diff options
494 files changed, 7424 insertions, 2572 deletions
@@ -589,6 +589,7 @@ Nikolay Aleksandrov <razor@blackwall.org> <nikolay@redhat.com> Nikolay Aleksandrov <razor@blackwall.org> <nikolay@cumulusnetworks.com> Nikolay Aleksandrov <razor@blackwall.org> <nikolay@nvidia.com> Nikolay Aleksandrov <razor@blackwall.org> <nikolay@isovalent.com> +Nobuhiro Iwamatsu <nobuhiro.iwamatsu.x90@mail.toshiba> <nobuhiro1.iwamatsu@toshiba.co.jp> Odelu Kukatla <quic_okukatla@quicinc.com> <okukatla@codeaurora.org> Oleksandr Natalenko <oleksandr@natalenko.name> <oleksandr@redhat.com> Oleksij Rempel <linux@rempel-privat.de> <bug-track@fisher-privat.net> diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index ab8cd337f43a..8aed6d94c4cd 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -586,6 +586,7 @@ What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/srbds /sys/devices/system/cpu/vulnerabilities/tsa /sys/devices/system/cpu/vulnerabilities/tsx_async_abort + /sys/devices/system/cpu/vulnerabilities/vmscape Date: January 2018 Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org> Description: Information about CPU vulnerabilities diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 89ca636081b7..55d747511f83 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -26,3 +26,4 @@ are configurable at compile, boot or run time. rsb old_microcode indirect-target-selection + vmscape diff --git a/Documentation/admin-guide/hw-vuln/vmscape.rst b/Documentation/admin-guide/hw-vuln/vmscape.rst new file mode 100644 index 000000000000..d9b9a2b6c114 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/vmscape.rst @@ -0,0 +1,110 @@ +.. SPDX-License-Identifier: GPL-2.0 + +VMSCAPE +======= + +VMSCAPE is a vulnerability that may allow a guest to influence the branch +prediction in host userspace. It particularly affects hypervisors like QEMU. + +Even if a hypervisor may not have any sensitive data like disk encryption keys, +guest-userspace may be able to attack the guest-kernel using the hypervisor as +a confused deputy. + +Affected processors +------------------- + +The following CPU families are affected by VMSCAPE: + +**Intel processors:** + - Skylake generation (Parts without Enhanced-IBRS) + - Cascade Lake generation - (Parts affected by ITS guest/host separation) + - Alder Lake and newer (Parts affected by BHI) + +Note that, BHI affected parts that use BHB clearing software mitigation e.g. +Icelake are not vulnerable to VMSCAPE. + +**AMD processors:** + - Zen series (families 0x17, 0x19, 0x1a) + +** Hygon processors:** + - Family 0x18 + +Mitigation +---------- + +Conditional IBPB +---------------- + +Kernel tracks when a CPU has run a potentially malicious guest and issues an +IBPB before the first exit to userspace after VM-exit. If userspace did not run +between VM-exit and the next VM-entry, no IBPB is issued. + +Note that the existing userspace mitigation against Spectre-v2 is effective in +protecting the userspace. They are insufficient to protect the userspace VMMs +from a malicious guest. This is because Spectre-v2 mitigations are applied at +context switch time, while the userspace VMM can run after a VM-exit without a +context switch. + +Vulnerability enumeration and mitigation is not applied inside a guest. This is +because nested hypervisors should already be deploying IBPB to isolate +themselves from nested guests. + +SMT considerations +------------------ + +When Simultaneous Multi-Threading (SMT) is enabled, hypervisors can be +vulnerable to cross-thread attacks. For complete protection against VMSCAPE +attacks in SMT environments, STIBP should be enabled. + +The kernel will issue a warning if SMT is enabled without adequate STIBP +protection. Warning is not issued when: + +- SMT is disabled +- STIBP is enabled system-wide +- Intel eIBRS is enabled (which implies STIBP protection) + +System information and options +------------------------------ + +The sysfs file showing VMSCAPE mitigation status is: + + /sys/devices/system/cpu/vulnerabilities/vmscape + +The possible values in this file are: + + * 'Not affected': + + The processor is not vulnerable to VMSCAPE attacks. + + * 'Vulnerable': + + The processor is vulnerable and no mitigation has been applied. + + * 'Mitigation: IBPB before exit to userspace': + + Conditional IBPB mitigation is enabled. The kernel tracks when a CPU has + run a potentially malicious guest and issues an IBPB before the first + exit to userspace after VM-exit. + + * 'Mitigation: IBPB on VMEXIT': + + IBPB is issued on every VM-exit. This occurs when other mitigations like + RETBLEED or SRSO are already issuing IBPB on VM-exit. + +Mitigation control on the kernel command line +---------------------------------------------- + +The mitigation can be controlled via the ``vmscape=`` command line parameter: + + * ``vmscape=off``: + + Disable the VMSCAPE mitigation. + + * ``vmscape=ibpb``: + + Enable conditional IBPB mitigation (default when CONFIG_MITIGATION_VMSCAPE=y). + + * ``vmscape=force``: + + Force vulnerability detection and mitigation even on processors that are + not known to be affected. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 747a55abf494..5a7a83c411e9 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3829,6 +3829,7 @@ srbds=off [X86,INTEL] ssbd=force-off [ARM64] tsx_async_abort=off [X86] + vmscape=off [X86] Exceptions: This does not have any effect on @@ -8041,6 +8042,16 @@ vmpoff= [KNL,S390] Perform z/VM CP command after power off. Format: <command> + vmscape= [X86] Controls mitigation for VMscape attacks. + VMscape attacks can leak information from a userspace + hypervisor to a guest via speculative side-channels. + + off - disable the mitigation + ibpb - use Indirect Branch Prediction Barrier + (IBPB) mitigation (default) + force - force vulnerability detection even on + unaffected processors + vsyscall= [X86-64,EARLY] Controls the behavior of vsyscalls (i.e. calls to fixed addresses of 0xffffffffff600x00 from legacy diff --git a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml index f2f87f0f545b..6493a6968bb4 100644 --- a/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml +++ b/Documentation/devicetree/bindings/dma/qcom,bam-dma.yaml @@ -92,8 +92,12 @@ required: anyOf: - required: - qcom,powered-remotely + - num-channels + - qcom,num-ees - required: - qcom,controlled-remotely + - num-channels + - qcom,num-ees - required: - clocks - clock-names diff --git a/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml b/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml index d9501df42886..c35d31642805 100644 --- a/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml +++ b/Documentation/devicetree/bindings/phy/marvell,comphy-cp110.yaml @@ -47,21 +47,19 @@ properties: const: 0 clocks: + minItems: 1 maxItems: 3 - description: Reference clocks for CP110; MG clock, MG Core clock, AXI clock clock-names: - items: - - const: mg_clk - - const: mg_core_clk - - const: axi_clk + minItems: 1 + maxItems: 3 marvell,system-controller: description: Phandle to the Marvell system controller (CP110 only) $ref: /schemas/types.yaml#/definitions/phandle patternProperties: - '^phy@[0-2]$': + '^phy@[0-5]$': description: A COMPHY lane child node type: object additionalProperties: false @@ -69,10 +67,14 @@ patternProperties: properties: reg: description: COMPHY lane number + maximum: 5 '#phy-cells': const: 1 + connector: + type: object + required: - reg - '#phy-cells' @@ -91,13 +93,24 @@ allOf: then: properties: - clocks: false - clock-names: false + clocks: + maxItems: 1 + clock-names: + const: xtal required: - reg-names else: + properties: + clocks: + minItems: 3 + clock-names: + items: + - const: mg_clk + - const: mg_core_clk + - const: axi_clk + required: - marvell,system-controller diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml index a1ae8c7988c8..b6f140bf5b3b 100644 --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml @@ -176,6 +176,8 @@ allOf: compatible: contains: enum: + - qcom,sa8775p-qmp-gen4x2-pcie-phy + - qcom,sa8775p-qmp-gen4x4-pcie-phy - qcom,sc8280xp-qmp-gen3x1-pcie-phy - qcom,sc8280xp-qmp-gen3x2-pcie-phy - qcom,sc8280xp-qmp-gen3x4-pcie-phy @@ -197,8 +199,6 @@ allOf: contains: enum: - qcom,qcs8300-qmp-gen4x2-pcie-phy - - qcom,sa8775p-qmp-gen4x2-pcie-phy - - qcom,sa8775p-qmp-gen4x4-pcie-phy then: properties: clocks: diff --git a/Documentation/devicetree/bindings/serial/8250.yaml b/Documentation/devicetree/bindings/serial/8250.yaml index e46bee8d25bf..b243afa69a1a 100644 --- a/Documentation/devicetree/bindings/serial/8250.yaml +++ b/Documentation/devicetree/bindings/serial/8250.yaml @@ -48,7 +48,6 @@ allOf: oneOf: - required: [ clock-frequency ] - required: [ clocks ] - - if: properties: compatible: @@ -60,12 +59,39 @@ allOf: items: - const: uartclk - const: reg - else: + - if: + properties: + compatible: + contains: + const: spacemit,k1-uart + then: properties: clock-names: items: - const: core - const: bus + - if: + properties: + compatible: + contains: + enum: + - spacemit,k1-uart + - nxp,lpc1850-uart + then: + required: + - clocks + - clock-names + properties: + clocks: + minItems: 2 + clock-names: + minItems: 2 + else: + properties: + clocks: + maxItems: 1 + clock-names: + maxItems: 1 properties: compatible: @@ -162,6 +188,9 @@ properties: minItems: 1 maxItems: 2 oneOf: + - enum: + - main + - uart - items: - const: core - const: bus @@ -264,29 +293,6 @@ required: - reg - interrupts -if: - properties: - compatible: - contains: - enum: - - spacemit,k1-uart - - nxp,lpc1850-uart -then: - required: - - clocks - - clock-names - properties: - clocks: - minItems: 2 - clock-names: - minItems: 2 -else: - properties: - clocks: - maxItems: 1 - clock-names: - maxItems: 1 - unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml b/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml index 89c462653e2d..8cc848ae11cb 100644 --- a/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml +++ b/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml @@ -41,7 +41,7 @@ properties: - const: dma_intr2 clocks: - minItems: 1 + maxItems: 1 clock-names: const: sw_baud diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml index a65a42ccaafe..a82360bed188 100644 --- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml +++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.yaml @@ -20,6 +20,7 @@ properties: - enum: - fsl,imx7ulp-spi - fsl,imx8qxp-spi + - nxp,s32g2-lpspi - items: - enum: - fsl,imx8ulp-spi @@ -27,6 +28,10 @@ properties: - fsl,imx94-spi - fsl,imx95-spi - const: fsl,imx7ulp-spi + - items: + - const: nxp,s32g3-lpspi + - const: nxp,s32g2-lpspi + reg: maxItems: 1 diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index 02f1ddcfbf1c..d15335684ec3 100644 --- a/Documentation/netlink/specs/mptcp_pm.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -256,7 +256,7 @@ attribute-sets: type: u32 - name: if-idx - type: u32 + type: s32 - name: reset-reason type: u32 diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst index bc1b585355f7..7650c4b5be5f 100644 --- a/Documentation/networking/can.rst +++ b/Documentation/networking/can.rst @@ -742,7 +742,7 @@ The broadcast manager sends responses to user space in the same form: struct timeval ival1, ival2; /* count and subsequent interval */ canid_t can_id; /* unique can_id for task */ __u32 nframes; /* number of can_frames following */ - struct can_frame frames[0]; + struct can_frame frames[]; }; The aligned payload 'frames' uses the same basic CAN frame structure defined diff --git a/Documentation/networking/mptcp.rst b/Documentation/networking/mptcp.rst index 17f2bab61164..2e31038d6462 100644 --- a/Documentation/networking/mptcp.rst +++ b/Documentation/networking/mptcp.rst @@ -60,10 +60,10 @@ address announcements. Typically, it is the client side that initiates subflows, and the server side that announces additional addresses via the ``ADD_ADDR`` and ``REMOVE_ADDR`` options. -Path managers are controlled by the ``net.mptcp.pm_type`` sysctl knob -- see -mptcp-sysctl.rst. There are two types: the in-kernel one (type ``0``) where the -same rules are applied for all the connections (see: ``ip mptcp``) ; and the -userspace one (type ``1``), controlled by a userspace daemon (i.e. `mptcpd +Path managers are controlled by the ``net.mptcp.path_manager`` sysctl knob -- +see mptcp-sysctl.rst. There are two types: the in-kernel one (``kernel``) where +the same rules are applied for all the connections (see: ``ip mptcp``) ; and the +userspace one (``userspace``), controlled by a userspace daemon (i.e. `mptcpd <https://mptcpd.mptcp.dev/>`_) where different rules can be applied for each connection. The path managers can be controlled via a Netlink API; see netlink_spec/mptcp_pm.rst. diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst index a15754adb041..7dd60366f4ff 100644 --- a/Documentation/networking/napi.rst +++ b/Documentation/networking/napi.rst @@ -433,9 +433,8 @@ Threaded NAPI Threaded NAPI is an operating mode that uses dedicated kernel threads rather than software IRQ context for NAPI processing. -The configuration is per netdevice and will affect all -NAPI instances of that device. Each NAPI instance will spawn a separate -thread (called ``napi/${ifc-name}-${napi-id}``). +Each threaded NAPI instance will spawn a separate thread +(called ``napi/${ifc-name}-${napi-id}``). It is recommended to pin each kernel thread to a single CPU, the same CPU as the CPU which services the interrupt. Note that the mapping diff --git a/MAINTAINERS b/MAINTAINERS index 03b433441836..6bbe4b4f8ec0 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3526,7 +3526,7 @@ F: Documentation/devicetree/bindings/arm/ti/nspire.yaml F: arch/arm/boot/dts/nspire/ ARM/TOSHIBA VISCONTI ARCHITECTURE -M: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp> +M: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.x90@mail.toshiba> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/iwamatsu/linux-visconti.git @@ -3667,6 +3667,7 @@ F: drivers/virt/coco/arm-cca-guest/ F: drivers/virt/coco/pkvm-guest/ F: tools/testing/selftests/arm64/ X: arch/arm64/boot/dts/ +X: arch/arm64/configs/defconfig ARROW SPEEDCHIPS XRS7000 SERIES ETHERNET SWITCH DRIVER M: George McCollister <george.mccollister@gmail.com> @@ -4682,7 +4683,6 @@ F: security/bpf/ BPF [SELFTESTS] (Test Runners & Infrastructure) M: Andrii Nakryiko <andrii@kernel.org> M: Eduard Zingerman <eddyz87@gmail.com> -R: Mykola Lysenko <mykolal@fb.com> L: bpf@vger.kernel.org S: Maintained F: tools/testing/selftests/bpf/ @@ -5258,7 +5258,6 @@ F: drivers/gpio/gpio-bt8xx.c BTRFS FILE SYSTEM M: Chris Mason <clm@fb.com> -M: Josef Bacik <josef@toxicpanda.com> M: David Sterba <dsterba@suse.com> L: linux-btrfs@vger.kernel.org S: Maintained @@ -7239,15 +7238,15 @@ F: include/linux/swiotlb.h F: kernel/dma/ DMA MAPPING HELPERS DEVICE DRIVER API [RUST] -M: Abdiel Janulgue <abdiel.janulgue@gmail.com> M: Danilo Krummrich <dakr@kernel.org> +R: Abdiel Janulgue <abdiel.janulgue@gmail.com> R: Daniel Almeida <daniel.almeida@collabora.com> R: Robin Murphy <robin.murphy@arm.com> R: Andreas Hindborg <a.hindborg@kernel.org> L: rust-for-linux@vger.kernel.org S: Supported W: https://rust-for-linux.com -T: git https://github.com/Rust-for-Linux/linux.git alloc-next +T: git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git F: rust/helpers/dma.c F: rust/kernel/dma.rs F: samples/rust/rust_dma.rs @@ -7820,7 +7819,7 @@ Q: https://patchwork.freedesktop.org/project/nouveau/ Q: https://gitlab.freedesktop.org/drm/nouveau/-/merge_requests B: https://gitlab.freedesktop.org/drm/nouveau/-/issues C: irc://irc.oftc.net/nouveau -T: git https://gitlab.freedesktop.org/drm/nouveau.git +T: git https://gitlab.freedesktop.org/drm/misc/kernel.git F: drivers/gpu/drm/nouveau/ F: include/uapi/drm/nouveau_drm.h @@ -8079,7 +8078,6 @@ F: Documentation/devicetree/bindings/gpu/ F: Documentation/gpu/ F: drivers/gpu/drm/ F: drivers/gpu/vga/ -F: rust/kernel/drm/ F: include/drm/drm F: include/linux/vga* F: include/uapi/drm/ @@ -8091,11 +8089,21 @@ X: drivers/gpu/drm/i915/ X: drivers/gpu/drm/kmb/ X: drivers/gpu/drm/mediatek/ X: drivers/gpu/drm/msm/ -X: drivers/gpu/drm/nouveau/ +X: drivers/gpu/drm/nova/ X: drivers/gpu/drm/radeon/ X: drivers/gpu/drm/tegra/ X: drivers/gpu/drm/xe/ +DRM DRIVERS AND COMMON INFRASTRUCTURE [RUST] +M: Danilo Krummrich <dakr@kernel.org> +M: Alice Ryhl <aliceryhl@google.com> +S: Supported +W: https://drm.pages.freedesktop.org/maintainer-tools/drm-rust.html +T: git https://gitlab.freedesktop.org/drm/rust/kernel.git +F: drivers/gpu/drm/nova/ +F: drivers/gpu/nova-core/ +F: rust/kernel/drm/ + DRM DRIVERS FOR ALLWINNER A10 M: Maxime Ripard <mripard@kernel.org> M: Chen-Yu Tsai <wens@csie.org> @@ -10388,7 +10396,7 @@ S: Maintained F: drivers/input/touchscreen/goodix* GOOGLE ETHERNET DRIVERS -M: Jeroen de Borst <jeroendb@google.com> +M: Joshua Washington <joshwash@google.com> M: Harshitha Ramamurthy <hramamurthy@google.com> L: netdev@vger.kernel.org S: Maintained @@ -15740,13 +15748,6 @@ S: Supported W: http://www.melexis.com F: drivers/iio/temperature/mlx90635.c -MELFAS MIP4 TOUCHSCREEN DRIVER -M: Sangwon Jee <jeesw@melfas.com> -S: Supported -W: http://www.melfas.com -F: Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt -F: drivers/input/touchscreen/melfas_mip4.c - MELLANOX BLUEFIELD I2C DRIVER M: Khalil Blaiech <kblaiech@nvidia.com> M: Asmaa Mnebhi <asmaa@nvidia.com> @@ -17482,6 +17483,7 @@ NETFILTER M: Pablo Neira Ayuso <pablo@netfilter.org> M: Jozsef Kadlecsik <kadlec@netfilter.org> M: Florian Westphal <fw@strlen.de> +R: Phil Sutter <phil@nwl.cc> L: netfilter-devel@vger.kernel.org L: coreteam@netfilter.org S: Maintained @@ -17853,6 +17855,7 @@ F: net/ipv6/tcp*.c NETWORKING [TLS] M: John Fastabend <john.fastabend@gmail.com> M: Jakub Kicinski <kuba@kernel.org> +M: Sabrina Dubroca <sd@queasysnail.net> L: netdev@vger.kernel.org S: Maintained F: include/net/tls.h @@ -24255,6 +24258,12 @@ S: Maintained F: Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml F: drivers/input/keyboard/sun4i-lradc-keys.c +SUNDANCE NETWORK DRIVER +M: Denis Kirjanov <dkirjanov@suse.de> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/dlink/sundance.c + SUNPLUS ETHERNET DRIVER M: Wells Lu <wellslutw@gmail.com> L: netdev@vger.kernel.org @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 17 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts b/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts index 7eaf6ca233ec..d086437f5e6f 100644 --- a/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts +++ b/arch/arm/boot/dts/microchip/at91-sama7d65_curiosity.dts @@ -387,6 +387,8 @@ &sdmmc1 { bus-width = <4>; + no-1-8-v; + sdhci-caps-mask = <0x0 0x00200000>; pinctrl-names = "default"; pinctrl-0 = <&pinctrl_sdmmc1_default>; status = "okay"; diff --git a/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts b/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts index 21f824b09191..decbf2726ec4 100644 --- a/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts +++ b/arch/arm/boot/dts/rockchip/rk3128-xpi-3128.dts @@ -272,7 +272,7 @@ phy-mode = "rmii"; phy-handle = <&phy0>; assigned-clocks = <&cru SCLK_MAC_SRC>; - assigned-clock-rates= <50000000>; + assigned-clock-rates = <50000000>; pinctrl-names = "default"; pinctrl-0 = <&rmii_pins>; status = "okay"; diff --git a/arch/arm/boot/dts/rockchip/rv1109-relfor-saib.dts b/arch/arm/boot/dts/rockchip/rv1109-relfor-saib.dts index c13829d32c32..8a92700349b4 100644 --- a/arch/arm/boot/dts/rockchip/rv1109-relfor-saib.dts +++ b/arch/arm/boot/dts/rockchip/rv1109-relfor-saib.dts @@ -250,9 +250,9 @@ &i2s0 { /delete-property/ pinctrl-0; rockchip,trcm-sync-rx-only; - pinctrl-0 = <&i2s0m0_sclk_rx>, - <&i2s0m0_lrck_rx>, - <&i2s0m0_sdi0>; + pinctrl-0 = <&i2s0m0_sclk_rx>, + <&i2s0m0_lrck_rx>, + <&i2s0m0_sdi0>; pinctrl-names = "default"; status = "okay"; }; diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig index 04bd91c72521..c5ef27e3cd8f 100644 --- a/arch/arm/mach-at91/Kconfig +++ b/arch/arm/mach-at91/Kconfig @@ -1,4 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only +config ARCH_MICROCHIP + bool + menuconfig ARCH_AT91 bool "AT91/Microchip SoCs" depends on (CPU_LITTLE_ENDIAN && (ARCH_MULTI_V4T || ARCH_MULTI_V5)) || \ @@ -8,6 +11,7 @@ menuconfig ARCH_AT91 select GPIOLIB select PINCTRL select SOC_BUS + select ARCH_MICROCHIP if ARCH_AT91 config SOC_SAMV7 diff --git a/arch/arm64/boot/dts/axiado/ax3000-evk.dts b/arch/arm64/boot/dts/axiado/ax3000-evk.dts index 92101c5b534b..b86e96962557 100644 --- a/arch/arm64/boot/dts/axiado/ax3000-evk.dts +++ b/arch/arm64/boot/dts/axiado/ax3000-evk.dts @@ -14,6 +14,9 @@ #size-cells = <2>; aliases { + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; serial3 = &uart3; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts index d0fc5977258f..16078ff60ef0 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-data-modul-edm-sbc.dts @@ -555,6 +555,7 @@ pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>; cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>; vmmc-supply = <®_usdhc2_vmmc>; + vqmmc-supply = <&ldo5>; bus-width = <4>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi index 7f754e0a5d69..68c2e0156a5c 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-dhcom-som.dtsi @@ -609,6 +609,7 @@ pinctrl-2 = <&pinctrl_usdhc2_200mhz>, <&pinctrl_usdhc2_gpio>; cd-gpios = <&gpio2 12 GPIO_ACTIVE_LOW>; vmmc-supply = <®_usdhc2_vmmc>; + vqmmc-supply = <&ldo5>; bus-width = <4>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts index d7fd9d36f824..f7346b3d35fe 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mp-ras314.dts @@ -467,6 +467,10 @@ status = "okay"; }; +®_usdhc2_vqmmc { + status = "okay"; +}; + &sai5 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_sai5>; @@ -876,8 +880,7 @@ <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0 0x1d2>, <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1 0x1d2>, <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2 0x1d2>, - <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d2>, - <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc0>; + <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d2>; }; pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { @@ -886,8 +889,7 @@ <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0 0x1d4>, <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1 0x1d4>, <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2 0x1d4>, - <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d4>, - <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc0>; + <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d4>; }; pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { @@ -896,8 +898,7 @@ <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0 0x1d4>, <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1 0x1d4>, <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2 0x1d4>, - <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d4>, - <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc0>; + <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d4>; }; pinctrl_usdhc2_gpio: usdhc2-gpiogrp { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts index 33cd92e63c5d..4eedd00d83b9 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts +++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql-mba8mpxl.dts @@ -604,6 +604,10 @@ status = "okay"; }; +®_usdhc2_vqmmc { + status = "okay"; +}; + &sai3 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_sai3>; @@ -983,8 +987,7 @@ <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0 0x1d2>, <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1 0x1d2>, <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2 0x1d2>, - <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d2>, - <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc0>; + <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d2>; }; pinctrl_usdhc2_100mhz: usdhc2-100mhzgrp { @@ -993,8 +996,7 @@ <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0 0x1d4>, <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1 0x1d4>, <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2 0x1d4>, - <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d4>, - <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc0>; + <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d4>; }; pinctrl_usdhc2_200mhz: usdhc2-200mhzgrp { @@ -1003,8 +1005,7 @@ <MX8MP_IOMUXC_SD2_DATA0__USDHC2_DATA0 0x1d4>, <MX8MP_IOMUXC_SD2_DATA1__USDHC2_DATA1 0x1d4>, <MX8MP_IOMUXC_SD2_DATA2__USDHC2_DATA2 0x1d4>, - <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d4>, - <MX8MP_IOMUXC_GPIO1_IO04__USDHC2_VSELECT 0xc0>; + <MX8MP_IOMUXC_SD2_DATA3__USDHC2_DATA3 0x1d4>; }; pinctrl_usdhc2_gpio: usdhc2-gpiogrp { diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi index fd70b686e7ef..9716f24f7c6e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi @@ -16,13 +16,18 @@ reg = <0x0 0x40000000 0 0x80000000>; }; - /* identical to buck4_reg, but should never change */ - reg_vcc3v3: regulator-vcc3v3 { - compatible = "regulator-fixed"; - regulator-name = "VCC3V3"; - regulator-min-microvolt = <3300000>; + reg_usdhc2_vqmmc: regulator-usdhc2-vqmmc { + compatible = "regulator-gpio"; + pinctrl-names = "default"; + pinctrl-0 = <&pinctrl_reg_usdhc2_vqmmc>; + regulator-name = "V_SD2"; + regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; - regulator-always-on; + gpios = <&gpio1 4 GPIO_ACTIVE_HIGH>; + states = <1800000 0x1>, + <3300000 0x0>; + vin-supply = <&ldo5_reg>; + status = "disabled"; }; }; @@ -173,17 +178,21 @@ read-only; reg = <0x53>; pagesize = <16>; - vcc-supply = <®_vcc3v3>; + vcc-supply = <&buck4_reg>; }; m24c64: eeprom@57 { compatible = "atmel,24c64"; reg = <0x57>; pagesize = <32>; - vcc-supply = <®_vcc3v3>; + vcc-supply = <&buck4_reg>; }; }; +&usdhc2 { + vqmmc-supply = <®_usdhc2_vqmmc>; +}; + &usdhc3 { pinctrl-names = "default", "state_100mhz", "state_200mhz"; pinctrl-0 = <&pinctrl_usdhc3>; @@ -193,7 +202,7 @@ non-removable; no-sd; no-sdio; - vmmc-supply = <®_vcc3v3>; + vmmc-supply = <&buck4_reg>; vqmmc-supply = <&buck5_reg>; status = "okay"; }; @@ -233,6 +242,10 @@ fsl,pins = <MX8MP_IOMUXC_SD2_RESET_B__GPIO2_IO19 0x10>; }; + pinctrl_reg_usdhc2_vqmmc: regusdhc2vqmmcgrp { + fsl,pins = <MX8MP_IOMUXC_GPIO1_IO04__GPIO1_IO04 0xc0>; + }; + pinctrl_usdhc3: usdhc3grp { fsl,pins = <MX8MP_IOMUXC_NAND_WE_B__USDHC3_CLK 0x194>, <MX8MP_IOMUXC_NAND_WP_B__USDHC3_CMD 0x1d4>, diff --git a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts index 2f949a0d48d2..9d034275c847 100644 --- a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts +++ b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts @@ -80,17 +80,17 @@ flexcan1_phy: can-phy0 { compatible = "nxp,tjr1443"; #phy-cells = <0>; - max-bitrate = <1000000>; + max-bitrate = <8000000>; enable-gpios = <&i2c6_pcal6416 6 GPIO_ACTIVE_HIGH>; - standby-gpios = <&i2c6_pcal6416 5 GPIO_ACTIVE_HIGH>; + standby-gpios = <&i2c6_pcal6416 5 GPIO_ACTIVE_LOW>; }; flexcan2_phy: can-phy1 { compatible = "nxp,tjr1443"; #phy-cells = <0>; - max-bitrate = <1000000>; - enable-gpios = <&i2c6_pcal6416 4 GPIO_ACTIVE_HIGH>; - standby-gpios = <&i2c6_pcal6416 3 GPIO_ACTIVE_HIGH>; + max-bitrate = <8000000>; + enable-gpios = <&i2c4_gpio_expander_21 4 GPIO_ACTIVE_HIGH>; + standby-gpios = <&i2c4_gpio_expander_21 3 GPIO_ACTIVE_LOW>; }; reg_vref_1v8: regulator-1p8v { diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index 4ca6a7ea586e..8296888bce59 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1843,7 +1843,7 @@ <GIC_SPI 294 IRQ_TYPE_LEVEL_HIGH>; clocks = <&scmi_clk IMX95_CLK_VPU>, <&vpu_blk_ctrl IMX95_CLK_VPUBLK_JPEG_ENC>; - assigned-clocks = <&vpu_blk_ctrl IMX95_CLK_VPUBLK_JPEG_DEC>; + assigned-clocks = <&vpu_blk_ctrl IMX95_CLK_VPUBLK_JPEG_ENC>; assigned-clock-parents = <&scmi_clk IMX95_CLK_VPUJPEG>; power-domains = <&scmi_devpd IMX95_PD_VPU>; }; diff --git a/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi b/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi index b4bd4e34747c..192791993f05 100644 --- a/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-pp1516.dtsi @@ -72,7 +72,7 @@ }; vcc_cam_avdd: regulator-vcc-cam-avdd { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; regulator-name = "vcc_cam_avdd"; gpio = <&gpio3 RK_PC0 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; @@ -83,7 +83,7 @@ }; vcc_cam_dovdd: regulator-vcc-cam-dovdd { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; regulator-name = "vcc_cam_dovdd"; gpio = <&gpio3 RK_PC1 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; @@ -94,7 +94,7 @@ }; vcc_cam_dvdd: regulator-vcc-cam-dvdd { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; regulator-name = "vcc_cam_dvdd"; gpio = <&gpio3 RK_PC5 GPIO_ACTIVE_HIGH>; enable-active-high; @@ -106,7 +106,7 @@ }; vcc_lens_afvdd: regulator-vcc-lens-afvdd { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; regulator-name = "vcc_lens_afvdd"; gpio = <&gpio3 RK_PB2 GPIO_ACTIVE_LOW>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso index ea5ce919984f..760d5139f95d 100644 --- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso +++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou-video-demo.dtso @@ -26,7 +26,7 @@ }; cam_afvdd_2v8: regulator-cam-afvdd-2v8 { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; gpio = <&pca9670 2 GPIO_ACTIVE_LOW>; regulator-max-microvolt = <2800000>; regulator-min-microvolt = <2800000>; @@ -35,7 +35,7 @@ }; cam_avdd_2v8: regulator-cam-avdd-2v8 { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; gpio = <&pca9670 4 GPIO_ACTIVE_LOW>; regulator-max-microvolt = <2800000>; regulator-min-microvolt = <2800000>; @@ -44,7 +44,7 @@ }; cam_dovdd_1v8: regulator-cam-dovdd-1v8 { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; gpio = <&pca9670 3 GPIO_ACTIVE_LOW>; regulator-max-microvolt = <1800000>; regulator-min-microvolt = <1800000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts b/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts index f9f633aebb64..e5e6b800c2d1 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-sakurapi-rk3308b.dts @@ -260,6 +260,6 @@ status = "okay"; }; -&usb_host_ohci{ +&usb_host_ohci { status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3368-lba3368.dts b/arch/arm64/boot/dts/rockchip/rk3368-lba3368.dts index b99bb0a5f900..b9801a691b48 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368-lba3368.dts +++ b/arch/arm64/boot/dts/rockchip/rk3368-lba3368.dts @@ -609,7 +609,7 @@ bluetooth { compatible = "brcm,bcm4345c5"; - interrupts-extended = <&gpio3 RK_PA7 GPIO_ACTIVE_HIGH>; + interrupts-extended = <&gpio3 RK_PA7 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "host-wakeup"; clocks = <&rk808 RK808_CLKOUT1>; clock-names = "lpo"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index 5a8551d9ffe4..b33a1509a8e9 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -959,6 +959,7 @@ reg = <0>; m25p,fast-read; spi-max-frequency = <10000000>; + vcc-supply = <&vcc_3v0>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts index 585ef0fd88ef..6f97e57f36f5 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinephone-pro.dts @@ -754,6 +754,7 @@ compatible = "jedec,spi-nor"; reg = <0>; spi-max-frequency = <10000000>; + vcc-supply = <&vcc_1v8>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso index d28880b8dd44..5e8f729c2cf2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma-haikou-video-demo.dtso @@ -26,7 +26,7 @@ }; cam_afvdd_2v8: regulator-cam-afvdd-2v8 { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; gpio = <&pca9670 2 GPIO_ACTIVE_LOW>; regulator-max-microvolt = <2800000>; regulator-min-microvolt = <2800000>; @@ -35,7 +35,7 @@ }; cam_avdd_2v8: regulator-cam-avdd-2v8 { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; gpio = <&pca9670 4 GPIO_ACTIVE_LOW>; regulator-max-microvolt = <2800000>; regulator-min-microvolt = <2800000>; @@ -44,7 +44,7 @@ }; cam_dovdd_1v8: regulator-cam-dovdd-1v8 { - compatible = "regulator-fixed"; + compatible = "regulator-fixed"; gpio = <&pca9670 3 GPIO_ACTIVE_LOW>; regulator-max-microvolt = <1800000>; regulator-min-microvolt = <1800000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi index e7ba477e75f9..7f578c50b4ad 100644 --- a/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3566-bigtreetech-cb2.dtsi @@ -53,7 +53,7 @@ gpios = <&gpio4 RK_PA1 GPIO_ACTIVE_LOW>; linux,default-trigger = "default-on"; pinctrl-names = "default"; - pinctrl-0 =<&blue_led>; + pinctrl-0 = <&blue_led>; }; led-1 { @@ -62,7 +62,7 @@ gpios = <&gpio0 RK_PB7 GPIO_ACTIVE_LOW>; linux,default-trigger = "heartbeat"; pinctrl-names = "default"; - pinctrl-0 =<&heartbeat_led>; + pinctrl-0 = <&heartbeat_led>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts index 101e2ee9766d..3386084f6318 100644 --- a/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts +++ b/arch/arm64/boot/dts/rockchip/rk3576-armsom-sige5.dts @@ -302,8 +302,7 @@ ð1m0_tx_bus2 ð1m0_rx_bus2 ð1m0_rgmii_clk - ð1m0_rgmii_bus - ðm0_clk1_25m_out>; + ð1m0_rgmii_bus>; status = "okay"; }; @@ -784,7 +783,6 @@ rgmii_phy0: phy@1 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <0x1>; - clocks = <&cru REFCLKO25M_GMAC0_OUT>; pinctrl-names = "default"; pinctrl-0 = <&gmac0_rst>; reset-assert-us = <20000>; @@ -797,7 +795,6 @@ rgmii_phy1: phy@1 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <0x1>; - clocks = <&cru REFCLKO25M_GMAC1_OUT>; pinctrl-names = "default"; pinctrl-0 = <&gmac1_rst>; reset-assert-us = <20000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts b/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts index e04f21d8c831..431ff77d4518 100644 --- a/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts +++ b/arch/arm64/boot/dts/rockchip/rk3582-radxa-e52c.dts @@ -250,6 +250,7 @@ compatible = "belling,bl24c16a", "atmel,24c16"; reg = <0x50>; pagesize = <16>; + read-only; vcc-supply = <&vcc_3v3_pmu>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts index 121e4d1c3fa5..8222f1fae8fa 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5-plus.dts @@ -77,7 +77,7 @@ pinctrl-names = "default"; pinctrl-0 = <&hp_detect>; simple-audio-card,aux-devs = <&speaker_amp>, <&headphone_amp>; - simple-audio-card,hp-det-gpios = <&gpio1 RK_PD3 GPIO_ACTIVE_LOW>; + simple-audio-card,hp-det-gpios = <&gpio1 RK_PD3 GPIO_ACTIVE_HIGH>; simple-audio-card,widgets = "Microphone", "Onboard Microphone", "Microphone", "Microphone Jack", diff --git a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi index 91d56c34a1e4..8a8f3b26754d 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-orangepi-5.dtsi @@ -365,6 +365,8 @@ max-frequency = <200000000>; mmc-hs400-1_8v; mmc-hs400-enhanced-strobe; + vmmc-supply = <&vcc_3v3_s3>; + vqmmc-supply = <&vcc_1v8_s3>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts index 258c7400301d..f16ff0064309 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5t.dts @@ -68,6 +68,22 @@ status = "okay"; }; +&pcie30phy { + data-lanes = <1 1 2 2>; +}; + +&pcie3x2 { + pinctrl-names = "default"; + pinctrl-0 = <&pcie3x2_rst>; + reset-gpios = <&gpio4 RK_PB0 GPIO_ACTIVE_HIGH>; + vpcie3v3-supply = <&vcc3v3_pcie30>; + status = "okay"; +}; + +&pcie3x4 { + num-lanes = <2>; +}; + &pinctrl { hdmirx { hdmirx_hpd: hdmirx-5v-detection { @@ -90,11 +106,23 @@ }; }; + pcie3 { + pcie3x2_rst: pcie3x2-rst { + rockchip,pins = <4 RK_PB0 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + sound { hp_detect: hp-detect { rockchip,pins = <4 RK_PC3 RK_FUNC_GPIO &pcfg_pull_none>; }; }; + + usb { + vcc5v0_host_en: vcc5v0-host-en { + rockchip,pins = <1 RK_PA1 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; }; &vcc3v3_pcie2x1l0 { @@ -103,3 +131,10 @@ pinctrl-0 = <&pcie2_0_vcc3v3_en>; status = "okay"; }; + +&vcc5v0_host { + enable-active-high; + gpio = <&gpio1 RK_PA1 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&vcc5v0_host_en>; +}; diff --git a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi index 3045cb3bd68c..9884a5df47df 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588j.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588j.dtsi @@ -28,7 +28,7 @@ compatible = "operating-points-v2"; opp-shared; - opp-1200000000{ + opp-1200000000 { opp-hz = /bits/ 64 <1200000000>; opp-microvolt = <750000 750000 950000>; clock-latency-ns = <40000>; @@ -49,7 +49,7 @@ compatible = "operating-points-v2"; opp-shared; - opp-1200000000{ + opp-1200000000 { opp-hz = /bits/ 64 <1200000000>; opp-microvolt = <750000 750000 950000>; clock-latency-ns = <40000>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts index 7434ac39246f..7e179862da6e 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588s-roc-pc.dts @@ -320,9 +320,9 @@ &i2c3 { status = "okay"; - es8388: audio-codec@10 { + es8388: audio-codec@11 { compatible = "everest,es8388", "everest,es8328"; - reg = <0x10>; + reg = <0x11>; clocks = <&cru I2S1_8CH_MCLKOUT>; AVDD-supply = <&vcc_3v3_s0>; DVDD-supply = <&vcc_1v8_s0>; diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index 79550b22ba19..fb9b88eebeb1 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -19,6 +19,7 @@ struct mod_arch_specific { /* for CONFIG_DYNAMIC_FTRACE */ struct plt_entry *ftrace_trampolines; + struct plt_entry *init_ftrace_trampolines; }; u64 module_emit_plt_entry(struct module *mod, Elf64_Shdr *sechdrs, diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h index b9ae8349e35d..fb944b46846d 100644 --- a/arch/arm64/include/asm/module.lds.h +++ b/arch/arm64/include/asm/module.lds.h @@ -2,6 +2,7 @@ SECTIONS { .plt 0 : { BYTE(0) } .init.plt 0 : { BYTE(0) } .text.ftrace_trampoline 0 : { BYTE(0) } + .init.text.ftrace_trampoline 0 : { BYTE(0) } #ifdef CONFIG_KASAN_SW_TAGS /* diff --git a/arch/arm64/include/uapi/asm/bitsperlong.h b/arch/arm64/include/uapi/asm/bitsperlong.h index 485d60bee26c..d59730975f30 100644 --- a/arch/arm64/include/uapi/asm/bitsperlong.h +++ b/arch/arm64/include/uapi/asm/bitsperlong.h @@ -17,7 +17,12 @@ #ifndef __ASM_BITSPERLONG_H #define __ASM_BITSPERLONG_H +#if defined(__KERNEL__) && !defined(__aarch64__) +/* Used by the compat vDSO */ +#define __BITS_PER_LONG 32 +#else #define __BITS_PER_LONG 64 +#endif #include <asm-generic/bitsperlong.h> diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 5a890714ee2e..5adad37ab4fa 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -258,10 +258,17 @@ int ftrace_update_ftrace_func(ftrace_func_t func) return ftrace_modify_code(pc, 0, new, false); } -static struct plt_entry *get_ftrace_plt(struct module *mod) +static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) { #ifdef CONFIG_MODULES - struct plt_entry *plt = mod->arch.ftrace_trampolines; + struct plt_entry *plt = NULL; + + if (within_module_mem_type(addr, mod, MOD_INIT_TEXT)) + plt = mod->arch.init_ftrace_trampolines; + else if (within_module_mem_type(addr, mod, MOD_TEXT)) + plt = mod->arch.ftrace_trampolines; + else + return NULL; return &plt[FTRACE_PLT_IDX]; #else @@ -332,7 +339,7 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, if (WARN_ON(!mod)) return false; - plt = get_ftrace_plt(mod); + plt = get_ftrace_plt(mod, pc); if (!plt) { pr_err("ftrace: no module PLT for %ps\n", (void *)*addr); return false; diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index bde32979c06a..7afd370da9f4 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -283,7 +283,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, unsigned long core_plts = 0; unsigned long init_plts = 0; Elf64_Sym *syms = NULL; - Elf_Shdr *pltsec, *tramp = NULL; + Elf_Shdr *pltsec, *tramp = NULL, *init_tramp = NULL; int i; /* @@ -298,6 +298,9 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, else if (!strcmp(secstrings + sechdrs[i].sh_name, ".text.ftrace_trampoline")) tramp = sechdrs + i; + else if (!strcmp(secstrings + sechdrs[i].sh_name, + ".init.text.ftrace_trampoline")) + init_tramp = sechdrs + i; else if (sechdrs[i].sh_type == SHT_SYMTAB) syms = (Elf64_Sym *)sechdrs[i].sh_addr; } @@ -363,5 +366,12 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry); } + if (init_tramp) { + init_tramp->sh_type = SHT_NOBITS; + init_tramp->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + init_tramp->sh_addralign = __alignof__(struct plt_entry); + init_tramp->sh_size = NR_FTRACE_PLTS * sizeof(struct plt_entry); + } + return 0; } diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 40148d2725ce..d6d443c4a01a 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -466,6 +466,17 @@ static int module_init_ftrace_plt(const Elf_Ehdr *hdr, __init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR); mod->arch.ftrace_trampolines = plts; + + s = find_section(hdr, sechdrs, ".init.text.ftrace_trampoline"); + if (!s) + return -ENOEXEC; + + plts = (void *)s->sh_addr; + + __init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR); + + mod->arch.init_ftrace_trampolines = plts; + #endif return 0; } diff --git a/arch/mips/configs/mtx1_defconfig b/arch/mips/configs/mtx1_defconfig index e4bcdb64df6c..2707ab134639 100644 --- a/arch/mips/configs/mtx1_defconfig +++ b/arch/mips/configs/mtx1_defconfig @@ -273,6 +273,7 @@ CONFIG_DM9102=m CONFIG_ULI526X=m CONFIG_PCMCIA_XIRCOM=m CONFIG_DL2K=m +CONFIG_SUNDANCE=m CONFIG_PCMCIA_FMVJ18X=m CONFIG_E100=m CONFIG_E1000=m diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index bb359643ddc1..b082c1fae13c 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -433,6 +433,7 @@ CONFIG_DM9102=m CONFIG_ULI526X=m CONFIG_PCMCIA_XIRCOM=m CONFIG_DL2K=m +CONFIG_SUNDANCE=m CONFIG_S2IO=m CONFIG_FEC_MPC52xx=m CONFIG_GIANFAR=m diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index a4b233a0659e..51dcd8eaa243 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -65,7 +65,7 @@ config RISCV select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE select ARCH_SUPPORTS_HUGETLBFS if MMU # LLD >= 14: https://github.com/llvm/llvm-project/issues/50505 - select ARCH_SUPPORTS_LTO_CLANG if LLD_VERSION >= 140000 + select ARCH_SUPPORTS_LTO_CLANG if LLD_VERSION >= 140000 && CMODEL_MEDANY select ARCH_SUPPORTS_LTO_CLANG_THIN if LLD_VERSION >= 140000 select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS if 64BIT && MMU select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index a8a2af6dfe9d..2a16e88e13de 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -91,7 +91,7 @@ #endif .macro asm_per_cpu dst sym tmp - REG_L \tmp, TASK_TI_CPU_NUM(tp) + lw \tmp, TASK_TI_CPU_NUM(tp) slli \tmp, \tmp, PER_CPU_OFFSET_SHIFT la \dst, __per_cpu_offset add \dst, \dst, \tmp diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h index b88a6218b7f2..f5f4f7f85543 100644 --- a/arch/riscv/include/asm/uaccess.h +++ b/arch/riscv/include/asm/uaccess.h @@ -209,7 +209,7 @@ do { \ err = 0; \ break; \ __gu_failed: \ - x = 0; \ + x = (__typeof__(x))0; \ err = -EFAULT; \ } while (0) @@ -311,7 +311,7 @@ do { \ do { \ if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \ !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \ - __inttype(x) ___val = (__inttype(x))x; \ + __typeof__(*(__gu_ptr)) ___val = (x); \ if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \ goto label; \ break; \ @@ -438,10 +438,10 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n) } #define __get_kernel_nofault(dst, src, type, err_label) \ - __get_user_nocheck(*((type *)(dst)), (type *)(src), err_label) + __get_user_nocheck(*((type *)(dst)), (__force __user type *)(src), err_label) #define __put_kernel_nofault(dst, src, type, err_label) \ - __put_user_nocheck(*((type *)(src)), (type *)(dst), err_label) + __put_user_nocheck(*((type *)(src)), (__force __user type *)(dst), err_label) static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 3a0ec6fd5956..d0ded2438533 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -46,7 +46,7 @@ * a0 = &new_vmalloc[BIT_WORD(cpu)] * a1 = BIT_MASK(cpu) */ - REG_L a2, TASK_TI_CPU(tp) + lw a2, TASK_TI_CPU(tp) /* * Compute the new_vmalloc element position: * (cpu / 64) * 8 = (cpu >> 6) << 3 diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 10e01ff06312..9883a55d61b5 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -1356,7 +1356,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, emit_mv(rd, rs, ctx); #ifdef CONFIG_SMP /* Load current CPU number in T1 */ - emit_ld(RV_REG_T1, offsetof(struct thread_info, cpu), + emit_lw(RV_REG_T1, offsetof(struct thread_info, cpu), RV_REG_TP, ctx); /* Load address of __per_cpu_offset array in T2 */ emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx); @@ -1763,7 +1763,7 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, */ if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) { /* Load current CPU number in R0 */ - emit_ld(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu), + emit_lw(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu), RV_REG_TP, ctx); break; } diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 4d09954ebf49..04457d88e589 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -760,8 +760,6 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) break; case PERF_TYPE_HARDWARE: - if (is_sampling_event(event)) /* No sampling support */ - return -ENOENT; ev = attr->config; if (!attr->exclude_user && attr->exclude_kernel) { /* @@ -859,6 +857,8 @@ static int cpumf_pmu_event_init(struct perf_event *event) unsigned int type = event->attr.type; int err = -ENOENT; + if (is_sampling_event(event)) /* No sampling support */ + return err; if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW) err = __hw_perf_event_init(event, type); else if (event->pmu->type == type) diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index f373a1009c45..9455f213dc20 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -285,10 +285,10 @@ static int paicrypt_event_init(struct perf_event *event) /* PAI crypto PMU registered as PERF_TYPE_RAW, check event type */ if (a->type != PERF_TYPE_RAW && event->pmu->type != a->type) return -ENOENT; - /* PAI crypto event must be in valid range */ + /* PAI crypto event must be in valid range, try others if not */ if (a->config < PAI_CRYPTO_BASE || a->config > PAI_CRYPTO_BASE + paicrypt_cnt) - return -EINVAL; + return -ENOENT; /* Allow only CRYPTO_ALL for sampling */ if (a->sample_period && a->config != PAI_CRYPTO_BASE) return -EINVAL; diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index d827473e7f87..7b32935273ce 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -265,7 +265,7 @@ static int paiext_event_valid(struct perf_event *event) event->hw.config_base = offsetof(struct paiext_cb, acc); return 0; } - return -EINVAL; + return -ENOENT; } /* Might be called on different CPU than the one the event is intended for. */ diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 60688be4e876..50eb57c976bc 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -335,7 +335,6 @@ pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, int nodat; struct mm_struct *mm = vma->vm_mm; - preempt_disable(); pgste = ptep_xchg_start(mm, addr, ptep); nodat = !!(pgste_val(pgste) & _PGSTE_GPS_NODAT); old = ptep_flush_lazy(mm, addr, ptep, nodat); @@ -360,7 +359,6 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, } else { set_pte(ptep, pte); } - preempt_enable(); } static inline void pmdp_idte_local(struct mm_struct *mm, diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 58d890fe2100..52c8910ba2ef 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2701,6 +2701,15 @@ config MITIGATION_TSA security vulnerability on AMD CPUs which can lead to forwarding of invalid info to subsequent instructions and thus can affect their timing and thereby cause a leakage. + +config MITIGATION_VMSCAPE + bool "Mitigate VMSCAPE" + depends on KVM + default y + help + Enable mitigation for VMSCAPE attacks. VMSCAPE is a hardware security + vulnerability on Intel and AMD CPUs that may allow a guest to do + Spectre v2 style attacks on userspace hypervisor. endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 06fc0479a23f..751ca35386b0 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -495,6 +495,7 @@ #define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */ #define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */ #define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */ +#define X86_FEATURE_IBPB_EXIT_TO_USER (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */ /* * BUG word(s) @@ -551,4 +552,5 @@ #define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */ #define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ #define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */ +#define X86_BUG_VMSCAPE X86_BUG( 1*32+10) /* "vmscape" CPU is affected by VMSCAPE attacks from guests */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index d535a97c7284..ce3eb6d5fdf9 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -93,6 +93,13 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, * 8 (ia32) bits. */ choose_random_kstack_offset(rdtsc()); + + /* Avoid unnecessary reads of 'x86_ibpb_exit_to_user' */ + if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER) && + this_cpu_read(x86_ibpb_exit_to_user)) { + indirect_branch_prediction_barrier(); + this_cpu_write(x86_ibpb_exit_to_user, false); + } } #define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 10f261678749..e29f82466f43 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -530,6 +530,8 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) : "memory"); } +DECLARE_PER_CPU(bool, x86_ibpb_exit_to_user); + static inline void indirect_branch_prediction_barrier(void) { asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index af838b8d845c..36dcfc5105be 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -96,6 +96,9 @@ static void __init its_update_mitigation(void); static void __init its_apply_mitigation(void); static void __init tsa_select_mitigation(void); static void __init tsa_apply_mitigation(void); +static void __init vmscape_select_mitigation(void); +static void __init vmscape_update_mitigation(void); +static void __init vmscape_apply_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -105,6 +108,14 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current); +/* + * Set when the CPU has run a potentially malicious guest. An IBPB will + * be needed to before running userspace. That IBPB will flush the branch + * predictor content. + */ +DEFINE_PER_CPU(bool, x86_ibpb_exit_to_user); +EXPORT_PER_CPU_SYMBOL_GPL(x86_ibpb_exit_to_user); + u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; static u64 __ro_after_init x86_arch_cap_msr; @@ -262,6 +273,7 @@ void __init cpu_select_mitigations(void) its_select_mitigation(); bhi_select_mitigation(); tsa_select_mitigation(); + vmscape_select_mitigation(); /* * After mitigations are selected, some may need to update their @@ -293,6 +305,7 @@ void __init cpu_select_mitigations(void) bhi_update_mitigation(); /* srso_update_mitigation() depends on retbleed_update_mitigation(). */ srso_update_mitigation(); + vmscape_update_mitigation(); spectre_v1_apply_mitigation(); spectre_v2_apply_mitigation(); @@ -310,6 +323,7 @@ void __init cpu_select_mitigations(void) its_apply_mitigation(); bhi_apply_mitigation(); tsa_apply_mitigation(); + vmscape_apply_mitigation(); } /* @@ -2538,88 +2552,6 @@ static void update_mds_branch_idle(void) } } -#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" -#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" -#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n" - -void cpu_bugs_smt_update(void) -{ - mutex_lock(&spec_ctrl_mutex); - - if (sched_smt_active() && unprivileged_ebpf_enabled() && - spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) - pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); - - switch (spectre_v2_user_stibp) { - case SPECTRE_V2_USER_NONE: - break; - case SPECTRE_V2_USER_STRICT: - case SPECTRE_V2_USER_STRICT_PREFERRED: - update_stibp_strict(); - break; - case SPECTRE_V2_USER_PRCTL: - case SPECTRE_V2_USER_SECCOMP: - update_indir_branch_cond(); - break; - } - - switch (mds_mitigation) { - case MDS_MITIGATION_FULL: - case MDS_MITIGATION_AUTO: - case MDS_MITIGATION_VMWERV: - if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY)) - pr_warn_once(MDS_MSG_SMT); - update_mds_branch_idle(); - break; - case MDS_MITIGATION_OFF: - break; - } - - switch (taa_mitigation) { - case TAA_MITIGATION_VERW: - case TAA_MITIGATION_AUTO: - case TAA_MITIGATION_UCODE_NEEDED: - if (sched_smt_active()) - pr_warn_once(TAA_MSG_SMT); - break; - case TAA_MITIGATION_TSX_DISABLED: - case TAA_MITIGATION_OFF: - break; - } - - switch (mmio_mitigation) { - case MMIO_MITIGATION_VERW: - case MMIO_MITIGATION_AUTO: - case MMIO_MITIGATION_UCODE_NEEDED: - if (sched_smt_active()) - pr_warn_once(MMIO_MSG_SMT); - break; - case MMIO_MITIGATION_OFF: - break; - } - - switch (tsa_mitigation) { - case TSA_MITIGATION_USER_KERNEL: - case TSA_MITIGATION_VM: - case TSA_MITIGATION_AUTO: - case TSA_MITIGATION_FULL: - /* - * TSA-SQ can potentially lead to info leakage between - * SMT threads. - */ - if (sched_smt_active()) - static_branch_enable(&cpu_buf_idle_clear); - else - static_branch_disable(&cpu_buf_idle_clear); - break; - case TSA_MITIGATION_NONE: - case TSA_MITIGATION_UCODE_NEEDED: - break; - } - - mutex_unlock(&spec_ctrl_mutex); -} - #undef pr_fmt #define pr_fmt(fmt) "Speculative Store Bypass: " fmt @@ -3331,8 +3263,184 @@ static void __init srso_apply_mitigation(void) } #undef pr_fmt +#define pr_fmt(fmt) "VMSCAPE: " fmt + +enum vmscape_mitigations { + VMSCAPE_MITIGATION_NONE, + VMSCAPE_MITIGATION_AUTO, + VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER, + VMSCAPE_MITIGATION_IBPB_ON_VMEXIT, +}; + +static const char * const vmscape_strings[] = { + [VMSCAPE_MITIGATION_NONE] = "Vulnerable", + /* [VMSCAPE_MITIGATION_AUTO] */ + [VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER] = "Mitigation: IBPB before exit to userspace", + [VMSCAPE_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT", +}; + +static enum vmscape_mitigations vmscape_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_VMSCAPE) ? VMSCAPE_MITIGATION_AUTO : VMSCAPE_MITIGATION_NONE; + +static int __init vmscape_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) { + vmscape_mitigation = VMSCAPE_MITIGATION_NONE; + } else if (!strcmp(str, "ibpb")) { + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER; + } else if (!strcmp(str, "force")) { + setup_force_cpu_bug(X86_BUG_VMSCAPE); + vmscape_mitigation = VMSCAPE_MITIGATION_AUTO; + } else { + pr_err("Ignoring unknown vmscape=%s option.\n", str); + } + + return 0; +} +early_param("vmscape", vmscape_parse_cmdline); + +static void __init vmscape_select_mitigation(void) +{ + if (cpu_mitigations_off() || + !boot_cpu_has_bug(X86_BUG_VMSCAPE) || + !boot_cpu_has(X86_FEATURE_IBPB)) { + vmscape_mitigation = VMSCAPE_MITIGATION_NONE; + return; + } + + if (vmscape_mitigation == VMSCAPE_MITIGATION_AUTO) + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER; +} + +static void __init vmscape_update_mitigation(void) +{ + if (!boot_cpu_has_bug(X86_BUG_VMSCAPE)) + return; + + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB || + srso_mitigation == SRSO_MITIGATION_IBPB_ON_VMEXIT) + vmscape_mitigation = VMSCAPE_MITIGATION_IBPB_ON_VMEXIT; + + pr_info("%s\n", vmscape_strings[vmscape_mitigation]); +} + +static void __init vmscape_apply_mitigation(void) +{ + if (vmscape_mitigation == VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER) + setup_force_cpu_cap(X86_FEATURE_IBPB_EXIT_TO_USER); +} + +#undef pr_fmt #define pr_fmt(fmt) fmt +#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n" +#define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n" +#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n" +#define VMSCAPE_MSG_SMT "VMSCAPE: SMT on, STIBP is required for full protection. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/vmscape.html for more details.\n" + +void cpu_bugs_smt_update(void) +{ + mutex_lock(&spec_ctrl_mutex); + + if (sched_smt_active() && unprivileged_ebpf_enabled() && + spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) + pr_warn_once(SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG); + + switch (spectre_v2_user_stibp) { + case SPECTRE_V2_USER_NONE: + break; + case SPECTRE_V2_USER_STRICT: + case SPECTRE_V2_USER_STRICT_PREFERRED: + update_stibp_strict(); + break; + case SPECTRE_V2_USER_PRCTL: + case SPECTRE_V2_USER_SECCOMP: + update_indir_branch_cond(); + break; + } + + switch (mds_mitigation) { + case MDS_MITIGATION_FULL: + case MDS_MITIGATION_AUTO: + case MDS_MITIGATION_VMWERV: + if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY)) + pr_warn_once(MDS_MSG_SMT); + update_mds_branch_idle(); + break; + case MDS_MITIGATION_OFF: + break; + } + + switch (taa_mitigation) { + case TAA_MITIGATION_VERW: + case TAA_MITIGATION_AUTO: + case TAA_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(TAA_MSG_SMT); + break; + case TAA_MITIGATION_TSX_DISABLED: + case TAA_MITIGATION_OFF: + break; + } + + switch (mmio_mitigation) { + case MMIO_MITIGATION_VERW: + case MMIO_MITIGATION_AUTO: + case MMIO_MITIGATION_UCODE_NEEDED: + if (sched_smt_active()) + pr_warn_once(MMIO_MSG_SMT); + break; + case MMIO_MITIGATION_OFF: + break; + } + + switch (tsa_mitigation) { + case TSA_MITIGATION_USER_KERNEL: + case TSA_MITIGATION_VM: + case TSA_MITIGATION_AUTO: + case TSA_MITIGATION_FULL: + /* + * TSA-SQ can potentially lead to info leakage between + * SMT threads. + */ + if (sched_smt_active()) + static_branch_enable(&cpu_buf_idle_clear); + else + static_branch_disable(&cpu_buf_idle_clear); + break; + case TSA_MITIGATION_NONE: + case TSA_MITIGATION_UCODE_NEEDED: + break; + } + + switch (vmscape_mitigation) { + case VMSCAPE_MITIGATION_NONE: + case VMSCAPE_MITIGATION_AUTO: + break; + case VMSCAPE_MITIGATION_IBPB_ON_VMEXIT: + case VMSCAPE_MITIGATION_IBPB_EXIT_TO_USER: + /* + * Hypervisors can be attacked across-threads, warn for SMT when + * STIBP is not already enabled system-wide. + * + * Intel eIBRS (!AUTOIBRS) implies STIBP on. + */ + if (!sched_smt_active() || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED || + (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && + !boot_cpu_has(X86_FEATURE_AUTOIBRS))) + break; + pr_warn_once(VMSCAPE_MSG_SMT); + break; + } + + mutex_unlock(&spec_ctrl_mutex); +} + #ifdef CONFIG_SYSFS #define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion" @@ -3578,6 +3686,11 @@ static ssize_t tsa_show_state(char *buf) return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]); } +static ssize_t vmscape_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", vmscape_strings[vmscape_mitigation]); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -3644,6 +3757,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_TSA: return tsa_show_state(buf); + case X86_BUG_VMSCAPE: + return vmscape_show_state(buf); + default: break; } @@ -3735,6 +3851,11 @@ ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *bu { return cpu_show_common(dev, attr, buf, X86_BUG_TSA); } + +ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_VMSCAPE); +} #endif void __warn_thunk(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 34a054181c4d..f98ec9c7fc07 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1236,55 +1236,71 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define ITS_NATIVE_ONLY BIT(9) /* CPU is affected by Transient Scheduler Attacks */ #define TSA BIT(10) +/* CPU is affected by VMSCAPE */ +#define VMSCAPE BIT(11) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { - VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_HASWELL, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_HASWELL_L, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_HASWELL_G, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_HASWELL_X, X86_STEP_MAX, MMIO), - VULNBL_INTEL_STEPS(INTEL_BROADWELL_D, X86_STEP_MAX, MMIO), - VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO), - VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), - VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED), + VULNBL_INTEL_STEPS(INTEL_SANDYBRIDGE_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SANDYBRIDGE, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_HASWELL, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_HASWELL_L, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_HASWELL_G, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_HASWELL_X, X86_STEP_MAX, MMIO | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_D, X86_STEP_MAX, MMIO | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED | VMSCAPE), VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | VMSCAPE), VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), - VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS), - VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS), - VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS), - VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P, X86_STEP_MAX, RFDS), - VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S, X86_STEP_MAX, RFDS), - VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT, X86_STEP_MAX, RFDS), + VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ALDERLAKE, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS | VMSCAPE), + VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P, X86_STEP_MAX, RFDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S, X86_STEP_MAX, RFDS | VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_METEORLAKE_L, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ARROWLAKE_H, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ARROWLAKE, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ARROWLAKE_U, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_LUNARLAKE_M, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_SAPPHIRERAPIDS_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_GRANITERAPIDS_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_EMERALDRAPIDS_X, X86_STEP_MAX, VMSCAPE), + VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT, X86_STEP_MAX, RFDS | VMSCAPE), VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_D, X86_STEP_MAX, MMIO | RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT, X86_STEP_MAX, RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_D, X86_STEP_MAX, RFDS), VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_CRESTMONT_X, X86_STEP_MAX, VMSCAPE), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), - VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), - VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), - VULNBL_AMD(0x19, SRSO | TSA), - VULNBL_AMD(0x1a, SRSO), + VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO | VMSCAPE), + VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO | VMSCAPE), + VULNBL_AMD(0x19, SRSO | TSA | VMSCAPE), + VULNBL_AMD(0x1a, SRSO | VMSCAPE), {} }; @@ -1543,6 +1559,14 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) } } + /* + * Set the bug only on bare-metal. A nested hypervisor should already be + * deploying IBPB to isolate itself from nested guests. + */ + if (cpu_matches(cpu_vuln_blacklist, VMSCAPE) && + !boot_cpu_has(X86_FEATURE_HYPERVISOR)) + setup_force_cpu_bug(X86_BUG_VMSCAPE); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c index 827dd0dbb6e9..c79ebbb639cb 100644 --- a/arch/x86/kernel/cpu/topology_amd.c +++ b/arch/x86/kernel/cpu/topology_amd.c @@ -175,27 +175,30 @@ static void topoext_fixup(struct topo_scan *tscan) static void parse_topology_amd(struct topo_scan *tscan) { - bool has_topoext = false; - /* - * If the extended topology leaf 0x8000_001e is available - * try to get SMT, CORE, TILE, and DIE shifts from extended + * Try to get SMT, CORE, TILE, and DIE shifts from extended * CPUID leaf 0x8000_0026 on supported processors first. If * extended CPUID leaf 0x8000_0026 is not supported, try to - * get SMT and CORE shift from leaf 0xb first, then try to - * get the CORE shift from leaf 0x8000_0008. + * get SMT and CORE shift from leaf 0xb. If either leaf is + * available, cpu_parse_topology_ext() will return true. */ - if (cpu_feature_enabled(X86_FEATURE_TOPOEXT)) - has_topoext = cpu_parse_topology_ext(tscan); + bool has_xtopology = cpu_parse_topology_ext(tscan); if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES)) tscan->c->topo.cpu_type = cpuid_ebx(0x80000026); - if (!has_topoext && !parse_8000_0008(tscan)) + /* + * If XTOPOLOGY leaves (0x26/0xb) are not available, try to + * get the CORE shift from leaf 0x8000_0008 first. + */ + if (!has_xtopology && !parse_8000_0008(tscan)) return; - /* Prefer leaf 0x8000001e if available */ - if (parse_8000_001e(tscan, has_topoext)) + /* + * Prefer leaf 0x8000001e if available to get the SMT shift and + * the initial APIC ID if XTOPOLOGY leaves are not available. + */ + if (parse_8000_001e(tscan, has_xtopology)) return; /* Try the NODEID MSR */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 604490b1cb19..706b6fd56d3c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11011,6 +11011,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) wrmsrq(MSR_IA32_XFD_ERR, 0); /* + * Mark this CPU as needing a branch predictor flush before running + * userspace. Must be done before enabling preemption to ensure it gets + * set for the CPU that actually ran the guest, and not the CPU that it + * may migrate to. + */ + if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER)) + this_cpu_write(x86_ibpb_exit_to_user, true); + + /* * Consume any pending interrupts, including the possible source of * VM-Exit on SVM and any ticks that occur between VM-Exit and now. * An instruction is required after local_irq_enable() to fully unblock diff --git a/block/fops.c b/block/fops.c index 82451ac8ff25..ddbc69c0922b 100644 --- a/block/fops.c +++ b/block/fops.c @@ -7,6 +7,7 @@ #include <linux/init.h> #include <linux/mm.h> #include <linux/blkdev.h> +#include <linux/blk-integrity.h> #include <linux/buffer_head.h> #include <linux/mpage.h> #include <linux/uio.h> @@ -54,7 +55,6 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct bio bio; ssize_t ret; - WARN_ON_ONCE(iocb->ki_flags & IOCB_HAS_METADATA); if (nr_pages <= DIO_INLINE_BIO_VECS) vecs = inline_vecs; else { @@ -131,7 +131,7 @@ static void blkdev_bio_end_io(struct bio *bio) if (bio->bi_status && !dio->bio.bi_status) dio->bio.bi_status = bio->bi_status; - if (!is_sync && (dio->iocb->ki_flags & IOCB_HAS_METADATA)) + if (bio_integrity(bio)) bio_integrity_unmap_user(bio); if (atomic_dec_and_test(&dio->ref)) { @@ -233,7 +233,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, } bio->bi_opf |= REQ_NOWAIT; } - if (!is_sync && (iocb->ki_flags & IOCB_HAS_METADATA)) { + if (iocb->ki_flags & IOCB_HAS_METADATA) { ret = bio_integrity_map_iter(bio, iocb->private); if (unlikely(ret)) goto fail; @@ -301,7 +301,7 @@ static void blkdev_bio_end_io_async(struct bio *bio) ret = blk_status_to_errno(bio->bi_status); } - if (iocb->ki_flags & IOCB_HAS_METADATA) + if (bio_integrity(bio)) bio_integrity_unmap_user(bio); iocb->ki_complete(iocb, ret); @@ -422,7 +422,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) } nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1); - if (likely(nr_pages <= BIO_MAX_VECS)) { + if (likely(nr_pages <= BIO_MAX_VECS && + !(iocb->ki_flags & IOCB_HAS_METADATA))) { if (is_sync_kiocb(iocb)) return __blkdev_direct_IO_simple(iocb, iter, bdev, nr_pages); @@ -687,6 +688,8 @@ static int blkdev_open(struct inode *inode, struct file *filp) if (bdev_can_atomic_write(bdev)) filp->f_mode |= FMODE_CAN_ATOMIC_WRITE; + if (blk_get_integrity(bdev->bd_disk)) + filp->f_mode |= FMODE_HAS_METADATA; ret = bdev_open(bdev, mode, filp->private_data, NULL, filp); if (ret) diff --git a/crypto/sha1.c b/crypto/sha1.c index ecef4bf2d9c0..4fbf61cf0370 100644 --- a/crypto/sha1.c +++ b/crypto/sha1.c @@ -49,6 +49,18 @@ static int __crypto_sha1_import(struct sha1_ctx *ctx, const void *in) return 0; } +static int __crypto_sha1_export_core(const struct sha1_ctx *ctx, void *out) +{ + memcpy(out, ctx, offsetof(struct sha1_ctx, buf)); + return 0; +} + +static int __crypto_sha1_import_core(struct sha1_ctx *ctx, const void *in) +{ + memcpy(ctx, in, offsetof(struct sha1_ctx, buf)); + return 0; +} + const u8 sha1_zero_message_hash[SHA1_DIGEST_SIZE] = { 0xda, 0x39, 0xa3, 0xee, 0x5e, 0x6b, 0x4b, 0x0d, 0x32, 0x55, 0xbf, 0xef, 0x95, 0x60, 0x18, 0x90, @@ -94,6 +106,16 @@ static int crypto_sha1_import(struct shash_desc *desc, const void *in) return __crypto_sha1_import(SHA1_CTX(desc), in); } +static int crypto_sha1_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha1_export_core(SHA1_CTX(desc), out); +} + +static int crypto_sha1_import_core(struct shash_desc *desc, const void *in) +{ + return __crypto_sha1_import_core(SHA1_CTX(desc), in); +} + #define HMAC_SHA1_KEY(tfm) ((struct hmac_sha1_key *)crypto_shash_ctx(tfm)) #define HMAC_SHA1_CTX(desc) ((struct hmac_sha1_ctx *)shash_desc_ctx(desc)) @@ -143,6 +165,19 @@ static int crypto_hmac_sha1_import(struct shash_desc *desc, const void *in) return __crypto_sha1_import(&ctx->sha_ctx, in); } +static int crypto_hmac_sha1_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha1_export_core(&HMAC_SHA1_CTX(desc)->sha_ctx, out); +} + +static int crypto_hmac_sha1_import_core(struct shash_desc *desc, const void *in) +{ + struct hmac_sha1_ctx *ctx = HMAC_SHA1_CTX(desc); + + ctx->ostate = HMAC_SHA1_KEY(desc->tfm)->ostate; + return __crypto_sha1_import_core(&ctx->sha_ctx, in); +} + static struct shash_alg algs[] = { { .base.cra_name = "sha1", @@ -157,6 +192,8 @@ static struct shash_alg algs[] = { .digest = crypto_sha1_digest, .export = crypto_sha1_export, .import = crypto_sha1_import, + .export_core = crypto_sha1_export_core, + .import_core = crypto_sha1_import_core, .descsize = sizeof(struct sha1_ctx), .statesize = SHA1_SHASH_STATE_SIZE, }, @@ -175,6 +212,8 @@ static struct shash_alg algs[] = { .digest = crypto_hmac_sha1_digest, .export = crypto_hmac_sha1_export, .import = crypto_hmac_sha1_import, + .export_core = crypto_hmac_sha1_export_core, + .import_core = crypto_hmac_sha1_import_core, .descsize = sizeof(struct hmac_sha1_ctx), .statesize = SHA1_SHASH_STATE_SIZE, }, diff --git a/crypto/sha256.c b/crypto/sha256.c index 052806559f06..fb81defe084c 100644 --- a/crypto/sha256.c +++ b/crypto/sha256.c @@ -50,6 +50,19 @@ static int __crypto_sha256_import(struct __sha256_ctx *ctx, const void *in) return 0; } +static int __crypto_sha256_export_core(const struct __sha256_ctx *ctx, + void *out) +{ + memcpy(out, ctx, offsetof(struct __sha256_ctx, buf)); + return 0; +} + +static int __crypto_sha256_import_core(struct __sha256_ctx *ctx, const void *in) +{ + memcpy(ctx, in, offsetof(struct __sha256_ctx, buf)); + return 0; +} + /* SHA-224 */ const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE] = { @@ -98,6 +111,16 @@ static int crypto_sha224_import(struct shash_desc *desc, const void *in) return __crypto_sha256_import(&SHA224_CTX(desc)->ctx, in); } +static int crypto_sha224_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha256_export_core(&SHA224_CTX(desc)->ctx, out); +} + +static int crypto_sha224_import_core(struct shash_desc *desc, const void *in) +{ + return __crypto_sha256_import_core(&SHA224_CTX(desc)->ctx, in); +} + /* SHA-256 */ const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE] = { @@ -146,6 +169,16 @@ static int crypto_sha256_import(struct shash_desc *desc, const void *in) return __crypto_sha256_import(&SHA256_CTX(desc)->ctx, in); } +static int crypto_sha256_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha256_export_core(&SHA256_CTX(desc)->ctx, out); +} + +static int crypto_sha256_import_core(struct shash_desc *desc, const void *in) +{ + return __crypto_sha256_import_core(&SHA256_CTX(desc)->ctx, in); +} + /* HMAC-SHA224 */ #define HMAC_SHA224_KEY(tfm) ((struct hmac_sha224_key *)crypto_shash_ctx(tfm)) @@ -198,6 +231,21 @@ static int crypto_hmac_sha224_import(struct shash_desc *desc, const void *in) return __crypto_sha256_import(&ctx->ctx.sha_ctx, in); } +static int crypto_hmac_sha224_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha256_export_core(&HMAC_SHA224_CTX(desc)->ctx.sha_ctx, + out); +} + +static int crypto_hmac_sha224_import_core(struct shash_desc *desc, + const void *in) +{ + struct hmac_sha224_ctx *ctx = HMAC_SHA224_CTX(desc); + + ctx->ctx.ostate = HMAC_SHA224_KEY(desc->tfm)->key.ostate; + return __crypto_sha256_import_core(&ctx->ctx.sha_ctx, in); +} + /* HMAC-SHA256 */ #define HMAC_SHA256_KEY(tfm) ((struct hmac_sha256_key *)crypto_shash_ctx(tfm)) @@ -250,6 +298,21 @@ static int crypto_hmac_sha256_import(struct shash_desc *desc, const void *in) return __crypto_sha256_import(&ctx->ctx.sha_ctx, in); } +static int crypto_hmac_sha256_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha256_export_core(&HMAC_SHA256_CTX(desc)->ctx.sha_ctx, + out); +} + +static int crypto_hmac_sha256_import_core(struct shash_desc *desc, + const void *in) +{ + struct hmac_sha256_ctx *ctx = HMAC_SHA256_CTX(desc); + + ctx->ctx.ostate = HMAC_SHA256_KEY(desc->tfm)->key.ostate; + return __crypto_sha256_import_core(&ctx->ctx.sha_ctx, in); +} + /* Algorithm definitions */ static struct shash_alg algs[] = { @@ -266,6 +329,8 @@ static struct shash_alg algs[] = { .digest = crypto_sha224_digest, .export = crypto_sha224_export, .import = crypto_sha224_import, + .export_core = crypto_sha224_export_core, + .import_core = crypto_sha224_import_core, .descsize = sizeof(struct sha224_ctx), .statesize = SHA256_SHASH_STATE_SIZE, }, @@ -282,6 +347,8 @@ static struct shash_alg algs[] = { .digest = crypto_sha256_digest, .export = crypto_sha256_export, .import = crypto_sha256_import, + .export_core = crypto_sha256_export_core, + .import_core = crypto_sha256_import_core, .descsize = sizeof(struct sha256_ctx), .statesize = SHA256_SHASH_STATE_SIZE, }, @@ -300,6 +367,8 @@ static struct shash_alg algs[] = { .digest = crypto_hmac_sha224_digest, .export = crypto_hmac_sha224_export, .import = crypto_hmac_sha224_import, + .export_core = crypto_hmac_sha224_export_core, + .import_core = crypto_hmac_sha224_import_core, .descsize = sizeof(struct hmac_sha224_ctx), .statesize = SHA256_SHASH_STATE_SIZE, }, @@ -318,6 +387,8 @@ static struct shash_alg algs[] = { .digest = crypto_hmac_sha256_digest, .export = crypto_hmac_sha256_export, .import = crypto_hmac_sha256_import, + .export_core = crypto_hmac_sha256_export_core, + .import_core = crypto_hmac_sha256_import_core, .descsize = sizeof(struct hmac_sha256_ctx), .statesize = SHA256_SHASH_STATE_SIZE, }, diff --git a/crypto/sha512.c b/crypto/sha512.c index fb1c520978ef..d320fe53913f 100644 --- a/crypto/sha512.c +++ b/crypto/sha512.c @@ -50,6 +50,19 @@ static int __crypto_sha512_import(struct __sha512_ctx *ctx, const void *in) return 0; } +static int __crypto_sha512_export_core(const struct __sha512_ctx *ctx, + void *out) +{ + memcpy(out, ctx, offsetof(struct __sha512_ctx, buf)); + return 0; +} + +static int __crypto_sha512_import_core(struct __sha512_ctx *ctx, const void *in) +{ + memcpy(ctx, in, offsetof(struct __sha512_ctx, buf)); + return 0; +} + /* SHA-384 */ const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE] = { @@ -100,6 +113,16 @@ static int crypto_sha384_import(struct shash_desc *desc, const void *in) return __crypto_sha512_import(&SHA384_CTX(desc)->ctx, in); } +static int crypto_sha384_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha512_export_core(&SHA384_CTX(desc)->ctx, out); +} + +static int crypto_sha384_import_core(struct shash_desc *desc, const void *in) +{ + return __crypto_sha512_import_core(&SHA384_CTX(desc)->ctx, in); +} + /* SHA-512 */ const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE] = { @@ -152,6 +175,16 @@ static int crypto_sha512_import(struct shash_desc *desc, const void *in) return __crypto_sha512_import(&SHA512_CTX(desc)->ctx, in); } +static int crypto_sha512_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha512_export_core(&SHA512_CTX(desc)->ctx, out); +} + +static int crypto_sha512_import_core(struct shash_desc *desc, const void *in) +{ + return __crypto_sha512_import_core(&SHA512_CTX(desc)->ctx, in); +} + /* HMAC-SHA384 */ #define HMAC_SHA384_KEY(tfm) ((struct hmac_sha384_key *)crypto_shash_ctx(tfm)) @@ -204,6 +237,21 @@ static int crypto_hmac_sha384_import(struct shash_desc *desc, const void *in) return __crypto_sha512_import(&ctx->ctx.sha_ctx, in); } +static int crypto_hmac_sha384_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha512_export_core(&HMAC_SHA384_CTX(desc)->ctx.sha_ctx, + out); +} + +static int crypto_hmac_sha384_import_core(struct shash_desc *desc, + const void *in) +{ + struct hmac_sha384_ctx *ctx = HMAC_SHA384_CTX(desc); + + ctx->ctx.ostate = HMAC_SHA384_KEY(desc->tfm)->key.ostate; + return __crypto_sha512_import_core(&ctx->ctx.sha_ctx, in); +} + /* HMAC-SHA512 */ #define HMAC_SHA512_KEY(tfm) ((struct hmac_sha512_key *)crypto_shash_ctx(tfm)) @@ -256,6 +304,21 @@ static int crypto_hmac_sha512_import(struct shash_desc *desc, const void *in) return __crypto_sha512_import(&ctx->ctx.sha_ctx, in); } +static int crypto_hmac_sha512_export_core(struct shash_desc *desc, void *out) +{ + return __crypto_sha512_export_core(&HMAC_SHA512_CTX(desc)->ctx.sha_ctx, + out); +} + +static int crypto_hmac_sha512_import_core(struct shash_desc *desc, + const void *in) +{ + struct hmac_sha512_ctx *ctx = HMAC_SHA512_CTX(desc); + + ctx->ctx.ostate = HMAC_SHA512_KEY(desc->tfm)->key.ostate; + return __crypto_sha512_import_core(&ctx->ctx.sha_ctx, in); +} + /* Algorithm definitions */ static struct shash_alg algs[] = { @@ -272,6 +335,8 @@ static struct shash_alg algs[] = { .digest = crypto_sha384_digest, .export = crypto_sha384_export, .import = crypto_sha384_import, + .export_core = crypto_sha384_export_core, + .import_core = crypto_sha384_import_core, .descsize = sizeof(struct sha384_ctx), .statesize = SHA512_SHASH_STATE_SIZE, }, @@ -288,6 +353,8 @@ static struct shash_alg algs[] = { .digest = crypto_sha512_digest, .export = crypto_sha512_export, .import = crypto_sha512_import, + .export_core = crypto_sha512_export_core, + .import_core = crypto_sha512_import_core, .descsize = sizeof(struct sha512_ctx), .statesize = SHA512_SHASH_STATE_SIZE, }, @@ -306,6 +373,8 @@ static struct shash_alg algs[] = { .digest = crypto_hmac_sha384_digest, .export = crypto_hmac_sha384_export, .import = crypto_hmac_sha384_import, + .export_core = crypto_hmac_sha384_export_core, + .import_core = crypto_hmac_sha384_import_core, .descsize = sizeof(struct hmac_sha384_ctx), .statesize = SHA512_SHASH_STATE_SIZE, }, @@ -324,6 +393,8 @@ static struct shash_alg algs[] = { .digest = crypto_hmac_sha512_digest, .export = crypto_hmac_sha512_export, .import = crypto_hmac_sha512_import, + .export_core = crypto_hmac_sha512_export_core, + .import_core = crypto_hmac_sha512_import_core, .descsize = sizeof(struct hmac_sha512_ctx), .statesize = SHA512_SHASH_STATE_SIZE, }, diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 3d6d52492536..3289751b4757 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -677,7 +677,7 @@ static void ivpu_bo_unbind_all_user_contexts(struct ivpu_device *vdev) static void ivpu_dev_fini(struct ivpu_device *vdev) { ivpu_jobs_abort_all(vdev); - ivpu_pm_cancel_recovery(vdev); + ivpu_pm_disable_recovery(vdev); ivpu_pm_disable(vdev); ivpu_prepare_for_reset(vdev); ivpu_shutdown(vdev); diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index eacda1dbe840..475ddc94f1cf 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -417,10 +417,10 @@ void ivpu_pm_init(struct ivpu_device *vdev) ivpu_dbg(vdev, PM, "Autosuspend delay = %d\n", delay); } -void ivpu_pm_cancel_recovery(struct ivpu_device *vdev) +void ivpu_pm_disable_recovery(struct ivpu_device *vdev) { drm_WARN_ON(&vdev->drm, delayed_work_pending(&vdev->pm->job_timeout_work)); - cancel_work_sync(&vdev->pm->recovery_work); + disable_work_sync(&vdev->pm->recovery_work); } void ivpu_pm_enable(struct ivpu_device *vdev) diff --git a/drivers/accel/ivpu/ivpu_pm.h b/drivers/accel/ivpu/ivpu_pm.h index 89b264cc0e3e..a2aa7a27f32e 100644 --- a/drivers/accel/ivpu/ivpu_pm.h +++ b/drivers/accel/ivpu/ivpu_pm.h @@ -25,7 +25,7 @@ struct ivpu_pm_info { void ivpu_pm_init(struct ivpu_device *vdev); void ivpu_pm_enable(struct ivpu_device *vdev); void ivpu_pm_disable(struct ivpu_device *vdev); -void ivpu_pm_cancel_recovery(struct ivpu_device *vdev); +void ivpu_pm_disable_recovery(struct ivpu_device *vdev); int ivpu_pm_suspend_cb(struct device *dev); int ivpu_pm_resume_cb(struct device *dev); diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 98759d6199d3..65f0f56ad753 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -937,8 +937,10 @@ static u32 *iort_rmr_alloc_sids(u32 *sids, u32 count, u32 id_start, new_sids = krealloc_array(sids, count + new_count, sizeof(*new_sids), GFP_KERNEL); - if (!new_sids) + if (!new_sids) { + kfree(sids); return NULL; + } for (i = count; i < total_count; i++) new_sids[i] = id_start++; diff --git a/drivers/acpi/riscv/cppc.c b/drivers/acpi/riscv/cppc.c index 440cf9fb91aa..42c1a9052470 100644 --- a/drivers/acpi/riscv/cppc.c +++ b/drivers/acpi/riscv/cppc.c @@ -119,7 +119,7 @@ int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val) *val = data.ret.value; - return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0; + return data.ret.error; } return -EINVAL; @@ -148,7 +148,7 @@ int cpc_write_ffh(int cpu, struct cpc_reg *reg, u64 val) smp_call_function_single(cpu, cppc_ffh_csr_write, &data, 1); - return (data.ret.error) ? sbi_err_map_linux_errno(data.ret.error) : 0; + return data.ret.error; } return -EINVAL; diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index efc575a00edd..008da0354fba 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -603,6 +603,7 @@ CPU_SHOW_VULN_FALLBACK(ghostwrite); CPU_SHOW_VULN_FALLBACK(old_microcode); CPU_SHOW_VULN_FALLBACK(indirect_target_selection); CPU_SHOW_VULN_FALLBACK(tsa); +CPU_SHOW_VULN_FALLBACK(vmscape); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -622,6 +623,7 @@ static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL); static DEVICE_ATTR(old_microcode, 0444, cpu_show_old_microcode, NULL); static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL); static DEVICE_ATTR(tsa, 0444, cpu_show_tsa, NULL); +static DEVICE_ATTR(vmscape, 0444, cpu_show_vmscape, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -642,6 +644,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_old_microcode.attr, &dev_attr_indirect_target_selection.attr, &dev_attr_tsa.attr, + &dev_attr_vmscape.attr, NULL }; diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index f7d8c3c00655..2fef08254d78 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -380,6 +380,28 @@ static const struct file_operations force_devcoredump_fops = { .write = force_devcd_write, }; +static void vhci_debugfs_init(struct vhci_data *data) +{ + struct hci_dev *hdev = data->hdev; + + debugfs_create_file("force_suspend", 0644, hdev->debugfs, data, + &force_suspend_fops); + + debugfs_create_file("force_wakeup", 0644, hdev->debugfs, data, + &force_wakeup_fops); + + if (IS_ENABLED(CONFIG_BT_MSFTEXT)) + debugfs_create_file("msft_opcode", 0644, hdev->debugfs, data, + &msft_opcode_fops); + + if (IS_ENABLED(CONFIG_BT_AOSPEXT)) + debugfs_create_file("aosp_capable", 0644, hdev->debugfs, data, + &aosp_capable_fops); + + debugfs_create_file("force_devcoredump", 0644, hdev->debugfs, data, + &force_devcoredump_fops); +} + static int __vhci_create_device(struct vhci_data *data, __u8 opcode) { struct hci_dev *hdev; @@ -434,22 +456,8 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode) return -EBUSY; } - debugfs_create_file("force_suspend", 0644, hdev->debugfs, data, - &force_suspend_fops); - - debugfs_create_file("force_wakeup", 0644, hdev->debugfs, data, - &force_wakeup_fops); - - if (IS_ENABLED(CONFIG_BT_MSFTEXT)) - debugfs_create_file("msft_opcode", 0644, hdev->debugfs, data, - &msft_opcode_fops); - - if (IS_ENABLED(CONFIG_BT_AOSPEXT)) - debugfs_create_file("aosp_capable", 0644, hdev->debugfs, data, - &aosp_capable_fops); - - debugfs_create_file("force_devcoredump", 0644, hdev->debugfs, data, - &force_devcoredump_fops); + if (!IS_ERR_OR_NULL(hdev->debugfs)) + vhci_debugfs_init(data); hci_skb_pkt_type(skb) = HCI_VENDOR_PKT; @@ -651,6 +659,21 @@ static int vhci_open(struct inode *inode, struct file *file) return 0; } +static void vhci_debugfs_remove(struct hci_dev *hdev) +{ + debugfs_lookup_and_remove("force_suspend", hdev->debugfs); + + debugfs_lookup_and_remove("force_wakeup", hdev->debugfs); + + if (IS_ENABLED(CONFIG_BT_MSFTEXT)) + debugfs_lookup_and_remove("msft_opcode", hdev->debugfs); + + if (IS_ENABLED(CONFIG_BT_AOSPEXT)) + debugfs_lookup_and_remove("aosp_capable", hdev->debugfs); + + debugfs_lookup_and_remove("force_devcoredump", hdev->debugfs); +} + static int vhci_release(struct inode *inode, struct file *file) { struct vhci_data *data = file->private_data; @@ -662,6 +685,8 @@ static int vhci_release(struct inode *inode, struct file *file) hdev = data->hdev; if (hdev) { + if (!IS_ERR_OR_NULL(hdev->debugfs)) + vhci_debugfs_remove(hdev); hci_unregister_dev(hdev); hci_free_dev(hdev); } diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c index bbc27ef9edf7..b4c79fde1979 100644 --- a/drivers/cpufreq/amd-pstate.c +++ b/drivers/cpufreq/amd-pstate.c @@ -1554,13 +1554,15 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy) pr_debug("CPU %d exiting\n", policy->cpu); } -static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy) +static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy, bool policy_change) { struct amd_cpudata *cpudata = policy->driver_data; union perf_cached perf; u8 epp; - if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq) + if (policy_change || + policy->min != cpudata->min_limit_freq || + policy->max != cpudata->max_limit_freq) amd_pstate_update_min_max_limit(policy); if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) @@ -1584,7 +1586,7 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy) cpudata->policy = policy->policy; - ret = amd_pstate_epp_update_limit(policy); + ret = amd_pstate_epp_update_limit(policy, true); if (ret) return ret; @@ -1626,13 +1628,14 @@ static int amd_pstate_suspend(struct cpufreq_policy *policy) * min_perf value across kexec reboots. If this CPU is just resumed back without kexec, * the limits, epp and desired perf will get reset to the cached values in cpudata struct */ - ret = amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false); + ret = amd_pstate_update_perf(policy, perf.bios_min_perf, + FIELD_GET(AMD_CPPC_DES_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached), + FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached), + false); if (ret) return ret; - /* invalidate to ensure it's rewritten during resume */ - cpudata->cppc_req_cached = 0; - /* set this flag to avoid setting core offline*/ cpudata->suspended = true; @@ -1658,7 +1661,7 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy) int ret; /* enable amd pstate from suspend state*/ - ret = amd_pstate_epp_update_limit(policy); + ret = amd_pstate_epp_update_limit(policy, false); if (ret) return ret; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index f366d35c5840..0d5d283a5429 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1034,8 +1034,8 @@ static bool hybrid_register_perf_domain(unsigned int cpu) if (!cpu_dev) return false; - if (em_dev_register_perf_domain(cpu_dev, HYBRID_EM_STATE_COUNT, &cb, - cpumask_of(cpu), false)) + if (em_dev_register_pd_no_update(cpu_dev, HYBRID_EM_STATE_COUNT, &cb, + cpumask_of(cpu), false)) return false; cpudata->pd_registered = true; diff --git a/drivers/dma/dw/rzn1-dmamux.c b/drivers/dma/dw/rzn1-dmamux.c index 4fb8508419db..deadf135681b 100644 --- a/drivers/dma/dw/rzn1-dmamux.c +++ b/drivers/dma/dw/rzn1-dmamux.c @@ -48,12 +48,16 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, u32 mask; int ret; - if (dma_spec->args_count != RNZ1_DMAMUX_NCELLS) - return ERR_PTR(-EINVAL); + if (dma_spec->args_count != RNZ1_DMAMUX_NCELLS) { + ret = -EINVAL; + goto put_device; + } map = kzalloc(sizeof(*map), GFP_KERNEL); - if (!map) - return ERR_PTR(-ENOMEM); + if (!map) { + ret = -ENOMEM; + goto put_device; + } chan = dma_spec->args[0]; map->req_idx = dma_spec->args[4]; @@ -94,12 +98,15 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (ret) goto clear_bitmap; + put_device(&pdev->dev); return map; clear_bitmap: clear_bit(map->req_idx, dmamux->used_chans); free_map: kfree(map); +put_device: + put_device(&pdev->dev); return ERR_PTR(ret); } diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 35bdefd3728b..8c4725ad1f64 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -189,27 +189,30 @@ static int idxd_setup_wqs(struct idxd_device *idxd) idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev)); if (!idxd->wq_enable_map) { rc = -ENOMEM; - goto err_bitmap; + goto err_free_wqs; } for (i = 0; i < idxd->max_wqs; i++) { wq = kzalloc_node(sizeof(*wq), GFP_KERNEL, dev_to_node(dev)); if (!wq) { rc = -ENOMEM; - goto err; + goto err_unwind; } idxd_dev_set_type(&wq->idxd_dev, IDXD_DEV_WQ); conf_dev = wq_confdev(wq); wq->id = i; wq->idxd = idxd; - device_initialize(wq_confdev(wq)); + device_initialize(conf_dev); conf_dev->parent = idxd_confdev(idxd); conf_dev->bus = &dsa_bus_type; conf_dev->type = &idxd_wq_device_type; rc = dev_set_name(conf_dev, "wq%d.