERFLIBS = $(LIBAPI) $(LIBPERF) $(LIBSUBCMD) $(LIBSYMBOL) -ifndef NO_LIBBPF - ifndef LIBBPF_DYNAMIC - PERFLIBS += $(LIBBPF) - endif +ifdef LIBBPF_STATIC + PERFLIBS += $(LIBBPF) endif # We choose to avoid "if .. else if .. else .. endif endif" @@ -756,12 +756,15 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc $(arch_errno_name_array) \ $(sync_file_range_arrays) \ $(LIBAPI) \ - $(LIBBPF) \ $(LIBPERF) \ $(LIBSUBCMD) \ $(LIBSYMBOL) \ bpf-skel +ifdef LIBBPF_STATIC +prepare: $(LIBBPF) +endif + $(OUTPUT)%.o: %.c prepare FORCE $(Q)$(MAKE) -f $(srctree)/tools/build/Makefile.build dir=$(build-dir) $@ diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index e20656c431a4..8ae0a1535293 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -26,6 +26,7 @@ #include "util/string2.h" #include <linux/kernel.h> +#include <linux/numa.h> #include <linux/rbtree.h> #include <linux/string.h> #include <linux/zalloc.h> @@ -185,22 +186,33 @@ static int evsel__process_alloc_event(struct evsel *evsel, struct perf_sample *s total_allocated += bytes_alloc; nr_allocs++; - return 0; -} -static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_sample *sample) -{ - int ret = evsel__process_alloc_event(evsel, sample); + /* + * Commit 11e9734bcb6a ("mm/slab_common: unify NUMA and UMA + * version of tracepoints") adds the field "node" into the + * tracepoints 'kmalloc' and 'kmem_cache_alloc'. + * + * The legacy tracepoints 'kmalloc_node' and 'kmem_cache_alloc_node' + * also contain the field "node". + * + * If the tracepoint contains the field "node" the tool stats the + * cross allocation. + */ + if (evsel__field(evsel, "node")) { + int node1, node2; - if (!ret) { - int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}), - node2 = evsel__intval(evsel, sample, "node"); + node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}); + node2 = evsel__intval(evsel, sample, "node"); - if (node1 != node2) + /* + * If the field "node" is NUMA_NO_NODE (-1), we don't take it + * as a cross allocation. + */ + if ((node2 != NUMA_NO_NODE) && (node1 != node2)) nr_cross_allocs++; } - return ret; + return 0; } static int ptr_cmp(void *, void *); @@ -1369,8 +1381,8 @@ static int __cmd_kmem(struct perf_session *session) /* slab allocator */ { "kmem:kmalloc", evsel__process_alloc_event, }, { "kmem:kmem_cache_alloc", evsel__process_alloc_event, }, - { "kmem:kmalloc_node", evsel__process_alloc_node_event, }, - { "kmem:kmem_cache_alloc_node", evsel__process_alloc_node_event, }, + { "kmem:kmalloc_node", evsel__process_alloc_event, }, + { "kmem:kmem_cache_alloc_node", evsel__process_alloc_event, }, { "kmem:kfree", evsel__process_free_event, }, { "kmem:kmem_cache_free", evsel__process_free_event, }, /* page allocator */ @@ -1824,6 +1836,19 @@ static int parse_line_opt(const struct option *opt __maybe_unused, return 0; } +static bool slab_legacy_tp_is_exposed(void) +{ + /* + * The tracepoints "kmem:kmalloc_node" and + * "kmem:kmem_cache_alloc_node" have been removed on the latest + * kernel, if the tracepoint "kmem:kmalloc_node" is existed it + * means the tool is running on an old kernel, we need to + * rollback to support these legacy tracepoints. + */ + return IS_ERR(trace_event__tp_format("kmem", "kmalloc_node")) ? + false : true; +} + static int __cmd_record(int argc, const char **argv) { const char * const record_args[] = { @@ -1831,22 +1856,28 @@ static int __cmd_record(int argc, const char **argv) }; const char * const slab_events[] = { "-e", "kmem:kmalloc", - "-e", "kmem:kmalloc_node", "-e", "kmem:kfree", "-e", "kmem:kmem_cache_alloc", - "-e", "kmem:kmem_cache_alloc_node", "-e", "kmem:kmem_cache_free", }; + const char * const slab_legacy_events[] = { + "-e", "kmem:kmalloc_node", + "-e", "kmem:kmem_cache_alloc_node", + }; const char * const page_events[] = { "-e", "kmem:mm_page_alloc", "-e", "kmem:mm_page_free", }; unsigned int rec_argc, i, j; const char **rec_argv; + unsigned int slab_legacy_tp_exposed = slab_legacy_tp_is_exposed(); rec_argc = ARRAY_SIZE(record_args) + argc - 1; - if (kmem_slab) + if (kmem_slab) { rec_argc += ARRAY_SIZE(slab_events); + if (slab_legacy_tp_exposed) + rec_argc += ARRAY_SIZE(slab_legacy_events); + } if (kmem_page) rec_argc += ARRAY_SIZE(page_events) + 1; /* for -g */ @@ -1861,6 +1892,10 @@ static int __cmd_record(int argc, const char **argv) if (kmem_slab) { for (j = 0; j < ARRAY_SIZE(slab_events); j++, i++) rec_argv[i] = strdup(slab_events[j]); + if (slab_legacy_tp_exposed) { + for (j = 0; j < ARRAY_SIZE(slab_legacy_events); j++, i++) + rec_argv[i] = strdup(slab_legacy_events[j]); + } } if (kmem_page) { rec_argv[i++] = strdup("-g"); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index 86e06f136f40..d21fe0f32a6d 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -16,7 +16,9 @@ #include "util/record.h" #include <api/fs/tracing_path.h> +#ifdef HAVE_LIBBPF_SUPPORT #include <bpf/bpf.h> +#endif #include "util/bpf_map.h" #include "util/rlimit.h" #include "builtin.h" diff --git a/tools/perf/tests/bpf-script-test-prologue.c b/tools/perf/tests/bpf-script-test-prologue.c index bd83d364cf30..91778b5c6125 100644 --- a/tools/perf/tests/bpf-script-test-prologue.c +++ b/tools/perf/tests/bpf-script-test-prologue.c @@ -20,6 +20,8 @@ # undef if #endif +typedef unsigned int __bitwise fmode_t; + #define FMODE_READ 0x1 #define FMODE_WRITE 0x2 diff --git a/tools/perf/tests/make b/tools/perf/tests/make index 05e818a8bbad..009d6efb673c 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -222,19 +222,7 @@ installed_files_bin := bin/perf installed_files_bin += etc/bash_completion.d/perf installed_files_bin += libexec/perf-core/perf-archive -installed_files_plugins := $(lib)/traceevent/plugins/plugin_cfg80211.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_scsi.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_xen.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_function.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_sched_switch.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_mac80211.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_kvm.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_kmem.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_hrtimer.so -installed_files_plugins += $(lib)/traceevent/plugins/plugin_jbd2.so - installed_files_all := $(installed_files_bin) -installed_files_all += $(installed_files_plugins) test_make_install := $(call test_dest_files,$(installed_files_all)) test_make_install_O := $(call test_dest_files,$(installed_files_all)) diff --git a/tools/perf/tests/shell/buildid.sh b/tools/perf/tests/shell/buildid.sh index f05670d1e39e..aaf851108ca3 100755 --- a/tools/perf/tests/shell/buildid.sh +++ b/tools/perf/tests/shell/buildid.sh @@ -77,7 +77,20 @@ check() file=${build_id_dir}/.build-id/${id:0:2}/`readlink ${link}`/elf echo "file: ${file}" - if [ ! -x $file ]; then + # Check for file permission of original file + # in case of pe-file.exe file + echo $1 | grep ".exe" + if [ $? -eq 0 ]; then + if [ -x $1 -a ! -x $file ]; then + echo "failed: file ${file} executable does not exist" + exit 1 + fi + + if [ ! -x $file -a ! -e $file ]; then + echo "failed: file ${file} does not exist" + exit 1 + fi + elif [ ! -x $file ]; then echo "failed: file ${file} does not exist" exit 1 fi diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index de3701a2a212..13c3a237b9c9 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -33,7 +33,10 @@ typedef __kernel_sa_family_t sa_family_t; struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ - char sa_data[14]; /* 14 bytes of protocol address */ + union { + char sa_data_min[14]; /* Minimum 14 bytes of protocol address */ + DECLARE_FLEX_ARRAY(char, sa_data); + }; }; struct linger { diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index 265d20cc126b..c2e323cd7d49 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -2611,7 +2611,7 @@ static int find_dso_sym(struct dso *dso, const char *sym_name, u64 *start, *size = sym->start - *start; if (idx > 0) { if (*size) - return 1; + return 0; } else if (dso_sym_match(sym, sym_name, &cnt, idx)) { print_duplicate_syms(dso, sym_name); return -EINVAL; diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h index 4dbf26408b69..c6d21c07b14c 100644 --- a/tools/perf/util/bpf_counter.h +++ b/tools/perf/util/bpf_counter.h @@ -4,9 +4,12 @@ #include <linux/list.h> #include <sys/resource.h> + +#ifdef HAVE_LIBBPF_SUPPORT #include <bpf/bpf.h> #include <bpf/btf.h> #include <bpf/libbpf.h> +#endif struct evsel; struct target; @@ -87,6 +90,8 @@ static inline void set_max_rlimit(void) setrlimit(RLIMIT_MEMLOCK, &rinf); } +#ifdef HAVE_BPF_SKEL + static inline __u32 bpf_link_get_id(int fd) { struct bpf_link_info link_info = { .id = 0, }; @@ -127,5 +132,6 @@ static inline int bperf_trigger_reading(int prog_fd, int cpu) return bpf_prog_test_run_opts(prog_fd, &opts); } +#endif /* HAVE_BPF_SKEL */ #endif /* __PERF_BPF_COUNTER_H */ diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c index a839b30c981b..ea9c083ab1e3 100644 --- a/tools/perf/util/build-id.c +++ b/tools/perf/util/build-id.c @@ -715,9 +715,13 @@ build_id_cache__add(const char *sbuild_id, const char *name, const char *realnam } else if (nsi && nsinfo__need_setns(nsi)) { if (copyfile_ns(name, filename, nsi)) goto out_free; - } else if (link(realname, filename) && errno != EEXIST && - copyfile(name, filename)) - goto out_free; + } else if (link(realname, filename) && errno != EEXIST) { + struct stat f_stat; + + if (!(stat(name, &f_stat) < 0) && + copyfile_mode(name, filename, f_stat.st_mode)) + goto out_free; + } } /* Some binaries are stripped, but have .debug files with their symbol diff --git a/tools/perf/util/expr.l b/tools/perf/util/expr.l index 0168a9637330..d47de5f270a8 100644 --- a/tools/perf/util/expr.l +++ b/tools/perf/util/expr.l @@ -42,8 +42,11 @@ static char *normalize(char *str, int runtime) char *dst = str; while (*str) { - if (*str == '\\') + if (*str == '\\') { *dst++ = *++str; + if (!*str) + break; + } else if (*str == '?') { char *paramval; int i = 0; diff --git a/tools/testing/memblock/internal.h b/tools/testing/memblock/internal.h index fdb7f5db7308..85973e55489e 100644 --- a/tools/testing/memblock/internal.h +++ b/tools/testing/memblock/internal.h @@ -15,6 +15,10 @@ bool mirrored_kernelcore = false; struct page {}; +void __free_pages_core(struct page *page, unsigned int order) +{ +} + void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order) { diff --git a/tools/testing/selftests/amd-pstate/Makefile b/tools/testing/selftests/amd-pstate/Makefile index 5f195ee756d6..5fd1424db37d 100644 --- a/tools/testing/selftests/amd-pstate/Makefile +++ b/tools/testing/selftests/amd-pstate/Makefile @@ -7,11 +7,6 @@ all: uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) -ifeq (x86,$(ARCH)) -TEST_GEN_FILES += ../../../power/x86/amd_pstate_tracer/amd_pstate_trace.py -TEST_GEN_FILES += ../../../power/x86/intel_pstate_tracer/intel_pstate_tracer.py -endif - TEST_PROGS := run.sh TEST_FILES := basic.sh tbench.sh gitsource.sh diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c index 2cf0c7a3fe23..567e07c19ecc 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c @@ -30,6 +30,8 @@ #define MAX_STRERR_LEN 256 #define MAX_TEST_NAME 80 +#define __always_unused __attribute__((__unused__)) + #define _FAIL(errnum, fmt...) \ ({ \ error_at_line(0, (errnum), __func__, __LINE__, fmt); \ @@ -321,7 +323,8 @@ static int socket_loopback(int family, int sotype) return socket_loopback_reuseport(family, sotype, -1); } -static void test_insert_invalid(int family, int sotype, int mapfd) +static void test_insert_invalid(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u32 key = 0; u64 value; @@ -338,7 +341,8 @@ static void test_insert_invalid(int family, int sotype, int mapfd) FAIL_ERRNO("map_update: expected EBADF"); } -static void test_insert_opened(int family, int sotype, int mapfd) +static void test_insert_opened(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u32 key = 0; u64 value; @@ -359,7 +363,8 @@ static void test_insert_opened(int family, int sotype, int mapfd) xclose(s); } -static void test_insert_bound(int family, int sotype, int mapfd) +static void test_insert_bound(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; socklen_t len; @@ -386,7 +391,8 @@ close: xclose(s); } -static void test_insert(int family, int sotype, int mapfd) +static void test_insert(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u64 value; u32 key; @@ -402,7 +408,8 @@ static void test_insert(int family, int sotype, int mapfd) xclose(s); } -static void test_delete_after_insert(int family, int sotype, int mapfd) +static void test_delete_after_insert(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u64 value; u32 key; @@ -419,7 +426,8 @@ static void test_delete_after_insert(int family, int sotype, int mapfd) xclose(s); } -static void test_delete_after_close(int family, int sotype, int mapfd) +static void test_delete_after_close(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { int err, s; u64 value; @@ -442,7 +450,8 @@ static void test_delete_after_close(int family, int sotype, int mapfd) FAIL_ERRNO("map_delete: expected EINVAL/EINVAL"); } -static void test_lookup_after_insert(int family, int sotype, int mapfd) +static void test_lookup_after_insert(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u64 cookie, value; socklen_t len; @@ -470,7 +479,8 @@ static void test_lookup_after_insert(int family, int sotype, int mapfd) xclose(s); } -static void test_lookup_after_delete(int family, int sotype, int mapfd) +static void test_lookup_after_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { int err, s; u64 value; @@ -493,7 +503,8 @@ static void test_lookup_after_delete(int family, int sotype, int mapfd) xclose(s); } -static void test_lookup_32_bit_value(int family, int sotype, int mapfd) +static void test_lookup_32_bit_value(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { u32 key, value32; int err, s; @@ -523,7 +534,8 @@ close: xclose(s); } -static void test_update_existing(int family, int sotype, int mapfd) +static void test_update_existing(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { int s1, s2; u64 value; @@ -551,7 +563,7 @@ close_s1: /* Exercise the code path where we destroy child sockets that never * got accept()'ed, aka orphans, when parent socket gets closed. */ -static void test_destroy_orphan_child(int family, int sotype, int mapfd) +static void do_destroy_orphan_child(int family, int sotype, int mapfd) { struct sockaddr_storage addr; socklen_t len; @@ -582,10 +594,38 @@ close_srv: xclose(s); } +static void test_destroy_orphan_child(struct test_sockmap_listen *skel, + int family, int sotype, int mapfd) +{ + int msg_verdict = bpf_program__fd(skel->progs.prog_msg_verdict); + int skb_verdict = bpf_program__fd(skel->progs.prog_skb_verdict); + const struct test { + int progfd; + enum bpf_attach_type atype; + } tests[] = { + { -1, -1 }, + { msg_verdict, BPF_SK_MSG_VERDICT }, + { skb_verdict, BPF_SK_SKB_VERDICT }, + }; + const struct test *t; + + for (t = tests; t < tests + ARRAY_SIZE(tests); t++) { + if (t->progfd != -1 && + xbpf_prog_attach(t->progfd, mapfd, t->atype, 0) != 0) + return; + + do_destroy_orphan_child(family, sotype, mapfd); + + if (t->progfd != -1) + xbpf_prog_detach2(t->progfd, mapfd, t->atype); + } +} + /* Perform a passive open after removing listening socket from SOCKMAP * to ensure that callbacks get restored properly. */ -static void test_clone_after_delete(int family, int sotype, int mapfd) +static void test_clone_after_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; socklen_t len; @@ -621,7 +661,8 @@ close_srv: * SOCKMAP, but got accept()'ed only after the parent has been removed * from SOCKMAP, gets cloned without parent psock state or callbacks. */ -static void test_accept_after_delete(int family, int sotype, int mapfd) +static void test_accept_after_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; const u32 zero = 0; @@ -675,7 +716,8 @@ close_srv: /* Check that child socket that got created and accepted while parent * was in a SOCKMAP is cloned without parent psock state or callbacks. */ -static void test_accept_before_delete(int family, int sotype, int mapfd) +static void test_accept_before_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct sockaddr_storage addr; const u32 zero = 0, one = 1; @@ -784,7 +826,8 @@ done: return NULL; } -static void test_syn_recv_insert_delete(int family, int sotype, int mapfd) +static void test_syn_recv_insert_delete(struct test_sockmap_listen *skel __always_unused, + int family, int sotype, int mapfd) { struct connect_accept_ctx ctx = { 0 }; struct sockaddr_storage addr; @@ -847,7 +890,8 @@ static void *listen_thread(void *arg) return NULL; } -static void test_race_insert_listen(int family, int socktype, int mapfd) +static void test_race_insert_listen(struct test_sockmap_listen *skel __always_unused, + int family, int socktype, int mapfd) { struct connect_accept_ctx ctx = { 0 }; const u32 zero = 0; @@ -1473,7 +1517,8 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, int family, int sotype) { const struct op_test { - void (*fn)(int family, int sotype, int mapfd); + void (*fn)(struct test_sockmap_listen *skel, + int family, int sotype, int mapfd); const char *name; int sotype; } tests[] = { @@ -1520,7 +1565,7 @@ static void test_ops(struct test_sockmap_listen *skel, struct bpf_map *map, if (!test__start_subtest(s)) continue; - t->fn(family, sotype, map_fd); + t->fn(skel, family, sotype, map_fd); test_ops_cleanup(map); } } diff --git a/tools/testing/selftests/bpf/verifier/search_pruning.c b/tools/testing/selftests/bpf/verifier/search_pruning.c index 68b14fdfebdb..d63fd8991b03 100644 --- a/tools/testing/selftests/bpf/verifier/search_pruning.c +++ b/tools/testing/selftests/bpf/verifier/search_pruning.c @@ -225,3 +225,39 @@ .result_unpriv = ACCEPT, .insn_processed = 15, }, +/* The test performs a conditional 64-bit write to a stack location + * fp[-8], this is followed by an unconditional 8-bit write to fp[-8], + * then data is read from fp[-8]. This sequence is unsafe. + * + * The test would be mistakenly marked as safe w/o dst register parent + * preservation in verifier.c:copy_register_state() function. + * + * Note the usage of BPF_F_TEST_STATE_FREQ to force creation of the + * checkpoint state after conditional 64-bit assignment. + */ +{ + "write tracking and register parent chain bug", + .insns = { + /* r6 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + /* r0 = ktime_get_ns() */ + BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns), + /* if r0 > r6 goto +1 */ + BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_6, 1), + /* *(u64 *)(r10 - 8) = 0xdeadbeef */ + BPF_ST_MEM(BPF_DW, BPF_REG_FP, -8, 0xdeadbeef), + /* r1 = 42 */ + BPF_MOV64_IMM(BPF_REG_1, 42), + /* *(u8 *)(r10 - 8) = r1 */ + BPF_STX_MEM(BPF_B, BPF_REG_FP, BPF_REG_1, -8), + /* r2 = *(u64 *)(r10 - 8) */ + BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_FP, -8), + /* exit(0) */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .flags = BPF_F_TEST_STATE_FREQ, + .errstr = "invalid read from stack off -8+1 size 8", + .result = REJECT, +}, diff --git a/tools/testing/selftests/cgroup/test_cpuset_prs.sh b/tools/testing/selftests/cgroup/test_cpuset_prs.sh index 186e1c26867e..75c100de90ff 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_prs.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_prs.sh @@ -268,6 +268,7 @@ TEST_MATRIX=( # Taking away all CPUs from parent or itself if there are tasks # will make the partition invalid. " S+ C2-3:P1:S+ C3:P1 . . T C2-3 . . 0 A1:2-3,A2:2-3 A1:P1,A2:P-1" + " S+ C3:P1:S+ C3 . . T P1 . . 0 A1:3,A2:3 A1:P1,A2:P-1" " S+ $SETUP_A123_PARTITIONS . T:C2-3 . . . 0 A1:2-3,A2:2-3,A3:3 A1:P1,A2:P-1,A3:P-1" " S+ $SETUP_A123_PARTITIONS . T:C2-3:C1-3 . . . 0 A1:1,A2:2,A3:3 A1:P1,A2:P1,A3:P1" diff --git a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh index 7f35dc3d15df..7f35dc3d15df 100644..100755 --- a/tools/testing/selftests/filesystems/fat/run_fat_tests.sh +++ b/tools/testing/selftests/filesystems/fat/run_fat_tests.sh diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index df0989949eb5..84a627c43795 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -67,6 +67,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid TEST_GEN_PROGS_x86_64 += x86_64/hyperv_evmcs +TEST_GEN_PROGS_x86_64 += x86_64/hyperv_extended_hypercalls TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features TEST_GEN_PROGS_x86_64 += x86_64/hyperv_ipi TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/aarch64/page_fault_test.c index beb944fa6fd4..54680dc5887f 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/aarch64/page_fault_test.c @@ -237,6 +237,11 @@ static void guest_check_s1ptw_wr_in_dirty_log(void) GUEST_SYNC(CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG); } +static void guest_check_no_s1ptw_wr_in_dirty_log(void) +{ + GUEST_SYNC(CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG); +} + static void guest_exec(void) { int (*code)(void) = (int (*)(void))TEST_EXEC_GVA; @@ -304,7 +309,7 @@ static struct uffd_args { /* Returns true to continue the test, and false if it should be skipped. */ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, - struct uffd_args *args, bool expect_write) + struct uffd_args *args) { uint64_t addr = msg->arg.pagefault.address; uint64_t flags = msg->arg.pagefault.flags; @@ -313,7 +318,6 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, TEST_ASSERT(uffd_mode == UFFDIO_REGISTER_MODE_MISSING, "The only expected UFFD mode is MISSING"); - ASSERT_EQ(!!(flags & UFFD_PAGEFAULT_FLAG_WRITE), expect_write); ASSERT_EQ(addr, (uint64_t)args->hva); pr_debug("uffd fault: addr=%p write=%d\n", @@ -337,19 +341,14 @@ static int uffd_generic_handler(int uffd_mode, int uffd, struct uffd_msg *msg, return 0; } -static int uffd_pt_write_handler(int mode, int uffd, struct uffd_msg *msg) -{ - return uffd_generic_handler(mode, uffd, msg, &pt_args, true); -} - -static int uffd_data_write_handler(int mode, int uffd, struct uffd_msg *msg) +static int uffd_pt_handler(int mode, int uffd, struct uffd_msg *msg) { - return uffd_generic_handler(mode, uffd, msg, &data_args, true); + return uffd_generic_handler(mode, uffd, msg, &pt_args); } -static int uffd_data_read_handler(int mode, int uffd, struct uffd_msg *msg) +static int uffd_data_handler(int mode, int uffd, struct uffd_msg *msg) { - return uffd_generic_handler(mode, uffd, msg, &data_args, false); + return uffd_generic_handler(mode, uffd, msg, &data_args); } static void setup_uffd_args(struct userspace_mem_region *region, @@ -471,9 +470,12 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd) { struct userspace_mem_region *data_region, *pt_region; bool continue_test = true; + uint64_t pte_gpa, pte_pg; data_region = vm_get_mem_region(vm, MEM_REGION_TEST_DATA); pt_region = vm_get_mem_region(vm, MEM_REGION_PT); + pte_gpa = addr_hva2gpa(vm, virt_get_pte_hva(vm, TEST_GVA)); + pte_pg = (pte_gpa - pt_region->region.guest_phys_addr) / getpagesize(); if (cmd == CMD_SKIP_TEST) continue_test = false; @@ -486,13 +488,13 @@ static bool handle_cmd(struct kvm_vm *vm, int cmd) TEST_ASSERT(check_write_in_dirty_log(vm, data_region, 0), "Missing write in dirty log"); if (cmd & CMD_CHECK_S1PTW_WR_IN_DIRTY_LOG) - TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, 0), + TEST_ASSERT(check_write_in_dirty_log(vm, pt_region, pte_pg), "Missing s1ptw write in dirty log"); if (cmd & CMD_CHECK_NO_WRITE_IN_DIRTY_LOG) TEST_ASSERT(!check_write_in_dirty_log(vm, data_region, 0), "Unexpected write in dirty log"); if (cmd & CMD_CHECK_NO_S1PTW_WR_IN_DIRTY_LOG) - TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, 0), + TEST_ASSERT(!check_write_in_dirty_log(vm, pt_region, pte_pg), "Unexpected s1ptw write in dirty log"); return continue_test; @@ -797,7 +799,7 @@ static void help(char *name) .expected_events = { .uffd_faults = _uffd_faults, }, \ } -#define TEST_DIRTY_LOG(_access, _with_af, _test_check) \ +#define TEST_DIRTY_LOG(_access, _with_af, _test_check, _pt_check) \ { \ .name = SCAT3(dirty_log, _access, _with_af), \ .data_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ @@ -805,13 +807,12 @@ static void help(char *name) .guest_prepare = { _PREPARE(_with_af), \ _PREPARE(_access) }, \ .guest_test = _access, \ - .guest_test_check = { _CHECK(_with_af), _test_check, \ - guest_check_s1ptw_wr_in_dirty_log}, \ + .guest_test_check = { _CHECK(_with_af), _test_check, _pt_check }, \ .expected_events = { 0 }, \ } #define TEST_UFFD_AND_DIRTY_LOG(_access, _with_af, _uffd_data_handler, \ - _uffd_faults, _test_check) \ + _uffd_faults, _test_check, _pt_check) \ { \ .name = SCAT3(uffd_and_dirty_log, _access, _with_af), \ .data_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ @@ -820,16 +821,17 @@ static void help(char *name) _PREPARE(_access) }, \ .guest_test = _access, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ - .guest_test_check = { _CHECK(_with_af), _test_check }, \ + .guest_test_check = { _CHECK(_with_af), _test_check, _pt_check }, \ .uffd_data_handler = _uffd_data_handler, \ - .uffd_pt_handler = uffd_pt_write_handler, \ + .uffd_pt_handler = uffd_pt_handler, \ .expected_events = { .uffd_faults = _uffd_faults, }, \ } #define TEST_RO_MEMSLOT(_access, _mmio_handler, _mmio_exits) \ { \ - .name = SCAT3(ro_memslot, _access, _with_af), \ + .name = SCAT2(ro_memslot, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .mmio_handler = _mmio_handler, \ @@ -840,6 +842,7 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_no_syndrome, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .guest_test = _access, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ .expected_events = { .fail_vcpu_runs = 1 }, \ @@ -848,9 +851,9 @@ static void help(char *name) #define TEST_RO_MEMSLOT_AND_DIRTY_LOG(_access, _mmio_handler, _mmio_exits, \ _test_check) \ { \ - .name = SCAT3(ro_memslot, _access, _with_af), \ + .name = SCAT2(ro_memslot, _access), \ .data_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ - .pt_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ + .pt_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .guest_test_check = { _test_check }, \ @@ -862,7 +865,7 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_no_syn_and_dlog, _access), \ .data_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ - .pt_memslot_flags = KVM_MEM_LOG_DIRTY_PAGES, \ + .pt_memslot_flags = KVM_MEM_READONLY | KVM_MEM_LOG_DIRTY_PAGES, \ .guest_test = _access, \ .guest_test_check = { _test_check }, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ @@ -874,11 +877,12 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_uffd, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ .guest_prepare = { _PREPARE(_access) }, \ .guest_test = _access, \ .uffd_data_handler = _uffd_data_handler, \ - .uffd_pt_handler = uffd_pt_write_handler, \ + .uffd_pt_handler = uffd_pt_handler, \ .mmio_handler = _mmio_handler, \ .expected_events = { .mmio_exits = _mmio_exits, \ .uffd_faults = _uffd_faults }, \ @@ -889,10 +893,11 @@ static void help(char *name) { \ .name = SCAT2(ro_memslot_no_syndrome, _access), \ .data_memslot_flags = KVM_MEM_READONLY, \ + .pt_memslot_flags = KVM_MEM_READONLY, \ .mem_mark_cmd = CMD_HOLE_DATA | CMD_HOLE_PT, \ .guest_test = _access, \ .uffd_data_handler = _uffd_data_handler, \ - .uffd_pt_handler = uffd_pt_write_handler, \ + .uffd_pt_handler = uffd_pt_handler, \ .fail_vcpu_run_handler = fail_vcpu_run_mmio_no_syndrome_handler, \ .expected_events = { .fail_vcpu_runs = 1, \ .uffd_faults = _uffd_faults }, \ @@ -933,44 +938,51 @@ static struct test_desc tests[] = { * (S1PTW). */ TEST_UFFD(guest_read64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), - /* no_af should also lead to a PT write. */ + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_read64, no_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), - /* Note how that cas invokes the read handler. */ + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_cas, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), /* * Can't test guest_at with_af as it's IMPDEF whether the AF is set. * The S1PTW fault should still be marked as a write. */ TEST_UFFD(guest_at, no_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 1), + uffd_no_handler, uffd_pt_handler, 1), TEST_UFFD(guest_ld_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_write64, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_write_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_dc_zva, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_write_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_st_preidx, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_write_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), TEST_UFFD(guest_exec, with_af, CMD_HOLE_DATA | CMD_HOLE_PT, - uffd_data_read_handler, uffd_pt_write_handler, 2), + uffd_data_handler, uffd_pt_handler, 2), /* * Try accesses when the data and PT memory regions are both * tracked for dirty logging. */ - TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log), - /* no_af should also lead to a PT write. */ - TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_ld_preidx, with_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log), - TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log), - TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log), - TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log), - TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log), + TEST_DIRTY_LOG(guest_read64, with_af, guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_read64, no_af, guest_check_no_write_in_dirty_log, + guest_check_no_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_ld_preidx, with_af, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_at, no_af, guest_check_no_write_in_dirty_log, + guest_check_no_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_exec, with_af, guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_write64, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_cas, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_dc_zva, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_DIRTY_LOG(guest_st_preidx, with_af, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), /* * Access when the data and PT memory regions are both marked for @@ -980,29 +992,43 @@ static struct test_desc tests[] = { * fault, and nothing in the dirty log. Any S1PTW should result in * a write in the dirty log and a userfaultfd write. */ - TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af, uffd_data_read_handler, 2, - guest_check_no_write_in_dirty_log), - /* no_af should also lead to a PT write. */ - TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af, uffd_data_read_handler, 2, - guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af, uffd_data_read_handler, - 2, guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, 0, 1, - guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af, uffd_data_read_handler, 2, - guest_check_no_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af, uffd_data_write_handler, - 2, guest_check_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af, uffd_data_read_handler, 2, - guest_check_write_in_dirty_log), - TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af, uffd_data_write_handler, - 2, guest_check_write_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_read64, with_af, + uffd_data_handler, 2, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_read64, no_af, + uffd_data_handler, 2, + guest_check_no_write_in_dirty_log, + guest_check_no_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_ld_preidx, with_af, + uffd_data_handler, + 2, guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_at, with_af, uffd_no_handler, 1, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_exec, with_af, + uffd_data_handler, 2, + guest_check_no_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_write64, with_af, + uffd_data_handler, + 2, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_cas, with_af, + uffd_data_handler, 2, + guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), + TEST_UFFD_AND_DIRTY_LOG(guest_dc_zva, with_af, + uffd_data_handler, + 2, guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), TEST_UFFD_AND_DIRTY_LOG(guest_st_preidx, with_af, - uffd_data_write_handler, 2, - guest_check_write_in_dirty_log), - + uffd_data_handler, 2, + guest_check_write_in_dirty_log, + guest_check_s1ptw_wr_in_dirty_log), /* - * Try accesses when the data memory region is marked read-only + * Access when both the PT and data regions are marked read-only * (with KVM_MEM_READONLY). Writes with a syndrome result in an * MMIO exit, writes with no syndrome (e.g., CAS) result in a * failed vcpu run, and reads/execs with and without syndroms do @@ -1018,7 +1044,7 @@ static struct test_desc tests[] = { TEST_RO_MEMSLOT_NO_SYNDROME(guest_st_preidx), /* - * Access when both the data region is both read-only and marked + * The PT and data regions are both read-only and marked * for dirty logging at the same time. The expected result is that * for writes there should be no write in the dirty log. The * readonly handling is the same as if the memslot was not marked @@ -1043,7 +1069,7 @@ static struct test_desc tests[] = { guest_check_no_write_in_dirty_log), /* - * Access when the data region is both read-only and punched with + * The PT and data regions are both read-only and punched with * holes tracked with userfaultfd. The expected result is the * union of both userfaultfd and read-only behaviors. For example, * write accesses result in a userfaultfd write fault and an MMIO @@ -1051,22 +1077,15 @@ static struct test_desc tests[] = { * no userfaultfd write fault. Reads result in userfaultfd getting * triggered. */ - TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0, - uffd_data_read_handler, 2), - TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0, - uffd_data_read_handler, 2), - TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0, - uffd_no_handler, 1), - TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0, - uffd_data_read_handler, 2), + TEST_RO_MEMSLOT_AND_UFFD(guest_read64, 0, 0, uffd_data_handler, 2), + TEST_RO_MEMSLOT_AND_UFFD(guest_ld_preidx, 0, 0, uffd_data_handler, 2), + TEST_RO_MEMSLOT_AND_UFFD(guest_at, 0, 0, uffd_no_handler, 1), + TEST_RO_MEMSLOT_AND_UFFD(guest_exec, 0, 0, uffd_data_handler, 2), TEST_RO_MEMSLOT_AND_UFFD(guest_write64, mmio_on_test_gpa_handler, 1, - uffd_data_write_handler, 2), - TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas, - uffd_data_read_handler, 2), - TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva, - uffd_no_handler, 1), - TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx, - uffd_no_handler, 1), + uffd_data_handler, 2), + TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_cas, uffd_data_handler, 2), + TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_dc_zva, uffd_no_handler, 1), + TEST_RO_MEMSLOT_NO_SYNDROME_AND_UFFD(guest_st_preidx, uffd_no_handler, 1), { 0 } }; diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h index 9218bb5f44bf..fa65b908b13e 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h @@ -85,61 +85,110 @@ #define HV_X64_MSR_SYNDBG_OPTIONS 0x400000FF /* HYPERV_CPUID_FEATURES.EAX */ -#define HV_MSR_VP_RUNTIME_AVAILABLE BIT(0) -#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1) -#define HV_MSR_SYNIC_AVAILABLE BIT(2) -#define HV_MSR_SYNTIMER_AVAILABLE BIT(3) -#define HV_MSR_APIC_ACCESS_AVAILABLE BIT(4) -#define HV_MSR_HYPERCALL_AVAILABLE BIT(5) -#define HV_MSR_VP_INDEX_AVAILABLE BIT(6) -#define HV_MSR_RESET_AVAILABLE BIT(7) -#define HV_MSR_STAT_PAGES_AVAILABLE BIT(8) -#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9) -#define HV_MSR_GUEST_IDLE_AVAILABLE BIT(10) -#define HV_ACCESS_FREQUENCY_MSRS BIT(11) -#define HV_ACCESS_REENLIGHTENMENT BIT(13) -#define HV_ACCESS_TSC_INVARIANT BIT(15) +#define HV_MSR_VP_RUNTIME_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 0) +#define HV_MSR_TIME_REF_COUNT_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 1) +#define HV_MSR_SYNIC_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 2) +#define HV_MSR_SYNTIMER_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 3) +#define HV_MSR_APIC_ACCESS_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 4) +#define HV_MSR_HYPERCALL_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 5) +#define HV_MSR_VP_INDEX_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 6) +#define HV_MSR_RESET_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 7) +#define HV_MSR_STAT_PAGES_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 8) +#define HV_MSR_REFERENCE_TSC_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 9) +#define HV_MSR_GUEST_IDLE_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 10) +#define HV_ACCESS_FREQUENCY_MSRS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 11) +#define HV_ACCESS_REENLIGHTENMENT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 13) +#define HV_ACCESS_TSC_INVARIANT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EAX, 15) /* HYPERV_CPUID_FEATURES.EBX */ -#define HV_CREATE_PARTITIONS BIT(0) -#define HV_ACCESS_PARTITION_ID BIT(1) -#define HV_ACCESS_MEMORY_POOL BIT(2) -#define HV_ADJUST_MESSAGE_BUFFERS BIT(3) -#define HV_POST_MESSAGES BIT(4) -#define HV_SIGNAL_EVENTS BIT(5) -#define HV_CREATE_PORT BIT(6) -#define HV_CONNECT_PORT BIT(7) -#define HV_ACCESS_STATS BIT(8) -#define HV_DEBUGGING BIT(11) -#define HV_CPU_MANAGEMENT BIT(12) -#define HV_ISOLATION BIT(22) +#define HV_CREATE_PARTITIONS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 0) +#define HV_ACCESS_PARTITION_ID \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 1) +#define HV_ACCESS_MEMORY_POOL \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 2) +#define HV_ADJUST_MESSAGE_BUFFERS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 3) +#define HV_POST_MESSAGES \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 4) +#define HV_SIGNAL_EVENTS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 5) +#define HV_CREATE_PORT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 6) +#define HV_CONNECT_PORT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 7) +#define HV_ACCESS_STATS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 8) +#define HV_DEBUGGING \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 11) +#define HV_CPU_MANAGEMENT \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 12) +#define HV_ENABLE_EXTENDED_HYPERCALLS \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 20) +#define HV_ISOLATION \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EBX, 22) /* HYPERV_CPUID_FEATURES.EDX */ -#define HV_X64_MWAIT_AVAILABLE BIT(0) -#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) -#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) -#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) -#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4) -#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) -#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) -#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) -#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) -#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) +#define HV_X64_MWAIT_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 0) +#define HV_X64_GUEST_DEBUGGING_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 1) +#define HV_X64_PERF_MONITOR_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 2) +#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 3) +#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 4) +#define HV_X64_GUEST_IDLE_STATE_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 5) +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 8) +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 10) +#define HV_FEATURE_DEBUG_MSRS_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 11) +#define HV_STIMER_DIRECT_MODE_AVAILABLE \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_FEATURES, 0, EDX, 19) /* HYPERV_CPUID_ENLIGHTMENT_INFO.EAX */ -#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) -#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) -#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) -#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) -#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) -#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) -#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) -#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) -#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) -#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) +#define HV_X64_AS_SWITCH_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 0) +#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 1) +#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 2) +#define HV_X64_APIC_ACCESS_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 3) +#define HV_X64_SYSTEM_RESET_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 4) +#define HV_X64_RELAXED_TIMING_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 5) +#define HV_DEPRECATING_AEOI_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 9) +#define HV_X64_CLUSTER_IPI_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 10) +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 11) +#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EAX, 14) /* HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX */ -#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING BIT(1) +#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0, EAX, 1) /* Hypercalls */ #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE 0x0002 @@ -166,6 +215,9 @@ #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 +/* Extended hypercalls */ +#define HV_EXT_CALL_QUERY_CAPABILITIES 0x8001 + #define HV_FLUSH_ALL_PROCESSORS BIT(0) #define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1) #define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2) @@ -288,4 +340,7 @@ struct hyperv_test_pages { struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm, vm_vaddr_t *p_hv_pages_gva); +/* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ +#define HV_INVARIANT_TSC_EXPOSED BIT_ULL(0) + #endif /* !SELFTEST_KVM_HYPERV_H */ diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index b1a31de7108a..53ffa43c90db 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -19,6 +19,9 @@ #include "../kvm_util.h" +extern bool host_cpu_is_intel; +extern bool host_cpu_is_amd; + #define NMI_VECTOR 0x02 #define X86_EFLAGS_FIXED (1u << 1) @@ -137,6 +140,7 @@ struct kvm_x86_cpu_feature { #define X86_FEATURE_GBPAGES KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 26) #define X86_FEATURE_RDTSCP KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 27) #define X86_FEATURE_LM KVM_X86_CPU_FEATURE(0x80000001, 0, EDX, 29) +#define X86_FEATURE_INVTSC KVM_X86_CPU_FEATURE(0x80000007, 0, EDX, 8) #define X86_FEATURE_RDPRU KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 4) #define X86_FEATURE_AMD_IBPB KVM_X86_CPU_FEATURE(0x80000008, 0, EBX, 12) #define X86_FEATURE_NPT KVM_X86_CPU_FEATURE(0x8000000A, 0, EDX, 0) @@ -554,6 +558,28 @@ static inline uint32_t this_cpu_model(void) return x86_model(this_cpu_fms()); } +static inline bool this_cpu_vendor_string_is(const char *vendor) +{ + const uint32_t *chunk = (const uint32_t *)vendor; + uint32_t eax, ebx, ecx, edx; + + cpuid(0, &eax, &ebx, &ecx, &edx); + return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); +} + +static inline bool this_cpu_is_intel(void) +{ + return this_cpu_vendor_string_is("GenuineIntel"); +} + +/* + * Exclude early K5 samples with a vendor string of "AMDisbetter!" + */ +static inline bool this_cpu_is_amd(void) +{ + return this_cpu_vendor_string_is("AuthenticAMD"); +} + static inline uint32_t __this_cpu_has(uint32_t function, uint32_t index, uint8_t reg, uint8_t lo, uint8_t hi) { @@ -690,9 +716,6 @@ static inline void cpu_relax(void) "hlt\n" \ ) -bool is_intel_cpu(void); -bool is_amd_cpu(void); - struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu); void vcpu_load_state(struct kvm_vcpu *vcpu, struct kvm_x86_state *state); void kvm_x86_state_cleanup(struct kvm_x86_state *state); @@ -716,7 +739,7 @@ static inline void vcpu_msrs_set(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs) int r = __vcpu_ioctl(vcpu, KVM_SET_MSRS, msrs); TEST_ASSERT(r == msrs->nmsrs, - "KVM_GET_MSRS failed, r: %i (failed on MSR %x)", + "KVM_SET_MSRS failed, r: %i (failed on MSR %x)", r, r < 0 || r >= msrs->nmsrs ? -1 : msrs->entries[r].index); } static inline void vcpu_debugregs_get(struct kvm_vcpu *vcpu, diff --git a/tools/testing/selftests/kvm/kvm_binary_stats_test.c b/tools/testing/selftests/kvm/kvm_binary_stats_test.c index 0b45ac593387..a7001e29dc06 100644 --- a/tools/testing/selftests/kvm/kvm_binary_stats_test.c +++ b/tools/testing/selftests/kvm/kvm_binary_stats_test.c @@ -19,6 +19,7 @@ #include "kvm_util.h" #include "asm/kvm.h" #include "linux/kvm.h" +#include "kselftest.h" static void stats_test(int stats_fd) { @@ -51,7 +52,7 @@ static void stats_test(int stats_fd) /* Sanity check for other fields in header */ if (header.num_desc == 0) { - printf("No KVM stats defined!"); + ksft_print_msg("No KVM stats defined!