diff options
309 files changed, 3554 insertions, 1629 deletions
diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst index 8aefa1001ae5..8c324ad638de 100644 --- a/Documentation/arm64/booting.rst +++ b/Documentation/arm64/booting.rst @@ -340,6 +340,14 @@ Before jumping into the kernel, the following conditions must be met: - SMCR_EL2.LEN must be initialised to the same value for all CPUs the kernel will execute on. + - HWFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01. + + - HWFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01. + + - HWFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01. + + - HWFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01. + For CPUs with the Scalable Matrix Extension FA64 feature (FEAT_SME_FA64) - If EL3 is present: diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst index 04ba83e1965f..c7adc7897df6 100644 --- a/Documentation/arm64/cpu-feature-registers.rst +++ b/Documentation/arm64/cpu-feature-registers.rst @@ -92,7 +92,7 @@ operation if the source belongs to the supported system register space. The infrastructure emulates only the following system register space:: - Op0=3, Op1=0, CRn=0, CRm=0,4,5,6,7 + Op0=3, Op1=0, CRn=0, CRm=0,2,3,4,5,6,7 (See Table C5-6 'System instruction encodings for non-Debug System register accesses' in ARMv8 ARM DDI 0487A.h, for the list of @@ -293,6 +293,42 @@ infrastructure: | WFXT | [3-0] | y | +------------------------------+---------+---------+ + 10) MVFR0_EL1 - AArch32 Media and VFP Feature Register 0 + + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | FPDP | [11-8] | y | + +------------------------------+---------+---------+ + + 11) MVFR1_EL1 - AArch32 Media and VFP Feature Register 1 + + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | SIMDFMAC | [31-28] | y | + +------------------------------+---------+---------+ + | SIMDSP | [19-16] | y | + +------------------------------+---------+---------+ + | SIMDInt | [15-12] | y | + +------------------------------+---------+---------+ + | SIMDLS | [11-8] | y | + +------------------------------+---------+---------+ + + 12) ID_ISAR5_EL1 - AArch32 Instruction Set Attribute Register 5 + + +------------------------------+---------+---------+ + | Name | bits | visible | + +------------------------------+---------+---------+ + | CRC32 | [19-16] | y | + +------------------------------+---------+---------+ + | SHA2 | [15-12] | y | + +------------------------------+---------+---------+ + | SHA1 | [11-8] | y | + +------------------------------+---------+---------+ + | AES | [7-4] | y | + +------------------------------+---------+---------+ + Appendix I: Example ------------------- diff --git a/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml b/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml index 58022ae7d5dd..dfdb8dfb6b65 100644 --- a/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml +++ b/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml @@ -81,6 +81,9 @@ properties: power-supply: true + power-domains: + maxItems: 1 + resets: description: | A number of phandles to resets that need to be asserted during diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst index 687adb58048e..56082265e8e5 100644 --- a/Documentation/driver-api/driver-model/devres.rst +++ b/Documentation/driver-api/driver-model/devres.rst @@ -279,6 +279,7 @@ GPIO devm_gpio_request_one() I2C + devm_i2c_add_adapter() devm_i2c_new_dummy_device() IIO diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst index 071f0151a7a4..f2dcc39044e6 100644 --- a/Documentation/kbuild/reproducible-builds.rst +++ b/Documentation/kbuild/reproducible-builds.rst @@ -119,6 +119,16 @@ To avoid this, you can make the vDSO different for different kernel versions by including an arbitrary string of "salt" in it. This is specified by the Kconfig symbol ``CONFIG_BUILD_SALT``. +Git +--- + +Uncommitted changes or different commit ids in git can also lead +to different compilation results. For example, after executing +``git reset HEAD^``, even if the code is the same, the +``include/config/kernel.release`` generated during compilation +will be different, which will eventually lead to binary differences. +See ``scripts/setlocalversion`` for details. + .. _KBUILD_BUILD_TIMESTAMP: kbuild.html#kbuild-build-timestamp .. _KBUILD_BUILD_USER and KBUILD_BUILD_HOST: kbuild.html#kbuild-build-user-kbuild-build-host .. _KCFLAGS: kbuild.html#kcflags diff --git a/Documentation/kernel-hacking/hacking.rst b/Documentation/kernel-hacking/hacking.rst index 9a1f020c8449..1717348a4404 100644 --- a/Documentation/kernel-hacking/hacking.rst +++ b/Documentation/kernel-hacking/hacking.rst @@ -120,7 +120,7 @@ You can tell you are in a softirq (or tasklet) using the .. warning:: Beware that this will return a false positive if a - :ref:`botton half lock <local_bh_disable>` is held. + :ref:`bottom half lock <local_bh_disable>` is held. Some Basic Rules ================ diff --git a/Documentation/process/2.Process.rst b/Documentation/process/2.Process.rst index e05fb1b8f8b6..6a919cffcbfd 100644 --- a/Documentation/process/2.Process.rst +++ b/Documentation/process/2.Process.rst @@ -126,17 +126,10 @@ than one development cycle past their initial release. So, for example, the 5.2.21 was the final stable update of the 5.2 release. Some kernels are designated "long term" kernels; they will receive support -for a longer period. As of this writing, the current long term kernels -and their maintainers are: - - ====== ================================ ======================= - 3.16 Ben Hutchings (very long-term kernel) - 4.4 Greg Kroah-Hartman & Sasha Levin (very long-term kernel) - 4.9 Greg Kroah-Hartman & Sasha Levin - 4.14 Greg Kroah-Hartman & Sasha Levin - 4.19 Greg Kroah-Hartman & Sasha Levin - 5.4 Greg Kroah-Hartman & Sasha Levin - ====== ================================ ======================= +for a longer period. Please refer to the following link for the list of active +long term kernel versions and their maintainers: + + https://www.kernel.org/category/releases.html The selection of a kernel for long-term support is purely a matter of a maintainer having the need and the time to maintain that release. There diff --git a/Documentation/process/howto.rst b/Documentation/process/howto.rst index bd15c393ba3c..cb6abcb2b6d0 100644 --- a/Documentation/process/howto.rst +++ b/Documentation/process/howto.rst @@ -36,7 +36,7 @@ experience, the following books are good for, if anything, reference: - "C: A Reference Manual" by Harbison and Steele [Prentice Hall] The kernel is written using GNU C and the GNU toolchain. While it -adheres to the ISO C89 standard, it uses a number of extensions that are +adheres to the ISO C11 standard, it uses a number of extensions that are not featured in the standard. The kernel is a freestanding C environment, with no reliance on the standard C library, so some portions of the C standard are not supported. Arbitrary long long diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst index c1b685a38f6b..87bd772836c0 100644 --- a/Documentation/trace/histogram.rst +++ b/Documentation/trace/histogram.rst @@ -39,7 +39,7 @@ Documentation written by Tom Zanussi will use the event's kernel stacktrace as the key. The keywords 'keys' or 'key' can be used to specify keys, and the keywords 'values', 'vals', or 'val' can be used to specify values. Compound - keys consisting of up to two fields can be specified by the 'keys' + keys consisting of up to three fields can be specified by the 'keys' keyword. Hashing a compound key produces a unique entry in the table for each unique combination of component keys, and can be useful for providing more fine-grained summaries of event data. diff --git a/Documentation/translations/it_IT/process/howto.rst b/Documentation/translations/it_IT/process/howto.rst index 15c08aea1dfe..052f1b3610cb 100644 --- a/Documentation/translations/it_IT/process/howto.rst +++ b/Documentation/translations/it_IT/process/howto.rst @@ -44,7 +44,7 @@ altro, utili riferimenti: - "C: A Reference Manual" di Harbison and Steele [Prentice Hall] Il kernel è stato scritto usando GNU C e la toolchain GNU. -Sebbene si attenga allo standard ISO C89, esso utilizza una serie di +Sebbene si attenga allo standard ISO C11, esso utilizza una serie di estensioni che non sono previste in questo standard. Il kernel è un ambiente C indipendente, che non ha alcuna dipendenza dalle librerie C standard, così alcune parti del C standard non sono supportate. diff --git a/Documentation/translations/ja_JP/howto.rst b/Documentation/translations/ja_JP/howto.rst index b47a682d8ded..b8eeb45a02d4 100644 --- a/Documentation/translations/ja_JP/howto.rst +++ b/Documentation/translations/ja_JP/howto.rst @@ -65,7 +65,7 @@ Linux カーネル開発のやり方 - 『新・詳説 C 言語 H&S リファレンス』 (サミュエル P ハービソン/ガイ L スティール共著 斉藤 信男監訳)[ソフトバンク] カーネルは GNU C と GNU ツールチェインを使って書かれています。カーネル -は ISO C89 仕様に準拠して書く一方で、標準には無い言語拡張を多く使って +は ISO C11 仕様に準拠して書く一方で、標準には無い言語拡張を多く使って います。カーネルは標準 C ライブラリに依存しない、C 言語非依存環境です。 そのため、C の標準の中で使えないものもあります。特に任意の long long の除算や浮動小数点は使えません。カーネルがツールチェインや C 言語拡張 diff --git a/Documentation/translations/ko_KR/howto.rst b/Documentation/translations/ko_KR/howto.rst index df53fafd1b10..969e91a95bb0 100644 --- a/Documentation/translations/ko_KR/howto.rst +++ b/Documentation/translations/ko_KR/howto.rst @@ -62,7 +62,7 @@ Documentation/process/howto.rst - "Practical C Programming" by Steve Oualline [O'Reilly] - "C: A Reference Manual" by Harbison and Steele [Prentice Hall] -커널은 GNU C와 GNU 툴체인을 사용하여 작성되었다. 이 툴들은 ISO C89 표준을 +커널은 GNU C와 GNU 툴체인을 사용하여 작성되었다. 이 툴들은 ISO C11 표준을 따르는 반면 표준에 있지 않은 많은 확장기능도 가지고 있다. 커널은 표준 C 라이브러리와는 관계없이 freestanding C 환경이어서 C 표준의 일부는 지원되지 않는다. 임의의 long long 나누기나 floating point는 지원되지 않는다. diff --git a/Documentation/translations/zh_CN/process/howto.rst b/Documentation/translations/zh_CN/process/howto.rst index 5bf953146929..888978a62db3 100644 --- a/Documentation/translations/zh_CN/process/howto.rst +++ b/Documentation/translations/zh_CN/process/howto.rst @@ -45,7 +45,7 @@ Linux内核大部分是由C语言写成的，一些体系结构相关的代码 - "C: A Reference Manual" by Harbison and Steele [Prentice Hall] 《C语言参考手册（原书第5版）》（邱仲潘 等译）[机械工业出版社] -Linux内核使用GNU C和GNU工具链开发。虽然它遵循ISO C89标准，但也用到了一些 +Linux内核使用GNU C和GNU工具链开发。虽然它遵循ISO C11标准，但也用到了一些 标准中没有定义的扩展。内核是自给自足的C环境，不依赖于标准C库的支持，所以 并不支持C标准中的部分定义。比如long long类型的大数除法和浮点运算就不允许 使用。有时候确实很难弄清楚内核对工具链的要求和它所使用的扩展，不幸的是目 diff --git a/Documentation/translations/zh_TW/process/howto.rst b/Documentation/translations/zh_TW/process/howto.rst index 86b0d4c6d6f9..8fb8edcaee66 100644 --- a/Documentation/translations/zh_TW/process/howto.rst +++ b/Documentation/translations/zh_TW/process/howto.rst @@ -48,7 +48,7 @@ Linux內核大部分是由C語言寫成的，一些體系結構相關的代碼 - "C: A Reference Manual" by Harbison and Steele [Prentice Hall] 《C語言參考手冊（原書第5版）》（邱仲潘 等譯）[機械工業出版社] -Linux內核使用GNU C和GNU工具鏈開發。雖然它遵循ISO C89標準，但也用到了一些 +Linux內核使用GNU C和GNU工具鏈開發。雖然它遵循ISO C11標準，但也用到了一些 標準中沒有定義的擴展。內核是自給自足的C環境，不依賴於標準C庫的支持，所以 並不支持C標準中的部分定義。比如long long類型的大數除法和浮點運算就不允許 使用。有時候確實很難弄清楚內核對工具鏈的要求和它所使用的擴展，不幸的是目 diff --git a/MAINTAINERS b/MAINTAINERS index 379945f82a64..046ff06ff97f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3984,7 +3984,7 @@ M: Rafał Miłecki <rafal@milecki.pl> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: Documentation/devicetree/bindings/arm/bcm/brcm,bcmbca.yaml F: arch/arm64/boot/dts/broadcom/bcmbca/* N: bcmbca @@ -4009,7 +4009,7 @@ R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml F: drivers/pci/controller/pcie-brcmstb.c F: drivers/staging/vc04_services @@ -4023,7 +4023,7 @@ M: Ray Jui <rjui@broadcom.com> M: Scott Branden <sbranden@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> S: Maintained -T: git git://github.com/broadcom/mach-bcm +T: git https://github.com/broadcom/mach-bcm F: arch/arm/mach-bcm/ N: bcm281* N: bcm113* @@ -4088,7 +4088,7 @@ M: Florian Fainelli <f.fainelli@gmail.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml F: arch/arm/boot/dts/bcm7*.dts* F: arch/arm/include/asm/hardware/cache-b15-rac.h @@ -4121,7 +4121,7 @@ M: Florian Fainelli <f.fainelli@gmail.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-mips@vger.kernel.org S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: arch/mips/bmips/* F: arch/mips/boot/dts/brcm/bcm*.dts* F: arch/mips/include/asm/mach-bmips/* @@ -4262,7 +4262,7 @@ M: Scott Branden <sbranden@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: arch/arm64/boot/dts/broadcom/northstar2/* F: arch/arm64/boot/dts/broadcom/stingray/* F: drivers/clk/bcm/clk-ns* @@ -4332,7 +4332,7 @@ M: Florian Fainelli <f.fainelli@gmail.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> L: linux-pm@vger.kernel.org S: Maintained -T: git git://github.com/broadcom/stblinux.git +T: git https://github.com/broadcom/stblinux.git F: drivers/soc/bcm/bcm63xx/bcm-pmb.c F: include/dt-bindings/soc/bcm-pmb.h @@ -5041,7 +5041,7 @@ F: drivers/scsi/snic/ CISCO VIC ETHERNET NIC DRIVER M: Christian Benvenuti <benve@cisco.com> -M: Govindarajulu Varadarajan <_govind@gmx.com> +M: Satish Kharat <satishkh@cisco.com> S: Supported F: drivers/net/ethernet/cisco/enic/ @@ -9217,7 +9217,7 @@ W: https://www.hisilicon.com F: drivers/i2c/busses/i2c-hisi.c HISILICON LPC BUS DRIVER -M: john.garry@huawei.com +M: Jay Fang <f.fangjian@huawei.com> S: Maintained W: http://www.hisilicon.com F: Documentation/devicetree/bindings/arm/hisilicon/low-pin-count.yaml @@ -9778,7 +9778,10 @@ S: Supported F: drivers/pci/hotplug/rpaphp* IBM Power SRIOV Virtual NIC Device Driver -M: Dany Madden <drt@linux.ibm.com> +M: Haren Myneni <haren@linux.ibm.com> +M: Rick Lindsley <ricklind@linux.ibm.com> +R: Nick Child <nnac123@linux.ibm.com> +R: Dany Madden <danymadden@us.ibm.com> R: Thomas Falcon <tlfalcon@linux.ibm.com> L: netdev@vger.kernel.org S: Supported @@ -11248,7 +11251,7 @@ L: kvm@vger.kernel.org L: kvm-riscv@lists.infradead.org L: linux-riscv@lists.infradead.org S: Maintained -T: git git://github.com/kvm-riscv/linux.git +T: git https://github.com/kvm-riscv/linux.git F: arch/riscv/include/asm/kvm* F: arch/riscv/include/uapi/asm/kvm* F: arch/riscv/kvm/ @@ -15630,7 +15633,7 @@ F: drivers/input/serio/gscps2.c F: drivers/input/serio/hp_sdc* F: drivers/parisc/ F: drivers/parport/parport_gsc.* -F: drivers/tty/serial/8250/8250_gsc.c +F: drivers/tty/serial/8250/8250_parisc.c F: drivers/video/console/sti* F: drivers/video/fbdev/sti* F: drivers/video/logo/logo_parisc* @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 1 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc4 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* @@ -1218,7 +1218,7 @@ quiet_cmd_ar_vmlinux.a = AR $@ cmd_ar_vmlinux.a = \ rm -f $@; \ $(AR) cDPrST $@ $(KBUILD_VMLINUX_OBJS); \ - $(AR) mPiT $$($(AR) t $@ | head -n1) $@ $$($(AR) t $@ | grep -F --file=$(srctree)/scripts/head-object-list.txt) + $(AR) mPiT $$($(AR) t $@ | sed -n 1p) $@ $$($(AR) t $@ | grep -F -f $(srctree)/scripts/head-object-list.txt) targets += vmlinux.a vmlinux.a: $(KBUILD_VMLINUX_OBJS) scripts/head-object-list.txt autoksyms_recursive FORCE diff --git a/arch/arm/boot/dts/imx6q-yapp4-crux.dts b/arch/arm/boot/dts/imx6q-yapp4-crux.dts index 15f4824a5142..bddf3822ebf7 100644 --- a/arch/arm/boot/dts/imx6q-yapp4-crux.dts +++ b/arch/arm/boot/dts/imx6q-yapp4-crux.dts @@ -33,6 +33,10 @@ status = "okay"; }; +®_pu { + regulator-always-on; +}; + ®_usb_h1_vbus { status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi index 68e5ab2e27e2..6bb4855d13ce 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi @@ -29,7 +29,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = <BTN_0>; }; diff --git a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi index 8e23cec7149e..696427b487f0 100644 --- a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi @@ -26,7 +26,7 @@ user-pb { label = "user_pb"; - gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>; + gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>; linux,code = <BTN_0>; }; diff --git a/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts b/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts index cea165f2161a..afaf4a6759d4 100644 --- a/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts +++ b/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts @@ -33,6 +33,10 @@ status = "okay"; }; +®_pu { + regulator-always-on; +}; + ®_usb_h1_vbus { status = "okay"; }; diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi index fbaa0ce46427..8f1bb78fc1e4 100644 --- a/arch/arm/boot/dts/ste-href.dtsi +++ b/arch/arm/boot/dts/ste-href.dtsi @@ -24,6 +24,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index 1c9094f24893..e2f0cdacba7d 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -28,6 +28,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts b/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts index d6940e0afa86..27a3ab7e25e1 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts @@ -44,6 +44,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts index 5f41256d7f4b..b88f0c07873d 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts @@ -57,6 +57,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts index 806da3fc33cd..7231bc745200 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts @@ -30,6 +30,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts index b0dce91aff4b..9604695edf53 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts @@ -35,6 +35,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-janice.dts b/arch/arm/boot/dts/ste-ux500-samsung-janice.dts index ed5c79c3d04b..69387e8754a9 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-janice.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-janice.dts @@ -30,6 +30,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts b/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts index c57676faf181..167846df3104 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts @@ -34,6 +34,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts index 81b341a5ae45..93e5f5ed888d 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts @@ -30,6 +30,14 @@ polling-delay = <0>; polling-delay-passive = <0>; thermal-sensors = <&bat_therm>; + + trips { + battery-crit-hi { + temperature = <70000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; }; diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi index 2f27619d8abd..8b4d280b1e7e 100644 --- a/arch/arm64/boot/dts/arm/juno-base.dtsi +++ b/arch/arm64/boot/dts/arm/juno-base.dtsi @@ -751,12 +751,26 @@ polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 0>; + trips { + pmic_crit0: trip0 { + temperature = <90000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; soc { polling-delay = <1000>; polling-delay-passive = <100>; thermal-sensors = <&scpi_sensors0 3>; + trips { + soc_crit0: trip0 { + temperature = <80000>; + hysteresis = <2000>; + type = "critical"; + }; + }; }; big_cluster_thermal_zone: big-cluster { diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi index 421d879013d7..260d045dbd9a 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi @@ -779,6 +779,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(1)>; status = "disabled"; }; @@ -788,6 +791,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(1)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi index f1b9cc8714dc..348d9e3a9125 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi @@ -532,6 +532,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; @@ -541,6 +544,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi index 6680fb2a6dc9..8c76d86cb756 100644 --- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi @@ -1385,6 +1385,9 @@ #address-cells = <1>; #size-cells = <0>; little-endian; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; @@ -1395,6 +1398,9 @@ little-endian; #address-cells = <1>; #size-cells = <0>; + clock-frequency = <2500000>; + clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL + QORIQ_CLK_PLL_DIV(2)>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi index 82a1c4488378..10370d1a6c6d 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi @@ -38,9 +38,9 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b010000 0x10000>; clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>, - <&sdhc0_lpcg IMX_LPCG_CLK_5>, - <&sdhc0_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc0_lpcg IMX_LPCG_CLK_0>, + <&sdhc0_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_0>; status = "disabled"; }; @@ -49,9 +49,9 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 233 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b020000 0x10000>; clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>, - <&sdhc1_lpcg IMX_LPCG_CLK_5>, - <&sdhc1_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc1_lpcg IMX_LPCG_CLK_0>, + <&sdhc1_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_1>; fsl,tuning-start-tap = <20>; fsl,tuning-step = <2>; @@ -62,9 +62,9 @@ conn_subsys: bus@5b000000 { interrupts = <GIC_SPI 234 IRQ_TYPE_LEVEL_HIGH>; reg = <0x5b030000 0x10000>; clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>, - <&sdhc2_lpcg IMX_LPCG_CLK_5>, - <&sdhc2_lpcg IMX_LPCG_CLK_0>; - clock-names = "ipg", "per", "ahb"; + <&sdhc2_lpcg IMX_LPCG_CLK_0>, + <&sdhc2_lpcg IMX_LPCG_CLK_5>; + clock-names = "ipg", "ahb", "per"; power-domains = <&pd IMX_SC_R_SDHC_2>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts index 32f6f2f50c10..43e89859c044 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts +++ b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts @@ -250,21 +250,21 @@ /* SODIMM 96 */ MX8MM_IOMUXC_SAI1_RXD2_GPIO4_IO4 0x1c4 /* CPLD_D[7] */ - MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5 0x1c4 + MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5 0x184 /* CPLD_D[6] */ - MX8MM_IOMUXC_SAI1_RXFS_GPIO4_IO0 0x1c4 + MX8MM_IOMUXC_SAI1_RXFS_GPIO4_IO0 0x184 /* CPLD_D[5] */ - MX8MM_IOMUXC_SAI1_TXC_GPIO4_IO11 0x1c4 + MX8MM_IOMUXC_SAI1_TXC_GPIO4_IO11 0x184 /* CPLD_D[4] */ - MX8MM_IOMUXC_SAI1_TXD0_GPIO4_IO12 0x1c4 + MX8MM_IOMUXC_SAI1_TXD0_GPIO4_IO12 0x184 /* CPLD_D[3] */ - MX8MM_IOMUXC_SAI1_TXD1_GPIO4_IO13 0x1c4 + MX8MM_IOMUXC_SAI1_TXD1_GPIO4_IO13 0x184 /* CPLD_D[2] */ - MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14 0x1c4 + MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14 0x184 /* CPLD_D[1] */ - MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15 0x1c4 + MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15 0x184 /* CPLD_D[0] */ - MX8MM_IOMUXC_SAI1_TXD4_GPIO4_IO16 0x1c4 + MX8MM_IOMUXC_SAI1_TXD4_GPIO4_IO16 0x184 /* KBD_intK */ MX8MM_IOMUXC_SAI2_MCLK_GPIO4_IO27 0x1c4 /* DISP_reset */ diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi index afb90f59c83c..dabd94dc30c4 100644 --- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi @@ -276,6 +276,7 @@ assigned-clocks = <&clk IMX8MM_CLK_USB_PHY_REF>; assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_100M>; clock-names = "main_clk"; + power-domains = <&pgc_otg1>; }; usbphynop2: usbphynop2 { @@ -285,6 +286,7 @@ assigned-clocks = <&clk IMX8MM_CLK_USB_PHY_REF>; assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_100M>; clock-names = "main_clk"; + power-domains = <&pgc_otg2>; }; soc: soc@0 { @@ -674,13 +676,11 @@ pgc_otg1: power-domain@2 { #power-domain-cells = <0>; reg = <IMX8MM_POWER_DOMAIN_OTG1>; - power-domains = <&pgc_hsiomix>; }; pgc_otg2: power-domain@3 { #power-domain-cells = <0>; reg = <IMX8MM_POWER_DOMAIN_OTG2>; - power-domains = <&pgc_hsiomix>; }; pgc_gpumix: power-domain@4 { @@ -1186,7 +1186,7 @@ assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>; phys = <&usbphynop1>; fsl,usbmisc = <&usbmisc1 0>; - power-domains = <&pgc_otg1>; + power-domains = <&pgc_hsiomix>; status = "disabled"; }; @@ -1206,7 +1206,7 @@ assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>; phys = <&usbphynop2>; fsl,usbmisc = <&usbmisc2 0>; - power-domains = <&pgc_otg2>; + power-domains = <&pgc_hsiomix>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index cb2836bfbd95..ad0b99adf691 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -662,7 +662,6 @@ pgc_otg1: power-domain@1 { #power-domain-cells = <0>; reg = <IMX8MN_POWER_DOMAIN_OTG1>; - power-domains = <&pgc_hsiomix>; }; pgc_gpumix: power-domain@2 { @@ -1076,7 +1075,7 @@ assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>; phys = <&usbphynop1>; fsl,usbmisc = <&usbmisc1 0>; - power-domains = <&pgc_otg1>; + power-domains = <&pgc_hsiomix>; status = "disabled"; }; @@ -1175,5 +1174,6 @@ assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>; assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>; clock-names = "main_clk"; + power-domains = <&pgc_otg1>; }; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi index 7b712d1888ea..5dcd1de586b5 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi @@ -354,16 +354,6 @@ "SODIMM_82", "SODIMM_70", "SODIMM_72"; - - ctrl-sleep-moci-hog { - gpio-hog; - /* Verdin CTRL_SLEEP_MOCI# (SODIMM 256) */ - gpios = <29 GPIO_ACTIVE_HIGH>; - line-name = "CTRL_SLEEP_MOCI#"; - output-high; - pinctrl-names = "default"; - pinctrl-0 = <&pinctrl_ctrl_sleep_moci>; - }; }; &gpio3 { @@ -432,6 +422,16 @@ "SODIMM_256", "SODIMM_48", "SODIMM_44"; + + ctrl-sleep-moci-hog { + gpio-hog; + /* Verdin CTRL_SLEEP_MOCI# (SODIMM 256) */ + gpios = <29 GPIO_ACTIVE_HIGH>; + line-name = "CTRL_SLEEP_MOCI#"; + output-high; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_ctrl_sleep_moci>; + }; }; /* On-module I2C */ diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi index 3a5713bb4880..0247866fc86b 100644 --- a/arch/arm64/boot/dts/freescale/imx93.dtsi +++ b/arch/arm64/boot/dts/freescale/imx93.dtsi @@ -451,7 +451,7 @@ clocks = <&clk IMX93_CLK_GPIO2_GATE>, <&clk IMX93_CLK_GPIO2_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 32 32>; + gpio-ranges = <&iomuxc 0 4 30>; }; gpio3: gpio@43820080 { @@ -465,7 +465,8 @@ clocks = <&clk IMX93_CLK_GPIO3_GATE>, <&clk IMX93_CLK_GPIO3_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 64 32>; + gpio-ranges = <&iomuxc 0 84 8>, <&iomuxc 8 66 18>, + <&iomuxc 26 34 2>, <&iomuxc 28 0 4>; }; gpio4: gpio@43830080 { @@ -479,7 +480,7 @@ clocks = <&clk IMX93_CLK_GPIO4_GATE>, <&clk IMX93_CLK_GPIO4_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 96 32>; + gpio-ranges = <&iomuxc 0 38 28>, <&iomuxc 28 36 2>; }; gpio1: gpio@47400080 { @@ -493,7 +494,7 @@ clocks = <&clk IMX93_CLK_GPIO1_GATE>, <&clk IMX93_CLK_GPIO1_GATE>; clock-names = "gpio", "port"; - gpio-ranges = <&iomuxc 0 0 32>; + gpio-ranges = <&iomuxc 0 92 16>; }; s4muap: mailbox@47520000 { @@ -501,7 +502,7 @@ reg = <0x47520000 0x10000>; interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>; - interrupt-names = "txirq", "rxirq"; + interrupt-names = "tx", "rx"; #mbox-cells = <2>; }; diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 439e2bc5d5d8..d6cf535d8352 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -14,8 +14,16 @@ #ifdef CONFIG_EFI extern void efi_init(void); + +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg); #else #define efi_init() + +static inline +bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg) +{ + return false; +} #endif int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6062454a9067..b3f37e2209ad 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -428,6 +428,30 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_mvfr0[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPROUND_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSHVEC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSQRT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDIVIDE_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPTRAP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_SIMD_SHIFT, 4, 0), + ARM64_FTR_END, +}; + +static const struct arm64_ftr_bits ftr_mvfr1[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDFMAC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDSP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDINT_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDLS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPDNAN_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPFTZ_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_mvfr2[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_FPMISC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_SIMDMISC_SHIFT, 4, 0), @@ -458,10 +482,10 @@ static const struct arm64_ftr_bits ftr_id_isar0[] = { static const struct arm64_ftr_bits ftr_id_isar5[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -574,7 +598,7 @@ static const struct arm64_ftr_bits ftr_smcr[] = { * Common ftr bits for a 32bit register with all hidden, strict * attributes, with 4bit feature fields and a default safe value of * 0. Covers the following 32bit registers: - * id_isar[1-4], id_mmfr[1-3], id_pfr1, mvfr[0-1] + * id_isar[1-3], id_mmfr[1-3] */ static const struct arm64_ftr_bits ftr_generic_32bits[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0), @@ -645,8 +669,8 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_ISAR6_EL1, ftr_id_isar6), /* Op1 = 0, CRn = 0, CRm = 3 */ - ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits), - ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_generic_32bits), + ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_mvfr0), + ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_mvfr1), ARM64_FTR_REG(SYS_MVFR2_EL1, ftr_mvfr2), ARM64_FTR_REG(SYS_ID_PFR2_EL1, ftr_id_pfr2), ARM64_FTR_REG(SYS_ID_DFR1_EL1, ftr_id_dfr1), @@ -3339,7 +3363,7 @@ static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *c /* * We emulate only the following system register space. - * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 4 - 7] + * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 2 - 7] * See Table C5-6 System instruction encodings for System register accesses, * ARMv8 ARM(ARM DDI 0487A.f) for more details. */ @@ -3349,7 +3373,7 @@ static inline bool __attribute_const__ is_emulated(u32 id) sys_reg_CRn(id) == 0x0 && sys_reg_Op1(id) == 0x0 && (sys_reg_CRm(id) == 0 || - ((sys_reg_CRm(id) >= 4) && (sys_reg_CRm(id) <= 7)))); + ((sys_reg_CRm(id) >= 2) && (sys_reg_CRm(id) <= 7)))); } /* diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S index 75691a2641c1..67babd5f04c2 100644 --- a/arch/arm64/kernel/efi-rt-wrapper.S +++ b/arch/arm64/kernel/efi-rt-wrapper.S @@ -6,7 +6,7 @@ #include <linux/linkage.h> SYM_FUNC_START(__efi_rt_asm_wrapper) - stp x29, x30, [sp, #-32]! + stp x29, x30, [sp, #-112]! mov x29, sp /* @@ -17,6 +17,20 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) stp x1, x18, [sp, #16] /* + * Preserve all callee saved registers and record the stack pointer + * value in a per-CPU variable so we can recover from synchronous + * exceptions occurring while running the firmware routines. + */ + stp x19, x20, [sp, #32] + stp x21, x22, [sp, #48] + stp x23, x24, [sp, #64] + stp x25, x26, [sp, #80] + stp x27, x28, [sp, #96] + + adr_this_cpu x8, __efi_rt_asm_recover_sp, x9 + str x29, [x8] + + /* * We are lucky enough that no EFI runtime services take more than * 5 arguments, so all are passed in registers rather than via the * stack. @@ -31,7 +45,7 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) ldp x1, x2, [sp, #16] cmp x2, x18 - ldp x29, x30, [sp], #32 + ldp x29, x30, [sp], #112 b.ne 0f ret 0: @@ -45,3 +59,18 @@ SYM_FUNC_START(__efi_rt_asm_wrapper) mov x18, x2 b efi_handle_corrupted_x18 // tail call SYM_FUNC_END(__efi_rt_asm_wrapper) + +SYM_FUNC_START(__efi_rt_asm_recover) + ldr_this_cpu x8, __efi_rt_asm_recover_sp, x9 + mov sp, x8 + + ldp x0, x18, [sp, #16] + ldp x19, x20, [sp, #32] + ldp x21, x22, [sp, #48] + ldp x23, x24, [sp, #64] + ldp x25, x26, [sp, #80] + ldp x27, x28, [sp, #96] + ldp x29, x30, [sp], #112 + + b efi_handle_runtime_exception +SYM_FUNC_END(__efi_rt_asm_recover) diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index e1be6c429810..8d36e66a6e64 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -9,6 +9,7 @@ #include <linux/efi.h> #include <linux/init.h> +#include <linux/percpu.h> #include <asm/efi.h> @@ -128,3 +129,28 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f) pr_err_ratelimited(FW_BUG "register x18 corrupted by EFI %s\n", f); return s; } + +asmlinkage DEFINE_PER_CPU(u64, __efi_rt_asm_recover_sp); + +asmlinkage efi_status_t __efi_rt_asm_recover(void); + +asmlinkage efi_status_t efi_handle_runtime_exception(const char *f) +{ + pr_err(FW_BUG "Synchronous exception occurred in EFI runtime service %s()\n", f); + clear_bit(EFI_RUNTIME_SERVICES, &efi.flags); + return EFI_ABORTED; +} + +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) + return false; + + pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg); + add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK); + dump_stack(); + + regs->pc = (u64)__efi_rt_asm_recover; + return true; +} diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 9173fad279af..27369fa1c032 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -329,7 +329,8 @@ static void cortex_a76_erratum_1463225_svc_handler(void) __this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0); } -static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) +static __always_inline bool +cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs) { if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa)) return false; diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index b7557b25ed56..791d3de76771 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -13,6 +13,7 @@ #include <hyp/adjust_pc.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> +#include <asm/kvm_mmu.h> #if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__) #error Hypervisor code only! @@ -115,7 +116,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, new |= (old & PSR_C_BIT); new |= (old & PSR_V_BIT); - if (kvm_has_mte(vcpu->kvm)) + if (kvm_has_mte(kern_hyp_va(vcpu->kvm))) new |= PSR_TCO_BIT; new |= (old & PSR_DIT_BIT); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 6cbbb6c02f66..3330d1b76bdd 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -87,6 +87,17 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2); write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); + + if (cpus_have_final_cap(ARM64_SME)) { + sysreg_clear_set_s(SYS_HFGRTR_EL2, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK, + 0); + sysreg_clear_set_s(SYS_HFGWTR_EL2, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK, + 0); + } } static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) @@ -96,6 +107,15 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) write_sysreg(0, hstr_el2); if (kvm_arm_support_pmu_v3()) write_sysreg(0, pmuserenr_el0); + + if (cpus_have_final_cap(ARM64_SME)) { + sysreg_clear_set_s(SYS_HFGRTR_EL2, 0, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK); + sysreg_clear_set_s(SYS_HFGWTR_EL2, 0, + HFGxTR_EL2_nSMPRI_EL1_MASK | + HFGxTR_EL2_nTPIDR2_EL0_MASK); + } } static inline void ___activate_traps(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 1e78acf9662e..07f9dc9848ef 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -516,7 +516,7 @@ static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte) if (!kvm_pte_valid(pte)) return PKVM_NOPAGE; - return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); + return pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte)); } static int __hyp_check_page_state_range(u64 addr, u64 size, diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 8e9d49a964be..c2cb46ca4fb6 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -55,18 +55,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu) write_sysreg(val, cptr_el2); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); - if (cpus_have_final_cap(ARM64_SME)) { - val = read_sysreg_s(SYS_HFGRTR_EL2); - val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK); - write_sysreg_s(val, SYS_HFGRTR_EL2); - - val = read_sysreg_s(SYS_HFGWTR_EL2); - val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK); - write_sysreg_s(val, SYS_HFGWTR_EL2); - } - if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; @@ -110,20 +98,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); - if (cpus_have_final_cap(ARM64_SME)) { - u64 val; - - val = read_sysreg_s(SYS_HFGRTR_EL2); - val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK; - write_sysreg_s(val, SYS_HFGRTR_EL2); - - val = read_sysreg_s(SYS_HFGWTR_EL2); - val |= HFGxTR_EL2_nTPIDR2_EL0_MASK | - HFGxTR_EL2_nSMPRI_EL1_MASK; - write_sysreg_s(val, SYS_HFGWTR_EL2); - } - cptr = CPTR_EL2_DEFAULT; if (vcpu_has_sve(vcpu) && (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED)) cptr |= CPTR_EL2_TZ; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 7acb87eaa092..1a97391fedd2 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -63,10 +63,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu) __activate_traps_fpsimd32(vcpu); } - if (cpus_have_final_cap(ARM64_SME)) - write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2, - sctlr_el2); - write_sysreg(val, cpacr_el1); write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1); @@ -88,10 +84,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) */ asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); - if (cpus_have_final_cap(ARM64_SME)) - write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2, - sctlr_el2); - write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1); if (!arm64_kernel_unmapped_at_el0()) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 5b391490e045..3e9cf9826417 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -30,6 +30,7 @@ #include <asm/bug.h> #include <asm/cmpxchg.h> #include <asm/cpufeature.h> +#include <asm/efi.h> #include <asm/exception.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> @@ -391,6 +392,9 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr, msg = "paging request"; } + if (efi_runtime_fixup_exception(regs, msg)) + return; + die_kernel_fault(msg, addr, esr, regs); } diff --git a/arch/parisc/include/asm/hardware.h b/arch/parisc/include/asm/hardware.h index 9d3d7737c58b..a005ebc54779 100644 --- a/arch/parisc/include/asm/hardware.h +++ b/arch/parisc/include/asm/hardware.h @@ -10,12 +10,12 @@ #define SVERSION_ANY_ID PA_SVERSION_ANY_ID struct hp_hardware { - unsigned short hw_type:5; /* HPHW_xxx */ - unsigned short hversion; - unsigned long sversion:28; - unsigned short opt; - const char name[80]; /* The hardware description */ -}; + unsigned int hw_type:8; /* HPHW_xxx */ + unsigned int hversion:12; + unsigned int sversion:12; + unsigned char opt; + unsigned char name[59]; /* The hardware description */ +} __packed; struct parisc_device; diff --git a/arch/parisc/include/uapi/asm/pdc.h b/arch/parisc/include/uapi/asm/pdc.h index e794e143ec5f..7a90070136e8 100644 --- a/arch/parisc/include/uapi/asm/pdc.h +++ b/arch/parisc/include/uapi/asm/pdc.h @@ -363,20 +363,25 @@ #if !defined(__ASSEMBLY__) -/* flags of the device_path */ +/* flags for hardware_path */ #define PF_AUTOBOOT 0x80 #define PF_AUTOSEARCH 0x40 #define PF_TIMER 0x0F -struct device_path { /* page 1-69 */ - unsigned char flags; /* flags see above! */ - unsigned char bc[6]; /* bus converter routing info */ - unsigned char mod; - unsigned int layers[6];/* device-specific layer-info */ -} __attribute__((aligned(8))) ; +struct hardware_path { + unsigned char flags; /* see bit definitions below */ + signed char bc[6]; /* Bus Converter routing info to a specific */ + /* I/O adaptor (< 0 means none, > 63 resvd) */ + signed char mod; /* fixed field of specified module */ +}; + +struct pdc_module_path { /* page 1-69 */ + struct hardware_path path; + unsigned int layers[6]; /* device-specific info (ctlr #, unit # ...) */ +} __attribute__((aligned(8))); struct pz_device { - struct device_path dp; /* see above */ + struct pdc_module_path dp; /* see above */ /* struct iomod *hpa; */ unsigned int hpa; /* HPA base address */ /* char *spa; */ @@ -611,21 +616,6 @@ struct pdc_initiator { /* PDC_INITIATOR */ int mode; }; -struct hardware_path { - char flags; /* see bit definitions below */ - char bc[6]; /* Bus Converter routing info to a specific */ - /* I/O adaptor (< 0 means none, > 63 resvd) */ - char mod; /* fixed field of specified module */ -}; - -/* - * Device path specifications used by PDC. - */ -struct pdc_module_path { - struct hardware_path path; - unsigned int layers[6]; /* device-specific info (ctlr #, unit # ...) */ -}; - /* Only used on some pre-PA2.0 boxes */ struct pdc_memory_map { /* PDC_MEMORY_MAP */ unsigned long hpa; /* mod's register set address */ diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c index d126e78e101a..e7ee0c0c91d3 100644 --- a/arch/parisc/kernel/drivers.c +++ b/arch/parisc/kernel/drivers.c @@ -882,15 +882,13 @@ void __init walk_central_bus(void) &root); } -static void print_parisc_device(struct parisc_device *dev) +static __init void print_parisc_device(struct parisc_device *dev) { - char hw_path[64]; - static int count; + static int count __initdata; - print_pa_hwpath(dev, hw_path); - pr_info("%d. %s at %pap [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }", - ++count, dev->name, &(dev->hpa.start), hw_path, dev->id.hw_type, - dev->id.hversion_rev, dev->id.hversion, dev->id.sversion); + pr_info("%d. %s at %pap { type:%d, hv:%#x, sv:%#x, rev:%#x }", + ++count, dev->name, &(dev->hpa.start), dev->id.hw_type, + dev->id.hversion, dev->id.sversion, dev->id.hversion_rev); if (dev->num_addrs) { int k; @@ -1079,7 +1077,7 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data) -static int print_one_device(struct device * dev, void * data) +static __init int print_one_device(struct device * dev, void * data) { struct parisc_device * pdev = to_parisc_device(dev); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 699df27b0e2f..2ca5418457ed 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -147,6 +147,7 @@ config PPC select ARCH_MIGHT_HAVE_PC_SERIO select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT + select ARCH_SPLIT_ARG64 if PPC32 select ARCH_STACKWALK select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC_BOOK3S || PPC_8xx || 40x @@ -285,7 +286,7 @@ config PPC # config PPC_LONG_DOUBLE_128 - depends on PPC64 + depends on PPC64 && ALTIVEC def_bool $(success,test "$(shell,echo __LONG_DOUBLE_128__ | $(CC) -E -P -)" = 1) config PPC_BARRIER_NOSPEC diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h index a1142496cd58..6d51b007b59e 100644 --- a/arch/powerpc/include/asm/syscalls.h +++ b/arch/powerpc/include/asm/syscalls.h @@ -104,6 +104,13 @@ long sys_ppc_ftruncate64(unsigned int fd, u32 reg4, unsigned long len1, unsigned long len2); long sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2, size_t len, int advice); +long sys_ppc_sync_file_range2(int fd, unsigned int flags, + unsigned int offset1, + unsigned int offset2, + unsigned int nbytes1, + unsigned int nbytes2); +long sys_ppc_fallocate(int fd, int mode, u32 offset1, u32 offset2, + u32 len1, u32 len2); #endif #ifdef CONFIG_COMPAT long compat_sys_mmap2(unsigned long addr, size_t len, diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c index 1ab4a4d95aba..d451a8229223 100644 --- a/arch/powerpc/kernel/sys_ppc32.c +++ b/arch/powerpc/kernel/sys_ppc32.c @@ -112,7 +112,7 @@ PPC32_SYSCALL_DEFINE6(ppc32_fadvise64, advice); } -COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2, +PPC32_SYSCALL_DEFINE6(ppc_sync_file_range2, int, fd, unsigned int, flags, unsigned int, offset1, unsigned int, offset2, unsigned int, nbytes1, unsigned int, nbytes2) @@ -122,3 +122,14 @@ COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2, return ksys_sync_file_range(fd, offset, nbytes, flags); } + +#ifdef CONFIG_PPC32 +SYSCALL_DEFINE6(ppc_fallocate, + int, fd, int, mode, + u32, offset1, u32, offset2, u32, len1, u32, len2) +{ + return ksys_fallocate(fd, mode, + merge_64(offset1, offset2), + merge_64(len1, len2)); +} +#endif diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index e9e0df4f9a61..a0be127475b1 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -394,8 +394,11 @@ 305 common signalfd sys_signalfd compat_sys_signalfd 306 common timerfd_create sys_timerfd_create 307 common eventfd sys_eventfd -308 common sync_file_range2 sys_sync_file_range2 compat_sys_ppc_sync_file_range2 -309 nospu fallocate sys_fallocate compat_sys_fallocate +308 32 sync_file_range2 sys_ppc_sync_file_range2 compat_sys_ppc_sync_file_range2 +308 64 sync_file_range2 sys_sync_file_range2 +308 spu sync_file_range2 sys_sync_file_range2 +309 32 fallocate sys_ppc_fallocate compat_sys_fallocate +309 64 fallocate sys_fallocate 310 nospu subpage_prot sys_subpage_prot 311 32 timerfd_settime sys_timerfd_settime32 311 64 timerfd_settime sys_timerfd_settime diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 928dcf7a20d9..b8998cf0508a 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -34,6 +34,8 @@ #define VE_GET_PORT_NUM(e) ((e) >> 16) #define VE_IS_IO_STRING(e) ((e) & BIT(4)) +#define ATTR_SEPT_VE_DISABLE BIT(28) + /* * Wrapper for standard use of __tdx_hypercall with no output aside from * return code. @@ -98,10 +100,11 @@ static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); } -static u64 get_cc_mask(void) +static void tdx_parse_tdinfo(u64 *cc_mask) { struct tdx_module_output out; unsigned int gpa_width; + u64 td_attr; /* * TDINFO TDX module call is used to get the TD execution environment @@ -109,19 +112,27 @@ static u64 get_cc_mask(void) * information, etc. More details about the ABI can be found in TDX * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL * [TDG.VP.INFO]. + */ + tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); + + /* + * The highest bit of a guest physical address is the "sharing" bit. + * Set it for shared pages and clear it for private pages. * * The GPA width that comes out of this call is critical. TDX guests * can not meaningfully run without it. */ - tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); - gpa_width = out.rcx & GENMASK(5, 0); + *cc_mask = BIT_ULL(gpa_width - 1); /* - * The highest bit of a guest physical address is the "sharing" bit. - * Set it for shared pages and clear it for private pages. + * The kernel can not handle #VE's when accessing normal kernel + * memory. Ensure that no #VE will be delivered for accesses to + * TD-private memory. Only VMM-shared memory (MMIO) will #VE. */ - return BIT_ULL(gpa_width - 1); + td_attr = out.rdx; + if (!(td_attr & ATTR_SEPT_VE_DISABLE)) + panic("TD misconfiguration: SEPT_VE_DISABLE attibute must be set.