%d", idxd->id, wq->id); - if (rc < 0) - goto err; + if (rc < 0) { + put_device(conf_dev); + kfree(wq); + goto err_unwind; + } mutex_init(&wq->wq_lock); init_waitqueue_head(&wq->err_queue); @@ -220,15 +223,20 @@ static int idxd_setup_wqs(struct idxd_device *idxd) wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev)); if (!wq->wqcfg) { + put_device(conf_dev); + kfree(wq); rc = -ENOMEM; - goto err; + goto err_unwind; } if (idxd->hw.wq_cap.op_config) { wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL); if (!wq->opcap_bmap) { + kfree(wq->wqcfg); + put_device(conf_dev); + kfree(wq); rc = -ENOMEM; - goto err_opcap_bmap; + goto err_unwind; } bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS); } @@ -239,13 +247,7 @@ static int idxd_setup_wqs(struct idxd_device *idxd) return 0; -err_opcap_bmap: - kfree(wq->wqcfg); - -err: - put_device(conf_dev); - kfree(wq); - +err_unwind: while (--i >= 0) { wq = idxd->wqs[i]; if (idxd->hw.wq_cap.op_config) @@ -254,11 +256,10 @@ err: conf_dev = wq_confdev(wq); put_device(conf_dev); kfree(wq); - } bitmap_free(idxd->wq_enable_map); -err_bitmap: +err_free_wqs: kfree(idxd->wqs); return rc; @@ -1291,10 +1292,12 @@ static void idxd_remove(struct pci_dev *pdev) device_unregister(idxd_confdev(idxd)); idxd_shutdown(pdev); idxd_device_remove_debugfs(idxd); - idxd_cleanup(idxd); + perfmon_pmu_remove(idxd); + idxd_cleanup_interrupts(idxd); + if (device_pasid_enabled(idxd)) + idxd_disable_system_pasid(idxd); pci_iounmap(pdev, idxd->reg_base); put_device(idxd_confdev(idxd)); - idxd_free(idxd); pci_disable_device(pdev); } diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c index bbc3276992bb..2cf060174795 100644 --- a/drivers/dma/qcom/bam_dma.c +++ b/drivers/dma/qcom/bam_dma.c @@ -1283,13 +1283,17 @@ static int bam_dma_probe(struct platform_device *pdev) if (!bdev->bamclk) { ret = of_property_read_u32(pdev->dev.of_node, "num-channels", &bdev->num_channels); - if (ret) + if (ret) { dev_err(bdev->dev, "num-channels unspecified in dt\n"); + return ret; + } ret = of_property_read_u32(pdev->dev.of_node, "qcom,num-ees", &bdev->num_ees); - if (ret) + if (ret) { dev_err(bdev->dev, "num-ees unspecified in dt\n"); + return ret; + } } ret = clk_prepare_enable(bdev->bamclk); diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index 3ed406f08c44..552be71db6c4 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -2064,8 +2064,8 @@ static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata, * priority. So Q0 is the highest priority queue and the last queue has * the lowest priority. */ - queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1, sizeof(s8), - GFP_KERNEL); + queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1, + sizeof(*queue_priority_map), GFP_KERNEL); if (!queue_priority_map) return -ENOMEM; diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index cae52c654a15..7685a8550d4b 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -128,7 +128,6 @@ static ssize_t altr_sdr_mc_err_inject_write(struct file *file, ptemp = dma_alloc_coherent(mci->pdev, 16, &dma_handle, GFP_KERNEL); if (!ptemp) { - dma_free_coherent(mci->pdev, 16, ptemp, dma_handle); edac_printk(KERN_ERR, EDAC_MC, "Inject: Buffer Allocation error\n"); return -ENOMEM; diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index e43abb322fa6..d8ac40d0eb6f 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -3,6 +3,9 @@ # GPIO infrastructure and drivers # +config GPIOLIB_LEGACY + def_bool y + menuconfig GPIOLIB bool "GPIO Support" help @@ -12,9 +15,6 @@ menuconfig GPIOLIB If unsure, say N. -config GPIOLIB_LEGACY - def_bool y - if GPIOLIB config GPIOLIB_FASTPATH_LIMIT diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 260165bbe373..b16cce7c22c3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -213,19 +213,35 @@ int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev, spin_lock(&kfd_mem_limit.mem_limit_lock); if (kfd_mem_limit.system_mem_used + system_mem_needed > - kfd_mem_limit.max_system_mem_limit) + kfd_mem_limit.max_system_mem_limit) { pr_debug("Set no_system_mem_limit=1 if using shared memory\n"); + if (!no_system_mem_limit) { + ret = -ENOMEM; + goto release; + } + } - if ((kfd_mem_limit.system_mem_used + system_mem_needed > - kfd_mem_limit.max_system_mem_limit && !no_system_mem_limit) || - (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > - kfd_mem_limit.max_ttm_mem_limit) || - (adev && xcp_id >= 0 && adev->kfd.vram_used[xcp_id] + vram_needed > - vram_size - reserved_for_pt - reserved_for_ras - atomic64_read(&adev->vram_pin_size))) { + if (kfd_mem_limit.ttm_mem_used + ttm_mem_needed > + kfd_mem_limit.max_ttm_mem_limit) { ret = -ENOMEM; goto release; } + /*if is_app_apu is false and apu_prefer_gtt is true, it is an APU with + * carve out < gtt. In that case, VRAM allocation will go to gtt domain, skip + * VRAM check since ttm_mem_limit check already cover this allocation + */ + + if (adev && xcp_id >= 0 && (!adev->apu_prefer_gtt || adev->gmc.is_app_apu)) { + uint64_t vram_available = + vram_size - reserved_for_pt - reserved_for_ras - + atomic64_read(&adev->vram_pin_size); + if (adev->kfd.vram_used[xcp_id] + vram_needed > vram_available) { + ret = -ENOMEM; + goto release; + } + } + /* Update memory accounting by decreasing available system * memory, TTM memory and GPU memory as computed above */ @@ -1626,11 +1642,15 @@ size_t amdgpu_amdkfd_get_available_memory(struct amdgpu_device *adev, uint64_t vram_available, system_mem_available, ttm_mem_available; spin_lock(&kfd_mem_limit.mem_limit_lock); - vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) - - adev->kfd.vram_used_aligned[xcp_id] - - atomic64_read(&adev->vram_pin_size) - - reserved_for_pt - - reserved_for_ras; + if (adev->apu_prefer_gtt && !adev->gmc.is_app_apu) + vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) + - adev->kfd.vram_used_aligned[xcp_id]; + else + vram_available = KFD_XCP_MEMORY_SIZE(adev, xcp_id) + - adev->kfd.vram_used_aligned[xcp_id] + - atomic64_read(&adev->vram_pin_size) + - reserved_for_pt + - reserved_for_ras; if (adev->apu_prefer_gtt) { system_mem_available = no_system_mem_limit ? diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 23484317a5fa..693357caa9a8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -448,7 +448,7 @@ static int psp_sw_init(struct amdgpu_ip_block *ip_block) psp->cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL); if (!psp->cmd) { dev_err(adev->dev, "Failed to allocate memory to command buffer!\n"); - ret = -ENOMEM; + return -ENOMEM; } adev->psp.xgmi_context.supports_extended_data = diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 6379bb25bf5c..486c3646710c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -421,8 +421,6 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) dma_fence_put(ring->vmid_wait); ring->vmid_wait = NULL; ring->me = 0; - - ring->adev->rings[ring->idx] = NULL; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c index bf7c22f81cda..ba73518f5cdf 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c @@ -1462,17 +1462,12 @@ static int dce_v10_0_audio_init(struct amdgpu_device *adev) static void dce_v10_0_audio_fini(struct amdgpu_device *adev) { - int i; - if (!amdgpu_audio) return; if (!adev->mode_info.audio.enabled) return; - for (i = 0; i < adev->mode_info.audio.num_pins; i++) - dce_v10_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - adev->mode_info.audio.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c index 47e05783c4a0..b01d88d078fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c @@ -1511,17 +1511,12 @@ static int dce_v11_0_audio_init(struct amdgpu_device *adev) static void dce_v11_0_audio_fini(struct amdgpu_device *adev) { - int i; - if (!amdgpu_audio) return; if (!adev->mode_info.audio.enabled) return; - for (i = 0; i < adev->mode_info.audio.num_pins; i++) - dce_v11_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - adev->mode_info.audio.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c index 276c025c4c03..81760a26f2ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c @@ -1451,17 +1451,12 @@ static int dce_v6_0_audio_init(struct amdgpu_device *adev) static void dce_v6_0_audio_fini(struct amdgpu_device *adev) { - int i; - if (!amdgpu_audio) return; if (!adev->mode_info.audio.enabled) return; - for (i = 0; i < adev->mode_info.audio.num_pins; i++) - dce_v6_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - adev->mode_info.audio.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c index e62ccf9eb73d..19a265bd4d19 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c @@ -1443,17 +1443,12 @@ static int dce_v8_0_audio_init(struct amdgpu_device *adev) static void dce_v8_0_audio_fini(struct amdgpu_device *adev) { - int i; - if (!amdgpu_audio) return; if (!adev->mode_info.audio.enabled) return; - for (i = 0; i < adev->mode_info.audio.num_pins; i++) - dce_v8_0_audio_enable(adev, &adev->mode_info.audio.pin[i], false); - adev->mode_info.audio.enabled = false; } diff --git a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c index a887df520414..4258d3e0b706 100644 --- a/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c +++ b/drivers/gpu/drm/amd/amdgpu/isp_v4_1_1.c @@ -29,6 +29,8 @@ #include "amdgpu.h" #include "isp_v4_1_1.h" +MODULE_FIRMWARE("amdgpu/isp_4_1_1.bin"); + #define ISP_PERFORMANCE_STATE_LOW 0 #define ISP_PERFORMANCE_STATE_HIGH 1 diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 28eb846280dd..3f6a828cad8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -641,8 +641,9 @@ static int mes_v11_0_misc_op(struct amdgpu_mes *mes, break; case MES_MISC_OP_CHANGE_CONFIG: if ((mes->adev->mes.sched_version & AMDGPU_MES_VERSION_MASK) < 0x63) { - dev_err(mes->adev->dev, "MES FW version must be larger than 0x63 to support limit single process feature.\n"); - return -EINVAL; + dev_warn_once(mes->adev->dev, + "MES FW version must be larger than 0x63 to support limit single process feature.\n"); + return 0; } misc_pkt.opcode = MESAPI_MISC__CHANGE_CONFIG; misc_pkt.change_config.opcode = diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 6cc05d36e359..64b240b51f1a 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -149,12 +149,12 @@ static int psp_v11_0_wait_for_bootloader(struct psp_context *psp) int ret; int retry_loop; - for (retry_loop = 0; retry_loop < 10; retry_loop++) { + for (retry_loop = 0; retry_loop < 20; retry_loop++) { /* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */ ret = psp_wait_for( psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35), - 0x80000000, 0x80000000, PSP_WAITREG_NOVERBOSE); + 0x80000000, 0x8000FFFF, PSP_WAITREG_NOVERBOSE); if (ret == 0) return 0; @@ -397,18 +397,6 @@ static int psp_v11_0_mode1_reset(struct psp_context *psp) msleep(500); - offset = SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_33); - - ret = psp_wait_for(psp, offset, MBOX_TOS_RESP_FLAG, MBOX_TOS_RESP_MASK, - 0); - - if (ret) { - DRM_INFO("psp mode 1 reset failed!\n"); - return -EINVAL; - } - - DRM_INFO("psp mode1 reset succeed \n"); - return 0; } @@ -665,7 +653,8 @@ static const struct psp_funcs psp_v11_0_funcs = { .ring_get_wptr = psp_v11_0_ring_get_wptr, .ring_set_wptr = psp_v11_0_ring_set_wptr, .load_usbc_pd_fw = psp_v11_0_load_usbc_pd_fw, - .read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw + .read_usbc_pd_fw = psp_v11_0_read_usbc_pd_fw, + .wait_for_bootloader = psp_v11_0_wait_for_bootloader }; void psp_v11_0_set_psp_funcs(struct psp_context *psp) diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c index e6d8eddda2bf..db6e41967f12 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c @@ -1377,7 +1377,7 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) { case IP_VERSION(6, 0, 0): - if ((adev->sdma.instance[0].fw_version >= 24) && !adev->sdma.disable_uq) + if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 0, 1): @@ -1385,11 +1385,11 @@ static int sdma_v6_0_sw_init(struct amdgpu_ip_block *ip_block) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 0, 2): - if ((adev->sdma.instance[0].fw_version >= 21) && !adev->sdma.disable_uq) + if ((adev->sdma.instance[0].fw_version >= 23) && !adev->sdma.disable_uq) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 0, 3): - if ((adev->sdma.instance[0].fw_version >= 25) && !adev->sdma.disable_uq) + if ((adev->sdma.instance[0].fw_version >= 27) && !adev->sdma.disable_uq) adev->userq_funcs[AMDGPU_HW_IP_DMA] = &userq_mes_funcs; break; case IP_VERSION(6, 1, 0): diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 4b8f4407047f..2811226b0ea5 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1888,15 +1888,19 @@ static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] [AMDGPU_RING_PRIO_DEFAULT].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 1924e075b66f..706f3b2f484f 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1808,15 +1808,19 @@ static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence; /* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL; + /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] [AMDGPU_RING_PRIO_0].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); @@ -1907,22 +1911,16 @@ out: #define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002) #define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) - #define RADEON_VCN_ENGINE_INFO (0x30000001) -#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16 - #define RENCODE_ENCODE_STANDARD_AV1 2 #define RENCODE_IB_PARAM_SESSION_INIT 0x00000003 -#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64 -/* return the offset in ib if id is found, -1 otherwise - * to speed up the searching we only search upto max_offset - */ -static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset) +/* return the offset in ib if id is found, -1 otherwise */ +static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int start) { int i; - for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) { + for (i = start; i < ib->length_dw && ib->ptr[i] >= 8; i += ib->ptr[i] / 4) { if (ib->ptr[i + 1] == id) return i; } @@ -1937,33 +1935,29 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_vcn_decode_buffer *decode_buffer; uint64_t addr; uint32_t val; - int idx; + int idx = 0, sidx; /* The first instance can decode anything */ if (!ring->me) return 0; - /* RADEON_VCN_ENGINE_INFO is at the top of ib block */ - idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, - RADEON_VCN_ENGINE_INFO_MAX_OFFSET); - if (idx < 0) /* engine info is missing */ - return 0; - - val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ - if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; - - if (!(decode_buffer->valid_buf_flag & 0x1)) - return 0; - - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_dec_msg(p, job, addr); - } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { - idx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, - RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET); - if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1) - return vcn_v4_0_limit_sched(p, job); + while ((idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, idx)) >= 0) { + val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ + if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { + decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; + + if (!(decode_buffer->valid_buf_flag & 0x1)) + return 0; + + addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | + decode_buffer->msg_buffer_address_lo; + return vcn_v4_0_dec_msg(p, job, addr); + } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { + sidx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, idx); + if (sidx >= 0 && ib->ptr[sidx + 2] == RENCODE_ENCODE_STANDARD_AV1) + return vcn_v4_0_limit_sched(p, job); + } + idx += ib->ptr[idx] / 4; } return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 4ec73f33535e..720b20e842ba 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -1587,7 +1587,8 @@ static int kfd_dev_create_p2p_links(void) break; if (!dev->gpu || !dev->gpu->adev || (dev->gpu->kfd->hive_id && - dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id)) + dev->gpu->kfd->hive_id == new_dev->gpu->kfd->hive_id && + amdgpu_xgmi_get_is_sharing_enabled(dev->gpu->adev, new_dev->gpu->adev))) goto next; /* check if node(s) is/are peer accessible in one direction or bi-direction */ 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 a0ca3b2c6bd8..4e86370ae705 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2913,6 +2913,17 @@ static int dm_oem_i2c_hw_init(struct amdgpu_device *adev) return 0; } +static void dm_oem_i2c_hw_fini(struct amdgpu_device *adev) +{ + struct amdgpu_display_manager *dm = &adev->dm; + + if (dm->oem_i2c) { + i2c_del_adapter(&dm->oem_i2c->base); + kfree(dm->oem_i2c); + dm->oem_i2c = NULL; + } +} + /** * dm_hw_init() - Initialize DC device * @ip_block: Pointer to the amdgpu_ip_block for this hw instance. @@ -2963,7 +2974,7 @@ static int dm_hw_fini(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; - kfree(adev->dm.oem_i2c); + dm_oem_i2c_hw_fini(adev); amdgpu_dm_hpd_fini(adev); @@ -3127,25 +3138,6 @@ static void dm_destroy_cached_state(struct amdgpu_device *adev) dm->cached_state = NULL; } -static void dm_complete(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - dm_destroy_cached_state(adev); -} - -static int dm_prepare_suspend(struct amdgpu_ip_block *ip_block) -{ - struct amdgpu_device *adev = ip_block->adev; - - if (amdgpu_in_reset(adev)) - return 0; - - WARN_ON(adev->dm.cached_state); - - return dm_cache_state(adev); -} - static int dm_suspend(struct amdgpu_ip_block *ip_block) { struct amdgpu_device *adev = ip_block->adev; @@ -3571,10 +3563,8 @@ static const struct amd_ip_funcs amdgpu_dm_funcs = { .early_fini = amdgpu_dm_early_fini, .hw_init = dm_hw_init, .hw_fini = dm_hw_fini, - .prepare_suspend = dm_prepare_suspend, .suspend = dm_suspend, .resume = dm_resume, - .complete = dm_complete, .is_idle = dm_is_idle, .wait_for_idle = dm_wait_for_idle, .check_soft_reset = dm_check_soft_reset, @@ -8381,8 +8371,7 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector) drm_add_modes_noedid(connector, 1920, 1080); } else { amdgpu_dm_connector_ddc_get_modes(connector, drm_edid); - if (encoder && (connector->connector_type != DRM_MODE_CONNECTOR_eDP) && - (connector->connector_type != DRM_MODE_CONNECTOR_LVDS)) + if (encoder) amdgpu_dm_connector_add_common_modes(encoder, connector); amdgpu_dm_connector_add_freesync_modes(connector, drm_edid); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 7187d5aedf0a..77a9d2c7d318 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -809,6 +809,7 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm, drm_dp_aux_init(&aconnector->dm_dp_aux.aux); drm_dp_cec_register_connector(&aconnector->dm_dp_aux.aux, &aconnector->base); + drm_dp_dpcd_set_probe(&aconnector->dm_dp_aux.aux, false); if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_eDP) return; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 59c07756130d..f24e1da68269 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -1145,6 +1145,7 @@ struct dc_debug_options { bool enable_hblank_borrow; bool force_subvp_df_throttle; uint32_t acpi_transition_bitmasks[MAX_PIPES]; + bool enable_pg_cntl_debug_logs; }; diff --git a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c index 58c84f555c0f..0ce9489ac6b7 100644 --- a/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dccg/dcn35/dcn35_dccg.c @@ -133,30 +133,34 @@ enum dsc_clk_source { }; -static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool enable) +static void dccg35_set_dsc_clk_rcg(struct dccg *dccg, int inst, bool allow_rcg) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && enable) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dsc && allow_rcg) return; switch (inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; default: BREAK_TO_DEBUGGER(); return; } + + /* Wait for clock to ramp */ + if (!allow_rcg) + udelay(10); } static void dccg35_set_symclk32_se_rcg( @@ -385,35 +389,34 @@ static void dccg35_set_dtbclk_p_rcg(struct dccg *dccg, int inst, bool enable) } } -static void dccg35_set_dppclk_rcg(struct dccg *dccg, - int inst, bool enable) +static void dccg35_set_dppclk_rcg(struct dccg *dccg, int inst, bool allow_rcg) { - struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && enable) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && allow_rcg) return; switch (inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable ? 0 : 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, allow_rcg ? 0 : 1); break; default: BREAK_TO_DEBUGGER(); break; } - //DC_LOG_DEBUG("%s: inst(%d) DPPCLK rcg_disable: %d\n", __func__, inst, enable ? 0 : 1); + /* Wait for clock to ramp */ + if (!allow_rcg) + udelay(10); } static void dccg35_set_dpstreamclk_rcg( @@ -1177,32 +1180,34 @@ static void dccg35_update_dpp_dto(struct dccg *dccg, int dpp_inst, } static void dccg35_set_dppclk_root_clock_gating(struct dccg *dccg, - uint32_t dpp_inst, uint32_t enable) + uint32_t dpp_inst, uint32_t disallow_rcg) { struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); - if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) + if (!dccg->ctx->dc->debug.root_clock_optimization.bits.dpp && !disallow_rcg) return; switch (dpp_inst) { case 0: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK0_ROOT_GATE_DISABLE, disallow_rcg); break; case 1: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK1_ROOT_GATE_DISABLE, disallow_rcg); break; case 2: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK2_ROOT_GATE_DISABLE, disallow_rcg); break; case 3: - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, enable); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DPPCLK3_ROOT_GATE_DISABLE, disallow_rcg); break; default: break; } - //DC_LOG_DEBUG("%s: dpp_inst(%d) rcg: %d\n", __func__, dpp_inst, enable); + /* Wait for clock to ramp */ + if (disallow_rcg) + udelay(10); } static void dccg35_get_pixel_rate_div( @@ -1782,8 +1787,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) //Disable DTO switch (inst) { case 0: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK0_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK0_DTO_PARAM, DSCCLK0_DTO_PHASE, 0, @@ -1791,8 +1795,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK0_EN, 1); break; case 1: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK1_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK1_DTO_PARAM, DSCCLK1_DTO_PHASE, 0, @@ -1800,8 +1803,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK1_EN, 1); break; case 2: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK2_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK2_DTO_PARAM, DSCCLK2_DTO_PHASE, 0, @@ -1809,8 +1811,7 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) REG_UPDATE(DSCCLK_DTO_CTRL, DSCCLK2_EN, 1); break; case 3: - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dsc) - REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1); + REG_UPDATE(DCCG_GATE_DISABLE_CNTL6, DSCCLK3_ROOT_GATE_DISABLE, 1); REG_UPDATE_2(DSCCLK3_DTO_PARAM, DSCCLK3_DTO_PHASE, 0, @@ -1821,6 +1822,9 @@ static void dccg35_enable_dscclk(struct dccg *dccg, int inst) BREAK_TO_DEBUGGER(); return; } + + /* Wait for clock to ramp */ + udelay(10); } static void dccg35_disable_dscclk(struct dccg *dccg, @@ -1864,6 +1868,9 @@ static void dccg35_disable_dscclk(struct dccg *dccg, default: return; } + + /* Wait for clock ramp */ + udelay(10); } static void dccg35_enable_symclk_se(struct dccg *dccg, uint32_t stream_enc_inst, uint32_t link_enc_inst) @@ -2349,10 +2356,7 @@ static void dccg35_disable_symclk_se_cb( void dccg35_root_gate_disable_control(struct dccg *dccg, uint32_t pipe_idx, uint32_t disable_clock_gating) { - - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) { - dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating); - } + dccg35_set_dppclk_root_clock_gating(dccg, pipe_idx, disable_clock_gating); } static const struct dccg_funcs dccg35_funcs_new = { diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c index 75fb77bca83b..01480a04f85e 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.c @@ -520,6 +520,15 @@ void dpp1_dppclk_control( REG_UPDATE(DPP_CONTROL, DPP_CLOCK_ENABLE, 0); } +void dpp_force_disable_cursor(struct dpp *dpp_base) +{ + struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base); + + /* Force disable cursor */ + REG_UPDATE(CURSOR0_CONTROL, CUR0_ENABLE, 0); + dpp_base->pos.cur0_ctl.bits.cur0_enable = 0; +} + static const struct dpp_funcs dcn10_dpp_funcs = { .dpp_read_state = dpp_read_state, .dpp_reset = dpp_reset, diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h index c48139bed11f..f466182963f7 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn10/dcn10_dpp.h @@ -1525,4 +1525,6 @@ void dpp1_construct(struct dcn10_dpp *dpp1, void dpp1_cm_get_gamut_remap(struct dpp *dpp_base, struct dpp_grph_csc_adjustment *adjust); +void dpp_force_disable_cursor(struct dpp *dpp_base); + #endif diff --git a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c index 2d70586cef40..09be2a90cc79 100644 --- a/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dpp/dcn30/dcn30_dpp.c @@ -1494,6 +1494,7 @@ static struct dpp_funcs dcn30_dpp_funcs = { .dpp_dppclk_control = dpp1_dppclk_control, .dpp_set_hdr_multiplier = dpp3_set_hdr_multiplier, .dpp_get_gamut_remap = dpp3_cm_get_gamut_remap, + .dpp_force_disable_cursor = dpp_force_disable_cursor, }; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 3207addbd4eb..b7c2d3095b25 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -955,7 +955,7 @@ enum dc_status dcn20_enable_stream_timing( return DC_ERROR_UNEXPECTED; } - fsleep(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); + udelay(stream->timing.v_total * (stream->timing.h_total * 10000u / stream->timing.pix_clk_100hz)); params.vertical_total_min = stream->adjust.v_total_min; params.vertical_total_max = stream->adjust.v_total_max; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c index e68f21fd5f0f..560984533950 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.c @@ -528,3 +528,75 @@ void dcn314_disable_link_output(struct dc_link *link, apply_symclk_on_tx_off_wa(link); } + +/** + * dcn314_dpp_pg_control - DPP power gate control. + * + * @hws: dce_hwseq reference. + * @dpp_inst: DPP instance reference. + * @power_on: true if we want to enable power gate, false otherwise. + * + * Enable or disable power gate in the specific DPP instance. + * If power gating is disabled, will force disable cursor in the DPP instance. + */ +void dcn314_dpp_pg_control( + struct dce_hwseq *hws, + unsigned int dpp_inst, + bool power_on) +{ + uint32_t power_gate = power_on ? 0 : 1; + uint32_t pwr_status = power_on ? 0 : 2; + + + if (hws->ctx->dc->debug.disable_dpp_power_gate) { + /* Workaround for DCN314 with disabled power gating */ + if (!power_on) { + + /* Force disable cursor if power gating is disabled */ + struct dpp *dpp = hws->ctx->dc->res_pool->dpps[dpp_inst]; + if (dpp && dpp->funcs->dpp_force_disable_cursor) + dpp->funcs->dpp_force_disable_cursor(dpp); + } + return; + } + if (REG(DOMAIN1_PG_CONFIG) == 0) + return; + + switch (dpp_inst) { + case 0: /* DPP0 */ + REG_UPDATE(DOMAIN1_PG_CONFIG, + DOMAIN1_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN1_PG_STATUS, + DOMAIN1_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + case 1: /* DPP1 */ + REG_UPDATE(DOMAIN3_PG_CONFIG, + DOMAIN3_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN3_PG_STATUS, + DOMAIN3_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + case 2: /* DPP2 */ + REG_UPDATE(DOMAIN5_PG_CONFIG, + DOMAIN5_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN5_PG_STATUS, + DOMAIN5_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + case 3: /* DPP3 */ + REG_UPDATE(DOMAIN7_PG_CONFIG, + DOMAIN7_POWER_GATE, power_gate); + + REG_WAIT(DOMAIN7_PG_STATUS, + DOMAIN7_PGFSM_PWR_STATUS, pwr_status, + 1, 1000); + break; + default: + BREAK_TO_DEBUGGER(); + break; + } +} diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h index 2305ad282f21..6c072d0274ea 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_hwseq.h @@ -47,4 +47,6 @@ void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, void dcn314_disable_link_output(struct dc_link *link, const struct link_resource *link_res, enum signal_type signal); +void dcn314_dpp_pg_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool power_on); + #endif /* __DC_HWSS_DCN314_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c index f5112742edf9..9f454fa90e65 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn314/dcn314_init.c @@ -141,6 +141,7 @@ static const struct hwseq_private_funcs dcn314_private_funcs = { .enable_power_gating_plane = dcn314_enable_power_gating_plane, .dpp_root_clock_control = dcn314_dpp_root_clock_control, .hubp_pg_control = dcn31_hubp_pg_control, + .dpp_pg_control = dcn314_dpp_pg_control, .program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree, .update_odm = dcn314_update_odm, .dsc_pg_control = dcn314_dsc_pg_control, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index a267f574b619..764eff6a4ec6 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -113,6 +113,14 @@ static void enable_memory_low_power(struct dc *dc) } #endif +static void print_pg_status(struct dc *dc, const char *debug_func, const char *debug_log) +{ + if (dc->debug.enable_pg_cntl_debug_logs && dc->res_pool->pg_cntl) { + if (dc->res_pool->pg_cntl->funcs->print_pg_status) + dc->res_pool->pg_cntl->funcs->print_pg_status(dc->res_pool->pg_cntl, debug_func, debug_log); + } +} + void dcn35_set_dmu_fgcg(struct dce_hwseq *hws, bool enable) { REG_UPDATE_3(DMU_CLK_CNTL, @@ -137,6 +145,8 @@ void dcn35_init_hw(struct dc *dc) uint32_t user_level = MAX_BACKLIGHT_LEVEL; int i; + print_pg_status(dc, __func__, ": start"); + if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks) dc->clk_mgr->funcs->init_clocks(dc->clk_mgr); @@ -200,10 +210,7 @@ void dcn35_init_hw(struct dc *dc) /* we want to turn off all dp displays before doing detection */ dc->link_srv->blank_all_dp_displays(dc); -/* - if (hws->funcs.enable_power_gating_plane) - hws->funcs.enable_power_gating_plane(dc->hwseq, true); -*/ + if (res_pool->hubbub && res_pool->hubbub->funcs->dchubbub_init) res_pool->hubbub->funcs->dchubbub_init(dc->res_pool->hubbub); /* If taking control over from VBIOS, we may want to optimize our first @@ -236,6 +243,8 @@ void dcn35_init_hw(struct dc *dc) } hws->funcs.init_pipes(dc, dc->current_state); + print_pg_status(dc, __func__, ": after init_pipes"); + if (dc->res_pool->hubbub->funcs->allow_self_refresh_control && !dc->res_pool->hubbub->ctx->dc->debug.disable_stutter) dc->res_pool->hubbub->funcs->allow_self_refresh_control(dc->res_pool->hubbub, @@ -312,6 +321,7 @@ void dcn35_init_hw(struct dc *dc) if (dc->res_pool->pg_cntl->funcs->init_pg_status) dc->res_pool->pg_cntl->funcs->init_pg_status(dc->res_pool->pg_cntl); } + print_pg_status(dc, __func__, ": after init_pg_status"); } static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable) @@ -500,97 +510,6 @@ void dcn35_physymclk_root_clock_control(struct dce_hwseq *hws, unsigned int phy_ } } -void dcn35_dsc_pg_control( - struct dce_hwseq *hws, - unsigned int dsc_inst, - bool power_on) -{ - uint32_t power_gate = power_on ? 0 : 1; - uint32_t pwr_status = power_on ? 0 : 2; - uint32_t org_ip_request_cntl = 0; - - if (hws->ctx->dc->debug.disable_dsc_power_gate) - return; - if (hws->ctx->dc->debug.ignore_pg) - return; - REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - - switch (dsc_inst) { - case 0: /* DSC0 */ - REG_UPDATE(DOMAIN16_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN16_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 1: /* DSC1 */ - REG_UPDATE(DOMAIN17_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN17_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 2: /* DSC2 */ - REG_UPDATE(DOMAIN18_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN18_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - case 3: /* DSC3 */ - REG_UPDATE(DOMAIN19_PG_CONFIG, - DOMAIN_POWER_GATE, power_gate); - - REG_WAIT(DOMAIN19_PG_STATUS, - DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); - break; - default: - BREAK_TO_DEBUGGER(); - break; - } - - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); -} - -void dcn35_enable_power_gating_plane(struct dce_hwseq *hws, bool enable) -{ - bool force_on = true; /* disable power gating */ - uint32_t org_ip_request_cntl = 0; - - if (hws->ctx->dc->debug.disable_hubp_power_gate) - return; - if (hws->ctx->dc->debug.ignore_pg) - return; - REG_GET(DC_IP_REQUEST_CNTL, IP_REQUEST_EN, &org_ip_request_cntl); - if (org_ip_request_cntl == 0) - REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); - /* DCHUBP0/1/2/3/4/5 */ - REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - /* DPP0/1/2/3/4/5 */ - REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - - force_on = true; /* disable power gating */ - if (enable && !hws->ctx->dc->debug.disable_dsc_power_gate) - force_on = false; - - /* DCS0/1/2/3/4 */ - REG_UPDATE(DOMAIN16_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN17_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN18_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - REG_UPDATE(DOMAIN19_PG_CONFIG, DOMAIN_POWER_FORCEON, force_on); - - -} - /* In headless boot cases, DIG may be turned * on which causes HW/SW discrepancies. * To avoid this, power down hardware on boot @@ -1453,6 +1372,8 @@ void dcn35_prepare_bandwidth( } dcn20_prepare_bandwidth(dc, context); + + print_pg_status(dc, __func__, ": after rcg and power up"); } void dcn35_optimize_bandwidth( @@ -1461,6 +1382,8 @@ void dcn35_optimize_bandwidth( { struct pg_block_update pg_update_state; + print_pg_status(dc, __func__, ": before rcg and power up"); + dcn20_optimize_bandwidth(dc, context); if (dc->hwss.calc_blocks_to_gate) { @@ -1472,6 +1395,8 @@ void dcn35_optimize_bandwidth( if (dc->hwss.root_clock_control) dc->hwss.root_clock_control(dc, &pg_update_state, false); } + + print_pg_status(dc, __func__, ": after rcg and power up"); } void dcn35_set_drr(struct pipe_ctx **pipe_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c index a3ccf805bd16..aefb7c473741 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_init.c @@ -115,7 +115,6 @@ static const struct hw_sequencer_funcs dcn35_funcs = { .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn10_update_visual_confirm_color, .apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations, - .update_dsc_pg = dcn32_update_dsc_pg, .calc_blocks_to_gate = dcn35_calc_blocks_to_gate, .calc_blocks_to_ungate = dcn35_calc_blocks_to_ungate, .hw_block_power_up = dcn35_hw_block_power_up, @@ -150,7 +149,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .plane_atomic_disable = dcn35_plane_atomic_disable, //.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/ //.hubp_pg_control = dcn35_hubp_pg_control, - .enable_power_gating_plane = dcn35_enable_power_gating_plane, .dpp_root_clock_control = dcn35_dpp_root_clock_control, .dpstream_root_clock_control = dcn35_dpstream_root_clock_control, .physymclk_root_clock_control = dcn35_physymclk_root_clock_control, @@ -165,7 +163,6 @@ static const struct hwseq_private_funcs dcn35_private_funcs = { .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .resync_fifo_dccg_dio = dcn314_resync_fifo_dccg_dio, .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, - .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, .wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c index 58f2be2a326b..a580a55695c3 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn351/dcn351_init.c @@ -114,7 +114,6 @@ static const struct hw_sequencer_funcs dcn351_funcs = { .exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state, .update_visual_confirm_color = dcn10_update_visual_confirm_color, .apply_idle_power_optimizations = dcn35_apply_idle_power_optimizations, - .update_dsc_pg = dcn32_update_dsc_pg, .calc_blocks_to_gate = dcn351_calc_blocks_to_gate, .calc_blocks_to_ungate = dcn351_calc_blocks_to_ungate, .hw_block_power_up = dcn351_hw_block_power_up, @@ -145,7 +144,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = { .plane_atomic_disable = dcn35_plane_atomic_disable, //.plane_atomic_disable = dcn20_plane_atomic_disable,/*todo*/ //.hubp_pg_control = dcn35_hubp_pg_control, - .enable_power_gating_plane = dcn35_enable_power_gating_plane, .dpp_root_clock_control = dcn35_dpp_root_clock_control, .dpstream_root_clock_control = dcn35_dpstream_root_clock_control, .physymclk_root_clock_control = dcn35_physymclk_root_clock_control, @@ -159,7 +157,6 @@ static const struct hwseq_private_funcs dcn351_private_funcs = { .setup_hpo_hw_control = dcn35_setup_hpo_hw_control, .calculate_dccg_k1_k2_values = dcn32_calculate_dccg_k1_k2_values, .is_dp_dig_pixel_rate_div_policy = dcn35_is_dp_dig_pixel_rate_div_policy, - .dsc_pg_control = dcn35_dsc_pg_control, .dsc_pg_status = dcn32_dsc_pg_status, .enable_plane = dcn35_enable_plane, .wait_for_pipe_update_if_needed = dcn10_wait_for_pipe_update_if_needed, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h index 0c5675d1c593..1b7c085dc2cc 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h @@ -349,6 +349,9 @@ struct dpp_funcs { struct dpp *dpp_base, enum dc_color_space color_space, struct dc_csc_transform cursor_csc_color_matrix); + + void (*dpp_force_disable_cursor)(struct dpp *dpp_base); + }; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h index 44f86cc2d1d6..227e3f8d7e5f 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/pg_cntl.h @@ -49,6 +49,7 @@ struct pg_cntl_funcs { void (*mem_pg_control)(struct pg_cntl *pg_cntl, bool power_on); void (*dio_pg_control)(struct pg_cntl *pg_cntl, bool power_on); void (*init_pg_status)(struct pg_cntl *pg_cntl); + void (*print_pg_status)(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log); }; #endif //__DC_PG_CNTL_H__ diff --git a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c index af21c0a27f86..72bd43f9bbe2 100644 --- a/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/pg/dcn35/dcn35_pg_cntl.c @@ -79,16 +79,12 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo uint32_t power_gate = power_on ? 0 : 1; uint32_t pwr_status = power_on ? 0 : 2; uint32_t org_ip_request_cntl = 0; - bool block_enabled; - - /*need to enable dscclk regardless DSC_PG*/ - if (pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc && power_on) - pg_cntl->ctx->dc->res_pool->dccg->funcs->enable_dsc( - pg_cntl->ctx->dc->res_pool->dccg, dsc_inst); + bool block_enabled = false; + bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg || + pg_cntl->ctx->dc->debug.disable_dsc_power_gate || + pg_cntl->ctx->dc->idle_optimizations_allowed; - if (pg_cntl->ctx->dc->debug.ignore_pg || - pg_cntl->ctx->dc->debug.disable_dsc_power_gate || - pg_cntl->ctx->dc->idle_optimizations_allowed) + if (skip_pg && !power_on) return; block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, dsc_inst); @@ -111,7 +107,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN16_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 1: /* DSC1 */ REG_UPDATE(DOMAIN17_PG_CONFIG, @@ -119,7 +115,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN17_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 2: /* DSC2 */ REG_UPDATE(DOMAIN18_PG_CONFIG, @@ -127,7 +123,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN18_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; case 3: /* DSC3 */ REG_UPDATE(DOMAIN19_PG_CONFIG, @@ -135,7 +131,7 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo REG_WAIT(DOMAIN19_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, - 1, 1000); + 1, 10000); break; default: BREAK_TO_DEBUGGER(); @@ -144,12 +140,6 @@ void pg_cntl35_dsc_pg_control(struct pg_cntl *pg_cntl, unsigned int dsc_inst, bo if (dsc_inst < MAX_PIPES) pg_cntl->pg_pipe_res_enable[PG_DSC][dsc_inst] = power_on; - - if (pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc && !power_on) { - /*this is to disable dscclk*/ - pg_cntl->ctx->dc->res_pool->dccg->funcs->disable_dsc( - pg_cntl->ctx->dc->res_pool->dccg, dsc_inst); - } } static bool pg_cntl35_hubp_dpp_pg_status(struct pg_cntl *pg_cntl, unsigned int hubp_dpp_inst) @@ -189,11 +179,12 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp uint32_t pwr_status = power_on ? 0 : 2; uint32_t org_ip_request_cntl; bool block_enabled; + bool skip_pg = pg_cntl->ctx->dc->debug.ignore_pg || + pg_cntl->ctx->dc->debug.disable_hubp_power_gate || + pg_cntl->ctx->dc->debug.disable_dpp_power_gate || + pg_cntl->ctx->dc->idle_optimizations_allowed; - if (pg_cntl->ctx->dc->debug.ignore_pg || - pg_cntl->ctx->dc->debug.disable_hubp_power_gate || - pg_cntl->ctx->dc->debug.disable_dpp_power_gate || - pg_cntl->ctx->dc->idle_optimizations_allowed) + if (skip_pg && !power_on) return; block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, hubp_dpp_inst); @@ -213,22 +204,22 @@ void pg_cntl35_hubp_dpp_pg_control(struct pg_cntl *pg_cntl, unsigned int hubp_dp case 0: /* DPP0 & HUBP0 */ REG_UPDATE(DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN0_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 1: /* DPP1 & HUBP1 */ REG_UPDATE(DOMAIN1_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN1_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 2: /* DPP2 & HUBP2 */ REG_UPDATE(DOMAIN2_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN2_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; case 3: /* DPP3 & HUBP3 */ REG_UPDATE(DOMAIN3_PG_CONFIG, DOMAIN_POWER_GATE, power_gate); - REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 1000); + REG_WAIT(DOMAIN3_PG_STATUS, DOMAIN_PGFSM_PWR_STATUS, pwr_status, 1, 10000); break; default: BREAK_TO_DEBUGGER(); @@ -501,6 +492,36 @@ void pg_cntl35_init_pg_status(struct pg_cntl *pg_cntl) pg_cntl->pg_res_enable[PG_DWB] = block_enabled; } +static void pg_cntl35_print_pg_status(struct pg_cntl *pg_cntl, const char *debug_func, const char *debug_log) +{ + int i = 0; + bool block_enabled = false; + + DC_LOG_DEBUG("%s: %s", debug_func, debug_log); + + DC_LOG_DEBUG("PG_CNTL status:\n"); + + block_enabled = pg_cntl35_io_clk_status(pg_cntl); + DC_LOG_DEBUG("ONO0=%d (DCCG, DIO, DCIO)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_mem_status(pg_cntl); + DC_LOG_DEBUG("ONO1=%d (DCHUBBUB, DCHVM, DCHUBBUBMEM)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_plane_otg_status(pg_cntl); + DC_LOG_DEBUG("ONO2=%d (MPC, OPP, OPTC, DWB)\n", block_enabled ? 1 : 0); + + block_enabled = pg_cntl35_hpo_pg_status(pg_cntl); + DC_LOG_DEBUG("ONO3=%d (HPO)\n", block_enabled ? 1 : 0); + + for (i = 0; i < pg_cntl->ctx->dc->res_pool->pipe_count; i++) { + block_enabled = pg_cntl35_hubp_dpp_pg_status(pg_cntl, i); + DC_LOG_DEBUG("ONO%d=%d (DCHUBP%d, DPP%d)\n", 4 + i * 2, block_enabled ? 1 : 0, i, i); + + block_enabled = pg_cntl35_dsc_pg_status(pg_cntl, i); + DC_LOG_DEBUG("ONO%d=%d (DSC%d)\n", 5 + i * 2, block_enabled ? 1 : 0, i); + } +} + static const struct pg_cntl_funcs pg_cntl35_funcs = { .init_pg_status = pg_cntl35_init_pg_status, .dsc_pg_control = pg_cntl35_dsc_pg_control, @@ -511,7 +532,8 @@ static const struct pg_cntl_funcs pg_cntl35_funcs = { .mpcc_pg_control = pg_cntl35_mpcc_pg_control, .opp_pg_control = pg_cntl35_opp_pg_control, .optc_pg_control = pg_cntl35_optc_pg_control, - .dwb_pg_control = pg_cntl35_dwb_pg_control + .dwb_pg_control = pg_cntl35_dwb_pg_control, + .print_pg_status = pg_cntl35_print_pg_status }; struct pg_cntl *pg_cntl35_create( diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index 464390372b34..ae0d08e5e960 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -393,6 +393,17 @@ static int __maybe_unused ti_sn65dsi86_resume(struct device *dev) gpiod_set_value_cansleep(pdata->enable_gpio, 1); /* + * After EN is deasserted and an external clock is detected, the bridge + * will sample GPIO3:1 to determine its frequency. The driver will + * overwrite this setting in ti_sn_bridge_set_refclk_freq(). But this is + * racy. Thus we have to wait a couple of us. According to the datasheet + * the GPIO lines has to be stable at least 5 us (td5) but it seems that + * is not enough and the refclk frequency value is still lost or + * overwritten by the bridge itself. Waiting for 20us seems to work. + */ + usleep_range(20, 30); + + /* * If we have a reference clock we can enable communication w/ the * panel (including the aux channel) w/out any need for an input clock * so we can do it in resume which lets us read the EDID before diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 273054c22325..c92f3e736228 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -1172,7 +1172,7 @@ static void icl_mbus_init(struct intel_display *display) if (DISPLAY_VER(display) == 12) abox_regs |= BIT(0); - for_each_set_bit(i, &abox_regs, sizeof(abox_regs)) + for_each_set_bit(i, &abox_regs, BITS_PER_TYPE(abox_regs)) intel_de_rmw(display, MBUS_ABOX_CTL(i), mask, val); } @@ -1629,11 +1629,11 @@ static void tgl_bw_buddy_init(struct intel_display *display) if (table[config].page_mask == 0) { drm_dbg_kms(display->drm, "Unknown memory configuration; disabling address buddy logic.\n"); - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) intel_de_write(display, BW_BUDDY_CTL(i), BW_BUDDY_DISABLE); } else { - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) { + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) { intel_de_write(display, BW_BUDDY_PAGE_MASK(i), table[config].page_mask); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index f8a817689e16..eb5537f0ac90 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -387,19 +387,21 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) of_id = of_match_node(mtk_drm_of_ids, node); if (!of_id) - goto next_put_node; + continue; pdev = of_find_device_by_node(node); if (!pdev) - goto next_put_node; + continue; drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match); + put_device(&pdev->dev); if (!drm_dev) - goto next_put_device_pdev_dev; + continue; temp_drm_priv = dev_get_drvdata(drm_dev); + put_device(drm_dev); if (!temp_drm_priv) - goto next_put_device_drm_dev; + continue; if (temp_drm_priv->data->main_len) all_drm_priv[CRTC_MAIN] = temp_drm_priv; @@ -411,17 +413,10 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) if (temp_drm_priv->mtk_drm_bound) cnt++; -next_put_device_drm_dev: - put_device(drm_dev); - -next_put_device_pdev_dev: - put_device(&pdev->dev); - -next_put_node: - of_node_put(node); - - if (cnt == MAX_CRTC) + if (cnt == MAX_CRTC) { + of_node_put(node); break; + } } if (drm_priv->data->mmsys_dev_num == cnt) { diff --git a/drivers/gpu/drm/nouveau/gv100_fence.c b/drivers/gpu/drm/nouveau/gv100_fence.c index cccdeca72002..317e516c4ec7 100644 --- a/drivers/gpu/drm/nouveau/gv100_fence.c +++ b/drivers/gpu/drm/nouveau/gv100_fence.c @@ -18,7 +18,7 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence) struct nvif_push *push = &chan->chan.push; int ret; - ret = PUSH_WAIT(push, 8); + ret = PUSH_WAIT(push, 13); if (ret) return ret; @@ -32,6 +32,11 @@ gv100_fence_emit32(struct nouveau_channel *chan, u64 virtual, u32 sequence) NVDEF(NVC36F, SEM_EXECUTE, PAYLOAD_SIZE, 32BIT) | NVDEF(NVC36F, SEM_EXECUTE, RELEASE_TIMESTAMP, DIS)); + PUSH_MTHD(push, NVC36F, MEM_OP_A, 0, + MEM_OP_B, 0, + MEM_OP_C, NVDEF(NVC36F, MEM_OP_C, MEMBAR_TYPE, SYS_MEMBAR), + MEM_OP_D, NVDEF(NVC36F, MEM_OP_D, OPERATION, MEMBAR)); + PUSH_MTHD(push, NVC36F, NON_STALL_INTERRUPT, 0); PUSH_KICK(push); diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h index 8735dda4c8a7..338f74b9f501 100644 --- a/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h +++ b/drivers/gpu/drm/nouveau/include/nvhw/class/clc36f.h @@ -7,6 +7,91 @@ #define NVC36F_NON_STALL_INTERRUPT (0x00000020) #define NVC36F_NON_STALL_INTERRUPT_HANDLE 31:0 +// NOTE - MEM_OP_A and MEM_OP_B have been replaced in gp100 with methods for +// specifying the page address for a targeted TLB invalidate and the uTLB for +// a targeted REPLAY_CANCEL for UVM. +// The previous MEM_OP_A/B functionality is in MEM_OP_C/D, with slightly +// rearranged fields. +#define NVC36F_MEM_OP_A (0x00000028) +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_CLIENT_UNIT_ID 5:0 // only relevant for REPLAY_CANCEL_TARGETED +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_INVALIDATION_SIZE 5:0 // Used to specify size of invalidate, used for invalidates which are not of the REPLAY_CANCEL_TARGETED type +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_TARGET_GPC_ID 10:6 // only relevant for REPLAY_CANCEL_TARGETED +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_CANCEL_MMU_ENGINE_ID 6:0 // only relevant for REPLAY_CANCEL_VA_GLOBAL +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR 11:11 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_EN 0x00000001 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_SYSMEMBAR_DIS 0x00000000 +#define NVC36F_MEM_OP_A_TLB_INVALIDATE_TARGET_ADDR_LO 31:12 +#define NVC36F_MEM_OP_B (0x0000002c) +#define NVC36F_MEM_OP_B_TLB_INVALIDATE_TARGET_ADDR_HI 31:0 +#define NVC36F_MEM_OP_C (0x00000030) +#define NVC36F_MEM_OP_C_MEMBAR_TYPE 2:0 +#define NVC36F_MEM_OP_C_MEMBAR_TYPE_SYS_MEMBAR 0x00000000 +#define NVC36F_MEM_OP_C_MEMBAR_TYPE_MEMBAR 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB 0:0 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ALL 0x00000001 // Probably nonsensical for MMU_TLB_INVALIDATE_TARGETED +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC 1:1 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_ENABLE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_GPC_DISABLE 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY 4:2 // only relevant if GPC ENABLE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_NONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_START_ACK_ALL 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_TARGETED 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_GLOBAL 0x00000004 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_REPLAY_CANCEL_VA_GLOBAL 0x00000005 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE 6:5 // only relevant if GPC ENABLE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_NONE 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_GLOBALLY 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACK_TYPE_INTRANODE 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE 9:7 //only relevant for REPLAY_CANCEL_VA_GLOBAL +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_READ 0 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE 1 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_STRONG 2 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_RSVRVD 3 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_WEAK 4 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ATOMIC_ALL 5 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_WRITE_AND_ATOMIC 6 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_ACCESS_TYPE_VIRT_ALL 7 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL 9:7 // Invalidate affects this level and all below +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_ALL 0x00000000 // Invalidate tlb caches at all levels of the page table +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_PTE_ONLY 0x00000001 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE0 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE1 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE2 0x00000004 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE3 0x00000005 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE4 0x00000006 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PAGE_TABLE_LEVEL_UP_TO_PDE5 0x00000007 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE 11:10 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_VID_MEM 0x00000000 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_COHERENT 0x00000002 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_APERTURE_SYS_MEM_NONCOHERENT 0x00000003 +#define NVC36F_MEM_OP_C_TLB_INVALIDATE_PDB_ADDR_LO 31:12 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_C_ACCESS_COUNTER_CLR_TARGETED_NOTIFY_TAG 19:0 +// MEM_OP_D MUST be preceded by MEM_OPs A-C. +#define NVC36F_MEM_OP_D (0x00000034) +#define NVC36F_MEM_OP_D_TLB_INVALIDATE_PDB_ADDR_HI 26:0 // only relevant if PDB_ONE +#define NVC36F_MEM_OP_D_OPERATION 31:27 +#define NVC36F_MEM_OP_D_OPERATION_MEMBAR 0x00000005 +#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE 0x00000009 +#define NVC36F_MEM_OP_D_OPERATION_MMU_TLB_INVALIDATE_TARGETED 0x0000000a +#define NVC36F_MEM_OP_D_OPERATION_L2_PEERMEM_INVALIDATE 0x0000000d +#define NVC36F_MEM_OP_D_OPERATION_L2_SYSMEM_INVALIDATE 0x0000000e +// CLEAN_LINES is an alias for Tegra/GPU IP usage +#define NVC36F_MEM_OP_B_OPERATION_L2_INVALIDATE_CLEAN_LINES 0x0000000e +#define NVC36F_MEM_OP_D_OPERATION_L2_CLEAN_COMPTAGS 0x0000000f +#define NVC36F_MEM_OP_D_OPERATION_L2_FLUSH_DIRTY 0x00000010 +#define NVC36F_MEM_OP_D_OPERATION_L2_WAIT_FOR_SYS_PENDING_READS 0x00000015 +#define NVC36F_MEM_OP_D_OPERATION_ACCESS_COUNTER_CLR 0x00000016 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE 1:0 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MIMC 0x00000000 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_MOMC 0x00000001 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_ALL 0x00000002 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TYPE_TARGETED 0x00000003 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE 2:2 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MIMC 0x00000000 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_TYPE_MOMC 0x00000001 +#define NVC36F_MEM_OP_D_ACCESS_COUNTER_CLR_TARGETED_BANK 6:3 #define NVC36F_SEM_ADDR_LO (0x0000005c) #define NVC36F_SEM_ADDR_LO_OFFSET 31:2 #define NVC36F_SEM_ADDR_HI (0x00000060) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index 9f345a008717..869d4335c0f4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -240,21 +240,6 @@ nouveau_fence_emit(struct nouveau_fence *fence) return ret; } -void -nouveau_fence_cancel(struct nouveau_fence *fence) -{ - struct nouveau_fence_chan *fctx = nouveau_fctx(fence); - unsigned long flags; - - spin_lock_irqsave(&fctx->lock, flags); - if (!dma_fence_is_signaled_locked(&fence->base)) { - dma_fence_set_error(&fence->base, -ECANCELED); - if (nouveau_fence_signal(fence)) - nvif_event_block(&fctx->event); - } - spin_unlock_irqrestore(&fctx->lock, flags); -} - bool nouveau_fence_done(struct nouveau_fence *fence) { diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 9957a919bd38..183dd43ecfff 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -29,7 +29,6 @@ void nouveau_fence_unref(struct nouveau_fence **); int nouveau_fence_emit(struct nouveau_fence *); bool nouveau_fence_done(struct nouveau_fence *); -void nouveau_fence_cancel(struct nouveau_fence *fence); int nouveau_fence_wait(struct nouveau_fence *, bool lazy, bool intr); int nouveau_fence_sync(struct nouveau_bo *, struct nouveau_channel *, bool exclusive, bool intr); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c index 0cc0bc9f9952..e60f7892f5ce 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.c +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -11,7 +11,6 @@ #include "nouveau_exec.h" #include "nouveau_abi16.h" #include "nouveau_sched.h" -#include "nouveau_chan.h" #define NOUVEAU_SCHED_JOB_TIMEOUT_MS 10000 @@ -122,9 +121,11 @@ nouveau_job_done(struct nouveau_job *job) { struct nouveau_sched *sched = job->sched; - spin_lock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); list_del(&job->entry); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); + + wake_up(&sched->job.wq); } void @@ -305,9 +306,9 @@ nouveau_job_submit(struct nouveau_job *job) } /* Submit was successful; add the job to the schedulers job list. */ - spin_lock(&sched->job_list.lock); - list_add(&job->entry, &sched->job_list.head); - spin_unlock(&sched->job_list.lock); + spin_lock(&sched->job.list.lock); + list_add(&job->entry, &sched->job.list.head); + spin_unlock(&sched->job.list.lock); drm_sched_job_arm(&job->base); job->done_fence = dma_fence_get(&job->base.s_fence->finished); @@ -392,23 +393,10 @@ nouveau_sched_free_job(struct drm_sched_job *sched_job) nouveau_job_fini(job); } -static void -nouveau_sched_cancel_job(struct drm_sched_job *sched_job) -{ - struct nouveau_fence *fence; - struct nouveau_job *job; - - job = to_nouveau_job(sched_job); - fence = to_nouveau_fence(job->done_fence); - - nouveau_fence_cancel(fence); -} - static const struct drm_sched_backend_ops nouveau_sched_ops = { .run_job = nouveau_sched_run_job, .timedout_job = nouveau_sched_timedout_job, .free_job = nouveau_sched_free_job, - .cancel_job = nouveau_sched_cancel_job, }; static int @@ -458,8 +446,9 @@ nouveau_sched_init(struct nouveau_sched *sched, struct nouveau_drm *drm, goto fail_sched; mutex_init(&sched->mutex); - spin_lock_init(&sched->job_list.lock); - INIT_LIST_HEAD(&sched->job_list.head); + spin_lock_init(&sched->job.list.lock); + INIT_LIST_HEAD(&sched->job.list.head); + init_waitqueue_head(&sched->job.wq); return 0; @@ -493,12 +482,16 @@ nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, return 0; } + static void nouveau_sched_fini(struct nouveau_sched *sched) { struct drm_gpu_scheduler *drm_sched = &sched->base; struct drm_sched_entity *entity = &sched->entity; + rmb(); /* for list_empty to work without lock */ + wait_event(sched->job.wq, list_empty(&sched->job.list.head)); + drm_sched_entity_fini(entity); drm_sched_fini(drm_sched); diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h index b98c3f0bef30..20cd1da8db73 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sched.h +++ b/drivers/gpu/drm/nouveau/nouveau_sched.h @@ -103,9 +103,12 @@ struct nouveau_sched { struct mutex mutex; struct { - struct list_head head; - spinlock_t lock; - } job_list; + struct { + struct list_head head; + spinlock_t lock; + } list; + struct wait_queue_head wq; + } job; }; int nouveau_sched_create(struct nouveau_sched **psched, struct nouveau_drm *drm, diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c index ddfc46bc1b3e..48f105239f42 100644 --- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -1019,8 +1019,8 @@ bind_validate_map_sparse(struct nouveau_job *job, u64 addr, u64 range) u64 end = addr + range; again: - spin_lock(&sched->job_list.lock); - list_for_each_entry(__job, &sched->job_list.head, entry) { + spin_lock(&sched->job.list.lock); + list_for_each_entry(__job, &sched->job.list.head, entry) { struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(__job); list_for_each_op(op, &bind_job->ops) { @@ -1030,7 +1030,7 @@ again: if (!(end <= op_addr || addr >= op_end)) { nouveau_uvmm_bind_job_get(bind_job); - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); wait_for_completion(&bind_job->complete); nouveau_uvmm_bind_job_put(bind_job); goto again; @@ -1038,7 +1038,7 @@ again: } } } - spin_unlock(&sched->job_list.lock); + spin_unlock(&sched->job.list.lock); } static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c index fdffa0391b31..6fd4e60634fb 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/base.c @@ -350,6 +350,8 @@ nvkm_fifo_dtor(struct nvkm_engine *engine) nvkm_chid_unref(&fifo->chid); nvkm_event_fini(&fifo->nonstall.event); + if (fifo->func->nonstall_dtor) + fifo->func->nonstall_dtor(fifo); mutex_destroy(&fifo->mutex); if (fifo->func->dtor) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c index e74493a4569e..6848a56f20c0 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga100.c @@ -517,19 +517,11 @@ ga100_fifo_nonstall_intr(struct nvkm_inth *inth) static void ga100_fifo_nonstall_block(struct nvkm_event *event, int type, int index) { - struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event); - struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0); - - nvkm_inth_block(&runl->nonstall.inth); } static void ga100_fifo_nonstall_allow(struct nvkm_event *event, int type, int index) { - struct nvkm_fifo *fifo = container_of(event, typeof(*fifo), nonstall.event); - struct nvkm_runl *runl = nvkm_runl_get(fifo, index, 0); - - nvkm_inth_allow(&runl->nonstall.inth); } const struct nvkm_event_func @@ -564,12 +556,26 @@ ga100_fifo_nonstall_ctor(struct nvkm_fifo *fifo) if (ret) return ret; + nvkm_inth_allow(&runl->nonstall.inth); + nr = max(nr, runl->id + 1); } return nr; } +void +ga100_fifo_nonstall_dtor(struct nvkm_fifo *fifo) +{ + struct nvkm_runl *runl; + + nvkm_runl_foreach(runl, fifo) { + if (runl->nonstall.vector < 0) + continue; + nvkm_inth_block(&runl->nonstall.inth); + } +} + int ga100_fifo_runl_ctor(struct nvkm_fifo *fifo) { @@ -599,6 +605,7 @@ ga100_fifo = { .runl_ctor = ga100_fifo_runl_ctor, .mmu_fault = &tu102_fifo_mmu_fault, .nonstall_ctor = ga100_fifo_nonstall_ctor, + .nonstall_dtor = ga100_fifo_nonstall_dtor, .nonstall = &ga100_fifo_nonstall, .runl = &ga100_runl, .runq = &ga100_runq, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c index 755235f55b3a..18a0b1f4eab7 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/ga102.c @@ -30,6 +30,7 @@ ga102_fifo = { .runl_ctor = ga100_fifo_runl_ctor, .mmu_fault = &tu102_fifo_mmu_fault, .nonstall_ctor = ga100_fifo_nonstall_ctor, + .nonstall_dtor = ga100_fifo_nonstall_dtor, .nonstall = &ga100_fifo_nonstall, .runl = &ga100_runl, .runq = &ga100_runq, diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h index 5e81ae195329..fff1428ef267 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/priv.h @@ -41,6 +41,7 @@ struct nvkm_fifo_func { void (*start)(struct nvkm_fifo *, unsigned long *); int (*nonstall_ctor)(struct nvkm_fifo *); + void (*nonstall_dtor)(struct nvkm_fifo *); const struct nvkm_event_func *nonstall; const struct nvkm_runl_func *runl; @@ -200,6 +201,7 @@ u32 tu102_chan_doorbell_handle(struct nvkm_chan *); int ga100_fifo_runl_ctor(struct nvkm_fifo *); int ga100_fifo_nonstall_ctor(struct nvkm_fifo *); +void ga100_fifo_nonstall_dtor(struct nvkm_fifo *); extern const struct nvkm_event_func ga100_fifo_nonstall; extern const struct nvkm_runl_func ga100_runl; extern const struct nvkm_runq_func ga100_runq; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c index 1ac5628c5140..4ed54b386a60 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/fifo.c @@ -601,6 +601,7 @@ r535_fifo_new(const struct nvkm_fifo_func *hw, struct nvkm_device *device, rm->chan.func = &r535_chan; rm->nonstall = &ga100_fifo_nonstall; rm->nonstall_ctor = ga100_fifo_nonstall_ctor; + rm->nonstall_dtor = ga100_fifo_nonstall_dtor; return nvkm_fifo_new_(rm, device, type, inst, pfifo); } diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c index 1116f2d2826e..4d8e9b34702a 100644 --- a/drivers/gpu/drm/panthor/panthor_drv.c +++ b/drivers/gpu/drm/panthor/panthor_drv.c @@ -1094,7 +1094,7 @@ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data, struct drm_panthor_queue_create *queue_args; int ret; - if (!args->queues.count) + if (!args->queues.count || args->queues.count > MAX_CS_PER_CSG) return -EINVAL; ret = PANTHOR_UOBJ_GET_ARRAY(queue_args, &args->queues); diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 8867b95ab089..3d06f72531ba 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -391,7 +391,8 @@ EXPORT_SYMBOL(drm_sched_entity_set_priority); * Add a callback to the current dependency of the entity to wake up the * scheduler when the entity becomes available. */ -static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) +static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity, + struct drm_sched_job *sched_job) { struct drm_gpu_scheduler *sched = entity->rq->sched; struct dma_fence *fence = entity->dependency; @@ -421,6 +422,10 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity) entity->dependency = fence; } + if (trace_drm_sched_job_unschedulable_enabled() && + !