\n"); return; } /* @@ -133,7 +134,7 @@ static void stats_test(int stats_fd) "Bucket size of stats (%s) is not zero", pdesc->name); } - size_data += pdesc->size * sizeof(*stats_data); + size_data = max(size_data, pdesc->offset + pdesc->size * sizeof(*stats_data)); } /* @@ -148,14 +149,6 @@ static void stats_test(int stats_fd) TEST_ASSERT(size_data >= header.num_desc * sizeof(*stats_data), "Data size is not correct"); - /* Check stats offset */ - for (i = 0; i < header.num_desc; ++i) { - pdesc = get_stats_descriptor(stats_desc, i, &header); - TEST_ASSERT(pdesc->offset < size_data, - "Invalid offset (%u) for stats: %s", - pdesc->offset, pdesc->name); - } - /* Allocate memory for stats data */ stats_data = malloc(size_data); TEST_ASSERT(stats_data, "Allocate memory for stats data"); @@ -224,9 +217,13 @@ int main(int argc, char *argv[]) max_vcpu = DEFAULT_NUM_VCPU; } + ksft_print_header(); + /* Check the extension for binary stats */ TEST_REQUIRE(kvm_has_cap(KVM_CAP_BINARY_STATS_FD)); + ksft_set_plan(max_vm); + /* Create VMs and VCPUs */ vms = malloc(sizeof(vms[0]) * max_vm); TEST_ASSERT(vms, "Allocate memory for storing VM pointers"); @@ -245,10 +242,12 @@ int main(int argc, char *argv[]) vm_stats_test(vms[i]); for (j = 0; j < max_vcpu; ++j) vcpu_stats_test(vcpus[i * max_vcpu + j]); + ksft_test_result_pass("vm%i\n", i); } for (i = 0; i < max_vm; ++i) kvm_vm_free(vms[i]); free(vms); - return 0; + + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c index 820ac2d08c98..266f3876e10a 100644 --- a/tools/testing/selftests/kvm/lib/elf.c +++ b/tools/testing/selftests/kvm/lib/elf.c @@ -90,6 +90,7 @@ static void elfhdr_get(const char *filename, Elf64_Ehdr *hdrp) " hdrp->e_shentsize: %x\n" " expected: %zx", hdrp->e_shentsize, sizeof(Elf64_Shdr)); + close(fd); } /* VM ELF Load @@ -190,4 +191,5 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename) phdr.p_filesz); } } + close(fd); } diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c index 99a575bbbc52..1df3ce4b16fd 100644 --- a/tools/testing/selftests/kvm/lib/guest_modes.c +++ b/tools/testing/selftests/kvm/lib/guest_modes.c @@ -127,7 +127,7 @@ void guest_modes_cmdline(const char *arg) mode_selected = true; } - mode = strtoul(optarg, NULL, 10); + mode = atoi_non_negative("Guest mode ID", arg); TEST_ASSERT(mode < NUM_VM_MODES, "Guest mode ID %d too big", mode); guest_modes[mode].enabled = true; } diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 56d5ea949cbb..3ea24a5f4c43 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1844,6 +1844,7 @@ static struct exit_reason { {KVM_EXIT_X86_RDMSR, "RDMSR"}, {KVM_EXIT_X86_WRMSR, "WRMSR"}, {KVM_EXIT_XEN, "XEN"}, + {KVM_EXIT_HYPERV, "HYPERV"}, #ifdef KVM_EXIT_MEMORY_NOT_PRESENT {KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"}, #endif @@ -1941,9 +1942,6 @@ vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm, vm_paddr_t paddr_min, return vm_phy_pages_alloc(vm, 1, paddr_min, memslot); } -/* Arbitrary minimum physical address used for virtual translation tables. */ -#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000 - vm_paddr_t vm_alloc_page_table(struct kvm_vm *vm) { return vm_phy_page_alloc(vm, KVM_GUEST_PAGE_TABLE_MIN_PADDR, diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c index acfa1d01e7df..ae1e573d94ce 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c @@ -19,6 +19,8 @@ #define MAX_NR_CPUID_ENTRIES 100 vm_vaddr_t exception_handlers; +bool host_cpu_is_amd; +bool host_cpu_is_intel; static void regs_dump(FILE *stream, struct kvm_regs *regs, uint8_t indent) { @@ -113,7 +115,7 @@ static void sregs_dump(FILE *stream, struct kvm_sregs *sregs, uint8_t indent) bool kvm_is_tdp_enabled(void) { - if (is_intel_cpu()) + if (host_cpu_is_intel) return get_kvm_intel_param_bool("ept"); else return get_kvm_amd_param_bool("npt"); @@ -555,6 +557,8 @@ static void vcpu_setup(struct kvm_vm *vm, struct kvm_vcpu *vcpu) void kvm_arch_vm_post_create(struct kvm_vm *vm) { vm_create_irqchip(vm); + sync_global_to_guest(vm, host_cpu_is_intel); + sync_global_to_guest(vm, host_cpu_is_amd); } struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id, @@ -1006,28 +1010,6 @@ void kvm_x86_state_cleanup(struct kvm_x86_state *state) free(state); } -static bool cpu_vendor_string_is(const char *vendor) -{ - const uint32_t *chunk = (const uint32_t *)vendor; - uint32_t eax, ebx, ecx, edx; - - cpuid(0, &eax, &ebx, &ecx, &edx); - return (ebx == chunk[0] && edx == chunk[1] && ecx == chunk[2]); -} - -bool is_intel_cpu(void) -{ - return cpu_vendor_string_is("GenuineIntel"); -} - -/* - * Exclude early K5 samples with a vendor string of "AMDisbetter!" - */ -bool is_amd_cpu(void) -{ - return cpu_vendor_string_is("AuthenticAMD"); -} - void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits) { if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) { @@ -1162,9 +1144,15 @@ uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2, { uint64_t r; - asm volatile("vmcall" + asm volatile("test %[use_vmmcall], %[use_vmmcall]\n\t" + "jnz 1f\n\t" + "vmcall\n\t" + "jmp 2f\n\t" + "1: vmmcall\n\t" + "2:" : "=a"(r) - : "a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3)); + : "a"(nr), "b"(a0), "c"(a1), "d"(a2), "S"(a3), + [use_vmmcall] "r" (host_cpu_is_amd)); return r; } @@ -1236,7 +1224,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm) max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1; /* Avoid reserved HyperTransport region on AMD processors. */ - if (!is_amd_cpu()) + if (!host_cpu_is_amd) return max_gfn; /* On parts with <40 physical address bits, the area is fully hidden */ @@ -1276,3 +1264,9 @@ bool vm_is_unrestricted_guest(struct kvm_vm *vm) return get_kvm_intel_param_bool("unrestricted_guest"); } + +void kvm_selftest_arch_init(void) +{ + host_cpu_is_intel = this_cpu_is_intel(); + host_cpu_is_amd = this_cpu_is_amd(); +} diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index e6587e193490..4210cd21d159 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -308,8 +308,6 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, data->hva_slots = malloc(sizeof(*data->hva_slots) * data->nslots); TEST_ASSERT(data->hva_slots, "malloc() fail"); - data->vm = __vm_create_with_one_vcpu(&data->vcpu, mempages, guest_code); - pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n", data->nslots, data->pages_per_slot, rempages); @@ -349,6 +347,7 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots, virt_map(data->vm, MEM_GPA, MEM_GPA, data->npages); sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); + sync->guest_page_size = data->vm->page_size; atomic_init(&sync->start_flag, false); atomic_init(&sync->exit_flag, false); atomic_init(&sync->sync_flag, false); @@ -810,8 +809,6 @@ static bool test_execute(int nslots, uint64_t *maxslots, } sync = (typeof(sync))vm_gpa2hva(data, MEM_SYNC_GPA, NULL); - - sync->guest_page_size = data->vm->page_size; if (tdata->prepare && !tdata->prepare(data, sync, maxslots)) { ret = false; diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c index 32f7e09ef67c..0f728f05ea82 100644 --- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c @@ -48,10 +48,10 @@ static void guest_main(void) const uint8_t *other_hypercall_insn; uint64_t ret; - if (is_intel_cpu()) { + if (host_cpu_is_intel) { native_hypercall_insn = vmx_vmcall; other_hypercall_insn = svm_vmmcall; - } else if (is_amd_cpu()) { + } else if (host_cpu_is_amd) { native_hypercall_insn = svm_vmmcall; other_hypercall_insn = vmx_vmcall; } else { diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c index d576bc8ce823..2ee0af0d449e 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c @@ -104,7 +104,7 @@ static void guest_main(struct ms_hyperv_tsc_page *tsc_page, vm_paddr_t tsc_page_ /* Set Guest OS id to enable Hyper-V emulation */ GUEST_SYNC(1); - wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48); + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); GUEST_SYNC(2); check_tsc_msr_rdtsc(); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c new file mode 100644 index 000000000000..73af44d2167f --- /dev/null +++ b/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Test Hyper-V extended hypercall, HV_EXT_CALL_QUERY_CAPABILITIES (0x8001), + * exit to userspace and receive result in guest. + * + * Negative tests are present in hyperv_features.c + * + * Copyright 2022 Google LLC + * Author: Vipin Sharma <vipinsh@google.com> + */ + +#include "kvm_util.h" +#include "processor.h" +#include "hyperv.h" + +/* Any value is fine */ +#define EXT_CAPABILITIES 0xbull + +static void guest_code(vm_paddr_t in_pg_gpa, vm_paddr_t out_pg_gpa, + vm_vaddr_t out_pg_gva) +{ + uint64_t *output_gva; + + wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID); + wrmsr(HV_X64_MSR_HYPERCALL, in_pg_gpa); + + output_gva = (uint64_t *)out_pg_gva; + + hyperv_hypercall(HV_EXT_CALL_QUERY_CAPABILITIES, in_pg_gpa, out_pg_gpa); + + /* TLFS states output will be a uint64_t value */ + GUEST_ASSERT_EQ(*output_gva, EXT_CAPABILITIES); + + GUEST_DONE(); +} + +int main(void) +{ + vm_vaddr_t hcall_out_page; + vm_vaddr_t hcall_in_page; + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + uint64_t *outval; + struct ucall uc; + + /* Verify if extended hypercalls are supported */ + if (!kvm_cpuid_has(kvm_get_supported_hv_cpuid(), + HV_ENABLE_EXTENDED_HYPERCALLS)) { + print_skip("Extended calls not supported by the kernel"); + exit(KSFT_SKIP); + } + + vm = vm_create_with_one_vcpu(&vcpu, guest_code); + run = vcpu->run; + vcpu_set_hv_cpuid(vcpu); + + /* Hypercall input */ + hcall_in_page = vm_vaddr_alloc_pages(vm, 1); + memset(addr_gva2hva(vm, hcall_in_page), 0x0, vm->page_size); + + /* Hypercall output */ + hcall_out_page = vm_vaddr_alloc_pages(vm, 1); + memset(addr_gva2hva(vm, hcall_out_page), 0x0, vm->page_size); + + vcpu_args_set(vcpu, 3, addr_gva2gpa(vm, hcall_in_page), + addr_gva2gpa(vm, hcall_out_page), hcall_out_page); + + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_HYPERV, + "Unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + outval = addr_gpa2hva(vm, run->hyperv.u.hcall.params[1]); + *outval = EXT_CAPABILITIES; + run->hyperv.u.hcall.result = HV_STATUS_SUCCESS; + + vcpu_run(vcpu); + + TEST_ASSERT(run->exit_reason == KVM_EXIT_IO, + "Unexpected exit reason: %u (%s)", + run->exit_reason, exit_reason_str(run->exit_reason)); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT_2(uc, "arg1 = %ld, arg2 = %ld"); + break; + case UCALL_DONE: + break; + default: + TEST_FAIL("Unhandled ucall: %ld", uc.cmd); + } + + kvm_vm_free(vm); + return 0; +} diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c index 3163c3e8db0a..c5e3b39edd07 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c @@ -13,9 +13,17 @@ #include "processor.h" #include "hyperv.h" +/* + * HYPERV_CPUID_ENLIGHTMENT_INFO.EBX is not a 'feature' CPUID leaf + * but to activate the feature it is sufficient to set it to a non-zero + * value. Use BIT(0) for that. + */ +#define HV_PV_SPINLOCKS_TEST \ + KVM_X86_CPU_FEATURE(HYPERV_CPUID_ENLIGHTMENT_INFO, 0, EBX, 0) + struct msr_data { uint32_t idx; - bool available; + bool fault_expected; bool write; u64 write_val; }; @@ -26,22 +34,46 @@ struct hcall_data { bool ud_expected; }; +static bool is_write_only_msr(uint32_t msr) +{ + return msr == HV_X64_MSR_EOI; +} + static void guest_msr(struct msr_data *msr) { - uint64_t ignored; - uint8_t vector; + uint8_t vector = 0; + uint64_t msr_val = 0; GUEST_ASSERT(msr->idx); - if (!msr->write) - vector = rdmsr_safe(msr->idx, &ignored); - else + if (msr->write) vector = wrmsr_safe(msr->idx, msr->write_val); - if (msr->available) - GUEST_ASSERT_2(!vector, msr->idx, vector); + if (!vector && (!msr->write || !is_write_only_msr(msr->idx))) + vector = rdmsr_safe(msr->idx, &msr_val); + + if (msr->fault_expected) + GUEST_ASSERT_3(vector == GP_VECTOR, msr->idx, vector, GP_VECTOR); else - GUEST_ASSERT_2(vector == GP_VECTOR, msr->idx, vector); + GUEST_ASSERT_3(!vector, msr->idx, vector, 0); + + if (vector || is_write_only_msr(msr->idx)) + goto done; + + if (msr->write) + GUEST_ASSERT_3(msr_val == msr->write_val, msr->idx, + msr_val, msr->write_val); + + /* Invariant TSC bit appears when TSC invariant control MSR is written to */ + if (msr->idx == HV_X64_MSR_TSC_INVARIANT_CONTROL) { + if (!this_cpu_has(HV_ACCESS_TSC_INVARIANT)) + GUEST_ASSERT(this_cpu_has(X86_FEATURE_INVTSC)); + else + GUEST_ASSERT(this_cpu_has(X86_FEATURE_INVTSC) == + !!(msr_val & HV_INVARIANT_TSC_EXPOSED)); + } + +done: GUEST_DONE(); } @@ -89,7 +121,6 @@ static void vcpu_reset_hv_cpuid(struct kvm_vcpu *vcpu) static void guest_test_msrs_access(void) { struct kvm_cpuid2 *prev_cpuid = NULL; - struct kvm_cpuid_entry2 *feat, *dbg; struct kvm_vcpu *vcpu; struct kvm_run *run; struct kvm_vm *vm; @@ -97,6 +128,7 @@ static void guest_test_msrs_access(void) int stage = 0; vm_vaddr_t msr_gva; struct msr_data *msr; + bool has_invtsc = kvm_cpu_has(X86_FEATURE_INVTSC); while (true) { vm = vm_create_with_one_vcpu(&vcpu, guest_msr); @@ -116,9 +148,6 @@ static void guest_test_msrs_access(void) vcpu_init_cpuid(vcpu, prev_cpuid); } - feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); - dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); - vm_init_descriptor_tables(vm); vcpu_init_descriptor_tables(vcpu); @@ -134,133 +163,139 @@ static void guest_test_msrs_access(void) * Only available when Hyper-V identification is set */ msr->idx = HV_X64_MSR_GUEST_OS_ID; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 1: msr->idx = HV_X64_MSR_HYPERCALL; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 2: - feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_HYPERCALL_AVAILABLE); /* * HV_X64_MSR_GUEST_OS_ID has to be written first to make * HV_X64_MSR_HYPERCALL available. */ msr->idx = HV_X64_MSR_GUEST_OS_ID; - msr->write = 1; + msr->write = true; msr->write_val = HYPERV_LINUX_OS_ID; - msr->available = 1; + msr->fault_expected = false; break; case 3: msr->idx = HV_X64_MSR_GUEST_OS_ID; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 4: msr->idx = HV_X64_MSR_HYPERCALL; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 5: msr->idx = HV_X64_MSR_VP_RUNTIME; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 6: - feat->eax |= HV_MSR_VP_RUNTIME_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_VP_RUNTIME_AVAILABLE); msr->idx = HV_X64_MSR_VP_RUNTIME; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 7: /* Read only */ msr->idx = HV_X64_MSR_VP_RUNTIME; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 8: msr->idx = HV_X64_MSR_TIME_REF_COUNT; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 9: - feat->eax |= HV_MSR_TIME_REF_COUNT_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_TIME_REF_COUNT_AVAILABLE); msr->idx = HV_X64_MSR_TIME_REF_COUNT; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 10: /* Read only */ msr->idx = HV_X64_MSR_TIME_REF_COUNT; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 11: msr->idx = HV_X64_MSR_VP_INDEX; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 12: - feat->eax |= HV_MSR_VP_INDEX_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_VP_INDEX_AVAILABLE); msr->idx = HV_X64_MSR_VP_INDEX; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 13: /* Read only */ msr->idx = HV_X64_MSR_VP_INDEX; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 14: msr->idx = HV_X64_MSR_RESET; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 15: - feat->eax |= HV_MSR_RESET_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_RESET_AVAILABLE); msr->idx = HV_X64_MSR_RESET; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 16: msr->idx = HV_X64_MSR_RESET; - msr->write = 1; + msr->write = true; + /* + * TODO: the test only writes '0' to HV_X64_MSR_RESET + * at the moment, writing some other value there will + * trigger real vCPU reset and the code is not prepared + * to handle it yet. + */ msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 17: msr->idx = HV_X64_MSR_REFERENCE_TSC; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 18: - feat->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_REFERENCE_TSC_AVAILABLE); msr->idx = HV_X64_MSR_REFERENCE_TSC; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 19: msr->idx = HV_X64_MSR_REFERENCE_TSC; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 20: msr->idx = HV_X64_MSR_EOM; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 21: /* @@ -268,149 +303,185 @@ static void guest_test_msrs_access(void) * capability enabled and guest visible CPUID bit unset. */ msr->idx = HV_X64_MSR_EOM; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 22: - feat->eax |= HV_MSR_SYNIC_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_SYNIC_AVAILABLE); msr->idx = HV_X64_MSR_EOM; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 23: msr->idx = HV_X64_MSR_EOM; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 24: msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 25: - feat->eax |= HV_MSR_SYNTIMER_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_SYNTIMER_AVAILABLE); msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 26: msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 27: /* Direct mode test */ msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 1; + msr->write = true; msr->write_val = 1 << 12; - msr->available = 0; + msr->fault_expected = true; break; case 28: - feat->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_STIMER_DIRECT_MODE_AVAILABLE); msr->idx = HV_X64_MSR_STIMER0_CONFIG; - msr->write = 1; + msr->write = true; msr->write_val = 1 << 12; - msr->available = 1; + msr->fault_expected = false; break; case 29: msr->idx = HV_X64_MSR_EOI; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 30: - feat->eax |= HV_MSR_APIC_ACCESS_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_APIC_ACCESS_AVAILABLE); msr->idx = HV_X64_MSR_EOI; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 1; + msr->fault_expected = false; break; case 31: msr->idx = HV_X64_MSR_TSC_FREQUENCY; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 32: - feat->eax |= HV_ACCESS_FREQUENCY_MSRS; + vcpu_set_cpuid_feature(vcpu, HV_ACCESS_FREQUENCY_MSRS); msr->idx = HV_X64_MSR_TSC_FREQUENCY; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 33: /* Read only */ msr->idx = HV_X64_MSR_TSC_FREQUENCY; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 34: msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 35: - feat->eax |= HV_ACCESS_REENLIGHTENMENT; + vcpu_set_cpuid_feature(vcpu, HV_ACCESS_REENLIGHTENMENT); msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 36: msr->idx = HV_X64_MSR_REENLIGHTENMENT_CONTROL; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 1; + msr->fault_expected = false; break; case 37: /* Can only write '0' */ msr->idx = HV_X64_MSR_TSC_EMULATION_STATUS; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 0; + msr->fault_expected = true; break; case 38: msr->idx = HV_X64_MSR_CRASH_P0; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 39: - feat->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE); msr->idx = HV_X64_MSR_CRASH_P0; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 40: msr->idx = HV_X64_MSR_CRASH_P0; - msr->write = 1; + msr->write = true; msr->write_val = 1; - msr->available = 1; + msr->fault_expected = false; break; case 41: msr->idx = HV_X64_MSR_SYNDBG_STATUS; - msr->write = 0; - msr->available = 0; + msr->write = false; + msr->fault_expected = true; break; case 42: - feat->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; - dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + vcpu_set_cpuid_feature(vcpu, HV_FEATURE_DEBUG_MSRS_AVAILABLE); + vcpu_set_cpuid_feature(vcpu, HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING); msr->idx = HV_X64_MSR_SYNDBG_STATUS; - msr->write = 0; - msr->available = 1; + msr->write = false; + msr->fault_expected = false; break; case 43: msr->idx = HV_X64_MSR_SYNDBG_STATUS; - msr->write = 1; + msr->write = true; msr->write_val = 0; - msr->available = 1; + msr->fault_expected = false; break; case 44: + /* MSR is not available when CPUID feature bit is unset */ + if (!has_invtsc) + continue; + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = false; + msr->fault_expected = true; + break; + case 45: + /* MSR is vailable when CPUID feature bit is set */ + if (!has_invtsc) + continue; + vcpu_set_cpuid_feature(vcpu, HV_ACCESS_TSC_INVARIANT); + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = false; + msr->fault_expected = false; + break; + case 46: + /* Writing bits other than 0 is forbidden */ + if (!has_invtsc) + continue; + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = true; + msr->write_val = 0xdeadbeef; + msr->fault_expected = true; + break; + case 47: + /* Setting bit 0 enables the feature */ + if (!has_invtsc) + continue; + msr->idx = HV_X64_MSR_TSC_INVARIANT_CONTROL; + msr->write = true; + msr->write_val = 1; + msr->fault_expected = false; + break; + + default: kvm_vm_free(vm); return; } @@ -429,7 +500,7 @@ static void guest_test_msrs_access(void) switch (get_ucall(vcpu, &uc)) { case UCALL_ABORT: - REPORT_GUEST_ASSERT_2(uc, "MSR = %lx, vector = %lx"); + REPORT_GUEST_ASSERT_3(uc, "MSR = %lx, arg1 = %lx, arg2 = %lx"); return; case UCALL_DONE: break; @@ -445,7 +516,6 @@ static void guest_test_msrs_access(void) static void guest_test_hcalls_access(void) { - struct kvm_cpuid_entry2 *feat, *recomm, *dbg; struct kvm_cpuid2 *prev_cpuid = NULL; struct kvm_vcpu *vcpu; struct kvm_run *run; @@ -480,15 +550,11 @@ static void guest_test_hcalls_access(void) vcpu_init_cpuid(vcpu, prev_cpuid); } - feat = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); - recomm = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); - dbg = vcpu_get_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); - run = vcpu->run; switch (stage) { case 0: - feat->eax |= HV_MSR_HYPERCALL_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_MSR_HYPERCALL_AVAILABLE); hcall->control = 0xbeef; hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; @@ -498,7 +564,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 2: - feat->ebx |= HV_POST_MESSAGES; + vcpu_set_cpuid_feature(vcpu, HV_POST_MESSAGES); hcall->control = HVCALL_POST_MESSAGE; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -508,7 +574,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 4: - feat->ebx |= HV_SIGNAL_EVENTS; + vcpu_set_cpuid_feature(vcpu, HV_SIGNAL_EVENTS); hcall->control = HVCALL_SIGNAL_EVENT; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -518,12 +584,12 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_INVALID_HYPERCALL_CODE; break; case 6: - dbg->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING; + vcpu_set_cpuid_feature(vcpu, HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING); hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 7: - feat->ebx |= HV_DEBUGGING; + vcpu_set_cpuid_feature(vcpu, HV_DEBUGGING); hcall->control = HVCALL_RESET_DEBUG_SESSION; hcall->expect = HV_STATUS_OPERATION_DENIED; break; @@ -533,7 +599,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 9: - recomm->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED; + vcpu_set_cpuid_feature(vcpu, HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED); hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE; hcall->expect = HV_STATUS_SUCCESS; break; @@ -542,7 +608,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 11: - recomm->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED; + vcpu_set_cpuid_feature(vcpu, HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED); hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX; hcall->expect = HV_STATUS_SUCCESS; break; @@ -552,7 +618,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 13: - recomm->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED; + vcpu_set_cpuid_feature(vcpu, HV_X64_CLUSTER_IPI_RECOMMENDED); hcall->control = HVCALL_SEND_IPI; hcall->expect = HV_STATUS_INVALID_HYPERCALL_INPUT; break; @@ -567,7 +633,7 @@ static void guest_test_hcalls_access(void) hcall->expect = HV_STATUS_ACCESS_DENIED; break; case 16: - recomm->ebx = 0xfff; + vcpu_set_cpuid_feature(vcpu, HV_PV_SPINLOCKS_TEST); hcall->control = HVCALL_NOTIFY_LONG_SPIN_WAIT; hcall->expect = HV_STATUS_SUCCESS; break; @@ -577,12 +643,21 @@ static void guest_test_hcalls_access(void) hcall->ud_expected = true; break; case 18: - feat->edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE; + vcpu_set_cpuid_feature(vcpu, HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE); hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT; hcall->ud_expected = false; hcall->expect = HV_STATUS_SUCCESS; break; case 19: + hcall->control = HV_EXT_CALL_QUERY_CAPABILITIES; + hcall->expect = HV_STATUS_ACCESS_DENIED; + break; + case 20: + vcpu_set_cpuid_feature(vcpu, HV_ENABLE_EXTENDED_HYPERCALLS); + hcall->control = HV_EXT_CALL_QUERY_CAPABILITIES | HV_HYPERCALL_FAST_BIT; + hcall->expect = HV_STATUS_INVALID_PARAMETER; + break; + case 21: kvm_vm_free(vm); return; } diff --git a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c index fb02581953a3..ce1ccc4c1503 100644 --- a/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c +++ b/tools/testing/selftests/kvm/x86_64/mmio_warning_test.c @@ -93,7 +93,7 @@ int main(void) { int warnings_before, warnings_after; - TEST_REQUIRE(is_intel_cpu()); + TEST_REQUIRE(host_cpu_is_intel); TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c index ea0978f22db8..251794f83719 100644 --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c @@ -241,7 +241,7 @@ int main(int argc, char **argv) while ((opt = getopt(argc, argv, "hp:t:r")) != -1) { switch (opt) { case 'p': - reclaim_period_ms = atoi_non_negative("Reclaim period", optarg); + reclaim_period_ms = atoi_positive("Reclaim period", optarg); break; case 't': token = atoi_paranoid(optarg); diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c index 2de98fce7edd..bad7ef8c5b92 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c @@ -198,14 +198,15 @@ static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents) static struct kvm_pmu_event_filter * -create_pmu_event_filter(const uint64_t event_list[], - int nevents, uint32_t action) +create_pmu_event_filter(const uint64_t event_list[], int nevents, + uint32_t action, uint32_t flags) { struct kvm_pmu_event_filter *f; int i; f = alloc_pmu_event_filter(nevents); f->action = action; + f->flags = flags; for (i = 0; i < nevents; i++) f->events[i] = event_list[i]; @@ -216,7 +217,7 @@ static struct kvm_pmu_event_filter *event_filter(uint32_t action) { return create_pmu_event_filter(event_list, ARRAY_SIZE(event_list), - action); + action, 0); } /* @@ -263,7 +264,7 @@ static void test_amd_deny_list(struct kvm_vcpu *vcpu) struct kvm_pmu_event_filter *f; uint64_t count; - f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY); + f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY, 0); count = test_with_filter(vcpu, f); free(f); @@ -363,7 +364,7 @@ static void test_pmu_config_disable(void (*guest_code)(void)) */ static bool use_intel_pmu(void) { - return is_intel_cpu() && + return host_cpu_is_intel && kvm_cpu_property(X86_PROPERTY_PMU_VERSION) && kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS) && kvm_pmu_has(X86_PMU_FEATURE_BRANCH_INSNS_RETIRED); @@ -397,19 +398,378 @@ static bool use_amd_pmu(void) uint32_t family = kvm_cpu_family(); uint32_t model = kvm_cpu_model(); - return is_amd_cpu() && + return host_cpu_is_amd && (is_zen1(family, model) || is_zen2(family, model) || is_zen3(family, model)); } +/* + * "MEM_INST_RETIRED.ALL_LOADS", "MEM_INST_RETIRED.ALL_STORES", and + * "MEM_INST_RETIRED.ANY" from https://perfmon-events.intel.com/ + * supported on Intel Xeon processors: + * - Sapphire Rapids, Ice Lake, Cascade Lake, Skylake. + */ +#define MEM_INST_RETIRED 0xD0 +#define MEM_INST_RETIRED_LOAD EVENT(MEM_INST_RETIRED, 0x81) +#define MEM_INST_RETIRED_STORE EVENT(MEM_INST_RETIRED, 0x82) +#define MEM_INST_RETIRED_LOAD_STORE EVENT(MEM_INST_RETIRED, 0x83) + +static bool supports_event_mem_inst_retired(void) +{ + uint32_t eax, ebx, ecx, edx; + + cpuid(1, &eax, &ebx, &ecx, &edx); + if (x86_family(eax) == 0x6) { + switch (x86_model(eax)) { + /* Sapphire Rapids */ + case 0x8F: + /* Ice Lake */ + case 0x6A: + /* Skylake */ + /* Cascade Lake */ + case 0x55: + return true; + } + } + + return false; +} + +/* + * "LS Dispatch", from Processor Programming Reference + * (PPR) for AMD Family 17h Model 01h, Revision B1 Processors, + * Preliminary Processor Programming Reference (PPR) for AMD Family + * 17h Model 31h, Revision B0 Processors, and Preliminary Processor + * Programming Reference (PPR) for AMD Family 19h Model 01h, Revision + * B1 Processors Volume 1 of 2. + */ +#define LS_DISPATCH 0x29 +#define LS_DISPATCH_LOAD EVENT(LS_DISPATCH, BIT(0)) +#define LS_DISPATCH_STORE EVENT(LS_DISPATCH, BIT(1)) +#define LS_DISPATCH_LOAD_STORE EVENT(LS_DISPATCH, BIT(2)) + +#define INCLUDE_MASKED_ENTRY(event_select, mask, match) \ + KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, false) +#define EXCLUDE_MASKED_ENTRY(event_select, mask, match) \ + KVM_PMU_ENCODE_MASKED_ENTRY(event_select, mask, match, true) + +struct perf_counter { + union { + uint64_t raw; + struct { + uint64_t loads:22; + uint64_t stores:22; + uint64_t loads_stores:20; + }; + }; +}; + +static uint64_t masked_events_guest_test(uint32_t msr_base) +{ + uint64_t ld0, ld1, st0, st1, ls0, ls1; + struct perf_counter c; + int val; + + /* + * The acutal value of the counters don't determine the outcome of + * the test. Only that they are zero or non-zero. + */ + ld0 = rdmsr(msr_base + 0); + st0 = rdmsr(msr_base + 1); + ls0 = rdmsr(msr_base + 2); + + __asm__ __volatile__("movl $0, %[v];" + "movl %[v], %%eax;" + "incl %[v];" + : [v]"+m"(val) :: "eax"); + + ld1 = rdmsr(msr_base + 0); + st1 = rdmsr(msr_base + 1); + ls1 = rdmsr(msr_base + 2); + + c.loads = ld1 - ld0; + c.stores = st1 - st0; + c.loads_stores = ls1 - ls0; + + return c.raw; +} + +static void intel_masked_events_guest_code(void) +{ + uint64_t r; + + for (;;) { + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + + wrmsr(MSR_P6_EVNTSEL0 + 0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | MEM_INST_RETIRED_LOAD); + wrmsr(MSR_P6_EVNTSEL0 + 1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | MEM_INST_RETIRED_STORE); + wrmsr(MSR_P6_EVNTSEL0 + 2, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | MEM_INST_RETIRED_LOAD_STORE); + + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0x7); + + r = masked_events_guest_test(MSR_IA32_PMC0); + + GUEST_SYNC(r); + } +} + +static void amd_masked_events_guest_code(void) +{ + uint64_t r; + + for (;;) { + wrmsr(MSR_K7_EVNTSEL0, 0); + wrmsr(MSR_K7_EVNTSEL1, 0); + wrmsr(MSR_K7_EVNTSEL2, 0); + + wrmsr(MSR_K7_EVNTSEL0, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_LOAD); + wrmsr(MSR_K7_EVNTSEL1, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_STORE); + wrmsr(MSR_K7_EVNTSEL2, ARCH_PERFMON_EVENTSEL_ENABLE | + ARCH_PERFMON_EVENTSEL_OS | LS_DISPATCH_LOAD_STORE); + + r = masked_events_guest_test(MSR_K7_PERFCTR0); + + GUEST_SYNC(r); + } +} + +static struct perf_counter run_masked_events_test(struct kvm_vcpu *vcpu, + const uint64_t masked_events[], + const int nmasked_events) +{ + struct kvm_pmu_event_filter *f; + struct perf_counter r; + + f = create_pmu_event_filter(masked_events, nmasked_events, + KVM_PMU_EVENT_ALLOW, + KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + r.raw = test_with_filter(vcpu, f); + free(f); + + return r; +} + +/* Matches KVM_PMU_EVENT_FILTER_MAX_EVENTS in pmu.c */ +#define MAX_FILTER_EVENTS 300 +#define MAX_TEST_EVENTS 10 + +#define ALLOW_LOADS BIT(0) +#define ALLOW_STORES BIT(1) +#define ALLOW_LOADS_STORES BIT(2) + +struct masked_events_test { + uint64_t intel_events[MAX_TEST_EVENTS]; + uint64_t intel_event_end; + uint64_t amd_events[MAX_TEST_EVENTS]; + uint64_t amd_event_end; + const char *msg; + uint32_t flags; +}; + +/* + * These are the test cases for the masked events tests. + * + * For each test, the guest enables 3 PMU counters (loads, stores, + * loads + stores). The filter is then set in KVM with the masked events + * provided. The test then verifies that the counters agree with which + * ones should be counting and which ones should be filtered. + */ +const struct masked_events_test test_cases[] = { + { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x81), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(0)), + }, + .msg = "Only allow loads.", + .flags = ALLOW_LOADS, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x82), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(1)), + }, + .msg = "Only allow stores.", + .flags = ALLOW_STORES, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x83), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(2)), + }, + .msg = "Only allow loads + stores.", + .flags = ALLOW_LOADS_STORES, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0x7C, 0), + EXCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x83), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, ~(BIT(0) | BIT(1)), 0), + }, + .msg = "Only allow loads and stores.", + .flags = ALLOW_LOADS | ALLOW_STORES, + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0x7C, 0), + EXCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFF, 0x82), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xF8, 0), + EXCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(1)), + }, + .msg = "Only allow loads and loads + stores.", + .flags = ALLOW_LOADS | ALLOW_LOADS_STORES + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0xFE, 0x82), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xF8, 0), + EXCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xFF, BIT(0)), + }, + .msg = "Only allow stores and loads + stores.", + .flags = ALLOW_STORES | ALLOW_LOADS_STORES + }, { + .intel_events = { + INCLUDE_MASKED_ENTRY(MEM_INST_RETIRED, 0x7C, 0), + }, + .amd_events = { + INCLUDE_MASKED_ENTRY(LS_DISPATCH, 0xF8, 0), + }, + .msg = "Only allow loads, stores, and loads + stores.", + .flags = ALLOW_LOADS | ALLOW_STORES | ALLOW_LOADS_STORES + }, +}; + +static int append_test_events(const struct masked_events_test *test, + uint64_t *events, int nevents) +{ + const uint64_t *evts; + int i; + + evts = use_intel_pmu() ? test->intel_events : test->amd_events; + for (i = 0; i < MAX_TEST_EVENTS; i++) { + if (evts[i] == 0) + break; + + events[nevents + i] = evts[i]; + } + + return nevents + i; +} + +static bool bool_eq(bool a, bool b) +{ + return a == b; +} + +static void run_masked_events_tests(struct kvm_vcpu *vcpu, uint64_t *events, + int nevents) +{ + int ntests = ARRAY_SIZE(test_cases); + struct perf_counter c; + int i, n; + + for (i = 0; i < ntests; i++) { + const struct masked_events_test *test = &test_cases[i]; + + /* Do any test case events overflow MAX_TEST_EVENTS? */ + assert(test->intel_event_end == 0); + assert(test->amd_event_end == 0); + + n = append_test_events(test, events, nevents); + + c = run_masked_events_test(vcpu, events, n); + TEST_ASSERT(bool_eq(c.loads, test->flags & ALLOW_LOADS) && + bool_eq(c.stores, test->flags & ALLOW_STORES) && + bool_eq(c.loads_stores, + test->flags & ALLOW_LOADS_STORES), + "%s loads: %u, stores: %u, loads + stores: %u", + test->msg, c.loads, c.stores, c.loads_stores); + } +} + +static void add_dummy_events(uint64_t *events, int nevents) +{ + int i; + + for (i = 0; i < nevents; i++) { + int event_select = i % 0xFF; + bool exclude = ((i % 4) == 0); + + if (event_select == MEM_INST_RETIRED || + event_select == LS_DISPATCH) + event_select++; + + events[i] = KVM_PMU_ENCODE_MASKED_ENTRY(event_select, 0, + 0, exclude); + } +} + +static void test_masked_events(struct kvm_vcpu *vcpu) +{ + int nevents = MAX_FILTER_EVENTS - MAX_TEST_EVENTS; + uint64_t events[MAX_FILTER_EVENTS]; + + /* Run the test cases against a sparse PMU event filter. */ + run_masked_events_tests(vcpu, events, 0); + + /* Run the test cases against a dense PMU event filter. */ + add_dummy_events(events, MAX_FILTER_EVENTS); + run_masked_events_tests(vcpu, events, nevents); +} + +static int run_filter_test(struct kvm_vcpu *vcpu, const uint64_t *events, + int nevents, uint32_t flags) +{ + struct kvm_pmu_event_filter *f; + int r; + + f = create_pmu_event_filter(events, nevents, KVM_PMU_EVENT_ALLOW, flags); + r = __vm_ioctl(vcpu->vm, KVM_SET_PMU_EVENT_FILTER, f); + free(f); + + return r; +} + +static void test_filter_ioctl(struct kvm_vcpu *vcpu) +{ + uint64_t e = ~0ul; + int r; + + /* + * Unfortunately having invalid bits set in event data is expected to + * pass when flags == 0 (bits other than eventsel+umask). + */ + r = run_filter_test(vcpu, &e, 1, 0); + TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing"); + + r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + TEST_ASSERT(r != 0, "Invalid PMU Event Filter is expected to fail"); + + e = KVM_PMU_ENCODE_MASKED_ENTRY(0xff, 0xff, 0xff, 0xf); + r = run_filter_test(vcpu, &e, 1, KVM_PMU_EVENT_FLAG_MASKED_EVENTS); + TEST_ASSERT(r == 0, "Valid PMU Event Filter is failing"); +} + int main(int argc, char *argv[]) { void (*guest_code)(void); - struct kvm_vcpu *vcpu; + struct kvm_vcpu *vcpu, *vcpu2 = NULL; struct kvm_vm *vm; TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER)); + TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_MASKED_EVENTS)); TEST_REQUIRE(use_intel_pmu() || use_amd_pmu()); guest_code = use_intel_pmu() ? intel_guest_code : amd_guest_code; @@ -430,6 +790,17 @@ int main(int argc, char *argv[]) test_not_member_deny_list(vcpu); test_not_member_allow_list(vcpu); + if (use_intel_pmu() && + supports_event_mem_inst_retired() && + kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS) >= 3) + vcpu2 = vm_vcpu_add(vm, 2, intel_masked_events_guest_code); + else if (use_amd_pmu()) + vcpu2 = vm_vcpu_add(vm, 2, amd_masked_events_guest_code); + + if (vcpu2) + test_masked_events(vcpu2); + test_filter_ioctl(vcpu); + kvm_vm_free(vm); test_pmu_config_disable(guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c index 22d366c697f7..c9f67702f657 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c @@ -72,11 +72,16 @@ static void run_vcpu(struct kvm_vcpu *vcpu, int stage) switch (get_ucall(vcpu, &uc)) { case UCALL_SYNC: - TEST_ASSERT(!strcmp((const char *)uc.args[0], "hello") && - uc.args[1] == stage + 1, "Stage %d: Unexpected register values vmexit, got %lx", - stage + 1, (ulong)uc.args[1]); + if (!strcmp((const char *)uc.args[0], "hello") && + uc.args[1] == stage + 1) + ksft_test_result_pass("stage %d passed\n", stage + 1); + else + ksft_test_result_fail( + "stage %d: Unexpected register values vmexit, got %lx", + stage + 1, (ulong)uc.args[1]); return; case UCALL_DONE: + ksft_test_result_pass("stage %d passed\n", stage + 1); return; case UCALL_ABORT: REPORT_GUEST_ASSERT_2(uc, "values: %#lx, %#lx"); @@ -92,6 +97,9 @@ int main(void) struct kvm_vm *vm; uint64_t val; + ksft_print_header(); + ksft_set_plan(5); + vm = vm_create_with_one_vcpu(&vcpu, guest_code); val = 0; @@ -149,5 +157,5 @@ int main(void) kvm_vm_free(vm); - return 0; + ksft_finished(); /* Print results and exit() accordingly */ } diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c index 2641b286b4ed..ccdfa5dc1a4d 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c @@ -111,7 +111,7 @@ int main(int argc, char *argv[]) struct kvm_vcpu *vcpu; struct kvm_vm *vm; - TEST_REQUIRE(is_intel_cpu()); + TEST_REQUIRE(host_cpu_is_intel); TEST_REQUIRE(!vm_is_unrestricted_guest(NULL)); vm = vm_create_with_one_vcpu(&vcpu, guest_code); diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index dae510c263b4..5a3bf8f61417 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -19,9 +19,6 @@ #include <sys/eventfd.h> -/* Defined in include/linux/kvm_types.h */ -#define GPA_INVALID (~(ulong)0) - #define SHINFO_REGION_GVA 0xc0000000ULL #define SHINFO_REGION_GPA 0xc0000000ULL #define SHINFO_REGION_SLOT 10 @@ -412,21 +409,21 @@ static void *juggle_shinfo_state(void *arg) { struct kvm_vm *vm = (struct kvm_vm *)arg; - struct kvm_xen_hvm_attr cache_init = { + struct kvm_xen_hvm_attr cache_activate = { .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE }; - struct kvm_xen_hvm_attr cache_destroy = { + struct kvm_xen_hvm_attr cache_deactivate = { .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, - .u.shared_info.gfn = GPA_INVALID + .u.shared_info.gfn = KVM_XEN_INVALID_GFN }; for (;;) { - __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_init); - __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_destroy); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_activate); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_deactivate); pthread_testcancel(); - }; + } return NULL; } @@ -434,6 +431,7 @@ static void *juggle_shinfo_state(void *arg) int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; + struct kvm_xen_hvm_attr evt_reset; struct kvm_vm *vm; pthread_t thread; bool verbose; @@ -962,10 +960,8 @@ int main(int argc, char *argv[]) } done: - struct kvm_xen_hvm_attr evt_reset = { - .type = KVM_XEN_ATTR_TYPE_EVTCHN, - .u.evtchn.flags = KVM_XEN_EVTCHN_RESET, - }; + evt_reset.type = KVM_XEN_ATTR_TYPE_EVTCHN; + evt_reset.u.evtchn.flags = KVM_XEN_EVTCHN_RESET; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &evt_reset); alarm(0); diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 291144c284fb..f7900e75d230 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -20,7 +20,7 @@ CLANG_TARGET_FLAGS := $(CLANG_TARGET_FLAGS_$(ARCH)) ifeq ($(CROSS_COMPILE),) ifeq ($(CLANG_TARGET_FLAGS),) -$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk +$(error Specify CROSS_COMPILE or add '--target=' option to lib.mk) else CLANG_FLAGS += --target=$(CLANG_TARGET_FLAGS) endif # CLANG_TARGET_FLAGS diff --git a/tools/testing/selftests/net/af_unix/test_unix_oob.c b/tools/testing/selftests/net/af_unix/test_unix_oob.c index b57e91e1c3f2..532459a15067 100644 --- a/tools/testing/selftests/net/af_unix/test_unix_oob.c +++ b/tools/testing/selftests/net/af_unix/test_unix_oob.c @@ -124,7 +124,7 @@ void producer(struct sockaddr_un *consumer_addr) wait_for_signal(pipefd[0]); if (connect(cfd, (struct sockaddr *)consumer_addr, - sizeof(struct sockaddr)) != 0) { + sizeof(*consumer_addr)) != 0) { perror("Connect failed"); kill(0, SIGTERM); exit(1); diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh index 2d89cb0ad288..330d0b1ceced 100755 --- a/tools/testing/selftests/net/cmsg_ipv6.sh +++ b/tools/testing/selftests/net/cmsg_ipv6.sh @@ -6,7 +6,7 @@ ksft_skip=4 NS=ns IP6=2001:db8:1::1/64 TGT6=2001:db8:1::2 -TMPF=`mktemp` +TMPF=$(mktemp --suffix ".pcap") cleanup() { diff --git a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh index dca1e6f777a8..f11756e7df2f 100755 --- a/tools/testing/selftests/net/l2_tos_ttl_inherit.sh +++ b/tools/testing/selftests/net/l2_tos_ttl_inherit.sh @@ -12,19 +12,27 @@ # In addition this script also checks if forcing a specific field in the # outer header is working. +# Return 4 by default (Kselftest SKIP code) +ERR=4 + if [ "$(id -u)" != "0" ]; then echo "Please run as root." - exit 0 + exit $ERR fi if ! which tcpdump > /dev/null 2>&1; then echo "No tcpdump found. Required for this test." - exit 0 + exit $ERR fi expected_tos="0x00" expected_ttl="0" failed=false +readonly NS0=$(mktemp -u ns0-XXXXXXXX) +readonly NS1=$(mktemp -u ns1-XXXXXXXX) + +RUN_NS0="ip netns exec ${NS0}" + get_random_tos() { # Get a random hex tos value between 0x00 and 0xfc, a multiple of 4 echo "0x$(tr -dc '0-9a-f' < /dev/urandom | head -c 1)\ @@ -61,7 +69,6 @@ setup() { local vlan="$5" local test_tos="0x00" local test_ttl="0" - local ns="ip netns exec testing" # We don't want a test-tos of 0x00, # because this is the value that we get when no tos is set. @@ -94,14 +101,15 @@ setup() { printf "│%7s │%6s │%6s │%13s │%13s │%6s │" \ "$type" "$outer" "$inner" "$tos" "$ttl" "$vlan" - # Create 'testing' netns, veth pair and connect main ns with testing ns - ip netns add testing - ip link add type veth - ip link set veth1 netns testing - ip link set veth0 up - $ns ip link set veth1 up - ip addr flush dev veth0 - $ns ip addr flush dev veth1 + # Create netns NS0 and NS1 and connect them with a veth pair + ip netns add "${NS0}" + ip netns add "${NS1}" + ip link add name veth0 netns "${NS0}" type veth \ + peer name veth1 netns "${NS1}" + ip -netns "${NS0}" link set dev veth0 up + ip -netns "${NS1}" link set dev veth1 up + ip -netns "${NS0}" address flush dev veth0 + ip -netns "${NS1}" address flush dev veth1 local local_addr1="" local local_addr2="" @@ -127,51 +135,59 @@ setup() { if [ "$type" = "gre" ]; then type="gretap" fi - ip addr add 198.18.0.1/24 dev veth0 - $ns ip addr add 198.18.0.2/24 dev veth1 - ip link add name tep0 type $type $local_addr1 remote \ - 198.18.0.2 tos $test_tos ttl $test_ttl $vxlan $geneve - $ns ip link add name tep1 type $type $local_addr2 remote \ - 198.18.0.1 tos $test_tos ttl $test_ttl $vxlan $geneve + ip -netns "${NS0}" address add 198.18.0.1/24 dev veth0 + ip -netns "${NS1}" address add 198.18.0.2/24 dev veth1 + ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \ + remote 198.18.0.2 tos $test_tos ttl $test_ttl \ + $vxlan $geneve + ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \ + remote 198.18.0.1 tos $test_tos ttl $test_ttl \ + $vxlan $geneve elif [ "$outer" = "6" ]; then if [ "$type" = "gre" ]; then type="ip6gretap" fi - ip addr add fdd1:ced0:5d88:3fce::1/64 dev veth0 - $ns ip addr add fdd1:ced0:5d88:3fce::2/64 dev veth1 - ip link add name tep0 type $type $local_addr1 \ - remote fdd1:ced0:5d88:3fce::2 tos $test_tos ttl $test_ttl \ - $vxlan $geneve - $ns ip link add name tep1 type $type $local_addr2 \ - remote fdd1:ced0:5d88:3fce::1 tos $test_tos ttl $test_ttl \ - $vxlan $geneve + ip -netns "${NS0}" address add fdd1:ced0:5d88:3fce::1/64 \ + dev veth0 nodad + ip -netns "${NS1}" address add fdd1:ced0:5d88:3fce::2/64 \ + dev veth1 nodad + ip -netns "${NS0}" link add name tep0 type $type $local_addr1 \ + remote fdd1:ced0:5d88:3fce::2 tos $test_tos \ + ttl $test_ttl $vxlan $geneve + ip -netns "${NS1}" link add name tep1 type $type $local_addr2 \ + remote fdd1:ced0:5d88:3fce::1 tos $test_tos \ + ttl $test_ttl $vxlan $geneve fi # Bring L2-tunnel link up and create VLAN on top - ip link set tep0 up - $ns ip link set tep1 up - ip addr flush dev tep0 - $ns ip addr flush dev tep1 + ip -netns "${NS0}" link set tep0 up + ip -netns "${NS1}" link set tep1 up + ip -netns "${NS0}" address flush dev tep0 + ip -netns "${NS1}" address flush dev tep1 local parent if $vlan; then parent="vlan99-" - ip link add link tep0 name ${parent}0 type vlan id 99 - $ns ip link add link tep1 name ${parent}1 type vlan id 99 - ip link set ${parent}0 up - $ns ip link set ${parent}1 up - ip addr flush dev ${parent}0 - $ns ip addr flush dev ${parent}1 + ip -netns "${NS0}" link add link tep0 name ${parent}0 \ + type vlan id 99 + ip -netns "${NS1}" link add link tep1 name ${parent}1 \ + type vlan id 99 + ip -netns "${NS0}" link set dev ${parent}0 up + ip -netns "${NS1}" link set dev ${parent}1 up + ip -netns "${NS0}" address flush dev ${parent}0 + ip -netns "${NS1}" address flush dev ${parent}1 else parent="tep" fi # Assign inner IPv4/IPv6 addresses if [ "$inner" = "4" ] || [ "$inner" = "other" ]; then - ip addr add 198.19.0.1/24 brd + dev ${parent}0 - $ns ip addr add 198.19.0.2/24 brd + dev ${parent}1 + ip -netns "${NS0}" address add 198.19.0.1/24 brd + dev ${parent}0 + ip -netns "${NS1}" address add 198.19.0.2/24 brd + dev ${parent}1 elif [ "$inner" = "6" ]; then - ip addr add fdd4:96cf:4eae:443b::1/64 dev ${parent}0 - $ns ip addr add fdd4:96cf:4eae:443b::2/64 dev ${parent}1 + ip -netns "${NS0}" address add fdd4:96cf:4eae:443b::1/64 \ + dev ${parent}0 nodad + ip -netns "${NS1}" address add fdd4:96cf:4eae:443b::2/64 \ + dev ${parent}1 nodad fi } @@ -192,10 +208,10 @@ verify() { ping_dst="198.19.0.3" # Generates ARPs which are not IPv4/IPv6 fi if [ "$tos_ttl" = "inherit" ]; then - ping -i 0.1 $ping_dst -Q "$expected_tos" -t "$expected_ttl" \ - 2>/dev/null 1>&2 & ping_pid="$!" + ${RUN_NS0} ping -i 0.1 $ping_dst -Q "$expected_tos" \ + -t "$expected_ttl" 2>/dev/null 1>&2 & ping_pid="$!" else - ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!" + ${RUN_NS0} ping -i 0.1 $ping_dst 2>/dev/null 1>&2 & ping_pid="$!" fi local tunnel_type_offset tunnel_type_proto req_proto_offset req_offset if [ "$type" = "gre" ]; then @@ -216,10 +232,12 @@ verify() { req_proto_offset="$((req_proto_offset + 4))" req_offset="$((req_offset + 4))" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip[$tunnel_type_offset] = $tunnel_type_proto and \ - ip[$req_proto_offset] = 0x01 and \ - ip[$req_offset] = 0x08 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip[$tunnel_type_offset] = $tunnel_type_proto and \ + ip[$req_proto_offset] = 0x01 and \ + ip[$req_offset] = 0x08 2>/dev/null \ + | head -n 1)" elif [ "$inner" = "6" ]; then req_proto_offset="44" req_offset="78" @@ -231,10 +249,12 @@ verify() { req_proto_offset="$((req_proto_offset + 4))" req_offset="$((req_offset + 4))" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip[$tunnel_type_offset] = $tunnel_type_proto