\n"); } /* @@ -758,7 +769,7 @@ void __init tdx_early_init(void) setup_force_cpu_cap(X86_FEATURE_TDX_GUEST); cc_set_vendor(CC_VENDOR_INTEL); - cc_mask = get_cc_mask(); + tdx_parse_tdinfo(&cc_mask); cc_set_mask(cc_mask); /* diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a646a5f9a235..1b92bf05fd65 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4911,6 +4911,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = { INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000), + INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c), INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e), diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 7839507b3844..446d2833efa7 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -982,8 +982,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ @@ -1004,8 +1009,13 @@ struct event_constraint intel_spr_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), INTEL_PLD_CONSTRAINT(0x1cd, 0xfe), INTEL_PSD_CONSTRAINT(0x2cd, 0x1), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index fea544e5842a..a829492bca4c 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -619,12 +619,8 @@ static int rapl_check_hw_unit(struct rapl_model *rm) case RAPL_UNIT_QUIRK_INTEL_HSW: rapl_hw_unit[PERF_RAPL_RAM] = 16; break; - /* - * SPR shares the same DRAM domain energy unit as HSW, plus it - * also has a fixed energy unit for Psys domain. - */ + /* SPR uses a fixed energy unit for Psys domain. */ case RAPL_UNIT_QUIRK_INTEL_SPR: - rapl_hw_unit[PERF_RAPL_RAM] = 16; rapl_hw_unit[PERF_RAPL_PSYS] = 0; break; default: diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5d75fe229342..347707d459c6 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -107,6 +107,11 @@ #define INTEL_FAM6_SAPPHIRERAPIDS_X 0x8F /* Golden Cove */ +#define INTEL_FAM6_EMERALDRAPIDS_X 0xCF + +#define INTEL_FAM6_GRANITERAPIDS_X 0xAD +#define INTEL_FAM6_GRANITERAPIDS_D 0xAE + #define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */ #define INTEL_FAM6_ALDERLAKE_N 0xBE @@ -118,7 +123,7 @@ #define INTEL_FAM6_METEORLAKE 0xAC #define INTEL_FAM6_METEORLAKE_L 0xAA -/* "Small Core" Processors (Atom) */ +/* "Small Core" Processors (Atom/E-Core) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ #define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */ @@ -145,6 +150,10 @@ #define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */ #define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */ +#define INTEL_FAM6_SIERRAFOREST_X 0xAF + +#define INTEL_FAM6_GRANDRIDGE 0xB6 + /* Xeon Phi */ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index 59358d1bf880..fd2669b1cb2d 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -6,7 +6,7 @@ #ifndef _ASM_X86_SYSCALL_WRAPPER_H #define _ASM_X86_SYSCALL_WRAPPER_H -struct pt_regs; +#include <asm/ptrace.h> extern long __x64_sys_ni_syscall(const struct pt_regs *regs); extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 7065462378e2..62bc7a01cecc 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1133,11 +1133,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = max(entry->eax, 0x80000021); break; case 0x80000001: + entry->ebx &= ~GENMASK(27, 16); cpuid_entry_override(entry, CPUID_8000_0001_EDX); cpuid_entry_override(entry, CPUID_8000_0001_ECX); break; case 0x80000006: - /* L2 cache and TLB: pass through host info. */ + /* Drop reserved bits, pass host L2 cache and TLB info. */ + entry->edx &= ~GENMASK(17, 16); break; case 0x80000007: /* Advanced power management */ /* invariant TSC is CPUID.80000007H:EDX[8] */ @@ -1167,6 +1169,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) g_phys_as = phys_as; entry->eax = g_phys_as | (virt_as << 8); + entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); break; @@ -1186,6 +1189,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->ecx = entry->edx = 0; break; case 0x8000001a: + entry->eax &= GENMASK(2, 0); + entry->ebx = entry->ecx = entry->edx = 0; + break; case 0x8000001e: break; case 0x8000001F: @@ -1193,7 +1199,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = entry->edx = 0; } else { cpuid_entry_override(entry, CPUID_8000_001F_EAX); - + /* Clear NumVMPL since KVM does not support VMPL. */ + entry->ebx &= ~GENMASK(31, 12); /* * Enumerate '0' for "PA bits reduction", the adjusted * MAXPHYADDR is enumerated directly (see 0x80000008). @@ -1331,7 +1338,7 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, if (sanity_check_entries(entries, cpuid->nent, type)) return -EINVAL; - array.entries = kvcalloc(sizeof(struct kvm_cpuid_entry2), cpuid->nent, GFP_KERNEL); + array.entries = kvcalloc(cpuid->nent, sizeof(struct kvm_cpuid_entry2), GFP_KERNEL); if (!array.entries) return -ENOMEM; diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index cfed36aba2f7..c1390357126a 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -158,11 +158,16 @@ out: static int kvm_mmu_rmaps_stat_open(struct inode *inode, struct file *file) { struct kvm *kvm = inode->i_private; + int r; if (!kvm_get_kvm_safe(kvm)) return -ENOENT; - return single_open(file, kvm_mmu_rmaps_stat_show, kvm); + r = single_open(file, kvm_mmu_rmaps_stat_show, kvm); + if (r < 0) + kvm_put_kvm(kvm); + + return r; } static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 3b27622d4642..4a43261d25a2 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -791,8 +791,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ctxt->mode, linear); } -static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, - enum x86emul_mode mode) +static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) { ulong linear; int rc; @@ -802,41 +801,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst, if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; } +static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt) +{ + u64 efer; + struct desc_struct cs; + u16 selector; + u32 base3; + + ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); + + if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) { + /* Real mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_REAL; + return X86EMUL_CONTINUE; + } + + if (ctxt->eflags & X86_EFLAGS_VM) { + /* Protected/VM86 mode. cpu must not have long mode active */ + if (efer & EFER_LMA) + return X86EMUL_UNHANDLEABLE; + ctxt->mode = X86EMUL_MODE_VM86; + return X86EMUL_CONTINUE; + } + + if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS)) + return X86EMUL_UNHANDLEABLE; + + if (efer & EFER_LMA) { + if (cs.l) { + /* Proper long mode */ + ctxt->mode = X86EMUL_MODE_PROT64; + } else if (cs.d) { + /* 32 bit compatibility mode*/ + ctxt->mode = X86EMUL_MODE_PROT32; + } else { + ctxt->mode = X86EMUL_MODE_PROT16; + } + } else { + /* Legacy 32 bit / 16 bit mode */ + ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; + } + + return X86EMUL_CONTINUE; +} + static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst) { - return assign_eip(ctxt, dst, ctxt->mode); + return assign_eip(ctxt, dst); } -static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst, - const struct desc_struct *cs_desc) +static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst) { - enum x86emul_mode mode = ctxt->mode; - int rc; + int rc = emulator_recalc_and_set_mode(ctxt); -#ifdef CONFIG_X86_64 - if (ctxt->mode >= X86EMUL_MODE_PROT16) { - if (cs_desc->l) { - u64 efer = 0; + if (rc != X86EMUL_CONTINUE) + return rc; - ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); - if (efer & EFER_LMA) - mode = X86EMUL_MODE_PROT64; - } else - mode = X86EMUL_MODE_PROT32; /* temporary value */ - } -#endif - if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32) - mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - rc = assign_eip(ctxt, dst, mode); - if (rc == X86EMUL_CONTINUE) - ctxt->mode = mode; - return rc; + return assign_eip(ctxt, dst); } static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel) @@ -2172,7 +2201,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2250,7 +2279,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) &new_desc); if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, eip, &new_desc); + rc = assign_eip_far(ctxt, eip); /* Error handling is not implemented. */ if (rc != X86EMUL_CONTINUE) return X86EMUL_UNHANDLEABLE; @@ -2432,7 +2461,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED; ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0); - for (i = 0; i < NR_EMULATOR_GPRS; i++) + for (i = 0; i < 8; i++) *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4); val = GET_SMSTATE(u32, smstate, 0x7fcc); @@ -2489,7 +2518,7 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u16 selector; int i, r; - for (i = 0; i < NR_EMULATOR_GPRS; i++) + for (i = 0; i < 16; i++) *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8); ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78); @@ -2633,7 +2662,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt) * those side effects need to be explicitly handled for both success * and shutdown. */ - return X86EMUL_CONTINUE; + return emulator_recalc_and_set_mode(ctxt); emulate_shutdown: ctxt->ops->triple_fault(ctxt); @@ -2876,6 +2905,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt) ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS); ctxt->_eip = rdx; + ctxt->mode = usermode; *reg_write(ctxt, VCPU_REGS_RSP) = rcx; return X86EMUL_CONTINUE; @@ -3469,7 +3499,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; - rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); + rc = assign_eip_far(ctxt, ctxt->src.val); if (rc != X86EMUL_CONTINUE) goto fail; @@ -3611,11 +3641,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt) static int em_cr_write(struct x86_emulate_ctxt *ctxt) { - if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) + int cr_num = ctxt->modrm_reg; + int r; + + if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val)) return emulate_gp(ctxt, 0); /* Disable writeback. */ ctxt->dst.type = OP_NONE; + + if (cr_num == 0) { + /* + * CR0 write might have updated CR0.PE and/or CR0.PG + * which can affect the cpu's execution mode. + */ + r = emulator_recalc_and_set_mode(ctxt); + if (r != X86EMUL_CONTINUE) + return r; + } + return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 87c4e46daf37..07254314f3dd 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -24,8 +24,6 @@ extern int __read_mostly pt_mode; #define PMU_CAP_FW_WRITES (1ULL << 13) #define PMU_CAP_LBR_FMT 0x3f -#define DEBUGCTLMSR_LBR_MASK (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) - struct nested_vmx_msrs { /* * We only store the "true" versions of the VMX capability MSRs. We @@ -400,6 +398,7 @@ static inline bool vmx_pebs_supported(void) static inline u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PMU_CAP_FW_WRITES; + struct x86_pmu_lbr lbr; u64 host_perf_cap = 0; if (!enable_pmu) @@ -408,7 +407,8 @@ static inline u64 vmx_get_perf_capabilities(void) if (boot_cpu_has(X86_FEATURE_PDCM)) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); - perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + if (x86_perf_get_lbr(&lbr) >= 0 && lbr.nr) + perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; @@ -419,19 +419,6 @@ static inline u64 vmx_get_perf_capabilities(void) return perf_cap; } -static inline u64 vmx_supported_debugctl(void) -{ - u64 debugctl = 0; - - if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT)) - debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - - if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) - debugctl |= DEBUGCTLMSR_LBR_MASK; - - return debugctl; -} - static inline bool cpu_has_notify_vmexit(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 9dba04b6b019..63247c57c72c 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -2021,15 +2021,17 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, return (unsigned long)data; } -static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu) +static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated) { - u64 debugctl = vmx_supported_debugctl(); + u64 debugctl = 0; - if (!intel_pmu_lbr_is_enabled(vcpu)) - debugctl &= ~DEBUGCTLMSR_LBR_MASK; + if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && + (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) + debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) - debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT; + if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) && + (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) + debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; return debugctl; } @@ -2103,7 +2105,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmcs_writel(GUEST_SYSENTER_ESP, data); break; case MSR_IA32_DEBUGCTLMSR: { - u64 invalid = data & ~vcpu_supported_debugctl(vcpu); + u64 invalid; + + 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", @@ -8263,6 +8267,11 @@ static __init int hardware_setup(void) if (!cpu_has_virtual_nmis()) enable_vnmi = 0; +#ifdef CONFIG_X86_SGX_KVM + if (!cpu_has_vmx_encls_vmexit()) + enable_sgx = false; +#endif + /* * set_apic_access_page_addr() is used to reload apic access * page upon invalidation. No need to do anything if not diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9cf1ba865562..5f5eb577d583 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2315,11 +2315,11 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, /* we verify if the enable bit is set... */ if (system_time & 1) { - kvm_gfn_to_pfn_cache_init(vcpu->kvm, &vcpu->arch.pv_time, vcpu, - KVM_HOST_USES_PFN, system_time & ~1ULL, - sizeof(struct pvclock_vcpu_time_info)); + kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu, + KVM_HOST_USES_PFN, system_time & ~1ULL, + sizeof(struct pvclock_vcpu_time_info)); } else { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); } return; @@ -3388,7 +3388,7 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); vcpu->arch.time = 0; } @@ -10044,7 +10044,20 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, kvm_x86_ops.nested_ops->has_events(vcpu)) *req_immediate_exit = true; - WARN_ON(kvm_is_exception_pending(vcpu)); + /* + * KVM must never queue a new exception while injecting an event; KVM + * is done emulating and should only propagate the to-be-injected event + * to the VMCS/VMCB. Queueing a new exception can put the vCPU into an + * infinite loop as KVM will bail from VM-Enter to inject the pending + * exception and start the cycle all over. + * + * Exempt triple faults as they have special handling and won't put the + * vCPU into an infinite loop. Triple fault can be queued when running + * VMX without unrestricted guest, as that requires KVM to emulate Real + * Mode events (see kvm_inject_realmode_interrupt()). + */ + WARN_ON_ONCE(vcpu->arch.exception.pending || + vcpu->arch.exception_vmexit.pending); return 0; out: @@ -10391,7 +10404,10 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm, kvm->arch.apicv_inhibit_reasons = new; if (new) { unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE); + int idx = srcu_read_lock(&kvm->srcu); + kvm_zap_gfn_range(kvm, gfn, gfn+1); + srcu_read_unlock(&kvm->srcu, idx); } } else { kvm->arch.apicv_inhibit_reasons = new; @@ -11816,6 +11832,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; + kvm_gpc_init(&vcpu->arch.pv_time); + if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 93c628d3e3a9..2dae413bd62a 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -42,13 +42,13 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) int idx = srcu_read_lock(&kvm->srcu); if (gfn == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(kvm, gpc); + kvm_gpc_deactivate(kvm, gpc); goto out; } do { - ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, KVM_HOST_USES_PFN, - gpa, PAGE_SIZE); + ret = kvm_gpc_activate(kvm, gpc, NULL, KVM_HOST_USES_PFN, gpa, + PAGE_SIZE); if (ret) goto out; @@ -554,15 +554,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) offsetof(struct compat_vcpu_info, time)); if (data->u.gpa == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); r = 0; break; } - r = kvm_gfn_to_pfn_cache_init(vcpu->kvm, - &vcpu->arch.xen.vcpu_info_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct vcpu_info)); + r = kvm_gpc_activate(vcpu->kvm, + &vcpu->arch.xen.vcpu_info_cache, NULL, + KVM_HOST_USES_PFN, data->u.gpa, + sizeof(struct vcpu_info)); if (!r) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -570,16 +570,16 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: if (data->u.gpa == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache); + kvm_gpc_deactivate(vcpu->kvm, + &vcpu->arch.xen.vcpu_time_info_cache); r = 0; break; } - r = kvm_gfn_to_pfn_cache_init(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct pvclock_vcpu_time_info)); + r = kvm_gpc_activate(vcpu->kvm, + &vcpu->arch.xen.vcpu_time_info_cache, + NULL, KVM_HOST_USES_PFN, data->u.gpa, + sizeof(struct pvclock_vcpu_time_info)); if (!r) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); break; @@ -590,16 +590,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; } if (data->u.gpa == GPA_INVALID) { - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.runstate_cache); + kvm_gpc_deactivate(vcpu->kvm, + &vcpu->arch.xen.runstate_cache); r = 0; break; } - r = kvm_gfn_to_pfn_cache_init(vcpu->kvm, - &vcpu->arch.xen.runstate_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct vcpu_runstate_info)); + r = kvm_gpc_activate(vcpu->kvm, &vcpu->arch.xen.runstate_cache, + NULL, KVM_HOST_USES_PFN, data->u.gpa, + sizeof(struct vcpu_runstate_info)); break; case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT: @@ -1667,18 +1666,18 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, case EVTCHNSTAT_ipi: /* IPI must map back to the same port# */ if (data->u.evtchn.deliver.port.port != data->u.evtchn.send_port) - goto out; /* -EINVAL */ + goto out_noeventfd; /* -EINVAL */ break; case EVTCHNSTAT_interdomain: if (data->u.evtchn.deliver.port.port) { if (data->u.evtchn.deliver.port.port >= max_evtchn_port(kvm)) - goto out; /* -EINVAL */ + goto out_noeventfd; /* -EINVAL */ } else { eventfd = eventfd_ctx_fdget(data->u.evtchn.deliver.eventfd.fd); if (IS_ERR(eventfd)) { ret = PTR_ERR(eventfd); - goto out; + goto out_noeventfd; } } break; @@ -1718,6 +1717,7 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm, out: if (eventfd) eventfd_ctx_put(eventfd); +out_noeventfd: kfree(evtchnfd); return ret; } @@ -1816,7 +1816,12 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu) { vcpu->arch.xen.vcpu_id = vcpu->vcpu_idx; vcpu->arch.xen.poll_evtchn = 0; + timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0); + + kvm_gpc_init(&vcpu->arch.xen.runstate_cache); + kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache); } void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) @@ -1824,18 +1829,17 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) if (kvm_xen_timer_enabled(vcpu)) kvm_xen_stop_timer(vcpu); - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.runstate_cache); - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.vcpu_info_cache); - kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.runstate_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache); + del_timer_sync(&vcpu->arch.xen.poll_timer); } void kvm_xen_init_vm(struct kvm *kvm) { idr_init(&kvm->arch.xen.evtchn_ports); + kvm_gpc_init(&kvm->arch.xen.shinfo_cache); } void kvm_xen_destroy_vm(struct kvm *kvm) @@ -1843,7 +1847,7 @@ void kvm_xen_destroy_vm(struct kvm *kvm) struct evtchnfd *evtchnfd; int i; - kvm_gfn_to_pfn_cache_destroy(kvm, &kvm->arch.xen.shinfo_cache); + kvm_gpc_deactivate(kvm, &kvm->arch.xen.shinfo_cache); idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) { if (!evtchnfd->deliver.port.port) diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index 68aff1382872..246d67dab510 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -302,7 +302,7 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read) static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read, bool *emul) { - int type, index; + int type, index = 0; if (is_amd_pmu_msr(msr)) *emul = xen_amd_pmu_emulate(msr, val, is_read); diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index cfa99e8f054b..4f4309500559 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -910,17 +910,9 @@ static int register_callback(unsigned type, const void *func) void xen_enable_sysenter(void) { - int ret; - unsigned sysenter_feature; - - sysenter_feature = X86_FEATURE_SYSENTER32; - - if (!boot_cpu_has(sysenter_feature)) - return; - - ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat); - if(ret != 0) - setup_clear_cpu_cap(sysenter_feature); + if (cpu_feature_enabled(X86_FEATURE_SYSENTER32) && + register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat)) + setup_clear_cpu_cap(X86_FEATURE_SYSENTER32); } void xen_enable_syscall(void) @@ -934,12 +926,9 @@ void xen_enable_syscall(void) mechanism for syscalls. */ } - if (boot_cpu_has(X86_FEATURE_SYSCALL32)) { - ret = register_callback(CALLBACKTYPE_syscall32, - xen_entry_SYSCALL_compat); - if (ret != 0) - setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); - } + if (cpu_feature_enabled(X86_FEATURE_SYSCALL32) && + register_callback(CALLBACKTYPE_syscall32, xen_entry_SYSCALL_compat)) + setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); } static void __init xen_pvmmu_arch_setup(void) diff --git a/block/blk-mq.c b/block/blk-mq.c index 75c8296b6feb..6a789cda68a5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1262,6 +1262,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) (!blk_queue_nomerges(rq->q) && blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) { blk_mq_flush_plug_list(plug, false); + last = NULL; trace_block_plug(rq->q); } @@ -4193,9 +4194,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, return 0; err_hctxs: - xa_destroy(&q->hctx_table); - q->nr_hw_queues = 0; - blk_mq_sysfs_deinit(q); + blk_mq_release(q); err_poll: blk_stat_free_callback(q->poll_cb); q->poll_cb = NULL; diff --git a/block/genhd.c b/block/genhd.c index fee90eb98b4a..0f9769db2de8 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -527,6 +527,7 @@ out_unregister_bdi: bdi_unregister(disk->bdi); out_unregister_queue: blk_unregister_queue(disk); + rq_qos_exit(disk->queue); out_put_slave_dir: kobject_put(disk->slave_dir); out_put_holder_dir: diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c index 3b818ab186be..1f4fc5f8a819 100644 --- a/drivers/acpi/numa/srat.c +++ b/drivers/acpi/numa/srat.c @@ -327,6 +327,7 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header, pr_warn("ACPI NUMA: Failed to add memblk for CFMWS node %d [mem %#llx-%#llx]\n", node, start, end); } + node_set(node, numa_nodes_parsed); /* Set the next available fake_pxm value */ (*fake_pxm)++; diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c index f8a2cbdc0ce2..d7d3f1669d4c 100644 --- a/drivers/acpi/x86/utils.c +++ b/drivers/acpi/x86/utils.c @@ -219,6 +219,12 @@ static const struct dmi_system_id force_storage_d3_dmi[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 14 7425 2-in-1"), } }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 16 5625"), + } + }, {} }; diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c index 0a8bf09a5c19..03c580625c2c 100644 --- a/drivers/ata/pata_legacy.c +++ b/drivers/ata/pata_legacy.c @@ -315,9 +315,10 @@ static void pdc20230_set_piomode(struct ata_port *ap, struct ata_device *adev) outb(inb(0x1F4) & 0x07, 0x1F4); rt = inb(0x1F3); - rt &= 0x07 << (3 * adev->devno); + rt &= ~(0x07 << (3 * !adev->devno)); if (pio) - rt |= (1 + 3 * pio) << (3 * adev->devno); + rt |= (1 + 3 * pio) << (3 * !adev->devno); + outb(rt, 0x1F3); udelay(100); outb(inb(0x1F2) | 0x01, 0x1F2); diff --git a/drivers/ata/pata_palmld.c b/drivers/ata/pata_palmld.c index 400e65190904..51caa2a427dd 100644 --- a/drivers/ata/pata_palmld.c +++ b/drivers/ata/pata_palmld.c @@ -63,8 +63,8 @@ static int palmld_pata_probe(struct platform_device *pdev) /* remap drive's physical memory address */ mem = devm_platform_ioremap_resource(pdev, 0); - if (!mem) - return -ENOMEM; + if (IS_ERR(mem)) + return PTR_ERR(mem); /* request and activate power and reset GPIOs */ lda->power = devm_gpiod_get(dev, "power", GPIOD_OUT_HIGH); diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index db1b4b202646..a41145d52de9 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -408,6 +408,12 @@ config BLK_DEV_UBLK definition isn't finalized yet, and might change according to future requirement, so mark is as experimental now. + Say Y if you want to get better performance because task_work_add() + can be used in IO path for replacing io_uring cmd, which will become + shared between IO tasks and ubq daemon, meantime task_work_add() can + can handle batch more effectively, but task_work_add() isn't exported + for module, so ublk has to be built to kernel. + source "drivers/block/rnbd/Kconfig" endif # BLK_DEV diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 5afce6ffaadf..f96cb01e9604 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -57,11 +57,14 @@ #define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD) struct ublk_rq_data { - struct callback_head work; + union { + struct callback_head work; + struct llist_node node; + }; }; struct ublk_uring_cmd_pdu { - struct request *req; + struct ublk_queue *ubq; }; /* @@ -119,6 +122,8 @@ struct ublk_queue { struct task_struct *ubq_daemon; char *io_cmd_buf; + struct llist_head io_cmds; + unsigned long io_addr; /* mapped vm address */ unsigned int max_io_sz; bool force_abort; @@ -764,8 +769,12 @@ static inline void __ublk_rq_task_work(struct request *req) static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) { struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + struct ublk_queue *ubq = pdu->ubq; + struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); + struct ublk_rq_data *data; - __ublk_rq_task_work(pdu->req); + llist_for_each_entry(data, io_cmds, node) + __ublk_rq_task_work(blk_mq_rq_from_pdu(data)); } static void ublk_rq_task_work_fn(struct callback_head *work) @@ -777,6 +786,54 @@ static void ublk_rq_task_work_fn(struct callback_head *work) __ublk_rq_task_work(req); } +static void ublk_submit_cmd(struct ublk_queue *ubq, const struct request *rq) +{ + struct ublk_io *io = &ubq->ios[rq->tag]; + + /* + * If the check pass, we know that this is a re-issued request aborted + * previously in monitor_work because the ubq_daemon(cmd's task) is + * PF_EXITING. We cannot call io_uring_cmd_complete_in_task() anymore + * because this ioucmd's io_uring context may be freed now if no inflight + * ioucmd exists. Otherwise we may cause null-deref in ctx->fallback_work. + * + * Note: monitor_work sets UBLK_IO_FLAG_ABORTED and ends this request(releasing + * the tag). Then the request is re-started(allocating the tag) and we are here. + * Since releasing/allocating a tag implies smp_mb(), finding UBLK_IO_FLAG_ABORTED + * guarantees that here is a re-issued request aborted previously. + */ + if (unlikely(io->flags & UBLK_IO_FLAG_ABORTED)) { + struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); + struct ublk_rq_data *data; + + llist_for_each_entry(data, io_cmds, node) + __ublk_abort_rq(ubq, blk_mq_rq_from_pdu(data)); + } else { + struct io_uring_cmd *cmd = io->cmd; + struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); + + pdu->ubq = ubq; + io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); + } +} + +static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq, + bool last) +{ + struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); + + if (ublk_can_use_task_work(ubq)) { + enum task_work_notify_mode notify_mode = last ? + TWA_SIGNAL_NO_IPI : TWA_NONE; + + if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode)) + __ublk_abort_rq(ubq, rq); + } else { + if (llist_add(&data->node, &ubq->io_cmds)) + ublk_submit_cmd(ubq, rq); + } +} + static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -788,6 +845,7 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, res = ublk_setup_iod(ubq, rq); if (unlikely(res != BLK_STS_OK)) return BLK_STS_IOERR; + /* With recovery feature enabled, force_abort is set in * ublk_stop_dev() before calling del_gendisk(). We have to * abort all requeued and new rqs here to let del_gendisk() @@ -803,41 +861,11 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(bd->rq); if (unlikely(ubq_daemon_is_dying(ubq))) { - fail: __ublk_abort_rq(ubq, rq); return BLK_STS_OK; } - if (ublk_can_use_task_work(ubq)) { - struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq); - enum task_work_notify_mode notify_mode = bd->last ? - TWA_SIGNAL_NO_IPI : TWA_NONE; - - if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode)) - goto fail; - } else { - struct ublk_io *io = &ubq->ios[rq->tag]; - struct io_uring_cmd *cmd = io->cmd; - struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); - - /* - * If the check pass, we know that this is a re-issued request aborted - * previously in monitor_work because the ubq_daemon(cmd's task) is - * PF_EXITING. We cannot call io_uring_cmd_complete_in_task() anymore - * because this ioucmd's io_uring context may be freed now if no inflight - * ioucmd exists. Otherwise we may cause null-deref in ctx->fallback_work. - * - * Note: monitor_work sets UBLK_IO_FLAG_ABORTED and ends this request(releasing - * the tag). Then the request is re-started(allocating the tag) and we are here. - * Since releasing/allocating a tag implies smp_mb(), finding UBLK_IO_FLAG_ABORTED - * guarantees that here is a re-issued request aborted previously. - */ - if ((io->flags & UBLK_IO_FLAG_ABORTED)) - goto fail; - - pdu->req = rq; - io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); - } + ublk_queue_cmd(ubq, rq, bd->last); return BLK_STS_OK; } @@ -1164,22 +1192,12 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) } static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, - int tag, struct io_uring_cmd *cmd) + int tag) { struct ublk_queue *ubq = ublk_get_queue(ub, q_id); struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag); - if (ublk_can_use_task_work(ubq)) { - struct ublk_rq_data *data = blk_mq_rq_to_pdu(req); - - /* should not fail since we call it just in ubq->ubq_daemon */ - task_work_add(ubq->ubq_daemon, &data->work, TWA_SIGNAL_NO_IPI); - } else { - struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); - - pdu->req = req; - io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb); - } + ublk_queue_cmd(ubq, req, true); } static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) @@ -1267,7 +1285,7 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) io->addr = ub_cmd->addr; io->cmd = cmd; io->flags |= UBLK_IO_FLAG_ACTIVE; - ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag, cmd); + ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag); break; default: goto out; @@ -1658,6 +1676,9 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) */ ub->dev_info.flags &= UBLK_F_ALL; + if (!IS_BUILTIN(CONFIG_BLK_DEV_UBLK)) + ub->dev_info.flags |= UBLK_F_URING_CMD_COMP_IN_TASK; + /* We are not ready to support zero copy */ ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY; diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 67c21263f9e0..fd281d439505 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -219,7 +219,7 @@ static void virtbt_rx_work(struct work_struct *work) if (!skb) return; - skb->len = len; + skb_put(skb, len); virtbt_rx_handle(vbt, skb); if (virtbt_add_inbuf(vbt) < 0) diff --git a/drivers/clk/clk-renesas-pcie.c b/drivers/clk/clk-renesas-pcie.c index 4f5df1fc74b4..e6247141d0c0 100644 --- a/drivers/clk/clk-renesas-pcie.c +++ b/drivers/clk/clk-renesas-pcie.c @@ -90,13 +90,66 @@ static const struct regmap_access_table rs9_writeable_table = { .n_yes_ranges = ARRAY_SIZE(rs9_writeable_ranges), }; +static int rs9_regmap_i2c_write(void *context, + unsigned int reg, unsigned int val) +{ + struct i2c_client *i2c = context; + const u8 data[3] = { reg, 1, val }; + const int count = ARRAY_SIZE(data); + int ret; + + ret = i2c_master_send(i2c, data, count); + if (ret == count) + return 0; + else if (ret < 0) + return ret; + else + return -EIO; +} + +static int rs9_regmap_i2c_read(void *context, + unsigned int reg, unsigned int *val) +{ + struct i2c_client *i2c = context; + struct i2c_msg xfer[2]; + u8 txdata = reg; + u8 rxdata[2]; + int ret; + + xfer[0].addr = i2c->addr; + xfer[0].flags = 0; + xfer[0].len = 1; + xfer[0].buf = (void *)&txdata; + + xfer[1].addr = i2c->addr; + xfer[1].flags = I2C_M_RD; + xfer[1].len = 2; + xfer[1].buf = (void *)rxdata; + + ret = i2c_transfer(i2c->adapter, xfer, 2); + if (ret < 0) + return ret; + if (ret != 2) + return -EIO; + + /* + * Byte 0 is transfer length, which is always 1 due + * to BCP register programming to 1 in rs9_probe(), + * ignore it and use data from Byte 1. + */ + *val = rxdata[1]; + return 0; +} + static const struct regmap_config rs9_regmap_config = { .reg_bits = 8, .val_bits = 8, - .cache_type = REGCACHE_FLAT, - .max_register = 0x8, + .cache_type = REGCACHE_NONE, + .max_register = RS9_REG_BCP, .rd_table = &rs9_readable_table, .wr_table = &rs9_writeable_table, + .reg_write = rs9_regmap_i2c_write, + .reg_read = rs9_regmap_i2c_read, }; static int rs9_get_output_config(struct rs9_driver_data *rs9, int idx) @@ -242,11 +295,17 @@ static int rs9_probe(struct i2c_client *client) return ret; } - rs9->regmap = devm_regmap_init_i2c(client, &rs9_regmap_config); + rs9->regmap = devm_regmap_init(&client->dev, NULL, + client, &rs9_regmap_config); if (IS_ERR(rs9->regmap)) return dev_err_probe(&client->dev, PTR_ERR(rs9->regmap), "Failed to allocate register map\n"); + /* Always read back 1 Byte via I2C */ + ret = regmap_write(rs9->regmap, RS9_REG_BCP, 1); + if (ret < 0) + return ret; + /* Register clock */ for (i = 0; i < rs9->chip_info->num_clks; i++) { snprintf(name, 5, "DIF%d", i); diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index c3c3f8c07258..57b83665e5c3 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1459,10 +1459,14 @@ static void clk_core_init_rate_req(struct clk_core * const core, { struct clk_core *parent; - if (WARN_ON(!core || !req)) + if (WARN_ON(!req)) return; memset(req, 0, sizeof(*req)); + req->max_rate = ULONG_MAX; + + if (!core) + return; req->rate = rate; clk_core_get_boundaries(core, &req->min_rate, &req->max_rate); diff --git a/drivers/clk/mediatek/clk-mt8195-topckgen.c b/drivers/clk/mediatek/clk-mt8195-topckgen.c index 8cbab5ca2e58..1e016329c1d2 100644 --- a/drivers/clk/mediatek/clk-mt8195-topckgen.c +++ b/drivers/clk/mediatek/clk-mt8195-topckgen.c @@ -1270,8 +1270,10 @@ static int clk_mt8195_topck_probe(struct platform_device *pdev) hw = devm_clk_hw_register_mux(&pdev->dev, "mfg_ck_fast_ref", mfg_fast_parents, ARRAY_SIZE(mfg_fast_parents), CLK_SET_RATE_PARENT, (base + 0x250), 8, 1, 0, &mt8195_clk_lock); - if (IS_ERR(hw)) + if (IS_ERR(hw)) { + r = PTR_ERR(hw); goto unregister_muxes; + } top_clk_data->hws[CLK_TOP_MFG_CK_FAST_REF] = hw; r = clk_mt8195_reg_mfg_mux_notifier(&pdev->dev, diff --git a/drivers/clk/qcom/gcc-sc7280.c b/drivers/clk/qcom/gcc-sc7280.c index 8afb7575e712..46d41ebce2b0 100644 --- a/drivers/clk/qcom/gcc-sc7280.c +++ b/drivers/clk/qcom/gcc-sc7280.c @@ -3467,6 +3467,7 @@ static int gcc_sc7280_probe(struct platform_device *pdev) regmap_update_bits(regmap, 0x28004, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x28014, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x71004, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x7100C, BIT(13), BIT(13)); ret = qcom_cc_register_rcg_dfs(regmap, gcc_dfs_clocks, ARRAY_SIZE(gcc_dfs_clocks)); diff --git a/drivers/clk/qcom/gpucc-sc7280.c b/drivers/clk/qcom/gpucc-sc7280.c index 9a832f2bcf49..1490cd45a654 100644 --- a/drivers/clk/qcom/gpucc-sc7280.c +++ b/drivers/clk/qcom/gpucc-sc7280.c @@ -463,6 +463,7 @@ static int gpu_cc_sc7280_probe(struct platform_device *pdev) */ regmap_update_bits(regmap, 0x1170, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x1098, BIT(0), BIT(0)); + regmap_update_bits(regmap, 0x1098, BIT(13), BIT(13)); return qcom_cc_really_probe(pdev, &gpu_cc_sc7280_desc, regmap); } diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c index 9641122133b5..d5b325e3c539 100644 --- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c +++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c @@ -47,6 +47,7 @@ enum clk_ids { CLK_S0_VIO, CLK_S0_VC, CLK_S0_HSC, + CLK_SASYNCPER, CLK_SV_VIP, CLK_SV_IR, CLK_SDSRC, @@ -84,6 +85,7 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = { DEF_FIXED(".s0_vio", CLK_S0_VIO, CLK_PLL1_DIV2, 2, 1), DEF_FIXED(".s0_vc", CLK_S0_VC, CLK_PLL1_DIV2, 2, 1), DEF_FIXED(".s0_hsc", CLK_S0_HSC, CLK_PLL1_DIV2, 2, 1), + DEF_FIXED(".sasyncper", CLK_SASYNCPER, CLK_PLL5_DIV4, 3, 1), DEF_FIXED(".sv_vip", CLK_SV_VIP, CLK_PLL1, 5, 1), DEF_FIXED(".sv_ir", CLK_SV_IR, CLK_PLL1, 5, 1), DEF_BASE(".sdsrc", CLK_SDSRC, CLK_TYPE_GEN4_SDSRC, CLK_PLL5), @@ -128,6 +130,9 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = { DEF_FIXED("s0d4_hsc", R8A779G0_CLK_S0D4_HSC, CLK_S0_HSC, 4, 1), DEF_FIXED("cl16m_hsc", R8A779G0_CLK_CL16M_HSC, CLK_S0_HSC, 48, 1), DEF_FIXED("s0d2_cc", R8A779G0_CLK_S0D2_CC, CLK_S0, 2, 1), + DEF_FIXED("sasyncperd1",R8A779G0_CLK_SASYNCPERD1, CLK_SASYNCPER,1, 1), + DEF_FIXED("sasyncperd2",R8A779G0_CLK_SASYNCPERD2, CLK_SASYNCPER,2, 1), + DEF_FIXED("sasyncperd4",R8A779G0_CLK_SASYNCPERD4, CLK_SASYNCPER,4, 1), DEF_FIXED("svd1_ir", R8A779G0_CLK_SVD1_IR, CLK_SV_IR, 1, 1), DEF_FIXED("svd2_ir", R8A779G0_CLK_SVD2_IR, CLK_SV_IR, 2, 1), DEF_FIXED("svd1_vip", R8A779G0_CLK_SVD1_VIP, CLK_SV_VIP, 1, 1), @@ -153,10 +158,10 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = { DEF_MOD("avb0", 211, R8A779G0_CLK_S0D4_HSC), DEF_MOD("avb1", 212, R8A779G0_CLK_S0D4_HSC), DEF_MOD("avb2", 213, R8A779G0_CLK_S0D4_HSC), - DEF_MOD("hscif0", 514, R8A779G0_CLK_S0D3_PER), - DEF_MOD("hscif1", 515, R8A779G0_CLK_S0D3_PER), - DEF_MOD("hscif2", 516, R8A779G0_CLK_S0D3_PER), - DEF_MOD("hscif3", 517, R8A779G0_CLK_S0D3_PER), + DEF_MOD("hscif0", 514, R8A779G0_CLK_SASYNCPERD1), + DEF_MOD("hscif1", 515, R8A779G0_CLK_SASYNCPERD1), + DEF_MOD("hscif2", 516, R8A779G0_CLK_SASYNCPERD1), + DEF_MOD("hscif3", 517, R8A779G0_CLK_SASYNCPERD1), DEF_MOD("i2c0", 518, R8A779G0_CLK_S0D6_PER), DEF_MOD("i2c1", 519, R8A779G0_CLK_S0D6_PER), DEF_MOD("i2c2", 520, R8A779G0_CLK_S0D6_PER), diff --git a/drivers/clk/sifive/Kconfig b/drivers/clk/sifive/Kconfig index 9132c3c4aa86..b7fde0aadfcb 100644 --- a/drivers/clk/sifive/Kconfig +++ b/drivers/clk/sifive/Kconfig @@ -2,7 +2,8 @@ menuconfig CLK_SIFIVE bool "SiFive SoC driver support" - depends on RISCV || COMPILE_TEST + depends on SOC_SIFIVE || COMPILE_TEST + default SOC_SIFIVE help SoC drivers for SiFive Linux-capable SoCs. @@ -10,6 +11,7 @@ if CLK_SIFIVE config CLK_SIFIVE_PRCI bool "PRCI driver for SiFive SoCs" + default SOC_SIFIVE select RESET_CONTROLLER select RESET_SIMPLE select CLK_ANALOGBITS_WRPLL_CLN28HPC diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 16176b9278b4..0c90f13870a4 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -174,7 +174,7 @@ int cxl_mbox_send_cmd(struct cxl_dev_state *cxlds, u16 opcode, void *in, }; int rc; - if (out_size > cxlds->payload_size) + if (in_size > cxlds->payload_size || out_size > cxlds->payload_size) return -E2BIG; rc = cxlds->mbox_send(cxlds, &mbox_cmd); diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c index 1d12a8206444..36aa5070d902 100644 --- a/drivers/cxl/core/pmem.c +++ b/drivers/cxl/core/pmem.c @@ -188,6 +188,7 @@ static void cxl_nvdimm_release(struct device *dev) { struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev); + xa_destroy(&cxl_nvd->pmem_regions); kfree(cxl_nvd); } @@ -230,6 +231,7 @@ static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_memdev *cxlmd) dev = &cxl_nvd->dev; cxl_nvd->cxlmd = cxlmd; + xa_init(&cxl_nvd->pmem_regions); device_initialize(dev); lockdep_set_class(&dev->mutex, &cxl_nvdimm_key); device_set_pm_not_required(dev); diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index bffde862de0b..e7556864ea80 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -811,6 +811,7 @@ static struct cxl_dport *find_dport(struct cxl_port *port, int id) static int add_dport(struct cxl_port *port, struct cxl_dport *new) { struct cxl_dport *dup; + int rc; device_lock_assert(&port->dev); dup = find_dport(port, new->port_id); @@ -821,8 +822,14 @@ static int add_dport(struct cxl_port *port, struct cxl_dport *new) dev_name(dup->dport)); return -EBUSY; } - return xa_insert(&port->dports, (unsigned long)new->dport, new, - GFP_KERNEL); + + rc = xa_insert(&port->dports, (unsigned long)new->dport, new, + GFP_KERNEL); + if (rc) + return rc; + + port->nr_dports++; + return 0; } /* diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 401148016978..f9ae5ad284ff 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -174,7 +174,8 @@ static int cxl_region_decode_commit(struct cxl_region *cxlr) iter = to_cxl_port(iter->dev.parent)) { cxl_rr = cxl_rr_load(iter, cxlr); cxld = cxl_rr->decoder; - rc = cxld->commit(cxld); + if (cxld->commit) + rc = cxld->commit(cxld); if (rc) break; } @@ -657,6 +658,9 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port, xa_for_each(&port->regions, index, iter) { struct cxl_region_params *ip = &iter->region->params; + if (!ip->res) + continue; + if (ip->res->start > p->res->start) { dev_dbg(&cxlr->dev, "%s: HPA order violation %s:%pr vs %pr\n", @@ -686,18 +690,27 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port, return cxl_rr; } -static void free_region_ref(struct cxl_region_ref *cxl_rr) +static void cxl_rr_free_decoder(struct cxl_region_ref *cxl_rr) { - struct cxl_port *port = cxl_rr->port; struct cxl_region *cxlr = cxl_rr->region; struct cxl_decoder *cxld = cxl_rr->decoder; + if (!cxld) + return; + dev_WARN_ONCE(&cxlr->dev, cxld->region != cxlr, "region mismatch\n"); if (cxld->region == cxlr) { cxld->region = NULL; put_device(&cxlr->dev); } +} +static void free_region_ref(struct cxl_region_ref *cxl_rr) +{ + struct cxl_port *port = cxl_rr->port; + struct cxl_region *cxlr = cxl_rr->region; + + cxl_rr_free_decoder(cxl_rr); xa_erase(&port->regions, (unsigned long)cxlr); xa_destroy(&cxl_rr->endpoints); kfree(cxl_rr); @@ -728,6 +741,33 @@ static int cxl_rr_ep_add(struct cxl_region_ref *cxl_rr, return 0; } +static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr, + struct cxl_endpoint_decoder *cxled, + struct cxl_region_ref *cxl_rr) +{ + struct cxl_decoder *cxld; + + if (port == cxled_to_port(cxled)) + cxld = &cxled->cxld; + else + cxld = cxl_region_find_decoder(port, cxlr); + if (!cxld) { + dev_dbg(&cxlr->dev, "%s: no decoder available\n", + dev_name(&port->dev)); + return -EBUSY; + } + + if (cxld->region) { + dev_dbg(&cxlr->dev, "%s: %s already attached to %s\n", + dev_name(&port->dev), dev_name(&cxld->dev), + dev_name(&cxld->region->dev)); + return -EBUSY; + } + + cxl_rr->decoder = cxld; + return 0; +} + /** * cxl_port_attach_region() - track a region's interest in a port by endpoint * @port: port to add a new region reference 'struct cxl_region_ref' @@ -794,12 +834,6 @@ static int cxl_port_attach_region(struct cxl_port *port, cxl_rr->nr_targets++; nr_targets_inc = true; } - - /* - * The decoder for @cxlr was allocated when the region was first - * attached to @port. - */ - cxld = cxl_rr->decoder; } else { cxl_rr = alloc_region_ref(port, cxlr); if (IS_ERR(cxl_rr)) { @@ -810,26 +844,11 @@ static int cxl_port_attach_region(struct cxl_port *port, } nr_targets_inc = true; - if (port == cxled_to_port(cxled)) - cxld = &cxled->cxld; - else - cxld = cxl_region_find_decoder(port, cxlr); - if (!cxld) { - dev_dbg(&cxlr->dev, "%s: no decoder available\n", - dev_name(&port->dev)); - goto out_erase; - } - - if (cxld->region) { - dev_dbg(&cxlr->dev, "%s: %s already attached to %s\n", - dev_name(&port->dev), dev_name(&cxld->dev), - dev_name(&cxld->region->dev)); - rc = -EBUSY; + rc = cxl_rr_alloc_decoder(port, cxlr, cxled, cxl_rr); + if (rc) goto out_erase; - } - - cxl_rr->decoder = cxld; } + cxld = cxl_rr->decoder; rc = cxl_rr_ep_add(cxl_rr, cxled); if (rc) { @@ -971,7 +990,14 @@ static int cxl_port_setup_targets(struct cxl_port *port, if (cxl_rr->nr_targets_set) { int i, distance; - distance = p->nr_targets / cxl_rr->nr_targets; + /* + * Passthrough ports impose no distance requirements between + * peers + */ + if (port->nr_dports == 1) + distance = 0; + else + distance = p->nr_targets / cxl_rr->nr_targets; for (i = 0; i < cxl_rr->nr_targets_set; i++) if (ep->dport == cxlsd->target[i]) { rc = check_last_peer(cxled, ep, cxl_rr, @@ -1508,9 +1534,24 @@ static const struct attribute_group *region_groups[] = { static void cxl_region_release(struct device *dev) { + struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev->parent); struct cxl_region *cxlr = to_cxl_region(dev); + int id = atomic_read(&cxlrd->region_id); + + /* + * Try to reuse the recently idled id rather than the cached + * next id to prevent the region id space from increasing + * unnecessarily. + */ + if (cxlr->id < id) + if (atomic_try_cmpxchg(&cxlrd->region_id, &id, cxlr->id)) { + memregion_free(id); + goto out; + } memregion_free(cxlr->id); +out: + put_device(dev->parent); kfree(cxlr); } @@ -1538,8 +1579,19 @@ static struct cxl_region *to_cxl_region(struct device *dev) static void unregister_region(void *dev) { struct cxl_region *cxlr = to_cxl_region(dev); + struct cxl_region_params *p = &cxlr->params; + int i; device_del(dev); + + /* + * Now that region sysfs is shutdown, the parameter block is now + * read-only, so no need to hold the region rwsem to access the + * region parameters. + */ + for (i = 0; i < p->interleave_ways; i++) + detach_target(cxlr, i); + cxl_region_iomem_release(cxlr); put_device(dev); } @@ -1561,6 +1613,11 @@ static struct cxl_region *cxl_region_alloc(struct cxl_root_decoder *cxlrd, int i device_initialize(dev); lockdep_set_class(&dev->mutex, &cxl_region_key); dev->parent = &cxlrd->cxlsd.cxld.dev; + /* + * Keep root decoder pinned through cxl_region_release to fixup + * region id allocations + */ + get_device(dev->parent); device_set_pm_not_required(dev); dev->bus = &cxl_bus_type; dev->type = &cxl_region_type; diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index f680450f0b16..ac75554b5d76 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -423,7 +423,7 @@ struct cxl_nvdimm { struct device dev; struct cxl_memdev *cxlmd; struct cxl_nvdimm_bridge *bridge; - struct cxl_pmem_region *region; + struct xarray pmem_regions; }; struct cxl_pmem_region_mapping { @@ -457,6 +457,7 @@ struct cxl_pmem_region { * @regions: cxl_region_ref instances, regions mapped by this port * @parent_dport: dport that points to this port in the parent * @decoder_ida: allocator for decoder ids + * @nr_dports: number of entries in @dports * @hdm_end: track last allocated HDM decoder instance for allocation ordering * @commit_end: cursor to track highest committed decoder for commit ordering * @component_reg_phys: component register capability base address (optional) @@ -475,6 +476,7 @@ struct cxl_port { struct xarray regions; struct cxl_dport *parent_dport; struct ida decoder_ida; + int nr_dports; int hdm_end; int commit_end; resource_size_t component_reg_phys; diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 7dc0a2fa1a6b..4c627d67281a 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -30,17 +30,20 @@ static void unregister_nvdimm(void *nvdimm) struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); struct cxl_nvdimm_bridge *cxl_nvb = cxl_nvd->bridge; struct cxl_pmem_region *cxlr_pmem; + unsigned long index; device_lock(&cxl_nvb->dev); - cxlr_pmem = cxl_nvd->region; dev_set_drvdata(&cxl_nvd->dev, NULL); - cxl_nvd->region = NULL; - device_unlock(&cxl_nvb->dev); + xa_for_each(&cxl_nvd->pmem_regions, index, cxlr_pmem) { + get_device(&cxlr_pmem->dev); + device_unlock(&cxl_nvb->dev); - if (cxlr_pmem) { device_release_driver(&cxlr_pmem->dev); put_device(&cxlr_pmem->dev); + + device_lock(&cxl_nvb->dev); } + device_unlock(&cxl_nvb->dev); nvdimm_delete(nvdimm); cxl_nvd->bridge = NULL; @@ -107,7 +110,7 @@ static int cxl_pmem_get_config_size(struct cxl_dev_state *cxlds, *cmd = (struct nd_cmd_get_config_size) { .config_size = cxlds->lsa_size, - .max_xfer = cxlds->payload_size, + .max_xfer = cxlds->payload_size - sizeof(struct cxl_mbox_set_lsa), }; return 0; @@ -148,7 +151,7 @@ static int cxl_pmem_set_config_data(struct cxl_dev_state *cxlds, return -EINVAL; /* 4-byte status follows the input data in the payload */ - if (struct_size(cmd, in_buf, cmd->in_length) + 4 > buf_len) + if (size_add(struct_size(cmd, in_buf, cmd->in_length), 4) > buf_len) return -EINVAL; set_lsa = @@ -366,25 +369,49 @@ static int match_cxl_nvdimm(struct device *dev, void *data) static void unregister_nvdimm_region(void *nd_region) { - struct cxl_nvdimm_bridge *cxl_nvb; - struct cxl_pmem_region *cxlr_pmem; + nvdimm_region_delete(nd_region); +} + +static int cxl_nvdimm_add_region(struct cxl_nvdimm *cxl_nvd, + struct cxl_pmem_region *cxlr_pmem) +{ + int rc; + + rc = xa_insert(&cxl_nvd->pmem_regions, (unsigned long)cxlr_pmem, + cxlr_pmem, GFP_KERNEL); + if (rc) + return rc; + + get_device(&cxlr_pmem->dev); + return 0; +} + +static void cxl_nvdimm_del_region(struct cxl_nvdimm *cxl_nvd, + struct cxl_pmem_region *cxlr_pmem) +{ + /* + * It is possible this is called without a corresponding + * cxl_nvdimm_add_region for @cxlr_pmem + */ + cxlr_pmem = xa_erase(&cxl_nvd->pmem_regions, (unsigned long)cxlr_pmem); + if (cxlr_pmem) + put_device(&cxlr_pmem->dev); +} + +static void release_mappings(void *data) +{ int i; + struct cxl_pmem_region *cxlr_pmem = data; + struct cxl_nvdimm_bridge *cxl_nvb = cxlr_pmem->bridge; - cxlr_pmem = nd_region_provider_data(nd_region); - cxl_nvb = cxlr_pmem->bridge; device_lock(&cxl_nvb->dev); for (i = 0; i < cxlr_pmem->nr_mappings; i++) { struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i]; struct cxl_nvdimm *cxl_nvd = m->cxl_nvd; - if (cxl_nvd->region) { - put_device(&cxlr_pmem->dev); - cxl_nvd->region = NULL; - } + cxl_nvdimm_del_region(cxl_nvd, cxlr_pmem); } device_unlock(&cxl_nvb->dev); - - nvdimm_region_delete(nd_region); } static void cxlr_pmem_remove_resource(void *res) @@ -422,7 +449,7 @@ static int cxl_pmem_region_probe(struct device *dev) if (!cxl_nvb->nvdimm_bus) { dev_dbg(dev, "nvdimm bus not found\n"); rc = -ENXIO; - goto err; + goto out_nvb; } memset(&mappings, 0, sizeof(mappings)); @@ -431,7 +458,7 @@ static int cxl_pmem_region_probe(struct device *dev) res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL); if (!res) { rc = -ENOMEM; - goto err; + goto out_nvb; } res->name = "Persistent Memory"; @@ -442,11 +469,11 @@ static int cxl_pmem_region_probe(struct device *dev) rc = insert_resource(&iomem_resource, res); if (rc) - goto err; + goto out_nvb; rc = devm_add_action_or_reset(dev, cxlr_pmem_remove_resource, res); if (rc) - goto err; + goto out_nvb; ndr_desc.res = res; ndr_desc.provider_data = cxlr_pmem; @@ -462,7 +489,7 @@ static int cxl_pmem_region_probe(struct device *dev) nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL); if (!nd_set) { rc = -ENOMEM; - goto err; + goto out_nvb; } ndr_desc.memregion = cxlr->id; @@ -472,9 +499,13 @@ static int cxl_pmem_region_probe(struct device *dev) info = kmalloc_array(cxlr_pmem->nr_mappings, sizeof(*info), GFP_KERNEL); if (!info) { rc = -ENOMEM; - goto err; + goto out_nvb; } + rc = devm_add_action_or_reset(dev, release_mappings, cxlr_pmem); + if (rc) + goto out_nvd; + for (i = 0; i < cxlr_pmem->nr_mappings; i++) { struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i]; struct cxl_memdev *cxlmd = m->cxlmd; @@ -486,7 +517,7 @@ static int cxl_pmem_region_probe(struct device *dev) dev_dbg(dev, "[%d]: %s: no cxl_nvdimm found\n", i, dev_name(&cxlmd->dev)); rc = -ENODEV; - goto err; + goto out_nvd; } /* safe to drop ref now with bridge lock held */ @@ -498,10 +529,17 @@ static int cxl_pmem_region_probe(struct device *dev) dev_dbg(dev, "[%d]: %s: no nvdimm found\n", i, dev_name(&cxlmd->dev)); rc = -ENODEV; - goto err; + goto out_nvd; } - cxl_nvd->region = cxlr_pmem; - get_device(&cxlr_pmem->dev); + + /* + * Pin the region per nvdimm device as those may be released + * out-of-order with respect to the region, and a single nvdimm + * maybe associated with multiple regions + */ + rc = cxl_nvdimm_add_region(cxl_nvd, cxlr_pmem); + if (rc) + goto out_nvd; m->cxl_nvd = cxl_nvd; mappings[i] = (struct nd_mapping_desc) { .nvdimm = nvdimm, @@ -527,27 +565,18 @@ static int cxl_pmem_region_probe(struct device *dev) nvdimm_pmem_region_create(cxl_nvb->nvdimm_bus, &ndr_desc); if (!cxlr_pmem->nd_region) { rc = -ENOMEM; - goto err; + goto out_nvd; } rc = devm_add_action_or_reset(dev, unregister_nvdimm_region, cxlr_pmem->nd_region); -out: +out_nvd: kfree(info); +out_nvb: device_unlock(&cxl_nvb->dev); put_device(&cxl_nvb->dev); return rc; - -err: - dev_dbg(dev, "failed to create nvdimm region\n"); - for (i--; i >= 0; i--) { - nvdimm = mappings[i].nvdimm; - cxl_nvd = nvdimm_provider_data(nvdimm); - put_device(&cxl_nvd->region->dev); - cxl_nvd->region = NULL; - } - goto out; } static struct cxl_driver cxl_pmem_region_driver = { diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index d4e23101448a..35bb70724d44 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -216,9 +216,20 @@ void scmi_device_destroy(struct scmi_device *scmi_dev) device_unregister(&scmi_dev->dev); } +void scmi_device_link_add(struct device *consumer, struct device *supplier) +{ + struct device_link *link; + + link = device_link_add(consumer, supplier, DL_FLAG_AUTOREMOVE_CONSUMER); + + WARN_ON(!link); +} + void scmi_set_handle(struct scmi_device *scmi_dev) { scmi_dev->handle = scmi_handle_get(&scmi_dev->dev); + if (scmi_dev->handle) + scmi_device_link_add(&scmi_dev->dev, scmi_dev->handle->dev); } int scmi_protocol_register(const struct scmi_protocol *proto) diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h index 61aba7447c32..a1c0154c31c6 100644 --- a/drivers/firmware/arm_scmi/common.h +++ b/drivers/firmware/arm_scmi/common.h @@ -97,6 +97,7 @@ static inline void unpack_scmi_header(u32 msg_hdr, struct scmi_msg_hdr *hdr) struct scmi_revision_info * scmi_revision_area_get(const struct scmi_protocol_handle *ph); int scmi_handle_put(const struct scmi_handle *handle); +void scmi_device_link_add(struct device *consumer, struct device *supplier); struct scmi_handle *scmi_handle_get(struct device *dev); void scmi_set_handle(struct scmi_device *scmi_dev); void scmi_setup_protocol_implemented(const struct scmi_protocol_handle *ph, @@ -117,6 +118,7 @@ void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id); * * @dev: Reference to device in the SCMI hierarchy corresponding to this * channel + * @rx_timeout_ms: The configured RX timeout in milliseconds. * @handle: Pointer to SCMI entity handle * @no_completion_irq: Flag to indicate that this channel has no completion * interrupt mechanism for synchronous commands. @@ -126,6 +128,7 @@ void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id); */ struct scmi_chan_info { struct device *dev; + unsigned int rx_timeout_ms; struct scmi_handle *handle; bool no_completion_irq; void *transport_info; @@ -232,7 +235,7 @@ void scmi_free_channel(struct scmi_chan_info *cinfo, struct idr *idr, int id); struct scmi_shared_mem; void shmem_tx_prepare(struct scmi_shared_mem __iomem *shmem, - struct scmi_xfer *xfer); + struct scmi_xfer *xfer, struct scmi_chan_info *cinfo); u32 shmem_read_header(struct scmi_shared_mem __iomem *shmem); void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem, struct scmi_xfer *xfer); diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c index 609ebedee9cb..f818d00bb2c6 100644 --- a/drivers/firmware/arm_scmi/driver.c +++ b/drivers/firmware/arm_scmi/driver.c @@ -2013,6 +2013,7 @@ static int scmi_chan_setup(struct scmi_info *info, struct device *dev, return -ENOMEM; cinfo->dev = dev; + cinfo->rx_timeout_ms = info->desc->max_rx_timeout_ms; ret = info->desc->ops->chan_setup(cinfo, info->dev, tx); if (ret) @@ -2044,8 +2045,12 @@ scmi_txrx_setup(struct scmi_info *info, struct device *dev, int prot_id) { int ret = scmi_chan_setup(info, dev, prot_id, true); - if (!ret) /* Rx is optional, hence no error check */ - scmi_chan_setup(info, dev, prot_id, false); + if (!ret) { + /* Rx is optional, report only memory errors */ + ret = scmi_chan_setup(info, dev, prot_id, false); + if (ret && ret != -ENOMEM) + ret = 0; + } return ret; } @@ -2273,10 +2278,16 @@ int scmi_protocol_device_request(const struct scmi_device_id *id_table) sdev = scmi_get_protocol_device(child, info, id_table->protocol_id, id_table->name); - /* Set handle if not already set: device existed */ - if (sdev && !sdev->handle) - sdev->handle = - scmi_handle_get_from_info_unlocked(info); + if (sdev) { + /* Set handle if not already set: device existed */ + if (!sdev->handle) + sdev->handle = + scmi_handle_get_from_info_unlocked(info); + /* Relink consumer and suppliers */ + if (sdev->handle) + scmi_device_link_add(&sdev->dev, + sdev->handle->dev); + } } else { dev_err(info->dev, "Failed. SCMI protocol %d not active.\n", @@ -2475,20 +2486,17 @@ void scmi_free_channel(struct scmi_chan_info *cinfo, struct idr *idr, int id) static int scmi_remove(struct platform_device *pdev) { - int ret = 0, id; + int ret, id; struct scmi_info *info = platform_get_drvdata(pdev); struct device_node *child; mutex_lock(&scmi_list_mutex); if (info->users) - ret = -EBUSY; - else - list_del(&info->node); + dev_warn(&pdev->dev, + "Still active SCMI users will be forcibly unbound.\n"); + list_del(&info->node); mutex_unlock(&scmi_list_mutex); - if (ret) - return ret; - scmi_notification_exit(&info->handle); mutex_lock(&info->protocols_mtx); @@ -2500,7 +2508,11 @@ static int scmi_remove(struct platform_device *pdev) idr_destroy(&info->active_protocols); /* Safe to free channels since no more users */ - return scmi_cleanup_txrx_channels(info); + ret = scmi_cleanup_txrx_channels(info); + if (ret) + dev_warn(&pdev->dev, "Failed to cleanup SCMI channels.\n"); + + return 0; } static ssize_t protocol_version_show(struct device *dev, @@ -2571,6 +2583,7 @@ MODULE_DEVICE_TABLE(of, scmi_of_match); static struct platform_driver scmi_driver = { .driver = { .name = "arm-scmi", + .suppress_bind_attrs = true, .of_match_table = scmi_of_match, .dev_groups = versions_groups, }, diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c index 08ff4d110beb..1e40cb035044 100644 --- a/drivers/firmware/arm_scmi/mailbox.c +++ b/drivers/firmware/arm_scmi/mailbox.c @@ -36,7 +36,7 @@ static void tx_prepare(struct mbox_client *cl, void *m) { struct scmi_mailbox *smbox = client_to_scmi_mailbox(cl); - shmem_tx_prepare(smbox->shmem, m); + shmem_tx_prepare(smbox->shmem, m, smbox->cinfo); } static void rx_callback(struct mbox_client *cl, void *m) diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c index f42dad997ac9..2a7aeab40e54 100644 --- a/drivers/firmware/arm_scmi/optee.c +++ b/drivers/firmware/arm_scmi/optee.c @@ -498,7 +498,7 @@ static int scmi_optee_send_message(struct scmi_chan_info *cinfo, msg_tx_prepare(channel->req.msg, xfer); ret = invoke_process_msg_channel(channel, msg_command_size(xfer)); } else { - shmem_tx_prepare(channel->req.shmem, xfer); + shmem_tx_prepare(channel->req.shmem, xfer, cinfo); ret = invoke_process_smt_channel(channel); } diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c index 0e3eaea5d852..1dfe534b8518 100644 --- a/drivers/firmware/arm_scmi/shmem.c +++ b/drivers/firmware/arm_scmi/shmem.c @@ -5,10 +5,13 @@ * Copyright (C) 2019 ARM Ltd. */ +#include <linux/ktime.h> #include <linux/io.h> #include <linux/processor.h> #include <linux/types.h> +#include <asm-generic/bug.h> + #include "common.h" /* @@ -30,16 +33,36 @@ struct scmi_shared_mem { }; void shmem_tx_prepare(struct scmi_shared_mem __iomem *shmem, - struct scmi_xfer *xfer) + struct scmi_xfer *xfer, struct scmi_chan_info *cinfo) { + ktime_t stop; + /* * Ideally channel must be free by now unless OS timeout last * request and platform continued to process the same, wait * until it releases the shared memory, otherwise we may endup - * overwriting its response with new message payload or vice-versa + * overwriting its response with new message payload or vice-versa. + * Giving up anyway after twice the expected channel timeout so as + * not to bail-out on intermittent issues where the platform is + * occasionally a bit slower to answer. + * + * Note that after a timeout is detected we bail-out and carry on but + * the transport functionality is probably permanently compromised: + * this is just to ease debugging and avoid complete hangs on boot + * due to a misbehaving SCMI firmware. */ - spin_until_cond(ioread32(&shmem->channel_status) & - SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE); + stop = ktime_add_ms(ktime_get(), 2 * cinfo->rx_timeout_ms); + spin_until_cond((ioread32(&shmem->channel_status) & + SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE) || + ktime_after(ktime_get(), stop)); + if (!(ioread32(&shmem->channel_status) & + SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE)) { + WARN_ON_ONCE(1); + dev_err(cinfo->dev, + "Timeout waiting for a free TX channel !\n"); + return; + } + /* Mark channel busy + clear error */ iowrite32(0x0, &shmem->channel_status); iowrite32(xfer->hdr.poll_completion ? 0 : SCMI_SHMEM_FLAG_INTR_ENABLED, diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c index 745acfdd0b3d..87a7b13cf868 100644 --- a/drivers/firmware/arm_scmi/smc.c +++ b/drivers/firmware/arm_scmi/smc.c @@ -188,7 +188,7 @@ static int smc_send_message(struct scmi_chan_info *cinfo, */ smc_channel_lock_acquire(scmi_info, xfer); - shmem_tx_prepare(scmi_info->shmem, xfer); + shmem_tx_prepare(scmi_info->shmem, xfer, cinfo); arm_smccc_1_1_invoke(scmi_info->func_id, 0, 0, 0, 0, 0, 0, 0, &res); diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c index 14709dbc96a1..33c9b81a55cd 100644 --- a/drivers/firmware/arm_scmi/virtio.c +++ b/drivers/firmware/arm_scmi/virtio.c @@ -148,7 +148,6 @@ static void scmi_vio_channel_cleanup_sync(struct scmi_vio_channel *vioch) { unsigned long flags; DECLARE_COMPLETION_ONSTACK(vioch_shutdown_done); - void *deferred_wq = NULL; /* * Prepare to wait for the last release if not already released @@ -162,16 +161,11 @@ 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) { - deferred_wq = vioch->deferred_tx_wq; + if (!vioch->is_rx && vioch->deferred_tx_wq) /* Cannot be kicked anymore after this...*/ vioch->deferred_tx_wq = NULL; - } spin_unlock_irqrestore(&vioch->lock, flags); - if (deferred_wq) - destroy_workqueue(deferred_wq); - scmi_vio_channel_release(vioch); /* Let any possibly concurrent RX path release the channel */ @@ -416,6 +410,11 @@ static bool virtio_chan_available(struct device *dev, int idx) return vioch && !vioch->cinfo; } +static void scmi_destroy_tx_workqueue(void *deferred_tx_wq) +{ + destroy_workqueue(deferred_tx_wq); +} + static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, bool tx) { @@ -430,6 +429,8 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, /* Setup a deferred worker for polling. */ if (tx && !vioch->deferred_tx_wq) { + int ret; + vioch->deferred_tx_wq = alloc_workqueue(dev_name(&scmi_vdev->dev), WQ_UNBOUND | WQ_FREEZABLE | WQ_SYSFS, @@ -437,6 +438,11 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, if (!vioch->deferred_tx_wq) return -ENOMEM; + ret = devm_add_action_or_reset(dev, scmi_destroy_tx_workqueue, + vioch->deferred_tx_wq); + if (ret) + return ret; + INIT_WORK(&vioch->deferred_tx_work, scmi_vio_deferred_tx_worker); } @@ -444,12 +450,12 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, for (i = 0; i < vioch->max_msg; i++) { struct scmi_vio_msg *msg; - msg = devm_kzalloc(cinfo->dev, sizeof(*msg), GFP_KERNEL); + msg = devm_kzalloc(dev, sizeof(*msg), GFP_KERNEL); if (!msg) return -ENOMEM; if (tx) { - msg->request = devm_kzalloc(cinfo->dev, + msg->request = devm_kzalloc(dev, VIRTIO_SCMI_MAX_PDU_SIZE, GFP_KERNEL); if (!msg->request) @@ -458,7 +464,7 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev, refcount_set(&msg->users, 1); } - msg->input = devm_kzalloc(cinfo->dev, VIRTIO_SCMI_MAX_PDU_SIZE, + msg->input = devm_kzalloc(dev, VIRTIO_SCMI_MAX_PDU_SIZE, GFP_KERNEL); if (!msg->input) return -ENOMEM; diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 3ecdc43a3f2b..a46df5d1d094 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -611,7 +611,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables, seed = early_memremap(efi_rng_seed, sizeof(*seed)); if (seed != NULL) { - size = READ_ONCE(seed->size); + size = min(seed->size, EFI_RANDOM_SEED_SIZE); early_memunmap(seed, sizeof(*seed)); } else { pr_err("Could not map UEFI random seed!\n"); diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c index 24aa37535372..33ab56769595 100644 --- a/drivers/firmware/efi/libstub/random.c +++ b/drivers/firmware/efi/libstub/random.c @@ -75,7 +75,12 @@ efi_status_t efi_random_get_seed(void) if (status != EFI_SUCCESS) return status; - status = efi_bs_call(allocate_pool, EFI_RUNTIME_SERVICES_DATA, + /* + * Use EFI_ACPI_RECLAIM_MEMORY here so that it is guaranteed that the + * allocation will survive a kexec reboot (although we refresh the seed + * beforehand) + */ + status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY, sizeof(*seed) + EFI_RANDOM_SEED_SIZE, (void **)&seed); if (status != EFI_SUCCESS) diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c index 8f665678e9e3..e8d69bd548f3 100644 --- a/drivers/firmware/efi/tpm.c +++ b/drivers/firmware/efi/tpm.c @@ -97,7 +97,7 @@ int __init efi_tpm_eventlog_init(void) goto out_calc; } - memblock_reserve((unsigned long)final_tbl, + memblock_reserve(efi.tpm_final_log, tbl_size + sizeof(*final_tbl)); efi_tpm_final_log_size = tbl_size; diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 433b61587139..0ba9f18312f5 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -21,29 +21,22 @@ static struct efivars *__efivars; static DEFINE_SEMAPHORE(efivars_lock); -static efi_status_t check_var_size(u32 attributes, unsigned long size) -{ - const struct efivar_operations *fops; - - fops = __efivars->ops; - - if (!fops->query_variable_store) - return (size <= SZ_64K) ? EFI_SUCCESS : EFI_OUT_OF_RESOURCES; - - return fops->query_variable_store(attributes, size, false); -} - -static -efi_status_t check_var_size_nonblocking(u32 attributes, unsigned long size) +static efi_status_t check_var_size(bool nonblocking, u32 attributes, + unsigned long size) { const struct efivar_operations *fops; + efi_status_t status; fops = __efivars->ops; if (!fops->query_variable_store) + status = EFI_UNSUPPORTED; + else + status = fops->query_variable_store(attributes, size, + nonblocking); + if (status == EFI_UNSUPPORTED) return (size <= SZ_64K) ? EFI_SUCCESS : EFI_OUT_OF_RESOURCES; - - return fops->query_variable_store(attributes, size, true); + return status; } /** @@ -196,26 +189,6 @@ efi_status_t efivar_get_next_variable(unsigned long *name_size, EXPORT_SYMBOL_NS_GPL(efivar_get_next_variable, EFIVAR); /* - * efivar_set_variable_blocking() - local helper function for set_variable - * - * Must be called with efivars_lock held. - */ -static efi_status_t -efivar_set_variable_blocking(efi_char16_t *name, efi_guid_t *vendor, - u32 attr, unsigned long data_size, void *data) -{ - efi_status_t status; - - if (data_size > 0) { - status = check_var_size(attr, data_size + - ucs2_strsize(name, 1024)); - if (status != EFI_SUCCESS) - return status; - } - return __efivars->ops->set_variable(name, vendor, attr, data_size, data); -} - -/* * efivar_set_variable_locked() - set a variable identified by name/vendor * * Must be called with efivars_lock held. If @nonblocking is set, it will use @@ -228,23 +201,21 @@ efi_status_t efivar_set_variable_locked(efi_char16_t *name, efi_guid_t *vendor, efi_set_variable_t *setvar; efi_status_t status; - if (!nonblocking) - return efivar_set_variable_blocking(name, vendor, attr, - data_size, data); + if (data_size > 0) { + status = check_var_size(nonblocking, attr, + data_size + ucs2_strsize(name, 1024)); + if (status != EFI_SUCCESS) + return status; + } /* * If no _nonblocking variant exists, the ordinary one * is assumed to be non-blocking. */ - setvar = __efivars->ops->set_variable_nonblocking ?: - __efivars->ops->set_variable; + setvar = __efivars->ops->set_variable_nonblocking; + if (!setvar || !nonblocking) + setvar = __efivars->ops->set_variable; - if (data_size > 0) { - status = check_var_size_nonblocking(attr, data_size + - ucs2_strsize(name, 1024)); - if (status != EFI_SUCCESS) - return status; - } return setvar(name, vendor, attr, data_size, data); } EXPORT_SYMBOL_NS_GPL(efivar_set_variable_locked, EFIVAR); @@ -264,7 +235,8 @@ efi_status_t efivar_set_variable(efi_char16_t *name, efi_guid_t *vendor, if (efivar_lock()) return EFI_ABORTED; - status = efivar_set_variable_blocking(name, vendor, attr, data_size, data); + status = efivar_set_variable_locked(name, vendor, attr, data_size, + data, false); efivar_unlock(); return status; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 1bbd39b3b0fc..d371000a5727 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -992,6 +992,7 @@ out_free_user_pages: kvfree(e->user_pages); e->user_pages = NULL; } + mutex_unlock(&p->bo_list->bo_list_mutex); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 2291aa14d888..003aa9e47085 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -143,32 +143,6 @@ int amdgpu_vm_set_pasid(struct amdgpu_device *adev, struct amdgpu_vm *vm, return 0; } -/* - * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS - * happens while holding this lock anywhere to prevent deadlocks when - * an MMU notifier runs in reclaim-FS context. - */ -static inline void amdgpu_vm_eviction_lock(struct amdgpu_vm *vm) -{ - mutex_lock(&vm->eviction_lock); - vm->saved_flags = memalloc_noreclaim_save(); -} - -static inline int amdgpu_vm_eviction_trylock(struct amdgpu_vm *vm) -{ - if (mutex_trylock(&vm->eviction_lock)) { - vm->saved_flags = memalloc_noreclaim_save(); - return 1; - } - return 0; -} - -static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm) -{ - memalloc_noreclaim_restore(vm->saved_flags); - mutex_unlock(&vm->eviction_lock); -} - /** * amdgpu_vm_bo_evicted - vm_bo is evicted * diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 83acb7bd80fe..6546e786bf00 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -492,7 +492,48 @@ void amdgpu_debugfs_vm_bo_info(struct amdgpu_vm *vm, struct seq_file *m); */ static inline uint64_t amdgpu_vm_tlb_seq(struct amdgpu_vm *vm) { + unsigned long flags; + spinlock_t *lock; + + /* + * Workaround to stop racing between the fence signaling and handling + * the cb. The lock is static after initially setting it up, just make + * sure that the dma_fence structure isn't freed up. + */ + rcu_read_lock(); + lock = vm->last_tlb_flush->lock; + rcu_read_unlock(); + + spin_lock_irqsave(lock, flags); + spin_unlock_irqrestore(lock, flags); + return atomic64_read(&vm->tlb_seq); } +/* + * vm eviction_lock can be taken in MMU notifiers. Make sure no reclaim-FS + * happens while holding this lock anywhere to prevent deadlocks when + * an MMU notifier runs in reclaim-FS context. + */ +static inline void amdgpu_vm_eviction_lock(struct amdgpu_vm *vm) +{ + mutex_lock(&vm->eviction_lock); + vm->saved_flags = memalloc_noreclaim_save(); +} + +static inline bool amdgpu_vm_eviction_trylock(struct amdgpu_vm *vm) +{ + if (mutex_trylock(&vm->eviction_lock)) { + vm->saved_flags = memalloc_noreclaim_save(); + return true; + } + return false; +} + +static inline void amdgpu_vm_eviction_unlock(struct amdgpu_vm *vm) +{ + memalloc_noreclaim_restore(vm->saved_flags); + mutex_unlock(&vm->eviction_lock); +} + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 358b91243e37..b5f3bba851db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -597,7 +597,9 @@ static int amdgpu_vm_pt_alloc(struct amdgpu_device *adev, if (entry->bo) return 0; + amdgpu_vm_eviction_unlock(vm); r = amdgpu_vm_pt_create(adev, vm, cursor->level, immediate, &pt); + amdgpu_vm_eviction_lock(vm); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 73a517bcf5c1..80dd1343594c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -435,7 +435,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, if (place->flags & TTM_PL_FLAG_TOPDOWN) vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION; - if (fpfn || lpfn != man->size) + if (fpfn || lpfn != mgr->mm.size) /* Allocate blocks in desired range */ vres->flags |= DRM_BUDDY_RANGE_ALLOCATION; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index 5feaba6a77de..6d291aa6386b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1950,7 +1950,7 @@ static int criu_checkpoint(struct file *filep, { int ret; uint32_t num_devices, num_bos, num_objects; - uint64_t priv_size, priv_offset = 0; + uint64_t priv_size, priv_offset = 0, bo_priv_offset; if (!args->devices || !args->bos || !args->priv_data) return -EINVAL; @@ -1994,38 +1994,34 @@ static int criu_checkpoint(struct file *filep, if (ret) goto exit_unlock; - ret = criu_checkpoint_bos(p, num_bos, (uint8_t __user *)args->bos, - (uint8_t __user *)args->priv_data, &priv_offset); - if (ret) - goto exit_unlock; + /* Leave room for BOs in the private data. They need to be restored + * before events, but we checkpoint them last to simplify the error + * handling. + */ + bo_priv_offset = priv_offset; + priv_offset += num_bos * sizeof(struct kfd_criu_bo_priv_data); if (num_objects) { ret = kfd_criu_checkpoint_queues(p, (uint8_t __user *)args->priv_data, &priv_offset); if (ret) - goto close_bo_fds; + goto exit_unlock; ret = kfd_criu_checkpoint_events(p, (uint8_t __user *)args->priv_data, &priv_offset); if (ret) - goto close_bo_fds; + goto exit_unlock; ret = kfd_criu_checkpoint_svm(p, (uint8_t __user *)args->priv_data, &priv_offset); if (ret) - goto close_bo_fds; + goto exit_unlock; } -close_bo_fds: - if (ret) { - /* If IOCTL returns err, user assumes all FDs opened in criu_dump_bos are closed */ - uint32_t i; - struct kfd_criu_bo_bucket *bo_buckets = (struct kfd_criu_bo_bucket *) args->bos; - - for (i = 0; i < num_bos; i++) { - if (bo_buckets[i].alloc_flags & KFD_IOC_ALLOC_MEM_FLAGS_VRAM) - close_fd(bo_buckets[i].dmabuf_fd); - } - } + /* This must be the last thing in this function that can fail. + * Otherwise we leak dmabuf file descriptors. + */ + ret = criu_checkpoint_bos(p, num_bos, (uint8_t __user *)args->bos, + (uint8_t __user *)args->priv_data, &bo_priv_offset); exit_unlock: mutex_unlock(&p->mutex); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index 83e3ce9f6049..729d26d648af 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -506,6 +506,7 @@ int kfd_criu_restore_event(struct file *devkfd, ret = create_other_event(p, ev, &ev_priv->event_id); break; } + mutex_unlock(&p->event_mutex); exit: if (ret) @@ -513,8 +514,6 @@ exit: kfree(ev_priv); - mutex_unlock(&p->event_mutex); - return ret; } 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 589bee9acf16..509739d83b5a 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -7622,9 +7622,10 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->surface_updates[planes_count].plane_info = &bundle->plane_infos[planes_count]; - fill_dc_dirty_rects(plane, old_plane_state, new_plane_state, - new_crtc_state, - &bundle->flip_addrs[planes_count]); + if (acrtc_state->stream->link->psr_settings.psr_feature_enabled) + fill_dc_dirty_rects(plane, old_plane_state, + new_plane_state, new_crtc_state, + &bundle->flip_addrs[planes_count]); /* * Only allow immediate flips for fast updates that don't diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index 1131c6d73f6c..20a06c04e4a1 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -363,32 +363,32 @@ static struct wm_table ddr5_wm_table = { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 9, - .sr_enter_plus_exit_time_us = 11, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 9, - .sr_enter_plus_exit_time_us = 11, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 9, - .sr_enter_plus_exit_time_us = 11, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.72, - .sr_exit_time_us = 9, - .sr_enter_plus_exit_time_us = 11, + .sr_exit_time_us = 12.5, + .sr_enter_plus_exit_time_us = 14.5, .valid = true, }, } @@ -400,32 +400,32 @@ static struct wm_table lpddr5_wm_table = { .wm_inst = WM_A, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 11.5, - .sr_enter_plus_exit_time_us = 14.5, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, .valid = true, }, { .wm_inst = WM_B, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 11.5, - .sr_enter_plus_exit_time_us = 14.5, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, .valid = true, }, { .wm_inst = WM_C, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 11.5, - .sr_enter_plus_exit_time_us = 14.5, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, .valid = true, }, { .wm_inst = WM_D, .wm_type = WM_TYPE_PSTATE_CHG, .pstate_latency_us = 11.65333, - .sr_exit_time_us = 11.5, - .sr_enter_plus_exit_time_us = 14.5, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, .valid = true, }, } diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 737b221ca689..0598465fd1a1 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -853,6 +853,7 @@ struct dc_debug_options { bool enable_dp_dig_pixel_rate_div_policy; enum lttpr_mode lttpr_mode_override; unsigned int dsc_delay_factor_wa_x1000; + unsigned int min_prefetch_in_strobe_ns; }; struct gpu_info_soc_bounding_box_v1_0; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c index 7e773bf7b895..38842f938bed 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dio_stream_encoder.c @@ -49,18 +49,30 @@ #define CTX \ enc1->base.ctx +static void enc314_reset_fifo(struct stream_encoder *enc, bool reset) +{ + struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); + uint32_t reset_val = reset ? 1 : 0; + uint32_t is_symclk_on; + + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, reset_val); + REG_GET(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, &is_symclk_on); + + if (is_symclk_on) + REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, reset_val, 10, 5000); + else + udelay(10); +} static void enc314_enable_fifo(struct stream_encoder *enc) { struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); - /* TODO: Confirm if we need to wait for DIG_SYMCLK_FE_ON */ - REG_WAIT(DIG_FE_CNTL, DIG_SYMCLK_FE_ON, 1, 10, 5000); REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7); - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 1); - REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 1, 10, 5000); - REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_RESET, 0); - REG_WAIT(DIG_FIFO_CTRL0, DIG_FIFO_RESET_DONE, 0, 10, 5000); + + enc314_reset_fifo(enc, true); + enc314_reset_fifo(enc, false); + REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 1); } diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index a88dd7b3d1c1..d1598e3131f6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -724,6 +724,7 @@ static const struct dc_debug_options debug_defaults_drv = { .enable_dp_dig_pixel_rate_div_policy = 1, .allow_sw_cursor_fallback = false, .alloc_extra_way_for_cursor = true, + .min_prefetch_in_strobe_ns = 60000, // 60us }; static const struct dc_debug_options debug_defaults_diags = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index 61087f2385a9..6292ac515d1a 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -722,6 +722,7 @@ static const struct dc_debug_options debug_defaults_drv = { .enable_dp_dig_pixel_rate_div_policy = 1, .allow_sw_cursor_fallback = false, .alloc_extra_way_for_cursor = true, + .min_prefetch_in_strobe_ns = 60000, // 60us }; static const struct dc_debug_options debug_defaults_diags = { diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c index cf420ad2b8dc..34b6c763a455 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c @@ -146,8 +146,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = { }, }, .num_states = 5, - .sr_exit_time_us = 9.0, - .sr_enter_plus_exit_time_us = 11.0, + .sr_exit_time_us = 16.5, + .sr_enter_plus_exit_time_us = 18.5, .sr_exit_z8_time_us = 442.0, .sr_enter_plus_exit_z8_time_us = 560.0, .writeback_latency_us = 12.0, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index f37c9a6b3b7e..659323ebd79d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -2364,6 +2364,8 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa /* DML DSC delay factor workaround */ dcn3_2_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0; + dcn3_2_ip.min_prefetch_in_strobe_us = dc->debug.min_prefetch_in_strobe_ns / 1000.0; + /* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */ dcn3_2_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 3d184679f129..244fd15d24b4 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -786,6 +786,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightY[k], v->SwathHeightC[k], TWait, + v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ ? + mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ &v->DSTXAfterScaler[k], &v->DSTYAfterScaler[k], @@ -3192,6 +3194,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l mode_lib->vba.FCLKChangeLatency, mode_lib->vba.UrgLatency[i], mode_lib->vba.SREnterPlusExitTime); + memset(&v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull, 0, sizeof(DmlPipe)); v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe.Dppclk = mode_lib->vba.RequiredDPPCLK[i][j][k]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe.Dispclk = mode_lib->vba.RequiredDISPCLK[i][j]; v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.myPipe.PixelClock = mode_lib->vba.PixelClock[k]; @@ -3244,6 +3247,8 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->swath_width_chroma_ub_this_state[k], v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, + v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ ? + mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ &v->dummy_vars.dml32_ModeSupportAndSystemConfigurationFull.DSTXAfterScaler[k], diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h index c62e0991358b..f82e14cd9d8a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h @@ -49,6 +49,9 @@ #define BPP_INVALID 0 #define BPP_BLENDED_PIPE 0xffffffff +#define MEM_STROBE_FREQ_MHZ 1600 +#define MEM_STROBE_MAX_DELIVERY_TIME_US 60.0 + struct display_mode_lib; void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_lib); diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c index 968924c491c1..635fc54338fa 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c @@ -3417,6 +3417,7 @@ bool dml32_CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, + double TPreReq, /* Output */ double *DSTXAfterScaler, double *DSTYAfterScaler, @@ -3474,6 +3475,7 @@ bool dml32_CalculatePrefetchSchedule( double min_Lsw; double Tsw_est1 = 0; double Tsw_est3 = 0; + double TPreMargin = 0; if (v->GPUVMEnable == true && v->HostVMEnable == true) HostVMDynamicLevelsTrips = v->HostVMMaxNonCachedPageTableLevels; @@ -3699,6 +3701,8 @@ bool dml32_CalculatePrefetchSchedule( dst_y_prefetch_equ = dml_floor(4.0 * (dst_y_prefetch_equ + 0.125), 1) / 4.0; Tpre_rounded = dst_y_prefetch_equ * LineTime; + + TPreMargin = Tpre_rounded - TPreReq; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: dst_y_prefetch_equ: %f (after round)\n", __func__, dst_y_prefetch_equ); dml_print("DML::%s: LineTime: %f\n", __func__, LineTime); @@ -3726,7 +3730,7 @@ bool dml32_CalculatePrefetchSchedule( *VRatioPrefetchY = 0; *VRatioPrefetchC = 0; *RequiredPrefetchPixDataBWLuma = 0; - if (dst_y_prefetch_equ > 1) { + if (dst_y_prefetch_equ > 1 && TPreMargin > 0.0) { double PrefetchBandwidth1; double PrefetchBandwidth2; double PrefetchBandwidth3; @@ -3872,7 +3876,11 @@ bool dml32_CalculatePrefetchSchedule( } if (dst_y_prefetch_oto < dst_y_prefetch_equ) { - *DestinationLinesForPrefetch = dst_y_prefetch_oto; + if (dst_y_prefetch_oto * LineTime < TPreReq) { + *DestinationLinesForPrefetch = dst_y_prefetch_equ; + } else { + *DestinationLinesForPrefetch = dst_y_prefetch_oto; + } TimeForFetchingMetaPTE = Tvm_oto; TimeForFetchingRowInVBlank = Tr0_oto; *PrefetchBandwidth = prefetch_bw_oto; @@ -4397,7 +4405,7 @@ void dml32_CalculateWatermarksMALLUseAndDRAMSpeedChangeSupport( if (v->NumberOfActiveSurfaces > 1) { ActiveClockChangeLatencyHidingY = ActiveClockChangeLatencyHidingY - - (1 - 1 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k] + - (1.0 - 1.0 / v->NumberOfActiveSurfaces) * SwathHeightY[k] * v->HTotal[k] / v->PixelClock[k] / v->VRatio[k]; } diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h index 2c3827546ac7..3989c2a28fae 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h @@ -30,7 +30,7 @@ #include "os_types.h" #include "../dc_features.h" #include "../display_mode_structs.h" -#include "dml/display_mode_vba.h" +#include "../display_mode_vba.h" unsigned int dml32_dscceComputeDelay( unsigned int bpc, @@ -743,6 +743,7 @@ bool dml32_CalculatePrefetchSchedule( unsigned int SwathHeightY, unsigned int SwathHeightC, double TWait, + double TPreReq, /* Output */ double *DSTXAfterScaler, double *DSTYAfterScaler, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c index ec0486efab14..432b4ecd01a7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c @@ -544,6 +544,8 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p /* DML DSC delay factor workaround */ dcn3_21_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0; + dcn3_21_ip.min_prefetch_in_strobe_us = dc->debug.min_prefetch_in_strobe_ns / 1000.0; + /* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */ dcn3_21_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h index d7be01ac0751..64d602e6412f 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h @@ -367,6 +367,7 @@ struct _vcs_dpi_ip_params_st { /* DM workarounds */ double dsc_delay_factor_wa; // TODO: Remove after implementing root cause fix + double min_prefetch_in_strobe_us; }; struct _vcs_dpi_display_xfc_params_st { diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c index d635b73af46f..0ea52ba5ac82 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn32/hw_factory_dcn32.c @@ -108,6 +108,13 @@ static const struct ddc_registers ddc_data_regs_dcn[] = { ddc_data_regs_dcn2(4), ddc_data_regs_dcn2(5), { + // add a dummy entry for cases no such port + {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,}, + .ddc_setup = 0, + .phy_aux_cntl = 0, + .dc_gpio_aux_ctrl_5 = 0 + }, + { DDC_GPIO_VGA_REG_LIST(DATA), .ddc_setup = 0, .phy_aux_cntl = 0, @@ -122,6 +129,13 @@ static const struct ddc_registers ddc_clk_regs_dcn[] = { ddc_clk_regs_dcn2(4), ddc_clk_regs_dcn2(5), { + // add a dummy entry for cases no such port + {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,}, + .ddc_setup = 0, + .phy_aux_cntl = 0, + .dc_gpio_aux_ctrl_5 = 0 + }, + { DDC_GPIO_VGA_REG_LIST(CLK), .ddc_setup = 0, .phy_aux_cntl = 0, diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c index 6fd38cdd68c0..525bc8881950 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_ddc.c @@ -94,11 +94,14 @@ static enum gpio_result set_config( * is required for detection of AUX mode */ if (hw_gpio->base.en != GPIO_DDC_LINE_VIP_PAD) { if (!ddc_data_pd_en || !ddc_clk_pd_en) { - - REG_SET_2(gpio.MASK_reg, regval, + if (hw_gpio->base.en == GPIO_DDC_LINE_DDC_VGA) { + // bit 4 of mask has different usage in some cases + REG_SET(gpio.MASK_reg, regval, DC_GPIO_DDC1DATA_PD_EN, 1); + } else { + REG_SET_2(gpio.MASK_reg, regval, DC_GPIO_DDC1DATA_PD_EN, 1, DC_GPIO_DDC1CLK_PD_EN, 1); - + } if (config_data->type == GPIO_CONFIG_TYPE_I2C_AUX_DUAL_MODE) msleep(3); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c index dad3e3741a4e..190af79f3236 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_thermal.c @@ -67,22 +67,21 @@ int vega10_fan_ctrl_get_fan_speed_info(struct pp_hwmgr *hwmgr, int vega10_fan_ctrl_get_fan_speed_pwm(struct pp_hwmgr *hwmgr, uint32_t *speed) { - uint32_t current_rpm; - uint32_t percent = 0; - - if (hwmgr->thermal_controller.fanInfo.bNoFan) - return 0; + struct amdgpu_device *adev = hwmgr->adev; + uint32_t duty100, duty; + uint64_t tmp64; - if (vega10_get_current_rpm(hwmgr, ¤t_rpm)) - return -1; + duty100 = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_FDO_CTRL1), + CG_FDO_CTRL1, FMAX_DUTY100); + duty = REG_GET_FIELD(RREG32_SOC15(THM, 0, mmCG_THERMAL_STATUS), + CG_THERMAL_STATUS, FDO_PWM_DUTY); - if (hwmgr->thermal_controller. - advanceFanControlParameters.usMaxFanRPM != 0) - percent = current_rpm * 255 / - hwmgr->thermal_controller. - advanceFanControlParameters.usMaxFanRPM; + if (!duty100) + return -EINVAL; - *speed = MIN(percent, 255); + tmp64 = (uint64_t)duty * 255; + do_div(tmp64, duty100); + *speed = MIN((uint32_t)tmp64, 255); return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h index d9b0cd752200..f4d6c07b56ea 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_4_ppsmc.h @@ -54,14 +54,14 @@ #define PPSMC_MSG_TestMessage 0x01 ///< To check if PMFW is alive and responding. Requirement specified by PMFW team #define PPSMC_MSG_GetPmfwVersion 0x02 ///< Get PMFW version #define PPSMC_MSG_GetDriverIfVersion 0x03 ///< Get PMFW_DRIVER_IF version -#define PPSMC_MSG_EnableGfxOff 0x04 ///< Enable GFXOFF -#define PPSMC_MSG_DisableGfxOff 0x05 ///< Disable GFXOFF +#define PPSMC_MSG_SPARE0 0x04 ///< SPARE +#define PPSMC_MSG_SPARE1 0x05 ///< SPARE #define PPSMC_MSG_PowerDownVcn 0x06 ///< Power down VCN #define PPSMC_MSG_PowerUpVcn 0x07 ///< Power up VCN; VCN is power gated by default #define PPSMC_MSG_SetHardMinVcn 0x08 ///< For wireless display #define PPSMC_MSG_SetSoftMinGfxclk 0x09 ///< Set SoftMin for GFXCLK, argument is frequency in MHz -#define PPSMC_MSG_ActiveProcessNotify 0x0A ///< Needs update -#define PPSMC_MSG_ForcePowerDownGfx 0x0B ///< Force power down GFX, i.e. enter GFXOFF +#define PPSMC_MSG_SPARE2 0x0A ///< SPARE +#define PPSMC_MSG_SPARE3 0x0B ///< SPARE #define PPSMC_MSG_PrepareMp1ForUnload 0x0C ///< Prepare PMFW for GFX driver unload #define PPSMC_MSG_SetDriverDramAddrHigh 0x0D ///< Set high 32 bits of DRAM address for Driver table transfer #define PPSMC_MSG_SetDriverDramAddrLow 0x0E ///< Set low 32 bits of DRAM address for Driver table transfer @@ -73,8 +73,7 @@ #define PPSMC_MSG_SetSoftMinFclk 0x14 ///< Set hard min for FCLK #define PPSMC_MSG_SetSoftMinVcn 0x15 ///< Set soft min for VCN clocks (VCLK and DCLK) - -#define PPSMC_MSG_EnableGfxImu 0x16 ///< Needs update +#define PPSMC_MSG_EnableGfxImu 0x16 ///< Enable GFX IMU #define PPSMC_MSG_GetGfxclkFrequency 0x17 ///< Get GFX clock frequency #define PPSMC_MSG_GetFclkFrequency 0x18 ///< Get FCLK frequency @@ -102,8 +101,8 @@ #define PPSMC_MSG_SetHardMinIspxclkByFreq 0x2C ///< Set HardMin by frequency for ISPXCLK #define PPSMC_MSG_PowerDownUmsch 0x2D ///< Power down VCN.UMSCH (aka VSCH) scheduler #define PPSMC_MSG_PowerUpUmsch 0x2E ///< Power up VCN.UMSCH (aka VSCH) scheduler -#define PPSMC_Message_IspStutterOn_MmhubPgDis 0x2F ///< ISP StutterOn mmHub PgDis -#define PPSMC_Message_IspStutterOff_MmhubPgEn 0x30 ///< ISP StufferOff mmHub PgEn +#define PPSMC_MSG_IspStutterOn_MmhubPgDis 0x2F ///< ISP StutterOn mmHub PgDis +#define PPSMC_MSG_IspStutterOff_MmhubPgEn 0x30 ///< ISP StufferOff mmHub PgEn #define PPSMC_Message_Count 0x31 ///< Total number of PPSMC messages /** @}*/ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index 74996a8fb671..6212fd270857 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -377,7 +377,9 @@ static void sienna_cichlid_check_bxco_support(struct smu_context *smu) if (((adev->pdev->device == 0x73A1) && (adev->pdev->revision == 0x00)) || ((adev->pdev->device == 0x73BF) && - (adev->pdev->revision == 0xCF))) + (adev->pdev->revision == 0xCF)) || + ((adev->pdev->device == 0x7422) && + (adev->pdev->revision == 0x00))) smu_baco->platform_support = false; } diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 8a0c0e0bb5bd..52d8800a8ab8 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -134,6 +134,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "One S1003"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* Acer Switch V 10 (SW5-017) */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "SW5-017"), + }, + .driver_data = (void *)&lcd800x1280_rightside_up, }, { /* Anbernic Win600 */ .matches = { DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "Anbernic"), @@ -319,6 +325,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_MATCH(DMI_BIOS_VERSION, "BLADE_21"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Nanote UMPC-01 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "RWC CO.,LTD"), + DMI_MATCH(DMI_PRODUCT_NAME, "UMPC-01"), + }, + .driver_data = (void *)&lcd1200x1920_rightside_up, }, { /* OneGX1 Pro */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SYSTEM_MANUFACTURER"), diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c index e246d914e7f6..4e83a1891f3e 100644 --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c @@ -250,13 +250,22 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev) static size_t get_pgsize(u64 addr, size_t size, size_t *count) { + /* + * io-pgtable only operates on multiple pages within a single table + * entry, so we need to split at boundaries of the table size, i.e. + * the next block size up. The distance from address A to the next + * boundary of block size B is logically B - A % B, but in unsigned + * two's complement where B is a power of two we get the equivalence + * B - A % B == (B - A) % B == (n * B - A) % B, and choose n = 0 :) + */ size_t blk_offset = -addr % SZ_2M; if (blk_offset || size < SZ_2M) { *count = min_not_zero(blk_offset, size) / SZ_4K; return SZ_4K; } - *count = size / SZ_2M; + blk_offset = -addr % SZ_1G ?: SZ_1G; + *count = min(blk_offset, size) / SZ_2M; return SZ_2M; } diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index 2027063fdc30..8c329c071c62 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -476,7 +476,12 @@ static int __init vc4_drm_register(void) if (ret) return ret; - return platform_driver_register(&vc4_platform_driver); + ret = platform_driver_register(&vc4_platform_driver); + if (ret) + platform_unregister_drivers(component_drivers, + ARRAY_SIZE(component_drivers)); + + return ret; } static void __exit vc4_drm_unregister(void) diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 596e311d6e58..470432c8fd70 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -349,27 +349,40 @@ static int vc4_hdmi_reset_link(struct drm_connector *connector, if (!crtc_state->active) return 0; - if (!vc4_hdmi_supports_scrambling(encoder)) + mutex_lock(&vc4_hdmi->mutex); + + if (!vc4_hdmi_supports_scrambling(encoder)) { + mutex_unlock(&vc4_hdmi->mutex); return 0; + } scrambling_needed = vc4_hdmi_mode_needs_scrambling(&vc4_hdmi->saved_adjusted_mode, vc4_hdmi->output_bpc, vc4_hdmi->output_format); - if (!scrambling_needed) + if (!scrambling_needed) { + mutex_unlock(&vc4_hdmi->mutex); return 0; + } if (conn_state->commit && - !try_wait_for_completion(&conn_state->commit->hw_done)) + !try_wait_for_completion(&conn_state->commit->hw_done)) { + mutex_unlock(&vc4_hdmi->mutex); return 0; + } ret = drm_scdc_readb(connector->ddc, SCDC_TMDS_CONFIG, &config); if (ret < 0) { drm_err(drm, "Failed to read TMDS config: %d\n", ret); + mutex_unlock(&vc4_hdmi->mutex); return 0; } - if (!!