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &entity->dependency->flags)) + trace_drm_sched_job_unschedulable(sched_job, entity->dependency); + if (!dma_fence_add_callback(entity->dependency, &entity->cb, drm_sched_entity_wakeup)) return true; @@ -461,10 +466,8 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) while ((entity->dependency = drm_sched_job_dependency(sched_job, entity))) { - if (drm_sched_entity_add_dependency_cb(entity)) { - trace_drm_sched_job_unschedulable(sched_job, entity->dependency); + if (drm_sched_entity_add_dependency_cb(entity, sched_job)) return NULL; - } } /* skip jobs from entity that marked guilty */ diff --git a/drivers/gpu/drm/xe/tests/xe_bo.c b/drivers/gpu/drm/xe/tests/xe_bo.c index bb469096d072..7b40cc8be1c9 100644 --- a/drivers/gpu/drm/xe/tests/xe_bo.c +++ b/drivers/gpu/drm/xe/tests/xe_bo.c @@ -236,7 +236,7 @@ static int evict_test_run_tile(struct xe_device *xe, struct xe_tile *tile, struc } xe_bo_lock(external, false); - err = xe_bo_pin_external(external); + err = xe_bo_pin_external(external, false); xe_bo_unlock(external); if (err) { KUNIT_FAIL(test, "external bo pin err=%pe\n", diff --git a/drivers/gpu/drm/xe/tests/xe_dma_buf.c b/drivers/gpu/drm/xe/tests/xe_dma_buf.c index c53f67ce4b0a..121f17c112ec 100644 --- a/drivers/gpu/drm/xe/tests/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/tests/xe_dma_buf.c @@ -89,15 +89,7 @@ static void check_residency(struct kunit *test, struct xe_bo *exported, return; } - /* - * If on different devices, the exporter is kept in system if - * possible, saving a migration step as the transfer is just - * likely as fast from system memory. - */ - if (params->mem_mask & XE_BO_FLAG_SYSTEM) - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, XE_PL_TT)); - else - KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); + KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(exported, mem_type)); if (params->force_different_devices) KUNIT_EXPECT_TRUE(test, xe_bo_is_mem_type(imported, XE_PL_TT)); diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 1be2415966df..bae7ff2e5927 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -186,6 +186,8 @@ static void try_add_system(struct xe_device *xe, struct xe_bo *bo, bo->placements[*c] = (struct ttm_place) { .mem_type = XE_PL_TT, + .flags = (bo_flags & XE_BO_FLAG_VRAM_MASK) ? + TTM_PL_FLAG_FALLBACK : 0, }; *c += 1; } @@ -819,8 +821,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, return ret; } - tt_has_data = ttm && (ttm_tt_is_populated(ttm) || - (ttm->page_flags & TTM_TT_FLAG_SWAPPED)); + tt_has_data = ttm && (ttm_tt_is_populated(ttm) || ttm_tt_is_swapped(ttm)); move_lacks_source = !old_mem || (handle_system_ccs ? (!bo->ccs_cleared) : (!mem_type_is_vram(old_mem_type) && !tt_has_data)); @@ -2270,6 +2271,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) /** * xe_bo_pin_external - pin an external BO * @bo: buffer object to be pinned + * @in_place: Pin in current placement, don't attempt to migrate. * * Pin an external (not tied to a VM, can be exported via dma-buf / prime FD) * BO. Unique call compared to xe_bo_pin as this function has it own set of @@ -2277,7 +2279,7 @@ uint64_t vram_region_gpu_offset(struct ttm_resource *res) * * Returns 0 for success, negative error code otherwise. */ -int xe_bo_pin_external(struct xe_bo *bo) +int xe_bo_pin_external(struct xe_bo *bo, bool in_place) { struct xe_device *xe = xe_bo_device(bo); int err; @@ -2286,9 +2288,11 @@ int xe_bo_pin_external(struct xe_bo *bo) xe_assert(xe, xe_bo_is_user(bo)); if (!xe_bo_is_pinned(bo)) { - err = xe_bo_validate(bo, NULL, false); - if (err) - return err; + if (!in_place) { + err = xe_bo_validate(bo, NULL, false); + if (err) + return err; + } spin_lock(&xe->pinned.lock); list_add_tail(&bo->pinned_link, &xe->pinned.late.external); @@ -2441,6 +2445,9 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict) }; int ret; + if (xe_bo_is_pinned(bo)) + return 0; + if (vm) { lockdep_assert_held(&vm->lock); xe_vm_assert_held(vm); diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h index 02e8cde4c6b2..9ce94d252015 100644 --- a/drivers/gpu/drm/xe/xe_bo.h +++ b/drivers/gpu/drm/xe/xe_bo.h @@ -198,7 +198,7 @@ static inline void xe_bo_unlock_vm_held(struct xe_bo *bo) } } -int xe_bo_pin_external(struct xe_bo *bo); +int xe_bo_pin_external(struct xe_bo *bo, bool in_place); int xe_bo_pin(struct xe_bo *bo); void xe_bo_unpin_external(struct xe_bo *bo); void xe_bo_unpin(struct xe_bo *bo); diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index d4d2c6854790..7ceb0c90f391 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -553,6 +553,12 @@ struct xe_device { /** @pm_notifier: Our PM notifier to perform actions in response to various PM events. */ struct notifier_block pm_notifier; + /** @pm_block: Completion to block validating tasks on suspend / hibernate prepare */ + struct completion pm_block; + /** @rebind_resume_list: List of wq items to kick on resume. */ + struct list_head rebind_resume_list; + /** @rebind_resume_lock: Lock to protect the rebind_resume_list */ + struct mutex rebind_resume_lock; /** @pmt: Support the PMT driver callback interface */ struct { diff --git a/drivers/gpu/drm/xe/xe_dma_buf.c b/drivers/gpu/drm/xe/xe_dma_buf.c index 346f857f3837..af64baf872ef 100644 --- a/drivers/gpu/drm/xe/xe_dma_buf.c +++ b/drivers/gpu/drm/xe/xe_dma_buf.c @@ -72,7 +72,7 @@ static int xe_dma_buf_pin(struct dma_buf_attachment *attach) return ret; } - ret = xe_bo_pin_external(bo); + ret = xe_bo_pin_external(bo, true); xe_assert(xe, !ret); return 0; diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c index 44364c042ad7..374c831e691b 100644 --- a/drivers/gpu/drm/xe/xe_exec.c +++ b/drivers/gpu/drm/xe/xe_exec.c @@ -237,6 +237,15 @@ retry: goto err_unlock_list; } + /* + * It's OK to block interruptible here with the vm lock held, since + * on task freezing during suspend / hibernate, the call will + * return -ERESTARTSYS and the IOCTL will be rerun. + */ + err = wait_for_completion_interruptible(&xe->pm_block); + if (err) + goto err_unlock_list; + vm_exec.vm = &vm->gpuvm; vm_exec.flags = DRM_EXEC_INTERRUPTIBLE_WAIT; if (xe_vm_in_lr_mode(vm)) { diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c index e279b47ba03b..bb9b6ecad2af 100644 --- a/drivers/gpu/drm/xe/xe_pm.c +++ b/drivers/gpu/drm/xe/xe_pm.c @@ -24,6 +24,7 @@ #include "xe_pcode.h" #include "xe_pxp.h" #include "xe_trace.h" +#include "xe_vm.h" #include "xe_wa.h" /** @@ -290,6 +291,19 @@ static u32 vram_threshold_value(struct xe_device *xe) return DEFAULT_VRAM_THRESHOLD; } +static void xe_pm_wake_rebind_workers(struct xe_device *xe) +{ + struct xe_vm *vm, *next; + + mutex_lock(&xe->rebind_resume_lock); + list_for_each_entry_safe(vm, next, &xe->rebind_resume_list, + preempt.pm_activate_link) { + list_del_init(&vm->preempt.pm_activate_link); + xe_vm_resume_rebind_worker(vm); + } + mutex_unlock(&xe->rebind_resume_lock); +} + static int xe_pm_notifier_callback(struct notifier_block *nb, unsigned long action, void *data) { @@ -299,30 +313,30 @@ static int xe_pm_notifier_callback(struct notifier_block *nb, switch (action) { case PM_HIBERNATION_PREPARE: case PM_SUSPEND_PREPARE: + reinit_completion(&xe->pm_block); xe_pm_runtime_get(xe); err = xe_bo_evict_all_user(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier evict user failed (%d)\n", err); - xe_pm_runtime_put(xe); - break; - } err = xe_bo_notifier_prepare_all_pinned(xe); - if (err) { + if (err) drm_dbg(&xe->drm, "Notifier prepare pin failed (%d)\n", err); - xe_pm_runtime_put(xe); - } + /* + * Keep the runtime pm reference until post hibernation / post suspend to + * avoid a runtime suspend interfering with evicted objects or backup + * allocations. + */ break; case PM_POST_HIBERNATION: case PM_POST_SUSPEND: + complete_all(&xe->pm_block); + xe_pm_wake_rebind_workers(xe); xe_bo_notifier_unprepare_all_pinned(xe); xe_pm_runtime_put(xe); break; } - if (err) - return NOTIFY_BAD; - return NOTIFY_DONE; } @@ -344,6 +358,14 @@ int xe_pm_init(struct xe_device *xe) if (err) return err; + err = drmm_mutex_init(&xe->drm, &xe->rebind_resume_lock); + if (err) + goto err_unregister; + + init_completion(&xe->pm_block); + complete_all(&xe->pm_block); + INIT_LIST_HEAD(&xe->rebind_resume_list); + /* For now suspend/resume is only allowed with GuC */ if (!xe_device_uc_enabled(xe)) return 0; diff --git a/drivers/gpu/drm/xe/xe_survivability_mode.c b/drivers/gpu/drm/xe/xe_survivability_mode.c index 41705f5d52e3..8f7b0add2364 100644 --- a/drivers/gpu/drm/xe/xe_survivability_mode.c +++ b/drivers/gpu/drm/xe/xe_survivability_mode.c @@ -41,6 +41,8 @@ * * # echo 1 > /sys/kernel/config/xe/0000:03:00.0/survivability_mode * + * It is the responsibility of the user to clear the mode once firmware flash is complete. + * * Refer :ref:`xe_configfs` for more details on how to use configfs * * Survivability mode is indicated by the below admin-only readable sysfs which provides additional @@ -147,7 +149,6 @@ static void xe_survivability_mode_fini(void *arg) struct pci_dev *pdev = to_pci_dev(xe->drm.dev); struct device *dev = &pdev->dev; - xe_configfs_clear_survivability_mode(pdev); sysfs_remove_file(&dev->kobj, &dev_attr_survivability_mode.attr); } diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index d60c4b115304..dc4f61e56579 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -393,6 +393,9 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec) list_move_tail(&gpuva_to_vma(gpuva)->combined_links.rebind, &vm->rebind_list); + if (!try_wait_for_completion(&vm->xe->pm_block)) + return -EAGAIN; + ret = xe_bo_validate(gem_to_xe_bo(vm_bo->obj), vm, false); if (ret) return ret; @@ -479,6 +482,33 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm, return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues); } +static bool vm_suspend_rebind_worker(struct xe_vm *vm) +{ + struct xe_device *xe = vm->xe; + bool ret = false; + + mutex_lock(&xe->rebind_resume_lock); + if (!try_wait_for_completion(&vm->xe->pm_block)) { + ret = true; + list_move_tail(&vm->preempt.pm_activate_link, &xe->rebind_resume_list); + } + mutex_unlock(&xe->rebind_resume_lock); + + return ret; +} + +/** + * xe_vm_resume_rebind_worker() - Resume the rebind worker. + * @vm: The vm whose preempt worker to resume. + * + * Resume a preempt worker that was previously suspended by + * vm_suspend_rebind_worker(). + */ +void xe_vm_resume_rebind_worker(struct xe_vm *vm) +{ + queue_work(vm->xe->ordered_wq, &vm->preempt.rebind_work); +} + static void preempt_rebind_work_func(struct work_struct *w) { struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work); @@ -502,6 +532,11 @@ static void preempt_rebind_work_func(struct work_struct *w) } retry: + if (!try_wait_for_completion(&vm->xe->pm_block) && vm_suspend_rebind_worker(vm)) { + up_write(&vm->lock); + return; + } + if (xe_vm_userptr_check_repin(vm)) { err = xe_vm_userptr_pin(vm); if (err) @@ -1714,6 +1749,7 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags, struct xe_file *xef) if (flags & XE_VM_FLAG_LR_MODE) { INIT_WORK(&vm->preempt.rebind_work, preempt_rebind_work_func); xe_pm_runtime_get_noresume(xe); + INIT_LIST_HEAD(&vm->preempt.pm_activate_link); } if (flags & XE_VM_FLAG_FAULT_MODE) { @@ -1895,8 +1931,12 @@ void xe_vm_close_and_put(struct xe_vm *vm) xe_assert(xe, !vm->preempt.num_exec_queues); xe_vm_close(vm); - if (xe_vm_in_preempt_fence_mode(vm)) + if (xe_vm_in_preempt_fence_mode(vm)) { + mutex_lock(&xe->rebind_resume_lock); + list_del_init(&vm->preempt.pm_activate_link); + mutex_unlock(&xe->rebind_resume_lock); flush_work(&vm->preempt.rebind_work); + } if (xe_vm_in_fault_mode(vm)) xe_svm_close(vm); diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h index 2ecb417c19a2..82b112795807 100644 --- a/drivers/gpu/drm/xe/xe_vm.h +++ b/drivers/gpu/drm/xe/xe_vm.h @@ -273,6 +273,8 @@ struct dma_fence *xe_vm_bind_kernel_bo(struct xe_vm *vm, struct xe_bo *bo, struct xe_exec_queue *q, u64 addr, enum xe_cache_level cache_lvl); +void xe_vm_resume_rebind_worker(struct xe_vm *vm); + /** * xe_vm_resv() - Return's the vm's reservation object * @vm: The vm diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index 8a07feef503b..6058cf739388 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -293,6 +293,11 @@ struct xe_vm { * BOs */ struct work_struct rebind_work; + /** + * @preempt.pm_activate_link: Link to list of rebind workers to be + * kicked on resume. + */ + struct list_head pm_activate_link; } preempt; /** @um: unified memory state */ diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules index e990f20eccfe..710f4423726c 100644 --- a/drivers/gpu/drm/xe/xe_wa_oob.rules +++ b/drivers/gpu/drm/xe/xe_wa_oob.rules @@ -30,7 +30,8 @@ 16022287689 GRAPHICS_VERSION(2001) GRAPHICS_VERSION(2004) 13011645652 GRAPHICS_VERSION(2004) - GRAPHICS_VERSION(3001) + GRAPHICS_VERSION_RANGE(3000, 3001) + GRAPHICS_VERSION(3003) 14022293748 GRAPHICS_VERSION_RANGE(2001, 2002) GRAPHICS_VERSION(2004) GRAPHICS_VERSION_RANGE(3000, 3001) diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig index 8726d80d6ba4..20d3e6d0d796 100644 --- a/drivers/gpu/nova-core/Kconfig +++ b/drivers/gpu/nova-core/Kconfig @@ -1,5 +1,6 @@ config NOVA_CORE tristate "Nova Core GPU driver" + depends on 64BIT depends on PCI depends on RUST depends on RUST_FW_LOADER_ABSTRACTIONS diff --git a/drivers/hwmon/ina238.c b/drivers/hwmon/ina238.c index 5a394eeff676..59a2c8889fa2 100644 --- a/drivers/hwmon/ina238.c +++ b/drivers/hwmon/ina238.c @@ -379,7 +379,7 @@ static int ina238_write_in(struct device *dev, u32 attr, int channel, regval = clamp_val(val, -163, 163); regval = (regval * 1000 * 4) / (INA238_SHUNT_VOLTAGE_LSB * data->gain); - regval = clamp_val(regval, S16_MIN, S16_MAX); + regval = clamp_val(regval, S16_MIN, S16_MAX) & 0xffff; switch (attr) { case hwmon_in_max: @@ -517,9 +517,10 @@ static int ina238_write_power(struct device *dev, u32 attr, long val) * Unsigned postive values. Compared against the 24-bit power register, * lower 8-bits are truncated. Same conversion to/from uW as POWER * register. + * The first clamp_val() is to establish a baseline to avoid overflows. */ - regval = clamp_val(val, 0, LONG_MAX); - regval = div_u64(val * 4 * 100 * data->rshunt, data->config->power_calculate_factor * + regval = clamp_val(val, 0, LONG_MAX / 2); + regval = div_u64(regval * 4 * 100 * data->rshunt, data->config->power_calculate_factor * 1000ULL * INA238_FIXED_SHUNT * data->gain); regval = clamp_val(regval >> 8, 0, U16_MAX); @@ -572,7 +573,7 @@ static int ina238_write_temp(struct device *dev, u32 attr, long val) return -EOPNOTSUPP; /* Signed */ - regval = clamp_val(val, -40000, 125000); + val = clamp_val(val, -40000, 125000); regval = div_s64(val * 10000, data->config->temp_lsb) << data->config->temp_shift; regval = clamp_val(regval, S16_MIN, S16_MAX) & (0xffff << data->config->temp_shift); diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c index a5f89aab3fb4..c25a54d5b39a 100644 --- a/drivers/hwmon/mlxreg-fan.c +++ b/drivers/hwmon/mlxreg-fan.c @@ -561,15 +561,14 @@ static int mlxreg_fan_cooling_config(struct device *dev, struct mlxreg_fan *fan) if (!pwm->connected) continue; pwm->fan = fan; + /* Set minimal PWM speed. */ + pwm->last_hwmon_state = MLXREG_FAN_PWM_DUTY2STATE(MLXREG_FAN_MIN_DUTY); pwm->cdev = devm_thermal_of_cooling_device_register(dev, NULL, mlxreg_fan_name[i], pwm, &mlxreg_fan_cooling_ops); if (IS_ERR(pwm->cdev)) { dev_err(dev, "Failed to register cooling device\n"); return PTR_ERR(pwm->cdev); } - - /* Set minimal PWM speed. */ - pwm->last_hwmon_state = MLXREG_FAN_PWM_DUTY2STATE(MLXREG_FAN_MIN_DUTY); } return 0; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index a7f89946dad4..e94ac746a741 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1052,7 +1052,7 @@ static const struct pci_device_id i801_ids[] = { { PCI_DEVICE_DATA(INTEL, METEOR_LAKE_P_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, METEOR_LAKE_SOC_S_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, METEOR_LAKE_PCH_S_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, - { PCI_DEVICE_DATA(INTEL, BIRCH_STREAM_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, + { PCI_DEVICE_DATA(INTEL, BIRCH_STREAM_SMBUS, FEATURES_ICH5) }, { PCI_DEVICE_DATA(INTEL, ARROW_LAKE_H_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, PANTHER_LAKE_H_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, PANTHER_LAKE_P_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, diff --git a/drivers/i2c/busses/i2c-rtl9300.c b/drivers/i2c/busses/i2c-rtl9300.c index cfafe089102a..9e1f71fed0fe 100644 --- a/drivers/i2c/busses/i2c-rtl9300.c +++ b/drivers/i2c/busses/i2c-rtl9300.c @@ -99,6 +99,9 @@ static int rtl9300_i2c_config_xfer(struct rtl9300_i2c *i2c, struct rtl9300_i2c_c { u32 val, mask; + if (len < 1 || len > 16) + return -EINVAL; + val = chan->bus_freq << RTL9300_I2C_MST_CTRL2_SCL_FREQ_OFS; mask = RTL9300_I2C_MST_CTRL2_SCL_FREQ_MASK; @@ -222,15 +225,6 @@ static int rtl9300_i2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned s } switch (size) { - case I2C_SMBUS_QUICK: - ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 0); - if (ret) - goto out_unlock; - ret = rtl9300_i2c_reg_addr_set(i2c, 0, 0); - if (ret) - goto out_unlock; - break; - case I2C_SMBUS_BYTE: if (read_write == I2C_SMBUS_WRITE) { ret = rtl9300_i2c_config_xfer(i2c, chan, addr, 0); @@ -312,9 +306,9 @@ out_unlock: static u32 rtl9300_i2c_func(struct i2c_adapter *a) { - return I2C_FUNC_SMBUS_QUICK | I2C_FUNC_SMBUS_BYTE | - I2C_FUNC_SMBUS_BYTE_DATA | I2C_FUNC_SMBUS_WORD_DATA | - I2C_FUNC_SMBUS_BLOCK_DATA; + return I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_BYTE_DATA | + I2C_FUNC_SMBUS_WORD_DATA | I2C_FUNC_SMBUS_BLOCK_DATA | + I2C_FUNC_SMBUS_I2C_BLOCK; } static const struct i2c_algorithm rtl9300_i2c_algo = { @@ -323,7 +317,7 @@ static const struct i2c_algorithm rtl9300_i2c_algo = { }; static struct i2c_adapter_quirks rtl9300_i2c_quirks = { - .flags = I2C_AQ_NO_CLK_STRETCH, + .flags = I2C_AQ_NO_CLK_STRETCH | I2C_AQ_NO_ZERO_LEN, .max_read_len = 16, .max_write_len = 16, }; @@ -353,7 +347,7 @@ static int rtl9300_i2c_probe(struct platform_device *pdev) platform_set_drvdata(pdev, i2c); - if (device_get_child_node_count(dev) >= RTL9300_I2C_MUX_NCHAN) + if (device_get_child_node_count(dev) > RTL9300_I2C_MUX_NCHAN) return dev_err_probe(dev, -EINVAL, "Too many channels\n"); device_for_each_child_node(dev, child) { diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index 4c94297e17e6..d72e89c25e50 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -422,6 +422,7 @@ static const struct xpad_device { { 0x3537, 0x1010, "GameSir G7 SE", 0, XTYPE_XBOXONE }, { 0x366c, 0x0005, "ByoWave Proteus Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE, FLAG_DELAY_INIT }, { 0x3767, 0x0101, "Fanatec Speedster 3 Forceshock Wheel", 0, XTYPE_XBOX }, + { 0x37d7, 0x2501, "Flydigi Apex 5", 0, XTYPE_XBOX360 }, { 0x413d, 0x2104, "Black Shark Green Ghost Gamepad", 0, XTYPE_XBOX360 }, { 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX }, { 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN } @@ -578,6 +579,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x3537), /* GameSir Controllers */ XPAD_XBOXONE_VENDOR(0x3537), /* GameSir Controllers */ XPAD_XBOXONE_VENDOR(0x366c), /* ByoWave controllers */ + XPAD_XBOX360_VENDOR(0x37d7), /* Flydigi Controllers */ XPAD_XBOX360_VENDOR(0x413d), /* Black Shark Green Ghost Controller */ { } }; diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c index 50e2e792c91d..c78d9f6d97c4 100644 --- a/drivers/input/keyboard/mtk-pmic-keys.c +++ b/drivers/input/keyboard/mtk-pmic-keys.c @@ -55,6 +55,7 @@ struct mtk_pmic_regs { const struct mtk_pmic_keys_regs keys_regs[MTK_PMIC_MAX_KEY_COUNT]; u32 pmic_rst_reg; u32 rst_lprst_mask; /* Long-press reset timeout bitmask */ + bool key_release_irq; }; static const struct mtk_pmic_regs mt6397_regs = { @@ -116,6 +117,7 @@ static const struct mtk_pmic_regs mt6358_regs = { MTK_PMIC_HOMEKEY_RST), .pmic_rst_reg = MT6358_TOP_RST_MISC, .rst_lprst_mask = MTK_PMIC_RST_DU_MASK, + .key_release_irq = true, }; static const struct mtk_pmic_regs mt6359_regs = { @@ -129,6 +131,7 @@ static const struct mtk_pmic_regs mt6359_regs = { MTK_PMIC_HOMEKEY_RST), .pmic_rst_reg = MT6359_TOP_RST_MISC, .rst_lprst_mask = MTK_PMIC_RST_DU_MASK, + .key_release_irq = true, }; struct mtk_pmic_keys_info { @@ -368,7 +371,7 @@ static int mtk_pmic_keys_probe(struct platform_device *pdev) if (keys->keys[index].irq < 0) return keys->keys[index].irq; - if (of_device_is_compatible(node, "mediatek,mt6358-keys")) { + if (mtk_pmic_regs->key_release_irq) { keys->keys[index].irq_r = platform_get_irq_byname(pdev, irqnames_r[index]); diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c index 6fac31c0d99f..ff23219a582a 100644 --- a/drivers/input/misc/iqs7222.c +++ b/drivers/input/misc/iqs7222.c @@ -2427,6 +2427,9 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222, if (error) return error; + if (!iqs7222->kp_type[chan_index][i]) + continue; + if (!dev_desc->event_offset) continue; diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 6ed9fc34948c..1caa6c4ca435 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -1155,6 +1155,20 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "XxHP4NAx"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "XxKK4NAx_XxSP4NAx"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, /* * A lot of modern Clevo barebones have touchpad and/or keyboard issues * after suspend fixable with the forcenorestore quirk. diff --git a/drivers/isdn/mISDN/dsp_hwec.c b/drivers/isdn/mISDN/dsp_hwec.c index 0b3f29195330..0cd216e28f00 100644 --- a/drivers/isdn/mISDN/dsp_hwec.c +++ b/drivers/isdn/mISDN/dsp_hwec.c @@ -51,14 +51,14 @@ void dsp_hwec_enable(struct dsp *dsp, const char *arg) goto _do; { - char *dup, *tok, *name, *val; + char *dup, *next, *tok, *name, *val; int tmp; - dup = kstrdup(arg, GFP_ATOMIC); + dup = next = kstrdup(arg, GFP_ATOMIC); if (!dup) return; - while ((tok = strsep(&dup, ","))) { + while ((tok = strsep(&next, ","))) { if (!strlen(tok)) continue; name = strsep(&tok, "="); diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index efeee0a873c0..ab96b692e5a3 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -133,7 +133,7 @@ struct journal_sector { commit_id_t commit_id; }; -#define MAX_TAG_SIZE (JOURNAL_SECTOR_DATA - JOURNAL_MAC_PER_SECTOR - offsetof(struct journal_entry, last_bytes[MAX_SECTORS_PER_BLOCK])) +#define MAX_TAG_SIZE 255 #define METADATA_PADDING_SECTORS 8 diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 79ea85d18e24..f4b904e24328 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3813,8 +3813,10 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits) struct raid_set *rs = ti->private; unsigned int chunk_size_bytes = to_bytes(rs->md.chunk_sectors); - limits->io_min = chunk_size_bytes; - limits->io_opt = chunk_size_bytes * mddev_data_stripes(rs); + if (chunk_size_bytes) { + limits->io_min = chunk_size_bytes; + limits->io_opt = chunk_size_bytes * mddev_data_stripes(rs); + } } static void raid_presuspend(struct dm_target *ti) diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c index 58902091bf79..1461dc740dae 100644 --- a/drivers/md/dm-stripe.c +++ b/drivers/md/dm-stripe.c @@ -456,11 +456,15 @@ static void stripe_io_hints(struct dm_target *ti, struct queue_limits *limits) { struct stripe_c *sc = ti->private; - unsigned int chunk_size = sc->chunk_size << SECTOR_SHIFT; + unsigned int io_min, io_opt; limits->chunk_sectors = sc->chunk_size; - limits->io_min = chunk_size; - limits->io_opt = chunk_size * sc->stripes; + + if (!check_shl_overflow(sc->chunk_size, SECTOR_SHIFT, &io_min) && + !check_mul_overflow(io_min, sc->stripes, &io_opt)) { + limits->io_min = io_min; + limits->io_opt = io_opt; + } } static struct target_type stripe_target = { diff --git a/drivers/md/md.c b/drivers/md/md.c index 1baaf52c603c..4e033c26fdd4 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -9125,6 +9125,11 @@ void md_do_sync(struct md_thread *thread) } action = md_sync_action(mddev); + if (action == ACTION_FROZEN || action == ACTION_IDLE) { + set_bit(MD_RECOVERY_INTR, &mddev->recovery); + goto skip; + } + desc = md_sync_action_name(action); mddev->last_sync_action = action; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 408c26398321..bf44878ec640 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1225,7 +1225,7 @@ static void alloc_behind_master_bio(struct r1bio *r1_bio, int i = 0; struct bio *behind_bio = NULL; - behind_bio = bio_alloc_bioset(NULL, vcnt, 0, GFP_NOIO, + behind_bio = bio_alloc_bioset(NULL, vcnt, bio->bi_opf, GFP_NOIO, &r1_bio->mddev->bio_set); /* discard op, we don't support writezero/writesame yet */ diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig index 46cebde79f34..e518dfeee654 100644 --- a/drivers/mtd/devices/Kconfig +++ b/drivers/mtd/devices/Kconfig @@ -185,8 +185,8 @@ config MTD_POWERNV_FLASH config MTD_INTEL_DG tristate "Intel Discrete Graphics non-volatile memory driver" - depends on AUXILIARY_BUS - depends on MTD + depends on AUXILIARY_BUS && MTD + depends on DRM_I915!=n || DRM_XE!=n || COMPILE_TEST help This provides an MTD device to access Intel Discrete Graphics non-volatile memory. diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c index 84ab4a83cbd6..db94d14a3807 100644 --- a/drivers/mtd/nand/raw/atmel/nand-controller.c +++ b/drivers/mtd/nand/raw/atmel/nand-controller.c @@ -1378,13 +1378,23 @@ static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand, return ret; /* + * Read setup timing depends on the operation done on the NAND: + * + * NRD_SETUP = max(tAR, tCLR) + */ + timeps = max(conf->timings.sdr.tAR_min, conf->timings.sdr.tCLR_min); + ncycles = DIV_ROUND_UP(timeps, mckperiodps); + totalcycles += ncycles; + ret = atmel_smc_cs_conf_set_setup(smcconf, ATMEL_SMC_NRD_SHIFT, ncycles); + if (ret) + return ret; + + /* * The read cycle timing is directly matching tRC, but is also * dependent on the setup and hold timings we calculated earlier, * which gives: * - * NRD_CYCLE = max(tRC, NRD_PULSE + NRD_HOLD) - * - * NRD_SETUP is always 0. + * NRD_CYCLE = max(tRC, NRD_SETUP + NRD_PULSE + NRD_HOLD) */ ncycles = DIV_ROUND_UP(conf->timings.sdr.tRC_min, mckperiodps); ncycles = max(totalcycles, ncycles); diff --git a/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c b/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c index c23b537948d5..1a285cd8fad6 100644 --- a/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c +++ b/drivers/mtd/nand/raw/nuvoton-ma35d1-nand-controller.c @@ -935,10 +935,10 @@ static void ma35_chips_cleanup(struct ma35_nand_info *nand) static int ma35_nand_chips_init(struct device *dev, struct ma35_nand_info *nand) { - struct device_node *np = dev->of_node, *nand_np; + struct device_node *np = dev->of_node; int ret; - for_each_child_of_node(np, nand_np) { + for_each_child_of_node_scoped(np, nand_np) { ret = ma35_nand_chip_init(dev, nand, nand_np); if (ret) { ma35_chips_cleanup(nand); diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index a960403081f1..d957327fb4fa 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -272,6 +272,7 @@ struct stm32_fmc2_nfc { struct sg_table dma_data_sg; struct sg_table dma_ecc_sg; u8 *ecc_buf; + dma_addr_t dma_ecc_addr; int dma_ecc_len; u32 tx_dma_max_burst; u32 rx_dma_max_burst; @@ -902,17 +903,10 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, if (!write_data && !raw) { /* Configure DMA ECC status */ - p = nfc->ecc_buf; for_each_sg(nfc->dma_ecc_sg.sgl, sg, eccsteps, s) { - sg_set_buf(sg, p, nfc->dma_ecc_len); - p += nfc->dma_ecc_len; - } - - ret = dma_map_sg(nfc->dev, nfc->dma_ecc_sg.sgl, - eccsteps, dma_data_dir); - if (!ret) { - ret = -EIO; - goto err_unmap_data; + sg_dma_address(sg) = nfc->dma_ecc_addr + + s * nfc->dma_ecc_len; + sg_dma_len(sg) = nfc->dma_ecc_len; } desc_ecc = dmaengine_prep_slave_sg(nfc->dma_ecc_ch, @@ -921,7 +915,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, DMA_PREP_INTERRUPT); if (!desc_ecc) { ret = -ENOMEM; - goto err_unmap_ecc; + goto err_unmap_data; } reinit_completion(&nfc->dma_ecc_complete); @@ -929,7 +923,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, desc_ecc->callback_param = &nfc->dma_ecc_complete; ret = dma_submit_error(dmaengine_submit(desc_ecc)); if (ret) - goto err_unmap_ecc; + goto err_unmap_data; dma_async_issue_pending(nfc->dma_ecc_ch); } @@ -949,7 +943,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, if (!write_data && !raw) dmaengine_terminate_all(nfc->dma_ecc_ch); ret = -ETIMEDOUT; - goto err_unmap_ecc; + goto err_unmap_data; } /* Wait DMA data transfer completion */ @@ -969,11 +963,6 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, } } -err_unmap_ecc: - if (!write_data && !raw) - dma_unmap_sg(nfc->dev, nfc->dma_ecc_sg.sgl, - eccsteps, dma_data_dir); - err_unmap_data: dma_unmap_sg(nfc->dev, nfc->dma_data_sg.sgl, eccsteps, dma_data_dir); @@ -996,9 +985,21 @@ static int stm32_fmc2_nfc_seq_write(struct nand_chip *chip, const u8 *buf, /* Write oob */ if (oob_required) { - ret = nand_change_write_column_op(chip, mtd->writesize, - chip->oob_poi, mtd->oobsize, - false); + unsigned int offset_in_page = mtd->writesize; + const void *buf = chip->oob_poi; + unsigned int len = mtd->oobsize; + + if (!raw) { + struct mtd_oob_region oob_free; + + mtd_ooblayout_free(mtd, 0, &oob_free); + offset_in_page += oob_free.offset; + buf += oob_free.offset; + len = oob_free.length; + } + + ret = nand_change_write_column_op(chip, offset_in_page, + buf, len, false); if (ret) return ret; } @@ -1610,7 +1611,8 @@ static int stm32_fmc2_nfc_dma_setup(struct stm32_fmc2_nfc *nfc) return ret; /* Allocate a buffer to store ECC status registers */ - nfc->ecc_buf = devm_kzalloc(nfc->dev, FMC2_MAX_ECC_BUF_LEN, GFP_KERNEL); + nfc->ecc_buf = dmam_alloc_coherent(nfc->dev, FMC2_MAX_ECC_BUF_LEN, + &nfc->dma_ecc_addr, GFP_KERNEL); if (!nfc->ecc_buf) return -ENOMEM; diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c index 87053389a1fc..4870b2d5edb2 100644 --- a/drivers/mtd/nand/spi/winbond.c +++ b/drivers/mtd/nand/spi/winbond.c @@ -176,6 +176,36 @@ static const struct mtd_ooblayout_ops w25n02kv_ooblayout = { .free = w25n02kv_ooblayout_free, }; +static int w25n01jw_ooblayout_ecc(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + region->offset = (16 * section) + 12; + region->length = 4; + + return 0; +} + +static int w25n01jw_ooblayout_free(struct mtd_info *mtd, int section, + struct mtd_oob_region *region) +{ + if (section > 3) + return -ERANGE; + + region->offset = (16 * section); + region->length = 12; + + /* Extract BBM */ + if (!section) { + region->offset += 2; + region->length -= 2; + } + + return 0; +} + static int w35n01jw_ooblayout_ecc(struct mtd_info *mtd, int section, struct mtd_oob_region *region) { @@ -206,6 +236,11 @@ static int w35n01jw_ooblayout_free(struct mtd_info *mtd, int section, return 0; } +static const struct mtd_ooblayout_ops w25n01jw_ooblayout = { + .ecc = w25n01jw_ooblayout_ecc, + .free = w25n01jw_ooblayout_free, +}; + static const struct mtd_ooblayout_ops w35n01jw_ooblayout = { .ecc = w35n01jw_ooblayout_ecc, .free = w35n01jw_ooblayout_free, @@ -394,7 +429,7 @@ static const struct spinand_info winbond_spinand_table[] = { &write_cache_variants, &update_cache_variants), 0, - SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL), + SPINAND_ECCINFO(&w25n01jw_ooblayout, NULL), SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg)), SPINAND_INFO("W25N01KV", /* 3.3V */ SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xae, 0x21), diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index 64e664f5adcc..87c134bcd48d 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -861,7 +861,6 @@ static int rcar_can_resume(struct device *dev) { struct net_device *ndev = dev_get_drvdata(dev); struct rcar_can_priv *priv = netdev_priv(ndev); - u16 ctlr; int err; if (!netif_running(ndev)) @@ -873,12 +872,7 @@ static int rcar_can_resume(struct device *dev) return err; } - ctlr = readw(&priv->regs->ctlr); - ctlr &= ~RCAR_CAN_CTLR_SLPM; - writew(ctlr, &priv->regs->ctlr); - ctlr &= ~RCAR_CAN_CTLR_CANM; - writew(ctlr, &priv->regs->ctlr); - priv->can.state = CAN_STATE_ERROR_ACTIVE; + rcar_can_start(ndev); netif_device_attach(ndev); netif_start_queue(ndev); diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index 81baec8eb1e5..a25a3ca62c12 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -690,14 +690,6 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb, dlc |= XCAN_DLCR_EDL_MASK; } - if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) && - (priv->devtype.flags & XCAN_FLAG_TXFEMP)) - can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0); - else - can_put_echo_skb(skb, ndev, 0, 0); - - priv->tx_head++; - priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id); /* If the CAN frame is RTR frame this write triggers transmission * (not on CAN FD) @@ -730,6 +722,14 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb, data[1]); } } + + if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) && + (priv->devtype.flags & XCAN_FLAG_TXFEMP)) + can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0); + else + can_put_echo_skb(skb, ndev, 0, 0); + + priv->tx_head++; } /** diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 829b1f087e9e..2f846381d5a7 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1273,9 +1273,15 @@ static int b53_setup(struct dsa_switch *ds) */ ds->untag_vlan_aware_bridge_pvid = true; - /* Ageing time is set in seconds */ - ds->ageing_time_min = 1 * 1000; - ds->ageing_time_max = AGE_TIME_MAX * 1000; + if (dev->chip_id == BCM53101_DEVICE_ID) { + /* BCM53101 uses 0.5 second increments */ + ds->ageing_time_min = 1 * 500; + ds->ageing_time_max = AGE_TIME_MAX * 500; + } else { + /* Everything else uses 1 second increments */ + ds->ageing_time_min = 1 * 1000; + ds->ageing_time_max = AGE_TIME_MAX * 1000; + } ret = b53_reset_switch(dev); if (ret) { @@ -2559,7 +2565,10 @@ int b53_set_ageing_time(struct dsa_switch *ds, unsigned int msecs) else reg = B53_AGING_TIME_CONTROL; - atc = DIV_ROUND_CLOSEST(msecs, 1000); + if (dev->chip_id == BCM53101_DEVICE_ID) + atc = DIV_ROUND_CLOSEST(msecs, 500); + else + atc = DIV_ROUND_CLOSEST(msecs, 1000); if (!is5325(dev) && !is5365(dev)) atc |= AGE_CHANGE; diff --git a/drivers/net/dsa/mv88e6xxx/leds.c b/drivers/net/dsa/mv88e6xxx/leds.c index 1c88bfaea46b..ab3bc645da56 100644 --- a/drivers/net/dsa/mv88e6xxx/leds.c +++ b/drivers/net/dsa/mv88e6xxx/leds.c @@ -779,7 +779,8 @@ int mv88e6xxx_port_setup_leds(struct mv88e6xxx_chip *chip, int port) continue; if (led_num > 1) { dev_err(dev, "invalid LED specified port %d\n", port); - return -EINVAL; + ret = -EINVAL; + goto err_put_led; } if (led_num == 0) @@ -823,17 +824,25 @@ int mv88e6xxx_port_setup_leds(struct mv88e6xxx_chip *chip, int port) init_data.devname_mandatory = true; init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d:0%d", chip->info->name, port, led_num); - if (!init_data.devicename) - return -ENOMEM; + if (!init_data.devicename) { + ret = -ENOMEM; + goto err_put_led; + } ret = devm_led_classdev_register_ext(dev, l, &init_data); kfree(init_data.devicename); if (ret) { dev_err(dev, "Failed to init LED %d for port %d", led_num, port); - return ret; + goto err_put_led; } } + fwnode_handle_put(leds); return 0; + +err_put_led: + fwnode_handle_put(led); + fwnode_handle_put(leds); + return ret; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 31e3d825b4bc..0daa08cecaf2 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4397,7 +4397,7 @@ static void bnxt_alloc_one_rx_ring_netmem(struct bnxt *bp, for (i = 0; i < bp->rx_agg_ring_size; i++) { if (bnxt_alloc_rx_netmem(bp, rxr, prod, GFP_KERNEL)) { netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d pages only\n", - ring_nr, i, bp->rx_ring_size); + ring_nr, i, bp->rx_agg_ring_size); break; } prod = NEXT_RX_AGG(prod); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 16d28a8b3b56..c769b7dbd3ba 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1223,12 +1223,13 @@ static int macb_tx_complete(struct macb_queue *queue, int budget) { struct macb *bp = queue->bp; u16 queue_index = queue - bp->queues; + unsigned long flags; unsigned int tail; unsigned int head; int packets = 0; u32 bytes = 0; - spin_lock(&queue->tx_ptr_lock); + spin_lock_irqsave(&queue->tx_ptr_lock, flags); head = queue->tx_head; for (tail = queue->tx_tail; tail != head && packets < budget; tail++) { struct macb_tx_skb *tx_skb; @@ -1291,7 +1292,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget) CIRC_CNT(queue->tx_head, queue->tx_tail, bp->tx_ring_size) <= MACB_TX_WAKEUP_THRESH(bp)) netif_wake_subqueue(bp->dev, queue_index); - spin_unlock(&queue->tx_ptr_lock); + spin_unlock_irqrestore(&queue->tx_ptr_lock, flags); return packets; } @@ -1707,8 +1708,9 @@ static void macb_tx_restart(struct macb_queue *queue) { struct macb *bp = queue->bp; unsigned int head_idx, tbqp; + unsigned long flags; - spin_lock(&queue->tx_ptr_lock); + spin_lock_irqsave(&queue->tx_ptr_lock, flags); if (queue->tx_head == queue->tx_tail) goto out_tx_ptr_unlock; @@ -1720,19 +1722,20 @@ static void macb_tx_restart(struct macb_queue *queue) if (tbqp == head_idx) goto out_tx_ptr_unlock; - spin_lock_irq(&bp->lock); + spin_lock(&bp->lock); macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); - spin_unlock_irq(&bp->lock); + spin_unlock(&bp->lock); out_tx_ptr_unlock: - spin_unlock(&queue->tx_ptr_lock); + spin_unlock_irqrestore(&queue->tx_ptr_lock, flags); } static bool macb_tx_complete_pending(struct macb_queue *queue) { bool retval = false; + unsigned long flags; - spin_lock(&queue->tx_ptr_lock); + spin_lock_irqsave(&queue->tx_ptr_lock, flags); if (queue->tx_head != queue->tx_tail) { /* Make hw descriptor updates visible to CPU */ rmb(); @@ -1740,7 +1743,7 @@ static bool macb_tx_complete_pending(struct macb_queue *queue) if (macb_tx_desc(queue, queue->tx_tail)->ctrl & MACB_BIT(TX_USED)) retval = true; } - spin_unlock(&queue->tx_ptr_lock); + spin_unlock_irqrestore(&queue->tx_ptr_lock, flags); return retval; } @@ -2308,6 +2311,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) struct macb_queue *queue = &bp->queues[queue_index]; unsigned int desc_cnt, nr_frags, frag_size, f; unsigned int hdrlen; + unsigned long flags; bool is_lso; netdev_tx_t ret = NETDEV_TX_OK; @@ -2368,7 +2372,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) desc_cnt += DIV_ROUND_UP(frag_size, bp->max_tx_length); } - spin_lock_bh(&queue->tx_ptr_lock); + spin_lock_irqsave(&queue->tx_ptr_lock, flags); /* This is a hard error, log it. */ if (CIRC_SPACE(queue->tx_head, queue->tx_tail, @@ -2392,15 +2396,15 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_sent_queue(netdev_get_tx_queue(bp->dev, queue_index), skb->len); - spin_lock_irq(&bp->lock); + spin_lock(&bp->lock); macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); - spin_unlock_irq(&bp->lock); + spin_unlock(&bp->lock); if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1) netif_stop_subqueue(dev, queue_index); unlock: - spin_unlock_bh(&queue->tx_ptr_lock); + spin_unlock_irqrestore(&queue->tx_ptr_lock, flags); return ret; } diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 21495b5dce25..9efb60842ad1 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -1493,13 +1493,17 @@ static int bgx_init_of_phy(struct bgx *bgx) * this cortina phy, for which there is no driver * support, ignore it. */ - if (phy_np && - !of_device_is_compatible(phy_np, "cortina,cs4223-slice")) { - /* Wait until the phy drivers are available */ - pd = of_phy_find_device(phy_np); - if (!pd) - goto defer; - bgx->lmac[lmac].phydev = pd; + if (phy_np) { + if (!of_device_is_compatible(phy_np, "cortina,cs4223-slice")) { + /* Wait until the phy drivers are available */ + pd = of_phy_find_device(phy_np); + if (!pd) { + of_node_put(phy_np); + goto defer; + } + bgx->lmac[lmac].phydev = pd; + } + of_node_put(phy_np); } lmac++; @@ -1515,11 +1519,11 @@ defer: * for phy devices we may have already found. */ while (lmac) { + lmac--; if (bgx->lmac[lmac].phydev) { put_device(&bgx->lmac[lmac].phydev->mdio.dev); bgx->lmac[lmac].phydev = NULL; } - lmac--; } of_node_put(node); return -EPROBE_DEFER; diff --git a/drivers/net/ethernet/dlink/Kconfig b/drivers/net/ethernet/dlink/Kconfig index e9e13654812c..0d77f84c8e7b 100644 --- a/drivers/net/ethernet/dlink/Kconfig +++ b/drivers/net/ethernet/dlink/Kconfig @@ -32,4 +32,24 @@ config DL2K To compile this driver as a module, choose M here: the module will be called dl2k. +config SUNDANCE + tristate "Sundance Alta support" + depends on PCI + select CRC32 + select MII + help + This driver is for the Sundance "Alta" chip. + More specific information and updates are available from + <http://www.scyld.com/network/sundance.html>. + +config SUNDANCE_MMIO + bool "Use MMIO instead of PIO" + depends on SUNDANCE + help + Enable memory-mapped I/O for interaction with Sundance NIC registers. + Do NOT enable this by default, PIO (enabled when MMIO is disabled) + is known to solve bugs on certain chips. + + If unsure, say N. + endif # NET_VENDOR_DLINK diff --git a/drivers/net/ethernet/dlink/Makefile b/drivers/net/ethernet/dlink/Makefile index 38c236eb6007..3ff503c747db 100644 --- a/drivers/net/ethernet/dlink/Makefile +++ b/drivers/net/ethernet/dlink/Makefile @@ -4,3 +4,4 @@ # obj-$(CONFIG_DL2K) += dl2k.o +obj-$(CONFIG_SUNDANCE) += sundance.o diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c new file mode 100644 index 000000000000..277c50ef773f --- /dev/null +++ b/drivers/net/ethernet/dlink/sundance.c @@ -0,0 +1,1990 @@ +/* sundance.c: A Linux device driver for the Sundance ST201 "Alta". */ +/* + Written 1999-2000 by Donald Becker. + + This software may be used and distributed according to the terms of + the GNU General Public License (GPL), incorporated herein by reference. + Drivers based on or derived from this code fall under the GPL and must + retain the authorship, copyright and license notice. This file is not + a complete program and may only be used when the entire operating + system is licensed under the GPL. + + The author may be reached as becker@scyld.com, or C/O + Scyld Computing Corporation + 410 Severn Ave., Suite 210 + Annapolis MD 21403 + + Support and updates available at + http://www.scyld.com/network/sundance.html + [link no longer provides useful info -jgarzik] + Archives of the mailing list are still available at + https://www.beowulf.org/pipermail/netdrivers/ + +*/ + +#define DRV_NAME "sundance" + +/* The user-configurable values. + These may be modified when a driver module is loaded.*/ +static int debug = 1; /* 1 normal messages, 0 quiet .. 7 verbose. */ +/* Maximum number of multicast addresses to filter (vs. rx-all-multicast). + Typical is a 64 element hash table based on the Ethernet CRC. */ +static const int multicast_filter_limit = 32; + +/* Set the copy breakpoint for the copy-only-tiny-frames scheme. + Setting to > 1518 effectively disables this feature. + This chip can receive into offset buffers, so the Alpha does not + need a copy-align. */ +static int rx_copybreak; +static int flowctrl=1; + +/* media[] specifies the media type the NIC operates at. + autosense Autosensing active media. + 10mbps_hd 10Mbps half duplex. + 10mbps_fd 10Mbps full duplex. + 100mbps_hd 100Mbps half duplex. + 100mbps_fd 100Mbps full duplex. + 0 Autosensing active media. + 1 10Mbps half duplex. + 2 10Mbps full duplex. + 3 100Mbps half duplex. + 4 100Mbps full duplex. +*/ +#define MAX_UNITS 8 +static char *media[MAX_UNITS]; + + +/* Operational parameters that are set at compile time. */ + +/* Keep the ring sizes a power of two for compile efficiency. + The compiler will convert <unsigned>'%'<2^N> into a bit mask. + Making the Tx ring too large decreases the effectiveness of channel + bonding and packet priority, and more than 128 requires modifying the + Tx error recovery. + Large receive rings merely waste memory. */ +#define TX_RING_SIZE 32 +#define TX_QUEUE_LEN (TX_RING_SIZE - 1) /* Limit ring entries actually used. */ +#define RX_RING_SIZE 64 +#define RX_BUDGET 32 +#define TX_TOTAL_SIZE TX_RING_SIZE*sizeof(struct netdev_desc) +#define RX_TOTAL_SIZE RX_RING_SIZE*sizeof(struct netdev_desc) + +/* Operational parameters that usually are not changed. */ +/* Time in jiffies before concluding the transmitter is hung. */ +#define TX_TIMEOUT (4*HZ) +#define PKT_BUF_SZ 1536 /* Size of each temporary Rx buffer.*/ + +/* Include files, designed to support most kernel versions 2.0.0 and later. */ +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/timer.h> +#include <linux/errno.h> +#include <linux/ioport.h> +#include <linux/interrupt.h> +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <linux/init.h> +#include <linux/bitops.h> +#include <linux/uaccess.h> +#include <asm/processor.h> /* Processor type for cache alignment. */ +#include <asm/io.h> +#include <linux/delay.h> +#include <linux/spinlock.h> +#include <linux/dma-mapping.h> +#include <linux/crc32.h> +#include <linux/ethtool.h> +#include <linux/mii.h> + +MODULE_AUTHOR("Donald Becker <becker@scyld.com>"); +MODULE_DESCRIPTION("Sundance Alta Ethernet driver"); +MODULE_LICENSE("GPL"); + +module_param(debug, int, 0); +module_param(rx_copybreak, int, 0); +module_param_array(media, charp, NULL, 0); +module_param(flowctrl, int, 0); +MODULE_PARM_DESC(debug, "Sundance Alta debug level (0-5)"); +MODULE_PARM_DESC(rx_copybreak, "Sundance Alta copy breakpoint for copy-only-tiny-frames"); +MODULE_PARM_DESC(flowctrl, "Sundance Alta flow control [0|1]"); + +/* + Theory of Operation + +I. Board Compatibility + +This driver is designed for the Sundance Technologies "Alta" ST201 chip. + +II. Board-specific settings + +III. Driver operation + +IIIa. Ring buffers + +This driver uses two statically allocated fixed-size descriptor lists +formed into rings by a branch from the final descriptor to the beginning of +the list. The ring sizes are set at compile time by RX/TX_RING_SIZE. +Some chips explicitly use only 2^N sized rings, while others use a +'next descriptor' pointer that the driver forms into rings. + +IIIb/c. Transmit/Receive Structure + +This driver uses a zero-copy receive and transmit scheme. +The driver allocates full frame size skbuffs for the Rx ring buffers at +open() time and passes the skb->data field to the chip as receive data +buffers. When an incoming frame is less than RX_COPYBREAK bytes long, +a fresh skbuff is allocated and the frame is copied to the new skbuff. +When the incoming frame is larger, the skbuff is passed directly up the +protocol stack. Buffers consumed this way are replaced by newly allocated +skbuffs in a later phase of receives. + +The RX_COPYBREAK value is chosen to trade-off the memory wasted by +using a full-sized skbuff for small frames vs. the copying costs of larger +frames. New boards are typically used in generously configured machines +and the underfilled buffers have negligible impact compared to the benefit of +a single allocation size, so the default value of zero results in never +copying packets. When copying is done, the cost is usually mitigated by using +a combined copy/checksum routine. Copying also preloads the cache, which is +most useful with small frames. + +A subtle aspect of the operation is that the IP header at offset 14 in an +ethernet frame isn't longword aligned for further processing. +Unaligned buffers are permitted by the Sundance hardware, so +frames are received into the skbuff at an offset of "+2", 16-byte aligning +the IP header. + +IIId. Synchronization + +The driver runs as two independent, single-threaded flows of control. One +is the send-packet routine, which enforces single-threaded use by the +dev->tbusy flag. The other thread is the interrupt handler, which is single +threaded by the hardware and interrupt handling software. + +The send packet thread has partial control over the Tx ring and 'dev->tbusy' +flag. It sets the tbusy flag whenever it's queuing a Tx packet. If the next +queue slot is empty, it clears the tbusy flag when finished otherwise it sets +the 'lp->tx_full' flag. + +The interrupt handler has exclusive control over the Rx ring and records stats +from the Tx ring. After reaping the stats, it marks the Tx queue entry as +empty by incrementing the dirty_tx mark. Iff the 'lp->tx_full' flag is set, it +clears both the tx_full and tbusy flags. + +IV. Notes + +IVb. References + +The Sundance ST201 datasheet, preliminary version. +The Kendin KS8723 datasheet, preliminary version. +The ICplus IP100 datasheet, preliminary version. +http://www.scyld.com/expert/100mbps.html +http://www.scyld.com/expert/NWay.html + +IVc. Errata + +*/ + +/* Work-around for Kendin chip bugs. */ +#ifndef CONFIG_SUNDANCE_MMIO +#define USE_IO_OPS 1 +#endif + +static const struct pci_device_id sundance_pci_tbl[] = { + { 0x1186, 0x1002, 0x1186, 0x1002, 0, 0, 0 }, + { 0x1186, 0x1002, 0x1186, 0x1003, 0, 0, 1 }, + { 0x1186, 0x1002, 0x1186, 0x1012, 0, 0, 2 }, + { 0x1186, 0x1002, 0x1186, 0x1040, 0, 0, 3 }, + { 0x1186, 0x1002, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 4 }, + { 0x13F0, 0x0201, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 5 }, + { 0x13F0, 0x0200, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 6 }, + { } +}; +MODULE_DEVICE_TABLE(pci, sundance_pci_tbl); + +enum { + netdev_io_size = 128 +}; + +struct pci_id_info { + const char *name; +}; +static const struct pci_id_info pci_id_tbl[] = { + {"D-Link DFE-550TX FAST Ethernet Adapter"}, + {"D-Link DFE-550FX 100Mbps Fiber-optics Adapter"}, + {"D-Link DFE-580TX 4 port Server Adapter"}, + {"D-Link DFE-530TXS FAST Ethernet Adapter"}, + {"D-Link DL10050-based FAST Ethernet Adapter"}, + {"Sundance Technology Alta"}, + {"IC Plus Corporation IP100A FAST Ethernet Adapter"}, + { } /* terminate list. */ +}; + +/* This driver was written to use PCI memory space, however x86-oriented + hardware often uses I/O space accesses. */ + +/* Offsets to the device registers. + Unlike software-only systems, device drivers interact with complex hardware. + It's not useful to define symbolic names for every register bit in the + device. The name can only partially document the semantics and make + the driver longer and more difficult to read. + In general, only the important configuration values or bits changed + multiple times should be defined symbolically. +*/ +enum alta_offsets { + DMACtrl = 0x00, + TxListPtr = 0x04, + TxDMABurstThresh = 0x08, + TxDMAUrgentThresh = 0x09, + TxDMAPollPeriod = 0x0a, + RxDMAStatus = 0x0c, + RxListPtr = 0x10, + DebugCtrl0 = 0x1a, + DebugCtrl1 = 0x1c, + RxDMABurstThresh = 0x14, + RxDMAUrgentThresh = 0x15, + RxDMAPollPeriod = 0x16, + LEDCtrl = 0x1a, + ASICCtrl = 0x30, + EEData = 0x34, + EECtrl = 0x36, + FlashAddr = 0x40, + FlashData = 0x44, + WakeEvent = 0x45, + TxStatus = 0x46, + TxFrameId = 0x47, + DownCounter = 0x18, + IntrClear = 0x4a, + IntrEnable = 0x4c, + IntrStatus = 0x4e, + MACCtrl0 = 0x50, + MACCtrl1 = 0x52, + StationAddr = 0x54, + MaxFrameSize = 0x5A, + RxMode = 0x5c, + MIICtrl = 0x5e, + MulticastFilter0 = 0x60, + MulticastFilter1 = 0x64, + RxOctetsLow = 0x68, + RxOctetsHigh = 0x6a, + TxOctetsLow = 0x6c, + TxOctetsHigh = 0x6e, + TxFramesOK = 0x70, + RxFramesOK = 0x72, + StatsCarrierError = 0x74, + StatsLateColl = 0x75, + StatsMultiColl = 0x76, + StatsOneColl = 0x77, + StatsTxDefer = 0x78, + RxMissed = 0x79, + StatsTxXSDefer = 0x7a, + StatsTxAbort = 0x7b, + StatsBcastTx = 0x7c, + StatsBcastRx = 0x7d, + StatsMcastTx = 0x7e, + StatsMcastRx = 0x7f, + /* Aliased and bogus values! */ + RxStatus = 0x0c, +}; + +#define ASIC_HI_WORD(x) ((x) + 2) + +enum ASICCtrl_HiWord_bit { + GlobalReset = 0x0001, + RxReset = 0x0002, + TxReset = 0x0004, + DMAReset = 0x0008, + FIFOReset = 0x0010, + NetworkReset = 0x0020, + HostReset = 0x0040, + ResetBusy = 0x0400, +}; + +/* Bits in the interrupt status/mask registers. */ +enum intr_status_bits { + IntrSummary=0x0001, IntrPCIErr=0x0002, IntrMACCtrl=0x0008, + IntrTxDone=0x0004, IntrRxDone=0x0010, IntrRxStart=0x0020, + IntrDrvRqst=0x0040, + StatsMax=0x0080, LinkChange=0x0100, + IntrTxDMADone=0x0200, IntrRxDMADone=0x0400, +}; + +/* Bits in the RxMode register. */ +enum rx_mode_bits { + AcceptAllIPMulti=0x20, AcceptMultiHash=0x10, AcceptAll=0x08, + AcceptBroadcast=0x04, AcceptMulticast=0x02, AcceptMyPhys=0x01, +}; +/* Bits in MACCtrl. */ +enum mac_ctrl0_bits { + EnbFullDuplex=0x20, EnbRcvLargeFrame=0x40, + EnbFlowCtrl=0x100, EnbPassRxCRC=0x200, +}; +enum mac_ctrl1_bits { + StatsEnable=0x0020, StatsDisable=0x0040, StatsEnabled=0x0080, + TxEnable=0x0100, TxDisable=0x0200, TxEnabled=0x0400, + RxEnable=0x0800, RxDisable=0x1000, RxEnabled=0x2000, +}; + +/* Bits in WakeEvent register. */ +enum wake_event_bits { + WakePktEnable = 0x01, + MagicPktEnable = 0x02, + LinkEventEnable = 0x04, + WolEnable = 0x80, +}; + +/* The Rx and Tx buffer descriptors. */ +/* Note that using only 32 bit fields simplifies conversion to big-endian + architectures. */ +struct netdev_desc { + __le32 next_desc; + __le32 status; + struct desc_frag { __le32 addr, length; } frag; +}; + +/* Bits in netdev_desc.status */ +enum desc_status_bits { + DescOwn=0x8000, + DescEndPacket=0x4000, + DescEndRing=0x2000, + LastFrag=0x80000000, + DescIntrOnTx=0x8000, + DescIntrOnDMADone=0x80000000, + DisableAlign = 0x00000001, +}; + +#define PRIV_ALIGN 15 /* Required alignment mask */ +/* Use __attribute__((aligned (L1_CACHE_BYTES))) to maintain alignment + within the structure. */ +#define MII_CNT 4 +struct netdev_private { + /* Descriptor rings first for alignment. */ + struct netdev_desc *rx_ring; + struct netdev_desc *tx_ring; + struct sk_buff* rx_skbuff[RX_RING_SIZE]; + struct sk_buff* tx_skbuff[TX_RING_SIZE]; + dma_addr_t tx_ring_dma; + dma_addr_t rx_ring_dma; + struct timer_list timer; /* Media monitoring timer. */ + struct net_device *ndev; /* backpointer */ + /* ethtool extra stats */ + struct { + u64 tx_multiple_collisions; + u64 tx_single_collisions; + u64 tx_late_collisions; + u64 tx_deferred; + u64 tx_deferred_excessive; + u64 tx_aborted; + u64 tx_bcasts; + u64 rx_bcasts; + u64 tx_mcasts; + u64 rx_mcasts; + } xstats; + /* Frequently used values: keep some adjacent for cache effect. */ + spinlock_t lock; + int msg_enable; + int chip_id; + unsigned int cur_rx, dirty_rx; /* Producer/consumer ring indices */ + unsigned int rx_buf_sz; /* Based on MTU+slack. */ + struct netdev_desc *last_tx; /* Last Tx descriptor used. */ + unsigned int cur_tx, dirty_tx; + /* These values are keep track of the transceiver/media in use. */ + unsigned int flowctrl:1; + unsigned int default_port:4; /* Last dev->if_port value. */ + unsigned int an_enable:1; + unsigned int speed; + unsigned int wol_enabled:1; /* Wake on LAN enabled */ + struct tasklet_struct rx_tasklet; + struct tasklet_struct tx_tasklet; + int budget; + int cur_task; + /* Multicast and receive mode. */ + spinlock_t mcastlock; /* SMP lock multicast updates. */ + u16 mcast_filter[4]; + /* MII transceiver section. */ + struct mii_if_info mii_if; + int mii_preamble_required; + unsigned char phys[MII_CNT]; /* MII device addresses, only first one used. */ + struct pci_dev *pci_dev; + void __iomem *base; + spinlock_t statlock; +}; + +/* The station address location in the EEPROM. */ +#define EEPROM_SA_OFFSET 0x10 +#define DEFAULT_INTR (IntrRxDMADone | IntrPCIErr | \ + IntrDrvRqst | IntrTxDone | StatsMax | \ + LinkChange) + +static int change_mtu(struct net_device *dev, int new_mtu); +static int eeprom_read(void __iomem *ioaddr, int location); +static int mdio_read(struct net_device *dev, int phy_id, int location); +static void mdio_write(struct net_device *dev, int phy_id, int location, int value); +static int mdio_wait_link(struct net_device *dev, int wait); +static int netdev_open(struct net_device *dev); +static void check_duplex(struct net_device *dev); +static void netdev_timer(struct timer_list *t); +static void tx_timeout(struct net_device *dev, unsigned int txqueue); +static void init_ring(struct net_device *dev); +static netdev_tx_t start_tx(struct sk_buff *skb, struct net_device *dev); +static int reset_tx (struct net_device *dev); +static irqreturn_t intr_handler(int irq, void *dev_instance); +static void rx_poll(struct tasklet_struct *t); +static void tx_poll(struct tasklet_struct *t); +static void refill_rx (struct net_device *dev); +static void netdev_error(struct net_device *dev, int intr_status); +static void netdev_error(struct net_device *dev, int intr_status); +static void set_rx_mode(struct net_device *dev); +static int __set_mac_addr(struct net_device *dev); +static int sundance_set_mac_addr(struct net_device *dev, void *data); +static struct net_device_stats *get_stats(struct net_device *dev); +static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); +static int netdev_close(struct net_device *dev); +static const struct ethtool_ops ethtool_ops; + +static void sundance_reset(struct net_device *dev, unsigned long reset_cmd) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base + ASICCtrl; + int countdown; + + /* ST201 documentation states ASICCtrl is a 32bit register */ + iowrite32 (reset_cmd | ioread32 (ioaddr), ioaddr); + /* ST201 documentation states reset can take up to 1 ms */ + countdown = 10 + 1; + while (ioread32 (ioaddr) & (ResetBusy << 16)) { + if (--countdown == 0) { + printk(KERN_WARNING "%s : reset not completed !!\n", dev->name); + break; + } + udelay(100); + } +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +static void sundance_poll_controller(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + + disable_irq(np->pci_dev->irq); + intr_handler(np->pci_dev->irq, dev); + enable_irq(np->pci_dev->irq); +} +#endif + +static const struct net_device_ops netdev_ops = { + .ndo_open = netdev_open, + .ndo_stop = netdev_close, + .ndo_start_xmit = start_tx, + .ndo_get_stats = get_stats, + .ndo_set_rx_mode = set_rx_mode, + .ndo_eth_ioctl = netdev_ioctl, + .ndo_tx_timeout = tx_timeout, + .ndo_change_mtu = change_mtu, + .ndo_set_mac_address = sundance_set_mac_addr, + .ndo_validate_addr = eth_validate_addr, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = sundance_poll_controller, +#endif +}; + +static int sundance_probe1(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct net_device *dev; + struct netdev_private *np; + static int card_idx; + int chip_idx = ent->driver_data; + int irq; + int i; + void __iomem *ioaddr; + u16 mii_ctl; + void *ring_space; + dma_addr_t ring_dma; +#ifdef USE_IO_OPS + int bar = 0; +#else + int bar = 1; +#endif + int phy, phy_end, phy_idx = 0; + __le16 addr[ETH_ALEN / 2]; + + if (pci_enable_device(pdev)) + return -EIO; + pci_set_master(pdev); + + irq = pdev->irq; + + dev = alloc_etherdev(sizeof(*np)); + if (!dev) + return -ENOMEM; + SET_NETDEV_DEV(dev, &pdev->dev); + + if (pci_request_regions(pdev, DRV_NAME)) + goto err_out_netdev; + + ioaddr = pci_iomap(pdev, bar, netdev_io_size); + if (!ioaddr) + goto err_out_res; + + for (i = 0; i < 3; i++) + addr[i] = + cpu_to_le16(eeprom_read(ioaddr, i + EEPROM_SA_OFFSET)); + eth_hw_addr_set(dev, (u8 *)addr); + + np = netdev_priv(dev); + np->ndev = dev; + np->base = ioaddr; + np->pci_dev = pdev; + np->chip_id = chip_idx; + np->msg_enable = (1 << debug) - 1; + spin_lock_init(&np->lock); + spin_lock_init(&np->statlock); + tasklet_setup(&np->rx_tasklet, rx_poll); + tasklet_setup(&np->tx_tasklet, tx_poll); + + ring_space = dma_alloc_coherent(&pdev->dev, TX_TOTAL_SIZE, + &ring_dma, GFP_KERNEL); + if (!ring_space) + goto err_out_cleardev; + np->tx_ring = (struct netdev_desc *)ring_space; + np->tx_ring_dma = ring_dma; + + ring_space = dma_alloc_coherent(&pdev->dev, RX_TOTAL_SIZE, + &ring_dma, GFP_KERNEL); + if (!ring_space) + goto err_out_unmap_tx; + np->rx_ring = (struct netdev_desc *)ring_space; + np->rx_ring_dma = ring_dma; + + np->mii_if.dev = dev; + np->mii_if.mdio_read = mdio_read; + np->mii_if.mdio_write = mdio_write; + np->mii_if.phy_id_mask = 0x1f; + np->mii_if.reg_num_mask = 0x1f; + + /* The chip-specific entries in the device structure. */ + dev->netdev_ops = &netdev_ops; + dev->ethtool_ops = ðtool_ops; + dev->watchdog_timeo = TX_TIMEOUT; + + /* MTU range: 68 - 8191 */ + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = 8191; + + pci_set_drvdata(pdev, dev); + + i = register_netdev(dev); + if (i) + goto err_out_unmap_rx; + + printk(KERN_INFO "%s: %s at %p, %pM, IRQ %d.\n", + dev->name, pci_id_tbl[chip_idx].name, ioaddr, + dev->dev_addr, irq); + + np->phys[0] = 1; /* Default setting */ + np->mii_preamble_required++; + + /* + * It seems some phys doesn't deal well with address 0 being accessed + * first + */ + if (sundance_pci_tbl[np->chip_id].device == 0x0200) { + phy = 0; + phy_end = 31; + } else { + phy = 1; + phy_end = 32; /* wraps to zero, due to 'phy & 0x1f' */ + } + for (; phy <= phy_end && phy_idx < MII_CNT; phy++) { + int phyx = phy & 0x1f; + int mii_status = mdio_read(dev, phyx, MII_BMSR); + if (mii_status != 0xffff && mii_status != 0x0000) { + np->phys[phy_idx++] = phyx; + np->mii_if.advertising = mdio_read(dev, phyx, MII_ADVERTISE); + if ((mii_status & 0x0040) == 0) + np->mii_preamble_required++; + printk(KERN_INFO "%s: MII PHY found at address %d, status " + "0x%4.4x advertising %4.4x.\n", + dev->name, phyx, mii_status, np->mii_if.advertising); + } + } + np->mii_preamble_required--; + + if (phy_idx == 0) { + printk(KERN_INFO "%s: No MII transceiver found, aborting. ASIC status %x\n", + dev->name, ioread32(ioaddr + ASICCtrl)); + goto err_out_unregister; + } + + np->mii_if.phy_id = np->phys[0]; + + /* Parse override configuration */ + np->an_enable = 1; + if (card_idx < MAX_UNITS) { + if (media[card_idx] != NULL) { + np->an_enable = 0; + if (strcmp (media[card_idx], "100mbps_fd") == 0 || + strcmp (media[card_idx], "4") == 0) { + np->speed = 100; + np->mii_if.full_duplex = 1; + } else if (strcmp (media[card_idx], "100mbps_hd") == 0 || + strcmp (media[card_idx], "3") == 0) { + np->speed = 100; + np->mii_if.full_duplex = 0; + } else if (strcmp (media[card_idx], "10mbps_fd") == 0 || + strcmp (media[card_idx], "2") == 0) { + np->speed = 10; + np->mii_if.full_duplex = 1; + } else if (strcmp (media[card_idx], "10mbps_hd") == 0 || + strcmp (media[card_idx], "1") == 0) { + np->speed = 10; + np->mii_if.full_duplex = 0; + } else { + np->an_enable = 1; + } + } + if (flowctrl == 1) + np->flowctrl = 1; + } + + /* Fibre PHY? */ + if (ioread32 (ioaddr + ASICCtrl) & 0x80) { + /* Default 100Mbps Full */ + if (np->an_enable) { + np->speed = 100; + np->mii_if.full_duplex = 1; + np->an_enable = 0; + } + } + /* Reset PHY */ + mdio_write (dev, np->phys[0], MII_BMCR, BMCR_RESET); + mdelay (300); + /* If flow control enabled, we need to advertise it.*/ + if (np->flowctrl) + mdio_write (dev, np->phys[0], MII_ADVERTISE, np->mii_if.advertising | 0x0400); + mdio_write (dev, np->phys[0], MII_BMCR, BMCR_ANENABLE|BMCR_ANRESTART); + /* Force media type */ + if (!np->an_enable) { + mii_ctl = 0; + mii_ctl |= (np->speed == 100) ? BMCR_SPEED100 : 0; + mii_ctl |= (np->mii_if.full_duplex) ? BMCR_FULLDPLX : 0; + mdio_write (dev, np->phys[0], MII_BMCR, mii_ctl); + printk (KERN_INFO "Override speed=%d, %s duplex\n", + np->speed, np->mii_if.full_duplex ? "Full" : "Half"); + + } + + /* Perhaps move the reset here? */ + /* Reset the chip to erase previous misconfiguration. */ + if (netif_msg_hw(np)) + printk("ASIC Control is %x.\n", ioread32(ioaddr + ASICCtrl)); + sundance_reset(dev, 0x00ff << 16); + if (netif_msg_hw(np)) + printk("ASIC Control is now %x.\n", ioread32(ioaddr + ASICCtrl)); + + card_idx++; + return 0; + +err_out_unregister: + unregister_netdev(dev); +err_out_unmap_rx: + dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, + np->rx_ring, np->rx_ring_dma); +err_out_unmap_tx: + dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, + np->tx_ring, np->tx_ring_dma); +err_out_cleardev: + pci_iounmap(pdev, ioaddr); +err_out_res: + pci_release_regions(pdev); +err_out_netdev: + free_netdev (dev); + return -ENODEV; +} + +static int change_mtu(struct net_device *dev, int new_mtu) +{ + if (netif_running(dev)) + return -EBUSY; + WRITE_ONCE(dev->mtu, new_mtu); + return 0; +} + +#define eeprom_delay(ee_addr) ioread32(ee_addr) +/* Read the EEPROM and MII Management Data I/O (MDIO) interfaces. */ +static int eeprom_read(void __iomem *ioaddr, int location) +{ + int boguscnt = 10000; /* Typical 1900 ticks. */ + iowrite16(0x0200 | (location & 0xff), ioaddr + EECtrl); + do { + eeprom_delay(ioaddr + EECtrl); + if (! (ioread16(ioaddr + EECtrl) & 0x8000)) { + return ioread16(ioaddr + EEData); + } + } while (--boguscnt > 0); + return 0; +} + +/* MII transceiver control section. + Read and write the MII registers using software-generated serial + MDIO protocol. See the MII specifications or DP83840A data sheet + for details. + + The maximum data clock rate is 2.5 Mhz. The minimum timing is usually + met by back-to-back 33Mhz PCI cycles. */ +#define mdio_delay() ioread8(mdio_addr) + +enum mii_reg_bits { + MDIO_ShiftClk=0x0001, MDIO_Data=0x0002, MDIO_EnbOutput=0x0004, +}; +#define MDIO_EnbIn (0) +#define MDIO_WRITE0 (MDIO_EnbOutput) +#define MDIO_WRITE1 (MDIO_Data | MDIO_EnbOutput) + +/* Generate the preamble required for initial synchronization and + a few older transceivers. */ +static void mdio_sync(void __iomem *mdio_addr) +{ + int bits = 32; + + /* Establish sync by sending at least 32 logic ones. */ + while (--bits >= 0) { + iowrite8(MDIO_WRITE1, mdio_addr); + mdio_delay(); + iowrite8(MDIO_WRITE1 | MDIO_ShiftClk, mdio_addr); + mdio_delay(); + } +} + +static int mdio_read(struct net_device *dev, int phy_id, int location) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *mdio_addr = np->base + MIICtrl; + int mii_cmd = (0xf6 << 10) | (phy_id << 5) | location; + int i, retval = 0; + + if (np->mii_preamble_required) + mdio_sync(mdio_addr); + + /* Shift the read command bits out. */ + for (i = 15; i >= 0; i--) { + int dataval = (mii_cmd & (1 << i)) ? MDIO_WRITE1 : MDIO_WRITE0; + + iowrite8(dataval, mdio_addr); + mdio_delay(); + iowrite8(dataval | MDIO_ShiftClk, mdio_addr); + mdio_delay(); + } + /* Read the two transition, 16 data, and wire-idle bits. */ + for (i = 19; i > 0; i--) { + iowrite8(MDIO_EnbIn, mdio_addr); + mdio_delay(); + retval = (retval << 1) | ((ioread8(mdio_addr) & MDIO_Data) ? 1 : 0); + iowrite8(MDIO_EnbIn | MDIO_ShiftClk, mdio_addr); + mdio_delay(); + } + return (retval>>1) & 0xffff; +} + +static void mdio_write(struct net_device *dev, int phy_id, int location, int value) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *mdio_addr = np->base + MIICtrl; + int mii_cmd = (0x5002 << 16) | (phy_id << 23) | (location<<18) | value; + int i; + + if (np->mii_preamble_required) + mdio_sync(mdio_addr); + + /* Shift the command bits out. */ + for (i = 31; i >= 0; i--) { + int dataval = (mii_cmd & (1 << i)) ? MDIO_WRITE1 : MDIO_WRITE0; + + iowrite8(dataval, mdio_addr); + mdio_delay(); + iowrite8(dataval | MDIO_ShiftClk, mdio_addr); + mdio_delay(); + } + /* Clear out extra bits. */ + for (i = 2; i > 0; i--) { + iowrite8(MDIO_EnbIn, mdio_addr); + mdio_delay(); + iowrite8(MDIO_EnbIn | MDIO_ShiftClk, mdio_addr); + mdio_delay(); + } +} + +static int mdio_wait_link(struct net_device *dev, int wait) +{ + int bmsr; + int phy_id; + struct netdev_private *np; + + np = netdev_priv(dev); + phy_id = np->phys[0]; + + do { + bmsr = mdio_read(dev, phy_id, MII_BMSR); + if (bmsr & 0x0004) + return 0; + mdelay(1); + } while (--wait > 0); + return -1; +} + +static int netdev_open(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + const int irq = np->pci_dev->irq; + unsigned long flags; + int i; + + sundance_reset(dev, 0x00ff << 16); + + i = request_irq(irq, intr_handler, IRQF_SHARED, dev->name, dev); + if (i) + return i; + + if (netif_msg_ifup(np)) + printk(KERN_DEBUG "%s: netdev_open() irq %d\n", dev->name, irq); + + init_ring(dev); + + iowrite32(np->rx_ring_dma, ioaddr + RxListPtr); + /* The Tx list pointer is written as packets are queued. */ + + /* Initialize other registers. */ + __set_mac_addr(dev); +#if IS_ENABLED(CONFIG_VLAN_8021Q) + iowrite16(dev->mtu + 18, ioaddr + MaxFrameSize); +#else + iowrite16(dev->mtu + 14, ioaddr + MaxFrameSize); +#endif + if (dev->mtu > 2047) + iowrite32(ioread32(ioaddr + ASICCtrl) | 0x0C, ioaddr + ASICCtrl); + + /* Configure the PCI bus bursts and FIFO thresholds. */ + + if (dev->if_port == 0) + dev->if_port = np->default_port; + + spin_lock_init(&np->mcastlock); + + set_rx_mode(dev); + iowrite16(0, ioaddr + IntrEnable); + iowrite16(0, ioaddr + DownCounter); + /* Set the chip to poll every N*320nsec. */ + iowrite8(100, ioaddr + RxDMAPollPeriod); + iowrite8(127, ioaddr + TxDMAPollPeriod); + /* Fix DFE-580TX packet drop issue */ + if (np->pci_dev->revision >= 0x14) + iowrite8(0x01, ioaddr + DebugCtrl1); + netif_start_queue(dev); + + spin_lock_irqsave(&np->lock, flags); + reset_tx(dev); + spin_unlock_irqrestore(&np->lock, flags); + + iowrite16 (StatsEnable | RxEnable | TxEnable, ioaddr + MACCtrl1); + + /* Disable Wol */ + iowrite8(ioread8(ioaddr + WakeEvent) | 0x00, ioaddr + WakeEvent); + np->wol_enabled = 0; + + if (netif_msg_ifup(np)) + printk(KERN_DEBUG "%s: Done netdev_open(), status: Rx %x Tx %x " + "MAC Control %x, %4.4x %4.4x.\n", + dev->name, ioread32(ioaddr + RxStatus), ioread8(ioaddr + TxStatus), + ioread32(ioaddr + MACCtrl0), + ioread16(ioaddr + MACCtrl1), ioread16(ioaddr + MACCtrl0)); + + /* Set the timer to check for link beat. */ + timer_setup(&np->timer, netdev_timer, 0); + np->timer.expires = jiffies + 3*HZ; + add_timer(&np->timer); + + /* Enable interrupts by setting the interrupt mask. */ + iowrite16(DEFAULT_INTR, ioaddr + IntrEnable); + + return 0; +} + +static void check_duplex(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + int mii_lpa = mdio_read(dev, np->phys[0], MII_LPA); + int negotiated = mii_lpa & np->mii_if.advertising; + int duplex; + + /* Force media */ + if (!np->an_enable || mii_lpa == 0xffff) { + if (np->mii_if.full_duplex) + iowrite16 (ioread16 (ioaddr + MACCtrl0) | EnbFullDuplex, + ioaddr + MACCtrl0); + return; + } + + /* Autonegotiation */ + duplex = (negotiated & 0x0100) || (negotiated & 0x01C0) == 0x0040; + if (np->mii_if.full_duplex != duplex) { + np->mii_if.full_duplex = duplex; + if (netif_msg_link(np)) + printk(KERN_INFO "%s: Setting %s-duplex based on MII #%d " + "negotiated capability %4.4x.\n", dev->name, + duplex ? "full" : "half", np->phys[0], negotiated); + iowrite16(ioread16(ioaddr + MACCtrl0) | (duplex ? 0x20 : 0), ioaddr + MACCtrl0); + } +} + +static void netdev_timer(struct timer_list *t) +{ + struct netdev_private *np = timer_container_of(np, t, timer); + struct net_device *dev = np->mii_if.dev; + void __iomem *ioaddr = np->base; + int next_tick = 10*HZ; + + if (netif_msg_timer(np)) { + printk(KERN_DEBUG "%s: Media selection timer tick, intr status %4.4x, " + "Tx %x Rx %x.\n", + dev->name, ioread16(ioaddr + IntrEnable), + ioread8(ioaddr + TxStatus), ioread32(ioaddr + RxStatus)); + } + check_duplex(dev); + np->timer.expires = jiffies + next_tick; + add_timer(&np->timer); +} + +static void tx_timeout(struct net_device *dev, unsigned int txqueue) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + unsigned long flag; + + netif_stop_queue(dev); + tasklet_disable_in_atomic(&np->tx_tasklet); + iowrite16(0, ioaddr + IntrEnable); + printk(KERN_WARNING "%s: Transmit timed out, TxStatus %2.2x " + "TxFrameId %2.2x," + " resetting...\n", dev->name, ioread8(ioaddr + TxStatus), + ioread8(ioaddr + TxFrameId)); + + { + int i; + for (i=0; i<TX_RING_SIZE; i++) { + printk(KERN_DEBUG "%02x %08llx %08x %08x(%02x) %08x %08x\n", i, + (unsigned long long)(np->tx_ring_dma + i*sizeof(*np->tx_ring)), + le32_to_cpu(np->tx_ring[i].next_desc), + le32_to_cpu(np->tx_ring[i].status), + (le32_to_cpu(np->tx_ring[i].status) >> 2) & 0xff, + le32_to_cpu(np->tx_ring[i].frag.addr), + le32_to_cpu(np->tx_ring[i].frag.length)); + } + printk(KERN_DEBUG "TxListPtr=%08x netif_queue_stopped=%d\n", + ioread32(np->base + TxListPtr), + netif_queue_stopped(dev)); + printk(KERN_DEBUG "cur_tx=%d(%02x) dirty_tx=%d(%02x)\n", + np->cur_tx, np->cur_tx % TX_RING_SIZE, + np->dirty_tx, np->dirty_tx % TX_RING_SIZE); + printk(KERN_DEBUG "cur_rx=%d dirty_rx=%d\n", np->cur_rx, np->dirty_rx); + printk(KERN_DEBUG "cur_task=%d\n", np->cur_task); + } + spin_lock_irqsave(&np->lock, flag); + + /* Stop and restart the chip's Tx processes . */ + reset_tx(dev); + spin_unlock_irqrestore(&np->lock, flag); + + dev->if_port = 0; + + netif_trans_update(dev); /* prevent tx timeout */ + dev->stats.tx_errors++; + if (np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 4) { + netif_wake_queue(dev); + } + iowrite16(DEFAULT_INTR, ioaddr + IntrEnable); + tasklet_enable(&np->tx_tasklet); +} + + +/* Initialize the Rx and Tx rings, along with various 'dev' bits. */ +static void init_ring(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + int i; + + np->cur_rx = np->cur_tx = 0; + np->dirty_rx = np->dirty_tx = 0; + np->cur_task = 0; + + np->rx_buf_sz = (dev->mtu <= 1520 ? PKT_BUF_SZ : dev->mtu + 16); + + /* Initialize all Rx descriptors. */ + for (i = 0; i < RX_RING_SIZE; i++) { + np->rx_ring[i].next_desc = cpu_to_le32(np->rx_ring_dma + + ((i+1)%RX_RING_SIZE)*sizeof(*np->rx_ring)); + np->rx_ring[i].status = 0; + np->rx_ring[i].frag.length = 0; + np->rx_skbuff[i] = NULL; + } + + /* Fill in the Rx buffers. Handle allocation failure gracefully. */ + for (i = 0; i < RX_RING_SIZE; i++) { + dma_addr_t addr; + + struct sk_buff *skb = + netdev_alloc_skb(dev, np->rx_buf_sz + 2); + np->rx_skbuff[i] = skb; + if (skb == NULL) + break; + skb_reserve(skb, 2); /* 16 byte align the IP header. */ + addr = dma_map_single(&np->pci_dev->dev, skb->data, + np->rx_buf_sz, DMA_FROM_DEVICE); + if (dma_mapping_error(&np->pci_dev->dev, addr)) { + dev_kfree_skb(skb); + np->rx_skbuff[i] = NULL; + break; + } + np->rx_ring[i].frag.addr = cpu_to_le32(addr); + np->rx_ring[i].frag.length = cpu_to_le32(np->rx_buf_sz | LastFrag); + } + np->dirty_rx = (unsigned int)(i - RX_RING_SIZE); + + for (i = 0; i < TX_RING_SIZE; i++) { + np->tx_skbuff[i] = NULL; + np->tx_ring[i].status = 0; + } +} + +static void tx_poll(struct tasklet_struct *t) +{ + struct netdev_private *np = from_tasklet(np, t, tx_tasklet); + unsigned head = np->cur_task % TX_RING_SIZE; + struct netdev_desc *txdesc = + &np->tx_ring[(np->cur_tx - 1) % TX_RING_SIZE]; + + /* Chain the next pointer */ + for (; np->cur_tx - np->cur_task > 0; np->cur_task++) { + int entry = np->cur_task % TX_RING_SIZE; + txdesc = &np->tx_ring[entry]; + if (np->last_tx) { + np->last_tx->next_desc = cpu_to_le32(np->tx_ring_dma + + entry*sizeof(struct netdev_desc)); + } + np->last_tx = txdesc; + } + /* Indicate the latest descriptor of tx ring */ + txdesc->status |= cpu_to_le32(DescIntrOnTx); + + if (ioread32 (np->base + TxListPtr) == 0) + iowrite32 (np->tx_ring_dma + head * sizeof(struct netdev_desc), + np->base + TxListPtr); +} + +static netdev_tx_t +start_tx (struct sk_buff *skb, struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + struct netdev_desc *txdesc; + dma_addr_t addr; + unsigned entry; + + /* Calculate the next Tx descriptor entry. */ + entry = np->cur_tx % TX_RING_SIZE; + np->tx_skbuff[entry] = skb; + txdesc = &np->tx_ring[entry]; + + addr = dma_map_single(&np->pci_dev->dev, skb->data, skb->len, + DMA_TO_DEVICE); + if (dma_mapping_error(&np->pci_dev->dev, addr)) + goto drop_frame; + + txdesc->next_desc = 0; + txdesc->status = cpu_to_le32 ((entry << 2) | DisableAlign); + txdesc->frag.addr = cpu_to_le32(addr); + txdesc->frag.length = cpu_to_le32 (skb->len | LastFrag); + + /* Increment cur_tx before tasklet_schedule() */ + np->cur_tx++; + mb(); + /* Schedule a tx_poll() task */ + tasklet_schedule(&np->tx_tasklet); + + /* On some architectures: explicitly flush cache lines here. */ + if (np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 1 && + !netif_queue_stopped(dev)) { + /* do nothing */ + } else { + netif_stop_queue (dev); + } + if (netif_msg_tx_queued(np)) { + printk (KERN_DEBUG + "%s: Transmit frame #%d queued in slot %d.\n", + dev->name, np->cur_tx, entry); + } + return NETDEV_TX_OK; + +drop_frame: + dev_kfree_skb_any(skb); + np->tx_skbuff[entry] = NULL; + dev->stats.tx_dropped++; + return NETDEV_TX_OK; +} + +/* Reset hardware tx and free all of tx buffers */ +static int +reset_tx (struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + struct sk_buff *skb; + int i; + + /* Reset tx logic, TxListPtr will be cleaned */ + iowrite16 (TxDisable, ioaddr + MACCtrl1); + sundance_reset(dev, (NetworkReset|FIFOReset|DMAReset|TxReset) << 16); + + /* free all tx skbuff */ + for (i = 0; i < TX_RING_SIZE; i++) { + np->tx_ring[i].next_desc = 0; + + skb = np->tx_skbuff[i]; + if (skb) { + dma_unmap_single(&np->pci_dev->dev, + le32_to_cpu(np->tx_ring[i].frag.addr), + skb->len, DMA_TO_DEVICE); + dev_kfree_skb_any(skb); + np->tx_skbuff[i] = NULL; + dev->stats.tx_dropped++; + } + } + np->cur_tx = np->dirty_tx = 0; + np->cur_task = 0; + + np->last_tx = NULL; + iowrite8(127, ioaddr + TxDMAPollPeriod); + + iowrite16 (StatsEnable | RxEnable | TxEnable, ioaddr + MACCtrl1); + return 0; +} + +/* The interrupt handler cleans up after the Tx thread, + and schedule a Rx thread work */ +static irqreturn_t intr_handler(int irq, void *dev_instance) +{ + struct net_device *dev = (struct net_device *)dev_instance; + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + int hw_frame_id; + int tx_cnt; + int tx_status; + int handled = 0; + int i; + + do { + int intr_status = ioread16(ioaddr + IntrStatus); + iowrite16(intr_status, ioaddr + IntrStatus); + + if (netif_msg_intr(np)) + printk(KERN_DEBUG "%s: Interrupt, status %4.4x.\n", + dev->name, intr_status); + + if (!(intr_status & DEFAULT_INTR)) + break; + + handled = 1; + + if (intr_status & (IntrRxDMADone)) { + iowrite16(DEFAULT_INTR & ~(IntrRxDone|IntrRxDMADone), + ioaddr + IntrEnable); + if (np->budget < 0) + np->budget = RX_BUDGET; + tasklet_schedule(&np->rx_tasklet); + } + if (intr_status & (IntrTxDone | IntrDrvRqst)) { + tx_status = ioread16 (ioaddr + TxStatus); + for (tx_cnt=32; tx_status & 0x80; --tx_cnt) { + if (netif_msg_tx_done(np)) + printk + ("%s: Transmit status is %2.2x.\n", + dev->name, tx_status); + if (tx_status & 0x1e) { + if (netif_msg_tx_err(np)) + printk("%s: Transmit error status %4.4x.\n", + dev->name, tx_status); + dev->stats.tx_errors++; + if (tx_status & 0x10) + dev->stats.tx_fifo_errors++; + if (tx_status & 0x08) + dev->stats.collisions++; + if (tx_status & 0x04) + dev->stats.tx_fifo_errors++; + if (tx_status & 0x02) + dev->stats.tx_window_errors++; + + /* + ** This reset has been verified on + ** DFE-580TX boards ! phdm@macqel.be. + */ + if (tx_status & 0x10) { /* TxUnderrun */ + /* Restart Tx FIFO and transmitter */ + sundance_reset(dev, (NetworkReset|FIFOReset|TxReset) << 16); + /* No need to reset the Tx pointer here */ + } + /* Restart the Tx. Need to make sure tx enabled */ + i = 10; + do { + iowrite16(ioread16(ioaddr + MACCtrl1) | TxEnable, ioaddr + MACCtrl1); + if (ioread16(ioaddr + MACCtrl1) & TxEnabled) + break; + mdelay(1); + } while (--i); + } + /* Yup, this is a documentation bug. It cost me *hours*. */ + iowrite16 (0, ioaddr + TxStatus); + if (tx_cnt < 0) { + iowrite32(5000, ioaddr + DownCounter); + break; + } + tx_status = ioread16 (ioaddr + TxStatus); + } + hw_frame_id = (tx_status >> 8) & 0xff; + } else { + hw_frame_id = ioread8(ioaddr + TxFrameId); + } + + if (np->pci_dev->revision >= 0x14) { + spin_lock(&np->lock); + for (; np->cur_tx - np->dirty_tx > 0; np->dirty_tx++) { + int entry = np->dirty_tx % TX_RING_SIZE; + struct sk_buff *skb; + int sw_frame_id; + sw_frame_id = (le32_to_cpu( + np->tx_ring[entry].status) >> 2) & 0xff; + if (sw_frame_id == hw_frame_id && + !(le32_to_cpu(np->tx_ring[entry].status) + & 0x00010000)) + break; + if (sw_frame_id == (hw_frame_id + 1) % + TX_RING_SIZE) + break; + skb = np->tx_skbuff[entry]; + /* Free the original skb. */ + dma_unmap_single(&np->pci_dev->dev, + le32_to_cpu(np->tx_ring[entry].frag.addr), + skb->len, DMA_TO_DEVICE); + dev_consume_skb_irq(np->tx_skbuff[entry]); + np->tx_skbuff[entry] = NULL; + np->tx_ring[entry].frag.addr = 0; + np->tx_ring[entry].frag.length = 0; + } + spin_unlock(&np->lock); + } else { + spin_lock(&np->lock); + for (; np->cur_tx - np->dirty_tx > 0; np->dirty_tx++) { + int entry = np->dirty_tx % TX_RING_SIZE; + struct sk_buff *skb; + if (!(le32_to_cpu(np->tx_ring[entry].status) + & 0x00010000)) + break; + skb = np->tx_skbuff[entry]; + /* Free the original skb. */ + dma_unmap_single(&np->pci_dev->dev, + le32_to_cpu(np->tx_ring[entry].frag.addr), + skb->len, DMA_TO_DEVICE); + dev_consume_skb_irq(np->tx_skbuff[entry]); + np->tx_skbuff[entry] = NULL; + np->tx_ring[entry].frag.addr = 0; + np->tx_ring[entry].frag.length = 0; + } + spin_unlock(&np->lock); + } + + if (netif_queue_stopped(dev) && + np->cur_tx - np->dirty_tx < TX_QUEUE_LEN - 4) { + /* The ring is no longer full, clear busy flag. */ + netif_wake_queue (dev); + } + /* Abnormal error summary/uncommon events handlers. */ + if (intr_status & (IntrPCIErr | LinkChange | StatsMax)) + netdev_error(dev, intr_status); + } while (0); + if (netif_msg_intr(np)) + printk(KERN_DEBUG "%s: exiting interrupt, status=%#4.4x.\n", + dev->name, ioread16(ioaddr + IntrStatus)); + return IRQ_RETVAL(handled); +} + +static void rx_poll(struct tasklet_struct *t) +{ + struct netdev_private *np = from_tasklet(np, t, rx_tasklet); + struct net_device *dev = np->ndev; + int entry = np->cur_rx % RX_RING_SIZE; + int boguscnt = np->budget; + void __iomem *ioaddr = np->base; + int received = 0; + + /* If EOP is set on the next entry, it's a new packet. Send it up. */ + while (1) { + struct netdev_desc *desc = &(np->rx_ring[entry]); + u32 frame_status = le32_to_cpu(desc->status); + int pkt_len; + + if (--boguscnt < 0) { + goto not_done; + } + if (!(frame_status & DescOwn)) + break; + pkt_len = frame_status & 0x1fff; /* Chip omits the CRC. */ + if (netif_msg_rx_status(np)) + printk(KERN_DEBUG " netdev_rx() status was %8.8x.\n", + frame_status); + if (frame_status & 0x001f4000) { + /* There was a error. */ + if (netif_msg_rx_err(np)) + printk(KERN_DEBUG " netdev_rx() Rx error was %8.8x.\n", + frame_status); + dev->stats.rx_errors++; + if (frame_status & 0x00100000) + dev->stats.rx_length_errors++; + if (frame_status & 0x00010000) + dev->stats.rx_fifo_errors++; + if (frame_status & 0x00060000) + dev->stats.rx_frame_errors++; + if (frame_status & 0x00080000) + dev->stats.rx_crc_errors++; + if (frame_status & 0x00100000) { + printk(KERN_WARNING "%s: Oversized Ethernet frame," + " status %8.8x.\n", + dev->name, frame_status); + } + } else { + struct sk_buff *skb; +#ifndef final_version + if (netif_msg_rx_status(np)) + printk(KERN_DEBUG " netdev_rx() normal Rx pkt length %d" + ", bogus_cnt %d.\n", + pkt_len, boguscnt); +#endif + /* Check if the packet is long enough to accept without copying + to a minimally-sized skbuff. */ + if (pkt_len < rx_copybreak && + (skb = netdev_alloc_skb(dev, pkt_len + 2)) != NULL) { + skb_reserve(skb, 2); /* 16 byte align the IP header */ + dma_sync_single_for_cpu(&np->pci_dev->dev, + le32_to_cpu(desc->frag.addr), + np->rx_buf_sz, DMA_FROM_DEVICE); + skb_copy_to_linear_data(skb, np->rx_skbuff[entry]->data, pkt_len); + dma_sync_single_for_device(&np->pci_dev->dev, + le32_to_cpu(desc->frag.addr), + np->rx_buf_sz, DMA_FROM_DEVICE); + skb_put(skb, pkt_len); + } else { + dma_unmap_single(&np->pci_dev->dev, + le32_to_cpu(desc->frag.addr), + np->rx_buf_sz, DMA_FROM_DEVICE); + skb_put(skb = np->rx_skbuff[entry], pkt_len); + np->rx_skbuff[entry] = NULL; + } + skb->protocol = eth_type_trans(skb, dev); + /* Note: checksum -> skb->ip_summed = CHECKSUM_UNNECESSARY; */ + netif_rx(skb); + } + entry = (entry + 1) % RX_RING_SIZE; + received++; + } + np->cur_rx = entry; + refill_rx (dev); + np->budget -= received; + iowrite16(DEFAULT_INTR, ioaddr + IntrEnable); + return; + +not_done: + np->cur_rx = entry; + refill_rx (dev); + if (!received) + received = 1; + np->budget -= received; + if (np->budget <= 0) + np->budget = RX_BUDGET; + tasklet_schedule(&np->rx_tasklet); +} + +static void refill_rx (struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + int entry; + + /* Refill the Rx ring buffers. */ + for (;(np->cur_rx - np->dirty_rx + RX_RING_SIZE) % RX_RING_SIZE > 0; + np->dirty_rx = (np->dirty_rx + 1) % RX_RING_SIZE) { + struct sk_buff *skb; + dma_addr_t addr; + + entry = np->dirty_rx % RX_RING_SIZE; + if (np->rx_skbuff[entry] == NULL) { + skb = netdev_alloc_skb(dev, np->rx_buf_sz + 2); + np->rx_skbuff[entry] = skb; + if (skb == NULL) + break; /* Better luck next round. */ + skb_reserve(skb, 2); /* Align IP on 16 byte boundaries */ + addr = dma_map_single(&np->pci_dev->dev, skb->data, + np->rx_buf_sz, DMA_FROM_DEVICE); + if (dma_mapping_error(&np->pci_dev->dev, addr)) { + dev_kfree_skb_irq(skb); + np->rx_skbuff[entry] = NULL; + break; + } + + np->rx_ring[entry].frag.addr = cpu_to_le32(addr); + } + /* Perhaps we need not reset this field. */ + np->rx_ring[entry].frag.length = + cpu_to_le32(np->rx_buf_sz | LastFrag); + np->rx_ring[entry].status = 0; + } +} +static void netdev_error(struct net_device *dev, int intr_status) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + u16 mii_ctl, mii_advertise, mii_lpa; + int speed; + + if (intr_status & LinkChange) { + if (mdio_wait_link(dev, 10) == 0) { + printk(KERN_INFO "%s: Link up\n", dev->name); + if (np->an_enable) { + mii_advertise = mdio_read(dev, np->phys[0], + MII_ADVERTISE); + mii_lpa = mdio_read(dev, np->phys[0], MII_LPA); + mii_advertise &= mii_lpa; + printk(KERN_INFO "%s: Link changed: ", + dev->name); + if (mii_advertise & ADVERTISE_100FULL) { + np->speed = 100; + printk("100Mbps, full duplex\n"); + } else if (mii_advertise & ADVERTISE_100HALF) { + np->speed = 100; + printk("100Mbps, half duplex\n"); + } else if (mii_advertise & ADVERTISE_10FULL) { + np->speed = 10; + printk("10Mbps, full duplex\n"); + } else if (mii_advertise & ADVERTISE_10HALF) { + np->speed = 10; + printk("10Mbps, half duplex\n"); + } else + printk("\n"); + + } else { + mii_ctl = mdio_read(dev, np->phys[0], MII_BMCR); + speed = (mii_ctl & BMCR_SPEED100) ? 100 : 10; + np->speed = speed; + printk(KERN_INFO "%s: Link changed: %dMbps ,", + dev->name, speed); + printk("%s duplex.\n", + (mii_ctl & BMCR_FULLDPLX) ? + "full" : "half"); + } + check_duplex(dev); + if (np->flowctrl && np->mii_if.full_duplex) { + iowrite16(ioread16(ioaddr + MulticastFilter1+2) | 0x0200, + ioaddr + MulticastFilter1+2); + iowrite16(ioread16(ioaddr + MACCtrl0) | EnbFlowCtrl, + ioaddr + MACCtrl0); + } + netif_carrier_on(dev); + } else { + printk(KERN_INFO "%s: Link down\n", dev->name); + netif_carrier_off(dev); + } + } + if (intr_status & StatsMax) { + get_stats(dev); + } + if (intr_status & IntrPCIErr) { + printk(KERN_ERR "%s: Something Wicked happened! %4.4x.\n", + dev->name, intr_status); + /* We must do a global reset of DMA to continue. */ + } +} + +static struct net_device_stats *get_stats(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + unsigned long flags; + u8 late_coll, single_coll, mult_coll; + + spin_lock_irqsave(&np->statlock, flags); + /* The chip only need report frame silently dropped. */ + dev->stats.rx_missed_errors += ioread8(ioaddr + RxMissed); + dev->stats.tx_packets += ioread16(ioaddr + TxFramesOK); + dev->stats.rx_packets += ioread16(ioaddr + RxFramesOK); + dev->stats.tx_carrier_errors += ioread8(ioaddr + StatsCarrierError); + + mult_coll = ioread8(ioaddr + StatsMultiColl); + np->xstats.tx_multiple_collisions += mult_coll; + single_coll = ioread8(ioaddr + StatsOneColl); + np->xstats.tx_single_collisions += single_coll; + late_coll = ioread8(ioaddr + StatsLateColl); + np->xstats.tx_late_collisions += late_coll; + dev->stats.collisions += mult_coll + + single_coll + + late_coll; + + np->xstats.tx_deferred += ioread8(ioaddr + StatsTxDefer); + np->xstats.tx_deferred_excessive += ioread8(ioaddr + StatsTxXSDefer); + np->xstats.tx_aborted += ioread8(ioaddr + StatsTxAbort); + np->xstats.tx_bcasts += ioread8(ioaddr + StatsBcastTx); + np->xstats.rx_bcasts += ioread8(ioaddr + StatsBcastRx); + np->xstats.tx_mcasts += ioread8(ioaddr + StatsMcastTx); + np->xstats.rx_mcasts += ioread8(ioaddr + StatsMcastRx); + + dev->stats.tx_bytes += ioread16(ioaddr + TxOctetsLow); + dev->stats.tx_bytes += ioread16(ioaddr + TxOctetsHigh) << 16; + dev->stats.rx_bytes += ioread16(ioaddr + RxOctetsLow); + dev->stats.rx_bytes += ioread16(ioaddr + RxOctetsHigh) << 16; + + spin_unlock_irqrestore(&np->statlock, flags); + + return &dev->stats; +} + +static void set_rx_mode(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + u16 mc_filter[4]; /* Multicast hash filter */ + u32 rx_mode; + int i; + + if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ + memset(mc_filter, 0xff, sizeof(mc_filter)); + rx_mode = AcceptBroadcast | AcceptMulticast | AcceptAll | AcceptMyPhys; + } else if ((netdev_mc_count(dev) > multicast_filter_limit) || + (dev->flags & IFF_ALLMULTI)) { + /* Too many to match, or accept all multicasts. */ + memset(mc_filter, 0xff, sizeof(mc_filter)); + rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; + } else if (!netdev_mc_empty(dev)) { + struct netdev_hw_addr *ha; + int bit; + int index; + int crc; + memset (mc_filter, 0, sizeof (mc_filter)); + netdev_for_each_mc_addr(ha, dev) { + crc = ether_crc_le(ETH_ALEN, ha->addr); + for (index=0, bit=0; bit < 6; bit++, crc <<= 1) + if (crc & 0x80000000) index |= 1 << bit; + mc_filter[index/16] |= (1 << (index % 16)); + } + rx_mode = AcceptBroadcast | AcceptMultiHash | AcceptMyPhys; + } else { + iowrite8(AcceptBroadcast | AcceptMyPhys, ioaddr + RxMode); + return; + } + if (np->mii_if.full_duplex && np->flowctrl) + mc_filter[3] |= 0x0200; + + for (i = 0; i < 4; i++) + iowrite16(mc_filter[i], ioaddr + MulticastFilter0 + i*2); + iowrite8(rx_mode, ioaddr + RxMode); +} + +static int __set_mac_addr(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + u16 addr16; + + addr16 = (dev->dev_addr[0] | (dev->dev_addr[1] << 8)); + iowrite16(addr16, np->base + StationAddr); + addr16 = (dev->dev_addr[2] | (dev->dev_addr[3] << 8)); + iowrite16(addr16, np->base + StationAddr+2); + addr16 = (dev->dev_addr[4] | (dev->dev_addr[5] << 8)); + iowrite16(addr16, np->base + StationAddr+4); + return 0; +} + +/* Invoked with rtnl_lock held */ +static int sundance_set_mac_addr(struct net_device *dev, void *data) +{ + const struct sockaddr *addr = data; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + eth_hw_addr_set(dev, addr->sa_data); + __set_mac_addr(dev); + + return 0; +} + +static const struct { + const char name[ETH_GSTRING_LEN]; +} sundance_stats[] = { + { "tx_multiple_collisions" }, + { "tx_single_collisions" }, + { "tx_late_collisions" }, + { "tx_deferred" }, + { "tx_deferred_excessive" }, + { "tx_aborted" }, + { "tx_bcasts" }, + { "rx_bcasts" }, + { "tx_mcasts" }, + { "rx_mcasts" }, +}; + +static int check_if_running(struct net_device *dev) +{ + if (!netif_running(dev)) + return -EINVAL; + return 0; +} + +static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) +{ + struct netdev_private *np = netdev_priv(dev); + strscpy(info->driver, DRV_NAME, sizeof(info->driver)); + strscpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info)); +} + +static int get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + struct netdev_private *np = netdev_priv(dev); + spin_lock_irq(&np->lock); + mii_ethtool_get_link_ksettings(&np->mii_if, cmd); + spin_unlock_irq(&np->lock); + return 0; +} + +static int set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) +{ + struct netdev_private *np = netdev_priv(dev); + int res; + spin_lock_irq(&np->lock); + res = mii_ethtool_set_link_ksettings(&np->mii_if, cmd); + spin_unlock_irq(&np->lock); + return res; +} + +static int nway_reset(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + return mii_nway_restart(&np->mii_if); +} + +static u32 get_link(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + return mii_link_ok(&np->mii_if); +} + +static u32 get_msglevel(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + return np->msg_enable; +} + +static void set_msglevel(struct net_device *dev, u32 val) +{ + struct netdev_private *np = netdev_priv(dev); + np->msg_enable = val; +} + +static void get_strings(struct net_device *dev, u32 stringset, + u8 *data) +{ + if (stringset == ETH_SS_STATS) + memcpy(data, sundance_stats, sizeof(sundance_stats)); +} + +static int get_sset_count(struct net_device *dev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return ARRAY_SIZE(sundance_stats); + default: + return -EOPNOTSUPP; + } +} + +static void get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct netdev_private *np = netdev_priv(dev); + int i = 0; + + get_stats(dev); + data[i++] = np->xstats.tx_multiple_collisions; + data[i++] = np->xstats.tx_single_collisions; + data[i++] = np->xstats.tx_late_collisions; + data[i++] = np->xstats.tx_deferred; + data[i++] = np->xstats.tx_deferred_excessive; + data[i++] = np->xstats.tx_aborted; + data[i++] = np->xstats.tx_bcasts; + data[i++] = np->xstats.rx_bcasts; + data[i++] = np->xstats.tx_mcasts; + data[i++] = np->xstats.rx_mcasts; +} + +#ifdef CONFIG_PM + +static void sundance_get_wol(struct net_device *dev, + struct ethtool_wolinfo *wol) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + u8 wol_bits; + + wol->wolopts = 0; + + wol->supported = (WAKE_PHY | WAKE_MAGIC); + if (!np->wol_enabled) + return; + + wol_bits = ioread8(ioaddr + WakeEvent); + if (wol_bits & MagicPktEnable) + wol->wolopts |= WAKE_MAGIC; + if (wol_bits & LinkEventEnable) + wol->wolopts |= WAKE_PHY; +} + +static int sundance_set_wol(struct net_device *dev, + struct ethtool_wolinfo *wol) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + u8 wol_bits; + + if (!device_can_wakeup(&np->pci_dev->dev)) + return -EOPNOTSUPP; + + np->wol_enabled = !!