and \ - ip[$req_proto_offset] = 0x3a and \ - ip[$req_offset] = 0x80 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip[$tunnel_type_offset] = $tunnel_type_proto and \ + ip[$req_proto_offset] = 0x3a and \ + ip[$req_offset] = 0x80 2>/dev/null \ + | head -n 1)" elif [ "$inner" = "other" ]; then req_proto_offset="36" req_offset="45" @@ -250,11 +270,13 @@ verify() { expected_tos="0x00" expected_ttl="64" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip[$tunnel_type_offset] = $tunnel_type_proto and \ - ip[$req_proto_offset] = 0x08 and \ - ip[$((req_proto_offset + 1))] = 0x06 and \ - ip[$req_offset] = 0x01 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip[$tunnel_type_offset] = $tunnel_type_proto and \ + ip[$req_proto_offset] = 0x08 and \ + ip[$((req_proto_offset + 1))] = 0x06 and \ + ip[$req_offset] = 0x01 2>/dev/null \ + | head -n 1)" fi elif [ "$outer" = "6" ]; then if [ "$type" = "gre" ]; then @@ -273,10 +295,12 @@ verify() { req_proto_offset="$((req_proto_offset + 4))" req_offset="$((req_offset + 4))" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip6[$tunnel_type_offset] = $tunnel_type_proto and \ - ip6[$req_proto_offset] = 0x01 and \ - ip6[$req_offset] = 0x08 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip6[$tunnel_type_offset] = $tunnel_type_proto and \ + ip6[$req_proto_offset] = 0x01 and \ + ip6[$req_offset] = 0x08 2>/dev/null \ + | head -n 1)" elif [ "$inner" = "6" ]; then local req_proto_offset="72" local req_offset="106" @@ -288,10 +312,12 @@ verify() { req_proto_offset="$((req_proto_offset + 4))" req_offset="$((req_offset + 4))" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip6[$tunnel_type_offset] = $tunnel_type_proto and \ - ip6[$req_proto_offset] = 0x3a and \ - ip6[$req_offset] = 0x80 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip6[$tunnel_type_offset] = $tunnel_type_proto and \ + ip6[$req_proto_offset] = 0x3a and \ + ip6[$req_offset] = 0x80 2>/dev/null \ + | head -n 1)" elif [ "$inner" = "other" ]; then local req_proto_offset="64" local req_offset="73" @@ -307,15 +333,17 @@ verify() { expected_tos="0x00" expected_ttl="64" fi - out="$(tcpdump --immediate-mode -p -c 1 -v -i veth0 -n \ - ip6[$tunnel_type_offset] = $tunnel_type_proto and \ - ip6[$req_proto_offset] = 0x08 and \ - ip6[$((req_proto_offset + 1))] = 0x06 and \ - ip6[$req_offset] = 0x01 2>/dev/null | head -n 1)" + out="$(${RUN_NS0} tcpdump --immediate-mode -p -c 1 -v \ + -i veth0 -n \ + ip6[$tunnel_type_offset] = $tunnel_type_proto and \ + ip6[$req_proto_offset] = 0x08 and \ + ip6[$((req_proto_offset + 1))] = 0x06 and \ + ip6[$req_offset] = 0x01 2>/dev/null \ + | head -n 1)" fi fi kill -9 $ping_pid - wait $ping_pid 2>/dev/null + wait $ping_pid 2>/dev/null || true result="FAIL" if [ "$outer" = "4" ]; then captured_ttl="$(get_field "ttl" "$out")" @@ -351,11 +379,35 @@ verify() { } cleanup() { - ip link del veth0 2>/dev/null - ip netns del testing 2>/dev/null - ip link del tep0 2>/dev/null + ip netns del "${NS0}" 2>/dev/null + ip netns del "${NS1}" 2>/dev/null } +exit_handler() { + # Don't exit immediately if one of the intermediate commands fails. + # We might be called at the end of the script, when the network + # namespaces have already been deleted. So cleanup() may fail, but we + # still need to run until 'exit $ERR' or the script won't return the + # correct error code. + set +e + + cleanup + + exit $ERR +} + +# Restore the default SIGINT handler (just in case) and exit. +# The exit handler will take care of cleaning everything up. +interrupted() { + trap - INT + + exit $ERR +} + +set -e +trap exit_handler EXIT +trap interrupted INT + printf "┌────────┬───────┬───────┬──────────────┬" printf "──────────────┬───────┬────────┐\n" for type in gre vxlan geneve; do @@ -385,6 +437,10 @@ done printf "└────────┴───────┴───────┴──────────────┴" printf "──────────────┴───────┴────────┘\n" +# All tests done. +# Set ERR appropriately: it will be returned by the exit handler. if $failed; then - exit 1 + ERR=1 +else + ERR=0 fi diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index a29deb9fa024..ab2d581f28a1 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -752,6 +752,52 @@ test_subflows() "$server4_token" > /dev/null 2>&1 } +test_subflows_v4_v6_mix() +{ + # Attempt to add a listener at 10.0.2.1:<subflow-port> + ip netns exec "$ns1" ./pm_nl_ctl listen 10.0.2.1\ + $app6_port > /dev/null 2>&1 & + local listener_pid=$! + + # ADD_ADDR4 from server to client machine reusing the subflow port on + # the established v6 connection + :>"$client_evts" + ip netns exec "$ns1" ./pm_nl_ctl ann 10.0.2.1 token "$server6_token" id\ + $server_addr_id dev ns1eth2 > /dev/null 2>&1 + stdbuf -o0 -e0 printf "ADD_ADDR4 id:%d 10.0.2.1 (ns1) => ns2, reuse port\t\t" $server_addr_id + sleep 0.5 + verify_announce_event "$client_evts" "$ANNOUNCED" "$client6_token" "10.0.2.1"\ + "$server_addr_id" "$app6_port" + + # CREATE_SUBFLOW from client to server machine + :>"$client_evts" + ip netns exec "$ns2" ./pm_nl_ctl csf lip 10.0.2.2 lid 23 rip 10.0.2.1 rport\ + $app6_port token "$client6_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$client_evts" "$SUB_ESTABLISHED" "$client6_token"\ + "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\ + "$server_addr_id" "ns2" "ns1" + + # Delete the listener from the server ns, if one was created + kill_wait $listener_pid + + sport=$(sed --unbuffered -n 's/.*\(sport:\)\([[:digit:]]*\).*$/\2/p;q' "$client_evts") + + # DESTROY_SUBFLOW from client to server machine + :>"$client_evts" + ip netns exec "$ns2" ./pm_nl_ctl dsf lip 10.0.2.2 lport "$sport" rip 10.0.2.1 rport\ + $app6_port token "$client6_token" > /dev/null 2>&1 + sleep 0.5 + verify_subflow_events "$client_evts" "$SUB_CLOSED" "$client6_token" \ + "$AF_INET" "10.0.2.2" "10.0.2.1" "$app6_port" "23"\ + "$server_addr_id" "ns2" "ns1" + + # RM_ADDR from server to client machine + ip netns exec "$ns1" ./pm_nl_ctl rem id $server_addr_id token\ + "$server6_token" > /dev/null 2>&1 + sleep 0.5 +} + test_prio() { local count @@ -861,6 +907,7 @@ make_connection "v6" test_announce test_remove test_subflows +test_subflows_v4_v6_mix test_prio test_listener diff --git a/tools/testing/selftests/net/toeplitz.c b/tools/testing/selftests/net/toeplitz.c index 90026a27eac0..9ba03164d73a 100644 --- a/tools/testing/selftests/net/toeplitz.c +++ b/tools/testing/selftests/net/toeplitz.c @@ -215,7 +215,7 @@ static char *recv_frame(const struct ring_state *ring, char *frame) } /* A single TPACKET_V3 block can hold multiple frames */ -static void recv_block(struct ring_state *ring) +static bool recv_block(struct ring_state *ring) { struct tpacket_block_desc *block; char *frame; @@ -223,7 +223,7 @@ static void recv_block(struct ring_state *ring) block = (void *)(ring->mmap + ring->idx * ring_block_sz); if (!(block->hdr.bh1.block_status & TP_STATUS_USER)) - return; + return false; frame = (char *)block; frame += block->hdr.bh1.offset_to_first_pkt; @@ -235,6 +235,8 @@ static void recv_block(struct ring_state *ring) block->hdr.bh1.block_status = TP_STATUS_KERNEL; ring->idx = (ring->idx + 1) % ring_block_nr; + + return true; } /* simple test: sleep once unconditionally and then process all rings */ @@ -245,7 +247,7 @@ static void process_rings(void) usleep(1000 * cfg_timeout_msec); for (i = 0; i < num_cpus; i++) - recv_block(&rings[i]); + do {} while (recv_block(&rings[i])); fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n", frames_received - frames_nohash - frames_error, @@ -257,12 +259,12 @@ static char *setup_ring(int fd) struct tpacket_req3 req3 = {0}; void *ring; - req3.tp_retire_blk_tov = cfg_timeout_msec; + req3.tp_retire_blk_tov = cfg_timeout_msec / 8; req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH; req3.tp_frame_size = 2048; req3.tp_frame_nr = 1 << 10; - req3.tp_block_nr = 2; + req3.tp_block_nr = 16; req3.tp_block_size = req3.tp_frame_size * req3.tp_frame_nr; req3.tp_block_size /= req3.tp_block_nr; diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh index dc932fd65363..640bc43452fa 100755 --- a/tools/testing/selftests/net/udpgso_bench.sh +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -7,6 +7,7 @@ readonly GREEN='\033[0;92m' readonly YELLOW='\033[0;33m' readonly RED='\033[0;31m' readonly NC='\033[0m' # No Color +readonly TESTPORT=8000 readonly KSFT_PASS=0 readonly KSFT_FAIL=1 @@ -56,11 +57,26 @@ trap wake_children EXIT run_one() { local -r args=$@ + local nr_socks=0 + local i=0 + local -r timeout=10 + + ./udpgso_bench_rx -p "$TESTPORT" & + ./udpgso_bench_rx -p "$TESTPORT" -t & + + # Wait for the above test program to get ready to receive connections. + while [ "$i" -lt "$timeout" ]; do + nr_socks="$(ss -lnHi | grep -c "\*:${TESTPORT}")" + [ "$nr_socks" -eq 2 ] && break + i=$((i + 1)) + sleep 1 + done + if [ "$nr_socks" -ne 2 ]; then + echo "timed out while waiting for udpgso_bench_rx" + exit 1 + fi - ./udpgso_bench_rx & - ./udpgso_bench_rx -t & - - ./udpgso_bench_tx ${args} + ./udpgso_bench_tx -p "$TESTPORT" ${args} } run_in_netns() { diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c index 6a193425c367..4058c7451e70 100644 --- a/tools/testing/selftests/net/udpgso_bench_rx.c +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -250,7 +250,7 @@ static int recv_msg(int fd, char *buf, int len, int *gso_size) static void do_flush_udp(int fd) { static char rbuf[ETH_MAX_MTU]; - int ret, len, gso_size, budget = 256; + int ret, len, gso_size = 0, budget = 256; len = cfg_read_all ? sizeof(rbuf) : 0; while (budget--) { @@ -336,6 +336,8 @@ static void parse_opts(int argc, char **argv) cfg_verify = true; cfg_read_all = true; break; + default: + exit(1); } } diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c index f1fdaa270291..477392715a9a 100644 --- a/tools/testing/selftests/net/udpgso_bench_tx.c +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -62,6 +62,7 @@ static int cfg_payload_len = (1472 * 42); static int cfg_port = 8000; static int cfg_runtime_ms = -1; static bool cfg_poll; +static int cfg_poll_loop_timeout_ms = 2000; static bool cfg_segment; static bool cfg_sendmmsg; static bool cfg_tcp; @@ -235,16 +236,17 @@ static void flush_errqueue_recv(int fd) } } -static void flush_errqueue(int fd, const bool do_poll) +static void flush_errqueue(int fd, const bool do_poll, + unsigned long poll_timeout, const bool poll_err) { if (do_poll) { struct pollfd fds = {0}; int ret; fds.fd = fd; - ret = poll(&fds, 1, 500); + ret = poll(&fds, 1, poll_timeout); if (ret == 0) { - if (cfg_verbose) + if ((cfg_verbose) && (poll_err)) fprintf(stderr, "poll timeout\n"); } else if (ret < 0) { error(1, errno, "poll"); @@ -254,6 +256,20 @@ static void flush_errqueue(int fd, const bool do_poll) flush_errqueue_recv(fd); } +static void flush_errqueue_retry(int fd, unsigned long num_sends) +{ + unsigned long tnow, tstop; + bool first_try = true; + + tnow = gettimeofday_ms(); + tstop = tnow + cfg_poll_loop_timeout_ms; + do { + flush_errqueue(fd, true, tstop - tnow, first_try); + first_try = false; + tnow = gettimeofday_ms(); + } while ((stat_zcopies != num_sends) && (tnow < tstop)); +} + static int send_tcp(int fd, char *data) { int ret, done = 0, count = 0; @@ -413,7 +429,8 @@ static int send_udp_segment(int fd, char *data) static void usage(const char *filepath) { - error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", + error(1, 0, "Usage: %s [-46acmHPtTuvz] [-C cpu] [-D dst ip] [-l secs] " + "[-L secs] [-M messagenr] [-p port] [-s sendsize] [-S gsosize]", filepath); } @@ -423,7 +440,7 @@ static void parse_opts(int argc, char **argv) int max_len, hdrlen; int c; - while ((c = getopt(argc, argv, "46acC:D:Hl:mM:p:s:PS:tTuvz")) != -1) { + while ((c = getopt(argc, argv, "46acC:D:Hl:L:mM:p:s:PS:tTuvz")) != -1) { switch (c) { case '4': if (cfg_family != PF_UNSPEC) @@ -452,6 +469,9 @@ static void parse_opts(int argc, char **argv) case 'l': cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000; break; + case 'L': + cfg_poll_loop_timeout_ms = strtoul(optarg, NULL, 10) * 1000; + break; case 'm': cfg_sendmmsg = true; break; @@ -490,6 +510,8 @@ static void parse_opts(int argc, char **argv) case 'z': cfg_zerocopy = true; break; + default: + exit(1); } } @@ -677,7 +699,7 @@ int main(int argc, char **argv) num_sends += send_udp(fd, buf[i]); num_msgs++; if ((cfg_zerocopy && ((num_msgs & 0xF) == 0)) || cfg_tx_tstamp) - flush_errqueue(fd, cfg_poll); + flush_errqueue(fd, cfg_poll, 500, true); if (cfg_msg_nr && num_msgs >= cfg_msg_nr) break; @@ -696,7 +718,7 @@ int main(int argc, char **argv) } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop)); if (cfg_zerocopy || cfg_tx_tstamp) - flush_errqueue(fd, true); + flush_errqueue_retry(fd, num_sends); if (close(fd)) error(1, errno, "close"); diff --git a/tools/testing/selftests/netfilter/nft_trans_stress.sh b/tools/testing/selftests/netfilter/nft_trans_stress.sh index a7f62ad4f661..2ffba45a78bf 100755 --- a/tools/testing/selftests/netfilter/nft_trans_stress.sh +++ b/tools/testing/selftests/netfilter/nft_trans_stress.sh @@ -10,12 +10,20 @@ ksft_skip=4 testns=testns-$(mktemp -u "XXXXXXXX") +tmp="" tables="foo bar baz quux" global_ret=0 eret=0 lret=0 +cleanup() { + ip netns pids "$testns" | xargs kill 2>/dev/null + ip netns del "$testns" + + rm -f "$tmp" +} + check_result() { local r=$1 @@ -43,6 +51,7 @@ if [ $? -ne 0 ];then exit $ksft_skip fi +trap cleanup EXIT tmp=$(mktemp) for table in $tables; do @@ -139,11 +148,4 @@ done check_result $lret "add/delete with nftrace enabled" -pkill -9 ping - -wait - -rm -f "$tmp" -ip netns del "$testns" - exit $global_ret diff --git a/tools/testing/selftests/netfilter/settings b/tools/testing/selftests/netfilter/settings new file mode 100644 index 000000000000..6091b45d226b --- /dev/null +++ b/tools/testing/selftests/netfilter/settings @@ -0,0 +1 @@ +timeout=120 diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c index d95b1cb43d9d..7588428b8fcd 100644 --- a/tools/testing/selftests/proc/proc-empty-vm.c +++ b/tools/testing/selftests/proc/proc-empty-vm.c @@ -25,6 +25,7 @@ #undef NDEBUG #include <assert.h> #include <errno.h> +#include <stdint.h> #include <stdio.h> #include <stdlib.h> #include <string.h> @@ -41,7 +42,7 @@ * 1: vsyscall VMA is --xp vsyscall=xonly * 2: vsyscall VMA is r-xp vsyscall=emulate */ -static int g_vsyscall; +static volatile int g_vsyscall; static const char *g_proc_pid_maps_vsyscall; static const char *g_proc_pid_smaps_vsyscall; @@ -147,11 +148,12 @@ static void vsyscall(void) g_vsyscall = 0; /* gettimeofday(NULL, NULL); */ + uint64_t rax = 0xffffffffff600000; asm volatile ( - "call %P0" - : - : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL) - : "rax", "rcx", "r11" + "call *%[rax]" + : [rax] "+a" (rax) + : "D" (NULL), "S" (NULL) + : "rcx", "r11" ); g_vsyscall = 1; diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c index 69551bfa215c..cacbd2a4aec9 100644 --- a/tools/testing/selftests/proc/proc-pid-vm.c +++ b/tools/testing/selftests/proc/proc-pid-vm.c @@ -257,11 +257,12 @@ static void vsyscall(void) g_vsyscall = 0; /* gettimeofday(NULL, NULL); */ + uint64_t rax = 0xffffffffff600000; asm volatile ( - "call %P0" - : - : "i" (0xffffffffff600000), "D" (NULL), "S" (NULL) - : "rax", "rcx", "r11" + "call *%[rax]" + : [rax] "+a" (rax) + : "D" (NULL), "S" (NULL) + : "rcx", "r11" ); g_vsyscall = 1; diff --git a/tools/testing/selftests/vm/hugetlb-madvise.c b/tools/testing/selftests/vm/hugetlb-madvise.c index a634f47d1e56..9a127a8fe176 100644 --- a/tools/testing/selftests/vm/hugetlb-madvise.c +++ b/tools/testing/selftests/vm/hugetlb-madvise.c @@ -17,7 +17,6 @@ #include <stdio.h> #include <unistd.h> #include <sys/mman.h> -#define __USE_GNU #include <fcntl.h> #define MIN_FREE_PAGES 20 diff --git a/tools/virtio/linux/bug.h b/tools/virtio/linux/bug.h index 813baf13f62a..51a919083d9b 100644 --- a/tools/virtio/linux/bug.h +++ b/tools/virtio/linux/bug.h @@ -1,13 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef BUG_H -#define BUG_H +#ifndef _LINUX_BUG_H +#define _LINUX_BUG_H #include <asm/bug.h> #define BUG_ON(__BUG_ON_cond) assert(!