(config & SCDC_SCRAMBLING_ENABLE) == scrambling_needed) + if (!!(config & SCDC_SCRAMBLING_ENABLE) == scrambling_needed) { + mutex_unlock(&vc4_hdmi->mutex); return 0; + } + + mutex_unlock(&vc4_hdmi->mutex); /* * HDMI 2.0 says that one should not send scrambled data @@ -397,9 +410,8 @@ static void vc4_hdmi_handle_hotplug(struct vc4_hdmi *vc4_hdmi, * .adap_enable, which leads to that funtion being called with * our mutex held. * - * A similar situation occurs with - * drm_atomic_helper_connector_hdmi_reset_link() that will call - * into our KMS hooks if the scrambling was enabled. + * A similar situation occurs with vc4_hdmi_reset_link() that + * will call into our KMS hooks if the scrambling was enabled. * * Concurrency isn't an issue at the moment since we don't share * any state with any of the other frameworks so we can ignore @@ -3160,9 +3172,16 @@ static int vc4_hdmi_init_resources(struct drm_device *drm, DRM_ERROR("Failed to get HDMI state machine clock\n"); return PTR_ERR(vc4_hdmi->hsm_clock); } + vc4_hdmi->audio_clock = vc4_hdmi->hsm_clock; vc4_hdmi->cec_clock = vc4_hdmi->hsm_clock; + vc4_hdmi->hsm_rpm_clock = devm_clk_get(dev, "hdmi"); + if (IS_ERR(vc4_hdmi->hsm_rpm_clock)) { + DRM_ERROR("Failed to get HDMI state machine clock\n"); + return PTR_ERR(vc4_hdmi->hsm_rpm_clock); + } + return 0; } @@ -3245,6 +3264,12 @@ static int vc5_hdmi_init_resources(struct drm_device *drm, return PTR_ERR(vc4_hdmi->hsm_clock); } + vc4_hdmi->hsm_rpm_clock = devm_clk_get(dev, "hdmi"); + if (IS_ERR(vc4_hdmi->hsm_rpm_clock)) { + DRM_ERROR("Failed to get HDMI state machine clock\n"); + return PTR_ERR(vc4_hdmi->hsm_rpm_clock); + } + vc4_hdmi->pixel_bvb_clock = devm_clk_get(dev, "bvb"); if (IS_ERR(vc4_hdmi->pixel_bvb_clock)) { DRM_ERROR("Failed to get pixel bvb clock\n"); @@ -3308,7 +3333,7 @@ static int vc4_hdmi_runtime_suspend(struct device *dev) { struct vc4_hdmi *vc4_hdmi = dev_get_drvdata(dev); - clk_disable_unprepare(vc4_hdmi->hsm_clock); + clk_disable_unprepare(vc4_hdmi->hsm_rpm_clock); return 0; } @@ -3326,11 +3351,11 @@ static int vc4_hdmi_runtime_resume(struct device *dev) * its frequency while the power domain is active so that it * keeps its rate. */ - ret = clk_set_min_rate(vc4_hdmi->hsm_clock, HSM_MIN_CLOCK_FREQ); + ret = clk_set_min_rate(vc4_hdmi->hsm_rpm_clock, HSM_MIN_CLOCK_FREQ); if (ret) return ret; - ret = clk_prepare_enable(vc4_hdmi->hsm_clock); + ret = clk_prepare_enable(vc4_hdmi->hsm_rpm_clock); if (ret) return ret; @@ -3343,7 +3368,7 @@ static int vc4_hdmi_runtime_resume(struct device *dev) * case, it will lead to a silent CPU stall. Let's make sure we * prevent such a case. */ - rate = clk_get_rate(vc4_hdmi->hsm_clock); + rate = clk_get_rate(vc4_hdmi->hsm_rpm_clock); if (!rate) { ret = -EINVAL; goto err_disable_clk; diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.h b/drivers/gpu/drm/vc4/vc4_hdmi.h index db823efb2563..1ad8e8c377e2 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.h +++ b/drivers/gpu/drm/vc4/vc4_hdmi.h @@ -172,6 +172,7 @@ struct vc4_hdmi { struct clk *cec_clock; struct clk *pixel_clock; struct clk *hsm_clock; + struct clk *hsm_rpm_clock; struct clk *audio_clock; struct clk *pixel_bvb_clock; diff --git a/drivers/hwmon/pmbus/pmbus.h b/drivers/hwmon/pmbus/pmbus.h index 7daaf0caf4d3..10fb17879f8e 100644 --- a/drivers/hwmon/pmbus/pmbus.h +++ b/drivers/hwmon/pmbus/pmbus.h @@ -467,7 +467,6 @@ extern const struct regulator_ops pmbus_regulator_ops; #define PMBUS_REGULATOR_STEP(_name, _id, _voltages, _step) \ [_id] = { \ .name = (_name # _id), \ - .supply_name = "vin", \ .id = (_id), \ .of_match = of_match_ptr(_name # _id), \ .regulators_node = of_match_ptr("regulators"), \ diff --git a/drivers/hwmon/scmi-hwmon.c b/drivers/hwmon/scmi-hwmon.c index b1329a58ce40..e192f0c67146 100644 --- a/drivers/hwmon/scmi-hwmon.c +++ b/drivers/hwmon/scmi-hwmon.c @@ -20,6 +20,11 @@ struct scmi_sensors { const struct scmi_sensor_info **info[hwmon_max]; }; +struct scmi_thermal_sensor { + const struct scmi_protocol_handle *ph; + const struct scmi_sensor_info *info; +}; + static inline u64 __pow10(u8 x) { u64 r = 1; @@ -64,16 +69,14 @@ static int scmi_hwmon_scale(const struct scmi_sensor_info *sensor, u64 *value) return 0; } -static int scmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type, - u32 attr, int channel, long *val) +static int scmi_hwmon_read_scaled_value(const struct scmi_protocol_handle *ph, + const struct scmi_sensor_info *sensor, + long *val) { int ret; u64 value; - const struct scmi_sensor_info *sensor; - struct scmi_sensors *scmi_sensors = dev_get_drvdata(dev); - sensor = *(scmi_sensors->info[type] + channel); - ret = sensor_ops->reading_get(scmi_sensors->ph, sensor->id, &value); + ret = sensor_ops->reading_get(ph, sensor->id, &value); if (ret) return ret; @@ -84,6 +87,17 @@ static int scmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type, return ret; } +static int scmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type, + u32 attr, int channel, long *val) +{ + const struct scmi_sensor_info *sensor; + struct scmi_sensors *scmi_sensors = dev_get_drvdata(dev); + + sensor = *(scmi_sensors->info[type] + channel); + + return scmi_hwmon_read_scaled_value(scmi_sensors->ph, sensor, val); +} + static int scmi_hwmon_read_string(struct device *dev, enum hwmon_sensor_types type, u32 attr, int channel, const char **str) @@ -122,6 +136,25 @@ static struct hwmon_chip_info scmi_chip_info = { .info = NULL, }; +static int scmi_hwmon_thermal_get_temp(struct thermal_zone_device *tz, + int *temp) +{ + int ret; + long value; + struct scmi_thermal_sensor *th_sensor = tz->devdata; + + ret = scmi_hwmon_read_scaled_value(th_sensor->ph, th_sensor->info, + &value); + if (!ret) + *temp = value; + + return ret; +} + +static const struct thermal_zone_device_ops scmi_hwmon_thermal_ops = { + .get_temp = scmi_hwmon_thermal_get_temp, +}; + static int scmi_hwmon_add_chan_info(struct hwmon_channel_info *scmi_hwmon_chan, struct device *dev, int num, enum hwmon_sensor_types type, u32 config) @@ -149,7 +182,6 @@ static enum hwmon_sensor_types scmi_types[] = { }; static u32 hwmon_attributes[hwmon_max] = { - [hwmon_chip] = HWMON_C_REGISTER_TZ, [hwmon_temp] = HWMON_T_INPUT | HWMON_T_LABEL, [hwmon_in] = HWMON_I_INPUT | HWMON_I_LABEL, [hwmon_curr] = HWMON_C_INPUT | HWMON_C_LABEL, @@ -157,6 +189,43 @@ static u32 hwmon_attributes[hwmon_max] = { [hwmon_energy] = HWMON_E_INPUT | HWMON_E_LABEL, }; +static int scmi_thermal_sensor_register(struct device *dev, + const struct scmi_protocol_handle *ph, + const struct scmi_sensor_info *sensor) +{ + struct scmi_thermal_sensor *th_sensor; + struct thermal_zone_device *tzd; + + th_sensor = devm_kzalloc(dev, sizeof(*th_sensor), GFP_KERNEL); + if (!th_sensor) + return -ENOMEM; + + th_sensor->ph = ph; + th_sensor->info = sensor; + + /* + * Try to register a temperature sensor with the Thermal Framework: + * skip sensors not defined as part of any thermal zone (-ENODEV) but + * report any other errors related to misconfigured zones/sensors. + */ + tzd = devm_thermal_of_zone_register(dev, th_sensor->info->id, th_sensor, + &scmi_hwmon_thermal_ops); + if (IS_ERR(tzd)) { + devm_kfree(dev, th_sensor); + + if (PTR_ERR(tzd) != -ENODEV) + return PTR_ERR(tzd); + + dev_dbg(dev, "Sensor '%s' not attached to any thermal zone.\n", + sensor->name); + } else { + dev_dbg(dev, "Sensor '%s' attached to thermal zone ID:%d\n", + sensor->name, tzd->id); + } + + return 0; +} + static int scmi_hwmon_probe(struct scmi_device *sdev) { int i, idx; @@ -164,7 +233,7 @@ static int scmi_hwmon_probe(struct scmi_device *sdev) enum hwmon_sensor_types type; struct scmi_sensors *scmi_sensors; const struct scmi_sensor_info *sensor; - int nr_count[hwmon_max] = {0}, nr_types = 0; + int nr_count[hwmon_max] = {0}, nr_types = 0, nr_count_temp = 0; const struct hwmon_chip_info *chip_info; struct device *hwdev, *dev = &sdev->dev; struct hwmon_channel_info *scmi_hwmon_chan; @@ -208,10 +277,8 @@ static int scmi_hwmon_probe(struct scmi_device *sdev) } } - if (nr_count[hwmon_temp]) { - nr_count[hwmon_chip]++; - nr_types++; - } + if (nr_count[hwmon_temp]) + nr_count_temp = nr_count[hwmon_temp]; scmi_hwmon_chan = devm_kcalloc(dev, nr_types, sizeof(*scmi_hwmon_chan), GFP_KERNEL); @@ -262,8 +329,31 @@ static int scmi_hwmon_probe(struct scmi_device *sdev) hwdev = devm_hwmon_device_register_with_info(dev, "scmi_sensors", scmi_sensors, chip_info, NULL); + if (IS_ERR(hwdev)) + return PTR_ERR(hwdev); - return PTR_ERR_OR_ZERO(hwdev); + for (i = 0; i < nr_count_temp; i++) { + int ret; + + sensor = *(scmi_sensors->info[hwmon_temp] + i); + if (!sensor) + continue; + + /* + * Warn on any misconfiguration related to thermal zones but + * bail out of probing only on memory errors. + */ + ret = scmi_thermal_sensor_register(dev, ph, sensor); + if (ret) { + if (ret == -ENOMEM) + return ret; + dev_warn(dev, + "Thermal zone misconfigured for %s. err=%d\n", + sensor->name, ret); + } + } + + return 0; } static const struct scmi_device_id scmi_id_table[] = { diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index e06509edc5f3..1fda1eaa6d6a 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1243,6 +1243,7 @@ static const struct { */ { "Latitude 5480", 0x29 }, { "Vostro V131", 0x1d }, + { "Vostro 5568", 0x29 }, }; static void register_dell_lis3lv02d_i2c_device(struct i801_priv *priv) diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c index 39cb1b7bb865..809fbd014cd6 100644 --- a/drivers/i2c/busses/i2c-piix4.c +++ b/drivers/i2c/busses/i2c-piix4.c @@ -1080,6 +1080,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id) "", &piix4_main_adapters[0]); if (retval < 0) return retval; + piix4_adapter_count = 1; } /* Check for auxiliary SMBus on some AMD chipsets */ diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c index 954022c04cc4..3869c258a529 100644 --- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -284,6 +284,7 @@ struct tegra_i2c_dev { struct dma_chan *tx_dma_chan; struct dma_chan *rx_dma_chan; unsigned int dma_buf_size; + struct device *dma_dev; dma_addr_t dma_phys; void *dma_buf; @@ -420,7 +421,7 @@ static int tegra_i2c_dma_submit(struct tegra_i2c_dev *i2c_dev, size_t len) static void tegra_i2c_release_dma(struct tegra_i2c_dev *i2c_dev) { if (i2c_dev->dma_buf) { - dma_free_coherent(i2c_dev->dev, i2c_dev->dma_buf_size, + dma_free_coherent(i2c_dev->dma_dev, i2c_dev->dma_buf_size, i2c_dev->dma_buf, i2c_dev->dma_phys); i2c_dev->dma_buf = NULL; } @@ -472,10 +473,13 @@ static int tegra_i2c_init_dma(struct tegra_i2c_dev *i2c_dev) i2c_dev->tx_dma_chan = chan; + WARN_ON(i2c_dev->tx_dma_chan->device != i2c_dev->rx_dma_chan->device); + i2c_dev->dma_dev = chan->device->dev; + i2c_dev->dma_buf_size = i2c_dev->hw->quirks->max_write_len + I2C_PACKET_HEADER_SIZE; - dma_buf = dma_alloc_coherent(i2c_dev->dev, i2c_dev->dma_buf_size, + dma_buf = dma_alloc_coherent(i2c_dev->dma_dev, i2c_dev->dma_buf_size, &dma_phys, GFP_KERNEL | __GFP_NOWARN); if (!dma_buf) { dev_err(i2c_dev->dev, "failed to allocate DMA buffer\n"); @@ -1272,7 +1276,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, if (i2c_dev->dma_mode) { if (i2c_dev->msg_read) { - dma_sync_single_for_device(i2c_dev->dev, + dma_sync_single_for_device(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_FROM_DEVICE); @@ -1280,7 +1284,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, if (err) return err; } else { - dma_sync_single_for_cpu(i2c_dev->dev, + dma_sync_single_for_cpu(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_TO_DEVICE); } @@ -1293,7 +1297,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, memcpy(i2c_dev->dma_buf + I2C_PACKET_HEADER_SIZE, msg->buf, msg->len); - dma_sync_single_for_device(i2c_dev->dev, + dma_sync_single_for_device(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_TO_DEVICE); @@ -1344,7 +1348,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev, } if (i2c_dev->msg_read && i2c_dev->msg_err == I2C_ERR_NONE) { - dma_sync_single_for_cpu(i2c_dev->dev, + dma_sync_single_for_cpu(i2c_dev->dma_dev, i2c_dev->dma_phys, xfer_size, DMA_FROM_DEVICE); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index cc2222b85c88..26d1772179b8 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -1556,7 +1556,7 @@ static bool validate_ipv4_net_dev(struct net_device *net_dev, return false; memset(&fl4, 0, sizeof(fl4)); - fl4.flowi4_iif = net_dev->ifindex; + fl4.flowi4_oif = net_dev->ifindex; fl4.daddr = daddr; fl4.saddr = saddr; diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index ae60c73babcc..b69e2c4e4d2a 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -2815,10 +2815,18 @@ static int __init ib_core_init(void) nldev_init(); rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table); - roce_gid_mgmt_init(); + ret = roce_gid_mgmt_init(); + if (ret) { + pr_warn("Couldn't init RoCE GID management\n"); + goto err_parent; + } return 0; +err_parent: + rdma_nl_unregister(RDMA_NL_LS); + nldev_exit(); + unregister_pernet_device(&rdma_dev_net_ops); err_compat: unregister_blocking_lsm_notifier(&ibdev_lsm_nb); err_sa: diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c index b92358f606d0..12dc97067ed2 100644 --- a/drivers/infiniband/core/nldev.c +++ b/drivers/infiniband/core/nldev.c @@ -2537,7 +2537,7 @@ void __init nldev_init(void) rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table); } -void __exit nldev_exit(void) +void nldev_exit(void) { rdma_nl_unregister(RDMA_NL_NLDEV); } diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c index 94b94cca4870..15ee92081118 100644 --- a/drivers/infiniband/hw/efa/efa_main.c +++ b/drivers/infiniband/hw/efa/efa_main.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause /* - * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved. + * Copyright 2018-2022 Amazon.com, Inc. or its affiliates. All rights reserved. */ #include <linux/module.h> @@ -14,10 +14,12 @@ #define PCI_DEV_ID_EFA0_VF 0xefa0 #define PCI_DEV_ID_EFA1_VF 0xefa1 +#define PCI_DEV_ID_EFA2_VF 0xefa2 static const struct pci_device_id efa_pci_tbl[] = { { PCI_VDEVICE(AMAZON, PCI_DEV_ID_EFA0_VF) }, { PCI_VDEVICE(AMAZON, PCI_DEV_ID_EFA1_VF) }, + { PCI_VDEVICE(AMAZON, PCI_DEV_ID_EFA2_VF) }, { } }; diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 3d42bd2b36bd..51ae58c02b15 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -913,8 +913,7 @@ void sc_disable(struct send_context *sc) spin_unlock(&sc->release_lock); write_seqlock(&sc->waitlock); - if (!list_empty(&sc->piowait)) - list_move(&sc->piowait, &wake_list); + list_splice_init(&sc->piowait, &wake_list); write_sequnlock(&sc->waitlock); while (!list_empty(&wake_list)) { struct iowait *wait; diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 1ead35fb031b..1435fe2ea176 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -118,7 +118,6 @@ static const u32 hns_roce_op_code[] = { HR_OPC_MAP(ATOMIC_CMP_AND_SWP, ATOM_CMP_AND_SWAP), HR_OPC_MAP(ATOMIC_FETCH_AND_ADD, ATOM_FETCH_AND_ADD), HR_OPC_MAP(SEND_WITH_INV, SEND_WITH_INV), - HR_OPC_MAP(LOCAL_INV, LOCAL_INV), HR_OPC_MAP(MASKED_ATOMIC_CMP_AND_SWP, ATOM_MSK_CMP_AND_SWAP), HR_OPC_MAP(MASKED_ATOMIC_FETCH_AND_ADD, ATOM_MSK_FETCH_AND_ADD), HR_OPC_MAP(REG_MR, FAST_REG_PMR), @@ -559,9 +558,6 @@ static int set_rc_opcode(struct hns_roce_dev *hr_dev, else ret = -EOPNOTSUPP; break; - case IB_WR_LOCAL_INV: - hr_reg_enable(rc_sq_wqe, RC_SEND_WQE_SO); - fallthrough; case IB_WR_SEND_WITH_INV: rc_sq_wqe->inv_key = cpu_to_le32(wr->ex.invalidate_rkey); break; @@ -2805,8 +2801,12 @@ static int free_mr_modify_qp(struct hns_roce_dev *hr_dev) static int free_mr_init(struct hns_roce_dev *hr_dev) { + struct hns_roce_v2_priv *priv = hr_dev->priv; + struct hns_roce_v2_free_mr *free_mr = &priv->free_mr; int ret; + mutex_init(&free_mr->mutex); + ret = free_mr_alloc_res(hr_dev); if (ret) return ret; @@ -3222,7 +3222,6 @@ static int hns_roce_v2_write_mtpt(struct hns_roce_dev *hr_dev, hr_reg_write(mpt_entry, MPT_ST, V2_MPT_ST_VALID); hr_reg_write(mpt_entry, MPT_PD, mr->pd); - hr_reg_enable(mpt_entry, MPT_L_INV_EN); hr_reg_write_bool(mpt_entry, MPT_BIND_EN, mr->access & IB_ACCESS_MW_BIND); @@ -3313,7 +3312,6 @@ static int hns_roce_v2_frmr_write_mtpt(struct hns_roce_dev *hr_dev, hr_reg_enable(mpt_entry, MPT_RA_EN); hr_reg_enable(mpt_entry, MPT_R_INV_EN); - hr_reg_enable(mpt_entry, MPT_L_INV_EN); hr_reg_enable(mpt_entry, MPT_FRE); hr_reg_clear(mpt_entry, MPT_MR_MW); @@ -3345,7 +3343,6 @@ static int hns_roce_v2_mw_write_mtpt(void *mb_buf, struct hns_roce_mw *mw) hr_reg_write(mpt_entry, MPT_PD, mw->pdn); hr_reg_enable(mpt_entry, MPT_R_INV_EN); - hr_reg_enable(mpt_entry, MPT_L_INV_EN); hr_reg_enable(mpt_entry, MPT_LW_EN); hr_reg_enable(mpt_entry, MPT_MR_MW); @@ -3794,7 +3791,6 @@ static const u32 wc_send_op_map[] = { HR_WC_OP_MAP(RDMA_READ, RDMA_READ), HR_WC_OP_MAP(RDMA_WRITE, RDMA_WRITE), HR_WC_OP_MAP(RDMA_WRITE_WITH_IMM, RDMA_WRITE), - HR_WC_OP_MAP(LOCAL_INV, LOCAL_INV), HR_WC_OP_MAP(ATOM_CMP_AND_SWAP, COMP_SWAP), HR_WC_OP_MAP(ATOM_FETCH_AND_ADD, FETCH_ADD), HR_WC_OP_MAP(ATOM_MSK_CMP_AND_SWAP, MASKED_COMP_SWAP), @@ -3844,9 +3840,6 @@ static void fill_send_wc(struct ib_wc *wc, struct hns_roce_v2_cqe *cqe) case HNS_ROCE_V2_WQE_OP_RDMA_WRITE_WITH_IMM: wc->wc_flags |= IB_WC_WITH_IMM; break; - case HNS_ROCE_V2_WQE_OP_LOCAL_INV: - wc->wc_flags |= IB_WC_WITH_INVALIDATE; - break; case HNS_ROCE_V2_WQE_OP_ATOM_CMP_AND_SWAP: case HNS_ROCE_V2_WQE_OP_ATOM_FETCH_AND_ADD: case HNS_ROCE_V2_WQE_OP_ATOM_MSK_CMP_AND_SWAP: diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index b11579027e82..c7bf2d52c1cd 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -179,7 +179,6 @@ enum { HNS_ROCE_V2_WQE_OP_ATOM_MSK_CMP_AND_SWAP = 0x8, HNS_ROCE_V2_WQE_OP_ATOM_MSK_FETCH_AND_ADD = 0x9, HNS_ROCE_V2_WQE_OP_FAST_REG_PMR = 0xa, - HNS_ROCE_V2_WQE_OP_LOCAL_INV = 0xb, HNS_ROCE_V2_WQE_OP_BIND_MW = 0xc, HNS_ROCE_V2_WQE_OP_MASK = 0x1f, }; @@ -915,7 +914,6 @@ struct hns_roce_v2_rc_send_wqe { #define RC_SEND_WQE_OWNER RC_SEND_WQE_FIELD_LOC(7, 7) #define RC_SEND_WQE_CQE RC_SEND_WQE_FIELD_LOC(8, 8) #define RC_SEND_WQE_FENCE RC_SEND_WQE_FIELD_LOC(9, 9) -#define RC_SEND_WQE_SO RC_SEND_WQE_FIELD_LOC(10, 10) #define RC_SEND_WQE_SE RC_SEND_WQE_FIELD_LOC(11, 11) #define RC_SEND_WQE_INLINE RC_SEND_WQE_FIELD_LOC(12, 12) #define RC_SEND_WQE_WQE_INDEX RC_SEND_WQE_FIELD_LOC(30, 15) diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c index 5152f10d2e6d..ba0c3e4c07d8 100644 --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@ -344,6 +344,10 @@ static int qedr_alloc_resources(struct qedr_dev *dev) if (IS_IWARP(dev)) { xa_init(&dev->qps); dev->iwarp_wq = create_singlethread_workqueue("qedr_iwarpq"); + if (!dev->iwarp_wq) { + rc = -ENOMEM; + goto err1; + } } /* Allocate Status blocks for CNQ */ @@ -351,7 +355,7 @@ static int qedr_alloc_resources(struct qedr_dev *dev) GFP_KERNEL); if (!dev->sb_array) { rc = -ENOMEM; - goto err1; + goto err_destroy_wq; } dev->cnq_array = kcalloc(dev->num_cnq, @@ -402,6 +406,9 @@ err3: kfree(dev->cnq_array); err2: kfree(dev->sb_array); +err_destroy_wq: + if (IS_IWARP(dev)) + destroy_workqueue(dev->iwarp_wq); err1: kfree(dev->sgid_tbl); return rc; diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c index ed5a09e86417..693081e813ec 100644 --- a/drivers/infiniband/sw/rxe/rxe_resp.c +++ b/drivers/infiniband/sw/rxe/rxe_resp.c @@ -806,8 +806,10 @@ static enum resp_states read_reply(struct rxe_qp *qp, skb = prepare_ack_packet(qp, &ack_pkt, opcode, payload, res->cur_psn, AETH_ACK_UNLIMITED); - if (!skb) + if (!skb) { + rxe_put(mr); return RESPST_ERR_RNR; + } rxe_mr_copy(mr, res->read.va, payload_addr(&ack_pkt), payload, RXE_FROM_MR_OBJ); diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index a52f275f8263..f8447135a902 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -956,7 +956,7 @@ nj_release(struct tiger_hw *card) } if (card->irq > 0) free_irq(card->irq, card); - if (card->isac.dch.dev.dev.class) + if (device_is_registered(&card->isac.dch.dev.dev)) mISDN_unregister_device(&card->isac.dch.dev); for (i = 0; i < 2; i++) { diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c index a41b4b264594..7ea0100f218a 100644 --- a/drivers/isdn/mISDN/core.c +++ b/drivers/isdn/mISDN/core.c @@ -233,11 +233,12 @@ mISDN_register_device(struct mISDNdevice *dev, if (debug & DEBUG_CORE) printk(KERN_DEBUG "mISDN_register %s %d\n", dev_name(&dev->dev), dev->id); + dev->dev.class = &mISDN_class; + err = create_stack(dev); if (err) goto error1; - dev->dev.class = &mISDN_class; dev->dev.platform_data = dev; dev->dev.parent = parent; dev_set_drvdata(&dev->dev, dev); @@ -249,8 +250,8 @@ mISDN_register_device(struct mISDNdevice *dev, error3: delete_stack(dev); - return err; error1: + put_device(&dev->dev); return err; } diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index b9107fe40023..5b139f2206b6 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -376,6 +376,17 @@ static struct mdio_driver dsa_loop_drv = { #define NUM_FIXED_PHYS (DSA_LOOP_NUM_PORTS - 2) +static void dsa_loop_phydevs_unregister(void) +{ + unsigned int i; + + for (i = 0; i < NUM_FIXED_PHYS; i++) + if (!IS_ERR(phydevs[i])) { + fixed_phy_unregister(phydevs[i]); + phy_device_free(phydevs[i]); + } +} + static int __init dsa_loop_init(void) { struct fixed_phy_status status = { @@ -383,23 +394,23 @@ static int __init dsa_loop_init(void) .speed = SPEED_100, .duplex = DUPLEX_FULL, }; - unsigned int i; + unsigned int i, ret; for (i = 0; i < NUM_FIXED_PHYS; i++) phydevs[i] = fixed_phy_register(PHY_POLL, &status, NULL); - return mdio_driver_register(&dsa_loop_drv); + ret = mdio_driver_register(&dsa_loop_drv); + if (ret) + dsa_loop_phydevs_unregister(); + + return ret; } module_init(dsa_loop_init); static void __exit dsa_loop_exit(void) { - unsigned int i; - mdio_driver_unregister(&dsa_loop_drv); - for (i = 0; i < NUM_FIXED_PHYS; i++) - if (!IS_ERR(phydevs[i])) - fixed_phy_unregister(phydevs[i]); + dsa_loop_phydevs_unregister(); } module_exit(dsa_loop_exit); diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index 1744d623999d..606c97610808 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -1512,16 +1512,15 @@ static struct notifier_block adin1110_switchdev_notifier = { .notifier_call = adin1110_switchdev_event, }; -static void adin1110_unregister_notifiers(void *data) +static void adin1110_unregister_notifiers(void) { unregister_switchdev_blocking_notifier(&adin1110_switchdev_blocking_notifier); unregister_switchdev_notifier(&adin1110_switchdev_notifier); unregister_netdevice_notifier(&adin1110_netdevice_nb); } -static int adin1110_setup_notifiers(struct adin1110_priv *priv) +static int adin1110_setup_notifiers(void) { - struct device *dev = &priv->spidev->dev; int ret; ret = register_netdevice_notifier(&adin1110_netdevice_nb); @@ -1536,13 +1535,14 @@ static int adin1110_setup_notifiers(struct adin1110_priv *priv) if (ret < 0) goto err_sdev; - return devm_add_action_or_reset(dev, adin1110_unregister_notifiers, NULL); + return 0; err_sdev: unregister_switchdev_notifier(&adin1110_switchdev_notifier); err_netdev: unregister_netdevice_notifier(&adin1110_netdevice_nb); + return ret; } @@ -1613,10 +1613,6 @@ static int adin1110_probe_netdevs(struct adin1110_priv *priv) if (ret < 0) return ret; - ret = adin1110_setup_notifiers(priv); - if (ret < 0) - return ret; - for (i = 0; i < priv->cfg->ports_nr; i++) { ret = devm_register_netdev(dev, priv->ports[i]->netdev); if (ret < 0) { @@ -1693,7 +1689,31 @@ static struct spi_driver adin1110_driver = { .probe = adin1110_probe, .id_table = adin1110_spi_id, }; -module_spi_driver(adin1110_driver); + +static int __init adin1110_driver_init(void) +{ + int ret; + + ret = adin1110_setup_notifiers(); + if (ret < 0) + return ret; + + ret = spi_register_driver(&adin1110_driver); + if (ret < 0) { + adin1110_unregister_notifiers(); + return ret; + } + + return 0; +} + +static void __exit adin1110_exit(void) +{ + adin1110_unregister_notifiers(); + spi_unregister_driver(&adin1110_driver); +} +module_init(adin1110_driver_init); +module_exit(adin1110_exit); MODULE_DESCRIPTION("ADIN1110 Network driver"); MODULE_AUTHOR("Alexandru Tachici <alexandru.tachici@analog.com>"); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 28ef4d3c1878..f623c12eaf95 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -713,7 +713,7 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb, dev_kfree_skb_any(skb); if (net_ratelimit()) netdev_err(ndev, "Tx DMA memory map failed\n"); - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } bdp->cbd_datlen = cpu_to_fec16(size); @@ -775,7 +775,7 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq, dev_kfree_skb_any(skb); if (net_ratelimit()) netdev_err(ndev, "Tx DMA memory map failed\n"); - return NETDEV_TX_BUSY; + return NETDEV_TX_OK; } } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 65dbfbec487a..9282381a438f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -3007,19 +3007,19 @@ static void __ibmvnic_reset(struct work_struct *work) rwi = get_next_rwi(adapter); /* - * If there is another reset queued, free the previous rwi - * and process the new reset even if previous reset failed - * (the previous reset could have failed because of a fail - * over for instance, so process the fail over). - * * If there are no resets queued and the previous reset failed, * the adapter would be in an undefined state. So retry the * previous reset as a hard reset. + * + * Else, free the previous rwi and, if there is another reset + * queued, process the new reset even if previous reset failed + * (the previous reset could have failed because of a fail + * over for instance, so process the fail over). */ - if (rwi) - kfree(tmprwi); - else if (rc) + if (!rwi && rc) rwi = tmprwi; + else + kfree(tmprwi); if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER || rwi->reset_reason == VNIC_RESET_MOBILITY || rc)) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c index a42035cec611..e6948939ccc2 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c @@ -414,13 +414,15 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx) /* Get the received frame and unmap it */ db = &rx->dcbs[rx->dcb_index].db[rx->db_index]; page = rx->page[rx->dcb_index][rx->db_index]; + + dma_sync_single_for_cpu(lan966x->dev, (dma_addr_t)db->dataptr, + FDMA_DCB_STATUS_BLOCKL(db->status), + DMA_FROM_DEVICE); + skb = build_skb(page_address(page), PAGE_SIZE << rx->page_order); if (unlikely(!skb)) goto unmap_page; - dma_unmap_single(lan966x->dev, (dma_addr_t)db->dataptr, - FDMA_DCB_STATUS_BLOCKL(db->status), - DMA_FROM_DEVICE); skb_put(skb, FDMA_DCB_STATUS_BLOCKL(db->status)); lan966x_ifh_get_src_port(skb->data, &src_port); @@ -429,6 +431,10 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx) if (WARN_ON(src_port >= lan966x->num_phys_ports)) goto free_skb; + dma_unmap_single_attrs(lan966x->dev, (dma_addr_t)db->dataptr, + PAGE_SIZE << rx->page_order, DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); + skb->dev = lan966x->ports[src_port]->dev; skb_pull(skb, IFH_LEN * sizeof(u32)); @@ -454,9 +460,9 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx) free_skb: kfree_skb(skb); unmap_page: - dma_unmap_page(lan966x->dev, (dma_addr_t)db->dataptr, - FDMA_DCB_STATUS_BLOCKL(db->status), - DMA_FROM_DEVICE); + dma_unmap_single_attrs(lan966x->dev, (dma_addr_t)db->dataptr, + PAGE_SIZE << rx->page_order, DMA_FROM_DEVICE, + DMA_ATTR_SKIP_CPU_SYNC); __free_pages(page, rx->page_order); return NULL; @@ -668,12 +674,14 @@ static int lan966x_fdma_get_max_mtu(struct lan966x *lan966x) int i; for (i = 0; i < lan966x->num_phys_ports; ++i) { + struct lan966x_port *port; int mtu; - if (!lan966x->ports[i]) + port = lan966x->ports[i]; + if (!port) continue; - mtu = lan966x->ports[i]->dev->mtu; + mtu = lan_rd(lan966x, DEV_MAC_MAXLEN_CFG(port->chip_port)); if (mtu > max_mtu) max_mtu = mtu; } @@ -733,6 +741,8 @@ int lan966x_fdma_change_mtu(struct lan966x *lan966x) max_mtu = lan966x_fdma_get_max_mtu(lan966x); max_mtu += IFH_LEN * sizeof(u32); + max_mtu += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + max_mtu += VLAN_HLEN * 2; if (round_up(max_mtu, PAGE_SIZE) / PAGE_SIZE - 1 == lan966x->rx.page_order) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index be2fd030cccb..20ee5b28f70a 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -386,7 +386,7 @@ static int lan966x_port_change_mtu(struct net_device *dev, int new_mtu) int old_mtu = dev->mtu; int err; - lan_wr(DEV_MAC_MAXLEN_CFG_MAX_LEN_SET(new_mtu), + lan_wr(DEV_MAC_MAXLEN_CFG_MAX_LEN_SET(LAN966X_HW_MTU(new_mtu)), lan966x, DEV_MAC_MAXLEN_CFG(port->chip_port)); dev->mtu = new_mtu; @@ -395,7 +395,7 @@ static int lan966x_port_change_mtu(struct net_device *dev, int new_mtu) err = lan966x_fdma_change_mtu(lan966x); if (err) { - lan_wr(DEV_MAC_MAXLEN_CFG_MAX_LEN_SET(old_mtu), + lan_wr(DEV_MAC_MAXLEN_CFG_MAX_LEN_SET(LAN966X_HW_MTU(old_mtu)), lan966x, DEV_MAC_MAXLEN_CFG(port->chip_port)); dev->mtu = old_mtu; } diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h index 9656071b8289..4ec33999e4df 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h @@ -26,6 +26,8 @@ #define LAN966X_BUFFER_MEMORY (160 * 1024) #define LAN966X_BUFFER_MIN_SZ 60 +#define LAN966X_HW_MTU(mtu) ((mtu) + ETH_HLEN + ETH_FCS_LEN) + #define PGID_AGGR 64 #define PGID_SRC 80 #define PGID_ENTRIES 89 diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h index 1d90b93dd417..fb5087fef22e 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h @@ -585,6 +585,21 @@ enum lan966x_target { #define DEV_MAC_MAXLEN_CFG_MAX_LEN_GET(x)\ FIELD_GET(DEV_MAC_MAXLEN_CFG_MAX_LEN, x) +/* DEV:MAC_CFG_STATUS:MAC_TAGS_CFG */ +#define DEV_MAC_TAGS_CFG(t) __REG(TARGET_DEV, t, 8, 28, 0, 1, 44, 12, 0, 1, 4) + +#define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA BIT(1) +#define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA_SET(x)\ + FIELD_PREP(DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA, x) +#define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA_GET(x)\ + FIELD_GET(DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA, x) + +#define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0) +#define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(x)\ + FIELD_PREP(DEV_MAC_TAGS_CFG_VLAN_AWR_ENA, x) +#define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA_GET(x)\ + FIELD_GET(DEV_MAC_TAGS_CFG_VLAN_AWR_ENA, x) + /* DEV:MAC_CFG_STATUS:MAC_IFG_CFG */ #define DEV_MAC_IFG_CFG(t) __REG(TARGET_DEV, t, 8, 28, 0, 1, 44, 20, 0, 1, 4) diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c index 8d7260cd7da9..3c44660128da 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c @@ -169,6 +169,12 @@ void lan966x_vlan_port_apply(struct lan966x_port *port) ANA_VLAN_CFG_VLAN_POP_CNT, lan966x, ANA_VLAN_CFG(port->chip_port)); + lan_rmw(DEV_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(port->vlan_aware) | + DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA_SET(port->vlan_aware), + DEV_MAC_TAGS_CFG_VLAN_AWR_ENA | + DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA, + lan966x, DEV_MAC_TAGS_CFG(port->chip_port)); + /* Drop frames with multicast source address */ val = ANA_DROP_CFG_DROP_MC_SMAC_ENA_SET(1); if (port->vlan_aware && !pvid) diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 054d5ce6029e..0556542d7a6b 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1059,8 +1059,10 @@ static int efx_pci_probe(struct pci_dev *pci_dev, /* Allocate and initialise a struct net_device */ net_dev = alloc_etherdev_mq(sizeof(probe_data), EFX_MAX_CORE_TX_QUEUES); - if (!net_dev) - return -ENOMEM; + if (!net_dev) { + rc = -ENOMEM; + goto fail0; + } probe_ptr = netdev_priv(net_dev); *probe_ptr = probe_data; efx->net_dev = net_dev; @@ -1132,6 +1134,8 @@ static int efx_pci_probe(struct pci_dev *pci_dev, WARN_ON(rc > 0); netif_dbg(efx, drv, efx->net_dev, "initialisation failed. rc=%d\n", rc); free_netdev(net_dev); + fail0: + kfree(probe_data); return rc; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 017dbbda0c1c..79fa7870563b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -51,7 +51,6 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id struct stmmac_resources res; struct device_node *np; int ret, i, phy_mode; - bool mdio = false; np = dev_of_node(&pdev->dev); @@ -69,12 +68,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id if (!plat) return -ENOMEM; + plat->mdio_node = of_get_child_by_name(np, "mdio"); if (plat->mdio_node) { - dev_err(&pdev->dev, "Found MDIO subnode\n"); - mdio = true; - } + dev_info(&pdev->dev, "Found MDIO subnode\n"); - if (mdio) { plat->mdio_bus_data = devm_kzalloc(&pdev->dev, sizeof(*plat->mdio_bus_data), GFP_KERNEL); diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 05848ff15fb5..a3967f8de417 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -108,7 +108,7 @@ * @next_tx_buf_to_use: next Tx buffer to write to * @next_rx_buf_to_use: next Rx buffer to read from * @base_addr: base address of the Emaclite device - * @reset_lock: lock used for synchronization + * @reset_lock: lock to serialize xmit and tx_timeout execution * @deferred_skb: holds an skb (for transmission at a later time) when the * Tx buffer is not free * @phy_dev: pointer to the PHY device diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index f82090bdf7ab..1cd604cd1fa1 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -583,7 +583,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner) } for (i = 0; i < PHY_MAX_ADDR; i++) { - if ((bus->phy_mask & (1 << i)) == 0) { + if ((bus->phy_mask & BIT(i)) == 0) { struct phy_device *phydev; phydev = mdiobus_scan(bus, i); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 27c6d235cbda..946628050f28 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1459,7 +1459,8 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile, int err; int i; - if (it->nr_segs > MAX_SKB_FRAGS + 1) + if (it->nr_segs > MAX_SKB_FRAGS + 1 || + len > (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN)) return ERR_PTR(-EMSGSIZE); local_bh_disable(); diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index c6b3334f24c9..f12f903a9dd1 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -249,11 +249,19 @@ static int fdp_nci_close(struct nci_dev *ndev) static int fdp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) { struct fdp_nci_info *info = nci_get_drvdata(ndev); + int ret; if (atomic_dec_and_test(&info->data_pkt_counter)) info->data_pkt_counter_cb(ndev); - return info->phy_ops->write(info->phy, skb); + ret = info->phy_ops->write(info->phy, skb); + if (ret < 0) { + kfree_skb(skb); + return ret; + } + + consume_skb(skb); + return 0; } static int fdp_nci_request_firmware(struct nci_dev *ndev) diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index acef0cfd76af..24436c9e54c9 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -132,10 +132,15 @@ static int nfcmrvl_i2c_nci_send(struct nfcmrvl_private *priv, ret = -EREMOTEIO; } else ret = 0; + } + + if (ret) { kfree_skb(skb); + return ret; } - return ret; + consume_skb(skb); + return 0; } static void nfcmrvl_i2c_nci_update_config(struct nfcmrvl_private *priv, diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c index 7c93d484dc1b..580cb6ecffee 100644 --- a/drivers/nfc/nxp-nci/core.c +++ b/drivers/nfc/nxp-nci/core.c @@ -80,10 +80,13 @@ static int nxp_nci_send(struct nci_dev *ndev, struct sk_buff *skb) return -EINVAL; r = info->phy_ops->write(info->phy_id, skb); - if (r < 0) + if (r < 0) { kfree_skb(skb); + return r; + } - return r; + consume_skb(skb); + return 0; } static int nxp_nci_rf_pll_unlocked_ntf(struct nci_dev *ndev, diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c index 1c412007fabb..0270e05b68df 100644 --- a/drivers/nfc/s3fwrn5/core.c +++ b/drivers/nfc/s3fwrn5/core.c @@ -110,11 +110,15 @@ static int s3fwrn5_nci_send(struct nci_dev *ndev, struct sk_buff *skb) } ret = s3fwrn5_write(info, skb); - if (ret < 0) + if (ret < 0) { kfree_skb(skb); + mutex_unlock(&info->mutex); + return ret; + } + consume_skb(skb); mutex_unlock(&info->mutex); - return ret; + return 0; } static int s3fwrn5_nci_post_setup(struct nci_dev *ndev) diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c index bdef7a8d6ab8..bcc1dae00780 100644 --- a/drivers/parisc/iosapic.c +++ b/drivers/parisc/iosapic.c @@ -866,6 +866,7 @@ int iosapic_serial_irq(struct parisc_device *dev) return vi->txn_irq; } +EXPORT_SYMBOL(iosapic_serial_irq); #endif diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c index d9e51036a4fa..d6af5726ddf3 100644 --- a/drivers/parisc/pdc_stable.c +++ b/drivers/parisc/pdc_stable.c @@ -14,7 +14,7 @@ * all) PA-RISC machines should have them. Anyway, for safety reasons, the * following code can deal with just 96 bytes of Stable Storage, and all * sizes between 96 and 192 bytes (provided they are multiple of struct - * device_path size, eg: 128, 160 and 192) to provide full information. + * pdc_module_path size, eg: 128, 160 and 192) to provide full information. * One last word: there's one path we can always count on: the primary path. * Anything above 224 bytes is used for 'osdep2' OS-dependent storage area. * @@ -88,7 +88,7 @@ struct pdcspath_entry { short ready; /* entry record is valid if != 0 */ unsigned long addr; /* entry address in stable storage */ char *name; /* entry name */ - struct device_path devpath; /* device path in parisc representation */ + struct pdc_module_path devpath; /* device path in parisc representation */ struct device *dev; /* corresponding device */ struct kobject kobj; }; @@ -138,7 +138,7 @@ struct pdcspath_attribute paths_attr_##_name = { \ static int pdcspath_fetch(struct pdcspath_entry *entry) { - struct device_path *devpath; + struct pdc_module_path *devpath; if (!entry) return -EINVAL; @@ -153,7 +153,7 @@ pdcspath_fetch(struct pdcspath_entry *entry) return -EIO; /* Find the matching device. - NOTE: hardware_path overlays with device_path, so the nice cast can + NOTE: hardware_path overlays with pdc_module_path, so the nice cast can be used */ entry->dev = hwpath_to_device((struct hardware_path *)devpath); @@ -179,7 +179,7 @@ pdcspath_fetch(struct pdcspath_entry *entry) static void pdcspath_store(struct pdcspath_entry *entry) { - struct device_path *devpath; + struct pdc_module_path *devpath; BUG_ON(!entry); @@ -221,7 +221,7 @@ static ssize_t pdcspath_hwpath_read(struct pdcspath_entry *entry, char *buf) { char *out = buf; - struct device_path *devpath; + struct pdc_module_path *devpath; short i; if (!entry || !buf) @@ -236,11 +236,11 @@ pdcspath_hwpath_read(struct pdcspath_entry *entry, char *buf) return -ENODATA; for (i = 0; i < 6; i++) { - if (devpath->bc[i] >= 128) + if (devpath->path.bc[i] < 0) continue; - out += sprintf(out, "%u/", (unsigned char)devpath->bc[i]); + out += sprintf(out, "%d/", devpath->path.bc[i]); } - out += sprintf(out, "%u\n", (unsigned char)devpath->mod); + out += sprintf(out, "%u\n", (unsigned char)devpath->path.mod); return out - buf; } @@ -296,12 +296,12 @@ pdcspath_hwpath_write(struct pdcspath_entry *entry, const char *buf, size_t coun for (i=5; ((temp = strrchr(in, '/'))) && (temp-in > 0) && (likely(i)); i--) { hwpath.bc[i] = simple_strtoul(temp+1, NULL, 10); in[temp-in] = '\0'; - DPRINTK("%s: bc[%d]: %d\n", __func__, i, hwpath.bc[i]); + DPRINTK("%s: bc[%d]: %d\n", __func__, i, hwpath.path.bc[i]); } /* Store the final field */ hwpath.bc[i] = simple_strtoul(in, NULL, 10); - DPRINTK("%s: bc[%d]: %d\n", __func__, i, hwpath.bc[i]); + DPRINTK("%s: bc[%d]: %d\n", __func__, i, hwpath.path.bc[i]); /* Now we check that the user isn't trying to lure us */ if (!(dev = hwpath_to_device((struct hardware_path *)&hwpath))) { @@ -342,7 +342,7 @@ static ssize_t pdcspath_layer_read(struct pdcspath_entry *entry, char *buf) { char *out = buf; - struct device_path *devpath; + struct pdc_module_path *devpath; short i; if (!entry || !buf) @@ -547,7 +547,7 @@ static ssize_t pdcs_auto_read(struct kobject *kobj, pathentry = &pdcspath_entry_primary; read_lock(&pathentry->rw_lock); - out += sprintf(out, "%s\n", (pathentry->devpath.flags & knob) ? + out += sprintf(out, "%s\n", (pathentry->devpath.path.flags & knob) ? "On" : "Off"); read_unlock(&pathentry->rw_lock); @@ -594,8 +594,8 @@ static ssize_t pdcs_timer_read(struct kobject *kobj, /* print the timer value in seconds */ read_lock(&pathentry->rw_lock); - out += sprintf(out, "%u\n", (pathentry->devpath.flags & PF_TIMER) ? - (1 << (pathentry->devpath.flags & PF_TIMER)) : 0); + out += sprintf(out, "%u\n", (pathentry->devpath.path.flags & PF_TIMER) ? + (1 << (pathentry->devpath.path.flags & PF_TIMER)) : 0); read_unlock(&pathentry->rw_lock); return out - buf; @@ -764,7 +764,7 @@ static ssize_t pdcs_auto_write(struct kobject *kobj, /* Be nice to the existing flag record */ read_lock(&pathentry->rw_lock); - flags = pathentry->devpath.flags; + flags = pathentry->devpath.path.flags; read_unlock(&pathentry->rw_lock); DPRINTK("%s: flags before: 0x%X\n", __func__, flags); @@ -785,7 +785,7 @@ static ssize_t pdcs_auto_write(struct kobject *kobj, write_lock(&pathentry->rw_lock); /* Change the path entry flags first */ - pathentry->devpath.flags = flags; + pathentry->devpath.path.flags = flags; /* Now, dive in. Write back to the hardware */ pdcspath_store(pathentry); diff --git a/drivers/soc/imx/imx93-pd.c b/drivers/soc/imx/imx93-pd.c index 1f3d7039c1de..4d235c8c4924 100644 --- a/drivers/soc/imx/imx93-pd.c +++ b/drivers/soc/imx/imx93-pd.c @@ -135,11 +135,24 @@ static int imx93_pd_probe(struct platform_device *pdev) ret = pm_genpd_init(&domain->genpd, NULL, domain->init_off); if (ret) - return ret; + goto err_clk_unprepare; platform_set_drvdata(pdev, domain); - return of_genpd_add_provider_simple(np, &domain->genpd); + ret = of_genpd_add_provider_simple(np, &domain->genpd); + if (ret) + goto err_genpd_remove; + + return 0; + +err_genpd_remove: + pm_genpd_remove(&domain->genpd); + +err_clk_unprepare: + if (!domain->init_off) + clk_bulk_disable_unprepare(domain->num_clks, domain->clks); + + return ret; } static const struct of_device_id imx93_pd_ids[] = { diff --git a/drivers/tty/serial/8250/8250_gsc.c b/drivers/tty/serial/8250/8250_parisc.c index 948d0a1c6ae8..948d0a1c6ae8 100644 --- a/drivers/tty/serial/8250/8250_gsc.c +++ b/drivers/tty/serial/8250/8250_parisc.c diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index d0b49e15fbf5..b0f62345bc84 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -116,9 +116,9 @@ config SERIAL_8250_CONSOLE If unsure, say N. -config SERIAL_8250_GSC +config SERIAL_8250_PARISC tristate - depends on SERIAL_8250 && GSC + depends on SERIAL_8250 && PARISC default SERIAL_8250 config SERIAL_8250_DMA diff --git a/drivers/tty/serial/8250/Makefile b/drivers/tty/serial/8250/Makefile index bee908f99ea0..1615bfdde2a0 100644 --- a/drivers/tty/serial/8250/Makefile +++ b/drivers/tty/serial/8250/Makefile @@ -12,7 +12,7 @@ obj-$(CONFIG_SERIAL_8250) += 8250.o 8250_base.o 8250_base-$(CONFIG_SERIAL_8250_DMA) += 8250_dma.o 8250_base-$(CONFIG_SERIAL_8250_DWLIB) += 8250_dwlib.o 8250_base-$(CONFIG_SERIAL_8250_FINTEK) += 8250_fintek.o -obj-$(CONFIG_SERIAL_8250_GSC) += 8250_gsc.o +obj-$(CONFIG_SERIAL_8250_PARISC) += 8250_parisc.o obj-$(CONFIG_SERIAL_8250_PCI) += 8250_pci.o obj-$(CONFIG_SERIAL_8250_EXAR) += 8250_exar.o obj-$(CONFIG_SERIAL_8250_HP300) += 8250_hp300.o diff --git a/drivers/watchdog/exar_wdt.c b/drivers/watchdog/exar_wdt.c index 35058d8b21bc..7c61ff343271 100644 --- a/drivers/watchdog/exar_wdt.c +++ b/drivers/watchdog/exar_wdt.c @@ -355,8 +355,10 @@ static int __init exar_wdt_register(struct wdt_priv *priv, const int idx) &priv->wdt_res, 1, priv, sizeof(*priv)); if (IS_ERR(n->pdev)) { + int err = PTR_ERR(n->pdev); + kfree(n); - return PTR_ERR(n->pdev); + return err; } list_add_tail(&n->list, &pdev_list); diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c index 78ba36689eec..2756ed54ca3d 100644 --- a/drivers/watchdog/sp805_wdt.c +++ b/drivers/watchdog/sp805_wdt.c @@ -88,7 +88,7 @@ static bool wdt_is_running(struct watchdog_device *wdd) return (wdtcontrol & ENABLE_MASK) == ENABLE_MASK; } -/* This routine finds load value that will reset system in required timout */ +/* This routine finds load value that will reset system in required timeout */ static int wdt_setload(struct watchdog_device *wdd, unsigned int timeout) { struct sp805_wdt *wdt = watchdog_get_drvdata(wdd); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 4ec18ceb2f21..18374a6d05bd 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -289,8 +289,10 @@ static void prelim_release(struct preftree *preftree) struct prelim_ref *ref, *next_ref; rbtree_postorder_for_each_entry_safe(ref, next_ref, - &preftree->root.rb_root, rbnode) + &preftree->root.rb_root, rbnode) { + free_inode_elem_list(ref->inode_list); free_pref(ref); + } preftree->root = RB_ROOT_CACHED; preftree->count = 0; @@ -648,6 +650,18 @@ unode_aux_to_inode_list(struct ulist_node *node) return (struct extent_inode_elem *)(uintptr_t)node->aux; } +static void free_leaf_list(struct ulist *ulist) +{ + struct ulist_node *node; + struct ulist_iterator uiter; + + ULIST_ITER_INIT(&uiter); + while ((node = ulist_next(ulist, &uiter))) + free_inode_elem_list(unode_aux_to_inode_list(node)); + + ulist_free(ulist); +} + /* * We maintain three separate rbtrees: one for direct refs, one for * indirect refs which have a key, and one for indirect refs which do not @@ -762,7 +776,11 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info, cond_resched(); } out: - ulist_free(parents); + /* + * We may have inode lists attached to refs in the parents ulist, so we + * must free them before freeing the ulist and its refs. + */ + free_leaf_list(parents); return ret; } @@ -1368,6 +1386,12 @@ again: if (ret < 0) goto out; ref->inode_list = eie; + /* + * We transferred the list ownership to the ref, + * so set to NULL to avoid a double free in case + * an error happens after this. + */ + eie = NULL; } ret = ulist_add_merge_ptr(refs, ref->parent, ref->inode_list, @@ -1393,6 +1417,14 @@ again: eie->next = ref->inode_list; } eie = NULL; + /* + * We have transferred the inode list ownership from + * this ref to the ref we added to the 'refs' ulist. + * So set this ref's inode list to NULL to avoid + * use-after-free when our caller uses it or double + * frees in case an error happens before we return. + */ + ref->inode_list = NULL; } cond_resched(); } @@ -1409,24 +1441,6 @@ out: return ret; } -static void free_leaf_list(struct ulist *blocks) -{ - struct ulist_node *node = NULL; - struct extent_inode_elem *eie; - struct ulist_iterator uiter; - - ULIST_ITER_INIT(&uiter); - while ((node = ulist_next(blocks, &uiter))) { - if (!node->aux) - continue; - eie = unode_aux_to_inode_list(node); - free_inode_elem_list(eie); - node->aux = 0; - } - - ulist_free(blocks); -} - /* * Finds all leafs with a reference to the specified