(wol->wolopts); + wol_bits = ioread8(ioaddr + WakeEvent); + wol_bits &= ~(WakePktEnable | MagicPktEnable | + LinkEventEnable | WolEnable); + + if (np->wol_enabled) { + if (wol->wolopts & WAKE_MAGIC) + wol_bits |= (MagicPktEnable | WolEnable); + if (wol->wolopts & WAKE_PHY) + wol_bits |= (LinkEventEnable | WolEnable); + } + iowrite8(wol_bits, ioaddr + WakeEvent); + + device_set_wakeup_enable(&np->pci_dev->dev, np->wol_enabled); + + return 0; +} +#else +#define sundance_get_wol NULL +#define sundance_set_wol NULL +#endif /* CONFIG_PM */ + +static const struct ethtool_ops ethtool_ops = { + .begin = check_if_running, + .get_drvinfo = get_drvinfo, + .nway_reset = nway_reset, + .get_link = get_link, + .get_wol = sundance_get_wol, + .set_wol = sundance_set_wol, + .get_msglevel = get_msglevel, + .set_msglevel = set_msglevel, + .get_strings = get_strings, + .get_sset_count = get_sset_count, + .get_ethtool_stats = get_ethtool_stats, + .get_link_ksettings = get_link_ksettings, + .set_link_ksettings = set_link_ksettings, +}; + +static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +{ + struct netdev_private *np = netdev_priv(dev); + int rc; + + if (!netif_running(dev)) + return -EINVAL; + + spin_lock_irq(&np->lock); + rc = generic_mii_ioctl(&np->mii_if, if_mii(rq), cmd, NULL); + spin_unlock_irq(&np->lock); + + return rc; +} + +static int netdev_close(struct net_device *dev) +{ + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + struct sk_buff *skb; + int i; + + /* Wait and kill tasklet */ + tasklet_kill(&np->rx_tasklet); + tasklet_kill(&np->tx_tasklet); + np->cur_tx = 0; + np->dirty_tx = 0; + np->cur_task = 0; + np->last_tx = NULL; + + netif_stop_queue(dev); + + if (netif_msg_ifdown(np)) { + printk(KERN_DEBUG "%s: Shutting down ethercard, status was Tx %2.2x " + "Rx %4.4x Int %2.2x.\n", + dev->name, ioread8(ioaddr + TxStatus), + ioread32(ioaddr + RxStatus), ioread16(ioaddr + IntrStatus)); + printk(KERN_DEBUG "%s: Queue pointers were Tx %d / %d, Rx %d / %d.\n", + dev->name, np->cur_tx, np->dirty_tx, np->cur_rx, np->dirty_rx); + } + + /* Disable interrupts by clearing the interrupt mask. */ + iowrite16(0x0000, ioaddr + IntrEnable); + + /* Disable Rx and Tx DMA for safely release resource */ + iowrite32(0x500, ioaddr + DMACtrl); + + /* Stop the chip's Tx and Rx processes. */ + iowrite16(TxDisable | RxDisable | StatsDisable, ioaddr + MACCtrl1); + + for (i = 2000; i > 0; i--) { + if ((ioread32(ioaddr + DMACtrl) & 0xc000) == 0) + break; + mdelay(1); + } + + iowrite16(GlobalReset | DMAReset | FIFOReset | NetworkReset, + ioaddr + ASIC_HI_WORD(ASICCtrl)); + + for (i = 2000; i > 0; i--) { + if ((ioread16(ioaddr + ASIC_HI_WORD(ASICCtrl)) & ResetBusy) == 0) + break; + mdelay(1); + } + +#ifdef __i386__ + if (netif_msg_hw(np)) { + printk(KERN_DEBUG " Tx ring at %8.8x:\n", + (int)(np->tx_ring_dma)); + for (i = 0; i < TX_RING_SIZE; i++) + printk(KERN_DEBUG " #%d desc. %4.4x %8.8x %8.8x.\n", + i, np->tx_ring[i].status, np->tx_ring[i].frag.addr, + np->tx_ring[i].frag.length); + printk(KERN_DEBUG " Rx ring %8.8x:\n", + (int)(np->rx_ring_dma)); + for (i = 0; i < /*RX_RING_SIZE*/4 ; i++) { + printk(KERN_DEBUG " #%d desc. %4.4x %4.4x %8.8x\n", + i, np->rx_ring[i].status, np->rx_ring[i].frag.addr, + np->rx_ring[i].frag.length); + } + } +#endif /* __i386__ debugging only */ + + free_irq(np->pci_dev->irq, dev); + + timer_delete_sync(&np->timer); + + /* Free all the skbuffs in the Rx queue. */ + for (i = 0; i < RX_RING_SIZE; i++) { + np->rx_ring[i].status = 0; + skb = np->rx_skbuff[i]; + if (skb) { + dma_unmap_single(&np->pci_dev->dev, + le32_to_cpu(np->rx_ring[i].frag.addr), + np->rx_buf_sz, DMA_FROM_DEVICE); + dev_kfree_skb(skb); + np->rx_skbuff[i] = NULL; + } + np->rx_ring[i].frag.addr = cpu_to_le32(0xBADF00D0); /* poison */ + } + for (i = 0; i < TX_RING_SIZE; i++) { + np->tx_ring[i].next_desc = 0; + skb = np->tx_skbuff[i]; + if (skb) { + dma_unmap_single(&np->pci_dev->dev, + le32_to_cpu(np->tx_ring[i].frag.addr), + skb->len, DMA_TO_DEVICE); + dev_kfree_skb(skb); + np->tx_skbuff[i] = NULL; + } + } + + return 0; +} + +static void sundance_remove1(struct pci_dev *pdev) +{ + struct net_device *dev = pci_get_drvdata(pdev); + + if (dev) { + struct netdev_private *np = netdev_priv(dev); + unregister_netdev(dev); + dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, + np->rx_ring, np->rx_ring_dma); + dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, + np->tx_ring, np->tx_ring_dma); + pci_iounmap(pdev, np->base); + pci_release_regions(pdev); + free_netdev(dev); + } +} + +static int __maybe_unused sundance_suspend(struct device *dev_d) +{ + struct net_device *dev = dev_get_drvdata(dev_d); + struct netdev_private *np = netdev_priv(dev); + void __iomem *ioaddr = np->base; + + if (!netif_running(dev)) + return 0; + + netdev_close(dev); + netif_device_detach(dev); + + if (np->wol_enabled) { + iowrite8(AcceptBroadcast | AcceptMyPhys, ioaddr + RxMode); + iowrite16(RxEnable, ioaddr + MACCtrl1); + } + + device_set_wakeup_enable(dev_d, np->wol_enabled); + + return 0; +} + +static int __maybe_unused sundance_resume(struct device *dev_d) +{ + struct net_device *dev = dev_get_drvdata(dev_d); + int err = 0; + + if (!netif_running(dev)) + return 0; + + err = netdev_open(dev); + if (err) { + printk(KERN_ERR "%s: Can't resume interface!\n", + dev->name); + goto out; + } + + netif_device_attach(dev); + +out: + return err; +} + +static SIMPLE_DEV_PM_OPS(sundance_pm_ops, sundance_suspend, sundance_resume); + +static struct pci_driver sundance_driver = { + .name = DRV_NAME, + .id_table = sundance_pci_tbl, + .probe = sundance_probe1, + .remove = sundance_remove1, + .driver.pm = &sundance_pm_ops, +}; + +module_pci_driver(sundance_driver); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 1383918f8a3f..adf1f2bbcbb1 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2363,7 +2363,8 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev) */ phy_dev = of_phy_find_device(fep->phy_node); phy_reset_after_clk_enable(phy_dev); - put_device(&phy_dev->mdio.dev); + if (phy_dev) + put_device(&phy_dev->mdio.dev); } } diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index c0bbb12eed2e..cf01a108a5bb 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -549,12 +549,12 @@ static int e1000_set_eeprom(struct net_device *netdev, { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + size_t total_len, max_len; u16 *eeprom_buff; - void *ptr; - int max_len; + int ret_val = 0; int first_word; int last_word; - int ret_val = 0; + void *ptr; u16 i; if (eeprom->len == 0) @@ -569,6 +569,10 @@ static int e1000_set_eeprom(struct net_device *netdev, max_len = hw->nvm.word_size * 2; + if (check_add_overflow(eeprom->offset, eeprom->len, &total_len) || + total_len > max_len) + return -EFBIG; + first_word = eeprom->offset >> 1; last_word = (eeprom->offset + eeprom->len - 1) >> 1; eeprom_buff = kmalloc(max_len, GFP_KERNEL); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 76d872b91a38..cc02a85ad42b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1561,6 +1561,7 @@ I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config); struct i40e_aq_set_mac_config { __le16 max_frame_size; u8 params; +#define I40E_AQ_SET_MAC_CONFIG_CRC_EN BIT(2) u8 tx_timer_priority; /* bitmap */ __le16 tx_timer_value; __le16 fc_refresh_threshold; diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index 5f1a405cbbf8..518bc738ea3b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -359,8 +359,8 @@ static void i40e_client_add_instance(struct i40e_pf *pf) if (i40e_client_get_params(vsi, &cdev->lan_info.params)) goto free_cdev; - mac = list_first_entry(&cdev->lan_info.netdev->dev_addrs.list, - struct netdev_hw_addr, list); + mac = list_first_entry_or_null(&cdev->lan_info.netdev->dev_addrs.list, + struct netdev_hw_addr, list); if (mac) ether_addr_copy(cdev->lan_info.lanmac, mac->addr); else diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 270e7e8cf9cf..59f5c1e810eb 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1190,6 +1190,40 @@ int i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, } /** + * i40e_aq_set_mac_config - Configure MAC settings + * @hw: pointer to the hw struct + * @max_frame_size: Maximum Frame Size to be supported by the port + * @cmd_details: pointer to command details structure or NULL + * + * Set MAC configuration (0x0603). Note that max_frame_size must be greater + * than zero. + * + * Return: 0 on success, or a negative error code on failure. + */ +int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_aq_set_mac_config *cmd; + struct libie_aq_desc desc; + + cmd = libie_aq_raw(&desc); + + if (max_frame_size == 0) + return -EINVAL; + + i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_mac_config); + + cmd->max_frame_size = cpu_to_le16(max_frame_size); + cmd->params = I40E_AQ_SET_MAC_CONFIG_CRC_EN; + +#define I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD 0x7FFF + cmd->fc_refresh_threshold = + cpu_to_le16(I40E_AQ_SET_MAC_CONFIG_FC_DEFAULT_THRESHOLD); + + return i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details); +} + +/** * i40e_aq_clear_pxe_mode * @hw: pointer to the hw struct * @cmd_details: pointer to command details structure or NULL diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 6cd6f23d42a6..c17b5d290f0a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -40,48 +40,6 @@ static struct i40e_vsi *i40e_dbg_find_vsi(struct i40e_pf *pf, int seid) * setup, adding or removing filters, or other things. Many of * these will be useful for some forms of unit testing. **************************************************************/ -static char i40e_dbg_command_buf[256] = ""; - -/** - * i40e_dbg_command_read - read for command datum - * @filp: the opened file - * @buffer: where to write the data for the user to read - * @count: the size of the user's buffer - * @ppos: file position offset - **/ -static ssize_t i40e_dbg_command_read(struct file *filp, char __user *buffer, - size_t count, loff_t *ppos) -{ - struct i40e_pf *pf = filp->private_data; - struct i40e_vsi *main_vsi; - int bytes_not_copied; - int buf_size = 256; - char *buf; - int len; - - /* don't allow partial reads */ - if (*ppos != 0) - return 0; - if (count < buf_size) - return -ENOSPC; - - buf = kzalloc(buf_size, GFP_KERNEL); - if (!buf) - return -ENOSPC; - - main_vsi = i40e_pf_get_main_vsi(pf); - len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name, - i40e_dbg_command_buf); - - bytes_not_copied = copy_to_user(buffer, buf, len); - kfree(buf); - - if (bytes_not_copied) - return -EFAULT; - - *ppos = len; - return len; -} static char *i40e_filter_state_string[] = { "INVALID", @@ -1621,7 +1579,6 @@ command_write_done: static const struct file_operations i40e_dbg_command_fops = { .owner = THIS_MODULE, .open = simple_open, - .read = i40e_dbg_command_read, .write = i40e_dbg_command_write, }; @@ -1630,48 +1587,6 @@ static const struct file_operations i40e_dbg_command_fops = { * The netdev_ops entry in debugfs is for giving the driver commands * to be executed from the netdev operations. **************************************************************/ -static char i40e_dbg_netdev_ops_buf[256] = ""; - -/** - * i40e_dbg_netdev_ops_read - read for netdev_ops datum - * @filp: the opened file - * @buffer: where to write the data for the user to read - * @count: the size of the user's buffer - * @ppos: file position offset - **/ -static ssize_t i40e_dbg_netdev_ops_read(struct file *filp, char __user *buffer, - size_t count, loff_t *ppos) -{ - struct i40e_pf *pf = filp->private_data; - struct i40e_vsi *main_vsi; - int bytes_not_copied; - int buf_size = 256; - char *buf; - int len; - - /* don't allow partal reads */ - if (*ppos != 0) - return 0; - if (count < buf_size) - return -ENOSPC; - - buf = kzalloc(buf_size, GFP_KERNEL); - if (!buf) - return -ENOSPC; - - main_vsi = i40e_pf_get_main_vsi(pf); - len = snprintf(buf, buf_size, "%s: %s\n", main_vsi->netdev->name, - i40e_dbg_netdev_ops_buf); - - bytes_not_copied = copy_to_user(buffer, buf, len); - kfree(buf); - - if (bytes_not_copied) - return -EFAULT; - - *ppos = len; - return len; -} /** * i40e_dbg_netdev_ops_write - write into netdev_ops datum @@ -1685,35 +1600,36 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp, size_t count, loff_t *ppos) { struct i40e_pf *pf = filp->private_data; + char *cmd_buf, *buf_tmp; int bytes_not_copied; struct i40e_vsi *vsi; - char *buf_tmp; int vsi_seid; int i, cnt; /* don't allow partial writes */ if (*ppos != 0) return 0; - if (count >= sizeof(i40e_dbg_netdev_ops_buf)) - return -ENOSPC; - memset(i40e_dbg_netdev_ops_buf, 0, sizeof(i40e_dbg_netdev_ops_buf)); - bytes_not_copied = copy_from_user(i40e_dbg_netdev_ops_buf, - buffer, count); - if (bytes_not_copied) + cmd_buf = kzalloc(count + 1, GFP_KERNEL); + if (!cmd_buf) + return count; + bytes_not_copied = copy_from_user(cmd_buf, buffer, count); + if (bytes_not_copied) { + kfree(cmd_buf); return -EFAULT; - i40e_dbg_netdev_ops_buf[count] = '\0'; + } + cmd_buf[count] = '\0'; - buf_tmp = strchr(i40e_dbg_netdev_ops_buf, '\n'); + buf_tmp = strchr(cmd_buf, '\n'); if (buf_tmp) { *buf_tmp = '\0'; - count = buf_tmp - i40e_dbg_netdev_ops_buf + 1; + count = buf_tmp - cmd_buf + 1; } - if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) { + if (strncmp(cmd_buf, "change_mtu", 10) == 0) { int mtu; - cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i %i", + cnt = sscanf(&cmd_buf[11], "%i %i", &vsi_seid, &mtu); if (cnt != 2) { dev_info(&pf->pdev->dev, "change_mtu <vsi_seid> <mtu>\n"); @@ -1735,8 +1651,8 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp, dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n"); } - } else if (strncmp(i40e_dbg_netdev_ops_buf, "set_rx_mode", 11) == 0) { - cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i", &vsi_seid); + } else if (strncmp(cmd_buf, "set_rx_mode", 11) == 0) { + cnt = sscanf(&cmd_buf[11], "%i", &vsi_seid); if (cnt != 1) { dev_info(&pf->pdev->dev, "set_rx_mode <vsi_seid>\n"); goto netdev_ops_write_done; @@ -1756,8 +1672,8 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp, dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n"); } - } else if (strncmp(i40e_dbg_netdev_ops_buf, "napi", 4) == 0) { - cnt = sscanf(&i40e_dbg_netdev_ops_buf[4], "%i", &vsi_seid); + } else if (strncmp(cmd_buf, "napi", 4) == 0) { + cnt = sscanf(&cmd_buf[4], "%i", &vsi_seid); if (cnt != 1) { dev_info(&pf->pdev->dev, "napi <vsi_seid>\n"); goto netdev_ops_write_done; @@ -1775,21 +1691,20 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp, dev_info(&pf->pdev->dev, "napi called\n"); } } else { - dev_info(&pf->pdev->dev, "unknown command '%s'\n", - i40e_dbg_netdev_ops_buf); + dev_info(&pf->pdev->dev, "unknown command '%s'\n", cmd_buf); dev_info(&pf->pdev->dev, "available commands\n"); dev_info(&pf->pdev->dev, " change_mtu <vsi_seid> <mtu>\n"); dev_info(&pf->pdev->dev, " set_rx_mode <vsi_seid>\n"); dev_info(&pf->pdev->dev, " napi <vsi_seid>\n"); } netdev_ops_write_done: + kfree(cmd_buf); return count; } static const struct file_operations i40e_dbg_netdev_ops_fops = { .owner = THIS_MODULE, .open = simple_open, - .read = i40e_dbg_netdev_ops_read, .write = i40e_dbg_netdev_ops_write, }; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b83f823e4917..b14019d44b58 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4156,7 +4156,7 @@ free_queue_irqs: irq_num = pf->msix_entries[base + vector].vector; irq_set_affinity_notifier(irq_num, NULL); irq_update_affinity_hint(irq_num, NULL); - free_irq(irq_num, &vsi->q_vectors[vector]); + free_irq(irq_num, vsi->q_vectors[vector]); } return err; } @@ -16045,13 +16045,17 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_dbg(&pf->pdev->dev, "get supported phy types ret = %pe last_status = %s\n", ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status)); - /* make sure the MFS hasn't been set lower than the default */ #define MAX_FRAME_SIZE_DEFAULT 0x2600 - val = FIELD_GET(I40E_PRTGL_SAH_MFS_MASK, - rd32(&pf->hw, I40E_PRTGL_SAH)); - if (val < MAX_FRAME_SIZE_DEFAULT) - dev_warn(&pdev->dev, "MFS for port %x (%d) has been set below the default (%d)\n", - pf->hw.port, val, MAX_FRAME_SIZE_DEFAULT); + + err = i40e_aq_set_mac_config(hw, MAX_FRAME_SIZE_DEFAULT, NULL); + if (err) + dev_warn(&pdev->dev, "set mac config ret = %pe last_status = %s\n", + ERR_PTR(err), libie_aq_str(pf->hw.aq.asq_last_status)); + + /* Make sure the MFS is set to the expected value */ + val = rd32(hw, I40E_PRTGL_SAH); + FIELD_MODIFY(I40E_PRTGL_SAH_MFS_MASK, &val, MAX_FRAME_SIZE_DEFAULT); + wr32(hw, I40E_PRTGL_SAH, val); /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index aef5de53ce3b..26bb7bffe361 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -98,6 +98,8 @@ int i40e_aq_set_mac_loopback(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); int i40e_aq_set_phy_int_mask(struct i40e_hw *hw, u16 mask, struct i40e_asq_cmd_details *cmd_details); +int i40e_aq_set_mac_config(struct i40e_hw *hw, u16 max_frame_size, + struct i40e_asq_cmd_details *cmd_details); int i40e_aq_clear_pxe_mode(struct i40e_hw *hw, struct i40e_asq_cmd_details *cmd_details); int i40e_aq_set_link_restart_an(struct i40e_hw *hw, diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index cae992d8f03c..77781277aa8e 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -3176,12 +3176,14 @@ static irqreturn_t ice_ll_ts_intr(int __always_unused irq, void *data) hw = &pf->hw; tx = &pf->ptp.port.tx; spin_lock_irqsave(&tx->lock, flags); - ice_ptp_complete_tx_single_tstamp(tx); + if (tx->init) { + ice_ptp_complete_tx_single_tstamp(tx); - idx = find_next_bit_wrap(tx->in_use, tx->len, - tx->last_ll_ts_idx_read + 1); - if (idx != tx->len) - ice_ptp_req_tx_single_tstamp(tx, idx); + idx = find_next_bit_wrap(tx->in_use, tx->len, + tx->last_ll_ts_idx_read + 1); + if (idx != tx->len) + ice_ptp_req_tx_single_tstamp(tx, idx); + } spin_unlock_irqrestore(&tx->lock, flags); val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M | diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index e358eb1d719f..fb0f6365a6d6 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -2701,16 +2701,19 @@ irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) */ if (hw->dev_caps.ts_dev_info.ts_ll_int_read) { struct ice_ptp_tx *tx = &pf->ptp.port.tx; - u8 idx; + u8 idx, last; if (!ice_pf_state_is_nominal(pf)) return IRQ_HANDLED; spin_lock(&tx->lock); - idx = find_next_bit_wrap(tx->in_use, tx->len, - tx->last_ll_ts_idx_read + 1); - if (idx != tx->len) - ice_ptp_req_tx_single_tstamp(tx, idx); + if (tx->init) { + last = tx->last_ll_ts_idx_read + 1; + idx = find_next_bit_wrap(tx->in_use, tx->len, + last); + if (idx != tx->len) + ice_ptp_req_tx_single_tstamp(tx, idx); + } spin_unlock(&tx->lock); return IRQ_HANDLED; diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c index 4d2905103215..7e20a07e98e5 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_idc.c +++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c @@ -247,10 +247,10 @@ static void idpf_unplug_aux_dev(struct auxiliary_device *adev) if (!adev) return; + ida_free(&idpf_idc_ida, adev->id); + auxiliary_device_delete(adev); auxiliary_device_uninit(adev); - - ida_free(&idpf_idc_ida, adev->id); } /** diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index 2c2a3e85d693..513032cb5f08 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -2344,6 +2344,7 @@ static int idpf_set_mac(struct net_device *netdev, void *p) struct idpf_netdev_priv *np = netdev_priv(netdev); struct idpf_vport_config *vport_config; struct sockaddr *addr = p; + u8 old_mac_addr[ETH_ALEN]; struct idpf_vport *vport; int err = 0; @@ -2367,17 +2368,19 @@ static int idpf_set_mac(struct net_device *netdev, void *p) if (ether_addr_equal(netdev->dev_addr, addr->sa_data)) goto unlock_mutex; + ether_addr_copy(old_mac_addr, vport->default_mac_addr); + ether_addr_copy(vport->default_mac_addr, addr->sa_data); vport_config = vport->adapter->vport_config[vport->idx]; err = idpf_add_mac_filter(vport, np, addr->sa_data, false); if (err) { __idpf_del_mac_filter(vport_config, addr->sa_data); + ether_addr_copy(vport->default_mac_addr, netdev->dev_addr); goto unlock_mutex; } - if (is_valid_ether_addr(vport->default_mac_addr)) - idpf_del_mac_filter(vport, np, vport->default_mac_addr, false); + if (is_valid_ether_addr(old_mac_addr)) + __idpf_del_mac_filter(vport_config, old_mac_addr); - ether_addr_copy(vport->default_mac_addr, addr->sa_data); eth_hw_addr_set(netdev, addr->sa_data); unlock_mutex: diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index a028c69f7fdc..6330d4a0ae07 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -3765,6 +3765,16 @@ u32 idpf_get_vport_id(struct idpf_vport *vport) return le32_to_cpu(vport_msg->vport_id); } +static void idpf_set_mac_type(struct idpf_vport *vport, + struct virtchnl2_mac_addr *mac_addr) +{ + bool is_primary; + + is_primary = ether_addr_equal(vport->default_mac_addr, mac_addr->addr); + mac_addr->type = is_primary ? VIRTCHNL2_MAC_ADDR_PRIMARY : + VIRTCHNL2_MAC_ADDR_EXTRA; +} + /** * idpf_mac_filter_async_handler - Async callback for mac filters * @adapter: private data struct @@ -3894,6 +3904,7 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport, list) { if (add && f->add) { ether_addr_copy(mac_addr[i].addr, f->macaddr); + idpf_set_mac_type(vport, &mac_addr[i]); i++; f->add = false; if (i == total_filters) @@ -3901,6 +3912,7 @@ int idpf_add_del_mac_filters(struct idpf_vport *vport, } if (!add && f->remove) { ether_addr_copy(mac_addr[i].addr, f->macaddr); + idpf_set_mac_type(vport, &mac_addr[i]); i++; f->remove = false; if (i == total_filters) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 92ef33459aec..7b8f32c5169a 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2081,11 +2081,8 @@ static void igb_diag_test(struct net_device *netdev, } else { dev_info(&adapter->pdev->dev, "online testing starting\n"); - /* PHY is powered down when interface is down */ - if (if_running && igb_link_test(adapter, &data[TEST_LINK])) + if (igb_link_test(adapter, &data[TEST_LINK])) eth_test->flags |= ETH_TEST_FL_FAILED; - else - data[TEST_LINK] = 0; /* Online tests aren't run; pass by default */ data[TEST_REG] = 0; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a9a7a94ae61e..453deb6d14b3 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4453,8 +4453,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index, - rx_ring->q_vector->napi.napi_id); + rx_ring->queue_index, 0); if (res < 0) { dev_err(dev, "Failed to register xdp_rxq index %u\n", rx_ring->queue_index); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 25c3a09ad7f1..1a2f1bdb91aa 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3571,13 +3571,13 @@ ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_keee *edata) for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) { if (hw->phy.eee_speeds_supported & ixgbe_ls_map[i].mac_speed) - linkmode_set_bit(ixgbe_lp_map[i].link_mode, + linkmode_set_bit(ixgbe_ls_map[i].link_mode, edata->supported); } for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) { if (hw->phy.eee_speeds_advertised & ixgbe_ls_map[i].mac_speed) - linkmode_set_bit(ixgbe_lp_map[i].link_mode, + linkmode_set_bit(ixgbe_ls_map[i].link_mode, edata->advertised); } diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 5a5fcde76dc0..e68997a29191 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1761,6 +1761,13 @@ static netdev_tx_t mtk_start_xmit(struct sk_buff *skb, struct net_device *dev) bool gso = false; int tx_num; + if (skb_vlan_tag_present(skb) && + !eth_proto_is_802_3(eth_hdr(skb)->h_proto)) { + skb = __vlan_hwaccel_push_inside(skb); + if (!skb) + goto dropped; + } + /* normally we can rely on the stack not calling this more than once, * however we have 2 queues running on the same ring so we need to lock * the ring access @@ -1806,8 +1813,9 @@ static netdev_tx_t mtk_start_xmit(struct sk_buff *skb, struct net_device *dev) drop: spin_unlock(ð->page_lock); - stats->tx_dropped++; dev_kfree_skb_any(skb); +dropped: + stats->tx_dropped++; return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 92a16ddb7d86..13666d50b90f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -267,8 +267,10 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, pp.dma_dir = priv->dma_dir; ring->pp = page_pool_create(&pp); - if (!ring->pp) + if (IS_ERR(ring->pp)) { + err = PTR_ERR(ring->pp); goto err_ring; + } if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0) goto err_pp; diff --git a/drivers/net/ethernet/microchip/lan865x/lan865x.c b/drivers/net/ethernet/microchip/lan865x/lan865x.c index 84c41f193561..79b800d2b72c 100644 --- a/drivers/net/ethernet/microchip/lan865x/lan865x.c +++ b/drivers/net/ethernet/microchip/lan865x/lan865x.c @@ -423,13 +423,16 @@ static void lan865x_remove(struct spi_device *spi) free_netdev(priv->netdev); } -static const struct spi_device_id spidev_spi_ids[] = { +static const struct spi_device_id lan865x_ids[] = { { .name = "lan8650" }, + { .name = "lan8651" }, {}, }; +MODULE_DEVICE_TABLE(spi, lan865x_ids); static const struct of_device_id lan865x_dt_ids[] = { { .compatible = "microchip,lan8650" }, + { .compatible = "microchip,lan8651" }, { /* Sentinel */ } }; MODULE_DEVICE_TABLE(of, lan865x_dt_ids); @@ -441,7 +444,7 @@ static struct spi_driver lan865x_driver = { }, .probe = lan865x_probe, .remove = lan865x_remove, - .id_table = spidev_spi_ids, + .id_table = lan865x_ids, }; module_spi_driver(lan865x_driver); diff --git a/drivers/net/ethernet/oa_tc6.c b/drivers/net/ethernet/oa_tc6.c index db200e4ec284..91a906a7918a 100644 --- a/drivers/net/ethernet/oa_tc6.c +++ b/drivers/net/ethernet/oa_tc6.c @@ -1249,7 +1249,8 @@ struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev) /* Set the SPI controller to pump at realtime priority */ tc6->spi->rt = true; - spi_setup(tc6->spi); + if (spi_setup(tc6->spi) < 0) + return NULL; tc6->spi_ctrl_tx_buf = devm_kzalloc(&tc6->spi->dev, OA_TC6_CTRL_SPI_BUF_SIZE, diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index ecd6ecac87bb..8b2364f5f731 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1522,7 +1522,7 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, } } - if (single_port) { + if (single_port && num_tx) { netif_txq = netdev_get_tx_queue(ndev, chn); netdev_tx_completed_queue(netif_txq, num_tx, total_bytes); am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq); diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index dadce6009791..e42d0fdefee1 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -654,7 +654,7 @@ static void icssg_prueth_hsr_fdb_add_del(struct prueth_emac *emac, static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) { - struct net_device *real_dev; + struct net_device *real_dev, *port_dev; struct prueth_emac *emac; u8 vlan_id, i; @@ -663,11 +663,15 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) if (is_hsr_master(real_dev)) { for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) { - emac = netdev_priv(hsr_get_port_ndev(real_dev, i)); - if (!emac) + port_dev = hsr_get_port_ndev(real_dev, i); + emac = netdev_priv(port_dev); + if (!emac) { + dev_put(port_dev); return -EINVAL; + } icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, true); + dev_put(port_dev); } } else { emac = netdev_priv(real_dev); @@ -679,7 +683,7 @@ static int icssg_prueth_hsr_add_mcast(struct net_device *ndev, const u8 *addr) static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr) { - struct net_device *real_dev; + struct net_device *real_dev, *port_dev; struct prueth_emac *emac; u8 vlan_id, i; @@ -688,11 +692,15 @@ static int icssg_prueth_hsr_del_mcast(struct net_device *ndev, const u8 *addr) if (is_hsr_master(real_dev)) { for (i = HSR_PT_SLAVE_A; i < HSR_PT_INTERLINK; i++) { - emac = netdev_priv(hsr_get_port_ndev(real_dev, i)); - if (!emac) + port_dev = hsr_get_port_ndev(real_dev, i); + emac = netdev_priv(port_dev); + if (!emac) { + dev_put(port_dev); return -EINVAL; + } icssg_prueth_hsr_fdb_add_del(emac, addr, vlan_id, false); + dev_put(port_dev); } } else { emac = netdev_priv(real_dev); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index bcd07a715752..5cb353a97d6d 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -2078,10 +2078,6 @@ static void wx_setup_mrqc(struct wx *wx) { u32 rss_field = 0; - /* VT, and RSS do not coexist at the same time */ - if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags)) - return; - /* Disable indicating checksum in descriptor, enables RSS hash */ wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_PCSD, WX_PSR_CTL_PCSD); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 0d8a05fe541a..ec6d47dc984a 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1168,6 +1168,15 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result) &meta_max_len); dma_unmap_single(lp->dev, skbuf_dma->dma_address, lp->max_frm_size, DMA_FROM_DEVICE); + + if (IS_ERR(app_metadata)) { + if (net_ratelimit()) + netdev_err(lp->ndev, "Failed to get RX metadata pointer\n"); + dev_kfree_skb_any(skb); + lp->ndev->stats.rx_dropped++; + goto rx_submit; + } + /* TODO: Derive app word index programmatically */ rx_len = (app_metadata[LEN_APP] & 0xFFFF); skb_put(skb, rx_len); @@ -1180,6 +1189,7 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result) u64_stats_add(&lp->rx_bytes, rx_len); u64_stats_update_end(&lp->rx_stat_sync); +rx_submit: for (i = 0; i < CIRC_SPACE(lp->rx_ring_head, lp->rx_ring_tail, RX_BUF_NUM_DEFAULT); i++) axienet_rx_submit_desc(lp->ndev); diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index a31d5d5e6593..97e88886253f 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -1576,7 +1576,7 @@ do_reset(struct net_device *dev, int full) msleep(40); /* wait 40 msec to let it complete */ } if (full_duplex) - PutByte(XIRCREG1_ECR, GetByte(XIRCREG1_ECR | FullDuplex)); + PutByte(XIRCREG1_ECR, GetByte(XIRCREG1_ECR) | FullDuplex); } else { /* No MII */ SelectPage(0); value = GetByte(XIRCREG_ESR); /* read the ESR */ diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 4c75d1fea552..0eca96eeed58 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1844,7 +1844,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) if (tb_sa[MACSEC_SA_ATTR_PN]) { spin_lock_bh(&rx_sa->lock); - rx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); + rx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&rx_sa->lock); } @@ -2086,7 +2086,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info) } spin_lock_bh(&tx_sa->lock); - tx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); + tx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&tx_sa->lock); if (tb_sa[MACSEC_SA_ATTR_ACTIVE]) @@ -2398,7 +2398,7 @@ static int macsec_upd_txsa(struct sk_buff *skb, struct genl_info *info) spin_lock_bh(&tx_sa->lock); prev_pn = tx_sa->next_pn_halves; - tx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); + tx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&tx_sa->lock); } @@ -2496,7 +2496,7 @@ static int macsec_upd_rxsa(struct sk_buff *skb, struct genl_info *info) spin_lock_bh(&rx_sa->lock); prev_pn = rx_sa->next_pn_halves; - rx_sa->next_pn = nla_get_u64(tb_sa[MACSEC_SA_ATTR_PN]); + rx_sa->next_pn = nla_get_uint(tb_sa[MACSEC_SA_ATTR_PN]); spin_unlock_bh(&rx_sa->lock); } @@ -4286,6 +4286,7 @@ static int macsec_newlink(struct net_device *dev, if (err < 0) goto del_dev; + netdev_update_features(dev); netif_stacked_transfer_operstate(real_dev, dev); linkwatch_fire_event(dev); diff --git a/drivers/net/mctp/mctp-usb.c b/drivers/net/mctp/mctp-usb.c index 775a386d0aca..36ccc53b1797 100644 --- a/drivers/net/mctp/mctp-usb.c +++ b/drivers/net/mctp/mctp-usb.c @@ -183,6 +183,7 @@ static void mctp_usb_in_complete(struct urb *urb) struct mctp_usb_hdr *hdr; u8 pkt_len; /* length of MCTP packet, no USB header */ + skb_reset_mac_header(skb); hdr = skb_pull_data(skb, sizeof(*hdr)); if (!hdr) break; diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c index d79bb9b06cd2..ce73d9474d5b 100644 --- a/drivers/net/pcs/pcs-rzn1-miic.c +++ b/drivers/net/pcs/pcs-rzn1-miic.c @@ -19,7 +19,7 @@ #define MIIC_PRCMD 0x0 #define MIIC_ESID_CODE 0x4 -#define MIIC_MODCTRL 0x20 +#define MIIC_MODCTRL 0x8 #define MIIC_MODCTRL_SW_MODE GENMASK(4, 0) #define MIIC_CONVCTRL(port) (0x100 + (port) * 4) diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 28acc6392cfc..392749aae54d 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -361,7 +361,7 @@ config NXP_TJA11XX_PHY tristate "NXP TJA11xx PHYs support" depends on HWMON help - Currently supports the NXP TJA1100 and TJA1101 PHY. + Currently supports the NXP TJA1100, TJA1101 and TJA1102 PHYs. config NCN26000_PHY tristate "Onsemi 10BASE-T1S Ethernet PHY" diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c index 72847320cb65..d692df7d975c 100644 --- a/drivers/net/phy/mscc/mscc_ptp.c +++ b/drivers/net/phy/mscc/mscc_ptp.c @@ -456,12 +456,12 @@ static void vsc85xx_dequeue_skb(struct vsc85xx_ptp *ptp) *p++ = (reg >> 24) & 0xff; } - len = skb_queue_len(&ptp->tx_queue); + len = skb_queue_len_lockless(&ptp->tx_queue); if (len < 1) return; while (len--) { - skb = __skb_dequeue(&ptp->tx_queue); + skb = skb_dequeue(&ptp->tx_queue); if (!skb) return; @@ -486,7 +486,7 @@ static void vsc85xx_dequeue_skb(struct vsc85xx_ptp *ptp) * packet in the FIFO right now, reschedule it for later * packets. */ - __skb_queue_tail(&ptp->tx_queue, skb); + skb_queue_tail(&ptp->tx_queue, skb); } } @@ -1068,6 +1068,7 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, case HWTSTAMP_TX_ON: break; case HWTSTAMP_TX_OFF: + skb_queue_purge(&vsc8531->ptp->tx_queue); break; default: return -ERANGE; @@ -1092,9 +1093,6 @@ static int vsc85xx_hwtstamp(struct mii_timestamper *mii_ts, mutex_lock(&vsc8531->ts_lock); - __skb_queue_purge(&vsc8531->ptp->tx_queue); - __skb_queue_head_init(&vsc8531->ptp->tx_queue); - /* Disable predictor while configuring the 1588 block */ val = vsc85xx_ts_read_csr(phydev, PROCESSOR, MSCC_PHY_PTP_INGR_PREDICTOR); @@ -1180,9 +1178,7 @@ static void vsc85xx_txtstamp(struct mii_timestamper *mii_ts, skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - mutex_lock(&vsc8531->ts_lock); - __skb_queue_tail(&vsc8531->ptp->tx_queue, skb); - mutex_unlock(&vsc8531->ts_lock); + skb_queue_tail(&vsc8531->ptp->tx_queue, skb); return; out: @@ -1548,6 +1544,7 @@ void vsc8584_ptp_deinit(struct phy_device *phydev) if (vsc8531->ptp->ptp_clock) { ptp_clock_unregister(vsc8531->ptp->ptp_clock); skb_queue_purge(&vsc8531->rx_skbs_list); + skb_queue_purge(&vsc8531->ptp->tx_queue); } } @@ -1571,7 +1568,7 @@ irqreturn_t vsc8584_handle_ts_interrupt(struct phy_device *phydev) if (rc & VSC85XX_1588_INT_FIFO_ADD) { vsc85xx_get_tx_ts(priv->ptp); } else if (rc & VSC85XX_1588_INT_FIFO_OVERFLOW) { - __skb_queue_purge(&priv->ptp->tx_queue); + skb_queue_purge(&priv->ptp->tx_queue); vsc85xx_ts_reset_fifo(phydev); } @@ -1591,6 +1588,7 @@ int vsc8584_ptp_probe(struct phy_device *phydev) mutex_init(&vsc8531->phc_lock); mutex_init(&vsc8531->ts_lock); skb_queue_head_init(&vsc8531->rx_skbs_list); + skb_queue_head_init(&vsc8531->ptp->tx_queue); /* Retrieve the shared load/save GPIO. Request it as non exclusive as * the same GPIO can be requested by all the PHYs of the same package. diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 13df28445f02..c02da57a4da5 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -1065,23 +1065,19 @@ EXPORT_SYMBOL_GPL(phy_inband_caps); */ int phy_config_inband(struct phy_device *phydev, unsigned int modes) { - int err; + lockdep_assert_held(&phydev->lock); if (!!(modes & LINK_INBAND_DISABLE) + !!(modes & LINK_INBAND_ENABLE) + !!(modes & LINK_INBAND_BYPASS) != 1) return -EINVAL; - mutex_lock(&phydev->lock); if (!phydev->drv) - err = -EIO; + return -EIO; else if (!phydev->drv->config_inband) - err = -EOPNOTSUPP; - else - err = phydev->drv->config_inband(phydev, modes); - mutex_unlock(&phydev->lock); + return -EOPNOTSUPP; - return err; + return phydev->drv->config_inband(phydev, modes); } EXPORT_SYMBOL(phy_config_inband); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 7556aa3dd7ee..c82c1997147b 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -287,8 +287,7 @@ static bool phy_uses_state_machine(struct phy_device *phydev) if (phydev->phy_link_change == phy_link_change) return phydev->attached_dev && phydev->adjust_link; - /* phydev->phy_link_change is implicitly phylink_phy_change() */ - return true; + return !!phydev->phy_link_change; } static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) @@ -1864,6 +1863,8 @@ void phy_detach(struct phy_device *phydev) phydev->attached_dev = NULL; phy_link_topo_del_phy(dev, phydev); } + + phydev->phy_link_change = NULL; phydev->phylink = NULL; if (!phydev->is_on_sfp_module) diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index c7f867b361dd..1988b7d2089a 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -67,6 +67,8 @@ struct phylink { struct timer_list link_poll; struct mutex state_mutex; + /* Serialize updates to pl->phydev with phylink_resolve() */ + struct mutex phydev_mutex; struct phylink_link_state phy_state; unsigned int phy_ib_mode; struct work_struct resolve; @@ -1016,6 +1018,42 @@ static void phylink_pcs_an_restart(struct phylink *pl) pl->pcs->ops->pcs_an_restart(pl->pcs); } +enum inband_type { + INBAND_NONE, + INBAND_CISCO_SGMII, + INBAND_BASEX, +}; + +static enum inband_type phylink_get_inband_type(phy_interface_t interface) +{ + switch (interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_QSGMII: + case PHY_INTERFACE_MODE_QUSGMII: + case PHY_INTERFACE_MODE_USXGMII: + case PHY_INTERFACE_MODE_10G_QXGMII: + /* These protocols are designed for use with a PHY which + * communicates its negotiation result back to the MAC via + * inband communication. Note: there exist PHYs that run + * with SGMII but do not send the inband data. + */ + return INBAND_CISCO_SGMII; + + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + /* 1000base-X is designed for use media-side for Fibre + * connections, and thus the Autoneg bit needs to be + * taken into account. We also do this for 2500base-X + * as well, but drivers may not support this, so may + * need to override this. + */ + return INBAND_BASEX; + + default: + return INBAND_NONE; + } +} + /** * phylink_pcs_neg_mode() - helper to determine PCS inband mode * @pl: a pointer to a &struct phylink returned from phylink_create() @@ -1043,46 +1081,19 @@ static void phylink_pcs_neg_mode(struct phylink *pl, struct phylink_pcs *pcs, unsigned int pcs_ib_caps = 0; unsigned int phy_ib_caps = 0; unsigned int neg_mode, mode; - enum { - INBAND_CISCO_SGMII, - INBAND_BASEX, - } type; - - mode = pl->req_link_an_mode; - - pl->phy_ib_mode = 0; - - switch (interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_QSGMII: - case PHY_INTERFACE_MODE_QUSGMII: - case PHY_INTERFACE_MODE_USXGMII: - case PHY_INTERFACE_MODE_10G_QXGMII: - /* These protocols are designed for use with a PHY which - * communicates its negotiation result back to the MAC via - * inband communication. Note: there exist PHYs that run - * with SGMII but do not send the inband data. - */ - type = INBAND_CISCO_SGMII; - break; + enum inband_type type; - case PHY_INTERFACE_MODE_1000BASEX: - case PHY_INTERFACE_MODE_2500BASEX: - /* 1000base-X is designed for use media-side for Fibre - * connections, and thus the Autoneg bit needs to be - * taken into account. We also do this for 2500base-X - * as well, but drivers may not support this, so may - * need to override this. - */ - type = INBAND_BASEX; - break; - - default: + type = phylink_get_inband_type(interface); + if (type == INBAND_NONE) { pl->pcs_neg_mode = PHYLINK_PCS_NEG_NONE; - pl->act_link_an_mode = mode; + pl->act_link_an_mode = pl->req_link_an_mode; return; } + mode = pl->req_link_an_mode; + + pl->phy_ib_mode = 0; + if (pcs) pcs_ib_caps = phylink_pcs_inband_caps(pcs, interface); @@ -1423,6 +1434,7 @@ static void phylink_get_fixed_state(struct phylink *pl, static void phylink_mac_initial_config(struct phylink *pl, bool force_restart) { struct phylink_link_state link_state; + struct phy_device *phy = pl->phydev; switch (pl->req_link_an_mode) { case MLO_AN_PHY: @@ -1446,7 +1458,11 @@ static void phylink_mac_initial_config(struct phylink *pl, bool force_restart) link_state.link = false; phylink_apply_manual_flow(pl, &link_state); + if (phy) + mutex_lock(&phy->lock); phylink_major_config(pl, force_restart, &link_state); + if (phy) + mutex_unlock(&phy->lock); } static const char *phylink_pause_to_str(int pause) @@ -1582,8 +1598,13 @@ static void phylink_resolve(struct work_struct *w) struct phylink_link_state link_state; bool mac_config = false; bool retrigger = false; + struct phy_device *phy; bool cur_link_state; + mutex_lock(&pl->phydev_mutex); + phy = pl->phydev; + if (phy) + mutex_lock(&phy->lock); mutex_lock(&pl->state_mutex); cur_link_state = phylink_link_is_up(pl); @@ -1617,11 +1638,11 @@ static void phylink_resolve(struct work_struct *w) /* If we have a phy, the "up" state is the union of both the * PHY and the MAC */ - if (pl->phydev) + if (phy) link_state.link &= pl->phy_state.link; /* Only update if the PHY link is up */ - if (pl->phydev && pl->phy_state.link) { + if (phy && pl->phy_state.link) { /* If the interface has changed, force a link down * event if the link isn't already down, and re-resolve. */ @@ -1685,6 +1706,9 @@ static void phylink_resolve(struct work_struct *w) queue_work(system_power_efficient_wq, &pl->resolve); } mutex_unlock(&pl->state_mutex); + if (phy) + mutex_unlock(&phy->lock); + mutex_unlock(&pl->phydev_mutex); } static void phylink_run_resolve(struct phylink *pl) @@ -1820,6 +1844,7 @@ struct phylink *phylink_create(struct phylink_config *config, if (!pl) return ERR_PTR(-ENOMEM); + mutex_init(&pl->phydev_mutex); mutex_init(&pl->state_mutex); INIT_WORK(&pl->resolve, phylink_resolve); @@ -2080,6 +2105,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, dev_name(&phy->mdio.dev), phy->drv->name, irq_str); kfree(irq_str); + mutex_lock(&pl->phydev_mutex); mutex_lock(&phy->lock); mutex_lock(&pl->state_mutex); pl->phydev = phy; @@ -2125,6 +2151,7 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, mutex_unlock(&pl->state_mutex); mutex_unlock(&phy->lock); + mutex_unlock(&pl->phydev_mutex); phylink_dbg(pl, "phy: %s setting supported %*pb advertising %*pb\n", @@ -2132,9 +2159,6 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, __ETHTOOL_LINK_MODE_MASK_NBITS, pl->supported, __ETHTOOL_LINK_MODE_MASK_NBITS, phy->advertising); - if (phy_interrupt_is_valid(phy)) - phy_request_interrupt(phy); - if (pl->config->mac_managed_pm) phy->mac_managed_pm = true; @@ -2151,6 +2175,9 @@ static int phylink_bringup_phy(struct phylink *pl, struct phy_device *phy, ret = 0; } + if (ret == 0 && phy_interrupt_is_valid(phy)) + phy_request_interrupt(phy); + return ret; } @@ -2303,6 +2330,7 @@ void phylink_disconnect_phy(struct phylink *pl) ASSERT_RTNL(); + mutex_lock(&pl->phydev_mutex); phy = pl->phydev; if (phy) { mutex_lock(&phy->lock); @@ -2312,8 +2340,11 @@ void phylink_disconnect_phy(struct phylink *pl) pl->mac_tx_clk_stop = false; mutex_unlock(&pl->state_mutex); mutex_unlock(&phy->lock); - flush_work(&pl->resolve); + } + mutex_unlock(&pl->phydev_mutex); + if (phy) { + flush_work(&pl->resolve); phy_disconnect(phy); } } @@ -3625,6 +3656,7 @@ static int phylink_sfp_config_optical(struct phylink *pl) { __ETHTOOL_DECLARE_LINK_MODE_MASK(support); struct phylink_link_state config; + enum inband_type inband_type; phy_interface_t interface; int ret; @@ -3671,6 +3703,23 @@ static int phylink_sfp_config_optical(struct phylink *pl) phylink_dbg(pl, "optical SFP: chosen %s interface\n", phy_modes(interface)); + inband_type = phylink_get_inband_type(interface); + if (inband_type == INBAND_NONE) { + /* If this is the sole interface, and there is no inband + * support, clear the advertising mask and Autoneg bit in + * the support mask. Otherwise, just clear the Autoneg bit + * in the advertising mask. + */ + if (phy_interface_weight(pl->sfp_interfaces) == 1) { + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + pl->sfp_support); + linkmode_zero(config.advertising); + } else { + linkmode_clear_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + config.advertising); + } + } + if (!phylink_validate_pcs_inband_autoneg(pl, interface, config.advertising)) { phylink_err(pl, "autoneg setting not compatible with PCS"); diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 5347c95d1e77..4cd1d6c51dc2 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -492,6 +492,9 @@ static const struct sfp_quirk sfp_quirks[] = { SFP_QUIRK("ALCATELLUCENT", "3FE46541AA", sfp_quirk_2500basex, sfp_fixup_nokia), + // FLYPRO SFP-10GT-CS-30M uses Rollball protocol to talk to the PHY. + SFP_QUIRK_F("FLYPRO", "SFP-10GT-CS-30M", sfp_fixup_rollball), + // Fiberstore SFP-10G-T doesn't identify as copper, uses the Rollball // protocol to talk to the PHY and needs 4 sec wait before probing the // PHY. diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 824c8dc4120b..702a7f7183ce 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1744,7 +1744,6 @@ pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) */ if (net_ratelimit()) netdev_err(ppp->dev, "ppp: compressor dropped pkt\n"); - kfree_skb(skb); consume_skb(new_skb); new_skb = NULL; } @@ -1845,9 +1844,10 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) "down - pkt dropped.\n"); goto drop; } - skb = pad_compress_skb(ppp, skb); - if (!skb) + new_skb = pad_compress_skb(ppp, skb); + if (!new_skb) goto drop; + skb = new_skb; } /* diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index f32be2e301f2..dab864bc733c 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -1445,6 +1445,10 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev, if (READ_ONCE(f->updated) != now) WRITE_ONCE(f->updated, now); + /* Don't override an fdb with nexthop with a learnt entry */ + if (rcu_access_pointer(f->nh)) + return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; + if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) && rdst->remote_ifindex == ifindex)) return SKB_NOT_DROPPED_YET; @@ -1453,10 +1457,6 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev, if (f->state & (NUD_PERMANENT | NUD_NOARP)) return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; - /* Don't override an fdb with nexthop with a learnt entry */ - if (rcu_access_pointer(f->nh)) - return SKB_DROP_REASON_VXLAN_ENTRY_EXISTS; - if (net_ratelimit()) netdev_info(dev, "%pM migrated from %pIS to %pIS\n", @@ -1877,6 +1877,7 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) n = neigh_lookup(&arp_tbl, &tip, dev); if (n) { + struct vxlan_rdst *rdst = NULL; struct vxlan_fdb *f; struct sk_buff *reply; @@ -1887,7 +1888,9 @@ static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) rcu_read_lock(); f = vxlan_find_mac_tx(vxlan, n->ha, vni); - if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { + if (f) + rdst = first_remote_rcu(f); + if (rdst && vxlan_addr_any(&rdst->remote_ip)) { /* bridge-local neighbor */ neigh_release(n); rcu_read_unlock(); @@ -2044,6 +2047,7 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev); if (n) { + struct vxlan_rdst *rdst = NULL; struct vxlan_fdb *f; struct sk_buff *reply; @@ -2053,7 +2057,9 @@ static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni) } f = vxlan_find_mac_tx(vxlan, n->ha, vni); - if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) { + if (f) + rdst = first_remote_rcu(f); + if (rdst && vxlan_addr_any(&rdst->remote_ip)) { /* bridge-local neighbor */ neigh_release(n); goto out; diff --git a/drivers/net/vxlan/vxlan_private.h b/drivers/net/vxlan/vxlan_private.h index 6c625fb29c6c..99fe772ad679 100644 --- a/drivers/net/vxlan/vxlan_private.h +++ b/drivers/net/vxlan/vxlan_private.h @@ -61,9 +61,7 @@ static inline struct hlist_head *vs_head(struct net *net, __be16 port) return &vn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)]; } -/* First remote destination for a forwarding entry. - * Guaranteed to be non-NULL because remotes are never deleted. - */ +/* First remote destination for a forwarding entry. */ static inline struct vxlan_rdst *first_remote_rcu(struct vxlan_fdb *fdb) { if (rcu_access_pointer(fdb->nh)) diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h index 220d69a7a429..e8780b05ce11 100644 --- a/drivers/net/wireless/ath/ath11k/core.h +++ b/drivers/net/wireless/ath/ath11k/core.h @@ -411,6 +411,8 @@ struct ath11k_vif { bool do_not_send_tmpl; struct ath11k_arp_ns_offload arp_ns_offload; struct ath11k_rekey_data rekey_data; + u32 num_stations; + bool reinstall_group_keys; struct ath11k_reg_tpc_power_info reg_tpc_info; diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 1fadf5faafb8..106e2530b64e 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -4317,6 +4317,40 @@ static int ath11k_clear_peer_keys(struct ath11k_vif *arvif, return first_errno; } +static int ath11k_set_group_keys(struct ath11k_vif *arvif) +{ + struct ath11k *ar = arvif->ar; + struct ath11k_base *ab = ar->ab; + const u8 *addr = arvif->bssid; + int i, ret, first_errno = 0; + struct ath11k_peer *peer; + + spin_lock_bh(&ab->base_lock); + peer = ath11k_peer_find(ab, arvif->vdev_id, addr); + spin_unlock_bh(&ab->base_lock); + + if (!peer) + return -ENOENT; + + for (i = 0; i < ARRAY_SIZE(peer->keys); i++) { + struct ieee80211_key_conf *key = peer->keys[i]; + + if (!key || (key->flags & IEEE80211_KEY_FLAG_PAIRWISE)) + continue; + + ret = ath11k_install_key(arvif, key, SET_KEY, addr, + WMI_KEY_GROUP); + if (ret < 0 && first_errno == 0) + first_errno = ret; + + if (ret < 0) + ath11k_warn(ab, "failed to set group key of idx %d for vdev %d: %d\n", + i, arvif->vdev_id, ret); + } + + return first_errno; +} + static int ath11k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, struct ieee80211_vif *vif, struct ieee80211_sta *sta, struct ieee80211_key_conf *key) @@ -4326,6 +4360,7 @@ static int ath11k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif); struct ath11k_peer *peer; struct ath11k_sta *arsta; + bool is_ap_with_no_sta; const u8 *peer_addr; int ret = 0; u32 flags = 0; @@ -4386,16 +4421,57 @@ static int ath11k_mac_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, else flags |= WMI_KEY_GROUP; - ret = ath11k_install_key(arvif, key, cmd, peer_addr, flags); - if (ret) { - ath11k_warn(ab, "ath11k_install_key failed (%d)\n", ret); - goto exit; - } + ath11k_dbg(ar->ab, ATH11K_DBG_MAC, + "%s for peer %pM on vdev %d flags 0x%X, type = %d, num_sta %d\n", + cmd == SET_KEY ? "SET_KEY" : "DEL_KEY", peer_addr, arvif->vdev_id, + flags, arvif->vdev_type, arvif->num_stations); + + /* Allow group key clearing only in AP mode when no stations are + * associated. There is a known race condition in firmware where + * group addressed packets may be dropped if the key is cleared + * and immediately set again during rekey. + * + * During GTK rekey, mac80211 issues a clear key (if the old key + * exists) followed by an install key operation for same key + * index. This causes ath11k to send two WMI commands in quick + * succession: one to clear the old key and another to install the + * new key in the same slot. + * + * Under certain conditions—especially under high load or time + * sensitive scenarios, firmware may process these commands + * asynchronously in a way that firmware assumes the key is + * cleared whereas hardware has a valid key. This inconsistency + * between hardware and firmware leads to group addressed packet + * drops after rekey. + * Only setting the same key again can restore a valid key in + * firmware and allow packets to be transmitted. + * + * There is a use case where an AP can transition from Secure mode + * to open mode without a vdev restart by just deleting all + * associated peers and clearing key, Hence allow clear key for + * that case alone. Mark arvif->reinstall_group_keys in such cases + * and reinstall the same key when the first peer is added, + * allowing firmware to recover from the race if it had occurred. + */ - ret = ath11k_dp_peer_rx_pn_replay_config(arvif, peer_addr, cmd, key); - if (ret) { - ath11k_warn(ab, "failed to offload PN replay detection %d\n", ret); - goto exit; + is_ap_with_no_sta = (vif->type == NL80211_IFTYPE_AP && + !arvif->num_stations); + if ((flags & WMI_KEY_PAIRWISE) || cmd == SET_KEY || is_ap_with_no_sta) { + ret = ath11k_install_key(arvif, key, cmd, peer_addr, flags); + if (ret) { + ath11k_warn(ab, "ath11k_install_key failed (%d)\n", ret); + goto exit; + } + + ret = ath11k_dp_peer_rx_pn_replay_config(arvif, peer_addr, cmd, key); + if (ret) { + ath11k_warn(ab, "failed to offload PN replay detection %d\n", + ret); + goto exit; + } + + if ((flags & WMI_KEY_GROUP) && cmd == SET_KEY && is_ap_with_no_sta) + arvif->reinstall_group_keys = true; } spin_lock_bh(&ab->base_lock); @@ -4994,6 +5070,7 @@ static int ath11k_mac_inc_num_stations(struct ath11k_vif *arvif, return -ENOBUFS; ar->num_stations++; + arvif->num_stations++; return 0; } @@ -5009,6 +5086,7 @@ static void ath11k_mac_dec_num_stations(struct ath11k_vif *arvif, return; ar->num_stations--; + arvif->num_stations--; } static u32 ath11k_mac_ieee80211_sta_bw_to_wmi(struct ath11k *ar, @@ -9540,6 +9618,21 @@ static int ath11k_mac_station_add(struct ath11k *ar, goto exit; } + /* Driver allows the DEL KEY followed by SET KEY sequence for + * group keys for only when there is no clients associated, if at + * all firmware has entered the race during that window, + * reinstalling the same key when the first sta connects will allow + * firmware to recover from the race. + */ + if (arvif->num_stations == 1 && arvif->reinstall_group_keys) { + ath11k_dbg(ab, ATH11K_DBG_MAC, "set group keys on 1st station add for vdev %d\n", + arvif->vdev_id); + ret = ath11k_set_group_keys(arvif); + if (ret) + goto dec_num_station; + arvif->reinstall_group_keys = false; + } + arsta->rx_stats = kzalloc(sizeof(*arsta->rx_stats), GFP_KERNEL); if (!arsta->rx_stats) { ret = -ENOMEM; diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index bd1ec3b2c084..3a3965b79942 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -4078,12 +4078,68 @@ static int ath12k_mac_fils_discovery(struct ath12k_link_vif *arvif, return ret; } +static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif) +{ + struct ath12k *ar = arvif->ar; + struct ieee80211_vif *vif = arvif->ahvif->vif; + struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf; + enum wmi_sta_powersave_param param; + struct ieee80211_bss_conf *info; + enum wmi_sta_ps_mode psmode; + int ret; + int timeout; + bool enable_ps; + + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + if (vif->type != NL80211_IFTYPE_STATION) + return; + + enable_ps = arvif->ahvif->ps; + if (enable_ps) { + psmode = WMI_STA_PS_MODE_ENABLED; + param = WMI_STA_PS_PARAM_INACTIVITY_TIME; + + timeout = conf->dynamic_ps_timeout; + if (timeout == 0) { + info = ath12k_mac_get_link_bss_conf(arvif); + if (!info) { + ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n", + vif->addr, arvif->link_id); + return; + } + + /* firmware doesn't like 0 */ + timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000; + } + + ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param, + timeout); + if (ret) { + ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n", + arvif->vdev_id, ret); + return; + } + } else { + psmode = WMI_STA_PS_MODE_DISABLED; + } + + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n", + arvif->vdev_id, psmode ? "enable" : "disable"); + + ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode); + if (ret) + ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n", + psmode, arvif->vdev_id, ret); +} + static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u64 changed) { struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif); unsigned long links = ahvif->links_map; + struct ieee80211_vif_cfg *vif_cfg; struct ieee80211_bss_conf *info; struct ath12k_link_vif *arvif; struct ieee80211_sta *sta; @@ -4147,61 +4203,24 @@ static void ath12k_mac_op_vif_cfg_changed(struct ieee80211_hw *hw, } } } -} - -static void ath12k_mac_vif_setup_ps(struct ath12k_link_vif *arvif) -{ - struct ath12k *ar = arvif->ar; - struct ieee80211_vif *vif = arvif->ahvif->vif; - struct ieee80211_conf *conf = &ath12k_ar_to_hw(ar)->conf; - enum wmi_sta_powersave_param param; - struct ieee80211_bss_conf *info; - enum wmi_sta_ps_mode psmode; - int ret; - int timeout; - bool enable_ps; - lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + if (changed & BSS_CHANGED_PS) { + links = ahvif->links_map; + vif_cfg = &vif->cfg; - if (vif->type != NL80211_IFTYPE_STATION) - return; + for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) { + arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]); + if (!arvif || !arvif->ar) + continue; - enable_ps = arvif->ahvif->ps; - if (enable_ps) { - psmode = WMI_STA_PS_MODE_ENABLED; - param = WMI_STA_PS_PARAM_INACTIVITY_TIME; + ar = arvif->ar; - timeout = conf->dynamic_ps_timeout; - if (timeout == 0) { - info = ath12k_mac_get_link_bss_conf(arvif); - if (!info) { - ath12k_warn(ar->ab, "unable to access bss link conf in setup ps for vif %pM link %u\n", - vif->addr, arvif->link_id); - return; + if (ar->ab->hw_params->supports_sta_ps) { + ahvif->ps = vif_cfg->ps; + ath12k_mac_vif_setup_ps(arvif); } - - /* firmware doesn't like 0 */ - timeout = ieee80211_tu_to_usec(info->beacon_int) / 1000; } - - ret = ath12k_wmi_set_sta_ps_param(ar, arvif->vdev_id, param, - timeout); - if (ret) { - ath12k_warn(ar->ab, "failed to set inactivity time for vdev %d: %i\n", - arvif->vdev_id, ret); - return; - } - } else { - psmode = WMI_STA_PS_MODE_DISABLED; } - - ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac vdev %d psmode %s\n", - arvif->vdev_id, psmode ? "enable" : "disable"); - - ret = ath12k_wmi_pdev_set_ps_mode(ar, arvif->vdev_id, psmode); - if (ret) - ath12k_warn(ar->ab, "failed to set sta power save mode %d for vdev %d: %d\n", - psmode, arvif->vdev_id, ret); } static bool ath12k_mac_supports_tpc(struct ath12k *ar, struct ath12k_vif *ahvif, @@ -4223,7 +4242,6 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, { struct ath12k_vif *ahvif = arvif->ahvif; struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif); - struct ieee80211_vif_cfg *vif_cfg = &vif->cfg; struct cfg80211_chan_def def; u32 param_id, param_value; enum nl80211_band band; @@ -4510,12 +4528,6 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, } ath12k_mac_fils_discovery(arvif, info); - - if (changed & BSS_CHANGED_PS && - ar->ab->hw_params->supports_sta_ps) { - ahvif->ps = vif_cfg->ps; - ath12k_mac_vif_setup_ps(arvif); - } } static struct ath12k_vif_cache *ath12k_ahvif_get_link_cache(struct ath12k_vif *ahvif, diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index da85c28ec355..29dadedefdd2 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -843,7 +843,7 @@ int ath12k_wmi_mgmt_send(struct ath12k_link_vif *arvif, u32 buf_id, cmd->tx_params_valid = 0; frame_tlv = (struct wmi_tlv *)(skb->data + sizeof(*cmd)); - frame_tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, buf_len); + frame_tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, buf_len_aligned); memcpy(frame_tlv->value, frame->data, buf_len); @@ -2423,6 +2423,7 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar, eml_cap = arg->ml.eml_cap; if (u16_get_bits(eml_cap, IEEE80211_EML_CAP_EMLSR_SUPP)) { + ml_params->flags |= cpu_to_le32(ATH12K_WMI_FLAG_MLO_EMLSR_SUPPORT); /* Padding delay */ eml_pad_delay = ieee80211_emlsr_pad_delay_in_us(eml_cap); ml_params->emlsr_padding_delay_us = cpu_to_le32(eml_pad_delay); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c index 69ef8cf203d2..67c0c5a92f99 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c @@ -393,10 +393,8 @@ void brcmf_btcoex_detach(struct brcmf_cfg80211_info *cfg) if (!cfg->btcoex) return; - if (cfg->btcoex->timer_on) { - cfg->btcoex->timer_on = false; - timer_shutdown_sync(&cfg->btcoex->timer); - } + timer_shutdown_sync(&cfg->btcoex->timer); + cfg->btcoex->timer_on = false; cancel_work_sync(&cfg->btcoex->work); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c index bee7d92293b8..7ec22738b5d6 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c @@ -169,7 +169,7 @@ int iwl_acpi_get_dsm(struct iwl_fw_runtime *fwrt, BUILD_BUG_ON(ARRAY_SIZE(acpi_dsm_size) != DSM_FUNC_NUM_FUNCS); - if (WARN_ON(func >= ARRAY_SIZE(acpi_dsm_size))) + if (WARN_ON(func >= ARRAY_SIZE(acpi_dsm_size) || !func)) return -EINVAL; expected_size = acpi_dsm_size[func]; @@ -178,6 +178,29 @@ int iwl_acpi_get_dsm(struct iwl_fw_runtime *fwrt, if (expected_size != sizeof(u8) && expected_size != sizeof(u32)) return -EOPNOTSUPP; + if (!fwrt->acpi_dsm_funcs_valid) { + ret = iwl_acpi_get_dsm_integer(fwrt->dev, ACPI_DSM_REV, + DSM_FUNC_QUERY, + &iwl_guid, &tmp, + acpi_dsm_size[DSM_FUNC_QUERY]); + if (ret) { + /* always indicate BIT(0) to avoid re-reading */ + fwrt->acpi_dsm_funcs_valid = BIT(0); + return ret; + } + + IWL_DEBUG_RADIO(fwrt, "ACPI DSM validity bitmap 0x%x\n", + (u32)tmp); + /* always indicate BIT(0) to avoid re-reading */ + fwrt->acpi_dsm_funcs_valid = tmp | BIT(0); + } + + if (!(fwrt->acpi_dsm_funcs_valid & BIT(func))) { + IWL_DEBUG_RADIO(fwrt, "ACPI DSM %d not indicated as valid\n", + func); + return -ENODATA; + } + ret = iwl_acpi_get_dsm_integer(fwrt->dev, ACPI_DSM_REV, func, &iwl_guid, &tmp, expected_size); if (ret) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h index 0444a736c2b2..bd3bc2846cfa 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h @@ -113,6 +113,10 @@ struct iwl_txf_iter_data { * @phy_filters: specific phy filters as read from WPFC BIOS table * @ppag_bios_rev: PPAG BIOS revision * @ppag_bios_source: see &enum bios_source + * @acpi_dsm_funcs_valid: bitmap indicating which DSM values are valid, + * zero (default initialization) means it hasn't been read yet, + * and BIT(0) is set when it has since function 0 also has this + * bitmap and is always supported */ struct iwl_fw_runtime { struct iwl_trans *trans; @@ -189,6 +193,10 @@ struct iwl_fw_runtime { bool uats_valid; u8 uefi_tables_lock_status; struct iwl_phy_specific_cfg phy_filters; + +#ifdef CONFIG_ACPI + u32 acpi_dsm_funcs_valid; +#endif }; void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c index 48126ec6b94b..99a17b9323e9 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c @@ -747,6 +747,12 @@ int iwl_uefi_get_dsm(struct iwl_fw_runtime *fwrt, enum iwl_dsm_funcs func, goto out; } + if (!(data->functions[DSM_FUNC_QUERY] & BIT(func))) { + IWL_DEBUG_RADIO(fwrt, "DSM func %d not in 0x%x\n", + func, data->functions[DSM_FUNC_QUERY]); + goto out; + } + *value = data->functions[func]; IWL_DEBUG_RADIO(fwrt, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index b7add05f7a85..7e56e4ff7642 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -124,13 +124,13 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x0082, 0x1304, iwl6005_mac_cfg)},/* low 5GHz active */ {IWL_PCI_DEVICE(0x0082, 0x1305, iwl6005_mac_cfg)},/* high 5GHz active */ -/* 6x30 Series */ - {IWL_PCI_DEVICE(0x008A, 0x5305, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008A, 0x5307, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008A, 0x5325, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008A, 0x5327, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008B, 0x5315, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x008B, 0x5317, iwl1000_mac_cfg)}, +/* 1030/6x30 Series */ + {IWL_PCI_DEVICE(0x008A, 0x5305, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008A, 0x5307, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008A, 0x5325, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008A, 0x5327, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008B, 0x5315, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x008B, 0x5317, iwl6030_mac_cfg)}, {IWL_PCI_DEVICE(0x0090, 0x5211, iwl6030_mac_cfg)}, {IWL_PCI_DEVICE(0x0090, 0x5215, iwl6030_mac_cfg)}, {IWL_PCI_DEVICE(0x0090, 0x5216, iwl6030_mac_cfg)}, @@ -181,12 +181,12 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x08AE, 0x1027, iwl1000_mac_cfg)}, /* 130 Series WiFi */ - {IWL_PCI_DEVICE(0x0896, 0x5005, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0896, 0x5007, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0897, 0x5015, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0897, 0x5017, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0896, 0x5025, iwl1000_mac_cfg)}, - {IWL_PCI_DEVICE(0x0896, 0x5027, iwl1000_mac_cfg)}, + {IWL_PCI_DEVICE(0x0896, 0x5005, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0896, 0x5007, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0897, 0x5015, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0897, 0x5017, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0896, 0x5025, iwl6030_mac_cfg)}, + {IWL_PCI_DEVICE(0x0896, 0x5027, iwl6030_mac_cfg)}, /* 2x00 Series */ {IWL_PCI_DEVICE(0x0890, 0x4022, iwl2000_mac_cfg)}, @@ -673,6 +673,8 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = { IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_sff_name, DEVICE(0x0082), SUBDEV_MASKED(0xC000, 0xF000)), + IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_sff_name, + DEVICE(0x0085), SUBDEV_MASKED(0xC000, 0xF000)), IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_d_name, DEVICE(0x0082), SUBDEV(0x4820)), IWL_DEV_INFO(iwl6005_n_cfg, iwl6005_2agn_mow1_name, @@ -729,10 +731,10 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = { DEVICE(0x0083), SUBDEV_MASKED(0x5, 0xF)), IWL_DEV_INFO(iwl1000_bg_cfg, iwl1000_bg_name, DEVICE(0x0083), SUBDEV_MASKED(0x6, 0xF)), + IWL_DEV_INFO(iwl1000_bgn_cfg, iwl1000_bgn_name, + DEVICE(0x0084), SUBDEV_MASKED(0x5, 0xF)), IWL_DEV_INFO(iwl1000_bg_cfg, iwl1000_bg_name, - DEVICE(0x0084), SUBDEV(0x1216)), - IWL_DEV_INFO(iwl1000_bg_cfg, iwl1000_bg_name, - DEVICE(0x0084), SUBDEV(0x1316)), + DEVICE(0x0084), SUBDEV_MASKED(0x6, 0xF)), /* 100 Series WiFi */ IWL_DEV_INFO(iwl100_bgn_cfg, iwl100_bgn_name, @@ -964,6 +966,12 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = { DEVICE(0x24F3), SUBDEV(0x0004)), IWL_DEV_INFO(iwl8260_cfg, iwl8260_2n_name, DEVICE(0x24F3), SUBDEV(0x0044)), + IWL_DEV_INFO(iwl8260_cfg, iwl8260_2ac_name, + DEVICE(0x24F4)), + IWL_DEV_INFO(iwl8260_cfg, iwl4165_2ac_name, + DEVICE(0x24F5)), + IWL_DEV_INFO(iwl8260_cfg, iwl4165_2ac_name, + DEVICE(0x24F6)), IWL_DEV_INFO(iwl8265_cfg, iwl8265_2ac_name, DEVICE(0x24FD)), IWL_DEV_INFO(iwl8265_cfg, iwl8275_2ac_name, @@ -1222,11 +1230,15 @@ static int _iwl_pci_resume(struct device *device, bool restore) * Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan, * but not bits [15:8]. So if we have bits set in lower word, assume * the device is alive. + * Alternatively, if the scratch value is 0xFFFFFFFF, then we no longer + * have access to the device and consider it powered off. * For older devices, just try silently to grab the NIC. */ if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) { - if (!(iwl_read32(trans, CSR_FUNC_SCRATCH) & - CSR_FUNC_SCRATCH_POWER_OFF_MASK)) + u32 scratch = iwl_read32(trans, CSR_FUNC_SCRATCH); + + if (!