(__BUG_ON_cond)) -#define BUILD_BUG_ON(x) - #define BUG() abort() -#endif /* BUG_H */ +#endif /* _LINUX_BUG_H */ diff --git a/tools/virtio/linux/build_bug.h b/tools/virtio/linux/build_bug.h new file mode 100644 index 000000000000..cdbb75e28a60 --- /dev/null +++ b/tools/virtio/linux/build_bug.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_BUILD_BUG_H +#define _LINUX_BUILD_BUG_H + +#define BUILD_BUG_ON(x) + +#endif /* _LINUX_BUILD_BUG_H */ diff --git a/tools/virtio/linux/cpumask.h b/tools/virtio/linux/cpumask.h new file mode 100644 index 000000000000..307da69d6b26 --- /dev/null +++ b/tools/virtio/linux/cpumask.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_CPUMASK_H +#define _LINUX_CPUMASK_H + +#include <linux/kernel.h> + +#endif /* _LINUX_CPUMASK_H */ diff --git a/tools/virtio/linux/gfp.h b/tools/virtio/linux/gfp.h new file mode 100644 index 000000000000..43d146f236f1 --- /dev/null +++ b/tools/virtio/linux/gfp.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GFP_H +#define __LINUX_GFP_H + +#include <linux/topology.h> + +#endif diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h index 21593bf97755..8b877167933d 100644 --- a/tools/virtio/linux/kernel.h +++ b/tools/virtio/linux/kernel.h @@ -10,6 +10,7 @@ #include <stdarg.h> #include <linux/compiler.h> +#include <linux/log2.h> #include <linux/types.h> #include <linux/overflow.h> #include <linux/list.h> diff --git a/tools/virtio/linux/kmsan.h b/tools/virtio/linux/kmsan.h new file mode 100644 index 000000000000..272b5aa285d5 --- /dev/null +++ b/tools/virtio/linux/kmsan.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_KMSAN_H +#define _LINUX_KMSAN_H + +#include <linux/gfp.h> + +inline void kmsan_handle_dma(struct page *page, size_t offset, size_t size, + enum dma_data_direction dir) +{ +} + +#endif /* _LINUX_KMSAN_H */ diff --git a/tools/virtio/linux/scatterlist.h b/tools/virtio/linux/scatterlist.h index 369ee308b668..74d9e1825748 100644 --- a/tools/virtio/linux/scatterlist.h +++ b/tools/virtio/linux/scatterlist.h @@ -2,6 +2,7 @@ #ifndef SCATTERLIST_H #define SCATTERLIST_H #include <linux/kernel.h> +#include <linux/bug.h> struct scatterlist { unsigned long page_link; diff --git a/tools/virtio/linux/topology.h b/tools/virtio/linux/topology.h new file mode 100644 index 000000000000..910794afb993 --- /dev/null +++ b/tools/virtio/linux/topology.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_TOPOLOGY_H +#define _LINUX_TOPOLOGY_H + +#include <linux/cpumask.h> + +#endif /* _LINUX_TOPOLOGY_H */ diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 9fb1ff6f19e5..b74916de5183 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -92,3 +92,6 @@ config KVM_XFER_TO_GUEST_WORK config HAVE_KVM_PM_NOTIFIER bool + +config KVM_GENERIC_HARDWARE_ENABLING + bool diff --git a/virt/kvm/coalesced_mmio.c b/virt/kvm/coalesced_mmio.c index 0be80c213f7f..5ef88f5a0864 100644 --- a/virt/kvm/coalesced_mmio.c +++ b/virt/kvm/coalesced_mmio.c @@ -187,15 +187,17 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm, r = kvm_io_bus_unregister_dev(kvm, zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev); + kvm_iodevice_destructor(&dev->dev); + /* * On failure, unregister destroys all devices on the * bus _except_ the target device, i.e. coalesced_zones - * has been modified. No need to restart the walk as - * there aren't any zones left. + * has been modified. Bail after destroying the target + * device, there's no need to restart the walk as there + * aren't any zones left. */ if (r) break; - kvm_iodevice_destructor(&dev->dev); } } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 13e88297f999..d255964ec331 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -100,13 +100,8 @@ EXPORT_SYMBOL_GPL(halt_poll_ns_shrink); */ DEFINE_MUTEX(kvm_lock); -static DEFINE_RAW_SPINLOCK(kvm_count_lock); LIST_HEAD(vm_list); -static cpumask_var_t cpus_hardware_enabled; -static int kvm_usage_count; -static atomic_t hardware_enable_failed; - static struct kmem_cache *kvm_vcpu_cache; static __read_mostly struct preempt_ops kvm_preempt_ops; @@ -148,9 +143,6 @@ static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); -__visible bool kvm_rebooting; -EXPORT_SYMBOL_GPL(kvm_rebooting); - #define KVM_EVENT_CREATE_VM 0 #define KVM_EVENT_DESTROY_VM 1 static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); @@ -3954,6 +3946,13 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } mutex_lock(&kvm->lock); + +#ifdef CONFIG_LOCKDEP + /* Ensure that lockdep knows vcpu->mutex is taken *inside* kvm->lock */ + mutex_lock(&vcpu->mutex); + mutex_unlock(&vcpu->mutex); +#endif + if (kvm_get_vcpu_by_id(kvm, id)) { r = -EEXIST; goto unlock_vcpu_destroy; @@ -5095,50 +5094,70 @@ static struct miscdevice kvm_dev = { &kvm_chardev_ops, }; -static void hardware_enable_nolock(void *junk) -{ - int cpu = raw_smp_processor_id(); - int r; - - if (cpumask_test_cpu(cpu, cpus_hardware_enabled)) - return; +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING +__visible bool kvm_rebooting; +EXPORT_SYMBOL_GPL(kvm_rebooting); - cpumask_set_cpu(cpu, cpus_hardware_enabled); +static DEFINE_PER_CPU(bool, hardware_enabled); +static int kvm_usage_count; - r = kvm_arch_hardware_enable(); +static int __hardware_enable_nolock(void) +{ + if (__this_cpu_read(hardware_enabled)) + return 0; - if (r) { - cpumask_clear_cpu(cpu, cpus_hardware_enabled); - atomic_inc(&hardware_enable_failed); - pr_info("kvm: enabling virtualization on CPU%d failed\n", cpu); + if (kvm_arch_hardware_enable()) { + pr_info("kvm: enabling virtualization on CPU%d failed\n", + raw_smp_processor_id()); + return -EIO; } + + __this_cpu_write(hardware_enabled, true); + return 0; } -static int kvm_starting_cpu(unsigned int cpu) +static void hardware_enable_nolock(void *failed) { - raw_spin_lock(&kvm_count_lock); + if (__hardware_enable_nolock()) + atomic_inc(failed); +} + +static int kvm_online_cpu(unsigned int cpu) +{ + int ret = 0; + + /* + * Abort the CPU online process if hardware virtualization cannot + * be enabled. Otherwise running VMs would encounter unrecoverable + * errors when scheduled to this CPU. + */ + mutex_lock(&kvm_lock); if (kvm_usage_count) - hardware_enable_nolock(NULL); - raw_spin_unlock(&kvm_count_lock); - return 0; + ret = __hardware_enable_nolock(); + mutex_unlock(&kvm_lock); + return ret; } static void hardware_disable_nolock(void *junk) { - int cpu = raw_smp_processor_id(); - - if (!cpumask_test_cpu(cpu, cpus_hardware_enabled)) + /* + * Note, hardware_disable_all_nolock() tells all online CPUs to disable + * hardware, not just CPUs that successfully enabled hardware! + */ + if (!__this_cpu_read(hardware_enabled)) return; - cpumask_clear_cpu(cpu, cpus_hardware_enabled); + kvm_arch_hardware_disable(); + + __this_cpu_write(hardware_enabled, false); } -static int kvm_dying_cpu(unsigned int cpu) +static int kvm_offline_cpu(unsigned int cpu) { - raw_spin_lock(&kvm_count_lock); + mutex_lock(&kvm_lock); if (kvm_usage_count) hardware_disable_nolock(NULL); - raw_spin_unlock(&kvm_count_lock); + mutex_unlock(&kvm_lock); return 0; } @@ -5153,29 +5172,41 @@ static void hardware_disable_all_nolock(void) static void hardware_disable_all(void) { - raw_spin_lock(&kvm_count_lock); + cpus_read_lock(); + mutex_lock(&kvm_lock); hardware_disable_all_nolock(); - raw_spin_unlock(&kvm_count_lock); + mutex_unlock(&kvm_lock); + cpus_read_unlock(); } static int hardware_enable_all(void) { + atomic_t failed = ATOMIC_INIT(0); int r = 0; - raw_spin_lock(&kvm_count_lock); + /* + * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() + * is called, and so on_each_cpu() between them includes the CPU that + * is being onlined. As a result, hardware_enable_nolock() may get + * invoked before kvm_online_cpu(), which also enables hardware if the + * usage count is non-zero. Disable CPU hotplug to avoid attempting to + * enable hardware multiple times. + */ + cpus_read_lock(); + mutex_lock(&kvm_lock); kvm_usage_count++; if (kvm_usage_count == 1) { - atomic_set(&hardware_enable_failed, 0); - on_each_cpu(hardware_enable_nolock, NULL, 1); + on_each_cpu(hardware_enable_nolock, &failed, 1); - if (atomic_read(&hardware_enable_failed)) { + if (atomic_read(&failed)) { hardware_disable_all_nolock(); r = -EBUSY; } } - raw_spin_unlock(&kvm_count_lock); + mutex_unlock(&kvm_lock); + cpus_read_unlock(); return r; } @@ -5200,6 +5231,49 @@ static struct notifier_block kvm_reboot_notifier = { .priority = 0, }; +static int kvm_suspend(void) +{ + /* + * Secondary CPUs and CPU hotplug are disabled across the suspend/resume + * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count + * is stable. Assert that kvm_lock is not held to ensure the system + * isn't suspended while KVM is enabling hardware. Hardware enabling + * can be preempted, but the task cannot be frozen until it has dropped + * all locks (userspace tasks are frozen via a fake signal). + */ + lockdep_assert_not_held(&kvm_lock); + lockdep_assert_irqs_disabled(); + + if (kvm_usage_count) + hardware_disable_nolock(NULL); + return 0; +} + +static void kvm_resume(void) +{ + lockdep_assert_not_held(&kvm_lock); + lockdep_assert_irqs_disabled(); + + if (kvm_usage_count) + WARN_ON_ONCE(__hardware_enable_nolock()); +} + +static struct syscore_ops kvm_syscore_ops = { + .suspend = kvm_suspend, + .resume = kvm_resume, +}; +#else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ +static int hardware_enable_all(void) +{ + return 0; +} + +static void hardware_disable_all(void) +{ + +} +#endif /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ + static void kvm_io_bus_destroy(struct kvm_io_bus *bus) { int i; @@ -5778,26 +5852,6 @@ static void kvm_init_debug(void) } } -static int kvm_suspend(void) -{ - if (kvm_usage_count) - hardware_disable_nolock(NULL); - return 0; -} - -static void kvm_resume(void) -{ - if (kvm_usage_count) { - lockdep_assert_not_held(&kvm_count_lock); - hardware_enable_nolock(NULL); - } -} - -static struct syscore_ops kvm_syscore_ops = { - .suspend = kvm_suspend, - .resume = kvm_resume, -}; - static inline struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) { @@ -5902,62 +5956,20 @@ void kvm_unregister_perf_callbacks(void) } #endif -struct kvm_cpu_compat_check { - void *opaque; - int *ret; -}; - -static void check_processor_compat(void *data) +int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) { - struct kvm_cpu_compat_check *c = data; - - *c->ret = kvm_arch_check_processor_compat(c->opaque); -} - -int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, - struct module *module) -{ - struct kvm_cpu_compat_check c; int r; int cpu; - r = kvm_arch_init(opaque); - if (r) - goto out_fail; - - /* - * kvm_arch_init makes sure there's at most one caller - * for architectures that support multiple implementations, - * like intel and amd on x86. - * kvm_arch_init must be called before kvm_irqfd_init to avoid creating - * conflicts in case kvm is already setup for another implementation. - */ - r = kvm_irqfd_init(); +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING + r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", + kvm_online_cpu, kvm_offline_cpu); if (r) - goto out_irqfd; - - if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { - r = -ENOMEM; - goto out_free_0; - } - - r = kvm_arch_hardware_setup(opaque); - if (r < 0) - goto out_free_1; - - c.ret = &r; - c.opaque = opaque; - for_each_online_cpu(cpu) { - smp_call_function_single(cpu, check_processor_compat, &c, 1); - if (r < 0) - goto out_free_2; - } + return r; - r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_STARTING, "kvm/cpu:starting", - kvm_starting_cpu, kvm_dying_cpu); - if (r) - goto out_free_2; register_reboot_notifier(&kvm_reboot_notifier); + register_syscore_ops(&kvm_syscore_ops); +#endif /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) @@ -5971,59 +5983,65 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, NULL); if (!kvm_vcpu_cache) { r = -ENOMEM; - goto out_free_3; + goto err_vcpu_cache; } for_each_possible_cpu(cpu) { if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), GFP_KERNEL, cpu_to_node(cpu))) { r = -ENOMEM; - goto out_free_4; + goto err_cpu_kick_mask; } } + r = kvm_irqfd_init(); + if (r) + goto err_irqfd; + r = kvm_async_pf_init(); if (r) - goto out_free_4; + goto err_async_pf; kvm_chardev_ops.owner = module; - r = misc_register(&kvm_dev); - if (r) { - pr_err("kvm: misc device register failed\n"); - goto out_unreg; - } - - register_syscore_ops(&kvm_syscore_ops); - kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; kvm_init_debug(); r = kvm_vfio_ops_init(); - WARN_ON(r); + if (WARN_ON_ONCE(r)) + goto err_vfio; + + /* + * Registration _must_ be the very last thing done, as this exposes + * /dev/kvm to userspace, i.e. all infrastructure must be setup! + */ + r = misc_register(&kvm_dev); + if (r) { + pr_err("kvm: misc device register failed\n"); + goto err_register; + } return 0; -out_unreg: +err_register: + kvm_vfio_ops_exit(); +err_vfio: kvm_async_pf_deinit(); -out_free_4: +err_async_pf: + kvm_irqfd_exit(); +err_irqfd: +err_cpu_kick_mask: for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); -out_free_3: +err_vcpu_cache: +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING + unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); -out_free_2: - kvm_arch_hardware_unsetup(); -out_free_1: - free_cpumask_var(cpus_hardware_enabled); -out_free_0: - kvm_irqfd_exit(); -out_irqfd: - kvm_arch_exit(); -out_fail: + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); +#endif return r; } EXPORT_SYMBOL_GPL(kvm_init); @@ -6032,21 +6050,25 @@ void kvm_exit(void) { int cpu; - debugfs_remove_recursive(kvm_debugfs_dir); + /* + * Note, unregistering /dev/kvm doesn't strictly need to come first, + * fops_get(), a.k.a. try_module_get(), prevents acquiring references + * to KVM while the module is being stopped. + */ misc_deregister(&kvm_dev); + + debugfs_remove_recursive(kvm_debugfs_dir); for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); + kvm_vfio_ops_exit(); kvm_async_pf_deinit(); +#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); - cpuhp_remove_state_nocalls(CPUHP_AP_KVM_STARTING); - on_each_cpu(hardware_disable_nolock, NULL, 1); - kvm_arch_hardware_unsetup(); - kvm_arch_exit(); + cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); +#endif kvm_irqfd_exit(); - free_cpumask_var(cpus_hardware_enabled); - kvm_vfio_ops_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 495ceabffe88..9584eb57e0ed 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -336,7 +336,7 @@ static int kvm_vfio_has_attr(struct kvm_device *dev, return -ENXIO; } -static void kvm_vfio_destroy(struct kvm_device *dev) +static void kvm_vfio_release(struct kvm_device *dev) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_group *kvg, *tmp; @@ -355,7 +355,7 @@ static void kvm_vfio_destroy(struct kvm_device *dev) kvm_vfio_update_coherency(dev); kfree(kv); - kfree(dev); /* alloc by kvm_ioctl_create_device, free by .destroy */ + kfree(dev); /* alloc by kvm_ioctl_create_device, free by .release */ } static int kvm_vfio_create(struct kvm_device *dev, u32 type); @@ -363,7 +363,7 @@ static int kvm_vfio_create(struct kvm_device *dev, u32 type); static struct kvm_device_ops kvm_vfio_ops = { .name = "kvm-vfio", .create = kvm_vfio_create, - .destroy = kvm_vfio_destroy, + .release = kvm_vfio_release, .set_attr = kvm_vfio_set_attr, .has_attr = kvm_vfio_has_attr, }; |