combination of bytenr and * offset. key_list_head will point to a list of corresponding keys (caller must diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 727595eee973..f677b49df8ae 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3462,7 +3462,10 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from, const struct btrfs_ioctl_encoded_io_args *encoded); -ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before); +ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter, + size_t done_before); +struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter, + size_t done_before); extern const struct dentry_operations btrfs_dentry_operations; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a2da9313c694..4b28263c3d32 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -166,11 +166,9 @@ static bool btrfs_supported_super_csum(u16 csum_type) * Return 0 if the superblock checksum type matches the checksum value of that * algorithm. Pass the raw disk superblock data. */ -static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, - char *raw_disk_sb) +int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, + const struct btrfs_super_block *disk_sb) { - struct btrfs_super_block *disk_sb = - (struct btrfs_super_block *)raw_disk_sb; char result[BTRFS_CSUM_SIZE]; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); @@ -181,7 +179,7 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space is * filled with zeros and is included in the checksum. */ - crypto_shash_digest(shash, raw_disk_sb + BTRFS_CSUM_SIZE, + crypto_shash_digest(shash, (const u8 *)disk_sb + BTRFS_CSUM_SIZE, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, result); if (memcmp(disk_sb->csum, result, fs_info->csum_size)) @@ -3479,7 +3477,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device * We want to check superblock checksum, the type is stored inside. * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k). */ - if (btrfs_check_super_csum(fs_info, (u8 *)disk_super)) { + if (btrfs_check_super_csum(fs_info, disk_super)) { btrfs_err(fs_info, "superblock checksum mismatch"); err = -EINVAL; btrfs_release_disk_super(disk_super); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index c67c15d4d20b..9fa923e005a3 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -42,6 +42,8 @@ struct extent_buffer *btrfs_find_create_tree_block( void btrfs_clean_tree_block(struct extent_buffer *buf); void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info); int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info); +int btrfs_check_super_csum(struct btrfs_fs_info *fs_info, + const struct btrfs_super_block *disk_sb); int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices, char *options); diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 1d4c2397d0d6..fab7eb76e53b 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -58,7 +58,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, } struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, - u64 root_objectid, u32 generation, + u64 root_objectid, u64 generation, int check_generation) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); diff --git a/fs/btrfs/export.h b/fs/btrfs/export.h index f32f4113c976..5afb7ca42828 100644 --- a/fs/btrfs/export.h +++ b/fs/btrfs/export.h @@ -19,7 +19,7 @@ struct btrfs_fid { } __attribute__ ((packed)); struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, - u64 root_objectid, u32 generation, + u64 root_objectid, u64 generation, int check_generation); struct dentry *btrfs_get_parent(struct dentry *child); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index cd2d36580f1a..2801c991814f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3295,21 +3295,22 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans, } /* - * If this is a leaf and there are tree mod log users, we may - * have recorded mod log operations that point to this leaf. - * So we must make sure no one reuses this leaf's extent before - * mod log operations are applied to a node, otherwise after - * rewinding a node using the mod log operations we get an - * inconsistent btree, as the leaf's extent may now be used as - * a node or leaf for another different btree. + * If there are tree mod log users we may have recorded mod log + * operations for this node. If we re-allocate this node we + * could replay operations on this node that happened when it + * existed in a completely different root. For example if it + * was part of root A, then was reallocated to root B, and we + * are doing a btrfs_old_search_slot(root b), we could replay + * operations that happened when the block was part of root A, + * giving us an inconsistent view of the btree. + * * We are safe from races here because at this point no other * node or root points to this extent buffer, so if after this - * check a new tree mod log user joins, it will not be able to - * find a node pointing to this leaf and record operations that - * point to this leaf. + * check a new tree mod log user joins we will not have an + * existing log of operations on this node that we have to + * contend with. */ - if (btrfs_header_level(buf) == 0 && - test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags)) + if (test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags)) must_pin = true; if (must_pin || btrfs_is_zoned(fs_info)) { diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 176b432035ae..d01631d47806 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1598,14 +1598,19 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb, write_bytes); else btrfs_check_nocow_unlock(BTRFS_I(inode)); + + if (nowait && ret == -ENOSPC) + ret = -EAGAIN; break; } release_bytes = reserve_bytes; again: ret = balance_dirty_pages_ratelimited_flags(inode->i_mapping, bdp_flags); - if (ret) + if (ret) { + btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes); break; + } /* * This is going to setup the pages array with the number of @@ -1765,6 +1770,7 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from) loff_t endbyte; ssize_t err; unsigned int ilock_flags = 0; + struct iomap_dio *dio; if (iocb->ki_flags & IOCB_NOWAIT) ilock_flags |= BTRFS_ILOCK_TRY; @@ -1825,11 +1831,22 @@ relock: * So here we disable page faults in the iov_iter and then retry if we * got -EFAULT, faulting in the pages before the retry. */ -again: from->nofault = true; - err = btrfs_dio_rw(iocb, from, written); + dio = btrfs_dio_write(iocb, from, written); from->nofault = false; + /* + * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync + * iocb, and that needs to lock the inode. So unlock it before calling + * iomap_dio_complete() to avoid a deadlock. + */ + btrfs_inode_unlock(inode, ilock_flags); + + if (IS_ERR_OR_NULL(dio)) + err = PTR_ERR_OR_ZERO(dio); + else + err = iomap_dio_complete(dio); + /* No increment (+=) because iomap returns a cumulative value. */ if (err > 0) written = err; @@ -1855,12 +1872,10 @@ again: } else { fault_in_iov_iter_readable(from, left); prev_left = left; - goto again; + goto relock; } } - btrfs_inode_unlock(inode, ilock_flags); - /* * If 'err' is -ENOTBLK or we have not written all data, then it means * we must fallback to buffered IO. @@ -4035,7 +4050,7 @@ again: */ pagefault_disable(); to->nofault = true; - ret = btrfs_dio_rw(iocb, to, read); + ret = btrfs_dio_read(iocb, to, read); to->nofault = false; pagefault_enable(); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b0807c59e321..0e516aefbf51 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7980,7 +7980,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter, */ status = BLK_STS_RESOURCE; dip->csums = kcalloc(nr_sectors, fs_info->csum_size, GFP_NOFS); - if (!dip) + if (!dip->csums) goto out_err; status = btrfs_lookup_bio_sums(inode, dio_bio, dip->csums); @@ -8078,13 +8078,21 @@ static const struct iomap_dio_ops btrfs_dio_ops = { .bio_set = &btrfs_dio_bioset, }; -ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before) +ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter, size_t done_before) { struct btrfs_dio_data data; return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops, - IOMAP_DIO_PARTIAL | IOMAP_DIO_NOSYNC, - &data, done_before); + IOMAP_DIO_PARTIAL, &data, done_before); +} + +struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter, + size_t done_before) +{ + struct btrfs_dio_data data; + + return __iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops, + IOMAP_DIO_PARTIAL, &data, done_before); } static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index f6395e8288d6..82c8e991300e 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -1632,10 +1632,8 @@ static int full_stripe_write(struct btrfs_raid_bio *rbio) int ret; ret = alloc_rbio_parity_pages(rbio); - if (ret) { - __free_raid_bio(rbio); + if (ret) return ret; - } ret = lock_stripe_add(rbio); if (ret == 0) @@ -1823,8 +1821,10 @@ void raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc) */ if (rbio_is_full(rbio)) { ret = full_stripe_write(rbio); - if (ret) + if (ret) { + __free_raid_bio(rbio); goto fail; + } return; } @@ -1838,8 +1838,10 @@ void raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc) list_add_tail(&rbio->plug_list, &plug->rbio_list); } else { ret = __raid56_parity_write(rbio); - if (ret) + if (ret) { + __free_raid_bio(rbio); goto fail; + } } return; @@ -2742,8 +2744,10 @@ raid56_alloc_missing_rbio(struct bio *bio, struct btrfs_io_context *bioc) rbio->faila = find_logical_bio_stripe(rbio, bio); if (rbio->faila == -1) { - BUG(); - kfree(rbio); + btrfs_warn_rl(fs_info, + "can not determine the failed stripe number for full stripe %llu", + bioc->raid_map[0]); + __free_raid_bio(rbio); return NULL; } diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index ec6e1752af2c..145c84b44fd0 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6668,17 +6668,19 @@ static int changed_inode(struct send_ctx *sctx, /* * First, process the inode as if it was deleted. */ - sctx->cur_inode_gen = right_gen; - sctx->cur_inode_new = false; - sctx->cur_inode_deleted = true; - sctx->cur_inode_size = btrfs_inode_size( - sctx->right_path->nodes[0], right_ii); - sctx->cur_inode_mode = btrfs_inode_mode( - sctx->right_path->nodes[0], right_ii); - ret = process_all_refs(sctx, - BTRFS_COMPARE_TREE_DELETED); - if (ret < 0) - goto out; + if (old_nlinks > 0) { + sctx->cur_inode_gen = right_gen; + sctx->cur_inode_new = false; + sctx->cur_inode_deleted = true; + sctx->cur_inode_size = btrfs_inode_size( + sctx->right_path->nodes[0], right_ii); + sctx->cur_inode_mode = btrfs_inode_mode( + sctx->right_path->nodes[0], right_ii); + ret = process_all_refs(sctx, + BTRFS_COMPARE_TREE_DELETED); + if (ret < 0) + goto out; + } /* * Now process the inode as if it was new. diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 9be4fd2db0f4..5942b9384088 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2555,6 +2555,7 @@ static int check_dev_super(struct btrfs_device *dev) { struct btrfs_fs_info *fs_info = dev->fs_info; struct btrfs_super_block *sb; + u16 csum_type; int ret = 0; /* This should be called with fs still frozen. */ @@ -2569,6 +2570,21 @@ static int check_dev_super(struct btrfs_device *dev) if (IS_ERR(sb)) return PTR_ERR(sb); + /* Verify the checksum. */ + csum_type = btrfs_super_csum_type(sb); + if (csum_type != btrfs_super_csum_type(fs_info->super_copy)) { + btrfs_err(fs_info, "csum type changed, has %u expect %u", + csum_type, btrfs_super_csum_type(fs_info->super_copy)); + ret = -EUCLEAN; + goto out; + } + + if (btrfs_check_super_csum(fs_info, sb)) { + btrfs_err(fs_info, "csum for on-disk super block no longer matches"); + ret = -EUCLEAN; + goto out; + } + /* Btrfs_validate_super() includes fsid check against super->fsid. */ ret = btrfs_validate_super(fs_info, sb, 0); if (ret < 0) diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index eee1e4459541..63676ea19f29 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -225,20 +225,20 @@ static int test_no_shared_qgroup(struct btrfs_root *root, */ ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -250,29 +250,31 @@ static int test_no_shared_qgroup(struct btrfs_root *root, return ret; } + /* btrfs_qgroup_account_extent() always frees the ulists passed to it. */ + old_roots = NULL; + new_roots = NULL; + if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID, nodesize, nodesize)) { test_err("qgroup counts didn't match expected values"); return -EINVAL; } - old_roots = NULL; - new_roots = NULL; ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = remove_extent_item(root, nodesize, nodesize); - if (ret) + if (ret) { + ulist_free(old_roots); return -EINVAL; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -322,20 +324,20 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = insert_normal_tree_ref(root, nodesize, nodesize, 0, BTRFS_FS_TREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -355,20 +357,20 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = add_tree_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } @@ -394,20 +396,20 @@ static int test_multiple_refs(struct btrfs_root *root, ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false); if (ret) { - ulist_free(old_roots); test_err("couldn't find old roots: %d", ret); return ret; } ret = remove_extent_ref(root, nodesize, nodesize, 0, BTRFS_FIRST_FREE_OBJECTID); - if (ret) + if (ret) { + ulist_free(old_roots); return ret; + } ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false); if (ret) { ulist_free(old_roots); - ulist_free(new_roots); test_err("couldn't find old roots: %d", ret); return ret; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 94ba46d57920..a8d4bc6a1937 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -7142,6 +7142,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf, u64 devid; u64 type; u8 uuid[BTRFS_UUID_SIZE]; + int index; int num_stripes; int ret; int i; @@ -7149,6 +7150,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf, logical = key->offset; length = btrfs_chunk_length(leaf, chunk); type = btrfs_chunk_type(leaf, chunk); + index = btrfs_bg_flags_to_raid_index(type); num_stripes = btrfs_chunk_num_stripes(leaf, chunk); #if BITS_PER_LONG == 32 @@ -7202,7 +7204,15 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf, map->io_align = btrfs_chunk_io_align(leaf, chunk); map->stripe_len = btrfs_chunk_stripe_len(leaf, chunk); map->type = type; - map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk); + /* + * We can't use the sub_stripes value, as for profiles other than + * RAID10, they may have 0 as sub_stripes for filesystems created by + * older mkfs (<v5.4). + * In that case, it can cause divide-by-zero errors later. + * Since currently sub_stripes is fixed for each profile, let's + * use the trusted value instead. + */ + map->sub_stripes = btrfs_raid_array[index].sub_stripes; map->verified_stripes = 0; em->orig_block_len = btrfs_calc_stripe_length(em); for (i = 0; i < num_stripes; i++) { diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 599b9d5af349..f8b668dc8bf8 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -395,6 +395,7 @@ typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio); */ struct btrfs_bio { unsigned int mirror_num; + struct bvec_iter iter; /* for direct I/O */ u64 file_offset; @@ -403,7 +404,6 @@ struct btrfs_bio { struct btrfs_device *device; u8 *csum; u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE]; - struct bvec_iter iter; /* End I/O information supplied to btrfs_bio_alloc */ btrfs_bio_end_io_t end_io; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index d0b9fec111aa..fe220686bba4 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1143,8 +1143,32 @@ const struct inode_operations cifs_file_inode_ops = { .fiemap = cifs_fiemap, }; +const char *cifs_get_link(struct dentry *dentry, struct inode *inode, + struct delayed_call *done) +{ + char *target_path; + + target_path = kmalloc(PATH_MAX, GFP_KERNEL); + if (!target_path) + return ERR_PTR(-ENOMEM); + + spin_lock(&inode->i_lock); + if (likely(CIFS_I(inode)->symlink_target)) { + strscpy(target_path, CIFS_I(inode)->symlink_target, PATH_MAX); + } else { + kfree(target_path); + target_path = ERR_PTR(-EOPNOTSUPP); + } + spin_unlock(&inode->i_lock); + + if (!IS_ERR(target_path)) + set_delayed_call(done, kfree_link, target_path); + + return target_path; +} + const struct inode_operations cifs_symlink_inode_ops = { - .get_link = simple_get_link, + .get_link = cifs_get_link, .permission = cifs_permission, .listxattr = cifs_listxattr, }; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 9bde08d44617..4e2ca3c6e5c0 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -215,11 +215,6 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) kfree(cifs_i->symlink_target); cifs_i->symlink_target = fattr->cf_symlink_target; fattr->cf_symlink_target = NULL; - - if (unlikely(!cifs_i->symlink_target)) - inode->i_link = ERR_PTR(-EOPNOTSUPP); - else - inode->i_link = cifs_i->symlink_target; } spin_unlock(&inode->i_lock); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index da51ffd02928..3e68d8208cf5 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -400,6 +400,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) { struct smb_hdr *buf = (struct smb_hdr *)buffer; struct smb_com_lock_req *pSMB = (struct smb_com_lock_req *)buf; + struct TCP_Server_Info *pserver; struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifsInodeInfo *pCifsInode; @@ -464,9 +465,12 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) if (!(pSMB->LockType & LOCKING_ANDX_OPLOCK_RELEASE)) return false; + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(srv) ? srv->primary_server : srv; + /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &srv->smb_ses_list, smb_ses_list) { + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid != buf->Tid) continue; diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index a38720477966..572293c18e16 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -135,6 +135,7 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len, int smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) { + struct TCP_Server_Info *pserver; struct smb2_hdr *shdr = (struct smb2_hdr *)buf; struct smb2_pdu *pdu = (struct smb2_pdu *)shdr; int hdr_size = sizeof(struct smb2_hdr); @@ -143,6 +144,9 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) __u32 calc_len; /* calculated length */ __u64 mid; + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + /* * Add function to do table lookup of StructureSize by command * ie Validate the wct via smb2_struct_sizes table above @@ -155,7 +159,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server) /* decrypt frame now that it is completely read in */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(iter, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(iter, &pserver->smb_ses_list, smb_ses_list) { if (iter->Suid == le64_to_cpu(thdr->SessionId)) { ses = iter; break; @@ -608,51 +612,52 @@ smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon, } static bool -smb2_is_valid_lease_break(char *buffer) +smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) { struct smb2_lease_break *rsp = (struct smb2_lease_break *)buffer; - struct TCP_Server_Info *server; + struct TCP_Server_Info *pserver; struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifs_pending_open *open; cifs_dbg(FYI, "Checking for lease break\n"); + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { - list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { - spin_lock(&tcon->open_file_lock); - cifs_stats_inc( - &tcon->stats.cifs_stats.num_oplock_brks); - if (smb2_tcon_has_lease(tcon, rsp)) { - spin_unlock(&tcon->open_file_lock); - spin_unlock(&cifs_tcp_ses_lock); - return true; - } - open = smb2_tcon_find_pending_open_lease(tcon, - rsp); - if (open) { - __u8 lease_key[SMB2_LEASE_KEY_SIZE]; - struct tcon_link *tlink; - - tlink = cifs_get_tlink(open->tlink); - memcpy(lease_key, open->lease_key, - SMB2_LEASE_KEY_SIZE); - spin_unlock(&tcon->open_file_lock); - spin_unlock(&cifs_tcp_ses_lock); - smb2_queue_pending_open_break(tlink, - lease_key, - rsp->NewLeaseState); - return true; - } + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { + spin_lock(&tcon->open_file_lock); + cifs_stats_inc( + &tcon->stats.cifs_stats.num_oplock_brks); + if (smb2_tcon_has_lease(tcon, rsp)) { spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_tcp_ses_lock); + return true; + } + open = smb2_tcon_find_pending_open_lease(tcon, + rsp); + if (open) { + __u8 lease_key[SMB2_LEASE_KEY_SIZE]; + struct tcon_link *tlink; + + tlink = cifs_get_tlink(open->tlink); + memcpy(lease_key, open->lease_key, + SMB2_LEASE_KEY_SIZE); + spin_unlock(&tcon->open_file_lock); + spin_unlock(&cifs_tcp_ses_lock); + smb2_queue_pending_open_break(tlink, + lease_key, + rsp->NewLeaseState); + return true; + } + spin_unlock(&tcon->open_file_lock); - if (cached_dir_lease_break(tcon, rsp->LeaseKey)) { - spin_unlock(&cifs_tcp_ses_lock); - return true; - } + if (cached_dir_lease_break(tcon, rsp->LeaseKey)) { + spin_unlock(&cifs_tcp_ses_lock); + return true; } } } @@ -671,6 +676,7 @@ bool smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) { struct smb2_oplock_break *rsp = (struct smb2_oplock_break *)buffer; + struct TCP_Server_Info *pserver; struct cifs_ses *ses; struct cifs_tcon *tcon; struct cifsInodeInfo *cinode; @@ -684,16 +690,19 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) if (rsp->StructureSize != smb2_rsp_struct_sizes[SMB2_OPLOCK_BREAK_HE]) { if (le16_to_cpu(rsp->StructureSize) == 44) - return smb2_is_valid_lease_break(buffer); + return smb2_is_valid_lease_break(buffer, server); else return false; } cifs_dbg(FYI, "oplock level 0x%x\n", rsp->OplockLevel); + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + /* look up tcon based on tid & uid */ spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { spin_lock(&tcon->open_file_lock); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 4f53fa012936..880cd494afea 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2302,14 +2302,18 @@ static void smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) { struct smb2_hdr *shdr = (struct smb2_hdr *)buf; + struct TCP_Server_Info *pserver; struct cifs_ses *ses; struct cifs_tcon *tcon; if (shdr->Status != STATUS_NETWORK_NAME_DELETED) return; + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { list_for_each_entry(tcon, &ses->tcon_list, tcon_list) { if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) { spin_lock(&tcon->tc_lock); @@ -4264,21 +4268,23 @@ init_sg(int num_rqst, struct smb_rqst *rqst, u8 *sign) static int smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key) { + struct TCP_Server_Info *pserver; struct cifs_ses *ses; u8 *ses_enc_key; + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) { - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { - if (ses->Suid == ses_id) { - spin_lock(&ses->ses_lock); - ses_enc_key = enc ? ses->smb3encryptionkey : - ses->smb3decryptionkey; - memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); - spin_unlock(&ses->ses_lock); - spin_unlock(&cifs_tcp_ses_lock); - return 0; - } + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (ses->Suid == ses_id) { + spin_lock(&ses->ses_lock); + ses_enc_key = enc ? ses->smb3encryptionkey : + ses->smb3decryptionkey; + memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE); + spin_unlock(&ses->ses_lock); + spin_unlock(&cifs_tcp_ses_lock); + return 0; } } spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 8e3f26e6f6b9..381babc1212c 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -77,18 +77,19 @@ static int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key) { struct cifs_chan *chan; + struct TCP_Server_Info *pserver; struct cifs_ses *ses = NULL; - struct TCP_Server_Info *it = NULL; int i; int rc = 0; spin_lock(&cifs_tcp_ses_lock); - list_for_each_entry(it, &cifs_tcp_ses_list, tcp_ses_list) { - list_for_each_entry(ses, &it->smb_ses_list, smb_ses_list) { - if (ses->Suid == ses_id) - goto found; - } + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { + if (ses->Suid == ses_id) + goto found; } cifs_server_dbg(VFS, "%s: Could not find session 0x%llx\n", __func__, ses_id); @@ -136,9 +137,13 @@ out: static struct cifs_ses * smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id) { + struct TCP_Server_Info *pserver; struct cifs_ses *ses; - list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { + /* If server is a channel, select the primary channel */ + pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; + + list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) { if (ses->Suid != ses_id) continue; ++ses->ses_count; diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index ef05bfa87798..0f6d0a80467d 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1521,6 +1521,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, struct ext4_iloc iloc; int inode_len, ino, ret, tag = tl->fc_tag; struct ext4_extent_header *eh; + size_t off_gen = offsetof(struct ext4_inode, i_generation); memcpy(&fc_inode, val, sizeof(fc_inode)); @@ -1548,8 +1549,8 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl, raw_inode = ext4_raw_inode(&iloc); memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block)); - memcpy(&raw_inode->i_generation, &raw_fc_inode->i_generation, - inode_len - offsetof(struct ext4_inode, i_generation)); + memcpy((u8 *)raw_inode + off_gen, (u8 *)raw_fc_inode + off_gen, + inode_len - off_gen); if (le32_to_cpu(raw_inode->i_flags) & EXT4_EXTENTS_FL) { eh = (struct ext4_extent_header *)(&raw_inode->i_block[0]); if (eh->eh_magic != EXT4_EXT_MAGIC) { diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index ded535535b27..95dfea28bf4e 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -145,9 +145,8 @@ static int ext4_update_backup_sb(struct super_block *sb, if (ext4_has_metadata_csum(sb) && es->s_checksum != ext4_superblock_csum(sb, es)) { ext4_msg(sb, KERN_ERR, "Invalid checksum for backup " - "superblock %llu\n", sb_block); + "superblock %llu", sb_block); unlock_buffer(bh); - err = -EFSBADCRC; goto out_bh; } func(es, arg); diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c index 0a220ec9862d..a19a9661646e 100644 --- a/fs/ext4/migrate.c +++ b/fs/ext4/migrate.c @@ -424,7 +424,8 @@ int ext4_ext_migrate(struct inode *inode) * already is extent-based, error out. */ if (!ext4_has_feature_extents(inode->i_sb) || - (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) + ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) || + ext4_has_inline_data(inode)) return -EINVAL; if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index d5daaf41e1fc..c08c0aba1883 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2259,8 +2259,16 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, memset(de, 0, len); /* wipe old data */ de = (struct ext4_dir_entry_2 *) data2; top = data2 + len; - while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) + while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) { + if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len, + (data2 + (blocksize - csum_size) - + (char *) de))) { + brelse(bh2); + brelse(bh); + return -EFSCORRUPTED; + } de = de2; + } de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) - (char *) de, blocksize); diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 6dfe9ccae0c5..46b87ffeb304 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -1158,6 +1158,7 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, while (group < sbi->s_groups_count) { struct buffer_head *bh; ext4_fsblk_t backup_block; + struct ext4_super_block *es; /* Out of journal space, and can't get more - abort - so sad */ err = ext4_resize_ensure_credits_batch(handle, 1); @@ -1186,6 +1187,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data, memcpy(bh->b_data, data, size); if (rest) memset(bh->b_data + size, 0, rest); + es = (struct ext4_super_block *) bh->b_data; + es->s_block_group_nr = cpu_to_le16(group); + if (ext4_has_metadata_csum(sb)) + es->s_checksum = ext4_superblock_csum(sb, es); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, NULL, bh); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 7950904fbf04..7cdd2138c897 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4881,7 +4881,7 @@ out: flush_work(&sbi->s_error_work); jbd2_journal_destroy(sbi->s_journal); sbi->s_journal = NULL; - return err; + return -EINVAL; } static int ext4_journal_data_mode_check(struct super_block *sb) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 1a3afd469e3a..71bfb663aac5 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3001,6 +3001,10 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset, goto out; } + err = file_modified(file); + if (err) + goto out; + if (!(mode & FALLOC_FL_KEEP_SIZE)) set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state); diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c index b4e565711045..e8deaacf1832 100644 --- a/fs/fuse/readdir.c +++ b/fs/fuse/readdir.c @@ -77,8 +77,10 @@ static void fuse_add_dirent_to_cache(struct file *file, goto unlock; addr = kmap_local_page(page); - if (!offset) + if (!offset) { clear_page(addr); + SetPageUptodate(page); + } memcpy(addr + offset, dirent, reclen); kunmap_local(addr); fi->rdc.size = (index << PAGE_SHIFT) + offset + reclen; @@ -516,6 +518,12 @@ retry_locked: page = find_get_page_flags(file->f_mapping, index, FGP_ACCESSED | FGP_LOCK); + /* Page gone missing, then re-added to cache, but not initialized? */ + if (page && !PageUptodate(page)) { + unlock_page(page); + put_page(page); + page = NULL; + } spin_lock(&fi->rdc.lock); if (!page) { /* diff --git a/fs/nfs/client.c b/fs/nfs/client.c index da8da5cdbbc1..f50e025ae406 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -280,7 +280,7 @@ EXPORT_SYMBOL_GPL(nfs_put_client); static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *data) { struct nfs_client *clp; - const struct sockaddr *sap = data->addr; + const struct sockaddr *sap = (struct sockaddr *)data->addr; struct nfs_net *nn = net_generic(data->net, nfs_net_id); int error; @@ -666,7 +666,7 @@ static int nfs_init_server(struct nfs_server *server, struct rpc_timeout timeparms; struct nfs_client_initdata cl_init = { .hostname = ctx->nfs_server.hostname, - .addr = (const struct sockaddr *)&ctx->nfs_server.address, + .addr = &ctx->nfs_server._address, .addrlen = ctx->nfs_server.addrlen, .nfs_mod = ctx->nfs_mod, .proto = ctx->nfs_server.protocol, diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 5c97cad741a7..ead8a0e06abf 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -228,8 +228,7 @@ again: * */ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, - fmode_t type, - const nfs4_stateid *stateid, + fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit) { struct nfs_delegation *delegation; @@ -239,25 +238,24 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation != NULL) { spin_lock(&delegation->lock); - if (nfs4_is_valid_delegation(delegation, 0)) { - nfs4_stateid_copy(&delegation->stateid, stateid); - delegation->type = type; - delegation->pagemod_limit = pagemod_limit; - oldcred = delegation->cred; - delegation->cred = get_cred(cred); - clear_bit(NFS_DELEGATION_NEED_RECLAIM, - &delegation->flags); - spin_unlock(&delegation->lock); - rcu_read_unlock(); - put_cred(oldcred); - trace_nfs4_reclaim_delegation(inode, type); - return; - } - /* We appear to have raced with a delegation return. */ + nfs4_stateid_copy(&delegation->stateid, stateid); + delegation->type = type; + delegation->pagemod_limit = pagemod_limit; + oldcred = delegation->cred; + delegation->cred = get_cred(cred); + clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags); + if (test_and_clear_bit(NFS_DELEGATION_REVOKED, + &delegation->flags)) + atomic_long_inc(&nfs_active_delegations); spin_unlock(&delegation->lock); + rcu_read_unlock(); + put_cred(oldcred); + trace_nfs4_reclaim_delegation(inode, type); + } else { + rcu_read_unlock(); + nfs_inode_set_delegation(inode, cred, type, stateid, + pagemod_limit); } - rcu_read_unlock(); - nfs_inode_set_delegation(inode, cred, type, stateid, pagemod_limit); } static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 58036f657126..f594dac436a7 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -2489,9 +2489,8 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry) spin_unlock(&dentry->d_lock); goto out; } - if (dentry->d_fsdata) - /* old devname */ - kfree(dentry->d_fsdata); + /* old devname */ + kfree(dentry->d_fsdata); dentry->d_fsdata = NFS_FSDATA_BLOCKED; spin_unlock(&dentry->d_lock); diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index e87d500ad95a..6603b5cee029 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -16,8 +16,9 @@ #include "dns_resolve.h" ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, - struct sockaddr *sa, size_t salen) + struct sockaddr_storage *ss, size_t salen) { + struct sockaddr *sa = (struct sockaddr *)ss; ssize_t ret; char *ip_addr = NULL; int ip_len; @@ -341,7 +342,7 @@ out: } ssize_t nfs_dns_resolve_name(struct net *net, char *name, - size_t namelen, struct sockaddr *sa, size_t salen) + size_t namelen, struct sockaddr_storage *ss, size_t salen) { struct nfs_dns_ent key = { .hostname = name, @@ -354,7 +355,7 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, ret = do_cache_lookup_wait(nn->nfs_dns_resolve, &key, &item); if (ret == 0) { if (salen >= item->addrlen) { - memcpy(sa, &item->addr, item->addrlen); + memcpy(ss, &item->addr, item->addrlen); ret = item->addrlen; } else ret = -EOVERFLOW; diff --git a/fs/nfs/dns_resolve.h b/fs/nfs/dns_resolve.h index 576ff4b54c82..fe3b172c4de1 100644 --- a/fs/nfs/dns_resolve.h +++ b/fs/nfs/dns_resolve.h @@ -32,6 +32,6 @@ extern void nfs_dns_resolver_cache_destroy(struct net *net); #endif extern ssize_t nfs_dns_resolve_name(struct net *net, char *name, - size_t namelen, struct sockaddr *sa, size_t salen); + size_t namelen, struct sockaddr_storage *sa, size_t salen); #endif diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c index 4da701fd1424..09833ec102fc 100644 --- a/fs/nfs/fs_context.c +++ b/fs/nfs/fs_context.c @@ -273,9 +273,9 @@ static const struct constant_table nfs_secflavor_tokens[] = { * Address family must be initialized, and address must not be * the ANY address for that family. */ -static int nfs_verify_server_address(struct sockaddr *addr) +static int nfs_verify_server_address(struct sockaddr_storage *addr) { - switch (addr->sa_family) { + switch (addr->ss_family) { case AF_INET: { struct sockaddr_in *sa = (struct sockaddr_in *)addr; return sa->sin_addr.s_addr != htonl(INADDR_ANY); @@ -969,7 +969,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc, { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_fh *mntfh = ctx->mntfh; - struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address; + struct sockaddr_storage *sap = &ctx->nfs_server._address; int extra_flags = NFS_MOUNT_LEGACY_INTERFACE; int ret; @@ -1044,7 +1044,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc, memcpy(sap, &data->addr, sizeof(data->addr)); ctx->nfs_server.addrlen = sizeof(data->addr); ctx->nfs_server.port = ntohs(data->addr.sin_port); - if (sap->sa_family != AF_INET || + if (sap->ss_family != AF_INET || !nfs_verify_server_address(sap)) goto out_no_address; @@ -1200,7 +1200,7 @@ static int nfs4_parse_monolithic(struct fs_context *fc, struct nfs4_mount_data *data) { struct nfs_fs_context *ctx = nfs_fc2context(fc); - struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address; + struct sockaddr_storage *sap = &ctx->nfs_server._address; int ret; char *c; @@ -1314,7 +1314,7 @@ static int nfs_fs_context_validate(struct fs_context *fc) { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_subversion *nfs_mod; - struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address; + struct sockaddr_storage *sap = &ctx->nfs_server._address; int max_namelen = PAGE_SIZE; int max_pathlen = NFS_MAXPATHLEN; int port = 0; @@ -1540,7 +1540,7 @@ static int nfs_init_fs_context(struct fs_context *fc) ctx->version = nfss->nfs_client->rpc_ops->version; ctx->minorversion = nfss->nfs_client->cl_minorversion; - memcpy(&ctx->nfs_server.address, &nfss->nfs_client->cl_addr, + memcpy(&ctx->nfs_server._address, &nfss->nfs_client->cl_addr, ctx->nfs_server.addrlen); if (fc->net_ns != net) { diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index d914d609b85b..647fc3f547cb 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -69,7 +69,7 @@ static inline fmode_t flags_to_mode(int flags) struct nfs_client_initdata { unsigned long init_flags; const char *hostname; /* Hostname of the server */ - const struct sockaddr *addr; /* Address of the server */ + const struct sockaddr_storage *addr; /* Address of the server */ const char *nodename; /* Hostname of the client */ const char *ip_addr; /* IP address of the client */ size_t addrlen; @@ -180,7 +180,7 @@ static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc) /* mount_clnt.c */ struct nfs_mount_request { - struct sockaddr *sap; + struct sockaddr_storage *sap; size_t salen; char *hostname; char *dirpath; @@ -223,7 +223,7 @@ extern void nfs4_server_set_init_caps(struct nfs_server *); extern struct nfs_server *nfs4_create_server(struct fs_context *); extern struct nfs_server *nfs4_create_referral_server(struct fs_context *); extern int nfs4_update_server(struct nfs_server *server, const char *hostname, - struct sockaddr *sap, size_t salen, + struct sockaddr_storage *sap, size_t salen, struct net *net); extern void nfs_free_server(struct nfs_server *server); extern struct nfs_server *nfs_clone_server(struct nfs_server *, @@ -235,7 +235,7 @@ extern int nfs_client_init_status(const struct nfs_client *clp); extern int nfs_wait_client_init_complete(const struct nfs_client *clp); extern void nfs_mark_client_ready(struct nfs_client *clp, int state); extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, @@ -243,7 +243,7 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *, struct inode *); extern struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, int ds_addrlen, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans); #ifdef CONFIG_PROC_FS @@ -894,13 +894,13 @@ static inline bool nfs_error_is_fatal_on_server(int err) * Select between a default port value and a user-specified port value. * If a zero value is set, then autobind will be used. */ -static inline void nfs_set_port(struct sockaddr *sap, int *port, +static inline void nfs_set_port(struct sockaddr_storage *sap, int *port, const unsigned short default_port) { if (*port == NFS_UNSPEC_PORT) *port = default_port; - rpc_set_port(sap, *port); + rpc_set_port((struct sockaddr *)sap, *port); } struct nfs_direct_req { diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index c5e3b6b3366a..68e76b626371 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -158,7 +158,7 @@ int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans) struct rpc_create_args args = { .net = info->net, .protocol = info->protocol, - .address = info->sap, + .address = (struct sockaddr *)info->sap, .addrsize = info->salen, .timeout = &mnt_timeout, .servername = info->hostname, @@ -245,7 +245,7 @@ void nfs_umount(const struct nfs_mount_request *info) struct rpc_create_args args = { .net = info->net, .protocol = IPPROTO_UDP, - .address = info->sap, + .address = (struct sockaddr *)info->sap, .addrsize = info->salen, .timeout = &nfs_umnt_timeout, .servername = info->hostname, diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 3295af4110f1..2f336ace7555 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -175,7 +175,7 @@ struct vfsmount *nfs_d_automount(struct path *path) } /* for submounts we want the same server; referrals will reassign */ - memcpy(&ctx->nfs_server.address, &client->cl_addr, client->cl_addrlen); + memcpy(&ctx->nfs_server._address, &client->cl_addr, client->cl_addrlen); ctx->nfs_server.addrlen = client->cl_addrlen; ctx->nfs_server.port = server->port; diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c index b49359afac88..669cda757a5c 100644 --- a/fs/nfs/nfs3client.c +++ b/fs/nfs/nfs3client.c @@ -78,7 +78,7 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source, * the MDS. */ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, int ds_addrlen, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans) { struct rpc_timeout ds_timeout; @@ -98,7 +98,7 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv, char buf[INET6_ADDRSTRLEN + 1]; /* fake a hostname because lockd wants it */ - if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0) + if (rpc_ntop((struct sockaddr *)ds_addr, buf, sizeof(buf)) <= 0) return ERR_PTR(-EINVAL); cl_init.hostname = buf; diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 13424f0d793b..ecb428512fe1 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -1093,6 +1093,9 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, &args.seq_args, &res.seq_res, 0); trace_nfs4_clone(src_inode, dst_inode, &args, status); if (status == 0) { + /* a zero-length count means clone to EOF in src */ + if (count == 0 && res.dst_fattr->valid & NFS_ATTR_FATTR_SIZE) + count = nfs_size_to_loff_t(res.dst_fattr->size) - dst_offset; nfs42_copy_dest_done(dst_inode, dst_offset, count); status = nfs_post_op_update_inode(dst_inode, res.dst_fattr); } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 400a71e75238..cfef738d765e 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -281,7 +281,7 @@ struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *, int nfs4_submount(struct fs_context *, struct nfs_server *); int nfs4_replace_transport(struct nfs_server *server, const struct nfs4_fs_locations *locations); -size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa, +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr_storage *ss, size_t salen, struct net *net, int port); /* nfs4proc.c */ extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index 7a5162afa5c0..d3051b051a56 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -346,6 +346,7 @@ int nfs40_init_client(struct nfs_client *clp) ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE, "NFSv4.0 transport Slot table"); if (ret) { + nfs4_shutdown_slot_table(tbl); kfree(tbl); return ret; } @@ -889,7 +890,7 @@ nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr, */ static int nfs4_set_client(struct nfs_server *server, const char *hostname, - const struct sockaddr *addr, + const struct sockaddr_storage *addr, const size_t addrlen, const char *ip_addr, int proto, const struct rpc_timeout *timeparms, @@ -924,7 +925,7 @@ static int nfs4_set_client(struct nfs_server *server, __set_bit(NFS_CS_MIGRATION, &cl_init.init_flags); if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status)) __set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags); - server->port = rpc_get_port(addr); + server->port = rpc_get_port((struct sockaddr *)addr); /* Allocate or find a client reference we can use */ clp = nfs_get_client(&cl_init); @@ -960,7 +961,7 @@ static int nfs4_set_client(struct nfs_server *server, * the MDS. */ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, int ds_addrlen, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans, u32 minor_version) { @@ -980,7 +981,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv, }; char buf[INET6_ADDRSTRLEN + 1]; - if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0) + if (rpc_ntop((struct sockaddr *)ds_addr, buf, sizeof(buf)) <= 0) return ERR_PTR(-EINVAL); cl_init.hostname = buf; @@ -1148,7 +1149,7 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc) /* Get a client record */ error = nfs4_set_client(server, ctx->nfs_server.hostname, - &ctx->nfs_server.address, + &ctx->nfs_server._address, ctx->nfs_server.addrlen, ctx->client_address, ctx->nfs_server.protocol, @@ -1238,7 +1239,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc) rpc_set_port(&ctx->nfs_server.address, NFS_RDMA_PORT); error = nfs4_set_client(server, ctx->nfs_server.hostname, - &ctx->nfs_server.address, + &ctx->nfs_server._address, ctx->nfs_server.addrlen, parent_client->cl_ipaddr, XPRT_TRANSPORT_RDMA, @@ -1254,7 +1255,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc) rpc_set_port(&ctx->nfs_server.address, NFS_PORT); error = nfs4_set_client(server, ctx->nfs_server.hostname, - &ctx->nfs_server.address, + &ctx->nfs_server._address, ctx->nfs_server.addrlen, parent_client->cl_ipaddr, XPRT_TRANSPORT_TCP, @@ -1303,14 +1304,14 @@ error: * Returns zero on success, or a negative errno value. */ int nfs4_update_server(struct nfs_server *server, const char *hostname, - struct sockaddr *sap, size_t salen, struct net *net) + struct sockaddr_storage *sap, size_t salen, struct net *net) { struct nfs_client *clp = server->nfs_client; struct rpc_clnt *clnt = server->client; struct xprt_create xargs = { .ident = clp->cl_proto, .net = net, - .dstaddr = sap, + .dstaddr = (struct sockaddr *)sap, .addrlen = salen, .servername = hostname, }; diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c index f2dbf904c598..9a98595bb160 100644 --- a/fs/nfs/nfs4namespace.c +++ b/fs/nfs/nfs4namespace.c @@ -164,16 +164,17 @@ static int nfs4_validate_fspath(struct dentry *dentry, return 0; } -size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa, +size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr_storage *ss, size_t salen, struct net *net, int port) { + struct sockaddr *sa = (struct sockaddr *)ss; ssize_t ret; ret = rpc_pton(net, string, len, sa, salen); if (ret == 0) { ret = rpc_uaddr2sockaddr(net, string, len, sa, salen); if (ret == 0) { - ret = nfs_dns_resolve_name(net, string, len, sa, salen); + ret = nfs_dns_resolve_name(net, string, len, ss, salen); if (ret < 0) ret = 0; } @@ -331,7 +332,7 @@ static int try_location(struct fs_context *fc, ctx->nfs_server.addrlen = nfs_parse_server_name(buf->data, buf->len, - &ctx->nfs_server.address, + &ctx->nfs_server._address, sizeof(ctx->nfs_server._address), fc->net_ns, 0); if (ctx->nfs_server.addrlen == 0) @@ -483,14 +484,13 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, char *page, char *page2, const struct nfs4_fs_location *location) { - const size_t addr_bufsize = sizeof(struct sockaddr_storage); struct net *net = rpc_net_ns(server->client); - struct sockaddr *sap; + struct sockaddr_storage *sap; unsigned int s; size_t salen; int error; - sap = kmalloc(addr_bufsize, GFP_KERNEL); + sap = kmalloc(sizeof(*sap), GFP_KERNEL); if (sap == NULL) return -ENOMEM; @@ -506,10 +506,10 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server, continue; salen = nfs_parse_server_name(buf->data, buf->len, - sap, addr_bufsize, net, 0); + sap, sizeof(*sap), net, 0); if (salen == 0) continue; - rpc_set_port(sap, NFS_PORT); + rpc_set_port((struct sockaddr *)sap, NFS_PORT); error = -ENOMEM; hostname = kmemdup_nul(buf->data, buf->len, GFP_KERNEL); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index e2efcd26336c..86ed5c0142c3 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3951,7 +3951,7 @@ static void test_fs_location_for_trunking(struct nfs4_fs_location *location, for (i = 0; i < location->nservers; i++) { struct nfs4_string *srv_loc = &location->servers[i]; - struct sockaddr addr; + struct sockaddr_storage addr; size_t addrlen; struct xprt_create xprt_args = { .ident = 0, @@ -3974,7 +3974,7 @@ static void test_fs_location_for_trunking(struct nfs4_fs_location *location, clp->cl_net, server->port); if (!addrlen) return; - xprt_args.dstaddr = &addr; + xprt_args.dstaddr = (struct sockaddr *)&addr; xprt_args.addrlen = addrlen; servername = kmalloc(srv_loc->len + 1, GFP_KERNEL); if (!servername) @@ -7138,6 +7138,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) { struct nfs4_lockdata *data = calldata; struct nfs4_lock_state *lsp = data->lsp; + struct nfs_server *server = NFS_SERVER(d_inode(data->ctx->dentry)); if (!nfs4_sequence_done(task, &data->res.seq_res)) return; @@ -7145,8 +7146,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) data->rpc_status = task->tk_status; switch (task->tk_status) { case 0: - renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)), - data->timestamp); + renew_lease(server, data->timestamp); if (data->arg.new_lock && !data->cancelled) { data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS); if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0) @@ -7167,6 +7167,8 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata) if (!nfs4_stateid_match(&data->arg.open_stateid, &lsp->ls_state->open_stateid)) goto out_restart; + else if (nfs4_async_handle_error(task, server, lsp->ls_state, NULL) == -EAGAIN) + goto out_restart; } else if (!nfs4_stateid_match(&data->arg.lock_stateid, &lsp->ls_stateid)) goto out_restart; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index c3503fb26fa2..a2d2d5d1b088 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1786,6 +1786,7 @@ static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp, static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp) { + set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); /* Mark all delegations for reclaim */ nfs_delegation_mark_reclaim(clp); nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot); @@ -2670,6 +2671,7 @@ static void nfs4_state_manager(struct nfs_client *clp) if (status < 0) goto out_error; nfs4_state_end_reclaim_reboot(clp); + continue; } /* Detect expired delegations... */ diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 987c88ddeaf0..5d035dd2d7bf 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -821,7 +821,7 @@ static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds) static struct nfs_client *(*get_v3_ds_connect)( struct nfs_server *mds_srv, - const struct sockaddr *ds_addr, + const struct sockaddr_storage *ds_addr, int ds_addrlen, int ds_proto, unsigned int ds_timeo, @@ -882,7 +882,7 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv, continue; } clp = get_v3_ds_connect(mds_srv, - (struct sockaddr *)&da->da_addr, + &da->da_addr, da->da_addrlen, da->da_transport, timeo, retrans); if (IS_ERR(clp)) @@ -951,7 +951,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv, put_cred(xprtdata.cred); } else { clp = nfs4_set_ds_client(mds_srv, - (struct sockaddr *)&da->da_addr, + &da->da_addr, da->da_addrlen, da->da_transport, timeo, retrans, minor_version); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ee66ffdb985e..05ae23657527 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -822,8 +822,7 @@ static int nfs_request_mount(struct fs_context *fc, { struct nfs_fs_context *ctx = nfs_fc2context(fc); struct nfs_mount_request request = { - .sap = (struct sockaddr *) - &ctx->mount_server.address, + .sap = &ctx->mount_server._address, .dirpath = ctx->nfs_server.export_path, .protocol = ctx->mount_server.protocol, .fh = root_fh, @@ -854,7 +853,7 @@ static int nfs_request_mount(struct fs_context *fc, * Construct the mount server's address. */ if (ctx->mount_server.address.sa_family == AF_UNSPEC) { - memcpy(request.sap, &ctx->nfs_server.address, + memcpy(request.sap, &ctx->nfs_server._address, ctx->nfs_server.addrlen); ctx->mount_server.addrlen = ctx->nfs_server.addrlen; } diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 29a62db155fb..adc4e87a71d2 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -893,9 +893,8 @@ __nfsd_file_cache_purge(struct net *net) nf = rhashtable_walk_next(&iter); while (!IS_ERR_OR_NULL(nf)) { - if (net && nf->nf_net != net) - continue; - nfsd_file_unhash_and_dispose(nf, &dispose); + if (!net || nf->nf_net == net) + nfsd_file_unhash_and_dispose(nf, &dispose); nf = rhashtable_walk_next(&iter); } diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h index 517a138faa66..191b22b9a35b 100644 --- a/fs/xfs/libxfs/xfs_ag.h +++ b/fs/xfs/libxfs/xfs_ag.h @@ -133,6 +133,21 @@ xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno) return true; } +static inline bool +xfs_verify_agbext( + struct xfs_perag *pag, + xfs_agblock_t agbno, + xfs_agblock_t len) +{ + if (agbno + len <= agbno) + return false; + + if (!xfs_verify_agbno(pag, agbno)) + return false; + + return xfs_verify_agbno(pag, agbno + len - 1); +} + /* * Verify that an AG inode number pointer neither points outside the AG * nor points at static metadata. diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 6261599bb389..de79f5d07f65 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -263,11 +263,7 @@ xfs_alloc_get_rec( goto out_bad_rec; /* check for valid extent range, including overflow */ - if (!xfs_verify_agbno(pag, *bno)) - goto out_bad_rec; - if (*bno > *bno + *len) - goto out_bad_rec; - if (!xfs_verify_agbno(pag, *bno + *len - 1)) + if (!xfs_verify_agbext(pag, *bno, *len)) goto out_bad_rec; return 0; diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c index d9b66306a9a7..cb9e950a911d 100644 --- a/fs/xfs/libxfs/xfs_dir2_leaf.c +++ b/fs/xfs/libxfs/xfs_dir2_leaf.c @@ -146,6 +146,8 @@ xfs_dir3_leaf_check_int( xfs_dir2_leaf_tail_t *ltp; int stale; int i; + bool isleaf1 = (hdr->magic == XFS_DIR2_LEAF1_MAGIC || + hdr->magic == XFS_DIR3_LEAF1_MAGIC); ltp = xfs_dir2_leaf_tail_p(geo, leaf); @@ -158,8 +160,7 @@ xfs_dir3_leaf_check_int( return __this_address; /* Leaves and bests don't overlap in leaf format. */ - if ((hdr->magic == XFS_DIR2_LEAF1_MAGIC || - hdr->magic == XFS_DIR3_LEAF1_MAGIC) && + if (isleaf1 && (char *)&hdr->ents[hdr->count] > (char *)xfs_dir2_leaf_bests_p(ltp)) return __this_address; @@ -175,6 +176,10 @@ xfs_dir3_leaf_check_int( } if (hdr->ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR)) stale++; + if (isleaf1 && xfs_dir2_dataptr_to_db(geo, + be32_to_cpu(hdr->ents[i].address)) >= + be32_to_cpu(ltp->bestcount)) + return __this_address; } if (hdr->stale != stale) return __this_address; diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index b55bdfa9c8a8..371dc07233e0 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -1564,20 +1564,6 @@ struct xfs_rmap_rec { #define RMAPBT_UNUSED_OFFSET_BITLEN 7 #define RMAPBT_OFFSET_BITLEN 54 -#define XFS_RMAP_ATTR_FORK (1 << 0) -#define XFS_RMAP_BMBT_BLOCK (1 << 1) -#define XFS_RMAP_UNWRITTEN (1 << 2) -#define XFS_RMAP_KEY_FLAGS (XFS_RMAP_ATTR_FORK | \ - XFS_RMAP_BMBT_BLOCK) -#define XFS_RMAP_REC_FLAGS (XFS_RMAP_UNWRITTEN) -struct xfs_rmap_irec { - xfs_agblock_t rm_startblock; /* extent start block */ - xfs_extlen_t rm_blockcount; /* extent length */ - uint64_t rm_owner; /* extent owner */ - uint64_t rm_offset; /* offset within the owner */ - unsigned int rm_flags; /* state flags */ -}; - /* * Key structure * @@ -1626,7 +1612,7 @@ unsigned int xfs_refc_block(struct xfs_mount *mp); * on the startblock. This speeds up mount time deletion of stale * staging extents because they're all at the right side of the tree. */ -#define XFS_REFC_COW_START ((xfs_agblock_t)(1U << 31)) +#define XFS_REFC_COWFLAG (1U << 31) #define REFCNTBT_COWFLAG_BITLEN 1 #define REFCNTBT_AGBLOCK_BITLEN 31 @@ -1640,12 +1626,6 @@ struct xfs_refcount_key { __be32 rc_startblock; /* starting block number */ }; -struct xfs_refcount_irec { - xfs_agblock_t rc_startblock; /* starting block number */ - xfs_extlen_t rc_blockcount; /* count of free blocks */ - xfs_nlink_t rc_refcount; /* number of inodes linked here */ -}; - #define MAXREFCOUNT ((xfs_nlink_t)~0U) #define MAXREFCEXTLEN ((xfs_extlen_t)~0U) diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index b351b9dc6561..f13e0809dc63 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -613,25 +613,49 @@ typedef struct xfs_efi_log_format { uint16_t efi_size; /* size of this item */ uint32_t efi_nextents; /* # extents to free */ uint64_t efi_id; /* efi identifier */ - xfs_extent_t efi_extents[1]; /* array of extents to free */ + xfs_extent_t efi_extents[]; /* array of extents to free */ } xfs_efi_log_format_t; +static inline size_t +xfs_efi_log_format_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efi_log_format) + + nr * sizeof(struct xfs_extent); +} + typedef struct xfs_efi_log_format_32 { uint16_t efi_type; /* efi log item type */ uint16_t efi_size; /* size of this item */ uint32_t efi_nextents; /* # extents to free */ uint64_t efi_id; /* efi identifier */ - xfs_extent_32_t efi_extents[1]; /* array of extents to free */ + xfs_extent_32_t efi_extents[]; /* array of extents to free */ } __attribute__((packed)) xfs_efi_log_format_32_t; +static inline size_t +xfs_efi_log_format32_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efi_log_format_32) + + nr * sizeof(struct xfs_extent_32); +} + typedef struct xfs_efi_log_format_64 { uint16_t efi_type; /* efi log item type */ uint16_t efi_size; /* size of this item */ uint32_t efi_nextents; /* # extents to free */ uint64_t efi_id; /* efi identifier */ - xfs_extent_64_t efi_extents[1]; /* array of extents to free */ + xfs_extent_64_t efi_extents[]; /* array of extents to free */ } xfs_efi_log_format_64_t; +static inline size_t +xfs_efi_log_format64_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efi_log_format_64) + + nr * sizeof(struct xfs_extent_64); +} + /* * This is the structure used to lay out an efd log item in the * log. The efd_extents array is a variable size array whose @@ -642,25 +666,49 @@ typedef struct xfs_efd_log_format { uint16_t efd_size; /* size of this item */ uint32_t efd_nextents; /* # of extents freed */ uint64_t efd_efi_id; /* id of corresponding efi */ - xfs_extent_t efd_extents[1]; /* array of extents freed */ + xfs_extent_t efd_extents[]; /* array of extents freed */ } xfs_efd_log_format_t; +static inline size_t +xfs_efd_log_format_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efd_log_format) + + nr * sizeof(struct xfs_extent); +} + typedef struct xfs_efd_log_format_32 { uint16_t efd_type; /* efd log item type */ uint16_t efd_size; /* size of this item */ uint32_t efd_nextents; /* # of extents freed */ uint64_t efd_efi_id; /* id of corresponding efi */ - xfs_extent_32_t efd_extents[1]; /* array of extents freed */ + xfs_extent_32_t efd_extents[]; /* array of extents freed */ } __attribute__((packed)) xfs_efd_log_format_32_t; +static inline size_t +xfs_efd_log_format32_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efd_log_format_32) + + nr * sizeof(struct xfs_extent_32); +} + typedef struct xfs_efd_log_format_64 { uint16_t efd_type; /* efd log item type */ uint16_t efd_size; /* size of this item */ uint32_t efd_nextents; /* # of extents freed */ uint64_t efd_efi_id; /* id of corresponding efi */ - xfs_extent_64_t efd_extents[1]; /* array of extents freed */ + xfs_extent_64_t efd_extents[]; /* array of extents freed */ } xfs_efd_log_format_64_t; +static inline size_t +xfs_efd_log_format64_sizeof( + unsigned int nr) +{ + return sizeof(struct xfs_efd_log_format_64) + + nr * sizeof(struct xfs_extent_64); +} + /* * RUI/RUD (reverse mapping) log format definitions */ diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index 64b910caafaa..3f34bafe18dd 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -46,13 +46,16 @@ STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur, int xfs_refcount_lookup_le( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat) { - trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno, + trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, + xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_LE); cur->bc_rec.rc.rc_startblock = bno; cur->bc_rec.rc.rc_blockcount = 0; + cur->bc_rec.rc.rc_domain = domain; return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat); } @@ -63,13 +66,16 @@ xfs_refcount_lookup_le( int xfs_refcount_lookup_ge( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat) { - trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno, + trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, + xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_GE); cur->bc_rec.rc.rc_startblock = bno; cur->bc_rec.rc.rc_blockcount = 0; + cur->bc_rec.rc.rc_domain = domain; return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat); } @@ -80,13 +86,16 @@ xfs_refcount_lookup_ge( int xfs_refcount_lookup_eq( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat) { - trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno, + trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, + xfs_refcount_encode_startblock(bno, domain), XFS_LOOKUP_LE); cur->bc_rec.rc.rc_startblock = bno; cur->bc_rec.rc.rc_blockcount = 0; + cur->bc_rec.rc.rc_domain = domain; return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat); } @@ -96,7 +105,17 @@ xfs_refcount_btrec_to_irec( const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec) { - irec->rc_startblock = be32_to_cpu(rec->refc.rc_startblock); + uint32_t start; + + start = be32_to_cpu(rec->refc.rc_startblock); + if (start & XFS_REFC_COWFLAG) { + start &= ~XFS_REFC_COWFLAG; + irec->rc_domain = XFS_REFC_DOMAIN_COW; + } else { + irec->rc_domain = XFS_REFC_DOMAIN_SHARED; + } + + irec->rc_startblock = start; irec->rc_blockcount = be32_to_cpu(rec->refc.rc_blockcount); irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount); } @@ -114,7 +133,6 @@ xfs_refcount_get_rec( struct xfs_perag *pag = cur->bc_ag.pag; union xfs_btree_rec *rec; int error; - xfs_agblock_t realstart; error = xfs_btree_get_rec(cur, &rec, stat); if (error || !*stat) @@ -124,22 +142,11 @@ xfs_refcount_get_rec( if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN) goto out_bad_rec; - /* handle special COW-staging state */ - realstart = irec->rc_startblock; - if (realstart & XFS_REFC_COW_START) { - if (irec->rc_refcount != 1) - goto out_bad_rec; - realstart &= ~XFS_REFC_COW_START; - } else if (irec->rc_refcount < 2) { + if (!xfs_refcount_check_domain(irec)) goto out_bad_rec; - } /* check for valid extent range, including overflow */ - if (!xfs_verify_agbno(pag, realstart)) - goto out_bad_rec; - if (realstart > realstart + irec->rc_blockcount) - goto out_bad_rec; - if (!xfs_verify_agbno(pag, realstart + irec->rc_blockcount - 1)) + if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount)) goto out_bad_rec; if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT) @@ -169,12 +176,17 @@ xfs_refcount_update( struct xfs_refcount_irec *irec) { union xfs_btree_rec rec; + uint32_t start; int error; trace_xfs_refcount_update(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); - rec.refc.rc_startblock = cpu_to_be32(irec->rc_startblock); + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + rec.refc.rc_startblock = cpu_to_be32(start); rec.refc.rc_blockcount = cpu_to_be32(irec->rc_blockcount); rec.refc.rc_refcount = cpu_to_be32(irec->rc_refcount); + error = xfs_btree_update(cur, &rec); if (error) trace_xfs_refcount_update_error(cur->bc_mp, @@ -196,9 +208,12 @@ xfs_refcount_insert( int error; trace_xfs_refcount_insert(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec); + cur->bc_rec.rc.rc_startblock = irec->rc_startblock; cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount; cur->bc_rec.rc.rc_refcount = irec->rc_refcount; + cur->bc_rec.rc.rc_domain = irec->rc_domain; + error = xfs_btree_insert(cur, i); if (error) goto out_error; @@ -244,7 +259,8 @@ xfs_refcount_delete( } if (error) goto out_error; - error = xfs_refcount_lookup_ge(cur, irec.rc_startblock, &found_rec); + error = xfs_refcount_lookup_ge(cur, irec.rc_domain, irec.rc_startblock, + &found_rec); out_error: if (error) trace_xfs_refcount_delete_error(cur->bc_mp, @@ -343,6 +359,7 @@ xfs_refc_next( STATIC int xfs_refcount_split_extent( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t agbno, bool *shape_changed) { @@ -351,7 +368,7 @@ xfs_refcount_split_extent( int error; *shape_changed = false; - error = xfs_refcount_lookup_le(cur, agbno, &found_rec); + error = xfs_refcount_lookup_le(cur, domain, agbno, &found_rec); if (error) goto out_error; if (!found_rec) @@ -364,6 +381,8 @@ xfs_refcount_split_extent( error = -EFSCORRUPTED; goto out_error; } + if (rcext.rc_domain != domain) + return 0; if (rcext.rc_startblock == agbno || xfs_refc_next(&rcext) <= agbno) return 0; @@ -415,6 +434,9 @@ xfs_refcount_merge_center_extents( trace_xfs_refcount_merge_center_extents(cur->bc_mp, cur->bc_ag.pag->pag_agno, left, center, right); + ASSERT(left->rc_domain == center->rc_domain); + ASSERT(right->rc_domain == center->rc_domain); + /* * Make sure the center and right extents are not in the btree. * If the center extent was synthesized, the first delete call @@ -423,8 +445,8 @@ xfs_refcount_merge_center_extents( * call removes the center and the second one removes the right * extent. */ - error = xfs_refcount_lookup_ge(cur, center->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_ge(cur, center->rc_domain, + center->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -451,8 +473,8 @@ xfs_refcount_merge_center_extents( } /* Enlarge the left extent. */ - error = xfs_refcount_lookup_le(cur, left->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, left->rc_domain, + left->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -491,10 +513,12 @@ xfs_refcount_merge_left_extent( trace_xfs_refcount_merge_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, left, cleft); + ASSERT(left->rc_domain == cleft->rc_domain); + /* If the extent at agbno (cleft) wasn't synthesized, remove it. */ if (cleft->rc_refcount > 1) { - error = xfs_refcount_lookup_le(cur, cleft->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, cleft->rc_domain, + cleft->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -512,8 +536,8 @@ xfs_refcount_merge_left_extent( } /* Enlarge the left extent. */ - error = xfs_refcount_lookup_le(cur, left->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, left->rc_domain, + left->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -552,13 +576,15 @@ xfs_refcount_merge_right_extent( trace_xfs_refcount_merge_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, cright, right); + ASSERT(right->rc_domain == cright->rc_domain); + /* * If the extent ending at agbno+aglen (cright) wasn't synthesized, * remove it. */ if (cright->rc_refcount > 1) { - error = xfs_refcount_lookup_le(cur, cright->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, cright->rc_domain, + cright->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -576,8 +602,8 @@ xfs_refcount_merge_right_extent( } /* Enlarge the right extent. */ - error = xfs_refcount_lookup_le(cur, right->rc_startblock, - &found_rec); + error = xfs_refcount_lookup_le(cur, right->rc_domain, + right->rc_startblock, &found_rec); if (error) goto out_error; if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) { @@ -600,8 +626,6 @@ out_error: return error; } -#define XFS_FIND_RCEXT_SHARED 1 -#define XFS_FIND_RCEXT_COW 2 /* * Find the left extent and the one after it (cleft). This function assumes * that we've already split any extent crossing agbno. @@ -611,16 +635,16 @@ xfs_refcount_find_left_extents( struct xfs_btree_cur *cur, struct xfs_refcount_irec *left, struct xfs_refcount_irec *cleft, + enum xfs_refc_domain domain, xfs_agblock_t agbno, - xfs_extlen_t aglen, - int flags) + xfs_extlen_t aglen) { struct xfs_refcount_irec tmp; int error; int found_rec; left->rc_startblock = cleft->rc_startblock = NULLAGBLOCK; - error = xfs_refcount_lookup_le(cur, agbno - 1, &found_rec); + error = xfs_refcount_lookup_le(cur, domain, agbno - 1, &found_rec); if (error) goto out_error; if (!found_rec) @@ -634,11 +658,9 @@ xfs_refcount_find_left_extents( goto out_error; } - if (xfs_refc_next(&tmp) != agbno) - return 0; - if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2) + if (tmp.rc_domain != domain) return 0; - if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1) + if (xfs_refc_next(&tmp) != agbno) return 0; /* We have a left extent; retrieve (or invent) the next right one */ *left = tmp; @@ -655,6 +677,9 @@ xfs_refcount_find_left_extents( goto out_error; } + if (tmp.rc_domain != domain) + goto not_found; + /* if tmp starts at the end of our range, just use that */ if (tmp.rc_startblock == agbno) *cleft = tmp; @@ -671,8 +696,10 @@ xfs_refcount_find_left_extents( cleft->rc_blockcount = min(aglen, tmp.rc_startblock - agbno); cleft->rc_refcount = 1; + cleft->rc_domain = domain; } } else { +not_found: /* * No extents, so pretend that there's one covering the whole * range. @@ -680,6 +707,7 @@ xfs_refcount_find_left_extents( cleft->rc_startblock = agbno; cleft->rc_blockcount = aglen; cleft->rc_refcount = 1; + cleft->rc_domain = domain; } trace_xfs_refcount_find_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, left, cleft, agbno); @@ -700,16 +728,16 @@ xfs_refcount_find_right_extents( struct xfs_btree_cur *cur, struct xfs_refcount_irec *right, struct xfs_refcount_irec *cright, + enum xfs_refc_domain domain, xfs_agblock_t agbno, - xfs_extlen_t aglen, - int flags) + xfs_extlen_t aglen) { struct xfs_refcount_irec tmp; int error; int found_rec; right->rc_startblock = cright->rc_startblock = NULLAGBLOCK; - error = xfs_refcount_lookup_ge(cur, agbno + aglen, &found_rec); + error = xfs_refcount_lookup_ge(cur, domain, agbno + aglen, &found_rec); if (error) goto out_error; if (!found_rec) @@ -723,11 +751,9 @@ xfs_refcount_find_right_extents( goto out_error; } - if (tmp.rc_startblock != agbno + aglen) - return 0; - if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2) + if (tmp.rc_domain != domain) return 0; - if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1) + if (tmp.rc_startblock != agbno + aglen) return 0; /* We have a right extent; retrieve (or invent) the next left one */ *right = tmp; @@ -744,6 +770,9 @@ xfs_refcount_find_right_extents( goto out_error; } + if (tmp.rc_domain != domain) + goto not_found; + /* if tmp ends at the end of our range, just use that */ if (xfs_refc_next(&tmp) == agbno + aglen) *cright = tmp; @@ -760,8 +789,10 @@ xfs_refcount_find_right_extents( cright->rc_blockcount = right->rc_startblock - cright->rc_startblock; cright->rc_refcount = 1; + cright->rc_domain = domain; } } else { +not_found: /* * No extents, so pretend that there's one covering the whole * range. @@ -769,6 +800,7 @@ xfs_refcount_find_right_extents( cright->rc_startblock = agbno; cright->rc_blockcount = aglen; cright->rc_refcount = 1; + cright->rc_domain = domain; } trace_xfs_refcount_find_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, cright, right, agbno + aglen); @@ -794,10 +826,10 @@ xfs_refc_valid( STATIC int xfs_refcount_merge_extents( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t *agbno, xfs_extlen_t *aglen, enum xfs_refc_adjust_op adjust, - int flags, bool *shape_changed) { struct xfs_refcount_irec left = {0}, cleft = {0}; @@ -812,12 +844,12 @@ xfs_refcount_merge_extents( * just below (agbno + aglen) [cright], and just above (agbno + aglen) * [right]. */ - error = xfs_refcount_find_left_extents(cur, &left, &cleft, *agbno, - *aglen, flags); + error = xfs_refcount_find_left_extents(cur, &left, &cleft, domain, + *agbno, *aglen); if (error) return error; - error = xfs_refcount_find_right_extents(cur, &right, &cright, *agbno, - *aglen, flags); + error = xfs_refcount_find_right_extents(cur, &right, &cright, domain, + *agbno, *aglen); if (error) return error; @@ -870,7 +902,7 @@ xfs_refcount_merge_extents( aglen); } - return error; + return 0; } /* @@ -933,7 +965,8 @@ xfs_refcount_adjust_extents( if (*aglen == 0) return 0; - error = xfs_refcount_lookup_ge(cur, *agbno, &found_rec); + error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_SHARED, *agbno, + &found_rec); if (error) goto out_error; @@ -941,10 +974,11 @@ xfs_refcount_adjust_extents( error = xfs_refcount_get_rec(cur, &ext, &found_rec); if (error) goto out_error; - if (!found_rec) { + if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) { ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; ext.rc_blockcount = 0; ext.rc_refcount = 0; + ext.rc_domain = XFS_REFC_DOMAIN_SHARED; } /* @@ -957,6 +991,8 @@ xfs_refcount_adjust_extents( tmp.rc_blockcount = min(*aglen, ext.rc_startblock - *agbno); tmp.rc_refcount = 1 + adj; + tmp.rc_domain = XFS_REFC_DOMAIN_SHARED; + trace_xfs_refcount_modify_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, &tmp); @@ -986,15 +1022,30 @@ xfs_refcount_adjust_extents( (*agbno) += tmp.rc_blockcount; (*aglen) -= tmp.rc_blockcount; - error = xfs_refcount_lookup_ge(cur, *agbno, + /* Stop if there's nothing left to modify */ + if (*aglen == 0 || !xfs_refcount_still_have_space(cur)) + break; + + /* Move the cursor to the start of ext. */ + error = xfs_refcount_lookup_ge(cur, + XFS_REFC_DOMAIN_SHARED, *agbno, &found_rec); if (error) goto out_error; } - /* Stop if there's nothing left to modify */ - if (*aglen == 0 || !xfs_refcount_still_have_space(cur)) - break; + /* + * A previous step trimmed agbno/aglen such that the end of the + * range would not be in the middle of the record. If this is + * no longer the case, something is seriously wrong with the + * btree. Make sure we never feed the synthesized record into + * the processing loop below. + */ + if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) || + XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) { + error = -EFSCORRUPTED; + goto out_error; + } /* * Adjust the reference count and either update the tree @@ -1070,13 +1121,15 @@ xfs_refcount_adjust( /* * Ensure that no rcextents cross the boundary of the adjustment range. */ - error = xfs_refcount_split_extent(cur, agbno, &shape_changed); + error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, + agbno, &shape_changed); if (error) goto out_error; if (shape_changed) shape_changes++; - error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed); + error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED, + agbno + aglen, &shape_changed); if (error) goto out_error; if (shape_changed) @@ -1085,8 +1138,8 @@ xfs_refcount_adjust( /* * Try to merge with the left or right extents of the range. */ - error = xfs_refcount_merge_extents(cur, new_agbno, new_aglen, adj, - XFS_FIND_RCEXT_SHARED, &shape_changed); + error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_SHARED, + new_agbno, new_aglen, adj, &shape_changed); if (error) goto out_error; if (shape_changed) @@ -1125,6 +1178,32 @@ xfs_refcount_finish_one_cleanup( } /* + * Set up a continuation a deferred refcount operation by updating the intent. + * Checks to make sure we're not going to run off the end of the AG. + */ +static inline int +xfs_refcount_continue_op( + struct xfs_btree_cur *cur, + xfs_fsblock_t startblock, + xfs_agblock_t new_agbno, + xfs_extlen_t new_len, + xfs_fsblock_t *new_fsbno) +{ + struct xfs_mount *mp = cur->bc_mp; + struct xfs_perag *pag = cur->bc_ag.pag; + + if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, new_len))) + return -EFSCORRUPTED; + + *new_fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); + + ASSERT(xfs_verify_fsbext(mp, *new_fsbno, new_len)); + ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, *new_fsbno)); + + return 0; +} + +/* * Process one of the deferred refcount operations. We pass back the * btree cursor to maintain our lock on the btree between calls. * This saves time and eliminates a buffer deadlock between the @@ -1191,12 +1270,20 @@ xfs_refcount_finish_one( case XFS_REFCOUNT_INCREASE: error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, new_len, XFS_REFCOUNT_ADJUST_INCREASE); - *new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); + if (error) + goto out_drop; + if (*new_len > 0) + error = xfs_refcount_continue_op(rcur, startblock, + new_agbno, *new_len, new_fsb); break; case XFS_REFCOUNT_DECREASE: error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno, new_len, XFS_REFCOUNT_ADJUST_DECREASE); - *new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno); + if (error) + goto out_drop; + if (*new_len > 0) + error = xfs_refcount_continue_op(rcur, startblock, + new_agbno, *new_len, new_fsb); break; case XFS_REFCOUNT_ALLOC_COW: *new_fsb = startblock + blockcount; @@ -1307,7 +1394,8 @@ xfs_refcount_find_shared( *flen = 0; /* Try to find a refcount extent that crosses the start */ - error = xfs_refcount_lookup_le(cur, agbno, &have); + error = xfs_refcount_lookup_le(cur, XFS_REFC_DOMAIN_SHARED, agbno, + &have); if (error) goto out_error; if (!have) { @@ -1325,6 +1413,8 @@ xfs_refcount_find_shared( error = -EFSCORRUPTED; goto out_error; } + if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED) + goto done; /* If the extent ends before the start, look at the next one */ if (tmp.rc_startblock + tmp.rc_blockcount <= agbno) { @@ -1340,6 +1430,8 @@ xfs_refcount_find_shared( error = -EFSCORRUPTED; goto out_error; } + if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED) + goto done; } /* If the extent starts after the range we want, bail out */ @@ -1371,7 +1463,8 @@ xfs_refcount_find_shared( error = -EFSCORRUPTED; goto out_error; } - if (tmp.rc_startblock >= agbno + aglen || + if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED || + tmp.rc_startblock >= agbno + aglen || tmp.rc_startblock != *fbno + *flen) break; *flen = min(*flen + tmp.rc_blockcount, agbno + aglen - *fbno); @@ -1455,17 +1548,23 @@ xfs_refcount_adjust_cow_extents( return 0; /* Find any overlapping refcount records */ - error = xfs_refcount_lookup_ge(cur, agbno, &found_rec); + error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_COW, agbno, + &found_rec); if (error) goto out_error; error = xfs_refcount_get_rec(cur, &ext, &found_rec); if (error) goto out_error; + if (XFS_IS_CORRUPT(cur->bc_mp, found_rec && + ext.rc_domain != XFS_REFC_DOMAIN_COW)) { + error = -EFSCORRUPTED; + goto out_error; + } if (!found_rec) { - ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks + - XFS_REFC_COW_START; + ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks; ext.rc_blockcount = 0; ext.rc_refcount = 0; + ext.rc_domain = XFS_REFC_DOMAIN_COW; } switch (adj) { @@ -1480,6 +1579,8 @@ xfs_refcount_adjust_cow_extents( tmp.rc_startblock = agbno; tmp.rc_blockcount = aglen; tmp.rc_refcount = 1; + tmp.rc_domain = XFS_REFC_DOMAIN_COW; + trace_xfs_refcount_modify_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno, &tmp); @@ -1542,24 +1643,24 @@ xfs_refcount_adjust_cow( bool shape_changed; int error; - agbno += XFS_REFC_COW_START; - /* * Ensure that no rcextents cross the boundary of the adjustment range. */ - error = xfs_refcount_split_extent(cur, agbno, &shape_changed); + error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW, + agbno, &shape_changed); if (error) goto out_error; - error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed); + error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW, + agbno + aglen, &shape_changed); if (error) goto out_error; /* * Try to merge with the left or right extents of the range. */ - error = xfs_refcount_merge_extents(cur, &agbno, &aglen, adj, - XFS_FIND_RCEXT_COW, &shape_changed); + error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_COW, &agbno, + &aglen, adj, &shape_changed); if (error) goto out_error; @@ -1666,10 +1767,18 @@ xfs_refcount_recover_extent( be32_to_cpu(rec->refc.rc_refcount) != 1)) return -EFSCORRUPTED; - rr = kmem_alloc(sizeof(struct xfs_refcount_recovery), 0); + rr = kmalloc(sizeof(struct xfs_refcount_recovery), + GFP_KERNEL | __GFP_NOFAIL); + INIT_LIST_HEAD(&rr->rr_list); xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec); - list_add_tail(&rr->rr_list, debris); + if (XFS_IS_CORRUPT(cur->bc_mp, + rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) { + kfree(rr); + return -EFSCORRUPTED; + } + + list_add_tail(&rr->rr_list, debris); return 0; } @@ -1687,10 +1796,11 @@ xfs_refcount_recover_cow_leftovers( union xfs_btree_irec low; union xfs_btree_irec high; xfs_fsblock_t fsb; - xfs_agblock_t agbno; int error; - if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START) + /* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */ + BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG); + if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS) return -EOPNOTSUPP; INIT_LIST_HEAD(&debris); @@ -1717,7 +1827,7 @@ xfs_refcount_recover_cow_leftovers( /* Find all the leftover CoW staging extents. */ memset(&low, 0, sizeof(low)); memset(&high, 0, sizeof(high)); - low.rc.rc_startblock = XFS_REFC_COW_START; + low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW; high.rc.rc_startblock = -1U; error = xfs_btree_query_range(cur, &low, &high, xfs_refcount_recover_extent, &debris); @@ -1738,8 +1848,8 @@ xfs_refcount_recover_cow_leftovers( &rr->rr_rrec); /* Free the orphan record */ - agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START; - fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno); + fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, + rr->rr_rrec.rc_startblock); xfs_refcount_free_cow_extent(tp, fsb, rr->rr_rrec.rc_blockcount); @@ -1751,7 +1861,7 @@ xfs_refcount_recover_cow_leftovers( goto out_free; list_del(&rr->rr_list); - kmem_free(rr); + kfree(rr); } return error; @@ -1761,7 +1871,7 @@ out_free: /* Free the leftover list */ list_for_each_entry_safe(rr, n, &debris, rr_list) { list_del(&rr->rr_list); - kmem_free(rr); + kfree(rr); } return error; } @@ -1770,6 +1880,7 @@ out_free: int xfs_refcount_has_record( struct xfs_btree_cur *cur, + enum xfs_refc_domain domain, xfs_agblock_t bno, xfs_extlen_t len, bool *exists) @@ -1781,6 +1892,7 @@ xfs_refcount_has_record( low.rc.rc_startblock = bno; memset(&high, 0xFF, sizeof(high)); high.rc.rc_startblock = bno + len - 1; + low.rc.rc_domain = high.rc.rc_domain = domain; return xfs_btree_has_record(cur, &low, &high, exists); } diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h index e8b322de7f3d..452f30556f5a 100644 --- a/fs/xfs/libxfs/xfs_refcount.h +++ b/fs/xfs/libxfs/xfs_refcount.h @@ -14,14 +14,33 @@ struct xfs_bmbt_irec; struct xfs_refcount_irec; extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur, - xfs_agblock_t bno, int *stat); + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); extern int xfs_refcount_lookup_ge(struct xfs_btree_cur *cur, - xfs_agblock_t bno, int *stat); + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); extern int xfs_refcount_lookup_eq(struct xfs_btree_cur *cur, - xfs_agblock_t bno, int *stat); + enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat); extern int xfs_refcount_get_rec(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, int *stat); +static inline uint32_t +xfs_refcount_encode_startblock( + xfs_agblock_t startblock, + enum xfs_refc_domain domain) +{ + uint32_t start; + + /* + * low level btree operations need to handle the generic btree range + * query functions (which set rc_domain == -1U), so we check that the + * domain is /not/ shared. + */ + start = startblock & ~XFS_REFC_COWFLAG; + if (domain != XFS_REFC_DOMAIN_SHARED) + start |= XFS_REFC_COWFLAG; + + return start; +} + enum xfs_refcount_intent_type { XFS_REFCOUNT_INCREASE = 1, XFS_REFCOUNT_DECREASE, @@ -36,6 +55,18 @@ struct xfs_refcount_intent { xfs_fsblock_t ri_startblock; }; +/* Check that the refcount is appropriate for the record domain. */ +static inline bool +xfs_refcount_check_domain( + const struct xfs_refcount_irec *irec) +{ + if (irec->rc_domain == XFS_REFC_DOMAIN_COW && irec->rc_refcount != 1) + return false; + if (irec->rc_domain == XFS_REFC_DOMAIN_SHARED && irec->rc_refcount < 2) + return false; + return true; +} + void xfs_refcount_increase_extent(struct xfs_trans *tp, struct xfs_bmbt_irec *irec); void xfs_refcount_decrease_extent(struct xfs_trans *tp, @@ -79,7 +110,8 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp, #define XFS_REFCOUNT_ITEM_OVERHEAD 32 extern int xfs_refcount_has_record(struct xfs_btree_cur *cur, - xfs_agblock_t bno, xfs_extlen_t len, bool *exists); + enum xfs_refc_domain domain, xfs_agblock_t bno, + xfs_extlen_t len, bool *exists); union xfs_btree_rec; extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec, struct xfs_refcount_irec *irec); diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c index 316c1ec0c3c2..e1f789866683 100644 --- a/fs/xfs/libxfs/xfs_refcount_btree.c +++ b/fs/xfs/libxfs/xfs_refcount_btree.c @@ -13,6 +13,7 @@ #include "xfs_btree.h" #include "xfs_btree_staging.h" #include "xfs_refcount_btree.h" +#include "xfs_refcount.h" #include "xfs_alloc.h" #include "xfs_error.h" #include "xfs_trace.h" @@ -160,7 +161,12 @@ xfs_refcountbt_init_rec_from_cur( struct xfs_btree_cur *cur, union xfs_btree_rec *rec) { - rec->refc.rc_startblock = cpu_to_be32(cur->bc_rec.rc.rc_startblock); + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; + + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + rec->refc.rc_startblock = cpu_to_be32(start); rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount); rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount); } @@ -182,10 +188,13 @@ xfs_refcountbt_key_diff( struct xfs_btree_cur *cur, const union xfs_btree_key *key) { - struct xfs_refcount_irec *rec = &cur->bc_rec.rc; const struct xfs_refcount_key *kp = &key->refc; + const struct xfs_refcount_irec *irec = &cur->bc_rec.rc; + uint32_t start; - return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock; + start = xfs_refcount_encode_startblock(irec->rc_startblock, + irec->rc_domain); + return (int64_t)be32_to_cpu(kp->rc_startblock) - start; } STATIC int64_t diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c index 094dfc897ebc..b56aca1e7c66 100644 --- a/fs/xfs/libxfs/xfs_rmap.c +++ b/fs/xfs/libxfs/xfs_rmap.c @@ -235,13 +235,8 @@ xfs_rmap_get_rec( goto out_bad_rec; } else { /* check for valid extent range, including overflow */ - if (!xfs_verify_agbno(pag, irec->rm_startblock)) - goto out_bad_rec; - if (irec->rm_startblock > - irec->rm_startblock + irec->rm_blockcount) - goto out_bad_rec; - if (!xfs_verify_agbno(pag, - irec->rm_startblock + irec->rm_blockcount - 1)) + if (!xfs_verify_agbext(pag, irec->rm_startblock, + irec->rm_blockcount)) goto out_bad_rec; } diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index 2c4ad6e4bb14..5b2f27cbdb80 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -422,7 +422,7 @@ xfs_calc_itruncate_reservation_minlogsize( /* * In renaming a files we can modify: - * the four inodes involved: 4 * inode size + * the five inodes involved: 5 * inode size * the two directory btrees: 2 * (max depth + v2) * dir block size * the two directory bmap btrees: 2 * max depth * block size * And the bmap_finish transaction can free dir and bmap blocks (two sets @@ -437,7 +437,7 @@ xfs_calc_rename_reservation( struct xfs_mount *mp) { return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 4) + + max((xfs_calc_inode_res(mp, 5) + xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1))), (xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) + diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h index a6b7d98cf68f..5ebdda7e1078 100644 --- a/fs/xfs/libxfs/xfs_types.h +++ b/fs/xfs/libxfs/xfs_types.h @@ -166,6 +166,36 @@ typedef struct xfs_bmbt_irec xfs_exntst_t br_state; /* extent state */ } xfs_bmbt_irec_t; +enum xfs_refc_domain { + XFS_REFC_DOMAIN_SHARED = 0, + XFS_REFC_DOMAIN_COW, +}; + +#define XFS_REFC_DOMAIN_STRINGS \ + { XFS_REFC_DOMAIN_SHARED, "shared" }, \ + { XFS_REFC_DOMAIN_COW, "cow" } + +struct xfs_refcount_irec { + xfs_agblock_t rc_startblock; /* starting block number */ + xfs_extlen_t rc_blockcount; /* count of free blocks */ + xfs_nlink_t rc_refcount; /* number of inodes linked here */ + enum xfs_refc_domain rc_domain; /* shared or cow staging extent? */ +}; + +#define XFS_RMAP_ATTR_FORK (1 << 0) +#define XFS_RMAP_BMBT_BLOCK (1 << 1) +#define XFS_RMAP_UNWRITTEN (1 << 2) +#define XFS_RMAP_KEY_FLAGS (XFS_RMAP_ATTR_FORK | \ + XFS_RMAP_BMBT_BLOCK) +#define XFS_RMAP_REC_FLAGS (XFS_RMAP_UNWRITTEN) +struct xfs_rmap_irec { + xfs_agblock_t rm_startblock; /* extent start block */ + xfs_extlen_t rm_blockcount; /* extent length */ + uint64_t rm_owner; /* extent owner */ + uint64_t rm_offset; /* offset within the owner */ + unsigned int rm_flags; /* state flags */ +}; + /* per-AG block reservation types */ enum xfs_ag_resv_type { XFS_AG_RESV_NONE = 0, diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c index ab427b4d7fe0..3b38f4e2a537 100644 --- a/fs/xfs/scrub/alloc.c +++ b/fs/xfs/scrub/alloc.c @@ -100,9 +100,7 @@ xchk_allocbt_rec( bno = be32_to_cpu(rec->alloc.ar_startblock); len = be32_to_cpu(rec->alloc.ar_blockcount); - if (bno + len <= bno || - !xfs_verify_agbno(pag, bno) || - !xfs_verify_agbno(pag, bno + len - 1)) + if (!xfs_verify_agbext(pag, bno, len)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); xchk_allocbt_xref(bs->sc, bno, len); diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c index e1026e07bf94..e312be7cd375 100644 --- a/fs/xfs/scrub/ialloc.c +++ b/fs/xfs/scrub/ialloc.c @@ -108,9 +108,8 @@ xchk_iallocbt_chunk( xfs_agblock_t bno; bno = XFS_AGINO_TO_AGBNO(mp, agino); - if (bno + len <= bno || - !xfs_verify_agbno(pag, bno) || - !xfs_verify_agbno(pag, bno + len - 1)) + + if (!xfs_verify_agbext(pag, bno, len)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len); diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c index c68b767dc08f..a26ee0f24ef2 100644 --- a/fs/xfs/scrub/refcount.c +++ b/fs/xfs/scrub/refcount.c @@ -269,15 +269,13 @@ done: STATIC void xchk_refcountbt_xref_rmap( struct xfs_scrub *sc, - xfs_agblock_t bno, - xfs_extlen_t len, - xfs_nlink_t refcount) + const struct xfs_refcount_irec *irec) { struct xchk_refcnt_check refchk = { - .sc = sc, - .bno = bno, - .len = len, - .refcount = refcount, + .sc = sc, + .bno = irec->rc_startblock, + .len = irec->rc_blockcount, + .refcount = irec->rc_refcount, .seen = 0, }; struct xfs_rmap_irec low; @@ -291,9 +289,9 @@ xchk_refcountbt_xref_rmap( /* Cross-reference with the rmapbt to confirm the refcount. */ memset(&low, 0, sizeof(low)); - low.rm_startblock = bno; + low.rm_startblock = irec->rc_startblock; memset(&high, 0xFF, sizeof(high)); - high.rm_startblock = bno + len - 1; + high.rm_startblock = irec->rc_startblock + irec->rc_blockcount - 1; INIT_LIST_HEAD(&refchk.fragments); error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high, @@ -302,7 +300,7 @@ xchk_refcountbt_xref_rmap( goto out_free; xchk_refcountbt_process_rmap_fragments(&refchk); - if (refcount != refchk.seen) + if (irec->rc_refcount != refchk.seen) xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0); out_free: @@ -315,17 +313,16 @@ out_free: /* Cross-reference with the other btrees. */ STATIC void xchk_refcountbt_xref( - struct xfs_scrub *sc, - xfs_agblock_t agbno, - xfs_extlen_t len, - xfs_nlink_t refcount) + struct xfs_scrub *sc, + const struct xfs_refcount_irec *irec) { if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT) return; - xchk_xref_is_used_space(sc, agbno, len); - xchk_xref_is_not_inode_chunk(sc, agbno, len); - xchk_refcountbt_xref_rmap(sc, agbno, len, refcount); + xchk_xref_is_used_space(sc, irec->rc_startblock, irec->rc_blockcount); + xchk_xref_is_not_inode_chunk(sc, irec->rc_startblock, + irec->rc_blockcount); + xchk_refcountbt_xref_rmap(sc, irec); } /* Scrub a refcountbt record. */ @@ -334,35 +331,27 @@ xchk_refcountbt_rec( struct xchk_btree *bs, const union xfs_btree_rec *rec) { + struct xfs_refcount_irec irec; xfs_agblock_t *cow_blocks = bs->private; struct xfs_perag *pag = bs->cur->bc_ag.pag; - xfs_agblock_t bno; - xfs_extlen_t len; - xfs_nlink_t refcount; - bool has_cowflag; - bno = be32_to_cpu(rec->refc.rc_startblock); - len = be32_to_cpu(rec->refc.rc_blockcount); - refcount = be32_to_cpu(rec->refc.rc_refcount); + xfs_refcount_btrec_to_irec(rec, &irec); - /* Only CoW records can have refcount == 1. */ - has_cowflag = (bno & XFS_REFC_COW_START); - if ((refcount == 1 && !has_cowflag) || (refcount != 1 && has_cowflag)) + /* Check the domain and refcount are not incompatible. */ + if (!xfs_refcount_check_domain(&irec)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - if (has_cowflag) - (*cow_blocks) += len; + + if (irec.rc_domain == XFS_REFC_DOMAIN_COW) + (*cow_blocks) += irec.rc_blockcount; /* Check the extent. */ - bno &= ~XFS_REFC_COW_START; - if (bno + len <= bno || - !xfs_verify_agbno(pag, bno) || - !xfs_verify_agbno(pag, bno + len - 1)) + if (!xfs_verify_agbext(pag, irec.rc_startblock, irec.rc_blockcount)) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - if (refcount == 0) + if (irec.rc_refcount == 0) xchk_btree_set_corrupt(bs->sc, bs->cur, 0); - xchk_refcountbt_xref(bs->sc, bno, len, refcount); + xchk_refcountbt_xref(bs->sc, &irec); return 0; } @@ -426,7 +415,6 @@ xchk_xref_is_cow_staging( xfs_extlen_t len) { struct xfs_refcount_irec rc; - bool has_cowflag; int has_refcount; int error; @@ -434,8 +422,8 @@ xchk_xref_is_cow_staging( return; /* Find the CoW staging extent. */ - error = xfs_refcount_lookup_le(sc->sa.refc_cur, - agbno + XFS_REFC_COW_START, &has_refcount); + error = xfs_refcount_lookup_le(sc->sa.refc_cur, XFS_REFC_DOMAIN_COW, + agbno, &has_refcount); if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur)) return; if (!has_refcount) { @@ -451,9 +439,8 @@ xchk_xref_is_cow_staging( return; } - /* CoW flag must be set, refcount must be 1. */ - has_cowflag = (rc.rc_startblock & XFS_REFC_COW_START); - if (!has_cowflag || rc.rc_refcount != 1) + /* CoW lookup returned a shared extent record? */ + if (rc.rc_domain != XFS_REFC_DOMAIN_COW) xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0); /* Must be at least as long as what was passed in */ @@ -477,7 +464,8 @@ xchk_xref_is_not_shared( if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm)) return; - error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared); + error = xfs_refcount_has_record(sc->sa.refc_cur, XFS_REFC_DOMAIN_SHARED, + agbno, len, &shared); if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur)) return; if (shared) diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c index cf5ce607dc05..2788a6f2edcd 100644 --- a/fs/xfs/xfs_attr_item.c +++ b/fs/xfs/xfs_attr_item.c @@ -245,28 +245,6 @@ xfs_attri_init( return attrip; } -/* - * Copy an attr format buffer from the given buf, and into the destination attr - * format structure. - */ -STATIC int -xfs_attri_copy_format( - struct xfs_log_iovec *buf, - struct xfs_attri_log_format *dst_attr_fmt) -{ - struct xfs_attri_log_format *src_attr_fmt = buf->i_addr; - size_t len; - - len = sizeof(struct xfs_attri_log_format); - if (buf->i_len != len) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); - return -EFSCORRUPTED; - } - - memcpy((char *)dst_attr_fmt, (char *)src_attr_fmt, len); - return 0; -} - static inline struct xfs_attrd_log_item *ATTRD_ITEM(struct xfs_log_item *lip) { return container_of(lip, struct xfs_attrd_log_item, attrd_item); @@ -731,24 +709,50 @@ xlog_recover_attri_commit_pass2( struct xfs_attri_log_nameval *nv; const void *attr_value = NULL; const void *attr_name; - int error; + size_t len; attri_formatp = item->ri_buf[0].i_addr; attr_name = item->ri_buf[1].i_addr; /* Validate xfs_attri_log_format before the large memory allocation */ + len = sizeof(struct xfs_attri_log_format); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + if (!xfs_attri_validate(mp, attri_formatp)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + /* Validate the attr name */ + if (item->ri_buf[1].i_len != + xlog_calc_iovec_len(attri_formatp->alfi_name_len)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } if (!xfs_attr_namecheck(attr_name, attri_formatp->alfi_name_len)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[1].i_addr, item->ri_buf[1].i_len); return -EFSCORRUPTED; } - if (attri_formatp->alfi_value_len) + /* Validate the attr value, if present */ + if (attri_formatp->alfi_value_len != 0) { + if (item->ri_buf[2].i_len != xlog_calc_iovec_len(attri_formatp->alfi_value_len)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, + item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + attr_value = item->ri_buf[2].i_addr; + } /* * Memory alloc failure will cause replay to abort. We attach the @@ -760,9 +764,7 @@ xlog_recover_attri_commit_pass2( attri_formatp->alfi_value_len); attrip = xfs_attri_init(mp, nv); - error = xfs_attri_copy_format(&item->ri_buf[0], &attrip->attri_format); - if (error) - goto out; + memcpy(&attrip->attri_format, attri_formatp, len); /* * The ATTRI has two references. One for the ATTRD and one for ATTRI to @@ -774,10 +776,6 @@ xlog_recover_attri_commit_pass2( xfs_attri_release(attrip); xfs_attri_log_nameval_put(nv); return 0; -out: - xfs_attri_item_free(attrip); - xfs_attri_log_nameval_put(nv); - return error; } /* @@ -842,7 +840,8 @@ xlog_recover_attrd_commit_pass2( attrd_formatp = item->ri_buf[0].i_addr; if (item->ri_buf[0].i_len != sizeof(struct xfs_attrd_log_format)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 51f66e982484..41323da523d1 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -608,28 +608,18 @@ static const struct xfs_item_ops xfs_bui_item_ops = { .iop_relog = xfs_bui_item_relog, }; -/* - * Copy an BUI format buffer from the given buf, and into the destination - * BUI format structure. The BUI/BUD items were designed not to need any - * special alignment handling. - */ -static int +static inline void xfs_bui_copy_format( - struct xfs_log_iovec *buf, - struct xfs_bui_log_format *dst_bui_fmt) + struct xfs_bui_log_format *dst, + const struct xfs_bui_log_format *src) { - struct xfs_bui_log_format *src_bui_fmt; - uint len; + unsigned int i; - src_bui_fmt = buf->i_addr; - len = xfs_bui_log_format_sizeof(src_bui_fmt->bui_nextents); + memcpy(dst, src, offsetof(struct xfs_bui_log_format, bui_extents)); - if (buf->i_len == len) { - memcpy(dst_bui_fmt, src_bui_fmt, len); - return 0; - } - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); - return -EFSCORRUPTED; + for (i = 0; i < src->bui_nextents; i++) + memcpy(&dst->bui_extents[i], &src->bui_extents[i], + sizeof(struct xfs_map_extent)); } /* @@ -646,23 +636,34 @@ xlog_recover_bui_commit_pass2( struct xlog_recover_item *item, xfs_lsn_t lsn) { - int error; struct xfs_mount *mp = log->l_mp; struct xfs_bui_log_item *buip; struct xfs_bui_log_format *bui_formatp; + size_t len; bui_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len < xfs_bui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } - buip = xfs_bui_init(mp); - error = xfs_bui_copy_format(&item->ri_buf[0], &buip->bui_format); - if (error) { - xfs_bui_item_free(buip); - return error; + + len = xfs_bui_log_format_sizeof(bui_formatp->bui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; } + + buip = xfs_bui_init(mp); + xfs_bui_copy_format(&buip->bui_format, bui_formatp); atomic_set(&buip->bui_next_extent, bui_formatp->bui_nextents); /* * Insert the intent into the AIL directly and drop one reference so @@ -696,7 +697,8 @@ xlog_recover_bud_commit_pass2( bud_formatp = item->ri_buf[0].i_addr; if (item->ri_buf[0].i_len != sizeof(struct xfs_bud_log_format)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c index 7db588ed0be5..c6b2aabd6f18 100644 --- a/fs/xfs/xfs_error.c +++ b/fs/xfs/xfs_error.c @@ -234,13 +234,18 @@ int xfs_errortag_init( struct xfs_mount *mp) { + int ret; + mp->m_errortag = kmem_zalloc(sizeof(unsigned int) * XFS_ERRTAG_MAX, KM_MAYFAIL); if (!mp->m_errortag) return -ENOMEM; - return xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype, - &mp->m_kobj, "errortag"); + ret = xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype, + &mp->m_kobj, "errortag"); + if (ret) + kmem_free(mp->m_errortag); + return ret; } void diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c index 27ccfcd82f04..d5130d1fcfae 100644 --- a/fs/xfs/xfs_extfree_item.c +++ b/fs/xfs/xfs_extfree_item.c @@ -66,27 +66,16 @@ xfs_efi_release( xfs_efi_item_free(efip); } -/* - * This returns the number of iovecs needed to log the given efi item. - * We only need 1 iovec for an efi item. It just logs the efi_log_format - * structure. - */ -static inline int -xfs_efi_item_sizeof( - struct xfs_efi_log_item *efip) -{ - return sizeof(struct xfs_efi_log_format) + - (efip->efi_format.efi_nextents - 1) * sizeof(xfs_extent_t); -} - STATIC void xfs_efi_item_size( struct xfs_log_item *lip, int *nvecs, int *nbytes) { + struct xfs_efi_log_item *efip = EFI_ITEM(lip); + *nvecs += 1; - *nbytes += xfs_efi_item_sizeof(EFI_ITEM(lip)); + *nbytes += xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents); } /* @@ -112,7 +101,7 @@ xfs_efi_item_format( xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFI_FORMAT, &efip->efi_format, - xfs_efi_item_sizeof(efip)); + xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents)); } @@ -155,13 +144,11 @@ xfs_efi_init( { struct xfs_efi_log_item *efip; - uint size; ASSERT(nextents > 0); if (nextents > XFS_EFI_MAX_FAST_EXTENTS) { - size = (uint)(sizeof(struct xfs_efi_log_item) + - ((nextents - 1) * sizeof(xfs_extent_t))); - efip = kmem_zalloc(size, 0); + efip = kzalloc(xfs_efi_log_item_sizeof(nextents), + GFP_KERNEL | __GFP_NOFAIL); } else { efip = kmem_cache_zalloc(xfs_efi_cache, GFP_KERNEL | __GFP_NOFAIL); @@ -188,15 +175,17 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt) { xfs_efi_log_format_t *src_efi_fmt = buf->i_addr; uint i; - uint len = sizeof(xfs_efi_log_format_t) + - (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_t); - uint len32 = sizeof(xfs_efi_log_format_32_t) + - (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_32_t); - uint len64 = sizeof(xfs_efi_log_format_64_t) + - (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_64_t); + uint len = xfs_efi_log_format_sizeof(src_efi_fmt->efi_nextents); + uint len32 = xfs_efi_log_format32_sizeof(src_efi_fmt->efi_nextents); + uint len64 = xfs_efi_log_format64_sizeof(src_efi_fmt->efi_nextents); if (buf->i_len == len) { - memcpy((char *)dst_efi_fmt, (char*)src_efi_fmt, len); + memcpy(dst_efi_fmt, src_efi_fmt, + offsetof(struct xfs_efi_log_format, efi_extents)); + for (i = 0; i < src_efi_fmt->efi_nextents; i++) + memcpy(&dst_efi_fmt->efi_extents[i], + &src_efi_fmt->efi_extents[i], + sizeof(struct xfs_extent)); return 0; } else if (buf->i_len == len32) { xfs_efi_log_format_32_t *src_efi_fmt_32 = buf->i_addr; @@ -227,7 +216,8 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt) } return 0; } - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, NULL, buf->i_addr, + buf->i_len); return -EFSCORRUPTED; } @@ -246,27 +236,16 @@ xfs_efd_item_free(struct xfs_efd_log_item *efdp) kmem_cache_free(xfs_efd_cache, efdp); } -/* - * This returns the number of iovecs needed to log the given efd item. - * We only need 1 iovec for an efd item. It just logs the efd_log_format - * structure. - */ -static inline int -xfs_efd_item_sizeof( - struct xfs_efd_log_item *efdp) -{ - return sizeof(xfs_efd_log_format_t) + - (efdp->efd_format.efd_nextents - 1) * sizeof(xfs_extent_t); -} - STATIC void xfs_efd_item_size( struct xfs_log_item *lip, int *nvecs, int *nbytes) { + struct xfs_efd_log_item *efdp = EFD_ITEM(lip); + *nvecs += 1; - *nbytes += xfs_efd_item_sizeof(EFD_ITEM(lip)); + *nbytes += xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents); } /* @@ -291,7 +270,7 @@ xfs_efd_item_format( xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFD_FORMAT, &efdp->efd_format, - xfs_efd_item_sizeof(efdp)); + xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents)); } /* @@ -340,9 +319,8 @@ xfs_trans_get_efd( ASSERT(nextents > 0); if (nextents > XFS_EFD_MAX_FAST_EXTENTS) { - efdp = kmem_zalloc(sizeof(struct xfs_efd_log_item) + - (nextents - 1) * sizeof(struct xfs_extent), - 0); + efdp = kzalloc(xfs_efd_log_item_sizeof(nextents), + GFP_KERNEL | __GFP_NOFAIL); } else { efdp = kmem_cache_zalloc(xfs_efd_cache, GFP_KERNEL | __GFP_NOFAIL); @@ -733,6 +711,12 @@ xlog_recover_efi_commit_pass2( efi_formatp = item->ri_buf[0].i_addr; + if (item->ri_buf[0].i_len < xfs_efi_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + efip = xfs_efi_init(mp, efi_formatp->efi_nextents); error = xfs_efi_copy_format(&item->ri_buf[0], &efip->efi_format); if (error) { @@ -769,12 +753,24 @@ xlog_recover_efd_commit_pass2( xfs_lsn_t lsn) { struct xfs_efd_log_format *efd_formatp; + int buflen = item->ri_buf[0].i_len; efd_formatp = item->ri_buf[0].i_addr; - ASSERT((item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_32_t) + - ((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_32_t)))) || - (item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_64_t) + - ((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_64_t))))); + + if (buflen < sizeof(struct xfs_efd_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + efd_formatp, buflen); + return -EFSCORRUPTED; + } + + if (item->ri_buf[0].i_len != xfs_efd_log_format32_sizeof( + efd_formatp->efd_nextents) && + item->ri_buf[0].i_len != xfs_efd_log_format64_sizeof( + efd_formatp->efd_nextents)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + efd_formatp, buflen); + return -EFSCORRUPTED; + } xlog_recover_release_intent(log, XFS_LI_EFI, efd_formatp->efd_efi_id); return 0; diff --git a/fs/xfs/xfs_extfree_item.h b/fs/xfs/xfs_extfree_item.h index 186d0f2137f1..da6a5afa607c 100644 --- a/fs/xfs/xfs_extfree_item.h +++ b/fs/xfs/xfs_extfree_item.h @@ -52,6 +52,14 @@ struct xfs_efi_log_item { xfs_efi_log_format_t efi_format; }; +static inline size_t +xfs_efi_log_item_sizeof( + unsigned int nr) +{ + return offsetof(struct xfs_efi_log_item, efi_format) + + xfs_efi_log_format_sizeof(nr); +} + /* * This is the "extent free done" log item. It is used to log * the fact that some extents earlier mentioned in an efi item @@ -64,6 +72,14 @@ struct xfs_efd_log_item { xfs_efd_log_format_t efd_format; }; +static inline size_t +xfs_efd_log_item_sizeof( + unsigned int nr) +{ + return offsetof(struct xfs_efd_log_item, efd_format) + + xfs_efd_log_format_sizeof(nr); +} + /* * Max number of extents in fast allocation path. */ diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index c6c80265c0b2..e462d39c840e 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1261,7 +1261,7 @@ xfs_file_llseek( } #ifdef CONFIG_FS_DAX -static int +static inline vm_fault_t xfs_dax_fault( struct vm_fault *vmf, enum page_entry_size pe_size, @@ -1274,14 +1274,15 @@ xfs_dax_fault( &xfs_read_iomap_ops); } #else -static int +static inline vm_fault_t xfs_dax_fault( struct vm_fault *vmf, enum page_entry_size pe_size, bool write_fault, pfn_t *pfn) { - return 0; + ASSERT(0); + return VM_FAULT_SIGBUS; } #endif diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index c000b74dd203..aa303be11576 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -2818,7 +2818,7 @@ retry: * Lock all the participating inodes. Depending upon whether * the target_name exists in the target directory, and * whether the target directory is the same as the source - * directory, we can lock from 2 to 4 inodes. + * directory, we can lock from 2 to 5 inodes. */ xfs_lock_inodes(inodes, num_inodes, XFS_ILOCK_EXCL); diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 17e923b9c5fa..322eb2ee6c55 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2552,6 +2552,8 @@ xlog_recover_process_intents( for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0); lip != NULL; lip = xfs_trans_ail_cursor_next(ailp, &cur)) { + const struct xfs_item_ops *ops; + if (!xlog_item_is_intent(lip)) break; @@ -2567,13 +2569,17 @@ xlog_recover_process_intents( * deferred ops, you /must/ attach them to the capture list in * the recover routine or else those subsequent intents will be * replayed in the wrong order! + * + * The recovery function can free the log item, so we must not + * access lip after it returns. */ spin_unlock(&ailp->ail_lock); - error = lip->li_ops->iop_recover(lip, &capture_list); + ops = lip->li_ops; + error = ops->iop_recover(lip, &capture_list); spin_lock(&ailp->ail_lock); if (error) { trace_xlog_intent_recovery_failed(log->l_mp, error, - lip->li_ops->iop_recover); + ops->iop_recover); break; } } diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h index 758702b9495f..9737b5a9f405 100644 --- a/fs/xfs/xfs_ondisk.h +++ b/fs/xfs/xfs_ondisk.h @@ -118,10 +118,10 @@ xfs_check_ondisk_structs(void) /* log structures */ XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format, 88); XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat, 24); - XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32, 28); - XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64, 32); - XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32, 28); - XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64, 16); XFS_CHECK_STRUCT_SIZE(struct xfs_extent_32, 12); XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64, 16); XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode, 176); @@ -134,6 +134,21 @@ xfs_check_ondisk_structs(void) XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header, 16); XFS_CHECK_STRUCT_SIZE(struct xfs_attri_log_format, 40); XFS_CHECK_STRUCT_SIZE(struct xfs_attrd_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_bui_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_bud_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_cui_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_cud_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_rui_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_rud_log_format, 16); + XFS_CHECK_STRUCT_SIZE(struct xfs_map_extent, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_phys_extent, 16); + + XFS_CHECK_OFFSET(struct xfs_bui_log_format, bui_extents, 16); + XFS_CHECK_OFFSET(struct xfs_cui_log_format, cui_extents, 16); + XFS_CHECK_OFFSET(struct xfs_rui_log_format, rui_extents, 16); + XFS_CHECK_OFFSET(struct xfs_efi_log_format, efi_extents, 16); + XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents, 16); + XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents, 16); /* * The v5 superblock format extended several v4 header structures with diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 7e97bf19793d..858e3e9eb4a8 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -523,7 +523,9 @@ xfs_cui_item_recover( type = refc_type; break; default: - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + &cuip->cui_format, + sizeof(cuip->cui_format)); error = -EFSCORRUPTED; goto abort_error; } @@ -536,7 +538,8 @@ xfs_cui_item_recover( &new_fsb, &new_len, &rcur); if (error == -EFSCORRUPTED) XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, - refc, sizeof(*refc)); + &cuip->cui_format, + sizeof(cuip->cui_format)); if (error) goto abort_error; @@ -622,28 +625,18 @@ static const struct xfs_item_ops xfs_cui_item_ops = { .iop_relog = xfs_cui_item_relog, }; -/* - * Copy an CUI format buffer from the given buf, and into the destination - * CUI format structure. The CUI/CUD items were designed not to need any - * special alignment handling. - */ -static int +static inline void xfs_cui_copy_format( - struct xfs_log_iovec *buf, - struct xfs_cui_log_format *dst_cui_fmt) + struct xfs_cui_log_format *dst, + const struct xfs_cui_log_format *src) { - struct xfs_cui_log_format *src_cui_fmt; - uint len; + unsigned int i; - src_cui_fmt = buf->i_addr; - len = xfs_cui_log_format_sizeof(src_cui_fmt->cui_nextents); + memcpy(dst, src, offsetof(struct xfs_cui_log_format, cui_extents)); - if (buf->i_len == len) { - memcpy(dst_cui_fmt, src_cui_fmt, len); - return 0; - } - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); - return -EFSCORRUPTED; + for (i = 0; i < src->cui_nextents; i++) + memcpy(&dst->cui_extents[i], &src->cui_extents[i], + sizeof(struct xfs_phys_extent)); } /* @@ -660,19 +653,28 @@ xlog_recover_cui_commit_pass2( struct xlog_recover_item *item, xfs_lsn_t lsn) { - int error; struct xfs_mount *mp = log->l_mp; struct xfs_cui_log_item *cuip; struct xfs_cui_log_format *cui_formatp; + size_t len; cui_formatp = item->ri_buf[0].i_addr; - cuip = xfs_cui_init(mp, cui_formatp->cui_nextents); - error = xfs_cui_copy_format(&item->ri_buf[0], &cuip->cui_format); - if (error) { - xfs_cui_item_free(cuip); - return error; + if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; } + + len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + cuip = xfs_cui_init(mp, cui_formatp->cui_nextents); + xfs_cui_copy_format(&cuip->cui_format, cui_formatp); atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents); /* * Insert the intent into the AIL directly and drop one reference so @@ -706,7 +708,8 @@ xlog_recover_cud_commit_pass2( cud_formatp = item->ri_buf[0].i_addr; if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); return -EFSCORRUPTED; } diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index fef92e02f3bb..534504ede1a3 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -155,31 +155,6 @@ xfs_rui_init( return ruip; } -/* - * Copy an RUI format buffer from the given buf, and into the destination - * RUI format structure. The RUI/RUD items were designed not to need any - * special alignment handling. - */ -STATIC int -xfs_rui_copy_format( - struct xfs_log_iovec *buf, - struct xfs_rui_log_format *dst_rui_fmt) -{ - struct xfs_rui_log_format *src_rui_fmt; - uint len; - - src_rui_fmt = buf->i_addr; - len = xfs_rui_log_format_sizeof(src_rui_fmt->rui_nextents); - - if (buf->i_len != len) { - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); - return -EFSCORRUPTED; - } - - memcpy(dst_rui_fmt, src_rui_fmt, len); - return 0; -} - static inline struct xfs_rud_log_item *RUD_ITEM(struct xfs_log_item *lip) { return container_of(lip, struct xfs_rud_log_item, rud_item); @@ -582,7 +557,9 @@ xfs_rui_item_recover( type = XFS_RMAP_FREE; break; default: - XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL); + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + &ruip->rui_format, + sizeof(ruip->rui_format)); error = -EFSCORRUPTED; goto abort_error; } @@ -652,6 +629,20 @@ static const struct xfs_item_ops xfs_rui_item_ops = { .iop_relog = xfs_rui_item_relog, }; +static inline void +xfs_rui_copy_format( + struct xfs_rui_log_format *dst, + const struct xfs_rui_log_format *src) +{ + unsigned int i; + + memcpy(dst, src, offsetof(struct xfs_rui_log_format, rui_extents)); + + for (i = 0; i < src->rui_nextents; i++) + memcpy(&dst->rui_extents[i], &src->rui_extents[i], + sizeof(struct xfs_map_extent)); +} + /* * This routine is called to create an in-core extent rmap update * item from the rui format structure which was logged on disk. @@ -666,19 +657,28 @@ xlog_recover_rui_commit_pass2( struct xlog_recover_item *item, xfs_lsn_t lsn) { - int error; struct xfs_mount *mp = log->l_mp; struct xfs_rui_log_item *ruip; struct xfs_rui_log_format *rui_formatp; + size_t len; rui_formatp = item->ri_buf[0].i_addr; - ruip = xfs_rui_init(mp, rui_formatp->rui_nextents); - error = xfs_rui_copy_format(&item->ri_buf[0], &ruip->rui_format); - if (error) { - xfs_rui_item_free(ruip); - return error; + if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } + + len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents); + if (item->ri_buf[0].i_len != len) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, + item->ri_buf[0].i_addr, item->ri_buf[0].i_len); + return -EFSCORRUPTED; } + + ruip = xfs_rui_init(mp, rui_formatp->rui_nextents); + xfs_rui_copy_format(&ruip->rui_format, rui_formatp); atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents); /* * Insert the intent into the AIL directly and drop one reference so @@ -711,7 +711,11 @@ xlog_recover_rud_commit_pass2( struct xfs_rud_log_format *rud_formatp; rud_formatp = item->ri_buf[0].i_addr; - ASSERT(item->ri_buf[0].i_len == sizeof(struct xfs_rud_log_format)); + if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) { + XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp, + rud_formatp, item->ri_buf[0].i_len); + return -EFSCORRUPTED; + } xlog_recover_release_intent(log, XFS_LI_RUI, rud_formatp->rud_rui_id); return 0; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index f029c6702dda..ee4b429a2f2c 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -2028,18 +2028,14 @@ xfs_init_caches(void) goto out_destroy_trans_cache; xfs_efd_cache = kmem_cache_create("xfs_efd_item", - (sizeof(struct xfs_efd_log_item) + - (XFS_EFD_MAX_FAST_EXTENTS - 1) * - sizeof(struct xfs_extent)), - 0, 0, NULL); + xfs_efd_log_item_sizeof(XFS_EFD_MAX_FAST_EXTENTS), + 0, 0, NULL); if (!xfs_efd_cache) goto out_destroy_buf_item_cache; xfs_efi_cache = kmem_cache_create("xfs_efi_item", - (sizeof(struct xfs_efi_log_item) + - (XFS_EFI_MAX_FAST_EXTENTS - 1) * - sizeof(struct xfs_extent)), - 0, 0, NULL); + xfs_efi_log_item_sizeof(XFS_EFI_MAX_FAST_EXTENTS), + 0, 0, NULL); if (!xfs_efi_cache) goto out_destroy_efd_cache; diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h index 43585850f154..513095e353a5 100644 --- a/fs/xfs/xfs_sysfs.h +++ b/fs/xfs/xfs_sysfs.h @@ -33,10 +33,15 @@ xfs_sysfs_init( const char *name) { struct kobject *parent; + int err; parent = parent_kobj ? &parent_kobj->kobject : NULL; init_completion(&kobj->complete); - return kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name); + err = kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name); + if (err) + kobject_put(&kobj->kobject); + + return err; } static inline void diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h index cb7c81ba7fa3..372d871bccc5 100644 --- a/fs/xfs/xfs_trace.h +++ b/fs/xfs/xfs_trace.h @@ -799,6 +799,9 @@ TRACE_DEFINE_ENUM(PE_SIZE_PTE); TRACE_DEFINE_ENUM(PE_SIZE_PMD); TRACE_DEFINE_ENUM(PE_SIZE_PUD); +TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED); +TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW); + TRACE_EVENT(xfs_filemap_fault, TP_PROTO(struct xfs_inode *ip, enum page_entry_size pe_size, bool write_fault), @@ -2925,6 +2928,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) @@ -2932,13 +2936,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount) @@ -2958,6 +2964,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) @@ -2966,14 +2973,16 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; __entry->agbno = agbno; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount, @@ -2994,9 +3003,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) __field(xfs_extlen_t, i1_blockcount) __field(xfs_nlink_t, i1_refcount) + __field(enum xfs_refc_domain, i2_domain) __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) @@ -3004,20 +3015,24 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; __entry->i1_blockcount = i1->rc_blockcount; __entry->i1_refcount = i1->rc_refcount; + __entry->i2_domain = i2->rc_domain; __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- " - "agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s agbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, __entry->i1_blockcount, __entry->i1_refcount, + __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount) @@ -3038,9 +3053,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) __field(xfs_extlen_t, i1_blockcount) __field(xfs_nlink_t, i1_refcount) + __field(enum xfs_refc_domain, i2_domain) __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) @@ -3049,21 +3066,25 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; __entry->i1_blockcount = i1->rc_blockcount; __entry->i1_refcount = i1->rc_refcount; + __entry->i2_domain = i2->rc_domain; __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; __entry->agbno = agbno; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- " - "agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, __entry->i1_blockcount, __entry->i1_refcount, + __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount, @@ -3086,12 +3107,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) + __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) __field(xfs_extlen_t, i1_blockcount) __field(xfs_nlink_t, i1_refcount) + __field(enum xfs_refc_domain, i2_domain) __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) + __field(enum xfs_refc_domain, i3_domain) __field(xfs_agblock_t, i3_startblock) __field(xfs_extlen_t, i3_blockcount) __field(xfs_nlink_t, i3_refcount) @@ -3099,27 +3123,33 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = agno; + __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; __entry->i1_blockcount = i1->rc_blockcount; __entry->i1_refcount = i1->rc_refcount; + __entry->i2_domain = i2->rc_domain; __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; + __entry->i3_domain = i3->rc_domain; __entry->i3_startblock = i3->rc_startblock; __entry->i3_blockcount = i3->rc_blockcount; __entry->i3_refcount = i3->rc_refcount; ), - TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- " - "agbno 0x%x fsbcount 0x%x refcount %u -- " - "agbno 0x%x fsbcount 0x%x refcount %u", + TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s agbno 0x%x fsbcount 0x%x refcount %u -- " + "dom %s agbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, + __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, __entry->i1_blockcount, __entry->i1_refcount, + __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount, + __print_symbolic(__entry->i3_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i3_startblock, __entry->i3_blockcount, __entry->i3_refcount) diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c index 16fbf2a1144c..f51df7d94ef7 100644 --- a/fs/xfs/xfs_trans_ail.c +++ b/fs/xfs/xfs_trans_ail.c @@ -730,11 +730,10 @@ void xfs_ail_push_all_sync( struct xfs_ail *ailp) { - struct xfs_log_item *lip; DEFINE_WAIT(wait); spin_lock(&ailp->ail_lock); - while ((lip = xfs_ail_max(ailp)) != NULL) { + while (xfs_ail_max(ailp) != NULL) { prepare_to_wait(&ailp->ail_empty, &wait, TASK_UNINTERRUPTIBLE); wake_up_process(ailp->ail_task); spin_unlock(&ailp->ail_lock); diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index aeb257ad3d1a..8392caea398f 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -15,7 +15,7 @@ #endif #ifndef compat_arg_u64 -#ifdef CONFIG_CPU_BIG_ENDIAN +#ifndef CONFIG_CPU_BIG_ENDIAN #define compat_arg_u64(name) u32 name##_lo, u32 name##_hi #define compat_arg_u64_dual(name) u32, name##_lo, u32, name##_hi #else diff --git a/include/linux/efi.h b/include/linux/efi.h index 80f3c1c7827d..929d559ad41d 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1222,7 +1222,7 @@ efi_status_t efi_random_get_seed(void); arch_efi_call_virt_teardown(); \ }) -#define EFI_RANDOM_SEED_SIZE 64U +#define EFI_RANDOM_SEED_SIZE 32U // BLAKE2S_HASH_SIZE struct linux_efi_random_seed { u32 size; diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index 18a31b125f9d..1067a8450826 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -454,13 +454,18 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size, #define __fortify_memcpy_chk(p, q, size, p_size, q_size, \ p_size_field, q_size_field, op) ({ \ - size_t __fortify_size = (size_t)(size); \ - WARN_ONCE(fortify_memcpy_chk(__fortify_size, p_size, q_size, \ - p_size_field, q_size_field, #op), \ + const size_t __fortify_size = (size_t)(size); \ + const size_t __p_size = (p_size); \ + const size_t __q_size = (q_size); \ + const size_t __p_size_field = (p_size_field); \ + const size_t __q_size_field = (q_size_field); \ + WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \ + __q_size, __p_size_field, \ + __q_size_field, #op), \ #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \ __fortify_size, \ "field \"" #p "\" at " __FILE__ ":" __stringify(__LINE__), \ - p_size_field); \ + __p_size_field); \ __underlying_##op(p, q, __fortify_size); \ }) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 00c3448ba7f8..18592bdf4c1b 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1240,8 +1240,18 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); /** - * kvm_gfn_to_pfn_cache_init - prepare a cached kernel mapping and HPA for a - * given guest physical address. + * kvm_gpc_init - initialize gfn_to_pfn_cache. + * + * @gpc: struct gfn_to_pfn_cache object. + * + * This sets up a gfn_to_pfn_cache by initializing locks. Note, the cache must + * be zero-allocated (or zeroed by the caller before init). + */ +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc); + +/** + * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest + * physical address. * * @kvm: pointer to kvm instance. * @gpc: struct gfn_to_pfn_cache object. @@ -1265,9 +1275,9 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before * accessing the target page. */ -int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, - gpa_t gpa, unsigned long len); +int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, + gpa_t gpa, unsigned long len); /** * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache. @@ -1324,7 +1334,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); /** - * kvm_gfn_to_pfn_cache_destroy - destroy and unlink a gfn_to_pfn_cache. + * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache. * * @kvm: pointer to kvm instance. * @gpc: struct gfn_to_pfn_cache object. @@ -1332,7 +1342,7 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); * This removes a cache from the @kvm's list to be processed on MMU notifier * invocation. */ -void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); +void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc); void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); diff --git a/include/net/netlink.h b/include/net/netlink.h index 4418b1981e31..6bfa972f2fbf 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -181,6 +181,8 @@ enum { NLA_S64, NLA_BITFIELD32, NLA_REJECT, + NLA_BE16, + NLA_BE32, __NLA_TYPE_MAX, }; @@ -231,6 +233,7 @@ enum nla_policy_validation { * NLA_U32, NLA_U64, * NLA_S8, NLA_S16, * NLA_S32, NLA_S64, + * NLA_BE16, NLA_BE32, * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" @@ -261,6 +264,8 @@ enum nla_policy_validation { * NLA_U16, * NLA_U32, * NLA_U64, + * NLA_BE16, + * NLA_BE32, * NLA_S8, * NLA_S16, * NLA_S32, @@ -317,19 +322,10 @@ struct nla_policy { u8 validation_type; u16 len; union { - const u32 bitfield32_valid; - const u32 mask; - const char *reject_message; - const struct nla_policy *nested_policy; - struct netlink_range_validation *range; - struct netlink_range_validation_signed *range_signed; - struct { - s16 min, max; - u8 network_byte_order:1; - }; - int (*validate)(const struct nlattr *attr, - struct netlink_ext_ack *extack); - /* This entry is special, and used for the attribute at index 0 + /** + * @strict_start_type: first attribute to validate strictly + * + * This entry is special, and used for the attribute at index 0 * only, and specifies special data about the policy, namely it * specifies the "boundary type" where strict length validation * starts for any attribute types >= this value, also, strict @@ -348,6 +344,19 @@ struct nla_policy { * was added to enforce strict validation from thereon. */ u16 strict_start_type; + + /* private: use NLA_POLICY_*() to set */ + const u32 bitfield32_valid; + const u32 mask; + const char *reject_message; + const struct nla_policy *nested_policy; + struct netlink_range_validation *range; + struct netlink_range_validation_signed *range_signed; + struct { + s16 min, max; + }; + int (*validate)(const struct nlattr *attr, + struct netlink_ext_ack *extack); }; }; @@ -369,6 +378,8 @@ struct nla_policy { (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || tp == NLA_U64) #define __NLA_IS_SINT_TYPE(tp) \ (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64) +#define __NLA_IS_BEINT_TYPE(tp) \ + (tp == NLA_BE16 || tp == NLA_BE32) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_TYPE(tp) \ @@ -382,6 +393,7 @@ struct nla_policy { #define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \ (__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \ __NLA_IS_SINT_TYPE(tp) || \ + __NLA_IS_BEINT_TYPE(tp) || \ tp == NLA_MSECS || \ tp == NLA_BINARY) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ @@ -389,6 +401,8 @@ struct nla_policy { tp != NLA_REJECT && \ tp != NLA_NESTED && \ tp != NLA_NESTED_ARRAY) + tp) +#define NLA_ENSURE_BEINT_TYPE(tp) \ + (__NLA_ENSURE(__NLA_IS_BEINT_TYPE(tp)) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ @@ -419,14 +433,6 @@ struct nla_policy { .type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ - .network_byte_order = 0, \ -} - -#define NLA_POLICY_MAX_BE(tp, _max) { \ - .type = NLA_ENSURE_UINT_TYPE(tp), \ - .validation_type = NLA_VALIDATE_MAX, \ - .max = _max, \ - .network_byte_order = 1, \ } #define NLA_POLICY_MASK(tp, _mask) { \ diff --git a/include/net/sock.h b/include/net/sock.h index 22f8bab583dd..5db02546941c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1889,6 +1889,13 @@ void sock_kfree_s(struct sock *sk, void *mem, int size); void sock_kzfree_s(struct sock *sk, void *mem, int size); void sk_send_sigurg(struct sock *sk); +static inline void sock_replace_proto(struct sock *sk, struct proto *proto) +{ + if (sk->sk_socket) + clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + WRITE_ONCE(sk->sk_prot, proto); +} + struct sockcm_cookie { u64 transmit_time; u32 mark; diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h index 6f93c915cc88..9f231d40a146 100644 --- a/include/uapi/drm/panfrost_drm.h +++ b/include/uapi/drm/panfrost_drm.h @@ -254,7 +254,7 @@ struct panfrost_dump_object_header { __u64 nbos; } reghdr; - struct pan_bomap_hdr { + struct { __u32 valid; __u64 iova; __u32 data[2]; diff --git a/kernel/events/hw_breakpoint_test.c b/kernel/events/hw_breakpoint_test.c index 5ced822df788..c57610f52bb4 100644 --- a/kernel/events/hw_breakpoint_test.c +++ b/kernel/events/hw_breakpoint_test.c @@ -295,11 +295,11 @@ static int test_init(struct kunit *test) { /* Most test cases want 2 distinct CPUs. */ if (num_online_cpus() < 2) - return -EINVAL; + kunit_skip(test, "not enough cpus"); /* Want the system to not use breakpoints elsewhere. */ if (hw_breakpoint_is_used()) - return -EBUSY; + kunit_skip(test, "hw breakpoint already in use"); return 0; } diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 3220b0a2fb4a..cd9f5a66a690 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2429,8 +2429,11 @@ int enable_kprobe(struct kprobe *kp) if (!kprobes_all_disarmed && kprobe_disabled(p)) { p->flags &= ~KPROBE_FLAG_DISABLED; ret = arm_kprobe(p); - if (ret) + if (ret) { p->flags |= KPROBE_FLAG_DISABLED; + if (p != kp) + kp->flags |= KPROBE_FLAG_DISABLED; + } } out: mutex_unlock(&kprobe_mutex); diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index aac63ca9c3d1..e8143e368074 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -141,6 +141,8 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) return -E2BIG; fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler); + if (!fp->rethook) + return -ENOMEM; for (i = 0; i < size; i++) { struct fprobe_rethook_node *node; @@ -301,7 +303,8 @@ int unregister_fprobe(struct fprobe *fp) { int ret; - if (!fp || fp->ops.func != fprobe_handler) + if (!fp || (fp->ops.saved_func != fprobe_handler && + fp->ops.saved_func != fprobe_kprobe_handler)) return -EINVAL; /* diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index fbf2543111c0..7dc023641bf1 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3028,18 +3028,8 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) command |= FTRACE_UPDATE_TRACE_FUNC; } - if (!command || !ftrace_enabled) { - /* - * If these are dynamic or per_cpu ops, they still - * need their data freed. Since, function tracing is - * not currently active, we can just free them - * without synchronizing all CPUs. - */ - if (ops->flags & FTRACE_OPS_FL_DYNAMIC) - goto free_ops; - - return 0; - } + if (!command || !ftrace_enabled) + goto out; /* * If the ops uses a trampoline, then it needs to be @@ -3076,6 +3066,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) removed_ops = NULL; ops->flags &= ~FTRACE_OPS_FL_REMOVING; +out: /* * Dynamic ops may be freed, we must make sure that all * callers are done before leaving this function. @@ -3103,7 +3094,6 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command) if (IS_ENABLED(CONFIG_PREEMPTION)) synchronize_rcu_tasks(); - free_ops: ftrace_trampoline_free(ops); } diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c index 80e04a1e1977..d81f7c51025c 100644 --- a/kernel/trace/kprobe_event_gen_test.c +++ b/kernel/trace/kprobe_event_gen_test.c @@ -100,20 +100,20 @@ static int __init test_gen_kprobe_cmd(void) KPROBE_GEN_TEST_FUNC, KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1); if (ret) - goto free; + goto out; /* Use kprobe_event_add_fields to add the rest of the fields */ ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3); if (ret) - goto free; + goto out; /* * This actually creates the event. */ ret = kprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out; /* * Now get the gen_kprobe_test event file. We need to prevent @@ -136,13 +136,11 @@ static int __init test_gen_kprobe_cmd(void) goto delete; } out: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kprobe_test"); - free: - kfree(buf); - goto out; } @@ -170,14 +168,14 @@ static int __init test_gen_kretprobe_cmd(void) KPROBE_GEN_TEST_FUNC, "$retval"); if (ret) - goto free; + goto out; /* * This actually creates the event. */ ret = kretprobe_event_gen_cmd_end(&cmd); if (ret) - goto free; + goto out; /* * Now get the gen_kretprobe_test event file. We need to @@ -201,13 +199,11 @@ static int __init test_gen_kretprobe_cmd(void) goto delete; } out: + kfree(buf); return ret; delete: /* We got an error after creating the event, delete it */ ret = kprobe_event_delete("gen_kretprobe_test"); - free: - kfree(buf); - goto out; } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 199759c73519..9712083832f4 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -937,6 +937,9 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) struct ring_buffer_per_cpu *cpu_buffer; struct rb_irq_work *rbwork; + if (!buffer) + return; + if (cpu == RING_BUFFER_ALL_CPUS) { /* Wake up individual ones too. One level recursion */ @@ -945,7 +948,15 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) rbwork = &buffer->irq_work; } else { + if (WARN_ON_ONCE(!buffer->buffers)) + return; + if (WARN_ON_ONCE(cpu >= nr_cpu_ids)) + return; + cpu_buffer = buffer->buffers[cpu]; + /* The CPU buffer may not have been initialized yet */ + if (!cpu_buffer) + return; rbwork = &cpu_buffer->irq_work; } diff --git a/lib/nlattr.c b/lib/nlattr.c index 40f22b177d69..b67a53e29b8f 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -124,10 +124,12 @@ void nla_get_range_unsigned(const struct nla_policy *pt, range->max = U8_MAX; break; case NLA_U16: + case NLA_BE16: case NLA_BINARY: range->max = U16_MAX; break; case NLA_U32: + case NLA_BE32: range->max = U32_MAX; break; case NLA_U64: @@ -159,31 +161,6 @@ void nla_get_range_unsigned(const struct nla_policy *pt, } } -static u64 nla_get_attr_bo(const struct nla_policy *pt, - const struct nlattr *nla) -{ - switch (pt->type) { - case NLA_U16: - if (pt->network_byte_order) - return ntohs(nla_get_be16(nla)); - - return nla_get_u16(nla); - case NLA_U32: - if (pt->network_byte_order) - return ntohl(nla_get_be32(nla)); - - return nla_get_u32(nla); - case NLA_U64: - if (pt->network_byte_order) - return be64_to_cpu(nla_get_be64(nla)); - - return nla_get_u64(nla); - } - - WARN_ON_ONCE(1); - return 0; -} - static int nla_validate_range_unsigned(const struct nla_policy *pt, const struct nlattr *nla, struct netlink_ext_ack *extack, @@ -197,9 +174,13 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt, value = nla_get_u8(nla); break; case NLA_U16: + value = nla_get_u16(nla); + break; case NLA_U32: + value = nla_get_u32(nla); + break; case NLA_U64: - value = nla_get_attr_bo(pt, nla); + value = nla_get_u64(nla); break; case NLA_MSECS: value = nla_get_u64(nla); @@ -207,6 +188,12 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt, case NLA_BINARY: value = nla_len(nla); break; + case NLA_BE16: + value = ntohs(nla_get_be16(nla)); + break; + case NLA_BE32: + value = ntohl(nla_get_be32(nla)); + break; default: return -EINVAL; } @@ -334,6 +321,8 @@ static int nla_validate_int_range(const struct nla_policy *pt, case NLA_U64: case NLA_MSECS: case NLA_BINARY: + case NLA_BE16: + case NLA_BE32: return nla_validate_range_unsigned(pt, nla, extack, validate); case NLA_S8: case NLA_S16: diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 7a59c4487050..a6c12863a253 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -1067,10 +1067,21 @@ int hci_conn_del(struct hci_conn *conn) hdev->acl_cnt += conn->sent; } else { struct hci_conn *acl = conn->link; + if (acl) { acl->link = NULL; hci_conn_drop(acl); } + + /* Unacked ISO frames */ + if (conn->type == ISO_LINK) { + if (hdev->iso_pkts) + hdev->iso_cnt += conn->sent; + else if (hdev->le_pkts) + hdev->le_cnt += conn->sent; + else + hdev->acl_cnt += conn->sent; + } } if (conn->amp_mgr) @@ -1761,6 +1772,7 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, if (!cis) return ERR_PTR(-ENOMEM); cis->cleanup = cis_cleanup; + cis->dst_type = dst_type; } if (cis->state == BT_CONNECTED) @@ -2140,12 +2152,6 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, struct hci_conn *le; struct hci_conn *cis; - /* Convert from ISO socket address type to HCI address type */ - if (dst_type == BDADDR_LE_PUBLIC) - dst_type = ADDR_LE_DEV_PUBLIC; - else - dst_type = ADDR_LE_DEV_RANDOM; - if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) le = hci_connect_le(hdev, dst, dst_type, false, BT_SECURITY_LOW, diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 613039ba5dbf..f825857db6d0 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -235,6 +235,14 @@ static int iso_chan_add(struct iso_conn *conn, struct sock *sk, return err; } +static inline u8 le_addr_type(u8 bdaddr_type) +{ + if (bdaddr_type == BDADDR_LE_PUBLIC) + return ADDR_LE_DEV_PUBLIC; + else + return ADDR_LE_DEV_RANDOM; +} + static int iso_connect_bis(struct sock *sk) { struct iso_conn *conn; @@ -328,14 +336,16 @@ static int iso_connect_cis(struct sock *sk) /* Just bind if DEFER_SETUP has been set */ if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { hcon = hci_bind_cis(hdev, &iso_pi(sk)->dst, - iso_pi(sk)->dst_type, &iso_pi(sk)->qos); + le_addr_type(iso_pi(sk)->dst_type), + &iso_pi(sk)->qos); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto done; } } else { hcon = hci_connect_cis(hdev, &iso_pi(sk)->dst, - iso_pi(sk)->dst_type, &iso_pi(sk)->qos); + le_addr_type(iso_pi(sk)->dst_type), + &iso_pi(sk)->qos); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto done; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 1f34b82ca0ec..9c24947aa41e 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -1990,7 +1990,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, if (link_type == LE_LINK && c->src_type == BDADDR_BREDR) continue; - if (c->psm == psm) { + if (c->chan_type != L2CAP_CHAN_FIXED && c->psm == psm) { int src_match, dst_match; int src_any, dst_any; @@ -3764,7 +3764,8 @@ done: l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc, endptr - ptr); - if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) { + if (remote_efs && + test_bit(FLAG_EFS_ENABLE, &chan->flags)) { chan->remote_id = efs.id; chan->remote_stype = efs.stype; chan->remote_msdu = le16_to_cpu(efs.msdu); @@ -5813,6 +5814,19 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn, BT_DBG("psm 0x%2.2x scid 0x%4.4x mtu %u mps %u", __le16_to_cpu(psm), scid, mtu, mps); + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A + * page 1059: + * + * Valid range: 0x0001-0x00ff + * + * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges + */ + if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) { + result = L2CAP_CR_LE_BAD_PSM; + chan = NULL; + goto response; + } + /* Check if we have socket listening on psm */ pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src, &conn->hcon->dst, LE_LINK); @@ -6001,6 +6015,18 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn, psm = req->psm; + /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A + * page 1059: + * + * Valid range: 0x0001-0x00ff + * + * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges + */ + if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) { + result = L2CAP_CR_LE_BAD_PSM; + goto response; + } + BT_DBG("psm 0x%2.2x mtu %u mps %u", __le16_to_cpu(psm), mtu, mps); memset(&pdu, 0, sizeof(pdu)); @@ -6885,6 +6911,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb, u8 event) { + struct l2cap_ctrl local_control; int err = 0; bool skb_in_use = false; @@ -6909,15 +6936,32 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan, chan->buffer_seq = chan->expected_tx_seq; skb_in_use = true; + /* l2cap_reassemble_sdu may free skb, hence invalidate + * control, so make a copy in advance to use it after + * l2cap_reassemble_sdu returns and to avoid the race + * condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but + * it was freed by skb_free_datagram. + */ + local_control = *control; err = l2cap_reassemble_sdu(chan, skb, control); if (err) break; - if (control->final) { + if (local_control.final) { if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) { - control->final = 0; - l2cap_retransmit_all(chan, control); + local_control.final = 0; + l2cap_retransmit_all(chan, &local_control); l2cap_ertm_send(chan); } } @@ -7297,11 +7341,27 @@ static int l2cap_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, struct sk_buff *skb) { + /* l2cap_reassemble_sdu may free skb, hence invalidate control, so store + * the txseq field in advance to use it after l2cap_reassemble_sdu + * returns and to avoid the race condition, for example: + * + * The current thread calls: + * l2cap_reassemble_sdu + * chan->ops->recv == l2cap_sock_recv_cb + * __sock_queue_rcv_skb + * Another thread calls: + * bt_sock_recvmsg + * skb_recv_datagram + * skb_free_datagram + * Then the current thread tries to access control, but it was freed by + * skb_free_datagram. + */ + u16 txseq = control->txseq; + BT_DBG("chan %p, control %p, skb %p, state %d", chan, control, skb, chan->rx_state); - if (l2cap_classify_txseq(chan, control->txseq) == - L2CAP_TXSEQ_EXPECTED) { + if (l2cap_classify_txseq(chan, txseq) == L2CAP_TXSEQ_EXPECTED) { l2cap_pass_to_tx(chan, control); BT_DBG("buffer_seq %u->%u", chan->buffer_seq, @@ -7324,8 +7384,8 @@ static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control, } } - chan->last_acked_seq = control->txseq; - chan->expected_tx_seq = __next_seq(chan, control->txseq); + chan->last_acked_seq = txseq; + chan->expected_tx_seq = __next_seq(chan, txseq); return 0; } @@ -7581,6 +7641,7 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid, return; } + l2cap_chan_hold(chan); l2cap_chan_lock(chan); } else { BT_DBG("unknown cid 0x%4.4x", cid); @@ -8426,9 +8487,8 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) * expected length. */ if (skb->len < L2CAP_LEN_SIZE) { - if (l2cap_recv_frag(conn, skb, conn->mtu) < 0) - goto drop; - return; + l2cap_recv_frag(conn, skb, conn->mtu); + break; } len = get_unaligned_le16(skb->data) + L2CAP_HDR_SIZE; @@ -8472,7 +8532,7 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags) /* Header still could not be read just continue */ if (conn->rx_skb->len < L2CAP_LEN_SIZE) - return; + break; } if (skb->len > conn->rx_len) { diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5aeb3646e74c..d087fd4c784a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1332,7 +1332,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_FDB_FLUSH]) { struct net_bridge_fdb_flush_desc desc = { - .flags_mask = BR_FDB_STATIC + .flags_mask = BIT(BR_FDB_STATIC) }; br_fdb_flush(br, &desc); diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 612e367fff20..ea733542244c 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -345,7 +345,7 @@ static int set_flush(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct net_bridge_fdb_flush_desc desc = { - .flags_mask = BR_FDB_STATIC + .flags_mask = BIT(BR_FDB_STATIC) }; br_fdb_flush(br, &desc); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 3c4786b99907..a77a85e357e0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -409,7 +409,7 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, write_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, skip_perm); pneigh_ifdown_and_unlock(tbl, dev); - pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev)); + pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL); if (skb_queue_empty_lockless(&tbl->proxy_queue)) del_timer_sync(&tbl->proxy_timer); return 0; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index af0e2c0394ac..e504a18fc125 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1409,9 +1409,9 @@ static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, const char *user_protocol) { + const struct dsa_device_ops *tag_ops = NULL; struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst = ds->dst; - const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol default_proto; /* Find out which protocol the switch would prefer. */ @@ -1434,10 +1434,17 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, } tag_ops = dsa_find_tagger_by_name(user_protocol); - } else { - tag_ops = dsa_tag_driver_get(default_proto); + if (IS_ERR(tag_ops)) { + dev_warn(ds->dev, + "Failed to find a tagging driver for protocol %s, using default\n", + user_protocol); + tag_ops = NULL; + } } + if (!tag_ops) + tag_ops = dsa_tag_driver_get(default_proto); + if (IS_ERR(tag_ops)) { if (PTR_ERR(tag_ops) == -ENOPROTOOPT) return -EPROBE_DEFER; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 3dd02396517d..4728087c42a5 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -754,6 +754,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags, (TCPF_ESTABLISHED | TCPF_SYN_RECV | TCPF_CLOSE_WAIT | TCPF_CLOSE))); + if (test_bit(SOCK_SUPPORT_ZC, &sock->flags)) + set_bit(SOCK_SUPPORT_ZC, &newsock->flags); sock_graft(sk2, newsock); newsock->state = SS_CONNECTED; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index a1626afe87a1..c501c329b1db 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -607,7 +607,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) } else { sk->sk_write_space = psock->saved_write_space; /* Pairs with lockless read in sk_clone_lock() */ - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); } return 0; } @@ -620,7 +620,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) } /* Pairs with lockless read in sk_clone_lock() */ - WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]); + sock_replace_proto(sk, &tcp_bpf_prots[family][config]); return 0; } EXPORT_SYMBOL_GPL(tcp_bpf_update_proto); diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 7c27aa629af1..9ae50b1bd844 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -136,6 +136,9 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops) if (icsk->icsk_ulp_ops) goto out_err; + if (sk->sk_socket) + clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + err = ulp_ops->init(sk); if (err) goto out_err; diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c index ff15918b7bdc..e5dc91d0e079 100644 --- a/net/ipv4/udp_bpf.c +++ b/net/ipv4/udp_bpf.c @@ -141,14 +141,14 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) if (restore) { sk->sk_write_space = psock->saved_write_space; - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); return 0; } if (sk->sk_family == AF_INET6) udp_bpf_check_v6_needs_rebuild(psock->sk_proto); - WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]); + sock_replace_proto(sk, &udp_bpf_prots[family]); return 0; } EXPORT_SYMBOL_GPL(udp_bpf_update_proto); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 69252eb462b2..2f355f0ec32a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6555,10 +6555,16 @@ static void __net_exit ip6_route_net_exit(struct net *net) static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS - proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, - sizeof(struct ipv6_route_iter)); - proc_create_net_single("rt6_stats", 0444, net->proc_net, - rt6_stats_seq_show, NULL); + if (!proc_create_net("ipv6_route", 0, net->proc_net, + &ipv6_route_seq_ops, + sizeof(struct ipv6_route_iter))) + return -ENOMEM; + + if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, + rt6_stats_seq_show, NULL)) { + remove_proc_entry("ipv6_route", net->proc_net); + return -ENOMEM; + } #endif return 0; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 129ec5a9b0eb..bc65e5b7195b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -66,6 +66,7 @@ int udpv6_init_sock(struct sock *sk) { skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udpv6_destruct_sock; + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); return 0; } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 6e391308431d..3adc291d9ce1 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -42,31 +42,8 @@ #define AHASH_MAX_SIZE (6 * AHASH_INIT_SIZE) /* Max muber of elements in the array block when tuned */ #define AHASH_MAX_TUNED 64 - #define AHASH_MAX(h) ((h)->bucketsize) -/* Max number of elements can be tuned */ -#ifdef IP_SET_HASH_WITH_MULTI -static u8 -tune_bucketsize(u8 curr, u32 multi) -{ - u32 n; - - if (multi < curr) - return curr; - - n = curr + AHASH_INIT_SIZE; - /* Currently, at listing one hash bucket must fit into a message. - * Therefore we have a hard limit here. - */ - return n > curr && n <= AHASH_MAX_TUNED ? n : curr; -} -#define TUNE_BUCKETSIZE(h, multi) \ - ((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi)) -#else -#define TUNE_BUCKETSIZE(h, multi) -#endif - /* A hash bucket */ struct hbucket { struct rcu_head rcu; /* for call_rcu */ @@ -936,7 +913,12 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto set_full; /* Create a new slot */ if (n->pos >= n->size) { - TUNE_BUCKETSIZE(h, multi); +#ifdef IP_SET_HASH_WITH_MULTI + if (h->bucketsize >= AHASH_MAX_TUNED) + goto set_full; + else if (h->bucketsize < multi) + h->bucketsize += AHASH_INIT_SIZE; +#endif if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index f9b16f2b2219..fdacbc3c15be 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -599,13 +599,19 @@ static const struct seq_operations ip_vs_app_seq_ops = { int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { INIT_LIST_HEAD(&ipvs->app_list); - proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops, - sizeof(struct seq_net_private)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, + &ip_vs_app_seq_ops, + sizeof(struct seq_net_private))) + return -ENOMEM; +#endif return 0; } void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { unregister_ip_vs_app(ipvs, NULL /* all */); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_app", ipvs->net->proc_net); +#endif } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 8c04bb57dd6f..13534e02346c 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1265,8 +1265,8 @@ static inline int todrop_entry(struct ip_vs_conn *cp) * The drop rate array needs tuning for real environments. * Called from timer bh only => no locking */ - static const char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; - static char todrop_counter[9] = {0}; + static const signed char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8}; + static signed char todrop_counter[9] = {0}; int i; /* if the conn entry hasn't lasted for 60 seconds, don't drop it. @@ -1447,20 +1447,36 @@ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs) { atomic_set(&ipvs->conn_count, 0); - proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, - &ip_vs_conn_seq_ops, sizeof(struct ip_vs_iter_state)); - proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, - &ip_vs_conn_sync_seq_ops, - sizeof(struct ip_vs_iter_state)); +#ifdef CONFIG_PROC_FS + if (!proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net, + &ip_vs_conn_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn; + + if (!proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net, + &ip_vs_conn_sync_seq_ops, + sizeof(struct ip_vs_iter_state))) + goto err_conn_sync; +#endif + return 0; + +#ifdef CONFIG_PROC_FS +err_conn_sync: + remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); +err_conn: + return -ENOMEM; +#endif } void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) { /* flush all the connection entries first */ ip_vs_conn_flush(ipvs); +#ifdef CONFIG_PROC_FS remove_proc_entry("ip_vs_conn", ipvs->net->proc_net); remove_proc_entry("ip_vs_conn_sync", ipvs->net->proc_net); +#endif } int __init ip_vs_conn_init(void) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 18319a6e6806..e29e4ccb5c5a 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -1152,7 +1152,16 @@ static int __init nf_nat_init(void) WARN_ON(nf_nat_hook != NULL); RCU_INIT_POINTER(nf_nat_hook, &nat_hook); - return register_nf_nat_bpf(); + ret = register_nf_nat_bpf(); + if (ret < 0) { + RCU_INIT_POINTER(nf_nat_hook, NULL); + nf_ct_helper_expectfn_unregister(&follow_master_nat); + synchronize_net(); + unregister_pernet_subsys(&nat_net_ops); + kvfree(nf_nat_bysource); + } + + return ret; } static void __exit nf_nat_cleanup(void) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 58d9cbc9ccdc..76bd4d03dbda 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -8465,9 +8465,6 @@ static void nft_commit_release(struct nft_trans *trans) nf_tables_chain_destroy(&trans->ctx); break; case NFT_MSG_DELRULE: - if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) - nft_flow_rule_destroy(nft_trans_flow_rule(trans)); - nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_DELSET: @@ -8973,6 +8970,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans), NFT_TRANS_COMMIT); + + if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) + nft_flow_rule_destroy(nft_trans_flow_rule(trans)); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -10030,6 +10030,8 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event, nft_net = nft_pernet(net); deleted = 0; mutex_lock(&nft_net->commit_mutex); + if (!list_empty(&nf_tables_destroy_list)) + rcu_barrier(); again: list_for_each_entry(table, &nft_net->tables, list) { if (nft_table_has_owner(table) && diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 088244f9d838..4edd899aeb9b 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -173,10 +173,10 @@ static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = { [NFTA_PAYLOAD_SREG] = { .type = NLA_U32 }, [NFTA_PAYLOAD_DREG] = { .type = NLA_U32 }, [NFTA_PAYLOAD_BASE] = { .type = NLA_U32 }, - [NFTA_PAYLOAD_OFFSET] = NLA_POLICY_MAX_BE(NLA_U32, 255), - [NFTA_PAYLOAD_LEN] = NLA_POLICY_MAX_BE(NLA_U32, 255), + [NFTA_PAYLOAD_OFFSET] = NLA_POLICY_MAX(NLA_BE32, 255), + [NFTA_PAYLOAD_LEN] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_PAYLOAD_CSUM_TYPE] = { .type = NLA_U32 }, - [NFTA_PAYLOAD_CSUM_OFFSET] = NLA_POLICY_MAX_BE(NLA_U32, 255), + [NFTA_PAYLOAD_CSUM_OFFSET] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_PAYLOAD_CSUM_FLAGS] = { .type = NLA_U32 }, }; diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 155263e73512..8b84869eb2ac 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -2544,6 +2544,7 @@ struct genl_family dp_vport_genl_family __ro_after_init = { .parallel_ops = true, .small_ops = dp_vport_genl_ops, .n_small_ops = ARRAY_SIZE(dp_vport_genl_ops), + .resv_start_op = OVS_VPORT_CMD_SET + 1, .mcgrps = &ovs_dp_vport_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index 8b96a56d3a49..0f77ae8ef944 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -236,6 +236,9 @@ void rose_transmit_clear_request(struct rose_neigh *neigh, unsigned int lci, uns unsigned char *dptr; int len; + if (!neigh->dev) + return; + len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 3; if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index a5a401f93c1a..98129324e157 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -72,6 +72,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; + unsigned int len; int ret; q->vars.qavg = red_calc_qavg(&q->parms, @@ -126,9 +127,10 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch, break; } + len = qdisc_pkt_len(skb); ret = qdisc_enqueue(skb, child, to_free); if (likely(ret == NET_XMIT_SUCCESS)) { - qdisc_qstats_backlog_inc(sch, skb); + sch->qstats.backlog += len; sch->q.qlen++; } else if (net_xmit_drop_count(ret)) { q->stats.pdrop++; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 3ccbf3c201cd..e12d4fa5aece 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3380,14 +3380,14 @@ static int __init smc_init(void) rc = register_pernet_subsys(&smc_net_stat_ops); if (rc) - return rc; + goto out_pernet_subsys; smc_ism_init(); smc_clc_init(); rc = smc_nl_init(); if (rc) - goto out_pernet_subsys; + goto out_pernet_subsys_stat; rc = smc_pnet_init(); if (rc) @@ -3480,6 +3480,8 @@ out_pnet: smc_pnet_exit(); out_nl: smc_nl_exit(); +out_pernet_subsys_stat: + unregister_pernet_subsys(&smc_net_stat_ops); out_pernet_subsys: unregister_pernet_subsys(&smc_net_ops); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index a31a27816cc0..7bb247c51e2f 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -1989,7 +1989,7 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred, goto unwrap_failed; mic.len = len; mic.data = kmalloc(len, GFP_KERNEL); - if (!mic.data) + if (ZERO_OR_NULL_PTR(mic.data)) goto unwrap_failed; if (read_bytes_from_xdr_buf(rcv_buf, offset, mic.data, mic.len)) goto unwrap_failed; diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index c65c90ad626a..c1f559892ae8 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -518,13 +518,16 @@ void rpc_sysfs_client_setup(struct rpc_clnt *clnt, struct net *net) { struct rpc_sysfs_client *rpc_client; + struct rpc_sysfs_xprt_switch *xswitch = + (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs; + + if (!xswitch) + return; rpc_client = rpc_sysfs_client_alloc(rpc_sunrpc_client_kobj, net, clnt->cl_clid); if (rpc_client) { char name[] = "switch"; - struct rpc_sysfs_xprt_switch *xswitch = - (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs; int ret; clnt->cl_sysfs = rpc_client; @@ -558,6 +561,8 @@ void rpc_sysfs_xprt_switch_setup(struct rpc_xprt_switch *xprt_switch, rpc_xprt_switch->xprt_switch = xprt_switch; rpc_xprt_switch->xprt = xprt; kobject_uevent(&rpc_xprt_switch->kobject, KOBJ_ADD); + } else { + xprt_switch->xps_sysfs = NULL; } } @@ -569,6 +574,9 @@ void rpc_sysfs_xprt_setup(struct rpc_xprt_switch *xprt_switch, struct rpc_sysfs_xprt_switch *switch_obj = (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs; + if (!switch_obj) + return; + rpc_xprt = rpc_sysfs_xprt_alloc(&switch_obj->kobject, xprt, gfp_flags); if (rpc_xprt) { xprt->xprt_sysfs = rpc_xprt; diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c index 7cf14c6b1725..e9bf15513961 100644 --- a/net/unix/unix_bpf.c +++ b/net/unix/unix_bpf.c @@ -145,12 +145,12 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re if (restore) { sk->sk_write_space = psock->saved_write_space; - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); return 0; } unix_dgram_bpf_check_needs_rebuild(psock->sk_proto); - WRITE_ONCE(sk->sk_prot, &unix_dgram_bpf_prot); + sock_replace_proto(sk, &unix_dgram_bpf_prot); return 0; } @@ -158,12 +158,12 @@ int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool r { if (restore) { sk->sk_write_space = psock->saved_write_space; - WRITE_ONCE(sk->sk_prot, psock->sk_proto); + sock_replace_proto(sk, psock->sk_proto); return 0; } unix_stream_bpf_check_needs_rebuild(psock->sk_proto); - WRITE_ONCE(sk->sk_prot, &unix_stream_bpf_prot); + sock_replace_proto(sk, &unix_stream_bpf_prot); return 0; } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index ee418701cdee..884eca7f6743 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1905,8 +1905,11 @@ static int vsock_connectible_wait_data(struct sock *sk, err = 0; transport = vsk->transport; - while ((data = vsock_connectible_has_data(vsk)) == 0) { + while (1) { prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); + data = vsock_connectible_has_data(vsk); + if (data != 0) + break; if (sk->sk_err != 0 || (sk->sk_shutdown & RCV_SHUTDOWN) || @@ -2092,8 +2095,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, const struct vsock_transport *transport; int err; - DEFINE_WAIT(wait); - sk = sock->sk; vsk = vsock_sk(sk); err = 0; diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost index 8489a3402eb8..e41dee64d429 100644 --- a/scripts/Makefile.modpost +++ b/scripts/Makefile.modpost @@ -122,7 +122,7 @@ quiet_cmd_modpost = MODPOST $@ sed 's/ko$$/o/' $(or $(modorder-if-needed), /dev/null) | $(MODPOST) $(modpost-args) -T - $(vmlinux.o-if-present) targets += $(output-symdump) -$(output-symdump): $(modorder-if-needed) $(vmlinux.o-if-present) $(moudle.symvers-if-present) $(MODPOST) FORCE +$(output-symdump): $(modorder-if-needed) $(vmlinux.o-if-present) $(module.symvers-if-present) $(MODPOST) FORCE $(call if_changed,modpost) __modpost: $(output-symdump) diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c index 62b6313f51c8..109325f31bef 100644 --- a/scripts/kconfig/menu.c +++ b/scripts/kconfig/menu.c @@ -722,8 +722,8 @@ static void get_prompt_str(struct gstr *r, struct property *prop, if (!expr_eq(prop->menu->dep, prop->visible.expr)) get_dep_str(r, prop->visible.expr, " Visible if: "); - menu = prop->menu->parent; - for (i = 0; menu && i < 8; menu = menu->parent) { + menu = prop->menu; + for (i = 0; menu != &rootmenu && i < 8; menu = menu->parent) { bool accessible = menu_is_visible(menu); submenu[i++] = menu; @@ -733,16 +733,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, if (head && location) { jump = xmalloc(sizeof(struct jump_key)); - if (menu_is_visible(prop->menu)) { - /* - * There is not enough room to put the hint at the - * beginning of the "Prompt" line. Put the hint on the - * last "Location" line even when it would belong on - * the former. - */ - jump->target = prop->menu; - } else - jump->target = location; + jump->target = location; if (list_empty(head)) jump->index = 0; @@ -758,13 +749,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop, menu = submenu[i]; if (jump && menu == location) jump->offset = strlen(r->s); - - if (menu == &rootmenu) - /* The real rootmenu prompt is ugly */ - str_printf(r, "%*cMain menu", j, ' '); - else - str_printf(r, "%*c-> %s", j, ' ', menu_get_prompt(menu)); - + str_printf(r, "%*c-> %s", j, ' ', menu_get_prompt(menu)); if (menu->sym) { str_printf(r, " (%s [=%s])", menu->sym->name ? menu->sym->name : "<choice>", diff --git a/security/commoncap.c b/security/commoncap.c index 5fc8986c3c77..bc751fa5adad 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -401,8 +401,10 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns, &tmpbuf, size, GFP_NOFS); dput(dentry); - if (ret < 0 || !tmpbuf) - return ret; + if (ret < 0 || !tmpbuf) { + size = ret; + goto out_free; + } fs_ns = inode->i_sb->s_user_ns; cap = (struct vfs_cap_data *) tmpbuf; diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h index bef35bee9c44..ad97c0d522b8 100644 --- a/tools/include/nolibc/string.h +++ b/tools/include/nolibc/string.h @@ -19,9 +19,9 @@ static __attribute__((unused)) int memcmp(const void *s1, const void *s2, size_t n) { size_t ofs = 0; - char c1 = 0; + int c1 = 0; - while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) { + while (ofs < n && !(c1 = ((unsigned char *)s1)[ofs] - ((unsigned char *)s2)[ofs])) { ofs++; } return c1; @@ -125,14 +125,18 @@ char *strcpy(char *dst, const char *src) } /* this function is only used with arguments that are not constants or when - * it's not known because optimizations are disabled. + * it's not known because optimizations are disabled. Note that gcc 12 + * recognizes an strlen() pattern and replaces it with a jump to strlen(), + * thus itself, hence the asm() statement below that's meant to disable this + * confusing practice. */ static __attribute__((unused)) -size_t nolibc_strlen(const char *str) +size_t strlen(const char *str) { size_t len; - for (len = 0; str[len]; len++); + for (len = 0; str[len]; len++) + asm(""); return len; } @@ -140,13 +144,12 @@ size_t nolibc_strlen(const char *str) * the two branches, then will rely on an external definition of strlen(). */ #if defined(__OPTIMIZE__) +#define nolibc_strlen(x) strlen(x) #define strlen(str) ({ \ __builtin_constant_p((str)) ? \ __builtin_strlen((str)) : \ nolibc_strlen((str)); \ }) -#else -#define strlen(str) nolibc_strlen((str)) #endif static __attribute__((unused)) diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index a072b2d3e726..7edce12fd2ce 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -12,30 +12,62 @@ #include "mock.h" #define NR_CXL_HOST_BRIDGES 2 +#define NR_CXL_SINGLE_HOST 1 #define NR_CXL_ROOT_PORTS 2 #define NR_CXL_SWITCH_PORTS 2 #define NR_CXL_PORT_DECODERS 8 static struct platform_device *cxl_acpi; static struct platform_device *cxl_host_bridge[NR_CXL_HOST_BRIDGES]; -static struct platform_device - *cxl_root_port[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; -static struct platform_device - *cxl_switch_uport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS]; -static struct platform_device - *cxl_switch_dport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * - NR_CXL_SWITCH_PORTS]; -struct platform_device - *cxl_mem[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * NR_CXL_SWITCH_PORTS]; +#define NR_MULTI_ROOT (NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS) +static struct platform_device *cxl_root_port[NR_MULTI_ROOT]; +static struct platform_device *cxl_switch_uport[NR_MULTI_ROOT]; +#define NR_MEM_MULTI \ + (NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * NR_CXL_SWITCH_PORTS) +static struct platform_device *cxl_switch_dport[NR_MEM_MULTI]; + +static struct platform_device *cxl_hb_single[NR_CXL_SINGLE_HOST]; +static struct platform_device *cxl_root_single[NR_CXL_SINGLE_HOST]; +static struct platform_device *cxl_swu_single[NR_CXL_SINGLE_HOST]; +#define NR_MEM_SINGLE (NR_CXL_SINGLE_HOST * NR_CXL_SWITCH_PORTS) +static struct platform_device *cxl_swd_single[NR_MEM_SINGLE]; + +struct platform_device *cxl_mem[NR_MEM_MULTI]; +struct platform_device *cxl_mem_single[NR_MEM_SINGLE]; + + +static inline bool is_multi_bridge(struct device *dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++) + if (&cxl_host_bridge[i]->dev == dev) + return true; + return false; +} + +static inline bool is_single_bridge(struct device *dev) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) + if (&cxl_hb_single[i]->dev == dev) + return true; + return false; +} static struct acpi_device acpi0017_mock; -static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES] = { +static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES + NR_CXL_SINGLE_HOST] = { [0] = { .handle = &host_bridge[0], }, [1] = { .handle = &host_bridge[1], }, + [2] = { + .handle = &host_bridge[2], + }, + }; static bool is_mock_dev(struct device *dev) @@ -45,6 +77,9 @@ static bool is_mock_dev(struct device *dev) for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) if (dev == &cxl_mem[i]->dev) return true; + for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) + if (dev == &cxl_mem_single[i]->dev) + return true; if (dev == &cxl_acpi->dev) return true; return false; @@ -66,7 +101,7 @@ static bool is_mock_adev(struct acpi_device *adev) static struct { struct acpi_table_cedt cedt; - struct acpi_cedt_chbs chbs[NR_CXL_HOST_BRIDGES]; + struct acpi_cedt_chbs chbs[NR_CXL_HOST_BRIDGES + NR_CXL_SINGLE_HOST]; struct { struct acpi_cedt_cfmws cfmws; u32 target[1]; @@ -83,6 +118,10 @@ static struct { struct acpi_cedt_cfmws cfmws; u32 target[2]; } cfmws3; + struct { + struct acpi_cedt_cfmws cfmws; + u32 target[1]; + } cfmws4; } __packed mock_cedt = { .cedt = { .header = { @@ -107,6 +146,14 @@ static struct { .uid = 1, .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, }, + .chbs[2] = { + .header = { + .type = ACPI_CEDT_TYPE_CHBS, + .length = sizeof(mock_cedt.chbs[0]), + }, + .uid = 2, + .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20, + }, .cfmws0 = { .cfmws = { .header = { @@ -167,13 +214,29 @@ static struct { }, .target = { 0, 1, }, }, + .cfmws4 = { + .cfmws = { + .header = { + .type = ACPI_CEDT_TYPE_CFMWS, + .length = sizeof(mock_cedt.cfmws4), + }, + .interleave_ways = 0, + .granularity = 4, + .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 | + ACPI_CEDT_CFMWS_RESTRICT_PMEM, + .qtg_id = 4, + .window_size = SZ_256M * 4UL, + }, + .target = { 2 }, + }, }; -struct acpi_cedt_cfmws *mock_cfmws[4] = { +struct acpi_cedt_cfmws *mock_cfmws[] = { [0] = &mock_cedt.cfmws0.cfmws, [1] = &mock_cedt.cfmws1.cfmws, [2] = &mock_cedt.cfmws2.cfmws, [3] = &mock_cedt.cfmws3.cfmws, + [4] = &mock_cedt.cfmws4.cfmws, }; struct cxl_mock_res { @@ -304,6 +367,9 @@ static bool is_mock_bridge(struct device *dev) for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++) if (dev == &cxl_host_bridge[i]->dev) return true; + for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) + if (dev == &cxl_hb_single[i]->dev) + return true; return false; } @@ -326,6 +392,18 @@ static bool is_mock_port(struct device *dev) if (dev == &cxl_switch_dport[i]->dev) return true; + for (i = 0; i < ARRAY_SIZE(cxl_root_single); i++) + if (dev == &cxl_root_single[i]->dev) + return true; + + for (i = 0; i < ARRAY_SIZE(cxl_swu_single); i++) + if (dev == &cxl_swu_single[i]->dev) + return true; + + for (i = 0; i < ARRAY_SIZE(cxl_swd_single); i++) + if (dev == &cxl_swd_single[i]->dev) + return true; + if (is_cxl_memdev(dev)) return is_mock_dev(dev->parent); @@ -561,11 +639,31 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port) int i, array_size; if (port->depth == 1) { - array_size = ARRAY_SIZE(cxl_root_port); - array = cxl_root_port; + if (is_multi_bridge(port->uport)) { + array_size = ARRAY_SIZE(cxl_root_port); + array = cxl_root_port; + } else if (is_single_bridge(port->uport)) { + array_size = ARRAY_SIZE(cxl_root_single); + array = cxl_root_single; + } else { + dev_dbg(&port->dev, "%s: unknown bridge type\n", + dev_name(port->uport)); + return -ENXIO; + } } else if (port->depth == 2) { - array_size = ARRAY_SIZE(cxl_switch_dport); - array = cxl_switch_dport; + struct cxl_port *parent = to_cxl_port(port->dev.parent); + + if (is_multi_bridge(parent->uport)) { + array_size = ARRAY_SIZE(cxl_switch_dport); + array = cxl_switch_dport; + } else if (is_single_bridge(parent->uport)) { + array_size = ARRAY_SIZE(cxl_swd_single); + array = cxl_swd_single; + } else { + dev_dbg(&port->dev, "%s: unknown bridge type\n", + dev_name(port->uport)); + return -ENXIO; + } } else { dev_WARN_ONCE(&port->dev, 1, "unexpected depth %d\n", port->depth); @@ -576,8 +674,12 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port) struct platform_device *pdev = array[i]; struct cxl_dport *dport; - if (pdev->dev.parent != port->uport) + if (pdev->dev.parent != port->uport) { + dev_dbg(&port->dev, "%s: mismatch parent %s\n", + dev_name(port->uport), + dev_name(pdev->dev.parent)); continue; + } dport = devm_cxl_add_dport(port, &pdev->dev, pdev->id, CXL_RESOURCE_NONE); @@ -627,6 +729,157 @@ static void mock_companion(struct acpi_device *adev, struct device *dev) #define SZ_512G (SZ_64G * 8) #endif +static __init int cxl_single_init(void) +{ + int i, rc; + + for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) { + struct acpi_device *adev = + &host_bridge[NR_CXL_HOST_BRIDGES + i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_host_bridge", + NR_CXL_HOST_BRIDGES + i); + if (!pdev) + goto err_bridge; + + mock_companion(adev, &pdev->dev); + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_bridge; + } + + cxl_hb_single[i] = pdev; + rc = sysfs_create_link(&pdev->dev.kobj, &pdev->dev.kobj, + "physical_node"); + if (rc) + goto err_bridge; + } + + for (i = 0; i < ARRAY_SIZE(cxl_root_single); i++) { + struct platform_device *bridge = + cxl_hb_single[i % ARRAY_SIZE(cxl_hb_single)]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_root_port", + NR_MULTI_ROOT + i); + if (!pdev) + goto err_port; + pdev->dev.parent = &bridge->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_port; + } + cxl_root_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_swu_single); i++) { + struct platform_device *root_port = cxl_root_single[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_switch_uport", + NR_MULTI_ROOT + i); + if (!pdev) + goto err_uport; + pdev->dev.parent = &root_port->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_uport; + } + cxl_swu_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_swd_single); i++) { + struct platform_device *uport = + cxl_swu_single[i % ARRAY_SIZE(cxl_swu_single)]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_switch_dport", + i + NR_MEM_MULTI); + if (!pdev) + goto err_dport; + pdev->dev.parent = &uport->dev; + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_dport; + } + cxl_swd_single[i] = pdev; + } + + for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) { + struct platform_device *dport = cxl_swd_single[i]; + struct platform_device *pdev; + + pdev = platform_device_alloc("cxl_mem", NR_MEM_MULTI + i); + if (!pdev) + goto err_mem; + pdev->dev.parent = &dport->dev; + set_dev_node(&pdev->dev, i % 2); + + rc = platform_device_add(pdev); + if (rc) { + platform_device_put(pdev); + goto err_mem; + } + cxl_mem_single[i] = pdev; + } + + return 0; + +err_mem: + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); +err_dport: + for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swd_single[i]); +err_uport: + for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swu_single[i]); +err_port: + for (i = ARRAY_SIZE(cxl_root_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_root_single[i]); +err_bridge: + for (i = ARRAY_SIZE(cxl_hb_single) - 1; i >= 0; i--) { + struct platform_device *pdev = cxl_hb_single[i]; + + if (!pdev) + continue; + sysfs_remove_link(&pdev->dev.kobj, "physical_node"); + platform_device_unregister(cxl_hb_single[i]); + } + + return rc; +} + +static void cxl_single_exit(void) +{ + int i; + + for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_mem_single[i]); + for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swd_single[i]); + for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_swu_single[i]); + for (i = ARRAY_SIZE(cxl_root_single) - 1; i >= 0; i--) + platform_device_unregister(cxl_root_single[i]); + for (i = ARRAY_SIZE(cxl_hb_single) - 1; i >= 0; i--) { + struct platform_device *pdev = cxl_hb_single[i]; + + if (!pdev) + continue; + sysfs_remove_link(&pdev->dev.kobj, "physical_node"); + platform_device_unregister(cxl_hb_single[i]); + } +} + static __init int cxl_test_init(void) { int rc, i; @@ -695,7 +948,7 @@ static __init int cxl_test_init(void) pdev = platform_device_alloc("cxl_switch_uport", i); if (!pdev) - goto err_port; + goto err_uport; pdev->dev.parent = &root_port->dev; rc = platform_device_add(pdev); @@ -713,7 +966,7 @@ static __init int cxl_test_init(void) pdev = platform_device_alloc("cxl_switch_dport", i); if (!pdev) - goto err_port; + goto err_dport; pdev->dev.parent = &uport->dev; rc = platform_device_add(pdev); @@ -724,7 +977,6 @@ static __init int cxl_test_init(void) cxl_switch_dport[i] = pdev; } - BUILD_BUG_ON(ARRAY_SIZE(cxl_mem) != ARRAY_SIZE(cxl_switch_dport)); for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) { struct platform_device *dport = cxl_switch_dport[i]; struct platform_device *pdev; @@ -743,9 +995,13 @@ static __init int cxl_test_init(void) cxl_mem[i] = pdev; } + rc = cxl_single_init(); + if (rc) + goto err_mem; + cxl_acpi = platform_device_alloc("cxl_acpi", 0); if (!cxl_acpi) - goto err_mem; + goto err_single; mock_companion(&acpi0017_mock, &cxl_acpi->dev); acpi0017_mock.dev.bus = &platform_bus_type; @@ -758,6 +1014,8 @@ static __init int cxl_test_init(void) err_add: platform_device_put(cxl_acpi); +err_single: + cxl_single_exit(); err_mem: for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) platform_device_unregister(cxl_mem[i]); @@ -793,6 +1051,7 @@ static __exit void cxl_test_exit(void) int i; platform_device_unregister(cxl_acpi); + cxl_single_exit(); for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--) platform_device_unregister(cxl_mem[i]); for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--) 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 8a5cb800f50e..2a5727188c8d 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -15,9 +15,13 @@ #include <time.h> #include <sched.h> #include <signal.h> +#include <pthread.h> #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 @@ -44,6 +48,8 @@ #define MIN_STEAL_TIME 50000 +#define SHINFO_RACE_TIMEOUT 2 /* seconds */ + #define __HYPERVISOR_set_timer_op 15 #define __HYPERVISOR_sched_op 29 #define __HYPERVISOR_event_channel_op 32 @@ -126,7 +132,7 @@ struct { struct kvm_irq_routing_entry entries[2]; } irq_routes; -bool guest_saw_irq; +static volatile bool guest_saw_irq; static void evtchn_handler(struct ex_regs *regs) { @@ -148,6 +154,7 @@ static void guest_wait_for_irq(void) static void guest_code(void) { struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR; + int i; __asm__ __volatile__( "sti\n" @@ -325,6 +332,49 @@ static void guest_code(void) guest_wait_for_irq(); GUEST_SYNC(21); + /* Racing host ioctls */ + + guest_wait_for_irq(); + + GUEST_SYNC(22); + /* Racing vmcall against host ioctl */ + + ports[0] = 0; + + p = (struct sched_poll) { + .ports = ports, + .nr_ports = 1, + .timeout = 0 + }; + +wait_for_timer: + /* + * Poll for a timer wake event while the worker thread is mucking with + * the shared info. KVM XEN drops timer IRQs if the shared info is + * invalid when the timer expires. Arbitrarily poll 100 times before + * giving up and asking the VMM to re-arm the timer. 100 polls should + * consume enough time to beat on KVM without taking too long if the + * timer IRQ is dropped due to an invalid event channel. + */ + for (i = 0; i < 100 && !guest_saw_irq; i++) + asm volatile("vmcall" + : "=a" (rax) + : "a" (__HYPERVISOR_sched_op), + "D" (SCHEDOP_poll), + "S" (&p) + : "memory"); + + /* + * Re-send the timer IRQ if it was (likely) dropped due to the timer + * expiring while the event channel was invalid. + */ + if (!guest_saw_irq) { + GUEST_SYNC(23); + goto wait_for_timer; + } + guest_saw_irq = false; + + GUEST_SYNC(24); } static int cmp_timespec(struct timespec *a, struct timespec *b) @@ -352,11 +402,36 @@ static void handle_alrm(int sig) TEST_FAIL("IRQ delivery timed out"); } +static void *juggle_shinfo_state(void *arg) +{ + struct kvm_vm *vm = (struct kvm_vm *)arg; + + struct kvm_xen_hvm_attr cache_init = { + .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, + .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE + }; + + struct kvm_xen_hvm_attr cache_destroy = { + .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, + .u.shared_info.gfn = GPA_INVALID + }; + + for (;;) { + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_init); + __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_destroy); + pthread_testcancel(); + }; + + return NULL; +} + int main(int argc, char *argv[]) { struct timespec min_ts, max_ts, vm_ts; struct kvm_vm *vm; + pthread_t thread; bool verbose; + int ret; verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) || !strncmp(argv[1], "--verbose", 10)); @@ -785,6 +860,71 @@ int main(int argc, char *argv[]) case 21: TEST_ASSERT(!evtchn_irq_expected, "Expected event channel IRQ but it didn't happen"); + alarm(0); + + if (verbose) + printf("Testing shinfo lock corruption (KVM_XEN_HVM_EVTCHN_SEND)\n"); + + ret = pthread_create(&thread, NULL, &juggle_shinfo_state, (void *)vm); + TEST_ASSERT(ret == 0, "pthread_create() failed: %s", strerror(ret)); + + struct kvm_irq_routing_xen_evtchn uxe = { + .port = 1, + .vcpu = vcpu->id, + .priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL + }; + + evtchn_irq_expected = true; + for (time_t t = time(NULL) + SHINFO_RACE_TIMEOUT; time(NULL) < t;) + __vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &uxe); + break; + + case 22: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + + if (verbose) + printf("Testing shinfo lock corruption (SCHEDOP_poll)\n"); + + shinfo->evtchn_pending[0] = 1; + + evtchn_irq_expected = true; + tmr.u.timer.expires_ns = rs->state_entry_time + + SHINFO_RACE_TIMEOUT * 1000000000ULL; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + break; + + case 23: + /* + * Optional and possibly repeated sync point. + * Injecting the timer IRQ may fail if the + * shinfo is invalid when the timer expires. + * If the timer has expired but the IRQ hasn't + * been delivered, rearm the timer and retry. + */ + vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr); + + /* Resume the guest if the timer is still pending. */ + if (tmr.u.timer.expires_ns) + break; + + /* All done if the IRQ was delivered. */ + if (!evtchn_irq_expected) + break; + + tmr.u.timer.expires_ns = rs->state_entry_time + + SHINFO_RACE_TIMEOUT * 1000000000ULL; + vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr); + break; + case 24: + TEST_ASSERT(!evtchn_irq_expected, + "Expected event channel IRQ but it didn't happen"); + + ret = pthread_cancel(thread); + TEST_ASSERT(ret == 0, "pthread_cancel() failed: %s", strerror(ret)); + + ret = pthread_join(thread, 0); + TEST_ASSERT(ret == 0, "pthread_join() failed: %s", strerror(ret)); goto done; case 0x20: diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index 6632bfff486b..348e2dbdb4e0 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -3,7 +3,6 @@ # First run: make -C ../../../.. headers_install CFLAGS += -Wall -O2 $(KHDR_INCLUDES) -LDLIBS += -lcap LOCAL_HDRS += common.h @@ -13,10 +12,12 @@ TEST_GEN_PROGS := $(src_test:.c=) TEST_GEN_PROGS_EXTENDED := true -# Static linking for short targets: +# Short targets: +$(TEST_GEN_PROGS): LDLIBS += -lcap $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static include ../lib.mk -# Static linking for targets with $(OUTPUT)/ prefix: +# Targets with $(OUTPUT)/ prefix: +$(TEST_GEN_PROGS): LDLIBS += -lcap $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index f4a2f28f926b..778b6cdc8aed 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only -CFLAGS += -g -I../../../../usr/include/ -pthread +CFLAGS += -g -I../../../../usr/include/ -pthread -Wall TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \ pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 9a2d64901d59..e2dd4ed84984 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -413,7 +413,7 @@ static void poll_pidfd(const char *test_name, int pidfd) c = epoll_wait(epoll_fd, events, MAX_EVENTS, 5000); if (c != 1 || !(events[0].events & EPOLLIN)) - ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) ", + ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) " "(errno %d)\n", test_name, c, events[0].events, errno); @@ -435,6 +435,8 @@ static int child_poll_exec_test(void *args) */ while (1) sleep(1); + + return 0; } static void test_pidfd_poll_exec(int use_waitpid) diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c index 070c1c876df1..0dcb8365ddc3 100644 --- a/tools/testing/selftests/pidfd/pidfd_wait.c +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -95,20 +95,28 @@ TEST(wait_states) .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, .exit_signal = SIGCHLD, }; + int pfd[2]; pid_t pid; siginfo_t info = { .si_signo = 0, }; + ASSERT_EQ(pipe(pfd), 0); pid = sys_clone3(&args); ASSERT_GE(pid, 0); if (pid == 0) { + char buf[2]; + + close(pfd[1]); kill(getpid(), SIGSTOP); + ASSERT_EQ(read(pfd[0], buf, 1), 1); + close(pfd[0]); kill(getpid(), SIGSTOP); exit(EXIT_SUCCESS); } + close(pfd[0]); ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_STOPPED); @@ -117,6 +125,8 @@ TEST(wait_states) ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0); ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL), 0); + ASSERT_EQ(write(pfd[1], "C", 1), 1); + close(pfd[1]); ASSERT_EQ(info.si_signo, SIGCHLD); ASSERT_EQ(info.si_code, CLD_CONTINUED); ASSERT_EQ(info.si_pid, parent_tid); @@ -138,7 +148,7 @@ TEST(wait_states) TEST(wait_nonblock) { - int pidfd, status = 0; + int pidfd; unsigned int flags = 0; pid_t parent_tid = -1; struct clone_args args = { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 1376a47fedee..25d7872b29c1 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4585,6 +4585,9 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, } case KVM_CAP_DIRTY_LOG_RING: case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: + if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap)) + return -EINVAL; + return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); default: return kvm_vm_ioctl_enable_cap(kvm, cap); @@ -5409,6 +5412,7 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { + int ret; struct kvm_stat_data *stat_data = (struct kvm_stat_data *) inode->i_private; @@ -5420,15 +5424,13 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file, if (!kvm_get_kvm_safe(stat_data->kvm)) return -ENOENT; - if (simple_attr_open(inode, file, get, - kvm_stats_debugfs_mode(stat_data->desc) & 0222 - ? set : NULL, - fmt)) { + ret = simple_attr_open(inode, file, get, + kvm_stats_debugfs_mode(stat_data->desc) & 0222 + ? set : NULL, fmt); + if (ret) kvm_put_kvm(stat_data->kvm); - return -ENOMEM; - } - return 0; + return ret; } static int kvm_debugfs_release(struct inode *inode, struct file *file) diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c index 68ff41d39545..346e47f15572 100644 --- a/virt/kvm/pfncache.c +++ b/virt/kvm/pfncache.c @@ -81,6 +81,9 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, { struct kvm_memslots *slots = kvm_memslots(kvm); + if (!gpc->active) + return false; + if ((gpa & ~PAGE_MASK) + len > PAGE_SIZE) return false; @@ -240,10 +243,11 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, { struct kvm_memslots *slots = kvm_memslots(kvm); unsigned long page_offset = gpa & ~PAGE_MASK; - kvm_pfn_t old_pfn, new_pfn; + bool unmap_old = false; unsigned long old_uhva; + kvm_pfn_t old_pfn; void *old_khva; - int ret = 0; + int ret; /* * If must fit within a single page. The 'len' argument is @@ -261,6 +265,11 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, write_lock_irq(&gpc->lock); + if (!gpc->active) { + ret = -EINVAL; + goto out_unlock; + } + old_pfn = gpc->pfn; old_khva = gpc->khva - offset_in_page(gpc->khva); old_uhva = gpc->uhva; @@ -291,6 +300,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, /* If the HVA→PFN mapping was already valid, don't unmap it. */ old_pfn = KVM_PFN_ERR_FAULT; old_khva = NULL; + ret = 0; } out: @@ -305,14 +315,15 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, gpc->khva = NULL; } - /* Snapshot the new pfn before dropping the lock! */ - new_pfn = gpc->pfn; + /* Detect a pfn change before dropping the lock! */ + unmap_old = (old_pfn != gpc->pfn); +out_unlock: write_unlock_irq(&gpc->lock); mutex_unlock(&gpc->refresh_lock); - if (old_pfn != new_pfn) + if (unmap_old) gpc_unmap_khva(kvm, old_pfn, old_khva); return ret; @@ -346,42 +357,61 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc) } EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_unmap); +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc) +{ + rwlock_init(&gpc->lock); + mutex_init(&gpc->refresh_lock); +} +EXPORT_SYMBOL_GPL(kvm_gpc_init); -int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, - struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, - gpa_t gpa, unsigned long len) +int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc, + struct kvm_vcpu *vcpu, enum pfn_cache_usage usage, + gpa_t gpa, unsigned long len) { WARN_ON_ONCE(!usage || (usage & KVM_GUEST_AND_HOST_USE_PFN) != usage); if (!gpc->active) { - rwlock_init(&gpc->lock); - mutex_init(&gpc->refresh_lock); - gpc->khva = NULL; gpc->pfn = KVM_PFN_ERR_FAULT; gpc->uhva = KVM_HVA_ERR_BAD; gpc->vcpu = vcpu; gpc->usage = usage; gpc->valid = false; - gpc->active = true; spin_lock(&kvm->gpc_lock); list_add(&gpc->list, &kvm->gpc_list); spin_unlock(&kvm->gpc_lock); + + /* + * Activate the cache after adding it to the list, a concurrent + * refresh must not establish a mapping until the cache is + * reachable by mmu_notifier events. + */ + write_lock_irq(&gpc->lock); + gpc->active = true; + write_unlock_irq(&gpc->lock); } return kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpa, len); } -EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_init); +EXPORT_SYMBOL_GPL(kvm_gpc_activate); -void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc) +void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc) { if (gpc->active) { + /* + * Deactivate the cache before removing it from the list, KVM + * must stall mmu_notifier events until all users go away, i.e. + * until gpc->lock is dropped and refresh is guaranteed to fail. + */ + write_lock_irq(&gpc->lock); + gpc->active = false; + write_unlock_irq(&gpc->lock); + spin_lock(&kvm->gpc_lock); list_del(&gpc->list); spin_unlock(&kvm->gpc_lock); kvm_gfn_to_pfn_cache_unmap(kvm, gpc); - gpc->active = false; } } -EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_destroy); +EXPORT_SYMBOL_GPL(kvm_gpc_deactivate); |