(scratch & CSR_FUNC_SCRATCH_POWER_OFF_MASK) || + scratch == ~0U) device_was_powered_off = true; } else { /* diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c index 84a05cc1c27a..d912e709a92c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/tx.c @@ -2092,7 +2092,8 @@ static void iwl_txq_gen1_update_byte_cnt_tbl(struct iwl_trans *trans, break; } - if (trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) + if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_9000 && + trans->mac_cfg->device_family < IWL_DEVICE_FAMILY_AX210) len = DIV_ROUND_UP(len, 4); if (WARN_ON(len > 0xFFF || write_ptr >= TFD_QUEUE_SIZE_MAX)) diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c index 94dd488becaf..caba7491cd5a 100644 --- a/drivers/net/wireless/marvell/libertas/cfg.c +++ b/drivers/net/wireless/marvell/libertas/cfg.c @@ -1151,10 +1151,13 @@ static int lbs_associate(struct lbs_private *priv, /* add SSID TLV */ rcu_read_lock(); ssid_eid = ieee80211_bss_get_ie(bss, WLAN_EID_SSID); - if (ssid_eid) - pos += lbs_add_ssid_tlv(pos, ssid_eid + 2, ssid_eid[1]); - else + if (ssid_eid) { + u32 ssid_len = min(ssid_eid[1], IEEE80211_MAX_SSID_LEN); + + pos += lbs_add_ssid_tlv(pos, ssid_eid + 2, ssid_len); + } else { lbs_deb_assoc("no SSID\n"); + } rcu_read_unlock(); /* add DS param TLV */ diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c index 3498743d5ec0..4c8c7a5fdf23 100644 --- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c +++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c @@ -4673,8 +4673,9 @@ int mwifiex_init_channel_scan_gap(struct mwifiex_adapter *adapter) * additional active scan request for hidden SSIDs on passive channels. */ adapter->num_in_chan_stats = 2 * (n_channels_bg + n_channels_a); - adapter->chan_stats = vmalloc(array_size(sizeof(*adapter->chan_stats), - adapter->num_in_chan_stats)); + adapter->chan_stats = kcalloc(adapter->num_in_chan_stats, + sizeof(*adapter->chan_stats), + GFP_KERNEL); if (!adapter->chan_stats) return -ENOMEM; diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c index 7b50a88a18e5..1ec069bc8ea1 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.c +++ b/drivers/net/wireless/marvell/mwifiex/main.c @@ -642,7 +642,7 @@ static int _mwifiex_fw_dpc(const struct firmware *firmware, void *context) goto done; err_add_intf: - vfree(adapter->chan_stats); + kfree(adapter->chan_stats); err_init_chan_scan: wiphy_unregister(adapter->wiphy); wiphy_free(adapter->wiphy); @@ -1485,7 +1485,7 @@ static void mwifiex_uninit_sw(struct mwifiex_adapter *adapter) wiphy_free(adapter->wiphy); adapter->wiphy = NULL; - vfree(adapter->chan_stats); + kfree(adapter->chan_stats); mwifiex_free_cmd_buffers(adapter); } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 3afe4c4cd7bb..59adf3312617 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -818,6 +818,43 @@ void mt76_free_device(struct mt76_dev *dev) } EXPORT_SYMBOL_GPL(mt76_free_device); +static void mt76_reset_phy(struct mt76_phy *phy) +{ + if (!phy) + return; + + INIT_LIST_HEAD(&phy->tx_list); +} + +void mt76_reset_device(struct mt76_dev *dev) +{ + int i; + + rcu_read_lock(); + for (i = 0; i < ARRAY_SIZE(dev->wcid); i++) { + struct mt76_wcid *wcid; + + wcid = rcu_dereference(dev->wcid[i]); + if (!wcid) + continue; + + wcid->sta = 0; + mt76_wcid_cleanup(dev, wcid); + rcu_assign_pointer(dev->wcid[i], NULL); + } + rcu_read_unlock(); + + INIT_LIST_HEAD(&dev->wcid_list); + INIT_LIST_HEAD(&dev->sta_poll_list); + dev->vif_mask = 0; + memset(dev->wcid_mask, 0, sizeof(dev->wcid_mask)); + + mt76_reset_phy(&dev->phy); + for (i = 0; i < ARRAY_SIZE(dev->phys); i++) + mt76_reset_phy(dev->phys[i]); +} +EXPORT_SYMBOL_GPL(mt76_reset_device); + struct mt76_phy *mt76_vif_phy(struct ieee80211_hw *hw, struct ieee80211_vif *vif) { @@ -1679,6 +1716,10 @@ void mt76_wcid_cleanup(struct mt76_dev *dev, struct mt76_wcid *wcid) skb_queue_splice_tail_init(&wcid->tx_pending, &list); spin_unlock(&wcid->tx_pending.lock); + spin_lock(&wcid->tx_offchannel.lock); + skb_queue_splice_tail_init(&wcid->tx_offchannel, &list); + spin_unlock(&wcid->tx_offchannel.lock); + spin_unlock_bh(&phy->tx_lock); while ((skb = __skb_dequeue(&list)) != NULL) { @@ -1690,7 +1731,7 @@ EXPORT_SYMBOL_GPL(mt76_wcid_cleanup); void mt76_wcid_add_poll(struct mt76_dev *dev, struct mt76_wcid *wcid) { - if (test_bit(MT76_MCU_RESET, &dev->phy.state)) + if (test_bit(MT76_MCU_RESET, &dev->phy.state) || !wcid->sta) return; spin_lock_bh(&dev->sta_poll_lock); diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 8dd5c29fb75b..127637454c82 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -1243,6 +1243,7 @@ int mt76_register_device(struct mt76_dev *dev, bool vht, struct ieee80211_rate *rates, int n_rates); void mt76_unregister_device(struct mt76_dev *dev); void mt76_free_device(struct mt76_dev *dev); +void mt76_reset_device(struct mt76_dev *dev); void mt76_unregister_phy(struct mt76_phy *phy); struct mt76_phy *mt76_alloc_radio_phy(struct mt76_dev *dev, unsigned int size, diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c index 6639976afcee..1c0d310146d6 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/mac.c @@ -1460,17 +1460,15 @@ mt7915_mac_full_reset(struct mt7915_dev *dev) if (i == 10) dev_err(dev->mt76.dev, "chip full reset failed\n"); - spin_lock_bh(&dev->mt76.sta_poll_lock); - while (!list_empty(&dev->mt76.sta_poll_list)) - list_del_init(dev->mt76.sta_poll_list.next); - spin_unlock_bh(&dev->mt76.sta_poll_lock); - - memset(dev->mt76.wcid_mask, 0, sizeof(dev->mt76.wcid_mask)); - dev->mt76.vif_mask = 0; dev->phy.omac_mask = 0; if (phy2) phy2->omac_mask = 0; + mt76_reset_device(&dev->mt76); + + INIT_LIST_HEAD(&dev->sta_rc_list); + INIT_LIST_HEAD(&dev->twt_list); + i = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7915_WTBL_STA); dev->mt76.global_wcid.idx = i; dev->recovery.hw_full_reset = false; diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index 40954e64c7fc..5881040ac195 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -1459,11 +1459,8 @@ static int mt7921_pre_channel_switch(struct ieee80211_hw *hw, if (vif->type != NL80211_IFTYPE_STATION || !vif->cfg.assoc) return -EOPNOTSUPP; - /* Avoid beacon loss due to the CAC(Channel Availability Check) time - * of the AP. - */ if (!cfg80211_chandef_usable(hw->wiphy, &chsw->chandef, - IEEE80211_CHAN_RADAR)) + IEEE80211_CHAN_DISABLED)) return -EOPNOTSUPP; return 0; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c index 75823c9fd3a1..b581ab9427f2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c @@ -1449,7 +1449,7 @@ void mt7925_usb_sdio_tx_complete_skb(struct mt76_dev *mdev, sta = wcid_to_sta(wcid); if (sta && likely(e->skb->protocol != cpu_to_be16(ETH_P_PAE))) - mt76_connac2_tx_check_aggr(sta, txwi); + mt7925_tx_check_aggr(sta, e->skb, wcid); skb_pull(e->skb, headroom); mt76_tx_complete_skb(mdev, e->wcid, e->skb); diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c index a8d25b7d47d0..b0e053b15227 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c @@ -1191,6 +1191,9 @@ mt7925_mac_sta_remove_links(struct mt792x_dev *dev, struct ieee80211_vif *vif, struct mt792x_bss_conf *mconf; struct mt792x_link_sta *mlink; + if (vif->type == NL80211_IFTYPE_AP) + break; + link_sta = mt792x_sta_to_link_sta(vif, sta, link_id); if (!link_sta) continue; @@ -2069,8 +2072,10 @@ mt7925_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif, GFP_KERNEL); mlink = devm_kzalloc(dev->mt76.dev, sizeof(*mlink), GFP_KERNEL); - if (!mconf || !mlink) + if (!mconf || !mlink) { + mt792x_mutex_release(dev); return -ENOMEM; + } } mconfs[link_id] = mconf; diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c index 300c863f0e3e..cd457be26523 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c @@ -1834,13 +1834,13 @@ mt7925_mcu_sta_eht_mld_tlv(struct sk_buff *skb, struct tlv *tlv; u16 eml_cap; + if (!ieee80211_vif_is_mld(vif)) + return; + tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_EHT_MLD, sizeof(*eht_mld)); eht_mld = (struct sta_rec_eht_mld *)tlv; eht_mld->mld_type = 0xff; - if (!ieee80211_vif_is_mld(vif)) - return; - ext_capa = cfg80211_get_iftype_ext_capa(wiphy, ieee80211_vif_type_p2p(vif)); if (!ext_capa) @@ -1912,6 +1912,7 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy, struct mt76_dev *dev = phy->dev; struct mt792x_bss_conf *mconf; struct sk_buff *skb; + int conn_state; mconf = mt792x_vif_to_link(mvif, info->wcid->link_id); @@ -1920,10 +1921,13 @@ mt7925_mcu_sta_cmd(struct mt76_phy *phy, if (IS_ERR(skb)) return PTR_ERR(skb); + conn_state = info->enable ? CONN_STATE_PORT_SECURE : + CONN_STATE_DISCONNECT; + if (info->enable && info->link_sta) { mt76_connac_mcu_sta_basic_tlv(dev, skb, info->link_conf, info->link_sta, - info->enable, info->newly); + conn_state, info->newly); mt7925_mcu_sta_phy_tlv(skb, info->vif, info->link_sta); mt7925_mcu_sta_ht_tlv(skb, info->link_sta); mt7925_mcu_sta_vht_tlv(skb, info->link_sta); diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c index 226534490792..b3fcca9bbb95 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c @@ -62,7 +62,7 @@ static struct mt76_wcid *mt7996_rx_get_wcid(struct mt7996_dev *dev, int i; wcid = mt76_wcid_ptr(dev, idx); - if (!wcid) + if (!wcid || !wcid->sta) return NULL; if (!mt7996_band_valid(dev, band_idx)) @@ -903,8 +903,12 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, IEEE80211_TX_CTRL_MLO_LINK); mvif = vif ? (struct mt7996_vif *)vif->drv_priv : NULL; - if (mvif) - mlink = rcu_dereference(mvif->mt76.link[link_id]); + if (mvif) { + if (wcid->offchannel) + mlink = rcu_dereference(mvif->mt76.offchannel_link); + if (!mlink) + mlink = rcu_dereference(mvif->mt76.link[link_id]); + } if (mlink) { omac_idx = mlink->omac_idx; @@ -1243,8 +1247,10 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len) idx = FIELD_GET(MT_TXFREE_INFO_WLAN_ID, info); wcid = mt76_wcid_ptr(dev, idx); sta = wcid_to_sta(wcid); - if (!sta) + if (!sta) { + link_sta = NULL; goto next; + } link_sta = rcu_dereference(sta->link[wcid->link_id]); if (!link_sta) @@ -1694,43 +1700,53 @@ mt7996_wait_reset_state(struct mt7996_dev *dev, u32 state) static void mt7996_update_vif_beacon(void *priv, u8 *mac, struct ieee80211_vif *vif) { - struct ieee80211_hw *hw = priv; + struct ieee80211_bss_conf *link_conf; + struct mt7996_phy *phy = priv; + struct mt7996_dev *dev = phy->dev; + unsigned int link_id; + switch (vif->type) { case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_AP: - mt7996_mcu_add_beacon(hw, vif, &vif->bss_conf); break; default: - break; + return; + } + + for_each_vif_active_link(vif, link_conf, link_id) { + struct mt7996_vif_link *link; + + link = mt7996_vif_link(dev, vif, link_id); + if (!link || link->phy != phy) + continue; + + mt7996_mcu_add_beacon(dev->mt76.hw, vif, link_conf); } } +void mt7996_mac_update_beacons(struct mt7996_phy *phy) +{ + ieee80211_iterate_active_interfaces(phy->mt76->hw, + IEEE80211_IFACE_ITER_RESUME_ALL, + mt7996_update_vif_beacon, phy); +} + static void mt7996_update_beacons(struct mt7996_dev *dev) { struct mt76_phy *phy2, *phy3; - ieee80211_iterate_active_interfaces(dev->mt76.hw, - IEEE80211_IFACE_ITER_RESUME_ALL, - mt7996_update_vif_beacon, dev->mt76.hw); + mt7996_mac_update_beacons(&dev->phy); phy2 = dev->mt76.phys[MT_BAND1]; - if (!phy2) - return; - - ieee80211_iterate_active_interfaces(phy2->hw, - IEEE80211_IFACE_ITER_RESUME_ALL, - mt7996_update_vif_beacon, phy2->hw); + if (phy2) + mt7996_mac_update_beacons(phy2->priv); phy3 = dev->mt76.phys[MT_BAND2]; - if (!phy3) - return; - - ieee80211_iterate_active_interfaces(phy3->hw, - IEEE80211_IFACE_ITER_RESUME_ALL, - mt7996_update_vif_beacon, phy3->hw); + if (phy3) + mt7996_mac_update_beacons(phy3->priv); } void mt7996_tx_token_put(struct mt7996_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 92b57bcce749..84f731b387d2 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -516,6 +516,9 @@ int mt7996_set_channel(struct mt76_phy *mphy) struct mt7996_phy *phy = mphy->priv; int ret; + if (mphy->offchannel) + mt7996_mac_update_beacons(phy); + ret = mt7996_mcu_set_chan_info(phy, UNI_CHANNEL_SWITCH); if (ret) goto out; @@ -533,6 +536,8 @@ int mt7996_set_channel(struct mt76_phy *mphy) mt7996_mac_reset_counters(phy); phy->noise = 0; + if (!mphy->offchannel) + mt7996_mac_update_beacons(phy); out: ieee80211_queue_delayed_work(mphy->hw, &mphy->mac_work, diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c index 3593fd40c51b..0be03eb3cf46 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c @@ -1879,8 +1879,8 @@ mt7996_mcu_get_mmps_mode(enum ieee80211_smps_mode smps) int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev, void *data, u16 version) { + struct uni_header hdr = {}; struct ra_fixed_rate *req; - struct uni_header hdr; struct sk_buff *skb; struct tlv *tlv; int len; @@ -2755,13 +2755,15 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_bss_conf *link_conf) { struct mt7996_dev *dev = mt7996_hw_dev(hw); - struct mt76_vif_link *mlink = mt76_vif_conf_link(&dev->mt76, vif, link_conf); + struct mt7996_vif_link *link = mt7996_vif_conf_link(dev, vif, link_conf); + struct mt76_vif_link *mlink = link ? &link->mt76 : NULL; struct ieee80211_mutable_offsets offs; struct ieee80211_tx_info *info; struct sk_buff *skb, *rskb; struct tlv *tlv; struct bss_bcn_content_tlv *bcn; int len, extra_len = 0; + bool enabled = link_conf->enable_beacon; if (link_conf->nontransmitted) return 0; @@ -2769,13 +2771,16 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, if (!mlink) return -EINVAL; + if (link->phy && link->phy->mt76->offchannel) + enabled = false; + rskb = __mt7996_mcu_alloc_bss_req(&dev->mt76, mlink, MT7996_MAX_BSS_OFFLOAD_SIZE); if (IS_ERR(rskb)) return PTR_ERR(rskb); skb = ieee80211_beacon_get_template(hw, vif, &offs, link_conf->link_id); - if (link_conf->enable_beacon && !skb) { + if (enabled && !skb) { dev_kfree_skb(rskb); return -EINVAL; } @@ -2794,7 +2799,7 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif, len = ALIGN(sizeof(*bcn) + MT_TXD_SIZE + extra_len, 4); tlv = mt7996_mcu_add_uni_tlv(rskb, UNI_BSS_INFO_BCN_CONTENT, len); bcn = (struct bss_bcn_content_tlv *)tlv; - bcn->enable = link_conf->enable_beacon; + bcn->enable = enabled; if (!bcn->enable) goto out; @@ -3372,7 +3377,7 @@ int mt7996_mcu_set_hdr_trans(struct mt7996_dev *dev, bool hdr_trans) { struct { u8 __rsv[4]; - } __packed hdr; + } __packed hdr = {}; struct hdr_trans_blacklist *req_blacklist; struct hdr_trans_en *req_en; struct sk_buff *skb; diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h index 33ac16b64ef1..8509d508e1e1 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h +++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h @@ -732,6 +732,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi, struct sk_buff *skb, struct mt76_wcid *wcid, struct ieee80211_key_conf *key, int pid, enum mt76_txq_id qid, u32 changed); +void mt7996_mac_update_beacons(struct mt7996_phy *phy); void mt7996_mac_set_coverage_class(struct mt7996_phy *phy); void mt7996_mac_work(struct work_struct *work); void mt7996_mac_reset_work(struct work_struct *work); diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index e6cf16706667..8ab5840fee57 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -332,6 +332,7 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta, struct mt76_wcid *wcid, struct sk_buff *skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_hdr *hdr = (void *)skb->data; struct sk_buff_head *head; if (mt76_testmode_enabled(phy)) { @@ -349,7 +350,8 @@ mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta, info->hw_queue |= FIELD_PREP(MT_TX_HW_QUEUE_PHY, phy->band_idx); if ((info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) || - (info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK)) + ((info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK) && + ieee80211_is_probe_req(hdr->frame_control))) head = &wcid->tx_offchannel; else head = &wcid->tx_pending; @@ -644,6 +646,7 @@ mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid, static void mt76_txq_schedule_pending(struct mt76_phy *phy) { LIST_HEAD(tx_list); + int ret = 0; if (list_empty(&phy->tx_list)) return; @@ -655,13 +658,13 @@ static void mt76_txq_schedule_pending(struct mt76_phy *phy) list_splice_init(&phy->tx_list, &tx_list); while (!list_empty(&tx_list)) { struct mt76_wcid *wcid; - int ret; wcid = list_first_entry(&tx_list, struct mt76_wcid, tx_list); list_del_init(&wcid->tx_list); spin_unlock(&phy->tx_lock); - ret = mt76_txq_schedule_pending_wcid(phy, wcid, &wcid->tx_offchannel); + if (ret >= 0) + ret = mt76_txq_schedule_pending_wcid(phy, wcid, &wcid->tx_offchannel); if (ret >= 0 && !phy->offchannel) ret = mt76_txq_schedule_pending_wcid(phy, wcid, &wcid->tx_pending); spin_lock(&phy->tx_lock); @@ -670,9 +673,6 @@ static void mt76_txq_schedule_pending(struct mt76_phy *phy) !skb_queue_empty(&wcid->tx_offchannel) && list_empty(&wcid->tx_list)) list_add_tail(&wcid->tx_list, &phy->tx_list); - - if (ret < 0) - break; } spin_unlock(&phy->tx_lock); diff --git a/drivers/net/wireless/microchip/wilc1000/wlan_cfg.c b/drivers/net/wireless/microchip/wilc1000/wlan_cfg.c index 131388886acb..cfabd5aebb54 100644 --- a/drivers/net/wireless/microchip/wilc1000/wlan_cfg.c +++ b/drivers/net/wireless/microchip/wilc1000/wlan_cfg.c @@ -41,10 +41,10 @@ static const struct wilc_cfg_word g_cfg_word[] = { }; static const struct wilc_cfg_str g_cfg_str[] = { - {WID_FIRMWARE_VERSION, NULL}, - {WID_MAC_ADDR, NULL}, - {WID_ASSOC_RES_INFO, NULL}, - {WID_NIL, NULL} + {WID_FIRMWARE_VERSION, 0, NULL}, + {WID_MAC_ADDR, 0, NULL}, + {WID_ASSOC_RES_INFO, 0, NULL}, + {WID_NIL, 0, NULL} }; #define WILC_RESP_MSG_TYPE_CONFIG_REPLY 'R' @@ -147,44 +147,58 @@ static void wilc_wlan_parse_response_frame(struct wilc *wl, u8 *info, int size) switch (FIELD_GET(WILC_WID_TYPE, wid)) { case WID_CHAR: + len = 3; + if (len + 2 > size) + return; + while (cfg->b[i].id != WID_NIL && cfg->b[i].id != wid) i++; if (cfg->b[i].id == wid) cfg->b[i].val = info[4]; - len = 3; break; case WID_SHORT: + len = 4; + if (len + 2 > size) + return; + while (cfg->hw[i].id != WID_NIL && cfg->hw[i].id != wid) i++; if (cfg->hw[i].id == wid) cfg->hw[i].val = get_unaligned_le16(&info[4]); - len = 4; break; case WID_INT: + len = 6; + if (len + 2 > size) + return; + while (cfg->w[i].id != WID_NIL && cfg->w[i].id != wid) i++; if (cfg->w[i].id == wid) cfg->w[i].val = get_unaligned_le32(&info[4]); - len = 6; break; case WID_STR: + len = 2 + get_unaligned_le16(&info[2]); + while (cfg->s[i].id != WID_NIL && cfg->s[i].id != wid) i++; - if (cfg->s[i].id == wid) + if (cfg->s[i].id == wid) { + if (len > cfg->s[i].len || (len + 2 > size)) + return; + memcpy(cfg->s[i].str, &info[2], - get_unaligned_le16(&info[2]) + 2); + len); + } - len = 2 + get_unaligned_le16(&info[2]); break; default: @@ -384,12 +398,15 @@ int wilc_wlan_cfg_init(struct wilc *wl) /* store the string cfg parameters */ wl->cfg.s[i].id = WID_FIRMWARE_VERSION; wl->cfg.s[i].str = str_vals->firmware_version; + wl->cfg.s[i].len = sizeof(str_vals->firmware_version); i++; wl->cfg.s[i].id = WID_MAC_ADDR; wl->cfg.s[i].str = str_vals->mac_address; + wl->cfg.s[i].len = sizeof(str_vals->mac_address); i++; wl->cfg.s[i].id = WID_ASSOC_RES_INFO; wl->cfg.s[i].str = str_vals->assoc_rsp; + wl->cfg.s[i].len = sizeof(str_vals->assoc_rsp); i++; wl->cfg.s[i].id = WID_NIL; wl->cfg.s[i].str = NULL; diff --git a/drivers/net/wireless/microchip/wilc1000/wlan_cfg.h b/drivers/net/wireless/microchip/wilc1000/wlan_cfg.h index 7038b74f8e8f..5ae74bced7d7 100644 --- a/drivers/net/wireless/microchip/wilc1000/wlan_cfg.h +++ b/drivers/net/wireless/microchip/wilc1000/wlan_cfg.h @@ -24,12 +24,13 @@ struct wilc_cfg_word { struct wilc_cfg_str { u16 id; + u16 len; u8 *str; }; struct wilc_cfg_str_vals { - u8 mac_address[7]; - u8 firmware_version[129]; + u8 mac_address[8]; + u8 firmware_version[130]; u8 assoc_rsp[WILC_MAX_ASSOC_RESP_FRAME_SIZE]; }; diff --git a/drivers/net/wireless/ralink/rt2x00/Kconfig b/drivers/net/wireless/ralink/rt2x00/Kconfig index 4d98b7723c56..17f063fc0b57 100644 --- a/drivers/net/wireless/ralink/rt2x00/Kconfig +++ b/drivers/net/wireless/ralink/rt2x00/Kconfig @@ -66,7 +66,6 @@ config RT2800PCI select RT2X00_LIB_PCI select RT2X00_LIB_FIRMWARE select RT2X00_LIB_CRYPTO - select CRC_CCITT select EEPROM_93CX6 help This adds support for rt27xx/rt28xx/rt30xx wireless chipset family. @@ -142,7 +141,6 @@ config RT2800USB select RT2X00_LIB_USB select RT2X00_LIB_FIRMWARE select RT2X00_LIB_CRYPTO - select CRC_CCITT help This adds support for rt27xx/rt28xx/rt30xx wireless chipset family. Supported chips: RT2770, RT2870 & RT3070, RT3071 & RT3072 @@ -217,6 +215,7 @@ config RT2800SOC config RT2800_LIB tristate + select CRC_CCITT config RT2800_LIB_MMIO tristate @@ -225,6 +224,7 @@ config RT2800_LIB_MMIO config RT2X00_LIB_MMIO tristate + select RT2X00_LIB config RT2X00_LIB_PCI tristate diff --git a/drivers/net/wireless/st/cw1200/sta.c b/drivers/net/wireless/st/cw1200/sta.c index b1dd76e8aecb..5d8eaa700779 100644 --- a/drivers/net/wireless/st/cw1200/sta.c +++ b/drivers/net/wireless/st/cw1200/sta.c @@ -1291,7 +1291,7 @@ static void cw1200_do_join(struct cw1200_common *priv) rcu_read_lock(); ssidie = ieee80211_bss_get_ie(bss, WLAN_EID_SSID); if (ssidie) { - join.ssid_len = ssidie[1]; + join.ssid_len = min(ssidie[1], IEEE80211_MAX_SSID_LEN); memcpy(join.ssid, &ssidie[2], join.ssid_len); } rcu_read_unlock(); diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c index 1fffeff2190c..4eae89376feb 100644 --- a/drivers/net/wireless/virtual/virt_wifi.c +++ b/drivers/net/wireless/virtual/virt_wifi.c @@ -277,7 +277,9 @@ static void virt_wifi_connect_complete(struct work_struct *work) priv->is_connected = true; /* Schedules an event that acquires the rtnl lock. */ - cfg80211_connect_result(priv->upperdev, requested_bss, NULL, 0, NULL, 0, + cfg80211_connect_result(priv->upperdev, + priv->is_connected ? fake_router_bssid : NULL, + NULL, 0, NULL, 0, status, GFP_KERNEL); netif_carrier_on(priv->upperdev); } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 812c1565114f..6b7493934535 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -903,6 +903,15 @@ static void nvme_set_ref_tag(struct nvme_ns *ns, struct nvme_command *cmnd, u32 upper, lower; u64 ref48; + /* only type1 and type 2 PI formats have a reftag */ + switch (ns->head->pi_type) { + case NVME_NS_DPS_PI_TYPE1: + case NVME_NS_DPS_PI_TYPE2: + break; + default: + return; + } + /* both rw and write zeroes share the same reftag format */ switch (ns->head->guard_type) { case NVME_NVM_NS_16B_GUARD: @@ -942,13 +951,7 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, if (nvme_ns_has_pi(ns->head)) { cmnd->write_zeroes.control |= cpu_to_le16(NVME_RW_PRINFO_PRACT); - - switch (ns->head->pi_type) { - case NVME_NS_DPS_PI_TYPE1: - case NVME_NS_DPS_PI_TYPE2: - nvme_set_ref_tag(ns, cmnd, req); - break; - } + nvme_set_ref_tag(ns, cmnd, req); } return BLK_STS_OK; @@ -1039,6 +1042,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, if (WARN_ON_ONCE(!nvme_ns_has_pi(ns->head))) return BLK_STS_NOTSUPP; control |= NVME_RW_PRINFO_PRACT; + nvme_set_ref_tag(ns, cmnd, req); } if (bio_integrity_flagged(req->bio, BIP_CHECK_GUARD)) diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index 755651f33811..a72aa57591c0 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -1168,12 +1168,6 @@ static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev, return devm_ioremap_resource(&pdev->dev, &port->regs); } -#define DT_FLAGS_TO_TYPE(flags) (((flags) >> 24) & 0x03) -#define DT_TYPE_IO 0x1 -#define DT_TYPE_MEM32 0x2 -#define DT_CPUADDR_TO_TARGET(cpuaddr) (((cpuaddr) >> 56) & 0xFF) -#define DT_CPUADDR_TO_ATTR(cpuaddr) (((cpuaddr) >> 48) & 0xFF) - static int mvebu_get_tgt_attr(struct device_node *np, int devfn, unsigned long type, unsigned int *tgt, @@ -1189,19 +1183,12 @@ static int mvebu_get_tgt_attr(struct device_node *np, int devfn, return -EINVAL; for_each_of_range(&parser, &range) { - unsigned long rtype; u32 slot = upper_32_bits(range.bus_addr); - if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_IO) - rtype = IORESOURCE_IO; - else if (DT_FLAGS_TO_TYPE(range.flags) == DT_TYPE_MEM32) - rtype = IORESOURCE_MEM; - else - continue; - - if (slot == PCI_SLOT(devfn) && type == rtype) { - *tgt = DT_CPUADDR_TO_TARGET(range.cpu_addr); - *attr = DT_CPUADDR_TO_ATTR(range.cpu_addr); + if (slot == PCI_SLOT(devfn) && + type == (range.flags & IORESOURCE_TYPE_BITS)) { + *tgt = (range.parent_bus_addr >> 56) & 0xFF; + *attr = (range.parent_bus_addr >> 48) & 0xFF; return 0; } } diff --git a/drivers/pcmcia/Kconfig b/drivers/pcmcia/Kconfig index dddb235dd020..660a95805524 100644 --- a/drivers/pcmcia/Kconfig +++ b/drivers/pcmcia/Kconfig @@ -250,7 +250,4 @@ config ELECTRA_CF config PCCARD_NONSTATIC bool -config PCCARD_IODYN - bool - endif # PCCARD diff --git a/drivers/pcmcia/Makefile b/drivers/pcmcia/Makefile index c9d51b150682..d16a0317ce43 100644 --- a/drivers/pcmcia/Makefile +++ b/drivers/pcmcia/Makefile @@ -12,7 +12,6 @@ obj-$(CONFIG_PCMCIA) += pcmcia.o pcmcia_rsrc-y += rsrc_mgr.o pcmcia_rsrc-$(CONFIG_PCCARD_NONSTATIC) += rsrc_nonstatic.o -pcmcia_rsrc-$(CONFIG_PCCARD_IODYN) += rsrc_iodyn.o obj-$(CONFIG_PCCARD) += pcmcia_rsrc.o diff --git a/drivers/pcmcia/cs.c b/drivers/pcmcia/cs.c index c75f55e1250a..adbc486af2ea 100644 --- a/drivers/pcmcia/cs.c +++ b/drivers/pcmcia/cs.c @@ -229,23 +229,6 @@ void pcmcia_unregister_socket(struct pcmcia_socket *socket) EXPORT_SYMBOL(pcmcia_unregister_socket); -struct pcmcia_socket *pcmcia_get_socket_by_nr(unsigned int nr) -{ - struct pcmcia_socket *s; - - down_read(&pcmcia_socket_list_rwsem); - list_for_each_entry(s, &pcmcia_socket_list, socket_list) - if (s->sock == nr) { - up_read(&pcmcia_socket_list_rwsem); - return s; - } - up_read(&pcmcia_socket_list_rwsem); - - return NULL; - -} -EXPORT_SYMBOL(pcmcia_get_socket_by_nr); - static int socket_reset(struct pcmcia_socket *skt) { int status, i; diff --git a/drivers/pcmcia/cs_internal.h b/drivers/pcmcia/cs_internal.h index 02a83ca44e77..5ac810ffda31 100644 --- a/drivers/pcmcia/cs_internal.h +++ b/drivers/pcmcia/cs_internal.h @@ -116,7 +116,6 @@ extern struct list_head pcmcia_socket_list; extern const struct class pcmcia_socket_class; int pccard_register_pcmcia(struct pcmcia_socket *s, struct pcmcia_callback *c); -struct pcmcia_socket *pcmcia_get_socket_by_nr(unsigned int nr); void pcmcia_parse_uevents(struct pcmcia_socket *socket, unsigned int events); #define PCMCIA_UEVENT_EJECT 0x0001 diff --git a/drivers/pcmcia/ds.c b/drivers/pcmcia/ds.c index da6f66f357cc..18f4eef28dbc 100644 --- a/drivers/pcmcia/ds.c +++ b/drivers/pcmcia/ds.c @@ -1308,7 +1308,7 @@ static int pcmcia_bus_early_resume(struct pcmcia_socket *skt) * physically present, even if the call to this function returns * non-NULL. Furthermore, the device driver most likely is unbound * almost immediately, so the timeframe where pcmcia_dev_present - * returns NULL is probably really really small. + * returns NULL is probably really, really small. */ struct pcmcia_device *pcmcia_dev_present(struct pcmcia_device *_p_dev) { diff --git a/drivers/pcmcia/omap_cf.c b/drivers/pcmcia/omap_cf.c index 1b1dff56ec7b..d6f24c7d1562 100644 --- a/drivers/pcmcia/omap_cf.c +++ b/drivers/pcmcia/omap_cf.c @@ -215,6 +215,8 @@ static int __init omap_cf_probe(struct platform_device *pdev) return -EINVAL; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) + return -EINVAL; cf = kzalloc(sizeof *cf, GFP_KERNEL); if (!cf) @@ -302,7 +304,13 @@ static void __exit omap_cf_remove(struct platform_device *pdev) kfree(cf); } -static struct platform_driver omap_cf_driver = { +/* + * omap_cf_remove() lives in .exit.text. For drivers registered via + * platform_driver_probe() this is ok because they cannot get unbound at + * runtime. So mark the driver struct with __refdata to prevent modpost + * triggering a section mismatch warning. + */ +static struct platform_driver omap_cf_driver __refdata = { .driver = { .name = driver_name, }, diff --git a/drivers/pcmcia/rsrc_iodyn.c b/drivers/pcmcia/rsrc_iodyn.c deleted file mode 100644 index b04b16496b0c..000000000000 --- a/drivers/pcmcia/rsrc_iodyn.c +++ /dev/null @@ -1,168 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * rsrc_iodyn.c -- Resource management routines for MEM-static sockets. - * - * The initial developer of the original code is David A. Hinds - * <dahinds@users.sourceforge.net>. Portions created by David A. Hinds - * are Copyright (C) 1999 David A. Hinds. All Rights Reserved. - * - * (C) 1999 David A. Hinds - */ - -#include <linux/slab.h> -#include <linux/module.h> -#include <linux/kernel.h> - -#include <pcmcia/ss.h> -#include <pcmcia/cistpl.h> -#include "cs_internal.h" - - -struct pcmcia_align_data { - unsigned long mask; - unsigned long offset; -}; - -static resource_size_t pcmcia_align(void *align_data, - const struct resource *res, - resource_size_t size, resource_size_t align) -{ - struct pcmcia_align_data *data = align_data; - resource_size_t start; - - start = (res->start & ~data->mask) + data->offset; - if (start < res->start) - start += data->mask + 1; - -#ifdef CONFIG_X86 - if (res->flags & IORESOURCE_IO) { - if (start & 0x300) - start = (start + 0x3ff) & ~0x3ff; - } -#endif - -#ifdef CONFIG_M68K - if (res->flags & IORESOURCE_IO) { - if ((res->start + size - 1) >= 1024) - start = res->end; - } -#endif - - return start; -} - - -static struct resource *__iodyn_find_io_region(struct pcmcia_socket *s, - unsigned long base, int num, - unsigned long align) -{ - struct resource *res = pcmcia_make_resource(0, num, IORESOURCE_IO, - dev_name(&s->dev)); - struct pcmcia_align_data data; - unsigned long min = base; - int ret; - - data.mask = align - 1; - data.offset = base & data.mask; - -#ifdef CONFIG_PCI - if (s->cb_dev) { - ret = pci_bus_alloc_resource(s->cb_dev->bus, res, num, 1, - min, 0, pcmcia_align, &data); - } else -#endif - ret = allocate_resource(&ioport_resource, res, num, min, ~0UL, - 1, pcmcia_align, &data); - - if (ret != 0) { - kfree(res); - res = NULL; - } - return res; -} - -static int iodyn_find_io(struct pcmcia_socket *s, unsigned int attr, - unsigned int *base, unsigned int num, - unsigned int align, struct resource **parent) -{ - int i, ret = 0; - - /* Check for an already-allocated window that must conflict with - * what was asked for. It is a hack because it does not catch all - * potential conflicts, just the most obvious ones. - */ - for (i = 0; i < MAX_IO_WIN; i++) { - if (!s->io[i].res) - continue; - - if (!*base) - continue; - - if ((s->io[i].res->start & (align-1)) == *base) - return -EBUSY; - } - - for (i = 0; i < MAX_IO_WIN; i++) { - struct resource *res = s->io[i].res; - unsigned int try; - - if (res && (res->flags & IORESOURCE_BITS) != - (attr & IORESOURCE_BITS)) - continue; - - if (!res) { - if (align == 0) - align = 0x10000; - - res = s->io[i].res = __iodyn_find_io_region(s, *base, - num, align); - if (!res) - return -EINVAL; - - *base = res->start; - s->io[i].res->flags = - ((res->flags & ~IORESOURCE_BITS) | - (attr & IORESOURCE_BITS)); - s->io[i].InUse = num; - *parent = res; - return 0; - } - - /* Try to extend top of window */ - try = res->end + 1; - if ((*base == 0) || (*base == try)) { - if (adjust_resource(s->io[i].res, res->start, - resource_size(res) + num)) - continue; - *base = try; - s->io[i].InUse += num; - *parent = res; - return 0; - } - - /* Try to extend bottom of window */ - try = res->start - num; - if ((*base == 0) || (*base == try)) { - if (adjust_resource(s->io[i].res, - res->start - num, - resource_size(res) + num)) - continue; - *base = try; - s->io[i].InUse += num; - *parent = res; - return 0; - } - } - - return -EINVAL; -} - - -struct pccard_resource_ops pccard_iodyn_ops = { - .validate_mem = NULL, - .find_io = iodyn_find_io, - .find_mem = NULL, - .init = static_init, - .exit = NULL, -}; -EXPORT_SYMBOL(pccard_iodyn_ops); diff --git a/drivers/pcmcia/rsrc_nonstatic.c b/drivers/pcmcia/rsrc_nonstatic.c index bf9d070a4496..da494fe451ba 100644 --- a/drivers/pcmcia/rsrc_nonstatic.c +++ b/drivers/pcmcia/rsrc_nonstatic.c @@ -375,7 +375,9 @@ static int do_validate_mem(struct pcmcia_socket *s, if (validate && !s->fake_cis) { /* move it to the validated data set */ - add_interval(&s_data->mem_db_valid, base, size); + ret = add_interval(&s_data->mem_db_valid, base, size); + if (ret) + return ret; sub_interval(&s_data->mem_db, base, size); } diff --git a/drivers/pcmcia/socket_sysfs.c b/drivers/pcmcia/socket_sysfs.c index c7a906664c36..4eadd0485066 100644 --- a/drivers/pcmcia/socket_sysfs.c +++ b/drivers/pcmcia/socket_sysfs.c @@ -10,6 +10,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/string.h> +#include <linux/string_choices.h> #include <linux/major.h> #include <linux/errno.h> #include <linux/mm.h> @@ -98,7 +99,7 @@ static ssize_t pccard_show_card_pm_state(struct device *dev, char *buf) { struct pcmcia_socket *s = to_socket(dev); - return sysfs_emit(buf, "%s\n", s->state & SOCKET_SUSPEND ? "off" : "on"); + return sysfs_emit(buf, "%s\n", str_off_on(s->state & SOCKET_SUSPEND)); } static ssize_t pccard_store_card_pm_state(struct device *dev, @@ -177,7 +178,7 @@ static ssize_t pccard_show_resource(struct device *dev, struct device_attribute *attr, char *buf) { struct pcmcia_socket *s = to_socket(dev); - return sysfs_emit(buf, "%s\n", s->resource_setup_done ? "yes" : "no"); + return sysfs_emit(buf, "%s\n", str_yes_no(s->resource_setup_done)); } static ssize_t pccard_store_resource(struct device *dev, diff --git a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c index e0f2acc8109c..8fcbc312fd61 100644 --- a/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c +++ b/drivers/phy/qualcomm/phy-qcom-eusb2-repeater.c @@ -127,13 +127,13 @@ static int eusb2_repeater_init(struct phy *phy) rptr->cfg->init_tbl[i].value); /* Override registers from devicetree values */ - if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val)) + if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val)) regmap_write(regmap, base + EUSB2_TUNE_USB2_PREEM, val); if (!of_property_read_u8(np, "qcom,tune-usb2-disc-thres", &val)) regmap_write(regmap, base + EUSB2_TUNE_HSDISC, val); - if (!of_property_read_u8(np, "qcom,tune-usb2-preem", &val)) + if (!of_property_read_u8(np, "qcom,tune-usb2-amplitude", &val)) regmap_write(regmap, base + EUSB2_TUNE_IUSB2, val); /* Wait for status OK */ diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c index 95830dcfdec9..0fa63b734b67 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c @@ -3067,6 +3067,14 @@ struct qmp_pcie { struct clk_fixed_rate aux_clk_fixed; }; +static bool qphy_checkbits(const void __iomem *base, u32 offset, u32 val) +{ + u32 reg; + + reg = readl(base + offset); + return (reg & val) == val; +} + static inline void qphy_setbits(void __iomem *base, u32 offset, u32 val) { u32 reg; @@ -4339,16 +4347,21 @@ static int qmp_pcie_init(struct phy *phy) struct qmp_pcie *qmp = phy_get_drvdata(phy); const struct qmp_phy_cfg *cfg = qmp->cfg; void __iomem *pcs = qmp->pcs; - bool phy_initialized = !!(readl(pcs + cfg->regs[QPHY_START_CTRL])); int ret; - qmp->skip_init = qmp->nocsr_reset && phy_initialized; /* - * We need to check the existence of init sequences in two cases: - * 1. The PHY doesn't support no_csr reset. - * 2. The PHY supports no_csr reset but isn't initialized by bootloader. - * As we can't skip init in these two cases. + * We can skip PHY initialization if all of the following conditions + * are met: + * 1. The PHY supports the nocsr_reset that preserves the PHY config. + * 2. The PHY was started (and not powered down again) by the + * bootloader, with all of the expected bits set correctly. + * In this case, we can continue without having the init sequence + * defined in the driver. */ + qmp->skip_init = qmp->nocsr_reset && + qphy_checkbits(pcs, cfg->regs[QPHY_START_CTRL], SERDES_START | PCS_START) && + qphy_checkbits(pcs, cfg->regs[QPHY_PCS_POWER_DOWN_CONTROL], cfg->pwrdn_ctrl); + if (!qmp->skip_init && !cfg->tbls.serdes_num) { dev_err(qmp->dev, "Init sequence not available\n"); return -ENODATA; diff --git a/drivers/phy/tegra/xusb-tegra210.c b/drivers/phy/tegra/xusb-tegra210.c index ebc8a7e21a31..3409924498e9 100644 --- a/drivers/phy/tegra/xusb-tegra210.c +++ b/drivers/phy/tegra/xusb-tegra210.c @@ -3164,18 +3164,22 @@ tegra210_xusb_padctl_probe(struct device *dev, } pdev = of_find_device_by_node(np); + of_node_put(np); if (!pdev) { dev_warn(dev, "PMC device is not available\n"); goto out; } - if (!platform_get_drvdata(pdev)) + if (!platform_get_drvdata(pdev)) { + put_device(&pdev->dev); return ERR_PTR(-EPROBE_DEFER); + } padctl->regmap = dev_get_regmap(&pdev->dev, "usb_sleepwalk"); if (!padctl->regmap) dev_info(dev, "failed to find PMC regmap\n"); + put_device(&pdev->dev); out: return &padctl->base; } diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c index ff5d5e29629f..50adabb867cb 100644 --- a/drivers/phy/ti/phy-gmii-sel.c +++ b/drivers/phy/ti/phy-gmii-sel.c @@ -34,6 +34,7 @@ enum { PHY_GMII_SEL_PORT_MODE = 0, PHY_GMII_SEL_RGMII_ID_MODE, PHY_GMII_SEL_RMII_IO_CLK_EN, + PHY_GMII_SEL_FIXED_TX_DELAY, PHY_GMII_SEL_LAST, }; @@ -127,6 +128,11 @@ static int phy_gmii_sel_mode(struct phy *phy, enum phy_mode mode, int submode) goto unsupported; } + /* With a fixed delay, some modes are not supported at all. */ + if (soc_data->features & BIT(PHY_GMII_SEL_FIXED_TX_DELAY) && + rgmii_id != 0) + return -EINVAL; + if_phy->phy_if_mode = submode; dev_dbg(dev, "%s id:%u mode:%u rgmii_id:%d rmii_clk_ext:%d\n", @@ -210,25 +216,46 @@ struct phy_gmii_sel_soc_data phy_gmii_sel_soc_dm814 = { static const struct reg_field phy_gmii_sel_fields_am654[][PHY_GMII_SEL_LAST] = { - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x0, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x4, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x8, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0xC, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x10, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x14, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x18, 0, 2), }, - { [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x1C, 0, 2), }, + { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x0, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x0, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x4, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x4, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x8, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x8, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0xC, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0xC, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x10, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x10, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x14, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x14, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x18, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x18, 4, 4), + }, { + [PHY_GMII_SEL_PORT_MODE] = REG_FIELD(0x1C, 0, 2), + [PHY_GMII_SEL_RGMII_ID_MODE] = REG_FIELD(0x1C, 4, 4), + }, }; static const struct phy_gmii_sel_soc_data phy_gmii_sel_soc_am654 = { .use_of_data = true, + .features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) | + BIT(PHY_GMII_SEL_FIXED_TX_DELAY), .regfields = phy_gmii_sel_fields_am654, }; static const struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw5g_soc_j7200 = { .use_of_data = true, + .features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) | + BIT(PHY_GMII_SEL_FIXED_TX_DELAY), .regfields = phy_gmii_sel_fields_am654, .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) | BIT(PHY_INTERFACE_MODE_USXGMII), @@ -239,6 +266,8 @@ struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw5g_soc_j7200 = { static const struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j721e = { .use_of_data = true, + .features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) | + BIT(PHY_GMII_SEL_FIXED_TX_DELAY), .regfields = phy_gmii_sel_fields_am654, .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII), .num_ports = 8, @@ -248,6 +277,8 @@ struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j721e = { static const struct phy_gmii_sel_soc_data phy_gmii_sel_cpsw9g_soc_j784s4 = { .use_of_data = true, + .features = BIT(PHY_GMII_SEL_RGMII_ID_MODE) | + BIT(PHY_GMII_SEL_FIXED_TX_DELAY), .regfields = phy_gmii_sel_fields_am654, .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) | BIT(PHY_INTERFACE_MODE_USXGMII), diff --git a/drivers/phy/ti/phy-omap-usb2.c b/drivers/phy/ti/phy-omap-usb2.c index c1a0ef979142..c444bb2530ca 100644 --- a/drivers/phy/ti/phy-omap-usb2.c +++ b/drivers/phy/ti/phy-omap-usb2.c @@ -363,6 +363,13 @@ static void omap_usb2_init_errata(struct omap_usb *phy) phy->flags |= OMAP_USB2_DISABLE_CHRG_DET; } +static void omap_usb2_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int omap_usb2_probe(struct platform_device *pdev) { struct omap_usb *phy; @@ -373,6 +380,7 @@ static int omap_usb2_probe(struct platform_device *pdev) struct device_node *control_node; struct platform_device *control_pdev; const struct usb_phy_data *phy_data; + int ret; phy_data = device_get_match_data(&pdev->dev); if (!phy_data) @@ -423,6 +431,11 @@ static int omap_usb2_probe(struct platform_device *pdev) return -EINVAL; } phy->control_dev = &control_pdev->dev; + + ret = devm_add_action_or_reset(&pdev->dev, omap_usb2_put_device, + phy->control_dev); + if (ret) + return ret; } else { if (of_property_read_u32_index(node, "syscon-phy-power", 1, diff --git a/drivers/phy/ti/phy-ti-pipe3.c b/drivers/phy/ti/phy-ti-pipe3.c index da2cbacb982c..ae764d6524c9 100644 --- a/drivers/phy/ti/phy-ti-pipe3.c +++ b/drivers/phy/ti/phy-ti-pipe3.c @@ -667,12 +667,20 @@ static int ti_pipe3_get_clk(struct ti_pipe3 *phy) return 0; } +static void ti_pipe3_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy) { struct device *dev = phy->dev; struct device_node *node = dev->of_node; struct device_node *control_node; struct platform_device *control_pdev; + int ret; phy->phy_power_syscon = syscon_regmap_lookup_by_phandle(node, "syscon-phy-power"); @@ -704,6 +712,11 @@ static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy) } phy->control_dev = &control_pdev->dev; + + ret = devm_add_action_or_reset(dev, ti_pipe3_put_device, + phy->control_dev); + if (ret) + return ret; } if (phy->mode == PIPE3_MODE_PCIE) { diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c index 69336bd778ee..13eb22b35aa8 100644 --- a/drivers/platform/x86/acer-wmi.c +++ b/drivers/platform/x86/acer-wmi.c @@ -129,6 +129,7 @@ enum acer_wmi_predator_v4_oc { enum acer_wmi_gaming_misc_setting { ACER_WMID_MISC_SETTING_OC_1 = 0x0005, ACER_WMID_MISC_SETTING_OC_2 = 0x0007, + /* Unreliable on some models */ ACER_WMID_MISC_SETTING_SUPPORTED_PROFILES = 0x000A, ACER_WMID_MISC_SETTING_PLATFORM_PROFILE = 0x000B, }; @@ -794,9 +795,6 @@ static bool platform_profile_support; */ static int last_non_turbo_profile = INT_MIN; -/* The most performant supported profile */ -static int acer_predator_v4_max_perf; - enum acer_predator_v4_thermal_profile { ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET = 0x00, ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED = 0x01, @@ -2014,7 +2012,7 @@ acer_predator_v4_platform_profile_set(struct device *dev, if (err) return err; - if (tp != acer_predator_v4_max_perf) + if (tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO) last_non_turbo_profile = tp; return 0; @@ -2023,55 +2021,14 @@ acer_predator_v4_platform_profile_set(struct device *dev, static int acer_predator_v4_platform_profile_probe(void *drvdata, unsigned long *choices) { - unsigned long supported_profiles; - int err; + set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); + set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices); + set_bit(PLATFORM_PROFILE_BALANCED, choices); + set_bit(PLATFORM_PROFILE_QUIET, choices); + set_bit(PLATFORM_PROFILE_LOW_POWER, choices); - err = WMID_gaming_get_misc_setting(ACER_WMID_MISC_SETTING_SUPPORTED_PROFILES, - (u8 *)&supported_profiles); - if (err) - return err; - - /* Iterate through supported profiles in order of increasing performance */ - if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_ECO, &supported_profiles)) { - set_bit(PLATFORM_PROFILE_LOW_POWER, choices); - acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO; - last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_ECO; - } - - if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET, &supported_profiles)) { - set_bit(PLATFORM_PROFILE_QUIET, choices); - acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET; - last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_QUIET; - } - - if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED, &supported_profiles)) { - set_bit(PLATFORM_PROFILE_BALANCED, choices); - acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED; - last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED; - } - - if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE, &supported_profiles)) { - set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices); - acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE; - - /* We only use this profile as a fallback option in case no prior - * profile is supported. - */ - if (last_non_turbo_profile < 0) - last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_PERFORMANCE; - } - - if (test_bit(ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO, &supported_profiles)) { - set_bit(PLATFORM_PROFILE_PERFORMANCE, choices); - acer_predator_v4_max_perf = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO; - - /* We need to handle the hypothetical case where only the turbo profile - * is supported. In this case the turbo toggle will essentially be a - * no-op. - */ - if (last_non_turbo_profile < 0) - last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO; - } + /* Set default non-turbo profile */ + last_non_turbo_profile = ACER_PREDATOR_V4_THERMAL_PROFILE_BALANCED; return 0; } @@ -2108,19 +2065,15 @@ static int acer_thermal_profile_change(void) if (cycle_gaming_thermal_profile) { platform_profile_cycle(); } else { - /* Do nothing if no suitable platform profiles where found */ - if (last_non_turbo_profile < 0) - return 0; - err = WMID_gaming_get_misc_setting( ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, ¤t_tp); if (err) return err; - if (current_tp == acer_predator_v4_max_perf) + if (current_tp == ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO) tp = last_non_turbo_profile; else - tp = acer_predator_v4_max_perf; + tp = ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO; err = WMID_gaming_set_misc_setting( ACER_WMID_MISC_SETTING_PLATFORM_PROFILE, tp); @@ -2128,7 +2081,7 @@ static int acer_thermal_profile_change(void) return err; /* Store last profile for toggle */ - if (current_tp != acer_predator_v4_max_perf) + if (current_tp != ACER_PREDATOR_V4_THERMAL_PROFILE_TURBO) last_non_turbo_profile = current_tp; platform_profile_notify(platform_profile_device); diff --git a/drivers/platform/x86/amd/hfi/hfi.c b/drivers/platform/x86/amd/hfi/hfi.c index 4f56149b3774..a465ac6f607e 100644 --- a/drivers/platform/x86/amd/hfi/hfi.c +++ b/drivers/platform/x86/amd/hfi/hfi.c @@ -385,12 +385,16 @@ static int amd_hfi_metadata_parser(struct platform_device *pdev, amd_hfi_data->pcct_entry = pcct_entry; pcct_ext = (struct acpi_pcct_ext_pcc_slave *)pcct_entry; - if (pcct_ext->length <= 0) - return -EINVAL; + if (pcct_ext->length <= 0) { + ret = -EINVAL; + goto out; + } amd_hfi_data->shmem = devm_kzalloc(amd_hfi_data->dev, pcct_ext->length, GFP_KERNEL); - if (!amd_hfi_data->shmem) - return -ENOMEM; + if (!amd_hfi_data->shmem) { + ret = -ENOMEM; + goto out; + } pcc_chan->shmem_base_addr = pcct_ext->base_address; pcc_chan->shmem_size = pcct_ext->length; @@ -398,6 +402,8 @@ static int amd_hfi_metadata_parser(struct platform_device *pdev, /* parse the shared memory info from the PCCT table */ ret = amd_hfi_fill_metadata(amd_hfi_data); +out: + /* Don't leak any ACPI memory */ acpi_put_table(pcct_tbl); return ret; diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index 7ffc659b2794..18fb44139de2 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -248,6 +248,20 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Lafite Pro V 14M"), } }, + { + .ident = "TUXEDO InfinityBook Pro 14/15 AMD Gen10", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "XxHP4NAx"), + } + }, + { + .ident = "TUXEDO InfinityBook Pro 14/15 AMD Gen10", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "XxKK4NAx_XxSP4NAx"), + } + }, {} }; diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index f84c3d03c1de..3a488cf9ca06 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -147,7 +147,12 @@ static struct quirk_entry quirk_asus_ignore_fan = { }; static struct quirk_entry quirk_asus_zenbook_duo_kbd = { - .ignore_key_wlan = true, + .key_wlan_event = ASUS_WMI_KEY_IGNORE, +}; + +static struct quirk_entry quirk_asus_z13 = { + .key_wlan_event = ASUS_WMI_KEY_ARMOURY, + .tablet_switch_mode = asus_wmi_kbd_dock_devid, }; static int dmi_matched(const struct dmi_system_id *dmi) @@ -539,6 +544,15 @@ static const struct dmi_system_id asus_quirks[] = { }, .driver_data = &quirk_asus_zenbook_duo_kbd, }, + { + .callback = dmi_matched, + .ident = "ASUS ROG Z13", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_PRODUCT_NAME, "ROG Flow Z13"), + }, + .driver_data = &quirk_asus_z13, + }, {}, }; @@ -618,6 +632,7 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, 0x93, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + CRT + TV + DVI */ { KE_KEY, 0x95, { KEY_MEDIA } }, { KE_KEY, 0x99, { KEY_PHONE } }, /* Conflicts with fan mode switch */ + { KE_KEY, 0X9D, { KEY_FN_F } }, { KE_KEY, 0xA0, { KEY_SWITCHVIDEOMODE } }, /* SDSP HDMI only */ { KE_KEY, 0xA1, { KEY_SWITCHVIDEOMODE } }, /* SDSP LCD + HDMI */ { KE_KEY, 0xA2, { KEY_SWITCHVIDEOMODE } }, /* SDSP CRT + HDMI */ @@ -632,10 +647,13 @@ static const struct key_entry asus_nb_wmi_keymap[] = { { KE_IGNORE, 0xC0, }, /* External display connect/disconnect notification */ { KE_KEY, 0xC4, { KEY_KBDILLUMUP } }, { KE_KEY, 0xC5, { KEY_KBDILLUMDOWN } }, + { KE_KEY, 0xCA, { KEY_F13 } }, /* Noise cancelling on Expertbook B9 */ + { KE_KEY, 0xCB, { KEY_F14 } }, /* Fn+noise-cancel */ { KE_IGNORE, 0xC6, }, /* Ambient Light Sensor notification */ { KE_IGNORE, 0xCF, }, /* AC mode */ { KE_KEY, 0xFA, { KEY_PROG2 } }, /* Lid flip action */ { KE_KEY, 0xBD, { KEY_PROG2 } }, /* Lid flip action on ROG xflow laptops */ + { KE_KEY, ASUS_WMI_KEY_ARMOURY, { KEY_PROG3 } }, { KE_END, 0}, }; @@ -655,11 +673,9 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code, if (atkbd_reports_vol_keys) *code = ASUS_WMI_KEY_IGNORE; break; - case 0x5D: /* Wireless console Toggle */ - case 0x5E: /* Wireless console Enable */ - case 0x5F: /* Wireless console Disable */ - if (quirks->ignore_key_wlan) - *code = ASUS_WMI_KEY_IGNORE; + case 0x5F: /* Wireless console Disable / Special Key */ + if (quirks->key_wlan_event) + *code = quirks->key_wlan_event; break; } } diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index f7191fdded14..e72a2b5d158e 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -5088,16 +5088,22 @@ static int asus_wmi_probe(struct platform_device *pdev) asus_s2idle_check_register(); - return asus_wmi_add(pdev); + ret = asus_wmi_add(pdev); + if (ret) + asus_s2idle_check_unregister(); + + return ret; } static bool used; +static DEFINE_MUTEX(register_mutex); int __init_or_module asus_wmi_register_driver(struct asus_wmi_driver *driver) { struct platform_driver *platform_driver; struct platform_device *platform_device; + guard(mutex)(®ister_mutex); if (used) return -EBUSY; @@ -5120,6 +5126,7 @@ EXPORT_SYMBOL_GPL(asus_wmi_register_driver); void asus_wmi_unregister_driver(struct asus_wmi_driver *driver) { + guard(mutex)(®ister_mutex); asus_s2idle_check_unregister(); platform_device_unregister(driver->platform_device); diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h index 018dfde4025e..5cd4392b964e 100644 --- a/drivers/platform/x86/asus-wmi.h +++ b/drivers/platform/x86/asus-wmi.h @@ -18,6 +18,7 @@ #include <linux/i8042.h> #define ASUS_WMI_KEY_IGNORE (-1) +#define ASUS_WMI_KEY_ARMOURY 0xffff01 #define ASUS_WMI_BRN_DOWN 0x2e #define ASUS_WMI_BRN_UP 0x2f @@ -40,7 +41,7 @@ struct quirk_entry { bool wmi_force_als_set; bool wmi_ignore_fan; bool filter_i8042_e1_extended_codes; - bool ignore_key_wlan; + int key_wlan_event; enum asus_wmi_tablet_switch_mode tablet_switch_mode; int wapf; /* diff --git a/drivers/platform/x86/hp/hp-wmi.c b/drivers/platform/x86/hp/hp-wmi.c index 60c8ac8d902c..8b3533d6ba09 100644 --- a/drivers/platform/x86/hp/hp-wmi.c +++ b/drivers/platform/x86/hp/hp-wmi.c @@ -122,6 +122,7 @@ enum hp_wmi_event_ids { HPWMI_BATTERY_CHARGE_PERIOD = 0x10, HPWMI_SANITIZATION_MODE = 0x17, HPWMI_CAMERA_TOGGLE = 0x1A, + HPWMI_FN_P_HOTKEY = 0x1B, HPWMI_OMEN_KEY = 0x1D, HPWMI_SMART_EXPERIENCE_APP = 0x21, }; @@ -981,6 +982,9 @@ static void hp_wmi_notify(union acpi_object *obj, void *context) key_code, 1, true)) pr_info("Unknown key code - 0x%x\n", key_code); break; + case HPWMI_FN_P_HOTKEY: + platform_profile_cycle(); + break; case HPWMI_OMEN_KEY: if (event_data) /* Only should be true for HP Omen */ key_code = event_data; diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c index 540cd2fb0673..d040290e80ff 100644 --- a/drivers/platform/x86/intel/pmc/core.c +++ b/drivers/platform/x86/intel/pmc/core.c @@ -1625,6 +1625,7 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = { X86_MATCH_VFM(INTEL_RAPTORLAKE_P, &tgl_l_pmc_dev), X86_MATCH_VFM(INTEL_RAPTORLAKE, &adl_pmc_dev), X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_pmc_dev), + X86_MATCH_VFM(INTEL_BARTLETTLAKE, &adl_pmc_dev), X86_MATCH_VFM(INTEL_METEORLAKE_L, &mtl_pmc_dev), X86_MATCH_VFM(INTEL_ARROWLAKE, &arl_pmc_dev), X86_MATCH_VFM(INTEL_ARROWLAKE_H, &arl_h_pmc_dev), diff --git a/drivers/platform/x86/intel/tpmi_power_domains.c b/drivers/platform/x86/intel/tpmi_power_domains.c index 9d8247bb9cfa..8641353b2e06 100644 --- a/drivers/platform/x86/intel/tpmi_power_domains.c +++ b/drivers/platform/x86/intel/tpmi_power_domains.c @@ -178,7 +178,7 @@ static int tpmi_get_logical_id(unsigned int cpu, struct tpmi_cpu_info *info) info->punit_thread_id = FIELD_GET(LP_ID_MASK, data); info->punit_core_id = FIELD_GET(MODULE_ID_MASK, data); - info->pkg_id = topology_physical_package_id(cpu); + info->pkg_id = topology_logical_package_id(cpu); info->linux_cpu = cpu; return 0; diff --git a/drivers/power/supply/bq27xxx_battery.c b/drivers/power/supply/bq27xxx_battery.c index 93dcebbe1141..ad2d9ecf32a5 100644 --- a/drivers/power/supply/bq27xxx_battery.c +++ b/drivers/power/supply/bq27xxx_battery.c @@ -1919,8 +1919,8 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di) bool has_singe_flag = di->opts & BQ27XXX_O_ZERO; cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag); - if ((cache.flags & 0xff) == 0xff) - cache.flags = -1; /* read error */ + if (di->chip == BQ27000 && (cache.flags & 0xff) == 0xff) + cache.flags = -ENODEV; /* bq27000 hdq read error */ if (cache.flags >= 0) { cache.capacity = bq27xxx_battery_read_soc(di); diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index d39073dc4072..4e1286ce05c9 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -4557,8 +4557,7 @@ ptp_ocp_detach(struct ptp_ocp *bp) ptp_ocp_debugfs_remove_device(bp); ptp_ocp_detach_sysfs(bp); ptp_ocp_attr_group_del(bp); - if (timer_pending(&bp->watchdog)) - timer_delete_sync(&bp->watchdog); + timer_delete_sync(&bp->watchdog); if (bp->ts0) ptp_ocp_unregister_ext(bp->ts0); if (bp->ts1) diff --git a/drivers/regulator/sy7636a-regulator.c b/drivers/regulator/sy7636a-regulator.c index d1e7ba1fb3e1..27e3d939b7bb 100644 --- a/drivers/regulator/sy7636a-regulator.c +++ b/drivers/regulator/sy7636a-regulator.c @@ -83,9 +83,11 @@ static int sy7636a_regulator_probe(struct platform_device *pdev) if (!regmap) return -EPROBE_DEFER; - gdp = devm_gpiod_get(pdev->dev.parent, "epd-pwr-good", GPIOD_IN); + device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent); + + gdp = devm_gpiod_get(&pdev->dev, "epd-pwr-good", GPIOD_IN); if (IS_ERR(gdp)) { - dev_err(pdev->dev.parent, "Power good GPIO fault %ld\n", PTR_ERR(gdp)); + dev_err(&pdev->dev, "Power good GPIO fault %ld\n", PTR_ERR(gdp)); return PTR_ERR(gdp); } @@ -105,7 +107,6 @@ static int sy7636a_regulator_probe(struct platform_device *pdev) } config.dev = &pdev->dev; - config.dev->of_node = pdev->dev.parent->of_node; config.regmap = regmap; rdev = devm_regulator_register(&pdev->dev, &desc, &config); diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c index fba2e62027b7..4cfc928bcf2d 100644 --- a/drivers/scsi/lpfc/lpfc_nvmet.c +++ b/drivers/scsi/lpfc/lpfc_nvmet.c @@ -1243,7 +1243,7 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport, struct lpfc_nvmet_tgtport *tgtp; struct lpfc_async_xchg_ctx *ctxp = container_of(rsp, struct lpfc_async_xchg_ctx, hdlrctx.fcp_req); - struct rqb_dmabuf *nvmebuf = ctxp->rqb_buffer; + struct rqb_dmabuf *nvmebuf; struct lpfc_hba *phba = ctxp->phba; unsigned long iflag; @@ -1251,13 +1251,18 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport, lpfc_nvmeio_data(phba, "NVMET DEFERRCV: xri x%x sz %d CPU %02x\n", ctxp->oxid, ctxp->size, raw_smp_processor_id()); + spin_lock_irqsave(&ctxp->ctxlock, iflag); + nvmebuf = ctxp->rqb_buffer; if (!nvmebuf) { + spin_unlock_irqrestore(&ctxp->ctxlock, iflag); lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR, "6425 Defer rcv: no buffer oxid x%x: " "flg %x ste %x\n", ctxp->oxid, ctxp->flag, ctxp->state); return; } + ctxp->rqb_buffer = NULL; + spin_unlock_irqrestore(&ctxp->ctxlock, iflag); tgtp = phba->targetport->private; if (tgtp) @@ -1265,9 +1270,6 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport, /* Free the nvmebuf since a new buffer already replaced it */ nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf); - spin_lock_irqsave(&ctxp->ctxlock, iflag); - ctxp->rqb_buffer = NULL; - spin_unlock_irqrestore(&ctxp->ctxlock, iflag); } /** diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index b17796d5ee66..add13e306898 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -475,13 +475,21 @@ static blk_status_t sr_init_command(struct scsi_cmnd *SCpnt) static int sr_revalidate_disk(struct scsi_cd *cd) { + struct request_queue *q = cd->device->request_queue; struct scsi_sense_hdr sshdr; + struct queue_limits lim; + int sector_size; /* if the unit is not ready, nothing more to do */ if (scsi_test_unit_ready(cd->device, SR_TIMEOUT, MAX_RETRIES, &sshdr)) return 0; sr_cd_check(&cd->cdi); - return get_sectorsize(cd); + sector_size = get_sectorsize(cd); + + lim = queue_limits_start_update(q); + lim.logical_block_size = sector_size; + lim.features |= BLK_FEAT_ROTATIONAL; + return queue_limits_commit_update_frozen(q, &lim); } static int sr_block_open(struct gendisk *disk, blk_mode_t mode) @@ -721,10 +729,8 @@ fail: static int get_sectorsize(struct scsi_cd *cd) { - struct request_queue *q = cd->device->request_queue; static const u8 cmd[10] = { READ_CAPACITY }; unsigned char buffer[8] = { }; - struct queue_limits lim; int err; int sector_size; struct scsi_failure failure_defs[] = { @@ -795,9 +801,7 @@ static int get_sectorsize(struct scsi_cd *cd) set_capacity(cd->disk, cd->capacity); } - lim = queue_limits_start_update(q); - lim.logical_block_size = sector_size; - return queue_limits_commit_update_frozen(q, &lim); + return sector_size; } static int get_capabilities(struct scsi_cd *cd) diff --git a/drivers/soc/qcom/mdt_loader.c b/drivers/soc/qcom/mdt_loader.c index 0ca268bdf1f8..5710ac0c07a8 100644 --- a/drivers/soc/qcom/mdt_loader.c +++ b/drivers/soc/qcom/mdt_loader.c @@ -39,12 +39,14 @@ static bool mdt_header_valid(const struct firmware *fw) if (phend > fw->size) return false; - if (ehdr->e_shentsize != sizeof(struct elf32_shdr)) - return false; + if (ehdr->e_shentsize || ehdr->e_shnum) { + if (ehdr->e_shentsize != sizeof(struct elf32_shdr)) + return false; - shend = size_add(size_mul(sizeof(struct elf32_shdr), ehdr->e_shnum), ehdr->e_shoff); - if (shend > fw->size) - return false; + shend = size_add(size_mul(sizeof(struct elf32_shdr), ehdr->e_shnum), ehdr->e_shoff); + if (shend > fw->size) + return false; + } return true; } diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c index 177f9a33f3a2..9bf823348cd3 100644 --- a/drivers/spi/spi-cadence-quadspi.c +++ b/drivers/spi/spi-cadence-quadspi.c @@ -108,6 +108,8 @@ struct cqspi_st { bool is_jh7110; /* Flag for StarFive JH7110 SoC */ bool disable_stig_mode; + refcount_t refcount; + refcount_t inflight_ops; const struct cqspi_driver_platdata *ddata; }; @@ -735,6 +737,9 @@ static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata, u8 *rxbuf_end = rxbuf + n_rx; int ret = 0; + if (!refcount_read(&cqspi->refcount)) + return -ENODEV; + writel(from_addr, reg_base + CQSPI_REG_INDIRECTRDSTARTADDR); writel(remaining, reg_base + CQSPI_REG_INDIRECTRDBYTES); @@ -1071,6 +1076,9 @@ static int cqspi_indirect_write_execute(struct cqspi_flash_pdata *f_pdata, unsigned int write_bytes; int ret; + if (!refcount_read(&cqspi->refcount)) + return -ENODEV; + writel(to_addr, reg_base + CQSPI_REG_INDIRECTWRSTARTADDR); writel(remaining, reg_base + CQSPI_REG_INDIRECTWRBYTES); @@ -1461,12 +1469,26 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op) struct cqspi_st *cqspi = spi_controller_get_devdata(mem->spi->controller); struct device *dev = &cqspi->pdev->dev; + if (refcount_read(&cqspi->inflight_ops) == 0) + return -ENODEV; + ret = pm_runtime_resume_and_get(dev); if (ret) { dev_err(&mem->spi->dev, "resume failed with %d\n", ret); return ret; } + if (!refcount_read(&cqspi->refcount)) + return -EBUSY; + + refcount_inc(&cqspi->inflight_ops); + + if (!refcount_read(&cqspi->refcount)) { + if (refcount_read(&cqspi->inflight_ops)) + refcount_dec(&cqspi->inflight_ops); + return -EBUSY; + } + ret = cqspi_mem_process(mem, op); pm_runtime_put_autosuspend(dev); @@ -1474,6 +1496,9 @@ static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op) if (ret) dev_err(&mem->spi->dev, "operation failed with %d\n", ret); + if (refcount_read(&cqspi->inflight_ops) > 1) + refcount_dec(&cqspi->inflight_ops); + return ret; } @@ -1925,6 +1950,9 @@ static int cqspi_probe(struct platform_device *pdev) } } + refcount_set(&cqspi->refcount, 1); + refcount_set(&cqspi->inflight_ops, 1); + ret = devm_request_irq(dev, irq, cqspi_irq_handler, 0, pdev->name, cqspi); if (ret) { @@ -1987,6 +2015,11 @@ static void cqspi_remove(struct platform_device *pdev) { struct cqspi_st *cqspi = platform_get_drvdata(pdev); + refcount_set(&cqspi->refcount, 0); + + if (!refcount_dec_and_test(&cqspi->inflight_ops)) + cqspi_wait_idle(cqspi); + spi_unregister_controller(cqspi->host); cqspi_controller_enable(cqspi, 0); diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c index 313e444a34f3..431439d4cdda 100644 --- a/drivers/spi/spi-fsl-lpspi.c +++ b/drivers/spi/spi-fsl-lpspi.c @@ -3,8 +3,9 @@ // Freescale i.MX7ULP LPSPI driver // // Copyright 2016 Freescale Semiconductor, Inc. -// Copyright 2018 NXP Semiconductors +// Copyright 2018, 2023, 2025 NXP +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/completion.h> #include <linux/delay.h> @@ -70,7 +71,7 @@ #define DER_TDDE BIT(0) #define CFGR1_PCSCFG BIT(27) #define CFGR1_PINCFG (BIT(24)|BIT(25)) -#define CFGR1_PCSPOL BIT(8) +#define CFGR1_PCSPOL_MASK GENMASK(11, 8) #define CFGR1_NOSTALL BIT(3) #define CFGR1_HOST BIT(0) #define FSR_TXCOUNT (0xFF) @@ -82,8 +83,11 @@ #define TCR_RXMSK BIT(19) #define TCR_TXMSK BIT(18) +#define SR_CLEAR_MASK GENMASK(13, 8) + struct fsl_lpspi_devtype_data { - u8 prescale_max; + u8 prescale_max : 3; /* 0 == no limit */ + bool query_hw_for_num_cs : 1; }; struct lpspi_config { @@ -129,20 +133,26 @@ struct fsl_lpspi_data { }; /* - * ERR051608 fixed or not: - * https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf + * Devices with ERR051608 have a max TCR_PRESCALE value of 1, otherwise there is + * no prescale limit: https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf */ -static struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = { +static const struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = { .prescale_max = 1, + .query_hw_for_num_cs = true, +}; + +static const struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = { + /* All defaults */ }; -static struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = { - .prescale_max = 7, +static const struct fsl_lpspi_devtype_data s32g_lpspi_devtype_data = { + .query_hw_for_num_cs = true, }; static const struct of_device_id fsl_lpspi_dt_ids[] = { { .compatible = "fsl,imx7ulp-spi", .data = &imx7ulp_lpspi_devtype_data,}, { .compatible = "fsl,imx93-spi", .data = &imx93_lpspi_devtype_data,}, + { .compatible = "nxp,s32g2-lpspi", .data = &s32g_lpspi_devtype_data,}, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, fsl_lpspi_dt_ids); @@ -321,7 +331,7 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi) int scldiv; perclk_rate = clk_get_rate(fsl_lpspi->clk_per); - prescale_max = fsl_lpspi->devtype_data->prescale_max; + prescale_max = fsl_lpspi->devtype_data->prescale_max ?: 7; if (!config.speed_hz) { dev_err(fsl_lpspi->dev, @@ -423,7 +433,9 @@ static int fsl_lpspi_config(struct fsl_lpspi_data *fsl_lpspi) else temp = CFGR1_PINCFG; if (fsl_lpspi->config.mode & SPI_CS_HIGH) - temp |= CFGR1_PCSPOL; + temp |= FIELD_PREP(CFGR1_PCSPOL_MASK, + BIT(fsl_lpspi->config.chip_select)); + writel(temp, fsl_lpspi->base + IMX7ULP_CFGR1); temp = readl(fsl_lpspi->base + IMX7ULP_CR); @@ -532,14 +544,13 @@ static int fsl_lpspi_reset(struct fsl_lpspi_data *fsl_lpspi) fsl_lpspi_intctrl(fsl_lpspi, 0); } - /* W1C for all flags in SR */ - temp = 0x3F << 8; - writel(temp, fsl_lpspi->base + IMX7ULP_SR); - /* Clear FIFO and disable module */ temp = CR_RRF | CR_RTF; writel(temp, fsl_lpspi->base + IMX7ULP_CR); + /* W1C for all flags in SR */ + writel(SR_CLEAR_MASK, fsl_lpspi->base + IMX7ULP_SR); + return 0; } @@ -730,12 +741,10 @@ static int fsl_lpspi_pio_transfer(struct spi_controller *controller, fsl_lpspi_write_tx_fifo(fsl_lpspi); ret = fsl_lpspi_wait_for_completion(controller); - if (ret) - return ret; fsl_lpspi_reset(fsl_lpspi); - return 0; + return ret; } static int fsl_lpspi_transfer_one(struct spi_controller *controller, @@ -785,7 +794,7 @@ static irqreturn_t fsl_lpspi_isr(int irq, void *dev_id) if (temp_SR & SR_MBF || readl(fsl_lpspi->base + IMX7ULP_FSR) & FSR_TXCOUNT) { writel(SR_FCF, fsl_lpspi->base + IMX7ULP_SR); - fsl_lpspi_intctrl(fsl_lpspi, IER_FCIE); + fsl_lpspi_intctrl(fsl_lpspi, IER_FCIE | (temp_IER & IER_TDIE)); return IRQ_HANDLED; } @@ -930,7 +939,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev) fsl_lpspi->rxfifosize = 1 << ((temp >> 8) & 0x0f); if (of_property_read_u32((&pdev->dev)->of_node, "num-cs", &num_cs)) { - if (of_device_is_compatible(pdev->dev.of_node, "fsl,imx93-spi")) + if (devtype_data->query_hw_for_num_cs) num_cs = ((temp >> 16) & 0xf); else num_cs = 1; diff --git a/drivers/spi/spi-microchip-core-qspi.c b/drivers/spi/spi-microchip-core-qspi.c index d13a9b755c7f..8dc98b17f77b 100644 --- a/drivers/spi/spi-microchip-core-qspi.c +++ b/drivers/spi/spi-microchip-core-qspi.c @@ -531,10 +531,6 @@ error: static bool mchp_coreqspi_supports_op(struct spi_mem *mem, const struct spi_mem_op *op) { - struct mchp_coreqspi *qspi = spi_controller_get_devdata(mem->spi->controller); - unsigned long clk_hz; - u32 baud_rate_val; - if (!spi_mem_default_supports_op(mem, op)) return false; @@ -557,14 +553,6 @@ static bool mchp_coreqspi_supports_op(struct spi_mem *mem, const struct spi_mem_ return false; } - clk_hz = clk_get_rate(qspi->clk); - if (!clk_hz) - return false; - - baud_rate_val = DIV_ROUND_UP(clk_hz, 2 * op->max_freq); - if (baud_rate_val > MAX_DIVIDER || baud_rate_val < MIN_DIVIDER) - return false; - return true; } diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c index 0ceaad7dba3c..780abb967822 100644 --- a/drivers/spi/spi-qpic-snand.c +++ b/drivers/spi/spi-qpic-snand.c @@ -1615,11 +1615,13 @@ static int qcom_spi_probe(struct platform_device *pdev) ret = spi_register_controller(ctlr); if (ret) { dev_err(&pdev->dev, "spi_register_controller failed.\n"); - goto err_spi_init; + goto err_register_controller; } return 0; +err_register_controller: + nand_ecc_unregister_on_host_hw_engine(&snandc->qspi->ecc_eng); err_spi_init: qcom_nandc_unalloc(snandc); err_snand_alloc: @@ -1641,7 +1643,7 @@ static void qcom_spi_remove(struct platform_device *pdev) struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); spi_unregister_controller(ctlr); - + nand_ecc_unregister_on_host_hw_engine(&snandc->qspi->ecc_eng); qcom_nandc_unalloc(snandc); clk_disable_unprepare(snandc->aon_clk); diff --git a/drivers/tee/optee/ffa_abi.c b/drivers/tee/optee/ffa_abi.c index f9ef7d94cebd..a963eed70c1d 100644 --- a/drivers/tee/optee/ffa_abi.c +++ b/drivers/tee/optee/ffa_abi.c @@ -657,7 +657,7 @@ static int optee_ffa_do_call_with_arg(struct tee_context *ctx, * with a matching configuration. */ -static bool optee_ffa_api_is_compatbile(struct ffa_device *ffa_dev, +static bool optee_ffa_api_is_compatible(struct ffa_device *ffa_dev, const struct ffa_ops *ops) { const struct ffa_msg_ops *msg_ops = ops->msg_ops; @@ -908,7 +908,7 @@ static int optee_ffa_probe(struct ffa_device *ffa_dev) ffa_ops = ffa_dev->ops; notif_ops = ffa_ops->notifier_ops; - if (!optee_ffa_api_is_compatbile(ffa_dev, ffa_ops)) + if (!optee_ffa_api_is_compatible(ffa_dev, ffa_ops)) return -EINVAL; if (!optee_ffa_exchange_caps(ffa_dev, ffa_ops, &sec_caps, diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c index daf6e5cfd59a..2a7d253d9c55 100644 --- a/drivers/tee/tee_shm.c +++ b/drivers/tee/tee_shm.c @@ -230,7 +230,7 @@ int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align, pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL); if (!pages) { rc = -ENOMEM; - goto err; + goto err_pages; } for (i = 0; i < nr_pages; i++) @@ -243,11 +243,13 @@ int tee_dyn_shm_alloc_helper(struct tee_shm *shm, size_t size, size_t align, rc = shm_register(shm->ctx, shm, pages, nr_pages, (unsigned long)shm->kaddr); if (rc) - goto err; + goto err_kfree; } return 0; -err: +err_kfree: + kfree(pages); +err_pages: free_pages_exact(shm->kaddr, shm->size); shm->kaddr = NULL; return rc; @@ -560,9 +562,13 @@ EXPORT_SYMBOL_GPL(tee_shm_get_from_id); */ void tee_shm_put(struct tee_shm *shm) { - struct tee_device *teedev = shm->ctx->teedev; + struct tee_device *teedev; bool do_release = false; + if (!shm || !shm->ctx || !shm->ctx->teedev) + return; + + teedev = shm->ctx->teedev; mutex_lock(&teedev->mutex); if (refcount_dec_and_test(&shm->refcount)) { /* diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index cd1f657f782d..13c663a154c4 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -543,10 +543,10 @@ static ssize_t hvc_write(struct tty_struct *tty, const u8 *buf, size_t count) } /* - * Racy, but harmless, kick thread if there is still pending data. + * Kick thread to flush if there's still pending data + * or to wakeup the write queue. */ - if (hp->n_outbuf) - hvc_kick(); + hvc_kick(); return written; } diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 3f38fba8f6ea..a668e0bb26b3 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1177,17 +1177,6 @@ static int sc16is7xx_startup(struct uart_port *port) sc16is7xx_port_write(port, SC16IS7XX_FCR_REG, SC16IS7XX_FCR_FIFO_BIT); - /* Enable EFR */ - sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, - SC16IS7XX_LCR_CONF_MODE_B); - - regcache_cache_bypass(one->regmap, true); - - /* Enable write access to enhanced features and internal clock div */ - sc16is7xx_port_update(port, SC16IS7XX_EFR_REG, - SC16IS7XX_EFR_ENABLE_BIT, - SC16IS7XX_EFR_ENABLE_BIT); - /* Enable TCR/TLR */ sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_TCRTLR_BIT, @@ -1199,7 +1188,8 @@ static int sc16is7xx_startup(struct uart_port *port) SC16IS7XX_TCR_RX_RESUME(24) | SC16IS7XX_TCR_RX_HALT(48)); - regcache_cache_bypass(one->regmap, false); + /* Disable TCR/TLR access */ + sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_TCRTLR_BIT, 0); /* Now, initialize the UART */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_WORD_LEN_8); diff --git a/drivers/tty/serial/xilinx_uartps.c b/drivers/tty/serial/xilinx_uartps.c index fe457bf1e15b..a66b44d21fba 100644 --- a/drivers/tty/serial/xilinx_uartps.c +++ b/drivers/tty/serial/xilinx_uartps.c @@ -33,7 +33,6 @@ #define CDNS_UART_MINOR 0 /* works best with devtmpfs */ #define CDNS_UART_NR_PORTS 16 #define CDNS_UART_FIFO_SIZE 64 /* FIFO size */ -#define CDNS_UART_REGISTER_SPACE 0x1000 #define TX_TIMEOUT 500000 /* Rx Trigger level */ @@ -1098,15 +1097,15 @@ static int cdns_uart_verify_port(struct uart_port *port, */ static int cdns_uart_request_port(struct uart_port *port) { - if (!request_mem_region(port->mapbase, CDNS_UART_REGISTER_SPACE, + if (!request_mem_region(port->mapbase, port->mapsize, CDNS_UART_NAME)) { return -ENOMEM; } - port->membase = ioremap(port->mapbase, CDNS_UART_REGISTER_SPACE); + port->membase = ioremap(port->mapbase, port->mapsize); if (!port->membase) { dev_err(port->dev, "Unable to map registers\n"); - release_mem_region(port->mapbase, CDNS_UART_REGISTER_SPACE); + release_mem_region(port->mapbase, port->mapsize); return -ENOMEM; } return 0; @@ -1121,7 +1120,7 @@ static int cdns_uart_request_port(struct uart_port *port) */ static void cdns_uart_release_port(struct uart_port *port) { - release_mem_region(port->mapbase, CDNS_UART_REGISTER_SPACE); + release_mem_region(port->mapbase, port->mapsize); iounmap(port->membase); port->membase = NULL; } @@ -1780,6 +1779,7 @@ static int cdns_uart_probe(struct platform_device *pdev) * and triggers invocation of the config_port() entry point. */ port->mapbase = res->start; + port->mapsize = resource_size(res); port->irq = irq; port->dev = &pdev->dev; port->uartclk = clk_get_rate(cdns_uart_data->uartclk); diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index c3177034b779..f441958b0ef4 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -119,11 +119,11 @@ ssize_t usb_show_dynids(struct usb_dynids *dynids, char *buf) guard(mutex)(&usb_dynids_lock); list_for_each_entry(dynid, &dynids->list, node) if (dynid->id.bInterfaceClass != 0) - count += sysfs_emit_at(&buf[count], count, "%04x %04x %02x\n", + count += sysfs_emit_at(buf, count, "%04x %04x %02x\n", dynid->id.idVendor, dynid->id.idProduct, dynid->id.bInterfaceClass); else - count += sysfs_emit_at(&buf[count], count, "%04x %04x\n", + count += sysfs_emit_at(buf, count, "%04x %04x\n", dynid->id.idVendor, dynid->id.idProduct); return count; } diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index 0a800ba53816..de16b02d857e 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -1599,6 +1599,7 @@ static int f_midi2_create_card(struct f_midi2 *midi2) strscpy(fb->info.name, ump_fb_name(b), sizeof(fb->info.name)); } + snd_ump_update_group_attrs(ump); } for (i = 0; i < midi2->num_eps; i++) { @@ -1736,9 +1737,12 @@ static int f_midi2_create_usb_configs(struct f_midi2 *midi2, case USB_SPEED_HIGH: midi2_midi1_ep_out_desc.wMaxPacketSize = cpu_to_le16(512); midi2_midi1_ep_in_desc.wMaxPacketSize = cpu_to_le16(512); - for (i = 0; i < midi2->num_eps; i++) + for (i = 0; i < midi2->num_eps; i++) { midi2_midi2_ep_out_desc[i].wMaxPacketSize = cpu_to_le16(512); + midi2_midi2_ep_in_desc[i].wMaxPacketSize = + cpu_to_le16(512); + } fallthrough; case USB_SPEED_FULL: midi1_in_eps = midi2_midi1_ep_in_descs; @@ -1747,9 +1751,12 @@ static int f_midi2_create_usb_configs(struct f_midi2 *midi2, case USB_SPEED_SUPER: midi2_midi1_ep_out_desc.wMaxPacketSize = cpu_to_le16(1024); midi2_midi1_ep_in_desc.wMaxPacketSize = cpu_to_le16(1024); - for (i = 0; i < midi2->num_eps; i++) + for (i = 0; i < midi2->num_eps; i++) { midi2_midi2_ep_out_desc[i].wMaxPacketSize = cpu_to_le16(1024); + midi2_midi2_ep_in_desc[i].wMaxPacketSize = + cpu_to_le16(1024); + } midi1_in_eps = midi2_midi1_ep_in_ss_descs; midi1_out_eps = midi2_midi1_ep_out_ss_descs; break; diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index 21dbfb0b3bac..1cefca660773 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -765,8 +765,7 @@ static int dummy_dequeue(struct usb_ep *_ep, struct usb_request *_req) if (!dum->driver) return -ESHUTDOWN; - local_irq_save(flags); - spin_lock(&dum->lock); + spin_lock_irqsave(&dum->lock, flags); list_for_each_entry(iter, &ep->queue, queue) { if (&iter->req != _req) continue; @@ -776,15 +775,16 @@ static int dummy_dequeue(struct usb_ep *_ep, struct usb_request *_req) retval = 0; break; } - spin_unlock(&dum->lock); if (retval == 0) { dev_dbg(udc_dev(dum), "dequeued req %p from %s, len %d buf %p\n", req, _ep->name, _req->length, _req->buf); + spin_unlock(&dum->lock); usb_gadget_giveback_request(_ep, _req); + spin_lock(&dum->lock); } - local_irq_restore(flags); + spin_unlock_irqrestore(&dum->lock, flags); return retval; } diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index 06a2edb9e86e..63edf2d8f245 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -101,13 +101,34 @@ static u32 xhci_dbc_populate_strings(struct dbc_str_descs *strings) return string_length; } +static void xhci_dbc_init_ep_contexts(struct xhci_dbc *dbc) +{ + struct xhci_ep_ctx *ep_ctx; + unsigned int max_burst; + dma_addr_t deq; + + max_burst = DBC_CTRL_MAXBURST(readl(&dbc->regs->control)); + + /* Populate bulk out endpoint context: */ + ep_ctx = dbc_bulkout_ctx(dbc); + deq = dbc_bulkout_enq(dbc); + ep_ctx->ep_info = 0; + ep_ctx->ep_info2 = dbc_epctx_info2(BULK_OUT_EP, 1024, max_burst); + ep_ctx->deq = cpu_to_le64(deq | dbc->ring_out->cycle_state); + + /* Populate bulk in endpoint context: */ + ep_ctx = dbc_bulkin_ctx(dbc); + deq = dbc_bulkin_enq(dbc); + ep_ctx->ep_info = 0; + ep_ctx->ep_info2 = dbc_epctx_info2(BULK_IN_EP, 1024, max_burst); + ep_ctx->deq = cpu_to_le64(deq | dbc->ring_in->cycle_state); +} + static void xhci_dbc_init_contexts(struct xhci_dbc *dbc, u32 string_length) { struct dbc_info_context *info; - struct xhci_ep_ctx *ep_ctx; u32 dev_info; - dma_addr_t deq, dma; - unsigned int max_burst; + dma_addr_t dma; if (!dbc) return; @@ -121,20 +142,8 @@ static void xhci_dbc_init_contexts(struct xhci_dbc *dbc, u32 string_length) info->serial = cpu_to_le64(dma + DBC_MAX_STRING_LENGTH * 3); info->length = cpu_to_le32(string_length); - /* Populate bulk out endpoint context: */ - ep_ctx = dbc_bulkout_ctx(dbc); - max_burst = DBC_CTRL_MAXBURST(readl(&dbc->regs->control)); - deq = dbc_bulkout_enq(dbc); - ep_ctx->ep_info = 0; - ep_ctx->ep_info2 = dbc_epctx_info2(BULK_OUT_EP, 1024, max_burst); - ep_ctx->deq = cpu_to_le64(deq | dbc->ring_out->cycle_state); - - /* Populate bulk in endpoint context: */ - ep_ctx = dbc_bulkin_ctx(dbc); - deq = dbc_bulkin_enq(dbc); - ep_ctx->ep_info = 0; - ep_ctx->ep_info2 = dbc_epctx_info2(BULK_IN_EP, 1024, max_burst); - ep_ctx->deq = cpu_to_le64(deq | dbc->ring_in->cycle_state); + /* Populate bulk in and out endpoint contexts: */ + xhci_dbc_init_ep_contexts(dbc); /* Set DbC context and info registers: */ lo_hi_writeq(dbc->ctx->dma, &dbc->regs->dccp); @@ -436,6 +445,42 @@ dbc_alloc_ctx(struct device *dev, gfp_t flags) return ctx; } +static void xhci_dbc_ring_init(struct xhci_ring *ring) +{ + struct xhci_segment *seg = ring->first_seg; + + /* clear all trbs on ring in case of old ring */ + memset(seg->trbs, 0, TRB_SEGMENT_SIZE); + + /* Only event ring does not use link TRB */ + if (ring->type != TYPE_EVENT) { + union xhci_trb *trb = &seg->trbs[TRBS_PER_SEGMENT - 1]; + + trb->link.segment_ptr = cpu_to_le64(ring->first_seg->dma); + trb->link.control = cpu_to_le32(LINK_TOGGLE | TRB_TYPE(TRB_LINK)); + } + xhci_initialize_ring_info(ring); +} + +static int xhci_dbc_reinit_ep_rings(struct xhci_dbc *dbc) +{ + struct xhci_ring *in_ring = dbc->eps[BULK_IN].ring; + struct xhci_ring *out_ring = dbc->eps[BULK_OUT].ring; + + if (!in_ring || !out_ring || !dbc->ctx) { + dev_warn(dbc->dev, "Can't re-init unallocated endpoints\n"); + return -ENODEV; + } + + xhci_dbc_ring_init(in_ring); + xhci_dbc_ring_init(out_ring); + + /* set ep context enqueue, dequeue, and cycle to initial values */ + xhci_dbc_init_ep_contexts(dbc); + + return 0; +} + static struct xhci_ring * xhci_dbc_ring_alloc(struct device *dev, enum xhci_ring_type type, gfp_t flags) { @@ -464,15 +509,10 @@ xhci_dbc_ring_alloc(struct device *dev, enum xhci_ring_type type, gfp_t flags) seg->dma = dma; - /* Only event ring does not use link TRB */ - if (type != TYPE_EVENT) { - union xhci_trb *trb = &seg->trbs[TRBS_PER_SEGMENT - 1]; - - trb->link.segment_ptr = cpu_to_le64(dma); - trb->link.control = cpu_to_le32(LINK_TOGGLE | TRB_TYPE(TRB_LINK)); - } INIT_LIST_HEAD(&ring->td_list); - xhci_initialize_ring_info(ring); + + xhci_dbc_ring_init(ring); + return ring; dma_fail: kfree(seg); @@ -864,7 +904,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) dev_info(dbc->dev, "DbC cable unplugged\n"); dbc->state = DS_ENABLED; xhci_dbc_flush_requests(dbc); - + xhci_dbc_reinit_ep_rings(dbc); return EVT_DISC; } @@ -874,7 +914,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) writel(portsc, &dbc->regs->portsc); dbc->state = DS_ENABLED; xhci_dbc_flush_requests(dbc); - + xhci_dbc_reinit_ep_rings(dbc); return EVT_DISC; } diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 81eaad87a3d9..c4a6544aa107 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -962,7 +962,7 @@ static void xhci_free_virt_devices_depth_first(struct xhci_hcd *xhci, int slot_i out: /* we are now at a leaf device */ xhci_debugfs_remove_slot(xhci, slot_id); - xhci_free_virt_device(xhci, vdev, slot_id); + xhci_free_virt_device(xhci, xhci->devs[slot_id], slot_id); } int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e5cd33093423..fc869b7f803f 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1322,7 +1322,18 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1033, 0xff), /* Telit LE910C1-EUX (ECM) */ .driver_info = NCTRL(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1034, 0xff), /* Telit LE910C4-WWX (rmnet) */ + .driver_info = RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1035, 0xff) }, /* Telit LE910C4-WWX (ECM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1036, 0xff) }, /* Telit LE910C4-WWX */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1037, 0xff), /* Telit LE910C4-WWX (rmnet) */ + .driver_info = NCTRL(0) | NCTRL(1) | RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1038, 0xff), /* Telit LE910C4-WWX (rmnet) */ + .driver_info = NCTRL(0) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103b, 0xff), /* Telit LE910C4-WWX */ + .driver_info = NCTRL(0) | NCTRL(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103c, 0xff), /* Telit LE910C4-WWX */ + .driver_info = NCTRL(0) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0), .driver_info = RSVD(0) | RSVD(1) | NCTRL(2) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG1), @@ -1369,6 +1380,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990A (PCIe) */ .driver_info = RSVD(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1077, 0xff), /* Telit FN990A (rmnet + audio) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1078, 0xff), /* Telit FN990A (MBIM + audio) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1079, 0xff), /* Telit FN990A (RNDIS + audio) */ + .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff), /* Telit FE990A (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff), /* Telit FE990A (MBIM) */ diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 1f6fdfaa34bf..b2a568a5bc9b 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2426,17 +2426,21 @@ static void tcpm_handle_vdm_request(struct tcpm_port *port, case ADEV_NONE: break; case ADEV_NOTIFY_USB_AND_QUEUE_VDM: - WARN_ON(typec_altmode_notify(adev, TYPEC_STATE_USB, NULL)); - typec_altmode_vdm(adev, p[0], &p[1], cnt); + if (rx_sop_type == TCPC_TX_SOP_PRIME) { + typec_cable_altmode_vdm(adev, TYPEC_PLUG_SOP_P, p[0], &p[1], cnt); + } else { + WARN_ON(typec_altmode_notify(adev, TYPEC_STATE_USB, NULL)); + typec_altmode_vdm(adev, p[0], &p[1], cnt); + } break; case ADEV_QUEUE_VDM: - if (response_tx_sop_type == TCPC_TX_SOP_PRIME) + if (rx_sop_type == TCPC_TX_SOP_PRIME) typec_cable_altmode_vdm(adev, TYPEC_PLUG_SOP_P, p[0], &p[1], cnt); else typec_altmode_vdm(adev, p[0], &p[1], cnt); break; case ADEV_QUEUE_VDM_SEND_EXIT_MODE_ON_FAIL: - if (response_tx_sop_type == TCPC_TX_SOP_PRIME) { + if (rx_sop_type == TCPC_TX_SOP_PRIME) { if (typec_cable_altmode_vdm(adev, TYPEC_PLUG_SOP_P, p[0], &p[1], cnt)) { int svdm_version = typec_get_cable_svdm_version( diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 9bf282d2453c..499a9edf0ca3 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1795,7 +1795,14 @@ static int reclaim_bgs_cmp(void *unused, const struct list_head *a, bg1 = list_entry(a, struct btrfs_block_group, bg_list); bg2 = list_entry(b, struct btrfs_block_group, bg_list); - return bg1->used > bg2->used; + /* + * Some other task may be updating the ->used field concurrently, but it + * is not serious if we get a stale value or load/store tearing issues, + * as sorting the list of block groups to reclaim is not critical and an + * occasional imperfect order is ok. So silence KCSAN and avoid the + * overhead of locking or any other synchronization. + */ + return data_race(bg1->used > bg2->used); } static inline bool btrfs_should_reclaim(const struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 0f8d8e275143..c0c1ddd46b67 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1843,7 +1843,6 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans, int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev) { - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_delayed_node *delayed_node; struct btrfs_inode_item *inode_item; struct inode *vfs_inode = &inode->vfs_inode; @@ -1864,8 +1863,6 @@ int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev) i_uid_write(vfs_inode, btrfs_stack_inode_uid(inode_item)); i_gid_write(vfs_inode, btrfs_stack_inode_gid(inode_item)); btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item)); - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); vfs_inode->i_mode = btrfs_stack_inode_mode(inode_item); set_nlink(vfs_inode, btrfs_stack_inode_nlink(inode_item)); inode_set_bytes(vfs_inode, btrfs_stack_inode_nbytes(inode_item)); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c953297aa89a..b21cb72835cc 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -111,6 +111,24 @@ struct btrfs_bio_ctrl { */ unsigned long submit_bitmap; struct readahead_control *ractl; + + /* + * The start offset of the last used extent map by a read operation. + * + * This is for proper compressed read merge. + * U64_MAX means we are starting the read and have made no progress yet. + * + * The current btrfs_bio_is_contig() only uses disk_bytenr as + * the condition to check if the read can be merged with previous + * bio, which is not correct. E.g. two file extents pointing to the + * same extent but with different offset. + * + * So here we need to do extra checks to only merge reads that are + * covered by the same extent map. + * Just extent_map::start will be enough, as they are unique + * inside the same inode. + */ + u64 last_em_start; }; static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) @@ -909,7 +927,7 @@ static void btrfs_readahead_expand(struct readahead_control *ractl, * return 0 on success, otherwise return error */ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, - struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start) + struct btrfs_bio_ctrl *bio_ctrl) { struct inode *inode = folio->mapping->host; struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); @@ -1019,12 +1037,11 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, * non-optimal behavior (submitting 2 bios for the same extent). */ if (compress_type != BTRFS_COMPRESS_NONE && - prev_em_start && *prev_em_start != (u64)-1 && - *prev_em_start != em->start) + bio_ctrl->last_em_start != U64_MAX && + bio_ctrl->last_em_start != em->start) force_bio_submit = true; - if (prev_em_start) - *prev_em_start = em->start; + bio_ctrl->last_em_start = em->start; btrfs_free_extent_map(em); em = NULL; @@ -1238,12 +1255,15 @@ int btrfs_read_folio(struct file *file, struct folio *folio) const u64 start = folio_pos(folio); const u64 end = start + folio_size(folio) - 1; struct extent_state *cached_state = NULL; - struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ }; + struct btrfs_bio_ctrl bio_ctrl = { + .opf = REQ_OP_READ, + .last_em_start = U64_MAX, + }; struct extent_map *em_cached = NULL; int ret; lock_extents_for_read(inode, start, end, &cached_state); - ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL); + ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state); btrfs_free_extent_map(em_cached); @@ -2583,7 +2603,8 @@ void btrfs_readahead(struct readahead_control *rac) { struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD, - .ractl = rac + .ractl = rac, + .last_em_start = U64_MAX, }; struct folio *folio; struct btrfs_inode *inode = BTRFS_I(rac->mapping->host); @@ -2591,12 +2612,11 @@ void btrfs_readahead(struct readahead_control *rac) const u64 end = start + readahead_length(rac) - 1; struct extent_state *cached_state = NULL; struct extent_map *em_cached = NULL; - u64 prev_em_start = (u64)-1; lock_extents_for_read(inode, start, end, &cached_state); while ((folio = readahead_folio(rac)) != NULL) - btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start); + btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index dd82dcc7b2b7..18db1053cdf0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3885,10 +3885,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path bool filled = false; int first_xattr_slot; - ret = btrfs_init_file_extent_tree(inode); - if (ret) - goto out; - ret = btrfs_fill_inode(inode, &rdev); if (!ret) filled = true; @@ -3920,8 +3916,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path i_uid_write(vfs_inode, btrfs_inode_uid(leaf, inode_item)); i_gid_write(vfs_inode, btrfs_inode_gid(leaf, inode_item)); btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item)); - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); inode_set_atime(vfs_inode, btrfs_timespec_sec(leaf, &inode_item->atime), btrfs_timespec_nsec(leaf, &inode_item->atime)); @@ -3953,6 +3947,11 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path btrfs_set_inode_mapping_order(inode); cache_index: + ret = btrfs_init_file_extent_tree(inode); + if (ret) + goto out; + btrfs_inode_set_file_extent_range(inode, 0, + round_up(i_size_read(vfs_inode), fs_info->sectorsize)); /* * If we were modified in the current generation and evicted from memory * and then re-read we need to do a full sync since we don't have any @@ -5696,7 +5695,17 @@ static void btrfs_del_inode_from_root(struct btrfs_inode *inode) bool empty = false; xa_lock(&root->inodes); - entry = __xa_erase(&root->inodes, btrfs_ino(inode)); + /* + * This btrfs_inode is being freed and has already been unhashed at this + * point. It's possible that another btrfs_inode has already been + * allocated for the same inode and inserted itself into the root, so + * don't delete it in that case. + * + * Note that this shouldn't need to allocate memory, so the gfp flags + * don't really matter. + */ + entry = __xa_cmpxchg(&root->inodes, btrfs_ino(inode), inode, NULL, + GFP_ATOMIC); if (entry == inode) empty = xa_empty(&root->inodes); xa_unlock(&root->inodes); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index ccaa9a3cf1ce..da102da169fd 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1455,6 +1455,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup *qgroup; LIST_HEAD(qgroup_list); u64 num_bytes = src->excl; + u64 num_bytes_cmpr = src->excl_cmpr; int ret = 0; qgroup = find_qgroup_rb(fs_info, ref_root); @@ -1466,11 +1467,12 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup_list *glist; qgroup->rfer += sign * num_bytes; - qgroup->rfer_cmpr += sign * num_bytes; + qgroup->rfer_cmpr += sign * num_bytes_cmpr; WARN_ON(sign < 0 && qgroup->excl < num_bytes); + WARN_ON(sign < 0 && qgroup->excl_cmpr < num_bytes_cmpr); qgroup->excl += sign * num_bytes; - qgroup->excl_cmpr += sign * num_bytes; + qgroup->excl_cmpr += sign * num_bytes_cmpr; if (sign > 0) qgroup_rsv_add_by_qgroup(fs_info, qgroup, src); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index a262b494a89f..df1f6cc3fe21 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -299,9 +299,12 @@ static int btrfs_parse_compress(struct btrfs_fs_context *ctx, btrfs_set_opt(ctx->mount_opt, COMPRESS); btrfs_clear_opt(ctx->mount_opt, NODATACOW); btrfs_clear_opt(ctx->mount_opt, NODATASUM); - } else if (btrfs_match_compress_type(string, "lzo", false)) { + } else if (btrfs_match_compress_type(string, "lzo", true)) { ctx->compress_type = BTRFS_COMPRESS_LZO; - ctx->compress_level = 0; + ctx->compress_level = btrfs_compress_str2level(BTRFS_COMPRESS_LZO, + string + 3); + if (string[3] == ':' && string[4]) + btrfs_warn(NULL, "Compression level ignored for LZO"); btrfs_set_opt(ctx->mount_opt, COMPRESS); btrfs_clear_opt(ctx->mount_opt, NODATACOW); btrfs_clear_opt(ctx->mount_opt, NODATASUM); @@ -1079,7 +1082,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_printf(seq, ",compress-force=%s", compress_type); else seq_printf(seq, ",compress=%s", compress_type); - if (info->compress_level) + if (info->compress_level && info->compress_type != BTRFS_COMPRESS_LZO) seq_printf(seq, ":%d", info->compress_level); } if (btrfs_test_opt(info, NOSSD)) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 7d5d90845ca9..7a63afedd01e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1964,7 +1964,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; - search_key.offset = key->objectid; + search_key.offset = btrfs_extref_hash(key->objectid, name.name, name.len); ret = backref_in_log(root->log_root, &search_key, key->objectid, &name); if (ret < 0) { goto out; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index fa7a929a0461..c6e3efd6f602 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2722,6 +2722,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path goto error; } + if (bdev_nr_bytes(file_bdev(bdev_file)) <= BTRFS_DEVICE_RANGE_RESERVED) { + ret = -EINVAL; + goto error; + } + if (fs_devices->seeding) { seeding_dev = true; down_write(&sb->s_umount); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index ea662036f441..efc2a81f50e5 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2582,9 +2582,9 @@ again: spin_lock(&space_info->lock); space_info->total_bytes -= bg->length; space_info->disk_total -= bg->length * factor; + space_info->disk_total -= bg->zone_unusable; /* There is no allocation ever happened. */ ASSERT(bg->used == 0); - ASSERT(bg->zone_unusable == 0); /* No super block in a block group on the zoned setup. */ ASSERT(bg->bytes_super == 0); spin_unlock(&space_info->lock); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8b202d789e93..322ed268f14a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1264,7 +1264,9 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping, 0, gfp_flags); if (IS_ERR(pages[index])) { - if (PTR_ERR(pages[index]) == -EINVAL) { + int err = PTR_ERR(pages[index]); + + if (err == -EINVAL) { pr_err_client(cl, "inode->i_blkbits=%hhu\n", inode->i_blkbits); } @@ -1273,7 +1275,7 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping, BUG_ON(ceph_wbc->locked_pages == 0); pages[index] = NULL; - return PTR_ERR(pages[index]); + return err; } } else { pages[index] = &folio->page; @@ -1687,6 +1689,7 @@ get_more_pages: process_folio_batch: rc = ceph_process_folio_batch(mapping, wbc, &ceph_wbc); + ceph_shift_unused_folios_left(&ceph_wbc.fbatch); if (rc) goto release_folios; @@ -1695,8 +1698,6 @@ process_folio_batch: goto release_folios; if (ceph_wbc.processed_in_fbatch) { - ceph_shift_unused_folios_left(&ceph_wbc.fbatch); - if (folio_batch_count(&ceph_wbc.fbatch) == 0 && ceph_wbc.locked_pages < ceph_wbc.max_pages) { doutc(cl, "reached end fbatch, trying for more\n"); diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index fdd404fc8112..f3fe786b4143 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -55,8 +55,6 @@ static int mdsc_show(struct seq_file *s, void *p) struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; struct rb_node *rp; - int pathlen = 0; - u64 pathbase; char *path; mutex_lock(&mdsc->mutex); @@ -81,8 +79,8 @@ static int mdsc_show(struct seq_file *s, void *p) if (req->r_inode) { seq_printf(s, " #%llx", ceph_ino(req->r_inode)); } else if (req->r_dentry) { - path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen, - &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; spin_lock(&req->r_dentry->d_lock); @@ -91,7 +89,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_dentry, path ? path : ""); spin_unlock(&req->r_dentry->d_lock); - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); } else if (req->r_path1) { seq_printf(s, " #%llx/%s", req->r_ino1.ino, req->r_path1); @@ -100,8 +98,8 @@ static int mdsc_show(struct seq_file *s, void *p) } if (req->r_old_dentry) { - path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &pathlen, - &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; spin_lock(&req->r_old_dentry->d_lock); @@ -111,7 +109,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_old_dentry, path ? path : ""); spin_unlock(&req->r_old_dentry->d_lock); - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); } else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) { if (req->r_ino2.ino) seq_printf(s, " #%llx/%s", req->r_ino2.ino, diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 8478e7e75df6..32973c62c1a2 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1271,10 +1271,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, /* If op failed, mark everyone involved for errors */ if (result) { - int pathlen = 0; - u64 base = 0; - char *path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, - &base, 0); + struct ceph_path_info path_info = {0}; + char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); /* mark error on parent + clear complete */ mapping_set_error(req->r_parent->i_mapping, result); @@ -1288,8 +1286,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, mapping_set_error(req->r_old_inode->i_mapping, result); pr_warn_client(cl, "failure path=(%llx)%s result=%d!\n", - base, IS_ERR(path) ? "<<bad>>" : path, result); - ceph_mdsc_free_path(path, pathlen); + path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result); + ceph_mdsc_free_path_info(&path_info); } out: iput(req->r_old_inode); @@ -1347,8 +1345,6 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) int err = -EROFS; int op; char *path; - int pathlen; - u64 pathbase; if (ceph_snap(dir) == CEPH_SNAPDIR) { /* rmdir .snap/foo is RMSNAP */ @@ -1367,14 +1363,15 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) if (!dn) { try_async = false; } else { - path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; err = 0; } else { err = ceph_mds_check_access(mdsc, path, MAY_WRITE); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dn); /* For none EACCES cases will let the MDS do the mds auth check */ diff --git a/fs/ceph/file.c b/fs/ceph/file.c index c02f100f8552..978acd3d4b32 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -368,8 +368,6 @@ int ceph_open(struct inode *inode, struct file *file) int flags, fmode, wanted; struct dentry *dentry; char *path; - int pathlen; - u64 pathbase; bool do_sync = false; int mask = MAY_READ; @@ -399,14 +397,15 @@ int ceph_open(struct inode *inode, struct file *file) if (!dentry) { do_sync = true; } else { - path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; err = 0; } else { err = ceph_mds_check_access(mdsc, path, mask); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dentry); /* For none EACCES cases will let the MDS do the mds auth check */ @@ -614,15 +613,13 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, mapping_set_error(req->r_parent->i_mapping, result); if (result) { - int pathlen = 0; - u64 base = 0; - char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen, - &base, 0); + struct ceph_path_info path_info = {0}; + char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0); pr_warn_client(cl, "async create failure path=(%llx)%s result=%d!\n", - base, IS_ERR(path) ? "<<bad>>" : path, result); - ceph_mdsc_free_path(path, pathlen); + path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result); + ceph_mdsc_free_path_info(&path_info); ceph_dir_clear_complete(req->r_parent); if (!d_unhashed(dentry)) @@ -791,8 +788,6 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, int mask; int err; char *path; - int pathlen; - u64 pathbase; doutc(cl, "%p %llx.%llx dentry %p '%pd' %s flags %d mode 0%o\n", dir, ceph_vinop(dir), dentry, dentry, @@ -814,7 +809,8 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, if (!dn) { try_async = false; } else { - path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; err = 0; @@ -826,7 +822,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, mask |= MAY_WRITE; err = ceph_mds_check_access(mdsc, path, mask); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dn); /* For none EACCES cases will let the MDS do the mds auth check */ diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index fc543075b827..f67025465de0 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -55,6 +55,52 @@ static int ceph_set_ino_cb(struct inode *inode, void *data) return 0; } +/* + * Check if the parent inode matches the vino from directory reply info + */ +static inline bool ceph_vino_matches_parent(struct inode *parent, + struct ceph_vino vino) +{ + return ceph_ino(parent) == vino.ino && ceph_snap(parent) == vino.snap; +} + +/* + * Validate that the directory inode referenced by @req->r_parent matches the + * inode number and snapshot id contained in the reply's directory record. If + * they do not match – which can theoretically happen if the parent dentry was + * moved between the time the request was issued and the reply arrived – fall + * back to looking up the correct inode in the inode cache. + * + * A reference is *always* returned. Callers that receive a different inode + * than the original @parent are responsible for dropping the extra reference + * once the reply has been processed. + */ +static struct inode *ceph_get_reply_dir(struct super_block *sb, + struct inode *parent, + struct ceph_mds_reply_info_parsed *rinfo) +{ + struct ceph_vino vino; + + if (unlikely(!rinfo->diri.in)) + return parent; /* nothing to compare against */ + + /* If we didn't have a cached parent inode to begin with, just bail out. */ + if (!parent) + return NULL; + + vino.ino = le64_to_cpu(rinfo->diri.in->ino); + vino.snap = le64_to_cpu(rinfo->diri.in->snapid); + + if (likely(ceph_vino_matches_parent(parent, vino))) + return parent; /* matches – use the original reference */ + + /* Mismatch – this should be rare. Emit a WARN and obtain the correct inode. */ + WARN_ONCE(1, "ceph: reply dir mismatch (parent valid %llx.%llx reply %llx.%llx)\n", + ceph_ino(parent), ceph_snap(parent), vino.ino, vino.snap); + + return ceph_get_inode(sb, vino, NULL); +} + /** * ceph_new_inode - allocate a new inode in advance of an expected create * @dir: parent directory for new inode @@ -1523,6 +1569,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) struct ceph_vino tvino, dvino; struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); struct ceph_client *cl = fsc->client; + struct inode *parent_dir = NULL; int err = 0; doutc(cl, "%p is_dentry %d is_target %d\n", req, @@ -1536,10 +1583,17 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) } if (rinfo->head->is_dentry) { - struct inode *dir = req->r_parent; - - if (dir) { - err = ceph_fill_inode(dir, NULL, &rinfo->diri, + /* + * r_parent may be stale, in cases when R_PARENT_LOCKED is not set, + * so we need to get the correct inode + */ + parent_dir = ceph_get_reply_dir(sb, req->r_parent, rinfo); + if (unlikely(IS_ERR(parent_dir))) { + err = PTR_ERR(parent_dir); + goto done; + } + if (parent_dir) { + err = ceph_fill_inode(parent_dir, NULL, &rinfo->diri, rinfo->dirfrag, session, -1, &req->r_caps_reservation); if (err < 0) @@ -1548,14 +1602,14 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) WARN_ON_ONCE(1); } - if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME && + if (parent_dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME && test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) && !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) { bool is_nokey = false; struct qstr dname; struct dentry *dn, *parent; struct fscrypt_str oname = FSTR_INIT(NULL, 0); - struct ceph_fname fname = { .dir = dir, + struct ceph_fname fname = { .dir = parent_dir, .name = rinfo->dname, .ctext = rinfo->altname, .name_len = rinfo->dname_len, @@ -1564,10 +1618,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) BUG_ON(!rinfo->head->is_target); BUG_ON(req->r_dentry); - parent = d_find_any_alias(dir); + parent = d_find_any_alias(parent_dir); BUG_ON(!parent); - err = ceph_fname_alloc_buffer(dir, &oname); + err = ceph_fname_alloc_buffer(parent_dir, &oname); if (err < 0) { dput(parent); goto done; @@ -1576,7 +1630,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) err = ceph_fname_to_usr(&fname, NULL, &oname, &is_nokey); if (err < 0) { dput(parent); - ceph_fname_free_buffer(dir, &oname); + ceph_fname_free_buffer(parent_dir, &oname); goto done; } dname.name = oname.name; @@ -1595,7 +1649,7 @@ retry_lookup: dname.len, dname.name, dn); if (!dn) { dput(parent); - ceph_fname_free_buffer(dir, &oname); + ceph_fname_free_buffer(parent_dir, &oname); err = -ENOMEM; goto done; } @@ -1610,12 +1664,12 @@ retry_lookup: ceph_snap(d_inode(dn)) != tvino.snap)) { doutc(cl, " dn %p points to wrong inode %p\n", dn, d_inode(dn)); - ceph_dir_clear_ordered(dir); + ceph_dir_clear_ordered(parent_dir); d_delete(dn); dput(dn); goto retry_lookup; } - ceph_fname_free_buffer(dir, &oname); + ceph_fname_free_buffer(parent_dir, &oname); req->r_dentry = dn; dput(parent); @@ -1794,6 +1848,9 @@ retry_lookup: &dvino, ptvino); } done: + /* Drop extra ref from ceph_get_reply_dir() if it returned a new inode */ + if (unlikely(!IS_ERR_OR_NULL(parent_dir) && parent_dir != req->r_parent)) + iput(parent_dir); doutc(cl, "done err=%d\n", err); return err; } @@ -2487,22 +2544,21 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode, int truncate_retry = 20; /* The RMW will take around 50ms */ struct dentry *dentry; char *path; - int pathlen; - u64 pathbase; bool do_sync = false; dentry = d_find_alias(inode); if (!dentry) { do_sync = true; } else { - path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; err = 0; } else { err = ceph_mds_check_access(mdsc, path, MAY_WRITE); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dentry); /* For none EACCES cases will let the MDS do the mds auth check */ diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 0f497c39ff82..3bc72b47fe4d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2681,8 +2681,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) * ceph_mdsc_build_path - build a path string to a given dentry * @mdsc: mds client * @dentry: dentry to which path should be built - * @plen: returned length of string - * @pbase: returned base inode number + * @path_info: output path, length, base ino+snap, and freepath ownership flag * @for_wire: is this path going to be sent to the MDS? * * Build a string that represents the path to the dentry. This is mostly called @@ -2700,7 +2699,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) * foo/.snap/bar -> foo//bar */ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry, - int *plen, u64 *pbase, int for_wire) + struct ceph_path_info *path_info, int for_wire) { struct ceph_client *cl = mdsc->fsc->client; struct dentry *cur; @@ -2810,16 +2809,28 @@ retry: return ERR_PTR(-ENAMETOOLONG); } - *pbase = base; - *plen = PATH_MAX - 1 - pos; + /* Initialize the output structure */ + memset(path_info, 0, sizeof(*path_info)); + + path_info->vino.ino = base; + path_info->pathlen = PATH_MAX - 1 - pos; + path_info->path = path + pos; + path_info->freepath = true; + + /* Set snap from dentry if available */ + if (d_inode(dentry)) + path_info->vino.snap = ceph_snap(d_inode(dentry)); + else + path_info->vino.snap = CEPH_NOSNAP; + doutc(cl, "on %p %d built %llx '%.*s'\n", dentry, d_count(dentry), - base, *plen, path + pos); + base, PATH_MAX - 1 - pos, path + pos); return path + pos; } static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry, - struct inode *dir, const char **ppath, int *ppathlen, - u64 *pino, bool *pfreepath, bool parent_locked) + struct inode *dir, struct ceph_path_info *path_info, + bool parent_locked) { char *path; @@ -2828,41 +2839,47 @@ static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry dir = d_inode_rcu(dentry->d_parent); if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP && !IS_ENCRYPTED(dir)) { - *pino = ceph_ino(dir); + path_info->vino.ino = ceph_ino(dir); + path_info->vino.snap = ceph_snap(dir); rcu_read_unlock(); - *ppath = dentry->d_name.name; - *ppathlen = dentry->d_name.len; + path_info->path = dentry->d_name.name; + path_info->pathlen = dentry->d_name.len; + path_info->freepath = false; return 0; } rcu_read_unlock(); - path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1); + path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1); if (IS_ERR(path)) return PTR_ERR(path); - *ppath = path; - *pfreepath = true; + /* + * ceph_mdsc_build_path already fills path_info, including snap handling. + */ return 0; } -static int build_inode_path(struct inode *inode, - const char **ppath, int *ppathlen, u64 *pino, - bool *pfreepath) +static int build_inode_path(struct inode *inode, struct ceph_path_info *path_info) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb); struct dentry *dentry; char *path; if (ceph_snap(inode) == CEPH_NOSNAP) { - *pino = ceph_ino(inode); - *ppathlen = 0; + path_info->vino.ino = ceph_ino(inode); + path_info->vino.snap = ceph_snap(inode); + path_info->pathlen = 0; + path_info->freepath = false; return 0; } dentry = d_find_alias(inode); - path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1); + path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1); dput(dentry); if (IS_ERR(path)) return PTR_ERR(path); - *ppath = path; - *pfreepath = true; + /* + * ceph_mdsc_build_path already fills path_info, including snap from dentry. + * Override with inode's snap since that's what this function is for. + */ + path_info->vino.snap = ceph_snap(inode); return 0; } @@ -2872,26 +2889,32 @@ static int build_inode_path(struct inode *inode, */ static int set_request_path_attr(struct ceph_mds_client *mdsc, struct inode *rinode, struct dentry *rdentry, struct inode *rdiri, - const char *rpath, u64 rino, const char **ppath, - int *pathlen, u64 *ino, bool *freepath, + const char *rpath, u64 rino, + struct ceph_path_info *path_info, bool parent_locked) { struct ceph_client *cl = mdsc->fsc->client; int r = 0; + /* Initialize the output structure */ + memset(path_info, 0, sizeof(*path_info)); + if (rinode) { - r = build_inode_path(rinode, ppath, pathlen, ino, freepath); + r = build_inode_path(rinode, path_info); doutc(cl, " inode %p %llx.%llx\n", rinode, ceph_ino(rinode), ceph_snap(rinode)); } else if (rdentry) { - r = build_dentry_path(mdsc, rdentry, rdiri, ppath, pathlen, ino, - freepath, parent_locked); - doutc(cl, " dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath); + r = build_dentry_path(mdsc, rdentry, rdiri, path_info, parent_locked); + doutc(cl, " dentry %p %llx/%.*s\n", rdentry, path_info->vino.ino, + path_info->pathlen, path_info->path); } else if (rpath || rino) { - *ino = rino; - *ppath = rpath; - *pathlen = rpath ? strlen(rpath) : 0; - doutc(cl, " path %.*s\n", *pathlen, rpath); + path_info->vino.ino = rino; + path_info->vino.snap = CEPH_NOSNAP; + path_info->path = rpath; + path_info->pathlen = rpath ? strlen(rpath) : 0; + path_info->freepath = false; + + doutc(cl, " path %.*s\n", path_info->pathlen, rpath); } return r; @@ -2968,11 +2991,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, struct ceph_client *cl = mdsc->fsc->client; struct ceph_msg *msg; struct ceph_mds_request_head_legacy *lhead; - const char *path1 = NULL; - const char *path2 = NULL; - u64 ino1 = 0, ino2 = 0; - int pathlen1 = 0, pathlen2 = 0; - bool freepath1 = false, freepath2 = false; + struct ceph_path_info path_info1 = {0}; + struct ceph_path_info path_info2 = {0}; struct dentry *old_dentry = NULL; int len; u16 releases; @@ -2982,25 +3002,49 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, u16 request_head_version = mds_supported_head_version(session); kuid_t caller_fsuid = req->r_cred->fsuid; kgid_t caller_fsgid = req->r_cred->fsgid; + bool parent_locked = test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); ret = set_request_path_attr(mdsc, req->r_inode, req->r_dentry, - req->r_parent, req->r_path1, req->r_ino1.ino, - &path1, &pathlen1, &ino1, &freepath1, - test_bit(CEPH_MDS_R_PARENT_LOCKED, - &req->r_req_flags)); + req->r_parent, req->r_path1, req->r_ino1.ino, + &path_info1, parent_locked); if (ret < 0) { msg = ERR_PTR(ret); goto out; } + /* + * When the parent directory's i_rwsem is *not* locked, req->r_parent may + * have become stale (e.g. after a concurrent rename) between the time the + * dentry was looked up and now. If we detect that the stored r_parent + * does not match the inode number we just encoded for the request, switch + * to the correct inode so that the MDS receives a valid parent reference. + */ + if (!parent_locked && req->r_parent && path_info1.vino.ino && + ceph_ino(req->r_parent) != path_info1.vino.ino) { + struct inode *old_parent = req->r_parent; + struct inode *correct_dir = ceph_get_inode(mdsc->fsc->sb, path_info1.vino, NULL); + if (!IS_ERR(correct_dir)) { + WARN_ONCE(1, "ceph: r_parent mismatch (had %llx wanted %llx) - updating\n", + ceph_ino(old_parent), path_info1.vino.ino); + /* + * Transfer CEPH_CAP_PIN from the old parent to the new one. + * The pin was taken earlier in ceph_mdsc_submit_request(). + */ + ceph_put_cap_refs(ceph_inode(old_parent), CEPH_CAP_PIN); + iput(old_parent); + req->r_parent = correct_dir; + ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + } + } + /* If r_old_dentry is set, then assume that its parent is locked */ if (req->r_old_dentry && !(req->r_old_dentry->d_flags & DCACHE_DISCONNECTED)) old_dentry = req->r_old_dentry; ret = set_request_path_attr(mdsc, NULL, old_dentry, - req->r_old_dentry_dir, - req->r_path2, req->r_ino2.ino, - &path2, &pathlen2, &ino2, &freepath2, true); + req->r_old_dentry_dir, + req->r_path2, req->r_ino2.ino, + &path_info2, true); if (ret < 0) { msg = ERR_PTR(ret); goto out_free1; @@ -3031,7 +3075,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, /* filepaths */ len += 2 * (1 + sizeof(u32) + sizeof(u64)); - len += pathlen1 + pathlen2; + len += path_info1.pathlen + path_info2.pathlen; /* cap releases */ len += sizeof(struct ceph_mds_request_release) * @@ -3039,9 +3083,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, !!req->r_old_inode_drop + !!req->r_old_dentry_drop); if (req->r_dentry_drop) - len += pathlen1; + len += path_info1.pathlen; if (req->r_old_dentry_drop) - len += pathlen2; + len += path_info2.pathlen; /* MClientRequest tail */ @@ -3154,8 +3198,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, lhead->ino = cpu_to_le64(req->r_deleg_ino); lhead->args = req->r_args; - ceph_encode_filepath(&p, end, ino1, path1); - ceph_encode_filepath(&p, end, ino2, path2); + ceph_encode_filepath(&p, end, path_info1.vino.ino, path_info1.path); + ceph_encode_filepath(&p, end, path_info2.vino.ino, path_info2.path); /* make note of release offset, in case we need to replay */ req->r_request_release_offset = p - msg->front.iov_base; @@ -3218,11 +3262,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, msg->hdr.data_off = cpu_to_le16(0); out_free2: - if (freepath2) - ceph_mdsc_free_path((char *)path2, pathlen2); + ceph_mdsc_free_path_info(&path_info2); out_free1: - if (freepath1) - ceph_mdsc_free_path((char *)path1, pathlen1); + ceph_mdsc_free_path_info(&path_info1); out: return msg; out_err: @@ -4579,24 +4621,20 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) struct ceph_pagelist *pagelist = recon_state->pagelist; struct dentry *dentry; struct ceph_cap *cap; - char *path; - int pathlen = 0, err; - u64 pathbase; + struct ceph_path_info path_info = {0}; + int err; u64 snap_follows; dentry = d_find_primary(inode); if (dentry) { /* set pathbase to parent dir when msg_version >= 2 */ - path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, + char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info, recon_state->msg_version >= 2); dput(dentry); if (IS_ERR(path)) { err = PTR_ERR(path); goto out_err; } - } else { - path = NULL; - pathbase = 0; } spin_lock(&ci->i_ceph_lock); @@ -4629,7 +4667,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) rec.v2.wanted = cpu_to_le32(__ceph_caps_wanted(ci)); rec.v2.issued = cpu_to_le32(cap->issued); rec.v2.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); - rec.v2.pathbase = cpu_to_le64(pathbase); + rec.v2.pathbase = cpu_to_le64(path_info.vino.ino); rec.v2.flock_len = (__force __le32) ((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1); } else { @@ -4644,7 +4682,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) ts = inode_get_atime(inode); ceph_encode_timespec64(&rec.v1.atime, &ts); rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); - rec.v1.pathbase = cpu_to_le64(pathbase); + rec.v1.pathbase = cpu_to_le64(path_info.vino.ino); } if (list_empty(&ci->i_cap_snaps)) { @@ -4706,7 +4744,7 @@ encode_again: sizeof(struct ceph_filelock); rec.v2.flock_len = cpu_to_le32(struct_len); - struct_len += sizeof(u32) + pathlen + sizeof(rec.v2); + struct_len += sizeof(u32) + path_info.pathlen + sizeof(rec.v2); if (struct_v >= 2) struct_len += sizeof(u64); /* snap_follows */ @@ -4730,7 +4768,7 @@ encode_again: ceph_pagelist_encode_8(pagelist, 1); ceph_pagelist_encode_32(pagelist, struct_len); } - ceph_pagelist_encode_string(pagelist, path, pathlen); + ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen); ceph_pagelist_append(pagelist, &rec, sizeof(rec.v2)); ceph_locks_to_pagelist(flocks, pagelist, num_fcntl_locks, num_flock_locks); @@ -4741,17 +4779,17 @@ out_freeflocks: } else { err = ceph_pagelist_reserve(pagelist, sizeof(u64) + sizeof(u32) + - pathlen + sizeof(rec.v1)); + path_info.pathlen + sizeof(rec.v1)); if (err) goto out_err; ceph_pagelist_encode_64(pagelist, ceph_ino(inode)); - ceph_pagelist_encode_string(pagelist, path, pathlen); + ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen); ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1)); } out_err: - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); if (!err) recon_state->nr_caps++; return err; diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 3e2a6fa7c19a..0428a5eaf28c 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -617,14 +617,24 @@ extern int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc); -static inline void ceph_mdsc_free_path(char *path, int len) +/* + * Structure to group path-related output parameters for build_*_path functions + */ +struct ceph_path_info { + const char *path; + int pathlen; + struct ceph_vino vino; + bool freepath; +}; + +static inline void ceph_mdsc_free_path_info(const struct ceph_path_info *path_info) { - if (!IS_ERR_OR_NULL(path)) - __putname(path - (PATH_MAX - 1 - len)); + if (path_info && path_info->freepath && !IS_ERR_OR_NULL(path_info->path)) + __putname((char *)path_info->path - (PATH_MAX - 1 - path_info->pathlen)); } extern char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, - struct dentry *dentry, int *plen, u64 *base, + struct dentry *dentry, struct ceph_path_info *path_info, int for_wire); extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry); diff --git a/fs/coredump.c b/fs/coredump.c index 5dce257c67fc..60bc9685e149 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1466,11 +1466,15 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write, ssize_t retval; char old_core_pattern[CORENAME_MAX_SIZE]; + if (write) + return proc_dostring(table, write, buffer, lenp, ppos); + retval = strscpy(old_core_pattern, core_pattern, CORENAME_MAX_SIZE); error = proc_dostring(table, write, buffer, lenp, ppos); if (error) return error; + if (!check_coredump_socket()) { strscpy(core_pattern, old_core_pattern, retval + 1); return -EINVAL; diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index 377ee12b8b96..3d5738f80072 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -12,10 +12,12 @@ /* to allow for x86 boot sectors and other oddities. */ #define EROFS_SUPER_OFFSET 1024 -#define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001 -#define EROFS_FEATURE_COMPAT_MTIME 0x00000002 -#define EROFS_FEATURE_COMPAT_XATTR_FILTER 0x00000004 +#define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001 +#define EROFS_FEATURE_COMPAT_MTIME 0x00000002 +#define EROFS_FEATURE_COMPAT_XATTR_FILTER 0x00000004 #define EROFS_FEATURE_COMPAT_SHARED_EA_IN_METABOX 0x00000008 +#define EROFS_FEATURE_COMPAT_PLAIN_XATTR_PFX 0x00000010 + /* * Any bits that aren't in EROFS_ALL_FEATURE_INCOMPAT should diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 4ccc5f0ee8df..9319c66e86c3 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -234,6 +234,7 @@ EROFS_FEATURE_FUNCS(metabox, incompat, INCOMPAT_METABOX) EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM) EROFS_FEATURE_FUNCS(xattr_filter, compat, COMPAT_XATTR_FILTER) EROFS_FEATURE_FUNCS(shared_ea_in_metabox, compat, COMPAT_SHARED_EA_IN_METABOX) +EROFS_FEATURE_FUNCS(plain_xattr_pfx, compat, COMPAT_PLAIN_XATTR_PFX) static inline u64 erofs_nid_to_ino64(struct erofs_sb_info *sbi, erofs_nid_t nid) { diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 1b529ace4db0..db13b40a78e0 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -1018,10 +1018,22 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) return 0; } +static void erofs_evict_inode(struct inode *inode) +{ +#ifdef CONFIG_FS_DAX + if (IS_DAX(inode)) + dax_break_layout_final(inode); +#endif + + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); +} + const struct super_operations erofs_sops = { .put_super = erofs_put_super, .alloc_inode = erofs_alloc_inode, .free_inode = erofs_free_inode, + .evict_inode = erofs_evict_inode, .statfs = erofs_statfs, .show_options = erofs_show_options, }; diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index eaa9efd766ee..396536d9a862 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -482,6 +482,7 @@ int erofs_xattr_prefixes_init(struct super_block *sb) erofs_off_t pos = (erofs_off_t)sbi->xattr_prefix_start << 2; struct erofs_xattr_prefix_item *pfs; int ret = 0, i, len; + bool plain = erofs_sb_has_plain_xattr_pfx(sbi); if (!sbi->xattr_prefix_count) return 0; @@ -490,9 +491,15 @@ int erofs_xattr_prefixes_init(struct super_block *sb) if (!pfs) return -ENOMEM; - if (sbi->packed_inode) - buf.mapping = sbi->packed_inode->i_mapping; - else + if (!plain) { + if (erofs_sb_has_metabox(sbi)) + (void)erofs_init_metabuf(&buf, sb, true); + else if (sbi->packed_inode) + buf.mapping = sbi->packed_inode->i_mapping; + else + plain = true; + } + if (plain) (void)erofs_init_metabuf(&buf, sb, false); for (i = 0; i < sbi->xattr_prefix_count; i++) { diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index a93efd95c555..798223e6da9c 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -394,10 +394,10 @@ static int z_erofs_map_blocks_fo(struct inode *inode, .map = map, .in_mbox = erofs_inode_in_metabox(inode), }; - int err = 0; - unsigned int endoff, afmt; + unsigned int endoff; unsigned long initial_lcn; unsigned long long ofs, end; + int err; ofs = flags & EROFS_GET_BLOCKS_FINDTAIL ? inode->i_size - 1 : map->m_la; if (fragment && !(flags & EROFS_GET_BLOCKS_FINDTAIL) && @@ -482,20 +482,15 @@ static int z_erofs_map_blocks_fo(struct inode *inode, err = -EFSCORRUPTED; goto unmap_out; } - afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ? - Z_EROFS_COMPRESSION_INTERLACED : - Z_EROFS_COMPRESSION_SHIFTED; + if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER) + map->m_algorithmformat = Z_EROFS_COMPRESSION_INTERLACED; + else + map->m_algorithmformat = Z_EROFS_COMPRESSION_SHIFTED; + } else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) { + map->m_algorithmformat = vi->z_algorithmtype[1]; } else { - afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ? - vi->z_algorithmtype[1] : vi->z_algorithmtype[0]; - if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) { - erofs_err(sb, "inconsistent algorithmtype %u for nid %llu", - afmt, vi->nid); - err = -EFSCORRUPTED; - goto unmap_out; - } + map->m_algorithmformat = vi->z_algorithmtype[0]; } - map->m_algorithmformat = afmt; if ((flags & EROFS_GET_BLOCKS_FIEMAP) || ((flags & EROFS_GET_BLOCKS_READMORE) && @@ -626,9 +621,9 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map) { struct erofs_inode *const vi = EROFS_I(inode); struct super_block *const sb = inode->i_sb; - int err, headnr; - erofs_off_t pos; struct z_erofs_map_header *h; + erofs_off_t pos; + int err = 0; if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) { /* @@ -642,7 +637,6 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map) if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE)) return -ERESTARTSYS; - err = 0; if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) goto out_unlock; @@ -679,15 +673,6 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map) else if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER) vi->z_idata_size = le16_to_cpu(h->h_idata_size); - headnr = 0; - if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX || - vi->z_algorithmtype[++headnr] >= Z_EROFS_COMPRESSION_MAX) { - erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel", - headnr + 1, vi->z_algorithmtype[headnr], vi->nid); - err = -EOPNOTSUPP; - goto out_unlock; - } - if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) && vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { @@ -726,6 +711,30 @@ out_unlock: return err; } +static int z_erofs_map_sanity_check(struct inode *inode, + struct erofs_map_blocks *map) +{ + struct erofs_sb_info *sbi = EROFS_I_SB(inode); + + if (!(map->m_flags & EROFS_MAP_ENCODED)) + return 0; + if (unlikely(map->m_algorithmformat >= Z_EROFS_COMPRESSION_RUNTIME_MAX)) { + erofs_err(inode->i_sb, "unknown algorithm %d @ pos %llu for nid %llu, please upgrade kernel", + map->m_algorithmformat, map->m_la, EROFS_I(inode)->nid); + return -EOPNOTSUPP; + } + if (unlikely(map->m_algorithmformat < Z_EROFS_COMPRESSION_MAX && + !(sbi->available_compr_algs & (1 << map->m_algorithmformat)))) { + erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu", + map->m_algorithmformat, EROFS_I(inode)->nid); + return -EFSCORRUPTED; + } + if (unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE || + map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE)) + return -EOPNOTSUPP; + return 0; +} + int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, int flags) { @@ -746,10 +755,8 @@ int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, else err = z_erofs_map_blocks_fo(inode, map, flags); } - if (!err && (map->m_flags & EROFS_MAP_ENCODED) && - unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE || - map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE)) - err = -EOPNOTSUPP; + if (!err) + err = z_erofs_map_sanity_check(inode, map); if (err) map->m_llen = 0; } diff --git a/fs/exec.c b/fs/exec.c index 2a1e5e4042a1..e861a4b7ffda 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -2048,7 +2048,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ { int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (!error) + if (!error && !write) validate_coredump_safety(); return error; } diff --git a/fs/fhandle.c b/fs/fhandle.c index 68a7d2861c58..a907ddfac4d5 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -208,6 +208,14 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry) return 1; /* + * Verify that the decoded dentry itself has a valid id mapping. + * In case the decoded dentry is the mountfd root itself, this + * verifies that the mountfd inode itself has a valid id mapping. + */ + if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(dentry))) + return 0; + + /* * It's racy as we're not taking rename_lock but we're able to ignore * permissions and we just need an approximation whether we were able * to follow a path to the file. diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index e80cd8f2c049..5150aa25e64b 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1893,7 +1893,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode, index = outarg->offset >> PAGE_SHIFT; - while (num) { + while (num && ap->num_folios < num_pages) { struct folio *folio; unsigned int folio_offset; unsigned int nr_bytes; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 2d817d7cab26..5c569c3cb53f 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1199,7 +1199,7 @@ static void fuse_fillattr(struct mnt_idmap *idmap, struct inode *inode, if (attr->blksize != 0) blkbits = ilog2(attr->blksize); else - blkbits = inode->i_sb->s_blocksize_bits; + blkbits = fc->blkbits; stat->blksize = 1 << blkbits; } @@ -1377,6 +1377,7 @@ retry: generic_fillattr(idmap, request_mask, inode, stat); stat->mode = fi->orig_i_mode; stat->ino = fi->orig_ino; + stat->blksize = 1 << fi->cached_i_blkbits; if (test_bit(FUSE_I_BTIME, &fi->state)) { stat->btime = fi->i_btime; stat->result_mask |= STATX_BTIME; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5525a4520b0f..4adcf09d4b01 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2960,7 +2960,7 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, .nodeid_out = ff_out->nodeid, .fh_out = ff_out->fh, .off_out = pos_out, - .len = len, + .len = min_t(size_t, len, UINT_MAX & PAGE_MASK), .flags = flags }; struct fuse_write_out outarg; @@ -3026,6 +3026,9 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, fc->no_copy_file_range = 1; err = -EOPNOTSUPP; } + if (!err && outarg.size > len) + err = -EIO; + if (err) goto out; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index ec248d13c8bf..cc428d04be3e 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -210,6 +210,12 @@ struct fuse_inode { /** Reference to backing file in passthrough mode */ struct fuse_backing *fb; #endif + + /* + * The underlying inode->i_blkbits value will not be modified, + * so preserve the blocksize specified by the server. + */ + u8 cached_i_blkbits; }; /** FUSE inode state bits */ @@ -969,6 +975,14 @@ struct fuse_conn { /* Request timeout (in jiffies). 0 = no timeout */ unsigned int req_timeout; } timeout; + + /* + * This is a workaround until fuse uses iomap for reads. + * For fuseblk servers, this represents the blocksize passed in at + * mount time and for regular fuse servers, this is equivalent to + * inode->i_blkbits. + */ + u8 blkbits; }; /* diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 67c2318bfc42..7ddfd2b3cc9c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -289,6 +289,11 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, } } + if (attr->blksize) + fi->cached_i_blkbits = ilog2(attr->blksize); + else + fi->cached_i_blkbits = fc->blkbits; + /* * Don't set the sticky bit in i_mode, unless we want the VFS * to check permissions. This prevents failures due to the @@ -1805,10 +1810,21 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx) err = -EINVAL; if (!sb_set_blocksize(sb, ctx->blksize)) goto err; + /* + * This is a workaround until fuse hooks into iomap for reads. + * Use PAGE_SIZE for the blocksize else if the writeback cache + * is enabled, buffered writes go through iomap and a read may + * overwrite partially written data if blocksize < PAGE_SIZE + */ + fc->blkbits = sb->s_blocksize_bits; + if (ctx->blksize != PAGE_SIZE && + !sb_set_blocksize(sb, PAGE_SIZE)) + goto err; #endif } else { sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; + fc->blkbits = sb->s_blocksize_bits; } sb->s_subtype = ctx->subtype; diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c index 607ef735ad4a..eb97ac009e75 100644 --- a/fs/fuse/passthrough.c +++ b/fs/fuse/passthrough.c @@ -237,6 +237,11 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map) if (!file) goto out; + /* read/write/splice/mmap passthrough only relevant for regular files */ + res = d_is_dir(file->f_path.dentry) ? -EISDIR : -EINVAL; + if (!d_is_reg(file->f_path.dentry)) + goto out_fput; + backing_sb = file_inode(file)->i_sb; res = -ELOOP; if (backing_sb->s_stack_depth >= fc->max_stack_depth) diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index c826e7ca49f5..76c8fd0bfc75 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -1016,7 +1016,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, if (kaddr) *kaddr = fs->window_kaddr + offset; if (pfn) - *pfn = fs->window_phys_addr + offset; + *pfn = PHYS_PFN(fs->window_phys_addr + offset); return nr_pages > max_nr_pages ? max_nr_pages : nr_pages; } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index a6c692cac616..9adf36e6364b 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -70,6 +70,24 @@ static struct kernfs_open_node *of_on(struct kernfs_open_file *of) !list_empty(&of->list)); } +/* Get active reference to kernfs node for an open file */ +static struct kernfs_open_file *kernfs_get_active_of(struct kernfs_open_file *of) +{ + /* Skip if file was already released */ + if (unlikely(of->released)) + return NULL; + + if (!kernfs_get_active(of->kn)) + return NULL; + + return of; +} + +static void kernfs_put_active_of(struct kernfs_open_file *of) +{ + return kernfs_put_active(of->kn); +} + /** * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn * @@ -139,7 +157,7 @@ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) if (ops->seq_stop) ops->seq_stop(sf, v); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) @@ -152,7 +170,7 @@ static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); @@ -238,7 +256,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; @@ -252,7 +270,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL; - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len < 0) @@ -323,7 +341,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; @@ -335,7 +353,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL; - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len > 0) @@ -357,13 +375,13 @@ static void kernfs_vma_open(struct vm_area_struct *vma) if (!of->vm_ops) return; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return; if (of->vm_ops->open) of->vm_ops->open(vma); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) @@ -375,14 +393,14 @@ static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -395,7 +413,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = 0; @@ -404,7 +422,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) else file_update_time(file); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -418,14 +436,14 @@ static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, if (!of->vm_ops) return -EINVAL; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -455,7 +473,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) mutex_lock(&of->mutex); rc = -ENODEV; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) goto out_unlock; ops = kernfs_ops(of->kn); @@ -490,7 +508,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) } vma->vm_ops = &kernfs_vm_ops; out_put: - kernfs_put_active(of->kn); + kernfs_put_active_of(of); out_unlock: mutex_unlock(&of->mutex); @@ -852,7 +870,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; - if (!kernfs_get_active(kn)) + if (!kernfs_get_active_of(of)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) @@ -860,7 +878,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) else ret = kernfs_generic_poll(of, wait); - kernfs_put_active(kn); + kernfs_put_active_of(of); return ret; } @@ -875,7 +893,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); return -ENODEV; } @@ -886,7 +904,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) else ret = generic_file_llseek(file, offset, whence); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); return ret; } diff --git a/fs/namespace.c b/fs/namespace.c index ae6d1312b184..51f77c65c0c6 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2455,7 +2455,7 @@ struct vfsmount *clone_private_mount(const struct path *path) return ERR_PTR(-EINVAL); } - if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN)) + if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); if (__has_locked_children(old_mnt, path->dentry)) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8fb4a950dd55..4e3dcc157a83 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -888,6 +888,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, if (fsinfo->xattr_support) server->caps |= NFS_CAP_XATTR; + else + server->caps &= ~NFS_CAP_XATTR; #endif } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 86e36c630f09..8059ece82468 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -28,6 +28,7 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/gfp.h> +#include <linux/rmap.h> #include <linux/swap.h> #include <linux/compaction.h> @@ -280,6 +281,37 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL_GPL(nfs_file_fsync); +void nfs_truncate_last_folio(struct address_space *mapping, loff_t from, + loff_t to) +{ + struct folio *folio; + + if (from >= to) + return; + + folio = filemap_lock_folio(mapping, from >> PAGE_SHIFT); + if (IS_ERR(folio)) + return; + + if (folio_mkclean(folio)) + folio_mark_dirty(folio); + + if (folio_test_uptodate(folio)) { + loff_t fpos = folio_pos(folio); + size_t offset = from - fpos; + size_t end = folio_size(folio); + + if (to - fpos < end) + end = to - fpos; + folio_zero_segment(folio, offset, end); + trace_nfs_size_truncate_folio(mapping->host, to); + } + + folio_unlock(folio); + folio_put(folio); +} +EXPORT_SYMBOL_GPL(nfs_truncate_last_folio); + /* * Decide whether a read/modify/write cycle may be more efficient * then a modify/write/read cycle when writing to a page in the @@ -356,6 +388,7 @@ static int nfs_write_begin(const struct kiocb *iocb, dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n", file, mapping->host->i_ino, len, (long long) pos); + nfs_truncate_last_folio(mapping, i_size_read(mapping->host), pos); fgp |= fgf_set_order(len); start: @@ -442,10 +475,11 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset, dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n", folio->index, offset, length); - if (offset != 0 || length < folio_size(folio)) - return; /* Cancel any unstarted writes on this page */ - nfs_wb_folio_cancel(inode, folio); + if (offset != 0 || length < folio_size(folio)) + nfs_wb_folio(inode, folio); + else + nfs_wb_folio_cancel(inode, folio); folio_wait_private_2(folio); /* [DEPRECATED] */ trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length); } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 8dc921d83538..9edb5f9b0c4e 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -293,7 +293,7 @@ ff_lseg_match_mirrors(struct pnfs_layout_segment *l1, struct pnfs_layout_segment *l2) { const struct nfs4_ff_layout_segment *fl1 = FF_LAYOUT_LSEG(l1); - const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l1); + const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l2); u32 i; if (fl1->mirror_array_cnt != fl2->mirror_array_cnt) @@ -773,8 +773,11 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, continue; if (check_device && - nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) + nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) { + // reinitialize the error state in case if this is the last iteration + ds = ERR_PTR(-EINVAL); continue; + } *best_idx = idx; break; @@ -804,7 +807,7 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, struct nfs4_pnfs_ds *ds; ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx); - if (ds) + if (!IS_ERR(ds)) return ds; return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx); } @@ -818,7 +821,7 @@ ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx, best_idx); - if (ds || !pgio->pg_mirror_idx) + if (!IS_ERR(ds) || !pgio->pg_mirror_idx) return ds; return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx); } @@ -868,7 +871,7 @@ retry: req->wb_nio = 0; ds = ff_layout_get_ds_for_read(pgio, &ds_idx); - if (!ds) { + if (IS_ERR(ds)) { if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; pnfs_generic_pg_cleanup(pgio); @@ -1072,11 +1075,13 @@ static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr) { u32 idx = hdr->pgio_mirror_idx + 1; u32 new_idx = 0; + struct nfs4_pnfs_ds *ds; - if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx)) - ff_layout_send_layouterror(hdr->lseg); - else + ds = ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx); + if (IS_ERR(ds)) pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg); + else + ff_layout_send_layouterror(hdr->lseg); pnfs_read_resend_pnfs(hdr, new_idx); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 338ef77ae423..49df9debb1a6 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -716,6 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; + loff_t oldsize = i_size_read(inode); int error = 0; nfs_inc_stats(inode, NFSIOS_VFSSETATTR); @@ -731,7 +732,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (error) return error; - if (attr->ia_size == i_size_read(inode)) + if (attr->ia_size == oldsize) attr->ia_valid &= ~ATTR_SIZE; } @@ -767,8 +768,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, trace_nfs_setattr_enter(inode); /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) + if (S_ISREG(inode->i_mode)) { + nfs_file_block_o_direct(NFS_I(inode)); nfs_sync_inode(inode); + } fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { @@ -777,8 +780,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, } error = NFS_PROTO(inode)->setattr(dentry, fattr, attr); - if (error == 0) + if (error == 0) { + if (attr->ia_valid & ATTR_SIZE) + nfs_truncate_last_folio(inode->i_mapping, oldsize, + attr->ia_size); error = nfs_refresh_inode(inode, fattr); + } nfs_free_fattr(fattr); out: trace_nfs_setattr_exit(inode, error); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 74d712b58423..c0a44f389f8f 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -437,6 +437,8 @@ int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); int nfs_check_flags(int); +void nfs_truncate_last_folio(struct address_space *mapping, loff_t from, + loff_t to); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; @@ -530,6 +532,16 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0; } +/* Must be called with exclusively locked inode->i_rwsem */ +static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi) +{ + if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { + clear_bit(NFS_INO_ODIRECT, &nfsi->flags); + inode_dio_wait(&nfsi->vfs_inode); + } +} + + /* namespace.c */ #define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, diff --git a/fs/nfs/io.c b/fs/nfs/io.c index 3388faf2acb9..d275b0a250bf 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -14,15 +14,6 @@ #include "internal.h" -/* Call with exclusively locked inode->i_rwsem */ -static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode) -{ - if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { - clear_bit(NFS_INO_ODIRECT, &nfsi->flags); - inode_dio_wait(inode); - } -} - /** * nfs_start_io_read - declare the file is being used for buffered reads * @inode: file inode @@ -57,7 +48,7 @@ nfs_start_io_read(struct inode *inode) err = down_write_killable(&inode->i_rwsem); if (err) return err; - nfs_block_o_direct(nfsi, inode); + nfs_file_block_o_direct(nfsi); downgrade_write(&inode->i_rwsem); return 0; @@ -90,7 +81,7 @@ nfs_start_io_write(struct inode *inode) err = down_write_killable(&inode->i_rwsem); if (!err) - nfs_block_o_direct(NFS_I(inode), inode); + nfs_file_block_o_direct(NFS_I(inode)); return err; } diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index bd5fca285899..97abf62f109d 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -180,10 +180,8 @@ static void nfs_local_probe(struct nfs_client *clp) return; } - if (nfs_client_is_local(clp)) { - /* If already enabled, disable and re-enable */ - nfs_localio_disable_client(clp); - } + if (nfs_client_is_local(clp)) + return; if (!nfs_uuid_begin(&clp->cl_uuid)) return; @@ -244,7 +242,8 @@ __nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, case -ENOMEM: case -ENXIO: case -ENOENT: - /* Revalidate localio, will disable if unsupported */ + /* Revalidate localio */ + nfs_localio_disable_client(clp); nfs_local_probe(clp); } } @@ -453,12 +452,13 @@ static void nfs_local_call_read(struct work_struct *work) nfs_local_iter_init(&iter, iocb, READ); status = filp->f_op->read_iter(&iocb->kiocb, &iter); + + revert_creds(save_cred); + if (status != -EIOCBQUEUED) { nfs_local_read_done(iocb, status); nfs_local_pgio_release(iocb); } - - revert_creds(save_cred); } static int @@ -648,14 +648,15 @@ static void nfs_local_call_write(struct work_struct *work) file_start_write(filp); status = filp->f_op->write_iter(&iocb->kiocb, &iter); file_end_write(filp); + + revert_creds(save_cred); + current->flags = old_flags; + if (status != -EIOCBQUEUED) { nfs_local_write_done(iocb, status); nfs_local_vfs_getattr(iocb); nfs_local_pgio_release(iocb); } - - revert_creds(save_cred); - current->flags = old_flags; } static int diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 01c01f45358b..6a0b5871ba3b 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -114,6 +114,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, exception.inode = inode; exception.state = lock->open_context->state; + nfs_file_block_o_direct(NFS_I(inode)); err = nfs_sync_inode(inode); if (err) goto out; @@ -137,6 +138,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], }; struct inode *inode = file_inode(filep); + loff_t oldsize = i_size_read(inode); int err; if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) @@ -145,7 +147,11 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) inode_lock(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); - if (err == -EOPNOTSUPP) + + if (err == 0) + nfs_truncate_last_folio(inode->i_mapping, oldsize, + offset + len); + else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE | NFS_CAP_ZERO_RANGE); @@ -183,6 +189,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE], }; struct inode *inode = file_inode(filep); + loff_t oldsize = i_size_read(inode); int err; if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE)) @@ -191,9 +198,11 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) inode_lock(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); - if (err == 0) + if (err == 0) { + nfs_truncate_last_folio(inode->i_mapping, oldsize, + offset + len); truncate_pagecache_range(inode, offset, (offset + len) -1); - if (err == -EOPNOTSUPP) + } else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE; inode_unlock(inode); @@ -354,22 +363,27 @@ out: /** * nfs42_copy_dest_done - perform inode cache updates after clone/copy offload - * @inode: pointer to destination inode + * @file: pointer to destination file * @pos: destination offset * @len: copy length + * @oldsize: length of the file prior to clone/copy * * Punch a hole in the inode page cache, so that the NFS client will * know to retrieve new data. * Update the file size if necessary, and then mark the inode as having * invalid cached values for change attribute, ctime, mtime and space used. */ -static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len) +static void nfs42_copy_dest_done(struct file *file, loff_t pos, loff_t len, + loff_t oldsize) { + struct inode *inode = file_inode(file); + struct address_space *mapping = file->f_mapping; loff_t newsize = pos + len; loff_t end = newsize - 1; - WARN_ON_ONCE(invalidate_inode_pages2_range(inode->i_mapping, - pos >> PAGE_SHIFT, end >> PAGE_SHIFT)); + nfs_truncate_last_folio(mapping, oldsize, pos); + WARN_ON_ONCE(invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, + end >> PAGE_SHIFT)); spin_lock(&inode->i_lock); if (newsize > i_size_read(inode)) @@ -402,6 +416,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct nfs_server *src_server = NFS_SERVER(src_inode); loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; + loff_t oldsize_dst = i_size_read(dst_inode); size_t count = args->count; ssize_t status; @@ -430,6 +445,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, return status; } + nfs_file_block_o_direct(NFS_I(dst_inode)); status = nfs_sync_inode(dst_inode); if (status) return status; @@ -475,7 +491,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, goto out; } - nfs42_copy_dest_done(dst_inode, pos_dst, res->write_res.count); + nfs42_copy_dest_done(dst, pos_dst, res->write_res.count, oldsize_dst); nfs_invalidate_atime(src_inode); status = res->write_res.count; out: @@ -1242,6 +1258,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, struct nfs42_clone_res res = { .server = server, }; + loff_t oldsize_dst = i_size_read(dst_inode); int status; msg->rpc_argp = &args; @@ -1276,7 +1293,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, /* 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); + nfs42_copy_dest_done(dst_f, dst_offset, count, oldsize_dst); status = nfs_post_op_update_inode(dst_inode, res.dst_fattr); } diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 1d6b5f4230c9..c9a0d1e420c6 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -278,9 +278,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off, lock_two_nondirectories(src_inode, dst_inode); /* flush all pending writes on both src and dst so that server * has the latest data */ + nfs_file_block_o_direct(NFS_I(src_inode)); ret = nfs_sync_inode(src_inode); if (ret) goto out_unlock; + nfs_file_block_o_direct(NFS_I(dst_inode)); ret = nfs_sync_inode(dst_inode); if (ret) goto out_unlock; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7d2b67e06cc3..ce61253efd45 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4013,8 +4013,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f res.attr_bitmask[2]; } memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask)); - server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | - NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL); + server->caps &= + ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS | + NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS | + NFS_CAP_OPEN_XOR | NFS_CAP_DELEGTIME); server->fattr_valid = NFS_ATTR_FATTR_V4; if (res.attr_bitmask[0] & FATTR4_WORD0_ACL && res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL) @@ -4092,7 +4094,6 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) }; int err; - nfs_server_set_init_caps(server); do { err = nfs4_handle_exception(server, _nfs4_server_capabilities(server, fhandle), diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 96b1323318c2..627115179795 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -272,6 +272,7 @@ DECLARE_EVENT_CLASS(nfs_update_size_class, TP_ARGS(inode, new_size)) DEFINE_NFS_UPDATE_SIZE_EVENT(truncate); +DEFINE_NFS_UPDATE_SIZE_EVENT(truncate_folio); DEFINE_NFS_UPDATE_SIZE_EVENT(wcc); DEFINE_NFS_UPDATE_SIZE_EVENT(update); DEFINE_NFS_UPDATE_SIZE_EVENT(grow); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 8b7c04737967..647c53d1418a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -237,59 +237,17 @@ static void nfs_mapping_set_error(struct folio *folio, int error) } /* - * nfs_page_group_search_locked - * @head - head request of page group - * @page_offset - offset into page + * nfs_page_covers_folio + * @req: struct nfs_page * - * Search page group with head @head to find a request that contains the - * page offset @page_offset. - * - * Returns a pointer to the first matching nfs request, or NULL if no - * match is found. - * - * Must be called with the page group lock held - */ -static struct nfs_page * -nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset) -{ - struct nfs_page *req; - - req = head; - do { - if (page_offset >= req->wb_pgbase && - page_offset < (req->wb_pgbase + req->wb_bytes)) - return req; - - req = req->wb_this_page; - } while (req != head); - - return NULL; -} - -/* - * nfs_page_group_covers_page - * @head - head request of page group - * - * Return true if the page group with head @head covers the whole page, - * returns false otherwise + * Return true if the request covers the whole folio. + * Note that the caller should ensure all subrequests have been joined */ static bool nfs_page_group_covers_page(struct nfs_page *req) { unsigned int len = nfs_folio_length(nfs_page_to_folio(req)); - struct nfs_page *tmp; - unsigned int pos = 0; - - nfs_page_group_lock(req); - for (;;) { - tmp = nfs_page_group_search_locked(req->wb_head, pos); - if (!tmp) - break; - pos = tmp->wb_pgbase + tmp->wb_bytes; - } - - nfs_page_group_unlock(req); - return pos >= len; + return req->wb_pgbase == 0 && req->wb_bytes == len; } /* We can set the PG_uptodate flag if we see that a write request @@ -2045,6 +2003,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) * release it */ nfs_inode_remove_request(req); nfs_unlock_and_release_request(req); + folio_cancel_dirty(folio); } return ret; diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index d98e0d2de09f..3c39cfacb251 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -625,11 +625,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) */ list_for_each_entry(d, &r->mon_domains, hdr.list) { if (d->ci_id == domid) { - rr.ci_id = d->ci_id; cpu = cpumask_any(&d->hdr.cpu_mask); ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); if (!ci) continue; + rr.ci = ci; mon_event_read(&rr, r, NULL, rdtgrp, &ci->shared_cpu_map, evtid, false); goto checkresult; diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index 0a1eedba2b03..9a8cf6f11151 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -98,7 +98,7 @@ struct mon_data { * domains in @r sharing L3 @ci.id * @evtid: Which monitor event to read. * @first: Initialize MBM counter when true. - * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains. + * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains. * @err: Error encountered when reading counter. * @val: Returned value of event counter. If @rgrp is a parent resource group, * @val includes the sum of event counts from its child resource groups. @@ -112,7 +112,7 @@ struct rmid_read { struct rdt_mon_domain *d; enum resctrl_event_id evtid; bool first; - unsigned int ci_id; + struct cacheinfo *ci; int err; u64 val; void *arch_mon_ctx; diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index f5637855c3ac..7326c28a7908 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -361,7 +361,6 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { int cpu = smp_processor_id(); struct rdt_mon_domain *d; - struct cacheinfo *ci; struct mbm_state *m; int err, ret; u64 tval = 0; @@ -389,8 +388,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) } /* Summing domains that share a cache, must be on a CPU for that cache. */ - ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); - if (!ci || ci->id != rr->ci_id) + if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map)) return -EINVAL; /* @@ -402,7 +400,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) */ ret = -EINVAL; list_for_each_entry(d, &rr->r->mon_domains, hdr.list) { - if (d->ci_id != rr->ci_id) + if (d->ci_id != rr->ci->id) continue; err = resctrl_arch_rmid_read(rr->r, d, closid, rmid, rr->evtid, &tval, rr->arch_mon_ctx); diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index beb4f18f05ef..2337cf795db3 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -304,6 +304,8 @@ static int cifs_debug_dirs_proc_show(struct seq_file *m, void *v) list_for_each(tmp1, &ses->tcon_list) { tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); cfids = tcon->cfids; + if (!cfids) + continue; spin_lock(&cfids->cfid_list_lock); /* check lock ordering */ seq_printf(m, "Num entries: %d\n", cfids->num_entries); list_for_each_entry(cfid, &cfids->entries, entry) { @@ -319,8 +321,6 @@ static int cifs_debug_dirs_proc_show(struct seq_file *m, void *v) seq_printf(m, "\n"); } spin_unlock(&cfids->cfid_list_lock); - - } } } @@ -347,6 +347,22 @@ static __always_inline const char *compression_alg_str(__le16 alg) } } +static __always_inline const char *cipher_alg_str(__le16 cipher) +{ + switch (cipher) { + case SMB2_ENCRYPTION_AES128_CCM: + return "AES128-CCM"; + case SMB2_ENCRYPTION_AES128_GCM: + return "AES128-GCM"; + case SMB2_ENCRYPTION_AES256_CCM: + return "AES256-CCM"; + case SMB2_ENCRYPTION_AES256_GCM: + return "AES256-GCM"; + default: + return "UNKNOWN"; + } +} + static int cifs_debug_data_proc_show(struct seq_file *m, void *v) { struct mid_q_entry *mid_entry; @@ -539,6 +555,11 @@ skip_rdma: else seq_puts(m, "disabled (not supported by this server)"); + /* Show negotiated encryption cipher, even if not required */ + seq_puts(m, "\nEncryption: "); + if (server->cipher_type) + seq_printf(m, "Negotiated cipher (%s)", cipher_alg_str(server->cipher_type)); + seq_printf(m, "\n\n\tSessions: "); i = 0; list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { @@ -576,12 +597,8 @@ skip_rdma: /* dump session id helpful for use with network trace */ seq_printf(m, " SessionId: 0x%llx", ses->Suid); - if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) { + if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) seq_puts(m, " encrypted"); - /* can help in debugging to show encryption type */ - if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM) - seq_puts(m, "(gcm256)"); - } if (ses->sign) seq_puts(m, " signed"); diff --git a/fs/smb/client/cifs_unicode.c b/fs/smb/client/cifs_unicode.c index 4cc6e0896fad..f8659d36793f 100644 --- a/fs/smb/client/cifs_unicode.c +++ b/fs/smb/client/cifs_unicode.c @@ -629,6 +629,9 @@ cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len, int len; __le16 *dst; + if (!src) + return NULL; + len = cifs_local_to_utf16_bytes(src, maxlen, cp); len += 2; /* NULL */ dst = kmalloc(len, GFP_KERNEL); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 1e64a4fb6af0..0fae95cf81c4 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -87,7 +87,7 @@ #define SMB_INTERFACE_POLL_INTERVAL 600 /* maximum number of PDUs in one compound */ -#define MAX_COMPOUND 7 +#define MAX_COMPOUND 10 /* * Default number of credits to keep available for SMB3. @@ -1882,9 +1882,12 @@ static inline bool is_replayable_error(int error) /* cifs_get_writable_file() flags */ -#define FIND_WR_ANY 0 -#define FIND_WR_FSUID_ONLY 1 -#define FIND_WR_WITH_DELETE 2 +enum cifs_writable_file_flags { + FIND_WR_ANY = 0U, + FIND_WR_FSUID_ONLY = (1U << 0), + FIND_WR_WITH_DELETE = (1U << 1), + FIND_WR_NO_PENDING_DELETE = (1U << 2), +}; #define MID_FREE 0 #define MID_REQUEST_ALLOCATED 1 @@ -2343,6 +2346,8 @@ struct smb2_compound_vars { struct kvec qi_iov; struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; + struct kvec unlink_iov[SMB2_SET_INFO_IOV_SIZE]; + struct kvec rename_iov[SMB2_SET_INFO_IOV_SIZE]; struct kvec close_iov; struct smb2_file_rename_info_hdr rename_info; struct smb2_file_link_info_hdr link_info; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 186e061068be..cb907e18cc35 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -998,7 +998,10 @@ int cifs_open(struct inode *inode, struct file *file) /* Get the cached handle as SMB2 close is deferred */ if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { - rc = cifs_get_writable_path(tcon, full_path, FIND_WR_FSUID_ONLY, &cfile); + rc = cifs_get_writable_path(tcon, full_path, + FIND_WR_FSUID_ONLY | + FIND_WR_NO_PENDING_DELETE, + &cfile); } else { rc = cifs_get_readable_path(tcon, full_path, &cfile); } @@ -2530,6 +2533,9 @@ refind_writable: continue; if (with_delete && !(open_file->fid.access & DELETE)) continue; + if ((flags & FIND_WR_NO_PENDING_DELETE) && + open_file->status_file_deleted) + continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { if (!open_file->invalidHandle) { /* found a good writable file */ @@ -2647,6 +2653,16 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, spin_unlock(&tcon->open_file_lock); free_dentry_path(page); *ret_file = find_readable_file(cinode, 0); + if (*ret_file) { + spin_lock(&cinode->open_file_lock); + if ((*ret_file)->status_file_deleted) { + spin_unlock(&cinode->open_file_lock); + cifsFileInfo_put(*ret_file); + *ret_file = NULL; + } else { + spin_unlock(&cinode->open_file_lock); + } + } return *ret_file ? 0 : -ENOENT; } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index fe453a4b3dc8..11d442e8b3d6 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1931,7 +1931,7 @@ cifs_drop_nlink(struct inode *inode) * but will return the EACCES to the caller. Note that the VFS does not call * unlink on negative dentries currently. */ -int cifs_unlink(struct inode *dir, struct dentry *dentry) +static int __cifs_unlink(struct inode *dir, struct dentry *dentry, bool sillyrename) { int rc = 0; unsigned int xid; @@ -2003,7 +2003,11 @@ retry_std_delete: goto psx_del_no_retry; } - rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry); + if (sillyrename || (server->vals->protocol_id > SMB10_PROT_ID && + d_is_positive(dentry) && d_count(dentry) > 2)) + rc = -EBUSY; + else + rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry); psx_del_no_retry: if (!rc) { @@ -2071,6 +2075,11 @@ unlink_out: return rc; } +int cifs_unlink(struct inode *dir, struct dentry *dentry) +{ + return __cifs_unlink(dir, dentry, false); +} + static int cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, const char *full_path, struct cifs_sb_info *cifs_sb, @@ -2358,14 +2367,16 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) rc = server->ops->rmdir(xid, tcon, full_path, cifs_sb); cifs_put_tlink(tlink); + cifsInode = CIFS_I(d_inode(direntry)); + if (!rc) { + set_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags); spin_lock(&d_inode(direntry)->i_lock); i_size_write(d_inode(direntry), 0); clear_nlink(d_inode(direntry)); spin_unlock(&d_inode(direntry)->i_lock); } - cifsInode = CIFS_I(d_inode(direntry)); /* force revalidate to go get info when needed */ cifsInode->time = 0; @@ -2458,8 +2469,11 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ do_rename_exit: - if (rc == 0) + if (rc == 0) { d_move(from_dentry, to_dentry); + /* Force a new lookup */ + d_drop(from_dentry); + } cifs_put_tlink(tlink); return rc; } @@ -2470,6 +2484,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, struct dentry *target_dentry, unsigned int flags) { const char *from_name, *to_name; + struct TCP_Server_Info *server; void *page1, *page2; struct cifs_sb_info *cifs_sb; struct tcon_link *tlink; @@ -2505,6 +2520,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, if (IS_ERR(tlink)) return PTR_ERR(tlink); tcon = tlink_tcon(tlink); + server = tcon->ses->server; page1 = alloc_dentry_path(); page2 = alloc_dentry_path(); @@ -2591,19 +2607,53 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, unlink_target: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - - /* Try unlinking the target dentry if it's not negative */ - if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) { - if (d_is_dir(target_dentry)) - tmprc = cifs_rmdir(target_dir, target_dentry); - else - tmprc = cifs_unlink(target_dir, target_dentry); - if (tmprc) - goto cifs_rename_exit; - rc = cifs_do_rename(xid, source_dentry, from_name, - target_dentry, to_name); - if (!rc) - rehash = false; + if (d_really_is_positive(target_dentry)) { + if (!rc) { + struct inode *inode = d_inode(target_dentry); + /* + * Samba and ksmbd servers allow renaming a target + * directory that is open, so make sure to update + * ->i_nlink and then mark it as delete pending. + */ + if (S_ISDIR(inode->i_mode)) { + drop_cached_dir_by_name(xid, tcon, to_name, cifs_sb); + spin_lock(&inode->i_lock); + i_size_write(inode, 0); + clear_nlink(inode); + spin_unlock(&inode->i_lock); + set_bit(CIFS_INO_DELETE_PENDING, &CIFS_I(inode)->flags); + CIFS_I(inode)->time = 0; /* force reval */ + inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + } + } else if (rc == -EACCES || rc == -EEXIST) { + /* + * Rename failed, possibly due to a busy target. + * Retry it by unliking the target first. + */ + if (d_is_dir(target_dentry)) { + tmprc = cifs_rmdir(target_dir, target_dentry); + } else { + tmprc = __cifs_unlink(target_dir, target_dentry, + server->vals->protocol_id > SMB10_PROT_ID); + } + if (tmprc) { + /* + * Some servers will return STATUS_ACCESS_DENIED + * or STATUS_DIRECTORY_NOT_EMPTY when failing to + * rename a non-empty directory. Make sure to + * propagate the appropriate error back to + * userspace. + */ + if (tmprc == -EEXIST || tmprc == -ENOTEMPTY) + rc = tmprc; + goto cifs_rename_exit; + } + rc = cifs_do_rename(xid, source_dentry, from_name, + target_dentry, to_name); + if (!rc) + rehash = false; + } } /* force revalidate to go get info when needed */ @@ -2629,6 +2679,8 @@ cifs_dentry_needs_reval(struct dentry *dentry) struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct cached_fid *cfid = NULL; + if (test_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags)) + return false; if (cifs_i->time == 0) return true; diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 7869cec58f52..10c84c095fe7 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -278,7 +278,7 @@ static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb, } /* - * For absolute symlinks it is not possible to determinate + * For absolute symlinks it is not possible to determine * if it should point to directory or file. */ if (symname[0] == '/') { diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 893a1ea8c000..a02d41d1ce4a 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -1005,7 +1005,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, rc = -EOPNOTSUPP; } - /* Fallback to SMB_COM_SETATTR command when absolutelty needed. */ + /* Fallback to SMB_COM_SETATTR command when absolutely needed. */ if (rc == -EOPNOTSUPP) { cifs_dbg(FYI, "calling SetInformation since SetPathInfo for attrs/times not supported by this server\n"); rc = SMBSetInformation(xid, tcon, full_path, @@ -1039,7 +1039,7 @@ set_via_filehandle: cifsFileInfo_put(open_file); /* - * Setting the read-only bit is not honered on non-NT servers when done + * Setting the read-only bit is not honored on non-NT servers when done * via open-semantics. So for setting it, use SMB_COM_SETATTR command. * This command works only after the file is closed, so use it only when * operation was called without the filehandle. diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h index 224495322a05..e56e4d402f13 100644 --- a/fs/smb/client/smb2glob.h +++ b/fs/smb/client/smb2glob.h @@ -30,10 +30,9 @@ enum smb2_compound_ops { SMB2_OP_QUERY_DIR, SMB2_OP_MKDIR, SMB2_OP_RENAME, - SMB2_OP_DELETE, SMB2_OP_HARDLINK, SMB2_OP_SET_EOF, - SMB2_OP_RMDIR, + SMB2_OP_UNLINK, SMB2_OP_POSIX_QUERY_INFO, SMB2_OP_SET_REPARSE, SMB2_OP_GET_REPARSE, diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 31c13fb5b85b..7cadc8ca4f55 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -346,9 +346,6 @@ replay_again: trace_smb3_posix_query_info_compound_enter(xid, tcon->tid, ses->Suid, full_path); break; - case SMB2_OP_DELETE: - trace_smb3_delete_enter(xid, tcon->tid, ses->Suid, full_path); - break; case SMB2_OP_MKDIR: /* * Directories are created through parameters in the @@ -356,23 +353,40 @@ replay_again: */ trace_smb3_mkdir_enter(xid, tcon->tid, ses->Suid, full_path); break; - case SMB2_OP_RMDIR: - rqst[num_rqst].rq_iov = &vars->si_iov[0]; + case SMB2_OP_UNLINK: + rqst[num_rqst].rq_iov = vars->unlink_iov; rqst[num_rqst].rq_nvec = 1; size[0] = 1; /* sizeof __u8 See MS-FSCC section 2.4.11 */ data[0] = &delete_pending[0]; - rc = SMB2_set_info_init(tcon, server, - &rqst[num_rqst], COMPOUND_FID, - COMPOUND_FID, current->tgid, - FILE_DISPOSITION_INFORMATION, - SMB2_O_INFO_FILE, 0, data, size); - if (rc) + if (cfile) { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + current->tgid, + FILE_DISPOSITION_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + } else { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + COMPOUND_FID, + COMPOUND_FID, + current->tgid, + FILE_DISPOSITION_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + } + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst++]); - trace_smb3_rmdir_enter(xid, tcon->tid, ses->Suid, full_path); + } + num_rqst++; + trace_smb3_unlink_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_SET_EOF: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -442,7 +456,7 @@ replay_again: ses->Suid, full_path); break; case SMB2_OP_RENAME: - rqst[num_rqst].rq_iov = &vars->si_iov[0]; + rqst[num_rqst].rq_iov = vars->rename_iov; rqst[num_rqst].rq_nvec = 2; len = in_iov[i].iov_len; @@ -732,19 +746,6 @@ finished: trace_smb3_posix_query_info_compound_done(xid, tcon->tid, ses->Suid); break; - case SMB2_OP_DELETE: - if (rc) - trace_smb3_delete_err(xid, tcon->tid, ses->Suid, rc); - else { - /* - * If dentry (hence, inode) is NULL, lease break is going to - * take care of degrading leases on handles for deleted files. - */ - if (inode) - cifs_mark_open_handles_for_deleted_file(inode, full_path); - trace_smb3_delete_done(xid, tcon->tid, ses->Suid); - } - break; case SMB2_OP_MKDIR: if (rc) trace_smb3_mkdir_err(xid, tcon->tid, ses->Suid, rc); @@ -765,11 +766,11 @@ finished: trace_smb3_rename_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; - case SMB2_OP_RMDIR: - if (rc) - trace_smb3_rmdir_err(xid, tcon->tid, ses->Suid, rc); + case SMB2_OP_UNLINK: + if (!rc) + trace_smb3_unlink_done(xid, tcon->tid, ses->Suid); else - trace_smb3_rmdir_done(xid, tcon->tid, ses->Suid); + trace_smb3_unlink_err(xid, tcon->tid, ses->Suid, rc); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_SET_EOF: @@ -1166,7 +1167,7 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, FILE_OPEN, CREATE_NOT_FILE, ACL_NO_MODE); return smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, NULL, - &(int){SMB2_OP_RMDIR}, 1, + &(int){SMB2_OP_UNLINK}, 1, NULL, NULL, NULL, NULL); } @@ -1175,20 +1176,29 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb, struct dentry *dentry) { struct cifs_open_parms oparms; + struct inode *inode = NULL; + int rc; - oparms = CIFS_OPARMS(cifs_sb, tcon, name, - DELETE, FILE_OPEN, - CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT, - ACL_NO_MODE); - int rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, - NULL, &(int){SMB2_OP_DELETE}, 1, - NULL, NULL, NULL, dentry); + if (dentry) + inode = d_inode(dentry); + + oparms = CIFS_OPARMS(cifs_sb, tcon, name, DELETE, + FILE_OPEN, OPEN_REPARSE_POINT, ACL_NO_MODE); + rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, + NULL, &(int){SMB2_OP_UNLINK}, + 1, NULL, NULL, NULL, dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease"); rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, - NULL, &(int){SMB2_OP_DELETE}, 1, - NULL, NULL, NULL, NULL); + NULL, &(int){SMB2_OP_UNLINK}, + 1, NULL, NULL, NULL, NULL); } + /* + * If dentry (hence, inode) is NULL, lease break is going to + * take care of degrading leases on handles for deleted files. + */ + if (!rc && inode) + cifs_mark_open_handles_for_deleted_file(inode, name); return rc; } @@ -1441,3 +1451,113 @@ out: cifs_free_open_info(&data); return rc; } + +static inline __le16 *utf16_smb2_path(struct cifs_sb_info *cifs_sb, + const char *name, size_t namelen) +{ + int len; + + if (*name == '\\' || + (cifs_sb_master_tlink(cifs_sb) && + cifs_sb_master_tcon(cifs_sb)->posix_extensions && *name == '/')) + name++; + return cifs_strndup_to_utf16(name, namelen, &len, + cifs_sb->local_nls, + cifs_remap(cifs_sb)); +} + +int smb2_rename_pending_delete(const char *full_path, + struct dentry *dentry, + const unsigned int xid) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(d_inode(dentry)->i_sb); + struct cifsInodeInfo *cinode = CIFS_I(d_inode(dentry)); + __le16 *utf16_path __free(kfree) = NULL; + __u32 co = file_create_options(dentry); + int cmds[] = { + SMB2_OP_SET_INFO, + SMB2_OP_RENAME, + SMB2_OP_UNLINK, + }; + const int num_cmds = ARRAY_SIZE(cmds); + char *to_name __free(kfree) = NULL; + __u32 attrs = cinode->cifsAttrs; + struct cifs_open_parms oparms; + static atomic_t sillycounter; + struct cifsFileInfo *cfile; + struct tcon_link *tlink; + struct cifs_tcon *tcon; + struct kvec iov[2]; + const char *ppath; + void *page; + size_t len; + int rc; + + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + + page = alloc_dentry_path(); + + ppath = build_path_from_dentry(dentry->d_parent, page); + if (IS_ERR(ppath)) { + rc = PTR_ERR(ppath); + goto out; + } + + len = strlen(ppath) + strlen("/.__smb1234") + 1; + to_name = kmalloc(len, GFP_KERNEL); + if (!to_name) { + rc = -ENOMEM; + goto out; + } + + scnprintf(to_name, len, "%s%c.__smb%04X", ppath, CIFS_DIR_SEP(cifs_sb), + atomic_inc_return(&sillycounter) & 0xffff); + + utf16_path = utf16_smb2_path(cifs_sb, to_name, len); + if (!utf16_path) { + rc = -ENOMEM; + goto out; + } + + drop_cached_dir_by_name(xid, tcon, full_path, cifs_sb); + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, + DELETE | FILE_WRITE_ATTRIBUTES, + FILE_OPEN, co, ACL_NO_MODE); + + attrs &= ~ATTR_READONLY; + if (!attrs) + attrs = ATTR_NORMAL; + if (d_inode(dentry)->i_nlink <= 1) + attrs |= ATTR_HIDDEN; + iov[0].iov_base = &(FILE_BASIC_INFO) { + .Attributes = cpu_to_le32(attrs), + }; + iov[0].iov_len = sizeof(FILE_BASIC_INFO); + iov[1].iov_base = utf16_path; + iov[1].iov_len = sizeof(*utf16_path) * UniStrlen((wchar_t *)utf16_path); + + cifs_get_writable_path(tcon, full_path, FIND_WR_WITH_DELETE, &cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov, + cmds, num_cmds, cfile, NULL, NULL, dentry); + if (rc == -EINVAL) { + cifs_dbg(FYI, "invalid lease key, resending request without lease\n"); + cifs_get_writable_path(tcon, full_path, + FIND_WR_WITH_DELETE, &cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov, + cmds, num_cmds, cfile, NULL, NULL, NULL); + } + if (!rc) { + set_bit(CIFS_INO_DELETE_PENDING, &cinode->flags); + } else { + cifs_tcon_dbg(FYI, "%s: failed to rename '%s' to '%s': %d\n", + __func__, full_path, to_name, rc); + rc = -EIO; + } +out: + cifs_put_tlink(tlink); + free_dentry_path(page); + return rc; +} diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index cddf273c14ae..89d933b4a8bc 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -614,6 +614,15 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) struct cifs_tcon *tcon; struct cifs_pending_open *open; + /* Trace receipt of lease break request from server */ + trace_smb3_lease_break_enter(le32_to_cpu(rsp->CurrentLeaseState), + le32_to_cpu(rsp->Flags), + le16_to_cpu(rsp->Epoch), + le32_to_cpu(rsp->hdr.Id.SyncId.TreeId), + le64_to_cpu(rsp->hdr.SessionId), + *((u64 *)rsp->LeaseKey), + *((u64 *)&rsp->LeaseKey[8])); + cifs_dbg(FYI, "Checking for lease break\n"); /* If server is a channel, select the primary channel */ @@ -660,10 +669,12 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) spin_unlock(&cifs_tcp_ses_lock); cifs_dbg(FYI, "Can not process lease break - no lease matched\n"); trace_smb3_lease_not_found(le32_to_cpu(rsp->CurrentLeaseState), - le32_to_cpu(rsp->hdr.Id.SyncId.TreeId), - le64_to_cpu(rsp->hdr.SessionId), - *((u64 *)rsp->LeaseKey), - *((u64 *)&rsp->LeaseKey[8])); + le32_to_cpu(rsp->Flags), + le16_to_cpu(rsp->Epoch), + le32_to_cpu(rsp->hdr.Id.SyncId.TreeId), + le64_to_cpu(rsp->hdr.SessionId), + *((u64 *)rsp->LeaseKey), + *((u64 *)&rsp->LeaseKey[8])); return false; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 94b1d7a395d5..e586f3f4b5c9 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2640,13 +2640,35 @@ smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst) } /* SMB headers in a compound are 8 byte aligned. */ - if (!IS_ALIGNED(len, 8)) { - num_padding = 8 - (len & 7); + if (IS_ALIGNED(len, 8)) + goto out; + + num_padding = 8 - (len & 7); + if (smb3_encryption_required(tcon)) { + int i; + + /* + * Flatten request into a single buffer with required padding as + * the encryption layer can't handle the padding iovs. + */ + for (i = 1; i < rqst->rq_nvec; i++) { + memcpy(rqst->rq_iov[0].iov_base + + rqst->rq_iov[0].iov_len, + rqst->rq_iov[i].iov_base, + rqst->rq_iov[i].iov_len); + rqst->rq_iov[0].iov_len += rqst->rq_iov[i].iov_len; + } + memset(rqst->rq_iov[0].iov_base + rqst->rq_iov[0].iov_len, + 0, num_padding); + rqst->rq_iov[0].iov_len += num_padding; + rqst->rq_nvec = 1; + } else { rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding; rqst->rq_iov[rqst->rq_nvec].iov_len = num_padding; rqst->rq_nvec++; - len += num_padding; } + len += num_padding; +out: shdr->NextCommand = cpu_to_le32(len); } @@ -5376,6 +5398,7 @@ struct smb_version_operations smb20_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; #endif /* CIFS_ALLOW_INSECURE_LEGACY */ @@ -5481,6 +5504,7 @@ struct smb_version_operations smb21_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; struct smb_version_operations smb30_operations = { @@ -5597,6 +5621,7 @@ struct smb_version_operations smb30_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; struct smb_version_operations smb311_operations = { @@ -5713,6 +5738,7 @@ struct smb_version_operations smb311_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 2df93a75e3b8..c3b9d3f6210f 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -6192,11 +6192,11 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, please_key_high = (__u64 *)(lease_key+8); if (rc) { cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE); - trace_smb3_lease_err(le32_to_cpu(lease_state), tcon->tid, + trace_smb3_lease_ack_err(le32_to_cpu(lease_state), tcon->tid, ses->Suid, *please_key_low, *please_key_high, rc); cifs_dbg(FYI, "Send error in Lease Break = %d\n", rc); } else - trace_smb3_lease_done(le32_to_cpu(lease_state), tcon->tid, + trace_smb3_lease_ack_done(le32_to_cpu(lease_state), tcon->tid, ses->Suid, *please_key_low, *please_key_high); return rc; diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 6e805ece6a7b..b3f1398c9f79 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -317,5 +317,8 @@ int posix_info_sid_size(const void *beg, const void *end); int smb2_make_nfs_node(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, const char *full_path, umode_t mode, dev_t dev); +int smb2_rename_pending_delete(const char *full_path, + struct dentry *dentry, + const unsigned int xid); #endif /* _SMB2PROTO_H */ diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 93e5b2bb9f28..fd650e2afc76 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -669,13 +669,12 @@ DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(posix_query_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(hardlink_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rename_enter); -DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rmdir_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(unlink_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_eof_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_reparse_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(get_reparse_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_wsl_ea_compound_enter); -DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(tdis_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mknod_enter); @@ -710,13 +709,12 @@ DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(posix_query_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(hardlink_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rename_done); -DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rmdir_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(unlink_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_eof_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_reparse_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(get_reparse_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_wsl_ea_compound_done); -DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(delete_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mkdir_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(tdis_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mknod_done); @@ -756,14 +754,13 @@ DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(posix_query_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(hardlink_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rename_err); -DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rmdir_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(unlink_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_eof_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_reparse_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(get_reparse_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_wsl_ea_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mkdir_err); -DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(delete_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(tdis_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mknod_err); @@ -1171,8 +1168,54 @@ DEFINE_EVENT(smb3_lease_done_class, smb3_##name, \ __u64 lease_key_high), \ TP_ARGS(lease_state, tid, sesid, lease_key_low, lease_key_high)) -DEFINE_SMB3_LEASE_DONE_EVENT(lease_done); -DEFINE_SMB3_LEASE_DONE_EVENT(lease_not_found); +DEFINE_SMB3_LEASE_DONE_EVENT(lease_ack_done); +/* Tracepoint when a lease break request is received/entered (includes epoch and flags) */ +DECLARE_EVENT_CLASS(smb3_lease_enter_class, + TP_PROTO(__u32 lease_state, + __u32 flags, + __u16 epoch, + __u32 tid, + __u64 sesid, + __u64 lease_key_low, + __u64 lease_key_high), + TP_ARGS(lease_state, flags, epoch, tid, sesid, lease_key_low, lease_key_high), + TP_STRUCT__entry( + __field(__u32, lease_state) + __field(__u32, flags) + __field(__u16, epoch) + __field(__u32, tid) + __field(__u64, sesid) + __field(__u64, lease_key_low) + __field(__u64, lease_key_high) + ), + TP_fast_assign( + __entry->lease_state = lease_state; + __entry->flags = flags; + __entry->epoch = epoch; + __entry->tid = tid; + __entry->sesid = sesid; + __entry->lease_key_low = lease_key_low; + __entry->lease_key_high = lease_key_high; + ), + TP_printk("sid=0x%llx tid=0x%x lease_key=0x%llx%llx lease_state=0x%x flags=0x%x epoch=%u", + __entry->sesid, __entry->tid, __entry->lease_key_high, + __entry->lease_key_low, __entry->lease_state, __entry->flags, __entry->epoch) +) + +#define DEFINE_SMB3_LEASE_ENTER_EVENT(name) \ +DEFINE_EVENT(smb3_lease_enter_class, smb3_##name, \ + TP_PROTO(__u32 lease_state, \ + __u32 flags, \ + __u16 epoch, \ + __u32 tid, \ + __u64 sesid, \ + __u64 lease_key_low, \ + __u64 lease_key_high), \ + TP_ARGS(lease_state, flags, epoch, tid, sesid, lease_key_low, lease_key_high)) + +DEFINE_SMB3_LEASE_ENTER_EVENT(lease_break_enter); +/* Lease not found: reuse lease_enter payload (includes epoch and flags) */ +DEFINE_SMB3_LEASE_ENTER_EVENT(lease_not_found); DECLARE_EVENT_CLASS(smb3_lease_err_class, TP_PROTO(__u32 lease_state, @@ -1213,7 +1256,7 @@ DEFINE_EVENT(smb3_lease_err_class, smb3_##name, \ int rc), \ TP_ARGS(lease_state, tid, sesid, lease_key_low, lease_key_high, rc)) -DEFINE_SMB3_LEASE_ERR_EVENT(lease_err); +DEFINE_SMB3_LEASE_ERR_EVENT(lease_ack_err); DECLARE_EVENT_CLASS(smb3_connect_class, TP_PROTO(char *hostname, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 0d92ce49aed7..a565fc36cee6 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2951,18 +2951,19 @@ int smb2_open(struct ksmbd_work *work) } ksmbd_debug(SMB, "converted name = %s\n", name); - if (strchr(name, ':')) { - if (!test_share_config_flag(work->tcon->share_conf, - KSMBD_SHARE_FLAG_STREAMS)) { - rc = -EBADF; - goto err_out2; - } - rc = parse_stream_name(name, &stream_name, &s_type); - if (rc < 0) - goto err_out2; - } if (posix_ctxt == false) { + if (strchr(name, ':')) { + if (!test_share_config_flag(work->tcon->share_conf, + KSMBD_SHARE_FLAG_STREAMS)) { + rc = -EBADF; + goto err_out2; + } + rc = parse_stream_name(name, &stream_name, &s_type); + if (rc < 0) + goto err_out2; + } + rc = ksmbd_validate_filename(name); if (rc < 0) goto err_out2; @@ -3443,6 +3444,8 @@ int smb2_open(struct ksmbd_work *work) fp->attrib_only = !(req->DesiredAccess & ~(FILE_READ_ATTRIBUTES_LE | FILE_WRITE_ATTRIBUTES_LE | FILE_SYNCHRONIZE_LE)); + fp->is_posix_ctxt = posix_ctxt; + /* fp should be searchable through ksmbd_inode.m_fp_list * after daccess, saccess, attrib_only, and stream are * initialized. @@ -5988,7 +5991,7 @@ static int smb2_rename(struct ksmbd_work *work, if (IS_ERR(new_name)) return PTR_ERR(new_name); - if (strchr(new_name, ':')) { + if (fp->is_posix_ctxt == false && strchr(new_name, ':')) { int s_type; char *xattr_stream_name, *stream_name = NULL; size_t xattr_stream_size; diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 5466aa8c39b1..6550bd9f002c 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -554,7 +554,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) case SMB_DIRECT_MSG_DATA_TRANSFER: { struct smb_direct_data_transfer *data_transfer = (struct smb_direct_data_transfer *)recvmsg->packet; - unsigned int data_length; + u32 remaining_data_length, data_offset, data_length; int avail_recvmsg_count, receive_credits; if (wc->byte_len < @@ -564,15 +564,25 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) return; } + remaining_data_length = le32_to_cpu(data_transfer->remaining_data_length); data_length = le32_to_cpu(data_transfer->data_length); - if (data_length) { - if (wc->byte_len < sizeof(struct smb_direct_data_transfer) + - (u64)data_length) { - put_recvmsg(t, recvmsg); - smb_direct_disconnect_rdma_connection(t); - return; - } + data_offset = le32_to_cpu(data_transfer->data_offset); + if (wc->byte_len < data_offset || + wc->byte_len < (u64)data_offset + data_length) { + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); + return; + } + if (remaining_data_length > t->max_fragmented_recv_size || + data_length > t->max_fragmented_recv_size || + (u64)remaining_data_length + (u64)data_length > + (u64)t->max_fragmented_recv_size) { + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); + return; + } + if (data_length) { if (t->full_packet_received) recvmsg->first_segment = true; @@ -1209,78 +1219,130 @@ static int smb_direct_writev(struct ksmbd_transport *t, bool need_invalidate, unsigned int remote_key) { struct smb_direct_transport *st = smb_trans_direct_transfort(t); - int remaining_data_length; - int start, i, j; - int max_iov_size = st->max_send_size - + size_t remaining_data_length; + size_t iov_idx; + size_t iov_ofs; + size_t max_iov_size = st->max_send_size - sizeof(struct smb_direct_data_transfer); int ret; - struct kvec vec; struct smb_direct_send_ctx send_ctx; + int error = 0; if (st->status != SMB_DIRECT_CS_CONNECTED) return -ENOTCONN; //FIXME: skip RFC1002 header.. + if (WARN_ON_ONCE(niovs <= 1 || iov[0].iov_len != 4)) + return -EINVAL; buflen -= 4; + iov_idx = 1; + iov_ofs = 0; remaining_data_length = buflen; ksmbd_debug(RDMA, "Sending smb (RDMA): smb_len=%u\n", buflen); smb_direct_send_ctx_init(st, &send_ctx, need_invalidate, remote_key); - start = i = 1; - buflen = 0; - while (true) { - buflen += iov[i].iov_len; - if (buflen > max_iov_size) { - if (i > start) { - remaining_data_length -= - (buflen - iov[i].iov_len); - ret = smb_direct_post_send_data(st, &send_ctx, - &iov[start], i - start, - remaining_data_length); - if (ret) + while (remaining_data_length) { + struct kvec vecs[SMB_DIRECT_MAX_SEND_SGES - 1]; /* minus smbdirect hdr */ + size_t possible_bytes = max_iov_size; + size_t possible_vecs; + size_t bytes = 0; + size_t nvecs = 0; + + /* + * For the last message remaining_data_length should be + * have been 0 already! + */ + if (WARN_ON_ONCE(iov_idx >= niovs)) { + error = -EINVAL; + goto done; + } + + /* + * We have 2 factors which limit the arguments we pass + * to smb_direct_post_send_data(): + * + * 1. The number of supported sges for the send, + * while one is reserved for the smbdirect header. + * And we currently need one SGE per page. + * 2. The number of negotiated payload bytes per send. + */ + possible_vecs = min_t(size_t, ARRAY_SIZE(vecs), niovs - iov_idx); + + while (iov_idx < niovs && possible_vecs && possible_bytes) { + struct kvec *v = &vecs[nvecs]; + int page_count; + + v->iov_base = ((u8 *)iov[iov_idx].iov_base) + iov_ofs; + v->iov_len = min_t(size_t, + iov[iov_idx].iov_len - iov_ofs, + possible_bytes); + page_count = get_buf_page_count(v->iov_base, v->iov_len); + if (page_count > possible_vecs) { + /* + * If the number of pages in the buffer + * is to much (because we currently require + * one SGE per page), we need to limit the + * length. + * + * We know possible_vecs is at least 1, + * so we always keep the first page. + * + * We need to calculate the number extra + * pages (epages) we can also keep. + * + * We calculate the number of bytes in the + * first page (fplen), this should never be + * larger than v->iov_len because page_count is + * at least 2, but adding a limitation feels + * better. + * + * Then we calculate the number of bytes (elen) + * we can keep for the extra pages. + */ + size_t epages = possible_vecs - 1; + size_t fpofs = offset_in_page(v->iov_base); + size_t fplen = min_t(size_t, PAGE_SIZE - fpofs, v->iov_len); + size_t elen = min_t(size_t, v->iov_len - fplen, epages*PAGE_SIZE); + + v->iov_len = fplen + elen; + page_count = get_buf_page_count(v->iov_base, v->iov_len); + if (WARN_ON_ONCE(page_count > possible_vecs)) { + /* + * Something went wrong in the above + * logic... + */ + error = -EINVAL; goto done; - } else { - /* iov[start] is too big, break it */ - int nvec = (buflen + max_iov_size - 1) / - max_iov_size; - - for (j = 0; j < nvec; j++) { - vec.iov_base = - (char *)iov[start].iov_base + - j * max_iov_size; - vec.iov_len = - min_t(int, max_iov_size, - buflen - max_iov_size * j); - remaining_data_length -= vec.iov_len; - ret = smb_direct_post_send_data(st, &send_ctx, &vec, 1, - remaining_data_length); - if (ret) - goto done; } - i++; - if (i == niovs) - break; } - start = i; - buflen = 0; - } else { - i++; - if (i == niovs) { - /* send out all remaining vecs */ - remaining_data_length -= buflen; - ret = smb_direct_post_send_data(st, &send_ctx, - &iov[start], i - start, - remaining_data_length); - if (ret) - goto done; - break; + possible_vecs -= page_count; + nvecs += 1; + possible_bytes -= v->iov_len; + bytes += v->iov_len; + + iov_ofs += v->iov_len; + if (iov_ofs >= iov[iov_idx].iov_len) { + iov_idx += 1; + iov_ofs = 0; } } + + remaining_data_length -= bytes; + + ret = smb_direct_post_send_data(st, &send_ctx, + vecs, nvecs, + remaining_data_length); + if (unlikely(ret)) { + error = ret; + goto done; + } } done: ret = smb_direct_flush_send_list(st, &send_ctx, true); + if (unlikely(!ret && error)) + ret = error; /* * As an optimization, we don't wait for individual I/O to finish @@ -1744,6 +1806,11 @@ static int smb_direct_init_params(struct smb_direct_transport *t, return -EINVAL; } + if (device->attrs.max_send_sge < SMB_DIRECT_MAX_SEND_SGES) { + pr_err("warning: device max_send_sge = %d too small\n", + device->attrs.max_send_sge); + return -EINVAL; + } if (device->attrs.max_recv_sge < SMB_DIRECT_MAX_RECV_SGES) { pr_err("warning: device max_recv_sge = %d too small\n", device->attrs.max_recv_sge); @@ -1767,7 +1834,7 @@ static int smb_direct_init_params(struct smb_direct_transport *t, cap->max_send_wr = max_send_wrs; cap->max_recv_wr = t->recv_credit_max; - cap->max_send_sge = max_sge_per_wr; + cap->max_send_sge = SMB_DIRECT_MAX_SEND_SGES; cap->max_recv_sge = SMB_DIRECT_MAX_RECV_SGES; cap->max_inline_data = 0; cap->max_rdma_ctxs = t->max_rw_credits; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 0708155b5caf..78b506c5ef03 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -112,6 +112,8 @@ struct ksmbd_file { bool is_durable; bool is_persistent; bool is_resilient; + + bool is_posix_ctxt; }; static inline void set_ctx_actor(struct dir_context *ctx, diff --git a/include/linux/cpu.h b/include/linux/cpu.h index b91b993f58ee..487b3bf2e1ea 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -83,6 +83,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev, extern ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h index 7fa1eb3cc823..61d50571ad88 100644 --- a/include/linux/energy_model.h +++ b/include/linux/energy_model.h @@ -171,6 +171,9 @@ int em_dev_update_perf_domain(struct device *dev, int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, const struct em_data_callback *cb, const cpumask_t *cpus, bool microwatts); +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts); void em_dev_unregister_perf_domain(struct device *dev); struct em_perf_table *em_table_alloc(struct em_perf_domain *pd); void em_table_free(struct em_perf_table *table); @@ -350,6 +353,13 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, { return -EINVAL; } +static inline +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts) +{ + return -EINVAL; +} static inline void em_dev_unregister_perf_domain(struct device *dev) { } diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index de5bd76a400c..d7d757e72554 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -856,8 +856,8 @@ struct kernel_ethtool_ts_info { enum hwtstamp_provider_qualifier phc_qualifier; enum hwtstamp_source phc_source; int phc_phyindex; - enum hwtstamp_tx_types tx_types; - enum hwtstamp_rx_filters rx_filters; + u32 tx_types; + u32 rx_filters; }; /** diff --git a/include/linux/fs.h b/include/linux/fs.h index d7ab4f96d705..601d036a6c78 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -149,7 +149,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* FMODE_* bit 13 */ +/* Supports IOCB_HAS_METADATA */ +#define FMODE_HAS_METADATA ((__force fmode_t)(1 << 13)) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) diff --git a/include/linux/phy.h b/include/linux/phy.h index 4c2b8b6e7187..bb45787d8684 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -169,6 +169,11 @@ static inline bool phy_interface_empty(const unsigned long *intf) return bitmap_empty(intf, PHY_INTERFACE_MODE_MAX); } +static inline unsigned int phy_interface_weight(const unsigned long *intf) +{ + return bitmap_weight(intf, PHY_INTERFACE_MODE_MAX); +} + static inline void phy_interface_and(unsigned long *dst, const unsigned long *a, const unsigned long *b) { diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index c27aac67cb3f..b8ae89ea28ab 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -76,6 +76,7 @@ struct tk_read_base { * @cs_was_changed_seq: The sequence number of clocksource change events * @clock_valid: Indicator for valid clock * @monotonic_to_boot: CLOCK_MONOTONIC to CLOCK_BOOTTIME offset + * @monotonic_to_aux: CLOCK_MONOTONIC to CLOCK_AUX offset * @cycle_interval: Number of clock cycles in one NTP interval * @xtime_interval: Number of clock shifted nano seconds in one NTP * interval. @@ -117,6 +118,9 @@ struct tk_read_base { * @offs_aux is used by the auxiliary timekeepers which do not utilize any * of the regular timekeeper offset fields. * + * @monotonic_to_aux is a timespec64 representation of @offs_aux to + * accelerate the VDSO update for CLOCK_AUX. + * * The cacheline ordering of the structure is optimized for in kernel usage of * the ktime_get() and ktime_get_ts64() family of time accessors. Struct * timekeeper is prepended in the core timekeeping code with a sequence count, @@ -159,7 +163,10 @@ struct timekeeper { u8 cs_was_changed_seq; u8 clock_valid; - struct timespec64 monotonic_to_boot; + union { + struct timespec64 monotonic_to_boot; + struct timespec64 monotonic_to_aux; + }; u64 cycle_interval; u64 xtime_interval; diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 891e43a01bdc..3faa80f5d801 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1912,7 +1912,6 @@ struct nftables_pernet { struct mutex commit_mutex; u64 table_handle; u64 tstamp; - unsigned int base_seq; unsigned int gc_seq; u8 validate_state; struct work_struct destroy_work; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 6c2f483d9828..656e784714f3 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -109,17 +109,11 @@ nft_hash_lookup_fast(const struct net *net, const struct nft_set *set, const struct nft_set_ext * nft_hash_lookup(const struct net *net, const struct nft_set *set, const u32 *key); +#endif + const struct nft_set_ext * nft_set_do_lookup(const struct net *net, const struct nft_set *set, const u32 *key); -#else -static inline const struct nft_set_ext * -nft_set_do_lookup(const struct net *net, const struct nft_set *set, - const u32 *key) -{ - return set->ops->lookup(net, set, key); -} -#endif /* called from nft_pipapo_avx2.c */ const struct nft_set_ext * diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h index cc8060c017d5..99dd166c5d07 100644 --- a/include/net/netns/nftables.h +++ b/include/net/netns/nftables.h @@ -3,6 +3,7 @@ #define _NETNS_NFTABLES_H_ struct netns_nftables { + unsigned int base_seq; u8 gencursor; }; diff --git a/include/net/sock.h b/include/net/sock.h index c8a4b283df6f..fb13322a11fc 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -285,6 +285,7 @@ struct sk_filter; * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner + * @sk_ino: inode number (zero if orphaned) * @sk_prefer_busy_poll: prefer busypolling over softirq processing * @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting @@ -518,6 +519,7 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; + unsigned long sk_ino; spinlock_t sk_peer_lock; int sk_bind_phc; struct pid *sk_peer_pid; @@ -2056,6 +2058,10 @@ static inline int sk_rx_queue_get(const struct sock *sk) static inline void sk_set_socket(struct sock *sk, struct socket *sock) { sk->sk_socket = sock; + if (sock) { + WRITE_ONCE(sk->sk_uid, SOCK_INODE(sock)->i_uid); + WRITE_ONCE(sk->sk_ino, SOCK_INODE(sock)->i_ino); + } } static inline wait_queue_head_t *sk_sleep(struct sock *sk) @@ -2077,6 +2083,7 @@ static inline void sock_orphan(struct sock *sk) sk_set_socket(sk, NULL); sk->sk_wq = NULL; /* Note: sk_uid is unchanged. */ + WRITE_ONCE(sk->sk_ino, 0); write_unlock_bh(&sk->sk_callback_lock); } @@ -2087,20 +2094,22 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) rcu_assign_pointer(sk->sk_wq, &parent->wq); parent->sk = sk; sk_set_socket(sk, parent); - WRITE_ONCE(sk->sk_uid, SOCK_INODE(parent)->i_uid); security_sock_graft(sk, parent); write_unlock_bh(&sk->sk_callback_lock); } +static inline unsigned long sock_i_ino(const struct sock *sk) +{ + /* Paired with WRITE_ONCE() in sock_graft() and sock_orphan() */ + return READ_ONCE(sk->sk_ino); +} + static inline kuid_t sk_uid(const struct sock *sk) { /* Paired with WRITE_ONCE() in sockfs_setattr() */ return READ_ONCE(sk->sk_uid); } -unsigned long __sock_i_ino(struct sock *sk); -unsigned long sock_i_ino(struct sock *sk); - static inline kuid_t sock_net_uid(const struct net *net, const struct sock *sk) { return sk ? sk_uid(sk) : make_kuid(net->user_ns, 0); diff --git a/include/pcmcia/ss.h b/include/pcmcia/ss.h index 7cf7dbbfa131..89aed99bfeae 100644 --- a/include/pcmcia/ss.h +++ b/include/pcmcia/ss.h @@ -227,12 +227,8 @@ struct pcmcia_socket { /* socket drivers must define the resource operations type they use. There - * are three options: + * are two options: * - pccard_static_ops iomem and ioport areas are assigned statically - * - pccard_iodyn_ops iomem areas is assigned statically, ioport - * areas dynamically - * If this option is selected, use - * "select PCCARD_IODYN" in Kconfig. * - pccard_nonstatic_ops iomem and ioport areas are assigned dynamically. * If this option is selected, use * "select PCCARD_NONSTATIC" in Kconfig. @@ -240,13 +236,11 @@ struct pcmcia_socket { */ extern struct pccard_resource_ops pccard_static_ops; #if defined(CONFIG_PCMCIA) || defined(CONFIG_PCMCIA_MODULE) -extern struct pccard_resource_ops pccard_iodyn_ops; extern struct pccard_resource_ops pccard_nonstatic_ops; #else /* If PCMCIA is not used, but only CARDBUS, these functions are not used * at all. Therefore, do not use the large (240K!) rsrc_nonstatic module */ -#define pccard_iodyn_ops pccard_static_ops #define pccard_nonstatic_ops pccard_static_ops #endif diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 2beb30be2c5f..8e0eb832bc01 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -1784,10 +1784,12 @@ enum nft_synproxy_attributes { * enum nft_device_attributes - nf_tables device netlink attributes * * @NFTA_DEVICE_NAME: name of this device (NLA_STRING) + * @NFTA_DEVICE_PREFIX: device name prefix, a simple wildcard (NLA_STRING) */ enum nft_devices_attributes { NFTA_DEVICE_UNSPEC, NFTA_DEVICE_NAME, + NFTA_DEVICE_PREFIX, __NFTA_DEVICE_MAX }; #define NFTA_DEVICE_MAX (__NFTA_DEVICE_MAX - 1) diff --git a/init/Kconfig b/init/Kconfig index d811cad02a75..e3eb63eadc87 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -146,6 +146,9 @@ config RUSTC_HAS_UNNECESSARY_TRANSMUTES config RUSTC_HAS_FILE_WITH_NUL def_bool RUSTC_VERSION >= 108900 +config RUSTC_HAS_FILE_AS_C_STR + def_bool RUSTC_VERSION >= 109100 + config PAHOLE_VERSION int default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE)) diff --git a/io_uring/rw.c b/io_uring/rw.c index 52a5b950b2e5..af5a54b5db12 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -886,6 +886,9 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) if (req->flags & REQ_F_HAS_METADATA) { struct io_async_rw *io = req->async_data; + if (!(file->f_mode & FMODE_HAS_METADATA)) + return -EINVAL; + /* * We have a union of meta fields with wpq used for buffered-io * in io_async_rw, so fail it here. diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index e3f42018ed46..f7708fe2c457 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1326,7 +1326,7 @@ int audit_compare_dname_path(const struct qstr *dname, const char *path, int par /* handle trailing slashes */ pathlen -= parentlen; - while (p[pathlen - 1] == '/') + while (pathlen > 0 && p[pathlen - 1] == '/') pathlen--; if (pathlen != dlen) diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 269c04a24664..f6cf8c2af5f7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -62,3 +62,4 @@ CFLAGS_REMOVE_bpf_lru_list.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_queue_stack_maps.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_lpm_trie.o = $(CC_FLAGS_FTRACE) CFLAGS_REMOVE_ringbuf.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rqspinlock.o = $(CC_FLAGS_FTRACE) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 5d1650af899d..e4568d44e827 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2366,8 +2366,7 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx, const struct bpf_insn *insn) { /* If this handler ever gets executed, then BPF_JIT_ALWAYS_ON - * is not working properly, or interpreter is being used when - * prog->jit_requested is not 0, so warn about it! + * is not working properly, so warn about it! */ WARN_ON_ONCE(1); return 0; @@ -2468,8 +2467,9 @@ out: return ret; } -static void bpf_prog_select_func(struct bpf_prog *fp) +static bool bpf_prog_select_interpreter(struct bpf_prog *fp) { + bool select_interpreter = false; #ifndef CONFIG_BPF_JIT_ALWAYS_ON u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1); u32 idx = (round_up(stack_depth, 32) / 32) - 1; @@ -2478,15 +2478,16 @@ static void bpf_prog_select_func(struct bpf_prog *fp) * But for non-JITed programs, we don't need bpf_func, so no bounds * check needed. */ - if (!fp->jit_requested && - !WARN_ON_ONCE(idx >= ARRAY_SIZE(interpreters))) { + if (idx < ARRAY_SIZE(interpreters)) { fp->bpf_func = interpreters[idx]; + select_interpreter = true; } else { fp->bpf_func = __bpf_prog_ret0_warn; } #else fp->bpf_func = __bpf_prog_ret0_warn; #endif + return select_interpreter; } /** @@ -2505,7 +2506,7 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) /* In case of BPF to BPF calls, verifier did all the prep * work with regards to JITing, etc. */ - bool jit_needed = fp->jit_requested; + bool jit_needed = false; if (fp->bpf_func) goto finalize; @@ -2514,7 +2515,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err) bpf_prog_has_kfunc_call(fp)) jit_needed = true; - bpf_prog_select_func(fp); + if (!bpf_prog_select_interpreter(fp)) + jit_needed = true; /* eBPF JITs can rewrite the program in case constant * blinding is active. However, in case of error during @@ -3024,7 +3026,10 @@ EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { - .func = NULL, + /* func is unused for tail_call, we set it to pass the + * get_helper_proto check + */ + .func = BPF_PTR_POISON, .gpl_only = false, .ret_type = RET_VOID, .arg1_type = ARG_PTR_TO_CTX, diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index b2b7b8ec2c2a..c46360b27871 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -186,7 +186,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, struct xdp_buff xdp; int i, nframes = 0; - xdp_set_return_frame_no_direct(); xdp.rxq = &rxq; for (i = 0; i < n; i++) { @@ -231,7 +230,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, } } - xdp_clear_return_frame_no_direct(); stats->pass += nframes; return nframes; @@ -255,6 +253,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, rcu_read_lock(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); + xdp_set_return_frame_no_direct(); ret->xdp_n = cpu_map_bpf_prog_run_xdp(rcpu, frames, ret->xdp_n, stats); if (unlikely(ret->skb_n)) @@ -264,6 +263,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames, if (stats->redirect) xdp_do_flush(); + xdp_clear_return_frame_no_direct(); bpf_net_ctx_clear(bpf_net_ctx); rcu_read_unlock(); diff --git a/kernel/bpf/crypto.c b/kernel/bpf/crypto.c index 94854cd9c4cc..83c4d9943084 100644 --- a/kernel/bpf/crypto.c +++ b/kernel/bpf/crypto.c @@ -278,7 +278,7 @@ static int bpf_crypto_crypt(const struct bpf_crypto_ctx *ctx, siv_len = siv ? __bpf_dynptr_size(siv) : 0; src_len = __bpf_dynptr_size(src); dst_len = __bpf_dynptr_size(dst); - if (!src_len || !dst_len) + if (!src_len || !dst_len || src_len > dst_len) return -EINVAL; if (siv_len != ctx->siv_len) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6b4877e85a68..8af62cb243d9 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1274,8 +1274,11 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u goto out; } - /* allocate hrtimer via map_kmalloc to use memcg accounting */ - cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, map->numa_node); + /* Allocate via bpf_map_kmalloc_node() for memcg accounting. Until + * kmalloc_nolock() is available, avoid locking issues by using + * __GFP_HIGH (GFP_ATOMIC & ~__GFP_RECLAIM). + */ + cb = bpf_map_kmalloc_node(map, size, __GFP_HIGH, map->numa_node); if (!cb) { ret = -ENOMEM; goto out; @@ -3664,10 +3667,17 @@ __bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len guard(pagefault)(); for (i = 0; i < XATTR_SIZE_MAX; i++) { - for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) { + for (j = 0; i + j <= len && j < XATTR_SIZE_MAX; j++) { __get_kernel_nofault(&c2, s2__ign + j, char, err_out); if (c2 == '\0') return i; + /* + * We allow reading an extra byte from s2 (note the + * `i + j <= len` above) to cover the case when s2 is + * a suffix of the first len chars of s1. + */ + if (i + j == len) + break; __get_kernel_nofault(&c1, s1__ign + j, char, err_out); if (c1 == '\0') return -ENOENT; diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c index 5ab354d55d82..a00561b1d3e5 100644 --- a/kernel/bpf/rqspinlock.c +++ b/kernel/bpf/rqspinlock.c @@ -471,7 +471,7 @@ queue: * any MCS node. This is not the most elegant solution, but is * simple enough. */ - if (unlikely(idx >= _Q_MAX_NODES)) { + if (unlikely(idx >= _Q_MAX_NODES || in_nmi())) { lockevent_inc(lock_no_node); RES_RESET_TIMEOUT(ts, RES_DEF_TIMEOUT); while (!queued_spin_trylock(lock)) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c4f69a9e9af6..9fb1f957a093 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8547,6 +8547,10 @@ static int process_timer_func(struct bpf_verifier_env *env, int regno, verifier_bug(env, "Two map pointers in a timer helper"); return -EFAULT; } + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + verbose(env, "bpf_timer cannot be used for PREEMPT_RT.\n"); + return -EOPNOTSUPP; + } meta->map_uid = reg->map_uid; meta->map_ptr = map; return 0; @@ -11354,7 +11358,7 @@ static int get_helper_proto(struct bpf_verifier_env *env, int func_id, return -EINVAL; *ptr = env->ops->get_func_proto(func_id, env->prog); - return *ptr ? 0 : -EINVAL; + return *ptr && (*ptr)->func ? 0 : -EINVAL; } static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 312c6a8b55bb..77d02f87f3f1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -126,8 +126,31 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem); * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. + * + * A cgroup destruction should enqueue work sequentially to: + * cgroup_offline_wq: use for css offline work + * cgroup_release_wq: use for css release work + * cgroup_free_wq: use for free work + * + * Rationale for using separate workqueues: + * The cgroup root free work may depend on completion of other css offline + * operations. If all tasks were enqueued to a single workqueue, this could + * create a deadlock scenario where: + * - Free work waits for other css offline work to complete. + * - But other css offline work is queued after free work in the same queue. + * + * Example deadlock scenario with single workqueue (cgroup_destroy_wq): + * 1. umount net_prio + * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx) + * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx) + * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline. + * 5. net_prio root destruction blocks waiting for perf_event CSS A offline, + * which can never complete as it's behind in the same queue and + * workqueue's max_active is 1. */ -static struct workqueue_struct *cgroup_destroy_wq; +static struct workqueue_struct *cgroup_offline_wq; +static struct workqueue_struct *cgroup_release_wq; +static struct workqueue_struct *cgroup_free_wq; /* generate an array of cgroup subsystem pointers */ #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, @@ -4159,6 +4182,7 @@ static void cgroup_file_release(struct kernfs_open_file *of) cft->release(of); put_cgroup_ns(ctx->ns); kfree(ctx); + of->priv = NULL; } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, @@ -5558,7 +5582,7 @@ static void css_release_work_fn(struct work_struct *work) cgroup_unlock(); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); - queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); + queue_rcu_work(cgroup_free_wq, &css->destroy_rwork); } static void css_release(struct percpu_ref *ref) @@ -5567,7 +5591,7 @@ static void css_release(struct percpu_ref *ref) container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_release_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + queue_work(cgroup_release_wq, &css->destroy_work); } static void init_and_link_css(struct cgroup_subsys_state *css, @@ -5701,7 +5725,7 @@ err_list_del: list_del_rcu(&css->sibling); err_free_css: INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); - queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); + queue_rcu_work(cgroup_free_wq, &css->destroy_rwork); return ERR_PTR(err); } @@ -5939,7 +5963,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref) if (atomic_dec_and_test(&css->online_cnt)) { INIT_WORK(&css->destroy_work, css_killed_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + queue_work(cgroup_offline_wq, &css->destroy_work); } } @@ -6325,8 +6349,14 @@ static int __init cgroup_wq_init(void) * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ - cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); - BUG_ON(!cgroup_destroy_wq); + cgroup_offline_wq = alloc_workqueue("cgroup_offline", 0, 1); + BUG_ON(!cgroup_offline_wq); + + cgroup_release_wq = alloc_workqueue("cgroup_release", 0, 1); + BUG_ON(!cgroup_release_wq); + + cgroup_free_wq = alloc_workqueue("cgroup_free", 0, 1); + BUG_ON(!cgroup_free_wq); return 0; } core_initcall(cgroup_wq_init); diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c index e43c6de2bce4..b82399437db0 100644 --- a/kernel/dma/debug.c +++ b/kernel/dma/debug.c @@ -39,6 +39,7 @@ enum { dma_debug_sg, dma_debug_coherent, dma_debug_resource, + dma_debug_noncoherent, }; enum map_err_types { @@ -141,6 +142,7 @@ static const char *type2name[] = { [dma_debug_sg] = "scatter-gather", [dma_debug_coherent] = "coherent", [dma_debug_resource] = "resource", + [dma_debug_noncoherent] = "noncoherent", }; static const char *dir2name[] = { @@ -993,7 +995,8 @@ static void check_unmap(struct dma_debug_entry *ref) "[mapped as %s] [unmapped as %s]\n", ref->dev_addr, ref->size, type2name[entry->type], type2name[ref->type]); - } else if (entry->type == dma_debug_coherent && + } else if ((entry->type == dma_debug_coherent || + entry->type == dma_debug_noncoherent) && ref->paddr != entry->paddr) { err_printk(ref->dev, entry, "device driver frees " "DMA memory with different CPU address " @@ -1581,6 +1584,49 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, } } +void debug_dma_alloc_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr, + unsigned long attrs) +{ + struct dma_debug_entry *entry; + + if (unlikely(dma_debug_disabled())) + return; + + entry = dma_entry_alloc(); + if (!entry) + return; + + entry->type = dma_debug_noncoherent; + entry->dev = dev; + entry->paddr = page_to_phys(page); + entry->size = size; + entry->dev_addr = dma_addr; + entry->direction = direction; + + add_dma_entry(entry, attrs); +} + +void debug_dma_free_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr) +{ + struct dma_debug_entry ref = { + .type = dma_debug_noncoherent, + .dev = dev, + .paddr = page_to_phys(page), + .dev_addr = dma_addr, + .size = size, + .direction = direction, + }; + + if (unlikely(dma_debug_disabled())) + return; + + check_unmap(&ref); +} + static int __init dma_debug_driver_setup(char *str) { int i; diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h index f525197d3cae..48757ca13f31 100644 --- a/kernel/dma/debug.h +++ b/kernel/dma/debug.h @@ -54,6 +54,13 @@ extern void debug_dma_sync_sg_for_cpu(struct device *dev, extern void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems, int direction); +extern void debug_dma_alloc_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr, + unsigned long attrs); +extern void debug_dma_free_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr); #else /* CONFIG_DMA_API_DEBUG */ static inline void debug_dma_map_page(struct device *dev, struct page *page, size_t offset, size_t size, @@ -126,5 +133,18 @@ static inline void debug_dma_sync_sg_for_device(struct device *dev, int nelems, int direction) { } + +static inline void debug_dma_alloc_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr, + unsigned long attrs) +{ +} + +static inline void debug_dma_free_pages(struct device *dev, struct page *page, + size_t size, int direction, + dma_addr_t dma_addr) +{ +} #endif /* CONFIG_DMA_API_DEBUG */ #endif /* _KERNEL_DMA_DEBUG_H */ diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 107e4a4d251d..56de28a3b179 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -712,7 +712,7 @@ struct page *dma_alloc_pages(struct device *dev, size_t size, if (page) { trace_dma_alloc_pages(dev, page_to_virt(page), *dma_handle, size, dir, gfp, 0); - debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0); + debug_dma_alloc_pages(dev, page, size, dir, *dma_handle, 0); } else { trace_dma_alloc_pages(dev, NULL, 0, size, dir, gfp, 0); } @@ -738,7 +738,7 @@ void dma_free_pages(struct device *dev, size_t size, struct page *page, dma_addr_t dma_handle, enum dma_data_direction dir) { trace_dma_free_pages(dev, page_to_virt(page), dma_handle, size, dir, 0); - debug_dma_unmap_page(dev, dma_handle, size, dir); + debug_dma_free_pages(dev, page, size, dir, dma_handle); __dma_free_pages(dev, size, page, dma_handle, dir); } EXPORT_SYMBOL_GPL(dma_free_pages); diff --git a/kernel/events/core.c b/kernel/events/core.c index 872122e074e5..820127536e62 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10330,6 +10330,7 @@ static int __perf_event_overflow(struct perf_event *event, ret = 1; event->pending_kill = POLL_HUP; perf_event_disable_inatomic(event); + event->pmu->stop(event, 0); } if (event->attr.sigtrap) { diff --git a/kernel/fork.c b/kernel/fork.c index af673856499d..c4ada32598bd 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -689,7 +689,6 @@ void __mmdrop(struct mm_struct *mm) mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); - futex_hash_free(mm); free_mm(mm); } @@ -1138,6 +1137,7 @@ static inline void __mmput(struct mm_struct *mm) if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); + futex_hash_free(mm); mmdrop(mm); } diff --git a/kernel/futex/core.c b/kernel/futex/core.c index d9bb5567af0c..125804fbb5cb 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -1722,12 +1722,9 @@ int futex_mm_init(struct mm_struct *mm) RCU_INIT_POINTER(mm->futex_phash, NULL); mm->futex_phash_new = NULL; /* futex-ref */ + mm->futex_ref = NULL; atomic_long_set(&mm->futex_atomic, 0); mm->futex_batches = get_state_synchronize_rcu(); - mm->futex_ref = alloc_percpu(unsigned int); - if (!mm->futex_ref) - return -ENOMEM; - this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */ return 0; } @@ -1801,6 +1798,17 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags) } } + if (!mm->futex_ref) { + /* + * This will always be allocated by the first thread and + * therefore requires no locking. + */ + mm->futex_ref = alloc_percpu(unsigned int); + if (!mm->futex_ref) + return -ENOMEM; + this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */ + } + fph = kvzalloc(struct_size(fph, queues, hash_slots), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!fph) diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index ea7995a25780..8df55397414a 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -553,6 +553,30 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, const struct em_data_callback *cb, const cpumask_t *cpus, bool microwatts) { + int ret = em_dev_register_pd_no_update(dev, nr_states, cb, cpus, microwatts); + + if (_is_cpu_device(dev)) + em_check_capacity_update(); + + return ret; +} +EXPORT_SYMBOL_GPL(em_dev_register_perf_domain); + +/** + * em_dev_register_pd_no_update() - Register a perf domain for a device + * @dev : Device to register the PD for + * @nr_states : Number of performance states in the new PD + * @cb : Callback functions for populating the energy model + * @cpus : CPUs to include in the new PD (mandatory if @dev is a CPU device) + * @microwatts : Whether or not the power values in the EM will be in uW + * + * Like em_dev_register_perf_domain(), but does not trigger a CPU capacity + * update after registering the PD, even if @dev is a CPU device. + */ +int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states, + const struct em_data_callback *cb, + const cpumask_t *cpus, bool microwatts) +{ struct em_perf_table *em_table; unsigned long cap, prev_cap = 0; unsigned long flags = 0; @@ -636,12 +660,9 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, unlock: mutex_unlock(&em_pd_mutex); - if (_is_cpu_device(dev)) - em_check_capacity_update(); - return ret; } -EXPORT_SYMBOL_GPL(em_dev_register_perf_domain); +EXPORT_SYMBOL_GPL(em_dev_register_pd_no_update); /** * em_dev_unregister_perf_domain() - Unregister Energy Model (EM) for a device diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 1f1f30cca573..2f66ab453823 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -449,6 +449,7 @@ int hibernation_snapshot(int platform_mode) shrink_shmem_memory(); console_suspend_all(); + pm_restrict_gfp_mask(); error = dpm_suspend(PMSG_FREEZE); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index be00629f0ba4..ccba6fc3c3fe 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9551,7 +9551,7 @@ static unsigned long tg_weight(struct task_group *tg) #ifdef CONFIG_FAIR_GROUP_SCHED return scale_load_down(tg->shares); #else - return sched_weight_from_cgroup(tg->scx_weight); + return sched_weight_from_cgroup(tg->scx.weight); #endif } diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index 4ae32ef179dd..088ceff38c8a 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -6788,12 +6788,8 @@ __bpf_kfunc u32 scx_bpf_reenqueue_local(void) * CPUs disagree, they use %ENQUEUE_RESTORE which is bypassed to * the current local DSQ for running tasks and thus are not * visible to the BPF scheduler. - * - * Also skip re-enqueueing tasks that can only run on this - * CPU, as they would just be re-added to the same local - * DSQ without any benefit. */ - if (p->migration_pending || is_migration_disabled(p) || p->nr_cpus_allowed == 1) + if (p->migration_pending) continue; dispatch_dequeue(rq, p); diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 977e133bb8a4..6e2f54169e66 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2201,6 +2201,8 @@ int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) goto unlock; hop_masks = bsearch(&k, k.masks, sched_domains_numa_levels, sizeof(k.masks[0]), hop_cmp); + if (!hop_masks) + goto unlock; hop = hop_masks - k.masks; ret = hop ? diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 30899a8cc52c..e8c479329282 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -787,10 +787,10 @@ static void retrigger_next_event(void *arg) * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. + * + * In periodic low resolution mode, the next softirq expiration + * must also be updated. */ - if (!hrtimer_hres_active(base) && !tick_nohz_active) - return; - raw_spin_lock(&base->lock); hrtimer_update_base(base); if (hrtimer_hres_active(base)) @@ -2295,11 +2295,6 @@ int hrtimers_cpu_dying(unsigned int dying_cpu) &new_base->clock_base[i]); } - /* - * The migration might have changed the first expiring softirq - * timer on this CPU. Update it. - */ - __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 059fa8b79be6..b6974fce800c 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -83,6 +83,12 @@ static inline bool tk_is_aux(const struct timekeeper *tk) } #endif +static inline void tk_update_aux_offs(struct timekeeper *tk, ktime_t offs) +{ + tk->offs_aux = offs; + tk->monotonic_to_aux = ktime_to_timespec64(offs); +} + /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; @@ -1506,7 +1512,7 @@ static int __timekeeping_inject_offset(struct tk_data *tkd, const struct timespe timekeeping_restore_shadow(tkd); return -EINVAL; } - tks->offs_aux = offs; + tk_update_aux_offs(tks, offs); } timekeeping_update_from_shadow(tkd, TK_UPDATE_ALL); @@ -2937,7 +2943,7 @@ static int aux_clock_set(const clockid_t id, const struct timespec64 *tnew) * xtime ("realtime") is not applicable for auxiliary clocks and * kept in sync with "monotonic". */ - aux_tks->offs_aux = ktime_sub(timespec64_to_ktime(*tnew), tnow); + tk_update_aux_offs(aux_tks, ktime_sub(timespec64_to_ktime(*tnew), tnow)); timekeeping_update_from_shadow(aux_tkd, TK_UPDATE_ALL); return 0; diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 8ba8b0d8a387..aa59919b8f2c 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -159,10 +159,10 @@ void vdso_time_update_aux(struct timekeeper *tk) if (clock_mode != VDSO_CLOCKMODE_NONE) { fill_clock_configuration(vc, &tk->tkr_mono); - vdso_ts->sec = tk->xtime_sec; + vdso_ts->sec = tk->xtime_sec + tk->monotonic_to_aux.tv_sec; nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; - nsec += tk->offs_aux; + nsec += tk->monotonic_to_aux.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec); nsec = nsec << tk->tkr_mono.shift; vdso_ts->nsec = nsec; diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c index 2a42c1036ea8..1e3b32b1e82c 100644 --- a/kernel/trace/fgraph.c +++ b/kernel/trace/fgraph.c @@ -1397,7 +1397,8 @@ error: ftrace_graph_active--; gops->saved_func = NULL; fgraph_lru_release_index(i); - unregister_pm_notifier(&ftrace_suspend_notifier); + if (!ftrace_graph_active) + unregister_pm_notifier(&ftrace_suspend_notifier); } return ret; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 1b7db732c0b1..b3c94fbaf002 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -834,7 +834,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, /* copy the current bits to the new max */ ret = trace_pid_list_first(filtered_pids, &pid); while (!ret) { - trace_pid_list_set(pid_list, pid); + ret = trace_pid_list_set(pid_list, pid); + if (ret < 0) + goto out; + ret = trace_pid_list_next(filtered_pids, pid + 1, &pid); nr_pids++; } @@ -871,6 +874,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, trace_parser_clear(&parser); ret = 0; } + out: trace_parser_put(&parser); if (ret < 0) { @@ -7209,7 +7213,7 @@ static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user entry = ring_buffer_event_data(event); entry->ip = ip; - len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt); + len = copy_from_user_nofault(&entry->buf, ubuf, cnt); if (len) { memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); cnt = FAULTED_SIZE; @@ -7306,7 +7310,7 @@ static ssize_t write_raw_marker_to_buffer(struct trace_array *tr, entry = ring_buffer_event_data(event); - len = __copy_from_user_inatomic(&entry->id, ubuf, cnt); + len = copy_from_user_nofault(&entry->id, ubuf, cnt); if (len) { entry->id = -1; memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c index af42aaa3d172..2ab283fd3032 100644 --- a/kernel/trace/trace_events_user.c +++ b/kernel/trace/trace_events_user.c @@ -496,7 +496,7 @@ static bool user_event_enabler_queue_fault(struct user_event_mm *mm, { struct user_event_enabler_fault *fault; - fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT | __GFP_NOWARN); + fault = kmem_cache_zalloc(fault_cache, GFP_NOWAIT); if (!fault) return false; diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index ccae62d4fb91..fa60362a3f31 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -908,6 +908,8 @@ static int trace_kprobe_create_internal(int argc, const char *argv[], return -EINVAL; } buf = kmemdup(&argv[0][1], len + 1, GFP_KERNEL); + if (!buf) + return -ENOMEM; buf[len] = '\0'; ret = kstrtouint(buf, 0, &maxactive); if (ret || !maxactive) { diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c index fd259da0aa64..337bc0eb5d71 100644 --- a/kernel/trace/trace_osnoise.c +++ b/kernel/trace/trace_osnoise.c @@ -2322,6 +2322,9 @@ osnoise_cpus_write(struct file *filp, const char __user *ubuf, size_t count, int running, err; char *buf __free(kfree) = NULL; + if (count < 1) + return 0; + buf = kmalloc(count, GFP_KERNEL); if (!buf) return -ENOMEM; diff --git a/mm/slub.c b/mm/slub.c index 30003763d224..d257141896c9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -962,19 +962,19 @@ static struct track *get_track(struct kmem_cache *s, void *object, } #ifdef CONFIG_STACKDEPOT -static noinline depot_stack_handle_t set_track_prepare(void) +static noinline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { depot_stack_handle_t handle; unsigned long entries[TRACK_ADDRS_COUNT]; unsigned int nr_entries; nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3); - handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT); + handle = stack_depot_save(entries, nr_entries, gfp_flags); return handle; } #else -static inline depot_stack_handle_t set_track_prepare(void) +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } @@ -996,9 +996,9 @@ static void set_track_update(struct kmem_cache *s, void *object, } static __always_inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) { - depot_stack_handle_t handle = set_track_prepare(); + depot_stack_handle_t handle = set_track_prepare(gfp_flags); set_track_update(s, object, alloc, addr, handle); } @@ -1140,7 +1140,12 @@ static void object_err(struct kmem_cache *s, struct slab *slab, return; slab_bug(s, reason); - print_trailer(s, slab, object); + if (!object || !check_valid_pointer(s, slab, object)) { + print_slab_info(slab); + pr_err("Invalid pointer 0x%p\n", object); + } else { + print_trailer(s, slab, object); + } add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); WARN_ON(1); @@ -1921,9 +1926,9 @@ static inline bool free_debug_processing(struct kmem_cache *s, static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {} static inline int check_object(struct kmem_cache *s, struct slab *slab, void *object, u8 val) { return 1; } -static inline depot_stack_handle_t set_track_prepare(void) { return 0; } +static inline depot_stack_handle_t set_track_prepare(gfp_t gfp_flags) { return 0; } static inline void set_track(struct kmem_cache *s, void *object, - enum track_item alloc, unsigned long addr) {} + enum track_item alloc, unsigned long addr, gfp_t gfp_flags) {} static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n, struct slab *slab) {} static inline void remove_full(struct kmem_cache *s, struct kmem_cache_node *n, @@ -3876,9 +3881,14 @@ new_objects: * For debug caches here we had to go through * alloc_single_from_partial() so just store the * tracking info and return the object. + * + * Due to disabled preemption we need to disallow + * blocking. The flags are further adjusted by + * gfp_nested_mask() in stack_depot itself. */ if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, + gfpflags & ~(__GFP_DIRECT_RECLAIM)); return freelist; } @@ -3910,7 +3920,8 @@ new_objects: goto new_objects; if (s->flags & SLAB_STORE_USER) - set_track(s, freelist, TRACK_ALLOC, addr); + set_track(s, freelist, TRACK_ALLOC, addr, + gfpflags & ~(__GFP_DIRECT_RECLAIM)); return freelist; } @@ -4421,8 +4432,12 @@ static noinline void free_to_partial_list( unsigned long flags; depot_stack_handle_t handle = 0; + /* + * We cannot use GFP_NOWAIT as there are callsites where waking up + * kswapd could deadlock + */ if (s->flags & SLAB_STORE_USER) - handle = set_track_prepare(); + handle = set_track_prepare(__GFP_NOWARN); spin_lock_irqsave(&n->list_lock, flags); diff --git a/net/atm/resources.c b/net/atm/resources.c index b19d851e1f44..7c6fdedbcf4e 100644 --- a/net/atm/resources.c +++ b/net/atm/resources.c @@ -112,7 +112,9 @@ struct atm_dev *atm_dev_register(const char *type, struct device *parent, if (atm_proc_dev_register(dev) < 0) { pr_err("atm_proc_dev_register failed for dev %s\n", type); - goto out_fail; + mutex_unlock(&atm_dev_mutex); + kfree(dev); + return NULL; } if (atm_register_sysfs(dev, parent) < 0) { @@ -128,7 +130,7 @@ out: return dev; out_fail: - kfree(dev); + put_device(&dev->class_dev); dev = NULL; goto out; } diff --git a/net/ax25/ax25_in.c b/net/ax25/ax25_in.c index 1cac25aca637..f2d66af86359 100644 --- a/net/ax25/ax25_in.c +++ b/net/ax25/ax25_in.c @@ -433,6 +433,10 @@ free: int ax25_kiss_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *ptype, struct net_device *orig_dev) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return NET_RX_DROP; + skb_orphan(skb); if (!net_eq(dev_net(dev), &init_net)) { diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 9f56308779cc..af97d077369f 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1687,7 +1687,12 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb, coding_len = ntohs(coded_packet_tmp.coded_len); - if (coding_len > skb->len) + /* ensure dst buffer is large enough (payload only) */ + if (coding_len + h_size > skb->len) + return NULL; + + /* ensure src buffer is large enough (payload only) */ + if (coding_len + h_size > nc_packet->skb->len) return NULL; /* Here the magic is reversed: diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index f4257c4d3052..814fb8610ac4 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1422,7 +1422,10 @@ static int l2cap_sock_release(struct socket *sock) if (!sk) return 0; + lock_sock_nested(sk, L2CAP_NESTING_PARENT); l2cap_sock_cleanup_listen(sk); + release_sock(sk); + bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, SHUT_RDWR); diff --git a/net/bridge/br.c b/net/bridge/br.c index 1885d0c315f0..c683baa3847f 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -324,6 +324,13 @@ int br_boolopt_multi_toggle(struct net_bridge *br, int err = 0; int opt_id; + opt_id = find_next_bit(&bitmap, BITS_PER_LONG, BR_BOOLOPT_MAX); + if (opt_id != BITS_PER_LONG) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Unknown boolean option %d", + opt_id); + return -EINVAL; + } + for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) { bool on = !!(bm->optval & BIT(opt_id)); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 94cbe967d1c1..083e2fe96441 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -626,9 +626,6 @@ static unsigned int br_nf_local_in(void *priv, break; } - ct = container_of(nfct, struct nf_conn, ct_general); - WARN_ON_ONCE(!nf_ct_is_confirmed(ct)); - return ret; } #endif diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c index 39844f14eed8..797719cb227e 100644 --- a/net/can/j1939/bus.c +++ b/net/can/j1939/bus.c @@ -290,8 +290,11 @@ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa) if (!ecu) ecu = j1939_ecu_create_locked(priv, name); err = PTR_ERR_OR_ZERO(ecu); - if (err) + if (err) { + if (j1939_address_is_unicast(sa)) + priv->ents[sa].nusers--; goto done; + } ecu->nusers++; /* TODO: do we care if ecu->addr != sa? */ diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index 31a93cae5111..81f58924b4ac 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -212,6 +212,7 @@ void j1939_priv_get(struct j1939_priv *priv); /* notify/alert all j1939 sockets bound to ifindex */ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv); +void j1939_sk_netdev_event_unregister(struct j1939_priv *priv); int j1939_cancel_active_session(struct j1939_priv *priv, struct sock *sk); void j1939_tp_init(struct j1939_priv *priv); diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c index 7e8a20f2fc42..3706a872ecaf 100644 --- a/net/can/j1939/main.c +++ b/net/can/j1939/main.c @@ -377,6 +377,9 @@ static int j1939_netdev_notify(struct notifier_block *nb, j1939_sk_netdev_event_netdown(priv); j1939_ecu_unmap_all(priv); break; + case NETDEV_UNREGISTER: + j1939_sk_netdev_event_unregister(priv); + break; } j1939_priv_put(priv); diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 3d8b588822f9..88e7160d4248 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -521,6 +521,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa); if (ret) { j1939_netdev_stop(priv); + jsk->priv = NULL; + synchronize_rcu(); + j1939_priv_put(priv); goto out_release_sock; } @@ -1300,6 +1303,55 @@ void j1939_sk_netdev_event_netdown(struct j1939_priv *priv) read_unlock_bh(&priv->j1939_socks_lock); } +void j1939_sk_netdev_event_unregister(struct j1939_priv *priv) +{ + struct sock *sk; + struct j1939_sock *jsk; + bool wait_rcu = false; + +rescan: /* The caller is holding a ref on this "priv" via j1939_priv_get_by_ndev(). */ + read_lock_bh(&priv->j1939_socks_lock); + list_for_each_entry(jsk, &priv->j1939_socks, list) { + /* Skip if j1939_jsk_add() is not called on this socket. */ + if (!(jsk->state & J1939_SOCK_BOUND)) + continue; + sk = &jsk->sk; + sock_hold(sk); + read_unlock_bh(&priv->j1939_socks_lock); + /* Check if j1939_jsk_del() is not yet called on this socket after holding + * socket's lock, for both j1939_sk_bind() and j1939_sk_release() call + * j1939_jsk_del() with socket's lock held. + */ + lock_sock(sk); + if (jsk->state & J1939_SOCK_BOUND) { + /* Neither j1939_sk_bind() nor j1939_sk_release() called j1939_jsk_del(). + * Make this socket no longer bound, by pretending as if j1939_sk_bind() + * dropped old references but did not get new references. + */ + j1939_jsk_del(priv, jsk); + j1939_local_ecu_put(priv, jsk->addr.src_name, jsk->addr.sa); + j1939_netdev_stop(priv); + /* Call j1939_priv_put() now and prevent j1939_sk_sock_destruct() from + * calling the corresponding j1939_priv_put(). + * + * j1939_sk_sock_destruct() is supposed to call j1939_priv_put() after + * an RCU grace period. But since the caller is holding a ref on this + * "priv", we can defer synchronize_rcu() until immediately before + * the caller calls j1939_priv_put(). + */ + j1939_priv_put(priv); + jsk->priv = NULL; + wait_rcu = true; + } + release_sock(sk); + sock_put(sk); + goto rescan; + } + read_unlock_bh(&priv->j1939_socks_lock); + if (wait_rcu) + synchronize_rcu(); +} + static int j1939_sk_no_ioctlcmd(struct socket *sock, unsigned int cmd, unsigned long arg) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index d1b5705dc0c6..9f6d860411cb 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1524,7 +1524,7 @@ static void con_fault_finish(struct ceph_connection *con) * in case we faulted due to authentication, invalidate our * current tickets so that we can get new ones. */ - if (con->v1.auth_retry) { + if (!ceph_msgr2(from_msgr(con->msgr)) && con->v1.auth_retry) { dout("auth_retry %d, invalidating\n", con->v1.auth_retry); if (con->ops->invalidate_authorizer) con->ops->invalidate_authorizer(con); @@ -1714,9 +1714,10 @@ static void clear_standby(struct ceph_connection *con) { /* come back from STANDBY? */ if (con->state == CEPH_CON_S_STANDBY) { - dout("clear_standby %p and ++connect_seq\n", con); + dout("clear_standby %p\n", con); con->state = CEPH_CON_S_PREOPEN; - con->v1.connect_seq++; + if (!ceph_msgr2(from_msgr(con->msgr))) + con->v1.connect_seq++; WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING)); WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)); } diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 9c0ad7f4b5d8..ad54b12d4b4c 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -464,8 +464,15 @@ int generic_hwtstamp_get_lower(struct net_device *dev, if (!netif_device_present(dev)) return -ENODEV; - if (ops->ndo_hwtstamp_get) - return dev_get_hwtstamp_phylib(dev, kernel_cfg); + if (ops->ndo_hwtstamp_get) { + int err; + + netdev_lock_ops(dev); + err = dev_get_hwtstamp_phylib(dev, kernel_cfg); + netdev_unlock_ops(dev); + + return err; + } /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCGHWTSTAMP, kernel_cfg); @@ -481,8 +488,15 @@ int generic_hwtstamp_set_lower(struct net_device *dev, if (!netif_device_present(dev)) return -ENODEV; - if (ops->ndo_hwtstamp_set) - return dev_set_hwtstamp_phylib(dev, kernel_cfg, extack); + if (ops->ndo_hwtstamp_set) { + int err; + + netdev_lock_ops(dev); + err = dev_set_hwtstamp_phylib(dev, kernel_cfg, extack); + netdev_unlock_ops(dev); + + return err; + } /* Legacy path: unconverted lower driver */ return generic_hwtstamp_ioctl_lower(dev, SIOCSHWTSTAMP, kernel_cfg); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 7d426a8e29f3..f112156db587 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -90,10 +90,12 @@ static void est_timer(struct timer_list *t) rate = (b_packets - est->last_packets) << (10 - est->intvl_log); rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); + preempt_disable_nested(); write_seqcount_begin(&est->seq); est->avbps += brate; est->avpps += rate; write_seqcount_end(&est->seq); + preempt_enable_nested(); est->last_bytes = b_bytes; est->last_packets = b_packets; diff --git a/net/core/sock.c b/net/core/sock.c index 7c26ec8dce63..158bddd23134 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2780,28 +2780,6 @@ void sock_pfree(struct sk_buff *skb) EXPORT_SYMBOL(sock_pfree); #endif /* CONFIG_INET */ -unsigned long __sock_i_ino(struct sock *sk) -{ - unsigned long ino; - - read_lock(&sk->sk_callback_lock); - ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock(&sk->sk_callback_lock); - return ino; -} -EXPORT_SYMBOL(__sock_i_ino); - -unsigned long sock_i_ino(struct sock *sk) -{ - unsigned long ino; - - local_bh_disable(); - ino = __sock_i_ino(sk); - local_bh_enable(); - return ino; -} -EXPORT_SYMBOL(sock_i_ino); - /* * Allocate a skb from the socket's send buffer. */ diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 88657255fec1..fbbc3ccf9df6 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -49,7 +49,7 @@ static bool hsr_check_carrier(struct hsr_port *master) ASSERT_RTNL(); - hsr_for_each_port(master->hsr, port) { + hsr_for_each_port_rtnl(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; @@ -105,7 +105,7 @@ int hsr_get_max_mtu(struct hsr_priv *hsr) struct hsr_port *port; mtu_max = ETH_DATA_LEN; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); @@ -139,7 +139,7 @@ static int hsr_dev_open(struct net_device *dev) hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -172,7 +172,7 @@ static int hsr_dev_close(struct net_device *dev) struct hsr_priv *hsr; hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -205,7 +205,7 @@ static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); @@ -226,6 +226,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; + rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; @@ -238,6 +239,8 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } + rcu_read_unlock(); + return NETDEV_TX_OK; } @@ -484,7 +487,7 @@ static void hsr_set_rx_mode(struct net_device *dev) hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -506,7 +509,7 @@ static void hsr_change_rx_flags(struct net_device *dev, int change) hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -534,7 +537,7 @@ static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) continue; @@ -580,7 +583,7 @@ static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, hsr = netdev_priv(dev); - hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: @@ -672,9 +675,14 @@ struct net_device *hsr_get_port_ndev(struct net_device *ndev, struct hsr_priv *hsr = netdev_priv(ndev); struct hsr_port *port; + rcu_read_lock(); hsr_for_each_port(hsr, port) - if (port->type == pt) + if (port->type == pt) { + dev_hold(port->dev); + rcu_read_unlock(); return port->dev; + } + rcu_read_unlock(); return NULL; } EXPORT_SYMBOL(hsr_get_port_ndev); diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 192893c3f2ec..bc94b07101d8 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -22,7 +22,7 @@ static bool hsr_slave_empty(struct hsr_priv *hsr) { struct hsr_port *port; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) return false; return true; @@ -134,7 +134,7 @@ struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt) { struct hsr_port *port; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type == pt) return port; return NULL; diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 135ec5fce019..33b0d2460c9b 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -224,6 +224,9 @@ struct hsr_priv { #define hsr_for_each_port(hsr, port) \ list_for_each_entry_rcu((port), &(hsr)->ports, port_list) +#define hsr_for_each_port_rtnl(hsr, port) \ + list_for_each_entry_rcu((port), &(hsr)->ports, port_list, lockdep_rtnl_is_held()) + struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt); /* Caller must ensure skb is a valid HSR frame */ diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c47d3828d4f6..942a887bf089 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -340,14 +340,13 @@ static void inetdev_destroy(struct in_device *in_dev) static int __init inet_blackhole_dev_init(void) { - int err = 0; + struct in_device *in_dev; rtnl_lock(); - if (!inetdev_init(blackhole_netdev)) - err = -ENOMEM; + in_dev = inetdev_init(blackhole_netdev); rtnl_unlock(); - return err; + return PTR_ERR_OR_ZERO(in_dev); } late_initcall(inet_blackhole_dev_init); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 2ffe73ea644f..c48c572f024d 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -799,11 +799,12 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) struct sk_buff *cloned_skb = NULL; struct ip_options opts = { 0 }; enum ip_conntrack_info ctinfo; + enum ip_conntrack_dir dir; struct nf_conn *ct; __be32 orig_ip; ct = nf_ct_get(skb_in, &ctinfo); - if (!ct || !(ct->status & IPS_SRC_NAT)) { + if (!ct || !(READ_ONCE(ct->status) & IPS_NAT_MASK)) { __icmp_send(skb_in, type, code, info, &opts); return; } @@ -818,7 +819,8 @@ void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) goto out; orig_ip = ip_hdr(skb_in)->saddr; - ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; + dir = CTINFO2DIR(ctinfo); + ip_hdr(skb_in)->saddr = ct->tuplehash[dir].tuple.src.u3.ip; __icmp_send(skb_in, type, code, info, &opts); ip_hdr(skb_in)->saddr = orig_ip; out: diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index cc9915543637..2e61ac137128 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -206,6 +206,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) return -EINVAL; + if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); @@ -300,6 +303,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) return -EINVAL; + if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index ba581785adb4..a268e1595b22 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -408,8 +408,11 @@ more_data: if (!psock->cork) { psock->cork = kzalloc(sizeof(*psock->cork), GFP_ATOMIC | __GFP_NOWARN); - if (!psock->cork) + if (!psock->cork) { + sk_msg_free(sk, msg); + *copied = 0; return -ENOMEM; + } } memcpy(psock->cork, msg, sizeof(*msg)); return 0; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index d1ef9644f826..a23eb8734e15 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -494,10 +494,8 @@ static int ipv6_rpl_srh_rcv(struct sk_buff *skb) idev = __in6_dev_get(skb->dev); - accept_rpl_seg = net->ipv6.devconf_all->rpl_seg_enabled; - if (accept_rpl_seg > idev->cnf.rpl_seg_enabled) - accept_rpl_seg = idev->cnf.rpl_seg_enabled; - + accept_rpl_seg = min(READ_ONCE(net->ipv6.devconf_all->rpl_seg_enabled), + READ_ONCE(idev->cnf.rpl_seg_enabled)); if (!accept_rpl_seg) { kfree_skb(skb); return -1; diff --git a/net/ipv6/ip6_icmp.c b/net/ipv6/ip6_icmp.c index 9e3574880cb0..233914b63bdb 100644 --- a/net/ipv6/ip6_icmp.c +++ b/net/ipv6/ip6_icmp.c @@ -54,11 +54,12 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) struct inet6_skb_parm parm = { 0 }; struct sk_buff *cloned_skb = NULL; enum ip_conntrack_info ctinfo; + enum ip_conntrack_dir dir; struct in6_addr orig_ip; struct nf_conn *ct; ct = nf_ct_get(skb_in, &ctinfo); - if (!ct || !(ct->status & IPS_SRC_NAT)) { + if (!ct || !(READ_ONCE(ct->status) & IPS_NAT_MASK)) { __icmpv6_send(skb_in, type, code, info, &parm); return; } @@ -73,7 +74,8 @@ void icmpv6_ndo_send(struct sk_buff *skb_in, u8 type, u8 code, __u32 info) goto out; orig_ip = ipv6_hdr(skb_in)->saddr; - ipv6_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.in6; + dir = CTINFO2DIR(ctinfo); + ipv6_hdr(skb_in)->saddr = ct->tuplehash[dir].tuple.src.u3.in6; __icmpv6_send(skb_in, type, code, info, &parm); ipv6_hdr(skb_in)->saddr = orig_ip; out: diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7577e7eb2c97..e885629312a4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1431,17 +1431,17 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * ireq = inet_rsk(req); if (sk_acceptq_is_full(sk)) - goto out_overflow; + goto exit_overflow; if (!dst) { dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP); if (!dst) - goto out; + goto exit; } newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) - goto out_nonewsk; + goto exit_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks @@ -1525,25 +1525,19 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * const union tcp_md5_addr *addr; addr = (union tcp_md5_addr *)&newsk->sk_v6_daddr; - if (tcp_md5_key_copy(newsk, addr, AF_INET6, 128, l3index, key)) { - inet_csk_prepare_forced_close(newsk); - tcp_done(newsk); - goto out; - } + if (tcp_md5_key_copy(newsk, addr, AF_INET6, 128, l3index, key)) + goto put_and_exit; } } #endif #ifdef CONFIG_TCP_AO /* Copy over tcp_ao_info if any */ if (tcp_ao_copy_all_matching(sk, newsk, req, skb, AF_INET6)) - goto out; /* OOM */ + goto put_and_exit; /* OOM */ #endif - if (__inet_inherit_port(sk, newsk) < 0) { - inet_csk_prepare_forced_close(newsk); - tcp_done(newsk); - goto out; - } + if (__inet_inherit_port(sk, newsk) < 0) + goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &found_dup_sk); if (*own_req) { @@ -1570,13 +1564,17 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * return newsk; -out_overflow: +exit_overflow: __NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); -out_nonewsk: +exit_nonewsk: dst_release(dst); -out: +exit: tcp_listendrop(sk); return NULL; +put_and_exit: + inet_csk_prepare_forced_close(newsk); + tcp_done(newsk); + goto exit; } INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 181bcb34b795..55105d238d6b 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1416,7 +1416,7 @@ drv_get_ftm_responder_stats(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct cfg80211_ftm_responder_stats *ftm_stats) { - u32 ret = -EOPNOTSUPP; + int ret = -EOPNOTSUPP; might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 9c8f18b258a6..3ae6104e5cb2 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -1111,7 +1111,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) int result, i; enum nl80211_band band; int channels, max_bitrates; - bool supp_ht, supp_vht, supp_he, supp_eht; + bool supp_ht, supp_vht, supp_he, supp_eht, supp_s1g; struct cfg80211_chan_def dflt_chandef = {}; if (ieee80211_hw_check(hw, QUEUE_CONTROL) && @@ -1227,6 +1227,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) supp_vht = false; supp_he = false; supp_eht = false; + supp_s1g = false; for (band = 0; band < NUM_NL80211_BANDS; band++) { const struct ieee80211_sband_iftype_data *iftd; struct ieee80211_supported_band *sband; @@ -1274,6 +1275,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) max_bitrates = sband->n_bitrates; supp_ht = supp_ht || sband->ht_cap.ht_supported; supp_vht = supp_vht || sband->vht_cap.vht_supported; + supp_s1g = supp_s1g || sband->s1g_cap.s1g; for_each_sband_iftype_data(sband, i, iftd) { u8 he_40_mhz_cap; @@ -1406,6 +1408,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->scan_ies_len += 2 + sizeof(struct ieee80211_vht_cap); + if (supp_s1g) + local->scan_ies_len += 2 + sizeof(struct ieee80211_s1g_cap); + /* * HE cap element is variable in size - set len to allow max size */ if (supp_he) { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 1008eb8e9b13..dd650a127a31 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1189,6 +1189,14 @@ again: "required MCSes not supported, disabling EHT\n"); } + if (conn->mode >= IEEE80211_CONN_MODE_EHT && + channel->band != NL80211_BAND_2GHZ && + conn->bw_limit == IEEE80211_CONN_BW_LIMIT_40) { + conn->mode = IEEE80211_CONN_MODE_HE; + link_id_info(sdata, link_id, + "required bandwidth not supported, disabling EHT\n"); + } + /* the mode can only decrease, so this must terminate */ if (ap_mode != conn->mode) { kfree(elems); diff --git a/net/mac80211/tests/chan-mode.c b/net/mac80211/tests/chan-mode.c index 96c7b3ab2744..adc069065e73 100644 --- a/net/mac80211/tests/chan-mode.c +++ b/net/mac80211/tests/chan-mode.c @@ -2,7 +2,7 @@ /* * KUnit tests for channel mode functions * - * Copyright (C) 2024 Intel Corporation + * Copyright (C) 2024-2025 Intel Corporation */ #include <net/cfg80211.h> #include <kunit/test.h> @@ -28,6 +28,10 @@ static const struct determine_chan_mode_case { u8 vht_basic_mcs_1_4, vht_basic_mcs_5_8; u8 he_basic_mcs_1_4, he_basic_mcs_5_8; u8 eht_mcs7_min_nss; + u16 eht_disabled_subchannels; + u8 eht_bw; + enum ieee80211_conn_bw_limit conn_bw_limit; + enum ieee80211_conn_bw_limit expected_bw_limit; int error; } determine_chan_mode_cases[] = { { @@ -128,6 +132,14 @@ static const struct determine_chan_mode_case { .conn_mode = IEEE80211_CONN_MODE_EHT, .eht_mcs7_min_nss = 0x15, .error = EINVAL, + }, { + .desc = "80 MHz EHT is downgraded to 40 MHz HE due to puncturing", + .conn_mode = IEEE80211_CONN_MODE_EHT, + .expected_mode = IEEE80211_CONN_MODE_HE, + .conn_bw_limit = IEEE80211_CONN_BW_LIMIT_80, + .expected_bw_limit = IEEE80211_CONN_BW_LIMIT_40, + .eht_disabled_subchannels = 0x08, + .eht_bw = IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ, } }; KUNIT_ARRAY_PARAM_DESC(determine_chan_mode, determine_chan_mode_cases, desc) @@ -138,7 +150,7 @@ static void test_determine_chan_mode(struct kunit *test) struct t_sdata *t_sdata = T_SDATA(test); struct ieee80211_conn_settings conn = { .mode = params->conn_mode, - .bw_limit = IEEE80211_CONN_BW_LIMIT_20, + .bw_limit = params->conn_bw_limit, }; struct cfg80211_bss cbss = { .channel = &t_sdata->band_5ghz.channels[0], @@ -191,14 +203,21 @@ static void test_determine_chan_mode(struct kunit *test) 0x7f, 0x01, 0x00, 0x88, 0x88, 0x88, 0x00, 0x00, 0x00, /* EHT Operation */ - WLAN_EID_EXTENSION, 0x09, WLAN_EID_EXT_EHT_OPERATION, - 0x01, params->eht_mcs7_min_nss ? params->eht_mcs7_min_nss : 0x11, - 0x00, 0x00, 0x00, 0x00, 0x24, 0x00, + WLAN_EID_EXTENSION, 0x0b, WLAN_EID_EXT_EHT_OPERATION, + 0x03, params->eht_mcs7_min_nss ? params->eht_mcs7_min_nss : 0x11, + 0x00, 0x00, 0x00, params->eht_bw, + params->eht_bw == IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ ? 42 : 36, + 0x00, + u16_get_bits(params->eht_disabled_subchannels, 0xff), + u16_get_bits(params->eht_disabled_subchannels, 0xff00), }; struct ieee80211_chan_req chanreq = {}; struct cfg80211_chan_def ap_chandef = {}; struct ieee802_11_elems *elems; + /* To force EHT downgrade to HE on punctured 80 MHz downgraded to 40 MHz */ + set_bit(IEEE80211_HW_DISALLOW_PUNCTURING, t_sdata->local.hw.flags); + if (params->strict) set_bit(IEEE80211_HW_STRICT, t_sdata->local.hw.flags); else @@ -237,6 +256,7 @@ static void test_determine_chan_mode(struct kunit *test) } else { KUNIT_ASSERT_NOT_ERR_OR_NULL(test, elems); KUNIT_ASSERT_EQ(test, conn.mode, params->expected_mode); + KUNIT_ASSERT_EQ(test, conn.bw_limit, params->expected_bw_limit); } } diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index df4e8cf33899..685524800d70 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -425,7 +425,7 @@ static int mctp_getsockopt(struct socket *sock, int level, int optname, return 0; } - return -EINVAL; + return -ENOPROTOOPT; } /* helpers for reading/writing the tag ioc, handling compatibility across the diff --git a/net/mctp/route.c b/net/mctp/route.c index 2b2b958ef6a3..4d314e062ba9 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -378,6 +378,7 @@ static void mctp_skb_set_flow(struct sk_buff *skb, struct mctp_sk_key *key) {} static void mctp_flow_prepare_output(struct sk_buff *skb, struct mctp_dev *dev) {} #endif +/* takes ownership of skb, both in success and failure cases */ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb) { struct mctp_hdr *hdr = mctp_hdr(skb); @@ -387,8 +388,10 @@ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb) & MCTP_HDR_SEQ_MASK; if (!key->reasm_head) { - /* Since we're manipulating the shared frag_list, ensure it isn't - * shared with any other SKBs. + /* Since we're manipulating the shared frag_list, ensure it + * isn't shared with any other SKBs. In the cloned case, + * this will free the skb; callers can no longer access it + * safely. */ key->reasm_head = skb_unshare(skb, GFP_ATOMIC); if (!key->reasm_head) @@ -402,10 +405,10 @@ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb) exp_seq = (key->last_seq + 1) & MCTP_HDR_SEQ_MASK; if (this_seq != exp_seq) - return -EINVAL; + goto err_free; if (key->reasm_head->len + skb->len > mctp_message_maxlen) - return -EINVAL; + goto err_free; skb->next = NULL; skb->sk = NULL; @@ -419,6 +422,10 @@ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb) key->reasm_head->truesize += skb->truesize; return 0; + +err_free: + kfree_skb(skb); + return -EINVAL; } static int mctp_dst_input(struct mctp_dst *dst, struct sk_buff *skb) @@ -532,18 +539,16 @@ static int mctp_dst_input(struct mctp_dst *dst, struct sk_buff *skb) * key isn't observable yet */ mctp_frag_queue(key, skb); + skb = NULL; /* if the key_add fails, we've raced with another * SOM packet with the same src, dest and tag. There's * no way to distinguish future packets, so all we - * can do is drop; we'll free the skb on exit from - * this function. + * can do is drop. */ rc = mctp_key_add(key, msk); - if (!rc) { + if (!rc) trace_mctp_key_acquire(key); - skb = NULL; - } /* we don't need to release key->lock on exit, so * clean up here and suppress the unlock via @@ -561,8 +566,7 @@ static int mctp_dst_input(struct mctp_dst *dst, struct sk_buff *skb) key = NULL; } else { rc = mctp_frag_queue(key, skb); - if (!rc) - skb = NULL; + skb = NULL; } } @@ -572,17 +576,16 @@ static int mctp_dst_input(struct mctp_dst *dst, struct sk_buff *skb) */ /* we need to be continuing an existing reassembly... */ - if (!key->reasm_head) + if (!key->reasm_head) { rc = -EINVAL; - else + } else { rc = mctp_frag_queue(key, skb); + skb = NULL; + } if (rc) goto out_unlock; - /* we've queued; the queue owns the skb now */ - skb = NULL; - /* end of message? deliver to socket, and we're done with * the reassembly/response key */ diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 9a287b75c1b3..e6fd97b21e9e 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3554,7 +3554,6 @@ void mptcp_sock_graft(struct sock *sk, struct socket *parent) write_lock_bh(&sk->sk_callback_lock); rcu_assign_pointer(sk->sk_wq, &parent->wq); sk_set_socket(sk, parent); - WRITE_ONCE(sk->sk_uid, SOCK_INODE(parent)->i_uid); write_unlock_bh(&sk->sk_callback_lock); } diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 2c267aff95be..2abe6f1e9940 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -1532,13 +1532,12 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) { static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK; struct sock *sk = (struct sock *)msk; + bool keep_open; - if (ssk->sk_prot->keepalive) { - if (sock_flag(sk, SOCK_KEEPOPEN)) - ssk->sk_prot->keepalive(ssk, 1); - else - ssk->sk_prot->keepalive(ssk, 0); - } + keep_open = sock_flag(sk, SOCK_KEEPOPEN); + if (ssk->sk_prot->keepalive) + ssk->sk_prot->keepalive(ssk, keep_open); + sock_valbool_flag(ssk, SOCK_KEEPOPEN, keep_open); ssk->sk_priority = sk->sk_priority; ssk->sk_bound_dev_if = sk->sk_bound_dev_if; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 4ed5878cb25b..ceb48c3ca0a4 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -368,7 +368,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) (cur->tuple.src.l3num == NFPROTO_UNSPEC || cur->tuple.src.l3num == me->tuple.src.l3num) && cur->tuple.dst.protonum == me->tuple.dst.protonum) { - ret = -EEXIST; + ret = -EBUSY; goto out; } } @@ -379,7 +379,7 @@ int nf_conntrack_helper_register(struct nf_conntrack_helper *me) hlist_for_each_entry(cur, &nf_ct_helper_hash[h], hnode) { if (nf_ct_tuple_src_mask_cmp(&cur->tuple, &me->tuple, &mask)) { - ret = -EEXIST; + ret = -EBUSY; goto out; } } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 58c5425d61c2..c3c73411c40c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1131,11 +1131,14 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, return ERR_PTR(-ENOENT); } -static __be16 nft_base_seq(const struct net *net) +static unsigned int nft_base_seq(const struct net *net) { - struct nftables_pernet *nft_net = nft_pernet(net); + return READ_ONCE(net->nft.base_seq); +} - return htons(nft_net->base_seq & 0xffff); +static __be16 nft_base_seq_be16(const struct net *net) +{ + return htons(nft_base_seq(net) & 0xffff); } static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = { @@ -1155,7 +1158,7 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -1248,7 +1251,7 @@ static int nf_tables_dump_tables(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -1959,6 +1962,18 @@ nla_put_failure: return -ENOSPC; } +static bool hook_is_prefix(struct nft_hook *hook) +{ + return strlen(hook->ifname) >= hook->ifnamelen; +} + +static int nft_nla_put_hook_dev(struct sk_buff *skb, struct nft_hook *hook) +{ + int attr = hook_is_prefix(hook) ? NFTA_DEVICE_PREFIX : NFTA_DEVICE_NAME; + + return nla_put_string(skb, attr, hook->ifname); +} + static int nft_dump_basechain_hook(struct sk_buff *skb, const struct net *net, int family, const struct nft_base_chain *basechain, @@ -1990,16 +2005,15 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, if (!first) first = hook; - if (nla_put(skb, NFTA_DEVICE_NAME, - hook->ifnamelen, hook->ifname)) + if (nft_nla_put_hook_dev(skb, hook)) goto nla_put_failure; n++; } nla_nest_end(skb, nest_devs); if (n == 1 && - nla_put(skb, NFTA_HOOK_DEV, - first->ifnamelen, first->ifname)) + !hook_is_prefix(first) && + nla_put_string(skb, NFTA_HOOK_DEV, first->ifname)) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -2019,7 +2033,7 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -2122,7 +2136,7 @@ static int nf_tables_dump_chains(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -2310,7 +2324,8 @@ void nf_tables_chain_destroy(struct nft_chain *chain) } static struct nft_hook *nft_netdev_hook_alloc(struct net *net, - const struct nlattr *attr) + const struct nlattr *attr, + bool prefix) { struct nf_hook_ops *ops; struct net_device *dev; @@ -2327,7 +2342,8 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, if (err < 0) goto err_hook_free; - hook->ifnamelen = nla_len(attr); + /* include the terminating NUL-char when comparing non-prefixes */ + hook->ifnamelen = strlen(hook->ifname) + !prefix; /* nf_tables_netdev_event() is called under rtnl_mutex, this is * indirectly serializing all the other holders of the commit_mutex with @@ -2374,14 +2390,22 @@ static int nf_tables_parse_netdev_hooks(struct net *net, struct nft_hook *hook, *next; const struct nlattr *tmp; int rem, n = 0, err; + bool prefix; nla_for_each_nested(tmp, attr, rem) { - if (nla_type(tmp) != NFTA_DEVICE_NAME) { + switch (nla_type(tmp)) { + case NFTA_DEVICE_NAME: + prefix = false; + break; + case NFTA_DEVICE_PREFIX: + prefix = true; + break; + default: err = -EINVAL; goto err_hook; } - hook = nft_netdev_hook_alloc(net, tmp); + hook = nft_netdev_hook_alloc(net, tmp, prefix); if (IS_ERR(hook)) { NL_SET_BAD_ATTR(extack, tmp); err = PTR_ERR(hook); @@ -2427,7 +2451,7 @@ static int nft_chain_parse_netdev(struct net *net, struct nlattr *tb[], int err; if (tb[NFTA_HOOK_DEV]) { - hook = nft_netdev_hook_alloc(net, tb[NFTA_HOOK_DEV]); + hook = nft_netdev_hook_alloc(net, tb[NFTA_HOOK_DEV], false); if (IS_ERR(hook)) { NL_SET_BAD_ATTR(extack, tb[NFTA_HOOK_DEV]); return PTR_ERR(hook); @@ -3650,7 +3674,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u16 type = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, type, flags, family, NFNETLINK_V0, - nft_base_seq(net)); + nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -3818,7 +3842,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -4029,7 +4053,7 @@ static int nf_tables_getrule_reset(struct sk_buff *skb, buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_RULE_TABLE]), (char *)nla_data(nla[NFTA_RULE_TABLE]), - nft_net->base_seq); + nft_base_seq(net)); audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC); kfree(buf); @@ -4866,7 +4890,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), flags, ctx->family, NFNETLINK_V0, - nft_base_seq(ctx->net)); + nft_base_seq_be16(ctx->net)); if (!nlh) goto nla_put_failure; @@ -5011,7 +5035,7 @@ static int nf_tables_dump_sets(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (ctx->family != NFPROTO_UNSPEC && @@ -6188,7 +6212,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (dump_ctx->ctx.family != NFPROTO_UNSPEC && @@ -6217,7 +6241,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) seq = cb->nlh->nlmsg_seq; nlh = nfnl_msg_put(skb, portid, seq, event, NLM_F_MULTI, - table->family, NFNETLINK_V0, nft_base_seq(net)); + table->family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -6310,7 +6334,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nfnl_msg_put(skb, portid, seq, event, flags, ctx->family, - NFNETLINK_V0, nft_base_seq(ctx->net)); + NFNETLINK_V0, nft_base_seq_be16(ctx->net)); if (!nlh) goto nla_put_failure; @@ -6609,7 +6633,7 @@ static int nf_tables_getsetelem_reset(struct sk_buff *skb, } nelems++; } - audit_log_nft_set_reset(dump_ctx.ctx.table, nft_net->base_seq, nelems); + audit_log_nft_set_reset(dump_ctx.ctx.table, nft_base_seq(info->net), nelems); out_unlock: rcu_read_unlock(); @@ -8360,7 +8384,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -8425,7 +8449,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -8459,7 +8483,7 @@ cont: idx++; } if (ctx->reset && entries) - audit_log_obj_reset(table, nft_net->base_seq, entries); + audit_log_obj_reset(table, nft_base_seq(net), entries); if (rc < 0) break; } @@ -8628,7 +8652,7 @@ static int nf_tables_getobj_reset(struct sk_buff *skb, buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_OBJ_TABLE]), (char *)nla_data(nla[NFTA_OBJ_TABLE]), - nft_net->base_seq); + nft_base_seq(net)); audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); @@ -8733,9 +8757,8 @@ void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, u16 flags, int family, int report, gfp_t gfp) { - struct nftables_pernet *nft_net = nft_pernet(net); char *buf = kasprintf(gfp, "%s:%u", - table->name, nft_net->base_seq); + table->name, nft_base_seq(net)); audit_log_nfcfg(buf, family, @@ -9421,7 +9444,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, nlh = nfnl_msg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event), - flags, family, NFNETLINK_V0, nft_base_seq(net)); + flags, family, NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; @@ -9458,8 +9481,7 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, list_for_each_entry_rcu(hook, hook_list, list, lockdep_commit_lock_is_held(net)) { - if (nla_put(skb, NFTA_DEVICE_NAME, - hook->ifnamelen, hook->ifname)) + if (nft_nla_put_hook_dev(skb, hook)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); @@ -9491,7 +9513,7 @@ static int nf_tables_dump_flowtable(struct sk_buff *skb, rcu_read_lock(); nft_net = nft_pernet(net); - cb->seq = READ_ONCE(nft_net->base_seq); + cb->seq = nft_base_seq(net); list_for_each_entry_rcu(table, &nft_net->tables, list) { if (family != NFPROTO_UNSPEC && family != table->family) @@ -9676,17 +9698,16 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq) { - struct nftables_pernet *nft_net = nft_pernet(net); struct nlmsghdr *nlh; char buf[TASK_COMM_LEN]; int event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_NEWGEN); nlh = nfnl_msg_put(skb, portid, seq, event, 0, AF_UNSPEC, - NFNETLINK_V0, nft_base_seq(net)); + NFNETLINK_V0, nft_base_seq_be16(net)); if (!nlh) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_net->base_seq)) || + if (nla_put_be32(skb, NFTA_GEN_ID, htonl(nft_base_seq(net))) || nla_put_be32(skb, NFTA_GEN_PROC_PID, htonl(task_pid_nr(current))) || nla_put_string(skb, NFTA_GEN_PROC_NAME, get_task_comm(buf, current))) goto nla_put_failure; @@ -10948,11 +10969,12 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) * Bump generation counter, invalidate any dump in progress. * Cannot fail after this point. */ - base_seq = READ_ONCE(nft_net->base_seq); + base_seq = nft_base_seq(net); while (++base_seq == 0) ; - WRITE_ONCE(nft_net->base_seq, base_seq); + /* pairs with smp_load_acquire in nft_lookup_eval */ + smp_store_release(&net->nft.base_seq, base_seq); gc_seq = nft_gc_seq_begin(nft_net); @@ -11161,7 +11183,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_commit_notify(net, NETLINK_CB(skb).portid); nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN); - nf_tables_commit_audit_log(&adl, nft_net->base_seq); + nf_tables_commit_audit_log(&adl, nft_base_seq(net)); nft_gc_seq_end(nft_net, gc_seq); nft_net->validate_state = NFT_VALIDATE_SKIP; @@ -11486,7 +11508,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid) mutex_lock(&nft_net->commit_mutex); nft_net->tstamp = get_jiffies_64(); - genid_ok = genid == 0 || nft_net->base_seq == genid; + genid_ok = genid == 0 || nft_base_seq(net) == genid; if (!genid_ok) mutex_unlock(&nft_net->commit_mutex); @@ -12123,7 +12145,7 @@ static int __net_init nf_tables_init_net(struct net *net) INIT_LIST_HEAD(&nft_net->module_list); INIT_LIST_HEAD(&nft_net->notify_list); mutex_init(&nft_net->commit_mutex); - nft_net->base_seq = 1; + net->nft.base_seq = 1; nft_net->gc_seq = 0; nft_net->validate_state = NFT_VALIDATE_SKIP; INIT_WORK(&nft_net->destroy_work, nf_tables_trans_destroy_work); diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 40c602ffbcba..58c5b14889c4 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -24,11 +24,11 @@ struct nft_lookup { struct nft_set_binding binding; }; -#ifdef CONFIG_MITIGATION_RETPOLINE -const struct nft_set_ext * -nft_set_do_lookup(const struct net *net, const struct nft_set *set, - const u32 *key) +static const struct nft_set_ext * +__nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) { +#ifdef CONFIG_MITIGATION_RETPOLINE if (set->ops == &nft_set_hash_fast_type.ops) return nft_hash_lookup_fast(net, set, key); if (set->ops == &nft_set_hash_type.ops) @@ -51,10 +51,46 @@ nft_set_do_lookup(const struct net *net, const struct nft_set *set, return nft_rbtree_lookup(net, set, key); WARN_ON_ONCE(1); +#endif return set->ops->lookup(net, set, key); } + +static unsigned int nft_base_seq(const struct net *net) +{ + /* pairs with smp_store_release() in nf_tables_commit() */ + return smp_load_acquire(&net->nft.base_seq); +} + +static bool nft_lookup_should_retry(const struct net *net, unsigned int seq) +{ + return unlikely(seq != nft_base_seq(net)); +} + +const struct nft_set_ext * +nft_set_do_lookup(const struct net *net, const struct nft_set *set, + const u32 *key) +{ + const struct nft_set_ext *ext; + unsigned int base_seq; + + do { + base_seq = nft_base_seq(net); + + ext = __nft_set_do_lookup(net, set, key); + if (ext) + break; + /* No match? There is a small chance that lookup was + * performed in the old generation, but nf_tables_commit() + * already unlinked a (matching) element. + * + * We need to repeat the lookup to make sure that we didn't + * miss a matching element in the new generation. + */ + } while (nft_lookup_should_retry(net, base_seq)); + + return ext; +} EXPORT_SYMBOL_GPL(nft_set_do_lookup); -#endif void nft_lookup_eval(const struct nft_expr *expr, struct nft_regs *regs, diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index c24c922f895d..8d3f040a904a 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -226,7 +226,8 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, const struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be; - list_for_each_entry_rcu(be, &priv->list, head) { + list_for_each_entry_rcu(be, &priv->list, head, + lockdep_is_held(&nft_pernet(ctx->net)->commit_mutex)) { if (iter->count < iter->skip) goto cont; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 9a10251228fd..793790d79d13 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -510,6 +510,23 @@ out: * * This function is called from the data path. It will search for * an element matching the given key in the current active copy. + * Unlike other set types, this uses NFT_GENMASK_ANY instead of + * nft_genmask_cur(). + * + * This is because new (future) elements are not reachable from + * priv->match, they get added to priv->clone instead. + * When the commit phase flips the generation bitmask, the + * 'now old' entries are skipped but without the 'now current' + * elements becoming visible. Using nft_genmask_cur() thus creates + * inconsistent state: matching old entries get skipped but thew + * newly matching entries are unreachable. + * + * GENMASK will still find the 'now old' entries which ensures consistent + * priv->match view. + * + * nft_pipapo_commit swaps ->clone and ->match shortly after the + * genbit flip. As ->clone doesn't contain the old entries in the first + * place, lookup will only find the now-current ones. * * Return: ntables API extension pointer or NULL if no match. */ @@ -518,12 +535,11 @@ nft_pipapo_lookup(const struct net *net, const struct nft_set *set, const u32 *key) { struct nft_pipapo *priv = nft_set_priv(set); - u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_elem *e; m = rcu_dereference(priv->match); - e = pipapo_get(m, (const u8 *)key, genmask, get_jiffies_64()); + e = pipapo_get(m, (const u8 *)key, NFT_GENMASK_ANY, get_jiffies_64()); return e ? &e->ext : NULL; } diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 2f090e253caf..c0884fa68c79 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -1152,7 +1152,6 @@ nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, struct nft_pipapo *priv = nft_set_priv(set); const struct nft_set_ext *ext = NULL; struct nft_pipapo_scratch *scratch; - u8 genmask = nft_genmask_cur(net); const struct nft_pipapo_match *m; const struct nft_pipapo_field *f; const u8 *rp = (const u8 *)key; @@ -1248,8 +1247,7 @@ next_match: if (last) { const struct nft_set_ext *e = &f->mt[ret].e->ext; - if (unlikely(nft_set_elem_expired(e) || - !nft_set_elem_active(e, genmask))) + if (unlikely(nft_set_elem_expired(e))) goto next_match; ext = e; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 938a257c069e..b1f04168ec93 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -77,7 +77,9 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, nft_rbtree_interval_end(rbe) && nft_rbtree_interval_start(interval)) continue; - interval = rbe; + if (nft_set_elem_active(&rbe->ext, genmask) && + !nft_rbtree_elem_expired(rbe)) + interval = rbe; } else if (d > 0) parent = rcu_dereference_raw(parent->rb_right); else { @@ -102,8 +104,6 @@ __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, } if (set->flags & NFT_SET_INTERVAL && interval != NULL && - nft_set_elem_active(&interval->ext, genmask) && - !nft_rbtree_elem_expired(interval) && nft_rbtree_interval_start(interval)) return &interval->ext; diff --git a/net/netlink/diag.c b/net/netlink/diag.c index 61981e01fd6f..b8e58132e8af 100644 --- a/net/netlink/diag.c +++ b/net/netlink/diag.c @@ -168,7 +168,7 @@ mc_list: NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - __sock_i_ino(sk)) < 0) { + sock_i_ino(sk)) < 0) { ret = 1; break; } diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 104732d34543..978c129c6095 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1836,6 +1836,9 @@ static int genl_bind(struct net *net, int group) !ns_capable(net->user_ns, CAP_SYS_ADMIN)) ret = -EPERM; + if (ret) + break; + if (family->bind) family->bind(i); diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 5a4db151fe95..08be56dfb3f2 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -426,8 +426,6 @@ smc_clc_msg_decl_valid(struct smc_clc_msg_decline *dclc) { struct smc_clc_msg_hdr *hdr = &dclc->hdr; - if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D) - return false; if (hdr->version == SMC_V1) { if (ntohs(hdr->length) != sizeof(struct smc_clc_msg_decline)) return false; diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 53828833a3f7..a42ef3f77b96 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -742,6 +742,9 @@ bool smc_ib_is_sg_need_sync(struct smc_link *lnk, unsigned int i; bool ret = false; + if (!lnk->smcibdev->ibdev->dma_device) + return ret; + /* for now there is just one DMA address */ for_each_sg(buf_slot->sgt[lnk->link_idx].sgl, sg, buf_slot->sgt[lnk->link_idx].nents, i) { diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 73bc39281ef5..9b45fbdc90ca 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -276,8 +276,6 @@ EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (unlikely(current->flags & PF_EXITING)) - return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c5f7bbf5775f..3aa987e7f072 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -407,9 +407,9 @@ xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags) iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1, alert_kvec.iov_len); ret = sock_recvmsg(sock, &msg, flags); - if (ret > 0 && - tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) { - iov_iter_revert(&msg.msg_iter, ret); + if (ret > 0) { + if (tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) + iov_iter_revert(&msg.msg_iter, ret); ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg, -EAGAIN); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 89519aa52893..852573423e52 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -7062,7 +7062,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, u32 seq, int flags, struct cfg80211_registered_device *rdev, struct net_device *dev, - const u8 *mac_addr, struct station_info *sinfo) + const u8 *mac_addr, struct station_info *sinfo, + bool link_stats) { void *hdr; struct nlattr *sinfoattr, *bss_param; @@ -7283,7 +7284,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, goto nla_put_failure; } - if (sinfo->valid_links) { + if (link_stats && sinfo->valid_links) { links = nla_nest_start(msg, NL80211_ATTR_MLO_LINKS); if (!links) goto nla_put_failure; @@ -7574,7 +7575,7 @@ static int nl80211_dump_station(struct sk_buff *skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev->netdev, mac_addr, - &sinfo) < 0) + &sinfo, false) < 0) goto out; sta_idx++; @@ -7635,7 +7636,7 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, info->snd_portid, info->snd_seq, 0, - rdev, dev, mac_addr, &sinfo) < 0) { + rdev, dev, mac_addr, &sinfo, false) < 0) { nlmsg_free(msg); return -ENOBUFS; } @@ -19680,7 +19681,7 @@ void cfg80211_new_sta(struct net_device *dev, const u8 *mac_addr, return; if (nl80211_send_station(msg, NL80211_CMD_NEW_STATION, 0, 0, 0, - rdev, dev, mac_addr, sinfo) < 0) { + rdev, dev, mac_addr, sinfo, false) < 0) { nlmsg_free(msg); return; } @@ -19710,7 +19711,7 @@ void cfg80211_del_sta_sinfo(struct net_device *dev, const u8 *mac_addr, } if (nl80211_send_station(msg, NL80211_CMD_DEL_STATION, 0, 0, 0, - rdev, dev, mac_addr, sinfo) < 0) { + rdev, dev, mac_addr, sinfo, false) < 0) { nlmsg_free(msg); return; } diff --git a/net/wireless/scan.c b/net/wireless/scan.c index a8339ed52404..6c7b7c3828a4 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1916,7 +1916,8 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev, */ f = rcu_access_pointer(new->pub.beacon_ies); - kfree_rcu((struct cfg80211_bss_ies *)f, rcu_head); + if (!new->pub.hidden_beacon_bss) + kfree_rcu((struct cfg80211_bss_ies *)f, rcu_head); return false; } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 826ec0a6355f..3a028ff287fb 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -900,13 +900,16 @@ void __cfg80211_connect_result(struct net_device *dev, if (!wdev->u.client.ssid_len) { rcu_read_lock(); for_each_valid_link(cr, link) { + u32 ssid_len; + ssid = ieee80211_bss_get_elem(cr->links[link].bss, WLAN_EID_SSID); if (!ssid || !ssid->datalen) continue; - memcpy(wdev->u.client.ssid, ssid->data, ssid->datalen); + ssid_len = min(ssid->datalen, IEEE80211_MAX_SSID_LEN); + memcpy(wdev->u.client.ssid, ssid->data, ssid_len); wdev->u.client.ssid_len = ssid->datalen; break; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 9c3acecc14b1..72e34bd2d925 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -36,6 +36,20 @@ #define TX_BATCH_SIZE 32 #define MAX_PER_SOCKET_BUDGET 32 +struct xsk_addr_node { + u64 addr; + struct list_head addr_node; +}; + +struct xsk_addr_head { + u32 num_descs; + struct list_head addrs_list; +}; + +static struct kmem_cache *xsk_tx_generic_cache; + +#define XSKCB(skb) ((struct xsk_addr_head *)((skb)->cb)) + void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool) { if (pool->cached_need_wakeup & XDP_WAKEUP_RX) @@ -532,24 +546,43 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags) return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags); } -static int xsk_cq_reserve_addr_locked(struct xsk_buff_pool *pool, u64 addr) +static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool) { unsigned long flags; int ret; spin_lock_irqsave(&pool->cq_lock, flags); - ret = xskq_prod_reserve_addr(pool->cq, addr); + ret = xskq_prod_reserve(pool->cq); spin_unlock_irqrestore(&pool->cq_lock, flags); return ret; } -static void xsk_cq_submit_locked(struct xsk_buff_pool *pool, u32 n) +static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool, + struct sk_buff *skb) { + struct xsk_addr_node *pos, *tmp; + u32 descs_processed = 0; unsigned long flags; + u32 idx; spin_lock_irqsave(&pool->cq_lock, flags); - xskq_prod_submit_n(pool->cq, n); + idx = xskq_get_prod(pool->cq); + + xskq_prod_write_addr(pool->cq, idx, + (u64)(uintptr_t)skb_shinfo(skb)->destructor_arg); + descs_processed++; + + if (unlikely(XSKCB(skb)->num_descs > 1)) { + list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) { + xskq_prod_write_addr(pool->cq, idx + descs_processed, + pos->addr); + descs_processed++; + list_del(&pos->addr_node); + kmem_cache_free(xsk_tx_generic_cache, pos); + } + } + xskq_prod_submit_n(pool->cq, descs_processed); spin_unlock_irqrestore(&pool->cq_lock, flags); } @@ -562,9 +595,14 @@ static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n) spin_unlock_irqrestore(&pool->cq_lock, flags); } +static void xsk_inc_num_desc(struct sk_buff *skb) +{ + XSKCB(skb)->num_descs++; +} + static u32 xsk_get_num_desc(struct sk_buff *skb) { - return skb ? (long)skb_shinfo(skb)->destructor_arg : 0; + return XSKCB(skb)->num_descs; } static void xsk_destruct_skb(struct sk_buff *skb) @@ -576,23 +614,33 @@ static void xsk_destruct_skb(struct sk_buff *skb) *compl->tx_timestamp = ktime_get_tai_fast_ns(); } - xsk_cq_submit_locked(xdp_sk(skb->sk)->pool, xsk_get_num_desc(skb)); + xsk_cq_submit_addr_locked(xdp_sk(skb->sk)->pool, skb); sock_wfree(skb); } -static void xsk_set_destructor_arg(struct sk_buff *skb) +static void xsk_set_destructor_arg(struct sk_buff *skb, u64 addr) { - long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1; - - skb_shinfo(skb)->destructor_arg = (void *)num; + BUILD_BUG_ON(sizeof(struct xsk_addr_head) > sizeof(skb->cb)); + INIT_LIST_HEAD(&XSKCB(skb)->addrs_list); + XSKCB(skb)->num_descs = 0; + skb_shinfo(skb)->destructor_arg = (void *)(uintptr_t)addr; } static void xsk_consume_skb(struct sk_buff *skb) { struct xdp_sock *xs = xdp_sk(skb->sk); + u32 num_descs = xsk_get_num_desc(skb); + struct xsk_addr_node *pos, *tmp; + + if (unlikely(num_descs > 1)) { + list_for_each_entry_safe(pos, tmp, &XSKCB(skb)->addrs_list, addr_node) { + list_del(&pos->addr_node); + kmem_cache_free(xsk_tx_generic_cache, pos); + } + } skb->destructor = sock_wfree; - xsk_cq_cancel_locked(xs->pool, xsk_get_num_desc(skb)); + xsk_cq_cancel_locked(xs->pool, num_descs); /* Free skb without triggering the perf drop trace */ consume_skb(skb); xs->skb = NULL; @@ -609,6 +657,7 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, { struct xsk_buff_pool *pool = xs->pool; u32 hr, len, ts, offset, copy, copied; + struct xsk_addr_node *xsk_addr; struct sk_buff *skb = xs->skb; struct page *page; void *buffer; @@ -623,6 +672,19 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs, return ERR_PTR(err); skb_reserve(skb, hr); + + xsk_set_destructor_arg(skb, desc->addr); + } else { + xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL); + if (!xsk_addr) + return ERR_PTR(-ENOMEM); + + /* in case of -EOVERFLOW that could happen below, + * xsk_consume_skb() will release this node as whole skb + * would be dropped, which implies freeing all list elements + */ + xsk_addr->addr = desc->addr; + list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list); } addr = desc->addr; @@ -694,8 +756,11 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, err = skb_store_bits(skb, 0, buffer, len); if (unlikely(err)) goto free_err; + + xsk_set_destructor_arg(skb, desc->addr); } else { int nr_frags = skb_shinfo(skb)->nr_frags; + struct xsk_addr_node *xsk_addr; struct page *page; u8 *vaddr; @@ -710,12 +775,22 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, goto free_err; } + xsk_addr = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL); + if (!xsk_addr) { + __free_page(page); + err = -ENOMEM; + goto free_err; + } + vaddr = kmap_local_page(page); memcpy(vaddr, buffer, len); kunmap_local(vaddr); skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); + + xsk_addr->addr = desc->addr; + list_add_tail(&xsk_addr->addr_node, &XSKCB(skb)->addrs_list); } if (first_frag && desc->options & XDP_TX_METADATA) { @@ -759,7 +834,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, skb->mark = READ_ONCE(xs->sk.sk_mark); skb->destructor = xsk_destruct_skb; xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta); - xsk_set_destructor_arg(skb); + xsk_inc_num_desc(skb); return skb; @@ -769,7 +844,7 @@ free_err: if (err == -EOVERFLOW) { /* Drop the packet */ - xsk_set_destructor_arg(xs->skb); + xsk_inc_num_desc(xs->skb); xsk_drop_skb(xs->skb); xskq_cons_release(xs->tx); } else { @@ -812,7 +887,7 @@ static int __xsk_generic_xmit(struct sock *sk) * if there is space in it. This avoids having to implement * any buffering in the Tx path. */ - err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr); + err = xsk_cq_reserve_locked(xs->pool); if (err) { err = -EAGAIN; goto out; @@ -1815,8 +1890,18 @@ static int __init xsk_init(void) if (err) goto out_pernet; + xsk_tx_generic_cache = kmem_cache_create("xsk_generic_xmit_cache", + sizeof(struct xsk_addr_node), + 0, SLAB_HWCACHE_ALIGN, NULL); + if (!xsk_tx_generic_cache) { + err = -ENOMEM; + goto out_unreg_notif; + } + return 0; +out_unreg_notif: + unregister_netdevice_notifier(&xsk_netdev_notifier); out_pernet: unregister_pernet_subsys(&xsk_net_ops); out_sk: diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 46d87e961ad6..f16f390370dc 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -344,6 +344,11 @@ static inline u32 xskq_cons_present_entries(struct xsk_queue *q) /* Functions for producers */ +static inline u32 xskq_get_prod(struct xsk_queue *q) +{ + return READ_ONCE(q->ring->producer); +} + static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max) { u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons); @@ -390,6 +395,13 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr) return 0; } +static inline void xskq_prod_write_addr(struct xsk_queue *q, u32 idx, u64 addr) +{ + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + + ring->desc[idx & q->ring_mask] = addr; +} + static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs, u32 nb_entries) { diff --git a/rust/kernel/device.rs b/rust/kernel/device.rs index 5902b3714a16..a1db49eb159a 100644 --- a/rust/kernel/device.rs +++ b/rust/kernel/device.rs @@ -138,7 +138,9 @@ pub mod property; /// } /// ``` /// -/// An example for a class device implementation is [`drm::Device`]. +/// An example for a class device implementation is +#[cfg_attr(CONFIG_DRM = "y", doc = "[`drm::Device`](kernel::drm::Device).")] +#[cfg_attr(not(CONFIG_DRM = "y"), doc = "`drm::Device`.")] /// /// # Invariants /// @@ -151,7 +153,6 @@ pub mod property; /// dropped from any thread. /// /// [`AlwaysRefCounted`]: kernel::types::AlwaysRefCounted -/// [`drm::Device`]: kernel::drm::Device /// [`impl_device_context_deref`]: kernel::impl_device_context_deref /// [`pci::Device`]: kernel::pci::Device /// [`platform::Device`]: kernel::platform::Device diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index ed53169e795c..fef97f2a5098 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -296,7 +296,7 @@ macro_rules! asm { /// Gets the C string file name of a [`Location`]. /// -/// If `file_with_nul()` is not available, returns a string that warns about it. +/// If `Location::file_as_c_str()` is not available, returns a string that warns about it. /// /// [`Location`]: core::panic::Location /// @@ -310,8 +310,8 @@ macro_rules! asm { /// let caller = core::panic::Location::caller(); /// /// // Output: -/// // - A path like "rust/kernel/example.rs" if file_with_nul() is available. -/// // - "<Location::file_with_nul() not supported>" otherwise. +/// // - A path like "rust/kernel/example.rs" if `file_as_c_str()` is available. +/// // - "<Location::file_as_c_str() not supported>" otherwise. /// let caller_file = file_from_location(caller); /// /// // Prints out the message with caller's file name. @@ -326,7 +326,12 @@ macro_rules! asm { /// ``` #[inline] pub fn file_from_location<'a>(loc: &'a core::panic::Location<'a>) -> &'a core::ffi::CStr { - #[cfg(CONFIG_RUSTC_HAS_FILE_WITH_NUL)] + #[cfg(CONFIG_RUSTC_HAS_FILE_AS_C_STR)] + { + loc.file_as_c_str() + } + + #[cfg(all(CONFIG_RUSTC_HAS_FILE_WITH_NUL, not(CONFIG_RUSTC_HAS_FILE_AS_C_STR)))] { loc.file_with_nul() } @@ -334,6 +339,6 @@ pub fn file_from_location<'a>(loc: &'a core::panic::Location<'a>) -> &'a core::f #[cfg(not(CONFIG_RUSTC_HAS_FILE_WITH_NUL))] { let _ = loc; - c"<Location::file_with_nul() not supported>" + c"<Location::file_as_c_str() not supported>" } } diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index cfea7a38befb..da3a9f2091f5 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -75,8 +75,8 @@ asm ( CALL_DEPTH_ACCOUNT " call my_direct_func1\n" " leave\n" -" .size my_tramp1, .-my_tramp1\n" ASM_RET +" .size my_tramp1, .-my_tramp1\n" " .type my_tramp2, @function\n" " .globl my_tramp2\n" diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 39c82908ff3a..38b3416bb979 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -225,7 +225,11 @@ fn main() { ts.push("features", features); ts.push("llvm-target", "x86_64-linux-gnu"); ts.push("supported-sanitizers", ["kcfi", "kernel-address"]); - ts.push("target-pointer-width", "64"); + if cfg.rustc_version_atleast(1, 91, 0) { + ts.push("target-pointer-width", 64); + } else { + ts.push("target-pointer-width", "64"); + } } else if cfg.has("X86_32") { // This only works on UML, as i386 otherwise needs regparm support in rustc if !cfg.has("UML") { @@ -245,7 +249,11 @@ fn main() { } ts.push("features", features); ts.push("llvm-target", "i386-unknown-linux-gnu"); - ts.push("target-pointer-width", "32"); + if cfg.rustc_version_atleast(1, 91, 0) { + ts.push("target-pointer-width", 32); + } else { + ts.push("target-pointer-width", "32"); + } } else if cfg.has("LOONGARCH") { panic!("loongarch uses the builtin rustc loongarch64-unknown-none-softfloat target"); } else { diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile index ed565eb52275..342e056c8c66 100644 --- a/tools/gpio/Makefile +++ b/tools/gpio/Makefile @@ -77,7 +77,7 @@ $(OUTPUT)gpio-watch: $(GPIO_WATCH_IN) clean: rm -f $(ALL_PROGRAMS) - rm -f $(OUTPUT)include/linux/gpio.h + rm -rf $(OUTPUT)include find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete install: $(ALL_PROGRAMS) diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c index 9ef569492560..ddaeb4eb3e24 100644 --- a/tools/lib/subcmd/help.c +++ b/tools/lib/subcmd/help.c @@ -75,6 +75,9 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) size_t ci, cj, ei; int cmp; + if (!excludes->cnt) + return; + ci = cj = ei = 0; while (ci < cmds->cnt && ei < excludes->cnt) { cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name); diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py index ef032e17fec4..eb295756c3bf 100755 --- a/tools/net/ynl/pyynl/ynl_gen_c.py +++ b/tools/net/ynl/pyynl/ynl_gen_c.py @@ -830,7 +830,7 @@ class TypeArrayNest(Type): 'ynl_attr_for_each_nested(attr2, attr) {', '\tif (ynl_attr_validate(yarg, attr2))', '\t\treturn YNL_PARSE_CB_ERROR;', - f'\t{var}->_count.{self.c_name}++;', + f'\tn_{self.c_name}++;', '}'] return get_lines, None, local_vars diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index fd49703021fd..078634461df2 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -2009,6 +2009,7 @@ static int __cmd_contention(int argc, const char **argv) .owner = show_lock_owner, .cgroups = RB_ROOT, }; + struct perf_env host_env; lockhash_table = calloc(LOCKHASH_SIZE, sizeof(*lockhash_table)); if (!lockhash_table) @@ -2024,7 +2025,10 @@ static int __cmd_contention(int argc, const char **argv) eops.mmap = perf_event__process_mmap; eops.tracing_data = perf_event__process_tracing_data; - session = perf_session__new(use_bpf ? NULL : &data, &eops); + perf_env__init(&host_env); + session = __perf_session__new(use_bpf ? NULL : &data, &eops, + /*trace_event_repipe=*/false, &host_env); + if (IS_ERR(session)) { pr_err("Initializing perf session failed\n"); err = PTR_ERR(session); @@ -2142,6 +2146,7 @@ out_delete: evlist__delete(con.evlist); lock_contention_finish(&con); perf_session__delete(session); + perf_env__exit(&host_env); zfree(&lockhash_table); return err; } diff --git a/tools/perf/tests/pe-file-parsing.c b/tools/perf/tests/pe-file-parsing.c index 30c7da79e109..8b31d1d05f90 100644 --- a/tools/perf/tests/pe-file-parsing.c +++ b/tools/perf/tests/pe-file-parsing.c @@ -37,7 +37,7 @@ static int run_dir(const char *d) size_t idx; scnprintf(filename, PATH_MAX, "%s/pe-file.exe", d); - ret = filename__read_build_id(filename, &bid); + ret = filename__read_build_id(filename, &bid, /*block=*/true); TEST_ASSERT_VAL("Failed to read build_id", ret == sizeof(expect_build_id)); TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id, @@ -49,7 +49,7 @@ static int run_dir(const char *d) !strcmp(debuglink, expect_debuglink)); scnprintf(debugfile, PATH_MAX, "%s/%s", d, debuglink); - ret = filename__read_build_id(debugfile, &bid); + ret = filename__read_build_id(debugfile, &bid, /*block=*/true); TEST_ASSERT_VAL("Failed to read debug file build_id", ret == sizeof(expect_build_id)); TEST_ASSERT_VAL("Wrong build_id", !memcmp(bid.data, expect_build_id, diff --git a/tools/perf/tests/shell/test_bpf_metadata.sh b/tools/perf/tests/shell/test_bpf_metadata.sh index 69e3c2055134..be67d56e0f09 100755 --- a/tools/perf/tests/shell/test_bpf_metadata.sh +++ b/tools/perf/tests/shell/test_bpf_metadata.sh @@ -61,7 +61,7 @@ test_bpf_metadata() { /perf_version/ { if (entry) print $NF; } - ' | egrep "$VERS" > /dev/null + ' | grep -qF "$VERS" then echo "Basic BPF metadata test [Failed invalid output]" err=1 diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c index 5b6d3e899e11..2298cd396c42 100644 --- a/tools/perf/util/bpf-event.c +++ b/tools/perf/util/bpf-event.c @@ -657,9 +657,15 @@ static int perf_event__synthesize_one_bpf_prog(struct perf_session *session, info_node->info_linear = info_linear; info_node->metadata = NULL; if (!perf_env__insert_bpf_prog_info(env, info_node)) { - free(info_linear); + /* + * Insert failed, likely because of a duplicate event + * made by the sideband thread. Ignore synthesizing the + * metadata. + */ free(info_node); + goto out; } + /* info_linear is now owned by info_node and shouldn't be freed below. */ info_linear = NULL; /* @@ -827,18 +833,18 @@ int perf_event__synthesize_bpf_events(struct perf_session *session, return err; } -static void perf_env__add_bpf_info(struct perf_env *env, u32 id) +static int perf_env__add_bpf_info(struct perf_env *env, u32 id) { struct bpf_prog_info_node *info_node; struct perf_bpil *info_linear; struct btf *btf = NULL; u64 arrays; u32 btf_id; - int fd; + int fd, err = 0; fd = bpf_prog_get_fd_by_id(id); if (fd < 0) - return; + return -EINVAL; arrays = 1UL << PERF_BPIL_JITED_KSYMS; arrays |= 1UL << PERF_BPIL_JITED_FUNC_LENS; @@ -852,6 +858,7 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id) info_linear = get_bpf_prog_info_linear(fd, arrays); if (IS_ERR_OR_NULL(info_linear)) { pr_debug("%s: failed to get BPF program info. aborting\n", __func__); + err = PTR_ERR(info_linear); goto out; } @@ -862,38 +869,46 @@ static void perf_env__add_bpf_info(struct perf_env *env, u32 id) info_node->info_linear = info_linear; info_node->metadata = bpf_metadata_create(&info_linear->info); if (!perf_env__insert_bpf_prog_info(env, info_node)) { + pr_debug("%s: duplicate add bpf info request for id %u\n", + __func__, btf_id); free(info_linear); free(info_node); + goto out; } - } else + } else { free(info_linear); + err = -ENOMEM; + goto out; + } if (btf_id == 0) goto out; btf = btf__load_from_kernel_by_id(btf_id); - if (libbpf_get_error(btf)) { - pr_debug("%s: failed to get BTF of id %u, aborting\n", - __func__, btf_id); - goto out; + if (!btf) { + err = -errno; + pr_debug("%s: failed to get BTF of id %u %d\n", __func__, btf_id, err); + } else { + perf_env__fetch_btf(env, btf_id, btf); } - perf_env__fetch_btf(env, btf_id, btf); out: btf__free(btf); close(fd); + return err; } static int bpf_event__sb_cb(union perf_event *event, void *data) { struct perf_env *env = data; + int ret = 0; if (event->header.type != PERF_RECORD_BPF_EVENT) return -1; switch (event->bpf.type) { case PERF_BPF_EVENT_PROG_LOAD: - perf_env__add_bpf_info(env, event->bpf.id); + ret = perf_env__add_bpf_info(env, event->bpf.id); case PERF_BPF_EVENT_PROG_UNLOAD: /* @@ -907,7 +922,7 @@ static int bpf_event__sb_cb(union perf_event *event, void *data) break; } - return 0; + return ret; } int evlist__add_bpf_sb_event(struct evlist *evlist, struct perf_env *env) diff --git a/tools/perf/util/bpf-utils.c b/tools/perf/util/bpf-utils.c index 80b1d2b3729b..5a66dc8594aa 100644 --- a/tools/perf/util/bpf-utils.c +++ b/tools/perf/util/bpf-utils.c @@ -20,7 +20,7 @@ struct bpil_array_desc { */ }; -static struct bpil_array_desc bpil_array_desc[] = { +static const struct bpil_array_desc bpil_array_desc[] = { [PERF_BPIL_JITED_INSNS] = { offsetof(struct bpf_prog_info, jited_prog_insns), offsetof(struct bpf_prog_info, jited_prog_len), @@ -115,7 +115,7 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) __u32 info_len = sizeof(info); __u32 data_len = 0; int i, err; - void *ptr; + __u8 *ptr; if (arrays >> PERF_BPIL_LAST_ARRAY) return ERR_PTR(-EINVAL); @@ -126,15 +126,15 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) pr_debug("can't get prog info: %s", strerror(errno)); return ERR_PTR(-EFAULT); } + if (info.type >= __MAX_BPF_PROG_TYPE) + pr_debug("%s:%d: unexpected program type %u\n", __func__, __LINE__, info.type); /* step 2: calculate total size of all arrays */ for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { + const struct bpil_array_desc *desc = &bpil_array_desc[i]; bool include_array = (arrays & (1UL << i)) > 0; - struct bpil_array_desc *desc; __u32 count, size; - desc = bpil_array_desc + i; - /* kernel is too old to support this field */ if (info_len < desc->array_offset + sizeof(__u32) || info_len < desc->count_offset + sizeof(__u32) || @@ -163,19 +163,20 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) ptr = info_linear->data; for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { - struct bpil_array_desc *desc; + const struct bpil_array_desc *desc = &bpil_array_desc[i]; __u32 count, size; if ((arrays & (1UL << i)) == 0) continue; - desc = bpil_array_desc + i; count = bpf_prog_info_read_offset_u32(&info, desc->count_offset); size = bpf_prog_info_read_offset_u32(&info, desc->size_offset); bpf_prog_info_set_offset_u32(&info_linear->info, desc->count_offset, count); bpf_prog_info_set_offset_u32(&info_linear->info, desc->size_offset, size); + assert(ptr >= info_linear->data); + assert(ptr < &info_linear->data[data_len]); bpf_prog_info_set_offset_u64(&info_linear->info, desc->array_offset, ptr_to_u64(ptr)); @@ -189,27 +190,45 @@ get_bpf_prog_info_linear(int fd, __u64 arrays) free(info_linear); return ERR_PTR(-EFAULT); } + if (info_linear->info.type >= __MAX_BPF_PROG_TYPE) { + pr_debug("%s:%d: unexpected program type %u\n", + __func__, __LINE__, info_linear->info.type); + } /* step 6: verify the data */ + ptr = info_linear->data; for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { - struct bpil_array_desc *desc; - __u32 v1, v2; + const struct bpil_array_desc *desc = &bpil_array_desc[i]; + __u32 count1, count2, size1, size2; + __u64 ptr2; if ((arrays & (1UL << i)) == 0) continue; - desc = bpil_array_desc + i; - v1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset); - v2 = bpf_prog_info_read_offset_u32(&info_linear->info, + count1 = bpf_prog_info_read_offset_u32(&info, desc->count_offset); + count2 = bpf_prog_info_read_offset_u32(&info_linear->info, desc->count_offset); - if (v1 != v2) - pr_warning("%s: mismatch in element count\n", __func__); + if (count1 != count2) { + pr_warning("%s: mismatch in element count %u vs %u\n", __func__, count1, count2); + free(info_linear); + return ERR_PTR(-ERANGE); + } - v1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset); - v2 = bpf_prog_info_read_offset_u32(&info_linear->info, + size1 = bpf_prog_info_read_offset_u32(&info, desc->size_offset); + size2 = bpf_prog_info_read_offset_u32(&info_linear->info, desc->size_offset); - if (v1 != v2) - pr_warning("%s: mismatch in rec size\n", __func__); + if (size1 != size2) { + pr_warning("%s: mismatch in rec size %u vs %u\n", __func__, size1, size2); + free(info_linear); + return ERR_PTR(-ERANGE); + } + ptr2 = bpf_prog_info_read_offset_u64(&info_linear->info, desc->array_offset); + if (ptr_to_u64(ptr) != ptr2) { + pr_warning("%s: mismatch in array %p vs %llx\n", __func__, ptr, ptr2); + free(info_linear); + return ERR_PTR(-ERANGE); + } + ptr += roundup(count1 * size1, sizeof(__u64)); } /* step 7: update info_len and data_len */ @@ -224,13 +243,12 @@ void bpil_addr_to_offs(struct perf_bpil *info_linear) int i; for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { - struct bpil_array_desc *desc; + const struct bpil_array_desc *desc = &bpil_array_desc[i]; __u64 addr, offs; if ((info_linear->arrays & (1UL << i)) == 0) continue; - desc = bpil_array_desc + i; addr = bpf_prog_info_read_offset_u64(&info_linear->info, desc->array_offset); offs = addr - ptr_to_u64(info_linear->data); @@ -244,13 +262,12 @@ void bpil_offs_to_addr(struct perf_bpil *info_linear) int i; for (i = PERF_BPIL_FIRST_ARRAY; i < PERF_BPIL_LAST_ARRAY; ++i) { - struct bpil_array_desc *desc; + const struct bpil_array_desc *desc = &bpil_array_desc[i]; __u64 addr, offs; if ((info_linear->arrays & (1UL << i)) == 0) continue; - desc = bpil_array_desc + i; offs = bpf_prog_info_read_offset_u64(&info_linear->info, desc->array_offset); addr = offs + ptr_to_u64(info_linear->data); diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c index 85b2a93a59ac..779f6230130a 100644 --- a/tools/perf/util/maps.c +++ b/tools/perf/util/maps.c @@ -477,6 +477,7 @@ static int __maps__insert(struct maps *maps, struct map *new) } /* Insert the value at the end. */ maps_by_address[nr_maps] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) maps_by_name[nr_maps] = map__get(new); @@ -502,8 +503,6 @@ static int __maps__insert(struct maps *maps, struct map *new) if (map__end(new) < map__start(new)) RC_CHK_ACCESS(maps)->ends_broken = true; - map__set_kmap_maps(new, maps); - return 0; } @@ -891,6 +890,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) if (before) { map__put(maps_by_address[i]); maps_by_address[i] = before; + map__set_kmap_maps(before, maps); if (maps_by_name) { map__put(maps_by_name[ni]); @@ -918,6 +918,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) { map__put(maps_by_name[ni]); @@ -942,14 +943,13 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new) */ map__put(maps_by_address[i]); maps_by_address[i] = map__get(new); + map__set_kmap_maps(new, maps); if (maps_by_name) { map__put(maps_by_name[ni]); maps_by_name[ni] = map__get(new); } - map__set_kmap_maps(new, maps); - check_invariants(maps); return err; } @@ -1019,6 +1019,7 @@ int maps__copy_from(struct maps *dest, struct maps *parent) err = unwind__prepare_access(dest, new, NULL); if (!err) { dest_maps_by_address[i] = new; + map__set_kmap_maps(new, dest); if (dest_maps_by_name) dest_maps_by_name[i] = map__get(new); RC_CHK_ACCESS(dest)->nr_maps = i + 1; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 033c79231a54..1346fd180653 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -873,13 +873,17 @@ out: #ifdef HAVE_LIBBFD_BUILDID_SUPPORT -static int read_build_id(const char *filename, struct build_id *bid) +static int read_build_id(const char *filename, struct build_id *bid, bool block) { size_t size = sizeof(bid->data); - int err = -1; + int err = -1, fd; bfd *abfd; - abfd = bfd_openr(filename, NULL); + fd = open(filename, block ? O_RDONLY : (O_RDONLY | O_NONBLOCK)); + if (fd < 0) + return -1; + + abfd = bfd_fdopenr(filename, /*target=*/NULL, fd); if (!abfd) return -1; diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c index b7b77a6b2979..0de8facca4c5 100644 --- a/tools/testing/selftests/bpf/prog_tests/free_timer.c +++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c @@ -124,6 +124,10 @@ void test_free_timer(void) int err; skel = free_timer__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(skel, "open_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index d66687f1ee6a..56f660ca567b 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -86,6 +86,10 @@ void serial_test_timer(void) int err; timer_skel = timer__open_and_load(); + if (!timer_skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/timer_crash.c b/tools/testing/selftests/bpf/prog_tests/timer_crash.c index f74b82305da8..b841597c8a3a 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_crash.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_crash.c @@ -12,6 +12,10 @@ static void test_timer_crash_mode(int mode) struct timer_crash *skel; skel = timer_crash__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(skel, "timer_crash__open_and_load")) return; skel->bss->pid = getpid(); diff --git a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c index 1a2f99596916..eb303fa1e09a 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_lockup.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_lockup.c @@ -59,6 +59,10 @@ void test_timer_lockup(void) } skel = timer_lockup__open_and_load(); + if (!skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(skel, "timer_lockup__open_and_load")) return; diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c index 9ff7843909e7..c930c7d7105b 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c +++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c @@ -65,6 +65,10 @@ void serial_test_timer_mim(void) goto cleanup; timer_skel = timer_mim__open_and_load(); + if (!timer_skel && errno == EOPNOTSUPP) { + test__skip(); + return; + } if (!ASSERT_OK_PTR(timer_skel, "timer_skel_load")) goto cleanup; diff --git a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h index d67466c1ff77..f90531cf3ee5 100644 --- a/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h +++ b/tools/testing/selftests/bpf/progs/bpf_arena_spin_lock.h @@ -302,7 +302,7 @@ int arena_spin_lock_slowpath(arena_spinlock_t __arena __arg_arena *lock, u32 val * barriers. */ if (val & _Q_LOCKED_MASK) - smp_cond_load_acquire_label(&lock->locked, !VAL, release_err); + (void)smp_cond_load_acquire_label(&lock->locked, !VAL, release_err); /* * take ownership and clear the pending bit. @@ -380,7 +380,7 @@ queue: /* Link @node into the waitqueue. */ WRITE_ONCE(prev->next, node); - arch_mcs_spin_lock_contended_label(&node->locked, release_node_err); + (void)arch_mcs_spin_lock_contended_label(&node->locked, release_node_err); /* * While waiting for the MCS lock, the next pointer may have diff --git a/tools/testing/selftests/bpf/progs/crypto_sanity.c b/tools/testing/selftests/bpf/progs/crypto_sanity.c index 645be6cddf36..dfd8a258f14a 100644 --- a/tools/testing/selftests/bpf/progs/crypto_sanity.c +++ b/tools/testing/selftests/bpf/progs/crypto_sanity.c @@ -14,7 +14,7 @@ unsigned char key[256] = {}; u16 udp_test_port = 7777; u32 authsize, key_len; char algo[128] = {}; -char dst[16] = {}; +char dst[16] = {}, dst_bad[8] = {}; int status; static int skb_dynptr_validate(struct __sk_buff *skb, struct bpf_dynptr *psrc) @@ -59,10 +59,9 @@ int skb_crypto_setup(void *ctx) .authsize = authsize, }; struct bpf_crypto_ctx *cctx; - int err = 0; + int err; status = 0; - if (key_len > 256) { status = -EINVAL; return 0; @@ -70,8 +69,8 @@ int skb_crypto_setup(void *ctx) __builtin_memcpy(¶ms.algo, algo, sizeof(algo)); __builtin_memcpy(¶ms.key, key, sizeof(key)); - cctx = bpf_crypto_ctx_create(¶ms, sizeof(params), &err); + cctx = bpf_crypto_ctx_create(¶ms, sizeof(params), &err); if (!cctx) { status = err; return 0; @@ -80,7 +79,6 @@ int skb_crypto_setup(void *ctx) err = crypto_ctx_insert(cctx); if (err && err != -EEXIST) status = err; - return 0; } @@ -92,6 +90,7 @@ int decrypt_sanity(struct __sk_buff *skb) struct bpf_dynptr psrc, pdst; int err; + status = 0; err = skb_dynptr_validate(skb, &psrc); if (err < 0) { status = err; @@ -110,13 +109,23 @@ int decrypt_sanity(struct __sk_buff *skb) return TC_ACT_SHOT; } - /* dst is a global variable to make testing part easier to check. In real - * production code, a percpu map should be used to store the result. + /* Check also bad case where the dst buffer is smaller than the + * skb's linear section. + */ + bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst); + status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL); + if (!status) + status = -EIO; + if (status != -EINVAL) + goto err; + + /* dst is a global variable to make testing part easier to check. + * In real production code, a percpu map should be used to store + * the result. */ bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst); - status = bpf_crypto_decrypt(ctx, &psrc, &pdst, NULL); - +err: return TC_ACT_SHOT; } @@ -129,7 +138,6 @@ int encrypt_sanity(struct __sk_buff *skb) int err; status = 0; - err = skb_dynptr_validate(skb, &psrc); if (err < 0) { status = err; @@ -148,13 +156,23 @@ int encrypt_sanity(struct __sk_buff *skb) return TC_ACT_SHOT; } - /* dst is a global variable to make testing part easier to check. In real - * production code, a percpu map should be used to store the result. + /* Check also bad case where the dst buffer is smaller than the + * skb's linear section. + */ + bpf_dynptr_from_mem(dst_bad, sizeof(dst_bad), 0, &pdst); + status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL); + if (!status) + status = -EIO; + if (status != -EINVAL) + goto err; + + /* dst is a global variable to make testing part easier to check. + * In real production code, a percpu map should be used to store + * the result. */ bpf_dynptr_from_mem(dst, sizeof(dst), 0, &pdst); - status = bpf_crypto_encrypt(ctx, &psrc, &pdst, NULL); - +err: return TC_ACT_SHOT; } diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c index 6438982b928b..ddd26d1a083f 100644 --- a/tools/testing/selftests/bpf/progs/linked_list_fail.c +++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c @@ -226,8 +226,7 @@ int obj_new_no_composite(void *ctx) SEC("?tc") int obj_new_no_struct(void *ctx) { - - bpf_obj_new(union { int data; unsigned udata; }); + (void)bpf_obj_new(union { int data; unsigned udata; }); return 0; } @@ -252,7 +251,7 @@ int new_null_ret(void *ctx) SEC("?tc") int obj_new_acq(void *ctx) { - bpf_obj_new(struct foo); + (void)bpf_obj_new(struct foo); return 0; } diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c index 46697f381878..a47690174e0e 100644 --- a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c +++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c @@ -30,8 +30,12 @@ __test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); } __test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); } __test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); } __test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); } -__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); } -__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(0) int test_strnstr_found1(void *ctx) { return bpf_strnstr("", "", 0); } +__test(0) int test_strnstr_found2(void *ctx) { return bpf_strnstr(str, "hello", 5); } +__test(0) int test_strnstr_found3(void *ctx) { return bpf_strnstr(str, "hello", 6); } +__test(-ENOENT) int test_strnstr_notfound1(void *ctx) { return bpf_strnstr(str, "hi", 10); } +__test(-ENOENT) int test_strnstr_notfound2(void *ctx) { return bpf_strnstr(str, "hello", 4); } +__test(-ENOENT) int test_strnstr_notfound3(void *ctx) { return bpf_strnstr("", "a", 0); } __test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); } char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py index cd23af875317..3e3a89a34afe 100755 --- a/tools/testing/selftests/drivers/net/hw/csum.py +++ b/tools/testing/selftests/drivers/net/hw/csum.py @@ -17,7 +17,7 @@ def test_receive(cfg, ipver="6", extra_args=None): ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}" rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}" - tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}" + tx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -n 100 {ip_args} -r 1 -T {extra_args}" with bkg(rx_cmd, exit_wait=True): wait_port_listen(34000, proto="udp") @@ -37,7 +37,7 @@ def test_transmit(cfg, ipver="6", extra_args=None): if extra_args != "-U -Z": extra_args += " -r 1" - rx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -L 1 -n 100 {ip_args} -R {extra_args}" + rx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -L 1 -n 100 {ip_args} -R {extra_args}" tx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -L 1 -n 100 {ip_args} -T {extra_args}" with bkg(rx_cmd, host=cfg.remote, exit_wait=True): diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c index 63ce708d93ed..e4b7c2b457ee 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test.c @@ -2,6 +2,13 @@ // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu> #define _GNU_SOURCE + +// Needed for linux/fanotify.h +typedef struct { + int val[2]; +} __kernel_fsid_t; +#define __kernel_fsid_t __kernel_fsid_t + #include <fcntl.h> #include <sched.h> #include <stdio.h> @@ -10,20 +17,12 @@ #include <sys/mount.h> #include <unistd.h> #include <sys/syscall.h> +#include <sys/fanotify.h> #include "../../kselftest_harness.h" #include "../statmount/statmount.h" #include "../utils.h" -// Needed for linux/fanotify.h -#ifndef __kernel_fsid_t -typedef struct { - int val[2]; -} __kernel_fsid_t; -#endif - -#include <sys/fanotify.h> - static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX"; static const int mark_cmds[] = { diff --git a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c index 090a5ca65004..9f57ca46e3af 100644 --- a/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c +++ b/tools/testing/selftests/filesystems/mount-notify/mount-notify_test_ns.c @@ -2,6 +2,13 @@ // Copyright (c) 2025 Miklos Szeredi <miklos@szeredi.hu> #define _GNU_SOURCE + +// Needed for linux/fanotify.h +typedef struct { + int val[2]; +} __kernel_fsid_t; +#define __kernel_fsid_t __kernel_fsid_t + #include <fcntl.h> #include <sched.h> #include <stdio.h> @@ -10,21 +17,12 @@ #include <sys/mount.h> #include <unistd.h> #include <sys/syscall.h> +#include <sys/fanotify.h> #include "../../kselftest_harness.h" -#include "../../pidfd/pidfd.h" #include "../statmount/statmount.h" #include "../utils.h" -// Needed for linux/fanotify.h -#ifndef __kernel_fsid_t -typedef struct { - int val[2]; -} __kernel_fsid_t; -#endif - -#include <sys/fanotify.h> - static const char root_mntpoint_templ[] = "/tmp/mount-notify_test_root.XXXXXX"; static const int mark_types[] = { diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index b31a71f2b372..2b31d4a93ad7 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -99,6 +99,7 @@ TEST_GEN_PROGS += bind_wildcard TEST_GEN_PROGS += bind_timewait TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh +TEST_PROGS += test_vxlan_nh.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh TEST_PROGS += test_neigh.sh @@ -115,6 +116,7 @@ TEST_PROGS += skf_net_off.sh TEST_GEN_FILES += skf_net_off TEST_GEN_FILES += tfo TEST_PROGS += tfo_passive.sh +TEST_PROGS += broadcast_ether_dst.sh TEST_PROGS += broadcast_pmtu.sh TEST_PROGS += ipv6_force_forwarding.sh diff --git a/tools/testing/selftests/net/bind_bhash.c b/tools/testing/selftests/net/bind_bhash.c index 57ff67a3751e..da04b0b19b73 100644 --- a/tools/testing/selftests/net/bind_bhash.c +++ b/tools/testing/selftests/net/bind_bhash.c @@ -75,7 +75,7 @@ static void *setup(void *arg) int *array = (int *)arg; for (i = 0; i < MAX_CONNECTIONS; i++) { - sock_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr); + sock_fd = bind_socket(SO_REUSEPORT, setup_addr); if (sock_fd < 0) { ret = sock_fd; pthread_exit(&ret); @@ -103,7 +103,7 @@ int main(int argc, const char *argv[]) setup_addr = use_v6 ? setup_addr_v6 : setup_addr_v4; - listener_fd = bind_socket(SO_REUSEADDR | SO_REUSEPORT, setup_addr); + listener_fd = bind_socket(SO_REUSEPORT, setup_addr); if (listen(listener_fd, 100) < 0) { perror("listen failed"); return -1; diff --git a/tools/testing/selftests/net/broadcast_ether_dst.sh b/tools/testing/selftests/net/broadcast_ether_dst.sh new file mode 100755 index 000000000000..334a7eca8a80 --- /dev/null +++ b/tools/testing/selftests/net/broadcast_ether_dst.sh @@ -0,0 +1,83 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Author: Brett A C Sheffield <bacs@librecast.net> +# Author: Oscar Maes <oscmaes92@gmail.com> +# +# Ensure destination ethernet field is correctly set for +# broadcast packets + +source lib.sh + +CLIENT_IP4="192.168.0.1" +GW_IP4="192.168.0.2" + +setup() { + setup_ns CLIENT_NS SERVER_NS + + ip -net "${SERVER_NS}" link add link1 type veth \ + peer name link0 netns "${CLIENT_NS}" + + ip -net "${CLIENT_NS}" link set link0 up + ip -net "${CLIENT_NS}" addr add "${CLIENT_IP4}"/24 dev link0 + + ip -net "${SERVER_NS}" link set link1 up + + ip -net "${CLIENT_NS}" route add default via "${GW_IP4}" + ip netns exec "${CLIENT_NS}" arp -s "${GW_IP4}" 00:11:22:33:44:55 +} + +cleanup() { + rm -f "${CAPFILE}" "${OUTPUT}" + ip -net "${SERVER_NS}" link del link1 + cleanup_ns "${CLIENT_NS}" "${SERVER_NS}" +} + +test_broadcast_ether_dst() { + local rc=0 + CAPFILE=$(mktemp -u cap.XXXXXXXXXX) + OUTPUT=$(mktemp -u out.XXXXXXXXXX) + + echo "Testing ethernet broadcast destination" + + # start tcpdump listening for icmp + # tcpdump will exit after receiving a single packet + # timeout will kill tcpdump if it is still running after 2s + timeout 2s ip netns exec "${CLIENT_NS}" \ + tcpdump -i link0 -c 1 -w "${CAPFILE}" icmp &> "${OUTPUT}" & + pid=$! + slowwait 1 grep -qs "listening" "${OUTPUT}" + + # send broadcast ping + ip netns exec "${CLIENT_NS}" \ + ping -W0.01 -c1 -b 255.255.255.255 &> /dev/null + + # wait for tcpdump for exit after receiving packet + wait "${pid}" + + # compare ethernet destination field to ff:ff:ff:ff:ff:ff + ether_dst=$(tcpdump -r "${CAPFILE}" -tnne 2>/dev/null | \ + awk '{sub(/,/,"",$3); print $3}') + if [[ "${ether_dst}" == "ff:ff:ff:ff:ff:ff" ]]; then + echo "[ OK ]" + rc="${ksft_pass}" + else + echo "[FAIL] expected dst ether addr to be ff:ff:ff:ff:ff:ff," \ + "got ${ether_dst}" + rc="${ksft_fail}" + fi + + return "${rc}" +} + +if [ ! -x "$(command -v tcpdump)" ]; then + echo "SKIP: Could not run test without tcpdump tool" + exit "${ksft_skip}" +fi + +trap cleanup EXIT + +setup +test_broadcast_ether_dst + +exit $? diff --git a/tools/testing/selftests/net/can/config b/tools/testing/selftests/net/can/config new file mode 100644 index 000000000000..188f79796670 --- /dev/null +++ b/tools/testing/selftests/net/can/config @@ -0,0 +1,3 @@ +CONFIG_CAN=m +CONFIG_CAN_DEV=m +CONFIG_CAN_VCAN=m diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 7a3cb4c09e45..d847ff1737c3 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -28,7 +28,7 @@ flush_pids() } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { ip netns pids "${ns}" | xargs --no-run-if-empty kill -SIGKILL &>/dev/null diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 5e3c56253274..c2ab9f7f0d21 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -134,7 +134,7 @@ ns4="" TEST_GROUP="" # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { rm -f "$cin_disconnect" diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 82cae37d9c20..7fd555b123b9 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -8,7 +8,7 @@ # ShellCheck incorrectly believes that most of the code here is unreachable # because it's invoked by variable name, see how the "tests" array is used -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 . "$(dirname "${0}")/mptcp_lib.sh" diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index 418a903c3a4d..f01989be6e9b 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -95,7 +95,7 @@ init() } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { mptcp_lib_ns_exit "${ns1}" "${ns2}" "${ns_sbox}" diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index ac7ec6f94023..ec6a87588191 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -32,7 +32,7 @@ ns1="" err=$(mktemp) # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { rm -f "${err}" @@ -70,8 +70,9 @@ format_endpoints() { mptcp_lib_pm_nl_format_endpoints "${@}" } +# This function is invoked indirectly +#shellcheck disable=SC2317,SC2329 get_endpoint() { - # shellcheck disable=SC2317 # invoked indirectly mptcp_lib_pm_nl_get_endpoint "${ns1}" "${@}" } diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 2329c2f8519b..1903e8e84a31 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -35,7 +35,7 @@ usage() { } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { rm -f "$cout" "$sout" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 333064b0b5ac..970c329735ff 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -94,7 +94,7 @@ test_fail() } # This function is used in the cleanup trap -#shellcheck disable=SC2317 +#shellcheck disable=SC2317,SC2329 cleanup() { print_title "Cleanup" diff --git a/tools/testing/selftests/net/netfilter/conntrack_clash.sh b/tools/testing/selftests/net/netfilter/conntrack_clash.sh index 606a43a60f73..7fc6c5dbd551 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_clash.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_clash.sh @@ -99,7 +99,7 @@ run_one_clash_test() local entries local cre - if ! ip netns exec "$ns" ./udpclash $daddr $dport;then + if ! ip netns exec "$ns" timeout 30 ./udpclash $daddr $dport;then echo "INFO: did not receive expected number of replies for $daddr:$dport" ip netns exec "$ctns" conntrack -S # don't fail: check if clash resolution triggered after all. diff --git a/tools/testing/selftests/net/netfilter/conntrack_resize.sh b/tools/testing/selftests/net/netfilter/conntrack_resize.sh index 788cd56ea4a0..615fe3c6f405 100755 --- a/tools/testing/selftests/net/netfilter/conntrack_resize.sh +++ b/tools/testing/selftests/net/netfilter/conntrack_resize.sh @@ -187,7 +187,7 @@ ct_udpclash() [ -x udpclash ] || return while [ $now -lt $end ]; do - ip netns exec "$ns" ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1 + ip netns exec "$ns" timeout 30 ./udpclash 127.0.0.1 $((RANDOM%65536)) > /dev/null 2>&1 now=$(date +%s) done @@ -277,6 +277,7 @@ check_taint() insert_flood() { local n="$1" + local timeout="$2" local r=0 r=$((RANDOM%$insert_count)) @@ -302,7 +303,7 @@ test_floodresize_all() read tainted_then < /proc/sys/kernel/tainted for n in "$nsclient1" "$nsclient2";do - insert_flood "$n" & + insert_flood "$n" "$timeout" & done # resize table constantly while flood/insert/dump/flushs diff --git a/tools/testing/selftests/net/netfilter/nft_flowtable.sh b/tools/testing/selftests/net/netfilter/nft_flowtable.sh index a4ee5496f2a1..45832df98295 100755 --- a/tools/testing/selftests/net/netfilter/nft_flowtable.sh +++ b/tools/testing/selftests/net/netfilter/nft_flowtable.sh @@ -20,6 +20,7 @@ ret=0 SOCAT_TIMEOUT=60 nsin="" +nsin_small="" ns1out="" ns2out="" @@ -36,7 +37,7 @@ cleanup() { cleanup_all_ns - rm -f "$nsin" "$ns1out" "$ns2out" + rm -f "$nsin" "$nsin_small" "$ns1out" "$ns2out" [ "$log_netns" -eq 0 ] && sysctl -q net.netfilter.nf_log_all_netns="$log_netns" } @@ -72,6 +73,7 @@ lmtu=1500 rmtu=2000 filesize=$((2 * 1024 * 1024)) +filesize_small=$((filesize / 16)) usage(){ echo "nft_flowtable.sh [OPTIONS]" @@ -89,7 +91,10 @@ do o) omtu=$OPTARG;; l) lmtu=$OPTARG;; r) rmtu=$OPTARG;; - s) filesize=$OPTARG;; + s) + filesize=$OPTARG + filesize_small=$((OPTARG / 16)) + ;; *) usage;; esac done @@ -215,6 +220,7 @@ if ! ip netns exec "$ns2" ping -c 1 -q 10.0.1.99 > /dev/null; then fi nsin=$(mktemp) +nsin_small=$(mktemp) ns1out=$(mktemp) ns2out=$(mktemp) @@ -265,6 +271,7 @@ check_counters() check_dscp() { local what=$1 + local pmtud="$2" local ok=1 local counter @@ -277,37 +284,39 @@ check_dscp() local pc4z=${counter%*bytes*} local pc4z=${pc4z#*packets} + local failmsg="FAIL: pmtu $pmtu: $what counters do not match, expected" + case "$what" in "dscp_none") if [ "$pc4" -gt 0 ] || [ "$pc4z" -eq 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 == 0, dscp0 > 0, but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; "dscp_fwd") if [ "$pc4" -eq 0 ] || [ "$pc4z" -eq 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 and dscp0 > 0 but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; "dscp_ingress") if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; "dscp_egress") if [ "$pc4" -eq 0 ] || [ "$pc4z" -gt 0 ]; then - echo "FAIL: dscp counters do not match, expected dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 + echo "$failmsg dscp3 > 0, dscp0 == 0 but got $pc4,$pc4z" 1>&2 ret=1 ok=0 fi ;; *) - echo "FAIL: Unknown DSCP check" 1>&2 + echo "$failmsg: Unknown DSCP check" 1>&2 ret=1 ok=0 esac @@ -319,9 +328,9 @@ check_dscp() check_transfer() { - in=$1 - out=$2 - what=$3 + local in=$1 + local out=$2 + local what=$3 if ! cmp "$in" "$out" > /dev/null 2>&1; then echo "FAIL: file mismatch for $what" 1>&2 @@ -342,25 +351,39 @@ test_tcp_forwarding_ip() { local nsa=$1 local nsb=$2 - local dstip=$3 - local dstport=$4 + local pmtu=$3 + local dstip=$4 + local dstport=$5 local lret=0 + local socatc + local socatl + local infile="$nsin" + + if [ $pmtu -eq 0 ]; then + infile="$nsin_small" + fi - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$nsin" > "$ns2out" & + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsb" socat -4 TCP-LISTEN:12345,reuseaddr STDIO < "$infile" > "$ns2out" & lpid=$! busywait 1000 listener_ready - timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$nsin" > "$ns1out" + timeout "$SOCAT_TIMEOUT" ip netns exec "$nsa" socat -4 TCP:"$dstip":"$dstport" STDIO < "$infile" > "$ns1out" + socatc=$? wait $lpid + socatl=$? - if ! check_transfer "$nsin" "$ns2out" "ns1 -> ns2"; then + if [ $socatl -ne 0 ] || [ $socatc -ne 0 ];then + rc=1 + fi + + if ! check_transfer "$infile" "$ns2out" "ns1 -> ns2"; then lret=1 ret=1 fi - if ! check_transfer "$nsin" "$ns1out" "ns1 <- ns2"; then + if ! check_transfer "$infile" "$ns1out" "ns1 <- ns2"; then lret=1 ret=1 fi @@ -370,14 +393,16 @@ test_tcp_forwarding_ip() test_tcp_forwarding() { - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 + local pmtu="$3" + + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 return $? } test_tcp_forwarding_set_dscp() { - check_dscp "dscp_none" + local pmtu="$3" ip netns exec "$nsr1" nft -f - <<EOF table netdev dscpmangle { @@ -388,8 +413,8 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - check_dscp "dscp_ingress" + test_tcp_forwarding_ip "$1" "$2" "$3" 10.0.2.99 12345 + check_dscp "dscp_ingress" "$pmtu" ip netns exec "$nsr1" nft delete table netdev dscpmangle else @@ -405,10 +430,10 @@ table netdev dscpmangle { } EOF if [ $? -eq 0 ]; then - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - check_dscp "dscp_egress" + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + check_dscp "dscp_egress" "$pmtu" - ip netns exec "$nsr1" nft flush table netdev dscpmangle + ip netns exec "$nsr1" nft delete table netdev dscpmangle else echo "SKIP: Could not load netdev:egress for veth1" fi @@ -416,48 +441,53 @@ fi # partial. If flowtable really works, then both dscp-is-0 and dscp-is-cs3 # counters should have seen packets (before and after ft offload kicks in). ip netns exec "$nsr1" nft -a insert rule inet filter forward ip dscp set cs3 - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - check_dscp "dscp_fwd" + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.0.2.99 12345 + check_dscp "dscp_fwd" "$pmtu" } test_tcp_forwarding_nat() { + local nsa="$1" + local nsb="$2" + local pmtu="$3" + local what="$4" local lret - local pmtu - test_tcp_forwarding_ip "$1" "$2" 10.0.2.99 12345 - lret=$? + [ "$pmtu" -eq 0 ] && what="$what (pmtu disabled)" - pmtu=$3 - what=$4 + test_tcp_forwarding_ip "$nsa" "$nsb" "$pmtu" 10.0.2.99 12345 + lret=$? if [ "$lret" -eq 0 ] ; then if [ "$pmtu" -eq 1 ] ;then - check_counters "flow offload for ns1/ns2 with masquerade and pmtu discovery $what" + check_counters "flow offload for ns1/ns2 with masquerade $what" else echo "PASS: flow offload for ns1/ns2 with masquerade $what" fi - test_tcp_forwarding_ip "$1" "$2" 10.6.6.6 1666 + test_tcp_forwarding_ip "$1" "$2" "$pmtu" 10.6.6.6 1666 lret=$? if [ "$pmtu" -eq 1 ] ;then - check_counters "flow offload for ns1/ns2 with dnat and pmtu discovery $what" + check_counters "flow offload for ns1/ns2 with dnat $what" elif [ "$lret" -eq 0 ] ; then echo "PASS: flow offload for ns1/ns2 with dnat $what" fi + else + echo "FAIL: flow offload for ns1/ns2 with dnat $what" fi return $lret } make_file "$nsin" "$filesize" +make_file "$nsin_small" "$filesize_small" # First test: # No PMTU discovery, nsr1 is expected to fragment packets from ns1 to ns2 as needed. # Due to MTU mismatch in both directions, all packets (except small packets like pure # acks) have to be handled by normal forwarding path. Therefore, packet counters # are not checked. -if test_tcp_forwarding "$ns1" "$ns2"; then +if test_tcp_forwarding "$ns1" "$ns2" 0; then echo "PASS: flow offloaded for ns1/ns2" else echo "FAIL: flow offload for ns1/ns2:" 1>&2 @@ -489,8 +519,9 @@ table ip nat { } EOF +check_dscp "dscp_none" "0" if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 0 ""; then - echo "FAIL: flow offload for ns1/ns2 with dscp update" 1>&2 + echo "FAIL: flow offload for ns1/ns2 with dscp update and no pmtu discovery" 1>&2 exit 0 fi @@ -513,6 +544,14 @@ ip netns exec "$ns2" sysctl net.ipv4.ip_no_pmtu_disc=0 > /dev/null # For earlier tests (large mtus), packets cannot be handled via flowtable # (except pure acks and other small packets). ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null +ip netns exec "$ns2" nft reset counters table inet filter >/dev/null + +if ! test_tcp_forwarding_set_dscp "$ns1" "$ns2" 1 ""; then + echo "FAIL: flow offload for ns1/ns2 with dscp update and pmtu discovery" 1>&2 + exit 0 +fi + +ip netns exec "$nsr1" nft reset counters table inet filter >/dev/null if ! test_tcp_forwarding_nat "$ns1" "$ns2" 1 ""; then echo "FAIL: flow offload for ns1/ns2 with NAT and pmtu discovery" 1>&2 @@ -644,7 +683,7 @@ ip -net "$ns2" route del 192.168.10.1 via 10.0.2.1 ip -net "$ns2" route add default via 10.0.2.1 ip -net "$ns2" route add default via dead:2::1 -if test_tcp_forwarding "$ns1" "$ns2"; then +if test_tcp_forwarding "$ns1" "$ns2" 1; then check_counters "ipsec tunnel mode for ns1/ns2" else echo "FAIL: ipsec tunnel mode for ns1/ns2" @@ -668,7 +707,7 @@ if [ "$1" = "" ]; then fi echo "re-run with random mtus and file size: -o $o -l $l -r $r -s $filesize" - $0 -o "$o" -l "$l" -r "$r" -s "$filesize" + $0 -o "$o" -l "$l" -r "$r" -s "$filesize" || ret=1 fi exit $ret diff --git a/tools/testing/selftests/net/netfilter/udpclash.c b/tools/testing/selftests/net/netfilter/udpclash.c index 85c7b906ad08..79de163d61ab 100644 --- a/tools/testing/selftests/net/netfilter/udpclash.c +++ b/tools/testing/selftests/net/netfilter/udpclash.c @@ -29,7 +29,7 @@ struct thread_args { int sockfd; }; -static int wait = 1; +static volatile int wait = 1; static void *thread_main(void *varg) { diff --git a/tools/testing/selftests/net/test_vxlan_nh.sh b/tools/testing/selftests/net/test_vxlan_nh.sh new file mode 100755 index 000000000000..20f3369f776b --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_nh.sh @@ -0,0 +1,223 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh +TESTS=" + basic_tx_ipv4 + basic_tx_ipv6 + learning + proxy_ipv4 + proxy_ipv6 +" +VERBOSE=0 + +################################################################################ +# Utilities + +run_cmd() +{ + local cmd="$1" + local out + local stderr="2>/dev/null" + + if [ "$VERBOSE" = "1" ]; then + echo "COMMAND: $cmd" + stderr= + fi + + out=$(eval "$cmd" "$stderr") + rc=$? + if [ "$VERBOSE" -eq 1 ] && [ -n "$out" ]; then + echo " $out" + fi + + return $rc +} + +################################################################################ +# Cleanup + +exit_cleanup_all() +{ + cleanup_all_ns + exit "${EXIT_STATUS}" +} + +################################################################################ +# Tests + +nh_stats_get() +{ + ip -n "$ns1" -s -j nexthop show id 10 | jq ".[][\"group_stats\"][][\"packets\"]" +} + +tc_stats_get() +{ + tc_rule_handle_stats_get "dev dummy1 egress" 101 ".packets" "-n $ns1" +} + +basic_tx_common() +{ + local af_str=$1; shift + local proto=$1; shift + local local_addr=$1; shift + local plen=$1; shift + local remote_addr=$1; shift + + RET=0 + + # Test basic Tx functionality. Check that stats are incremented on + # both the FDB nexthop group and the egress device. + + run_cmd "ip -n $ns1 link add name dummy1 up type dummy" + run_cmd "ip -n $ns1 route add $remote_addr/$plen dev dummy1" + run_cmd "tc -n $ns1 qdisc add dev dummy1 clsact" + run_cmd "tc -n $ns1 filter add dev dummy1 egress proto $proto pref 1 handle 101 flower ip_proto udp dst_ip $remote_addr dst_port 4789 action pass" + + run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo" + + run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb" + run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb" + + run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789" + run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10" + + run_cmd "ip netns exec $ns1 mausezahn vx0 -a own -b 00:11:22:33:44:55 -c 1 -q" + + busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" nh_stats_get > /dev/null + check_err $? "FDB nexthop group stats did not increase" + + busywait "$BUSYWAIT_TIMEOUT" until_counter_is "== 1" tc_stats_get > /dev/null + check_err $? "tc filter stats did not increase" + + log_test "VXLAN FDB nexthop: $af_str basic Tx" +} + +basic_tx_ipv4() +{ + basic_tx_common "IPv4" ipv4 192.0.2.1 32 192.0.2.2 +} + +basic_tx_ipv6() +{ + basic_tx_common "IPv6" ipv6 2001:db8:1::1 128 2001:db8:1::2 +} + +learning() +{ + RET=0 + + # When learning is enabled on the VXLAN device, an incoming packet + # might try to refresh an FDB entry that points to an FDB nexthop group + # instead of an ordinary remote destination. Check that the kernel does + # not crash in this situation. + + run_cmd "ip -n $ns1 address add 192.0.2.1/32 dev lo" + run_cmd "ip -n $ns1 address add 192.0.2.2/32 dev lo" + + run_cmd "ip -n $ns1 nexthop add id 1 via 192.0.2.3 fdb" + run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb" + + run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local 192.0.2.1 dstport 12345 localbypass" + run_cmd "ip -n $ns1 link add name vx1 up type vxlan id 10020 local 192.0.2.2 dstport 54321 learning" + + run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static dst 192.0.2.2 port 54321 vni 10020" + run_cmd "bridge -n $ns1 fdb add 00:aa:bb:cc:dd:ee dev vx1 self static nhid 10" + + run_cmd "ip netns exec $ns1 mausezahn vx0 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 1 -q" + + log_test "VXLAN FDB nexthop: learning" +} + +proxy_common() +{ + local af_str=$1; shift + local local_addr=$1; shift + local plen=$1; shift + local remote_addr=$1; shift + local neigh_addr=$1; shift + local ping_cmd=$1; shift + + RET=0 + + # When the "proxy" option is enabled on the VXLAN device, the device + # will suppress ARP requests and IPv6 Neighbor Solicitation messages if + # it is able to reply on behalf of the remote host. That is, if a + # matching and valid neighbor entry is configured on the VXLAN device + # whose MAC address is not behind the "any" remote (0.0.0.0 / ::). The + # FDB entry for the neighbor's MAC address might point to an FDB + # nexthop group instead of an ordinary remote destination. Check that + # the kernel does not crash in this situation. + + run_cmd "ip -n $ns1 address add $local_addr/$plen dev lo" + + run_cmd "ip -n $ns1 nexthop add id 1 via $remote_addr fdb" + run_cmd "ip -n $ns1 nexthop add id 10 group 1 fdb" + + run_cmd "ip -n $ns1 link add name vx0 up type vxlan id 10010 local $local_addr dstport 4789 proxy" + + run_cmd "ip -n $ns1 neigh add $neigh_addr lladdr 00:11:22:33:44:55 nud perm dev vx0" + + run_cmd "bridge -n $ns1 fdb add 00:11:22:33:44:55 dev vx0 self static nhid 10" + + run_cmd "ip netns exec $ns1 $ping_cmd" + + log_test "VXLAN FDB nexthop: $af_str proxy" +} + +proxy_ipv4() +{ + proxy_common "IPv4" 192.0.2.1 32 192.0.2.2 192.0.2.3 \ + "arping -b -c 1 -s 192.0.2.1 -I vx0 192.0.2.3" +} + +proxy_ipv6() +{ + proxy_common "IPv6" 2001:db8:1::1 128 2001:db8:1::2 2001:db8:1::3 \ + "ndisc6 -r 1 -s 2001:db8:1::1 -w 1 2001:db8:1::3 vx0" +} + +################################################################################ +# Usage + +usage() +{ + cat <<EOF +usage: ${0##*/} OPTS + + -t <test> Test(s) to run (default: all) + (options: $TESTS) + -p Pause on fail + -v Verbose mode (show commands and output) +EOF +} + +################################################################################ +# Main + +while getopts ":t:pvh" opt; do + case $opt in + t) TESTS=$OPTARG;; + p) PAUSE_ON_FAIL=yes;; + v) VERBOSE=$((VERBOSE + 1));; + h) usage; exit 0;; + *) usage; exit 1;; + esac +done + +require_command mausezahn +require_command arping +require_command ndisc6 +require_command jq + +if ! ip nexthop help 2>&1 | grep -q "stats"; then + echo "SKIP: iproute2 ip too old, missing nexthop stats support" + exit "$ksft_skip" +fi + +trap exit_cleanup_all EXIT + +for t in $TESTS +do + setup_ns ns1; $t; cleanup_all_ns; +done |